unsigned int
alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
{
/* 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).
*/
__be32 ip
= (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip
: ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
struct nf_nat_range range
= { IP_NAT_RANGE_MAP_IPS, ip, ip, { 0 }, { 0 } };
pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, &ip);
return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
}
unsigned int
alloc_null_binding_confirmed(struct nf_conn *ct, unsigned int hooknum)
{
__be32 ip
= (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip
: ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
u_int16_t all
= (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.all
: ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.all);
struct nf_nat_range range
= { IP_NAT_RANGE_MAP_IPS, ip, ip, { all }, { all } };
pr_debug("Allocating NULL binding for confirmed %p (%pI4)\n",
ct, &ip);
return nf_nat_setup_info(ct, &range, hooknum);
}
static unsigned int
amanda_nat_expected(struct sk_buff **pskb,
unsigned int hooknum,
struct ip_conntrack *ct,
struct ip_nat_info *info)
{
struct ip_nat_multi_range mr;
u_int32_t newdstip, newsrcip, newip;
u_int16_t port;
struct ip_ct_amanda_expect *exp_info;
struct ip_conntrack *master = master_ct(ct);
IP_NF_ASSERT(info);
IP_NF_ASSERT(master);
IP_NF_ASSERT(!(info->initialized & (1 << HOOK2MANIP(hooknum))));
DEBUGP("nat_expected: We have a connection!\n");
exp_info = &ct->master->help.exp_amanda_info;
newdstip = ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip;
newsrcip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip;
DEBUGP("nat_expected: %u.%u.%u.%u->%u.%u.%u.%u\n",
NIPQUAD(newsrcip), NIPQUAD(newdstip));
port = exp_info->port;
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC)
newip = newsrcip;
else
newip = newdstip;
DEBUGP("nat_expected: IP to %u.%u.%u.%u\n", NIPQUAD(newip));
mr.rangesize = 1;
/* We don't want to manip the per-protocol, just the IPs. */
mr.range[0].flags = IP_NAT_RANGE_MAP_IPS;
mr.range[0].min_ip = mr.range[0].max_ip = newip;
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_DST) {
mr.range[0].flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
mr.range[0].min = mr.range[0].max
= ((union ip_conntrack_manip_proto)
{ .udp = { htons(port) } });
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);
}
unsigned int
alloc_null_binding_confirmed(struct ip_conntrack *conntrack,
struct ip_nat_info *info,
unsigned int hooknum)
{
u_int32_t ip
= (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
? conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip
: conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip);
u_int16_t all
= (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
? conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.all
: conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.all);
struct ip_nat_range range
= { IP_NAT_RANGE_MAP_IPS, ip, ip, { all }, { all } };
DEBUGP("Allocating NULL binding for confirmed %p (%u.%u.%u.%u)\n",
conntrack, NIPQUAD(ip));
return ip_nat_setup_info(conntrack, &range, hooknum);
}
static unsigned int
mms_nat_expected(struct sk_buff **pskb,
unsigned int hooknum,
struct ip_conntrack *ct,
struct ip_nat_info *info)
{
struct ip_nat_multi_range mr;
u_int32_t newdstip, newsrcip, newip;
struct ip_conntrack *master = master_ct(ct);
IP_NF_ASSERT(info);
IP_NF_ASSERT(master);
IP_NF_ASSERT(!(info->initialized & (1 << HOOK2MANIP(hooknum))));
DEBUGP("ip_nat_mms: mms_nat_expected: We have a connection!\n");
newdstip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip;
newsrcip = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip;
DEBUGP("ip_nat_mms: mms_nat_expected: hook %s: newsrc->newdst %u.%u.%u.%u->%u.%u.%u.%u\n",
