summaryrefslogtreecommitdiffstats
path: root/drivers/net/tap/rte_eth_tap.c
blob: e44de027d705fa7c10f756cd0c00f9477bb46087 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
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
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2016 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 <rte_atomic.h>
#include <rte_branch_prediction.h>
#include <rte_common.h>
#include <rte_mbuf.h>
#include <rte_ethdev.h>
#include <rte_ethdev_vdev.h>
#include <rte_malloc.h>
#include <rte_vdev.h>
#include <rte_kvargs.h>
#include <rte_net.h>

#include <sys/types.h>
#include <sys/stat.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
#include <sys/utsname.h>
#include <sys/mman.h>
#include <errno.h>
#include <signal.h>
#include <stdint.h>
#include <sys/uio.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <net/if.h>
#include <linux/if_tun.h>
#include <linux/if_ether.h>
#include <linux/version.h>
#include <fcntl.h>

#include <rte_eth_tap.h>
#include <tap_flow.h>
#include <tap_netlink.h>
#include <tap_tcmsgs.h>

/* Linux based path to the TUN device */
#define TUN_TAP_DEV_PATH        "/dev/net/tun"
#define DEFAULT_TAP_NAME        "dtap"

#define ETH_TAP_IFACE_ARG       "iface"
#define ETH_TAP_SPEED_ARG       "speed"
#define ETH_TAP_REMOTE_ARG      "remote"

#define FLOWER_KERNEL_VERSION KERNEL_VERSION(4, 2, 0)
#define FLOWER_VLAN_KERNEL_VERSION KERNEL_VERSION(4, 9, 0)

static struct rte_vdev_driver pmd_tap_drv;

static const char *valid_arguments[] = {
	ETH_TAP_IFACE_ARG,
	ETH_TAP_SPEED_ARG,
	ETH_TAP_REMOTE_ARG,
	NULL
};

static int tap_unit;

static volatile uint32_t tap_trigger;	/* Rx trigger */

static struct rte_eth_link pmd_link = {
	.link_speed = ETH_SPEED_NUM_10G,
	.link_duplex = ETH_LINK_FULL_DUPLEX,
	.link_status = ETH_LINK_DOWN,
	.link_autoneg = ETH_LINK_SPEED_AUTONEG
};

static void
tap_trigger_cb(int sig __rte_unused)
{
	/* Valid trigger values are nonzero */
	tap_trigger = (tap_trigger + 1) | 0x80000000;
}

/* Specifies on what netdevices the ioctl should be applied */
enum ioctl_mode {
	LOCAL_AND_REMOTE,
	LOCAL_ONLY,
	REMOTE_ONLY,
};

static int
tap_ioctl(struct pmd_internals *pmd, unsigned long request,
	  struct ifreq *ifr, int set, enum ioctl_mode mode);

static int tap_intr_handle_set(struct rte_eth_dev *dev, int set);

/* Tun/Tap allocation routine
 *
 * name is the number of the interface to use, unless NULL to take the host
 * supplied name.
 */
static int
tun_alloc(struct pmd_internals *pmd, uint16_t qid)
{
	struct ifreq ifr;
#ifdef IFF_MULTI_QUEUE
	unsigned int features;
#endif
	int fd;

	memset(&ifr, 0, sizeof(struct ifreq));

	/*
	 * Do not set IFF_NO_PI as packet information header will be needed
	 * to check if a received packet has been truncated.
	 */
	ifr.ifr_flags = IFF_TAP;
	snprintf(ifr.ifr_name, IFNAMSIZ, "%s", pmd->name);

	RTE_LOG(DEBUG, PMD, "ifr_name '%s'\n", ifr.ifr_name);

	fd = open(TUN_TAP_DEV_PATH, O_RDWR);
	if (fd < 0) {
		RTE_LOG(ERR, PMD, "Unable to create TAP interface");
		goto error;
	}

#ifdef IFF_MULTI_QUEUE
	/* Grab the TUN features to verify we can work multi-queue */
	if (ioctl(fd, TUNGETFEATURES, &features) < 0) {
		RTE_LOG(ERR, PMD, "TAP unable to get TUN/TAP features\n");
		goto error;
	}
	RTE_LOG(DEBUG, PMD, "  TAP Features %08x\n", features);

	if (features & IFF_MULTI_QUEUE) {
		RTE_LOG(DEBUG, PMD, "  Multi-queue support for %d queues\n",
			RTE_PMD_TAP_MAX_QUEUES);
		ifr.ifr_flags |= IFF_MULTI_QUEUE;
	} else
#endif
	{
		ifr.ifr_flags |= IFF_ONE_QUEUE;
		RTE_LOG(DEBUG, PMD, "  Single queue only support\n");
	}

	/* Set the TUN/TAP configuration and set the name if needed */
	if (ioctl(fd, TUNSETIFF, (void *)&ifr) < 0) {
		RTE_LOG(WARNING, PMD,
			"Unable to set TUNSETIFF for %s\n",
			ifr.ifr_name);
		perror("TUNSETIFF");
		goto error;
	}

	/* Always set the file descriptor to non-blocking */
	if (fcntl(fd, F_SETFL, O_NONBLOCK) < 0) {
		RTE_LOG(WARNING, PMD,
			"Unable to set %s to nonblocking\n",
			ifr.ifr_name);
		perror("F_SETFL, NONBLOCK");
		goto error;
	}

