aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_itable.c
blob: bc92c5306a170afd58ca55945bc9471287933699 (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
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
/*
 * Copyright (c) 2000-2002,2005 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_types.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_ialloc.h"
#include "xfs_itable.h"
#include "xfs_error.h"
#include "xfs_btree.h"
#include "xfs_trace.h"
#include "xfs_icache.h"

STATIC int
xfs_internal_inum(
	xfs_mount_t	*mp,
	xfs_ino_t	ino)
{
	return (ino == mp->m_sb.sb_rbmino || ino == mp->m_sb.sb_rsumino ||
		(xfs_sb_version_hasquota(&mp->m_sb) &&
		 xfs_is_quota_inode(&mp->m_sb, ino)));
}

/*
 * Return stat information for one inode.
 * Return 0 if ok, else errno.
 */
int
xfs_bulkstat_one_int(
	struct xfs_mount	*mp,		/* mount point for filesystem */
	xfs_ino_t		ino,		/* inode to get data for */
	void __user		*buffer,	/* buffer to place output in */
	int			ubsize,		/* size of buffer */
	bulkstat_one_fmt_pf	formatter,	/* formatter, copy to user */
	int			*ubused,	/* bytes used by me */
	int			*stat)		/* BULKSTAT_RV_... */
{
	struct xfs_icdinode	*dic;		/* dinode core info pointer */
	struct xfs_inode	*ip;		/* incore inode pointer */
	struct xfs_bstat	*buf;		/* return buffer */
	int			error = 0;	/* error value */

	*stat = BULKSTAT_RV_NOTHING;

	if (!buffer || xfs_internal_inum(mp, ino))
		return XFS_ERROR(EINVAL);

	buf = kmem_alloc(sizeof(*buf), KM_SLEEP | KM_MAYFAIL);
	if (!buf)
		return XFS_ERROR(ENOMEM);

	error = xfs_iget(mp, NULL, ino,
			 (XFS_IGET_DONTCACHE | XFS_IGET_UNTRUSTED),
			 XFS_ILOCK_SHARED, &ip);
	if (error) {
		*stat = BULKSTAT_RV_NOTHING;
		goto out_free;
	}

	ASSERT(ip != NULL);
	ASSERT(ip->i_imap.im_blkno != 0);

	dic = &ip->i_d;

	/* xfs_iget returns the following without needing
	 * further change.
	 */
	buf->bs_nlink = dic->di_nlink;
	buf->bs_projid_lo = dic->di_projid_lo;
	buf->bs_projid_hi = dic->di_projid_hi;
	buf->bs_ino = ino;
	buf->bs_mode = dic->di_mode;
	buf->bs_uid = dic->di_uid;
	buf->bs_gid = dic->di_gid;
	buf->bs_size = dic->di_size;
	buf->bs_atime.tv_sec = dic->di_atime.t_sec;
	buf->bs_atime.tv_nsec = dic->di_atime.t_nsec;
	buf->bs_mtime.tv_sec = dic->di_mtime.t_sec;
	buf->bs_mtime.tv_nsec = dic->di_mtime.t_nsec;
	buf->bs_ctime.tv_sec = dic->di_ctime.t_sec;
	buf->bs_ctime.tv_nsec = dic->di_ctime.t_nsec;
	buf->bs_xflags = xfs_ip2xflags(ip);
	buf->bs_extsize = dic->di_extsize << mp->m_sb.sb_blocklog;
	buf->bs_extents = dic->di_nextents;
	buf->bs_gen = dic->di_gen;
	memset(buf->bs_pad, 0, sizeof(buf->bs_pad));
	buf->bs_dmevmask = dic->di_dmevmask;
	buf->bs_dmstate = dic->di_dmstate;
	buf->bs_aextents = dic->di_anextents;
	buf->bs_forkoff = XFS_IFORK_BOFF(ip);

