OpenCloudOS-Kernel/fs/btrfs/block-group.c

// SPDX-License-Identifier: GPL-2.0

#include "ctree.h"
#include "block-group.h"
#include "space-info.h"
#include "disk-io.h"
#include "free-space-cache.h"
#include "free-space-tree.h"
#include "disk-io.h"
#include "volumes.h"
#include "transaction.h"
#include "ref-verify.h"
#include "sysfs.h"
#include "tree-log.h"
#include "delalloc-space.h"

void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
{
	atomic_inc(&cache->count);
}

void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
{
	if (atomic_dec_and_test(&cache->count)) {
		WARN_ON(cache->pinned > 0);
		WARN_ON(cache->reserved > 0);

		/*
		 * If not empty, someone is still holding mutex of
		 * full_stripe_lock, which can only be released by caller.
		 * And it will definitely cause use-after-free when caller
		 * tries to release full stripe lock.
		 *
		 * No better way to resolve, but only to warn.
		 */
		WARN_ON(!RB_EMPTY_ROOT(&cache->full_stripe_locks_root.root));
		kfree(cache->free_space_ctl);
		kfree(cache);
	}
}

/*
 * This adds the block group to the fs_info rb tree for the block group cache
 */
static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
				struct btrfs_block_group_cache *block_group)
{
	struct rb_node **p;
	struct rb_node *parent = NULL;
	struct btrfs_block_group_cache *cache;

	spin_lock(&info->block_group_cache_lock);
	p = &info->block_group_cache_tree.rb_node;

	while (*p) {
		parent = *p;
		cache = rb_entry(parent, struct btrfs_block_group_cache,
				 cache_node);
		if (block_group->key.objectid < cache->key.objectid) {
			p = &(*p)->rb_left;
		} else if (block_group->key.objectid > cache->key.objectid) {
			p = &(*p)->rb_right;
		} else {
			spin_unlock(&info->block_group_cache_lock);
			return -EEXIST;
		}
	}

	rb_link_node(&block_group->cache_node, parent, p);
	rb_insert_color(&block_group->cache_node,
			&info->block_group_cache_tree);

	if (info->first_logical_byte > block_group->key.objectid)
		info->first_logical_byte = block_group->key.objectid;

	spin_unlock(&info->block_group_cache_lock);

	return 0;
}

/*
 * This will return the block group at or after bytenr if contains is 0, else
 * it will return the block group that contains the bytenr
 */
static struct btrfs_block_group_cache *block_group_cache_tree_search(
		struct btrfs_fs_info *info, u64 bytenr, int contains)
{
	struct btrfs_block_group_cache *cache, *ret = NULL;
	struct rb_node *n;
	u64 end, start;

	spin_lock(&info->block_group_cache_lock);
	n = info->block_group_cache_tree.rb_node;

	while (n) {
		cache = rb_entry(n, struct btrfs_block_group_cache,
				 cache_node);
		end = cache->key.objectid + cache->key.offset - 1;
		start = cache->key.objectid;

		if (bytenr < start) {
			if (!contains && (!ret || start < ret->key.objectid))
				ret = cache;
			n = n->rb_left;
		} else if (bytenr > start) {
			if (contains && bytenr <= end) {
				ret = cache;
				break;
			}
			n = n->rb_right;
		} else {
			ret = cache;
			break;
		}
	}
	if (ret) {
		btrfs_get_block_group(ret);
		if (bytenr == 0 && info->first_logical_byte > ret->key.objectid)
			info->first_logical_byte = ret->key.objectid;
	}
	spin_unlock(&info->block_group_cache_lock);

	return ret;
}

/*
 * Return the block group that starts at or after bytenr
 */
struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
		struct btrfs_fs_info *info, u64 bytenr)
{
	return block_group_cache_tree_search(info, bytenr, 0);
}

/*
 * Return the block group that contains the given bytenr
 */
struct btrfs_block_group_cache *btrfs_lookup_block_group(
		struct btrfs_fs_info *info, u64 bytenr)
{
	return block_group_cache_tree_search(info, bytenr, 1);
}

struct btrfs_block_group_cache *btrfs_next_block_group(
		struct btrfs_block_group_cache *cache)
{
	struct btrfs_fs_info *fs_info = cache->fs_info;
	struct rb_node *node;

	spin_lock(&fs_info->block_group_cache_lock);

	/* If our block group was removed, we need a full search. */
	if (RB_EMPTY_NODE(&cache->cache_node)) {
		const u64 next_bytenr = cache->key.objectid + cache->key.offset;

		spin_unlock(&fs_info->block_group_cache_lock);
		btrfs_put_block_group(cache);
		cache = btrfs_lookup_first_block_group(fs_info, next_bytenr); return cache;
	}
	node = rb_next(&cache->cache_node);
	btrfs_put_block_group(cache);
	if (node) {
		cache = rb_entry(node, struct btrfs_block_group_cache,
				 cache_node);
		btrfs_get_block_group(cache);
	} else
		cache = NULL;
	spin_unlock(&fs_info->block_group_cache_lock);
	return cache;
}

bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_block_group_cache *bg;
	bool ret = true;

	bg = btrfs_lookup_block_group(fs_info, bytenr);
	if (!bg)
		return false;

	spin_lock(&bg->lock);
	if (bg->ro)
		ret = false;
	else
		atomic_inc(&bg->nocow_writers);
	spin_unlock(&bg->lock);

	/* No put on block group, done by btrfs_dec_nocow_writers */
	if (!ret)
		btrfs_put_block_group(bg);

	return ret;
}

void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_block_group_cache *bg;

	bg = btrfs_lookup_block_group(fs_info, bytenr);
	ASSERT(bg);
	if (atomic_dec_and_test(&bg->nocow_writers))
		wake_up_var(&bg->nocow_writers);
	/*
	 * Once for our lookup and once for the lookup done by a previous call
	 * to btrfs_inc_nocow_writers()
	 */
	btrfs_put_block_group(bg);
	btrfs_put_block_group(bg);
}

void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
{
	wait_var_event(&bg->nocow_writers, !atomic_read(&bg->nocow_writers));
}

void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
					const u64 start)
{
	struct btrfs_block_group_cache *bg;

	bg = btrfs_lookup_block_group(fs_info, start);
	ASSERT(bg);
	if (atomic_dec_and_test(&bg->reservations))
		wake_up_var(&bg->reservations);
	btrfs_put_block_group(bg);
}

void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
{
	struct btrfs_space_info *space_info = bg->space_info;

	ASSERT(bg->ro);

	if (!(bg->flags & BTRFS_BLOCK_GROUP_DATA))
		return;

	/*
	 * Our block group is read only but before we set it to read only,
	 * some task might have had allocated an extent from it already, but it
	 * has not yet created a respective ordered extent (and added it to a
	 * root's list of ordered extents).
	 * Therefore wait for any task currently allocating extents, since the
	 * block group's reservations counter is incremented while a read lock
	 * on the groups' semaphore is held and decremented after releasing
	 * the read access on that semaphore and creating the ordered extent.
	 */
	down_write(&space_info->groups_sem);
	up_write(&space_info->groups_sem);

	wait_var_event(&bg->reservations, !atomic_read(&bg->reservations));
}

struct btrfs_caching_control *btrfs_get_caching_control(
		struct btrfs_block_group_cache *cache)
{
	struct btrfs_caching_control *ctl;

	spin_lock(&cache->lock);
	if (!cache->caching_ctl) {
		spin_unlock(&cache->lock);
		return NULL;
	}

	ctl = cache->caching_ctl;
	refcount_inc(&ctl->count);
	spin_unlock(&cache->lock);
	return ctl;
}

void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
{
	if (refcount_dec_and_test(&ctl->count))
		kfree(ctl);
}

/*
 * When we wait for progress in the block group caching, its because our
 * allocation attempt failed at least once.  So, we must sleep and let some
 * progress happen before we try again.
 *
 * This function will sleep at least once waiting for new free space to show
 * up, and then it will check the block group free space numbers for our min
 * num_bytes.  Another option is to have it go ahead and look in the rbtree for
 * a free extent of a given size, but this is a good start.
 *
 * Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using
 * any of the information in this block group.
 */
void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
					   u64 num_bytes)
{
	struct btrfs_caching_control *caching_ctl;

	caching_ctl = btrfs_get_caching_control(cache);
	if (!caching_ctl)
		return;

	wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache) ||
		   (cache->free_space_ctl->free_space >= num_bytes));

	btrfs_put_caching_control(caching_ctl);
}

int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
{
	struct btrfs_caching_control *caching_ctl;
	int ret = 0;

	caching_ctl = btrfs_get_caching_control(cache);
	if (!caching_ctl)
		return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;

	wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache));
	if (cache->cached == BTRFS_CACHE_ERROR)
		ret = -EIO;
	btrfs_put_caching_control(caching_ctl);
	return ret;
}

#ifdef CONFIG_BTRFS_DEBUG
void btrfs_fragment_free_space(struct btrfs_block_group_cache *block_group)
{
	struct btrfs_fs_info *fs_info = block_group->fs_info;
	u64 start = block_group->key.objectid;
	u64 len = block_group->key.offset;
	u64 chunk = block_group->flags & BTRFS_BLOCK_GROUP_METADATA ?
		fs_info->nodesize : fs_info->sectorsize;
	u64 step = chunk << 1;

	while (len > chunk) {
		btrfs_remove_free_space(block_group, start, chunk);
		start += step;
		if (len < step)
			len = 0;
		else
			len -= step;
	}
}
#endif

