},
};
-const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
[BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1,
[BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP,
{
struct btrfs_fs_devices *fs_devs;
- fs_devs = kzalloc(sizeof(*fs_devs), GFP_NOFS);
+ fs_devs = kzalloc(sizeof(*fs_devs), GFP_KERNEL);
if (!fs_devs)
return ERR_PTR(-ENOMEM);
{
struct btrfs_device *dev;
- dev = kzalloc(sizeof(*dev), GFP_NOFS);
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev)
return ERR_PTR(-ENOMEM);
spin_lock_init(&dev->reada_lock);
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
+ btrfs_device_data_ordered_init(dev);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
* uuid mutex so nothing we touch in here is going to disappear.
*/
if (orig_dev->name) {
- name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
+ name = rcu_string_strdup(orig_dev->name->str,
+ GFP_KERNEL);
if (!name) {
kfree(device);
goto error;
}
/* make sure our super fits in the device */
- if (bytenr + PAGE_CACHE_SIZE >= i_size_read(bdev->bd_inode))
+ if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
goto error_bdev_put;
/* make sure our super fits in the page */
- if (sizeof(*disk_super) > PAGE_CACHE_SIZE)
+ if (sizeof(*disk_super) > PAGE_SIZE)
goto error_bdev_put;
/* make sure our super doesn't straddle pages on disk */
- index = bytenr >> PAGE_CACHE_SHIFT;
- if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_CACHE_SHIFT != index)
+ index = bytenr >> PAGE_SHIFT;
+ if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_SHIFT != index)
goto error_bdev_put;
/* pull in the page with our super */
p = kmap(page);
/* align our pointer to the offset of the super block */
- disk_super = p + (bytenr & ~PAGE_CACHE_MASK);
+ disk_super = p + (bytenr & ~PAGE_MASK);
if (btrfs_super_bytenr(disk_super) != bytenr ||
btrfs_super_magic(disk_super) != BTRFS_MAGIC)
error_unmap:
kunmap(page);
- page_cache_release(page);
+ put_page(page);
error_bdev_put:
blkdev_put(bdev, flags);
struct map_lookup *map;
int i;
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
u64 end;
} while (read_seqretry(&root->fs_info->profiles_lock, seq));
num_devices = root->fs_info->fs_devices->num_devices;
- btrfs_dev_replace_lock(&root->fs_info->dev_replace);
+ btrfs_dev_replace_lock(&root->fs_info->dev_replace, 0);
if (btrfs_dev_replace_is_ongoing(&root->fs_info->dev_replace)) {
WARN_ON(num_devices < 1);
num_devices--;
}
- btrfs_dev_replace_unlock(&root->fs_info->dev_replace);
+ btrfs_dev_replace_unlock(&root->fs_info->dev_replace, 0);
if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && num_devices <= 4) {
ret = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET;
}
/*
- * strore the expected generation for seed devices in device items.
+ * Store the expected generation for seed devices in device items.
*/
static int btrfs_finish_sprout(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
goto error;
}
- name = rcu_string_strdup(device_path, GFP_NOFS);
+ name = rcu_string_strdup(device_path, GFP_KERNEL);
if (!name) {
kfree(device);
ret = -ENOMEM;
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
+ * user having built with ASSERT enabled, so if ASSERT doesn't
* do anything we still error out.
*/
ASSERT(0);
free_extent_map(em);
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
lock_chunks(root->fs_info->chunk_root);
check_system_chunk(trans, extent_root, map->type);
unlock_chunks(root->fs_info->chunk_root);
}
key.objectid = BTRFS_BALANCE_OBJECTID;
- key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.type = BTRFS_TEMPORARY_ITEM_KEY;
key.offset = 0;
ret = btrfs_insert_empty_item(trans, root, path, &key,
}
key.objectid = BTRFS_BALANCE_OBJECTID;
- key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.type = BTRFS_TEMPORARY_ITEM_KEY;
key.offset = 0;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
} else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) {
/*
* Same logic as the 'limit' filter; the minimum cannot be
- * determined here because we do not have the global informatoin
+ * determined here because we do not have the global information
* about the count of all chunks that satisfy the filters.
