forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathactions.c
1583 lines (1313 loc) · 39 KB
/
actions.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) 2007-2017 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/skbuff.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/openvswitch.h>
#include <linux/netfilter_ipv6.h>
#include <linux/sctp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/in6.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <net/dst.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/mpls.h>
#include <net/sctp/checksum.h>
#include "datapath.h"
#include "flow.h"
#include "conntrack.h"
#include "vport.h"
#include "flow_netlink.h"
struct deferred_action {
struct sk_buff *skb;
const struct nlattr *actions;
int actions_len;
/* Store pkt_key clone when creating deferred action. */
struct sw_flow_key pkt_key;
};
#define MAX_L2_LEN (VLAN_ETH_HLEN + 3 * MPLS_HLEN)
struct ovs_frag_data {
unsigned long dst;
struct vport *vport;
struct ovs_skb_cb cb;
__be16 inner_protocol;
u16 network_offset; /* valid only for MPLS */
u16 vlan_tci;
__be16 vlan_proto;
unsigned int l2_len;
u8 mac_proto;
u8 l2_data[MAX_L2_LEN];
};
static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
#define DEFERRED_ACTION_FIFO_SIZE 10
#define OVS_RECURSION_LIMIT 5
#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2)
struct action_fifo {
int head;
int tail;
/* Deferred action fifo queue storage. */
struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
};
struct action_flow_keys {
struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
};
static struct action_fifo __percpu *action_fifos;
static struct action_flow_keys __percpu *flow_keys;
static DEFINE_PER_CPU(int, exec_actions_level);
/* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
* space. Return NULL if out of key spaces.
*/
static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
{
struct action_flow_keys *keys = this_cpu_ptr(flow_keys);
int level = this_cpu_read(exec_actions_level);
struct sw_flow_key *key = NULL;
if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
key = &keys->key[level - 1];
*key = *key_;
}
return key;
}
static void action_fifo_init(struct action_fifo *fifo)
{
fifo->head = 0;
fifo->tail = 0;
}
static bool action_fifo_is_empty(const struct action_fifo *fifo)
{
return (fifo->head == fifo->tail);
}
static struct deferred_action *action_fifo_get(struct action_fifo *fifo)
{
if (action_fifo_is_empty(fifo))
return NULL;
return &fifo->fifo[fifo->tail++];
}
static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
{
if (fifo->head >= DEFERRED_ACTION_FIFO_SIZE - 1)
return NULL;
return &fifo->fifo[fifo->head++];
}
/* Return true if fifo is not full */
static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
const struct sw_flow_key *key,
const struct nlattr *actions,
const int actions_len)
{
struct action_fifo *fifo;
struct deferred_action *da;
fifo = this_cpu_ptr(action_fifos);
da = action_fifo_put(fifo);
if (da) {
da->skb = skb;
da->actions = actions;
da->actions_len = actions_len;
da->pkt_key = *key;
}
return da;
}
static void invalidate_flow_key(struct sw_flow_key *key)
{
key->mac_proto |= SW_FLOW_KEY_INVALID;
}
static bool is_flow_key_valid(const struct sw_flow_key *key)
{
return !(key->mac_proto & SW_FLOW_KEY_INVALID);
}
static int clone_execute(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
u32 recirc_id,
const struct nlattr *actions, int len,
bool last, bool clone_flow_key);
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
const struct nlattr *attr, int len);
static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
__be16 ethertype)
{
if (skb->ip_summed == CHECKSUM_COMPLETE) {
__be16 diff[] = { ~(hdr->h_proto), ethertype };
skb->csum = ~csum_partial((char *)diff, sizeof(diff),
~skb->csum);
}
hdr->h_proto = ethertype;
}
static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_mpls *mpls)
{
struct mpls_shim_hdr *new_mpls_lse;
/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
if (skb->encapsulation)
return -ENOTSUPP;
if (skb_cow_head(skb, MPLS_HLEN) < 0)
return -ENOMEM;
if (!skb->inner_protocol) {
skb_set_inner_network_header(skb, skb->mac_len);
skb_set_inner_protocol(skb, skb->protocol);
}
skb_push(skb, MPLS_HLEN);
memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->mac_len);
new_mpls_lse = mpls_hdr(skb);
new_mpls_lse->label_stack_entry = mpls->mpls_lse;
skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET)
update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
skb->protocol = mpls->mpls_ethertype;
invalidate_flow_key(key);
return 0;
}
static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const __be16 ethertype)
{
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->mac_len);
if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
struct ethhdr *hdr;
/* mpls_hdr() is used to locate the ethertype field correctly in the
* presence of VLAN tags.