/*
 * This is only called by btrfs_cache_block_group, since we could have freed
 * extents we need to check the pinned_extents for any extents that can't be
 * used yet since their free space will be released as soon as the transaction
 * commits.
 */
u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
		       u64 start, u64 end)
{
	struct btrfs_fs_info *info = block_group->fs_info;
	u64 extent_start, extent_end, size, total_added = 0;
	int ret;

	while (start < end) {
		ret = find_first_extent_bit(info->pinned_extents, start,
					    &extent_start, &extent_end,
					    EXTENT_DIRTY | EXTENT_UPTODATE,
					    NULL);
		if (ret)
			break;

		if (extent_start <= start) {
			start = extent_end + 1;
		} else if (extent_start > start && extent_start < end) {
			size = extent_start - start;
			total_added += size;
			ret = btrfs_add_free_space(block_group, start,
						   size);
			BUG_ON(ret); /* -ENOMEM or logic error */
			start = extent_end + 1;
		} else {
			break;
		}
	}

	if (start < end) {
		size = end - start;
		total_added += size;
		ret = btrfs_add_free_space(block_group, start, size);
		BUG_ON(ret); /* -ENOMEM or logic error */
	}

	return total_added;
}

static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
{
	struct btrfs_block_group_cache *block_group = caching_ctl->block_group;
	struct btrfs_fs_info *fs_info = block_group->fs_info;
	struct btrfs_root *extent_root = fs_info->extent_root;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	u64 total_found = 0;
	u64 last = 0;
	u32 nritems;
	int ret;
	bool wakeup = true;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);

#ifdef CONFIG_BTRFS_DEBUG
	/*
	 * If we're fragmenting we don't want to make anybody think we can
	 * allocate from this block group until we've had a chance to fragment
	 * the free space.
	 */
	if (btrfs_should_fragment_free_space(block_group))
		wakeup = false;
#endif
	/*
	 * We don't want to deadlock with somebody trying to allocate a new
	 * extent for the extent root while also trying to search the extent
	 * root to add free space.  So we skip locking and search the commit
	 * root, since its read-only
	 */
	path->skip_locking = 1;
	path->search_commit_root = 1;
	path->reada = READA_FORWARD;

	key.objectid = last;
	key.offset = 0;
	key.type = BTRFS_EXTENT_ITEM_KEY;

next:
	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
	if (ret < 0)
		goto out;

	leaf = path->nodes[0];
	nritems = btrfs_header_nritems(leaf);

	while (1) {
		if (btrfs_fs_closing(fs_info) > 1) {
			last = (u64)-1;
			break;
		}

		if (path->slots[0] < nritems) {
			btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		} else {
			ret = btrfs_find_next_key(extent_root, path, &key, 0, 0);
			if (ret)
				break;

			if (need_resched() ||
			    rwsem_is_contended(&fs_info->commit_root_sem)) {
				if (wakeup)
					caching_ctl->progress = last;
				btrfs_release_path(path);
				up_read(&fs_info->commit_root_sem);
				mutex_unlock(&caching_ctl->mutex);
				cond_resched();
				mutex_lock(&caching_ctl->mutex);
				down_read(&fs_info->commit_root_sem);
				goto next;
			}

			ret = btrfs_next_leaf(extent_root, path);
			if (ret < 0)
				goto out;
			if (ret)
				break;
			leaf = path->nodes[0];
			nritems = btrfs_header_nritems(leaf);
			continue;
		}

		if (key.objectid < last) {
			key.objectid = last;
			key.offset = 0;
			key.type = BTRFS_EXTENT_ITEM_KEY;

			if (wakeup)
				caching_ctl->progress = last;
			btrfs_release_path(path);
			goto next;
		}

		if (key.objectid < block_group->key.objectid) {
			path->slots[0]++;
			continue;
		}

		if (key.objectid >= block_group->key.objectid +
		    block_group->key.offset)
			break;

		if (key.type == BTRFS_EXTENT_ITEM_KEY ||
		    key.type == BTRFS_METADATA_ITEM_KEY) {
			total_found += add_new_free_space(block_group, last,
							  key.objectid);
			if (key.type == BTRFS_METADATA_ITEM_KEY)
				last = key.objectid +
					fs_info->nodesize;
			else
				last = key.objectid + key.offset;

			if (total_found > CACHING_CTL_WAKE_UP) {
				total_found = 0;
				if (wakeup)
					wake_up(&caching_ctl->wait);
			}
		}
		path->slots[0]++;
	}
	ret = 0;

	total_found += add_new_free_space(block_group, last,
					  block_group->key.objectid +
					  block_group->key.offset);
	caching_ctl->progress = (u64)-1;

out:
	btrfs_free_path(path);
	return ret;
}

static noinline void caching_thread(struct btrfs_work *work)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_fs_info *fs_info;
	struct btrfs_caching_control *caching_ctl;
	int ret;

	caching_ctl = container_of(work, struct btrfs_caching_control, work);
	block_group = caching_ctl->block_group;
	fs_info = block_group->fs_info;

	mutex_lock(&caching_ctl->mutex);
	down_read(&fs_info->commit_root_sem);

	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
		ret = load_free_space_tree(caching_ctl);
	else
		ret = load_extent_tree_free(caching_ctl);

	spin_lock(&block_group->lock);
	block_group->caching_ctl = NULL;
	block_group->cached = ret ? BTRFS_CACHE_ERROR : BTRFS_CACHE_FINISHED;
	spin_unlock(&block_group->lock);

#ifdef CONFIG_BTRFS_DEBUG
	if (btrfs_should_fragment_free_space(block_group)) {
		u64 bytes_used;

		spin_lock(&block_group->space_info->lock);
		spin_lock(&block_group->lock);
		bytes_used = block_group->key.offset -
			btrfs_block_group_used(&block_group->item);
		block_group->space_info->bytes_used += bytes_used >> 1;
		spin_unlock(&block_group->lock);
		spin_unlock(&block_group->space_info->lock);
		btrfs_fragment_free_space(block_group);
	}
#endif

	caching_ctl->progress = (u64)-1;

	up_read(&fs_info->commit_root_sem);
	btrfs_free_excluded_extents(block_group);
	mutex_unlock(&caching_ctl->mutex);

	wake_up(&caching_ctl->wait);

	btrfs_put_caching_control(caching_ctl);
	btrfs_put_block_group(block_group);
}

int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
			    int load_cache_only)
{
	DEFINE_WAIT(wait);
	struct btrfs_fs_info *fs_info = cache->fs_info;
	struct btrfs_caching_control *caching_ctl;
	int ret = 0;

	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
	if (!caching_ctl)
		return -ENOMEM;

	INIT_LIST_HEAD(&caching_ctl->list);
	mutex_init(&caching_ctl->mutex);
	init_waitqueue_head(&caching_ctl->wait);
	caching_ctl->block_group = cache;
	caching_ctl->progress = cache->key.objectid;
	refcount_set(&caching_ctl->count, 1);
	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
			caching_thread, NULL, NULL);

	spin_lock(&cache->lock);
	/*
	 * This should be a rare occasion, but this could happen I think in the
	 * case where one thread starts to load the space cache info, and then
	 * some other thread starts a transaction commit which tries to do an
	 * allocation while the other thread is still loading the space cache
	 * info.  The previous loop should have kept us from choosing this block
	 * group, but if we've moved to the state where we will wait on caching
	 * block groups we need to first check if we're doing a fast load here,
	 * so we can wait for it to finish, otherwise we could end up allocating
	 * from a block group who's cache gets evicted for one reason or
	 * another.
	 */
	while (cache->cached == BTRFS_CACHE_FAST) {
		struct btrfs_caching_control *ctl;

		ctl = cache->caching_ctl;
		refcount_inc(&ctl->count);
		prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
		spin_unlock(&cache->lock);

		schedule();

		finish_wait(&ctl->wait, &wait);
		btrfs_put_caching_control(ctl);
		spin_lock(&cache->lock);
	}

	if (cache->cached != BTRFS_CACHE_NO) {
		spin_unlock(&cache->lock);
		kfree(caching_ctl);
		return 0;
	}
	WARN_ON(cache->caching_ctl);
	cache->caching_ctl = caching_ctl;
	cache->cached = BTRFS_CACHE_FAST;
	spin_unlock(&cache->lock);

	if (btrfs_test_opt(fs_info, SPACE_CACHE)) {
		mutex_lock(&caching_ctl->mutex);
		ret = load_free_space_cache(cache);

		spin_lock(&cache->lock);
		if (ret == 1) {
			cache->caching_ctl = NULL;
			cache->cached = BTRFS_CACHE_FINISHED;
			cache->last_byte_to_unpin = (u64)-1;
			caching_ctl->progress = (u64)-1;
		} else {
			if (load_cache_only) {
				cache->caching_ctl = NULL;
				cache->cached = BTRFS_CACHE_NO;
			} else {
				cache->cached = BTRFS_CACHE_STARTED;
				cache->has_caching_ctl = 1;
			}
		}
		spin_unlock(&cache->lock);
#ifdef CONFIG_BTRFS_DEBUG
		if (ret == 1 &&
		    btrfs_should_fragment_free_space(cache)) {
			u64 bytes_used;

			spin_lock(&cache->space_info->lock);
			spin_lock(&cache->lock);
			bytes_used = cache->key.offset -
				btrfs_block_group_used(&cache->item);
			cache->space_info->bytes_used += bytes_used >> 1;
			spin_unlock(&cache->lock);
			spin_unlock(&cache->space_info->lock);
			btrfs_fragment_free_space(cache);
		}
#endif
		mutex_unlock(&caching_ctl->mutex);

