linux/net/ipv6/netfilter.c

266 lines
6.5 KiB
C
Raw Normal View History

/*
* IPv6 specific functions of netfilter core
*
* Rusty Russell (C) 2000 -- This code is GPL.
* Patrick McHardy (C) 2006-2012
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/ipv6.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <linux/export.h>
netfilter: add nf_ipv6_ops hook to fix xt_addrtype with IPv6 Quoting https://bugzilla.netfilter.org/show_bug.cgi?id=812: [ ip6tables -m addrtype ] When I tried to use in the nat/PREROUTING it messes up the routing cache even if the rule didn't matched at all. [..] If I remove the --limit-iface-in from the non-working scenario, so just use the -m addrtype --dst-type LOCAL it works! This happens when LOCAL type matching is requested with --limit-iface-in, and the default ipv6 route is via the interface the packet we test arrived on. Because xt_addrtype uses ip6_route_output, the ipv6 routing implementation creates an unwanted cached entry, and the packet won't make it to the real/expected destination. Silently ignoring --limit-iface-in makes the routing work but it breaks rule matching (--dst-type LOCAL with limit-iface-in is supposed to only match if the dst address is configured on the incoming interface; without --limit-iface-in it will match if the address is reachable via lo). The test should call ipv6_chk_addr() instead. However, this would add a link-time dependency on ipv6. There are two possible solutions: 1) Revert the commit that moved ipt_addrtype to xt_addrtype, and put ipv6 specific code into ip6t_addrtype. 2) add new "nf_ipv6_ops" struct to register pointers to ipv6 functions. While the former might seem preferable, Pablo pointed out that there are more xt modules with link-time dependeny issues regarding ipv6, so lets go for 2). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-05-17 11:56:10 +08:00
#include <net/addrconf.h>
#include <net/dst.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/xfrm.h>
#include <net/netfilter/nf_queue.h>
#include <net/netfilter/nf_conntrack_bridge.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include "../bridge/br_private.h"
int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct sock *sk = sk_to_full_sk(skb->sk);
unsigned int hh_len;
struct dst_entry *dst;
int strict = (ipv6_addr_type(&iph->daddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
struct flowi6 fl6 = {
.flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if :
strict ? skb_dst(skb)->dev->ifindex : 0,
.flowi6_mark = skb->mark,
.flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
.saddr = iph->saddr,
};
int err;
dst = ip6_route_output(net, sk, &fl6);
err = dst->error;
if (err) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
net_dbg_ratelimited("ip6_route_me_harder: No more route\n");
dst_release(dst);
return err;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, dst);
#ifdef CONFIG_XFRM
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_dst_set(skb, dst);
}
#endif
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
0, GFP_ATOMIC))
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL(ip6_route_me_harder);
static int nf_ip6_reroute(struct sk_buff *skb,
const struct nf_queue_entry *entry)
{
struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
if (entry->state.hook == NF_INET_LOCAL_OUT) {
const struct ipv6hdr *iph = ipv6_hdr(skb);
if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
!ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
skb->mark != rt_info->mark)
return ip6_route_me_harder(entry->state.net, skb);
}
return 0;
}
int __nf_ip6_route(struct net *net, struct dst_entry **dst,
struct flowi *fl, bool strict)
{
static const struct ipv6_pinfo fake_pinfo;
static const struct inet_sock fake_sk = {
/* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */
.sk.sk_bound_dev_if = 1,
