Linux Audio

Check our new training course

Embedded Linux Audio

Check our new training course
with Creative Commons CC-BY-SA
lecture materials

Bootlin logo

Elixir Cross Referencer

Loading...
   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
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
/*
 * linux/fs/nfsd/vfs.c
 *
 * File operations used by nfsd. Some of these have been ripped from
 * other parts of the kernel because they weren't in ksyms.c, others
 * are partial duplicates with added or changed functionality.
 *
 * Note that several functions dget() the dentry upon which they want
 * to act, most notably those that create directory entries. Response
 * dentry's are dput()'d if necessary in the release callback.
 * So if you notice code paths that apparently fail to dput() the
 * dentry, don't worry--they have been taken care of.
 *
 * Copyright (C) 1995-1999 Olaf Kirch <okir@monad.swb.de>
 */

#include <linux/config.h>
#include <linux/version.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/locks.h>
#include <linux/fs.h>
#include <linux/major.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/net.h>
#include <linux/unistd.h>
#include <linux/malloc.h>
#include <linux/in.h>

#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#ifdef CONFIG_NFSD_V3
#include <linux/nfs3.h>
#include <linux/nfsd/xdr3.h>
#endif /* CONFIG_NFSD_V3 */
#include <linux/nfsd/nfsfh.h>
#include <linux/quotaops.h>

#if LINUX_VERSION_CODE >= 0x020100
#include <asm/uaccess.h>
#endif

#define NFSDDBG_FACILITY		NFSDDBG_FILEOP
#define NFSD_PARANOIA


/* We must ignore files (but only files) which might have mandatory
 * locks on them because there is no way to know if the accesser has
 * the lock.
 */
/* MANDATORY_LOCK taken from 2.3 */
#define MANDATORY_LOCK(inode) \
	(IS_MANDLOCK(inode) && ((inode)->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
#define IS_ISMNDLK(i)	(S_ISREG((i)->i_mode) && MANDATORY_LOCK(i))
/* Time difference margin in seconds for comparison. It is a
   dynamically-tunable parameter via /proc/fs/nfs/time-diff-margin.
 */
extern long nfsd_time_diff_margin;

/*
 * This is a cache of readahead params that help us choose the proper
 * readahead strategy. Initially, we set all readahead parameters to 0
 * and let the VFS handle things.
 * If you increase the number of cached files very much, you'll need to
 * add a hash table here.
 */
struct raparms {
	struct raparms		*p_next;
	unsigned int		p_count;
	ino_t			p_ino;
	dev_t			p_dev;
	unsigned long		p_reada,
				p_ramax,
				p_raend,
				p_ralen,
				p_rawin;
};

int nfsd_nservers = 0;
#define FILECACHE_MAX		(2 * nfsd_nservers) 
static struct raparms *		raparml = NULL;
static struct raparms *		raparm_cache = NULL;


/*
 * We need to do a check-parent every time
 * after we have locked the parent - to verify
 * that the parent is still our parent and
 * that we are still hashed onto it..
 *
 * This is required in case two processes race
 * on removing (or moving) the same entry: the
 * parent lock will serialize them, but the
 * other process will be too late..
 *
 * Note that this nfsd_check_parent is identical
 * the check_parent in linux/fs/namei.c.
 */
#define nfsd_check_parent(dir, dentry) \
	((dir) == (dentry)->d_parent && !list_empty(&dentry->d_hash))

/*
 * Lock a parent directory following the VFS locking protocol.
 */
int
fh_lock_parent(struct svc_fh *parent_fh, struct dentry *dchild)
{
	fh_lock(parent_fh);
	/*
	 * Make sure the parent->child relationship still holds,
	 * and that the child is still hashed.
	 */
	if (nfsd_check_parent(parent_fh->fh_dentry, dchild))
	    return 0;

	printk(KERN_WARNING
		"fh_lock_parent: %s/%s parent changed or child unhashed\n",
		dchild->d_parent->d_name.name, dchild->d_name.name);

	fh_unlock(parent_fh);
	return nfserr_noent;
}


/*
 * Look up one component of a pathname.
 * N.B. After this call _both_ fhp and resfh need an fh_put
 *
 * If the lookup would cross a mountpoint, and the mounted filesystem
 * is exported to the client with NFSEXP_CROSSMNT, then the lookup is
 * accepted as it stands and the mounted directory is
 * returned. Otherwise the covered directory is returned.
 * NOTE: this mountpoint crossing is not supported properly by all
 *   clients and is explicitly disallowed for NFSv3
 *      NeilBrown <neilb@cse.unsw.edu.au>
 */
int
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
					int len, struct svc_fh *resfh)
{
	struct svc_export	*exp;
	struct dentry		*dparent, *dchild;
	int			err;

	dprintk("nfsd: nfsd_lookup(fh %p, %s)\n", SVCFH_DENTRY(fhp), name);

	/* Obtain dentry and export. */
	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC);
	if (err)
		goto out;

	dparent = fhp->fh_dentry;
	exp  = fhp->fh_export;

	err = nfserr_acces;

	/* Lookup the name, but don't follow links */
	if (strcmp(name, ".")==0) {
		dchild = dget(dparent);
	} else if (strcmp(name, "..")==0) {
		/* checking mountpoint crossing is very different when stepping up */
		if (dparent == exp->ex_dentry) {
			if (!EX_CROSSMNT(exp))
				dchild = dget(dparent); /* .. == . just like at / */
			else
			{
				struct svc_export *exp2 = NULL;
				struct dentry *dp;
				dchild = dparent->d_covers->d_parent;
				for (dp=dchild;
				     exp2 == NULL && dp->d_covers->d_parent != dp;
				     dp=dp->d_covers->d_parent)
					exp2 = exp_get(exp->ex_client, dp->d_inode->i_dev, dp->d_inode->i_ino);
				if (exp2==NULL || dchild->d_sb != exp2->ex_dentry->d_sb) {
					dchild = dget(dparent);
				} else {
					dget(dchild);
					exp = exp2;
				}
			}
		} else
			dchild = dget(dparent->d_parent);
	} else {
		dchild = lookup_dentry(name, dget(dparent), 0);
		if (IS_ERR(dchild))
			goto out_nfserr;
		/*
		 * check if we have crossed a mount point ...
		 */
		if (dchild->d_sb != dparent->d_sb) {
			struct svc_export *exp2 = NULL;
			exp2 = exp_get(rqstp->rq_client,
				       dchild->d_inode->i_dev,
				       dchild->d_inode->i_ino);
			if (exp2 && EX_CROSSMNT(exp2))
				/* successfully crossed mount point */
				exp = exp2;
			else if (dchild->d_covers->d_sb == dparent->d_sb) {
				/* stay in the original filesystem */
				struct dentry *tdentry = dget(dchild->d_covers);
				dput(dchild);
				dchild = tdentry;
			} else {
				/* This cannot possibly happen */
				printk("nfsd_lookup: %s/%s impossible mount point!\n", dparent->d_name.name, dchild->d_name.name);
				dput(dchild);
				err = nfserr_acces;
				goto out;

