static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
struct nf_conn_nat *nat;
enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
unsigned int ret;
if (ct == NULL || nf_ct_is_untracked(ct))
return NF_ACCEPT;
NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
nat = nfct_nat(ct);
if (nat == NULL) {
/* Conntrack module was loaded late, can't add extension. */
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
if (nat == NULL)
return NF_ACCEPT;
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED + IP_CT_IS_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
ops->hooknum))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall through */
case IP_CT_NEW:
if (nf_nat_initialized(ct, maniptype))
break;
ret = nft_do_chain(ops, skb, in, out, okfn);
if (ret != NF_ACCEPT)
return ret;
if (!nf_nat_initialized(ct, maniptype)) {
ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
if (ret != NF_ACCEPT)
return ret;
}
default:
break;
}
return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
}
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;
}
/* This function is called under rcu_read_lock() */
static int
nfnetlink_parse_nat_setup(struct nf_conn *ct,
enum nf_nat_manip_type manip,
const struct nlattr *attr)
{
struct nf_nat_range range;
const struct nf_nat_l3proto *l3proto;
int err;
/* Should not happen, restricted to creating new conntracks
* via ctnetlink.
*/
if (WARN_ON_ONCE(nf_nat_initialized(ct, manip)))
return -EEXIST;
/* Make sure that L3 NAT is there by when we call nf_nat_setup_info to
* attach the null binding, otherwise this may oops.
*/
l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
if (l3proto == NULL)
return -EAGAIN;
/* No NAT information has been passed, allocate the null-binding */
if (attr == NULL)
return __nf_nat_alloc_null_binding(ct, manip);
err = nfnetlink_parse_nat(attr, ct, &range, l3proto);
if (err < 0)
return err;
return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0;
}
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;
#ifdef CONFIG_ATHRS_HW_NAT
void (*athr_ct_check_layer2if)(struct sk_buff *, struct nf_conn *, int nf_nat_manip_type);
#endif
ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table);
#ifdef CONFIG_ATHRS_HW_NAT
if (athr_nat_sw_ops) {
athr_ct_check_layer2if = rcu_dereference(athr_nat_sw_ops->check_layer2if);
if (athr_ct_check_layer2if)
athr_ct_check_layer2if(skb, ct, HOOK2MANIP(hooknum));
}
#endif
if (ret == NF_ACCEPT) {
if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
/* NUL mapping */
ret = alloc_null_binding(ct, hooknum);
}
return ret;
}
static unsigned 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);
unsigned int ret;
ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table);
if (ret == NF_ACCEPT) {
if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
ret = alloc_null_binding(ct, hooknum);
}
return ret;
}
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)
{
int ret;
ret = ipt_do_table(skb, hooknum, in, out, &nat_table);
if (ret == NF_ACCEPT) {
if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
/* NUL mapping */
ret = alloc_null_binding(ct, hooknum);
}
return ret;
}
static unsigned int
nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
/* maniptype == SRC for postrouting. */
enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
/* We never see fragments: conntrack defrags on pre-routing
* and local-out, and nf_nat_out protects post-routing.
*/
NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
* packet filter it out, or implement conntrack/NAT for that
* protocol. 8) --RR
*/
if (!ct)
return NF_ACCEPT;
/* Don't try to NAT if this packet is not conntracked */
if (nf_ct_is_untracked(ct))
return NF_ACCEPT;
nat = nfct_nat(ct);
if (!nat) {
/* NAT module was loaded late. */
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
if (nat == NULL) {
pr_debug("failed to add NAT extension\n");
return NF_ACCEPT;
}
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
ops->hooknum))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
*/
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
if (ret != NF_ACCEPT)
return ret;
} else {
pr_debug("Already setup manip %s for ct %p\n",
maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
goto oif_changed;
}
break;
default:
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == IP_CT_ESTABLISHED_REPLY);
if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
goto oif_changed;
}
return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
oif_changed:
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_DROP;
}
static unsigned int
nf_nat_ipv6_fn(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
__be16 frag_off;
int hdrlen;
u8 nexthdr;
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
* packet filter it out, or implement conntrack/NAT for that
* protocol. 8) --RR
*/
if (!ct)
return NF_ACCEPT;
/* Don't try to NAT if this packet is not conntracked */
if (nf_ct_is_untracked(ct))
return NF_ACCEPT;
nat = nfct_nat(ct);
if (!nat) {
/* NAT module was loaded late. */
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
if (nat == NULL) {
pr_debug("failed to add NAT extension\n");
return NF_ACCEPT;
}
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
nexthdr = ipv6_hdr(skb)->nexthdr;
hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
&nexthdr, &frag_off);
if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
hooknum, hdrlen))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
*/
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
if (ret != NF_ACCEPT)
return ret;
} else {
pr_debug("Already setup manip %s for ct %p\n",
maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
goto oif_changed;
}
break;
default:
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == IP_CT_ESTABLISHED_REPLY);
