summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs/xfs_bmap_btree.c
blob: d89d06bea6e342d829674353b129c6a0231f8a47 (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
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
/*
 * Copyright (c) 2000-2003,2005 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_defer.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_alloc.h"
#include "xfs_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
#include "xfs_rmap.h"

/*
 * Convert on-disk form of btree root to in-memory form.
 */
void
xfs_bmdr_to_bmbt(
	struct xfs_inode	*ip,
	xfs_bmdr_block_t	*dblock,
	int			dblocklen,
	struct xfs_btree_block	*rblock,
	int			rblocklen)
{
	struct xfs_mount	*mp = ip->i_mount;
	int			dmxr;
	xfs_bmbt_key_t		*fkp;
	__be64			*fpp;
	xfs_bmbt_key_t		*tkp;
	__be64			*tpp;

	xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
				 XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
				 XFS_BTREE_LONG_PTRS);
	rblock->bb_level = dblock->bb_level;
	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
	rblock->bb_numrecs = dblock->bb_numrecs;
	dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
	fkp = XFS_BMDR_KEY_ADDR(dblock, 1);
	tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
	fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
	tpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
	dmxr = be16_to_cpu(dblock->bb_numrecs);
	memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
	memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
}

void
xfs_bmbt_disk_get_all(
	struct xfs_bmbt_rec	*rec,
	struct xfs_bmbt_irec	*irec)
{
	uint64_t		l0 = get_unaligned_be64(&rec->l0);
	uint64_t		l1 = get_unaligned_be64(&rec->l1);

	irec->br_startoff = (l0 & xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9;
	irec->br_startblock = ((l0 & xfs_mask64lo(9)) << 43) | (l1 >> 21);
	irec->br_blockcount = l1 & xfs_mask64lo(21);
	if (l0 >> (64 - BMBT_EXNTFLAG_BITLEN))
		irec->br_state = XFS_EXT_UNWRITTEN;
	else
		irec->br_state = XFS_EXT_NORM;
}

/*
 * Extract the blockcount field from an on disk bmap extent record.
 */
xfs_filblks_t
xfs_bmbt_disk_get_blockcount(
	xfs_bmbt_rec_t	*r)
{
	return (xfs_filblks_t)(be64_to_cpu(r->l1) & xfs_mask64lo(21));
}

/*
 * Extract the startoff field from a disk format bmap extent record.
 */
xfs_fileoff_t
xfs_bmbt_disk_get_startoff(
	xfs_bmbt_rec_t	*r)
{
	return ((xfs_fileoff_t)be64_to_cpu(r->l0) &
		 xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9;
}

/*
 * Set all the fields in a bmap extent record from the uncompressed form.
 */
void
xfs_bmbt_disk_set_all(
	struct xfs_bmbt_rec	*r,
	struct xfs_bmbt_irec	*s)
{
	int			extent_flag = (s->br_state != XFS_EXT_NORM);

	ASSERT(s->br_state == XFS_EXT_NORM || s->br_state == XFS_EXT_UNWRITTEN);
	ASSERT(!(s->br_startoff & xfs_mask64hi(64-BMBT_STARTOFF_BITLEN)));
	ASSERT(!(s->br_blockcount & xfs_mask64hi(64-BMBT_BLOCKCOUNT_BITLEN)));
	ASSERT(!(s->br_startblock & xfs_mask64hi(64-BMBT_STARTBLOCK_BITLEN)));

	put_unaligned_be64(
		((xfs_bmbt_rec_base_t)extent_flag << 63) |
		 ((xfs_bmbt_rec_base_t)s->br_startoff << 9) |
		 ((xfs_bmbt_rec_base_t)s->br_startblock >> 43), &r->l0);
	put_unaligned_be64(
		((xfs_bmbt_rec_base_t)s->br_startblock << 21) |
		 ((xfs_bmbt_rec_base_t)s->br_blockcount &
		  (xfs_bmbt_rec_base_t)xfs_mask64lo(21)), &r->l1);
}

