forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathflow_dissector.c
1613 lines (1380 loc) · 43 KB
/
flow_dissector.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
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/export.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/if_vlan.h>
#include <net/dsa.h>
#include <net/dst_metadata.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/gre.h>
#include <net/pptp.h>
#include <net/tipc.h>
#include <linux/igmp.h>
#include <linux/icmp.h>
#include <linux/sctp.h>
#include <linux/dccp.h>
#include <linux/if_tunnel.h>
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
#include <linux/stddef.h>
#include <linux/if_ether.h>
#include <linux/mpls.h>
#include <linux/tcp.h>
#include <net/flow_dissector.h>
#include <scsi/fc/fc_fcoe.h>
#include <uapi/linux/batadv_packet.h>
#include <linux/bpf.h>
static DEFINE_MUTEX(flow_dissector_mutex);
static void dissector_set_key(struct flow_dissector *flow_dissector,
enum flow_dissector_key_id key_id)
{
flow_dissector->used_keys |= (1 << key_id);
}
void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
const struct flow_dissector_key *key,
unsigned int key_count)
{
unsigned int i;
memset(flow_dissector, 0, sizeof(*flow_dissector));
for (i = 0; i < key_count; i++, key++) {
/* User should make sure that every key target offset is withing
* boundaries of unsigned short.
*/
BUG_ON(key->offset > USHRT_MAX);
BUG_ON(dissector_uses_key(flow_dissector,
key->key_id));
dissector_set_key(flow_dissector, key->key_id);
flow_dissector->offset[key->key_id] = key->offset;
}
/* Ensure that the dissector always includes control and basic key.
* That way we are able to avoid handling lack of these in fast path.
*/
BUG_ON(!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_CONTROL));
BUG_ON(!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_BASIC));
}
EXPORT_SYMBOL(skb_flow_dissector_init);
int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
struct bpf_prog *prog)
{
struct bpf_prog *attached;
struct net *net;
net = current->nsproxy->net_ns;
mutex_lock(&flow_dissector_mutex);
attached = rcu_dereference_protected(net->flow_dissector_prog,
lockdep_is_held(&flow_dissector_mutex));
if (attached) {
/* Only one BPF program can be attached at a time */
mutex_unlock(&flow_dissector_mutex);
return -EEXIST;
}
rcu_assign_pointer(net->flow_dissector_prog, prog);
mutex_unlock(&flow_dissector_mutex);
return 0;
}
int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
{
struct bpf_prog *attached;
struct net *net;
net = current->nsproxy->net_ns;
mutex_lock(&flow_dissector_mutex);
attached = rcu_dereference_protected(net->flow_dissector_prog,
lockdep_is_held(&flow_dissector_mutex));
if (!attached) {
mutex_unlock(&flow_dissector_mutex);
return -ENOENT;
}
bpf_prog_put(attached);
RCU_INIT_POINTER(net->flow_dissector_prog, NULL);
mutex_unlock(&flow_dissector_mutex);
return 0;
}
/**
* skb_flow_get_be16 - extract be16 entity
* @skb: sk_buff to extract from
* @poff: offset to extract at
* @data: raw buffer pointer to the packet
* @hlen: packet header length
*
* The function will try to retrieve a be32 entity at
* offset poff
*/
static __be16 skb_flow_get_be16(const struct sk_buff *skb, int poff,
void *data, int hlen)
{
__be16 *u, _u;
u = __skb_header_pointer(skb, poff, sizeof(_u), data, hlen, &_u);
if (u)
return *u;
return 0;
}
/**
* __skb_flow_get_ports - extract the upper layer ports and return them
* @skb: sk_buff to extract the ports from
* @thoff: transport header offset
* @ip_proto: protocol for which to get port offset
* @data: raw buffer pointer to the packet, if NULL use skb->data
* @hlen: packet header length, if @data is NULL use skb_headlen(skb)
*
* The function will try to retrieve the ports at offset thoff + poff where poff
* is the protocol port offset returned from proto_ports_offset
*/
__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
void *data, int hlen)
{
int poff = proto_ports_offset(ip_proto);
if (!data) {
data = skb->data;
hlen = skb_headlen(skb);
}
if (poff >= 0) {
__be32 *ports, _ports;
ports = __skb_header_pointer(skb, thoff + poff,
sizeof(_ports), data, hlen, &_ports);
if (ports)
return *ports;
}
return 0;
}
EXPORT_SYMBOL(__skb_flow_get_ports);
static void
skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type,
struct flow_dissector *flow_dissector,
void *target_container)
{
struct flow_dissector_key_control *ctrl;
if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL))
return;
ctrl = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_CONTROL,
target_container);
ctrl->addr_type = type;
}
void
skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container)
{
struct ip_tunnel_info *info;
struct ip_tunnel_key *key;
/* A quick check to see if there might be something to do. */