*/
if (bargs->limit_max == 0)
}
num_devices = fs_info->fs_devices->num_devices;
- btrfs_dev_replace_lock(&fs_info->dev_replace);
+ btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
BUG_ON(num_devices < 1);
num_devices--;
}
- btrfs_dev_replace_unlock(&fs_info->dev_replace);
+ btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
if (num_devices == 1)
allowed |= BTRFS_BLOCK_GROUP_DUP;
if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) <
btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) {
btrfs_warn(fs_info,
- "metatdata profile 0x%llx has lower redundancy than data profile 0x%llx",
+ "metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
bctl->meta.target, bctl->data.target);
}
return -ENOMEM;
key.objectid = BTRFS_BALANCE_OBJECTID;
- key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.type = BTRFS_TEMPORARY_ITEM_KEY;
key.offset = 0;
ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
* Callback for btrfs_uuid_tree_iterate().
* returns:
* 0 check succeeded, the entry is not outdated.
- * < 0 if an error occured.
+ * < 0 if an error occurred.
* > 0 if the check failed, which means the caller shall remove the entry.
*/
static int btrfs_check_uuid_tree_entry(struct btrfs_fs_info *fs_info,
goto error;
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
- em->bdev = (struct block_device *)map;
+ em->map_lookup = map;
em->start = start;
em->len = num_bytes;
em->block_start = 0;
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
item_size = btrfs_chunk_item_size(map->num_stripes);
stripe_size = em->orig_block_len;
if (!em)
return 1;
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
if (map->stripes[i].dev->missing) {
miss_ndevs++;
return 1;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
ret = map->num_stripes;
else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
ret = 1;
free_extent_map(em);
- btrfs_dev_replace_lock(&fs_info->dev_replace);
+ btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace))
ret++;
- btrfs_dev_replace_unlock(&fs_info->dev_replace);
+ btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
return ret;
}
BUG_ON(!em);
BUG_ON(em->start > logical || em->start + em->len < logical);
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
len = map->stripe_len * nr_data_stripes(map);
free_extent_map(em);
BUG_ON(!em);
BUG_ON(em->start > logical || em->start + em->len < logical);
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
ret = 1;
free_extent_map(em);
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
offset = logical - em->start;
stripe_len = map->stripe_len;
if (!bbio_ret)
goto out;
- btrfs_dev_replace_lock(dev_replace);
+ btrfs_dev_replace_lock(dev_replace, 0);
dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
if (!dev_replace_is_ongoing)
- btrfs_dev_replace_unlock(dev_replace);
+ btrfs_dev_replace_unlock(dev_replace, 0);
+ else
+ btrfs_dev_replace_set_lock_blocking(dev_replace);
if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
!(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)) &&
* target drive.
*/
for (i = 0; i < tmp_num_stripes; i++) {
- if (tmp_bbio->stripes[i].dev->devid == srcdev_devid) {
- /*
- * In case of DUP, in order to keep it
- * simple, only add the mirror with the
- * lowest physical address
- */
- if (found &&
- physical_of_found <=
- tmp_bbio->stripes[i].physical)
- continue;
- index_srcdev = i;
- found = 1;
- physical_of_found =
- tmp_bbio->stripes[i].physical;
- }
+ if (tmp_bbio->stripes[i].dev->devid != srcdev_devid)
+ continue;
+
+ /*
+ * In case of DUP, in order to keep it simple, only add
+ * the mirror with the lowest physical address
+ */
+ if (found &&
+ physical_of_found <= tmp_bbio->stripes[i].physical)
+ continue;
+
+ index_srcdev = i;
+ found = 1;
+ physical_of_found = tmp_bbio->stripes[i].physical;
}
- if (found) {
- mirror_num = index_srcdev + 1;
- patch_the_first_stripe_for_dev_replace = 1;
- physical_to_patch_in_first_stripe = physical_of_found;
- } else {
+ btrfs_put_bbio(tmp_bbio);
+
+ if (!found) {
WARN_ON(1);
ret = -EIO;
- btrfs_put_bbio(tmp_bbio);
goto out;
}
- btrfs_put_bbio(tmp_bbio);
+ mirror_num = index_srcdev + 1;
