/fs/btrfs/disk-io.c

/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>
#include <linux/swap.h>
#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/crc32c.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
#include <asm/unaligned.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "print-tree.h"
#include "async-thread.h"
#include "locking.h"
#include "tree-log.h"
#include "free-space-cache.h"
#include "inode-map.h"

static struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
static void free_fs_root(struct btrfs_root *root);
static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
				    int read_only);
static int btrfs_destroy_ordered_operations(struct btrfs_root *root);
static int btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
				      struct btrfs_root *root);
static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t);
static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
static int btrfs_destroy_marked_extents(struct btrfs_root *root,
					struct extent_io_tree *dirty_pages,
					int mark);
static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
				       struct extent_io_tree *pinned_extents);
static int btrfs_cleanup_transaction(struct btrfs_root *root);

/*
 * end_io_wq structs are used to do processing in task context when an IO is
 * complete.  This is used during reads to verify checksums, and it is used
 * by writes to insert metadata for new file extents after IO is complete.
 */
struct end_io_wq {
	struct bio *bio;
	bio_end_io_t *end_io;
	void *private;
	struct btrfs_fs_info *info;
	int error;
	int metadata;
	struct list_head list;
	struct btrfs_work work;
};

/*
 * async submit bios are used to offload expensive checksumming
 * onto the worker threads.  They checksum file and metadata bios
 * just before they are sent down the IO stack.
 */
struct async_submit_bio {
	struct inode *inode;
	struct bio *bio;
	struct list_head list;
	extent_submit_bio_hook_t *submit_bio_start;
	extent_submit_bio_hook_t *submit_bio_done;
	int rw;
	int mirror_num;
	unsigned long bio_flags;
	/*
	 * bio_offset is optional, can be used if the pages in the bio
	 * can't tell us where in the file the bio should go
	 */
	u64 bio_offset;
	struct btrfs_work work;
};

/*
 * Lockdep class keys for extent_buffer->lock's in this root.  For a given
 * eb, the lockdep key is determined by the btrfs_root it belongs to and
 * the level the eb occupies in the tree.
 *
 * Different roots are used for different purposes and may nest inside each
 * other and they require separate keysets.  As lockdep keys should be
 * static, assign keysets according to the purpose of the root as indicated
 * by btrfs_root->objectid.  This ensures that all special purpose roots
 * have separate keysets.
 *
 * Lock-nesting across peer nodes is always done with the immediate parent
 * node locked thus preventing deadlock.  As lockdep doesn't know this, use
 * subclass to avoid triggering lockdep warning in such cases.
 *
 * The key is set by the readpage_end_io_hook after the buffer has passed
 * csum validation but before the pages are unlocked.  It is also set by
 * btrfs_init_new_buffer on freshly allocated blocks.
 *
 * We also add a check to make sure the highest level of the tree is the
 * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
 * needs update as well.
 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# if BTRFS_MAX_LEVEL != 8
#  error
# endif

static struct btrfs_lockdep_keyset {
	u64			id;		/* root objectid */
	const char		*name_stem;	/* lock name stem */
	char			names[BTRFS_MAX_LEVEL + 1][20];
	struct lock_class_key	keys[BTRFS_MAX_LEVEL + 1];
} btrfs_lockdep_keysets[] = {
	{ .id = BTRFS_ROOT_TREE_OBJECTID,	.name_stem = "root"	},
	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	.name_stem = "extent"	},
	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	.name_stem = "chunk"	},
	{ .id = BTRFS_DEV_TREE_OBJECTID,	.name_stem = "dev"	},
	{ .id = BTRFS_FS_TREE_OBJECTID,		.name_stem = "fs"	},
	{ .id = BTRFS_CSUM_TREE_OBJECTID,	.name_stem = "csum"	},
	{ .id = BTRFS_ORPHAN_OBJECTID,		.name_stem = "orphan"	},
	{ .id = BTRFS_TREE_LOG_OBJECTID,	.name_stem = "log"	},
	{ .id = BTRFS_TREE_RELOC_OBJECTID,	.name_stem = "treloc"	},
	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	.name_stem = "dreloc"	},
	{ .id = 0,				.name_stem = "tree"	},
};

void __init btrfs_init_lockdep(void)
{
	int i, j;

	/* initialize lockdep class names */
	for (i = 0; i < ARRAY_SIZE(btrfs_lockdep_keysets); i++) {
		struct btrfs_lockdep_keyset *ks = &btrfs_lockdep_keysets[i];

		for (j = 0; j < ARRAY_SIZE(ks->names); j++)
			snprintf(ks->names[j], sizeof(ks->names[j]),
				 "btrfs-%s-%02d", ks->name_stem, j);
	}
}

void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
				    int level)
{
	struct btrfs_lockdep_keyset *ks;

	BUG_ON(level >= ARRAY_SIZE(ks->keys));

	/* find the matching keyset, id 0 is the default entry */
	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
		if (ks->id == objectid)
			break;

	lockdep_set_class_and_name(&eb->lock,
				   &ks->keys[level], ks->names[level]);
}

#endif

/*
 * extents on the btree inode are pretty simple, there's one extent
 * that covers the entire device
 */
static struct extent_map *btree_get_extent(struct inode *inode,
		struct page *page, size_t pg_offset, u64 start, u64 len,
		int create)
{
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	struct extent_map *em;
	int ret;

	read_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, start, len);
	if (em) {
		em->bdev =
			BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
		read_unlock(&em_tree->lock);
		goto out;
	}
	read_unlock(&em_tree->lock);

	em = alloc_extent_map();
	if (!em) {
		em = ERR_PTR(-ENOMEM);
		goto out;
	}
	em->start = 0;
	em->len = (u64)-1;
	em->block_len = (u64)-1;
	em->block_start = 0;
	em->bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;

	write_lock(&em_tree->lock);
	ret = add_extent_mapping(em_tree, em);
	if (ret == -EEXIST) {
		u64 failed_start = em->start;
		u64 failed_len = em->len;

		free_extent_map(em);
		em = lookup_extent_mapping(em_tree, start, len);
		if (em) {
			ret = 0;
		} else {
			em = lookup_extent_mapping(em_tree, failed_start,
						   failed_len);
			ret = -EIO;
		}
	} else if (ret) {
		free_extent_map(em);
		em = NULL;
	}
	write_unlock(&em_tree->lock);

	if (ret)
		em = ERR_PTR(ret);
out:
	return em;
}

u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len)
{
	return crc32c(seed, data, len);
}

void btrfs_csum_final(u32 crc, char *result)
{
	put_unaligned_le32(~crc, result);
}

