/* save tcp sequense for fullnat/nat, INside to OUTside */
static void
tcp_save_out_seq(struct sk_buff *skb, struct ip_vs_conn *cp,
struct tcphdr *th, int ihl)
{
if (unlikely(th == NULL) || unlikely(cp == NULL) ||
unlikely(skb == NULL))
return;
if (sysctl_ip_vs_conn_expire_tcp_rst && !th->rst) {
/* seq out of order. just skip */
if (before(ntohl(th->ack_seq), ntohl(cp->rs_ack_seq)) &&
(cp->rs_ack_seq != 0))
return;
if (th->syn && th->ack)
cp->rs_end_seq = htonl(ntohl(th->seq) + 1);
else
cp->rs_end_seq = htonl(ntohl(th->seq) + skb->len
- ihl - (th->doff << 2));
cp->rs_ack_seq = th->ack_seq;
IP_VS_DBG_RL("packet from RS, seq:%u ack_seq:%u.",
ntohl(th->seq), ntohl(th->ack_seq));
IP_VS_DBG_RL("port:%u->%u", ntohs(th->source), ntohs(th->dest));
}
}
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;
}
}
*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;
}
static struct rtable *
__ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos)
{
struct rtable *rt; /* Route to the other host */
struct ip_vs_dest *dest = cp->dest;
if (dest) {
spin_lock(&dest->dst_lock);
if (!(rt = (struct rtable *)
__ip_vs_dst_check(dest, rtos, 0))) {
struct flowi fl = {
.oif = 0,
.nl_u = {
.ip4_u = {
.daddr = dest->addr.ip,
.saddr = 0,
.tos = rtos, } },
};
if (ip_route_output_key(&init_net, &rt, &fl)) {
spin_unlock(&dest->dst_lock);
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
&dest->addr.ip);
return NULL;
}
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->u.dst));
IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n",
&dest->addr.ip,
atomic_read(&rt->u.dst.__refcnt), rtos);
}
spin_unlock(&dest->dst_lock);
} else {
int
ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rt6_info *rt; /* Route to the other host */
int mtu;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, 1|2)))
goto tx_error_icmp;
if (__ip_vs_is_local_route6(rt)) {
dst_release(&rt->dst);
IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
dst_release(&rt->dst);
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?
*/
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(skb == NULL)) {
dst_release(&rt->dst);
return NF_STOLEN;
}
/* 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_IPV6, 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;
}
/* Get route to daddr, update *saddr, optionally bind route to saddr */
static struct rtable *do_output_route4(struct net *net, __be32 daddr,
int rt_mode, __be32 *saddr)
{
struct flowi4 fl4;
struct rtable *rt;
int loop = 0;
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
FLOWI_FLAG_KNOWN_NH : 0;
retry:
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt)) {
/* Invalid saddr ? */
if (PTR_ERR(rt) == -EINVAL && *saddr &&
rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
*saddr = 0;
flowi4_update_output(&fl4, 0, 0, daddr, 0);
goto retry;
}
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
return NULL;
} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
ip_rt_put(rt);
*saddr = fl4.saddr;
flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr);
loop++;
goto retry;
}
*saddr = fl4.saddr;
return rt;
}
/*
* 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 rtable *
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
__be32 daddr, u32 rtos, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */
int local;
if (dest) {
spin_lock(&dest->dst_lock);
if (!(rt = (struct rtable *)
__ip_vs_dst_check(dest, rtos))) {
struct flowi fl = {
.oif = 0,
.nl_u = {
.ip4_u = {
.daddr = dest->addr.ip,
.saddr = 0,
.tos = rtos, } },
};
if (ip_route_output_key(net, &rt, &fl)) {
spin_unlock(&dest->dst_lock);
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
&dest->addr.ip);
return NULL;
}
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n",
&dest->addr.ip,
atomic_read(&rt->dst.__refcnt), rtos);
}
spin_unlock(&dest->dst_lock);
} else {
/*
* 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),
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);
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu &&
!skb_is_gso(skb)) {
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;
}
/*
* 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;
}
int
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rt6_info *rt; /* Route to the other host */
struct in6_addr saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct ipv6hdr *old_iph = ipv6_hdr(skb);
struct ipv6hdr *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_v6(skb, cp->dest, &cp->daddr.in6,
&saddr, 1, 1|2)))
goto tx_error_icmp;
if (__ip_vs_is_local_route6(rt)) {
dst_release(&rt->dst);
IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
}
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
if (mtu < IPV6_MIN_MTU) {
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
IPV6_MIN_MTU);
goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
!skb_is_gso(skb)) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, 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 ipv6hdr);
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) {
dst_release(&rt->dst);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
}
kfree_skb(skb);
skb = new_skb;
old_iph = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct ipv6hdr));
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 = ipv6_hdr(skb);
iph->version = 6;
iph->nexthdr = IPPROTO_IPV6;
iph->payload_len = old_iph->payload_len;
be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
iph->priority = old_iph->priority;
memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
ipv6_addr_copy(&iph->daddr, &cp->daddr.in6);