		wake_up(&caching_ctl->wait);
		if (ret == 1) {
			btrfs_put_caching_control(caching_ctl);
			btrfs_free_excluded_extents(cache);
			return 0;
		}
	} else {
		/*
		 * We're either using the free space tree or no caching at all.
		 * Set cached to the appropriate value and wakeup any waiters.
		 */
		spin_lock(&cache->lock);
		if (load_cache_only) {
			cache->caching_ctl = NULL;
			cache->cached = BTRFS_CACHE_NO;
		} else {
			cache->cached = BTRFS_CACHE_STARTED;
			cache->has_caching_ctl = 1;
		}
		spin_unlock(&cache->lock);
		wake_up(&caching_ctl->wait);
	}

	if (load_cache_only) {
		btrfs_put_caching_control(caching_ctl);
		return 0;
	}

	down_write(&fs_info->commit_root_sem);
	refcount_inc(&caching_ctl->count);
	list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
	up_write(&fs_info->commit_root_sem);

	btrfs_get_block_group(cache);

	btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);

	return ret;
}

static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
	u64 extra_flags = chunk_to_extended(flags) &
				BTRFS_EXTENDED_PROFILE_MASK;

	write_seqlock(&fs_info->profiles_lock);
	if (flags & BTRFS_BLOCK_GROUP_DATA)
		fs_info->avail_data_alloc_bits &= ~extra_flags;
	if (flags & BTRFS_BLOCK_GROUP_METADATA)
		fs_info->avail_metadata_alloc_bits &= ~extra_flags;
	if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
		fs_info->avail_system_alloc_bits &= ~extra_flags;
	write_sequnlock(&fs_info->profiles_lock);
}

/*
 * Clear incompat bits for the following feature(s):
 *
 * - RAID56 - in case there's neither RAID5 nor RAID6 profile block group
 *            in the whole filesystem
 */
static void clear_incompat_bg_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
	if (flags & BTRFS_BLOCK_GROUP_RAID56_MASK) {
		struct list_head *head = &fs_info->space_info;
		struct btrfs_space_info *sinfo;

		list_for_each_entry_rcu(sinfo, head, list) {
			bool found = false;

			down_read(&sinfo->groups_sem);
			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID5]))
				found = true;
			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID6]))
				found = true;
			up_read(&sinfo->groups_sem);

			if (found)
				return;
		}
		btrfs_clear_fs_incompat(fs_info, RAID56);
	}
}

int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
			     u64 group_start, struct extent_map *em)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *root = fs_info->extent_root;
	struct btrfs_path *path;
	struct btrfs_block_group_cache *block_group;
	struct btrfs_free_cluster *cluster;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_key key;
	struct inode *inode;
	struct kobject *kobj = NULL;
	int ret;
	int index;
	int factor;
	struct btrfs_caching_control *caching_ctl = NULL;
	bool remove_em;
	bool remove_rsv = false;

	block_group = btrfs_lookup_block_group(fs_info, group_start);
	BUG_ON(!block_group);
	BUG_ON(!block_group->ro);

	trace_btrfs_remove_block_group(block_group);
	/*
	 * Free the reserved super bytes from this block group before
	 * remove it.
	 */
	btrfs_free_excluded_extents(block_group);
	btrfs_free_ref_tree_range(fs_info, block_group->key.objectid,
				  block_group->key.offset);

	memcpy(&key, &block_group->key, sizeof(key));
	index = btrfs_bg_flags_to_raid_index(block_group->flags);
	factor = btrfs_bg_type_to_factor(block_group->flags);

	/* make sure this block group isn't part of an allocation cluster */
	cluster = &fs_info->data_alloc_cluster;
	spin_lock(&cluster->refill_lock);
	btrfs_return_cluster_to_free_space(block_group, cluster);
	spin_unlock(&cluster->refill_lock);

	/*
	 * make sure this block group isn't part of a metadata
	 * allocation cluster
	 */
	cluster = &fs_info->meta_alloc_cluster;
	spin_lock(&cluster->refill_lock);
	btrfs_return_cluster_to_free_space(block_group, cluster);
	spin_unlock(&cluster->refill_lock);

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

	/*
	 * get the inode first so any iput calls done for the io_list
	 * aren't the final iput (no unlinks allowed now)
	 */
	inode = lookup_free_space_inode(block_group, path);

	mutex_lock(&trans->transaction->cache_write_mutex);
	/*
	 * Make sure our free space cache IO is done before removing the
	 * free space inode
	 */
	spin_lock(&trans->transaction->dirty_bgs_lock);
	if (!list_empty(&block_group->io_list)) {
		list_del_init(&block_group->io_list);

		WARN_ON(!IS_ERR(inode) && inode != block_group->io_ctl.inode);

		spin_unlock(&trans->transaction->dirty_bgs_lock);
		btrfs_wait_cache_io(trans, block_group, path);
		btrfs_put_block_group(block_group);
		spin_lock(&trans->transaction->dirty_bgs_lock);
	}

	if (!list_empty(&block_group->dirty_list)) {
		list_del_init(&block_group->dirty_list);
		remove_rsv = true;
		btrfs_put_block_group(block_group);
	}
	spin_unlock(&trans->transaction->dirty_bgs_lock);
	mutex_unlock(&trans->transaction->cache_write_mutex);

	if (!IS_ERR(inode)) {
		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
		if (ret) {
			btrfs_add_delayed_iput(inode);
			goto out;
		}
		clear_nlink(inode);
		/* One for the block groups ref */
		spin_lock(&block_group->lock);
		if (block_group->iref) {
			block_group->iref = 0;
			block_group->inode = NULL;
			spin_unlock(&block_group->lock);
			iput(inode);
		} else {
			spin_unlock(&block_group->lock);
		}
		/* One for our lookup ref */
		btrfs_add_delayed_iput(inode);
	}

	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
	key.offset = block_group->key.objectid;
	key.type = 0;

	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
	if (ret < 0)
		goto out;
	if (ret > 0)
		btrfs_release_path(path);
	if (ret == 0) {
		ret = btrfs_del_item(trans, tree_root, path);
		if (ret)
			goto out;
		btrfs_release_path(path);
	}

	spin_lock(&fs_info->block_group_cache_lock);
	rb_erase(&block_group->cache_node,
		 &fs_info->block_group_cache_tree);
	RB_CLEAR_NODE(&block_group->cache_node);

	if (fs_info->first_logical_byte == block_group->key.objectid)
		fs_info->first_logical_byte = (u64)-1;
	spin_unlock(&fs_info->block_group_cache_lock);

	down_write(&block_group->space_info->groups_sem);
	/*
	 * we must use list_del_init so people can check to see if they
	 * are still on the list after taking the semaphore
	 */
	list_del_init(&block_group->list);
	if (list_empty(&block_group->space_info->block_groups[index])) {
		kobj = block_group->space_info->block_group_kobjs[index];
		block_group->space_info->block_group_kobjs[index] = NULL;
		clear_avail_alloc_bits(fs_info, block_group->flags);
	}
	up_write(&block_group->space_info->groups_sem);
	clear_incompat_bg_bits(fs_info, block_group->flags);
	if (kobj) {
		kobject_del(kobj);
		kobject_put(kobj);
	}

	if (block_group->has_caching_ctl)
		caching_ctl = btrfs_get_caching_control(block_group);
	if (block_group->cached == BTRFS_CACHE_STARTED)
		btrfs_wait_block_group_cache_done(block_group);
	if (block_group->has_caching_ctl) {
		down_write(&fs_info->commit_root_sem);
		if (!caching_ctl) {
			struct btrfs_caching_control *ctl;

			list_for_each_entry(ctl,
				    &fs_info->caching_block_groups, list)
				if (ctl->block_group == block_group) {
					caching_ctl = ctl;
					refcount_inc(&caching_ctl->count);
					break;
				}
		}
		if (caching_ctl)
			list_del_init(&caching_ctl->list);
		up_write(&fs_info->commit_root_sem);
		if (caching_ctl) {
			/* Once for the caching bgs list and once for us. */
			btrfs_put_caching_control(caching_ctl);
			btrfs_put_caching_control(caching_ctl);
		}
	}

	spin_lock(&trans->transaction->dirty_bgs_lock);
	WARN_ON(!list_empty(&block_group->dirty_list));
	WARN_ON(!list_empty(&block_group->io_list));
	spin_unlock(&trans->transaction->dirty_bgs_lock);

	btrfs_remove_free_space_cache(block_group);

	spin_lock(&block_group->space_info->lock);
	list_del_init(&block_group->ro_list);

	if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
		WARN_ON(block_group->space_info->total_bytes
			< block_group->key.offset);
		WARN_ON(block_group->space_info->bytes_readonly
			< block_group->key.offset);
		WARN_ON(block_group->space_info->disk_total
			< block_group->key.offset * factor);
	}
	block_group->space_info->total_bytes -= block_group->key.offset;
	block_group->space_info->bytes_readonly -= block_group->key.offset;
	block_group->space_info->disk_total -= block_group->key.offset * factor;

	spin_unlock(&block_group->space_info->lock);

	memcpy(&key, &block_group->key, sizeof(key));

	mutex_lock(&fs_info->chunk_mutex);
	spin_lock(&block_group->lock);
	block_group->removed = 1;
	/*
	 * At this point trimming can't start on this block group, because we
	 * removed the block group from the tree fs_info->block_group_cache_tree
	 * so no one can't find it anymore and even if someone already got this
	 * block group before we removed it from the rbtree, they have already
	 * incremented block_group->trimming - if they didn't, they won't find
	 * any free space entries because we already removed them all when we
	 * called btrfs_remove_free_space_cache().
	 *
	 * And we must not remove the extent map from the fs_info->mapping_tree
	 * to prevent the same logical address range and physical device space
	 * ranges from being reused for a new block group. This is because our
	 * fs trim operation (btrfs_trim_fs() / btrfs_ioctl_fitrim()) is
	 * completely transactionless, so while it is trimming a range the
	 * currently running transaction might finish and a new one start,
	 * allowing for new block groups to be created that can reuse the same
	 * physical device locations unless we take this special care.
	 *
	 * There may also be an implicit trim operation if the file system
	 * is mounted with -odiscard. The same protections must remain
	 * in place until the extents have been discarded completely when
	 * the transaction commit has completed.
	 */
	remove_em = (atomic_read(&block_group->trimming) == 0);
	spin_unlock(&block_group->lock);

	mutex_unlock(&fs_info->chunk_mutex);

	ret = remove_block_group_free_space(trans, block_group);
	if (ret)
		goto out;

	btrfs_put_block_group(block_group);
	btrfs_put_block_group(block_group);

