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
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
/*-
 *   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 <arpa/inet.h>
#include <getopt.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/virtio_net.h>
#include <linux/virtio_ring.h>
#include <signal.h>
#include <stdint.h>
#include <sys/eventfd.h>
#include <sys/param.h>
#include <unistd.h>

#include <rte_atomic.h>
#include <rte_cycles.h>
#include <rte_ethdev.h>
#include <rte_log.h>
#include <rte_string_fns.h>

#include "main.h"
#include "virtio-net.h"
#include "vhost-net-cdev.h"

#define MAX_QUEUES 128

/* the maximum number of external ports supported */
#define MAX_SUP_PORTS 1

/*
 * Calculate the number of buffers needed per port
 */
#define NUM_MBUFS_PER_PORT ((MAX_QUEUES*RTE_TEST_RX_DESC_DEFAULT) +  		\
							(num_switching_cores*MAX_PKT_BURST) +  			\
							(num_switching_cores*RTE_TEST_TX_DESC_DEFAULT) +\
							(num_switching_cores*MBUF_CACHE_SIZE))

#define MBUF_CACHE_SIZE 128 
#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)

/*
 * 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 		/* Max burst size for RX/TX */
#define MAX_MRG_PKT_BURST 16 	/* Max burst for merge buffers. Set to 1 due to performance issue. */
#define BURST_TX_DRAIN_US 100 	/* TX drain every ~100us */

#define BURST_RX_WAIT_US 15 	/* Defines how long we wait between retries on RX */
#define BURST_RX_RETRIES 4		/* Number of retries on RX. */

/* State of virtio device. */
#define DEVICE_MAC_LEARNING 0
#define DEVICE_RX			1
#define DEVICE_SAFE_REMOVE	2

/* Config_core_flag status definitions. */
#define REQUEST_DEV_REMOVAL 1
#define ACK_DEV_REMOVAL 0

/* Configurable number of RX/TX ring descriptors */
#define RTE_TEST_RX_DESC_DEFAULT 1024 
#define RTE_TEST_TX_DESC_DEFAULT 512

#define INVALID_PORT_ID 0xFF

/* Max number of devices. Limited by vmdq. */
#define MAX_DEVICES 64

/* Size of buffers used for rte_snprintfs. */
#define MAX_PRINT_BUFF 6072

/* Maximum character device basename size. */
#define MAX_BASENAME_SZ 10

/* Maximum long option length for option parsing. */
#define MAX_LONG_OPT_SZ 64

/* Used to compare MAC addresses. */
#define MAC_ADDR_CMP 0xFFFFFFFFFFFFULL

/* Number of descriptors per cacheline. */
#define DESC_PER_CACHELINE (CACHE_LINE_SIZE / sizeof(struct vring_desc))

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

/*Number of switching cores enabled*/
static uint32_t num_switching_cores = 0;

/* number of devices/queues to support*/
static uint32_t num_queues = 0;
uint32_t num_devices = 0;

/* Enable VM2VM communications. If this is disabled then the MAC address compare is skipped. */
static uint32_t enable_vm2vm = 1;
/* Enable stats. */
static uint32_t enable_stats = 0;
/* Enable retries on RX. */
static uint32_t enable_retry = 1;
/* Specify timeout (in useconds) between retries on RX. */
static uint32_t burst_rx_delay_time = BURST_RX_WAIT_US;
/* Specify the number of retries on RX. */
static uint32_t burst_rx_retry_num = BURST_RX_RETRIES;

/* Character device basename. Can be set by user. */
static char dev_basename[MAX_BASENAME_SZ] = "vhost-net";

/* Charater device index. Can be set by user. */
static uint32_t dev_index = 0;

/* This can be set by the user so it is made available here. */
extern uint64_t VHOST_FEATURES;

/* Default configuration for rx and tx thresholds etc. */
static const struct rte_eth_rxconf rx_conf_default = {
	.rx_thresh = {
		.pthresh = RX_PTHRESH,
		.hthresh = RX_HTHRESH,
		.wthresh = RX_WTHRESH,
	},
	.rx_drop_en = 1,
};

/*
 * These default values are optimized for use with the Intel(R) 82599 10 GbE
 * Controller and the DPDK ixgbe/igb PMD. Consider using other values for other
 * network controllers and/or network drivers.
 */
static const struct rte_eth_txconf tx_conf_default = {
	.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 */
};

/* empty vmdq configuration structure. Filled in programatically */
static const struct rte_eth_conf vmdq_conf_default = {
	.rxmode = {
		.mq_mode        = ETH_MQ_RX_VMDQ_ONLY,
		.split_hdr_size = 0,
		.header_split   = 0, /**< Header Split disabled */
		.hw_ip_checksum = 0, /**< IP checksum offload disabled */
		.hw_vlan_filter = 0, /**< VLAN filtering disabled */
		/*
		 * It is necessary for 1G NIC such as I350,
		 * this fixes bug of ipv4 forwarding in guest can't
		 * forward pakets from one virtio dev to another virtio dev.
		 */
		.hw_vlan_strip  = 1, /**< VLAN strip enabled. */
		.jumbo_frame    = 0, /**< Jumbo Frame Support disabled */
		.hw_strip_crc   = 0, /**< CRC stripped by hardware */
	},

	.txmode = {
		.mq_mode = ETH_MQ_TX_NONE,
	},
	.rx_adv_conf = {
		/*
		 * should be overridden separately in code with
		 * appropriate values
		 */
		.vmdq_rx_conf = {
			.nb_queue_pools = ETH_8_POOLS,
			.enable_default_pool = 0,
			.default_pool = 0,
			.nb_pool_maps = 0,
			.pool_map = {{0, 0},},
		},
	},
};

static unsigned lcore_ids[RTE_MAX_LCORE];
static uint8_t ports[RTE_MAX_ETHPORTS];
static unsigned num_ports = 0; /**< The number of ports specified in command line */

const uint16_t vlan_tags[] = {
	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,
};

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

/* heads for the main used and free linked lists for the data path. */
static struct virtio_net_data_ll *ll_root_used = NULL;
static struct virtio_net_data_ll *ll_root_free = NULL;

/* Array of data core structures containing information on individual core linked lists. */
static struct lcore_info lcore_info[RTE_MAX_LCORE];

/* Used for queueing bursts of TX packets. */
struct mbuf_table {
	unsigned len;
	unsigned txq_id;
	struct rte_mbuf *m_table[MAX_PKT_BURST];
};

/* TX queue for each data core. */
struct mbuf_table lcore_tx_queue[RTE_MAX_LCORE];

/* Vlan header struct used to insert vlan tags on TX. */
struct vlan_ethhdr {
	unsigned char   h_dest[ETH_ALEN];
	unsigned char   h_source[ETH_ALEN];
	__be16          h_vlan_proto;
	__be16          h_vlan_TCI;
	__be16          h_vlan_encapsulated_proto;
};

/* Header lengths. */
#define VLAN_HLEN       4
#define VLAN_ETH_HLEN   18

/* Per-device statistics struct */
struct device_statistics {
	uint64_t tx_total;
	rte_atomic64_t rx_total;
	uint64_t tx;
	rte_atomic64_t rx;
} __rte_cache_aligned;
struct device_statistics dev_statistics[MAX_DEVICES];

