aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/udp_offload.c
blob: 64f9715173ac8bf3a8d641ae40ef95f67aa7a7a0 (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
/*
 *	IPV4 GSO/GRO offload support
 *	Linux INET implementation
 *
 *	This program is free software; you can redistribute it and/or
 *	modify it under the terms of the GNU General Public License
 *	as published by the Free Software Foundation; either version
 *	2 of the License, or (at your option) any later version.
 *
 *	UDPv4 GSO support
 */

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

static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
	netdev_features_t features,
	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
					     netdev_features_t features),
	__be16 new_protocol, bool is_ipv6)
{
	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
	bool remcsum, need_csum, offload_csum, gso_partial;
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	struct udphdr *uh = udp_hdr(skb);
	u16 mac_offset = skb->mac_header;
	__be16 protocol = skb->protocol;
	u16 mac_len = skb->mac_len;
	int udp_offset, outer_hlen;
	__wsum partial;
	bool need_ipsec;

	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
		goto out;

	/* Adjust partial header checksum to negate old length.
	 * We cannot rely on the value contained in uh->len as it is
	 * possible that the actual value exceeds the boundaries of the
	 * 16 bit length field due to the header being added outside of an
	 * IP or IPv6 frame that was already limited to 64K - 1.
	 */
	if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)
		partial = (__force __wsum)uh->len;
	else
		partial = (__force __wsum)htonl(skb->len);
	partial = csum_sub(csum_unfold(uh->check), partial);

	/* setup inner skb. */
	skb->encapsulation = 0;
	SKB_GSO_CB(skb)->encap_level = 0;
	__skb_pull(skb, tnl_hlen);
	skb_reset_mac_header(skb);
	skb_set_network_header(skb, skb_inner_network_offset(skb));
	skb->mac_len = skb_inner_network_offset(skb);
	skb->protocol = new_protocol;

	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
	skb->encap_hdr_csum = need_csum;

	remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
	skb->remcsum_offload = remcsum;

	need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
	/* Try to offload checksum if possible */
	offload_csum = !!(need_csum &&
			  !need_ipsec &&
			  (skb->dev->features &
			   (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
				      (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));

	features &= skb->dev->hw_enc_features;

	/* The only checksum offload we care about from here on out is the
	 * outer one so strip the existing checksum feature flags and
	 * instead set the flag based on our outer checksum offload value.
	 */
	if (remcsum) {
		features &= ~NETIF_F_CSUM_MASK;
		if (!need_csum || offload_csum)
			features |= NETIF_F_HW_CSUM;
	}

	/* segment inner packet. */
	segs = gso_inner_segment(skb, features);
	if (IS_ERR_OR_NULL(segs)) {
		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
				     mac_len);
		goto out;
	}

	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);

	outer_hlen = skb_tnl_header_len(skb);
	udp_offset = outer_hlen - tnl_hlen;
	skb = segs;
	do {
		unsigned int len;

		if (remcsum)
			skb->ip_summed = CHECKSUM_NONE;

		/* Set up inner headers if we are offloading inner checksum */
		if (skb->ip_summed == CHECKSUM_PARTIAL) {
			skb_reset_inner_headers(skb);
			skb->encapsulation = 1;
		}

		skb->mac_len = mac_len;
		skb->protocol = protocol;

		__skb_push(skb, outer_hlen);
		skb_reset_mac_header(skb);
		skb_set_network_header(skb, mac_len);
		skb_set_transport_header(skb, udp_offset);
		len = skb->len - udp_offset;
		uh = udp_hdr(skb);

		/* If we are only performing partial GSO the inner header
		 * will be using a length value equal to only one MSS sized
		 * segment instead of the entire frame.
		 */
		if (gso_partial && skb_is_gso(skb)) {
			uh->len = htons(skb_shinfo(skb)->gso_size +
					SKB_GSO_CB(skb)->data_offset +
					skb->head - (unsigned char *)uh);
		} else {
			uh->len = htons(len);
		}

		if (!need_csum)
			continue;

		uh->check = ~csum_fold(csum_add(partial,
				       (__force __wsum)htonl(len)));

		if (skb->encapsulation || !offload_csum) {
			uh->check = gso_make_checksum(skb, ~uh->check);
			if (uh->check == 0)
				uh->check = CSUM_MANGLED_0;
		} else {
			skb->ip_summed = CHECKSUM_PARTIAL;
			skb->csum_start = skb_transport_header(skb) - skb->head;
			skb->csum_offset = offsetof(struct udphdr, check);
		}
	} while ((skb = skb->next));
out:
	return segs;
}

struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
				       netdev_features_t features,
				       bool is_ipv6)
{
	__be16 protocol = skb->protocol;
	const struct net_offload **offloads;
	const struct net_offload *ops;
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
					     netdev_features_t features);

	rcu_read_lock();

