Free Electrons

Embedded Linux Experts

   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
/*
 * 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.
 *
 * Locking works like so:
 * Directory components (xattr root, xattr dir) are protectd by their i_mutex.
 * The xattrs themselves are protected by the xattr_sem.
 */

#include "reiserfs.h"
#include <linux/capability.h>
#include <linux/dcache.h>
#include <linux/namei.h>
#include <linux/errno.h>
#include <linux/gfp.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
#include "xattr.h"
#include "acl.h"
#include <asm/uaccess.h>
#include <net/checksum.h>
#include <linux/stat.h>
#include <linux/quotaops.h>
#include <linux/security.h>

#define PRIVROOT_NAME ".reiserfs_priv"
#define XAROOT_NAME   "xattrs"


/* Helpers for inode ops. We do this so that we don't have all the VFS
 * overhead and also for proper i_mutex annotation.
 * dir->i_mutex must be held for all of them. */
#ifdef CONFIG_REISERFS_FS_XATTR
static int xattr_create(struct inode *dir, struct dentry *dentry, int mode)
{
	BUG_ON(!mutex_is_locked(&dir->i_mutex));
	return dir->i_op->create(dir, dentry, mode, NULL);
}
#endif

static int xattr_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
	BUG_ON(!mutex_is_locked(&dir->i_mutex));
	return dir->i_op->mkdir(dir, dentry, mode);
}

/* We use I_MUTEX_CHILD here to silence lockdep. It's safe because xattr
 * mutation ops aren't called during rename or splace, which are the
 * only other users of I_MUTEX_CHILD. It violates the ordering, but that's
 * better than allocating another subclass just for this code. */
static int xattr_unlink(struct inode *dir, struct dentry *dentry)
{
	int error;
	BUG_ON(!mutex_is_locked(&dir->i_mutex));

	reiserfs_mutex_lock_nested_safe(&dentry->d_inode->i_mutex,
					I_MUTEX_CHILD, dir->i_sb);
	error = dir->i_op->unlink(dir, dentry);
	mutex_unlock(&dentry->d_inode->i_mutex);

	if (!error)
		d_delete(dentry);
	return error;
}

static int xattr_rmdir(struct inode *dir, struct dentry *dentry)
{
	int error;
	BUG_ON(!mutex_is_locked(&dir->i_mutex));

	reiserfs_mutex_lock_nested_safe(&dentry->d_inode->i_mutex,
					I_MUTEX_CHILD, dir->i_sb);
	error = dir->i_op->rmdir(dir, dentry);
	if (!error)
		dentry->d_inode->i_flags |= S_DEAD;
	mutex_unlock(&dentry->d_inode->i_mutex);
	if (!error)
		d_delete(dentry);

	return error;
}

#define xattr_may_create(flags)	(!flags || flags & XATTR_CREATE)

static struct dentry *open_xa_root(struct super_block *sb, int flags)
{
	struct dentry *privroot = REISERFS_SB(sb)->priv_root;
	struct dentry *xaroot;
	if (!privroot->d_inode)
		return ERR_PTR(-ENODATA);

	mutex_lock_nested(&privroot->d_inode->i_mutex, I_MUTEX_XATTR);

	xaroot = dget(REISERFS_SB(sb)->xattr_root);
	if (!xaroot)
		xaroot = ERR_PTR(-ENODATA);
	else if (!xaroot->d_inode) {
		int err = -ENODATA;
		if (xattr_may_create(flags))
			err = xattr_mkdir(privroot->d_inode, xaroot, 0700);
		if (err) {
			dput(xaroot);
			xaroot = ERR_PTR(err);
		}
	}

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

static struct dentry *open_xa_dir(const struct inode *inode, int flags)
{
	struct dentry *xaroot, *xadir;
	char namebuf[17];

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

	snprintf(namebuf, sizeof(namebuf), "%X.%X",
		 le32_to_cpu(INODE_PKEY(inode)->k_objectid),
		 inode->i_generation);

	mutex_lock_nested(&xaroot->d_inode->i_mutex, I_MUTEX_XATTR);

	xadir = lookup_one_len(namebuf, xaroot, strlen(namebuf));
	if (!IS_ERR(xadir) && !xadir->d_inode) {
		int err = -ENODATA;
		if (xattr_may_create(flags))
			err = xattr_mkdir(xaroot->d_inode, xadir, 0700);
		if (err) {
			dput(xadir);
			xadir = ERR_PTR(err);
		}
	}

