summaryrefslogtreecommitdiffstats
path: root/fs/xfs/scrub/refcount.c
blob: 324a5f159145ce4c8c3e659bac1076125f0af21a (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
/*
 * Copyright (C) 2017 Oracle.  All Rights Reserved.
 *
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 *
 * 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; either version 2
 * of the License, or (at your option) any later version.
 *
 * 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_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_alloc.h"
#include "xfs_rmap.h"
#include "xfs_refcount.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 reference count btrees.
 */
int
xfs_scrub_setup_ag_refcountbt(
	struct xfs_scrub_context	*sc,
	struct xfs_inode		*ip)
{
	return xfs_scrub_setup_ag_btree(sc, ip, false);
}

/* Reference count btree scrubber. */

/*
 * Confirming Reference Counts via Reverse Mappings
 *
 * We want to count the reverse mappings overlapping a refcount record
 * (bno, len, refcount), allowing for the possibility that some of the
 * overlap may come from smaller adjoining reverse mappings, while some
 * comes from single extents which overlap the range entirely.  The
 * outer loop is as follows:
 *
 * 1. For all reverse mappings overlapping the refcount extent,
 *    a. If a given rmap completely overlaps, mark it as seen.
 *    b. Otherwise, record the fragment (in agbno order) for later
 *       processing.
 *
 * Once we've seen all the rmaps, we know that for all blocks in the
 * refcount record we want to find $refcount owners and we've already
 * visited $seen extents that overlap all the blocks.  Therefore, we
 * need to find ($refcount - $seen) owners for every block in the
 * extent; call that quantity $target_nr.  Proceed as follows:
 *
 * 2. Pull the first $target_nr fragments from the list; all of them
 *    should start at or before the start of the extent.
 *    Call this subset of fragments the working set.
 * 3. Until there are no more unprocessed fragments,
 *    a. Find the shortest fragments in the set and remove them.
 *    b. Note the block number of the end of these fragments.
 *    c. Pull the same number of fragments from the list.  All of these
 *       fragments should start at the block number recorded in the
 *       previous step.
 *    d. Put those fragments in the set.
 * 4. Check that there are $target_nr fragments remaining in the list,
 *    and that they all end at or beyond the end of the refcount extent.
 *
 * If the refcount is correct, all the check conditions in the algorithm
 * should always hold true.  If not, the refcount is incorrect.
 */
struct xfs_scrub_refcnt_frag {
	struct list_head		list;
	struct xfs_rmap_irec		rm;
};

struct xfs_scrub_refcnt_check {
	struct xfs_scrub_context	*sc;
	struct list_head		fragments;

	/* refcount extent we're examining */
	xfs_agblock_t			bno;
	xfs_extlen_t			len;
	xfs_nlink_t			refcount;

	/* number of owners seen */
	xfs_nlink_t			seen;
};

/*
 * Decide if the given rmap is large enough that we can redeem it
 * towards refcount verification now, or if it's a fragment, in
 * which case we'll hang onto it in the hopes that we'll later
 * discover that we've collected exactly the correct number of
 * fragments as the refcountbt says we should have.
 */
STATIC int
xfs_scrub_refcountbt_rmap_check(
	struct xfs_btree_cur		*cur,
	struct xfs_rmap_irec		*rec,
	void				*priv)
{
	struct xfs_scrub_refcnt_check	*refchk = priv;
	struct xfs_scrub_refcnt_frag	*frag;
	xfs_agblock_t			rm_last;
	xfs_agblock_t			rc_last;
	int				error = 0;

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

	rm_last = rec->rm_startblock + rec->rm_blockcount - 1;
	rc_last = refchk->bno + refchk->len - 1;

	/* Confirm that a single-owner refc extent is a CoW stage. */
	if (refchk->refcount == 1 && rec->rm_owner != XFS_RMAP_OWN_COW) {
		xfs_scrub_btree_xref_set_corrupt(refchk->sc, cur, 0);
		return 0;
	}

	if (rec->rm_startblock <= refchk->bno && rm_last >= rc_last) {
		/*
		 * The rmap overlaps the refcount record, so we can confirm
		 * one refcount owner seen.
		 */
		refchk->seen++;
	} else {
		/*
		 * This rmap covers only part of the refcount record, so
		 * save the fragment for later processing.  If the rmapbt
		 * is healthy each rmap_irec we see will be in agbno order
		 * so we don't need insertion sort here.
		 */
		frag = kmem_alloc(sizeof(struct xfs_scrub_refcnt_frag),
				KM_MAYFAIL);
		if (!frag)
			return -ENOMEM;
		memcpy(&frag->rm, rec, sizeof(frag->rm));
		list_add_tail(&frag->list, &refchk->fragments);
	}

