aboutsummaryrefslogtreecommitdiff
path: root/fs/nfsd/nfs4proc.c
blob: 669461e291aecbd7f15e2065c61e86f26cd9d2e7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
/*
 *  fs/nfsd/nfs4proc.c
 *
 *  Server-side procedures for NFSv4.
 *
 *  Copyright (c) 2002 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Kendrick Smith <kmsmith@umich.edu>
 *  Andy Adamson   <andros@umich.edu>
 *
 *  Redistribution and use in source and binary forms, with or without
 *  modification, are permitted provided that the following conditions
 *  are met:
 *
 *  1. Redistributions of source code must retain the above copyright
 *     notice, this list of conditions and the following disclaimer.
 *  2. Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *  3. Neither the name of the University nor the names of its
 *     contributors may be used to endorse or promote products derived
 *     from this software without specific prior written permission.
 *
 *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
 *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <linux/param.h>
#include <linux/major.h>
#include <linux/slab.h>
#include <linux/file.h>

#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/cache.h>
#include <linux/nfs4.h>
#include <linux/nfsd/state.h>
#include <linux/nfsd/xdr4.h>
#include <linux/nfs4_acl.h>
#include <linux/sunrpc/gss_api.h>

#define NFSDDBG_FACILITY		NFSDDBG_PROC

static inline void
fh_dup2(struct svc_fh *dst, struct svc_fh *src)
{
	fh_put(dst);
	dget(src->fh_dentry);
	if (src->fh_export)
		cache_get(&src->fh_export->h);
	*dst = *src;
}

static __be32
do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open, int accmode)
{
	__be32 status;

	if (open->op_truncate &&
		!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
		return nfserr_inval;

	if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
		accmode |= NFSD_MAY_READ;
	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
		accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC);
	if (open->op_share_deny & NFS4_SHARE_DENY_WRITE)
		accmode |= NFSD_MAY_WRITE;

	status = fh_verify(rqstp, current_fh, S_IFREG, accmode);

	return status;
}

static __be32
do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
	struct svc_fh resfh;
	__be32 status;
	int created = 0;

	fh_init(&resfh, NFS4_FHSIZE);
	open->op_truncate = 0;

	if (open->op_create) {
		/*
		 * Note: create modes (UNCHECKED,GUARDED...) are the same
		 * in NFSv4 as in v3.
		 */
		status = nfsd_create_v3(rqstp, current_fh, open->op_fname.data,
					open->op_fname.len, &open->op_iattr,
					&resfh, open->op_createmode,
					(u32 *)open->op_verf.data,
					&open->op_truncate, &created);

		/* If we ever decide to use different attrs to store the
		 * verifier in nfsd_create_v3, then we'll need to change this
		 */
		if (open->op_createmode == NFS4_CREATE_EXCLUSIVE && status == 0)
			open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
						FATTR4_WORD1_TIME_MODIFY);
	} else {
		status = nfsd_lookup(rqstp, current_fh,
				     open->op_fname.data, open->op_fname.len, &resfh);
		fh_unlock(current_fh);
	}
	if (status)
		goto out;

	set_change_info(&open->op_cinfo, current_fh);

	/* set reply cache */
	fh_dup2(current_fh, &resfh);
	open->op_stateowner->so_replay.rp_openfh_len = resfh.fh_handle.fh_size;
	memcpy(open->op_stateowner->so_replay.rp_openfh,
			&resfh.fh_handle.fh_base, resfh.fh_handle.fh_size);

	if (!created)
		status = do_open_permission(rqstp, current_fh, open,
					    NFSD_MAY_NOP);

out:
	fh_put(&resfh);
	return status;
}

static __be32
do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
	__be32 status;

	/* Only reclaims from previously confirmed clients are valid */
	if ((status = nfs4_check_open_reclaim(&open->op_clientid)))
		return status;

	/* We don't know the target directory, and therefore can not
	* set the change info
	*/

	memset(&open->op_cinfo, 0, sizeof(struct nfsd4_change_info));

	/* set replay cache */
	open->op_stateowner->so_replay.rp_openfh_len = current_fh->fh_handle.fh_size;
	memcpy(open->op_stateowner->so_replay.rp_openfh,
		&current_fh->fh_handle.fh_base,
		current_fh->fh_handle.fh_size);

	open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
		(open->op_iattr.ia_size == 0);

	status = do_open_permission(rqstp, current_fh, open,
				    NFSD_MAY_OWNER_OVERRIDE);

	return status;
}


static __be32
nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	   struct nfsd4_open *open)
{
	__be32 status;
	dprintk("NFSD: nfsd4_open filename %.*s op_stateowner %p\n",
		(int)open->op_fname.len, open->op_fname.data,
		open->op_stateowner);

