fs/btrfs/ctree.h

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

#ifndef BTRFS_CTREE_H
#define BTRFS_CTREE_H

#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/highmem.h>
#include <linux/fs.h>
#include <linux/rwsem.h>
#include <linux/semaphore.h>
#include <linux/completion.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/slab.h>
#include <trace/events/btrfs.h>
#include <asm/unaligned.h>
#include <linux/pagemap.h>
#include <linux/btrfs.h>
#include <linux/btrfs_tree.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/sizes.h>
#include <linux/dynamic_debug.h>
#include <linux/refcount.h>
#include <linux/crc32c.h>
#include <linux/iomap.h>
#include <linux/fscrypt.h>
#include "extent-io-tree.h"
#include "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
#include "block-rsv.h"
#include "locking.h"
#include "misc.h"

struct btrfs_trans_handle;
struct btrfs_transaction;
struct btrfs_pending_snapshot;
struct btrfs_delayed_ref_root;
struct btrfs_space_info;
struct btrfs_block_group;
struct btrfs_ordered_sum;
struct btrfs_ref;
struct btrfs_bio;
struct btrfs_ioctl_encoded_io_args;
struct btrfs_device;
struct btrfs_fs_devices;
struct btrfs_balance_control;
struct btrfs_delayed_root;
struct reloc_control;

#define BTRFS_OLDEST_GENERATION	0ULL

#define BTRFS_EMPTY_DIR_SIZE 0

#define BTRFS_DIRTY_METADATA_THRESH	SZ_32M

#define BTRFS_MAX_EXTENT_SIZE SZ_128M

static inline unsigned long btrfs_chunk_item_size(int num_stripes)
{
	BUG_ON(num_stripes == 0);
	return sizeof(struct btrfs_chunk) +
		sizeof(struct btrfs_stripe) * (num_stripes - 1);
}

#define BTRFS_SUPER_INFO_OFFSET			SZ_64K
#define BTRFS_SUPER_INFO_SIZE			4096
static_assert(sizeof(struct btrfs_super_block) == BTRFS_SUPER_INFO_SIZE);

/*
 * The reserved space at the beginning of each device.
 * It covers the primary super block and leaves space for potential use by other
 * tools like bootloaders or to lower potential damage of accidental overwrite.
 */
#define BTRFS_DEVICE_RANGE_RESERVED			(SZ_1M)

/* Read ahead values for struct btrfs_path.reada */
enum {
	READA_NONE,
	READA_BACK,
	READA_FORWARD,
	/*
	 * Similar to READA_FORWARD but unlike it:
	 *
	 * 1) It will trigger readahead even for leaves that are not close to
	 *    each other on disk;
	 * 2) It also triggers readahead for nodes;
	 * 3) During a search, even when a node or leaf is already in memory, it
	 *    will still trigger readahead for other nodes and leaves that follow
	 *    it.
	 *
	 * This is meant to be used only when we know we are iterating over the
	 * entire tree or a very large part of it.
	 */
	READA_FORWARD_ALWAYS,
};

/*
 * btrfs_paths remember the path taken from the root down to the leaf.
 * level 0 is always the leaf, and nodes[1...BTRFS_MAX_LEVEL] will point
 * to any other levels that are present.
 *
 * The slots array records the index of the item or block pointer
 * used while walking the tree.
 */
struct btrfs_path {
	struct extent_buffer *nodes[BTRFS_MAX_LEVEL];
	int slots[BTRFS_MAX_LEVEL];
	/* if there is real range locking, this locks field will change */
	u8 locks[BTRFS_MAX_LEVEL];
	u8 reada;
	/* keep some upper locks as we walk down */
	u8 lowest_level;

	/*
	 * set by btrfs_split_item, tells search_slot to keep all locks
	 * and to force calls to keep space in the nodes
	 */
	unsigned int search_for_split:1;
	unsigned int keep_locks:1;
	unsigned int skip_locking:1;
	unsigned int search_commit_root:1;
	unsigned int need_commit_sem:1;
	unsigned int skip_release_on_error:1;
	/*
	 * Indicate that new item (btrfs_search_slot) is extending already
	 * existing item and ins_len contains only the data size and not item
	 * header (ie. sizeof(struct btrfs_item) is not included).
	 */
	unsigned int search_for_extension:1;
	/* Stop search if any locks need to be taken (for read) */
	unsigned int nowait:1;
};

struct btrfs_dev_replace {
	u64 replace_state;	/* see #define above */
	time64_t time_started;	/* seconds since 1-Jan-1970 */
	time64_t time_stopped;	/* seconds since 1-Jan-1970 */
	atomic64_t num_write_errors;
	atomic64_t num_uncorrectable_read_errors;

	u64 cursor_left;
	u64 committed_cursor_left;
	u64 cursor_left_last_write_of_item;
	u64 cursor_right;

	u64 cont_reading_from_srcdev_mode;	/* see #define above */

	int is_valid;
	int item_needs_writeback;
	struct btrfs_device *srcdev;
	struct btrfs_device *tgtdev;

	struct mutex lock_finishing_cancel_unmount;
	struct rw_semaphore rwsem;

	struct btrfs_scrub_progress scrub_progress;

	struct percpu_counter bio_counter;
	wait_queue_head_t replace_wait;
};

/*
 * free clusters are used to claim free space in relatively large chunks,
 * allowing us to do less seeky writes. They are used for all metadata
 * allocations. In ssd_spread mode they are also used for data allocations.
 */
struct btrfs_free_cluster {
	spinlock_t lock;
	spinlock_t refill_lock;
	struct rb_root root;

	/* largest extent in this cluster */
	u64 max_size;

	/* first extent starting offset */
	u64 window_start;

	/* We did a full search and couldn't create a cluster */
	bool fragmented;

	struct btrfs_block_group *block_group;
	/*
	 * when a cluster is allocated from a block group, we put the
	 * cluster onto a list in the block group so that it can
	 * be freed before the block group is freed.
	 */
	struct list_head block_group_list;
};

/* Discard control. */
/*
 * Async discard uses multiple lists to differentiate the discard filter
 * parameters.  Index 0 is for completely free block groups where we need to
 * ensure the entire block group is trimmed without being lossy.  Indices
 * afterwards represent monotonically decreasing discard filter sizes to
 * prioritize what should be discarded next.
 */
#define BTRFS_NR_DISCARD_LISTS		3
#define BTRFS_DISCARD_INDEX_UNUSED	0
#define BTRFS_DISCARD_INDEX_START	1

struct btrfs_discard_ctl {
	struct workqueue_struct *discard_workers;
	struct delayed_work work;
	spinlock_t lock;
	struct btrfs_block_group *block_group;
	struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
	u64 prev_discard;
	u64 prev_discard_time;
	atomic_t discardable_extents;
	atomic64_t discardable_bytes;
	u64 max_discard_size;
	u64 delay_ms;
	u32 iops_limit;
	u32 kbps_limit;
	u64 discard_extent_bytes;
	u64 discard_bitmap_bytes;
	atomic64_t discard_bytes_saved;
};

/*
 * Exclusive operations (device replace, resize, device add/remove, balance)
 */
enum btrfs_exclusive_operation {
	BTRFS_EXCLOP_NONE,
	BTRFS_EXCLOP_BALANCE_PAUSED,
	BTRFS_EXCLOP_BALANCE,
	BTRFS_EXCLOP_DEV_ADD,
	BTRFS_EXCLOP_DEV_REMOVE,
	BTRFS_EXCLOP_DEV_REPLACE,
	BTRFS_EXCLOP_RESIZE,
	BTRFS_EXCLOP_SWAP_ACTIVATE,
};

/* Store data about transaction commits, exported via sysfs. */
struct btrfs_commit_stats {
	/* Total number of commits */
	u64 commit_count;
	/* The maximum commit duration so far in ns */
	u64 max_commit_dur;
	/* The last commit duration in ns */
	u64 last_commit_dur;
	/* The total commit duration in ns */
	u64 total_commit_dur;
};

struct btrfs_fs_info {
	u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
	unsigned long flags;
	struct btrfs_root *tree_root;
	struct btrfs_root *chunk_root;
	struct btrfs_root *dev_root;
	struct btrfs_root *fs_root;
	struct btrfs_root *quota_root;
	struct btrfs_root *uuid_root;
	struct btrfs_root *data_reloc_root;
	struct btrfs_root *block_group_root;

