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
|
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Stateless NAT actions
*
* Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
*/
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netfilter.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/tc_act/tc_nat.h>
#include <net/act_api.h>
#include <net/pkt_cls.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/netlink.h>
#include <net/tc_act/tc_nat.h>
#include <net/tcp.h>
#include <net/udp.h>
static struct tc_action_ops act_nat_ops;
static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
[TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) },
};
static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
struct tc_action **a, struct tcf_proto *tp,
u32 flags, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, act_nat_ops.net_id);
bool bind = flags & TCA_ACT_FLAGS_BIND;
struct nlattr *tb[TCA_NAT_MAX + 1];
struct tcf_chain *goto_ch = NULL;
struct tc_nat *parm;
int ret = 0, err;
struct tcf_nat *p;
u32 index;
if (nla == NULL)
return -EINVAL;
err = nla_parse_nested_deprecated(tb, TCA_NAT_MAX, nla, nat_policy,
NULL);
if (err < 0)
return err;
if (tb[TCA_NAT_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_NAT_PARMS]);
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
ret = tcf_idr_create(tn, index, est, a,
&act_nat_ops, bind, false, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
} else if (err > 0) {
if (bind)
return 0;
if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
} else {
return err;
}
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto release_idr;
p = to_tcf_nat(*a);
spin_lock_bh(&p->tcf_lock);
p->old_addr = parm->old_addr;
p->new_addr = parm->new_addr;
p->mask = parm->mask;
p->flags = parm->flags;
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
spin_unlock_bh(&p->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
return ret;
release_idr:
tcf_idr_release(*a, bind);
return err;
}
static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_nat *p = to_tcf_nat(a);
struct iphdr *iph;
__be32 old_addr;
__be32 new_addr;
__be32 mask;
__be32 addr;
int egress;
int action;
int ihl;
int noff;
spin_lock(&p->tcf_lock);
tcf_lastuse_update(&p->tcf_tm);
old_addr = p->old_addr;
new_addr = p->new_addr;
mask = p->mask;
egress = p->flags & TCA_NAT_FLAG_EGRESS;
action = p->tcf_action;
bstats_update(&p->tcf_bstats, skb);
spin_unlock(&p->tcf_lock);
if (unlikely(action == TC_ACT_SHOT))
goto drop;
noff = skb_network_offset(skb);
if (!pskb_may_pull(skb, sizeof(*iph) + noff))
goto drop;
iph = ip_hdr(skb);
if (egress)
addr = iph->saddr;
else
addr = iph->daddr;
if (!((old_addr ^ addr) & mask)) {
if (skb_try_make_writable(skb, sizeof(*iph) + noff))
goto drop;
new_addr &= mask;
new_addr |= addr & ~mask;
/* Rewrite IP header */
iph = ip_hdr(skb);
if (egress)
iph->saddr = new_addr;
else
iph->daddr = new_addr;
csum_replace4(&iph->check, addr, new_addr);
} else if ((iph->frag_off & htons(IP_OFFSET)) ||
iph->protocol != IPPROTO_ICMP) {
goto out;
}
ihl = iph->ihl * 4;
/* It would be nice to share code with stateful NAT. */
switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
case IPPROTO_TCP:
{
struct tcphdr *tcph;
if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
goto drop;
tcph = (void *)(skb_network_header(skb) + ihl);
inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr,
true);
break;
}
case IPPROTO_UDP:
{
struct udphdr *udph;
if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
goto drop;
udph = (void *)(skb_network_header(skb) + ihl);
if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&udph->check, skb, addr,
new_addr, true);
if (!udph->check)
udph->check = CSUM_MANGLED_0;
}
break;
}
case IPPROTO_ICMP:
{
struct icmphdr *icmph;
if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
if (!icmp_is_err(icmph->type))
break;
if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) +
noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
iph = (void *)(icmph + 1);
if (egress)
addr = iph->daddr;
else
addr = iph->saddr;
if ((old_addr ^ addr) & mask)
break;
if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
sizeof(*iph) + noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
iph = (void *)(icmph + 1);
new_addr &= mask;
new_addr |= addr & ~mask;
/* XXX Fix up the inner checksums. */
if (egress)
iph->daddr = new_addr;
else
iph->saddr = new_addr;
inet_proto_csum_replace4(&icmph->checksum, skb, addr, new_addr,
false);
break;
}
default:
break;
}
out:
return action;
drop:
spin_lock(&p->tcf_lock);
p->tcf_qstats.drops++;
spin_unlock(&p->tcf_lock);
return TC_ACT_SHOT;
}
static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_nat *p = to_tcf_nat(a);
struct tc_nat opt = {
.index = p->tcf_index,
.refcnt = refcount_read(&p->tcf_refcnt) - ref,
.bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
};
struct tcf_t t;
spin_lock_bh(&p->tcf_lock);
opt.old_addr = p->old_addr;
opt.new_addr = p->new_addr;
opt.mask = p->mask;
opt.flags = p->flags;
opt.action = p->tcf_action;
if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &p->tcf_tm);
if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD))
goto nla_put_failure;
spin_unlock_bh(&p->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&p->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static struct tc_action_ops act_nat_ops = {
.kind = "nat",
.id = TCA_ID_NAT,
.owner = THIS_MODULE,
.act = tcf_nat_act,
.dump = tcf_nat_dump,
.init = tcf_nat_init,
.size = sizeof(struct tcf_nat),
};
static __net_init int nat_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, act_nat_ops.net_id);
return tc_action_net_init(net, tn, &act_nat_ops);
}
static void __net_exit nat_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, act_nat_ops.net_id);
}
static struct pernet_operations nat_net_ops = {
.init = nat_init_net,
.exit_batch = nat_exit_net,
.id = &act_nat_ops.net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_DESCRIPTION("Stateless NAT actions");
MODULE_LICENSE("GPL");
static int __init nat_init_module(void)
{
return tcf_register_action(&act_nat_ops, &nat_net_ops);
}
static void __exit nat_cleanup_module(void)
{
tcf_unregister_action(&act_nat_ops, &nat_net_ops);
}
module_init(nat_init_module);
module_exit(nat_cleanup_module);
|