-
Notifications
You must be signed in to change notification settings - Fork 16
/
0002-ovs-nsh-support-push-and-pop-actions-for-vxlan-gpe-a.patch
2746 lines (2669 loc) · 93.6 KB
/
0002-ovs-nsh-support-push-and-pop-actions-for-vxlan-gpe-a.patch
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
From 4022104c9647a660a43680ac9e0173b4e7b65a73 Mon Sep 17 00:00:00 2001
From: Yi Yang <yi.y.yang@intel.com>
Date: Wed, 13 Apr 2016 11:15:42 +0800
Subject: [PATCH 2/8] ovs-nsh: support push and pop actions for vxlan-gpe and
Ethernet nsh
Signed-off-by: Mengke Liu <mengke.liu@intel.com>
Signed-off-by: Ricky Li <ricky.li@intel.com>
Signed-off-by: Johnson Li <johnson.li@intel.com>
Signed-off-by: Yi Yang <yi.y.yang@intel.com>
---
datapath/actions.c | 73 ++++
datapath/datapath.h | 2 +
datapath/flow.c | 107 ++++++
datapath/flow.h | 15 +
datapath/flow_netlink.c | 81 ++++-
datapath/linux/compat/include/linux/openvswitch.h | 174 +++++++++
datapath/linux/compat/include/net/vxlan.h | 5 +-
lib/dpif-netdev.c | 4 +
lib/dpif.c | 4 +
lib/flow.c | 19 +
lib/flow.h | 21 +-
lib/match.c | 190 ++++++++++
lib/match.h | 24 ++
lib/meta-flow.c | 256 ++++++++++++-
lib/meta-flow.h | 174 +++++++++
lib/netdev-vport.c | 10 +-
lib/nx-match.c | 19 +
lib/odp-execute.c | 10 +
lib/odp-util.c | 417 +++++++++++++++++++++-
lib/odp-util.h | 10 +-
lib/ofp-actions.c | 154 +++++++-
lib/ofp-actions.h | 6 +
ofproto/ofproto-dpif-sflow.c | 2 +
ofproto/ofproto-dpif-upcall.c | 19 +
ofproto/ofproto-dpif-xlate.c | 22 ++
tests/ofproto.at | 13 +-
tests/tunnel.at | 157 ++++++++
27 files changed, 1976 insertions(+), 12 deletions(-)
diff --git a/datapath/actions.c b/datapath/actions.c
index dcf8591..16fc58f 100644
--- a/datapath/actions.c
+++ b/datapath/actions.c
@@ -252,6 +252,63 @@ static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
}
+static int pop_nsh(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ if (!pskb_may_pull(skb, NSH_M_TYPE1_LEN))
+ return -ENOMEM;
+ else
+ __skb_pull(skb, NSH_M_TYPE1_LEN);
+
+ return 0;
+}
+
+static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct ovs_action_push_nsh *nsh)
+{
+
+ if (nsh->nsh_mdtype == NSH_M_TYPE1) {
+ if (skb_cow_head(skb, NSH_M_TYPE1_LEN) < 0)
+ return -ENOMEM;
+
+ skb_push(skb, NSH_M_TYPE1_LEN);
+ OVS_CB(skb)->nsh_header = skb->data;
+ memcpy(OVS_CB(skb)->nsh_header, nsh->header, NSH_M_TYPE1_LEN);
+ }
+ else
+ return -EINVAL;
+
+ return 0;
+}
+
+static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ if (!pskb_may_pull(skb, ENCAP_ETH_PUSH_HEADER_SIZE))
+ return -ENOMEM;
+ else
+ __skb_pull(skb, ENCAP_ETH_PUSH_HEADER_SIZE);
+
+ return 0;
+}
+
+static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct ovs_action_push_eth *encap_eth)
+{
+ if (encap_eth->encap_eth_type == htons(ETH_P_NSH)) {
+ if (skb_cow_head(skb, ENCAP_ETH_PUSH_HEADER_SIZE) < 0)
+ return -ENOMEM;
+
+ skb_push(skb, ENCAP_ETH_PUSH_HEADER_SIZE);
+ OVS_CB(skb)->encap_eth_header = skb->data;
+ memcpy(OVS_CB(skb)->encap_eth_header, encap_eth->header, ENCAP_ETH_PUSH_HEADER_SIZE);
+ }
+ else {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+
/* 'src' is already properly masked. */
static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_)
{
@@ -1079,6 +1136,22 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
err = pop_vlan(skb, key);
break;
+ case OVS_ACTION_ATTR_PUSH_NSH:
+ err = push_nsh(skb, key, nla_data(a));
+ break;
+
+ case OVS_ACTION_ATTR_POP_NSH:
+ err = pop_nsh(skb, key);
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ err = push_eth(skb, key, nla_data(a));
+ break;
+
+ case OVS_ACTION_ATTR_POP_ETH:
+ err = pop_eth(skb, key);
+ break;
+
case OVS_ACTION_ATTR_RECIRC:
