static
struct nf_conn_colo *nfct_create_colo(struct nf_conn *ct, u32 vm_pid, u32 flag)
{
struct nf_conn_colo *conn = NULL;
size_t length = 0;
if (nf_ct_is_confirmed(ct)) {
pr_dbg("conntrack %p is confirmed!\n", ct);
//return NULL;
}
if (nf_ct_protonum(ct) == IPPROTO_TCP) {
length = sizeof(union nf_conn_colo_tcp);
if (flag & COLO_CONN_SECONDARY) {
/* seq adjust is only meaningful for TCP conn */
if (!nfct_seqadj_ext_add(ct)) {
pr_dbg("failed to add SEQADJ extension\n");
}
}
}
conn = (struct nf_conn_colo *) nf_ct_ext_add_length(ct, NF_CT_EXT_COLO,
length, GFP_ATOMIC);
if (!conn) {
pr_dbg("add extend failed\n");
return NULL;
}
conn->nfct = &ct->ct_general;
return conn;
}
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);
}
struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct)
{
struct nf_conn_nat *nat = nfct_nat(ct);
if (nat)
return nat;
if (!nf_ct_is_confirmed(ct))
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
return nat;
}
/* deliver cached events and clear cache entry - must be called with locally
* disabled softirqs */
static inline void
__nf_ct_deliver_cached_events(struct nf_conntrack_ecache *ecache)
{
if (nf_ct_is_confirmed(ecache->ct) && !nf_ct_is_dying(ecache->ct)
&& ecache->events)
atomic_notifier_call_chain(&nf_conntrack_chain, ecache->events,
ecache->ct);
ecache->events = 0;
nf_ct_put(ecache->ct);
ecache->ct = NULL;
}
/* deliver cached events and clear cache entry - must be called with locally
* disabled softirqs */
void nf_ct_deliver_cached_events(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
unsigned long events, missed;
struct nf_ct_event_notifier *notify;
struct nf_conntrack_ecache *e;
struct nf_ct_event item;
int ret;
rcu_read_lock();
notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
if (notify == NULL)
goto out_unlock;
e = nf_ct_ecache_find(ct);
if (e == NULL)
goto out_unlock;
events = xchg(&e->cache, 0);
if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct) || !events)
goto out_unlock;
/* We make a copy of the missed event cache without taking
* the lock, thus we may send missed events twice. However,
* this does not harm and it happens very rarely. */
missed = e->missed;
if (!((events | missed) & e->ctmask))
goto out_unlock;
item.ct = ct;
item.portid = 0;
item.report = 0;
ret = notify->fcn(events | missed, &item);
if (likely(ret >= 0 && !missed))
goto out_unlock;
spin_lock_bh(&ct->lock);
if (ret < 0)
e->missed |= events;
else
e->missed &= ~missed;
spin_unlock_bh(&ct->lock);
out_unlock:
rcu_read_unlock();
}
void nf_ct_deliver_cached_events(struct nf_conn *ct)
{
unsigned long events, missed;
struct nf_conntrack_ecache *e;
struct nf_ct_event item;
int ret = 0;
e = nf_ct_ecache_find(ct);
if (e == NULL)
return;
events = xchg(&e->cache, 0);
if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct) || !events)
return;
/* We make a copy of the missed event cache without taking
* the lock, thus we may send missed events twice. However,
* this does not harm and it happens very rarely. */
missed = e->missed;
if (!((events | missed) & e->ctmask))
return;
item.ct = ct;
item.pid = 0;
item.report = 0;
atomic_notifier_call_chain(&nf_conntrack_chain,
events | missed,
&item);
if (likely(ret >= 0 && !missed))
return;
spin_lock_bh(&ct->lock);
if (ret < 0)
e->missed |= events;
else
e->missed &= ~missed;
spin_unlock_bh(&ct->lock);
}
/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has
* previously sent the packet to conntrack via the ct action.
