summaryrefslogtreecommitdiffstats
path: root/fs/nfsd/nfs4callback.c
blob: 5694cfb7a47b73a0d7128ed987cf1aaba6ea8859 (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
/*
 *  Copyright (c) 2001 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/sunrpc/clnt.h>
#include <linux/sunrpc/xprt.h>
#include <linux/sunrpc/svc_xprt.h>
#include <linux/slab.h>
#include "nfsd.h"
#include "state.h"
#include "netns.h"
#include "xdr4cb.h"

#define NFSDDBG_FACILITY                NFSDDBG_PROC

static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);

#define NFSPROC4_CB_NULL 0
#define NFSPROC4_CB_COMPOUND 1

/* Index of predefined Linux callback client operations */

struct nfs4_cb_compound_hdr {
	/* args */
	u32		ident;	/* minorversion 0 only */
	u32		nops;
	__be32		*nops_p;
	u32		minorversion;
	/* res */
	int		status;
};

/*
 * Handle decode buffer overflows out-of-line.
 */
static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
{
	dprintk("NFS: %s prematurely hit the end of our receive buffer. "
		"Remaining buffer length is %tu words.\n",
		func, xdr->end - xdr->p);
}

static __be32 *xdr_encode_empty_array(__be32 *p)
{
	*p++ = xdr_zero;
	return p;
}

/*
 * Encode/decode NFSv4 CB basic data types
 *
 * Basic NFSv4 callback data types are defined in section 15 of RFC
 * 3530: "Network File System (NFS) version 4 Protocol" and section
 * 20 of RFC 5661: "Network File System (NFS) Version 4 Minor Version
 * 1 Protocol"
 */

/*
 *	nfs_cb_opnum4
 *
 *	enum nfs_cb_opnum4 {
 *		OP_CB_GETATTR		= 3,
 *		  ...
 *	};
 */
enum nfs_cb_opnum4 {
	OP_CB_GETATTR			= 3,
	OP_CB_RECALL			= 4,
	OP_CB_LAYOUTRECALL		= 5,
	OP_CB_NOTIFY			= 6,
	OP_CB_PUSH_DELEG		= 7,
	OP_CB_RECALL_ANY		= 8,
	OP_CB_RECALLABLE_OBJ_AVAIL	= 9,
	OP_CB_RECALL_SLOT		= 10,
	OP_CB_SEQUENCE			= 11,
	OP_CB_WANTS_CANCELLED		= 12,
	OP_CB_NOTIFY_LOCK		= 13,
	OP_CB_NOTIFY_DEVICEID		= 14,
	OP_CB_ILLEGAL			= 10044
};

static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op)
{
	__be32 *p;

	p = xdr_reserve_space(xdr, 4);
	*p = cpu_to_be32(op);
}

/*
 * nfs_fh4
 *
 *	typedef opaque nfs_fh4<NFS4_FHSIZE>;
 */
static void encode_nfs_fh4(struct xdr_stream *xdr, const struct knfsd_fh *fh)
{
	u32 length = fh->fh_size;
	__be32 *p;

	BUG_ON(length > NFS4_FHSIZE);
	p = xdr_reserve_space(xdr, 4 + length);
	xdr_encode_opaque(p, &fh->fh_base, length);
}

/*
 * stateid4
 *
 *	struct stateid4 {
 *		uint32_t	seqid;
 *		opaque		other[12];
 *	};
 */
static void encode_stateid4(struct xdr_stream *xdr, const stateid_t *sid)
{
	__be32 *p;

	p = xdr_reserve_space(xdr, NFS4_STATEID_SIZE);
	*p++ = cpu_to_be32(sid->si_generation);
	xdr_encode_opaque_fixed(p, &sid->si_opaque, NFS4_STATEID_OTHER_SIZE);
}

/*
 * sessionid4
 *
 *	typedef opaque sessionid4[NFS4_SESSIONID_SIZE];
 */
static void encode_sessionid4(struct xdr_stream *xdr,
			      const struct nfsd4_session *session)
{
	__be32 *p;

	p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN);
	xdr_encode_opaque_fixed(p, session->se_sessionid.data,
					NFS4_MAX_SESSIONID_LEN);
}

