aboutsummaryrefslogtreecommitdiffstats
path: root/examples/kni/main.c
blob: e37b1ad36245a10d8b0c00722080edd962243a6f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2014 Intel Corporation
 */

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

#include <netinet/in.h>
#include <linux/if.h>
#include <linux/if_tun.h>
#include <fcntl.h>
#include <sys/ioctl.h>
#include <unistd.h>
#include <signal.h>

#include <rte_common.h>
#include <rte_log.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_eal.h>
#include <rte_per_lcore.h>
#include <rte_launch.h>
#include <rte_atomic.h>
#include <rte_lcore.h>
#include <rte_branch_prediction.h>
#include <rte_interrupts.h>
#include <rte_bus_pci.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
#include <rte_string_fns.h>
#include <rte_cycles.h>
#include <rte_malloc.h>
#include <rte_kni.h>

/* Macros for printing using RTE_LOG */
#define RTE_LOGTYPE_APP RTE_LOGTYPE_USER1

/* Max size of a single packet */
#define MAX_PACKET_SZ           2048

/* Size of the data buffer in each mbuf */
#define MBUF_DATA_SZ (MAX_PACKET_SZ + RTE_PKTMBUF_HEADROOM)

/* Number of mbufs in mempool that is created */
#define NB_MBUF                 (8192 * 16)

/* How many packets to attempt to read from NIC in one go */
#define PKT_BURST_SZ            32

/* How many objects (mbufs) to keep in per-lcore mempool cache */
#define MEMPOOL_CACHE_SZ        PKT_BURST_SZ

/* Number of RX ring descriptors */
#define NB_RXD                  1024

/* Number of TX ring descriptors */
#define NB_TXD                  1024

/* Total octets in ethernet header */
#define KNI_ENET_HEADER_SIZE    14

/* Total octets in the FCS */
#define KNI_ENET_FCS_SIZE       4

#define KNI_US_PER_SECOND       1000000
#define KNI_SECOND_PER_DAY      86400

#define KNI_MAX_KTHREAD 32
/*
 * Structure of port parameters
 */
struct kni_port_params {
	uint16_t port_id;/* Port ID */
	unsigned lcore_rx; /* lcore ID for RX */
	unsigned lcore_tx; /* lcore ID for TX */
	uint32_t nb_lcore_k; /* Number of lcores for KNI multi kernel threads */
	uint32_t nb_kni; /* Number of KNI devices to be created */
	unsigned lcore_k[KNI_MAX_KTHREAD]; /* lcore ID list for kthreads */
	struct rte_kni *kni[KNI_MAX_KTHREAD]; /* KNI context pointers */
} __rte_cache_aligned;

static struct kni_port_params *kni_port_params_array[RTE_MAX_ETHPORTS];


/* Options for configuring ethernet port */
static struct rte_eth_conf port_conf = {
	.txmode = {
		.mq_mode = ETH_MQ_TX_NONE,
	},
};

/* Mempool for mbufs */
static struct rte_mempool * pktmbuf_pool = NULL;

/* Mask of enabled ports */
static uint32_t ports_mask = 0;
/* Ports set in promiscuous mode off by default. */
static int promiscuous_on = 0;
/* Monitor link status continually. off by default. */
static int monitor_links;

/* Structure type for recording kni interface specific stats */
struct kni_interface_stats {
	/* number of pkts received from NIC, and sent to KNI */
	uint64_t rx_packets;

	/* number of pkts received from NIC, but failed to send to KNI */
	uint64_t rx_dropped;

	/* number of pkts received from KNI, and sent to NIC */
	uint64_t tx_packets;

	/* number of pkts received from KNI, but failed to send to NIC */
	uint64_t tx_dropped;
};

/* kni device statistics array */
static struct kni_interface_stats kni_stats[RTE_MAX_ETHPORTS];

static int kni_change_mtu(uint16_t port_id, unsigned int new_mtu);
static int kni_config_network_interface(uint16_t port_id, uint8_t if_up);
static int kni_config_mac_address(uint16_t port_id, uint8_t mac_addr[]);

static rte_atomic32_t kni_stop = RTE_ATOMIC32_INIT(0);

