/*
* Add an ip header to a skbuff and send it out.
*
*/
int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
u32 saddr, u32 daddr, struct ip_options *opt)
{
struct inet_sock *inet = inet_sk(sk);
struct rtable *rt = (struct rtable *)skb->dst;
struct iphdr *iph;
/* Build the IP header. */
if (opt)
iph=(struct iphdr *)skb_push(skb,sizeof(struct iphdr) + opt->optlen);
else
iph=(struct iphdr *)skb_push(skb,sizeof(struct iphdr));
iph->version = 4;
iph->ihl = 5;
iph->tos = inet->tos;
if (ip_dont_fragment(sk, &rt->u.dst))
iph->frag_off = htons(IP_DF);
else
iph->frag_off = 0;
iph->ttl = ip_select_ttl(inet, &rt->u.dst);
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
iph->protocol = sk->sk_protocol;
iph->tot_len = htons(skb->len);
ip_select_ident(iph, &rt->u.dst, sk);
skb->nh.iph = iph;
if (opt && opt->optlen) {
iph->ihl += opt->optlen>>2;
ip_options_build(skb, opt, daddr, rt, 0);
}
static int raw_getrawfrag(const void *p, char *to, unsigned int offset,
unsigned int fraglen, struct sk_buff *skb)
{
struct rawfakehdr *rfh = (struct rawfakehdr *) p;
if (memcpy_fromiovecend(to, rfh->iov, offset, fraglen))
return -EFAULT;
if (!offset) {
struct iphdr *iph = (struct iphdr *)to;
if (!iph->saddr)
iph->saddr = rfh->saddr;
iph->check = 0;
iph->tot_len = htons(fraglen); /* This is right as you can't
frag RAW packets */
/*
* Deliberate breach of modularity to keep
* ip_build_xmit clean (well less messy).
*/
if (!iph->id)
ip_select_ident(iph, rfh->dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
return 0;
}
int ip_format_and_send_pkt(struct sk_buff *skb,struct sock*sk,__be32 saddr, __be32 daddr,u16 tcp_len)
{
int ret = 0;
struct net *pnet = sock_net(sk);
struct netns_ipv4 *n_ipv4 = &pnet->ipv4;
struct inet_sock *inet = inet_sk(sk);
struct tcphdr *th = tcp_hdr(skb);
struct iphdr *iph = ip_hdr(skb);
iph->tos = inet->tos;
iph->tot_len = htons(sizeof(struct iphdr) + tcp_len);
iph->frag_off = htons(IP_DF);
ip_select_ident(skb, sk);
iph->ttl = ip_select_ttl(sk);
iph->protocol = sk->sk_protocol;
iph->daddr = daddr;
iph->saddr = saddr;
iph->check = 0;
th->check = 0;
th->check = get_ipv4_psd_sum(iph);
if(n_ipv4->aft_route_out){
ret = n_ipv4->aft_route_out(skb);
if(ret < 0)
return US_ENETUNREACH;
}
return mbuf_format_and_send(skb, tcp_len);
}
/*
* Add an ip header to a skbuff and send it out.
*
*/
int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
__be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
{
struct inet_sock *inet = inet_sk(sk);
struct rtable *rt = skb_rtable(skb);
struct iphdr *iph;
/* Build the IP header. */
skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 5;
iph->tos = inet->tos;
if (ip_dont_fragment(sk, &rt->dst))
iph->frag_off = htons(IP_DF);
else
iph->frag_off = 0;
iph->ttl = ip_select_ttl(inet, &rt->dst);
iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
iph->saddr = saddr;
iph->protocol = sk->sk_protocol;
ip_select_ident(skb, sk);
if (opt && opt->opt.optlen) {
iph->ihl += opt->opt.optlen>>2;
ip_options_build(skb, &opt->opt, daddr, rt, 0);
}
int igmp_send_report_full(struct net_device *dev, u32 group, int type,
u8 respond, u32 dst)
{
struct sk_buff *skb;
struct iphdr *iph;
struct igmphdr *ih;
struct rtable *rt;
if (ip_route_output(&rt, dst, 0, 0, dev->ifindex))
return -1;
if (rt->rt_src == 0) {
ip_rt_put(rt);
return -1;
}
skb=alloc_skb(IGMP_SIZE+dev->hard_header_len+15, GFP_ATOMIC);
if (skb == NULL) {
ip_rt_put(rt);
return -1;
}
skb->dst = &rt->u.dst;
skb_reserve(skb, (dev->hard_header_len+15)&~15);
skb->nh.iph = iph = (struct iphdr *)skb_put(skb, sizeof(struct iphdr)+4);
iph->version = 4;
iph->ihl = (sizeof(struct iphdr)+4)>>2;
iph->tos = 0;
iph->frag_off = htons(IP_DF);
iph->ttl = 1;
iph->daddr = dst;
iph->saddr = rt->rt_src;
iph->protocol = IPPROTO_IGMP;
iph->tot_len = htons(IGMP_SIZE);
ip_select_ident(iph, &rt->u.dst, NULL);
((u8*)&iph[1])[0] = IPOPT_RA;
((u8*)&iph[1])[1] = 4;
((u8*)&iph[1])[2] = 0;
((u8*)&iph[1])[3] = 0;
ip_send_check(iph);
ih = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr));
ih->type=type;
ih->code=respond;
ih->csum=0;
ih->group=group;
ih->csum=ip_compute_csum((void *)ih, sizeof(struct igmphdr));
return NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
output_maybe_reroute);
}
/*
* Add an ip header to a skbuff and send it out.