	/* Set up trigger to optimize empty Rx bursts */
	errno = 0;
	do {
		struct sigaction sa;
		int flags = fcntl(fd, F_GETFL);

		if (flags == -1 || sigaction(SIGIO, NULL, &sa) == -1)
			break;
		if (sa.sa_handler != tap_trigger_cb) {
			/*
			 * Make sure SIGIO is not already taken. This is done
			 * as late as possible to leave the application a
			 * chance to set up its own signal handler first.
			 */
			if (sa.sa_handler != SIG_IGN &&
			    sa.sa_handler != SIG_DFL) {
				errno = EBUSY;
				break;
			}
			sa = (struct sigaction){
				.sa_flags = SA_RESTART,
				.sa_handler = tap_trigger_cb,
			};
			if (sigaction(SIGIO, &sa, NULL) == -1)
				break;
		}
		/* Enable SIGIO on file descriptor */
		fcntl(fd, F_SETFL, flags | O_ASYNC);
		fcntl(fd, F_SETOWN, getpid());
	} while (0);
	if (errno) {
		/* Disable trigger globally in case of error */
		tap_trigger = 0;
		RTE_LOG(WARNING, PMD, "Rx trigger disabled: %s\n",
			strerror(errno));
	}

	if (qid == 0) {
		struct ifreq ifr;

		/*
		 * pmd->eth_addr contains the desired MAC, either from remote
		 * or from a random assignment. Sync it with the tap netdevice.
		 */
		ifr.ifr_hwaddr.sa_family = AF_LOCAL;
		rte_memcpy(ifr.ifr_hwaddr.sa_data, &pmd->eth_addr,
			   ETHER_ADDR_LEN);
		if (tap_ioctl(pmd, SIOCSIFHWADDR, &ifr, 0, LOCAL_ONLY) < 0)
			goto error;

		pmd->if_index = if_nametoindex(pmd->name);
		if (!pmd->if_index) {
			RTE_LOG(ERR, PMD,
				"Could not find ifindex for %s: rte_flow won't be usable.\n",
				pmd->name);
			return fd;
		}
		if (!pmd->flower_support)
			return fd;
		if (qdisc_create_multiq(pmd->nlsk_fd, pmd->if_index) < 0) {
			RTE_LOG(ERR, PMD,
				"Could not create multiq qdisc for %s: rte_flow won't be usable.\n",
				pmd->name);
			return fd;
		}
		if (qdisc_create_ingress(pmd->nlsk_fd, pmd->if_index) < 0) {
			RTE_LOG(ERR, PMD,
				"Could not create multiq qdisc for %s: rte_flow won't be usable.\n",
				pmd->name);
			return fd;
		}
		if (pmd->remote_if_index) {
			/*
			 * Flush usually returns negative value because it tries
			 * to delete every QDISC (and on a running device, one
			 * QDISC at least is needed). Ignore negative return
			 * value.
			 */
			qdisc_flush(pmd->nlsk_fd, pmd->remote_if_index);
			if (qdisc_create_ingress(pmd->nlsk_fd,
						 pmd->remote_if_index) < 0)
				goto remote_fail;
			LIST_INIT(&pmd->implicit_flows);
			if (tap_flow_implicit_create(
				    pmd, TAP_REMOTE_LOCAL_MAC) < 0)
				goto remote_fail;
			if (tap_flow_implicit_create(
				    pmd, TAP_REMOTE_BROADCAST) < 0)
				goto remote_fail;
			if (tap_flow_implicit_create(
				    pmd, TAP_REMOTE_BROADCASTV6) < 0)
				goto remote_fail;
			if (tap_flow_implicit_create(
				    pmd, TAP_REMOTE_TX) < 0)
				goto remote_fail;
		}
	}

	return fd;

remote_fail:
	RTE_LOG(ERR, PMD,
		"Could not set up remote flow rules for %s: remote disabled.\n",
		pmd->name);
	pmd->remote_if_index = 0;
	tap_flow_implicit_flush(pmd, NULL);
	return fd;

error:
	if (fd > 0)
		close(fd);
	return -1;
}

/* Callback to handle the rx burst of packets to the correct interface and
 * file descriptor(s) in a multi-queue setup.
 */
static uint16_t
pmd_rx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
{
	struct rx_queue *rxq = queue;
	uint16_t num_rx;
	unsigned long num_rx_bytes = 0;
	uint32_t trigger = tap_trigger;

	if (trigger == rxq->trigger_seen)
		return 0;
	if (trigger)
		rxq->trigger_seen = trigger;
	rte_compiler_barrier();
	for (num_rx = 0; num_rx < nb_pkts; ) {
		struct rte_mbuf *mbuf = rxq->pool;
		struct rte_mbuf *seg = NULL;
		struct rte_mbuf *new_tail = NULL;
		uint16_t data_off = rte_pktmbuf_headroom(mbuf);
		int len;

		len = readv(rxq->fd, *rxq->iovecs,
			    1 + (rxq->rxmode->enable_scatter ?
				 rxq->nb_rx_desc : 1));
		if (len < (int)sizeof(struct tun_pi))
			break;

		/* Packet couldn't fit in the provided mbuf */
		if (unlikely(rxq->pi.flags & TUN_PKT_STRIP)) {
			rxq->stats.ierrors++;
			continue;
		}

		len -= sizeof(struct tun_pi);

		mbuf->pkt_len = len;
		mbuf->port = rxq->in_port;
		while (1) {
			struct rte_mbuf *buf = rte_pktmbuf_alloc(rxq->mp);

			if (unlikely(!buf)) {
				rxq->stats.rx_nombuf++;
				/* No new buf has been allocated: do nothing */
				if (!new_tail || !seg)
					goto end;

				seg->next = NULL;
				rte_pktmbuf_free(mbuf);

				goto end;
			}
			seg = seg ? seg->next : mbuf;
			if (rxq->pool == mbuf)
				rxq->pool = buf;
			if (new_tail)
				new_tail->next = buf;
			new_tail = buf;
			new_tail->next = seg->next;

			/* iovecs[0] is reserved for packet info (pi) */
			(*rxq->iovecs)[mbuf->nb_segs].iov_len =
				buf->buf_len - data_off;
			(*rxq->iovecs)[mbuf->nb_segs].iov_base =
				(char *)buf->buf_addr + data_off;

			seg->data_len = RTE_MIN(seg->buf_len - data_off, len);
			seg->data_off = data_off;

			len -= seg->data_len;
			if (len <= 0)
				break;
			mbuf->nb_segs++;
			/* First segment has headroom, not the others */
			data_off = 0;
		}
		seg->next = NULL;
		mbuf->packet_type = rte_net_get_ptype(mbuf, NULL,
						      RTE_PTYPE_ALL_MASK);

