DPDK logo

Elixir Cross Referencer

   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
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
/*-
 *   BSD LICENSE
 * 
 *   Copyright(c) 2010-2013 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 <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_tailq.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_ring.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
#include <rte_ip.h>
#include <rte_tcp.h>
#include <rte_udp.h>
#include <rte_string_fns.h>

#include "main.h"

#define APP_LOOKUP_EXACT_MATCH          0
#define APP_LOOKUP_LPM                  1
#define DO_RFC_1812_CHECKS

//#define APP_LOOKUP_METHOD             APP_LOOKUP_EXACT_MATCH
#ifndef APP_LOOKUP_METHOD
#define APP_LOOKUP_METHOD             APP_LOOKUP_LPM
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
#include <rte_hash.h>
#elif (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
#include <rte_lpm.h>
#else
#error "APP_LOOKUP_METHOD set to incorrect value"
#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 RTE_LOGTYPE_L3FWD RTE_LOGTYPE_USER1

#define MAX_PORTS 32

#define MAX_JUMBO_PKT_LEN  9600

#define IPV6_ADDR_LEN 16

#define MEMPOOL_CACHE_SIZE 256

#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)

/*
 * This expression is used to calculate the number of mbufs needed depending on user input, taking
 *  into account memory for rx and tx hardware rings, cache per lcore and mtable per port per lcore.
 *  RTE_MAX is used to ensure that NB_MBUF never goes below a minimum value of 8192
 */

#define NB_MBUF RTE_MAX	(																	\
				(nb_ports*nb_rx_queue*RTE_TEST_RX_DESC_DEFAULT +							\
				nb_ports*nb_lcores*MAX_PKT_BURST +											\
				nb_ports*n_tx_queue*RTE_TEST_TX_DESC_DEFAULT +								\
				nb_lcores*MEMPOOL_CACHE_SIZE),												\
				(unsigned)8192)

/*
 * RX and TX Prefetch, Host, and Write-back threshold values should be
 * carefully set for optimal performance. Consult the network
 * controller's datasheet and supporting DPDK documentation for guidance
 * on how these parameters should be set.
 */
#define RX_PTHRESH 8 /**< Default values of RX prefetch threshold reg. */
#define RX_HTHRESH 8 /**< Default values of RX host threshold reg. */
#define RX_WTHRESH 4 /**< Default values of RX write-back threshold reg. */

/*
 * These default values are optimized for use with the Intel(R) 82599 10 GbE
 * Controller and the DPDK ixgbe PMD. Consider using other values for other
 * network controllers and/or network drivers.
 */
#define TX_PTHRESH 36 /**< Default values of TX prefetch threshold reg. */
#define TX_HTHRESH 0  /**< Default values of TX host threshold reg. */
#define TX_WTHRESH 0  /**< Default values of TX write-back threshold reg. */

#define MAX_PKT_BURST 32
#define BURST_TX_DRAIN 200000ULL /* around 100us at 2 Ghz */

#define NB_SOCKETS 8

#define SOCKET0 0

/* 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[MAX_PORTS];

/* mask of enabled ports */
static uint32_t enabled_port_mask = 0;
static int promiscuous_on = 0; /**< Ports set in promiscuous mode off by default. */
static int numa_on = 1; /**< NUMA is enabled by default. */

struct mbuf_table {
	uint16_t len;
	struct rte_mbuf *m_table[MAX_PKT_BURST];
};

struct lcore_rx_queue {
	uint8_t port_id;
	uint8_t queue_id;
} __rte_cache_aligned;

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

#define MAX_LCORE_PARAMS 1024
struct lcore_params {
	uint8_t port_id;
	uint8_t queue_id;
	uint8_t lcore_id;
} __rte_cache_aligned;

static struct lcore_params lcore_params_array[MAX_LCORE_PARAMS];
static struct lcore_params lcore_params_array_default[] = {
	{0, 0, 2},
	{0, 1, 2},
	{0, 2, 2},
	{1, 0, 2},
	{1, 1, 2},
	{1, 2, 2},
	{2, 0, 2},
	{3, 0, 3},
	{3, 1, 3},
};

static struct lcore_params * lcore_params = lcore_params_array_default;
static uint16_t nb_lcore_params = sizeof(lcore_params_array_default) /
				sizeof(lcore_params_array_default[0]);