			}
		}
	}
	/*
	 * Note: we compose the file handle now, but as the
	 * dentry may be negative, it may need to be updated.
	 */
	fh_compose(resfh, exp, dchild);
	err = nfserr_noent;
	if (dchild->d_inode)
		err = 0;
out:
	return err;

out_nfserr:
	err = nfserrno(PTR_ERR(dchild));
	goto out;
}

/*
 * Set various file attributes.
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap)
{
	struct dentry	*dentry;
	struct inode	*inode;
	int		accmode = MAY_SATTR;
	int		ftype = 0;
	int		imode;
	int		err;
	kernel_cap_t	saved_cap = 0;
	int		size_change = 0;

	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
		accmode |= MAY_WRITE;
	if (iap->ia_valid & ATTR_SIZE)
		ftype = S_IFREG;

	/* Get inode */
	err = fh_verify(rqstp, fhp, ftype, accmode);
	if (err || !iap->ia_valid)
		goto out;

	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;

	err = inode_change_ok(inode, iap);
	/* could be a "touch" (utimes) request where the user is not the owner but does
	 * have write permission. In this case the user should be allowed to set
	 * both times to the current time.  We could just assume any such SETATTR
	 * is intended to set the times to "now", but we do a couple of simple tests
	 * to increase our confidence.
	 */
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define	MAX_TOUCH_TIME_ERROR (30*60)
	if (err
	    && (iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET
	    && iap->ia_mtime == iap->ia_ctime
	    ) {
	    /* looks good.  now just make sure time is in the right ballpark.
	     * solaris, at least, doesn't seem to care what the time request is
	     */
	    time_t delta = iap->ia_atime - CURRENT_TIME;
	    if (delta<0) delta = -delta;
	    if (delta < MAX_TOUCH_TIME_ERROR) {
		/* turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME
		 * this will cause notify_change to set these times to "now"
		 */
		iap->ia_valid &= ~BOTH_TIME_SET;
		err = inode_change_ok(inode, iap);
	    }
	}

	if (err)
		goto out_nfserr;

	/* The size case is special. It changes the file as well as the attributes.  */
	if (iap->ia_valid & ATTR_SIZE) {
		if (iap->ia_size < inode->i_size) {
			err = nfsd_permission(fhp->fh_export, dentry, MAY_TRUNC);
			if (err)
				goto out;
		}
		err = get_write_access(inode);
		if (err)
			goto out_nfserr;
		size_change = 1;

		DQUOT_INIT(inode);
	}

	imode = inode->i_mode;
	if (iap->ia_valid & ATTR_MODE) {
		iap->ia_mode &= S_IALLUGO;
		imode = iap->ia_mode |= (imode & ~S_IALLUGO);
	}

	/* Revoke setuid/setgid bit on chown/chgrp */
	if ((iap->ia_valid & ATTR_UID) && (imode & S_ISUID)
	 && iap->ia_uid != inode->i_uid) {
		iap->ia_valid |= ATTR_MODE;
		iap->ia_mode = imode &= ~S_ISUID;
	}
	if ((iap->ia_valid & ATTR_GID) && (imode & S_ISGID)
	 && iap->ia_gid != inode->i_gid) {
		iap->ia_valid |= ATTR_MODE;
		iap->ia_mode = imode &= ~S_ISGID;
	}

	/* Change the attributes. */


	iap->ia_valid |= ATTR_CTIME;
	if (current->fsuid != 0) {
		saved_cap = current->cap_effective;
		cap_clear(current->cap_effective);
	}
#ifdef CONFIG_QUOTA
	/* DQUOT_TRANSFER needs both ia_uid and ia_gid defined */
	if (iap->ia_valid & (ATTR_UID|ATTR_GID)) {
		if (! (iap->ia_valid & ATTR_UID))
			iap->ia_uid = inode->i_uid;
		if (! (iap->ia_valid & ATTR_GID))
			iap->ia_gid = inode->i_gid;
		iap->ia_valid |= ATTR_UID|ATTR_GID;
	}
#endif /* CONFIG_QUOTA */

	fh_lock(fhp);
#ifdef CONFIG_QUOTA
	if (iap->ia_valid & (ATTR_UID|ATTR_GID)) 
		err = DQUOT_TRANSFER(dentry, iap);
	else
#endif
		err = notify_change(dentry, iap);

	if (size_change) {
		if (!err) {
			vmtruncate(inode,iap->ia_size);		
			if (inode->i_op && inode->i_op->truncate)
				inode->i_op->truncate(inode);
		}
		fh_unlock(fhp);
		put_write_access(inode);
	} else
		fh_unlock(fhp);

	if (current->fsuid != 0)
		current->cap_effective = saved_cap;
	if (err)
		goto out_nfserr;
	if (EX_ISSYNC(fhp->fh_export))
		write_inode_now(inode);
	err = 0;

	/* Don't unlock inode; the nfssvc_release functions are supposed
	 * to do this. */
out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

#ifdef CONFIG_NFSD_V3
/*
 * Check server access rights to a file system object
 */
struct accessmap {
	u32		access;
	int		how;
};
static struct accessmap	nfs3_regaccess[] = {
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_EXECUTE,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_WRITE|MAY_TRUNC		},
    {	NFS3_ACCESS_EXTEND,	MAY_WRITE			},

    {	0,			0				}
};

static struct accessmap	nfs3_diraccess[] = {
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_LOOKUP,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_EXEC|MAY_WRITE|MAY_TRUNC	},
    {	NFS3_ACCESS_EXTEND,	MAY_EXEC|MAY_WRITE		},
    {	NFS3_ACCESS_DELETE,	MAY_REMOVE			},

