fs/btrfs/disk-io.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
#include <linux/uuid.h>
#include <linux/semaphore.h>
#include <linux/error-injection.h>
#include <linux/crc32c.h>
#include <linux/sched/mm.h>
#include <asm/unaligned.h>
#include <crypto/hash.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "print-tree.h"
#include "locking.h"
#include "tree-log.h"
#include "free-space-cache.h"
#include "free-space-tree.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "raid56.h"
#include "sysfs.h"
#include "qgroup.h"
#include "compression.h"
#include "tree-checker.h"
#include "ref-verify.h"
#include "block-group.h"
#include "discard.h"
#include "space-info.h"
#include "zoned.h"
#include "subpage.h"

#define BTRFS_SUPER_FLAG_SUPP	(BTRFS_HEADER_FLAG_WRITTEN |\
				 BTRFS_HEADER_FLAG_RELOC |\
				 BTRFS_SUPER_FLAG_ERROR |\
				 BTRFS_SUPER_FLAG_SEEDING |\
				 BTRFS_SUPER_FLAG_METADUMP |\
				 BTRFS_SUPER_FLAG_METADUMP_V2)

static void end_workqueue_fn(struct btrfs_work *work);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
				      struct btrfs_fs_info *fs_info);
static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info,
					struct extent_io_tree *dirty_pages,
					int mark);
static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info,
				       struct extent_io_tree *pinned_extents);
static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info);
static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info);

/*
 * btrfs_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 btrfs_end_io_wq {
	struct bio *bio;
	bio_end_io_t *end_io;
	void *private;
	struct btrfs_fs_info *info;
	blk_status_t status;
	enum btrfs_wq_endio_type metadata;
	struct btrfs_work work;
};

static struct kmem_cache *btrfs_end_io_wq_cache;

int __init btrfs_end_io_wq_init(void)
{
	btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq",
					sizeof(struct btrfs_end_io_wq),
					0,
					SLAB_MEM_SPREAD,
					NULL);
	if (!btrfs_end_io_wq_cache)
		return -ENOMEM;
	return 0;
}

void __cold btrfs_end_io_wq_exit(void)
{
	kmem_cache_destroy(btrfs_end_io_wq_cache);
}

static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info)
{
	if (fs_info->csum_shash)
		crypto_free_shash(fs_info->csum_shash);
}

/*
 * 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;
	extent_submit_bio_start_t *submit_bio_start;
	int mirror_num;

	/* Optional parameter for submit_bio_start used by direct io */
	u64 dio_file_offset;
	struct btrfs_work work;
	blk_status_t status;
};

/*
 * 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->root_key.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

#define DEFINE_LEVEL(stem, level)					\
	.names[level] = "btrfs-" stem "-0" #level,

#define DEFINE_NAME(stem)						\
	DEFINE_LEVEL(stem, 0)						\
	DEFINE_LEVEL(stem, 1)						\
	DEFINE_LEVEL(stem, 2)						\
	DEFINE_LEVEL(stem, 3)						\
	DEFINE_LEVEL(stem, 4)						\
	DEFINE_LEVEL(stem, 5)						\
	DEFINE_LEVEL(stem, 6)						\
	DEFINE_LEVEL(stem, 7)

static struct btrfs_lockdep_keyset {
	u64			id;		/* root objectid */
	/* Longest entry: btrfs-free-space-00 */
	char			names[BTRFS_MAX_LEVEL][20];
	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
} btrfs_lockdep_keysets[] = {
	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
	{ .id = 0,				DEFINE_NAME("tree")	},
};

#undef DEFINE_LEVEL
#undef DEFINE_NAME

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

/*
 * Compute the csum of a btree block and store the result to provided buffer.
 */
static void csum_tree_block(struct extent_buffer *buf, u8 *result)
{
	struct btrfs_fs_info *fs_info = buf->fs_info;
	const int num_pages = num_extent_pages(buf);
	const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize);
	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
	char *kaddr;
	int i;

	shash->tfm = fs_info->csum_shash;
	crypto_shash_init(shash);
	kaddr = page_address(buf->pages[0]) + offset_in_page(buf->start);
	crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE,
			    first_page_part - BTRFS_CSUM_SIZE);

	for (i = 1; i < num_pages; i++) {
		kaddr = page_address(buf->pages[i]);
		crypto_shash_update(shash, kaddr, PAGE_SIZE);
	}
	memset(result, 0, BTRFS_CSUM_SIZE);
	crypto_shash_final(shash, result);
}

/*
 * 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,
				 int atomic)
{
	struct extent_state *cached_state = NULL;
	int ret;

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

	if (atomic)
		return -EAGAIN;

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

static bool btrfs_supported_super_csum(u16 csum_type)
{
	switch (csum_type) {
	case BTRFS_CSUM_TYPE_CRC32:
	case BTRFS_CSUM_TYPE_XXHASH:
	case BTRFS_CSUM_TYPE_SHA256:
	case BTRFS_CSUM_TYPE_BLAKE2:
		return true;
	default:
		return false;
	}
}

/*
 * Return 0 if the superblock checksum type matches the checksum value of that
 * algorithm. Pass the raw disk superblock data.
 */
static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
				  char *raw_disk_sb)
{
	struct btrfs_super_block *disk_sb =
		(struct btrfs_super_block *)raw_disk_sb;
	char result[BTRFS_CSUM_SIZE];
	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);

	shash->tfm = fs_info->csum_shash;

	/*
	 * The super_block structure does not span the whole
	 * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is
	 * filled with zeros and is included in the checksum.
	 */
	crypto_shash_digest(shash, raw_disk_sb + BTRFS_CSUM_SIZE,
			    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result);

	if (memcmp(disk_sb->csum, result, fs_info->csum_size))
		return 1;

	return 0;
}

int btrfs_verify_level_key(struct extent_buffer *eb, int level,
			   struct btrfs_key *first_key, u64 parent_transid)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	int found_level;
	struct btrfs_key found_key;
	int ret;

	found_level = btrfs_header_level(eb);
	if (found_level != level) {
		WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
		     KERN_ERR "BTRFS: tree level check failed\n");
		btrfs_err(fs_info,
"tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
			  eb->start, level, found_level);
		return -EIO;
	}

	if (!first_key)
		return 0;

	/*
	 * For live tree block (new tree blocks in current transaction),
	 * we need proper lock context to avoid race, which is impossible here.
	 * So we only checks tree blocks which is read from disk, whose
	 * generation <= fs_info->last_trans_committed.
	 */
	if (btrfs_header_generation(eb) > fs_info->last_trans_committed)
		return 0;

	/* We have @first_key, so this @eb must have at least one item */
	if (btrfs_header_nritems(eb) == 0) {
		btrfs_err(fs_info,
		"invalid tree nritems, bytenr=%llu nritems=0 expect >0",
			  eb->start);
		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
		return -EUCLEAN;
	}

	if (found_level)
		btrfs_node_key_to_cpu(eb, &found_key, 0);
	else
		btrfs_item_key_to_cpu(eb, &found_key, 0);
	ret = btrfs_comp_cpu_keys(first_key, &found_key);

	if (ret) {
		WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
		     KERN_ERR "BTRFS: tree first key check failed\n");
		btrfs_err(fs_info,
"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)",
			  eb->start, parent_transid, first_key->objectid,
			  first_key->type, first_key->offset,
			  found_key.objectid, found_key.type,
			  found_key.offset);
	}
	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.
 *
 * @parent_transid:	expected transid, skip check if 0
 * @level:		expected level, mandatory check
 * @first_key:		expected key of first slot, skip check if NULL
 */
static int btree_read_extent_buffer_pages(struct extent_buffer *eb,
					  u64 parent_transid, int level,
					  struct btrfs_key *first_key)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	struct extent_io_tree *io_tree;
	int failed = 0;
	int ret;
	int num_copies = 0;
	int mirror_num = 0;
	int failed_mirror = 0;

	io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
	while (1) {
		clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
		ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num);
		if (!ret) {
			if (verify_parent_transid(io_tree, eb,
						   parent_transid, 0))
				ret = -EIO;
			else if (btrfs_verify_level_key(eb, level,
						first_key, parent_transid))
				ret = -EUCLEAN;
			else
				break;
		}

		num_copies = btrfs_num_copies(fs_info,
					      eb->start, eb->len);
		if (num_copies == 1)
			break;

		if (!failed_mirror) {
			failed = 1;
			failed_mirror = eb->read_mirror;
		}

		mirror_num++;
		if (mirror_num == failed_mirror)
			mirror_num++;

		if (mirror_num > num_copies)
			break;
	}

	if (failed && !ret && failed_mirror)
		btrfs_repair_eb_io_failure(eb, failed_mirror);

	return ret;
}

static int csum_one_extent_buffer(struct extent_buffer *eb)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	u8 result[BTRFS_CSUM_SIZE];
	int ret;

	ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
				    offsetof(struct btrfs_header, fsid),
				    BTRFS_FSID_SIZE) == 0);
	csum_tree_block(eb, result);

	if (btrfs_header_level(eb))
		ret = btrfs_check_node(eb);
	else
		ret = btrfs_check_leaf_full(eb);

	if (ret < 0) {
		btrfs_print_tree(eb, 0);
		btrfs_err(fs_info,
			"block=%llu write time tree block corruption detected",
			eb->start);
		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
		return ret;
	}
	write_extent_buffer(eb, result, 0, fs_info->csum_size);

	return 0;
}

/* Checksum all dirty extent buffers in one bio_vec */
static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info,
				      struct bio_vec *bvec)
{
	struct page *page = bvec->bv_page;
	u64 bvec_start = page_offset(page) + bvec->bv_offset;
	u64 cur;
	int ret = 0;

	for (cur = bvec_start; cur < bvec_start + bvec->bv_len;
	     cur += fs_info->nodesize) {
		struct extent_buffer *eb;
		bool uptodate;

		eb = find_extent_buffer(fs_info, cur);
		uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur,
						       fs_info->nodesize);

		/* A dirty eb shouldn't disappear from buffer_radix */
		if (WARN_ON(!eb))
			return -EUCLEAN;

		if (WARN_ON(cur != btrfs_header_bytenr(eb))) {
			free_extent_buffer(eb);
			return -EUCLEAN;
		}
		if (WARN_ON(!uptodate)) {
			free_extent_buffer(eb);
			return -EUCLEAN;
		}

		ret = csum_one_extent_buffer(eb);
		free_extent_buffer(eb);
		if (ret < 0)
			return ret;
	}
	return ret;
}