ipv6_addr_copy(&iph->saddr, &saddr);
iph->hop_limit = old_iph->hop_limit;
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = IP_VS_XMIT_TUNNEL(skb, cp);
if (ret == NF_ACCEPT)
ip6_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:
dst_release(&rt->dst);
goto tx_error;
}
int
ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset)
{
struct rt6_info *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_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, 1|2|4)))
goto tx_error_icmp;
local = __ip_vs_is_local_route6(rt);
/*
* 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 %pI6\n",
__func__, &cp->daddr.in6);
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
IP_VS_DBG(1, "%s(): "
"stopping DNAT to loopback %pI6\n",
__func__, &cp->daddr.in6);
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu && !skb_is_gso(skb)) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, 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_v6(skb, pp, cp, 0);
if (!local || !skb->dev) {
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
/* destined to loopback, do we need to change route? */
dst_release(&rt->dst);
}
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV6, 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:
dst_release(&rt->dst);
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);
}
/* Get route to destination or remote server */
static struct rtable *
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
__be32 daddr, u32 rtos, int rt_mode, __be32 *ret_saddr)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */
int local;
if (dest) {
spin_lock(&dest->dst_lock);
if (!(rt = (struct rtable *)
__ip_vs_dst_check(dest, rtos))) {
rt = do_output_route4(net, dest->addr.ip, rtos,
rt_mode, &dest->dst_saddr.ip);
if (!rt) {
spin_unlock(&dest->dst_lock);
return NULL;
}
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, "
"rtos=%X\n",
&dest->addr.ip, &dest->dst_saddr.ip,
atomic_read(&rt->dst.__refcnt), rtos);
}
daddr = dest->addr.ip;
if (ret_saddr)
*ret_saddr = dest->dst_saddr.ip;
spin_unlock(&dest->dst_lock);
} else {
__be32 saddr = htonl(INADDR_ANY);
/* For such unconfigured boxes avoid many route lookups
* for performance reasons because we do not remember saddr
*/
rt_mode &= ~IP_VS_RT_MODE_CONNECT;
rt = do_output_route4(net, daddr, rtos, rt_mode, &saddr);
if (!rt)
return NULL;
if (ret_saddr)
*ret_saddr = saddr;
}
local = rt->rt_flags & RTCF_LOCAL;
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
(rt->rt_flags & RTCF_LOCAL) ?
"local":"non-local", &daddr);
ip_rt_put(rt);
return NULL;
}
if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
!((ort = skb_rtable(skb)) && ort->rt_flags & RTCF_LOCAL)) {
IP_VS_DBG_RL("Redirect from non-local address %pI4 to local "
"requires NAT method, dest: %pI4\n",
&ip_hdr(skb)->daddr, &daddr);
ip_rt_put(rt);
return NULL;
}
if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) {
IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 "
"to non-local address, dest: %pI4\n",
&ip_hdr(skb)->saddr, &daddr);
ip_rt_put(rt);
return NULL;
}
return rt;
}
/*
* 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;
}
/*
* 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;
}
/*
* Check if it's for virtual services, look it up,
* and send it on its way...
*/
static unsigned int
ip_vs_in(unsigned int hooknum, struct sk_buff **pskb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *pskb;
struct iphdr *iph;
struct ip_vs_protocol *pp;
struct ip_vs_conn *cp;
int ret, restart;
int ihl;
/*
* Big tappo: only PACKET_HOST (neither loopback nor mcasts)
* ... don't know why 1st test DOES NOT include 2nd (?)
*/
if (unlikely(skb->pkt_type != PACKET_HOST
|| skb->dev == &loopback_dev || skb->sk)) {
IP_VS_DBG(12, "packet type=%d proto=%d daddr=%d.%d.%d.%d ignored\n",
skb->pkt_type,
ip_hdr(skb)->protocol,
NIPQUAD(ip_hdr(skb)->daddr));
return NF_ACCEPT;
}
iph = ip_hdr(skb);
if (unlikely(iph->protocol == IPPROTO_ICMP)) {
int related, verdict = ip_vs_in_icmp(pskb, &related, hooknum);
if (related)
return verdict;
skb = *pskb;
iph = ip_hdr(skb);
}
/* Protocol supported? */
pp = ip_vs_proto_get(iph->protocol);
if (unlikely(!pp))
return NF_ACCEPT;
ihl = iph->ihl << 2;
/*
* Check if the packet belongs to an existing connection entry
*/
cp = pp->conn_in_get(skb, pp, iph, ihl, 0);
if (unlikely(!cp)) {
int v;
if (!pp->conn_schedule(skb, pp, &v, &cp))
return v;
}
if (unlikely(!cp)) {
/* sorry, all this trouble for a no-hit :) */
IP_VS_DBG_PKT(12, pp, skb, 0,
"packet continues traversal as normal");
return NF_ACCEPT;
}
IP_VS_DBG_PKT(11, pp, skb, 0, "Incoming packet");
/* Check the server status */
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
if (sysctl_ip_vs_expire_nodest_conn) {
/* try to expire the connection immediately */
ip_vs_conn_expire_now(cp);
}
/* don't restart its timer, and silently
drop the packet. */
__ip_vs_conn_put(cp);
return NF_DROP;
}
ip_vs_in_stats(cp, skb);
restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
if (cp->packet_xmit)
ret = cp->packet_xmit(skb, cp, pp);
/* do not touch skb anymore */
else {
IP_VS_DBG_RL("warning: packet_xmit is null");
ret = NF_ACCEPT;
}
/* increase its packet counter and check if it is needed
to be synchronized */
atomic_inc(&cp->in_pkts);
if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
(cp->protocol != IPPROTO_TCP ||
cp->state == IP_VS_TCP_S_ESTABLISHED) &&
(atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1]
== sysctl_ip_vs_sync_threshold[0]))
ip_vs_sync_conn(cp);
ip_vs_conn_put(cp);
return ret;
}
/*
* It is hooked at the NF_IP_FORWARD chain, used only for VS/NAT.
