summaryrefslogtreecommitdiff
path: root/fs/xfs/scrub/refcount_repair.c
blob: 8b19e2b809eafce726c26edc52cce1cf33515578 (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
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2018 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_itable.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_refcount.h"
#include "xfs_refcount_btree.h"
#include "xfs_error.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/bitmap.h"
#include "scrub/array.h"

/*
 * Rebuilding the Reference Count Btree
 * ====================================
 *
 * This algorithm is "borrowed" from xfs_repair.  Imagine the rmap
 * entries as rectangles representing extents of physical blocks, and
 * that the rectangles can be laid down to allow them to overlap each
 * other; then we know that we must emit a refcnt btree entry wherever
 * the amount of overlap changes, i.e. the emission stimulus is
 * level-triggered:
 *
 *                 -    ---
 *       --      ----- ----   ---        ------
 * --   ----     ----------- ----     ---------
 * -------------------------------- -----------
 * ^ ^  ^^ ^^    ^ ^^ ^^^  ^^^^  ^ ^^ ^  ^     ^
 * 2 1  23 21    3 43 234  2123  1 01 2  3     0
 *
 * For our purposes, a rmap is a tuple (startblock, len, fileoff, owner).
 *
 * Note that in the actual refcnt btree we don't store the refcount < 2
 * cases because the bnobt tells us which blocks are free; single-use
 * blocks aren't recorded in the bnobt or the refcntbt.  If the rmapbt
 * supports storing multiple entries covering a given block we could
 * theoretically dispense with the refcntbt and simply count rmaps, but
 * that's inefficient in the (hot) write path, so we'll take the cost of
 * the extra tree to save time.  Also there's no guarantee that rmap
 * will be enabled.
 *
 * Given an array of rmaps sorted by physical block number, a starting
 * physical block (sp), a bag to hold rmaps that cover sp, and the next
 * physical block where the level changes (np), we can reconstruct the
 * refcount btree as follows:
 *
 * While there are still unprocessed rmaps in the array,
 *  - Set sp to the physical block (pblk) of the next unprocessed rmap.
 *  - Add to the bag all rmaps in the array where startblock == sp.
 *  - Set np to the physical block where the bag size will change.  This
 *    is the minimum of (the pblk of the next unprocessed rmap) and
 *    (startblock + len of each rmap in the bag).
 *  - Record the bag size as old_bag_size.
 *
 *  - While the bag isn't empty,
 *     - Remove from the bag all rmaps where startblock + len == np.
 *     - Add to the bag all rmaps in the array where startblock == np.
 *     - If the bag size isn't old_bag_size, store the refcount entry
 *       (sp, np - sp, bag_size) in the refcnt btree.
 *     - If the bag is empty, break out of the inner loop.
 *     - Set old_bag_size to the bag size
 *     - Set sp = np.
 *     - Set np to the physical block where the bag size will change.
 *       This is the minimum of (the pblk of the next unprocessed rmap)
 *       and (startblock + len of each rmap in the bag).
 *
 * Like all the other repairers, we make a list of all the refcount
 * records we need, then reinitialize the refcount btree root and
 * insert all the records.
 */

/* The only parts of the rmap that we care about for computing refcounts. */
struct xrep_refc_rmap {
	xfs_agblock_t		startblock;
	xfs_extlen_t		blockcount;
} __attribute__((packed));

/* Smallest possible representation of a refcount extent. */
struct xrep_refc_extent {
	xfs_agblock_t		startblock;
	xfs_extlen_t		blockcount;
	xfs_nlink_t		refcount;
} __attribute__((packed));

struct xrep_refc {
	struct xfbma		*rmap_bag; /* rmaps we're tracking */
	struct xfbma		*refcount_records;	/* refcount extents */
	struct xfs_bitmap	*btlist;   /* old refcountbt blocks */
	struct xfs_scrub	*sc;
	xfs_extlen_t		btblocks;  /* # of refcountbt blocks */
};

/* Grab the next (abbreviated) rmap record from the rmapbt. */
STATIC int
xrep_refc_next_rrm(
	struct xfs_btree_cur	*cur,
	struct xrep_refc	*rr,
	struct xrep_refc_rmap	*rrm,
	bool			*have_rec)
{
	struct xfs_rmap_irec	rmap;
	struct xfs_mount	*mp = cur->bc_mp;
	xfs_fsblock_t		fsbno;
	int			have_gt;
	int			error = 0;

