aboutsummaryrefslogtreecommitdiff
path: root/fs/afs/dir.c
blob: ba2b458b36d15e2e5757046586e72160f51e23cb (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
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
/* dir.c: AFS filesystem directory handling
 *
 * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * 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; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/ctype.h>
#include <linux/sched.h>
#include <linux/dns_resolver.h>
#include "internal.h"

static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
				 unsigned int flags);
static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
					 unsigned int flags);
static int afs_dir_open(struct inode *inode, struct file *file);
static int afs_readdir(struct file *file, struct dir_context *ctx);
static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
static int afs_d_delete(const struct dentry *dentry);
static void afs_d_release(struct dentry *dentry);
static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen,
				  loff_t fpos, u64 ino, unsigned dtype);
static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
		      bool excl);
static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
static int afs_rmdir(struct inode *dir, struct dentry *dentry);
static int afs_unlink(struct inode *dir, struct dentry *dentry);
static int afs_link(struct dentry *from, struct inode *dir,
		    struct dentry *dentry);
static int afs_symlink(struct inode *dir, struct dentry *dentry,
		       const char *content);
static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
		      struct inode *new_dir, struct dentry *new_dentry,
		      unsigned int flags);

const struct file_operations afs_dir_file_operations = {
	.open		= afs_dir_open,
	.release	= afs_release,
	.iterate_shared	= afs_readdir,
	.lock		= afs_lock,
	.llseek		= generic_file_llseek,
};

const struct inode_operations afs_dir_inode_operations = {
	.create		= afs_create,
	.lookup		= afs_lookup,
	.link		= afs_link,
	.unlink		= afs_unlink,
	.symlink	= afs_symlink,
	.mkdir		= afs_mkdir,
	.rmdir		= afs_rmdir,
	.rename		= afs_rename,
	.permission	= afs_permission,
	.getattr	= afs_getattr,
	.setattr	= afs_setattr,
	.listxattr	= afs_listxattr,
};

const struct file_operations afs_dynroot_file_operations = {
	.open		= dcache_dir_open,
	.release	= dcache_dir_close,
	.iterate_shared	= dcache_readdir,
	.llseek		= dcache_dir_lseek,
};

const struct inode_operations afs_dynroot_inode_operations = {
	.lookup		= afs_dynroot_lookup,
};

const struct dentry_operations afs_fs_dentry_operations = {
	.d_revalidate	= afs_d_revalidate,
	.d_delete	= afs_d_delete,
	.d_release	= afs_d_release,
	.d_automount	= afs_d_automount,
};

#define AFS_DIR_HASHTBL_SIZE	128
#define AFS_DIR_DIRENT_SIZE	32
#define AFS_DIRENT_PER_BLOCK	64

union afs_dirent {
	struct {
		uint8_t		valid;
		uint8_t		unused[1];
		__be16		hash_next;
		__be32		vnode;
		__be32		unique;
		uint8_t		name[16];
		uint8_t		overflow[4];	/* if any char of the name (inc
						 * NUL) reaches here, consume
						 * the next dirent too */
	} u;
	uint8_t	extended_name[32];
};

/* AFS directory page header (one at the beginning of every 2048-byte chunk) */
struct afs_dir_pagehdr {
	__be16		npages;
	__be16		magic;
#define AFS_DIR_MAGIC htons(1234)
	uint8_t		nentries;
	uint8_t		bitmap[8];
	uint8_t		pad[19];
};

/* directory block layout */
union afs_dir_block {

	struct afs_dir_pagehdr pagehdr;

	struct {
		struct afs_dir_pagehdr	pagehdr;
		uint8_t			alloc_ctrs[128];
		/* dir hash table */
		uint16_t		hashtable[AFS_DIR_HASHTBL_SIZE];
	} hdr;

	union afs_dirent dirents[AFS_DIRENT_PER_BLOCK];
};

/* layout on a linux VM page */
struct afs_dir_page {
	union afs_dir_block blocks[PAGE_SIZE / sizeof(union afs_dir_block)];
};

struct afs_lookup_cookie {
	struct dir_context ctx;
	struct afs_fid	fid;
	struct qstr name;
	int		found;
};

/*
 * check that a directory page is valid
 */
bool afs_dir_check_page(struct inode *dir, struct page *page)
{
	struct afs_dir_page *dbuf;
	struct afs_vnode *vnode = AFS_FS_I(dir);
	loff_t latter, i_size, off;
	int tmp, qty;

#if 0
	/* check the page count */
	qty = desc.size / sizeof(dbuf->blocks[0]);
	if (qty == 0)
		goto error;

	if (page->index == 0 && qty != ntohs(dbuf->blocks[0].pagehdr.npages)) {
		printk("kAFS: %s(%lu): wrong number of dir blocks %d!=%hu\n",
		       __func__, dir->i_ino, qty,
		       ntohs(dbuf->blocks[0].pagehdr.npages));
		goto error;
	}
#endif