/*
 * compute the csum for a btree block, and either verify it or write it
 * into the csum field of the block.
 */
static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
			   int verify)
{
	u16 csum_size =
		btrfs_super_csum_size(&root->fs_info->super_copy);
	char *result = NULL;
	unsigned long len;
	unsigned long cur_len;
	unsigned long offset = BTRFS_CSUM_SIZE;
	char *kaddr;
	unsigned long map_start;
	unsigned long map_len;
	int err;
	u32 crc = ~(u32)0;
	unsigned long inline_result;

	len = buf->len - offset;
	while (len > 0) {
		err = map_private_extent_buffer(buf, offset, 32,
					&kaddr, &map_start, &map_len);
		if (err)
			return 1;
		cur_len = min(len, map_len - (offset - map_start));
		crc = btrfs_csum_data(root, kaddr + offset - map_start,
				      crc, cur_len);
		len -= cur_len;
		offset += cur_len;
	}
	if (csum_size > sizeof(inline_result)) {
		result = kzalloc(csum_size * sizeof(char), GFP_NOFS);
		if (!result)
			return 1;
	} else {
		result = (char *)&inline_result;
	}

	btrfs_csum_final(crc, result);

	if (verify) {
		if (memcmp_extent_buffer(buf, result, 0, csum_size)) {
			u32 val;
			u32 found = 0;
			memcpy(&found, result, csum_size);

			read_extent_buffer(buf, &val, 0, csum_size);
			printk_ratelimited(KERN_INFO "btrfs: %s checksum verify "
				       "failed on %llu wanted %X found %X "
				       "level %d\n",
				       root->fs_info->sb->s_id,
				       (unsigned long long)buf->start, val, found,
				       btrfs_header_level(buf));
			if (result != (char *)&inline_result)
				kfree(result);
			return 1;
		}
	} else {
		write_extent_buffer(buf, result, 0, csum_size);
	}
	if (result != (char *)&inline_result)
		kfree(result);
	return 0;
}

/*
 * we can't consider a given block up to date unless the transid of the
 * block matches the transid in the parent node's pointer.  This is how we
 * detect blocks that either didn't get written at all or got written
 * in the wrong place.
 */
static int verify_parent_transid(struct extent_io_tree *io_tree,
				 struct extent_buffer *eb, u64 parent_transid)
{
	struct extent_state *cached_state = NULL;
	int ret;

	if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
		return 0;

	lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
			 0, &cached_state, GFP_NOFS);
	if (extent_buffer_uptodate(io_tree, eb, cached_state) &&
	    btrfs_header_generation(eb) == parent_transid) {
		ret = 0;
		goto out;
	}
	printk_ratelimited("parent transid verify failed on %llu wanted %llu "
		       "found %llu\n",
		       (unsigned long long)eb->start,
		       (unsigned long long)parent_transid,
		       (unsigned long long)btrfs_header_generation(eb));
	ret = 1;
	clear_extent_buffer_uptodate(io_tree, eb, &cached_state);
out:
	unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
			     &cached_state, GFP_NOFS);
	return ret;
}

/*
 * helper to read a given tree block, doing retries as required when
 * the checksums don't match and we have alternate mirrors to try.
 */
static int btree_read_extent_buffer_pages(struct btrfs_root *root,
					  struct extent_buffer *eb,
					  u64 start, u64 parent_transid)
{
	struct extent_io_tree *io_tree;
	int ret;
	int num_copies = 0;
	int mirror_num = 0;

	clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
	io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
	while (1) {
		ret = read_extent_buffer_pages(io_tree, eb, start, 1,
					       btree_get_extent, mirror_num);
		if (!ret &&
		    !verify_parent_transid(io_tree, eb, parent_transid))
			return ret;

		/*
		 * This buffer's crc is fine, but its contents are corrupted, so
		 * there is no reason to read the other copies, they won't be
		 * any less wrong.
		 */
		if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
			return ret;

		num_copies = btrfs_num_copies(&root->fs_info->mapping_tree,
					      eb->start, eb->len);
		if (num_copies == 1)
			return ret;

		mirror_num++;
		if (mirror_num > num_copies)
			return ret;
	}
	return -EIO;
}

/*
 * checksum a dirty tree block before IO.  This has extra checks to make sure
 * we only fill in the checksum field in the first page of a multi-page block
 */

static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
{
	struct extent_io_tree *tree;
	u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
	u64 found_start;
	unsigned long len;
	struct extent_buffer *eb;
	int ret;

	tree = &BTRFS_I(page->mapping->host)->io_tree;

	if (page->private == EXTENT_PAGE_PRIVATE) {
		WARN_ON(1);
		goto out;
	}
	if (!page->private) {
		WARN_ON(1);
		goto out;
	}
	len = page->private >> 2;
	WARN_ON(len == 0);

	eb = alloc_extent_buffer(tree, start, len, page);
	if (eb == NULL) {
		WARN_ON(1);
		goto out;
	}
	ret = btree_read_extent_buffer_pages(root, eb, start + PAGE_CACHE_SIZE,
					     btrfs_header_generation(eb));
	BUG_ON(ret);
	WARN_ON(!btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN));

	found_start = btrfs_header_bytenr(eb);
	if (found_start != start) {
		WARN_ON(1);
		goto err;
	}
	if (eb->first_page != page) {
		WARN_ON(1);
		goto err;
	}
	if (!PageUptodate(page)) {
		WARN_ON(1);
		goto err;
	}
	csum_tree_block(root, eb, 0);
err:
	free_extent_buffer(eb);
out:
	return 0;
}

static int check_tree_block_fsid(struct btrfs_root *root,
				 struct extent_buffer *eb)
{
	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
	u8 fsid[BTRFS_UUID_SIZE];
	int ret = 1;

	read_extent_buffer(eb, fsid, (unsigned long)btrfs_header_fsid(eb),
			   BTRFS_FSID_SIZE);
	while (fs_devices) {
		if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) {
			ret = 0;
			break;
		}
		fs_devices = fs_devices->seed;
	}
	return ret;
}

#define CORRUPT(reason, eb, root, slot)				\
	printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu,"	\
	       "root=%llu, slot=%d\n", reason,			\
	       (unsigned long long)btrfs_header_bytenr(eb),	\
	       (unsigned long long)root->objectid, slot)

static noinline int check_leaf(struct btrfs_root *root,
			       struct extent_buffer *leaf)
{
	struct btrfs_key key;
	struct btrfs_key leaf_key;
	u32 nritems = btrfs_header_nritems(leaf);
	int slot;

	if (nritems == 0)
		return 0;

	/* Check the 0 item */
	if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
	    BTRFS_LEAF_DATA_SIZE(root)) {
		CORRUPT("invalid item offset size pair", leaf, root, 0);
		return -EIO;
	}