/*
 * 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.
 * For subpage extent buffers we need bvec to also read the offset in the page.
 */
static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec)
{
	struct page *page = bvec->bv_page;
	u64 start = page_offset(page);
	u64 found_start;
	struct extent_buffer *eb;

	if (fs_info->sectorsize < PAGE_SIZE)
		return csum_dirty_subpage_buffers(fs_info, bvec);

	eb = (struct extent_buffer *)page->private;
	if (page != eb->pages[0])
		return 0;

	found_start = btrfs_header_bytenr(eb);

	if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) {
		WARN_ON(found_start != 0);
		return 0;
	}

	/*
	 * Please do not consolidate these warnings into a single if.
	 * It is useful to know what went wrong.
	 */
	if (WARN_ON(found_start != start))
		return -EUCLEAN;
	if (WARN_ON(!PageUptodate(page)))
		return -EUCLEAN;

	return csum_one_extent_buffer(eb);
}

static int check_tree_block_fsid(struct extent_buffer *eb)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs;
	u8 fsid[BTRFS_FSID_SIZE];
	u8 *metadata_uuid;

	read_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid),
			   BTRFS_FSID_SIZE);
	/*
	 * Checking the incompat flag is only valid for the current fs. For
	 * seed devices it's forbidden to have their uuid changed so reading
	 * ->fsid in this case is fine
	 */
	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
		metadata_uuid = fs_devices->metadata_uuid;
	else
		metadata_uuid = fs_devices->fsid;

	if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE))
		return 0;

	list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list)
		if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE))
			return 0;

	return 1;
}

/* Do basic extent buffer checks at read time */
static int validate_extent_buffer(struct extent_buffer *eb)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	u64 found_start;
	const u32 csum_size = fs_info->csum_size;
	u8 found_level;
	u8 result[BTRFS_CSUM_SIZE];
	const u8 *header_csum;
	int ret = 0;

	found_start = btrfs_header_bytenr(eb);
	if (found_start != eb->start) {
		btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu",
			     eb->start, found_start);
		ret = -EIO;
		goto out;
	}
	if (check_tree_block_fsid(eb)) {
		btrfs_err_rl(fs_info, "bad fsid on block %llu",
			     eb->start);
		ret = -EIO;
		goto out;
	}
	found_level = btrfs_header_level(eb);
	if (found_level >= BTRFS_MAX_LEVEL) {
		btrfs_err(fs_info, "bad tree block level %d on %llu",
			  (int)btrfs_header_level(eb), eb->start);
		ret = -EIO;
		goto out;
	}

	csum_tree_block(eb, result);
	header_csum = page_address(eb->pages[0]) +
		get_eb_offset_in_page(eb, offsetof(struct btrfs_header, csum));

	if (memcmp(result, header_csum, csum_size) != 0) {
		btrfs_warn_rl(fs_info,
	"checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d",
			      eb->start,
			      CSUM_FMT_VALUE(csum_size, header_csum),
			      CSUM_FMT_VALUE(csum_size, result),
			      btrfs_header_level(eb));
		ret = -EUCLEAN;
		goto out;
	}

	/*
	 * 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 && btrfs_check_leaf_full(eb)) {
		set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
		ret = -EIO;
	}

	if (found_level > 0 && btrfs_check_node(eb))
		ret = -EIO;

	if (!ret)
		set_extent_buffer_uptodate(eb);
	else
		btrfs_err(fs_info,
			  "block=%llu read time tree block corruption detected",
			  eb->start);
out:
	return ret;
}

static int validate_subpage_buffer(struct page *page, u64 start, u64 end,
				   int mirror)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
	struct extent_buffer *eb;
	bool reads_done;
	int ret = 0;

	/*
	 * We don't allow bio merge for subpage metadata read, so we should
	 * only get one eb for each endio hook.
	 */
	ASSERT(end == start + fs_info->nodesize - 1);
	ASSERT(PagePrivate(page));

	eb = find_extent_buffer(fs_info, start);
	/*
	 * When we are reading one tree block, eb must have been inserted into
	 * the radix tree. If not, something is wrong.
	 */
	ASSERT(eb);

	reads_done = atomic_dec_and_test(&eb->io_pages);
	/* Subpage read must finish in page read */
	ASSERT(reads_done);

	eb->read_mirror = mirror;
	if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
		ret = -EIO;
		goto err;
	}
	ret = validate_extent_buffer(eb);
	if (ret < 0)
		goto err;

	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
		btree_readahead_hook(eb, ret);

	set_extent_buffer_uptodate(eb);

	free_extent_buffer(eb);
	return ret;
err:
	/*
	 * end_bio_extent_readpage decrements io_pages in case of error,
	 * make sure it has something to decrement.
	 */
	atomic_inc(&eb->io_pages);
	clear_extent_buffer_uptodate(eb);
	free_extent_buffer(eb);
	return ret;
}

int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio,
				   struct page *page, u64 start, u64 end,
				   int mirror)
{
	struct extent_buffer *eb;
	int ret = 0;
	int reads_done;

	ASSERT(page->private);

	if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE)
		return validate_subpage_buffer(page, start, end, mirror);

	eb = (struct extent_buffer *)page->private;

	/*
	 * The pending IO might have been the only thing that kept this buffer
	 * in memory.  Make sure we have a ref for all this other checks
	 */
	atomic_inc(&eb->refs);

	reads_done = atomic_dec_and_test(&eb->io_pages);
	if (!reads_done)
		goto err;

	eb->read_mirror = mirror;
	if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
		ret = -EIO;
		goto err;
	}
	ret = validate_extent_buffer(eb);
err:
	if (reads_done &&
	    test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
		btree_readahead_hook(eb, ret);

	if (ret) {
		/*
		 * our io error hook is going to dec the io pages
		 * again, we have to make sure it has something
		 * to decrement
		 */
		atomic_inc(&eb->io_pages);
		clear_extent_buffer_uptodate(eb);
	}
	free_extent_buffer(eb);

	return ret;
}

static void end_workqueue_bio(struct bio *bio)
{
	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
	struct btrfs_fs_info *fs_info;
	struct btrfs_workqueue *wq;

	fs_info = end_io_wq->info;
	end_io_wq->status = bio->bi_status;

	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
			wq = fs_info->endio_meta_write_workers;
		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
			wq = fs_info->endio_freespace_worker;
		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
			wq = fs_info->endio_raid56_workers;
		else
			wq = fs_info->endio_write_workers;
	} else {
		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
			wq = fs_info->endio_raid56_workers;
		else if (end_io_wq->metadata)
			wq = fs_info->endio_meta_workers;
		else
			wq = fs_info->endio_workers;
	}

	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
	btrfs_queue_work(wq, &end_io_wq->work);
}

blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
			enum btrfs_wq_endio_type metadata)
{
	struct btrfs_end_io_wq *end_io_wq;

	end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
	if (!end_io_wq)
		return BLK_STS_RESOURCE;

	end_io_wq->private = bio->bi_private;
	end_io_wq->end_io = bio->bi_end_io;
	end_io_wq->info = info;
	end_io_wq->status = 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;
}

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

	async = container_of(work, struct  async_submit_bio, work);
	ret = async->submit_bio_start(async->inode, async->bio,
				      async->dio_file_offset);
	if (ret)
		async->status = ret;
}

/*
 * In order to insert checksums into the metadata in large chunks, we wait
 * until bio submission time.   All the pages in the bio are checksummed and
 * sums are attached onto the ordered extent record.
 *
 * At IO completion time the csums attached on the ordered extent record are
 * inserted into the tree.
 */
static void run_one_async_done(struct btrfs_work *work)
{
	struct async_submit_bio *async;
	struct inode *inode;
	blk_status_t ret;

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

	/* If an error occurred we just want to clean up the bio and move on */
	if (async->status) {
		async->bio->bi_status = async->status;
		bio_endio(async->bio);
		return;
	}

	/*
	 * All of the bios that pass through here are from async helpers.
	 * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
	 * This changes nothing when cgroups aren't in use.
	 */
	async->bio->bi_opf |= REQ_CGROUP_PUNT;
	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);
	if (ret) {
		async->bio->bi_status = ret;
		bio_endio(async->bio);
	}
}

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);
}

blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio,
				 int mirror_num, unsigned long bio_flags,
				 u64 dio_file_offset,
				 extent_submit_bio_start_t *submit_bio_start)
{
	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
	struct async_submit_bio *async;

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

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

	btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
			run_one_async_free);

	async->dio_file_offset = dio_file_offset;

	async->status = 0;

	if (op_is_sync(bio->bi_opf))
		btrfs_set_work_high_priority(&async->work);

	btrfs_queue_work(fs_info->workers, &async->work);
	return 0;
}

static blk_status_t btree_csum_one_bio(struct bio *bio)
{
	struct bio_vec *bvec;
	struct btrfs_root *root;
	int ret = 0;
	struct bvec_iter_all iter_all;