/*
 * nfsstat4
 */
static const struct {
	int stat;
	int errno;
} nfs_cb_errtbl[] = {
	{ NFS4_OK,		0		},
	{ NFS4ERR_PERM,		-EPERM		},
	{ NFS4ERR_NOENT,	-ENOENT		},
	{ NFS4ERR_IO,		-EIO		},
	{ NFS4ERR_NXIO,		-ENXIO		},
	{ NFS4ERR_ACCESS,	-EACCES		},
	{ NFS4ERR_EXIST,	-EEXIST		},
	{ NFS4ERR_XDEV,		-EXDEV		},
	{ NFS4ERR_NOTDIR,	-ENOTDIR	},
	{ NFS4ERR_ISDIR,	-EISDIR		},
	{ NFS4ERR_INVAL,	-EINVAL		},
	{ NFS4ERR_FBIG,		-EFBIG		},
	{ NFS4ERR_NOSPC,	-ENOSPC		},
	{ NFS4ERR_ROFS,		-EROFS		},
	{ NFS4ERR_MLINK,	-EMLINK		},
	{ NFS4ERR_NAMETOOLONG,	-ENAMETOOLONG	},
	{ NFS4ERR_NOTEMPTY,	-ENOTEMPTY	},
	{ NFS4ERR_DQUOT,	-EDQUOT		},
	{ NFS4ERR_STALE,	-ESTALE		},
	{ NFS4ERR_BADHANDLE,	-EBADHANDLE	},
	{ NFS4ERR_BAD_COOKIE,	-EBADCOOKIE	},
	{ NFS4ERR_NOTSUPP,	-ENOTSUPP	},
	{ NFS4ERR_TOOSMALL,	-ETOOSMALL	},
	{ NFS4ERR_SERVERFAULT,	-ESERVERFAULT	},
	{ NFS4ERR_BADTYPE,	-EBADTYPE	},
	{ NFS4ERR_LOCKED,	-EAGAIN		},
	{ NFS4ERR_RESOURCE,	-EREMOTEIO	},
	{ NFS4ERR_SYMLINK,	-ELOOP		},
	{ NFS4ERR_OP_ILLEGAL,	-EOPNOTSUPP	},
	{ NFS4ERR_DEADLOCK,	-EDEADLK	},
	{ -1,			-EIO		}
};

/*
 * If we cannot translate the error, the recovery routines should
 * handle it.
 *
 * Note: remaining NFSv4 error codes have values > 10000, so should
 * not conflict with native Linux error codes.
 */
static int nfs_cb_stat_to_errno(int status)
{
	int i;

	for (i = 0; nfs_cb_errtbl[i].stat != -1; i++) {
		if (nfs_cb_errtbl[i].stat == status)
			return nfs_cb_errtbl[i].errno;
	}

	dprintk("NFSD: Unrecognized NFS CB status value: %u\n", status);
	return -status;
}

static int decode_cb_op_status(struct xdr_stream *xdr, enum nfs_opnum4 expected,
			       int *status)
{
	__be32 *p;
	u32 op;

	p = xdr_inline_decode(xdr, 4 + 4);
	if (unlikely(p == NULL))
		goto out_overflow;
	op = be32_to_cpup(p++);
	if (unlikely(op != expected))
		goto out_unexpected;
	*status = nfs_cb_stat_to_errno(be32_to_cpup(p));
	return 0;
out_overflow:
	print_overflow_msg(__func__, xdr);
	return -EIO;
out_unexpected:
	dprintk("NFSD: Callback server returned operation %d but "
		"we issued a request for %d\n", op, expected);
	return -EIO;
}

/*
 * CB_COMPOUND4args
 *
 *	struct CB_COMPOUND4args {
 *		utf8str_cs	tag;
 *		uint32_t	minorversion;
 *		uint32_t	callback_ident;
 *		nfs_cb_argop4	argarray<>;
 *	};
*/
static void encode_cb_compound4args(struct xdr_stream *xdr,
				    struct nfs4_cb_compound_hdr *hdr)
{
	__be32 * p;

	p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4);
	p = xdr_encode_empty_array(p);		/* empty tag */
	*p++ = cpu_to_be32(hdr->minorversion);
	*p++ = cpu_to_be32(hdr->ident);

	hdr->nops_p = p;
	*p = cpu_to_be32(hdr->nops);		/* argarray element count */
}

/*
 * Update argarray element count
 */
static void encode_cb_nops(struct nfs4_cb_compound_hdr *hdr)
{
	BUG_ON(hdr->nops > NFS4_MAX_BACK_CHANNEL_OPS);
	*hdr->nops_p = cpu_to_be32(hdr->nops);
}