hooknum == NF_IP_POST_ROUTING ? "POSTROUTING"
: hooknum == NF_IP_PRE_ROUTING ? "PREROUTING"
: hooknum == NF_IP_LOCAL_OUT ? "OUTPUT" : "???",
NIPQUAD(newsrcip), NIPQUAD(newdstip));
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC)
newip = newsrcip;
else
newip = newdstip;
DEBUGP("ip_nat_mms: mms_nat_expected: IP to %u.%u.%u.%u\n", NIPQUAD(newip));
mr.rangesize = 1;
/* We don't want to manip the per-protocol, just the IPs. */
mr.range[0].flags = IP_NAT_RANGE_MAP_IPS;
mr.range[0].min_ip = mr.range[0].max_ip = newip;
return ip_nat_setup_info(ct, &mr, hooknum);
}
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 FASTPATHNET bcm_do_fastnat(struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
struct sk_buff **pskb,
struct nf_conntrack_l3proto *l3proto,
struct nf_conntrack_l4proto *l4proto)
{
static int hn[2] = {NF_IP_PRE_ROUTING, NF_IP_POST_ROUTING};
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
unsigned int i = 1;
do {
enum nf_nat_manip_type mtype = HOOK2MANIP(hn[i]);
unsigned long statusbit;
if (mtype == IP_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;
if (ct->status & statusbit) {
struct nf_conntrack_tuple target;
if ((*pskb)->dst == NULL && mtype == IP_NAT_MANIP_SRC) {
struct net_device *dev = (*pskb)->dev;
struct iphdr *iph = ip_hdr(*pskb);
if (ip_route_input((*pskb), iph->daddr, iph->saddr, iph->tos, dev))
return NF_DROP;
/* Change skb owner to output device */
(*pskb)->dev = (*pskb)->dst->dev;
}
/* We are aiming to look like inverse of other direction. */
nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple, l3proto, l4proto);
if (!manip_pkt(target.dst.protonum, pskb, 0, &target, mtype))
return NF_DROP;
}
} while (i++ < 2);
return NF_FAST_NAT;
}
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;
}
int ip_nat_rule_find(struct sk_buff **pskb,
unsigned int hooknum,
const struct net_device *in,
const struct net_device *out,
struct ip_conntrack *ct,
struct ip_nat_info *info)
{
int ret;
ret = ipt_do_table(pskb, hooknum, in, out, &nat_table, NULL);
if (ret == NF_ACCEPT) {
if (!ip_nat_initialized(ct, HOOK2MANIP(hooknum)))
/* NUL mapping */
ret = alloc_null_binding(ct, info, hooknum);
}
return ret;
}
inline unsigned int
alloc_null_binding(struct ip_conntrack *conntrack,
struct ip_nat_info *info,
unsigned int hooknum)
{
/* 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).
*/
u_int32_t ip
= (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
? conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip
: conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip);
struct ip_nat_range range
= { IP_NAT_RANGE_MAP_IPS, ip, ip, { 0 }, { 0 } };
DEBUGP("Allocating NULL binding for %p (%u.%u.%u.%u)\n", conntrack,
NIPQUAD(ip));
return ip_nat_setup_info(conntrack, &range, hooknum);
}
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;
}
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_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_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
{
return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum));
}
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);
}
static unsigned int
pptp_nat_expected(struct sk_buff **pskb,
unsigned int hooknum,
struct ip_conntrack *ct,
struct ip_nat_info *info)
{
struct ip_conntrack *master = master_ct(ct);
struct ip_nat_multi_range mr;
struct ip_ct_pptp_master *ct_pptp_info;
struct ip_nat_pptp *nat_pptp_info;
u_int32_t newip, newcid;
int ret;
IP_NF_ASSERT(info);
IP_NF_ASSERT(master);
IP_NF_ASSERT(!(info->initialized & (1 << HOOK2MANIP(hooknum))));
DEBUGP("we have a connection!\n");
LOCK_BH(&ip_pptp_lock);
ct_pptp_info = &master->help.ct_pptp_info;
nat_pptp_info = &master->nat.help.nat_pptp_info;
