forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
netpoll.c
1363 lines (1142 loc) · 32 KB
/
netpoll.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
/*
* Common framework for low-level network console, dump, and debugger code
*
* Sep 8 2003 Matt Mackall <[email protected]>
*
* based on the netconsole code from:
*
* Copyright (C) 2001 Ingo Molnar <[email protected]>
* Copyright (C) 2002 Red Hat, Inc.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/moduleparam.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/string.h>
#include <linux/if_arp.h>
#include <linux/inetdevice.h>
#include <linux/inet.h>
#include <linux/interrupt.h>
#include <linux/netpoll.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/if_vlan.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/addrconf.h>
#include <net/ndisc.h>
#include <net/ip6_checksum.h>
#include <asm/unaligned.h>
#include <trace/events/napi.h>
/*
* We maintain a small pool of fully-sized skbs, to make sure the
* message gets out even in extreme OOM situations.
*/
#define MAX_UDP_CHUNK 1460
#define MAX_SKBS 32
static struct sk_buff_head skb_pool;
#ifdef CONFIG_NETPOLL_TRAP
static atomic_t trapped;
static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
#endif
DEFINE_STATIC_SRCU(netpoll_srcu);
#define USEC_PER_POLL 50
#define MAX_SKB_SIZE \
(sizeof(struct ethhdr) + \
sizeof(struct iphdr) + \
sizeof(struct udphdr) + \
MAX_UDP_CHUNK)
static void zap_completion_queue(void);
static void netpoll_async_cleanup(struct work_struct *work);
static unsigned int carrier_timeout = 4;
module_param(carrier_timeout, uint, 0644);
#define np_info(np, fmt, ...) \
pr_info("%s: " fmt, np->name, ##__VA_ARGS__)
#define np_err(np, fmt, ...) \
pr_err("%s: " fmt, np->name, ##__VA_ARGS__)
#define np_notice(np, fmt, ...) \
pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
static void queue_process(struct work_struct *work)
{
struct netpoll_info *npinfo =
container_of(work, struct netpoll_info, tx_work.work);
struct sk_buff *skb;
unsigned long flags;
while ((skb = skb_dequeue(&npinfo->txq))) {
struct net_device *dev = skb->dev;
const struct net_device_ops *ops = dev->netdev_ops;
struct netdev_queue *txq;
if (!netif_device_present(dev) || !netif_running(dev)) {
__kfree_skb(skb);
continue;
}
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
local_irq_save(flags);
__netif_tx_lock(txq, smp_processor_id());
if (netif_xmit_frozen_or_stopped(txq) ||
ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {
skb_queue_head(&npinfo->txq, skb);
__netif_tx_unlock(txq);
local_irq_restore(flags);
schedule_delayed_work(&npinfo->tx_work, HZ/10);
return;
}
__netif_tx_unlock(txq);
local_irq_restore(flags);
}
}
#ifdef CONFIG_NETPOLL_TRAP
static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
unsigned short ulen, __be32 saddr, __be32 daddr)
{
__wsum psum;
if (uh->check == 0 || skb_csum_unnecessary(skb))
return 0;
psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
if (skb->ip_summed == CHECKSUM_COMPLETE &&
!csum_fold(csum_add(psum, skb->csum)))
return 0;
skb->csum = psum;
return __skb_checksum_complete(skb);
}
#endif /* CONFIG_NETPOLL_TRAP */
/*
* Check whether delayed processing was scheduled for our NIC. If so,
* we attempt to grab the poll lock and use ->poll() to pump the card.
* If this fails, either we've recursed in ->poll() or it's already
* running on another CPU.
*
* Note: we don't mask interrupts with this lock because we're using
* trylock here and interrupts are already disabled in the softirq
* case. Further, we test the poll_owner to avoid recursion on UP
* systems where the lock doesn't exist.
*
* In cases where there is bi-directional communications, reading only
* one message at a time can lead to packets being dropped by the
* network adapter, forcing superfluous retries and possibly timeouts.
* Thus, we set our budget to greater than 1.
*/
static int poll_one_napi(struct napi_struct *napi, int budget)
{
int work;
/* net_rx_action's ->poll() invocations and our's are
* synchronized by this test which is only made while
* holding the napi->poll_lock.