    {	0,			0				}
};

static struct accessmap	nfs3_anyaccess[] = {
	/* Some clients - Solaris 2.6 at least, make an access call
	 * to the server to check for access for things like /dev/null
	 * (which really, the server doesn't care about).  So
	 * We provide simple access checking for them, looking
	 * mainly at mode bits
	 */
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_EXECUTE,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_WRITE			},
    {	NFS3_ACCESS_EXTEND,	MAY_WRITE			},

    {	0,			0				}
};

int
nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access)
{
	struct accessmap	*map;
	struct svc_export	*export;
	struct dentry		*dentry;
	u32			query, result = 0;
	unsigned int		error;

	error = fh_verify(rqstp, fhp, 0, MAY_NOP);
	if (error)
		goto out;

	export = fhp->fh_export;
	dentry = fhp->fh_dentry;

	if (S_ISREG(dentry->d_inode->i_mode))
		map = nfs3_regaccess;
	else if (S_ISDIR(dentry->d_inode->i_mode))
		map = nfs3_diraccess;
	else
		map = nfs3_anyaccess;


	query = *access;
	for  (; map->access; map++) {
		if (map->access & query) {
			error = nfsd_permission(export, dentry, (map->how | NO_OWNER_OVERRIDE));
			switch(error) {
			case 0:
				result |= map->access;
				break;
			case nfserr_perm:
			case nfserr_acces:
			case nfserr_rofs:
				/*
				 *  This access type is denyed; but the 
				 *  access query itself succeeds.
				 */
				error = 0;
				break;
			default:
				/*
				 *  Some fatal error.  Fail the query.
				 */
				goto out;
			}
		}
	}
	*access = result;

out:
	return error;
}
#endif /* CONFIG_NFSD_V3 */



/*
 * Open an existing file or directory.
 * The access argument indicates the type of open (read/write/lock)
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
			int access, struct file *filp)
{
	struct dentry	*dentry;
	struct inode	*inode;
	int		err;

	err = fh_verify(rqstp, fhp, type, access);
	if (err)
		goto out;

	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;

	/* Disallow access to files with the append-only bit set or
	 * with mandatory locking enabled
	 */
	err = nfserr_perm;
	if (IS_APPEND(inode) || IS_ISMNDLK(inode))
		goto out;
	if (!inode->i_op || !inode->i_op->default_file_ops)
		goto out;

	if ((access & MAY_WRITE) && (err = get_write_access(inode)) != 0)
		goto out_nfserr;

	memset(filp, 0, sizeof(*filp));
	filp->f_op    = inode->i_op->default_file_ops;
	filp->f_count = 1;
	filp->f_dentry = dentry;
	if (access & MAY_WRITE) {
		filp->f_flags = O_WRONLY;
		filp->f_mode  = FMODE_WRITE;
		DQUOT_INIT(inode);
	} else {
		filp->f_flags = O_RDONLY;
		filp->f_mode  = FMODE_READ;
	}

	err = 0;
	if (filp->f_op && filp->f_op->open) {
		err = filp->f_op->open(inode, filp);
		if (err) {
			if (access & MAY_WRITE)
				put_write_access(inode);

			/* I nearly added put_filp() call here, but this filp
			 * is really on callers stack frame. -DaveM
			 */
			filp->f_count--;
		}
	}
out_nfserr:
	if (err)
		err = nfserrno(err);
out:
	return err;
}

/*
 * Close a file.
 */
void
nfsd_close(struct file *filp)
{
	struct dentry	*dentry = filp->f_dentry;
	struct inode	*inode = dentry->d_inode;

	if (!inode->i_count)
		printk(KERN_WARNING "nfsd: inode count == 0!\n");
	if (!dentry->d_count)
		printk(KERN_WARNING "nfsd: wheee, %s/%s d_count == 0!\n",
			dentry->d_parent->d_name.name, dentry->d_name.name);
	if (filp->f_op && filp->f_op->release)
		filp->f_op->release(inode, filp);
	if (filp->f_mode & FMODE_WRITE) 
		put_write_access(inode);
}

/*
 * Sync a file
 * As this calls fsync (not fdatasync) there is no need for a write_inode
 * after it.
 */
void
nfsd_sync(struct file *filp)
{
	dprintk("nfsd: sync file %s\n", filp->f_dentry->d_name.name);
	down(&filp->f_dentry->d_inode->i_sem);
	filp->f_op->fsync(filp, filp->f_dentry);
	up(&filp->f_dentry->d_inode->i_sem);
}

void
nfsd_sync_dir(struct dentry *dp)
{
	struct inode *inode = dp->d_inode;
	int (*fsync) (struct file *, struct dentry *);
	
	if (inode->i_op->default_file_ops
	    && (fsync = inode->i_op->default_file_ops->fsync)) {
		fsync(NULL, dp);
	}
}

/*
 * Obtain the readahead parameters for the file
 * specified by (dev, ino).
 */
static inline struct raparms *
nfsd_get_raparms(dev_t dev, ino_t ino)
{
	struct raparms	*ra, **rap, **frap = NULL;

	for (rap = &raparm_cache; (ra = *rap); rap = &ra->p_next) {
		if (ra->p_ino == ino && ra->p_dev == dev)
			goto found;
		if (ra->p_count == 0)
			frap = rap;
	}
	if (!frap)
		return NULL;
	rap = frap;
	ra = *frap;
	memset(ra, 0, sizeof(*ra));
	ra->p_dev = dev;
	ra->p_ino = ino;
found:
	if (rap != &raparm_cache) {
		*rap = ra->p_next;
		ra->p_next   = raparm_cache;
		raparm_cache = ra;
	}
	ra->p_count++;
	return ra;
}

/*
 * Read data from a file. count must contain the requested read count
 * on entry. On return, *count contains the number of bytes actually read.
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
          char *buf, unsigned long *count)
{
	struct raparms	*ra;
	mm_segment_t	oldfs;
	int		err;
	struct file	file;

	err = nfsd_open(rqstp, fhp, S_IFREG, MAY_READ, &file);
	if (err)
		goto out;
	err = nfserr_perm;
	if (!file.f_op->read)
		goto out_close;

	/* Get readahead parameters */
	ra = nfsd_get_raparms(fhp->fh_export->ex_dev, fhp->fh_dentry->d_inode->i_ino);
	if (ra) {
		file.f_reada = ra->p_reada;
		file.f_ramax = ra->p_ramax;
		file.f_raend = ra->p_raend;
		file.f_ralen = ra->p_ralen;
		file.f_rawin = ra->p_rawin;
	}
	file.f_pos = offset;

	oldfs = get_fs(); set_fs(KERNEL_DS);
	err = file.f_op->read(&file, buf, *count, &file.f_pos);
	set_fs(oldfs);

