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
|
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2017 Facebook
#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/ip.h>
#include <linux/ipv6.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <bpf/bpf_helpers.h>
#include "test_iptunnel_common.h"
#include <bpf/bpf_endian.h>
static __always_inline __u32 rol32(__u32 word, unsigned int shift)
{
return (word << shift) | (word >> ((-shift) & 31));
}
/* copy paste of jhash from kernel sources to make sure llvm
* can compile it into valid sequence of bpf instructions
*/
#define __jhash_mix(a, b, c) \
{ \
a -= c; a ^= rol32(c, 4); c += b; \
b -= a; b ^= rol32(a, 6); a += c; \
c -= b; c ^= rol32(b, 8); b += a; \
a -= c; a ^= rol32(c, 16); c += b; \
b -= a; b ^= rol32(a, 19); a += c; \
c -= b; c ^= rol32(b, 4); b += a; \
}
#define __jhash_final(a, b, c) \
{ \
c ^= b; c -= rol32(b, 14); \
a ^= c; a -= rol32(c, 11); \
b ^= a; b -= rol32(a, 25); \
c ^= b; c -= rol32(b, 16); \
a ^= c; a -= rol32(c, 4); \
b ^= a; b -= rol32(a, 14); \
c ^= b; c -= rol32(b, 24); \
}
#define JHASH_INITVAL 0xdeadbeef
typedef unsigned int u32;
static __noinline u32 jhash(const void *key, u32 length, u32 initval)
{
u32 a, b, c;
const unsigned char *k = key;
a = b = c = JHASH_INITVAL + length + initval;
while (length > 12) {
a += *(u32 *)(k);
b += *(u32 *)(k + 4);
c += *(u32 *)(k + 8);
__jhash_mix(a, b, c);
length -= 12;
k += 12;
}
switch (length) {
case 12: c += (u32)k[11]<<24;
case 11: c += (u32)k[10]<<16;
case 10: c += (u32)k[9]<<8;
case 9: c += k[8];
case 8: b += (u32)k[7]<<24;
case 7: b += (u32)k[6]<<16;
case 6: b += (u32)k[5]<<8;
case 5: b += k[4];
case 4: a += (u32)k[3]<<24;
case 3: a += (u32)k[2]<<16;
case 2: a += (u32)k[1]<<8;
case 1: a += k[0];
__jhash_final(a, b, c);
case 0: /* Nothing left to add */
break;
}
return c;
}
static __noinline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
{
a += initval;
b += initval;
c += initval;
__jhash_final(a, b, c);
return c;
}
static __noinline u32 jhash_2words(u32 a, u32 b, u32 initval)
{
return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
}
#define PCKT_FRAGMENTED 65343
#define IPV4_HDR_LEN_NO_OPT 20
#define IPV4_PLUS_ICMP_HDR 28
#define IPV6_PLUS_ICMP_HDR 48
#define RING_SIZE 2
#define MAX_VIPS 12
#define MAX_REALS 5
#define CTL_MAP_SIZE 16
#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE)
#define F_IPV6 (1 << 0)
#define F_HASH_NO_SRC_PORT (1 << 0)
#define F_ICMP (1 << 0)
#define F_SYN_SET (1 << 1)
struct packet_description {
union {
__be32 src;
__be32 srcv6[4];
};
union {
__be32 dst;
__be32 dstv6[4];
};
union {
__u32 ports;
__u16 port16[2];
};
__u8 proto;
__u8 flags;
};
struct ctl_value {
union {
__u64 value;
__u32 ifindex;
__u8 mac[6];
};
};
struct vip_meta {
__u32 flags;
__u32 vip_num;
};
struct real_definition {
union {
__be32 dst;
__be32 dstv6[4];
};
__u8 flags;
};
struct vip_stats {
__u64 bytes;
__u64 pkts;
};
struct eth_hdr {
unsigned char eth_dest[ETH_ALEN];
unsigned char eth_source[ETH_ALEN];
unsigned short eth_proto;
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, MAX_VIPS);
__type(key, struct vip);
__type(value, struct vip_meta);
} vip_map SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, CH_RINGS_SIZE);
__type(key, __u32);
__type(value, __u32);
} ch_rings SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, MAX_REALS);
