aboutsummaryrefslogtreecommitdiffstats
path: root/fs/reiserfs/xattr.c
blob: f9bcdd5750f7be288ae7cd21fba2224a77c30f61 (plain) (blame)
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
/*
 * linux/fs/reiserfs/xattr.c
 *
 * Copyright (c) 2002 by Jeff Mahoney, <jeffm@suse.com>
 *
 */

/*
 * In order to implement EA/ACLs in a clean, backwards compatible manner,
 * they are implemented as files in a "private" directory.
 * Each EA is in it's own file, with the directory layout like so (/ is assumed
 * to be relative to fs root). Inside the /.reiserfs_priv/xattrs directory,
 * directories named using the capital-hex form of the objectid and
 * generation number are used. Inside each directory are individual files
 * named with the name of the extended attribute.
 *
 * So, for objectid 12648430, we could have:
 * /.reiserfs_priv/xattrs/C0FFEE.0/system.posix_acl_access
 * /.reiserfs_priv/xattrs/C0FFEE.0/system.posix_acl_default
 * /.reiserfs_priv/xattrs/C0FFEE.0/user.Content-Type
 * .. or similar.
 *
 * The file contents are the text of the EA. The size is known based on the
 * stat data describing the file.
 *
 * In the case of system.posix_acl_access and system.posix_acl_default, since
 * these are special cases for filesystem ACLs, they are interpreted by the
 * kernel, in addition, they are negatively and positively cached and attached
 * to the inode so that unnecessary lookups are avoided.
 */

#include <linux/reiserfs_fs.h>
#include <linux/capability.h>
#include <linux/dcache.h>
#include <linux/namei.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
#include <linux/reiserfs_xattr.h>
#include <linux/reiserfs_acl.h>
#include <asm/uaccess.h>
#include <net/checksum.h>
#include <linux/smp_lock.h>
#include <linux/stat.h>

#define FL_READONLY 128
#define FL_DIR_SEM_HELD 256
#define PRIVROOT_NAME ".reiserfs_priv"
#define XAROOT_NAME   "xattrs"

/* Returns the dentry referring to the root of the extended attribute
 * directory tree. If it has already been retrieved, it is used. If it
 * hasn't been created and the flags indicate creation is allowed, we
 * attempt to create it. On error, we return a pointer-encoded error.
 */
static struct dentry *get_xa_root(struct super_block *sb, int flags)
{
	struct dentry *privroot = dget(REISERFS_SB(sb)->priv_root);
	struct dentry *xaroot;

	/* This needs to be created at mount-time */
	if (!privroot)
		return ERR_PTR(-ENODATA);

	mutex_lock_nested(&privroot->d_inode->i_mutex, I_MUTEX_XATTR);
	if (REISERFS_SB(sb)->xattr_root) {
		xaroot = dget(REISERFS_SB(sb)->xattr_root);
		goto out;
	}

	xaroot = lookup_one_len(XAROOT_NAME, privroot, strlen(XAROOT_NAME));
	if (IS_ERR(xaroot)) {
		goto out;
	} else if (!xaroot->d_inode) {
		int err = -ENODATA;
		if (flags == 0 || flags & XATTR_CREATE)
			err = privroot->d_inode->i_op->mkdir(privroot->d_inode,
			                                     xaroot, 0700);
		if (err) {
			dput(xaroot);
			xaroot = ERR_PTR(err);
			goto out;
		}
	}
	REISERFS_SB(sb)->xattr_root = dget(xaroot);

      out:
	mutex_unlock(&privroot->d_inode->i_mutex);
	dput(privroot);
	return xaroot;
}

/* Opens the directory corresponding to the inode's extended attribute store.
 * If flags allow, the tree to the directory may be created. If creation is
 * prohibited, -ENODATA is returned. */
static struct dentry *open_xa_dir(const struct inode *inode, int flags)
{
	struct dentry *xaroot, *xadir;
	char namebuf[17];

	xaroot = get_xa_root(inode->i_sb, flags);
	if (IS_ERR(xaroot))
		return xaroot;

	/* ok, we have xaroot open */
	snprintf(namebuf, sizeof(namebuf), "%X.%X",
		 le32_to_cpu(INODE_PKEY(inode)->k_objectid),
		 inode->i_generation);
	xadir = lookup_one_len(namebuf, xaroot, strlen(namebuf));
	if (IS_ERR(xadir)) {
		dput(xaroot);
		return xadir;
	}

	if (!xadir->d_inode) {
		int err;
		if (flags == 0 || flags & XATTR_CREATE) {
			/* Although there is nothing else trying to create this directory,
			 * another directory with the same hash may be created, so we need
			 * to protect against that */
			err =
			    xaroot->d_inode->i_op->mkdir(xaroot->d_inode, xadir,
							 0700);
			if (err) {
				dput(xaroot);
				dput(xadir);
				return ERR_PTR(err);
			}
		}
		if (!xadir->d_inode) {
			dput(xaroot);
			dput(xadir);
			return ERR_PTR(-ENODATA);
		}
	}

