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
|
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/module.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_core.h>
#include <net/netfilter/nf_tproxy.h>
#include <net/inet_sock.h>
#include <net/tcp.h>
#include <linux/if_ether.h>
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#endif
struct nft_tproxy {
u8 sreg_addr;
u8 sreg_port;
u8 family;
};
static void nft_tproxy_eval_v4(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
const struct nft_tproxy *priv = nft_expr_priv(expr);
struct sk_buff *skb = pkt->skb;
const struct iphdr *iph = ip_hdr(skb);
struct udphdr _hdr, *hp;
__be32 taddr = 0;
__be16 tport = 0;
struct sock *sk;
if (pkt->tprot != IPPROTO_TCP &&
pkt->tprot != IPPROTO_UDP) {
regs->verdict.code = NFT_BREAK;
return;
}
hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
if (!hp) {
regs->verdict.code = NFT_BREAK;
return;
}
/* check if there's an ongoing connection on the packet addresses, this
* happens if the redirect already happened and the current packet
* belongs to an already established connection
*/
sk = nf_tproxy_get_sock_v4(nft_net(pkt), skb, iph->protocol,
iph->saddr, iph->daddr,
hp->source, hp->dest,
skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED);
if (priv->sreg_addr)
taddr = nft_reg_load_be32(®s->data[priv->sreg_addr]);
taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr);
if (priv->sreg_port)
tport = nft_reg_load_be16(®s->data[priv->sreg_port]);
if (!tport)
tport = hp->dest;
/* UDP has no TCP_TIME_WAIT state, so we never enter here */
if (sk && sk->sk_state == TCP_TIME_WAIT) {
/* reopening a TIME_WAIT connection needs special handling */
sk = nf_tproxy_handle_time_wait4(nft_net(pkt), skb, taddr, tport, sk);
} else if (!sk) {
/* no, there's no established connection, check if
* there's a listener on the redirected addr/port
*/
sk = nf_tproxy_get_sock_v4(nft_net(pkt), skb, iph->protocol,
iph->saddr, taddr,
hp->source, tport,
skb->dev, NF_TPROXY_LOOKUP_LISTENER);
}
if (sk && nf_tproxy_sk_is_transparent(sk))
nf_tproxy_assign_sock(skb, sk);
else
regs->verdict.code = NFT_BREAK;
}
#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
static void nft_tproxy_eval_v6(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
const struct nft_tproxy *priv = nft_expr_priv(expr);
struct sk_buff *skb = pkt->skb;
const struct ipv6hdr *iph = ipv6_hdr(skb);
int thoff = nft_thoff(pkt);
struct udphdr _hdr, *hp;
struct in6_addr taddr;
__be16 tport = 0;
struct sock *sk;
int l4proto;
memset(&taddr, 0, sizeof(taddr));
if (pkt->tprot != IPPROTO_TCP &&
pkt->tprot != IPPROTO_UDP) {
regs->verdict.code = NFT_BREAK;
return;
}
l4proto = pkt->tprot;
hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
if (hp == NULL) {
regs->verdict.code = NFT_BREAK;
return;
}
/* check if there's an ongoing connection on the packet addresses, this
* happens if the redirect already happened and the current packet
* belongs to an already established connection
*/
sk = nf_tproxy_get_sock_v6(nft_net(pkt), skb, thoff, l4proto,
&iph->saddr, &iph->daddr,
hp->source, hp->dest,
nft_in(pkt), NF_TPROXY_LOOKUP_ESTABLISHED);
if (priv->sreg_addr)
memcpy(&taddr, ®s->data[priv->sreg_addr], sizeof(taddr));
taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr);
if (priv->sreg_port)
tport = nft_reg_load_be16(®s->data[priv->sreg_port]);
if (!tport)
tport = hp->dest;
/* UDP has no TCP_TIME_WAIT state, so we never enter here */
if (sk && sk->sk_state == TCP_TIME_WAIT) {
/* reopening a TIME_WAIT connection needs special handling */
sk = nf_tproxy_handle_time_wait6(skb, l4proto, thoff,
nft_net(pkt),
&taddr,
tport,
sk);
} else if (!sk) {
/* no there's no established connection, check if
* there's a listener on the redirected addr/port
*/
sk = nf_tproxy_get_sock_v6(nft_net(pkt), skb, thoff,
l4proto, &iph->saddr, &taddr,
hp->source, tport,
nft_in(pkt), NF_TPROXY_LOOKUP_LISTENER);
}
/* NOTE: assign_sock consumes our sk reference */
if (sk && nf_tproxy_sk_is_transparent(sk))
nf_tproxy_assign_sock(skb, sk);
else
regs->verdict.code = NFT_BREAK;
}
#endif
static void nft_tproxy_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
const struct nft_tproxy *priv = nft_expr_priv(expr);
switch (nft_pf(pkt)) {
case NFPROTO_IPV4:
switch (priv->family) {