	ASSERT(!bio_flagged(bio, BIO_CLONED));
	bio_for_each_segment_all(bvec, bio, iter_all) {
		root = BTRFS_I(bvec->bv_page->mapping->host)->root;
		ret = csum_dirty_buffer(root->fs_info, bvec);
		if (ret)
			break;
	}

	return errno_to_blk_status(ret);
}

static blk_status_t btree_submit_bio_start(struct inode *inode, struct bio *bio,
					   u64 dio_file_offset)
{
	/*
	 * when we're called for a write, we're already in the async
	 * submission context.  Just jump into btrfs_map_bio
	 */
	return btree_csum_one_bio(bio);
}

static bool should_async_write(struct btrfs_fs_info *fs_info,
			     struct btrfs_inode *bi)
{
	if (btrfs_is_zoned(fs_info))
		return false;
	if (atomic_read(&bi->sync_writers))
		return false;
	if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
		return false;
	return true;
}

blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio,
				       int mirror_num, unsigned long bio_flags)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	blk_status_t ret;

	if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
		/*
		 * called for a read, do the setup so that checksum validation
		 * can happen in the async kernel threads
		 */
		ret = btrfs_bio_wq_end_io(fs_info, bio,
					  BTRFS_WQ_ENDIO_METADATA);
		if (ret)
			goto out_w_error;
		ret = btrfs_map_bio(fs_info, bio, mirror_num);
	} else if (!should_async_write(fs_info, BTRFS_I(inode))) {
		ret = btree_csum_one_bio(bio);
		if (ret)
			goto out_w_error;
		ret = btrfs_map_bio(fs_info, bio, mirror_num);
	} else {
		/*
		 * kthread helpers are used to submit writes so that
		 * checksumming can happen in parallel across all CPUs
		 */
		ret = btrfs_wq_submit_bio(inode, bio, mirror_num, 0,
					  0, btree_submit_bio_start);
	}

	if (ret)
		goto out_w_error;
	return 0;

out_w_error:
	bio->bi_status = ret;
	bio_endio(bio);
	return ret;
}

#ifdef CONFIG_MIGRATION
static int btree_migratepage(struct address_space *mapping,
			struct page *newpage, struct page *page,
			enum migrate_mode mode)
{
	/*
	 * 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, mode);
}
#endif


static int btree_writepages(struct address_space *mapping,
			    struct writeback_control *wbc)
{
	struct btrfs_fs_info *fs_info;
	int ret;

	if (wbc->sync_mode == WB_SYNC_NONE) {

		if (wbc->for_kupdate)
			return 0;

		fs_info = BTRFS_I(mapping->host)->root->fs_info;
		/* this is a bit racy, but that's ok */
		ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
					     BTRFS_DIRTY_METADATA_THRESH,
					     fs_info->dirty_metadata_batch);
		if (ret < 0)
			return 0;
	}
	return btree_write_cache_pages(mapping, wbc);
}

static int btree_releasepage(struct page *page, gfp_t gfp_flags)
{
	if (PageWriteback(page) || PageDirty(page))
		return 0;

	return try_release_extent_buffer(page);
}

static void btree_invalidatepage(struct page *page, unsigned int offset,
				 unsigned int length)
{
	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)) {
		btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info,
			   "page private not zero on page %llu",
			   (unsigned long long)page_offset(page));
		detach_page_private(page);
	}
}

static int btree_set_page_dirty(struct page *page)
{
#ifdef DEBUG
	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
	struct btrfs_subpage *subpage;
	struct extent_buffer *eb;
	int cur_bit = 0;
	u64 page_start = page_offset(page);

	if (fs_info->sectorsize == PAGE_SIZE) {
		BUG_ON(!PagePrivate(page));
		eb = (struct extent_buffer *)page->private;
		BUG_ON(!eb);
		BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
		BUG_ON(!atomic_read(&eb->refs));
		btrfs_assert_tree_write_locked(eb);
		return __set_page_dirty_nobuffers(page);
	}
	ASSERT(PagePrivate(page) && page->private);
	subpage = (struct btrfs_subpage *)page->private;

	ASSERT(subpage->dirty_bitmap);
	while (cur_bit < BTRFS_SUBPAGE_BITMAP_SIZE) {
		unsigned long flags;
		u64 cur;
		u16 tmp = (1 << cur_bit);

		spin_lock_irqsave(&subpage->lock, flags);
		if (!(tmp & subpage->dirty_bitmap)) {
			spin_unlock_irqrestore(&subpage->lock, flags);
			cur_bit++;
			continue;
		}
		spin_unlock_irqrestore(&subpage->lock, flags);
		cur = page_start + cur_bit * fs_info->sectorsize;

		eb = find_extent_buffer(fs_info, cur);
		ASSERT(eb);
		ASSERT(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
		ASSERT(atomic_read(&eb->refs));
		btrfs_assert_tree_write_locked(eb);
		free_extent_buffer(eb);

		cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits);
	}
#endif
	return __set_page_dirty_nobuffers(page);
}

static const struct address_space_operations btree_aops = {
	.writepages	= btree_writepages,
	.releasepage	= btree_releasepage,
	.invalidatepage = btree_invalidatepage,
#ifdef CONFIG_MIGRATION
	.migratepage	= btree_migratepage,
#endif
	.set_page_dirty = btree_set_page_dirty,
};

struct extent_buffer *btrfs_find_create_tree_block(
						struct btrfs_fs_info *fs_info,
						u64 bytenr, u64 owner_root,
						int level)
{
	if (btrfs_is_testing(fs_info))
		return alloc_test_extent_buffer(fs_info, bytenr);
	return alloc_extent_buffer(fs_info, bytenr, owner_root, level);
}

/*
 * Read tree block at logical address @bytenr and do variant basic but critical
 * verification.
 *
 * @owner_root:		the objectid of the root owner for this block.
 * @parent_transid:	expected transid of this tree block, skip check if 0
 * @level:		expected level, mandatory check
 * @first_key:		expected key in slot 0, skip check if NULL
 */
struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
				      u64 owner_root, u64 parent_transid,
				      int level, struct btrfs_key *first_key)
{
	struct extent_buffer *buf = NULL;
	int ret;

	buf = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level);
	if (IS_ERR(buf))
		return buf;

	ret = btree_read_extent_buffer_pages(buf, parent_transid,
					     level, first_key);
	if (ret) {
		free_extent_buffer_stale(buf);
		return ERR_PTR(ret);
	}
	return buf;

}

void btrfs_clean_tree_block(struct extent_buffer *buf)
{
	struct btrfs_fs_info *fs_info = buf->fs_info;
	if (btrfs_header_generation(buf) ==
	    fs_info->running_transaction->transid) {
		btrfs_assert_tree_write_locked(buf);

		if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
			percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
						 -buf->len,
						 fs_info->dirty_metadata_batch);
			clear_extent_buffer_dirty(buf);
		}
	}
}

static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
			 u64 objectid)
{
	bool dummy = test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
	root->fs_info = fs_info;
	root->node = NULL;
	root->commit_root = NULL;
	root->state = 0;
	root->orphan_cleanup_state = 0;

	root->last_trans = 0;
	root->free_objectid = 0;
	root->nr_delalloc_inodes = 0;
	root->nr_ordered_extents = 0;
	root->inode_tree = RB_ROOT;
	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
	root->block_rsv = NULL;

	INIT_LIST_HEAD(&root->dirty_list);
	INIT_LIST_HEAD(&root->root_list);
	INIT_LIST_HEAD(&root->delalloc_inodes);
	INIT_LIST_HEAD(&root->delalloc_root);
	INIT_LIST_HEAD(&root->ordered_extents);
	INIT_LIST_HEAD(&root->ordered_root);
	INIT_LIST_HEAD(&root->reloc_dirty_list);
	INIT_LIST_HEAD(&root->logged_list[0]);
	INIT_LIST_HEAD(&root->logged_list[1]);
	spin_lock_init(&root->inode_lock);
	spin_lock_init(&root->delalloc_lock);
	spin_lock_init(&root->ordered_extent_lock);
	spin_lock_init(&root->accounting_lock);
	spin_lock_init(&root->log_extents_lock[0]);
	spin_lock_init(&root->log_extents_lock[1]);
	spin_lock_init(&root->qgroup_meta_rsv_lock);
	mutex_init(&root->objectid_mutex);
	mutex_init(&root->log_mutex);
	mutex_init(&root->ordered_extent_mutex);
	mutex_init(&root->delalloc_mutex);
	init_waitqueue_head(&root->qgroup_flush_wait);
	init_waitqueue_head(&root->log_writer_wait);
	init_waitqueue_head(&root->log_commit_wait[0]);
	init_waitqueue_head(&root->log_commit_wait[1]);
	INIT_LIST_HEAD(&root->log_ctxs[0]);
	INIT_LIST_HEAD(&root->log_ctxs[1]);
	atomic_set(&root->log_commit[0], 0);
	atomic_set(&root->log_commit[1], 0);
	atomic_set(&root->log_writers, 0);
	atomic_set(&root->log_batch, 0);
	refcount_set(&root->refs, 1);
	atomic_set(&root->snapshot_force_cow, 0);
	atomic_set(&root->nr_swapfiles, 0);
	root->log_transid = 0;
	root->log_transid_committed = -1;
	root->last_log_commit = 0;
	if (!dummy) {
		extent_io_tree_init(fs_info, &root->dirty_log_pages,
				    IO_TREE_ROOT_DIRTY_LOG_PAGES, NULL);
		extent_io_tree_init(fs_info, &root->log_csum_range,
				    IO_TREE_LOG_CSUM_RANGE, NULL);
	}

	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));
	root->root_key.objectid = objectid;
	root->anon_dev = 0;

	spin_lock_init(&root->root_item_lock);
	btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks);
#ifdef CONFIG_BTRFS_DEBUG
	INIT_LIST_HEAD(&root->leak_list);
	spin_lock(&fs_info->fs_roots_radix_lock);
	list_add_tail(&root->leak_list, &fs_info->allocated_roots);
	spin_unlock(&fs_info->fs_roots_radix_lock);
#endif
}

static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
					   u64 objectid, gfp_t flags)
{
	struct btrfs_root *root = kzalloc(sizeof(*root), flags);
	if (root)
		__setup_root(root, fs_info, objectid);
	return root;
}

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
/* Should only be used by the testing infrastructure */
struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;

	if (!fs_info)
		return ERR_PTR(-EINVAL);

	root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, GFP_KERNEL);
	if (!root)
		return ERR_PTR(-ENOMEM);

	/* We don't use the stripesize in selftest, set it as sectorsize */
	root->alloc_bytenr = 0;

	return root;
}
#endif

struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
				     u64 objectid)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct extent_buffer *leaf;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_root *root;
	struct btrfs_key key;
	unsigned int nofs_flag;
	int ret = 0;

	/*
	 * We're holding a transaction handle, so use a NOFS memory allocation
	 * context to avoid deadlock if reclaim happens.
	 */
	nofs_flag = memalloc_nofs_save();
	root = btrfs_alloc_root(fs_info, objectid, GFP_KERNEL);
	memalloc_nofs_restore(nofs_flag);
	if (!root)
		return ERR_PTR(-ENOMEM);

	root->root_key.objectid = objectid;
	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
	root->root_key.offset = 0;