if (!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_KEYID) &&
!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) &&
!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) &&
!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_CONTROL) &&
!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_PORTS) &&
!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_IP) &&
!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_OPTS))
return;
info = skb_tunnel_info(skb);
if (!info)
return;
key = &info->key;
switch (ip_tunnel_info_af(info)) {
case AF_INET:
skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS,
flow_dissector,
target_container);
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
struct flow_dissector_key_ipv4_addrs *ipv4;
ipv4 = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
target_container);
ipv4->src = key->u.ipv4.src;
ipv4->dst = key->u.ipv4.dst;
}
break;
case AF_INET6:
skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS,
flow_dissector,
target_container);
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
struct flow_dissector_key_ipv6_addrs *ipv6;
ipv6 = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS,
target_container);
ipv6->src = key->u.ipv6.src;
ipv6->dst = key->u.ipv6.dst;
}
break;
}
if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
struct flow_dissector_key_keyid *keyid;
keyid = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_KEYID,
target_container);
keyid->keyid = tunnel_id_to_key32(key->tun_id);
}
if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
struct flow_dissector_key_ports *tp;
tp = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_PORTS,
target_container);
tp->src = key->tp_src;
tp->dst = key->tp_dst;
}
if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
struct flow_dissector_key_ip *ip;
ip = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_IP,
target_container);
ip->tos = key->tos;
ip->ttl = key->ttl;
}
if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) {
struct flow_dissector_key_enc_opts *enc_opt;
enc_opt = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_OPTS,
target_container);
if (info->options_len) {
enc_opt->len = info->options_len;
ip_tunnel_info_opts_get(enc_opt->data, info);
enc_opt->dst_opt_type = info->key.tun_flags &
TUNNEL_OPTIONS_PRESENT;
}
}
}
EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
static enum flow_dissect_ret
__skb_flow_dissect_mpls(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, void *data, int nhoff, int hlen)
{
struct flow_dissector_key_keyid *key_keyid;
struct mpls_label *hdr, _hdr[2];
u32 entry, label;
if (!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_MPLS_ENTROPY) &&
!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS))
return FLOW_DISSECT_RET_OUT_GOOD;
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
hlen, &_hdr);
if (!hdr)
return FLOW_DISSECT_RET_OUT_BAD;
entry = ntohl(hdr[0].entry);
label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) {
struct flow_dissector_key_mpls *key_mpls;
key_mpls = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_MPLS,
target_container);
key_mpls->mpls_label = label;
key_mpls->mpls_ttl = (entry & MPLS_LS_TTL_MASK)
>> MPLS_LS_TTL_SHIFT;
key_mpls->mpls_tc = (entry & MPLS_LS_TC_MASK)
>> MPLS_LS_TC_SHIFT;
key_mpls->mpls_bos = (entry & MPLS_LS_S_MASK)
>> MPLS_LS_S_SHIFT;
}
if (label == MPLS_LABEL_ENTROPY) {
key_keyid = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
target_container);
key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK);
}
return FLOW_DISSECT_RET_OUT_GOOD;
}
static enum flow_dissect_ret
__skb_flow_dissect_arp(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, void *data, int nhoff, int hlen)
{
struct flow_dissector_key_arp *key_arp;
struct {
unsigned char ar_sha[ETH_ALEN];
unsigned char ar_sip[4];
unsigned char ar_tha[ETH_ALEN];
unsigned char ar_tip[4];
} *arp_eth, _arp_eth;
const struct arphdr *arp;
struct arphdr _arp;
if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP))
return FLOW_DISSECT_RET_OUT_GOOD;
arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
hlen, &_arp);
if (!arp)
return FLOW_DISSECT_RET_OUT_BAD;
if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
arp->ar_pro != htons(ETH_P_IP) ||
arp->ar_hln != ETH_ALEN ||
arp->ar_pln != 4 ||
(arp->ar_op != htons(ARPOP_REPLY) &&
arp->ar_op != htons(ARPOP_REQUEST)))
return FLOW_DISSECT_RET_OUT_BAD;
arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
sizeof(_arp_eth), data,
hlen, &_arp_eth);
if (!arp_eth)
return FLOW_DISSECT_RET_OUT_BAD;
key_arp = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ARP,
target_container);
memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip));
memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip));
/* Only store the lower byte of the opcode;
* this covers ARPOP_REPLY and ARPOP_REQUEST.
