/* Is the fragment too far ahead to be part of ipq? */
static inline int ip_frag_too_far(struct ipq *qp)
{
struct inet_peer *peer = qp->peer;
unsigned int max = sysctl_ipfrag_max_dist;
unsigned int start, end;
int rc;
if (!peer || !max)
return 0;
start = qp->rid;
end = atomic_inc_return(&peer->rid);
qp->rid = end;
rc = qp->q.fragments && (end - start) > max;
if (rc) {
struct net *net;
net = container_of(qp->q.net, struct net, ipv4.frags);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
}
return rc;
}
static inline int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options * opt = &(IPCB(skb)->opt);
IP_INC_STATS_BH(IpForwDatagrams);
if (opt->optlen == 0) {
#ifdef CONFIG_NET_FASTROUTE
struct rtable *rt = (struct rtable*)skb->dst;
if (rt->rt_flags&RTCF_FAST && !netdev_fastroute_obstacles) {
struct dst_entry *old_dst;
unsigned h = ((*(u8*)&rt->key.dst)^(*(u8*)&rt->key.src))&NETDEV_FASTROUTE_HMASK;
write_lock_irq(&skb->dev->fastpath_lock);
old_dst = skb->dev->fastpath[h];
skb->dev->fastpath[h] = dst_clone(&rt->u.dst);
write_unlock_irq(&skb->dev->fastpath_lock);
dst_release(old_dst);
}
#endif
return (ip_send(skb));
}
ip_forward_options(skb);
return (ip_send(skb));
}
static int br_parse_ip_options(struct sk_buff *skb)
{
const struct iphdr *iph;
struct net_device *dev = skb->dev;
u32 len;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
iph = ip_hdr(skb);
/* Basic sanity checks */
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
iph = ip_hdr(skb);
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto inhdr_error;
len = ntohs(iph->tot_len);
if (skb->len < len) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
} else if (len < (iph->ihl*4))
goto inhdr_error;
if (pskb_trim_rcsum(skb, len)) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto drop;
}
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
/* We should really parse IP options here but until
* somebody who actually uses IP options complains to
* us we'll just silently ignore the options because
* we're lazy!
*/
return 0;
inhdr_error:
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
drop:
return -1;
}
static int ip_rcv_finish(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (skb->dst == NULL) {
int err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos,
skb->dev);
if (unlikely(err)) {
if (err == -EHOSTUNREACH)
IP_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
else if (err == -ENETUNREACH)
IP_INC_STATS_BH(IPSTATS_MIB_INNOROUTES);
goto drop;
}
}
#ifdef CONFIG_NET_CLS_ROUTE
if (unlikely(skb->dst->tclassid)) {
struct ip_rt_acct *st = per_cpu_ptr(ip_rt_acct, smp_processor_id());
u32 idx = skb->dst->tclassid;
st[idx&0xFF].o_packets++;
st[idx&0xFF].o_bytes+=skb->len;
st[(idx>>16)&0xFF].i_packets++;
st[(idx>>16)&0xFF].i_bytes+=skb->len;
}
#endif
if (iph->ihl > 5 && ip_rcv_options(skb))
goto drop;
rt = skb->rtable;
if (rt->rt_type == RTN_MULTICAST)
IP_INC_STATS_BH(IPSTATS_MIB_INMCASTPKTS);
else if (rt->rt_type == RTN_BROADCAST)
IP_INC_STATS_BH(IPSTATS_MIB_INBCASTPKTS);
return dst_input(skb);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
static void inc_stats_ipv4(struct sk_buff *skb, int field)
{
if (is_error(inc_stats_validate(skb))) {
skb = skb_original_skb(skb);
if (is_error(inc_stats_validate(skb)))
return;
}
IP_INC_STATS_BH(dev_net(skb->dev), field);
}
int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
struct rtable *rt;
__be32 saddr;
int oif;
int err;
if (addr_len < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
sk_dst_reset(sk);
oif = sk->sk_bound_dev_if;
saddr = inet->inet_saddr;
if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
if (!oif)
oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
}
err = ip_route_connect(&rt, usin->sin_addr.s_addr, saddr,
RT_CONN_FLAGS(sk), oif,
sk->sk_protocol,
inet->inet_sport, usin->sin_port, sk, 1);
if (err) {
if (err == -ENETUNREACH)
IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return err;
}
if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) {
ip_rt_put(rt);
return -EACCES;
}
if (!inet->inet_saddr)
inet->inet_saddr = rt->rt_src; /* Update source address */
if (!inet->inet_rcv_saddr) {
inet->inet_rcv_saddr = rt->rt_src;
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
}
inet->inet_daddr = rt->rt_dst;
inet->inet_dport = usin->sin_port;
sk->sk_state = TCP_ESTABLISHED;
inet->inet_id = jiffies;
sk_dst_set(sk, &rt->dst);
return(0);
}
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 = skb_rtable(skb)->rt_iif,