	*have_rec = false;
	/*
	 * Loop through the remaining rmaps.  Remember CoW staging
	 * extents and the refcountbt blocks from the old tree for later
	 * disposal.  We can only share written data fork extents, so
	 * keep looping until we find an rmap for one.
	 */
	do {
		if (xchk_should_terminate(rr->sc, &error))
			goto out_error;

		error = xfs_btree_increment(cur, 0, &have_gt);
		if (error)
			goto out_error;
		if (!have_gt)
			return 0;

		error = xfs_rmap_get_rec(cur, &rmap, &have_gt);
		if (error)
			goto out_error;
		XFS_WANT_CORRUPTED_GOTO(mp, have_gt == 1, out_error);

		if (rmap.rm_owner == XFS_RMAP_OWN_COW) {
			struct xrep_refc_extent	ext = {
				.startblock	= rmap.rm_startblock +
					XFS_REFC_COW_START,
				.blockcount	= rmap.rm_blockcount,
				.refcount	= 1,
			};

			/* Pass CoW staging extents right through. */
			error = xfbma_append(rr->refcount_records, &ext);
			if (error)
				goto out_error;
		} else if (rmap.rm_owner == XFS_RMAP_OWN_REFC) {
			/* refcountbt block, dump it when we're done. */
			rr->btblocks += rmap.rm_blockcount;
			fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
					cur->bc_private.a.agno,
					rmap.rm_startblock);
			error = xfs_bitmap_set(rr->btlist, fsbno,
					rmap.rm_blockcount);
			if (error)
				goto out_error;
		}
	} while (XFS_RMAP_NON_INODE_OWNER(rmap.rm_owner) ||
		 xfs_internal_inum(mp, rmap.rm_owner) ||
		 (rmap.rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
				   XFS_RMAP_UNWRITTEN)));

	rrm->startblock = rmap.rm_startblock;
	rrm->blockcount = rmap.rm_blockcount;
	*have_rec = true;
	return 0;

out_error:
	return error;
}

/* Compare two btree extents. */
static int
xrep_refc_extent_cmp(
	const void			*a,
	const void			*b)
{
	const struct xrep_refc_extent	*ap = a;
	const struct xrep_refc_extent	*bp = b;

	if (ap->startblock > bp->startblock)
		return 1;
	else if (ap->startblock < bp->startblock)
		return -1;
	return 0;
}

/* Record a reference count extent. */
STATIC int
xrep_refc_remember(
	struct xfs_scrub		*sc,
	struct xrep_refc		*rr,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len,
	xfs_nlink_t			refcount)
{
	struct xrep_refc_extent		rre = {
		.startblock	= agbno,
		.blockcount	= len,
		.refcount	= refcount,
	};

	trace_xrep_refcount_extent_fn(sc->mp, sc->sa.agno, agbno, len,
			refcount);

	return xfbma_append(rr->refcount_records, &rre);
}

#define RRM_NEXT(r)	((r).startblock + (r).blockcount)
/*
 * Find the next block where the refcount changes, given the next rmap we
 * looked at and the ones we're already tracking.
 */
static inline xfs_agblock_t
xrep_refc_next_edge(
	struct xfbma		*rmap_bag,
	struct xrep_refc_rmap	*next_rrm,
	bool			next_valid)
{
	struct xrep_refc_rmap	rrm;
	uint64_t		i;
	xfs_agblock_t		nbno;

	nbno = next_valid ? next_rrm->startblock : NULLAGBLOCK;
	foreach_xfbma_item(rmap_bag, i, rrm)
		nbno = min_t(xfs_agblock_t, nbno, RRM_NEXT(rrm));
	return nbno;
}

/* Iterate all the rmap records to generate reference count data. */
STATIC int
xrep_refc_generate_refcounts(
	struct xfs_scrub	*sc,
	struct xrep_refc	*rr)
{
	struct xrep_refc_rmap	rrm;
	struct xfs_btree_cur	*cur;
	xfs_agblock_t		sbno;
	xfs_agblock_t		cbno;
	xfs_agblock_t		nbno;
	size_t			old_stack_sz;
	size_t			stack_sz = 0;
	bool			have;
	int			have_gt;
	int			error;

	/* Start the rmapbt cursor to the left of all records. */
	cur = xfs_rmapbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
			sc->sa.agno);
	error = xfs_rmap_lookup_le(cur, 0, 0, 0, 0, 0, &have_gt);
	if (error)
		goto out;
	ASSERT(have_gt == 0);

	/* Process reverse mappings into refcount data. */
	while (xfs_btree_has_more_records(cur)) {
		/* Push all rmaps with pblk == sbno onto the stack */
		error = xrep_refc_next_rrm(cur, rr, &rrm, &have);
		if (error)
			goto out;
		if (!have)
			break;
		sbno = cbno = rrm.startblock;
		while (have && rrm.startblock == sbno) {
			error = xfbma_insert_anywhere(rr->rmap_bag, &rrm);
			if (error)
				goto out;
			stack_sz++;
			error = xrep_refc_next_rrm(cur, rr, &rrm, &have);
			if (error)
				goto out;
		}
		error = xfs_btree_decrement(cur, 0, &have_gt);
		if (error)
			goto out;
		XFS_WANT_CORRUPTED_GOTO(sc->mp, have_gt, out);

