blob: 0a61dff27f57a50120ef4c3bf0f4424bf29ba262 [file] [log] [blame]
/* SPDX-License-Identifier: GPL-2.0 */
* Copyright (C) 2007 Oracle. All rights reserved.
#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 <linux/kobject.h>
#include <trace/events/btrfs.h>
#include <asm/kmap_types.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 "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
struct btrfs_trans_handle;
struct btrfs_transaction;
struct btrfs_pending_snapshot;
struct btrfs_delayed_ref_root;
extern struct kmem_cache *btrfs_trans_handle_cachep;
extern struct kmem_cache *btrfs_bit_radix_cachep;
extern struct kmem_cache *btrfs_path_cachep;
extern struct kmem_cache *btrfs_free_space_cachep;
struct btrfs_ordered_sum;
struct btrfs_ref;
#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */
* the max metadata block size. This limit is somewhat artificial,
* but the memmove costs go through the roof for larger blocks.
* we can actually store much bigger names, but lets not confuse the rest
* of linux
#define BTRFS_NAME_LEN 255
* Theoretical limit is larger, but we keep this down to a sane
* value. That should limit greatly the possibility of collisions on
* inode ref items.
#define BTRFS_LINK_MAX 65535U
/* four bytes for CRC32 */
static const int btrfs_csum_sizes[] = { 4 };
/* ioprio of readahead is set to idle */
* Use large batch size to reduce overhead of metadata updates. On the reader
* side, we only read it when we are close to ENOSPC and the read overhead is
* mostly related to the number of CPUs, so it is OK to use arbitrary large
* value here.
* Count how many BTRFS_MAX_EXTENT_SIZE cover the @size
static inline u32 count_max_extents(u64 size)
return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
struct btrfs_mapping_tree {
struct extent_map_tree map_tree;
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);
* Runtime (in-memory) states of filesystem
enum {
/* Global indicator of serious filesystem errors */
* Filesystem is being remounted, allow to skip some operations, like
* defrag
/* Track if a transaction abort has been reported on this filesystem */
* Bio operations should be blocked on this filesystem because a source
* or target device is being destroyed as part of a device replace
/* The btrfs_fs_info created for self-tests */
* every tree block (leaf or node) starts with this header.
struct btrfs_header {
/* these first four must match the super block */
u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
__le64 bytenr; /* which block this node is supposed to live in */
__le64 flags;
/* allowed to be different from the super from here on down */
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
__le64 generation;
__le64 owner;
__le32 nritems;
u8 level;
} __attribute__ ((__packed__));
* this is a very generous portion of the super block, giving us
* room to translate 14 chunks with 3 stripes each.
* just in case we somehow lose the roots and are not able to mount,
* we store an array of the roots from previous transactions
* in the super.
struct btrfs_root_backup {
__le64 tree_root;
__le64 tree_root_gen;
__le64 chunk_root;
__le64 chunk_root_gen;
__le64 extent_root;
__le64 extent_root_gen;
__le64 fs_root;
__le64 fs_root_gen;
__le64 dev_root;
__le64 dev_root_gen;
__le64 csum_root;
__le64 csum_root_gen;
__le64 total_bytes;
__le64 bytes_used;
__le64 num_devices;
/* future */
__le64 unused_64[4];
u8 tree_root_level;
u8 chunk_root_level;
u8 extent_root_level;
u8 fs_root_level;
u8 dev_root_level;
u8 csum_root_level;
/* future and to align */
u8 unused_8[10];
} __attribute__ ((__packed__));
* the super block basically lists the main trees of the FS
* it currently lacks any block count etc etc
struct btrfs_super_block {
/* the first 4 fields must match struct btrfs_header */
/* FS specific UUID, visible to user */
__le64 bytenr; /* this block number */
__le64 flags;
/* allowed to be different from the btrfs_header from here own down */
__le64 magic;
__le64 generation;
__le64 root;
__le64 chunk_root;
__le64 log_root;
/* this will help find the new super based on the log root */
__le64 log_root_transid;
__le64 total_bytes;
__le64 bytes_used;
__le64 root_dir_objectid;
__le64 num_devices;
__le32 sectorsize;
__le32 nodesize;
__le32 __unused_leafsize;
__le32 stripesize;
__le32 sys_chunk_array_size;
__le64 chunk_root_generation;
__le64 compat_flags;
__le64 compat_ro_flags;
__le64 incompat_flags;
__le16 csum_type;
u8 root_level;
u8 chunk_root_level;
u8 log_root_level;
struct btrfs_dev_item dev_item;
char label[BTRFS_LABEL_SIZE];
__le64 cache_generation;
__le64 uuid_tree_generation;
/* the UUID written into btree blocks */
u8 metadata_uuid[BTRFS_FSID_SIZE];
/* future expansion */
__le64 reserved[28];
u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE];
struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS];
} __attribute__ ((__packed__));
* Compat flags that we support. If any incompat flags are set other than the
* ones specified below then we will fail to mount
* A leaf is full of items. offset and size tell us where to find
* the item in the leaf (relative to the start of the data area)
struct btrfs_item {
struct btrfs_disk_key key;
__le32 offset;
__le32 size;
} __attribute__ ((__packed__));
* leaves have an item area and a data area:
* [item0, item1....itemN] [free space] [dataN...data1, data0]
* The data is separate from the items to get the keys closer together
* during searches.
struct btrfs_leaf {
struct btrfs_header header;
struct btrfs_item items[];
} __attribute__ ((__packed__));
* all non-leaf blocks are nodes, they hold only keys and pointers to
* other blocks
struct btrfs_key_ptr {
struct btrfs_disk_key key;
__le64 blockptr;
__le64 generation;
} __attribute__ ((__packed__));
struct btrfs_node {
struct btrfs_header header;
struct btrfs_key_ptr ptrs[];
} __attribute__ ((__packed__));
* 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 leave_spinning:1;
unsigned int search_commit_root:1;
unsigned int need_commit_sem:1;
unsigned int skip_release_on_error:1;
#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
sizeof(struct btrfs_item))
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;
/* For raid type sysfs entries */
struct raid_kobject {
u64 flags;
struct kobject kobj;
struct list_head list;
struct btrfs_space_info {
spinlock_t lock;
u64 total_bytes; /* total bytes in the space,
this doesn't take mirrors into account */
u64 bytes_used; /* total bytes used,
this doesn't take mirrors into account */
u64 bytes_pinned; /* total bytes pinned, will be freed when the
transaction finishes */
u64 bytes_reserved; /* total bytes the allocator has reserved for
current allocations */
u64 bytes_may_use; /* number of bytes that may be used for
delalloc/allocations */
u64 bytes_readonly; /* total bytes that are read only */
u64 max_extent_size; /* This will hold the maximum extent size of
the space info if we had an ENOSPC in the
allocator. */
unsigned int full:1; /* indicates that we cannot allocate any more
chunks for this space */
unsigned int chunk_alloc:1; /* set if we are allocating a chunk */
unsigned int flush:1; /* set if we are trying to make space */
unsigned int force_alloc; /* set if we need to force a chunk
alloc for this space */
u64 disk_used; /* total bytes used on disk */
u64 disk_total; /* total bytes on disk, takes mirrors into
account */
u64 flags;
* bytes_pinned is kept in line with what is actually pinned, as in
* we've called update_block_group and dropped the bytes_used counter
* and increased the bytes_pinned counter. However this means that
* bytes_pinned does not reflect the bytes that will be pinned once the
* delayed refs are flushed, so this counter is inc'ed every time we
* call btrfs_free_extent so it is a realtime count of what will be
* freed once the transaction is committed. It will be zeroed every
* time the transaction commits.
struct percpu_counter total_bytes_pinned;
struct list_head list;
/* Protected by the spinlock 'lock'. */
struct list_head ro_bgs;
struct list_head priority_tickets;
struct list_head tickets;
* tickets_id just indicates the next ticket will be handled, so note
* it's not stored per ticket.
u64 tickets_id;
struct rw_semaphore groups_sem;
/* for block groups in our same type */
struct list_head block_groups[BTRFS_NR_RAID_TYPES];
wait_queue_head_t wait;
struct kobject kobj;
struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES];
* Types of block reserves
enum {
struct btrfs_block_rsv {
u64 size;
u64 reserved;
struct btrfs_space_info *space_info;
spinlock_t lock;
unsigned short full;
unsigned short type;
unsigned short failfast;
* Qgroup equivalent for @size @reserved
* Unlike normal @size/@reserved for inode rsv, qgroup doesn't care
* about things like csum size nor how many tree blocks it will need to
* reserve.
* Qgroup cares more about net change of the extent usage.
