Loading...
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 | /* NAT for netfilter; shared with compatibility layer. */
/* (c) 1999 Paul `Rusty' Russell. Licenced under the GNU General
Public Licence. */
#ifdef MODULE
#define __NO_VERSION__
#endif
#include <linux/version.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/timer.h>
#include <linux/skbuff.h>
#include <linux/netfilter_ipv4.h>
#include <linux/brlock.h>
#include <net/checksum.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/tcp.h> /* For tcp_prot in getorigdst */
#define ASSERT_READ_LOCK(x) MUST_BE_READ_LOCKED(&ip_nat_lock)
#define ASSERT_WRITE_LOCK(x) MUST_BE_WRITE_LOCKED(&ip_nat_lock)
#include <linux/netfilter_ipv4/ip_nat.h>
#include <linux/netfilter_ipv4/ip_nat_protocol.h>
#include <linux/netfilter_ipv4/ip_nat_core.h>
#include <linux/netfilter_ipv4/ip_nat_helper.h>
#include <linux/netfilter_ipv4/listhelp.h>
#if 0
#define DEBUGP printk
#else
#define DEBUGP(format, args...)
#endif
DECLARE_RWLOCK(ip_nat_lock);
#define IP_NAT_HTABLE_SIZE 64
static struct list_head bysource[IP_NAT_HTABLE_SIZE];
static struct list_head byipsproto[IP_NAT_HTABLE_SIZE];
LIST_HEAD(protos);
static LIST_HEAD(helpers);
extern struct ip_nat_protocol unknown_nat_protocol;
/* We keep extra hashes for each conntrack, for fast searching. */
static inline size_t
hash_by_ipsproto(u_int32_t src, u_int32_t dst, u_int16_t proto)
{
/* Modified src and dst, to ensure we don't create two
identical streams. */
return (src + dst + proto) % IP_NAT_HTABLE_SIZE;
}
static inline size_t
hash_by_src(const struct ip_conntrack_manip *manip, u_int16_t proto)
{
/* Original src, to ensure we map it consistently if poss. */
return (manip->ip + manip->u.all + proto) % IP_NAT_HTABLE_SIZE;
}
/* Noone using conntrack by the time this called. */
static void ip_nat_cleanup_conntrack(struct ip_conntrack *conn)
{
struct ip_nat_info *info = &conn->nat.info;
if (!info->initialized)
return;
IP_NF_ASSERT(info->bysource.conntrack);
IP_NF_ASSERT(info->byipsproto.conntrack);
WRITE_LOCK(&ip_nat_lock);
LIST_DELETE(&bysource[hash_by_src(&conn->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.src,
conn->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.dst.protonum)],
&info->bysource);
LIST_DELETE(&byipsproto
[hash_by_ipsproto(conn->tuplehash[IP_CT_DIR_REPLY]
.tuple.src.ip,
conn->tuplehash[IP_CT_DIR_REPLY]
.tuple.dst.ip,
conn->tuplehash[IP_CT_DIR_REPLY]
.tuple.dst.protonum)],
&info->byipsproto);
WRITE_UNLOCK(&ip_nat_lock);
}
/* We do checksum mangling, so if they were wrong before they're still
* wrong. Also works for incomplete packets (eg. ICMP dest
* unreachables.) */
u_int16_t
ip_nat_cheat_check(u_int32_t oldvalinv, u_int32_t newval, u_int16_t oldcheck)
{
u_int32_t diffs[] = { oldvalinv, newval };
return csum_fold(csum_partial((char *)diffs, sizeof(diffs),
oldcheck^0xFFFF));
}
static inline int cmp_proto(const struct ip_nat_protocol *i, int proto)
{
return i->protonum == proto;
}
struct ip_nat_protocol *
find_nat_proto(u_int16_t protonum)
{
struct ip_nat_protocol *i;
MUST_BE_READ_LOCKED(&ip_nat_lock);
i = LIST_FIND(&protos, cmp_proto, struct ip_nat_protocol *, protonum);
if (!i)
i = &unknown_nat_protocol;
return i;
}
/* Is this tuple already taken? (not by us) */
int
ip_nat_used_tuple(const struct ip_conntrack_tuple *tuple,
const struct ip_conntrack *ignored_conntrack)
{
/* Conntrack tracking doesn't keep track of outgoing tuples; only
incoming ones. NAT means they don't have a fixed mapping,
so we invert the tuple and look for the incoming reply.
