summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
blob: 37bce7a7c3944663297d56c3b0a72f7c01f427b1 (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
// SPDX-License-Identifier: GPL-2.0

/* In-place tunneling */

#include <stdbool.h>
#include <string.h>

#include <linux/stddef.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/mpls.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/pkt_cls.h>
#include <linux/types.h>

#include <bpf/bpf_endian.h>
#include <bpf/bpf_helpers.h>

static const int cfg_port = 8000;

static const int cfg_udp_src = 20000;

#define	UDP_PORT		5555
#define	MPLS_OVER_UDP_PORT	6635
#define	ETH_OVER_UDP_PORT	7777

/* MPLS label 1000 with S bit (last label) set and ttl of 255. */
static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
						     MPLS_LS_S_MASK | 0xff);

struct gre_hdr {
	__be16 flags;
	__be16 protocol;
} __attribute__((packed));

union l4hdr {
	struct udphdr udp;
	struct gre_hdr gre;
};

struct v4hdr {
	struct iphdr ip;
	union l4hdr l4hdr;
	__u8 pad[16];			/* enough space for L2 header */
} __attribute__((packed));

struct v6hdr {
	struct ipv6hdr ip;
	union l4hdr l4hdr;
	__u8 pad[16];			/* enough space for L2 header */
} __attribute__((packed));

static __always_inline void set_ipv4_csum(struct iphdr *iph)
{
	__u16 *iph16 = (__u16 *)iph;
	__u32 csum;
	int i;

	iph->check = 0;

#pragma clang loop unroll(full)
	for (i = 0, csum = 0; i < sizeof(*iph) >> 1; i++)
		csum += *iph16++;

	iph->check = ~((csum & 0xffff) + (csum >> 16));
}

static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
				      __u16 l2_proto)
{
	__u16 udp_dst = UDP_PORT;
	struct iphdr iph_inner;
	struct v4hdr h_outer;
	struct tcphdr tcph;
	int olen, l2_len;
	int tcp_off;
	__u64 flags;

	/* Most tests encapsulate a packet into a tunnel with the same
	 * network protocol, and derive the outer header fields from
	 * the inner header.
	 *
	 * The 6in4 case tests different inner and outer protocols. As
	 * the inner is ipv6, but the outer expects an ipv4 header as
	 * input, manually build a struct iphdr based on the ipv6hdr.
	 */
	if (encap_proto == IPPROTO_IPV6) {
		const __u32 saddr = (192 << 24) | (168 << 16) | (1 << 8) | 1;
		const __u32 daddr = (192 << 24) | (168 << 16) | (1 << 8) | 2;
		struct ipv6hdr iph6_inner;

		/* Read the IPv6 header */
		if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph6_inner,
				       sizeof(iph6_inner)) < 0)
			return TC_ACT_OK;

		/* Derive the IPv4 header fields from the IPv6 header */
		memset(&iph_inner, 0, sizeof(iph_inner));
		iph_inner.version = 4;
		iph_inner.ihl = 5;
		iph_inner.tot_len = bpf_htons(sizeof(iph6_inner) +
				    bpf_ntohs(iph6_inner.payload_len));
		iph_inner.ttl = iph6_inner.hop_limit - 1;
		iph_inner.protocol = iph6_inner.nexthdr;
		iph_inner.saddr = __bpf_constant_htonl(saddr);
		iph_inner.daddr = __bpf_constant_htonl(daddr);

		tcp_off = sizeof(iph6_inner);
	} else {
		if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
				       sizeof(iph_inner)) < 0)
			return TC_ACT_OK;

		tcp_off = sizeof(iph_inner);
	}

	/* filter only packets we want */
	if (iph_inner.ihl != 5 || iph_inner.protocol != IPPROTO_TCP)
		return TC_ACT_OK;

	if (bpf_skb_load_bytes(skb, ETH_HLEN + tcp_off,
			       &tcph, sizeof(tcph)) < 0)
		return TC_ACT_OK;

	if (tcph.dest != __bpf_constant_htons(cfg_port))
		return TC_ACT_OK;

	olen = sizeof(h_outer.ip);
	l2_len = 0;

	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV4;

	switch (l2_proto) {
	case ETH_P_MPLS_UC:
		l2_len = sizeof(mpls_label);
		udp_dst = MPLS_OVER_UDP_PORT;
		break;
	case ETH_P_TEB:
		l2_len = ETH_HLEN;
		udp_dst = ETH_OVER_UDP_PORT;
		break;
	}
	flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);

	switch (encap_proto) {
	case IPPROTO_GRE:
		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE;
		olen += sizeof(h_outer.l4hdr.gre);
		h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto);
		h_outer.l4hdr.gre.flags = 0;
		break;
	case IPPROTO_UDP:
		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP;
		olen += sizeof(h_outer.l4hdr.udp);
		h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
		h_outer.l4hdr.udp.dest = bpf_htons(udp_dst);
		h_outer.l4hdr.udp.check = 0;
		h_outer.l4hdr.udp.len = bpf_htons(bpf_ntohs(iph_inner.tot_len) +
						  sizeof(h_outer.l4hdr.udp) +
						  l2_len);
		break;
	case IPPROTO_IPIP:
	case IPPROTO_IPV6:
		break;
	default:
		return TC_ACT_OK;
	}