	switch (skb->inner_protocol_type) {
	case ENCAP_TYPE_ETHER:
		protocol = skb->inner_protocol;
		gso_inner_segment = skb_mac_gso_segment;
		break;
	case ENCAP_TYPE_IPPROTO:
		offloads = is_ipv6 ? inet6_offloads : inet_offloads;
		ops = rcu_dereference(offloads[skb->inner_ipproto]);
		if (!ops || !ops->callbacks.gso_segment)
			goto out_unlock;
		gso_inner_segment = ops->callbacks.gso_segment;
		break;
	default:
		goto out_unlock;
	}

	segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment,
					protocol, is_ipv6);

out_unlock:
	rcu_read_unlock();

	return segs;
}
EXPORT_SYMBOL(skb_udp_tunnel_segment);

struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
				  netdev_features_t features)
{
	struct sock *sk = gso_skb->sk;
	unsigned int sum_truesize = 0;
	struct sk_buff *segs, *seg;
	struct udphdr *uh;
	unsigned int mss;
	bool copy_dtor;
	__sum16 check;
	__be16 newlen;

	mss = skb_shinfo(gso_skb)->gso_size;
	if (gso_skb->len <= sizeof(*uh) + mss)
		return ERR_PTR(-EINVAL);

	skb_pull(gso_skb, sizeof(*uh));

	/* clear destructor to avoid skb_segment assigning it to tail */
	copy_dtor = gso_skb->destructor == sock_wfree;
	if (copy_dtor)
		gso_skb->destructor = NULL;

	segs = skb_segment(gso_skb, features);
	if (unlikely(IS_ERR_OR_NULL(segs))) {
		if (copy_dtor)
			gso_skb->destructor = sock_wfree;
		return segs;
	}

	/* GSO partial and frag_list segmentation only requires splitting
	 * the frame into an MSS multiple and possibly a remainder, both
	 * cases return a GSO skb. So update the mss now.
	 */
	if (skb_is_gso(segs))
		mss *= skb_shinfo(segs)->gso_segs;

	seg = segs;
	uh = udp_hdr(seg);

	/* compute checksum adjustment based on old length versus new */
	newlen = htons(sizeof(*uh) + mss);
	check = csum16_add(csum16_sub(uh->check, uh->len), newlen);

	for (;;) {
		if (copy_dtor) {
			seg->destructor = sock_wfree;
			seg->sk = sk;
			sum_truesize += seg->truesize;
		}

		if (!seg->next)
			break;

		uh->len = newlen;
		uh->check = check;

		if (seg->ip_summed == CHECKSUM_PARTIAL)
			gso_reset_checksum(seg, ~check);
		else
			uh->check = gso_make_checksum(seg, ~check) ? :
				    CSUM_MANGLED_0;

		seg = seg->next;
		uh = udp_hdr(seg);
	}

	/* last packet can be partial gso_size, account for that in checksum */
	newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) +
		       seg->data_len);
	check = csum16_add(csum16_sub(uh->check, uh->len), newlen);

	uh->len = newlen;
	uh->check = check;

	if (seg->ip_summed == CHECKSUM_PARTIAL)
		gso_reset_checksum(seg, ~check);
	else
		uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0;

	/* update refcount for the packet */
	if (copy_dtor) {
		int delta = sum_truesize - gso_skb->truesize;

		/* In some pathological cases, delta can be negative.
		 * We need to either use refcount_add() or refcount_sub_and_test()
		 */
		if (likely(delta >= 0))
			refcount_add(delta, &sk->sk_wmem_alloc);
		else
			WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
	}
	return segs;
}
EXPORT_SYMBOL_GPL(__udp_gso_segment);

static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
					 netdev_features_t features)
{
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	unsigned int mss;
	__wsum csum;
	struct udphdr *uh;
	struct iphdr *iph;

	if (skb->encapsulation &&
	    (skb_shinfo(skb)->gso_type &
	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
		segs = skb_udp_tunnel_segment(skb, features, false);
		goto out;
	}

	if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4)))
		goto out;

	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
		goto out;

	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
		return __udp_gso_segment(skb, features);

	mss = skb_shinfo(skb)->gso_size;
	if (unlikely(skb->len <= mss))
		goto out;

	/* Do software UFO. Complete and fill in the UDP checksum as
	 * HW cannot do checksum of UDP packets sent as multiple
	 * IP fragments.
	 */

	uh = udp_hdr(skb);
	iph = ip_hdr(skb);

	uh->check = 0;
	csum = skb_checksum(skb, 0, skb->len, 0);
	uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
	if (uh->check == 0)
		uh->check = CSUM_MANGLED_0;

	skb->ip_summed = CHECKSUM_UNNECESSARY;

	/* If there is no outer header we can fake a checksum offload
	 * due to the fact that we have already done the checksum in
	 * software prior to segmenting the frame.
	 */
	if (!skb->encap_hdr_csum)
		features |= NETIF_F_HW_CSUM;

	/* Fragment the skb. IP headers of the fragments are updated in
	 * inet_gso_segment()
	 */
	segs = skb_segment(skb, features);
out:
	return segs;
}

#define UDP_GRO_CNT_MAX 64
static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
					       struct sk_buff *skb)
{
	struct udphdr *uh = udp_hdr(skb);
	struct sk_buff *pp = NULL;
	struct udphdr *uh2;
	struct sk_buff *p;