We could keep a separate hash if this proves too slow. */
struct ip_conntrack_tuple reply;
invert_tuplepr(&reply, tuple);
return ip_conntrack_tuple_taken(&reply, ignored_conntrack);
}
/* Does tuple + the source manip come within the range mr */
static int
in_range(const struct ip_conntrack_tuple *tuple,
const struct ip_conntrack_manip *manip,
const struct ip_nat_multi_range *mr)
{
struct ip_nat_protocol *proto = find_nat_proto(tuple->dst.protonum);
unsigned int i;
struct ip_conntrack_tuple newtuple = { *manip, tuple->dst };
for (i = 0; i < mr->rangesize; i++) {
/* If we are allowed to map IPs, then we must be in the
range specified, otherwise we must be unchanged. */
if (mr->range[i].flags & IP_NAT_RANGE_MAP_IPS) {
if (ntohl(newtuple.src.ip) < ntohl(mr->range[i].min_ip)
|| (ntohl(newtuple.src.ip)
> ntohl(mr->range[i].max_ip)))
continue;
} else {
if (newtuple.src.ip != tuple->src.ip)
continue;
}
if ((mr->range[i].flags & IP_NAT_RANGE_PROTO_SPECIFIED)
&& proto->in_range(&newtuple, IP_NAT_MANIP_SRC,
&mr->range[i].min, &mr->range[i].max))
return 1;
}
return 0;
}
static inline int
src_cmp(const struct ip_nat_hash *i,
const struct ip_conntrack_tuple *tuple,
const struct ip_nat_multi_range *mr)
{
return (i->conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum
== tuple->dst.protonum
&& i->conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip
== tuple->src.ip
&& i->conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all
== tuple->src.u.all
&& in_range(tuple,
&i->conntrack->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.src,
mr));
}
/* Only called for SRC manip */
static struct ip_conntrack_manip *
find_appropriate_src(const struct ip_conntrack_tuple *tuple,
const struct ip_nat_multi_range *mr)
{
unsigned int h = hash_by_src(&tuple->src, tuple->dst.protonum);
struct ip_nat_hash *i;
MUST_BE_READ_LOCKED(&ip_nat_lock);
i = LIST_FIND(&bysource[h], src_cmp, struct ip_nat_hash *, tuple, mr);
if (i)
return &i->conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src;
else
return NULL;
}
/* If it's really a local destination manip, it may need to do a
source manip too. */
static int
do_extra_mangle(u_int32_t var_ip, u_int32_t *other_ipp)
{
struct rtable *rt;
/* FIXME: IPTOS_TOS(iph->tos) --RR */
if (ip_route_output(&rt, var_ip, 0, 0, 0) != 0) {
DEBUGP("do_extra_mangle: Can't get route to %u.%u.%u.%u\n",
NIPQUAD(var_ip));
return 0;
}
*other_ipp = rt->rt_src;
ip_rt_put(rt);
return 1;
}
/* Simple way to iterate through all. */
static inline int fake_cmp(const struct ip_nat_hash *i,
u_int32_t src, u_int32_t dst, u_int16_t protonum,
unsigned int *score,
const struct ip_conntrack *conntrack)
{
/* Compare backwards: we're dealing with OUTGOING tuples, and
inside the conntrack is the REPLY tuple. Don't count this
conntrack. */
if (i->conntrack != conntrack
&& i->conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip == dst
&& i->conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip == src
&& (i->conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum
== protonum))
(*score)++;
return 0;
}
static inline unsigned int
count_maps(u_int32_t src, u_int32_t dst, u_int16_t protonum,
const struct ip_conntrack *conntrack)
{
unsigned int score = 0;
MUST_BE_READ_LOCKED(&ip_nat_lock);
LIST_FIND(&byipsproto[hash_by_ipsproto(src, dst, protonum)],
fake_cmp, struct ip_nat_hash *, src, dst, protonum, &score,
conntrack);
return score;
}
/* For [FUTURE] fragmentation handling, we want the least-used
src-ip/dst-ip/proto triple. Fairness doesn't come into it. Thus
if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports
1-65535, we don't do pro-rata allocation based on ports; we choose
the ip with the lowest src-ip/dst-ip/proto usage.