	/* This check required by spec. */
	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
		return nfserr_inval;

	nfs4_lock_state();

	/* check seqid for replay. set nfs4_owner */
	status = nfsd4_process_open1(open);
	if (status == nfserr_replay_me) {
		struct nfs4_replay *rp = &open->op_stateowner->so_replay;
		fh_put(&cstate->current_fh);
		cstate->current_fh.fh_handle.fh_size = rp->rp_openfh_len;
		memcpy(&cstate->current_fh.fh_handle.fh_base, rp->rp_openfh,
				rp->rp_openfh_len);
		status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
		if (status)
			dprintk("nfsd4_open: replay failed"
				" restoring previous filehandle\n");
		else
			status = nfserr_replay_me;
	}
	if (status)
		goto out;

	/* Openowner is now set, so sequence id will get bumped.  Now we need
	 * these checks before we do any creates: */
	status = nfserr_grace;
	if (locks_in_grace() && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
		goto out;
	status = nfserr_no_grace;
	if (!locks_in_grace() && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
		goto out;

	switch (open->op_claim_type) {
		case NFS4_OPEN_CLAIM_DELEGATE_CUR:
			status = nfserr_inval;
			if (open->op_create)
				goto out;
			/* fall through */
		case NFS4_OPEN_CLAIM_NULL:
			/*
			 * (1) set CURRENT_FH to the file being opened,
			 * creating it if necessary, (2) set open->op_cinfo,
			 * (3) set open->op_truncate if the file is to be
			 * truncated after opening, (4) do permission checking.
			 */
			status = do_open_lookup(rqstp, &cstate->current_fh,
						open);
			if (status)
				goto out;
			break;
		case NFS4_OPEN_CLAIM_PREVIOUS:
			open->op_stateowner->so_confirmed = 1;
			/*
			 * The CURRENT_FH is already set to the file being
			 * opened.  (1) set open->op_cinfo, (2) set
			 * open->op_truncate if the file is to be truncated
			 * after opening, (3) do permission checking.
			*/
			status = do_open_fhandle(rqstp, &cstate->current_fh,
						 open);
			if (status)
				goto out;
			break;
             	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
			open->op_stateowner->so_confirmed = 1;
			dprintk("NFSD: unsupported OPEN claim type %d\n",
				open->op_claim_type);
			status = nfserr_notsupp;
			goto out;
		default:
			dprintk("NFSD: Invalid OPEN claim type %d\n",
				open->op_claim_type);
			status = nfserr_inval;
			goto out;
	}
	/*
	 * nfsd4_process_open2() does the actual opening of the file.  If
	 * successful, it (1) truncates the file if open->op_truncate was
	 * set, (2) sets open->op_stateid, (3) sets open->op_delegation.
	 */
	status = nfsd4_process_open2(rqstp, &cstate->current_fh, open);
out:
	if (open->op_stateowner) {
		nfs4_get_stateowner(open->op_stateowner);
		cstate->replay_owner = open->op_stateowner;
	}
	nfs4_unlock_state();
	return status;
}

/*
 * filehandle-manipulating ops.
 */
static __be32
nfsd4_getfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	    struct svc_fh **getfh)
{
	if (!cstate->current_fh.fh_dentry)
		return nfserr_nofilehandle;

	*getfh = &cstate->current_fh;
	return nfs_ok;
}

static __be32
nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	    struct nfsd4_putfh *putfh)
{
	fh_put(&cstate->current_fh);
	cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
	memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
	       putfh->pf_fhlen);
	return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
}

static __be32
nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		void *arg)
{
	__be32 status;

	fh_put(&cstate->current_fh);
	status = exp_pseudoroot(rqstp, &cstate->current_fh);
	return status;
}

static __be32
nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		void *arg)
{
	if (!cstate->save_fh.fh_dentry)
		return nfserr_restorefh;

	fh_dup2(&cstate->current_fh, &cstate->save_fh);
	return nfs_ok;
}

static __be32
nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     void *arg)
{
	if (!cstate->current_fh.fh_dentry)
		return nfserr_nofilehandle;