	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
				      BTRFS_NESTING_NORMAL);
	if (IS_ERR(leaf)) {
		ret = PTR_ERR(leaf);
		leaf = NULL;
		goto fail_unlock;
	}

	root->node = leaf;
	btrfs_mark_buffer_dirty(leaf);

	root->commit_root = btrfs_root_node(root);
	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);

	btrfs_set_root_flags(&root->root_item, 0);
	btrfs_set_root_limit(&root->root_item, 0);
	btrfs_set_root_bytenr(&root->root_item, leaf->start);
	btrfs_set_root_generation(&root->root_item, trans->transid);
	btrfs_set_root_level(&root->root_item, 0);
	btrfs_set_root_refs(&root->root_item, 1);
	btrfs_set_root_used(&root->root_item, leaf->len);
	btrfs_set_root_last_snapshot(&root->root_item, 0);
	btrfs_set_root_dirid(&root->root_item, 0);
	if (is_fstree(objectid))
		generate_random_guid(root->root_item.uuid);
	else
		export_guid(root->root_item.uuid, &guid_null);
	btrfs_set_root_drop_level(&root->root_item, 0);

	btrfs_tree_unlock(leaf);

	key.objectid = objectid;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = 0;
	ret = btrfs_insert_root(trans, tree_root, &key, &root->root_item);
	if (ret)
		goto fail;

	return root;

fail_unlock:
	if (leaf)
		btrfs_tree_unlock(leaf);
fail:
	btrfs_put_root(root);

	return ERR_PTR(ret);
}

static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
					 struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;

	root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS);
	if (!root)
		return ERR_PTR(-ENOMEM);

	root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
	root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;

	return root;
}

int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans,
			      struct btrfs_root *root)
{
	struct extent_buffer *leaf;

	/*
	 * DON'T set SHAREABLE bit for log trees.
	 *
	 * Log trees are not exposed to user space thus can't be snapshotted,
	 * and 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).
	 */

	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
			NULL, 0, 0, 0, BTRFS_NESTING_NORMAL);
	if (IS_ERR(leaf))
		return PTR_ERR(leaf);

	root->node = leaf;

	btrfs_mark_buffer_dirty(root->node);
	btrfs_tree_unlock(root->node);

	return 0;
}

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);

	if (!btrfs_is_zoned(fs_info)) {
		int ret = btrfs_alloc_log_tree_node(trans, log_root);

		if (ret) {
			btrfs_put_root(log_root);
			return ret;
		}
	}

	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_fs_info *fs_info = root->fs_info;
	struct btrfs_root *log_root;
	struct btrfs_inode_item *inode_item;
	int ret;

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

	ret = btrfs_alloc_log_tree_node(trans, log_root);
	if (ret) {
		btrfs_put_root(log_root);
		return ret;
	}

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

	inode_item = &log_root->root_item.inode;
	btrfs_set_stack_inode_generation(inode_item, 1);
	btrfs_set_stack_inode_size(inode_item, 3);
	btrfs_set_stack_inode_nlink(inode_item, 1);
	btrfs_set_stack_inode_nbytes(inode_item,
				     fs_info->nodesize);
	btrfs_set_stack_inode_mode(inode_item, 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->log_transid_committed = -1;
	root->last_log_commit = 0;
	return 0;
}

static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root,
					      struct btrfs_path *path,
					      struct btrfs_key *key)
{
	struct btrfs_root *root;
	struct btrfs_fs_info *fs_info = tree_root->fs_info;
	u64 generation;
	int ret;
	int level;

	root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS);
	if (!root)
		return ERR_PTR(-ENOMEM);

	ret = btrfs_find_root(tree_root, key, path,
			      &root->root_item, &root->root_key);
	if (ret) {
		if (ret > 0)
			ret = -ENOENT;
		goto fail;
	}

	generation = btrfs_root_generation(&root->root_item);
	level = btrfs_root_level(&root->root_item);
	root->node = read_tree_block(fs_info,
				     btrfs_root_bytenr(&root->root_item),
				     key->objectid, generation, level, NULL);
	if (IS_ERR(root->node)) {
		ret = PTR_ERR(root->node);
		root->node = NULL;
		goto fail;
	} else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
		ret = -EIO;
		goto fail;
	}
	root->commit_root = btrfs_root_node(root);
	return root;
fail:
	btrfs_put_root(root);
	return ERR_PTR(ret);
}

struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
					struct btrfs_key *key)
{
	struct btrfs_root *root;
	struct btrfs_path *path;

	path = btrfs_alloc_path();
	if (!path)
		return ERR_PTR(-ENOMEM);
	root = read_tree_root_path(tree_root, path, key);
	btrfs_free_path(path);

	return root;
}

/*
 * Initialize subvolume root in-memory structure
 *
 * @anon_dev:	anonymous device to attach to the root, if zero, allocate new
 */
static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
{
	int ret;
	unsigned int nofs_flag;

	/*
	 * We might be called under a transaction (e.g. indirect backref
	 * resolution) which could deadlock if it triggers memory reclaim
	 */
	nofs_flag = memalloc_nofs_save();
	ret = btrfs_drew_lock_init(&root->snapshot_lock);
	memalloc_nofs_restore(nofs_flag);
	if (ret)
		goto fail;

	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
	    !btrfs_is_data_reloc_root(root)) {
		set_bit(BTRFS_ROOT_SHAREABLE, &root->state);
		btrfs_check_and_init_root_item(&root->root_item);
	}

	/*
	 * Don't assign anonymous block device to roots that are not exposed to
	 * userspace, the id pool is limited to 1M
	 */
	if (is_fstree(root->root_key.objectid) &&
	    btrfs_root_refs(&root->root_item) > 0) {
		if (!anon_dev) {
			ret = get_anon_bdev(&root->anon_dev);
			if (ret)
				goto fail;
		} else {
			root->anon_dev = anon_dev;
		}
	}

	mutex_lock(&root->objectid_mutex);
	ret = btrfs_init_root_free_objectid(root);
	if (ret) {
		mutex_unlock(&root->objectid_mutex);
		goto fail;
	}

	ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID);

	mutex_unlock(&root->objectid_mutex);

	return 0;
fail:
	/* The caller is responsible to call btrfs_free_fs_root */
	return ret;
}

static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
					       u64 root_id)
{
	struct btrfs_root *root;

	spin_lock(&fs_info->fs_roots_radix_lock);
	root = radix_tree_lookup(&fs_info->fs_roots_radix,
				 (unsigned long)root_id);
	if (root)
		root = btrfs_grab_root(root);
	spin_unlock(&fs_info->fs_roots_radix_lock);
	return root;
}

static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info,
						u64 objectid)
{
	if (objectid == BTRFS_ROOT_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->tree_root);
	if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->extent_root);
	if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->chunk_root);
	if (objectid == BTRFS_DEV_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->dev_root);
	if (objectid == BTRFS_CSUM_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->csum_root);
	if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->quota_root) ?
			fs_info->quota_root : ERR_PTR(-ENOENT);
	if (objectid == BTRFS_UUID_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->uuid_root) ?
			fs_info->uuid_root : ERR_PTR(-ENOENT);
	if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->free_space_root) ?
			fs_info->free_space_root : ERR_PTR(-ENOENT);
	return NULL;
}

int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
			 struct btrfs_root *root)
{
	int ret;

	ret = radix_tree_preload(GFP_NOFS);
	if (ret)
		return ret;

	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) {
		btrfs_grab_root(root);
		set_bit(BTRFS_ROOT_IN_RADIX, &root->state);
	}
	spin_unlock(&fs_info->fs_roots_radix_lock);
	radix_tree_preload_end();

	return ret;
}

void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
{
#ifdef CONFIG_BTRFS_DEBUG
	struct btrfs_root *root;

	while (!list_empty(&fs_info->allocated_roots)) {
		char buf[BTRFS_ROOT_NAME_BUF_LEN];

		root = list_first_entry(&fs_info->allocated_roots,
					struct btrfs_root, leak_list);
		btrfs_err(fs_info, "leaked root %s refcount %d",
			  btrfs_root_name(&root->root_key, buf),
			  refcount_read(&root->refs));
		while (refcount_read(&root->refs) > 1)
			btrfs_put_root(root);
		btrfs_put_root(root);
	}
#endif
}

void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
{
	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
	percpu_counter_destroy(&fs_info->delalloc_bytes);
	percpu_counter_destroy(&fs_info->ordered_bytes);
	percpu_counter_destroy(&fs_info->dev_replace.bio_counter);
	btrfs_free_csum_hash(fs_info);
	btrfs_free_stripe_hash_table(fs_info);
	btrfs_free_ref_cache(fs_info);
	kfree(fs_info->balance_ctl);
	kfree(fs_info->delayed_root);
	btrfs_put_root(fs_info->extent_root);
	btrfs_put_root(fs_info->tree_root);
	btrfs_put_root(fs_info->chunk_root);
	btrfs_put_root(fs_info->dev_root);
	btrfs_put_root(fs_info->csum_root);
	btrfs_put_root(fs_info->quota_root);
	btrfs_put_root(fs_info->uuid_root);
	btrfs_put_root(fs_info->free_space_root);
	btrfs_put_root(fs_info->fs_root);
	btrfs_put_root(fs_info->data_reloc_root);
	btrfs_check_leaked_roots(fs_info);
	btrfs_extent_buffer_leak_debug_check(fs_info);
	kfree(fs_info->super_copy);
	kfree(fs_info->super_for_commit);
	kfree(fs_info->subpage_info);
	kvfree(fs_info);
}


/*
 * Get an in-memory reference of a root structure.
 *
 * For essential trees like root/extent tree, we grab it from fs_info directly.
 * For subvolume trees, we check the cached filesystem roots first. If not
 * found, then read it from disk and add it to cached fs roots.
 *
 * Caller should release the root by calling btrfs_put_root() after the usage.
 *
 * NOTE: Reloc and log trees can't be read by this function as they share the
 *	 same root objectid.
 *
 * @objectid:	root id
 * @anon_dev:	preallocated anonymous block device number for new roots,
 * 		pass 0 for new allocation.
 * @check_ref:	whether to check root item references, If true, return -ENOENT
 *		for orphan roots
 */
static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
					     u64 objectid, dev_t anon_dev,
					     bool check_ref)
{
	struct btrfs_root *root;
	struct btrfs_path *path;
	struct btrfs_key key;
	int ret;

	root = btrfs_get_global_root(fs_info, objectid);
	if (root)
		return root;
again:
	root = btrfs_lookup_fs_root(fs_info, objectid);
	if (root) {
		/* Shouldn't get preallocated anon_dev for cached roots */
		ASSERT(!anon_dev);
		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
			btrfs_put_root(root);
			return ERR_PTR(-ENOENT);
		}
		return root;
	}

	key.objectid = objectid;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;
	root = btrfs_read_tree_root(fs_info->tree_root, &key);
	if (IS_ERR(root))
		return root;