.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_BH(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
return &rt->dst;
}
static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
struct request_values *rv_unused)
{
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->loc_addr,
ireq->rmt_addr);
err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
ireq->rmt_addr,
ireq->opt);
err = net_xmit_eval(err);
}
out:
dst_release(dst);
return err;
}
static inline int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options * opt = &(IPCB(skb)->opt);
IP_INC_STATS_BH(IPSTATS_MIB_OUTFORWDATAGRAMS);
if (unlikely(opt->optlen))
ip_forward_options(skb);
return dst_output(skb);
}
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
if (unlikely(opt->optlen))
ip_forward_options(skb);
return dst_output(skb);
}
static inline int ip_rcv_finish(struct sk_buff *skb)
{
struct iphdr *iph = skb->nh.iph;
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (likely(skb->dst == NULL)) {
/* TF1: CONFIG_VIPSEC */
/* Function which does all the IPSec multicast/broadcast processing */
if (ipsec_mcastforward_lookup_hook != NULL){
(*ipsec_mcastforward_lookup_hook)(skb);
}
/* TF1: CONFIG_VIPSEC */
int err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos,
skb->dev);
if (unlikely(err)) {
if (err == -EHOSTUNREACH)
IP_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
goto drop;
}
}
#ifdef CONFIG_NET_CLS_ROUTE
if (unlikely(skb->dst->tclassid)) {
struct ip_rt_acct *st = ip_rt_acct + 256*smp_processor_id();
u32 idx = skb->dst->tclassid;
st[idx&0xFF].o_packets++;
st[idx&0xFF].o_bytes+=skb->len;
st[(idx>>16)&0xFF].i_packets++;
st[(idx>>16)&0xFF].i_bytes+=skb->len;
}
#endif
if (iph->ihl > 5 && ip_rcv_options(skb))
goto drop;
return dst_input(skb);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
/*
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;
}
s32 mpls_forward(struct sk_buff*skb)
{
struct ip_options * opt = &(IPCB(skb)->opt);
MPLS_DEBUG_FORWARD("Entry mpls_forward.\n ");
MPLS_DEBUG_COUNTER_INC(mpls_forward);
if (FF_ENABLE)
{
/*Mpls not support fast route now, so, set linux forward flag.*/
skb->ff_flag = ff_set_flag(skb, DRV_FF_FLAG_LINUX_FORWARD);
}
IP_INC_STATS_BH(if_dev_vrf(skb->dst->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
if (unlikely(opt->optlen))
ip_forward_options(skb);
return dst_output(skb);
}
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options * opt = &(IPCB(skb)->opt);
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
if (unlikely(opt->optlen))
ip_forward_options(skb);
#ifdef CONFIG_NET_GIANFAR_FP
else {
struct rtable *rt = skb_rtable(skb);
#ifdef FASTPATH_DEBUG
if (printk_ratelimit())
printk(KERN_INFO" %s: rt = %p, rt->rt_flags = %x "
"(fast=%x), netdev_fastroute_ob=%d\n",
__func___, rt, rt ? rt->rt_flags : 0,
RTCF_FAST, netdev_fastroute_obstacles);
#endif
if ((rt->rt_flags & RTCF_FAST) && !netdev_fastroute_obstacles) {
struct dst_entry *old_dst;
unsigned h = gfar_fastroute_hash(*(u8 *)&rt->rt_dst,
*(u8 *)&rt->rt_src);
#ifdef FASTPATH_DEBUG
if (printk_ratelimit())
printk(KERN_INFO " h = %d (%d, %d)\n",
h, rt->rt_dst, rt->rt_src);
#endif
write_lock_irq(&skb->dev->fastpath_lock);
old_dst = skb->dev->fastpath[h];
skb->dev->fastpath[h] = dst_clone(&rt->u.dst);
write_unlock_irq(&skb->dev->fastpath_lock);
dst_release(old_dst);
}
}
#endif
return dst_output(skb);
}
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
int ihlen;
int err;
int sum_truesize;
u8 ecn;
ipq_kill(qp);
ecn = ip_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
}
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_nomem;
fp->next = head->next;
if (!fp->next)
qp->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, qp->q.fragments);
head->next = qp->q.fragments->next;
consume_skb(qp->q.fragments);
qp->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG_CB(head)->offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
len = ihlen + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_nomem;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
goto out_nomem;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
add_frag_mem_limit(&qp->q, clone->truesize);
}
skb_push(head, head->data - skb_network_header(head));
sum_truesize = head->truesize;
for (fp = head->next; fp;) {
bool headstolen;
int delta;
struct sk_buff *next = fp->next;
sum_truesize += fp->truesize;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
kfree_skb_partial(fp, headstolen);
} else {