		/* Set nbno to the bno of the next refcount change */
		nbno = xrep_refc_next_edge(rr->rmap_bag, &rrm, have);
		if (nbno == NULLAGBLOCK) {
			error = -EFSCORRUPTED;
			goto out;
		}

		ASSERT(nbno > sbno);
		old_stack_sz = stack_sz;

		/* While stack isn't empty... */
		while (stack_sz) {
			uint64_t	i;

			/* Pop all rmaps that end at nbno */
			foreach_xfbma_item(rr->rmap_bag, i, rrm) {
				if (RRM_NEXT(rrm) != nbno)
					continue;
				error = xfbma_nullify(rr->rmap_bag, i);
				if (error)
					goto out;
				stack_sz--;
			}

			/* Push array items that start at nbno */
			error = xrep_refc_next_rrm(cur, rr, &rrm, &have);
			if (error)
				goto out;
			while (have && rrm.startblock == nbno) {
				error = xfbma_insert_anywhere(rr->rmap_bag, &rrm);
				if (error)
					goto out;
				stack_sz++;
				error = xrep_refc_next_rrm(cur, rr, &rrm,
						&have);
				if (error)
					goto out;
			}
			error = xfs_btree_decrement(cur, 0, &have_gt);
			if (error)
				goto out;
			XFS_WANT_CORRUPTED_GOTO(sc->mp, have_gt, out);

			/* Emit refcount if necessary */
			ASSERT(nbno > cbno);
			if (stack_sz != old_stack_sz) {
				if (old_stack_sz > 1) {
					error = xrep_refc_remember(sc, rr, cbno,
							nbno - cbno,
							old_stack_sz);
					if (error)
						goto out;
				}
				cbno = nbno;
			}

			/* Stack empty, go find the next rmap */
			if (stack_sz == 0)
				break;
			old_stack_sz = stack_sz;
			sbno = nbno;

			/* Set nbno to the bno of the next refcount change */
			nbno = xrep_refc_next_edge(rr->rmap_bag, &rrm, have);
			if (nbno == NULLAGBLOCK) {
				error = -EFSCORRUPTED;
				goto out;
			}

			ASSERT(nbno > sbno);
		}
	}

	ASSERT(stack_sz == 0);
out:
	xfs_btree_del_cursor(cur, error);
	return error;
}
#undef RRM_NEXT

/*
 * Generate all the reference counts for this AG and a list of the old
 * refcount btree blocks.  Figure out if we have enough free space to
 * reconstruct the inode btrees.  The caller must clean up the lists if
 * anything goes wrong.
 */
STATIC int
xrep_refc_find_refcounts(
	struct xfs_scrub	*sc,
	struct xfbma		*refcount_records,
	struct xfs_bitmap	*old_refcountbt_blocks)
{
	struct xrep_refc	rr = {
		.sc			= sc,
		.refcount_records	= refcount_records,
		.btlist			= old_refcountbt_blocks,
	};
	struct xfs_mount	*mp = sc->mp;
	xfs_extlen_t		blocks;
	int			error;

	/* Set up some storage */
	rr.rmap_bag = xfbma_init(sizeof(struct xrep_refc_rmap));
	if (IS_ERR(rr.rmap_bag))
		return PTR_ERR(rr.rmap_bag);

	/* Generate all the refcount records. */
	error = xrep_refc_generate_refcounts(sc, &rr);
	if (error)
		goto out;

	/* Do we actually have enough space to do this? */
	blocks = xfs_refcountbt_calc_size(mp, xfbma_length(refcount_records));
	if (!xrep_ag_has_space(sc->sa.pag, blocks, XFS_AG_RESV_METADATA)) {
		error = -ENOSPC;
		goto out;
	}

out:
	xfbma_destroy(rr.rmap_bag);
	return error;
}

/* Initialize new refcountbt root and implant it into the AGF. */
STATIC int
xrep_refc_reset_btree(
	struct xfs_scrub	*sc,
	int			*log_flags)
{
	struct xfs_buf		*bp;
	struct xfs_agf		*agf;
	xfs_fsblock_t		btfsb;
	int			error;

	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);

