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
|
// SPDX-License-Identifier: GPL-2.0
#include <limits.h>
#include <stddef.h>
#include <stdbool.h>
#include <string.h>
#include <linux/pkt_cls.h>
#include <linux/bpf.h>
#include <linux/in.h>
#include <linux/if_ether.h>
#include <linux/icmp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_packet.h>
#include <sys/socket.h>
#include <linux/if_tunnel.h>
#include <linux/mpls.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
int _version SEC("version") = 1;
#define PROG(F) SEC(#F) int bpf_func_##F
/* These are the identifiers of the BPF programs that will be used in tail
* calls. Name is limited to 16 characters, with the terminating character and
* bpf_func_ above, we have only 6 to work with, anything after will be cropped.
*/
enum {
IP,
IPV6,
IPV6OP, /* Destination/Hop-by-Hop Options IPv6 Extension header */
IPV6FR, /* Fragmentation IPv6 Extension Header */
MPLS,
VLAN,
};
#define IP_MF 0x2000
#define IP_OFFSET 0x1FFF
#define IP6_MF 0x0001
#define IP6_OFFSET 0xFFF8
struct vlan_hdr {
__be16 h_vlan_TCI;
__be16 h_vlan_encapsulated_proto;
};
struct gre_hdr {
__be16 flags;
__be16 proto;
};
struct frag_hdr {
__u8 nexthdr;
__u8 reserved;
__be16 frag_off;
__be32 identification;
};
struct bpf_map_def SEC("maps") jmp_table = {
.type = BPF_MAP_TYPE_PROG_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = 8
};
static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb,
__u16 hdr_size,
void *buffer)
{
void *data_end = (void *)(long)skb->data_end;
void *data = (void *)(long)skb->data;
__u16 nhoff = skb->flow_keys->nhoff;
__u8 *hdr;
/* Verifies this variable offset does not overflow */
if (nhoff > (USHRT_MAX - hdr_size))
return NULL;
hdr = data + nhoff;
if (hdr + hdr_size <= data_end)
return hdr;
if (bpf_skb_load_bytes(skb, nhoff, buffer, hdr_size))
return NULL;
return buffer;
}
/* Dispatches on ETHERTYPE */
static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
{
struct bpf_flow_keys *keys = skb->flow_keys;
keys->n_proto = proto;
switch (proto) {
case bpf_htons(ETH_P_IP):
bpf_tail_call(skb, &jmp_table, IP);
break;
case bpf_htons(ETH_P_IPV6):
bpf_tail_call(skb, &jmp_table, IPV6);
break;
case bpf_htons(ETH_P_MPLS_MC):
case bpf_htons(ETH_P_MPLS_UC):
bpf_tail_call(skb, &jmp_table, MPLS);
break;
case bpf_htons(ETH_P_8021Q):
case bpf_htons(ETH_P_8021AD):
bpf_tail_call(skb, &jmp_table, VLAN);
break;
default:
/* Protocol not supported */
return BPF_DROP;
}
return BPF_DROP;
}
SEC("dissect")
int _dissect(struct __sk_buff *skb)
{
if (!skb->vlan_present)
return parse_eth_proto(skb, skb->protocol);
else
return parse_eth_proto(skb, skb->vlan_proto);
}
/* Parses on IPPROTO_* */
static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
{
struct bpf_flow_keys *keys = skb->flow_keys;
void *data_end = (void *)(long)skb->data_end;
struct icmphdr *icmp, _icmp;
struct gre_hdr *gre, _gre;
struct ethhdr *eth, _eth;
struct tcphdr *tcp, _tcp;
struct udphdr *udp, _udp;
keys->ip_proto = proto;
switch (proto) {
case IPPROTO_ICMP:
icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp);
if (!icmp)
return BPF_DROP;
return BPF_OK;
case IPPROTO_IPIP:
keys->is_encap = true;
return parse_eth_proto(skb, bpf_htons(ETH_P_IP));
case IPPROTO_IPV6:
keys->is_encap = true;
return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6));
case IPPROTO_GRE:
gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre);
if (!gre)
return BPF_DROP;
if (bpf_htons(gre->flags & GRE_VERSION))
/* Only inspect standard GRE packets with version 0 */
return BPF_OK;
keys->nhoff += sizeof(*gre); /* Step over GRE Flags and Proto */
if (GRE_IS_CSUM(gre->flags))
keys->nhoff += 4; /* Step over chksum and Padding */
if (GRE_IS_KEY(gre->flags))
keys->nhoff += 4; /* Step over key */
if (GRE_IS_SEQ(gre->flags))
keys->nhoff += 4; /* Step over sequence number */
keys->is_encap = true;
if (gre->proto == bpf_htons(ETH_P_TEB)) {
eth = bpf_flow_dissect_get_header(skb, sizeof(*eth),
&_eth);
if (!eth)
return BPF_DROP;
keys->nhoff += sizeof(*eth);