static struct rte_eth_conf port_conf = {
	.rxmode = {
		.max_rx_pkt_len = ETHER_MAX_LEN,
		.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    = 0, /**< Jumbo Frame Support disabled */
		.hw_strip_crc   = 0, /**< CRC stripped by hardware */
	},
	.rx_adv_conf = {
		.rss_conf = {
			.rss_key = NULL,
			.rss_hf = ETH_RSS_IPV4 | ETH_RSS_IPV6,
		},
	},
	.txmode = {
		.mq_mode = ETH_DCB_NONE,
	},
};

static const struct rte_eth_rxconf rx_conf = {
	.rx_thresh = {
		.pthresh = RX_PTHRESH,
		.hthresh = RX_HTHRESH,
		.wthresh = RX_WTHRESH,
	},
	.rx_free_thresh = 32,
};

static const struct rte_eth_txconf tx_conf = {
	.tx_thresh = {
		.pthresh = TX_PTHRESH,
		.hthresh = TX_HTHRESH,
		.wthresh = TX_WTHRESH,
	},
	.tx_free_thresh = 0, /* Use PMD default values */
	.tx_rs_thresh = 0, /* Use PMD default values */
	.txq_flags = 0x0,
};

static struct rte_mempool * pktmbuf_pool[NB_SOCKETS];


#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)

#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
#include <rte_hash_crc.h>
#define DEFAULT_HASH_FUNC       rte_hash_crc
#else
#include <rte_jhash.h>
#define DEFAULT_HASH_FUNC       rte_jhash
#endif

struct ipv4_5tuple {
	uint32_t ip_dst;
	uint32_t ip_src;
	uint16_t port_dst;
	uint16_t port_src;
	uint8_t  proto;
} __attribute__((__packed__));

struct ipv6_5tuple {
	uint8_t  ip_dst[IPV6_ADDR_LEN];
	uint8_t  ip_src[IPV6_ADDR_LEN];
	uint16_t port_dst;
	uint16_t port_src;
	uint8_t  proto;
} __attribute__((__packed__));

struct ipv4_l3fwd_route {
	struct ipv4_5tuple key;
	uint8_t if_out;
};

struct ipv6_l3fwd_route {
	struct ipv6_5tuple key;
	uint8_t if_out;
};

static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = {
	{{IPv4(100,10,0,1), IPv4(200,10,0,1), 101, 11, IPPROTO_TCP}, 0},
	{{IPv4(100,20,0,2), IPv4(200,20,0,2), 102, 12, IPPROTO_TCP}, 1},
	{{IPv4(100,30,0,3), IPv4(200,30,0,3), 103, 13, IPPROTO_TCP}, 2},
	{{IPv4(100,40,0,4), IPv4(200,40,0,4), 104, 14, IPPROTO_TCP}, 3},
};

static struct ipv6_l3fwd_route ipv6_l3fwd_route_array[] = {
	{
		{
			{0xfe, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
			 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
			{0xfe, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
			 0x02, 0x1e, 0x67, 0xff, 0xfe, 0x0d, 0xb6, 0x0a},
			 1, 10, IPPROTO_UDP
		}, 4
	},
};

typedef struct rte_hash lookup_struct_t;
static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS];
static lookup_struct_t *ipv6_l3fwd_lookup_struct[NB_SOCKETS];

#define L3FWD_HASH_ENTRIES	1024

struct rte_hash_parameters ipv4_l3fwd_hash_params = {
	.name = "ipv4_l3fwd_hash_0",
	.entries = L3FWD_HASH_ENTRIES,
	.bucket_entries = 4,
	.key_len = sizeof(struct ipv4_5tuple),
	.hash_func = DEFAULT_HASH_FUNC,
	.hash_func_init_val = 0,
	.socket_id = SOCKET0,
};

struct rte_hash_parameters ipv6_l3fwd_hash_params = {
	.name = "ipv6_l3fwd_hash_0",
	.entries = L3FWD_HASH_ENTRIES,
	.bucket_entries = 4,
	.key_len = sizeof(struct ipv6_5tuple),
	.hash_func = DEFAULT_HASH_FUNC,
	.hash_func_init_val = 0,
	.socket_id = SOCKET0,
};

#define IPV4_L3FWD_NUM_ROUTES \
	(sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0]))

#define IPV6_L3FWD_NUM_ROUTES \
	(sizeof(ipv6_l3fwd_route_array) / sizeof(ipv6_l3fwd_route_array[0]))

static uint8_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
static uint8_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
struct ipv4_l3fwd_route {
	uint32_t ip;
	uint8_t  depth;
	uint8_t  if_out;
};

static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = {
	{IPv4(1,1,1,0), 24, 0},
	{IPv4(2,1,1,0), 24, 1},
	{IPv4(3,1,1,0), 24, 2},
	{IPv4(4,1,1,0), 24, 3},
	{IPv4(5,1,1,0), 24, 4},
	{IPv4(6,1,1,0), 24, 5},
	{IPv4(7,1,1,0), 24, 6},
	{IPv4(8,1,1,0), 24, 7},
};