*
*/
int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,__be32 saddr, __be32 daddr)
{
int ret = 0;
struct inet_sock *inet = inet_sk(sk);
struct tcphdr *th = tcp_hdr(skb);
struct net *pnet = sock_net(sk);
struct netns_ipv4 *n_ipv4 = &pnet->ipv4;
struct iphdr *iph;
// Build the IP header.
skb_push(skb, sizeof(struct iphdr)); ////+ (opt ? opt->opt.optlen : 0)
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 5;
//iph->tos = 0;//inet->tos;
iph->tos = inet->tos;
iph->tot_len = htons(skb->len);
iph->frag_off = htons(IP_DF); //smallboy :must before ip_select_ident;
ip_select_ident(skb, sk);
iph->ttl = ip_select_ttl(sk);
iph->protocol = sk->sk_protocol;
iph->daddr = daddr;
iph->saddr = saddr;
iph->check = 0;
//iph->check = ip_fast_csum(iph, iph->ihl);
th->check = 0;
//th->check = get_ipv4_udptcp_checksum(iph , th);
th->check = get_ipv4_psd_sum(iph);
//skb->mark = sk->sk_mark;
//fprintf(stderr,"TH:%u,src:%s,dst:%s,sport:%u,dport:%u,seq:%-12u,ack:%-12u,ipid:%-12u,len:%-12u,SYN:%u;PSH:%u;ACK:%u;FIN:%u;RST:%u; send!!!\n"
// ,US_GET_LCORE(),trans_ip(iph->saddr),trans_ip(iph->daddr)
// ,ntohs(th->source),ntohs(th->dest)
// ,ntohl(th->seq),ntohl(th->ack_seq)
// ,iph->id,skb->len,th->syn,th->psh,th->ack,th->fin,th->rst);
if(n_ipv4->aft_route_out){
ret = n_ipv4->aft_route_out(skb);
if(ret < 0)
return US_ENETUNREACH;
}
// Send it out.
return ip_local_out(skb);
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401.
*/
static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct iphdr *top_iph;
int flags;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ip_hdr(skb);
top_iph->ihl = 5;
top_iph->version = 4;
top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
/* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
top_iph->tos = 0;
else
top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
XFRM_MODE_SKB_CB(skb)->tos);
flags = x->props.flags;
if (flags & XFRM_STATE_NOECN)
IP_ECN_clear(top_iph);
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
top_iph->ttl = ip4_dst_hoplimit(dst->child);
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
ip_select_ident(dev_net(dst->dev), skb, NULL);
return 0;
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401.
