aboutsummaryrefslogtreecommitdiff
path: root/net/sunrpc/xdr.c
blob: f86d1baa63029b38524c7ef0a1c225038f7a9b9a (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
/*
 * linux/net/sunrpc/xdr.c
 *
 * Generic XDR support.
 *
 * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
 */

#include <linux/types.h>
#include <linux/socket.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/pagemap.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/net.h>
#include <net/sock.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/msg_prot.h>

/*
 * XDR functions for basic NFS types
 */
u32 *
xdr_encode_netobj(u32 *p, const struct xdr_netobj *obj)
{
	unsigned int	quadlen = XDR_QUADLEN(obj->len);

	p[quadlen] = 0;		/* zero trailing bytes */
	*p++ = htonl(obj->len);
	memcpy(p, obj->data, obj->len);
	return p + XDR_QUADLEN(obj->len);
}

u32 *
xdr_decode_netobj(u32 *p, struct xdr_netobj *obj)
{
	unsigned int	len;

	if ((len = ntohl(*p++)) > XDR_MAX_NETOBJ)
		return NULL;
	obj->len  = len;
	obj->data = (u8 *) p;
	return p + XDR_QUADLEN(len);
}

/**
 * xdr_encode_opaque_fixed - Encode fixed length opaque data
 * @p: pointer to current position in XDR buffer.
 * @ptr: pointer to data to encode (or NULL)
 * @nbytes: size of data.
 *
 * Copy the array of data of length nbytes at ptr to the XDR buffer
 * at position p, then align to the next 32-bit boundary by padding
 * with zero bytes (see RFC1832).
 * Note: if ptr is NULL, only the padding is performed.
 *
 * Returns the updated current XDR buffer position
 *
 */
u32 *xdr_encode_opaque_fixed(u32 *p, const void *ptr, unsigned int nbytes)
{
	if (likely(nbytes != 0)) {
		unsigned int quadlen = XDR_QUADLEN(nbytes);
		unsigned int padding = (quadlen << 2) - nbytes;

		if (ptr != NULL)
			memcpy(p, ptr, nbytes);
		if (padding != 0)
			memset((char *)p + nbytes, 0, padding);
		p += quadlen;
	}
	return p;
}
EXPORT_SYMBOL(xdr_encode_opaque_fixed);

/**
 * xdr_encode_opaque - Encode variable length opaque data
 * @p: pointer to current position in XDR buffer.
 * @ptr: pointer to data to encode (or NULL)
 * @nbytes: size of data.
 *
 * Returns the updated current XDR buffer position
 */
u32 *xdr_encode_opaque(u32 *p, const void *ptr, unsigned int nbytes)
{
	*p++ = htonl(nbytes);
	return xdr_encode_opaque_fixed(p, ptr, nbytes);
}
EXPORT_SYMBOL(xdr_encode_opaque);

u32 *
xdr_encode_string(u32 *p, const char *string)
{
	return xdr_encode_array(p, string, strlen(string));
}

u32 *
xdr_decode_string(u32 *p, char **sp, int *lenp, int maxlen)
{
	unsigned int	len;
	char		*string;

	if ((len = ntohl(*p++)) > maxlen)
		return NULL;
	if (lenp)
		*lenp = len;
	if ((len % 4) != 0) {
		string = (char *) p;
	} else {
		string = (char *) (p - 1);
		memmove(string, p, len);
	}
	string[len] = '\0';
	*sp = string;
	return p + XDR_QUADLEN(len);
}

u32 *
xdr_decode_string_inplace(u32 *p, char **sp, int *lenp, int maxlen)
{
	unsigned int	len;

	if ((len = ntohl(*p++)) > maxlen)
		return NULL;
	*lenp = len;
	*sp = (char *) p;
	return p + XDR_QUADLEN(len);
}

void
xdr_encode_pages(struct xdr_buf *xdr, struct page **pages, unsigned int base,
		 unsigned int len)
{
	struct kvec *tail = xdr->tail;
	u32 *p;

	xdr->pages = pages;
	xdr->page_base = base;
	xdr->page_len = len;

	p = (u32 *)xdr->head[0].iov_base + XDR_QUADLEN(xdr->head[0].iov_len);
	tail->iov_base = p;
	tail->iov_len = 0;

	if (len & 3) {
		unsigned int pad = 4 - (len & 3);