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

	ret = btrfs_init_fs_root(root, anon_dev);
	if (ret)
		goto fail;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto fail;
	}
	key.objectid = BTRFS_ORPHAN_OBJECTID;
	key.type = BTRFS_ORPHAN_ITEM_KEY;
	key.offset = objectid;

	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
	btrfs_free_path(path);
	if (ret < 0)
		goto fail;
	if (ret == 0)
		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);

	ret = btrfs_insert_fs_root(fs_info, root);
	if (ret) {
		btrfs_put_root(root);
		if (ret == -EEXIST)
			goto again;
		goto fail;
	}
	return root;
fail:
	btrfs_put_root(root);
	return ERR_PTR(ret);
}

/*
 * Get in-memory reference of a root structure
 *
 * @objectid:	tree objectid
 * @check_ref:	if set, verify that the tree exists and the item has at least
 *		one reference
 */
struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
				     u64 objectid, bool check_ref)
{
	return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
}

/*
 * Get in-memory reference of a root structure, created as new, optionally pass
 * the anonymous block device id
 *
 * @objectid:	tree objectid
 * @anon_dev:	if zero, allocate a new anonymous block device or use the
 *		parameter value
 */
struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
					 u64 objectid, dev_t anon_dev)
{
	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
}

/*
 * btrfs_get_fs_root_commit_root - return a root for the given objectid
 * @fs_info:	the fs_info
 * @objectid:	the objectid we need to lookup
 *
 * This is exclusively used for backref walking, and exists specifically because
 * of how qgroups does lookups.  Qgroups will do a backref lookup at delayed ref
 * creation time, which means we may have to read the tree_root in order to look
 * up a fs root that is not in memory.  If the root is not in memory we will
 * read the tree root commit root and look up the fs root from there.  This is a
 * temporary root, it will not be inserted into the radix tree as it doesn't
 * have the most uptodate information, it'll simply be discarded once the
 * backref code is finished using the root.
 */
struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
						 struct btrfs_path *path,
						 u64 objectid)
{
	struct btrfs_root *root;
	struct btrfs_key key;

	ASSERT(path->search_commit_root && path->skip_locking);

	/*
	 * This can return -ENOENT if we ask for a root that doesn't exist, but
	 * since this is called via the backref walking code we won't be looking
	 * up a root that doesn't exist, unless there's corruption.  So if root
	 * != NULL just return it.
	 */
	root = btrfs_get_global_root(fs_info, objectid);
	if (root)
		return root;

	root = btrfs_lookup_fs_root(fs_info, objectid);
	if (root)
		return root;

	key.objectid = objectid;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;
	root = read_tree_root_path(fs_info->tree_root, path, &key);
	btrfs_release_path(path);

	return root;
}

/*
 * 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 btrfs_end_io_wq *end_io_wq;

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

	bio->bi_status = end_io_wq->status;
	bio->bi_private = end_io_wq->private;
	bio->bi_end_io = end_io_wq->end_io;
	bio_endio(bio);
	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
}

static int cleaner_kthread(void *arg)
{
	struct btrfs_root *root = arg;
	struct btrfs_fs_info *fs_info = root->fs_info;
	int again;

	while (1) {
		again = 0;

		set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);

		/* Make the cleaner go to sleep early. */
		if (btrfs_need_cleaner_sleep(fs_info))
			goto sleep;

		/*
		 * Do not do anything if we might cause open_ctree() to block
		 * before we have finished mounting the filesystem.
		 */
		if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
			goto sleep;

		if (!mutex_trylock(&fs_info->cleaner_mutex))
			goto sleep;

		/*
		 * Avoid the problem that we change the status of the fs
		 * during the above check and trylock.
		 */
		if (btrfs_need_cleaner_sleep(fs_info)) {
			mutex_unlock(&fs_info->cleaner_mutex);
			goto sleep;
		}

		btrfs_run_delayed_iputs(fs_info);

		again = btrfs_clean_one_deleted_snapshot(root);
		mutex_unlock(&fs_info->cleaner_mutex);

		/*
		 * The defragger has dealt with the R/O remount and umount,
		 * needn't do anything special here.
		 */
		btrfs_run_defrag_inodes(fs_info);

		/*
		 * Acquires fs_info->reclaim_bgs_lock to avoid racing
		 * with relocation (btrfs_relocate_chunk) and relocation
		 * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group)
		 * after acquiring fs_info->reclaim_bgs_lock. So we
		 * can't hold, nor need to, fs_info->cleaner_mutex when deleting
		 * unused block groups.
		 */
		btrfs_delete_unused_bgs(fs_info);

		/*
		 * Reclaim block groups in the reclaim_bgs list after we deleted
		 * all unused block_groups. This possibly gives us some more free
		 * space.
		 */
		btrfs_reclaim_bgs(fs_info);
sleep:
		clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
		if (kthread_should_park())
			kthread_parkme();
		if (kthread_should_stop())
			return 0;
		if (!again) {
			set_current_state(TASK_INTERRUPTIBLE);
			schedule();
			__set_current_state(TASK_RUNNING);
		}
	}
}

static int transaction_kthread(void *arg)
{
	struct btrfs_root *root = arg;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	struct btrfs_transaction *cur;
	u64 transid;
	time64_t delta;
	unsigned long delay;
	bool cannot_commit;

	do {
		cannot_commit = false;
		delay = msecs_to_jiffies(fs_info->commit_interval * 1000);
		mutex_lock(&fs_info->transaction_kthread_mutex);

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

		delta = ktime_get_seconds() - cur->start_time;
		if (cur->state < TRANS_STATE_COMMIT_START &&
		    delta < fs_info->commit_interval) {
			spin_unlock(&fs_info->trans_lock);
			delay -= msecs_to_jiffies((delta - 1) * 1000);
			delay = min(delay,
				    msecs_to_jiffies(fs_info->commit_interval * 1000));
			goto sleep;
		}
		transid = cur->transid;
		spin_unlock(&fs_info->trans_lock);

		/* If the file system is aborted, this will always fail. */
		trans = btrfs_attach_transaction(root);
		if (IS_ERR(trans)) {
			if (PTR_ERR(trans) != -ENOENT)
				cannot_commit = true;
			goto sleep;
		}
		if (transid == trans->transid) {
			btrfs_commit_transaction(trans);
		} else {
			btrfs_end_transaction(trans);
		}
sleep:
		wake_up_process(fs_info->cleaner_kthread);
		mutex_unlock(&fs_info->transaction_kthread_mutex);

		if (BTRFS_FS_ERROR(fs_info))
			btrfs_cleanup_transaction(fs_info);
		if (!kthread_should_stop() &&
				(!btrfs_transaction_blocked(fs_info) ||
				 cannot_commit))
			schedule_timeout_interruptible(delay);
	} while (!kthread_should_stop());
	return 0;
}

/*
 * This will find the highest generation in the array of root backups.  The
 * index of the highest array is returned, or -EINVAL if we can't find
 * anything.
 *
 * We check to make sure the array is valid by comparing the
 * generation of the latest  root in the array with the generation
 * in the super block.  If they don't match we pitch it.
 */
static int find_newest_super_backup(struct btrfs_fs_info *info)
{
	const u64 newest_gen = btrfs_super_generation(info->super_copy);
	u64 cur;
	struct btrfs_root_backup *root_backup;
	int i;

	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
		root_backup = info->super_copy->super_roots + i;
		cur = btrfs_backup_tree_root_gen(root_backup);
		if (cur == newest_gen)
			return i;
	}

	return -EINVAL;
}

/*
 * copy all the root pointers into the super backup array.
 * this will bump the backup pointer by one when it is
 * done
 */
static void backup_super_roots(struct btrfs_fs_info *info)
{
	const int next_backup = info->backup_root_index;
	struct btrfs_root_backup *root_backup;

	root_backup = info->super_for_commit->super_roots + next_backup;

	/*
	 * make sure all of our padding and empty slots get zero filled
	 * regardless of which ones we use today
	 */
	memset(root_backup, 0, sizeof(*root_backup));

	info->backup_root_index = (next_backup + 1) % BTRFS_NUM_BACKUP_ROOTS;

	btrfs_set_backup_tree_root(root_backup, info->tree_root->node->start);
	btrfs_set_backup_tree_root_gen(root_backup,
			       btrfs_header_generation(info->tree_root->node));

	btrfs_set_backup_tree_root_level(root_backup,
			       btrfs_header_level(info->tree_root->node));

	btrfs_set_backup_chunk_root(root_backup, info->chunk_root->node->start);
	btrfs_set_backup_chunk_root_gen(root_backup,
			       btrfs_header_generation(info->chunk_root->node));
	btrfs_set_backup_chunk_root_level(root_backup,
			       btrfs_header_level(info->chunk_root->node));

	btrfs_set_backup_extent_root(root_backup, info->extent_root->node->start);
	btrfs_set_backup_extent_root_gen(root_backup,
			       btrfs_header_generation(info->extent_root->node));
	btrfs_set_backup_extent_root_level(root_backup,
			       btrfs_header_level(info->extent_root->node));

	/*
	 * we might commit during log recovery, which happens before we set
	 * the fs_root.  Make sure it is valid before we fill it in.
	 */
	if (info->fs_root && info->fs_root->node) {
		btrfs_set_backup_fs_root(root_backup,
					 info->fs_root->node->start);
		btrfs_set_backup_fs_root_gen(root_backup,
			       btrfs_header_generation(info->fs_root->node));
		btrfs_set_backup_fs_root_level(root_backup,
			       btrfs_header_level(info->fs_root->node));
	}

	btrfs_set_backup_dev_root(root_backup, info->dev_root->node->start);
	btrfs_set_backup_dev_root_gen(root_backup,
			       btrfs_header_generation(info->dev_root->node));
	btrfs_set_backup_dev_root_level(root_backup,
				       btrfs_header_level(info->dev_root->node));

	btrfs_set_backup_csum_root(root_backup, info->csum_root->node->start);
	btrfs_set_backup_csum_root_gen(root_backup,
			       btrfs_header_generation(info->csum_root->node));
	btrfs_set_backup_csum_root_level(root_backup,
			       btrfs_header_level(info->csum_root->node));

	btrfs_set_backup_total_bytes(root_backup,
			     btrfs_super_total_bytes(info->super_copy));
	btrfs_set_backup_bytes_used(root_backup,
			     btrfs_super_bytes_used(info->super_copy));
	btrfs_set_backup_num_devices(root_backup,
			     btrfs_super_num_devices(info->super_copy));