	return 0;
}

/*
 * Given a bunch of rmap fragments, iterate through them, keeping
 * a running tally of the refcount.  If this ever deviates from
 * what we expect (which is the refcountbt's refcount minus the
 * number of extents that totally covered the refcountbt extent),
 * we have a refcountbt error.
 */
STATIC void
xfs_scrub_refcountbt_process_rmap_fragments(
	struct xfs_scrub_refcnt_check	*refchk)
{
	struct list_head		worklist;
	struct xfs_scrub_refcnt_frag	*frag;
	struct xfs_scrub_refcnt_frag	*n;
	xfs_agblock_t			bno;
	xfs_agblock_t			rbno;
	xfs_agblock_t			next_rbno;
	xfs_nlink_t			nr;
	xfs_nlink_t			target_nr;

	target_nr = refchk->refcount - refchk->seen;
	if (target_nr == 0)
		return;

	/*
	 * There are (refchk->rc.rc_refcount - refchk->nr refcount)
	 * references we haven't found yet.  Pull that many off the
	 * fragment list and figure out where the smallest rmap ends
	 * (and therefore the next rmap should start).  All the rmaps
	 * we pull off should start at or before the beginning of the
	 * refcount record's range.
	 */
	INIT_LIST_HEAD(&worklist);
	rbno = NULLAGBLOCK;
	nr = 1;

	/* Make sure the fragments actually /are/ in agbno order. */
	bno = 0;
	list_for_each_entry(frag, &refchk->fragments, list) {
		if (frag->rm.rm_startblock < bno)
			goto done;
		bno = frag->rm.rm_startblock;
	}

	/*
	 * Find all the rmaps that start at or before the refc extent,
	 * and put them on the worklist.
	 */
	list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
		if (frag->rm.rm_startblock > refchk->bno)
			goto done;
		bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
		if (bno < rbno)
			rbno = bno;
		list_move_tail(&frag->list, &worklist);
		if (nr == target_nr)
			break;
		nr++;
	}

	/*
	 * We should have found exactly $target_nr rmap fragments starting
	 * at or before the refcount extent.
	 */
	if (nr != target_nr)
		goto done;

	while (!list_empty(&refchk->fragments)) {
		/* Discard any fragments ending at rbno from the worklist. */
		nr = 0;
		next_rbno = NULLAGBLOCK;
		list_for_each_entry_safe(frag, n, &worklist, list) {
			bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
			if (bno != rbno) {
				if (bno < next_rbno)
					next_rbno = bno;
				continue;
			}
			list_del(&frag->list);
			kmem_free(frag);
			nr++;
		}

		/* Try to add nr rmaps starting at rbno to the worklist. */
		list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
			bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
			if (frag->rm.rm_startblock != rbno)
				goto done;
			list_move_tail(&frag->list, &worklist);
			if (next_rbno > bno)
				next_rbno = bno;
			nr--;
			if (nr == 0)
				break;
		}

		/*
		 * If we get here and nr > 0, this means that we added fewer
		 * items to the worklist than we discarded because the fragment
		 * list ran out of items.  Therefore, we cannot maintain the
		 * required refcount.  Something is wrong, so we're done.
		 */
		if (nr)
			goto done;

		rbno = next_rbno;
	}

	/*
	 * Make sure the last extent we processed ends at or beyond
	 * the end of the refcount extent.
	 */
	if (rbno < refchk->bno + refchk->len)
		goto done;

	/* Actually record us having seen the remaining refcount. */
	refchk->seen = refchk->refcount;
done:
	/* Delete fragments and work list. */
	list_for_each_entry_safe(frag, n, &worklist, list) {
		list_del(&frag->list);
		kmem_free(frag);
	}
	list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
		list_del(&frag->list);
		kmem_free(frag);
	}
}

/* Use the rmap entries covering this extent to verify the refcount. */
STATIC void
xfs_scrub_refcountbt_xref_rmap(
	struct xfs_scrub_context	*sc,
	xfs_agblock_t			bno,
	xfs_extlen_t			len,
	xfs_nlink_t			refcount)
{
	struct xfs_scrub_refcnt_check	refchk = {
		.sc = sc,
		.bno = bno,
		.len = len,
		.refcount = refcount,
		.seen = 0,
	};
	struct xfs_rmap_irec		low;
	struct xfs_rmap_irec		high;
	struct xfs_scrub_refcnt_frag	*frag;
	struct xfs_scrub_refcnt_frag	*n;
	int				error;

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

	/* Cross-reference with the rmapbt to confirm the refcount. */
	memset(&low, 0, sizeof(low));
	low.rm_startblock = bno;
	memset(&high, 0xFF, sizeof(high));
	high.rm_startblock = bno + len - 1;

