__sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
unsigned int dataoff, u_int8_t protocol)
{
const struct iphdr *iph = ip_hdr(skb);
__sum16 csum = 0;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
break;
if ((protocol == 0 && !csum_fold(skb->csum)) ||
!csum_tcpudp_magic(iph->saddr, iph->daddr,
skb->len - dataoff, protocol,
skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
/* fall through */
case CHECKSUM_NONE:
if (protocol == 0)
skb->csum = 0;
else
skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
skb->len - dataoff,
protocol, 0);
csum = __skb_checksum_complete(skb);
}
return csum;
}
__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
unsigned int dataoff, u_int8_t protocol)
{
struct ipv6hdr *ip6h = ipv6_hdr(skb);
__sum16 csum = 0;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
break;
if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
skb->len - dataoff, protocol,
csum_sub(skb->csum,
skb_checksum(skb, 0,
dataoff, 0)))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
/* fall through */
case CHECKSUM_NONE:
skb->csum = ~csum_unfold(
csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
skb->len - dataoff,
protocol,
csum_sub(0,
skb_checksum(skb, 0,
dataoff, 0))));
csum = __skb_checksum_complete(skb);
}
return csum;
}
static bool check_checksum(struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
struct gre_base_hdr *greh = (struct gre_base_hdr *)(iph + 1);
__sum16 csum = 0;
if (greh->flags & GRE_CSUM) {
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
csum = csum_fold(skb->csum);
if (!csum)
break;
/* Fall through. */
case CHECKSUM_NONE:
skb->csum = 0;
csum = __skb_checksum_complete(skb);
skb->ip_summed = CHECKSUM_COMPLETE;
break;
}
}
return (csum == 0);
}
/**
* skb_copy_and_csum_datagram_iovec - Copy and checkum skb to user iovec.
* @skb: skbuff
* @hlen: hardware length
* @iov: io vector
*
* Caller _must_ check that skb will fit to this iovec.
*
* Returns: 0 - success.
* -EINVAL - checksum failure.
* -EFAULT - fault during copy. Beware, in this case iovec
* can be modified!
*/
int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
int hlen, struct iovec *iov)
{
__wsum csum;
int chunk = skb->len - hlen;
/* Skip filled elements.
* Pretty silly, look at memcpy_toiovec, though 8)
*/
while (!iov->iov_len)
iov++;
if (iov->iov_len < chunk) {
if (__skb_checksum_complete(skb))
goto csum_error;
if (skb_copy_datagram_iovec(skb, hlen, iov, chunk))
goto fault;
} else {
csum = csum_partial(skb->data, hlen, skb->csum);
if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base,
chunk, &csum))
goto fault;
if (csum_fold(csum))
goto csum_error;
if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
netdev_rx_csum_fault(skb->dev);
iov->iov_len -= chunk;
iov->iov_base += chunk;
}
return 0;
csum_error:
return -EINVAL;
fault:
return -EFAULT;
}
/* Small and modified version of icmp_rcv */
static int
icmp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo,
unsigned int hooknum)
{
struct icmphdr _ih, *icmph;
/* Not enough header? */
icmph = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_ih), &_ih);
if (icmph == NULL) {
if (LOG_INVALID(IPPROTO_ICMP))
nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL,
"ip_ct_icmp: short packet ");
return -NF_ACCEPT;
}
/* See ip_conntrack_proto_tcp.c */
if (hooknum != NF_IP_PRE_ROUTING)
goto checksum_skipped;
switch (skb->ip_summed) {
case CHECKSUM_HW:
if (!(u16)csum_fold(skb->csum))
break;
/* fall through */
case CHECKSUM_NONE:
skb->csum = 0;
if (__skb_checksum_complete(skb)) {
if (LOG_INVALID(IPPROTO_ICMP))
nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL,
"ip_ct_icmp: bad ICMP checksum ");
return -NF_ACCEPT;
}
}
checksum_skipped:
/*
* 18 is the highest 'known' ICMP type. Anything else is a mystery
*
* RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently
* discarded.
