netfilter: add netfilter hooks to SRv6 data plane

This patch introduces netfilter hooks for solving the problem that
conntrack couldn't record both inner flows and outer flows.

This patch also introduces a new sysctl toggle for enabling lightweight
tunnel netfilter hooks.

Signed-off-by: Ryoga Saito <contact@proelbtn.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

2 files changed, 150 insertions, 36 deletions

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 897fa59c47de..6ebc7aa24466 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -26,6 +26,8 @@
 #ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
 #endif
+#include <net/lwtunnel.h>
+#include <linux/netfilter.h>
 
 static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo)
 {
@@ -295,11 +297,19 @@ static int seg6_do_srh(struct sk_buff *skb)
 
 	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+	nf_reset_ct(skb);
 
 	return 0;
 }
 
-static int seg6_input(struct sk_buff *skb)
+static int seg6_input_finish(struct net *net, struct sock *sk,
+			     struct sk_buff *skb)
+{
+	return dst_input(skb);
+}
+
+static int seg6_input_core(struct net *net, struct sock *sk,
+			   struct sk_buff *skb)
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct dst_entry *dst = NULL;
@@ -337,10 +347,41 @@ static int seg6_input(struct sk_buff *skb)
 	if (unlikely(err))
 		return err;
 
-	return dst_input(skb);
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
+			       dev_net(skb->dev), NULL, skb, NULL,
+			       skb_dst(skb)->dev, seg6_input_finish);
+
+	return seg6_input_finish(dev_net(skb->dev), NULL, skb);
 }
 
-static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int seg6_input_nf(struct sk_buff *skb)
+{
+	struct net_device *dev = skb_dst(skb)->dev;
+	struct net *net = dev_net(skb->dev);
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, NULL,
+			       skb, NULL, dev, seg6_input_core);
+	case htons(ETH_P_IPV6):
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, NULL,
+			       skb, NULL, dev, seg6_input_core);
+	}
+
+	return -EINVAL;
+}
+
+static int seg6_input(struct sk_buff *skb)
+{
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return seg6_input_nf(skb);
+
+	return seg6_input_core(dev_net(skb->dev), NULL, skb);
+}
+
+static int seg6_output_core(struct net *net, struct sock *sk,
+			    struct sk_buff *skb)
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct dst_entry *dst = NULL;
@@ -387,12 +428,40 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (unlikely(err))
 		goto drop;
 
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
+			       NULL, skb_dst(skb)->dev, dst_output);
+
 	return dst_output(net, sk, skb);
 drop:
 	kfree_skb(skb);
 	return err;
 }
 
+static int seg6_output_nf(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct net_device *dev = skb_dst(skb)->dev;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb,
+			       NULL, dev, seg6_output_core);
+	case htons(ETH_P_IPV6):
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb,
+			       NULL, dev, seg6_output_core);
+	}
+
+	return -EINVAL;
+}
+
+static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return seg6_output_nf(net, sk, skb);
+
+	return seg6_output_core(net, sk, skb);
+}
+
 static int seg6_build_state(struct net *net, struct nlattr *nla,
 			    unsigned int family, const void *cfg,
 			    struct lwtunnel_state **ts,
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 60bf3b877957..ddc8dfcd4e2b 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -30,6 +30,8 @@
 #include <net/seg6_local.h>
 #include <linux/etherdevice.h>
 #include <linux/bpf.h>
+#include <net/lwtunnel.h>
+#include <linux/netfilter.h>
 
 #define SEG6_F_ATTR(i)		BIT(i)
 
@@ -413,12 +415,33 @@ drop:
 	return -EINVAL;
 }
 
+static int input_action_end_dx6_finish(struct net *net, struct sock *sk,
+				       struct sk_buff *skb)
+{
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct in6_addr *nhaddr = NULL;
+	struct seg6_local_lwt *slwt;
+
+	slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
+
+	/* The inner packet is not associated to any local interface,
+	 * so we do not call netif_rx().
+	 *
+	 * If slwt->nh6 is set to ::, then lookup the nexthop for the
+	 * inner packet's DA. Otherwise, use the specified nexthop.
+	 */
+	if (!ipv6_addr_any(&slwt->nh6))
+		nhaddr = &slwt->nh6;
+
+	seg6_lookup_nexthop(skb, nhaddr, 0);
+
+	return dst_input(skb);
+}
+
 /* decapsulate and forward to specified nexthop */
 static int input_action_end_dx6(struct sk_buff *skb,
 				struct seg6_local_lwt *slwt)
 {
-	struct in6_addr *nhaddr = NULL;
-
 	/* this function accepts IPv6 encapsulated packets, with either
 	 * an SRH with SL=0, or no SRH.
 	 */
@@ -429,40 +452,30 @@ static int input_action_end_dx6(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto drop;
 