/*
 * Convert in-memory form of btree root to on-disk form.
 */
void
xfs_bmbt_to_bmdr(
	struct xfs_mount	*mp,
	struct xfs_btree_block	*rblock,
	int			rblocklen,
	xfs_bmdr_block_t	*dblock,
	int			dblocklen)
{
	int			dmxr;
	xfs_bmbt_key_t		*fkp;
	__be64			*fpp;
	xfs_bmbt_key_t		*tkp;
	__be64			*tpp;

	if (xfs_sb_version_hascrc(&mp->m_sb)) {
		ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_CRC_MAGIC));
		ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid,
		       &mp->m_sb.sb_meta_uuid));
		ASSERT(rblock->bb_u.l.bb_blkno ==
		       cpu_to_be64(XFS_BUF_DADDR_NULL));
	} else
		ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_MAGIC));
	ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK));
	ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK));
	ASSERT(rblock->bb_level != 0);
	dblock->bb_level = rblock->bb_level;
	dblock->bb_numrecs = rblock->bb_numrecs;
	dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
	fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
	tkp = XFS_BMDR_KEY_ADDR(dblock, 1);
	fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
	tpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
	dmxr = be16_to_cpu(dblock->bb_numrecs);
	memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
	memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
}

STATIC struct xfs_btree_cur *
xfs_bmbt_dup_cursor(
	struct xfs_btree_cur	*cur)
{
	struct xfs_btree_cur	*new;

	new = xfs_bmbt_init_cursor(cur->bc_mp, cur->bc_tp,
			cur->bc_private.b.ip, cur->bc_private.b.whichfork);

	/*
	 * Copy the firstblock, dfops, and flags values,
	 * since init cursor doesn't get them.
	 */
	new->bc_private.b.firstblock = cur->bc_private.b.firstblock;
	new->bc_private.b.dfops = cur->bc_private.b.dfops;
	new->bc_private.b.flags = cur->bc_private.b.flags;

	return new;
}

STATIC void
xfs_bmbt_update_cursor(
	struct xfs_btree_cur	*src,
	struct xfs_btree_cur	*dst)
{
	ASSERT((dst->bc_private.b.firstblock != NULLFSBLOCK) ||
	       (dst->bc_private.b.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
	ASSERT(dst->bc_private.b.dfops == src->bc_private.b.dfops);

	dst->bc_private.b.allocated += src->bc_private.b.allocated;
	dst->bc_private.b.firstblock = src->bc_private.b.firstblock;

	src->bc_private.b.allocated = 0;
}

STATIC int
xfs_bmbt_alloc_block(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*start,
	union xfs_btree_ptr	*new,
	int			*stat)
{
	xfs_alloc_arg_t		args;		/* block allocation args */
	int			error;		/* error return value */

	memset(&args, 0, sizeof(args));
	args.tp = cur->bc_tp;
	args.mp = cur->bc_mp;
	args.fsbno = cur->bc_private.b.firstblock;
	args.firstblock = args.fsbno;
	xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_private.b.ip->i_ino,
			cur->bc_private.b.whichfork);

	if (args.fsbno == NULLFSBLOCK) {
		args.fsbno = be64_to_cpu(start->l);
		args.type = XFS_ALLOCTYPE_START_BNO;
		/*
		 * Make sure there is sufficient room left in the AG to
		 * complete a full tree split for an extent insert.  If
		 * we are converting the middle part of an extent then
		 * we may need space for two tree splits.
		 *
		 * We are relying on the caller to make the correct block
		 * reservation for this operation to succeed.  If the
		 * reservation amount is insufficient then we may fail a
		 * block allocation here and corrupt the filesystem.
		 */
		args.minleft = args.tp->t_blk_res;
	} else if (cur->bc_private.b.dfops->dop_low) {
		args.type = XFS_ALLOCTYPE_START_BNO;
	} else {
		args.type = XFS_ALLOCTYPE_NEAR_BNO;
	}

	args.minlen = args.maxlen = args.prod = 1;
	args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL;
	if (!args.wasdel && args.tp->t_blk_res == 0) {
		error = -ENOSPC;
		goto error0;
	}
	error = xfs_alloc_vextent(&args);
	if (error)
		goto error0;

	if (args.fsbno == NULLFSBLOCK && args.minleft) {
		/*
		 * Could not find an AG with enough free space to satisfy
		 * a full btree split.  Try again and if
		 * successful activate the lowspace algorithm.
		 */
		args.fsbno = 0;
		args.type = XFS_ALLOCTYPE_FIRST_AG;
		error = xfs_alloc_vextent(&args);
		if (error)
			goto error0;
		cur->bc_private.b.dfops->dop_low = true;
	}
	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
		*stat = 0;
		return 0;
	}