	dput(xaroot);
	return xadir;
}

/*
 * this is very similar to fs/reiserfs/dir.c:reiserfs_readdir, but
 * we need to drop the path before calling the filldir struct.  That
 * would be a big performance hit to the non-xattr case, so I've copied
 * the whole thing for now. --clm
 *
 * the big difference is that I go backwards through the directory,
 * and don't mess with f->f_pos, but the idea is the same.  Do some
 * action on each and every entry in the directory.
 *
 * we're called with i_mutex held, so there are no worries about the directory
 * changing underneath us.
 */
static int __xattr_readdir(struct inode *inode, void *dirent, filldir_t filldir)
{
	struct cpu_key pos_key;	/* key of current position in the directory (key of directory entry) */
	INITIALIZE_PATH(path_to_entry);
	struct buffer_head *bh;
	int entry_num;
	struct item_head *ih, tmp_ih;
	int search_res;
	char *local_buf;
	loff_t next_pos;
	char small_buf[32];	/* avoid kmalloc if we can */
	struct reiserfs_de_head *deh;
	int d_reclen;
	char *d_name;
	off_t d_off;
	ino_t d_ino;
	struct reiserfs_dir_entry de;

	/* form key for search the next directory entry using f_pos field of
	   file structure */
	next_pos = max_reiserfs_offset(inode);

	while (1) {
	      research:
		if (next_pos <= DOT_DOT_OFFSET)
			break;
		make_cpu_key(&pos_key, inode, next_pos, TYPE_DIRENTRY, 3);

		search_res =
		    search_by_entry_key(inode->i_sb, &pos_key, &path_to_entry,
					&de);
		if (search_res == IO_ERROR) {
			// FIXME: we could just skip part of directory which could
			// not be read
			pathrelse(&path_to_entry);
			return -EIO;
		}

		if (search_res == NAME_NOT_FOUND)
			de.de_entry_num--;

		set_de_name_and_namelen(&de);
		entry_num = de.de_entry_num;
		deh = &(de.de_deh[entry_num]);

		bh = de.de_bh;
		ih = de.de_ih;

		if (!is_direntry_le_ih(ih)) {
			reiserfs_error(inode->i_sb, "jdm-20000",
				       "not direntry %h", ih);
			break;
		}
		copy_item_head(&tmp_ih, ih);

		/* we must have found item, that is item of this directory, */
		RFALSE(COMP_SHORT_KEYS(&(ih->ih_key), &pos_key),
		       "vs-9000: found item %h does not match to dir we readdir %K",
		       ih, &pos_key);

		if (deh_offset(deh) <= DOT_DOT_OFFSET) {
			break;
		}

		/* look for the previous entry in the directory */
		next_pos = deh_offset(deh) - 1;

		if (!de_visible(deh))
			/* it is hidden entry */
			continue;

		d_reclen = entry_length(bh, ih, entry_num);
		d_name = B_I_DEH_ENTRY_FILE_NAME(bh, ih, deh);
		d_off = deh_offset(deh);
		d_ino = deh_objectid(deh);

		if (!d_name[d_reclen - 1])
			d_reclen = strlen(d_name);

		if (d_reclen > REISERFS_MAX_NAME(inode->i_sb->s_blocksize)) {
			/* too big to send back to VFS */
			continue;
		}

		/* Ignore the .reiserfs_priv entry */
		if (reiserfs_xattrs(inode->i_sb) &&
		    !old_format_only(inode->i_sb) &&
		    deh_objectid(deh) ==
		    le32_to_cpu(INODE_PKEY
				(REISERFS_SB(inode->i_sb)->priv_root->d_inode)->
				k_objectid))
			continue;

		if (d_reclen <= 32) {
			local_buf = small_buf;
		} else {
			local_buf = kmalloc(d_reclen, GFP_NOFS);
			if (!local_buf) {
				pathrelse(&path_to_entry);
				return -ENOMEM;
			}
			if (item_moved(&tmp_ih, &path_to_entry)) {
				kfree(local_buf);

				/* sigh, must retry.  Do this same offset again */
				next_pos = d_off;
				goto research;
			}
		}

		// Note, that we copy name to user space via temporary
		// buffer (local_buf) because filldir will block if
		// user space buffer is swapped out. At that time
		// entry can move to somewhere else
		memcpy(local_buf, d_name, d_reclen);

		/* the filldir function might need to start transactions,
		 * or do who knows what.  Release the path now that we've
		 * copied all the important stuff out of the deh
		 */
		pathrelse(&path_to_entry);

		if (filldir(dirent, local_buf, d_reclen, d_off, d_ino,
			    DT_UNKNOWN) < 0) {
			if (local_buf != small_buf) {
				kfree(local_buf);
			}
			goto end;
		}
		if (local_buf != small_buf) {
			kfree(local_buf);
		}
	}			/* while */

      end:
	pathrelse(&path_to_entry);
	return 0;
}

/*
 * this could be done with dedicated readdir ops for the xattr files,
 * but I want to get something working asap
 * this is stolen from vfs_readdir
 *
 */
static
int xattr_readdir(struct inode *inode, filldir_t filler, void *buf)
{
	int res = -ENOENT;
	mutex_lock_nested(&inode->i_mutex, I_MUTEX_XATTR);
	if (!IS_DEADDIR(inode)) {
		lock_kernel();
		res = __xattr_readdir(inode, buf, filler);
		unlock_kernel();
	}
	mutex_unlock(&inode->i_mutex);
	return res;
}

static int
__reiserfs_xattr_del(struct dentry *xadir, const char *name, int namelen)
{
	struct dentry *dentry;
	struct inode *dir = xadir->d_inode;
	int err = 0;

	dentry = lookup_one_len(name, xadir, namelen);
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out;
	} else if (!dentry->d_inode) {
		err = -ENODATA;
		goto out_file;
	}