*/
if (!test_bit(NAPI_STATE_SCHED, &napi->state))
return budget;
set_bit(NAPI_STATE_NPSVC, &napi->state);
work = napi->poll(napi, budget);
WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
trace_napi_poll(napi);
clear_bit(NAPI_STATE_NPSVC, &napi->state);
return budget - work;
}
static void poll_napi(struct net_device *dev, int budget)
{
struct napi_struct *napi;
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner != smp_processor_id() &&
spin_trylock(&napi->poll_lock)) {
budget = poll_one_napi(napi, budget);
spin_unlock(&napi->poll_lock);
}
}
}
#ifdef CONFIG_NETPOLL_TRAP
static void service_neigh_queue(struct net_device *dev,
struct netpoll_info *npi)
{
struct sk_buff *skb;
if (dev->flags & IFF_SLAVE) {
struct net_device *bond_dev;
struct netpoll_info *bond_ni;
bond_dev = netdev_master_upper_dev_get_rcu(dev);
bond_ni = rcu_dereference_bh(bond_dev->npinfo);
while ((skb = skb_dequeue(&npi->neigh_tx))) {
skb->dev = bond_dev;
skb_queue_tail(&bond_ni->neigh_tx, skb);
}
}
while ((skb = skb_dequeue(&npi->neigh_tx)))
netpoll_neigh_reply(skb, npi);
}
#else /* !CONFIG_NETPOLL_TRAP */
static inline void service_neigh_queue(struct net_device *dev,
struct netpoll_info *npi)
{
}
#endif /* CONFIG_NETPOLL_TRAP */
static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
bool rx_processing = netpoll_rx_processing(ni);
int budget = rx_processing? 16 : 0;
/* Don't do any rx activity if the dev_lock mutex is held
* the dev_open/close paths use this to block netpoll activity
* while changing device state
*/
if (down_trylock(&ni->dev_lock))
return;
if (!netif_running(dev)) {
up(&ni->dev_lock);
return;
}
if (rx_processing)
netpoll_set_trap(1);
ops = dev->netdev_ops;
if (!ops->ndo_poll_controller) {
up(&ni->dev_lock);
return;
}
/* Process pending work on NIC */
ops->ndo_poll_controller(dev);
poll_napi(dev, budget);
if (rx_processing)
netpoll_set_trap(0);
up(&ni->dev_lock);
service_neigh_queue(dev, ni);
zap_completion_queue();
}
void netpoll_rx_disable(struct net_device *dev)
{
struct netpoll_info *ni;
int idx;
might_sleep();
idx = srcu_read_lock(&netpoll_srcu);
ni = srcu_dereference(dev->npinfo, &netpoll_srcu);
if (ni)
down(&ni->dev_lock);
srcu_read_unlock(&netpoll_srcu, idx);
}
EXPORT_SYMBOL(netpoll_rx_disable);
void netpoll_rx_enable(struct net_device *dev)
{
struct netpoll_info *ni;
rcu_read_lock();
ni = rcu_dereference(dev->npinfo);
if (ni)
up(&ni->dev_lock);
rcu_read_unlock();
}
EXPORT_SYMBOL(netpoll_rx_enable);
static void refill_skbs(void)
{
struct sk_buff *skb;
unsigned long flags;
spin_lock_irqsave(&skb_pool.lock, flags);
while (skb_pool.qlen < MAX_SKBS) {
skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC);
if (!skb)
break;
__skb_queue_tail(&skb_pool, skb);
}
spin_unlock_irqrestore(&skb_pool.lock, flags);
}
static void zap_completion_queue(void)
{
unsigned long flags;
struct softnet_data *sd = &get_cpu_var(softnet_data);
if (sd->completion_queue) {
struct sk_buff *clist;
local_irq_save(flags);
clist = sd->completion_queue;
sd->completion_queue = NULL;
local_irq_restore(flags);
while (clist != NULL) {
struct sk_buff *skb = clist;
clist = clist->next;
if (skb->destructor) {
atomic_inc(&skb->users);
dev_kfree_skb_any(skb); /* put this one back */
} else {
__kfree_skb(skb);
}
}
}
put_cpu_var(softnet_data);
}
static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve)
{
int count = 0;
struct sk_buff *skb;
zap_completion_queue();
refill_skbs();