	/*
	 * Check to make sure each items keys are in the correct order and their
	 * offsets make sense.  We only have to loop through nritems-1 because
	 * we check the current slot against the next slot, which verifies the
	 * next slot's offset+size makes sense and that the current's slot
	 * offset is correct.
	 */
	for (slot = 0; slot < nritems - 1; slot++) {
		btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
		btrfs_item_key_to_cpu(leaf, &key, slot + 1);

		/* Make sure the keys are in the right order */
		if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
			CORRUPT("bad key order", leaf, root, slot);
			return -EIO;
		}

		/*
		 * Make sure the offset and ends are right, remember that the
		 * item data starts at the end of the leaf and grows towards the
		 * front.
		 */
		if (btrfs_item_offset_nr(leaf, slot) !=
			btrfs_item_end_nr(leaf, slot + 1)) {
			CORRUPT("slot offset bad", leaf, root, slot);
			return -EIO;
		}

		/*
		 * Check to make sure that we don't point outside of the leaf,
		 * just incase all the items are consistent to eachother, but
		 * all point outside of the leaf.
		 */
		if (btrfs_item_end_nr(leaf, slot) >
		    BTRFS_LEAF_DATA_SIZE(root)) {
			CORRUPT("slot end outside of leaf", leaf, root, slot);
			return -EIO;
		}
	}

	return 0;
}

static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
			       struct extent_state *state)
{
	struct extent_io_tree *tree;
	u64 found_start;
	int found_level;
	unsigned long len;
	struct extent_buffer *eb;
	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
	int ret = 0;

	tree = &BTRFS_I(page->mapping->host)->io_tree;
	if (page->private == EXTENT_PAGE_PRIVATE)
		goto out;
	if (!page->private)
		goto out;

	len = page->private >> 2;
	WARN_ON(len == 0);

	eb = alloc_extent_buffer(tree, start, len, page);
	if (eb == NULL) {
		ret = -EIO;
		goto out;
	}

	found_start = btrfs_header_bytenr(eb);
	if (found_start != start) {
		printk_ratelimited(KERN_INFO "btrfs bad tree block start "
			       "%llu %llu\n",
			       (unsigned long long)found_start,
			       (unsigned long long)eb->start);
		ret = -EIO;
		goto err;
	}
	if (eb->first_page != page) {
		printk(KERN_INFO "btrfs bad first page %lu %lu\n",
		       eb->first_page->index, page->index);
		WARN_ON(1);
		ret = -EIO;
		goto err;
	}
	if (check_tree_block_fsid(root, eb)) {
		printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n",
			       (unsigned long long)eb->start);
		ret = -EIO;
		goto err;
	}
	found_level = btrfs_header_level(eb);

	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb),
				       eb, found_level);

	ret = csum_tree_block(root, eb, 1);
	if (ret) {
		ret = -EIO;
		goto err;
	}

	/*
	 * If this is a leaf block and it is corrupt, set the corrupt bit so
	 * that we don't try and read the other copies of this block, just
	 * return -EIO.
	 */
	if (found_level == 0 && check_leaf(root, eb)) {
		set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
		ret = -EIO;
	}

	end = min_t(u64, eb->len, PAGE_CACHE_SIZE);
	end = eb->start + end - 1;
err:
	free_extent_buffer(eb);
out:
	return ret;
}

static void end_workqueue_bio(struct bio *bio, int err)
{
	struct end_io_wq *end_io_wq = bio->bi_private;
	struct btrfs_fs_info *fs_info;

	fs_info = end_io_wq->info;
	end_io_wq->error = err;
	end_io_wq->work.func = end_workqueue_fn;
	end_io_wq->work.flags = 0;

	if (bio->bi_rw & REQ_WRITE) {
		if (end_io_wq->metadata == 1)
			btrfs_queue_worker(&fs_info->endio_meta_write_workers,
					   &end_io_wq->work);
		else if (end_io_wq->metadata == 2)
			btrfs_queue_worker(&fs_info->endio_freespace_worker,
					   &end_io_wq->work);
		else
			btrfs_queue_worker(&fs_info->endio_write_workers,
					   &end_io_wq->work);
	} else {
		if (end_io_wq->metadata)
			btrfs_queue_worker(&fs_info->endio_meta_workers,
					   &end_io_wq->work);
		else
			btrfs_queue_worker(&fs_info->endio_workers,
					   &end_io_wq->work);
	}
}

/*
 * For the metadata arg you want
 *
 * 0 - if data
 * 1 - if normal metadta
 * 2 - if writing to the free space cache area
 */
int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
			int metadata)
{
	struct end_io_wq *end_io_wq;
	end_io_wq = kmalloc(sizeof(*end_io_wq), GFP_NOFS);
	if (!end_io_wq)
		return -ENOMEM;

	end_io_wq->private = bio->bi_private;
	end_io_wq->end_io = bio->bi_end_io;
	end_io_wq->info = info;
	end_io_wq->error = 0;
	end_io_wq->bio = bio;
	end_io_wq->metadata = metadata;

	bio->bi_private = end_io_wq;
	bio->bi_end_io = end_workqueue_bio;
	return 0;
}

unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
{
	unsigned long limit = min_t(unsigned long,
				    info->workers.max_workers,
				    info->fs_devices->open_devices);
	return 256 * limit;
}

static void run_one_async_start(struct btrfs_work *work)
{
	struct async_submit_bio *async;

	async = container_of(work, struct  async_submit_bio, work);
	async->submit_bio_start(async->inode, async->rw, async->bio,
			       async->mirror_num, async->bio_flags,
			       async->bio_offset);
}

static void run_one_async_done(struct btrfs_work *work)
{
	struct btrfs_fs_info *fs_info;
	struct async_submit_bio *async;
	int limit;

	async = container_of(work, struct  async_submit_bio, work);
	fs_info = BTRFS_I(async->inode)->root->fs_info;

	limit = btrfs_async_submit_limit(fs_info);
	limit = limit * 2 / 3;

	atomic_dec(&fs_info->nr_async_submits);

	if (atomic_read(&fs_info->nr_async_submits) < limit &&
	    waitqueue_active(&fs_info->async_submit_wait))
		wake_up(&fs_info->async_submit_wait);

	async->submit_bio_done(async->inode, async->rw, async->bio,
			       async->mirror_num, async->bio_flags,
			       async->bio_offset);
}

static void run_one_async_free(struct btrfs_work *work)
{
	struct async_submit_bio *async;

	async = container_of(work, struct  async_submit_bio, work);
	kfree(async);
}

int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
			int rw, struct bio *bio, int mirror_num,
			unsigned long bio_flags,
			u64 bio_offset,
			extent_submit_bio_hook_t *submit_bio_start,
			extent_submit_bio_hook_t *submit_bio_done)
{
	struct async_submit_bio *async;