/*
 * Builds up the correct configuration for VMDQ VLAN pool map
 * according to the pool & queue limits.
 */
static inline int
get_eth_conf(struct rte_eth_conf *eth_conf, uint32_t num_devices)
{
	struct rte_eth_vmdq_rx_conf conf;
	unsigned i;

	memset(&conf, 0, sizeof(conf));
	conf.nb_queue_pools = (enum rte_eth_nb_pools)num_devices;
	conf.nb_pool_maps = num_devices;

	for (i = 0; i < conf.nb_pool_maps; i++) {
		conf.pool_map[i].vlan_id = vlan_tags[ i ];
		conf.pool_map[i].pools = (1UL << i);
	}

	(void)(rte_memcpy(eth_conf, &vmdq_conf_default, sizeof(*eth_conf)));
	(void)(rte_memcpy(&eth_conf->rx_adv_conf.vmdq_rx_conf, &conf,
		   sizeof(eth_conf->rx_adv_conf.vmdq_rx_conf)));
	return 0;
}

/*
 * Validate the device number according to the max pool number gotten form dev_info
 * If the device number is invalid, give the error message and return -1.
 * Each device must have its own pool.
 */
static inline int
validate_num_devices(uint32_t max_nb_devices)
{
	if (num_devices > max_nb_devices) {
		RTE_LOG(ERR, PORT, "invalid number of devices\n");
		return -1;
	}
	return 0;
}

/*
 * Initialises a given port using global settings and with the rx buffers
 * coming from the mbuf_pool passed as parameter
 */
static inline int
port_init(uint8_t port, struct rte_mempool *mbuf_pool)
{
	struct rte_eth_dev_info dev_info;
	struct rte_eth_conf port_conf;
	uint16_t rx_rings, tx_rings = (uint16_t)rte_lcore_count();
	const uint16_t rx_ring_size = RTE_TEST_RX_DESC_DEFAULT, tx_ring_size = RTE_TEST_TX_DESC_DEFAULT;
	int retval;
	uint16_t q;

	/* The max pool number from dev_info will be used to validate the pool number specified in cmd line */
	rte_eth_dev_info_get (port, &dev_info);

	/*configure the number of supported virtio devices based on VMDQ limits */
	num_devices = dev_info.max_vmdq_pools;
	num_queues = dev_info.max_rx_queues;

	retval = validate_num_devices(MAX_DEVICES);
	if (retval < 0)
		return retval;

	/* Get port configuration. */
	retval = get_eth_conf(&port_conf, num_devices);
	if (retval < 0)
		return retval;

	if (port >= rte_eth_dev_count()) return -1;

	rx_rings = (uint16_t)num_queues,
	/* Configure ethernet device. */
	retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
	if (retval != 0)
		return retval;

	/* Setup the queues. */
	for (q = 0; q < rx_rings; q ++) {
		retval = rte_eth_rx_queue_setup(port, q, rx_ring_size,
						rte_eth_dev_socket_id(port), &rx_conf_default,
						mbuf_pool);
		if (retval < 0)
			return retval;
	}
	for (q = 0; q < tx_rings; q ++) {
		retval = rte_eth_tx_queue_setup(port, q, tx_ring_size,
						rte_eth_dev_socket_id(port), &tx_conf_default);
		if (retval < 0)
			return retval;
	}

	/* Start the device. */
	retval  = rte_eth_dev_start(port);
	if (retval < 0)
		return retval;

	rte_eth_macaddr_get(port, &vmdq_ports_eth_addr[port]);
	RTE_LOG(INFO, PORT, "Max virtio devices supported: %u\n", num_devices);
	RTE_LOG(INFO, PORT, "Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8
			" %02"PRIx8" %02"PRIx8" %02"PRIx8"\n",
			(unsigned)port,
			vmdq_ports_eth_addr[port].addr_bytes[0],
			vmdq_ports_eth_addr[port].addr_bytes[1],
			vmdq_ports_eth_addr[port].addr_bytes[2],
			vmdq_ports_eth_addr[port].addr_bytes[3],
			vmdq_ports_eth_addr[port].addr_bytes[4],
			vmdq_ports_eth_addr[port].addr_bytes[5]);

	return 0;
}

/*
 * Set character device basename.
 */
static int
us_vhost_parse_basename(const char *q_arg)
{
	/* parse number string */

	if (strnlen(q_arg, MAX_BASENAME_SZ) > MAX_BASENAME_SZ)
		return -1;
	else
		rte_snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg);

	return 0;
}

/*
 * Parse the portmask provided at run time.
 */
static int
parse_portmask(const char *portmask)
{
	char *end = NULL;
	unsigned long pm;

	errno = 0;

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

	if (pm == 0)
		return -1;

	return pm;

}

/*
 * Parse num options at run time.
 */
static int
parse_num_opt(const char *q_arg, uint32_t max_valid_value)
{
	char *end = NULL;
	unsigned long num;

	errno = 0;

	/* parse unsigned int string */
	num = strtoul(q_arg, &end, 10);
	if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0') || (errno != 0))
		return -1;

	if (num > max_valid_value)
		return -1;

	return num;

}

/*
 * Display usage
 */
static void
us_vhost_usage(const char *prgname)
{
	RTE_LOG(INFO, CONFIG, "%s [EAL options] -- -p PORTMASK --vm2vm [0|1] --rx_retry [0|1] --mergeable [0|1] --stats [0-N] --dev-basename <name> --dev-index [0-N] --nb-devices ND\n"
	"		-p PORTMASK: Set mask for ports to be used by application\n"
	"		--vm2vm [0|1]: disable/enable(default) vm2vm comms\n"
	"		--rx-retry [0|1]: disable/enable(default) retries on rx. Enable retry if destintation queue is full\n"
	"		--rx-retry-delay [0-N]: timeout(in usecond) between retries on RX. This makes effect only if retries on rx enabled\n"
	"		--rx-retry-num [0-N]: the number of retries on rx. This makes effect only if retries on rx enabled\n"
	"		--mergeable [0|1]: disable(default)/enable RX mergeable buffers\n"
	"		--stats [0-N]: 0: Disable stats, N: Time in seconds to print stats\n"
	"		--dev-basename: The basename to be used for the character device.\n"
	"		--dev-index [0-N]: Defaults to zero if not used. Index is appended to basename.\n",
	       prgname);
}

/*
 * Parse the arguments given in the command line of the application.
 */
static int
us_vhost_parse_args(int argc, char **argv)
{
	int opt, ret;
	int option_index;
	unsigned i;
	const char *prgname = argv[0];
	static struct option long_option[] = {
		{"vm2vm", required_argument, NULL, 0},
		{"rx-retry", required_argument, NULL, 0},
		{"rx-retry-delay", required_argument, NULL, 0},
		{"rx-retry-num", required_argument, NULL, 0},
		{"mergeable", required_argument, NULL, 0},
		{"stats", required_argument, NULL, 0},
		{"dev-basename", required_argument, NULL, 0},
		{"dev-index", required_argument, NULL, 0},
		{NULL, 0, 0, 0}
	};

