forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathaf_packet.c
3115 lines (2640 loc) · 69 KB
/
af_packet.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
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* PACKET - implements raw packet sockets.
*
* Authors: Ross Biro
* Fred N. van Kempen, <[email protected]>
* Alan Cox, <[email protected]>
*
* Fixes:
* Alan Cox : verify_area() now used correctly
* Alan Cox : new skbuff lists, look ma no backlogs!
* Alan Cox : tidied skbuff lists.
* Alan Cox : Now uses generic datagram routines I
* added. Also fixed the peek/read crash
* from all old Linux datagram code.
* Alan Cox : Uses the improved datagram code.
* Alan Cox : Added NULL's for socket options.
* Alan Cox : Re-commented the code.
* Alan Cox : Use new kernel side addressing
* Rob Janssen : Correct MTU usage.
* Dave Platt : Counter leaks caused by incorrect
* interrupt locking and some slightly
* dubious gcc output. Can you read
* compiler: it said _VOLATILE_
* Richard Kooijman : Timestamp fixes.
* Alan Cox : New buffers. Use sk->mac.raw.
* Alan Cox : sendmsg/recvmsg support.
* Alan Cox : Protocol setting support
* Alexey Kuznetsov : Untied from IPv4 stack.
* Cyrus Durgin : Fixed kerneld for kmod.
* Michal Ostrowski : Module initialization cleanup.
* Ulises Alonso : Frame number limit removal and
* packet_set_ring memory leak.
* Eric Biederman : Allow for > 8 byte hardware addresses.
* The convention is that longer addresses
* will simply extend the hardware address
* byte arrays at the end of sockaddr_ll
* and packet_mreq.
* Johann Baudy : Added TX RING.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
*/
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/capability.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/if_packet.h>
#include <linux/wireless.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
#include <asm/page.h>
#include <asm/cacheflush.h>
#include <asm/io.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/if_vlan.h>
#include <linux/virtio_net.h>
#include <linux/errqueue.h>
#include <linux/net_tstamp.h>
#ifdef CONFIG_INET
#include <net/inet_common.h>
#endif
/*
Assumptions:
- if device has no dev->hard_header routine, it adds and removes ll header
inside itself. In this case ll header is invisible outside of device,
but higher levels still should reserve dev->hard_header_len.
Some devices are enough clever to reallocate skb, when header
will not fit to reserved space (tunnel), another ones are silly
(PPP).
- packet socket receives packets with pulled ll header,
so that SOCK_RAW should push it back.
On receive:
-----------
Incoming, dev->hard_header!=NULL
mac_header -> ll header
data -> data
Outgoing, dev->hard_header!=NULL
mac_header -> ll header
data -> ll header
Incoming, dev->hard_header==NULL
mac_header -> UNKNOWN position. It is very likely, that it points to ll
header. PPP makes it, that is wrong, because introduce
assymetry between rx and tx paths.
data -> data
Outgoing, dev->hard_header==NULL
mac_header -> data. ll header is still not built!
data -> data
Resume
If dev->hard_header==NULL we are unlikely to restore sensible ll header.
On transmit:
------------
dev->hard_header != NULL
mac_header -> ll header
data -> ll header
dev->hard_header == NULL (ll header is added by device, we cannot control it)
mac_header -> data
data -> data
We should set nh.raw on output to correct posistion,
packet classifier depends on it.
*/
/* Private packet socket structures. */
struct packet_mclist {
struct packet_mclist *next;
int ifindex;
int count;
unsigned short type;
unsigned short alen;
unsigned char addr[MAX_ADDR_LEN];
};
/* identical to struct packet_mreq except it has
* a longer address field.
