aboutsummaryrefslogtreecommitdiffstats
path: root/examples/ip_reassembly/main.c
blob: e096b9173a91f44ba836b031721e4faf0f499a13 (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
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
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <inttypes.h>
#include <sys/types.h>
#include <string.h>
#include <sys/queue.h>
#include <stdarg.h>
#include <errno.h>
#include <getopt.h>
#include <signal.h>
#include <sys/param.h>

#include <rte_common.h>
#include <rte_byteorder.h>
#include <rte_log.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_memzone.h>
#include <rte_eal.h>
#include <rte_per_lcore.h>
#include <rte_launch.h>
#include <rte_atomic.h>
#include <rte_cycles.h>
#include <rte_prefetch.h>
#include <rte_lcore.h>
#include <rte_per_lcore.h>
#include <rte_branch_prediction.h>
#include <rte_interrupts.h>
#include <rte_pci.h>
#include <rte_random.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
#include <rte_malloc.h>
#include <rte_ip.h>
#include <rte_tcp.h>
#include <rte_udp.h>
#include <rte_string_fns.h>
#include <rte_lpm.h>
#include <rte_lpm6.h>

#include <rte_ip_frag.h>

#define MAX_PKT_BURST 32


#define RTE_LOGTYPE_IP_RSMBL RTE_LOGTYPE_USER1

#define MAX_JUMBO_PKT_LEN  9600

#define	BUF_SIZE	RTE_MBUF_DEFAULT_DATAROOM
#define MBUF_SIZE	\
	(BUF_SIZE + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)

#define NB_MBUF 8192

/* allow max jumbo frame 9.5 KB */
#define JUMBO_FRAME_MAX_SIZE	0x2600

#define	MAX_FLOW_NUM	UINT16_MAX
#define	MIN_FLOW_NUM	1
#define	DEF_FLOW_NUM	0x1000

/* TTL numbers are in ms. */
#define	MAX_FLOW_TTL	(3600 * MS_PER_S)
#define	MIN_FLOW_TTL	1
#define	DEF_FLOW_TTL	MS_PER_S

#define MAX_FRAG_NUM RTE_LIBRTE_IP_FRAG_MAX_FRAG

/* Should be power of two. */
#define	IP_FRAG_TBL_BUCKET_ENTRIES	16

static uint32_t max_flow_num = DEF_FLOW_NUM;
static uint32_t max_flow_ttl = DEF_FLOW_TTL;

#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */

#define NB_SOCKETS 8

/* Configure how many packets ahead to prefetch, when reading packets */
#define PREFETCH_OFFSET	3

/*
 * Configurable number of RX/TX ring descriptors
 */
#define RTE_TEST_RX_DESC_DEFAULT 128
#define RTE_TEST_TX_DESC_DEFAULT 512

static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT;
static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT;

/* ethernet addresses of ports */
static struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];

#ifndef IPv4_BYTES
#define IPv4_BYTES_FMT "%" PRIu8 ".%" PRIu8 ".%" PRIu8 ".%" PRIu8
#define IPv4_BYTES(addr) \
		(uint8_t) (((addr) >> 24) & 0xFF),\
		(uint8_t) (((addr) >> 16) & 0xFF),\
		(uint8_t) (((addr) >> 8) & 0xFF),\
		(uint8_t) ((addr) & 0xFF)
#endif

#ifndef IPv6_BYTES
#define IPv6_BYTES_FMT "%02x%02x:%02x%02x:%02x%02x:%02x%02x:"\
                       "%02x%02x:%02x%02x:%02x%02x:%02x%02x"
#define IPv6_BYTES(addr) \
	addr[0],  addr[1], addr[2],  addr[3], \
	addr[4],  addr[5], addr[6],  addr[7], \
	addr[8],  addr[9], addr[10], addr[11],\
	addr[12], addr[13],addr[14], addr[15]
#endif

#define IPV6_ADDR_LEN 16

/* mask of enabled ports */
static uint32_t enabled_port_mask = 0;

static int rx_queue_per_lcore = 1;

struct mbuf_table {
	uint32_t len;
	uint32_t head;
	uint32_t tail;
	struct rte_mbuf *m_table[0];
};

struct rx_queue {
	struct rte_ip_frag_tbl *frag_tbl;
	struct rte_mempool *pool;
	struct rte_lpm *lpm;
	struct rte_lpm6 *lpm6;
	uint8_t portid;
};

struct tx_lcore_stat {
	uint64_t call;
	uint64_t drop;
	uint64_t queue;
	uint64_t send;
};