	/* Determine how many magic numbers there should be in this page, but
	 * we must take care because the directory may change size under us.
	 */
	off = page_offset(page);
	i_size = i_size_read(dir);
	if (i_size <= off)
		goto checked;

	latter = i_size - off;
	if (latter >= PAGE_SIZE)
		qty = PAGE_SIZE;
	else
		qty = latter;
	qty /= sizeof(union afs_dir_block);

	/* check them */
	dbuf = page_address(page);
	for (tmp = 0; tmp < qty; tmp++) {
		if (dbuf->blocks[tmp].pagehdr.magic != AFS_DIR_MAGIC) {
			printk("kAFS: %s(%lx): bad magic %d/%d is %04hx\n",
			       __func__, dir->i_ino, tmp, qty,
			       ntohs(dbuf->blocks[tmp].pagehdr.magic));
			trace_afs_dir_check_failed(vnode, off, i_size);
			goto error;
		}
	}

checked:
	SetPageChecked(page);
	return true;

error:
	SetPageError(page);
	return false;
}

/*
 * discard a page cached in the pagecache
 */
static inline void afs_dir_put_page(struct page *page)
{
	kunmap(page);
	unlock_page(page);
	put_page(page);
}

/*
 * get a page into the pagecache
 */
static struct page *afs_dir_get_page(struct inode *dir, unsigned long index,
				     struct key *key)
{
	struct page *page;
	_enter("{%lu},%lu", dir->i_ino, index);

	page = read_cache_page(dir->i_mapping, index, afs_page_filler, key);
	if (!IS_ERR(page)) {
		lock_page(page);
		kmap(page);
		if (unlikely(!PageChecked(page))) {
			if (PageError(page))
				goto fail;
		}
	}
	return page;

fail:
	afs_dir_put_page(page);
	_leave(" = -EIO");
	return ERR_PTR(-EIO);
}

/*
 * open an AFS directory file
 */
static int afs_dir_open(struct inode *inode, struct file *file)
{
	_enter("{%lu}", inode->i_ino);

	BUILD_BUG_ON(sizeof(union afs_dir_block) != 2048);
	BUILD_BUG_ON(sizeof(union afs_dirent) != 32);

	if (test_bit(AFS_VNODE_DELETED, &AFS_FS_I(inode)->flags))
		return -ENOENT;

	return afs_open(inode, file);
}

/*
 * deal with one block in an AFS directory
 */
static int afs_dir_iterate_block(struct dir_context *ctx,
				 union afs_dir_block *block,
				 unsigned blkoff)
{
	union afs_dirent *dire;
	unsigned offset, next, curr;
	size_t nlen;
	int tmp;

	_enter("%u,%x,%p,,",(unsigned)ctx->pos,blkoff,block);

	curr = (ctx->pos - blkoff) / sizeof(union afs_dirent);

	/* walk through the block, an entry at a time */
	for (offset = AFS_DIRENT_PER_BLOCK - block->pagehdr.nentries;
	     offset < AFS_DIRENT_PER_BLOCK;
	     offset = next
	     ) {
		next = offset + 1;

		/* skip entries marked unused in the bitmap */
		if (!(block->pagehdr.bitmap[offset / 8] &
		      (1 << (offset % 8)))) {
			_debug("ENT[%zu.%u]: unused",
			       blkoff / sizeof(union afs_dir_block), offset);
			if (offset >= curr)
				ctx->pos = blkoff +
					next * sizeof(union afs_dirent);
			continue;
		}

		/* got a valid entry */
		dire = &block->dirents[offset];
		nlen = strnlen(dire->u.name,
			       sizeof(*block) -
			       offset * sizeof(union afs_dirent));

		_debug("ENT[%zu.%u]: %s %zu \"%s\"",
		       blkoff / sizeof(union afs_dir_block), offset,
		       (offset < curr ? "skip" : "fill"),
		       nlen, dire->u.name);

		/* work out where the next possible entry is */
		for (tmp = nlen; tmp > 15; tmp -= sizeof(union afs_dirent)) {
			if (next >= AFS_DIRENT_PER_BLOCK) {
				_debug("ENT[%zu.%u]:"
				       " %u travelled beyond end dir block"
				       " (len %u/%zu)",
				       blkoff / sizeof(union afs_dir_block),
				       offset, next, tmp, nlen);
				return -EIO;
			}
			if (!(block->pagehdr.bitmap[next / 8] &
			      (1 << (next % 8)))) {
				_debug("ENT[%zu.%u]:"
				       " %u unmarked extension (len %u/%zu)",
				       blkoff / sizeof(union afs_dir_block),
				       offset, next, tmp, nlen);
				return -EIO;
			}