if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
goto oif_changed;
}
return nf_nat_packet(ct, ctinfo, hooknum, skb);
oif_changed:
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_DROP;
}
static unsigned int
nf_nat_fn(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
/* maniptype == SRC for postrouting. */
enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
/* We never see fragments: conntrack defrags on pre-routing
and local-out, and nf_nat_out protects post-routing. */
NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
have dropped it. Hence it's the user's responsibilty to
packet filter it out, or implement conntrack/NAT for that
protocol. 8) --RR */
if (!ct)
return NF_ACCEPT;
/* Don't try to NAT if this packet is not conntracked */
if (ct == &nf_conntrack_untracked)
return NF_ACCEPT;
nat = nfct_nat(ct);
if (!nat) {
/* NAT module was loaded late. */
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
if (nat == NULL) {
pr_debug("failed to add NAT extension\n");
return NF_ACCEPT;
}
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(ct, ctinfo,
hooknum, skb))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
or local packets.. */
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
if (hooknum == NF_INET_LOCAL_IN)
/* LOCAL_IN hook doesn't have a chain! */
ret = alloc_null_binding(ct, hooknum);
else
ret = nf_nat_rule_find(skb, hooknum, in, out,
ct);
if (ret != NF_ACCEPT) {
return ret;
}
} else
pr_debug("Already setup manip %s for ct %p\n",
maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
default:
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
}
return nf_nat_packet(ct, ctinfo, hooknum, skb);
}
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);
}
static unsigned int
nf_nat_fn(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
/* maniptype == SRC for postrouting. */
enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
/* We never see fragments: conntrack defrags on pre-routing
and local-out, and nf_nat_out protects post-routing. */
NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
have dropped it. Hence it's the user's responsibilty to
packet filter it out, or implement conntrack/NAT for that
protocol. 8) --RR */
if (!ct) {
/* Exception: ICMP redirect to new connection (not in
hash table yet). We must not let this through, in
case we're doing NAT to the same network. */
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
struct icmphdr _hdr, *hp;
hp = skb_header_pointer(skb, ip_hdrlen(skb),
sizeof(_hdr), &_hdr);
if (hp != NULL &&
hp->type == ICMP_REDIRECT)
return NF_DROP;
}
return NF_ACCEPT;
}
/* Don't try to NAT if this packet is not conntracked */
if (ct == &nf_conntrack_untracked)
return NF_ACCEPT;
nat = nfct_nat(ct);
if (!nat)
return NF_ACCEPT;
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(ct, ctinfo,
hooknum, skb))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
or local packets.. */
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
if (unlikely(nf_ct_is_confirmed(ct)))
/* NAT module was loaded late */
ret = alloc_null_binding_confirmed(ct, hooknum);
else if (hooknum == NF_IP_LOCAL_IN)
/* LOCAL_IN hook doesn't have a chain! */
ret = alloc_null_binding(ct, hooknum);
else
ret = nf_nat_rule_find(skb, hooknum, in, out,
ct);
if (ret != NF_ACCEPT) {
return ret;
}
ipt_cone_place_in_hashes(ct);
} else
DEBUGP("Already setup manip %s for ct %p\n",
maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
default:
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
}
return nf_nat_packet(ct, ctinfo, hooknum, skb);
}
unsigned int
nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
/* maniptype == SRC for postrouting. */
enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
* packet filter it out, or implement conntrack/NAT for that
* protocol. 8) --RR
*/
if (!ct)
return NF_ACCEPT;
nat = nfct_nat(ct);
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
state->hook))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Only ICMPs can be IP_CT_IS_REPLY: */
/* fall through */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
*/
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
ret = do_chain(priv, skb, state, ct);
if (ret != NF_ACCEPT)
return ret;
if (nf_nat_initialized(ct, HOOK2MANIP(state->hook)))
break;
ret = nf_nat_alloc_null_binding(ct, state->hook);
if (ret != NF_ACCEPT)
return ret;
} else {
pr_debug("Already setup manip %s for ct %p\n",
maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
if (nf_nat_oif_changed(state->hook, ctinfo, nat,
state->out))
goto oif_changed;
}
break;
default:
/* ESTABLISHED */
WARN_ON(ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED_REPLY);
if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out))
goto oif_changed;
}
return nf_nat_packet(ct, ctinfo, state->hook, skb);
oif_changed:
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_DROP;
}
static unsigned int
nf_nat_fn(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
return NF_ACCEPT;
if (ct == &nf_conntrack_untracked)
return NF_ACCEPT;
nat = nfct_nat(ct);
if (!nat) {
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
if (nat == NULL) {
pr_debug("failed to add NAT extension\n");
return NF_ACCEPT;
}
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(ct, ctinfo,
hooknum, skb))
return NF_DROP;
else
return NF_ACCEPT;
}
case IP_CT_NEW:
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
if (hooknum == NF_INET_LOCAL_IN)
ret = alloc_null_binding(ct, hooknum);
else
ret = nf_nat_rule_find(skb, hooknum, in, out,
ct);
if (ret != NF_ACCEPT) {
return ret;
}
} else
pr_debug("Already setup manip %s for ct %p\n",
maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
default:
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
}
return nf_nat_packet(ct, ctinfo, hooknum, skb);
}