*/
struct packet_mreq_max {
int mr_ifindex;
unsigned short mr_type;
unsigned short mr_alen;
unsigned char mr_address[MAX_ADDR_LEN];
};
static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
int closing, int tx_ring);
struct pgv {
char *buffer;
};
struct packet_ring_buffer {
struct pgv *pg_vec;
unsigned int head;
unsigned int frames_per_block;
unsigned int frame_size;
unsigned int frame_max;
unsigned int pg_vec_order;
unsigned int pg_vec_pages;
unsigned int pg_vec_len;
atomic_t pending;
};
struct packet_sock;
static int tpacket_snd(struct packet_sock *po, struct msghdr *msg);
static void packet_flush_mclist(struct sock *sk);
struct packet_fanout;
struct packet_sock {
/* struct sock has to be the first member of packet_sock */
struct sock sk;
struct packet_fanout *fanout;
struct tpacket_stats stats;
struct packet_ring_buffer rx_ring;
struct packet_ring_buffer tx_ring;
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
unsigned int running:1, /* prot_hook is attached*/
auxdata:1,
origdev:1,
has_vnet_hdr:1;
int ifindex; /* bound device */
__be16 num;
struct packet_mclist *mclist;
atomic_t mapped;
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
unsigned int tp_loss:1;
unsigned int tp_tstamp;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
#define PACKET_FANOUT_MAX 256
struct packet_fanout {
#ifdef CONFIG_NET_NS
struct net *net;
#endif
unsigned int num_members;
u16 id;
u8 type;
u8 defrag;
atomic_t rr_cur;
struct list_head list;
struct sock *arr[PACKET_FANOUT_MAX];
spinlock_t lock;
atomic_t sk_ref;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
struct packet_skb_cb {
unsigned int origlen;
union {
struct sockaddr_pkt pkt;
struct sockaddr_ll ll;
} sa;
};
#define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb))
static inline struct packet_sock *pkt_sk(struct sock *sk)
{
return (struct packet_sock *)sk;
}
static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
static void __fanout_link(struct sock *sk, struct packet_sock *po);
/* register_prot_hook must be invoked with the po->bind_lock held,
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
*/
static void register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
if (!po->running) {
if (po->fanout)
__fanout_link(sk, po);
else
dev_add_pack(&po->prot_hook);
sock_hold(sk);
po->running = 1;
}
}
/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
* held. If the sync parameter is true, we will temporarily drop
* the po->bind_lock and do a synchronize_net to make sure no
* asynchronous packet processing paths still refer to the elements
* of po->prot_hook. If the sync parameter is false, it is the
* callers responsibility to take care of this.
*/
static void __unregister_prot_hook(struct sock *sk, bool sync)
{
struct packet_sock *po = pkt_sk(sk);
po->running = 0;
if (po->fanout)
__fanout_unlink(sk, po);
else
__dev_remove_pack(&po->prot_hook);
__sock_put(sk);
if (sync) {
spin_unlock(&po->bind_lock);
synchronize_net();
spin_lock(&po->bind_lock);
}
}
static void unregister_prot_hook(struct sock *sk, bool sync)
{
struct packet_sock *po = pkt_sk(sk);
if (po->running)
__unregister_prot_hook(sk, sync);
}
static inline __pure struct page *pgv_to_page(void *addr)
{
if (is_vmalloc_addr(addr))
return vmalloc_to_page(addr);
return virt_to_page(addr);
}
static void __packet_set_status(struct packet_sock *po, void *frame, int status)
{
union {
struct tpacket_hdr *h1;
struct tpacket2_hdr *h2;
void *raw;
} h;
h.raw = frame;
switch (po->tp_version) {
case TPACKET_V1:
