static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct net_device_stats *stats = &tunnel->dev->stats;
struct iphdr *tiph = &tunnel->parms.iph;
struct ipv6hdr *iph6 = ipv6_hdr(skb);
u8 tos = tunnel->parms.iph.tos;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
int mtu;
struct in6_addr *addr6;
int addr_type;
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
/* ISATAP (RFC4214) - must come before 6to4 */
if (dev->priv_flags & IFF_ISATAP) {
struct neighbour *neigh = NULL;
if (skb_dst(skb))
neigh = skb_dst(skb)->neighbour;
if (neigh == NULL) {
if (net_ratelimit())
printk(KERN_DEBUG "sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (struct in6_addr*)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if ((addr_type & IPV6_ADDR_UNICAST) &&
ipv6_addr_is_isatap(addr6))
dst = addr6->s6_addr32[3];
else
goto tx_error;
}
if (!dst)
dst = try_6to4(&iph6->daddr);
if (!dst) {
struct neighbour *neigh = NULL;
if (skb_dst(skb))
neigh = skb_dst(skb)->neighbour;
if (neigh == NULL) {
if (net_ratelimit())
printk(KERN_DEBUG "sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (struct in6_addr*)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
goto tx_error_icmp;
dst = addr6->s6_addr32[3];
}
{
struct flowi fl = { .nl_u = { .ip4_u =
{ .daddr = dst,
.saddr = tiph->saddr,
.tos = RT_TOS(tos) } },
.oif = tunnel->parms.link,
.proto = IPPROTO_IPV6 };
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
stats->tx_carrier_errors++;
goto tx_error_icmp;
}
}
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(rt);
stats->tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
stats->collisions++;
goto tx_error;
}
if (tiph->frag_off)
mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
else
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (mtu < 68) {
stats->collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (tunnel->parms.iph.daddr && skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
stats->tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
iph6 = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags = 0;
skb_dst_drop(skb);
skb_dst_set(skb, &rt->u.dst);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
if (mtu > IPV6_MIN_MTU)
iph->frag_off = tiph->frag_off;
else
iph->frag_off = 0;
iph->protocol = IPPROTO_IPV6;
iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = iph6->hop_limit;
nf_reset(skb);
IPTUNNEL_XMIT();
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
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;
}
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
struct iphdr *iph = oldskb->nh.iph;
struct tcphdr _otcph, *oth, *tcph;
__be16 tmp_port;
__be32 tmp_addr;
int needs_ack;
unsigned int addr_type;
/* IP header checks: fragment. */
if (oldskb->nh.iph->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, oldskb->nh.iph->ihl * 4,
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
/* Check checksum */
if (nf_ip_checksum(oldskb, hook, iph->ihl * 4, IPPROTO_TCP))
return;
/* We need a linear, writeable skb. We also need to expand
headroom in case hh_len of incoming interface < hh_len of
outgoing interface */
nskb = skb_copy_expand(oldskb, LL_MAX_HEADER, skb_tailroom(oldskb),
GFP_ATOMIC);
if (!nskb)
return;
/* This packet will not be the same as the other: clear nf fields */
nf_reset(nskb);
nskb->mark = 0;
skb_init_secmark(nskb);
tcph = (struct tcphdr *)((u_int32_t*)nskb->nh.iph + nskb->nh.iph->ihl);
