summaryrefslogtreecommitdiff
path: root/fs/btrfs/btrfs_inode.h
blob: 7c1527fcc7b381fd1ac972d96aeb33b1c049f43b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#ifndef BTRFS_INODE_H
#define BTRFS_INODE_H

#include <linux/hash.h>
#include <linux/refcount.h>
#include "extent_map.h"
#include "extent_io.h"
#include "ordered-data.h"
#include "delayed-inode.h"

/*
 * Since we search a directory based on f_pos (struct dir_context::pos) we have
 * to start at 2 since '.' and '..' have f_pos of 0 and 1 respectively, so
 * everybody else has to start at 2 (see btrfs_real_readdir() and dir_emit_dots()).
 */
#define BTRFS_DIR_START_INDEX 2

/*
 * ordered_data_close is set by truncate when a file that used
 * to have good data has been truncated to zero.  When it is set
 * the btrfs file release call will add this inode to the
 * ordered operations list so that we make sure to flush out any
 * new data the application may have written before commit.
 */
enum {
	BTRFS_INODE_FLUSH_ON_CLOSE,
	BTRFS_INODE_DUMMY,
	BTRFS_INODE_IN_DEFRAG,
	BTRFS_INODE_HAS_ASYNC_EXTENT,
	 /*
	  * Always set under the VFS' inode lock, otherwise it can cause races
	  * during fsync (we start as a fast fsync and then end up in a full
	  * fsync racing with ordered extent completion).
	  */
	BTRFS_INODE_NEEDS_FULL_SYNC,
	BTRFS_INODE_COPY_EVERYTHING,
	BTRFS_INODE_IN_DELALLOC_LIST,
	BTRFS_INODE_HAS_PROPS,
	BTRFS_INODE_SNAPSHOT_FLUSH,
	/*
	 * Set and used when logging an inode and it serves to signal that an
	 * inode does not have xattrs, so subsequent fsyncs can avoid searching
	 * for xattrs to log. This bit must be cleared whenever a xattr is added
	 * to an inode.
	 */
	BTRFS_INODE_NO_XATTRS,
	/*
	 * Set when we are in a context where we need to start a transaction and
	 * have dirty pages with the respective file range locked. This is to
	 * ensure that when reserving space for the transaction, if we are low
	 * on available space and need to flush delalloc, we will not flush
	 * delalloc for this inode, because that could result in a deadlock (on
	 * the file range, inode's io_tree).
	 */
	BTRFS_INODE_NO_DELALLOC_FLUSH,
	/*
	 * Set when we are working on enabling verity for a file. Computing and
	 * writing the whole Merkle tree can take a while so we want to prevent
	 * races where two separate tasks attempt to simultaneously start verity
	 * on the same file.
	 */
	BTRFS_INODE_VERITY_IN_PROGRESS,
	/* Set when this inode is a free space inode. */
	BTRFS_INODE_FREE_SPACE_INODE,
};

/* in memory btrfs inode */
struct btrfs_inode {
	/* which subvolume this inode belongs to */
	struct btrfs_root *root;

	/* key used to find this inode on disk.  This is used by the code
	 * to read in roots of subvolumes
	 */
	struct btrfs_key location;

	/*
	 * Lock for counters and all fields used to determine if the inode is in
	 * the log or not (last_trans, last_sub_trans, last_log_commit,
	 * logged_trans), to access/update new_delalloc_bytes and to update the
	 * VFS' inode number of bytes used.
	 */
	spinlock_t lock;

	/* the extent_tree has caches of all the extent mappings to disk */
	struct extent_map_tree extent_tree;

	/* the io_tree does range state (DIRTY, LOCKED etc) */
	struct extent_io_tree io_tree;

	/* special utility tree used to record which mirrors have already been
	 * tried when checksums fail for a given block
	 */
	struct rb_root io_failure_tree;
	spinlock_t io_failure_lock;

	/*
	 * Keep track of where the inode has extent items mapped in order to
	 * make sure the i_size adjustments are accurate
	 */
	struct extent_io_tree file_extent_tree;

	/* held while logging the inode in tree-log.c */
	struct mutex log_mutex;

	/* used to order data wrt metadata */
	struct btrfs_ordered_inode_tree ordered_tree;

	/* list of all the delalloc inodes in the FS.  There are times we need
	 * to write all the delalloc pages to disk, and this list is used
	 * to walk them all.
	 */
	struct list_head delalloc_inodes;

	/* node for the red-black tree that links inodes in subvolume root */
	struct rb_node rb_node;

	unsigned long runtime_flags;

	/* Keep track of who's O_SYNC/fsyncing currently */
	atomic_t sync_writers;

