[NETFILTER]: Add ctnetlink subsystem
Add ctnetlink subsystem for userspace-access to ip_conntrack table.
This allows reading and updating of existing entries, as well as
creating new ones (and new expect's) via nfnetlink.
Please note the 'strange' byte order: nfattr (tag+length) are in host
byte order, while the payload is always guaranteed to be in network
byte order. This allows a simple userspace process to encapsulate netlink
messages into arch-independent udp packets by just processing/swapping the
headers and not knowing anything about the actual payload.
Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/netfilter/ip_nat_core.c b/net/ipv4/netfilter/ip_nat_core.c
index ed4d731..567c802 100644
--- a/net/ipv4/netfilter/ip_nat_core.c
+++ b/net/ipv4/netfilter/ip_nat_core.c
@@ -47,8 +47,39 @@
static unsigned int ip_nat_htable_size;
static struct list_head *bysource;
+
+#define MAX_IP_NAT_PROTO 256
struct ip_nat_protocol *ip_nat_protos[MAX_IP_NAT_PROTO];
+static inline struct ip_nat_protocol *
+__ip_nat_proto_find(u_int8_t protonum)
+{
+ return ip_nat_protos[protonum];
+}
+
+struct ip_nat_protocol *
+ip_nat_proto_find_get(u_int8_t protonum)
+{
+ struct ip_nat_protocol *p;
+
+ /* we need to disable preemption to make sure 'p' doesn't get
+ * removed until we've grabbed the reference */
+ preempt_disable();
+ p = __ip_nat_proto_find(protonum);
+ if (p) {
+ if (!try_module_get(p->me))
+ p = &ip_nat_unknown_protocol;
+ }
+ preempt_enable();
+
+ return p;
+}
+
+void
+ip_nat_proto_put(struct ip_nat_protocol *p)
+{
+ module_put(p->me);
+}
/* We keep an extra hash for each conntrack, for fast searching. */
static inline unsigned int
@@ -103,7 +134,8 @@
in_range(const struct ip_conntrack_tuple *tuple,
const struct ip_nat_range *range)
{
- struct ip_nat_protocol *proto = ip_nat_find_proto(tuple->dst.protonum);
+ struct ip_nat_protocol *proto =
+ __ip_nat_proto_find(tuple->dst.protonum);
/* If we are supposed to map IPs, then we must be in the
range specified, otherwise let this drag us onto a new src IP. */
@@ -216,8 +248,7 @@
struct ip_conntrack *conntrack,
enum ip_nat_manip_type maniptype)
{
- struct ip_nat_protocol *proto
- = ip_nat_find_proto(orig_tuple->dst.protonum);
+ struct ip_nat_protocol *proto;
/* 1) If this srcip/proto/src-proto-part is currently mapped,
and that same mapping gives a unique tuple within the given
@@ -242,14 +273,20 @@
/* 3) The per-protocol part of the manip is made to map into
the range to make a unique tuple. */
+ proto = ip_nat_proto_find_get(orig_tuple->dst.protonum);
+
/* Only bother mapping if it's not already in range and unique */
if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)
|| proto->in_range(tuple, maniptype, &range->min, &range->max))
- && !ip_nat_used_tuple(tuple, conntrack))
+ && !ip_nat_used_tuple(tuple, conntrack)) {
+ ip_nat_proto_put(proto);
return;
+ }
/* Last change: get protocol to try to obtain unique tuple. */
proto->unique_tuple(tuple, range, maniptype, conntrack);
+
+ ip_nat_proto_put(proto);
}
unsigned int
@@ -320,6 +357,7 @@
enum ip_nat_manip_type maniptype)
{
struct iphdr *iph;
+ struct ip_nat_protocol *p;
if (!skb_ip_make_writable(pskb, iphdroff + sizeof(*iph)))
return 0;
@@ -327,9 +365,12 @@
iph = (void *)(*pskb)->data + iphdroff;
/* Manipulate protcol part. */
- if (!ip_nat_find_proto(proto)->manip_pkt(pskb, iphdroff,
- target, maniptype))
+ p = ip_nat_proto_find_get(proto);
+ if (!p->manip_pkt(pskb, iphdroff, target, maniptype)) {
+ ip_nat_proto_put(p);
return 0;
+ }
+ ip_nat_proto_put(p);
iph = (void *)(*pskb)->data + iphdroff;
@@ -425,7 +466,8 @@
if (!ip_ct_get_tuple(&inside->ip, *pskb, (*pskb)->nh.iph->ihl*4 +
sizeof(struct icmphdr) + inside->ip.ihl*4,
- &inner, ip_ct_find_proto(inside->ip.protocol)))
+ &inner,
+ __ip_conntrack_proto_find(inside->ip.protocol)))
return 0;
/* Change inner back to look like incoming packet. We do the
@@ -495,6 +537,49 @@
synchronize_net();
}
+#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \
+ defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE)
+int
+ip_nat_port_range_to_nfattr(struct sk_buff *skb,
+ const struct ip_nat_range *range)
+{
+ NFA_PUT(skb, CTA_PROTONAT_PORT_MIN, sizeof(u_int16_t),
+ &range->min.tcp.port);
+ NFA_PUT(skb, CTA_PROTONAT_PORT_MAX, sizeof(u_int16_t),
+ &range->max.tcp.port);
+
+ return 0;
+
+nfattr_failure:
+ return -1;
+}
+
+int
+ip_nat_port_nfattr_to_range(struct nfattr *tb[], struct ip_nat_range *range)
+{
+ int ret = 0;
+
+ /* we have to return whether we actually parsed something or not */
+
+ if (tb[CTA_PROTONAT_PORT_MIN-1]) {
+ ret = 1;
+ range->min.tcp.port =
+ *(u_int16_t *)NFA_DATA(tb[CTA_PROTONAT_PORT_MIN-1]);
+ }
+
+ if (!tb[CTA_PROTONAT_PORT_MAX-1]) {
+ if (ret)
+ range->max.tcp.port = range->min.tcp.port;
+ } else {
+ ret = 1;
+ range->max.tcp.port =
+ *(u_int16_t *)NFA_DATA(tb[CTA_PROTONAT_PORT_MAX-1]);
+ }
+
+ return ret;
+}
+#endif
+
int __init ip_nat_init(void)
{
size_t i;