	fh_dup2(&cstate->save_fh, &cstate->current_fh);
	return nfs_ok;
}

/*
 * misc nfsv4 ops
 */
static __be32
nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     struct nfsd4_access *access)
{
	if (access->ac_req_access & ~NFS3_ACCESS_FULL)
		return nfserr_inval;

	access->ac_resp_access = access->ac_req_access;
	return nfsd_access(rqstp, &cstate->current_fh, &access->ac_resp_access,
			   &access->ac_supported);
}

static __be32
nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     struct nfsd4_commit *commit)
{
	__be32 status;

	u32 *p = (u32 *)commit->co_verf.data;
	*p++ = nfssvc_boot.tv_sec;
	*p++ = nfssvc_boot.tv_usec;

	status = nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
			     commit->co_count);
	if (status == nfserr_symlink)
		status = nfserr_inval;
	return status;
}

static __be32
nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     struct nfsd4_create *create)
{
	struct svc_fh resfh;
	__be32 status;
	dev_t rdev;

	fh_init(&resfh, NFS4_FHSIZE);

	status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR,
			   NFSD_MAY_CREATE);
	if (status == nfserr_symlink)
		status = nfserr_notdir;
	if (status)
		return status;

	switch (create->cr_type) {
	case NF4LNK:
		/* ugh! we have to null-terminate the linktext, or
		 * vfs_symlink() will choke.  it is always safe to
		 * null-terminate by brute force, since at worst we
		 * will overwrite the first byte of the create namelen
		 * in the XDR buffer, which has already been extracted
		 * during XDR decode.
		 */
		create->cr_linkname[create->cr_linklen] = 0;

		status = nfsd_symlink(rqstp, &cstate->current_fh,
				      create->cr_name, create->cr_namelen,
				      create->cr_linkname, create->cr_linklen,
				      &resfh, &create->cr_iattr);
		break;

	case NF4BLK:
		rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
		if (MAJOR(rdev) != create->cr_specdata1 ||
		    MINOR(rdev) != create->cr_specdata2)
			return nfserr_inval;
		status = nfsd_create(rqstp, &cstate->current_fh,
				     create->cr_name, create->cr_namelen,
				     &create->cr_iattr, S_IFBLK, rdev, &resfh);
		break;

	case NF4CHR:
		rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
		if (MAJOR(rdev) != create->cr_specdata1 ||
		    MINOR(rdev) != create->cr_specdata2)
			return nfserr_inval;
		status = nfsd_create(rqstp, &cstate->current_fh,
				     create->cr_name, create->cr_namelen,
				     &create->cr_iattr,S_IFCHR, rdev, &resfh);
		break;

	case NF4SOCK:
		status = nfsd_create(rqstp, &cstate->current_fh,
				     create->cr_name, create->cr_namelen,
				     &create->cr_iattr, S_IFSOCK, 0, &resfh);
		break;

	case NF4FIFO:
		status = nfsd_create(rqstp, &cstate->current_fh,
				     create->cr_name, create->cr_namelen,
				     &create->cr_iattr, S_IFIFO, 0, &resfh);
		break;

	case NF4DIR:
		create->cr_iattr.ia_valid &= ~ATTR_SIZE;
		status = nfsd_create(rqstp, &cstate->current_fh,
				     create->cr_name, create->cr_namelen,
				     &create->cr_iattr, S_IFDIR, 0, &resfh);
		break;

	default:
		status = nfserr_badtype;
	}

	if (!status) {
		fh_unlock(&cstate->current_fh);
		set_change_info(&create->cr_cinfo, &cstate->current_fh);
		fh_dup2(&cstate->current_fh, &resfh);
	}

	fh_put(&resfh);
	return status;
}

static __be32
nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	      struct nfsd4_getattr *getattr)
{
	__be32 status;

	status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
	if (status)
		return status;

	if (getattr->ga_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
		return nfserr_inval;

	getattr->ga_bmval[0] &= NFSD_SUPPORTED_ATTRS_WORD0;
	getattr->ga_bmval[1] &= NFSD_SUPPORTED_ATTRS_WORD1;

	getattr->ga_fhp = &cstate->current_fh;
	return nfs_ok;
}

static __be32
nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	   struct nfsd4_link *link)
{
	__be32 status = nfserr_nofilehandle;

	if (!cstate->save_fh.fh_dentry)
		return status;
	status = nfsd_link(rqstp, &cstate->current_fh,
			   link->li_name, link->li_namelen, &cstate->save_fh);
	if (!status)
		set_change_info(&link->li_cinfo, &cstate->current_fh);
	return status;
}