	/* Write back readahead params */
	if (ra != NULL) {
		dprintk("nfsd: raparms %ld %ld %ld %ld %ld\n",
			file.f_reada, file.f_ramax, file.f_raend,
			file.f_ralen, file.f_rawin);
		ra->p_reada = file.f_reada;
		ra->p_ramax = file.f_ramax;
		ra->p_raend = file.f_raend;
		ra->p_ralen = file.f_ralen;
		ra->p_rawin = file.f_rawin;
		ra->p_count -= 1;
	}

	if (err >= 0) {
		*count = err;
		err = 0;
	} else 
		err = nfserrno(err);
out_close:
	nfsd_close(&file);
out:
	return err;
}

/*
 * Write data to a file.
 * The stable flag requests synchronous writes.
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
				char *buf, unsigned long cnt, int *stablep)
{
	struct svc_export	*exp;
	struct file		file;
	struct dentry		*dentry;
	struct inode		*inode;
	mm_segment_t		oldfs;
	int			err = 0;
	int			stable = *stablep;
#ifdef CONFIG_QUOTA
	uid_t			saved_euid;
#endif

	err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file);
	if (err)
		goto out;
	if (!cnt)
		goto out_close;
	err = nfserr_perm;
	if (!file.f_op->write)
		goto out_close;

	dentry = file.f_dentry;
	inode = dentry->d_inode;
	exp   = fhp->fh_export;

	/*
	 * Request sync writes if
	 *  -	the sync export option has been set, or
	 *  -	the client requested O_SYNC behavior (NFSv3 feature).
	 *  -   The file system doesn't support fsync().
	 * When gathered writes have been configured for this volume,
	 * flushing the data to disk is handled separately below.
	 */

	if (file.f_op->fsync == 0) {/* COMMIT3 cannot work */
	       stable = 2;
	       *stablep = 2; /* FILE_SYNC */
	}

	if (!EX_ISSYNC(exp))
		stable = 0;
	if (stable && !EX_WGATHER(exp))
		file.f_flags |= O_SYNC;

	fh_lock(fhp);			/* lock inode */
	file.f_pos = offset;		/* set write offset */

	/* Write the data. */
	oldfs = get_fs(); set_fs(KERNEL_DS);
#ifdef CONFIG_QUOTA
	/* This is for disk quota. */
	saved_euid = current->euid;
	current->euid = current->fsuid;
	err = file.f_op->write(&file, buf, cnt, &file.f_pos);
	current->euid = saved_euid;
#else
	err = file.f_op->write(&file, buf, cnt, &file.f_pos);
#endif
	set_fs(oldfs);

	/* clear setuid/setgid flag after write */
	if (err >= 0 && (inode->i_mode & (S_ISUID | S_ISGID))) {
		struct iattr	ia;
		kernel_cap_t	saved_cap = 0;

		ia.ia_valid = ATTR_MODE;
		ia.ia_mode  = inode->i_mode & ~(S_ISUID | S_ISGID);
		if (current->fsuid != 0) {
			saved_cap = current->cap_effective;
			cap_clear(current->cap_effective);
		}
		notify_change(dentry, &ia);
		if (current->fsuid != 0)
			current->cap_effective = saved_cap;
	}

	fh_unlock(fhp);			/* unlock inode */

	if (err >= 0 && stable) {
		static unsigned long	last_ino = 0;
		static kdev_t		last_dev = NODEV;

		/*
		 * Gathered writes: If another process is currently
		 * writing to the file, there's a high chance
		 * this is another nfsd (triggered by a bulk write
		 * from a client's biod). Rather than syncing the
		 * file with each write request, we sleep for 10 msec.
		 *
		 * I don't know if this roughly approximates
		 * C. Juszak's idea of gathered writes, but it's a
		 * nice and simple solution (IMHO), and it seems to
		 * work:-)
		 */
		if (EX_WGATHER(exp) && (inode->i_writecount > 1
		 || (last_ino == inode->i_ino && last_dev == inode->i_dev))) {
			dprintk("nfsd: write defer %d\n", current->pid);
			current->state = TASK_UNINTERRUPTIBLE;
			schedule_timeout((HZ+99)/100);
			current->state = TASK_RUNNING;
			dprintk("nfsd: write resume %d\n", current->pid);
		}

		if (EX_WGATHER(exp) && (inode->i_state & I_DIRTY)) {
			dprintk("nfsd: write sync %d\n", current->pid);
			nfsd_sync(&file);
		}
#if 0
		wake_up(&inode->i_wait);
#endif
		last_ino = inode->i_ino;
		last_dev = inode->i_dev;
	}

	dprintk("nfsd: write complete err=%d\n", err);
	if (err >= 0)
		err = 0;
	else 
		err = nfserrno(err);
out_close:
	nfsd_close(&file);
out:
	return err;
}


#ifdef CONFIG_NFSD_V3
/*
 * Commit all pending writes to stable storage.
 * Strictly speaking, we could sync just the indicated file region here,
 * but there's currently no way we can ask the VFS to do so.
 *
 * We lock the file to make sure we return full WCC data to the client.
 */
int
nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
               off_t offset, unsigned long count)
{
	struct file	file;
	int		err;

	if ((err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file)) != 0)
		return err;
	if (EX_ISSYNC(fhp->fh_export)) {
		fh_lock(fhp);
		if (file.f_op && file.f_op->fsync) {
			file.f_op->fsync(&file, file.f_dentry);
		} else {
			err = nfserr_notsupp;
		}
		fh_unlock(fhp);
	}

	nfsd_close(&file);
	return err;
}
#endif /* CONFIG_NFSD_V3 */

/*
 * Create a file (regular, directory, device, fifo); UNIX sockets 
 * not yet implemented.
 * If the response fh has been verified, the parent directory should
 * already be locked. Note that the parent directory is left locked.
 *
 * N.B. Every call to nfsd_create needs an fh_put for _both_ fhp and resfhp
 */
int
nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
		char *fname, int flen, struct iattr *iap,
		int type, dev_t rdev, struct svc_fh *resfhp)
{
	struct dentry	*dentry, *dchild;
	struct inode	*dirp;
	nfsd_dirop_t	opfunc = NULL;
	int		err;

	err = nfserr_perm;
	if (!flen)
		goto out;
	err = nfserr_exist;
	if (isdotent(fname, flen))
		goto out;