	/* the log root tree is a directory of all the other log roots */
	struct btrfs_root *log_root_tree;

	/* The tree that holds the global roots (csum, extent, etc) */
	rwlock_t global_root_lock;
	struct rb_root global_root_tree;

	spinlock_t fs_roots_radix_lock;
	struct radix_tree_root fs_roots_radix;

	/* block group cache stuff */
	rwlock_t block_group_cache_lock;
	struct rb_root_cached block_group_cache_tree;

	/* keep track of unallocated space */
	atomic64_t free_chunk_space;

	/* Track ranges which are used by log trees blocks/logged data extents */
	struct extent_io_tree excluded_extents;

	/* logical->physical extent mapping */
	struct extent_map_tree mapping_tree;

	/*
	 * block reservation for extent, checksum, root tree and
	 * delayed dir index item
	 */
	struct btrfs_block_rsv global_block_rsv;
	/* block reservation for metadata operations */
	struct btrfs_block_rsv trans_block_rsv;
	/* block reservation for chunk tree */
	struct btrfs_block_rsv chunk_block_rsv;
	/* block reservation for delayed operations */
	struct btrfs_block_rsv delayed_block_rsv;
	/* block reservation for delayed refs */
	struct btrfs_block_rsv delayed_refs_rsv;

	struct btrfs_block_rsv empty_block_rsv;

	u64 generation;
	u64 last_trans_committed;
	/*
	 * Generation of the last transaction used for block group relocation
	 * since the filesystem was last mounted (or 0 if none happened yet).
	 * Must be written and read while holding btrfs_fs_info::commit_root_sem.
	 */
	u64 last_reloc_trans;
	u64 avg_delayed_ref_runtime;

	/*
	 * this is updated to the current trans every time a full commit
	 * is required instead of the faster short fsync log commits
	 */
	u64 last_trans_log_full_commit;
	unsigned long mount_opt;

	unsigned long compress_type:4;
	unsigned int compress_level;
	u32 commit_interval;
	/*
	 * It is a suggestive number, the read side is safe even it gets a
	 * wrong number because we will write out the data into a regular
	 * extent. The write side(mount/remount) is under ->s_umount lock,
	 * so it is also safe.
	 */
	u64 max_inline;

	struct btrfs_transaction *running_transaction;
	wait_queue_head_t transaction_throttle;
	wait_queue_head_t transaction_wait;
	wait_queue_head_t transaction_blocked_wait;
	wait_queue_head_t async_submit_wait;

	/*
	 * Used to protect the incompat_flags, compat_flags, compat_ro_flags
	 * when they are updated.
	 *
	 * Because we do not clear the flags for ever, so we needn't use
	 * the lock on the read side.
	 *
	 * We also needn't use the lock when we mount the fs, because
	 * there is no other task which will update the flag.
	 */
	spinlock_t super_lock;
	struct btrfs_super_block *super_copy;
	struct btrfs_super_block *super_for_commit;
	struct super_block *sb;
	struct inode *btree_inode;
	struct mutex tree_log_mutex;
	struct mutex transaction_kthread_mutex;
	struct mutex cleaner_mutex;
	struct mutex chunk_mutex;

	/*
	 * this is taken to make sure we don't set block groups ro after
	 * the free space cache has been allocated on them
	 */
	struct mutex ro_block_group_mutex;

	/* this is used during read/modify/write to make sure
	 * no two ios are trying to mod the same stripe at the same
	 * time
	 */
	struct btrfs_stripe_hash_table *stripe_hash_table;

	/*
	 * this protects the ordered operations list only while we are
	 * processing all of the entries on it.  This way we make
	 * sure the commit code doesn't find the list temporarily empty
	 * because another function happens to be doing non-waiting preflush
	 * before jumping into the main commit.
	 */
	struct mutex ordered_operations_mutex;

	struct rw_semaphore commit_root_sem;

	struct rw_semaphore cleanup_work_sem;

	struct rw_semaphore subvol_sem;

	spinlock_t trans_lock;
	/*
	 * the reloc mutex goes with the trans lock, it is taken
	 * during commit to protect us from the relocation code
	 */
	struct mutex reloc_mutex;

	struct list_head trans_list;
	struct list_head dead_roots;
	struct list_head caching_block_groups;

	spinlock_t delayed_iput_lock;
	struct list_head delayed_iputs;
	atomic_t nr_delayed_iputs;
	wait_queue_head_t delayed_iputs_wait;

	atomic64_t tree_mod_seq;

	/* this protects tree_mod_log and tree_mod_seq_list */
	rwlock_t tree_mod_log_lock;
	struct rb_root tree_mod_log;
	struct list_head tree_mod_seq_list;

	atomic_t async_delalloc_pages;

	/*
	 * this is used to protect the following list -- ordered_roots.
	 */
	spinlock_t ordered_root_lock;

	/*
	 * all fs/file tree roots in which there are data=ordered extents
	 * pending writeback are added into this list.
	 *
	 * these can span multiple transactions and basically include
	 * every dirty data page that isn't from nodatacow
	 */
	struct list_head ordered_roots;

	struct mutex delalloc_root_mutex;
	spinlock_t delalloc_root_lock;
	/* all fs/file tree roots that have delalloc inodes. */
	struct list_head delalloc_roots;

	/*
	 * there is a pool of worker threads for checksumming during writes
	 * and a pool for checksumming after reads.  This is because readers
	 * can run with FS locks held, and the writers may be waiting for
	 * those locks.  We don't want ordering in the pending list to cause
	 * deadlocks, and so the two are serviced separately.
	 *
	 * A third pool does submit_bio to avoid deadlocking with the other
	 * two
	 */
	struct btrfs_workqueue *workers;
	struct btrfs_workqueue *hipri_workers;
	struct btrfs_workqueue *delalloc_workers;
	struct btrfs_workqueue *flush_workers;
	struct workqueue_struct *endio_workers;
	struct workqueue_struct *endio_meta_workers;
	struct workqueue_struct *endio_raid56_workers;
	struct workqueue_struct *rmw_workers;
	struct workqueue_struct *compressed_write_workers;
	struct btrfs_workqueue *endio_write_workers;
	struct btrfs_workqueue *endio_freespace_worker;
	struct btrfs_workqueue *caching_workers;

	/*
	 * fixup workers take dirty pages that didn't properly go through
	 * the cow mechanism and make them safe to write.  It happens
	 * for the sys_munmap function call path
	 */
	struct btrfs_workqueue *fixup_workers;
	struct btrfs_workqueue *delayed_workers;

	struct task_struct *transaction_kthread;
	struct task_struct *cleaner_kthread;
	u32 thread_pool_size;

	struct kobject *space_info_kobj;
	struct kobject *qgroups_kobj;
	struct kobject *discard_kobj;

	/* used to keep from writing metadata until there is a nice batch */
	struct percpu_counter dirty_metadata_bytes;
	struct percpu_counter delalloc_bytes;
	struct percpu_counter ordered_bytes;
	s32 dirty_metadata_batch;
	s32 delalloc_batch;

	struct list_head dirty_cowonly_roots;

	struct btrfs_fs_devices *fs_devices;

	/*
	 * The space_info list is effectively read only after initial
	 * setup.  It is populated at mount time and cleaned up after
	 * all block groups are removed.  RCU is used to protect it.
	 */
	struct list_head space_info;

	struct btrfs_space_info *data_sinfo;

	struct reloc_control *reloc_ctl;

	/* data_alloc_cluster is only used in ssd_spread mode */
	struct btrfs_free_cluster data_alloc_cluster;

	/* all metadata allocations go through this cluster */
	struct btrfs_free_cluster meta_alloc_cluster;

	/* auto defrag inodes go here */
	spinlock_t defrag_inodes_lock;
	struct rb_root defrag_inodes;
	atomic_t defrag_running;