#define MAX_RX_QUEUE_PER_LCORE 16
#define MAX_TX_QUEUE_PER_PORT 16
#define MAX_RX_QUEUE_PER_PORT 128

struct lcore_queue_conf {
	uint16_t n_rx_queue;
	struct rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE];
	uint16_t tx_queue_id[RTE_MAX_ETHPORTS];
	struct rte_ip_frag_death_row death_row;
	struct mbuf_table *tx_mbufs[RTE_MAX_ETHPORTS];
	struct tx_lcore_stat tx_stat;
} __rte_cache_aligned;
static struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE];

static struct rte_eth_conf port_conf = {
	.rxmode = {
		.mq_mode        = ETH_MQ_RX_RSS,
		.max_rx_pkt_len = JUMBO_FRAME_MAX_SIZE,
		.split_hdr_size = 0,
		.header_split   = 0, /**< Header Split disabled */
		.hw_ip_checksum = 1, /**< IP checksum offload enabled */
		.hw_vlan_filter = 0, /**< VLAN filtering disabled */
		.jumbo_frame    = 1, /**< Jumbo Frame Support disabled */
		.hw_strip_crc   = 1, /**< CRC stripped by hardware */
	},
	.rx_adv_conf = {
			.rss_conf = {
				.rss_key = NULL,
				.rss_hf = ETH_RSS_IP,
		},
	},
	.txmode = {
		.mq_mode = ETH_MQ_TX_NONE,
	},
};

/*
 * IPv4 forwarding table
 */
struct l3fwd_ipv4_route {
	uint32_t ip;
	uint8_t  depth;
	uint8_t  if_out;
};

struct l3fwd_ipv4_route l3fwd_ipv4_route_array[] = {
		{IPv4(100,10,0,0), 16, 0},
		{IPv4(100,20,0,0), 16, 1},
		{IPv4(100,30,0,0), 16, 2},
		{IPv4(100,40,0,0), 16, 3},
		{IPv4(100,50,0,0), 16, 4},
		{IPv4(100,60,0,0), 16, 5},
		{IPv4(100,70,0,0), 16, 6},
		{IPv4(100,80,0,0), 16, 7},
};

/*
 * IPv6 forwarding table
 */

struct l3fwd_ipv6_route {
	uint8_t ip[IPV6_ADDR_LEN];
	uint8_t depth;
	uint8_t if_out;
};

static struct l3fwd_ipv6_route l3fwd_ipv6_route_array[] = {
	{{1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 0},
	{{2,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 1},
	{{3,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 2},
	{{4,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 3},
	{{5,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 4},
	{{6,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 5},
	{{7,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 6},
	{{8,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}, 48, 7},
};

#define LPM_MAX_RULES         1024
#define LPM6_MAX_RULES         1024
#define LPM6_NUMBER_TBL8S (1 << 16)

struct rte_lpm6_config lpm6_config = {
		.max_rules = LPM6_MAX_RULES,
		.number_tbl8s = LPM6_NUMBER_TBL8S,
		.flags = 0
};

static struct rte_lpm *socket_lpm[RTE_MAX_NUMA_NODES];
static struct rte_lpm6 *socket_lpm6[RTE_MAX_NUMA_NODES];

#ifdef RTE_LIBRTE_IP_FRAG_TBL_STAT
#define TX_LCORE_STAT_UPDATE(s, f, v)   ((s)->f += (v))
#else
#define TX_LCORE_STAT_UPDATE(s, f, v)   do {} while (0)
#endif /* RTE_LIBRTE_IP_FRAG_TBL_STAT */

/*
 * If number of queued packets reached given threahold, then
 * send burst of packets on an output interface.
 */
static inline uint32_t
send_burst(struct lcore_queue_conf *qconf, uint32_t thresh, uint8_t port)
{
	uint32_t fill, len, k, n;
	struct mbuf_table *txmb;

	txmb = qconf->tx_mbufs[port];
	len = txmb->len;

	if ((int32_t)(fill = txmb->head - txmb->tail) < 0)
		fill += len;

	if (fill >= thresh) {
		n = RTE_MIN(len - txmb->tail, fill);

		k = rte_eth_tx_burst(port, qconf->tx_queue_id[port],
			txmb->m_table + txmb->tail, (uint16_t)n);

		TX_LCORE_STAT_UPDATE(&qconf->tx_stat, call, 1);
		TX_LCORE_STAT_UPDATE(&qconf->tx_stat, send, k);

		fill -= k;
		if ((txmb->tail += k) == len)
			txmb->tail = 0;
	}

	return fill;
}

/* Enqueue a single packet, and send burst if queue is filled */
static inline int
send_single_packet(struct rte_mbuf *m, uint8_t port)
{
	uint32_t fill, lcore_id, len;
	struct lcore_queue_conf *qconf;
	struct mbuf_table *txmb;

	lcore_id = rte_lcore_id();
	qconf = &lcore_queue_conf[lcore_id];

	txmb = qconf->tx_mbufs[port];
	len = txmb->len;

	fill = send_burst(qconf, MAX_PKT_BURST, port);

	if (fill == len - 1) {
		TX_LCORE_STAT_UPDATE(&qconf->tx_stat, drop, 1);
		rte_pktmbuf_free(txmb->m_table[txmb->tail]);
		if (++txmb->tail == len)
			txmb->tail = 0;
	}

