static int ip_rcv_finish(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
const struct net_protocol *ipprot;
int protocol = iph->protocol;
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot && ipprot->early_demux) {
ipprot->early_demux(skb);
/* must reload iph, skb->head might have changed */
iph = ip_hdr(skb);
}
}
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (!skb_dst(skb)) {
int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev);
if (unlikely(err)) {
if (err == -EXDEV)
NET_INC_STATS_BH(dev_net(skb->dev),
LINUX_MIB_IPRPFILTER);
goto drop;
}
}
#ifdef CONFIG_IP_ROUTE_CLASSID
if (unlikely(skb_dst(skb)->tclassid)) {
struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
u32 idx = skb_dst(skb)->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(skb);
if (rt->rt_type == RTN_MULTICAST) {
IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INMCAST,
skb->len);
} else if (rt->rt_type == RTN_BROADCAST)
IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INBCAST,
skb->len);
return dst_input(skb);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
static void ip_expire(unsigned long arg)
{
struct ipq *qp;
struct net *net;
qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
spin_lock(&qp->q.lock);
if (qp->q.flags & INET_FRAG_COMPLETE)
goto out;
ipq_kill(qp);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
if (!(qp->q.flags & INET_FRAG_EVICTED)) {
struct sk_buff *head = qp->q.fragments;
const struct iphdr *iph;
int err;
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
goto out;
rcu_read_lock();
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out_rcu_unlock;
/* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
if (err)
goto out_rcu_unlock;
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (qp->user == IP_DEFRAG_AF_PACKET ||
((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
(qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
(skb_rtable(head)->rt_type != RTN_LOCAL)))
goto out_rcu_unlock;
/* Send an ICMP "Fragment Reassembly Timeout" message. */
icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
out_rcu_unlock:
rcu_read_unlock();
}
out:
spin_unlock(&qp->q.lock);
ipq_put(qp);
}
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(skb) == NULL) {
int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev);
if (unlikely(err)) {
if (err == -EHOSTUNREACH)
IP_INC_STATS_BH(dev_net(skb->dev),
IPSTATS_MIB_INADDRERRORS);
else if (err == -ENETUNREACH)
IP_INC_STATS_BH(dev_net(skb->dev),
IPSTATS_MIB_INNOROUTES);
else if (err == -EXDEV)
NET_INC_STATS_BH(dev_net(skb->dev),
LINUX_MIB_IPRPFILTER);
goto drop;
}
}
#ifdef CONFIG_IP_ROUTE_CLASSID
if (unlikely(skb_dst(skb)->tclassid)) {
struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
u32 idx = skb_dst(skb)->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(skb);
if (rt->rt_type == RTN_MULTICAST) {
IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INMCAST,
skb->len);
} else if (rt->rt_type == RTN_BROADCAST)
IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INBCAST,
skb->len);
return dst_input(skb);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
static void ip_expire(unsigned long arg)
{
struct ipq *qp;
struct net *net;
qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
spin_lock(&qp->q.lock);
if (qp->q.last_in & INET_FRAG_COMPLETE)
goto out;
ipq_kill(qp);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) {
struct sk_buff *head = qp->q.fragments;
const struct iphdr *iph;
int err;
rcu_read_lock();
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out_rcu_unlock;
/* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
if (err)
goto out_rcu_unlock;
if (qp->user == IP_DEFRAG_AF_PACKET ||
(qp->user == IP_DEFRAG_CONNTRACK_IN &&
skb_rtable(head)->rt_type != RTN_LOCAL))
goto out_rcu_unlock;
icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
out_rcu_unlock:
rcu_read_unlock();
}
out:
spin_unlock(&qp->q.lock);
ipq_put(qp);
}
static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb)
{
if (skb_dst(skb) == NULL) {
const struct iphdr *iph = ip_hdr(skb);
if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev))
goto drop;
}
return dst_input(skb);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
if (!skb_dst(skb)) {
const struct iphdr *iph = ip_hdr(skb);
if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev))
goto drop;
}
if (xfrm_trans_queue(skb, xfrm4_rcv_encap_finish2))
goto drop;
return 0;
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
static void ip_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct ipq *qp;
struct net *net;
qp = container_of(frag, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
rcu_read_lock();
spin_lock(&qp->q.lock);
if (qp->q.flags & INET_FRAG_COMPLETE)
goto out;
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
if (!inet_frag_evicting(&qp->q)) {
struct sk_buff *clone, *head = qp->q.fragments;
const struct iphdr *iph;
int err;
__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
goto out;
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out;
/* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
if (err)
goto out;
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (frag_expire_skip_icmp(qp->user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
clone = skb_clone(head, GFP_ATOMIC);
/* Send an ICMP "Fragment Reassembly Timeout" message. */
if (clone) {
spin_unlock(&qp->q.lock);
icmp_send(clone, ICMP_TIME_EXCEEDED,
ICMP_EXC_FRAGTIME, 0);
consume_skb(clone);
goto out_rcu_unlock;
}
}
out:
spin_unlock(&qp->q.lock);
out_rcu_unlock:
rcu_read_unlock();
ipq_put(qp);
}
static int arp_process(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct arphdr *arp;
unsigned char *arp_ptr;
struct rtable *rt;
unsigned char *sha;
__be32 sip, tip;
u16 dev_type = dev->type;
int addr_type;
struct neighbour *n;
struct net *net = dev_net(dev);
if (in_dev == NULL)
goto out;
arp = arp_hdr(skb);
switch (dev_type) {
default:
if (arp->ar_pro != htons(ETH_P_IP) ||
htons(dev_type) != arp->ar_hrd)
goto out;
break;
case ARPHRD_ETHER:
case ARPHRD_IEEE802_TR:
case ARPHRD_FDDI:
case ARPHRD_IEEE802:
if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
arp->ar_pro != htons(ETH_P_IP))
goto out;
break;
case ARPHRD_AX25:
if (arp->ar_pro != htons(AX25_P_IP) ||
arp->ar_hrd != htons(ARPHRD_AX25))
goto out;
break;
case ARPHRD_NETROM:
if (arp->ar_pro != htons(AX25_P_IP) ||
arp->ar_hrd != htons(ARPHRD_NETROM))
goto out;
break;
}
if (arp->ar_op != htons(ARPOP_REPLY) &&
arp->ar_op != htons(ARPOP_REQUEST))
goto out;
arp_ptr = (unsigned char *)(arp + 1);
sha = arp_ptr;
arp_ptr += dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4;
arp_ptr += dev->addr_len;
memcpy(&tip, arp_ptr, 4);
if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
goto out;
if (dev_type == ARPHRD_DLCI)
sha = dev->broadcast;
if (sip == 0) {
if (arp->ar_op == htons(ARPOP_REQUEST) &&
inet_addr_type(net, tip) == RTN_LOCAL &&
!arp_ignore(in_dev, sip, tip))
arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
dev->dev_addr, sha);
goto out;
}
if (arp->ar_op == htons(ARPOP_REQUEST) &&
ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb);
addr_type = rt->rt_type;
if (addr_type == RTN_LOCAL) {
int dont_send;
dont_send = arp_ignore(in_dev, sip, tip);
if (!dont_send && IN_DEV_ARPFILTER(in_dev))
dont_send = arp_filter(sip, tip, dev);
if (!dont_send) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n) {
arp_send(ARPOP_REPLY, ETH_P_ARP, sip,
dev, tip, sha, dev->dev_addr,
sha);
neigh_release(n);
}
}
goto out;
} else if (IN_DEV_FORWARD(in_dev)) {
if (addr_type == RTN_UNICAST &&
(arp_fwd_proxy(in_dev, dev, rt) ||
arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
(rt->dst.dev != dev &&
pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n)
neigh_release(n);
if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED ||
skb->pkt_type == PACKET_HOST ||
in_dev->arp_parms->proxy_delay == 0) {
arp_send(ARPOP_REPLY, ETH_P_ARP, sip,
dev, tip, sha, dev->dev_addr,
sha);
} else {
pneigh_enqueue(&arp_tbl,
in_dev->arp_parms, skb);
return 0;
}
goto out;
}
}
}
n = __neigh_lookup(&arp_tbl, &sip, dev, 0);
if (IN_DEV_ARP_ACCEPT(in_dev)) {
if (n == NULL &&
(arp->ar_op == htons(ARPOP_REPLY) ||
(arp->ar_op == htons(ARPOP_REQUEST) && tip == sip)) &&
inet_addr_type(net, sip) == RTN_UNICAST)
n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
}
if (n) {
int state = NUD_REACHABLE;
int override;
override = time_after(jiffies, n->updated + n->parms->locktime);
if (arp->ar_op != htons(ARPOP_REPLY) ||
skb->pkt_type != PACKET_HOST)
state = NUD_STALE;
neigh_update(n, sha, state,
override ? NEIGH_UPDATE_F_OVERRIDE : 0);
neigh_release(n);
}
static int arp_process(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct arphdr *arp;
unsigned char *arp_ptr;
struct rtable *rt;
unsigned char *sha;
__be32 sip, tip;
u16 dev_type = dev->type;
int addr_type;
struct neighbour *n;
struct net *net = dev_net(dev);
/* arp_rcv below verifies the ARP header and verifies the device
* is ARP'able.
*/
if (in_dev == NULL)
goto out;
arp = arp_hdr(skb);
switch (dev_type) {
default:
if (arp->ar_pro != htons(ETH_P_IP) ||
htons(dev_type) != arp->ar_hrd)
goto out;
break;
case ARPHRD_ETHER:
case ARPHRD_IEEE802_TR:
case ARPHRD_FDDI:
case ARPHRD_IEEE802:
/*
* ETHERNET, Token Ring and Fibre Channel (which are IEEE 802
* devices, according to RFC 2625) devices will accept ARP
* hardware types of either 1 (Ethernet) or 6 (IEEE 802.2).
* This is the case also of FDDI, where the RFC 1390 says that
* FDDI devices should accept ARP hardware of (1) Ethernet,
* however, to be more robust, we'll accept both 1 (Ethernet)
* or 6 (IEEE 802.2)
*/
if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
arp->ar_pro != htons(ETH_P_IP))
goto out;
break;
case ARPHRD_AX25:
if (arp->ar_pro != htons(AX25_P_IP) ||
arp->ar_hrd != htons(ARPHRD_AX25))
goto out;
break;
case ARPHRD_NETROM:
if (arp->ar_pro != htons(AX25_P_IP) ||
arp->ar_hrd != htons(ARPHRD_NETROM))
goto out;
break;
}
/* Understand only these message types */
if (arp->ar_op != htons(ARPOP_REPLY) &&
arp->ar_op != htons(ARPOP_REQUEST))
goto out;
/*
* Extract fields
*/
arp_ptr = (unsigned char *)(arp + 1);
sha = arp_ptr;
arp_ptr += dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4;
arp_ptr += dev->addr_len;
memcpy(&tip, arp_ptr, 4);
/*
* Check for bad requests for 127.x.x.x and requests for multicast
* addresses. If this is one such, delete it.
*/
if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
goto out;
/*
* Special case: We must set Frame Relay source Q.922 address
*/
if (dev_type == ARPHRD_DLCI)
sha = dev->broadcast;
/*
* Process entry. The idea here is we want to send a reply if it is a
* request for us or if it is a request for someone else that we hold
* a proxy for. We want to add an entry to our cache if it is a reply
* to us or if it is a request for our address.
* (The assumption for this last is that if someone is requesting our
* address, they are probably intending to talk to us, so it saves time
* if we cache their address. Their address is also probably not in
* our cache, since ours is not in their cache.)
*
* Putting this another way, we only care about replies if they are to
* us, in which case we add them to the cache. For requests, we care
* about those for us and those for our proxies. We reply to both,
* and in the case of requests for us we add the requester to the arp
* cache.