/* Swap source and dest */
tmp_addr = nskb->nh.iph->saddr;
nskb->nh.iph->saddr = nskb->nh.iph->daddr;
nskb->nh.iph->daddr = tmp_addr;
tmp_port = tcph->source;
tcph->source = tcph->dest;
tcph->dest = tmp_port;
/* Truncate to length (no data) */
tcph->doff = sizeof(struct tcphdr)/4;
skb_trim(nskb, nskb->nh.iph->ihl*4 + sizeof(struct tcphdr));
nskb->nh.iph->tot_len = htons(nskb->len);
if (tcph->ack) {
needs_ack = 0;
tcph->seq = oth->ack_seq;
tcph->ack_seq = 0;
} else {
needs_ack = 1;
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin
+ oldskb->len - oldskb->nh.iph->ihl*4
- (oth->doff<<2));
tcph->seq = 0;
}
/* Reset flags */
((u_int8_t *)tcph)[13] = 0;
tcph->rst = 1;
tcph->ack = needs_ack;
tcph->window = 0;
tcph->urg_ptr = 0;
/* Adjust TCP checksum */
tcph->check = 0;
tcph->check = tcp_v4_check(tcph, sizeof(struct tcphdr),
nskb->nh.iph->saddr,
nskb->nh.iph->daddr,
csum_partial((char *)tcph,
sizeof(struct tcphdr), 0));
/* Set DF, id = 0 */
nskb->nh.iph->frag_off = htons(IP_DF);
nskb->nh.iph->id = 0;
addr_type = RTN_UNSPEC;
if (hook != NF_IP_FORWARD
#ifdef CONFIG_BRIDGE_NETFILTER
|| (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED)
#endif
)
addr_type = RTN_LOCAL;
if (ip_route_me_harder(&nskb, addr_type))
goto free_nskb;
nskb->ip_summed = CHECKSUM_NONE;
/* Adjust IP TTL */
nskb->nh.iph->ttl = dst_metric(nskb->dst, RTAX_HOPLIMIT);
/* Adjust IP checksum */
nskb->nh.iph->check = 0;
nskb->nh.iph->check = ip_fast_csum((unsigned char *)nskb->nh.iph,
nskb->nh.iph->ihl);
/* "Never happens" */
if (nskb->len > dst_mtu(nskb->dst))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, nskb, NULL, nskb->dst->dev,
dst_output);
return;
free_nskb:
kfree_skb(nskb);
}
/*
* Deliver the packet to the host
*/
void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
bool have_final)
{
const struct inet6_protocol *ipprot;
struct inet6_dev *idev;
unsigned int nhoff;
bool raw;
/*
* Parse extension headers
*/
resubmit:
idev = ip6_dst_idev(skb_dst(skb));
nhoff = IP6CB(skb)->nhoff;
if (!have_final) {
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nexthdr = skb_network_header(skb)[nhoff];
}
resubmit_final:
raw = raw6_local_deliver(skb, nexthdr);
ipprot = rcu_dereference(inet6_protos[nexthdr]);
if (ipprot) {
int ret;
if (have_final) {
if (!(ipprot->flags & INET6_PROTO_FINAL)) {
/* Once we've seen a final protocol don't
* allow encapsulation on any non-final
* ones. This allows foo in UDP encapsulation
* to work.
*/
goto discard;
}
} else if (ipprot->flags & INET6_PROTO_FINAL) {
const struct ipv6hdr *hdr;
int sdif = inet6_sdif(skb);
struct net_device *dev;
/* Only do this once for first final protocol */
have_final = true;
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
nf_reset(skb);
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
/* skb->dev passed may be master dev for vrfs. */
if (sdif) {
dev = dev_get_by_index_rcu(net, sdif);
if (!dev)
goto discard;
} else {
dev = skb->dev;
}
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(dev, &hdr->daddr,
&hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
goto discard;
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
ret = ipprot->handler(skb);
if (ret > 0) {
if (ipprot->flags & INET6_PROTO_FINAL) {
/* Not an extension header, most likely UDP
* encapsulation. Use return value as nexthdr
* protocol not nhoff (which presumably is
* not set by handler).
