summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_health.c
blob: b39f959146bc1dca7bb2c70bf6404cd04af08409 (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
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2019 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_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trace.h"
#include "xfs_health.h"
#include "xfs_ag.h"
#include "xfs_btree.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_quota_defs.h"

/*
 * Warn about metadata corruption that we detected but haven't fixed, and
 * make sure we're not sitting on anything that would get in the way of
 * recovery.
 */
void
xfs_health_unmount(
	struct xfs_mount	*mp)
{
	struct xfs_perag	*pag;
	xfs_agnumber_t		agno;
	unsigned int		sick = 0;
	unsigned int		checked = 0;
	bool			warn = false;

	if (xfs_is_shutdown(mp))
		return;

	/* Measure AG corruption levels. */
	for_each_perag(mp, agno, pag) {
		xfs_ag_measure_sickness(pag, &sick, &checked);
		if (sick) {
			trace_xfs_ag_unfixed_corruption(mp, agno, sick);
			warn = true;
		}
	}

	/* Measure realtime volume corruption levels. */
	xfs_rt_measure_sickness(mp, &sick, &checked);
	if (sick) {
		trace_xfs_rt_unfixed_corruption(mp, sick);
		warn = true;
	}

	/*
	 * Measure fs corruption and keep the sample around for the warning.
	 * See the note below for why we exempt FS_COUNTERS.
	 */
	xfs_fs_measure_sickness(mp, &sick, &checked);
	if (sick & ~XFS_SICK_FS_COUNTERS) {
		trace_xfs_fs_unfixed_corruption(mp, sick);
		warn = true;
	}

	if (warn) {
		xfs_warn(mp,
"Uncorrected metadata errors detected; please run xfs_repair.");

		/*
		 * We discovered uncorrected metadata problems at some point
		 * during this filesystem mount and have advised the
		 * administrator to run repair once the unmount completes.
		 *
		 * However, we must be careful -- when FSCOUNTERS are flagged
		 * unhealthy, the unmount procedure omits writing the clean
		 * unmount record to the log so that the next mount will run
		 * recovery and recompute the summary counters.  In other
		 * words, we leave a dirty log to get the counters fixed.
		 *
		 * Unfortunately, xfs_repair cannot recover dirty logs, so if
		 * there were filesystem problems, FSCOUNTERS was flagged, and
		 * the administrator takes our advice to run xfs_repair,
		 * they'll have to zap the log before repairing structures.
		 * We don't really want to encourage this, so we mark the
		 * FSCOUNTERS healthy so that a subsequent repair run won't see
		 * a dirty log.
		 */
		if (sick & XFS_SICK_FS_COUNTERS)
			xfs_fs_mark_healthy(mp, XFS_SICK_FS_COUNTERS);
	}
}

/* Mark unhealthy per-fs metadata. */
void
xfs_fs_mark_sick(
	struct xfs_mount	*mp,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_FS_ALL));
	trace_xfs_fs_mark_sick(mp, mask);

	spin_lock(&mp->m_sb_lock);
	mp->m_fs_sick |= mask;
	spin_unlock(&mp->m_sb_lock);
}

/* Mark per-fs metadata as having been checked and found unhealthy by fsck. */
void
xfs_fs_mark_corrupt(
	struct xfs_mount	*mp,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_FS_ALL));
	trace_xfs_fs_mark_corrupt(mp, mask);

	spin_lock(&mp->m_sb_lock);
	mp->m_fs_sick |= mask;
	mp->m_fs_checked |= mask;
	spin_unlock(&mp->m_sb_lock);
}

/* Mark a per-fs metadata healed. */
void
xfs_fs_mark_healthy(
	struct xfs_mount	*mp,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_FS_ALL));
	trace_xfs_fs_mark_healthy(mp, mask);

	spin_lock(&mp->m_sb_lock);
	mp->m_fs_sick &= ~mask;
	if (!(mp->m_fs_sick & XFS_SICK_FS_PRIMARY))
		mp->m_fs_sick &= ~XFS_SICK_FS_SECONDARY;
	mp->m_fs_checked |= mask;
	spin_unlock(&mp->m_sb_lock);
}