*/
/* Special case: IPv4 duplicate address detection packet (RFC2131) */
if (sip == 0) {
if (arp->ar_op == htons(ARPOP_REQUEST) &&
inet_addr_type(net, tip) == RTN_LOCAL &&
!arp_ignore(in_dev, sip, tip))
arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
dev->dev_addr, sha);
goto out;
}
if (arp->ar_op == htons(ARPOP_REQUEST) &&
ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb);
addr_type = rt->rt_type;
if (addr_type == RTN_LOCAL) {
int dont_send;
dont_send = arp_ignore(in_dev, sip, tip);
if (!dont_send && IN_DEV_ARPFILTER(in_dev))
dont_send |= arp_filter(sip, tip, dev);
if (!dont_send) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n) {
arp_send(ARPOP_REPLY, ETH_P_ARP, sip,
dev, tip, sha, dev->dev_addr,
sha);
neigh_release(n);
}
}
goto out;
} else if (IN_DEV_FORWARD(in_dev)) {
if (addr_type == RTN_UNICAST &&
(arp_fwd_proxy(in_dev, dev, rt) ||
arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n)
neigh_release(n);
if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED ||
skb->pkt_type == PACKET_HOST ||
in_dev->arp_parms->proxy_delay == 0) {
arp_send(ARPOP_REPLY, ETH_P_ARP, sip,
dev, tip, sha, dev->dev_addr,
sha);
} else {
pneigh_enqueue(&arp_tbl,
in_dev->arp_parms, skb);
return 0;
}
goto out;
}
}
}
/* Update our ARP tables */
n = __neigh_lookup(&arp_tbl, &sip, dev, 0);
if (IPV4_DEVCONF_ALL(dev_net(dev), ARP_ACCEPT)) {
/* Unsolicited ARP is not accepted by default.
It is possible, that this option should be enabled for some
devices (strip is candidate)
*/
if (n == NULL &&
(arp->ar_op == htons(ARPOP_REPLY) ||
(arp->ar_op == htons(ARPOP_REQUEST) && tip == sip)) &&
inet_addr_type(net, sip) == RTN_UNICAST)
n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
}
if (n) {
int state = NUD_REACHABLE;
int override;
/* If several different ARP replies follows back-to-back,
use the FIRST one. It is possible, if several proxy
agents are active. Taking the first reply prevents
arp trashing and chooses the fastest router.
*/
/*
* If n->updated is after jiffies, then the clock has wrapped and
* we are *well* past the locktime, so set the override flag
*/
if (time_after(n->updated, jiffies))
override = 1;
else
override = time_after(jiffies, n->updated + n->parms->locktime);
/* Broadcast replies and request packets
do not assert neighbour reachability.
*/
if (arp->ar_op != htons(ARPOP_REPLY) ||
skb->pkt_type != PACKET_HOST)
state = NUD_STALE;
neigh_update(n, sha, state,
override ? NEIGH_UPDATE_F_OVERRIDE : 0);
neigh_release(n);
}
void kni_net_process_rx_packet(struct sk_buff *skb,
struct net_device *dev,
struct rw_kni_mbuf_metadata *meta_data)
{
struct kni_dev *kni = netdev_priv(dev);
skb->dev = dev;
if (kni->no_pci){
skb_reset_mac_header(skb);
skb->protocol = htons(RW_KNI_VF_GET_MDATA_PAYLOAD(meta_data));
} else {
skb->protocol = eth_type_trans(skb, dev);
}
skb->ip_summed = CHECKSUM_UNNECESSARY;
/*Eth-type trans would have populated the packet-type. Store
the old packet-type and populate the new packet-type depending
on the mbuf flags*/
rw_fpath_kni_set_skb_packet_type(meta_data, skb);
if (RW_KNI_VF_VALID_MDATA_NH_POLICY(meta_data)){
int route_lookup;
BUG_ON(RW_KNI_VF_VALID_MDATA_ENCAP(meta_data) == 0);
switch(RW_KNI_VF_GET_MDATA_ENCAP(meta_data)){
default:
break;
case 1: //AKKI fix this later
{
uint32_t daddr;
memcpy(&daddr, RW_KNI_VF_GET_MDATA_NH_POLICY(meta_data), 4);
route_lookup = ip_route_input_noref(skb, ntohl(daddr),