* So for one newly inserted file extent, in worst case it will cause
* leaf split and level increase, nodesize for each file extent is
* already too much.
* In short, qgroup_size/reserved is the upper limit of possible needed
* qgroup metadata reservation.
u64 qgroup_rsv_size;
u64 qgroup_rsv_reserved;
* 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_cache *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;
enum btrfs_caching_type {
enum btrfs_disk_cache_state {
struct btrfs_caching_control {
struct list_head list;
struct mutex mutex;
wait_queue_head_t wait;
struct btrfs_work work;
struct btrfs_block_group_cache *block_group;
u64 progress;
refcount_t count;
/* Once caching_thread() finds this much free space, it will wake up waiters. */
struct btrfs_io_ctl {
void *cur, *orig;
struct page *page;
struct page **pages;
struct btrfs_fs_info *fs_info;
struct inode *inode;
unsigned long size;
int index;
int num_pages;
int entries;
int bitmaps;
unsigned check_crcs:1;
* Tree to record all locked full stripes of a RAID5/6 block group
struct btrfs_full_stripe_locks_tree {
struct rb_root root;
struct mutex lock;
struct btrfs_block_group_cache {
struct btrfs_key key;
struct btrfs_block_group_item item;
struct btrfs_fs_info *fs_info;
struct inode *inode;
spinlock_t lock;
u64 pinned;
u64 reserved;
u64 delalloc_bytes;
u64 bytes_super;
u64 flags;
u64 cache_generation;
* If the free space extent count exceeds this number, convert the block
* group to bitmaps.
u32 bitmap_high_thresh;
* If the free space extent count drops below this number, convert the
* block group back to extents.
u32 bitmap_low_thresh;
* It is just used for the delayed data space allocation because
* only the data space allocation and the relative metadata update
* can be done cross the transaction.
struct rw_semaphore data_rwsem;
/* for raid56, this is a full stripe, without parity */
unsigned long full_stripe_len;
unsigned int ro;
unsigned int iref:1;
unsigned int has_caching_ctl:1;
unsigned int removed:1;
int disk_cache_state;
/* cache tracking stuff */
int cached;
struct btrfs_caching_control *caching_ctl;
u64 last_byte_to_unpin;
struct btrfs_space_info *space_info;
/* free space cache stuff */
struct btrfs_free_space_ctl *free_space_ctl;
/* block group cache stuff */
struct rb_node cache_node;
/* for block groups in the same raid type */
struct list_head list;
/* usage count */
atomic_t count;
/* List of struct btrfs_free_clusters for this block group.
* Today it will only have one thing on it, but that may change
struct list_head cluster_list;
/* For delayed block group creation or deletion of empty block groups */
struct list_head bg_list;
/* For read-only block groups */
struct list_head ro_list;
atomic_t trimming;
/* For dirty block groups */
struct list_head dirty_list;
struct list_head io_list;
struct btrfs_io_ctl io_ctl;
* Incremented when doing extent allocations and holding a read lock
* on the space_info's groups_sem semaphore.
* Decremented when an ordered extent that represents an IO against this
* block group's range is created (after it's added to its inode's
* root's list of ordered extents) or immediately after the allocation
* if it's a metadata extent or fallocate extent (for these cases we
* don't create ordered extents).
atomic_t reservations;
* Incremented while holding the spinlock *lock* by a task checking if
* it can perform a nocow write (incremented if the value for the *ro*
* field is 0). Decremented by such tasks once they create an ordered
* extent or before that if some error happens before reaching that step.
* This is to prevent races between block group relocation and nocow
* writes through direct IO.
atomic_t nocow_writers;
/* Lock for free space tree operations. */
struct mutex free_space_lock;
* Does the block group need to be added to the free space tree?
* Protected by free_space_lock.
int needs_free_space;
/* Record locked full stripes for RAID5/6 block group */
struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
/* delayed seq elem */
struct seq_list {
struct list_head list;
u64 seq;
#define SEQ_LIST_INIT(name) { .list = LIST_HEAD_INIT((name).list), .seq = 0 }
#define SEQ_LAST ((u64)-1)
enum btrfs_orphan_cleanup_state {
/* used by the raid56 code to lock stripes for read/modify/write */
struct btrfs_stripe_hash {
struct list_head hash_list;
spinlock_t lock;
/* used by the raid56 code to lock stripes for read/modify/write */
struct btrfs_stripe_hash_table {
struct list_head stripe_cache;
spinlock_t cache_lock;
int cache_size;
struct btrfs_stripe_hash table[];
void btrfs_init_async_reclaim_work(struct work_struct *work);
/* fs_info */
struct reloc_control;
struct btrfs_device;
struct btrfs_fs_devices;
struct btrfs_balance_control;
struct btrfs_delayed_root;
* Block group or device which contains an active swapfile. Used for preventing
* unsafe operations while a swapfile is active.
* These are sorted on (ptr, inode) (note that a block group or device can
* contain more than one swapfile). We compare the pointer values because we
* don't actually care what the object is, we just need a quick check whether
* the object exists in the rbtree.
struct btrfs_swapfile_pin {
struct rb_node node;
void *ptr;
struct inode *inode;
* If true, ptr points to a struct btrfs_block_group_cache. Otherwise,
* ptr points to a struct btrfs_device.
bool is_block_group;
bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr);
enum {
/* Used to record internally whether fs has been frozen */
* Indicate that a whole-filesystem exclusive operation is running
* (device replace, resize, device add/delete, balance)
* To info transaction_kthread we need an immediate commit so it
* doesn't need to wait for commit_interval
* Indicate that balance has been set up from the ioctl and is in the
* main phase. The fs_info::balance_ctl is initialized.
/* Indicate that the cleaner thread is awake and doing something. */
struct btrfs_fs_info {
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
unsigned long flags;
struct btrfs_root *extent_root;
struct btrfs_root *tree_root;
struct btrfs_root *chunk_root;
struct btrfs_root *dev_root;
struct btrfs_root *fs_root;
struct btrfs_root *csum_root;
struct btrfs_root *quota_root;
struct btrfs_root *uuid_root;
struct btrfs_root *free_space_root;
/* the log root tree is a directory of all the other log roots */
struct btrfs_root *log_root_tree;
spinlock_t fs_roots_radix_lock;
struct radix_tree_root fs_roots_radix;
/* block group cache stuff */
spinlock_t block_group_cache_lock;
u64 first_logical_byte;
struct rb_root block_group_cache_tree;
/* keep track of unallocated space */
atomic64_t free_chunk_space;
struct extent_io_tree freed_extents[2];
struct extent_io_tree *pinned_extents;
/* logical->physical extent mapping */
struct btrfs_mapping_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;
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;
* Track requests for actions that need to be done during transaction
* commit (like for some mount options).
unsigned long pending_changes;
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;
struct srcu_struct subvol_srcu;
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;
/* this protects tree_mod_seq_list */
spinlock_t tree_mod_seq_lock;
atomic64_t tree_mod_seq;
struct list_head tree_mod_seq_list;
/* this protects tree_mod_log */
rwlock_t tree_mod_log_lock;
struct rb_root tree_mod_log;
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 *delalloc_workers;
struct btrfs_workqueue *flush_workers;
struct btrfs_workqueue *endio_workers;
struct btrfs_workqueue *endio_meta_workers;
struct btrfs_workqueue *endio_raid56_workers;
struct btrfs_workqueue *endio_repair_workers;
struct btrfs_workqueue *rmw_workers;
struct btrfs_workqueue *endio_meta_write_workers;
struct btrfs_workqueue *endio_write_workers;
struct btrfs_workqueue *endio_freespace_worker;
struct btrfs_workqueue *submit_workers;
struct btrfs_workqueue *caching_workers;
struct btrfs_workqueue *readahead_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;
/* the extent workers do delayed refs on the extent allocation tree */
struct btrfs_workqueue *extent_workers;
struct task_struct *transaction_kthread;
struct task_struct *cleaner_kthread;
u32 thread_pool_size;
struct kobject *space_info_kobj;
struct list_head pending_raid_kobjs;
spinlock_t pending_raid_kobjs_lock; /* uncontended */
u64 total_pinned;
/* 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 dio_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;
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 btrfs_workqueue *scrub_workers;
struct btrfs_workqueue *scrub_wr_completion_workers;
struct btrfs_workqueue *scrub_parity_workers;
u32 check_integrity_print_mask;
/* 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 */
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 */
/* filesystem state */
unsigned long fs_state;
struct btrfs_delayed_root *delayed_root;
/* readahead tree */
spinlock_t reada_lock;
struct radix_tree_root reada_tree;
/* readahead works cnt */
atomic_t reada_works_cnt;
/* Extent buffer radix tree */
spinlock_t buffer_lock;
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;
spinlock_t unused_bgs_lock;
struct list_head unused_bgs;
struct mutex unused_bg_unpin_mutex;
struct mutex delete_unused_bgs_mutex;
/* Cached block sizes */
u32 nodesize;
u32 sectorsize;
u32 stripesize;
/* Block groups and devices containing active swapfiles. */
spinlock_t swapfile_pins_lock;
struct rb_root swapfile_pins;
spinlock_t ref_verify_lock;
struct rb_root block_tree;
static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
return sb->s_fs_info;
struct btrfs_subvolume_writers {
struct percpu_counter counter;
wait_queue_head_t wait;
* 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
* Reloc tree is orphan, only kept here for qgroup delayed subtree scan
* Set for the subvolume tree owning the reloc tree.
