summaryrefslogtreecommitdiffstats
path: root/fs/xfs/scrub/nlinks_repair.c
blob: b3e707f47b7b522393678e7ae596db97e4db31f8 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <djwong@kernel.org>
 */
#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_log_format.h"
#include "xfs_trans.h"
#include "xfs_inode.h"
#include "xfs_icache.h"
#include "xfs_bmap_util.h"
#include "xfs_iwalk.h"
#include "xfs_ialloc.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_parent.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/repair.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
#include "scrub/iscan.h"
#include "scrub/orphanage.h"
#include "scrub/nlinks.h"
#include "scrub/trace.h"
#include "scrub/tempfile.h"

/*
 * Live Inode Link Count Repair
 * ============================
 *
 * Use the live inode link count information that we collected to replace the
 * nlink values of the incore inodes.  A scrub->repair cycle should have left
 * the live data and hooks active, so this is safe so long as we make sure the
 * inode is locked.
 */

/* Set up to repair inode link counts. */
int
xrep_setup_nlinks(
	struct xfs_scrub	*sc)
{
	return xrep_orphanage_try_create(sc);
}

/*
 * Inodes that aren't the root directory or the orphanage, have a nonzero link
 * count, and no observed parents should be moved to the orphanage.
 */
static inline bool
xrep_nlinks_is_orphaned(
	struct xfs_scrub	*sc,
	struct xfs_inode	*ip,
	unsigned int		actual_nlink,
	const struct xchk_nlink	*obs)
{
	struct xfs_mount	*mp = ip->i_mount;

	if (obs->parents != 0)
		return false;
	if (ip == mp->m_rootip || ip == sc->orphanage)
		return false;
	return actual_nlink != 0;
}

/* Remove an inode from the unlinked list. */
STATIC int
xrep_nlinks_iunlink_remove(
	struct xfs_scrub	*sc)
{
	struct xfs_perag	*pag;
	int			error;

	pag = xfs_perag_get(sc->mp, XFS_INO_TO_AGNO(sc->mp, sc->ip->i_ino));
	error = xfs_iunlink_remove(sc->tp, pag, sc->ip);
	xfs_perag_put(pag);
	return error;
}

/*
 * Correct the link count of the given inode.  Because we have to grab locks
 * and resources in a certain order, it's possible that this will be a no-op.
 */
STATIC int
xrep_nlinks_repair_inode(
	struct xchk_nlink_ctrs	*xnc)
{
	struct xchk_nlink	obs;
	struct xfs_scrub	*sc = xnc->sc;
	struct xfs_mount	*mp = sc->mp;
	struct xfs_inode	*ip = sc->ip;
	uint64_t		total_links;
	uint64_t		actual_nlink;
	bool			orphanage_available = false;
	bool			dirty = false;
	int			error;

	/*
	 * Ignore temporary files being used to stage repairs, since we assume
	 * they're correct for non-directories, and the directory repair code
	 * doesn't bump the link counts for the children.
	 */
	if (xrep_is_tempfile(ip))
		return 0;

	/*
	 * If the filesystem has an orphanage attached to the scrub context,
	 * prepare for a link count repair that could involve @ip being adopted
	 * by the lost+found.
	 */
	if (xrep_orphanage_can_adopt(sc)) {
		error = xrep_orphanage_iolock_two(sc);
		if (error)
			return error;

		error = xrep_adoption_trans_alloc(sc, &xnc->adoption);
		if (error) {
			xchk_iunlock(sc, XFS_IOLOCK_EXCL);
			xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
		} else {
			orphanage_available = true;
		}
	}

	/*
	 * Either there is no orphanage or we couldn't allocate resources for
	 * that kind of update.  Let's try again with only the resources we
	 * need for a simple link count update, since that's much more common.
	 */
	if (!orphanage_available) {
		xchk_ilock(sc, XFS_IOLOCK_EXCL);

		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0,
				&sc->tp);
		if (error) {
			xchk_iunlock(sc, XFS_IOLOCK_EXCL);
			return error;
		}

		xchk_ilock(sc, XFS_ILOCK_EXCL);
		xfs_trans_ijoin(sc->tp, ip, 0);
	}

	mutex_lock(&xnc->lock);

	if (xchk_iscan_aborted(&xnc->collect_iscan)) {
		error = -ECANCELED;
		goto out_scanlock;
	}

	error = xfarray_load_sparse(xnc->nlinks, ip->i_ino, &obs);
	if (error)
		goto out_scanlock;

	/*
	 * We're done accessing the shared scan data, so we can drop the lock.
	 * We still hold @ip's ILOCK, so its link count cannot change.
	 */
	mutex_unlock(&xnc->lock);

	total_links = xchk_nlink_total(ip, &obs);
	actual_nlink = VFS_I(ip)->i_nlink;

	/*
	 * Non-directories cannot have directories pointing up to them.
	 *
	 * We previously set error to zero, but set it again because one static
	 * checker author fears that programmers will fail to maintain this
	 * invariant and built their tool to flag this as a security risk.  A
	 * different tool author made their bot complain about the redundant
	 * store.  This is a never-ending and stupid battle; both tools missed
	 * *actual bugs* elsewhere; and I no longer care.
	 */
	if (!S_ISDIR(VFS_I(ip)->i_mode) && obs.children != 0) {
		trace_xrep_nlinks_unfixable_inode(mp, ip, &obs);
		error = 0;
		goto out_trans;
	}