*/
static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct iphdr *top_iph;
int flags;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ip_hdr(skb);
top_iph->ihl = 5;
top_iph->version = 4;
top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
/* DS disclosed */
top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos,
XFRM_MODE_SKB_CB(skb)->tos);
flags = x->props.flags;
if (flags & XFRM_STATE_NOECN)
IP_ECN_clear(top_iph);
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
ip_select_ident(top_iph, dst->child, NULL);
top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT);
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
return 0;
}
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;
}
static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
void *from, size_t length,
struct rtable **rtp,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct iphdr *iph;
struct sk_buff *skb;
unsigned int iphlen;
int err;
struct rtable *rt = *rtp;
int hlen, tlen;
if (length > rt->dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
rt->dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
hlen = LL_RESERVED_SPACE(rt->dst.dev);
tlen = rt->dst.dev->needed_tailroom;
skb = sock_alloc_send_skb(sk,
length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
skb_reserve(skb, hlen);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, &rt->dst);
*rtp = NULL;
skb_reset_network_header(skb);
iph = ip_hdr(skb);
skb_put(skb,sizeof(*iph));
skb->ip_summed = CHECKSUM_NONE;
skb->transport_header = skb->network_header;
err = -EFAULT;
if (!memcpy_fromiovecend2((void *)iph, from, 0, length))
goto error_free;
iphlen = iph->ihl * 4;
/*
* We don't want to modify the ip header, but we do need to
* be sure that it won't cause problems later along the network
* stack. Specifically we want to make sure that iph->ihl is a
* sane value. If ihl points beyond the length of the buffer passed
* in, reject the frame as invalid
*/
err = -EINVAL;
if (iphlen > length)
goto error_free;
if (iphlen >= sizeof(*iph)) {
if (!iph->saddr)
iph->saddr = fl4->saddr;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(skb, &rt->dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
if (iph->protocol == IPPROTO_ICMP)
icmp_out_count(net, ((struct icmphdr *)
skb_transport_header(skb))->type);
err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
rt->dst.dev, dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
out:
return 0;
error_free:
kfree_skb(skb);
error:
IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
return err;
}
/*
* 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;
}
/*
* 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;
}
static int raw_send_hdrinc(struct sock *sk, void *from, int length,
struct rtable *rt,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
int hh_len;
struct iphdr *iph;
struct sk_buff *skb;
int err;
if (length > rt->u.dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport,
rt->u.dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
skb = sock_alloc_send_skb(sk, length+hh_len+15,
flags&MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
skb_reserve(skb, hh_len);
skb->priority = sk->sk_priority;
skb->dst = dst_clone(&rt->u.dst);
skb->nh.iph = iph = (struct iphdr *)skb_put(skb, length);
skb->ip_summed = CHECKSUM_NONE;
skb->h.raw = skb->nh.raw;
err = memcpy_fromiovecend((void *)iph, from, 0, length);
if (err)
goto error_fault;
/* We don't modify invalid header */
if (length >= sizeof(*iph) && iph->ihl * 4 <= length) {
if (!iph->saddr)
iph->saddr = rt->rt_src;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(iph, &rt->u.dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
dst_output);
if (err > 0)
err = inet->recverr ? net_xmit_errno(err) : 0;
if (err)
goto error;
out:
return 0;
error_fault:
err = -EFAULT;
kfree_skb(skb);
error:
IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
return err;
}
int esp_output(struct sk_buff *skb)
{
int err;
struct dst_entry *dst = skb->dst;
struct xfrm_state *x = dst->xfrm;
struct iphdr *iph, *top_iph;
struct ip_esp_hdr *esph;
struct crypto_tfm *tfm;
struct esp_data *esp;
struct sk_buff *trailer;