	/* Skip directories.. */
	if (S_ISDIR(dentry->d_inode->i_mode))
		goto out_file;

	if (!IS_PRIVATE(dentry->d_inode)) {
		reiserfs_error(dir->i_sb, "jdm-20003",
			       "OID %08x [%.*s/%.*s] doesn't have "
			       "priv flag set [parent is %sset].",
			       le32_to_cpu(INODE_PKEY(dentry->d_inode)->
					   k_objectid), xadir->d_name.len,
			       xadir->d_name.name, namelen, name,
			       IS_PRIVATE(xadir->d_inode) ? "" :
			       "not ");
		dput(dentry);
		return -EIO;
	}

	err = dir->i_op->unlink(dir, dentry);
	if (!err)
		d_delete(dentry);

out_file:
	dput(dentry);

out:
	return err;
}

/* The following are side effects of other operations that aren't explicitly
 * modifying extended attributes. This includes operations such as permissions
 * or ownership changes, object deletions, etc. */

static int
reiserfs_delete_xattrs_filler(void *buf, const char *name, int namelen,
			      loff_t offset, u64 ino, unsigned int d_type)
{
	struct dentry *xadir = (struct dentry *)buf;

	return __reiserfs_xattr_del(xadir, name, namelen);

}

/* This is called w/ inode->i_mutex downed */
int reiserfs_delete_xattrs(struct inode *inode)
{
	struct dentry *dir, *root;
	int err = 0;

	/* Skip out, an xattr has no xattrs associated with it */
	if (IS_PRIVATE(inode) || get_inode_sd_version(inode) == STAT_DATA_V1)
		return 0;

	reiserfs_read_lock_xattrs(inode->i_sb);
	dir = open_xa_dir(inode, FL_READONLY);
	reiserfs_read_unlock_xattrs(inode->i_sb);
	if (IS_ERR(dir)) {
		err = PTR_ERR(dir);
		goto out;
	} else if (!dir->d_inode) {
		dput(dir);
		return 0;
	}

	lock_kernel();
	err = xattr_readdir(dir->d_inode, reiserfs_delete_xattrs_filler, dir);
	if (err) {
		unlock_kernel();
		goto out_dir;
	}

	/* Leftovers besides . and .. -- that's not good. */
	if (dir->d_inode->i_nlink <= 2) {
		root = get_xa_root(inode->i_sb, XATTR_REPLACE);
		reiserfs_write_lock_xattrs(inode->i_sb);
		err = vfs_rmdir(root->d_inode, dir);
		reiserfs_write_unlock_xattrs(inode->i_sb);
		dput(root);
	} else {
		reiserfs_warning(inode->i_sb, "jdm-20006",
				 "Couldn't remove all entries in directory");
	}
	unlock_kernel();

out_dir:
	dput(dir);

out:
	if (!err)
		REISERFS_I(inode)->i_flags =
		    REISERFS_I(inode)->i_flags & ~i_has_xattr_dir;
	return err;
}

struct reiserfs_chown_buf {
	struct inode *inode;
	struct dentry *xadir;
	struct iattr *attrs;
};

/* XXX: If there is a better way to do this, I'd love to hear about it */
static int
reiserfs_chown_xattrs_filler(void *buf, const char *name, int namelen,
			     loff_t offset, u64 ino, unsigned int d_type)
{
	struct reiserfs_chown_buf *chown_buf = (struct reiserfs_chown_buf *)buf;
	struct dentry *xafile, *xadir = chown_buf->xadir;
	struct iattr *attrs = chown_buf->attrs;
	int err = 0;

	xafile = lookup_one_len(name, xadir, namelen);
	if (IS_ERR(xafile))
		return PTR_ERR(xafile);
	else if (!xafile->d_inode) {
		dput(xafile);
		return -ENODATA;
	}

	if (!S_ISDIR(xafile->d_inode->i_mode))
		err = notify_change(xafile, attrs);
	dput(xafile);

	return err;
}

int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs)
{
	struct dentry *dir;
	int err = 0;
	struct reiserfs_chown_buf buf;
	unsigned int ia_valid = attrs->ia_valid;