*/
static void ovs_ct_update_key(const struct sk_buff *skb,
struct sw_flow_key *key, bool post_ct)
{
const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
u8 state = 0;
ct = nf_ct_get(skb, &ctinfo);
if (ct) {
state = ovs_ct_get_state(ctinfo);
if (!nf_ct_is_confirmed(ct))
state |= OVS_CS_F_NEW;
if (ct->master)
state |= OVS_CS_F_RELATED;
zone = nf_ct_zone(ct);
} else if (post_ct) {
state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID;
}
__ovs_ct_update_key(key, state, zone, ct);
}
/* Returns verdict for packet, and may modify conntracktype */
int nf_conntrack_udp_packet(struct nf_conn *ct,
struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
unsigned int *timeouts;
if (udp_error(skb, dataoff, state))
return -NF_ACCEPT;
timeouts = nf_ct_timeout_lookup(ct);
if (!timeouts)
timeouts = udp_get_timeouts(nf_ct_net(ct));
if (!nf_ct_is_confirmed(ct))
ct->proto.udp.stream_ts = 2 * HZ + jiffies;
/* If we've seen traffic both ways, this is some kind of UDP
* stream. Set Assured.
*/
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
unsigned long extra = timeouts[UDP_CT_UNREPLIED];
/* Still active after two seconds? Extend timeout. */
if (time_after(jiffies, ct->proto.udp.stream_ts))
extra = timeouts[UDP_CT_REPLIED];
nf_ct_refresh_acct(ct, ctinfo, skb, extra);
/* Also, more likely to be important, and not a probe */
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else {
nf_ct_refresh_acct(ct, ctinfo, skb,
timeouts[UDP_CT_UNREPLIED]);
}
return NF_ACCEPT;
}
/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has
* previously sent the packet to conntrack via the ct action. If
* 'keep_nat_flags' is true, the existing NAT flags retained, else they are
* initialized from the connection status.
*/
static void ovs_ct_update_key(const struct sk_buff *skb,
const struct ovs_conntrack_info *info,
struct sw_flow_key *key, bool post_ct,
bool keep_nat_flags)
{
const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
u8 state = 0;
ct = nf_ct_get(skb, &ctinfo);
if (ct) {
state = ovs_ct_get_state(ctinfo);
/* All unconfirmed entries are NEW connections. */
if (!nf_ct_is_confirmed(ct))
state |= OVS_CS_F_NEW;
/* OVS persists the related flag for the duration of the
* connection.
*/
if (ct->master)
state |= OVS_CS_F_RELATED;
if (keep_nat_flags) {
state |= key->ct.state & OVS_CS_F_NAT_MASK;
} else {
if (ct->status & IPS_SRC_NAT)
state |= OVS_CS_F_SRC_NAT;
if (ct->status & IPS_DST_NAT)
state |= OVS_CS_F_DST_NAT;
}
zone = nf_ct_zone(ct);
} else if (post_ct) {
state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID;
if (info)
zone = &info->zone;
}
__ovs_ct_update_key(key, state, zone, ct);
}
/* Returns verdict for packet, or -1 for invalid. */
static int icmpv6_packet(struct nf_conn *ct,
struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
unsigned int *timeout = nf_ct_timeout_lookup(ct);
static const u8 valid_new[] = {
[ICMPV6_ECHO_REQUEST - 128] = 1,
[ICMPV6_NI_QUERY - 128] = 1
};
if (state->pf != NFPROTO_IPV6)
return -NF_ACCEPT;
if (!nf_ct_is_confirmed(ct)) {
int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128;
if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) {
/* Can't create a new ICMPv6 `conn' with this. */
pr_debug("icmpv6: can't create new conn with type %u\n",
type + 128);
nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple);
return -NF_ACCEPT;
}
}
if (!timeout)
timeout = icmpv6_get_timeouts(nf_ct_net(ct));
/* Do not immediately delete the connection after the first
successful reply to avoid excessive conntrackd traffic
and also to handle correctly ICMP echo reply duplicates. */
nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
return NF_ACCEPT;
}
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;
/* 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;
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);