if (!skb_shinfo(head)->frag_list)
skb_shinfo(head)->frag_list = fp;
head->data_len += fp->len;
head->len += fp->len;
head->truesize += fp->truesize;
}
fp = next;
}
sub_frag_mem_limit(&qp->q, sum_truesize);
head->next = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
IPCB(head)->frag_max_size = qp->q.max_size;
iph = ip_hdr(head);
/* max_size != 0 implies at least one fragment had IP_DF set */
iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
iph->tot_len = htons(len);
iph->tos |= ecn;
ip_send_check(iph);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
return 0;
out_nomem:
LIMIT_NETDEBUG(KERN_ERR pr_fmt("queue_glue: no memory for gluing queue %p\n"),
qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
return err;
}
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
int ihlen;
int err;
u8 ecn;
ipq_kill(qp);
ecn = ip_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
}
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_nomem;
fp->next = head->next;
if (!fp->next)
qp->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, qp->q.fragments);
head->next = qp->q.fragments->next;
consume_skb(qp->q.fragments);
qp->q.fragments = head;
}
WARN_ON(!head);
WARN_ON(FRAG_CB(head)->offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
len = ihlen + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_nomem;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
goto out_nomem;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
add_frag_mem_limit(qp->q.net, clone->truesize);
}
skb_shinfo(head)->frag_list = head->next;
skb_push(head, head->data - skb_network_header(head));
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
}
sub_frag_mem_limit(qp->q.net, head->truesize);
head->next = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
iph = ip_hdr(head);
iph->tot_len = htons(len);
iph->tos |= ecn;
/* When we set IP_DF on a refragmented skb we must also force a
* call to ip_fragment to avoid forwarding a DF-skb of size s while
* original sender only sent fragments of size f (where f < s).
*
* We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
* frag seen to avoid sending tiny DF-fragments in case skb was built
* from one very small df-fragment and one large non-df frag.
*/
if (qp->max_df_size == qp->q.max_size) {
IPCB(head)->flags |= IPSKB_FRAG_PMTU;
iph->frag_off = htons(IP_DF);
} else {
iph->frag_off = 0;
}
ip_send_check(iph);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
return 0;
out_nomem:
net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
return err;
}
static int ip_local_deliver_finish(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
__skb_pull(skb, ip_hdrlen(skb));
/* Point into the IP datagram, just past the header. */
skb_reset_transport_header(skb);
rcu_read_lock();
{
int protocol = ip_hdr(skb)->protocol;
int hash, raw;
const struct net_protocol *ipprot;
resubmit:
raw = raw_local_deliver(skb, protocol);
hash = protocol & (MAX_INET_PROTOS - 1);
ipprot = rcu_dereference(inet_protos[hash]);
if (ipprot != NULL) {
int ret;
if (!net_eq(net, &init_net) && !ipprot->netns_ok) {
if (net_ratelimit())
printk("%s: proto %d isn't netns-ready\n",
__func__, protocol);
kfree_skb(skb);
goto out;
}
if (!ipprot->no_policy) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
goto out;
}
nf_reset(skb);
}
ret = ipprot->handler(skb);
if (ret < 0) {
protocol = -ret;
goto resubmit;
}
IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw) {
if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP_INC_STATS_BH(net, IPSTATS_MIB_INUNKNOWNPROTOS);
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PROT_UNREACH, 0);
}
} else
IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
}
out:
rcu_read_unlock();
return 0;
}
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
int ihlen;
int err;
ipq_kill(qp);
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_nomem;
fp->next = head->next;
prev->next = fp;
skb_morph(head, qp->q.fragments);
head->next = qp->q.fragments->next;
kfree_skb(qp->q.fragments);
qp->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG_CB(head)->offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
len = ihlen + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
goto out_nomem;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frags(head)) {
struct sk_buff *clone;
int i, plen = 0;
if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
goto out_nomem;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i=0; i<skb_shinfo(head)->nr_frags; i++)