	/* Parse command line */
	while ((opt = getopt_long(argc, argv, "p:",long_option, &option_index)) != EOF) {
		switch (opt) {
		/* Portmask */
		case 'p':
			enabled_port_mask = parse_portmask(optarg);
			if (enabled_port_mask == 0) {
				RTE_LOG(INFO, CONFIG, "Invalid portmask\n");
				us_vhost_usage(prgname);
				return -1;
			}
			break;

		case 0:
			/* Enable/disable vm2vm comms. */
			if (!strncmp(long_option[option_index].name, "vm2vm", MAX_LONG_OPT_SZ)) {
				ret = parse_num_opt(optarg, 1);
				if (ret == -1) {
					RTE_LOG(INFO, CONFIG, "Invalid argument for vm2vm [0|1]\n");
					us_vhost_usage(prgname);
					return -1;
				} else {
					enable_vm2vm = ret;
				}
			}

			/* Enable/disable retries on RX. */
			if (!strncmp(long_option[option_index].name, "rx-retry", MAX_LONG_OPT_SZ)) {
				ret = parse_num_opt(optarg, 1);
				if (ret == -1) {
					RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry [0|1]\n");
					us_vhost_usage(prgname);
					return -1;
				} else {
					enable_retry = ret;
				}
			}

			/* Specify the retries delay time (in useconds) on RX. */
			if (!strncmp(long_option[option_index].name, "rx-retry-delay", MAX_LONG_OPT_SZ)) {
				ret = parse_num_opt(optarg, INT32_MAX);
				if (ret == -1) {
					RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry-delay [0-N]\n");
					us_vhost_usage(prgname);
					return -1;
				} else {
					burst_rx_delay_time = ret;
				}
			}

			/* Specify the retries number on RX. */
			if (!strncmp(long_option[option_index].name, "rx-retry-num", MAX_LONG_OPT_SZ)) {
				ret = parse_num_opt(optarg, INT32_MAX);
				if (ret == -1) {
					RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry-num [0-N]\n");
					us_vhost_usage(prgname);
					return -1;
				} else {
					burst_rx_retry_num = ret;
				}
			}

			/* Enable/disable RX mergeable buffers. */
			if (!strncmp(long_option[option_index].name, "mergeable", MAX_LONG_OPT_SZ)) {
				ret = parse_num_opt(optarg, 1);
				if (ret == -1) {
					RTE_LOG(INFO, CONFIG, "Invalid argument for mergeable [0|1]\n");
					us_vhost_usage(prgname);
					return -1;
				} else {
					if (ret)
						VHOST_FEATURES = (1ULL << VIRTIO_NET_F_MRG_RXBUF);
				}
			}

			/* Enable/disable stats. */
			if (!strncmp(long_option[option_index].name, "stats", MAX_LONG_OPT_SZ)) {
				ret = parse_num_opt(optarg, INT32_MAX);
				if (ret == -1) {
					RTE_LOG(INFO, CONFIG, "Invalid argument for stats [0..N]\n");
					us_vhost_usage(prgname);
					return -1;
				} else {
					enable_stats = ret;
				}
			}

			/* Set character device basename. */
			if (!strncmp(long_option[option_index].name, "dev-basename", MAX_LONG_OPT_SZ)) {
				if (us_vhost_parse_basename(optarg) == -1) {
					RTE_LOG(INFO, CONFIG, "Invalid argument for character device basename (Max %d characters)\n", MAX_BASENAME_SZ);
					us_vhost_usage(prgname);
					return -1;
				}
			}

			/* Set character device index. */
			if (!strncmp(long_option[option_index].name, "dev-index", MAX_LONG_OPT_SZ)) {
				ret = parse_num_opt(optarg, INT32_MAX);
				if (ret == -1) {
					RTE_LOG(INFO, CONFIG, "Invalid argument for character device index [0..N]\n");
					us_vhost_usage(prgname);
					return -1;
				} else {
					dev_index = ret;
				}
			}

			break;

			/* Invalid option - print options. */
		default:
			us_vhost_usage(prgname);
			return -1;
		}
	}

	for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
		if (enabled_port_mask & (1 << i))
			ports[num_ports++] = (uint8_t)i;
	}

	if ((num_ports ==  0) || (num_ports > MAX_SUP_PORTS)) {
		RTE_LOG(INFO, PORT, "Current enabled port number is %u,"
			"but only %u port can be enabled\n",num_ports, MAX_SUP_PORTS);
		return -1;
	}

	return 0;
}

/*
 * Update the global var NUM_PORTS and array PORTS according to system ports number
 * and return valid ports number
 */
static unsigned check_ports_num(unsigned nb_ports)
{
	unsigned valid_num_ports = num_ports;
	unsigned portid;

	if (num_ports > nb_ports) {
		RTE_LOG(INFO, PORT, "\nSpecified port number(%u) exceeds total system port number(%u)\n",
			num_ports, nb_ports);
		num_ports = nb_ports;
	}

	for (portid = 0; portid < num_ports; portid ++) {
		if (ports[portid] >= nb_ports) {
			RTE_LOG(INFO, PORT, "\nSpecified port ID(%u) exceeds max system port ID(%u)\n",
				ports[portid], (nb_ports - 1));
			ports[portid] = INVALID_PORT_ID;
			valid_num_ports--;
		}
	}
	return valid_num_ports;
}

/*
 * Macro to print out packet contents. Wrapped in debug define so that the
 * data path is not effected when debug is disabled.
 */
#ifdef DEBUG
#define PRINT_PACKET(device, addr, size, header) do {																\
	char *pkt_addr = (char*)(addr);																					\
	unsigned int index;																								\
	char packet[MAX_PRINT_BUFF];																					\
																													\
	if ((header))																									\
		rte_snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Header size %d: ", (device->device_fh), (size));				\
	else																											\
		rte_snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Packet size %d: ", (device->device_fh), (size));				\
	for (index = 0; index < (size); index++) {																		\
		rte_snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF),	\
			"%02hhx ", pkt_addr[index]);																			\
	}																												\
	rte_snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), "\n");	\
																													\
	LOG_DEBUG(DATA, "%s", packet);																					\
} while(0)
#else
#define PRINT_PACKET(device, addr, size, header) do{} while(0)
#endif

/*
 * Function to convert guest physical addresses to vhost virtual addresses. This
 * is used to convert virtio buffer addresses.
 */
static inline uint64_t __attribute__((always_inline))
gpa_to_vva(struct virtio_net *dev, uint64_t guest_pa)
{
	struct virtio_memory_regions *region;
	uint32_t regionidx;
	uint64_t vhost_va = 0;

	for (regionidx = 0; regionidx < dev->mem->nregions; regionidx++) {
		region = &dev->mem->regions[regionidx];
		if ((guest_pa >= region->guest_phys_address) &&
			(guest_pa <= region->guest_phys_address_end)) {
			vhost_va = region->address_offset + guest_pa;
			break;
		}
	}
	LOG_DEBUG(DATA, "(%"PRIu64") GPA %p| VVA %p\n",
		dev->device_fh, (void*)(uintptr_t)guest_pa, (void*)(uintptr_t)vhost_va);

	return vhost_va;
}

/*
 * This function adds buffers to the virtio devices RX virtqueue. Buffers can
 * be received from the physical port or from another virtio device. A packet
 * count is returned to indicate the number of packets that were succesfully
 * added to the RX queue.
 */
static inline uint32_t __attribute__((always_inline))
virtio_dev_rx(struct virtio_net *dev, struct rte_mbuf **pkts, uint32_t count)
{
	struct vhost_virtqueue *vq;
	struct vring_desc *desc;
	struct rte_mbuf *buff;
	/* The virtio_hdr is initialised to 0. */
	struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0,0,0,0,0,0},0};
	uint64_t buff_addr = 0;
	uint64_t buff_hdr_addr = 0;
	uint32_t head[MAX_PKT_BURST], packet_len = 0;
	uint32_t head_idx, packet_success = 0;
	uint32_t mergeable, mrg_count = 0;
	uint32_t retry = 0;
	uint16_t avail_idx, res_cur_idx;
	uint16_t res_base_idx, res_end_idx;
	uint16_t free_entries;
	uint8_t success = 0;