repeat:
skb = alloc_skb(len, GFP_ATOMIC);
if (!skb)
skb = skb_dequeue(&skb_pool);
if (!skb) {
if (++count < 10) {
netpoll_poll_dev(np->dev);
goto repeat;
}
return NULL;
}
atomic_set(&skb->users, 1);
skb_reserve(skb, reserve);
return skb;
}
static int netpoll_owner_active(struct net_device *dev)
{
struct napi_struct *napi;
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner == smp_processor_id())
return 1;
}
return 0;
}
/* call with IRQ disabled */
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
struct net_device *dev)
{
int status = NETDEV_TX_BUSY;
unsigned long tries;
const struct net_device_ops *ops = dev->netdev_ops;
/* It is up to the caller to keep npinfo alive. */
struct netpoll_info *npinfo;
WARN_ON_ONCE(!irqs_disabled());
npinfo = rcu_dereference_bh(np->dev->npinfo);
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
__kfree_skb(skb);
return;
}
/* don't get messages out of order, and no recursion */
if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
struct netdev_queue *txq;
txq = netdev_pick_tx(dev, skb, NULL);
/* try until next clock tick */
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
tries > 0; --tries) {
if (__netif_tx_trylock(txq)) {
if (!netif_xmit_stopped(txq)) {
if (vlan_tx_tag_present(skb) &&
!vlan_hw_offload_capable(netif_skb_features(skb),
skb->vlan_proto)) {
skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
if (unlikely(!skb)) {
/* This is actually a packet drop, but we
* don't want the code at the end of this
* function to try and re-queue a NULL skb.
*/
status = NETDEV_TX_OK;
goto unlock_txq;
}
skb->vlan_tci = 0;
}
status = ops->ndo_start_xmit(skb, dev);
if (status == NETDEV_TX_OK)
txq_trans_update(txq);
}
unlock_txq:
__netif_tx_unlock(txq);
if (status == NETDEV_TX_OK)
break;
}
/* tickle device maybe there is some cleanup */
netpoll_poll_dev(np->dev);
udelay(USEC_PER_POLL);
}
WARN_ONCE(!irqs_disabled(),
"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
dev->name, ops->ndo_start_xmit);
}
if (status != NETDEV_TX_OK) {
skb_queue_tail(&npinfo->txq, skb);
schedule_delayed_work(&npinfo->tx_work,0);
}
}
EXPORT_SYMBOL(netpoll_send_skb_on_dev);
void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
{
int total_len, ip_len, udp_len;
struct sk_buff *skb;
struct udphdr *udph;
struct iphdr *iph;
struct ethhdr *eth;
static atomic_t ip_ident;
struct ipv6hdr *ip6h;
udp_len = len + sizeof(*udph);
if (np->ipv6)
ip_len = udp_len + sizeof(*ip6h);
else
ip_len = udp_len + sizeof(*iph);
total_len = ip_len + LL_RESERVED_SPACE(np->dev);
skb = find_skb(np, total_len + np->dev->needed_tailroom,
total_len - len);
if (!skb)
return;
skb_copy_to_linear_data(skb, msg, len);
skb_put(skb, len);
skb_push(skb, sizeof(*udph));
skb_reset_transport_header(skb);
udph = udp_hdr(skb);
udph->source = htons(np->local_port);
udph->dest = htons(np->remote_port);
udph->len = htons(udp_len);
if (np->ipv6) {
udph->check = 0;
udph->check = csum_ipv6_magic(&np->local_ip.in6,
&np->remote_ip.in6,
udp_len, IPPROTO_UDP,
csum_partial(udph, udp_len, 0));
if (udph->check == 0)
udph->check = CSUM_MANGLED_0;
skb_push(skb, sizeof(*ip6h));
skb_reset_network_header(skb);
ip6h = ipv6_hdr(skb);
/* ip6h->version = 6; ip6h->priority = 0; */
put_unaligned(0x60, (unsigned char *)ip6h);
ip6h->flow_lbl[0] = 0;
ip6h->flow_lbl[1] = 0;
ip6h->flow_lbl[2] = 0;
ip6h->payload_len = htons(sizeof(struct udphdr) + len);
ip6h->nexthdr = IPPROTO_UDP;
