-
Notifications
You must be signed in to change notification settings - Fork 558
/
Copy pathroutesync.cpp
1510 lines (1301 loc) · 45 KB
/
routesync.cpp
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
#include <netlink/route/link.h>
#include <netlink/route/route.h>
#include <netlink/route/nexthop.h>
#include "logger.h"
#include "select.h"
#include "netmsg.h"
#include "ipprefix.h"
#include "dbconnector.h"
#include "producerstatetable.h"
#include "fpmsyncd/fpmlink.h"
#include "fpmsyncd/routesync.h"
#include "macaddress.h"
#include "converter.h"
#include <string.h>
#include <arpa/inet.h>
using namespace std;
using namespace swss;
#define VXLAN_IF_NAME_PREFIX "Brvxlan"
#define VNET_PREFIX "Vnet"
#define VRF_PREFIX "Vrf"
#define MGMT_VRF_PREFIX "mgmt"
#define NHG_DELIMITER ','
#ifndef ETH_ALEN
#define ETH_ALEN 6
#endif
#ifndef NDA_RTA
#define NDA_RTA(r) \
((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct ndmsg))))
#endif
#define VXLAN_VNI 0
#define VXLAN_RMAC 1
#define NH_ENCAP_VXLAN 100
#define IPV4_MAX_BYTE 4
#define IPV6_MAX_BYTE 16
#define IPV4_MAX_BITLEN 32
#define IPV6_MAX_BITLEN 128
#define ETHER_ADDR_STRLEN (3*ETH_ALEN)
/* Returns name of the protocol passed number represents */
static string getProtocolString(int proto)
{
static constexpr size_t protocolNameBufferSize = 128;
char buffer[protocolNameBufferSize] = {};
if (!rtnl_route_proto2str(proto, buffer, sizeof(buffer)))
{
return std::to_string(proto);
}
return buffer;
}
/* Helper to create unique pointer with custom destructor */
template<typename T, typename F>
static decltype(auto) makeUniqueWithDestructor(T* ptr, F func)
{
return std::unique_ptr<T, F>(ptr, func);
}
template<typename T>
static decltype(auto) makeNlAddr(const T& ip)
{
nl_addr* addr;
nl_addr_parse(ip.to_string().c_str(), AF_UNSPEC, &addr);
return makeUniqueWithDestructor(addr, nl_addr_put);
}
RouteSync::RouteSync(RedisPipeline *pipeline) :
m_routeTable(pipeline, APP_ROUTE_TABLE_NAME, true),
m_label_routeTable(pipeline, APP_LABEL_ROUTE_TABLE_NAME, true),
m_vnet_routeTable(pipeline, APP_VNET_RT_TABLE_NAME, true),
m_vnet_tunnelTable(pipeline, APP_VNET_RT_TUNNEL_TABLE_NAME, true),
m_warmStartHelper(pipeline, &m_routeTable, APP_ROUTE_TABLE_NAME, "bgp", "bgp"),
m_nl_sock(NULL), m_link_cache(NULL)
{
m_nl_sock = nl_socket_alloc();
nl_connect(m_nl_sock, NETLINK_ROUTE);
rtnl_link_alloc_cache(m_nl_sock, AF_UNSPEC, &m_link_cache);
}
char *RouteSync::prefixMac2Str(char *mac, char *buf, int size)
{
char *ptr = buf;
if (!mac)
{
return NULL;
}
if (!buf)
{
return NULL;
}
snprintf(ptr, (ETHER_ADDR_STRLEN), "%02x:%02x:%02x:%02x:%02x:%02x",
(uint8_t)mac[0], (uint8_t)mac[1],
(uint8_t)mac[2], (uint8_t)mac[3],
(uint8_t)mac[4], (uint8_t)mac[5]);
return ptr;
}
/**
* parseRtAttrNested() - Parses a nested route attribute
* @tb: Pointer to array for storing rtattr in.
* @max: Max number to store.
* @rta: Pointer to rtattr to look for nested items in.
*/
void RouteSync::parseRtAttrNested(struct rtattr **tb, int max,
struct rtattr *rta)
{
netlink_parse_rtattr(tb, max, (struct rtattr *)RTA_DATA(rta), (int)RTA_PAYLOAD(rta));
}
/**
* @parseEncap() - Parses encapsulated attributes
* @tb: Pointer to rtattr to look for nested items in.