plen += skb_shinfo(head)->frags[i].size;
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
atomic_add(clone->truesize, &qp->q.net->mem);
}
skb_shinfo(head)->frag_list = head->next;
skb_push(head, head->data - skb_network_header(head));
atomic_sub(head->truesize, &qp->q.net->mem);
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
atomic_sub(fp->truesize, &qp->q.net->mem);
}
head->next = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
iph = ip_hdr(head);
iph->frag_off = 0;
iph->tot_len = htons(len);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
return 0;
out_nomem:
LIMIT_NETDEBUG(KERN_ERR "IP: queue_glue: no memory for gluing "
"queue %p\n", qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
if (net_ratelimit())
printk(KERN_INFO "Oversized IP packet from %pI4.\n",
&qp->saddr);
out_fail:
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
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 ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
int ihlen;
int err;
u8 ecn;
ipq_kill(qp);
ecn = ip4_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
}
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_nomem;
fp->next = head->next;
if (!fp->next)
qp->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, qp->q.fragments);
head->next = qp->q.fragments->next;
kfree_skb(qp->q.fragments);
qp->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG_CB(head)->offset != 0);
ihlen = ip_hdrlen(head);
len = ihlen + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
goto out_nomem;
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
goto out_nomem;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
atomic_add(clone->truesize, &qp->q.net->mem);
}
skb_shinfo(head)->frag_list = head->next;
skb_push(head, head->data - skb_network_header(head));
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
}
atomic_sub(head->truesize, &qp->q.net->mem);
head->next = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
iph = ip_hdr(head);
iph->frag_off = 0;
iph->tot_len = htons(len);
iph->tos |= ecn;
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
return 0;
out_nomem:
LIMIT_NETDEBUG(KERN_ERR pr_fmt("queue_glue: no memory for gluing queue %p\n"),
qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
if (net_ratelimit())
pr_info("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
return err;
}
int ip_rcv_finish(struct sk_buff *skb)
{
struct iphdr *iph = skb->nh.iph;
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (skb->dst == NULL) {
int err = 1;
if(g_session_forward_enable)
{
if (skb->nfct && IP_CT_DIR_REPLY == CTINFO2DIR(skb->nfctinfo)
&& !(((struct ff_cache_info_ex*)skb->nfct)->ff_info[IP_CT_DIR_ORIGINAL].flag & DRV_FF_FLAG_LINUX)
&& !is_vpn_pkt(skb)){
sessfw_debug(1, "--- don't lookup route ---\n" TUPLE_INFO(
&((struct ff_cache_info_ex*)skb->nfct)->ct.tuplehash[IP_CT_DIR_ORIGINAL].tuple,
&((struct ff_cache_info_ex*)skb->nfct)->ct.tuplehash[IP_CT_DIR_REPLY].tuple));
err = 0;
goto route_label;
}
#ifdef CONFIG_NETSESSION
if (skb->ns && NS_DIR_REPLY == NSINFO2DIR(skb->nsinfo) &&
!(((struct net_session *)skb->ns)->ff_info[NS_DIR_ORIGINAL].flag & NS_FF_LINUX)){
err = 0;
goto route_label;
}
#endif
}
if (0 != err)
{
sessfw_debug(2, "--- lookup route ---\n" TUPLE_INFO(
&((struct ff_cache_info_ex*)skb->nfct)->ct.tuplehash[IP_CT_DIR_ORIGINAL].tuple,
&((struct ff_cache_info_ex*)skb->nfct)->ct.tuplehash[IP_CT_DIR_REPLY].tuple));
err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos,
skb->dev);
}
route_label:
if (unlikely(err)) {
if (err == -EHOSTUNREACH)
IP_INC_STATS_BH(if_dev_vrf(skb->dev), IPSTATS_MIB_INADDRERRORS);
goto drop;
}
}
if (iph->ihl > 5 && ip_rcv_options(skb))
{
goto drop;
}
//goto drop;
/*A new entry of mcast packet. add by wangdi*/
if (MULTICAST(iph->daddr))
{
return ipv4_mcast_rcv(skb, iph);
}
else if (g_session_forward_enable)
{
s32 ret;
ret = session_forward_fix[ns_mode](skb);
if (ret != 2)
return ret;
else
return dst_input(skb);/* 没匹配上会话转发 */
}
else
return dst_input(skb);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct iphdr *iph;
/* Code for SYNSNOOP Starts here */
struct tcphdr *tcph;
/* Code for SYNSNOOP Ends here */
u32 len;
/* Code for SYNSNOOP Starts here */
iph = ip_hdr(skb);
tcph = tcp_hdr(skb);
if((iph->protocol == IPPROTO_TCP) && (tcph->syn == TCP_FLAG_SYN))
if(decide(tcph->dest) == 0)
goto drop;
/* Code for SYNSNOOP Ends here */
/* When the interface is in promisc. mode, drop all the crap
* that it receives, do not try to analyse it.