			_debug("ENT[%zu.%u]: ext %u/%zu",
			       blkoff / sizeof(union afs_dir_block),
			       next, tmp, nlen);
			next++;
		}

		/* skip if starts before the current position */
		if (offset < curr)
			continue;

		/* found the next entry */
		if (!dir_emit(ctx, dire->u.name, nlen,
			      ntohl(dire->u.vnode),
			      ctx->actor == afs_lookup_filldir ?
			      ntohl(dire->u.unique) : DT_UNKNOWN)) {
			_leave(" = 0 [full]");
			return 0;
		}

		ctx->pos = blkoff + next * sizeof(union afs_dirent);
	}

	_leave(" = 1 [more]");
	return 1;
}

/*
 * iterate through the data blob that lists the contents of an AFS directory
 */
static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
			   struct key *key)
{
	union afs_dir_block *dblock;
	struct afs_dir_page *dbuf;
	struct page *page;
	unsigned blkoff, limit;
	int ret;

	_enter("{%lu},%u,,", dir->i_ino, (unsigned)ctx->pos);

	if (test_bit(AFS_VNODE_DELETED, &AFS_FS_I(dir)->flags)) {
		_leave(" = -ESTALE");
		return -ESTALE;
	}

	/* round the file position up to the next entry boundary */
	ctx->pos += sizeof(union afs_dirent) - 1;
	ctx->pos &= ~(sizeof(union afs_dirent) - 1);

	/* walk through the blocks in sequence */
	ret = 0;
	while (ctx->pos < dir->i_size) {
		blkoff = ctx->pos & ~(sizeof(union afs_dir_block) - 1);

		/* fetch the appropriate page from the directory */
		page = afs_dir_get_page(dir, blkoff / PAGE_SIZE, key);
		if (IS_ERR(page)) {
			ret = PTR_ERR(page);
			break;
		}

		limit = blkoff & ~(PAGE_SIZE - 1);

		dbuf = page_address(page);

		/* deal with the individual blocks stashed on this page */
		do {
			dblock = &dbuf->blocks[(blkoff % PAGE_SIZE) /
					       sizeof(union afs_dir_block)];
			ret = afs_dir_iterate_block(ctx, dblock, blkoff);
			if (ret != 1) {
				afs_dir_put_page(page);
				goto out;
			}

			blkoff += sizeof(union afs_dir_block);

		} while (ctx->pos < dir->i_size && blkoff < limit);

		afs_dir_put_page(page);
		ret = 0;
	}

out:
	_leave(" = %d", ret);
	return ret;
}

/*
 * read an AFS directory
 */
static int afs_readdir(struct file *file, struct dir_context *ctx)
{
	return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file));
}

/*
 * search the directory for a name
 * - if afs_dir_iterate_block() spots this function, it'll pass the FID
 *   uniquifier through dtype
 */
static int afs_lookup_filldir(struct dir_context *ctx, const char *name,
			      int nlen, loff_t fpos, u64 ino, unsigned dtype)
{
	struct afs_lookup_cookie *cookie =
		container_of(ctx, struct afs_lookup_cookie, ctx);

	_enter("{%s,%u},%s,%u,,%llu,%u",
	       cookie->name.name, cookie->name.len, name, nlen,
	       (unsigned long long) ino, dtype);

	/* insanity checks first */
	BUILD_BUG_ON(sizeof(union afs_dir_block) != 2048);
	BUILD_BUG_ON(sizeof(union afs_dirent) != 32);

	if (cookie->name.len != nlen ||
	    memcmp(cookie->name.name, name, nlen) != 0) {
		_leave(" = 0 [no]");
		return 0;
	}

	cookie->fid.vnode = ino;
	cookie->fid.unique = dtype;
	cookie->found = 1;

	_leave(" = -1 [found]");
	return -1;
}

/*
 * do a lookup in a directory
 * - just returns the FID the dentry name maps to if found
 */
static int afs_do_lookup(struct inode *dir, struct dentry *dentry,
			 struct afs_fid *fid, struct key *key)
{
	struct afs_super_info *as = dir->i_sb->s_fs_info;
	struct afs_lookup_cookie cookie = {
		.ctx.actor = afs_lookup_filldir,
		.name = dentry->d_name,
		.fid.vid = as->volume->vid
	};
	int ret;

	_enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry);