ntohl(daddr), 0, dev);
if (route_lookup){
kni->rx_drop_noroute++;
}else{
struct neighbour *neigh;
struct dst_entry *dst = dst_clone(skb_dst(skb));
struct net_device *neighdev;
skb_dst_drop(skb);
neighdev = dst->dev;
if (likely(neighdev)){
rcu_read_lock_bh();
neigh = __neigh_lookup(&arp_tbl, &daddr, neighdev, 1);
if (likely(!neigh)){
__neigh_event_send(neigh, NULL);
}
rcu_read_unlock_bh();
neigh_release(neigh);
}
dst_release(dst);
}
}
break;
case 2:
{
struct neighbour *neigh = NULL;
struct dst_entry *dst = NULL;
int i;
uint32_t *v6addr;
struct flowi6 fl6;
struct rt6_info *rt;
struct net_device *neighdev;
v6addr = (uint32_t*)RW_KNI_VF_GET_MDATA_NH_POLICY(meta_data);
for (i = 0; i < 4; i++){
fl6.daddr.s6_addr32[i] = htonl(v6addr[i]);
}
rt = rt6_lookup(dev_net(dev), &fl6.daddr,
NULL, 0, 0);
if (!rt){
kni->rx_drop_noroute++;
}else{
dst = &rt->dst;
neighdev = dst->dev;
if (likely(neighdev)){
rcu_read_lock_bh();
neigh = __neigh_lookup(ipv6_stub->nd_tbl,
&fl6.daddr.s6_addr32[0],
neighdev, 1);
if (likely(!neigh)){
__neigh_event_send(neigh, NULL);
}
rcu_read_unlock_bh();
neigh_release(neigh);
}
dst_release(dst);
}
}
break;
}
}
/* Call netif interface */
netif_rx(skb);
/* Update statistics */
kni->stats.rx_packets++;
}
static struct sk_buff *ipvlan_l3_rcv(struct net_device *dev,
struct sk_buff *skb, u16 proto)
{
struct ipvl_addr *addr;
struct net_device *sdev;
addr = ipvlan_skb_to_addr(skb, dev);
if (!addr)
goto out;
sdev = addr->master->dev;
switch (proto) {
case AF_INET:
{
struct iphdr *ip4h = ip_hdr(skb);
int err;
err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr,
ip4h->tos, sdev);
if (unlikely(err))
goto out;
break;
}
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
{
struct dst_entry *dst;
struct ipv6hdr *ip6h = ipv6_hdr(skb);
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct flowi6 fl6 = {
.flowi6_iif = sdev->ifindex,
.daddr = ip6h->daddr,
.saddr = ip6h->saddr,
.flowlabel = ip6_flowinfo(ip6h),
.flowi6_mark = skb->mark,
.flowi6_proto = ip6h->nexthdr,
};
skb_dst_drop(skb);
dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6,
skb, flags);
skb_dst_set(skb, dst);
break;
}
#endif
default:
break;
}
out:
return skb;
}
static const struct l3mdev_ops ipvl_l3mdev_ops = {
.l3mdev_l3_rcv = ipvlan_l3_rcv,
};
static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct ipvl_addr *addr;
unsigned int len;
addr = ipvlan_skb_to_addr(skb, skb->dev);
if (!addr)
goto out;
skb->dev = addr->master->dev;
len = skb->len + ETH_HLEN;
ipvlan_count_rx(addr->master, len, true, false);
out:
return NF_ACCEPT;
}
static const struct nf_hook_ops ipvl_nfops[] = {
{
.hook = ipvlan_nf_input,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = INT_MAX,
},
#if IS_ENABLED(CONFIG_IPV6)
{
.hook = ipvlan_nf_input,
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
static void ip_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
const struct iphdr *iph;
struct sk_buff *head = NULL;
struct net *net;
struct ipq *qp;
int err;
qp = container_of(frag, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
rcu_read_lock();
spin_lock(&qp->q.lock);
if (qp->q.flags & INET_FRAG_COMPLETE)
goto out;
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
if (!(qp->q.flags & INET_FRAG_FIRST_IN))
goto out;
/* sk_buff::dev and sk_buff::rbnode are unionized. So we
* pull the head out of the tree in order to be able to
* deal with head->dev.