#define IPV4_L3FWD_NUM_ROUTES \
	(sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0]))

#define IPV4_L3FWD_LPM_MAX_RULES     1024

typedef struct rte_lpm lookup_struct_t;
static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS];
#endif

struct lcore_conf {
	uint16_t n_rx_queue;
	struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE];
	uint16_t tx_queue_id[MAX_PORTS];
	struct mbuf_table tx_mbufs[MAX_PORTS];
	lookup_struct_t * ipv4_lookup_struct;
	lookup_struct_t * ipv6_lookup_struct;
} __rte_cache_aligned;

static struct lcore_conf lcore_conf[RTE_MAX_LCORE];

/* Send burst of packets on an output interface */
static inline int
send_burst(struct lcore_conf *qconf, uint16_t n, uint8_t port)
{
	struct rte_mbuf **m_table;
	int ret;
	uint16_t queueid;

	queueid = qconf->tx_queue_id[port];
	m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table;

	ret = rte_eth_tx_burst(port, queueid, m_table, n);
	if (unlikely(ret < n)) {
		do {
			rte_pktmbuf_free(m_table[ret]);
		} while (++ret < n);
	}

	return 0;
}

/* 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 lcore_id;
	uint16_t len;
	struct lcore_conf *qconf;

	lcore_id = rte_lcore_id();

	qconf = &lcore_conf[lcore_id];
	len = qconf->tx_mbufs[port].len;
	qconf->tx_mbufs[port].m_table[len] = m;
	len++;

	/* enough pkts to be sent */
	if (unlikely(len == MAX_PKT_BURST)) {
		send_burst(qconf, MAX_PKT_BURST, port);
		len = 0;
	}

	qconf->tx_mbufs[port].len = len;
	return 0;
}

#ifdef DO_RFC_1812_CHECKS
static inline int
is_valid_ipv4_pkt(struct ipv4_hdr *pkt, uint32_t link_len)
{
	/* From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2 */
	/*
	 * 1. The packet length reported by the Link Layer must be large
	 * enough to hold the minimum length legal IP datagram (20 bytes).
	 */
	if (link_len < sizeof(struct ipv4_hdr))
		return -1;

	/* 2. The IP checksum must be correct. */
	/* this is checked in H/W */

	/*
	 * 3. The IP version number must be 4. If the version number is not 4
	 * then the packet may be another version of IP, such as IPng or
	 * ST-II.
	 */
	if (((pkt->version_ihl) >> 4) != 4)
		return -3;
	/*
	 * 4. The IP header length field must be large enough to hold the
	 * minimum length legal IP datagram (20 bytes = 5 words).
	 */
	if ((pkt->version_ihl & 0xf) < 5)
		return -4;

	/*
	 * 5. The IP total length field must be large enough to hold the IP
	 * datagram header, whose length is specified in the IP header length
	 * field.
	 */
	if (rte_cpu_to_be_16(pkt->total_length) < sizeof(struct ipv4_hdr))
		return -5;

	return 0;
}
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
static void
print_ipv4_key(struct ipv4_5tuple key)
{
	printf("IP dst = %08x, IP src = %08x, port dst = %d, port src = %d, proto = %d\n",
			(unsigned)key.ip_dst, (unsigned)key.ip_src, key.port_dst, key.port_src, key.proto);
}
static void
print_ipv6_key(struct ipv6_5tuple key)
{
	printf( "IP dst = " IPv6_BYTES_FMT ", IP src = " IPv6_BYTES_FMT ", "
	        "port dst = %d, port src = %d, proto = %d\n",
	        IPv6_BYTES(key.ip_dst), IPv6_BYTES(key.ip_src),
	        key.port_dst, key.port_src, key.proto);
}

static inline uint8_t
get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr,  uint8_t portid, lookup_struct_t * ipv4_l3fwd_lookup_struct)
{
	struct ipv4_5tuple key;
	struct tcp_hdr *tcp;
	struct udp_hdr *udp;
	int ret = 0;

	key.ip_dst = rte_be_to_cpu_32(ipv4_hdr->dst_addr);
	key.ip_src = rte_be_to_cpu_32(ipv4_hdr->src_addr);
	key.proto = ipv4_hdr->next_proto_id;

