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
|
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2022 Meta */
#include <stddef.h>
#include <string.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#include "test_iptunnel_common.h"
#include "bpf_kfuncs.h"
const size_t tcphdr_sz = sizeof(struct tcphdr);
const size_t udphdr_sz = sizeof(struct udphdr);
const size_t ethhdr_sz = sizeof(struct ethhdr);
const size_t iphdr_sz = sizeof(struct iphdr);
const size_t ipv6hdr_sz = sizeof(struct ipv6hdr);
struct {
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
__uint(max_entries, 256);
__type(key, __u32);
__type(value, __u64);
} rxcnt SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, MAX_IPTNL_ENTRIES);
__type(key, struct vip);
__type(value, struct iptnl_info);
} vip2tnl SEC(".maps");
static __always_inline void count_tx(__u32 protocol)
{
__u64 *rxcnt_count;
rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
if (rxcnt_count)
*rxcnt_count += 1;
}
static __always_inline int get_dport(void *trans_data, __u8 protocol)
{
struct tcphdr *th;
struct udphdr *uh;
switch (protocol) {
case IPPROTO_TCP:
th = (struct tcphdr *)trans_data;
return th->dest;
case IPPROTO_UDP:
uh = (struct udphdr *)trans_data;
return uh->dest;
default:
return 0;
}
}
static __always_inline void set_ethhdr(struct ethhdr *new_eth,
const struct ethhdr *old_eth,
const struct iptnl_info *tnl,
__be16 h_proto)
{
memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
new_eth->h_proto = h_proto;
}
static __always_inline int handle_ipv4(struct xdp_md *xdp, struct bpf_dynptr *xdp_ptr)
{
__u8 eth_buffer[ethhdr_sz + iphdr_sz + ethhdr_sz];
__u8 iph_buffer_tcp[iphdr_sz + tcphdr_sz];
__u8 iph_buffer_udp[iphdr_sz + udphdr_sz];
struct bpf_dynptr new_xdp_ptr;
struct iptnl_info *tnl;
struct ethhdr *new_eth;
struct ethhdr *old_eth;
__u32 transport_hdr_sz;
struct iphdr *iph;
__u16 *next_iph;
__u16 payload_len;
struct vip vip = {};
int dport;
__u32 csum = 0;
int i;
__builtin_memset(eth_buffer, 0, sizeof(eth_buffer));
__builtin_memset(iph_buffer_tcp, 0, sizeof(iph_buffer_tcp));
__builtin_memset(iph_buffer_udp, 0, sizeof(iph_buffer_udp));
if (ethhdr_sz + iphdr_sz + tcphdr_sz > xdp->data_end - xdp->data)
iph = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, iph_buffer_udp, sizeof(iph_buffer_udp));
else
iph = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, iph_buffer_tcp, sizeof(iph_buffer_tcp));
if (!iph)
return XDP_DROP;
dport = get_dport(iph + 1, iph->protocol);
if (dport == -1)
return XDP_DROP;
vip.protocol = iph->protocol;
vip.family = AF_INET;
vip.daddr.v4 = iph->daddr;
vip.dport = dport;
payload_len = bpf_ntohs(iph->tot_len);
tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
/* It only does v4-in-v4 */
if (!tnl || tnl->family != AF_INET)
return XDP_PASS;
if (bpf_xdp_adjust_head(xdp, 0 - (int)iphdr_sz))
return XDP_DROP;
bpf_dynptr_from_xdp(xdp, 0, &new_xdp_ptr);
new_eth = bpf_dynptr_slice_rdwr(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer));
if (!new_eth)
return XDP_DROP;
iph = (struct iphdr *)(new_eth + 1);
old_eth = (struct ethhdr *)(iph + 1);