	async = kmalloc(sizeof(*async), GFP_NOFS);
	if (!async)
		return -ENOMEM;

	async->inode = inode;
	async->rw = rw;
	async->bio = bio;
	async->mirror_num = mirror_num;
	async->submit_bio_start = submit_bio_start;
	async->submit_bio_done = submit_bio_done;

	async->work.func = run_one_async_start;
	async->work.ordered_func = run_one_async_done;
	async->work.ordered_free = run_one_async_free;

	async->work.flags = 0;
	async->bio_flags = bio_flags;
	async->bio_offset = bio_offset;

	atomic_inc(&fs_info->nr_async_submits);

	if (rw & REQ_SYNC)
		btrfs_set_work_high_prio(&async->work);

	btrfs_queue_worker(&fs_info->workers, &async->work);

	while (atomic_read(&fs_info->async_submit_draining) &&
	      atomic_read(&fs_info->nr_async_submits)) {
		wait_event(fs_info->async_submit_wait,
			   (atomic_read(&fs_info->nr_async_submits) == 0));
	}

	return 0;
}

static int btree_csum_one_bio(struct bio *bio)
{
	struct bio_vec *bvec = bio->bi_io_vec;
	int bio_index = 0;
	struct btrfs_root *root;

	WARN_ON(bio->bi_vcnt <= 0);
	while (bio_index < bio->bi_vcnt) {
		root = BTRFS_I(bvec->bv_page->mapping->host)->root;
		csum_dirty_buffer(root, bvec->bv_page);
		bio_index++;
		bvec++;
	}
	return 0;
}

static int __btree_submit_bio_start(struct inode *inode, int rw,
				    struct bio *bio, int mirror_num,
				    unsigned long bio_flags,
				    u64 bio_offset)
{
	/*
	 * when we're called for a write, we're already in the async
	 * submission context.  Just jump into btrfs_map_bio
	 */
	btree_csum_one_bio(bio);
	return 0;
}

static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
				 int mirror_num, unsigned long bio_flags,
				 u64 bio_offset)
{
	/*
	 * when we're called for a write, we're already in the async
	 * submission context.  Just jump into btrfs_map_bio
	 */
	return btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1);
}

static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
				 int mirror_num, unsigned long bio_flags,
				 u64 bio_offset)
{
	int ret;

	ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info,
					  bio, 1);
	BUG_ON(ret);

	if (!(rw & REQ_WRITE)) {
		/*
		 * called for a read, do the setup so that checksum validation
		 * can happen in the async kernel threads
		 */
		return btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
				     mirror_num, 0);
	}

	/*
	 * kthread helpers are used to submit writes so that checksumming
	 * can happen in parallel across all CPUs
	 */
	return btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
				   inode, rw, bio, mirror_num, 0,
				   bio_offset,
				   __btree_submit_bio_start,
				   __btree_submit_bio_done);
}

#ifdef CONFIG_MIGRATION
static int btree_migratepage(struct address_space *mapping,
			struct page *newpage, struct page *page)
{
	/*
	 * we can't safely write a btree page from here,
	 * we haven't done the locking hook
	 */
	if (PageDirty(page))
		return -EAGAIN;
	/*
	 * Buffers may be managed in a filesystem specific way.
	 * We must have no buffers or drop them.
	 */
	if (page_has_private(page) &&
	    !try_to_release_page(page, GFP_KERNEL))
		return -EAGAIN;
	return migrate_page(mapping, newpage, page);
}
#endif

static int btree_writepage(struct page *page, struct writeback_control *wbc)
{
	struct extent_io_tree *tree;
	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
	struct extent_buffer *eb;
	int was_dirty;

	tree = &BTRFS_I(page->mapping->host)->io_tree;
	if (!(current->flags & PF_MEMALLOC)) {
		return extent_write_full_page(tree, page,
					      btree_get_extent, wbc);
	}

	redirty_page_for_writepage(wbc, page);
	eb = btrfs_find_tree_block(root, page_offset(page), PAGE_CACHE_SIZE);
	WARN_ON(!eb);

	was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
	if (!was_dirty) {
		spin_lock(&root->fs_info->delalloc_lock);
		root->fs_info->dirty_metadata_bytes += PAGE_CACHE_SIZE;
		spin_unlock(&root->fs_info->delalloc_lock);
	}
	free_extent_buffer(eb);

	unlock_page(page);
	return 0;
}

static int btree_writepages(struct address_space *mapping,
			    struct writeback_control *wbc)
{
	struct extent_io_tree *tree;
	tree = &BTRFS_I(mapping->host)->io_tree;
	if (wbc->sync_mode == WB_SYNC_NONE) {
		struct btrfs_root *root = BTRFS_I(mapping->host)->root;
		u64 num_dirty;
		unsigned long thresh = 32 * 1024 * 1024;

		if (wbc->for_kupdate)
			return 0;

		/* this is a bit racy, but that's ok */
		num_dirty = root->fs_info->dirty_metadata_bytes;
		if (num_dirty < thresh)
			return 0;
	}
	return extent_writepages(tree, mapping, btree_get_extent, wbc);
}

static int btree_readpage(struct file *file, struct page *page)
{
	struct extent_io_tree *tree;
	tree = &BTRFS_I(page->mapping->host)->io_tree;
	return extent_read_full_page(tree, page, btree_get_extent);
}

static int btree_releasepage(struct page *page, gfp_t gfp_flags)
{
	struct extent_io_tree *tree;
	struct extent_map_tree *map;
	int ret;

	if (PageWriteback(page) || PageDirty(page))
		return 0;

	tree = &BTRFS_I(page->mapping->host)->io_tree;
	map = &BTRFS_I(page->mapping->host)->extent_tree;

	ret = try_release_extent_state(map, tree, page, gfp_flags);
	if (!ret)
		return 0;

	ret = try_release_extent_buffer(tree, page);
	if (ret == 1) {
		ClearPagePrivate(page);
		set_page_private(page, 0);
		page_cache_release(page);
	}

	return ret;
}

static void btree_invalidatepage(struct page *page, unsigned long offset)
{
	struct extent_io_tree *tree;
	tree = &BTRFS_I(page->mapping->host)->io_tree;
	extent_invalidatepage(tree, page, offset);
	btree_releasepage(page, GFP_NOFS);
	if (PagePrivate(page)) {
		printk(KERN_WARNING "btrfs warning page private not zero "
		       "on page %llu\n", (unsigned long long)page_offset(page));
		ClearPagePrivate(page);
		set_page_private(page, 0);
		page_cache_release(page);
	}
}

static const struct address_space_operations btree_aops = {
	.readpage	= btree_readpage,
	.writepage	= btree_writepage,
	.writepages	= btree_writepages,
	.releasepage	= btree_releasepage,
	.invalidatepage = btree_invalidatepage,
#ifdef CONFIG_MIGRATION
	.migratepage	= btree_migratepage,
#endif
};

int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
			 u64 parent_transid)
{
	struct extent_buffer *buf = NULL;
	struct inode *btree_inode = root->fs_info->btree_inode;
	int ret = 0;