/* need to alter GRE tuple because conntrack expectfn() used 'wrong'
* (unmanipulated) values */
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_DST) {
DEBUGP("completing tuples with NAT info \n");
/* we can do this, since we're unconfirmed */
if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.gre.key ==
htonl(ct_pptp_info->pac_call_id)) {
/* assume PNS->PAC */
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.gre.key =
htonl(nat_pptp_info->pns_call_id);
ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.gre.key =
htonl(nat_pptp_info->pns_call_id);
newip = master->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip;
newcid = htonl(nat_pptp_info->pac_call_id);
} else {
/* assume PAC->PNS */
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.gre.key =
htonl(nat_pptp_info->pac_call_id);
ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.gre.key =
htonl(nat_pptp_info->pac_call_id);
newip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip;
newcid = htonl(nat_pptp_info->pns_call_id);
}
} else {
if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.gre.key ==
htonl(ct_pptp_info->pac_call_id)) {
/* assume PNS->PAC */
newip = master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip;
newcid = htonl(ct_pptp_info->pns_call_id);
}
else {
/* assume PAC->PNS */
newip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip;
newcid = htonl(ct_pptp_info->pac_call_id);
}
}
mr.rangesize = 1;
mr.range[0].flags = IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED;
mr.range[0].min_ip = mr.range[0].max_ip = newip;
mr.range[0].min = mr.range[0].max =
((union ip_conntrack_manip_proto ) { newcid });
static unsigned int
talk_nat_expected(struct sk_buff **pskb,
unsigned int hooknum,
struct ip_conntrack *ct,
struct ip_nat_info *info)
{
struct ip_nat_multi_range mr;
u_int32_t newdstip, newsrcip, newip;
u_int16_t port;
unsigned int ret;
struct ip_conntrack *master = master_ct(ct);
IP_NF_ASSERT(info);
IP_NF_ASSERT(master);
IP_NF_ASSERT(!(info->initialized & (1<<HOOK2MANIP(hooknum))));
DEBUGP("ip_nat_talk_expected: We have a connection!\n");
LOCK_BH(&ip_talk_lock);
port = ct->master->help.exp_talk_info.port;
UNLOCK_BH(&ip_talk_lock);
DEBUGP("ip_nat_talk_expected: dir %s at hook %s, ct %p, master %p\n",
CTINFO2DIR((*pskb)->nfct - ct->infos) == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY",
hooknum == NF_IP_POST_ROUTING ? "POSTROUTING"
: hooknum == NF_IP_PRE_ROUTING ? "PREROUTING"
: hooknum == NF_IP_LOCAL_OUT ? "OUTPUT" : "???",
ct, master);
if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum == IPPROTO_UDP) {
/* Callee client -> caller server */
#ifdef IP_NAT_TALK_DEBUG
struct iphdr *iph = (*pskb)->nh.iph;
struct udphdr *udph = (void *)iph + iph->ihl * 4;
DEBUGP("ip_nat_talk_expected: UDP %u.%u.%u.%u:%u->%u.%u.%u.%u:%u\n",
NIPQUAD(iph->saddr), ntohs(udph->source),
NIPQUAD(iph->daddr), ntohs(udph->dest));
#endif
newdstip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip;
newsrcip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip;
DEBUGP("ip_nat_talk_expected: callee client -> caller server, newsrc: %u.%u.%u.%u, newdst: %u.%u.%u.%u\n",
NIPQUAD(newsrcip), NIPQUAD(newdstip));
} else {
/* Callee client -> caller client */
#ifdef IP_NAT_TALK_DEBUG
struct iphdr *iph = (*pskb)->nh.iph;
struct tcphdr *tcph = (void *)iph + iph->ihl * 4;
DEBUGP("ip_nat_talk_expected: TCP %u.%u.%u.%u:%u->%u.%u.%u.%u:%u\n",
NIPQUAD(iph->saddr), ntohs(tcph->source),
NIPQUAD(iph->daddr), ntohs(tcph->dest));
#endif
newdstip = master->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip;
newsrcip = master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip;
DEBUGP("ip_nat_talk_expected: callee client -> caller client, newsrc: %u.%u.%u.%u, newdst: %u.%u.%u.%u\n",
