summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/bpf/test_xdp_noinline.c
blob: 5e4aac74f9d02f998c212ce536dc3243b805a514 (plain) (blame)
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
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
// 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_helpers.h"

#define bpf_printk(fmt, ...)				\
({							\
	char ____fmt[] = fmt;				\
	bpf_trace_printk(____fmt, sizeof(____fmt),	\
			##__VA_ARGS__);			\
})

static __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 __attribute__ ((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 __attribute__ ((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 __attribute__ ((noinline))
u32 jhash_2words(u32 a, u32 b, u32 initval)
{
	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
}

struct flow_key {
	union {
		__be32 src;
		__be32 srcv6[4];
	};
	union {
		__be32 dst;
		__be32 dstv6[4];
	};
	union {
		__u32 ports;
		__u16 port16[2];
	};
	__u8 proto;
};

struct packet_description {
	struct flow_key flow;
	__u8 flags;
};

struct ctl_value {
	union {
		__u64 value;
		__u32 ifindex;
		__u8 mac[6];
	};
};

struct vip_definition {
	union {
		__be32 vip;
		__be32 vipv6[4];
	};
	__u16 port;
	__u16 family;
	__u8 proto;
};

struct vip_meta {
	__u32 flags;
	__u32 vip_num;
};

struct real_pos_lru {
	__u32 pos;
	__u64 atime;
};

struct real_definition {
	union {
		__be32 dst;
		__be32 dstv6[4];
	};
	__u8 flags;
};

struct lb_stats {
	__u64 v2;
	__u64 v1;
};

struct bpf_map_def __attribute__ ((section("maps"), used)) vip_map = {
	.type = BPF_MAP_TYPE_HASH,
	.key_size = sizeof(struct vip_definition),
	.value_size = sizeof(struct vip_meta),
	.max_entries = 512,
	.map_flags = 0,
};

struct bpf_map_def __attribute__ ((section("maps"), used)) lru_cache = {
	.type = BPF_MAP_TYPE_LRU_HASH,
	.key_size = sizeof(struct flow_key),
	.value_size = sizeof(struct real_pos_lru),
	.max_entries = 300,
	.map_flags = 1U << 1,
};

struct bpf_map_def __attribute__ ((section("maps"), used)) ch_rings = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(__u32),
	.value_size = sizeof(__u32),
	.max_entries = 12 * 655,
	.map_flags = 0,
};

struct bpf_map_def __attribute__ ((section("maps"), used)) reals = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(__u32),
	.value_size = sizeof(struct real_definition),
	.max_entries = 40,
	.map_flags = 0,
};

struct bpf_map_def __attribute__ ((section("maps"), used)) stats = {
	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
	.key_size = sizeof(__u32),
	.value_size = sizeof(struct lb_stats),
	.max_entries = 515,
	.map_flags = 0,
};

struct bpf_map_def __attribute__ ((section("maps"), used)) ctl_array = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(__u32),
	.value_size = sizeof(struct ctl_value),
	.max_entries = 16,
	.map_flags = 0,
};

struct eth_hdr {
	unsigned char eth_dest[6];
	unsigned char eth_source[6];
	unsigned short eth_proto;
};

static inline __u64 calc_offset(bool is_ipv6, bool is_icmp)
{
	__u64 off = sizeof(struct eth_hdr);
	if (is_ipv6) {
		off += sizeof(struct ipv6hdr);
		if (is_icmp)
			off += sizeof(struct icmp6hdr) + sizeof(struct ipv6hdr);
	} else {
		off += sizeof(struct iphdr);
		if (is_icmp)
			off += sizeof(struct icmphdr) + sizeof(struct iphdr);
	}
	return off;
}

static __attribute__ ((noinline))
bool parse_udp(void *data, void *data_end,
	       bool is_ipv6, struct packet_description *pckt)
{

	bool is_icmp = !((pckt->flags & (1 << 0)) == 0);
	__u64 off = calc_offset(is_ipv6, is_icmp);
	struct udphdr *udp;
	udp = data + off;

