/* 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;
}
/*
* Direct Routing transmitter
* Used for ANY protocol
*/
int
ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
struct iphdr *iph = ip_hdr(skb);
int mtu;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(iph->tos), 1|2)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error;
}
/*
* Call ip_send_check because we are not sure it is called
* after ip_defrag. Is copy-on-write needed?
*/
if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
ip_rt_put(rt);
return NF_STOLEN;
}
ip_send_check(ip_hdr(skb));
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
}
/* Try to route the packet according to the routing keys specified in
* route_info. Keys are :
* - ifindex :
* 0 if no oif preferred,
* otherwise set to the index of the desired oif
* - route_info->gw :
* 0 if no gateway specified,
* otherwise set to the next host to which the pkt must be routed
* If success, skb->dev is the output device to which the packet must
* be sent and skb->dst is not NULL
*
* RETURN: -1 if an error occured
* 1 if the packet was succesfully routed to the
* destination desired
* 0 if the kernel routing table could not route the packet
* according to the keys specified
*/
static int route(struct sk_buff *skb,
unsigned int ifindex,
const struct ipt_route_target_info *route_info)
{
int err;
struct rtable *rt;
struct iphdr *iph = ip_hdr(skb);
struct flowi fl = {
.oif = ifindex,
.nl_u = {
.ip4_u = {
.daddr = iph->daddr,
.saddr = 0,
.tos = RT_TOS(iph->tos),
.scope = RT_SCOPE_UNIVERSE,
}
}
};
/* The destination address may be overloaded by the target */
if (route_info->gw)
fl.fl4_dst = route_info->gw;
/* Trying to route the packet using the standard routing table. */
if ((err = ip_route_output_key(&init_net,&rt, &fl))) {
if (net_ratelimit())
pr_debug("ipt_ROUTE: couldn't route pkt (err: %i)",err);
return -1;
}
/* Drop old route. */
skb_dst_drop(skb);
/* Success if no oif specified or if the oif correspond to the
* one desired */
if (!ifindex || rt->dst.dev->ifindex == ifindex) {
skb_dst_set(skb, &rt->dst);
skb->dev = skb_dst(skb)->dev;
skb->protocol = htons(ETH_P_IP);
return 1;
}
/* The interface selected by the routing table is not the one
* specified by the user. This may happen because the dst address
* is one of our own addresses.
*/
if (net_ratelimit())
pr_debug("ipt_ROUTE: failed to route as desired gw, oif=%i (got oif=%i)\n",
//pr_debug("ipt_ROUTE: failed to route as desired gw=%u.%u.%u.%u oif=%i (got oif=%i)\n",
ifindex, rt->dst.dev->ifindex);
//NIPQUAD(route_info->gw), ifindex, rt->dst.dev->ifindex);
return 0;
}
static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
struct net *net = ovs_dp_get_net(vport->dp);
struct vxlan_port *vxlan_port = vxlan_vport(vport);
__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
struct ovs_key_ipv4_tunnel *tun_key;
struct rtable *rt;
struct flowi4 fl;
__be16 src_port;
__be16 df;
int err;
if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
err = -EINVAL;
goto error;
}
tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
/* Route lookup */
memset(&fl, 0, sizeof(fl));
fl.daddr = tun_key->ipv4_dst;
fl.saddr = tun_key->ipv4_src;
fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
fl.flowi4_mark = skb->mark;
fl.flowi4_proto = IPPROTO_UDP;
rt = ip_route_output_key(net, &fl);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
goto error;
}
df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
htons(IP_DF) : 0;
skb->ignore_df = 1;
src_port = udp_flow_src_port(net, skb, 0, 0, true);
err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
fl.saddr, tun_key->ipv4_dst,
tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
src_port, dst_port,
htonl(be64_to_cpu(tun_key->tun_id) << 8),
false);
if (err < 0)
ip_rt_put(rt);
return err;
error:
kfree_skb(skb);
return err;
}
static inline struct rtable *route_mirror(struct sk_buff *skb, int local)
{
struct iphdr *iph = skb->nh.iph;
struct dst_entry *odst;
struct rt_key key = {};
struct rtable *rt;
if (local) {
key.dst = iph->saddr;
key.src = iph->daddr;
key.tos = RT_TOS(iph->tos);
if (ip_route_output_key(&rt, &key) != 0)
return NULL;
} else {
/* non-local src, find valid iif to satisfy
* rp-filter when calling ip_route_input. */
key.dst = iph->daddr;
if (ip_route_output_key(&rt, &key) != 0)
return NULL;
odst = skb->dst;
if (ip_route_input(skb, iph->saddr, iph->daddr,
RT_TOS(iph->tos), rt->u.dst.dev) != 0) {
dst_release(&rt->u.dst);
return NULL;
}
dst_release(&rt->u.dst);
rt = (struct rtable *)skb->dst;
skb->dst = odst;
}
if (rt->u.dst.error) {
dst_release(&rt->u.dst);
rt = NULL;
}
return rt;
}
static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
struct net_device *vrf_dev)
{
struct iphdr *ip4h = ip_hdr(skb);
int ret = NET_XMIT_DROP;
struct flowi4 fl4 = {
/* needed to match OIF rule */
.flowi4_oif = vrf_dev->ifindex,
.flowi4_iif = LOOPBACK_IFINDEX,
.flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC |
FLOWI_FLAG_SKIP_NH_OIF,
.daddr = ip4h->daddr,
};
if (vrf_send_v4_prep(skb, &fl4, vrf_dev))
goto err;
if (!ip4h->saddr) {
ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0,
RT_SCOPE_LINK);
}
ret = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
vrf_dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
out:
return ret;
err:
vrf_tx_error(vrf_dev, skb);
goto out;
}
static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
{
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));
switch (skb->protocol) {
case htons(ETH_P_IP):
return vrf_process_v4_outbound(skb, dev);
case htons(ETH_P_IPV6):
return vrf_process_v6_outbound(skb, dev);
default:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
}
static int ip_masq_user_maddr(struct ip_masq_user *ums)
{
struct device *dev;
struct rtable *rt;
int ret = -EINVAL;
u32 rt_daddr, rt_saddr;
u32 tos;
/*
* Did specify masq address.
*/
if (ums->maddr)
return 0;
/*
* Select address to use for routing query
*/
rt_daddr = ums->rt_daddr? ums->rt_daddr : ums->daddr;
rt_saddr = ums->rt_saddr? ums->rt_saddr : ums->saddr;
/*
* No address for routing, cannot continue
*/
if (rt_daddr == 0) {
IP_MASQ_DEBUG(1-debug, "cannot setup maddr with daddr=%lX, rt_addr=%lX\n",
ntohl(ums->daddr), ntohl(ums->rt_daddr));
return -EINVAL;
}
/*
* Find out rt device
*/
rt_saddr = 0;
tos = RT_TOS(ums->ip_tos) | RTO_CONN;
if ((ret=ip_route_output(&rt, rt_daddr, rt_saddr, tos, 0 /* dev */))) {
IP_MASQ_DEBUG(0-debug, "could not setup maddr for routing daddr=%lX, saddr=%lX\n",
ntohl(rt_daddr), ntohl(rt_saddr));
return ret;
}
dev = rt->u.dst.dev;
ums->maddr = ip_masq_select_addr(dev, rt->rt_gateway, RT_SCOPE_UNIVERSE);
IP_MASQ_DEBUG(1-debug, "did setup maddr=%lX\n", ntohl(ums->maddr));
ip_rt_put(rt);
return 0;
}
int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
struct net *net,
const struct ovs_tunnel_info *tun_info,
u8 ipproto,
u32 skb_mark,
__be16 tp_src,
__be16 tp_dst)
{
const struct ovs_key_ipv4_tunnel *tun_key;
struct rtable *rt;
struct flowi4 fl;
if (unlikely(!tun_info))
return -EINVAL;
tun_key = &tun_info->tunnel;
/* Route lookup to get srouce IP address.
