[PATCH 46/52] netfilter: flow table support for IPv4

[Pablo Neira Ayuso <pablo@netfilter.org>]

This patch adds the IPv4 flow table type, that implements the datapath
flow table to forward IPv4 traffic. Rationale is:

1) Look up for the packet in the flow table, from the ingress hook.
2) If there's a hit, decrement ttl and pass it on to the neighbour layer
   for transmission.
3) If there's a miss, packet is passed up to the classic forwarding
   path.

This patch also supports layer 3 source and destination NAT.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/Kconfig              |   8 +
 net/ipv4/netfilter/Makefile             |   3 +
 net/ipv4/netfilter/nf_flow_table_ipv4.c | 283 ++++++++++++++++++++++++++++++++
 3 files changed, 294 insertions(+)
 create mode 100644 net/ipv4/netfilter/nf_flow_table_ipv4.c

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index cee51045e2f7..7d5d444964aa 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -78,6 +78,14 @@ config NF_TABLES_ARP
 
 endif # NF_TABLES
 
+config NF_FLOW_TABLE_IPV4
+	select NF_FLOW_TABLE
+	tristate "Netfilter flow table IPv4 module"
+	help
+	  This option adds the flow table IPv4 support.
+
+	  To compile it as a module, choose M here.
+
 config NF_DUP_IPV4
 	tristate "Netfilter IPv4 packet duplication to alternate destination"
 	depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index adcdae358365..8bb1f0c7a375 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -43,6 +43,9 @@ obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o
 obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
+# flow table support
+obj-$(CONFIG_NF_FLOW_TABLE_IPV4) += nf_flow_table_ipv4.o
+
 # generic IP tables 
 obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
 