If an allocation then fails (eg. all 6 ports used in the 1.2.3.4
range), we eliminate that and try again. This is not the most
efficient approach, but if you're worried about that, don't hand us
ranges you don't really have. */
static struct ip_nat_range *
find_best_ips_proto(struct ip_conntrack_tuple *tuple,
const struct ip_nat_multi_range *mr,
const struct ip_conntrack *conntrack,
unsigned int hooknum)
{
unsigned int i;
struct {
const struct ip_nat_range *range;
unsigned int score;
struct ip_conntrack_tuple tuple;
} best = { NULL, 0xFFFFFFFF };
u_int32_t *var_ipp, *other_ipp, saved_ip, orig_dstip;
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC) {
var_ipp = &tuple->src.ip;
saved_ip = tuple->dst.ip;
other_ipp = &tuple->dst.ip;
} else {
var_ipp = &tuple->dst.ip;
saved_ip = tuple->src.ip;
other_ipp = &tuple->src.ip;
}
/* Don't do do_extra_mangle unless neccessary (overrides
explicit socket bindings, for example) */
orig_dstip = tuple->dst.ip;
IP_NF_ASSERT(mr->rangesize >= 1);
for (i = 0; i < mr->rangesize; i++) {
u_int32_t minip, maxip;
/* Don't do ranges which are already eliminated. */
if (mr->range[i].flags & IP_NAT_RANGE_FULL) {
continue;
}
if (mr->range[i].flags & IP_NAT_RANGE_MAP_IPS) {
minip = mr->range[i].min_ip;
maxip = mr->range[i].max_ip;
} else
minip = maxip = *var_ipp;
for (*var_ipp = minip;
ntohl(*var_ipp) <= ntohl(maxip);
*var_ipp = htonl(ntohl(*var_ipp) + 1)) {
unsigned int score;
/* Reset the other ip in case it was mangled by
* do_extra_mangle last time. */
*other_ipp = saved_ip;
if (hooknum == NF_IP_LOCAL_OUT
&& *var_ipp != orig_dstip
&& !do_extra_mangle(*var_ipp, other_ipp)) {
DEBUGP("Range %u %u.%u.%u.%u rt failed!\n",
i, NIPQUAD(*var_ipp));
/* Can't route? This whole range part is
* probably screwed, but keep trying
* anyway. */
continue;
}
/* Count how many others map onto this. */
score = count_maps(tuple->src.ip, tuple->dst.ip,
tuple->dst.protonum, conntrack);
if (score < best.score) {
/* Optimization: doesn't get any better than
this. */
if (score == 0)
return (struct ip_nat_range *)
&mr->range[i];
best.score = score;
best.tuple = *tuple;
best.range = &mr->range[i];
}
}
}
*tuple = best.tuple;
/* Discard const. */
return (struct ip_nat_range *)best.range;
}
/* Fast version doesn't iterate through hash chains, but only handles
common case of single IP address (null NAT, masquerade) */
static struct ip_nat_range *
find_best_ips_proto_fast(struct ip_conntrack_tuple *tuple,
const struct ip_nat_multi_range *mr,
const struct ip_conntrack *conntrack,
unsigned int hooknum)
{
if (mr->rangesize != 1
|| (mr->range[0].flags & IP_NAT_RANGE_FULL)
|| ((mr->range[0].flags & IP_NAT_RANGE_MAP_IPS)
&& mr->range[0].min_ip != mr->range[0].max_ip))
return find_best_ips_proto(tuple, mr, conntrack, hooknum);
if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) {
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC)
tuple->src.ip = mr->range[0].min_ip;
else {
/* Only do extra mangle when required (breaks
socket binding) */
if (tuple->dst.ip != mr->range[0].min_ip
&& hooknum == NF_IP_LOCAL_OUT
&& !do_extra_mangle(mr->range[0].min_ip,
&tuple->src.ip))
return NULL;
tuple->dst.ip = mr->range[0].min_ip;
}
}
/* Discard const. */
return (struct ip_nat_range *)&mr->range[0];
}
static int
get_unique_tuple(struct ip_conntrack_tuple *tuple,
const struct ip_conntrack_tuple *orig_tuple,
const struct ip_nat_multi_range *mrr,
struct ip_conntrack *conntrack,
unsigned int hooknum)
{
struct ip_nat_protocol *proto
= find_nat_proto(orig_tuple->dst.protonum);
struct ip_nat_range *rptr;
unsigned int i;
int ret;
/* We temporarily use flags for marking full parts, but we
always clean up afterwards */
struct ip_nat_multi_range *mr = (void *)mrr;
/* 1) If this srcip/proto/src-proto-part is currently mapped,
and that same mapping gives a unique tuple within the given
range, use that.
