summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs/xfs_ialloc_btree.c
blob: 7c471881c9a67482bd6bf88df59bd6f2e63a57a7 (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
553
554
555
556
557
558
559
560
561
562
563
564
565
566
/*
 * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_ialloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
#include "xfs_trans.h"
#include "xfs_rmap.h"


STATIC int
xfs_inobt_get_minrecs(
	struct xfs_btree_cur	*cur,
	int			level)
{
	return cur->bc_mp->m_inobt_mnr[level != 0];
}

STATIC struct xfs_btree_cur *
xfs_inobt_dup_cursor(
	struct xfs_btree_cur	*cur)
{
	return xfs_inobt_init_cursor(cur->bc_mp, cur->bc_tp,
			cur->bc_private.a.agbp, cur->bc_private.a.agno,
			cur->bc_btnum);
}

STATIC void
xfs_inobt_set_root(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*nptr,
	int			inc)	/* level change */
{
	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);

	agi->agi_root = nptr->s;
	be32_add_cpu(&agi->agi_level, inc);
	xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_ROOT | XFS_AGI_LEVEL);
}

STATIC void
xfs_finobt_set_root(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*nptr,
	int			inc)	/* level change */
{
	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);

	agi->agi_free_root = nptr->s;
	be32_add_cpu(&agi->agi_free_level, inc);
	xfs_ialloc_log_agi(cur->bc_tp, agbp,
			   XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL);
}

STATIC int
__xfs_inobt_alloc_block(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*start,
	union xfs_btree_ptr	*new,
	int			*stat,
	enum xfs_ag_resv_type	resv)
{
	xfs_alloc_arg_t		args;		/* block allocation args */
	int			error;		/* error return value */
	xfs_agblock_t		sbno = be32_to_cpu(start->s);

	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);

	memset(&args, 0, sizeof(args));
	args.tp = cur->bc_tp;
	args.mp = cur->bc_mp;
	xfs_rmap_ag_owner(&args.oinfo, XFS_RMAP_OWN_INOBT);
	args.fsbno = XFS_AGB_TO_FSB(args.mp, cur->bc_private.a.agno, sbno);
	args.minlen = 1;
	args.maxlen = 1;
	args.prod = 1;
	args.type = XFS_ALLOCTYPE_NEAR_BNO;
	args.resv = resv;

	error = xfs_alloc_vextent(&args);
	if (error) {
		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
		return error;
	}
	if (args.fsbno == NULLFSBLOCK) {
		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
		*stat = 0;
		return 0;
	}
	ASSERT(args.len == 1);
	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);

	new->s = cpu_to_be32(XFS_FSB_TO_AGBNO(args.mp, args.fsbno));
	*stat = 1;
	return 0;
}

STATIC int
xfs_inobt_alloc_block(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*start,
	union xfs_btree_ptr	*new,
	int			*stat)
{
	return __xfs_inobt_alloc_block(cur, start, new, stat, XFS_AG_RESV_NONE);
}

STATIC int
xfs_finobt_alloc_block(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*start,
	union xfs_btree_ptr	*new,
	int			*stat)
{
	return __xfs_inobt_alloc_block(cur, start, new, stat,
			XFS_AG_RESV_METADATA);
}

STATIC int
xfs_inobt_free_block(
	struct xfs_btree_cur	*cur,
	struct xfs_buf		*bp)
{
	struct xfs_owner_info	oinfo;

	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
	return xfs_free_extent(cur->bc_tp,
			XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1,
			&oinfo, XFS_AG_RESV_NONE);
}

STATIC int
xfs_inobt_get_maxrecs(
	struct xfs_btree_cur	*cur,
	int			level)
{
	return cur->bc_mp->m_inobt_mxr[level != 0];
}

STATIC void
xfs_inobt_init_key_from_rec(
	union xfs_btree_key	*key,
	union xfs_btree_rec	*rec)
{
	key->inobt.ir_startino = rec->inobt.ir_startino;
}