	switch (ipv4_hdr->next_proto_id) {
	case IPPROTO_TCP:
		tcp = (struct tcp_hdr *)((unsigned char *) ipv4_hdr +
					sizeof(struct ipv4_hdr));
		key.port_dst = rte_be_to_cpu_16(tcp->dst_port);
		key.port_src = rte_be_to_cpu_16(tcp->src_port);
		break;

	case IPPROTO_UDP:
		udp = (struct udp_hdr *)((unsigned char *) ipv4_hdr +
					sizeof(struct ipv4_hdr));
		key.port_dst = rte_be_to_cpu_16(udp->dst_port);
		key.port_src = rte_be_to_cpu_16(udp->src_port);
		break;

	default:
		key.port_dst = 0;
		key.port_src = 0;
		break;
	}

	/* Find destination port */
	ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key);
	return (uint8_t)((ret < 0)? portid : ipv4_l3fwd_out_if[ret]);
}

static inline uint8_t
get_ipv6_dst_port(struct ipv6_hdr *ipv6_hdr,  uint8_t portid, lookup_struct_t * ipv6_l3fwd_lookup_struct)
{
	struct ipv6_5tuple key;
	struct tcp_hdr *tcp;
	struct udp_hdr *udp;
	int ret = 0;

	memcpy(key.ip_dst, ipv6_hdr->dst_addr, IPV6_ADDR_LEN);
	memcpy(key.ip_src, ipv6_hdr->src_addr, IPV6_ADDR_LEN);

	key.proto = ipv6_hdr->proto;

	switch (ipv6_hdr->proto) {
	case IPPROTO_TCP:
		tcp = (struct tcp_hdr *)((unsigned char *) ipv6_hdr +
					sizeof(struct ipv6_hdr));
		key.port_dst = rte_be_to_cpu_16(tcp->dst_port);
		key.port_src = rte_be_to_cpu_16(tcp->src_port);
		break;

	case IPPROTO_UDP:
		udp = (struct udp_hdr *)((unsigned char *) ipv6_hdr +
					sizeof(struct ipv6_hdr));
		key.port_dst = rte_be_to_cpu_16(udp->dst_port);
		key.port_src = rte_be_to_cpu_16(udp->src_port);
		break;

	default:
		key.port_dst = 0;
		key.port_src = 0;
		break;
	}

	/* Find destination port */
	ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key);
	return (uint8_t)((ret < 0)? portid : ipv6_l3fwd_out_if[ret]);
}
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
static inline uint8_t
get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr,  uint8_t portid, lookup_struct_t * ipv4_l3fwd_lookup_struct)
{
	uint8_t next_hop;

	return (uint8_t) ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct,
			rte_be_to_cpu_32(ipv4_hdr->dst_addr), &next_hop) == 0)?
			next_hop : portid);
}
#endif

static inline void
l3fwd_simple_forward(struct rte_mbuf *m, uint8_t portid, struct lcore_conf *qconf)
{
	struct ether_hdr *eth_hdr;
	struct ipv4_hdr *ipv4_hdr;
	void *d_addr_bytes;
	uint8_t dst_port;

	eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);

	if (m->ol_flags & PKT_RX_IPV4_HDR) {
		/* Handle IPv4 headers.*/
		ipv4_hdr = (struct ipv4_hdr *)(rte_pktmbuf_mtod(m, unsigned char *) +
				sizeof(struct ether_hdr));

#ifdef DO_RFC_1812_CHECKS
		/* Check to make sure the packet is valid (RFC1812) */
		if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt.pkt_len) < 0) {
			rte_pktmbuf_free(m);
			return;
		}
#endif

		dst_port = get_ipv4_dst_port(ipv4_hdr, portid, qconf->ipv4_lookup_struct);
		if (dst_port >= MAX_PORTS || (enabled_port_mask & 1 << dst_port) == 0)
			dst_port = portid;

		/* 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);

#ifdef DO_RFC_1812_CHECKS
		/* Update time to live and header checksum */
		--(ipv4_hdr->time_to_live);
		++(ipv4_hdr->hdr_checksum);
#endif

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

		send_single_packet(m, dst_port);
	}
	else {
		/* Handle IPv6 headers.*/
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
		struct ipv6_hdr *ipv6_hdr;

		ipv6_hdr = (struct ipv6_hdr *)(rte_pktmbuf_mtod(m, unsigned char *) +
				sizeof(struct ether_hdr));

		dst_port = get_ipv6_dst_port(ipv6_hdr, portid, qconf->ipv6_lookup_struct);

		if (dst_port >= MAX_PORTS || (enabled_port_mask & 1 << dst_port) == 0)
			dst_port = portid;

