summaryrefslogtreecommitdiffstats
path: root/fs/xfs/scrub/common.c
blob: ac95fe911d96aacfd545aaa0ff594f3c783e5009 (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
/*
 * 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_inode.h"
#include "xfs_icache.h"
#include "xfs_itable.h"
#include "xfs_alloc.h"
#include "xfs_alloc_btree.h"
#include "xfs_bmap.h"
#include "xfs_bmap_btree.h"
#include "xfs_ialloc.h"
#include "xfs_ialloc_btree.h"
#include "xfs_refcount.h"
#include "xfs_refcount_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.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/trace.h"
#include "scrub/btree.h"

/* Common code for the metadata scrubbers. */

/*
 * Handling operational errors.
 *
 * The *_process_error() family of functions are used to process error return
 * codes from functions called as part of a scrub operation.
 *
 * If there's no error, we return true to tell the caller that it's ok
 * to move on to the next check in its list.
 *
 * For non-verifier errors (e.g. ENOMEM) we return false to tell the
 * caller that something bad happened, and we preserve *error so that
 * the caller can return the *error up the stack to userspace.
 *
 * Verifier errors (EFSBADCRC/EFSCORRUPTED) are recorded by setting
 * OFLAG_CORRUPT in sm_flags and the *error is cleared.  In other words,
 * we track verifier errors (and failed scrub checks) via OFLAG_CORRUPT,
 * not via return codes.  We return false to tell the caller that
 * something bad happened.  Since the error has been cleared, the caller
 * will (presumably) return that zero and scrubbing will move on to
 * whatever's next.
 *
 * ftrace can be used to record the precise metadata location and the
 * approximate code location of the failed operation.
 */

/* Check for operational errors. */
bool
xfs_scrub_process_error(
	struct xfs_scrub_context	*sc,
	xfs_agnumber_t			agno,
	xfs_agblock_t			bno,
	int				*error)
{
	switch (*error) {
	case 0:
		return true;
	case -EDEADLOCK:
		/* Used to restart an op with deadlock avoidance. */
		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
		break;
	case -EFSBADCRC:
	case -EFSCORRUPTED:
		/* Note the badness but don't abort. */
		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
		*error = 0;
		/* fall through */
	default:
		trace_xfs_scrub_op_error(sc, agno, bno, *error,
				__return_address);
		break;
	}
	return false;
}

/* Check for operational errors for a file offset. */
bool
xfs_scrub_fblock_process_error(
	struct xfs_scrub_context	*sc,
	int				whichfork,
	xfs_fileoff_t			offset,
	int				*error)
{
	switch (*error) {
	case 0:
		return true;
	case -EDEADLOCK:
		/* Used to restart an op with deadlock avoidance. */
		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
		break;
	case -EFSBADCRC:
	case -EFSCORRUPTED:
		/* Note the badness but don't abort. */
		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
		*error = 0;
		/* fall through */
	default:
		trace_xfs_scrub_file_op_error(sc, whichfork, offset, *error,
				__return_address);
		break;
	}
	return false;
}

/*
 * Handling scrub corruption/optimization/warning checks.
 *
 * The *_set_{corrupt,preen,warning}() family of functions are used to
 * record the presence of metadata that is incorrect (corrupt), could be
 * optimized somehow (preen), or should be flagged for administrative
 * review but is not incorrect (warn).
 *
 * ftrace can be used to record the precise metadata location and
 * approximate code location of the failed check.
 */

/* Record a block which could be optimized. */
void
xfs_scrub_block_set_preen(
	struct xfs_scrub_context	*sc,
	struct xfs_buf			*bp)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
	trace_xfs_scrub_block_preen(sc, bp->b_bn, __return_address);
}

/*
 * Record an inode which could be optimized.  The trace data will
 * include the block given by bp if bp is given; otherwise it will use
 * the block location of the inode record itself.
 */
void
xfs_scrub_ino_set_preen(
	struct xfs_scrub_context	*sc,
	xfs_ino_t			ino,
	struct xfs_buf			*bp)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
	trace_xfs_scrub_ino_preen(sc, ino, bp ? bp->b_bn : 0,
			__return_address);
}