STATIC void
xfs_inobt_init_rec_from_cur(
	struct xfs_btree_cur	*cur,
	union xfs_btree_rec	*rec)
{
	rec->inobt.ir_startino = cpu_to_be32(cur->bc_rec.i.ir_startino);
	if (xfs_sb_version_hassparseinodes(&cur->bc_mp->m_sb)) {
		rec->inobt.ir_u.sp.ir_holemask =
					cpu_to_be16(cur->bc_rec.i.ir_holemask);
		rec->inobt.ir_u.sp.ir_count = cur->bc_rec.i.ir_count;
		rec->inobt.ir_u.sp.ir_freecount = cur->bc_rec.i.ir_freecount;
	} else {
		/* ir_holemask/ir_count not supported on-disk */
		rec->inobt.ir_u.f.ir_freecount =
					cpu_to_be32(cur->bc_rec.i.ir_freecount);
	}
	rec->inobt.ir_free = cpu_to_be64(cur->bc_rec.i.ir_free);
}

/*
 * initial value of ptr for lookup
 */
STATIC void
xfs_inobt_init_ptr_from_cur(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*ptr)
{
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);

	ASSERT(cur->bc_private.a.agno == be32_to_cpu(agi->agi_seqno));

	ptr->s = agi->agi_root;
}

STATIC void
xfs_finobt_init_ptr_from_cur(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*ptr)
{
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);

	ASSERT(cur->bc_private.a.agno == be32_to_cpu(agi->agi_seqno));
	ptr->s = agi->agi_free_root;
}

STATIC __int64_t
xfs_inobt_key_diff(
	struct xfs_btree_cur	*cur,
	union xfs_btree_key	*key)
{
	return (__int64_t)be32_to_cpu(key->inobt.ir_startino) -
			  cur->bc_rec.i.ir_startino;
}

static int
xfs_inobt_verify(
	struct xfs_buf		*bp)
{
	struct xfs_mount	*mp = bp->b_target->bt_mount;
	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
	unsigned int		level;

	/*
	 * During growfs operations, we can't verify the exact owner as the
	 * perag is not fully initialised and hence not attached to the buffer.
	 *
	 * Similarly, during log recovery we will have a perag structure
	 * attached, but the agi information will not yet have been initialised
	 * from the on disk AGI. We don't currently use any of this information,
	 * but beware of the landmine (i.e. need to check pag->pagi_init) if we
	 * ever do.
	 */
	switch (block->bb_magic) {
	case cpu_to_be32(XFS_IBT_CRC_MAGIC):
	case cpu_to_be32(XFS_FIBT_CRC_MAGIC):
		if (!xfs_btree_sblock_v5hdr_verify(bp))
			return false;
		/* fall through */
	case cpu_to_be32(XFS_IBT_MAGIC):
	case cpu_to_be32(XFS_FIBT_MAGIC):
		break;
	default:
		return 0;
	}

	/* level verification */
	level = be16_to_cpu(block->bb_level);
	if (level >= mp->m_in_maxlevels)
		return false;

	return xfs_btree_sblock_verify(bp, mp->m_inobt_mxr[level != 0]);
}

static void
xfs_inobt_read_verify(
	struct xfs_buf	*bp)
{
	if (!xfs_btree_sblock_verify_crc(bp))
		xfs_buf_ioerror(bp, -EFSBADCRC);
	else if (!xfs_inobt_verify(bp))
		xfs_buf_ioerror(bp, -EFSCORRUPTED);

	if (bp->b_error) {
		trace_xfs_btree_corrupt(bp, _RET_IP_);
		xfs_verifier_error(bp);
	}
}

static void
xfs_inobt_write_verify(
	struct xfs_buf	*bp)
{
	if (!xfs_inobt_verify(bp)) {
		trace_xfs_btree_corrupt(bp, _RET_IP_);
		xfs_buf_ioerror(bp, -EFSCORRUPTED);
		xfs_verifier_error(bp);
		return;
	}
	xfs_btree_sblock_calc_crc(bp);

}

const struct xfs_buf_ops xfs_inobt_buf_ops = {
	.name = "xfs_inobt",
	.verify_read = xfs_inobt_read_verify,
	.verify_write = xfs_inobt_write_verify,
};

#if defined(DEBUG) || defined(XFS_WARN)
STATIC int
xfs_inobt_keys_inorder(
	struct xfs_btree_cur	*cur,
	union xfs_btree_key	*k1,
	union xfs_btree_key	*k2)
{
	return be32_to_cpu(k1->inobt.ir_startino) <
		be32_to_cpu(k2->inobt.ir_startino);
}