	/* requires non zero csum, for symmetry with GSO */
	if (!uh->check) {
		NAPI_GRO_CB(skb)->flush = 1;
		return NULL;
	}

	/* pull encapsulating udp header */
	skb_gro_pull(skb, sizeof(struct udphdr));
	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));

	list_for_each_entry(p, head, list) {
		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		uh2 = udp_hdr(p);

		/* Match ports only, as csum is always non zero */
		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}

		/* Terminate the flow on len mismatch or if it grow "too much".
		 * Under small packet flood GRO count could elsewhere grow a lot
		 * leading to execessive truesize values
		 */
		if (!skb_gro_receive(p, skb) &&
		    NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
			pp = p;
		else if (uh->len != uh2->len)
			pp = p;

		return pp;
	}

	/* mismatch, but we never need to flush */
	return NULL;
}

INDIRECT_CALLABLE_DECLARE(struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
						   __be16 sport, __be16 dport));
struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
				struct udphdr *uh, udp_lookup_t lookup)
{
	struct sk_buff *pp = NULL;
	struct sk_buff *p;
	struct udphdr *uh2;
	unsigned int off = skb_gro_offset(skb);
	int flush = 1;
	struct sock *sk;

	rcu_read_lock();
	sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
				udp4_lib_lookup_skb, skb, uh->source, uh->dest);
	if (!sk)
		goto out_unlock;

	if (udp_sk(sk)->gro_enabled) {
		pp = call_gro_receive(udp_gro_receive_segment, head, skb);
		rcu_read_unlock();
		return pp;
	}

	if (NAPI_GRO_CB(skb)->encap_mark ||
	    (skb->ip_summed != CHECKSUM_PARTIAL &&
	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
	     !NAPI_GRO_CB(skb)->csum_valid) ||
	    !udp_sk(sk)->gro_receive)
		goto out_unlock;

	/* mark that this skb passed once through the tunnel gro layer */
	NAPI_GRO_CB(skb)->encap_mark = 1;

	flush = 0;

	list_for_each_entry(p, head, list) {
		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		uh2 = (struct udphdr   *)(p->data + off);

		/* Match ports and either checksums are either both zero
		 * or nonzero.
		 */
		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
		    (!uh->check ^ !uh2->check)) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}
	}

	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
	pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);

out_unlock:
	rcu_read_unlock();
	skb_gro_flush_final(skb, pp, flush);
	return pp;
}
EXPORT_SYMBOL(udp_gro_receive);

INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
{
	struct udphdr *uh = udp_gro_udphdr(skb);

	if (unlikely(!uh) || !static_branch_unlikely(&udp_encap_needed_key))
		goto flush;

	/* Don't bother verifying checksum if we're going to flush anyway. */
	if (NAPI_GRO_CB(skb)->flush)
		goto skip;

	if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
						 inet_gro_compute_pseudo))
		goto flush;
	else if (uh->check)
		skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
					     inet_gro_compute_pseudo);
skip:
	NAPI_GRO_CB(skb)->is_ipv6 = 0;
	return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb);

flush:
	NAPI_GRO_CB(skb)->flush = 1;
	return NULL;
}

static int udp_gro_complete_segment(struct sk_buff *skb)
{
	struct udphdr *uh = udp_hdr(skb);

	skb->csum_start = (unsigned char *)uh - skb->head;
	skb->csum_offset = offsetof(struct udphdr, check);
	skb->ip_summed = CHECKSUM_PARTIAL;

	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
	skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
	return 0;
}

int udp_gro_complete(struct sk_buff *skb, int nhoff,
		     udp_lookup_t lookup)
{
	__be16 newlen = htons(skb->len - nhoff);
	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
	int err = -ENOSYS;
	struct sock *sk;

	uh->len = newlen;

	rcu_read_lock();
	sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
				udp4_lib_lookup_skb, skb, uh->source, uh->dest);
	if (sk && udp_sk(sk)->gro_enabled) {
		err = udp_gro_complete_segment(skb);
	} else if (sk && udp_sk(sk)->gro_complete) {
		skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
					: SKB_GSO_UDP_TUNNEL;

		/* Set encapsulation before calling into inner gro_complete()
		 * functions to make them set up the inner offsets.
		 */
		skb->encapsulation = 1;
		err = udp_sk(sk)->gro_complete(sk, skb,
				nhoff + sizeof(struct udphdr));
	}
	rcu_read_unlock();

	if (skb->remcsum_offload)
		skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;

	return err;
}
EXPORT_SYMBOL(udp_gro_complete);

INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);

	if (uh->check)
		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
					  iph->daddr, 0);

	return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
}

static const struct net_offload udpv4_offload = {
	.callbacks = {
		.gso_segment = udp4_ufo_fragment,
		.gro_receive  =	udp4_gro_receive,
		.gro_complete =	udp4_gro_complete,
	},
};

int __init udpv4_offload_init(void)
{
	return inet_add_offload(&udpv4_offload, IPPROTO_UDP);
}