static __be32
nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	      void *arg)
{
	struct svc_fh tmp_fh;
	__be32 ret;

	fh_init(&tmp_fh, NFS4_FHSIZE);
	ret = exp_pseudoroot(rqstp, &tmp_fh);
	if (ret)
		return ret;
	if (tmp_fh.fh_dentry == cstate->current_fh.fh_dentry) {
		fh_put(&tmp_fh);
		return nfserr_noent;
	}
	fh_put(&tmp_fh);
	return nfsd_lookup(rqstp, &cstate->current_fh,
			   "..", 2, &cstate->current_fh);
}

static __be32
nfsd4_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     struct nfsd4_lookup *lookup)
{
	return nfsd_lookup(rqstp, &cstate->current_fh,
			   lookup->lo_name, lookup->lo_len,
			   &cstate->current_fh);
}

static __be32
nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	   struct nfsd4_read *read)
{
	__be32 status;

	/* no need to check permission - this will be done in nfsd_read() */

	read->rd_filp = NULL;
	if (read->rd_offset >= OFFSET_MAX)
		return nfserr_inval;

	nfs4_lock_state();
	/* check stateid */
	if ((status = nfs4_preprocess_stateid_op(&cstate->current_fh,
				&read->rd_stateid,
				CHECK_FH | RD_STATE, &read->rd_filp))) {
		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
		goto out;
	}
	if (read->rd_filp)
		get_file(read->rd_filp);
	status = nfs_ok;
out:
	nfs4_unlock_state();
	read->rd_rqstp = rqstp;
	read->rd_fhp = &cstate->current_fh;
	return status;
}

static __be32
nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	      struct nfsd4_readdir *readdir)
{
	u64 cookie = readdir->rd_cookie;
	static const nfs4_verifier zeroverf;

	/* no need to check permission - this will be done in nfsd_readdir() */

	if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
		return nfserr_inval;

	readdir->rd_bmval[0] &= NFSD_SUPPORTED_ATTRS_WORD0;
	readdir->rd_bmval[1] &= NFSD_SUPPORTED_ATTRS_WORD1;

	if ((cookie > ~(u32)0) || (cookie == 1) || (cookie == 2) ||
	    (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
		return nfserr_bad_cookie;

	readdir->rd_rqstp = rqstp;
	readdir->rd_fhp = &cstate->current_fh;
	return nfs_ok;
}

static __be32
nfsd4_readlink(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	       struct nfsd4_readlink *readlink)
{
	readlink->rl_rqstp = rqstp;
	readlink->rl_fhp = &cstate->current_fh;
	return nfs_ok;
}

static __be32
nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     struct nfsd4_remove *remove)
{
	__be32 status;

	if (locks_in_grace())
		return nfserr_grace;
	status = nfsd_unlink(rqstp, &cstate->current_fh, 0,
			     remove->rm_name, remove->rm_namelen);
	if (status == nfserr_symlink)
		return nfserr_notdir;
	if (!status) {
		fh_unlock(&cstate->current_fh);
		set_change_info(&remove->rm_cinfo, &cstate->current_fh);
	}
	return status;
}

static __be32
nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     struct nfsd4_rename *rename)
{
	__be32 status = nfserr_nofilehandle;

	if (!cstate->save_fh.fh_dentry)
		return status;
	if (locks_in_grace() && !(cstate->save_fh.fh_export->ex_flags
					& NFSEXP_NOSUBTREECHECK))
		return nfserr_grace;
	status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname,
			     rename->rn_snamelen, &cstate->current_fh,
			     rename->rn_tname, rename->rn_tnamelen);

	/* the underlying filesystem returns different error's than required
	 * by NFSv4. both save_fh and current_fh have been verified.. */
	if (status == nfserr_isdir)
		status = nfserr_exist;
	else if ((status == nfserr_notdir) &&
                  (S_ISDIR(cstate->save_fh.fh_dentry->d_inode->i_mode) &&
                   S_ISDIR(cstate->current_fh.fh_dentry->d_inode->i_mode)))
		status = nfserr_exist;
	else if (status == nfserr_symlink)
		status = nfserr_notdir;

	if (!status) {
		set_change_info(&rename->rn_sinfo, &cstate->current_fh);
		set_change_info(&rename->rn_tinfo, &cstate->save_fh);
	}
	return status;
}

static __be32
nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	      struct nfsd4_secinfo *secinfo)
{
	struct svc_fh resfh;
	struct svc_export *exp;
	struct dentry *dentry;
	__be32 err;

	fh_init(&resfh, NFS4_FHSIZE);
	err = nfsd_lookup_dentry(rqstp, &cstate->current_fh,
				    secinfo->si_name, secinfo->si_namelen,
				    &exp, &dentry);
	if (err)
		return err;
	if (dentry->d_inode == NULL) {
		exp_put(exp);
		err = nfserr_noent;
	} else
		secinfo->si_exp = exp;
	dput(dentry);
	return err;
}

static __be32
nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	      struct nfsd4_setattr *setattr)
{
	__be32 status = nfs_ok;