STATIC int
xfs_inobt_recs_inorder(
	struct xfs_btree_cur	*cur,
	union xfs_btree_rec	*r1,
	union xfs_btree_rec	*r2)
{
	return be32_to_cpu(r1->inobt.ir_startino) + XFS_INODES_PER_CHUNK <=
		be32_to_cpu(r2->inobt.ir_startino);
}
#endif	/* DEBUG */

static const struct xfs_btree_ops xfs_inobt_ops = {
	.rec_len		= sizeof(xfs_inobt_rec_t),
	.key_len		= sizeof(xfs_inobt_key_t),

	.dup_cursor		= xfs_inobt_dup_cursor,
	.set_root		= xfs_inobt_set_root,
	.alloc_block		= xfs_inobt_alloc_block,
	.free_block		= xfs_inobt_free_block,
	.get_minrecs		= xfs_inobt_get_minrecs,
	.get_maxrecs		= xfs_inobt_get_maxrecs,
	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
	.init_ptr_from_cur	= xfs_inobt_init_ptr_from_cur,
	.key_diff		= xfs_inobt_key_diff,
	.buf_ops		= &xfs_inobt_buf_ops,
#if defined(DEBUG) || defined(XFS_WARN)
	.keys_inorder		= xfs_inobt_keys_inorder,
	.recs_inorder		= xfs_inobt_recs_inorder,
#endif
};

static const struct xfs_btree_ops xfs_finobt_ops = {
	.rec_len		= sizeof(xfs_inobt_rec_t),
	.key_len		= sizeof(xfs_inobt_key_t),

	.dup_cursor		= xfs_inobt_dup_cursor,
	.set_root		= xfs_finobt_set_root,
	.alloc_block		= xfs_finobt_alloc_block,
	.free_block		= xfs_inobt_free_block,
	.get_minrecs		= xfs_inobt_get_minrecs,
	.get_maxrecs		= xfs_inobt_get_maxrecs,
	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
	.init_ptr_from_cur	= xfs_finobt_init_ptr_from_cur,
	.key_diff		= xfs_inobt_key_diff,
	.buf_ops		= &xfs_inobt_buf_ops,
#if defined(DEBUG) || defined(XFS_WARN)
	.keys_inorder		= xfs_inobt_keys_inorder,
	.recs_inorder		= xfs_inobt_recs_inorder,
#endif
};

/*
 * Allocate a new inode btree cursor.
 */
struct xfs_btree_cur *				/* new inode btree cursor */
xfs_inobt_init_cursor(
	struct xfs_mount	*mp,		/* file system mount point */
	struct xfs_trans	*tp,		/* transaction pointer */
	struct xfs_buf		*agbp,		/* buffer for agi structure */
	xfs_agnumber_t		agno,		/* allocation group number */
	xfs_btnum_t		btnum)		/* ialloc or free ino btree */
{
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
	struct xfs_btree_cur	*cur;

	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);

	cur->bc_tp = tp;
	cur->bc_mp = mp;
	cur->bc_btnum = btnum;
	if (btnum == XFS_BTNUM_INO) {
		cur->bc_nlevels = be32_to_cpu(agi->agi_level);
		cur->bc_ops = &xfs_inobt_ops;
		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_ibt_2);
	} else {
		cur->bc_nlevels = be32_to_cpu(agi->agi_free_level);
		cur->bc_ops = &xfs_finobt_ops;
		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_fibt_2);
	}

	cur->bc_blocklog = mp->m_sb.sb_blocklog;

	if (xfs_sb_version_hascrc(&mp->m_sb))
		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;

	cur->bc_private.a.agbp = agbp;
	cur->bc_private.a.agno = agno;

	return cur;
}

/*
 * Calculate number of records in an inobt btree block.
 */
int
xfs_inobt_maxrecs(
	struct xfs_mount	*mp,
	int			blocklen,
	int			leaf)
{
	blocklen -= XFS_INOBT_BLOCK_LEN(mp);

	if (leaf)
		return blocklen / sizeof(xfs_inobt_rec_t);
	return blocklen / (sizeof(xfs_inobt_key_t) + sizeof(xfs_inobt_ptr_t));
}