	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
	if (!buf)
		return 0;
	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
				 buf, 0, 0, btree_get_extent, 0);
	free_extent_buffer(buf);
	return ret;
}

struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
					    u64 bytenr, u32 blocksize)
{
	struct inode *btree_inode = root->fs_info->btree_inode;
	struct extent_buffer *eb;
	eb = find_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
				bytenr, blocksize);
	return eb;
}

struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
						 u64 bytenr, u32 blocksize)
{
	struct inode *btree_inode = root->fs_info->btree_inode;
	struct extent_buffer *eb;

	eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
				 bytenr, blocksize, NULL);
	return eb;
}


int btrfs_write_tree_block(struct extent_buffer *buf)
{
	return filemap_fdatawrite_range(buf->first_page->mapping, buf->start,
					buf->start + buf->len - 1);
}

int btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
{
	return filemap_fdatawait_range(buf->first_page->mapping,
				       buf->start, buf->start + buf->len - 1);
}

struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
				      u32 blocksize, u64 parent_transid)
{
	struct extent_buffer *buf = NULL;
	int ret;

	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
	if (!buf)
		return NULL;

	ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);

	if (ret == 0)
		set_bit(EXTENT_BUFFER_UPTODATE, &buf->bflags);
	return buf;

}

int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		     struct extent_buffer *buf)
{
	struct inode *btree_inode = root->fs_info->btree_inode;
	if (btrfs_header_generation(buf) ==
	    root->fs_info->running_transaction->transid) {
		btrfs_assert_tree_locked(buf);

		if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
			spin_lock(&root->fs_info->delalloc_lock);
			if (root->fs_info->dirty_metadata_bytes >= buf->len)
				root->fs_info->dirty_metadata_bytes -= buf->len;
			else
				WARN_ON(1);
			spin_unlock(&root->fs_info->delalloc_lock);
		}

		/* ugh, clear_extent_buffer_dirty needs to lock the page */
		btrfs_set_lock_blocking(buf);
		clear_extent_buffer_dirty(&BTRFS_I(btree_inode)->io_tree,
					  buf);
	}
	return 0;
}

static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
			u32 stripesize, struct btrfs_root *root,
			struct btrfs_fs_info *fs_info,
			u64 objectid)
{
	root->node = NULL;
	root->commit_root = NULL;
	root->sectorsize = sectorsize;
	root->nodesize = nodesize;
	root->leafsize = leafsize;
	root->stripesize = stripesize;
	root->ref_cows = 0;
	root->track_dirty = 0;
	root->in_radix = 0;
	root->orphan_item_inserted = 0;
	root->orphan_cleanup_state = 0;

	root->fs_info = fs_info;
	root->objectid = objectid;
	root->last_trans = 0;
	root->highest_objectid = 0;
	root->name = NULL;
	root->inode_tree = RB_ROOT;
	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
	root->block_rsv = NULL;
	root->orphan_block_rsv = NULL;

	INIT_LIST_HEAD(&root->dirty_list);
	INIT_LIST_HEAD(&root->orphan_list);
	INIT_LIST_HEAD(&root->root_list);
	spin_lock_init(&root->orphan_lock);
	spin_lock_init(&root->inode_lock);
	spin_lock_init(&root->accounting_lock);
	mutex_init(&root->objectid_mutex);
	mutex_init(&root->log_mutex);
	init_waitqueue_head(&root->log_writer_wait);
	init_waitqueue_head(&root->log_commit_wait[0]);
	init_waitqueue_head(&root->log_commit_wait[1]);
	atomic_set(&root->log_commit[0], 0);
	atomic_set(&root->log_commit[1], 0);
	atomic_set(&root->log_writers, 0);
	root->log_batch = 0;
	root->log_transid = 0;
	root->last_log_commit = 0;
	extent_io_tree_init(&root->dirty_log_pages,
			     fs_info->btree_inode->i_mapping);

	memset(&root->root_key, 0, sizeof(root->root_key));
	memset(&root->root_item, 0, sizeof(root->root_item));
	memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
	memset(&root->root_kobj, 0, sizeof(root->root_kobj));
	root->defrag_trans_start = fs_info->generation;
	init_completion(&root->kobj_unregister);
	root->defrag_running = 0;
	root->root_key.objectid = objectid;
	root->anon_dev = 0;
	return 0;
}

static int find_and_setup_root(struct btrfs_root *tree_root,
			       struct btrfs_fs_info *fs_info,
			       u64 objectid,
			       struct btrfs_root *root)
{
	int ret;
	u32 blocksize;
	u64 generation;

	__setup_root(tree_root->nodesize, tree_root->leafsize,
		     tree_root->sectorsize, tree_root->stripesize,
		     root, fs_info, objectid);
	ret = btrfs_find_last_root(tree_root, objectid,
				   &root->root_item, &root->root_key);
	if (ret > 0)
		return -ENOENT;
	BUG_ON(ret);

	generation = btrfs_root_generation(&root->root_item);
	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
				     blocksize, generation);
	if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) {
		free_extent_buffer(root->node);
		return -EIO;
	}
	root->commit_root = btrfs_root_node(root);
	return 0;
}

static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
					 struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct extent_buffer *leaf;

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

	__setup_root(tree_root->nodesize, tree_root->leafsize,
		     tree_root->sectorsize, tree_root->stripesize,
		     root, fs_info, BTRFS_TREE_LOG_OBJECTID);

	root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
	root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
	/*
	 * log trees do not get reference counted because they go away
	 * before a real commit is actually done.  They do store pointers
	 * to file data extents, and those reference counts still get
	 * updated (along with back refs to the log tree).
	 */
	root->ref_cows = 0;

	leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
				      BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0);
	if (IS_ERR(leaf)) {
		kfree(root);
		return ERR_CAST(leaf);
	}

	memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
	btrfs_set_header_bytenr(leaf, leaf->start);
	btrfs_set_header_generation(leaf, trans->transid);
	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
	btrfs_set_header_owner(leaf, BTRFS_TREE_LOG_OBJECTID);
	root->node = leaf;