*/
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INRECEIVES);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto out;
}
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
iph = ip_hdr(skb);
/*
* RFC1122: 3.2.1.2 MUST silently discard any IP frame that fails the checksum.
*
* Is the datagram acceptable?
*
* 1. Length at least the size of an ip header
* 2. Version of 4
* 3. Checksums correctly. [Speed optimisation for later, skip loopback checksums]
* 4. Doesn't have a bogus length
*/
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
iph = ip_hdr(skb);
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto inhdr_error;
len = ntohs(iph->tot_len);
if (skb->len < len) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
} else if (len < (iph->ihl*4))
goto inhdr_error;
/* Our transport medium may have padded the buffer out. Now we know it
* is IP we can trim to the true length of the frame.
* Note this now means skb->len holds ntohs(iph->tot_len).
*/
if (pskb_trim_rcsum(skb, len)) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto drop;
}
/* Remove any debris in the socket control block */
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
return NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, dev, NULL,
ip_rcv_finish);
inhdr_error:
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
drop:
kfree_skb(skb);
out:
return NET_RX_DROP;
}
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;
}
/*
* Main IP Receive routine.
*/
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct iphdr *iph;
u32 len;
u32 ret = 0;
char *raw;
struct udphdr *uh;
/* When the interface is in promisc. mode, drop all the crap
* that it receives, do not try to analyse it.
*/
raw = (char*)skb->nh.iph + skb->nh.iph->ihl *4;
uh = (struct udphdr *)raw;
/* just for debug... */
SNIFFER_PACKET(SNIFFER_MODULE_IP, skb, in, NF_ACCEPT);
skb->vid = 0;
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
if (skb->ucbitflag & SKB_FLAG_MPLS_PACKET)
{
dev = __if_dev_get_by_index((IF_DEV_TYPE_LO << 24) | skb->fpga_vrf_id);
if (dev)
{
skb->dev = dev;
skb->iif = (IF_DEV_TYPE_LO << 24) | skb->fpga_vrf_id;
}
else
{
skb->litevrf_id = skb->fpga_vrf_id;
}
}
IP_INC_STATS_BH(if_dev_vrf(dev), IPSTATS_MIB_INRECEIVES);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
IP_INC_STATS_BH(if_dev_vrf(dev), IPSTATS_MIB_INDISCARDS);
goto out;
}
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
iph = skb->nh.iph;
/*
* RFC1122: 3.1.2.2 MUST silently discard any IP frame that fails the checksum.
*
* Is the datagram acceptable?
*
* 1. Length at least the size of an ip header
* 2. Version of 4
* 3. Checksums correctly. [Speed optimisation for later, skip loopback checksums]
* 4. Doesn't have a bogus length
*/
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
iph = skb->nh.iph;
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto inhdr_error;
len = ntohs(iph->tot_len);
if (skb->len < len || len < (iph->ihl*4))
goto inhdr_error;
/* Our transport medium may have padded the buffer out. Now we know it
* is IP we can trim to the true length of the frame.
* Note this now means skb->len holds ntohs(iph->tot_len).