h.h1->tp_status = status;
flush_dcache_page(pgv_to_page(&h.h1->tp_status));
break;
case TPACKET_V2:
h.h2->tp_status = status;
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
break;
default:
pr_err("TPACKET version not supported\n");
BUG();
}
smp_wmb();
}
static int __packet_get_status(struct packet_sock *po, void *frame)
{
union {
struct tpacket_hdr *h1;
struct tpacket2_hdr *h2;
void *raw;
} h;
smp_rmb();
h.raw = frame;
switch (po->tp_version) {
case TPACKET_V1:
flush_dcache_page(pgv_to_page(&h.h1->tp_status));
return h.h1->tp_status;
case TPACKET_V2:
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
return h.h2->tp_status;
default:
pr_err("TPACKET version not supported\n");
BUG();
return 0;
}
}
static void *packet_lookup_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
unsigned int position,
int status)
{
unsigned int pg_vec_pos, frame_offset;
union {
struct tpacket_hdr *h1;
struct tpacket2_hdr *h2;
void *raw;
} h;
pg_vec_pos = position / rb->frames_per_block;
frame_offset = position % rb->frames_per_block;
h.raw = rb->pg_vec[pg_vec_pos].buffer +
(frame_offset * rb->frame_size);
if (status != __packet_get_status(po, h.raw))
return NULL;
return h.raw;
}
static inline void *packet_current_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status)
{
return packet_lookup_frame(po, rb, rb->head, status);
}
static inline void *packet_previous_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status)
{
unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max;
return packet_lookup_frame(po, rb, previous, status);
}
static inline void packet_increment_head(struct packet_ring_buffer *buff)
{
buff->head = buff->head != buff->frame_max ? buff->head+1 : 0;
}
static void packet_sock_destruct(struct sock *sk)
{
skb_queue_purge(&sk->sk_error_queue);
WARN_ON(atomic_read(&sk->sk_rmem_alloc));
WARN_ON(atomic_read(&sk->sk_wmem_alloc));
if (!sock_flag(sk, SOCK_DEAD)) {
pr_err("Attempt to release alive packet socket: %p\n", sk);
return;
}
sk_refcnt_debug_dec(sk);
}
static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
{
int x = atomic_read(&f->rr_cur) + 1;
if (x >= num)
x = 0;
return x;
}
static struct sock *fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
{
u32 idx, hash = skb->rxhash;
idx = ((u64)hash * num) >> 32;
return f->arr[idx];
}
static struct sock *fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
{
int cur, old;
cur = atomic_read(&f->rr_cur);
while ((old = atomic_cmpxchg(&f->rr_cur, cur,
fanout_rr_next(f, num))) != cur)
cur = old;
return f->arr[cur];
}
static struct sock *fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
{
unsigned int cpu = smp_processor_id();
return f->arr[cpu % num];
}
static struct sk_buff *fanout_check_defrag(struct sk_buff *skb)
{
#ifdef CONFIG_INET
const struct iphdr *iph;
u32 len;
if (skb->protocol != htons(ETH_P_IP))
return skb;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
return skb;
iph = ip_hdr(skb);
if (iph->ihl < 5 || iph->version != 4)
return skb;
if (!pskb_may_pull(skb, iph->ihl*4))
return skb;
iph = ip_hdr(skb);
len = ntohs(iph->tot_len);
if (skb->len < len || len < (iph->ihl * 4))
return skb;
if (ip_is_fragment(ip_hdr(skb))) {
skb = skb_share_check(skb, GFP_ATOMIC);
if (skb) {
if (pskb_trim_rcsum(skb, len))
return skb;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
if (ip_defrag(skb, IP_DEFRAG_AF_PACKET))
return NULL;
skb->rxhash = 0;
}
}
#endif
return skb;
}
static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct packet_fanout *f = pt->af_packet_priv;