	switch (dic->di_format) {
	case XFS_DINODE_FMT_DEV:
		buf->bs_rdev = ip->i_df.if_u2.if_rdev;
		buf->bs_blksize = BLKDEV_IOSIZE;
		buf->bs_blocks = 0;
		break;
	case XFS_DINODE_FMT_LOCAL:
	case XFS_DINODE_FMT_UUID:
		buf->bs_rdev = 0;
		buf->bs_blksize = mp->m_sb.sb_blocksize;
		buf->bs_blocks = 0;
		break;
	case XFS_DINODE_FMT_EXTENTS:
	case XFS_DINODE_FMT_BTREE:
		buf->bs_rdev = 0;
		buf->bs_blksize = mp->m_sb.sb_blocksize;
		buf->bs_blocks = dic->di_nblocks + ip->i_delayed_blks;
		break;
	}
	xfs_iunlock(ip, XFS_ILOCK_SHARED);
	IRELE(ip);

	error = formatter(buffer, ubsize, ubused, buf);

	if (!error)
		*stat = BULKSTAT_RV_DIDONE;

 out_free:
	kmem_free(buf);
	return error;
}

/* Return 0 on success or positive error */
STATIC int
xfs_bulkstat_one_fmt(
	void			__user *ubuffer,
	int			ubsize,
	int			*ubused,
	const xfs_bstat_t	*buffer)
{
	if (ubsize < sizeof(*buffer))
		return XFS_ERROR(ENOMEM);
	if (copy_to_user(ubuffer, buffer, sizeof(*buffer)))
		return XFS_ERROR(EFAULT);
	if (ubused)
		*ubused = sizeof(*buffer);
	return 0;
}

int
xfs_bulkstat_one(
	xfs_mount_t	*mp,		/* mount point for filesystem */
	xfs_ino_t	ino,		/* inode number to get data for */
	void		__user *buffer,	/* buffer to place output in */
	int		ubsize,		/* size of buffer */
	int		*ubused,	/* bytes used by me */
	int		*stat)		/* BULKSTAT_RV_... */
{
	return xfs_bulkstat_one_int(mp, ino, buffer, ubsize,
				    xfs_bulkstat_one_fmt, ubused, stat);
}

#define XFS_BULKSTAT_UBLEFT(ubleft)	((ubleft) >= statstruct_size)

/*
 * Return stat information in bulk (by-inode) for the filesystem.
 */
int					/* error status */
xfs_bulkstat(
	xfs_mount_t		*mp,	/* mount point for filesystem */
	xfs_ino_t		*lastinop, /* last inode returned */
	int			*ubcountp, /* size of buffer/count returned */
	bulkstat_one_pf		formatter, /* func that'd fill a single buf */
	size_t			statstruct_size, /* sizeof struct filling */
	char			__user *ubuffer, /* buffer with inode stats */
	int			*done)	/* 1 if there are more stats to get */
{
	xfs_agblock_t		agbno=0;/* allocation group block number */
	xfs_buf_t		*agbp;	/* agi header buffer */
	xfs_agi_t		*agi;	/* agi header data */
	xfs_agino_t		agino;	/* inode # in allocation group */
	xfs_agnumber_t		agno;	/* allocation group number */
	int			chunkidx; /* current index into inode chunk */
	int			clustidx; /* current index into inode cluster */
	xfs_btree_cur_t		*cur;	/* btree cursor for ialloc btree */
	int			end_of_ag; /* set if we've seen the ag end */
	int			error;	/* error code */
	int                     fmterror;/* bulkstat formatter result */
	int			i;	/* loop index */
	int			icount;	/* count of inodes good in irbuf */
	size_t			irbsize; /* size of irec buffer in bytes */
	xfs_ino_t		ino;	/* inode number (filesystem) */
	xfs_inobt_rec_incore_t	*irbp;	/* current irec buffer pointer */
	xfs_inobt_rec_incore_t	*irbuf;	/* start of irec buffer */
	xfs_inobt_rec_incore_t	*irbufend; /* end of good irec buffer entries */
	xfs_ino_t		lastino; /* last inode number returned */
	int			nbcluster; /* # of blocks in a cluster */
	int			nicluster; /* # of inodes in a cluster */
	int			nimask;	/* mask for inode clusters */
	int			nirbuf;	/* size of irbuf */
	int			rval;	/* return value error code */
	int			tmp;	/* result value from btree calls */
	int			ubcount; /* size of user's buffer */
	int			ubleft;	/* bytes left in user's buffer */
	char			__user *ubufp;	/* pointer into user's buffer */
	int			ubelem;	/* spaces used in user's buffer */
	int			ubused;	/* bytes used by formatter */
	xfs_buf_t		*bp;	/* ptr to on-disk inode cluster buf */