/* Print out statistics on packets handled */
static void
print_stats(void)
{
	uint16_t i;

	printf("\n**KNI example application statistics**\n"
	       "======  ==============  ============  ============  ============  ============\n"
	       " Port    Lcore(RX/TX)    rx_packets    rx_dropped    tx_packets    tx_dropped\n"
	       "------  --------------  ------------  ------------  ------------  ------------\n");
	for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
		if (!kni_port_params_array[i])
			continue;

		printf("%7d %10u/%2u %13"PRIu64" %13"PRIu64" %13"PRIu64" "
							"%13"PRIu64"\n", i,
					kni_port_params_array[i]->lcore_rx,
					kni_port_params_array[i]->lcore_tx,
						kni_stats[i].rx_packets,
						kni_stats[i].rx_dropped,
						kni_stats[i].tx_packets,
						kni_stats[i].tx_dropped);
	}
	printf("======  ==============  ============  ============  ============  ============\n");
}

/* Custom handling of signals to handle stats and kni processing */
static void
signal_handler(int signum)
{
	/* When we receive a USR1 signal, print stats */
	if (signum == SIGUSR1) {
		print_stats();
	}

	/* When we receive a USR2 signal, reset stats */
	if (signum == SIGUSR2) {
		memset(&kni_stats, 0, sizeof(kni_stats));
		printf("\n** Statistics have been reset **\n");
		return;
	}

	/* When we receive a RTMIN or SIGINT signal, stop kni processing */
	if (signum == SIGRTMIN || signum == SIGINT){
		printf("\nSIGRTMIN/SIGINT received. KNI processing stopping.\n");
		rte_atomic32_inc(&kni_stop);
		return;
        }
}

static void
kni_burst_free_mbufs(struct rte_mbuf **pkts, unsigned num)
{
	unsigned i;

	if (pkts == NULL)
		return;

	for (i = 0; i < num; i++) {
		rte_pktmbuf_free(pkts[i]);
		pkts[i] = NULL;
	}
}

/**
 * Interface to burst rx and enqueue mbufs into rx_q
 */
static void
kni_ingress(struct kni_port_params *p)
{
	uint8_t i;
	uint16_t port_id;
	unsigned nb_rx, num;
	uint32_t nb_kni;
	struct rte_mbuf *pkts_burst[PKT_BURST_SZ];

	if (p == NULL)
		return;

	nb_kni = p->nb_kni;
	port_id = p->port_id;
	for (i = 0; i < nb_kni; i++) {
		/* Burst rx from eth */
		nb_rx = rte_eth_rx_burst(port_id, 0, pkts_burst, PKT_BURST_SZ);
		if (unlikely(nb_rx > PKT_BURST_SZ)) {
			RTE_LOG(ERR, APP, "Error receiving from eth\n");
			return;
		}
		/* Burst tx to kni */
		num = rte_kni_tx_burst(p->kni[i], pkts_burst, nb_rx);
		if (num)
			kni_stats[port_id].rx_packets += num;

		rte_kni_handle_request(p->kni[i]);
		if (unlikely(num < nb_rx)) {
			/* Free mbufs not tx to kni interface */
			kni_burst_free_mbufs(&pkts_burst[num], nb_rx - num);
			kni_stats[port_id].rx_dropped += nb_rx - num;
		}
	}
}

/**
 * Interface to dequeue mbufs from tx_q and burst tx
 */
static void
kni_egress(struct kni_port_params *p)
{
	uint8_t i;
	uint16_t port_id;
	unsigned nb_tx, num;
	uint32_t nb_kni;
	struct rte_mbuf *pkts_burst[PKT_BURST_SZ];

	if (p == NULL)
		return;

	nb_kni = p->nb_kni;
	port_id = p->port_id;
	for (i = 0; i < nb_kni; i++) {
		/* Burst rx from kni */
		num = rte_kni_rx_burst(p->kni[i], pkts_burst, PKT_BURST_SZ);
		if (unlikely(num > PKT_BURST_SZ)) {
			RTE_LOG(ERR, APP, "Error receiving from KNI\n");
			return;
		}
		/* Burst tx to eth */
		nb_tx = rte_eth_tx_burst(port_id, 0, pkts_burst, (uint16_t)num);
		if (nb_tx)
			kni_stats[port_id].tx_packets += nb_tx;
		if (unlikely(nb_tx < num)) {
			/* Free mbufs not tx to NIC */
			kni_burst_free_mbufs(&pkts_burst[nb_tx], num - nb_tx);
			kni_stats[port_id].tx_dropped += num - nb_tx;
		}
	}
}

static int
main_loop(__rte_unused void *arg)
{
	uint16_t i;
	int32_t f_stop;
	const unsigned lcore_id = rte_lcore_id();
	enum lcore_rxtx {
		LCORE_NONE,
		LCORE_RX,
		LCORE_TX,
		LCORE_MAX
	};
	enum lcore_rxtx flag = LCORE_NONE;