		*p = 0;
		tail->iov_base = (char *)p + (len & 3);
		tail->iov_len  = pad;
		len += pad;
	}
	xdr->buflen += len;
	xdr->len += len;
}

void
xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset,
		 struct page **pages, unsigned int base, unsigned int len)
{
	struct kvec *head = xdr->head;
	struct kvec *tail = xdr->tail;
	char *buf = (char *)head->iov_base;
	unsigned int buflen = head->iov_len;

	head->iov_len  = offset;

	xdr->pages = pages;
	xdr->page_base = base;
	xdr->page_len = len;

	tail->iov_base = buf + offset;
	tail->iov_len = buflen - offset;

	xdr->buflen += len;
}

void
xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base,
			  skb_reader_t *desc,
			  skb_read_actor_t copy_actor)
{
	struct page	**ppage = xdr->pages;
	unsigned int	len, pglen = xdr->page_len;
	int		ret;

	len = xdr->head[0].iov_len;
	if (base < len) {
		len -= base;
		ret = copy_actor(desc, (char *)xdr->head[0].iov_base + base, len);
		if (ret != len || !desc->count)
			return;
		base = 0;
	} else
		base -= len;

	if (pglen == 0)
		goto copy_tail;
	if (base >= pglen) {
		base -= pglen;
		goto copy_tail;
	}
	if (base || xdr->page_base) {
		pglen -= base;
		base  += xdr->page_base;
		ppage += base >> PAGE_CACHE_SHIFT;
		base &= ~PAGE_CACHE_MASK;
	}
	do {
		char *kaddr;

		len = PAGE_CACHE_SIZE;
		kaddr = kmap_atomic(*ppage, KM_SKB_SUNRPC_DATA);
		if (base) {
			len -= base;
			if (pglen < len)
				len = pglen;
			ret = copy_actor(desc, kaddr + base, len);
			base = 0;
		} else {
			if (pglen < len)
				len = pglen;
			ret = copy_actor(desc, kaddr, len);
		}
		flush_dcache_page(*ppage);
		kunmap_atomic(kaddr, KM_SKB_SUNRPC_DATA);
		if (ret != len || !desc->count)
			return;
		ppage++;
	} while ((pglen -= len) != 0);
copy_tail:
	len = xdr->tail[0].iov_len;
	if (base < len)
		copy_actor(desc, (char *)xdr->tail[0].iov_base + base, len - base);
}


int
xdr_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
		struct xdr_buf *xdr, unsigned int base, int msgflags)
{
	struct page **ppage = xdr->pages;
	unsigned int len, pglen = xdr->page_len;
	int err, ret = 0;
	ssize_t (*sendpage)(struct socket *, struct page *, int, size_t, int);

	len = xdr->head[0].iov_len;
	if (base < len || (addr != NULL && base == 0)) {
		struct kvec iov = {
			.iov_base = xdr->head[0].iov_base + base,
			.iov_len  = len - base,
		};
		struct msghdr msg = {
			.msg_name    = addr,
			.msg_namelen = addrlen,
			.msg_flags   = msgflags,
		};
		if (xdr->len > len)
			msg.msg_flags |= MSG_MORE;

		if (iov.iov_len != 0)
			err = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
		else
			err = kernel_sendmsg(sock, &msg, NULL, 0, 0);
		if (ret == 0)
			ret = err;
		else if (err > 0)
			ret += err;
		if (err != iov.iov_len)
			goto out;
		base = 0;
	} else
		base -= len;

	if (pglen == 0)
		goto copy_tail;
	if (base >= pglen) {
		base -= pglen;
		goto copy_tail;
	}
	if (base || xdr->page_base) {
		pglen -= base;
		base  += xdr->page_base;
		ppage += base >> PAGE_CACHE_SHIFT;
		base &= ~PAGE_CACHE_MASK;
	}

	sendpage = sock->ops->sendpage ? : sock_no_sendpage;
	do {
		int flags = msgflags;

		len = PAGE_CACHE_SIZE;
		if (base)
			len -= base;
		if (pglen < len)
			len = pglen;

		if (pglen != len || xdr->tail[0].iov_len != 0)
			flags |= MSG_MORE;