		/* 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);
#else
		/* We don't currently handle IPv6 packets in LPM mode. */
		rte_pktmbuf_free(m);
#endif
	}

}

/* main processing loop */
static __attribute__((noreturn)) int
main_loop(__attribute__((unused)) void *dummy)
{
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
	unsigned lcore_id;
	uint64_t prev_tsc = 0;
	uint64_t diff_tsc, cur_tsc;
	int i, j, nb_rx;
	uint8_t portid, queueid;
	struct lcore_conf *qconf;

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

	if (qconf->n_rx_queue == 0) {
		RTE_LOG(INFO, L3FWD, "lcore %u has nothing to do\n", lcore_id);
		while(1);
	}

	RTE_LOG(INFO, L3FWD, "entering main loop on lcore %u\n", lcore_id);

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

		portid = qconf->rx_queue_list[i].port_id;
		queueid = qconf->rx_queue_list[i].queue_id;
		RTE_LOG(INFO, L3FWD, " -- lcoreid=%u portid=%hhu rxqueueid=%hhu\n", lcore_id,
			portid, queueid);
	}

	while (1) {

		cur_tsc = rte_rdtsc();

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

			/*
			 * This could be optimized (use queueid instead of
			 * portid), but it is not called so often
			 */
			for (portid = 0; portid < MAX_PORTS; portid++) {
				if (qconf->tx_mbufs[portid].len == 0)
					continue;
				send_burst(&lcore_conf[lcore_id],
					qconf->tx_mbufs[portid].len,
					portid);
				qconf->tx_mbufs[portid].len = 0;
			}

			prev_tsc = cur_tsc;
		}

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

			portid = qconf->rx_queue_list[i].port_id;
			queueid = qconf->rx_queue_list[i].queue_id;
			nb_rx = rte_eth_rx_burst(portid, queueid, 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 *));
				l3fwd_simple_forward(pkts_burst[j], portid, qconf);
			}

			/* Forward remaining prefetched packets */
			for (; j < nb_rx; j++) {
				l3fwd_simple_forward(pkts_burst[j], portid, qconf);
			}
		}
	}
}

static int
check_lcore_params(void)
{
	uint8_t queue, lcore;
	uint16_t i;
	int socketid;

	for (i = 0; i < nb_lcore_params; ++i) {
		queue = lcore_params[i].queue_id;
		if (queue >= MAX_RX_QUEUE_PER_PORT) {
			printf("invalid queue number: %hhu\n", queue);
			return -1;
		}
		lcore = lcore_params[i].lcore_id;
		if (!rte_lcore_is_enabled(lcore)) {
			printf("error: lcore %hhu is not enabled in lcore mask\n", lcore);
			return -1;
		}
		if ((socketid = rte_lcore_to_socket_id(lcore) != 0) &&
			(numa_on == 0)) {
			printf("warning: lcore %hhu is on socket %d with numa off \n",
				lcore, socketid);
		}
	}
	return 0;
}

static int
check_port_config(const unsigned nb_ports)
{
	unsigned portid;
	uint16_t i;

	for (i = 0; i < nb_lcore_params; ++i) {
		portid = lcore_params[i].port_id;
		if ((enabled_port_mask & (1 << portid)) == 0) {
			printf("port %u is not enabled in port mask\n", portid);
			return -1;
		}
		if (portid >= nb_ports) {
			printf("port %u is not present on the board\n", portid);
			return -1;
		}
	}
	return 0;
}

static uint8_t
get_port_n_rx_queues(const uint8_t port)
{
	int queue = -1;
	uint16_t i;

	for (i = 0; i < nb_lcore_params; ++i) {
		if (lcore_params[i].port_id == port && lcore_params[i].queue_id > queue)
			queue = lcore_params[i].queue_id;
	}
	return (uint8_t)(++queue);
}

static int
init_lcore_rx_queues(void)
{
	uint16_t i, nb_rx_queue;
	uint8_t lcore;

	for (i = 0; i < nb_lcore_params; ++i) {
		lcore = lcore_params[i].lcore_id;
		nb_rx_queue = lcore_conf[lcore].n_rx_queue;
		if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) {
			printf("error: too many queues (%u) for lcore: %u\n",
				(unsigned)nb_rx_queue + 1, (unsigned)lcore);
			return -1;
		} else {
			lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id =
				lcore_params[i].port_id;
			lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id =
				lcore_params[i].queue_id;
			lcore_conf[lcore].n_rx_queue++;
		}
	}
	return 0;
}