	RTE_ETH_FOREACH_DEV(i) {
		if (!kni_port_params_array[i])
			continue;
		if (kni_port_params_array[i]->lcore_rx == (uint8_t)lcore_id) {
			flag = LCORE_RX;
			break;
		} else if (kni_port_params_array[i]->lcore_tx ==
						(uint8_t)lcore_id) {
			flag = LCORE_TX;
			break;
		}
	}

	if (flag == LCORE_RX) {
		RTE_LOG(INFO, APP, "Lcore %u is reading from port %d\n",
					kni_port_params_array[i]->lcore_rx,
					kni_port_params_array[i]->port_id);
		while (1) {
			f_stop = rte_atomic32_read(&kni_stop);
			if (f_stop)
				break;
			kni_ingress(kni_port_params_array[i]);
		}
	} else if (flag == LCORE_TX) {
		RTE_LOG(INFO, APP, "Lcore %u is writing to port %d\n",
					kni_port_params_array[i]->lcore_tx,
					kni_port_params_array[i]->port_id);
		while (1) {
			f_stop = rte_atomic32_read(&kni_stop);
			if (f_stop)
				break;
			kni_egress(kni_port_params_array[i]);
		}
	} else
		RTE_LOG(INFO, APP, "Lcore %u has nothing to do\n", lcore_id);

	return 0;
}

/* Display usage instructions */
static void
print_usage(const char *prgname)
{
	RTE_LOG(INFO, APP, "\nUsage: %s [EAL options] -- -p PORTMASK -P -m "
		   "[--config (port,lcore_rx,lcore_tx,lcore_kthread...)"
		   "[,(port,lcore_rx,lcore_tx,lcore_kthread...)]]\n"
		   "    -p PORTMASK: hex bitmask of ports to use\n"
		   "    -P : enable promiscuous mode\n"
		   "    -m : enable monitoring of port carrier state\n"
		   "    --config (port,lcore_rx,lcore_tx,lcore_kthread...): "
		   "port and lcore configurations\n",
	           prgname);
}

/* Convert string to unsigned number. 0 is returned if error occurs */
static uint32_t
parse_unsigned(const char *portmask)
{
	char *end = NULL;
	unsigned long num;

	num = strtoul(portmask, &end, 16);
	if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0'))
		return 0;

	return (uint32_t)num;
}

static void
print_config(void)
{
	uint32_t i, j;
	struct kni_port_params **p = kni_port_params_array;

	for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
		if (!p[i])
			continue;
		RTE_LOG(DEBUG, APP, "Port ID: %d\n", p[i]->port_id);
		RTE_LOG(DEBUG, APP, "Rx lcore ID: %u, Tx lcore ID: %u\n",
					p[i]->lcore_rx, p[i]->lcore_tx);
		for (j = 0; j < p[i]->nb_lcore_k; j++)
			RTE_LOG(DEBUG, APP, "Kernel thread lcore ID: %u\n",
							p[i]->lcore_k[j]);
	}
}

static int
parse_config(const char *arg)
{
	const char *p, *p0 = arg;
	char s[256], *end;
	unsigned size;
	enum fieldnames {
		FLD_PORT = 0,
		FLD_LCORE_RX,
		FLD_LCORE_TX,
		_NUM_FLD = KNI_MAX_KTHREAD + 3,
	};
	int i, j, nb_token;
	char *str_fld[_NUM_FLD];
	unsigned long int_fld[_NUM_FLD];
	uint16_t port_id, nb_kni_port_params = 0;

