/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
{
struct net *net = dev_net(skb_dst(skb)->dev);
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi4 fl4 = {};
__be32 saddr = iph->saddr;
__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
unsigned int hh_len;
if (addr_type == RTN_UNSPEC)
addr_type = inet_addr_type(net, saddr);
if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
flags |= FLOWI_FLAG_ANYSRC;
else
saddr = 0;
/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
* packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
*/
fl4.daddr = iph->daddr;
fl4.saddr = saddr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
fl4.flowi4_mark = skb->mark;
fl4.flowi4_flags = flags;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return -1;
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
if (skb_dst(skb)->error)
return -1;
#ifdef CONFIG_XFRM
if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
struct dst_entry *dst = skb_dst(skb);
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
if (IS_ERR(dst))
return -1;
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 -1;
return 0;
}
static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct rtable *rt;
const struct iphdr *iph = ip_hdr(skb);
struct flowi4 fl4 = {
.flowi4_oif = inet_iif(skb),
.daddr = iph->saddr,
.saddr = iph->daddr,
.flowi4_tos = RT_CONN_FLAGS(sk),
.flowi4_proto = sk->sk_protocol,
.fl4_sport = dccp_hdr(skb)->dccph_dport,
.fl4_dport = dccp_hdr(skb)->dccph_sport,
};
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
if (IS_ERR(rt)) {
IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
return &rt->dst;
}
static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req)
{
int err = -1;
struct sk_buff *skb;
struct dst_entry *dst;
struct flowi4 fl4;
dst = inet_csk_route_req(sk, &fl4, req);
if (dst == NULL)
goto out;
skb = dccp_make_response(sk, dst, req);
if (skb != NULL) {
const struct inet_request_sock *ireq = inet_rsk(req);
struct dccp_hdr *dh = dccp_hdr(skb);
dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
ireq->ir_rmt_addr);
rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
rcu_dereference(ireq->ireq_opt));
rcu_read_unlock();
err = net_xmit_eval(err);
}
out:
dst_release(dst);
return err;
}
int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res)
{
struct fib_lookup_arg arg = {
.result = res,
.flags = FIB_LOOKUP_NOREF,
};
int err;
err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg);
res->r = arg.rule;
return err;
}
static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
{
struct inet_sock *inet = inet_sk(sk);
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
struct flowi4 fl4;
int free = 0;
__be32 daddr;
__be32 saddr;
u8 tos;
int err;
struct ip_options_data opt_copy;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
/*
* Check the flags.
*/
err = -EOPNOTSUPP;
if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message */
goto out; /* compatibility */
/*
* Get and verify the address.
*/
if (msg->msg_namelen) {
struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
err = -EINVAL;
if (msg->msg_namelen < sizeof(*usin))
goto out;
if (usin->sin_family != AF_INET) {
pr_info_once("%s: %s forgot to set AF_INET. Fix it!\n",
__func__, current->comm);
err = -EAFNOSUPPORT;
if (usin->sin_family)
goto out;
}
daddr = usin->sin_addr.s_addr;
/* ANK: I did not forget to get protocol from port field.
* I just do not know, who uses this weirdness.
* IP_HDRINCL is much more convenient.