	/* Used to protect avail_{data, metadata, system}_alloc_bits */
	seqlock_t profiles_lock;
	/*
	 * these three are in extended format (availability of single
	 * chunks is denoted by BTRFS_AVAIL_ALLOC_BIT_SINGLE bit, other
	 * types are denoted by corresponding BTRFS_BLOCK_GROUP_* bits)
	 */
	u64 avail_data_alloc_bits;
	u64 avail_metadata_alloc_bits;
	u64 avail_system_alloc_bits;

	/* restriper state */
	spinlock_t balance_lock;
	struct mutex balance_mutex;
	atomic_t balance_pause_req;
	atomic_t balance_cancel_req;
	struct btrfs_balance_control *balance_ctl;
	wait_queue_head_t balance_wait_q;

	/* Cancellation requests for chunk relocation */
	atomic_t reloc_cancel_req;

	u32 data_chunk_allocations;
	u32 metadata_ratio;

	void *bdev_holder;

	/* private scrub information */
	struct mutex scrub_lock;
	atomic_t scrubs_running;
	atomic_t scrub_pause_req;
	atomic_t scrubs_paused;
	atomic_t scrub_cancel_req;
	wait_queue_head_t scrub_pause_wait;
	/*
	 * The worker pointers are NULL iff the refcount is 0, ie. scrub is not
	 * running.
	 */
	refcount_t scrub_workers_refcnt;
	struct workqueue_struct *scrub_workers;
	struct workqueue_struct *scrub_wr_completion_workers;
	struct workqueue_struct *scrub_parity_workers;
	struct btrfs_subpage_info *subpage_info;

	struct btrfs_discard_ctl discard_ctl;

#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
	u32 check_integrity_print_mask;
#endif
	/* is qgroup tracking in a consistent state? */
	u64 qgroup_flags;

	/* holds configuration and tracking. Protected by qgroup_lock */
	struct rb_root qgroup_tree;
	spinlock_t qgroup_lock;

	/*
	 * used to avoid frequently calling ulist_alloc()/ulist_free()
	 * when doing qgroup accounting, it must be protected by qgroup_lock.
	 */
	struct ulist *qgroup_ulist;

	/*
	 * Protect user change for quota operations. If a transaction is needed,
	 * it must be started before locking this lock.
	 */
	struct mutex qgroup_ioctl_lock;

	/* list of dirty qgroups to be written at next commit */
	struct list_head dirty_qgroups;

	/* used by qgroup for an efficient tree traversal */
	u64 qgroup_seq;

	/* qgroup rescan items */
	struct mutex qgroup_rescan_lock; /* protects the progress item */
	struct btrfs_key qgroup_rescan_progress;
	struct btrfs_workqueue *qgroup_rescan_workers;
	struct completion qgroup_rescan_completion;
	struct btrfs_work qgroup_rescan_work;
	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
	u8 qgroup_drop_subtree_thres;

	/* filesystem state */
	unsigned long fs_state;

	struct btrfs_delayed_root *delayed_root;

	/* Extent buffer radix tree */
	spinlock_t buffer_lock;
	/* Entries are eb->start / sectorsize */
	struct radix_tree_root buffer_radix;

	/* next backup root to be overwritten */
	int backup_root_index;

	/* device replace state */
	struct btrfs_dev_replace dev_replace;

	struct semaphore uuid_tree_rescan_sem;

	/* Used to reclaim the metadata space in the background. */
	struct work_struct async_reclaim_work;
	struct work_struct async_data_reclaim_work;
	struct work_struct preempt_reclaim_work;

	/* Reclaim partially filled block groups in the background */
	struct work_struct reclaim_bgs_work;
	struct list_head reclaim_bgs;
	int bg_reclaim_threshold;

	spinlock_t unused_bgs_lock;
	struct list_head unused_bgs;
	struct mutex unused_bg_unpin_mutex;
	/* Protect block groups that are going to be deleted */
	struct mutex reclaim_bgs_lock;

	/* Cached block sizes */
	u32 nodesize;
	u32 sectorsize;
	/* ilog2 of sectorsize, use to avoid 64bit division */
	u32 sectorsize_bits;
	u32 csum_size;
	u32 csums_per_leaf;
	u32 stripesize;

	/*
	 * Maximum size of an extent. BTRFS_MAX_EXTENT_SIZE on regular
	 * filesystem, on zoned it depends on the device constraints.
	 */
	u64 max_extent_size;

	/* Block groups and devices containing active swapfiles. */
	spinlock_t swapfile_pins_lock;
	struct rb_root swapfile_pins;

	struct crypto_shash *csum_shash;

	/* Type of exclusive operation running, protected by super_lock */
	enum btrfs_exclusive_operation exclusive_operation;

	/*
	 * Zone size > 0 when in ZONED mode, otherwise it's used for a check
	 * if the mode is enabled
	 */
	u64 zone_size;

	/* Max size to emit ZONE_APPEND write command */
	u64 max_zone_append_size;
	struct mutex zoned_meta_io_lock;
	spinlock_t treelog_bg_lock;
	u64 treelog_bg;

	/*
	 * Start of the dedicated data relocation block group, protected by
	 * relocation_bg_lock.
	 */
	spinlock_t relocation_bg_lock;
	u64 data_reloc_bg;
	struct mutex zoned_data_reloc_io_lock;

	u64 nr_global_roots;

	spinlock_t zone_active_bgs_lock;
	struct list_head zone_active_bgs;

	/* Updates are not protected by any lock */
	struct btrfs_commit_stats commit_stats;

	/*
	 * Last generation where we dropped a non-relocation root.
	 * Use btrfs_set_last_root_drop_gen() and btrfs_get_last_root_drop_gen()
	 * to change it and to read it, respectively.
	 */
	u64 last_root_drop_gen;

	/*
	 * Annotations for transaction events (structures are empty when
	 * compiled without lockdep).
	 */
	struct lockdep_map btrfs_trans_num_writers_map;
	struct lockdep_map btrfs_trans_num_extwriters_map;
	struct lockdep_map btrfs_state_change_map[4];
	struct lockdep_map btrfs_trans_pending_ordered_map;
	struct lockdep_map btrfs_ordered_extent_map;

#ifdef CONFIG_BTRFS_FS_REF_VERIFY
	spinlock_t ref_verify_lock;
	struct rb_root block_tree;
#endif

#ifdef CONFIG_BTRFS_DEBUG
	struct kobject *debug_kobj;
	struct list_head allocated_roots;

	spinlock_t eb_leak_lock;
	struct list_head allocated_ebs;
#endif
};

static inline void btrfs_set_last_root_drop_gen(struct btrfs_fs_info *fs_info,
						u64 gen)
{
	WRITE_ONCE(fs_info->last_root_drop_gen, gen);
}

static inline u64 btrfs_get_last_root_drop_gen(const struct btrfs_fs_info *fs_info)
{
	return READ_ONCE(fs_info->last_root_drop_gen);
}

static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
{
	return sb->s_fs_info;
}

/*
 * Take the number of bytes to be checksummed and figure out how many leaves
 * it would require to store the csums for that many bytes.
 */
static inline u64 btrfs_csum_bytes_to_leaves(
			const struct btrfs_fs_info *fs_info, u64 csum_bytes)
{
	const u64 num_csums = csum_bytes >> fs_info->sectorsize_bits;

	return DIV_ROUND_UP_ULL(num_csums, fs_info->csums_per_leaf);
}

/*
 * Use this if we would be adding new items, as we could split nodes as we cow
 * down the tree.
 */
static inline u64 btrfs_calc_insert_metadata_size(struct btrfs_fs_info *fs_info,
						  unsigned num_items)
{
	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
}

/*
 * Doing a truncate or a modification won't result in new nodes or leaves, just
 * what we need for COW.
 */
static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
						 unsigned num_items)
{
	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
}

#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
					sizeof(struct btrfs_item))

static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
{
	return fs_info->zone_size > 0;
}

/*
 * Count how many fs_info->max_extent_size cover the @size
 */
static inline u32 count_max_extents(struct btrfs_fs_info *fs_info, u64 size)
{
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
	if (!fs_info)
		return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
#endif

	return div_u64(size + fs_info->max_extent_size - 1, fs_info->max_extent_size);
}

bool btrfs_exclop_start(struct btrfs_fs_info *fs_info,
			enum btrfs_exclusive_operation type);
bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info,
				 enum btrfs_exclusive_operation type);
void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info);
void btrfs_exclop_finish(struct btrfs_fs_info *fs_info);
void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
			  enum btrfs_exclusive_operation op);