		/* Hmm... We might be dealing with highmem pages */
		if (PageHighMem(*ppage))
			sendpage = sock_no_sendpage;
		err = sendpage(sock, *ppage, base, len, flags);
		if (ret == 0)
			ret = err;
		else if (err > 0)
			ret += err;
		if (err != len)
			goto out;
		base = 0;
		ppage++;
	} while ((pglen -= len) != 0);
copy_tail:
	len = xdr->tail[0].iov_len;
	if (base < len) {
		struct kvec iov = {
			.iov_base = xdr->tail[0].iov_base + base,
			.iov_len  = len - base,
		};
		struct msghdr msg = {
			.msg_flags   = msgflags,
		};
		err = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
		if (ret == 0)
			ret = err;
		else if (err > 0)
			ret += err;
	}
out:
	return ret;
}


/*
 * Helper routines for doing 'memmove' like operations on a struct xdr_buf
 *
 * _shift_data_right_pages
 * @pages: vector of pages containing both the source and dest memory area.
 * @pgto_base: page vector address of destination
 * @pgfrom_base: page vector address of source
 * @len: number of bytes to copy
 *
 * Note: the addresses pgto_base and pgfrom_base are both calculated in
 *       the same way:
 *            if a memory area starts at byte 'base' in page 'pages[i]',
 *            then its address is given as (i << PAGE_CACHE_SHIFT) + base
 * Also note: pgfrom_base must be < pgto_base, but the memory areas
 * 	they point to may overlap.
 */
static void
_shift_data_right_pages(struct page **pages, size_t pgto_base,
		size_t pgfrom_base, size_t len)
{
	struct page **pgfrom, **pgto;
	char *vfrom, *vto;
	size_t copy;

	BUG_ON(pgto_base <= pgfrom_base);

	pgto_base += len;
	pgfrom_base += len;

	pgto = pages + (pgto_base >> PAGE_CACHE_SHIFT);
	pgfrom = pages + (pgfrom_base >> PAGE_CACHE_SHIFT);

	pgto_base &= ~PAGE_CACHE_MASK;
	pgfrom_base &= ~PAGE_CACHE_MASK;

	do {
		/* Are any pointers crossing a page boundary? */
		if (pgto_base == 0) {
			flush_dcache_page(*pgto);
			pgto_base = PAGE_CACHE_SIZE;
			pgto--;
		}
		if (pgfrom_base == 0) {
			pgfrom_base = PAGE_CACHE_SIZE;
			pgfrom--;
		}

		copy = len;
		if (copy > pgto_base)
			copy = pgto_base;
		if (copy > pgfrom_base)
			copy = pgfrom_base;
		pgto_base -= copy;
		pgfrom_base -= copy;

		vto = kmap_atomic(*pgto, KM_USER0);
		vfrom = kmap_atomic(*pgfrom, KM_USER1);
		memmove(vto + pgto_base, vfrom + pgfrom_base, copy);
		kunmap_atomic(vfrom, KM_USER1);
		kunmap_atomic(vto, KM_USER0);