err = execute_recirc(dp, skb, key, a, rem);
if (nla_is_last(a, rem)) {
diff --git a/datapath/datapath.h b/datapath/datapath.h
index ceb3372..b2d5fcd 100644
--- a/datapath/datapath.h
+++ b/datapath/datapath.h
@@ -102,6 +102,8 @@ struct datapath {
struct ovs_skb_cb {
struct vport *input_vport;
u16 mru;
+ struct nsh_hdr *nsh_header;
+ struct encap_eth_hdr *encap_eth_header;
};
#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
diff --git a/datapath/flow.c b/datapath/flow.c
index c97c9c9..67b2f1d 100644
--- a/datapath/flow.c
+++ b/datapath/flow.c
@@ -44,6 +44,7 @@
#include <net/ipv6.h>
#include <net/mpls.h>
#include <net/ndisc.h>
+#include <net/vxlan.h>
#include "datapath.h"
#include "conntrack.h"
@@ -318,6 +319,32 @@ static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
return 0;
}
+static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key){
+ struct nsh_hdr *nsh_hdr = (struct nsh_hdr *)skb->data;
+ OVS_CB(skb)->nsh_header = nsh_hdr;
+ key->nsh.nsh_mdtype = nsh_hdr->base.mdtype;
+ if (key->nsh.nsh_mdtype != NSH_M_TYPE1)
+ return -EPERM;
+ key->nsh.nsh_np = nsh_hdr->base.proto;
+ key->nsh.nsi = nsh_hdr->base.svc_idx;
+ key->nsh.nsp = nsh_hdr->base.path_hdr << 8;
+ key->nsh.nshc1 = nsh_hdr->ctx.nshc1;
+ key->nsh.nshc2 = nsh_hdr->ctx.nshc2;
+ key->nsh.nshc3 = nsh_hdr->ctx.nshc3;
+ key->nsh.nshc4 = nsh_hdr->ctx.nshc4;
+ return 0;
+}
+
+static void parse_encap_eth(struct sk_buff *skb, struct sw_flow_key *key){
+ struct encap_eth_hdr *encap_eth_header = (struct encap_eth_hdr *)skb->data;
+ OVS_CB(skb)->encap_eth_header = encap_eth_header;
+ key->encap_eth.encap_eth_type = encap_eth_header->encap_eth_type;
+ ether_addr_copy(key->encap_eth.encap_eth_src, encap_eth_header->encap_eth_src);
+ ether_addr_copy(key->encap_eth.encap_eth_dst, encap_eth_header->encap_eth_dst);
+
+ return;
+}
+
static __be16 parse_ethertype(struct sk_buff *skb)
{
struct llc_snap_hdr {
@@ -457,6 +484,24 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
int error;
struct ethhdr *eth;
+ /* Extract ethernet+nsh if ethernet type is 0x894F */
+ eth = (struct ethhdr *)skb->data;
+ if (eth->h_proto == htons(ETH_P_NSH)) {
+ parse_encap_eth(skb, key);
+ __skb_pull(skb, ENCAP_ETH_LEN);
+
+ if (unlikely(parse_nsh(skb, key)))
+ return -EINVAL;
+ if (key->nsh.nsh_mdtype == NSH_M_TYPE1 && key->nsh.nsh_np == NSH_P_ETHERNET) {
+ __skb_pull(skb, NSH_M_TYPE1_LEN);
+ } else {
+ return -EINVAL;
+ }
+ } else {
+ void *encap_eth_hdr = &(key->encap_eth);
+ memset(encap_eth_hdr, 0, ENCAP_ETH_LEN);
+ }
+
/* Flags are always used as part of stats */
key->tp.flags = 0;
@@ -676,11 +721,54 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
}
}
}
+
+ if (key->encap_eth.encap_eth_type == htons(ETH_P_NSH))
+ __skb_push(skb, ENCAP_ETH_LEN + NSH_M_TYPE1_LEN);
+
+ return 0;
+}
+
+static void ovs_key_nsh_init(struct sw_flow_key *key, __u16 len) {
+ void *nsh_hdr = &(key->nsh);
+ memset(nsh_hdr, 0, len);
+}
+
+static int nsh_extract(struct sk_buff *skb, struct sw_flow_key *key) {
+ int ret;
+
+ /* only support NSH MD tpye1 */
+ if (unlikely(parse_nsh(skb, key)))
+ return -EINVAL;
+ if (key->nsh.nsh_mdtype == NSH_M_TYPE1) {
+ __skb_pull(skb, NSH_M_TYPE1_LEN);
+ if(key->nsh.nsh_np == NSH_P_ETHERNET)
+ ret = key_extract(skb, key);
+ else
+ return -EINVAL;
+ __skb_push(skb, NSH_M_TYPE1_LEN);
+
+ return ret;
+ } else {
+ ovs_key_nsh_init(key, NSH_M_TYPE1_LEN);
+ }
+
return 0;
}
+static bool is_nsh_header(const void *tun_opts, __be16 tun_flags) {
+ struct vxlan_metadata *md = NULL;
+ if (tun_opts && (tun_flags & TUNNEL_VXLAN_OPT))
+ md = (struct vxlan_metadata *)tun_opts;
+
+ if (md && (md->gpe & VXLAN_GPE_NP_MASK) == VXLAN_GPE_NP_NSH)