*/
key_arp->op = ntohs(arp->ar_op) & 0xff;
ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
return FLOW_DISSECT_RET_OUT_GOOD;
}
static enum flow_dissect_ret
__skb_flow_dissect_gre(const struct sk_buff *skb,
struct flow_dissector_key_control *key_control,
struct flow_dissector *flow_dissector,
void *target_container, void *data,
__be16 *p_proto, int *p_nhoff, int *p_hlen,
unsigned int flags)
{
struct flow_dissector_key_keyid *key_keyid;
struct gre_base_hdr *hdr, _hdr;
int offset = 0;
u16 gre_ver;
hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr),
data, *p_hlen, &_hdr);
if (!hdr)
return FLOW_DISSECT_RET_OUT_BAD;
/* Only look inside GRE without routing */
if (hdr->flags & GRE_ROUTING)
return FLOW_DISSECT_RET_OUT_GOOD;
/* Only look inside GRE for version 0 and 1 */
gre_ver = ntohs(hdr->flags & GRE_VERSION);
if (gre_ver > 1)
return FLOW_DISSECT_RET_OUT_GOOD;
*p_proto = hdr->protocol;
if (gre_ver) {
/* Version1 must be PPTP, and check the flags */
if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
return FLOW_DISSECT_RET_OUT_GOOD;
}
offset += sizeof(struct gre_base_hdr);
if (hdr->flags & GRE_CSUM)
offset += FIELD_SIZEOF(struct gre_full_hdr, csum) +
FIELD_SIZEOF(struct gre_full_hdr, reserved1);
if (hdr->flags & GRE_KEY) {
const __be32 *keyid;
__be32 _keyid;
keyid = __skb_header_pointer(skb, *p_nhoff + offset,
sizeof(_keyid),
data, *p_hlen, &_keyid);
if (!keyid)
return FLOW_DISSECT_RET_OUT_BAD;
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_GRE_KEYID)) {
key_keyid = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_GRE_KEYID,
target_container);
if (gre_ver == 0)
key_keyid->keyid = *keyid;
else
key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
}
offset += FIELD_SIZEOF(struct gre_full_hdr, key);
}
if (hdr->flags & GRE_SEQ)
offset += FIELD_SIZEOF(struct pptp_gre_header, seq);
if (gre_ver == 0) {
if (*p_proto == htons(ETH_P_TEB)) {
const struct ethhdr *eth;
struct ethhdr _eth;
eth = __skb_header_pointer(skb, *p_nhoff + offset,
sizeof(_eth),
data, *p_hlen, &_eth);
if (!eth)
return FLOW_DISSECT_RET_OUT_BAD;
*p_proto = eth->h_proto;
offset += sizeof(*eth);
/* Cap headers that we access via pointers at the
* end of the Ethernet header as our maximum alignment
* at that point is only 2 bytes.
*/
if (NET_IP_ALIGN)
*p_hlen = *p_nhoff + offset;
}
} else { /* version 1, must be PPTP */
u8 _ppp_hdr[PPP_HDRLEN];
u8 *ppp_hdr;
if (hdr->flags & GRE_ACK)
offset += FIELD_SIZEOF(struct pptp_gre_header, ack);
ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset,
sizeof(_ppp_hdr),
data, *p_hlen, _ppp_hdr);
if (!ppp_hdr)
return FLOW_DISSECT_RET_OUT_BAD;
switch (PPP_PROTOCOL(ppp_hdr)) {
case PPP_IP:
*p_proto = htons(ETH_P_IP);
break;
case PPP_IPV6:
*p_proto = htons(ETH_P_IPV6);
break;
default:
/* Could probably catch some more like MPLS */
break;
}
offset += PPP_HDRLEN;
}
*p_nhoff += offset;
key_control->flags |= FLOW_DIS_ENCAPSULATION;
if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
return FLOW_DISSECT_RET_OUT_GOOD;
return FLOW_DISSECT_RET_PROTO_AGAIN;
}
/**
* __skb_flow_dissect_batadv() - dissect batman-adv header
* @skb: sk_buff to with the batman-adv header
* @key_control: flow dissectors control key
* @data: raw buffer pointer to the packet, if NULL use skb->data
* @p_proto: pointer used to update the protocol to process next
* @p_nhoff: pointer used to update inner network header offset
* @hlen: packet header length
* @flags: any combination of FLOW_DISSECTOR_F_*
*
* ETH_P_BATMAN packets are tried to be dissected. Only
* &struct batadv_unicast packets are actually processed because they contain an
* inner ethernet header and are usually followed by actual network header. This
* allows the flow dissector to continue processing the packet.