	memset(&kni_port_params_array, 0, sizeof(kni_port_params_array));
	while (((p = strchr(p0, '(')) != NULL) &&
		nb_kni_port_params < RTE_MAX_ETHPORTS) {
		p++;
		if ((p0 = strchr(p, ')')) == NULL)
			goto fail;
		size = p0 - p;
		if (size >= sizeof(s)) {
			printf("Invalid config parameters\n");
			goto fail;
		}
		snprintf(s, sizeof(s), "%.*s", size, p);
		nb_token = rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',');
		if (nb_token <= FLD_LCORE_TX) {
			printf("Invalid config parameters\n");
			goto fail;
		}
		for (i = 0; i < nb_token; i++) {
			errno = 0;
			int_fld[i] = strtoul(str_fld[i], &end, 0);
			if (errno != 0 || end == str_fld[i]) {
				printf("Invalid config parameters\n");
				goto fail;
			}
		}

		i = 0;
		port_id = int_fld[i++];
		if (port_id >= RTE_MAX_ETHPORTS) {
			printf("Port ID %d could not exceed the maximum %d\n",
						port_id, RTE_MAX_ETHPORTS);
			goto fail;
		}
		if (kni_port_params_array[port_id]) {
			printf("Port %d has been configured\n", port_id);
			goto fail;
		}
		kni_port_params_array[port_id] =
			rte_zmalloc("KNI_port_params",
				    sizeof(struct kni_port_params), RTE_CACHE_LINE_SIZE);
		kni_port_params_array[port_id]->port_id = port_id;
		kni_port_params_array[port_id]->lcore_rx =
					(uint8_t)int_fld[i++];
		kni_port_params_array[port_id]->lcore_tx =
					(uint8_t)int_fld[i++];
		if (kni_port_params_array[port_id]->lcore_rx >= RTE_MAX_LCORE ||
		kni_port_params_array[port_id]->lcore_tx >= RTE_MAX_LCORE) {
			printf("lcore_rx %u or lcore_tx %u ID could not "
						"exceed the maximum %u\n",
				kni_port_params_array[port_id]->lcore_rx,
				kni_port_params_array[port_id]->lcore_tx,
						(unsigned)RTE_MAX_LCORE);
			goto fail;
		}
		for (j = 0; i < nb_token && j < KNI_MAX_KTHREAD; i++, j++)
			kni_port_params_array[port_id]->lcore_k[j] =
						(uint8_t)int_fld[i];
		kni_port_params_array[port_id]->nb_lcore_k = j;
	}
	print_config();

	return 0;

fail:
	for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
		if (kni_port_params_array[i]) {
			rte_free(kni_port_params_array[i]);
			kni_port_params_array[i] = NULL;
		}
	}

	return -1;
}

static int
validate_parameters(uint32_t portmask)
{
	uint32_t i;

	if (!portmask) {
		printf("No port configured in port mask\n");
		return -1;
	}

	for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
		if (((portmask & (1 << i)) && !kni_port_params_array[i]) ||
			(!(portmask & (1 << i)) && kni_port_params_array[i]))
			rte_exit(EXIT_FAILURE, "portmask is not consistent "
				"to port ids specified in --config\n");

		if (kni_port_params_array[i] && !rte_lcore_is_enabled(\
			(unsigned)(kni_port_params_array[i]->lcore_rx)))
			rte_exit(EXIT_FAILURE, "lcore id %u for "
					"port %d receiving not enabled\n",
					kni_port_params_array[i]->lcore_rx,
					kni_port_params_array[i]->port_id);

		if (kni_port_params_array[i] && !rte_lcore_is_enabled(\
			(unsigned)(kni_port_params_array[i]->lcore_tx)))
			rte_exit(EXIT_FAILURE, "lcore id %u for "
					"port %d transmitting not enabled\n",
					kni_port_params_array[i]->lcore_tx,
					kni_port_params_array[i]->port_id);

	}

	return 0;
}

#define CMDLINE_OPT_CONFIG  "config"

/* Parse the arguments given in the command line of the application */
static int
parse_args(int argc, char **argv)
{
	int opt, longindex, ret = 0;
	const char *prgname = argv[0];
	static struct option longopts[] = {
		{CMDLINE_OPT_CONFIG, required_argument, NULL, 0},
		{NULL, 0, NULL, 0}
	};

	/* Disable printing messages within getopt() */
	opterr = 0;

