summaryrefslogtreecommitdiffstats
path: root/fs/xfs/scrub/ialloc.c
blob: 13d43d108574e3715acbd40ab49b31e06178a93a (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
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2017 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_btree.h"
#include "xfs_bit.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_ialloc_btree.h"
#include "xfs_icache.h"
#include "xfs_rmap.h"
#include "xfs_log.h"
#include "xfs_trans_priv.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/trace.h"

/*
 * Set us up to scrub inode btrees.
 * If we detect a discrepancy between the inobt and the inode,
 * try again after forcing logged inode cores out to disk.
 */
int
xfs_scrub_setup_ag_iallocbt(
	struct xfs_scrub_context	*sc,
	struct xfs_inode		*ip)
{
	return xfs_scrub_setup_ag_btree(sc, ip, sc->try_harder);
}

/* Inode btree scrubber. */

/*
 * If we're checking the finobt, cross-reference with the inobt.
 * Otherwise we're checking the inobt; if there is an finobt, make sure
 * we have a record or not depending on freecount.
 */
static inline void
xfs_scrub_iallocbt_chunk_xref_other(
	struct xfs_scrub_context	*sc,
	struct xfs_inobt_rec_incore	*irec,
	xfs_agino_t			agino)
{
	struct xfs_btree_cur		**pcur;
	bool				has_irec;
	int				error;

	if (sc->sm->sm_type == XFS_SCRUB_TYPE_FINOBT)
		pcur = &sc->sa.ino_cur;
	else
		pcur = &sc->sa.fino_cur;
	if (!(*pcur))
		return;
	error = xfs_ialloc_has_inode_record(*pcur, agino, agino, &has_irec);
	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
		return;
	if (((irec->ir_freecount > 0 && !has_irec) ||
	     (irec->ir_freecount == 0 && has_irec)))
		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
}

/* Cross-reference with the other btrees. */
STATIC void
xfs_scrub_iallocbt_chunk_xref(
	struct xfs_scrub_context	*sc,
	struct xfs_inobt_rec_incore	*irec,
	xfs_agino_t			agino,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len)
{
	struct xfs_owner_info		oinfo;

	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
		return;

	xfs_scrub_xref_is_used_space(sc, agbno, len);
	xfs_scrub_iallocbt_chunk_xref_other(sc, irec, agino);
	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
	xfs_scrub_xref_is_owned_by(sc, agbno, len, &oinfo);
	xfs_scrub_xref_is_not_shared(sc, agbno, len);
}

/* Is this chunk worth checking? */
STATIC bool
xfs_scrub_iallocbt_chunk(
	struct xfs_scrub_btree		*bs,
	struct xfs_inobt_rec_incore	*irec,
	xfs_agino_t			agino,
	xfs_extlen_t			len)
{
	struct xfs_mount		*mp = bs->cur->bc_mp;
	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
	xfs_agblock_t			bno;

	bno = XFS_AGINO_TO_AGBNO(mp, agino);
	if (bno + len <= bno ||
	    !xfs_verify_agbno(mp, agno, bno) ||
	    !xfs_verify_agbno(mp, agno, bno + len - 1))
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);

	xfs_scrub_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);

	return true;
}

/* Count the number of free inodes. */
static unsigned int
xfs_scrub_iallocbt_freecount(
	xfs_inofree_t			freemask)
{
	BUILD_BUG_ON(sizeof(freemask) != sizeof(__u64));
	return hweight64(freemask);
}

/* Check a particular inode with ir_free. */
STATIC int
xfs_scrub_iallocbt_check_cluster_freemask(
	struct xfs_scrub_btree		*bs,
	xfs_ino_t			fsino,
	xfs_agino_t			chunkino,
	xfs_agino_t			clusterino,
	struct xfs_inobt_rec_incore	*irec,
	struct xfs_buf			*bp)
{
	struct xfs_dinode		*dip;
	struct xfs_mount		*mp = bs->cur->bc_mp;
	bool				inode_is_free = false;
	bool				freemask_ok;
	bool				inuse;
	int				error = 0;

	if (xfs_scrub_should_terminate(bs->sc, &error))
		return error;