	/*
	 * Get the last inode value, see if there's nothing to do.
	 */
	ino = (xfs_ino_t)*lastinop;
	lastino = ino;
	agno = XFS_INO_TO_AGNO(mp, ino);
	agino = XFS_INO_TO_AGINO(mp, ino);
	if (agno >= mp->m_sb.sb_agcount ||
	    ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
		*done = 1;
		*ubcountp = 0;
		return 0;
	}
	if (!ubcountp || *ubcountp <= 0) {
		return EINVAL;
	}
	ubcount = *ubcountp; /* statstruct's */
	ubleft = ubcount * statstruct_size; /* bytes */
	*ubcountp = ubelem = 0;
	*done = 0;
	fmterror = 0;
	ubufp = ubuffer;
	nicluster = mp->m_sb.sb_blocksize >= XFS_INODE_CLUSTER_SIZE(mp) ?
		mp->m_sb.sb_inopblock :
		(XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog);
	nimask = ~(nicluster - 1);
	nbcluster = nicluster >> mp->m_sb.sb_inopblog;
	irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
	if (!irbuf)
		return ENOMEM;

	nirbuf = irbsize / sizeof(*irbuf);

	/*
	 * Loop over the allocation groups, starting from the last
	 * inode returned; 0 means start of the allocation group.
	 */
	rval = 0;
	while (XFS_BULKSTAT_UBLEFT(ubleft) && agno < mp->m_sb.sb_agcount) {
		cond_resched();
		bp = NULL;
		error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
		if (error) {
			/*
			 * Skip this allocation group and go to the next one.
			 */
			agno++;
			agino = 0;
			continue;
		}
		agi = XFS_BUF_TO_AGI(agbp);
		/*
		 * Allocate and initialize a btree cursor for ialloc btree.
		 */
		cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
		irbp = irbuf;
		irbufend = irbuf + nirbuf;
		end_of_ag = 0;
		/*
		 * If we're returning in the middle of an allocation group,
		 * we need to get the remainder of the chunk we're in.
		 */
		if (agino > 0) {
			xfs_inobt_rec_incore_t r;

			/*
			 * Lookup the inode chunk that this inode lives in.
			 */
			error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE,
						 &tmp);
			if (!error &&	/* no I/O error */
			    tmp &&	/* lookup succeeded */
					/* got the record, should always work */
			    !(error = xfs_inobt_get_rec(cur, &r, &i)) &&
			    i == 1 &&
					/* this is the right chunk */
			    agino < r.ir_startino + XFS_INODES_PER_CHUNK &&
					/* lastino was not last in chunk */
			    (chunkidx = agino - r.ir_startino + 1) <
				    XFS_INODES_PER_CHUNK &&
					/* there are some left allocated */
			    xfs_inobt_maskn(chunkidx,
				    XFS_INODES_PER_CHUNK - chunkidx) &
				    ~r.ir_free) {
				/*
				 * Grab the chunk record.  Mark all the
				 * uninteresting inodes (because they're
				 * before our start point) free.
				 */
				for (i = 0; i < chunkidx; i++) {
					if (XFS_INOBT_MASK(i) & ~r.ir_free)
						r.ir_freecount++;
				}
				r.ir_free |= xfs_inobt_maskn(0, chunkidx);
				irbp->ir_startino = r.ir_startino;
				irbp->ir_freecount = r.ir_freecount;
				irbp->ir_free = r.ir_free;
				irbp++;
				agino = r.ir_startino + XFS_INODES_PER_CHUNK;
				icount = XFS_INODES_PER_CHUNK - r.ir_freecount;
			} else {
				/*
				 * If any of those tests failed, bump the
				 * inode number (just in case).
				 */
				agino++;
				icount = 0;
			}
			/*
			 * In any case, increment to the next record.
			 */
			if (!error)
				error = xfs_btree_increment(cur, 0, &tmp);
		} else {
			/*
			 * Start of ag.  Lookup the first inode chunk.
			 */
			error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &tmp);
			icount = 0;
		}
		/*
		 * Loop through inode btree records in this ag,
		 * until we run out of inodes or space in the buffer.
		 */
		while (irbp < irbufend && icount < ubcount) {
			xfs_inobt_rec_incore_t r;