/*
 * CB_COMPOUND4res
 *
 *	struct CB_COMPOUND4res {
 *		nfsstat4	status;
 *		utf8str_cs	tag;
 *		nfs_cb_resop4	resarray<>;
 *	};
 */
static int decode_cb_compound4res(struct xdr_stream *xdr,
				  struct nfs4_cb_compound_hdr *hdr)
{
	u32 length;
	__be32 *p;

	p = xdr_inline_decode(xdr, 4 + 4);
	if (unlikely(p == NULL))
		goto out_overflow;
	hdr->status = be32_to_cpup(p++);
	/* Ignore the tag */
	length = be32_to_cpup(p++);
	p = xdr_inline_decode(xdr, length + 4);
	if (unlikely(p == NULL))
		goto out_overflow;
	hdr->nops = be32_to_cpup(p);
	return 0;
out_overflow:
	print_overflow_msg(__func__, xdr);
	return -EIO;
}

/*
 * CB_RECALL4args
 *
 *	struct CB_RECALL4args {
 *		stateid4	stateid;
 *		bool		truncate;
 *		nfs_fh4		fh;
 *	};
 */
static void encode_cb_recall4args(struct xdr_stream *xdr,
				  const struct nfs4_delegation *dp,
				  struct nfs4_cb_compound_hdr *hdr)
{
	__be32 *p;

	encode_nfs_cb_opnum4(xdr, OP_CB_RECALL);
	encode_stateid4(xdr, &dp->dl_stid.sc_stateid);

	p = xdr_reserve_space(xdr, 4);
	*p++ = xdr_zero;			/* truncate */

	encode_nfs_fh4(xdr, &dp->dl_stid.sc_file->fi_fhandle);

	hdr->nops++;
}

/*
 * CB_SEQUENCE4args
 *
 *	struct CB_SEQUENCE4args {
 *		sessionid4		csa_sessionid;
 *		sequenceid4		csa_sequenceid;
 *		slotid4			csa_slotid;
 *		slotid4			csa_highest_slotid;
 *		bool			csa_cachethis;
 *		referring_call_list4	csa_referring_call_lists<>;
 *	};
 */
static void encode_cb_sequence4args(struct xdr_stream *xdr,
				    const struct nfsd4_callback *cb,
				    struct nfs4_cb_compound_hdr *hdr)
{
	struct nfsd4_session *session = cb->cb_clp->cl_cb_session;
	__be32 *p;

	if (hdr->minorversion == 0)
		return;

	encode_nfs_cb_opnum4(xdr, OP_CB_SEQUENCE);
	encode_sessionid4(xdr, session);

	p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4 + 4);
	*p++ = cpu_to_be32(session->se_cb_seq_nr);	/* csa_sequenceid */
	*p++ = xdr_zero;			/* csa_slotid */
	*p++ = xdr_zero;			/* csa_highest_slotid */
	*p++ = xdr_zero;			/* csa_cachethis */
	xdr_encode_empty_array(p);		/* csa_referring_call_lists */

	hdr->nops++;
}

/*
 * CB_SEQUENCE4resok
 *
 *	struct CB_SEQUENCE4resok {
 *		sessionid4	csr_sessionid;
 *		sequenceid4	csr_sequenceid;
 *		slotid4		csr_slotid;
 *		slotid4		csr_highest_slotid;
 *		slotid4		csr_target_highest_slotid;
 *	};
 *
 *	union CB_SEQUENCE4res switch (nfsstat4 csr_status) {
 *	case NFS4_OK:
 *		CB_SEQUENCE4resok	csr_resok4;
 *	default:
 *		void;
 *	};
 *
 * Our current back channel implmentation supports a single backchannel
 * with a single slot.
 */
static int decode_cb_sequence4resok(struct xdr_stream *xdr,
				    struct nfsd4_callback *cb)
{
	struct nfsd4_session *session = cb->cb_clp->cl_cb_session;
	struct nfs4_sessionid id;
	int status;
	__be32 *p;
	u32 dummy;

	status = -ESERVERFAULT;

