summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_inode_buf.c
blob: 38fe509827dd6409db01decfcd40d48b375ab61a (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
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * 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.
 *
 * 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_format.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_error.h"
#include "xfs_cksum.h"
#include "xfs_icache.h"
#include "xfs_ialloc.h"

/*
 * Check that none of the inode's in the buffer have a next
 * unlinked field of 0.
 */
#if defined(DEBUG)
void
xfs_inobp_check(
	xfs_mount_t	*mp,
	xfs_buf_t	*bp)
{
	int		i;
	int		j;
	xfs_dinode_t	*dip;

	j = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;

	for (i = 0; i < j; i++) {
		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
					i * mp->m_sb.sb_inodesize);
		if (!dip->di_next_unlinked)  {
			xfs_alert(mp,
	"Detected bogus zero next_unlinked field in incore inode buffer 0x%p.",
				bp);
			ASSERT(dip->di_next_unlinked);
		}
	}
}
#endif

static void
xfs_inode_buf_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount *mp = bp->b_target->bt_mount;
	int		i;
	int		ni;

	/*
	 * Validate the magic number and version of every inode in the buffer
	 */
	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
	for (i = 0; i < ni; i++) {
		int		di_ok;
		xfs_dinode_t	*dip;

		dip = (struct xfs_dinode *)xfs_buf_offset(bp,
					(i << mp->m_sb.sb_inodelog));
		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
			    XFS_DINODE_GOOD_VERSION(dip->di_version);
		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
						XFS_ERRTAG_ITOBP_INOTOBP,
						XFS_RANDOM_ITOBP_INOTOBP))) {
			xfs_buf_ioerror(bp, EFSCORRUPTED);
			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
					     mp, dip);
#ifdef DEBUG
			xfs_emerg(mp,
				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
				(unsigned long long)bp->b_bn, i,
				be16_to_cpu(dip->di_magic));
			ASSERT(0);
#endif
		}
	}
	xfs_inobp_check(mp, bp);
}


static void
xfs_inode_buf_read_verify(
	struct xfs_buf	*bp)
{
	xfs_inode_buf_verify(bp);
}

static void
xfs_inode_buf_write_verify(
	struct xfs_buf	*bp)
{
	xfs_inode_buf_verify(bp);
}

const struct xfs_buf_ops xfs_inode_buf_ops = {
	.verify_read = xfs_inode_buf_read_verify,
	.verify_write = xfs_inode_buf_write_verify,
};


/*
 * This routine is called to map an inode to the buffer containing the on-disk
 * version of the inode.  It returns a pointer to the buffer containing the
 * on-disk inode in the bpp parameter, and in the dipp parameter it returns a
 * pointer to the on-disk inode within that buffer.
 *
 * If a non-zero error is returned, then the contents of bpp and dipp are
 * undefined.
 */
int
xfs_imap_to_bp(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	struct xfs_imap		*imap,
	struct xfs_dinode       **dipp,
	struct xfs_buf		**bpp,
	uint			buf_flags,
	uint			iget_flags)
{
	struct xfs_buf		*bp;
	int			error;

	buf_flags |= XBF_UNMAPPED;
	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
				   (int)imap->im_len, buf_flags, &bp,
				   &xfs_inode_buf_ops);
	if (error) {
		if (error == EAGAIN) {
			ASSERT(buf_flags & XBF_TRYLOCK);
			return error;
		}

		if (error == EFSCORRUPTED &&
		    (iget_flags & XFS_IGET_UNTRUSTED))
			return XFS_ERROR(EINVAL);

		xfs_warn(mp, "%s: xfs_trans_read_buf() returned error %d.",
			__func__, error);
		return error;
	}

	*bpp = bp;
	*dipp = (struct xfs_dinode *)xfs_buf_offset(bp, imap->im_boffset);
	return 0;
}

