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
|
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2022 Meta
#include <stddef.h>
#include <stdint.h>
#include <stdbool.h>
#include <linux/bpf.h>
#include <linux/stddef.h>
#include <linux/pkt_cls.h>
#include <linux/if_ether.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
/* veth_src --- veth_src_fwd --- veth_det_fwd --- veth_dst
* | |
* ns_src | ns_fwd | ns_dst
*
* ns_src and ns_dst: ENDHOST namespace
* ns_fwd: Fowarding namespace
*/
#define ctx_ptr(field) (void *)(long)(field)
#define ip4_src __bpf_htonl(0xac100164) /* 172.16.1.100 */
#define ip4_dst __bpf_htonl(0xac100264) /* 172.16.2.100 */
#define ip6_src { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
0x00, 0x01, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe }
#define ip6_dst { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
0x00, 0x02, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe }
#define v6_equal(a, b) (a.s6_addr32[0] == b.s6_addr32[0] && \
a.s6_addr32[1] == b.s6_addr32[1] && \
a.s6_addr32[2] == b.s6_addr32[2] && \
a.s6_addr32[3] == b.s6_addr32[3])
volatile const __u32 IFINDEX_SRC;
volatile const __u32 IFINDEX_DST;
#define EGRESS_ENDHOST_MAGIC 0x0b9fbeef
#define INGRESS_FWDNS_MAGIC 0x1b9fbeef
#define EGRESS_FWDNS_MAGIC 0x2b9fbeef
enum {
INGRESS_FWDNS_P100,
INGRESS_FWDNS_P101,
EGRESS_FWDNS_P100,
EGRESS_FWDNS_P101,
INGRESS_ENDHOST,
EGRESS_ENDHOST,
SET_DTIME,
__MAX_CNT,
};
enum {
TCP_IP6_CLEAR_DTIME,
TCP_IP4,
TCP_IP6,
UDP_IP4,
UDP_IP6,
TCP_IP4_RT_FWD,
TCP_IP6_RT_FWD,
UDP_IP4_RT_FWD,
UDP_IP6_RT_FWD,
UKN_TEST,
__NR_TESTS,
};
enum {
SRC_NS = 1,
DST_NS,
};
__u32 dtimes[__NR_TESTS][__MAX_CNT] = {};
__u32 errs[__NR_TESTS][__MAX_CNT] = {};
__u32 test = 0;
static void inc_dtimes(__u32 idx)
{
if (test < __NR_TESTS)
dtimes[test][idx]++;
else
dtimes[UKN_TEST][idx]++;
}
static void inc_errs(__u32 idx)
{
if (test < __NR_TESTS)
errs[test][idx]++;
else
errs[UKN_TEST][idx]++;
}
static int skb_proto(int type)
{
return type & 0xff;
}
static int skb_ns(int type)
{
return (type >> 8) & 0xff;
}
static bool fwdns_clear_dtime(void)
{
return test == TCP_IP6_CLEAR_DTIME;
}
static bool bpf_fwd(void)
{
return test < TCP_IP4_RT_FWD;
}
static __u8 get_proto(void)
{
switch (test) {
case UDP_IP4:
case UDP_IP6:
case UDP_IP4_RT_FWD:
case UDP_IP6_RT_FWD:
return IPPROTO_UDP;
default:
return IPPROTO_TCP;
}
}
/* -1: parse error: TC_ACT_SHOT
* 0: not testing traffic: TC_ACT_OK
* >0: first byte is the inet_proto, second byte has the netns
* of the sender
*/
static int skb_get_type(struct __sk_buff *skb)
{
__u16 dst_ns_port = __bpf_htons(50000 + test);
void *data_end = ctx_ptr(skb->data_end);
void *data = ctx_ptr(skb->data);
__u8 inet_proto = 0, ns = 0;
struct ipv6hdr *ip6h;
__u16 sport, dport;
struct iphdr *iph;
struct tcphdr *th;
struct udphdr *uh;
void *trans;
switch (skb->protocol) {
case __bpf_htons(ETH_P_IP):
iph = data + sizeof(struct ethhdr);
if (iph + 1 > data_end)
return -1;
if (iph->saddr == ip4_src)
ns = SRC_NS;
else if (iph->saddr == ip4_dst)
ns = DST_NS;
inet_proto = iph->protocol;
trans = iph + 1;
break;
case __bpf_htons(ETH_P_IPV6):
ip6h = data + sizeof(struct ethhdr);
if (ip6h + 1 > data_end)
return -1;
if (v6_equal(ip6h->saddr, (struct in6_addr){{ip6_src}}))
ns = SRC_NS;
else if (v6_equal(ip6h->saddr, (struct in6_addr){{ip6_dst}}))
ns = DST_NS;
inet_proto = ip6h->nexthdr;
trans = ip6h + 1;
break;
default:
return 0;
}
/* skb is not from src_ns or dst_ns.
* skb is not the testing IPPROTO.