*/
if (qp->q.fragments) {
head = qp->q.fragments;
qp->q.fragments = head->next;
} else {
head = skb_rb_first(&qp->q.rb_fragments);
if (!head)
goto out;
if (FRAG_CB(head)->next_frag)
rb_replace_node(&head->rbnode,
&FRAG_CB(head)->next_frag->rbnode,
&qp->q.rb_fragments);
else
rb_erase(&head->rbnode, &qp->q.rb_fragments);
memset(&head->rbnode, 0, sizeof(head->rbnode));
barrier();
}
if (head == qp->q.fragments_tail)
qp->q.fragments_tail = NULL;
sub_frag_mem_limit(qp->q.net, head->truesize);
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out;
/* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
if (err)
goto out;
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
spin_unlock(&qp->q.lock);
icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
goto out_rcu_unlock;
out:
spin_unlock(&qp->q.lock);
out_rcu_unlock:
rcu_read_unlock();
if (head)
kfree_skb(head);
ipq_put(qp);
}
int serval_ipv4_forward_out(struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
int err;
#if defined(ENABLE_DEBUG)
{
char srcstr[18], dststr[18];
LOG_DBG("%s %s->%s skb->len=%u iph_len=[%u] %u\n",
skb->dev ? skb->dev->name : "no dev",
inet_ntop(AF_INET, &iph->saddr, srcstr, 18),
inet_ntop(AF_INET, &iph->daddr, dststr, 18),
skb->len, iph->ihl << 2, iph->tos);
}
#endif
skb->protocol = htons(ETH_P_IP);
#if defined(OS_LINUX_KERNEL)
/* IP forwarding must be enabled for this to
work. */
err = ip_route_input_noref(skb,
iph->daddr,
iph->saddr,
iph->tos,
skb->dev);
if (err < 0) {
LOG_ERR("Could not forward SAL packet, NO route [err=%d]\n", err);
kfree_skb(skb);
return NET_RX_DROP;
} else {
struct rtable *rt = skb_rtable(skb);
iph->saddr = rt->rt_src;
}
#else
iph->ttl = iph->ttl - 1;
#endif
/* Update tot_len, we might have added SAL extension
headers. */
iph->tot_len = htons(skb->len);
LOG_DBG("Forwarding skb->len=%u\n",
skb->len);
/* Update checksum */
ip_send_check(iph);
/* It may seem counter intuitive that we call dst_input
here. The reason is that we want to call ip_forward, but
that function is not exported in the kernel. However, if we
re-route the packet in the kernel (using a new dst
address), the input function (as called by dst_input) will
point to ip_forward. The ip_forward function will
eventually call dst_output, after having updated TTL, etc.
*/
#if defined(OS_LINUX_KERNEL)
err = dst_input(skb);
#else
err = dev_queue_xmit(skb);
#endif
return err;
}
static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct arphdr *arp;
unsigned char *arp_ptr;
struct rtable *rt;
unsigned char *sha;
unsigned char *tha = NULL;
__be32 sip, tip;
u16 dev_type = dev->type;
int addr_type;
struct neighbour *n;
struct dst_entry *reply_dst = NULL;
bool is_garp = false;
/* arp_rcv below verifies the ARP header and verifies the device
* is ARP'able.
*/
if (!in_dev)
goto out_free_skb;
arp = arp_hdr(skb);
switch (dev_type) {
default:
if (arp->ar_pro != htons(ETH_P_IP) ||
htons(dev_type) != arp->ar_hrd)
goto out_free_skb;
break;
case ARPHRD_ETHER:
case ARPHRD_FDDI:
case ARPHRD_IEEE802:
/*
* ETHERNET, and Fibre Channel (which are IEEE 802
* devices, according to RFC 2625) devices will accept ARP
* hardware types of either 1 (Ethernet) or 6 (IEEE 802.2).