	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
		nfs4_lock_state();
		status = nfs4_preprocess_stateid_op(&cstate->current_fh,
			&setattr->sa_stateid, CHECK_FH | WR_STATE, NULL);
		nfs4_unlock_state();
		if (status) {
			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
			return status;
		}
	}
	status = mnt_want_write(cstate->current_fh.fh_export->ex_path.mnt);
	if (status)
		return status;
	status = nfs_ok;
	if (setattr->sa_acl != NULL)
		status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh,
					    setattr->sa_acl);
	if (status)
		goto out;
	status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr,
				0, (time_t)0);
out:
	mnt_drop_write(cstate->current_fh.fh_export->ex_path.mnt);
	return status;
}

static __be32
nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	    struct nfsd4_write *write)
{
	stateid_t *stateid = &write->wr_stateid;
	struct file *filp = NULL;
	u32 *p;
	__be32 status = nfs_ok;

	/* no need to check permission - this will be done in nfsd_write() */

	if (write->wr_offset >= OFFSET_MAX)
		return nfserr_inval;

	nfs4_lock_state();
	status = nfs4_preprocess_stateid_op(&cstate->current_fh, stateid,
					CHECK_FH | WR_STATE, &filp);
	if (filp)
		get_file(filp);
	nfs4_unlock_state();

	if (status) {
		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
		return status;
	}

	write->wr_bytes_written = write->wr_buflen;
	write->wr_how_written = write->wr_stable_how;
	p = (u32 *)write->wr_verifier.data;
	*p++ = nfssvc_boot.tv_sec;
	*p++ = nfssvc_boot.tv_usec;

	status =  nfsd_write(rqstp, &cstate->current_fh, filp,
			     write->wr_offset, rqstp->rq_vec, write->wr_vlen,
			     write->wr_buflen, &write->wr_how_written);
	if (filp)
		fput(filp);

	if (status == nfserr_symlink)
		status = nfserr_inval;
	return status;
}

/* This routine never returns NFS_OK!  If there are no other errors, it
 * will return NFSERR_SAME or NFSERR_NOT_SAME depending on whether the
 * attributes matched.  VERIFY is implemented by mapping NFSERR_SAME
 * to NFS_OK after the call; NVERIFY by mapping NFSERR_NOT_SAME to NFS_OK.
 */
static __be32
_nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     struct nfsd4_verify *verify)
{
	__be32 *buf, *p;
	int count;
	__be32 status;

	status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
	if (status)
		return status;

	if ((verify->ve_bmval[0] & ~NFSD_SUPPORTED_ATTRS_WORD0)
	    || (verify->ve_bmval[1] & ~NFSD_SUPPORTED_ATTRS_WORD1))
		return nfserr_attrnotsupp;
	if ((verify->ve_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)
	    || (verify->ve_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1))
		return nfserr_inval;
	if (verify->ve_attrlen & 3)
		return nfserr_inval;

	/* count in words:
	 *   bitmap_len(1) + bitmap(2) + attr_len(1) = 4
	 */
	count = 4 + (verify->ve_attrlen >> 2);
	buf = kmalloc(count << 2, GFP_KERNEL);
	if (!buf)
		return nfserr_resource;

	status = nfsd4_encode_fattr(&cstate->current_fh,
				    cstate->current_fh.fh_export,
				    cstate->current_fh.fh_dentry, buf,
				    &count, verify->ve_bmval,
				    rqstp, 0);

	/* this means that nfsd4_encode_fattr() ran out of space */
	if (status == nfserr_resource && count == 0)
		status = nfserr_not_same;
	if (status)
		goto out_kfree;

	p = buf + 3;
	status = nfserr_not_same;
	if (ntohl(*p++) != verify->ve_attrlen)
		goto out_kfree;
	if (!memcmp(p, verify->ve_attrval, verify->ve_attrlen))
		status = nfserr_same;

out_kfree:
	kfree(buf);
	return status;
}

static __be32
nfsd4_nverify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	      struct nfsd4_verify *verify)
{
	__be32 status;

	status = _nfsd4_verify(rqstp, cstate, verify);
	return status == nfserr_not_same ? nfs_ok : status;
}

static __be32
nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	     struct nfsd4_verify *verify)
{
	__be32 status;

	status = _nfsd4_verify(rqstp, cstate, verify);
	return status == nfserr_same ? nfs_ok : status;
}