return parse_eth_proto(skb, eth->h_proto);
} else {
return parse_eth_proto(skb, gre->proto);
}
case IPPROTO_TCP:
tcp = bpf_flow_dissect_get_header(skb, sizeof(*tcp), &_tcp);
if (!tcp)
return BPF_DROP;
if (tcp->doff < 5)
return BPF_DROP;
if ((__u8 *)tcp + (tcp->doff << 2) > data_end)
return BPF_DROP;
keys->thoff = keys->nhoff;
keys->sport = tcp->source;
keys->dport = tcp->dest;
return BPF_OK;
case IPPROTO_UDP:
case IPPROTO_UDPLITE:
udp = bpf_flow_dissect_get_header(skb, sizeof(*udp), &_udp);
if (!udp)
return BPF_DROP;
keys->thoff = keys->nhoff;
keys->sport = udp->source;
keys->dport = udp->dest;
return BPF_OK;
default:
return BPF_DROP;
}
return BPF_DROP;
}
static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr)
{
struct bpf_flow_keys *keys = skb->flow_keys;
keys->ip_proto = nexthdr;
switch (nexthdr) {
case IPPROTO_HOPOPTS:
case IPPROTO_DSTOPTS:
bpf_tail_call(skb, &jmp_table, IPV6OP);
break;
case IPPROTO_FRAGMENT:
bpf_tail_call(skb, &jmp_table, IPV6FR);
break;
default:
return parse_ip_proto(skb, nexthdr);
}
return BPF_DROP;
}
PROG(IP)(struct __sk_buff *skb)
{
void *data_end = (void *)(long)skb->data_end;
struct bpf_flow_keys *keys = skb->flow_keys;
void *data = (void *)(long)skb->data;
struct iphdr *iph, _iph;
bool done = false;
iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph);
if (!iph)
return BPF_DROP;
/* IP header cannot be smaller than 20 bytes */
if (iph->ihl < 5)
return BPF_DROP;
keys->addr_proto = ETH_P_IP;
keys->ipv4_src = iph->saddr;
keys->ipv4_dst = iph->daddr;
keys->nhoff += iph->ihl << 2;
if (data + keys->nhoff > data_end)
return BPF_DROP;
if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) {
keys->is_frag = true;
if (iph->frag_off & bpf_htons(IP_OFFSET))
/* From second fragment on, packets do not have headers
* we can parse.
*/
done = true;
else
keys->is_first_frag = true;
}
if (done)
return BPF_OK;
return parse_ip_proto(skb, iph->protocol);
}
PROG(IPV6)(struct __sk_buff *skb)
{
struct bpf_flow_keys *keys = skb->flow_keys;
struct ipv6hdr *ip6h, _ip6h;
ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h);
if (!ip6h)
return BPF_DROP;
keys->addr_proto = ETH_P_IPV6;
memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr));
keys->nhoff += sizeof(struct ipv6hdr);
return parse_ipv6_proto(skb, ip6h->nexthdr);
}
PROG(IPV6OP)(struct __sk_buff *skb)
{
struct ipv6_opt_hdr *ip6h, _ip6h;
ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h);
if (!ip6h)
return BPF_DROP;
/* hlen is in 8-octets and does not include the first 8 bytes
* of the header
*/
skb->flow_keys->nhoff += (1 + ip6h->hdrlen) << 3;
return parse_ipv6_proto(skb, ip6h->nexthdr);
}
PROG(IPV6FR)(struct __sk_buff *skb)
{
struct bpf_flow_keys *keys = skb->flow_keys;
struct frag_hdr *fragh, _fragh;
fragh = bpf_flow_dissect_get_header(skb, sizeof(*fragh), &_fragh);
if (!fragh)
return BPF_DROP;
keys->nhoff += sizeof(*fragh);
keys->is_frag = true;
if (!(fragh->frag_off & bpf_htons(IP6_OFFSET)))
keys->is_first_frag = true;
return parse_ipv6_proto(skb, fragh->nexthdr);
}
PROG(MPLS)(struct __sk_buff *skb)
{
struct mpls_label *mpls, _mpls;
mpls = bpf_flow_dissect_get_header(skb, sizeof(*mpls), &_mpls);
if (!mpls)
return BPF_DROP;
return BPF_OK;
}
PROG(VLAN)(struct __sk_buff *skb)
{
struct bpf_flow_keys *keys = skb->flow_keys;
struct vlan_hdr *vlan, _vlan;
__be16 proto;
/* Peek back to see if single or double-tagging */
if (bpf_skb_load_bytes(skb, keys->nhoff - sizeof(proto), &proto,
sizeof(proto)))
return BPF_DROP;
/* Account for double-tagging */
if (proto == bpf_htons(ETH_P_8021AD)) {
vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
if (!vlan)
return BPF_DROP;
if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
return BPF_DROP;
keys->nhoff += sizeof(*vlan);
}
vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
if (!vlan)
return BPF_DROP;
keys->nhoff += sizeof(*vlan);
/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
return BPF_DROP;
return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
}
char __license[] SEC("license") = "GPL";
|