-	/* The inner packet is not associated to any local interface,
-	 * so we do not call netif_rx().
-	 *
-	 * If slwt->nh6 is set to ::, then lookup the nexthop for the
-	 * inner packet's DA. Otherwise, use the specified nexthop.
-	 */
-
-	if (!ipv6_addr_any(&slwt->nh6))
-		nhaddr = &slwt->nh6;
-
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+	nf_reset_ct(skb);
 
-	seg6_lookup_nexthop(skb, nhaddr, 0);
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
+			       dev_net(skb->dev), NULL, skb, NULL,
+			       skb_dst(skb)->dev, input_action_end_dx6_finish);
 
-	return dst_input(skb);
+	return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb);
 drop:
 	kfree_skb(skb);
 	return -EINVAL;
 }
 
-static int input_action_end_dx4(struct sk_buff *skb,
-				struct seg6_local_lwt *slwt)
+static int input_action_end_dx4_finish(struct net *net, struct sock *sk,
+				       struct sk_buff *skb)
 {
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct seg6_local_lwt *slwt;
 	struct iphdr *iph;
 	__be32 nhaddr;
 	int err;
 
-	if (!decap_and_validate(skb, IPPROTO_IPIP))
-		goto drop;
-
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		goto drop;
-
-	skb->protocol = htons(ETH_P_IP);
+	slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
 
 	iph = ip_hdr(skb);
 
@@ -470,14 +483,34 @@ static int input_action_end_dx4(struct sk_buff *skb,
 
 	skb_dst_drop(skb);
 
-	skb_set_transport_header(skb, sizeof(struct iphdr));
-
 	err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev);
-	if (err)
-		goto drop;
+	if (err) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
 
 	return dst_input(skb);
+}
+
+static int input_action_end_dx4(struct sk_buff *skb,
+				struct seg6_local_lwt *slwt)
+{
+	if (!decap_and_validate(skb, IPPROTO_IPIP))
+		goto drop;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto drop;
+
+	skb->protocol = htons(ETH_P_IP);
+	skb_set_transport_header(skb, sizeof(struct iphdr));
+	nf_reset_ct(skb);
+
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
+			       dev_net(skb->dev), NULL, skb, NULL,
+			       skb_dst(skb)->dev, input_action_end_dx4_finish);
 
+	return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb);
 drop:
 	kfree_skb(skb);
 	return -EINVAL;
@@ -645,6 +678,7 @@ static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb,
 	skb_dst_drop(skb);
 
 	skb_set_transport_header(skb, hdrlen);
+	nf_reset_ct(skb);
 
 	return end_dt_vrf_rcv(skb, family, vrf);
 
@@ -1078,7 +1112,8 @@ static void seg6_local_update_counters(struct seg6_local_lwt *slwt,
 	u64_stats_update_end(&pcounters->syncp);
 }
 
-static int seg6_local_input(struct sk_buff *skb)
+static int seg6_local_input_core(struct net *net, struct sock *sk,
+				 struct sk_buff *skb)
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct seg6_action_desc *desc;
@@ -1086,11 +1121,6 @@ static int seg6_local_input(struct sk_buff *skb)
 	unsigned int len = skb->len;
 	int rc;
 
-	if (skb->protocol != htons(ETH_P_IPV6)) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
-
 	slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
 	desc = slwt->desc;
 
@@ -1104,6 +1134,21 @@ static int seg6_local_input(struct sk_buff *skb)
 	return rc;
 }
 
+static int seg6_local_input(struct sk_buff *skb)
+{
+	if (skb->protocol != htons(ETH_P_IPV6)) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
+			       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+			       seg6_local_input_core);
+
+	return seg6_local_input_core(dev_net(skb->dev), NULL, skb);
+}
+
 static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
 	[SEG6_LOCAL_ACTION]	= { .type = NLA_U32 },
 	[SEG6_LOCAL_SRH]	= { .type = NLA_BINARY },