forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
ip_output.c
1666 lines (1426 loc) · 42.2 KB
/
ip_output.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-only
/*
* 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.
*
* The Internet Protocol (IP) output module.
*
* Authors: Ross Biro
* Fred N. van Kempen, <[email protected]>
* Donald Becker, <[email protected]>
* Alan Cox, <[email protected]>
* Richard Underwood
* Stefan Becker, <[email protected]>
* Jorge Cwik, <[email protected]>
* Arnt Gulbrandsen, <[email protected]>
* Hirokazu Takahashi, <[email protected]>
*
* See ip_input.c for original log
*
* Fixes:
* Alan Cox : Missing nonblock feature in ip_build_xmit.
* Mike Kilburn : htons() missing in ip_build_xmit.
* Bradford Johnson: Fix faulty handling of some frames when
* no route is found.
* Alexander Demenshin: Missing sk/skb free in ip_queue_xmit
* (in case if packet not accepted by
* output firewall rules)
* Mike McLagan : Routing by source
* Alexey Kuznetsov: use new route cache
* Andi Kleen: Fix broken PMTU recovery and remove
* some redundant tests.
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
* Andi Kleen : Replace ip_reply with ip_send_reply.
* Andi Kleen : Split fast and slow ip_build_xmit path
* for decreased register pressure on x86
* and more readability.
* Marc Boucher : When call_out_firewall returns FW_QUEUE,
* silently drop skb instead of failing with -EPERM.
* Detlev Wengorz : Copy protocol for fragments.
* Hirokazu Takahashi: HW checksumming for outgoing UDP
* datagrams.
* Hirokazu Takahashi: sendfile() on UDP works now.
*/
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/xfrm.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/gso.h>
#include <net/inetpeer.h>
#include <net/inet_ecn.h>
#include <net/lwtunnel.h>
#include <linux/bpf-cgroup.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
#include <linux/netlink.h>
#include <linux/tcp.h>
static int
ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
unsigned int mtu,
int (*output)(struct net *, struct sock *, struct sk_buff *));
/* Generate a checksum for an outgoing IP datagram. */
void ip_send_check(struct iphdr *iph)
{
iph->check = 0;
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
EXPORT_SYMBOL(ip_send_check);
int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
IP_INC_STATS(net, IPSTATS_MIB_OUTREQUESTS);
iph_set_totlen(iph, skb->len);
ip_send_check(iph);
/* if egress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
skb = l3mdev_ip_out(sk, skb);
if (unlikely(!skb))
return 0;
skb->protocol = htons(ETH_P_IP);
return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, skb_dst(skb)->dev,
dst_output);
}
int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
int err;
err = __ip_local_out(net, sk, skb);
if (likely(err == 1))
err = dst_output(net, sk, skb);
return err;
}
EXPORT_SYMBOL_GPL(ip_local_out);
static inline int ip_select_ttl(const struct inet_sock *inet,
const struct dst_entry *dst)
{
int ttl = READ_ONCE(inet->uc_ttl);
if (ttl < 0)
ttl = ip4_dst_hoplimit(dst);
return ttl;
}
/*
* Add an ip header to a skbuff and send it out.
*
*/
int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
__be32 saddr, __be32 daddr, struct ip_options_rcu *opt,
u8 tos)
{
const struct inet_sock *inet = inet_sk(sk);
struct rtable *rt = skb_rtable(skb);
struct net *net = sock_net(sk);
struct iphdr *iph;
/* Build the IP header. */
skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 5;
iph->tos = tos;
iph->ttl = ip_select_ttl(inet, &rt->dst);
iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
iph->saddr = saddr;
iph->protocol = sk->sk_protocol;
/* Do not bother generating IPID for small packets (eg SYNACK) */
if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) {
iph->frag_off = htons(IP_DF);
iph->id = 0;
} else {
iph->frag_off = 0;
/* TCP packets here are SYNACK with fat IPv4/TCP options.
* Avoid using the hashed IP ident generator.
