/* Do packet manipulations according to nf_nat_setup_info. */
unsigned int nf_nat_packet(struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int hooknum,
struct sk_buff *skb)
{
const struct nf_nat_l3proto *l3proto;
const struct nf_nat_l4proto *l4proto;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
unsigned long statusbit;
enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum);
if (mtype == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
/* Invert if this is reply dir. */
if (dir == IP_CT_DIR_REPLY)
statusbit ^= IPS_NAT_MASK;
/* Non-atomic: these bits don't change. */
if (ct->status & statusbit) {
struct nf_conntrack_tuple target;
/* We are aiming to look like inverse of other direction. */
nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
l3proto = __nf_nat_l3proto_find(target.src.l3num);
l4proto = __nf_nat_l4proto_find(target.src.l3num,
target.dst.protonum);
if (!l3proto->manip_pkt(skb, 0, l4proto, &target, mtype))
return NF_DROP;
}
return NF_ACCEPT;
}
/* Only called for SRC manip */
static int
find_appropriate_src(struct net *net,
const struct nf_conntrack_zone *zone,
const struct nf_nat_l3proto *l3proto,
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
const struct nf_nat_range *range)
{
const struct nf_conn *ct;
struct nf_nat_conn_key key = {
.net = net,
.tuple = tuple,
.zone = zone
};
ct = rhashtable_lookup_fast(&nf_nat_bysource_table, &key,
nf_nat_bysource_params);
if (!ct)
return 0;
nf_ct_invert_tuplepr(result,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
result->dst = tuple->dst;
return in_range(l3proto, l4proto, result, range);
}
/* Only called for SRC manip */
static int
find_appropriate_src(struct net *net,
const struct nf_conntrack_zone *zone,
const struct nf_nat_l3proto *l3proto,
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
const struct nf_nat_range *range)
{
const struct nf_conn *ct;
struct nf_nat_conn_key key = {
.net = net,
.tuple = tuple,
.zone = zone
};
struct rhlist_head *hl;
hl = rhltable_lookup(&nf_nat_bysource_table, &key,
nf_nat_bysource_params);
if (!hl)
return 0;
ct = container_of(hl, typeof(*ct), nat_bysource);
nf_ct_invert_tuplepr(result,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
result->dst = tuple->dst;
return in_range(l3proto, l4proto, result, range);
}
/* Only called for SRC manip */
static int
find_appropriate_src(struct net *net,
const struct nf_conntrack_zone *zone,
const struct nf_nat_l3proto *l3proto,
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
const struct nf_nat_range *range)
{
const struct nf_conn *ct;
struct nf_nat_conn_key key = {
.net = net,
.tuple = tuple,
.zone = zone
};
struct rhlist_head *hl, *h;
hl = rhltable_lookup(&nf_nat_bysource_table, &key,
nf_nat_bysource_params);
rhl_for_each_entry_rcu(ct, h, hl, nat_bysource) {
nf_ct_invert_tuplepr(result,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
result->dst = tuple->dst;
if (in_range(l3proto, l4proto, result, range))
return 1;
}
/* Is this tuple already taken? (not by us) */
int
nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
const struct nf_conn *ignored_conntrack)
{
/* Conntrack tracking doesn't keep track of outgoing tuples; only
* incoming ones. NAT means they don't have a fixed mapping,
* so we invert the tuple and look for the incoming reply.
*
* We could keep a separate hash if this proves too slow.