	LOG_DEBUG(DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh);
	vq = dev->virtqueue[VIRTIO_RXQ];
	count = (count > MAX_PKT_BURST) ? MAX_PKT_BURST : count;
	/* As many data cores may want access to available buffers, they need to be reserved. */
	do {
		res_base_idx = vq->last_used_idx_res;
		avail_idx = *((volatile uint16_t *)&vq->avail->idx);

		free_entries = (avail_idx - res_base_idx);		
		/* If retry is enabled and the queue is full then we wait and retry to avoid packet loss. */
		if (enable_retry && unlikely(count > free_entries)) {
			for (retry = 0; retry < burst_rx_retry_num; retry++) {
				rte_delay_us(burst_rx_delay_time);
				avail_idx =
					*((volatile uint16_t *)&vq->avail->idx);
				free_entries = (avail_idx - res_base_idx);
				if (count <= free_entries)
					break;
			}
		}

		/*check that we have enough buffers*/
		if (unlikely(count > free_entries))
			count = free_entries;

		if (count == 0)
			return 0;

		res_end_idx = res_base_idx + count;
		/* vq->last_used_idx_res is atomically updated. */
		success = rte_atomic16_cmpset(&vq->last_used_idx_res, res_base_idx,
									res_end_idx);
	} while (unlikely(success == 0));
	res_cur_idx = res_base_idx;
	LOG_DEBUG(DATA, "(%"PRIu64") Current Index %d| End Index %d\n", dev->device_fh, res_cur_idx, res_end_idx);

	/* Prefetch available ring to retrieve indexes. */
	rte_prefetch0(&vq->avail->ring[res_cur_idx & (vq->size - 1)]);

	/* Check if the VIRTIO_NET_F_MRG_RXBUF feature is enabled. */
	mergeable = dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF);

	/* Retrieve all of the head indexes first to avoid caching issues. */
	for (head_idx = 0; head_idx < count; head_idx++)
		head[head_idx] = vq->avail->ring[(res_cur_idx + head_idx) & (vq->size - 1)];

	/*Prefetch descriptor index. */
	rte_prefetch0(&vq->desc[head[packet_success]]);

	while (res_cur_idx != res_end_idx) {
		/* Get descriptor from available ring */
		desc = &vq->desc[head[packet_success]];

		buff = pkts[packet_success];

		/* Convert from gpa to vva (guest physical addr -> vhost virtual addr) */
		buff_addr = gpa_to_vva(dev, desc->addr);
		/* Prefetch buffer address. */
		rte_prefetch0((void*)(uintptr_t)buff_addr);

		if (mergeable && (mrg_count != 0)) {
			desc->len = packet_len = rte_pktmbuf_data_len(buff);
		} else {
			/* Copy virtio_hdr to packet and increment buffer address */
			buff_hdr_addr = buff_addr;
			packet_len = rte_pktmbuf_data_len(buff) + vq->vhost_hlen;

			/*
			 * If the descriptors are chained the header and data are placed in
			 * separate buffers.
			 */
			if (desc->flags & VRING_DESC_F_NEXT) {
				desc->len = vq->vhost_hlen;
				desc = &vq->desc[desc->next];
				/* Buffer address translation. */
				buff_addr = gpa_to_vva(dev, desc->addr);
				desc->len = rte_pktmbuf_data_len(buff);
			} else {
				buff_addr += vq->vhost_hlen;
				desc->len = packet_len;
			}
		}

		PRINT_PACKET(dev, (uintptr_t)buff_addr, rte_pktmbuf_data_len(buff), 0);

		/* Update used ring with desc information */
		vq->used->ring[res_cur_idx & (vq->size - 1)].id = head[packet_success];
		vq->used->ring[res_cur_idx & (vq->size - 1)].len = packet_len;

		/* Copy mbuf data to buffer */
		rte_memcpy((void *)(uintptr_t)buff_addr, (const void*)buff->pkt.data, rte_pktmbuf_data_len(buff));

		res_cur_idx++;
		packet_success++;

		/* If mergeable is disabled then a header is required per buffer. */
		if (!mergeable) {
			rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void*)&virtio_hdr, vq->vhost_hlen);
			PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1);
		} else {
			mrg_count++;
			/* Merge buffer can only handle so many buffers at a time. Tell the guest if this limit is reached. */
			if ((mrg_count == MAX_MRG_PKT_BURST) || (res_cur_idx == res_end_idx)) {
				virtio_hdr.num_buffers = mrg_count;
				LOG_DEBUG(DATA, "(%"PRIu64") RX: Num merge buffers %d\n", dev->device_fh, virtio_hdr.num_buffers);
				rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void*)&virtio_hdr, vq->vhost_hlen);
				PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1);
				mrg_count = 0;
			}
		}
		if (res_cur_idx < res_end_idx) {
			/* Prefetch descriptor index. */
			rte_prefetch0(&vq->desc[head[packet_success]]);
		}
	}

	rte_compiler_barrier();

	/* Wait until it's our turn to add our buffer to the used ring. */
	while (unlikely(vq->last_used_idx != res_base_idx))
		rte_pause();

	*(volatile uint16_t *)&vq->used->idx += count;
	vq->last_used_idx = res_end_idx;

	/* Kick the guest if necessary. */
	if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
		eventfd_write((int)vq->kickfd, 1);
	return count;
}

/*
 * Compares a packet destination MAC address to a device MAC address.
 */
static inline int __attribute__((always_inline))
ether_addr_cmp(struct ether_addr *ea, struct ether_addr *eb)
{
	return (((*(uint64_t *)ea ^ *(uint64_t *)eb) & MAC_ADDR_CMP) == 0);
}

/*
 * This function learns the MAC address of the device and registers this along with a
 * vlan tag to a VMDQ.
 */
static int
link_vmdq(struct virtio_net *dev, struct rte_mbuf *m)
{
	struct ether_hdr *pkt_hdr;
	struct virtio_net_data_ll *dev_ll;
	int i, ret;

	/* Learn MAC address of guest device from packet */
	pkt_hdr = (struct ether_hdr *)m->pkt.data;

	dev_ll = ll_root_used;

	while (dev_ll != NULL) {
		if (ether_addr_cmp(&(pkt_hdr->s_addr), &dev_ll->dev->mac_address)) {
			RTE_LOG(INFO, DATA, "(%"PRIu64") WARNING: This device is using an existing MAC address and has not been registered.\n", dev->device_fh);
			return -1;
		}
		dev_ll = dev_ll->next;
	}

	for (i = 0; i < ETHER_ADDR_LEN; i++)
		dev->mac_address.addr_bytes[i] = pkt_hdr->s_addr.addr_bytes[i];

	/* vlan_tag currently uses the device_id. */
	dev->vlan_tag = vlan_tags[dev->device_fh];
	dev->vmdq_rx_q = dev->device_fh * (num_queues/num_devices);