	/*
	 * If the server returns different values for sessionID, slotID or
	 * sequence number, the server is looney tunes.
	 */
	p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4 + 4 + 4);
	if (unlikely(p == NULL))
		goto out_overflow;
	memcpy(id.data, p, NFS4_MAX_SESSIONID_LEN);
	if (memcmp(id.data, session->se_sessionid.data,
					NFS4_MAX_SESSIONID_LEN) != 0) {
		dprintk("NFS: %s Invalid session id\n", __func__);
		goto out;
	}
	p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN);

	dummy = be32_to_cpup(p++);
	if (dummy != session->se_cb_seq_nr) {
		dprintk("NFS: %s Invalid sequence number\n", __func__);
		goto out;
	}

	dummy = be32_to_cpup(p++);
	if (dummy != 0) {
		dprintk("NFS: %s Invalid slotid\n", __func__);
		goto out;
	}

	/*
	 * FIXME: process highest slotid and target highest slotid
	 */
	status = 0;
out:
	if (status)
		nfsd4_mark_cb_fault(cb->cb_clp, status);
	return status;
out_overflow:
	print_overflow_msg(__func__, xdr);
	return -EIO;
}

static int decode_cb_sequence4res(struct xdr_stream *xdr,
				  struct nfsd4_callback *cb)
{
	int status;

	if (cb->cb_minorversion == 0)
		return 0;

	status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &cb->cb_status);
	if (unlikely(status || cb->cb_status))
		return status;

	return decode_cb_sequence4resok(xdr, cb);
}

/*
 * NFSv4.0 and NFSv4.1 XDR encode functions
 *
 * NFSv4.0 callback argument types are defined in section 15 of RFC
 * 3530: "Network File System (NFS) version 4 Protocol" and section 20
 * of RFC 5661:  "Network File System (NFS) Version 4 Minor Version 1
 * Protocol".
 */

/*
 * NB: Without this zero space reservation, callbacks over krb5p fail
 */
static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
				 void *__unused)
{
	xdr_reserve_space(xdr, 0);
}

/*
 * 20.2. Operation 4: CB_RECALL - Recall a Delegation
 */
static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
				   const struct nfsd4_callback *cb)
{
	const struct nfs4_delegation *dp = cb_to_delegation(cb);
	struct nfs4_cb_compound_hdr hdr = {
		.ident = cb->cb_clp->cl_cb_ident,
		.minorversion = cb->cb_minorversion,
	};

	encode_cb_compound4args(xdr, &hdr);
	encode_cb_sequence4args(xdr, cb, &hdr);
	encode_cb_recall4args(xdr, dp, &hdr);
	encode_cb_nops(&hdr);
}


/*
 * NFSv4.0 and NFSv4.1 XDR decode functions
 *
 * NFSv4.0 callback result types are defined in section 15 of RFC
 * 3530: "Network File System (NFS) version 4 Protocol" and section 20
 * of RFC 5661:  "Network File System (NFS) Version 4 Minor Version 1
 * Protocol".
 */

static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
				void *__unused)
{
	return 0;
}

/*
 * 20.2. Operation 4: CB_RECALL - Recall a Delegation
 */
static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
				  struct xdr_stream *xdr,
				  struct nfsd4_callback *cb)
{
	struct nfs4_cb_compound_hdr hdr;
	int status;

	status = decode_cb_compound4res(xdr, &hdr);
	if (unlikely(status))
		return status;

	if (cb != NULL) {
		status = decode_cb_sequence4res(xdr, cb);
		if (unlikely(status || cb->cb_status))
			return status;
	}