*/
if (sk->sk_protocol == IPPROTO_TCP)
iph->id = (__force __be16)get_random_u16();
else
__ip_select_ident(net, iph, 1);
}
if (opt && opt->opt.optlen) {
iph->ihl += opt->opt.optlen>>2;
ip_options_build(skb, &opt->opt, daddr, rt);
}
skb->priority = READ_ONCE(sk->sk_priority);
if (!skb->mark)
skb->mark = READ_ONCE(sk->sk_mark);
/* Send it out. */
return ip_local_out(net, skb->sk, skb);
}
EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
bool is_v6gw = false;
if (rt->rt_type == RTN_MULTICAST) {
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len);
} else if (rt->rt_type == RTN_BROADCAST)
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len);
/* OUTOCTETS should be counted after fragment */
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
skb = skb_expand_head(skb, hh_len);
if (!skb)
return -ENOMEM;
}
if (lwtunnel_xmit_redirect(dst->lwtstate)) {
int res = lwtunnel_xmit(skb);
if (res != LWTUNNEL_XMIT_CONTINUE)
return res;
}
rcu_read_lock();
neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
if (!IS_ERR(neigh)) {
int res;
sock_confirm_neigh(skb, neigh);
/* if crossing protocols, can not use the cached header */
res = neigh_output(neigh, skb, is_v6gw);
rcu_read_unlock();
return res;
}
rcu_read_unlock();
net_dbg_ratelimited("%s: No header cache and no neighbour!\n",
__func__);
kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
return PTR_ERR(neigh);
}
static int ip_finish_output_gso(struct net *net, struct sock *sk,
struct sk_buff *skb, unsigned int mtu)
{
struct sk_buff *segs, *nskb;
netdev_features_t features;
int ret = 0;
/* common case: seglen is <= mtu
*/
if (skb_gso_validate_network_len(skb, mtu))
return ip_finish_output2(net, sk, skb);
/* Slowpath - GSO segment length exceeds the egress MTU.
*
* This can happen in several cases:
* - Forwarding of a TCP GRO skb, when DF flag is not set.
* - Forwarding of an skb that arrived on a virtualization interface
* (virtio-net/vhost/tap) with TSO/GSO size set by other network
* stack.
* - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an
* interface with a smaller MTU.
* - Arriving GRO skb (or GSO skb in a virtualized environment) that is
* bridged to a NETIF_F_TSO tunnel stacked over an interface with an
* insufficient MTU.
*/
features = netif_skb_features(skb);
BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET);
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
if (IS_ERR_OR_NULL(segs)) {
kfree_skb(skb);
return -ENOMEM;
}
consume_skb(skb);
skb_list_walk_safe(segs, segs, nskb) {
int err;
skb_mark_not_on_list(segs);
err = ip_fragment(net, sk, segs, mtu, ip_finish_output2);
if (err && ret == 0)
ret = err;
}
return ret;
}
static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
unsigned int mtu;
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
if (skb_dst(skb)->xfrm) {
IPCB(skb)->flags |= IPSKB_REROUTED;
return dst_output(net, sk, skb);
}
#endif
mtu = ip_skb_dst_mtu(sk, skb);
if (skb_is_gso(skb))
return ip_finish_output_gso(net, sk, skb, mtu);
if (skb->len > mtu || IPCB(skb)->frag_max_size)
return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
return ip_finish_output2(net, sk, skb);
}
static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
int ret;
ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
switch (ret) {
case NET_XMIT_SUCCESS:
return __ip_finish_output(net, sk, skb);
case NET_XMIT_CN:
return __ip_finish_output(net, sk, skb) ? : ret;
default:
kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS);
return ret;
}
}
static int ip_mc_finish_output(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct rtable *new_rt;
bool do_cn = false;
int ret, err;
ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
switch (ret) {
case NET_XMIT_CN:
do_cn = true;
fallthrough;
case NET_XMIT_SUCCESS:
break;
default:
kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS);
return ret;
}
/* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting
* this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten,
* see ipv4_pktinfo_prepare().
*/
new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb));
if (new_rt) {
new_rt->rt_iif = 0;
skb_dst_drop(skb);
skb_dst_set(skb, &new_rt->dst);
}
err = dev_loopback_xmit(net, sk, skb);
return (do_cn && err) ? ret : err;
}
int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->dst.dev;
/*
* If the indicated interface is up and running, send the packet.
*/
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
/*
* Multicasts are looped back for other local users
*/
if (rt->rt_flags&RTCF_MULTICAST) {
if (sk_mc_loop(sk)
#ifdef CONFIG_IP_MROUTE
/* Small optimization: do not loopback not local frames,
which returned after forwarding; they will be dropped
by ip_mr_input in any case.
Note, that local frames are looped back to be delivered
to local recipients.
This check is duplicated in ip_mr_input at the moment.
