summaryrefslogtreecommitdiff
path: root/lib/netdev-vport.c
blob: 88f5022f4bd53548799fe18e12670c17eea3694d (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
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
/*
 * Copyright (c) 2010, 2011, 2012, 2013, 2014 Nicira, Inc.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at:
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#include <config.h>

#include "netdev-vport.h"

#include <errno.h>
#include <fcntl.h>
#include <sys/socket.h>
#include <net/if.h>
#include <netinet/ip6.h>
#include <sys/ioctl.h>

#include "byte-order.h"
#include "csum.h"
#include "daemon.h"
#include "dirs.h"
#include "dpif.h"
#include "dp-packet.h"
#include "dynamic-string.h"
#include "flow.h"
#include "hash.h"
#include "hmap.h"
#include "list.h"
#include "netdev-provider.h"
#include "odp-netlink.h"
#include "dp-packet.h"
#include "ovs-router.h"
#include "packets.h"
#include "poll-loop.h"
#include "route-table.h"
#include "shash.h"
#include "socket-util.h"
#include "openvswitch/vlog.h"
#include "unaligned.h"
#include "unixctl.h"
#include "util.h"

VLOG_DEFINE_THIS_MODULE(netdev_vport);
static struct vlog_rate_limit err_rl = VLOG_RATE_LIMIT_INIT(60, 5);

#define GENEVE_DST_PORT 6081
#define VXLAN_DST_PORT 4789
#define LISP_DST_PORT 4341
#define STT_DST_PORT 7471

#define VXLAN_HLEN   (sizeof(struct udp_header) +         \
                      sizeof(struct vxlanhdr))

#define GENEVE_BASE_HLEN   (sizeof(struct udp_header) +         \
                            sizeof(struct genevehdr))

#define DEFAULT_TTL 64

struct netdev_vport {
    struct netdev up;

    /* Protects all members below. */
    struct ovs_mutex mutex;

    struct eth_addr etheraddr;
    struct netdev_stats stats;

    /* Tunnels. */
    struct netdev_tunnel_config tnl_cfg;
    char egress_iface[IFNAMSIZ];
    bool carrier_status;

    /* Patch Ports. */
    char *peer;
};

struct vport_class {
    const char *dpif_port;
    struct netdev_class netdev_class;
};

/* Last read of the route-table's change number. */
static uint64_t rt_change_seqno;

static int netdev_vport_construct(struct netdev *);
static int get_patch_config(const struct netdev *netdev, struct smap *args);
static int get_tunnel_config(const struct netdev *, struct smap *args);
static bool tunnel_check_status_change__(struct netdev_vport *);

static uint16_t tnl_udp_port_min = 32768;
static uint16_t tnl_udp_port_max = 61000;

static bool
is_vport_class(const struct netdev_class *class)
{
    return class->construct == netdev_vport_construct;
}

bool
netdev_vport_is_vport_class(const struct netdev_class *class)
{
    return is_vport_class(class);
}

static const struct vport_class *
vport_class_cast(const struct netdev_class *class)
{
    ovs_assert(is_vport_class(class));
    return CONTAINER_OF(class, struct vport_class, netdev_class);
}

static struct netdev_vport *
netdev_vport_cast(const struct netdev *netdev)
{
    ovs_assert(is_vport_class(netdev_get_class(netdev)));
    return CONTAINER_OF(netdev, struct netdev_vport, up);
}

static const struct netdev_tunnel_config *
get_netdev_tunnel_config(const struct netdev *netdev)
{
    return &netdev_vport_cast(netdev)->tnl_cfg;
}

bool
netdev_vport_is_patch(const struct netdev *netdev)
{
    const struct netdev_class *class = netdev_get_class(netdev);

    return class->get_config == get_patch_config;
}

bool
netdev_vport_is_layer3(const struct netdev *dev)
{
    const char *type = netdev_get_type(dev);

    return (!strcmp("lisp", type));
}

static bool
netdev_vport_needs_dst_port(const struct netdev *dev)
{
    const struct netdev_class *class = netdev_get_class(dev);
    const char *type = netdev_get_type(dev);

    return (class->get_config == get_tunnel_config &&
            (!strcmp("geneve", type) || !strcmp("vxlan", type) ||
             !strcmp("lisp", type) || !strcmp("stt", type)) );
}

const char *
netdev_vport_class_get_dpif_port(const struct netdev_class *class)
{
    return is_vport_class(class) ? vport_class_cast(class)->dpif_port : NULL;
}

const char *
netdev_vport_get_dpif_port(const struct netdev *netdev,
                           char namebuf[], size_t bufsize)
{
    const struct netdev_class *class = netdev_get_class(netdev);
    const char *dpif_port = netdev_vport_class_get_dpif_port(class);

    if (!dpif_port) {
        return netdev_get_name(netdev);
    }

    if (netdev_vport_needs_dst_port(netdev)) {
        const struct netdev_vport *vport = netdev_vport_cast(netdev);

        /*
         * Note: IFNAMSIZ is 16 bytes long. Implementations should choose
         * a dpif port name that is short enough to fit including any
         * port numbers but assert just in case.
         */
        BUILD_ASSERT(NETDEV_VPORT_NAME_BUFSIZE >= IFNAMSIZ);
        ovs_assert(strlen(dpif_port) + 6 < IFNAMSIZ);
        snprintf(namebuf, bufsize, "%s_%d", dpif_port,
                 ntohs(vport->tnl_cfg.dst_port));
        return namebuf;
    } else {
        return dpif_port;
    }
}

char *
netdev_vport_get_dpif_port_strdup(const struct netdev *netdev)
{
    char namebuf[NETDEV_VPORT_NAME_BUFSIZE];

    return xstrdup(netdev_vport_get_dpif_port(netdev, namebuf,
                                              sizeof namebuf));
}

/* Whenever the route-table change number is incremented,
 * netdev_vport_route_changed() should be called to update
 * the corresponding tunnel interface status. */
static void
netdev_vport_route_changed(void)
{
    struct netdev **vports;
    size_t i, n_vports;

    vports = netdev_get_vports(&n_vports);
    for (i = 0; i < n_vports; i++) {
        struct netdev *netdev_ = vports[i];
        struct netdev_vport *netdev = netdev_vport_cast(netdev_);

        ovs_mutex_lock(&netdev->mutex);
        /* Finds all tunnel vports. */
        if (ipv6_addr_is_set(&netdev->tnl_cfg.ipv6_dst)) {
            if (tunnel_check_status_change__(netdev)) {
                netdev_change_seq_changed(netdev_);
            }
        }
        ovs_mutex_unlock(&netdev->mutex);

        netdev_close(netdev_);
    }

    free(vports);
}

static struct netdev *
netdev_vport_alloc(void)
{
    struct netdev_vport *netdev = xzalloc(sizeof *netdev);
    return &netdev->up;
}

static int
netdev_vport_construct(struct netdev *netdev_)
{
    struct netdev_vport *dev = netdev_vport_cast(netdev_);
    const char *type = netdev_get_type(netdev_);

    ovs_mutex_init(&dev->mutex);
    eth_addr_random(&dev->etheraddr);