*/
if (!ns || inet_proto != get_proto())
return 0;
switch (inet_proto) {
case IPPROTO_TCP:
th = trans;
if (th + 1 > data_end)
return -1;
sport = th->source;
dport = th->dest;
break;
case IPPROTO_UDP:
uh = trans;
if (uh + 1 > data_end)
return -1;
sport = uh->source;
dport = uh->dest;
break;
default:
return 0;
}
/* The skb is the testing traffic */
if ((ns == SRC_NS && dport == dst_ns_port) ||
(ns == DST_NS && sport == dst_ns_port))
return (ns << 8 | inet_proto);
return 0;
}
/* format: direction@iface@netns
* egress@veth_(src|dst)@ns_(src|dst)
*/
SEC("tc")
int egress_host(struct __sk_buff *skb)
{
int skb_type;
skb_type = skb_get_type(skb);
if (skb_type == -1)
return TC_ACT_SHOT;
if (!skb_type)
return TC_ACT_OK;
if (skb_proto(skb_type) == IPPROTO_TCP) {
if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO &&
skb->tstamp)
inc_dtimes(EGRESS_ENDHOST);
else
inc_errs(EGRESS_ENDHOST);
} else {
if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC &&
skb->tstamp)
inc_dtimes(EGRESS_ENDHOST);
else
inc_errs(EGRESS_ENDHOST);
}
skb->tstamp = EGRESS_ENDHOST_MAGIC;
return TC_ACT_OK;
}
/* ingress@veth_(src|dst)@ns_(src|dst) */
SEC("tc")
int ingress_host(struct __sk_buff *skb)
{
int skb_type;
skb_type = skb_get_type(skb);
if (skb_type == -1)
return TC_ACT_SHOT;
if (!skb_type)
return TC_ACT_OK;
if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO &&
skb->tstamp == EGRESS_FWDNS_MAGIC)
inc_dtimes(INGRESS_ENDHOST);
else
inc_errs(INGRESS_ENDHOST);
return TC_ACT_OK;
}
/* ingress@veth_(src|dst)_fwd@ns_fwd priority 100 */
SEC("tc")
int ingress_fwdns_prio100(struct __sk_buff *skb)
{
int skb_type;
skb_type = skb_get_type(skb);
if (skb_type == -1)
return TC_ACT_SHOT;
if (!skb_type)
return TC_ACT_OK;
/* delivery_time is only available to the ingress
* if the tc-bpf checks the skb->tstamp_type.
*/
if (skb->tstamp == EGRESS_ENDHOST_MAGIC)
inc_errs(INGRESS_FWDNS_P100);
if (fwdns_clear_dtime())
skb->tstamp = 0;
return TC_ACT_UNSPEC;
}
/* egress@veth_(src|dst)_fwd@ns_fwd priority 100 */
SEC("tc")
int egress_fwdns_prio100(struct __sk_buff *skb)
{
int skb_type;
skb_type = skb_get_type(skb);
if (skb_type == -1)
return TC_ACT_SHOT;
if (!skb_type)
return TC_ACT_OK;
/* delivery_time is always available to egress even
* the tc-bpf did not use the tstamp_type.
*/
if (skb->tstamp == INGRESS_FWDNS_MAGIC)
inc_dtimes(EGRESS_FWDNS_P100);
else
inc_errs(EGRESS_FWDNS_P100);
if (fwdns_clear_dtime())
skb->tstamp = 0;
return TC_ACT_UNSPEC;
}
/* ingress@veth_(src|dst)_fwd@ns_fwd priority 101 */
SEC("tc")
int ingress_fwdns_prio101(struct __sk_buff *skb)
{
__u64 expected_dtime = EGRESS_ENDHOST_MAGIC;
int skb_type;
skb_type = skb_get_type(skb);
if (skb_type == -1 || !skb_type)
/* Should have handled in prio100 */
return TC_ACT_SHOT;
if (skb_proto(skb_type) == IPPROTO_UDP)
expected_dtime = 0;
if (skb->tstamp_type) {
if (fwdns_clear_dtime() ||
skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO ||
skb->tstamp != expected_dtime)
inc_errs(INGRESS_FWDNS_P101);
else
inc_dtimes(INGRESS_FWDNS_P101);
} else {
if (!fwdns_clear_dtime() && expected_dtime)
inc_errs(INGRESS_FWDNS_P101);
}
if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) {
skb->tstamp = INGRESS_FWDNS_MAGIC;
} else {
if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
BPF_SKB_TSTAMP_DELIVERY_MONO))
inc_errs(SET_DTIME);
if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
BPF_SKB_TSTAMP_UNSPEC))
inc_errs(SET_DTIME);
}
if (skb_ns(skb_type) == SRC_NS)
return bpf_fwd() ?
bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0) : TC_ACT_OK;
else
return bpf_fwd() ?
bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0) : TC_ACT_OK;
}
/* egress@veth_(src|dst)_fwd@ns_fwd priority 101 */
SEC("tc")
int egress_fwdns_prio101(struct __sk_buff *skb)
{
int skb_type;
skb_type = skb_get_type(skb);
if (skb_type == -1 || !skb_type)
/* Should have handled in prio100 */
return TC_ACT_SHOT;
if (skb->tstamp_type) {
if (fwdns_clear_dtime() ||
skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO ||
skb->tstamp != INGRESS_FWDNS_MAGIC)
inc_errs(EGRESS_FWDNS_P101);
else
inc_dtimes(EGRESS_FWDNS_P101);
} else {
if (!fwdns_clear_dtime())
inc_errs(EGRESS_FWDNS_P101);
}
if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) {
skb->tstamp = EGRESS_FWDNS_MAGIC;
} else {
if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC,
BPF_SKB_TSTAMP_DELIVERY_MONO))
inc_errs(SET_DTIME);
if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
BPF_SKB_TSTAMP_UNSPEC))
inc_errs(SET_DTIME);
}
return TC_ACT_OK;
}
char __license[] SEC("license") = "GPL";
|