*/
hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
update_ethertype(skb, hdr, ethertype);
}
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
invalidate_flow_key(key);
return 0;
}
static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
const __be32 *mpls_lse, const __be32 *mask)
{
struct mpls_shim_hdr *stack;
__be32 lse;
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
stack = mpls_hdr(skb);
lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
if (skb->ip_summed == CHECKSUM_COMPLETE) {
__be32 diff[] = { ~(stack->label_stack_entry), lse };
skb->csum = ~csum_partial((char *)diff, sizeof(diff),
~skb->csum);
}
stack->label_stack_entry = lse;
flow_key->mpls.top_lse = lse;
return 0;
}
static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
{
int err;
err = skb_vlan_pop(skb);
if (skb_vlan_tag_present(skb)) {
invalidate_flow_key(key);
} else {
key->eth.vlan.tci = 0;
key->eth.vlan.tpid = 0;
}
return err;
}
static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_vlan *vlan)
{
if (skb_vlan_tag_present(skb)) {
invalidate_flow_key(key);
} else {
key->eth.vlan.tci = vlan->vlan_tci;
key->eth.vlan.tpid = vlan->vlan_tpid;
}
return skb_vlan_push(skb, vlan->vlan_tpid,
ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
}
/* 'src' is already properly masked. */
static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_)
{
u16 *dst = (u16 *)dst_;
const u16 *src = (const u16 *)src_;
const u16 *mask = (const u16 *)mask_;
OVS_SET_MASKED(dst[0], src[0], mask[0]);
OVS_SET_MASKED(dst[1], src[1], mask[1]);
OVS_SET_MASKED(dst[2], src[2], mask[2]);
}
static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_ethernet *key,
const struct ovs_key_ethernet *mask)
{
int err;
err = skb_ensure_writable(skb, ETH_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
ether_addr_copy_masked(eth_hdr(skb)->h_source, key->eth_src,
mask->eth_src);
ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
mask->eth_dst);
skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
return 0;
}
/* pop_eth does not support VLAN packets as this action is never called
* for them.
*/
static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
{
skb_pull_rcsum(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
/* safe right before invalidate_flow_key */
key->mac_proto = MAC_PROTO_NONE;
invalidate_flow_key(key);
return 0;
}
static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_eth *ethh)
{
struct ethhdr *hdr;
/* Add the new Ethernet header */
if (skb_cow_head(skb, ETH_HLEN) < 0)
return -ENOMEM;
skb_push(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
hdr = eth_hdr(skb);
ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
hdr->h_proto = skb->protocol;
skb_postpush_rcsum(skb, hdr, ETH_HLEN);
/* safe right before invalidate_flow_key */
key->mac_proto = MAC_PROTO_ETHERNET;
invalidate_flow_key(key);
return 0;
}
static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key,
const struct nshhdr *nh)
{
int err;
err = nsh_push(skb, nh);
if (err)
return err;
/* safe right before invalidate_flow_key */
key->mac_proto = MAC_PROTO_NONE;
invalidate_flow_key(key);
return 0;
}
static int pop_nsh(struct sk_buff *skb, struct sw_flow_key *key)
{
int err;
err = nsh_pop(skb);
if (err)
return err;
/* safe right before invalidate_flow_key */
if (skb->protocol == htons(ETH_P_TEB))
key->mac_proto = MAC_PROTO_ETHERNET;
else
key->mac_proto = MAC_PROTO_NONE;
invalidate_flow_key(key);
return 0;
}
static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
__be32 addr, __be32 new_addr)
{
int transport_len = skb->len - skb_transport_offset(skb);
if (nh->frag_off & htons(IP_OFFSET))
return;
if (nh->protocol == IPPROTO_TCP) {
if (likely(transport_len >= sizeof(struct tcphdr)))
inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
addr, new_addr, true);