This is only required for source (ie. NAT/masq) mappings.
So far, we don't do local source mappings, so multiple
manips not an issue. */
if (hooknum == NF_IP_POST_ROUTING) {
struct ip_conntrack_manip *manip;
manip = find_appropriate_src(orig_tuple, mr);
if (manip) {
/* Apply same source manipulation. */
*tuple = ((struct ip_conntrack_tuple)
{ *manip, orig_tuple->dst });
DEBUGP("get_unique_tuple: Found current src map\n");
return 1;
}
}
/* 2) Select the least-used IP/proto combination in the given
range.
*/
*tuple = *orig_tuple;
while ((rptr = find_best_ips_proto_fast(tuple, mr, conntrack, hooknum))
!= NULL) {
DEBUGP("Found best for "); DUMP_TUPLE(tuple);
/* 3) The per-protocol part of the manip is made to
map into the range to make a unique tuple. */
/* Only bother mapping if it's not already in range
and unique */
if ((!(rptr->flags & IP_NAT_RANGE_PROTO_SPECIFIED)
|| proto->in_range(tuple, HOOK2MANIP(hooknum),
&rptr->min, &rptr->max))
&& !ip_nat_used_tuple(tuple, conntrack)) {
ret = 1;
goto clear_fulls;
} else {
if (proto->unique_tuple(tuple, rptr,
HOOK2MANIP(hooknum),
conntrack)) {
/* Must be unique. */
IP_NF_ASSERT(!ip_nat_used_tuple(tuple,
conntrack));
ret = 1;
goto clear_fulls;
}
DEBUGP("Protocol can't get unique tuple.\n");
}
/* Eliminate that from range, and try again. */
rptr->flags |= IP_NAT_RANGE_FULL;
*tuple = *orig_tuple;
}
ret = 0;
clear_fulls:
/* Clear full flags. */
IP_NF_ASSERT(mr->rangesize >= 1);
for (i = 0; i < mr->rangesize; i++)
mr->range[i].flags &= ~IP_NAT_RANGE_FULL;
return ret;
}
static inline int
helper_cmp(const struct ip_nat_helper *helper,
const struct ip_conntrack_tuple *tuple)
{
return ip_ct_tuple_mask_cmp(tuple, &helper->tuple, &helper->mask);
}
/* Where to manip the reply packets (will be reverse manip). */
static unsigned int opposite_hook[NF_IP_NUMHOOKS]
= { [NF_IP_PRE_ROUTING] = NF_IP_POST_ROUTING,
[NF_IP_POST_ROUTING] = NF_IP_PRE_ROUTING,
[NF_IP_LOCAL_OUT] = NF_IP_POST_ROUTING
};
unsigned int
ip_nat_setup_info(struct ip_conntrack *conntrack,