+ return true;
+ else
+ return false;
+}
+
int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
{
+ ovs_key_nsh_init(key, NSH_M_TYPE1_LEN);
return key_extract(skb, key);
}
@@ -715,6 +803,15 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
key->ovs_flow_hash = 0;
key->recirc_id = 0;
+ /* Extract NSH and inner Ethernet if NSH header exists */
+ if (tun_info && is_nsh_header(ip_tunnel_info_opts(tun_info), key->tun_key.tun_flags)) {
+ int ret ;
+ ret = nsh_extract(skb, key);
+ if (key->nsh.nsh_mdtype)
+ return ret;
+ } else {
+ ovs_key_nsh_init(key, NSH_M_TYPE1_LEN);
+ }
return key_extract(skb, key);
}
@@ -729,5 +826,15 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
if (err)
return err;
+ /* Extract NSH and inner Ethernet if NSH header exists */
+ if (key && is_nsh_header(key->tun_opts, key->tun_key.tun_flags)) {
+ int ret ;
+ ret = nsh_extract(skb, key);
+ if (key->nsh.nsh_mdtype)
+ return ret;
+ } else {
+ ovs_key_nsh_init(key, NSH_M_TYPE1_LEN);
+ }
+
return key_extract(skb, key);
}
diff --git a/datapath/flow.h b/datapath/flow.h
index c0b628a..c8ccd5f 100644
--- a/datapath/flow.h
+++ b/datapath/flow.h
@@ -63,6 +63,21 @@ struct sw_flow_key {
u32 skb_mark; /* SKB mark. */
u16 in_port; /* Input switch port (or DP_MAX_PORTS). */
} __packed phy; /* Safe when right after 'tun_key'. */
+ struct {
+ u32 nshc1; /* NSH context C1-C4 */
+ u32 nshc2;
+ u32 nshc3;
+ u32 nshc4;
+ u32 nsp; /* NSH path id */
+ u8 nsi; /* NSH index */
+ u8 nsh_mdtype; /* NSH metadata type */
+ u8 nsh_np; /* NSH next protocol */
+ }__packed nsh; /* network service header */
+ struct {
+ u8 encap_eth_src[ETH_ALEN]; /* ENCAP ethernet source address. */
+ u8 encap_eth_dst[ETH_ALEN]; /* ENCAP ethernet destination address. */
+ u16 encap_eth_type; /* ENCAP ethernet type. */
+ } encap_eth;
u32 ovs_flow_hash; /* Datapath computed hash value. */
u32 recirc_id; /* Recirculation ID. */
struct {
diff --git a/datapath/flow_netlink.c b/datapath/flow_netlink.c
index 351a504..ebfae37 100644
--- a/datapath/flow_netlink.c
+++ b/datapath/flow_netlink.c
@@ -284,7 +284,7 @@ size_t ovs_key_attr_size(void)
/* Whenever adding new OVS_KEY_ FIELDS, we should consider
* updating this function.
*/
- BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 26);
+ BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 28);
return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
@@ -297,6 +297,8 @@ size_t ovs_key_attr_size(void)
+ nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */
+ nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */
+ nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */
+ + nla_total_size(24) /* OVS_KEY_ATTR_NSH */
+ + nla_total_size(14) /* OVS_KEY_ATTR_ENCAP_ETH */
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
+ nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ nla_total_size(4) /* OVS_KEY_ATTR_VLAN */
@@ -334,6 +336,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
[OVS_KEY_ATTR_PRIORITY] = { .len = sizeof(u32) },
[OVS_KEY_ATTR_IN_PORT] = { .len = sizeof(u32) },
[OVS_KEY_ATTR_SKB_MARK] = { .len = sizeof(u32) },
+ [OVS_KEY_ATTR_NSH] = { .len = sizeof(struct ovs_key_nsh) },
+ [OVS_KEY_ATTR_ENCAP_ETH] = { .len = sizeof(struct ovs_key_encap_eth) },
[OVS_KEY_ATTR_ETHERNET] = { .len = sizeof(struct ovs_key_ethernet) },
[OVS_KEY_ATTR_VLAN] = { .len = sizeof(__be16) },
[OVS_KEY_ATTR_ETHERTYPE] = { .len = sizeof(__be16) },
@@ -869,6 +873,42 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
if (err)
return err;
+ if (attrs & (1ULL << OVS_KEY_ATTR_NSH)) {
+ const struct ovs_key_nsh *nsh_key;
+
+ nsh_key = nla_data(a[OVS_KEY_ATTR_NSH]);
+ SW_FLOW_KEY_PUT(match, nsh.nshc1,