} else if (nh->protocol == IPPROTO_UDP) {
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&uh->check, skb,
addr, new_addr, true);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
}
}
}
static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
__be32 *addr, __be32 new_addr)
{
update_ip_l4_checksum(skb, nh, *addr, new_addr);
csum_replace4(&nh->check, *addr, new_addr);
skb_clear_hash(skb);
*addr = new_addr;
}
static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
__be32 addr[4], const __be32 new_addr[4])
{
int transport_len = skb->len - skb_transport_offset(skb);
if (l4_proto == NEXTHDR_TCP) {
if (likely(transport_len >= sizeof(struct tcphdr)))
inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb,
addr, new_addr, true);
} else if (l4_proto == NEXTHDR_UDP) {
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace16(&uh->check, skb,
addr, new_addr, true);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
}
} else if (l4_proto == NEXTHDR_ICMP) {
if (likely(transport_len >= sizeof(struct icmp6hdr)))
inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum,
skb, addr, new_addr, true);
}
}
static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4],
const __be32 mask[4], __be32 masked[4])
{
masked[0] = OVS_MASKED(old[0], addr[0], mask[0]);
masked[1] = OVS_MASKED(old[1], addr[1], mask[1]);
masked[2] = OVS_MASKED(old[2], addr[2], mask[2]);
masked[3] = OVS_MASKED(old[3], addr[3], mask[3]);
}
static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
__be32 addr[4], const __be32 new_addr[4],
bool recalculate_csum)
{
if (recalculate_csum)
update_ipv6_checksum(skb, l4_proto, addr, new_addr);
skb_clear_hash(skb);
memcpy(addr, new_addr, sizeof(__be32[4]));
}
static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
{
/* Bits 21-24 are always unmasked, so this retains their values. */
OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
}
static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
u8 mask)
{
new_ttl = OVS_MASKED(nh->ttl, new_ttl, mask);
csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
nh->ttl = new_ttl;
}
static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_ipv4 *key,
const struct ovs_key_ipv4 *mask)
{
struct iphdr *nh;
__be32 new_addr;
int err;
err = skb_ensure_writable(skb, skb_network_offset(skb) +
sizeof(struct iphdr));
if (unlikely(err))
return err;
nh = ip_hdr(skb);
/* Setting an IP addresses is typically only a side effect of
* matching on them in the current userspace implementation, so it
* makes sense to check if the value actually changed.
*/
if (mask->ipv4_src) {
new_addr = OVS_MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src);
if (unlikely(new_addr != nh->saddr)) {
set_ip_addr(skb, nh, &nh->saddr, new_addr);
flow_key->ipv4.addr.src = new_addr;
}
}
if (mask->ipv4_dst) {
new_addr = OVS_MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst);
if (unlikely(new_addr != nh->daddr)) {
set_ip_addr(skb, nh, &nh->daddr, new_addr);
flow_key->ipv4.addr.dst = new_addr;
}
}
if (mask->ipv4_tos) {
ipv4_change_dsfield(nh, ~mask->ipv4_tos, key->ipv4_tos);
flow_key->ip.tos = nh->tos;
}
if (mask->ipv4_ttl) {
set_ip_ttl(skb, nh, key->ipv4_ttl, mask->ipv4_ttl);
flow_key->ip.ttl = nh->ttl;
}
return 0;
}
static bool is_ipv6_mask_nonzero(const __be32 addr[4])
{
return !!(addr[0] | addr[1] | addr[2] | addr[3]);
}
static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_ipv6 *key,
const struct ovs_key_ipv6 *mask)
{
struct ipv6hdr *nh;
int err;
err = skb_ensure_writable(skb, skb_network_offset(skb) +
sizeof(struct ipv6hdr));
if (unlikely(err))
return err;
nh = ipv6_hdr(skb);
/* Setting an IP addresses is typically only a side effect of
* matching on them in the current userspace implementation, so it
* makes sense to check if the value actually changed.