	/* Skip out, an xattr has no xattrs associated with it */
	if (IS_PRIVATE(inode) || get_inode_sd_version(inode) == STAT_DATA_V1)
		return 0;

	reiserfs_read_lock_xattrs(inode->i_sb);
	dir = open_xa_dir(inode, FL_READONLY);
	reiserfs_read_unlock_xattrs(inode->i_sb);
	if (IS_ERR(dir)) {
		if (PTR_ERR(dir) != -ENODATA)
			err = PTR_ERR(dir);
		goto out;
	} else if (!dir->d_inode) {
		dput(dir);
		goto out;
	}

	lock_kernel();

	attrs->ia_valid &= (ATTR_UID | ATTR_GID | ATTR_CTIME);
	buf.xadir = dir;
	buf.attrs = attrs;
	buf.inode = inode;

	err = xattr_readdir(dir->d_inode, reiserfs_chown_xattrs_filler, &buf);
	if (err) {
		unlock_kernel();
		goto out_dir;
	}

	err = notify_change(dir, attrs);
	unlock_kernel();

out_dir:
	dput(dir);

out:
	attrs->ia_valid = ia_valid;
	return err;
}

#ifdef CONFIG_REISERFS_FS_XATTR
static struct reiserfs_xattr_handler *find_xattr_handler_prefix(const char
								*prefix);

/* Returns a dentry corresponding to a specific extended attribute file
 * for the inode. If flags allow, the file is created. Otherwise, a
 * valid or negative dentry, or an error is returned. */
static struct dentry *get_xa_file_dentry(const struct inode *inode,
					 const char *name, int flags)
{
	struct dentry *xadir, *xafile;
	int err = 0;

	xadir = open_xa_dir(inode, flags);
	if (IS_ERR(xadir)) {
		return ERR_CAST(xadir);
	} else if (xadir && !xadir->d_inode) {
		dput(xadir);
		return ERR_PTR(-ENODATA);
	}

	xafile = lookup_one_len(name, xadir, strlen(name));
	if (IS_ERR(xafile)) {
		dput(xadir);
		return ERR_CAST(xafile);
	}

	if (xafile->d_inode) {	/* file exists */
		if (flags & XATTR_CREATE) {
			err = -EEXIST;
			dput(xafile);
			goto out;
		}
	} else if (flags & XATTR_REPLACE || flags & FL_READONLY) {
		goto out;
	} else {
		/* inode->i_mutex is down, so nothing else can try to create
		 * the same xattr */
		err = xadir->d_inode->i_op->create(xadir->d_inode, xafile,
						   0700 | S_IFREG, NULL);

		if (err) {
			dput(xafile);
			goto out;
		}
	}

out:
	dput(xadir);
	if (err)
		xafile = ERR_PTR(err);
	else if (!xafile->d_inode) {
		dput(xafile);
		xafile = ERR_PTR(-ENODATA);
	}
	return xafile;
}

/* Internal operations on file data */
static inline void reiserfs_put_page(struct page *page)
{
	kunmap(page);
	page_cache_release(page);
}

static struct page *reiserfs_get_page(struct inode *dir, size_t n)
{
	struct address_space *mapping = dir->i_mapping;
	struct page *page;
	/* We can deadlock if we try to free dentries,
	   and an unlink/rmdir has just occured - GFP_NOFS avoids this */
	mapping_set_gfp_mask(mapping, GFP_NOFS);
	page = read_mapping_page(mapping, n >> PAGE_CACHE_SHIFT, NULL);
	if (!IS_ERR(page)) {
		kmap(page);
		if (PageError(page))
			goto fail;
	}
	return page;

      fail:
	reiserfs_put_page(page);
	return ERR_PTR(-EIO);
}

static inline __u32 xattr_hash(const char *msg, int len)
{
	return csum_partial(msg, len, 0);
}

int reiserfs_commit_write(struct file *f, struct page *page,
			  unsigned from, unsigned to);
int reiserfs_prepare_write(struct file *f, struct page *page,
			   unsigned from, unsigned to);


/* Generic extended attribute operations that can be used by xa plugins */

/*
 * inode->i_mutex: down
 */
int
reiserfs_xattr_set(struct inode *inode, const char *name, const void *buffer,
		   size_t buffer_size, int flags)
{
	int err = 0;
	struct dentry *dentry;
	struct page *page;
	char *data;
	size_t file_pos = 0;
	size_t buffer_pos = 0;
	struct iattr newattrs;
	__u32 xahash = 0;

	if (get_inode_sd_version(inode) == STAT_DATA_V1)
		return -EOPNOTSUPP;

	/* Empty xattrs are ok, they're just empty files, no hash */
	if (buffer && buffer_size)
		xahash = xattr_hash(buffer, buffer_size);

	dentry = get_xa_file_dentry(inode, name, flags);
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out;
	}

	REISERFS_I(inode)->i_flags |= i_has_xattr_dir;

