static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
{
/* Charge it to the socket. */
if (sock_queue_rcv_skb(sk, skb) < 0) {
IP_INC_STATS(IpInDiscards);
kfree_skb(skb);
return NET_RX_DROP;
}
IP_INC_STATS(IpInDelivers);
return NET_RX_SUCCESS;
}
s32 mpls_output(struct sk_buff*skb)
{
s32 ret = 0 ;
struct net_device *dev = skb->dst->dev;
skb->dev = dev;
MPLS_DEBUG_COUNTER_INC(mpls_output);
MPLS_DEBUG_FORWARD("Entry mpls_output.\n ");
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_OUTREQUESTS);
if (IPCB(skb)->flags & IPSKB_REROUTED)
{
ret = 1;
}
else
{
if(GET_UNDISCOVERED_NEIGHBOUR(skb))
ret = mpls_output_finish(skb);
else
ret = NS_HOOK(NS_IP_POST_ROUTING, PF_INET, skb, NULL,dev, mpls_output_finish);
}
return ret ;
}
static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct rtable *rt;
const struct iphdr *iph = ip_hdr(skb);
struct flowi4 fl4 = {
.flowi4_oif = inet_iif(skb),
.daddr = iph->saddr,
.saddr = iph->daddr,
.flowi4_tos = RT_CONN_FLAGS(sk),
.flowi4_proto = sk->sk_protocol,
.fl4_sport = dccp_hdr(skb)->dccph_dport,
.fl4_dport = dccp_hdr(skb)->dccph_sport,
};
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
if (IS_ERR(rt)) {
IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
return &rt->dst;
}
static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req)
{
int err = -1;
struct sk_buff *skb;
struct dst_entry *dst;
struct flowi4 fl4;
dst = inet_csk_route_req(sk, &fl4, req);
if (dst == NULL)
goto out;
skb = dccp_make_response(sk, dst, req);
if (skb != NULL) {
const struct inet_request_sock *ireq = inet_rsk(req);
struct dccp_hdr *dh = dccp_hdr(skb);
dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
ireq->ir_rmt_addr);
rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
rcu_dereference(ireq->ireq_opt));
rcu_read_unlock();
err = net_xmit_eval(err);
}
out:
dst_release(dst);
return err;
}
static int
br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *))
{
unsigned int mtu = ip_skb_dst_mtu(sk, skb);
struct iphdr *iph = ip_hdr(skb);
if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
(IPCB(skb)->frag_max_size &&
IPCB(skb)->frag_max_size > mtu))) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
return ip_do_fragment(net, sk, skb, output);
}
/*
This will route a SYN-ACK, i.e., the response to a request to open a
new connection.
*/
struct dst_entry *serval_ipv4_req_route(struct sock *sk,
struct request_sock *rsk,
int protocol,
u32 saddr,
u32 daddr)
{
struct rtable *rt;
struct ip_options *opt = NULL; /* inet_rsk(req)->opt; */
struct flowi fl;
serval_flow_init_output(&fl, sk->sk_bound_dev_if, sk->sk_mark,
RT_CONN_FLAGS(sk), 0, protocol,
#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,28))
inet_sk_flowi_flags(sk),
#else
0,
#endif
daddr, saddr, 0, 0);
serval_security_req_classify_flow(rsk, &fl);
rt = serval_ip_route_output_flow(sock_net(sk), &fl, sk, 0);
if (!rt)
goto no_route;
if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto route_err;
return route_dst(rt);
route_err:
ip_rt_put(rt);
no_route:
#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,25))
IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
#else
IP_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
#endif
return NULL;
}
int rpl_ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(OVS_VPORT_OUTPUT_PARAMS))
{
struct iphdr *iph;
int ptr;
struct net_device *dev;
struct sk_buff *skb2;
unsigned int mtu, hlen, left, len, ll_rs;
int offset;
__be16 not_last_frag;
struct rtable *rt = skb_rtable(skb);
int err = 0;
dev = rt->dst.dev;
/* for offloaded checksums cleanup checksum before fragmentation */
if (skb->ip_summed == CHECKSUM_PARTIAL &&
(err = skb_checksum_help(skb)))
goto fail;
/*
* Point into the IP datagram header.
*/
iph = ip_hdr(skb);
mtu = ip_skb_dst_mtu(skb);
if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu)
mtu = IPCB(skb)->frag_max_size;
/*
* Setup starting values.