*/
if (is_ipv6_mask_nonzero(mask->ipv6_src)) {
__be32 *saddr = (__be32 *)&nh->saddr;
__be32 masked[4];
mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked,
true);
memcpy(&flow_key->ipv6.addr.src, masked,
sizeof(flow_key->ipv6.addr.src));
}
}
if (is_ipv6_mask_nonzero(mask->ipv6_dst)) {
unsigned int offset = 0;
int flags = IP6_FH_F_SKIP_RH;
bool recalc_csum = true;
__be32 *daddr = (__be32 *)&nh->daddr;
__be32 masked[4];
mask_ipv6_addr(daddr, key->ipv6_dst, mask->ipv6_dst, masked);
if (unlikely(memcmp(daddr, masked, sizeof(masked)))) {
if (ipv6_ext_hdr(nh->nexthdr))
recalc_csum = (ipv6_find_hdr(skb, &offset,
NEXTHDR_ROUTING,
NULL, &flags)
!= NEXTHDR_ROUTING);
set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked,
recalc_csum);
memcpy(&flow_key->ipv6.addr.dst, masked,
sizeof(flow_key->ipv6.addr.dst));
}
}
if (mask->ipv6_tclass) {
ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
flow_key->ip.tos = ipv6_get_dsfield(nh);
}
if (mask->ipv6_label) {
set_ipv6_fl(nh, ntohl(key->ipv6_label),
ntohl(mask->ipv6_label));
flow_key->ipv6.label =
*(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
}
if (mask->ipv6_hlimit) {
OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit,
mask->ipv6_hlimit);
flow_key->ip.ttl = nh->hop_limit;
}
return 0;
}
static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct nlattr *a)
{
struct nshhdr *nh;
size_t length;
int err;
u8 flags;
u8 ttl;
int i;
struct ovs_key_nsh key;
struct ovs_key_nsh mask;
err = nsh_key_from_nlattr(a, &key, &mask);
if (err)
return err;
/* Make sure the NSH base header is there */
if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN))
return -ENOMEM;
nh = nsh_hdr(skb);
length = nsh_hdr_len(nh);
/* Make sure the whole NSH header is there */
err = skb_ensure_writable(skb, skb_network_offset(skb) +
length);
if (unlikely(err))
return err;
nh = nsh_hdr(skb);
skb_postpull_rcsum(skb, nh, length);
flags = nsh_get_flags(nh);
flags = OVS_MASKED(flags, key.base.flags, mask.base.flags);
flow_key->nsh.base.flags = flags;
ttl = nsh_get_ttl(nh);
ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl);
flow_key->nsh.base.ttl = ttl;
nsh_set_flags_and_ttl(nh, flags, ttl);
nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr,
mask.base.path_hdr);
flow_key->nsh.base.path_hdr = nh->path_hdr;
switch (nh->mdtype) {
case NSH_M_TYPE1:
for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) {
nh->md1.context[i] =
OVS_MASKED(nh->md1.context[i], key.context[i],
mask.context[i]);
}
memcpy(flow_key->nsh.context, nh->md1.context,
sizeof(nh->md1.context));
break;
case NSH_M_TYPE2:
memset(flow_key->nsh.context, 0,
sizeof(flow_key->nsh.context));
break;
default:
return -EINVAL;
}
skb_postpush_rcsum(skb, nh, length);
return 0;
}
/* Must follow skb_ensure_writable() since that can move the skb data. */
static void set_tp_port(struct sk_buff *skb, __be16 *port,
__be16 new_port, __sum16 *check)
{
inet_proto_csum_replace2(check, skb, *port, new_port, false);
*port = new_port;
}
static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_udp *key,
const struct ovs_key_udp *mask)
{
struct udphdr *uh;
__be16 src, dst;
int err;
err = skb_ensure_writable(skb, skb_transport_offset(skb) +
sizeof(struct udphdr));
if (unlikely(err))
return err;
uh = udp_hdr(skb);