* This is the case also of FDDI, where the RFC 1390 says that
* FDDI devices should accept ARP hardware of (1) Ethernet,
* however, to be more robust, we'll accept both 1 (Ethernet)
* or 6 (IEEE 802.2)
*/
if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
arp->ar_pro != htons(ETH_P_IP))
goto out_free_skb;
break;
case ARPHRD_AX25:
if (arp->ar_pro != htons(AX25_P_IP) ||
arp->ar_hrd != htons(ARPHRD_AX25))
goto out_free_skb;
break;
case ARPHRD_NETROM:
if (arp->ar_pro != htons(AX25_P_IP) ||
arp->ar_hrd != htons(ARPHRD_NETROM))
goto out_free_skb;
break;
}
/* Understand only these message types */
if (arp->ar_op != htons(ARPOP_REPLY) &&
arp->ar_op != htons(ARPOP_REQUEST))
goto out_free_skb;
/*
* Extract fields
*/
arp_ptr = (unsigned char *)(arp + 1);
sha = arp_ptr;
arp_ptr += dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4;
switch (dev_type) {
#if IS_ENABLED(CONFIG_FIREWIRE_NET)
case ARPHRD_IEEE1394:
break;
#endif
default:
tha = arp_ptr;
arp_ptr += dev->addr_len;
}
memcpy(&tip, arp_ptr, 4);
/*
* Check for bad requests for 127.x.x.x and requests for multicast
* addresses. If this is one such, delete it.
*/
if (ipv4_is_multicast(tip) ||
(!IN_DEV_ROUTE_LOCALNET(in_dev) && ipv4_is_loopback(tip)))
goto out_free_skb;
/*
* For some 802.11 wireless deployments (and possibly other networks),
* there will be an ARP proxy and gratuitous ARP frames are attacks
* and thus should not be accepted.
*/
if (sip == tip && IN_DEV_ORCONF(in_dev, DROP_GRATUITOUS_ARP))
goto out_free_skb;
/*
* Special case: We must set Frame Relay source Q.922 address
*/
if (dev_type == ARPHRD_DLCI)
sha = dev->broadcast;
/*
* Process entry. The idea here is we want to send a reply if it is a
* request for us or if it is a request for someone else that we hold
* a proxy for. We want to add an entry to our cache if it is a reply
* to us or if it is a request for our address.
* (The assumption for this last is that if someone is requesting our
* address, they are probably intending to talk to us, so it saves time
* if we cache their address. Their address is also probably not in
* our cache, since ours is not in their cache.)
*
* Putting this another way, we only care about replies if they are to
* us, in which case we add them to the cache. For requests, we care
* about those for us and those for our proxies. We reply to both,
* and in the case of requests for us we add the requester to the arp
* cache.
*/
if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb))
reply_dst = (struct dst_entry *)
iptunnel_metadata_reply(skb_metadata_dst(skb),
GFP_ATOMIC);
/* Special case: IPv4 duplicate address detection packet (RFC2131) */
if (sip == 0) {
if (arp->ar_op == htons(ARPOP_REQUEST) &&
inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL &&
!arp_ignore(in_dev, sip, tip))
arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip,
sha, dev->dev_addr, sha, reply_dst);
goto out_consume_skb;
}
if (arp->ar_op == htons(ARPOP_REQUEST) &&
ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb);
addr_type = rt->rt_type;
if (addr_type == RTN_LOCAL) {
int dont_send;
dont_send = arp_ignore(in_dev, sip, tip);
if (!dont_send && IN_DEV_ARPFILTER(in_dev))
dont_send = arp_filter(sip, tip, dev);
if (!dont_send) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n) {
arp_send_dst(ARPOP_REPLY, ETH_P_ARP,
sip, dev, tip, sha,
dev->dev_addr, sha,
reply_dst);
neigh_release(n);
}
}
goto out_consume_skb;
} else if (IN_DEV_FORWARD(in_dev)) {
if (addr_type == RTN_UNICAST &&
(arp_fwd_proxy(in_dev, dev, rt) ||
arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
(rt->dst.dev != dev &&
pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n)
neigh_release(n);
if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED ||
skb->pkt_type == PACKET_HOST ||
NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) {
arp_send_dst(ARPOP_REPLY, ETH_P_ARP,
sip, dev, tip, sha,
dev->dev_addr, sha,
reply_dst);
} else {
pneigh_enqueue(&arp_tbl,
in_dev->arp_parms, skb);
goto out_free_dst;
}
goto out_consume_skb;
}
}
}
/* Update our ARP tables */
n = __neigh_lookup(&arp_tbl, &sip, dev, 0);
addr_type = -1;
if (n || IN_DEV_ARP_ACCEPT(in_dev)) {
is_garp = arp_is_garp(net, dev, &addr_type, arp->ar_op,
sip, tip, sha, tha);
}
if (IN_DEV_ARP_ACCEPT(in_dev)) {
/* Unsolicited ARP is not accepted by default.