*
* Return: FLOW_DISSECT_RET_PROTO_AGAIN when &struct batadv_unicast was found,
* FLOW_DISSECT_RET_OUT_GOOD when dissector should stop after encapsulation,
* otherwise FLOW_DISSECT_RET_OUT_BAD
*/
static enum flow_dissect_ret
__skb_flow_dissect_batadv(const struct sk_buff *skb,
struct flow_dissector_key_control *key_control,
void *data, __be16 *p_proto, int *p_nhoff, int hlen,
unsigned int flags)
{
struct {
struct batadv_unicast_packet batadv_unicast;
struct ethhdr eth;
} *hdr, _hdr;
hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, hlen,
&_hdr);
if (!hdr)
return FLOW_DISSECT_RET_OUT_BAD;
if (hdr->batadv_unicast.version != BATADV_COMPAT_VERSION)
return FLOW_DISSECT_RET_OUT_BAD;
if (hdr->batadv_unicast.packet_type != BATADV_UNICAST)
return FLOW_DISSECT_RET_OUT_BAD;
*p_proto = hdr->eth.h_proto;
*p_nhoff += sizeof(*hdr);
key_control->flags |= FLOW_DIS_ENCAPSULATION;
if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
return FLOW_DISSECT_RET_OUT_GOOD;
return FLOW_DISSECT_RET_PROTO_AGAIN;
}
static void
__skb_flow_dissect_tcp(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, void *data, int thoff, int hlen)
{
struct flow_dissector_key_tcp *key_tcp;
struct tcphdr *th, _th;
if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP))
return;
th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th);
if (!th)
return;
if (unlikely(__tcp_hdrlen(th) < sizeof(_th)))
return;
key_tcp = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_TCP,
target_container);
key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF));
}
static void
__skb_flow_dissect_ipv4(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, void *data, const struct iphdr *iph)
{
struct flow_dissector_key_ip *key_ip;
if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP))
return;
key_ip = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IP,
target_container);
key_ip->tos = iph->tos;
key_ip->ttl = iph->ttl;
}
static void
__skb_flow_dissect_ipv6(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, void *data, const struct ipv6hdr *iph)
{
struct flow_dissector_key_ip *key_ip;
if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP))
return;
key_ip = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IP,
target_container);
key_ip->tos = ipv6_get_dsfield(iph);
key_ip->ttl = iph->hop_limit;
}
/* Maximum number of protocol headers that can be parsed in
* __skb_flow_dissect
*/
#define MAX_FLOW_DISSECT_HDRS 15
static bool skb_flow_dissect_allowed(int *num_hdrs)
{
++*num_hdrs;
return (*num_hdrs <= MAX_FLOW_DISSECT_HDRS);
}
static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
struct flow_dissector *flow_dissector,
void *target_container)
{
struct flow_dissector_key_control *key_control;
struct flow_dissector_key_basic *key_basic;
struct flow_dissector_key_addrs *key_addrs;
struct flow_dissector_key_ports *key_ports;
key_control = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_CONTROL,
target_container);
key_control->thoff = flow_keys->thoff;
if (flow_keys->is_frag)
key_control->flags |= FLOW_DIS_IS_FRAGMENT;
if (flow_keys->is_first_frag)
key_control->flags |= FLOW_DIS_FIRST_FRAG;
if (flow_keys->is_encap)
key_control->flags |= FLOW_DIS_ENCAPSULATION;
key_basic = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_BASIC,
target_container);
key_basic->n_proto = flow_keys->n_proto;
key_basic->ip_proto = flow_keys->ip_proto;
if (flow_keys->addr_proto == ETH_P_IP &&
dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
key_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IPV4_ADDRS,
target_container);
key_addrs->v4addrs.src = flow_keys->ipv4_src;
key_addrs->v4addrs.dst = flow_keys->ipv4_dst;
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
} else if (flow_keys->addr_proto == ETH_P_IPV6 &&
dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
key_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IPV6_ADDRS,
target_container);
memcpy(&key_addrs->v6addrs, &flow_keys->ipv6_src,
sizeof(key_addrs->v6addrs));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
}
if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) {
key_ports = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_PORTS,
target_container);
key_ports->src = flow_keys->sport;
key_ports->dst = flow_keys->dport;
}
}
/**
* __skb_flow_dissect - extract the flow_keys struct and return it
* @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
* @flow_dissector: list of keys to dissect
* @target_container: target structure to put dissected values into
* @data: raw buffer pointer to the packet, if NULL use skb->data
* @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
* @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
* @hlen: packet header length, if @data is NULL use skb_headlen(skb)
*
* The function will try to retrieve individual keys into target specified
* by flow_dissector from either the skbuff or a raw buffer specified by the
* rest parameters.