case NFPROTO_IPV4:
case NFPROTO_UNSPEC:
nft_tproxy_eval_v4(expr, regs, pkt);
return;
}
break;
#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
case NFPROTO_IPV6:
switch (priv->family) {
case NFPROTO_IPV6:
case NFPROTO_UNSPEC:
nft_tproxy_eval_v6(expr, regs, pkt);
return;
}
#endif
}
regs->verdict.code = NFT_BREAK;
}
static const struct nla_policy nft_tproxy_policy[NFTA_TPROXY_MAX + 1] = {
[NFTA_TPROXY_FAMILY] = { .type = NLA_U32 },
[NFTA_TPROXY_REG_ADDR] = { .type = NLA_U32 },
[NFTA_TPROXY_REG_PORT] = { .type = NLA_U32 },
};
static int nft_tproxy_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[])
{
struct nft_tproxy *priv = nft_expr_priv(expr);
unsigned int alen = 0;
int err;
if (!tb[NFTA_TPROXY_FAMILY] ||
(!tb[NFTA_TPROXY_REG_ADDR] && !tb[NFTA_TPROXY_REG_PORT]))
return -EINVAL;
priv->family = ntohl(nla_get_be32(tb[NFTA_TPROXY_FAMILY]));
switch (ctx->family) {
case NFPROTO_IPV4:
if (priv->family != NFPROTO_IPV4)
return -EINVAL;
break;
#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
case NFPROTO_IPV6:
if (priv->family != NFPROTO_IPV6)
return -EINVAL;
break;
#endif
case NFPROTO_INET:
break;
default:
return -EOPNOTSUPP;
}
/* Address is specified but the rule family is not set accordingly */
if (priv->family == NFPROTO_UNSPEC && tb[NFTA_TPROXY_REG_ADDR])
return -EINVAL;
switch (priv->family) {
case NFPROTO_IPV4:
alen = sizeof_field(union nf_inet_addr, in);
err = nf_defrag_ipv4_enable(ctx->net);
if (err)
return err;
break;
#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
case NFPROTO_IPV6:
alen = sizeof_field(union nf_inet_addr, in6);
err = nf_defrag_ipv6_enable(ctx->net);
if (err)
return err;
break;
#endif
case NFPROTO_UNSPEC:
/* No address is specified here */
err = nf_defrag_ipv4_enable(ctx->net);
if (err)
return err;
#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
err = nf_defrag_ipv6_enable(ctx->net);
if (err)
return err;
#endif
break;
default:
return -EOPNOTSUPP;
}
if (tb[NFTA_TPROXY_REG_ADDR]) {
err = nft_parse_register_load(tb[NFTA_TPROXY_REG_ADDR],
&priv->sreg_addr, alen);
if (err < 0)
return err;
}
if (tb[NFTA_TPROXY_REG_PORT]) {
err = nft_parse_register_load(tb[NFTA_TPROXY_REG_PORT],
&priv->sreg_port, sizeof(u16));
if (err < 0)
return err;
}
return 0;
}
static void nft_tproxy_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr)
{
const struct nft_tproxy *priv = nft_expr_priv(expr);
switch (priv->family) {
case NFPROTO_IPV4:
nf_defrag_ipv4_disable(ctx->net);
break;
#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
case NFPROTO_IPV6:
nf_defrag_ipv6_disable(ctx->net);
break;
#endif
case NFPROTO_UNSPEC:
nf_defrag_ipv4_disable(ctx->net);
#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
nf_defrag_ipv6_disable(ctx->net);
#endif
break;
}
}
static int nft_tproxy_dump(struct sk_buff *skb,
const struct nft_expr *expr)
{
const struct nft_tproxy *priv = nft_expr_priv(expr);
if (nla_put_be32(skb, NFTA_TPROXY_FAMILY, htonl(priv->family)))
return -1;
if (priv->sreg_addr &&
nft_dump_register(skb, NFTA_TPROXY_REG_ADDR, priv->sreg_addr))
return -1;
if (priv->sreg_port &&
nft_dump_register(skb, NFTA_TPROXY_REG_PORT, priv->sreg_port))
return -1;
return 0;
}
static int nft_tproxy_validate(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nft_data **data)
{
return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING);
}
static struct nft_expr_type nft_tproxy_type;
static const struct nft_expr_ops nft_tproxy_ops = {
.type = &nft_tproxy_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_tproxy)),
.eval = nft_tproxy_eval,
.init = nft_tproxy_init,
.destroy = nft_tproxy_destroy,
.dump = nft_tproxy_dump,
.reduce = NFT_REDUCE_READONLY,
.validate = nft_tproxy_validate,
};
static struct nft_expr_type nft_tproxy_type __read_mostly = {
.name = "tproxy",
.ops = &nft_tproxy_ops,
.policy = nft_tproxy_policy,
.maxattr = NFTA_TPROXY_MAX,
.owner = THIS_MODULE,
};
static int __init nft_tproxy_module_init(void)
{
return nft_register_expr(&nft_tproxy_type);
}
static void __exit nft_tproxy_module_exit(void)
{
nft_unregister_expr(&nft_tproxy_type);
}
module_init(nft_tproxy_module_init);
module_exit(nft_tproxy_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Máté Eckl");
MODULE_DESCRIPTION("nf_tables tproxy support module");
MODULE_ALIAS_NFT_EXPR("tproxy");
|