	dip = xfs_buf_offset(bp, clusterino * mp->m_sb.sb_inodesize);
	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
	    (dip->di_version >= 3 &&
	     be64_to_cpu(dip->di_ino) != fsino + clusterino)) {
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
		goto out;
	}

	if (irec->ir_free & XFS_INOBT_MASK(chunkino + clusterino))
		inode_is_free = true;
	error = xfs_icache_inode_is_allocated(mp, bs->cur->bc_tp,
			fsino + clusterino, &inuse);
	if (error == -ENODATA) {
		/* Not cached, just read the disk buffer */
		freemask_ok = inode_is_free ^ !!(dip->di_mode);
		if (!bs->sc->try_harder && !freemask_ok)
			return -EDEADLOCK;
	} else if (error < 0) {
		/*
		 * Inode is only half assembled, or there was an IO error,
		 * or the verifier failed, so don't bother trying to check.
		 * The inode scrubber can deal with this.
		 */
		goto out;
	} else {
		/* Inode is all there. */
		freemask_ok = inode_is_free ^ inuse;
	}
	if (!freemask_ok)
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
out:
	return 0;
}

/* Make sure the free mask is consistent with what the inodes think. */
STATIC int
xfs_scrub_iallocbt_check_freemask(
	struct xfs_scrub_btree		*bs,
	struct xfs_inobt_rec_incore	*irec)
{
	struct xfs_owner_info		oinfo;
	struct xfs_imap			imap;
	struct xfs_mount		*mp = bs->cur->bc_mp;
	struct xfs_dinode		*dip;
	struct xfs_buf			*bp;
	xfs_ino_t			fsino;
	xfs_agino_t			nr_inodes;
	xfs_agino_t			agino;
	xfs_agino_t			chunkino;
	xfs_agino_t			clusterino;
	xfs_agblock_t			agbno;
	int				blks_per_cluster;
	uint16_t			holemask;
	uint16_t			ir_holemask;
	int				error = 0;

	/* Make sure the freemask matches the inode records. */
	blks_per_cluster = xfs_icluster_size_fsb(mp);
	nr_inodes = XFS_OFFBNO_TO_AGINO(mp, blks_per_cluster, 0);
	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);

	for (agino = irec->ir_startino;
	     agino < irec->ir_startino + XFS_INODES_PER_CHUNK;
	     agino += blks_per_cluster * mp->m_sb.sb_inopblock) {
		fsino = XFS_AGINO_TO_INO(mp, bs->cur->bc_private.a.agno, agino);
		chunkino = agino - irec->ir_startino;
		agbno = XFS_AGINO_TO_AGBNO(mp, agino);

		/* Compute the holemask mask for this cluster. */
		for (clusterino = 0, holemask = 0; clusterino < nr_inodes;
		     clusterino += XFS_INODES_PER_HOLEMASK_BIT)
			holemask |= XFS_INOBT_MASK((chunkino + clusterino) /
					XFS_INODES_PER_HOLEMASK_BIT);

		/* The whole cluster must be a hole or not a hole. */
		ir_holemask = (irec->ir_holemask & holemask);
		if (ir_holemask != holemask && ir_holemask != 0) {
			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
			continue;
		}

		/* If any part of this is a hole, skip it. */
		if (ir_holemask) {
			xfs_scrub_xref_is_not_owned_by(bs->sc, agbno,
					blks_per_cluster, &oinfo);
			continue;
		}

		xfs_scrub_xref_is_owned_by(bs->sc, agbno, blks_per_cluster,
				&oinfo);

		/* Grab the inode cluster buffer. */
		imap.im_blkno = XFS_AGB_TO_DADDR(mp, bs->cur->bc_private.a.agno,
				agbno);
		imap.im_len = XFS_FSB_TO_BB(mp, blks_per_cluster);
		imap.im_boffset = 0;

		error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap,
				&dip, &bp, 0, 0);
		if (!xfs_scrub_btree_xref_process_error(bs->sc, bs->cur, 0,
				&error))
			continue;