    /* Add a default destination port for tunnel ports if none specified. */
    if (!strcmp(type, "geneve")) {
        dev->tnl_cfg.dst_port = htons(GENEVE_DST_PORT);
    } else if (!strcmp(type, "vxlan")) {
        dev->tnl_cfg.dst_port = htons(VXLAN_DST_PORT);
    } else if (!strcmp(type, "lisp")) {
        dev->tnl_cfg.dst_port = htons(LISP_DST_PORT);
    } else if (!strcmp(type, "stt")) {
        dev->tnl_cfg.dst_port = htons(STT_DST_PORT);
    }

    dev->tnl_cfg.dont_fragment = true;
    dev->tnl_cfg.ttl = DEFAULT_TTL;
    return 0;
}

static void
netdev_vport_destruct(struct netdev *netdev_)
{
    struct netdev_vport *netdev = netdev_vport_cast(netdev_);

    free(netdev->peer);
    ovs_mutex_destroy(&netdev->mutex);
}

static void
netdev_vport_dealloc(struct netdev *netdev_)
{
    struct netdev_vport *netdev = netdev_vport_cast(netdev_);
    free(netdev);
}

static int
netdev_vport_set_etheraddr(struct netdev *netdev_, const struct eth_addr mac)
{
    struct netdev_vport *netdev = netdev_vport_cast(netdev_);

    ovs_mutex_lock(&netdev->mutex);
    netdev->etheraddr = mac;
    ovs_mutex_unlock(&netdev->mutex);
    netdev_change_seq_changed(netdev_);

    return 0;
}

static int
netdev_vport_get_etheraddr(const struct netdev *netdev_, struct eth_addr *mac)
{
    struct netdev_vport *netdev = netdev_vport_cast(netdev_);

    ovs_mutex_lock(&netdev->mutex);
    *mac = netdev->etheraddr;
    ovs_mutex_unlock(&netdev->mutex);

    return 0;
}

/* Checks if the tunnel status has changed and returns a boolean.
 * Updates the tunnel status if it has changed. */
static bool
tunnel_check_status_change__(struct netdev_vport *netdev)
    OVS_REQUIRES(netdev->mutex)
{
    char iface[IFNAMSIZ];
    bool status = false;
    struct in6_addr *route;
    struct in6_addr gw;

    iface[0] = '\0';
    route = &netdev->tnl_cfg.ipv6_dst;
    if (ovs_router_lookup(route, iface, &gw)) {
        struct netdev *egress_netdev;

        if (!netdev_open(iface, "system", &egress_netdev)) {
            status = netdev_get_carrier(egress_netdev);
            netdev_close(egress_netdev);
        }
    }

    if (strcmp(netdev->egress_iface, iface)
        || netdev->carrier_status != status) {
        ovs_strlcpy(netdev->egress_iface, iface, IFNAMSIZ);
        netdev->carrier_status = status;

        return true;
    }

    return false;
}

static int
tunnel_get_status(const struct netdev *netdev_, struct smap *smap)
{
    struct netdev_vport *netdev = netdev_vport_cast(netdev_);

    if (netdev->egress_iface[0]) {
        smap_add(smap, "tunnel_egress_iface", netdev->egress_iface);

        smap_add(smap, "tunnel_egress_iface_carrier",
                 netdev->carrier_status ? "up" : "down");
    }

    return 0;
}

static int
netdev_vport_update_flags(struct netdev *netdev OVS_UNUSED,
                          enum netdev_flags off,
                          enum netdev_flags on OVS_UNUSED,
                          enum netdev_flags *old_flagsp)
{
    if (off & (NETDEV_UP | NETDEV_PROMISC)) {
        return EOPNOTSUPP;
    }

    *old_flagsp = NETDEV_UP | NETDEV_PROMISC;
    return 0;
}

static void
netdev_vport_run(void)
{
    uint64_t seq;

    route_table_run();
    seq = route_table_get_change_seq();
    if (rt_change_seqno != seq) {
        rt_change_seqno = seq;
        netdev_vport_route_changed();
    }
}

static void
netdev_vport_wait(void)
{
    uint64_t seq;

    route_table_wait();
    seq = route_table_get_change_seq();
    if (rt_change_seqno != seq) {
        poll_immediate_wake();
    }
}

/* Code specific to tunnel types. */

static ovs_be64
parse_key(const struct smap *args, const char *name,
          bool *present, bool *flow)
{
    const char *s;

    *present = false;
    *flow = false;

    s = smap_get(args, name);
    if (!s) {
        s = smap_get(args, "key");
        if (!s) {
            return 0;
        }
    }

    *present = true;

    if (!strcmp(s, "flow")) {
        *flow = true;
        return 0;
    } else {
        return htonll(strtoull(s, NULL, 0));
    }
}

static int
parse_tunnel_ip(const char *value, bool accept_mcast, bool *flow,
                struct in6_addr *ipv6, uint16_t *protocol)
{
    if (!strcmp(value, "flow")) {
        *flow = true;
        *protocol = 0;
        return 0;
    }
    if (addr_is_ipv6(value)) {
        if (lookup_ipv6(value, ipv6)) {
            return ENOENT;
        }
        if (!accept_mcast && ipv6_addr_is_multicast(ipv6)) {
            return EINVAL;
        }
        *protocol = ETH_TYPE_IPV6;
    } else {
        struct in_addr ip;
        if (lookup_ip(value, &ip)) {
            return ENOENT;
        }
        if (!accept_mcast && ip_is_multicast(ip.s_addr)) {
            return EINVAL;
        }
        in6_addr_set_mapped_ipv4(ipv6, ip.s_addr);
        *protocol = ETH_TYPE_IP;
    }
    return 0;
}

static int
set_tunnel_config(struct netdev *dev_, const struct smap *args)
{
    struct netdev_vport *dev = netdev_vport_cast(dev_);
    const char *name = netdev_get_name(dev_);
    const char *type = netdev_get_type(dev_);
    bool ipsec_mech_set, needs_dst_port, has_csum;
    uint16_t dst_proto = 0, src_proto = 0;
    struct netdev_tunnel_config tnl_cfg;
    struct smap_node *node;

    has_csum = strstr(type, "gre") || strstr(type, "geneve") ||
               strstr(type, "stt") || strstr(type, "vxlan");
    ipsec_mech_set = false;
    memset(&tnl_cfg, 0, sizeof tnl_cfg);