ip6h->hop_limit = 32;
ip6h->saddr = np->local_ip.in6;
ip6h->daddr = np->remote_ip.in6;
eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb->protocol = eth->h_proto = htons(ETH_P_IPV6);
} else {
udph->check = 0;
udph->check = csum_tcpudp_magic(np->local_ip.ip,
np->remote_ip.ip,
udp_len, IPPROTO_UDP,
csum_partial(udph, udp_len, 0));
if (udph->check == 0)
udph->check = CSUM_MANGLED_0;
skb_push(skb, sizeof(*iph));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
/* iph->version = 4; iph->ihl = 5; */
put_unaligned(0x45, (unsigned char *)iph);
iph->tos = 0;
put_unaligned(htons(ip_len), &(iph->tot_len));
iph->id = htons(atomic_inc_return(&ip_ident));
iph->frag_off = 0;
iph->ttl = 64;
iph->protocol = IPPROTO_UDP;
iph->check = 0;
put_unaligned(np->local_ip.ip, &(iph->saddr));
put_unaligned(np->remote_ip.ip, &(iph->daddr));
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb->protocol = eth->h_proto = htons(ETH_P_IP);
}
ether_addr_copy(eth->h_source, np->dev->dev_addr);
ether_addr_copy(eth->h_dest, np->remote_mac);
skb->dev = np->dev;
netpoll_send_skb(np, skb);
}
EXPORT_SYMBOL(netpoll_send_udp);
#ifdef CONFIG_NETPOLL_TRAP
static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
{
int size, type = ARPOP_REPLY;
__be32 sip, tip;
unsigned char *sha;
struct sk_buff *send_skb;
struct netpoll *np, *tmp;
unsigned long flags;
int hlen, tlen;
int hits = 0, proto;
if (!netpoll_rx_processing(npinfo))
return;
/* Before checking the packet, we do some early
inspection whether this is interesting at all */
spin_lock_irqsave(&npinfo->rx_lock, flags);
list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
if (np->dev == skb->dev)
hits++;
}
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
/* No netpoll struct is using this dev */
if (!hits)
return;
proto = ntohs(eth_hdr(skb)->h_proto);
if (proto == ETH_P_ARP) {
struct arphdr *arp;
unsigned char *arp_ptr;
/* No arp on this interface */
if (skb->dev->flags & IFF_NOARP)
return;
if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
return;
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
arp = arp_hdr(skb);
if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
arp->ar_pro != htons(ETH_P_IP) ||
arp->ar_op != htons(ARPOP_REQUEST))
return;
arp_ptr = (unsigned char *)(arp+1);
/* save the location of the src hw addr */
sha = arp_ptr;
arp_ptr += skb->dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4;
/* If we actually cared about dst hw addr,
it would get copied here */
arp_ptr += skb->dev->addr_len;
memcpy(&tip, arp_ptr, 4);
/* Should we ignore arp? */
if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
return;
size = arp_hdr_len(skb->dev);
spin_lock_irqsave(&npinfo->rx_lock, flags);
list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
if (tip != np->local_ip.ip)
continue;
hlen = LL_RESERVED_SPACE(np->dev);
tlen = np->dev->needed_tailroom;
send_skb = find_skb(np, size + hlen + tlen, hlen);
if (!send_skb)
continue;
skb_reset_network_header(send_skb);
arp = (struct arphdr *) skb_put(send_skb, size);
send_skb->dev = skb->dev;
send_skb->protocol = htons(ETH_P_ARP);
/* Fill the device header for the ARP frame */
if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP,
sha, np->dev->dev_addr,
send_skb->len) < 0) {
kfree_skb(send_skb);
continue;
}
/*
* Fill out the arp protocol part.
*
* we only support ethernet device type,
* which (according to RFC 1390) should
* always equal 1 (Ethernet).