	ASSERT(args.len == 1);
	cur->bc_private.b.firstblock = args.fsbno;
	cur->bc_private.b.allocated++;
	cur->bc_private.b.ip->i_d.di_nblocks++;
	xfs_trans_log_inode(args.tp, cur->bc_private.b.ip, XFS_ILOG_CORE);
	xfs_trans_mod_dquot_byino(args.tp, cur->bc_private.b.ip,
			XFS_TRANS_DQ_BCOUNT, 1L);

	new->l = cpu_to_be64(args.fsbno);

	*stat = 1;
	return 0;

 error0:
	return error;
}

STATIC int
xfs_bmbt_free_block(
	struct xfs_btree_cur	*cur,
	struct xfs_buf		*bp)
{
	struct xfs_mount	*mp = cur->bc_mp;
	struct xfs_inode	*ip = cur->bc_private.b.ip;
	struct xfs_trans	*tp = cur->bc_tp;
	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));
	struct xfs_owner_info	oinfo;

	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_private.b.whichfork);
	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, fsbno, 1, &oinfo);
	ip->i_d.di_nblocks--;

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
	return 0;
}

STATIC int
xfs_bmbt_get_minrecs(
	struct xfs_btree_cur	*cur,
	int			level)
{
	if (level == cur->bc_nlevels - 1) {
		struct xfs_ifork	*ifp;

		ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
				    cur->bc_private.b.whichfork);

		return xfs_bmbt_maxrecs(cur->bc_mp,
					ifp->if_broot_bytes, level == 0) / 2;
	}

	return cur->bc_mp->m_bmap_dmnr[level != 0];
}

int
xfs_bmbt_get_maxrecs(
	struct xfs_btree_cur	*cur,
	int			level)
{
	if (level == cur->bc_nlevels - 1) {
		struct xfs_ifork	*ifp;

		ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
				    cur->bc_private.b.whichfork);

		return xfs_bmbt_maxrecs(cur->bc_mp,
					ifp->if_broot_bytes, level == 0);
	}

	return cur->bc_mp->m_bmap_dmxr[level != 0];

}

/*
 * Get the maximum records we could store in the on-disk format.
 *
 * For non-root nodes this is equivalent to xfs_bmbt_get_maxrecs, but
 * for the root node this checks the available space in the dinode fork
 * so that we can resize the in-memory buffer to match it.  After a
 * resize to the maximum size this function returns the same value
 * as xfs_bmbt_get_maxrecs for the root node, too.
 */
STATIC int
xfs_bmbt_get_dmaxrecs(
	struct xfs_btree_cur	*cur,
	int			level)
{
	if (level != cur->bc_nlevels - 1)
		return cur->bc_mp->m_bmap_dmxr[level != 0];
	return xfs_bmdr_maxrecs(cur->bc_private.b.forksize, level == 0);
}

STATIC void
xfs_bmbt_init_key_from_rec(
	union xfs_btree_key	*key,
	union xfs_btree_rec	*rec)
{
	key->bmbt.br_startoff =
		cpu_to_be64(xfs_bmbt_disk_get_startoff(&rec->bmbt));
}

STATIC void
xfs_bmbt_init_high_key_from_rec(
	union xfs_btree_key	*key,
	union xfs_btree_rec	*rec)
{
	key->bmbt.br_startoff = cpu_to_be64(
			xfs_bmbt_disk_get_startoff(&rec->bmbt) +
			xfs_bmbt_disk_get_blockcount(&rec->bmbt) - 1);
}

STATIC void
xfs_bmbt_init_rec_from_cur(
	struct xfs_btree_cur	*cur,
	union xfs_btree_rec	*rec)
{
	xfs_bmbt_disk_set_all(&rec->bmbt, &cur->bc_rec.b);
}