	/*
	 * if we don't copy this out to the super_copy, it won't get remembered
	 * for the next commit
	 */
	memcpy(&info->super_copy->super_roots,
	       &info->super_for_commit->super_roots,
	       sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS);
}

/*
 * read_backup_root - Reads a backup root based on the passed priority. Prio 0
 * is the newest, prio 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots
 *
 * fs_info - filesystem whose backup roots need to be read
 * priority - priority of backup root required
 *
 * Returns backup root index on success and -EINVAL otherwise.
 */
static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
{
	int backup_index = find_newest_super_backup(fs_info);
	struct btrfs_super_block *super = fs_info->super_copy;
	struct btrfs_root_backup *root_backup;

	if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) {
		if (priority == 0)
			return backup_index;

		backup_index = backup_index + BTRFS_NUM_BACKUP_ROOTS - priority;
		backup_index %= BTRFS_NUM_BACKUP_ROOTS;
	} else {
		return -EINVAL;
	}

	root_backup = super->super_roots + backup_index;

	btrfs_set_super_generation(super,
				   btrfs_backup_tree_root_gen(root_backup));
	btrfs_set_super_root(super, btrfs_backup_tree_root(root_backup));
	btrfs_set_super_root_level(super,
				   btrfs_backup_tree_root_level(root_backup));
	btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup));

	/*
	 * Fixme: the total bytes and num_devices need to match or we should
	 * need a fsck
	 */
	btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
	btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));

	return backup_index;
}

/* helper to cleanup workers */
static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
{
	btrfs_destroy_workqueue(fs_info->fixup_workers);
	btrfs_destroy_workqueue(fs_info->delalloc_workers);
	btrfs_destroy_workqueue(fs_info->workers);
	btrfs_destroy_workqueue(fs_info->endio_workers);
	btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
	btrfs_destroy_workqueue(fs_info->rmw_workers);
	btrfs_destroy_workqueue(fs_info->endio_write_workers);
	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
	btrfs_destroy_workqueue(fs_info->delayed_workers);
	btrfs_destroy_workqueue(fs_info->caching_workers);
	btrfs_destroy_workqueue(fs_info->readahead_workers);
	btrfs_destroy_workqueue(fs_info->flush_workers);
	btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
	if (fs_info->discard_ctl.discard_workers)
		destroy_workqueue(fs_info->discard_ctl.discard_workers);
	/*
	 * Now that all other work queues are destroyed, we can safely destroy
	 * the queues used for metadata I/O, since tasks from those other work
	 * queues can do metadata I/O operations.
	 */
	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
}

static void free_root_extent_buffers(struct btrfs_root *root)
{
	if (root) {
		free_extent_buffer(root->node);
		free_extent_buffer(root->commit_root);
		root->node = NULL;
		root->commit_root = NULL;
	}
}

/* helper to cleanup tree roots */
static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
{
	free_root_extent_buffers(info->tree_root);

	free_root_extent_buffers(info->dev_root);
	free_root_extent_buffers(info->extent_root);
	free_root_extent_buffers(info->csum_root);
	free_root_extent_buffers(info->quota_root);
	free_root_extent_buffers(info->uuid_root);
	free_root_extent_buffers(info->fs_root);
	free_root_extent_buffers(info->data_reloc_root);
	if (free_chunk_root)
		free_root_extent_buffers(info->chunk_root);
	free_root_extent_buffers(info->free_space_root);
}

void btrfs_put_root(struct btrfs_root *root)
{
	if (!root)
		return;

	if (refcount_dec_and_test(&root->refs)) {
		WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
		WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state));
		if (root->anon_dev)
			free_anon_bdev(root->anon_dev);
		btrfs_drew_lock_destroy(&root->snapshot_lock);
		free_root_extent_buffers(root);
#ifdef CONFIG_BTRFS_DEBUG
		spin_lock(&root->fs_info->fs_roots_radix_lock);
		list_del_init(&root->leak_list);
		spin_unlock(&root->fs_info->fs_roots_radix_lock);
#endif
		kfree(root);
	}
}

void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
{
	int ret;
	struct btrfs_root *gang[8];
	int i;

	while (!list_empty(&fs_info->dead_roots)) {
		gang[0] = list_entry(fs_info->dead_roots.next,
				     struct btrfs_root, root_list);
		list_del(&gang[0]->root_list);

		if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state))
			btrfs_drop_and_free_fs_root(fs_info, gang[0]);
		btrfs_put_root(gang[0]);
	}

	while (1) {
		ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
					     (void **)gang, 0,
					     ARRAY_SIZE(gang));
		if (!ret)
			break;
		for (i = 0; i < ret; i++)
			btrfs_drop_and_free_fs_root(fs_info, gang[i]);
	}
}

static void btrfs_init_scrub(struct btrfs_fs_info *fs_info)
{
	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);
	refcount_set(&fs_info->scrub_workers_refcnt, 0);
}

static void btrfs_init_balance(struct btrfs_fs_info *fs_info)
{
	spin_lock_init(&fs_info->balance_lock);
	mutex_init(&fs_info->balance_mutex);
	atomic_set(&fs_info->balance_pause_req, 0);
	atomic_set(&fs_info->balance_cancel_req, 0);
	fs_info->balance_ctl = NULL;
	init_waitqueue_head(&fs_info->balance_wait_q);
	atomic_set(&fs_info->reloc_cancel_req, 0);
}

static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
{
	struct inode *inode = fs_info->btree_inode;

	inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
	set_nlink(inode, 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
	 */
	inode->i_size = OFFSET_MAX;
	inode->i_mapping->a_ops = &btree_aops;

	RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
	extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree,
			    IO_TREE_BTREE_INODE_IO, inode);
	BTRFS_I(inode)->io_tree.track_uptodate = false;
	extent_map_tree_init(&BTRFS_I(inode)->extent_tree);

	BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root);
	memset(&BTRFS_I(inode)->location, 0, sizeof(struct btrfs_key));
	set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
	btrfs_insert_inode_hash(inode);
}

static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
{
	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
	init_rwsem(&fs_info->dev_replace.rwsem);
	init_waitqueue_head(&fs_info->dev_replace.replace_wait);
}

static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
{
	spin_lock_init(&fs_info->qgroup_lock);
	mutex_init(&fs_info->qgroup_ioctl_lock);
	fs_info->qgroup_tree = RB_ROOT;
	INIT_LIST_HEAD(&fs_info->dirty_qgroups);
	fs_info->qgroup_seq = 1;
	fs_info->qgroup_ulist = NULL;
	fs_info->qgroup_rescan_running = false;
	mutex_init(&fs_info->qgroup_rescan_lock);
}

static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
		struct btrfs_fs_devices *fs_devices)
{
	u32 max_active = fs_info->thread_pool_size;
	unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;

	fs_info->workers =
		btrfs_alloc_workqueue(fs_info, "worker",
				      flags | WQ_HIGHPRI, max_active, 16);

	fs_info->delalloc_workers =
		btrfs_alloc_workqueue(fs_info, "delalloc",
				      flags, max_active, 2);

	fs_info->flush_workers =
		btrfs_alloc_workqueue(fs_info, "flush_delalloc",
				      flags, max_active, 0);

	fs_info->caching_workers =
		btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);

	fs_info->fixup_workers =
		btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);

	/*
	 * endios are largely parallel and should have a very
	 * low idle thresh
	 */
	fs_info->endio_workers =
		btrfs_alloc_workqueue(fs_info, "endio", flags, max_active, 4);
	fs_info->endio_meta_workers =
		btrfs_alloc_workqueue(fs_info, "endio-meta", flags,
				      max_active, 4);
	fs_info->endio_meta_write_workers =
		btrfs_alloc_workqueue(fs_info, "endio-meta-write", flags,
				      max_active, 2);
	fs_info->endio_raid56_workers =
		btrfs_alloc_workqueue(fs_info, "endio-raid56", flags,
				      max_active, 4);
	fs_info->rmw_workers =
		btrfs_alloc_workqueue(fs_info, "rmw", flags, max_active, 2);
	fs_info->endio_write_workers =
		btrfs_alloc_workqueue(fs_info, "endio-write", flags,
				      max_active, 2);
	fs_info->endio_freespace_worker =
		btrfs_alloc_workqueue(fs_info, "freespace-write", flags,
				      max_active, 0);
	fs_info->delayed_workers =
		btrfs_alloc_workqueue(fs_info, "delayed-meta", flags,
				      max_active, 0);
	fs_info->readahead_workers =
		btrfs_alloc_workqueue(fs_info, "readahead", flags,
				      max_active, 2);
	fs_info->qgroup_rescan_workers =
		btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
	fs_info->discard_ctl.discard_workers =
		alloc_workqueue("btrfs_discard", WQ_UNBOUND | WQ_FREEZABLE, 1);

	if (!(fs_info->workers && fs_info->delalloc_workers &&
	      fs_info->flush_workers &&
	      fs_info->endio_workers && fs_info->endio_meta_workers &&
	      fs_info->endio_meta_write_workers &&
	      fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
	      fs_info->endio_freespace_worker && fs_info->rmw_workers &&
	      fs_info->caching_workers && fs_info->readahead_workers &&
	      fs_info->fixup_workers && fs_info->delayed_workers &&
	      fs_info->qgroup_rescan_workers &&
	      fs_info->discard_ctl.discard_workers)) {
		return -ENOMEM;
	}

	return 0;
}

static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type)
{
	struct crypto_shash *csum_shash;
	const char *csum_driver = btrfs_super_csum_driver(csum_type);

	csum_shash = crypto_alloc_shash(csum_driver, 0, 0);

	if (IS_ERR(csum_shash)) {
		btrfs_err(fs_info, "error allocating %s hash for checksum",
			  csum_driver);
		return PTR_ERR(csum_shash);
	}

	fs_info->csum_shash = csum_shash;

	return 0;
}

static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
			    struct btrfs_fs_devices *fs_devices)
{
	int ret;
	struct btrfs_root *log_tree_root;
	struct btrfs_super_block *disk_super = fs_info->super_copy;
	u64 bytenr = btrfs_super_log_root(disk_super);
	int level = btrfs_super_log_root_level(disk_super);

	if (fs_devices->rw_devices == 0) {
		btrfs_warn(fs_info, "log replay required on RO media");
		return -EIO;
	}

	log_tree_root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID,
					 GFP_KERNEL);
	if (!log_tree_root)
		return -ENOMEM;

	log_tree_root->node = read_tree_block(fs_info, bytenr,
					      BTRFS_TREE_LOG_OBJECTID,
					      fs_info->generation + 1, level,
					      NULL);
	if (IS_ERR(log_tree_root->node)) {
		btrfs_warn(fs_info, "failed to read log tree");
		ret = PTR_ERR(log_tree_root->node);
		log_tree_root->node = NULL;
		btrfs_put_root(log_tree_root);
		return ret;
	} else if (!extent_buffer_uptodate(log_tree_root->node)) {
		btrfs_err(fs_info, "failed to read log tree");
		btrfs_put_root(log_tree_root);
		return -EIO;
	}
	/* returns with log_tree_root freed on success */
	ret = btrfs_recover_log_trees(log_tree_root);
	if (ret) {
		btrfs_handle_fs_error(fs_info, ret,
				      "Failed to recover log tree");
		btrfs_put_root(log_tree_root);
		return ret;
	}

	if (sb_rdonly(fs_info->sb)) {
		ret = btrfs_commit_super(fs_info);
		if (ret)
			return ret;
	}

	return 0;
}

static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_root *root;
	struct btrfs_key location;
	int ret;