*/
} else {
err = -EDESTADDRREQ;
if (sk->sk_state != TCP_ESTABLISHED)
goto out;
daddr = inet->inet_daddr;
}
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
err = ip_cmsg_send(sock_net(sk), msg, &ipc);
if (err)
goto out;
if (ipc.opt)
free = 1;
}
saddr = ipc.addr;
ipc.addr = daddr;
if (!ipc.opt) {
struct ip_options_rcu *inet_opt;
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt) {
memcpy(&opt_copy, inet_opt,
sizeof(*inet_opt) + inet_opt->opt.optlen);
ipc.opt = &opt_copy.opt;
}
rcu_read_unlock();
}
if (ipc.opt) {
err = -EINVAL;
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
if (inet->hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
goto done;
daddr = ipc.opt->opt.faddr;
}
}
tos = RT_CONN_FLAGS(sk);
if (msg->msg_flags & MSG_DONTROUTE)
tos |= RTO_ONLINK;
if (ipv4_is_multicast(daddr)) {
if (!ipc.oif)
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
} else if (!ipc.oif)
ipc.oif = inet->uc_index;
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP |
(inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0,
sock_i_uid(sk));
if (!inet->hdrincl) {
err = raw_probe_proto_opt(&fl4, msg);
if (err)
goto done;
}
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
goto done;
}
err = -EACCES;
if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
goto done;
if (msg->msg_flags & MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
if (inet->hdrincl)
err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len,
&rt, msg->msg_flags);
else {
if (!ipc.addr)
ipc.addr = fl4.daddr;
lock_sock(sk);
err = ip_append_data(sk, &fl4, ip_generic_getfrag,
msg->msg_iov, len, 0,
&ipc, &rt, msg->msg_flags);
if (err)
ip_flush_pending_frames(sk);
else if (!(msg->msg_flags & MSG_MORE)) {
err = ip_push_pending_frames(sk, &fl4);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
}
release_sock(sk);
}
done:
if (free)
kfree(ipc.opt);
ip_rt_put(rt);
out:
if (err < 0)
return err;
return len;
do_confirm:
dst_confirm(&rt->dst);
if (!(msg->msg_flags & MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto done;
}
static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
{
struct inet_sock *inet = inet_sk(sk);
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
int free = 0;
__be32 daddr;
__be32 saddr;
u8 tos;
int err;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
/*
* Check the flags.
*/
err = -EOPNOTSUPP;
if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message */
goto out; /* compatibility */
/*
* Get and verify the address.
*/
if (msg->msg_namelen) {
struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
err = -EINVAL;
if (msg->msg_namelen < sizeof(*usin))
goto out;
if (usin->sin_family != AF_INET) {
static int complained;
if (!complained++)
printk(KERN_INFO "%s forgot to set AF_INET in "
"raw sendmsg. Fix it!\n",
current->comm);
err = -EAFNOSUPPORT;
if (usin->sin_family)
goto out;
}
daddr = usin->sin_addr.s_addr;
/* ANK: I did not forget to get protocol from port field.
* I just do not know, who uses this weirdness.
* IP_HDRINCL is much more convenient.
*/
} else {
err = -EDESTADDRREQ;
if (sk->sk_state != TCP_ESTABLISHED)
goto out;
daddr = inet->inet_daddr;
}
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
err = ip_cmsg_send(sock_net(sk), msg, &ipc);
if (err)
goto out;
if (ipc.opt)
free = 1;
}
saddr = ipc.addr;
ipc.addr = daddr;
if (!ipc.opt)
ipc.opt = inet->opt;
if (ipc.opt) {
err = -EINVAL;
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
if (inet->hdrincl)
goto done;
if (ipc.opt->srr) {
if (!daddr)
goto done;
daddr = ipc.opt->faddr;
}
}
tos = RT_CONN_FLAGS(sk);
if (msg->msg_flags & MSG_DONTROUTE)
tos |= RTO_ONLINK;
if (ipv4_is_multicast(daddr)) {
if (!ipc.oif)
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
}
{
struct flowi4 fl4 = {
.flowi4_oif = ipc.oif,
.flowi4_mark = sk->sk_mark,
.daddr = daddr,
.saddr = saddr,
.flowi4_tos = tos,
.flowi4_proto = (inet->hdrincl ?