	write_extent_buffer(root->node, root->fs_info->fsid,
			    (unsigned long)btrfs_header_fsid(root->node),
			    BTRFS_FSID_SIZE);
	btrfs_mark_buffer_dirty(root->node);
	btrfs_tree_unlock(root->node);
	return root;
}

int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
			     struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *log_root;

	log_root = alloc_log_tree(trans, fs_info);
	if (IS_ERR(log_root))
		return PTR_ERR(log_root);
	WARN_ON(fs_info->log_root_tree);
	fs_info->log_root_tree = log_root;
	return 0;
}

int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
		       struct btrfs_root *root)
{
	struct btrfs_root *log_root;
	struct btrfs_inode_item *inode_item;

	log_root = alloc_log_tree(trans, root->fs_info);
	if (IS_ERR(log_root))
		return PTR_ERR(log_root);

	log_root->last_trans = trans->transid;
	log_root->root_key.offset = root->root_key.objectid;

	inode_item = &log_root->root_item.inode;
	inode_item->generation = cpu_to_le64(1);
	inode_item->size = cpu_to_le64(3);
	inode_item->nlink = cpu_to_le32(1);
	inode_item->nbytes = cpu_to_le64(root->leafsize);
	inode_item->mode = cpu_to_le32(S_IFDIR | 0755);

	btrfs_set_root_node(&log_root->root_item, log_root->node);

	WARN_ON(root->log_root);
	root->log_root = log_root;
	root->log_transid = 0;
	root->last_log_commit = 0;
	return 0;
}

struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
					       struct btrfs_key *location)
{
	struct btrfs_root *root;
	struct btrfs_fs_info *fs_info = tree_root->fs_info;
	struct btrfs_path *path;
	struct extent_buffer *l;
	u64 generation;
	u32 blocksize;
	int ret = 0;

	root = kzalloc(sizeof(*root), GFP_NOFS);
	if (!root)
		return ERR_PTR(-ENOMEM);
	if (location->offset == (u64)-1) {
		ret = find_and_setup_root(tree_root, fs_info,
					  location->objectid, root);
		if (ret) {
			kfree(root);
			return ERR_PTR(ret);
		}
		goto out;
	}

	__setup_root(tree_root->nodesize, tree_root->leafsize,
		     tree_root->sectorsize, tree_root->stripesize,
		     root, fs_info, location->objectid);

	path = btrfs_alloc_path();
	if (!path) {
		kfree(root);
		return ERR_PTR(-ENOMEM);
	}
	ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0);
	if (ret == 0) {
		l = path->nodes[0];
		read_extent_buffer(l, &root->root_item,
				btrfs_item_ptr_offset(l, path->slots[0]),
				sizeof(root->root_item));
		memcpy(&root->root_key, location, sizeof(*location));
	}
	btrfs_free_path(path);
	if (ret) {
		kfree(root);
		if (ret > 0)
			ret = -ENOENT;
		return ERR_PTR(ret);
	}

	generation = btrfs_root_generation(&root->root_item);
	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
				     blocksize, generation);
	root->commit_root = btrfs_root_node(root);
	BUG_ON(!root->node);
out:
	if (location->objectid != BTRFS_TREE_LOG_OBJECTID) {
		root->ref_cows = 1;
		btrfs_check_and_init_root_item(&root->root_item);
	}

	return root;
}

struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
					      struct btrfs_key *location)
{
	struct btrfs_root *root;
	int ret;

	if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
		return fs_info->tree_root;
	if (location->objectid == BTRFS_EXTENT_TREE_OBJECTID)
		return fs_info->extent_root;
	if (location->objectid == BTRFS_CHUNK_TREE_OBJECTID)
		return fs_info->chunk_root;
	if (location->objectid == BTRFS_DEV_TREE_OBJECTID)
		return fs_info->dev_root;
	if (location->objectid == BTRFS_CSUM_TREE_OBJECTID)
		return fs_info->csum_root;
again:
	spin_lock(&fs_info->fs_roots_radix_lock);
	root = radix_tree_lookup(&fs_info->fs_roots_radix,
				 (unsigned long)location->objectid);
	spin_unlock(&fs_info->fs_roots_radix_lock);
	if (root)
		return root;

	root = btrfs_read_fs_root_no_radix(fs_info->tree_root, location);
	if (IS_ERR(root))
		return root;

	root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
	root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
					GFP_NOFS);
	if (!root->free_ino_pinned || !root->free_ino_ctl) {
		ret = -ENOMEM;
		goto fail;
	}

	btrfs_init_free_ino_ctl(root);
	mutex_init(&root->fs_commit_mutex);
	spin_lock_init(&root->cache_lock);
	init_waitqueue_head(&root->cache_wait);

	ret = get_anon_bdev(&root->anon_dev);
	if (ret)
		goto fail;

	if (btrfs_root_refs(&root->root_item) == 0) {
		ret = -ENOENT;
		goto fail;
	}

	ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid);
	if (ret < 0)
		goto fail;
	if (ret == 0)
		root->orphan_item_inserted = 1;

	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
	if (ret)
		goto fail;

	spin_lock(&fs_info->fs_roots_radix_lock);
	ret = radix_tree_insert(&fs_info->fs_roots_radix,
				(unsigned long)root->root_key.objectid,
				root);
	if (ret == 0)
		root->in_radix = 1;

	spin_unlock(&fs_info->fs_roots_radix_lock);
	radix_tree_preload_end();
	if (ret) {
		if (ret == -EEXIST) {
			free_fs_root(root);
			goto again;
		}
		goto fail;
	}

	ret = btrfs_find_dead_roots(fs_info->tree_root,
				    root->root_key.objectid);
	WARN_ON(ret);
	return root;
fail:
	free_fs_root(root);
	return ERR_PTR(ret);
}

static int btrfs_congested_fn(void *congested_data, int bdi_bits)
{
	struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
	int ret = 0;
	struct btrfs_device *device;
	struct backing_dev_info *bdi;

	rcu_read_lock();
	list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
		if (!device->bdev)
			continue;
		bdi = blk_get_backing_dev_info(device->bdev);
		if (bdi && bdi_congested(bdi, bdi_bits)) {
			ret = 1;
			break;
		}
	}
	rcu_read_unlock();
	return ret;
}