STATIC void
xfs_dinode_from_disk(
	xfs_icdinode_t		*to,
	xfs_dinode_t		*from)
{
	to->di_magic = be16_to_cpu(from->di_magic);
	to->di_mode = be16_to_cpu(from->di_mode);
	to->di_version = from ->di_version;
	to->di_format = from->di_format;
	to->di_onlink = be16_to_cpu(from->di_onlink);
	to->di_uid = be32_to_cpu(from->di_uid);
	to->di_gid = be32_to_cpu(from->di_gid);
	to->di_nlink = be32_to_cpu(from->di_nlink);
	to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
	to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
	to->di_flushiter = be16_to_cpu(from->di_flushiter);
	to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
	to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec);
	to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec);
	to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec);
	to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec);
	to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec);
	to->di_size = be64_to_cpu(from->di_size);
	to->di_nblocks = be64_to_cpu(from->di_nblocks);
	to->di_extsize = be32_to_cpu(from->di_extsize);
	to->di_nextents = be32_to_cpu(from->di_nextents);
	to->di_anextents = be16_to_cpu(from->di_anextents);
	to->di_forkoff = from->di_forkoff;
	to->di_aformat	= from->di_aformat;
	to->di_dmevmask	= be32_to_cpu(from->di_dmevmask);
	to->di_dmstate	= be16_to_cpu(from->di_dmstate);
	to->di_flags	= be16_to_cpu(from->di_flags);
	to->di_gen	= be32_to_cpu(from->di_gen);

	if (to->di_version == 3) {
		to->di_changecount = be64_to_cpu(from->di_changecount);
		to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
		to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
		to->di_flags2 = be64_to_cpu(from->di_flags2);
		to->di_ino = be64_to_cpu(from->di_ino);
		to->di_lsn = be64_to_cpu(from->di_lsn);
		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
		uuid_copy(&to->di_uuid, &from->di_uuid);
	}
}

void
xfs_dinode_to_disk(
	xfs_dinode_t		*to,
	xfs_icdinode_t		*from)
{
	to->di_magic = cpu_to_be16(from->di_magic);
	to->di_mode = cpu_to_be16(from->di_mode);
	to->di_version = from ->di_version;
	to->di_format = from->di_format;
	to->di_onlink = cpu_to_be16(from->di_onlink);
	to->di_uid = cpu_to_be32(from->di_uid);
	to->di_gid = cpu_to_be32(from->di_gid);
	to->di_nlink = cpu_to_be32(from->di_nlink);
	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
	to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
	to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
	to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
	to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
	to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
	to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
	to->di_size = cpu_to_be64(from->di_size);
	to->di_nblocks = cpu_to_be64(from->di_nblocks);
	to->di_extsize = cpu_to_be32(from->di_extsize);
	to->di_nextents = cpu_to_be32(from->di_nextents);
	to->di_anextents = cpu_to_be16(from->di_anextents);
	to->di_forkoff = from->di_forkoff;
	to->di_aformat = from->di_aformat;
	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
	to->di_dmstate = cpu_to_be16(from->di_dmstate);
	to->di_flags = cpu_to_be16(from->di_flags);
	to->di_gen = cpu_to_be32(from->di_gen);

	if (from->di_version == 3) {
		to->di_changecount = cpu_to_be64(from->di_changecount);
		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
		to->di_flags2 = cpu_to_be64(from->di_flags2);
		to->di_ino = cpu_to_be64(from->di_ino);
		to->di_lsn = cpu_to_be64(from->di_lsn);
		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
		uuid_copy(&to->di_uuid, &from->di_uuid);
		to->di_flushiter = 0;
	} else {
		to->di_flushiter = cpu_to_be16(from->di_flushiter);
	}
}

static bool
xfs_dinode_verify(
	struct xfs_mount	*mp,
	struct xfs_inode	*ip,
	struct xfs_dinode	*dip)
{
	if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
		return false;

	/* only version 3 or greater inodes are extensively verified here */
	if (dip->di_version < 3)
		return true;

	if (!xfs_sb_version_hascrc(&mp->m_sb))
		return false;
	if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
			      offsetof(struct xfs_dinode, di_crc)))
		return false;
	if (be64_to_cpu(dip->di_ino) != ip->i_ino)
		return false;
	if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_uuid))
		return false;
	return true;
}

void
xfs_dinode_calc_crc(
	struct xfs_mount	*mp,
	struct xfs_dinode	*dip)
{
	__uint32_t		crc;

	if (dip->di_version < 3)
		return;

	ASSERT(xfs_sb_version_hascrc(&mp->m_sb));
	crc = xfs_start_cksum((char *)dip, mp->m_sb.sb_inodesize,
			      offsetof(struct xfs_dinode, di_crc));
	dip->di_crc = xfs_end_cksum(crc);
}

/*
 * Read the disk inode attributes into the in-core inode structure.
 *
 * For version 5 superblocks, if we are initialising a new inode and we are not
 * utilising the XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new
 * inode core with a random generation number. If we are keeping inodes around,
 * we need to read the inode cluster to get the existing generation number off
 * disk. Further, if we are using version 4 superblocks (i.e. v1/v2 inode
 * format) then log recovery is dependent on the di_flushiter field being
 * initialised from the current on-disk value and hence we must also read the
 * inode off disk.
 */
int
xfs_iread(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_inode_t	*ip,
	uint		iget_flags)
{
	xfs_buf_t	*bp;
	xfs_dinode_t	*dip;
	int		error;