.pinet6 = (struct ipv6_pinfo *) &fake_pinfo,
};
const void *sk = strict ? &fake_sk : NULL;
struct dst_entry *result;
int err;
result = ip6_route_output(net, sk, &fl->u.ip6);
err = result->error;
if (err)
dst_release(result);
else
*dst = result;
return err;
}
EXPORT_SYMBOL_GPL(__nf_ip6_route);
int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
struct nf_bridge_frag_data *data,
int (*output)(struct net *, struct sock *sk,
const struct nf_bridge_frag_data *data,
struct sk_buff *))
{
int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
ktime_t tstamp = skb->tstamp;
struct ip6_frag_state state;
u8 *prevhdr, nexthdr = 0;
unsigned int mtu, hlen;
int hroom, err = 0;
__be32 frag_id;
err = ip6_find_1stfragopt(skb, &prevhdr);
if (err < 0)
goto blackhole;
hlen = err;
nexthdr = *prevhdr;
mtu = skb->dev->mtu;
if (frag_max_size > mtu ||
frag_max_size < IPV6_MIN_MTU)
goto blackhole;
mtu = frag_max_size;
if (mtu < hlen + sizeof(struct frag_hdr) + 8)
goto blackhole;
mtu -= hlen + sizeof(struct frag_hdr);
frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr);
if (skb->ip_summed == CHECKSUM_PARTIAL &&
(err = skb_checksum_help(skb)))
goto blackhole;
hroom = LL_RESERVED_SPACE(skb->dev);
if (skb_has_frag_list(skb)) {
unsigned int first_len = skb_pagelen(skb);
struct ip6_fraglist_iter iter;
struct sk_buff *frag2;
if (first_len - hlen > mtu ||
skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
goto blackhole;
if (skb_cloned(skb))
goto slow_path;
skb_walk_frags(skb, frag2) {
if (frag2->len > mtu ||
skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
goto blackhole;
/* Partially cloned skb? */
if (skb_shared(frag2))
goto slow_path;
}
err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id,
&iter);
if (err < 0)
goto blackhole;
for (;;) {
/* Prepare header of the next frame,
* before previous one went down.
*/
if (iter.frag)
ip6_fraglist_prepare(skb, &iter);
skb->tstamp = tstamp;
err = output(net, sk, data, skb);
if (err || !iter.frag)
break;
skb = ip6_fraglist_next(&iter);
}
kfree(iter.tmp_hdr);
if (!err)
return 0;
net: fix use-after-free in kfree_skb_list syzbot reported nasty use-after-free [1] Lets remove frag_list field from structs ip_fraglist_iter and ip6_fraglist_iter. This seens not needed anyway. [1] : BUG: KASAN: use-after-free in kfree_skb_list+0x5d/0x60 net/core/skbuff.c:706 Read of size 8 at addr ffff888085a3cbc0 by task syz-executor303/8947 CPU: 0 PID: 8947 Comm: syz-executor303 Not tainted 5.2.0-rc2+ #12 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 kasan_report+0x12/0x20 mm/kasan/common.c:614 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132 kfree_skb_list+0x5d/0x60 net/core/skbuff.c:706 ip6_fragment+0x1ef4/0x2680 net/ipv6/ip6_output.c:882 __ip6_finish_output+0x577/0xaa0 net/ipv6/ip6_output.c:144 ip6_finish_output+0x38/0x1f0 net/ipv6/ip6_output.c:156 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip6_output+0x235/0x7f0 net/ipv6/ip6_output.c:179 dst_output include/net/dst.h:433 [inline] ip6_local_out+0xbb/0x1b0 net/ipv6/output_core.c:179 ip6_send_skb+0xbb/0x350 net/ipv6/ip6_output.c:1796 ip6_push_pending_frames+0xc8/0xf0 net/ipv6/ip6_output.c:1816 rawv6_push_pending_frames net/ipv6/raw.c:617 [inline] rawv6_sendmsg+0x2993/0x35e0 net/ipv6/raw.c:947 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:671 ___sys_sendmsg+0x803/0x920 net/socket.c:2292 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330 __do_sys_sendmsg net/socket.c:2339 [inline] __se_sys_sendmsg net/socket.c:2337 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x44add9 Code: e8 7c e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 1b 05 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f826f33bce8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000006e7a18 RCX: 000000000044add9 RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000005 