aboutsummaryrefslogtreecommitdiffstats
path: root/net/core/datagram.c
blob: 454ec89233331ed0676acaaac11c41000a4d0d23 (plain) (blame)
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
/*
 *	SUCS NET3:
 *
 *	Generic datagram handling routines. These are generic for all
 *	protocols. Possibly a generic IP version on top of these would
 *	make sense. Not tonight however 8-).
 *	This is used because UDP, RAW, PACKET, DDP, IPX, AX.25 and
 *	NetROM layer all have identical poll code and mostly
 *	identical recvmsg() code. So we share it here. The poll was
 *	shared before but buried in udp.c so I moved it.
 *
 *	Authors:	Alan Cox <alan@lxorguk.ukuu.org.uk>. (datagram_poll() from old
 *						     udp.c code)
 *
 *	Fixes:
 *		Alan Cox	:	NULL return from skb_peek_copy()
 *					understood
 *		Alan Cox	:	Rewrote skb_read_datagram to avoid the
 *					skb_peek_copy stuff.
 *		Alan Cox	:	Added support for SOCK_SEQPACKET.
 *					IPX can no longer use the SO_TYPE hack
 *					but AX.25 now works right, and SPX is
 *					feasible.
 *		Alan Cox	:	Fixed write poll of non IP protocol
 *					crash.
 *		Florian  La Roche:	Changed for my new skbuff handling.
 *		Darryl Miles	:	Fixed non-blocking SOCK_SEQPACKET.
 *		Linus Torvalds	:	BSD semantic fixes.
 *		Alan Cox	:	Datagram iovec handling
 *		Darryl Miles	:	Fixed non-blocking SOCK_STREAM.
 *		Alan Cox	:	POSIXisms
 *		Pete Wyckoff    :       Unconnected accept() fix.
 *
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/uaccess.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/poll.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/uio.h>

#include <net/protocol.h>
#include <linux/skbuff.h>

#include <net/checksum.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <trace/events/skb.h>
#include <net/busy_poll.h>

/*
 *	Is a socket 'connection oriented' ?
 */
static inline int connection_based(struct sock *sk)
{
	return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
}

static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync,
				  void *key)
{
	unsigned long bits = (unsigned long)key;

	/*
	 * Avoid a wakeup if event not interesting for us
	 */
	if (bits && !(bits & (POLLIN | POLLERR)))
		return 0;
	return autoremove_wake_function(wait, mode, sync, key);
}
/*
 * Wait for the last received packet to be different from skb
 */
int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
				const struct sk_buff *skb)
{
	int error;
	DEFINE_WAIT_FUNC(wait, receiver_wake_function);

	prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

	/* Socket errors? */
	error = sock_error(sk);
	if (error)
		goto out_err;

	if (sk->sk_receive_queue.prev != skb)
		goto out;

	/* Socket shut down? */
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		goto out_noerr;

	/* Sequenced packets can come disconnected.
	 * If so we report the problem
	 */
	error = -ENOTCONN;
	if (connection_based(sk) &&
	    !(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_LISTEN))
		goto out_err;

	/* handle signals */
	if (signal_pending(current))
		goto interrupted;

	error = 0;
	*timeo_p = schedule_timeout(*timeo_p);
out:
	finish_wait(sk_sleep(sk), &wait);
	return error;
interrupted:
	error = sock_intr_errno(*timeo_p);
out_err:
	*err = error;
	goto out;
out_noerr:
	*err = 0;
	error = 1;
	goto out;
}
EXPORT_SYMBOL(__skb_wait_for_more_packets);

static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
{
	struct sk_buff *nskb;

	if (skb->peeked)
		return skb;

	/* We have to unshare an skb before modifying it. */
	if (!skb_shared(skb))
		goto done;

	nskb = skb_clone(skb, GFP_ATOMIC);
	if (!nskb)
		return ERR_PTR(-ENOMEM);

	skb->prev->next = nskb;
	skb->next->prev = nskb;
	nskb->prev = skb->prev;
	nskb->next = skb->next;

	consume_skb(skb);
	skb = nskb;

done:
	skb->peeked = 1;

	return skb;
}

struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
					  struct sk_buff_head *queue,
					  unsigned int flags,
					  void (*destructor)(struct sock *sk,
							   struct sk_buff *skb),
					  int *peeked, int *off, int *err,
					  struct sk_buff **last)
{
	struct sk_buff *skb;
	int _off = *off;