    /* Add a default destination port for tunnel ports if none specified. */
    if (!strcmp(type, "geneve")) {
        tnl_cfg.dst_port = htons(GENEVE_DST_PORT);
    }

    if (!strcmp(type, "vxlan")) {
        tnl_cfg.dst_port = htons(VXLAN_DST_PORT);
    }

    if (!strcmp(type, "lisp")) {
        tnl_cfg.dst_port = htons(LISP_DST_PORT);
    }

    if (!strcmp(type, "stt")) {
        tnl_cfg.dst_port = htons(STT_DST_PORT);
    }

    needs_dst_port = netdev_vport_needs_dst_port(dev_);
    tnl_cfg.ipsec = strstr(type, "ipsec");
    tnl_cfg.dont_fragment = true;

    SMAP_FOR_EACH (node, args) {
        if (!strcmp(node->key, "remote_ip")) {
            int err;
            err = parse_tunnel_ip(node->value, false, &tnl_cfg.ip_dst_flow,
                                  &tnl_cfg.ipv6_dst, &dst_proto);
            switch (err) {
            case ENOENT:
                VLOG_WARN("%s: bad %s 'remote_ip'", name, type);
                break;
            case EINVAL:
                VLOG_WARN("%s: multicast remote_ip=%s not allowed",
                          name, node->value);
                return EINVAL;
            }
        } else if (!strcmp(node->key, "local_ip")) {
            int err;
            err = parse_tunnel_ip(node->value, true, &tnl_cfg.ip_src_flow,
                                  &tnl_cfg.ipv6_src, &src_proto);
            switch (err) {
            case ENOENT:
                VLOG_WARN("%s: bad %s 'local_ip'", name, type);
                break;
            }
        } else if (!strcmp(node->key, "tos")) {
            if (!strcmp(node->value, "inherit")) {
                tnl_cfg.tos_inherit = true;
            } else {
                char *endptr;
                int tos;
                tos = strtol(node->value, &endptr, 0);
                if (*endptr == '\0' && tos == (tos & IP_DSCP_MASK)) {
                    tnl_cfg.tos = tos;
                } else {
                    VLOG_WARN("%s: invalid TOS %s", name, node->value);
                }
            }
        } else if (!strcmp(node->key, "ttl")) {
            if (!strcmp(node->value, "inherit")) {
                tnl_cfg.ttl_inherit = true;
            } else {
                tnl_cfg.ttl = atoi(node->value);
            }
        } else if (!strcmp(node->key, "dst_port") && needs_dst_port) {
            tnl_cfg.dst_port = htons(atoi(node->value));
        } else if (!strcmp(node->key, "csum") && has_csum) {
            if (!strcmp(node->value, "true")) {
                tnl_cfg.csum = true;
            }
        } else if (!strcmp(node->key, "df_default")) {
            if (!strcmp(node->value, "false")) {
                tnl_cfg.dont_fragment = false;
            }
        } else if (!strcmp(node->key, "peer_cert") && tnl_cfg.ipsec) {
            if (smap_get(args, "certificate")) {
                ipsec_mech_set = true;
            } else {
                const char *use_ssl_cert;

                /* If the "use_ssl_cert" is true, then "certificate" and
                 * "private_key" will be pulled from the SSL table.  The
                 * use of this option is strongly discouraged, since it
                 * will like be removed when multiple SSL configurations
                 * are supported by OVS.
                 */
                use_ssl_cert = smap_get(args, "use_ssl_cert");
                if (!use_ssl_cert || strcmp(use_ssl_cert, "true")) {
                    VLOG_ERR("%s: 'peer_cert' requires 'certificate' argument",
                             name);
                    return EINVAL;
                }
                ipsec_mech_set = true;
            }
        } else if (!strcmp(node->key, "psk") && tnl_cfg.ipsec) {
            ipsec_mech_set = true;
        } else if (tnl_cfg.ipsec
                && (!strcmp(node->key, "certificate")
                    || !strcmp(node->key, "private_key")
                    || !strcmp(node->key, "use_ssl_cert"))) {
            /* Ignore options not used by the netdev. */
        } else if (!strcmp(node->key, "key") ||
                   !strcmp(node->key, "in_key") ||
                   !strcmp(node->key, "out_key")) {
            /* Handled separately below. */
        } else if (!strcmp(node->key, "exts")) {
            char *str = xstrdup(node->value);
            char *ext, *save_ptr = NULL;

            tnl_cfg.exts = 0;

            ext = strtok_r(str, ",", &save_ptr);
            while (ext) {
                if (!strcmp(type, "vxlan") && !strcmp(ext, "gbp")) {
                    tnl_cfg.exts |= (1 << OVS_VXLAN_EXT_GBP);
                } else {
                    VLOG_WARN("%s: unknown extension '%s'", name, ext);
                }

                ext = strtok_r(NULL, ",", &save_ptr);
            }

            free(str);
        } else {
            VLOG_WARN("%s: unknown %s argument '%s'", name, type, node->key);
        }
    }

    if (tnl_cfg.ipsec) {
        static struct ovs_mutex mutex = OVS_MUTEX_INITIALIZER;
        static pid_t pid = 0;

#ifndef _WIN32
        ovs_mutex_lock(&mutex);
        if (pid <= 0) {
            char *file_name = xasprintf("%s/%s", ovs_rundir(),
                                        "ovs-monitor-ipsec.pid");
            pid = read_pidfile(file_name);
            free(file_name);
        }
        ovs_mutex_unlock(&mutex);
#endif

        if (pid < 0) {
            VLOG_ERR("%s: IPsec requires the ovs-monitor-ipsec daemon",
                     name);
            return EINVAL;
        }

        if (smap_get(args, "peer_cert") && smap_get(args, "psk")) {
            VLOG_ERR("%s: cannot define both 'peer_cert' and 'psk'", name);
            return EINVAL;
        }

        if (!ipsec_mech_set) {
            VLOG_ERR("%s: IPsec requires an 'peer_cert' or psk' argument",
                     name);
            return EINVAL;
        }
    }

    if (!ipv6_addr_is_set(&tnl_cfg.ipv6_dst) && !tnl_cfg.ip_dst_flow) {
        VLOG_ERR("%s: %s type requires valid 'remote_ip' argument",
                 name, type);
        return EINVAL;
    }
    if (tnl_cfg.ip_src_flow && !tnl_cfg.ip_dst_flow) {
        VLOG_ERR("%s: %s type requires 'remote_ip=flow' with 'local_ip=flow'",
                 name, type);
        return EINVAL;
    }
    if (src_proto && dst_proto && src_proto != dst_proto) {
        VLOG_ERR("%s: 'remote_ip' and 'local_ip' has to be of the same address family",
                 name);
        return EINVAL;
    }
    if (!tnl_cfg.ttl) {
        tnl_cfg.ttl = DEFAULT_TTL;
    }