	if (udp + 1 > data_end)
		return 0;
	if (!is_icmp) {
		pckt->flow.port16[0] = udp->source;
		pckt->flow.port16[1] = udp->dest;
	} else {
		pckt->flow.port16[0] = udp->dest;
		pckt->flow.port16[1] = udp->source;
	}
	return 1;
}

static __attribute__ ((noinline))
bool parse_tcp(void *data, void *data_end,
	       bool is_ipv6, struct packet_description *pckt)
{

	bool is_icmp = !((pckt->flags & (1 << 0)) == 0);
	__u64 off = calc_offset(is_ipv6, is_icmp);
	struct tcphdr *tcp;

	tcp = data + off;
	if (tcp + 1 > data_end)
		return 0;
	if (tcp->syn)
		pckt->flags |= (1 << 1);
	if (!is_icmp) {
		pckt->flow.port16[0] = tcp->source;
		pckt->flow.port16[1] = tcp->dest;
	} else {
		pckt->flow.port16[0] = tcp->dest;
		pckt->flow.port16[1] = tcp->source;
	}
	return 1;
}

static __attribute__ ((noinline))
bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval,
	      struct packet_description *pckt,
	      struct real_definition *dst, __u32 pkt_bytes)
{
	struct eth_hdr *new_eth;
	struct eth_hdr *old_eth;
	struct ipv6hdr *ip6h;
	__u32 ip_suffix;
	void *data_end;
	void *data;

	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
		return 0;
	data = (void *)(long)xdp->data;
	data_end = (void *)(long)xdp->data_end;
	new_eth = data;
	ip6h = data + sizeof(struct eth_hdr);
	old_eth = data + sizeof(struct ipv6hdr);
	if (new_eth + 1 > data_end ||
	    old_eth + 1 > data_end || ip6h + 1 > data_end)
		return 0;
	memcpy(new_eth->eth_dest, cval->mac, 6);
	memcpy(new_eth->eth_source, old_eth->eth_dest, 6);
	new_eth->eth_proto = 56710;
	ip6h->version = 6;
	ip6h->priority = 0;
	memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));

	ip6h->nexthdr = IPPROTO_IPV6;
	ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0];
	ip6h->payload_len =
	    __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr));
	ip6h->hop_limit = 4;

	ip6h->saddr.in6_u.u6_addr32[0] = 1;
	ip6h->saddr.in6_u.u6_addr32[1] = 2;
	ip6h->saddr.in6_u.u6_addr32[2] = 3;
	ip6h->saddr.in6_u.u6_addr32[3] = ip_suffix;
	memcpy(ip6h->daddr.in6_u.u6_addr32, dst->dstv6, 16);
	return 1;
}

static __attribute__ ((noinline))
bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
	      struct packet_description *pckt,
	      struct real_definition *dst, __u32 pkt_bytes)
{

	__u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]);
	struct eth_hdr *new_eth;
	struct eth_hdr *old_eth;
	__u16 *next_iph_u16;
	struct iphdr *iph;
	__u32 csum = 0;
	void *data_end;
	void *data;

	ip_suffix <<= 15;
	ip_suffix ^= pckt->flow.src;
	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
		return 0;
	data = (void *)(long)xdp->data;
	data_end = (void *)(long)xdp->data_end;
	new_eth = data;
	iph = data + sizeof(struct eth_hdr);
	old_eth = data + sizeof(struct iphdr);
	if (new_eth + 1 > data_end ||
	    old_eth + 1 > data_end || iph + 1 > data_end)
		return 0;
	memcpy(new_eth->eth_dest, cval->mac, 6);
	memcpy(new_eth->eth_source, old_eth->eth_dest, 6);
	new_eth->eth_proto = 8;
	iph->version = 4;
	iph->ihl = 5;
	iph->frag_off = 0;
	iph->protocol = IPPROTO_IPIP;
	iph->check = 0;
	iph->tos = 1;
	iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr));
	/* don't update iph->daddr, since it will overwrite old eth_proto
	 * and multiple iterations of bpf_prog_run() will fail
	 */

