xref: /kernel/linux/linux-5.10/net/sched/act_nat.c (revision 8c2ecf20) 
1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * Stateless NAT actions
4 *
5 * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
6 */
7
8#include <linux/errno.h>
9#include <linux/init.h>
10#include <linux/kernel.h>
11#include <linux/module.h>
12#include <linux/netfilter.h>
13#include <linux/rtnetlink.h>
14#include <linux/skbuff.h>
15#include <linux/slab.h>
16#include <linux/spinlock.h>
17#include <linux/string.h>
18#include <linux/tc_act/tc_nat.h>
19#include <net/act_api.h>
20#include <net/pkt_cls.h>
21#include <net/icmp.h>
22#include <net/ip.h>
23#include <net/netlink.h>
24#include <net/tc_act/tc_nat.h>
25#include <net/tcp.h>
26#include <net/udp.h>
27
28
29static unsigned int nat_net_id;
30static struct tc_action_ops act_nat_ops;
31
32static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
33	[TCA_NAT_PARMS]	= { .len = sizeof(struct tc_nat) },
34};
35
36static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
37			struct tc_action **a, int ovr, int bind,
38			bool rtnl_held,	struct tcf_proto *tp,
39			u32 flags, struct netlink_ext_ack *extack)
40{
41	struct tc_action_net *tn = net_generic(net, nat_net_id);
42	struct nlattr *tb[TCA_NAT_MAX + 1];
43	struct tcf_chain *goto_ch = NULL;
44	struct tc_nat *parm;
45	int ret = 0, err;
46	struct tcf_nat *p;
47	u32 index;
48
49	if (nla == NULL)
50		return -EINVAL;
51
52	err = nla_parse_nested_deprecated(tb, TCA_NAT_MAX, nla, nat_policy,
53					  NULL);
54	if (err < 0)
55		return err;
56
57	if (tb[TCA_NAT_PARMS] == NULL)
58		return -EINVAL;
59	parm = nla_data(tb[TCA_NAT_PARMS]);
60	index = parm->index;
61	err = tcf_idr_check_alloc(tn, &index, a, bind);
62	if (!err) {
63		ret = tcf_idr_create(tn, index, est, a,
64				     &act_nat_ops, bind, false, flags);
65		if (ret) {
66			tcf_idr_cleanup(tn, index);
67			return ret;
68		}
69		ret = ACT_P_CREATED;
70	} else if (err > 0) {
71		if (bind)
72			return 0;
73		if (!ovr) {
74			tcf_idr_release(*a, bind);
75			return -EEXIST;
76		}
77	} else {
78		return err;
79	}
80	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
81	if (err < 0)
82		goto release_idr;
83	p = to_tcf_nat(*a);
84
85	spin_lock_bh(&p->tcf_lock);
86	p->old_addr = parm->old_addr;
87	p->new_addr = parm->new_addr;
88	p->mask = parm->mask;
89	p->flags = parm->flags;
90
91	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
92	spin_unlock_bh(&p->tcf_lock);
93	if (goto_ch)
94		tcf_chain_put_by_act(goto_ch);
95
96	return ret;
97release_idr:
98	tcf_idr_release(*a, bind);
99	return err;
100}
101
102static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a,
103		       struct tcf_result *res)
104{
105	struct tcf_nat *p = to_tcf_nat(a);
106	struct iphdr *iph;
107	__be32 old_addr;
108	__be32 new_addr;
109	__be32 mask;
110	__be32 addr;
111	int egress;
112	int action;
113	int ihl;
114	int noff;
115
116	spin_lock(&p->tcf_lock);
117
118	tcf_lastuse_update(&p->tcf_tm);
119	old_addr = p->old_addr;
120	new_addr = p->new_addr;
121	mask = p->mask;
122	egress = p->flags & TCA_NAT_FLAG_EGRESS;
123	action = p->tcf_action;
124
125	bstats_update(&p->tcf_bstats, skb);
126
127	spin_unlock(&p->tcf_lock);
128
129	if (unlikely(action == TC_ACT_SHOT))
130		goto drop;
131
132	noff = skb_network_offset(skb);
133	if (!pskb_may_pull(skb, sizeof(*iph) + noff))
134		goto drop;
135
136	iph = ip_hdr(skb);
137
138	if (egress)
139		addr = iph->saddr;
140	else
141		addr = iph->daddr;
142
143	if (!((old_addr ^ addr) & mask)) {
144		if (skb_try_make_writable(skb, sizeof(*iph) + noff))
145			goto drop;
146
147		new_addr &= mask;
148		new_addr |= addr & ~mask;
149
150		/* Rewrite IP header */
151		iph = ip_hdr(skb);
152		if (egress)
153			iph->saddr = new_addr;
154		else
155			iph->daddr = new_addr;
156
157		csum_replace4(&iph->check, addr, new_addr);
158	} else if ((iph->frag_off & htons(IP_OFFSET)) ||
159		   iph->protocol != IPPROTO_ICMP) {
160		goto out;
161	}
162
163	ihl = iph->ihl * 4;
164
165	/* It would be nice to share code with stateful NAT. */
166	switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
167	case IPPROTO_TCP:
168	{
169		struct tcphdr *tcph;
170
171		if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
172		    skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
173			goto drop;
174
175		tcph = (void *)(skb_network_header(skb) + ihl);
176		inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr,
177					 true);