	*last = queue->prev;
	skb_queue_walk(queue, skb) {
		if (flags & MSG_PEEK) {
			if (_off >= skb->len && (skb->len || _off ||
						 skb->peeked)) {
				_off -= skb->len;
				continue;
			}
			if (!skb->len) {
				skb = skb_set_peeked(skb);
				if (unlikely(IS_ERR(skb))) {
					*err = PTR_ERR(skb);
					return NULL;
				}
			}
			*peeked = 1;
			refcount_inc(&skb->users);
		} else {
			__skb_unlink(skb, queue);
			if (destructor)
				destructor(sk, skb);
		}
		*off = _off;
		return skb;
	}
	return NULL;
}

/**
 *	__skb_try_recv_datagram - Receive a datagram skbuff
 *	@sk: socket
 *	@flags: MSG_ flags
 *	@destructor: invoked under the receive lock on successful dequeue
 *	@peeked: returns non-zero if this packet has been seen before
 *	@off: an offset in bytes to peek skb from. Returns an offset
 *	      within an skb where data actually starts
 *	@err: error code returned
 *	@last: set to last peeked message to inform the wait function
 *	       what to look for when peeking
 *
 *	Get a datagram skbuff, understands the peeking, nonblocking wakeups
 *	and possible races. This replaces identical code in packet, raw and
 *	udp, as well as the IPX AX.25 and Appletalk. It also finally fixes
 *	the long standing peek and read race for datagram sockets. If you
 *	alter this routine remember it must be re-entrant.
 *
 *	This function will lock the socket if a skb is returned, so
 *	the caller needs to unlock the socket in that case (usually by
 *	calling skb_free_datagram). Returns NULL with *err set to
 *	-EAGAIN if no data was available or to some other value if an
 *	error was detected.
 *
 *	* It does not lock socket since today. This function is
 *	* free of race conditions. This measure should/can improve
 *	* significantly datagram socket latencies at high loads,
 *	* when data copying to user space takes lots of time.
 *	* (BTW I've just killed the last cli() in IP/IPv6/core/netlink/packet
 *	*  8) Great win.)
 *	*			                    --ANK (980729)
 *
 *	The order of the tests when we find no data waiting are specified
 *	quite explicitly by POSIX 1003.1g, don't change them without having
 *	the standard around please.
 */
struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
					void (*destructor)(struct sock *sk,
							   struct sk_buff *skb),
					int *peeked, int *off, int *err,
					struct sk_buff **last)
{
	struct sk_buff_head *queue = &sk->sk_receive_queue;
	struct sk_buff *skb;
	unsigned long cpu_flags;
	/*
	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
	 */
	int error = sock_error(sk);

	if (error)
		goto no_packet;

	*peeked = 0;
	do {
		/* Again only user level code calls this function, so nothing
		 * interrupt level will suddenly eat the receive_queue.
		 *
		 * Look at current nfs client by the way...
		 * However, this function was correct in any case. 8)
		 */
		spin_lock_irqsave(&queue->lock, cpu_flags);
		skb = __skb_try_recv_from_queue(sk, queue, flags, destructor,
						peeked, off, &error, last);
		spin_unlock_irqrestore(&queue->lock, cpu_flags);
		if (error)
			goto no_packet;
		if (skb)
			return skb;

		if (!sk_can_busy_loop(sk))
			break;

		sk_busy_loop(sk, flags & MSG_DONTWAIT);
	} while (!skb_queue_empty(&sk->sk_receive_queue));

	error = -EAGAIN;

no_packet:
	*err = error;
	return NULL;
}
EXPORT_SYMBOL(__skb_try_recv_datagram);

struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
				    void (*destructor)(struct sock *sk,
						       struct sk_buff *skb),
				    int *peeked, int *off, int *err)
{
	struct sk_buff *skb, *last;
	long timeo;

	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

	do {
		skb = __skb_try_recv_datagram(sk, flags, destructor, peeked,
					      off, err, &last);
		if (skb)
			return skb;

		if (*err != -EAGAIN)
			break;
	} while (timeo &&
		!__skb_wait_for_more_packets(sk, err, &timeo, last));

	return NULL;
}
EXPORT_SYMBOL(__skb_recv_datagram);

struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
				  int noblock, int *err)
{
	int peeked, off = 0;

	return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
				   NULL, &peeked, &off, err);
}
EXPORT_SYMBOL(skb_recv_datagram);

void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
{
	consume_skb(skb);
	sk_mem_reclaim_partial(sk);
}
EXPORT_SYMBOL(skb_free_datagram);

void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len)
{
	bool slow;

	if (!skb_unref(skb)) {
		sk_peek_offset_bwd(sk, len);
		return;
	}

	slow = lock_sock_fast(sk);
	sk_peek_offset_bwd(sk, len);
	skb_orphan(skb);
	sk_mem_reclaim_partial(sk);
	unlock_sock_fast(sk, slow);