*/
struct nf_conntrack_tuple reply;
nf_ct_invert_tuplepr(&reply, tuple);
return nf_conntrack_tuple_taken(&reply, ignored_conntrack);
}
int nf_nat_rule_find(struct sk_buff *skb,
unsigned int hooknum,
const struct net_device *in,
const struct net_device *out,
struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
int ret;
ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table);
if (ret == NF_ACCEPT) {
/*
* Reason: Hairpin translation for TCP/UDP not working
* Modified: Ubicom
* Date: 2009.11.18
*/
if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum))) {
#if defined(CONFIG_IP_NF_TARGET_SNATP2P)
if ((HOOK2MANIP(hooknum) == IP_NAT_MANIP_DST)){
struct nf_conntrack_tuple reply_tuple, new_tuple;
nf_ct_invert_tuplepr(&reply_tuple,
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
if (find_appropriate_p2p_dst(net, &reply_tuple, &new_tuple)) {
struct nf_nat_range range;
/* This must be a fresh one. */
BUG_ON(ct->status & IPS_SNATP2P_DONE_MASK);
ct->status |= IPS_SNATP2P_DST;
range.flags = (IP_NAT_RANGE_MAP_IPS);
//range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
//range.min = range.max = new_tuple.dst.u;
range.min_ip = range.max_ip = new_tuple.dst.u3.ip;
ret = nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST);
range.min_ip = range.max_ip = new_tuple.src.u3.ip;
ret = nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC);
}
}
if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
#endif
/* NUL mapping */
ret = alloc_null_binding(ct, hooknum);
}
}
return ret;
}
static void pptp_expectfn(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
struct net *net = nf_ct_net(ct);
typeof(nf_nat_pptp_hook_expectfn) nf_nat_pptp_expectfn;
pr_debug("increasing timeouts\n");
/* increase timeout of GRE data channel conntrack entry */
ct->proto.gre.timeout = PPTP_GRE_TIMEOUT;
ct->proto.gre.stream_timeout = PPTP_GRE_STREAM_TIMEOUT;
/* Can you see how rusty this code is, compared with the pre-2.6.11
* one? That's what happened to my shiny newnat of 2002 ;( -HW */
rcu_read_lock();
nf_nat_pptp_expectfn = rcu_dereference(nf_nat_pptp_hook_expectfn);
if (nf_nat_pptp_expectfn && ct->master->status & IPS_NAT_MASK)
nf_nat_pptp_expectfn(ct, exp);
else {
struct nf_conntrack_tuple inv_t;
struct nf_conntrack_expect *exp_other;
/* obviously this tuple inversion only works until you do NAT */
nf_ct_invert_tuplepr(&inv_t, &exp->tuple);
pr_debug("trying to unexpect other dir: ");
nf_ct_dump_tuple(&inv_t);
exp_other = nf_ct_expect_find_get(net, &inv_t);
if (exp_other) {
/* delete other expectation. */
pr_debug("found\n");
nf_ct_unexpect_related(exp_other);
nf_ct_expect_put(exp_other);
} else {
pr_debug("not found\n");
}
}
rcu_read_unlock();
}
unsigned int
nf_nat_setup_info(struct nf_conn *ct,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype)
{
struct nf_conntrack_tuple curr_tuple, new_tuple;
struct nf_conn_nat *nat;
/* nat helper or nfctnetlink also setup binding */
nat = nf_ct_nat_ext_add(ct);
if (nat == NULL)
return NF_ACCEPT;
NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
maniptype == NF_NAT_MANIP_DST);
BUG_ON(nf_nat_initialized(ct, maniptype));
/* What we've got will look like inverse of reply. Normally
* this is what is in the conntrack, except for prior
* manipulations (future optimization: if num_manips == 0,
* orig_tp = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)
*/
nf_ct_invert_tuplepr(&curr_tuple,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype);
if (!nf_ct_tuple_equal(&new_tuple, &curr_tuple)) {
struct nf_conntrack_tuple reply;
/* Alter conntrack table so will recognize replies. */
nf_ct_invert_tuplepr(&reply, &new_tuple);
nf_conntrack_alter_reply(ct, &reply);
/* Non-atomic: we own this at the moment. */
if (maniptype == NF_NAT_MANIP_SRC)
ct->status |= IPS_SRC_NAT;
else
ct->status |= IPS_DST_NAT;
if (nfct_help(ct))
if (!nfct_seqadj_ext_add(ct))
return NF_DROP;
}
if (maniptype == NF_NAT_MANIP_SRC) {
int err;
err = rhashtable_insert_fast(&nf_nat_bysource_table,
&ct->nat_bysource,
nf_nat_bysource_params);
if (err)
return NF_DROP;
}
/* It's done. */
if (maniptype == NF_NAT_MANIP_DST)
ct->status |= IPS_DST_NAT_DONE;
else
ct->status |= IPS_SRC_NAT_DONE;
return NF_ACCEPT;
}
unsigned int
nf_nat_setup_info(struct nf_conn *ct,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype)
{
struct nf_conntrack_tuple curr_tuple, new_tuple;
/* Can't setup nat info for confirmed ct. */
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
maniptype == NF_NAT_MANIP_DST);
BUG_ON(nf_nat_initialized(ct, maniptype));
/* What we've got will look like inverse of reply. Normally
* this is what is in the conntrack, except for prior
* manipulations (future optimization: if num_manips == 0,
* orig_tp = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)
*/
nf_ct_invert_tuplepr(&curr_tuple,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype);
