static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
{
const struct iphdr *iph;
int ntkoff;
ntkoff = skb_network_offset(skb);
if (!pskb_may_pull(skb, sizeof(*iph) + ntkoff))
goto fail;
iph = ip_hdr(skb);
switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
case IPPROTO_ICMP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP)
if (!tcf_csum_ipv4_icmp(skb, iph->ihl * 4,
ntohs(iph->tot_len)))
goto fail;
break;
case IPPROTO_IGMP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP)
if (!tcf_csum_ipv4_igmp(skb, iph->ihl * 4,
ntohs(iph->tot_len)))
goto fail;
break;
case IPPROTO_TCP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP)
if (!tcf_csum_ipv4_tcp(skb, iph->ihl * 4,
ntohs(iph->tot_len)))
goto fail;
break;
case IPPROTO_UDP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP)
if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4,
ntohs(iph->tot_len), 0))
goto fail;
break;
case IPPROTO_UDPLITE:
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE)
if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4,
ntohs(iph->tot_len), 1))
goto fail;
break;
}
if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff))
goto fail;
ip_send_check(ip_hdr(skb));
}
return 1;
fail:
return 0;
}
unsigned int
nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct flow_offload_tuple_rhash *tuplehash;
struct nf_flowtable *flow_table = priv;
struct flow_offload_tuple tuple = {};
enum flow_offload_tuple_dir dir;
struct flow_offload *flow;
struct net_device *outdev;
struct in6_addr *nexthop;
struct ipv6hdr *ip6h;
struct rt6_info *rt;
if (skb->protocol != htons(ETH_P_IPV6))
return NF_ACCEPT;
if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0)
return NF_ACCEPT;
tuplehash = flow_offload_lookup(flow_table, &tuple);
if (tuplehash == NULL)
return NF_ACCEPT;
outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
if (!outdev)
return NF_ACCEPT;
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
return NF_ACCEPT;
if (skb_try_make_writable(skb, sizeof(*ip6h)))
return NF_DROP;
if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
nf_flow_nat_ipv6(flow, skb, dir) < 0)
return NF_DROP;
flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
ip6h = ipv6_hdr(skb);
ip6h->hop_limit--;
skb->dev = outdev;
nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
return NF_STOLEN;
}
/**
* tcf_csum_skb_nextlayer - Get next layer pointer
* @skb: sk_buff to use
* @ihl: previous summed headers length
* @ipl: complete packet length
* @jhl: next header length
*
* Check the expected next layer availability in the specified sk_buff.
* Return the next layer pointer if pass, NULL otherwise.
*/
static void *tcf_csum_skb_nextlayer(struct sk_buff *skb,
unsigned int ihl, unsigned int ipl,
unsigned int jhl)
{
int ntkoff = skb_network_offset(skb);
int hl = ihl + jhl;
if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) ||
skb_try_make_writable(skb, hl + ntkoff))
return NULL;
else
return (void *)(skb_network_header(skb) + ihl);
}
static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
struct in6_addr *addr,
struct in6_addr *new_addr)
{
struct tcphdr *tcph;
if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
skb_try_make_writable(skb, thoff + sizeof(*tcph)))
return -1;
tcph = (void *)(skb_network_header(skb) + thoff);
inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32,
new_addr->s6_addr32, true);
return 0;
}
static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
struct in6_addr *addr,
struct in6_addr *new_addr)
{
struct udphdr *udph;
if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
skb_try_make_writable(skb, thoff + sizeof(*udph)))
return -1;
udph = (void *)(skb_network_header(skb) + thoff);
if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32,
new_addr->s6_addr32, true);
if (!udph->check)
udph->check = CSUM_MANGLED_0;
}
return 0;
}
static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_nat *p = to_tcf_nat(a);
struct iphdr *iph;
__be32 old_addr;
__be32 new_addr;
__be32 mask;
__be32 addr;
int egress;
int action;
int ihl;
int noff;
spin_lock(&p->tcf_lock);
tcf_lastuse_update(&p->tcf_tm);
old_addr = p->old_addr;
new_addr = p->new_addr;
mask = p->mask;
egress = p->flags & TCA_NAT_FLAG_EGRESS;
action = p->tcf_action;
bstats_update(&p->tcf_bstats, skb);
spin_unlock(&p->tcf_lock);
if (unlikely(action == TC_ACT_SHOT))
goto drop;
noff = skb_network_offset(skb);
if (!pskb_may_pull(skb, sizeof(*iph) + noff))
goto drop;
iph = ip_hdr(skb);
if (egress)
addr = iph->saddr;
else
addr = iph->daddr;
if (!((old_addr ^ addr) & mask)) {
if (skb_try_make_writable(skb, sizeof(*iph) + noff))
goto drop;
new_addr &= mask;
new_addr |= addr & ~mask;
/* Rewrite IP header */
iph = ip_hdr(skb);
if (egress)
iph->saddr = new_addr;
else
iph->daddr = new_addr;
csum_replace4(&iph->check, addr, new_addr);
} else if ((iph->frag_off & htons(IP_OFFSET)) ||
iph->protocol != IPPROTO_ICMP) {
goto out;
}
ihl = iph->ihl * 4;
/* It would be nice to share code with stateful NAT. */
switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
case IPPROTO_TCP:
{
struct tcphdr *tcph;
if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
goto drop;
tcph = (void *)(skb_network_header(skb) + ihl);
inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr,
true);
break;
}
case IPPROTO_UDP:
{
struct udphdr *udph;
if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
goto drop;
udph = (void *)(skb_network_header(skb) + ihl);
if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&udph->check, skb, addr,
new_addr, true);
if (!udph->check)
udph->check = CSUM_MANGLED_0;
}
break;
}
case IPPROTO_ICMP:
{
struct icmphdr *icmph;
if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
if ((icmph->type != ICMP_DEST_UNREACH) &&
(icmph->type != ICMP_TIME_EXCEEDED) &&
(icmph->type != ICMP_PARAMETERPROB))
break;
if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) +
noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
iph = (void *)(icmph + 1);
if (egress)
addr = iph->daddr;
else
addr = iph->saddr;
if ((old_addr ^ addr) & mask)
break;
if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
sizeof(*iph) + noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
iph = (void *)(icmph + 1);
new_addr &= mask;
new_addr |= addr & ~mask;
/* XXX Fix up the inner checksums. */
if (egress)
iph->daddr = new_addr;
else
iph->saddr = new_addr;
inet_proto_csum_replace4(&icmph->checksum, skb, addr, new_addr,
false);
break;
}
default:
break;
}
out:
return action;
drop:
spin_lock(&p->tcf_lock);
p->tcf_qstats.drops++;
spin_unlock(&p->tcf_lock);
return TC_ACT_SHOT;
}