*/
if (pskb_trim_rcsum(skb, len)) {
IP_INC_STATS_BH(if_dev_vrf(dev), IPSTATS_MIB_INDISCARDS);
goto drop;
}
if(0 == skb->litevrf_id)
{
skb->litevrf_id = if_dev_litevrf_id(skb->dev);
}
if (skb->nh.iph->ttl == 0 && g_icmp_status.exc_ttl == IP_OPTION_SUPPORT)
{
ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, skb->dev);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
goto drop;
}
#ifdef CONFIG_NLM_NET_OPTS
*(uint64_t *)(unsigned long)IPCB(skb) = 0;
*(uint64_t *)((unsigned long)IPCB(skb)+8) = 0;
#else
/* Remove any debris in the socket control block */
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
#endif
if(IPPROTO_RSVP == iph->protocol)
{
__rsvp_input__(skb);
return NF_STOLEN;
}
/* web认证pre_routing入口 */
if(sg_webauth_switch)
{
if (NULL != conplat_handle_webauth)
{
ret = conplat_handle_webauth(NF_IP_PRE_ROUTING, &skb, dev, NULL, NULL);
if (NF_DROP == ret)
{
goto drop;
}
if (NF_STOLEN == ret)
{
return NF_STOLEN;
}
}
}
/*web监听pre_routing 入口*/
if((!sg_webauth_switch || (NF_REPEAT == ret))&& (NULL != conplat_handle_web_listen))
{
ret = conplat_handle_web_listen(NF_IP_PRE_ROUTING, &skb, dev, NULL, NULL);
if (NF_DROP == ret)
{
goto drop;
}
if (NF_STOLEN == ret)
{
return NF_STOLEN;
}
}
if(GET_UNDISCOVERED_NEIGHBOUR(skb))
return ip_rcv_finish(skb);
/*Packet route for mpls*/
if(ip_route_mpls(skb))
{
dev = init_vrf.loopback_dev;
}
return NS_HOOK(NS_IP_PRE_ROUTING, PF_INET, skb, dev, NULL, ip_rcv_finish);
inhdr_error:
IP_INC_STATS_BH(if_dev_vrf(dev), IPSTATS_MIB_INHDRERRORS);
drop:
kfree_skb(skb);
out:
return NET_RX_DROP;
}
/*
* Main IP Receive routine.
*/
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
{
struct iphdr *iph;
/* When the interface is in promisc. mode, drop all the crap
* that it receives, do not try to analyse it.
*/
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
IP_INC_STATS_BH(IpInReceives);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
goto out;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
iph = skb->nh.iph;
/*
* RFC1122: 3.1.2.2 MUST silently discard any IP frame that fails the checksum.
*
* Is the datagram acceptable?
*
* 1. Length at least the size of an ip header
* 2. Version of 4
* 3. Checksums correctly. [Speed optimisation for later, skip loopback checksums]
* 4. Doesn't have a bogus length
*/
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
iph = skb->nh.iph;
if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
goto inhdr_error;
{
__u32 len = ntohs(iph->tot_len);
if (skb->len < len || len < (iph->ihl<<2))
goto inhdr_error;
/* Our transport medium may have padded the buffer out. Now we know it
* is IP we can trim to the true length of the frame.
* Note this now means skb->len holds ntohs(iph->tot_len).
*/
if (skb->len > len) {
__pskb_trim(skb, len);
if (skb->ip_summed == CHECKSUM_HW)
skb->ip_summed = CHECKSUM_NONE;
}
}
return NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, dev, NULL,
ip_rcv_finish);
inhdr_error:
IP_INC_STATS_BH(IpInHdrErrors);
drop:
kfree_skb(skb);
out:
return NET_RX_DROP;
}
static inline int ip_rcv_finish(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct iphdr *iph = skb->nh.iph;
DEENC_CHECK();
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (skb->dst == NULL) {
DEENC_CHECK();
if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))
goto drop;
}
#ifdef CONFIG_NET_CLS_ROUTE
if (skb->dst->tclassid) {
struct ip_rt_acct *st = ip_rt_acct + 256*smp_processor_id();
u32 idx = skb->dst->tclassid;
st[idx&0xFF].o_packets++;
st[idx&0xFF].o_bytes+=skb->len;
st[(idx>>16)&0xFF].i_packets++;
st[(idx>>16)&0xFF].i_bytes+=skb->len;
}
#endif
if (iph->ihl > 5) {
struct ip_options *opt;
DEENC_CHECK();
/* It looks as overkill, because not all
IP options require packet mangling.
But it is the easiest for now, especially taking
into account that combination of IP options
and running sniffer is extremely rare condition.