		/* account for the receive frame */
		bufs[num_rx++] = mbuf;
		num_rx_bytes += mbuf->pkt_len;
	}
end:
	rxq->stats.ipackets += num_rx;
	rxq->stats.ibytes += num_rx_bytes;

	return num_rx;
}

/* Callback to handle sending packets from the tap interface
 */
static uint16_t
pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
{
	struct tx_queue *txq = queue;
	uint16_t num_tx = 0;
	unsigned long num_tx_bytes = 0;
	uint32_t max_size;
	int i;

	if (unlikely(nb_pkts == 0))
		return 0;

	max_size = *txq->mtu + (ETHER_HDR_LEN + ETHER_CRC_LEN + 4);
	for (i = 0; i < nb_pkts; i++) {
		struct rte_mbuf *mbuf = bufs[num_tx];
		struct iovec iovecs[mbuf->nb_segs + 1];
		struct tun_pi pi = { .flags = 0 };
		struct rte_mbuf *seg = mbuf;
		int n;
		int j;

		/* stats.errs will be incremented */
		if (rte_pktmbuf_pkt_len(mbuf) > max_size)
			break;

		iovecs[0].iov_base = &pi;
		iovecs[0].iov_len = sizeof(pi);
		for (j = 1; j <= mbuf->nb_segs; j++) {
			iovecs[j].iov_len = rte_pktmbuf_data_len(seg);
			iovecs[j].iov_base =
				rte_pktmbuf_mtod(seg, void *);
			seg = seg->next;
		}
		/* copy the tx frame data */
		n = writev(txq->fd, iovecs, mbuf->nb_segs + 1);
		if (n <= 0)
			break;

		num_tx++;
		num_tx_bytes += mbuf->pkt_len;
		rte_pktmbuf_free(mbuf);
	}

	txq->stats.opackets += num_tx;
	txq->stats.errs += nb_pkts - num_tx;
	txq->stats.obytes += num_tx_bytes;

	return num_tx;
}

static int
tap_ioctl(struct pmd_internals *pmd, unsigned long request,
	  struct ifreq *ifr, int set, enum ioctl_mode mode)
{
	short req_flags = ifr->ifr_flags;
	int remote = pmd->remote_if_index &&
		(mode == REMOTE_ONLY || mode == LOCAL_AND_REMOTE);

	if (!pmd->remote_if_index && mode == REMOTE_ONLY)
		return 0;
	/*
	 * If there is a remote netdevice, apply ioctl on it, then apply it on
	 * the tap netdevice.
	 */
apply:
	if (remote)
		snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->remote_iface);
	else if (mode == LOCAL_ONLY || mode == LOCAL_AND_REMOTE)
		snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->name);
	switch (request) {
	case SIOCSIFFLAGS:
		/* fetch current flags to leave other flags untouched */
		if (ioctl(pmd->ioctl_sock, SIOCGIFFLAGS, ifr) < 0)
			goto error;
		if (set)
			ifr->ifr_flags |= req_flags;
		else
			ifr->ifr_flags &= ~req_flags;
		break;
	case SIOCGIFFLAGS:
	case SIOCGIFHWADDR:
	case SIOCSIFHWADDR:
	case SIOCSIFMTU:
		break;
	default:
		RTE_LOG(WARNING, PMD, "%s: ioctl() called with wrong arg\n",
			pmd->name);
		return -EINVAL;
	}
	if (ioctl(pmd->ioctl_sock, request, ifr) < 0)
		goto error;
	if (remote-- && mode == LOCAL_AND_REMOTE)
		goto apply;
	return 0;

error:
	RTE_LOG(ERR, PMD, "%s: ioctl(%lu) failed with error: %s\n",
		ifr->ifr_name, request, strerror(errno));
	return -errno;
}

static int
tap_link_set_down(struct rte_eth_dev *dev)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr = { .ifr_flags = IFF_UP };

	dev->data->dev_link.link_status = ETH_LINK_DOWN;
	return tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 0, LOCAL_AND_REMOTE);
}

static int
tap_link_set_up(struct rte_eth_dev *dev)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr = { .ifr_flags = IFF_UP };

	dev->data->dev_link.link_status = ETH_LINK_UP;
	return tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 1, LOCAL_AND_REMOTE);
}

static int
tap_dev_start(struct rte_eth_dev *dev)
{
	int err;

	err = tap_intr_handle_set(dev, 1);
	if (err)
		return err;
	return tap_link_set_up(dev);
}

/* This function gets called when the current port gets stopped.
 */
static void
tap_dev_stop(struct rte_eth_dev *dev)
{
	tap_intr_handle_set(dev, 0);
	tap_link_set_down(dev);
}

static int
tap_dev_configure(struct rte_eth_dev *dev __rte_unused)
{
	return 0;
}

static uint32_t
tap_dev_speed_capa(void)
{
	uint32_t speed = pmd_link.link_speed;
	uint32_t capa = 0;

	if (speed >= ETH_SPEED_NUM_10M)
		capa |= ETH_LINK_SPEED_10M;
	if (speed >= ETH_SPEED_NUM_100M)
		capa |= ETH_LINK_SPEED_100M;
	if (speed >= ETH_SPEED_NUM_1G)
		capa |= ETH_LINK_SPEED_1G;
	if (speed >= ETH_SPEED_NUM_5G)
		capa |= ETH_LINK_SPEED_2_5G;
	if (speed >= ETH_SPEED_NUM_5G)
		capa |= ETH_LINK_SPEED_5G;
	if (speed >= ETH_SPEED_NUM_10G)
		capa |= ETH_LINK_SPEED_10G;
	if (speed >= ETH_SPEED_NUM_20G)
		capa |= ETH_LINK_SPEED_20G;
	if (speed >= ETH_SPEED_NUM_25G)
		capa |= ETH_LINK_SPEED_25G;
	if (speed >= ETH_SPEED_NUM_40G)
		capa |= ETH_LINK_SPEED_40G;
	if (speed >= ETH_SPEED_NUM_50G)
		capa |= ETH_LINK_SPEED_50G;
	if (speed >= ETH_SPEED_NUM_56G)
		capa |= ETH_LINK_SPEED_56G;
	if (speed >= ETH_SPEED_NUM_100G)
		capa |= ETH_LINK_SPEED_100G;

