linux-stable/net/ipv6/netfilter/ip6table_mangle.c

138 lines
3.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* IPv6 packet mangling table, a port of the IPv4 mangle table to IPv6
*
* Copyright (C) 2000-2001 by Harald Welte <laforge@gnumonks.org>
* Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org>
*/
#include <linux/module.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <net/ipv6.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("ip6tables mangle table");
#define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \
(1 << NF_INET_LOCAL_IN) | \
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT) | \
(1 << NF_INET_POST_ROUTING))
static const struct xt_table packet_mangler = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
.priority = NF_IP6_PRI_MANGLE,
};
static unsigned int
ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state)
{
struct in6_addr saddr, daddr;
unsigned int ret, verdict;
u32 flowlabel, mark;
u8 hop_limit;
int err;
/* save source/dest address, mark, hoplimit, flowlabel, priority, */
memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
mark = skb->mark;
hop_limit = ipv6_hdr(skb)->hop_limit;
/* flowlabel and prio (includes version, which shouldn't change either */
flowlabel = *((u_int32_t *)ipv6_hdr(skb));
ret = ip6t_do_table(priv, skb, state);
verdict = ret & NF_VERDICT_MASK;
if (verdict != NF_DROP && verdict != NF_STOLEN &&
(!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) ||
!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) ||
skb->mark != mark ||
ipv6_hdr(skb)->hop_limit != hop_limit ||
flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
netfilter: use actual socket sk rather than skb sk when routing harder If netfilter changes the packet mark when mangling, the packet is rerouted using the route_me_harder set of functions. Prior to this commit, there's one big difference between route_me_harder and the ordinary initial routing functions, described in the comment above __ip_queue_xmit(): /* 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, That function goes on to correctly make use of sk->sk_bound_dev_if, rather than skb->sk->sk_bound_dev_if. And indeed the comment is true: a tunnel will receive a packet in ndo_start_xmit with an initial skb->sk. It will make some transformations to that packet, and then it will send the encapsulated packet out of a *new* socket. That new socket will basically always have a different sk_bound_dev_if (otherwise there'd be a routing loop). So for the purposes of routing the encapsulated packet, the routing information as it pertains to the socket should come from that socket's sk, rather than the packet's original skb->sk. For that reason __ip_queue_xmit() and related functions all do the right thing. One might argue that all tunnels should just call skb_orphan(skb) before transmitting the encapsulated packet into the new socket. But tunnels do *not* do this -- and this is wisely avoided in skb_scrub_packet() too -- because features like TSQ rely on skb->destructor() being called when that buffer space is truely available again. Calling skb_orphan(skb) too early would result in buffers filling up unnecessarily and accounting info being all wrong. Instead, additional routing must take into account the new sk, just as __ip_queue_xmit() notes. So, this commit addresses the problem by fishing the correct sk out of state->sk -- it's already set properly in the call to nf_hook() in __ip_local_out(), which receives the sk as part of its normal functionality. So we make sure to plumb state->sk through the various route_me_harder functions, and then make correct use of it following the example of __ip_queue_xmit(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2020-10-29 02:56:06 +00:00
err = ip6_route_me_harder(state->net, state->sk, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
return ret;
}
/* The work comes in here from netfilter.c. */
static unsigned int
ip6table_mangle_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
if (state->hook == NF_INET_LOCAL_OUT)
return ip6t_mangle_out(priv, skb, state);
return ip6t_do_table(priv, skb, state);
}
static struct nf_hook_ops *mangle_ops __read_mostly;
static int ip6table_mangle_table_init(struct net *net)
{
struct ip6t_replace *repl;
int ret;
repl = ip6t_alloc_initial_table(&packet_mangler);
if (repl == NULL)
return -ENOMEM;
ret = ip6t_register_table(net, &packet_mangler, repl, mangle_ops);
kfree(repl);
return ret;
}
static void __net_exit ip6table_mangle_net_pre_exit(struct net *net)
{
ip6t_unregister_table_pre_exit(net, "mangle");
}
static void __net_exit ip6table_mangle_net_exit(struct net *net)
{
ip6t_unregister_table_exit(net, "mangle");
}
static struct pernet_operations ip6table_mangle_net_ops = {
.pre_exit = ip6table_mangle_net_pre_exit,
.exit = ip6table_mangle_net_exit,
};
static int __init ip6table_mangle_init(void)
{
int ret = xt_register_template(&packet_mangler,
ip6table_mangle_table_init);
if (ret < 0)
return ret;
2016-02-25 09:08:36 +00:00
mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook);
if (IS_ERR(mangle_ops)) {
xt_unregister_template(&packet_mangler);
2016-02-25 09:08:36 +00:00
return PTR_ERR(mangle_ops);
}
2016-02-25 09:08:36 +00:00
ret = register_pernet_subsys(&ip6table_mangle_net_ops);
2016-02-25 09:08:36 +00:00
if (ret < 0) {
xt_unregister_template(&packet_mangler);
2016-02-25 09:08:36 +00:00
kfree(mangle_ops);
return ret;
}
return ret;
}
static void __exit ip6table_mangle_fini(void)
{
unregister_pernet_subsys(&ip6table_mangle_net_ops);
xt_unregister_template(&packet_mangler);
2016-02-25 09:08:36 +00:00
kfree(mangle_ops);
}
module_init(ip6table_mangle_init);
module_exit(ip6table_mangle_fini);