	mutex_unlock(&xaroot->d_inode->i_mutex);
	dput(xaroot);
	return xadir;
}

/* 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. */
struct reiserfs_dentry_buf {
	struct dentry *xadir;
	int count;
	struct dentry *dentries[8];
};

static int
fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset,
		    u64 ino, unsigned int d_type)
{
	struct reiserfs_dentry_buf *dbuf = buf;
	struct dentry *dentry;
	WARN_ON_ONCE(!mutex_is_locked(&dbuf->xadir->d_inode->i_mutex));

	if (dbuf->count == ARRAY_SIZE(dbuf->dentries))
		return -ENOSPC;

	if (name[0] == '.' && (name[1] == '\0' ||
			       (name[1] == '.' && name[2] == '\0')))
		return 0;

	dentry = lookup_one_len(name, dbuf->xadir, namelen);
	if (IS_ERR(dentry)) {
		return PTR_ERR(dentry);
	} else if (!dentry->d_inode) {
		/* A directory entry exists, but no file? */
		reiserfs_error(dentry->d_sb, "xattr-20003",
			       "Corrupted directory: xattr %s listed but "
			       "not found for file %s.\n",
			       dentry->d_name.name, dbuf->xadir->d_name.name);
		dput(dentry);
		return -EIO;
	}

	dbuf->dentries[dbuf->count++] = dentry;
	return 0;
}

static void
cleanup_dentry_buf(struct reiserfs_dentry_buf *buf)
{
	int i;
	for (i = 0; i < buf->count; i++)
		if (buf->dentries[i])
			dput(buf->dentries[i]);
}

static int reiserfs_for_each_xattr(struct inode *inode,
				   int (*action)(struct dentry *, void *),
				   void *data)
{
	struct dentry *dir;
	int i, err = 0;
	loff_t pos = 0;
	struct reiserfs_dentry_buf buf = {
		.count = 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_write_unlock(inode->i_sb);
	dir = open_xa_dir(inode, XATTR_REPLACE);
	if (IS_ERR(dir)) {
		err = PTR_ERR(dir);
		reiserfs_write_lock(inode->i_sb);
		goto out;
	} else if (!dir->d_inode) {
		err = 0;
		reiserfs_write_lock(inode->i_sb);
		goto out_dir;
	}

	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_XATTR);

	reiserfs_write_lock(inode->i_sb);

	buf.xadir = dir;
	err = reiserfs_readdir_dentry(dir, &buf, fill_with_dentries, &pos);
	while ((err == 0 || err == -ENOSPC) && buf.count) {
		err = 0;

		for (i = 0; i < buf.count && buf.dentries[i]; i++) {
			int lerr = 0;
			struct dentry *dentry = buf.dentries[i];

			if (err == 0 && !S_ISDIR(dentry->d_inode->i_mode))
				lerr = action(dentry, data);

			dput(dentry);
			buf.dentries[i] = NULL;
			err = lerr ?: err;
		}
		buf.count = 0;
		if (!err)
			err = reiserfs_readdir_dentry(dir, &buf,
						      fill_with_dentries, &pos);
	}
	mutex_unlock(&dir->d_inode->i_mutex);

	/* Clean up after a failed readdir */
	cleanup_dentry_buf(&buf);

	if (!err) {
		/* We start a transaction here to avoid a ABBA situation
		 * between the xattr root's i_mutex and the journal lock.
		 * This doesn't incur much additional overhead since the
		 * new transaction will just nest inside the
		 * outer transaction. */
		int blocks = JOURNAL_PER_BALANCE_CNT * 2 + 2 +
			     4 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
		struct reiserfs_transaction_handle th;
		err = journal_begin(&th, inode->i_sb, blocks);
		if (!err) {
			int jerror;
			reiserfs_mutex_lock_nested_safe(
					  &dir->d_parent->d_inode->i_mutex,
					  I_MUTEX_XATTR, inode->i_sb);
			err = action(dir, data);
			jerror = journal_end(&th, inode->i_sb, blocks);
			mutex_unlock(&dir->d_parent->d_inode->i_mutex);
			err = jerror ?: err;
		}
	}
out_dir:
	dput(dir);
out:
	/* -ENODATA isn't an error */
	if (err == -ENODATA)
		err = 0;
	return err;
}

static int delete_one_xattr(struct dentry *dentry, void *data)
{
	struct inode *dir = dentry->d_parent->d_inode;

	/* This is the xattr dir, handle specially. */
	if (S_ISDIR(dentry->d_inode->i_mode))
		return xattr_rmdir(dir, dentry);

	return xattr_unlink(dir, dentry);
}

static int chown_one_xattr(struct dentry *dentry, void *data)
{
	struct iattr *attrs = data;
	return reiserfs_setattr(dentry, attrs);
}