	/* Print out VMDQ registration info. */
	RTE_LOG(INFO, DATA, "(%"PRIu64") MAC_ADDRESS %02x:%02x:%02x:%02x:%02x:%02x and VLAN_TAG %d registered\n",
		dev->device_fh,
		dev->mac_address.addr_bytes[0], dev->mac_address.addr_bytes[1],
		dev->mac_address.addr_bytes[2], dev->mac_address.addr_bytes[3],
		dev->mac_address.addr_bytes[4], dev->mac_address.addr_bytes[5],
		dev->vlan_tag);

	/* Register the MAC address. */
	ret = rte_eth_dev_mac_addr_add(ports[0], &dev->mac_address, (uint32_t)dev->device_fh);
	if (ret)
		RTE_LOG(ERR, DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n",
					dev->device_fh);

	/* Enable stripping of the vlan tag as we handle routing. */
	rte_eth_dev_set_vlan_strip_on_queue(ports[0], (uint16_t)dev->vmdq_rx_q, 1);

	/* Set device as ready for RX. */
	dev->ready = DEVICE_RX;

	return 0;
}

/*
 * Removes MAC address and vlan tag from VMDQ. Ensures that nothing is adding buffers to the RX
 * queue before disabling RX on the device.
 */
static inline void
unlink_vmdq(struct virtio_net *dev)
{
	unsigned i = 0;
	unsigned rx_count;
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];

	if (dev->ready == DEVICE_RX) {
		/*clear MAC and VLAN settings*/
		rte_eth_dev_mac_addr_remove(ports[0], &dev->mac_address);
		for (i = 0; i < 6; i++)
			dev->mac_address.addr_bytes[i] = 0;

		dev->vlan_tag = 0;

		/*Clear out the receive buffers*/
		rx_count = rte_eth_rx_burst(ports[0],
					(uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);

		while (rx_count) {
			for (i = 0; i < rx_count; i++)
				rte_pktmbuf_free(pkts_burst[i]);

			rx_count = rte_eth_rx_burst(ports[0],
					(uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);
		}

		dev->ready = DEVICE_MAC_LEARNING;
	}
}

/*
 * Check if the packet destination MAC address is for a local device. If so then put
 * the packet on that devices RX queue. If not then return.
 */
static inline unsigned __attribute__((always_inline))
virtio_tx_local(struct virtio_net *dev, struct rte_mbuf *m)
{
	struct virtio_net_data_ll *dev_ll;
	struct ether_hdr *pkt_hdr;
	uint64_t ret = 0;

	pkt_hdr = (struct ether_hdr *)m->pkt.data;

	/*get the used devices list*/
	dev_ll = ll_root_used;

	while (dev_ll != NULL) {
		if ((dev_ll->dev->ready == DEVICE_RX) && ether_addr_cmp(&(pkt_hdr->d_addr),
				          &dev_ll->dev->mac_address)) {

			/* Drop the packet if the TX packet is destined for the TX device. */
			if (dev_ll->dev->device_fh == dev->device_fh) {
				LOG_DEBUG(DATA, "(%"PRIu64") TX: Source and destination MAC addresses are the same. Dropping packet.\n",
							dev_ll->dev->device_fh);
				return 0;
			}


			LOG_DEBUG(DATA, "(%"PRIu64") TX: MAC address is local\n", dev_ll->dev->device_fh);

			if (dev_ll->dev->remove) {
				/*drop the packet if the device is marked for removal*/
				LOG_DEBUG(DATA, "(%"PRIu64") Device is marked for removal\n", dev_ll->dev->device_fh);
			} else {
				/*send the packet to the local virtio device*/
				ret = virtio_dev_rx(dev_ll->dev, &m, 1);
				if (enable_stats) {
					rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx_total, 1);
					rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx, ret);
					dev_statistics[dev->device_fh].tx_total++;
					dev_statistics[dev->device_fh].tx += ret;
				}
			}

			return 0;
		}
		dev_ll = dev_ll->next;
	}

	return -1;
}

/*
 * This function routes the TX packet to the correct interface. This may be a local device
 * or the physical port.
 */
static inline void __attribute__((always_inline))
virtio_tx_route(struct virtio_net* dev, struct rte_mbuf *m, struct rte_mempool *mbuf_pool, uint16_t vlan_tag)
{
	struct mbuf_table *tx_q;
	struct vlan_ethhdr *vlan_hdr;
	struct rte_mbuf **m_table;
	struct rte_mbuf *mbuf;
	unsigned len, ret;
	const uint16_t lcore_id = rte_lcore_id();

	/*check if destination is local VM*/
	if (enable_vm2vm && (virtio_tx_local(dev, m) == 0)) {
		return;
	}

	LOG_DEBUG(DATA, "(%"PRIu64") TX: MAC address is external\n", dev->device_fh);

	/*Add packet to the port tx queue*/
	tx_q = &lcore_tx_queue[lcore_id];
	len = tx_q->len;

	/* Allocate an mbuf and populate the structure. */
	mbuf = rte_pktmbuf_alloc(mbuf_pool);
	if (unlikely(mbuf == NULL)) {
		RTE_LOG(ERR, DATA, "Failed to allocate memory for mbuf.\n");
		return;
	}

	mbuf->pkt.data_len = m->pkt.data_len + VLAN_HLEN;
	mbuf->pkt.pkt_len = mbuf->pkt.data_len;

	/* Copy ethernet header to mbuf. */
	rte_memcpy((void*)mbuf->pkt.data, (const void*)m->pkt.data, ETH_HLEN);


	/* Setup vlan header. Bytes need to be re-ordered for network with htons()*/
	vlan_hdr = (struct vlan_ethhdr *) mbuf->pkt.data;
	vlan_hdr->h_vlan_encapsulated_proto = vlan_hdr->h_vlan_proto;
	vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q);
	vlan_hdr->h_vlan_TCI = htons(vlan_tag);

	/* Copy the remaining packet contents to the mbuf. */
	rte_memcpy((void*) ((uint8_t*)mbuf->pkt.data + VLAN_ETH_HLEN),
		(const void*) ((uint8_t*)m->pkt.data + ETH_HLEN), (m->pkt.data_len - ETH_HLEN));
	tx_q->m_table[len] = mbuf;
	len++;
	if (enable_stats) {
		dev_statistics[dev->device_fh].tx_total++;
		dev_statistics[dev->device_fh].tx++;
	}

	if (unlikely(len == MAX_PKT_BURST)) {
		m_table = (struct rte_mbuf **)tx_q->m_table;
		ret = rte_eth_tx_burst(ports[0], (uint16_t)tx_q->txq_id, m_table, (uint16_t) len);
		/* Free any buffers not handled by TX and update the port stats. */
		if (unlikely(ret < len)) {
			do {
				rte_pktmbuf_free(m_table[ret]);
			} while (++ret < len);
		}

		len = 0;
	}

	tx_q->len = len;
	return;
}

static inline void __attribute__((always_inline))
virtio_dev_tx(struct virtio_net* dev, struct rte_mempool *mbuf_pool)
{
	struct rte_mbuf m;
	struct vhost_virtqueue *vq;
	struct vring_desc *desc;
	uint64_t buff_addr = 0;
	uint32_t head[MAX_PKT_BURST];
	uint32_t used_idx;
	uint32_t i;
	uint16_t free_entries, packet_success = 0;
	uint16_t avail_idx;

	vq = dev->virtqueue[VIRTIO_TXQ];
	avail_idx =  *((volatile uint16_t *)&vq->avail->idx);