	/*
	 * Decide if we're going to move this file to the orphanage, and fix
	 * up the incore link counts if we are.
	 */
	if (orphanage_available &&
	    xrep_nlinks_is_orphaned(sc, ip, actual_nlink, &obs)) {
		/* Figure out what name we're going to use here. */
		error = xrep_adoption_compute_name(&xnc->adoption, &xnc->xname);
		if (error)
			goto out_trans;

		/*
		 * Reattach this file to the directory tree by moving it to
		 * the orphanage per the adoption parameters that we already
		 * computed.
		 */
		error = xrep_adoption_move(&xnc->adoption);
		if (error)
			goto out_trans;

		/*
		 * Re-read the link counts since the reparenting will have
		 * updated our scan info.
		 */
		mutex_lock(&xnc->lock);
		error = xfarray_load_sparse(xnc->nlinks, ip->i_ino, &obs);
		mutex_unlock(&xnc->lock);
		if (error)
			goto out_trans;

		total_links = xchk_nlink_total(ip, &obs);
		actual_nlink = VFS_I(ip)->i_nlink;
		dirty = true;
	}

	/*
	 * If this inode is linked from the directory tree and on the unlinked
	 * list, remove it from the unlinked list.
	 */
	if (total_links > 0 && xfs_inode_on_unlinked_list(ip)) {
		error = xrep_nlinks_iunlink_remove(sc);
		if (error)
			goto out_trans;
		dirty = true;
	}

	/*
	 * If this inode is not linked from the directory tree yet not on the
	 * unlinked list, put it on the unlinked list.
	 */
	if (total_links == 0 && !xfs_inode_on_unlinked_list(ip)) {
		error = xfs_iunlink(sc->tp, ip);
		if (error)
			goto out_trans;
		dirty = true;
	}

	/* Commit the new link count if it changed. */
	if (total_links != actual_nlink) {
		trace_xrep_nlinks_update_inode(mp, ip, &obs);

		set_nlink(VFS_I(ip), min_t(unsigned long long, total_links,
					   XFS_NLINK_PINNED));
		dirty = true;
	}

	if (!dirty) {
		error = 0;
		goto out_trans;
	}

	xfs_trans_log_inode(sc->tp, ip, XFS_ILOG_CORE);

	error = xrep_trans_commit(sc);
	goto out_unlock;

out_scanlock:
	mutex_unlock(&xnc->lock);
out_trans:
	xchk_trans_cancel(sc);
out_unlock:
	xchk_iunlock(sc, XFS_ILOCK_EXCL);
	if (orphanage_available) {
		xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
		xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
	}
	xchk_iunlock(sc, XFS_IOLOCK_EXCL);
	return error;
}

/*
 * Try to visit every inode in the filesystem for repairs.  Move on if we can't
 * grab an inode, since we're still making forward progress.
 */
static int
xrep_nlinks_iter(
	struct xchk_nlink_ctrs	*xnc,
	struct xfs_inode	**ipp)
{
	int			error;

	do {
		error = xchk_iscan_iter(&xnc->compare_iscan, ipp);
	} while (error == -EBUSY);

	return error;
}

/* Commit the new inode link counters. */
int
xrep_nlinks(
	struct xfs_scrub	*sc)
{
	struct xchk_nlink_ctrs	*xnc = sc->buf;
	int			error;

	/*
	 * We need ftype for an accurate count of the number of child
	 * subdirectory links.  Child subdirectories with a back link (dotdot
	 * entry) but no forward link are moved to the orphanage, so we cannot
	 * repair the link count of the parent directory based on the back link
	 * count alone.  Filesystems without ftype support are rare (old V4) so
	 * we just skip out here.
	 */
	if (!xfs_has_ftype(sc->mp))
		return -EOPNOTSUPP;

	/*
	 * Use the inobt to walk all allocated inodes to compare and fix the
	 * link counts.  Retry iget every tenth of a second for up to 30
	 * seconds -- even if repair misses a few inodes, we still try to fix
	 * as many of them as we can.
	 */
	xchk_iscan_start(sc, 30000, 100, &xnc->compare_iscan);
	ASSERT(sc->ip == NULL);

	while ((error = xrep_nlinks_iter(xnc, &sc->ip)) == 1) {
		/*
		 * Commit the scrub transaction so that we can create repair
		 * transactions with the correct reservations.
		 */
		xchk_trans_cancel(sc);

		error = xrep_nlinks_repair_inode(xnc);
		xchk_iscan_mark_visited(&xnc->compare_iscan, sc->ip);
		xchk_irele(sc, sc->ip);
		sc->ip = NULL;
		if (error)
			break;

		if (xchk_should_terminate(sc, &error))
			break;

		/*
		 * Create a new empty transaction so that we can advance the
		 * iscan cursor without deadlocking if the inobt has a cycle.
		 * We can only push the inactivation workqueues with an empty
		 * transaction.
		 */
		error = xchk_trans_alloc_empty(sc);
		if (error)
			break;
	}
	xchk_iscan_iter_finish(&xnc->compare_iscan);
	xchk_iscan_teardown(&xnc->compare_iscan);

	return error;
}