	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
	if (err)
		goto out;

	dentry = fhp->fh_dentry;
	dirp = dentry->d_inode;

	err = nfserr_notdir;
	if(!dirp->i_op || !dirp->i_op->lookup)
		goto out;
	/*
	 * Check whether the response file handle has been verified yet.
	 * If it has, the parent directory should already be locked.
	 */
	if (!resfhp->fh_dentry) {
		dchild = lookup_dentry(fname, dget(dentry), 0);
		err = PTR_ERR(dchild);
		if (IS_ERR(dchild))
			goto out_nfserr;
		fh_compose(resfhp, fhp->fh_export, dchild);
		/* Lock the parent and check for errors ... */
		err = fh_lock_parent(fhp, dchild);
		if (err)
			goto out;
	} else {
		dchild = resfhp->fh_dentry;
		if (!fhp->fh_locked) {
			/* not actually possible */
			printk(KERN_ERR
				"nfsd_create: parent %s/%s not locked!\n",
				dentry->d_parent->d_name.name,
				dentry->d_name.name);
			err = -EIO;
			goto out;
		}
	}
	/*
	 * Make sure the child dentry is still negative ...
	 */
	err = nfserr_exist;
	if (dchild->d_inode) {
		dprintk("nfsd_create: dentry %s/%s not negative!\n",
			dentry->d_name.name, dchild->d_name.name);
		goto out; 
	}

	/*
	 * Get the dir op function pointer.
	 */
	err = nfserr_perm;
	switch (type) {
	case S_IFREG:
		opfunc = (nfsd_dirop_t) dirp->i_op->create;
		break;
	case S_IFDIR:
		opfunc = (nfsd_dirop_t) dirp->i_op->mkdir;
		break;
	case S_IFCHR:
	case S_IFBLK:
		/* The client is _NOT_ required to do security enforcement */
		if(!capable(CAP_SYS_ADMIN)) {
			err = -EPERM;
			goto out;
		}
	case S_IFIFO:
	case S_IFSOCK:
		opfunc = dirp->i_op->mknod;
		break;
	default:
	        printk("nfsd: bad file type %o in nfsd_create\n", type);
		err = nfserr_inval;
	}
	if (!opfunc)
		goto out;

	if (!(iap->ia_valid & ATTR_MODE))
		iap->ia_mode = 0;
	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;

	/*
	 * Call the dir op function to create the object.
	 */
	DQUOT_INIT(dirp);
	err = opfunc(dirp, dchild, iap->ia_mode, rdev);
	if (err < 0)
		goto out_nfserr;

	if (EX_ISSYNC(fhp->fh_export)) {
		nfsd_sync_dir(dentry);
		write_inode_now(dchild->d_inode);
	}


	/* Set file attributes. Mode has already been set and
	 * setting uid/gid works only for root. Irix appears to
	 * send along the gid when it tries to implement setgid
	 * directories via NFS.
	 */
	err = 0;
	if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0)
		err = nfsd_setattr(rqstp, resfhp, iap);
	/*
	 * Update the file handle to get the new inode info.
	 */
	fh_update(resfhp);
out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

#ifdef CONFIG_NFSD_V3
/*
 * NFSv3 version of nfsd_create
 */
int
nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
		char *fname, int flen, struct iattr *iap,
		struct svc_fh *resfhp, int createmode, u32 *verifier)
{
	struct dentry	*dentry, *dchild;
	struct inode	*dirp;
	int		err;
	__u32		v_mtime=0, v_atime=0;
	int		v_mode=0;

	err = nfserr_perm;
	if (!flen)
		goto out;
	err = nfserr_exist;
	if (isdotent(fname, flen))
		goto out;
	if (!(iap->ia_valid & ATTR_MODE))
		iap->ia_mode = 0;
	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
	if (err)
		goto out;

	dentry = fhp->fh_dentry;
	dirp = dentry->d_inode;

	/* Get all the sanity checks out of the way before
	 * we lock the parent. */
	err = nfserr_notdir;
	if(!dirp->i_op || !dirp->i_op->lookup)
		goto out;
	err = nfserr_perm;
	if(!dirp->i_op->create)
		goto out;

	/*
	 * Compose the response file handle.
	 */
	dchild = lookup_dentry(fname, dget(dentry), 0);
	err = PTR_ERR(dchild);
	if(IS_ERR(dchild))
		goto out_nfserr;
	fh_compose(resfhp, fhp->fh_export, dchild);

	/*
	 * We must lock the directory before we check for the inode.
	 */
	err = fh_lock_parent(fhp, dchild);
	if (err)
	    goto out;

	if (createmode == NFS3_CREATE_EXCLUSIVE) {
		/* while the verifier would fit in mtime+atime,
		 * solaris7 gets confused (bugid 4218508) if these have
		 * the high bit set, so we use the mode as well
		 */
		v_mtime = verifier[0]&0x7fffffff;
		v_atime = verifier[1]&0x7fffffff;
		v_mode  = S_IFREG
			| ((verifier[0]&0x80000000) >> (32-7)) /* u+x */
			| ((verifier[1]&0x80000000) >> (32-9)) /* u+r */
			;
	}
	
	if (dchild->d_inode) {
		err = 0;

		if (resfhp->fh_handle.fh_ino == 0)
		     /* inode might have been instantiated while we slept */
		    fh_update(resfhp);
		
		switch (createmode) {
		case NFS3_CREATE_UNCHECKED:
			if (! S_ISREG(dchild->d_inode->i_mode))
				err = nfserr_exist;
			else {
				iap->ia_valid &= ATTR_SIZE;
				goto set_attr;
			}
			break;
		case NFS3_CREATE_EXCLUSIVE:
			if (   dchild->d_inode->i_mtime == v_mtime
			    && dchild->d_inode->i_atime == v_atime
			    && dchild->d_inode->i_mode  == v_mode
			    && dchild->d_inode->i_size  == 0 )
				break;
			 /* fallthru */
		case NFS3_CREATE_GUARDED:
			err = nfserr_exist;
		}
		goto out;
	}

	err = dirp->i_op->create(dirp, dchild, iap->ia_mode);
	if (err < 0)
		goto out_nfserr;

	if (EX_ISSYNC(fhp->fh_export)) {
		nfsd_sync_dir(dentry);
		/* setattr will sync the child (or not) */
	}