	return capa;
}

static void
tap_dev_info(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
{
	struct pmd_internals *internals = dev->data->dev_private;

	dev_info->if_index = internals->if_index;
	dev_info->max_mac_addrs = 1;
	dev_info->max_rx_pktlen = (uint32_t)ETHER_MAX_VLAN_FRAME_LEN;
	dev_info->max_rx_queues = internals->nb_queues;
	dev_info->max_tx_queues = internals->nb_queues;
	dev_info->min_rx_bufsize = 0;
	dev_info->pci_dev = NULL;
	dev_info->speed_capa = tap_dev_speed_capa();
}

static void
tap_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *tap_stats)
{
	unsigned int i, imax;
	unsigned long rx_total = 0, tx_total = 0, tx_err_total = 0;
	unsigned long rx_bytes_total = 0, tx_bytes_total = 0;
	unsigned long rx_nombuf = 0, ierrors = 0;
	const struct pmd_internals *pmd = dev->data->dev_private;

	imax = (pmd->nb_queues < RTE_ETHDEV_QUEUE_STAT_CNTRS) ?
		pmd->nb_queues : RTE_ETHDEV_QUEUE_STAT_CNTRS;

	for (i = 0; i < imax; i++) {
		tap_stats->q_ipackets[i] = pmd->rxq[i].stats.ipackets;
		tap_stats->q_ibytes[i] = pmd->rxq[i].stats.ibytes;
		rx_total += tap_stats->q_ipackets[i];
		rx_bytes_total += tap_stats->q_ibytes[i];
		rx_nombuf += pmd->rxq[i].stats.rx_nombuf;
		ierrors += pmd->rxq[i].stats.ierrors;

		tap_stats->q_opackets[i] = pmd->txq[i].stats.opackets;
		tap_stats->q_errors[i] = pmd->txq[i].stats.errs;
		tap_stats->q_obytes[i] = pmd->txq[i].stats.obytes;
		tx_total += tap_stats->q_opackets[i];
		tx_err_total += tap_stats->q_errors[i];
		tx_bytes_total += tap_stats->q_obytes[i];
	}

	tap_stats->ipackets = rx_total;
	tap_stats->ibytes = rx_bytes_total;
	tap_stats->ierrors = ierrors;
	tap_stats->rx_nombuf = rx_nombuf;
	tap_stats->opackets = tx_total;
	tap_stats->oerrors = tx_err_total;
	tap_stats->obytes = tx_bytes_total;
}

static void
tap_stats_reset(struct rte_eth_dev *dev)
{
	int i;
	struct pmd_internals *pmd = dev->data->dev_private;

	for (i = 0; i < pmd->nb_queues; i++) {
		pmd->rxq[i].stats.ipackets = 0;
		pmd->rxq[i].stats.ibytes = 0;
		pmd->rxq[i].stats.ierrors = 0;
		pmd->rxq[i].stats.rx_nombuf = 0;

		pmd->txq[i].stats.opackets = 0;
		pmd->txq[i].stats.errs = 0;
		pmd->txq[i].stats.obytes = 0;
	}
}

static void
tap_dev_close(struct rte_eth_dev *dev __rte_unused)
{
	int i;
	struct pmd_internals *internals = dev->data->dev_private;

	tap_link_set_down(dev);
	tap_flow_flush(dev, NULL);
	tap_flow_implicit_flush(internals, NULL);

	for (i = 0; i < internals->nb_queues; i++) {
		if (internals->rxq[i].fd != -1)
			close(internals->rxq[i].fd);
		internals->rxq[i].fd = -1;
		internals->txq[i].fd = -1;
	}
}

static void
tap_rx_queue_release(void *queue)
{
	struct rx_queue *rxq = queue;

	if (rxq && (rxq->fd > 0)) {
		close(rxq->fd);
		rxq->fd = -1;
		rte_pktmbuf_free(rxq->pool);
		rte_free(rxq->iovecs);
		rxq->pool = NULL;
		rxq->iovecs = NULL;
	}
}

static void
tap_tx_queue_release(void *queue)
{
	struct tx_queue *txq = queue;

	if (txq && (txq->fd > 0)) {
		close(txq->fd);
		txq->fd = -1;
	}
}

static int
tap_link_update(struct rte_eth_dev *dev, int wait_to_complete __rte_unused)
{
	struct rte_eth_link *dev_link = &dev->data->dev_link;
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr = { .ifr_flags = 0 };

	if (pmd->remote_if_index) {
		tap_ioctl(pmd, SIOCGIFFLAGS, &ifr, 0, REMOTE_ONLY);
		if (!(ifr.ifr_flags & IFF_UP) ||
		    !(ifr.ifr_flags & IFF_RUNNING)) {
			dev_link->link_status = ETH_LINK_DOWN;
			return 0;
		}
	}
	tap_ioctl(pmd, SIOCGIFFLAGS, &ifr, 0, LOCAL_ONLY);
	dev_link->link_status =
		((ifr.ifr_flags & IFF_UP) && (ifr.ifr_flags & IFF_RUNNING) ?
		 ETH_LINK_UP :
		 ETH_LINK_DOWN);
	return 0;
}

static void
tap_promisc_enable(struct rte_eth_dev *dev)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr = { .ifr_flags = IFF_PROMISC };

