forked from openvswitch/ovs
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathflow.c
2247 lines (1968 loc) · 74.8 KB
/
flow.c
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
/*
* Copyright (c) 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015 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 <sys/types.h>
#include "flow.h"
#include <errno.h>
#include <inttypes.h>
#include <limits.h>
#include <netinet/in.h>
#include <netinet/icmp6.h>
#include <netinet/ip6.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>
#include "byte-order.h"
#include "coverage.h"
#include "csum.h"
#include "dynamic-string.h"
#include "hash.h"
#include "jhash.h"
#include "match.h"
#include "dp-packet.h"
#include "openflow/openflow.h"
#include "packets.h"
#include "odp-util.h"
#include "random.h"
#include "unaligned.h"
COVERAGE_DEFINE(flow_extract);
COVERAGE_DEFINE(miniflow_malloc);
/* U64 indices for segmented flow classification. */
const uint8_t flow_segment_u64s[4] = {
FLOW_SEGMENT_1_ENDS_AT / sizeof(uint64_t),
FLOW_SEGMENT_2_ENDS_AT / sizeof(uint64_t),
FLOW_SEGMENT_3_ENDS_AT / sizeof(uint64_t),
FLOW_U64S
};
/* Asserts that field 'f1' follows immediately after 'f0' in struct flow,
* without any intervening padding. */
#define ASSERT_SEQUENTIAL(f0, f1) \
BUILD_ASSERT_DECL(offsetof(struct flow, f0) \
+ MEMBER_SIZEOF(struct flow, f0) \
== offsetof(struct flow, f1))
/* Asserts that fields 'f0' and 'f1' are in the same 32-bit aligned word within
* struct flow. */
#define ASSERT_SAME_WORD(f0, f1) \
BUILD_ASSERT_DECL(offsetof(struct flow, f0) / 4 \
== offsetof(struct flow, f1) / 4)
/* Asserts that 'f0' and 'f1' are both sequential and within the same 32-bit
* aligned word in struct flow. */
#define ASSERT_SEQUENTIAL_SAME_WORD(f0, f1) \
ASSERT_SEQUENTIAL(f0, f1); \
ASSERT_SAME_WORD(f0, f1)
/* miniflow_extract() assumes the following to be true to optimize the
* extraction process. */
ASSERT_SEQUENTIAL_SAME_WORD(dl_type, vlan_tci);
ASSERT_SEQUENTIAL_SAME_WORD(nw_frag, nw_tos);
ASSERT_SEQUENTIAL_SAME_WORD(nw_tos, nw_ttl);
ASSERT_SEQUENTIAL_SAME_WORD(nw_ttl, nw_proto);
/* TCP flags in the middle of a BE64, zeroes in the other half. */
BUILD_ASSERT_DECL(offsetof(struct flow, tcp_flags) % 8 == 4);
#if WORDS_BIGENDIAN
#define TCP_FLAGS_BE32(tcp_ctl) ((OVS_FORCE ovs_be32)TCP_FLAGS_BE16(tcp_ctl) \
<< 16)
#else
#define TCP_FLAGS_BE32(tcp_ctl) ((OVS_FORCE ovs_be32)TCP_FLAGS_BE16(tcp_ctl))
#endif
ASSERT_SEQUENTIAL_SAME_WORD(tp_src, tp_dst);
/* Removes 'size' bytes from the head end of '*datap', of size '*sizep', which
* must contain at least 'size' bytes of data. Returns the first byte of data
* removed. */
static inline const void *
data_pull(const void **datap, size_t *sizep, size_t size)
{
const char *data = *datap;
*datap = data + size;
*sizep -= size;
return data;
}
/* If '*datap' has at least 'size' bytes of data, removes that many bytes from
* the head end of '*datap' and returns the first byte removed. Otherwise,
* returns a null pointer without modifying '*datap'. */
static inline const void *
data_try_pull(const void **datap, size_t *sizep, size_t size)
{
return OVS_LIKELY(*sizep >= size) ? data_pull(datap, sizep, size) : NULL;
}
/* Context for pushing data to a miniflow. */
struct mf_ctx {
uint64_t map;
uint64_t *data;
uint64_t * const end;
};
/* miniflow_push_* macros allow filling in a miniflow data values in order.
* Assertions are needed only when the layout of the struct flow is modified.