	/* skb is now orphaned, can be freed outside of locked section */
	__kfree_skb(skb);
}
EXPORT_SYMBOL(__skb_free_datagram_locked);

int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
			struct sk_buff *skb, unsigned int flags,
			void (*destructor)(struct sock *sk,
					   struct sk_buff *skb))
{
	int err = 0;

	if (flags & MSG_PEEK) {
		err = -ENOENT;
		spin_lock_bh(&sk_queue->lock);
		if (skb == skb_peek(sk_queue)) {
			__skb_unlink(skb, sk_queue);
			refcount_dec(&skb->users);
			if (destructor)
				destructor(sk, skb);
			err = 0;
		}
		spin_unlock_bh(&sk_queue->lock);
	}

	atomic_inc(&sk->sk_drops);
	return err;
}
EXPORT_SYMBOL(__sk_queue_drop_skb);

/**
 *	skb_kill_datagram - Free a datagram skbuff forcibly
 *	@sk: socket
 *	@skb: datagram skbuff
 *	@flags: MSG_ flags
 *
 *	This function frees a datagram skbuff that was received by
 *	skb_recv_datagram.  The flags argument must match the one
 *	used for skb_recv_datagram.
 *
 *	If the MSG_PEEK flag is set, and the packet is still on the
 *	receive queue of the socket, it will be taken off the queue
 *	before it is freed.
 *
 *	This function currently only disables BH when acquiring the
 *	sk_receive_queue lock.  Therefore it must not be used in a
 *	context where that lock is acquired in an IRQ context.
 *
 *	It returns 0 if the packet was removed by us.
 */

int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
{
	int err = __sk_queue_drop_skb(sk, &sk->sk_receive_queue, skb, flags,
				      NULL);

	kfree_skb(skb);
	sk_mem_reclaim_partial(sk);
	return err;
}
EXPORT_SYMBOL(skb_kill_datagram);

/**
 *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
 *	@skb: buffer to copy
 *	@offset: offset in the buffer to start copying from
 *	@to: iovec iterator to copy to
 *	@len: amount of data to copy from buffer to iovec
 */
int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
			   struct iov_iter *to, int len)
{
	int start = skb_headlen(skb);
	int i, copy = start - offset, start_off = offset, n;
	struct sk_buff *frag_iter;

	trace_skb_copy_datagram_iovec(skb, len);

	/* Copy header. */
	if (copy > 0) {
		if (copy > len)
			copy = len;
		n = copy_to_iter(skb->data + offset, copy, to);
		offset += n;
		if (n != copy)
			goto short_copy;
		if ((len -= copy) == 0)
			return 0;
	}

	/* Copy paged appendix. Hmm... why does this look so complicated? */
	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		int end;
		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

		WARN_ON(start > offset + len);

		end = start + skb_frag_size(frag);
		if ((copy = end - offset) > 0) {
			if (copy > len)
				copy = len;
			n = copy_page_to_iter(skb_frag_page(frag),
					      frag->page_offset + offset -
					      start, copy, to);
			offset += n;
			if (n != copy)
				goto short_copy;
			if (!(len -= copy))
				return 0;
		}
		start = end;
	}

	skb_walk_frags(skb, frag_iter) {
		int end;

		WARN_ON(start > offset + len);

		end = start + frag_iter->len;
		if ((copy = end - offset) > 0) {
			if (copy > len)
				copy = len;
			if (skb_copy_datagram_iter(frag_iter, offset - start,
						   to, copy))
				goto fault;
			if ((len -= copy) == 0)
				return 0;
			offset += copy;
		}
		start = end;
	}
	if (!len)
		return 0;

	/* This is not really a user copy fault, but rather someone
	 * gave us a bogus length on the skb.  We should probably
	 * print a warning here as it may indicate a kernel bug.
	 */

fault:
	iov_iter_revert(to, offset - start_off);
	return -EFAULT;

short_copy:
	if (iov_iter_count(to))
		goto fault;

	return 0;
}
EXPORT_SYMBOL(skb_copy_datagram_iter);