* @labels: Pointer to store vni in.
*
* Return: void.
*/
void RouteSync::parseEncap(struct rtattr *tb, uint32_t &encap_value, string &rmac)
{
struct rtattr *tb_encap[3] = {0};
char mac_buf[MAX_ADDR_SIZE+1];
char mac_val[MAX_ADDR_SIZE+1];
parseRtAttrNested(tb_encap, 3, tb);
encap_value = *(uint32_t *)RTA_DATA(tb_encap[VXLAN_VNI]);
memcpy(&mac_buf, RTA_DATA(tb_encap[VXLAN_RMAC]), MAX_ADDR_SIZE);
SWSS_LOG_INFO("Rx MAC %s VNI %d",
prefixMac2Str(mac_buf, mac_val, ETHER_ADDR_STRLEN), encap_value);
rmac = mac_val;
return;
}
void RouteSync::getEvpnNextHopSep(string& nexthops, string& vni_list,
string& mac_list, string& intf_list)
{
nexthops += NHG_DELIMITER;
vni_list += NHG_DELIMITER;
mac_list += NHG_DELIMITER;
intf_list += NHG_DELIMITER;
return;
}
void RouteSync::getEvpnNextHopGwIf(char *gwaddr, int vni_value,
string& nexthops, string& vni_list,
string& mac_list, string& intf_list,
string rmac, string vlan_id)
{
nexthops+= gwaddr;
vni_list+= to_string(vni_value);
mac_list+=rmac;
intf_list+=vlan_id;
}
bool RouteSync::getEvpnNextHop(struct nlmsghdr *h, int received_bytes,
struct rtattr *tb[], string& nexthops,
string& vni_list, string& mac_list,
string& intf_list)
{
void *gate = NULL;
char nexthopaddr[MAX_ADDR_SIZE] = {0};
char gateaddr[MAX_ADDR_SIZE] = {0};
uint32_t encap_value = 0;
uint32_t ecmp_count = 0;
uint16_t encap = 0;
int gw_af;
struct in6_addr ipv6_address;
string rmac;
string vlan;
int index;
char if_name[IFNAMSIZ] = "0";
char ifname_unknown[IFNAMSIZ] = "unknown";
if (tb[RTA_GATEWAY])
gate = RTA_DATA(tb[RTA_GATEWAY]);
if (h->nlmsg_type == RTM_NEWROUTE)
{
if (!tb[RTA_MULTIPATH])
{
gw_af = AF_INET; // default value
if (gate)
{
if (RTA_PAYLOAD(tb[RTA_GATEWAY]) <= IPV4_MAX_BYTE)
{
memcpy(gateaddr, gate, IPV4_MAX_BYTE);
gw_af = AF_INET;
}
else
{
memcpy(ipv6_address.s6_addr, gate, IPV6_MAX_BYTE);
gw_af = AF_INET6;
}
}
if(gw_af == AF_INET6)
{
if (IN6_IS_ADDR_V4MAPPED(&ipv6_address))
{
memcpy(gateaddr, (ipv6_address.s6_addr+12), IPV4_MAX_BYTE);
gw_af = AF_INET;
}
else
{
SWSS_LOG_NOTICE("IPv6 tunnel nexthop not supported Nexthop:%s encap:%d encap_value:%d",
inet_ntop(gw_af, ipv6_address.s6_addr, nexthopaddr, MAX_ADDR_SIZE), encap, encap_value);
return false;
}
}
inet_ntop(gw_af, gateaddr, nexthopaddr, MAX_ADDR_SIZE);
if (tb[RTA_OIF])
{
index = *(int *)RTA_DATA(tb[RTA_OIF]);
/* If we cannot get the interface name */
if (!getIfName(index, if_name, IFNAMSIZ))
{
strcpy(if_name, ifname_unknown);
}
vlan = if_name;
}
if (tb[RTA_ENCAP_TYPE])
{
encap = *(uint16_t *)RTA_DATA(tb[RTA_ENCAP_TYPE]);
}
if (tb[RTA_ENCAP] && tb[RTA_ENCAP_TYPE]
