forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmacvlan.c
1875 lines (1562 loc) · 47.9 KB
/
macvlan.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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2007 Patrick McHardy <[email protected]>
*
* The code this is based on carried the following copyright notice:
* ---
* (C) Copyright 2001-2006
* Alex Zeffertt, Cambridge Broadband Ltd, [email protected]
* Re-worked by Ben Greear <[email protected]>
* ---
*/
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/rculist.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/net_tstamp.h>
#include <linux/ethtool.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/if_link.h>
#include <linux/if_macvlan.h>
#include <linux/hash.h>
#include <linux/workqueue.h>
#include <net/rtnetlink.h>
#include <net/xfrm.h>
#include <linux/netpoll.h>
#include <linux/phy.h>
#define MACVLAN_HASH_BITS 8
#define MACVLAN_HASH_SIZE (1<<MACVLAN_HASH_BITS)
#define MACVLAN_DEFAULT_BC_QUEUE_LEN 1000
#define MACVLAN_F_PASSTHRU 1
#define MACVLAN_F_ADDRCHANGE 2
struct macvlan_port {
struct net_device *dev;
struct hlist_head vlan_hash[MACVLAN_HASH_SIZE];
struct list_head vlans;
struct sk_buff_head bc_queue;
struct work_struct bc_work;
u32 bc_queue_len_used;
int bc_cutoff;
u32 flags;
int count;
struct hlist_head vlan_source_hash[MACVLAN_HASH_SIZE];
DECLARE_BITMAP(bc_filter, MACVLAN_MC_FILTER_SZ);
DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ);
unsigned char perm_addr[ETH_ALEN];
};
struct macvlan_source_entry {
struct hlist_node hlist;
struct macvlan_dev *vlan;
unsigned char addr[6+2] __aligned(sizeof(u16));
struct rcu_head rcu;
};
struct macvlan_skb_cb {
const struct macvlan_dev *src;
};
#define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0]))
static void macvlan_port_destroy(struct net_device *dev);
static void update_port_bc_queue_len(struct macvlan_port *port);
static inline bool macvlan_passthru(const struct macvlan_port *port)
{
return port->flags & MACVLAN_F_PASSTHRU;
}
static inline void macvlan_set_passthru(struct macvlan_port *port)
{
port->flags |= MACVLAN_F_PASSTHRU;
}
static inline bool macvlan_addr_change(const struct macvlan_port *port)
{
return port->flags & MACVLAN_F_ADDRCHANGE;
}
static inline void macvlan_set_addr_change(struct macvlan_port *port)
{
port->flags |= MACVLAN_F_ADDRCHANGE;
}
static inline void macvlan_clear_addr_change(struct macvlan_port *port)
{
port->flags &= ~MACVLAN_F_ADDRCHANGE;
}
/* Hash Ethernet address */
static u32 macvlan_eth_hash(const unsigned char *addr)
{
u64 value = get_unaligned((u64 *)addr);
/* only want 6 bytes */
#ifdef __BIG_ENDIAN
value >>= 16;
#else
value <<= 16;
#endif
return hash_64(value, MACVLAN_HASH_BITS);
}
static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->rx_handler_data);
}
static struct macvlan_port *macvlan_port_get_rtnl(const struct net_device *dev)
{
return rtnl_dereference(dev->rx_handler_data);
}
static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port,
const unsigned char *addr)
{
struct macvlan_dev *vlan;
u32 idx = macvlan_eth_hash(addr);
hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist,
lockdep_rtnl_is_held()) {
if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr))
return vlan;
}
return NULL;
}
static struct macvlan_source_entry *macvlan_hash_lookup_source(
const struct macvlan_dev *vlan,
const unsigned char *addr)
{
struct macvlan_source_entry *entry;
u32 idx = macvlan_eth_hash(addr);
struct hlist_head *h = &vlan->port->vlan_source_hash[idx];
hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) {
if (ether_addr_equal_64bits(entry->addr, addr) &&
entry->vlan == vlan)
return entry;
}
return NULL;
}
static int macvlan_hash_add_source(struct macvlan_dev *vlan,
const unsigned char *addr)
{
struct macvlan_port *port = vlan->port;
struct macvlan_source_entry *entry;
struct hlist_head *h;
entry = macvlan_hash_lookup_source(vlan, addr);
if (entry)
return 0;
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
return -ENOMEM;
ether_addr_copy(entry->addr, addr);
entry->vlan = vlan;
h = &port->vlan_source_hash[macvlan_eth_hash(addr)];
hlist_add_head_rcu(&entry->hlist, h);
vlan->macaddr_count++;
return 0;
}
static void macvlan_hash_add(struct macvlan_dev *vlan)
{
struct macvlan_port *port = vlan->port;
const unsigned char *addr = vlan->dev->dev_addr;
u32 idx = macvlan_eth_hash(addr);
hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]);
}
static void macvlan_hash_del_source(struct macvlan_source_entry *entry)
{
hlist_del_rcu(&entry->hlist);
kfree_rcu(entry, rcu);
}
static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync)
{
hlist_del_rcu(&vlan->hlist);
if (sync)
synchronize_rcu();
}
static void macvlan_hash_change_addr(struct macvlan_dev *vlan,
const unsigned char *addr)
{
macvlan_hash_del(vlan, true);
/* Now that we are unhashed it is safe to change the device
* address without confusing packet delivery.