	return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status);
}

#ifdef CONFIG_NFSD_PNFS
/*
 * CB_LAYOUTRECALL4args
 *
 *	struct layoutrecall_file4 {
 *		nfs_fh4         lor_fh;
 *		offset4         lor_offset;
 *		length4         lor_length;
 *		stateid4        lor_stateid;
 *	};
 *
 *	union layoutrecall4 switch(layoutrecall_type4 lor_recalltype) {
 *	case LAYOUTRECALL4_FILE:
 *		layoutrecall_file4 lor_layout;
 *	case LAYOUTRECALL4_FSID:
 *		fsid4              lor_fsid;
 *	case LAYOUTRECALL4_ALL:
 *		void;
 *	};
 *
 *	struct CB_LAYOUTRECALL4args {
 *		layouttype4             clora_type;
 *		layoutiomode4           clora_iomode;
 *		bool                    clora_changed;
 *		layoutrecall4           clora_recall;
 *	};
 */
static void encode_cb_layout4args(struct xdr_stream *xdr,
				  const struct nfs4_layout_stateid *ls,
				  struct nfs4_cb_compound_hdr *hdr)
{
	__be32 *p;

	BUG_ON(hdr->minorversion == 0);

	p = xdr_reserve_space(xdr, 5 * 4);
	*p++ = cpu_to_be32(OP_CB_LAYOUTRECALL);
	*p++ = cpu_to_be32(ls->ls_layout_type);
	*p++ = cpu_to_be32(IOMODE_ANY);
	*p++ = cpu_to_be32(1);
	*p = cpu_to_be32(RETURN_FILE);

	encode_nfs_fh4(xdr, &ls->ls_stid.sc_file->fi_fhandle);

	p = xdr_reserve_space(xdr, 2 * 8);
	p = xdr_encode_hyper(p, 0);
	xdr_encode_hyper(p, NFS4_MAX_UINT64);

	encode_stateid4(xdr, &ls->ls_recall_sid);

	hdr->nops++;
}

static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req,
				   struct xdr_stream *xdr,
				   const struct nfsd4_callback *cb)
{
	const struct nfs4_layout_stateid *ls =
		container_of(cb, struct nfs4_layout_stateid, ls_recall);
	struct nfs4_cb_compound_hdr hdr = {
		.ident = 0,
		.minorversion = cb->cb_minorversion,
	};

	encode_cb_compound4args(xdr, &hdr);
	encode_cb_sequence4args(xdr, cb, &hdr);
	encode_cb_layout4args(xdr, ls, &hdr);
	encode_cb_nops(&hdr);
}

static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp,
				  struct xdr_stream *xdr,
				  struct nfsd4_callback *cb)
{
	struct nfs4_cb_compound_hdr hdr;
	int status;

	status = decode_cb_compound4res(xdr, &hdr);
	if (unlikely(status))
		return status;

	if (cb) {
		status = decode_cb_sequence4res(xdr, cb);
		if (unlikely(status || cb->cb_status))
			return status;
	}
	return decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &cb->cb_status);
}
#endif /* CONFIG_NFSD_PNFS */

/*
 * RPC procedure tables
 */
#define PROC(proc, call, argtype, restype)				\
[NFSPROC4_CLNT_##proc] = {						\
	.p_proc    = NFSPROC4_CB_##call,				\
	.p_encode  = (kxdreproc_t)nfs4_xdr_enc_##argtype,		\
	.p_decode  = (kxdrdproc_t)nfs4_xdr_dec_##restype,		\
	.p_arglen  = NFS4_enc_##argtype##_sz,				\
	.p_replen  = NFS4_dec_##restype##_sz,				\
	.p_statidx = NFSPROC4_CB_##call,				\
	.p_name    = #proc,						\
}

static struct rpc_procinfo nfs4_cb_procedures[] = {
	PROC(CB_NULL,	NULL,		cb_null,	cb_null),
	PROC(CB_RECALL,	COMPOUND,	cb_recall,	cb_recall),
#ifdef CONFIG_NFSD_PNFS
	PROC(CB_LAYOUT,	COMPOUND,	cb_layout,	cb_layout),
#endif
};

static struct rpc_version nfs_cb_version4 = {
/*
 * Note on the callback rpc program version number: despite language in rfc
 * 5661 section 18.36.3 requiring servers to use 4 in this field, the
 * official xdr descriptions for both 4.0 and 4.1 specify version 1, and
 * in practice that appears to be what implementations use.  The section
 * 18.36.3 language is expected to be fixed in an erratum.
 */
	.number			= 1,
	.nrprocs		= ARRAY_SIZE(nfs4_cb_procedures),
	.procs			= nfs4_cb_procedures
};

static const struct rpc_version *nfs_cb_version[] = {
	&nfs_cb_version4,
};

static const struct rpc_program cb_program;

static struct rpc_stat cb_stats = {
	.program		= &cb_program
};