const struct ip_nat_multi_range *mr,
unsigned int hooknum)
{
struct ip_conntrack_tuple new_tuple, inv_tuple, reply;
struct ip_conntrack_tuple orig_tp;
struct ip_nat_info *info = &conntrack->nat.info;
MUST_BE_WRITE_LOCKED(&ip_nat_lock);
IP_NF_ASSERT(hooknum == NF_IP_PRE_ROUTING
|| hooknum == NF_IP_POST_ROUTING
|| hooknum == NF_IP_LOCAL_OUT);
IP_NF_ASSERT(info->num_manips < IP_NAT_MAX_MANIPS);
/* What we've got will look like inverse of reply. Normally
this is what is in the conntrack, except for prior
manipulations (future optimization: if num_manips == 0,
orig_tp =
conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple) */
invert_tuplepr(&orig_tp,
&conntrack->tuplehash[IP_CT_DIR_REPLY].tuple);
#if 0
{
unsigned int i;
DEBUGP("Hook %u (%s), ", hooknum,
HOOK2MANIP(hooknum)==IP_NAT_MANIP_SRC ? "SRC" : "DST");
DUMP_TUPLE(&orig_tp);
DEBUGP("Range %p: ", mr);
for (i = 0; i < mr->rangesize; i++) {
DEBUGP("%u:%s%s%s %u.%u.%u.%u - %u.%u.%u.%u %u - %u\n",
i,
(mr->range[i].flags & IP_NAT_RANGE_MAP_IPS)
? " MAP_IPS" : "",
(mr->range[i].flags
& IP_NAT_RANGE_PROTO_SPECIFIED)
? " PROTO_SPECIFIED" : "",
(mr->range[i].flags & IP_NAT_RANGE_FULL)
? " FULL" : "",
NIPQUAD(mr->range[i].min_ip),
NIPQUAD(mr->range[i].max_ip),
mr->range[i].min.all,
mr->range[i].max.all);
}
}
#endif
do {
if (!get_unique_tuple(&new_tuple, &orig_tp, mr, conntrack,
hooknum)) {
DEBUGP("ip_nat_setup_info: Can't get unique for %p.\n",
conntrack);
return NF_DROP;
}
#if 0
DEBUGP("Hook %u (%s) %p\n", hooknum,
HOOK2MANIP(hooknum)==IP_NAT_MANIP_SRC ? "SRC" : "DST",
conntrack);
DEBUGP("Original: ");
DUMP_TUPLE(&orig_tp);
DEBUGP("New: ");
DUMP_TUPLE(&new_tuple);
#endif
/* We now have two tuples (SRCIP/SRCPT/DSTIP/DSTPT):
the original (A/B/C/D') and the mangled one (E/F/G/H').
We're only allowed to work with the SRC per-proto
part, so we create inverses of both to start, then
derive the other fields we need. */
/* Reply connection: simply invert the new tuple
(G/H/E/F') */
invert_tuplepr(&reply, &new_tuple);
/* Alter conntrack table so it recognizes replies.