	BUG_ON(!fs_info->tree_root);

	location.objectid = BTRFS_EXTENT_TREE_OBJECTID;
	location.type = BTRFS_ROOT_ITEM_KEY;
	location.offset = 0;

	root = btrfs_read_tree_root(tree_root, &location);
	if (IS_ERR(root)) {
		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
			ret = PTR_ERR(root);
			goto out;
		}
	} else {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		fs_info->extent_root = root;
	}

	location.objectid = BTRFS_DEV_TREE_OBJECTID;
	root = btrfs_read_tree_root(tree_root, &location);
	if (IS_ERR(root)) {
		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
			ret = PTR_ERR(root);
			goto out;
		}
	} else {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		fs_info->dev_root = root;
	}
	/* Initialize fs_info for all devices in any case */
	btrfs_init_devices_late(fs_info);

	/* If IGNOREDATACSUMS is set don't bother reading the csum root. */
	if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
		location.objectid = BTRFS_CSUM_TREE_OBJECTID;
		root = btrfs_read_tree_root(tree_root, &location);
		if (IS_ERR(root)) {
			if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
				ret = PTR_ERR(root);
				goto out;
			}
		} else {
			set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
			fs_info->csum_root = root;
		}
	}

	/*
	 * This tree can share blocks with some other fs tree during relocation
	 * and we need a proper setup by btrfs_get_fs_root
	 */
	root = btrfs_get_fs_root(tree_root->fs_info,
				 BTRFS_DATA_RELOC_TREE_OBJECTID, true);
	if (IS_ERR(root)) {
		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
			ret = PTR_ERR(root);
			goto out;
		}
	} else {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		fs_info->data_reloc_root = root;
	}

	location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
	root = btrfs_read_tree_root(tree_root, &location);
	if (!IS_ERR(root)) {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
		fs_info->quota_root = root;
	}

	location.objectid = BTRFS_UUID_TREE_OBJECTID;
	root = btrfs_read_tree_root(tree_root, &location);
	if (IS_ERR(root)) {
		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
			ret = PTR_ERR(root);
			if (ret != -ENOENT)
				goto out;
		}
	} else {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		fs_info->uuid_root = root;
	}

	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
		location.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID;
		root = btrfs_read_tree_root(tree_root, &location);
		if (IS_ERR(root)) {
			if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
				ret = PTR_ERR(root);
				goto out;
			}
		}  else {
			set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
			fs_info->free_space_root = root;
		}
	}

	return 0;
out:
	btrfs_warn(fs_info, "failed to read root (objectid=%llu): %d",
		   location.objectid, ret);
	return ret;
}

/*
 * Real super block validation
 * NOTE: super csum type and incompat features will not be checked here.
 *
 * @sb:		super block to check
 * @mirror_num:	the super block number to check its bytenr:
 * 		0	the primary (1st) sb
 * 		1, 2	2nd and 3rd backup copy
 * 	       -1	skip bytenr check
 */
static int validate_super(struct btrfs_fs_info *fs_info,
			    struct btrfs_super_block *sb, int mirror_num)
{
	u64 nodesize = btrfs_super_nodesize(sb);
	u64 sectorsize = btrfs_super_sectorsize(sb);
	int ret = 0;

	if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
		btrfs_err(fs_info, "no valid FS found");
		ret = -EINVAL;
	}
	if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) {
		btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu",
				btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
		ret = -EINVAL;
	}
	if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
		btrfs_err(fs_info, "tree_root level too big: %d >= %d",
				btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
		ret = -EINVAL;
	}
	if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
		btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
				btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
		ret = -EINVAL;
	}
	if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
		btrfs_err(fs_info, "log_root level too big: %d >= %d",
				btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
		ret = -EINVAL;
	}

	/*
	 * Check sectorsize and nodesize first, other check will need it.
	 * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
	 */
	if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
	    sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
		btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
		ret = -EINVAL;
	}

	/*
	 * For 4K page size, we only support 4K sector size.
	 * For 64K page size, we support 64K and 4K sector sizes.
	 */
	if ((PAGE_SIZE == SZ_4K && sectorsize != PAGE_SIZE) ||
	    (PAGE_SIZE == SZ_64K && (sectorsize != SZ_4K &&
				     sectorsize != SZ_64K))) {
		btrfs_err(fs_info,
			"sectorsize %llu not yet supported for page size %lu",
			sectorsize, PAGE_SIZE);
		ret = -EINVAL;
	}

	if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
	    nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
		btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
		ret = -EINVAL;
	}
	if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
		btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
			  le32_to_cpu(sb->__unused_leafsize), nodesize);
		ret = -EINVAL;
	}

	/* Root alignment check */
	if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
		btrfs_warn(fs_info, "tree_root block unaligned: %llu",
			   btrfs_super_root(sb));
		ret = -EINVAL;
	}
	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
		btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
			   btrfs_super_chunk_root(sb));
		ret = -EINVAL;
	}
	if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
		btrfs_warn(fs_info, "log_root block unaligned: %llu",
			   btrfs_super_log_root(sb));
		ret = -EINVAL;
	}

	if (memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid,
		   BTRFS_FSID_SIZE)) {
		btrfs_err(fs_info,
		"superblock fsid doesn't match fsid of fs_devices: %pU != %pU",
			fs_info->super_copy->fsid, fs_info->fs_devices->fsid);
		ret = -EINVAL;
	}

	if (btrfs_fs_incompat(fs_info, METADATA_UUID) &&
	    memcmp(fs_info->fs_devices->metadata_uuid,
		   fs_info->super_copy->metadata_uuid, BTRFS_FSID_SIZE)) {
		btrfs_err(fs_info,
"superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU",
			fs_info->super_copy->metadata_uuid,
			fs_info->fs_devices->metadata_uuid);
		ret = -EINVAL;
	}

	if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid,
		   BTRFS_FSID_SIZE) != 0) {
		btrfs_err(fs_info,
			"dev_item UUID does not match metadata fsid: %pU != %pU",
			fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid);
		ret = -EINVAL;
	}

	/*
	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
	 * done later
	 */
	if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
		btrfs_err(fs_info, "bytes_used is too small %llu",
			  btrfs_super_bytes_used(sb));
		ret = -EINVAL;
	}
	if (!is_power_of_2(btrfs_super_stripesize(sb))) {
		btrfs_err(fs_info, "invalid stripesize %u",
			  btrfs_super_stripesize(sb));
		ret = -EINVAL;
	}
	if (btrfs_super_num_devices(sb) > (1UL << 31))
		btrfs_warn(fs_info, "suspicious number of devices: %llu",
			   btrfs_super_num_devices(sb));
	if (btrfs_super_num_devices(sb) == 0) {
		btrfs_err(fs_info, "number of devices is 0");
		ret = -EINVAL;
	}

	if (mirror_num >= 0 &&
	    btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) {
		btrfs_err(fs_info, "super offset mismatch %llu != %u",
			  btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
		ret = -EINVAL;
	}

	/*
	 * Obvious sys_chunk_array corruptions, it must hold at least one key
	 * and one chunk
	 */
	if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
		btrfs_err(fs_info, "system chunk array too big %u > %u",
			  btrfs_super_sys_array_size(sb),
			  BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
		ret = -EINVAL;
	}
	if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
			+ sizeof(struct btrfs_chunk)) {
		btrfs_err(fs_info, "system chunk array too small %u < %zu",
			  btrfs_super_sys_array_size(sb),
			  sizeof(struct btrfs_disk_key)
			  + sizeof(struct btrfs_chunk));
		ret = -EINVAL;
	}

	/*
	 * The generation is a global counter, we'll trust it more than the others
	 * but it's still possible that it's the one that's wrong.
	 */
	if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
		btrfs_warn(fs_info,
			"suspicious: generation < chunk_root_generation: %llu < %llu",
			btrfs_super_generation(sb),
			btrfs_super_chunk_root_generation(sb));
	if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
	    && btrfs_super_cache_generation(sb) != (u64)-1)
		btrfs_warn(fs_info,
			"suspicious: generation < cache_generation: %llu < %llu",
			btrfs_super_generation(sb),
			btrfs_super_cache_generation(sb));

	return ret;
}

/*
 * Validation of super block at mount time.
 * Some checks already done early at mount time, like csum type and incompat
 * flags will be skipped.
 */
static int btrfs_validate_mount_super(struct btrfs_fs_info *fs_info)
{
	return validate_super(fs_info, fs_info->super_copy, 0);
}