/* Record a corrupt block. */
void
xfs_scrub_block_set_corrupt(
	struct xfs_scrub_context	*sc,
	struct xfs_buf			*bp)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
}

/*
 * Record a corrupt inode.  The trace data will include the block given
 * by bp if bp is given; otherwise it will use the block location of the
 * inode record itself.
 */
void
xfs_scrub_ino_set_corrupt(
	struct xfs_scrub_context	*sc,
	xfs_ino_t			ino,
	struct xfs_buf			*bp)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
	trace_xfs_scrub_ino_error(sc, ino, bp ? bp->b_bn : 0, __return_address);
}

/* Record corruption in a block indexed by a file fork. */
void
xfs_scrub_fblock_set_corrupt(
	struct xfs_scrub_context	*sc,
	int				whichfork,
	xfs_fileoff_t			offset)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
}

/*
 * Warn about inodes that need administrative review but is not
 * incorrect.
 */
void
xfs_scrub_ino_set_warning(
	struct xfs_scrub_context	*sc,
	xfs_ino_t			ino,
	struct xfs_buf			*bp)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
	trace_xfs_scrub_ino_warning(sc, ino, bp ? bp->b_bn : 0,
			__return_address);
}

/* Warn about a block indexed by a file fork that needs review. */
void
xfs_scrub_fblock_set_warning(
	struct xfs_scrub_context	*sc,
	int				whichfork,
	xfs_fileoff_t			offset)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
	trace_xfs_scrub_fblock_warning(sc, whichfork, offset, __return_address);
}

/* Signal an incomplete scrub. */
void
xfs_scrub_set_incomplete(
	struct xfs_scrub_context	*sc)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_INCOMPLETE;
	trace_xfs_scrub_incomplete(sc, __return_address);
}

/*
 * AG scrubbing
 *
 * These helpers facilitate locking an allocation group's header
 * buffers, setting up cursors for all btrees that are present, and
 * cleaning everything up once we're through.
 */

/* Decide if we want to return an AG header read failure. */
static inline bool
want_ag_read_header_failure(
	struct xfs_scrub_context	*sc,
	unsigned int			type)
{
	/* Return all AG header read failures when scanning btrees. */
	if (sc->sm->sm_type != XFS_SCRUB_TYPE_AGF &&
	    sc->sm->sm_type != XFS_SCRUB_TYPE_AGFL &&
	    sc->sm->sm_type != XFS_SCRUB_TYPE_AGI)
		return true;
	/*
	 * If we're scanning a given type of AG header, we only want to
	 * see read failures from that specific header.  We'd like the
	 * other headers to cross-check them, but this isn't required.
	 */
	if (sc->sm->sm_type == type)
		return true;
	return false;
}

/*
 * Grab all the headers for an AG.
 *
 * The headers should be released by xfs_scrub_ag_free, but as a fail
 * safe we attach all the buffers we grab to the scrub transaction so
 * they'll all be freed when we cancel it.
 */
int
xfs_scrub_ag_read_headers(
	struct xfs_scrub_context	*sc,
	xfs_agnumber_t			agno,
	struct xfs_buf			**agi,
	struct xfs_buf			**agf,
	struct xfs_buf			**agfl)
{
	struct xfs_mount		*mp = sc->mp;
	int				error;

	error = xfs_ialloc_read_agi(mp, sc->tp, agno, agi);
	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
		goto out;

	error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, agf);
	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGF))
		goto out;

	error = xfs_alloc_read_agfl(mp, sc->tp, agno, agfl);
	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGFL))
		goto out;