If fail this race (reply tuple now used), repeat. */
} while (!ip_conntrack_alter_reply(conntrack, &reply));
/* FIXME: We can simply used existing conntrack reply tuple
here --RR */
/* Create inverse of original: C/D/A/B' */
invert_tuplepr(&inv_tuple, &orig_tp);
/* Has source changed?. */
if (!ip_ct_tuple_src_equal(&new_tuple, &orig_tp)) {
/* In this direction, a source manip. */
info->manips[info->num_manips++] =
((struct ip_nat_info_manip)
{ IP_CT_DIR_ORIGINAL, hooknum,
IP_NAT_MANIP_SRC, new_tuple.src });
IP_NF_ASSERT(info->num_manips < IP_NAT_MAX_MANIPS);
/* In the reverse direction, a destination manip. */
info->manips[info->num_manips++] =
((struct ip_nat_info_manip)
{ IP_CT_DIR_REPLY, opposite_hook[hooknum],
IP_NAT_MANIP_DST, orig_tp.src });
IP_NF_ASSERT(info->num_manips <= IP_NAT_MAX_MANIPS);
}
/* Has destination changed? */
if (!ip_ct_tuple_dst_equal(&new_tuple, &orig_tp)) {
/* In this direction, a destination manip */
info->manips[info->num_manips++] =
((struct ip_nat_info_manip)
{ IP_CT_DIR_ORIGINAL, hooknum,
IP_NAT_MANIP_DST, reply.src });
IP_NF_ASSERT(info->num_manips < IP_NAT_MAX_MANIPS);
/* In the reverse direction, a source manip. */
info->manips[info->num_manips++] =
((struct ip_nat_info_manip)
{ IP_CT_DIR_REPLY, opposite_hook[hooknum],
IP_NAT_MANIP_SRC, inv_tuple.src });
IP_NF_ASSERT(info->num_manips <= IP_NAT_MAX_MANIPS);
}
/* If there's a helper, assign it; based on new tuple. */
info->helper = LIST_FIND(&helpers, helper_cmp, struct ip_nat_helper *,
&reply);
/* It's done. */
info->initialized |= (1 << HOOK2MANIP(hooknum));
return NF_ACCEPT;
}
void replace_in_hashes(struct ip_conntrack *conntrack,
struct ip_nat_info *info)
{
/* Source has changed, so replace in hashes. */
unsigned int srchash
= hash_by_src(&conntrack->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.src,
conntrack->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.dst.protonum);
/* We place packet as seen OUTGOUNG in byips_proto hash
(ie. reverse dst and src of reply packet. */
unsigned int ipsprotohash
= hash_by_ipsproto(conntrack->tuplehash[IP_CT_DIR_REPLY]
.tuple.dst.ip,
conntrack->tuplehash[IP_CT_DIR_REPLY]
.tuple.src.ip,
conntrack->tuplehash[IP_CT_DIR_REPLY]
.tuple.dst.protonum);
IP_NF_ASSERT(info->bysource.conntrack == conntrack);
MUST_BE_WRITE_LOCKED(&ip_nat_lock);
list_del(&info->bysource.list);
list_del(&info->byipsproto.list);
list_prepend(&bysource[srchash], &info->bysource);
list_prepend(&byipsproto[ipsprotohash], &info->byipsproto);
}
void place_in_hashes(struct ip_conntrack *conntrack,
struct ip_nat_info *info)
{
unsigned int srchash
= hash_by_src(&conntrack->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.src,
conntrack->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.dst.protonum);
/* We place packet as seen OUTGOUNG in byips_proto hash
(ie. reverse dst and src of reply packet. */
unsigned int ipsprotohash
= hash_by_ipsproto(conntrack->tuplehash[IP_CT_DIR_REPLY]
.tuple.dst.ip,
conntrack->tuplehash[IP_CT_DIR_REPLY]
.tuple.src.ip,
conntrack->tuplehash[IP_CT_DIR_REPLY]
.tuple.dst.protonum);
IP_NF_ASSERT(!info->bysource.conntrack);
MUST_BE_WRITE_LOCKED(&ip_nat_lock);
info->byipsproto.conntrack = conntrack;
info->bysource.conntrack = conntrack;
list_prepend(&bysource[srchash], &info->bysource);
list_prepend(&byipsproto[ipsprotohash], &info->byipsproto);
}
static void
manip_pkt(u_int16_t proto, struct iphdr *iph, size_t len,
const struct ip_conntrack_manip *manip,
enum ip_nat_manip_type maniptype,
__u32 *nfcache)
{
*nfcache |= NFC_ALTERED;