	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
	if (ret > 0)
		ret = -EIO;
	if (ret < 0)
		goto out;

	ret = btrfs_del_item(trans, root, path);
	if (ret)
		goto out;

	if (remove_em) {
		struct extent_map_tree *em_tree;

		em_tree = &fs_info->mapping_tree;
		write_lock(&em_tree->lock);
		remove_extent_mapping(em_tree, em);
		write_unlock(&em_tree->lock);
		/* once for the tree */
		free_extent_map(em);
	}
out:
	if (remove_rsv)
		btrfs_delayed_refs_rsv_release(fs_info, 1);
	btrfs_free_path(path);
	return ret;
}

struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
		struct btrfs_fs_info *fs_info, const u64 chunk_offset)
{
	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
	struct extent_map *em;
	struct map_lookup *map;
	unsigned int num_items;

	read_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
	read_unlock(&em_tree->lock);
	ASSERT(em && em->start == chunk_offset);

	/*
	 * We need to reserve 3 + N units from the metadata space info in order
	 * to remove a block group (done at btrfs_remove_chunk() and at
	 * btrfs_remove_block_group()), which are used for:
	 *
	 * 1 unit for adding the free space inode's orphan (located in the tree
	 * of tree roots).
	 * 1 unit for deleting the block group item (located in the extent
	 * tree).
	 * 1 unit for deleting the free space item (located in tree of tree
	 * roots).
	 * N units for deleting N device extent items corresponding to each
	 * stripe (located in the device tree).
	 *
	 * In order to remove a block group we also need to reserve units in the
	 * system space info in order to update the chunk tree (update one or
	 * more device items and remove one chunk item), but this is done at
	 * btrfs_remove_chunk() through a call to check_system_chunk().
	 */
	map = em->map_lookup;
	num_items = 3 + map->num_stripes;
	free_extent_map(em);

	return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root,
							   num_items, 1);
}

/*
 * Mark block group @cache read-only, so later write won't happen to block
 * group @cache.
 *
 * If @force is not set, this function will only mark the block group readonly
 * if we have enough free space (1M) in other metadata/system block groups.
 * If @force is not set, this function will mark the block group readonly
 * without checking free space.
 *
 * NOTE: This function doesn't care if other block groups can contain all the
 * data in this block group. That check should be done by relocation routine,
 * not this function.
 */
int __btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
{
	struct btrfs_space_info *sinfo = cache->space_info;
	u64 num_bytes;
	u64 sinfo_used;
	u64 min_allocable_bytes;
	int ret = -ENOSPC;

	/*
	 * We need some metadata space and system metadata space for
	 * allocating chunks in some corner cases until we force to set
	 * it to be readonly.
	 */
	if ((sinfo->flags &
	     (BTRFS_BLOCK_GROUP_SYSTEM | BTRFS_BLOCK_GROUP_METADATA)) &&
	    !force)
		min_allocable_bytes = SZ_1M;
	else
		min_allocable_bytes = 0;

	spin_lock(&sinfo->lock);
	spin_lock(&cache->lock);

	if (cache->ro) {
		cache->ro++;
		ret = 0;
		goto out;
	}

	num_bytes = cache->key.offset - cache->reserved - cache->pinned -
		    cache->bytes_super - btrfs_block_group_used(&cache->item);
	sinfo_used = btrfs_space_info_used(sinfo, true);

	/*
	 * sinfo_used + num_bytes should always <= sinfo->total_bytes.
	 *
	 * Here we make sure if we mark this bg RO, we still have enough
	 * free space as buffer (if min_allocable_bytes is not 0).
	 */
	if (sinfo_used + num_bytes + min_allocable_bytes <=
	    sinfo->total_bytes) {
		sinfo->bytes_readonly += num_bytes;
		cache->ro++;
		list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
		ret = 0;
	}
out:
	spin_unlock(&cache->lock);
	spin_unlock(&sinfo->lock);
	if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) {
		btrfs_info(cache->fs_info,
			"unable to make block group %llu ro",
			cache->key.objectid);
		btrfs_info(cache->fs_info,
			"sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu",
			sinfo_used, num_bytes, min_allocable_bytes);
		btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0);
	}
	return ret;
}

/*
 * Process the unused_bgs list and remove any that don't have any allocated
 * space inside of them.
 */
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_space_info *space_info;
	struct btrfs_trans_handle *trans;
	int ret = 0;

	if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
		return;

	spin_lock(&fs_info->unused_bgs_lock);
	while (!list_empty(&fs_info->unused_bgs)) {
		u64 start, end;
		int trimming;

		block_group = list_first_entry(&fs_info->unused_bgs,
					       struct btrfs_block_group_cache,
					       bg_list);
		list_del_init(&block_group->bg_list);

		space_info = block_group->space_info;

		if (ret || btrfs_mixed_space_info(space_info)) {
			btrfs_put_block_group(block_group);
			continue;
		}
		spin_unlock(&fs_info->unused_bgs_lock);

		mutex_lock(&fs_info->delete_unused_bgs_mutex);

		/* Don't want to race with allocators so take the groups_sem */
		down_write(&space_info->groups_sem);
		spin_lock(&block_group->lock);
		if (block_group->reserved || block_group->pinned ||
		    btrfs_block_group_used(&block_group->item) ||
		    block_group->ro ||
		    list_is_singular(&block_group->list)) {
			/*
			 * We want to bail if we made new allocations or have
			 * outstanding allocations in this block group.  We do
			 * the ro check in case balance is currently acting on
			 * this block group.
			 */
			trace_btrfs_skip_unused_block_group(block_group);
			spin_unlock(&block_group->lock);
			up_write(&space_info->groups_sem);
			goto next;
		}
		spin_unlock(&block_group->lock);

		/* We don't want to force the issue, only flip if it's ok. */
		ret = __btrfs_inc_block_group_ro(block_group, 0);
		up_write(&space_info->groups_sem);
		if (ret < 0) {
			ret = 0;
			goto next;
		}

		/*
		 * Want to do this before we do anything else so we can recover
		 * properly if we fail to join the transaction.
		 */
		trans = btrfs_start_trans_remove_block_group(fs_info,
						     block_group->key.objectid);
		if (IS_ERR(trans)) {
			btrfs_dec_block_group_ro(block_group);
			ret = PTR_ERR(trans);
			goto next;
		}

		/*
		 * We could have pending pinned extents for this block group,
		 * just delete them, we don't care about them anymore.
		 */
		start = block_group->key.objectid;
		end = start + block_group->key.offset - 1;
		/*
		 * Hold the unused_bg_unpin_mutex lock to avoid racing with
		 * btrfs_finish_extent_commit(). If we are at transaction N,
		 * another task might be running finish_extent_commit() for the
		 * previous transaction N - 1, and have seen a range belonging
		 * to the block group in freed_extents[] before we were able to
		 * clear the whole block group range from freed_extents[]. This
		 * means that task can lookup for the block group after we
		 * unpinned it from freed_extents[] and removed it, leading to
		 * a BUG_ON() at btrfs_unpin_extent_range().
		 */
		mutex_lock(&fs_info->unused_bg_unpin_mutex);
		ret = clear_extent_bits(&fs_info->freed_extents[0], start, end,
				  EXTENT_DIRTY);
		if (ret) {
			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
			btrfs_dec_block_group_ro(block_group);
			goto end_trans;
		}
		ret = clear_extent_bits(&fs_info->freed_extents[1], start, end,
				  EXTENT_DIRTY);
		if (ret) {
			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
			btrfs_dec_block_group_ro(block_group);
			goto end_trans;
		}
		mutex_unlock(&fs_info->unused_bg_unpin_mutex);

		/* Reset pinned so btrfs_put_block_group doesn't complain */
		spin_lock(&space_info->lock);
		spin_lock(&block_group->lock);

		btrfs_space_info_update_bytes_pinned(fs_info, space_info,
						     -block_group->pinned);
		space_info->bytes_readonly += block_group->pinned;
		percpu_counter_add_batch(&space_info->total_bytes_pinned,
				   -block_group->pinned,
				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
		block_group->pinned = 0;

		spin_unlock(&block_group->lock);
		spin_unlock(&space_info->lock);

		/* DISCARD can flip during remount */
		trimming = btrfs_test_opt(fs_info, DISCARD);