	/* add L2 encap (if specified) */
	switch (l2_proto) {
	case ETH_P_MPLS_UC:
		*((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
		break;
	case ETH_P_TEB:
		if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
				       ETH_HLEN))
			return TC_ACT_SHOT;
		break;
	}
	olen += l2_len;

	/* add room between mac and network header */
	if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
		return TC_ACT_SHOT;

	/* prepare new outer network header */
	h_outer.ip = iph_inner;
	h_outer.ip.tot_len = bpf_htons(olen +
				       bpf_ntohs(h_outer.ip.tot_len));
	h_outer.ip.protocol = encap_proto;

	set_ipv4_csum((void *)&h_outer.ip);

	/* store new outer network header */
	if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
				BPF_F_INVALIDATE_HASH) < 0)
		return TC_ACT_SHOT;

	/* if changing outer proto type, update eth->h_proto */
	if (encap_proto == IPPROTO_IPV6) {
		struct ethhdr eth;

		if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)) < 0)
			return TC_ACT_SHOT;
		eth.h_proto = bpf_htons(ETH_P_IP);
		if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0) < 0)
			return TC_ACT_SHOT;
	}

	return TC_ACT_OK;
}

static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
				      __u16 l2_proto)
{
	__u16 udp_dst = UDP_PORT;
	struct ipv6hdr iph_inner;
	struct v6hdr h_outer;
	struct tcphdr tcph;
	int olen, l2_len;
	__u16 tot_len;
	__u64 flags;

	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
			       sizeof(iph_inner)) < 0)
		return TC_ACT_OK;

	/* filter only packets we want */
	if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(iph_inner),
			       &tcph, sizeof(tcph)) < 0)
		return TC_ACT_OK;

	if (tcph.dest != __bpf_constant_htons(cfg_port))
		return TC_ACT_OK;

	olen = sizeof(h_outer.ip);
	l2_len = 0;

	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;

	switch (l2_proto) {
	case ETH_P_MPLS_UC:
		l2_len = sizeof(mpls_label);
		udp_dst = MPLS_OVER_UDP_PORT;
		break;
	case ETH_P_TEB:
		l2_len = ETH_HLEN;
		udp_dst = ETH_OVER_UDP_PORT;
		break;
	}
	flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);

	switch (encap_proto) {
	case IPPROTO_GRE:
		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE;
		olen += sizeof(h_outer.l4hdr.gre);
		h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto);
		h_outer.l4hdr.gre.flags = 0;
		break;
	case IPPROTO_UDP:
		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP;
		olen += sizeof(h_outer.l4hdr.udp);
		h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
		h_outer.l4hdr.udp.dest = bpf_htons(udp_dst);
		tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) +
			  sizeof(h_outer.l4hdr.udp);
		h_outer.l4hdr.udp.check = 0;
		h_outer.l4hdr.udp.len = bpf_htons(tot_len);
		break;
	case IPPROTO_IPV6:
		break;
	default:
		return TC_ACT_OK;
	}

	/* add L2 encap (if specified) */
	switch (l2_proto) {
	case ETH_P_MPLS_UC:
		*((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
		break;
	case ETH_P_TEB:
		if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
				       ETH_HLEN))
			return TC_ACT_SHOT;
		break;
	}
	olen += l2_len;

	/* add room between mac and network header */
	if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
		return TC_ACT_SHOT;

	/* prepare new outer network header */
	h_outer.ip = iph_inner;
	h_outer.ip.payload_len = bpf_htons(olen +
					   bpf_ntohs(h_outer.ip.payload_len));

	h_outer.ip.nexthdr = encap_proto;

	/* store new outer network header */
	if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
				BPF_F_INVALIDATE_HASH) < 0)
		return TC_ACT_SHOT;

	return TC_ACT_OK;
}

SEC("encap_ipip_none")
int __encap_ipip_none(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
		return encap_ipv4(skb, IPPROTO_IPIP, ETH_P_IP);
	else
		return TC_ACT_OK;
}

SEC("encap_gre_none")
int __encap_gre_none(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
		return encap_ipv4(skb, IPPROTO_GRE, ETH_P_IP);
	else
		return TC_ACT_OK;
}

SEC("encap_gre_mpls")
int __encap_gre_mpls(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
		return encap_ipv4(skb, IPPROTO_GRE, ETH_P_MPLS_UC);
	else
		return TC_ACT_OK;
}

SEC("encap_gre_eth")
int __encap_gre_eth(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
		return encap_ipv4(skb, IPPROTO_GRE, ETH_P_TEB);
	else
		return TC_ACT_OK;
}