* 'ofs' is a compile-time constant, which allows most of the code be optimized
* away. Some GCC versions gave warnings on ALWAYS_INLINE, so these are
* defined as macros. */
#if (FLOW_WC_SEQ != 31)
#define MINIFLOW_ASSERT(X) ovs_assert(X)
BUILD_MESSAGE("FLOW_WC_SEQ changed: miniflow_extract() will have runtime "
"assertions enabled. Consider updating FLOW_WC_SEQ after "
"testing")
#else
#define MINIFLOW_ASSERT(X)
#endif
#define miniflow_push_uint64_(MF, OFS, VALUE) \
{ \
MINIFLOW_ASSERT(MF.data < MF.end && (OFS) % 8 == 0 \
&& !(MF.map & (UINT64_MAX << (OFS) / 8))); \
*MF.data++ = VALUE; \
MF.map |= UINT64_C(1) << (OFS) / 8; \
}
#define miniflow_push_be64_(MF, OFS, VALUE) \
miniflow_push_uint64_(MF, OFS, (OVS_FORCE uint64_t)(VALUE))
#define miniflow_push_uint32_(MF, OFS, VALUE) \
{ \
MINIFLOW_ASSERT(MF.data < MF.end && \
(((OFS) % 8 == 0 && !(MF.map & (UINT64_MAX << (OFS) / 8))) \
|| ((OFS) % 8 == 4 && MF.map & (UINT64_C(1) << (OFS) / 8) \
&& !(MF.map & (UINT64_MAX << ((OFS) / 8 + 1)))))); \
\
if ((OFS) % 8 == 0) { \
*(uint32_t *)MF.data = VALUE; \
MF.map |= UINT64_C(1) << (OFS) / 8; \
} else if ((OFS) % 8 == 4) { \
*((uint32_t *)MF.data + 1) = VALUE; \
MF.data++; \
} \
}
#define miniflow_push_be32_(MF, OFS, VALUE) \
miniflow_push_uint32_(MF, OFS, (OVS_FORCE uint32_t)(VALUE))
#define miniflow_push_uint16_(MF, OFS, VALUE) \
{ \
MINIFLOW_ASSERT(MF.data < MF.end && \
(((OFS) % 8 == 0 && !(MF.map & (UINT64_MAX << (OFS) / 8))) \
|| ((OFS) % 2 == 0 && MF.map & (UINT64_C(1) << (OFS) / 8) \
&& !(MF.map & (UINT64_MAX << ((OFS) / 8 + 1)))))); \
\
if ((OFS) % 8 == 0) { \
*(uint16_t *)MF.data = VALUE; \
MF.map |= UINT64_C(1) << (OFS) / 8; \
} else if ((OFS) % 8 == 2) { \
*((uint16_t *)MF.data + 1) = VALUE; \
} else if ((OFS) % 8 == 4) { \
*((uint16_t *)MF.data + 2) = VALUE; \
} else if ((OFS) % 8 == 6) { \
*((uint16_t *)MF.data + 3) = VALUE; \
MF.data++; \
} \
}
#define miniflow_pad_to_64_(MF, OFS) \
{ \
MINIFLOW_ASSERT((OFS) % 8 != 0); \
MINIFLOW_ASSERT(MF.map & (UINT64_C(1) << (OFS) / 8)); \
MINIFLOW_ASSERT(!(MF.map & (UINT64_MAX << ((OFS) / 8 + 1)))); \
\
memset((uint8_t *)MF.data + (OFS) % 8, 0, 8 - (OFS) % 8); \
MF.data++; \
}
#define miniflow_push_be16_(MF, OFS, VALUE) \
miniflow_push_uint16_(MF, OFS, (OVS_FORCE uint16_t)VALUE);
/* Data at 'valuep' may be unaligned. */
#define miniflow_push_words_(MF, OFS, VALUEP, N_WORDS) \
{ \
int ofs64 = (OFS) / 8; \
\
MINIFLOW_ASSERT(MF.data + (N_WORDS) <= MF.end && (OFS) % 8 == 0 \
&& !(MF.map & (UINT64_MAX << ofs64))); \
\
memcpy(MF.data, (VALUEP), (N_WORDS) * sizeof *MF.data); \
MF.data += (N_WORDS); \
MF.map |= ((UINT64_MAX >> (64 - (N_WORDS))) << ofs64); \
}
/* Push 32-bit words padded to 64-bits. */
#define miniflow_push_words_32_(MF, OFS, VALUEP, N_WORDS) \
{ \
int ofs64 = (OFS) / 8; \
\
MINIFLOW_ASSERT(MF.data + DIV_ROUND_UP(N_WORDS, 2) <= MF.end \
&& (OFS) % 8 == 0 \
&& !(MF.map & (UINT64_MAX << ofs64))); \
\
memcpy(MF.data, (VALUEP), (N_WORDS) * sizeof(uint32_t)); \
MF.data += DIV_ROUND_UP(N_WORDS, 2); \
MF.map |= ((UINT64_MAX >> (64 - DIV_ROUND_UP(N_WORDS, 2))) << ofs64); \
if ((N_WORDS) & 1) { \
*((uint32_t *)MF.data - 1) = 0; \
} \
}
/* Data at 'valuep' may be unaligned. */
/* MACs start 64-aligned, and must be followed by other data or padding. */
#define miniflow_push_macs_(MF, OFS, VALUEP) \
{ \
int ofs64 = (OFS) / 8; \
\
MINIFLOW_ASSERT(MF.data + 2 <= MF.end && (OFS) % 8 == 0 \
&& !(MF.map & (UINT64_MAX << ofs64))); \
\
memcpy(MF.data, (VALUEP), 2 * ETH_ADDR_LEN); \
MF.data += 1; /* First word only. */ \
MF.map |= UINT64_C(3) << ofs64; /* Both words. */ \
}
#define miniflow_push_uint32(MF, FIELD, VALUE) \
miniflow_push_uint32_(MF, offsetof(struct flow, FIELD), VALUE)
#define miniflow_push_be32(MF, FIELD, VALUE) \
miniflow_push_be32_(MF, offsetof(struct flow, FIELD), VALUE)
#define miniflow_push_uint16(MF, FIELD, VALUE) \