*/
arp->ar_hrd = htons(np->dev->type);
arp->ar_pro = htons(ETH_P_IP);
arp->ar_hln = np->dev->addr_len;
arp->ar_pln = 4;
arp->ar_op = htons(type);
arp_ptr = (unsigned char *)(arp + 1);
memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
arp_ptr += np->dev->addr_len;
memcpy(arp_ptr, &tip, 4);
arp_ptr += 4;
memcpy(arp_ptr, sha, np->dev->addr_len);
arp_ptr += np->dev->addr_len;
memcpy(arp_ptr, &sip, 4);
netpoll_send_skb(np, send_skb);
/* If there are several rx_skb_hooks for the same
* address we're fine by sending a single reply
*/
break;
}
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
} else if( proto == ETH_P_IPV6) {
#if IS_ENABLED(CONFIG_IPV6)
struct nd_msg *msg;
u8 *lladdr = NULL;
struct ipv6hdr *hdr;
struct icmp6hdr *icmp6h;
const struct in6_addr *saddr;
const struct in6_addr *daddr;
struct inet6_dev *in6_dev = NULL;
struct in6_addr *target;
in6_dev = in6_dev_get(skb->dev);
if (!in6_dev || !in6_dev->cnf.accept_ra)
return;
if (!pskb_may_pull(skb, skb->len))
return;
msg = (struct nd_msg *)skb_transport_header(skb);
__skb_push(skb, skb->data - skb_transport_header(skb));
if (ipv6_hdr(skb)->hop_limit != 255)
return;
if (msg->icmph.icmp6_code != 0)
return;
if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
return;
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr);
spin_lock_irqsave(&npinfo->rx_lock, flags);
list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
if (!ipv6_addr_equal(daddr, &np->local_ip.in6))
continue;
hlen = LL_RESERVED_SPACE(np->dev);
tlen = np->dev->needed_tailroom;
send_skb = find_skb(np, size + hlen + tlen, hlen);
if (!send_skb)
continue;
send_skb->protocol = htons(ETH_P_IPV6);
send_skb->dev = skb->dev;
skb_reset_network_header(send_skb);
hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr));
*(__be32*)hdr = htonl(0x60000000);
hdr->payload_len = htons(size);
hdr->nexthdr = IPPROTO_ICMPV6;
hdr->hop_limit = 255;
hdr->saddr = *saddr;
hdr->daddr = *daddr;
icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr));
icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
icmp6h->icmp6_router = 0;
icmp6h->icmp6_solicited = 1;
target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr));
*target = msg->target;
icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
IPPROTO_ICMPV6,
csum_partial(icmp6h,
size, 0));
if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6,
lladdr, np->dev->dev_addr,
send_skb->len) < 0) {
kfree_skb(send_skb);
continue;
}
netpoll_send_skb(np, send_skb);
/* If there are several rx_skb_hooks for the same
* address, we're fine by sending a single reply
*/
break;
}
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
#endif
}
}
static bool pkt_is_ns(struct sk_buff *skb)
{
struct nd_msg *msg;
struct ipv6hdr *hdr;
if (skb->protocol != htons(ETH_P_ARP))
return false;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
return false;
msg = (struct nd_msg *)skb_transport_header(skb);
__skb_push(skb, skb->data - skb_transport_header(skb));
hdr = ipv6_hdr(skb);
if (hdr->nexthdr != IPPROTO_ICMPV6)
return false;
if (hdr->hop_limit != 255)
return false;
if (msg->icmph.icmp6_code != 0)
return false;
if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
return false;
return true;
}
int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
{
int proto, len, ulen, data_len;
int hits = 0, offset;
const struct iphdr *iph;
struct udphdr *uh;
struct netpoll *np, *tmp;
uint16_t source;
if (!netpoll_rx_processing(npinfo))
goto out;
if (skb->dev->type != ARPHRD_ETHER)
goto out;
/* check if netpoll clients need ARP */
if (skb->protocol == htons(ETH_P_ARP) && netpoll_trap()) {
skb_queue_tail(&npinfo->neigh_tx, skb);
return 1;
} else if (pkt_is_ns(skb) && netpoll_trap()) {
skb_queue_tail(&npinfo->neigh_tx, skb);
return 1;
}
if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
goto out;
}
proto = ntohs(eth_hdr(skb)->h_proto);
if (proto != ETH_P_IP && proto != ETH_P_IPV6)
goto out;
if (skb->pkt_type == PACKET_OTHERHOST)
goto out;
if (skb_shared(skb))
goto out;
if (proto == ETH_P_IP) {
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto out;
iph = (struct iphdr *)skb->data;
if (iph->ihl < 5 || iph->version != 4)
goto out;
if (!pskb_may_pull(skb, iph->ihl*4))
goto out;
iph = (struct iphdr *)skb->data;
if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
goto out;
len = ntohs(iph->tot_len);
if (skb->len < len || len < iph->ihl*4)
goto out;
/*
* Our transport medium may have padded the buffer out.