/*
 * The state of btrfs root
 */
enum {
	/*
	 * btrfs_record_root_in_trans is a multi-step process, and it can race
	 * with the balancing code.   But the race is very small, and only the
	 * first time the root is added to each transaction.  So IN_TRANS_SETUP
	 * is used to tell us when more checks are required
	 */
	BTRFS_ROOT_IN_TRANS_SETUP,

	/*
	 * Set if tree blocks of this root can be shared by other roots.
	 * Only subvolume trees and their reloc trees have this bit set.
	 * Conflicts with TRACK_DIRTY bit.
	 *
	 * This affects two things:
	 *
	 * - How balance works
	 *   For shareable roots, we need to use reloc tree and do path
	 *   replacement for balance, and need various pre/post hooks for
	 *   snapshot creation to handle them.
	 *
	 *   While for non-shareable trees, we just simply do a tree search
	 *   with COW.
	 *
	 * - How dirty roots are tracked
	 *   For shareable roots, btrfs_record_root_in_trans() is needed to
	 *   track them, while non-subvolume roots have TRACK_DIRTY bit, they
	 *   don't need to set this manually.
	 */
	BTRFS_ROOT_SHAREABLE,
	BTRFS_ROOT_TRACK_DIRTY,
	BTRFS_ROOT_IN_RADIX,
	BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
	BTRFS_ROOT_DEFRAG_RUNNING,
	BTRFS_ROOT_FORCE_COW,
	BTRFS_ROOT_MULTI_LOG_TASKS,
	BTRFS_ROOT_DIRTY,
	BTRFS_ROOT_DELETING,

	/*
	 * Reloc tree is orphan, only kept here for qgroup delayed subtree scan
	 *
	 * Set for the subvolume tree owning the reloc tree.
	 */
	BTRFS_ROOT_DEAD_RELOC_TREE,
	/* Mark dead root stored on device whose cleanup needs to be resumed */
	BTRFS_ROOT_DEAD_TREE,
	/* The root has a log tree. Used for subvolume roots and the tree root. */
	BTRFS_ROOT_HAS_LOG_TREE,
	/* Qgroup flushing is in progress */
	BTRFS_ROOT_QGROUP_FLUSHING,
	/* We started the orphan cleanup for this root. */
	BTRFS_ROOT_ORPHAN_CLEANUP,
	/* This root has a drop operation that was started previously. */
	BTRFS_ROOT_UNFINISHED_DROP,
	/* This reloc root needs to have its buffers lockdep class reset. */
	BTRFS_ROOT_RESET_LOCKDEP_CLASS,
};

enum btrfs_lockdep_trans_states {
	BTRFS_LOCKDEP_TRANS_COMMIT_START,
	BTRFS_LOCKDEP_TRANS_UNBLOCKED,
	BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED,
	BTRFS_LOCKDEP_TRANS_COMPLETED,
};

/*
 * Lockdep annotation for wait events.
 *
 * @owner:  The struct where the lockdep map is defined
 * @lock:   The lockdep map corresponding to a wait event
 *
 * This macro is used to annotate a wait event. In this case a thread acquires
 * the lockdep map as writer (exclusive lock) because it has to block until all
 * the threads that hold the lock as readers signal the condition for the wait
 * event and release their locks.
 */
#define btrfs_might_wait_for_event(owner, lock)					\
	do {									\
		rwsem_acquire(&owner->lock##_map, 0, 0, _THIS_IP_);		\
		rwsem_release(&owner->lock##_map, _THIS_IP_);			\
	} while (0)

/*
 * Protection for the resource/condition of a wait event.
 *
 * @owner:  The struct where the lockdep map is defined
 * @lock:   The lockdep map corresponding to a wait event
 *
 * Many threads can modify the condition for the wait event at the same time
 * and signal the threads that block on the wait event. The threads that modify
 * the condition and do the signaling acquire the lock as readers (shared
 * lock).
 */
#define btrfs_lockdep_acquire(owner, lock)					\
	rwsem_acquire_read(&owner->lock##_map, 0, 0, _THIS_IP_)

/*
 * Used after signaling the condition for a wait event to release the lockdep
 * map held by a reader thread.
 */
#define btrfs_lockdep_release(owner, lock)					\
	rwsem_release(&owner->lock##_map, _THIS_IP_)

/*
 * Macros for the transaction states wait events, similar to the generic wait
 * event macros.
 */
#define btrfs_might_wait_for_state(owner, i)					\
	do {									\
		rwsem_acquire(&owner->btrfs_state_change_map[i], 0, 0, _THIS_IP_); \
		rwsem_release(&owner->btrfs_state_change_map[i], _THIS_IP_);	\
	} while (0)

#define btrfs_trans_state_lockdep_acquire(owner, i)				\
	rwsem_acquire_read(&owner->btrfs_state_change_map[i], 0, 0, _THIS_IP_)

#define btrfs_trans_state_lockdep_release(owner, i)				\
	rwsem_release(&owner->btrfs_state_change_map[i], _THIS_IP_)

/* Initialization of the lockdep map */
#define btrfs_lockdep_init_map(owner, lock)					\
	do {									\
		static struct lock_class_key lock##_key;			\
		lockdep_init_map(&owner->lock##_map, #lock, &lock##_key, 0);	\
	} while (0)

/* Initialization of the transaction states lockdep maps. */
#define btrfs_state_lockdep_init_map(owner, lock, state)			\
	do {									\
		static struct lock_class_key lock##_key;			\
		lockdep_init_map(&owner->btrfs_state_change_map[state], #lock,	\
				 &lock##_key, 0);				\
	} while (0)

/*
 * Record swapped tree blocks of a subvolume tree for delayed subtree trace
 * code. For detail check comment in fs/btrfs/qgroup.c.
 */
struct btrfs_qgroup_swapped_blocks {
	spinlock_t lock;
	/* RM_EMPTY_ROOT() of above blocks[] */
	bool swapped;
	struct rb_root blocks[BTRFS_MAX_LEVEL];
};

/*
 * in ram representation of the tree.  extent_root is used for all allocations
 * and for the extent tree extent_root root.
 */
struct btrfs_root {
	struct rb_node rb_node;

	struct extent_buffer *node;

	struct extent_buffer *commit_root;
	struct btrfs_root *log_root;
	struct btrfs_root *reloc_root;

	unsigned long state;
	struct btrfs_root_item root_item;
	struct btrfs_key root_key;
	struct btrfs_fs_info *fs_info;
	struct extent_io_tree dirty_log_pages;

	struct mutex objectid_mutex;

	spinlock_t accounting_lock;
	struct btrfs_block_rsv *block_rsv;

	struct mutex log_mutex;
	wait_queue_head_t log_writer_wait;
	wait_queue_head_t log_commit_wait[2];
	struct list_head log_ctxs[2];
	/* Used only for log trees of subvolumes, not for the log root tree */
	atomic_t log_writers;
	atomic_t log_commit[2];
	/* Used only for log trees of subvolumes, not for the log root tree */
	atomic_t log_batch;
	int log_transid;
	/* No matter the commit succeeds or not*/
	int log_transid_committed;
	/* Just be updated when the commit succeeds. */
	int last_log_commit;
	pid_t log_start_pid;

	u64 last_trans;

	u32 type;

	u64 free_objectid;

	struct btrfs_key defrag_progress;
	struct btrfs_key defrag_max;

	/* The dirty list is only used by non-shareable roots */
	struct list_head dirty_list;

	struct list_head root_list;

	spinlock_t log_extents_lock[2];
	struct list_head logged_list[2];

	spinlock_t inode_lock;
	/* red-black tree that keeps track of in-memory inodes */
	struct rb_root inode_tree;