* Check if outgoing packet belongs to the established ip_vs_conn,
* rewrite addresses of the packet and send it on its way...
*/
static unsigned int ip_vs_out(unsigned int hooknum,
struct sk_buff **skb_p,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *skb_p;
struct iphdr *iph;
union ip_vs_tphdr h;
struct ip_vs_conn *cp;
int size;
int ihl;
EnterFunction(11);
if (skb->nfcache & NFC_IPVS_PROPERTY)
return NF_ACCEPT;
iph = skb->nh.iph;
if (iph->protocol == IPPROTO_ICMP)
return ip_vs_out_icmp(skb_p);
/* let it go if other IP protocols */
if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)
return NF_ACCEPT;
/* reassemble IP fragments */
if (iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) {
skb = ip_defrag(skb, IP_DEFRAG_VS_OUT);
if (!skb)
return NF_STOLEN;
iph = skb->nh.iph;
*skb_p = skb;
}
/* make sure that protocol header available in skb data area,
note that skb data area may be reallocated. */
ihl = iph->ihl << 2;
if (ip_vs_header_check(skb, iph->protocol, ihl) == -1)
return NF_DROP;
iph = skb->nh.iph;
h.raw = (char*) iph + ihl;
/*
* Check if the packet belongs to an old entry
*/
cp = ip_vs_conn_out_get(iph->protocol, iph->saddr, h.portp[0],
iph->daddr, h.portp[1]);
if (!cp) {
if (sysctl_ip_vs_nat_icmp_send &&
ip_vs_lookup_real_service(iph->protocol,
iph->saddr, h.portp[0])) {
/*
* Notify the real server: there is no existing
* entry if it is not RST packet or not TCP packet.
*/
if (!h.th->rst || iph->protocol != IPPROTO_TCP) {
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PORT_UNREACH, 0);
kfree_skb(skb);
return NF_STOLEN;
}
}
IP_VS_DBG(12, "packet for %s %d.%d.%d.%d:%d "
"continue traversal as normal.\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->daddr),
ntohs(h.portp[1]));
if (skb_is_nonlinear(skb))
ip_send_check(iph);
return NF_ACCEPT;
}
/*
* If it has ip_vs_app helper, the helper may change the payload,
* so it needs full checksum checking and checksum calculation.
* If not, only the header (addr/port) is changed, so it is fast
* to do incremental checksum update, and let the destination host
* do final checksum checking.
*/
if (cp->app && skb_is_nonlinear(skb)) {
if (skb_linearize(skb, GFP_ATOMIC) != 0) {
ip_vs_conn_put(cp);
return NF_DROP;
}
iph = skb->nh.iph;
h.raw = (char*) iph + ihl;
}
size = skb->len - ihl;
IP_VS_DBG(11, "O-pkt: %s size=%d\n",
ip_vs_proto_name(iph->protocol), size);
/* do TCP/UDP checksum checking if it has application helper */
if (cp->app && (iph->protocol != IPPROTO_UDP || h.uh->check != 0)) {
switch (skb->ip_summed) {
case CHECKSUM_NONE:
skb->csum = csum_partial(h.raw, size, 0);
case CHECKSUM_HW:
if (csum_tcpudp_magic(iph->saddr, iph->daddr, size,
iph->protocol, skb->csum)) {
ip_vs_conn_put(cp);
IP_VS_DBG_RL("Outgoing failed %s checksum "
"from %d.%d.%d.%d (size=%d)!\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->saddr),
size);
return NF_DROP;
}
break;
default:
/* CHECKSUM_UNNECESSARY */
break;
}
}
IP_VS_DBG(11, "Outgoing %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->saddr), ntohs(h.portp[0]),
NIPQUAD(iph->daddr), ntohs(h.portp[1]));
/* mangle the packet */
iph->saddr = cp->vaddr;
h.portp[0] = cp->vport;
/*
* Call application helper if needed
*/
if (ip_vs_app_pkt_out(cp, skb) != 0) {
/* skb data has probably changed, update pointers */
iph = skb->nh.iph;
h.raw = (char*)iph + ihl;
size = skb->len - ihl;
}
/*
* Adjust TCP/UDP checksums
*/
if (!cp->app && (iph->protocol != IPPROTO_UDP || h.uh->check != 0)) {
/* Only port and addr are changed, do fast csum update */
ip_vs_fast_check_update(&h, cp->daddr, cp->vaddr,
cp->dport, cp->vport, iph->protocol);
if (skb->ip_summed == CHECKSUM_HW)
skb->ip_summed = CHECKSUM_NONE;
} else {
/* full checksum calculation */
switch (iph->protocol) {
case IPPROTO_TCP:
h.th->check = 0;
skb->csum = csum_partial(h.raw, size, 0);
h.th->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
size, iph->protocol,
skb->csum);
IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%d)\n",
ip_vs_proto_name(iph->protocol), h.th->check,
(char*)&(h.th->check) - (char*)h.raw);
break;
case IPPROTO_UDP:
h.uh->check = 0;
skb->csum = csum_partial(h.raw, size, 0);
h.uh->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
size, iph->protocol,
skb->csum);
if (h.uh->check == 0)
h.uh->check = 0xFFFF;
IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%d)\n",
ip_vs_proto_name(iph->protocol), h.uh->check,
(char*)&(h.uh->check) - (char*)h.raw);
break;
}
}
ip_send_check(iph);
ip_vs_out_stats(cp, skb);
ip_vs_set_state(cp, VS_STATE_OUTPUT, iph, h.portp);
ip_vs_conn_put(cp);
skb->nfcache |= NFC_IPVS_PROPERTY;
LeaveFunction(11);
return NF_ACCEPT;
}
/*
* Check if it's for virtual services, look it up,
* and send it on its way...