	/* If there are no available buffers then return. */
	if (vq->last_used_idx == avail_idx)
		return;

	LOG_DEBUG(DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh);

	/* Prefetch available ring to retrieve head indexes. */
	rte_prefetch0(&vq->avail->ring[vq->last_used_idx & (vq->size - 1)]);

	/*get the number of free entries in the ring*/
	free_entries = (avail_idx - vq->last_used_idx);

	/* Limit to MAX_PKT_BURST. */
	if (free_entries > MAX_PKT_BURST)
		free_entries = MAX_PKT_BURST;

	LOG_DEBUG(DATA, "(%"PRIu64") Buffers available %d\n", dev->device_fh, free_entries);
	/* Retrieve all of the head indexes first to avoid caching issues. */
	for (i = 0; i < free_entries; i++)
		head[i] = vq->avail->ring[(vq->last_used_idx + i) & (vq->size - 1)];

	/* Prefetch descriptor index. */
	rte_prefetch0(&vq->desc[head[packet_success]]);
	rte_prefetch0(&vq->used->ring[vq->last_used_idx & (vq->size - 1)]);

	while (packet_success < free_entries) {
		desc = &vq->desc[head[packet_success]];

		/* Discard first buffer as it is the virtio header */
		desc = &vq->desc[desc->next];
			
		/* Buffer address translation. */
		buff_addr = gpa_to_vva(dev, desc->addr);
		/* Prefetch buffer address. */
		rte_prefetch0((void*)(uintptr_t)buff_addr);
		
		used_idx = vq->last_used_idx & (vq->size - 1);
		
		if (packet_success < (free_entries - 1)) {
			/* Prefetch descriptor index. */
			rte_prefetch0(&vq->desc[head[packet_success+1]]);
			rte_prefetch0(&vq->used->ring[(used_idx + 1) & (vq->size - 1)]);
		}

		/* Update used index buffer information. */
		vq->used->ring[used_idx].id = head[packet_success];
		vq->used->ring[used_idx].len = 0;

		/* Setup dummy mbuf. This is copied to a real mbuf if transmitted out the physical port. */
		m.pkt.data_len = desc->len;
		m.pkt.data = (void*)(uintptr_t)buff_addr;

		PRINT_PACKET(dev, (uintptr_t)buff_addr, desc->len, 0);

		/* If this is the first received packet we need to learn the MAC and setup VMDQ */
		if (dev->ready == DEVICE_MAC_LEARNING) {
			if (dev->remove || (link_vmdq(dev, &m) == -1)) {
				/*discard frame if device is scheduled for removal or a duplicate MAC address is found. */
				packet_success += free_entries;
				vq->last_used_idx += packet_success;
				break;
			}
		}
		virtio_tx_route(dev, &m, mbuf_pool, (uint16_t)dev->device_fh);

		vq->last_used_idx++;
		packet_success++;
	}

	rte_compiler_barrier();
	vq->used->idx += packet_success;
	/* Kick guest if required. */
	if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
		eventfd_write((int)vq->kickfd, 1);
}

/*
 * This function is called by each data core. It handles all RX/TX registered with the
 * core. For TX the specific lcore linked list is used. For RX, MAC addresses are compared
 * with all devices in the main linked list.
 */
static int
switch_worker(__attribute__((unused)) void *arg)
{
	struct rte_mempool *mbuf_pool = arg;
	struct virtio_net *dev = NULL;
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
	struct virtio_net_data_ll *dev_ll;
	struct mbuf_table *tx_q;
	volatile struct lcore_ll_info *lcore_ll;
	const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
	uint64_t prev_tsc, diff_tsc, cur_tsc, ret_count = 0;
	unsigned ret, i;
	const uint16_t lcore_id = rte_lcore_id();
	const uint16_t num_cores = (uint16_t)rte_lcore_count();
	uint16_t rx_count = 0;

	RTE_LOG(INFO, DATA, "Procesing on Core %u started \n", lcore_id);
	lcore_ll = lcore_info[lcore_id].lcore_ll;
	prev_tsc = 0;

	tx_q = &lcore_tx_queue[lcore_id];
	for (i = 0; i < num_cores; i ++) {
		if (lcore_ids[i] == lcore_id) {
			tx_q->txq_id = i;
			break;
		}
	}

	while(1) {
		cur_tsc = rte_rdtsc();
		/*
		 * TX burst queue drain
		 */
		diff_tsc = cur_tsc - prev_tsc;
		if (unlikely(diff_tsc > drain_tsc)) {

			if (tx_q->len) {
				LOG_DEBUG(DATA, "TX queue drained after timeout with burst size %u \n", tx_q->len);

				/*Tx any packets in the queue*/
				ret = rte_eth_tx_burst(ports[0], (uint16_t)tx_q->txq_id,
									   (struct rte_mbuf **)tx_q->m_table,
									   (uint16_t)tx_q->len);
				if (unlikely(ret < tx_q->len)) {
					do {
						rte_pktmbuf_free(tx_q->m_table[ret]);
					} while (++ret < tx_q->len);
				}

				tx_q->len = 0;
			}

			prev_tsc = cur_tsc;

		}

		rte_prefetch0(lcore_ll->ll_root_used);
		/* 
		 * Inform the configuration core that we have exited the linked list and that no devices are
		 * in use if requested.
		 */
		if (lcore_ll->dev_removal_flag == REQUEST_DEV_REMOVAL) 
			lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;

		/*
		 * Process devices
		 */
		dev_ll = lcore_ll->ll_root_used;

		while (dev_ll != NULL) {
			/*get virtio device ID*/
			dev = dev_ll->dev;

			if (dev->remove) {
				dev_ll = dev_ll->next;
				unlink_vmdq(dev);
				dev->ready = DEVICE_SAFE_REMOVE;
				continue;
			}
			if (likely(dev->ready == DEVICE_RX)) {
				/*Handle guest RX*/
				rx_count = rte_eth_rx_burst(ports[0],
					(uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);

				if (rx_count) {
					ret_count = virtio_dev_rx(dev, pkts_burst, rx_count);
					if (enable_stats) {
						rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx_total, rx_count);
						rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx, ret_count);
					}
					while (likely(rx_count)) {
						rx_count--;
						rte_pktmbuf_free_seg(pkts_burst[rx_count]);
					}

				}
			}

			if (!dev->remove)
				/*Handle guest TX*/
				virtio_dev_tx(dev, mbuf_pool);

			/*move to the next device in the list*/
			dev_ll = dev_ll->next;
		}
	}

	return 0;
}

/*
 * Add an entry to a used linked list. A free entry must first be found in the free linked list
 * using get_data_ll_free_entry();
 */
static void
add_data_ll_entry(struct virtio_net_data_ll **ll_root_addr, struct virtio_net_data_ll *ll_dev)
{
	struct virtio_net_data_ll *ll = *ll_root_addr;

	/* Set next as NULL and use a compiler barrier to avoid reordering. */
	ll_dev->next = NULL;
	rte_compiler_barrier();