RBP: 00000000006e7a10 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006e7a1c R13: 00007ffcec4f7ebf R14: 00007f826f33c9c0 R15: 20c49ba5e353f7cf Allocated by task 8947: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_kmalloc mm/kasan/common.c:489 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:497 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc_node mm/slab.c:3269 [inline] kmem_cache_alloc_node+0x131/0x710 mm/slab.c:3579 __alloc_skb+0xd5/0x5e0 net/core/skbuff.c:199 alloc_skb include/linux/skbuff.h:1058 [inline] __ip6_append_data.isra.0+0x2a24/0x3640 net/ipv6/ip6_output.c:1519 ip6_append_data+0x1e5/0x320 net/ipv6/ip6_output.c:1688 rawv6_sendmsg+0x1467/0x35e0 net/ipv6/raw.c:940 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:671 ___sys_sendmsg+0x803/0x920 net/socket.c:2292 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330 __do_sys_sendmsg net/socket.c:2339 [inline] __se_sys_sendmsg net/socket.c:2337 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 8947: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459 __cache_free mm/slab.c:3432 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3698 kfree_skbmem net/core/skbuff.c:625 [inline] kfree_skbmem+0xc5/0x150 net/core/skbuff.c:619 __kfree_skb net/core/skbuff.c:682 [inline] kfree_skb net/core/skbuff.c:699 [inline] kfree_skb+0xf0/0x390 net/core/skbuff.c:693 kfree_skb_list+0x44/0x60 net/core/skbuff.c:708 __dev_xmit_skb net/core/dev.c:3551 [inline] __dev_queue_xmit+0x3034/0x36b0 net/core/dev.c:3850 dev_queue_xmit+0x18/0x20 net/core/dev.c:3914 neigh_direct_output+0x16/0x20 net/core/neighbour.c:1532 neigh_output include/net/neighbour.h:511 [inline] ip6_finish_output2+0x1034/0x2550 net/ipv6/ip6_output.c:120 ip6_fragment+0x1ebb/0x2680 net/ipv6/ip6_output.c:863 __ip6_finish_output+0x577/0xaa0 net/ipv6/ip6_output.c:144 ip6_finish_output+0x38/0x1f0 net/ipv6/ip6_output.c:156 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip6_output+0x235/0x7f0 net/ipv6/ip6_output.c:179 dst_output include/net/dst.h:433 [inline] ip6_local_out+0xbb/0x1b0 net/ipv6/output_core.c:179 ip6_send_skb+0xbb/0x350 net/ipv6/ip6_output.c:1796 ip6_push_pending_frames+0xc8/0xf0 net/ipv6/ip6_output.c:1816 rawv6_push_pending_frames net/ipv6/raw.c:617 [inline] rawv6_sendmsg+0x2993/0x35e0 net/ipv6/raw.c:947 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:671 ___sys_sendmsg+0x803/0x920 net/socket.c:2292 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330 __do_sys_sendmsg net/socket.c:2339 [inline] __se_sys_sendmsg net/socket.c:2337 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff888085a3cbc0 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 0 bytes inside of 224-byte region [ffff888085a3cbc0, ffff888085a3cca0) The buggy address belongs to the page: page:ffffea0002168f00 refcount:1 mapcount:0 mapping:ffff88821b6f63c0 index:0x0 flags: 0x1fffc0000000200(slab) raw: 01fffc0000000200 ffffea00027bbf88 ffffea0002105b88 ffff88821b6f63c0 raw: 0000000000000000 ffff888085a3c080 000000010000000c 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888085a3ca80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888085a3cb00: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc >ffff888085a3cb80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb ^ ffff888085a3cc00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888085a3cc80: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc Fixes: 0feca6190f88 ("net: ipv6: add skbuff fraglist splitter") Fixes: c8b17be0b7a4 ("net: ipv4: add skbuff fraglist splitter") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Pablo Neira Ayuso <pablo@netfilter.org> Acked-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-03 02:24:18 +08:00
kfree_skb_list(iter.frag);
return err;
}
slow_path:
/* This is a linearized skbuff, the original geometry is lost for us.