find_nat_proto(proto)->manip_pkt(iph, len, manip, maniptype);
if (maniptype == IP_NAT_MANIP_SRC) {
iph->check = ip_nat_cheat_check(~iph->saddr, manip->ip,
iph->check);
iph->saddr = manip->ip;
} else {
iph->check = ip_nat_cheat_check(~iph->daddr, manip->ip,
iph->check);
iph->daddr = manip->ip;
}
#if 0
if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
DEBUGP("IP: checksum on packet bad.\n");
if (proto == IPPROTO_TCP) {
void *th = (u_int32_t *)iph + iph->ihl;
if (tcp_v4_check(th, len - 4*iph->ihl, iph->saddr, iph->daddr,
csum_partial((char *)th, len-4*iph->ihl, 0)))
DEBUGP("TCP: checksum on packet bad\n");
}
#endif
}
/* Do packet manipulations according to binding. */
unsigned int
do_bindings(struct ip_conntrack *ct,
enum ip_conntrack_info ctinfo,
struct ip_nat_info *info,
unsigned int hooknum,
struct sk_buff **pskb)
{
unsigned int i;
struct ip_nat_helper *helper;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
/* Need nat lock to protect against modification, but neither
conntrack (referenced) and helper (deleted with
synchronize_bh()) can vanish. */
READ_LOCK(&ip_nat_lock);
for (i = 0; i < info->num_manips; i++) {
if (info->manips[i].direction == dir
&& info->manips[i].hooknum == hooknum) {
DEBUGP("Mangling %p: %s to %u.%u.%u.%u %u\n",
*pskb,
info->manips[i].maniptype == IP_NAT_MANIP_SRC
? "SRC" : "DST",
NIPQUAD(info->manips[i].manip.ip),
htons(info->manips[i].manip.u.all));
manip_pkt((*pskb)->nh.iph->protocol,
(*pskb)->nh.iph,
(*pskb)->len,
&info->manips[i].manip,
info->manips[i].maniptype,
&(*pskb)->nfcache);
}
}
helper = info->helper;
READ_UNLOCK(&ip_nat_lock);
if (helper) {
/* Always defragged for helpers */
IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off
& __constant_htons(IP_MF|IP_OFFSET)));
return helper->help(ct, info, ctinfo, hooknum, pskb);
} else return NF_ACCEPT;
}
unsigned int
icmp_reply_translation(struct sk_buff *skb,
struct ip_conntrack *conntrack,
unsigned int hooknum,
int dir)
{
struct iphdr *iph = skb->nh.iph;
struct icmphdr *hdr = (struct icmphdr *)((u_int32_t *)iph + iph->ihl);
struct iphdr *inner = (struct iphdr *)(hdr + 1);
size_t datalen = skb->len - ((void *)inner - (void *)iph);
unsigned int i;
struct ip_nat_info *info = &conntrack->nat.info;
IP_NF_ASSERT(skb->len >= iph->ihl*4 + sizeof(struct icmphdr));
/* Must be RELATED */
IP_NF_ASSERT(skb->nfct - (struct ip_conntrack *)skb->nfct->master
== IP_CT_RELATED
|| skb->nfct - (struct ip_conntrack *)skb->nfct->master
== IP_CT_RELATED+IP_CT_IS_REPLY);
/* Redirects on non-null nats must be dropped, else they'll
start talking to each other without our translation, and be
confused... --RR */
if (hdr->type == ICMP_REDIRECT) {
/* Don't care about races here. */
if (info->initialized
!= ((1 << IP_NAT_MANIP_SRC) | (1 << IP_NAT_MANIP_DST))
|| info->num_manips != 0)
return NF_DROP;
}
DEBUGP("icmp_reply_translation: translating error %p hook %u dir %s\n",
skb, hooknum, dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY");
/* Note: May not be from a NAT'd host, but probably safest to
do translation always as if it came from the host itself
(even though a "host unreachable" coming from the host
itself is a bit wierd).
More explanation: some people use NAT for anonymizing.
Also, CERT recommends dropping all packets from private IP
addresses (although ICMP errors from internal links with
such addresses are not too uncommon, as Alan Cox points
out) */
READ_LOCK(&ip_nat_lock);
for (i = 0; i < info->num_manips; i++) {
DEBUGP("icmp_reply: manip %u dir %s hook %u\n",
i, info->manips[i].direction == IP_CT_DIR_ORIGINAL ?