*/
eth_hw_addr_set(vlan->dev, addr);
macvlan_hash_add(vlan);
}
static bool macvlan_addr_busy(const struct macvlan_port *port,
const unsigned char *addr)
{
/* Test to see if the specified address is
* currently in use by the underlying device or
* another macvlan.
*/
if (!macvlan_passthru(port) && !macvlan_addr_change(port) &&
ether_addr_equal_64bits(port->dev->dev_addr, addr))
return true;
if (macvlan_hash_lookup(port, addr))
return true;
return false;
}
static int macvlan_broadcast_one(struct sk_buff *skb,
const struct macvlan_dev *vlan,
const struct ethhdr *eth, bool local)
{
struct net_device *dev = vlan->dev;
if (local)
return __dev_forward_skb(dev, skb);
skb->dev = dev;
if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
skb->pkt_type = PACKET_BROADCAST;
else
skb->pkt_type = PACKET_MULTICAST;
return 0;
}
static u32 macvlan_hash_mix(const struct macvlan_dev *vlan)
{
return (u32)(((unsigned long)vlan) >> L1_CACHE_SHIFT);
}
static unsigned int mc_hash(const struct macvlan_dev *vlan,
const unsigned char *addr)
{
u32 val = __get_unaligned_cpu32(addr + 2);
val ^= macvlan_hash_mix(vlan);
return hash_32(val, MACVLAN_MC_FILTER_BITS);
}
static void macvlan_broadcast(struct sk_buff *skb,
const struct macvlan_port *port,
struct net_device *src,
enum macvlan_mode mode)
{
const struct ethhdr *eth = eth_hdr(skb);
const struct macvlan_dev *vlan;
struct sk_buff *nskb;
unsigned int i;
int err;
unsigned int hash;
if (skb->protocol == htons(ETH_P_PAUSE))
return;
hash_for_each_rcu(port->vlan_hash, i, vlan, hlist) {
if (vlan->dev == src || !(vlan->mode & mode))
continue;
hash = mc_hash(vlan, eth->h_dest);
if (!test_bit(hash, vlan->mc_filter))
continue;
err = NET_RX_DROP;
nskb = skb_clone(skb, GFP_ATOMIC);
if (likely(nskb))
err = macvlan_broadcast_one(nskb, vlan, eth,
mode == MACVLAN_MODE_BRIDGE) ?:
netif_rx(nskb);
macvlan_count_rx(vlan, skb->len + ETH_HLEN,
err == NET_RX_SUCCESS, true);
}
}
static void macvlan_multicast_rx(const struct macvlan_port *port,
const struct macvlan_dev *src,
struct sk_buff *skb)
{
if (!src)
/* frame comes from an external address */
macvlan_broadcast(skb, port, NULL,
MACVLAN_MODE_PRIVATE |
MACVLAN_MODE_VEPA |
MACVLAN_MODE_PASSTHRU|
MACVLAN_MODE_BRIDGE);
else if (src->mode == MACVLAN_MODE_VEPA)
/* flood to everyone except source */
macvlan_broadcast(skb, port, src->dev,
MACVLAN_MODE_VEPA |
MACVLAN_MODE_BRIDGE);
else
/*
* flood only to VEPA ports, bridge ports
* already saw the frame on the way out.