/*
 * Convert the inode record holemask to an inode allocation bitmap. The inode
 * allocation bitmap is inode granularity and specifies whether an inode is
 * physically allocated on disk (not whether the inode is considered allocated
 * or free by the fs).
 *
 * A bit value of 1 means the inode is allocated, a value of 0 means it is free.
 */
uint64_t
xfs_inobt_irec_to_allocmask(
	struct xfs_inobt_rec_incore	*rec)
{
	uint64_t			bitmap = 0;
	uint64_t			inodespbit;
	int				nextbit;
	uint				allocbitmap;

	/*
	 * The holemask has 16-bits for a 64 inode record. Therefore each
	 * holemask bit represents multiple inodes. Create a mask of bits to set
	 * in the allocmask for each holemask bit.
	 */
	inodespbit = (1 << XFS_INODES_PER_HOLEMASK_BIT) - 1;

	/*
	 * Allocated inodes are represented by 0 bits in holemask. Invert the 0
	 * bits to 1 and convert to a uint so we can use xfs_next_bit(). Mask
	 * anything beyond the 16 holemask bits since this casts to a larger
	 * type.
	 */
	allocbitmap = ~rec->ir_holemask & ((1 << XFS_INOBT_HOLEMASK_BITS) - 1);

	/*
	 * allocbitmap is the inverted holemask so every set bit represents
	 * allocated inodes. To expand from 16-bit holemask granularity to
	 * 64-bit (e.g., bit-per-inode), set inodespbit bits in the target
	 * bitmap for every holemask bit.
	 */
	nextbit = xfs_next_bit(&allocbitmap, 1, 0);
	while (nextbit != -1) {
		ASSERT(nextbit < (sizeof(rec->ir_holemask) * NBBY));

		bitmap |= (inodespbit <<
			   (nextbit * XFS_INODES_PER_HOLEMASK_BIT));

		nextbit = xfs_next_bit(&allocbitmap, 1, nextbit + 1);
	}

	return bitmap;
}

#if defined(DEBUG) || defined(XFS_WARN)
/*
 * Verify that an in-core inode record has a valid inode count.
 */
int
xfs_inobt_rec_check_count(
	struct xfs_mount		*mp,
	struct xfs_inobt_rec_incore	*rec)
{
	int				inocount = 0;
	int				nextbit = 0;
	uint64_t			allocbmap;
	int				wordsz;

	wordsz = sizeof(allocbmap) / sizeof(unsigned int);
	allocbmap = xfs_inobt_irec_to_allocmask(rec);

	nextbit = xfs_next_bit((uint *) &allocbmap, wordsz, nextbit);
	while (nextbit != -1) {
		inocount++;
		nextbit = xfs_next_bit((uint *) &allocbmap, wordsz,
				       nextbit + 1);
	}

	if (inocount != rec->ir_count)
		return -EFSCORRUPTED;

	return 0;
}
#endif	/* DEBUG */

static xfs_extlen_t
xfs_inobt_max_size(
	struct xfs_mount	*mp)
{
	/* Bail out if we're uninitialized, which can happen in mkfs. */
	if (mp->m_inobt_mxr[0] == 0)
		return 0;

	return xfs_btree_calc_size(mp, mp->m_inobt_mnr,
		(uint64_t)mp->m_sb.sb_agblocks * mp->m_sb.sb_inopblock /
				XFS_INODES_PER_CHUNK);
}

static int
xfs_inobt_count_blocks(
	struct xfs_mount	*mp,
	xfs_agnumber_t		agno,
	xfs_btnum_t		btnum,
	xfs_extlen_t		*tree_blocks)
{
	struct xfs_buf		*agbp;
	struct xfs_btree_cur	*cur;
	int			error;

	error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
	if (error)
		return error;

	cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
	error = xfs_btree_count_blocks(cur, tree_blocks);
	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
	xfs_buf_relse(agbp);

	return error;
}

/*
 * Figure out how many blocks to reserve and how many are used by this btree.
 */
int
xfs_finobt_calc_reserves(
	struct xfs_mount	*mp,
	xfs_agnumber_t		agno,
	xfs_extlen_t		*ask,
	xfs_extlen_t		*used)
{
	xfs_extlen_t		tree_len = 0;
	int			error;

	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
		return 0;

	error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len);
	if (error)
		return error;

	*ask += xfs_inobt_max_size(mp);
	*used += tree_len;
	return 0;
}