*/
nexthdr = ret;
goto resubmit_final;
} else {
goto resubmit;
}
} else if (ret == 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
}
} else {
if (!raw) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
__IP6_INC_STATS(net, idev,
IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff);
}
kfree_skb(skb);
} else {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
consume_skb(skb);
}
}
return;
discard:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
kfree_skb(skb);
}
static int ip6_input_finish(struct sk_buff *skb)
{
struct inet6_protocol *ipprot;
struct sock *raw_sk;
unsigned int nhoff;
int nexthdr;
u8 hash;
struct inet6_dev *idev;
/*
* Parse extension headers
*/
rcu_read_lock();
resubmit:
idev = ip6_dst_idev(skb->dst);
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb_network_header(skb)[nhoff];
raw_sk = sk_head(&raw_v6_htable[nexthdr & (MAX_INET_PROTOS - 1)]);
if (raw_sk && !ipv6_raw_deliver(skb, nexthdr))
raw_sk = NULL;
hash = nexthdr & (MAX_INET_PROTOS - 1);
if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) {
int ret;
if (ipprot->flags & INET6_PROTO_FINAL) {
struct ipv6hdr *hdr;
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
nf_reset(skb);
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
&hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr))
goto discard;
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
ret = ipprot->handler(skb);
if (ret > 0)
goto resubmit;
else if (ret == 0)
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw_sk) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff,
skb->dev);
}
} else
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
rcu_read_unlock();
return 0;
discard:
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDISCARDS);
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
{
struct net *net = dev_net(skb->dev);
int err;
__be32 seq;
__be32 seq_hi;
struct xfrm_state *x = NULL;
xfrm_address_t *daddr;
struct xfrm_mode *inner_mode;
unsigned int family;
int decaps = 0;
int async = 0;
/* A negative encap_type indicates async resumption. */
if (encap_type < 0) {
async = 1;
x = xfrm_input_state(skb);
seq = XFRM_SKB_CB(skb)->seq.input.low;
family = x->outer_mode->afinfo->family;
goto resume;
}
daddr = (xfrm_address_t *)(skb_network_header(skb) +
XFRM_SPI_SKB_CB(skb)->daddroff);
family = XFRM_SPI_SKB_CB(skb)->family;
/* Allocate new secpath or COW existing one. */
if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
struct sec_path *sp;
sp = secpath_dup(skb->sp);
if (!sp) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR);
goto drop;
}
if (skb->sp)
secpath_put(skb->sp);
skb->sp = sp;
}
seq = 0;
if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
goto drop;
}
do {
if (skb->sp->len == XFRM_MAX_DEPTH) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
goto drop;
}
x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family);
if (x == NULL) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
xfrm_audit_state_notfound(skb, family, spi, seq);
goto drop;
}
skb->sp->xvec[skb->sp->len++] = x;
spin_lock(&x->lock);
if (unlikely(x->km.state != XFRM_STATE_VALID)) {
if (x->km.state == XFRM_STATE_ACQ)
XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
else
XFRM_INC_STATS(net,
LINUX_MIB_XFRMINSTATEINVALID);
goto drop_unlock;
}
if ((x->encap ? x->encap->encap_type : 0) != encap_type) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
goto drop_unlock;
}
if (x->repl->check(x, skb, seq)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
goto drop_unlock;
}
if (xfrm_state_check_expire(x)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEEXPIRED);
goto drop_unlock;
}
spin_unlock(&x->lock);
if (xfrm_tunnel_check(skb, x, family)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
goto drop;
}
seq_hi = htonl(xfrm_replay_seqhi(x, seq));
XFRM_SKB_CB(skb)->seq.input.low = seq;
XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
skb_dst_force(skb);
nexthdr = x->type->input(x, skb);
if (nexthdr == -EINPROGRESS)
return 0;
resume:
spin_lock(&x->lock);
if (nexthdr <= 0) {
if (nexthdr == -EBADMSG) {
xfrm_audit_state_icvfail(x, skb,
x->type->proto);
x->stats.integrity_failed++;
}
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR);
goto drop_unlock;
}
/* only the first xfrm gets the encap type */
encap_type = 0;
if (async && x->repl->recheck(x, skb, seq)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
goto drop_unlock;
}
x->repl->advance(x, seq);
x->curlft.bytes += skb->len;
x->curlft.packets++;
spin_unlock(&x->lock);
XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
inner_mode = x->inner_mode;
if (x->sel.family == AF_UNSPEC) {
inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
if (inner_mode == NULL)
goto drop;
}
if (inner_mode->input(x, skb)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
goto drop;
}
if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) {
decaps = 1;
break;
}
/*
* We need the inner address. However, we only get here for
* transport mode so the outer address is identical.