+ nsh_key->nshc1, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.nshc2,
+ nsh_key->nshc2, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.nshc3,
+ nsh_key->nshc3, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.nshc4,
+ nsh_key->nshc4, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.nsh_mdtype,
+ nsh_key->nsh_mdtype, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.nsh_np,
+ nsh_key->nsh_np, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.nsp,
+ nsh_key->nsp, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.nsi,
+ nsh_key->nsi, is_mask);
+ attrs &= ~(1ULL << OVS_KEY_ATTR_NSH);
+ }
+
+ if (attrs & (1ULL << OVS_KEY_ATTR_ENCAP_ETH)) {
+ const struct ovs_key_encap_eth *encap_eth_key;
+
+ encap_eth_key = nla_data(a[OVS_KEY_ATTR_ENCAP_ETH]);
+ SW_FLOW_KEY_MEMCPY(match, encap_eth.encap_eth_src,
+ encap_eth_key->encap_eth_src, ETH_ALEN, is_mask);
+ SW_FLOW_KEY_MEMCPY(match, encap_eth.encap_eth_dst,
+ encap_eth_key->encap_eth_dst, ETH_ALEN, is_mask);
+ SW_FLOW_KEY_PUT(match, encap_eth.encap_eth_type,
+ encap_eth_key->encap_eth_type, is_mask);
+ attrs &= ~(1ULL << OVS_KEY_ATTR_ENCAP_ETH);
+ }
+
if (attrs & (1ULL << OVS_KEY_ATTR_ETHERNET)) {
const struct ovs_key_ethernet *eth_key;
@@ -1386,6 +1426,35 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
goto nla_put_failure;
+ if ((swkey->nsh.nsh_mdtype || is_mask)) {
+ struct ovs_key_nsh *nsh_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_NSH, sizeof(*nsh_key));
+ if (!nla)
+ goto nla_put_failure;
+ nsh_key = nla_data(nla);
+ nsh_key->nsi = output->nsh.nsi;
+ nsh_key->nsp = output->nsh.nsp;
+ nsh_key->nsh_mdtype= output->nsh.nsh_mdtype;
+ nsh_key->nsh_np= output->nsh.nsh_np;
+ nsh_key->nshc1= output->nsh.nshc1;
+ nsh_key->nshc2 = output->nsh.nshc2;
+ nsh_key->nshc3 = output->nsh.nshc3;
+ nsh_key->nshc4 = output->nsh.nshc4;
+ }
+
+ if ((swkey->encap_eth.encap_eth_type || is_mask)) {
+ struct ovs_key_encap_eth *encap_eth_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ENCAP_ETH, sizeof(*encap_eth_key));
+ if (!nla)
+ goto nla_put_failure;
+ encap_eth_key = nla_data(nla);
+ memcpy(encap_eth_key->encap_eth_src, output->encap_eth.encap_eth_src, ETH_ALEN);
+ memcpy(encap_eth_key->encap_eth_dst, output->encap_eth.encap_eth_dst, ETH_ALEN);
+ encap_eth_key->encap_eth_type= output->encap_eth.encap_eth_type;
+ }
+
if ((swkey->tun_key.u.ipv4.dst || is_mask)) {
const void *opts = NULL;
@@ -2182,6 +2251,10 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
[OVS_ACTION_ATTR_POP_MPLS] = sizeof(__be16),
[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
[OVS_ACTION_ATTR_POP_VLAN] = 0,
+ [OVS_ACTION_ATTR_PUSH_NSH] = sizeof(struct ovs_action_push_nsh),
+ [OVS_ACTION_ATTR_POP_NSH] = 0,
+ [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth),
+ [OVS_ACTION_ATTR_POP_ETH] = 0,
[OVS_ACTION_ATTR_SET] = (u32)-1,
[OVS_ACTION_ATTR_SET_MASKED] = (u32)-1,
[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
@@ -2226,6 +2299,12 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
break;
}
+ case OVS_ACTION_ATTR_PUSH_NSH:
+ case OVS_ACTION_ATTR_POP_NSH:
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ case OVS_ACTION_ATTR_POP_ETH:
+ break;
+
case OVS_ACTION_ATTR_POP_VLAN:
vlan_tci = htons(0);
break;
diff --git a/datapath/linux/compat/include/linux/openvswitch.h b/datapath/linux/compat/include/linux/openvswitch.h
index 44adb81..187bb9b 100644
--- a/datapath/linux/compat/include/linux/openvswitch.h
+++ b/datapath/linux/compat/include/linux/openvswitch.h
@@ -42,6 +42,7 @@
#include <linux/types.h>
#include <linux/if_ether.h>
+#include <asm/byteorder.h>
/**
* struct ovs_header - header for OVS Generic Netlink messages.