	TX_LCORE_STAT_UPDATE(&qconf->tx_stat, queue, 1);
	txmb->m_table[txmb->head] = m;
	if(++txmb->head == len)
		txmb->head = 0;

	return 0;
}

static inline void
reassemble(struct rte_mbuf *m, uint8_t portid, uint32_t queue,
	struct lcore_queue_conf *qconf, uint64_t tms)
{
	struct ether_hdr *eth_hdr;
	struct rte_ip_frag_tbl *tbl;
	struct rte_ip_frag_death_row *dr;
	struct rx_queue *rxq;
	void *d_addr_bytes;
	uint32_t next_hop_ipv4;
	uint8_t next_hop_ipv6, dst_port;

	rxq = &qconf->rx_queue_list[queue];

	eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);

	dst_port = portid;

	/* if packet is IPv4 */
	if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) {
		struct ipv4_hdr *ip_hdr;
		uint32_t ip_dst;

		ip_hdr = (struct ipv4_hdr *)(eth_hdr + 1);

		 /* if it is a fragmented packet, then try to reassemble. */
		if (rte_ipv4_frag_pkt_is_fragmented(ip_hdr)) {
			struct rte_mbuf *mo;

			tbl = rxq->frag_tbl;
			dr = &qconf->death_row;

			/* prepare mbuf: setup l2_len/l3_len. */
			m->l2_len = sizeof(*eth_hdr);
			m->l3_len = sizeof(*ip_hdr);

			/* process this fragment. */
			mo = rte_ipv4_frag_reassemble_packet(tbl, dr, m, tms, ip_hdr);
			if (mo == NULL)
				/* no packet to send out. */
				return;

			/* we have our packet reassembled. */
			if (mo != m) {
				m = mo;
				eth_hdr = rte_pktmbuf_mtod(m,
					struct ether_hdr *);
				ip_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
			}
		}
		ip_dst = rte_be_to_cpu_32(ip_hdr->dst_addr);

		/* Find destination port */
		if (rte_lpm_lookup(rxq->lpm, ip_dst, &next_hop_ipv4) == 0 &&
				(enabled_port_mask & 1 << next_hop_ipv4) != 0) {
			dst_port = next_hop_ipv4;
		}

		eth_hdr->ether_type = rte_be_to_cpu_16(ETHER_TYPE_IPv4);
	} else if (RTE_ETH_IS_IPV6_HDR(m->packet_type)) {
		/* if packet is IPv6 */
		struct ipv6_extension_fragment *frag_hdr;
		struct ipv6_hdr *ip_hdr;

		ip_hdr = (struct ipv6_hdr *)(eth_hdr + 1);

		frag_hdr = rte_ipv6_frag_get_ipv6_fragment_header(ip_hdr);

		if (frag_hdr != NULL) {
			struct rte_mbuf *mo;

			tbl = rxq->frag_tbl;
			dr  = &qconf->death_row;

			/* prepare mbuf: setup l2_len/l3_len. */
			m->l2_len = sizeof(*eth_hdr);
			m->l3_len = sizeof(*ip_hdr) + sizeof(*frag_hdr);

			mo = rte_ipv6_frag_reassemble_packet(tbl, dr, m, tms, ip_hdr, frag_hdr);
			if (mo == NULL)
				return;

			if (mo != m) {
				m = mo;
				eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
				ip_hdr = (struct ipv6_hdr *)(eth_hdr + 1);
			}
		}

		/* Find destination port */
		if (rte_lpm6_lookup(rxq->lpm6, ip_hdr->dst_addr, &next_hop_ipv6) == 0 &&
				(enabled_port_mask & 1 << next_hop_ipv6) != 0) {
			dst_port = next_hop_ipv6;
		}

		eth_hdr->ether_type = rte_be_to_cpu_16(ETHER_TYPE_IPv6);
	}
	/* if packet wasn't IPv4 or IPv6, it's forwarded to the port it came from */

	/* 02:00:00:00:00:xx */
	d_addr_bytes = &eth_hdr->d_addr.addr_bytes[0];
	*((uint64_t *)d_addr_bytes) = 0x000000000002 + ((uint64_t)dst_port << 40);

