forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdatapath.c
2047 lines (1686 loc) · 48.8 KB
/
datapath.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) 2007-2012 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/init.h>
#include <linux/module.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/jhash.h>
#include <linux/delay.h>
#include <linux/time.h>
#include <linux/etherdevice.h>
#include <linux/genetlink.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/ethtool.h>
#include <linux/wait.h>
#include <asm/div64.h>
#include <linux/highmem.h>
#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv4.h>
#include <linux/inetdevice.h>
#include <linux/list.h>
#include <linux/openvswitch.h>
#include <linux/rculist.h>
#include <linux/dmi.h>
#include <linux/workqueue.h>
#include <net/genetlink.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include "datapath.h"
#include "flow.h"
#include "vport-internal_dev.h"
/**
* struct ovs_net - Per net-namespace data for ovs.
* @dps: List of datapaths to enable dumping them all out.
* Protected by genl_mutex.
*/
struct ovs_net {
struct list_head dps;
};
static int ovs_net_id __read_mostly;
#define REHASH_FLOW_INTERVAL (10 * 60 * HZ)
static void rehash_flow_table(struct work_struct *work);
static DECLARE_DELAYED_WORK(rehash_flow_wq, rehash_flow_table);
/**
* DOC: Locking:
*
* Writes to device state (add/remove datapath, port, set operations on vports,
* etc.) are protected by RTNL.
*
* Writes to other state (flow table modifications, set miscellaneous datapath
* parameters, etc.) are protected by genl_mutex. The RTNL lock nests inside
* genl_mutex.
*
* Reads are protected by RCU.
*
* There are a few special cases (mostly stats) that have their own
* synchronization but they nest under all of above and don't interact with
* each other.
*/
static struct vport *new_vport(const struct vport_parms *);
static int queue_gso_packets(struct net *, int dp_ifindex, struct sk_buff *,
const struct dp_upcall_info *);
static int queue_userspace_packet(struct net *, int dp_ifindex,
struct sk_buff *,
const struct dp_upcall_info *);
/* Must be called with rcu_read_lock, genl_mutex, or RTNL lock. */
static struct datapath *get_dp(struct net *net, int dp_ifindex)
{
struct datapath *dp = NULL;
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, dp_ifindex);
if (dev) {
struct vport *vport = ovs_internal_dev_get_vport(dev);
if (vport)
dp = vport->dp;
}
rcu_read_unlock();
return dp;
}
/* Must be called with rcu_read_lock or RTNL lock. */
const char *ovs_dp_name(const struct datapath *dp)
{
struct vport *vport = ovs_vport_rtnl_rcu(dp, OVSP_LOCAL);
return vport->ops->get_name(vport);
}
static int get_dpifindex(struct datapath *dp)
{
struct vport *local;
int ifindex;
rcu_read_lock();
local = ovs_vport_rcu(dp, OVSP_LOCAL);
if (local)
ifindex = local->ops->get_ifindex(local);
else
ifindex = 0;
rcu_read_unlock();
return ifindex;
}
static void destroy_dp_rcu(struct rcu_head *rcu)
{
struct datapath *dp = container_of(rcu, struct datapath, rcu);
ovs_flow_tbl_destroy((__force struct flow_table *)dp->table);
free_percpu(dp->stats_percpu);
release_net(ovs_dp_get_net(dp));
kfree(dp->ports);
kfree(dp);
}
static struct hlist_head *vport_hash_bucket(const struct datapath *dp,
u16 port_no)
{
return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)];
}
struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no)