STATIC void
xfs_bmbt_init_ptr_from_cur(
	struct xfs_btree_cur	*cur,
	union xfs_btree_ptr	*ptr)
{
	ptr->l = 0;
}

STATIC int64_t
xfs_bmbt_key_diff(
	struct xfs_btree_cur	*cur,
	union xfs_btree_key	*key)
{
	return (int64_t)be64_to_cpu(key->bmbt.br_startoff) -
				      cur->bc_rec.b.br_startoff;
}

STATIC int64_t
xfs_bmbt_diff_two_keys(
	struct xfs_btree_cur	*cur,
	union xfs_btree_key	*k1,
	union xfs_btree_key	*k2)
{
	return (int64_t)be64_to_cpu(k1->bmbt.br_startoff) -
			  be64_to_cpu(k2->bmbt.br_startoff);
}

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

	switch (block->bb_magic) {
	case cpu_to_be32(XFS_BMAP_CRC_MAGIC):
		/*
		 * XXX: need a better way of verifying the owner here. Right now
		 * just make sure there has been one set.
		 */
		fa = xfs_btree_lblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN);
		if (fa)
			return fa;
		/* fall through */
	case cpu_to_be32(XFS_BMAP_MAGIC):
		break;
	default:
		return __this_address;
	}

	/*
	 * numrecs and level verification.
	 *
	 * We don't know what fork we belong to, so just verify that the level
	 * is less than the maximum of the two. Later checks will be more
	 * precise.
	 */
	level = be16_to_cpu(block->bb_level);
	if (level > max(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1]))
		return __this_address;

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

static void
xfs_bmbt_read_verify(
	struct xfs_buf	*bp)
{
	xfs_failaddr_t	fa;

	if (!xfs_btree_lblock_verify_crc(bp))
		xfs_verifier_error(bp, -EFSBADCRC, __this_address);
	else {
		fa = xfs_bmbt_verify(bp);
		if (fa)
			xfs_verifier_error(bp, -EFSCORRUPTED, fa);
	}

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

static void
xfs_bmbt_write_verify(
	struct xfs_buf	*bp)
{
	xfs_failaddr_t	fa;

	fa = xfs_bmbt_verify(bp);
	if (fa) {
		trace_xfs_btree_corrupt(bp, _RET_IP_);
		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
		return;
	}
	xfs_btree_lblock_calc_crc(bp);
}

const struct xfs_buf_ops xfs_bmbt_buf_ops = {
	.name = "xfs_bmbt",
	.verify_read = xfs_bmbt_read_verify,
	.verify_write = xfs_bmbt_write_verify,
	.verify_struct = xfs_bmbt_verify,
};


STATIC int
xfs_bmbt_keys_inorder(
	struct xfs_btree_cur	*cur,
	union xfs_btree_key	*k1,
	union xfs_btree_key	*k2)
{
	return be64_to_cpu(k1->bmbt.br_startoff) <
		be64_to_cpu(k2->bmbt.br_startoff);
}

STATIC int
xfs_bmbt_recs_inorder(
	struct xfs_btree_cur	*cur,
	union xfs_btree_rec	*r1,
	union xfs_btree_rec	*r2)
{
	return xfs_bmbt_disk_get_startoff(&r1->bmbt) +
		xfs_bmbt_disk_get_blockcount(&r1->bmbt) <=
		xfs_bmbt_disk_get_startoff(&r2->bmbt);
}

static const struct xfs_btree_ops xfs_bmbt_ops = {
	.rec_len		= sizeof(xfs_bmbt_rec_t),
	.key_len		= sizeof(xfs_bmbt_key_t),