/* display usage */
static void
print_usage(const char *prgname)
{
	printf ("%s [EAL options] -- -p PORTMASK -P"
		"  [--config (port,queue,lcore)[,(port,queue,lcore]]"
		"  [--enable-jumbo [--max-pkt-len PKTLEN]]\n"
		"  -p PORTMASK: hexadecimal bitmask of ports to configure\n"
		"  -P : enable promiscuous mode\n"
		"  --config (port,queue,lcore): rx queues configuration\n"
		"  --no-numa: optional, disable numa awareness\n"
		"  --enable-jumbo: enable jumbo frame"
		" which max packet len is PKTLEN in decimal (64-9600)\n",
		prgname);
}

static int parse_max_pkt_len(const char *pktlen)
{
	char *end = NULL;
	unsigned long len;

	/* parse decimal string */
	len = strtoul(pktlen, &end, 10);
	if ((pktlen[0] == '\0') || (end == NULL) || (*end != '\0'))
		return -1;

	if (len == 0)
		return -1;

	return len;
}

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_config(const char *q_arg)
{
	char s[256];
	const char *p, *p0 = q_arg;
	char *end;
	enum fieldnames {
		FLD_PORT = 0,
		FLD_QUEUE,
		FLD_LCORE,
		_NUM_FLD
	};
	unsigned long int_fld[_NUM_FLD];
	char *str_fld[_NUM_FLD];
	int i;
	unsigned size;

	nb_lcore_params = 0;

	while ((p = strchr(p0,'(')) != NULL) {
		++p;
		if((p0 = strchr(p,')')) == NULL)
			return -1;

		size = p0 - p;
		if(size >= sizeof(s))
			return -1;

		rte_snprintf(s, sizeof(s), "%.*s", size, p);
		if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != _NUM_FLD)
			return -1;
		for (i = 0; i < _NUM_FLD; i++){
			errno = 0;
			int_fld[i] = strtoul(str_fld[i], &end, 0);
			if (errno != 0 || end == str_fld[i] || int_fld[i] > 255)
				return -1;
		}
		if (nb_lcore_params >= MAX_LCORE_PARAMS) {
			printf("exceeded max number of lcore params: %hu\n",
				nb_lcore_params);
			return -1;
		}
		lcore_params_array[nb_lcore_params].port_id = (uint8_t)int_fld[FLD_PORT];
		lcore_params_array[nb_lcore_params].queue_id = (uint8_t)int_fld[FLD_QUEUE];
		lcore_params_array[nb_lcore_params].lcore_id = (uint8_t)int_fld[FLD_LCORE];
		++nb_lcore_params;
	}
	lcore_params = lcore_params_array;
	return 0;
}

/* 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[] = {
		{"config", 1, 0, 0},
		{"no-numa", 0, 0, 0},
		{"enable-jumbo", 0, 0, 0},
		{NULL, 0, 0, 0}
	};

	argvopt = argv;

	while ((opt = getopt_long(argc, argvopt, "p:P",
				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;
		case 'P':
			printf("Promiscuous mode selected\n");
			promiscuous_on = 1;
			break;

		/* long options */
		case 0:
			if (!strncmp(lgopts[option_index].name, "config", 6)) {
				ret = parse_config(optarg);
				if (ret) {
					printf("invalid config\n");
					print_usage(prgname);
					return -1;
				}
			}

			if (!strncmp(lgopts[option_index].name, "no-numa", 7)) {
				printf("numa is disabled \n");
				numa_on = 0;
			}
			
			if (!strncmp(lgopts[option_index].name, "enable-jumbo", 12)) {
				struct option lenopts = {"max-pkt-len", required_argument, 0, 0};

				printf("jumbo frame is enabled \n");
				port_conf.rxmode.jumbo_frame = 1;
	
				/* if no max-pkt-len set, use the default value ETHER_MAX_LEN */	
				if (0 == getopt_long(argc, argvopt, "", &lenopts, &option_index)) {
					ret = parse_max_pkt_len(optarg);
					if ((ret < 64) || (ret > MAX_JUMBO_PKT_LEN)){
						printf("invalid packet length\n");
						print_usage(prgname);
						return -1;
					}
					port_conf.rxmode.max_rx_pkt_len = ret;
				}
				printf("set jumbo frame max packet length to %u\n", 
						(unsigned int)port_conf.rxmode.max_rx_pkt_len);
			}
			
