summaryrefslogtreecommitdiff
path: root/samples/bpf/xdp_redirect_cpu.bpf.c
blob: 25e3a405375f28e867023ba4dc9d364a6b100316 (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
537
538
539
/*  XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP)
 *
 *  GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
 */
#include "vmlinux.h"
#include "xdp_sample.bpf.h"
#include "xdp_sample_shared.h"
#include "hash_func01.h"

/* Special map type that can XDP_REDIRECT frames to another CPU */
struct {
	__uint(type, BPF_MAP_TYPE_CPUMAP);
	__uint(key_size, sizeof(u32));
	__uint(value_size, sizeof(struct bpf_cpumap_val));
} cpu_map SEC(".maps");

/* Set of maps controlling available CPU, and for iterating through
 * selectable redirect CPUs.
 */
struct {
	__uint(type, BPF_MAP_TYPE_ARRAY);
	__type(key, u32);
	__type(value, u32);
} cpus_available SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_ARRAY);
	__type(key, u32);
	__type(value, u32);
	__uint(max_entries, 1);
} cpus_count SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
	__type(key, u32);
	__type(value, u32);
	__uint(max_entries, 1);
} cpus_iterator SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_DEVMAP);
	__uint(key_size, sizeof(int));
	__uint(value_size, sizeof(struct bpf_devmap_val));
	__uint(max_entries, 1);
} tx_port SEC(".maps");

char tx_mac_addr[ETH_ALEN];

/* Helper parse functions */

static __always_inline
bool parse_eth(struct ethhdr *eth, void *data_end,
	       u16 *eth_proto, u64 *l3_offset)
{
	u16 eth_type;
	u64 offset;

	offset = sizeof(*eth);
	if ((void *)eth + offset > data_end)
		return false;

	eth_type = eth->h_proto;

	/* Skip non 802.3 Ethertypes */
	if (__builtin_expect(bpf_ntohs(eth_type) < ETH_P_802_3_MIN, 0))
		return false;

	/* Handle VLAN tagged packet */
	if (eth_type == bpf_htons(ETH_P_8021Q) ||
	    eth_type == bpf_htons(ETH_P_8021AD)) {
		struct vlan_hdr *vlan_hdr;

		vlan_hdr = (void *)eth + offset;
		offset += sizeof(*vlan_hdr);
		if ((void *)eth + offset > data_end)
			return false;
		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
	}
	/* Handle double VLAN tagged packet */
	if (eth_type == bpf_htons(ETH_P_8021Q) ||
	    eth_type == bpf_htons(ETH_P_8021AD)) {
		struct vlan_hdr *vlan_hdr;

		vlan_hdr = (void *)eth + offset;
		offset += sizeof(*vlan_hdr);
		if ((void *)eth + offset > data_end)
			return false;
		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
	}

	*eth_proto = bpf_ntohs(eth_type);
	*l3_offset = offset;
	return true;
}

static __always_inline
u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	struct iphdr *iph = data + nh_off;
	struct udphdr *udph;

	if (iph + 1 > data_end)
		return 0;
	if (!(iph->protocol == IPPROTO_UDP))
		return 0;

	udph = (void *)(iph + 1);
	if (udph + 1 > data_end)
		return 0;

	return bpf_ntohs(udph->dest);
}

static __always_inline
int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	struct iphdr *iph = data + nh_off;

	if (iph + 1 > data_end)
		return 0;
	return iph->protocol;
}

static __always_inline
int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	struct ipv6hdr *ip6h = data + nh_off;

	if (ip6h + 1 > data_end)
		return 0;
	return ip6h->nexthdr;
}

SEC("xdp")
int  xdp_prognum0_no_touch(struct xdp_md *ctx)
{
	u32 key = bpf_get_smp_processor_id();
	struct datarec *rec;
	u32 *cpu_selected;
	u32 cpu_dest = 0;
	u32 key0 = 0;

	/* Only use first entry in cpus_available */
	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key0);
	if (!cpu_selected)
		return XDP_ABORTED;
	cpu_dest = *cpu_selected;

	rec = bpf_map_lookup_elem(&rx_cnt, &key);
	if (!rec)
		return XDP_PASS;
	NO_TEAR_INC(rec->processed);

	if (cpu_dest >= nr_cpus) {
		NO_TEAR_INC(rec->issue);
		return XDP_ABORTED;
	}
	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
}

SEC("xdp")
int  xdp_prognum1_touch_data(struct xdp_md *ctx)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	u32 key = bpf_get_smp_processor_id();
	struct ethhdr *eth = data;
	struct datarec *rec;
	u32 *cpu_selected;
	u32 cpu_dest = 0;
	u32 key0 = 0;
	u16 eth_type;

	/* Only use first entry in cpus_available */
	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key0);
	if (!cpu_selected)
		return XDP_ABORTED;
	cpu_dest = *cpu_selected;

	/* Validate packet length is minimum Eth header size */
	if (eth + 1 > data_end)
		return XDP_ABORTED;

	rec = bpf_map_lookup_elem(&rx_cnt, &key);
	if (!rec)
		return XDP_PASS;
	NO_TEAR_INC(rec->processed);