/* Either of the masks is non-zero, so do not bother checking them. */
src = OVS_MASKED(uh->source, key->udp_src, mask->udp_src);
dst = OVS_MASKED(uh->dest, key->udp_dst, mask->udp_dst);
if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
if (likely(src != uh->source)) {
set_tp_port(skb, &uh->source, src, &uh->check);
flow_key->tp.src = src;
}
if (likely(dst != uh->dest)) {
set_tp_port(skb, &uh->dest, dst, &uh->check);
flow_key->tp.dst = dst;
}
if (unlikely(!uh->check))
uh->check = CSUM_MANGLED_0;
} else {
uh->source = src;
uh->dest = dst;
flow_key->tp.src = src;
flow_key->tp.dst = dst;
}
skb_clear_hash(skb);
return 0;
}
static int set_tcp(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_tcp *key,
const struct ovs_key_tcp *mask)
{
struct tcphdr *th;
__be16 src, dst;
int err;
err = skb_ensure_writable(skb, skb_transport_offset(skb) +
sizeof(struct tcphdr));
if (unlikely(err))
return err;
th = tcp_hdr(skb);
src = OVS_MASKED(th->source, key->tcp_src, mask->tcp_src);
if (likely(src != th->source)) {
set_tp_port(skb, &th->source, src, &th->check);
flow_key->tp.src = src;
}
dst = OVS_MASKED(th->dest, key->tcp_dst, mask->tcp_dst);
if (likely(dst != th->dest)) {
set_tp_port(skb, &th->dest, dst, &th->check);
flow_key->tp.dst = dst;
}
skb_clear_hash(skb);
return 0;
}
static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_sctp *key,
const struct ovs_key_sctp *mask)
{
unsigned int sctphoff = skb_transport_offset(skb);
struct sctphdr *sh;
__le32 old_correct_csum, new_csum, old_csum;
int err;
err = skb_ensure_writable(skb, sctphoff + sizeof(struct sctphdr));
if (unlikely(err))
return err;
sh = sctp_hdr(skb);
old_csum = sh->checksum;
old_correct_csum = sctp_compute_cksum(skb, sctphoff);
sh->source = OVS_MASKED(sh->source, key->sctp_src, mask->sctp_src);
sh->dest = OVS_MASKED(sh->dest, key->sctp_dst, mask->sctp_dst);
new_csum = sctp_compute_cksum(skb, sctphoff);
/* Carry any checksum errors through. */
sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
skb_clear_hash(skb);
flow_key->tp.src = sh->source;
flow_key->tp.dst = sh->dest;
return 0;
}
static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
struct vport *vport = data->vport;
if (skb_cow_head(skb, data->l2_len) < 0) {
kfree_skb(skb);
return -ENOMEM;
}
__skb_dst_copy(skb, data->dst);
*OVS_CB(skb) = data->cb;
skb->inner_protocol = data->inner_protocol;
if (data->vlan_tci & VLAN_CFI_MASK)
__vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci & ~VLAN_CFI_MASK);
else
__vlan_hwaccel_clear_tag(skb);
/* Reconstruct the MAC header. */
skb_push(skb, data->l2_len);
memcpy(skb->data, &data->l2_data, data->l2_len);
skb_postpush_rcsum(skb, skb->data, data->l2_len);
skb_reset_mac_header(skb);
if (eth_p_mpls(skb->protocol)) {
skb->inner_network_header = skb->network_header;
skb_set_network_header(skb, data->network_offset);
skb_reset_mac_len(skb);
}
ovs_vport_send(vport, skb, data->mac_proto);
return 0;
}
static unsigned int
ovs_dst_get_mtu(const struct dst_entry *dst)
{
return dst->dev->mtu;
}
static struct dst_ops ovs_dst_ops = {
.family = AF_UNSPEC,
.mtu = ovs_dst_get_mtu,
};
/* prepare_frag() is called once per (larger-than-MTU) frame; its inverse is
* ovs_vport_output(), which is called once per fragmented packet.