	/*
	 * Update the filehandle to get the new inode info.
	 */
	fh_update(resfhp);
	err = 0;

	if (createmode == NFS3_CREATE_EXCLUSIVE) {
		/* Cram the verifier into atime/mtime/mode */
		iap->ia_valid = ATTR_MTIME|ATTR_ATIME
			| ATTR_MTIME_SET|ATTR_ATIME_SET
			| ATTR_MODE;
		iap->ia_mtime = v_mtime;
		iap->ia_atime = v_atime;
		iap->ia_mode  = v_mode;
	}

	/* Set file attributes.
	 * Mode has already been set but we might need to reset it
	 * for CREATE_EXCLUSIVE
	 * Irix appears to send along the gid when it tries to
	 * implement setgid directories via NFS. Clear out all that cruft.
	 */
 set_attr:
	if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID)) != 0)
 		err = nfsd_setattr(rqstp, resfhp, iap);

 out:
	fh_unlock(fhp);
 	return err;
 
 out_nfserr:
	err = nfserrno(err);
	goto out;
}
#endif /* CONFIG_NFSD_V3 */

/*
 * Read a symlink. On entry, *lenp must contain the maximum path length that
 * fits into the buffer. On return, it contains the true length.
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
{
	struct dentry	*dentry;
	struct inode	*inode;
	mm_segment_t	oldfs;
	int		err;

	err = fh_verify(rqstp, fhp, S_IFLNK, MAY_NOP);
	if (err)
		goto out;

	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;

	err = nfserr_inval;
	if (!inode->i_op || !inode->i_op->readlink)
		goto out;

	UPDATE_ATIME(inode);
	/* N.B. Why does this call need a get_fs()??
	 * Remove the set_fs and watch the fireworks:-) --okir
	 */

	oldfs = get_fs(); set_fs(KERNEL_DS);
	err = inode->i_op->readlink(dentry, buf, *lenp);
	set_fs(oldfs);

	if (err < 0)
		goto out_nfserr;
	*lenp = err;
	err = 0;
out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

/*
 * Create a symlink and look up its inode
 * N.B. After this call _both_ fhp and resfhp need an fh_put
 */
int
nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
				char *fname, int flen,
				char *path,  int plen,
				struct svc_fh *resfhp,
				struct iattr *iap)
{
	struct dentry	*dentry, *dnew;
	struct inode	*dirp;
	int		err;

	err = nfserr_noent;
	if (!flen || !plen)
		goto out;

	err = nfserr_exist;
	if (isdotent(fname, flen))
		goto out;

	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
	if (err)
		goto out;
	dentry = fhp->fh_dentry;

	err = nfserr_perm;
	dirp = dentry->d_inode;
	if (!dirp->i_op	|| !dirp->i_op->symlink)
		goto out;

	dnew = lookup_dentry(fname, dget(dentry), 0);
	err = PTR_ERR(dnew);
	if (IS_ERR(dnew))
		goto out_nfserr;

	/*
	 * Lock the parent before checking for existence
	 */
	err = fh_lock_parent(fhp, dnew);
	if (err)
		goto out_compose;

	err = nfserr_exist;
	if (!dnew->d_inode) {
		DQUOT_INIT(dirp);
		err = dirp->i_op->symlink(dirp, dnew, path);
		if (!err) {
			if (EX_ISSYNC(fhp->fh_export))
				nfsd_sync_dir(dentry);
			if (iap) {
				iap->ia_valid &= ATTR_MODE /* ~(ATTR_MODE|ATTR_UID|ATTR_GID)*/;
				if (iap->ia_valid) {
					iap->ia_valid |= ATTR_CTIME;
					iap->ia_mode = (iap->ia_mode&S_IALLUGO)
						| S_IFLNK;
					err = notify_change(dnew, iap);
					if (!err && EX_ISSYNC(fhp->fh_export))
						write_inode_now(dentry->d_inode);
			       }
			}
		} else
			err = nfserrno(err);
	}
	fh_unlock(fhp);

	/* Compose the fh so the dentry will be freed ... */
out_compose:
	fh_compose(resfhp, fhp->fh_export, dnew);

out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

/*
 * Create a hardlink
 * N.B. After this call _both_ ffhp and tfhp need an fh_put
 */
int
nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
				char *fname, int flen, struct svc_fh *tfhp)
{
	struct dentry	*ddir, *dnew, *dold;
	struct inode	*dirp, *dest;
	int		err;

	err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_CREATE);
	if (err)
		goto out;

	err = nfserr_exist;
	if (isdotent(fname, flen))
		goto out;

	err = fh_verify(rqstp, tfhp, -S_IFDIR, MAY_NOP);
	if (err)
		goto out;

	err = nfserr_perm;
	if (!flen)
		goto out;

	ddir = ffhp->fh_dentry;
	dirp = ddir->d_inode;

	dnew = lookup_dentry(fname, dget(ddir), 0);
	err = PTR_ERR(dnew);
	if (IS_ERR(dnew))
		goto out_nfserr;
	/*
	 * Lock the parent before checking for existence
	 */
	err = fh_lock_parent(ffhp, dnew);
	if (err)
		goto out_dput;

	err = nfserr_exist;
	if (dnew->d_inode)
		goto out_unlock;

	dold = tfhp->fh_dentry;
	dest = dold->d_inode;

	err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
	if (dirp->i_dev != dest->i_dev)
		goto out_unlock;

	err = nfserr_perm;
	if (IS_IMMUTABLE(dest) || IS_APPEND(dest))
		goto out_unlock;
	if (!dirp->i_op || !dirp->i_op->link)
		goto out_unlock;

	DQUOT_INIT(dirp);
	err = dirp->i_op->link(dold, dirp, dnew);
	if (!err) {
		if (EX_ISSYNC(ffhp->fh_export)) {
			nfsd_sync_dir(ddir);
			write_inode_now(dest);
		}
	} else
		err = nfserrno(err);

out_unlock:
	fh_unlock(ffhp);
out_dput:
	dput(dnew);
out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

/*
 * This follows the model of double_lock() in the VFS.
 */
static inline void nfsd_double_down(struct semaphore *s1, struct semaphore *s2)
{
	if (s1 != s2) {
		if ((unsigned long) s1 < (unsigned long) s2) {
			struct semaphore *tmp = s1;
			s1 = s2;
			s2 = tmp;
		}
		down(s1);
	}
	down(s2);
}

static inline void nfsd_double_up(struct semaphore *s1, struct semaphore *s2)
{
	up(s1);
	if (s1 != s2)
		up(s2);
}