miniflow_push_uint16_(MF, offsetof(struct flow, FIELD), VALUE)
#define miniflow_push_be16(MF, FIELD, VALUE) \
miniflow_push_be16_(MF, offsetof(struct flow, FIELD), VALUE)
#define miniflow_pad_to_64(MF, FIELD) \
miniflow_pad_to_64_(MF, offsetof(struct flow, FIELD))
#define miniflow_push_words(MF, FIELD, VALUEP, N_WORDS) \
miniflow_push_words_(MF, offsetof(struct flow, FIELD), VALUEP, N_WORDS)
#define miniflow_push_words_32(MF, FIELD, VALUEP, N_WORDS) \
miniflow_push_words_32_(MF, offsetof(struct flow, FIELD), VALUEP, N_WORDS)
#define miniflow_push_macs(MF, FIELD, VALUEP) \
miniflow_push_macs_(MF, offsetof(struct flow, FIELD), VALUEP)
/* Pulls the MPLS headers at '*datap' and returns the count of them. */
static inline int
parse_mpls(const void **datap, size_t *sizep)
{
const struct mpls_hdr *mh;
int count = 0;
while ((mh = data_try_pull(datap, sizep, sizeof *mh))) {
count++;
if (mh->mpls_lse.lo & htons(1 << MPLS_BOS_SHIFT)) {
break;
}
}
return MIN(count, FLOW_MAX_MPLS_LABELS);
}
static inline ovs_be16
parse_vlan(const void **datap, size_t *sizep)
{
const struct eth_header *eth = *datap;
struct qtag_prefix {
ovs_be16 eth_type; /* ETH_TYPE_VLAN */
ovs_be16 tci;
};
data_pull(datap, sizep, ETH_ADDR_LEN * 2);
if (eth->eth_type == htons(ETH_TYPE_VLAN)) {
if (OVS_LIKELY(*sizep
>= sizeof(struct qtag_prefix) + sizeof(ovs_be16))) {
const struct qtag_prefix *qp = data_pull(datap, sizep, sizeof *qp);
return qp->tci | htons(VLAN_CFI);
}
}
return 0;
}
static inline ovs_be16
parse_ethertype(const void **datap, size_t *sizep)
{
const struct llc_snap_header *llc;
ovs_be16 proto;
proto = *(ovs_be16 *) data_pull(datap, sizep, sizeof proto);
if (OVS_LIKELY(ntohs(proto) >= ETH_TYPE_MIN)) {
return proto;
}
if (OVS_UNLIKELY(*sizep < sizeof *llc)) {
return htons(FLOW_DL_TYPE_NONE);
}
llc = *datap;
if (OVS_UNLIKELY(llc->llc.llc_dsap != LLC_DSAP_SNAP
|| llc->llc.llc_ssap != LLC_SSAP_SNAP
|| llc->llc.llc_cntl != LLC_CNTL_SNAP
|| memcmp(llc->snap.snap_org, SNAP_ORG_ETHERNET,
sizeof llc->snap.snap_org))) {
return htons(FLOW_DL_TYPE_NONE);
}
data_pull(datap, sizep, sizeof *llc);
if (OVS_LIKELY(ntohs(llc->snap.snap_type) >= ETH_TYPE_MIN)) {
return llc->snap.snap_type;
}
return htons(FLOW_DL_TYPE_NONE);
}
static inline bool
parse_icmpv6(const void **datap, size_t *sizep, const struct icmp6_hdr *icmp,
const struct in6_addr **nd_target,
uint8_t arp_buf[2][ETH_ADDR_LEN])
{
if (icmp->icmp6_code == 0 &&
(icmp->icmp6_type == ND_NEIGHBOR_SOLICIT ||
icmp->icmp6_type == ND_NEIGHBOR_ADVERT)) {
*nd_target = data_try_pull(datap, sizep, sizeof **nd_target);
if (OVS_UNLIKELY(!*nd_target)) {
return false;
}
while (*sizep >= 8) {
/* The minimum size of an option is 8 bytes, which also is
* the size of Ethernet link-layer options. */
const struct nd_opt_hdr *nd_opt = *datap;
int opt_len = nd_opt->nd_opt_len * 8;
if (!opt_len || opt_len > *sizep) {
goto invalid;
}
/* Store the link layer address if the appropriate option is
* provided. It is considered an error if the same link
* layer option is specified twice. */
if (nd_opt->nd_opt_type == ND_OPT_SOURCE_LINKADDR
&& opt_len == 8) {
if (OVS_LIKELY(eth_addr_is_zero(arp_buf[0]))) {
memcpy(arp_buf[0], nd_opt + 1, ETH_ADDR_LEN);
} else {
goto invalid;
}
} else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LINKADDR
&& opt_len == 8) {
if (OVS_LIKELY(eth_addr_is_zero(arp_buf[1]))) {
memcpy(arp_buf[1], nd_opt + 1, ETH_ADDR_LEN);
} else {
goto invalid;
}
}
if (OVS_UNLIKELY(!data_try_pull(datap, sizep, opt_len))) {
goto invalid;
}
}
}
return true;
invalid:
return false;
}
/* Initializes 'flow' members from 'packet' and 'md'
*
* Initializes 'packet' header l2 pointer to the start of the Ethernet
* header, and the layer offsets as follows:
*
* - packet->l2_5_ofs to the start of the MPLS shim header, or UINT16_MAX
* when there is no MPLS shim header.