*/
static void prepare_frag(struct vport *vport, struct sk_buff *skb,
u16 orig_network_offset, u8 mac_proto)
{
unsigned int hlen = skb_network_offset(skb);
struct ovs_frag_data *data;
data = this_cpu_ptr(&ovs_frag_data_storage);
data->dst = skb->_skb_refdst;
data->vport = vport;
data->cb = *OVS_CB(skb);
data->inner_protocol = skb->inner_protocol;
data->network_offset = orig_network_offset;
if (skb_vlan_tag_present(skb))
data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK;
else
data->vlan_tci = 0;
data->vlan_proto = skb->vlan_proto;
data->mac_proto = mac_proto;
data->l2_len = hlen;
memcpy(&data->l2_data, skb->data, hlen);
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
skb_pull(skb, hlen);
}
static void ovs_fragment(struct net *net, struct vport *vport,
struct sk_buff *skb, u16 mru,
struct sw_flow_key *key)
{
u16 orig_network_offset = 0;
if (eth_p_mpls(skb->protocol)) {
orig_network_offset = skb_network_offset(skb);
skb->network_header = skb->inner_network_header;
}
if (skb_network_offset(skb) > MAX_L2_LEN) {
OVS_NLERR(1, "L2 header too long to fragment");
goto err;
}
if (key->eth.type == htons(ETH_P_IP)) {
struct dst_entry ovs_dst;
unsigned long orig_dst;
prepare_frag(vport, skb, orig_network_offset,
ovs_key_mac_proto(key));
dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_dst.dev = vport->dev;
orig_dst = skb->_skb_refdst;
skb_dst_set_noref(skb, &ovs_dst);
IPCB(skb)->frag_max_size = mru;
ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
} else if (key->eth.type == htons(ETH_P_IPV6)) {
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
unsigned long orig_dst;
struct rt6_info ovs_rt;
if (!v6ops)
goto err;
prepare_frag(vport, skb, orig_network_offset,
ovs_key_mac_proto(key));
memset(&ovs_rt, 0, sizeof(ovs_rt));
dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_rt.dst.dev = vport->dev;
orig_dst = skb->_skb_refdst;
skb_dst_set_noref(skb, &ovs_rt.dst);
IP6CB(skb)->frag_max_size = mru;
v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
} else {
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
ovs_vport_name(vport), ntohs(key->eth.type), mru,
vport->dev->mtu);
goto err;
}
return;
err:
kfree_skb(skb);
}
static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
struct sw_flow_key *key)
{
struct vport *vport = ovs_vport_rcu(dp, out_port);
if (likely(vport)) {
u16 mru = OVS_CB(skb)->mru;
u32 cutlen = OVS_CB(skb)->cutlen;
if (unlikely(cutlen > 0)) {
if (skb->len - cutlen > ovs_mac_header_len(key))
pskb_trim(skb, skb->len - cutlen);
else
pskb_trim(skb, ovs_mac_header_len(key));
}
if (likely(!mru ||
(skb->len <= mru + vport->dev->hard_header_len))) {
ovs_vport_send(vport, skb, ovs_key_mac_proto(key));
} else if (mru <= vport->dev->mtu) {
struct net *net = read_pnet(&dp->net);
ovs_fragment(net, vport, skb, mru, key);
} else {
kfree_skb(skb);
}
} else {
kfree_skb(skb);
}
}
static int output_userspace(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr,
const struct nlattr *actions, int actions_len,
uint32_t cutlen)
{
struct dp_upcall_info upcall;
const struct nlattr *a;
int rem;
memset(&upcall, 0, sizeof(upcall));
upcall.cmd = OVS_PACKET_CMD_ACTION;
upcall.mru = OVS_CB(skb)->mru;
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
switch (nla_type(a)) {