NIPQUAD(newsrcip), NIPQUAD(newdstip));
}
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC)
newip = newsrcip;
else
newip = newdstip;
DEBUGP("ip_nat_talk_expected: IP to %u.%u.%u.%u, port %u\n", NIPQUAD(newip), ntohs(port));
mr.rangesize = 1;
/* We don't want to manip the per-protocol, just the IPs... */
mr.range[0].flags = IP_NAT_RANGE_MAP_IPS;
mr.range[0].min_ip = mr.range[0].max_ip = newip;
/* ... unless we're doing a MANIP_DST, in which case, make
sure we map to the correct port */
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_DST) {
mr.range[0].flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
mr.range[0].min = mr.range[0].max
= ((union ip_conntrack_manip_proto)
{ .udp = { port } });
static unsigned int
ip_nat_fn(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct ip_conntrack *ct;
enum ip_conntrack_info ctinfo;
struct ip_nat_info *info;
/* maniptype == SRC for postrouting. */
enum ip_nat_manip_type maniptype = HOOK2MANIP(hooknum);
/* jimmy added 20080324 */
struct sip_rtp_binding *sip_rtp_binding_tmp = NULL;
/* --------------------------------- */
/* We never see fragments: conntrack defrags on pre-routing
and local-out, and ip_nat_out protects post-routing. */
IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off
& htons(IP_MF|IP_OFFSET)));
/* If we had a hardware checksum before, it's now invalid */
if ((*pskb)->ip_summed == CHECKSUM_HW)
if (skb_checksum_help(*pskb, (out == NULL)))
return NF_DROP;
ct = ip_conntrack_get(*pskb, &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 ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) {
struct icmphdr _hdr, *hp;
hp = skb_header_pointer(*pskb,
(*pskb)->nh.iph->ihl*4,
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 == &ip_conntrack_untracked)
return NF_ACCEPT;
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) {
if (!ip_nat_icmp_reply_translation(pskb, ct, maniptype,
CTINFO2DIR(ctinfo)))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
info = &ct->nat.info;
/* Seen it before? This can happen for loopback, retrans,
or local packets.. */
if (!ip_nat_initialized(ct, maniptype)) {
unsigned int ret;
if (unlikely(is_confirmed(ct)))
/* NAT module was loaded late */
ret = alloc_null_binding_confirmed(ct, info,
hooknum);
else if (hooknum == NF_IP_LOCAL_IN)
/* LOCAL_IN hook doesn't have a chain! */
ret = alloc_null_binding(ct, info, hooknum);
else{
ret = ip_nat_rule_find(pskb, hooknum,
in, out, ct,
info);
/* jimmy added 20080324 */
if((hooknum == NF_IP_POST_ROUTING) && ((*pskb)->nh.iph->protocol == IPPROTO_UDP)){
sip_rtp_binding_tmp = sip_rtp_binding_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip,
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip);
if(sip_rtp_binding_tmp){
/* jimmy added 20080328, for avoid sip pattern 100 run through in */
if( sip_rtp_binding_tmp->wan_uac_port &&
(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.all == sip_rtp_binding_tmp->wan_uac_port)){
/* ----------------------------------------------- */
if(sip_rtp_binding_tmp->router_port && sip_rtp_binding_tmp->router_ip &&
(sip_rtp_binding_tmp->router_ip == ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip) &&
(sip_rtp_binding_tmp->router_port != ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.all)){
write_lock_bh(&ip_conntrack_lock);
ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.all = sip_rtp_binding_tmp->router_port;
write_unlock_bh(&ip_conntrack_lock);
DEBUGP("After modified conntrack for sip incoming conntrack hash, this ct are\n");
DEBUGP("[IP_CT_DIR_REPLY] : %u %u.%u.%u.%u:%hu -> %u.%u.%u.%u:%hu\n",
ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum,
NIPQUAD(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip), ntohs(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.all),
