blob: 6dea6e92e686342a50c2fdb651923853463fb0d6 [file] [log] [blame]
rjw1f884582022-01-06 17:20:42 +08001/*
2 * IPv6 fragment reassembly
3 * Linux INET6 implementation
4 *
5 * Authors:
6 * Pedro Roque <roque@di.fc.ul.pt>
7 *
8 * Based on: net/ipv4/ip_fragment.c
9 *
10 * This program is free software; you can redistribute it and/or
11 * modify it under the terms of the GNU General Public License
12 * as published by the Free Software Foundation; either version
13 * 2 of the License, or (at your option) any later version.
14 */
15
16/*
17 * Fixes:
18 * Andi Kleen Make it work with multiple hosts.
19 * More RFC compliance.
20 *
21 * Horst von Brand Add missing #include <linux/string.h>
22 * Alexey Kuznetsov SMP races, threading, cleanup.
23 * Patrick McHardy LRU queue of frag heads for evictor.
24 * Mitsuru KANDA @USAGI Register inet6_protocol{}.
25 * David Stevens and
26 * YOSHIFUJI,H. @USAGI Always remove fragment header to
27 * calculate ICV correctly.
28 */
29
30#define pr_fmt(fmt) "IPv6: " fmt
31
32#include <linux/errno.h>
33#include <linux/types.h>
34#include <linux/string.h>
35#include <linux/socket.h>
36#include <linux/sockios.h>
37#include <linux/jiffies.h>
38#include <linux/net.h>
39#include <linux/list.h>
40#include <linux/netdevice.h>
41#include <linux/in6.h>
42#include <linux/ipv6.h>
43#include <linux/icmpv6.h>
44#include <linux/random.h>
45#include <linux/jhash.h>
46#include <linux/skbuff.h>
47#include <linux/slab.h>
48#include <linux/export.h>
49
50#include <net/sock.h>
51#include <net/snmp.h>
52
53#include <net/ipv6.h>
54#include <net/ip6_route.h>
55#include <net/protocol.h>
56#include <net/transp_v6.h>
57#include <net/rawv6.h>
58#include <net/ndisc.h>
59#include <net/addrconf.h>
60#include <net/ipv6_frag.h>
61#include <net/inet_ecn.h>
62
63static const char ip6_frag_cache_name[] = "ip6-frags";
64
65static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
66{
67 return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
68}
69
70static struct inet_frags ip6_frags;
71
72static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
73 struct sk_buff *prev_tail, struct net_device *dev);
74
75static void ip6_frag_expire(struct timer_list *t)
76{
77 struct inet_frag_queue *frag = from_timer(frag, t, timer);
78 struct frag_queue *fq;
79 struct net *net;
80
81 fq = container_of(frag, struct frag_queue, q);
82 net = container_of(fq->q.net, struct net, ipv6.frags);
83
84 ip6frag_expire_frag_queue(net, fq);
85}
86
87static struct frag_queue *
88fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
89{
90 struct frag_v6_compare_key key = {
91 .id = id,
92 .saddr = hdr->saddr,
93 .daddr = hdr->daddr,
94 .user = IP6_DEFRAG_LOCAL_DELIVER,
95 .iif = iif,
96 };
97 struct inet_frag_queue *q;
98
99 if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
100 IPV6_ADDR_LINKLOCAL)))
101 key.iif = 0;
102
103 q = inet_frag_find(&net->ipv6.frags, &key);
104 if (!q)
105 return NULL;
106
107 return container_of(q, struct frag_queue, q);
108}
109
110static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
111 struct frag_hdr *fhdr, int nhoff,
112 u32 *prob_offset)
113{
114 struct net *net = dev_net(skb_dst(skb)->dev);
115 int offset, end, fragsize;
116 struct sk_buff *prev_tail;
117 struct net_device *dev;
118 int err = -ENOENT;
119 u8 ecn;
120
121 if (fq->q.flags & INET_FRAG_COMPLETE)
122 goto err;
123
124 err = -EINVAL;
125 offset = ntohs(fhdr->frag_off) & ~0x7;
126 end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
127 ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
128
129 if ((unsigned int)end > IPV6_MAXPLEN) {
130 *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb);
131 /* note that if prob_offset is set, the skb is freed elsewhere,
132 * we do not free it here.
133 */
134 return -1;
135 }
136
137 ecn = ip6_frag_ecn(ipv6_hdr(skb));
138
139 if (skb->ip_summed == CHECKSUM_COMPLETE) {
140 const unsigned char *nh = skb_network_header(skb);
141 skb->csum = csum_sub(skb->csum,
142 csum_partial(nh, (u8 *)(fhdr + 1) - nh,
143 0));
144 }
145
146 /* Is this the final fragment? */
147 if (!(fhdr->frag_off & htons(IP6_MF))) {
148 /* If we already have some bits beyond end
149 * or have different end, the segment is corrupted.