	dev->data->promiscuous = 1;
	tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 1, LOCAL_AND_REMOTE);
	if (pmd->remote_if_index)
		tap_flow_implicit_create(pmd, TAP_REMOTE_PROMISC);
}

static void
tap_promisc_disable(struct rte_eth_dev *dev)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr = { .ifr_flags = IFF_PROMISC };

	dev->data->promiscuous = 0;
	tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 0, LOCAL_AND_REMOTE);
	if (pmd->remote_if_index)
		tap_flow_implicit_destroy(pmd, TAP_REMOTE_PROMISC);
}

static void
tap_allmulti_enable(struct rte_eth_dev *dev)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr = { .ifr_flags = IFF_ALLMULTI };

	dev->data->all_multicast = 1;
	tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 1, LOCAL_AND_REMOTE);
	if (pmd->remote_if_index)
		tap_flow_implicit_create(pmd, TAP_REMOTE_ALLMULTI);
}

static void
tap_allmulti_disable(struct rte_eth_dev *dev)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr = { .ifr_flags = IFF_ALLMULTI };

	dev->data->all_multicast = 0;
	tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 0, LOCAL_AND_REMOTE);
	if (pmd->remote_if_index)
		tap_flow_implicit_destroy(pmd, TAP_REMOTE_ALLMULTI);
}


static void
tap_mac_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr;

	if (is_zero_ether_addr(mac_addr)) {
		RTE_LOG(ERR, PMD, "%s: can't set an empty MAC address\n",
			dev->data->name);
		return;
	}
	/* Check the actual current MAC address on the tap netdevice */
	if (tap_ioctl(pmd, SIOCGIFHWADDR, &ifr, 0, LOCAL_ONLY) != 0) {
		RTE_LOG(ERR, PMD,
			"%s: couldn't check current tap MAC address\n",
			dev->data->name);
		return;
	}
	if (is_same_ether_addr((struct ether_addr *)&ifr.ifr_hwaddr.sa_data,
			       mac_addr))
		return;

	ifr.ifr_hwaddr.sa_family = AF_LOCAL;
	rte_memcpy(ifr.ifr_hwaddr.sa_data, mac_addr, ETHER_ADDR_LEN);
	if (tap_ioctl(pmd, SIOCSIFHWADDR, &ifr, 1, LOCAL_AND_REMOTE) < 0)
		return;
	rte_memcpy(&pmd->eth_addr, mac_addr, ETHER_ADDR_LEN);
	if (pmd->remote_if_index) {
		/* Replace MAC redirection rule after a MAC change */
		if (tap_flow_implicit_destroy(pmd, TAP_REMOTE_LOCAL_MAC) < 0) {
			RTE_LOG(ERR, PMD,
				"%s: Couldn't delete MAC redirection rule\n",
				dev->data->name);
			return;
		}
		if (tap_flow_implicit_create(pmd, TAP_REMOTE_LOCAL_MAC) < 0)
			RTE_LOG(ERR, PMD,
				"%s: Couldn't add MAC redirection rule\n",
				dev->data->name);
	}
}

static int
tap_setup_queue(struct rte_eth_dev *dev,
		struct pmd_internals *internals,
		uint16_t qid)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct rx_queue *rx = &internals->rxq[qid];
	struct tx_queue *tx = &internals->txq[qid];
	int fd;

	fd = rx->fd;
	if (fd < 0) {
		fd = tx->fd;
		if (fd < 0) {
			RTE_LOG(INFO, PMD, "Add queue to TAP %s for qid %d\n",
				pmd->name, qid);
			fd = tun_alloc(pmd, qid);
			if (fd < 0) {
				RTE_LOG(ERR, PMD, "tun_alloc(%s, %d) failed\n",
					pmd->name, qid);
				return -1;
			}
			if (qid == 0) {
				struct ifreq ifr;

				ifr.ifr_mtu = dev->data->mtu;
				if (tap_ioctl(pmd, SIOCSIFMTU, &ifr, 1,
					      LOCAL_AND_REMOTE) < 0) {
					close(fd);
					return -1;
				}
			}
		}
	}

	rx->fd = fd;
	tx->fd = fd;
	tx->mtu = &dev->data->mtu;
	rx->rxmode = &dev->data->dev_conf.rxmode;

	return fd;
}

static int
rx_setup_queue(struct rte_eth_dev *dev,
		struct pmd_internals *internals,
		uint16_t qid)
{
	dev->data->rx_queues[qid] = &internals->rxq[qid];

	return tap_setup_queue(dev, internals, qid);
}

static int
tx_setup_queue(struct rte_eth_dev *dev,
		struct pmd_internals *internals,
		uint16_t qid)
{
	dev->data->tx_queues[qid] = &internals->txq[qid];

	return tap_setup_queue(dev, internals, qid);
}

static int
tap_rx_queue_setup(struct rte_eth_dev *dev,
		   uint16_t rx_queue_id,
		   uint16_t nb_rx_desc,
		   unsigned int socket_id,
		   const struct rte_eth_rxconf *rx_conf __rte_unused,
		   struct rte_mempool *mp)
{
	struct pmd_internals *internals = dev->data->dev_private;
	struct rx_queue *rxq = &internals->rxq[rx_queue_id];
	struct rte_mbuf **tmp = &rxq->pool;
	long iov_max = sysconf(_SC_IOV_MAX);
	uint16_t nb_desc = RTE_MIN(nb_rx_desc, iov_max - 1);
	struct iovec (*iovecs)[nb_desc + 1];
	int data_off = RTE_PKTMBUF_HEADROOM;
	int ret = 0;
	int fd;
	int i;

	if ((rx_queue_id >= internals->nb_queues) || !mp) {
		RTE_LOG(WARNING, PMD,
			"nb_queues %d too small or mempool NULL\n",
			internals->nb_queues);
		return -1;
	}

	rxq->mp = mp;
	rxq->trigger_seen = 1; /* force initial burst */
	rxq->in_port = dev->data->port_id;
	rxq->nb_rx_desc = nb_desc;
	iovecs = rte_zmalloc_socket(dev->data->name, sizeof(*iovecs), 0,
				    socket_id);
	if (!iovecs) {
		RTE_LOG(WARNING, PMD,
			"%s: Couldn't allocate %d RX descriptors\n",
			dev->data->name, nb_desc);
		return -ENOMEM;
	}
	rxq->iovecs = iovecs;

	fd = rx_setup_queue(dev, internals, rx_queue_id);
	if (fd == -1) {
		ret = fd;
		goto error;
	}