{
struct vport *vport;
struct hlist_head *head;
head = vport_hash_bucket(dp, port_no);
hlist_for_each_entry_rcu(vport, head, dp_hash_node) {
if (vport->port_no == port_no)
return vport;
}
return NULL;
}
/* Called with RTNL lock and genl_lock. */
static struct vport *new_vport(const struct vport_parms *parms)
{
struct vport *vport;
vport = ovs_vport_add(parms);
if (!IS_ERR(vport)) {
struct datapath *dp = parms->dp;
struct hlist_head *head = vport_hash_bucket(dp, vport->port_no);
hlist_add_head_rcu(&vport->dp_hash_node, head);
}
return vport;
}
/* Called with RTNL lock. */
void ovs_dp_detach_port(struct vport *p)
{
ASSERT_RTNL();
/* First drop references to device. */
hlist_del_rcu(&p->dp_hash_node);
/* Then destroy it. */
ovs_vport_del(p);
}
/* Must be called with rcu_read_lock. */
void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
{
struct datapath *dp = p->dp;
struct sw_flow *flow;
struct dp_stats_percpu *stats;
struct sw_flow_key key;
u64 *stats_counter;
int error;
int key_len;
stats = this_cpu_ptr(dp->stats_percpu);
/* Extract flow from 'skb' into 'key'. */
error = ovs_flow_extract(skb, p->port_no, &key, &key_len);
if (unlikely(error)) {
kfree_skb(skb);
return;
}
/* Look up flow. */
flow = ovs_flow_tbl_lookup(rcu_dereference(dp->table), &key, key_len);
if (unlikely(!flow)) {
struct dp_upcall_info upcall;
upcall.cmd = OVS_PACKET_CMD_MISS;
upcall.key = &key;
upcall.userdata = NULL;
upcall.portid = p->upcall_portid;
ovs_dp_upcall(dp, skb, &upcall);
consume_skb(skb);
stats_counter = &stats->n_missed;
goto out;
}
OVS_CB(skb)->flow = flow;
stats_counter = &stats->n_hit;
ovs_flow_used(OVS_CB(skb)->flow, skb);
ovs_execute_actions(dp, skb);
out:
/* Update datapath statistics. */
u64_stats_update_begin(&stats->sync);
(*stats_counter)++;
u64_stats_update_end(&stats->sync);
}
static struct genl_family dp_packet_genl_family = {
.id = GENL_ID_GENERATE,
.hdrsize = sizeof(struct ovs_header),
.name = OVS_PACKET_FAMILY,
.version = OVS_PACKET_VERSION,
.maxattr = OVS_PACKET_ATTR_MAX,
.netnsok = true
};
int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
struct dp_stats_percpu *stats;
int dp_ifindex;
int err;
if (upcall_info->portid == 0) {
err = -ENOTCONN;
goto err;
}
dp_ifindex = get_dpifindex(dp);
if (!dp_ifindex) {
err = -ENODEV;
goto err;
}
if (!skb_is_gso(skb))
err = queue_userspace_packet(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info);
else
err = queue_gso_packets(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info);
if (err)
goto err;
return 0;
err:
stats = this_cpu_ptr(dp->stats_percpu);
u64_stats_update_begin(&stats->sync);
stats->n_lost++;
u64_stats_update_end(&stats->sync);
return err;
}
static int queue_gso_packets(struct net *net, int dp_ifindex,
struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
unsigned short gso_type = skb_shinfo(skb)->gso_type;
struct dp_upcall_info later_info;
struct sw_flow_key later_key;
struct sk_buff *segs, *nskb;
int err;
segs = __skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM, false);
if (IS_ERR(segs))
return PTR_ERR(segs);
/* Queue all of the segments. */
skb = segs;
do {
err = queue_userspace_packet(net, dp_ifindex, skb, upcall_info);
if (err)
break;
if (skb == segs && gso_type & SKB_GSO_UDP) {
/* The initial flow key extracted by ovs_flow_extract()
* in this case is for a first fragment, so we need to
* properly mark later fragments.