*
* - packet->l3_ofs to just past the Ethernet header, or just past the
* vlan_header if one is present, to the first byte of the payload of the
* Ethernet frame. UINT16_MAX if the frame is too short to contain an
* Ethernet header.
*
* - packet->l4_ofs to just past the IPv4 header, if one is present and
* has at least the content used for the fields of interest for the flow,
* otherwise UINT16_MAX.
*/
void
flow_extract(struct dp_packet *packet, struct flow *flow)
{
struct {
struct miniflow mf;
uint64_t buf[FLOW_U64S];
} m;
COVERAGE_INC(flow_extract);
miniflow_initialize(&m.mf, m.buf);
miniflow_extract(packet, &m.mf);
miniflow_expand(&m.mf, flow);
}
/* Caller is responsible for initializing 'dst' with enough storage for
* FLOW_U64S * 8 bytes. */
void
miniflow_extract(struct dp_packet *packet, struct miniflow *dst)
{
const struct pkt_metadata *md = &packet->md;
const void *data = dp_packet_data(packet);
size_t size = dp_packet_size(packet);
uint64_t *values = miniflow_values(dst);
struct mf_ctx mf = { 0, values, values + FLOW_U64S };
const char *l2;
ovs_be16 dl_type;
uint8_t nw_frag, nw_tos, nw_ttl, nw_proto;
/* Metadata. */
if (md->tunnel.ip_dst) {
miniflow_push_words(mf, tunnel, &md->tunnel,
sizeof md->tunnel / sizeof(uint64_t));
}
if (md->skb_priority || md->pkt_mark) {
miniflow_push_uint32(mf, skb_priority, md->skb_priority);
miniflow_push_uint32(mf, pkt_mark, md->pkt_mark);
}
miniflow_push_uint32(mf, dp_hash, md->dp_hash);
miniflow_push_uint32(mf, in_port, odp_to_u32(md->in_port.odp_port));
if (md->recirc_id) {
miniflow_push_uint32(mf, recirc_id, md->recirc_id);
miniflow_pad_to_64(mf, conj_id);
}
/* Initialize packet's layer pointer and offsets. */
l2 = data;
dp_packet_reset_offsets(packet);
/* Must have full Ethernet header to proceed. */
if (OVS_UNLIKELY(size < sizeof(struct eth_header))) {
goto out;
} else {
ovs_be16 vlan_tci;
/* Link layer. */
ASSERT_SEQUENTIAL(dl_dst, dl_src);
miniflow_push_macs(mf, dl_dst, data);
/* dl_type, vlan_tci. */
vlan_tci = parse_vlan(&data, &size);
dl_type = parse_ethertype(&data, &size);
miniflow_push_be16(mf, dl_type, dl_type);
miniflow_push_be16(mf, vlan_tci, vlan_tci);
}
/* Parse mpls. */
if (OVS_UNLIKELY(eth_type_mpls(dl_type))) {
int count;
const void *mpls = data;
packet->l2_5_ofs = (char *)data - l2;
count = parse_mpls(&data, &size);
miniflow_push_words_32(mf, mpls_lse, mpls, count);
}
/* Network layer. */
packet->l3_ofs = (char *)data - l2;
nw_frag = 0;
if (OVS_LIKELY(dl_type == htons(ETH_TYPE_IP))) {
const struct ip_header *nh = data;
int ip_len;
uint16_t tot_len;
if (OVS_UNLIKELY(size < IP_HEADER_LEN)) {
goto out;
}
ip_len = IP_IHL(nh->ip_ihl_ver) * 4;
if (OVS_UNLIKELY(ip_len < IP_HEADER_LEN)) {
goto out;
}
if (OVS_UNLIKELY(size < ip_len)) {
goto out;
}
tot_len = ntohs(nh->ip_tot_len);
if (OVS_UNLIKELY(tot_len > size)) {
goto out;
}
if (OVS_UNLIKELY(size - tot_len > UINT8_MAX)) {
goto out;
}
dp_packet_set_l2_pad_size(packet, size - tot_len);
size = tot_len; /* Never pull padding. */
/* Push both source and destination address at once. */
miniflow_push_words(mf, nw_src, &nh->ip_src, 1);
miniflow_push_be32(mf, ipv6_label, 0); /* Padding for IPv4. */
nw_tos = nh->ip_tos;