150 */
151 if (end < fq->q.len ||
152 ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
153 goto discard_fq;
154 fq->q.flags |= INET_FRAG_LAST_IN;
155 fq->q.len = end;
156 } else {
157 /* Check if the fragment is rounded to 8 bytes.
158 * Required by the RFC.
159 */
160 if (end & 0x7) {
161 /* RFC2460 says always send parameter problem in
162 * this case. -DaveM
163 */
164 *prob_offset = offsetof(struct ipv6hdr, payload_len);
165 return -1;
166 }
167 if (end > fq->q.len) {
168 /* Some bits beyond end -> corruption. */
169 if (fq->q.flags & INET_FRAG_LAST_IN)
170 goto discard_fq;
171 fq->q.len = end;
172 }
173 }
174
175 if (end == offset)
176 goto discard_fq;
177
178 err = -ENOMEM;
179 /* Point into the IP datagram 'data' part. */
180 if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
181 goto discard_fq;
182
183 err = pskb_trim_rcsum(skb, end - offset);
184 if (err)
185 goto discard_fq;
186
187 /* Note : skb->rbnode and skb->dev share the same location. */
188 dev = skb->dev;
189 /* Makes sure compiler wont do silly aliasing games */
190 barrier();
191
192 prev_tail = fq->q.fragments_tail;
193 err = inet_frag_queue_insert(&fq->q, skb, offset, end);
194 if (err)
195 goto insert_error;
196
197 if (dev)
198 fq->iif = dev->ifindex;
199
200 fq->q.stamp = skb->tstamp;
201 fq->q.meat += skb->len;
202 fq->ecn |= ecn;
203 add_frag_mem_limit(fq->q.net, skb->truesize);
204
205 fragsize = -skb_network_offset(skb) + skb->len;
206 if (fragsize > fq->q.max_size)
207 fq->q.max_size = fragsize;
208
209 /* The first fragment.
210 * nhoffset is obtained from the first fragment, of course.
211 */
212 if (offset == 0) {
213 fq->nhoffset = nhoff;
214 fq->q.flags |= INET_FRAG_FIRST_IN;
215 }
216
217 if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
218 fq->q.meat == fq->q.len) {
219 unsigned long orefdst = skb->_skb_refdst;
220
221 skb->_skb_refdst = 0UL;
222 err = ip6_frag_reasm(fq, skb, prev_tail, dev);
223 skb->_skb_refdst = orefdst;
224 return err;
225 }
226
227 skb_dst_drop(skb);
228 return -EINPROGRESS;
229
230insert_error:
231 if (err == IPFRAG_DUP) {
232 kfree_skb(skb);
233 return -EINVAL;
234 }
235 err = -EINVAL;
236 __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
237 IPSTATS_MIB_REASM_OVERLAPS);
238discard_fq:
239 inet_frag_kill(&fq->q);
240 __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
241 IPSTATS_MIB_REASMFAILS);
242err:
243 kfree_skb(skb);
244 return err;
245}
246
247/*
248 * Check if this packet is complete.
249 *
250 * It is called with locked fq, and caller must check that
251 * queue is eligible for reassembly i.e. it is not COMPLETE,
252 * the last and the first frames arrived and all the bits are here.