}
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);
}
/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct nf_conn *ct,
struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
struct net *net = nf_ct_net(ct);
struct nf_tcp_net *tn = nf_tcp_pernet(net);
struct nf_conntrack_tuple *tuple;
enum tcp_conntrack new_state, old_state;
unsigned int index, *timeouts;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
struct tcphdr _tcph;
unsigned long timeout;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
if (th == NULL)
return -NF_ACCEPT;
if (tcp_error(th, skb, dataoff, state))
return -NF_ACCEPT;
if (!nf_ct_is_confirmed(ct) && !tcp_new(ct, skb, dataoff, th))
return -NF_ACCEPT;
spin_lock_bh(&ct->lock);
old_state = ct->proto.tcp.state;
dir = CTINFO2DIR(ctinfo);
index = get_conntrack_index(th);
new_state = tcp_conntracks[dir][index][old_state];
tuple = &ct->tuplehash[dir].tuple;
switch (new_state) {
case TCP_CONNTRACK_SYN_SENT:
if (old_state < TCP_CONNTRACK_TIME_WAIT)
break;
/* RFC 1122: "When a connection is closed actively,
* it MUST linger in TIME-WAIT state for a time 2xMSL
* (Maximum Segment Lifetime). However, it MAY accept
* a new SYN from the remote TCP to reopen the connection
* directly from TIME-WAIT state, if..."
* We ignore the conditions because we are in the
* TIME-WAIT state anyway.
*
* Handle aborted connections: we and the server
* think there is an existing connection but the client
* aborts it and starts a new one.
*/
if (((ct->proto.tcp.seen[dir].flags
| ct->proto.tcp.seen[!dir].flags)
& IP_CT_TCP_FLAG_CLOSE_INIT)
|| (ct->proto.tcp.last_dir == dir
&& ct->proto.tcp.last_index == TCP_RST_SET)) {
/* Attempt to reopen a closed/aborted connection.
* Delete this connection and look up again. */
spin_unlock_bh(&ct->lock);
/* Only repeat if we can actually remove the timer.
* Destruction may already be in progress in process
* context and we must give it a chance to terminate.
*/
if (nf_ct_kill(ct))
return -NF_REPEAT;
return NF_DROP;
}
/* Fall through */
case TCP_CONNTRACK_IGNORE:
/* Ignored packets:
*
* Our connection entry may be out of sync, so ignore
* packets which may signal the real connection between
* the client and the server.
*
* a) SYN in ORIGINAL
* b) SYN/ACK in REPLY
* c) ACK in reply direction after initial SYN in original.
*
* If the ignored packet is invalid, the receiver will send
* a RST we'll catch below.
*/
if (index == TCP_SYNACK_SET
&& ct->proto.tcp.last_index == TCP_SYN_SET
&& ct->proto.tcp.last_dir != dir
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* b) This SYN/ACK acknowledges a SYN that we earlier
* ignored as invalid. This means that the client and
* the server are both in sync, while the firewall is
* not. We get in sync from the previously annotated
* values.
*/
old_state = TCP_CONNTRACK_SYN_SENT;
new_state = TCP_CONNTRACK_SYN_RECV;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin =
ct->proto.tcp.last_win == 0 ?
1 : ct->proto.tcp.last_win;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale =
ct->proto.tcp.last_wscale;
ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
ct->proto.tcp.last_flags;
memset(&ct->proto.tcp.seen[dir], 0,
sizeof(struct ip_ct_tcp_state));
break;
}
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
ct->proto.tcp.last_seq = ntohl(th->seq);
ct->proto.tcp.last_end =
segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
ct->proto.tcp.last_win = ntohs(th->window);
/* a) This is a SYN in ORIGINAL. The client and the server
* may be in sync but we are not. In that case, we annotate
* the TCP options and let the packet go through. If it is a
* valid SYN packet, the server will reply with a SYN/ACK, and
* then we'll get in sync. Otherwise, the server potentially
* responds with a challenge ACK if implementing RFC5961.