@@ -328,6 +329,9 @@ enum ovs_key_attr {
OVS_KEY_ATTR_ENCAP, /* Nested set of encapsulated attributes. */
OVS_KEY_ATTR_PRIORITY, /* u32 skb->priority */
OVS_KEY_ATTR_IN_PORT, /* u32 OVS dp port number */
+ OVS_KEY_ATTR_NSH, /* struct ovs_key_nsh. Only support NSH MD
+ type 1 now */
+ OVS_KEY_ATTR_ENCAP_ETH, /* struct ovs_key_encap_eth */
OVS_KEY_ATTR_ETHERNET, /* struct ovs_key_ethernet */
OVS_KEY_ATTR_VLAN, /* be16 VLAN TCI */
OVS_KEY_ATTR_ETHERTYPE, /* be16 Ethernet type */
@@ -401,6 +405,24 @@ enum ovs_frag_type {
#define OVS_FRAG_TYPE_MAX (__OVS_FRAG_TYPE_MAX - 1)
+struct ovs_key_nsh {
+ __u32 nshc1;
+ __u32 nshc2;
+ __u32 nshc3;
+ __u32 nshc4;
+ __u32 nsp;
+ __u8 nsi;
+ __u8 nsh_mdtype;
+ __u8 nsh_np;
+ __u8 reserved;
+};
+
+struct ovs_key_encap_eth {
+ __u8 encap_eth_src[ETH_ALEN];
+ __u8 encap_eth_dst[ETH_ALEN];
+ __u16 encap_eth_type;
+};
+
struct ovs_key_ethernet {
__u8 eth_src[ETH_ALEN];
__u8 eth_dst[ETH_ALEN];
@@ -630,6 +652,154 @@ struct ovs_action_push_vlan {
__be16 vlan_tci; /* 802.1Q TCI (VLAN ID and priority). */
};
+/*
+ * Network Service Header:
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |Ver|O|C|R|R|R|R|R|R| Length | MD Type | Next Proto |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Service Path ID | Service Index |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * Ver = The version field is used to ensure backward compatibility
+ * going forward with future NSH updates. It MUST be set to 0x0
+ * by the sender, in this first revision of NSH.
+ *
+ * O = OAM. when set to 0x1 indicates that this packet is an operations
+ * and management (OAM) packet. The receiving SFF and SFs nodes
+ * MUST examine the payload and take appropriate action.
+ *
+ * C = context. Indicates that a critical metadata TLV is present.
+ *
+ * Length : total length, in 4-byte words, of NSH including the Base
+ * Header, the Service Path Header and the optional variable
+ * TLVs.
+ * MD Type: indicates the format of NSH beyond the mandatory Base Header
+ * and the Service Path Header.
+ *
+ * Next Protocol: indicates the protocol type of the original packet. A
+ * new IANA registry will be created for protocol type.
+ *
+ * Service Path Identifier (SPI): identifies a service path.
+ * Participating nodes MUST use this identifier for Service
+ * Function Path selection.
+ *
+ * Service Index (SI): provides location within the SFP.
+ *
+ * [0] https://tools.ietf.org/html/draft-ietf-sfc-nsh-01
+ */
+
+struct nsh_base {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+
+ __u8 reserved_flags1:4;
+ __u8 context_flag:1;
+ __u8 oam_flag:1;
+ __u8 version:2;
+
+ __u8 length:6;
+ __u8 reserved_flags2:2;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+
+ __u8 version:2;
+ __u8 oam_flag:1;
+ __u8 context_flag:1;
+ __u8 reserved_flags1:4;
+
+ __u8 reserved_flags2:2;
+ __u8 length:6;
+#else
+#error "Bitfield Endianess not defined."
+#endif
+ __u8 mdtype;
+ __u8 proto;
+ union {
+ struct {
+ __u8 svc_path[3];
+ __u8 svc_idx;
+ };
+ __be32 path_hdr;
+ };
+};
+
+
+/**
+ * struct nsh_ctx - Keeps track of NSH context data
+ * @c<1-4>: NSH Contexts.
+ */
+struct nsh_ctx {
+ __be32 nshc1;
+ __be32 nshc2;
+ __be32 nshc3;
+ __be32 nshc4;
+};
+
+/**
+ * struct nshdr - Network Service header
+ * @nsh_base: Network Service Base Header.
+ * @nsh_ctx: Network Service Context Header.
+ */
+struct nsh_hdr {
+ struct nsh_base base;
+ struct nsh_ctx ctx;
+};
+
+
+#define ETH_P_NSH 0x894F /* Ethertype for NSH */
+
+/* NSH Base Header Next Protocol */
+#define NSH_P_IPV4 0x01
+#define NSH_P_IPV6 0x02
+#define NSH_P_ETHERNET 0x03
+
+/* MD Type Registry */
+#define NSH_M_TYPE1 0x01
+#define NSH_M_EXP1 0xFE
+#define NSH_M_EXP2 0xFF
+
+#define NSH_DST_PORT 4790 /* UDP Port for NSH on VXLAN */
+
+#define NSH_M_TYPE1_LEN 24
+
+/* Used for masking nsp and nsi values in field nsp below */
+#define NSH_M_NSP 0x00FFFFFF
+#define NSH_M_NSI 0xFF000000
+
+/* NSH header for MD type 1. Unit is bytes */
+#define NSH_PUSH_TYPE1_HEADER_SIZE 24
+#define NSH_PUSH_HEADER_SIZE 256
+
+#define ENCAP_ETH_LEN 14
+
+/**
+ * struct encap_eth - encap ethernet header for ethernet NSH
+ * @encap_eth_src: encap ethernet source address.