__type(key, __u32);
__type(value, struct real_definition);
} reals SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
__uint(max_entries, MAX_VIPS);
__type(key, __u32);
__type(value, struct vip_stats);
} stats SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, CTL_MAP_SIZE);
__type(key, __u32);
__type(value, struct ctl_value);
} ctl_array SEC(".maps");
static __noinline __u32 get_packet_hash(struct packet_description *pckt, bool ipv6)
{
if (ipv6)
return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
pckt->ports, CH_RINGS_SIZE);
else
return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
}
static __noinline bool get_packet_dst(struct real_definition **real,
struct packet_description *pckt,
struct vip_meta *vip_info,
bool is_ipv6)
{
__u32 hash = get_packet_hash(pckt, is_ipv6);
__u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE;
__u32 *real_pos;
if (hash != 0x358459b7 /* jhash of ipv4 packet */ &&
hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
return false;
real_pos = bpf_map_lookup_elem(&ch_rings, &key);
if (!real_pos)
return false;
key = *real_pos;
*real = bpf_map_lookup_elem(&reals, &key);
if (!(*real))
return false;
return true;
}
static __noinline int parse_icmpv6(void *data, void *data_end, __u64 off,
struct packet_description *pckt)
{
struct icmp6hdr *icmp_hdr;
struct ipv6hdr *ip6h;
icmp_hdr = data + off;
if (icmp_hdr + 1 > data_end)
return TC_ACT_SHOT;
if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG)
return TC_ACT_OK;
off += sizeof(struct icmp6hdr);
ip6h = data + off;
if (ip6h + 1 > data_end)
return TC_ACT_SHOT;
pckt->proto = ip6h->nexthdr;
pckt->flags |= F_ICMP;
memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16);
memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16);
return TC_ACT_UNSPEC;
}
static __noinline int parse_icmp(void *data, void *data_end, __u64 off,
struct packet_description *pckt)
{
struct icmphdr *icmp_hdr;
struct iphdr *iph;
icmp_hdr = data + off;
if (icmp_hdr + 1 > data_end)
return TC_ACT_SHOT;
if (icmp_hdr->type != ICMP_DEST_UNREACH ||
icmp_hdr->code != ICMP_FRAG_NEEDED)
return TC_ACT_OK;
off += sizeof(struct icmphdr);
iph = data + off;
if (iph + 1 > data_end)
return TC_ACT_SHOT;
if (iph->ihl != 5)
return TC_ACT_SHOT;
pckt->proto = iph->protocol;
pckt->flags |= F_ICMP;
pckt->src = iph->daddr;
pckt->dst = iph->saddr;
return TC_ACT_UNSPEC;
}
static __noinline bool parse_udp(void *data, __u64 off, void *data_end,
struct packet_description *pckt)
{
struct udphdr *udp;
udp = data + off;
if (udp + 1 > data_end)
return false;
if (!(pckt->flags & F_ICMP)) {
pckt->port16[0] = udp->source;
pckt->port16[1] = udp->dest;
} else {
pckt->port16[0] = udp->dest;
pckt->port16[1] = udp->source;
}
return true;
}
static __noinline bool parse_tcp(void *data, __u64 off, void *data_end,
struct packet_description *pckt)
{
struct tcphdr *tcp;
tcp = data + off;
if (tcp + 1 > data_end)
return false;
if (tcp->syn)
pckt->flags |= F_SYN_SET;
if (!(pckt->flags & F_ICMP)) {
pckt->port16[0] = tcp->source;
pckt->port16[1] = tcp->dest;
} else {
pckt->port16[0] = tcp->dest;
pckt->port16[1] = tcp->source;
}
return true;
}
static __noinline int process_packet(void *data, __u64 off, void *data_end,
bool is_ipv6, struct __sk_buff *skb)
{
void *pkt_start = (void *)(long)skb->data;
struct packet_description pckt = {};
struct eth_hdr *eth = pkt_start;