	/* Parse command line */
	while ((opt = getopt_long(argc, argv, "p:Pm", longopts,
						&longindex)) != EOF) {
		switch (opt) {
		case 'p':
			ports_mask = parse_unsigned(optarg);
			break;
		case 'P':
			promiscuous_on = 1;
			break;
		case 'm':
			monitor_links = 1;
			break;
		case 0:
			if (!strncmp(longopts[longindex].name,
				     CMDLINE_OPT_CONFIG,
				     sizeof(CMDLINE_OPT_CONFIG))) {
				ret = parse_config(optarg);
				if (ret) {
					printf("Invalid config\n");
					print_usage(prgname);
					return -1;
				}
			}
			break;
		default:
			print_usage(prgname);
			rte_exit(EXIT_FAILURE, "Invalid option specified\n");
		}
	}

	/* Check that options were parsed ok */
	if (validate_parameters(ports_mask) < 0) {
		print_usage(prgname);
		rte_exit(EXIT_FAILURE, "Invalid parameters\n");
	}

	return ret;
}

/* Initialize KNI subsystem */
static void
init_kni(void)
{
	unsigned int num_of_kni_ports = 0, i;
	struct kni_port_params **params = kni_port_params_array;

	/* Calculate the maximum number of KNI interfaces that will be used */
	for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
		if (kni_port_params_array[i]) {
			num_of_kni_ports += (params[i]->nb_lcore_k ?
				params[i]->nb_lcore_k : 1);
		}
	}

	/* Invoke rte KNI init to preallocate the ports */
	rte_kni_init(num_of_kni_ports);
}

/* Initialise a single port on an Ethernet device */
static void
init_port(uint16_t port)
{
	int ret;
	uint16_t nb_rxd = NB_RXD;
	uint16_t nb_txd = NB_TXD;
	struct rte_eth_dev_info dev_info;
	struct rte_eth_rxconf rxq_conf;
	struct rte_eth_txconf txq_conf;
	struct rte_eth_conf local_port_conf = port_conf;

	/* Initialise device and RX/TX queues */
	RTE_LOG(INFO, APP, "Initialising port %u ...\n", (unsigned)port);
	fflush(stdout);
	rte_eth_dev_info_get(port, &dev_info);
	if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
		local_port_conf.txmode.offloads |=
			DEV_TX_OFFLOAD_MBUF_FAST_FREE;
	ret = rte_eth_dev_configure(port, 1, 1, &local_port_conf);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Could not configure port%u (%d)\n",
		            (unsigned)port, ret);

	ret = rte_eth_dev_adjust_nb_rx_tx_desc(port, &nb_rxd, &nb_txd);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Could not adjust number of descriptors "
				"for port%u (%d)\n", (unsigned)port, ret);

	rxq_conf = dev_info.default_rxconf;
	rxq_conf.offloads = local_port_conf.rxmode.offloads;
	ret = rte_eth_rx_queue_setup(port, 0, nb_rxd,
		rte_eth_dev_socket_id(port), &rxq_conf, pktmbuf_pool);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Could not setup up RX queue for "
				"port%u (%d)\n", (unsigned)port, ret);

	txq_conf = dev_info.default_txconf;
	txq_conf.offloads = local_port_conf.txmode.offloads;
	ret = rte_eth_tx_queue_setup(port, 0, nb_txd,
		rte_eth_dev_socket_id(port), &txq_conf);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Could not setup up TX queue for "
				"port%u (%d)\n", (unsigned)port, ret);

	ret = rte_eth_dev_start(port);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Could not start port%u (%d)\n",
						(unsigned)port, ret);

	if (promiscuous_on)
		rte_eth_promiscuous_enable(port);
}

/* Check the link status of all ports in up to 9s, and print them finally */
static void
check_all_ports_link_status(uint32_t port_mask)
{
#define CHECK_INTERVAL 100 /* 100ms */
#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */
	uint16_t portid;
	uint8_t count, all_ports_up, print_flag = 0;
	struct rte_eth_link link;

	printf("\nChecking link status\n");
	fflush(stdout);
	for (count = 0; count <= MAX_CHECK_TIME; count++) {
		all_ports_up = 1;
		RTE_ETH_FOREACH_DEV(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 %uMbps - %s\n",
						portid, link.link_speed,
				(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
					("full-duplex") : ("half-duplex\n"));
				else
					printf("Port %d Link Down\n", portid);
				continue;
			}
			/* clear all_ports_up flag if any link down */
			if (link.link_status == ETH_LINK_DOWN) {
				all_ports_up = 0;
				break;
			}
		}
		/* after finally printing all link status, get out */
		if (print_flag == 1)
			break;