+ * @encap_eth_src: encap ethernet destination address.
+ * @encap_eth_type: encap ethernet type.
+ */
+struct encap_eth_hdr {
+ __u8 encap_eth_dst[ETH_ALEN];
+ __u8 encap_eth_src[ETH_ALEN];
+ __u16 encap_eth_type;
+};
+
+#define ENCAP_ETH_PUSH_HEADER_SIZE 14
+/**
+ * struct ovs_action_push_nsh - %OVS_ACTION_ATTR_PUSH_NSH action argument.
+ * @header
+ */
+struct ovs_action_push_nsh {
+ uint8_t nsh_mdtype;
+ uint8_t header[NSH_PUSH_HEADER_SIZE];
+};
+
+/**
+ * struct ovs_action_push_nsh - %OVS_ACTION_ATTR_PUSH_NSH action argument.
+ * @header
+ */
+struct ovs_action_push_eth {
+ uint16_t encap_eth_type;
+ uint8_t header[ENCAP_ETH_PUSH_HEADER_SIZE];
+};
+
/* Data path hash algorithm for computing Datapath hash.
*
* The algorithm type only specifies the fields in a flow
@@ -793,6 +963,10 @@ enum ovs_action_attr {
OVS_ACTION_ATTR_SET, /* One nested OVS_KEY_ATTR_*. */
OVS_ACTION_ATTR_PUSH_VLAN, /* struct ovs_action_push_vlan. */
OVS_ACTION_ATTR_POP_VLAN, /* No argument. */
+ OVS_ACTION_ATTR_PUSH_NSH, /* struct ovs_action_push_nsh. */
+ OVS_ACTION_ATTR_POP_NSH, /* No argument. */
+ OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */
+ OVS_ACTION_ATTR_POP_ETH, /* No argument. */
OVS_ACTION_ATTR_SAMPLE, /* Nested OVS_SAMPLE_ATTR_*. */
OVS_ACTION_ATTR_RECIRC, /* u32 recirc_id. */
OVS_ACTION_ATTR_HASH, /* struct ovs_action_hash. */
diff --git a/datapath/linux/compat/include/net/vxlan.h b/datapath/linux/compat/include/net/vxlan.h
index 2bfc3f8..3aeac88 100644
--- a/datapath/linux/compat/include/net/vxlan.h
+++ b/datapath/linux/compat/include/net/vxlan.h
@@ -85,7 +85,7 @@ struct vxlanhdr_gbp {
#define VXLAN_GBP_ID_MASK (0xFFFF)
/*
- * VXLAN Generic Protocol Extension Extension:
+ * VXLAN Generic Protocol Extension:
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |R|R|Ver|I|P|R|O|R|R|R|R|R|R|R|R|R|R|R|R|R|R|R|R| Next Proto |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -103,6 +103,9 @@ struct vxlanhdr_gbp {
* O = OAM Flag Bit. The O bit is set to indicate that the packet
* is an OAM packet.
*
+ * Next Protocol = This 8 bit field indicates the protocol header
+ * immediately following the VXLAN GPE header.
+ *
* [1] https://www.ietf.org/id/draft-ietf-nvo3-vxlan-gpe-01.txt
*/
diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
index 119dc2d..8e67bfd 100644
--- a/lib/dpif-netdev.c
+++ b/lib/dpif-netdev.c
@@ -3874,6 +3874,10 @@ dp_execute_cb(void *aux_, struct dp_packet **packets, int cnt,
VLOG_WARN("Cannot execute conntrack action in userspace.");
break;
+ case OVS_ACTION_ATTR_PUSH_NSH:
+ case OVS_ACTION_ATTR_POP_NSH:
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ case OVS_ACTION_ATTR_POP_ETH:
case OVS_ACTION_ATTR_PUSH_VLAN:
case OVS_ACTION_ATTR_POP_VLAN:
case OVS_ACTION_ATTR_PUSH_MPLS:
diff --git a/lib/dpif.c b/lib/dpif.c
index a784de7..b5265c4 100644
--- a/lib/dpif.c
+++ b/lib/dpif.c
@@ -1139,6 +1139,10 @@ dpif_execute_helper_cb(void *aux_, struct dp_packet **packets, int cnt,
}
case OVS_ACTION_ATTR_HASH:
+ case OVS_ACTION_ATTR_PUSH_NSH:
+ case OVS_ACTION_ATTR_POP_NSH:
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ case OVS_ACTION_ATTR_POP_ETH:
case OVS_ACTION_ATTR_PUSH_VLAN:
case OVS_ACTION_ATTR_POP_VLAN:
case OVS_ACTION_ATTR_PUSH_MPLS:
diff --git a/lib/flow.c b/lib/flow.c
index d24bdc9..fc8b98c 100644
--- a/lib/flow.c
+++ b/lib/flow.c
@@ -1289,6 +1289,25 @@ void flow_wildcards_init_for_packet(struct flow_wildcards *wc,
WC_MASK_FIELD(wc, tunnel.tun_id);