* Now We trim to the true length of the frame.
*/
if (pskb_trim_rcsum(skb, len))
goto out;
iph = (struct iphdr *)skb->data;
if (iph->protocol != IPPROTO_UDP)
goto out;
len -= iph->ihl*4;
uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
offset = (unsigned char *)(uh + 1) - skb->data;
ulen = ntohs(uh->len);
data_len = skb->len - offset;
source = ntohs(uh->source);
if (ulen != len)
goto out;
if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
goto out;
list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
if (np->local_ip.ip && np->local_ip.ip != iph->daddr)
continue;
if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr)
continue;
if (np->local_port && np->local_port != ntohs(uh->dest))
continue;
np->rx_skb_hook(np, source, skb, offset, data_len);
hits++;
}
} else {
#if IS_ENABLED(CONFIG_IPV6)
const struct ipv6hdr *ip6h;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
ip6h = (struct ipv6hdr *)skb->data;
if (ip6h->version != 6)
goto out;
len = ntohs(ip6h->payload_len);
if (!len)
goto out;
if (len + sizeof(struct ipv6hdr) > skb->len)
goto out;
if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr)))
goto out;
ip6h = ipv6_hdr(skb);
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
uh = udp_hdr(skb);
offset = (unsigned char *)(uh + 1) - skb->data;
ulen = ntohs(uh->len);
data_len = skb->len - offset;
source = ntohs(uh->source);
if (ulen != skb->len)
goto out;
if (udp6_csum_init(skb, uh, IPPROTO_UDP))
goto out;
list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr))
continue;
if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr))
continue;
if (np->local_port && np->local_port != ntohs(uh->dest))
continue;
np->rx_skb_hook(np, source, skb, offset, data_len);
hits++;
}
#endif
}
if (!hits)
goto out;
kfree_skb(skb);
return 1;
out:
if (netpoll_trap()) {
kfree_skb(skb);
return 1;
}
return 0;
}
static void netpoll_trap_setup_info(struct netpoll_info *npinfo)
{
INIT_LIST_HEAD(&npinfo->rx_np);
spin_lock_init(&npinfo->rx_lock);
skb_queue_head_init(&npinfo->neigh_tx);
}
static void netpoll_trap_cleanup_info(struct netpoll_info *npinfo)
{
skb_queue_purge(&npinfo->neigh_tx);
}
static void netpoll_trap_setup(struct netpoll *np, struct netpoll_info *npinfo)
{
unsigned long flags;
if (np->rx_skb_hook) {
spin_lock_irqsave(&npinfo->rx_lock, flags);
list_add_tail(&np->rx, &npinfo->rx_np);
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
}
static void netpoll_trap_cleanup(struct netpoll *np, struct netpoll_info *npinfo)
{
unsigned long flags;
if (!list_empty(&npinfo->rx_np)) {
spin_lock_irqsave(&npinfo->rx_lock, flags);
list_del(&np->rx);
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
}
#else /* !CONFIG_NETPOLL_TRAP */
static inline void netpoll_trap_setup_info(struct netpoll_info *npinfo)
{
}
static inline void netpoll_trap_cleanup_info(struct netpoll_info *npinfo)
{
}
static inline
void netpoll_trap_setup(struct netpoll *np, struct netpoll_info *npinfo)
{
}
static inline
void netpoll_trap_cleanup(struct netpoll *np, struct netpoll_info *npinfo)
{
}
#endif /* CONFIG_NETPOLL_TRAP */
void netpoll_print_options(struct netpoll *np)
{
np_info(np, "local port %d\n", np->local_port);
if (np->ipv6)
np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
else
np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
np_info(np, "interface '%s'\n", np->dev_name);
np_info(np, "remote port %d\n", np->remote_port);
if (np->ipv6)
np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
else
np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip);
np_info(np, "remote ethernet address %pM\n", np->remote_mac);
}
EXPORT_SYMBOL(netpoll_print_options);
static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr)
{
const char *end;
if (!strchr(str, ':') &&
in4_pton(str, -1, (void *)addr, -1, &end) > 0) {
if (!*end)
return 0;
}
if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) {
#if IS_ENABLED(CONFIG_IPV6)
if (!*end)
return 1;
#else
return -1;
#endif
}
return -1;
}
int netpoll_parse_options(struct netpoll *np, char *opt)
{