summaryrefslogtreecommitdiff
path: root/net/ipv6/ip6_offload.c
blob: 5c045691c30203d3f8d2d12957e283bc01cae259 (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
/*
 *	IPV6 GSO/GRO offload support
 *	Linux INET6 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.
 */

#include <linux/kernel.h>
#include <linux/socket.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/printk.h>

#include <net/protocol.h>
#include <net/ipv6.h>
#include <net/inet_common.h>

#include "ip6_offload.h"

/* All GRO functions are always builtin, except UDP over ipv6, which lays in
 * ipv6 module, as it depends on UDPv6 lookup function, so we need special care
 * when ipv6 is built as a module
 */
#if IS_BUILTIN(CONFIG_IPV6)
#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)
#else
#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)
#endif

#define indirect_call_gro_receive_l4(f2, f1, cb, head, skb)	\
({								\
	unlikely(gro_recursion_inc_test(skb)) ?			\
		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\
		INDIRECT_CALL_L4(cb, f2, f1, head, skb);	\
})

static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
{
	const struct net_offload *ops = NULL;

	for (;;) {
		struct ipv6_opt_hdr *opth;
		int len;

		if (proto != NEXTHDR_HOP) {
			ops = rcu_dereference(inet6_offloads[proto]);

			if (unlikely(!ops))
				break;

			if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
				break;
		}

		if (unlikely(!pskb_may_pull(skb, 8)))
			break;

		opth = (void *)skb->data;
		len = ipv6_optlen(opth);

		if (unlikely(!pskb_may_pull(skb, len)))
			break;

		opth = (void *)skb->data;
		proto = opth->nexthdr;
		__skb_pull(skb, len);
	}

	return proto;
}

static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
	netdev_features_t features)
{
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	struct ipv6hdr *ipv6h;
	const struct net_offload *ops;
	int proto;
	struct frag_hdr *fptr;
	unsigned int payload_len;
	u8 *prevhdr;
	int offset = 0;
	bool encap, udpfrag;
	int nhoff;
	bool gso_partial;

	skb_reset_network_header(skb);
	nhoff = skb_network_header(skb) - skb_mac_header(skb);
	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
		goto out;

	encap = SKB_GSO_CB(skb)->encap_level > 0;
	if (encap)
		features &= skb->dev->hw_enc_features;
	SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);

	ipv6h = ipv6_hdr(skb);
	__skb_pull(skb, sizeof(*ipv6h));
	segs = ERR_PTR(-EPROTONOSUPPORT);

	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);

	if (skb->encapsulation &&
	    skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6))
		udpfrag = proto == IPPROTO_UDP && encap &&
			  (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
	else
		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation &&
			  (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);

	ops = rcu_dereference(inet6_offloads[proto]);
	if (likely(ops && ops->callbacks.gso_segment)) {
		skb_reset_transport_header(skb);
		segs = ops->callbacks.gso_segment(skb, features);
	}

	if (IS_ERR_OR_NULL(segs))
		goto out;

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

	for (skb = segs; skb; skb = skb->next) {
		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
		if (gso_partial && skb_is_gso(skb))
			payload_len = skb_shinfo(skb)->gso_size +
				      SKB_GSO_CB(skb)->data_offset +
				      skb->head - (unsigned char *)(ipv6h + 1);
		else
			payload_len = skb->len - nhoff - sizeof(*ipv6h);
		ipv6h->payload_len = htons(payload_len);
		skb->network_header = (u8 *)ipv6h - skb->head;
		skb_reset_mac_len(skb);

		if (udpfrag) {
			int err = ip6_find_1stfragopt(skb, &prevhdr);
			if (err < 0) {
				kfree_skb_list(segs);
				return ERR_PTR(err);
			}
			fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
			fptr->frag_off = htons(offset);
			if (skb->next)
				fptr->frag_off |= htons(IP6_MF);
			offset += (ntohs(ipv6h->payload_len) -
				   sizeof(struct frag_hdr));
		}
		if (encap)
			skb_reset_inner_headers(skb);
	}

out:
	return segs;
}

/* Return the total length of all the extension hdrs, following the same
 * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs.
 */
static int ipv6_exthdrs_len(struct ipv6hdr *iph,
			    const struct net_offload **opps)
{
	struct ipv6_opt_hdr *opth = (void *)iph;
	int len = 0, proto, optlen = sizeof(*iph);

	proto = iph->nexthdr;
	for (;;) {
		if (proto != NEXTHDR_HOP) {
			*opps = rcu_dereference(inet6_offloads[proto]);
			if (unlikely(!(*opps)))
				break;
			if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
				break;
		}
		opth = (void *)opth + optlen;
		optlen = ipv6_optlen(opth);
		len += optlen;
		proto = opth->nexthdr;
	}
	return len;
}

INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *,
							   struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *,
							   struct sk_buff *));
INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
							 struct sk_buff *skb)
{
	const struct net_offload *ops;
	struct sk_buff *pp = NULL;
	struct sk_buff *p;
	struct ipv6hdr *iph;
	unsigned int nlen;
	unsigned int hlen;
	unsigned int off;
	u16 flush = 1;
	int proto;

	off = skb_gro_offset(skb);
	hlen = off + sizeof(*iph);
	iph = skb_gro_header_fast(skb, off);
	if (skb_gro_header_hard(skb, hlen)) {
		iph = skb_gro_header_slow(skb, hlen, off);
		if (unlikely(!iph))
			goto out;
	}

	skb_set_network_header(skb, off);
	skb_gro_pull(skb, sizeof(*iph));
	skb_set_transport_header(skb, skb_gro_offset(skb));

	flush += ntohs(iph->payload_len) != skb_gro_len(skb);