	/* Read packet data, and use it (drop non 802.3 Ethertypes) */
	eth_type = eth->h_proto;
	if (bpf_ntohs(eth_type) < ETH_P_802_3_MIN) {
		NO_TEAR_INC(rec->dropped);
		return XDP_DROP;
	}

	if (cpu_dest >= nr_cpus) {
		NO_TEAR_INC(rec->issue);
		return XDP_ABORTED;
	}
	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
}

SEC("xdp")
int  xdp_prognum2_round_robin(struct xdp_md *ctx)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	u32 key = bpf_get_smp_processor_id();
	struct datarec *rec;
	u32 cpu_dest = 0;
	u32 key0 = 0;

	u32 *cpu_selected;
	u32 *cpu_iterator;
	u32 *cpu_max;
	u32 cpu_idx;

	cpu_max = bpf_map_lookup_elem(&cpus_count, &key0);
	if (!cpu_max)
		return XDP_ABORTED;

	cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0);
	if (!cpu_iterator)
		return XDP_ABORTED;
	cpu_idx = *cpu_iterator;

	*cpu_iterator += 1;
	if (*cpu_iterator == *cpu_max)
		*cpu_iterator = 0;

	cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
	if (!cpu_selected)
		return XDP_ABORTED;
	cpu_dest = *cpu_selected;

	rec = bpf_map_lookup_elem(&rx_cnt, &key);
	if (!rec)
		return XDP_PASS;
	NO_TEAR_INC(rec->processed);

	if (cpu_dest >= nr_cpus) {
		NO_TEAR_INC(rec->issue);
		return XDP_ABORTED;
	}
	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
}

SEC("xdp")
int  xdp_prognum3_proto_separate(struct xdp_md *ctx)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	u32 key = bpf_get_smp_processor_id();
	struct ethhdr *eth = data;
	u8 ip_proto = IPPROTO_UDP;
	struct datarec *rec;
	u16 eth_proto = 0;
	u64 l3_offset = 0;
	u32 cpu_dest = 0;
	u32 *cpu_lookup;
	u32 cpu_idx = 0;

	rec = bpf_map_lookup_elem(&rx_cnt, &key);
	if (!rec)
		return XDP_PASS;
	NO_TEAR_INC(rec->processed);

	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
		return XDP_PASS; /* Just skip */

	/* Extract L4 protocol */
	switch (eth_proto) {
	case ETH_P_IP:
		ip_proto = get_proto_ipv4(ctx, l3_offset);
		break;
	case ETH_P_IPV6:
		ip_proto = get_proto_ipv6(ctx, l3_offset);
		break;
	case ETH_P_ARP:
		cpu_idx = 0; /* ARP packet handled on separate CPU */
		break;
	default:
		cpu_idx = 0;
	}

	/* Choose CPU based on L4 protocol */
	switch (ip_proto) {
	case IPPROTO_ICMP:
	case IPPROTO_ICMPV6:
		cpu_idx = 2;
		break;
	case IPPROTO_TCP:
		cpu_idx = 0;
		break;
	case IPPROTO_UDP:
		cpu_idx = 1;
		break;
	default:
		cpu_idx = 0;
	}

	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
	if (!cpu_lookup)
		return XDP_ABORTED;
	cpu_dest = *cpu_lookup;

	if (cpu_dest >= nr_cpus) {
		NO_TEAR_INC(rec->issue);
		return XDP_ABORTED;
	}
	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
}

SEC("xdp")
int  xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	u32 key = bpf_get_smp_processor_id();
	struct ethhdr *eth = data;
	u8 ip_proto = IPPROTO_UDP;
	struct datarec *rec;
	u16 eth_proto = 0;
	u64 l3_offset = 0;
	u32 cpu_dest = 0;
	u32 *cpu_lookup;
	u32 cpu_idx = 0;
	u16 dest_port;

	rec = bpf_map_lookup_elem(&rx_cnt, &key);
	if (!rec)
		return XDP_PASS;
	NO_TEAR_INC(rec->processed);

	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
		return XDP_PASS; /* Just skip */

	/* Extract L4 protocol */
	switch (eth_proto) {
	case ETH_P_IP:
		ip_proto = get_proto_ipv4(ctx, l3_offset);
		break;
	case ETH_P_IPV6:
		ip_proto = get_proto_ipv6(ctx, l3_offset);
		break;
	case ETH_P_ARP:
		cpu_idx = 0; /* ARP packet handled on separate CPU */
		break;
	default:
		cpu_idx = 0;
	}

	/* Choose CPU based on L4 protocol */
	switch (ip_proto) {
	case IPPROTO_ICMP:
	case IPPROTO_ICMPV6:
		cpu_idx = 2;
		break;
	case IPPROTO_TCP:
		cpu_idx = 0;
		break;
	case IPPROTO_UDP:
		cpu_idx = 1;
		/* DDoS filter UDP port 9 (pktgen) */
		dest_port = get_dest_port_ipv4_udp(ctx, l3_offset);
		if (dest_port == 9) {
			NO_TEAR_INC(rec->dropped);
			return XDP_DROP;
		}
		break;
	default:
		cpu_idx = 0;
	}