--ANK (980813)
*/
if (skb_cow(skb, skb_headroom(skb)))
goto drop;
iph = skb->nh.iph;
if (ip_options_compile(NULL, skb))
goto inhdr_error;
opt = &(IPCB(skb)->opt);
if (opt->srr) {
struct in_device *in_dev = in_dev_get(dev);
if (in_dev) {
if (!IN_DEV_SOURCE_ROUTE(in_dev)) {
if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
printk(KERN_INFO "source route option %u.%u.%u.%u -> %u.%u.%u.%u\n",
NIPQUAD(iph->saddr), NIPQUAD(iph->daddr));
in_dev_put(in_dev);
goto drop;
}
in_dev_put(in_dev);
}
if (ip_options_rcv_srr(skb))
goto drop;
}
}
DEENC_CHECK();
return skb->dst->input(skb);
inhdr_error:
IP_INC_STATS_BH(IpInHdrErrors);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
int ip_local_deliver_finish(struct sk_buff *skb)
{
int ihl = skb->nh.iph->ihl*4;
struct nf_conn *ct = (struct nf_conn *)skb->nfct;
struct vrf *vrf = if_dev_vrf(skb->dev);
__skb_pull(skb, ihl);
skb->h.raw = skb->data;
if(ipsec_data_packet(skb))
{
return ipsec_receive_skb(skb);
}
/* 上送本机的报文，若经过流分类，则需要下发快转表项
如果是ipsec数据报文则不需要下发快转表，数据报文会在后面
下发快转表*/
if (ct && test_bit(IPS_CONFIRMED_BIT, &ct->status))
{
if (0 == smp_processor_id ())
{
NF_GET_CPU(ct) = 0;
}
if(ipsec_udp_float_packet(skb))
{
skb->ff_flag = ff_set_flag(skb, DRV_FF_FLAG_IPSEC_DPCRYPT);
skb->ff_flag = ff_clr_flag(skb, DRV_FF_FLAG_LINUX);
}
else
{
skb->ff_flag = ff_set_flag(skb, DRV_FF_FLAG_LINUX);
}
if(nf_ct_tcp_loose)
{
ff_items_add_for_simple_state(skb);
}
else
{
ff_items_add_basic_on_session(skb);
}
}
if (ipsec_conn_packet(skb))
{
#ifdef CONFIG_NETSESSION
struct net_session *ns = (struct net_session *)(skb->ns);
if(ns)
{
ns_ff_set_flag(skb, NS_FF_IPSEC_DPCRYPT);
}
#endif
ipsec_pkt_send2user(skb);
return 0;
}
rcu_read_lock();
{
/* Note: See raw.c and net/raw.h, RAWV4_HTABLE_SIZE==MAX_INET_PROTOS */
int protocol = skb->nh.iph->protocol;
int hash, raw;
struct net_protocol *ipprot;
resubmit:
raw = raw_local_deliver(skb, protocol);
hash = protocol & (MAX_INET_PROTOS - 1);
if ((ipprot = rcu_dereference(inet_protos[hash])) != NULL) {
int ret;
if (!ipprot->no_policy) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
goto out;
}
nf_reset(skb);
ns_reset(skb);
}
conplat_bh_disable();
ret = ipprot->handler(skb);
conplat_bh_enable();
if (ret < 0) {
protocol = -ret;
goto resubmit;
}
IP_INC_STATS_BH(vrf, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw) {
if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP_INC_STATS_BH(vrf, IPSTATS_MIB_INUNKNOWNPROTOS);
if(g_icmp_status.prot_unreach == IP_OPTION_SUPPORT)
{
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PROT_UNREACH, 0);
}
}
} else
IP_INC_STATS_BH(vrf, IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
}
out:
rcu_read_unlock();
return 0;
}
/*
* Main IP Receive routine.
*/
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
const struct iphdr *iph;
u32 len;
/* When the interface is in promisc. mode, drop all the crap
* that it receives, do not try to analyse it.
*/
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
IP_UPD_PO_STATS_BH(dev_net(dev), IPSTATS_MIB_IN, skb->len);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto out;
}
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
iph = ip_hdr(skb);
/*
* RFC1122: 3.2.1.2 MUST silently discard any IP frame that fails the checksum.
*
* Is the datagram acceptable?
*
* 1. Length at least the size of an ip header
* 2. Version of 4
* 3. Checksums correctly. [Speed optimisation for later, skip loopback checksums]
* 4. Doesn't have a bogus length
*/
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1);
BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0);
BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE);
IP_ADD_STATS_BH(dev_net(dev),
IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
iph = ip_hdr(skb);
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto csum_error;
len = ntohs(iph->tot_len);
if (skb->len < len) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
} else if (len < (iph->ihl*4))
goto inhdr_error;
/* Our transport medium may have padded the buffer out. Now we know it
* is IP we can trim to the true length of the frame.
* Note this now means skb->len holds ntohs(iph->tot_len).