/* Mark dead root stored on device whose cleanup needs to be resumed */
* 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 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;
/* free ino cache stuff */
struct btrfs_free_space_ctl *free_ino_ctl;
enum btrfs_caching_type ino_cache_state;
spinlock_t ino_cache_lock;
wait_queue_head_t ino_cache_wait;
struct btrfs_free_space_ctl *free_ino_pinned;
u64 ino_cache_progress;
struct inode *ino_cache_inode;
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];
atomic_t log_writers;
atomic_t log_commit[2];
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 highest_objectid;
u64 defrag_trans_start;
struct btrfs_key defrag_progress;
struct btrfs_key defrag_max;
/* the dirty list is only used by non-reference counted roots */
struct list_head dirty_list;
struct list_head root_list;
spinlock_t log_extents_lock[2];
struct list_head logged_list[2];
int orphan_cleanup_state;
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;
struct btrfs_subvolume_writers *subv_writers;
atomic_t will_be_snapshotted;
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;
/* Number of active swapfiles */
atomic_t nr_swapfiles;
/* Record pairs of swapped blocks for qgroup */
struct btrfs_qgroup_swapped_blocks swapped_blocks;
u64 alloc_bytenr;
struct btrfs_file_private {
void *filldir_buf;
static inline u32 btrfs_inode_sectorsize(const struct inode *inode)
return btrfs_sb(inode->i_sb)->sectorsize;
static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
return info->nodesize - sizeof(struct btrfs_header);
#define BTRFS_LEAF_DATA_OFFSET offsetof(struct btrfs_leaf, items)
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);
(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) -
static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
return BTRFS_MAX_ITEM_SIZE(info) - sizeof(struct btrfs_dir_item);
* Flags for mount options.
* Note: don't forget to add new options to btrfs_show_options()
#define BTRFS_MOUNT_NODATASUM (1 << 0)
#define BTRFS_MOUNT_NODATACOW (1 << 1)
#define BTRFS_MOUNT_NOBARRIER (1 << 2)
#define BTRFS_MOUNT_SSD (1 << 3)
#define BTRFS_MOUNT_DEGRADED (1 << 4)
#define BTRFS_MOUNT_COMPRESS (1 << 5)
#define BTRFS_MOUNT_NOTREELOG (1 << 6)
#define BTRFS_MOUNT_SSD_SPREAD (1 << 8)
#define BTRFS_MOUNT_NOSSD (1 << 9)
#define BTRFS_MOUNT_DISCARD (1 << 10)
#define BTRFS_MOUNT_SPACE_CACHE (1 << 12)
#define BTRFS_MOUNT_CLEAR_CACHE (1 << 13)
#define BTRFS_MOUNT_ENOSPC_DEBUG (1 << 15)
#define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16)
#define BTRFS_MOUNT_SKIP_BALANCE (1 << 19)
#define BTRFS_MOUNT_REF_VERIFY (1 << 28)
#define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt)
#define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt)
#define btrfs_raw_test_opt(o, opt) ((o) & BTRFS_MOUNT_##opt)
#define btrfs_test_opt(fs_info, opt) ((fs_info)->mount_opt & \
#define btrfs_set_and_info(fs_info, opt, fmt, args...) \
{ \
if (!btrfs_test_opt(fs_info, opt)) \
btrfs_info(fs_info, fmt, ##args); \
btrfs_set_opt(fs_info->mount_opt, opt); \
#define btrfs_clear_and_info(fs_info, opt, fmt, args...) \
{ \
if (btrfs_test_opt(fs_info, opt)) \
btrfs_info(fs_info, fmt, ##args); \
btrfs_clear_opt(fs_info->mount_opt, opt); \
static inline int
btrfs_should_fragment_free_space(struct btrfs_block_group_cache *block_group)
struct btrfs_fs_info *fs_info = block_group->fs_info;
return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) &&
block_group->flags & BTRFS_BLOCK_GROUP_METADATA) ||
(btrfs_test_opt(fs_info, FRAGMENT_DATA) &&
block_group->flags & BTRFS_BLOCK_GROUP_DATA);
* Requests for changes that need to be done during transaction commit.
* Internal mount options that are used for special handling of the real
* mount options (eg. cannot be set during remount and have to be set during
* transaction commit)
#define btrfs_test_pending(info, opt) \
test_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
#define btrfs_set_pending(info, opt) \
set_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
#define btrfs_clear_pending(info, opt) \
clear_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
* Helpers for setting pending mount option changes.
* Expects corresponding macros
* BTRFS_PENDING_SET_ and CLEAR_ + short mount option name
#define btrfs_set_pending_and_info(info, opt, fmt, args...) \
do { \
if (!btrfs_raw_test_opt((info)->mount_opt, opt)) { \
btrfs_info((info), fmt, ##args); \
btrfs_set_pending((info), SET_##opt); \
btrfs_clear_pending((info), CLEAR_##opt); \
} \
} while(0)
#define btrfs_clear_pending_and_info(info, opt, fmt, args...) \
do { \
if (btrfs_raw_test_opt((info)->mount_opt, opt)) { \
btrfs_info((info), fmt, ##args); \
btrfs_set_pending((info), CLEAR_##opt); \
btrfs_clear_pending((info), SET_##opt); \
} \
} while(0)
* Inode flags
#define BTRFS_INODE_NODATASUM (1 << 0)
#define BTRFS_INODE_NODATACOW (1 << 1)
#define BTRFS_INODE_READONLY (1 << 2)
#define BTRFS_INODE_PREALLOC (1 << 4)
#define BTRFS_INODE_SYNC (1 << 5)
#define BTRFS_INODE_IMMUTABLE (1 << 6)
#define BTRFS_INODE_APPEND (1 << 7)
#define BTRFS_INODE_NODUMP (1 << 8)
#define BTRFS_INODE_NOATIME (1 << 9)
#define BTRFS_INODE_DIRSYNC (1 << 10)
#define BTRFS_INODE_COMPRESS (1 << 11)
#define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31)
struct btrfs_map_token {
const struct extent_buffer *eb;
char *kaddr;
unsigned long offset;
#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
((bytes) >> (fs_info)->sb->s_blocksize_bits)
static inline void btrfs_init_map_token (struct btrfs_map_token *token)
token->kaddr = NULL;
/* some macros to generate set/get functions for the struct fields. This
* assumes there is a lefoo_to_cpu for every type, so lets make a simple
* one for u8:
#define le8_to_cpu(v) (v)
#define cpu_to_le8(v) (v)
#define __le8 u8
#define read_eb_member(eb, ptr, type, member, result) (\
read_extent_buffer(eb, (char *)(result), \
((unsigned long)(ptr)) + \
offsetof(type, member), \
sizeof(((type *)0)->member)))
#define write_eb_member(eb, ptr, type, member, result) (\
write_extent_buffer(eb, (char *)(result), \
((unsigned long)(ptr)) + \
offsetof(type, member), \
sizeof(((type *)0)->member)))
u##bits btrfs_get_token_##bits(const struct extent_buffer *eb, \
const void *ptr, unsigned long off, \
struct btrfs_map_token *token); \
void btrfs_set_token_##bits(struct extent_buffer *eb, const void *ptr, \
unsigned long off, u##bits val, \
struct btrfs_map_token *token); \
static inline u##bits btrfs_get_##bits(const struct extent_buffer *eb, \
const void *ptr, \
unsigned long off) \
{ \
return btrfs_get_token_##bits(eb, ptr, off, NULL); \
} \
static inline void btrfs_set_##bits(struct extent_buffer *eb, void *ptr,\
unsigned long off, u##bits val) \
{ \
btrfs_set_token_##bits(eb, ptr, off, val, NULL); \
#define BTRFS_SETGET_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(const struct extent_buffer *eb, \
const type *s) \
{ \
BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
return btrfs_get_##bits(eb, s, offsetof(type, member)); \
} \
static inline void btrfs_set_##name(struct extent_buffer *eb, type *s, \
u##bits val) \
{ \
BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
btrfs_set_##bits(eb, s, offsetof(type, member), val); \
} \
static inline u##bits btrfs_token_##name(const struct extent_buffer *eb,\
const type *s, \
struct btrfs_map_token *token) \
{ \
BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
return btrfs_get_token_##bits(eb, s, offsetof(type, member), token); \
} \
static inline void btrfs_set_token_##name(struct extent_buffer *eb, \
type *s, u##bits val, \
struct btrfs_map_token *token) \
{ \
BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
btrfs_set_token_##bits(eb, s, offsetof(type, member), val, token); \
#define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(const struct extent_buffer *eb) \
{ \
const type *p = page_address(eb->pages[0]); \
u##bits res = le##bits##_to_cpu(p->member); \
return res; \
} \
static inline void btrfs_set_##name(struct extent_buffer *eb, \
u##bits val) \
{ \
type *p = page_address(eb->pages[0]); \
p->member = cpu_to_le##bits(val); \
#define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(const type *s) \
{ \
return le##bits##_to_cpu(s->member); \
} \
static inline void btrfs_set_##name(type *s, u##bits val) \
{ \
s->member = cpu_to_le##bits(val); \
static inline u64 btrfs_device_total_bytes(struct extent_buffer *eb,
struct btrfs_dev_item *s)
BUILD_BUG_ON(sizeof(u64) !=
sizeof(((struct btrfs_dev_item *)0))->total_bytes);
return btrfs_get_64(eb, s, offsetof(struct btrfs_dev_item,
static inline void btrfs_set_device_total_bytes(struct extent_buffer *eb,
struct btrfs_dev_item *s,
u64 val)
BUILD_BUG_ON(sizeof(u64) !=
sizeof(((struct btrfs_dev_item *)0))->total_bytes);
WARN_ON(!IS_ALIGNED(val, eb->fs_info->sectorsize));
btrfs_set_64(eb, s, offsetof(struct btrfs_dev_item, total_bytes), val);
BTRFS_SETGET_FUNCS(device_type, struct btrfs_dev_item, type, 64);
BTRFS_SETGET_FUNCS(device_bytes_used, struct btrfs_dev_item, bytes_used, 64);
BTRFS_SETGET_FUNCS(device_io_align, struct btrfs_dev_item, io_align, 32);
BTRFS_SETGET_FUNCS(device_io_width, struct btrfs_dev_item, io_width, 32);
BTRFS_SETGET_FUNCS(device_start_offset, struct btrfs_dev_item,
start_offset, 64);
BTRFS_SETGET_FUNCS(device_sector_size, struct btrfs_dev_item, sector_size, 32);
BTRFS_SETGET_FUNCS(device_id, struct btrfs_dev_item, devid, 64);
BTRFS_SETGET_FUNCS(device_group, struct btrfs_dev_item, dev_group, 32);
BTRFS_SETGET_FUNCS(device_seek_speed, struct btrfs_dev_item, seek_speed, 8);
BTRFS_SETGET_FUNCS(device_bandwidth, struct btrfs_dev_item, bandwidth, 8);
BTRFS_SETGET_FUNCS(device_generation, struct btrfs_dev_item, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_type, struct btrfs_dev_item, type, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_total_bytes, struct btrfs_dev_item,
total_bytes, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_bytes_used, struct btrfs_dev_item,
bytes_used, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_io_align, struct btrfs_dev_item,
io_align, 32);
BTRFS_SETGET_STACK_FUNCS(stack_device_io_width, struct btrfs_dev_item,
io_width, 32);
BTRFS_SETGET_STACK_FUNCS(stack_device_sector_size, struct btrfs_dev_item,
sector_size, 32);
BTRFS_SETGET_STACK_FUNCS(stack_device_id, struct btrfs_dev_item, devid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_group, struct btrfs_dev_item,
dev_group, 32);
BTRFS_SETGET_STACK_FUNCS(stack_device_seek_speed, struct btrfs_dev_item,
seek_speed, 8);
BTRFS_SETGET_STACK_FUNCS(stack_device_bandwidth, struct btrfs_dev_item,
bandwidth, 8);
BTRFS_SETGET_STACK_FUNCS(stack_device_generation, struct btrfs_dev_item,
generation, 64);
static inline unsigned long btrfs_device_uuid(struct btrfs_dev_item *d)
return (unsigned long)d + offsetof(struct btrfs_dev_item, uuid);
static inline unsigned long btrfs_device_fsid(struct btrfs_dev_item *d)
return (unsigned long)d + offsetof(struct btrfs_dev_item, fsid);
BTRFS_SETGET_FUNCS(chunk_length, struct btrfs_chunk, length, 64);
BTRFS_SETGET_FUNCS(chunk_owner, struct btrfs_chunk, owner, 64);
BTRFS_SETGET_FUNCS(chunk_stripe_len, struct btrfs_chunk, stripe_len, 64);
BTRFS_SETGET_FUNCS(chunk_io_align, struct btrfs_chunk, io_align, 32);
BTRFS_SETGET_FUNCS(chunk_io_width, struct btrfs_chunk, io_width, 32);
BTRFS_SETGET_FUNCS(chunk_sector_size, struct btrfs_chunk, sector_size, 32);
BTRFS_SETGET_FUNCS(chunk_type, struct btrfs_chunk, type, 64);
BTRFS_SETGET_FUNCS(chunk_num_stripes, struct btrfs_chunk, num_stripes, 16);
BTRFS_SETGET_FUNCS(chunk_sub_stripes, struct btrfs_chunk, sub_stripes, 16);
BTRFS_SETGET_FUNCS(stripe_devid, struct btrfs_stripe, devid, 64);
BTRFS_SETGET_FUNCS(stripe_offset, struct btrfs_stripe, offset, 64);
static inline char *btrfs_stripe_dev_uuid(struct btrfs_stripe *s)
return (char *)s + offsetof(struct btrfs_stripe, dev_uuid);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_length, struct btrfs_chunk, length, 64);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_owner, struct btrfs_chunk, owner, 64);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_stripe_len, struct btrfs_chunk,
stripe_len, 64);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_io_align, struct btrfs_chunk,
io_align, 32);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_io_width, struct btrfs_chunk,
io_width, 32);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_sector_size, struct btrfs_chunk,
sector_size, 32);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_type, struct btrfs_chunk, type, 64);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_num_stripes, struct btrfs_chunk,
num_stripes, 16);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_sub_stripes, struct btrfs_chunk,
sub_stripes, 16);
BTRFS_SETGET_STACK_FUNCS(stack_stripe_devid, struct btrfs_stripe, devid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_stripe_offset, struct btrfs_stripe, offset, 64);
static inline struct btrfs_stripe *btrfs_stripe_nr(struct btrfs_chunk *c,
int nr)
unsigned long offset = (unsigned long)c;
offset += offsetof(struct btrfs_chunk, stripe);
offset += nr * sizeof(struct btrfs_stripe);
return (struct btrfs_stripe *)offset;
static inline char *btrfs_stripe_dev_uuid_nr(struct btrfs_chunk *c, int nr)
return btrfs_stripe_dev_uuid(btrfs_stripe_nr(c, nr));
static inline u64 btrfs_stripe_offset_nr(struct extent_buffer *eb,
struct btrfs_chunk *c, int nr)
return btrfs_stripe_offset(eb, btrfs_stripe_nr(c, nr));
static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb,
struct btrfs_chunk *c, int nr)
return btrfs_stripe_devid(eb, btrfs_stripe_nr(c, nr));
/* struct btrfs_block_group_item */
BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item,
used, 64);
BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item,
used, 64);
struct btrfs_block_group_item, chunk_objectid, 64);
struct btrfs_block_group_item, chunk_objectid, 64);
struct btrfs_block_group_item, flags, 64);
struct btrfs_block_group_item, flags, 64);
/* struct btrfs_free_space_info */
BTRFS_SETGET_FUNCS(free_space_extent_count, struct btrfs_free_space_info,
extent_count, 32);
BTRFS_SETGET_FUNCS(free_space_flags, struct btrfs_free_space_info, flags, 32);
/* struct btrfs_inode_ref */
BTRFS_SETGET_FUNCS(inode_ref_name_len, struct btrfs_inode_ref, name_len, 16);
BTRFS_SETGET_FUNCS(inode_ref_index, struct btrfs_inode_ref, index, 64);
/* struct btrfs_inode_extref */
BTRFS_SETGET_FUNCS(inode_extref_parent, struct btrfs_inode_extref,
parent_objectid, 64);
BTRFS_SETGET_FUNCS(inode_extref_name_len, struct btrfs_inode_extref,
name_len, 16);
BTRFS_SETGET_FUNCS(inode_extref_index, struct btrfs_inode_extref, index, 64);
/* struct btrfs_inode_item */
BTRFS_SETGET_FUNCS(inode_generation, struct btrfs_inode_item, generation, 64);