	/*
	 * radix tree that keeps track of delayed nodes of every inode,
	 * protected by inode_lock
	 */
	struct radix_tree_root delayed_nodes_tree;
	/*
	 * right now this just gets used so that a root has its own devid
	 * for stat.  It may be used for more later
	 */
	dev_t anon_dev;

	spinlock_t root_item_lock;
	refcount_t refs;

	struct mutex delalloc_mutex;
	spinlock_t delalloc_lock;
	/*
	 * all of the inodes that have delalloc bytes.  It is possible for
	 * this list to be empty even when there is still dirty data=ordered
	 * extents waiting to finish IO.
	 */
	struct list_head delalloc_inodes;
	struct list_head delalloc_root;
	u64 nr_delalloc_inodes;

	struct mutex ordered_extent_mutex;
	/*
	 * this is used by the balancing code to wait for all the pending
	 * ordered extents
	 */
	spinlock_t ordered_extent_lock;

	/*
	 * all of the data=ordered extents pending writeback
	 * these can span multiple transactions and basically include
	 * every dirty data page that isn't from nodatacow
	 */
	struct list_head ordered_extents;
	struct list_head ordered_root;
	u64 nr_ordered_extents;

	/*
	 * Not empty if this subvolume root has gone through tree block swap
	 * (relocation)
	 *
	 * Will be used by reloc_control::dirty_subvol_roots.
	 */
	struct list_head reloc_dirty_list;

	/*
	 * Number of currently running SEND ioctls to prevent
	 * manipulation with the read-only status via SUBVOL_SETFLAGS
	 */
	int send_in_progress;
	/*
	 * Number of currently running deduplication operations that have a
	 * destination inode belonging to this root. Protected by the lock
	 * root_item_lock.
	 */
	int dedupe_in_progress;
	/* For exclusion of snapshot creation and nocow writes */
	struct btrfs_drew_lock snapshot_lock;

	atomic_t snapshot_force_cow;

	/* For qgroup metadata reserved space */
	spinlock_t qgroup_meta_rsv_lock;
	u64 qgroup_meta_rsv_pertrans;
	u64 qgroup_meta_rsv_prealloc;
	wait_queue_head_t qgroup_flush_wait;

	/* Number of active swapfiles */
	atomic_t nr_swapfiles;

	/* Record pairs of swapped blocks for qgroup */
	struct btrfs_qgroup_swapped_blocks swapped_blocks;

	/* Used only by log trees, when logging csum items */
	struct extent_io_tree log_csum_range;

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
	u64 alloc_bytenr;
#endif

#ifdef CONFIG_BTRFS_DEBUG
	struct list_head leak_list;
#endif
};

/*
 * Structure that conveys information about an extent that is going to replace
 * all the extents in a file range.
 */
struct btrfs_replace_extent_info {
	u64 disk_offset;
	u64 disk_len;
	u64 data_offset;
	u64 data_len;
	u64 file_offset;
	/* Pointer to a file extent item of type regular or prealloc. */
	char *extent_buf;
	/*
	 * Set to true when attempting to replace a file range with a new extent
	 * described by this structure, set to false when attempting to clone an
	 * existing extent into a file range.
	 */
	bool is_new_extent;
	/* Indicate if we should update the inode's mtime and ctime. */
	bool update_times;
	/* Meaningful only if is_new_extent is true. */
	int qgroup_reserved;
	/*
	 * Meaningful only if is_new_extent is true.
	 * Used to track how many extent items we have already inserted in a
	 * subvolume tree that refer to the extent described by this structure,
	 * so that we know when to create a new delayed ref or update an existing
	 * one.
	 */
	int insertions;
};

/* Arguments for btrfs_drop_extents() */
struct btrfs_drop_extents_args {
	/* Input parameters */

	/*
	 * If NULL, btrfs_drop_extents() will allocate and free its own path.
	 * If 'replace_extent' is true, this must not be NULL. Also the path
	 * is always released except if 'replace_extent' is true and
	 * btrfs_drop_extents() sets 'extent_inserted' to true, in which case
	 * the path is kept locked.
	 */
	struct btrfs_path *path;
	/* Start offset of the range to drop extents from */
	u64 start;
	/* End (exclusive, last byte + 1) of the range to drop extents from */
	u64 end;
	/* If true drop all the extent maps in the range */
	bool drop_cache;
	/*
	 * If true it means we want to insert a new extent after dropping all
	 * the extents in the range. If this is true, the 'extent_item_size'
	 * parameter must be set as well and the 'extent_inserted' field will
	 * be set to true by btrfs_drop_extents() if it could insert the new
	 * extent.
	 * Note: when this is set to true the path must not be NULL.
	 */
	bool replace_extent;
	/*
	 * Used if 'replace_extent' is true. Size of the file extent item to
	 * insert after dropping all existing extents in the range
	 */
	u32 extent_item_size;

	/* Output parameters */

	/*
	 * Set to the minimum between the input parameter 'end' and the end
	 * (exclusive, last byte + 1) of the last dropped extent. This is always
	 * set even if btrfs_drop_extents() returns an error.
	 */
	u64 drop_end;
	/*
	 * The number of allocated bytes found in the range. This can be smaller
	 * than the range's length when there are holes in the range.
	 */
	u64 bytes_found;
	/*
	 * Only set if 'replace_extent' is true. Set to true if we were able
	 * to insert a replacement extent after dropping all extents in the
	 * range, otherwise set to false by btrfs_drop_extents().
	 * Also, if btrfs_drop_extents() has set this to true it means it
	 * returned with the path locked, otherwise if it has set this to
	 * false it has returned with the path released.
	 */
	bool extent_inserted;
};

struct btrfs_file_private {
	void *filldir_buf;
};


static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
{

	return info->nodesize - sizeof(struct btrfs_header);
}

static inline u32 BTRFS_MAX_ITEM_SIZE(const struct btrfs_fs_info *info)
{
	return BTRFS_LEAF_DATA_SIZE(info) - sizeof(struct btrfs_item);
}

static inline u32 BTRFS_NODEPTRS_PER_BLOCK(const struct btrfs_fs_info *info)
{
	return BTRFS_LEAF_DATA_SIZE(info) / sizeof(struct btrfs_key_ptr);
}

#define BTRFS_FILE_EXTENT_INLINE_DATA_START		\
		(offsetof(struct btrfs_file_extent_item, disk_bytenr))
static inline u32 BTRFS_MAX_INLINE_DATA_SIZE(const struct btrfs_fs_info *info)
{
	return BTRFS_MAX_ITEM_SIZE(info) -
	       BTRFS_FILE_EXTENT_INLINE_DATA_START;
}

static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
{
	return BTRFS_MAX_ITEM_SIZE(info) - sizeof(struct btrfs_dir_item);
}

#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
				((bytes) >> (fs_info)->sectorsize_bits)

static inline u32 btrfs_crc32c(u32 crc, const void *address, unsigned length)
{
	return crc32c(crc, address, length);
}

static inline void btrfs_crc32c_final(u32 crc, u8 *result)
{
	put_unaligned_le32(~crc, result);
}

static inline u64 btrfs_name_hash(const char *name, int len)
{
       return crc32c((u32)~1, name, len);
}

/*
 * Figure the key offset of an extended inode ref
 */
static inline u64 btrfs_extref_hash(u64 parent_objectid, const char *name,
                                   int len)
{
       return (u64) crc32c(parent_objectid, name, len);
}

static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
{
	return mapping_gfp_constraint(mapping, ~__GFP_FS);
}