/**
 *	skb_copy_datagram_from_iter - Copy a datagram from an iov_iter.
 *	@skb: buffer to copy
 *	@offset: offset in the buffer to start copying to
 *	@from: the copy source
 *	@len: amount of data to copy to buffer from iovec
 *
 *	Returns 0 or -EFAULT.
 */
int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
				 struct iov_iter *from,
				 int len)
{
	int start = skb_headlen(skb);
	int i, copy = start - offset;
	struct sk_buff *frag_iter;

	/* Copy header. */
	if (copy > 0) {
		if (copy > len)
			copy = len;
		if (copy_from_iter(skb->data + offset, copy, from) != copy)
			goto fault;
		if ((len -= copy) == 0)
			return 0;
		offset += copy;
	}

	/* Copy paged appendix. Hmm... why does this look so complicated? */
	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		int end;
		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

		WARN_ON(start > offset + len);

		end = start + skb_frag_size(frag);
		if ((copy = end - offset) > 0) {
			size_t copied;

			if (copy > len)
				copy = len;
			copied = copy_page_from_iter(skb_frag_page(frag),
					  frag->page_offset + offset - start,
					  copy, from);
			if (copied != copy)
				goto fault;

			if (!(len -= copy))
				return 0;
			offset += copy;
		}
		start = end;
	}

	skb_walk_frags(skb, frag_iter) {
		int end;

		WARN_ON(start > offset + len);

		end = start + frag_iter->len;
		if ((copy = end - offset) > 0) {
			if (copy > len)
				copy = len;
			if (skb_copy_datagram_from_iter(frag_iter,
							offset - start,
							from, copy))
				goto fault;
			if ((len -= copy) == 0)
				return 0;
			offset += copy;
		}
		start = end;
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}
EXPORT_SYMBOL(skb_copy_datagram_from_iter);

/**
 *	zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter
 *	@skb: buffer to copy
 *	@from: the source to copy from
 *
 *	The function will first copy up to headlen, and then pin the userspace
 *	pages and build frags through them.
 *
 *	Returns 0, -EFAULT or -EMSGSIZE.
 */
int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
{
	int len = iov_iter_count(from);
	int copy = min_t(int, skb_headlen(skb), len);
	int frag = 0;

	/* copy up to skb headlen */
	if (skb_copy_datagram_from_iter(skb, 0, from, copy))
		return -EFAULT;

	while (iov_iter_count(from)) {
		struct page *pages[MAX_SKB_FRAGS];
		size_t start;
		ssize_t copied;
		unsigned long truesize;
		int n = 0;

		if (frag == MAX_SKB_FRAGS)
			return -EMSGSIZE;

		copied = iov_iter_get_pages(from, pages, ~0U,
					    MAX_SKB_FRAGS - frag, &start);
		if (copied < 0)
			return -EFAULT;

		iov_iter_advance(from, copied);

		truesize = PAGE_ALIGN(copied + start);
		skb->data_len += copied;
		skb->len += copied;
		skb->truesize += truesize;
		refcount_add(truesize, &skb->sk->sk_wmem_alloc);
		while (copied) {
			int size = min_t(int, copied, PAGE_SIZE - start);
			skb_fill_page_desc(skb, frag++, pages[n], start, size);
			start = 0;
			copied -= size;
			n++;
		}
	}
	return 0;
}
EXPORT_SYMBOL(zerocopy_sg_from_iter);

static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
				      struct iov_iter *to, int len,
				      __wsum *csump)
{
	int start = skb_headlen(skb);
	int i, copy = start - offset, start_off = offset;
	struct sk_buff *frag_iter;
	int pos = 0;
	int n;

	/* Copy header. */
	if (copy > 0) {
		if (copy > len)
			copy = len;
		n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
		offset += n;
		if (n != copy)
			goto fault;
		if ((len -= copy) == 0)
			return 0;
		pos = copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		int end;
		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

		WARN_ON(start > offset + len);

		end = start + skb_frag_size(frag);
		if ((copy = end - offset) > 0) {
			__wsum csum2 = 0;
			struct page *page = skb_frag_page(frag);
			u8  *vaddr = kmap(page);

			if (copy > len)
				copy = len;
			n = csum_and_copy_to_iter(vaddr + frag->page_offset +
						  offset - start, copy,
						  &csum2, to);
			kunmap(page);
			offset += n;
			if (n != copy)
				goto fault;
			*csump = csum_block_add(*csump, csum2, pos);
			if (!(len -= copy))
				return 0;
			pos += copy;
		}
		start = end;
	}

	skb_walk_frags(skb, frag_iter) {
		int end;