*/
later_key = *upcall_info->key;
later_key.ip.frag = OVS_FRAG_TYPE_LATER;
later_info = *upcall_info;
later_info.key = &later_key;
upcall_info = &later_info;
}
} while ((skb = skb->next));
/* Free all of the segments. */
skb = segs;
do {
nskb = skb->next;
if (err)
kfree_skb(skb);
else
consume_skb(skb);
} while ((skb = nskb));
return err;
}
static int queue_userspace_packet(struct net *net, int dp_ifindex,
struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
struct ovs_header *upcall;
struct sk_buff *nskb = NULL;
struct sk_buff *user_skb; /* to be queued to userspace */
struct nlattr *nla;
unsigned int len;
int err;
if (vlan_tx_tag_present(skb)) {
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return -ENOMEM;
nskb = __vlan_put_tag(nskb, vlan_tx_tag_get(nskb));
if (!nskb)
return -ENOMEM;
nskb->vlan_tci = 0;
skb = nskb;
}
if (nla_attr_size(skb->len) > USHRT_MAX) {
err = -EFBIG;
goto out;
}
len = sizeof(struct ovs_header);
len += nla_total_size(skb->len);
len += nla_total_size(FLOW_BUFSIZE);
if (upcall_info->cmd == OVS_PACKET_CMD_ACTION)
len += nla_total_size(8);
user_skb = genlmsg_new(len, GFP_ATOMIC);
if (!user_skb) {
err = -ENOMEM;
goto out;
}
upcall = genlmsg_put(user_skb, 0, 0, &dp_packet_genl_family,
0, upcall_info->cmd);
upcall->dp_ifindex = dp_ifindex;
nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
ovs_flow_to_nlattrs(upcall_info->key, user_skb);
nla_nest_end(user_skb, nla);
if (upcall_info->userdata)
nla_put_u64(user_skb, OVS_PACKET_ATTR_USERDATA,
nla_get_u64(upcall_info->userdata));
nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len);
skb_copy_and_csum_dev(skb, nla_data(nla));
err = genlmsg_unicast(net, user_skb, upcall_info->portid);
out:
kfree_skb(nskb);
return err;
}
/* Called with genl_mutex. */
static int flush_flows(struct datapath *dp)
{
struct flow_table *old_table;
struct flow_table *new_table;
old_table = genl_dereference(dp->table);
new_table = ovs_flow_tbl_alloc(TBL_MIN_BUCKETS);
if (!new_table)
return -ENOMEM;
rcu_assign_pointer(dp->table, new_table);
ovs_flow_tbl_deferred_destroy(old_table);
return 0;
}
static int validate_actions(const struct nlattr *attr,
const struct sw_flow_key *key, int depth);
static int validate_sample(const struct nlattr *attr,
const struct sw_flow_key *key, int depth)
{
const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
const struct nlattr *probability, *actions;
const struct nlattr *a;
int rem;
memset(attrs, 0, sizeof(attrs));
nla_for_each_nested(a, attr, rem) {
int type = nla_type(a);
if (!type || type > OVS_SAMPLE_ATTR_MAX || attrs[type])
return -EINVAL;
attrs[type] = a;
}
if (rem)
return -EINVAL;
probability = attrs[OVS_SAMPLE_ATTR_PROBABILITY];
if (!probability || nla_len(probability) != sizeof(u32))
return -EINVAL;
actions = attrs[OVS_SAMPLE_ATTR_ACTIONS];
if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
return -EINVAL;
return validate_actions(actions, key, depth + 1);
}
static int validate_tp_port(const struct sw_flow_key *flow_key)
{
if (flow_key->eth.type == htons(ETH_P_IP)) {
if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst)
return 0;
} else if (flow_key->eth.type == htons(ETH_P_IPV6)) {
if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst)
return 0;
}
return -EINVAL;
}
static int validate_set(const struct nlattr *a,
const struct sw_flow_key *flow_key)
{
const struct nlattr *ovs_key = nla_data(a);
int key_type = nla_type(ovs_key);
/* There can be only one key in a action */
if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
return -EINVAL;
if (key_type > OVS_KEY_ATTR_MAX ||
nla_len(ovs_key) != ovs_key_lens[key_type])
return -EINVAL;
switch (key_type) {
const struct ovs_key_ipv4 *ipv4_key;
const struct ovs_key_ipv6 *ipv6_key;
case OVS_KEY_ATTR_PRIORITY:
case OVS_KEY_ATTR_SKB_MARK:
case OVS_KEY_ATTR_ETHERNET:
break;
case OVS_KEY_ATTR_IPV4:
if (flow_key->eth.type != htons(ETH_P_IP))
return -EINVAL;
if (!flow_key->ip.proto)
return -EINVAL;
