netfilter: flow table support for IPv6

This patch adds the IPv6 flow table type, that implements the datapath
flow table to forward IPv6 traffic.

This patch exports ip6_dst_mtu_forward() that is required to check for
mtu to pass up packets that need PMTUD handling to the classic
forwarding path.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 25be4715578c380d7c01633aa7d5563da8348032..9dc1230d789ce001958b4a2e28ef6134042f9309 100644 (file)
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -969,6 +969,8 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
                              &inet6_sk(sk)->cork);
 }
 
+unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst);
+
 int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
                   struct flowi6 *fl6);
 struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index bcdb615aed6eec7606a7a884a8514b13db4c3f66..19adad6d90bc1956e61d9273b37b2b10cf088185 100644 (file)
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -378,7 +378,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
        return dst_output(net, sk, skb);
 }
 
-static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 {
        unsigned int mtu;
        struct inet6_dev *idev;
@@ -398,6 +398,7 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 
        return mtu;
 }
+EXPORT_SYMBOL_GPL(ip6_dst_mtu_forward);
 
 static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 {

diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 6acb2eecd986cbf64deb0fcdb47c3931cf18a4ed..806e95375ec8fc5a3e829f67260ee82914f20ea0 100644 (file)
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -71,6 +71,14 @@ config NFT_FIB_IPV6
 endif # NF_TABLES_IPV6
 endif # NF_TABLES
 
+config NF_FLOW_TABLE_IPV6
+       select NF_FLOW_TABLE
+       tristate "Netfilter flow table IPv6 module"
+       help
+         This option adds the flow table IPv6 support.
+
+         To compile it as a module, choose M here.
+
 config NF_DUP_IPV6
        tristate "Netfilter IPv6 packet duplication to alternate destination"
        depends on !NF_CONNTRACK || NF_CONNTRACK

diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index c6ee0cdd0ba9821e9ae93045aaeac41ae2e4bcc7..95611c4b39b05ad4ef83b060955eb2a8dfab7e95 100644 (file)
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -45,6 +45,9 @@ obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o
 obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
 obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
 
+# flow table support
+obj-$(CONFIG_NF_FLOW_TABLE_IPV6) += nf_flow_table_ipv6.o
+
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
 obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o

diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
new file mode 100644 (file)
index 0000000..d7d073b
--- /dev/null
+++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c
@@ -0,0 +1,277 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <linux/ipv6.h>
+#include <linux/netdevice.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.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_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
+                               struct in6_addr *addr,
+                               struct in6_addr *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_replace16(&tcph->check, skb, addr->s6_addr32,
+                                 new_addr->s6_addr32, true);
+
+       return 0;
+}
+
+static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
+                               struct in6_addr *addr,
+                               struct in6_addr *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_replace16(&udph->check, skb, addr->s6_addr32,
+                                         new_addr->s6_addr32, true);
+               if (!udph->check)
+                       udph->check = CSUM_MANGLED_0;
+       }
+
+       return 0;
+}
+
+static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h,
+                                   unsigned int thoff, struct in6_addr *addr,
+                                   struct in6_addr *new_addr)
+{
+       switch (ip6h->nexthdr) {
+       case IPPROTO_TCP:
+               if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0)
+                       return NF_DROP;
+               break;
+       case IPPROTO_UDP:
+               if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0)
+                       return NF_DROP;
+               break;
+       }
+
+       return 0;
+}
+
+static int nf_flow_snat_ipv6(const struct flow_offload *flow,
+                            struct sk_buff *skb, struct ipv6hdr *ip6h,
+                            unsigned int thoff,
+                            enum flow_offload_tuple_dir dir)
+{
+       struct in6_addr addr, new_addr;
+
+       switch (dir) {
+       case FLOW_OFFLOAD_DIR_ORIGINAL:
+               addr = ip6h->saddr;
+               new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6;
+               ip6h->saddr = new_addr;
+               break;
+       case FLOW_OFFLOAD_DIR_REPLY:
+               addr = ip6h->daddr;
+               new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6;
+               ip6h->daddr = new_addr;
+               break;
+       default:
+               return -1;
+       }
+
+       return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
+}
+
+static int nf_flow_dnat_ipv6(const struct flow_offload *flow,
+                            struct sk_buff *skb, struct ipv6hdr *ip6h,
+                            unsigned int thoff,
+                            enum flow_offload_tuple_dir dir)
+{
+       struct in6_addr addr, new_addr;
+
+       switch (dir) {
+       case FLOW_OFFLOAD_DIR_ORIGINAL:
+               addr = ip6h->daddr;
+               new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6;
+               ip6h->daddr = new_addr;
+               break;
+       case FLOW_OFFLOAD_DIR_REPLY:
+               addr = ip6h->saddr;
+               new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6;
+               ip6h->saddr = new_addr;
+               break;
+       default:
+               return -1;
+       }
+
+       return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
+}
+
+static int nf_flow_nat_ipv6(const struct flow_offload *flow,
+                           struct sk_buff *skb,
+                           enum flow_offload_tuple_dir dir)
+{
+       struct ipv6hdr *ip6h = ipv6_hdr(skb);
+       unsigned int thoff = sizeof(*ip6h);
+
+       if (flow->flags & FLOW_OFFLOAD_SNAT &&
+           (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
+            nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
+               return -1;
+       if (flow->flags & FLOW_OFFLOAD_DNAT &&
+           (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
+            nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
+               return -1;
+
+       return 0;
+}
+
+static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
+                             struct flow_offload_tuple *tuple)
+{
+       struct flow_ports *ports;
+       struct ipv6hdr *ip6h;
+       unsigned int thoff;
+
+       if (!pskb_may_pull(skb, sizeof(*ip6h)))
+               return -1;
+
+       ip6h = ipv6_hdr(skb);
+
+       if (ip6h->nexthdr != IPPROTO_TCP &&
+           ip6h->nexthdr != IPPROTO_UDP)
+               return -1;
+
+       thoff = sizeof(*ip6h);
+       if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+               return -1;
+
+       ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+
+       tuple->src_v6           = ip6h->saddr;
+       tuple->dst_v6           = ip6h->daddr;
+       tuple->src_port         = ports->source;
+       tuple->dst_port         = ports->dest;
+       tuple->l3proto          = AF_INET6;
+       tuple->l4proto          = ip6h->nexthdr;
+       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 (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 rt6_info *rt)
+{
+       u32 mtu;
+
+       mtu = ip6_dst_mtu_forward(&rt->dst);
+       if (__nf_flow_exceeds_mtu(skb, mtu))
+               return true;
+
+       return false;
+}
+
+static unsigned int
+nf_flow_offload_ipv6_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;
+       struct in6_addr *nexthop;
+       struct ipv6hdr *ip6h;
+       struct rt6_info *rt;
+
+       if (skb->protocol != htons(ETH_P_IPV6))
+               return NF_ACCEPT;
+
+       if (nf_flow_tuple_ipv6(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 = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
+       if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
+               return NF_ACCEPT;
+
+       if (skb_try_make_writable(skb, sizeof(*ip6h)))
+               return NF_DROP;
+
+       if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
+           nf_flow_nat_ipv6(flow, skb, dir) < 0)
+               return NF_DROP;
+
+       flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+       ip6h = ipv6_hdr(skb);
+       ip6h->hop_limit--;
+
+       skb->dev = outdev;
+       nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
+       neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
+
+       return NF_STOLEN;
+}
+
+static struct nf_flowtable_type flowtable_ipv6 = {
+       .family         = NFPROTO_IPV6,
+       .params         = &nf_flow_offload_rhash_params,
+       .gc             = nf_flow_offload_work_gc,
+       .hook           = nf_flow_offload_ipv6_hook,
+       .owner          = THIS_MODULE,
+};
+
+static int __init nf_flow_ipv6_module_init(void)
+{
+       nft_register_flowtable_type(&flowtable_ipv6);
+
+       return 0;
+}
+
+static void __exit nf_flow_ipv6_module_exit(void)
+{
+       nft_unregister_flowtable_type(&flowtable_ipv6);
+}
+
+module_init(nf_flow_ipv6_module_init);
+module_exit(nf_flow_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NF_FLOWTABLE(AF_INET6);