nw_ttl = nh->ip_ttl;
nw_proto = nh->ip_proto;
if (OVS_UNLIKELY(IP_IS_FRAGMENT(nh->ip_frag_off))) {
nw_frag = FLOW_NW_FRAG_ANY;
if (nh->ip_frag_off & htons(IP_FRAG_OFF_MASK)) {
nw_frag |= FLOW_NW_FRAG_LATER;
}
}
data_pull(&data, &size, ip_len);
} else if (dl_type == htons(ETH_TYPE_IPV6)) {
const struct ovs_16aligned_ip6_hdr *nh;
ovs_be32 tc_flow;
uint16_t plen;
if (OVS_UNLIKELY(size < sizeof *nh)) {
goto out;
}
nh = data_pull(&data, &size, sizeof *nh);
plen = ntohs(nh->ip6_plen);
if (OVS_UNLIKELY(plen > size)) {
goto out;
}
/* Jumbo Payload option not supported yet. */
if (OVS_UNLIKELY(size - plen > UINT8_MAX)) {
goto out;
}
dp_packet_set_l2_pad_size(packet, size - plen);
size = plen; /* Never pull padding. */
miniflow_push_words(mf, ipv6_src, &nh->ip6_src,
sizeof nh->ip6_src / 8);
miniflow_push_words(mf, ipv6_dst, &nh->ip6_dst,
sizeof nh->ip6_dst / 8);
tc_flow = get_16aligned_be32(&nh->ip6_flow);
{
ovs_be32 label = tc_flow & htonl(IPV6_LABEL_MASK);
miniflow_push_be32(mf, ipv6_label, label);
}
nw_tos = ntohl(tc_flow) >> 20;
nw_ttl = nh->ip6_hlim;
nw_proto = nh->ip6_nxt;
while (1) {
if (OVS_LIKELY((nw_proto != IPPROTO_HOPOPTS)
&& (nw_proto != IPPROTO_ROUTING)
&& (nw_proto != IPPROTO_DSTOPTS)
&& (nw_proto != IPPROTO_AH)
&& (nw_proto != IPPROTO_FRAGMENT))) {
/* It's either a terminal header (e.g., TCP, UDP) or one we
* don't understand. In either case, we're done with the
* packet, so use it to fill in 'nw_proto'. */
break;
}
/* We only verify that at least 8 bytes of the next header are
* available, but many of these headers are longer. Ensure that
* accesses within the extension header are within those first 8
* bytes. All extension headers are required to be at least 8
* bytes. */
if (OVS_UNLIKELY(size < 8)) {
goto out;
}
if ((nw_proto == IPPROTO_HOPOPTS)
|| (nw_proto == IPPROTO_ROUTING)
|| (nw_proto == IPPROTO_DSTOPTS)) {
/* These headers, while different, have the fields we care
* about in the same location and with the same
* interpretation. */
const struct ip6_ext *ext_hdr = data;
nw_proto = ext_hdr->ip6e_nxt;
if (OVS_UNLIKELY(!data_try_pull(&data, &size,
(ext_hdr->ip6e_len + 1) * 8))) {
goto out;
}
} else if (nw_proto == IPPROTO_AH) {
/* A standard AH definition isn't available, but the fields
* we care about are in the same location as the generic
* option header--only the header length is calculated
* differently. */
const struct ip6_ext *ext_hdr = data;
nw_proto = ext_hdr->ip6e_nxt;
if (OVS_UNLIKELY(!data_try_pull(&data, &size,
(ext_hdr->ip6e_len + 2) * 4))) {
goto out;
}
} else if (nw_proto == IPPROTO_FRAGMENT) {
const struct ovs_16aligned_ip6_frag *frag_hdr = data;
nw_proto = frag_hdr->ip6f_nxt;
if (!data_try_pull(&data, &size, sizeof *frag_hdr)) {
goto out;
}
/* We only process the first fragment. */
if (frag_hdr->ip6f_offlg != htons(0)) {
nw_frag = FLOW_NW_FRAG_ANY;
if ((frag_hdr->ip6f_offlg & IP6F_OFF_MASK) != htons(0)) {
nw_frag |= FLOW_NW_FRAG_LATER;
nw_proto = IPPROTO_FRAGMENT;
break;
}
}
}
}
} else {
if (dl_type == htons(ETH_TYPE_ARP) ||
dl_type == htons(ETH_TYPE_RARP)) {
uint8_t arp_buf[2][ETH_ADDR_LEN];
const struct arp_eth_header *arp = (const struct arp_eth_header *)