"ORIG" : "REPLY", info->manips[i].hooknum);
if (info->manips[i].direction != dir)
continue;
/* Mapping the inner packet is just like a normal
packet, except it was never src/dst reversed, so
where we would normally apply a dst manip, we apply
a src, and vice versa. */
if (info->manips[i].hooknum == opposite_hook[hooknum]) {
DEBUGP("icmp_reply: inner %s -> %u.%u.%u.%u %u\n",
info->manips[i].maniptype == IP_NAT_MANIP_SRC
? "DST" : "SRC",
NIPQUAD(info->manips[i].manip.ip),
ntohs(info->manips[i].manip.u.udp.port));
manip_pkt(inner->protocol, inner,
skb->len - ((void *)inner - (void *)iph),
&info->manips[i].manip,
!info->manips[i].maniptype,
&skb->nfcache);
/* Outer packet needs to have IP header NATed like
it's a reply. */
} else if (info->manips[i].hooknum == hooknum) {
/* Use mapping to map outer packet: 0 give no
per-proto mapping */
DEBUGP("icmp_reply: outer %s -> %u.%u.%u.%u\n",
info->manips[i].maniptype == IP_NAT_MANIP_SRC
? "SRC" : "DST",
NIPQUAD(info->manips[i].manip.ip));
manip_pkt(0, iph, skb->len,
&info->manips[i].manip,
info->manips[i].maniptype,
&skb->nfcache);
}
}
READ_UNLOCK(&ip_nat_lock);
/* Since we mangled inside ICMP packet, recalculate its
checksum from scratch. (Hence the handling of incorrect
checksums in conntrack, so we don't accidentally fix one.) */
hdr->checksum = 0;
hdr->checksum = ip_compute_csum((unsigned char *)hdr,
sizeof(*hdr) + datalen);
return NF_ACCEPT;
}
int ip_nat_helper_register(struct ip_nat_helper *me)
{
int ret = 0;
WRITE_LOCK(&ip_nat_lock);
if (LIST_FIND(&helpers, helper_cmp, struct ip_nat_helper *,&me->tuple))
ret = -EBUSY;
else {
list_prepend(&helpers, me);
MOD_INC_USE_COUNT;
}
WRITE_UNLOCK(&ip_nat_lock);
return ret;
}
static int
kill_helper(const struct ip_conntrack *i, void *helper)
{
int ret;
READ_LOCK(&ip_nat_lock);
ret = (i->nat.info.helper == helper);
READ_UNLOCK(&ip_nat_lock);
return ret;
}
void ip_nat_helper_unregister(struct ip_nat_helper *me)
{
WRITE_LOCK(&ip_nat_lock);
LIST_DELETE(&helpers, me);
WRITE_UNLOCK(&ip_nat_lock);
/* Someone could be still looking at the helper in a bh. */
br_write_lock_bh(BR_NETPROTO_LOCK);
br_write_unlock_bh(BR_NETPROTO_LOCK);
/* Find anything using it, and umm, kill them. We can't turn
them into normal connections: if we've adjusted SYNs, then
they'll ackstorm. So we just drop it. We used to just
bump module count when a connection existed, but that
forces admins to gen fake RSTs or bounce box, either of
which is just a long-winded way of making things
worse. --RR */
ip_ct_selective_cleanup(kill_helper, me);
MOD_DEC_USE_COUNT;
}
int __init ip_nat_init(void)
{
size_t i;
/* Sew in builtin protocols. */
WRITE_LOCK(&ip_nat_lock);
list_append(&protos, &ip_nat_protocol_tcp);
list_append(&protos, &ip_nat_protocol_udp);
list_append(&protos, &ip_nat_protocol_icmp);
WRITE_UNLOCK(&ip_nat_lock);
for (i = 0; i < IP_NAT_HTABLE_SIZE; i++) {
INIT_LIST_HEAD(&bysource[i]);
INIT_LIST_HEAD(&byipsproto[i]);
}
/* FIXME: Man, this is a hack. <SIGH> */
IP_NF_ASSERT(ip_conntrack_destroyed == NULL);
ip_conntrack_destroyed = &ip_nat_cleanup_conntrack;
return 0;
}
void ip_nat_cleanup(void)
{
ip_conntrack_destroyed = NULL;
}
|