* The process may need to be changed if the corresponding process
* in vports ops changed.
*/
memset(&fl, 0, sizeof(fl));
fl.daddr = tun_key->ipv4_dst;
fl.saddr = tun_key->ipv4_src;
fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
fl.flowi4_mark = skb_mark;
fl.flowi4_proto = ipproto;
rt = ip_route_output_key(net, &fl);
if (IS_ERR(rt))
return PTR_ERR(rt);
ip_rt_put(rt);
/* Generate egress_tun_info based on tun_info,
* saddr, tp_src and tp_dst
*/
__ovs_flow_tun_info_init(egress_tun_info,
fl.saddr, tun_key->ipv4_dst,
tun_key->ipv4_tos,
tun_key->ipv4_ttl,
tp_src, tp_dst,
tun_key->tun_id,
tun_key->tun_flags,
tun_info->options,
tun_info->options_len);
return 0;
}
static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
struct net *net = ovs_dp_get_net(vport->dp);
struct vxlan_port *vxlan_port = vxlan_vport(vport);
__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->sport;
struct rtable *rt;
struct flowi fl;
__be16 src_port;
int port_min;
int port_max;
__be16 df;
int err;
if (unlikely(!OVS_CB(skb)->tun_key)) {
err = -EINVAL;
goto error;
}
/* Route lookup */
memset(&fl, 0, sizeof(fl));
fl.fl4_dst = OVS_CB(skb)->tun_key->ipv4_dst;
fl.fl4_src = OVS_CB(skb)->tun_key->ipv4_src;
fl.fl4_tos = RT_TOS(OVS_CB(skb)->tun_key->ipv4_tos);
fl.mark = skb->mark;
fl.proto = IPPROTO_UDP;
err = ip_route_output_key(net, &rt, &fl);
if (err)
goto error;
df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
htons(IP_DF) : 0;
skb->local_df = 1;
inet_get_local_port_range(&port_min, &port_max);
src_port = vxlan_src_port(port_min, port_max, skb);
err = vxlan_xmit_skb(net, vxlan_port->vs, rt, skb,
fl.fl4_src, OVS_CB(skb)->tun_key->ipv4_dst,
OVS_CB(skb)->tun_key->ipv4_tos,
OVS_CB(skb)->tun_key->ipv4_ttl, df,
src_port, dst_port,
htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8));
if (err < 0)
ip_rt_put(rt);
error:
return err;
}
static struct rtable *gre_get_rt(struct sk_buff *skb,
struct net_device *dev,
struct flowi4 *fl,
const struct ip_tunnel_key *key)
{
struct net *net = dev_net(dev);
memset(fl, 0, sizeof(*fl));
fl->daddr = key->u.ipv4.dst;
fl->saddr = key->u.ipv4.src;
fl->flowi4_tos = RT_TOS(key->tos);
fl->flowi4_mark = skb->mark;
fl->flowi4_proto = IPPROTO_GRE;
return ip_route_output_key(net, fl);
}
static int ip_tunnel_bind_dev(struct net_device *dev)
{
struct net_device *tdev = NULL;
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *iph;
int hlen = LL_MAX_HEADER;
int mtu = ETH_DATA_LEN;
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
iph = &tunnel->parms.iph;
/* Guess output device to choose reasonable mtu and needed_headroom */
if (iph->daddr) {
struct flowi4 fl4;
struct rtable *rt;
rt = ip_route_output_tunnel(dev_net(dev), &fl4,
tunnel->parms.iph.protocol,
iph->daddr, iph->saddr,
tunnel->parms.o_key,
RT_TOS(iph->tos),
tunnel->parms.link);
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
ip_rt_put(rt);
}
if (dev->type != ARPHRD_ETHER)
dev->flags |= IFF_POINTOPOINT;
}
if (!tdev && tunnel->parms.link)
tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
if (tdev) {
hlen = tdev->hard_header_len + tdev->needed_headroom;
mtu = tdev->mtu;
}
dev->iflink = tunnel->parms.link;
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);
if (mtu < 68)
mtu = 68;
return mtu;
}
static struct rtable *ovs_tunnel_route_lookup(struct net *net,
const struct ip_tunnel_key *key,
u32 mark,
struct flowi4 *fl,
u8 protocol)
{
struct rtable *rt;
memset(fl, 0, sizeof(*fl));
fl->daddr = key->u.ipv4.dst;
fl->saddr = key->u.ipv4.src;
fl->flowi4_tos = RT_TOS(key->tos);
fl->flowi4_mark = mark;
fl->flowi4_proto = protocol;
rt = ip_route_output_key(net, fl);
return rt;
}
static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
{
struct net *net = ovs_dp_get_net(vport->dp);
struct ovs_key_ipv4_tunnel *tun_key;
struct flowi4 fl;
struct rtable *rt;
int min_headroom;
int tunnel_hlen;
__be16 df;
int err;
if (unlikely(!OVS_CB(skb)->egress_tun_key)) {
err = -EINVAL;
goto error;
}
tun_key = OVS_CB(skb)->egress_tun_key;
/* Route lookup */
memset(&fl, 0, sizeof(fl));
fl.daddr = tun_key->ipv4_dst;
fl.saddr = tun_key->ipv4_src;
fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
fl.flowi4_mark = skb->mark;
fl.flowi4_proto = IPPROTO_GRE;
rt = ip_route_output_key(net, &fl);
if (IS_ERR(rt))
return PTR_ERR(rt);
tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags);
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+ tunnel_hlen + sizeof(struct iphdr)
+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
int head_delta = SKB_DATA_ALIGN(min_headroom -
skb_headroom(skb) +
16);
err = pskb_expand_head(skb, max_t(int, head_delta, 0),
0, GFP_ATOMIC);
if (unlikely(err))
goto err_free_rt;
}
static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel_info *tun_info;
struct net *net = dev_net(dev);
const struct ip_tunnel_key *key;
struct flowi4 fl;
struct rtable *rt;
int min_headroom;
int tunnel_hlen;
__be16 df, flags;
int err;
tun_info = skb_tunnel_info(skb, AF_INET);
if (unlikely(!tun_info || tun_info->mode != IP_TUNNEL_INFO_TX))
goto err_free_skb;
key = &tun_info->key;
memset(&fl, 0, sizeof(fl));
fl.daddr = key->ipv4_dst;
fl.saddr = key->ipv4_src;
fl.flowi4_tos = RT_TOS(key->ipv4_tos);
fl.flowi4_mark = skb->mark;
fl.flowi4_proto = IPPROTO_GRE;
rt = ip_route_output_key(net, &fl);
if (IS_ERR(rt))
goto err_free_skb;
tunnel_hlen = ip_gre_calc_hlen(key->tun_flags);
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+ tunnel_hlen + sizeof(struct iphdr);
if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
int head_delta = SKB_DATA_ALIGN(min_headroom -
skb_headroom(skb) +
16);
err = pskb_expand_head(skb, max_t(int, head_delta, 0),
0, GFP_ATOMIC);
if (unlikely(err))
goto err_free_rt;
}
static int route_mirror(struct sk_buff *skb)
{
struct iphdr *iph = skb->nh.iph;
struct rtable *rt;
/* Backwards */
if (ip_route_output(&rt, iph->saddr, iph->daddr,
RT_TOS(iph->tos) | RTO_CONN,
0)) {
return 0;
}
/* check if the interface we are leaving by is the same as the
one we arrived on */
if (skb->dev == rt->u.dst.dev) {
/* Drop old route. */
dst_release(skb->dst);
skb->dst = &rt->u.dst;
return 1;
}
return 0;
}
/* With a chainsaw... */
static int route_me_harder(struct sk_buff *skb)
{
struct iphdr *iph = skb->nh.iph;
struct rtable *rt;
struct rt_key key = {
dst:iph->daddr, src:iph->saddr,
oif:skb->sk ? skb->sk->bound_dev_if : 0,
tos:RT_TOS(iph->tos) | RTO_CONN,
#ifdef CONFIG_IP_ROUTE_FWMARK
fwmark:skb->nfmark
#endif
};
if (ip_route_output_key(&rt, &key) != 0)
return -EINVAL;
/* Drop old route. */
dst_release(skb->dst);
skb->dst = &rt->u.dst;
return 0;
}
static struct rtable *route_packet_ipv4(struct sk_buff *skb)
{
struct iphdr *ip_header = ip_hdr(skb);
struct flowi fl;
struct rtable *table;
memset(&fl, 0, sizeof(fl));
fl.u.ip4.daddr = ip_header->daddr;
fl.flowi_tos = RT_TOS(ip_header->tos);
fl.flowi_proto = skb->protocol;
table = ip_route_output_key(&init_net, &fl.u.ip4);
if (!table) {
log_err(ERR_ROUTE_FAILED, "ip_route_output_key() returned NULL. Cannot route packet.");
return NULL;
}
if (IS_ERR(table)) {
log_err(ERR_ROUTE_FAILED, "ip_route_output_key() returned %p. Cannot route packet.", table);