data_try_pull(&data, &size, ARP_ETH_HEADER_LEN);
if (OVS_LIKELY(arp) && OVS_LIKELY(arp->ar_hrd == htons(1))
&& OVS_LIKELY(arp->ar_pro == htons(ETH_TYPE_IP))
&& OVS_LIKELY(arp->ar_hln == ETH_ADDR_LEN)
&& OVS_LIKELY(arp->ar_pln == 4)) {
miniflow_push_be32(mf, nw_src,
get_16aligned_be32(&arp->ar_spa));
miniflow_push_be32(mf, nw_dst,
get_16aligned_be32(&arp->ar_tpa));
/* We only match on the lower 8 bits of the opcode. */
if (OVS_LIKELY(ntohs(arp->ar_op) <= 0xff)) {
miniflow_push_be32(mf, ipv6_label, 0); /* Pad with ARP. */
miniflow_push_be32(mf, nw_frag, htonl(ntohs(arp->ar_op)));
}
/* Must be adjacent. */
ASSERT_SEQUENTIAL(arp_sha, arp_tha);
memcpy(arp_buf[0], arp->ar_sha, ETH_ADDR_LEN);
memcpy(arp_buf[1], arp->ar_tha, ETH_ADDR_LEN);
miniflow_push_macs(mf, arp_sha, arp_buf);
miniflow_pad_to_64(mf, tcp_flags);
}
}
goto out;
}
packet->l4_ofs = (char *)data - l2;
miniflow_push_be32(mf, nw_frag,
BYTES_TO_BE32(nw_frag, nw_tos, nw_ttl, nw_proto));
if (OVS_LIKELY(!(nw_frag & FLOW_NW_FRAG_LATER))) {
if (OVS_LIKELY(nw_proto == IPPROTO_TCP)) {
if (OVS_LIKELY(size >= TCP_HEADER_LEN)) {
const struct tcp_header *tcp = data;
miniflow_push_be32(mf, arp_tha[2], 0);
miniflow_push_be32(mf, tcp_flags,
TCP_FLAGS_BE32(tcp->tcp_ctl));
miniflow_push_be16(mf, tp_src, tcp->tcp_src);
miniflow_push_be16(mf, tp_dst, tcp->tcp_dst);
miniflow_pad_to_64(mf, igmp_group_ip4);
}
} else if (OVS_LIKELY(nw_proto == IPPROTO_UDP)) {
if (OVS_LIKELY(size >= UDP_HEADER_LEN)) {
const struct udp_header *udp = data;
miniflow_push_be16(mf, tp_src, udp->udp_src);
miniflow_push_be16(mf, tp_dst, udp->udp_dst);
miniflow_pad_to_64(mf, igmp_group_ip4);
}
} else if (OVS_LIKELY(nw_proto == IPPROTO_SCTP)) {
if (OVS_LIKELY(size >= SCTP_HEADER_LEN)) {
const struct sctp_header *sctp = data;
miniflow_push_be16(mf, tp_src, sctp->sctp_src);
miniflow_push_be16(mf, tp_dst, sctp->sctp_dst);
miniflow_pad_to_64(mf, igmp_group_ip4);
}
} else if (OVS_LIKELY(nw_proto == IPPROTO_ICMP)) {
if (OVS_LIKELY(size >= ICMP_HEADER_LEN)) {
const struct icmp_header *icmp = data;
miniflow_push_be16(mf, tp_src, htons(icmp->icmp_type));
miniflow_push_be16(mf, tp_dst, htons(icmp->icmp_code));
miniflow_pad_to_64(mf, igmp_group_ip4);
}
} else if (OVS_LIKELY(nw_proto == IPPROTO_IGMP)) {
if (OVS_LIKELY(size >= IGMP_HEADER_LEN)) {
const struct igmp_header *igmp = data;
miniflow_push_be16(mf, tp_src, htons(igmp->igmp_type));
miniflow_push_be16(mf, tp_dst, htons(igmp->igmp_code));
miniflow_push_be32(mf, igmp_group_ip4,
get_16aligned_be32(&igmp->group));
}
} else if (OVS_LIKELY(nw_proto == IPPROTO_ICMPV6)) {
if (OVS_LIKELY(size >= sizeof(struct icmp6_hdr))) {
const struct in6_addr *nd_target = NULL;
uint8_t arp_buf[2][ETH_ADDR_LEN];
const struct icmp6_hdr *icmp = data_pull(&data, &size,
sizeof *icmp);
memset(arp_buf, 0, sizeof arp_buf);
if (OVS_LIKELY(parse_icmpv6(&data, &size, icmp, &nd_target,
arp_buf))) {
if (nd_target) {
miniflow_push_words(mf, nd_target, nd_target,
sizeof *nd_target / 8);
}
miniflow_push_macs(mf, arp_sha, arp_buf);
miniflow_pad_to_64(mf, tcp_flags);
miniflow_push_be16(mf, tp_src, htons(icmp->icmp6_type));
miniflow_push_be16(mf, tp_dst, htons(icmp->icmp6_code));
miniflow_pad_to_64(mf, igmp_group_ip4);