&& (*(uint16_t *)RTA_DATA(tb[RTA_ENCAP_TYPE]) == NH_ENCAP_VXLAN))
{
parseEncap(tb[RTA_ENCAP], encap_value, rmac);
}
SWSS_LOG_DEBUG("Rx MsgType:%d Nexthop:%s encap:%d encap_value:%d rmac:%s vlan:%s", h->nlmsg_type,
nexthopaddr, encap, encap_value, rmac.c_str(), vlan.c_str());
if (encap_value == 0 || !(vlan.compare(ifname_unknown)) || MacAddress(rmac) == MacAddress("00:00:00:00:00:00"))
{
return false;
}
getEvpnNextHopGwIf(nexthopaddr, encap_value, nexthops, vni_list, mac_list, intf_list, rmac, vlan);
}
else
{
/* This is a multipath route */
/* Need to add the code for multipath */
int len;
struct rtattr *subtb[RTA_MAX + 1];
struct rtnexthop *rtnh = (struct rtnexthop *)RTA_DATA(tb[RTA_MULTIPATH]);
len = (int)RTA_PAYLOAD(tb[RTA_MULTIPATH]);
for (;;)
{
uint16_t encap = 0;
if (len < (int)sizeof(*rtnh) || rtnh->rtnh_len > len)
{
break;
}
gate = 0;
if (rtnh->rtnh_len > sizeof(*rtnh))
{
memset(subtb, 0, sizeof(subtb));
netlink_parse_rtattr(subtb, RTA_MAX, RTNH_DATA(rtnh),
(int)(rtnh->rtnh_len - sizeof(*rtnh)));
if (subtb[RTA_GATEWAY])
{
gate = RTA_DATA(subtb[RTA_GATEWAY]);
}
if (gate)
{
if (RTA_PAYLOAD(subtb[RTA_GATEWAY]) <= IPV4_MAX_BYTE)
{
memcpy(gateaddr, gate, IPV4_MAX_BYTE);
gw_af = AF_INET;
}
else
{
memcpy(ipv6_address.s6_addr, gate, IPV6_MAX_BYTE);
gw_af = AF_INET6;
}
}
if(gw_af == AF_INET6)
{
if (IN6_IS_ADDR_V4MAPPED(&ipv6_address))
{
memcpy(gateaddr, (ipv6_address.s6_addr+12), IPV4_MAX_BYTE);
gw_af = AF_INET;
}
else
{
SWSS_LOG_NOTICE("IPv6 tunnel nexthop not supported Nexthop:%s encap:%d encap_value:%d",
inet_ntop(gw_af, ipv6_address.s6_addr, nexthopaddr, MAX_ADDR_SIZE), encap, encap_value);
return false;
}
}
inet_ntop(gw_af, gateaddr, nexthopaddr, MAX_ADDR_SIZE);
if (rtnh->rtnh_ifindex)
{
index = rtnh->rtnh_ifindex;
/* If we cannot get the interface name */
if (!getIfName(index, if_name, IFNAMSIZ))
{
strcpy(if_name, ifname_unknown);
}
vlan = if_name;
}
if (subtb[RTA_ENCAP_TYPE])
{
encap = *(uint16_t *)RTA_DATA(subtb[RTA_ENCAP_TYPE]);
}
if (subtb[RTA_ENCAP] && subtb[RTA_ENCAP_TYPE]
&& (*(uint16_t *)RTA_DATA(subtb[RTA_ENCAP_TYPE]) == NH_ENCAP_VXLAN))
{
parseEncap(subtb[RTA_ENCAP], encap_value, rmac);
}
SWSS_LOG_DEBUG("Multipath Nexthop:%s encap:%d encap_value:%d rmac:%s vlan:%s",
nexthopaddr, encap, encap_value, rmac.c_str(), vlan.c_str());
if (encap_value == 0 || !(vlan.compare(ifname_unknown)) || MacAddress(rmac) == MacAddress("00:00:00:00:00:00"))
{
return false;
}
if (gate)
{
if (ecmp_count)
{
getEvpnNextHopSep(nexthops, vni_list, mac_list, intf_list);
}