		/* Implicit trim during transaction commit. */
		if (trimming)
			btrfs_get_block_group_trimming(block_group);

		/*
		 * Btrfs_remove_chunk will abort the transaction if things go
		 * horribly wrong.
		 */
		ret = btrfs_remove_chunk(trans, block_group->key.objectid);

		if (ret) {
			if (trimming)
				btrfs_put_block_group_trimming(block_group);
			goto end_trans;
		}

		/*
		 * If we're not mounted with -odiscard, we can just forget
		 * about this block group. Otherwise we'll need to wait
		 * until transaction commit to do the actual discard.
		 */
		if (trimming) {
			spin_lock(&fs_info->unused_bgs_lock);
			/*
			 * A concurrent scrub might have added us to the list
			 * fs_info->unused_bgs, so use a list_move operation
			 * to add the block group to the deleted_bgs list.
			 */
			list_move(&block_group->bg_list,
				  &trans->transaction->deleted_bgs);
			spin_unlock(&fs_info->unused_bgs_lock);
			btrfs_get_block_group(block_group);
		}
end_trans:
		btrfs_end_transaction(trans);
next:
		mutex_unlock(&fs_info->delete_unused_bgs_mutex);
		btrfs_put_block_group(block_group);
		spin_lock(&fs_info->unused_bgs_lock);
	}
	spin_unlock(&fs_info->unused_bgs_lock);
}

void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
{
	struct btrfs_fs_info *fs_info = bg->fs_info;

	spin_lock(&fs_info->unused_bgs_lock);
	if (list_empty(&bg->bg_list)) {
		btrfs_get_block_group(bg);
		trace_btrfs_add_unused_block_group(bg);
		list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
	}
	spin_unlock(&fs_info->unused_bgs_lock);
}

static int find_first_block_group(struct btrfs_fs_info *fs_info,
				  struct btrfs_path *path,
				  struct btrfs_key *key)
{
	struct btrfs_root *root = fs_info->extent_root;
	int ret = 0;
	struct btrfs_key found_key;
	struct extent_buffer *leaf;
	struct btrfs_block_group_item bg;
	u64 flags;
	int slot;

	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
	if (ret < 0)
		goto out;

	while (1) {
		slot = path->slots[0];
		leaf = path->nodes[0];
		if (slot >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(root, path);
			if (ret == 0)
				continue;
			if (ret < 0)
				goto out;
			break;
		}
		btrfs_item_key_to_cpu(leaf, &found_key, slot);

		if (found_key.objectid >= key->objectid &&
		    found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
			struct extent_map_tree *em_tree;
			struct extent_map *em;

			em_tree = &root->fs_info->mapping_tree;
			read_lock(&em_tree->lock);
			em = lookup_extent_mapping(em_tree, found_key.objectid,
						   found_key.offset);
			read_unlock(&em_tree->lock);
			if (!em) {
				btrfs_err(fs_info,
			"logical %llu len %llu found bg but no related chunk",
					  found_key.objectid, found_key.offset);
				ret = -ENOENT;
			} else if (em->start != found_key.objectid ||
				   em->len != found_key.offset) {
				btrfs_err(fs_info,
		"block group %llu len %llu mismatch with chunk %llu len %llu",
					  found_key.objectid, found_key.offset,
					  em->start, em->len);
				ret = -EUCLEAN;
			} else {
				read_extent_buffer(leaf, &bg,
					btrfs_item_ptr_offset(leaf, slot),
					sizeof(bg));
				flags = btrfs_block_group_flags(&bg) &
					BTRFS_BLOCK_GROUP_TYPE_MASK;

				if (flags != (em->map_lookup->type &
					      BTRFS_BLOCK_GROUP_TYPE_MASK)) {
					btrfs_err(fs_info,
"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
						found_key.objectid,
						found_key.offset, flags,
						(BTRFS_BLOCK_GROUP_TYPE_MASK &
						 em->map_lookup->type));
					ret = -EUCLEAN;
				} else {
					ret = 0;
				}
			}
			free_extent_map(em);
			goto out;
		}
		path->slots[0]++;
	}
out:
	return ret;
}

static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
	u64 extra_flags = chunk_to_extended(flags) &
				BTRFS_EXTENDED_PROFILE_MASK;

	write_seqlock(&fs_info->profiles_lock);
	if (flags & BTRFS_BLOCK_GROUP_DATA)
		fs_info->avail_data_alloc_bits |= extra_flags;
	if (flags & BTRFS_BLOCK_GROUP_METADATA)
		fs_info->avail_metadata_alloc_bits |= extra_flags;
	if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
		fs_info->avail_system_alloc_bits |= extra_flags;
	write_sequnlock(&fs_info->profiles_lock);
}

static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
{
	struct btrfs_fs_info *fs_info = cache->fs_info;
	u64 bytenr;
	u64 *logical;
	int stripe_len;
	int i, nr, ret;

	if (cache->key.objectid < BTRFS_SUPER_INFO_OFFSET) {
		stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->key.objectid;
		cache->bytes_super += stripe_len;
		ret = btrfs_add_excluded_extent(fs_info, cache->key.objectid,
						stripe_len);
		if (ret)
			return ret;
	}

	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
		bytenr = btrfs_sb_offset(i);
		ret = btrfs_rmap_block(fs_info, cache->key.objectid,
				       bytenr, &logical, &nr, &stripe_len);
		if (ret)
			return ret;

		while (nr--) {
			u64 start, len;

			if (logical[nr] > cache->key.objectid +
			    cache->key.offset)
				continue;

			if (logical[nr] + stripe_len <= cache->key.objectid)
				continue;

			start = logical[nr];
			if (start < cache->key.objectid) {
				start = cache->key.objectid;
				len = (logical[nr] + stripe_len) - start;
			} else {
				len = min_t(u64, stripe_len,
					    cache->key.objectid +
					    cache->key.offset - start);
			}

			cache->bytes_super += len;
			ret = btrfs_add_excluded_extent(fs_info, start, len);
			if (ret) {
				kfree(logical);
				return ret;
			}
		}

		kfree(logical);
	}
	return 0;
}

static void link_block_group(struct btrfs_block_group_cache *cache)
{
	struct btrfs_space_info *space_info = cache->space_info;
	int index = btrfs_bg_flags_to_raid_index(cache->flags);
	bool first = false;

	down_write(&space_info->groups_sem);
	if (list_empty(&space_info->block_groups[index]))
		first = true;
	list_add_tail(&cache->list, &space_info->block_groups[index]);
	up_write(&space_info->groups_sem);

	if (first)
		btrfs_sysfs_add_block_group_type(cache);
}

static struct btrfs_block_group_cache *btrfs_create_block_group_cache(
		struct btrfs_fs_info *fs_info, u64 start, u64 size)
{
	struct btrfs_block_group_cache *cache;

	cache = kzalloc(sizeof(*cache), GFP_NOFS);
	if (!cache)
		return NULL;

	cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
					GFP_NOFS);
	if (!cache->free_space_ctl) {
		kfree(cache);
		return NULL;
	}

	cache->key.objectid = start;
	cache->key.offset = size;
	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;

	cache->fs_info = fs_info;
	cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start);
	set_free_space_tree_thresholds(cache);

	atomic_set(&cache->count, 1);
	spin_lock_init(&cache->lock);
	init_rwsem(&cache->data_rwsem);
	INIT_LIST_HEAD(&cache->list);
	INIT_LIST_HEAD(&cache->cluster_list);
	INIT_LIST_HEAD(&cache->bg_list);
	INIT_LIST_HEAD(&cache->ro_list);
	INIT_LIST_HEAD(&cache->dirty_list);
	INIT_LIST_HEAD(&cache->io_list);
	btrfs_init_free_space_ctl(cache);
	atomic_set(&cache->trimming, 0);
	mutex_init(&cache->free_space_lock);
	btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root);

	return cache;
}

/*
 * Iterate all chunks and verify that each of them has the corresponding block
 * group
 */
static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
{
	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
	struct extent_map *em;
	struct btrfs_block_group_cache *bg;
	u64 start = 0;
	int ret = 0;

	while (1) {
		read_lock(&map_tree->lock);
		/*
		 * lookup_extent_mapping will return the first extent map
		 * intersecting the range, so setting @len to 1 is enough to
		 * get the first chunk.
		 */
		em = lookup_extent_mapping(map_tree, start, 1);
		read_unlock(&map_tree->lock);
		if (!em)
			break;

		bg = btrfs_lookup_block_group(fs_info, em->start);
		if (!bg) {
			btrfs_err(fs_info,
	"chunk start=%llu len=%llu doesn't have corresponding block group",
				     em->start, em->len);
			ret = -EUCLEAN;
			free_extent_map(em);
			break;
		}
		if (bg->key.objectid != em->start ||
		    bg->key.offset != em->len ||
		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
			btrfs_err(fs_info,
"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
				em->start, em->len,
				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
				bg->key.objectid, bg->key.offset,
				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
			ret = -EUCLEAN;
			free_extent_map(em);
			btrfs_put_block_group(bg);
			break;
		}
		start = em->start + em->len;
		free_extent_map(em);
		btrfs_put_block_group(bg);
	}
	return ret;
}

int btrfs_read_block_groups(struct btrfs_fs_info *info)
{
	struct btrfs_path *path;
	int ret;
	struct btrfs_block_group_cache *cache;
	struct btrfs_space_info *space_info;
	struct btrfs_key key;
	struct btrfs_key found_key;
	struct extent_buffer *leaf;
	int need_clear = 0;
	u64 cache_gen;
	u64 feature;
	int mixed;

	feature = btrfs_super_incompat_flags(info->super_copy);
	mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS);

	key.objectid = 0;
	key.offset = 0;
	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
	path->reada = READA_FORWARD;

	cache_gen = btrfs_super_cache_generation(info->super_copy);
	if (btrfs_test_opt(info, SPACE_CACHE) &&
	    btrfs_super_generation(info->super_copy) != cache_gen)
		need_clear = 1;
	if (btrfs_test_opt(info, CLEAR_CACHE))
		need_clear = 1;

	while (1) {
		ret = find_first_block_group(info, path, &key);
		if (ret > 0)
			break;
		if (ret != 0)
			goto error;