out:
	return error;
}

/* Release all the AG btree cursors. */
void
xfs_scrub_ag_btcur_free(
	struct xfs_scrub_ag		*sa)
{
	if (sa->refc_cur)
		xfs_btree_del_cursor(sa->refc_cur, XFS_BTREE_ERROR);
	if (sa->rmap_cur)
		xfs_btree_del_cursor(sa->rmap_cur, XFS_BTREE_ERROR);
	if (sa->fino_cur)
		xfs_btree_del_cursor(sa->fino_cur, XFS_BTREE_ERROR);
	if (sa->ino_cur)
		xfs_btree_del_cursor(sa->ino_cur, XFS_BTREE_ERROR);
	if (sa->cnt_cur)
		xfs_btree_del_cursor(sa->cnt_cur, XFS_BTREE_ERROR);
	if (sa->bno_cur)
		xfs_btree_del_cursor(sa->bno_cur, XFS_BTREE_ERROR);

	sa->refc_cur = NULL;
	sa->rmap_cur = NULL;
	sa->fino_cur = NULL;
	sa->ino_cur = NULL;
	sa->bno_cur = NULL;
	sa->cnt_cur = NULL;
}

/* Initialize all the btree cursors for an AG. */
int
xfs_scrub_ag_btcur_init(
	struct xfs_scrub_context	*sc,
	struct xfs_scrub_ag		*sa)
{
	struct xfs_mount		*mp = sc->mp;
	xfs_agnumber_t			agno = sa->agno;

	if (sa->agf_bp) {
		/* Set up a bnobt cursor for cross-referencing. */
		sa->bno_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp,
				agno, XFS_BTNUM_BNO);
		if (!sa->bno_cur)
			goto err;

		/* Set up a cntbt cursor for cross-referencing. */
		sa->cnt_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp,
				agno, XFS_BTNUM_CNT);
		if (!sa->cnt_cur)
			goto err;
	}

	/* Set up a inobt cursor for cross-referencing. */
	if (sa->agi_bp) {
		sa->ino_cur = xfs_inobt_init_cursor(mp, sc->tp, sa->agi_bp,
					agno, XFS_BTNUM_INO);
		if (!sa->ino_cur)
			goto err;
	}

	/* Set up a finobt cursor for cross-referencing. */
	if (sa->agi_bp && xfs_sb_version_hasfinobt(&mp->m_sb)) {
		sa->fino_cur = xfs_inobt_init_cursor(mp, sc->tp, sa->agi_bp,
				agno, XFS_BTNUM_FINO);
		if (!sa->fino_cur)
			goto err;
	}

	/* Set up a rmapbt cursor for cross-referencing. */
	if (sa->agf_bp && xfs_sb_version_hasrmapbt(&mp->m_sb)) {
		sa->rmap_cur = xfs_rmapbt_init_cursor(mp, sc->tp, sa->agf_bp,
				agno);
		if (!sa->rmap_cur)
			goto err;
	}

	/* Set up a refcountbt cursor for cross-referencing. */
	if (sa->agf_bp && xfs_sb_version_hasreflink(&mp->m_sb)) {
		sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
				sa->agf_bp, agno, NULL);
		if (!sa->refc_cur)
			goto err;
	}

	return 0;
err:
	return -ENOMEM;
}

/* Release the AG header context and btree cursors. */
void
xfs_scrub_ag_free(
	struct xfs_scrub_context	*sc,
	struct xfs_scrub_ag		*sa)
{
	xfs_scrub_ag_btcur_free(sa);
	if (sa->agfl_bp) {
		xfs_trans_brelse(sc->tp, sa->agfl_bp);
		sa->agfl_bp = NULL;
	}
	if (sa->agf_bp) {
		xfs_trans_brelse(sc->tp, sa->agf_bp);
		sa->agf_bp = NULL;
	}
	if (sa->agi_bp) {
		xfs_trans_brelse(sc->tp, sa->agi_bp);
		sa->agi_bp = NULL;
	}
	sa->agno = NULLAGNUMBER;
}