	/* src addr */
	ether_addr_copy(&ports_eth_addr[dst_port], &eth_hdr->s_addr);

	send_single_packet(m, dst_port);
}

/* main processing loop */
static int
main_loop(__attribute__((unused)) void *dummy)
{
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
	unsigned lcore_id;
	uint64_t diff_tsc, cur_tsc, prev_tsc;
	int i, j, nb_rx;
	uint8_t portid;
	struct lcore_queue_conf *qconf;
	const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;

	prev_tsc = 0;

	lcore_id = rte_lcore_id();
	qconf = &lcore_queue_conf[lcore_id];

	if (qconf->n_rx_queue == 0) {
		RTE_LOG(INFO, IP_RSMBL, "lcore %u has nothing to do\n", lcore_id);
		return 0;
	}

	RTE_LOG(INFO, IP_RSMBL, "entering main loop on lcore %u\n", lcore_id);

	for (i = 0; i < qconf->n_rx_queue; i++) {

		portid = qconf->rx_queue_list[i].portid;
		RTE_LOG(INFO, IP_RSMBL, " -- lcoreid=%u portid=%hhu\n", lcore_id,
			portid);
	}

	while (1) {

		cur_tsc = rte_rdtsc();

		/*
		 * TX burst queue drain
		 */
		diff_tsc = cur_tsc - prev_tsc;
		if (unlikely(diff_tsc > drain_tsc)) {

			/*
			 * This could be optimized (use queueid instead of
			 * portid), but it is not called so often
			 */
			for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) {
				if ((enabled_port_mask & (1 << portid)) != 0)
					send_burst(qconf, 1, portid);
			}

			prev_tsc = cur_tsc;
		}

		/*
		 * Read packet from RX queues
		 */
		for (i = 0; i < qconf->n_rx_queue; ++i) {

			portid = qconf->rx_queue_list[i].portid;

			nb_rx = rte_eth_rx_burst(portid, 0, pkts_burst,
				MAX_PKT_BURST);

			/* Prefetch first packets */
			for (j = 0; j < PREFETCH_OFFSET && j < nb_rx; j++) {
				rte_prefetch0(rte_pktmbuf_mtod(
						pkts_burst[j], void *));
			}

			/* Prefetch and forward already prefetched packets */
			for (j = 0; j < (nb_rx - PREFETCH_OFFSET); j++) {
				rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[
					j + PREFETCH_OFFSET], void *));
				reassemble(pkts_burst[j], portid,
					i, qconf, cur_tsc);
			}

			/* Forward remaining prefetched packets */
			for (; j < nb_rx; j++) {
				reassemble(pkts_burst[j], portid,
					i, qconf, cur_tsc);
			}

			rte_ip_frag_free_death_row(&qconf->death_row,
				PREFETCH_OFFSET);
		}
	}
}

/* display usage */
static void
print_usage(const char *prgname)
{
	printf("%s [EAL options] -- -p PORTMASK [-q NQ]"
		"  [--max-pkt-len PKTLEN]"
		"  [--maxflows=<flows>]  [--flowttl=<ttl>[(s|ms)]]\n"
		"  -p PORTMASK: hexadecimal bitmask of ports to configure\n"
		"  -q NQ: number of RX queues per lcore\n"
		"  --maxflows=<flows>: optional, maximum number of flows "
		"supported\n"
		"  --flowttl=<ttl>[(s|ms)]: optional, maximum TTL for each "
		"flow\n",
		prgname);
}

static uint32_t
parse_flow_num(const char *str, uint32_t min, uint32_t max, uint32_t *val)
{
	char *end;
	uint64_t v;

	/* parse decimal string */
	errno = 0;
	v = strtoul(str, &end, 10);
	if (errno != 0 || *end != '\0')
		return -EINVAL;

	if (v < min || v > max)
		return -EINVAL;

	*val = (uint32_t)v;
	return 0;
}

static int
parse_flow_ttl(const char *str, uint32_t min, uint32_t max, uint32_t *val)
{
	char *end;
	uint64_t v;

	static const char frmt_sec[] = "s";
	static const char frmt_msec[] = "ms";

	/* parse decimal string */
	errno = 0;
	v = strtoul(str, &end, 10);
	if (errno != 0)
		return -EINVAL;

	if (*end != '\0') {
		if (strncmp(frmt_sec, end, sizeof(frmt_sec)) == 0)
			v *= MS_PER_S;
		else if (strncmp(frmt_msec, end, sizeof (frmt_msec)) != 0)
			return -EINVAL;
	}

	if (v < min || v > max)
		return -EINVAL;

