static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
struct ip_vs_iphdr *ipvsh,
struct sk_buff *skb, int mtu)
{
#ifdef CONFIG_IP_VS_IPV6
if (skb_af == AF_INET6) {
struct net *net = dev_net(skb_dst(skb)->dev);
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);
return false;
}
} else
#endif
{
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
/* If we're going to tunnel the packet and pmtu discovery
* is disabled, we'll just fragment it anyway
*/
if ((rt_mode & IP_VS_RT_MODE_TUNNEL) && !sysctl_pmtu_disc(ipvs))
return true;
if (unlikely(ip_hdr(skb)->frag_off & htons(IP_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",
&ip_hdr(skb)->saddr);
return false;
}
}
return true;
}
/*
* 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 ip_vs_iphdr *ipvsh)
{
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
__be16 df;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_CONNECT |
IP_VS_RT_MODE_TUNNEL, &saddr);
if (local < 0)
goto tx_error;
if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
rt = skb_rtable(skb);
tdev = rt->dst.dev;
/* Copy DF, reset fragment offset and MF */
df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
/*
* 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)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb)
goto tx_error;
consume_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));
/*
* 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 = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
ip_select_ident(skb, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
tx_error:
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
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;
}
/*
* 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 ip_vs_iphdr *ipvsh)
{
struct net *net = skb_net(skb);
struct netns_ipvs *ipvs = net_ipvs(net);
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
__u8 next_protocol = 0;
__u8 dsfield = 0;
__u8 ttl = 0;
__be16 df = 0;
__be16 *dfp = NULL;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_CONNECT |
IP_VS_RT_MODE_TUNNEL, &saddr, ipvsh);
if (local < 0)
goto tx_error;
if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
rt = skb_rtable(skb);
tdev = rt->dst.dev;
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
&next_protocol, NULL, &dsfield,
&ttl, dfp);
if (IS_ERR(skb))
goto tx_error;
skb = iptunnel_handle_offloads(
skb, false, __tun_gso_type_mask(AF_INET, cp->af));
if (IS_ERR(skb))
goto tx_error;
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/*
* 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 = next_protocol;
iph->tos = dsfield;
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = ttl;
ip_select_ident(net, skb, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->ignore_df = 1;
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
tx_error:
if (!IS_ERR(skb))
kfree_skb(skb);
rcu_read_unlock();
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 netns_ipvs *ipvs = net_ipvs(skb_net(skb));
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
__be16 df;
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 |
IP_VS_RT_MODE_CONNECT,
&saddr)))
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 (rt_is_output_route(skb_rtable(skb)))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
/* Copy DF, reset fragment offset and MF */
df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
if (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;
}
consume_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 = cp->daddr.ip;
iph->saddr = saddr;
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;
}