	} while ((len -= copy) != 0);
	flush_dcache_page(*pgto);
}

/*
 * _copy_to_pages
 * @pages: array of pages
 * @pgbase: page vector address of destination
 * @p: pointer to source data
 * @len: length
 *
 * Copies data from an arbitrary memory location into an array of pages
 * The copy is assumed to be non-overlapping.
 */
static void
_copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len)
{
	struct page **pgto;
	char *vto;
	size_t copy;

	pgto = pages + (pgbase >> PAGE_CACHE_SHIFT);
	pgbase &= ~PAGE_CACHE_MASK;

	do {
		copy = PAGE_CACHE_SIZE - pgbase;
		if (copy > len)
			copy = len;

		vto = kmap_atomic(*pgto, KM_USER0);
		memcpy(vto + pgbase, p, copy);
		kunmap_atomic(vto, KM_USER0);

		pgbase += copy;
		if (pgbase == PAGE_CACHE_SIZE) {
			flush_dcache_page(*pgto);
			pgbase = 0;
			pgto++;
		}
		p += copy;

	} while ((len -= copy) != 0);
	flush_dcache_page(*pgto);
}

/*
 * _copy_from_pages
 * @p: pointer to destination
 * @pages: array of pages
 * @pgbase: offset of source data
 * @len: length
 *
 * Copies data into an arbitrary memory location from an array of pages
 * The copy is assumed to be non-overlapping.
 */
static void
_copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
{
	struct page **pgfrom;
	char *vfrom;
	size_t copy;

	pgfrom = pages + (pgbase >> PAGE_CACHE_SHIFT);
	pgbase &= ~PAGE_CACHE_MASK;

	do {
		copy = PAGE_CACHE_SIZE - pgbase;
		if (copy > len)
			copy = len;

		vfrom = kmap_atomic(*pgfrom, KM_USER0);
		memcpy(p, vfrom + pgbase, copy);
		kunmap_atomic(vfrom, KM_USER0);

		pgbase += copy;
		if (pgbase == PAGE_CACHE_SIZE) {
			pgbase = 0;
			pgfrom++;
		}
		p += copy;

	} while ((len -= copy) != 0);
}

/*
 * xdr_shrink_bufhead
 * @buf: xdr_buf
 * @len: bytes to remove from buf->head[0]
 *
 * Shrinks XDR buffer's header kvec buf->head[0] by 
 * 'len' bytes. The extra data is not lost, but is instead
 * moved into the inlined pages and/or the tail.
 */
static void
xdr_shrink_bufhead(struct xdr_buf *buf, size_t len)
{
	struct kvec *head, *tail;
	size_t copy, offs;
	unsigned int pglen = buf->page_len;

	tail = buf->tail;
	head = buf->head;
	BUG_ON (len > head->iov_len);

	/* Shift the tail first */
	if (tail->iov_len != 0) {
		if (tail->iov_len > len) {
			copy = tail->iov_len - len;
			memmove((char *)tail->iov_base + len,
					tail->iov_base, copy);
		}
		/* Copy from the inlined pages into the tail */
		copy = len;
		if (copy > pglen)
			copy = pglen;
		offs = len - copy;
		if (offs >= tail->iov_len)
			copy = 0;
		else if (copy > tail->iov_len - offs)
			copy = tail->iov_len - offs;
		if (copy != 0)
			_copy_from_pages((char *)tail->iov_base + offs,
					buf->pages,
					buf->page_base + pglen + offs - len,
					copy);
		/* Do we also need to copy data from the head into the tail ? */
		if (len > pglen) {
			offs = copy = len - pglen;
			if (copy > tail->iov_len)
				copy = tail->iov_len;
			memcpy(tail->iov_base,
					(char *)head->iov_base +
					head->iov_len - offs,
					copy);
		}
	}
	/* Now handle pages */
	if (pglen != 0) {
		if (pglen > len)
			_shift_data_right_pages(buf->pages,
					buf->page_base + len,
					buf->page_base,
					pglen - len);
		copy = len;
		if (len > pglen)
			copy = pglen;
		_copy_to_pages(buf->pages, buf->page_base,
				(char *)head->iov_base + head->iov_len - len,
				copy);
	}
	head->iov_len -= len;
	buf->buflen -= len;
	/* Have we truncated the message? */
	if (buf->len > buf->buflen)
		buf->len = buf->buflen;
}

