summaryrefslogtreecommitdiff
path: root/fs/btrfs/btrfs_inode.h
blob: ab2a4a52e0bb687e990874b4153f08c0cd4c6a1e (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
/* 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"

/*
 * 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,
};

/* 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 extent_io_tree io_failure_tree;

	/*
	 * 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;

	union {
		/*
		 * 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;
		/*
		 * The offset of the last dir item key that was logged.
		 * This is used only for directories.
		 */
		u64 last_dir_item_offset;
	};

	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
	 */
	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 u32 btrfs_inode_sectorsize(const struct btrfs_inode *inode)
{
	return inode->root->fs_info->sectorsize;
}

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;
}

static inline void btrfs_insert_inode_hash(struct inode *inode)
{
	unsigned long h = btrfs_inode_hash(inode->i_ino, BTRFS_I(inode)->root);

	__insert_inode_hash(inode, h);
}

static inline u64 btrfs_ino(const struct btrfs_inode *inode)
{
	u64 ino = inode->location.objectid;

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

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)
{
	struct btrfs_root *root = inode->root;

	if (root == root->fs_info->tree_root &&
	    btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID)
		return true;
	if (inode->location.objectid == BTRFS_FREE_INO_OBJECTID)
		return true;
	return false;
}

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);
}

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;
}

struct btrfs_dio_private {
	struct inode *inode;

	/*
	 * Since DIO can use anonymous page, we cannot use page_offset() to
	 * grab the file offset, thus need a dedicated member for file offset.
	 */
	u64 file_offset;
	u64 disk_bytenr;
	/* Used for bio::bi_size */
	u32 bytes;

	/*
	 * References to this structure. There is one reference per in-flight
	 * bio plus one while we're still setting up.
	 */
	refcount_t refs;

	/* dio_bio came from fs/direct-io.c */
	struct bio *dio_bio;

	/* Array of checksums */
	u8 csums[];
};

/*
 * 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

static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode,
		u64 logical_start, u8 *csum, u8 *csum_expected, int mirror_num)
{
	struct btrfs_root *root = inode->root;
	const u32 csum_size = root->fs_info->csum_size;

	/* Output minus objectid, which is more meaningful */
	if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID)
		btrfs_warn_rl(root->fs_info,
"csum failed root %lld ino %lld off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
			root->root_key.objectid, btrfs_ino(inode),
			logical_start,
			CSUM_FMT_VALUE(csum_size, csum),
			CSUM_FMT_VALUE(csum_size, csum_expected),
			mirror_num);
	else
		btrfs_warn_rl(root->fs_info,
"csum failed root %llu ino %llu off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
			root->root_key.objectid, btrfs_ino(inode),
			logical_start,
			CSUM_FMT_VALUE(csum_size, csum),
			CSUM_FMT_VALUE(csum_size, csum_expected),
			mirror_num);
}

#endif