/* Sample which per-fs metadata are unhealthy. */
void
xfs_fs_measure_sickness(
	struct xfs_mount	*mp,
	unsigned int		*sick,
	unsigned int		*checked)
{
	spin_lock(&mp->m_sb_lock);
	*sick = mp->m_fs_sick;
	*checked = mp->m_fs_checked;
	spin_unlock(&mp->m_sb_lock);
}

/* Mark unhealthy realtime metadata. */
void
xfs_rt_mark_sick(
	struct xfs_mount	*mp,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_RT_ALL));
	trace_xfs_rt_mark_sick(mp, mask);

	spin_lock(&mp->m_sb_lock);
	mp->m_rt_sick |= mask;
	spin_unlock(&mp->m_sb_lock);
}

/* Mark realtime metadata as having been checked and found unhealthy by fsck. */
void
xfs_rt_mark_corrupt(
	struct xfs_mount	*mp,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_RT_ALL));
	trace_xfs_rt_mark_corrupt(mp, mask);

	spin_lock(&mp->m_sb_lock);
	mp->m_rt_sick |= mask;
	mp->m_rt_checked |= mask;
	spin_unlock(&mp->m_sb_lock);
}

/* Mark a realtime metadata healed. */
void
xfs_rt_mark_healthy(
	struct xfs_mount	*mp,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_RT_ALL));
	trace_xfs_rt_mark_healthy(mp, mask);

	spin_lock(&mp->m_sb_lock);
	mp->m_rt_sick &= ~mask;
	if (!(mp->m_rt_sick & XFS_SICK_RT_PRIMARY))
		mp->m_rt_sick &= ~XFS_SICK_RT_SECONDARY;
	mp->m_rt_checked |= mask;
	spin_unlock(&mp->m_sb_lock);
}

/* Sample which realtime metadata are unhealthy. */
void
xfs_rt_measure_sickness(
	struct xfs_mount	*mp,
	unsigned int		*sick,
	unsigned int		*checked)
{
	spin_lock(&mp->m_sb_lock);
	*sick = mp->m_rt_sick;
	*checked = mp->m_rt_checked;
	spin_unlock(&mp->m_sb_lock);
}

/* Mark unhealthy per-ag metadata given a raw AG number. */
void
xfs_agno_mark_sick(
	struct xfs_mount	*mp,
	xfs_agnumber_t		agno,
	unsigned int		mask)
{
	struct xfs_perag	*pag = xfs_perag_get(mp, agno);

	/* per-ag structure not set up yet? */
	if (!pag)
		return;

	xfs_ag_mark_sick(pag, mask);
	xfs_perag_put(pag);
}

/* Mark unhealthy per-ag metadata. */
void
xfs_ag_mark_sick(
	struct xfs_perag	*pag,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
	trace_xfs_ag_mark_sick(pag->pag_mount, pag->pag_agno, mask);

	spin_lock(&pag->pag_state_lock);
	pag->pag_sick |= mask;
	spin_unlock(&pag->pag_state_lock);
}

/* Mark per-ag metadata as having been checked and found unhealthy by fsck. */
void
xfs_ag_mark_corrupt(
	struct xfs_perag	*pag,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
	trace_xfs_ag_mark_corrupt(pag->pag_mount, pag->pag_agno, mask);

	spin_lock(&pag->pag_state_lock);
	pag->pag_sick |= mask;
	pag->pag_checked |= mask;
	spin_unlock(&pag->pag_state_lock);
}

/* Mark per-ag metadata ok. */
void
xfs_ag_mark_healthy(
	struct xfs_perag	*pag,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
	trace_xfs_ag_mark_healthy(pag->pag_mount, pag->pag_agno, mask);

	spin_lock(&pag->pag_state_lock);
	pag->pag_sick &= ~mask;
	if (!(pag->pag_sick & XFS_SICK_AG_PRIMARY))
		pag->pag_sick &= ~XFS_SICK_AG_SECONDARY;
	pag->pag_checked |= mask;
	spin_unlock(&pag->pag_state_lock);
}