	iph->saddr = ((0xFFFF0000 & ip_suffix) | 4268) ^ dst->dst;
	iph->ttl = 4;

	next_iph_u16 = (__u16 *) iph;
#pragma clang loop unroll(full)
	for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
		csum += *next_iph_u16++;
	iph->check = ~((csum & 0xffff) + (csum >> 16));
	if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr)))
		return 0;
	return 1;
}

static __attribute__ ((noinline))
bool decap_v6(struct xdp_md *xdp, void **data, void **data_end, bool inner_v4)
{
	struct eth_hdr *new_eth;
	struct eth_hdr *old_eth;

	old_eth = *data;
	new_eth = *data + sizeof(struct ipv6hdr);
	memcpy(new_eth->eth_source, old_eth->eth_source, 6);
	memcpy(new_eth->eth_dest, old_eth->eth_dest, 6);
	if (inner_v4)
		new_eth->eth_proto = 8;
	else
		new_eth->eth_proto = 56710;
	if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct ipv6hdr)))
		return 0;
	*data = (void *)(long)xdp->data;
	*data_end = (void *)(long)xdp->data_end;
	return 1;
}

static __attribute__ ((noinline))
bool decap_v4(struct xdp_md *xdp, void **data, void **data_end)
{
	struct eth_hdr *new_eth;
	struct eth_hdr *old_eth;

	old_eth = *data;
	new_eth = *data + sizeof(struct iphdr);
	memcpy(new_eth->eth_source, old_eth->eth_source, 6);
	memcpy(new_eth->eth_dest, old_eth->eth_dest, 6);
	new_eth->eth_proto = 8;
	if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr)))
		return 0;
	*data = (void *)(long)xdp->data;
	*data_end = (void *)(long)xdp->data_end;
	return 1;
}

static __attribute__ ((noinline))
int swap_mac_and_send(void *data, void *data_end)
{
	unsigned char tmp_mac[6];
	struct eth_hdr *eth;

	eth = data;
	memcpy(tmp_mac, eth->eth_source, 6);
	memcpy(eth->eth_source, eth->eth_dest, 6);
	memcpy(eth->eth_dest, tmp_mac, 6);
	return XDP_TX;
}

static __attribute__ ((noinline))
int send_icmp_reply(void *data, void *data_end)
{
	struct icmphdr *icmp_hdr;
	__u16 *next_iph_u16;
	__u32 tmp_addr = 0;
	struct iphdr *iph;
	__u32 csum1 = 0;
	__u32 csum = 0;
	__u64 off = 0;

	if (data + sizeof(struct eth_hdr)
	     + sizeof(struct iphdr) + sizeof(struct icmphdr) > data_end)
		return XDP_DROP;
	off += sizeof(struct eth_hdr);
	iph = data + off;
	off += sizeof(struct iphdr);
	icmp_hdr = data + off;
	icmp_hdr->type = 0;
	icmp_hdr->checksum += 0x0007;
	iph->ttl = 4;
	tmp_addr = iph->daddr;
	iph->daddr = iph->saddr;
	iph->saddr = tmp_addr;
	iph->check = 0;
	next_iph_u16 = (__u16 *) iph;
#pragma clang loop unroll(full)
	for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
		csum += *next_iph_u16++;
	iph->check = ~((csum & 0xffff) + (csum >> 16));
	return swap_mac_and_send(data, data_end);
}

static __attribute__ ((noinline))
int send_icmp6_reply(void *data, void *data_end)
{
	struct icmp6hdr *icmp_hdr;
	struct ipv6hdr *ip6h;
	__be32 tmp_addr[4];
	__u64 off = 0;