			/*
			 * Loop as long as we're unable to read the
			 * inode btree.
			 */
			while (error) {
				agino += XFS_INODES_PER_CHUNK;
				if (XFS_AGINO_TO_AGBNO(mp, agino) >=
						be32_to_cpu(agi->agi_length))
					break;
				error = xfs_inobt_lookup(cur, agino,
							 XFS_LOOKUP_GE, &tmp);
				cond_resched();
			}
			/*
			 * If ran off the end of the ag either with an error,
			 * or the normal way, set end and stop collecting.
			 */
			if (error) {
				end_of_ag = 1;
				break;
			}

			error = xfs_inobt_get_rec(cur, &r, &i);
			if (error || i == 0) {
				end_of_ag = 1;
				break;
			}

			/*
			 * If this chunk has any allocated inodes, save it.
			 * Also start read-ahead now for this chunk.
			 */
			if (r.ir_freecount < XFS_INODES_PER_CHUNK) {
				struct blk_plug	plug;
				/*
				 * Loop over all clusters in the next chunk.
				 * Do a readahead if there are any allocated
				 * inodes in that cluster.
				 */
				blk_start_plug(&plug);
				agbno = XFS_AGINO_TO_AGBNO(mp, r.ir_startino);
				for (chunkidx = 0;
				     chunkidx < XFS_INODES_PER_CHUNK;
				     chunkidx += nicluster,
				     agbno += nbcluster) {
					if (xfs_inobt_maskn(chunkidx, nicluster)
							& ~r.ir_free)
						xfs_btree_reada_bufs(mp, agno,
							agbno, nbcluster,
							&xfs_inode_buf_ops);
				}
				blk_finish_plug(&plug);
				irbp->ir_startino = r.ir_startino;
				irbp->ir_freecount = r.ir_freecount;
				irbp->ir_free = r.ir_free;
				irbp++;
				icount += XFS_INODES_PER_CHUNK - r.ir_freecount;
			}
			/*
			 * Set agino to after this chunk and bump the cursor.
			 */
			agino = r.ir_startino + XFS_INODES_PER_CHUNK;
			error = xfs_btree_increment(cur, 0, &tmp);
			cond_resched();
		}
		/*
		 * Drop the btree buffers and the agi buffer.
		 * We can't hold any of the locks these represent
		 * when calling iget.
		 */
		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
		xfs_buf_relse(agbp);
		/*
		 * Now format all the good inodes into the user's buffer.
		 */
		irbufend = irbp;
		for (irbp = irbuf;
		     irbp < irbufend && XFS_BULKSTAT_UBLEFT(ubleft); irbp++) {
			/*
			 * Now process this chunk of inodes.
			 */
			for (agino = irbp->ir_startino, chunkidx = clustidx = 0;
			     XFS_BULKSTAT_UBLEFT(ubleft) &&
				irbp->ir_freecount < XFS_INODES_PER_CHUNK;
			     chunkidx++, clustidx++, agino++) {
				ASSERT(chunkidx < XFS_INODES_PER_CHUNK);
				/*
				 * Recompute agbno if this is the
				 * first inode of the cluster.
				 *
				 * Careful with clustidx.   There can be
				 * multiple clusters per chunk, a single
				 * cluster per chunk or a cluster that has
				 * inodes represented from several different
				 * chunks (if blocksize is large).
				 *
				 * Because of this, the starting clustidx is
				 * initialized to zero in this loop but must
				 * later be reset after reading in the cluster
				 * buffer.
				 */
				if ((chunkidx & (nicluster - 1)) == 0) {
					agbno = XFS_AGINO_TO_AGBNO(mp,
							irbp->ir_startino) +
						((chunkidx & nimask) >>
						 mp->m_sb.sb_inopblog);
				}
				ino = XFS_AGINO_TO_INO(mp, agno, agino);
				/*
				 * Skip if this inode is free.
				 */
				if (XFS_INOBT_MASK(chunkidx) & irbp->ir_free) {
					lastino = ino;
					continue;
				}
				/*
				 * Count used inodes as free so we can tell
				 * when the chunk is used up.
				 */
				irbp->ir_freecount++;