		/* Which inodes are free? */
		for (clusterino = 0; clusterino < nr_inodes; clusterino++) {
			error = xfs_scrub_iallocbt_check_cluster_freemask(bs,
					fsino, chunkino, clusterino, irec, bp);
			if (error) {
				xfs_trans_brelse(bs->cur->bc_tp, bp);
				return error;
			}
		}

		xfs_trans_brelse(bs->cur->bc_tp, bp);
	}

	return error;
}

/* Scrub an inobt/finobt record. */
STATIC int
xfs_scrub_iallocbt_rec(
	struct xfs_scrub_btree		*bs,
	union xfs_btree_rec		*rec)
{
	struct xfs_mount		*mp = bs->cur->bc_mp;
	xfs_filblks_t			*inode_blocks = bs->private;
	struct xfs_inobt_rec_incore	irec;
	uint64_t			holes;
	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
	xfs_agino_t			agino;
	xfs_agblock_t			agbno;
	xfs_extlen_t			len;
	int				holecount;
	int				i;
	int				error = 0;
	unsigned int			real_freecount;
	uint16_t			holemask;

	xfs_inobt_btrec_to_irec(mp, rec, &irec);

	if (irec.ir_count > XFS_INODES_PER_CHUNK ||
	    irec.ir_freecount > XFS_INODES_PER_CHUNK)
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);

	real_freecount = irec.ir_freecount +
			(XFS_INODES_PER_CHUNK - irec.ir_count);
	if (real_freecount != xfs_scrub_iallocbt_freecount(irec.ir_free))
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);

	agino = irec.ir_startino;
	/* Record has to be properly aligned within the AG. */
	if (!xfs_verify_agino(mp, agno, agino) ||
	    !xfs_verify_agino(mp, agno, agino + XFS_INODES_PER_CHUNK - 1)) {
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
		goto out;
	}

	/* Make sure this record is aligned to cluster and inoalignmnt size. */
	agbno = XFS_AGINO_TO_AGBNO(mp, irec.ir_startino);
	if ((agbno & (xfs_ialloc_cluster_alignment(mp) - 1)) ||
	    (agbno & (xfs_icluster_size_fsb(mp) - 1)))
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);

	*inode_blocks += XFS_B_TO_FSB(mp,
			irec.ir_count * mp->m_sb.sb_inodesize);

	/* Handle non-sparse inodes */
	if (!xfs_inobt_issparse(irec.ir_holemask)) {
		len = XFS_B_TO_FSB(mp,
				XFS_INODES_PER_CHUNK * mp->m_sb.sb_inodesize);
		if (irec.ir_count != XFS_INODES_PER_CHUNK)
			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);

		if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
			goto out;
		goto check_freemask;
	}

	/* Check each chunk of a sparse inode cluster. */
	holemask = irec.ir_holemask;
	holecount = 0;
	len = XFS_B_TO_FSB(mp,
			XFS_INODES_PER_HOLEMASK_BIT * mp->m_sb.sb_inodesize);
	holes = ~xfs_inobt_irec_to_allocmask(&irec);
	if ((holes & irec.ir_free) != holes ||
	    irec.ir_freecount > irec.ir_count)
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);

	for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; i++) {
		if (holemask & 1)
			holecount += XFS_INODES_PER_HOLEMASK_BIT;
		else if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
			break;
		holemask >>= 1;
		agino += XFS_INODES_PER_HOLEMASK_BIT;
	}

	if (holecount > XFS_INODES_PER_CHUNK ||
	    holecount + irec.ir_count != XFS_INODES_PER_CHUNK)
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);

check_freemask:
	error = xfs_scrub_iallocbt_check_freemask(bs, &irec);
	if (error)
		goto out;

out:
	return error;
}

/*
 * Make sure the inode btrees are as large as the rmap thinks they are.
 * Don't bother if we're missing btree cursors, as we're already corrupt.
 */
STATIC void
xfs_scrub_iallocbt_xref_rmap_btreeblks(
	struct xfs_scrub_context	*sc,
	int				which)
{
	struct xfs_owner_info		oinfo;
	xfs_filblks_t			blocks;
	xfs_extlen_t			inobt_blocks = 0;
	xfs_extlen_t			finobt_blocks = 0;
	int				error;

	if (!sc->sa.ino_cur || !sc->sa.rmap_cur ||
	    (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur) ||
	    xfs_scrub_skip_xref(sc->sm))
		return;