	/* If ll == NULL then this is the first device. */
	if (ll) {
		/* Increment to the tail of the linked list. */
		while ((ll->next != NULL) )
			ll = ll->next;

		ll->next = ll_dev;
	} else {
		*ll_root_addr = ll_dev;
	}
}

/*
 * Remove an entry from a used linked list. The entry must then be added to the free linked list
 * using put_data_ll_free_entry().
 */
static void
rm_data_ll_entry(struct virtio_net_data_ll **ll_root_addr, struct virtio_net_data_ll *ll_dev, struct virtio_net_data_ll *ll_dev_last)
{
	struct virtio_net_data_ll *ll = *ll_root_addr;
	
	if (unlikely((ll == NULL) || (ll_dev == NULL)))
		return;

	if (ll_dev == ll)
		*ll_root_addr = ll_dev->next;
	else
		if (likely(ll_dev_last != NULL))
			ll_dev_last->next = ll_dev->next;
		else
			RTE_LOG(ERR, CONFIG, "Remove entry form ll failed.\n");
}

/*
 * Find and return an entry from the free linked list.
 */
static struct virtio_net_data_ll *
get_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr)
{
	struct virtio_net_data_ll *ll_free = *ll_root_addr;
	struct virtio_net_data_ll *ll_dev;

	if (ll_free == NULL)
		return NULL;

	ll_dev = ll_free;
	*ll_root_addr = ll_free->next;

	return ll_dev;
}

/*
 * Place an entry back on to the free linked list.
 */
static void
put_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr, struct virtio_net_data_ll *ll_dev)
{
	struct virtio_net_data_ll *ll_free = *ll_root_addr;

	if (ll_dev == NULL)
		return;

	ll_dev->next = ll_free;
	*ll_root_addr = ll_dev;
}

/*
 * Creates a linked list of a given size.
 */
static struct virtio_net_data_ll *
alloc_data_ll(uint32_t size)
{
	struct virtio_net_data_ll *ll_new;
	uint32_t i;

	/* Malloc and then chain the linked list. */
	ll_new = malloc(size * sizeof(struct virtio_net_data_ll));
	if (ll_new == NULL) {
		RTE_LOG(ERR, CONFIG, "Failed to allocate memory for ll_new.\n");
		return NULL;
	}

	for (i = 0; i < size - 1; i++) {
		ll_new[i].dev = NULL;
		ll_new[i].next = &ll_new[i+1];
	}
	ll_new[i].next = NULL;

	return (ll_new);
}

/*
 * Create the main linked list along with each individual cores linked list. A used and a free list
 * are created to manage entries.
 */
static int
init_data_ll (void)
{
	int lcore;

	RTE_LCORE_FOREACH_SLAVE(lcore) {
		lcore_info[lcore].lcore_ll = malloc(sizeof(struct lcore_ll_info));
		if (lcore_info[lcore].lcore_ll == NULL) {
			RTE_LOG(ERR, CONFIG, "Failed to allocate memory for lcore_ll.\n");
			return -1;
		}

		lcore_info[lcore].lcore_ll->device_num = 0;
		lcore_info[lcore].lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
		lcore_info[lcore].lcore_ll->ll_root_used = NULL;
		if (num_devices % num_switching_cores)
			lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll((num_devices / num_switching_cores) + 1);
		else
			lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll(num_devices / num_switching_cores);
	}

	/* Allocate devices up to a maximum of MAX_DEVICES. */
	ll_root_free = alloc_data_ll(MIN((num_devices), MAX_DEVICES));

	return 0;
}

/*
 * Set virtqueue flags so that we do not receive interrupts.
 */
static void
set_irq_status (struct virtio_net *dev)
{
	dev->virtqueue[VIRTIO_RXQ]->used->flags = VRING_USED_F_NO_NOTIFY;
	dev->virtqueue[VIRTIO_TXQ]->used->flags = VRING_USED_F_NO_NOTIFY;
}

/*
 * Remove a device from the specific data core linked list and from the main linked list. Synchonization 
 * occurs through the use of the lcore dev_removal_flag. Device is made volatile here to avoid re-ordering 
 * of dev->remove=1 which can cause an infinite loop in the rte_pause loop.
 */
static void
destroy_device (volatile struct virtio_net *dev)
{
	struct virtio_net_data_ll *ll_lcore_dev_cur;
	struct virtio_net_data_ll *ll_main_dev_cur;
	struct virtio_net_data_ll *ll_lcore_dev_last = NULL;
	struct virtio_net_data_ll *ll_main_dev_last = NULL;
	int lcore;

	dev->flags &= ~VIRTIO_DEV_RUNNING;

	/*set the remove flag. */
	dev->remove = 1;

	while(dev->ready != DEVICE_SAFE_REMOVE) {
		rte_pause();
	}

	/* Search for entry to be removed from lcore ll */
	ll_lcore_dev_cur = lcore_info[dev->coreid].lcore_ll->ll_root_used;
	while (ll_lcore_dev_cur != NULL) {
		if (ll_lcore_dev_cur->dev == dev) {
			break;
		} else {
			ll_lcore_dev_last = ll_lcore_dev_cur;
			ll_lcore_dev_cur = ll_lcore_dev_cur->next;
		}
	}

	if (ll_lcore_dev_cur == NULL) {
		RTE_LOG(ERR, CONFIG, "Failed to find the dev to be destroy.\n");
		return;
	}

	/* Search for entry to be removed from main ll */
	ll_main_dev_cur = ll_root_used;
	ll_main_dev_last = NULL;
	while (ll_main_dev_cur != NULL) {
		if (ll_main_dev_cur->dev == dev) {
			break;
		} else {
			ll_main_dev_last = ll_main_dev_cur;
			ll_main_dev_cur = ll_main_dev_cur->next;
		}
	}

	/* Remove entries from the lcore and main ll. */
	rm_data_ll_entry(&lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->ll_root_used, ll_lcore_dev_cur, ll_lcore_dev_last);
	rm_data_ll_entry(&ll_root_used, ll_main_dev_cur, ll_main_dev_last);

	/* Set the dev_removal_flag on each lcore. */
	RTE_LCORE_FOREACH_SLAVE(lcore) {
		lcore_info[lcore].lcore_ll->dev_removal_flag = REQUEST_DEV_REMOVAL;
	}
	
	/* 
	 * Once each core has set the dev_removal_flag to ACK_DEV_REMOVAL we can be sure that
	 * they can no longer access the device removed from the linked lists and that the devices
	 * are no longer in use.
	 */
	RTE_LCORE_FOREACH_SLAVE(lcore) {
		while (lcore_info[lcore].lcore_ll->dev_removal_flag != ACK_DEV_REMOVAL) {
			rte_pause();
		}
	}

	/* Add the entries back to the lcore and main free ll.*/
	put_data_ll_free_entry(&lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->ll_root_free, ll_lcore_dev_cur);
	put_data_ll_free_entry(&ll_root_free, ll_main_dev_cur);
	
	/* Decrement number of device on the lcore. */
	lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->device_num--;
	
	RTE_LOG(INFO, DATA, "(%"PRIu64") Device has been removed from data core\n", dev->device_fh);
}

/*
 * A new device is added to a data core. First the device is added to the main linked list
 * and the allocated to a specific data core.
 */
static int
new_device (struct virtio_net *dev)
{
	struct virtio_net_data_ll *ll_dev;
	int lcore, core_add = 0;
	uint32_t device_num_min = num_devices;