SEC("encap_udp_none")
int __encap_udp_none(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
		return encap_ipv4(skb, IPPROTO_UDP, ETH_P_IP);
	else
		return TC_ACT_OK;
}

SEC("encap_udp_mpls")
int __encap_udp_mpls(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
		return encap_ipv4(skb, IPPROTO_UDP, ETH_P_MPLS_UC);
	else
		return TC_ACT_OK;
}

SEC("encap_udp_eth")
int __encap_udp_eth(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
		return encap_ipv4(skb, IPPROTO_UDP, ETH_P_TEB);
	else
		return TC_ACT_OK;
}

SEC("encap_sit_none")
int __encap_sit_none(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
		return encap_ipv4(skb, IPPROTO_IPV6, ETH_P_IP);
	else
		return TC_ACT_OK;
}

SEC("encap_ip6tnl_none")
int __encap_ip6tnl_none(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
		return encap_ipv6(skb, IPPROTO_IPV6, ETH_P_IPV6);
	else
		return TC_ACT_OK;
}

SEC("encap_ip6gre_none")
int __encap_ip6gre_none(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
		return encap_ipv6(skb, IPPROTO_GRE, ETH_P_IPV6);
	else
		return TC_ACT_OK;
}

SEC("encap_ip6gre_mpls")
int __encap_ip6gre_mpls(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
		return encap_ipv6(skb, IPPROTO_GRE, ETH_P_MPLS_UC);
	else
		return TC_ACT_OK;
}

SEC("encap_ip6gre_eth")
int __encap_ip6gre_eth(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
		return encap_ipv6(skb, IPPROTO_GRE, ETH_P_TEB);
	else
		return TC_ACT_OK;
}

SEC("encap_ip6udp_none")
int __encap_ip6udp_none(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
		return encap_ipv6(skb, IPPROTO_UDP, ETH_P_IPV6);
	else
		return TC_ACT_OK;
}

SEC("encap_ip6udp_mpls")
int __encap_ip6udp_mpls(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
		return encap_ipv6(skb, IPPROTO_UDP, ETH_P_MPLS_UC);
	else
		return TC_ACT_OK;
}

SEC("encap_ip6udp_eth")
int __encap_ip6udp_eth(struct __sk_buff *skb)
{
	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
		return encap_ipv6(skb, IPPROTO_UDP, ETH_P_TEB);
	else
		return TC_ACT_OK;
}

static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
{
	char buf[sizeof(struct v6hdr)];
	struct gre_hdr greh;
	struct udphdr udph;
	int olen = len;

	switch (proto) {
	case IPPROTO_IPIP:
	case IPPROTO_IPV6:
		break;
	case IPPROTO_GRE:
		olen += sizeof(struct gre_hdr);
		if (bpf_skb_load_bytes(skb, off + len, &greh, sizeof(greh)) < 0)
			return TC_ACT_OK;
		switch (bpf_ntohs(greh.protocol)) {
		case ETH_P_MPLS_UC:
			olen += sizeof(mpls_label);
			break;
		case ETH_P_TEB:
			olen += ETH_HLEN;
			break;
		}
		break;
	case IPPROTO_UDP:
		olen += sizeof(struct udphdr);
		if (bpf_skb_load_bytes(skb, off + len, &udph, sizeof(udph)) < 0)
			return TC_ACT_OK;
		switch (bpf_ntohs(udph.dest)) {
		case MPLS_OVER_UDP_PORT:
			olen += sizeof(mpls_label);
			break;
		case ETH_OVER_UDP_PORT:
			olen += ETH_HLEN;
			break;
		}
		break;
	default:
		return TC_ACT_OK;
	}

	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC,
				BPF_F_ADJ_ROOM_FIXED_GSO))
		return TC_ACT_SHOT;

	return TC_ACT_OK;
}

static int decap_ipv4(struct __sk_buff *skb)
{
	struct iphdr iph_outer;

	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_outer,
			       sizeof(iph_outer)) < 0)
		return TC_ACT_OK;

	if (iph_outer.ihl != 5)
		return TC_ACT_OK;

	return decap_internal(skb, ETH_HLEN, sizeof(iph_outer),
			      iph_outer.protocol);
}

static int decap_ipv6(struct __sk_buff *skb)
{
	struct ipv6hdr iph_outer;

	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_outer,
			       sizeof(iph_outer)) < 0)
		return TC_ACT_OK;

	return decap_internal(skb, ETH_HLEN, sizeof(iph_outer),
			      iph_outer.nexthdr);
}

SEC("decap")
int decap_f(struct __sk_buff *skb)
{
	switch (skb->protocol) {
	case __bpf_constant_htons(ETH_P_IP):
		return decap_ipv4(skb);
	case __bpf_constant_htons(ETH_P_IPV6):
		return decap_ipv6(skb);
	default:
		/* does not match, ignore */
		return TC_ACT_OK;
	}
}

char __license[] SEC("license") = "GPL";