return NULL;
}
return table;
}
/*
* IP Tunneling transmitter
*
* This function encapsulates the packet in a new IP packet, its
* destination will be set to cp->daddr. Most code of this function
* is taken from ipip.c.
*
* It is used in VS/TUN cluster. The load balancer selects a real
* server from a cluster based on a scheduling algorithm,
* encapsulates the request packet and forwards it to the selected
* server. For example, all real servers are configured with
* "ifconfig tunl0 <Virtual IP Address> up". When the server receives
* the encapsulated packet, it will decapsulate the packet, processe
* the request and return the response packets directly to the client
* without passing the load balancer. This can greatly increase the
* scalability of virtual server.
*
* Used for ANY protocol
*/
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
__be16 df = old_iph->frag_off;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int mtu;
int ret;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
df |= (old_iph->frag_off & htons(IP_DF));
if ((old_iph->frag_off & htons(IP_DF) &&
mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom
|| skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
}
kfree_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
skb->transport_header = skb->network_header;
/* fix old IP header checksum */
ip_send_check(old_iph);
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
iph->ttl = old_iph->ttl;
ip_select_ident(iph, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = IP_VS_XMIT_TUNNEL(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
/*
* NAT transmitter (only for outside-to-inside nat forwarding)
* Not used for related ICMP
*/
int
ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
int mtu;
struct iphdr *iph = ip_hdr(skb);
int local;
EnterFunction(10);
/* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
__be16 _pt, *p;
p = skb_header_pointer(skb, iph->ihl*4, sizeof(_pt), &_pt);
if (p == NULL)
goto tx_error;
ip_vs_conn_fill_cport(cp, *p);
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(iph->tos),
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0,
"ip_vs_nat_xmit(): "
"stopping DNAT to local address");
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && ipv4_is_loopback(rt->rt_dst) &&
rt_is_input_route(skb_rtable(skb))) {
IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
"stopping DNAT to loopback address");
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
!skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
"ip_vs_nat_xmit(): frag needed for");
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct iphdr)))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
goto tx_error_put;
ip_hdr(skb)->daddr = cp->daddr.ip;
ip_send_check(ip_hdr(skb));
if (!local) {
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
ip_rt_put(rt);
/*
* Some IPv4 replies get local address from routes,
* not from iph, so while we DNAT after routing
* we need this second input/output route.
*/
if (!__ip_vs_reroute_locally(skb))
goto tx_error;
}
IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
/* Reroute packet to local IPv4 stack after DNAT */
static int
__ip_vs_reroute_locally(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->dst.dev;
struct net *net = dev_net(dev);
struct iphdr *iph = ip_hdr(skb);
if (rt_is_input_route(rt)) {
unsigned long orefdst = skb->_skb_refdst;
if (ip_route_input(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev))
return 0;
refdst_drop(orefdst);
} else {
struct flowi4 fl4 = {
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowi4_tos = RT_TOS(iph->tos),
.flowi4_mark = skb->mark,
};
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return 0;
if (!(rt->rt_flags & RTCF_LOCAL)) {
ip_rt_put(rt);
return 0;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
}
return 1;
}
#ifdef CONFIG_IP_VS_IPV6
static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
{
return rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK;
}
static struct dst_entry *
__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
struct in6_addr *ret_saddr, int do_xfrm)
{
struct dst_entry *dst;
struct flowi6 fl6 = {
.daddr = *daddr,
};
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error)
goto out_err;
if (!ret_saddr)
return dst;
if (ipv6_addr_any(&fl6.saddr) &&
ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
&fl6.daddr, 0, &fl6.saddr) < 0)
goto out_err;
if (do_xfrm) {
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst)) {
dst = NULL;
goto out_err;
}
}
ipv6_addr_copy(ret_saddr, &fl6.saddr);
return dst;
out_err:
dst_release(dst);
IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", daddr);
return NULL;
}
/*
* Get route to destination or remote server
* rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest,
* &4=Allow redirect from remote daddr to local
*/
static struct rt6_info *
__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
int do_xfrm, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rt6_info *rt; /* Route to the other host */
struct rt6_info *ort; /* Original route */
struct dst_entry *dst;
int local;
if (dest) {
spin_lock(&dest->dst_lock);
rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0);
if (!rt) {
u32 cookie;
dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
&dest->dst_saddr,
do_xfrm);
if (!dst) {
spin_unlock(&dest->dst_lock);
return NULL;
}
rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
__ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
&dest->addr.in6, &dest->dst_saddr,
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
ipv6_addr_copy(ret_saddr, &dest->dst_saddr);
spin_unlock(&dest->dst_lock);
} else {
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
if (!dst)
return NULL;
rt = (struct rt6_info *) dst;
}
local = __ip_vs_is_local_route6(rt);
if (!((local ? 1 : 2) & rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n",
local ? "local":"non-local", daddr);
dst_release(&rt->dst);
return NULL;
}
if (local && !(rt_mode & 4) &&
!((ort = (struct rt6_info *) skb_dst(skb)) &&
__ip_vs_is_local_route6(ort))) {
IP_VS_DBG_RL("Redirect from non-local address %pI6 to local "
"requires NAT method, dest: %pI6\n",
&ipv6_hdr(skb)->daddr, daddr);
dst_release(&rt->dst);
return NULL;
}
if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
IPV6_ADDR_LOOPBACK)) {
IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 "
"to non-local address, dest: %pI6\n",
&ipv6_hdr(skb)->saddr, daddr);
dst_release(&rt->dst);
return NULL;
}
return rt;
}
#endif
/*
* Release dest->dst_cache before a dest is removed
*/
void
ip_vs_dst_reset(struct ip_vs_dest *dest)
{
struct dst_entry *old_dst;
old_dst = dest->dst_cache;
dest->dst_cache = NULL;
dst_release(old_dst);
}
#define IP_VS_XMIT_TUNNEL(skb, cp) \
({ \
int __ret = NF_ACCEPT; \
\
(skb)->ipvs_property = 1; \
if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \
__ret = ip_vs_confirm_conntrack(skb, cp); \
if (__ret == NF_ACCEPT) { \
nf_reset(skb); \
skb_forward_csum(skb); \
} \
__ret; \
})
#define IP_VS_XMIT_NAT(pf, skb, cp, local) \
do { \
(skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