/* No i_mutex, but the inode is unconnected. */
int reiserfs_delete_xattrs(struct inode *inode)
{
	int err = reiserfs_for_each_xattr(inode, delete_one_xattr, NULL);
	if (err)
		reiserfs_warning(inode->i_sb, "jdm-20004",
				 "Couldn't delete all xattrs (%d)\n", err);
	return err;
}

/* inode->i_mutex: down */
int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs)
{
	int err = reiserfs_for_each_xattr(inode, chown_one_xattr, attrs);
	if (err)
		reiserfs_warning(inode->i_sb, "jdm-20007",
				 "Couldn't chown all xattrs (%d)\n", err);
	return err;
}

#ifdef CONFIG_REISERFS_FS_XATTR
/* 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 *xattr_lookup(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);

	mutex_lock_nested(&xadir->d_inode->i_mutex, I_MUTEX_XATTR);
	xafile = lookup_one_len(name, xadir, strlen(name));
	if (IS_ERR(xafile)) {
		err = PTR_ERR(xafile);
		goto out;
	}

	if (xafile->d_inode && (flags & XATTR_CREATE))
		err = -EEXIST;

	if (!xafile->d_inode) {
		err = -ENODATA;
		if (xattr_may_create(flags))
			err = xattr_create(xadir->d_inode, xafile,
					      0700|S_IFREG);
	}

	if (err)
		dput(xafile);
out:
	mutex_unlock(&xadir->d_inode->i_mutex);
	dput(xadir);
	if (err)
		return ERR_PTR(err);
	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 occurred - 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);

static void update_ctime(struct inode *inode)
{
	struct timespec now = current_fs_time(inode->i_sb);
	if (inode_unhashed(inode) || !inode->i_nlink ||
	    timespec_equal(&inode->i_ctime, &now))
		return;

	inode->i_ctime = CURRENT_TIME_SEC;
	mark_inode_dirty(inode);
}

static int lookup_and_delete_xattr(struct inode *inode, const char *name)
{
	int err = 0;
	struct dentry *dentry, *xadir;

	xadir = open_xa_dir(inode, XATTR_REPLACE);
	if (IS_ERR(xadir))
		return PTR_ERR(xadir);

	mutex_lock_nested(&xadir->d_inode->i_mutex, I_MUTEX_XATTR);
	dentry = lookup_one_len(name, xadir, strlen(name));
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out_dput;
	}

	if (dentry->d_inode) {
		reiserfs_write_lock(inode->i_sb);
		err = xattr_unlink(xadir->d_inode, dentry);
		reiserfs_write_unlock(inode->i_sb);
		update_ctime(inode);
	}

	dput(dentry);
out_dput:
	mutex_unlock(&xadir->d_inode->i_mutex);
	dput(xadir);
	return err;
}


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

/*
 * inode->i_mutex: down
 */
int
reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
			  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;
	size_t new_size;
	__u32 xahash = 0;

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

	reiserfs_write_unlock(inode->i_sb);

	if (!buffer) {
		err = lookup_and_delete_xattr(inode, name);
		reiserfs_write_lock(inode->i_sb);
		return err;
	}

	dentry = xattr_lookup(inode, name, flags);
	if (IS_ERR(dentry)) {
		reiserfs_write_lock(inode->i_sb);
		return PTR_ERR(dentry);
	}

	down_write(&REISERFS_I(inode)->i_xattr_sem);

	reiserfs_write_lock(inode->i_sb);

	xahash = xattr_hash(buffer, buffer_size);
	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_unlock;
		}

		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_write_begin(page, 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;
	}

	new_size = buffer_size + sizeof(struct reiserfs_xattr_header);
	if (!err && new_size < i_size_read(dentry->d_inode)) {
		struct iattr newattrs = {
			.ia_ctime = current_fs_time(inode->i_sb),
			.ia_size = new_size,
			.ia_valid = ATTR_SIZE | ATTR_CTIME,
		};

		reiserfs_write_unlock(inode->i_sb);
		mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR);
		inode_dio_wait(dentry->d_inode);
		reiserfs_write_lock(inode->i_sb);

		err = reiserfs_setattr(dentry, &newattrs);
		mutex_unlock(&dentry->d_inode->i_mutex);
	} else
		update_ctime(inode);
out_unlock:
	up_write(&REISERFS_I(inode)->i_xattr_sem);
	dput(dentry);
	return err;
}