*/
hlen = iph->ihl * 4;
mtu = mtu - hlen; /* Size of data space */
IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
/* When frag_list is given, use it. First, check its validity:
* some transformers could create wrong frag_list or break existing
* one, it is not prohibited. In this case fall back to copying.
*
* LATER: this step can be merged to real generation of fragments,
* we can switch to copy when see the first bad fragment.
*/
if (skb_has_frag_list(skb)) {
struct sk_buff *frag, *frag2;
int first_len = skb_pagelen(skb);
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
ip_is_fragment(iph) ||
skb_cloned(skb))
goto slow_path;
skb_walk_frags(skb, frag) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
}
skb->truesize -= frag->truesize;
}
/* Everything is OK. Generate! */
err = 0;
offset = 0;
frag = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
skb->data_len = first_len - skb_headlen(skb);
skb->len = first_len;
iph->tot_len = htons(first_len);
iph->frag_off = htons(IP_MF);
ip_send_check(iph);
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
skb_reset_transport_header(frag);
__skb_push(frag, hlen);
skb_reset_network_header(frag);
memcpy(skb_network_header(frag), iph, hlen);
iph = ip_hdr(frag);
iph->tot_len = htons(frag->len);
ip_copy_metadata(frag, skb);
if (offset == 0)
ip_options_fragment(frag);
offset += skb->len - hlen;
iph->frag_off = htons(offset>>3);
if (frag->next)
iph->frag_off |= htons(IP_MF);
/* Ready, complete checksum */
ip_send_check(iph);
}
err = OUTPUT(net, sk, skb);
if (!err)
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
break;
skb = frag;
frag = skb->next;
skb->next = NULL;
}
if (err == 0) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
return 0;
}
while (frag) {
skb = frag->next;
kfree_skb(frag);
frag = skb;
}
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
slow_path_clean:
skb_walk_frags(skb, frag2) {
if (frag2 == frag)
break;
frag2->sk = NULL;
frag2->destructor = NULL;
skb->truesize += frag2->truesize;
}
}
slow_path:
iph = ip_hdr(skb);
left = skb->len - hlen; /* Space per frame */
ptr = hlen; /* Where to start from */
ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
/*
* Fragment the datagram.
*/
offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
not_last_frag = iph->frag_off & htons(IP_MF);
/*
* Keep copying data until we run out.
*/
while (left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
len = mtu;
/* IF: we are not sending up to and including the packet end
then align the next start on an eight byte boundary */
if (len < left) {
len &= ~7;
}
/* Allocate buffer */
skb2 = alloc_skb(len + hlen + ll_rs, GFP_ATOMIC);
if (!skb2) {
err = -ENOMEM;
goto fail;
}
/*
* Set up data on packet
*/
ip_copy_metadata(skb2, skb);
skb_reserve(skb2, ll_rs);
skb_put(skb2, len + hlen);
skb_reset_network_header(skb2);
skb2->transport_header = skb2->network_header + hlen;
/*
* Charge the memory for the fragment to any owner
* it might possess
*/
if (skb->sk)
skb_set_owner_w(skb2, skb->sk);
/*
* Copy the packet header into the new buffer.
*/
skb_copy_from_linear_data(skb, skb_network_header(skb2), hlen);
/*
* Copy a block of the IP datagram.
*/
if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len))
BUG();
left -= len;
/*
* Fill in the new header fields.
*/
iph = ip_hdr(skb2);
iph->frag_off = htons((offset >> 3));
if (IPCB(skb)->flags & IPSKB_FRAG_PMTU)
iph->frag_off |= htons(IP_DF);
/* ANK: dirty, but effective trick. Upgrade options only if
* the segment to be fragmented was THE FIRST (otherwise,
* options are already fixed) and make it ONCE
* on the initial skb, so that all the following fragments
* will inherit fixed options.
*/
if (offset == 0)
ip_options_fragment(skb);
/*
* Added AC : If we are fragmenting a fragment that's not the
* last fragment then keep MF on each bit
*/
if (left > 0 || not_last_frag)
iph->frag_off |= htons(IP_MF);
ptr += len;
offset += len;
/*
* Put this fragment into the sending queue.