	/*
	 * Fill in the location information in the in-core inode.
	 */
	error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
	if (error)
		return error;

	/* shortcut IO on inode allocation if possible */
	if ((iget_flags & XFS_IGET_CREATE) &&
	    xfs_sb_version_hascrc(&mp->m_sb) &&
	    !(mp->m_flags & XFS_MOUNT_IKEEP)) {
		/* initialise the on-disk inode core */
		memset(&ip->i_d, 0, sizeof(ip->i_d));
		ip->i_d.di_magic = XFS_DINODE_MAGIC;
		ip->i_d.di_gen = prandom_u32();
		if (xfs_sb_version_hascrc(&mp->m_sb)) {
			ip->i_d.di_version = 3;
			ip->i_d.di_ino = ip->i_ino;
			uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid);
		} else
			ip->i_d.di_version = 2;
		return 0;
	}

	/*
	 * Get pointers to the on-disk inode and the buffer containing it.
	 */
	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
	if (error)
		return error;

	/* even unallocated inodes are verified */
	if (!xfs_dinode_verify(mp, ip, dip)) {
		xfs_alert(mp, "%s: validation failed for inode %lld failed",
				__func__, ip->i_ino);

		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, dip);
		error = XFS_ERROR(EFSCORRUPTED);
		goto out_brelse;
	}

	/*
	 * If the on-disk inode is already linked to a directory
	 * entry, copy all of the inode into the in-core inode.
	 * xfs_iformat_fork() handles copying in the inode format
	 * specific information.
	 * Otherwise, just get the truly permanent information.
	 */
	if (dip->di_mode) {
		xfs_dinode_from_disk(&ip->i_d, dip);
		error = xfs_iformat_fork(ip, dip);
		if (error)  {
#ifdef DEBUG
			xfs_alert(mp, "%s: xfs_iformat() returned error %d",
				__func__, error);
#endif /* DEBUG */
			goto out_brelse;
		}
	} else {
		/*
		 * Partial initialisation of the in-core inode. Just the bits
		 * that xfs_ialloc won't overwrite or relies on being correct.
		 */
		ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
		ip->i_d.di_version = dip->di_version;
		ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
		ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);

		if (dip->di_version == 3) {
			ip->i_d.di_ino = be64_to_cpu(dip->di_ino);
			uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid);
		}

		/*
		 * Make sure to pull in the mode here as well in
		 * case the inode is released without being used.
		 * This ensures that xfs_inactive() will see that
		 * the inode is already free and not try to mess
		 * with the uninitialized part of it.
		 */
		ip->i_d.di_mode = 0;
	}

	/*
	 * The inode format changed when we moved the link count and
	 * made it 32 bits long.  If this is an old format inode,
	 * convert it in memory to look like a new one.  If it gets
	 * flushed to disk we will convert back before flushing or
	 * logging it.  We zero out the new projid field and the old link
	 * count field.  We'll handle clearing the pad field (the remains
	 * of the old uuid field) when we actually convert the inode to
	 * the new format. We don't change the version number so that we
	 * can distinguish this from a real new format inode.
	 */
	if (ip->i_d.di_version == 1) {
		ip->i_d.di_nlink = ip->i_d.di_onlink;
		ip->i_d.di_onlink = 0;
		xfs_set_projid(ip, 0);
	}

	ip->i_delayed_blks = 0;

	/*
	 * Mark the buffer containing the inode as something to keep
	 * around for a while.  This helps to keep recently accessed
	 * meta-data in-core longer.
	 */
	xfs_buf_set_ref(bp, XFS_INO_REF);

	/*
	 * Use xfs_trans_brelse() to release the buffer containing the on-disk
	 * inode, because it was acquired with xfs_trans_read_buf() in
	 * xfs_imap_to_bp() above.  If tp is NULL, this is just a normal
	 * brelse().  If we're within a transaction, then xfs_trans_brelse()
	 * will only release the buffer if it is not dirty within the
	 * transaction.  It will be OK to release the buffer in this case,
	 * because inodes on disk are never destroyed and we will be locking the
	 * new in-core inode before putting it in the cache where other
	 * processes can find it.  Thus we don't have to worry about the inode
	 * being changed just because we released the buffer.
	 */
 out_brelse:
	xfs_trans_brelse(tp, bp);
	return error;
}