/* We need to start a transaction to maintain lock ordering */
int reiserfs_xattr_set(struct inode *inode, const char *name,
		       const void *buffer, size_t buffer_size, int flags)
{

	struct reiserfs_transaction_handle th;
	int error, error2;
	size_t jbegin_count = reiserfs_xattr_nblocks(inode, buffer_size);

	if (!(flags & XATTR_REPLACE))
		jbegin_count += reiserfs_xattr_jcreate_nblocks(inode);

	reiserfs_write_lock(inode->i_sb);
	error = journal_begin(&th, inode->i_sb, jbegin_count);
	if (error) {
		reiserfs_write_unlock(inode->i_sb);
		return error;
	}

	error = reiserfs_xattr_set_handle(&th, inode, name,
					  buffer, buffer_size, flags);

	error2 = journal_end(&th, inode->i_sb, jbegin_count);
	if (error == 0)
		error = error2;
	reiserfs_write_unlock(inode->i_sb);

	return error;
}

/*
 * inode->i_mutex: down
 */
int
reiserfs_xattr_get(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 = xattr_lookup(inode, name, XATTR_REPLACE);
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out;
	}

	down_read(&REISERFS_I(inode)->i_xattr_sem);

	isize = i_size_read(dentry->d_inode);

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

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

	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_unlock;
		}

		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_unlock;
			}
			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_unlock:
	up_read(&REISERFS_I(inode)->i_xattr_sem);
	dput(dentry);

out:
	return err;
}

/*
 * In order to implement different sets of xattr operations for each xattr
 * prefix with the generic xattr API, a filesystem should create a
 * null-terminated array of struct xattr_handler (one for each prefix) and
 * hang a pointer to it off of the s_xattr field of the superblock.
 *
 * The generic_fooxattr() functions will use this list to dispatch xattr
 * operations to the correct xattr_handler.
 */
#define for_each_xattr_handler(handlers, handler)		\
		for ((handler) = *(handlers)++;			\
			(handler) != NULL;			\
			(handler) = *(handlers)++)

/* This is the implementation for the xattr plugin infrastructure */
static inline const struct xattr_handler *
find_xattr_handler_prefix(const struct xattr_handler **handlers,
			   const char *name)
{
	const struct xattr_handler *xah;

	if (!handlers)
		return NULL;

	for_each_xattr_handler(handlers, xah) {
		if (strncmp(xah->prefix, name, strlen(xah->prefix)) == 0)
			break;
	}

	return xah;
}


/*
 * Inode operation getxattr()
 */
ssize_t
reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer,
		  size_t size)
{
	const struct xattr_handler *handler;

	handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);

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

	return handler->get(dentry, name, buffer, size, handler->flags);
}

/*
 * 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)
{
	const struct xattr_handler *handler;

	handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);

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

	return handler->set(dentry, name, value, size, flags, handler->flags);
}

/*
 * Inode operation removexattr()
 *
 * dentry->d_inode->i_mutex down
 */
int reiserfs_removexattr(struct dentry *dentry, const char *name)
{
	const struct xattr_handler *handler;
	handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);

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

	return handler->set(dentry, name, NULL, 0, XATTR_REPLACE, handler->flags);
}

struct listxattr_buf {
	size_t size;
	size_t pos;
	char *buf;
	struct dentry *dentry;
};

static int listxattr_filler(void *buf, const char *name, int namelen,
			    loff_t offset, u64 ino, unsigned int d_type)
{
	struct listxattr_buf *b = (struct listxattr_buf *)buf;
	size_t size;
	if (name[0] != '.' ||
	    (namelen != 1 && (name[1] != '.' || namelen != 2))) {
		const struct xattr_handler *handler;
		handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr,
						    name);
		if (!handler)	/* Unsupported xattr name */
			return 0;
		if (b->buf) {
			size = handler->list(b->dentry, b->buf + b->pos,
					 b->size, name, namelen,
					 handler->flags);
			if (size > b->size)
				return -ERANGE;
		} else {
			size = handler->list(b->dentry, NULL, 0, name,
					     namelen, handler->flags);
		}

		b->pos += size;
	}
	return 0;
}

/*
 * Inode operation listxattr()
 *
 * We totally ignore the generic listxattr here because it would be stupid
 * not to. Since the xattrs are organized in a directory, we can just
 * readdir to find them.
 */
ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size)
{
	struct dentry *dir;
	int err = 0;
	loff_t pos = 0;
	struct listxattr_buf buf = {
		.dentry = dentry,
		.buf = buffer,
		.size = buffer ? size : 0,
	};