*
* Caller must take care of zeroing target container memory.
*/
bool __skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container,
void *data, __be16 proto, int nhoff, int hlen,
unsigned int flags)
{
struct flow_dissector_key_control *key_control;
struct flow_dissector_key_basic *key_basic;
struct flow_dissector_key_addrs *key_addrs;
struct flow_dissector_key_ports *key_ports;
struct flow_dissector_key_icmp *key_icmp;
struct flow_dissector_key_tags *key_tags;
struct flow_dissector_key_vlan *key_vlan;
enum flow_dissect_ret fdret;
enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
struct bpf_prog *attached = NULL;
int num_hdrs = 0;
u8 ip_proto = 0;
bool ret;
if (!data) {
data = skb->data;
proto = skb_vlan_tag_present(skb) ?
skb->vlan_proto : skb->protocol;
nhoff = skb_network_offset(skb);
hlen = skb_headlen(skb);
#if IS_ENABLED(CONFIG_NET_DSA)
if (unlikely(skb->dev && netdev_uses_dsa(skb->dev))) {
const struct dsa_device_ops *ops;
int offset;
ops = skb->dev->dsa_ptr->tag_ops;
if (ops->flow_dissect &&
!ops->flow_dissect(skb, &proto, &offset)) {
hlen -= offset;
nhoff += offset;
}
}
#endif
}
/* It is ensured by skb_flow_dissector_init() that control key will
* be always present.
*/
key_control = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_CONTROL,
target_container);
/* It is ensured by skb_flow_dissector_init() that basic key will
* be always present.
*/
key_basic = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_BASIC,
target_container);
rcu_read_lock();
if (skb) {
if (skb->dev)
attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog);
else if (skb->sk)
attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog);
else
WARN_ON_ONCE(1);
}
if (attached) {
/* Note that even though the const qualifier is discarded
* throughout the execution of the BPF program, all changes(the
* control block) are reverted after the BPF program returns.
* Therefore, __skb_flow_dissect does not alter the skb.