#define NFS4_CALLBACK 0x40000000
static const struct rpc_program cb_program = {
	.name			= "nfs4_cb",
	.number			= NFS4_CALLBACK,
	.nrvers			= ARRAY_SIZE(nfs_cb_version),
	.version		= nfs_cb_version,
	.stats			= &cb_stats,
	.pipe_dir_name		= "nfsd4_cb",
};

static int max_cb_time(struct net *net)
{
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
	return max(nn->nfsd4_lease/10, (time_t)1) * HZ;
}

static struct rpc_cred *callback_cred;

int set_callback_cred(void)
{
	if (callback_cred)
		return 0;
	callback_cred = rpc_lookup_machine_cred("nfs");
	if (!callback_cred)
		return -ENOMEM;
	return 0;
}

static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
{
	if (clp->cl_minorversion == 0) {
		return get_rpccred(callback_cred);
	} else {
		struct rpc_auth *auth = client->cl_auth;
		struct auth_cred acred = {};

		acred.uid = ses->se_cb_sec.uid;
		acred.gid = ses->se_cb_sec.gid;
		return auth->au_ops->lookup_cred(client->cl_auth, &acred, 0);
	}
}

static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args)
{
	struct rpc_xprt *xprt;

	if (args->protocol != XPRT_TRANSPORT_BC_TCP)
		return rpc_create(args);

	xprt = args->bc_xprt->xpt_bc_xprt;
	if (xprt) {
		xprt_get(xprt);
		return rpc_create_xprt(args, xprt);
	}

	return rpc_create(args);
}

static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
{
	int maxtime = max_cb_time(clp->net);
	struct rpc_timeout	timeparms = {
		.to_initval	= maxtime,
		.to_retries	= 0,
		.to_maxval	= maxtime,
	};
	struct rpc_create_args args = {
		.net		= clp->net,
		.address	= (struct sockaddr *) &conn->cb_addr,
		.addrsize	= conn->cb_addrlen,
		.saddress	= (struct sockaddr *) &conn->cb_saddr,
		.timeout	= &timeparms,
		.program	= &cb_program,
		.version	= 0,
		.flags		= (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
	};
	struct rpc_clnt *client;
	struct rpc_cred *cred;

	if (clp->cl_minorversion == 0) {
		if (!clp->cl_cred.cr_principal &&
				(clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5))
			return -EINVAL;
		args.client_name = clp->cl_cred.cr_principal;
		args.prognumber	= conn->cb_prog;
		args.protocol = XPRT_TRANSPORT_TCP;
		args.authflavor = clp->cl_cred.cr_flavor;
		clp->cl_cb_ident = conn->cb_ident;
	} else {
		if (!conn->cb_xprt)
			return -EINVAL;
		clp->cl_cb_conn.cb_xprt = conn->cb_xprt;
		clp->cl_cb_session = ses;
		args.bc_xprt = conn->cb_xprt;
		args.prognumber = clp->cl_cb_session->se_cb_prog;
		args.protocol = conn->cb_xprt->xpt_class->xcl_ident |
				XPRT_TRANSPORT_BC;
		args.authflavor = ses->se_cb_sec.flavor;
	}
	/* Create RPC client */
	client = create_backchannel_client(&args);
	if (IS_ERR(client)) {
		dprintk("NFSD: couldn't create callback client: %ld\n",
			PTR_ERR(client));
		return PTR_ERR(client);
	}
	cred = get_backchannel_cred(clp, client, ses);
	if (IS_ERR(cred)) {
		rpc_shutdown_client(client);
		return PTR_ERR(cred);
	}
	clp->cl_cb_client = client;
	clp->cl_cb_cred = cred;
	return 0;
}

static void warn_no_callback_path(struct nfs4_client *clp, int reason)
{
	dprintk("NFSD: warning: no callback path to client %.*s: error %d\n",
		(int)clp->cl_name.len, clp->cl_name.data, reason);
}