/* extent-tree.c */

enum btrfs_inline_ref_type {
	BTRFS_REF_TYPE_INVALID,
	BTRFS_REF_TYPE_BLOCK,
	BTRFS_REF_TYPE_DATA,
	BTRFS_REF_TYPE_ANY,
};

int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
				     struct btrfs_extent_inline_ref *iref,
				     enum btrfs_inline_ref_type is_data);
u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset);


int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
			      u64 start, u64 num_bytes);
void btrfs_free_excluded_extents(struct btrfs_block_group *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
			   unsigned long count);
void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
				  struct btrfs_delayed_ref_root *delayed_refs,
				  struct btrfs_delayed_ref_head *head);
int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
			     struct btrfs_fs_info *fs_info, u64 bytenr,
			     u64 offset, int metadata, u64 *refs, u64 *flags);
int btrfs_pin_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num,
		     int reserved);
int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
				    u64 bytenr, u64 num_bytes);
int btrfs_exclude_logged_extents(struct extent_buffer *eb);
int btrfs_cross_ref_exist(struct btrfs_root *root,
			  u64 objectid, u64 offset, u64 bytenr, bool strict,
			  struct btrfs_path *path);
struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
					     struct btrfs_root *root,
					     u64 parent, u64 root_objectid,
					     const struct btrfs_disk_key *key,
					     int level, u64 hint,
					     u64 empty_size,
					     enum btrfs_lock_nesting nest);
void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
			   u64 root_id,
			   struct extent_buffer *buf,
			   u64 parent, int last_ref);
int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
				     struct btrfs_root *root, u64 owner,
				     u64 offset, u64 ram_bytes,
				     struct btrfs_key *ins);
int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
				   u64 root_objectid, u64 owner, u64 offset,
				   struct btrfs_key *ins);
int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
			 u64 min_alloc_size, u64 empty_size, u64 hint_byte,
			 struct btrfs_key *ins, int is_data, int delalloc);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		  struct extent_buffer *buf, int full_backref);
int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		  struct extent_buffer *buf, int full_backref);
int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
				struct extent_buffer *eb, u64 flags, int level);
int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref);

int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
			       u64 start, u64 len, int delalloc);
int btrfs_pin_reserved_extent(struct btrfs_trans_handle *trans, u64 start,
			      u64 len);
int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans);
int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
			 struct btrfs_ref *generic_ref);

void btrfs_clear_space_info_full(struct btrfs_fs_info *info);

int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
				     struct btrfs_block_rsv *rsv,
				     int nitems, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_root *root,
				      struct btrfs_block_rsv *rsv);
void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);

int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
				    u64 disk_num_bytes, bool noflush);
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
				   u64 start, u64 end);
int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
			 u64 num_bytes, u64 *actual_bytes);
int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);

int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
					 struct btrfs_fs_info *fs_info);
int btrfs_start_write_no_snapshotting(struct btrfs_root *root);
void btrfs_end_write_no_snapshotting(struct btrfs_root *root);
void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);

/* ctree.c */
int __init btrfs_ctree_init(void);
void __cold btrfs_ctree_exit(void);
int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
		     int *slot);
int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
int btrfs_previous_item(struct btrfs_root *root,
			struct btrfs_path *path, u64 min_objectid,
			int type);
int btrfs_previous_extent_item(struct btrfs_root *root,
			struct btrfs_path *path, u64 min_objectid);
void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
			     struct btrfs_path *path,
			     const struct btrfs_key *new_key);
struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
			struct btrfs_key *key, int lowest_level,
			u64 min_trans);
int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
			 struct btrfs_path *path,
			 u64 min_trans);
struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent,
					   int slot);

int btrfs_cow_block(struct btrfs_trans_handle *trans,
		    struct btrfs_root *root, struct extent_buffer *buf,
		    struct extent_buffer *parent, int parent_slot,
		    struct extent_buffer **cow_ret,
		    enum btrfs_lock_nesting nest);
int btrfs_copy_root(struct btrfs_trans_handle *trans,
		      struct btrfs_root *root,
		      struct extent_buffer *buf,
		      struct extent_buffer **cow_ret, u64 new_root_objectid);
int btrfs_block_can_be_shared(struct btrfs_root *root,
			      struct extent_buffer *buf);
void btrfs_extend_item(struct btrfs_path *path, u32 data_size);
void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end);
int btrfs_split_item(struct btrfs_trans_handle *trans,
		     struct btrfs_root *root,
		     struct btrfs_path *path,
		     const struct btrfs_key *new_key,
		     unsigned long split_offset);
int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
			 struct btrfs_root *root,
			 struct btrfs_path *path,
			 const struct btrfs_key *new_key);
int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
		u64 inum, u64 ioff, u8 key_type, struct btrfs_key *found_key);
int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		      const struct btrfs_key *key, struct btrfs_path *p,
		      int ins_len, int cow);
int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
			  struct btrfs_path *p, u64 time_seq);
int btrfs_search_slot_for_read(struct btrfs_root *root,
			       const struct btrfs_key *key,
			       struct btrfs_path *p, int find_higher,
			       int return_any);
int btrfs_realloc_node(struct btrfs_trans_handle *trans,
		       struct btrfs_root *root, struct extent_buffer *parent,
		       int start_slot, u64 *last_ret,
		       struct btrfs_key *progress);
void btrfs_release_path(struct btrfs_path *p);
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);

int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		   struct btrfs_path *path, int slot, int nr);
static inline int btrfs_del_item(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root,
				 struct btrfs_path *path)
{
	return btrfs_del_items(trans, root, path, path->slots[0], 1);
}

/*
 * Describes a batch of items to insert in a btree. This is used by
 * btrfs_insert_empty_items().
 */
struct btrfs_item_batch {
	/*
	 * Pointer to an array containing the keys of the items to insert (in
	 * sorted order).
	 */
	const struct btrfs_key *keys;
	/* Pointer to an array containing the data size for each item to insert. */
	const u32 *data_sizes;
	/*
	 * The sum of data sizes for all items. The caller can compute this while
	 * setting up the data_sizes array, so it ends up being more efficient
	 * than having btrfs_insert_empty_items() or setup_item_for_insert()
	 * doing it, as it would avoid an extra loop over a potentially large
	 * array, and in the case of setup_item_for_insert(), we would be doing
	 * it while holding a write lock on a leaf and often on upper level nodes
	 * too, unnecessarily increasing the size of a critical section.
	 */
	u32 total_data_size;
	/* Size of the keys and data_sizes arrays (number of items in the batch). */
	int nr;
};

void btrfs_setup_item_for_insert(struct btrfs_root *root,
				 struct btrfs_path *path,
				 const struct btrfs_key *key,
				 u32 data_size);
int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		      const struct btrfs_key *key, void *data, u32 data_size);
int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root,
			     struct btrfs_path *path,
			     const struct btrfs_item_batch *batch);

static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
					  struct btrfs_root *root,
					  struct btrfs_path *path,
					  const struct btrfs_key *key,
					  u32 data_size)
{
	struct btrfs_item_batch batch;

	batch.keys = key;
	batch.data_sizes = &data_size;
	batch.total_data_size = data_size;
	batch.nr = 1;

	return btrfs_insert_empty_items(trans, root, path, &batch);
}

int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
			u64 time_seq);

int btrfs_search_backwards(struct btrfs_root *root, struct btrfs_key *key,
			   struct btrfs_path *path);

int btrfs_get_next_valid_item(struct btrfs_root *root, struct btrfs_key *key,
			      struct btrfs_path *path);

/*
 * Search in @root for a given @key, and store the slot found in @found_key.
 *
 * @root:	The root node of the tree.
 * @key:	The key we are looking for.
 * @found_key:	Will hold the found item.
 * @path:	Holds the current slot/leaf.
 * @iter_ret:	Contains the value returned from btrfs_search_slot or
 * 		btrfs_get_next_valid_item, whichever was executed last.
 *
 * The @iter_ret is an output variable that will contain the return value of
 * btrfs_search_slot, if it encountered an error, or the value returned from
 * btrfs_get_next_valid_item otherwise. That return value can be 0, if a valid
 * slot was found, 1 if there were no more leaves, and <0 if there was an error.
 *
 * It's recommended to use a separate variable for iter_ret and then use it to
 * set the function return value so there's no confusion of the 0/1/errno
 * values stemming from btrfs_search_slot.
 */
#define btrfs_for_each_slot(root, key, found_key, path, iter_ret)		\
	for (iter_ret = btrfs_search_slot(NULL, (root), (key), (path), 0, 0);	\
		(iter_ret) >= 0 &&						\
		(iter_ret = btrfs_get_next_valid_item((root), (found_key), (path))) == 0; \
		(path)->slots[0]++						\
	)

int btrfs_next_old_item(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq);

/*
 * Search the tree again to find a leaf with greater keys.
 *
 * Returns 0 if it found something or 1 if there are no greater leaves.
 * Returns < 0 on error.
 */
static inline int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
{
	return btrfs_next_old_leaf(root, path, 0);
}

static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p)
{
	return btrfs_next_old_item(root, p, 0);
}
int btrfs_leaf_free_space(struct extent_buffer *leaf);
int __must_check btrfs_drop_snapshot(struct btrfs_root *root, int update_ref,
				     int for_reloc);
int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
			struct btrfs_root *root,
			struct extent_buffer *node,
			struct extent_buffer *parent);