*/
if (icmph->type > NR_ICMP_TYPES) {
if (LOG_INVALID(IPPROTO_ICMP))
nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL,
"ip_ct_icmp: invalid ICMP type ");
return -NF_ACCEPT;
}
/* Need to track icmp error message? */
if (icmph->type != ICMP_DEST_UNREACH
&& icmph->type != ICMP_SOURCE_QUENCH
&& icmph->type != ICMP_TIME_EXCEEDED
&& icmph->type != ICMP_PARAMETERPROB
&& icmph->type != ICMP_REDIRECT)
return NF_ACCEPT;
return icmp_error_message(skb, ctinfo, hooknum);
}
static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
unsigned short ulen, __be32 saddr, __be32 daddr)
{
__wsum psum;
if (uh->check == 0 || skb_csum_unnecessary(skb))
return 0;
psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
if (skb->ip_summed == CHECKSUM_COMPLETE &&
!csum_fold(csum_add(psum, skb->csum)))
return 0;
skb->csum = psum;
return __skb_checksum_complete(skb);
}
static int checksum_udp(struct sk_buff *skb, struct udphdr *uh,
unsigned short ulen, u32 saddr, u32 daddr)
{
unsigned int psum;
if (uh->check == 0 || skb->ip_summed == CHECKSUM_UNNECESSARY)
return 0;
psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
if (skb->ip_summed == CHECKSUM_HW &&
!(u16)csum_fold(csum_add(psum, skb->csum)))
return 0;
skb->csum = psum;
return __skb_checksum_complete(skb);
}
static __sum16 check_checksum(struct sk_buff *skb)
{
__sum16 csum = 0;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
csum = csum_fold(skb->csum);
if (!csum)
break;
/* Fall through. */
case CHECKSUM_NONE:
skb->csum = 0;
csum = __skb_checksum_complete(skb);
skb->ip_summed = CHECKSUM_COMPLETE;
break;
}
return csum;
}
static int ipgre_rcv(struct sk_buff *skb)
{
struct iphdr *iph;
u8 *h;
__be16 flags;
__sum16 csum = 0;
__be32 key = 0;
u32 seqno = 0;
struct ip_tunnel *tunnel;
int offset = 4;
__be16 gre_proto;
unsigned int len;
if (!pskb_may_pull(skb, 16))
goto drop_nolock;
iph = ip_hdr(skb);
h = skb->data;
flags = *(__be16*)h;
if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
/* - Version must be 0.
- We do not support routing headers.
*/
if (flags&(GRE_VERSION|GRE_ROUTING))
goto drop_nolock;
if (flags&GRE_CSUM) {
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
csum = csum_fold(skb->csum);
if (!csum)
break;
/* fall through */
case CHECKSUM_NONE:
skb->csum = 0;
csum = __skb_checksum_complete(skb);
skb->ip_summed = CHECKSUM_COMPLETE;
}
offset += 4;
}
if (flags&GRE_KEY) {
key = *(__be32*)(h + offset);
offset += 4;
}
if (flags&GRE_SEQ) {
seqno = ntohl(*(__be32*)(h + offset));
offset += 4;
}
}
gre_proto = *(__be16 *)(h + 2);
read_lock(&ipgre_lock);
if ((tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, key,
gre_proto))) {
struct net_device_stats *stats = &tunnel->dev->stats;
secpath_reset(skb);
skb->protocol = gre_proto;
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IP
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
skb->protocol = htons(ETH_P_IP);
if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
skb->mac_header = skb->network_header;
__pskb_pull(skb, offset);
skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
if (skb_rtable(skb)->fl.iif == 0)
goto drop;
stats->multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
stats->rx_crc_errors++;
stats->rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&GRE_SEQ) {
if (!(flags&GRE_SEQ) ||
(tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
stats->rx_fifo_errors++;
stats->rx_errors++;
goto drop;
}
tunnel->i_seqno = seqno + 1;
}
len = skb->len;
/* Warning: All skb pointers will be invalidated! */
if (tunnel->dev->type == ARPHRD_ETHER) {
if (!pskb_may_pull(skb, ETH_HLEN)) {
stats->rx_length_errors++;
stats->rx_errors++;
goto drop;
}
iph = ip_hdr(skb);
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
stats->rx_packets++;
stats->rx_bytes += len;
skb->dev = tunnel->dev;
skb_dst_drop(skb);
nf_reset(skb);
skb_reset_network_header(skb);
ipgre_ecn_decapsulate(iph, skb);
netif_rx(skb);
read_unlock(&ipgre_lock);
return(0);
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
read_unlock(&ipgre_lock);
drop_nolock:
kfree_skb(skb);
return(0);
}
int ip6_route_me_harder(struct sk_buff *skb)
{
struct net *net = dev_net(skb_dst(skb)->dev);
const struct ipv6hdr *iph = ipv6_hdr(skb);
unsigned int hh_len;
struct dst_entry *dst;
struct flowi6 fl6 = {
.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.flowi6_mark = skb->mark,
.daddr = iph->daddr,
.saddr = iph->saddr,
};
int err;
dst = ip6_route_output(net, skb->sk, &fl6);
err = dst->error;
if (err) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
net_dbg_ratelimited("ip6_route_me_harder: No more route\n");
dst_release(dst);
return err;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, dst);
#ifdef CONFIG_XFRM
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_dst_set(skb, dst);
}
#endif
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
0, GFP_ATOMIC))
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL(ip6_route_me_harder);
/*
* Extra routing may needed on local out, as the QUEUE target never
* returns control to the table.