	if (data + sizeof(struct eth_hdr)
	     + sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) > data_end)
		return XDP_DROP;
	off += sizeof(struct eth_hdr);
	ip6h = data + off;
	off += sizeof(struct ipv6hdr);
	icmp_hdr = data + off;
	icmp_hdr->icmp6_type = 129;
	icmp_hdr->icmp6_cksum -= 0x0001;
	ip6h->hop_limit = 4;
	memcpy(tmp_addr, ip6h->saddr.in6_u.u6_addr32, 16);
	memcpy(ip6h->saddr.in6_u.u6_addr32, ip6h->daddr.in6_u.u6_addr32, 16);
	memcpy(ip6h->daddr.in6_u.u6_addr32, tmp_addr, 16);
	return swap_mac_and_send(data, data_end);
}

static __attribute__ ((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 XDP_DROP;
	if (icmp_hdr->icmp6_type == 128)
		return send_icmp6_reply(data, data_end);
	if (icmp_hdr->icmp6_type != 3)
		return XDP_PASS;
	off += sizeof(struct icmp6hdr);
	ip6h = data + off;
	if (ip6h + 1 > data_end)
		return XDP_DROP;
	pckt->flow.proto = ip6h->nexthdr;
	pckt->flags |= (1 << 0);
	memcpy(pckt->flow.srcv6, ip6h->daddr.in6_u.u6_addr32, 16);
	memcpy(pckt->flow.dstv6, ip6h->saddr.in6_u.u6_addr32, 16);
	return -1;
}

static __attribute__ ((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 XDP_DROP;
	if (icmp_hdr->type == 8)
		return send_icmp_reply(data, data_end);
	if ((icmp_hdr->type != 3) || (icmp_hdr->code != 4))
		return XDP_PASS;
	off += sizeof(struct icmphdr);
	iph = data + off;
	if (iph + 1 > data_end)
		return XDP_DROP;
	if (iph->ihl != 5)
		return XDP_DROP;
	pckt->flow.proto = iph->protocol;
	pckt->flags |= (1 << 0);
	pckt->flow.src = iph->daddr;
	pckt->flow.dst = iph->saddr;
	return -1;
}

static __attribute__ ((noinline))
__u32 get_packet_hash(struct packet_description *pckt,
		      bool hash_16bytes)
{
	if (hash_16bytes)
		return jhash_2words(jhash(pckt->flow.srcv6, 16, 12),
				    pckt->flow.ports, 24);
	else
		return jhash_2words(pckt->flow.src, pckt->flow.ports,
				    24);
}

__attribute__ ((noinline))
static bool get_packet_dst(struct real_definition **real,
			   struct packet_description *pckt,
			   struct vip_meta *vip_info,
			   bool is_ipv6, void *lru_map)
{
	struct real_pos_lru new_dst_lru = { };
	bool hash_16bytes = is_ipv6;
	__u32 *real_pos, hash, key;
	__u64 cur_time;

	if (vip_info->flags & (1 << 2))
		hash_16bytes = 1;
	if (vip_info->flags & (1 << 3)) {
		pckt->flow.port16[0] = pckt->flow.port16[1];
		memset(pckt->flow.srcv6, 0, 16);
	}
	hash = get_packet_hash(pckt, hash_16bytes);
	if (hash != 0x358459b7 /* jhash of ipv4 packet */  &&
	    hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
		return 0;
	key = 2 * vip_info->vip_num + hash % 2;
	real_pos = bpf_map_lookup_elem(&ch_rings, &key);
	if (!real_pos)
		return 0;
	key = *real_pos;
	*real = bpf_map_lookup_elem(&reals, &key);
	if (!(*real))
		return 0;
	if (!(vip_info->flags & (1 << 1))) {
		__u32 conn_rate_key = 512 + 2;
		struct lb_stats *conn_rate_stats =
		    bpf_map_lookup_elem(&stats, &conn_rate_key);

		if (!conn_rate_stats)
			return 1;
		cur_time = bpf_ktime_get_ns();
		if ((cur_time - conn_rate_stats->v2) >> 32 > 0xffFFFF) {
			conn_rate_stats->v1 = 1;
			conn_rate_stats->v2 = cur_time;
		} else {
			conn_rate_stats->v1 += 1;
			if (conn_rate_stats->v1 >= 1)
				return 1;
		}
		if (pckt->flow.proto == IPPROTO_UDP)
			new_dst_lru.atime = cur_time;
		new_dst_lru.pos = key;
		bpf_map_update_elem(lru_map, &pckt->flow, &new_dst_lru, 0);
	}
	return 1;
}