*/
macvlan_broadcast(skb, port, src->dev,
MACVLAN_MODE_VEPA);
}
static void macvlan_process_broadcast(struct work_struct *w)
{
struct macvlan_port *port = container_of(w, struct macvlan_port,
bc_work);
struct sk_buff *skb;
struct sk_buff_head list;
__skb_queue_head_init(&list);
spin_lock_bh(&port->bc_queue.lock);
skb_queue_splice_tail_init(&port->bc_queue, &list);
spin_unlock_bh(&port->bc_queue.lock);
while ((skb = __skb_dequeue(&list))) {
const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
rcu_read_lock();
macvlan_multicast_rx(port, src, skb);
rcu_read_unlock();
if (src)
dev_put(src->dev);
consume_skb(skb);
cond_resched();
}
}
static void macvlan_broadcast_enqueue(struct macvlan_port *port,
const struct macvlan_dev *src,
struct sk_buff *skb)
{
struct sk_buff *nskb;
int err = -ENOMEM;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
goto err;
MACVLAN_SKB_CB(nskb)->src = src;
spin_lock(&port->bc_queue.lock);
if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) {
if (src)
dev_hold(src->dev);
__skb_queue_tail(&port->bc_queue, nskb);
err = 0;
}
spin_unlock(&port->bc_queue.lock);
queue_work(system_unbound_wq, &port->bc_work);
if (err)
goto free_nskb;
return;
free_nskb:
kfree_skb(nskb);
err:
dev_core_stats_rx_dropped_inc(skb->dev);
}
static void macvlan_flush_sources(struct macvlan_port *port,
struct macvlan_dev *vlan)
{
struct macvlan_source_entry *entry;
struct hlist_node *next;
int i;
hash_for_each_safe(port->vlan_source_hash, i, next, entry, hlist)
if (entry->vlan == vlan)
macvlan_hash_del_source(entry);
vlan->macaddr_count = 0;
}
static void macvlan_forward_source_one(struct sk_buff *skb,
struct macvlan_dev *vlan)
{
struct sk_buff *nskb;
struct net_device *dev;
int len;
int ret;
dev = vlan->dev;
if (unlikely(!(dev->flags & IFF_UP)))
return;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return;
len = nskb->len + ETH_HLEN;
nskb->dev = dev;
if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr))
nskb->pkt_type = PACKET_HOST;
ret = __netif_rx(nskb);
macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false);
}
static bool macvlan_forward_source(struct sk_buff *skb,
struct macvlan_port *port,
const unsigned char *addr)
{
struct macvlan_source_entry *entry;
u32 idx = macvlan_eth_hash(addr);
struct hlist_head *h = &port->vlan_source_hash[idx];
bool consume = false;
hlist_for_each_entry_rcu(entry, h, hlist) {
if (ether_addr_equal_64bits(entry->addr, addr)) {
if (entry->vlan->flags & MACVLAN_FLAG_NODST)
consume = true;
macvlan_forward_source_one(skb, entry->vlan);
}
}
return consume;
}
/* called under rcu_read_lock() from netif_receive_skb */
static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
{
struct macvlan_port *port;
struct sk_buff *skb = *pskb;
const struct ethhdr *eth = eth_hdr(skb);
const struct macvlan_dev *vlan;
const struct macvlan_dev *src;
struct net_device *dev;
unsigned int len = 0;
int ret;
rx_handler_result_t handle_res;
/* Packets from dev_loopback_xmit() do not have L2 header, bail out */
if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
return RX_HANDLER_PASS;
port = macvlan_port_get_rcu(skb->dev);
if (is_multicast_ether_addr(eth->h_dest)) {
unsigned int hash;
skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN);
if (!skb)
return RX_HANDLER_CONSUMED;
*pskb = skb;
eth = eth_hdr(skb);
if (macvlan_forward_source(skb, port, eth->h_source)) {
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
src = macvlan_hash_lookup(port, eth->h_source);
if (src && src->mode != MACVLAN_MODE_VEPA &&
src->mode != MACVLAN_MODE_BRIDGE) {
/* forward to original port. */
vlan = src;
ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?:
__netif_rx(skb);
handle_res = RX_HANDLER_CONSUMED;
goto out;
}
hash = mc_hash(NULL, eth->h_dest);