*/
daddr = &x->id.daddr;
family = x->outer_mode->afinfo->family;
err = xfrm_parse_spi(skb, nexthdr, &spi, &seq);
if (err < 0) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
goto drop;
}
} while (!err);
err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
if (err)
goto drop;
nf_reset(skb);
if (decaps) {
skb_dst_drop(skb);
netif_rx(skb);
return 0;
} else {
return x->inner_mode->afinfo->transport_finish(skb, async);
}
drop_unlock:
spin_unlock(&x->lock);
drop:
xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1);
kfree_skb(skb);
return 0;
}
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 xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi)
{
int err;
__be32 seq;
struct xfrm_state *xfrm_vec[XFRM_MAX_DEPTH];
struct xfrm_state *x;
int xfrm_nr = 0;
int decaps = 0;
int nexthdr;
unsigned int nhoff;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb_network_header(skb)[nhoff];
seq = 0;
if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0)
goto drop;
do {
struct ipv6hdr *iph = ipv6_hdr(skb);
if (xfrm_nr == XFRM_MAX_DEPTH)
goto drop;
x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi,
nexthdr != IPPROTO_IPIP ? nexthdr : IPPROTO_IPV6, AF_INET6);
if (x == NULL)
goto drop;
spin_lock(&x->lock);
if (unlikely(x->km.state != XFRM_STATE_VALID))
goto drop_unlock;
if (x->props.replay_window && xfrm_replay_check(x, seq))
goto drop_unlock;
if (xfrm_state_check_expire(x))
goto drop_unlock;
nexthdr = x->type->input(x, skb);
if (nexthdr <= 0)
goto drop_unlock;
skb_network_header(skb)[nhoff] = nexthdr;
if (x->props.replay_window)
xfrm_replay_advance(x, seq);
x->curlft.bytes += skb->len;
x->curlft.packets++;
spin_unlock(&x->lock);
xfrm_vec[xfrm_nr++] = x;
if (x->mode->input(x, skb))
goto drop;
if (x->props.mode == XFRM_MODE_TUNNEL) { /* XXX */
decaps = 1;
break;
}
if ((err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) < 0)
goto drop;
} while (!err);
/* Allocate new secpath or COW existing one. */
if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
struct sec_path *sp;
sp = secpath_dup(skb->sp);
if (!sp)
goto drop;
if (skb->sp)
secpath_put(skb->sp);
skb->sp = sp;
}
if (xfrm_nr + skb->sp->len > XFRM_MAX_DEPTH)
goto drop;
memcpy(skb->sp->xvec + skb->sp->len, xfrm_vec,
xfrm_nr * sizeof(xfrm_vec[0]));
skb->sp->len += xfrm_nr;
skb->ip_summed = CHECKSUM_NONE;
nf_reset(skb);
if (decaps) {
dst_release(skb->dst);
skb->dst = NULL;
netif_rx(skb);
return -1;
} else {
#ifdef CONFIG_NETFILTER
ipv6_hdr(skb)->payload_len = htons(skb->len);
__skb_push(skb, skb->data - skb_network_header(skb));
NF_HOOK(PF_INET6, NF_IP6_PRE_ROUTING, skb, skb->dev, NULL,
ip6_rcv_finish);
return -1;
#else
return 1;
#endif
}
drop_unlock:
spin_unlock(&x->lock);
xfrm_state_put(x);
drop:
while (--xfrm_nr >= 0)
xfrm_state_put(xfrm_vec[xfrm_nr]);
kfree_skb(skb);
return -1;
}
static int ip6_tnl_xmit2(struct sk_buff *skb,
struct net_device *dev,
__u8 dsfield,
struct flowi *fl,
int encap_limit,
__u32 *pmtu)
{
struct net *net = dev_net(dev);
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->dev->stats;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct ipv6_tel_txoption opt;
struct dst_entry *dst;
struct net_device *tdev;
int mtu;
unsigned int max_headroom = sizeof(struct ipv6hdr);
u8 proto;
int err = -1;
int pkt_len;
if ((dst = ip6_tnl_dst_check(t)) != NULL)
dst_hold(dst);
else {
dst = ip6_route_output(net, NULL, fl);
if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0)
goto tx_err_link_failure;
}
tdev = dst->dev;
if (tdev == dev) {
stats->collisions++;
if (net_ratelimit())
printk(KERN_WARNING
"%s: Local routing loop detected!\n",
t->parms.name);
goto tx_err_dst_release;
}
mtu = dst_mtu(dst) - sizeof (*ipv6h);
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (skb->len > mtu) {
*pmtu = mtu;
err = -EMSGSIZE;
goto tx_err_dst_release;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom += LL_RESERVED_SPACE(tdev);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb;