}
+ /* NSH fields wildcarded */
+ if (flow->nsh_mdtype) {
+ WC_MASK_FIELD(wc, nshc1);
+ WC_MASK_FIELD(wc, nshc2);
+ WC_MASK_FIELD(wc, nshc3);
+ WC_MASK_FIELD(wc, nshc4);
+ WC_MASK_FIELD(wc, nsh_mdtype);
+ WC_MASK_FIELD(wc, nsh_np);
+ WC_MASK_FIELD(wc, nsp);
+ WC_MASK_FIELD(wc, nsi);
+ }
+
+ /* ENCAP Eth wildcarded */
+ if (flow->encap_eth_type) {
+ WC_MASK_FIELD(wc, encap_eth_src);
+ WC_MASK_FIELD(wc, encap_eth_dst);
+ WC_MASK_FIELD(wc, encap_eth_type);
+ }
+
/* metadata, regs, and conj_id wildcarded. */
WC_MASK_FIELD(wc, skb_priority);
diff --git a/lib/flow.h b/lib/flow.h
index dc7130d..a8677b1 100644
--- a/lib/flow.h
+++ b/lib/flow.h
@@ -111,6 +111,23 @@ struct flow {
ofp_port_t actset_output; /* Output port in action set. */
uint8_t pad2[2]; /* Pad to 64 bits. */
+ /* NSH (64-bit aligned) */
+ ovs_be32 nshc1;
+ ovs_be32 nshc2;
+ ovs_be32 nshc3;
+ ovs_be32 nshc4;
+ ovs_be32 nsp;
+ uint8_t nsi;
+ uint8_t nsh_mdtype;
+ uint8_t nsh_np;
+ uint8_t pad3;
+
+ /* ENCAP_ETH (64-bit aligned) */
+ struct eth_addr encap_eth_src; /* Encap ethernet source address. */
+ struct eth_addr encap_eth_dst; /* Encap ethernet destination address. */
+ ovs_be16 encap_eth_type; /* Encap ethernet frame type. */
+ uint8_t pad4[2];
+
/* L2, Order the same as in the Ethernet header! (64-bit aligned) */
struct eth_addr dl_dst; /* Ethernet destination address. */
struct eth_addr dl_src; /* Ethernet source address. */
@@ -132,7 +149,7 @@ struct flow {
struct eth_addr arp_sha; /* ARP/ND source hardware address. */
struct eth_addr arp_tha; /* ARP/ND target hardware address. */
ovs_be16 tcp_flags; /* TCP flags. With L3 to avoid matching L4. */
- ovs_be16 pad3; /* Pad to 64 bits. */
+ ovs_be16 pad5; /* Pad to 64 bits. */
/* L4 (64-bit aligned) */
ovs_be16 tp_src; /* TCP/UDP/SCTP source port/ICMP type. */
@@ -158,7 +175,7 @@ BUILD_ASSERT_DECL(sizeof(struct flow_tnl) % sizeof(uint64_t) == 0);
/* Remember to update FLOW_WC_SEQ when changing 'struct flow'. */
BUILD_ASSERT_DECL(offsetof(struct flow, igmp_group_ip4) + sizeof(uint32_t)
- == sizeof(struct flow_tnl) + 216
+ == sizeof(struct flow_tnl) + 256
&& FLOW_WC_SEQ == 35);
/* Incremental points at which flow classification may be performed in
diff --git a/lib/match.c b/lib/match.c
index 52437c9..3db2a2b 100644
--- a/lib/match.c
+++ b/lib/match.c
@@ -862,6 +862,152 @@ match_set_nd_target_masked(struct match *match,
match->wc.masks.nd_target = *mask;
}
+void
+match_set_nsp_masked(struct match *match, ovs_be32 nsp, ovs_be32 mask)
+{
+ match->wc.masks.nsp = mask;
+ match->flow.nsp = nsp & mask;
+}
+
+void
+match_set_nsi_masked(struct match *match, uint8_t nsi, uint8_t mask)
+{
+ match->wc.masks.nsi = mask;
+ match->flow.nsi = nsi & mask;
+}
+
+void
+match_set_nsh_mdtype_masked(struct match *match, uint8_t nsh_mdtype, uint8_t mask)
+{
+ match->wc.masks.nsh_mdtype = mask;
+ match->flow.nsh_mdtype = nsh_mdtype & mask;
+}
+
+void
+match_set_nsh_np_masked(struct match *match, uint8_t nsh_np, uint8_t mask)
+{
+ match->wc.masks.nsh_np = mask;
+ match->flow.nsh_np = nsh_np & mask;
+}
+
+void
+match_set_encap_eth_src_masked(struct match *match,
+ const struct eth_addr encap_eth_src,
+ const struct eth_addr mask)
+{
+ set_eth_masked(encap_eth_src, mask, &match->flow.encap_eth_src, &match->wc.masks.encap_eth_src);
+}
+
+void
+match_set_encap_eth_dst_masked(struct match *match,
+ const struct eth_addr encap_eth_dst,
+ const struct eth_addr mask)
+{