if (test_bit(hash, port->bc_filter))
macvlan_broadcast_enqueue(port, src, skb);
else if (test_bit(hash, port->mc_filter))
macvlan_multicast_rx(port, src, skb);
return RX_HANDLER_PASS;
}
if (macvlan_forward_source(skb, port, eth->h_source)) {
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
if (macvlan_passthru(port))
vlan = list_first_or_null_rcu(&port->vlans,
struct macvlan_dev, list);
else
vlan = macvlan_hash_lookup(port, eth->h_dest);
if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE)
return RX_HANDLER_PASS;
dev = vlan->dev;
if (unlikely(!(dev->flags & IFF_UP))) {
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
len = skb->len + ETH_HLEN;
skb = skb_share_check(skb, GFP_ATOMIC);
if (!skb) {
ret = NET_RX_DROP;
handle_res = RX_HANDLER_CONSUMED;
goto out;
}
*pskb = skb;
skb->dev = dev;
skb->pkt_type = PACKET_HOST;
ret = NET_RX_SUCCESS;
handle_res = RX_HANDLER_ANOTHER;
out:
macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false);
return handle_res;
}
static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
{
const struct macvlan_dev *vlan = netdev_priv(dev);
const struct macvlan_port *port = vlan->port;
const struct macvlan_dev *dest;
if (vlan->mode == MACVLAN_MODE_BRIDGE) {
const struct ethhdr *eth = skb_eth_hdr(skb);
/* send to other bridge ports directly */
if (is_multicast_ether_addr(eth->h_dest)) {
skb_reset_mac_header(skb);
macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE);
goto xmit_world;
}
dest = macvlan_hash_lookup(port, eth->h_dest);
if (dest && dest->mode == MACVLAN_MODE_BRIDGE) {
/* send to lowerdev first for its network taps */
dev_forward_skb(vlan->lowerdev, skb);
return NET_XMIT_SUCCESS;
}
}
xmit_world:
skb->dev = vlan->lowerdev;
return dev_queue_xmit_accel(skb,
netdev_get_sb_channel(dev) ? dev : NULL);
}
static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
{
#ifdef CONFIG_NET_POLL_CONTROLLER
return netpoll_send_skb(vlan->netpoll, skb);
#else
BUG();
return NETDEV_TX_OK;
#endif
}
static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
unsigned int len = skb->len;
int ret;
if (unlikely(netpoll_tx_running(dev)))
return macvlan_netpoll_send_skb(vlan, skb);
ret = macvlan_queue_xmit(skb, dev);
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct vlan_pcpu_stats *pcpu_stats;
pcpu_stats = this_cpu_ptr(vlan->pcpu_stats);
u64_stats_update_begin(&pcpu_stats->syncp);
u64_stats_inc(&pcpu_stats->tx_packets);
u64_stats_add(&pcpu_stats->tx_bytes, len);
u64_stats_update_end(&pcpu_stats->syncp);
} else {
this_cpu_inc(vlan->pcpu_stats->tx_dropped);
}
return ret;
}
static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type, const void *daddr,
const void *saddr, unsigned len)
{
const struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
return dev_hard_header(skb, lowerdev, type, daddr,
saddr ? : dev->dev_addr, len);
}
static const struct header_ops macvlan_hard_header_ops = {
.create = macvlan_hard_header,
.parse = eth_header_parse,
.cache = eth_header_cache,
.cache_update = eth_header_cache_update,
.parse_protocol = eth_header_parse_protocol,
};
static int macvlan_open(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
int err;
if (macvlan_passthru(vlan->port)) {
if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) {
err = dev_set_promiscuity(lowerdev, 1);
if (err < 0)
goto out;
}
goto hash_add;
}
err = -EADDRINUSE;
if (macvlan_addr_busy(vlan->port, dev->dev_addr))
goto out;
/* Attempt to populate accel_priv which is used to offload the L2
* forwarding requests for unicast packets.
*/
if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD)
vlan->accel_priv =
lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
/* If earlier attempt to offload failed, or accel_priv is not
* populated we must add the unicast address to the lower device.