253 */
254static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
255 struct sk_buff *prev_tail, struct net_device *dev)
256{
257 struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
258 unsigned int nhoff;
259 void *reasm_data;
260 int payload_len;
261 u8 ecn;
262
263 inet_frag_kill(&fq->q);
264
265 ecn = ip_frag_ecn_table[fq->ecn];
266 if (unlikely(ecn == 0xff))
267 goto out_fail;
268
269 reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
270 if (!reasm_data)
271 goto out_oom;
272
273 payload_len = ((skb->data - skb_network_header(skb)) -
274 sizeof(struct ipv6hdr) + fq->q.len -
275 sizeof(struct frag_hdr));
276 if (payload_len > IPV6_MAXPLEN)
277 goto out_oversize;
278
279 /* We have to remove fragment header from datagram and to relocate
280 * header in order to calculate ICV correctly. */
281 nhoff = fq->nhoffset;
282 skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0];
283 memmove(skb->head + sizeof(struct frag_hdr), skb->head,
284 (skb->data - skb->head) - sizeof(struct frag_hdr));
285 if (skb_mac_header_was_set(skb))
286 skb->mac_header += sizeof(struct frag_hdr);
287 skb->network_header += sizeof(struct frag_hdr);
288
289 skb_reset_transport_header(skb);
290
291 inet_frag_reasm_finish(&fq->q, skb, reasm_data);
292
293 skb->dev = dev;
294 ipv6_hdr(skb)->payload_len = htons(payload_len);
295 ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
296 IP6CB(skb)->nhoff = nhoff;
297 IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
298 IP6CB(skb)->frag_max_size = fq->q.max_size;
299
300 /* Yes, and fold redundant checksum back. 8) */
301 skb_postpush_rcsum(skb, skb_network_header(skb),
302 skb_network_header_len(skb));
303
304 rcu_read_lock();
305 __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
306 rcu_read_unlock();
307 fq->q.fragments = NULL;
308 fq->q.rb_fragments = RB_ROOT;
309 fq->q.fragments_tail = NULL;
310 fq->q.last_run_head = NULL;
311 return 1;
312
313out_oversize:
314 net_dbg_ratelimited("ip6_frag_reasm: payload len = %d\n", payload_len);
315 goto out_fail;
316out_oom:
317 net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
318out_fail:
319 rcu_read_lock();
320 __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
321 rcu_read_unlock();
322 inet_frag_kill(&fq->q);
323 return -1;
324}
325
326static int ipv6_frag_rcv(struct sk_buff *skb)
327{
328 struct frag_hdr *fhdr;
329 struct frag_queue *fq;
330 const struct ipv6hdr *hdr = ipv6_hdr(skb);
331 struct net *net = dev_net(skb_dst(skb)->dev);
332 int iif;
333
334 if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
335 goto fail_hdr;
336
337 __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
338
339 /* Jumbo payload inhibits frag. header */
340 if (hdr->payload_len == 0)
341 goto fail_hdr;
342
343 if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
344 sizeof(struct frag_hdr))))
345 goto fail_hdr;
346
347 hdr = ipv6_hdr(skb);
348 fhdr = (struct frag_hdr *)skb_transport_header(skb);
349
350 if (!(fhdr->frag_off & htons(0xFFF9))) {
351 /* It is not a fragmented frame */
352 skb->transport_header += sizeof(struct frag_hdr);
353 __IP6_INC_STATS(net,
354 ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
355
356 IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
357 IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
358 return 1;
359 }
360
361 iif = skb->dev ? skb->dev->ifindex : 0;
362 fq = fq_find(net, fhdr->identification, hdr, iif);
363 if (fq) {
364 u32 prob_offset = 0;
365 int ret;
366
367 spin_lock(&fq->q.lock);
368
369 fq->iif = iif;
370 ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff,
371 &prob_offset);
372
373 spin_unlock(&fq->q.lock);
374 inet_frag_put(&fq->q);
375 if (prob_offset) {
376 __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
377 IPSTATS_MIB_INHDRERRORS);
378 /* icmpv6_param_prob() calls kfree_skb(skb) */
379 icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset);
380 }
381 return ret;
382 }
383
384 __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
385 kfree_skb(skb);
386 return -1;
387
388fail_hdr:
389 __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
390 IPSTATS_MIB_INHDRERRORS);
391 icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
392 return -1;
393}
394
395static const struct inet6_protocol frag_protocol = {
396 .handler = ipv6_frag_rcv,
397 .flags = INET6_PROTO_NOPOLICY,
398};
399
400#ifdef CONFIG_SYSCTL
401
402static struct ctl_table ip6_frags_ns_ctl_table[] = {
403 {
404 .procname = "ip6frag_high_thresh",
405 .data = &init_net.ipv6.frags.high_thresh,
406 .maxlen = sizeof(unsigned long),
407 .mode = 0644,
408 .proc_handler = proc_doulongvec_minmax,
409 .extra1 = &init_net.ipv6.frags.low_thresh
410 },
411 {
412 .procname = "ip6frag_low_thresh",
413 .data = &init_net.ipv6.frags.low_thresh,