/*
 * For scrub, grab the AGI and the AGF headers, in that order.  Locking
 * order requires us to get the AGI before the AGF.  We use the
 * transaction to avoid deadlocking on crosslinked metadata buffers;
 * either the caller passes one in (bmap scrub) or we have to create a
 * transaction ourselves.
 */
int
xfs_scrub_ag_init(
	struct xfs_scrub_context	*sc,
	xfs_agnumber_t			agno,
	struct xfs_scrub_ag		*sa)
{
	int				error;

	sa->agno = agno;
	error = xfs_scrub_ag_read_headers(sc, agno, &sa->agi_bp,
			&sa->agf_bp, &sa->agfl_bp);
	if (error)
		return error;

	return xfs_scrub_ag_btcur_init(sc, sa);
}

/* Per-scrubber setup functions */

/* Set us up with a transaction and an empty context. */
int
xfs_scrub_setup_fs(
	struct xfs_scrub_context	*sc,
	struct xfs_inode		*ip)
{
	return xfs_scrub_trans_alloc(sc->sm, sc->mp, &sc->tp);
}

/* Set us up with AG headers and btree cursors. */
int
xfs_scrub_setup_ag_btree(
	struct xfs_scrub_context	*sc,
	struct xfs_inode		*ip,
	bool				force_log)
{
	struct xfs_mount		*mp = sc->mp;
	int				error;

	/*
	 * If the caller asks us to checkpont the log, do so.  This
	 * expensive operation should be performed infrequently and only
	 * as a last resort.  Any caller that sets force_log should
	 * document why they need to do so.
	 */
	if (force_log) {
		error = xfs_scrub_checkpoint_log(mp);
		if (error)
			return error;
	}

	error = xfs_scrub_setup_ag_header(sc, ip);
	if (error)
		return error;

	return xfs_scrub_ag_init(sc, sc->sm->sm_agno, &sc->sa);
}

/* Push everything out of the log onto disk. */
int
xfs_scrub_checkpoint_log(
	struct xfs_mount	*mp)
{
	int			error;

	error = _xfs_log_force(mp, XFS_LOG_SYNC, NULL);
	if (error)
		return error;
	xfs_ail_push_all_sync(mp->m_ail);
	return 0;
}

/*
 * Given an inode and the scrub control structure, grab either the
 * inode referenced in the control structure or the inode passed in.
 * The inode is not locked.
 */
int
xfs_scrub_get_inode(
	struct xfs_scrub_context	*sc,
	struct xfs_inode		*ip_in)
{
	struct xfs_mount		*mp = sc->mp;
	struct xfs_inode		*ip = NULL;
	int				error;

	/*
	 * If userspace passed us an AG number or a generation number
	 * without an inode number, they haven't got a clue so bail out
	 * immediately.
	 */
	if (sc->sm->sm_agno || (sc->sm->sm_gen && !sc->sm->sm_ino))
		return -EINVAL;

	/* We want to scan the inode we already had opened. */
	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) {
		sc->ip = ip_in;
		return 0;
	}

	/* Look up the inode, see if the generation number matches. */
	if (xfs_internal_inum(mp, sc->sm->sm_ino))
		return -ENOENT;
	error = xfs_iget(mp, NULL, sc->sm->sm_ino,
			XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE, 0, &ip);
	if (error == -ENOENT || error == -EINVAL) {
		/* inode doesn't exist... */
		return -ENOENT;
	} else if (error) {
		trace_xfs_scrub_op_error(sc,
				XFS_INO_TO_AGNO(mp, sc->sm->sm_ino),
				XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino),
				error, __return_address);
		return error;
	}
	if (VFS_I(ip)->i_generation != sc->sm->sm_gen) {
		iput(VFS_I(ip));
		return -ENOENT;
	}

	sc->ip = ip;
	return 0;
}

/* Set us up to scrub a file's contents. */
int
xfs_scrub_setup_inode_contents(
	struct xfs_scrub_context	*sc,
	struct xfs_inode		*ip,
	unsigned int			resblks)
{
	struct xfs_mount		*mp = sc->mp;
	int				error;

	error = xfs_scrub_get_inode(sc, ip);
	if (error)
		return error;

	/* Got the inode, lock it and we're ready to go. */
	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
	xfs_ilock(sc->ip, sc->ilock_flags);
	error = xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
	if (error)
		goto out;
	sc->ilock_flags |= XFS_ILOCK_EXCL;
	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);

out:
	/* scrub teardown will unlock and release the inode for us */
	return error;
}