/*
 * If this fails, caller must call bdi_destroy() to get rid of the
 * bdi again.
 */
static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
{
	int err;

	bdi->capabilities = BDI_CAP_MAP_COPY;
	err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY);
	if (err)
		return err;

	bdi->ra_pages	= default_backing_dev_info.ra_pages;
	bdi->congested_fn	= btrfs_congested_fn;
	bdi->congested_data	= info;
	return 0;
}

static int bio_ready_for_csum(struct bio *bio)
{
	u64 length = 0;
	u64 buf_len = 0;
	u64 start = 0;
	struct page *page;
	struct extent_io_tree *io_tree = NULL;
	struct bio_vec *bvec;
	int i;
	int ret;

	bio_for_each_segment(bvec, bio, i) {
		page = bvec->bv_page;
		if (page->private == EXTENT_PAGE_PRIVATE) {
			length += bvec->bv_len;
			continue;
		}
		if (!page->private) {
			length += bvec->bv_len;
			continue;
		}
		length = bvec->bv_len;
		buf_len = page->private >> 2;
		start = page_offset(page) + bvec->bv_offset;
		io_tree = &BTRFS_I(page->mapping->host)->io_tree;
	}
	/* are we fully contained in this bio? */
	if (buf_len <= length)
		return 1;

	ret = extent_range_uptodate(io_tree, start + length,
				    start + buf_len - 1);
	return ret;
}

/*
 * called by the kthread helper functions to finally call the bio end_io
 * functions.  This is where read checksum verification actually happens
 */
static void end_workqueue_fn(struct btrfs_work *work)
{
	struct bio *bio;
	struct end_io_wq *end_io_wq;
	struct btrfs_fs_info *fs_info;
	int error;

	end_io_wq = container_of(work, struct end_io_wq, work);
	bio = end_io_wq->bio;
	fs_info = end_io_wq->info;

	/* metadata bio reads are special because the whole tree block must
	 * be checksummed at once.  This makes sure the entire block is in
	 * ram and up to date before trying to verify things.  For
	 * blocksize <= pagesize, it is basically a noop
	 */
	if (!(bio->bi_rw & REQ_WRITE) && end_io_wq->metadata &&
	    !bio_ready_for_csum(bio)) {
		btrfs_queue_worker(&fs_info->endio_meta_workers,
				   &end_io_wq->work);
		return;
	}
	error = end_io_wq->error;
	bio->bi_private = end_io_wq->private;
	bio->bi_end_io = end_io_wq->end_io;
	kfree(end_io_wq);
	bio_endio(bio, error);
}

static int cleaner_kthread(void *arg)
{
	struct btrfs_root *root = arg;

	do {
		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);

		if (!(root->fs_info->sb->s_flags & MS_RDONLY) &&
		    mutex_trylock(&root->fs_info->cleaner_mutex)) {
			btrfs_run_delayed_iputs(root);
			btrfs_clean_old_snapshots(root);
			mutex_unlock(&root->fs_info->cleaner_mutex);
			btrfs_run_defrag_inodes(root->fs_info);
		}

		if (freezing(current)) {
			refrigerator();
		} else {
			set_current_state(TASK_INTERRUPTIBLE);
			if (!kthread_should_stop())
				schedule();
			__set_current_state(TASK_RUNNING);
		}
	} while (!kthread_should_stop());
	return 0;
}

static int transaction_kthread(void *arg)
{
	struct btrfs_root *root = arg;
	struct btrfs_trans_handle *trans;
	struct btrfs_transaction *cur;
	u64 transid;
	unsigned long now;
	unsigned long delay;
	int ret;

	do {
		delay = HZ * 30;
		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
		mutex_lock(&root->fs_info->transaction_kthread_mutex);

		spin_lock(&root->fs_info->trans_lock);
		cur = root->fs_info->running_transaction;
		if (!cur) {
			spin_unlock(&root->fs_info->trans_lock);
			goto sleep;
		}

		now = get_seconds();
		if (!cur->blocked &&
		    (now < cur->start_time || now - cur->start_time < 30)) {
			spin_unlock(&root->fs_info->trans_lock);
			delay = HZ * 5;
			goto sleep;
		}
		transid = cur->transid;
		spin_unlock(&root->fs_info->trans_lock);

		trans = btrfs_join_transaction(root);
		BUG_ON(IS_ERR(trans));
		if (transid == trans->transid) {
			ret = btrfs_commit_transaction(trans, root);
			BUG_ON(ret);
		} else {
			btrfs_end_transaction(trans, root);
		}
sleep:
		wake_up_process(root->fs_info->cleaner_kthread);
		mutex_unlock(&root->fs_info->transaction_kthread_mutex);

		if (freezing(current)) {
			refrigerator();
		} else {
			set_current_state(TASK_INTERRUPTIBLE);
			if (!kthread_should_stop() &&
			    !btrfs_transaction_blocked(root->fs_info))
				schedule_timeout(delay);
			__set_current_state(TASK_RUNNING);
		}
	} while (!kthread_should_stop());
	return 0;
}

struct btrfs_root *open_ctree(struct super_block *sb,
			      struct btrfs_fs_devices *fs_devices,
			      char *options)
{
	u32 sectorsize;
	u32 nodesize;
	u32 leafsize;
	u32 blocksize;
	u32 stripesize;
	u64 generation;
	u64 features;
	struct btrfs_key location;
	struct buffer_head *bh;
	struct btrfs_root *extent_root = kzalloc(sizeof(struct btrfs_root),
						 GFP_NOFS);
	struct btrfs_root *csum_root = kzalloc(sizeof(struct btrfs_root),
						 GFP_NOFS);
	struct btrfs_root *tree_root = btrfs_sb(sb);
	struct btrfs_fs_info *fs_info = NULL;
	struct btrfs_root *chunk_root = kzalloc(sizeof(struct btrfs_root),
						GFP_NOFS);
	struct btrfs_root *dev_root = kzalloc(sizeof(struct btrfs_root),
					      GFP_NOFS);
	struct btrfs_root *log_tree_root;

	int ret;
	int err = -EINVAL;

	struct btrfs_super_block *disk_super;

	if (!extent_root || !tree_root || !tree_root->fs_info ||
	    !chunk_root || !dev_root || !csum_root) {
		err = -ENOMEM;
		goto fail;
	}
	fs_info = tree_root->fs_info;

	ret = init_srcu_struct(&fs_info->subvol_srcu);
	if (ret) {
		err = ret;
		goto fail;
	}

	ret = setup_bdi(fs_info, &fs_info->bdi);
	if (ret) {
		err = ret;
		goto fail_srcu;
	}

	fs_info->btree_inode = new_inode(sb);
	if (!fs_info->btree_inode) {
		err = -ENOMEM;
		goto fail_bdi;
	}

	mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);

