/*
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph;
struct iphdr fiph;
if (unlikely(skb->protocol != htons(ETH_P_IP)))
goto tx_error;
skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
if (IS_ERR(skb))
goto out;
if (ipip_tunnel_is_fan(tunnel)) {
if (ipip_build_fan_iphdr(tunnel, skb, &fiph))
goto tx_error;
tiph = &fiph;
} else {
tiph = &tunnel->parms.iph;
}
skb_set_inner_ipproto(skb, IPPROTO_IPIP);
ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
return NETDEV_TX_OK;
tx_error:
kfree_skb(skb);
out:
dev->stats.tx_errors++;
return NETDEV_TX_OK;
}
static bool expand_for_outer_iph(struct sk_buff *skb,
const struct net_device *out_dev)
{
unsigned int max_headroom;
unsigned int len_to_expand;
max_headroom = sizeof(struct iphdr) + LL_RESERVED_SPACE(out_dev);
if (skb_headroom(skb) < max_headroom) {
len_to_expand = max_headroom - skb_headroom(skb);
if (unlikely(skb_cow_head(skb, len_to_expand))) {
printk(KERN_INFO "[FlexPath] Failed to expand sk_buff\n");
return false;
}
}
skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
return true;
}
/*
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
if (unlikely(skb->protocol != htons(ETH_P_IP)))
goto tx_error;
skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
if (IS_ERR(skb))
goto out;
ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
return NETDEV_TX_OK;
tx_error:
kfree_skb(skb);
out:
dev->stats.tx_errors++;
return NETDEV_TX_OK;
}
/*
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
u8 ipproto;
switch (skb->protocol) {
case htons(ETH_P_IP):
ipproto = IPPROTO_IPIP;
break;
#if IS_ENABLED(CONFIG_MPLS)
case htons(ETH_P_MPLS_UC):
ipproto = IPPROTO_MPLS;
break;
#endif
default:
goto tx_error;
}
if (tiph->protocol != ipproto && tiph->protocol != 0)
goto tx_error;
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
goto tx_error;
skb_set_inner_ipproto(skb, ipproto);
if (tunnel->collect_md)
ip_md_tunnel_xmit(skb, dev, ipproto);
else
ip_tunnel_xmit(skb, dev, tiph, ipproto);
return NETDEV_TX_OK;
tx_error:
kfree_skb(skb);
dev->stats.tx_errors++;
return NETDEV_TX_OK;
}
/*
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
struct net_device *mcdev; /* madcap device */
#ifdef OVBENCH
if (SKB_OVBENCH (skb)) {
skb->ipip_tunnel_xmit_in = rdtsc ();
}
#endif
if (unlikely(skb->protocol != htons(ETH_P_IP)))
goto tx_error;
skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
if (IS_ERR(skb))
goto out;
if (madcap_enable) {
mcdev = __dev_get_by_index (dev_net (dev), tunnel->parms.link);
if (mcdev && get_madcap_ops (mcdev)) {
madcap_queue_xmit (skb, mcdev);
return NETDEV_TX_OK;
}
}
skb_set_inner_ipproto(skb, IPPROTO_IPIP);
ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
return NETDEV_TX_OK;
tx_error:
kfree_skb(skb);
out:
dev->stats.tx_errors++;
return NETDEV_TX_OK;
}
/*
* 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;
}
int
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
struct rt6_info *rt; /* Route to the other host */
struct in6_addr saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
__u8 next_protocol = 0;
__u32 payload_len = 0;
__u8 dsfield = 0;
__u8 ttl = 0;
struct ipv6hdr *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_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
&saddr, ipvsh, 1,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_TUNNEL);
if (local < 0)
goto tx_error;
if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1);
}
rt = (struct rt6_info *) skb_dst(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 ipv6hdr);
skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
&next_protocol, &payload_len,
&dsfield, &ttl, NULL);
if (IS_ERR(skb))
goto tx_error;
skb = iptunnel_handle_offloads(
skb, false, __tun_gso_type_mask(AF_INET6, cp->af));
if (IS_ERR(skb))
goto tx_error;
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));
/*
* Push down and install the IPIP header.
*/
iph = ipv6_hdr(skb);
iph->version = 6;
iph->nexthdr = next_protocol;
iph->payload_len = htons(payload_len);
memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
ipv6_change_dsfield(iph, 0, dsfield);
iph->daddr = cp->daddr.in6;
iph->saddr = saddr;
iph->hop_limit = ttl;
/* Another hack: avoid icmp_send in ip_fragment */
skb->ignore_df = 1;
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
ip6_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;
}
static struct sk_buff *gre_handle_offloads(struct sk_buff *skb,
bool csum)
{
return iptunnel_handle_offloads(skb, csum,
csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE);
}