	*val = (uint32_t)v;
	return 0;
}

static int
parse_portmask(const char *portmask)
{
	char *end = NULL;
	unsigned long pm;

	/* parse hexadecimal string */
	pm = strtoul(portmask, &end, 16);
	if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0'))
		return -1;

	if (pm == 0)
		return -1;

	return pm;
}

static int
parse_nqueue(const char *q_arg)
{
	char *end = NULL;
	unsigned long n;

	printf("%p\n", q_arg);

	/* parse hexadecimal string */
	n = strtoul(q_arg, &end, 10);
	if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0'))
		return -1;
	if (n == 0)
		return -1;
	if (n >= MAX_RX_QUEUE_PER_LCORE)
		return -1;

	return n;
}

/* Parse the argument given in the command line of the application */
static int
parse_args(int argc, char **argv)
{
	int opt, ret;
	char **argvopt;
	int option_index;
	char *prgname = argv[0];
	static struct option lgopts[] = {
		{"max-pkt-len", 1, 0, 0},
		{"maxflows", 1, 0, 0},
		{"flowttl", 1, 0, 0},
		{NULL, 0, 0, 0}
	};

	argvopt = argv;

	while ((opt = getopt_long(argc, argvopt, "p:q:",
				lgopts, &option_index)) != EOF) {

		switch (opt) {
		/* portmask */
		case 'p':
			enabled_port_mask = parse_portmask(optarg);
			if (enabled_port_mask == 0) {
				printf("invalid portmask\n");
				print_usage(prgname);
				return -1;
			}
			break;

		/* nqueue */
		case 'q':
			rx_queue_per_lcore = parse_nqueue(optarg);
			if (rx_queue_per_lcore < 0) {
				printf("invalid queue number\n");
				print_usage(prgname);
				return -1;
			}
			break;

		/* long options */
		case 0:
			if (!strncmp(lgopts[option_index].name,
					"maxflows", 8)) {
				if ((ret = parse_flow_num(optarg, MIN_FLOW_NUM,
						MAX_FLOW_NUM,
						&max_flow_num)) != 0) {
					printf("invalid value: \"%s\" for "
						"parameter %s\n",
						optarg,
						lgopts[option_index].name);
					print_usage(prgname);
					return ret;
				}
			}

			if (!strncmp(lgopts[option_index].name, "flowttl", 7)) {
				if ((ret = parse_flow_ttl(optarg, MIN_FLOW_TTL,
						MAX_FLOW_TTL,
						&max_flow_ttl)) != 0) {
					printf("invalid value: \"%s\" for "
						"parameter %s\n",
						optarg,
						lgopts[option_index].name);
					print_usage(prgname);
					return ret;
				}
			}

			break;

		default:
			print_usage(prgname);
			return -1;
		}
	}

	if (optind >= 0)
		argv[optind-1] = prgname;

	ret = optind-1;
	optind = 0; /* reset getopt lib */
	return ret;
}

static void
print_ethaddr(const char *name, const struct ether_addr *eth_addr)
{
	char buf[ETHER_ADDR_FMT_SIZE];
	ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr);
	printf("%s%s", name, buf);
}

/* Check the link status of all ports in up to 9s, and print them finally */
static void
check_all_ports_link_status(uint8_t port_num, uint32_t port_mask)
{
#define CHECK_INTERVAL 100 /* 100ms */
#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */
	uint8_t portid, count, all_ports_up, print_flag = 0;
	struct rte_eth_link link;

	printf("\nChecking link status");
	fflush(stdout);
	for (count = 0; count <= MAX_CHECK_TIME; count++) {
		all_ports_up = 1;
		for (portid = 0; portid < port_num; portid++) {
			if ((port_mask & (1 << portid)) == 0)
				continue;
			memset(&link, 0, sizeof(link));
			rte_eth_link_get_nowait(portid, &link);
			/* print link status if flag set */
			if (print_flag == 1) {
				if (link.link_status)
					printf("Port %d Link Up - speed %u "
						"Mbps - %s\n", (uint8_t)portid,
						(unsigned)link.link_speed,
				(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
					("full-duplex") : ("half-duplex\n"));
				else
					printf("Port %d Link Down\n",
						(uint8_t)portid);
				continue;
			}
			/* clear all_ports_up flag if any link down */
			if (link.link_status == ETH_LINK_DOWN) {
				all_ports_up = 0;
				break;
			}
		}
		/* after finally printing all link status, get out */
		if (print_flag == 1)
			break;

		if (all_ports_up == 0) {
			printf(".");
			fflush(stdout);
			rte_delay_ms(CHECK_INTERVAL);
		}