*/
iph->tot_len = htons(len + hlen);
ip_send_check(iph);
err = OUTPUT(net, sk, skb2);
if (err)
goto fail;
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
}
consume_skb(skb);
IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
return err;
fail:
kfree_skb(skb);
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
}
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = skb_rtable(skb);
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) &&
(ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->u.dst)));
goto drop;
}
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = ip_hdr(skb);
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
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;
}
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph;
struct rtable *rt;
struct ip_options * opt = &(IPCB(skb)->opt);
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = skb_rtable(skb);
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) &&
(ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->u.dst)));
goto drop;
}
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = ip_hdr(skb);
ip_decrease_ttl(iph);
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
sr_failed:
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
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;
}
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;
}
/* 会话转发发送报文前的分片处理 */
int ip_session_out_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
{
struct iphdr *iph;
int raw = 0;
int ptr;
struct net_device *dev = skb->dev;
struct sk_buff *skb2;
unsigned int mtu, hlen, left, len, ll_rs, pad;
int offset;
__be16 not_last_frag;
int err = 0;
struct nf_conn* ct = (struct nf_conn*)skb->nfct;
struct drv_ff_cache_info *ff_info =
&((struct ff_cache_info_ex*)ct)->ff_info[IP_CT_DIR_REPLY];
//u32 out_inf = ff_info->out_inf;
mtu = 1500;
iph = skb->nh.iph;
if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) {
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGFAILS);
if(g_icmp_status.fragment_unreach == IP_OPTION_SUPPORT)
{
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
}
kfree_skb(skb);
return -EMSGSIZE;
}
/*
* Setup starting values.
*/
hlen = iph->ihl * 4;
IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
/* When frag_list is given, use it. First, check its validity:
* some transformers could create wrong frag_list or break existing
* one, it is not prohibited. In this case fall back to copying.
*
* LATER: this step can be merged to real generation of fragments,
* we can switch to copy when see the first bad fragment.
*/
if (skb_shinfo(skb)->frag_list) {
struct sk_buff *frag;
int first_len = skb_pagelen(skb);
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
(iph->frag_off & htons(IP_MF|IP_OFFSET)) ||
skb_cloned(skb))
goto slow_path;
for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
goto slow_path;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path;
BUG_ON(frag->sk);
if (skb->sk) {
sock_hold(skb->sk);
frag->sk = skb->sk;
frag->destructor = sock_wfree;
skb->truesize -= frag->truesize;
}
}
/* Everything is OK. Generate! */
err = 0;
offset = 0;
frag = skb_shinfo(skb)->frag_list;
skb_shinfo(skb)->frag_list = NULL;
skb->data_len = first_len - skb_headlen(skb);
skb->len = first_len;
iph->tot_len = htons(first_len);
iph->frag_off = htons(IP_MF);
ip_send_check(iph);
/* process for session forward l2header */
skb_push(skb, ETH_HLEN);
memcpy(skb->data, (u8*)ff_info->gw_ether_mac, ETH_ALEN);
memcpy(skb->data+ETH_ALEN, (u8*)ff_info->gw_ether_mac+ETH_ALEN, ETH_ALEN);
memcpy(skb->data+2*ETH_ALEN, (u8*)ff_info->gw_ether_mac+2*ETH_ALEN, 2);
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
frag->h.raw = frag->data;
frag->nh.raw = __skb_push(frag, hlen);
memcpy(frag->nh.raw, iph, hlen);
iph = frag->nh.iph;
iph->tot_len = htons(frag->len);
ip_copy_metadata(frag, skb);
if (offset == 0)
ip_options_fragment(frag);
offset += skb->len - hlen - ETH_HLEN;
iph->frag_off = htons(offset>>3);
if (frag->next != NULL)
iph->frag_off |= htons(IP_MF);
/* Ready, complete checksum */
ip_send_check(iph);
/* process for session forward l2header */
skb_push(frag, ETH_HLEN);
memcpy(frag->data, (u8*)ff_info->gw_ether_mac, ETH_ALEN);
memcpy(frag->data+ETH_ALEN,
(u8*)ff_info->gw_ether_mac+ETH_ALEN, ETH_ALEN);
memcpy(frag->data+2*ETH_ALEN,
(u8*)ff_info->gw_ether_mac+2*ETH_ALEN, 2);
}
g_session_forward_count++;
err = output(skb);
if (!err)
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
break;
skb = frag;
frag = skb->next;
skb->next = NULL;
}
if (err == 0) {
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGOKS);
return 0;
}
while (frag) {
skb = frag->next;
kfree_skb(frag);
frag = skb;
}
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
slow_path:
left = skb->len - hlen; /* Space per frame */
ptr = raw + hlen; /* Where to start from */
/* for bridged IP traffic encapsulated inside f.e. a vlan header,
* we need to make room for the encapsulating header
*/
pad = nf_bridge_pad(skb);
ll_rs = ((ETH_HLEN+pad)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD;
mtu -= pad;
/*
* Fragment the datagram.