ipv4_key = nla_data(ovs_key);
if (ipv4_key->ipv4_proto != flow_key->ip.proto)
return -EINVAL;
if (ipv4_key->ipv4_frag != flow_key->ip.frag)
return -EINVAL;
break;
case OVS_KEY_ATTR_IPV6:
if (flow_key->eth.type != htons(ETH_P_IPV6))
return -EINVAL;
if (!flow_key->ip.proto)
return -EINVAL;
ipv6_key = nla_data(ovs_key);
if (ipv6_key->ipv6_proto != flow_key->ip.proto)
return -EINVAL;
if (ipv6_key->ipv6_frag != flow_key->ip.frag)
return -EINVAL;
if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000)
return -EINVAL;
break;
case OVS_KEY_ATTR_TCP:
if (flow_key->ip.proto != IPPROTO_TCP)
return -EINVAL;
return validate_tp_port(flow_key);
case OVS_KEY_ATTR_UDP:
if (flow_key->ip.proto != IPPROTO_UDP)
return -EINVAL;
return validate_tp_port(flow_key);
default:
return -EINVAL;
}
return 0;
}
static int validate_userspace(const struct nlattr *attr)
{
static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_U64 },
};
struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
int error;
error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
attr, userspace_policy);
if (error)
return error;
if (!a[OVS_USERSPACE_ATTR_PID] ||
!nla_get_u32(a[OVS_USERSPACE_ATTR_PID]))
return -EINVAL;
return 0;
}
static int validate_actions(const struct nlattr *attr,
const struct sw_flow_key *key, int depth)
{
const struct nlattr *a;
int rem, err;
if (depth >= SAMPLE_ACTION_DEPTH)
return -EOVERFLOW;
nla_for_each_nested(a, attr, rem) {
/* Expected argument lengths, (u32)-1 for variable length. */
static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
[OVS_ACTION_ATTR_POP_VLAN] = 0,
[OVS_ACTION_ATTR_SET] = (u32)-1,
[OVS_ACTION_ATTR_SAMPLE] = (u32)-1
};
const struct ovs_action_push_vlan *vlan;
int type = nla_type(a);
if (type > OVS_ACTION_ATTR_MAX ||
(action_lens[type] != nla_len(a) &&
action_lens[type] != (u32)-1))
return -EINVAL;
switch (type) {
case OVS_ACTION_ATTR_UNSPEC:
return -EINVAL;
case OVS_ACTION_ATTR_USERSPACE:
err = validate_userspace(a);
if (err)
return err;
break;
case OVS_ACTION_ATTR_OUTPUT:
if (nla_get_u32(a) >= DP_MAX_PORTS)
return -EINVAL;
break;
case OVS_ACTION_ATTR_POP_VLAN:
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
vlan = nla_data(a);
if (vlan->vlan_tpid != htons(ETH_P_8021Q))
return -EINVAL;
if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
return -EINVAL;
break;
case OVS_ACTION_ATTR_SET:
err = validate_set(a, key);
if (err)
return err;
break;
case OVS_ACTION_ATTR_SAMPLE:
err = validate_sample(a, key, depth);
if (err)
return err;
break;
default:
return -EINVAL;
}
}
if (rem > 0)
return -EINVAL;
return 0;
}
static void clear_stats(struct sw_flow *flow)
{
flow->used = 0;
flow->tcp_flags = 0;
flow->packet_count = 0;
flow->byte_count = 0;
}
static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
{
struct ovs_header *ovs_header = info->userhdr;
struct nlattr **a = info->attrs;
struct sw_flow_actions *acts;
struct sk_buff *packet;
struct sw_flow *flow;
struct datapath *dp;
struct ethhdr *eth;
int len;
int err;
int key_len;
err = -EINVAL;
if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
!a[OVS_PACKET_ATTR_ACTIONS] ||
nla_len(a[OVS_PACKET_ATTR_PACKET]) < ETH_HLEN)
goto err;
len = nla_len(a[OVS_PACKET_ATTR_PACKET]);
packet = __dev_alloc_skb(NET_IP_ALIGN + len, GFP_KERNEL);
err = -ENOMEM;
if (!packet)
goto err;
skb_reserve(packet, NET_IP_ALIGN);
memcpy(__skb_put(packet, len), nla_data(a[OVS_PACKET_ATTR_PACKET]), len);
skb_reset_mac_header(packet);
eth = eth_hdr(packet);
/* Normally, setting the skb 'protocol' field would be handled by a
* call to eth_type_trans(), but it assumes there's a sending
* device, which we may not have. */
if (ntohs(eth->h_proto) >= 1536)
packet->protocol = eth->h_proto;
else
packet->protocol = htons(ETH_P_802_2);
/* Build an sw_flow for sending this packet. */
flow = ovs_flow_alloc();
err = PTR_ERR(flow);
if (IS_ERR(flow))
goto err_kfree_skb;
err = ovs_flow_extract(packet, -1, &flow->key, &key_len);