static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason)
{
	clp->cl_cb_state = NFSD4_CB_DOWN;
	warn_no_callback_path(clp, reason);
}

static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason)
{
	clp->cl_cb_state = NFSD4_CB_FAULT;
	warn_no_callback_path(clp, reason);
}

static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata)
{
	struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null);

	if (task->tk_status)
		nfsd4_mark_cb_down(clp, task->tk_status);
	else
		clp->cl_cb_state = NFSD4_CB_UP;
}

static const struct rpc_call_ops nfsd4_cb_probe_ops = {
	/* XXX: release method to ensure we set the cb channel down if
	 * necessary on early failure? */
	.rpc_call_done = nfsd4_cb_probe_done,
};

static struct workqueue_struct *callback_wq;

/*
 * Poke the callback thread to process any updates to the callback
 * parameters, and send a null probe.
 */
void nfsd4_probe_callback(struct nfs4_client *clp)
{
	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
	nfsd4_run_cb(&clp->cl_cb_null);
}

void nfsd4_probe_callback_sync(struct nfs4_client *clp)
{
	nfsd4_probe_callback(clp);
	flush_workqueue(callback_wq);
}

void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
{
	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
	spin_lock(&clp->cl_lock);
	memcpy(&clp->cl_cb_conn, conn, sizeof(struct nfs4_cb_conn));
	spin_unlock(&clp->cl_lock);
}

/*
 * There's currently a single callback channel slot.
 * If the slot is available, then mark it busy.  Otherwise, set the
 * thread for sleeping on the callback RPC wait queue.
 */
static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task)
{
	if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
		rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
		/* Race breaker */
		if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
			dprintk("%s slot is busy\n", __func__);
			return false;
		}
		rpc_wake_up_queued_task(&clp->cl_cb_waitq, task);
	}
	return true;
}

/*
 * TODO: cb_sequence should support referring call lists, cachethis, multiple
 * slots, and mark callback channel down on communication errors.
 */
static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
{
	struct nfsd4_callback *cb = calldata;
	struct nfs4_client *clp = cb->cb_clp;
	u32 minorversion = clp->cl_minorversion;

	cb->cb_minorversion = minorversion;
	if (minorversion) {
		if (!nfsd41_cb_get_slot(clp, task))
			return;
	}
	rpc_call_start(task);
}

static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
{
	struct nfsd4_callback *cb = calldata;
	struct nfs4_client *clp = cb->cb_clp;

	dprintk("%s: minorversion=%d\n", __func__,
		clp->cl_minorversion);

	if (clp->cl_minorversion) {
		/* No need for lock, access serialized in nfsd4_cb_prepare */
		if (!task->tk_status)
			++clp->cl_cb_session->se_cb_seq_nr;
		clear_bit(0, &clp->cl_cb_slot_busy);
		rpc_wake_up_next(&clp->cl_cb_waitq);
		dprintk("%s: freed slot, new seqid=%d\n", __func__,
			clp->cl_cb_session->se_cb_seq_nr);
	}

	/*
	 * If the backchannel connection was shut down while this
	 * task was queued, we need to resubmit it after setting up
	 * a new backchannel connection.
	 *
	 * Note that if we lost our callback connection permanently
	 * the submission code will error out, so we don't need to
	 * handle that case here.
	 */
	if (task->tk_flags & RPC_TASK_KILLED) {
		task->tk_status = 0;
		cb->cb_need_restart = true;
		return;
	}

	if (cb->cb_status) {
		WARN_ON_ONCE(task->tk_status);
		task->tk_status = cb->cb_status;
	}

	switch (cb->cb_ops->done(cb, task)) {
	case 0:
		task->tk_status = 0;
		rpc_restart_call_prepare(task);
		return;
	case 1:
		break;
	case -1:
		/* Network partition? */
		nfsd4_mark_cb_down(clp, task->tk_status);
		break;
	default:
		BUG();
	}
}

static void nfsd4_cb_release(void *calldata)
{
	struct nfsd4_callback *cb = calldata;

	if (cb->cb_need_restart)
		nfsd4_run_cb(cb);
	else
		cb->cb_ops->release(cb);