}
}
}
}
out:
dst->map = mf.map;
}
/* For every bit of a field that is wildcarded in 'wildcards', sets the
* corresponding bit in 'flow' to zero. */
void
flow_zero_wildcards(struct flow *flow, const struct flow_wildcards *wildcards)
{
uint64_t *flow_u64 = (uint64_t *) flow;
const uint64_t *wc_u64 = (const uint64_t *) &wildcards->masks;
size_t i;
for (i = 0; i < FLOW_U64S; i++) {
flow_u64[i] &= wc_u64[i];
}
}
void
flow_unwildcard_tp_ports(const struct flow *flow, struct flow_wildcards *wc)
{
if (flow->nw_proto != IPPROTO_ICMP) {
memset(&wc->masks.tp_src, 0xff, sizeof wc->masks.tp_src);
memset(&wc->masks.tp_dst, 0xff, sizeof wc->masks.tp_dst);
} else {
wc->masks.tp_src = htons(0xff);
wc->masks.tp_dst = htons(0xff);
}
}
/* Initializes 'flow_metadata' with the metadata found in 'flow'. */
void
flow_get_metadata(const struct flow *flow, struct match *flow_metadata)
{
int i;
BUILD_ASSERT_DECL(FLOW_WC_SEQ == 31);
match_init_catchall(flow_metadata);
if (flow->tunnel.tun_id != htonll(0)) {
match_set_tun_id(flow_metadata, flow->tunnel.tun_id);
}
if (flow->tunnel.ip_src != htonl(0)) {
match_set_tun_src(flow_metadata, flow->tunnel.ip_src);
}
if (flow->tunnel.ip_dst != htonl(0)) {
match_set_tun_dst(flow_metadata, flow->tunnel.ip_dst);
}
if (flow->tunnel.gbp_id != htons(0)) {
match_set_tun_gbp_id(flow_metadata, flow->tunnel.gbp_id);
}
if (flow->tunnel.gbp_flags) {
match_set_tun_gbp_flags(flow_metadata, flow->tunnel.gbp_flags);
}
if (flow->metadata != htonll(0)) {
match_set_metadata(flow_metadata, flow->metadata);
}
for (i = 0; i < FLOW_N_REGS; i++) {
if (flow->regs[i]) {
match_set_reg(flow_metadata, i, flow->regs[i]);
}
}
if (flow->pkt_mark != 0) {
match_set_pkt_mark(flow_metadata, flow->pkt_mark);
}
match_set_in_port(flow_metadata, flow->in_port.ofp_port);
}
char *
flow_to_string(const struct flow *flow)
{
struct ds ds = DS_EMPTY_INITIALIZER;
flow_format(&ds, flow);
return ds_cstr(&ds);
}
const char *
flow_tun_flag_to_string(uint32_t flags)
{
switch (flags) {
case FLOW_TNL_F_DONT_FRAGMENT:
return "df";
case FLOW_TNL_F_CSUM:
return "csum";
case FLOW_TNL_F_KEY:
return "key";
case FLOW_TNL_F_OAM:
return "oam";
default:
return NULL;
}
}
void
format_flags(struct ds *ds, const char *(*bit_to_string)(uint32_t),
uint32_t flags, char del)
{
uint32_t bad = 0;
if (!flags) {
return;
}
while (flags) {
uint32_t bit = rightmost_1bit(flags);
const char *s;
s = bit_to_string(bit);
if (s) {
ds_put_format(ds, "%s%c", s, del);
} else {
bad |= bit;
}
flags &= ~bit;
}
if (bad) {
ds_put_format(ds, "0x%"PRIx32"%c", bad, del);
}
ds_chomp(ds, del);
}
void
format_flags_masked(struct ds *ds, const char *name,
const char *(*bit_to_string)(uint32_t), uint32_t flags,
uint32_t mask)
{
if (name) {
ds_put_format(ds, "%s=", name);
}
while (mask) {
uint32_t bit = rightmost_1bit(mask);
const char *s = bit_to_string(bit);
ds_put_format(ds, "%s%s", (flags & bit) ? "+" : "-",
s ? s : "[Unknown]");
mask &= ~bit;
}
}
void
flow_format(struct ds *ds, const struct flow *flow)
{
struct match match;
struct flow_wildcards *wc = &match.wc;
match_wc_init(&match, flow);
/* As this function is most often used for formatting a packet in a
* packet-in message, skip formatting the packet context fields that are