				/*
				 * Get the inode and fill in a single buffer.
				 */
				ubused = statstruct_size;
				error = formatter(mp, ino, ubufp, ubleft,
						  &ubused, &fmterror);
				if (fmterror == BULKSTAT_RV_NOTHING) {
					if (error && error != ENOENT &&
						error != EINVAL) {
						ubleft = 0;
						rval = error;
						break;
					}
					lastino = ino;
					continue;
				}
				if (fmterror == BULKSTAT_RV_GIVEUP) {
					ubleft = 0;
					ASSERT(error);
					rval = error;
					break;
				}
				if (ubufp)
					ubufp += ubused;
				ubleft -= ubused;
				ubelem++;
				lastino = ino;
			}

			cond_resched();
		}

		if (bp)
			xfs_buf_relse(bp);

		/*
		 * Set up for the next loop iteration.
		 */
		if (XFS_BULKSTAT_UBLEFT(ubleft)) {
			if (end_of_ag) {
				agno++;
				agino = 0;
			} else
				agino = XFS_INO_TO_AGINO(mp, lastino);
		} else
			break;
	}
	/*
	 * Done, we're either out of filesystem or space to put the data.
	 */
	kmem_free_large(irbuf);
	*ubcountp = ubelem;
	/*
	 * Found some inodes, return them now and return the error next time.
	 */
	if (ubelem)
		rval = 0;
	if (agno >= mp->m_sb.sb_agcount) {
		/*
		 * If we ran out of filesystem, mark lastino as off
		 * the end of the filesystem, so the next call
		 * will return immediately.
		 */
		*lastinop = (xfs_ino_t)XFS_AGINO_TO_INO(mp, agno, 0);
		*done = 1;
	} else
		*lastinop = (xfs_ino_t)lastino;

	return rval;
}

/*
 * Return stat information in bulk (by-inode) for the filesystem.
 * Special case for non-sequential one inode bulkstat.
 */
int					/* error status */
xfs_bulkstat_single(
	xfs_mount_t		*mp,	/* mount point for filesystem */
	xfs_ino_t		*lastinop, /* inode to return */
	char			__user *buffer, /* buffer with inode stats */
	int			*done)	/* 1 if there are more stats to get */
{
	int			count;	/* count value for bulkstat call */
	int			error;	/* return value */
	xfs_ino_t		ino;	/* filesystem inode number */
	int			res;	/* result from bs1 */

	/*
	 * note that requesting valid inode numbers which are not allocated
	 * to inodes will most likely cause xfs_imap_to_bp to generate warning
	 * messages about bad magic numbers. This is ok. The fact that
	 * the inode isn't actually an inode is handled by the
	 * error check below. Done this way to make the usual case faster
	 * at the expense of the error case.
	 */

	ino = (xfs_ino_t)*lastinop;
	error = xfs_bulkstat_one(mp, ino, buffer, sizeof(xfs_bstat_t), 0, &res);
	if (error) {
		/*
		 * Special case way failed, do it the "long" way
		 * to see if that works.
		 */
		(*lastinop)--;
		count = 1;
		if (xfs_bulkstat(mp, lastinop, &count, xfs_bulkstat_one,
				sizeof(xfs_bstat_t), buffer, done))
			return error;
		if (count == 0 || (xfs_ino_t)*lastinop != ino)
			return error == EFSCORRUPTED ?
				XFS_ERROR(EINVAL) : error;
		else
			return 0;
	}
	*done = 0;
	return 0;
}

int
xfs_inumbers_fmt(
	void			__user *ubuffer, /* buffer to write to */
	const xfs_inogrp_t	*buffer,	/* buffer to read from */
	long			count,		/* # of elements to read */
	long			*written)	/* # of bytes written */
{
	if (copy_to_user(ubuffer, buffer, count * sizeof(*buffer)))
		return -EFAULT;
	*written = count * sizeof(*buffer);
	return 0;
}