414 .maxlen = sizeof(unsigned long),
415 .mode = 0644,
416 .proc_handler = proc_doulongvec_minmax,
417 .extra2 = &init_net.ipv6.frags.high_thresh
418 },
419 {
420 .procname = "ip6frag_time",
421 .data = &init_net.ipv6.frags.timeout,
422 .maxlen = sizeof(int),
423 .mode = 0644,
424 .proc_handler = proc_dointvec_jiffies,
425 },
426 { }
427};
428
429/* secret interval has been deprecated */
430static int ip6_frags_secret_interval_unused;
431static struct ctl_table ip6_frags_ctl_table[] = {
432 {
433 .procname = "ip6frag_secret_interval",
434 .data = &ip6_frags_secret_interval_unused,
435 .maxlen = sizeof(int),
436 .mode = 0644,
437 .proc_handler = proc_dointvec_jiffies,
438 },
439 { }
440};
441
442static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
443{
444 struct ctl_table *table;
445 struct ctl_table_header *hdr;
446
447 table = ip6_frags_ns_ctl_table;
448 if (!net_eq(net, &init_net)) {
449 table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL);
450 if (!table)
451 goto err_alloc;
452
453 table[0].data = &net->ipv6.frags.high_thresh;
454 table[0].extra1 = &net->ipv6.frags.low_thresh;
455 table[0].extra2 = &init_net.ipv6.frags.high_thresh;
456 table[1].data = &net->ipv6.frags.low_thresh;
457 table[1].extra2 = &net->ipv6.frags.high_thresh;
458 table[2].data = &net->ipv6.frags.timeout;
459 }
460
461 hdr = register_net_sysctl(net, "net/ipv6", table);
462 if (!hdr)
463 goto err_reg;
464
465 net->ipv6.sysctl.frags_hdr = hdr;
466 return 0;
467
468err_reg:
469 if (!net_eq(net, &init_net))
470 kfree(table);
471err_alloc:
472 return -ENOMEM;
473}
474
475static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net)
476{
477 struct ctl_table *table;
478
479 table = net->ipv6.sysctl.frags_hdr->ctl_table_arg;
480 unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr);
481 if (!net_eq(net, &init_net))
482 kfree(table);
483}
484
485static struct ctl_table_header *ip6_ctl_header;
486
487static int ip6_frags_sysctl_register(void)
488{
489 ip6_ctl_header = register_net_sysctl(&init_net, "net/ipv6",
490 ip6_frags_ctl_table);
491 return ip6_ctl_header == NULL ? -ENOMEM : 0;
492}
493
494static void ip6_frags_sysctl_unregister(void)
495{
496 unregister_net_sysctl_table(ip6_ctl_header);
497}
498#else
499static int ip6_frags_ns_sysctl_register(struct net *net)
500{
501 return 0;
502}
503
504static void ip6_frags_ns_sysctl_unregister(struct net *net)
505{
506}
507
508static int ip6_frags_sysctl_register(void)
509{
510 return 0;
511}
512
513static void ip6_frags_sysctl_unregister(void)
514{
515}
516#endif
517
518static int __net_init ipv6_frags_init_net(struct net *net)
519{
520 int res;
521
522 net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
523 net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
524 net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
525 net->ipv6.frags.f = &ip6_frags;
526
527 res = inet_frags_init_net(&net->ipv6.frags);
528 if (res < 0)
529 return res;
530
531 res = ip6_frags_ns_sysctl_register(net);
532 if (res < 0)
533 inet_frags_exit_net(&net->ipv6.frags);
534 return res;
535}
536
537static void __net_exit ipv6_frags_exit_net(struct net *net)
538{
539 ip6_frags_ns_sysctl_unregister(net);
540 inet_frags_exit_net(&net->ipv6.frags);
541}
542
543static struct pernet_operations ip6_frags_ops = {
544 .init = ipv6_frags_init_net,
545 .exit = ipv6_frags_exit_net,
546};
547
548static const struct rhashtable_params ip6_rhash_params = {
549 .head_offset = offsetof(struct inet_frag_queue, node),
550 .hashfn = ip6frag_key_hashfn,
551 .obj_hashfn = ip6frag_obj_hashfn,
552 .obj_cmpfn = ip6frag_obj_cmpfn,
553 .automatic_shrinking = true,
554};
555
556int __init ipv6_frag_init(void)
557{
558 int ret;
559
560 ip6_frags.constructor = ip6frag_init;
561 ip6_frags.destructor = NULL;
562 ip6_frags.qsize = sizeof(struct frag_queue);
563 ip6_frags.frag_expire = ip6_frag_expire;
564 ip6_frags.frags_cache_name = ip6_frag_cache_name;
565 ip6_frags.rhash_params = ip6_rhash_params;
566 ret = inet_frags_init(&ip6_frags);
567 if (ret)
568 goto out;
569
570 ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
571 if (ret)
572 goto err_protocol;
573
574 ret = ip6_frags_sysctl_register();
575 if (ret)
576 goto err_sysctl;
577
578 ret = register_pernet_subsys(&ip6_frags_ops);
579 if (ret)
580 goto err_pernet;
581
582out:
583 return ret;
584
585err_pernet:
586 ip6_frags_sysctl_unregister();
587err_sysctl:
588 inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
589err_protocol:
590 inet_frags_fini(&ip6_frags);
591 goto out;
592}
593
594void ipv6_frag_exit(void)
595{
596 ip6_frags_sysctl_unregister();
597 unregister_pernet_subsys(&ip6_frags_ops);
598 inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
599 inet_frags_fini(&ip6_frags);
600}