*/
if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) {
struct ip_ct_tcp_state seen = {};
ct->proto.tcp.last_flags =
ct->proto.tcp.last_wscale = 0;
tcp_options(skb, dataoff, th, &seen);
if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_WINDOW_SCALE;
ct->proto.tcp.last_wscale = seen.td_scale;
}
if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_SACK_PERM;
}
/* Mark the potential for RFC5961 challenge ACK,
* this pose a special problem for LAST_ACK state
* as ACK is intrepretated as ACKing last FIN.
*/
if (old_state == TCP_CONNTRACK_LAST_ACK)
ct->proto.tcp.last_flags |=
IP_CT_EXP_CHALLENGE_ACK;
}
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "invalid packet ignored in "
"state %s ", tcp_conntrack_names[old_state]);
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Special case for SYN proxy: when the SYN to the server or
* the SYN/ACK from the server is lost, the client may transmit
* a keep-alive packet while in SYN_SENT state. This needs to
* be associated with the original conntrack entry in order to
* generate a new SYN with the correct sequence number.
*/
if (nfct_synproxy(ct) && old_state == TCP_CONNTRACK_SYN_SENT &&
index == TCP_ACK_SET && dir == IP_CT_DIR_ORIGINAL &&
ct->proto.tcp.last_dir == IP_CT_DIR_ORIGINAL &&
ct->proto.tcp.seen[dir].td_end - 1 == ntohl(th->seq)) {
pr_debug("nf_ct_tcp: SYN proxy client keep alive\n");
spin_unlock_bh(&ct->lock);
return NF_ACCEPT;
}
/* Invalid packet */
pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th), old_state);
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "invalid state");
return -NF_ACCEPT;
case TCP_CONNTRACK_TIME_WAIT:
/* RFC5961 compliance cause stack to send "challenge-ACK"
* e.g. in response to spurious SYNs. Conntrack MUST
* not believe this ACK is acking last FIN.
*/
if (old_state == TCP_CONNTRACK_LAST_ACK &&
index == TCP_ACK_SET &&
ct->proto.tcp.last_dir != dir &&
ct->proto.tcp.last_index == TCP_SYN_SET &&
(ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) {
/* Detected RFC5961 challenge ACK */
ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "challenge-ack ignored");
return NF_ACCEPT; /* Don't change state */
}
break;
case TCP_CONNTRACK_SYN_SENT2:
/* tcp_conntracks table is not smart enough to handle
* simultaneous open.
*/
ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN;
break;
case TCP_CONNTRACK_SYN_RECV:
if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET &&
ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN)
new_state = TCP_CONNTRACK_ESTABLISHED;
break;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
&& before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
/* Invalid RST */
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "invalid rst");
return -NF_ACCEPT;
}
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_ACK_SET))
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* RST sent to invalid SYN or ACK we had let through
* at a) and c) above:
*
* a) SYN was in window then
* c) we hold a half-open connection.
*
* Delete our connection entry.
* We skip window checking, because packet might ACK
* segments we ignored. */
goto in_window;
}
/* Just fall through */
default:
/* Keep compilers happy. */
break;
}
if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
skb, dataoff, th)) {
spin_unlock_bh(&ct->lock);
return -NF_ACCEPT;
}
in_window:
/* From now on we have got in-window packets */
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
pr_debug("tcp_conntracks: ");
nf_ct_dump_tuple(tuple);
pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
(th->syn ? 1 : 0), (th->ack ? 1 : 0),
(th->fin ? 1 : 0), (th->rst ? 1 : 0),
old_state, new_state);
ct->proto.tcp.state = new_state;
if (old_state != new_state
&& new_state == TCP_CONNTRACK_FIN_WAIT)
ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
timeouts = nf_ct_timeout_lookup(ct);
if (!timeouts)
timeouts = tn->timeouts;
if (ct->proto.tcp.retrans >= tn->tcp_max_retrans &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
timeout = timeouts[TCP_CONNTRACK_RETRANS];
else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK])
timeout = timeouts[TCP_CONNTRACK_UNACK];
else if (ct->proto.tcp.last_win == 0 &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
timeout = timeouts[TCP_CONNTRACK_RETRANS];
else
timeout = timeouts[new_state];
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* If only reply is a RST, we can consider ourselves not to
have an established connection: this is a fairly common
problem case, so we can delete the conntrack
immediately. --RR */
if (th->rst) {
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
/* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
* pickup with loose=1. Avoid large ESTABLISHED timeout.