* This may also be a clone skbuff, we could preserve the geometry for
* the copies but probably not worth the effort.
*/
ip6_frag_init(skb, hlen, mtu, skb->dev->needed_tailroom,
LL_RESERVED_SPACE(skb->dev), prevhdr, nexthdr, frag_id,
&state);
while (state.left > 0) {
struct sk_buff *skb2;
skb2 = ip6_frag_next(skb, &state);
if (IS_ERR(skb2)) {
err = PTR_ERR(skb2);
goto blackhole;
}
skb2->tstamp = tstamp;
err = output(net, sk, data, skb2);
if (err)
goto blackhole;
}
consume_skb(skb);
return err;
blackhole:
kfree_skb(skb);
return 0;
}
EXPORT_SYMBOL_GPL(br_ip6_fragment);
netfilter: add nf_ipv6_ops hook to fix xt_addrtype with IPv6 Quoting https://bugzilla.netfilter.org/show_bug.cgi?id=812: [ ip6tables -m addrtype ] When I tried to use in the nat/PREROUTING it messes up the routing cache even if the rule didn't matched at all. [..] If I remove the --limit-iface-in from the non-working scenario, so just use the -m addrtype --dst-type LOCAL it works! This happens when LOCAL type matching is requested with --limit-iface-in, and the default ipv6 route is via the interface the packet we test arrived on. Because xt_addrtype uses ip6_route_output, the ipv6 routing implementation creates an unwanted cached entry, and the packet won't make it to the real/expected destination. Silently ignoring --limit-iface-in makes the routing work but it breaks rule matching (--dst-type LOCAL with limit-iface-in is supposed to only match if the dst address is configured on the incoming interface; without --limit-iface-in it will match if the address is reachable via lo). The test should call ipv6_chk_addr() instead. However, this would add a link-time dependency on ipv6. There are two possible solutions: 1) Revert the commit that moved ipt_addrtype to xt_addrtype, and put ipv6 specific code into ip6t_addrtype. 2) add new "nf_ipv6_ops" struct to register pointers to ipv6 functions. While the former might seem preferable, Pablo pointed out that there are more xt modules with link-time dependeny issues regarding ipv6, so lets go for 2). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-05-17 11:56:10 +08:00
static const struct nf_ipv6_ops ipv6ops = {
#if IS_MODULE(CONFIG_IPV6)
.chk_addr = ipv6_chk_addr,
.route_me_harder = ip6_route_me_harder,
.dev_get_saddr = ipv6_dev_get_saddr,
.route = __nf_ip6_route,
#if IS_ENABLED(CONFIG_SYN_COOKIES)
.cookie_init_sequence = __cookie_v6_init_sequence,
.cookie_v6_check = __cookie_v6_check,
#endif
#endif
.route_input = ip6_route_input,
.fragment = ip6_fragment,
.reroute = nf_ip6_reroute,
#if IS_MODULE(CONFIG_IPV6)
.br_fragment = br_ip6_fragment,
#endif
netfilter: add nf_ipv6_ops hook to fix xt_addrtype with IPv6 Quoting https://bugzilla.netfilter.org/show_bug.cgi?id=812: [ ip6tables -m addrtype ] When I tried to use in the nat/PREROUTING it messes up the routing cache even if the rule didn't matched at all. [..] If I remove the --limit-iface-in from the non-working scenario, so just use the -m addrtype --dst-type LOCAL it works! This happens when LOCAL type matching is requested with --limit-iface-in, and the default ipv6 route is via the interface the packet we test arrived on. Because xt_addrtype uses ip6_route_output, the ipv6 routing implementation creates an unwanted cached entry, and the packet won't make it to the real/expected destination. Silently ignoring --limit-iface-in makes the routing work but it breaks rule matching (--dst-type LOCAL with limit-iface-in is supposed to only match if the dst address is configured on the incoming interface; without --limit-iface-in it will match if the address is reachable via lo). The test should call ipv6_chk_addr() instead. However, this would add a link-time dependency on ipv6. There are two possible solutions: 1) Revert the commit that moved ipt_addrtype to xt_addrtype, and put ipv6 specific code into ip6t_addrtype. 2) add new "nf_ipv6_ops" struct to register pointers to ipv6 functions. While the former might seem preferable, Pablo pointed out that there are more xt modules with link-time dependeny issues regarding ipv6, so lets go for 2). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-05-17 11:56:10 +08:00