		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);

		cache = btrfs_create_block_group_cache(info, found_key.objectid,
						       found_key.offset);
		if (!cache) {
			ret = -ENOMEM;
			goto error;
		}

		if (need_clear) {
			/*
			 * When we mount with old space cache, we need to
			 * set BTRFS_DC_CLEAR and set dirty flag.
			 *
			 * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
			 *    truncate the old free space cache inode and
			 *    setup a new one.
			 * b) Setting 'dirty flag' makes sure that we flush
			 *    the new space cache info onto disk.
			 */
			if (btrfs_test_opt(info, SPACE_CACHE))
				cache->disk_cache_state = BTRFS_DC_CLEAR;
		}

		read_extent_buffer(leaf, &cache->item,
				   btrfs_item_ptr_offset(leaf, path->slots[0]),
				   sizeof(cache->item));
		cache->flags = btrfs_block_group_flags(&cache->item);
		if (!mixed &&
		    ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
		    (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
			btrfs_err(info,
"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
				  cache->key.objectid);
			ret = -EINVAL;
			goto error;
		}

		key.objectid = found_key.objectid + found_key.offset;
		btrfs_release_path(path);

		/*
		 * We need to exclude the super stripes now so that the space
		 * info has super bytes accounted for, otherwise we'll think
		 * we have more space than we actually do.
		 */
		ret = exclude_super_stripes(cache);
		if (ret) {
			/*
			 * We may have excluded something, so call this just in
			 * case.
			 */
			btrfs_free_excluded_extents(cache);
			btrfs_put_block_group(cache);
			goto error;
		}

		/*
		 * Check for two cases, either we are full, and therefore
		 * don't need to bother with the caching work since we won't
		 * find any space, or we are empty, and we can just add all
		 * the space in and be done with it.  This saves us _a_lot_ of
		 * time, particularly in the full case.
		 */
		if (found_key.offset == btrfs_block_group_used(&cache->item)) {
			cache->last_byte_to_unpin = (u64)-1;
			cache->cached = BTRFS_CACHE_FINISHED;
			btrfs_free_excluded_extents(cache);
		} else if (btrfs_block_group_used(&cache->item) == 0) {
			cache->last_byte_to_unpin = (u64)-1;
			cache->cached = BTRFS_CACHE_FINISHED;
			add_new_free_space(cache, found_key.objectid,
					   found_key.objectid +
					   found_key.offset);
			btrfs_free_excluded_extents(cache);
		}

		ret = btrfs_add_block_group_cache(info, cache);
		if (ret) {
			btrfs_remove_free_space_cache(cache);
			btrfs_put_block_group(cache);
			goto error;
		}

		trace_btrfs_add_block_group(info, cache, 0);
		btrfs_update_space_info(info, cache->flags, found_key.offset,
					btrfs_block_group_used(&cache->item),
					cache->bytes_super, &space_info);

		cache->space_info = space_info;

		link_block_group(cache);

		set_avail_alloc_bits(info, cache->flags);
		if (btrfs_chunk_readonly(info, cache->key.objectid)) {
			__btrfs_inc_block_group_ro(cache, 1);
		} else if (btrfs_block_group_used(&cache->item) == 0) {
			ASSERT(list_empty(&cache->bg_list));
			btrfs_mark_bg_unused(cache);
		}
	}

	list_for_each_entry_rcu(space_info, &info->space_info, list) {
		if (!(btrfs_get_alloc_profile(info, space_info->flags) &
		      (BTRFS_BLOCK_GROUP_RAID10 |
		       BTRFS_BLOCK_GROUP_RAID1_MASK |
		       BTRFS_BLOCK_GROUP_RAID56_MASK |
		       BTRFS_BLOCK_GROUP_DUP)))
			continue;
		/*
		 * Avoid allocating from un-mirrored block group if there are
		 * mirrored block groups.
		 */
		list_for_each_entry(cache,
				&space_info->block_groups[BTRFS_RAID_RAID0],
				list)
			__btrfs_inc_block_group_ro(cache, 1);
		list_for_each_entry(cache,
				&space_info->block_groups[BTRFS_RAID_SINGLE],
				list)
			__btrfs_inc_block_group_ro(cache, 1);
	}

	btrfs_init_global_block_rsv(info);
	ret = check_chunk_block_group_mappings(info);
error:
	btrfs_free_path(path);
	return ret;
}

void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *block_group;
	struct btrfs_root *extent_root = fs_info->extent_root;
	struct btrfs_block_group_item item;
	struct btrfs_key key;
	int ret = 0;

	if (!trans->can_flush_pending_bgs)
		return;

	while (!list_empty(&trans->new_bgs)) {
		block_group = list_first_entry(&trans->new_bgs,
					       struct btrfs_block_group_cache,
					       bg_list);
		if (ret)
			goto next;

		spin_lock(&block_group->lock);
		memcpy(&item, &block_group->item, sizeof(item));
		memcpy(&key, &block_group->key, sizeof(key));
		spin_unlock(&block_group->lock);

		ret = btrfs_insert_item(trans, extent_root, &key, &item,
					sizeof(item));
		if (ret)
			btrfs_abort_transaction(trans, ret);
		ret = btrfs_finish_chunk_alloc(trans, key.objectid, key.offset);
		if (ret)
			btrfs_abort_transaction(trans, ret);
		add_block_group_free_space(trans, block_group);
		/* Already aborted the transaction if it failed. */
next:
		btrfs_delayed_refs_rsv_release(fs_info, 1);
		list_del_init(&block_group->bg_list);
	}
	btrfs_trans_release_chunk_metadata(trans);
}

int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
			   u64 type, u64 chunk_offset, u64 size)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *cache;
	int ret;

	btrfs_set_log_full_commit(trans);

	cache = btrfs_create_block_group_cache(fs_info, chunk_offset, size);
	if (!cache)
		return -ENOMEM;

	btrfs_set_block_group_used(&cache->item, bytes_used);
	btrfs_set_block_group_chunk_objectid(&cache->item,
					     BTRFS_FIRST_CHUNK_TREE_OBJECTID);
	btrfs_set_block_group_flags(&cache->item, type);

	cache->flags = type;
	cache->last_byte_to_unpin = (u64)-1;
	cache->cached = BTRFS_CACHE_FINISHED;
	cache->needs_free_space = 1;
	ret = exclude_super_stripes(cache);
	if (ret) {
		/* We may have excluded something, so call this just in case */
		btrfs_free_excluded_extents(cache);
		btrfs_put_block_group(cache);
		return ret;
	}

	add_new_free_space(cache, chunk_offset, chunk_offset + size);

	btrfs_free_excluded_extents(cache);

#ifdef CONFIG_BTRFS_DEBUG
	if (btrfs_should_fragment_free_space(cache)) {
		u64 new_bytes_used = size - bytes_used;

		bytes_used += new_bytes_used >> 1;
		btrfs_fragment_free_space(cache);
	}
#endif
	/*
	 * Ensure the corresponding space_info object is created and
	 * assigned to our block group. We want our bg to be added to the rbtree
	 * with its ->space_info set.
	 */
	cache->space_info = btrfs_find_space_info(fs_info, cache->flags);
	ASSERT(cache->space_info);

	ret = btrfs_add_block_group_cache(fs_info, cache);
	if (ret) {
		btrfs_remove_free_space_cache(cache);
		btrfs_put_block_group(cache);
		return ret;
	}

	/*
	 * Now that our block group has its ->space_info set and is inserted in
	 * the rbtree, update the space info's counters.
	 */
	trace_btrfs_add_block_group(fs_info, cache, 1);
	btrfs_update_space_info(fs_info, cache->flags, size, bytes_used,
				cache->bytes_super, &cache->space_info);
	btrfs_update_global_block_rsv(fs_info);

	link_block_group(cache);

	list_add_tail(&cache->bg_list, &trans->new_bgs);
	trans->delayed_ref_updates++;
	btrfs_update_delayed_refs_rsv(trans);

	set_avail_alloc_bits(fs_info, type);
	return 0;
}

static u64 update_block_group_flags(struct btrfs_fs_info *fs_info, u64 flags)
{
	u64 num_devices;
	u64 stripped;

	/*
	 * if restripe for this chunk_type is on pick target profile and
	 * return, otherwise do the usual balance
	 */
	stripped = btrfs_get_restripe_target(fs_info, flags);
	if (stripped)
		return extended_to_chunk(stripped);

	num_devices = fs_info->fs_devices->rw_devices;

	stripped = BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID56_MASK |
		BTRFS_BLOCK_GROUP_RAID1_MASK | BTRFS_BLOCK_GROUP_RAID10;

	if (num_devices == 1) {
		stripped |= BTRFS_BLOCK_GROUP_DUP;
		stripped = flags & ~stripped;

		/* turn raid0 into single device chunks */
		if (flags & BTRFS_BLOCK_GROUP_RAID0)
			return stripped;