getEvpnNextHopGwIf(nexthopaddr, encap_value, nexthops, vni_list, mac_list, intf_list, rmac, vlan);
ecmp_count++;
}
}
if (rtnh->rtnh_len == 0)
{
break;
}
len -= NLMSG_ALIGN(rtnh->rtnh_len);
rtnh = RTNH_NEXT(rtnh);
}
}
}
return true;
}
void RouteSync::onEvpnRouteMsg(struct nlmsghdr *h, int len)
{
struct rtmsg *rtm;
struct rtattr *tb[RTA_MAX + 1] = {0};
void *dest = NULL;
char anyaddr[16] = {0};
char dstaddr[16] = {0};
int dst_len = 0;
char buf[MAX_ADDR_SIZE];
char destipprefix[IFNAMSIZ + MAX_ADDR_SIZE + 2] = {0};
int nlmsg_type = h->nlmsg_type;
unsigned int vrf_index;
rtm = (struct rtmsg *)NLMSG_DATA(h);
/* Parse attributes and extract fields of interest. */
netlink_parse_rtattr(tb, RTA_MAX, RTM_RTA(rtm), len);
if (tb[RTA_DST])
{
dest = RTA_DATA(tb[RTA_DST]);
}
else
{
dest = anyaddr;
}
if (rtm->rtm_family == AF_INET)
{
if (rtm->rtm_dst_len > IPV4_MAX_BITLEN)
{
return;
}
memcpy(dstaddr, dest, IPV4_MAX_BYTE);
dst_len = rtm->rtm_dst_len;
}
else if (rtm->rtm_family == AF_INET6)
{
if (rtm->rtm_dst_len > IPV6_MAX_BITLEN)
{
return;
}
memcpy(dstaddr, dest, IPV6_MAX_BYTE);
dst_len = rtm->rtm_dst_len;
}
SWSS_LOG_DEBUG("Rx MsgType:%d Family:%d Prefix:%s/%d", h->nlmsg_type, rtm->rtm_family,
inet_ntop(rtm->rtm_family, dstaddr, buf, MAX_ADDR_SIZE), dst_len);
/* Table corresponding to route. */
if (tb[RTA_TABLE])
{
vrf_index = *(int *)RTA_DATA(tb[RTA_TABLE]);
}
else
{
vrf_index = rtm->rtm_table;
}
if (vrf_index)
{
if (!getIfName(vrf_index, destipprefix, IFNAMSIZ))
{
SWSS_LOG_ERROR("Fail to get the VRF name (ifindex %u)", vrf_index);
return;
}
/*
* Now vrf device name is required to start with VRF_PREFIX,
* it is difficult to split vrf_name:ipv6_addr.
*/
if (memcmp(destipprefix, VRF_PREFIX, strlen(VRF_PREFIX)))
{
SWSS_LOG_ERROR("Invalid VRF name %s (ifindex %u)", destipprefix, vrf_index);
return;
}
destipprefix[strlen(destipprefix)] = ':';
}
if((rtm->rtm_family == AF_INET && dst_len == IPV4_MAX_BITLEN)
|| (rtm->rtm_family == AF_INET6 && dst_len == IPV6_MAX_BITLEN))
{
snprintf(destipprefix + strlen(destipprefix), sizeof(destipprefix) - strlen(destipprefix), "%s",
inet_ntop(rtm->rtm_family, dstaddr, buf, MAX_ADDR_SIZE));
}
else
{
snprintf(destipprefix + strlen(destipprefix), sizeof(destipprefix) - strlen(destipprefix), "%s/%u",
inet_ntop(rtm->rtm_family, dstaddr, buf, MAX_ADDR_SIZE), dst_len);
}
SWSS_LOG_INFO("Receive route message dest ip prefix: %s Op:%s",
destipprefix,
nlmsg_type == RTM_NEWROUTE ? "add":"del");
/*
* Upon arrival of a delete msg we could either push the change right away,
* or we could opt to defer it if we are going through a warm-reboot cycle.