	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
	if (!cpu_lookup)
		return XDP_ABORTED;
	cpu_dest = *cpu_lookup;

	if (cpu_dest >= nr_cpus) {
		NO_TEAR_INC(rec->issue);
		return XDP_ABORTED;
	}
	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
}

/* Hashing initval */
#define INITVAL 15485863

static __always_inline
u32 get_ipv4_hash_ip_pair(struct xdp_md *ctx, u64 nh_off)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	struct iphdr *iph = data + nh_off;
	u32 cpu_hash;

	if (iph + 1 > data_end)
		return 0;

	cpu_hash = iph->saddr + iph->daddr;
	cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + iph->protocol);

	return cpu_hash;
}

static __always_inline
u32 get_ipv6_hash_ip_pair(struct xdp_md *ctx, u64 nh_off)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	struct ipv6hdr *ip6h = data + nh_off;
	u32 cpu_hash;

	if (ip6h + 1 > data_end)
		return 0;

	cpu_hash  = ip6h->saddr.in6_u.u6_addr32[0] + ip6h->daddr.in6_u.u6_addr32[0];
	cpu_hash += ip6h->saddr.in6_u.u6_addr32[1] + ip6h->daddr.in6_u.u6_addr32[1];
	cpu_hash += ip6h->saddr.in6_u.u6_addr32[2] + ip6h->daddr.in6_u.u6_addr32[2];
	cpu_hash += ip6h->saddr.in6_u.u6_addr32[3] + ip6h->daddr.in6_u.u6_addr32[3];
	cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + ip6h->nexthdr);

	return cpu_hash;
}

/* Load-Balance traffic based on hashing IP-addrs + L4-proto.  The
 * hashing scheme is symmetric, meaning swapping IP src/dest still hit
 * same CPU.
 */
SEC("xdp")
int  xdp_prognum5_lb_hash_ip_pairs(struct xdp_md *ctx)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data     = (void *)(long)ctx->data;
	u32 key = bpf_get_smp_processor_id();
	struct ethhdr *eth = data;
	struct datarec *rec;
	u16 eth_proto = 0;
	u64 l3_offset = 0;
	u32 cpu_dest = 0;
	u32 cpu_idx = 0;
	u32 *cpu_lookup;
	u32 key0 = 0;
	u32 *cpu_max;
	u32 cpu_hash;

	rec = bpf_map_lookup_elem(&rx_cnt, &key);
	if (!rec)
		return XDP_PASS;
	NO_TEAR_INC(rec->processed);

	cpu_max = bpf_map_lookup_elem(&cpus_count, &key0);
	if (!cpu_max)
		return XDP_ABORTED;

	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
		return XDP_PASS; /* Just skip */

	/* Hash for IPv4 and IPv6 */
	switch (eth_proto) {
	case ETH_P_IP:
		cpu_hash = get_ipv4_hash_ip_pair(ctx, l3_offset);
		break;
	case ETH_P_IPV6:
		cpu_hash = get_ipv6_hash_ip_pair(ctx, l3_offset);
		break;
	case ETH_P_ARP: /* ARP packet handled on CPU idx 0 */
	default:
		cpu_hash = 0;
	}

	/* Choose CPU based on hash */
	cpu_idx = cpu_hash % *cpu_max;

	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
	if (!cpu_lookup)
		return XDP_ABORTED;
	cpu_dest = *cpu_lookup;

	if (cpu_dest >= nr_cpus) {
		NO_TEAR_INC(rec->issue);
		return XDP_ABORTED;
	}
	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
}

SEC("xdp_cpumap/redirect")
int xdp_redirect_cpu_devmap(struct xdp_md *ctx)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data = (void *)(long)ctx->data;
	struct ethhdr *eth = data;
	u64 nh_off;

	nh_off = sizeof(*eth);
	if (data + nh_off > data_end)
		return XDP_DROP;

	swap_src_dst_mac(data);
	return bpf_redirect_map(&tx_port, 0, 0);
}

SEC("xdp_cpumap/pass")
int xdp_redirect_cpu_pass(struct xdp_md *ctx)
{
	return XDP_PASS;
}

SEC("xdp_cpumap/drop")
int xdp_redirect_cpu_drop(struct xdp_md *ctx)
{
	return XDP_DROP;
}

SEC("xdp_devmap/egress")
int xdp_redirect_egress_prog(struct xdp_md *ctx)
{
	void *data_end = (void *)(long)ctx->data_end;
	void *data = (void *)(long)ctx->data;
	struct ethhdr *eth = data;
	u64 nh_off;

	nh_off = sizeof(*eth);
	if (data + nh_off > data_end)
		return XDP_DROP;

	__builtin_memcpy(eth->h_source, (const char *)tx_mac_addr, ETH_ALEN);

	return XDP_PASS;
}

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