if (!nf_ct_tuple_equal(&new_tuple, &curr_tuple)) {
struct nf_conntrack_tuple reply;
/* Alter conntrack table so will recognize replies. */
nf_ct_invert_tuplepr(&reply, &new_tuple);
nf_conntrack_alter_reply(ct, &reply);
/* Non-atomic: we own this at the moment. */
if (maniptype == NF_NAT_MANIP_SRC)
ct->status |= IPS_SRC_NAT;
else
ct->status |= IPS_DST_NAT;
if (nfct_help(ct))
if (!nfct_seqadj_ext_add(ct))
return NF_DROP;
}
if (maniptype == NF_NAT_MANIP_SRC) {
struct nf_nat_conn_key key = {
.net = nf_ct_net(ct),
.tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
.zone = nf_ct_zone(ct),
};
int err;
err = rhltable_insert_key(&nf_nat_bysource_table,
&key,
&ct->nat_bysource,
nf_nat_bysource_params);
if (err)
return NF_DROP;
}
/* It's done. */
if (maniptype == NF_NAT_MANIP_DST)
ct->status |= IPS_DST_NAT_DONE;
else
ct->status |= IPS_SRC_NAT_DONE;
return NF_ACCEPT;
}
EXPORT_SYMBOL(nf_nat_setup_info);
static unsigned int
__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip)
{
/* Force range to this IP; let proto decide mapping for
* per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
* Use reply in case it's already been mangled (eg local packet).
*/
union nf_inet_addr ip =
(manip == NF_NAT_MANIP_SRC ?
ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 :
ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3);
struct nf_nat_range range = {
.flags = NF_NAT_RANGE_MAP_IPS,
.min_addr = ip,
.max_addr = ip,
};
return nf_nat_setup_info(ct, &range, manip);
}
unsigned int
nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
{
return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum));
}
EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding);
/* Do packet manipulations according to nf_nat_setup_info. */
unsigned int nf_nat_packet(struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int hooknum,
struct sk_buff *skb)
{
const struct nf_nat_l3proto *l3proto;
const struct nf_nat_l4proto *l4proto;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
unsigned long statusbit;
enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum);
if (mtype == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
/* Invert if this is reply dir. */
if (dir == IP_CT_DIR_REPLY)
statusbit ^= IPS_NAT_MASK;
/* Non-atomic: these bits don't change. */
if (ct->status & statusbit) {
struct nf_conntrack_tuple target;
/* We are aiming to look like inverse of other direction. */
nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
l3proto = __nf_nat_l3proto_find(target.src.l3num);
l4proto = __nf_nat_l4proto_find(target.src.l3num,
target.dst.protonum);
if (!l3proto->manip_pkt(skb, 0, l4proto, &target, mtype))
return NF_DROP;
}
return NF_ACCEPT;
}
EXPORT_SYMBOL_GPL(nf_nat_packet);
struct nf_nat_proto_clean {
u8 l3proto;
u8 l4proto;
};
/* kill conntracks with affected NAT section */
static int nf_nat_proto_remove(struct nf_conn *i, void *data)
{
const struct nf_nat_proto_clean *clean = data;
if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) ||
(clean->l4proto && nf_ct_protonum(i) != clean->l4proto))
return 0;
return i->status & IPS_NAT_MASK ? 1 : 0;
}
static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
{
if (nf_nat_proto_remove(ct, data))
return 1;
if ((ct->status & IPS_SRC_NAT_DONE) == 0)
return 0;
/* This netns is being destroyed, and conntrack has nat null binding.
* Remove it from bysource hash, as the table will be freed soon.
*
* Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
* will delete entry from already-freed table.
*/
clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource,
nf_nat_bysource_params);
/* don't delete conntrack. Although that would make things a lot
* simpler, we'd end up flushing all conntracks on nat rmmod.
*/
return 0;
}
static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
{
struct nf_nat_proto_clean clean = {
.l3proto = l3proto,
.l4proto = l4proto,
};
struct net *net;
rtnl_lock();
for_each_net(net)
nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0);
rtnl_unlock();
}
static void nf_nat_l3proto_clean(u8 l3proto)
{
struct nf_nat_proto_clean clean = {
.l3proto = l3proto,
};
struct net *net;
rtnl_lock();
for_each_net(net)
nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0);
rtnl_unlock();
}
/* Protocol registration. */
int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto)
{
const struct nf_nat_l4proto **l4protos;
unsigned int i;
int ret = 0;
mutex_lock(&nf_nat_proto_mutex);
if (nf_nat_l4protos[l3proto] == NULL) {
l4protos = kmalloc(IPPROTO_MAX * sizeof(struct nf_nat_l4proto *),
GFP_KERNEL);
if (l4protos == NULL) {
ret = -ENOMEM;
goto out;
}
for (i = 0; i < IPPROTO_MAX; i++)
RCU_INIT_POINTER(l4protos[i], &nf_nat_l4proto_unknown);
/* Before making proto_array visible to lockless readers,
* we must make sure its content is committed to memory.