	/* Resize it so we're ok to write there */
	newattrs.ia_size = buffer_size;
	newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
	mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR);
	err = notify_change(dentry, &newattrs);
	if (err)
		goto out_filp;

	while (buffer_pos < buffer_size || buffer_pos == 0) {
		size_t chunk;
		size_t skip = 0;
		size_t page_offset = (file_pos & (PAGE_CACHE_SIZE - 1));
		if (buffer_size - buffer_pos > PAGE_CACHE_SIZE)
			chunk = PAGE_CACHE_SIZE;
		else
			chunk = buffer_size - buffer_pos;

		page = reiserfs_get_page(dentry->d_inode, file_pos);
		if (IS_ERR(page)) {
			err = PTR_ERR(page);
			goto out_filp;
		}

		lock_page(page);
		data = page_address(page);

		if (file_pos == 0) {
			struct reiserfs_xattr_header *rxh;
			skip = file_pos = sizeof(struct reiserfs_xattr_header);
			if (chunk + skip > PAGE_CACHE_SIZE)
				chunk = PAGE_CACHE_SIZE - skip;
			rxh = (struct reiserfs_xattr_header *)data;
			rxh->h_magic = cpu_to_le32(REISERFS_XATTR_MAGIC);
			rxh->h_hash = cpu_to_le32(xahash);
		}

		err = reiserfs_prepare_write(NULL, page, page_offset,
					    page_offset + chunk + skip);
		if (!err) {
			if (buffer)
				memcpy(data + skip, buffer + buffer_pos, chunk);
			err = reiserfs_commit_write(NULL, page, page_offset,
						    page_offset + chunk +
						    skip);
		}
		unlock_page(page);
		reiserfs_put_page(page);
		buffer_pos += chunk;
		file_pos += chunk;
		skip = 0;
		if (err || buffer_size == 0 || !buffer)
			break;
	}

	/* We can't mark the inode dirty if it's not hashed. This is the case
	 * when we're inheriting the default ACL. If we dirty it, the inode
	 * gets marked dirty, but won't (ever) make it onto the dirty list until
	 * it's synced explicitly to clear I_DIRTY. This is bad. */
	if (!hlist_unhashed(&inode->i_hash)) {
		inode->i_ctime = CURRENT_TIME_SEC;
		mark_inode_dirty(inode);
	}

      out_filp:
	mutex_unlock(&dentry->d_inode->i_mutex);
	dput(dentry);

      out:
	return err;
}

/*
 * inode->i_mutex: down
 */
int
reiserfs_xattr_get(const struct inode *inode, const char *name, void *buffer,
		   size_t buffer_size)
{
	ssize_t err = 0;
	struct dentry *dentry;
	size_t isize;
	size_t file_pos = 0;
	size_t buffer_pos = 0;
	struct page *page;
	__u32 hash = 0;

	if (name == NULL)
		return -EINVAL;

	/* We can't have xattrs attached to v1 items since they don't have
	 * generation numbers */
	if (get_inode_sd_version(inode) == STAT_DATA_V1)
		return -EOPNOTSUPP;

	dentry = get_xa_file_dentry(inode, name, FL_READONLY);
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out;
	}

	isize = i_size_read(dentry->d_inode);
	REISERFS_I(inode)->i_flags |= i_has_xattr_dir;

	/* Just return the size needed */
	if (buffer == NULL) {
		err = isize - sizeof(struct reiserfs_xattr_header);
		goto out_dput;
	}

	if (buffer_size < isize - sizeof(struct reiserfs_xattr_header)) {
		err = -ERANGE;
		goto out_dput;
	}

	while (file_pos < isize) {
		size_t chunk;
		char *data;
		size_t skip = 0;
		if (isize - file_pos > PAGE_CACHE_SIZE)
			chunk = PAGE_CACHE_SIZE;
		else
			chunk = isize - file_pos;

		page = reiserfs_get_page(dentry->d_inode, file_pos);
		if (IS_ERR(page)) {
			err = PTR_ERR(page);
			goto out_dput;
		}

		lock_page(page);
		data = page_address(page);
		if (file_pos == 0) {
			struct reiserfs_xattr_header *rxh =
			    (struct reiserfs_xattr_header *)data;
			skip = file_pos = sizeof(struct reiserfs_xattr_header);
			chunk -= skip;
			/* Magic doesn't match up.. */
			if (rxh->h_magic != cpu_to_le32(REISERFS_XATTR_MAGIC)) {
				unlock_page(page);
				reiserfs_put_page(page);
				reiserfs_warning(inode->i_sb, "jdm-20001",
						 "Invalid magic for xattr (%s) "
						 "associated with %k", name,
						 INODE_PKEY(inode));
				err = -EIO;
				goto out_dput;
			}
			hash = le32_to_cpu(rxh->h_hash);
		}
		memcpy(buffer + buffer_pos, data + skip, chunk);
		unlock_page(page);
		reiserfs_put_page(page);
		file_pos += chunk;
		buffer_pos += chunk;
		skip = 0;
	}
	err = isize - sizeof(struct reiserfs_xattr_header);

	if (xattr_hash(buffer, isize - sizeof(struct reiserfs_xattr_header)) !=
	    hash) {
		reiserfs_warning(inode->i_sb, "jdm-20002",
				 "Invalid hash for xattr (%s) associated "
				 "with %k", name, INODE_PKEY(inode));
		err = -EIO;
	}

out_dput:
	dput(dentry);