*/
if (IS_ERR_OR_NULL(vlan->accel_priv)) {
vlan->accel_priv = NULL;
err = dev_uc_add(lowerdev, dev->dev_addr);
if (err < 0)
goto out;
}
if (dev->flags & IFF_ALLMULTI) {
err = dev_set_allmulti(lowerdev, 1);
if (err < 0)
goto del_unicast;
}
if (dev->flags & IFF_PROMISC) {
err = dev_set_promiscuity(lowerdev, 1);
if (err < 0)
goto clear_multi;
}
hash_add:
macvlan_hash_add(vlan);
return 0;
clear_multi:
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, -1);
del_unicast:
if (vlan->accel_priv) {
lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
vlan->accel_priv);
vlan->accel_priv = NULL;
} else {
dev_uc_del(lowerdev, dev->dev_addr);
}
out:
return err;
}
static int macvlan_stop(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
if (vlan->accel_priv) {
lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
vlan->accel_priv);
vlan->accel_priv = NULL;
}
dev_uc_unsync(lowerdev, dev);
dev_mc_unsync(lowerdev, dev);
if (macvlan_passthru(vlan->port)) {
if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC))
dev_set_promiscuity(lowerdev, -1);
goto hash_del;
}
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, -1);
if (dev->flags & IFF_PROMISC)
dev_set_promiscuity(lowerdev, -1);
dev_uc_del(lowerdev, dev->dev_addr);
hash_del:
macvlan_hash_del(vlan, !dev->dismantle);
return 0;
}
static int macvlan_sync_address(struct net_device *dev,
const unsigned char *addr)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
struct macvlan_port *port = vlan->port;
int err;
if (!(dev->flags & IFF_UP)) {
/* Just copy in the new address */
eth_hw_addr_set(dev, addr);
} else {
/* Rehash and update the device filters */
if (macvlan_addr_busy(vlan->port, addr))
return -EADDRINUSE;
if (!macvlan_passthru(port)) {
err = dev_uc_add(lowerdev, addr);
if (err)
return err;
dev_uc_del(lowerdev, dev->dev_addr);
}
macvlan_hash_change_addr(vlan, addr);
}
if (macvlan_passthru(port) && !macvlan_addr_change(port)) {
/* Since addr_change isn't set, we are here due to lower
* device change. Save the lower-dev address so we can
* restore it later.
*/
ether_addr_copy(vlan->port->perm_addr,
lowerdev->dev_addr);
}
macvlan_clear_addr_change(port);
return 0;
}
static int macvlan_set_mac_address(struct net_device *dev, void *p)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct sockaddr *addr = p;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
/* If the addresses are the same, this is a no-op */
if (ether_addr_equal(dev->dev_addr, addr->sa_data))
return 0;
if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
macvlan_set_addr_change(vlan->port);
return dev_set_mac_address(vlan->lowerdev, addr, NULL);
}
if (macvlan_addr_busy(vlan->port, addr->sa_data))
return -EADDRINUSE;
return macvlan_sync_address(dev, addr->sa_data);
}
static void macvlan_change_rx_flags(struct net_device *dev, int change)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
if (dev->flags & IFF_UP) {
if (change & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC)
dev_set_promiscuity(lowerdev,
dev->flags & IFF_PROMISC ? 1 : -1);
}
}
static void macvlan_compute_filter(unsigned long *mc_filter,
struct net_device *dev,
struct macvlan_dev *vlan, int cutoff)
{
if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
bitmap_fill(mc_filter, MACVLAN_MC_FILTER_SZ);
} else {
DECLARE_BITMAP(filter, MACVLAN_MC_FILTER_SZ);
struct netdev_hw_addr *ha;
bitmap_zero(filter, MACVLAN_MC_FILTER_SZ);
netdev_for_each_mc_addr(ha, dev) {
if (!vlan && ha->synced <= cutoff)
continue;
__set_bit(mc_hash(vlan, ha->addr), filter);
}
__set_bit(mc_hash(vlan, dev->broadcast), filter);
bitmap_copy(mc_filter, filter, MACVLAN_MC_FILTER_SZ);
}
}
static void macvlan_recompute_bc_filter(struct macvlan_dev *vlan)
{
if (vlan->port->bc_cutoff < 0) {
bitmap_zero(vlan->port->bc_filter, MACVLAN_MC_FILTER_SZ);
return;
}
macvlan_compute_filter(vlan->port->bc_filter, vlan->lowerdev, NULL,
vlan->port->bc_cutoff);
}
static void macvlan_set_mac_lists(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
macvlan_compute_filter(vlan->mc_filter, dev, vlan, 0);
dev_uc_sync(vlan->lowerdev, dev);
dev_mc_sync(vlan->lowerdev, dev);
/* This is slightly inaccurate as we're including the subscription
* list of vlan->lowerdev too.
*
* Bug alert: This only works if everyone has the same broadcast
* address as lowerdev. As soon as someone changes theirs this
* will break.
*
* However, this is already broken as when you change your broadcast
* address we don't get called.
*
* The solution is to maintain a list of broadcast addresses like
* we do for uc/mc, if you care.