unsigned int num = f->num_members;
struct packet_sock *po;
struct sock *sk;
if (!net_eq(dev_net(dev), read_pnet(&f->net)) ||
!num) {
kfree_skb(skb);
return 0;
}
switch (f->type) {
case PACKET_FANOUT_HASH:
default:
if (f->defrag) {
skb = fanout_check_defrag(skb);
if (!skb)
return 0;
}
skb_get_rxhash(skb);
sk = fanout_demux_hash(f, skb, num);
break;
case PACKET_FANOUT_LB:
sk = fanout_demux_lb(f, skb, num);
break;
case PACKET_FANOUT_CPU:
sk = fanout_demux_cpu(f, skb, num);
break;
}
po = pkt_sk(sk);
return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev);
}
static DEFINE_MUTEX(fanout_mutex);
static LIST_HEAD(fanout_list);
static void __fanout_link(struct sock *sk, struct packet_sock *po)
{
struct packet_fanout *f = po->fanout;
spin_lock(&f->lock);
f->arr[f->num_members] = sk;
smp_wmb();
f->num_members++;
spin_unlock(&f->lock);
}
static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
{
struct packet_fanout *f = po->fanout;
int i;
spin_lock(&f->lock);
for (i = 0; i < f->num_members; i++) {
if (f->arr[i] == sk)
break;
}
BUG_ON(i >= f->num_members);
f->arr[i] = f->arr[f->num_members - 1];
f->num_members--;
spin_unlock(&f->lock);
}
static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
{
struct packet_sock *po = pkt_sk(sk);
struct packet_fanout *f, *match;
u8 type = type_flags & 0xff;
u8 defrag = (type_flags & PACKET_FANOUT_FLAG_DEFRAG) ? 1 : 0;
int err;
switch (type) {
case PACKET_FANOUT_HASH:
case PACKET_FANOUT_LB:
case PACKET_FANOUT_CPU:
break;
default:
return -EINVAL;
}
if (!po->running)
return -EINVAL;
if (po->fanout)
return -EALREADY;
mutex_lock(&fanout_mutex);
match = NULL;
list_for_each_entry(f, &fanout_list, list) {
if (f->id == id &&
read_pnet(&f->net) == sock_net(sk)) {
match = f;
break;
}
}
err = -EINVAL;
if (match && match->defrag != defrag)
goto out;
if (!match) {
err = -ENOMEM;
match = kzalloc(sizeof(*match), GFP_KERNEL);
if (!match)
goto out;
write_pnet(&match->net, sock_net(sk));
match->id = id;
match->type = type;
match->defrag = defrag;
atomic_set(&match->rr_cur, 0);
INIT_LIST_HEAD(&match->list);
spin_lock_init(&match->lock);
atomic_set(&match->sk_ref, 0);
match->prot_hook.type = po->prot_hook.type;
match->prot_hook.dev = po->prot_hook.dev;
match->prot_hook.func = packet_rcv_fanout;
match->prot_hook.af_packet_priv = match;
dev_add_pack(&match->prot_hook);
list_add(&match->list, &fanout_list);
}
err = -EINVAL;
if (match->type == type &&
match->prot_hook.type == po->prot_hook.type &&
match->prot_hook.dev == po->prot_hook.dev) {
err = -ENOSPC;
if (atomic_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
__dev_remove_pack(&po->prot_hook);
po->fanout = match;
atomic_inc(&match->sk_ref);
__fanout_link(sk, po);
err = 0;
}
}
out:
mutex_unlock(&fanout_mutex);
return err;
}
static void fanout_release(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
struct packet_fanout *f;
f = po->fanout;
if (!f)
return;
po->fanout = NULL;
mutex_lock(&fanout_mutex);
if (atomic_dec_and_test(&f->sk_ref)) {
list_del(&f->list);
dev_remove_pack(&f->prot_hook);
kfree(f);
}
mutex_unlock(&fanout_mutex);
}
static const struct proto_ops packet_ops;
static const struct proto_ops packet_ops_spkt;
static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct sock *sk;
struct sockaddr_pkt *spkt;
/*
* When we registered the protocol we saved the socket in the data
* field for just this event.
*/
sk = pt->af_packet_priv;
/*
* Yank back the headers [hope the device set this
* right or kerboom...]
*
* Incoming packets have ll header pulled,
* push it back.