	(*rxq->iovecs)[0].iov_len = sizeof(struct tun_pi);
	(*rxq->iovecs)[0].iov_base = &rxq->pi;

	for (i = 1; i <= nb_desc; i++) {
		*tmp = rte_pktmbuf_alloc(rxq->mp);
		if (!*tmp) {
			RTE_LOG(WARNING, PMD,
				"%s: couldn't allocate memory for queue %d\n",
				dev->data->name, rx_queue_id);
			ret = -ENOMEM;
			goto error;
		}
		(*rxq->iovecs)[i].iov_len = (*tmp)->buf_len - data_off;
		(*rxq->iovecs)[i].iov_base =
			(char *)(*tmp)->buf_addr + data_off;
		data_off = 0;
		tmp = &(*tmp)->next;
	}

	RTE_LOG(DEBUG, PMD, "  RX TAP device name %s, qid %d on fd %d\n",
		internals->name, rx_queue_id, internals->rxq[rx_queue_id].fd);

	return 0;

error:
	rte_pktmbuf_free(rxq->pool);
	rxq->pool = NULL;
	rte_free(rxq->iovecs);
	rxq->iovecs = NULL;
	return ret;
}

static int
tap_tx_queue_setup(struct rte_eth_dev *dev,
		   uint16_t tx_queue_id,
		   uint16_t nb_tx_desc __rte_unused,
		   unsigned int socket_id __rte_unused,
		   const struct rte_eth_txconf *tx_conf __rte_unused)
{
	struct pmd_internals *internals = dev->data->dev_private;
	int ret;

	if (tx_queue_id >= internals->nb_queues)
		return -1;

	ret = tx_setup_queue(dev, internals, tx_queue_id);
	if (ret == -1)
		return -1;

	RTE_LOG(DEBUG, PMD, "  TX TAP device name %s, qid %d on fd %d\n",
		internals->name, tx_queue_id, internals->txq[tx_queue_id].fd);

	return 0;
}

static int
tap_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
{
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifreq ifr = { .ifr_mtu = mtu };
	int err = 0;

	err = tap_ioctl(pmd, SIOCSIFMTU, &ifr, 1, LOCAL_AND_REMOTE);
	if (!err)
		dev->data->mtu = mtu;

	return err;
}

static int
tap_set_mc_addr_list(struct rte_eth_dev *dev __rte_unused,
		     struct ether_addr *mc_addr_set __rte_unused,
		     uint32_t nb_mc_addr __rte_unused)
{
	/*
	 * Nothing to do actually: the tap has no filtering whatsoever, every
	 * packet is received.
	 */
	return 0;
}

static int
tap_nl_msg_handler(struct nlmsghdr *nh, void *arg)
{
	struct rte_eth_dev *dev = arg;
	struct pmd_internals *pmd = dev->data->dev_private;
	struct ifinfomsg *info = NLMSG_DATA(nh);

	if (nh->nlmsg_type != RTM_NEWLINK ||
	    (info->ifi_index != pmd->if_index &&
	     info->ifi_index != pmd->remote_if_index))
		return 0;
	return tap_link_update(dev, 0);
}

static void
tap_dev_intr_handler(void *cb_arg)
{
	struct rte_eth_dev *dev = cb_arg;
	struct pmd_internals *pmd = dev->data->dev_private;

	nl_recv(pmd->intr_handle.fd, tap_nl_msg_handler, dev);
}

static int
tap_intr_handle_set(struct rte_eth_dev *dev, int set)
{
	struct pmd_internals *pmd = dev->data->dev_private;

	/* In any case, disable interrupt if the conf is no longer there. */
	if (!dev->data->dev_conf.intr_conf.lsc) {
		if (pmd->intr_handle.fd != -1)
			nl_final(pmd->intr_handle.fd);
		rte_intr_callback_unregister(
			&pmd->intr_handle, tap_dev_intr_handler, dev);
		return 0;
	}
	if (set) {
		pmd->intr_handle.fd = nl_init(RTMGRP_LINK);
		if (unlikely(pmd->intr_handle.fd == -1))
			return -EBADF;
		return rte_intr_callback_register(
			&pmd->intr_handle, tap_dev_intr_handler, dev);
	}
	nl_final(pmd->intr_handle.fd);
	return rte_intr_callback_unregister(&pmd->intr_handle,
					    tap_dev_intr_handler, dev);
}

static const uint32_t*
tap_dev_supported_ptypes_get(struct rte_eth_dev *dev __rte_unused)
{
	static const uint32_t ptypes[] = {
		RTE_PTYPE_INNER_L2_ETHER,
		RTE_PTYPE_INNER_L2_ETHER_VLAN,
		RTE_PTYPE_INNER_L2_ETHER_QINQ,
		RTE_PTYPE_INNER_L3_IPV4,
		RTE_PTYPE_INNER_L3_IPV4_EXT,
		RTE_PTYPE_INNER_L3_IPV6,
		RTE_PTYPE_INNER_L3_IPV6_EXT,
		RTE_PTYPE_INNER_L4_FRAG,
		RTE_PTYPE_INNER_L4_UDP,
		RTE_PTYPE_INNER_L4_TCP,
		RTE_PTYPE_INNER_L4_SCTP,
		RTE_PTYPE_L2_ETHER,
		RTE_PTYPE_L2_ETHER_VLAN,
		RTE_PTYPE_L2_ETHER_QINQ,
		RTE_PTYPE_L3_IPV4,
		RTE_PTYPE_L3_IPV4_EXT,
		RTE_PTYPE_L3_IPV6_EXT,
		RTE_PTYPE_L3_IPV6,
		RTE_PTYPE_L4_FRAG,
		RTE_PTYPE_L4_UDP,
		RTE_PTYPE_L4_TCP,
		RTE_PTYPE_L4_SCTP,
	};