	/* search the directory */
	ret = afs_dir_iterate(dir, &cookie.ctx, key);
	if (ret < 0) {
		_leave(" = %d [iter]", ret);
		return ret;
	}

	ret = -ENOENT;
	if (!cookie.found) {
		_leave(" = -ENOENT [not found]");
		return -ENOENT;
	}

	*fid = cookie.fid;
	_leave(" = 0 { vn=%u u=%u }", fid->vnode, fid->unique);
	return 0;
}

/*
 * Probe to see if a cell may exist.  This prevents positive dentries from
 * being created unnecessarily.
 */
static int afs_probe_cell_name(struct dentry *dentry)
{
	struct afs_cell *cell;
	const char *name = dentry->d_name.name;
	size_t len = dentry->d_name.len;
	int ret;

	/* Names prefixed with a dot are R/W mounts. */
	if (name[0] == '.') {
		if (len == 1)
			return -EINVAL;
		name++;
		len--;
	}

	cell = afs_lookup_cell_rcu(afs_d2net(dentry), name, len);
	if (!IS_ERR(cell)) {
		afs_put_cell(afs_d2net(dentry), cell);
		return 0;
	}

	ret = dns_query("afsdb", name, len, "ipv4", NULL, NULL);
	if (ret == -ENODATA)
		ret = -EDESTADDRREQ;
	return ret;
}

/*
 * Try to auto mount the mountpoint with pseudo directory, if the autocell
 * operation is setted.
 */
static struct inode *afs_try_auto_mntpt(struct dentry *dentry,
					struct inode *dir, struct afs_fid *fid)
{
	struct afs_vnode *vnode = AFS_FS_I(dir);
	struct inode *inode;
	int ret = -ENOENT;

	_enter("%p{%pd}, {%x:%u}",
	       dentry, dentry, vnode->fid.vid, vnode->fid.vnode);

	if (!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags))
		goto out;

	ret = afs_probe_cell_name(dentry);
	if (ret < 0)
		goto out;

	inode = afs_iget_pseudo_dir(dir->i_sb, false);
	if (IS_ERR(inode)) {
		ret = PTR_ERR(inode);
		goto out;
	}

	*fid = AFS_FS_I(inode)->fid;
	_leave("= %p", inode);
	return inode;

out:
	_leave("= %d", ret);
	return ERR_PTR(ret);
}

/*
 * look up an entry in a directory
 */
static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
				 unsigned int flags)
{
	struct afs_vnode *vnode;
	struct afs_fid fid;
	struct inode *inode;
	struct key *key;
	int ret;

	vnode = AFS_FS_I(dir);

	_enter("{%x:%u},%p{%pd},",
	       vnode->fid.vid, vnode->fid.vnode, dentry, dentry);

	ASSERTCMP(d_inode(dentry), ==, NULL);

	if (dentry->d_name.len >= AFSNAMEMAX) {
		_leave(" = -ENAMETOOLONG");
		return ERR_PTR(-ENAMETOOLONG);
	}

	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
		_leave(" = -ESTALE");
		return ERR_PTR(-ESTALE);
	}

	key = afs_request_key(vnode->volume->cell);
	if (IS_ERR(key)) {
		_leave(" = %ld [key]", PTR_ERR(key));
		return ERR_CAST(key);
	}

	ret = afs_validate(vnode, key);
	if (ret < 0) {
		key_put(key);
		_leave(" = %d [val]", ret);
		return ERR_PTR(ret);
	}

	ret = afs_do_lookup(dir, dentry, &fid, key);
	if (ret < 0) {
		if (ret == -ENOENT) {
			inode = afs_try_auto_mntpt(dentry, dir, &fid);
			if (!IS_ERR(inode)) {
				key_put(key);
				goto success;
			}

			ret = PTR_ERR(inode);
		}

		key_put(key);
		if (ret == -ENOENT) {
			d_add(dentry, NULL);
			_leave(" = NULL [negative]");
			return NULL;
		}
		_leave(" = %d [do]", ret);
		return ERR_PTR(ret);
	}
	dentry->d_fsdata = (void *)(unsigned long) vnode->status.data_version;

	/* instantiate the dentry */
	inode = afs_iget(dir->i_sb, key, &fid, NULL, NULL, NULL);
	key_put(key);
	if (IS_ERR(inode)) {
		_leave(" = %ld", PTR_ERR(inode));
		return ERR_CAST(inode);
	}

success:
	d_add(dentry, inode);
	_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%u }",
	       fid.vnode,
	       fid.unique,
	       d_inode(dentry)->i_ino,
	       d_inode(dentry)->i_generation);

	return NULL;
}

/*
 * Look up an entry in a dynroot directory.
 */
static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
					 unsigned int flags)
{
	struct afs_vnode *vnode;
	struct afs_fid fid;
	struct inode *inode;
	int ret;

	vnode = AFS_FS_I(dir);