*
* For outgoing ones skb->data == skb_mac_header(skb)
* so that this procedure is noop.
*/
if (skb->pkt_type == PACKET_LOOPBACK)
goto out;
if (!net_eq(dev_net(dev), sock_net(sk)))
goto out;
skb = skb_share_check(skb, GFP_ATOMIC);
if (skb == NULL)
goto oom;
/* drop any routing info */
skb_dst_drop(skb);
/* drop conntrack reference */
nf_reset(skb);
spkt = &PACKET_SKB_CB(skb)->sa.pkt;
skb_push(skb, skb->data - skb_mac_header(skb));
/*
* The SOCK_PACKET socket receives _all_ frames.
*/
spkt->spkt_family = dev->type;
strlcpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device));
spkt->spkt_protocol = skb->protocol;
/*
* Charge the memory to the socket. This is done specifically
* to prevent sockets using all the memory up.
*/
if (sock_queue_rcv_skb(sk, skb) == 0)
return 0;
out:
kfree_skb(skb);
oom:
return 0;
}
/*
* Output a raw packet to a device layer. This bypasses all the other
* protocol layers and you must therefore supply it with a complete frame
*/
static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t len)
{
struct sock *sk = sock->sk;
struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name;
struct sk_buff *skb = NULL;
struct net_device *dev;
__be16 proto = 0;
int err;
/*
* Get and verify the address.
*/
if (saddr) {
if (msg->msg_namelen < sizeof(struct sockaddr))
return -EINVAL;
if (msg->msg_namelen == sizeof(struct sockaddr_pkt))
proto = saddr->spkt_protocol;
} else
return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */
/*
* Find the device first to size check it
*/
saddr->spkt_device[13] = 0;
retry:
rcu_read_lock();
dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device);
err = -ENODEV;
if (dev == NULL)
goto out_unlock;
err = -ENETDOWN;
if (!(dev->flags & IFF_UP))
goto out_unlock;
/*
* You may not queue a frame bigger than the mtu. This is the lowest level
* raw protocol and you must do your own fragmentation at this level.
*/
err = -EMSGSIZE;
if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN)
goto out_unlock;
if (!skb) {
size_t reserved = LL_RESERVED_SPACE(dev);
unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0;
rcu_read_unlock();
skb = sock_wmalloc(sk, len + reserved, 0, GFP_KERNEL);
if (skb == NULL)
return -ENOBUFS;
/* FIXME: Save some space for broken drivers that write a hard
* header at transmission time by themselves. PPP is the notable
* one here. This should really be fixed at the driver level.
*/
skb_reserve(skb, reserved);
skb_reset_network_header(skb);
/* Try to align data part correctly */
if (hhlen) {
skb->data -= hhlen;
skb->tail -= hhlen;
if (len < hhlen)
skb_reset_network_header(skb);
}
err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
if (err)
goto out_free;
goto retry;
}
if (len > (dev->mtu + dev->hard_header_len)) {
/* Earlier code assumed this would be a VLAN pkt,
* double-check this now that we have the actual
* packet in hand.
*/
struct ethhdr *ehdr;
skb_reset_mac_header(skb);
ehdr = eth_hdr(skb);
if (ehdr->h_proto != htons(ETH_P_8021Q)) {
err = -EMSGSIZE;
goto out_unlock;
}
}
skb->protocol = proto;
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
err = sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
if (err < 0)
goto out_unlock;
dev_queue_xmit(skb);
rcu_read_unlock();
return len;
out_unlock:
rcu_read_unlock();
out_free:
kfree_skb(skb);
return err;
}
static inline unsigned int run_filter(const struct sk_buff *skb,
const struct sock *sk,
unsigned int res)
{
struct sk_filter *filter;
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter != NULL)
res = SK_RUN_FILTER(filter, skb);
rcu_read_unlock();
return res;
}
/*
* This function makes lazy skb cloning in hope that most of packets
* are discarded by BPF.