	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
	INIT_LIST_HEAD(&fs_info->trans_list);
	INIT_LIST_HEAD(&fs_info->dead_roots);
	INIT_LIST_HEAD(&fs_info->delayed_iputs);
	INIT_LIST_HEAD(&fs_info->hashers);
	INIT_LIST_HEAD(&fs_info->delalloc_inodes);
	INIT_LIST_HEAD(&fs_info->ordered_operations);
	INIT_LIST_HEAD(&fs_info->caching_block_groups);
	spin_lock_init(&fs_info->delalloc_lock);
	spin_lock_init(&fs_info->trans_lock);
	spin_lock_init(&fs_info->ref_cache_lock);
	spin_lock_init(&fs_info->fs_roots_radix_lock);
	spin_lock_init(&fs_info->delayed_iput_lock);
	spin_lock_init(&fs_info->defrag_inodes_lock);
	mutex_init(&fs_info->reloc_mutex);

	init_completion(&fs_info->kobj_unregister);
	fs_info->tree_root = tree_root;
	fs_info->extent_root = extent_root;
	fs_info->csum_root = csum_root;
	fs_info->chunk_root = chunk_root;
	fs_info->dev_root = dev_root;
	fs_info->fs_devices = fs_devices;
	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
	INIT_LIST_HEAD(&fs_info->space_info);
	btrfs_mapping_init(&fs_info->mapping_tree);
	btrfs_init_block_rsv(&fs_info->global_block_rsv);
	btrfs_init_block_rsv(&fs_info->delalloc_block_rsv);
	btrfs_init_block_rsv(&fs_info->trans_block_rsv);
	btrfs_init_block_rsv(&fs_info->chunk_block_rsv);
	btrfs_init_block_rsv(&fs_info->empty_block_rsv);
	INIT_LIST_HEAD(&fs_info->durable_block_rsv_list);
	mutex_init(&fs_info->durable_block_rsv_mutex);
	atomic_set(&fs_info->nr_async_submits, 0);
	atomic_set(&fs_info->async_delalloc_pages, 0);
	atomic_set(&fs_info->async_submit_draining, 0);
	atomic_set(&fs_info->nr_async_bios, 0);
	atomic_set(&fs_info->defrag_running, 0);
	fs_info->sb = sb;
	fs_info->max_inline = 8192 * 1024;
	fs_info->metadata_ratio = 0;
	fs_info->defrag_inodes = RB_ROOT;
	fs_info->trans_no_join = 0;

	fs_info->thread_pool_size = min_t(unsigned long,
					  num_online_cpus() + 2, 8);

	INIT_LIST_HEAD(&fs_info->ordered_extents);
	spin_lock_init(&fs_info->ordered_extent_lock);
	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
					GFP_NOFS);
	if (!fs_info->delayed_root) {
		err = -ENOMEM;
		goto fail_iput;
	}
	btrfs_init_delayed_root(fs_info->delayed_root);

	mutex_init(&fs_info->scrub_lock);
	atomic_set(&fs_info->scrubs_running, 0);
	atomic_set(&fs_info->scrub_pause_req, 0);
	atomic_set(&fs_info->scrubs_paused, 0);
	atomic_set(&fs_info->scrub_cancel_req, 0);
	init_waitqueue_head(&fs_info->scrub_pause_wait);
	init_rwsem(&fs_info->scrub_super_lock);
	fs_info->scrub_workers_refcnt = 0;

	sb->s_blocksize = 4096;
	sb->s_blocksize_bits = blksize_bits(4096);
	sb->s_bdi = &fs_info->bdi;

	fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
	fs_info->btree_inode->i_nlink = 1;
	/*
	 * we set the i_size on the btree inode to the max possible int.
	 * the real end of the address space is determined by all of
	 * the devices in the system
	 */
	fs_info->btree_inode->i_size = OFFSET_MAX;
	fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
	fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;

	RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
	extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
			     fs_info->btree_inode->i_mapping);
	extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree);

	BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops;

	BTRFS_I(fs_info->btree_inode)->root = tree_root;
	memset(&BTRFS_I(fs_info->btree_inode)->location, 0,
	       sizeof(struct btrfs_key));
	BTRFS_I(fs_info->btree_inode)->dummy_inode = 1;
	insert_inode_hash(fs_info->btree_inode);

	spin_lock_init(&fs_info->block_group_cache_lock);
	fs_info->block_group_cache_tree = RB_ROOT;

	extent_io_tree_init(&fs_info->freed_extents[0],
			     fs_info->btree_inode->i_mapping);
	extent_io_tree_init(&fs_info->freed_extents[1],
			     fs_info->btree_inode->i_mapping);
	fs_info->pinned_extents = &fs_info->freed_extents[0];
	fs_info->do_barriers = 1;


	mutex_init(&fs_info->ordered_operations_mutex);
	mutex_init(&fs_info->tree_log_mutex);
	mutex_init(&fs_info->chunk_mutex);
	mutex_init(&fs_info->transaction_kthread_mutex);
	mutex_init(&fs_info->cleaner_mutex);
	mutex_init(&fs_info->volume_mutex);
	init_rwsem(&fs_info->extent_commit_sem);
	init_rwsem(&fs_info->cleanup_work_sem);
	init_rwsem(&fs_info->subvol_sem);

	btrfs_init_free_cluster(&fs_info->meta_alloc_cluster);
	btrfs_init_free_cluster(&fs_info->data_alloc_cluster);

	init_waitqueue_head(&fs_info->transaction_throttle);
	init_waitqueue_head(&fs_info->transaction_wait);
	init_waitqueue_head(&fs_info->transaction_blocked_wait);
	init_waitqueue_head(&fs_info->async_submit_wait);

	__setup_root(4096, 4096, 4096, 4096, tree_root,
		     fs_info, BTRFS_ROOT_TREE_OBJECTID);

	bh = btrfs_read_dev_super(fs_devices->latest_bdev);
	if (!bh) {
		err = -EINVAL;
		goto fail_alloc;
	}

	memcpy(&fs_info->super_copy, bh->b_data, sizeof(fs_info->super_copy));
	memcpy(&fs_info->super_for_commit, &fs_info->super_copy,
	       sizeof(fs_info->super_for_commit));
	brelse(bh);

	memcpy(fs_info->fsid, fs_info->super_copy.fsid, BTRFS_FSID_SIZE);

	disk_super = &fs_info->super_copy;
	if (!btrfs_super_root(disk_super))
		goto fail_alloc;

	/* check FS state, whether FS is broken. */
	fs_info->fs_state |= btrfs_super_flags(disk_super);

	btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);

	/*
	 * In the long term, we'll store the compression type in the super
	 * block, and it'll be used for per file compression control.
	 */
	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;

	ret = btrfs_parse_options(tree_root, options);
	if (ret) {
		err = ret;
		goto fail_alloc;
	}

	features = btrfs_super_incompat_flags(disk_super) &
		~BTRFS_FEATURE_INCOMPAT_SUPP;
	if (features) {
		printk(KERN_ERR "BTRFS: couldn't mount because of "
		       "unsupported optional features (%Lx).\n",
		       (unsigned long long)