struct udphdr *uh = NULL;
struct xfrm_encap_tmpl *encap = NULL;
int blksize;
int clen;
int alen;
int nfrags;
union {
struct iphdr iph;
char buf[60];
} tmp_iph;
/* First, if the skb is not checksummed, complete checksum. */
if (skb->ip_summed == CHECKSUM_HW && skb_checksum_help(skb) == NULL) {
err = -EINVAL;
goto error_nolock;
}
spin_lock_bh(&x->lock);
err = xfrm_check_output(x, skb, AF_INET);
if (err)
goto error;
err = -ENOMEM;
/* Strip IP header in transport mode. Save it. */
if (!x->props.mode) {
iph = skb->nh.iph;
memcpy(&tmp_iph, iph, iph->ihl*4);
__skb_pull(skb, iph->ihl*4);
}
/* Now skb is pure payload to encrypt */
/* Round to block size */
clen = skb->len;
esp = x->data;
alen = esp->auth.icv_trunc_len;
tfm = esp->conf.tfm;
blksize = (crypto_tfm_alg_blocksize(tfm) + 3) & ~3;
clen = (clen + 2 + blksize-1)&~(blksize-1);
if (esp->conf.padlen)
clen = (clen + esp->conf.padlen-1)&~(esp->conf.padlen-1);
if ((nfrags = skb_cow_data(skb, clen-skb->len+alen, &trailer)) < 0)
goto error;
/* Fill padding... */
do {
int i;
for (i=0; i<clen-skb->len - 2; i++)
*(u8*)(trailer->tail + i) = i+1;
} while (0);
*(u8*)(trailer->tail + clen-skb->len - 2) = (clen - skb->len)-2;
pskb_put(skb, trailer, clen - skb->len);
encap = x->encap;
iph = skb->nh.iph;
if (x->props.mode) {
top_iph = (struct iphdr*)skb_push(skb, x->props.header_len);
esph = (struct ip_esp_hdr*)(top_iph+1);
if (encap && encap->encap_type) {
switch (encap->encap_type) {
case UDP_ENCAP_ESPINUDP:
uh = (struct udphdr*) esph;
esph = (struct ip_esp_hdr*)(uh+1);
top_iph->protocol = IPPROTO_UDP;
break;
default:
printk(KERN_INFO
"esp_output(): Unhandled encap: %u\n",
encap->encap_type);
top_iph->protocol = IPPROTO_ESP;
break;
}
} else
top_iph->protocol = IPPROTO_ESP;
*(u8*)(trailer->tail - 1) = IPPROTO_IPIP;
top_iph->ihl = 5;
top_iph->version = 4;
top_iph->tos = iph->tos; /* DS disclosed */
if (x->props.flags & XFRM_STATE_NOECN)
IP_ECN_clear(top_iph);
top_iph->tot_len = htons(skb->len + alen);
top_iph->frag_off = iph->frag_off&htons(IP_DF);
if (!(top_iph->frag_off))
ip_select_ident(top_iph, dst, 0);
top_iph->ttl = iph->ttl; /* TTL disclosed */
top_iph->check = 0;
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
} else {
esph = (struct ip_esp_hdr*)skb_push(skb, x->props.header_len);
top_iph = (struct iphdr*)skb_push(skb, iph->ihl*4);
memcpy(top_iph, &tmp_iph, iph->ihl*4);
if (encap && encap->encap_type) {
switch (encap->encap_type) {
case UDP_ENCAP_ESPINUDP:
uh = (struct udphdr*) esph;
esph = (struct ip_esp_hdr*)(uh+1);
top_iph->protocol = IPPROTO_UDP;
break;
default:
printk(KERN_INFO
"esp_output(): Unhandled encap: %u\n",
encap->encap_type);
top_iph->protocol = IPPROTO_ESP;
break;
}
} else
top_iph->protocol = IPPROTO_ESP;
iph = &tmp_iph.iph;
top_iph->tot_len = htons(skb->len + alen);
top_iph->check = 0;
top_iph->frag_off = iph->frag_off;
*(u8*)(trailer->tail - 1) = iph->protocol;
}
/* this is non-NULL only with UDP Encapsulation */
if (encap && uh) {
uh->source = encap->encap_sport;
uh->dest = encap->encap_dport;
uh->len = htons(skb->len + alen - sizeof(struct iphdr));
uh->check = 0;
}
esph->spi = x->id.spi;
esph->seq_no = htonl(++x->replay.oseq);
if (esp->conf.ivlen)
crypto_cipher_set_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
do {
struct scatterlist sgbuf[nfrags>MAX_SG_ONSTACK ? 0 : nfrags];
struct scatterlist *sg = sgbuf;
if (unlikely(nfrags > MAX_SG_ONSTACK)) {
sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC);
if (!sg)
goto error;
}
skb_to_sgvec(skb, sg, esph->enc_data+esp->conf.ivlen-skb->data, clen);
crypto_cipher_encrypt(tfm, sg, sg, clen);
if (unlikely(sg != sgbuf))
kfree(sg);
} while (0);
if (esp->conf.ivlen) {
memcpy(esph->enc_data, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
crypto_cipher_get_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
}
if (esp->auth.icv_full_len) {
esp->auth.icv(esp, skb, (u8*)esph-skb->data,
sizeof(struct ip_esp_hdr) + esp->conf.ivlen+clen, trailer->tail);
pskb_put(skb, trailer, alen);
}
ip_send_check(top_iph);
skb->nh.raw = skb->data;
x->curlft.bytes += skb->len;
x->curlft.packets++;
spin_unlock_bh(&x->lock);