			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)
{
	printf ("%s%02X:%02X:%02X:%02X:%02X:%02X", name,
		eth_addr->addr_bytes[0],
		eth_addr->addr_bytes[1],
		eth_addr->addr_bytes[2],
		eth_addr->addr_bytes[3],
		eth_addr->addr_bytes[4],
		eth_addr->addr_bytes[5]);
}

#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
static void
setup_hash(int socketid)
{
	unsigned i;
	int ret;
	char s[64];

	/* create ipv4 hash */
	rte_snprintf(s, sizeof(s), "ipv4_l3fwd_hash_%d", socketid);
	ipv4_l3fwd_hash_params.name = s;
	ipv4_l3fwd_hash_params.socket_id = socketid;
	ipv4_l3fwd_lookup_struct[socketid] = rte_hash_create(&ipv4_l3fwd_hash_params);
	if (ipv4_l3fwd_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on "
				"socket %d\n", socketid);

	/* create ipv6 hash */
	rte_snprintf(s, sizeof(s), "ipv6_l3fwd_hash_%d", socketid);
	ipv6_l3fwd_hash_params.name = s;
	ipv6_l3fwd_hash_params.socket_id = socketid;
	ipv6_l3fwd_lookup_struct[socketid] = rte_hash_create(&ipv6_l3fwd_hash_params);
	if (ipv6_l3fwd_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on "
				"socket %d\n", socketid);


	/* populate the ipv4 hash */
	for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) {
		ret = rte_hash_add_key (ipv4_l3fwd_lookup_struct[socketid],
				(void *) &ipv4_l3fwd_route_array[i].key);
		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %u to the"
				"l3fwd hash on socket %d\n", i, socketid);
		}
		ipv4_l3fwd_out_if[ret] = ipv4_l3fwd_route_array[i].if_out;
		printf("Hash: Adding key\n");
		print_ipv4_key(ipv4_l3fwd_route_array[i].key);
	}

	/* populate the ipv6 hash */
	for (i = 0; i < IPV6_L3FWD_NUM_ROUTES; i++) {
		ret = rte_hash_add_key (ipv6_l3fwd_lookup_struct[socketid],
				(void *) &ipv6_l3fwd_route_array[i].key);
		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %u to the"
				"l3fwd hash on socket %d\n", i, socketid);
		}
		ipv6_l3fwd_out_if[ret] = ipv6_l3fwd_route_array[i].if_out;
		printf("Hash: Adding key\n");
		print_ipv6_key(ipv6_l3fwd_route_array[i].key);
	}
}
#endif

#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
static void
setup_lpm(int socketid)
{
	unsigned i;
	int ret;
	char s[64];

	/* create the LPM table */
	rte_snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", socketid);
	ipv4_l3fwd_lookup_struct[socketid] = rte_lpm_create(s, socketid,
				IPV4_L3FWD_LPM_MAX_RULES, 0);
	if (ipv4_l3fwd_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE, "Unable to create the l3fwd LPM table"
				" on socket %d\n", socketid);

	/* populate the LPM table */
	for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) {
		ret = rte_lpm_add(ipv4_l3fwd_lookup_struct[socketid],
			ipv4_l3fwd_route_array[i].ip,
			ipv4_l3fwd_route_array[i].depth,
			ipv4_l3fwd_route_array[i].if_out);

		if (ret < 0) {
			rte_exit(EXIT_FAILURE, "Unable to add entry %u to the "
				"l3fwd LPM table on socket %d\n",
				i, socketid);
		}

		printf("LPM: Adding route 0x%08x / %d (%d)\n",
			(unsigned)ipv4_l3fwd_route_array[i].ip,
			ipv4_l3fwd_route_array[i].depth,
			ipv4_l3fwd_route_array[i].if_out);
	}
}
#endif

static int
init_mem(unsigned nb_mbuf)
{
	struct lcore_conf *qconf;
	int socketid;
	unsigned lcore_id;
	char s[64];

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

		if (numa_on)
			socketid = rte_lcore_to_socket_id(lcore_id);
		else
			socketid = 0;

		if (socketid >= NB_SOCKETS) {
			rte_exit(EXIT_FAILURE, "Socket %d of lcore %u is out of range %d\n",
				socketid, lcore_id, NB_SOCKETS);
		}
		if (pktmbuf_pool[socketid] == NULL) {
			rte_snprintf(s, sizeof(s), "mbuf_pool_%d", socketid);
			pktmbuf_pool[socketid] =
				rte_mempool_create(s, nb_mbuf, MBUF_SIZE, MEMPOOL_CACHE_SIZE,
					sizeof(struct rte_pktmbuf_pool_private),
					rte_pktmbuf_pool_init, NULL,
					rte_pktmbuf_init, NULL,
					socketid, 0);
			if (pktmbuf_pool[socketid] == NULL)
				rte_exit(EXIT_FAILURE,
						"Cannot init mbuf pool on socket %d\n", socketid);
			else
				printf("Allocated mbuf pool on socket %d\n", socketid);