*/
smp_wmb();
nf_nat_l4protos[l3proto] = l4protos;
}
if (rcu_dereference_protected(
nf_nat_l4protos[l3proto][l4proto->l4proto],
lockdep_is_held(&nf_nat_proto_mutex)
) != &nf_nat_l4proto_unknown) {
ret = -EBUSY;
goto out;
}
RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto], l4proto);
out:
mutex_unlock(&nf_nat_proto_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(nf_nat_l4proto_register);
/* No one stores the protocol anywhere; simply delete it. */
void nf_nat_l4proto_unregister(u8 l3proto, const struct nf_nat_l4proto *l4proto)
{
mutex_lock(&nf_nat_proto_mutex);
RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto],
&nf_nat_l4proto_unknown);
mutex_unlock(&nf_nat_proto_mutex);
synchronize_rcu();
nf_nat_l4proto_clean(l3proto, l4proto->l4proto);
}
int nf_nat_icmp_reply_translation(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int hooknum)
{
struct {
struct icmphdr icmp;
struct iphdr ip;
} *inside;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
unsigned int hdrlen = ip_hdrlen(skb);
const struct nf_nat_l4proto *l4proto;
struct nf_conntrack_tuple target;
unsigned long statusbit;
WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY);
if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
return 0;
if (nf_ip_checksum(skb, hooknum, hdrlen, 0))
return 0;
inside = (void *)skb->data + hdrlen;
if (inside->icmp.type == ICMP_REDIRECT) {
if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
return 0;
if (ct->status & IPS_NAT_MASK)
return 0;
}
if (manip == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
/* Invert if this is reply direction */
if (dir == IP_CT_DIR_REPLY)
statusbit ^= IPS_NAT_MASK;
if (!(ct->status & statusbit))
return 1;
l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, inside->ip.protocol);
if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp),
l4proto, &ct->tuplehash[!dir].tuple, !manip))
return 0;
if (skb->ip_summed != CHECKSUM_PARTIAL) {
/* Reloading "inside" here since manip_pkt may reallocate */
inside = (void *)skb->data + hdrlen;
inside->icmp.checksum = 0;
inside->icmp.checksum =
csum_fold(skb_checksum(skb, hdrlen,
skb->len - hdrlen, 0));
}
/* Change outer to look like the reply to an incoming packet */
nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, 0);
if (!nf_nat_ipv4_manip_pkt(skb, 0, l4proto, &target, manip))
return 0;
return 1;
}
int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int hooknum,
unsigned int hdrlen)
{
struct {
struct icmp6hdr icmp6;
struct ipv6hdr ip6;
} *inside;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
const struct nf_nat_l4proto *l4proto;
struct nf_conntrack_tuple target;
unsigned long statusbit;
NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY);
if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
return 0;
if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6))
return 0;
inside = (void *)skb->data + hdrlen;
if (inside->icmp6.icmp6_type == NDISC_REDIRECT) {
if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
return 0;
if (ct->status & IPS_NAT_MASK)
return 0;
}
if (manip == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
/* Invert if this is reply direction */
if (dir == IP_CT_DIR_REPLY)
statusbit ^= IPS_NAT_MASK;
if (!(ct->status & statusbit))
return 1;
l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, inside->ip6.nexthdr);
if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6),
l4proto, &ct->tuplehash[!dir].tuple, !manip))
return 0;
if (skb->ip_summed != CHECKSUM_PARTIAL) {
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
inside = (void *)skb->data + hdrlen;
inside->icmp6.icmp6_cksum = 0;
inside->icmp6.icmp6_cksum =
csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
skb->len - hdrlen, IPPROTO_ICMPV6,
csum_partial(&inside->icmp6,
skb->len - hdrlen, 0));
}
nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, IPPROTO_ICMPV6);
if (!nf_nat_ipv6_manip_pkt(skb, 0, l4proto, &target, manip))
return 0;
return 1;
}