/*
 * NULL call.
 */
static __be32
nfsd4_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
{
	return nfs_ok;
}

static inline void nfsd4_increment_op_stats(u32 opnum)
{
	if (opnum >= FIRST_NFS4_OP && opnum <= LAST_NFS4_OP)
		nfsdstats.nfs4_opcount[opnum]++;
}

static void cstate_free(struct nfsd4_compound_state *cstate)
{
	if (cstate == NULL)
		return;
	fh_put(&cstate->current_fh);
	fh_put(&cstate->save_fh);
	BUG_ON(cstate->replay_owner);
	kfree(cstate);
}

static struct nfsd4_compound_state *cstate_alloc(void)
{
	struct nfsd4_compound_state *cstate;

	cstate = kmalloc(sizeof(struct nfsd4_compound_state), GFP_KERNEL);
	if (cstate == NULL)
		return NULL;
	fh_init(&cstate->current_fh, NFS4_FHSIZE);
	fh_init(&cstate->save_fh, NFS4_FHSIZE);
	cstate->replay_owner = NULL;
	return cstate;
}

typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
			      void *);

struct nfsd4_operation {
	nfsd4op_func op_func;
	u32 op_flags;
/* Most ops require a valid current filehandle; a few don't: */
#define ALLOWED_WITHOUT_FH 1
/* GETATTR and ops not listed as returning NFS4ERR_MOVED: */
#define ALLOWED_ON_ABSENT_FS 2
	char *op_name;
};

static struct nfsd4_operation nfsd4_ops[];

static const char *nfsd4_op_name(unsigned opnum);

/*
 * COMPOUND call.
 */
static __be32
nfsd4_proc_compound(struct svc_rqst *rqstp,
		    struct nfsd4_compoundargs *args,
		    struct nfsd4_compoundres *resp)
{
	struct nfsd4_op	*op;
	struct nfsd4_operation *opdesc;
	struct nfsd4_compound_state *cstate = NULL;
	int		slack_bytes;
	__be32		status;

	resp->xbuf = &rqstp->rq_res;
	resp->p = rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len;
	resp->tagp = resp->p;
	/* reserve space for: taglen, tag, and opcnt */
	resp->p += 2 + XDR_QUADLEN(args->taglen);
	resp->end = rqstp->rq_res.head[0].iov_base + PAGE_SIZE;
	resp->taglen = args->taglen;
	resp->tag = args->tag;
	resp->opcnt = 0;
	resp->rqstp = rqstp;

	/*
	 * According to RFC3010, this takes precedence over all other errors.
	 */
	status = nfserr_minor_vers_mismatch;
	if (args->minorversion > NFSD_SUPPORTED_MINOR_VERSION)
		goto out;

	status = nfserr_resource;
	cstate = cstate_alloc();
	if (cstate == NULL)
		goto out;

	status = nfs_ok;
	while (!status && resp->opcnt < args->opcnt) {
		op = &args->ops[resp->opcnt++];

		dprintk("nfsv4 compound op #%d/%d: %d (%s)\n",
			resp->opcnt, args->opcnt, op->opnum,
			nfsd4_op_name(op->opnum));

		/*
		 * The XDR decode routines may have pre-set op->status;
		 * for example, if there is a miscellaneous XDR error
		 * it will be set to nfserr_bad_xdr.
		 */
		if (op->status)
			goto encode_op;

		/* We must be able to encode a successful response to
		 * this operation, with enough room left over to encode a
		 * failed response to the next operation.  If we don't
		 * have enough room, fail with ERR_RESOURCE.
		 */
		slack_bytes = (char *)resp->end - (char *)resp->p;
		if (slack_bytes < COMPOUND_SLACK_SPACE
				+ COMPOUND_ERR_SLACK_SPACE) {
			BUG_ON(slack_bytes < COMPOUND_ERR_SLACK_SPACE);
			op->status = nfserr_resource;
			goto encode_op;
		}

		opdesc = &nfsd4_ops[op->opnum];