if ((skb->dst = dst_pop(dst)) == NULL) {
err = -EHOSTUNREACH;
goto error_nolock;
}
return NET_XMIT_BYPASS;
error:
spin_unlock_bh(&x->lock);
error_nolock:
kfree_skb(skb);
return err;
}
//int encap(struct sk_buff *skb, struct tun_param *tp, unsigned int mark, struct ka_payload *kap){
int encap(struct sk_buff *skb, struct tun_param *tp, unsigned int mark, struct ka_payload *kap){
struct sk_buff *new_skb;
struct iphdr *old_iph;
//struct iphdr *iph;
struct net_device *dev;
int ret = 0;
struct sock tmpsk;
struct udphdr *udph;
u32 saddr, daddr;
u16 sport, dport;
struct rtable *rt;
struct flowi4 fl4;
unsigned int pushroom, piggyroom;
piggyroom = 0;
if(kap->tid == 0) piggyroom = 0;
else piggyroom = PIGGYROOM;
pushroom = HEADROOM + piggyroom;
old_iph = get_IP_header(skb);
daddr = tp->tr.addr;
sport = tp->tl.port;
dport = tp->tr.port;
// since 2.6.36 rtable no longer has rt_src attribute, now I get source address from the device (Sander)
dev = dev_get_by_index(upmtns->net_ns, tp->tl.ifindex);
if (!dev) {
dmesge("no device found during encap");
return -1;
}
saddr = get_dev_ip_address(dev, NULL, 0);
// since 2.6.39 ip_route_output_key flowi parameter has been replaced with flowi4, rtable no longer has rt_src attribute
// ip_route_output_key function now returns an rtable and should be replaced with ip_route_output_ports (Sander)
tmpsk.sk_mark = mark;
rt = ip_route_output_ports(dev_net(dev), &fl4, &tmpsk, daddr, 0, 0, 0, IPPROTO_IP, RT_TOS(old_iph->tos), tp->tl.ifindex);
if (!rt) {
dmesge("encap - no rtable found during encap");
ret = -1;
goto end;
}
if (skb_headroom(skb) < pushroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
new_skb = skb_realloc_headroom(skb, pushroom);
printk(" --- socket buffer REALLOCATION\n");
if (!new_skb) {
dmesge("encap - can not realloc skb room");
ret = -1;
goto end;
}
if (skb->sk) skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb_any(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
if(piggyroom > 0){
skb_push(skb, PIGGYROOM);
//print_ka_info(kap->info);
memcpy(skb->data, kap, sizeof(struct ka_payload));
skb_push(skb, HEADROOM);
}
else{
//printk("Creating normal packet...\n");
skb_push(skb, HEADROOM);
}
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
skb_dst_drop(skb);
// since 2.6.36 rtable has no 'u' attribute, you can use dst directly (Sander)
skb_dst_set(skb, &rt->dst);
set_ip_header(skb, old_iph, saddr, daddr, piggyroom);
set_udp_header(skb, old_iph, sport, dport, piggyroom);
nf_reset(skb);
// since 2.6.36 rtable has no 'u' attribute, you can use dst directly (Sander)
ip_select_ident(ip_hdr(skb), &rt->dst, NULL);
skb->mark = mark; //useless...
/*************/
udph = get_UDP_header(skb);
//dmesg("ENCAP ---> UDP src: %u dst: %u mark: %u", ntohs(udph->source), ntohs(udph->dest),skb->mark);
end:
dev_put(dev);
return ret;
}
static void send_unreach(struct sk_buff *skb_in, int code)
{
struct iphdr *iph;
struct udphdr *udph;
struct icmphdr *icmph;
struct sk_buff *nskb;
u32 saddr;
u8 tos;
int hh_len, length;
struct rtable *rt = (struct rtable*)skb_in->dst;
unsigned char *data;
if (!rt)
return;
/* FIXME: Use sysctl number. --RR */
if (!xrlim_allow(&rt->u.dst, 1*HZ))
return;
iph = skb_in->nh.iph;
/* No replies to physical multicast/broadcast */
if (skb_in->pkt_type!=PACKET_HOST)
return;
/* Now check at the protocol level */
if (rt->rt_flags&(RTCF_BROADCAST|RTCF_MULTICAST))
return;
/* Only reply to fragment 0. */
if (iph->frag_off&htons(IP_OFFSET))
return;
/* if UDP checksum is set, verify it's correct */
if (iph->protocol == IPPROTO_UDP
&& skb_in->tail-(u8*)iph >= sizeof(struct udphdr)) {
int datalen = skb_in->len - (iph->ihl<<2);
udph = (struct udphdr *)((char *)iph + (iph->ihl<<2));
if (udph->check
&& csum_tcpudp_magic(iph->saddr, iph->daddr,
datalen, IPPROTO_UDP,
csum_partial((char *)udph, datalen,
0)) != 0)
return;
}
/* If we send an ICMP error to an ICMP error a mess would result.. */
if (iph->protocol == IPPROTO_ICMP
&& skb_in->tail-(u8*)iph >= sizeof(struct icmphdr)) {
icmph = (struct icmphdr *)((char *)iph + (iph->ihl<<2));
/* Between echo-reply (0) and timestamp (13),
everything except echo-request (8) is an error.