    tnl_cfg.in_key = parse_key(args, "in_key",
                               &tnl_cfg.in_key_present,
                               &tnl_cfg.in_key_flow);

    tnl_cfg.out_key = parse_key(args, "out_key",
                               &tnl_cfg.out_key_present,
                               &tnl_cfg.out_key_flow);

    ovs_mutex_lock(&dev->mutex);
    if (memcmp(&dev->tnl_cfg, &tnl_cfg, sizeof tnl_cfg)) {
        dev->tnl_cfg = tnl_cfg;
        tunnel_check_status_change__(dev);
        netdev_change_seq_changed(dev_);
    }
    ovs_mutex_unlock(&dev->mutex);

    return 0;
}

static int
get_tunnel_config(const struct netdev *dev, struct smap *args)
{
    struct netdev_vport *netdev = netdev_vport_cast(dev);
    struct netdev_tunnel_config tnl_cfg;

    ovs_mutex_lock(&netdev->mutex);
    tnl_cfg = netdev->tnl_cfg;
    ovs_mutex_unlock(&netdev->mutex);

    if (ipv6_addr_is_set(&tnl_cfg.ipv6_dst)) {
        smap_add_ipv6(args, "remote_ip", &tnl_cfg.ipv6_dst);
    } else if (tnl_cfg.ip_dst_flow) {
        smap_add(args, "remote_ip", "flow");
    }

    if (ipv6_addr_is_set(&tnl_cfg.ipv6_src)) {
        smap_add_ipv6(args, "local_ip", &tnl_cfg.ipv6_src);
    } else if (tnl_cfg.ip_src_flow) {
        smap_add(args, "local_ip", "flow");
    }

    if (tnl_cfg.in_key_flow && tnl_cfg.out_key_flow) {
        smap_add(args, "key", "flow");
    } else if (tnl_cfg.in_key_present && tnl_cfg.out_key_present
               && tnl_cfg.in_key == tnl_cfg.out_key) {
        smap_add_format(args, "key", "%"PRIu64, ntohll(tnl_cfg.in_key));
    } else {
        if (tnl_cfg.in_key_flow) {
            smap_add(args, "in_key", "flow");
        } else if (tnl_cfg.in_key_present) {
            smap_add_format(args, "in_key", "%"PRIu64,
                            ntohll(tnl_cfg.in_key));
        }

        if (tnl_cfg.out_key_flow) {
            smap_add(args, "out_key", "flow");
        } else if (tnl_cfg.out_key_present) {
            smap_add_format(args, "out_key", "%"PRIu64,
                            ntohll(tnl_cfg.out_key));
        }
    }

    if (tnl_cfg.ttl_inherit) {
        smap_add(args, "ttl", "inherit");
    } else if (tnl_cfg.ttl != DEFAULT_TTL) {
        smap_add_format(args, "ttl", "%"PRIu8, tnl_cfg.ttl);
    }

    if (tnl_cfg.tos_inherit) {
        smap_add(args, "tos", "inherit");
    } else if (tnl_cfg.tos) {
        smap_add_format(args, "tos", "0x%x", tnl_cfg.tos);
    }

    if (tnl_cfg.dst_port) {
        uint16_t dst_port = ntohs(tnl_cfg.dst_port);
        const char *type = netdev_get_type(dev);

        if ((!strcmp("geneve", type) && dst_port != GENEVE_DST_PORT) ||
            (!strcmp("vxlan", type) && dst_port != VXLAN_DST_PORT) ||
            (!strcmp("lisp", type) && dst_port != LISP_DST_PORT) ||
            (!strcmp("stt", type) && dst_port != STT_DST_PORT)) {
            smap_add_format(args, "dst_port", "%d", dst_port);
        }
    }

    if (tnl_cfg.csum) {
        smap_add(args, "csum", "true");
    }

    if (!tnl_cfg.dont_fragment) {
        smap_add(args, "df_default", "false");
    }

    return 0;
}

/* Code specific to patch ports. */

/* If 'netdev' is a patch port, returns the name of its peer as a malloc()'d
 * string that the caller must free.
 *
 * If 'netdev' is not a patch port, returns NULL. */
char *
netdev_vport_patch_peer(const struct netdev *netdev_)
{
    char *peer = NULL;

    if (netdev_vport_is_patch(netdev_)) {
        struct netdev_vport *netdev = netdev_vport_cast(netdev_);

        ovs_mutex_lock(&netdev->mutex);
        if (netdev->peer) {
            peer = xstrdup(netdev->peer);
        }
        ovs_mutex_unlock(&netdev->mutex);
    }

    return peer;
}

void
netdev_vport_inc_rx(const struct netdev *netdev,
                    const struct dpif_flow_stats *stats)
{
    if (is_vport_class(netdev_get_class(netdev))) {
        struct netdev_vport *dev = netdev_vport_cast(netdev);

        ovs_mutex_lock(&dev->mutex);
        dev->stats.rx_packets += stats->n_packets;
        dev->stats.rx_bytes += stats->n_bytes;
        ovs_mutex_unlock(&dev->mutex);
    }
}

void
netdev_vport_inc_tx(const struct netdev *netdev,
                    const struct dpif_flow_stats *stats)
{
    if (is_vport_class(netdev_get_class(netdev))) {
        struct netdev_vport *dev = netdev_vport_cast(netdev);

        ovs_mutex_lock(&dev->mutex);
        dev->stats.tx_packets += stats->n_packets;
        dev->stats.tx_bytes += stats->n_bytes;
        ovs_mutex_unlock(&dev->mutex);
    }
}

static int
get_patch_config(const struct netdev *dev_, struct smap *args)
{
    struct netdev_vport *dev = netdev_vport_cast(dev_);

    ovs_mutex_lock(&dev->mutex);
    if (dev->peer) {
        smap_add(args, "peer", dev->peer);
    }
    ovs_mutex_unlock(&dev->mutex);

    return 0;
}

static int
set_patch_config(struct netdev *dev_, const struct smap *args)
{
    struct netdev_vport *dev = netdev_vport_cast(dev_);
    const char *name = netdev_get_name(dev_);
    const char *peer;

    peer = smap_get(args, "peer");
    if (!peer) {
        VLOG_ERR("%s: patch type requires valid 'peer' argument", name);
        return EINVAL;
    }

    if (smap_count(args) > 1) {
        VLOG_ERR("%s: patch type takes only a 'peer' argument", name);
        return EINVAL;
    }