*/
struct bpf_flow_keys flow_keys = {};
struct bpf_skb_data_end cb_saved;
struct bpf_skb_data_end *cb;
u32 result;
cb = (struct bpf_skb_data_end *)skb->cb;
/* Save Control Block */
memcpy(&cb_saved, cb, sizeof(cb_saved));
memset(cb, 0, sizeof(cb_saved));
/* Pass parameters to the BPF program */
cb->qdisc_cb.flow_keys = &flow_keys;
flow_keys.nhoff = nhoff;
flow_keys.thoff = nhoff;
bpf_compute_data_pointers((struct sk_buff *)skb);
result = BPF_PROG_RUN(attached, skb);
/* Restore state */
memcpy(cb, &cb_saved, sizeof(cb_saved));
flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len);
flow_keys.thoff = clamp_t(u16, flow_keys.thoff,
flow_keys.nhoff, skb->len);
__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
target_container);
rcu_read_unlock();
return result == BPF_OK;
}
rcu_read_unlock();
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
struct ethhdr *eth = eth_hdr(skb);
struct flow_dissector_key_eth_addrs *key_eth_addrs;
key_eth_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS,
target_container);
memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs));
}
proto_again:
fdret = FLOW_DISSECT_RET_CONTINUE;
switch (proto) {
case htons(ETH_P_IP): {
const struct iphdr *iph;
struct iphdr _iph;
iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
if (!iph || iph->ihl < 5) {
fdret = FLOW_DISSECT_RET_OUT_BAD;
break;
}
nhoff += iph->ihl * 4;
ip_proto = iph->protocol;
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
key_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IPV4_ADDRS,
target_container);
memcpy(&key_addrs->v4addrs, &iph->saddr,
sizeof(key_addrs->v4addrs));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
}
if (ip_is_fragment(iph)) {
key_control->flags |= FLOW_DIS_IS_FRAGMENT;
if (iph->frag_off & htons(IP_OFFSET)) {
fdret = FLOW_DISSECT_RET_OUT_GOOD;
break;
} else {
key_control->flags |= FLOW_DIS_FIRST_FRAG;
if (!(flags &
FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) {
fdret = FLOW_DISSECT_RET_OUT_GOOD;
break;
}
}
}
__skb_flow_dissect_ipv4(skb, flow_dissector,
target_container, data, iph);
if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) {
fdret = FLOW_DISSECT_RET_OUT_GOOD;
break;
}
break;
}
case htons(ETH_P_IPV6): {
const struct ipv6hdr *iph;
struct ipv6hdr _iph;
iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
if (!iph) {
fdret = FLOW_DISSECT_RET_OUT_BAD;
break;
}
ip_proto = iph->nexthdr;
nhoff += sizeof(struct ipv6hdr);
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
key_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IPV6_ADDRS,
target_container);
memcpy(&key_addrs->v6addrs, &iph->saddr,
sizeof(key_addrs->v6addrs));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
}
if ((dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_FLOW_LABEL) ||
(flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) &&
ip6_flowlabel(iph)) {
__be32 flow_label = ip6_flowlabel(iph);
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
key_tags = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_FLOW_LABEL,
target_container);
key_tags->flow_label = ntohl(flow_label);
}
if (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) {
fdret = FLOW_DISSECT_RET_OUT_GOOD;
break;
}
}
__skb_flow_dissect_ipv6(skb, flow_dissector,
target_container, data, iph);
if (flags & FLOW_DISSECTOR_F_STOP_AT_L3)
fdret = FLOW_DISSECT_RET_OUT_GOOD;
break;
}
case htons(ETH_P_8021AD):
case htons(ETH_P_8021Q): {
const struct vlan_hdr *vlan = NULL;
struct vlan_hdr _vlan;
__be16 saved_vlan_tpid = proto;
if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX &&
skb && skb_vlan_tag_present(skb)) {
proto = skb->protocol;
} else {
vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan),
data, hlen, &_vlan);
if (!vlan) {
fdret = FLOW_DISSECT_RET_OUT_BAD;
break;
}
proto = vlan->h_vlan_encapsulated_proto;
nhoff += sizeof(*vlan);
}
if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) {
dissector_vlan = FLOW_DISSECTOR_KEY_VLAN;
} else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) {
dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN;
} else {
fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
break;
}
if (dissector_uses_key(flow_dissector, dissector_vlan)) {
key_vlan = skb_flow_dissector_target(flow_dissector,
dissector_vlan,
target_container);
if (!vlan) {
key_vlan->vlan_id = skb_vlan_tag_get_id(skb);
key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb);
} else {
key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) &
VLAN_VID_MASK;
key_vlan->vlan_priority =
(ntohs(vlan->h_vlan_TCI) &
VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
}
key_vlan->vlan_tpid = saved_vlan_tpid;
}
fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
break;
}
case htons(ETH_P_PPP_SES): {
struct {
struct pppoe_hdr hdr;
__be16 proto;
} *hdr, _hdr;
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr) {
fdret = FLOW_DISSECT_RET_OUT_BAD;
break;
}
proto = hdr->proto;
nhoff += PPPOE_SES_HLEN;
switch (proto) {
case htons(PPP_IP):
proto = htons(ETH_P_IP);
fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
break;
case htons(PPP_IPV6):
proto = htons(ETH_P_IPV6);
fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
break;
default:
fdret = FLOW_DISSECT_RET_OUT_BAD;
break;
}
break;
}