	rcu_read_lock();
	proto = iph->nexthdr;
	ops = rcu_dereference(inet6_offloads[proto]);
	if (!ops || !ops->callbacks.gro_receive) {
		__pskb_pull(skb, skb_gro_offset(skb));
		skb_gro_frag0_invalidate(skb);
		proto = ipv6_gso_pull_exthdrs(skb, proto);
		skb_gro_pull(skb, -skb_transport_offset(skb));
		skb_reset_transport_header(skb);
		__skb_push(skb, skb_gro_offset(skb));

		ops = rcu_dereference(inet6_offloads[proto]);
		if (!ops || !ops->callbacks.gro_receive)
			goto out_unlock;

		iph = ipv6_hdr(skb);
	}

	NAPI_GRO_CB(skb)->proto = proto;

	flush--;
	nlen = skb_network_header_len(skb);

	list_for_each_entry(p, head, list) {
		const struct ipv6hdr *iph2;
		__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */

		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		iph2 = (struct ipv6hdr *)(p->data + off);
		first_word = *(__be32 *)iph ^ *(__be32 *)iph2;

		/* All fields must match except length and Traffic Class.
		 * XXX skbs on the gro_list have all been parsed and pulled
		 * already so we don't need to compare nlen
		 * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
		 * memcmp() alone below is sufficient, right?
		 */
		 if ((first_word & htonl(0xF00FFFFF)) ||
		    !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
		    !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
		    *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) {
not_same_flow:
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}
		if (unlikely(nlen > sizeof(struct ipv6hdr))) {
			if (memcmp(iph + 1, iph2 + 1,
				   nlen - sizeof(struct ipv6hdr)))
				goto not_same_flow;
		}
		/* flush if Traffic Class fields are different */
		NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
		NAPI_GRO_CB(p)->flush |= flush;

		/* If the previous IP ID value was based on an atomic
		 * datagram we can overwrite the value and ignore it.
		 */
		if (NAPI_GRO_CB(skb)->is_atomic)
			NAPI_GRO_CB(p)->flush_id = 0;
	}

	NAPI_GRO_CB(skb)->is_atomic = true;
	NAPI_GRO_CB(skb)->flush |= flush;

	skb_gro_postpull_rcsum(skb, iph, nlen);

	pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive,
					 ops->callbacks.gro_receive, head, skb);

out_unlock:
	rcu_read_unlock();

out:
	skb_gro_flush_final(skb, pp, flush);

	return pp;
}

static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head,
					      struct sk_buff *skb)
{
	/* Common GRO receive for SIT and IP6IP6 */

	if (NAPI_GRO_CB(skb)->encap_mark) {
		NAPI_GRO_CB(skb)->flush = 1;
		return NULL;
	}

	NAPI_GRO_CB(skb)->encap_mark = 1;

	return ipv6_gro_receive(head, skb);
}

static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
					  struct sk_buff *skb)
{
	/* Common GRO receive for SIT and IP6IP6 */

	if (NAPI_GRO_CB(skb)->encap_mark) {
		NAPI_GRO_CB(skb)->flush = 1;
		return NULL;
	}

	NAPI_GRO_CB(skb)->encap_mark = 1;

	return inet_gro_receive(head, skb);
}

INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *, int));
INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int));
INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
{
	const struct net_offload *ops;
	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
	int err = -ENOSYS;

	if (skb->encapsulation) {
		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
		skb_set_inner_network_header(skb, nhoff);
	}

	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));

	rcu_read_lock();

	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
		goto out_unlock;

	err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete,
			       udp6_gro_complete, skb, nhoff);

out_unlock:
	rcu_read_unlock();

	return err;
}

static int sit_gro_complete(struct sk_buff *skb, int nhoff)
{
	skb->encapsulation = 1;
	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
	return ipv6_gro_complete(skb, nhoff);
}

static int ip6ip6_gro_complete(struct sk_buff *skb, int nhoff)
{
	skb->encapsulation = 1;
	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
	return ipv6_gro_complete(skb, nhoff);
}

static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff)
{
	skb->encapsulation = 1;
	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
	return inet_gro_complete(skb, nhoff);
}

static struct packet_offload ipv6_packet_offload __read_mostly = {
	.type = cpu_to_be16(ETH_P_IPV6),
	.callbacks = {
		.gso_segment = ipv6_gso_segment,
		.gro_receive = ipv6_gro_receive,
		.gro_complete = ipv6_gro_complete,
	},
};

static const struct net_offload sit_offload = {
	.callbacks = {
		.gso_segment	= ipv6_gso_segment,
		.gro_receive    = sit_ip6ip6_gro_receive,
		.gro_complete   = sit_gro_complete,
	},
};

static const struct net_offload ip4ip6_offload = {
	.callbacks = {
		.gso_segment	= inet_gso_segment,
		.gro_receive    = ip4ip6_gro_receive,
		.gro_complete   = ip4ip6_gro_complete,
	},
};

static const struct net_offload ip6ip6_offload = {
	.callbacks = {
		.gso_segment	= ipv6_gso_segment,
		.gro_receive    = sit_ip6ip6_gro_receive,
		.gro_complete   = ip6ip6_gro_complete,
	},
};
static int __init ipv6_offload_init(void)
{

	if (tcpv6_offload_init() < 0)
		pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
	if (ipv6_exthdrs_offload_init() < 0)
		pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__);

	dev_add_offload(&ipv6_packet_offload);

	inet_add_offload(&sit_offload, IPPROTO_IPV6);
	inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6);
	inet6_add_offload(&ip4ip6_offload, IPPROTO_IPIP);

	return 0;
}

fs_initcall(ipv6_offload_init);