NIPQUAD(ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip), ntohs(ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.all));
DEBUGP("[IP_CT_DIR_ORIGINAL] : %u %u.%u.%u.%u:%hu -> %u.%u.%u.%u:%hu\n",
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum,
NIPQUAD(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip), ntohs(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all),
NIPQUAD(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip), ntohs(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.all));
}
/* jimmy added 20080328, for avoid sip pattern 100 */
}
/* ----------------------------------------------- */
}
}
/* ---------------------- */
}
if (ret != NF_ACCEPT) {
return ret;
}
} else
DEBUGP("Already setup manip %s for ct %p\n",
maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
default:
/* ESTABLISHED */
IP_NF_ASSERT(ctinfo == IP_CT_ESTABLISHED
|| ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
info = &ct->nat.info;
}
IP_NF_ASSERT(info);
return ip_nat_packet(ct, ctinfo, hooknum, pskb);
}
static unsigned int
ip_nat_fn(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct ip_conntrack *ct;
enum ip_conntrack_info ctinfo;
struct ip_nat_info *info;
/* maniptype == SRC for postrouting. */
enum ip_nat_manip_type maniptype = HOOK2MANIP(hooknum);
/* We never see fragments: conntrack defrags on pre-routing
and local-out, and ip_nat_out protects post-routing. */
IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off
& htons(IP_MF|IP_OFFSET)));
(*pskb)->nfcache |= NFC_UNKNOWN;
/* If we had a hardware checksum before, it's now invalid */
if ((*pskb)->ip_summed == CHECKSUM_HW)
(*pskb)->ip_summed = CHECKSUM_NONE;
ct = ip_conntrack_get(*pskb, &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. */
struct iphdr *iph = (*pskb)->nh.iph;
struct icmphdr *hdr = (struct icmphdr *)
((u_int32_t *)iph + iph->ihl);
if (iph->protocol == IPPROTO_ICMP
&& hdr->type == ICMP_REDIRECT)
return NF_DROP;
return NF_ACCEPT;
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) {
return icmp_reply_translation(*pskb, ct, hooknum,
CTINFO2DIR(ctinfo));
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
#ifdef CONFIG_IP_NF_NAT_LOCAL
/* LOCAL_IN hook doesn't have a chain and thus doesn't care
* about new packets -HW */
if (hooknum == NF_IP_LOCAL_IN)
return NF_ACCEPT;
#endif
info = &ct->nat.info;
WRITE_LOCK(&ip_nat_lock);
/* Seen it before? This can happen for loopback, retrans,
or local packets.. */
if (!(info->initialized & (1 << maniptype))) {
int in_hashes = info->initialized;
unsigned int ret;
if (ct->master
&& master_ct(ct)->nat.info.helper
&& master_ct(ct)->nat.info.helper->expect) {
ret = call_expect(master_ct(ct), pskb,
hooknum, ct, info);
} else {
ret = ip_nat_rule_find(pskb, hooknum, in, out,
ct, info);
}
if (ret != NF_ACCEPT) {
WRITE_UNLOCK(&ip_nat_lock);
return ret;
}
if (in_hashes) {
IP_NF_ASSERT(info->bysource.conntrack);
replace_in_hashes(ct, info);
} else {
place_in_hashes(ct, info);
}
} else
DEBUGP("Already setup manip %s for ct %p\n",
maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
WRITE_UNLOCK(&ip_nat_lock);
break;
default:
/* ESTABLISHED */
IP_NF_ASSERT(ctinfo == IP_CT_ESTABLISHED
|| ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
info = &ct->nat.info;
}
IP_NF_ASSERT(info);
return do_bindings(ct, ctinfo, info, hooknum, pskb);
}
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;
}
static unsigned int
h225_nat_expected(struct sk_buff **pskb,
unsigned int hooknum,
struct ip_conntrack *ct,
struct ip_nat_info *info)
{
struct ip_nat_multi_range mr;
u_int32_t newdstip, newsrcip, newip;
u_int16_t port;
struct ip_ct_h225_expect *exp_info;
struct ip_ct_h225_master *master_info;