/*
 * Rename a file
 * N.B. After this call _both_ ffhp and tfhp need an fh_put
 */
int
nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
			    struct svc_fh *tfhp, char *tname, int tlen)
{
	struct dentry	*fdentry, *tdentry, *odentry, *ndentry;
	struct inode	*fdir, *tdir;
	int		err;

	err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_REMOVE);
	if (err)
		goto out;
	err = fh_verify(rqstp, tfhp, S_IFDIR, MAY_CREATE);
	if (err)
		goto out;

	fdentry = ffhp->fh_dentry;
	fdir = fdentry->d_inode;

	tdentry = tfhp->fh_dentry;
	tdir = tdentry->d_inode;

	err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
	if (fdir->i_dev != tdir->i_dev)
		goto out;

	err = nfserr_perm;
	if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen))
		goto out;

	odentry = lookup_dentry(fname, dget(fdentry), 0);
	err = PTR_ERR(odentry);
	if (IS_ERR(odentry))
		goto out_nfserr;

	err = -ENOENT;
	if (!odentry->d_inode)
		goto out_dput_old;

	ndentry = lookup_dentry(tname, dget(tdentry), 0);
	err = PTR_ERR(ndentry);
	if (IS_ERR(ndentry))
		goto out_dput_old;

	/*
	 * Lock the parent directories.
	 */
	nfsd_double_down(&tdir->i_sem, &fdir->i_sem);

#ifdef CONFIG_NFSD_V3
	/* Fill in the pre-op attr for the wcc data for both 
	 * tdir and fdir
	 */ 
	fill_pre_wcc(ffhp);
	fill_pre_wcc(tfhp);
#endif /* CONFIG_NFSD_V3 */

	err = -ENOENT;
	/* GAM3 check for parent changes after locking. */
	if (nfsd_check_parent(fdentry, odentry) &&
	    nfsd_check_parent(tdentry, ndentry)) {

		err = vfs_rename(fdir, odentry, tdir, ndentry);
		if (!err && EX_ISSYNC(tfhp->fh_export)) {
			nfsd_sync_dir(tdentry);
			nfsd_sync_dir(fdentry);
		}
	} else
		dprintk("nfsd: Caught race in nfsd_rename");

#ifdef CONFIG_NFSD_V3
        /* Fill in the post-op attr for the wcc data for both 
         * tdir and fdir
         */
	fill_post_wcc(ffhp);
	fill_post_wcc(tfhp);
#endif /* CONFIG_NFSD_V3 */
	nfsd_double_up(&tdir->i_sem, &fdir->i_sem);
	dput(ndentry);

out_dput_old:
	dput(odentry);
	if (err)
		goto out_nfserr;
out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

/*
 * Unlink a file or directory
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
				char *fname, int flen)
{
	struct dentry	*dentry, *rdentry;
	struct inode	*dirp;
	int		err;

	err = nfserr_acces;
	if (!flen || isdotent(fname, flen))
		goto out;

	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_REMOVE);
	if (err)
		goto out;

	dentry = fhp->fh_dentry;
	dirp = dentry->d_inode;

	rdentry = lookup_dentry(fname, dget(dentry), 0);
	err = PTR_ERR(rdentry);
	if (IS_ERR(rdentry))
		goto out_nfserr;

	if (!rdentry->d_inode) {
		dput(rdentry);
		err = nfserr_noent;
		goto out;
	}


	if (type != S_IFDIR) {
		/* It's UNLINK */

		err = fh_lock_parent(fhp, rdentry);
		if (err) {
			dput(rdentry);
			goto out;
		}

		err = vfs_unlink(dirp, rdentry);

		fh_unlock(fhp);

		dput(rdentry);

	} else {
		/* It's RMDIR */
		/* See comments in fs/namei.c:do_rmdir */

		rdentry->d_count++;
		nfsd_double_down(&dirp->i_sem, &rdentry->d_inode->i_sem);

#ifdef CONFIG_NFSD_V3
		fill_pre_wcc(fhp);
#else
		fhp->fh_locked = 1;
#endif /* CONFIG_NFSD_V3 */

		err = -ENOENT;
		if (nfsd_check_parent(dentry, rdentry))
			err = vfs_rmdir(dirp, rdentry);

		rdentry->d_count--;
#ifdef CONFIG_NFSD_V3
		fill_post_wcc(fhp);
#else
		fhp->fh_locked = 0;
#endif /* CONFIG_NFSD_V3 */
		nfsd_double_up(&dirp->i_sem, &rdentry->d_inode->i_sem);

		dput(rdentry);
	}

	if (err)
		goto out_nfserr;
	if (EX_ISSYNC(fhp->fh_export)) {
		down(&dentry->d_inode->i_sem);
		nfsd_sync_dir(dentry);
		up(&dentry->d_inode->i_sem);
	}
out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

/*
 * Read entries from a directory.
 * The verifier is an NFSv3 thing we ignore for now.
 */
int
nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset, 
             encode_dent_fn func, u32 *buffer, int *countp, u32 *verf)
{
	struct inode	*inode;
	u32		*p;
	int		oldlen, eof, err;
	struct file	file;
	struct readdir_cd cd;

	err = nfsd_open(rqstp, fhp, S_IFDIR, MAY_READ, &file);
	if (err)
		goto out;
	if (offset > ~(u32) 0)
		goto out_close;

	err = nfserr_notdir;
	if (!file.f_op->readdir)
		goto out_close;
	file.f_pos = offset;

	/* Set up the readdir context */
	memset(&cd, 0, sizeof(cd));
	cd.rqstp  = rqstp;
	cd.buffer = buffer;
	cd.buflen = *countp; /* count of words */
	cd.dirfh  = fhp;

	/*
	 * Read the directory entries. This silly loop is necessary because
	 * readdir() is not guaranteed to fill up the entire buffer, but
	 * may choose to do less.
	 */
	inode = file.f_dentry->d_inode;
	down(&inode->i_sem);
	while (1) {
		oldlen = cd.buflen;

		/*
		dprintk("nfsd: f_op->readdir(%x/%ld @ %d) buflen = %d (%d)\n",
			file.f_inode->i_dev, file.f_inode->i_ino,
			(int) file.f_pos, (int) oldlen, (int) cd.buflen);
		 */
		err = file.f_op->readdir(&file, &cd, (filldir_t) func);
		if (err < 0)
			goto out_nfserr;
		if (oldlen == cd.buflen)
			break;
		if (cd.eob)
			break;
	}
	up(&inode->i_sem);