ip_vs_notrack(skb); \
else \
ip_vs_update_conntrack(skb, cp, 1); \
if (local) \
return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
#define IP_VS_XMIT(pf, skb, cp, local) \
do { \
(skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
ip_vs_notrack(skb); \
if (local) \
return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
/*
* NULL transmitter (do nothing except return NF_ACCEPT)
*/
int
ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
/* we do not touch skb and do not need pskb ptr */
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
/*
* ICMP packet transmitter
* called by the ip_vs_in_icmp
*/
int
ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset)
{
struct rtable *rt; /* Route to the other host */
int mtu;
int rc;
int local;
EnterFunction(10);
/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
forwarded directly here, because there is no need to
translate address/port back */
if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
if (cp->packet_xmit)
rc = cp->packet_xmit(skb, cp, pp);
else
rc = NF_ACCEPT;
/* do not touch skb anymore */
atomic_inc_unchecked(&cp->in_pkts);
goto out;
}
/*
* mangle and send the packet here (only for VS/NAT)
*/
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(ip_hdr(skb)->tos),
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG(10, "%s(): "
"stopping DNAT to local address %pI4\n",
__func__, &cp->daddr.ip);
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && ipv4_is_loopback(rt->rt_dst) &&
rt_is_input_route(skb_rtable(skb))) {
IP_VS_DBG(1, "%s(): "
"stopping DNAT to loopback %pI4\n",
__func__, &cp->daddr.ip);
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) &&
!skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, offset))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
ip_vs_nat_icmp(skb, pp, cp, 0);
if (!local) {
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
ip_rt_put(rt);
/*
* Some IPv4 replies get local address from routes,
* not from iph, so while we DNAT after routing
* we need this second input/output route.
*/
if (!__ip_vs_reroute_locally(skb))
goto tx_error;
}
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
rc = NF_STOLEN;
goto out;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev_kfree_skb(skb);
rc = NF_STOLEN;
out:
LeaveFunction(10);
return rc;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
int
ip_do_nat(struct sk_buff *skb)
{
struct rtable *rt = (struct rtable*)skb->dst;
struct iphdr *iph = skb->nh.iph;
u32 odaddr = iph->daddr;
u32 osaddr = iph->saddr;
u16 check;
IPCB(skb)->flags |= IPSKB_TRANSLATED;
/* Rewrite IP header */
iph->daddr = rt->rt_dst_map;
iph->saddr = rt->rt_src_map;
iph->check = 0;
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
/* If it is the first fragment, rewrite protocol headers */
if (!(iph->frag_off & htons(IP_OFFSET))) {
u16 *cksum;
switch(iph->protocol) {
case IPPROTO_TCP:
cksum = (u16*)&((struct tcphdr*)(((char*)iph) + (iph->ihl<<2)))->check;
if ((u8*)(cksum+1) > skb->tail)
goto truncated;
check = *cksum;
if (skb->ip_summed != CHECKSUM_HW)
check = ~check;
check = csum_tcpudp_magic(iph->saddr, iph->daddr, 0, 0, check);
check = csum_tcpudp_magic(~osaddr, ~odaddr, 0, 0, ~check);
if (skb->ip_summed == CHECKSUM_HW)
check = ~check;
*cksum = check;
break;
case IPPROTO_UDP:
cksum = (u16*)&((struct udphdr*)(((char*)iph) + (iph->ihl<<2)))->check;
if ((u8*)(cksum+1) > skb->tail)
goto truncated;
if ((check = *cksum) != 0) {
check = csum_tcpudp_magic(iph->saddr, iph->daddr, 0, 0, ~check);
check = csum_tcpudp_magic(~osaddr, ~odaddr, 0, 0, ~check);
*cksum = check ? : 0xFFFF;
}
break;
case IPPROTO_ICMP:
{
struct icmphdr *icmph = (struct icmphdr*)((char*)iph + (iph->ihl<<2));
struct iphdr *ciph;
u32 idaddr, isaddr;
int updated;
if ((icmph->type != ICMP_DEST_UNREACH) &&
(icmph->type != ICMP_TIME_EXCEEDED) &&
(icmph->type != ICMP_PARAMETERPROB))
break;
ciph = (struct iphdr *) (icmph + 1);
if ((u8*)(ciph+1) > skb->tail)
goto truncated;
isaddr = ciph->saddr;
idaddr = ciph->daddr;
updated = 0;
if (rt->rt_flags&RTCF_DNAT && ciph->saddr == odaddr) {
ciph->saddr = iph->daddr;
updated = 1;
}
if (rt->rt_flags&RTCF_SNAT) {
if (ciph->daddr != osaddr) {
struct fib_result res;
struct rt_key key;
unsigned flags = 0;
key.src = ciph->daddr;
key.dst = ciph->saddr;
key.iif = skb->dev->ifindex;
key.oif = 0;
#ifdef CONFIG_IP_ROUTE_TOS
key.tos = RT_TOS(ciph->tos);
#endif
#ifdef CONFIG_IP_ROUTE_FWMARK
key.fwmark = 0;
#endif
/* Use fib_lookup() until we get our own
* hash table of NATed hosts -- Rani
*/
if (fib_lookup(&key, &res) == 0) {
if (res.r) {
ciph->daddr = fib_rules_policy(ciph->daddr, &res, &flags);
if (ciph->daddr != idaddr)
updated = 1;
}
fib_res_put(&res);
}
} else {
ciph->daddr = iph->saddr;
updated = 1;
}
}
if (updated) {
cksum = &icmph->checksum;
/* Using tcpudp primitive. Why not? */
check = csum_tcpudp_magic(ciph->saddr, ciph->daddr, 0, 0, ~(*cksum));
*cksum = csum_tcpudp_magic(~isaddr, ~idaddr, 0, 0, ~check);
}
break;
}
default:
break;
}
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, const u8 protocol)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *inner_iph;
struct flowi4 fl4;
u8 tos, ttl;
__be16 df;
struct rtable *rt; /* Route to the other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
int err;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
if (skb_dst(skb) == NULL) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, inner_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
const struct in6_addr *addr6;
struct neighbour *neigh;
bool do_tx_error_icmp;
int addr_type;
neigh = dst_neigh_lookup(skb_dst(skb),
&ipv6_hdr(skb)->daddr);
if (neigh == NULL)
goto tx_error;
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
do_tx_error_icmp = true;
else {
do_tx_error_icmp = false;
dst = addr6->s6_addr32[3];
}
neigh_release(neigh);
if (do_tx_error_icmp)
goto tx_error_icmp;
}
#endif
else
goto tx_error;
}
tos = tnl_params->tos;
if (tos & 0x1) {
tos &= ~0x1;
if (skb->protocol == htons(ETH_P_IP))
tos = inner_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
}
rt = ip_route_output_tunnel(tunnel->net, &fl4,
protocol,
dst, tnl_params->saddr,
tunnel->parms.o_key,
RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
if (rt->dst.dev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->net != dev_net(dev))
skb_scrub_packet(skb);
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
ttl = tnl_params->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
#endif
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
df = tnl_params->frag_off;
if (skb->protocol == htons(ETH_P_IP))
df |= (inner_iph->frag_off&htons(IP_DF));
max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
+ rt->dst.header_len;
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return;
}
err = iptunnel_xmit(dev_net(dev), rt, skb,
fl4.saddr, fl4.daddr, protocol,
tos, ttl, df);
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
return;
#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
#endif
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
}
static int ipip_tunnel_xmit(struct sk_buff *skb, struct device *dev)
{
struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv;
struct net_device_stats *stats = &tunnel->stat;
struct iphdr *tiph = &tunnel->parms.iph;
u8 tos = tunnel->parms.iph.tos;
u16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
struct device *tdev; /* Device to other host */
struct iphdr *old_iph = skb->nh.iph;
struct iphdr *iph; /* Our new IP header */
int max_headroom; /* The extra header space needed */
u32 dst = tiph->daddr;
int mtu;
if (tunnel->recursion++) {
tunnel->stat.collisions++;
goto tx_error;
}
if (skb->protocol != __constant_htons(ETH_P_IP))
goto tx_error;
if (tos&1)
tos = old_iph->tos;
if (!dst) {
/* NBMA tunnel */
if ((rt = (struct rtable*)skb->dst) == NULL) {
tunnel->stat.tx_fifo_errors++;
goto tx_error;
}
if ((dst = rt->rt_gateway) == 0)
goto tx_error_icmp;
}
if (ip_route_output(&rt, dst, tiph->saddr, RT_TOS(tos), tunnel->parms.link)) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
tunnel->stat.collisions++;
goto tx_error;
}
mtu = rt->u.dst.pmtu - sizeof(struct iphdr);
if (mtu < 68) {
tunnel->stat.collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (skb->dst && mtu < skb->dst->pmtu)
skb->dst->pmtu = mtu;
df |= (old_iph->frag_off&__constant_htons(IP_DF));
if ((old_iph->frag_off&__constant_htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
skb->h.raw = skb->nh.raw;
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = (((tdev->hard_header_len+15)&~15)+sizeof(struct iphdr));
if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
}
skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
dst_release(skb->dst);
skb->dst = &rt->u.dst;
/*
* Push down and install the IPIP header.
*/
iph = skb->nh.iph;
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = old_iph->ttl;
iph->tot_len = htons(skb->len);
iph->id = htons(ip_id_count++);
ip_send_check(iph);
stats->tx_bytes += skb->len;
stats->tx_packets++;
ip_send(skb);
tunnel->recursion--;
return 0;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
/* This requires some explaining. If DNAT has taken place,
* we will need to fix up the destination Ethernet address.
*
* There are two cases to consider:
* 1. The packet was DNAT'ed to a device in the same bridge
* port group as it was received on. We can still bridge
* the packet.
* 2. The packet was DNAT'ed to a different device, either
* a non-bridged device or another bridge port group.
* The packet will need to be routed.
*
* The correct way of distinguishing between these two cases is to
* call ip_route_input() and to look at skb->dst->dev, which is
* changed to the destination device if ip_route_input() succeeds.
*
* Let's first consider the case that ip_route_input() succeeds:
*
* If the output device equals the logical bridge device the packet
* came in on, we can consider this bridging. The corresponding MAC
* address will be obtained in br_nf_pre_routing_finish_bridge.
* Otherwise, the packet is considered to be routed and we just
* change the destination MAC address so that the packet will
* later be passed up to the IP stack to be routed. For a redirected
* packet, ip_route_input() will give back the localhost as output device,
* which differs from the bridge device.
*
* Let's now consider the case that ip_route_input() fails:
*
* This can be because the destination address is martian, in which case
* the packet will be dropped.
* If IP forwarding is disabled, ip_route_input() will fail, while
* ip_route_output_key() can return success. The source
* address for ip_route_output_key() is set to zero, so ip_route_output_key()
* thinks we're handling a locally generated packet and won't care
* if IP forwarding is enabled. If the output device equals the logical bridge
* device, we proceed as if ip_route_input() succeeded. If it differs from the
* logical bridge port or if ip_route_output_key() fails we drop the packet.
*/
static int br_nf_pre_routing_finish(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct iphdr *iph = ip_hdr(skb);
struct nf_bridge_info *nf_bridge = skb->nf_bridge;
struct rtable *rt;
int err;
if (nf_bridge->mask & BRNF_PKT_TYPE) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->mask ^= BRNF_PKT_TYPE;
}
nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
if (dnat_took_place(skb)) {
if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
/* If err equals -EHOSTUNREACH the error is due to a
* martian destination or due to the fact that
* forwarding is disabled. For most martian packets,
* ip_route_output_key() will fail. It won't fail for 2 types of
* martian destinations: loopback destinations and destination
* 0.0.0.0. In both cases the packet will be dropped because the
* destination is the loopback device and not the bridge. */
if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
goto free_skb;
rt = ip_route_output(dev_net(dev), iph->daddr, 0,
RT_TOS(iph->tos), 0);
if (!IS_ERR(rt)) {
/* - Bridged-and-DNAT'ed traffic doesn't
* require ip_forwarding. */
if (rt->dst.dev == dev) {
skb_dst_set(skb, &rt->dst);
goto bridged_dnat;
}
ip_rt_put(rt);
}
free_skb:
kfree_skb(skb);
return 0;
} else {
if (skb_dst(skb)->dev == dev) {
bridged_dnat:
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
NF_HOOK_THRESH(NFPROTO_BRIDGE,
NF_BR_PRE_ROUTING,
skb, skb->dev, NULL,
br_nf_pre_routing_finish_bridge,
1);
return 0;
}
memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN);
skb->pkt_type = PACKET_HOST;
}
} else {
rt = bridge_parent_rtable(nf_bridge->physindev);
if (!rt) {
kfree_skb(skb);
return 0;
}
skb_dst_set_noref(skb, &rt->dst);
}
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
br_handle_frame_finish, 1);
return 0;
}
void ipip_err(struct sk_buff *skb, unsigned char *dp, int len)
{
#ifndef I_WISH_WORLD_WERE_PERFECT
/* It is not :-( All the routers (except for Linux) return only
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
*/
struct iphdr *iph = (struct iphdr*)dp;
int type = skb->h.icmph->type;
int code = skb->h.icmph->code;
struct ip_tunnel *t;
if (len < sizeof(struct iphdr))
return;
switch (type) {
default:
case ICMP_PARAMETERPROB:
return;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
case ICMP_FRAG_NEEDED:
/* Soft state for pmtu is maintained by IP core. */
return;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe they are just ether pollution. --ANK
*/
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return;
break;
}
t = ipip_tunnel_lookup(iph->daddr, iph->saddr);
if (t == NULL || t->parms.iph.daddr == 0)
return;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
return;
if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
return;
#else
struct iphdr *iph = (struct iphdr*)dp;
int hlen = iph->ihl<<2;
struct iphdr *eiph;
int type = skb->h.icmph->type;
int code = skb->h.icmph->code;
int rel_type = 0;
int rel_code = 0;
int rel_info = 0;
struct sk_buff *skb2;
struct rtable *rt;
if (len < hlen + sizeof(struct iphdr))
return;
eiph = (struct iphdr*)(dp + hlen);
switch (type) {
default:
return;
case ICMP_PARAMETERPROB:
if (skb->h.icmph->un.gateway < hlen)
return;
/* So... This guy found something strange INSIDE encapsulated
packet. Well, he is fool, but what can we do ?