	_enter("%pd", dentry);

	ASSERTCMP(d_inode(dentry), ==, NULL);

	if (dentry->d_name.len >= AFSNAMEMAX) {
		_leave(" = -ENAMETOOLONG");
		return ERR_PTR(-ENAMETOOLONG);
	}

	inode = afs_try_auto_mntpt(dentry, dir, &fid);
	if (IS_ERR(inode)) {
		ret = PTR_ERR(inode);
		if (ret == -ENOENT) {
			d_add(dentry, NULL);
			_leave(" = NULL [negative]");
			return NULL;
		}
		_leave(" = %d [do]", ret);
		return ERR_PTR(ret);
	}

	d_add(dentry, inode);
	_leave(" = 0 { ino=%lu v=%u }",
	       d_inode(dentry)->i_ino, d_inode(dentry)->i_generation);
	return NULL;
}

/*
 * check that a dentry lookup hit has found a valid entry
 * - NOTE! the hit can be a negative hit too, so we can't assume we have an
 *   inode
 */
static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
	struct afs_super_info *as = dentry->d_sb->s_fs_info;
	struct afs_vnode *vnode, *dir;
	struct afs_fid uninitialized_var(fid);
	struct dentry *parent;
	struct inode *inode;
	struct key *key;
	void *dir_version;
	int ret;

	if (flags & LOOKUP_RCU)
		return -ECHILD;

	if (as->dyn_root)
		return 1;

	if (d_really_is_positive(dentry)) {
		vnode = AFS_FS_I(d_inode(dentry));
		_enter("{v={%x:%u} n=%pd fl=%lx},",
		       vnode->fid.vid, vnode->fid.vnode, dentry,
		       vnode->flags);
	} else {
		_enter("{neg n=%pd}", dentry);
	}

	key = afs_request_key(AFS_FS_S(dentry->d_sb)->volume->cell);
	if (IS_ERR(key))
		key = NULL;

	if (d_really_is_positive(dentry)) {
		inode = d_inode(dentry);
		if (inode) {
			vnode = AFS_FS_I(inode);
			afs_validate(vnode, key);
			if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
				goto out_bad;
		}
	}

	/* lock down the parent dentry so we can peer at it */
	parent = dget_parent(dentry);
	dir = AFS_FS_I(d_inode(parent));

	/* validate the parent directory */
	afs_validate(dir, key);

	if (test_bit(AFS_VNODE_DELETED, &dir->flags)) {
		_debug("%pd: parent dir deleted", dentry);
		goto out_bad_parent;
	}

	dir_version = (void *) (unsigned long) dir->status.data_version;
	if (dentry->d_fsdata == dir_version)
		goto out_valid; /* the dir contents are unchanged */

	_debug("dir modified");

	/* search the directory for this vnode */
	ret = afs_do_lookup(&dir->vfs_inode, dentry, &fid, key);
	switch (ret) {
	case 0:
		/* the filename maps to something */
		if (d_really_is_negative(dentry))
			goto out_bad_parent;
		inode = d_inode(dentry);
		if (is_bad_inode(inode)) {
			printk("kAFS: afs_d_revalidate: %pd2 has bad inode\n",
			       dentry);
			goto out_bad_parent;
		}

		vnode = AFS_FS_I(inode);

		/* if the vnode ID has changed, then the dirent points to a
		 * different file */
		if (fid.vnode != vnode->fid.vnode) {
			_debug("%pd: dirent changed [%u != %u]",
			       dentry, fid.vnode,
			       vnode->fid.vnode);
			goto not_found;
		}

		/* if the vnode ID uniqifier has changed, then the file has
		 * been deleted and replaced, and the original vnode ID has
		 * been reused */
		if (fid.unique != vnode->fid.unique) {
			_debug("%pd: file deleted (uq %u -> %u I:%u)",
			       dentry, fid.unique,
			       vnode->fid.unique,
			       vnode->vfs_inode.i_generation);
			write_seqlock(&vnode->cb_lock);
			set_bit(AFS_VNODE_DELETED, &vnode->flags);
			write_sequnlock(&vnode->cb_lock);
			goto not_found;
		}
		goto out_valid;

	case -ENOENT:
		/* the filename is unknown */
		_debug("%pd: dirent not found", dentry);
		if (d_really_is_positive(dentry))
			goto not_found;
		goto out_valid;

	default:
		_debug("failed to iterate dir %pd: %d",
		       parent, ret);
		goto out_bad_parent;
	}

out_valid:
	dentry->d_fsdata = dir_version;
	dput(parent);
	key_put(key);
	_leave(" = 1 [valid]");
	return 1;