Also, anything greater than NR_ICMP_TYPES is
unknown, and hence should be treated as an error... */
if ((icmph->type < ICMP_TIMESTAMP
&& icmph->type != ICMP_ECHOREPLY
&& icmph->type != ICMP_ECHO)
|| icmph->type > NR_ICMP_TYPES)
return;
}
saddr = iph->daddr;
if (!(rt->rt_flags & RTCF_LOCAL))
saddr = 0;
tos = (iph->tos & IPTOS_TOS_MASK) | IPTOS_PREC_INTERNETCONTROL;
if (ip_route_output(&rt, iph->saddr, saddr, RT_TOS(tos), 0))
return;
/* RFC says return as much as we can without exceeding 576 bytes. */
length = skb_in->len + sizeof(struct iphdr) + sizeof(struct icmphdr);
if (length > rt->u.dst.pmtu)
length = rt->u.dst.pmtu;
if (length > 576)
length = 576;
hh_len = (rt->u.dst.dev->hard_header_len + 15)&~15;
nskb = alloc_skb(hh_len+15+length, GFP_ATOMIC);
if (!nskb) {
ip_rt_put(rt);
return;
}
nskb->priority = 0;
nskb->dst = &rt->u.dst;
skb_reserve(nskb, hh_len);
/* Set up IP header */
iph = nskb->nh.iph
= (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
iph->version=4;
iph->ihl=5;
iph->tos=tos;
iph->tot_len = htons(length);
/* PMTU discovery never applies to ICMP packets. */
iph->frag_off = 0;
iph->ttl = MAXTTL;
ip_select_ident(iph, &rt->u.dst, NULL);
iph->protocol=IPPROTO_ICMP;
iph->saddr=rt->rt_src;
iph->daddr=rt->rt_dst;
iph->check=0;
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
/* Set up ICMP header. */
icmph = nskb->h.icmph
= (struct icmphdr *)skb_put(nskb, sizeof(struct icmphdr));
icmph->type = ICMP_DEST_UNREACH;
icmph->code = code;
icmph->un.gateway = 0;
icmph->checksum = 0;
/* Copy as much of original packet as will fit */
data = skb_put(nskb,
length - sizeof(struct iphdr) - sizeof(struct icmphdr));
/* FIXME: won't work with nonlinear skbs --RR */
memcpy(data, skb_in->nh.iph,
length - sizeof(struct iphdr) - sizeof(struct icmphdr));
icmph->checksum = ip_compute_csum((unsigned char *)icmph,
length - sizeof(struct iphdr));
nf_ct_attach(nskb, skb_in);
NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, nskb, NULL, nskb->dst->dev,
ip_finish_output);
}
/*
* 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;
}
static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
struct rtable *rt,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct iphdr *iph;
struct sk_buff *skb;
unsigned int iphlen;
int err;
if (length > rt->u.dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport,
rt->u.dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
skb = sock_alloc_send_skb(sk,
length + LL_ALLOCATED_SPACE(rt->u.dst.dev) + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
skb_reserve(skb, LL_RESERVED_SPACE(rt->u.dst.dev));
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, dst_clone(&rt->u.dst));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
skb_put(skb, length);
skb->ip_summed = CHECKSUM_NONE;
skb->transport_header = skb->network_header;
err = memcpy_fromiovecend((void *)iph, from, 0, length);
if (err)
goto error_fault;
/* We don't modify invalid header */
iphlen = iph->ihl * 4;
if (iphlen >= sizeof(*iph) && iphlen <= length) {
if (!iph->saddr)
iph->saddr = rt->rt_src;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(iph, &rt->u.dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
if (iph->protocol == IPPROTO_ICMP)
icmp_out_count(net, ((struct icmphdr *)
skb_transport_header(skb))->type);
err = NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
out:
return 0;
error_fault:
err = -EFAULT;
kfree_skb(skb);
error:
IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
return err;
}