*/
static unsigned int ip_vs_in(unsigned int hooknum,
struct sk_buff **skb_p,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *skb_p;
struct iphdr *iph = skb->nh.iph;
union ip_vs_tphdr h;
struct ip_vs_conn *cp;
struct ip_vs_service *svc;
int ihl;
int ret;
/*
* Big tappo: only PACKET_HOST (nor loopback neither mcasts)
* ... don't know why 1st test DOES NOT include 2nd (?)
*/
if (skb->pkt_type != PACKET_HOST || skb->dev == &loopback_dev) {
IP_VS_DBG(12, "packet type=%d proto=%d daddr=%d.%d.%d.%d ignored\n",
skb->pkt_type,
iph->protocol,
NIPQUAD(iph->daddr));
return NF_ACCEPT;
}
if (iph->protocol == IPPROTO_ICMP)
return ip_vs_in_icmp(skb_p);
/* let it go if other IP protocols */
if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)
return NF_ACCEPT;
/* make sure that protocol header available in skb data area,
note that skb data area may be reallocated. */
ihl = iph->ihl << 2;
if (ip_vs_header_check(skb, iph->protocol, ihl) == -1)
return NF_DROP;
iph = skb->nh.iph;
h.raw = (char*) iph + ihl;
/*
* Check if the packet belongs to an existing connection entry
*/
cp = ip_vs_conn_in_get(iph->protocol, iph->saddr, h.portp[0],
iph->daddr, h.portp[1]);
if (!cp &&
(h.th->syn || (iph->protocol!=IPPROTO_TCP)) &&
(svc = ip_vs_service_get(skb->nfmark, iph->protocol,
iph->daddr, h.portp[1]))) {
if (ip_vs_todrop()) {
/*
* It seems that we are very loaded.
* We have to drop this packet :(
*/
ip_vs_service_put(svc);
return NF_DROP;
}
/*
* Let the virtual server select a real server for the
* incoming connection, and create a connection entry.
*/
cp = ip_vs_schedule(svc, iph);
if (!cp)
return ip_vs_leave(svc, skb);
ip_vs_conn_stats(cp, svc);
ip_vs_service_put(svc);
}
if (!cp) {
/* sorry, all this trouble for a no-hit :) */
IP_VS_DBG(12, "packet for %s %d.%d.%d.%d:%d continue "
"traversal as normal.\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->daddr),
ntohs(h.portp[1]));
return NF_ACCEPT;
}
IP_VS_DBG(11, "Incoming %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d\n",
ip_vs_proto_name(iph->protocol),
NIPQUAD(iph->saddr), ntohs(h.portp[0]),
NIPQUAD(iph->daddr), ntohs(h.portp[1]));
/* Check the server status */
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
if (sysctl_ip_vs_expire_nodest_conn) {
/* try to expire the connection immediately */
ip_vs_conn_expire_now(cp);
} else {
/* don't restart its timer, and silently
drop the packet. */
__ip_vs_conn_put(cp);
}
return NF_DROP;
}
ip_vs_in_stats(cp, skb);
ip_vs_set_state(cp, VS_STATE_INPUT, iph, h.portp);
if (cp->packet_xmit)
ret = cp->packet_xmit(skb, cp);
else {
IP_VS_DBG_RL("warning: packet_xmit is null");
ret = NF_ACCEPT;
}
/* increase its packet counter and check if it is needed
to be synchronized */
atomic_inc(&cp->in_pkts);
if (ip_vs_sync_state & IP_VS_STATE_MASTER &&
(cp->protocol != IPPROTO_TCP ||
cp->state == IP_VS_S_ESTABLISHED) &&
(atomic_read(&cp->in_pkts) % 50 == sysctl_ip_vs_sync_threshold))
ip_vs_sync_conn(cp);
ip_vs_conn_put(cp);
return ret;
}
/*
* Handle ICMP messages in the outside-to-inside direction (incoming)
* and sometimes in outgoing direction from ip_vs_forward_icmp.
* Find any that might be relevant, check against existing connections,
* forward to the right destination host if relevant.
* Currently handles error types - unreachable, quench, ttl exceeded.