    if (!strcmp(name, peer)) {
        VLOG_ERR("%s: patch peer must not be self", name);
        return EINVAL;
    }

    ovs_mutex_lock(&dev->mutex);
    if (!dev->peer || strcmp(dev->peer, peer)) {
        free(dev->peer);
        dev->peer = xstrdup(peer);
        netdev_change_seq_changed(dev_);
    }
    ovs_mutex_unlock(&dev->mutex);

    return 0;
}

static int
get_stats(const struct netdev *netdev, struct netdev_stats *stats)
{
    struct netdev_vport *dev = netdev_vport_cast(netdev);

    ovs_mutex_lock(&dev->mutex);
    *stats = dev->stats;
    ovs_mutex_unlock(&dev->mutex);

    return 0;
}


/* Tunnel push pop ops. */

static struct ip_header *
ip_hdr(void *eth)
{
    return (void *)((char *)eth + sizeof (struct eth_header));
}

static struct ovs_16aligned_ip6_hdr *
ipv6_hdr(void *eth)
{
    return (void *)((char *)eth + sizeof (struct eth_header));
}

static void *
ip_extract_tnl_md(struct dp_packet *packet, struct flow_tnl *tnl,
                  unsigned int *hlen)
{
    void *nh;
    struct ip_header *ip;
    struct ovs_16aligned_ip6_hdr *ip6;
    void *l4;
    int l3_size;

    nh = dp_packet_l3(packet);
    ip = nh;
    ip6 = nh;
    l4 = dp_packet_l4(packet);

    if (!nh || !l4) {
        return NULL;
    }

    *hlen = sizeof(struct eth_header);

    l3_size = dp_packet_size(packet) -
              ((char *)nh - (char *)dp_packet_data(packet));

    if (IP_VER(ip->ip_ihl_ver) == 4) {

        ovs_be32 ip_src, ip_dst;

        if (csum(ip, IP_IHL(ip->ip_ihl_ver) * 4)) {
            VLOG_WARN_RL(&err_rl, "ip packet has invalid checksum");
            return NULL;
        }

        if (ntohs(ip->ip_tot_len) > l3_size) {
            VLOG_WARN_RL(&err_rl, "ip packet is truncated (IP length %d, actual %d)",
                         ntohs(ip->ip_tot_len), l3_size);
            return NULL;
        }
        if (IP_IHL(ip->ip_ihl_ver) * 4 > sizeof(struct ip_header)) {
            VLOG_WARN_RL(&err_rl, "ip options not supported on tunnel packets "
                         "(%d bytes)", IP_IHL(ip->ip_ihl_ver) * 4);
            return NULL;
        }

        ip_src = get_16aligned_be32(&ip->ip_src);
        ip_dst = get_16aligned_be32(&ip->ip_dst);

        tnl->ip_src = ip_src;
        tnl->ip_dst = ip_dst;
        tnl->ip_tos = ip->ip_tos;
        tnl->ip_ttl = ip->ip_ttl;

        *hlen += IP_HEADER_LEN;

    } else if (IP_VER(ip->ip_ihl_ver) == 6) {

        memcpy(tnl->ipv6_src.s6_addr, ip6->ip6_src.be16, sizeof ip6->ip6_src);
        memcpy(tnl->ipv6_dst.s6_addr, ip6->ip6_dst.be16, sizeof ip6->ip6_dst);
        tnl->ip_tos = 0;
        tnl->ip_ttl = ip6->ip6_hlim;

        *hlen += IPV6_HEADER_LEN;

    } else {
        VLOG_WARN_RL(&err_rl, "ipv4 packet has invalid version (%d)",
                     IP_VER(ip->ip_ihl_ver));
        return NULL;
    }

    return l4;
}

static bool
is_header_ipv6(const void *header)
{
    const struct eth_header *eth;
    eth = header;
    return eth->eth_type == htons(ETH_TYPE_IPV6);
}

/* Pushes the 'size' bytes of 'header' into the headroom of 'packet',
 * reallocating the packet if necessary.  'header' should contain an Ethernet
 * header, followed by an IPv4 header (without options), and an L4 header.
 *
 * This function sets the IP header's ip_tot_len field (which should be zeroed
 * as part of 'header') and puts its value into '*ip_tot_size' as well.  Also
 * updates IP header checksum.
 *
 * Return pointer to the L4 header added to 'packet'. */
static void *
push_ip_header(struct dp_packet *packet,
               const void *header, int size, int *ip_tot_size)
{
    struct eth_header *eth;
    struct ip_header *ip;
    struct ovs_16aligned_ip6_hdr *ip6;

    eth = dp_packet_push_uninit(packet, size);
    *ip_tot_size = dp_packet_size(packet) - sizeof (struct eth_header);

    memcpy(eth, header, size);

    if (is_header_ipv6(header)) {
        ip6 = ipv6_hdr(eth);
        *ip_tot_size -= IPV6_HEADER_LEN;
        ip6->ip6_plen = htons(*ip_tot_size);
        return ip6 + 1;
    } else {
        ip = ip_hdr(eth);
        ip->ip_tot_len = htons(*ip_tot_size);
        ip->ip_csum = recalc_csum16(ip->ip_csum, 0, ip->ip_tot_len);
        *ip_tot_size -= IP_HEADER_LEN;
        return ip + 1;
    }
}

static void *
udp_extract_tnl_md(struct dp_packet *packet, struct flow_tnl *tnl,
                   unsigned int *hlen)
{
    struct udp_header *udp;

    udp = ip_extract_tnl_md(packet, tnl, hlen);
    if (!udp) {
        return NULL;
    }

    if (udp->udp_csum) {
        uint32_t csum;
        if (is_header_ipv6(dp_packet_data(packet))) {
            csum = packet_csum_pseudoheader6(dp_packet_l3(packet));
        } else {
            csum = packet_csum_pseudoheader(dp_packet_l3(packet));
        }

        csum = csum_continue(csum, udp, dp_packet_size(packet) -
                             ((const unsigned char *)udp -
                              (const unsigned char *)dp_packet_l2(packet)));
        if (csum_finish(csum)) {
            return NULL;
        }
        tnl->flags |= FLOW_TNL_F_CSUM;
    }

    tnl->tp_src = udp->udp_src;
    tnl->tp_dst = udp->udp_dst;

    return udp + 1;
}

static ovs_be16
get_src_port(struct dp_packet *packet)
{
    uint32_t hash;

    hash = dp_packet_get_rss_hash(packet);

    return htons((((uint64_t) hash * (tnl_udp_port_max - tnl_udp_port_min)) >> 32) +
                 tnl_udp_port_min);
}

static void
push_udp_header(struct dp_packet *packet,
                const struct ovs_action_push_tnl *data)
{
    struct udp_header *udp;
    int ip_tot_size;

    udp = push_ip_header(packet, data->header, data->header_len, &ip_tot_size);

