/* holds quota configuration and tracking */
#define BTRFS_QUOTA_TREE_OBJECTID 8ULL
+/* for storing items that use the BTRFS_UUID_KEY* types */
+#define BTRFS_UUID_TREE_OBJECTID 9ULL
+
/* for storing balance parameters in the root tree */
#define BTRFS_BALANCE_OBJECTID -4ULL
#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4)
#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5)
#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6)
-#define BTRFS_BLOCK_GROUP_RAID5 (1 << 7)
-#define BTRFS_BLOCK_GROUP_RAID6 (1 << 8)
+#define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7)
+#define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8)
#define BTRFS_BLOCK_GROUP_RESERVED BTRFS_AVAIL_ALLOC_BIT_SINGLE
enum btrfs_raid_types {
account */
/*
+ * 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 everytime we call
+ * btrfs_free_extent so it is a realtime count of what will be freed
+ * once the transaction is committed. It will be zero'ed everytime the
+ * transaction commits.
+ */
+ struct percpu_counter total_bytes_pinned;
+
+ /*
* we bump reservation progress every time we decrement
* bytes_reserved. This way people waiting for reservations
* know something good has happened and they can check
BTRFS_CACHE_STARTED = 1,
BTRFS_CACHE_FAST = 2,
BTRFS_CACHE_FINISHED = 3,
+ BTRFS_CACHE_ERROR = 4,
};
enum btrfs_disk_cache_state {
u64 last_trans_log_full_commit;
unsigned long mount_opt;
unsigned long compress_type:4;
+ int 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
* before jumping into the main commit.
*/
struct mutex ordered_operations_mutex;
+
+ /*
+ * Same as ordered_operations_mutex except this is for ordered extents
+ * and not the operations.
+ */
+ struct mutex ordered_extent_flush_mutex;
+
struct rw_semaphore extent_commit_sem;
struct rw_semaphore cleanup_work_sem;
atomic_t open_ioctl_trans;
/*
- * this is used by the balancing code to wait for all the pending
- * ordered extents
+ * this is used to protect the following list -- ordered_roots.
*/
- spinlock_t ordered_extent_lock;
+ spinlock_t ordered_root_lock;
/*
- * all of the data=ordered extents pending writeback
+ * 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_extents;
+ struct list_head ordered_roots;
- 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;
+ 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
int do_barriers;
int closing;
int log_root_recovering;
- int enospc_unlink;
- int trans_no_join;
u64 total_pinned;
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;
struct mutex qgroup_rescan_lock; /* protects the progress item */
struct btrfs_key qgroup_rescan_progress;
struct btrfs_workers qgroup_rescan_workers;
+ struct completion qgroup_rescan_completion;
+ struct btrfs_work qgroup_rescan_work;
/* filesystem state */
unsigned long fs_state;
int force_cow;
spinlock_t root_item_lock;
+ atomic_t refs;
+
+ 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;
+ /*
+ * 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;
};
struct btrfs_ioctl_defrag_range_args {
#define BTRFS_DEV_REPLACE_KEY 250
/*
+ * Stores items that allow to quickly map UUIDs to something else.
+ * These items are part of the filesystem UUID tree.
+ * The key is built like this:
+ * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits).
+ */
+#if BTRFS_UUID_SIZE != 16
+#error "UUID items require BTRFS_UUID_SIZE == 16!"