*/
macvlan_compute_filter(vlan->port->mc_filter, vlan->lowerdev, NULL,
0);
macvlan_recompute_bc_filter(vlan);
}
static void update_port_bc_cutoff(struct macvlan_dev *vlan, int cutoff)
{
if (vlan->port->bc_cutoff == cutoff)
return;
vlan->port->bc_cutoff = cutoff;
macvlan_recompute_bc_filter(vlan);
}
static int macvlan_change_mtu(struct net_device *dev, int new_mtu)
{
struct macvlan_dev *vlan = netdev_priv(dev);
if (vlan->lowerdev->mtu < new_mtu)
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
static int macvlan_hwtstamp_get(struct net_device *dev,
struct kernel_hwtstamp_config *cfg)
{
struct net_device *real_dev = macvlan_dev_real_dev(dev);
return generic_hwtstamp_get_lower(real_dev, cfg);
}
static int macvlan_hwtstamp_set(struct net_device *dev,
struct kernel_hwtstamp_config *cfg,
struct netlink_ext_ack *extack)
{
struct net_device *real_dev = macvlan_dev_real_dev(dev);
if (!net_eq(dev_net(dev), &init_net))
return -EOPNOTSUPP;
return generic_hwtstamp_set_lower(real_dev, cfg, extack);
}
/*
* macvlan network devices have devices nesting below it and are a special
* "super class" of normal network devices; split their locks off into a
* separate class since they always nest.
*/
static struct lock_class_key macvlan_netdev_addr_lock_key;
#define ALWAYS_ON_OFFLOADS \
(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \
NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL)
#define ALWAYS_ON_FEATURES (ALWAYS_ON_OFFLOADS | NETIF_F_LLTX)
#define MACVLAN_FEATURES \
(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
NETIF_F_GSO | NETIF_F_TSO | NETIF_F_LRO | \
NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \
NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
#define MACVLAN_STATE_MASK \
((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
static void macvlan_set_lockdep_class(struct net_device *dev)
{
netdev_lockdep_set_classes(dev);
lockdep_set_class(&dev->addr_list_lock,
&macvlan_netdev_addr_lock_key);
}
static int macvlan_init(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
struct macvlan_port *port = vlan->port;
dev->state = (dev->state & ~MACVLAN_STATE_MASK) |
(lowerdev->state & MACVLAN_STATE_MASK);
dev->features = lowerdev->features & MACVLAN_FEATURES;
dev->features |= ALWAYS_ON_FEATURES;
dev->hw_features |= NETIF_F_LRO;
dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES;
dev->vlan_features |= ALWAYS_ON_OFFLOADS;
dev->hw_enc_features |= dev->features;
netif_inherit_tso_max(dev, lowerdev);
dev->hard_header_len = lowerdev->hard_header_len;
macvlan_set_lockdep_class(dev);
vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
if (!vlan->pcpu_stats)
return -ENOMEM;
port->count += 1;
/* Get macvlan's reference to lowerdev */
netdev_hold(lowerdev, &vlan->dev_tracker, GFP_KERNEL);
return 0;
}
static void macvlan_uninit(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct macvlan_port *port = vlan->port;
free_percpu(vlan->pcpu_stats);
macvlan_flush_sources(port, vlan);
port->count -= 1;
if (!port->count)
macvlan_port_destroy(port->dev);
}
static void macvlan_dev_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct macvlan_dev *vlan = netdev_priv(dev);
if (vlan->pcpu_stats) {
struct vlan_pcpu_stats *p;
u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes;
u32 rx_errors = 0, tx_dropped = 0;
unsigned int start;
int i;
for_each_possible_cpu(i) {
p = per_cpu_ptr(vlan->pcpu_stats, i);
do {
start = u64_stats_fetch_begin(&p->syncp);
rx_packets = u64_stats_read(&p->rx_packets);
rx_bytes = u64_stats_read(&p->rx_bytes);
rx_multicast = u64_stats_read(&p->rx_multicast);
tx_packets = u64_stats_read(&p->tx_packets);
tx_bytes = u64_stats_read(&p->tx_bytes);
} while (u64_stats_fetch_retry(&p->syncp, start));
stats->rx_packets += rx_packets;
stats->rx_bytes += rx_bytes;
stats->multicast += rx_multicast;
stats->tx_packets += tx_packets;
stats->tx_bytes += tx_bytes;
/* rx_errors & tx_dropped are u32, updated
* without syncp protection.
*/
rx_errors += READ_ONCE(p->rx_errors);
tx_dropped += READ_ONCE(p->tx_dropped);
}
stats->rx_errors = rx_errors;
stats->rx_dropped = rx_errors;
stats->tx_dropped = tx_dropped;