if (err)
goto err_flow_free;
err = ovs_flow_metadata_from_nlattrs(&flow->key.phy.priority,
&flow->key.phy.skb_mark,
&flow->key.phy.in_port,
a[OVS_PACKET_ATTR_KEY]);
if (err)
goto err_flow_free;
err = validate_actions(a[OVS_PACKET_ATTR_ACTIONS], &flow->key, 0);
if (err)
goto err_flow_free;
flow->hash = ovs_flow_hash(&flow->key, key_len);
acts = ovs_flow_actions_alloc(a[OVS_PACKET_ATTR_ACTIONS]);
err = PTR_ERR(acts);
if (IS_ERR(acts))
goto err_flow_free;
rcu_assign_pointer(flow->sf_acts, acts);
OVS_CB(packet)->flow = flow;
packet->priority = flow->key.phy.priority;
packet->mark = flow->key.phy.skb_mark;
rcu_read_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
err = -ENODEV;
if (!dp)
goto err_unlock;
local_bh_disable();
err = ovs_execute_actions(dp, packet);
local_bh_enable();
rcu_read_unlock();
ovs_flow_free(flow);
return err;
err_unlock:
rcu_read_unlock();
err_flow_free:
ovs_flow_free(flow);
err_kfree_skb:
kfree_skb(packet);
err:
return err;
}
static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
[OVS_PACKET_ATTR_PACKET] = { .type = NLA_UNSPEC },
[OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED },
[OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED },
};
static struct genl_ops dp_packet_genl_ops[] = {
{ .cmd = OVS_PACKET_CMD_EXECUTE,
.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
.policy = packet_policy,
.doit = ovs_packet_cmd_execute
}
};
static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats)
{
int i;
struct flow_table *table = genl_dereference(dp->table);
stats->n_flows = ovs_flow_tbl_count(table);
stats->n_hit = stats->n_missed = stats->n_lost = 0;
for_each_possible_cpu(i) {
const struct dp_stats_percpu *percpu_stats;
struct dp_stats_percpu local_stats;
unsigned int start;
percpu_stats = per_cpu_ptr(dp->stats_percpu, i);
do {
start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
local_stats = *percpu_stats;
} while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
stats->n_hit += local_stats.n_hit;
stats->n_missed += local_stats.n_missed;
stats->n_lost += local_stats.n_lost;
}
}
static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
};
static struct genl_family dp_flow_genl_family = {
.id = GENL_ID_GENERATE,
.hdrsize = sizeof(struct ovs_header),
.name = OVS_FLOW_FAMILY,
.version = OVS_FLOW_VERSION,
.maxattr = OVS_FLOW_ATTR_MAX,
.netnsok = true
};
static struct genl_multicast_group ovs_dp_flow_multicast_group = {
.name = OVS_FLOW_MCGROUP
};
/* Called with genl_lock. */
static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
struct sk_buff *skb, u32 portid,
u32 seq, u32 flags, u8 cmd)
{
const int skb_orig_len = skb->len;
const struct sw_flow_actions *sf_acts;
struct ovs_flow_stats stats;
struct ovs_header *ovs_header;
struct nlattr *nla;
unsigned long used;
u8 tcp_flags;
int err;
sf_acts = rcu_dereference_protected(flow->sf_acts,
lockdep_genl_is_held());
ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd);
if (!ovs_header)
return -EMSGSIZE;
ovs_header->dp_ifindex = get_dpifindex(dp);
nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
if (!nla)
goto nla_put_failure;
err = ovs_flow_to_nlattrs(&flow->key, skb);
if (err)
goto error;
nla_nest_end(skb, nla);
spin_lock_bh(&flow->lock);
used = flow->used;
stats.n_packets = flow->packet_count;
stats.n_bytes = flow->byte_count;
tcp_flags = flow->tcp_flags;
spin_unlock_bh(&flow->lock);
if (used &&
nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used)))
goto nla_put_failure;
if (stats.n_packets &&
nla_put(skb, OVS_FLOW_ATTR_STATS,
sizeof(struct ovs_flow_stats), &stats))
goto nla_put_failure;
if (tcp_flags &&
nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags))
goto nla_put_failure;
/* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
* this is the first flow to be dumped into 'skb'. This is unusual for
* Netlink but individual action lists can be longer than
* NLMSG_GOODSIZE and thus entirely undumpable if we didn't do this.