struct bpf_tunnel_key tkey = {};
struct vip_stats *data_stats;
struct real_definition *dst;
struct vip_meta *vip_info;
struct ctl_value *cval;
__u32 v4_intf_pos = 1;
__u32 v6_intf_pos = 2;
struct ipv6hdr *ip6h;
struct vip vip = {};
struct iphdr *iph;
int tun_flag = 0;
__u16 pkt_bytes;
__u64 iph_len;
__u32 ifindex;
__u8 protocol;
__u32 vip_num;
int action;
tkey.tunnel_ttl = 64;
if (is_ipv6) {
ip6h = data + off;
if (ip6h + 1 > data_end)
return TC_ACT_SHOT;
iph_len = sizeof(struct ipv6hdr);
protocol = ip6h->nexthdr;
pckt.proto = protocol;
pkt_bytes = bpf_ntohs(ip6h->payload_len);
off += iph_len;
if (protocol == IPPROTO_FRAGMENT) {
return TC_ACT_SHOT;
} else if (protocol == IPPROTO_ICMPV6) {
action = parse_icmpv6(data, data_end, off, &pckt);
if (action >= 0)
return action;
off += IPV6_PLUS_ICMP_HDR;
} else {
memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16);
memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16);
}
} else {
iph = data + off;
if (iph + 1 > data_end)
return TC_ACT_SHOT;
if (iph->ihl != 5)
return TC_ACT_SHOT;
protocol = iph->protocol;
pckt.proto = protocol;
pkt_bytes = bpf_ntohs(iph->tot_len);
off += IPV4_HDR_LEN_NO_OPT;
if (iph->frag_off & PCKT_FRAGMENTED)
return TC_ACT_SHOT;
if (protocol == IPPROTO_ICMP) {
action = parse_icmp(data, data_end, off, &pckt);
if (action >= 0)
return action;
off += IPV4_PLUS_ICMP_HDR;
} else {
pckt.src = iph->saddr;
pckt.dst = iph->daddr;
}
}
protocol = pckt.proto;
if (protocol == IPPROTO_TCP) {
if (!parse_tcp(data, off, data_end, &pckt))
return TC_ACT_SHOT;
} else if (protocol == IPPROTO_UDP) {
if (!parse_udp(data, off, data_end, &pckt))
return TC_ACT_SHOT;
} else {
return TC_ACT_SHOT;
}
if (is_ipv6)
memcpy(vip.daddr.v6, pckt.dstv6, 16);
else
vip.daddr.v4 = pckt.dst;
vip.dport = pckt.port16[1];
vip.protocol = pckt.proto;
vip_info = bpf_map_lookup_elem(&vip_map, &vip);
if (!vip_info) {
vip.dport = 0;
vip_info = bpf_map_lookup_elem(&vip_map, &vip);
if (!vip_info)
return TC_ACT_SHOT;
pckt.port16[1] = 0;
}
if (vip_info->flags & F_HASH_NO_SRC_PORT)
pckt.port16[0] = 0;
if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
return TC_ACT_SHOT;
if (dst->flags & F_IPV6) {
cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos);
if (!cval)
return TC_ACT_SHOT;
ifindex = cval->ifindex;
memcpy(tkey.remote_ipv6, dst->dstv6, 16);
tun_flag = BPF_F_TUNINFO_IPV6;
} else {
cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos);
if (!cval)
return TC_ACT_SHOT;
ifindex = cval->ifindex;
tkey.remote_ipv4 = dst->dst;
}
vip_num = vip_info->vip_num;
data_stats = bpf_map_lookup_elem(&stats, &vip_num);
if (!data_stats)
return TC_ACT_SHOT;
data_stats->pkts++;
data_stats->bytes += pkt_bytes;
bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag);
*(u32 *)eth->eth_dest = tkey.remote_ipv4;
return bpf_redirect(ifindex, 0);
}
SEC("tc")
int balancer_ingress(struct __sk_buff *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
struct eth_hdr *eth = data;
__u32 eth_proto;
__u32 nh_off;
nh_off = sizeof(struct eth_hdr);
if (data + nh_off > data_end)
return TC_ACT_SHOT;
eth_proto = eth->eth_proto;
if (eth_proto == bpf_htons(ETH_P_IP))
return process_packet(data, nh_off, data_end, false, ctx);
else if (eth_proto == bpf_htons(ETH_P_IPV6))
return process_packet(data, nh_off, data_end, true, ctx);
else
return TC_ACT_SHOT;
}
char _license[] SEC("license") = "GPL";
|