		WARN_ON(start > offset + len);

		end = start + frag_iter->len;
		if ((copy = end - offset) > 0) {
			__wsum csum2 = 0;
			if (copy > len)
				copy = len;
			if (skb_copy_and_csum_datagram(frag_iter,
						       offset - start,
						       to, copy,
						       &csum2))
				goto fault;
			*csump = csum_block_add(*csump, csum2, pos);
			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			pos += copy;
		}
		start = end;
	}
	if (!len)
		return 0;

fault:
	iov_iter_revert(to, offset - start_off);
	return -EFAULT;
}

__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
{
	__sum16 sum;

	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
	if (likely(!sum)) {
		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
		    !skb->csum_complete_sw)
			netdev_rx_csum_fault(skb->dev);
	}
	if (!skb_shared(skb))
		skb->csum_valid = !sum;
	return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete_head);

__sum16 __skb_checksum_complete(struct sk_buff *skb)
{
	__wsum csum;
	__sum16 sum;

	csum = skb_checksum(skb, 0, skb->len, 0);

	/* skb->csum holds pseudo checksum */
	sum = csum_fold(csum_add(skb->csum, csum));
	if (likely(!sum)) {
		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
		    !skb->csum_complete_sw)
			netdev_rx_csum_fault(skb->dev);
	}

	if (!skb_shared(skb)) {
		/* Save full packet checksum */
		skb->csum = csum;
		skb->ip_summed = CHECKSUM_COMPLETE;
		skb->csum_complete_sw = 1;
		skb->csum_valid = !sum;
	}

	return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete);

/**
 *	skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec.
 *	@skb: skbuff
 *	@hlen: hardware length
 *	@msg: destination
 *
 *	Caller _must_ check that skb will fit to this iovec.
 *
 *	Returns: 0       - success.
 *		 -EINVAL - checksum failure.
 *		 -EFAULT - fault during copy.
 */
int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
				   int hlen, struct msghdr *msg)
{
	__wsum csum;
	int chunk = skb->len - hlen;

	if (!chunk)
		return 0;

	if (msg_data_left(msg) < chunk) {
		if (__skb_checksum_complete(skb))
			return -EINVAL;
		if (skb_copy_datagram_msg(skb, hlen, msg, chunk))
			goto fault;
	} else {
		csum = csum_partial(skb->data, hlen, skb->csum);
		if (skb_copy_and_csum_datagram(skb, hlen, &msg->msg_iter,
					       chunk, &csum))
			goto fault;

		if (csum_fold(csum)) {
			iov_iter_revert(&msg->msg_iter, chunk);
			return -EINVAL;
		}

		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
			netdev_rx_csum_fault(skb->dev);
	}
	return 0;
fault:
	return -EFAULT;
}
EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);

/**
 * 	datagram_poll - generic datagram poll
 *	@file: file struct
 *	@sock: socket
 *	@wait: poll table
 *
 *	Datagram poll: Again totally generic. This also handles
 *	sequenced packet sockets providing the socket receive queue
 *	is only ever holding data ready to receive.
 *
 *	Note: when you _don't_ use this routine for this protocol,
 *	and you use a different write policy from sock_writeable()
 *	then please supply your own write_space callback.
 */
unsigned int datagram_poll(struct file *file, struct socket *sock,
			   poll_table *wait)
{
	struct sock *sk = sock->sk;
	unsigned int mask;

	sock_poll_wait(file, sk_sleep(sk), wait);
	mask = 0;

	/* exceptional events? */
	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
		mask |= POLLERR |
			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);

	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= POLLRDHUP | POLLIN | POLLRDNORM;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		mask |= POLLHUP;

	/* readable? */
	if (!skb_queue_empty(&sk->sk_receive_queue))
		mask |= POLLIN | POLLRDNORM;

	/* Connection-based need to check for termination and startup */
	if (connection_based(sk)) {
		if (sk->sk_state == TCP_CLOSE)
			mask |= POLLHUP;
		/* connection hasn't started yet? */
		if (sk->sk_state == TCP_SYN_SENT)
			return mask;
	}

	/* writable? */
	if (sock_writeable(sk))
		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
	else
		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);

	return mask;
}
EXPORT_SYMBOL(datagram_poll);