*/
&&
((rt->rt_flags & RTCF_LOCAL) ||
!(IPCB(skb)->flags & IPSKB_FORWARDED))
#endif
) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, newskb, NULL, newskb->dev,
ip_mc_finish_output);
}
/* Multicasts with ttl 0 must not go beyond the host */
if (ip_hdr(skb)->ttl == 0) {
kfree_skb(skb);
return 0;
}
}
if (rt->rt_flags&RTCF_BROADCAST) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, newskb, NULL, newskb->dev,
ip_mc_finish_output);
}
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, skb, NULL, skb->dev,
ip_finish_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, skb, indev, dev,
ip_finish_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
EXPORT_SYMBOL(ip_output);
/*
* copy saddr and daddr, possibly using 64bit load/stores
* Equivalent to :
* iph->saddr = fl4->saddr;
* iph->daddr = fl4->daddr;
*/
static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
{
BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
iph->saddr = fl4->saddr;
iph->daddr = fl4->daddr;
}
/* Note: skb->sk can be different from sk, in case of tunnels */
int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
__u8 tos)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct ip_options_rcu *inet_opt;
struct flowi4 *fl4;
struct rtable *rt;
struct iphdr *iph;
int res;
/* Skip all of this if the packet is already routed,
* f.e. by something like SCTP.
*/
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
fl4 = &fl->u.ip4;
rt = skb_rtable(skb);
if (rt)
goto packet_routed;
/* Make sure we can route this packet. */
rt = (struct rtable *)__sk_dst_check(sk, 0);
if (!rt) {
__be32 daddr;
/* Use correct destination address if we have options. */
daddr = inet->inet_daddr;
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
/* If this fails, retransmit mechanism of transport layer will
* keep trying until route appears or the connection times
* itself out.
*/
rt = ip_route_output_ports(net, fl4, sk,
daddr, inet->inet_saddr,
inet->inet_dport,
inet->inet_sport,
sk->sk_protocol,
RT_CONN_FLAGS_TOS(sk, tos),
sk->sk_bound_dev_if);
if (IS_ERR(rt))
goto no_route;
sk_setup_caps(sk, &rt->dst);
}
skb_dst_set_noref(skb, &rt->dst);
packet_routed:
if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
goto no_route;
/* OK, we know where to send it, allocate and build IP header. */
skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff));
if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
iph->frag_off = htons(IP_DF);
else
iph->frag_off = 0;
iph->ttl = ip_select_ttl(inet, &rt->dst);
iph->protocol = sk->sk_protocol;
ip_copy_addrs(iph, fl4);
/* Transport layer set skb->h.foo itself. */
if (inet_opt && inet_opt->opt.optlen) {
iph->ihl += inet_opt->opt.optlen >> 2;
ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt);
}
ip_select_ident_segs(net, skb, sk,
skb_shinfo(skb)->gso_segs ?: 1);
/* TODO : should we use skb->sk here instead of sk ? */
skb->priority = READ_ONCE(sk->sk_priority);
skb->mark = READ_ONCE(sk->sk_mark);
res = ip_local_out(net, sk, skb);
rcu_read_unlock();
return res;
no_route:
rcu_read_unlock();
IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
kfree_skb_reason(skb, SKB_DROP_REASON_IP_OUTNOROUTES);
return -EHOSTUNREACH;
}
EXPORT_SYMBOL(__ip_queue_xmit);
int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
{
return __ip_queue_xmit(sk, skb, fl, READ_ONCE(inet_sk(sk)->tos));
}
EXPORT_SYMBOL(ip_queue_xmit);
static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
{
to->pkt_type = from->pkt_type;
to->priority = from->priority;
to->protocol = from->protocol;
to->skb_iif = from->skb_iif;
skb_dst_drop(to);
skb_dst_copy(to, from);
to->dev = from->dev;
to->mark = from->mark;
skb_copy_hash(to, from);
#ifdef CONFIG_NET_SCHED
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
skb_ext_copy(to, from);
#if IS_ENABLED(CONFIG_IP_VS)
to->ipvs_property = from->ipvs_property;
#endif
skb_copy_secmark(to, from);
}
static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
unsigned int mtu,
int (*output)(struct net *, struct sock *, struct sk_buff *))
{
struct iphdr *iph = ip_hdr(skb);
if ((iph->frag_off & htons(IP_DF)) == 0)
return ip_do_fragment(net, sk, skb, output);
if (unlikely(!skb->ignore_df ||
(IPCB(skb)->frag_max_size &&
IPCB(skb)->frag_max_size > mtu))) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
kfree_skb(skb);
return -EMSGSIZE;
}
return ip_do_fragment(net, sk, skb, output);
}