+#endif
+#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */
+#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to
+ * received subvols */
+
+/*
* string items are for debugging. They just store a short string of
* data in the FS
*/
#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
#define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22)
+#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
+
#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)
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);
static inline struct btrfs_timespec *
btrfs_inode_atime(struct btrfs_inode_item *inode_item)
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,
/* 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)
{
/* 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)
{
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(struct extent_buffer *eb,
struct btrfs_dir_item *item,
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(struct extent_buffer *eb, u64 flag)
{
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);
static inline int btrfs_super_csum_size(struct btrfs_super_block *s)
{
/* struct btrfs_file_extent_item */
BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_bytenr,
+ struct btrfs_file_extent_item, disk_bytenr, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_offset,
+ struct btrfs_file_extent_item, offset, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_generation,
+ struct btrfs_file_extent_item, generation, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_num_bytes,
+ struct btrfs_file_extent_item, num_bytes, 64);
static inline unsigned long
btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e)
num_items;
}
+int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root, unsigned long count);
u64 bytenr, u64 num, int reserved);
int btrfs_pin_extent_for_log_replay(struct btrfs_root *root,
u64 bytenr, u64 num_bytes);
+int btrfs_exclude_logged_extents(struct btrfs_root *root,
+ struct extent_buffer *eb);
int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 objectid, u64 offset, u64 bytenr);
struct btrfs_root *root,
u64 root_objectid, u64 owner, u64 offset,
struct btrfs_key *ins);
-int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- u64 num_bytes, u64 min_alloc_size,
- u64 empty_size, u64 hint_byte,
- struct btrfs_key *ins, int is_data);
+int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
+ u64 min_alloc_size, u64 empty_size, u64 hint_byte,
+ struct btrfs_key *ins, int is_data);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf, int full_backref, int for_cow);
int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int nitems,
- u64 *qgroup_reserved);
+ u64 *qgroup_reserved, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
u64 qgroup_reserved);
int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
struct btrfs_block_rsv *dst_rsv,
u64 num_bytes);
+int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
+ struct btrfs_block_rsv *dest, u64 num_bytes,
+ int min_factor);
void btrfs_block_rsv_release(struct btrfs_root *root,
struct btrfs_block_rsv *block_rsv,
u64 num_bytes);
BTRFS_COMPARE_TREE_NEW,
BTRFS_COMPARE_TREE_DELETED,
BTRFS_COMPARE_TREE_CHANGED,
+ BTRFS_COMPARE_TREE_SAME,
};
typedef int (*btrfs_changed_cb_t)(struct btrfs_root *left_root,
struct btrfs_root *right_root,
smp_mb();
return fs_info->closing;
}
+
+/*
+ * If we remount the fs to be R/O or umount the fs, the cleaner needn't do
+ * anything except sleeping. This function is used to check the status of
+ * the fs.
+ */
+static inline int btrfs_need_cleaner_sleep(struct btrfs_root *root)
+{
+ return (root->fs_info->sb->s_flags & MS_RDONLY ||
+ btrfs_fs_closing(root->fs_info));
+}
+
static inline void free_fs_info(struct btrfs_fs_info *fs_info)
{
kfree(fs_info->balance_ctl);
struct btrfs_root *root,
struct btrfs_key *key,
struct btrfs_root_item *item);
-void btrfs_read_root_item(struct extent_buffer *eb, int slot,
- struct btrfs_root_item *item);
-int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, struct
- btrfs_root_item *item, struct btrfs_key *key);
-int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid);
+int btrfs_find_root(struct btrfs_root *root, 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_root *tree_root);
void btrfs_set_root_node(struct btrfs_root_item *item,
struct extent_buffer *node);
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,
+ struct btrfs_root *uuid_root, u8 *uuid, u8 type,
+ u64 subid);
+int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
+ struct btrfs_root *uuid_root, u8 *uuid, u8 type,
+ u64 subid);
+
/* dir-item.c */
int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
const char *name, int name_len);
struct btrfs_inode_extref **extref_ret);
/* file-item.c */
+struct btrfs_dio_private;
int btrfs_del_csums(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr, u64 len);
int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode,
struct bio *bio, u32 *dst);
int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
- struct bio *bio, u64 logical_offset);
+ struct btrfs_dio_private *dip, struct bio *bio,
+ u64 logical_offset);
int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 objectid, u64 pos,
struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
size_t pg_offset, u64 start, u64 len,
int create);
+noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
+ u64 *orig_start, u64 *orig_block_len,
+ u64 *ram_bytes);
/* RHEL and EL kernels have a patch that renames PG_checked to FsMisc */
#if defined(ClearPageFsMisc) && !defined(ClearPageChecked)
u32 min_type);
int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
+int btrfs_start_all_delalloc_inodes(struct btrfs_fs_info *fs_info,
+ int delay_iput);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
struct extent_state **cached_state);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
u64 newer_than, unsigned long max_pages);
void btrfs_get_block_group_info(struct list_head *groups_list,
struct btrfs_ioctl_space_info *space);
+void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+ struct btrfs_ioctl_balance_args *bargs);
+
/* file.c */
int btrfs_auto_defrag_init(void);
int btrfs_quota_disable(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
+void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 src, u64 dst);
int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,