BTRFS_SETGET_FUNCS(inode_sequence, struct btrfs_inode_item, sequence, 64);
BTRFS_SETGET_FUNCS(inode_transid, struct btrfs_inode_item, transid, 64);
BTRFS_SETGET_FUNCS(inode_size, struct btrfs_inode_item, size, 64);
BTRFS_SETGET_FUNCS(inode_nbytes, struct btrfs_inode_item, nbytes, 64);
BTRFS_SETGET_FUNCS(inode_block_group, struct btrfs_inode_item, block_group, 64);
BTRFS_SETGET_FUNCS(inode_nlink, struct btrfs_inode_item, nlink, 32);
BTRFS_SETGET_FUNCS(inode_uid, struct btrfs_inode_item, uid, 32);
BTRFS_SETGET_FUNCS(inode_gid, struct btrfs_inode_item, gid, 32);
BTRFS_SETGET_FUNCS(inode_mode, struct btrfs_inode_item, mode, 32);
BTRFS_SETGET_FUNCS(inode_rdev, struct btrfs_inode_item, rdev, 64);
BTRFS_SETGET_FUNCS(inode_flags, struct btrfs_inode_item, flags, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_generation, struct btrfs_inode_item,
generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_sequence, struct btrfs_inode_item,
sequence, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_transid, struct btrfs_inode_item,
transid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_size, struct btrfs_inode_item, size, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_nbytes, struct btrfs_inode_item,
nbytes, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_block_group, struct btrfs_inode_item,
block_group, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_nlink, struct btrfs_inode_item, nlink, 32);
BTRFS_SETGET_STACK_FUNCS(stack_inode_uid, struct btrfs_inode_item, uid, 32);
BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, struct btrfs_inode_item, gid, 32);
BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, struct btrfs_inode_item, mode, 32);
BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, struct btrfs_inode_item, rdev, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, struct btrfs_inode_item, flags, 64);
BTRFS_SETGET_FUNCS(timespec_sec, struct btrfs_timespec, sec, 64);
BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
/* struct btrfs_dev_extent */
BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent,
chunk_tree, 64);
BTRFS_SETGET_FUNCS(dev_extent_chunk_objectid, struct btrfs_dev_extent,
chunk_objectid, 64);
BTRFS_SETGET_FUNCS(dev_extent_chunk_offset, struct btrfs_dev_extent,
chunk_offset, 64);
BTRFS_SETGET_FUNCS(dev_extent_length, struct btrfs_dev_extent, length, 64);
static inline unsigned long btrfs_dev_extent_chunk_tree_uuid(struct btrfs_dev_extent *dev)
unsigned long ptr = offsetof(struct btrfs_dev_extent, chunk_tree_uuid);
return (unsigned long)dev + ptr;
BTRFS_SETGET_FUNCS(extent_refs, struct btrfs_extent_item, refs, 64);
BTRFS_SETGET_FUNCS(extent_generation, struct btrfs_extent_item,
generation, 64);
BTRFS_SETGET_FUNCS(extent_flags, struct btrfs_extent_item, flags, 64);
BTRFS_SETGET_FUNCS(extent_refs_v0, struct btrfs_extent_item_v0, refs, 32);
BTRFS_SETGET_FUNCS(tree_block_level, struct btrfs_tree_block_info, level, 8);
static inline void btrfs_tree_block_key(struct extent_buffer *eb,
struct btrfs_tree_block_info *item,
struct btrfs_disk_key *key)
read_eb_member(eb, item, struct btrfs_tree_block_info, key, key);
static inline void btrfs_set_tree_block_key(struct extent_buffer *eb,
struct btrfs_tree_block_info *item,
struct btrfs_disk_key *key)
write_eb_member(eb, item, struct btrfs_tree_block_info, key, key);
BTRFS_SETGET_FUNCS(extent_data_ref_root, struct btrfs_extent_data_ref,
root, 64);
BTRFS_SETGET_FUNCS(extent_data_ref_objectid, struct btrfs_extent_data_ref,
objectid, 64);
BTRFS_SETGET_FUNCS(extent_data_ref_offset, struct btrfs_extent_data_ref,
offset, 64);
BTRFS_SETGET_FUNCS(extent_data_ref_count, struct btrfs_extent_data_ref,
count, 32);
BTRFS_SETGET_FUNCS(shared_data_ref_count, struct btrfs_shared_data_ref,
count, 32);
BTRFS_SETGET_FUNCS(extent_inline_ref_type, struct btrfs_extent_inline_ref,
type, 8);
BTRFS_SETGET_FUNCS(extent_inline_ref_offset, struct btrfs_extent_inline_ref,
offset, 64);
static inline u32 btrfs_extent_inline_ref_size(int type)
return sizeof(struct btrfs_extent_inline_ref);
return sizeof(struct btrfs_shared_data_ref) +
sizeof(struct btrfs_extent_inline_ref);
return sizeof(struct btrfs_extent_data_ref) +
offsetof(struct btrfs_extent_inline_ref, offset);
return 0;
BTRFS_SETGET_FUNCS(ref_root_v0, struct btrfs_extent_ref_v0, root, 64);
BTRFS_SETGET_FUNCS(ref_generation_v0, struct btrfs_extent_ref_v0,
generation, 64);
BTRFS_SETGET_FUNCS(ref_objectid_v0, struct btrfs_extent_ref_v0, objectid, 64);
BTRFS_SETGET_FUNCS(ref_count_v0, struct btrfs_extent_ref_v0, count, 32);
/* struct btrfs_node */
BTRFS_SETGET_FUNCS(key_blockptr, struct btrfs_key_ptr, blockptr, 64);
BTRFS_SETGET_FUNCS(key_generation, struct btrfs_key_ptr, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_key_blockptr, struct btrfs_key_ptr,
blockptr, 64);
BTRFS_SETGET_STACK_FUNCS(stack_key_generation, struct btrfs_key_ptr,
generation, 64);
static inline u64 btrfs_node_blockptr(struct extent_buffer *eb, int nr)
unsigned long ptr;
ptr = offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
return btrfs_key_blockptr(eb, (struct btrfs_key_ptr *)ptr);
static inline void btrfs_set_node_blockptr(struct extent_buffer *eb,
int nr, u64 val)
unsigned long ptr;
ptr = offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
btrfs_set_key_blockptr(eb, (struct btrfs_key_ptr *)ptr, val);
static inline u64 btrfs_node_ptr_generation(struct extent_buffer *eb, int nr)
unsigned long ptr;
ptr = offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
return btrfs_key_generation(eb, (struct btrfs_key_ptr *)ptr);
static inline void btrfs_set_node_ptr_generation(struct extent_buffer *eb,
int nr, u64 val)
unsigned long ptr;
ptr = offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
btrfs_set_key_generation(eb, (struct btrfs_key_ptr *)ptr, val);
static inline unsigned long btrfs_node_key_ptr_offset(int nr)
return offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
void btrfs_node_key(const struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr);
static inline void btrfs_set_node_key(struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr)
unsigned long ptr;
ptr = btrfs_node_key_ptr_offset(nr);
write_eb_member(eb, (struct btrfs_key_ptr *)ptr,
struct btrfs_key_ptr, key, disk_key);
/* struct btrfs_item */
BTRFS_SETGET_FUNCS(item_offset, struct btrfs_item, offset, 32);
BTRFS_SETGET_FUNCS(item_size, struct btrfs_item, size, 32);
BTRFS_SETGET_STACK_FUNCS(stack_item_offset, struct btrfs_item, offset, 32);
BTRFS_SETGET_STACK_FUNCS(stack_item_size, struct btrfs_item, size, 32);
static inline unsigned long btrfs_item_nr_offset(int nr)
return offsetof(struct btrfs_leaf, items) +
sizeof(struct btrfs_item) * nr;
static inline struct btrfs_item *btrfs_item_nr(int nr)
return (struct btrfs_item *)btrfs_item_nr_offset(nr);
static inline u32 btrfs_item_end(const struct extent_buffer *eb,
struct btrfs_item *item)
return btrfs_item_offset(eb, item) + btrfs_item_size(eb, item);
static inline u32 btrfs_item_end_nr(const struct extent_buffer *eb, int nr)
return btrfs_item_end(eb, btrfs_item_nr(nr));
static inline u32 btrfs_item_offset_nr(const struct extent_buffer *eb, int nr)
return btrfs_item_offset(eb, btrfs_item_nr(nr));
static inline u32 btrfs_item_size_nr(const struct extent_buffer *eb, int nr)
return btrfs_item_size(eb, btrfs_item_nr(nr));