/* Sample which per-ag metadata are unhealthy. */
void
xfs_ag_measure_sickness(
	struct xfs_perag	*pag,
	unsigned int		*sick,
	unsigned int		*checked)
{
	spin_lock(&pag->pag_state_lock);
	*sick = pag->pag_sick;
	*checked = pag->pag_checked;
	spin_unlock(&pag->pag_state_lock);
}

/* Mark the unhealthy parts of an inode. */
void
xfs_inode_mark_sick(
	struct xfs_inode	*ip,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_INO_ALL));
	trace_xfs_inode_mark_sick(ip, mask);

	spin_lock(&ip->i_flags_lock);
	ip->i_sick |= mask;
	spin_unlock(&ip->i_flags_lock);

	/*
	 * Keep this inode around so we don't lose the sickness report.  Scrub
	 * grabs inodes with DONTCACHE assuming that most inode are ok, which
	 * is not the case here.
	 */
	spin_lock(&VFS_I(ip)->i_lock);
	VFS_I(ip)->i_state &= ~I_DONTCACHE;
	spin_unlock(&VFS_I(ip)->i_lock);
}

/* Mark inode metadata as having been checked and found unhealthy by fsck. */
void
xfs_inode_mark_corrupt(
	struct xfs_inode	*ip,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_INO_ALL));
	trace_xfs_inode_mark_corrupt(ip, mask);

	spin_lock(&ip->i_flags_lock);
	ip->i_sick |= mask;
	ip->i_checked |= mask;
	spin_unlock(&ip->i_flags_lock);

	/*
	 * Keep this inode around so we don't lose the sickness report.  Scrub
	 * grabs inodes with DONTCACHE assuming that most inode are ok, which
	 * is not the case here.
	 */
	spin_lock(&VFS_I(ip)->i_lock);
	VFS_I(ip)->i_state &= ~I_DONTCACHE;
	spin_unlock(&VFS_I(ip)->i_lock);
}

/* Mark parts of an inode healed. */
void
xfs_inode_mark_healthy(
	struct xfs_inode	*ip,
	unsigned int		mask)
{
	ASSERT(!(mask & ~XFS_SICK_INO_ALL));
	trace_xfs_inode_mark_healthy(ip, mask);

	spin_lock(&ip->i_flags_lock);
	ip->i_sick &= ~mask;
	if (!(ip->i_sick & XFS_SICK_INO_PRIMARY))
		ip->i_sick &= ~XFS_SICK_INO_SECONDARY;
	ip->i_checked |= mask;
	spin_unlock(&ip->i_flags_lock);
}

/* Sample which parts of an inode are unhealthy. */
void
xfs_inode_measure_sickness(
	struct xfs_inode	*ip,
	unsigned int		*sick,
	unsigned int		*checked)
{
	spin_lock(&ip->i_flags_lock);
	*sick = ip->i_sick;
	*checked = ip->i_checked;
	spin_unlock(&ip->i_flags_lock);
}

/* Mappings between internal sick masks and ioctl sick masks. */

struct ioctl_sick_map {
	unsigned int		sick_mask;
	unsigned int		ioctl_mask;
};

static const struct ioctl_sick_map fs_map[] = {
	{ XFS_SICK_FS_COUNTERS,	XFS_FSOP_GEOM_SICK_COUNTERS},
	{ XFS_SICK_FS_UQUOTA,	XFS_FSOP_GEOM_SICK_UQUOTA },
	{ XFS_SICK_FS_GQUOTA,	XFS_FSOP_GEOM_SICK_GQUOTA },
	{ XFS_SICK_FS_PQUOTA,	XFS_FSOP_GEOM_SICK_PQUOTA },
	{ XFS_SICK_FS_QUOTACHECK, XFS_FSOP_GEOM_SICK_QUOTACHECK },
	{ XFS_SICK_FS_NLINKS,	XFS_FSOP_GEOM_SICK_NLINKS },
	{ 0, 0 },
};