*/
static int ip_vs_in_icmp(struct sk_buff **skb_p)
{
struct sk_buff *skb = *skb_p;
struct iphdr *iph;
struct icmphdr *icmph;
struct iphdr *ciph; /* The ip header contained within the ICMP */
__u16 *pptr; /* port numbers from TCP/UDP contained header */
unsigned short len;
unsigned short clen, csize;
struct ip_vs_conn *cp;
struct rtable *rt; /* Route to the other host */
int mtu;
if (skb_is_nonlinear(skb)) {
if (skb_linearize(skb, GFP_ATOMIC) != 0)
return NF_DROP;
}
iph = skb->nh.iph;
ip_send_check(iph);
icmph = (struct icmphdr *)((char *)iph + (iph->ihl << 2));
len = ntohs(iph->tot_len) - (iph->ihl<<2);
if (len < sizeof(struct icmphdr))
return NF_DROP;
IP_VS_DBG(12, "icmp in (%d,%d) %u.%u.%u.%u -> %u.%u.%u.%u\n",
icmph->type, ntohs(icmp_id(icmph)),
NIPQUAD(iph->saddr), NIPQUAD(iph->daddr));
if ((icmph->type != ICMP_DEST_UNREACH) &&
(icmph->type != ICMP_SOURCE_QUENCH) &&
(icmph->type != ICMP_TIME_EXCEEDED))
return NF_ACCEPT;
/*
* If we get here we have an ICMP error of one of the above 3 types
* Now find the contained IP header
*/
clen = len - sizeof(struct icmphdr);
if (clen < sizeof(struct iphdr))
return NF_DROP;
ciph = (struct iphdr *) (icmph + 1);
csize = ciph->ihl << 2;
if (clen < csize)
return NF_DROP;
/* We are only interested ICMPs generated from TCP or UDP packets */
if (ciph->protocol != IPPROTO_UDP && ciph->protocol != IPPROTO_TCP)
return NF_ACCEPT;
/* Skip non-first embedded TCP/UDP fragments */
if (ciph->frag_off & __constant_htons(IP_OFFSET))
return NF_ACCEPT;
/* We need at least TCP/UDP ports here */
if (clen < csize + sizeof(struct udphdr))
return NF_DROP;
/* Ensure the checksum is correct */
if (ip_compute_csum((unsigned char *) icmph, len)) {
/* Failed checksum! */
IP_VS_ERR_RL("incoming ICMP: failed checksum from "
"%d.%d.%d.%d!\n", NIPQUAD(iph->saddr));
return NF_DROP;
}
pptr = (__u16 *)&(((char *)ciph)[csize]);
IP_VS_DBG(11, "Handling incoming ICMP for "
"%u.%u.%u.%u:%d -> %u.%u.%u.%u:%d\n",
NIPQUAD(ciph->saddr), ntohs(pptr[0]),
NIPQUAD(ciph->daddr), ntohs(pptr[1]));
/* This is pretty much what ip_vs_conn_in_get() does,
except parameters are in the reverse order */
cp = ip_vs_conn_in_get(ciph->protocol,
ciph->daddr, pptr[1],
ciph->saddr, pptr[0]);
if (cp == NULL)
return NF_ACCEPT;
ip_vs_in_stats(cp, skb);
/* 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) {
int ret;
if (cp->packet_xmit)
ret = cp->packet_xmit(skb, cp);
else
ret = NF_ACCEPT;
atomic_inc(&cp->in_pkts);
ip_vs_conn_put(cp);
return ret;
}
/*
* mangle and send the packet here
*/
if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(iph->tos))))
goto tx_error_icmp;
/* MTU checking */
mtu = rt->u.dst.pmtu;
if ((skb->len > mtu) && (iph->frag_off&__constant_htons(IP_DF))) {
ip_rt_put(rt);
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("ip_vs_in_icmp(): frag needed\n");
goto tx_error;
}
/* drop old route */
dst_release(skb->dst);
skb->dst = &rt->u.dst;
/* copy-on-write the packet before mangling it */
if (ip_vs_skb_cow(skb, rt->u.dst.dev->hard_header_len,
&iph, (unsigned char**)&icmph)) {
ip_vs_conn_put(cp);
return NF_DROP;
}
ciph = (struct iphdr *) (icmph + 1);
pptr = (__u16 *)&(((char *)ciph)[csize]);
/* The ICMP packet for VS/NAT must be written to correct addresses
before being forwarded to the right server */
/* First change the dest IP address, and recalc checksum */
iph->daddr = cp->daddr;
ip_send_check(iph);
/* Now change the *source* address in the contained IP */
ciph->saddr = cp->daddr;
ip_send_check(ciph);
/* the TCP/UDP source port - cannot redo check */
pptr[0] = cp->dport;
/* And finally the ICMP checksum */
icmph->checksum = 0;
icmph->checksum = ip_compute_csum((unsigned char *) icmph, len);
skb->ip_summed = CHECKSUM_UNNECESSARY;
IP_VS_DBG(11, "Forwarding incoming ICMP to "
"%u.%u.%u.%u:%d -> %u.%u.%u.%u:%d\n",
NIPQUAD(ciph->saddr), ntohs(pptr[0]),
NIPQUAD(ciph->daddr), ntohs(pptr[1]));
#ifdef CONFIG_NETFILTER_DEBUG
skb->nf_debug = 1 << NF_IP_LOCAL_OUT;
#endif /* CONFIG_NETFILTER_DEBUG */
ip_send(skb);
ip_vs_conn_put(cp);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev_kfree_skb(skb);
ip_vs_conn_put(cp);
return NF_STOLEN;
}
/* Get route to destination or remote server */
static int
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
__be32 daddr, int rt_mode, __be32 *ret_saddr)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_dest_dst *dest_dst;
struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */
struct iphdr *iph;
__be16 df;
int mtu;
int local, noref = 1;
if (dest) {
dest_dst = __ip_vs_dst_check(dest);
if (likely(dest_dst))
rt = (struct rtable *) dest_dst->dst_cache;
else {
dest_dst = ip_vs_dest_dst_alloc();
spin_lock_bh(&dest->dst_lock);
if (!dest_dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
goto err_unreach;
}
rt = do_output_route4(net, dest->addr.ip, rt_mode,
&dest_dst->dst_saddr.ip);
if (!rt) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
ip_vs_dest_dst_free(dest_dst);
goto err_unreach;
}
__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
spin_unlock_bh(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n",
&dest->addr.ip, &dest_dst->dst_saddr.ip,
atomic_read(&rt->dst.__refcnt));
}
daddr = dest->addr.ip;
if (ret_saddr)
*ret_saddr = dest_dst->dst_saddr.ip;
} else {
__be32 saddr = htonl(INADDR_ANY);
noref = 0;
/* For such unconfigured boxes avoid many route lookups
* for performance reasons because we do not remember saddr
*/
rt_mode &= ~IP_VS_RT_MODE_CONNECT;
rt = do_output_route4(net, daddr, rt_mode, &saddr);
if (!rt)
goto err_unreach;
if (ret_saddr)
*ret_saddr = saddr;
}
local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
(rt->rt_flags & RTCF_LOCAL) ?