/*
 * Validation of super block at write time.
 * Some checks like bytenr check will be skipped as their values will be
 * overwritten soon.
 * Extra checks like csum type and incompat flags will be done here.
 */
static int btrfs_validate_write_super(struct btrfs_fs_info *fs_info,
				      struct btrfs_super_block *sb)
{
	int ret;

	ret = validate_super(fs_info, sb, -1);
	if (ret < 0)
		goto out;
	if (!btrfs_supported_super_csum(btrfs_super_csum_type(sb))) {
		ret = -EUCLEAN;
		btrfs_err(fs_info, "invalid csum type, has %u want %u",
			  btrfs_super_csum_type(sb), BTRFS_CSUM_TYPE_CRC32);
		goto out;
	}
	if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
		ret = -EUCLEAN;
		btrfs_err(fs_info,
		"invalid incompat flags, has 0x%llx valid mask 0x%llx",
			  btrfs_super_incompat_flags(sb),
			  (unsigned long long)BTRFS_FEATURE_INCOMPAT_SUPP);
		goto out;
	}
out:
	if (ret < 0)
		btrfs_err(fs_info,
		"super block corruption detected before writing it to disk");
	return ret;
}

static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
{
	int backup_index = find_newest_super_backup(fs_info);
	struct btrfs_super_block *sb = fs_info->super_copy;
	struct btrfs_root *tree_root = fs_info->tree_root;
	bool handle_error = false;
	int ret = 0;
	int i;

	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
		u64 generation;
		int level;

		if (handle_error) {
			if (!IS_ERR(tree_root->node))
				free_extent_buffer(tree_root->node);
			tree_root->node = NULL;

			if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
				break;

			free_root_pointers(fs_info, 0);

			/*
			 * Don't use the log in recovery mode, it won't be
			 * valid
			 */
			btrfs_set_super_log_root(sb, 0);

			/* We can't trust the free space cache either */
			btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);

			ret = read_backup_root(fs_info, i);
			backup_index = ret;
			if (ret < 0)
				return ret;
		}
		generation = btrfs_super_generation(sb);
		level = btrfs_super_root_level(sb);
		tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb),
						  BTRFS_ROOT_TREE_OBJECTID,
						  generation, level, NULL);
		if (IS_ERR(tree_root->node)) {
			handle_error = true;
			ret = PTR_ERR(tree_root->node);
			tree_root->node = NULL;
			btrfs_warn(fs_info, "couldn't read tree root");
			continue;

		} else if (!extent_buffer_uptodate(tree_root->node)) {
			handle_error = true;
			ret = -EIO;
			btrfs_warn(fs_info, "error while reading tree root");
			continue;
		}

		btrfs_set_root_node(&tree_root->root_item, tree_root->node);
		tree_root->commit_root = btrfs_root_node(tree_root);
		btrfs_set_root_refs(&tree_root->root_item, 1);

		/*
		 * No need to hold btrfs_root::objectid_mutex since the fs
		 * hasn't been fully initialised and we are the only user
		 */
		ret = btrfs_init_root_free_objectid(tree_root);
		if (ret < 0) {
			handle_error = true;
			continue;
		}

		ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID);

		ret = btrfs_read_roots(fs_info);
		if (ret < 0) {
			handle_error = true;
			continue;
		}

		/* All successful */
		fs_info->generation = generation;
		fs_info->last_trans_committed = generation;

		/* Always begin writing backup roots after the one being used */
		if (backup_index < 0) {
			fs_info->backup_root_index = 0;
		} else {
			fs_info->backup_root_index = backup_index + 1;
			fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS;
		}
		break;
	}

	return ret;
}

void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
{
	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
	INIT_RADIX_TREE(&fs_info->buffer_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->delalloc_roots);
	INIT_LIST_HEAD(&fs_info->caching_block_groups);
	spin_lock_init(&fs_info->delalloc_root_lock);
	spin_lock_init(&fs_info->trans_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);
	spin_lock_init(&fs_info->super_lock);
	spin_lock_init(&fs_info->buffer_lock);
	spin_lock_init(&fs_info->unused_bgs_lock);
	spin_lock_init(&fs_info->treelog_bg_lock);
	spin_lock_init(&fs_info->zone_active_bgs_lock);
	spin_lock_init(&fs_info->relocation_bg_lock);
	rwlock_init(&fs_info->tree_mod_log_lock);
	mutex_init(&fs_info->unused_bg_unpin_mutex);
	mutex_init(&fs_info->reclaim_bgs_lock);
	mutex_init(&fs_info->reloc_mutex);
	mutex_init(&fs_info->delalloc_root_mutex);
	mutex_init(&fs_info->zoned_meta_io_lock);
	seqlock_init(&fs_info->profiles_lock);

	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
	INIT_LIST_HEAD(&fs_info->space_info);
	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
	INIT_LIST_HEAD(&fs_info->unused_bgs);
	INIT_LIST_HEAD(&fs_info->reclaim_bgs);
	INIT_LIST_HEAD(&fs_info->zone_active_bgs);
#ifdef CONFIG_BTRFS_DEBUG
	INIT_LIST_HEAD(&fs_info->allocated_roots);
	INIT_LIST_HEAD(&fs_info->allocated_ebs);
	spin_lock_init(&fs_info->eb_leak_lock);
#endif
	extent_map_tree_init(&fs_info->mapping_tree);
	btrfs_init_block_rsv(&fs_info->global_block_rsv,
			     BTRFS_BLOCK_RSV_GLOBAL);
	btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
	btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK);
	btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY);
	btrfs_init_block_rsv(&fs_info->delayed_block_rsv,
			     BTRFS_BLOCK_RSV_DELOPS);
	btrfs_init_block_rsv(&fs_info->delayed_refs_rsv,
			     BTRFS_BLOCK_RSV_DELREFS);

	atomic_set(&fs_info->async_delalloc_pages, 0);
	atomic_set(&fs_info->defrag_running, 0);
	atomic_set(&fs_info->reada_works_cnt, 0);
	atomic_set(&fs_info->nr_delayed_iputs, 0);
	atomic64_set(&fs_info->tree_mod_seq, 0);
	fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
	fs_info->metadata_ratio = 0;
	fs_info->defrag_inodes = RB_ROOT;
	atomic64_set(&fs_info->free_chunk_space, 0);
	fs_info->tree_mod_log = RB_ROOT;
	fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
	fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
	/* readahead state */
	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
	spin_lock_init(&fs_info->reada_lock);
	btrfs_init_ref_verify(fs_info);

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

	INIT_LIST_HEAD(&fs_info->ordered_roots);
	spin_lock_init(&fs_info->ordered_root_lock);

	btrfs_init_scrub(fs_info);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
	fs_info->check_integrity_print_mask = 0;
#endif
	btrfs_init_balance(fs_info);
	btrfs_init_async_reclaim_work(fs_info);

	spin_lock_init(&fs_info->block_group_cache_lock);
	fs_info->block_group_cache_tree = RB_ROOT;
	fs_info->first_logical_byte = (u64)-1;

	extent_io_tree_init(fs_info, &fs_info->excluded_extents,
			    IO_TREE_FS_EXCLUDED_EXTENTS, NULL);
	set_bit(BTRFS_FS_BARRIER, &fs_info->flags);

	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->ro_block_group_mutex);
	init_rwsem(&fs_info->commit_root_sem);
	init_rwsem(&fs_info->cleanup_work_sem);
	init_rwsem(&fs_info->subvol_sem);
	sema_init(&fs_info->uuid_tree_rescan_sem, 1);

	btrfs_init_dev_replace_locks(fs_info);
	btrfs_init_qgroup(fs_info);
	btrfs_discard_init(fs_info);

	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);
	init_waitqueue_head(&fs_info->delayed_iputs_wait);

	/* Usable values until the real ones are cached from the superblock */
	fs_info->nodesize = 4096;
	fs_info->sectorsize = 4096;
	fs_info->sectorsize_bits = ilog2(4096);
	fs_info->stripesize = 4096;

	spin_lock_init(&fs_info->swapfile_pins_lock);
	fs_info->swapfile_pins = RB_ROOT;

	spin_lock_init(&fs_info->send_reloc_lock);
	fs_info->send_in_progress = 0;

	fs_info->bg_reclaim_threshold = BTRFS_DEFAULT_RECLAIM_THRESH;
	INIT_WORK(&fs_info->reclaim_bgs_work, btrfs_reclaim_bgs_work);
}

static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block *sb)
{
	int ret;

	fs_info->sb = sb;
	sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE;
	sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE);

	ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL);
	if (ret)
		return ret;

	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
	if (ret)
		return ret;

	fs_info->dirty_metadata_batch = PAGE_SIZE *
					(1 + ilog2(nr_cpu_ids));

	ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL);
	if (ret)
		return ret;

	ret = percpu_counter_init(&fs_info->dev_replace.bio_counter, 0,
			GFP_KERNEL);
	if (ret)
		return ret;

	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
					GFP_KERNEL);
	if (!fs_info->delayed_root)
		return -ENOMEM;
	btrfs_init_delayed_root(fs_info->delayed_root);

	if (sb_rdonly(sb))
		set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);

	return btrfs_alloc_stripe_hash_table(fs_info);
}

static int btrfs_uuid_rescan_kthread(void *data)
{
	struct btrfs_fs_info *fs_info = (struct btrfs_fs_info *)data;
	int ret;

	/*
	 * 1st step is to iterate through the existing UUID tree and
	 * to delete all entries that contain outdated data.
	 * 2nd step is to add all missing entries to the UUID tree.
	 */
	ret = btrfs_uuid_tree_iterate(fs_info);
	if (ret < 0) {
		if (ret != -EINTR)
			btrfs_warn(fs_info, "iterating uuid_tree failed %d",
				   ret);
		up(&fs_info->uuid_tree_rescan_sem);
		return ret;
	}
	return btrfs_uuid_scan_kthread(data);
}

static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info)
{
	struct task_struct *task;

	down(&fs_info->uuid_tree_rescan_sem);
	task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
	if (IS_ERR(task)) {
		/* fs_info->update_uuid_tree_gen remains 0 in all error case */
		btrfs_warn(fs_info, "failed to start uuid_rescan task");
		up(&fs_info->uuid_tree_rescan_sem);
		return PTR_ERR(task);
	}

	return 0;
}

/*
 * Some options only have meaning at mount time and shouldn't persist across
 * remounts, or be displayed. Clear these at the end of mount and remount
 * code paths.
 */
void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info)
{
	btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT);
	btrfs_clear_opt(fs_info->mount_opt, CLEAR_CACHE);
}

/*
 * Mounting logic specific to read-write file systems. Shared by open_ctree
 * and btrfs_remount when remounting from read-only to read-write.
 */
int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
{
	int ret;
	const