out:
	return err;
}

int reiserfs_xattr_del(struct inode *inode, const char *name)
{
	struct dentry *dir;
	int err;

	dir = open_xa_dir(inode, FL_READONLY);
	if (IS_ERR(dir)) {
		err = PTR_ERR(dir);
		goto out;
	}

	err = __reiserfs_xattr_del(dir, name, strlen(name));
	dput(dir);

	if (!err) {
		inode->i_ctime = CURRENT_TIME_SEC;
		mark_inode_dirty(inode);
	}

      out:
	return err;
}

/* Actual operations that are exported to VFS-land */

/*
 * Inode operation getxattr()
 * Preliminary locking: we down dentry->d_inode->i_mutex
 */
ssize_t
reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer,
		  size_t size)
{
	struct reiserfs_xattr_handler *xah = find_xattr_handler_prefix(name);
	int err;

	if (!xah || !reiserfs_xattrs(dentry->d_sb) ||
	    get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
		return -EOPNOTSUPP;

	reiserfs_read_lock_xattr_i(dentry->d_inode);
	reiserfs_read_lock_xattrs(dentry->d_sb);
	err = xah->get(dentry->d_inode, name, buffer, size);
	reiserfs_read_unlock_xattrs(dentry->d_sb);
	reiserfs_read_unlock_xattr_i(dentry->d_inode);
	return err;
}

/*
 * Inode operation setxattr()
 *
 * dentry->d_inode->i_mutex down
 */
int
reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value,
		  size_t size, int flags)
{
	struct reiserfs_xattr_handler *xah = find_xattr_handler_prefix(name);
	int err;
	int lock;

	if (!xah || !reiserfs_xattrs(dentry->d_sb) ||
	    get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
		return -EOPNOTSUPP;

	reiserfs_write_lock_xattr_i(dentry->d_inode);
	lock = !has_xattr_dir(dentry->d_inode);
	if (lock)
		reiserfs_write_lock_xattrs(dentry->d_sb);
	else
		reiserfs_read_lock_xattrs(dentry->d_sb);
	err = xah->set(dentry->d_inode, name, value, size, flags);
	if (lock)
		reiserfs_write_unlock_xattrs(dentry->d_sb);
	else
		reiserfs_read_unlock_xattrs(dentry->d_sb);
	reiserfs_write_unlock_xattr_i(dentry->d_inode);
	return err;
}

/*
 * Inode operation removexattr()
 *
 * dentry->d_inode->i_mutex down
 */
int reiserfs_removexattr(struct dentry *dentry, const char *name)
{
	int err;
	struct reiserfs_xattr_handler *xah = find_xattr_handler_prefix(name);

	if (!xah || !reiserfs_xattrs(dentry->d_sb) ||
	    get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
		return -EOPNOTSUPP;

	reiserfs_write_lock_xattr_i(dentry->d_inode);
	reiserfs_read_lock_xattrs(dentry->d_sb);

	/* Deletion pre-operation */
	if (xah->del) {
		err = xah->del(dentry->d_inode, name);
		if (err)
			goto out;
	}

	err = reiserfs_xattr_del(dentry->d_inode, name);

	dentry->d_inode->i_ctime = CURRENT_TIME_SEC;
	mark_inode_dirty(dentry->d_inode);

      out:
	reiserfs_read_unlock_xattrs(dentry->d_sb);
	reiserfs_write_unlock_xattr_i(dentry->d_inode);
	return err;
}

/* This is what filldir will use:
 * r_pos will always contain the amount of space required for the entire
 * list. If r_pos becomes larger than r_size, we need more space and we
 * return an error indicating this. If r_pos is less than r_size, then we've
 * filled the buffer successfully and we return success */
struct reiserfs_listxattr_buf {
	int r_pos;
	int r_size;
	char *r_buf;
	struct inode *r_inode;
};

static int
reiserfs_listxattr_filler(void *buf, const char *name, int namelen,
			  loff_t offset, u64 ino, unsigned int d_type)
{
	struct reiserfs_listxattr_buf *b = (struct reiserfs_listxattr_buf *)buf;
	int len = 0;
	if (name[0] != '.'
	    || (namelen != 1 && (name[1] != '.' || namelen != 2))) {
		struct reiserfs_xattr_handler *xah =
		    find_xattr_handler_prefix(name);
		if (!xah)
			return 0;	/* Unsupported xattr name, skip it */