*/
bool warmRestartInProgress = m_warmStartHelper.inProgress();
if (nlmsg_type == RTM_DELROUTE)
{
if (!warmRestartInProgress)
{
m_routeTable.del(destipprefix);
return;
}
else
{
SWSS_LOG_INFO("Warm-Restart mode: Receiving delete msg: %s",
destipprefix);
vector<FieldValueTuple> fvVector;
const KeyOpFieldsValuesTuple kfv = std::make_tuple(destipprefix,
DEL_COMMAND,
fvVector);
m_warmStartHelper.insertRefreshMap(kfv);
return;
}
}
else if (nlmsg_type != RTM_NEWROUTE)
{
return;
}
sendOffloadReply(h);
switch (rtm->rtm_type)
{
case RTN_BLACKHOLE:
case RTN_UNREACHABLE:
case RTN_PROHIBIT:
{
SWSS_LOG_ERROR("RTN_BLACKHOLE route not expected (%s)", destipprefix);
return;
}
case RTN_UNICAST:
break;
case RTN_MULTICAST:
case RTN_BROADCAST:
case RTN_LOCAL:
SWSS_LOG_NOTICE("BUM routes aren't supported yet (%s)", destipprefix);
return;
default:
return;
}
/* Get nexthop lists */
string nexthops;
string vni_list;
string mac_list;
string intf_list;
bool ret;
ret = getEvpnNextHop(h, len, tb, nexthops, vni_list, mac_list, intf_list);
if (ret == false)
{
SWSS_LOG_NOTICE("EVPN Route issue with RouteTable msg: %s vtep:%s vni:%s mac:%s intf:%s",
destipprefix, nexthops.c_str(), vni_list.c_str(), mac_list.c_str(), intf_list.c_str());
return;
}
if (nexthops.empty() || mac_list.empty())
{
SWSS_LOG_NOTICE("EVPN IP Prefix: %s nexthop or rmac is empty", destipprefix);
return;
}
vector<FieldValueTuple> fvVector;
FieldValueTuple nh("nexthop", nexthops);
FieldValueTuple intf("ifname", intf_list);
FieldValueTuple vni("vni_label", vni_list);
FieldValueTuple mac("router_mac", mac_list);
fvVector.push_back(nh);
fvVector.push_back(intf);
fvVector.push_back(vni);
fvVector.push_back(mac);
if (!warmRestartInProgress)
{
m_routeTable.set(destipprefix, fvVector);
SWSS_LOG_DEBUG("RouteTable set msg: %s vtep:%s vni:%s mac:%s intf:%s",
destipprefix, nexthops.c_str(), vni_list.c_str(), mac_list.c_str(), intf_list.c_str());
}
/*
* During routing-stack restarting scenarios route-updates will be temporarily
* put on hold by warm-reboot logic.
*/
else
{
SWSS_LOG_INFO("Warm-Restart mode: RouteTable set msg: %s vtep:%s vni:%s mac:%s",
destipprefix, nexthops.c_str(), vni_list.c_str(), mac_list.c_str());
const KeyOpFieldsValuesTuple kfv = std::make_tuple(destipprefix,
SET_COMMAND,
fvVector);
m_warmStartHelper.insertRefreshMap(kfv);
}
return;
}
void RouteSync::onMsgRaw(struct nlmsghdr *h)
{
int len;
if ((h->nlmsg_type != RTM_NEWROUTE)
&& (h->nlmsg_type != RTM_DELROUTE))
return;
/* Length validity. */
len = (int)(h->nlmsg_len - NLMSG_LENGTH(sizeof(struct ndmsg)));
if (len < 0)
{
SWSS_LOG_ERROR("%s: Message received from netlink is of a broken size %d %zu",
__PRETTY_FUNCTION__, h->nlmsg_len,
(size_t)NLMSG_LENGTH(sizeof(struct ndmsg)));
return;
}
onEvpnRouteMsg(h, len);
return;
}
void RouteSync::onMsg(int nlmsg_type, struct nl_object *obj)
{
if (nlmsg_type == RTM_NEWLINK || nlmsg_type == RTM_DELLINK)
{
nl_cache_refill(m_nl_sock, m_link_cache);
return;
}
struct rtnl_route *route_obj = (struct rtnl_route *)obj;
/* Supports IPv4 or IPv6 address, otherwise return immediately */
auto family = rtnl_route_get_family(route_obj);
/* Check for Label route. */
if (family == AF_MPLS)
{
onLabelRouteMsg(nlmsg_type, obj);
return;
}
if (family != AF_INET && family != AF_INET6)
{
SWSS_LOG_INFO("Unknown route family support (object: %s)", nl_object_get_type(obj));
return;
}
/* Get the index of the master device */
unsigned int master_index = rtnl_route_get_table(route_obj);
char master_name[IFNAMSIZ] = {0};
/* if the table_id is not set in the route obj then route is for default vrf. */
if (master_index)
{
/* Get the name of the master device */
getIfName(master_index, master_name, IFNAMSIZ);
/* If the master device name starts with VNET_PREFIX, it is a VNET route.