struct ip_conntrack *master = master_ct(ct);
unsigned int is_h225, ret;
IP_NF_ASSERT(info);
IP_NF_ASSERT(master);
IP_NF_ASSERT(!(info->initialized & (1<<HOOK2MANIP(hooknum))));
DEBUGP("h225_nat_expected: We have a connection!\n");
master_info = &ct->master->expectant->help.ct_h225_info;
exp_info = &ct->master->help.exp_h225_info;
LOCK_BH(&ip_h323_lock);
DEBUGP("master: ");
DUMP_TUPLE(&master->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
DUMP_TUPLE(&master->tuplehash[IP_CT_DIR_REPLY].tuple);
DEBUGP("conntrack: ");
DUMP_TUPLE(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
if (exp_info->dir == IP_CT_DIR_ORIGINAL) {
/* Make connection go to the client. */
newdstip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip;
newsrcip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip;
DEBUGP("h225_nat_expected: %u.%u.%u.%u->%u.%u.%u.%u (to client)\n",
NIPQUAD(newsrcip), NIPQUAD(newdstip));
} else {
/* Make the connection go to the server */
newdstip = master->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip;
newsrcip = master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip;
DEBUGP("h225_nat_expected: %u.%u.%u.%u->%u.%u.%u.%u (to server)\n",
NIPQUAD(newsrcip), NIPQUAD(newdstip));
}
port = exp_info->port;
is_h225 = master_info->is_h225 == H225_PORT;
UNLOCK_BH(&ip_h323_lock);
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC)
newip = newsrcip;
else
newip = newdstip;
DEBUGP("h225_nat_expected: IP to %u.%u.%u.%u\n", NIPQUAD(newip));
mr.rangesize = 1;
/* We don't want to manip the per-protocol, just the IPs... */
mr.range[0].flags = IP_NAT_RANGE_MAP_IPS;
mr.range[0].min_ip = mr.range[0].max_ip = newip;
/* ... unless we're doing a MANIP_DST, in which case, make
sure we map to the correct port */
if (HOOK2MANIP(hooknum) == IP_NAT_MANIP_DST) {
mr.range[0].flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
mr.range[0].min = mr.range[0].max
= ((union ip_conntrack_manip_proto)
{ .tcp = { port } });
static unsigned int
ip_nat_fn(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct ip_conntrack *ct;
enum ip_conntrack_info ctinfo;
struct ip_nat_info *info;
/* maniptype == SRC for postrouting. */
enum ip_nat_manip_type maniptype = HOOK2MANIP(hooknum);
/* We never see fragments: conntrack defrags on pre-routing
and local-out, and ip_nat_out protects post-routing. */
IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off
& __constant_htons(IP_MF|IP_OFFSET)));
(*pskb)->nfcache |= NFC_UNKNOWN;
/* If we had a hardware checksum before, it's now invalid */
if ((*pskb)->pkt_type != PACKET_LOOPBACK)
(*pskb)->ip_summed = CHECKSUM_NONE;
ct = ip_conntrack_get(*pskb, &ctinfo);
/* Can't track? Maybe out of memory: this would make NAT
unreliable. */
if (!ct) {
if (net_ratelimit())
printk(KERN_DEBUG "NAT: %u dropping untracked packet %p %u %u.%u.%u.%u -> %u.%u.%u.%u\n",
hooknum,
*pskb,
(*pskb)->nh.iph->protocol,
NIPQUAD((*pskb)->nh.iph->saddr),
NIPQUAD((*pskb)->nh.iph->daddr));
return NF_DROP;
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) {
return icmp_reply_translation(*pskb, ct, hooknum,
CTINFO2DIR(ctinfo));
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
info = &ct->nat.info;
WRITE_LOCK(&ip_nat_lock);
/* Seen it before? This can happen for loopback, retrans,
or local packets.. */
if (!(info->initialized & (1 << maniptype))) {
int in_hashes = info->initialized;
unsigned int ret;
ret = ip_nat_rule_find(pskb, hooknum, in, out,
ct, info);
if (ret != NF_ACCEPT) {
WRITE_UNLOCK(&ip_nat_lock);
return ret;
}
if (in_hashes) {
IP_NF_ASSERT(info->bysource.conntrack);
replace_in_hashes(ct, info);
} else {
place_in_hashes(ct, info);
}
} else
DEBUGP("Already setup manip %s for ct %p\n",
maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