		if (!cstate->current_fh.fh_dentry) {
			if (!(opdesc->op_flags & ALLOWED_WITHOUT_FH)) {
				op->status = nfserr_nofilehandle;
				goto encode_op;
			}
		} else if (cstate->current_fh.fh_export->ex_fslocs.migrated &&
			  !(opdesc->op_flags & ALLOWED_ON_ABSENT_FS)) {
			op->status = nfserr_moved;
			goto encode_op;
		}

		if (opdesc->op_func)
			op->status = opdesc->op_func(rqstp, cstate, &op->u);
		else
			BUG_ON(op->status == nfs_ok);

encode_op:
		if (op->status == nfserr_replay_me) {
			op->replay = &cstate->replay_owner->so_replay;
			nfsd4_encode_replay(resp, op);
			status = op->status = op->replay->rp_status;
		} else {
			nfsd4_encode_operation(resp, op);
			status = op->status;
		}
		if (cstate->replay_owner) {
			nfs4_put_stateowner(cstate->replay_owner);
			cstate->replay_owner = NULL;
		}
		/* XXX Ugh, we need to get rid of this kind of special case: */
		if (op->opnum == OP_READ && op->u.read.rd_filp)
			fput(op->u.read.rd_filp);

		nfsd4_increment_op_stats(op->opnum);
	}

	cstate_free(cstate);
out:
	nfsd4_release_compoundargs(args);
	dprintk("nfsv4 compound returned %d\n", ntohl(status));
	return status;
}

static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
	[OP_ACCESS] = {
		.op_func = (nfsd4op_func)nfsd4_access,
		.op_name = "OP_ACCESS",
	},
	[OP_CLOSE] = {
		.op_func = (nfsd4op_func)nfsd4_close,
		.op_name = "OP_CLOSE",
	},
	[OP_COMMIT] = {
		.op_func = (nfsd4op_func)nfsd4_commit,
		.op_name = "OP_COMMIT",
	},
	[OP_CREATE] = {
		.op_func = (nfsd4op_func)nfsd4_create,
		.op_name = "OP_CREATE",
	},
	[OP_DELEGRETURN] = {
		.op_func = (nfsd4op_func)nfsd4_delegreturn,
		.op_name = "OP_DELEGRETURN",
	},
	[OP_GETATTR] = {
		.op_func = (nfsd4op_func)nfsd4_getattr,
		.op_flags = ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_GETATTR",
	},
	[OP_GETFH] = {
		.op_func = (nfsd4op_func)nfsd4_getfh,
		.op_name = "OP_GETFH",
	},
	[OP_LINK] = {
		.op_func = (nfsd4op_func)nfsd4_link,
		.op_name = "OP_LINK",
	},
	[OP_LOCK] = {
		.op_func = (nfsd4op_func)nfsd4_lock,
		.op_name = "OP_LOCK",
	},
	[OP_LOCKT] = {
		.op_func = (nfsd4op_func)nfsd4_lockt,
		.op_name = "OP_LOCKT",
	},
	[OP_LOCKU] = {
		.op_func = (nfsd4op_func)nfsd4_locku,
		.op_name = "OP_LOCKU",
	},
	[OP_LOOKUP] = {
		.op_func = (nfsd4op_func)nfsd4_lookup,
		.op_name = "OP_LOOKUP",
	},
	[OP_LOOKUPP] = {
		.op_func = (nfsd4op_func)nfsd4_lookupp,
		.op_name = "OP_LOOKUPP",
	},
	[OP_NVERIFY] = {
		.op_func = (nfsd4op_func)nfsd4_nverify,
		.op_name = "OP_NVERIFY",
	},
	[OP_OPEN] = {
		.op_func = (nfsd4op_func)nfsd4_open,
		.op_name = "OP_OPEN",
	},
	[OP_OPEN_CONFIRM] = {
		.op_func = (nfsd4op_func)nfsd4_open_confirm,
		.op_name = "OP_OPEN_CONFIRM",
	},
	[OP_OPEN_DOWNGRADE] = {
		.op_func = (nfsd4op_func)nfsd4_open_downgrade,
		.op_name = "OP_OPEN_DOWNGRADE",
	},
	[OP_PUTFH] = {
		.op_func = (nfsd4op_func)nfsd4_putfh,
		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_PUTFH",
	},
	[OP_PUTPUBFH] = {
		/* unsupported, just for future reference: */
		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_PUTPUBFH",
	},
	[OP_PUTROOTFH] = {
		.op_func = (nfsd4op_func)nfsd4_putrootfh,
		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_PUTROOTFH",
	},
	[OP_READ] = {
		.op_func = (nfsd4op_func)nfsd4_read,
		.op_name = "OP_READ",
	},
	[OP_READDIR] = {
		.op_func = (nfsd4op_func)nfsd4_readdir,
		.op_name = "OP_READDIR",
	},
	[OP_READLINK] = {
		.op_func = (nfsd4op_func)nfsd4_readlink,
		.op_name = "OP_READLINK",
	},
	[OP_REMOVE] = {
		.op_func = (nfsd4op_func)nfsd4_remove,
		.op_name = "OP_REMOVE",
	},
	[OP_RENAME] = {
		.op_name = "OP_RENAME",
		.op_func = (nfsd4op_func)nfsd4_rename,
	},
	[OP_RENEW] = {
		.op_func = (nfsd4op_func)nfsd4_renew,
		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_RENEW",
	},
	[OP_RESTOREFH] = {
		.op_func = (nfsd4op_func)nfsd4_restorefh,
		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_RESTOREFH",
	},
	[OP_SAVEFH] = {
		.op_func = (nfsd4op_func)nfsd4_savefh,
		.op_name = "OP_SAVEFH",
	},
	[OP_SECINFO] = {
		.op_func = (nfsd4op_func)nfsd4_secinfo,
		.op_name = "OP_SECINFO",
	},
	[OP_SETATTR] = {
		.op_func = (nfsd4op_func)nfsd4_setattr,
		.op_name = "OP_SETATTR",
	},
	[OP_SETCLIENTID] = {
		.op_func = (nfsd4op_func)nfsd4_setclientid,
		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_SETCLIENTID",
	},
	[OP_SETCLIENTID_CONFIRM] = {
		.op_func = (nfsd4op_func)nfsd4_setclientid_confirm,
		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_SETCLIENTID_CONFIRM",
	},
	[OP_VERIFY] = {
		.op_func = (nfsd4op_func)nfsd4_verify,
		.op_name = "OP_VERIFY",
	},
	[OP_WRITE] = {
		.op_func = (nfsd4op_func)nfsd4_write,
		.op_name = "OP_WRITE",
	},
	[OP_RELEASE_LOCKOWNER] = {
		.op_func = (nfsd4op_func)nfsd4_release_lockowner,
		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
		.op_name = "OP_RELEASE_LOCKOWNER",
	},
};