static const struct ioctl_sick_map rt_map[] = {
	{ XFS_SICK_RT_BITMAP,	XFS_FSOP_GEOM_SICK_RT_BITMAP },
	{ XFS_SICK_RT_SUMMARY,	XFS_FSOP_GEOM_SICK_RT_SUMMARY },
	{ 0, 0 },
};

static inline void
xfgeo_health_tick(
	struct xfs_fsop_geom		*geo,
	unsigned int			sick,
	unsigned int			checked,
	const struct ioctl_sick_map	*m)
{
	if (checked & m->sick_mask)
		geo->checked |= m->ioctl_mask;
	if (sick & m->sick_mask)
		geo->sick |= m->ioctl_mask;
}

/* Fill out fs geometry health info. */
void
xfs_fsop_geom_health(
	struct xfs_mount		*mp,
	struct xfs_fsop_geom		*geo)
{
	const struct ioctl_sick_map	*m;
	unsigned int			sick;
	unsigned int			checked;

	geo->sick = 0;
	geo->checked = 0;

	xfs_fs_measure_sickness(mp, &sick, &checked);
	for (m = fs_map; m->sick_mask; m++)
		xfgeo_health_tick(geo, sick, checked, m);

	xfs_rt_measure_sickness(mp, &sick, &checked);
	for (m = rt_map; m->sick_mask; m++)
		xfgeo_health_tick(geo, sick, checked, m);
}

static const struct ioctl_sick_map ag_map[] = {
	{ XFS_SICK_AG_SB,	XFS_AG_GEOM_SICK_SB },
	{ XFS_SICK_AG_AGF,	XFS_AG_GEOM_SICK_AGF },
	{ XFS_SICK_AG_AGFL,	XFS_AG_GEOM_SICK_AGFL },
	{ XFS_SICK_AG_AGI,	XFS_AG_GEOM_SICK_AGI },
	{ XFS_SICK_AG_BNOBT,	XFS_AG_GEOM_SICK_BNOBT },
	{ XFS_SICK_AG_CNTBT,	XFS_AG_GEOM_SICK_CNTBT },
	{ XFS_SICK_AG_INOBT,	XFS_AG_GEOM_SICK_INOBT },
	{ XFS_SICK_AG_FINOBT,	XFS_AG_GEOM_SICK_FINOBT },
	{ XFS_SICK_AG_RMAPBT,	XFS_AG_GEOM_SICK_RMAPBT },
	{ XFS_SICK_AG_REFCNTBT,	XFS_AG_GEOM_SICK_REFCNTBT },
	{ XFS_SICK_AG_INODES,	XFS_AG_GEOM_SICK_INODES },
	{ 0, 0 },
};

/* Fill out ag geometry health info. */
void
xfs_ag_geom_health(
	struct xfs_perag		*pag,
	struct xfs_ag_geometry		*ageo)
{
	const struct ioctl_sick_map	*m;
	unsigned int			sick;
	unsigned int			checked;

	ageo->ag_sick = 0;
	ageo->ag_checked = 0;

	xfs_ag_measure_sickness(pag, &sick, &checked);
	for (m = ag_map; m->sick_mask; m++) {
		if (checked & m->sick_mask)
			ageo->ag_checked |= m->ioctl_mask;
		if (sick & m->sick_mask)
			ageo->ag_sick |= m->ioctl_mask;
	}
}