/* root-item.c */
int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
		       u64 ref_id, u64 dirid, u64 sequence,
		       const struct qstr *name);
int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
		       u64 ref_id, u64 dirid, u64 *sequence,
		       const struct qstr *name);
int btrfs_del_root(struct btrfs_trans_handle *trans,
		   const struct btrfs_key *key);
int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		      const struct btrfs_key *key,
		      struct btrfs_root_item *item);
int __must_check btrfs_update_root(struct btrfs_trans_handle *trans,
				   struct btrfs_root *root,
				   struct btrfs_key *key,
				   struct btrfs_root_item *item);
int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key,
		    struct btrfs_path *path, struct btrfs_root_item *root_item,
		    struct btrfs_key *root_key);
int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info);
void btrfs_set_root_node(struct btrfs_root_item *item,
			 struct extent_buffer *node);
void btrfs_check_and_init_root_item(struct btrfs_root_item *item);
void btrfs_update_root_times(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root);

/* uuid-tree.c */
int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
			u64 subid);
int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
			u64 subid);
int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info);

/* dir-item.c */
int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
			  const struct qstr *name);
int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
			  const struct qstr *name, struct btrfs_inode *dir,
			  struct btrfs_key *location, u8 type, u64 index);
struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
					     struct btrfs_root *root,
					     struct btrfs_path *path, u64 dir,
					     const struct qstr *name, int mod);
struct btrfs_dir_item *
btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans,
			    struct btrfs_root *root,
			    struct btrfs_path *path, u64 dir,
			    u64 index, const struct qstr *name, int mod);
struct btrfs_dir_item *
btrfs_search_dir_index_item(struct btrfs_root *root,
			    struct btrfs_path *path, u64 dirid,
			    const struct qstr *name);
int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans,
			      struct btrfs_root *root,
			      struct btrfs_path *path,
			      struct btrfs_dir_item *di);
int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
			    struct btrfs_root *root,
			    struct btrfs_path *path, u64 objectid,
			    const char *name, u16 name_len,
			    const void *data, u16 data_len);
struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
					  struct btrfs_root *root,
					  struct btrfs_path *path, u64 dir,
					  const char *name, u16 name_len,
					  int mod);
struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info,
						 struct btrfs_path *path,
						 const char *name,
						 int name_len);

/* orphan.c */
int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root, u64 offset);
int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root, u64 offset);
int btrfs_find_orphan_item(struct btrfs_root *root, u64 offset);

/* file-item.c */
int btrfs_del_csums(struct btrfs_trans_handle *trans,
		    struct btrfs_root *root, u64 bytenr, u64 len);
blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst);
int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root, u64 objectid, u64 pos,
			     u64 num_bytes);
int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root,
			     struct btrfs_path *path, u64 objectid,
			     u64 bytenr, int mod);
int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root,
			   struct btrfs_ordered_sum *sums);
blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
				u64 offset, bool one_ordered);
int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
			     struct list_head *list, int search_commit,
			     bool nowait);
void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
				     const struct btrfs_path *path,
				     struct btrfs_file_extent_item *fi,
				     const bool new_inline,
				     struct extent_map *em);
int btrfs_inode_clear_file_extent_range(struct btrfs_inode *inode, u64 start,
					u64 len);
int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start,
				      u64 len);
void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_size);
u64 btrfs_file_extent_end(const struct btrfs_path *path);

/* inode.c */
void btrfs_submit_data_write_bio(struct inode *inode, struct bio *bio, int mirror_num);
void btrfs_submit_data_read_bio(struct inode *inode, struct bio *bio,
			int mirror_num, enum btrfs_compression_type compress_type);
int btrfs_check_sector_csum(struct btrfs_fs_info *fs_info, struct page *page,
			    u32 pgoff, u8 *csum, const u8 * const csum_expected);
int btrfs_check_data_csum(struct inode *inode, struct btrfs_bio *bbio,
			  u32 bio_offset, struct page *page, u32 pgoff);
unsigned int btrfs_verify_data_csum(struct btrfs_bio *bbio,
				    u32 bio_offset, struct page *page,
				    u64 start, u64 end);
int btrfs_check_data_csum(struct inode *inode, struct btrfs_bio *bbio,
			  u32 bio_offset, struct page *page, u32 pgoff);
noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
			      u64 *orig_start, u64 *orig_block_len,
			      u64 *ram_bytes, bool nowait, bool strict);

void __btrfs_del_delalloc_inode(struct btrfs_root *root,
				struct btrfs_inode *inode);
struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
		       struct btrfs_inode *dir, struct btrfs_inode *inode,
		       const struct qstr *name);
int btrfs_add_link(struct btrfs_trans_handle *trans,
		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
		   const struct qstr *name, int add_backref, u64 index);
int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry);
int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
			 int front);

int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
			       bool in_reclaim_context);
int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
			      unsigned int extra_bits,
			      struct extent_state **cached_state);
struct btrfs_new_inode_args {
	/* Input */
	struct inode *dir;
	struct dentry *dentry;
	struct inode *inode;
	bool orphan;
	bool subvol;

	/*
	 * Output from btrfs_new_inode_prepare(), input to
	 * btrfs_create_new_inode().
	 */
	struct posix_acl *default_acl;
	struct posix_acl *acl;
	struct fscrypt_name fname;
	struct qstr name;
};
int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args,
			    unsigned int *trans_num_items);
int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
			   struct btrfs_new_inode_args *args);
void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args);
struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns,
				     struct inode *dir);
 void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
			        u32 bits);
void btrfs_clear_delalloc_extent(struct inode *inode,
				 struct extent_state *state, u32 bits);
void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
				 struct extent_state *other);
void btrfs_split_delalloc_extent(struct inode *inode,
				 struct extent_state *orig, u64 split);
void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end);
vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
void btrfs_evict_inode(struct inode *inode);
struct inode *btrfs_alloc_inode(struct super_block *sb);
void btrfs_destroy_inode(struct inode *inode);
void btrfs_free_inode(struct inode *inode);
int btrfs_drop_inode(struct inode *inode);
int __init btrfs_init_cachep(void);
void __cold btrfs_destroy_cachep(void);
struct inode *btrfs_iget_path(struct super_block *s, u64 ino,
			      struct btrfs_root *root, struct btrfs_path *path);
struct inode *btrfs_iget(struct super_block *s, u64 ino, struct btrfs_root *root);
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
				    struct page *page, size_t pg_offset,
				    u64 start, u64 end);
int btrfs_update_inode(struct btrfs_trans_handle *trans,
		       struct btrfs_root *root, struct btrfs_inode *inode);
int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
				struct btrfs_root *root, struct btrfs_inode *inode);
int btrfs_orphan_add(struct btrfs_trans_handle *trans,
		struct btrfs_inode *inode);
int btrfs_orphan_cleanup(struct btrfs_root *root);
int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size);
void btrfs_add_delayed_iput(struct inode *inode);
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info);
int btrfs_prealloc_file_range(struct inode *inode, int mode,
			      u64 start, u64 num_bytes, u64 min_size,
			      loff_t actual_len, u64 *alloc_hint);
int btrfs_prealloc_file_range_trans(struct inode *inode,
				    struct btrfs_trans_handle *trans, int mode,
				    u64 start, u64 num_bytes, u64 min_size,
				    loff_t actual_len, u64 *alloc_hint);
int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page,
		u64 start, u64 end, int *page_started, unsigned long *nr_written,
		struct writeback_control *wbc);
int btrfs_writepage_cow_fixup(struct page *page);
void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
					  struct page *page, u64 start,
					  u64 end, bool uptodate);
int btrfs_encoded_io_compression_from_extent(struct btrfs_fs_info *fs_info,
					     int compress_type);
int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
					  u64 file_offset, u64 disk_bytenr,
					  u64 disk_io_size,
					  struct page **pages);
ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
			   struct btrfs_ioctl_encoded_io_args *encoded);
ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
			     const struct btrfs_ioctl_encoded_io_args *encoded);

ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter,
		       size_t done_before);
struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
				  size_t done_before);

extern const struct dentry_operations btrfs_dentry_operations;

/* Inode locking type flags, by default the exclusive lock is taken */
enum btrfs_ilock_type {
	ENUM_BIT(BTRFS_ILOCK_SHARED),
	ENUM_BIT(BTRFS_ILOCK_TRY),
	ENUM_BIT(BTRFS_ILOCK_MMAP),
};

int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags);
void btrfs_inode_unlock(struct inode *inode, unsigned int ilock_flags);
void btrfs_update_inode_bytes(struct btrfs_inode *inode,
			      const u64 add_bytes,
			      const u64 del_bytes);
void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 end);

/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
int btrfs_fileattr_set(struct user_namespace *mnt_userns,
		       struct dentry *dentry, struct fileattr *fa);
int btrfs_ioctl_get_supported_features(void __user *arg);
void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
int __pure btrfs_is_empty_uuid(u8 *uuid);
int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
		      struct btrfs_ioctl_defrag_range_args *range,
		      u64 newer_than, unsigned long max_to_defrag);
void btrfs_get_block_group_info(struct list_head *groups_list,
				struct btrfs_ioctl_space_info *space);
void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
			       struct btrfs_ioctl_balance_args *bargs);

/* file.c */
int __init btrfs_auto_defrag_init(void);
void __cold btrfs_auto_defrag_exit(void);
int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
			   struct btrfs_inode *inode, u32 extent_thresh);
int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
extern const struct file_operations btrfs_file_operations;
int btrfs_drop_extents(struct btrfs_trans_handle *trans,
		       struct btrfs_root *root, struct btrfs_inode *inode,
		       struct btrfs_drop_extents_args *args);
int btrfs_replace_file_extents(struct btrfs_inode *inode,
			   struct btrfs_path *path, const u64 start,
			   const u64 end,
			   struct btrfs_replace_extent_info *extent_info,
			   struct btrfs_trans_handle **trans_out);
int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
			      struct btrfs_inode *inode, u64 start, u64 end);
ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
			    const struct btrfs_ioctl_encoded_io_args *encoded);
int btrfs_release_file(struct inode *inode, struct file *file);
int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
		      size_t num_pages, loff_t pos, size_t write_bytes,
		      struct extent_state **cached, bool noreserve);
int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos,
			   size_t *write_bytes, bool nowait);
void btrfs_check_nocow_unlock(struct btrfs_inode *inode);
bool btrfs_find_delalloc_in_range(struct btrfs_inode *inode, u64 start, u64 end,
				  u64 *delalloc_start_ret, u64 *delalloc_end_ret);

/* tree-defrag.c */
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
			struct btrfs_root *root);

/* super.c */
int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
			unsigned long new_flags);
int btrfs_sync_fs(struct super_block *sb, int wait);
char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
					  u64 subvol_objectid);

#if BITS_PER_LONG == 32
#define BTRFS_32BIT_MAX_FILE_SIZE (((u64)ULONG_MAX + 1) << PAGE_SHIFT)
/*
 * The warning threshold is 5/8th of the MAX_LFS_FILESIZE that limits the logical
 * addresses of extents.
 *
 * For 4K page size it's about 10T, for 64K it's 160T.
 */
#define BTRFS_32BIT_EARLY_WARN_THRESHOLD (BTRFS_32BIT_MAX_FILE_SIZE * 5 / 8)
void btrfs_warn_32bit_limit(struct btrfs_fs_info *fs_info);
void btrfs_err_32bit_limit(struct btrfs_fs_info *fs_info);
#endif

/*
 * Get the correct offset inside the page of extent buffer.
 *
 * @eb:		target extent buffer
 * @start:	offset inside the extent buffer
 *
 * Will handle both sectorsize == PAGE_SIZE and sectorsize < PAGE_SIZE cases.
 */
static inline size_t get_eb_offset_in_page(const struct extent_buffer *eb,
					   unsigned long offset)
{
	/*
	 * For sectorsize == PAGE_SIZE case, eb->start will always be aligned
	 * to PAGE_SIZE, thus adding it won't cause any difference.
	 *
	 * For sectorsize < PAGE_SIZE, we must only read the data that belongs
	 * to the eb, thus we have to take the eb->start into consideration.
	 */
	return offset_in_page(offset + eb->start);
}

static inline unsigned long get_eb_page_index(unsigned long offset)
{
	/*
	 * For sectorsize == PAGE_SIZE case, plain >> PAGE_SHIFT is enough.
	 *
	 * For sectorsize < PAGE_SIZE case, we only support 64K PAGE_SIZE,
	 * and have ensured that all tree blocks are contained in one page,
	 * thus we always get index == 0.
	 */
	return offset >> PAGE_SHIFT;
}

/*
 * Use that for functions that are conditionally exported for sanity tests but
 * otherwise static
 */
#ifndef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
#define EXPORT_FOR_TESTS static
#else
#define EXPORT_FOR_TESTS
#endif

/* acl.c */
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu);
int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
		  struct posix_acl *acl, int type);
int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
		    struct posix_acl *acl, int type);
#else
#define btrfs_get_acl NULL
#define btrfs_set_acl NULL
static inline int __btrfs_set_acl(struct btrfs_trans_handle *trans,
				  struct inode *inode, struct posix_acl *acl,
				  int type)
{
	return -EOPNOTSUPP;
}
#endif

/* relocation.c */
int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start);
int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root);
int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
			    struct btrfs_root *root);
int btrfs_recover_relocation(struct btrfs_fs_info *fs_info);
int btrfs_reloc_clone_csums(struct btrfs_inode *inode, u64 file_pos, u64 len);
int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root, struct extent_buffer *buf,
			  struct extent_buffer *cow);
void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending,
			      u64 *bytes_to_reserve);
int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
			      struct btrfs_pending_snapshot *pending);
int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info);
struct btrfs_root *find_reloc_root(struct btrfs_fs_info *fs_info,
				   u64 bytenr);
int btrfs_should_ignore_reloc_root(struct btrfs_root *root);

/* scrub.c */
int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
		    u64 end, struct btrfs_scrub_progress *progress,
		    int readonly, int is_dev_replace);
void btrfs_scrub_pause(struct btrfs_fs_info *fs_info);
void btrfs_scrub_continue(struct btrfs_fs_info *fs_info);
int btrfs_scrub_cancel(struct btrfs_fs_info *info);
int btrfs_scrub_cancel_dev(struct btrfs_device *dev);
int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
			 struct btrfs_scrub_progress *progress);

/* dev-replace.c */
void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info);
void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount);

static inline void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info)
{
	btrfs_bio_counter_sub(fs_info, 1);
}

static inline int is_fstree(u64 rootid)
{
	if (rootid == BTRFS_FS_TREE_OBJECTID ||
	    ((s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID &&
	      !btrfs_qgroup_level(rootid)))
		return 1;
	return 0;
}

static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
{
	return signal_pending(current);
}

/* verity.c */
#ifdef CONFIG_FS_VERITY

extern const struct fsverity_operations btrfs_verityops;
int btrfs_drop_verity_items(struct btrfs_inode *inode);
int btrfs_get_verity_descriptor(struct inode *inode, void *buf, size_t buf_size);

#else

static inline int btrfs_drop_verity_items(struct btrfs_inode *inode)
{
	return 0;
}

static inline int btrfs_get_verity_descriptor(struct inode *inode, void *buf,
					      size_t buf_size)
{
	return -EPERM;
}

#endif

/* Sanity test specific functions */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_destroy_inode(struct inode *inode);
#endif

static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root)
{
	return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID;
}

/*
 * We use page status Private2 to indicate there is an ordered extent with
 * unfinished IO.
 *
 * Rename the Private2 accessors to Ordered, to improve readability.
 */
#define PageOrdered(page)		PagePrivate2(page)
#define SetPageOrdered(page)		SetPagePrivate2(page)
#define ClearPageOrdered(page)		ClearPagePrivate2(page)
#define folio_test_ordered(folio)	folio_test_private_2(folio)
#define folio_set_ordered(folio)	folio_set_private_2(folio)
#define folio_clear_ordered(folio)	folio_clear_private_2(folio)

#endif