"local":"non-local", &daddr);
goto err_put;
}
iph = ip_hdr(skb);
if (likely(!local)) {
if (unlikely(ipv4_is_loopback(iph->saddr))) {
IP_VS_DBG_RL("Stopping traffic from loopback address "
"%pI4 to non-local address, dest: %pI4\n",
&iph->saddr, &daddr);
goto err_put;
}
} else {
ort = skb_rtable(skb);
if (!(rt_mode & IP_VS_RT_MODE_RDR) &&
!(ort->rt_flags & RTCF_LOCAL)) {
IP_VS_DBG_RL("Redirect from non-local address %pI4 to "
"local requires NAT method, dest: %pI4\n",
&iph->daddr, &daddr);
goto err_put;
}
/* skb to local stack, preserve old route */
if (!noref)
ip_rt_put(rt);
return local;
}
if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL))) {
mtu = dst_mtu(&rt->dst);
df = iph->frag_off & htons(IP_DF);
} else {
struct sock *sk = skb->sk;
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto err_put;
}
ort = skb_rtable(skb);
if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
/* MTU check allowed? */
df = sysctl_pmtu_disc(ipvs) ? iph->frag_off & htons(IP_DF) : 0;
}
/* MTU checking */
if (unlikely(df && skb->len > mtu && !skb_is_gso(skb))) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG(1, "frag needed for %pI4\n", &iph->saddr);
goto err_put;
}
skb_dst_drop(skb);
if (noref) {
if (!local)
skb_dst_set_noref_force(skb, &rt->dst);
else
skb_dst_set(skb, dst_clone(&rt->dst));
} else
skb_dst_set(skb, &rt->dst);
return local;
err_put:
if (!noref)
ip_rt_put(rt);
return -1;
err_unreach:
dst_link_failure(skb);
return -1;
}
/* Get route to destination or remote server */
static int
__ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
__be32 daddr, int rt_mode, __be32 *ret_saddr,
struct ip_vs_iphdr *ipvsh)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct ip_vs_dest_dst *dest_dst;
struct rtable *rt; /* Route to the other host */
int mtu;
int local, noref = 1;
if (dest) {
dest_dst = __ip_vs_dst_check(dest);
if (likely(dest_dst))
rt = (struct rtable *) dest_dst->dst_cache;
else {
dest_dst = ip_vs_dest_dst_alloc();
spin_lock_bh(&dest->dst_lock);
if (!dest_dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
goto err_unreach;
}
rt = do_output_route4(net, dest->addr.ip, rt_mode,
&dest_dst->dst_saddr.ip);
if (!rt) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
ip_vs_dest_dst_free(dest_dst);
goto err_unreach;
}
__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
spin_unlock_bh(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n",
&dest->addr.ip, &dest_dst->dst_saddr.ip,
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
*ret_saddr = dest_dst->dst_saddr.ip;
} else {
__be32 saddr = htonl(INADDR_ANY);
noref = 0;
/* For such unconfigured boxes avoid many route lookups
* for performance reasons because we do not remember saddr
*/
rt_mode &= ~IP_VS_RT_MODE_CONNECT;
rt = do_output_route4(net, daddr, rt_mode, &saddr);
if (!rt)
goto err_unreach;
if (ret_saddr)
*ret_saddr = saddr;
}
local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
if (unlikely(crosses_local_route_boundary(skb_af, skb, rt_mode,
local))) {
IP_VS_DBG_RL("We are crossing local and non-local addresses"
" daddr=%pI4\n", &daddr);
goto err_put;
}
if (unlikely(local)) {
/* skb to local stack, preserve old route */
if (!noref)
ip_rt_put(rt);
return local;
}
if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL))) {
mtu = dst_mtu(&rt->dst);
} else {
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto err_put;
}
maybe_update_pmtu(skb_af, skb, mtu);
}
if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
goto err_put;
skb_dst_drop(skb);
if (noref) {
if (!local)
skb_dst_set_noref(skb, &rt->dst);
else
skb_dst_set(skb, dst_clone(&rt->dst));
} else
skb_dst_set(skb, &rt->dst);
return local;
err_put:
if (!noref)
ip_rt_put(rt);
return -1;
err_unreach:
dst_link_failure(skb);
return -1;
}
/* Get route to destination or remote server */
static struct rtable *
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
__be32 daddr, u32 rtos, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */
int local;
if (dest) {
spin_lock(&dest->dst_lock);
if (!(rt = (struct rtable *)
__ip_vs_dst_check(dest, rtos))) {
rt = ip_route_output(net, dest->addr.ip, 0, rtos, 0);
if (IS_ERR(rt)) {
spin_unlock(&dest->dst_lock);
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
&dest->addr.ip);
return NULL;
}
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n",
&dest->addr.ip,
atomic_read(&rt->dst.__refcnt), rtos);
}
spin_unlock(&dest->dst_lock);
} else {
rt = ip_route_output(net, daddr, 0, rtos, 0);
if (IS_ERR(rt)) {
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
&daddr);
return NULL;
}
}
local = rt->rt_flags & RTCF_LOCAL;
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
(rt->rt_flags & RTCF_LOCAL) ?