The VNET name is exactly the name of the associated master device. */
if (string(master_name).find(VNET_PREFIX) == 0)
{
onVnetRouteMsg(nlmsg_type, obj, string(master_name));
}
/* Otherwise, it is a regular route (include VRF route). */
else
{
onRouteMsg(nlmsg_type, obj, master_name);
}
}
else
{
onRouteMsg(nlmsg_type, obj, NULL);
}
}
/*
* Handle regular route (include VRF route)
* @arg nlmsg_type Netlink message type
* @arg obj Netlink object
* @arg vrf Vrf name
*/
void RouteSync::onRouteMsg(int nlmsg_type, struct nl_object *obj, char *vrf)
{
struct rtnl_route *route_obj = (struct rtnl_route *)obj;
struct nl_addr *dip;
char destipprefix[IFNAMSIZ + MAX_ADDR_SIZE + 2] = {0};
if (vrf)
{
/*
* Now vrf device name is required to start with VRF_PREFIX,
* it is difficult to split vrf_name:ipv6_addr.
*/
if (memcmp(vrf, VRF_PREFIX, strlen(VRF_PREFIX)))
{
if(memcmp(vrf, MGMT_VRF_PREFIX, strlen(MGMT_VRF_PREFIX)))
{
SWSS_LOG_ERROR("Invalid VRF name %s (ifindex %u)", vrf, rtnl_route_get_table(route_obj));
}
else
{
dip = rtnl_route_get_dst(route_obj);
nl_addr2str(dip, destipprefix, MAX_ADDR_SIZE);
SWSS_LOG_INFO("Skip routes for Mgmt VRF name %s (ifindex %u) prefix: %s", vrf,
rtnl_route_get_table(route_obj), destipprefix);
}
return;
}
memcpy(destipprefix, vrf, strlen(vrf));
destipprefix[strlen(vrf)] = ':';
}
dip = rtnl_route_get_dst(route_obj);
nl_addr2str(dip, destipprefix + strlen(destipprefix), MAX_ADDR_SIZE);
/*
* Upon arrival of a delete msg we could either push the change right away,
* or we could opt to defer it if we are going through a warm-reboot cycle.
*/
bool warmRestartInProgress = m_warmStartHelper.inProgress();
if (nlmsg_type == RTM_DELROUTE)
{
if (!warmRestartInProgress)
{
m_routeTable.del(destipprefix);
return;
}
else
{
SWSS_LOG_INFO("Warm-Restart mode: Receiving delete msg: %s",
destipprefix);
vector<FieldValueTuple> fvVector;
const KeyOpFieldsValuesTuple kfv = std::make_tuple(destipprefix,
DEL_COMMAND,
fvVector);
m_warmStartHelper.insertRefreshMap(kfv);
return;
}
}
else if (nlmsg_type != RTM_NEWROUTE)
{
SWSS_LOG_INFO("Unknown message-type: %d for %s", nlmsg_type, destipprefix);
return;
}
if (!isSuppressionEnabled())
{
sendOffloadReply(route_obj);
}
switch (rtnl_route_get_type(route_obj))
{
case RTN_BLACKHOLE:
{
vector<FieldValueTuple> fvVector;
FieldValueTuple fv("blackhole", "true");
fvVector.push_back(fv);
m_routeTable.set(destipprefix, fvVector);
return;
}
case RTN_UNICAST:
break;
case RTN_MULTICAST:
case RTN_BROADCAST:
case RTN_LOCAL:
SWSS_LOG_INFO("BUM routes aren't supported yet (%s)", destipprefix);
return;
default:
return;
}
struct nl_list_head *nhs = rtnl_route_get_nexthops(route_obj);
if (!nhs)
{
SWSS_LOG_INFO("Nexthop list is empty for %s", destipprefix);
return;
}
/* Get nexthop lists */
string gw_list;
string intf_list;
string mpls_list;
getNextHopList(route_obj, gw_list, mpls_list, intf_list);
string weights = getNextHopWt(route_obj);
vector<string> alsv = tokenize(intf_list, NHG_DELIMITER);
for (auto alias : alsv)
{
/*
* An FRR behavior change from 7.2 to 7.5 makes FRR update default route to eth0 in interface
* up/down events. Skipping routes to eth0 or docker0 to avoid such behavior
*/
if (alias == "eth0" || alias == "docker0")
{
SWSS_LOG_DEBUG("Skip routes to eth0 or docker0: %s %s %s",
destipprefix, gw_list.c_str(), intf_list.c_str());
// If intf_list has only this interface, that means all of the next hops of this route
// have been removed and the next hop on the eth0/docker0 has become the only next hop.