*/
offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
not_last_frag = iph->frag_off & htons(IP_MF);
/*
* Keep copying data until we run out.
*/
while(left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
len = mtu;
/* IF: we are not sending upto and including the packet end
then align the next start on an eight byte boundary */
if (len < left) {
len &= ~7;
}
/*
* Allocate buffer.
*/
if ((skb2 = alloc_skb(len+hlen+ll_rs, GFP_ATOMIC)) == NULL) {
NETDEBUG(KERN_INFO "IP: frag: no memory for new fragment!\n");
err = -ENOMEM;
goto fail;
}
/*
* Set up data on packet
*/
ip_copy_metadata(skb2, skb);
skb2->mac_len = skb->mac_len;
skb2->ff_flag = skb->ff_flag;
skb2->in_if = skb->in_if;
skb_reserve(skb2, ll_rs);
skb_put(skb2, len + hlen);
skb2->mac.raw = skb2->data - skb2->mac_len;
skb2->nh.raw = skb2->data;
skb2->h.raw = skb2->data + hlen;
/*
* Charge the memory for the fragment to any owner
* it might possess
*/
if (skb->sk)
skb_set_owner_w(skb2, skb->sk);
/*
* Copy the packet header into the new buffer.
*/
memcpy(skb2->nh.raw, skb->data, hlen);
/*
* Copy a block of the IP datagram.
*/
if (skb_copy_bits(skb, ptr, skb2->h.raw, len))
BUG();
left -= len;
/*
* Fill in the new header fields.
*/
iph = skb2->nh.iph;
iph->frag_off = htons((offset >> 3));
/* ANK: dirty, but effective trick. Upgrade options only if
* the segment to be fragmented was THE FIRST (otherwise,
* options are already fixed) and make it ONCE
* on the initial skb, so that all the following fragments
* will inherit fixed options.
*/
if (offset == 0)
ip_options_fragment(skb);
/*
* Added AC : If we are fragmenting a fragment that's not the
* last fragment then keep MF on each bit
*/
if (left > 0 || not_last_frag)
iph->frag_off |= htons(IP_MF);
ptr += len;
offset += len;
/*
* Put this fragment into the sending queue.
*/
iph->tot_len = htons(len + hlen);
ip_send_check(iph);
/* process for session forward l2header */
memcpy(skb2->mac.raw, (u8*)ff_info->gw_ether_mac, ETH_ALEN);
memcpy(skb2->mac.raw+ETH_ALEN, (u8*)ff_info->gw_ether_mac+ETH_ALEN, ETH_ALEN);
memcpy(skb2->mac.raw+2*ETH_ALEN, (u8*)ff_info->gw_ether_mac+2*ETH_ALEN, 2);
err = output(skb2);
if (err)
goto fail;
g_session_forward_count++;
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGCREATES);
}
kfree_skb(skb);
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGOKS);
return err;
fail:
kfree_skb(skb);
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
#ifdef CONFIG_NETFILTER_TABLE_INDEX
int verdict;
#endif
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = skb_rtable(skb);
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) &&
(ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->u.dst)));
goto drop;
}
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = ip_hdr(skb);
#ifdef CONFIG_AS_FASTPATH
/* ToS in route table is not actually that is in packet */
_route_add_hook(rt, iph->tos);
#endif
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
#ifdef CONFIG_NETFILTER_TABLE_INDEX
verdict = match_netfilter_table_index(
NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev,
p_netfilter_table_index);
if (-1 == verdict) /* not found, go along the old path */
return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
else{
if (verdict == NF_ACCEPT || verdict == NF_STOP)
return ip_forward_finish(skb);
else
goto drop;
/* We only recorded 3 kinds of results,
* NF_ACCEPT, NF_STOP, NF DROP.
* NF_DROP will be processed.
* we don't accelorate NF_QUEUE
*/
}
#endif /* end CONFIG_NETFILTER_TABLE_INDEX */
return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev,
rt->u.dst.dev, ip_forward_finish);
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