"local":"non-local", &rt->rt_dst);
ip_rt_put(rt);
return NULL;
}
if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
!((ort = skb_rtable(skb)) && ort->rt_flags & RTCF_LOCAL)) {
IP_VS_DBG_RL("Redirect from non-local address %pI4 to local "
"requires NAT method, dest: %pI4\n",
&ip_hdr(skb)->daddr, &rt->rt_dst);
ip_rt_put(rt);
return NULL;
}
if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) {
IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 "
"to non-local address, dest: %pI4\n",
&ip_hdr(skb)->saddr, &rt->rt_dst);
ip_rt_put(rt);
return NULL;
}
return rt;
}
/*
* Syn-proxy step 3 logic: receive syn-ack from rs
* Update syn_proxy_seq.delta and send stored ack skbs
* to rs.
*/
int
ip_vs_synproxy_synack_rcv(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int ihl, int *verdict)
{
struct tcphdr _tcph, *th;
struct sk_buff_head save_skb;
struct sk_buff *tmp_skb = NULL;
struct ip_vs_dest *dest = cp->dest;
th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph);
if (th == NULL) {
*verdict = NF_DROP;
return 0;
}
IP_VS_DBG(6, "in syn_proxy_synack_rcv, "
"seq = %u ack_seq = %u %c%c%c cp->is_synproxy = %u cp->state = %u\n",
ntohl(th->seq),
ntohl(th->ack_seq),
(th->syn) ? 'S' : '-',
(th->ack) ? 'A' : '-',
(th->rst) ? 'R' : '-',
cp->flags & IP_VS_CONN_F_SYNPROXY, cp->state);
skb_queue_head_init(&save_skb);
spin_lock(&cp->lock);
if ((th->syn) && (th->ack) && (!th->rst) &&
(cp->flags & IP_VS_CONN_F_SYNPROXY) &&
cp->state == IP_VS_TCP_S_SYN_SENT) {
cp->syn_proxy_seq.delta =
htonl(cp->syn_proxy_seq.init_seq) - htonl(th->seq);
cp->timeout = pp->timeout_table[cp->state =
IP_VS_TCP_S_ESTABLISHED];
if (dest) {
atomic_inc(&dest->activeconns);
atomic_dec(&dest->inactconns);
cp->flags &= ~IP_VS_CONN_F_INACTIVE;
}
/* save tcp sequense for fullnat/nat, INside to OUTside */
if (sysctl_ip_vs_conn_expire_tcp_rst == 1) {
cp->rs_end_seq = htonl(ntohl(th->seq) + 1);
cp->rs_ack_seq = th->ack_seq;
IP_VS_DBG_RL("packet from RS, seq:%u ack_seq:%u.",
ntohl(th->seq), ntohl(th->ack_seq));
IP_VS_DBG_RL("port:%u->%u", ntohs(th->source),
ntohs(th->dest));
}
/* First: free stored syn skb */
if ((tmp_skb = xchg(&cp->syn_skb, NULL)) != NULL) {
kfree_skb(tmp_skb);
tmp_skb = NULL;
}
if (skb_queue_len(&cp->ack_skb) <= 0) {
/*
* FIXME: maybe a bug here, print err msg and go.
* Attention: cp->state has been changed and we
* should still DROP the Syn/Ack skb.
*/
IP_VS_ERR_RL
("Got ack_skb NULL pointer in syn_proxy_synack_rcv\n");
spin_unlock(&cp->lock);
*verdict = NF_DROP;
return 0;
}
while ((tmp_skb = skb_dequeue(&cp->ack_skb)) != NULL) {
skb_queue_tail(&save_skb, tmp_skb);
}
/*
* Release the lock, because we don't
* touch session any more.