if (!(new_skb = skb_realloc_headroom(skb, max_headroom)))
goto tx_err_dst_release;
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
kfree_skb(skb);
skb = new_skb;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst_clone(dst));
skb->transport_header = skb->network_header;
proto = fl->proto;
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
*(__be32*)ipv6h = fl->fl6_flowlabel | htonl(0x60000000);
dsfield = INET_ECN_encapsulate(0, dsfield);
ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = proto;
ipv6_addr_copy(&ipv6h->saddr, &fl->fl6_src);
ipv6_addr_copy(&ipv6h->daddr, &fl->fl6_dst);
nf_reset(skb);
pkt_len = skb->len;
err = ip6_local_out(skb);
if (net_xmit_eval(err) == 0) {
stats->tx_bytes += pkt_len;
stats->tx_packets++;
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
}
ip6_tnl_dst_store(t, dst);
return 0;
tx_err_link_failure:
stats->tx_carrier_errors++;
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
return err;
}
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
struct iphdr *iph = oldskb->nh.iph;
struct tcphdr _otcph, *oth, *tcph;
struct rtable *rt;
u_int16_t tmp_port;
u_int32_t tmp_addr;
unsigned int tcplen;
int needs_ack;
int hh_len;
/* IP header checks: fragment. */
if (oldskb->nh.iph->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, oldskb->nh.iph->ihl * 4,
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
/* Check checksum */
tcplen = oldskb->len - iph->ihl * 4;
if (((hook != NF_IP_LOCAL_IN && oldskb->ip_summed != CHECKSUM_HW) ||
(hook == NF_IP_LOCAL_IN &&
oldskb->ip_summed != CHECKSUM_UNNECESSARY)) &&
csum_tcpudp_magic(iph->saddr, iph->daddr, tcplen, IPPROTO_TCP,
oldskb->ip_summed == CHECKSUM_HW ? oldskb->csum :
skb_checksum(oldskb, iph->ihl * 4, tcplen, 0)))
return;
if ((rt = route_reverse(oldskb, oth, hook)) == NULL)
return;
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
/* We need a linear, writeable skb. We also need to expand
headroom in case hh_len of incoming interface < hh_len of
outgoing interface */
nskb = skb_copy_expand(oldskb, hh_len, skb_tailroom(oldskb),
GFP_ATOMIC);
if (!nskb) {
dst_release(&rt->u.dst);
return;
}
dst_release(nskb->dst);
nskb->dst = &rt->u.dst;
/* This packet will not be the same as the other: clear nf fields */
nf_reset(nskb);
nskb->nfmark = 0;
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(nskb->nf_bridge);
nskb->nf_bridge = NULL;
#endif
tcph = (struct tcphdr *)((u_int32_t*)nskb->nh.iph + nskb->nh.iph->ihl);
/* Swap source and dest */
tmp_addr = nskb->nh.iph->saddr;
nskb->nh.iph->saddr = nskb->nh.iph->daddr;
nskb->nh.iph->daddr = tmp_addr;
tmp_port = tcph->source;
tcph->source = tcph->dest;
tcph->dest = tmp_port;
/* Truncate to length (no data) */
tcph->doff = sizeof(struct tcphdr)/4;
skb_trim(nskb, nskb->nh.iph->ihl*4 + sizeof(struct tcphdr));
nskb->nh.iph->tot_len = htons(nskb->len);
if (tcph->ack) {
needs_ack = 0;
tcph->seq = oth->ack_seq;
tcph->ack_seq = 0;
} else {
needs_ack = 1;
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin
+ oldskb->len - oldskb->nh.iph->ihl*4
- (oth->doff<<2));
tcph->seq = 0;
}
/* Reset flags */
((u_int8_t *)tcph)[13] = 0;
tcph->rst = 1;
tcph->ack = needs_ack;
tcph->window = 0;
tcph->urg_ptr = 0;
/* Adjust TCP checksum */
tcph->check = 0;
tcph->check = tcp_v4_check(tcph, sizeof(struct tcphdr),
nskb->nh.iph->saddr,
nskb->nh.iph->daddr,
csum_partial((char *)tcph,
sizeof(struct tcphdr), 0));
/* Adjust IP TTL, DF */
nskb->nh.iph->ttl = dst_metric(nskb->dst, RTAX_HOPLIMIT);
/* Set DF, id = 0 */
nskb->nh.iph->frag_off = htons(IP_DF);
nskb->nh.iph->id = 0;
/* Adjust IP checksum */
nskb->nh.iph->check = 0;
nskb->nh.iph->check = ip_fast_csum((unsigned char *)nskb->nh.iph,
nskb->nh.iph->ihl);
/* "Never happens" */
if (nskb->len > dst_mtu(nskb->dst))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, nskb, NULL, nskb->dst->dev,
dst_output);
return;
free_nskb:
kfree_skb(nskb);
}