static const char *nfsd4_op_name(unsigned opnum)
{
	if (opnum < ARRAY_SIZE(nfsd4_ops))
		return nfsd4_ops[opnum].op_name;
	return "unknown_operation";
}

#define nfs4svc_decode_voidargs		NULL
#define nfs4svc_release_void		NULL
#define nfsd4_voidres			nfsd4_voidargs
#define nfs4svc_release_compound	NULL
struct nfsd4_voidargs { int dummy; };

#define PROC(name, argt, rest, relt, cache, respsize)	\
 { (svc_procfunc) nfsd4_proc_##name,		\
   (kxdrproc_t) nfs4svc_decode_##argt##args,	\
   (kxdrproc_t) nfs4svc_encode_##rest##res,	\
   (kxdrproc_t) nfs4svc_release_##relt,		\
   sizeof(struct nfsd4_##argt##args),		\
   sizeof(struct nfsd4_##rest##res),		\
   0,						\
   cache,					\
   respsize,					\
 }

/*
 * TODO: At the present time, the NFSv4 server does not do XID caching
 * of requests.  Implementing XID caching would not be a serious problem,
 * although it would require a mild change in interfaces since one
 * doesn't know whether an NFSv4 request is idempotent until after the
 * XDR decode.  However, XID caching totally confuses pynfs (Peter
 * Astrand's regression testsuite for NFSv4 servers), which reuses
 * XID's liberally, so I've left it unimplemented until pynfs generates
 * better XID's.
 */
static struct svc_procedure		nfsd_procedures4[2] = {
  PROC(null,	 void,		void,		void,	  RC_NOCACHE, 1),
  PROC(compound, compound,	compound,	compound, RC_NOCACHE, NFSD_BUFSIZE/4)
};

struct svc_version	nfsd_version4 = {
		.vs_vers	= 4,
		.vs_nproc	= 2,
		.vs_proc	= nfsd_procedures4,
		.vs_dispatch	= nfsd_dispatch,
		.vs_xdrsize	= NFS4_SVC_XDRSIZE,
};

/*
 * Local variables:
 *  c-basic-offset: 8
 * End:
 */