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
new file mode 100644
index 000000000000..ac56c0f0492a
--- /dev/null
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -0,0 +1,283 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <linux/ip.h>
+#include <linux/netdevice.h>
+#include <net/ip.h>
+#include <net/neighbour.h>
+#include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_tables.h>
+/* For layer 4 checksum field offset. */
+#include <linux/tcp.h>
+#include <linux/udp.h>
+
+static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
+			      __be32 addr, __be32 new_addr)
+{
+	struct tcphdr *tcph;
+
+	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
+	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+		return -1;
+
+	tcph = (void *)(skb_network_header(skb) + thoff);
+	inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
+
+	return 0;
+}
+
+static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
+			      __be32 addr, __be32 new_addr)
+{
+	struct udphdr *udph;
+
+	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
+	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
+		return -1;
+
+	udph = (void *)(skb_network_header(skb) + thoff);
+	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+		inet_proto_csum_replace4(&udph->check, skb, addr,
+					 new_addr, true);
+		if (!udph->check)
+			udph->check = CSUM_MANGLED_0;
+	}
+
+	return 0;
+}
+
+static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
+				  unsigned int thoff, __be32 addr,
+				  __be32 new_addr)
+{
+	switch (iph->protocol) {
+	case IPPROTO_TCP:
+		if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
+			return NF_DROP;
+		break;
+	case IPPROTO_UDP:
+		if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
+			return NF_DROP;
+		break;
+	}
+
+	return 0;
+}
+
+static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+			   struct iphdr *iph, unsigned int thoff,
+			   enum flow_offload_tuple_dir dir)
+{
+	__be32 addr, new_addr;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		addr = iph->saddr;
+		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
+		iph->saddr = new_addr;
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		addr = iph->daddr;
+		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
+		iph->daddr = new_addr;
+		break;
+	default:
+		return -1;
+	}
+	csum_replace4(&iph->check, addr, new_addr);
+
+	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+}
+
+static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+			   struct iphdr *iph, unsigned int thoff,
+			   enum flow_offload_tuple_dir dir)
+{
+	__be32 addr, new_addr;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		addr = iph->daddr;
+		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
+		iph->daddr = new_addr;
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		addr = iph->saddr;
+		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
+		iph->saddr = new_addr;
+		break;
+	default:
+		return -1;
+	}
+
+	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+}
+
+static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+			  enum flow_offload_tuple_dir dir)
+{
+	struct iphdr *iph = ip_hdr(skb);
+	unsigned int thoff = iph->ihl * 4;
+
+	if (flow->flags & FLOW_OFFLOAD_SNAT &&
+	    (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
+	     nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
+		return -1;
+	if (flow->flags & FLOW_OFFLOAD_DNAT &&
+	    (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
+	     nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
+		return -1;
+
+	return 0;
+}
+
+static bool ip_has_options(unsigned int thoff)
+{
+	return thoff != sizeof(struct iphdr);
+}
+
+static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
+			    struct flow_offload_tuple *tuple)
+{
+	struct flow_ports *ports;
+	unsigned int thoff;
+	struct iphdr *iph;
+
+	if (!pskb_may_pull(skb, sizeof(*iph)))
+		return -1;
+
+	iph = ip_hdr(skb);
+	thoff = iph->ihl * 4;
+
+	if (ip_is_fragment(iph) ||
+	    unlikely(ip_has_options(thoff)))
+		return -1;
+
+	if (iph->protocol != IPPROTO_TCP &&
+	    iph->protocol != IPPROTO_UDP)
+		return -1;
+
+	thoff = iph->ihl * 4;
+	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+		return -1;
+
+	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+
+	tuple->src_v4.s_addr	= iph->saddr;
+	tuple->dst_v4.s_addr	= iph->daddr;
+	tuple->src_port		= ports->source;
+	tuple->dst_port		= ports->dest;
+	tuple->l3proto		= AF_INET;
+	tuple->l4proto		= iph->protocol;
+	tuple->iifidx		= dev->ifindex;
+
+	return 0;
+}
+
+/* Based on ip_exceeds_mtu(). */
+static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu)
+		return false;
+
+	if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+		return false;
+
+	return true;
+}
+
+static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rtable *rt)
+{
+	u32 mtu;
+
+	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
+	if (__nf_flow_exceeds_mtu(skb, mtu))
+		return true;
+
+	return false;
+}
+
+static unsigned int
+nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
+			const struct nf_hook_state *state)
+{
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct nf_flowtable *flow_table = priv;
+	struct flow_offload_tuple tuple = {};
+	enum flow_offload_tuple_dir dir;
+	struct flow_offload *flow;
+	struct net_device *outdev;
+	const struct rtable *rt;
+	struct iphdr *iph;
+	__be32 nexthop;
+
+	if (skb->protocol != htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
+		return NF_ACCEPT;
+
+	tuplehash = flow_offload_lookup(flow_table, &tuple);
+	if (tuplehash == NULL)
+		return NF_ACCEPT;
+
+	outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
+	if (!outdev)
+		return NF_ACCEPT;
+
+	dir = tuplehash->tuple.dir;
+	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+
+	rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
+	if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
+		return NF_ACCEPT;
+
+	if (skb_try_make_writable(skb, sizeof(*iph)))
+		return NF_DROP;
+
+	if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
+	    nf_flow_nat_ip(flow, skb, dir) < 0)
+		return NF_DROP;
+
+	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+	iph = ip_hdr(skb);
+	ip_decrease_ttl(iph);
+
+	skb->dev = outdev;
+	nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
+	neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
+
+	return NF_STOLEN;
+}
+
+static struct nf_flowtable_type flowtable_ipv4 = {
+	.family		= NFPROTO_IPV4,
+	.params		= &nf_flow_offload_rhash_params,
+	.gc		= nf_flow_offload_work_gc,
+	.hook		= nf_flow_offload_ip_hook,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nf_flow_ipv4_module_init(void)
+{
+	nft_register_flowtable_type(&flowtable_ipv4);
+
+	return 0;
+}
+
+static void __exit nf_flow_ipv4_module_exit(void)
+{
+	nft_unregister_flowtable_type(&flowtable_ipv4);
+}
+
+module_init(nf_flow_ipv4_module_init);
+module_exit(nf_flow_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NF_FLOWTABLE(AF_INET);
-- 
2.11.0