/*
 * Return inode number table for the filesystem.
 */
int					/* error status */
xfs_inumbers(
	xfs_mount_t	*mp,		/* mount point for filesystem */
	xfs_ino_t	*lastino,	/* last inode returned */
	int		*count,		/* size of buffer/count returned */
	void		__user *ubuffer,/* buffer with inode descriptions */
	inumbers_fmt_pf	formatter)
{
	xfs_buf_t	*agbp;
	xfs_agino_t	agino;
	xfs_agnumber_t	agno;
	int		bcount;
	xfs_inogrp_t	*buffer;
	int		bufidx;
	xfs_btree_cur_t	*cur;
	int		error;
	xfs_inobt_rec_incore_t r;
	int		i;
	xfs_ino_t	ino;
	int		left;
	int		tmp;

	ino = (xfs_ino_t)*lastino;
	agno = XFS_INO_TO_AGNO(mp, ino);
	agino = XFS_INO_TO_AGINO(mp, ino);
	left = *count;
	*count = 0;
	bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
	buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
	error = bufidx = 0;
	cur = NULL;
	agbp = NULL;
	while (left > 0 && agno < mp->m_sb.sb_agcount) {
		if (agbp == NULL) {
			error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
			if (error) {
				/*
				 * If we can't read the AGI of this ag,
				 * then just skip to the next one.
				 */
				ASSERT(cur == NULL);
				agbp = NULL;
				agno++;
				agino = 0;
				continue;
			}
			cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
			error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_GE,
						 &tmp);
			if (error) {
				xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
				cur = NULL;
				xfs_buf_relse(agbp);
				agbp = NULL;
				/*
				 * Move up the last inode in the current
				 * chunk.  The lookup_ge will always get
				 * us the first inode in the next chunk.
				 */
				agino += XFS_INODES_PER_CHUNK - 1;
				continue;
			}
		}
		error = xfs_inobt_get_rec(cur, &r, &i);
		if (error || i == 0) {
			xfs_buf_relse(agbp);
			agbp = NULL;
			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
			cur = NULL;
			agno++;
			agino = 0;
			continue;
		}
		agino = r.ir_startino + XFS_INODES_PER_CHUNK - 1;
		buffer[bufidx].xi_startino =
			XFS_AGINO_TO_INO(mp, agno, r.ir_startino);
		buffer[bufidx].xi_alloccount =
			XFS_INODES_PER_CHUNK - r.ir_freecount;
		buffer[bufidx].xi_allocmask = ~r.ir_free;
		bufidx++;
		left--;
		if (bufidx == bcount) {
			long written;
			if (formatter(ubuffer, buffer, bufidx, &written)) {
				error = XFS_ERROR(EFAULT);
				break;
			}
			ubuffer += written;
			*count += bufidx;
			bufidx = 0;
		}
		if (left) {
			error = xfs_btree_increment(cur, 0, &tmp);
			if (error) {
				xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
				cur = NULL;
				xfs_buf_relse(agbp);
				agbp = NULL;
				/*
				 * The agino value has already been bumped.
				 * Just try to skip up to it.
				 */
				agino += XFS_INODES_PER_CHUNK;
				continue;
			}
		}
	}
	if (!error) {
		if (bufidx) {
			long written;
			if (formatter(ubuffer, buffer, bufidx, &written))
				error = XFS_ERROR(EFAULT);
			else
				*count += bufidx;
		}
		*lastino = XFS_AGINO_TO_INO(mp, agno, agino);
	}
	kmem_free(buffer);
	if (cur)
		xfs_btree_del_cursor(cur, (error ? XFS_BTREE_ERROR :
					   XFS_BTREE_NOERROR));
	if (agbp)
		xfs_buf_relse(agbp);
	return error;
}