		/* We call ->list() twice because the operation isn't required to just
		 * return the name back - we want to make sure we have enough space */
		len += xah->list(b->r_inode, name, namelen, NULL);

		if (len) {
			if (b->r_pos + len + 1 <= b->r_size) {
				char *p = b->r_buf + b->r_pos;
				p += xah->list(b->r_inode, name, namelen, p);
				*p++ = '\0';
			}
			b->r_pos += len + 1;
		}
	}

	return 0;
}

/*
 * Inode operation listxattr()
 *
 * Preliminary locking: we down dentry->d_inode->i_mutex
 */
ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size)
{
	struct dentry *dir;
	int err = 0;
	struct reiserfs_listxattr_buf buf;

	if (!dentry->d_inode)
		return -EINVAL;

	if (!reiserfs_xattrs(dentry->d_sb) ||
	    get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
		return -EOPNOTSUPP;

	reiserfs_read_lock_xattr_i(dentry->d_inode);
	reiserfs_read_lock_xattrs(dentry->d_sb);
	dir = open_xa_dir(dentry->d_inode, FL_READONLY);
	reiserfs_read_unlock_xattrs(dentry->d_sb);
	if (IS_ERR(dir)) {
		err = PTR_ERR(dir);
		if (err == -ENODATA)
			err = 0;	/* Not an error if there aren't any xattrs */
		goto out;
	}

	buf.r_buf = buffer;
	buf.r_size = buffer ? size : 0;
	buf.r_pos = 0;
	buf.r_inode = dentry->d_inode;

	REISERFS_I(dentry->d_inode)->i_flags |= i_has_xattr_dir;

	err = xattr_readdir(dir->d_inode, reiserfs_listxattr_filler, &buf);
	if (err)
		goto out_dir;

	if (buf.r_pos > buf.r_size && buffer != NULL)
		err = -ERANGE;
	else
		err = buf.r_pos;

      out_dir:
	dput(dir);

      out:
	reiserfs_read_unlock_xattr_i(dentry->d_inode);
	return err;
}

/* This is the implementation for the xattr plugin infrastructure */
static LIST_HEAD(xattr_handlers);
static DEFINE_RWLOCK(handler_lock);

static struct reiserfs_xattr_handler *find_xattr_handler_prefix(const char
								*prefix)
{
	struct reiserfs_xattr_handler *xah = NULL;
	struct list_head *p;

	read_lock(&handler_lock);
	list_for_each(p, &xattr_handlers) {
		xah = list_entry(p, struct reiserfs_xattr_handler, handlers);
		if (strncmp(xah->prefix, prefix, strlen(xah->prefix)) == 0)
			break;
		xah = NULL;
	}

	read_unlock(&handler_lock);
	return xah;
}

static void __unregister_handlers(void)
{
	struct reiserfs_xattr_handler *xah;
	struct list_head *p, *tmp;

	list_for_each_safe(p, tmp, &xattr_handlers) {
		xah = list_entry(p, struct reiserfs_xattr_handler, handlers);
		if (xah->exit)
			xah->exit();

		list_del_init(p);
	}
	INIT_LIST_HEAD(&xattr_handlers);
}

int __init reiserfs_xattr_register_handlers(void)
{
	int err = 0;
	struct reiserfs_xattr_handler *xah;
	struct list_head *p;

	write_lock(&handler_lock);

	/* If we're already initialized, nothing to do */
	if (!list_empty(&xattr_handlers)) {
		write_unlock(&handler_lock);
		return 0;
	}

	/* Add the handlers */
	list_add_tail(&user_handler.handlers, &xattr_handlers);
	list_add_tail(&trusted_handler.handlers, &xattr_handlers);
#ifdef CONFIG_REISERFS_FS_SECURITY
	list_add_tail(&security_handler.handlers, &xattr_handlers);
#endif
#ifdef CONFIG_REISERFS_FS_POSIX_ACL
	list_add_tail(&posix_acl_access_handler.handlers, &xattr_handlers);
	list_add_tail(&posix_acl_default_handler.handlers, &xattr_handlers);
#endif

	/* Run initializers, if available */
	list_for_each(p, &xattr_handlers) {
		xah = list_entry(p, struct reiserfs_xattr_handler, handlers);
		if (xah->init) {
			err = xah->init();
			if (err) {
				list_del_init(p);
				break;
			}
		}
	}

	/* Clean up other handlers, if any failed */
	if (err)
		__unregister_handlers();

	write_unlock(&handler_lock);
	return err;
}

void reiserfs_xattr_unregister_handlers(void)
{
	write_lock(&handler_lock);
	__unregister_handlers();
	write_unlock(&handler_lock);
}

static int reiserfs_check_acl(struct inode *inode, int mask)
{
	struct posix_acl *acl;
	int error = -EAGAIN; /* do regular unix permission checks by default */

	reiserfs_read_lock_xattr_i(inode);
	reiserfs_read_lock_xattrs(inode->i_sb);

	acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);

	reiserfs_read_unlock_xattrs(inode->i_sb);
	reiserfs_read_unlock_xattr_i(inode);

	if (acl) {
		if (!IS_ERR(acl)) {
			error = posix_acl_permission(inode, acl, mask);
			posix_acl_release(acl);
		} else if (PTR_ERR(acl) != -ENODATA)
			error = PTR_ERR(acl);
	}

	return error;
}

int reiserfs_permission(struct inode *inode, int mask)
{
	/*
	 * We don't do permission checks on the internal objects.
	 * Permissions are determined by the "owning" object.
	 */
	if (IS_PRIVATE(inode))
		return 0;
	/*
	 * Stat data v1 doesn't support ACLs.
	 */
	if (get_inode_sd_version(inode) == STAT_DATA_V1)
		return generic_permission(inode, mask, NULL);
	else
		return generic_permission(inode, mask, reiserfs_check_acl);
}