*/
if (new_state == TCP_CONNTRACK_ESTABLISHED &&
timeout > timeouts[TCP_CONNTRACK_UNACK])
timeout = timeouts[TCP_CONNTRACK_UNACK];
} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
&& new_state == TCP_CONNTRACK_ESTABLISHED) {
/* Set ASSURED if we see see valid ack in ESTABLISHED
after SYN_RECV or a valid answer for a picked up
connection. */
set_bit(IPS_ASSURED_BIT, &ct->status);
nf_conntrack_event_cache(IPCT_ASSURED, ct);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
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;
}
/* after ipt_filter */
static unsigned int ezp_nat_pre_hook(unsigned int hooknum,
struct sk_buff *skb, const struct net_device *indev,
const struct net_device *outdev,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
int ret = NF_ACCEPT;
enum ip_conntrack_dir dir;
__u32 dnat_addr = 0, snat_addr = 0;
int* nat_flag;
struct dst_entry** dst_to_use = NULL;
struct iphdr *iph = ip_hdr(skb);
struct icmphdr *hdr = icmp_hdr(skb);
struct tcphdr *tcph = tcp_hdr(skb);
/* EZP: enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); */
if(!ezp_nat_enable_flag){
return NF_ACCEPT;
}
ct = nf_ct_get(skb, &ctinfo);
if (!ct) {
if (iph->protocol == IPPROTO_ICMP
&& hdr->type == ICMP_REDIRECT)
return NF_DROP;
return NF_ACCEPT;
}
/* TCP or UDP. */
if ((iph->protocol != IPPROTO_TCP) &&
(iph->protocol != IPPROTO_UDP) ) {
return NF_ACCEPT;
}
if ((iph->protocol == IPPROTO_TCP) &&
((tcp_flag_word(tcph) & (TCP_FLAG_RST | TCP_FLAG_SYN)) ==
TCP_FLAG_SYN)) {
return NF_ACCEPT;
}
/* Make sure it is confirmed. */
if (!nf_ct_is_confirmed(ct)) {
return NF_ACCEPT;
}
/* We comment out this part since
((tcp_flag_word((*pskb)->h.th) == TCP_FLAG_SYN) ||
* 1. conntrack establishing is a 2 way process, but after routing, we have
* established routing entry and address resolution table, so we don't
* need to check ESTABLISH state.
* 2. With establishing state, we need to go through forward state and
* routing several times. It may occur that our holded entry may be
* replaced. */
/*
if ((ctinfo != IP_CT_ESTABLISHED) &&
(ctinfo != IP_CT_ESTABLISHED+IP_CT_IS_REPLY)) {
return NF_ACCEPT;
}
*/
dir = CTINFO2DIR(ctinfo);
if (dir == IP_CT_DIR_ORIGINAL) {
if (!ct->orgdir_dst) {
return NF_ACCEPT;
} else {
nat_flag = &ct->orgdir_rid;
if (!(*nat_flag & ((1 << IP_NAT_MANIP_DST) |
(1 << IP_NAT_MANIP_SRC) |
(1 << EZP_IP_LOCAL_IN)))) {
return NF_ACCEPT;
}
/* Check only in forward case and ignore input case */
if (!(*nat_flag & (1 << EZP_IP_LOCAL_IN))) {
if ((!ct->orgdir_dst->hh) && (!ct->orgdir_dst->neighbour)) {
printk("%s:orig dst and neighbour null dir\n",__FUNCTION__);
return NF_ACCEPT;
}
}
if (skb->dst) {
/* skb might has its own dst already.