static const struct ioctl_sick_map ino_map[] = {
	{ XFS_SICK_INO_CORE,	XFS_BS_SICK_INODE },
	{ XFS_SICK_INO_BMBTD,	XFS_BS_SICK_BMBTD },
	{ XFS_SICK_INO_BMBTA,	XFS_BS_SICK_BMBTA },
	{ XFS_SICK_INO_BMBTC,	XFS_BS_SICK_BMBTC },
	{ XFS_SICK_INO_DIR,	XFS_BS_SICK_DIR },
	{ XFS_SICK_INO_XATTR,	XFS_BS_SICK_XATTR },
	{ XFS_SICK_INO_SYMLINK,	XFS_BS_SICK_SYMLINK },
	{ XFS_SICK_INO_PARENT,	XFS_BS_SICK_PARENT },
	{ XFS_SICK_INO_BMBTD_ZAPPED,	XFS_BS_SICK_BMBTD },
	{ XFS_SICK_INO_BMBTA_ZAPPED,	XFS_BS_SICK_BMBTA },
	{ XFS_SICK_INO_DIR_ZAPPED,	XFS_BS_SICK_DIR },
	{ XFS_SICK_INO_SYMLINK_ZAPPED,	XFS_BS_SICK_SYMLINK },
	{ 0, 0 },
};

/* Fill out bulkstat health info. */
void
xfs_bulkstat_health(
	struct xfs_inode		*ip,
	struct xfs_bulkstat		*bs)
{
	const struct ioctl_sick_map	*m;
	unsigned int			sick;
	unsigned int			checked;

	bs->bs_sick = 0;
	bs->bs_checked = 0;

	xfs_inode_measure_sickness(ip, &sick, &checked);
	for (m = ino_map; m->sick_mask; m++) {
		if (checked & m->sick_mask)
			bs->bs_checked |= m->ioctl_mask;
		if (sick & m->sick_mask)
			bs->bs_sick |= m->ioctl_mask;
	}
}

/* Mark a block mapping sick. */
void
xfs_bmap_mark_sick(
	struct xfs_inode	*ip,
	int			whichfork)
{
	unsigned int		mask;

	switch (whichfork) {
	case XFS_DATA_FORK:
		mask = XFS_SICK_INO_BMBTD;
		break;
	case XFS_ATTR_FORK:
		mask = XFS_SICK_INO_BMBTA;
		break;
	case XFS_COW_FORK:
		mask = XFS_SICK_INO_BMBTC;
		break;
	default:
		ASSERT(0);
		return;
	}

	xfs_inode_mark_sick(ip, mask);
}

/* Record observations of btree corruption with the health tracking system. */
void
xfs_btree_mark_sick(
	struct xfs_btree_cur		*cur)
{
	switch (cur->bc_ops->type) {
	case XFS_BTREE_TYPE_MEM:
		/* no health state tracking for ephemeral btrees */
		return;
	case XFS_BTREE_TYPE_AG:
		ASSERT(cur->bc_ops->sick_mask);
		xfs_ag_mark_sick(cur->bc_ag.pag, cur->bc_ops->sick_mask);
		return;
	case XFS_BTREE_TYPE_INODE:
		if (xfs_btree_is_bmap(cur->bc_ops)) {
			xfs_bmap_mark_sick(cur->bc_ino.ip,
					   cur->bc_ino.whichfork);
			return;
		}
		fallthrough;
	default:
		ASSERT(0);
		return;
	}
}

/*
 * Record observations of dir/attr btree corruption with the health tracking
 * system.
 */
void
xfs_dirattr_mark_sick(
	struct xfs_inode	*ip,
	int			whichfork)
{
	unsigned int		mask;

	switch (whichfork) {
	case XFS_DATA_FORK:
		mask = XFS_SICK_INO_DIR;
		break;
	case XFS_ATTR_FORK:
		mask = XFS_SICK_INO_XATTR;
		break;
	default:
		ASSERT(0);
		return;
	}

	xfs_inode_mark_sick(ip, mask);
}

/*
 * Record observations of dir/attr btree corruption with the health tracking
 * system.
 */
void
xfs_da_mark_sick(
	struct xfs_da_args	*args)
{
	xfs_dirattr_mark_sick(args->dp, args->whichfork);
}