*/
spin_unlock(&cp->lock);
while ((tmp_skb = skb_dequeue(&save_skb)) != NULL) {
/* If xmit failed, syn_skb will be freed correctly. */
cp->packet_xmit(tmp_skb, cp, pp);
}
*verdict = NF_DROP;
return 0;
} else if ((th->rst) &&
(cp->flags & IP_VS_CONN_F_SYNPROXY) &&
cp->state == IP_VS_TCP_S_SYN_SENT) {
__u32 temp_seq;
temp_seq = ntohl(th->seq);
IP_VS_DBG(6, "get rst from rs, seq = %u ack_seq= %u\n",
ntohl(th->seq), ntohl(th->ack_seq));
/* coute the delta of seq */
cp->syn_proxy_seq.delta =
ntohl(cp->syn_proxy_seq.init_seq) - ntohl(th->seq);
cp->timeout = pp->timeout_table[cp->state = IP_VS_TCP_S_CLOSE];
spin_unlock(&cp->lock);
th->seq = htonl(ntohl(th->seq) + 1);
syn_proxy_seq_csum_update(th, htonl(temp_seq), th->seq);
return 1;
}
spin_unlock(&cp->lock);
return 1;
}
/*
* Get route to destination or remote server
*/
static int
__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct ip_vs_dest_dst *dest_dst;
struct rt6_info *rt; /* Route to the other host */
struct rt6_info *ort; /* Original route */
struct dst_entry *dst;
int mtu;
int local, noref = 1;
if (dest) {
dest_dst = __ip_vs_dst_check(dest);
if (likely(dest_dst))
rt = (struct rt6_info *) dest_dst->dst_cache;
else {
u32 cookie;
dest_dst = ip_vs_dest_dst_alloc();
spin_lock_bh(&dest->dst_lock);
if (!dest_dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
goto err_unreach;
}
dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
&dest_dst->dst_saddr.in6,
do_xfrm);
if (!dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
ip_vs_dest_dst_free(dest_dst);
goto err_unreach;
}
rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
__ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
spin_unlock_bh(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
&dest->addr.in6, &dest_dst->dst_saddr.in6,
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
*ret_saddr = dest_dst->dst_saddr.in6;
} else {
noref = 0;
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
if (!dst)
goto err_unreach;
rt = (struct rt6_info *) dst;
}
local = __ip_vs_is_local_route6(rt);
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6c\n",
local ? "local":"non-local", daddr);
goto err_put;
}
if (likely(!local)) {
if (unlikely((!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 "
"%pI6c to non-local address, "
"dest: %pI6c\n",
&ipv6_hdr(skb)->saddr, daddr);
goto err_put;
}
} else {
ort = (struct rt6_info *) skb_dst(skb);
if (!(rt_mode & IP_VS_RT_MODE_RDR) &&
!__ip_vs_is_local_route6(ort)) {
IP_VS_DBG_RL("Redirect from non-local address %pI6c "
"to local requires NAT method, "
"dest: %pI6c\n",
&ipv6_hdr(skb)->daddr, daddr);
goto err_put;
}
/* skb to local stack, preserve old route */
if (!noref)
dst_release(&rt->dst);
return local;
}
/* MTU checking */
if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL)))
mtu = dst_mtu(&rt->dst);
else {
struct sock *sk = skb->sk;
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
if (mtu < IPV6_MIN_MTU) {
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
IPV6_MIN_MTU);
goto err_put;
}
ort = (struct rt6_info *) skb_dst(skb);
if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
}
if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {
if (!skb->dev)
skb->dev = net->loopback_dev;
/* only send ICMP too big on first fragment */
if (!ipvsh->fragoffs)
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG(1, "frag needed for %pI6c\n", &ipv6_hdr(skb)->saddr);
goto err_put;
}
skb_dst_drop(skb);
if (noref) {
if (!local)
skb_dst_set_noref_force(skb, &rt->dst);
else
skb_dst_set(skb, dst_clone(&rt->dst));
} else
skb_dst_set(skb, &rt->dst);
return local;
err_put:
if (!noref)
dst_release(&rt->dst);
return -1;
err_unreach:
dst_link_failure(skb);
return -1;
}
/*
* Get route to destination or remote server
*/
static int
__ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct ip_vs_dest_dst *dest_dst;
struct rt6_info *rt; /* Route to the other host */
struct dst_entry *dst;
int mtu;
int local, noref = 1;
if (dest) {
dest_dst = __ip_vs_dst_check(dest);
if (likely(dest_dst))
rt = (struct rt6_info *) dest_dst->dst_cache;
else {
u32 cookie;
dest_dst = ip_vs_dest_dst_alloc();
spin_lock_bh(&dest->dst_lock);
if (!dest_dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
goto err_unreach;
}
dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
&dest_dst->dst_saddr.in6,
do_xfrm, rt_mode);
if (!dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
ip_vs_dest_dst_free(dest_dst);
goto err_unreach;
}
rt = (struct rt6_info *) dst;
cookie = rt6_get_cookie(rt);
__ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
spin_unlock_bh(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
&dest->addr.in6, &dest_dst->dst_saddr.in6,
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
*ret_saddr = dest_dst->dst_saddr.in6;
} else {
noref = 0;
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm,
rt_mode);
if (!dst)
goto err_unreach;
rt = (struct rt6_info *) dst;
}
local = __ip_vs_is_local_route6(rt);
if (unlikely(crosses_local_route_boundary(skb_af, skb, rt_mode,
local))) {
IP_VS_DBG_RL("We are crossing local and non-local addresses"
" daddr=%pI6\n", daddr);
goto err_put;
}
if (unlikely(local)) {
/* skb to local stack, preserve old route */
if (!noref)
dst_release(&rt->dst);
return local;
}
/* MTU checking */
if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL)))
mtu = dst_mtu(&rt->dst);
else {
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
if (mtu < IPV6_MIN_MTU) {
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
IPV6_MIN_MTU);
goto err_put;
}
maybe_update_pmtu(skb_af, skb, mtu);
}
if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
goto err_put;
skb_dst_drop(skb);
if (noref) {
if (!local)
skb_dst_set_noref(skb, &rt->dst);
else
skb_dst_set(skb, dst_clone(&rt->dst));
} else
skb_dst_set(skb, &rt->dst);
return local;
err_put:
if (!noref)
dst_release(&rt->dst);
return -1;
err_unreach:
/* The ip6_link_failure function requires the dev field to be set
* in order to get the net (further for the sake of fwmark
* reflection).
*/
if (!skb->dev)
skb->dev = skb_dst(skb)->dev;
dst_link_failure(skb);
return -1;
}