// In this case since we do not want the route with next hop on eth0/docker0, we return.
// But still we need to clear the route from the APPL_DB. Otherwise the APPL_DB and data
// path will be left with stale route entry
if(alsv.size() == 1)
{
if (!warmRestartInProgress)
{
SWSS_LOG_NOTICE("RouteTable del msg for route with only one nh on eth0/docker0: %s %s %s %s",
destipprefix, gw_list.c_str(), intf_list.c_str(), mpls_list.c_str());
m_routeTable.del(destipprefix);
}
else
{
SWSS_LOG_NOTICE("Warm-Restart mode: Receiving delete msg for route with only nh on eth0/docker0: %s %s %s %s",
destipprefix, gw_list.c_str(), intf_list.c_str(), mpls_list.c_str());
vector<FieldValueTuple> fvVector;
const KeyOpFieldsValuesTuple kfv = std::make_tuple(destipprefix,
DEL_COMMAND,
fvVector);
m_warmStartHelper.insertRefreshMap(kfv);
}
}
return;
}
}
auto proto_num = rtnl_route_get_protocol(route_obj);
auto proto_str = getProtocolString(proto_num);
vector<FieldValueTuple> fvVector;
FieldValueTuple proto("protocol", proto_str);
FieldValueTuple gw("nexthop", gw_list);
FieldValueTuple intf("ifname", intf_list);
fvVector.push_back(proto);
fvVector.push_back(gw);
fvVector.push_back(intf);
if (!mpls_list.empty())
{
FieldValueTuple mpls_nh("mpls_nh", mpls_list);
fvVector.push_back(mpls_nh);
}
if (!weights.empty())
{
FieldValueTuple wt("weight", weights);
fvVector.push_back(wt);
}
if (!warmRestartInProgress)
{
m_routeTable.set(destipprefix, fvVector);
SWSS_LOG_DEBUG("RouteTable set msg: %s %s %s %s", destipprefix,
gw_list.c_str(), intf_list.c_str(), mpls_list.c_str());
}
/*
* During routing-stack restarting scenarios route-updates will be temporarily
* put on hold by warm-reboot logic.