};
int __init ipv6_netfilter_init(void)
{
netfilter: add nf_ipv6_ops hook to fix xt_addrtype with IPv6 Quoting https://bugzilla.netfilter.org/show_bug.cgi?id=812: [ ip6tables -m addrtype ] When I tried to use in the nat/PREROUTING it messes up the routing cache even if the rule didn't matched at all. [..] If I remove the --limit-iface-in from the non-working scenario, so just use the -m addrtype --dst-type LOCAL it works! This happens when LOCAL type matching is requested with --limit-iface-in, and the default ipv6 route is via the interface the packet we test arrived on. Because xt_addrtype uses ip6_route_output, the ipv6 routing implementation creates an unwanted cached entry, and the packet won't make it to the real/expected destination. Silently ignoring --limit-iface-in makes the routing work but it breaks rule matching (--dst-type LOCAL with limit-iface-in is supposed to only match if the dst address is configured on the incoming interface; without --limit-iface-in it will match if the address is reachable via lo). The test should call ipv6_chk_addr() instead. However, this would add a link-time dependency on ipv6. There are two possible solutions: 1) Revert the commit that moved ipt_addrtype to xt_addrtype, and put ipv6 specific code into ip6t_addrtype. 2) add new "nf_ipv6_ops" struct to register pointers to ipv6 functions. While the former might seem preferable, Pablo pointed out that there are more xt modules with link-time dependeny issues regarding ipv6, so lets go for 2). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-05-17 11:56:10 +08:00
RCU_INIT_POINTER(nf_ipv6_ops, &ipv6ops);
return 0;
}
/* This can be called from inet6_init() on errors, so it cannot
* be marked __exit. -DaveM
*/
void ipv6_netfilter_fini(void)
{
netfilter: add nf_ipv6_ops hook to fix xt_addrtype with IPv6 Quoting https://bugzilla.netfilter.org/show_bug.cgi?id=812: [ ip6tables -m addrtype ] When I tried to use in the nat/PREROUTING it messes up the routing cache even if the rule didn't matched at all. [..] If I remove the --limit-iface-in from the non-working scenario, so just use the -m addrtype --dst-type LOCAL it works! This happens when LOCAL type matching is requested with --limit-iface-in, and the default ipv6 route is via the interface the packet we test arrived on. Because xt_addrtype uses ip6_route_output, the ipv6 routing implementation creates an unwanted cached entry, and the packet won't make it to the real/expected destination. Silently ignoring --limit-iface-in makes the routing work but it breaks rule matching (--dst-type LOCAL with limit-iface-in is supposed to only match if the dst address is configured on the incoming interface; without --limit-iface-in it will match if the address is reachable via lo). The test should call ipv6_chk_addr() instead. However, this would add a link-time dependency on ipv6. There are two possible solutions: 1) Revert the commit that moved ipt_addrtype to xt_addrtype, and put ipv6 specific code into ip6t_addrtype. 2) add new "nf_ipv6_ops" struct to register pointers to ipv6 functions. While the former might seem preferable, Pablo pointed out that there are more xt modules with link-time dependeny issues regarding ipv6, so lets go for 2). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-05-17 11:56:10 +08:00
RCU_INIT_POINTER(nf_ipv6_ops, NULL);
}