* The userspace caller can always fetch the actions separately if it
* really wants them. (Most userspace callers in fact don't care.)
*
* This can only fail for dump operations because the skb is always
* properly sized for single flows.
*/
err = nla_put(skb, OVS_FLOW_ATTR_ACTIONS, sf_acts->actions_len,
sf_acts->actions);
if (err < 0 && skb_orig_len)
goto error;
return genlmsg_end(skb, ovs_header);
nla_put_failure:
err = -EMSGSIZE;
error:
genlmsg_cancel(skb, ovs_header);
return err;
}
static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow)
{
const struct sw_flow_actions *sf_acts;
int len;
sf_acts = rcu_dereference_protected(flow->sf_acts,
lockdep_genl_is_held());
/* OVS_FLOW_ATTR_KEY */
len = nla_total_size(FLOW_BUFSIZE);
/* OVS_FLOW_ATTR_ACTIONS */
len += nla_total_size(sf_acts->actions_len);
/* OVS_FLOW_ATTR_STATS */
len += nla_total_size(sizeof(struct ovs_flow_stats));
/* OVS_FLOW_ATTR_TCP_FLAGS */
len += nla_total_size(1);
/* OVS_FLOW_ATTR_USED */
len += nla_total_size(8);
len += NLMSG_ALIGN(sizeof(struct ovs_header));
return genlmsg_new(len, GFP_KERNEL);
}
static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
struct datapath *dp,
u32 portid, u32 seq, u8 cmd)
{
struct sk_buff *skb;
int retval;
skb = ovs_flow_cmd_alloc_info(flow);
if (!skb)
return ERR_PTR(-ENOMEM);
retval = ovs_flow_cmd_fill_info(flow, dp, skb, portid, seq, 0, cmd);
BUG_ON(retval < 0);
return skb;
}
static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr **a = info->attrs;
struct ovs_header *ovs_header = info->userhdr;
struct sw_flow_key key;
struct sw_flow *flow;
struct sk_buff *reply;
struct datapath *dp;
struct flow_table *table;
int error;
int key_len;
/* Extract key. */
error = -EINVAL;
if (!a[OVS_FLOW_ATTR_KEY])
goto error;
error = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
if (error)
goto error;
/* Validate actions. */
if (a[OVS_FLOW_ATTR_ACTIONS]) {
error = validate_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, 0);
if (error)
goto error;
} else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) {
error = -EINVAL;
goto error;
}
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
error = -ENODEV;
if (!dp)
goto error;
table = genl_dereference(dp->table);
flow = ovs_flow_tbl_lookup(table, &key, key_len);
if (!flow) {
struct sw_flow_actions *acts;
/* Bail out if we're not allowed to create a new flow. */
error = -ENOENT;
if (info->genlhdr->cmd == OVS_FLOW_CMD_SET)
goto error;
/* Expand table, if necessary, to make room. */
if (ovs_flow_tbl_need_to_expand(table)) {
struct flow_table *new_table;
new_table = ovs_flow_tbl_expand(table);
if (!IS_ERR(new_table)) {
rcu_assign_pointer(dp->table, new_table);
ovs_flow_tbl_deferred_destroy(table);
table = genl_dereference(dp->table);
}
}
/* Allocate flow. */
flow = ovs_flow_alloc();
if (IS_ERR(flow)) {
error = PTR_ERR(flow);
goto error;
}
flow->key = key;
clear_stats(flow);
/* Obtain actions. */
acts = ovs_flow_actions_alloc(a[OVS_FLOW_ATTR_ACTIONS]);
error = PTR_ERR(acts);
if (IS_ERR(acts))
goto error_free_flow;
rcu_assign_pointer(flow->sf_acts, acts);
/* Put flow in bucket. */
flow->hash = ovs_flow_hash(&key, key_len);
ovs_flow_tbl_insert(table, flow);
reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
info->snd_seq,
OVS_FLOW_CMD_NEW);
} else {
/* We found a matching flow. */
struct sw_flow_actions *old_acts;