*/
rel_type = ICMP_PARAMETERPROB;
rel_info = skb->h.icmph->un.gateway - hlen;
break;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
case ICMP_FRAG_NEEDED:
/* And it is the only really necessary thing :-) */
rel_info = ntohs(skb->h.icmph->un.frag.mtu);
if (rel_info < hlen+68)
return;
rel_info -= hlen;
/* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */
if (rel_info > ntohs(eiph->tot_len))
return;
break;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe, it is just ether pollution. --ANK
*/
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return;
break;
}
/* Prepare fake skb to feed it to icmp_send */
skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 == NULL)
return;
dst_release(skb2->dst);
skb2->dst = NULL;
skb_pull(skb2, skb->data - (u8*)eiph);
skb2->nh.raw = skb2->data;
/* Try to guess incoming interface */
if (ip_route_output(&rt, eiph->saddr, 0, RT_TOS(eiph->tos), 0)) {
kfree_skb(skb2);
return;
}
skb2->dev = rt->u.dst.dev;
/* route "incoming" packet */
if (rt->rt_flags&RTCF_LOCAL) {
ip_rt_put(rt);
rt = NULL;
if (ip_route_output(&rt, eiph->daddr, eiph->saddr, eiph->tos, 0) ||
rt->u.dst.dev->type != ARPHRD_IPGRE) {
ip_rt_put(rt);
kfree_skb(skb2);
return;
}
} else {
ip_rt_put(rt);
if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) ||
skb2->dst->dev->type != ARPHRD_IPGRE) {
kfree_skb(skb2);
return;
}
}
/* change mtu on this route */
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
if (rel_info > skb2->dst->pmtu) {
kfree_skb(skb2);
return;
}
skb2->dst->pmtu = rel_info;
rel_info = htonl(rel_info);
} else if (type == ICMP_TIME_EXCEEDED) {
struct ip_tunnel *t = (struct ip_tunnel*)skb2->dev->priv;
if (t->parms.iph.ttl) {
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
}
}
icmp_send(skb2, rel_type, rel_code, rel_info);
kfree_skb(skb2);
return;
#endif
}
/*
* Create syn packet and send it to rs.
* ATTENTION: we also store syn skb in cp if syn retransimition
* is tured on.
*/
static int
syn_proxy_send_rs_syn(int af, const struct tcphdr *th,
struct ip_vs_conn *cp, struct sk_buff *skb,
struct ip_vs_protocol *pp, struct ip_vs_synproxy_opt *opt)
{
struct sk_buff *syn_skb;
int tcp_hdr_size;
__u8 tcp_flags = TCPCB_FLAG_SYN;
unsigned int tcphoff;
struct tcphdr *new_th;
if (!cp->packet_xmit) {
IP_VS_ERR_RL("warning: packet_xmit is null");
return 0;
}
syn_skb = alloc_skb(MAX_TCP_HEADER + 15, GFP_ATOMIC);
if (unlikely(syn_skb == NULL)) {
IP_VS_ERR_RL("alloc skb failed when send rs syn packet\n");
return 0;
}
/* Reserve space for headers */
skb_reserve(syn_skb, MAX_TCP_HEADER);
tcp_hdr_size = (sizeof(struct tcphdr) + TCPOLEN_MSS +
(opt->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) +
(opt->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) +
/* SACK_PERM is in the place of NOP NOP of TS */
((opt->sack_ok
&& !opt->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0));
new_th = (struct tcphdr *)skb_push(syn_skb, tcp_hdr_size);
/* Compose tcp header */
skb_reset_transport_header(syn_skb);
syn_skb->csum = 0;
/* Set tcp hdr */
new_th->source = th->source;
new_th->dest = th->dest;
new_th->seq = htonl(ntohl(th->seq) - 1);
new_th->ack_seq = 0;
*(((__u16 *) new_th) + 6) =
htons(((tcp_hdr_size >> 2) << 12) | tcp_flags);
/* FIX_ME: what window should we use */
new_th->window = htons(5000);
new_th->check = 0;
new_th->urg_ptr = 0;
new_th->urg = 0;
new_th->ece = 0;
new_th->cwr = 0;
syn_proxy_syn_build_options((__be32 *) (new_th + 1), opt);
/*
* Set ip hdr
* Attention: set source and dest addr to ack skb's.
* we rely on packet_xmit func to do NATs thing.