178		break;
179	}
180	case IPPROTO_UDP:
181	{
182		struct udphdr *udph;
183
184		if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
185		    skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
186			goto drop;
187
188		udph = (void *)(skb_network_header(skb) + ihl);
189		if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
190			inet_proto_csum_replace4(&udph->check, skb, addr,
191						 new_addr, true);
192			if (!udph->check)
193				udph->check = CSUM_MANGLED_0;
194		}
195		break;
196	}
197	case IPPROTO_ICMP:
198	{
199		struct icmphdr *icmph;
200
201		if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + noff))
202			goto drop;
203
204		icmph = (void *)(skb_network_header(skb) + ihl);
205
206		if (!icmp_is_err(icmph->type))
207			break;
208
209		if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) +
210					noff))
211			goto drop;
212
213		icmph = (void *)(skb_network_header(skb) + ihl);
214		iph = (void *)(icmph + 1);
215		if (egress)
216			addr = iph->daddr;
217		else
218			addr = iph->saddr;
219
220		if ((old_addr ^ addr) & mask)
221			break;
222
223		if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
224					  sizeof(*iph) + noff))
225			goto drop;
226
227		icmph = (void *)(skb_network_header(skb) + ihl);
228		iph = (void *)(icmph + 1);
229
230		new_addr &= mask;
231		new_addr |= addr & ~mask;
232
233		/* XXX Fix up the inner checksums. */
234		if (egress)
235			iph->daddr = new_addr;
236		else
237			iph->saddr = new_addr;
238
239		inet_proto_csum_replace4(&icmph->checksum, skb, addr, new_addr,
240					 false);
241		break;
242	}
243	default:
244		break;
245	}
246
247out:
248	return action;
249
250drop:
251	spin_lock(&p->tcf_lock);
252	p->tcf_qstats.drops++;
253	spin_unlock(&p->tcf_lock);
254	return TC_ACT_SHOT;
255}
256
257static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
258			int bind, int ref)
259{
260	unsigned char *b = skb_tail_pointer(skb);
261	struct tcf_nat *p = to_tcf_nat(a);
262	struct tc_nat opt = {
263		.index    = p->tcf_index,
264		.refcnt   = refcount_read(&p->tcf_refcnt) - ref,
265		.bindcnt  = atomic_read(&p->tcf_bindcnt) - bind,
266	};
267	struct tcf_t t;
268
269	spin_lock_bh(&p->tcf_lock);
270	opt.old_addr = p->old_addr;
271	opt.new_addr = p->new_addr;
272	opt.mask = p->mask;
273	opt.flags = p->flags;
274	opt.action = p->tcf_action;
275
276	if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt))
277		goto nla_put_failure;
278
279	tcf_tm_dump(&t, &p->tcf_tm);
280	if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD))
281		goto nla_put_failure;
282	spin_unlock_bh(&p->tcf_lock);
283
284	return skb->len;
285
286nla_put_failure:
287	spin_unlock_bh(&p->tcf_lock);
288	nlmsg_trim(skb, b);
289	return -1;
290}
291
292static int tcf_nat_walker(struct net *net, struct sk_buff *skb,
293			  struct netlink_callback *cb, int type,
294			  const struct tc_action_ops *ops,
295			  struct netlink_ext_ack *extack)
296{
297	struct tc_action_net *tn = net_generic(net, nat_net_id);
298
299	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
300}
301
302static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index)
303{
304	struct tc_action_net *tn = net_generic(net, nat_net_id);
305
306	return tcf_idr_search(tn, a, index);
307}
308
309static struct tc_action_ops act_nat_ops = {
310	.kind		=	"nat",
311	.id		=	TCA_ID_NAT,
312	.owner		=	THIS_MODULE,
313	.act		=	tcf_nat_act,
314	.dump		=	tcf_nat_dump,
315	.init		=	tcf_nat_init,
316	.walk		=	tcf_nat_walker,
317	.lookup		=	tcf_nat_search,
318	.size		=	sizeof(struct tcf_nat),
319};
320
321static __net_init int nat_init_net(struct net *net)
322{
323	struct tc_action_net *tn = net_generic(net, nat_net_id);
324
325	return tc_action_net_init(net, tn, &act_nat_ops);
326}
327
328static void __net_exit nat_exit_net(struct list_head *net_list)
329{
330	tc_action_net_exit(net_list, nat_net_id);
331}
332
333static struct pernet_operations nat_net_ops = {
334	.init = nat_init_net,
335	.exit_batch = nat_exit_net,
336	.id   = &nat_net_id,
337	.size = sizeof(struct tc_action_net),
338};
339
340MODULE_DESCRIPTION("Stateless NAT actions");
341MODULE_LICENSE("GPL");
342
343static int __init nat_init_module(void)
344{
345	return tcf_register_action(&act_nat_ops, &nat_net_ops);
346}
347
348static void __exit nat_cleanup_module(void)
349{
350	tcf_unregister_action(&act_nat_ops, &nat_net_ops);
351}
352
353module_init(nat_init_module);
354module_exit(nat_cleanup_module);
355