*
* Note tricky part: we DO mangle shared skb! skb->data, skb->len
* and skb->cb are mangled. It works because (and until) packets
* falling here are owned by current CPU. Output packets are cloned
* by dev_queue_xmit_nit(), input packets are processed by net_bh
* sequencially, so that if we return skb to original state on exit,
* we will not harm anyone.
*/
static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct sock *sk;
struct sockaddr_ll *sll;
struct packet_sock *po;
u8 *skb_head = skb->data;
int skb_len = skb->len;
unsigned int snaplen, res;
if (skb->pkt_type == PACKET_LOOPBACK)
goto drop;
sk = pt->af_packet_priv;
po = pkt_sk(sk);
if (!net_eq(dev_net(dev), sock_net(sk)))
goto drop;
skb->dev = dev;
if (dev->header_ops) {
/* The device has an explicit notion of ll header,
* exported to higher levels.
*
* Otherwise, the device hides details of its frame
* structure, so that corresponding packet head is
* never delivered to user.
*/
if (sk->sk_type != SOCK_DGRAM)
skb_push(skb, skb->data - skb_mac_header(skb));
else if (skb->pkt_type == PACKET_OUTGOING) {
/* Special case: outgoing packets have ll header at head */
skb_pull(skb, skb_network_offset(skb));
}
}
snaplen = skb->len;
res = run_filter(skb, sk, snaplen);
if (!res)
goto drop_n_restore;
if (snaplen > res)
snaplen = res;
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
(unsigned)sk->sk_rcvbuf)
goto drop_n_acct;
if (skb_shared(skb)) {
struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
if (nskb == NULL)
goto drop_n_acct;
if (skb_head != skb->data) {
skb->data = skb_head;
skb->len = skb_len;
}
kfree_skb(skb);
skb = nskb;
}
BUILD_BUG_ON(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8 >
sizeof(skb->cb));
sll = &PACKET_SKB_CB(skb)->sa.ll;
sll->sll_family = AF_PACKET;
sll->sll_hatype = dev->type;
sll->sll_protocol = skb->protocol;
sll->sll_pkttype = skb->pkt_type;
if (unlikely(po->origdev))
sll->sll_ifindex = orig_dev->ifindex;
else
sll->sll_ifindex = dev->ifindex;
sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
PACKET_SKB_CB(skb)->origlen = skb->len;
if (pskb_trim(skb, snaplen))
goto drop_n_acct;
skb_set_owner_r(skb, sk);
skb->dev = NULL;
skb_dst_drop(skb);
/* drop conntrack reference */
nf_reset(skb);
spin_lock(&sk->sk_receive_queue.lock);
po->stats.tp_packets++;
skb->dropcount = atomic_read(&sk->sk_drops);
__skb_queue_tail(&sk->sk_receive_queue, skb);
spin_unlock(&sk->sk_receive_queue.lock);
sk->sk_data_ready(sk, skb->len);
return 0;
drop_n_acct:
po->stats.tp_drops = atomic_inc_return(&sk->sk_drops);
drop_n_restore:
if (skb_head != skb->data && skb_shared(skb)) {
skb->data = skb_head;
skb->len = skb_len;
}
drop:
consume_skb(skb);
return 0;
}
static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct sock *sk;
struct packet_sock *po;
struct sockaddr_ll *sll;
union {
struct tpacket_hdr *h1;
struct tpacket2_hdr *h2;
void *raw;
} h;
u8 *skb_head = skb->data;
int skb_len = skb->len;
unsigned int snaplen, res;
unsigned long status = TP_STATUS_LOSING|TP_STATUS_USER;
unsigned short macoff, netoff, hdrlen;
struct sk_buff *copy_skb = NULL;
struct timeval tv;
struct timespec ts;
struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
if (skb->pkt_type == PACKET_LOOPBACK)
goto drop;
sk = pt->af_packet_priv;