	/* If we didn't fill the buffer completely, we're at EOF */
	eof = !cd.eob;

	if (cd.offset) {
		if (rqstp->rq_vers == 3)
			(void)xdr_encode_hyper(cd.offset, file.f_pos);
		else
			*cd.offset = htonl(file.f_pos);
	}

	p = cd.buffer;
	*p++ = 0;			/* no more entries */
	*p++ = htonl(eof);		/* end of directory */
	*countp = (caddr_t) p - (caddr_t) buffer;

	dprintk("nfsd: readdir result %d bytes, eof %d offset %d\n",
				*countp, eof,
				cd.offset? ntohl(*cd.offset) : -1);
	err = 0;
out_close:
	nfsd_close(&file);
out:
	return err;

out_nfserr:
	up(&inode->i_sem);
	err = nfserrno(err);
	goto out_close;
}

/*
 * Get file system stats
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct statfs *stat)
{
	struct dentry		*dentry;
	struct inode		*inode;
	struct super_block	*sb;
	mm_segment_t		oldfs;
	int			err;

	err = fh_verify(rqstp, fhp, 0, MAY_NOP);
	if (err)
		goto out;
	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;

	err = nfserr_io;
	if (!(sb = inode->i_sb) || !sb->s_op->statfs)
		goto out;

	oldfs = get_fs();
	set_fs (KERNEL_DS);
	sb->s_op->statfs(sb, stat, sizeof(*stat));
	set_fs (oldfs);
	err = 0;

out:
	return err;
}

/*
 * Check for a user's access permissions to this inode.
 */
int
nfsd_permission(struct svc_export *exp, struct dentry *dentry, int acc)
{
	struct inode	*inode = dentry->d_inode;
	int		err;
	kernel_cap_t	saved_cap = 0;
	int		owneraccess;

	/*
	 *  Check if we are to use "owner may always access" semantics,
	 *  then clean out the flag bit which controls this. It might be
	 *  clearer to reverse the logic of this flag, but I didn't
	 *  want to change a lot of code in a stable kernel - dhiggen.
	 */

	if (acc & NO_OWNER_OVERRIDE) {
		owneraccess = 0;
		acc &= ~NO_OWNER_OVERRIDE;
	} else {
		owneraccess = 1;
	}

	if (acc == MAY_NOP)
		return 0;
#if 0
	dprintk("nfsd: permission 0x%x%s%s%s%s%s%s mode 0%o%s%s%s\n",
		acc,
		(acc & MAY_READ)?	" read"  : "",
		(acc & MAY_WRITE)?	" write" : "",
		(acc & MAY_EXEC)?	" exec"  : "",
		(acc & MAY_SATTR)?	" sattr" : "",
		(acc & MAY_TRUNC)?	" trunc" : "",
		(acc & MAY_LOCK)?	" lock"  : "",
		inode->i_mode,
		IS_IMMUTABLE(inode)?	" immut" : "",
		IS_APPEND(inode)?	" append" : "",
		IS_RDONLY(inode)?	" ro" : "");
	dprintk("      owner %d/%d user %d/%d\n",
		inode->i_uid, inode->i_gid, current->fsuid, current->fsgid);
#endif

	/* only care about readonly exports for files and
	 * directories. links don't have meaningful write access,
	 * and all else is local to the client
	 */
	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) 
		if (acc & (MAY_WRITE | MAY_SATTR | MAY_TRUNC)) {
			if (EX_RDONLY(exp) || IS_RDONLY(inode))
				return nfserr_rofs;
			if (/* (acc & MAY_WRITE) && */ IS_IMMUTABLE(inode))
				return nfserr_perm;
		}
	if ((acc & MAY_TRUNC) && IS_APPEND(inode))
		return nfserr_perm;

	if (acc & MAY_LOCK) {
		/* If we cannot rely on authentication in NLM requests,
		 * just allow locks, others require read permission
		 */
		if (exp->ex_flags & NFSEXP_NOAUTHNLM)
			return 0;
		else
			acc = MAY_READ;
	}
	/*
	 * The file owner always gets access permission (except in the 
	 * special case of a V3 ACCESS call, which is used for checking at 
	 * open() time). This is to make file access work even when the 
	 * client has done a fchmod(fd, 0).
	 *
	 * However, `cp foo bar' should fail nevertheless when bar is
	 * readonly. A sensible way to do this might be to reject all
	 * attempts to truncate a read-only file, because a creat() call
	 * always implies file truncation.
	 *  dhXXX we are not currently setting MAY_TRUNC from a SETATTR which
	 *  changes the size, so this check is not enforced.  It probably
	 *  should be?
	 */
	if (owneraccess && inode->i_uid == current->fsuid /* && !(acc & MAY_TRUNC) */)
		return 0;

	if (current->fsuid != 0) {
		saved_cap = current->cap_effective;
		cap_clear(current->cap_effective);
	}

	err = permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC));

	/* Allow read access to binaries even when mode 111 */
	if (err == -EACCES && S_ISREG(inode->i_mode) && acc == MAY_READ)
		err = permission(inode, MAY_EXEC);

	if (current->fsuid != 0)
		current->cap_effective = saved_cap;

	return err? nfserrno(err) : 0;
}

void
nfsd_racache_shutdown(void)
{
	if (!raparm_cache)
		return;
	dprintk("nfsd: freeing %d readahead buffers.\n", FILECACHE_MAX);
	kfree(raparml);
	nfsd_nservers = 0;
	raparm_cache = raparml = NULL;
}
/*
 * Initialize readahead param cache
 */
void
nfsd_racache_init(void)
{
	int	i;

	if (raparm_cache)
		return;
	raparml = kmalloc(sizeof(struct raparms) * FILECACHE_MAX, GFP_KERNEL);

	if (raparml != NULL) {
		dprintk("nfsd: allocating %d readahead buffers.\n",
			FILECACHE_MAX);
		memset(raparml, 0, sizeof(struct raparms) * FILECACHE_MAX);
		for (i = 0; i < FILECACHE_MAX - 1; i++) {
			raparml[i].p_next = raparml + i + 1;
		}
		raparm_cache = raparml;
	} else {
		printk(KERN_WARNING
		       "nfsd: Could not allocate memory read-ahead cache.\n");
		nfsd_nservers = 0;
	}
}