	/* the dirent, if it exists, now points to a different vnode */
not_found:
	spin_lock(&dentry->d_lock);
	dentry->d_flags |= DCACHE_NFSFS_RENAMED;
	spin_unlock(&dentry->d_lock);

out_bad_parent:
	_debug("dropping dentry %pd2", dentry);
	dput(parent);
out_bad:
	key_put(key);

	_leave(" = 0 [bad]");
	return 0;
}

/*
 * allow the VFS to enquire as to whether a dentry should be unhashed (mustn't
 * sleep)
 * - called from dput() when d_count is going to 0.
 * - return 1 to request dentry be unhashed, 0 otherwise
 */
static int afs_d_delete(const struct dentry *dentry)
{
	_enter("%pd", dentry);

	if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
		goto zap;

	if (d_really_is_positive(dentry) &&
	    (test_bit(AFS_VNODE_DELETED,   &AFS_FS_I(d_inode(dentry))->flags) ||
	     test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(d_inode(dentry))->flags)))
		goto zap;

	_leave(" = 0 [keep]");
	return 0;

zap:
	_leave(" = 1 [zap]");
	return 1;
}

/*
 * handle dentry release
 */
static void afs_d_release(struct dentry *dentry)
{
	_enter("%pd", dentry);
}

/*
 * Create a new inode for create/mkdir/symlink
 */
static void afs_vnode_new_inode(struct afs_fs_cursor *fc,
				struct dentry *new_dentry,
				struct afs_fid *newfid,
				struct afs_file_status *newstatus,
				struct afs_callback *newcb)
{
	struct inode *inode;

	if (fc->ac.error < 0)
		return;

	d_drop(new_dentry);

	inode = afs_iget(fc->vnode->vfs_inode.i_sb, fc->key,
			 newfid, newstatus, newcb, fc->cbi);
	if (IS_ERR(inode)) {
		/* ENOMEM or EINTR at a really inconvenient time - just abandon
		 * the new directory on the server.
		 */
		fc->ac.error = PTR_ERR(inode);
		return;
	}

	d_add(new_dentry, inode);
}

/*
 * create a directory on an AFS filesystem
 */
static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
	struct afs_file_status newstatus;
	struct afs_fs_cursor fc;
	struct afs_callback newcb;
	struct afs_vnode *dvnode = AFS_FS_I(dir);
	struct afs_fid newfid;
	struct key *key;
	int ret;

	mode |= S_IFDIR;

	_enter("{%x:%u},{%pd},%ho",
	       dvnode->fid.vid, dvnode->fid.vnode, dentry, mode);

	key = afs_request_key(dvnode->volume->cell);
	if (IS_ERR(key)) {
		ret = PTR_ERR(key);
		goto error;
	}

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
			afs_fs_create(&fc, dentry->d_name.name, mode,
				      &newfid, &newstatus, &newcb);
		}

		afs_check_for_remote_deletion(&fc, fc.vnode);
		afs_vnode_commit_status(&fc, dvnode, fc.cb_break);
		afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, &newcb);
		ret = afs_end_vnode_operation(&fc);
		if (ret < 0)
			goto error_key;
	} else {
		goto error_key;
	}

	key_put(key);
	_leave(" = 0");
	return 0;

error_key:
	key_put(key);
error:
	d_drop(dentry);
	_leave(" = %d", ret);
	return ret;
}

/*
 * Remove a subdir from a directory.
 */
static void afs_dir_remove_subdir(struct dentry *dentry)
{
	if (d_really_is_positive(dentry)) {
		struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));

		clear_nlink(&vnode->vfs_inode);
		set_bit(AFS_VNODE_DELETED, &vnode->flags);
		clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
	}
}

/*
 * remove a directory from an AFS filesystem
 */
static int afs_rmdir(struct inode *dir, struct dentry *dentry)
{
	struct afs_fs_cursor fc;
	struct afs_vnode *dvnode = AFS_FS_I(dir);
	struct key *key;
	int ret;

	_enter("{%x:%u},{%pd}",
	       dvnode->fid.vid, dvnode->fid.vnode, dentry);

	key = afs_request_key(dvnode->volume->cell);
	if (IS_ERR(key)) {
		ret = PTR_ERR(key);
		goto error;
	}

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
			afs_fs_remove(&fc, dentry->d_name.name, true);
		}

		afs_vnode_commit_status(&fc, dvnode, fc.cb_break);
		ret = afs_end_vnode_operation(&fc);
		if (ret == 0)
			afs_dir_remove_subdir(dentry);
	}

	key_put(key);
error:
	return ret;
}

/*
 * Remove a link to a file or symlink from a directory.
 *
 * If the file was not deleted due to excess hard links, the fileserver will
 * break the callback promise on the file - if it had one - before it returns
 * to us, and if it was deleted, it won't
 *
 * However, if we didn't have a callback promise outstanding, or it was
 * outstanding on a different server, then it won't break it either...
 */
static int afs_dir_remove_link(struct dentry *dentry, struct key *key,
			       unsigned long d_version_before,
			       unsigned long d_version_after)
{
	bool dir_valid;
	int ret = 0;