#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
			setup_lpm(socketid);
#else
			setup_hash(socketid);
#endif
		}
		qconf = &lcore_conf[lcore_id];
		qconf->ipv4_lookup_struct = ipv4_l3fwd_lookup_struct[socketid];
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
		qconf->ipv6_lookup_struct = ipv6_l3fwd_lookup_struct[socketid];
#endif
	}
	return 0;
}

/* 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 == 0) {
				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("done\n");
		}
	}
}

int
MAIN(int argc, char **argv)
{
	struct lcore_conf *qconf;
	int ret;
	unsigned nb_ports;
	uint16_t queueid;
	unsigned lcore_id;
	uint32_t n_tx_queue, nb_lcores;
	uint8_t portid, nb_rx_queue, queue, socketid;

	/* 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 L3FWD parameters\n");

	if (check_lcore_params() < 0)
		rte_exit(EXIT_FAILURE, "check_lcore_params failed\n");

	ret = init_lcore_rx_queues();
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n");


	/* init driver(s) */
	if (rte_pmd_init_all() < 0)
		rte_exit(EXIT_FAILURE, "Cannot init pmd\n");

	if (rte_eal_pci_probe() < 0)
		rte_exit(EXIT_FAILURE, "Cannot probe PCI\n");

	nb_ports = rte_eth_dev_count();
	if (nb_ports > MAX_PORTS)
		nb_ports = MAX_PORTS;

	if (check_port_config(nb_ports) < 0)
		rte_exit(EXIT_FAILURE, "check_port_config failed\n");

	nb_lcores = rte_lcore_count();

	/* 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;
		}

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

		nb_rx_queue = get_port_n_rx_queues(portid);
		n_tx_queue = nb_lcores;
		if (n_tx_queue > MAX_TX_QUEUE_PER_PORT)
			n_tx_queue = MAX_TX_QUEUE_PER_PORT;
		printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
			nb_rx_queue, (unsigned)n_tx_queue );
		ret = rte_eth_dev_configure(portid, nb_rx_queue,
					(uint16_t)n_tx_queue, &port_conf);
		if (ret < 0)
			rte_exit(EXIT_FAILURE, "Cannot configure device: err=%d, port=%d\n",
				ret, portid);

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

		/* init memory */
		ret = init_mem(NB_MBUF);
		if (ret < 0)
			rte_exit(EXIT_FAILURE, "init_mem failed\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;

			if (numa_on)
				socketid = (uint8_t)rte_lcore_to_socket_id(lcore_id);
			else
				socketid = 0;

			printf("txq=%u,%d,%d ", lcore_id, queueid, socketid);
			fflush(stdout);
			ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd,
						     socketid, &tx_conf);
			if (ret < 0)
				rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: err=%d, "
					"port=%d\n", ret, portid);

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

	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
		if (rte_lcore_is_enabled(lcore_id) == 0)
			continue;
		qconf = &lcore_conf[lcore_id];
		printf("\nInitializing rx queues on lcore %u ... ", lcore_id );
		fflush(stdout);
		/* init RX queues */
		for(queue = 0; queue < qconf->n_rx_queue; ++queue) {
			portid = qconf->rx_queue_list[queue].port_id;
			queueid = qconf->rx_queue_list[queue].queue_id;

			if (numa_on)
				socketid = (uint8_t)rte_lcore_to_socket_id(lcore_id);
			else
				socketid = 0;

			printf("rxq=%d,%d,%d ", portid, queueid, socketid);
			fflush(stdout);

			ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd,
				        socketid, &rx_conf, pktmbuf_pool[socketid]);
			if (ret < 0)
				rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup: err=%d,"
						"port=%d\n", ret, portid);
		}
	}

	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);

		/*
		 * If enabled, put device in promiscuous mode.
		 * This allows IO forwarding mode to forward packets
		 * to itself through 2 cross-connected  ports of the
		 * target machine.
		 */
		if (promiscuous_on)
			rte_eth_promiscuous_enable(portid);
	}

	check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask);

	/* 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;
}