__attribute__ ((noinline))
static void connection_table_lookup(struct real_definition **real,
				    struct packet_description *pckt,
				    void *lru_map)
{

	struct real_pos_lru *dst_lru;
	__u64 cur_time;
	__u32 key;

	dst_lru = bpf_map_lookup_elem(lru_map, &pckt->flow);
	if (!dst_lru)
		return;
	if (pckt->flow.proto == IPPROTO_UDP) {
		cur_time = bpf_ktime_get_ns();
		if (cur_time - dst_lru->atime > 300000)
			return;
		dst_lru->atime = cur_time;
	}
	key = dst_lru->pos;
	*real = bpf_map_lookup_elem(&reals, &key);
}

/* don't believe your eyes!
 * below function has 6 arguments whereas bpf and llvm allow maximum of 5
 * but since it's _static_ llvm can optimize one argument away
 */
__attribute__ ((noinline))
static int process_l3_headers_v6(struct packet_description *pckt,
				 __u8 *protocol, __u64 off,
				 __u16 *pkt_bytes, void *data,
				 void *data_end)
{
	struct ipv6hdr *ip6h;
	__u64 iph_len;
	int action;

	ip6h = data + off;
	if (ip6h + 1 > data_end)
		return XDP_DROP;
	iph_len = sizeof(struct ipv6hdr);
	*protocol = ip6h->nexthdr;
	pckt->flow.proto = *protocol;
	*pkt_bytes = __builtin_bswap16(ip6h->payload_len);
	off += iph_len;
	if (*protocol == 45) {
		return XDP_DROP;
	} else if (*protocol == 59) {
		action = parse_icmpv6(data, data_end, off, pckt);
		if (action >= 0)
			return action;
	} else {
		memcpy(pckt->flow.srcv6, ip6h->saddr.in6_u.u6_addr32, 16);
		memcpy(pckt->flow.dstv6, ip6h->daddr.in6_u.u6_addr32, 16);
	}
	return -1;
}

__attribute__ ((noinline))
static int process_l3_headers_v4(struct packet_description *pckt,
				 __u8 *protocol, __u64 off,
				 __u16 *pkt_bytes, void *data,
				 void *data_end)
{
	struct iphdr *iph;
	__u64 iph_len;
	int action;

	iph = data + off;
	if (iph + 1 > data_end)
		return XDP_DROP;
	if (iph->ihl != 5)
		return XDP_DROP;
	*protocol = iph->protocol;
	pckt->flow.proto = *protocol;
	*pkt_bytes = __builtin_bswap16(iph->tot_len);
	off += 20;
	if (iph->frag_off & 65343)
		return XDP_DROP;
	if (*protocol == IPPROTO_ICMP) {
		action = parse_icmp(data, data_end, off, pckt);
		if (action >= 0)
			return action;
	} else {
		pckt->flow.src = iph->saddr;
		pckt->flow.dst = iph->daddr;
	}
	return -1;
}

__attribute__ ((noinline))
static int process_packet(void *data, __u64 off, void *data_end,
			  bool is_ipv6, struct xdp_md *xdp)
{

	struct real_definition *dst = NULL;
	struct packet_description pckt = { };
	struct vip_definition vip = { };
	struct lb_stats *data_stats;
	struct eth_hdr *eth = data;
	void *lru_map = &lru_cache;
	struct vip_meta *vip_info;
	__u32 lru_stats_key = 513;
	__u32 mac_addr_pos = 0;
	__u32 stats_key = 512;
	struct ctl_value *cval;
	__u16 pkt_bytes;
	__u64 iph_len;
	__u8 protocol;
	__u32 vip_num;
	int action;