	/* Add device to main ll */
	ll_dev = get_data_ll_free_entry(&ll_root_free);
	if (ll_dev == NULL) {
		RTE_LOG(INFO, DATA, "(%"PRIu64") No free entry found in linked list. Device limit "
			"of %d devices per core has been reached\n",
			dev->device_fh, num_devices);
		return -1;
	}
	ll_dev->dev = dev;
	add_data_ll_entry(&ll_root_used, ll_dev);

	/*reset ready flag*/
	dev->ready = DEVICE_MAC_LEARNING;
	dev->remove = 0;

	/* Find a suitable lcore to add the device. */
	RTE_LCORE_FOREACH_SLAVE(lcore) {
		if (lcore_info[lcore].lcore_ll->device_num < device_num_min) {
			device_num_min = lcore_info[lcore].lcore_ll->device_num;
			core_add = lcore;
		}
	}
	/* Add device to lcore ll */
	ll_dev->dev->coreid = core_add;
	ll_dev = get_data_ll_free_entry(&lcore_info[ll_dev->dev->coreid].lcore_ll->ll_root_free);
	if (ll_dev == NULL) {
		RTE_LOG(INFO, DATA, "(%"PRIu64") Failed to add device to data core\n", dev->device_fh);
		destroy_device(dev);
		return -1;
	}
	ll_dev->dev = dev;
	add_data_ll_entry(&lcore_info[ll_dev->dev->coreid].lcore_ll->ll_root_used, ll_dev);

	/* Initialize device stats */
	memset(&dev_statistics[dev->device_fh], 0, sizeof(struct device_statistics));

	/* Disable notifications. */
	set_irq_status(dev);
	lcore_info[ll_dev->dev->coreid].lcore_ll->device_num++;
	dev->flags |= VIRTIO_DEV_RUNNING;

	RTE_LOG(INFO, DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, dev->coreid);

	return 0;
}

/*
 * These callback allow devices to be added to the data core when configuration
 * has been fully complete.
 */
static const struct virtio_net_device_ops virtio_net_device_ops =
{
	.new_device =  new_device,
	.destroy_device = destroy_device,
};

/*
 * This is a thread will wake up after a period to print stats if the user has
 * enabled them.
 */
static void
print_stats(void)
{
	struct virtio_net_data_ll *dev_ll;
	uint64_t tx_dropped, rx_dropped;
	uint64_t tx, tx_total, rx, rx_total;
	uint32_t device_fh;
	const char clr[] = { 27, '[', '2', 'J', '\0' };
	const char top_left[] = { 27, '[', '1', ';', '1', 'H','\0' };

	while(1) {
		sleep(enable_stats);

		/* Clear screen and move to top left */
		printf("%s%s", clr, top_left);

		printf("\nDevice statistics ====================================");

		dev_ll = ll_root_used;
		while (dev_ll != NULL) {
			device_fh = (uint32_t)dev_ll->dev->device_fh;
			tx_total = dev_statistics[device_fh].tx_total;
			tx = dev_statistics[device_fh].tx;
			tx_dropped = tx_total - tx;
			rx_total = rte_atomic64_read(&dev_statistics[device_fh].rx_total);
			rx = rte_atomic64_read(&dev_statistics[device_fh].rx);
			rx_dropped = rx_total - rx;

			printf("\nStatistics for device %"PRIu32" ------------------------------"
					"\nTX total: 		%"PRIu64""
					"\nTX dropped: 		%"PRIu64""
					"\nTX successful: 		%"PRIu64""
					"\nRX total: 		%"PRIu64""
					"\nRX dropped: 		%"PRIu64""
					"\nRX successful: 		%"PRIu64"",
					device_fh,
					tx_total,
					tx_dropped,
					tx,
					rx_total,
					rx_dropped,
					rx);

			dev_ll = dev_ll->next;
		}
		printf("\n======================================================\n");
	}
}

/*
 * Main function, does initialisation and calls the per-lcore functions. The CUSE
 * device is also registered here to handle the IOCTLs.
 */
int
MAIN(int argc, char *argv[])
{
	struct rte_mempool *mbuf_pool;
	unsigned lcore_id, core_id = 0;
	unsigned nb_ports, valid_num_ports;
	int ret;
	uint8_t portid;
	static pthread_t tid;

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

	/* parse app arguments */
	ret = us_vhost_parse_args(argc, argv);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Invalid argument\n");

	if (rte_pmd_init_all() != 0 || rte_eal_pci_probe() != 0)
		rte_exit(EXIT_FAILURE, "Error with NIC driver initialization\n");

	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id ++)
		if (rte_lcore_is_enabled(lcore_id))
			lcore_ids[core_id ++] = lcore_id;

	if (rte_lcore_count() > RTE_MAX_LCORE)
		rte_exit(EXIT_FAILURE,"Not enough cores\n");

	/*set the number of swithcing cores available*/
	num_switching_cores = rte_lcore_count()-1;

	/* Get the number of physical ports. */
	nb_ports = rte_eth_dev_count();
	if (nb_ports > RTE_MAX_ETHPORTS)
		nb_ports = RTE_MAX_ETHPORTS;

	/*
   	 * Update the global var NUM_PORTS and global array PORTS
  	 * and get value of var VALID_NUM_PORTS according to system ports number
  	 */
	valid_num_ports = check_ports_num(nb_ports);

	if ((valid_num_ports ==  0) || (valid_num_ports > MAX_SUP_PORTS)) {
		RTE_LOG(INFO, PORT, "Current enabled port number is %u,"
			"but only %u port can be enabled\n",num_ports, MAX_SUP_PORTS);
		return -1;
	}

	/* Create the mbuf pool. */
	mbuf_pool = rte_mempool_create("MBUF_POOL", NUM_MBUFS_PER_PORT * valid_num_ports,
				       MBUF_SIZE, MBUF_CACHE_SIZE,
				       sizeof(struct rte_pktmbuf_pool_private),
				       rte_pktmbuf_pool_init, NULL,
				       rte_pktmbuf_init, NULL,
				       rte_socket_id(), 0);
	if (mbuf_pool == NULL)
		rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");

	/* Set log level. */
	rte_set_log_level(LOG_LEVEL);

	/* initialize all ports */
	for (portid = 0; portid < nb_ports; portid++) {
		/* skip ports that are not enabled */
		if ((enabled_port_mask & (1 << portid)) == 0) {
			RTE_LOG(INFO, PORT, "Skipping disabled port %d\n", portid);
			continue;
		}
		if (port_init(portid, mbuf_pool) != 0)
			rte_exit(EXIT_FAILURE, "Cannot initialize network ports\n");
	}

	/* Initialise all linked lists. */
	if (init_data_ll() == -1)
		rte_exit(EXIT_FAILURE, "Failed to initialize linked list\n");

	/* Initialize device stats */
	memset(&dev_statistics, 0, sizeof(dev_statistics));

	/* Enable stats if the user option is set. */
	if (enable_stats)
		pthread_create(&tid, NULL, (void*)print_stats, NULL );

	/* Launch all data cores. */
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		rte_eal_remote_launch(switch_worker, mbuf_pool, lcore_id);
	}

	/* Register CUSE device to handle IOCTLs. */
	ret = register_cuse_device((char*)&dev_basename, dev_index, get_virtio_net_callbacks());
	if (ret != 0)
		rte_exit(EXIT_FAILURE,"CUSE device setup failure.\n");

	init_virtio_net(&virtio_net_device_ops);

	/* Start CUSE session. */
	start_cuse_session_loop();
	return 0;

}