	/* Initialize a new refcountbt root. */
	error = xrep_alloc_ag_block(sc, &XFS_RMAP_OINFO_REFC, &btfsb,
			XFS_AG_RESV_METADATA);
	if (error)
		return error;
	error = xrep_init_btblock(sc, btfsb, &bp, XFS_BTNUM_REFC,
			&xfs_refcountbt_buf_ops);
	if (error)
		return error;
	agf->agf_refcount_root = cpu_to_be32(XFS_FSB_TO_AGBNO(sc->mp, btfsb));
	agf->agf_refcount_level = cpu_to_be32(1);
	agf->agf_refcount_blocks = cpu_to_be32(1);
	*log_flags |= XFS_AGF_REFCOUNT_BLOCKS | XFS_AGF_REFCOUNT_ROOT |
		      XFS_AGF_REFCOUNT_LEVEL;

	return 0;
}

/* Insert a single record into the refcount btree. */
STATIC int
xrep_refc_insert_rec(
	const void			*item,
	void				*priv)
{
	const struct xrep_refc_extent	*rre = item;
	struct xfs_refcount_irec	refc = {
		.rc_startblock	= rre->startblock,
		.rc_blockcount	= rre->blockcount,
		.rc_refcount	= rre->refcount,
	};
	struct xfs_scrub		*sc = priv;
	struct xfs_mount		*mp = sc->mp;
	struct xfs_btree_cur		*cur;
	int				have_gt;
	int				error;

	/* Insert into the refcountbt. */
	cur = xfs_refcountbt_init_cursor(mp, sc->tp, sc->sa.agf_bp,
			sc->sa.agno);
	error = xfs_refcount_lookup_eq(cur, rre->startblock, &have_gt);
	if (error)
		goto out;
	XFS_WANT_CORRUPTED_GOTO(mp, have_gt == 0, out);
	error = xfs_refcount_insert(cur, &refc, &have_gt);
	if (error)
		goto out;
	XFS_WANT_CORRUPTED_GOTO(mp, have_gt == 1, out);
	xfs_btree_del_cursor(cur, error);
	return xrep_roll_ag_trans(sc);
out:
	xfs_btree_del_cursor(cur, error);
	return error;
}

/* Build new refcount btree and dispose of the old one. */
STATIC int
xrep_refc_rebuild_tree(
	struct xfs_scrub	*sc,
	struct xfbma		*refcount_records,
	struct xfs_bitmap	*old_refcountbt_blocks)
{
	int			error;

	/*
	 * Sort the refcount extents by startblock to avoid btree splits when
	 * we rebuild the refcount btree.
	 */
	error = xfbma_sort(refcount_records, xrep_refc_extent_cmp);
	if (error)
		return error;

	/* Free the old refcountbt blocks if they're not in use. */
	error = xrep_reap_extents(sc, old_refcountbt_blocks,
			&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
	if (error)
		return error;

	/* Add all records. */
	return xfbma_iter_del(refcount_records, xrep_refc_insert_rec, sc);
}

/* Rebuild the refcount btree. */
int
xrep_refcountbt(
	struct xfs_scrub	*sc)
{
	struct xfs_bitmap	old_refcountbt_blocks;
	struct xfbma		*refcount_records;
	struct xfs_mount	*mp = sc->mp;
	int			log_flags = 0;
	int			error;

	/* We require the rmapbt to rebuild anything. */
	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
		return -EOPNOTSUPP;

	xchk_perag_get(sc->mp, &sc->sa);

	/* Set up some storage */
	refcount_records = xfbma_init(sizeof(struct xrep_refc_extent));
	if (IS_ERR(refcount_records))
		return PTR_ERR(refcount_records);

	/* Collect all reference counts. */
	xfs_bitmap_init(&old_refcountbt_blocks);
	error = xrep_refc_find_refcounts(sc, refcount_records,
			&old_refcountbt_blocks);
	if (error)
		goto out;

	/*
	 * Blow out the old refcount btrees.  This is the point at which
	 * we are no longer able to bail out gracefully.
	 */
	error = xrep_refc_reset_btree(sc, &log_flags);
	if (error)
		goto out;
	xfs_alloc_log_agf(sc->tp, sc->sa.agf_bp, log_flags);

	/* Invalidate all the inobt/finobt blocks in btlist. */
	error = xrep_invalidate_blocks(sc, &old_refcountbt_blocks);
	if (error)
		goto out;
	error = xrep_roll_ag_trans(sc);
	if (error)
		goto out;

	/* Now rebuild the refcount information. */
	error = xrep_refc_rebuild_tree(sc, refcount_records,
			&old_refcountbt_blocks);
	if (error)
		goto out;
	sc->reset_perag_resv = true;
out:
	xfs_bitmap_destroy(&old_refcountbt_blocks);
	xfbma_destroy(refcount_records);
	return error;
}