*/
if (pskb_trim_rcsum(skb, len)) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto drop;
}
skb->transport_header = skb->network_header + iph->ihl*4;
/* Remove any debris in the socket control block */
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, dev, NULL,
ip_rcv_finish);
csum_error:
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_CSUMERRORS);
inhdr_error:
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
drop:
kfree_skb(skb);
out:
return NET_RX_DROP;
}
int ip_forward(struct sk_buff *skb)
{
struct net_device *dev2; /* Output device */
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
unsigned short mtu;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb->ip_summed = CHECKSUM_NONE;
/*
* 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.
*/
iph = skb->nh.iph;
rt = (struct rtable*)skb->dst;
if (iph->ttl <= 1)
goto too_many_hops;
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
/*
* Having picked a route we can now send the frame out
* after asking the firewall permission to do so.
*/
skb->priority = rt_tos2priority(iph->tos);
dev2 = rt->u.dst.dev;
mtu = rt->u.dst.pmtu;
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr)
ip_rt_send_redirect(skb);
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, dev2->hard_header_len))
goto drop;
iph = skb->nh.iph;
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now may allocate a new buffer, and copy the datagram into it.
* If the indicated interface is up and running, kick it.
*/
if (skb->len > mtu && (ntohs(iph->frag_off) & IP_DF))
goto frag_needed;
#ifdef CONFIG_IP_ROUTE_NAT
if (rt->rt_flags & RTCF_NAT) {
if (ip_do_nat(skb)) {
kfree_skb(skb);
return NET_RX_BAD;
}
}
#endif
return NF_HOOK(PF_INET, NF_IP_FORWARD, skb, skb->dev, dev2,
ip_forward_finish);
frag_needed:
IP_INC_STATS_BH(IpFragFails);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
goto drop;
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... */
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
static int br_parse_ip_options(struct sk_buff *skb)
{
struct ip_options *opt;
const struct iphdr *iph;
struct net_device *dev = skb->dev;
u32 len;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
iph = ip_hdr(skb);
opt = &(IPCB(skb)->opt);
/* Basic sanity checks */
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
iph = ip_hdr(skb);
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto inhdr_error;
len = ntohs(iph->tot_len);
if (skb->len < len) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
} else if (len < (iph->ihl*4))
goto inhdr_error;
if (pskb_trim_rcsum(skb, len)) {
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto drop;
}
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
if (iph->ihl == 5)
return 0;
opt->optlen = iph->ihl*4 - sizeof(struct iphdr);
if (ip_options_compile(dev_net(dev), opt, skb))
goto inhdr_error;
/* Check correct handling of SRR option */
if (unlikely(opt->srr)) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
if (in_dev && !IN_DEV_SOURCE_ROUTE(in_dev))
goto drop;
if (ip_options_rcv_srr(skb))
goto drop;
}
return 0;
inhdr_error:
IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
drop:
return -1;
}
static inline int ip_local_deliver_finish(struct sk_buff *skb)
{
int ihl = skb->nh.iph->ihl*4;
#ifdef CONFIG_NETFILTER_DEBUG
nf_debug_ip_local_deliver(skb);
#endif /*CONFIG_NETFILTER_DEBUG*/
__skb_pull(skb, ihl);
/* Free reference early: we don't need it any more, and it may
hold ip_conntrack module loaded indefinitely. */
nf_reset(skb);
/* Point into the IP datagram, just past the header. */
skb->h.raw = skb->data;
rcu_read_lock();
{
/* Note: See raw.c and net/raw.h, RAWV4_HTABLE_SIZE==MAX_INET_PROTOS */
int protocol = skb->nh.iph->protocol;
int hash;
struct sock *raw_sk;
struct net_protocol *ipprot;
resubmit:
hash = protocol & (MAX_INET_PROTOS - 1);
raw_sk = sk_head(&raw_v4_htable[hash]);
/* If there maybe a raw socket we must check - if not we
* don't care less
*/
if (raw_sk)
raw_v4_input(skb, skb->nh.iph, hash);
if ((ipprot = rcu_dereference(inet_protos[hash])) != NULL) {
int ret;
if (!ipprot->no_policy &&
!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
goto out;
}
ret = ipprot->handler(skb);
if (ret < 0) {
protocol = -ret;
goto resubmit;
}
IP_INC_STATS_BH(IPSTATS_MIB_INDELIVERS);
} else {
if (!raw_sk) {
if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP_INC_STATS_BH(IPSTATS_MIB_INUNKNOWNPROTOS);
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PROT_UNREACH, 0);
}
} else
IP_INC_STATS_BH(IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
}
out:
rcu_read_unlock();
return 0;
}