	/* There were no intervening changes on the server if the version
	 * number we got back was incremented by exactly 1.
	 */
	dir_valid = (d_version_after == d_version_before + 1);

	if (d_really_is_positive(dentry)) {
		struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));

		if (dir_valid) {
			drop_nlink(&vnode->vfs_inode);
			if (vnode->vfs_inode.i_nlink == 0) {
				set_bit(AFS_VNODE_DELETED, &vnode->flags);
				clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
			}
			ret = 0;
		} else {
			clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);

			if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
				kdebug("AFS_VNODE_DELETED");

			ret = afs_validate(vnode, key);
			if (ret == -ESTALE)
				ret = 0;
		}
		_debug("nlink %d [val %d]", vnode->vfs_inode.i_nlink, ret);
	}

	return ret;
}

/*
 * Remove a file or symlink from an AFS filesystem.
 */
static int afs_unlink(struct inode *dir, struct dentry *dentry)
{
	struct afs_fs_cursor fc;
	struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode;
	struct key *key;
	unsigned long d_version = (unsigned long)dentry->d_fsdata;
	int ret;

	_enter("{%x:%u},{%pd}",
	       dvnode->fid.vid, dvnode->fid.vnode, dentry);

	if (dentry->d_name.len >= AFSNAMEMAX)
		return -ENAMETOOLONG;

	key = afs_request_key(dvnode->volume->cell);
	if (IS_ERR(key)) {
		ret = PTR_ERR(key);
		goto error;
	}

	/* Try to make sure we have a callback promise on the victim. */
	if (d_really_is_positive(dentry)) {
		vnode = AFS_FS_I(d_inode(dentry));
		ret = afs_validate(vnode, key);
		if (ret < 0)
			goto error_key;
	}

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
			afs_fs_remove(&fc, dentry->d_name.name, false);
		}

		afs_vnode_commit_status(&fc, dvnode, fc.cb_break);
		ret = afs_end_vnode_operation(&fc);
		if (ret == 0)
			ret = afs_dir_remove_link(
				dentry, key, d_version,
				(unsigned long)dvnode->status.data_version);
	}

error_key:
	key_put(key);
error:
	_leave(" = %d", ret);
	return ret;
}

/*
 * create a regular file on an AFS filesystem
 */
static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
		      bool excl)
{
	struct afs_fs_cursor fc;
	struct afs_file_status newstatus;
	struct afs_callback newcb;
	struct afs_vnode *dvnode = AFS_FS_I(dir);
	struct afs_fid newfid;
	struct key *key;
	int ret;

	mode |= S_IFREG;

	_enter("{%x:%u},{%pd},%ho,",
	       dvnode->fid.vid, dvnode->fid.vnode, dentry, mode);

	ret = -ENAMETOOLONG;
	if (dentry->d_name.len >= AFSNAMEMAX)
		goto error;

	key = afs_request_key(dvnode->volume->cell);
	if (IS_ERR(key)) {
		ret = PTR_ERR(key);
		goto error;
	}

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
			afs_fs_create(&fc, dentry->d_name.name, mode,
				      &newfid, &newstatus, &newcb);
		}

		afs_check_for_remote_deletion(&fc, fc.vnode);
		afs_vnode_commit_status(&fc, dvnode, fc.cb_break);
		afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, &newcb);
		ret = afs_end_vnode_operation(&fc);
		if (ret < 0)
			goto error_key;
	} else {
		goto error_key;
	}

	key_put(key);
	_leave(" = 0");
	return 0;

error_key:
	key_put(key);
error:
	d_drop(dentry);
	_leave(" = %d", ret);
	return ret;
}

/*
 * create a hard link between files in an AFS filesystem
 */
static int afs_link(struct dentry *from, struct inode *dir,
		    struct dentry *dentry)
{
	struct afs_fs_cursor fc;
	struct afs_vnode *dvnode, *vnode;
	struct key *key;
	int ret;

	vnode = AFS_FS_I(d_inode(from));
	dvnode = AFS_FS_I(dir);

	_enter("{%x:%u},{%x:%u},{%pd}",
	       vnode->fid.vid, vnode->fid.vnode,
	       dvnode->fid.vid, dvnode->fid.vnode,
	       dentry);

	ret = -ENAMETOOLONG;
	if (dentry->d_name.len >= AFSNAMEMAX)
		goto error;

	key = afs_request_key(dvnode->volume->cell);
	if (IS_ERR(key)) {
		ret = PTR_ERR(key);
		goto error;
	}