		/* set the print_flag if all ports up or timeout */
		if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) {
			print_flag = 1;
			printf("\ndone\n");
		}
	}
}

static int
init_routing_table(void)
{
	struct rte_lpm *lpm;
	struct rte_lpm6 *lpm6;
	int socket, ret;
	unsigned i;

	for (socket = 0; socket < RTE_MAX_NUMA_NODES; socket++) {
		if (socket_lpm[socket]) {
			lpm = socket_lpm[socket];
			/* populate the LPM table */
			for (i = 0; i < RTE_DIM(l3fwd_ipv4_route_array); i++) {
				ret = rte_lpm_add(lpm,
					l3fwd_ipv4_route_array[i].ip,
					l3fwd_ipv4_route_array[i].depth,
					l3fwd_ipv4_route_array[i].if_out);

				if (ret < 0) {
					RTE_LOG(ERR, IP_RSMBL, "Unable to add entry %i to the l3fwd "
						"LPM table\n", i);
					return -1;
				}

				RTE_LOG(INFO, IP_RSMBL, "Socket %i: adding route " IPv4_BYTES_FMT
						"/%d (port %d)\n",
					socket,
					IPv4_BYTES(l3fwd_ipv4_route_array[i].ip),
					l3fwd_ipv4_route_array[i].depth,
					l3fwd_ipv4_route_array[i].if_out);
			}
		}

		if (socket_lpm6[socket]) {
			lpm6 = socket_lpm6[socket];
			/* populate the LPM6 table */
			for (i = 0; i < RTE_DIM(l3fwd_ipv6_route_array); i++) {
				ret = rte_lpm6_add(lpm6,
					l3fwd_ipv6_route_array[i].ip,
					l3fwd_ipv6_route_array[i].depth,
					l3fwd_ipv6_route_array[i].if_out);

				if (ret < 0) {
					RTE_LOG(ERR, IP_RSMBL, "Unable to add entry %i to the l3fwd "
						"LPM6 table\n", i);
					return -1;
				}

				RTE_LOG(INFO, IP_RSMBL, "Socket %i: adding route " IPv6_BYTES_FMT
						"/%d (port %d)\n",
					socket,
					IPv6_BYTES(l3fwd_ipv6_route_array[i].ip),
					l3fwd_ipv6_route_array[i].depth,
					l3fwd_ipv6_route_array[i].if_out);
			}
		}
	}
	return 0;
}

static int
setup_port_tbl(struct lcore_queue_conf *qconf, uint32_t lcore, int socket,
	uint32_t port)
{
	struct mbuf_table *mtb;
	uint32_t n;
	size_t sz;

	n = RTE_MAX(max_flow_num, 2UL * MAX_PKT_BURST);
	sz = sizeof (*mtb) + sizeof (mtb->m_table[0]) *  n;

	if ((mtb = rte_zmalloc_socket(__func__, sz, RTE_CACHE_LINE_SIZE,
			socket)) == NULL) {
		RTE_LOG(ERR, IP_RSMBL, "%s() for lcore: %u, port: %u "
			"failed to allocate %zu bytes\n",
			__func__, lcore, port, sz);
		return -1;
	}

	mtb->len = n;
	qconf->tx_mbufs[port] = mtb;

	return 0;
}

static int
setup_queue_tbl(struct rx_queue *rxq, uint32_t lcore, uint32_t queue)
{
	int socket;
	uint32_t nb_mbuf;
	uint64_t frag_cycles;
	char buf[RTE_MEMPOOL_NAMESIZE];

	socket = rte_lcore_to_socket_id(lcore);
	if (socket == SOCKET_ID_ANY)
		socket = 0;

	frag_cycles = (rte_get_tsc_hz() + MS_PER_S - 1) / MS_PER_S *
		max_flow_ttl;

	if ((rxq->frag_tbl = rte_ip_frag_table_create(max_flow_num,
			IP_FRAG_TBL_BUCKET_ENTRIES, max_flow_num, frag_cycles,
			socket)) == NULL) {
		RTE_LOG(ERR, IP_RSMBL, "ip_frag_tbl_create(%u) on "
			"lcore: %u for queue: %u failed\n",
			max_flow_num, lcore, queue);
		return -1;
	}