+ patch_the_first_stripe_for_dev_replace = 1;
+ physical_to_patch_in_first_stripe = physical_of_found;
} else if (mirror_num > map->num_stripes) {
mirror_num = 0;
}
bbio->mirror_num = map->num_stripes + 1;
}
out:
- if (dev_replace_is_ongoing)
- btrfs_dev_replace_unlock(dev_replace);
+ if (dev_replace_is_ongoing) {
+ btrfs_dev_replace_clear_lock_blocking(dev_replace);
+ btrfs_dev_replace_unlock(dev_replace, 0);
+ }
free_extent_map(em);
return ret;
}
free_extent_map(em);
return -EIO;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
length = em->len;
rmap_len = map->stripe_len;
{
atomic_inc(&bbio->error);
if (atomic_dec_and_test(&bbio->stripes_pending)) {
- /* Shoud be the original bio. */
+ /* Should be the original bio. */
WARN_ON(bio != bbio->orig_bio);
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
bbio->fs_info = root->fs_info;
atomic_set(&bbio->stripes_pending, bbio->num_stripes);
- if (bbio->raid_map) {
+ if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
+ ((rw & WRITE) || (mirror_num > 1))) {
/* In this case, map_length has been set to the length of
a single stripe; not the whole write */
if (rw & WRITE) {
struct extent_map *em;
u64 logical;
u64 length;
+ u64 stripe_len;
u64 devid;
u8 uuid[BTRFS_UUID_SIZE];
int num_stripes;
logical = key->offset;
length = btrfs_chunk_length(leaf, chunk);
+ stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+ num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+ /* Validation check */
+ if (!num_stripes) {
+ btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
+ num_stripes);
+ return -EIO;
+ }
+ if (!IS_ALIGNED(logical, root->sectorsize)) {
+ btrfs_err(root->fs_info,
+ "invalid chunk logical %llu", logical);
+ return -EIO;
+ }
+ if (!length || !IS_ALIGNED(length, root->sectorsize)) {
+ btrfs_err(root->fs_info,
+ "invalid chunk length %llu", length);
+ return -EIO;
+ }
+ if (!is_power_of_2(stripe_len)) {
+ btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
+ stripe_len);
+ return -EIO;
+ }
+ if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+ btrfs_chunk_type(leaf, chunk)) {
+ btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
+ ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
+ BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+ btrfs_chunk_type(leaf, chunk));
+ return -EIO;
+ }
read_lock(&map_tree->map_tree.lock);
em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
em = alloc_extent_map();
if (!em)
return -ENOMEM;
- num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
if (!map) {
free_extent_map(em);
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
- em->bdev = (struct block_device *)map;
+ em->map_lookup = map;
em->start = logical;
em->len = length;
em->orig_start = 0;
set_extent_buffer_uptodate(sb);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
/*
- * The sb extent buffer is artifical and just used to read the system array.
+ * The sb extent buffer is artificial and just used to read the system array.
* set_extent_buffer_uptodate() call does not properly mark all it's
* pages up-to-date when the page is larger: extent does not cover the
* whole page and consequently check_page_uptodate does not find all
* but sb spans only this function. Add an explicit SetPageUptodate call
* to silence the warning eg. on PowerPC 64.
*/
- if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE)
+ if (PAGE_SIZE > BTRFS_SUPER_INFO_SIZE)
SetPageUptodate(sb->pages[0]);
write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
int item_size;
struct btrfs_dev_stats_item *ptr;
- key.objectid = 0;
- key.type = BTRFS_DEV_STATS_KEY;
+ key.objectid = BTRFS_DEV_STATS_OBJECTID;
+ key.type = BTRFS_PERSISTENT_ITEM_KEY;
key.offset = device->devid;
ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
if (ret) {
int ret;
int i;
- key.objectid = 0;
- key.type = BTRFS_DEV_STATS_KEY;
+ key.objectid = BTRFS_DEV_STATS_OBJECTID;
+ key.type = BTRFS_PERSISTENT_ITEM_KEY;
key.offset = device->devid;
path = btrfs_alloc_path();
/* 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;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
dev = map->stripes[i].dev;