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
		if (mutex_lock_interruptible_nested(&vnode->io_lock, 1) < 0) {
			afs_end_vnode_operation(&fc);
			goto error_key;
		}

		while (afs_select_fileserver(&fc)) {
			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
			fc.cb_break_2 = vnode->cb_break + vnode->cb_s_break;
			afs_fs_link(&fc, vnode, dentry->d_name.name);
		}

		afs_vnode_commit_status(&fc, dvnode, fc.cb_break);
		afs_vnode_commit_status(&fc, vnode, fc.cb_break_2);
		ihold(&vnode->vfs_inode);
		d_instantiate(dentry, &vnode->vfs_inode);

		mutex_unlock(&vnode->io_lock);
		ret = afs_end_vnode_operation(&fc);
		if (ret < 0)
			goto error_key;
	} else {
		goto error_key;
	}

	key_put(key);
	_leave(" = 0");
	return 0;

error_key:
	key_put(key);
error:
	d_drop(dentry);
	_leave(" = %d", ret);
	return ret;
}

/*
 * create a symlink in an AFS filesystem
 */
static int afs_symlink(struct inode *dir, struct dentry *dentry,
		       const char *content)
{
	struct afs_fs_cursor fc;
	struct afs_file_status newstatus;
	struct afs_vnode *dvnode = AFS_FS_I(dir);
	struct afs_fid newfid;
	struct key *key;
	int ret;

	_enter("{%x:%u},{%pd},%s",
	       dvnode->fid.vid, dvnode->fid.vnode, dentry,
	       content);

	ret = -ENAMETOOLONG;
	if (dentry->d_name.len >= AFSNAMEMAX)
		goto error;

	ret = -EINVAL;
	if (strlen(content) >= AFSPATHMAX)
		goto error;

	key = afs_request_key(dvnode->volume->cell);
	if (IS_ERR(key)) {
		ret = PTR_ERR(key);
		goto error;
	}

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
			afs_fs_symlink(&fc, dentry->d_name.name, content,
				       &newfid, &newstatus);
		}

		afs_check_for_remote_deletion(&fc, fc.vnode);
		afs_vnode_commit_status(&fc, dvnode, fc.cb_break);
		afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, NULL);
		ret = afs_end_vnode_operation(&fc);
		if (ret < 0)
			goto error_key;
	} else {
		goto error_key;
	}

	key_put(key);
	_leave(" = 0");
	return 0;

error_key:
	key_put(key);
error:
	d_drop(dentry);
	_leave(" = %d", ret);
	return ret;
}

/*
 * rename a file in an AFS filesystem and/or move it between directories
 */
static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
		      struct inode *new_dir, struct dentry *new_dentry,
		      unsigned int flags)
{
	struct afs_fs_cursor fc;
	struct afs_vnode *orig_dvnode, *new_dvnode, *vnode;
	struct key *key;
	int ret;

	if (flags)
		return -EINVAL;

	vnode = AFS_FS_I(d_inode(old_dentry));
	orig_dvnode = AFS_FS_I(old_dir);
	new_dvnode = AFS_FS_I(new_dir);

	_enter("{%x:%u},{%x:%u},{%x:%u},{%pd}",
	       orig_dvnode->fid.vid, orig_dvnode->fid.vnode,
	       vnode->fid.vid, vnode->fid.vnode,
	       new_dvnode->fid.vid, new_dvnode->fid.vnode,
	       new_dentry);

	key = afs_request_key(orig_dvnode->volume->cell);
	if (IS_ERR(key)) {
		ret = PTR_ERR(key);
		goto error;
	}

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, orig_dvnode, key)) {
		if (orig_dvnode != new_dvnode) {
			if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) {
				afs_end_vnode_operation(&fc);
				goto error_key;
			}
		}
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = orig_dvnode->cb_break + orig_dvnode->cb_s_break;
			fc.cb_break_2 = new_dvnode->cb_break + new_dvnode->cb_s_break;
			afs_fs_rename(&fc, old_dentry->d_name.name,
				      new_dvnode, new_dentry->d_name.name);
		}

		afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break);
		afs_vnode_commit_status(&fc, new_dvnode, fc.cb_break_2);
		if (orig_dvnode != new_dvnode)
			mutex_unlock(&new_dvnode->io_lock);
		ret = afs_end_vnode_operation(&fc);
		if (ret < 0)
			goto error_key;
	}

error_key:
	key_put(key);
error:
	_leave(" = %d", ret);
	return ret;
}