    /* set udp src port */
    udp->udp_src = get_src_port(packet);
    udp->udp_len = htons(ip_tot_size);

    if (udp->udp_csum) {
        uint32_t csum;
        if (is_header_ipv6(dp_packet_data(packet))) {
            csum = packet_csum_pseudoheader6(ipv6_hdr(dp_packet_data(packet)));
        } else {
            csum = packet_csum_pseudoheader(ip_hdr(dp_packet_data(packet)));
        }

        csum = csum_continue(csum, udp, ip_tot_size);
        udp->udp_csum = csum_finish(csum);

        if (!udp->udp_csum) {
            udp->udp_csum = htons(0xffff);
        }
    }
}

static void *
udp_build_header(struct netdev_tunnel_config *tnl_cfg,
                 const struct flow *tnl_flow,
                 struct ovs_action_push_tnl *data,
                 unsigned int *hlen)
{
    struct ip_header *ip;
    struct ovs_16aligned_ip6_hdr *ip6;
    struct udp_header *udp;
    bool is_ipv6;

    *hlen = sizeof(struct eth_header);

    is_ipv6 = is_header_ipv6(data->header);

    if (is_ipv6) {
        ip6 = ipv6_hdr(data->header);
        ip6->ip6_nxt = IPPROTO_UDP;
        udp = (struct udp_header *) (ip6 + 1);
        *hlen += IPV6_HEADER_LEN;
    } else {
        ip = ip_hdr(data->header);
        ip->ip_proto = IPPROTO_UDP;
        udp = (struct udp_header *) (ip + 1);
        *hlen += IP_HEADER_LEN;
    }

    udp->udp_dst = tnl_cfg->dst_port;

    if (is_ipv6 || tnl_flow->tunnel.flags & FLOW_TNL_F_CSUM) {
        /* Write a value in now to mark that we should compute the checksum
         * later. 0xffff is handy because it is transparent to the
         * calculation. */
        udp->udp_csum = htons(0xffff);
    }

    return udp + 1;
}

static int
gre_header_len(ovs_be16 flags)
{
    int hlen = 4;

    if (flags & htons(GRE_CSUM)) {
        hlen += 4;
    }
    if (flags & htons(GRE_KEY)) {
        hlen += 4;
    }
    if (flags & htons(GRE_SEQ)) {
        hlen += 4;
    }
    return hlen;
}

static int
parse_gre_header(struct dp_packet *packet,
                 struct flow_tnl *tnl)
{
    const struct gre_base_hdr *greh;
    ovs_16aligned_be32 *options;
    int hlen;
    unsigned int ulen;

    greh = ip_extract_tnl_md(packet, tnl, &ulen);
    if (!greh) {
        return -EINVAL;
    }

    if (greh->flags & ~(htons(GRE_CSUM | GRE_KEY | GRE_SEQ))) {
        return -EINVAL;
    }

    if (greh->protocol != htons(ETH_TYPE_TEB)) {
        return -EINVAL;
    }

    hlen = ulen + gre_header_len(greh->flags);
    if (hlen > dp_packet_size(packet)) {
        return -EINVAL;
    }

    options = (ovs_16aligned_be32 *)(greh + 1);
    if (greh->flags & htons(GRE_CSUM)) {
        ovs_be16 pkt_csum;

        pkt_csum = csum(greh, dp_packet_size(packet) -
                              ((const unsigned char *)greh -
                               (const unsigned char *)dp_packet_l2(packet)));
        if (pkt_csum) {
            return -EINVAL;
        }
        tnl->flags = FLOW_TNL_F_CSUM;
        options++;
    }

    if (greh->flags & htons(GRE_KEY)) {
        tnl->tun_id = (OVS_FORCE ovs_be64) ((OVS_FORCE uint64_t)(get_16aligned_be32(options)) << 32);
        tnl->flags |= FLOW_TNL_F_KEY;
        options++;
    }

    if (greh->flags & htons(GRE_SEQ)) {
        options++;
    }

    return hlen;
}

static void
pkt_metadata_init_tnl(struct pkt_metadata *md)
{
    /* Zero up through the tunnel metadata options. The length and table
     * are before this and as long as they are empty, the options won't
     * be looked at. */
    memset(md, 0, offsetof(struct pkt_metadata, tunnel.metadata.opts));
}

static int
netdev_gre_pop_header(struct dp_packet *packet)
{
    struct pkt_metadata *md = &packet->md;
    struct flow_tnl *tnl = &md->tunnel;
    int hlen = sizeof(struct eth_header) + 4;

    hlen += is_header_ipv6(dp_packet_data(packet)) ?
            IPV6_HEADER_LEN : IP_HEADER_LEN;

    pkt_metadata_init_tnl(md);
    if (hlen > dp_packet_size(packet)) {
        return EINVAL;
    }

    hlen = parse_gre_header(packet, tnl);
    if (hlen < 0) {
        return -hlen;
    }

    dp_packet_reset_packet(packet, hlen);

    return 0;
}

static void
netdev_gre_push_header(struct dp_packet *packet,
                       const struct ovs_action_push_tnl *data)
{
    struct gre_base_hdr *greh;
    int ip_tot_size;

    greh = push_ip_header(packet, data->header, data->header_len, &ip_tot_size);

    if (greh->flags & htons(GRE_CSUM)) {
        ovs_be16 *csum_opt = (ovs_be16 *) (greh + 1);
        *csum_opt = csum(greh, ip_tot_size);
    }
}

static int
netdev_gre_build_header(const struct netdev *netdev,
                        struct ovs_action_push_tnl *data,
                        const struct flow *tnl_flow)
{
    struct netdev_vport *dev = netdev_vport_cast(netdev);
    struct netdev_tunnel_config *tnl_cfg;
    struct ip_header *ip;
    struct ovs_16aligned_ip6_hdr *ip6;
    struct gre_base_hdr *greh;
    ovs_16aligned_be32 *options;
    int hlen;
    bool is_ipv6;

    is_ipv6 = is_header_ipv6(data->header);