	return ptypes;
}

static int
tap_flow_ctrl_get(struct rte_eth_dev *dev __rte_unused,
		  struct rte_eth_fc_conf *fc_conf)
{
	fc_conf->mode = RTE_FC_NONE;
	return 0;
}

static int
tap_flow_ctrl_set(struct rte_eth_dev *dev __rte_unused,
		  struct rte_eth_fc_conf *fc_conf)
{
	if (fc_conf->mode != RTE_FC_NONE)
		return -ENOTSUP;
	return 0;
}

static const struct eth_dev_ops ops = {
	.dev_start              = tap_dev_start,
	.dev_stop               = tap_dev_stop,
	.dev_close              = tap_dev_close,
	.dev_configure          = tap_dev_configure,
	.dev_infos_get          = tap_dev_info,
	.rx_queue_setup         = tap_rx_queue_setup,
	.tx_queue_setup         = tap_tx_queue_setup,
	.rx_queue_release       = tap_rx_queue_release,
	.tx_queue_release       = tap_tx_queue_release,
	.flow_ctrl_get          = tap_flow_ctrl_get,
	.flow_ctrl_set          = tap_flow_ctrl_set,
	.link_update            = tap_link_update,
	.dev_set_link_up        = tap_link_set_up,
	.dev_set_link_down      = tap_link_set_down,
	.promiscuous_enable     = tap_promisc_enable,
	.promiscuous_disable    = tap_promisc_disable,
	.allmulticast_enable    = tap_allmulti_enable,
	.allmulticast_disable   = tap_allmulti_disable,
	.mac_addr_set           = tap_mac_set,
	.mtu_set                = tap_mtu_set,
	.set_mc_addr_list       = tap_set_mc_addr_list,
	.stats_get              = tap_stats_get,
	.stats_reset            = tap_stats_reset,
	.dev_supported_ptypes_get = tap_dev_supported_ptypes_get,
	.filter_ctrl            = tap_dev_filter_ctrl,
};

static int
tap_kernel_support(struct pmd_internals *pmd)
{
	struct utsname utsname;
	int ver[3];

	if (uname(&utsname) == -1 ||
	    sscanf(utsname.release, "%d.%d.%d",
		   &ver[0], &ver[1], &ver[2]) != 3)
		return 0;
	if (KERNEL_VERSION(ver[0], ver[1], ver[2]) >= FLOWER_KERNEL_VERSION)
		pmd->flower_support = 1;
	if (KERNEL_VERSION(ver[0], ver[1], ver[2]) >=
	    FLOWER_VLAN_KERNEL_VERSION)
		pmd->flower_vlan_support = 1;
	return 1;
}

static int
eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
		   char *remote_iface)
{
	int numa_node = rte_socket_id();
	struct rte_eth_dev *dev;
	struct pmd_internals *pmd;
	struct rte_eth_dev_data *data;
	int i;

	RTE_LOG(DEBUG, PMD, "  TAP device on numa %u\n", rte_socket_id());

	data = rte_zmalloc_socket(tap_name, sizeof(*data), 0, numa_node);
	if (!data) {
		RTE_LOG(ERR, PMD, "TAP Failed to allocate data\n");
		goto error_exit;
	}

	dev = rte_eth_vdev_allocate(vdev, sizeof(*pmd));
	if (!dev) {
		RTE_LOG(ERR, PMD, "TAP Unable to allocate device struct\n");
		goto error_exit;
	}

	pmd = dev->data->dev_private;
	snprintf(pmd->name, sizeof(pmd->name), "%s", tap_name);
	pmd->nb_queues = RTE_PMD_TAP_MAX_QUEUES;

	pmd->ioctl_sock = socket(AF_INET, SOCK_DGRAM, 0);
	if (pmd->ioctl_sock == -1) {
		RTE_LOG(ERR, PMD,
			"TAP Unable to get a socket for management: %s\n",
			strerror(errno));
		goto error_exit;
	}

	/* Setup some default values */
	rte_memcpy(data, dev->data, sizeof(*data));
	data->dev_private = pmd;
	data->dev_flags = RTE_ETH_DEV_DETACHABLE | RTE_ETH_DEV_INTR_LSC;
	data->numa_node = numa_node;
	data->drv_name = pmd_tap_drv.driver.name;

	data->dev_link = pmd_link;
	data->mac_addrs = &pmd->eth_addr;
	data->nb_rx_queues = pmd->nb_queues;
	data->nb_tx_queues = pmd->nb_queues;

	dev->data = data;
	dev->dev_ops = &ops;
	dev->rx_pkt_burst = pmd_rx_burst;
	dev->tx_pkt_burst = pmd_tx_burst;

	pmd->intr_handle.type = RTE_INTR_HANDLE_EXT;
	pmd->intr_handle.fd = -1;