* e.g. output to local input */
dst_release(skb->dst);
}
skb->protocol = htons(ETH_P_IP);
skb->dst = ct->orgdir_dst;
/* XXX: */
skb->dev = ct->orgdir_dst->dev;
/* skb uses this dst_entry */
dst_use(skb->dst, jiffies);
dst_to_use = &ct->orgdir_dst;
}
} else {
/* IP_CT_DIR_REPLY */
if (!ct->replydir_dst) {
return NF_ACCEPT;
} else {
nat_flag = &ct->replydir_rid;
if (!(*nat_flag & ((1 << IP_NAT_MANIP_DST) |
(1 << IP_NAT_MANIP_SRC) |
(1 << EZP_IP_LOCAL_IN)))) {
return NF_ACCEPT;
}
/* Check only in forward case and ignore input case */
if (!(*nat_flag & (1 << EZP_IP_LOCAL_IN))) {
if ((!ct->replydir_dst->hh) && (!ct->replydir_dst->neighbour)) {
printk("%s:reply dst and neighbour null\n",__FUNCTION__);
return NF_ACCEPT;
}
}
if (skb->dst) {
/* skb might has its own dst already. */
/* e.g. output to local input */
dst_release(skb->dst);
}
skb->protocol = htons(ETH_P_IP);
skb->dst = ct->replydir_dst;
/* XXX: */
skb->dev = ct->replydir_dst->dev;
/* skb uses this dst_entry */
dst_use(skb->dst, jiffies);
dst_to_use = &ct->replydir_dst;
}
}
/* After this point, every "return NF_ACCEPT" action need to release
* holded dst entry. So we use "goto release_dst_and_return" to handle the
* action commonly. */
/* EZP:
if (!nf_nat_initialized(ct, maniptype)) {
goto release_dst_and_return;
}
*/
/* If we have helper, we need to go original path until conntrack
* confirmed */
if(nfct_help(ct)){
goto release_dst_and_return;
}
if (dir == IP_CT_DIR_ORIGINAL) {
(skb)->imq_flags = ct->ct_orig_imq_flags;
}
else{
(skb)->imq_flags = ct->ct_repl_imq_flags;
}
/* PRE_ROUTING NAT */
/* Assume DNAT conntrack is ready. */
if ((*nat_flag & (1 << IP_NAT_MANIP_DST))){
dnat_addr = iph->daddr;
ret = nf_nat_packet(ct, ctinfo, NF_INET_PRE_ROUTING, skb);
if (ret != NF_ACCEPT) {
goto release_dst_and_return;
}
if (dnat_addr == iph->daddr) {
*nat_flag &= ~(1 << IP_NAT_MANIP_DST);
}
}
/* INPUT */
if ((*nat_flag & (1 << EZP_IP_LOCAL_IN))){
/* TODO: use ip_local_deliver_finish() and add ip_defrag(). */
/* XXX: Not sure this will hit or not. */
/*
* Reassemble IP fragments.
*/
if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER)) {
/* If return value is not 0, defrag error */
/* return 0; */
/* XXX: return NF_STOLEN? */
goto release_dst_and_return;
}
}
/* For INPUT path, there is no need to check dst_mtu but defrag.
if (skb->len > dst_mtu(&((struct rtable*)skb->dst)->u.dst)) {
goto release_dst_and_return;
}*/
if (ezp_nat_queue_enable_flag) {
if ((skb)->imq_flags & IMQ_F_ENQUEUE) {
struct nf_hook_ops *elem = nf_get_imq_ops();
/* With to apply IMQ, we have to check the IMQ flag, if the flag is
* set, we have to enquene this skb and leave it to IMQ*/
if (elem != NULL) {
nf_queue(skb, (struct list_head*)elem, AF_INET,
NF_INET_POST_ROUTING,
(struct net_device*)indev,
(struct net_device*)
((struct rtable*)skb->dst)->u.dst.dev,
ip_local_deliver_finish, NF_ACCEPT >> NF_VERDICT_BITS);
return NF_STOLEN;
}
}
}
ret = ip_local_deliver_finish(skb);
return NF_STOLEN;
}