static inline void btrfs_item_key(const struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr)
struct btrfs_item *item = btrfs_item_nr(nr);
read_eb_member(eb, item, struct btrfs_item, key, disk_key);
static inline void btrfs_set_item_key(struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr)
struct btrfs_item *item = btrfs_item_nr(nr);
write_eb_member(eb, item, struct btrfs_item, key, disk_key);
BTRFS_SETGET_FUNCS(dir_log_end, struct btrfs_dir_log_item, end, 64);
* struct btrfs_root_ref
BTRFS_SETGET_FUNCS(root_ref_dirid, struct btrfs_root_ref, dirid, 64);
BTRFS_SETGET_FUNCS(root_ref_sequence, struct btrfs_root_ref, sequence, 64);
BTRFS_SETGET_FUNCS(root_ref_name_len, struct btrfs_root_ref, name_len, 16);
/* struct btrfs_dir_item */
BTRFS_SETGET_FUNCS(dir_data_len, struct btrfs_dir_item, data_len, 16);
BTRFS_SETGET_FUNCS(dir_type, struct btrfs_dir_item, type, 8);
BTRFS_SETGET_FUNCS(dir_name_len, struct btrfs_dir_item, name_len, 16);
BTRFS_SETGET_FUNCS(dir_transid, struct btrfs_dir_item, transid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dir_type, struct btrfs_dir_item, type, 8);
BTRFS_SETGET_STACK_FUNCS(stack_dir_data_len, struct btrfs_dir_item,
data_len, 16);
BTRFS_SETGET_STACK_FUNCS(stack_dir_name_len, struct btrfs_dir_item,
name_len, 16);
BTRFS_SETGET_STACK_FUNCS(stack_dir_transid, struct btrfs_dir_item,
transid, 64);
static inline void btrfs_dir_item_key(const struct extent_buffer *eb,
const struct btrfs_dir_item *item,
struct btrfs_disk_key *key)
read_eb_member(eb, item, struct btrfs_dir_item, location, key);
static inline void btrfs_set_dir_item_key(struct extent_buffer *eb,
struct btrfs_dir_item *item,
const struct btrfs_disk_key *key)
write_eb_member(eb, item, struct btrfs_dir_item, location, key);
BTRFS_SETGET_FUNCS(free_space_entries, struct btrfs_free_space_header,
num_entries, 64);
BTRFS_SETGET_FUNCS(free_space_bitmaps, struct btrfs_free_space_header,
num_bitmaps, 64);
BTRFS_SETGET_FUNCS(free_space_generation, struct btrfs_free_space_header,
generation, 64);
static inline void btrfs_free_space_key(const struct extent_buffer *eb,
const struct btrfs_free_space_header *h,
struct btrfs_disk_key *key)
read_eb_member(eb, h, struct btrfs_free_space_header, location, key);
static inline void btrfs_set_free_space_key(struct extent_buffer *eb,
struct btrfs_free_space_header *h,
const struct btrfs_disk_key *key)
write_eb_member(eb, h, struct btrfs_free_space_header, location, key);
/* struct btrfs_disk_key */
BTRFS_SETGET_STACK_FUNCS(disk_key_objectid, struct btrfs_disk_key,
objectid, 64);
BTRFS_SETGET_STACK_FUNCS(disk_key_offset, struct btrfs_disk_key, offset, 64);
BTRFS_SETGET_STACK_FUNCS(disk_key_type, struct btrfs_disk_key, type, 8);
static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu,
const struct btrfs_disk_key *disk)
cpu->offset = le64_to_cpu(disk->offset);
cpu->type = disk->type;
cpu->objectid = le64_to_cpu(disk->objectid);
static inline void btrfs_cpu_key_to_disk(struct btrfs_disk_key *disk,
const struct btrfs_key *cpu)
disk->offset = cpu_to_le64(cpu->offset);
disk->type = cpu->type;
disk->objectid = cpu_to_le64(cpu->objectid);
static inline void btrfs_node_key_to_cpu(const struct extent_buffer *eb,
struct btrfs_key *key, int nr)
struct btrfs_disk_key disk_key;
btrfs_node_key(eb, &disk_key, nr);
btrfs_disk_key_to_cpu(key, &disk_key);
static inline void btrfs_item_key_to_cpu(const struct extent_buffer *eb,
struct btrfs_key *key, int nr)
struct btrfs_disk_key disk_key;
btrfs_item_key(eb, &disk_key, nr);
btrfs_disk_key_to_cpu(key, &disk_key);
static inline void btrfs_dir_item_key_to_cpu(const struct extent_buffer *eb,
const struct btrfs_dir_item *item,
struct btrfs_key *key)
struct btrfs_disk_key disk_key;
btrfs_dir_item_key(eb, item, &disk_key);
btrfs_disk_key_to_cpu(key, &disk_key);
static inline u8 btrfs_key_type(const struct btrfs_key *key)
return key->type;
static inline void btrfs_set_key_type(struct btrfs_key *key, u8 val)
key->type = val;
/* struct btrfs_header */
BTRFS_SETGET_HEADER_FUNCS(header_bytenr, struct btrfs_header, bytenr, 64);
BTRFS_SETGET_HEADER_FUNCS(header_generation, struct btrfs_header,
generation, 64);
BTRFS_SETGET_HEADER_FUNCS(header_owner, struct btrfs_header, owner, 64);
BTRFS_SETGET_HEADER_FUNCS(header_nritems, struct btrfs_header, nritems, 32);
BTRFS_SETGET_HEADER_FUNCS(header_flags, struct btrfs_header, flags, 64);
BTRFS_SETGET_HEADER_FUNCS(header_level, struct btrfs_header, level, 8);
BTRFS_SETGET_STACK_FUNCS(stack_header_generation, struct btrfs_header,
generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_header_owner, struct btrfs_header, owner, 64);
BTRFS_SETGET_STACK_FUNCS(stack_header_nritems, struct btrfs_header,
nritems, 32);
BTRFS_SETGET_STACK_FUNCS(stack_header_bytenr, struct btrfs_header, bytenr, 64);
static inline int btrfs_header_flag(const struct extent_buffer *eb, u64 flag)
return (btrfs_header_flags(eb) & flag) == flag;
static inline void btrfs_set_header_flag(struct extent_buffer *eb, u64 flag)
u64 flags = btrfs_header_flags(eb);
btrfs_set_header_flags(eb, flags | flag);
static inline void btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag)
u64 flags = btrfs_header_flags(eb);
btrfs_set_header_flags(eb, flags & ~flag);
static inline int btrfs_header_backref_rev(const struct extent_buffer *eb)
u64 flags = btrfs_header_flags(eb);
return flags >> BTRFS_BACKREF_REV_SHIFT;
static inline void btrfs_set_header_backref_rev(struct extent_buffer *eb,
int rev)
u64 flags = btrfs_header_flags(eb);
flags |= (u64)rev << BTRFS_BACKREF_REV_SHIFT;
btrfs_set_header_flags(eb, flags);
static inline unsigned long btrfs_header_fsid(void)
return offsetof(struct btrfs_header, fsid);
static inline unsigned long btrfs_header_chunk_tree_uuid(const struct extent_buffer *eb)
return offsetof(struct btrfs_header, chunk_tree_uuid);
static inline int btrfs_is_leaf(const struct extent_buffer *eb)
return btrfs_header_level(eb) == 0;
/* struct btrfs_root_item */
BTRFS_SETGET_FUNCS(disk_root_generation, struct btrfs_root_item,
generation, 64);
BTRFS_SETGET_FUNCS(disk_root_refs, struct btrfs_root_item, refs, 32);
BTRFS_SETGET_FUNCS(disk_root_bytenr, struct btrfs_root_item, bytenr, 64);
BTRFS_SETGET_FUNCS(disk_root_level, struct btrfs_root_item, level, 8);
BTRFS_SETGET_STACK_FUNCS(root_generation, struct btrfs_root_item,
generation, 64);
BTRFS_SETGET_STACK_FUNCS(root_bytenr, struct btrfs_root_item, bytenr, 64);
BTRFS_SETGET_STACK_FUNCS(root_level, struct btrfs_root_item, level, 8);
BTRFS_SETGET_STACK_FUNCS(root_dirid, struct btrfs_root_item, root_dirid, 64);
BTRFS_SETGET_STACK_FUNCS(root_refs, struct btrfs_root_item, refs, 32);
BTRFS_SETGET_STACK_FUNCS(root_flags, struct btrfs_root_item, flags, 64);
BTRFS_SETGET_STACK_FUNCS(root_used, struct btrfs_root_item, bytes_used, 64);
BTRFS_SETGET_STACK_FUNCS(root_limit, struct btrfs_root_item, byte_limit, 64);
BTRFS_SETGET_STACK_FUNCS(root_last_snapshot, struct btrfs_root_item,
last_snapshot, 64);
BTRFS_SETGET_STACK_FUNCS(root_generation_v2, struct btrfs_root_item,
generation_v2, 64);
BTRFS_SETGET_STACK_FUNCS(root_ctransid, struct btrfs_root_item,
ctransid, 64);
BTRFS_SETGET_STACK_FUNCS(root_otransid, struct btrfs_root_item,
otransid, 64);
BTRFS_SETGET_STACK_FUNCS(root_stransid, struct btrfs_root_item,
stransid, 64);
BTRFS_SETGET_STACK_FUNCS(root_rtransid, struct btrfs_root_item,
rtransid, 64);
static inline bool btrfs_root_readonly(const struct btrfs_root *root)