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

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

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

	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_XATTR);
	err = reiserfs_readdir_dentry(dir, &buf, listxattr_filler, &pos);
	mutex_unlock(&dir->d_inode->i_mutex);

	if (!err)
		err = buf.pos;

	dput(dir);
out:
	return err;
}

static int create_privroot(struct dentry *dentry)
{
	int err;
	struct inode *inode = dentry->d_parent->d_inode;
	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));

	err = xattr_mkdir(inode, dentry, 0700);
	if (err || !dentry->d_inode) {
		reiserfs_warning(dentry->d_sb, "jdm-20006",
				 "xattrs/ACLs enabled and couldn't "
				 "find/create .reiserfs_priv. "
				 "Failing mount.");
		return -EOPNOTSUPP;
	}

	dentry->d_inode->i_flags |= S_PRIVATE;
	reiserfs_info(dentry->d_sb, "Created %s - reserved for xattr "
		      "storage.\n", PRIVROOT_NAME);

	return 0;
}

#else
int __init reiserfs_xattr_register_handlers(void) { return 0; }
void reiserfs_xattr_unregister_handlers(void) {}
static int create_privroot(struct dentry *dentry) { return 0; }
#endif

/* Actual operations that are exported to VFS-land */
const struct xattr_handler *reiserfs_xattr_handlers[] = {
#ifdef CONFIG_REISERFS_FS_XATTR
	&reiserfs_xattr_user_handler,
	&reiserfs_xattr_trusted_handler,
#endif
#ifdef CONFIG_REISERFS_FS_SECURITY
	&reiserfs_xattr_security_handler,
#endif
#ifdef CONFIG_REISERFS_FS_POSIX_ACL
	&reiserfs_posix_acl_access_handler,
	&reiserfs_posix_acl_default_handler,
#endif
	NULL
};

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)) {
		if (reiserfs_xattrs_optional(s)) {
			/* Old format filesystem, but optional xattrs have
			 * been enabled. Error out. */
			reiserfs_warning(s, "jdm-2005",
					 "xattrs/ACLs not supported "
					 "on pre-v3.6 format filesystems. "
					 "Failing mount.");
			return -EOPNOTSUPP;
		}
	}

	return 0;
}

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;

	return generic_permission(inode, mask);
}

static int xattr_hide_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	return -EPERM;
}

static const struct dentry_operations xattr_lookup_poison_ops = {
	.d_revalidate = xattr_hide_revalidate,
};

int reiserfs_lookup_privroot(struct super_block *s)
{
	struct dentry *dentry;
	int err = 0;

	/* If we don't have the privroot located yet - go find it */
	reiserfs_mutex_lock_safe(&s->s_root->d_inode->i_mutex, s);
	dentry = lookup_one_len(PRIVROOT_NAME, s->s_root,
				strlen(PRIVROOT_NAME));
	if (!IS_ERR(dentry)) {
		REISERFS_SB(s)->priv_root = dentry;
		d_set_d_op(dentry, &xattr_lookup_poison_ops);
		if (dentry->d_inode)
			dentry->d_inode->i_flags |= S_PRIVATE;
	} else
		err = PTR_ERR(dentry);
	mutex_unlock(&s->s_root->d_inode->i_mutex);

	return err;
}

/* 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;
	struct dentry *privroot = REISERFS_SB(s)->priv_root;

	err = xattr_mount_check(s);
	if (err)
		goto error;

	if (!privroot->d_inode && !(mount_flags & MS_RDONLY)) {
		reiserfs_mutex_lock_safe(&s->s_root->d_inode->i_mutex, s);
		err = create_privroot(REISERFS_SB(s)->priv_root);
		mutex_unlock(&s->s_root->d_inode->i_mutex);
	}

	if (privroot->d_inode) {
		s->s_xattr = reiserfs_xattr_handlers;
		reiserfs_mutex_lock_safe(&privroot->d_inode->i_mutex, s);
		if (!REISERFS_SB(s)->xattr_root) {
			struct dentry *dentry;
			dentry = lookup_one_len(XAROOT_NAME, privroot,
						strlen(XAROOT_NAME));
			if (!IS_ERR(dentry))
				REISERFS_SB(s)->xattr_root = dentry;
			else
				err = PTR_ERR(dentry);
		}
		mutex_unlock(&privroot->d_inode->i_mutex);
	}

error:
	if (err) {
		clear_bit(REISERFS_XATTRS_USER, &(REISERFS_SB(s)->s_mount_opt));
		clear_bit(REISERFS_POSIXACL, &(REISERFS_SB(s)->s_mount_opt));
	}

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

	return err;
}