static int create_privroot(struct dentry *dentry)
{
	int err;
	struct inode *inode = dentry->d_parent->d_inode;
	mutex_lock_nested(&inode->i_mutex, I_MUTEX_XATTR);
	err = inode->i_op->mkdir(inode, dentry, 0700);
	mutex_unlock(&inode->i_mutex);
	if (err) {
		dput(dentry);
		dentry = NULL;
	}

	if (dentry && dentry->d_inode)
		reiserfs_info(dentry->d_sb, "Created %s - reserved for xattr "
			      "storage.\n", PRIVROOT_NAME);

	return err;
}

static int xattr_mount_check(struct super_block *s)
{
	/* We need generation numbers to ensure that the oid mapping is correct
	 * v3.5 filesystems don't have them. */
	if (!old_format_only(s)) {
		set_bit(REISERFS_XATTRS, &(REISERFS_SB(s)->s_mount_opt));
	} else if (reiserfs_xattrs_optional(s)) {
		/* Old format filesystem, but optional xattrs have been enabled
		 * at mount time. Error out. */
		reiserfs_warning(s, "jdm-20005",
				 "xattrs/ACLs not supported on pre v3.6 "
				 "format filesystem. Failing mount.");
		return -EOPNOTSUPP;
	} else {
		/* Old format filesystem, but no optional xattrs have
		 * been enabled. This means we silently disable xattrs
		 * on the filesystem. */
		clear_bit(REISERFS_XATTRS, &(REISERFS_SB(s)->s_mount_opt));
	}

	return 0;
}

#else
int __init reiserfs_xattr_register_handlers(void) { return 0; }
void reiserfs_xattr_unregister_handlers(void) {}
#endif

/* This will catch lookups from the fs root to .reiserfs_priv */
static int
xattr_lookup_poison(struct dentry *dentry, struct qstr *q1, struct qstr *name)
{
	struct dentry *priv_root = REISERFS_SB(dentry->d_sb)->priv_root;
	if (name->len == priv_root->d_name.len &&
	    name->hash == priv_root->d_name.hash &&
	    !memcmp(name->name, priv_root->d_name.name, name->len)) {
		return -ENOENT;
	} else if (q1->len == name->len &&
		   !memcmp(q1->name, name->name, name->len))
		return 0;
	return 1;
}

static struct dentry_operations xattr_lookup_poison_ops = {
	.d_compare = xattr_lookup_poison,
};

/* We need to take a copy of the mount flags since things like
 * MS_RDONLY don't get set until *after* we're called.
 * mount_flags != mount_options */
int reiserfs_xattr_init(struct super_block *s, int mount_flags)
{
	int err = 0;

#ifdef CONFIG_REISERFS_FS_XATTR
	err = xattr_mount_check(s);
	if (err)
		goto error;
#endif

	/* If we don't have the privroot located yet - go find it */
	if (!REISERFS_SB(s)->priv_root) {
		struct dentry *dentry;
		dentry = lookup_one_len(PRIVROOT_NAME, s->s_root,
					strlen(PRIVROOT_NAME));
		if (!IS_ERR(dentry)) {
#ifdef CONFIG_REISERFS_FS_XATTR
			if (!(mount_flags & MS_RDONLY) && !dentry->d_inode)
				err = create_privroot(dentry);
#endif
			if (!dentry->d_inode) {
				dput(dentry);
				dentry = NULL;
			}
		} else
			err = PTR_ERR(dentry);

		if (!err && dentry) {
			s->s_root->d_op = &xattr_lookup_poison_ops;
			dentry->d_inode->i_flags |= S_PRIVATE;
			REISERFS_SB(s)->priv_root = dentry;
#ifdef CONFIG_REISERFS_FS_XATTR
		/* xattrs are unavailable */
		} else if (!(mount_flags & MS_RDONLY)) {
			/* If we're read-only it just means that the dir
			 * hasn't been created. Not an error -- just no
			 * xattrs on the fs. We'll check again if we
			 * go read-write */
			reiserfs_warning(s, "jdm-20006",
					 "xattrs/ACLs enabled and couldn't "
					 "find/create .reiserfs_priv. "
					 "Failing mount.");
			err = -EOPNOTSUPP;
#endif
		}
	}

#ifdef CONFIG_REISERFS_FS_XATTR
error:
	if (err) {
		clear_bit(REISERFS_XATTRS, &(REISERFS_SB(s)->s_mount_opt));
		clear_bit(REISERFS_XATTRS_USER, &(REISERFS_SB(s)->s_mount_opt));
		clear_bit(REISERFS_POSIXACL, &(REISERFS_SB(s)->s_mount_opt));
	}
#endif

	/* The super_block MS_POSIXACL must mirror the (no)acl mount option. */
	s->s_flags = s->s_flags & ~MS_POSIXACL;
#ifdef CONFIG_REISERFS_FS_POSIX_ACL
	if (reiserfs_posixacl(s))
		s->s_flags |= MS_POSIXACL;
#endif

	return err;
}