*/
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
struct ipv6hdr *ack_iph = ipv6_hdr(skb);
struct ipv6hdr *iph =
(struct ipv6hdr *)skb_push(syn_skb, sizeof(struct ipv6hdr));
tcphoff = sizeof(struct ipv6hdr);
skb_reset_network_header(syn_skb);
memcpy(&iph->saddr, &ack_iph->saddr, sizeof(struct in6_addr));
memcpy(&iph->daddr, &ack_iph->daddr, sizeof(struct in6_addr));
iph->version = 6;
iph->nexthdr = NEXTHDR_TCP;
iph->payload_len = htons(tcp_hdr_size);
iph->hop_limit = IPV6_DEFAULT_HOPLIMIT;
new_th->check = 0;
syn_skb->csum =
skb_checksum(syn_skb, tcphoff, syn_skb->len - tcphoff, 0);
new_th->check =
csum_ipv6_magic(&iph->saddr, &iph->daddr,
syn_skb->len - tcphoff, IPPROTO_TCP,
syn_skb->csum);
} else
#endif
{
struct iphdr *ack_iph = ip_hdr(skb);
u32 rtos = RT_TOS(ack_iph->tos);
struct iphdr *iph =
(struct iphdr *)skb_push(syn_skb, sizeof(struct iphdr));
tcphoff = sizeof(struct iphdr);
skb_reset_network_header(syn_skb);
*((__u16 *) iph) = htons((4 << 12) | (5 << 8) | (rtos & 0xff));
iph->tot_len = htons(syn_skb->len);
iph->frag_off = htons(IP_DF);
/* FIX_ME: what ttl shoule we use */
iph->ttl = IPDEFTTL;
iph->protocol = IPPROTO_TCP;
iph->saddr = ack_iph->saddr;
iph->daddr = ack_iph->daddr;
ip_send_check(iph);
new_th->check = 0;
syn_skb->csum =
skb_checksum(syn_skb, tcphoff, syn_skb->len - tcphoff, 0);
new_th->check =
csum_tcpudp_magic(iph->saddr, iph->daddr,
syn_skb->len - tcphoff, IPPROTO_TCP,
syn_skb->csum);
}
/* Save syn_skb if syn retransmission is on */
if (sysctl_ip_vs_synproxy_syn_retry > 0) {
cp->syn_skb = skb_copy(syn_skb, GFP_ATOMIC);
atomic_set(&cp->syn_retry_max, sysctl_ip_vs_synproxy_syn_retry);
}
/* Save info for fast_response_xmit */
if(sysctl_ip_vs_fast_xmit && skb->dev &&
likely(skb->dev->type == ARPHRD_ETHER) &&
skb_mac_header_was_set(skb)) {
struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb);
if(likely(cp->indev == NULL)) {
cp->indev = skb->dev;
dev_hold(cp->indev);
}
if (unlikely(cp->indev != skb->dev)) {
dev_put(cp->indev);
cp->indev = skb->dev;
dev_hold(cp->indev);
}
memcpy(cp->src_hwaddr, eth->h_source, ETH_ALEN);
memcpy(cp->dst_hwaddr, eth->h_dest, ETH_ALEN);
IP_VS_INC_ESTATS(ip_vs_esmib, FAST_XMIT_SYNPROXY_SAVE);
IP_VS_DBG_RL("syn_proxy_send_rs_syn netdevice:%s\n",
netdev_name(skb->dev));
}
/* count in the syn packet */
ip_vs_in_stats(cp, skb);
/* If xmit failed, syn_skb will be freed correctly. */
cp->packet_xmit(syn_skb, cp, pp);
return 1;
}
static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
{
struct sock *sk = (struct sock *) chan->private;
struct pppox_sock *po = pppox_sk(sk);
struct pptp_opt *opt=&po->proto.pptp;
struct pptp_gre_header *hdr;
unsigned int header_len=sizeof(*hdr);
int len=skb?skb->len:0;
int err=0;
int window;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
int max_headroom; /* The extra header space needed */
INC_TX_PACKETS;
spin_lock_bh(&opt->xmit_lock);
window=WRAPPED(opt->ack_recv,opt->seq_sent)?(__u32)0xffffffff-opt->seq_sent+opt->ack_recv:opt->seq_sent-opt->ack_recv;
if (!skb){
if (opt->ack_sent == opt->seq_recv) goto exit;
}else if (window>opt->window){
__set_bit(PPTP_FLAG_PAUSE,(unsigned long*)&opt->flags);
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
mod_timer(&opt->ack_timeout_timer,opt->stat->rtt/100*HZ/10000);
#else
schedule_delayed_work(&opt->ack_timeout_work,opt->stat->rtt/100*HZ/10000);
#endif
goto exit;
}
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
{
struct rt_key key = {
.dst=opt->dst_addr.sin_addr.s_addr,
.src=opt->src_addr.sin_addr.s_addr,
.tos=RT_TOS(0),
};
if ((err=ip_route_output_key(&rt, &key))) {
goto tx_error;
}
}
#else
{
struct flowi fl = { .oif = 0,
.nl_u = { .ip4_u =
{ .daddr = opt->dst_addr.sin_addr.s_addr,
.saddr = opt->src_addr.sin_addr.s_addr,
.tos = RT_TOS(0) } },
.proto = IPPROTO_GRE };
if ((err=ip_route_output_key(&rt, &fl))) {
goto tx_error;
}
}
#endif
tdev = rt->u.dst.dev;
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
max_headroom = ((tdev->hard_header_len+15)&~15) + sizeof(*iph)+sizeof(*hdr)+2;
#else
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(*iph)+sizeof(*hdr)+2;
#endif
if (!skb){
skb=dev_alloc_skb(max_headroom);
if (!skb) {
ip_rt_put(rt);
goto tx_error;
}
skb_reserve(skb,max_headroom-skb_headroom(skb));
}else if (skb_headroom(skb) < max_headroom ||
skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
goto tx_error;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
kfree_skb(skb);
skb = new_skb;
}
if (skb->len){
int islcp;
unsigned char *data=skb->data;
islcp=((data[0] << 8) + data[1])== PPP_LCP && 1 <= data[2] && data[2] <= 7;
/* compress protocol field */
if ((opt->ppp_flags & SC_COMP_PROT) && data[0]==0 && !islcp)
skb_pull(skb,1);
/*
* Put in the address/control bytes if necessary
*/
if ((opt->ppp_flags & SC_COMP_AC) == 0 || islcp) {
data=skb_push(skb,2);
data[0]=0xff;
data[1]=0x03;
}
}
len=skb->len;
if (len==0) header_len-=sizeof(hdr->seq);
if (opt->ack_sent == opt->seq_recv) header_len-=sizeof(hdr->ack);
// Push down and install GRE header
skb_push(skb,header_len);
hdr=(struct pptp_gre_header *)(skb->data);
hdr->flags = PPTP_GRE_FLAG_K;
hdr->ver = PPTP_GRE_VER;
hdr->protocol = htons(PPTP_GRE_PROTO);
hdr->call_id = htons(opt->dst_addr.call_id);
if (!len){
hdr->payload_len = 0;
hdr->ver |= PPTP_GRE_FLAG_A;
/* ack is in odd place because S == 0 */
hdr->seq = htonl(opt->seq_recv);
opt->ack_sent = opt->seq_recv;
opt->stat->tx_acks++;
}else {
hdr->flags |= PPTP_GRE_FLAG_S;
hdr->seq = htonl(opt->seq_sent++);
if (log_level>=3 && opt->seq_sent<=log_packets)
printk(KERN_INFO"PPTP[%i]: send packet: seq=%i",opt->src_addr.call_id,opt->seq_sent);
if (opt->ack_sent != opt->seq_recv) {
/* send ack with this message */
hdr->ver |= PPTP_GRE_FLAG_A;
hdr->ack = htonl(opt->seq_recv);
opt->ack_sent = opt->seq_recv;
if (log_level>=3 && opt->seq_sent<=log_packets)
printk(" ack=%i",opt->seq_recv);
}
hdr->payload_len = htons(len);
if (log_level>=3 && opt->seq_sent<=log_packets)
printk("\n");
}
/*
* Push down and install the IP header.