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

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

static void
log_link_state(struct rte_kni *kni, int prev, struct rte_eth_link *link)
{
	if (kni == NULL || link == NULL)
		return;

	if (prev == ETH_LINK_DOWN && link->link_status == ETH_LINK_UP) {
		RTE_LOG(INFO, APP, "%s NIC Link is Up %d Mbps %s %s.\n",
			rte_kni_get_name(kni),
			link->link_speed,
			link->link_autoneg ?  "(AutoNeg)" : "(Fixed)",
			link->link_duplex ?  "Full Duplex" : "Half Duplex");
	} else if (prev == ETH_LINK_UP && link->link_status == ETH_LINK_DOWN) {
		RTE_LOG(INFO, APP, "%s NIC Link is Down.\n",
			rte_kni_get_name(kni));
	}
}

/*
 * Monitor the link status of all ports and update the
 * corresponding KNI interface(s)
 */
static void *
monitor_all_ports_link_status(void *arg)
{
	uint16_t portid;
	struct rte_eth_link link;
	unsigned int i;
	struct kni_port_params **p = kni_port_params_array;
	int prev;
	(void) arg;

	while (monitor_links) {
		rte_delay_ms(500);
		RTE_ETH_FOREACH_DEV(portid) {
			if ((ports_mask & (1 << portid)) == 0)
				continue;
			memset(&link, 0, sizeof(link));
			rte_eth_link_get_nowait(portid, &link);
			for (i = 0; i < p[portid]->nb_kni; i++) {
				prev = rte_kni_update_link(p[portid]->kni[i],
						link.link_status);
				log_link_state(p[portid]->kni[i], prev, &link);
			}
		}
	}
	return NULL;
}

/* Callback for request of changing MTU */
static int
kni_change_mtu(uint16_t port_id, unsigned int new_mtu)
{
	int ret;
	uint16_t nb_rxd = NB_RXD;
	struct rte_eth_conf conf;
	struct rte_eth_dev_info dev_info;
	struct rte_eth_rxconf rxq_conf;

	if (!rte_eth_dev_is_valid_port(port_id)) {
		RTE_LOG(ERR, APP, "Invalid port id %d\n", port_id);
		return -EINVAL;
	}

	RTE_LOG(INFO, APP, "Change MTU of port %d to %u\n", port_id, new_mtu);

	/* Stop specific port */
	rte_eth_dev_stop(port_id);

	memcpy(&conf, &port_conf, sizeof(conf));
	/* Set new MTU */
	if (new_mtu > ETHER_MAX_LEN)
		conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
	else
		conf.rxmode.offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;

	/* mtu + length of header + length of FCS = max pkt length */
	conf.rxmode.max_rx_pkt_len = new_mtu + KNI_ENET_HEADER_SIZE +
							KNI_ENET_FCS_SIZE;
	ret = rte_eth_dev_configure(port_id, 1, 1, &conf);
	if (ret < 0) {
		RTE_LOG(ERR, APP, "Fail to reconfigure port %d\n", port_id);
		return ret;
	}

	ret = rte_eth_dev_adjust_nb_rx_tx_desc(port_id, &nb_rxd, NULL);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Could not adjust number of descriptors "
				"for port%u (%d)\n", (unsigned int)port_id,
				ret);

	rte_eth_dev_info_get(port_id, &dev_info);
	rxq_conf = dev_info.default_rxconf;
	rxq_conf.offloads = conf.rxmode.offloads;
	ret = rte_eth_rx_queue_setup(port_id, 0, nb_rxd,
		rte_eth_dev_socket_id(port_id), &rxq_conf, pktmbuf_pool);
	if (ret < 0) {
		RTE_LOG(ERR, APP, "Fail to setup Rx queue of port %d\n",
				port_id);
		return ret;
	}

	/* Restart specific port */
	ret = rte_eth_dev_start(port_id);
	if (ret < 0) {
		RTE_LOG(ERR, APP, "Fail to restart port %d\n", port_id);
		return ret;
	}

	return 0;
}

/* Callback for request of configuring network interface up/down */
static int
kni_config_network_interface(uint16_t port_id, uint8_t if_up)
{
	int ret = 0;

	if (!rte_eth_dev_is_valid_port(port_id)) {
		RTE_LOG(ERR, APP, "Invalid port id %d\n", port_id);
		return -EINVAL;
	}