		/* turn mirroring into duplication */
		if (flags & (BTRFS_BLOCK_GROUP_RAID1_MASK |
			     BTRFS_BLOCK_GROUP_RAID10))
			return stripped | BTRFS_BLOCK_GROUP_DUP;
	} else {
		/* they already had raid on here, just return */
		if (flags & stripped)
			return flags;

		stripped |= BTRFS_BLOCK_GROUP_DUP;
		stripped = flags & ~stripped;

		/* switch duplicated blocks with raid1 */
		if (flags & BTRFS_BLOCK_GROUP_DUP)
			return stripped | BTRFS_BLOCK_GROUP_RAID1;

		/* this is drive concat, leave it alone */
	}

	return flags;
}

int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache)

{
	struct btrfs_fs_info *fs_info = cache->fs_info;
	struct btrfs_trans_handle *trans;
	u64 alloc_flags;
	int ret;

again:
	trans = btrfs_join_transaction(fs_info->extent_root);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	/*
	 * we're not allowed to set block groups readonly after the dirty
	 * block groups cache has started writing.  If it already started,
	 * back off and let this transaction commit
	 */
	mutex_lock(&fs_info->ro_block_group_mutex);
	if (test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &trans->transaction->flags)) {
		u64 transid = trans->transid;

		mutex_unlock(&fs_info->ro_block_group_mutex);
		btrfs_end_transaction(trans);

		ret = btrfs_wait_for_commit(fs_info, transid);
		if (ret)
			return ret;
		goto again;
	}

	/*
	 * if we are changing raid levels, try to allocate a corresponding
	 * block group with the new raid level.
	 */
	alloc_flags = update_block_group_flags(fs_info, cache->flags);
	if (alloc_flags != cache->flags) {
		ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
		/*
		 * ENOSPC is allowed here, we may have enough space
		 * already allocated at the new raid level to
		 * carry on
		 */
		if (ret == -ENOSPC)
			ret = 0;
		if (ret < 0)
			goto out;
	}

	ret = __btrfs_inc_block_group_ro(cache, 0);
	if (!ret)
		goto out;
	alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags);
	ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
	if (ret < 0)
		goto out;
	ret = __btrfs_inc_block_group_ro(cache, 0);
out:
	if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
		alloc_flags = update_block_group_flags(fs_info, cache->flags);
		mutex_lock(&fs_info->chunk_mutex);
		check_system_chunk(trans, alloc_flags);
		mutex_unlock(&fs_info->chunk_mutex);
	}
	mutex_unlock(&fs_info->ro_block_group_mutex);

	btrfs_end_transaction(trans);
	return ret;
}

void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
{
	struct btrfs_space_info *sinfo = cache->space_info;
	u64 num_bytes;

	BUG_ON(!cache->ro);

	spin_lock(&sinfo->lock);
	spin_lock(&cache->lock);
	if (!--cache->ro) {
		num_bytes = cache->key.offset - cache->reserved -
			    cache->pinned - cache->bytes_super -
			    btrfs_block_group_used(&cache->item);
		sinfo->bytes_readonly -= num_bytes;
		list_del_init(&cache->ro_list);
	}
	spin_unlock(&cache->lock);
	spin_unlock(&sinfo->lock);
}

static int write_one_cache_group(struct btrfs_trans_handle *trans,
				 struct btrfs_path *path,
				 struct btrfs_block_group_cache *cache)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	int ret;
	struct btrfs_root *extent_root = fs_info->extent_root;
	unsigned long bi;
	struct extent_buffer *leaf;

	ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
	if (ret) {
		if (ret > 0)
			ret = -ENOENT;
		goto fail;
	}

	leaf = path->nodes[0];
	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
	write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item));
	btrfs_mark_buffer_dirty(leaf);
fail:
	btrfs_release_path(path);
	return ret;

}

static int cache_save_setup(struct btrfs_block_group_cache *block_group,
			    struct btrfs_trans_handle *trans,
			    struct btrfs_path *path)
{
	struct btrfs_fs_info *fs_info = block_group->fs_info;
	struct btrfs_root *root = fs_info->tree_root;
	struct inode *inode = NULL;
	struct extent_changeset *data_reserved = NULL;
	u64 alloc_hint = 0;
	int dcs = BTRFS_DC_ERROR;
	u64 num_pages = 0;
	int retries = 0;
	int ret = 0;

	/*
	 * If this block group is smaller than 100 megs don't bother caching the
	 * block group.
	 */
	if (block_group->key.offset < (100 * SZ_1M)) {
		spin_lock(&block_group->lock);
		block_group->disk_cache_state = BTRFS_DC_WRITTEN;
		spin_unlock(&block_group->lock);
		return 0;
	}

	if (trans->aborted)
		return 0;
again:
	inode = lookup_free_space_inode(block_group, path);
	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
		ret = PTR_ERR(inode);
		btrfs_release_path(path);
		goto out;
	}

	if (IS_ERR(inode)) {
		BUG_ON(retries);
		retries++;

		if (block_group->ro)
			goto out_free;

		ret = create_free_space_inode(trans, block_group, path);
		if (ret)
			goto out_free;
		goto again;
	}

	/*
	 * We want to set the generation to 0, that way if anything goes wrong
	 * from here on out we know not to trust this cache when we load up next
	 * time.
	 */
	BTRFS_I(inode)->generation = 0;
	ret = btrfs_update_inode(trans, root, inode);
	if (ret) {
		/*
		 * So theoretically we could recover from this, simply set the
		 * super cache generation to 0 so we know to invalidate the
		 * cache, but then we'd have to keep track of the block groups
		 * that fail this way so we know we _have_ to reset this cache
		 * before the next commit or risk reading stale cache.  So to
		 * limit our exposure to horrible edge cases lets just abort the
		 * transaction, this only happens in really bad situations
		 * anyway.
		 */
		btrfs_abort_transaction(trans, ret);
		goto out_put;
	}
	WARN_ON(ret);

	/* We've already setup this transaction, go ahead and exit */
	if (block_group->cache_generation == trans->transid &&
	    i_size_read(inode)) {
		dcs = BTRFS_DC_SETUP;
		goto out_put;
	}

	if (i_size_read(inode) > 0) {
		ret = btrfs_check_trunc_cache_free_space(fs_info,
					&fs_info->global_block_rsv);
		if (ret)
			goto out_put;

		ret = btrfs_truncate_free_space_cache(trans, NULL, inode);
		if (ret)
			goto out_put;
	}

	spin_lock(&block_group->lock);
	if (block_group->cached != BTRFS_CACHE_FINISHED ||
	    !btrfs_test_opt(fs_info, SPACE_CACHE)) {
		/*
		 * don't bother trying to write stuff out _if_
		 * a) we're not cached,
		 * b) we're with nospace_cache mount option,
		 * c) we're with v2 space_cache (FREE_SPACE_TREE).
		 */
		dcs = BTRFS_DC_WRITTEN;
		spin_unlock(&block_group->lock);
		goto out_put;
	}
	spin_unlock(&block_group->lock);

	/*
	 * We hit an ENOSPC when setting up the cache in this transaction, just
	 * skip doing the setup, we've already cleared the cache so we're safe.
	 */
	if (test_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags)) {
		ret = -ENOSPC;
		goto out_put;
	}

	/*
	 * Try to preallocate enough space based on how big the block group is.
	 * Keep in mind this has to include any pinned space which could end up
	 * taking up quite a bit since it's not folded into the other space
	 * cache.
	 */
	num_pages = div_u64(block_group->key.offset, SZ_256M);
	if (!num_pages)
		num_pages = 1;

	num_pages *= 16;
	num_pages *= PAGE_SIZE;

	ret = btrfs_check_data_free_space(inode, &data_reserved, 0, num_pages);
	if (ret)
		goto out_put;

	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, num_pages,
					      num_pages, num_pages,
					      &alloc_hint);
	/*
	 * Our cache requires contiguous chunks so that we don't modify a bunch
	 * of metadata or split extents when writing the cache out, which means
	 * we can enospc if we are heavily fragmented in addition to just normal
	 * out of space conditions.  So if we hit this just skip setting up any
	 * other block groups for this transaction, maybe we'll unpin enough
	 * space the next time around.
	 */
	if (!ret)
		dcs = BTRFS_DC_SETUP;
	else if (ret == -ENOSPC)
		set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags);

out_put:
	iput(inode);
out_free:
	btrfs_release_path(path);
out:
	spin_lock(&block_group->lock);
	if (!ret && dcs == BTRFS_DC_SETUP)
		block_group->cache_generation = trans->transid;
	block_group->disk_cache_state = dcs;
	spin_unlock(&block_group->lock);

	extent_changeset_free(data_reserved);
	return ret;
}

int btrfs_setup_space_cache(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *cache, *tmp;
	struct btrfs_transaction *cur_trans = trans->transaction;
	struct btrfs_path *path;

	if (list_empty(&cur_trans->dirty_bgs) ||
	    !btrfs_test_opt(fs_info, SPACE_CACHE))
		return 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	/* Could add new block groups, use _safe just in case */
	list_for_each_entry_safe(cache, tmp, &cur_trans->dirty_bgs,
				 dirty_list) {
		if (cache->disk_cache_state == BTRFS_DC_CLEAR)
			cache_save_setup(cache, trans, path);
	}