	/* full 64 bit generation number, struct vfs_inode doesn't have a big
	 * enough field for this.
	 */
	u64 generation;

	/*
	 * transid of the trans_handle that last modified this inode
	 */
	u64 last_trans;

	/*
	 * transid that last logged this inode
	 */
	u64 logged_trans;

	/*
	 * log transid when this inode was last modified
	 */
	int last_sub_trans;

	/* a local copy of root's last_log_commit */
	int last_log_commit;

	/*
	 * Total number of bytes pending delalloc, used by stat to calculate the
	 * real block usage of the file. This is used only for files.
	 */
	u64 delalloc_bytes;

	union {
		/*
		 * Total number of bytes pending delalloc that fall within a file
		 * range that is either a hole or beyond EOF (and no prealloc extent
		 * exists in the range). This is always <= delalloc_bytes and this
		 * is used only for files.
		 */
		u64 new_delalloc_bytes;
		/*
		 * The offset of the last dir index key that was logged.
		 * This is used only for directories.
		 */
		u64 last_dir_index_offset;
	};

	/*
	 * total number of bytes pending defrag, used by stat to check whether
	 * it needs COW.
	 */
	u64 defrag_bytes;

	/*
	 * the size of the file stored in the metadata on disk.  data=ordered
	 * means the in-memory i_size might be larger than the size on disk
	 * because not all the blocks are written yet.
	 */
	u64 disk_i_size;

	/*
	 * If this is a directory then index_cnt is the counter for the index
	 * number for new files that are created. For an empty directory, this
	 * must be initialized to BTRFS_DIR_START_INDEX.
	 */
	u64 index_cnt;

	/* Cache the directory index number to speed the dir/file remove */
	u64 dir_index;

	/* the fsync log has some corner cases that mean we have to check
	 * directories to see if any unlinks have been done before
	 * the directory was logged.  See tree-log.c for all the
	 * details
	 */
	u64 last_unlink_trans;

	/*
	 * The id/generation of the last transaction where this inode was
	 * either the source or the destination of a clone/dedupe operation.
	 * Used when logging an inode to know if there are shared extents that
	 * need special care when logging checksum items, to avoid duplicate
	 * checksum items in a log (which can lead to a corruption where we end
	 * up with missing checksum ranges after log replay).
	 * Protected by the vfs inode lock.
	 */
	u64 last_reflink_trans;

	/*
	 * Number of bytes outstanding that are going to need csums.  This is
	 * used in ENOSPC accounting.
	 */
	u64 csum_bytes;

	/* Backwards incompatible flags, lower half of inode_item::flags  */
	u32 flags;
	/* Read-only compatibility flags, upper half of inode_item::flags */
	u32 ro_flags;

	/*
	 * Counters to keep track of the number of extent item's we may use due
	 * to delalloc and such.  outstanding_extents is the number of extent
	 * items we think we'll end up using, and reserved_extents is the number
	 * of extent items we've reserved metadata for.
	 */
	unsigned outstanding_extents;

	struct btrfs_block_rsv block_rsv;

	/*
	 * Cached values of inode properties
	 */
	unsigned prop_compress;		/* per-file compression algorithm */
	/*
	 * Force compression on the file using the defrag ioctl, could be
	 * different from prop_compress and takes precedence if set
	 */
	unsigned defrag_compress;

	struct btrfs_delayed_node *delayed_node;

	/* File creation time. */
	struct timespec64 i_otime;

	/* Hook into fs_info->delayed_iputs */
	struct list_head delayed_iput;

	struct rw_semaphore i_mmap_lock;
	struct inode vfs_inode;
};

static inline struct btrfs_inode *BTRFS_I(const struct inode *inode)
{
	return container_of(inode, struct btrfs_inode, vfs_inode);
}

static inline unsigned long btrfs_inode_hash(u64 objectid,
					     const struct btrfs_root *root)
{
	u64 h = objectid ^ (root->root_key.objectid * GOLDEN_RATIO_PRIME);

#if BITS_PER_LONG == 32
	h = (h >> 32) ^ (h & 0xffffffff);
#endif

	return (unsigned long)h;
}

#if BITS_PER_LONG == 32

/*
 * On 32 bit systems the i_ino of struct inode is 32 bits (unsigned long), so
 * we use the inode's location objectid which is a u64 to avoid truncation.
 */
static inline u64 btrfs_ino(const struct btrfs_inode *inode)
{
	u64 ino = inode->location.objectid;

	/* type == BTRFS_ROOT_ITEM_KEY: subvol dir */
	if (inode->location.type == BTRFS_ROOT_ITEM_KEY)
		ino = inode->vfs_inode.i_ino;
	return ino;
}