	RTE_LOG(INFO, APP, "Configure network interface of %d %s\n",
					port_id, if_up ? "up" : "down");

	if (if_up != 0) { /* Configure network interface up */
		rte_eth_dev_stop(port_id);
		ret = rte_eth_dev_start(port_id);
	} else /* Configure network interface down */
		rte_eth_dev_stop(port_id);

	if (ret < 0)
		RTE_LOG(ERR, APP, "Failed to start port %d\n", port_id);

	return ret;
}

static void
print_ethaddr(const char *name, struct ether_addr *mac_addr)
{
	char buf[ETHER_ADDR_FMT_SIZE];
	ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, mac_addr);
	RTE_LOG(INFO, APP, "\t%s%s\n", name, buf);
}

/* Callback for request of configuring mac address */
static int
kni_config_mac_address(uint16_t port_id, uint8_t mac_addr[])
{
	int ret = 0;

	if (!rte_eth_dev_is_valid_port(port_id)) {
		RTE_LOG(ERR, APP, "Invalid port id %d\n", port_id);
		return -EINVAL;
	}

	RTE_LOG(INFO, APP, "Configure mac address of %d\n", port_id);
	print_ethaddr("Address:", (struct ether_addr *)mac_addr);

	ret = rte_eth_dev_default_mac_addr_set(port_id,
					       (struct ether_addr *)mac_addr);
	if (ret < 0)
		RTE_LOG(ERR, APP, "Failed to config mac_addr for port %d\n",
			port_id);

	return ret;
}

static int
kni_alloc(uint16_t port_id)
{
	uint8_t i;
	struct rte_kni *kni;
	struct rte_kni_conf conf;
	struct kni_port_params **params = kni_port_params_array;

	if (port_id >= RTE_MAX_ETHPORTS || !params[port_id])
		return -1;

	params[port_id]->nb_kni = params[port_id]->nb_lcore_k ?
				params[port_id]->nb_lcore_k : 1;

	for (i = 0; i < params[port_id]->nb_kni; i++) {
		/* Clear conf at first */
		memset(&conf, 0, sizeof(conf));
		if (params[port_id]->nb_lcore_k) {
			snprintf(conf.name, RTE_KNI_NAMESIZE,
					"vEth%u_%u", port_id, i);
			conf.core_id = params[port_id]->lcore_k[i];
			conf.force_bind = 1;
		} else
			snprintf(conf.name, RTE_KNI_NAMESIZE,
						"vEth%u", port_id);
		conf.group_id = port_id;
		conf.mbuf_size = MAX_PACKET_SZ;
		/*
		 * The first KNI device associated to a port
		 * is the master, for multiple kernel thread
		 * environment.
		 */
		if (i == 0) {
			struct rte_kni_ops ops;
			struct rte_eth_dev_info dev_info;
			const struct rte_pci_device *pci_dev;
			const struct rte_bus *bus = NULL;

			memset(&dev_info, 0, sizeof(dev_info));
			rte_eth_dev_info_get(port_id, &dev_info);

			if (dev_info.device)
				bus = rte_bus_find_by_device(dev_info.device);
			if (bus && !strcmp(bus->name, "pci")) {
				pci_dev = RTE_DEV_TO_PCI(dev_info.device);
				conf.addr = pci_dev->addr;
				conf.id = pci_dev->id;
			}
			/* Get the interface default mac address */
			rte_eth_macaddr_get(port_id,
					(struct ether_addr *)&conf.mac_addr);

			rte_eth_dev_get_mtu(port_id, &conf.mtu);

			memset(&ops, 0, sizeof(ops));
			ops.port_id = port_id;
			ops.change_mtu = kni_change_mtu;
			ops.config_network_if = kni_config_network_interface;
			ops.config_mac_address = kni_config_mac_address;

			kni = rte_kni_alloc(pktmbuf_pool, &conf, &ops);
		} else
			kni = rte_kni_alloc(pktmbuf_pool, &conf, NULL);

		if (!kni)
			rte_exit(EXIT_FAILURE, "Fail to create kni for "
						"port: %d\n", port_id);
		params[port_id]->kni[i] = kni;
	}