/*
 * xdr_shrink_pagelen
 * @buf: xdr_buf
 * @len: bytes to remove from buf->pages
 *
 * Shrinks XDR buffer's page array buf->pages by 
 * 'len' bytes. The extra data is not lost, but is instead
 * moved into the tail.
 */
static void
xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
{
	struct kvec *tail;
	size_t copy;
	char *p;
	unsigned int pglen = buf->page_len;

	tail = buf->tail;
	BUG_ON (len > pglen);

	/* Shift the tail first */
	if (tail->iov_len != 0) {
		p = (char *)tail->iov_base + len;
		if (tail->iov_len > len) {
			copy = tail->iov_len - len;
			memmove(p, tail->iov_base, copy);
		} else
			buf->buflen -= len;
		/* Copy from the inlined pages into the tail */
		copy = len;
		if (copy > tail->iov_len)
			copy = tail->iov_len;
		_copy_from_pages((char *)tail->iov_base,
				buf->pages, buf->page_base + pglen - len,
				copy);
	}
	buf->page_len -= len;
	buf->buflen -= len;
	/* Have we truncated the message? */
	if (buf->len > buf->buflen)
		buf->len = buf->buflen;
}

void
xdr_shift_buf(struct xdr_buf *buf, size_t len)
{
	xdr_shrink_bufhead(buf, len);
}

/**
 * xdr_init_encode - Initialize a struct xdr_stream for sending data.
 * @xdr: pointer to xdr_stream struct
 * @buf: pointer to XDR buffer in which to encode data
 * @p: current pointer inside XDR buffer
 *
 * Note: at the moment the RPC client only passes the length of our
 *	 scratch buffer in the xdr_buf's header kvec. Previously this
 *	 meant we needed to call xdr_adjust_iovec() after encoding the
 *	 data. With the new scheme, the xdr_stream manages the details
 *	 of the buffer length, and takes care of adjusting the kvec
 *	 length for us.
 */
void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p)
{
	struct kvec *iov = buf->head;
	int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len;

	BUG_ON(scratch_len < 0);
	xdr->buf = buf;
	xdr->iov = iov;
	xdr->p = (uint32_t *)((char *)iov->iov_base + iov->iov_len);
	xdr->end = (uint32_t *)((char *)iov->iov_base + scratch_len);
	BUG_ON(iov->iov_len > scratch_len);

	if (p != xdr->p && p != NULL) {
		size_t len;

		BUG_ON(p < xdr->p || p > xdr->end);
		len = (char *)p - (char *)xdr->p;
		xdr->p = p;
		buf->len += len;
		iov->iov_len += len;
	}
}
EXPORT_SYMBOL(xdr_init_encode);

/**
 * xdr_reserve_space - Reserve buffer space for sending
 * @xdr: pointer to xdr_stream
 * @nbytes: number of bytes to reserve
 *
 * Checks that we have enough buffer space to encode 'nbytes' more
 * bytes of data. If so, update the total xdr_buf length, and
 * adjust the length of the current kvec.
 */
uint32_t * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
{
	uint32_t *p = xdr->p;
	uint32_t *q;

	/* align nbytes on the next 32-bit boundary */
	nbytes += 3;
	nbytes &= ~3;
	q = p + (nbytes >> 2);
	if (unlikely(q > xdr->end || q < p))
		return NULL;
	xdr->p = q;
	xdr->iov->iov_len += nbytes;
	xdr->buf->len += nbytes;
	return p;
}
EXPORT_SYMBOL(xdr_reserve_space);

/**
 * xdr_write_pages - Insert a list of pages into an XDR buffer for sending
 * @xdr: pointer to xdr_stream
 * @pages: list of pages
 * @base: offset of first byte
 * @len: length of data in bytes
 *
 */
void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base,
		 unsigned int len)
{
	struct xdr_buf *buf = xdr->buf;
	struct kvec *iov = buf->tail;
	buf->pages = pages;
	buf->page_base = base;
	buf->page_len = len;

	iov->iov_base = (char *)xdr->p;
	iov->iov_len  = 0;
	xdr->iov = iov;

	if (len & 3) {
		unsigned int pad = 4 - (len & 3);