void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph,
unsigned int hlen, struct ip_fraglist_iter *iter)
{
unsigned int first_len = skb_pagelen(skb);
iter->frag = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
iter->offset = 0;
iter->iph = iph;
iter->hlen = hlen;
skb->data_len = first_len - skb_headlen(skb);
skb->len = first_len;
iph->tot_len = htons(first_len);
iph->frag_off = htons(IP_MF);
ip_send_check(iph);
}
EXPORT_SYMBOL(ip_fraglist_init);
void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter)
{
unsigned int hlen = iter->hlen;
struct iphdr *iph = iter->iph;
struct sk_buff *frag;
frag = iter->frag;
frag->ip_summed = CHECKSUM_NONE;
skb_reset_transport_header(frag);
__skb_push(frag, hlen);
skb_reset_network_header(frag);
memcpy(skb_network_header(frag), iph, hlen);
iter->iph = ip_hdr(frag);
iph = iter->iph;
iph->tot_len = htons(frag->len);
ip_copy_metadata(frag, skb);
iter->offset += skb->len - hlen;
iph->frag_off = htons(iter->offset >> 3);
if (frag->next)
iph->frag_off |= htons(IP_MF);
/* Ready, complete checksum */
ip_send_check(iph);
}
EXPORT_SYMBOL(ip_fraglist_prepare);
void ip_frag_init(struct sk_buff *skb, unsigned int hlen,
unsigned int ll_rs, unsigned int mtu, bool DF,
struct ip_frag_state *state)
{
struct iphdr *iph = ip_hdr(skb);
state->DF = DF;
state->hlen = hlen;
state->ll_rs = ll_rs;
state->mtu = mtu;
state->left = skb->len - hlen; /* Space per frame */
state->ptr = hlen; /* Where to start from */
state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
state->not_last_frag = iph->frag_off & htons(IP_MF);
}
EXPORT_SYMBOL(ip_frag_init);
static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to,
bool first_frag)
{
/* Copy the flags to each fragment. */
IPCB(to)->flags = IPCB(from)->flags;
/* ANK: dirty, but effective trick. Upgrade options only if
* the segment to be fragmented was THE FIRST (otherwise,
* options are already fixed) and make it ONCE
* on the initial skb, so that all the following fragments
* will inherit fixed options.
*/
if (first_frag)
ip_options_fragment(from);
}
struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state)
{
unsigned int len = state->left;
struct sk_buff *skb2;
struct iphdr *iph;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > state->mtu)
len = state->mtu;
/* IF: we are not sending up to and including the packet end
then align the next start on an eight byte boundary */
if (len < state->left) {
len &= ~7;
}
/* Allocate buffer */
skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC);
if (!skb2)
return ERR_PTR(-ENOMEM);
/*
* Set up data on packet
*/
ip_copy_metadata(skb2, skb);
skb_reserve(skb2, state->ll_rs);
skb_put(skb2, len + state->hlen);
skb_reset_network_header(skb2);
skb2->transport_header = skb2->network_header + state->hlen;
/*
* Charge the memory for the fragment to any owner
* it might possess
*/
if (skb->sk)
skb_set_owner_w(skb2, skb->sk);
/*
* Copy the packet header into the new buffer.
*/
skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen);
/*
* Copy a block of the IP datagram.
*/
if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len))
BUG();
state->left -= len;
/*
* Fill in the new header fields.
*/
iph = ip_hdr(skb2);
iph->frag_off = htons((state->offset >> 3));
if (state->DF)
iph->frag_off |= htons(IP_DF);
/*
* Added AC : If we are fragmenting a fragment that's not the
* last fragment then keep MF on each bit
*/
if (state->left > 0 || state->not_last_frag)
iph->frag_off |= htons(IP_MF);
state->ptr += len;
state->offset += len;
iph->tot_len = htons(len + state->hlen);
ip_send_check(iph);
return skb2;
}
EXPORT_SYMBOL(ip_frag_next);
/*
* This IP datagram is too large to be sent in one piece. Break it up into
* smaller pieces (each of size equal to IP header plus
* a block of the data of the original IP data part) that will yet fit in a
* single device frame, and queue such a frame for sending.
*/
int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *))
{
struct iphdr *iph;
struct sk_buff *skb2;
bool mono_delivery_time = skb->mono_delivery_time;
struct rtable *rt = skb_rtable(skb);
unsigned int mtu, hlen, ll_rs;
struct ip_fraglist_iter iter;
ktime_t tstamp = skb->tstamp;
struct ip_frag_state state;
int err = 0;
/* for offloaded checksums cleanup checksum before fragmentation */
if (skb->ip_summed == CHECKSUM_PARTIAL &&
(err = skb_checksum_help(skb)))
goto fail;
/*
* Point into the IP datagram header.