*/
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,22)
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(*iph));
skb_reset_network_header(skb);
#else
skb->h.raw = skb->nh.raw;
skb->nh.raw = skb_push(skb, sizeof(*iph));
#endif
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,16)
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
#endif
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,22)
iph = ip_hdr(skb);
#else
iph = skb->nh.iph;
#endif
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = 0;//df;
iph->protocol = IPPROTO_GRE;
iph->tos = 0;
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
iph->ttl = sysctl_ip_default_ttl;
#else
iph->ttl = dst_metric(&rt->u.dst, RTAX_HOPLIMIT);
#endif
iph->tot_len = htons(skb->len);
dst_release(skb->dst);
skb->dst = &rt->u.dst;
nf_reset(skb);
skb->ip_summed = CHECKSUM_NONE;
ip_select_ident(iph, &rt->u.dst, NULL);
ip_send_check(iph);
err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output);
wake_up(&opt->wait);
if (err == NET_XMIT_SUCCESS || err == NET_XMIT_CN) {
opt->stat->tx_sent++;
if (!opt->stat->pt_seq){
opt->stat->pt_seq = opt->seq_sent;
do_gettimeofday(&opt->stat->pt_time);
}
}else{
INC_TX_ERRORS;
opt->stat->tx_failed++;
}
spin_unlock_bh(&opt->xmit_lock);
return 1;
tx_error:
INC_TX_ERRORS;
opt->stat->tx_failed++;
if (!len) kfree_skb(skb);
spin_unlock_bh(&opt->xmit_lock);
return 1;
exit:
spin_unlock_bh(&opt->xmit_lock);
return 0;
}
/* This requires some explaining. If DNAT has taken place,
* we will need to fix up the destination Ethernet address.
* This is also true when SNAT takes place (for the reply direction).
*
* There are two cases to consider:
* 1. The packet was DNAT'ed to a device in the same bridge
* port group as it was received on. We can still bridge
* the packet.
* 2. The packet was DNAT'ed to a different device, either
* a non-bridged device or another bridge port group.
* The packet will need to be routed.
*
* The correct way of distinguishing between these two cases is to
* call ip_route_input() and to look at skb->dst->dev, which is
* changed to the destination device if ip_route_input() succeeds.
*
* Let's first consider the case that ip_route_input() succeeds:
*
* If the output device equals the logical bridge device the packet
* came in on, we can consider this bridging. The corresponding MAC
* address will be obtained in br_nf_pre_routing_finish_bridge.
* Otherwise, the packet is considered to be routed and we just
* change the destination MAC address so that the packet will
* later be passed up to the IP stack to be routed. For a redirected
* packet, ip_route_input() will give back the localhost as output device,
* which differs from the bridge device.
*
* Let's now consider the case that ip_route_input() fails:
*
* This can be because the destination address is martian, in which case
* the packet will be dropped.
* If IP forwarding is disabled, ip_route_input() will fail, while
* ip_route_output_key() can return success. The source
* address for ip_route_output_key() is set to zero, so ip_route_output_key()
* thinks we're handling a locally generated packet and won't care
* if IP forwarding is enabled. If the output device equals the logical bridge
* device, we proceed as if ip_route_input() succeeded. If it differs from the
* logical bridge port or if ip_route_output_key() fails we drop the packet.
*/
static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct iphdr *iph = ip_hdr(skb);
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct rtable *rt;
int err;
nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
if (nf_bridge->pkt_otherhost) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->pkt_otherhost = false;
}
nf_bridge->in_prerouting = 0;
if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
/* If err equals -EHOSTUNREACH the error is due to a
* martian destination or due to the fact that
* forwarding is disabled. For most martian packets,
* ip_route_output_key() will fail. It won't fail for 2 types of
* martian destinations: loopback destinations and destination
* 0.0.0.0. In both cases the packet will be dropped because the
* destination is the loopback device and not the bridge. */
if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
goto free_skb;
rt = ip_route_output(net, iph->daddr, 0,
RT_TOS(iph->tos), 0);
if (!IS_ERR(rt)) {
/* - Bridged-and-DNAT'ed traffic doesn't
* require ip_forwarding. */
if (rt->dst.dev == dev) {
skb_dst_set(skb, &rt->dst);
goto bridged_dnat;
}
ip_rt_put(rt);
}
free_skb:
kfree_skb(skb);
return 0;
} else {
if (skb_dst(skb)->dev == dev) {
bridged_dnat:
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
br_nf_hook_thresh(NF_BR_PRE_ROUTING,
net, sk, skb, skb->dev,
NULL,
br_nf_pre_routing_finish_bridge);
return 0;
}
ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
skb->pkt_type = PACKET_HOST;
}
} else {
rt = bridge_parent_rtable(nf_bridge->physindev);
if (!rt) {
kfree_skb(skb);
return 0;
}
skb_dst_set_noref(skb, &rt->dst);
}
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL,
br_handle_frame_finish);
return 0;
}
static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv;
struct net_device_stats *stats = &tunnel->stat;
struct iphdr *tiph = &tunnel->parms.iph;
struct ipv6hdr *iph6 = skb->nh.ipv6h;
u8 tos = tunnel->parms.iph.tos;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
int max_headroom; /* The extra header space needed */
u32 dst = tiph->daddr;
int mtu;
struct in6_addr *addr6;
int addr_type;
if (tunnel->recursion++) {
tunnel->stat.collisions++;
goto tx_error;
}
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
if (!dst)
dst = try_6to4(&iph6->daddr);
if (!dst) {
struct neighbour *neigh = NULL;
if (skb->dst)
neigh = skb->dst->neighbour;
if (neigh == NULL) {
if (net_ratelimit())
printk(KERN_DEBUG "sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (struct in6_addr*)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &skb->nh.ipv6h->daddr;
addr_type = ipv6_addr_type(addr6);
}
if (addr_type & IPV6_ADDR_COMPATv4)
dst = addr6->s6_addr32[3];
else
#ifdef CONFIG_IPV6_6TO4_NEXTHOP
if (!(dst = try_6to4(addr6)))
#endif
goto tx_error_icmp;
}
if (ip_route_output(&rt, dst, tiph->saddr, RT_TOS(tos), tunnel->parms.link)) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
if (rt->rt_type != RTN_UNICAST) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
tunnel->stat.collisions++;
goto tx_error;
}
if (tiph->frag_off)
mtu = rt->u.dst.pmtu - sizeof(struct iphdr);
else
mtu = skb->dst ? skb->dst->pmtu : dev->mtu;
if (mtu < 68) {
tunnel->stat.collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb->dst && mtu < skb->dst->pmtu) {
struct rt6_info *rt6 = (struct rt6_info*)skb->dst;
if (mtu < rt6->u.dst.pmtu) {
if (tunnel->parms.iph.daddr || rt6->rt6i_dst.plen == 128) {
rt6->rt6i_flags |= RTF_MODIFIED;
rt6->u.dst.pmtu = mtu;
}
}
}
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = (((tdev->hard_header_len+15)&~15)+sizeof(struct iphdr));
if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
iph6 = skb->nh.ipv6h;
}
skb->h.raw = skb->nh.raw;
skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
dst_release(skb->dst);
skb->dst = &rt->u.dst;
/*
* Push down and install the IPIP header.
*/
iph = skb->nh.iph;
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
if (mtu > IPV6_MIN_MTU)
iph->frag_off = htons(IP_DF);
else
iph->frag_off = 0;
iph->protocol = IPPROTO_IPV6;
iph->tos = INET_ECN_encapsulate(tos, ip6_get_dsfield(iph6));
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = iph6->hop_limit;
nf_reset(skb);
IPTUNNEL_XMIT();
tunnel->recursion--;
return 0;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