IPPROTO_RAW :
sk->sk_protocol),
.flowi4_flags = FLOWI_FLAG_CAN_SLEEP,
};
if (!inet->hdrincl) {
err = raw_probe_proto_opt(&fl4, msg);
if (err)
goto done;
}
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
goto done;
}
}
err = -EACCES;
if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
goto done;
if (msg->msg_flags & MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
if (inet->hdrincl)
err = raw_send_hdrinc(sk, msg->msg_iov, len,
&rt, msg->msg_flags);
else {
if (!ipc.addr)
ipc.addr = rt->rt_dst;
lock_sock(sk);
err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0,
&ipc, &rt, msg->msg_flags);
if (err)
ip_flush_pending_frames(sk);
else if (!(msg->msg_flags & MSG_MORE)) {
err = ip_push_pending_frames(sk);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
}
release_sock(sk);
}
done:
if (free)
kfree(ipc.opt);
ip_rt_put(rt);
out:
if (err < 0)
return err;
return len;
do_confirm:
dst_confirm(&rt->dst);
if (!(msg->msg_flags & MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto done;
}
static void raw_close(struct sock *sk, long timeout)
{
/*
* Raw sockets may have direct kernel refereneces. Kill them.
*/
ip_ra_control(sk, 0, NULL);
sk_common_release(sk);
}
static int callforward_do_filter(const union nf_inet_addr *src,
const union nf_inet_addr *dst,
u_int8_t family)
{
const struct nf_afinfo *afinfo;
int ret = 0;
afinfo = nf_get_afinfo(family);
if (!afinfo)
return 0;
switch (family) {
case AF_INET: {
struct flowi4 fl1, fl2;
struct rtable *rt1, *rt2;
memset(&fl1, 0, sizeof(fl1));
fl1.daddr = src->ip;
memset(&fl2, 0, sizeof(fl2));
fl2.daddr = dst->ip;
if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
flowi4_to_flowi(&fl1), false)) {
if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
flowi4_to_flowi(&fl2), false)) {
if (rt1->rt_gateway == rt2->rt_gateway &&
rt1->dst.dev == rt2->dst.dev)
ret = 1;
dst_release(&rt2->dst);
}
dst_release(&rt1->dst);
}
break;
}
#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
case AF_INET6: {
struct flowi6 fl1, fl2;
struct rt6_info *rt1, *rt2;
memset(&fl1, 0, sizeof(fl1));
fl1.daddr = src->in6;
memset(&fl2, 0, sizeof(fl2));
fl2.daddr = dst->in6;
if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
flowi6_to_flowi(&fl1), false)) {
if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
flowi6_to_flowi(&fl2), false)) {
if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
sizeof(rt1->rt6i_gateway)) &&
rt1->dst.dev == rt2->dst.dev)
ret = 1;
dst_release(&rt2->dst);
}
dst_release(&rt1->dst);
}
break;
}
#endif
}
return ret;
}
/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
{
struct net *net = dev_net(skb_dst(skb)->dev);
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi4 fl4 = {};
unsigned long orefdst;
unsigned int hh_len;
unsigned int type;
type = inet_addr_type(net, iph->saddr);
if (skb->sk && inet_sk(skb->sk)->transparent)
type = RTN_LOCAL;
if (addr_type == RTN_UNSPEC)
addr_type = type;
/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
* packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
*/
if (addr_type == RTN_LOCAL) {
fl4.daddr = iph->daddr;
if (type == RTN_LOCAL)
fl4.saddr = iph->saddr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
fl4.flowi4_mark = skb->mark;
fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return -1;
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
/* non-local src, find valid iif to satisfy
* rp-filter when calling ip_route_input. */
fl4.daddr = iph->saddr;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return -1;
orefdst = skb->_skb_refdst;
if (ip_route_input(skb, iph->daddr, iph->saddr,
RT_TOS(iph->tos), rt->dst.dev) != 0) {
dst_release(&rt->dst);
return -1;
}
dst_release(&rt->dst);
refdst_drop(orefdst);
}
if (skb_dst(skb)->error)
return -1;
#ifdef CONFIG_XFRM
if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
struct dst_entry *dst = skb_dst(skb);
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
if (IS_ERR(dst))
return -1;
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_len - skb_headroom(skb), 0, GFP_ATOMIC))
return -1;
return 0;
}