* all-zeroes to make the print-out easier on the eyes. This means that a
* missing context field implies a zero value for that field. This is
* similar to OpenFlow encoding of these fields, as the specification
* states that all-zeroes context fields should not be encoded in the
* packet-in messages. */
if (!flow->in_port.ofp_port) {
WC_UNMASK_FIELD(wc, in_port);
}
if (!flow->skb_priority) {
WC_UNMASK_FIELD(wc, skb_priority);
}
if (!flow->pkt_mark) {
WC_UNMASK_FIELD(wc, pkt_mark);
}
if (!flow->recirc_id) {
WC_UNMASK_FIELD(wc, recirc_id);
}
if (!flow->dp_hash) {
WC_UNMASK_FIELD(wc, dp_hash);
}
for (int i = 0; i < FLOW_N_REGS; i++) {
if (!flow->regs[i]) {
WC_UNMASK_FIELD(wc, regs[i]);
}
}
if (!flow->metadata) {
WC_UNMASK_FIELD(wc, metadata);
}
match_format(&match, ds, OFP_DEFAULT_PRIORITY);
}
void
flow_print(FILE *stream, const struct flow *flow)
{
char *s = flow_to_string(flow);
fputs(s, stream);
free(s);
}
/* flow_wildcards functions. */
/* Initializes 'wc' as a set of wildcards that matches every packet. */
void
flow_wildcards_init_catchall(struct flow_wildcards *wc)
{
memset(&wc->masks, 0, sizeof wc->masks);
}
/* Converts a flow into flow wildcards. It sets the wildcard masks based on
* the packet headers extracted to 'flow'. It will not set the mask for fields
* that do not make sense for the packet type. OpenFlow-only metadata is
* wildcarded, but other metadata is unconditionally exact-matched. */
void flow_wildcards_init_for_packet(struct flow_wildcards *wc,
const struct flow *flow)
{
memset(&wc->masks, 0x0, sizeof wc->masks);
/* Update this function whenever struct flow changes. */
BUILD_ASSERT_DECL(FLOW_WC_SEQ == 31);
if (flow->tunnel.ip_dst) {
if (flow->tunnel.flags & FLOW_TNL_F_KEY) {
WC_MASK_FIELD(wc, tunnel.tun_id);
}
WC_MASK_FIELD(wc, tunnel.ip_src);
WC_MASK_FIELD(wc, tunnel.ip_dst);
WC_MASK_FIELD(wc, tunnel.flags);
WC_MASK_FIELD(wc, tunnel.ip_tos);
WC_MASK_FIELD(wc, tunnel.ip_ttl);
WC_MASK_FIELD(wc, tunnel.tp_src);
WC_MASK_FIELD(wc, tunnel.tp_dst);
WC_MASK_FIELD(wc, tunnel.gbp_id);
WC_MASK_FIELD(wc, tunnel.gbp_flags);
} else if (flow->tunnel.tun_id) {
WC_MASK_FIELD(wc, tunnel.tun_id);
}
/* metadata, regs, and conj_id wildcarded. */
WC_MASK_FIELD(wc, skb_priority);
WC_MASK_FIELD(wc, pkt_mark);
WC_MASK_FIELD(wc, recirc_id);
WC_MASK_FIELD(wc, dp_hash);
WC_MASK_FIELD(wc, in_port);
/* actset_output wildcarded. */
WC_MASK_FIELD(wc, dl_dst);
WC_MASK_FIELD(wc, dl_src);
WC_MASK_FIELD(wc, dl_type);
WC_MASK_FIELD(wc, vlan_tci);
if (flow->dl_type == htons(ETH_TYPE_IP)) {
WC_MASK_FIELD(wc, nw_src);
WC_MASK_FIELD(wc, nw_dst);
} else if (flow->dl_type == htons(ETH_TYPE_IPV6)) {
WC_MASK_FIELD(wc, ipv6_src);
WC_MASK_FIELD(wc, ipv6_dst);
WC_MASK_FIELD(wc, ipv6_label);
} else if (flow->dl_type == htons(ETH_TYPE_ARP) ||
flow->dl_type == htons(ETH_TYPE_RARP)) {
WC_MASK_FIELD(wc, nw_src);
WC_MASK_FIELD(wc, nw_dst);
WC_MASK_FIELD(wc, nw_proto);
WC_MASK_FIELD(wc, arp_sha);
WC_MASK_FIELD(wc, arp_tha);
return;
} else if (eth_type_mpls(flow->dl_type)) {
for (int i = 0; i < FLOW_MAX_MPLS_LABELS; i++) {
WC_MASK_FIELD(wc, mpls_lse[i]);
if (flow->mpls_lse[i] & htonl(MPLS_BOS_MASK)) {
break;
}
}