		BUG_ON(xdr->p >= xdr->end);
		iov->iov_base = (char *)xdr->p + (len & 3);
		iov->iov_len  += pad;
		len += pad;
		*xdr->p++ = 0;
	}
	buf->buflen += len;
	buf->len += len;
}
EXPORT_SYMBOL(xdr_write_pages);

/**
 * xdr_init_decode - Initialize an xdr_stream for decoding data.
 * @xdr: pointer to xdr_stream struct
 * @buf: pointer to XDR buffer from which to decode data
 * @p: current pointer inside XDR buffer
 */
void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p)
{
	struct kvec *iov = buf->head;
	unsigned int len = iov->iov_len;

	if (len > buf->len)
		len = buf->len;
	xdr->buf = buf;
	xdr->iov = iov;
	xdr->p = p;
	xdr->end = (uint32_t *)((char *)iov->iov_base + len);
}
EXPORT_SYMBOL(xdr_init_decode);

/**
 * xdr_inline_decode - Retrieve non-page XDR data to decode
 * @xdr: pointer to xdr_stream struct
 * @nbytes: number of bytes of data to decode
 *
 * Check if the input buffer is long enough to enable us to decode
 * 'nbytes' more bytes of data starting at the current position.
 * If so return the current pointer, then update the current
 * pointer position.
 */
uint32_t * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
{
	uint32_t *p = xdr->p;
	uint32_t *q = p + XDR_QUADLEN(nbytes);

	if (unlikely(q > xdr->end || q < p))
		return NULL;
	xdr->p = q;
	return p;
}
EXPORT_SYMBOL(xdr_inline_decode);

/**
 * xdr_read_pages - Ensure page-based XDR data to decode is aligned at current pointer position
 * @xdr: pointer to xdr_stream struct
 * @len: number of bytes of page data
 *
 * Moves data beyond the current pointer position from the XDR head[] buffer
 * into the page list. Any data that lies beyond current position + "len"
 * bytes is moved into the XDR tail[]. The current pointer is then
 * repositioned at the beginning of the XDR tail.
 */
void xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
{
	struct xdr_buf *buf = xdr->buf;
	struct kvec *iov;
	ssize_t shift;
	unsigned int end;
	int padding;

	/* Realign pages to current pointer position */
	iov  = buf->head;
	shift = iov->iov_len + (char *)iov->iov_base - (char *)xdr->p;
	if (shift > 0)
		xdr_shrink_bufhead(buf, shift);

	/* Truncate page data and move it into the tail */
	if (buf->page_len > len)
		xdr_shrink_pagelen(buf, buf->page_len - len);
	padding = (XDR_QUADLEN(len) << 2) - len;
	xdr->iov = iov = buf->tail;
	/* Compute remaining message length.  */
	end = iov->iov_len;
	shift = buf->buflen - buf->len;
	if (shift < end)
		end -= shift;
	else if (shift > 0)
		end = 0;
	/*
	 * Position current pointer at beginning of tail, and
	 * set remaining message length.
	 */
	xdr->p = (uint32_t *)((char *)iov->iov_base + padding);
	xdr->end = (uint32_t *)((char *)iov->iov_base + end);
}
EXPORT_SYMBOL(xdr_read_pages);

static struct kvec empty_iov = {.iov_base = NULL, .iov_len = 0};

void
xdr_buf_from_iov(struct kvec *iov, struct xdr_buf *buf)
{
	buf->head[0] = *iov;
	buf->tail[0] = empty_iov;
	buf->page_len = 0;
	buf->buflen = buf->len = iov->iov_len;
}

/* Sets subiov to the intersection of iov with the buffer of length len
 * starting base bytes after iov.  Indicates empty intersection by setting
 * length of subiov to zero.  Decrements len by length of subiov, sets base
 * to zero (or decrements it by length of iov if subiov is empty). */
static void
iov_subsegment(struct kvec *iov, struct kvec *subiov, int *base, int *len)
{
	if (*base > iov->iov_len) {
		subiov->iov_base = NULL;
		subiov->iov_len = 0;
		*base -= iov->iov_len;
	} else {
		subiov->iov_base = iov->iov_base + *base;
		subiov->iov_len = min(*len, (int)iov->iov_len - *base);
		*base = 0;
	}
	*len -= subiov->iov_len; 
}