It is possible, that this option should be enabled for some
devices (strip is candidate)
*/
if (!n &&
(is_garp ||
(arp->ar_op == htons(ARPOP_REPLY) &&
(addr_type == RTN_UNICAST ||
(addr_type < 0 &&
/* postpone calculation to as late as possible */
inet_addr_type_dev_table(net, dev, sip) ==
RTN_UNICAST)))))
n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
}
if (n) {
int state = NUD_REACHABLE;
int override;
/* If several different ARP replies follows back-to-back,
use the FIRST one. It is possible, if several proxy
agents are active. Taking the first reply prevents
arp trashing and chooses the fastest router.
*/
override = time_after(jiffies,
n->updated +
NEIGH_VAR(n->parms, LOCKTIME)) ||
is_garp;
/* Broadcast replies and request packets
do not assert neighbour reachability.
*/
if (arp->ar_op != htons(ARPOP_REPLY) ||
skb->pkt_type != PACKET_HOST)
state = NUD_STALE;
neigh_update(n, sha, state,
override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0);
neigh_release(n);
}
static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
if (net->ipv4.sysctl_ip_early_demux &&
!skb_dst(skb) &&
!skb->sk &&
!ip_is_fragment(iph)) {
const struct net_protocol *ipprot;
int protocol = iph->protocol;
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot && ipprot->early_demux) {
ipprot->early_demux(skb);
/* must reload iph, skb->head might have changed */
iph = ip_hdr(skb);
}
}
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (!skb_valid_dst(skb)) {
int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev);
if (unlikely(err)) {
if (err == -EXDEV)
NET_INC_STATS_BH(net, LINUX_MIB_IPRPFILTER);
goto drop;
}
}
#ifdef CONFIG_IP_ROUTE_CLASSID
if (unlikely(skb_dst(skb)->tclassid)) {
struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
u32 idx = skb_dst(skb)->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(skb);
if (rt->rt_type == RTN_MULTICAST) {
IP_UPD_PO_STATS_BH(net, IPSTATS_MIB_INMCAST, skb->len);
} else if (rt->rt_type == RTN_BROADCAST) {
IP_UPD_PO_STATS_BH(net, IPSTATS_MIB_INBCAST, skb->len);
} else if (skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) {
struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
/* RFC 1122 3.3.6:
*
* When a host sends a datagram to a link-layer broadcast
* address, the IP destination address MUST be a legal IP
* broadcast or IP multicast address.
*
* A host SHOULD silently discard a datagram that is received
* via a link-layer broadcast (see Section 2.4) but does not
* specify an IP multicast or broadcast destination address.
*
* This doesn't explicitly say L2 *broadcast*, but broadcast is
* in a way a form of multicast and the most common use case for
* this is 802.11 protecting against cross-station spoofing (the
* so-called "hole-196" attack) so do it for both.
*/
if (in_dev &&
IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST))
goto drop;
}
return dst_input(skb);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