*/
iph = ip_hdr(skb);
mtu = ip_skb_dst_mtu(sk, skb);
if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu)
mtu = IPCB(skb)->frag_max_size;
/*
* Setup starting values.
*/
hlen = iph->ihl * 4;
mtu = mtu - hlen; /* Size of data space */
IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
/* When frag_list is given, use it. First, check its validity:
* some transformers could create wrong frag_list or break existing
* one, it is not prohibited. In this case fall back to copying.
*
* LATER: this step can be merged to real generation of fragments,
* we can switch to copy when see the first bad fragment.
*/
if (skb_has_frag_list(skb)) {
struct sk_buff *frag, *frag2;
unsigned int first_len = skb_pagelen(skb);
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
ip_is_fragment(iph) ||
skb_cloned(skb) ||
skb_headroom(skb) < ll_rs)
goto slow_path;
skb_walk_frags(skb, frag) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen + ll_rs)
goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
}
skb->truesize -= frag->truesize;
}
/* Everything is OK. Generate! */
ip_fraglist_init(skb, iph, hlen, &iter);
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
if (iter.frag) {
bool first_frag = (iter.offset == 0);
IPCB(iter.frag)->flags = IPCB(skb)->flags;
ip_fraglist_prepare(skb, &iter);
if (first_frag && IPCB(skb)->opt.optlen) {
/* ipcb->opt is not populated for frags
* coming from __ip_make_skb(),
* ip_options_fragment() needs optlen
*/
IPCB(iter.frag)->opt.optlen =
IPCB(skb)->opt.optlen;
ip_options_fragment(iter.frag);
ip_send_check(iter.iph);
}
}
skb_set_delivery_time(skb, tstamp, mono_delivery_time);
err = output(net, sk, skb);
if (!err)
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
if (err || !iter.frag)
break;
skb = ip_fraglist_next(&iter);
}
if (err == 0) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
return 0;
}
kfree_skb_list(iter.frag);
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
slow_path_clean:
skb_walk_frags(skb, frag2) {
if (frag2 == frag)
break;
frag2->sk = NULL;
frag2->destructor = NULL;
skb->truesize += frag2->truesize;
}
}
slow_path:
/*
* Fragment the datagram.
*/
ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU,
&state);
/*
* Keep copying data until we run out.
*/
while (state.left > 0) {
bool first_frag = (state.offset == 0);
skb2 = ip_frag_next(skb, &state);
if (IS_ERR(skb2)) {
err = PTR_ERR(skb2);
goto fail;
}
ip_frag_ipcb(skb, skb2, first_frag);
/*
* Put this fragment into the sending queue.
*/
skb_set_delivery_time(skb2, tstamp, mono_delivery_time);
err = output(net, sk, skb2);
if (err)
goto fail;
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
}
consume_skb(skb);
IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
return err;
fail:
kfree_skb(skb);
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
}
EXPORT_SYMBOL(ip_do_fragment);
int
ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
struct msghdr *msg = from;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
if (!copy_from_iter_full(to, len, &msg->msg_iter))
return -EFAULT;
} else {
__wsum csum = 0;
if (!csum_and_copy_from_iter_full(to, len, &csum, &msg->msg_iter))
return -EFAULT;
skb->csum = csum_block_add(skb->csum, csum, odd);
}
return 0;
}
EXPORT_SYMBOL(ip_generic_getfrag);
static int __ip_append_data(struct sock *sk,
struct flowi4 *fl4,
struct sk_buff_head *queue,
struct inet_cork *cork,
struct page_frag *pfrag,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct ubuf_info *uarg = NULL;
struct sk_buff *skb;
struct ip_options *opt = cork->opt;
int hh_len;
int exthdrlen;
int mtu;
int copy;
int err;
int offset = 0;
bool zc = false;
unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
int csummode = CHECKSUM_NONE;
struct rtable *rt = (struct rtable *)cork->dst;
unsigned int wmem_alloc_delta = 0;
bool paged, extra_uref = false;
u32 tskey = 0;
skb = skb_peek_tail(queue);
exthdrlen = !skb ? rt->dst.header_len : 0;
mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
paged = !!cork->gso_size;
if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
tskey = atomic_inc_return(&sk->sk_tskey) - 1;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu;
if (cork->length + length > maxnonfragsize - fragheaderlen) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
mtu - (opt ? opt->optlen : 0));
return -EMSGSIZE;
}