	/*
	 * At any given moment up to <max_flow_num * (MAX_FRAG_NUM)>
	 * mbufs could be stored int the fragment table.
	 * Plus, each TX queue can hold up to <max_flow_num> packets.
	 */

	nb_mbuf = RTE_MAX(max_flow_num, 2UL * MAX_PKT_BURST) * MAX_FRAG_NUM;
	nb_mbuf *= (port_conf.rxmode.max_rx_pkt_len + BUF_SIZE - 1) / BUF_SIZE;
	nb_mbuf *= 2; /* ipv4 and ipv6 */
	nb_mbuf += RTE_TEST_RX_DESC_DEFAULT + RTE_TEST_TX_DESC_DEFAULT;

	nb_mbuf = RTE_MAX(nb_mbuf, (uint32_t)NB_MBUF);

	snprintf(buf, sizeof(buf), "mbuf_pool_%u_%u", lcore, queue);

	if ((rxq->pool = rte_mempool_create(buf, nb_mbuf, MBUF_SIZE, 0,
			sizeof(struct rte_pktmbuf_pool_private),
			rte_pktmbuf_pool_init, NULL, rte_pktmbuf_init, NULL,
			socket, MEMPOOL_F_SP_PUT | MEMPOOL_F_SC_GET)) == NULL) {
		RTE_LOG(ERR, IP_RSMBL, "mempool_create(%s) failed", buf);
		return -1;
	}

	return 0;
}

static int
init_mem(void)
{
	char buf[PATH_MAX];
	struct rte_lpm *lpm;
	struct rte_lpm6 *lpm6;
	struct rte_lpm_config lpm_config;
	int socket;
	unsigned lcore_id;

	/* traverse through lcores and initialize structures on each socket */

	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {

		if (rte_lcore_is_enabled(lcore_id) == 0)
			continue;

		socket = rte_lcore_to_socket_id(lcore_id);

		if (socket == SOCKET_ID_ANY)
			socket = 0;

		if (socket_lpm[socket] == NULL) {
			RTE_LOG(INFO, IP_RSMBL, "Creating LPM table on socket %i\n", socket);
			snprintf(buf, sizeof(buf), "IP_RSMBL_LPM_%i", socket);

			lpm_config.max_rules = LPM_MAX_RULES;
			lpm_config.number_tbl8s = 256;
			lpm_config.flags = 0;

			lpm = rte_lpm_create(buf, socket, &lpm_config);
			if (lpm == NULL) {
				RTE_LOG(ERR, IP_RSMBL, "Cannot create LPM table\n");
				return -1;
			}
			socket_lpm[socket] = lpm;
		}

		if (socket_lpm6[socket] == NULL) {
			RTE_LOG(INFO, IP_RSMBL, "Creating LPM6 table on socket %i\n", socket);
			snprintf(buf, sizeof(buf), "IP_RSMBL_LPM_%i", socket);

			lpm6 = rte_lpm6_create(buf, socket, &lpm6_config);
			if (lpm6 == NULL) {
				RTE_LOG(ERR, IP_RSMBL, "Cannot create LPM table\n");
				return -1;
			}
			socket_lpm6[socket] = lpm6;
		}
	}

	return 0;
}

static void
queue_dump_stat(void)
{
	uint32_t i, lcore;
	const struct lcore_queue_conf *qconf;

	for (lcore = 0; lcore < RTE_MAX_LCORE; lcore++) {
		if (rte_lcore_is_enabled(lcore) == 0)
			continue;

		qconf = &lcore_queue_conf[lcore];
		for (i = 0; i < qconf->n_rx_queue; i++) {

			fprintf(stdout, " -- lcoreid=%u portid=%hhu "
				"frag tbl stat:\n",
				lcore,  qconf->rx_queue_list[i].portid);
			rte_ip_frag_table_statistics_dump(stdout,
					qconf->rx_queue_list[i].frag_tbl);
			fprintf(stdout, "TX bursts:\t%" PRIu64 "\n"
				"TX packets _queued:\t%" PRIu64 "\n"
				"TX packets dropped:\t%" PRIu64 "\n"
				"TX packets send:\t%" PRIu64 "\n",
				qconf->tx_stat.call,
				qconf->tx_stat.queue,
				qconf->tx_stat.drop,
				qconf->tx_stat.send);
		}
	}
}

static void
signal_handler(int signum)
{
	queue_dump_stat();
	if (signum != SIGUSR1)
		rte_exit(0, "received signal: %d, exiting\n", signum);
}

int
main(int argc, char **argv)
{
	struct lcore_queue_conf *qconf;
	struct rte_eth_dev_info dev_info;
	struct rte_eth_txconf *txconf;
	struct rx_queue *rxq;
	int ret, socket;
	unsigned nb_ports;
	uint16_t queueid;
	unsigned lcore_id = 0, rx_lcore_id = 0;
	uint32_t n_tx_queue, nb_lcores;
	uint8_t portid;

	/* init EAL */
	ret = rte_eal_init(argc, argv);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Invalid EAL parameters\n");
	argc -= ret;
	argv += ret;

	/* parse application arguments (after the EAL ones) */
	ret = parse_args(argc, argv);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Invalid IP reassembly parameters\n");

	nb_ports = rte_eth_dev_count();
	if (nb_ports == 0)
		rte_exit(EXIT_FAILURE, "No ports found!\n");

	nb_lcores = rte_lcore_count();