    /* XXX: RCUfy tnl_cfg. */
    ovs_mutex_lock(&dev->mutex);
    tnl_cfg = &dev->tnl_cfg;

    if (is_ipv6) {
        ip6 = ipv6_hdr(data->header);
        ip6->ip6_nxt = IPPROTO_GRE;
        greh = (struct gre_base_hdr *) (ip6 + 1);
    } else {
        ip = ip_hdr(data->header);
        ip->ip_proto = IPPROTO_GRE;
        greh = (struct gre_base_hdr *) (ip + 1);
    }

    greh->protocol = htons(ETH_TYPE_TEB);
    greh->flags = 0;

    options = (ovs_16aligned_be32 *) (greh + 1);
    if (tnl_flow->tunnel.flags & FLOW_TNL_F_CSUM) {
        greh->flags |= htons(GRE_CSUM);
        put_16aligned_be32(options, 0);
        options++;
    }

    if (tnl_cfg->out_key_present) {
        greh->flags |= htons(GRE_KEY);
        put_16aligned_be32(options, (OVS_FORCE ovs_be32)
                                    ((OVS_FORCE uint64_t) tnl_flow->tunnel.tun_id >> 32));
        options++;
    }

    ovs_mutex_unlock(&dev->mutex);

    hlen = (uint8_t *) options - (uint8_t *) greh;

    data->header_len = sizeof(struct eth_header) + hlen +
                       (is_ipv6 ? IPV6_HEADER_LEN : IP_HEADER_LEN);
    data->tnl_type = OVS_VPORT_TYPE_GRE;
    return 0;
}

static int
netdev_vxlan_pop_header(struct dp_packet *packet)
{
    struct pkt_metadata *md = &packet->md;
    struct flow_tnl *tnl = &md->tunnel;
    struct vxlanhdr *vxh;
    unsigned int hlen;

    pkt_metadata_init_tnl(md);
    if (VXLAN_HLEN > dp_packet_l4_size(packet)) {
        return EINVAL;
    }

    vxh = udp_extract_tnl_md(packet, tnl, &hlen);
    if (!vxh) {
        return EINVAL;
    }

    if (get_16aligned_be32(&vxh->vx_flags) != htonl(VXLAN_FLAGS) ||
       (get_16aligned_be32(&vxh->vx_vni) & htonl(0xff))) {
        VLOG_WARN_RL(&err_rl, "invalid vxlan flags=%#x vni=%#x\n",
                     ntohl(get_16aligned_be32(&vxh->vx_flags)),
                     ntohl(get_16aligned_be32(&vxh->vx_vni)));
        return EINVAL;
    }
    tnl->tun_id = htonll(ntohl(get_16aligned_be32(&vxh->vx_vni)) >> 8);
    tnl->flags |= FLOW_TNL_F_KEY;

    dp_packet_reset_packet(packet, hlen + VXLAN_HLEN);

    return 0;
}

static int
netdev_vxlan_build_header(const struct netdev *netdev,
                          struct ovs_action_push_tnl *data,
                          const struct flow *tnl_flow)
{
    struct netdev_vport *dev = netdev_vport_cast(netdev);
    struct netdev_tunnel_config *tnl_cfg;
    struct vxlanhdr *vxh;
    unsigned int hlen;

    /* XXX: RCUfy tnl_cfg. */
    ovs_mutex_lock(&dev->mutex);
    tnl_cfg = &dev->tnl_cfg;

    vxh = udp_build_header(tnl_cfg, tnl_flow, data, &hlen);

    put_16aligned_be32(&vxh->vx_flags, htonl(VXLAN_FLAGS));
    put_16aligned_be32(&vxh->vx_vni, htonl(ntohll(tnl_flow->tunnel.tun_id) << 8));

    ovs_mutex_unlock(&dev->mutex);
    data->header_len = hlen + VXLAN_HLEN;
    data->tnl_type = OVS_VPORT_TYPE_VXLAN;
    return 0;
}

static int
netdev_geneve_pop_header(struct dp_packet *packet)
{
    struct pkt_metadata *md = &packet->md;
    struct flow_tnl *tnl = &md->tunnel;
    struct genevehdr *gnh;
    unsigned int hlen, opts_len, ulen;

    pkt_metadata_init_tnl(md);
    if (GENEVE_BASE_HLEN > dp_packet_l4_size(packet)) {
        VLOG_WARN_RL(&err_rl, "geneve packet too small: min header=%u packet size=%"PRIuSIZE"\n",
                     (unsigned int)GENEVE_BASE_HLEN, dp_packet_l4_size(packet));
        return EINVAL;
    }

    gnh = udp_extract_tnl_md(packet, tnl, &ulen);
    if (!gnh) {
        return EINVAL;
    }

    opts_len = gnh->opt_len * 4;
    hlen = ulen + GENEVE_BASE_HLEN + opts_len;
    if (hlen > dp_packet_size(packet)) {
        VLOG_WARN_RL(&err_rl, "geneve packet too small: header len=%u packet size=%u\n",
                     hlen, dp_packet_size(packet));
        return EINVAL;
    }

    if (gnh->ver != 0) {
        VLOG_WARN_RL(&err_rl, "unknown geneve version: %"PRIu8"\n", gnh->ver);
        return EINVAL;
    }

    if (gnh->proto_type != htons(ETH_TYPE_TEB)) {
        VLOG_WARN_RL(&err_rl, "unknown geneve encapsulated protocol: %#x\n",
                     ntohs(gnh->proto_type));
        return EINVAL;
    }

    tnl->flags |= gnh->oam ? FLOW_TNL_F_OAM : 0;
    tnl->tun_id = htonll(ntohl(get_16aligned_be32(&gnh->vni)) >> 8);
    tnl->flags |= FLOW_TNL_F_KEY;

    memcpy(tnl->metadata.opts.gnv, gnh->options, opts_len);
    tnl->metadata.present.len = opts_len;
    tnl->flags |= FLOW_TNL_F_UDPIF;

    dp_packet_reset_packet(packet, hlen);

    return 0;
}

static int
netdev_geneve_build_header(const struct netdev *netdev,
                           struct ovs_action_push_tnl *data,
                           const struct flow *tnl_flow)
{
    struct netdev_vport *dev = netdev_vport_cast(netdev);
    struct netdev_tunnel_config *tnl_cfg;
    struct genevehdr *gnh;
    int opt_len;
    bool crit_opt;
    unsigned int hlen;