	if (is_ipv6)
		action = process_l3_headers_v6(&pckt, &protocol, off,
					       &pkt_bytes, data, data_end);
	else
		action = process_l3_headers_v4(&pckt, &protocol, off,
					       &pkt_bytes, data, data_end);
	if (action >= 0)
		return action;
	protocol = pckt.flow.proto;
	if (protocol == IPPROTO_TCP) {
		if (!parse_tcp(data, data_end, is_ipv6, &pckt))
			return XDP_DROP;
	} else if (protocol == IPPROTO_UDP) {
		if (!parse_udp(data, data_end, is_ipv6, &pckt))
			return XDP_DROP;
	} else {
		return XDP_TX;
	}

	if (is_ipv6)
		memcpy(vip.vipv6, pckt.flow.dstv6, 16);
	else
		vip.vip = pckt.flow.dst;
	vip.port = pckt.flow.port16[1];
	vip.proto = pckt.flow.proto;
	vip_info = bpf_map_lookup_elem(&vip_map, &vip);
	if (!vip_info) {
		vip.port = 0;
		vip_info = bpf_map_lookup_elem(&vip_map, &vip);
		if (!vip_info)
			return XDP_PASS;
		if (!(vip_info->flags & (1 << 4)))
			pckt.flow.port16[1] = 0;
	}
	if (data_end - data > 1400)
		return XDP_DROP;
	data_stats = bpf_map_lookup_elem(&stats, &stats_key);
	if (!data_stats)
		return XDP_DROP;
	data_stats->v1 += 1;
	if (!dst) {
		if (vip_info->flags & (1 << 0))
			pckt.flow.port16[0] = 0;
		if (!(pckt.flags & (1 << 1)) && !(vip_info->flags & (1 << 1)))
			connection_table_lookup(&dst, &pckt, lru_map);
		if (dst)
			goto out;
		if (pckt.flow.proto == IPPROTO_TCP) {
			struct lb_stats *lru_stats =
			    bpf_map_lookup_elem(&stats, &lru_stats_key);

			if (!lru_stats)
				return XDP_DROP;
			if (pckt.flags & (1 << 1))
				lru_stats->v1 += 1;
			else
				lru_stats->v2 += 1;
		}
		if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6, lru_map))
			return XDP_DROP;
		data_stats->v2 += 1;
	}
out:
	cval = bpf_map_lookup_elem(&ctl_array, &mac_addr_pos);
	if (!cval)
		return XDP_DROP;
	if (dst->flags & (1 << 0)) {
		if (!encap_v6(xdp, cval, &pckt, dst, pkt_bytes))
			return XDP_DROP;
	} else {
		if (!encap_v4(xdp, cval, &pckt, dst, pkt_bytes))
			return XDP_DROP;
	}
	vip_num = vip_info->vip_num;
	data_stats = bpf_map_lookup_elem(&stats, &vip_num);
	if (!data_stats)
		return XDP_DROP;
	data_stats->v1 += 1;
	data_stats->v2 += pkt_bytes;

	data = (void *)(long)xdp->data;
	data_end = (void *)(long)xdp->data_end;
	if (data + 4 > data_end)
		return XDP_DROP;
	*(u32 *)data = dst->dst;
	return XDP_DROP;
}

__attribute__ ((section("xdp-test"), used))
int balancer_ingress(struct xdp_md *ctx)
{
	void *data = (void *)(long)ctx->data;
	void *data_end = (void *)(long)ctx->data_end;
	struct eth_hdr *eth = data;
	__u32 eth_proto;
	__u32 nh_off;

	nh_off = sizeof(struct eth_hdr);
	if (data + nh_off > data_end)
		return XDP_DROP;
	eth_proto = eth->eth_proto;
	if (eth_proto == 8)
		return process_packet(data, nh_off, data_end, 0, ctx);
	else if (eth_proto == 56710)
		return process_packet(data, nh_off, data_end, 1, ctx);
	else
		return XDP_DROP;
}

char _license[] __attribute__ ((section("license"), used)) = "GPL";
int _version __attribute__ ((section("version"), used)) = 1;