	btrfs_free_path(path);
	return 0;
}

/*
 * Transaction commit does final block group cache writeback during a critical
 * section where nothing is allowed to change the FS.  This is required in
 * order for the cache to actually match the block group, but can introduce a
 * lot of latency into the commit.
 *
 * So, btrfs_start_dirty_block_groups is here to kick off block group cache IO.
 * There's a chance we'll have to redo some of it if the block group changes
 * again during the commit, but it greatly reduces the commit latency by
 * getting rid of the easy block groups while we're still allowing others to
 * join the commit.
 */
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *cache;
	struct btrfs_transaction *cur_trans = trans->transaction;
	int ret = 0;
	int should_put;
	struct btrfs_path *path = NULL;
	LIST_HEAD(dirty);
	struct list_head *io = &cur_trans->io_bgs;
	int num_started = 0;
	int loops = 0;

	spin_lock(&cur_trans->dirty_bgs_lock);
	if (list_empty(&cur_trans->dirty_bgs)) {
		spin_unlock(&cur_trans->dirty_bgs_lock);
		return 0;
	}
	list_splice_init(&cur_trans->dirty_bgs, &dirty);
	spin_unlock(&cur_trans->dirty_bgs_lock);

again:
	/* Make sure all the block groups on our dirty list actually exist */
	btrfs_create_pending_block_groups(trans);

	if (!path) {
		path = btrfs_alloc_path();
		if (!path)
			return -ENOMEM;
	}

	/*
	 * cache_write_mutex is here only to save us from balance or automatic
	 * removal of empty block groups deleting this block group while we are
	 * writing out the cache
	 */
	mutex_lock(&trans->transaction->cache_write_mutex);
	while (!list_empty(&dirty)) {
		bool drop_reserve = true;

		cache = list_first_entry(&dirty,
					 struct btrfs_block_group_cache,
					 dirty_list);
		/*
		 * This can happen if something re-dirties a block group that
		 * is already under IO.  Just wait for it to finish and then do
		 * it all again
		 */
		if (!list_empty(&cache->io_list)) {
			list_del_init(&cache->io_list);
			btrfs_wait_cache_io(trans, cache, path);
			btrfs_put_block_group(cache);
		}


		/*
		 * btrfs_wait_cache_io uses the cache->dirty_list to decide if
		 * it should update the cache_state.  Don't delete until after
		 * we wait.
		 *
		 * Since we're not running in the commit critical section
		 * we need the dirty_bgs_lock to protect from update_block_group
		 */
		spin_lock(&cur_trans->dirty_bgs_lock);
		list_del_init(&cache->dirty_list);
		spin_unlock(&cur_trans->dirty_bgs_lock);

		should_put = 1;

		cache_save_setup(cache, trans, path);

		if (cache->disk_cache_state == BTRFS_DC_SETUP) {
			cache->io_ctl.inode = NULL;
			ret = btrfs_write_out_cache(trans, cache, path);
			if (ret == 0 && cache->io_ctl.inode) {
				num_started++;
				should_put = 0;

				/*
				 * The cache_write_mutex is protecting the
				 * io_list, also refer to the definition of
				 * btrfs_transaction::io_bgs for more details
				 */
				list_add_tail(&cache->io_list, io);
			} else {
				/*
				 * If we failed to write the cache, the
				 * generation will be bad and life goes on
				 */
				ret = 0;
			}
		}
		if (!ret) {
			ret = write_one_cache_group(trans, path, cache);
			/*
			 * Our block group might still be attached to the list
			 * of new block groups in the transaction handle of some
			 * other task (struct btrfs_trans_handle->new_bgs). This
			 * means its block group item isn't yet in the extent
			 * tree. If this happens ignore the error, as we will
			 * try again later in the critical section of the
			 * transaction commit.
			 */
			if (ret == -ENOENT) {
				ret = 0;
				spin_lock(&cur_trans->dirty_bgs_lock);
				if (list_empty(&cache->dirty_list)) {
					list_add_tail(&cache->dirty_list,
						      &cur_trans->dirty_bgs);
					btrfs_get_block_group(cache);
					drop_reserve = false;
				}
				spin_unlock(&cur_trans->dirty_bgs_lock);
			} else if (ret) {
				btrfs_abort_transaction(trans, ret);
			}
		}

		/* If it's not on the io list, we need to put the block group */
		if (should_put)
			btrfs_put_block_group(cache);
		if (drop_reserve)
			btrfs_delayed_refs_rsv_release(fs_info, 1);

		if (ret)
			break;

		/*
		 * Avoid blocking other tasks for too long. It might even save
		 * us from writing caches for block groups that are going to be
		 * removed.
		 */
		mutex_unlock(&trans->transaction->cache_write_mutex);
		mutex_lock(&trans->transaction->cache_write_mutex);
	}
	mutex_unlock(&trans->transaction->cache_write_mutex);

	/*
	 * Go through delayed refs for all the stuff we've just kicked off
	 * and then loop back (just once)
	 */
	ret = btrfs_run_delayed_refs(trans, 0);
	if (!ret && loops == 0) {
		loops++;
		spin_lock(&cur_trans->dirty_bgs_lock);
		list_splice_init(&cur_trans->dirty_bgs, &dirty);
		/*
		 * dirty_bgs_lock protects us from concurrent block group
		 * deletes too (not just cache_write_mutex).
		 */
		if (!list_empty(&dirty)) {
			spin_unlock(&cur_trans->dirty_bgs_lock);
			goto again;
		}
		spin_unlock(&cur_trans->dirty_bgs_lock);
	} else if (ret < 0) {
		btrfs_cleanup_dirty_bgs(cur_trans, fs_info);
	}

	btrfs_free_path(path);
	return ret;
}

int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *cache;
	struct btrfs_transaction *cur_trans = trans->transaction;
	int ret = 0;
	int should_put;
	struct btrfs_path *path;
	struct list_head *io = &cur_trans->io_bgs;
	int num_started = 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	/*
	 * Even though we are in the critical section of the transaction commit,
	 * we can still have concurrent tasks adding elements to this
	 * transaction's list of dirty block groups. These tasks correspond to
	 * endio free space workers started when writeback finishes for a
	 * space cache, which run inode.c:btrfs_finish_ordered_io(), and can
	 * allocate new block groups as a result of COWing nodes of the root
	 * tree when updating the free space inode. The writeback for the space
	 * caches is triggered by an earlier call to
	 * btrfs_start_dirty_block_groups() and iterations of the following
	 * loop.
	 * Also we want to do the cache_save_setup first and then run the
	 * delayed refs to make sure we have the best chance at doing this all
	 * in one shot.
	 */
	spin_lock(&cur_trans->dirty_bgs_lock);
	while (!list_empty(&cur_trans->dirty_bgs)) {
		cache = list_first_entry(&cur_trans->dirty_bgs,
					 struct btrfs_block_group_cache,
					 dirty_list);

		/*
		 * This can happen if cache_save_setup re-dirties a block group
		 * that is already under IO.  Just wait for it to finish and
		 * then do it all again
		 */
		if (!list_empty(&cache->io_list)) {
			spin_unlock(&cur_trans->dirty_bgs_lock);
			list_del_init(&cache->io_list);
			btrfs_wait_cache_io(trans, cache, path);
			btrfs_put_block_group(cache);
			spin_lock(&cur_trans->dirty_bgs_lock);
		}

		/*
		 * Don't remove from the dirty list until after we've waited on
		 * any pending IO
		 */
		list_del_init(&cache->dirty_list);
		spin_unlock(&cur_trans->dirty_bgs_lock);
		should_put = 1;

		cache_save_setup(cache, trans, path);

		if (!ret)
			ret = btrfs_run_delayed_refs(trans,
						     (unsigned long) -1);

		if (!ret && cache->disk_cache_state == BTRFS_DC_SETUP) {
			cache->io_ctl.inode = NULL;
			ret = btrfs_write_out_cache(trans, cache, path);
			if (ret == 0 && cache->io_ctl.inode) {
				num_started++;
				should_put = 0;
				list_add_tail(&cache->io_list, io);
			} else {
				/*
				 * If we failed to write the cache, the
				 * generation will be bad and life goes on
				 */
				ret = 0;
			}
		}
		if (!ret) {
			ret = write_one_cache_group(trans, path, cache);
			/*
			 * One of the free space endio workers might have
			 * created a new block group while updating a free space
			 * cache's inode (at inode.c:btrfs_finish_ordered_io())
			 * and hasn't released its transaction handle yet, in
			 * which case the new block group is still attached to
			 * its transaction handle and its creation has not
			 * finished yet (no block group item in the extent tree
			 * yet, etc). If this is the case, wait for all free
			 * space endio workers to finish and retry. This is a
			 * a very rare case so no need for a more efficient and
			 * complex approach.
			 */
			if (ret == -ENOENT) {
				wait_event(cur_trans->writer_wait,
				   atomic_read(&cur_trans->num_writers) == 1);
				ret = write_one_cache_group(trans, path, cache);
			}
			if (ret)
				btrfs_abort_transaction(trans, ret);
		}

		/* If its not on the io list, we need to put the block group */
		if (should_put)
			btrfs_put_block_group(cache);
		btrfs_delayed_refs_rsv_release(fs_info, 1);
		spin_lock(&cur_trans->dirty_bgs_lock);
	}
	spin_unlock(&cur_trans->dirty_bgs_lock);

	/*
	 * Refer to the definition of io_bgs member for details why it's safe
	 * to use it without any locking
	 */
	while (!list_empty(io)) {
		cache = list_first_entry(io, struct btrfs_block_group_cache,
					 io_list);
		list_del_init(&cache->io_list);
		btrfs_wait_cache_io(trans, cache, path);
		btrfs_put_block_group(cache);
	}

	btrfs_free_path(path);
	return ret;
}