	.dup_cursor		= xfs_bmbt_dup_cursor,
	.update_cursor		= xfs_bmbt_update_cursor,
	.alloc_block		= xfs_bmbt_alloc_block,
	.free_block		= xfs_bmbt_free_block,
	.get_maxrecs		= xfs_bmbt_get_maxrecs,
	.get_minrecs		= xfs_bmbt_get_minrecs,
	.get_dmaxrecs		= xfs_bmbt_get_dmaxrecs,
	.init_key_from_rec	= xfs_bmbt_init_key_from_rec,
	.init_high_key_from_rec	= xfs_bmbt_init_high_key_from_rec,
	.init_rec_from_cur	= xfs_bmbt_init_rec_from_cur,
	.init_ptr_from_cur	= xfs_bmbt_init_ptr_from_cur,
	.key_diff		= xfs_bmbt_key_diff,
	.diff_two_keys		= xfs_bmbt_diff_two_keys,
	.buf_ops		= &xfs_bmbt_buf_ops,
	.keys_inorder		= xfs_bmbt_keys_inorder,
	.recs_inorder		= xfs_bmbt_recs_inorder,
};

/*
 * Allocate a new bmap btree cursor.
 */
struct xfs_btree_cur *				/* new bmap btree cursor */
xfs_bmbt_init_cursor(
	struct xfs_mount	*mp,		/* file system mount point */
	struct xfs_trans	*tp,		/* transaction pointer */
	struct xfs_inode	*ip,		/* inode owning the btree */
	int			whichfork)	/* data or attr fork */
{
	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
	struct xfs_btree_cur	*cur;
	ASSERT(whichfork != XFS_COW_FORK);

	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);

	cur->bc_tp = tp;
	cur->bc_mp = mp;
	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
	cur->bc_btnum = XFS_BTNUM_BMAP;
	cur->bc_blocklog = mp->m_sb.sb_blocklog;
	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);

	cur->bc_ops = &xfs_bmbt_ops;
	cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
	if (xfs_sb_version_hascrc(&mp->m_sb))
		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;

	cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
	cur->bc_private.b.ip = ip;
	cur->bc_private.b.firstblock = NULLFSBLOCK;
	cur->bc_private.b.dfops = NULL;
	cur->bc_private.b.allocated = 0;
	cur->bc_private.b.flags = 0;
	cur->bc_private.b.whichfork = whichfork;

	return cur;
}

/*
 * Calculate number of records in a bmap btree block.
 */
int
xfs_bmbt_maxrecs(
	struct xfs_mount	*mp,
	int			blocklen,
	int			leaf)
{
	blocklen -= XFS_BMBT_BLOCK_LEN(mp);

	if (leaf)
		return blocklen / sizeof(xfs_bmbt_rec_t);
	return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
}

/*
 * Calculate number of records in a bmap btree inode root.
 */
int
xfs_bmdr_maxrecs(
	int			blocklen,
	int			leaf)
{
	blocklen -= sizeof(xfs_bmdr_block_t);

	if (leaf)
		return blocklen / sizeof(xfs_bmdr_rec_t);
	return blocklen / (sizeof(xfs_bmdr_key_t) + sizeof(xfs_bmdr_ptr_t));
}

/*
 * Change the owner of a btree format fork fo the inode passed in. Change it to
 * the owner of that is passed in so that we can change owners before or after
 * we switch forks between inodes. The operation that the caller is doing will
 * determine whether is needs to change owner before or after the switch.
 *
 * For demand paged transactional modification, the fork switch should be done
 * after reading in all the blocks, modifying them and pinning them in the
 * transaction. For modification when the buffers are already pinned in memory,
 * the fork switch can be done before changing the owner as we won't need to
 * validate the owner until the btree buffers are unpinned and writes can occur
 * again.
 *
 * For recovery based ownership change, there is no transactional context and
 * so a buffer list must be supplied so that we can record the buffers that we
 * modified for the caller to issue IO on.
 */
int
xfs_bmbt_change_owner(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	int			whichfork,
	xfs_ino_t		new_owner,
	struct list_head	*buffer_list)
{
	struct xfs_btree_cur	*cur;
	int			error;

	ASSERT(tp || buffer_list);
	ASSERT(!(tp && buffer_list));
	if (whichfork == XFS_DATA_FORK)
		ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_BTREE);
	else
		ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_BTREE);

	cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
	if (!cur)
		return -ENOMEM;
	cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER;

	error = xfs_btree_change_owner(cur, new_owner, buffer_list);
	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
	return error;
}