	INIT_LIST_HEAD(&refchk.fragments);
	error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high,
			&xfs_scrub_refcountbt_rmap_check, &refchk);
	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
		goto out_free;

	xfs_scrub_refcountbt_process_rmap_fragments(&refchk);
	if (refcount != refchk.seen)
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);

out_free:
	list_for_each_entry_safe(frag, n, &refchk.fragments, list) {
		list_del(&frag->list);
		kmem_free(frag);
	}
}

/* Cross-reference with the other btrees. */
STATIC void
xfs_scrub_refcountbt_xref(
	struct xfs_scrub_context	*sc,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len,
	xfs_nlink_t			refcount)
{
	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
		return;

	xfs_scrub_xref_is_used_space(sc, agbno, len);
	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
	xfs_scrub_refcountbt_xref_rmap(sc, agbno, len, refcount);
}

/* Scrub a refcountbt record. */
STATIC int
xfs_scrub_refcountbt_rec(
	struct xfs_scrub_btree		*bs,
	union xfs_btree_rec		*rec)
{
	struct xfs_mount		*mp = bs->cur->bc_mp;
	xfs_agblock_t			*cow_blocks = bs->private;
	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
	xfs_agblock_t			bno;
	xfs_extlen_t			len;
	xfs_nlink_t			refcount;
	bool				has_cowflag;
	int				error = 0;

	bno = be32_to_cpu(rec->refc.rc_startblock);
	len = be32_to_cpu(rec->refc.rc_blockcount);
	refcount = be32_to_cpu(rec->refc.rc_refcount);

	/* Only CoW records can have refcount == 1. */
	has_cowflag = (bno & XFS_REFC_COW_START);
	if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag))
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
	if (has_cowflag)
		(*cow_blocks) += len;

	/* Check the extent. */
	bno &= ~XFS_REFC_COW_START;
	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);

	if (refcount == 0)
		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);

	xfs_scrub_refcountbt_xref(bs->sc, bno, len, refcount);

	return error;
}

/* Make sure we have as many refc blocks as the rmap says. */
STATIC void
xfs_scrub_refcount_xref_rmap(
	struct xfs_scrub_context	*sc,
	struct xfs_owner_info		*oinfo,
	xfs_filblks_t			cow_blocks)
{
	xfs_extlen_t			refcbt_blocks = 0;
	xfs_filblks_t			blocks;
	int				error;

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

	/* Check that we saw as many refcbt blocks as the rmap knows about. */
	error = xfs_btree_count_blocks(sc->sa.refc_cur, &refcbt_blocks);
	if (!xfs_scrub_btree_process_error(sc, sc->sa.refc_cur, 0, &error))
		return;
	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 != refcbt_blocks)
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);

	/* Check that we saw as many cow blocks as the rmap knows about. */
	xfs_rmap_ag_owner(oinfo, XFS_RMAP_OWN_COW);
	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 != cow_blocks)
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
}

/* Scrub the refcount btree for some AG. */
int
xfs_scrub_refcountbt(
	struct xfs_scrub_context	*sc)
{
	struct xfs_owner_info		oinfo;
	xfs_agblock_t			cow_blocks = 0;
	int				error;

	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_REFC);
	error = xfs_scrub_btree(sc, sc->sa.refc_cur, xfs_scrub_refcountbt_rec,
			&oinfo, &cow_blocks);
	if (error)
		return error;

	xfs_scrub_refcount_xref_rmap(sc, &oinfo, cow_blocks);

	return 0;
}

/* xref check that a cow staging extent is marked in the refcountbt. */
void
xfs_scrub_xref_is_cow_staging(
	struct xfs_scrub_context	*sc,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len)
{
	struct xfs_refcount_irec	rc;
	bool				has_cowflag;
	int				has_refcount;
	int				error;

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

	/* Find the CoW staging extent. */
	error = xfs_refcount_lookup_le(sc->sa.refc_cur,
			agbno + XFS_REFC_COW_START, &has_refcount);
	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
		return;
	if (!has_refcount) {
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
		return;
	}

	error = xfs_refcount_get_rec(sc->sa.refc_cur, &rc, &has_refcount);
	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
		return;
	if (!has_refcount) {
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
		return;
	}

	/* CoW flag must be set, refcount must be 1. */
	has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START);
	if (!has_cowflag || rc.rc_refcount != 1)
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);

	/* Must be at least as long as what was passed in */
	if (rc.rc_blockcount < len)
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
}

/*
 * xref check that the extent is not shared.  Only file data blocks
 * can have multiple owners.
 */
void
xfs_scrub_xref_is_not_shared(
	struct xfs_scrub_context	*sc,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len)
{
	bool				shared;
	int				error;

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

	error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared);
	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
		return;
	if (shared)
		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
}