	/* Check that we saw as many inobt blocks as the rmap says. */
	error = xfs_btree_count_blocks(sc->sa.ino_cur, &inobt_blocks);
	if (!xfs_scrub_process_error(sc, 0, 0, &error))
		return;

	if (sc->sa.fino_cur) {
		error = xfs_btree_count_blocks(sc->sa.fino_cur, &finobt_blocks);
		if (!xfs_scrub_process_error(sc, 0, 0, &error))
			return;
	}

	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
			&blocks);
	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
		return;
	if (blocks != inobt_blocks + finobt_blocks)
		xfs_scrub_btree_set_corrupt(sc, sc->sa.ino_cur, 0);
}

/*
 * Make sure that the inobt records point to the same number of blocks as
 * the rmap says are owned by inodes.
 */
STATIC void
xfs_scrub_iallocbt_xref_rmap_inodes(
	struct xfs_scrub_context	*sc,
	int				which,
	xfs_filblks_t			inode_blocks)
{
	struct xfs_owner_info		oinfo;
	xfs_filblks_t			blocks;
	int				error;

	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
		return;

	/* Check that we saw as many inode blocks as the rmap knows about. */
	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
			&blocks);
	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
		return;
	if (blocks != inode_blocks)
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
}

/* Scrub the inode btrees for some AG. */
STATIC int
xfs_scrub_iallocbt(
	struct xfs_scrub_context	*sc,
	xfs_btnum_t			which)
{
	struct xfs_btree_cur		*cur;
	struct xfs_owner_info		oinfo;
	xfs_filblks_t			inode_blocks = 0;
	int				error;

	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
	cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
	error = xfs_scrub_btree(sc, cur, xfs_scrub_iallocbt_rec, &oinfo,
			&inode_blocks);
	if (error)
		return error;

	xfs_scrub_iallocbt_xref_rmap_btreeblks(sc, which);

	/*
	 * If we're scrubbing the inode btree, inode_blocks is the number of
	 * blocks pointed to by all the inode chunk records.  Therefore, we
	 * should compare to the number of inode chunk blocks that the rmap
	 * knows about.  We can't do this for the finobt since it only points
	 * to inode chunks with free inodes.
	 */
	if (which == XFS_BTNUM_INO)
		xfs_scrub_iallocbt_xref_rmap_inodes(sc, which, inode_blocks);

	return error;
}

int
xfs_scrub_inobt(
	struct xfs_scrub_context	*sc)
{
	return xfs_scrub_iallocbt(sc, XFS_BTNUM_INO);
}

int
xfs_scrub_finobt(
	struct xfs_scrub_context	*sc)
{
	return xfs_scrub_iallocbt(sc, XFS_BTNUM_FINO);
}

/* See if an inode btree has (or doesn't have) an inode chunk record. */
static inline void
xfs_scrub_xref_inode_check(
	struct xfs_scrub_context	*sc,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len,
	struct xfs_btree_cur		**icur,
	bool				should_have_inodes)
{
	bool				has_inodes;
	int				error;

	if (!(*icur) || xfs_scrub_skip_xref(sc->sm))
		return;

	error = xfs_ialloc_has_inodes_at_extent(*icur, agbno, len, &has_inodes);
	if (!xfs_scrub_should_check_xref(sc, &error, icur))
		return;
	if (has_inodes != should_have_inodes)
		xfs_scrub_btree_xref_set_corrupt(sc, *icur, 0);
}

/* xref check that the extent is not covered by inodes */
void
xfs_scrub_xref_is_not_inode_chunk(
	struct xfs_scrub_context	*sc,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len)
{
	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false);
	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false);
}

/* xref check that the extent is covered by inodes */
void
xfs_scrub_xref_is_inode_chunk(
	struct xfs_scrub_context	*sc,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len)
{
	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true);
}