}

static const struct rpc_call_ops nfsd4_cb_ops = {
	.rpc_call_prepare = nfsd4_cb_prepare,
	.rpc_call_done = nfsd4_cb_done,
	.rpc_release = nfsd4_cb_release,
};

int nfsd4_create_callback_queue(void)
{
	callback_wq = create_singlethread_workqueue("nfsd4_callbacks");
	if (!callback_wq)
		return -ENOMEM;
	return 0;
}

void nfsd4_destroy_callback_queue(void)
{
	destroy_workqueue(callback_wq);
}

/* must be called under the state lock */
void nfsd4_shutdown_callback(struct nfs4_client *clp)
{
	set_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags);
	/*
	 * Note this won't actually result in a null callback;
	 * instead, nfsd4_run_cb_null() will detect the killed
	 * client, destroy the rpc client, and stop:
	 */
	nfsd4_run_cb(&clp->cl_cb_null);
	flush_workqueue(callback_wq);
}

/* requires cl_lock: */
static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp)
{
	struct nfsd4_session *s;
	struct nfsd4_conn *c;

	list_for_each_entry(s, &clp->cl_sessions, se_perclnt) {
		list_for_each_entry(c, &s->se_conns, cn_persession) {
			if (c->cn_flags & NFS4_CDFC4_BACK)
				return c;
		}
	}
	return NULL;
}

static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
{
	struct nfs4_cb_conn conn;
	struct nfs4_client *clp = cb->cb_clp;
	struct nfsd4_session *ses = NULL;
	struct nfsd4_conn *c;
	int err;

	/*
	 * This is either an update, or the client dying; in either case,
	 * kill the old client:
	 */
	if (clp->cl_cb_client) {
		rpc_shutdown_client(clp->cl_cb_client);
		clp->cl_cb_client = NULL;
		put_rpccred(clp->cl_cb_cred);
		clp->cl_cb_cred = NULL;
	}
	if (clp->cl_cb_conn.cb_xprt) {
		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
		clp->cl_cb_conn.cb_xprt = NULL;
	}
	if (test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags))
		return;
	spin_lock(&clp->cl_lock);
	/*
	 * Only serialized callback code is allowed to clear these
	 * flags; main nfsd code can only set them:
	 */
	BUG_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK));
	clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
	memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn));
	c = __nfsd4_find_backchannel(clp);
	if (c) {
		svc_xprt_get(c->cn_xprt);
		conn.cb_xprt = c->cn_xprt;
		ses = c->cn_session;
	}
	spin_unlock(&clp->cl_lock);

	err = setup_callback_client(clp, &conn, ses);
	if (err) {
		nfsd4_mark_cb_down(clp, err);
		return;
	}
}

static void
nfsd4_run_cb_work(struct work_struct *work)
{
	struct nfsd4_callback *cb =
		container_of(work, struct nfsd4_callback, cb_work);
	struct nfs4_client *clp = cb->cb_clp;
	struct rpc_clnt *clnt;

	if (cb->cb_need_restart) {
		cb->cb_need_restart = false;
	} else {
		if (cb->cb_ops && cb->cb_ops->prepare)
			cb->cb_ops->prepare(cb);
	}

	if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)
		nfsd4_process_cb_update(cb);

	clnt = clp->cl_cb_client;
	if (!clnt) {
		/* Callback channel broken, or client killed; give up: */
		if (cb->cb_ops && cb->cb_ops->release)
			cb->cb_ops->release(cb);
		return;
	}

	/*
	 * Don't send probe messages for 4.1 or later.
	 */
	if (!cb->cb_ops && clp->cl_minorversion) {
		clp->cl_cb_state = NFSD4_CB_UP;
		return;
	}

	cb->cb_msg.rpc_cred = clp->cl_cb_cred;
	rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
			cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb);
}

void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
		struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op)
{
	cb->cb_clp = clp;
	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[op];
	cb->cb_msg.rpc_argp = cb;
	cb->cb_msg.rpc_resp = cb;
	cb->cb_ops = ops;
	INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
	cb->cb_status = 0;
	cb->cb_need_restart = false;
}

void nfsd4_run_cb(struct nfsd4_callback *cb)
{
	queue_work(callback_wq, &cb->cb_work);
}