WRITE_UNLOCK(&ip_nat_lock);
break;
default:
/* ESTABLISHED */
IP_NF_ASSERT(ctinfo == IP_CT_ESTABLISHED
|| ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
info = &ct->nat.info;
}
IP_NF_ASSERT(info);
return do_bindings(ct, ctinfo, info, hooknum, pskb);
}
static unsigned int
ip_nat_fn(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct ip_conntrack *ct;
enum ip_conntrack_info ctinfo;
struct ip_nat_info *info;
/* maniptype == SRC for postrouting. */
enum ip_nat_manip_type maniptype = HOOK2MANIP(hooknum);
/* We never see fragments: conntrack defrags on pre-routing
and local-out, and ip_nat_out protects post-routing. */
IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off
& htons(IP_MF|IP_OFFSET)));
(*pskb)->nfcache |= NFC_UNKNOWN;
/* If we had a hardware checksum before, it's now invalid */
if ((*pskb)->ip_summed == CHECKSUM_HW)
if (skb_checksum_help(*pskb, (out == NULL)))
return NF_DROP;
ct = ip_conntrack_get(*pskb, &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 ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) {
struct icmphdr _hdr, *hp;
hp = skb_header_pointer(*pskb,
(*pskb)->nh.iph->ihl*4,
sizeof(_hdr), &_hdr);
if (hp != NULL &&
hp->type == ICMP_REDIRECT)
return NF_DROP;
}
return NF_ACCEPT;
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) {
if (!icmp_reply_translation(pskb, ct, maniptype,
CTINFO2DIR(ctinfo)))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
info = &ct->nat.info;
/* Seen it before? This can happen for loopback, retrans,
or local packets.. */
if (!ip_nat_initialized(ct, maniptype)) {
unsigned int ret;
/* LOCAL_IN hook doesn't have a chain! */
if (hooknum == NF_IP_LOCAL_IN)
ret = alloc_null_binding(ct, info, hooknum);
else
ret = ip_nat_rule_find(pskb, hooknum,
in, out, ct,
info);
if (ret != NF_ACCEPT) {
return ret;
}
} else
DEBUGP("Already setup manip %s for ct %p\n",
maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
default:
/* ESTABLISHED */
IP_NF_ASSERT(ctinfo == IP_CT_ESTABLISHED
|| ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
info = &ct->nat.info;
}
IP_NF_ASSERT(info);
return nat_packet(ct, ctinfo, hooknum, pskb);
}
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_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 inline int
bcm_do_bindings(struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
struct sk_buff **pskb,
struct nf_conntrack_l4proto *l4proto)
{
struct iphdr *iph = ip_hdr(*pskb);
unsigned int i;
static int hn[2] = {NF_IP_PRE_ROUTING, NF_IP_POST_ROUTING};
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
#ifdef HNDCTF
bool enabled = ip_conntrack_is_ipc_allowed(*pskb, NF_IP_PRE_ROUTING);
#endif /* HNDCTF */
for (i = 0; i < 2; i++) {
enum nf_nat_manip_type mtype = HOOK2MANIP(hn[i]);
unsigned long statusbit;
if (mtype == IP_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;
if (ct->status & statusbit) {
struct nf_conntrack_tuple target;
if (skb_cloned(*pskb) && !(*pskb)->sk)
{
struct sk_buff *nskb = skb_copy(*pskb, GFP_ATOMIC);
printk("[debug %s:%d] should not happen!!\n" , __FILE__ , __LINE__);
if (!nskb)
return NF_DROP;
kfree_skb(*pskb);
*pskb = nskb;
}
if (skb_dst((*pskb)) == NULL && mtype == IP_NAT_MANIP_SRC) {
struct net_device *dev = (*pskb)->dev;
if (ip_route_input((*pskb), iph->daddr, iph->saddr, iph->tos, dev))
return NF_DROP;
/* Change skb owner */
(*pskb)->dev = skb_dst((*pskb))->dev;
}
/* We are aiming to look like inverse of other direction. */
ipv4_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple, l4proto);
#ifdef HNDCTF
if (enabled)
ip_conntrack_ipct_add(*pskb, hn[i], ct, ctinfo, &target);
#endif /* HNDCTF */
if (!bcm_manip_pkt(target.dst.protonum, pskb, 0, &target, mtype))
return NF_DROP;
}
}
return NF_FAST_NAT;
}