	/* Presetup the fds to -1 as being not valid */
	for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
		pmd->rxq[i].fd = -1;
		pmd->txq[i].fd = -1;
	}

	tap_kernel_support(pmd);
	if (!pmd->flower_support)
		return 0;
	LIST_INIT(&pmd->flows);
	/*
	 * If no netlink socket can be created, then it will fail when
	 * creating/destroying flow rules.
	 */
	pmd->nlsk_fd = nl_init(0);
	if (strlen(remote_iface)) {
		struct ifreq ifr;

		pmd->remote_if_index = if_nametoindex(remote_iface);
		snprintf(pmd->remote_iface, RTE_ETH_NAME_MAX_LEN,
			 "%s", remote_iface);
		if (!pmd->remote_if_index) {
			RTE_LOG(ERR, PMD, "Could not find %s ifindex: "
				"remote interface will remain unconfigured\n",
				remote_iface);
			return 0;
		}
		if (tap_ioctl(pmd, SIOCGIFHWADDR, &ifr, 0, REMOTE_ONLY) < 0) {
			RTE_LOG(ERR, PMD, "Could not get remote MAC address\n");
			goto error_exit;
		}
		rte_memcpy(&pmd->eth_addr, ifr.ifr_hwaddr.sa_data,
			   ETHER_ADDR_LEN);
	} else {
		eth_random_addr((uint8_t *)&pmd->eth_addr);
	}

	return 0;

error_exit:
	RTE_LOG(DEBUG, PMD, "TAP Unable to initialize %s\n",
		rte_vdev_device_name(vdev));

	rte_free(data);
	return -EINVAL;
}

static int
set_interface_name(const char *key __rte_unused,
		   const char *value,
		   void *extra_args)
{
	char *name = (char *)extra_args;

	if (value)
		snprintf(name, RTE_ETH_NAME_MAX_LEN - 1, "%s", value);
	else
		snprintf(name, RTE_ETH_NAME_MAX_LEN - 1, "%s%d",
			 DEFAULT_TAP_NAME, (tap_unit - 1));

	return 0;
}

static int
set_interface_speed(const char *key __rte_unused,
		    const char *value,
		    void *extra_args)
{
	*(int *)extra_args = (value) ? atoi(value) : ETH_SPEED_NUM_10G;

	return 0;
}

static int
set_remote_iface(const char *key __rte_unused,
		 const char *value,
		 void *extra_args)
{
	char *name = (char *)extra_args;

	if (value)
		snprintf(name, RTE_ETH_NAME_MAX_LEN, "%s", value);

	return 0;
}

/* Open a TAP interface device.
 */
static int
rte_pmd_tap_probe(struct rte_vdev_device *dev)
{
	const char *name, *params;
	int ret;
	struct rte_kvargs *kvlist = NULL;
	int speed;
	char tap_name[RTE_ETH_NAME_MAX_LEN];
	char remote_iface[RTE_ETH_NAME_MAX_LEN];

	name = rte_vdev_device_name(dev);
	params = rte_vdev_device_args(dev);

	speed = ETH_SPEED_NUM_10G;
	snprintf(tap_name, sizeof(tap_name), "%s%d",
		 DEFAULT_TAP_NAME, tap_unit++);
	memset(remote_iface, 0, RTE_ETH_NAME_MAX_LEN);

	if (params && (params[0] != '\0')) {
		RTE_LOG(DEBUG, PMD, "paramaters (%s)\n", params);

		kvlist = rte_kvargs_parse(params, valid_arguments);
		if (kvlist) {
			if (rte_kvargs_count(kvlist, ETH_TAP_SPEED_ARG) == 1) {
				ret = rte_kvargs_process(kvlist,
							 ETH_TAP_SPEED_ARG,
							 &set_interface_speed,
							 &speed);
				if (ret == -1)
					goto leave;
			}

			if (rte_kvargs_count(kvlist, ETH_TAP_IFACE_ARG) == 1) {
				ret = rte_kvargs_process(kvlist,
							 ETH_TAP_IFACE_ARG,
							 &set_interface_name,
							 tap_name);
				if (ret == -1)
					goto leave;
			}

			if (rte_kvargs_count(kvlist, ETH_TAP_REMOTE_ARG) == 1) {
				ret = rte_kvargs_process(kvlist,
							 ETH_TAP_REMOTE_ARG,
							 &set_remote_iface,
							 remote_iface);
				if (ret == -1)
					goto leave;
			}
		}
	}
	pmd_link.link_speed = speed;

	RTE_LOG(NOTICE, PMD, "Initializing pmd_tap for %s as %s\n",
		name, tap_name);

	ret = eth_dev_tap_create(dev, tap_name, remote_iface);

leave:
	if (ret == -1) {
		RTE_LOG(ERR, PMD, "Failed to create pmd for %s as %s\n",
			name, tap_name);
		tap_unit--;		/* Restore the unit number */
	}
	rte_kvargs_free(kvlist);

	return ret;
}

/* detach a TAP device.
 */
static int
rte_pmd_tap_remove(struct rte_vdev_device *dev)
{
	struct rte_eth_dev *eth_dev = NULL;
	struct pmd_internals *internals;
	int i;

	RTE_LOG(DEBUG, PMD, "Closing TUN/TAP Ethernet device on numa %u\n",
		rte_socket_id());

	/* find the ethdev entry */
	eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
	if (!eth_dev)
		return 0;

	internals = eth_dev->data->dev_private;
	if (internals->flower_support && internals->nlsk_fd) {
		tap_flow_flush(eth_dev, NULL);
		tap_flow_implicit_flush(internals, NULL);
		nl_final(internals->nlsk_fd);
	}
	for (i = 0; i < internals->nb_queues; i++)
		if (internals->rxq[i].fd != -1)
			close(internals->rxq[i].fd);

	close(internals->ioctl_sock);
	rte_free(eth_dev->data->dev_private);
	rte_free(eth_dev->data);

	rte_eth_dev_release_port(eth_dev);

	return 0;
}

static struct rte_vdev_driver pmd_tap_drv = {
	.probe = rte_pmd_tap_probe,
	.remove = rte_pmd_tap_remove,
};
RTE_PMD_REGISTER_VDEV(net_tap, pmd_tap_drv);
RTE_PMD_REGISTER_ALIAS(net_tap, eth_tap);
RTE_PMD_REGISTER_PARAM_STRING(net_tap,
			      ETH_TAP_IFACE_ARG "=<string> "
			      ETH_TAP_SPEED_ARG "=<int> "
			      ETH_TAP_REMOTE_ARG "=<string>");