/* Sets subbuf to the portion of buf of length len beginning base bytes
 * from the start of buf. Returns -1 if base of length are out of bounds. */
int
xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
			int base, int len)
{
	int i;

	subbuf->buflen = subbuf->len = len;
	iov_subsegment(buf->head, subbuf->head, &base, &len);

	if (base < buf->page_len) {
		i = (base + buf->page_base) >> PAGE_CACHE_SHIFT;
		subbuf->pages = &buf->pages[i];
		subbuf->page_base = (base + buf->page_base) & ~PAGE_CACHE_MASK;
		subbuf->page_len = min((int)buf->page_len - base, len);
		len -= subbuf->page_len;
		base = 0;
	} else {
		base -= buf->page_len;
		subbuf->page_len = 0;
	}

	iov_subsegment(buf->tail, subbuf->tail, &base, &len);
	if (base || len)
		return -1;
	return 0;
}

/* obj is assumed to point to allocated memory of size at least len: */
int
read_bytes_from_xdr_buf(struct xdr_buf *buf, int base, void *obj, int len)
{
	struct xdr_buf subbuf;
	int this_len;
	int status;

	status = xdr_buf_subsegment(buf, &subbuf, base, len);
	if (status)
		goto out;
	this_len = min(len, (int)subbuf.head[0].iov_len);
	memcpy(obj, subbuf.head[0].iov_base, this_len);
	len -= this_len;
	obj += this_len;
	this_len = min(len, (int)subbuf.page_len);
	if (this_len)
		_copy_from_pages(obj, subbuf.pages, subbuf.page_base, this_len);
	len -= this_len;
	obj += this_len;
	this_len = min(len, (int)subbuf.tail[0].iov_len);
	memcpy(obj, subbuf.tail[0].iov_base, this_len);
out:
	return status;
}

static int
read_u32_from_xdr_buf(struct xdr_buf *buf, int base, u32 *obj)
{
	u32	raw;
	int	status;

	status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj));
	if (status)
		return status;
	*obj = ntohl(raw);
	return 0;
}

/* If the netobj starting offset bytes from the start of xdr_buf is contained
 * entirely in the head or the tail, set object to point to it; otherwise
 * try to find space for it at the end of the tail, copy it there, and
 * set obj to point to it. */
int
xdr_buf_read_netobj(struct xdr_buf *buf, struct xdr_netobj *obj, int offset)
{
	u32	tail_offset = buf->head[0].iov_len + buf->page_len;
	u32	obj_end_offset;

	if (read_u32_from_xdr_buf(buf, offset, &obj->len))
		goto out;
	obj_end_offset = offset + 4 + obj->len;

	if (obj_end_offset <= buf->head[0].iov_len) {
		/* The obj is contained entirely in the head: */
		obj->data = buf->head[0].iov_base + offset + 4;
	} else if (offset + 4 >= tail_offset) {
		if (obj_end_offset - tail_offset
				> buf->tail[0].iov_len)
			goto out;
		/* The obj is contained entirely in the tail: */
		obj->data = buf->tail[0].iov_base
			+ offset - tail_offset + 4;
	} else {
		/* use end of tail as storage for obj:
		 * (We don't copy to the beginning because then we'd have
		 * to worry about doing a potentially overlapping copy.
		 * This assumes the object is at most half the length of the
		 * tail.) */
		if (obj->len > buf->tail[0].iov_len)
			goto out;
		obj->data = buf->tail[0].iov_base + buf->tail[0].iov_len - 
				obj->len;
		if (read_bytes_from_xdr_buf(buf, offset + 4,
					obj->data, obj->len))
			goto out;

	}
	return 0;
out:
	return -1;
}