*/
struct ip6_rt_info {
struct in6_addr daddr;
struct in6_addr saddr;
u_int32_t mark;
};
static void nf_ip6_saveroute(const struct sk_buff *skb,
struct nf_queue_entry *entry)
{
struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
if (entry->hook == NF_INET_LOCAL_OUT) {
const struct ipv6hdr *iph = ipv6_hdr(skb);
rt_info->daddr = iph->daddr;
rt_info->saddr = iph->saddr;
rt_info->mark = skb->mark;
}
}
static int nf_ip6_reroute(struct sk_buff *skb,
const struct nf_queue_entry *entry)
{
struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
if (entry->hook == NF_INET_LOCAL_OUT) {
const struct ipv6hdr *iph = ipv6_hdr(skb);
if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
!ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
skb->mark != rt_info->mark)
return ip6_route_me_harder(skb);
}
return 0;
}
static int nf_ip6_route(struct net *net, struct dst_entry **dst,
struct flowi *fl, bool strict)
{
static const struct ipv6_pinfo fake_pinfo;
static const struct inet_sock fake_sk = {
/* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */
.sk.sk_bound_dev_if = 1,
.pinet6 = (struct ipv6_pinfo *) &fake_pinfo,
};
const void *sk = strict ? &fake_sk : NULL;
struct dst_entry *result;
int err;
result = ip6_route_output(net, sk, &fl->u.ip6);
err = result->error;
if (err)
dst_release(result);
else
*dst = result;
return err;
}
__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
unsigned int dataoff, u_int8_t protocol)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
__sum16 csum = 0;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
break;
if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
skb->len - dataoff, protocol,
csum_sub(skb->csum,
skb_checksum(skb, 0,
dataoff, 0)))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
/* fall through */
case CHECKSUM_NONE:
skb->csum = ~csum_unfold(
csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
skb->len - dataoff,
protocol,
csum_sub(0,
skb_checksum(skb, 0,
dataoff, 0))));
csum = __skb_checksum_complete(skb);
}
return csum;
}
EXPORT_SYMBOL(nf_ip6_checksum);
static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook,
unsigned int dataoff, unsigned int len,
u_int8_t protocol)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
__wsum hsum;
__sum16 csum = 0;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (len == skb->len - dataoff)
return nf_ip6_checksum(skb, hook, dataoff, protocol);
/* fall through */
case CHECKSUM_NONE:
hsum = skb_checksum(skb, 0, dataoff, 0);
skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
&ip6h->daddr,
skb->len - dataoff,
protocol,
csum_sub(0, hsum)));
skb->ip_summed = CHECKSUM_NONE;
return __skb_checksum_complete_head(skb, dataoff + len);
}
return csum;
};
static const struct nf_ipv6_ops ipv6ops = {
.chk_addr = ipv6_chk_addr,
};
static const struct nf_afinfo nf_ip6_afinfo = {
.family = AF_INET6,
.checksum = nf_ip6_checksum,
.checksum_partial = nf_ip6_checksum_partial,
.route = nf_ip6_route,
.saveroute = nf_ip6_saveroute,
.reroute = nf_ip6_reroute,
.route_key_size = sizeof(struct ip6_rt_info),
};
int __init ipv6_netfilter_init(void)
{
RCU_INIT_POINTER(nf_ipv6_ops, &ipv6ops);
return nf_register_afinfo(&nf_ip6_afinfo);
}
/* This can be called from inet6_init() on errors, so it cannot
* be marked __exit. -DaveM
*/
void ipv6_netfilter_fini(void)
{
RCU_INIT_POINTER(nf_ipv6_ops, NULL);
nf_unregister_afinfo(&nf_ip6_afinfo);
}