#else

static inline u64 btrfs_ino(const struct btrfs_inode *inode)
{
	return inode->vfs_inode.i_ino;
}

#endif

static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size)
{
	i_size_write(&inode->vfs_inode, size);
	inode->disk_i_size = size;
}

static inline bool btrfs_is_free_space_inode(struct btrfs_inode *inode)
{
	return test_bit(BTRFS_INODE_FREE_SPACE_INODE, &inode->runtime_flags);
}

static inline bool is_data_inode(struct inode *inode)
{
	return btrfs_ino(BTRFS_I(inode)) != BTRFS_BTREE_INODE_OBJECTID;
}

static inline void btrfs_mod_outstanding_extents(struct btrfs_inode *inode,
						 int mod)
{
	lockdep_assert_held(&inode->lock);
	inode->outstanding_extents += mod;
	if (btrfs_is_free_space_inode(inode))
		return;
	trace_btrfs_inode_mod_outstanding_extents(inode->root, btrfs_ino(inode),
						  mod);
}

/*
 * Called every time after doing a buffered, direct IO or memory mapped write.
 *
 * This is to ensure that if we write to a file that was previously fsynced in
 * the current transaction, then try to fsync it again in the same transaction,
 * we will know that there were changes in the file and that it needs to be
 * logged.
 */
static inline void btrfs_set_inode_last_sub_trans(struct btrfs_inode *inode)
{
	spin_lock(&inode->lock);
	inode->last_sub_trans = inode->root->log_transid;
	spin_unlock(&inode->lock);
}

/*
 * Should be called while holding the inode's VFS lock in exclusive mode or in a
 * context where no one else can access the inode concurrently (during inode
 * creation or when loading an inode from disk).
 */
static inline void btrfs_set_inode_full_sync(struct btrfs_inode *inode)
{
	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
	/*
	 * The inode may have been part of a reflink operation in the last
	 * transaction that modified it, and then a fsync has reset the
	 * last_reflink_trans to avoid subsequent fsyncs in the same
	 * transaction to do unnecessary work. So update last_reflink_trans
	 * to the last_trans value (we have to be pessimistic and assume a
	 * reflink happened).
	 *
	 * The ->last_trans is protected by the inode's spinlock and we can
	 * have a concurrent ordered extent completion update it. Also set
	 * last_reflink_trans to ->last_trans only if the former is less than
	 * the later, because we can be called in a context where
	 * last_reflink_trans was set to the current transaction generation
	 * while ->last_trans was not yet updated in the current transaction,
	 * and therefore has a lower value.
	 */
	spin_lock(&inode->lock);
	if (inode->last_reflink_trans < inode->last_trans)
		inode->last_reflink_trans = inode->last_trans;
	spin_unlock(&inode->lock);
}

static inline bool btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation)
{
	bool ret = false;

	spin_lock(&inode->lock);
	if (inode->logged_trans == generation &&
	    inode->last_sub_trans <= inode->last_log_commit &&
	    inode->last_sub_trans <= inode->root->last_log_commit)
		ret = true;
	spin_unlock(&inode->lock);
	return ret;
}

/*
 * Check if the inode has flags compatible with compression
 */
static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode)
{
	if (inode->flags & BTRFS_INODE_NODATACOW ||
	    inode->flags & BTRFS_INODE_NODATASUM)
		return false;
	return true;
}

/*
 * btrfs_inode_item stores flags in a u64, btrfs_inode stores them in two
 * separate u32s. These two functions convert between the two representations.
 */
static inline u64 btrfs_inode_combine_flags(u32 flags, u32 ro_flags)
{
	return (flags | ((u64)ro_flags << 32));
}

static inline void btrfs_inode_split_flags(u64 inode_item_flags,
					   u32 *flags, u32 *ro_flags)
{
	*flags = (u32)inode_item_flags;
	*ro_flags = (u32)(inode_item_flags >> 32);
}

/* Array of bytes with variable length, hexadecimal format 0x1234 */
#define CSUM_FMT				"0x%*phN"
#define CSUM_FMT_VALUE(size, bytes)		size, bytes

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

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

int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
			       bool in_reclaim_context);
int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
			      unsigned int extra_bits,
			      struct extent_state **cached_state);

struct btrfs_new_inode_args {
	/* Input */
	struct inode *dir;
	struct dentry *dentry;
	struct inode *inode;
	bool orphan;
	bool subvol;

	/* Output from btrfs_new_inode_prepare(), input to btrfs_create_new_inode(). */
	struct posix_acl *default_acl;
	struct posix_acl *acl;
	struct fscrypt_name fname;
};

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

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

extern const struct dentry_operations btrfs_dentry_operations;

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

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

#endif