return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_RDONLY)) != 0;
static inline bool btrfs_root_dead(const struct btrfs_root *root)
return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0;
/* struct btrfs_root_backup */
BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup,
tree_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_tree_root_gen, struct btrfs_root_backup,
tree_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_tree_root_level, struct btrfs_root_backup,
tree_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_chunk_root, struct btrfs_root_backup,
chunk_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_gen, struct btrfs_root_backup,
chunk_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_level, struct btrfs_root_backup,
chunk_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_extent_root, struct btrfs_root_backup,
extent_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_extent_root_gen, struct btrfs_root_backup,
extent_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_extent_root_level, struct btrfs_root_backup,
extent_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_fs_root, struct btrfs_root_backup,
fs_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_fs_root_gen, struct btrfs_root_backup,
fs_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_fs_root_level, struct btrfs_root_backup,
fs_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_dev_root, struct btrfs_root_backup,
dev_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_dev_root_gen, struct btrfs_root_backup,
dev_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_dev_root_level, struct btrfs_root_backup,
dev_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_csum_root, struct btrfs_root_backup,
csum_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_csum_root_gen, struct btrfs_root_backup,
csum_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_csum_root_level, struct btrfs_root_backup,
csum_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_total_bytes, struct btrfs_root_backup,
total_bytes, 64);
BTRFS_SETGET_STACK_FUNCS(backup_bytes_used, struct btrfs_root_backup,
bytes_used, 64);
BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup,
num_devices, 64);
/* struct btrfs_balance_item */
BTRFS_SETGET_FUNCS(balance_flags, struct btrfs_balance_item, flags, 64);
static inline void btrfs_balance_data(const struct extent_buffer *eb,
const struct btrfs_balance_item *bi,
struct btrfs_disk_balance_args *ba)
read_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
static inline void btrfs_set_balance_data(struct extent_buffer *eb,
struct btrfs_balance_item *bi,
const struct btrfs_disk_balance_args *ba)
write_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
static inline void btrfs_balance_meta(const struct extent_buffer *eb,
const struct btrfs_balance_item *bi,
struct btrfs_disk_balance_args *ba)
read_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
static inline void btrfs_set_balance_meta(struct extent_buffer *eb,
struct btrfs_balance_item *bi,
const struct btrfs_disk_balance_args *ba)
write_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
static inline void btrfs_balance_sys(const struct extent_buffer *eb,
const struct btrfs_balance_item *bi,
struct btrfs_disk_balance_args *ba)
read_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
static inline void btrfs_set_balance_sys(struct extent_buffer *eb,
struct btrfs_balance_item *bi,
const struct btrfs_disk_balance_args *ba)
write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
static inline void
btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
const struct btrfs_disk_balance_args *disk)
memset(cpu, 0, sizeof(*cpu));
cpu->profiles = le64_to_cpu(disk->profiles);
cpu->usage = le64_to_cpu(disk->usage);
cpu->devid = le64_to_cpu(disk->devid);
cpu->pstart = le64_to_cpu(disk->pstart);
cpu->pend = le64_to_cpu(disk->pend);
cpu->vstart = le64_to_cpu(disk->vstart);
cpu->vend = le64_to_cpu(disk->vend);
cpu->target = le64_to_cpu(disk->target);
cpu->flags = le64_to_cpu(disk->flags);
cpu->limit = le64_to_cpu(disk->limit);
cpu->stripes_min = le32_to_cpu(disk->stripes_min);
cpu->stripes_max = le32_to_cpu(disk->stripes_max);
static inline void
btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
const struct btrfs_balance_args *cpu)
memset(disk, 0, sizeof(*disk));
disk->profiles = cpu_to_le64(cpu->profiles);
disk->usage = cpu_to_le64(cpu->usage);
disk->devid = cpu_to_le64(cpu->devid);
disk->pstart = cpu_to_le64(cpu->pstart);
disk->pend = cpu_to_le64(cpu->pend);
disk->vstart = cpu_to_le64(cpu->vstart);
disk->vend = cpu_to_le64(cpu->vend);
disk->target = cpu_to_le64(cpu->target);
disk->flags = cpu_to_le64(cpu->flags);
disk->limit = cpu_to_le64(cpu->limit);
disk->stripes_min = cpu_to_le32(cpu->stripes_min);
disk->stripes_max = cpu_to_le32(cpu->stripes_max);
/* struct btrfs_super_block */
BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64);
BTRFS_SETGET_STACK_FUNCS(super_flags, struct btrfs_super_block, flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_generation, struct btrfs_super_block,
generation, 64);
BTRFS_SETGET_STACK_FUNCS(super_root, struct btrfs_super_block, root, 64);
struct btrfs_super_block, sys_chunk_array_size, 32);
struct btrfs_super_block, chunk_root_generation, 64);
BTRFS_SETGET_STACK_FUNCS(super_root_level, struct btrfs_super_block,
root_level, 8);
BTRFS_SETGET_STACK_FUNCS(super_chunk_root, struct btrfs_super_block,
chunk_root, 64);
BTRFS_SETGET_STACK_FUNCS(super_chunk_root_level, struct btrfs_super_block,
chunk_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(super_log_root, struct btrfs_super_block,
log_root, 64);
BTRFS_SETGET_STACK_FUNCS(super_log_root_transid, struct btrfs_super_block,
log_root_transid, 64);
BTRFS_SETGET_STACK_FUNCS(super_log_root_level, struct btrfs_super_block,
log_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(super_total_bytes, struct btrfs_super_block,
total_bytes, 64);
BTRFS_SETGET_STACK_FUNCS(super_bytes_used, struct btrfs_super_block,
bytes_used, 64);
BTRFS_SETGET_STACK_FUNCS(super_sectorsize, struct btrfs_super_block,
sectorsize, 32);
BTRFS_SETGET_STACK_FUNCS(super_nodesize, struct btrfs_super_block,
nodesize, 32);
BTRFS_SETGET_STACK_FUNCS(super_stripesize, struct btrfs_super_block,
stripesize, 32);
BTRFS_SETGET_STACK_FUNCS(super_root_dir, struct btrfs_super_block,
root_dir_objectid, 64);
BTRFS_SETGET_STACK_FUNCS(super_num_devices, struct btrfs_super_block,
num_devices, 64);
BTRFS_SETGET_STACK_FUNCS(super_compat_flags, struct btrfs_super_block,
compat_flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_compat_ro_flags, struct btrfs_super_block,
compat_ro_flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_incompat_flags, struct btrfs_super_block,
incompat_flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_csum_type, struct btrfs_super_block,
csum_type, 16);
BTRFS_SETGET_STACK_FUNCS(super_cache_generation, struct btrfs_super_block,
cache_generation, 64);
BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64);
BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
uuid_tree_generation, 64);
static inline int btrfs_super_csum_size(const struct btrfs_super_block *s)
u16 t = btrfs_super_csum_type(s);
* csum type is validated at mount time
return btrfs_csum_sizes[t];
* The leaf data grows from end-to-front in the node.