	return 0;
}

static int
kni_free_kni(uint16_t port_id)
{
	uint8_t i;
	struct kni_port_params **p = kni_port_params_array;

	if (port_id >= RTE_MAX_ETHPORTS || !p[port_id])
		return -1;

	for (i = 0; i < p[port_id]->nb_kni; i++) {
		if (rte_kni_release(p[port_id]->kni[i]))
			printf("Fail to release kni\n");
		p[port_id]->kni[i] = NULL;
	}
	rte_eth_dev_stop(port_id);

	return 0;
}

/* Initialise ports/queues etc. and start main loop on each core */
int
main(int argc, char** argv)
{
	int ret;
	uint16_t nb_sys_ports, port;
	unsigned i;
	void *retval;
	pthread_t kni_link_tid;
	int pid;

	/* Associate signal_hanlder function with USR signals */
	signal(SIGUSR1, signal_handler);
	signal(SIGUSR2, signal_handler);
	signal(SIGRTMIN, signal_handler);
	signal(SIGINT, signal_handler);

	/* Initialise EAL */
	ret = rte_eal_init(argc, argv);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Could not initialise EAL (%d)\n", ret);
	argc -= ret;
	argv += ret;

	/* Parse application arguments (after the EAL ones) */
	ret = parse_args(argc, argv);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Could not parse input parameters\n");

	/* Create the mbuf pool */
	pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", NB_MBUF,
		MEMPOOL_CACHE_SZ, 0, MBUF_DATA_SZ, rte_socket_id());
	if (pktmbuf_pool == NULL) {
		rte_exit(EXIT_FAILURE, "Could not initialise mbuf pool\n");
		return -1;
	}

	/* Get number of ports found in scan */
	nb_sys_ports = rte_eth_dev_count_avail();
	if (nb_sys_ports == 0)
		rte_exit(EXIT_FAILURE, "No supported Ethernet device found\n");

	/* Check if the configured port ID is valid */
	for (i = 0; i < RTE_MAX_ETHPORTS; i++)
		if (kni_port_params_array[i] && !rte_eth_dev_is_valid_port(i))
			rte_exit(EXIT_FAILURE, "Configured invalid "
						"port ID %u\n", i);

	/* Initialize KNI subsystem */
	init_kni();

	/* Initialise each port */
	RTE_ETH_FOREACH_DEV(port) {
		/* Skip ports that are not enabled */
		if (!(ports_mask & (1 << port)))
			continue;
		init_port(port);

		if (port >= RTE_MAX_ETHPORTS)
			rte_exit(EXIT_FAILURE, "Can not use more than "
				"%d ports for kni\n", RTE_MAX_ETHPORTS);

		kni_alloc(port);
	}
	check_all_ports_link_status(ports_mask);

	pid = getpid();
	RTE_LOG(INFO, APP, "========================\n");
	RTE_LOG(INFO, APP, "KNI Running\n");
	RTE_LOG(INFO, APP, "kill -SIGUSR1 %d\n", pid);
	RTE_LOG(INFO, APP, "    Show KNI Statistics.\n");
	RTE_LOG(INFO, APP, "kill -SIGUSR2 %d\n", pid);
	RTE_LOG(INFO, APP, "    Zero KNI Statistics.\n");
	RTE_LOG(INFO, APP, "========================\n");
	fflush(stdout);

	ret = rte_ctrl_thread_create(&kni_link_tid,
				     "KNI link status check", NULL,
				     monitor_all_ports_link_status, NULL);
	if (ret < 0)
		rte_exit(EXIT_FAILURE,
			"Could not create link status thread!\n");

	/* Launch per-lcore function on every lcore */
	rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);
	RTE_LCORE_FOREACH_SLAVE(i) {
		if (rte_eal_wait_lcore(i) < 0)
			return -1;
	}
	monitor_links = 0;
	pthread_join(kni_link_tid, &retval);

	/* Release resources */
	RTE_ETH_FOREACH_DEV(port) {
		if (!(ports_mask & (1 << port)))
			continue;
		kni_free_kni(port);
	}
	for (i = 0; i < RTE_MAX_ETHPORTS; i++)
		if (kni_port_params_array[i]) {
			rte_free(kni_port_params_array[i]);
			kni_port_params_array[i] = NULL;
		}

	return 0;
}