	/* initialize structures (mempools, lpm etc.) */
	if (init_mem() < 0)
		rte_panic("Cannot initialize memory structures!\n");

	/* check if portmask has non-existent ports */
	if (enabled_port_mask & ~(RTE_LEN2MASK(nb_ports, unsigned)))
		rte_exit(EXIT_FAILURE, "Non-existent ports in portmask!\n");

	/* initialize all ports */
	for (portid = 0; portid < nb_ports; portid++) {
		/* skip ports that are not enabled */
		if ((enabled_port_mask & (1 << portid)) == 0) {
			printf("\nSkipping disabled port %d\n", portid);
			continue;
		}

		qconf = &lcore_queue_conf[rx_lcore_id];

		/* get the lcore_id for this port */
		while (rte_lcore_is_enabled(rx_lcore_id) == 0 ||
			   qconf->n_rx_queue == (unsigned)rx_queue_per_lcore) {

			rx_lcore_id++;
			if (rx_lcore_id >= RTE_MAX_LCORE)
				rte_exit(EXIT_FAILURE, "Not enough cores\n");

			qconf = &lcore_queue_conf[rx_lcore_id];
		}

		socket = rte_lcore_to_socket_id(portid);
		if (socket == SOCKET_ID_ANY)
			socket = 0;

		queueid = qconf->n_rx_queue;
		rxq = &qconf->rx_queue_list[queueid];
		rxq->portid = portid;
		rxq->lpm = socket_lpm[socket];
		rxq->lpm6 = socket_lpm6[socket];
		if (setup_queue_tbl(rxq, rx_lcore_id, queueid) < 0)
			rte_exit(EXIT_FAILURE, "Failed to set up queue table\n");
		qconf->n_rx_queue++;

		/* init port */
		printf("Initializing port %d ... ", portid );
		fflush(stdout);

		n_tx_queue = nb_lcores;
		if (n_tx_queue > MAX_TX_QUEUE_PER_PORT)
			n_tx_queue = MAX_TX_QUEUE_PER_PORT;
		ret = rte_eth_dev_configure(portid, 1, (uint16_t)n_tx_queue,
					    &port_conf);
		if (ret < 0) {
			printf("\n");
			rte_exit(EXIT_FAILURE, "Cannot configure device: "
				"err=%d, port=%d\n",
				ret, portid);
		}

		/* init one RX queue */
		ret = rte_eth_rx_queue_setup(portid, 0, nb_rxd,
					     socket, NULL,
					     rxq->pool);
		if (ret < 0) {
			printf("\n");
			rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup: "
				"err=%d, port=%d\n",
				ret, portid);
		}

		rte_eth_macaddr_get(portid, &ports_eth_addr[portid]);
		print_ethaddr(" Address:", &ports_eth_addr[portid]);
		printf("\n");

		/* init one TX queue per couple (lcore,port) */
		queueid = 0;
		for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
			if (rte_lcore_is_enabled(lcore_id) == 0)
				continue;

			socket = (int) rte_lcore_to_socket_id(lcore_id);

			printf("txq=%u,%d,%d ", lcore_id, queueid, socket);
			fflush(stdout);

			rte_eth_dev_info_get(portid, &dev_info);
			txconf = &dev_info.default_txconf;
			txconf->txq_flags = 0;

			ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd,
					socket, txconf);
			if (ret < 0)
				rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: err=%d, "
					"port=%d\n", ret, portid);

			qconf = &lcore_queue_conf[lcore_id];
			qconf->tx_queue_id[portid] = queueid;
			setup_port_tbl(qconf, lcore_id, socket, portid);
			queueid++;
		}
		printf("\n");
	}

	printf("\n");

	/* start ports */
	for (portid = 0; portid < nb_ports; portid++) {
		if ((enabled_port_mask & (1 << portid)) == 0) {
			continue;
		}
		/* Start device */
		ret = rte_eth_dev_start(portid);
		if (ret < 0)
			rte_exit(EXIT_FAILURE, "rte_eth_dev_start: err=%d, port=%d\n",
				ret, portid);

		rte_eth_promiscuous_enable(portid);
	}

	if (init_routing_table() < 0)
		rte_exit(EXIT_FAILURE, "Cannot init routing table\n");

	check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask);

	signal(SIGUSR1, signal_handler);
	signal(SIGTERM, signal_handler);
	signal(SIGINT, signal_handler);

	/* launch per-lcore init on every lcore */
	rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		if (rte_eal_wait_lcore(lcore_id) < 0)
			return -1;
	}

	return 0;
}