* this returns the address of the start of the last item,
* which is the stop of the leaf data stack
static inline unsigned int leaf_data_end(const struct extent_buffer *leaf)
u32 nr = btrfs_header_nritems(leaf);
if (nr == 0)
return BTRFS_LEAF_DATA_SIZE(leaf->fs_info);
return btrfs_item_offset_nr(leaf, nr - 1);
/* struct btrfs_file_extent_item */
BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8);
struct btrfs_file_extent_item, disk_bytenr, 64);
struct btrfs_file_extent_item, offset, 64);
struct btrfs_file_extent_item, generation, 64);
struct btrfs_file_extent_item, num_bytes, 64);
struct btrfs_file_extent_item, disk_num_bytes, 64);
struct btrfs_file_extent_item, compression, 8);
static inline unsigned long
btrfs_file_extent_inline_start(const struct btrfs_file_extent_item *e)
return (unsigned long)e + BTRFS_FILE_EXTENT_INLINE_DATA_START;
static inline u32 btrfs_file_extent_calc_inline_size(u32 datasize)
BTRFS_SETGET_FUNCS(file_extent_disk_bytenr, struct btrfs_file_extent_item,
disk_bytenr, 64);
BTRFS_SETGET_FUNCS(file_extent_generation, struct btrfs_file_extent_item,
generation, 64);
BTRFS_SETGET_FUNCS(file_extent_disk_num_bytes, struct btrfs_file_extent_item,
disk_num_bytes, 64);
BTRFS_SETGET_FUNCS(file_extent_offset, struct btrfs_file_extent_item,
offset, 64);
BTRFS_SETGET_FUNCS(file_extent_num_bytes, struct btrfs_file_extent_item,
num_bytes, 64);
BTRFS_SETGET_FUNCS(file_extent_ram_bytes, struct btrfs_file_extent_item,
ram_bytes, 64);
BTRFS_SETGET_FUNCS(file_extent_compression, struct btrfs_file_extent_item,
compression, 8);
BTRFS_SETGET_FUNCS(file_extent_encryption, struct btrfs_file_extent_item,
encryption, 8);
BTRFS_SETGET_FUNCS(file_extent_other_encoding, struct btrfs_file_extent_item,
other_encoding, 16);
* this returns the number of bytes used by the item on disk, minus the
* size of any extent headers. If a file is compressed on disk, this is
* the compressed size
static inline u32 btrfs_file_extent_inline_item_len(
const struct extent_buffer *eb,
struct btrfs_item *e)
return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
/* btrfs_dev_stats_item */
static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb,
const struct btrfs_dev_stats_item *ptr,
int index)
u64 val;
read_extent_buffer(eb, &val,
offsetof(struct btrfs_dev_stats_item, values) +
((unsigned long)ptr) + (index * sizeof(u64)),
return val;
static inline void btrfs_set_dev_stats_value(struct extent_buffer *eb,
struct btrfs_dev_stats_item *ptr,
int index, u64 val)
write_extent_buffer(eb, &val,
offsetof(struct btrfs_dev_stats_item, values) +
((unsigned long)ptr) + (index * sizeof(u64)),
/* btrfs_qgroup_status_item */
BTRFS_SETGET_FUNCS(qgroup_status_generation, struct btrfs_qgroup_status_item,
generation, 64);
BTRFS_SETGET_FUNCS(qgroup_status_version, struct btrfs_qgroup_status_item,
version, 64);
BTRFS_SETGET_FUNCS(qgroup_status_flags, struct btrfs_qgroup_status_item,
flags, 64);
BTRFS_SETGET_FUNCS(qgroup_status_rescan, struct btrfs_qgroup_status_item,
rescan, 64);
/* btrfs_qgroup_info_item */
BTRFS_SETGET_FUNCS(qgroup_info_generation, struct btrfs_qgroup_info_item,
generation, 64);
BTRFS_SETGET_FUNCS(qgroup_info_rfer, struct btrfs_qgroup_info_item, rfer, 64);
BTRFS_SETGET_FUNCS(qgroup_info_rfer_cmpr, struct btrfs_qgroup_info_item,
rfer_cmpr, 64);
BTRFS_SETGET_FUNCS(qgroup_info_excl, struct btrfs_qgroup_info_item, excl, 64);
BTRFS_SETGET_FUNCS(qgroup_info_excl_cmpr, struct btrfs_qgroup_info_item,
excl_cmpr, 64);
struct btrfs_qgroup_info_item, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_rfer, struct btrfs_qgroup_info_item,
rfer, 64);
struct btrfs_qgroup_info_item, rfer_cmpr, 64);
BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_excl, struct btrfs_qgroup_info_item,
excl, 64);
struct btrfs_qgroup_info_item, excl_cmpr, 64);
/* btrfs_qgroup_limit_item */
BTRFS_SETGET_FUNCS(qgroup_limit_flags, struct btrfs_qgroup_limit_item,
flags, 64);
BTRFS_SETGET_FUNCS(qgroup_limit_max_rfer, struct btrfs_qgroup_limit_item,
max_rfer, 64);
BTRFS_SETGET_FUNCS(qgroup_limit_max_excl, struct btrfs_qgroup_limit_item,
max_excl, 64);
BTRFS_SETGET_FUNCS(qgroup_limit_rsv_rfer, struct btrfs_qgroup_limit_item,
rsv_rfer, 64);
BTRFS_SETGET_FUNCS(qgroup_limit_rsv_excl, struct btrfs_qgroup_limit_item,
rsv_excl, 64);
/* btrfs_dev_replace_item */
struct btrfs_dev_replace_item, src_devid, 64);
struct btrfs_dev_replace_item, cont_reading_from_srcdev_mode,
BTRFS_SETGET_FUNCS(dev_replace_replace_state, struct btrfs_dev_replace_item,
replace_state, 64);
BTRFS_SETGET_FUNCS(dev_replace_time_started, struct btrfs_dev_replace_item,
time_started, 64);
BTRFS_SETGET_FUNCS(dev_replace_time_stopped, struct btrfs_dev_replace_item,
time_stopped, 64);
BTRFS_SETGET_FUNCS(dev_replace_num_write_errors, struct btrfs_dev_replace_item,
num_write_errors, 64);
struct btrfs_dev_replace_item, num_uncorrectable_read_errors,
BTRFS_SETGET_FUNCS(dev_replace_cursor_left, struct btrfs_dev_replace_item,
cursor_left, 64);
BTRFS_SETGET_FUNCS(dev_replace_cursor_right, struct btrfs_dev_replace_item,
cursor_right, 64);
struct btrfs_dev_replace_item, src_devid, 64);
struct btrfs_dev_replace_item,
cont_reading_from_srcdev_mode, 64);
struct btrfs_dev_replace_item, replace_state, 64);
struct btrfs_dev_replace_item, time_started, 64);
struct btrfs_dev_replace_item, time_stopped, 64);
struct btrfs_dev_replace_item, num_write_errors, 64);
struct btrfs_dev_replace_item,
num_uncorrectable_read_errors, 64);
struct btrfs_dev_replace_item, cursor_left, 64);
struct btrfs_dev_replace_item, cursor_right, 64);
/* helper function to cast into the data area of the leaf. */
#define btrfs_item_ptr(leaf, slot, type) \
btrfs_item_offset_nr(leaf, slot)))
#define btrfs_item_ptr_offset(leaf, slot) \
((unsigned long)(BTRFS_LEAF_DATA_OFFSET + \
btrfs_item_offset_nr(leaf, slot)))
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 bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
return ((space_info->flags & BTRFS_BLOCK_GROUP_METADATA) &&
(space_info->flags & BTRFS_BLOCK_GROUP_DATA));
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 {
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 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes);
static inline u64 btrfs_calc_trans_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 won't result in new nodes or leaves, just what we need for
* COW.
static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
unsigned num_items)
return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans);
bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
const u64 start);
void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
void btrfs_put_block_group(struct btrfs_block_group_cache *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_fs_info *fs_info,
u64 bytenr, u64 num, int reserved);
int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
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);
struct btrfs_block_group_cache *btrfs_lookup_block_group(
struct btrfs_fs_info *info,
u64 bytenr);
void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
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);
void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
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,
u64 bytenr, u64 num_bytes, u64 flags,
int level, int is_data);
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_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 len);
void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info);
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);
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
int btrfs_free_block_groups(struct btrfs_fs_info *info);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr);
int btrfs_make_block_group(struct btrfs_trans_handle *trans,
u64 bytes_used, u64 type, u64 chunk_offset,
u64 size);
void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
struct btrfs_fs_info *fs_info,
const u64 chunk_offset);
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
u64 group_start, struct extent_map *em);
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info);
u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info);
u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
enum btrfs_reserve_flush_enum {
/* If we are in the transaction, we can't flush anything.*/
* Flushing delalloc may cause deadlock somewhere, in this
* case, use FLUSH LIMIT
enum btrfs_flush_state {
int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
int btrfs_check_data_free_space(struct inode *inode,
struct extent_changeset **reserved, u64 start, u64 len);
void btrfs_free_reserved_data_space(struct inode *inode,
struct extent_changeset *reserved, u64 start, u64 len);
void btrfs_delalloc_release_space(struct inode *inode,
struct extent_changeset *reserved,
u64 start, u64 len, bool qgroup_free);
void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
u64 len);
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
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_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
bool qgroup_free);
int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
bool qgroup_free);
int btrfs_delalloc_reserve_space(struct inode *inode,
struct extent_changeset **reserved, u64 start, u64 len);
void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,