*/
else
{
SWSS_LOG_INFO("Warm-Restart mode: RouteTable set msg: %s %s %s %s", destipprefix,
gw_list.c_str(), intf_list.c_str(), mpls_list.c_str());
const KeyOpFieldsValuesTuple kfv = std::make_tuple(destipprefix,
SET_COMMAND,
fvVector);
m_warmStartHelper.insertRefreshMap(kfv);
}
}
/*
* Handle label route
* @arg nlmsg_type Netlink message type
* @arg obj Netlink object
*/
void RouteSync::onLabelRouteMsg(int nlmsg_type, struct nl_object *obj)
{
struct rtnl_route *route_obj = (struct rtnl_route *)obj;
struct nl_addr *daddr;
char destaddr[MAX_ADDR_SIZE + 1] = {0};
daddr = rtnl_route_get_dst(route_obj);
nl_addr2str(daddr, destaddr, MAX_ADDR_SIZE);
SWSS_LOG_INFO("Receive new LabelRoute message dest addr: %s", destaddr);
if (nl_addr_iszero(daddr)) return;
if (nlmsg_type == RTM_DELROUTE)
{
m_label_routeTable.del(destaddr);
return;
}
else if (nlmsg_type != RTM_NEWROUTE)
{
SWSS_LOG_INFO("Unknown message-type: %d for LabelRoute %s", nlmsg_type, destaddr);
return;
}
sendOffloadReply(route_obj);
/* Get the index of the master device */
uint32_t master_index = rtnl_route_get_table(route_obj);
/* if the table_id is not set in the route obj then route is for default vrf. */
if (master_index)
{
SWSS_LOG_INFO("Unsupported Non-default VRF: %d for LabelRoute %s",
master_index, destaddr);
return;
}
switch (rtnl_route_get_type(route_obj))
{
case RTN_BLACKHOLE:
{
vector<FieldValueTuple> fvVector;
FieldValueTuple fv("blackhole", "true");
fvVector.push_back(fv);
m_label_routeTable.set(destaddr, fvVector);
return;
}
case RTN_UNICAST:
break;
case RTN_MULTICAST:
case RTN_BROADCAST:
case RTN_LOCAL:
SWSS_LOG_INFO("BUM routes aren't supported yet (%s)", destaddr);
return;
default:
return;
}
struct nl_list_head *nhs = rtnl_route_get_nexthops(route_obj);
if (!nhs)
{
SWSS_LOG_INFO("Nexthop list is empty for LabelRoute %s", destaddr);
return;
}
/* Get nexthop lists */
string gw_list;
string intf_list;
string mpls_list;
getNextHopList(route_obj, gw_list, mpls_list, intf_list);
vector<FieldValueTuple> fvVector;
FieldValueTuple gw("nexthop", gw_list);
FieldValueTuple intf("ifname", intf_list);
FieldValueTuple mpls_pop("mpls_pop", "1");
fvVector.push_back(gw);
fvVector.push_back(intf);
if (!mpls_list.empty())
{
FieldValueTuple mpls_nh("mpls_nh", mpls_list);
fvVector.push_back(mpls_nh);
}
fvVector.push_back(mpls_pop);
m_label_routeTable.set(destaddr, fvVector);
SWSS_LOG_INFO("LabelRouteTable set msg: %s %s %s %s", destaddr,
gw_list.c_str(), intf_list.c_str(), mpls_list.c_str());
}
/*
* Handle vnet route
* @arg nlmsg_type Netlink message type
* @arg obj Netlink object
* @arg vnet Vnet name
*/
void RouteSync::onVnetRouteMsg(int nlmsg_type, struct nl_object *obj, string vnet)
{
struct rtnl_route *route_obj = (struct rtnl_route *)obj;
/* Get the destination IP prefix */
struct nl_addr *dip = rtnl_route_get_dst(route_obj);
char destipprefix[MAX_ADDR_SIZE + 1] = {0};
nl_addr2str(dip, destipprefix, MAX_ADDR_SIZE);
string vnet_dip = vnet + string(":") + destipprefix;
SWSS_LOG_DEBUG("Receive new vnet route message %s", vnet_dip.c_str());
/* Ignore IPv6 link-local and mc addresses as Vnet routes */
auto family = rtnl_route_get_family(route_obj);
if (family == AF_INET6 &&
(IN6_IS_ADDR_LINKLOCAL(nl_addr_get_binary_addr(dip)) || IN6_IS_ADDR_MULTICAST(nl_addr_get_binary_addr(dip))))
{
SWSS_LOG_INFO("Ignore linklocal vnet routes %d for %s", nlmsg_type, vnet_dip.c_str());
return;
}
if (nlmsg_type == RTM_DELROUTE)
{
/* Duplicated delete as we do not know if it is a VXLAN tunnel route*/
m_vnet_routeTable.del(vnet_dip);
m_vnet_tunnelTable.del(vnet_dip);
return;
}
else if (nlmsg_type != RTM_NEWROUTE)
{
SWSS_LOG_INFO("Unknown message-type: %d for %s", nlmsg_type, vnet_dip.c_str());
return;
}
sendOffloadReply(route_obj);
switch (rtnl_route_get_type(route_obj))
{
case RTN_UNICAST:
break;
/* We may support blackhole in the future */
case RTN_BLACKHOLE:
SWSS_LOG_INFO("Blackhole route is supported yet (%s)", vnet_dip.c_str());
return;