    /* XXX: RCUfy tnl_cfg. */
    ovs_mutex_lock(&dev->mutex);
    tnl_cfg = &dev->tnl_cfg;

    gnh = udp_build_header(tnl_cfg, tnl_flow, data, &hlen);

    put_16aligned_be32(&gnh->vni, htonl(ntohll(tnl_flow->tunnel.tun_id) << 8));

    ovs_mutex_unlock(&dev->mutex);

    opt_len = tun_metadata_to_geneve_header(&tnl_flow->tunnel,
                                            gnh->options, &crit_opt);

    gnh->opt_len = opt_len / 4;
    gnh->oam = !!(tnl_flow->tunnel.flags & FLOW_TNL_F_OAM);
    gnh->critical = crit_opt ? 1 : 0;
    gnh->proto_type = htons(ETH_TYPE_TEB);

    data->header_len = hlen + GENEVE_BASE_HLEN + opt_len;
    data->tnl_type = OVS_VPORT_TYPE_GENEVE;
    return 0;
}

static void
netdev_vport_range(struct unixctl_conn *conn, int argc,
                   const char *argv[], void *aux OVS_UNUSED)
{
    int val1, val2;

    if (argc < 3) {
        struct ds ds = DS_EMPTY_INITIALIZER;

        ds_put_format(&ds, "Tunnel UDP source port range: %"PRIu16"-%"PRIu16"\n",
                            tnl_udp_port_min, tnl_udp_port_max);

        unixctl_command_reply(conn, ds_cstr(&ds));
        ds_destroy(&ds);
        return;
    }

    if (argc != 3) {
        return;
    }

    val1 = atoi(argv[1]);
    if (val1 <= 0 || val1 > UINT16_MAX) {
        unixctl_command_reply(conn, "Invalid min.");
        return;
    }
    val2 = atoi(argv[2]);
    if (val2 <= 0 || val2 > UINT16_MAX) {
        unixctl_command_reply(conn, "Invalid max.");
        return;
    }

    if (val1 > val2) {
        tnl_udp_port_min = val2;
        tnl_udp_port_max = val1;
    } else {
        tnl_udp_port_min = val1;
        tnl_udp_port_max = val2;
    }
    seq_change(tnl_conf_seq);

    unixctl_command_reply(conn, "OK");
}


#define VPORT_FUNCTIONS(GET_CONFIG, SET_CONFIG,             \
                        GET_TUNNEL_CONFIG, GET_STATUS,      \
                        BUILD_HEADER,                       \
                        PUSH_HEADER, POP_HEADER)            \
    NULL,                                                   \
    netdev_vport_run,                                       \
    netdev_vport_wait,                                      \
                                                            \
    netdev_vport_alloc,                                     \
    netdev_vport_construct,                                 \
    netdev_vport_destruct,                                  \
    netdev_vport_dealloc,                                   \
    GET_CONFIG,                                             \
    SET_CONFIG,                                             \
    GET_TUNNEL_CONFIG,                                      \
    BUILD_HEADER,                                           \
    PUSH_HEADER,                                            \
    POP_HEADER,                                             \
    NULL,                       /* get_numa_id */           \
    NULL,                       /* set_multiq */            \
                                                            \
    NULL,                       /* send */                  \
    NULL,                       /* send_wait */             \
                                                            \
    netdev_vport_set_etheraddr,                             \
    netdev_vport_get_etheraddr,                             \
    NULL,                       /* get_mtu */               \
    NULL,                       /* set_mtu */               \
    NULL,                       /* get_ifindex */           \
    NULL,                       /* get_carrier */           \
    NULL,                       /* get_carrier_resets */    \
    NULL,                       /* get_miimon */            \
    get_stats,                                              \
                                                            \
    NULL,                       /* get_features */          \
    NULL,                       /* set_advertisements */    \
                                                            \
    NULL,                       /* set_policing */          \
    NULL,                       /* get_qos_types */         \
    NULL,                       /* get_qos_capabilities */  \
    NULL,                       /* get_qos */               \
    NULL,                       /* set_qos */               \
    NULL,                       /* get_queue */             \
    NULL,                       /* set_queue */             \
    NULL,                       /* delete_queue */          \
    NULL,                       /* get_queue_stats */       \
    NULL,                       /* queue_dump_start */      \
    NULL,                       /* queue_dump_next */       \
    NULL,                       /* queue_dump_done */       \
    NULL,                       /* dump_queue_stats */      \
                                                            \
    NULL,                       /* get_in4 */               \
    NULL,                       /* set_in4 */               \
    NULL,                       /* get_in6 */               \
    NULL,                       /* add_router */            \
    NULL,                       /* get_next_hop */          \
    GET_STATUS,                                             \
    NULL,                       /* arp_lookup */            \
                                                            \
    netdev_vport_update_flags,                              \
                                                            \
    NULL,                   /* rx_alloc */                  \
    NULL,                   /* rx_construct */              \
    NULL,                   /* rx_destruct */               \
    NULL,                   /* rx_dealloc */                \
    NULL,                   /* rx_recv */                   \
    NULL,                   /* rx_wait */                   \
    NULL,                   /* rx_drain */


#define TUNNEL_CLASS(NAME, DPIF_PORT, BUILD_HEADER, PUSH_HEADER, POP_HEADER)   \
    { DPIF_PORT,                                                               \
        { NAME, VPORT_FUNCTIONS(get_tunnel_config,                             \
                                set_tunnel_config,                             \
                                get_netdev_tunnel_config,                      \
                                tunnel_get_status,                             \
                                BUILD_HEADER, PUSH_HEADER, POP_HEADER) }}

void
netdev_vport_tunnel_register(void)
{
    /* The name of the dpif_port should be short enough to accomodate adding
     * a port number to the end if one is necessary. */
    static const struct vport_class vport_classes[] = {
        TUNNEL_CLASS("geneve", "genev_sys", netdev_geneve_build_header,
                                            push_udp_header,
                                            netdev_geneve_pop_header),
        TUNNEL_CLASS("gre", "gre_sys", netdev_gre_build_header,
                                       netdev_gre_push_header,
                                       netdev_gre_pop_header),
        TUNNEL_CLASS("ipsec_gre", "gre_sys", NULL, NULL, NULL),
        TUNNEL_CLASS("vxlan", "vxlan_sys", netdev_vxlan_build_header,
                                           push_udp_header,
                                           netdev_vxlan_pop_header),
        TUNNEL_CLASS("lisp", "lisp_sys", NULL, NULL, NULL),
        TUNNEL_CLASS("stt", "stt_sys", NULL, NULL, NULL),
    };
    static struct ovsthread_once once = OVSTHREAD_ONCE_INITIALIZER;

    if (ovsthread_once_start(&once)) {
        int i;

        for (i = 0; i < ARRAY_SIZE(vport_classes); i++) {
            netdev_register_provider(&vport_classes[i].netdev_class);
        }

        unixctl_command_register("tnl/egress_port_range", "min max", 0, 2,
                                 netdev_vport_range, NULL);

        ovsthread_once_done(&once);
    }
}

void
netdev_vport_patch_register(void)
{
    static const struct vport_class patch_class =
        { NULL,
            { "patch", VPORT_FUNCTIONS(get_patch_config,
                                       set_patch_config,
                                       NULL,
                                       NULL, NULL, NULL, NULL) }};
    netdev_register_provider(&patch_class.netdev_class);
}