set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP));
if (new_eth == eth_buffer)
bpf_dynptr_write(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer), 0);
iph->version = 4;
iph->ihl = iphdr_sz >> 2;
iph->frag_off = 0;
iph->protocol = IPPROTO_IPIP;
iph->check = 0;
iph->tos = 0;
iph->tot_len = bpf_htons(payload_len + iphdr_sz);
iph->daddr = tnl->daddr.v4;
iph->saddr = tnl->saddr.v4;
iph->ttl = 8;
next_iph = (__u16 *)iph;
for (i = 0; i < iphdr_sz >> 1; i++)
csum += *next_iph++;
iph->check = ~((csum & 0xffff) + (csum >> 16));
count_tx(vip.protocol);
return XDP_TX;
}
static __always_inline int handle_ipv6(struct xdp_md *xdp, struct bpf_dynptr *xdp_ptr)
{
__u8 eth_buffer[ethhdr_sz + ipv6hdr_sz + ethhdr_sz];
__u8 ip6h_buffer_tcp[ipv6hdr_sz + tcphdr_sz];
__u8 ip6h_buffer_udp[ipv6hdr_sz + udphdr_sz];
struct bpf_dynptr new_xdp_ptr;
struct iptnl_info *tnl;
struct ethhdr *new_eth;
struct ethhdr *old_eth;
__u32 transport_hdr_sz;
struct ipv6hdr *ip6h;
__u16 payload_len;
struct vip vip = {};
int dport;
__builtin_memset(eth_buffer, 0, sizeof(eth_buffer));
__builtin_memset(ip6h_buffer_tcp, 0, sizeof(ip6h_buffer_tcp));
__builtin_memset(ip6h_buffer_udp, 0, sizeof(ip6h_buffer_udp));
if (ethhdr_sz + iphdr_sz + tcphdr_sz > xdp->data_end - xdp->data)
ip6h = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, ip6h_buffer_udp, sizeof(ip6h_buffer_udp));
else
ip6h = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, ip6h_buffer_tcp, sizeof(ip6h_buffer_tcp));
if (!ip6h)
return XDP_DROP;
dport = get_dport(ip6h + 1, ip6h->nexthdr);
if (dport == -1)
return XDP_DROP;
vip.protocol = ip6h->nexthdr;
vip.family = AF_INET6;
memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
vip.dport = dport;
payload_len = ip6h->payload_len;
tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
/* It only does v6-in-v6 */
if (!tnl || tnl->family != AF_INET6)
return XDP_PASS;
if (bpf_xdp_adjust_head(xdp, 0 - (int)ipv6hdr_sz))
return XDP_DROP;
bpf_dynptr_from_xdp(xdp, 0, &new_xdp_ptr);
new_eth = bpf_dynptr_slice_rdwr(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer));
if (!new_eth)
return XDP_DROP;
ip6h = (struct ipv6hdr *)(new_eth + 1);
old_eth = (struct ethhdr *)(ip6h + 1);
set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6));
if (new_eth == eth_buffer)
bpf_dynptr_write(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer), 0);
ip6h->version = 6;
ip6h->priority = 0;
memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + ipv6hdr_sz);
ip6h->nexthdr = IPPROTO_IPV6;
ip6h->hop_limit = 8;
memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
count_tx(vip.protocol);
return XDP_TX;
}
SEC("xdp")
int _xdp_tx_iptunnel(struct xdp_md *xdp)
{
__u8 buffer[ethhdr_sz];
struct bpf_dynptr ptr;
struct ethhdr *eth;
__u16 h_proto;
__builtin_memset(buffer, 0, sizeof(buffer));
bpf_dynptr_from_xdp(xdp, 0, &ptr);
eth = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
if (!eth)
return XDP_DROP;
h_proto = eth->h_proto;
if (h_proto == bpf_htons(ETH_P_IP))
return handle_ipv4(xdp, &ptr);
else if (h_proto == bpf_htons(ETH_P_IPV6))
return handle_ipv6(xdp, &ptr);
else
return XDP_DROP;
}
char _license[] SEC("license") = "GPL";
|