+ set_eth_masked(encap_eth_dst, mask, &match->flow.encap_eth_dst, &match->wc.masks.encap_eth_dst);
+}
+
+void
+match_set_encap_eth_type_masked(struct match *match, ovs_be16 encap_eth_type, ovs_be16 mask)
+{
+ match->wc.masks.encap_eth_type = mask;
+ match->flow.encap_eth_type = encap_eth_type & mask;
+}
+
+void
+match_set_nshc1_masked(struct match *match, ovs_be32 nshc1, ovs_be32 mask)
+{
+ match->wc.masks.nshc1 = mask;
+ match->flow.nshc1 = nshc1 & mask;
+}
+
+void
+match_set_nshc2_masked(struct match *match, ovs_be32 nshc2, ovs_be32 mask)
+{
+ match->wc.masks.nshc2 = mask;
+ match->flow.nshc2 = nshc2 & mask;
+}
+
+void
+match_set_nshc3_masked(struct match *match, ovs_be32 nshc3, ovs_be32 mask)
+{
+ match->wc.masks.nshc3 = mask;
+ match->flow.nshc3 = nshc3 & mask;
+}
+
+void
+match_set_nshc4_masked(struct match *match, ovs_be32 nshc4, ovs_be32 mask)
+{
+ match->wc.masks.nshc4 = mask;
+ match->flow.nshc4 = nshc4 & mask;
+}
+
+void
+match_set_nsp(struct match *match, ovs_be32 nsp)
+{
+ match_set_nsp_masked(match, nsp, OVS_BE32_MAX);
+}
+
+void
+match_set_nsi(struct match *match, uint8_t nsi)
+{
+ match_set_nsi_masked(match, nsi, UINT8_MAX);
+}
+
+void
+match_set_nsh_mdtype(struct match *match, uint8_t nsh_mdtype)
+{
+ match_set_nsh_mdtype_masked(match, nsh_mdtype, UINT8_MAX);
+}
+
+void
+match_set_nsh_np(struct match *match, uint8_t nsh_np)
+{
+ match_set_nsh_np_masked(match, nsh_np, UINT8_MAX);
+}
+
+void
+match_set_nshc1(struct match *match, ovs_be32 nshc1)
+{
+ match_set_nshc1_masked(match, nshc1, OVS_BE32_MAX);
+}
+
+void
+match_set_nshc2(struct match *match, ovs_be32 nshc2)
+{
+ match_set_nshc2_masked(match, nshc2, OVS_BE32_MAX);
+}
+
+void
+match_set_nshc3(struct match *match, ovs_be32 nshc3)
+{
+ match_set_nshc3_masked(match, nshc3, OVS_BE32_MAX);
+}
+
+void
+match_set_nshc4(struct match *match, ovs_be32 nshc4)
+{
+ match_set_nshc4_masked(match, nshc4, OVS_BE32_MAX);
+}
+
+void
+match_set_encap_eth_src(struct match *match, const struct eth_addr encap_eth_src)
+{
+ set_eth(encap_eth_src, &match->flow.encap_eth_src, &match->wc.masks.encap_eth_src);
+}
+
+void
+match_set_encap_eth_dst(struct match *match, const struct eth_addr encap_eth_dst)
+{
+ set_eth(encap_eth_dst, &match->flow.encap_eth_dst, &match->wc.masks.encap_eth_dst);
+}
+
+void
+match_set_encap_eth_type(struct match *match, uint16_t encap_eth_type)
+{
+ match_set_encap_eth_type_masked(match, encap_eth_type, UINT16_MAX);
+}
+
+
/* Returns true if 'a' and 'b' wildcard the same fields and have the same
* values for fixed fields, otherwise false. */
bool
@@ -1155,6 +1301,50 @@ match_format(const struct match *match, struct ds *s, int priority)
format_ct_label_masked(s, &f->ct_label, &wc->masks.ct_label);
}
+ if (wc->masks.nsi) {
+ ds_put_format(s, "nsi=%"PRIu8",", f->nsi);
+ }
+
+ if (wc->masks.nsh_mdtype) {
+ ds_put_format(s, "nsh_mdtype=%"PRIu8",", f->nsh_mdtype);
+ }
+
+ if (wc->masks.nsh_np) {
+ ds_put_format(s, "nsh_np=%"PRIu8",", f->nsh_np);
+ }
+
+ if (wc->masks.nsp) {
+ format_be32_masked(s, "nsp", f->nsp,
+ wc->masks.nsp);
+ }
+
+ if (wc->masks.nshc1) {
+ format_be32_masked(s, "nshc1", f->nshc1,
+ wc->masks.nshc1);
+ }
+
+ if (wc->masks.nshc2) {
+ format_be32_masked(s, "nshc2", f->nshc2,
+ wc->masks.nshc2);
+ }
+
+ if (wc->masks.nshc3) {
+ format_be32_masked(s, "nshc3", f->nshc3,
+ wc->masks.nshc3);
+ }
+
+ if (wc->masks.nshc4) {
+ format_be32_masked(s, "nshc4", f->nshc4,
+ wc->masks.nshc4);
+ }