static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type)
{
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel != NULL) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
skb->mark = be32_to_cpu(tunnel->parms.i_key);
return xfrm_input(skb, nexthdr, spi, encap_type);
}
return -EINVAL;
drop:
kfree_skb(skb);
return 0;
}
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
struct net_device *dev;
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct xfrm_mode *inner_mode;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
u32 orig_mark = skb->mark;
int ret;
if (!tunnel)
return 1;
dev = tunnel->dev;
if (err) {
dev->stats.rx_errors++;
dev->stats.rx_dropped++;
return 0;
}
x = xfrm_input_state(skb);
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) {
XFRM_INC_STATS(dev_net(skb->dev),
LINUX_MIB_XFRMINSTATEMODEERROR);
return -EINVAL;
}
}
family = inner_mode->afinfo->family;
skb->mark = be32_to_cpu(tunnel->parms.i_key);
ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
skb->mark = orig_mark;
if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
skb->dev = dev;
tstats = this_cpu_ptr(dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
return 0;
}
static int xfrm4_esp_rcv(struct sk_buff *skb)
{
int ret;
struct xfrm4_protocol *handler;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
for_each_protocol_rcu(esp4_handlers, handler)
if ((ret = handler->handler(skb)) != -EINVAL)
return ret;
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
kfree_skb(skb);
return 0;
}
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
struct net_device *dev;
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
if (!tunnel)
return 1;
dev = tunnel->dev;
if (err) {
dev->stats.rx_errors++;
dev->stats.rx_dropped++;
return 0;
}
x = xfrm_input_state(skb);
family = x->inner_mode->afinfo->family;
if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
return -EPERM;
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
skb->dev = dev;
tstats = this_cpu_ptr(dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
return 0;
}
int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type)
{
int ret;
struct xfrm4_protocol *handler;
struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr);
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
if (!head)
goto out;
for_each_protocol_rcu(*head, handler)
if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
return ret;
out:
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
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;
u32 mark = skb->mark;
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;
/* if tunnel is present override skb->mark value with tunnel i_key */
if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) {
switch (family) {
case AF_INET:
mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key);
break;
case AF_INET6:
mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key);
break;
}
}
/* 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, 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) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
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;
}
