netfilter: introduce support for reject at prerouting stage

REJECT statement can be only used in INPUT, FORWARD and OUTPUT
chains. This patch adds support of REJECT, both icmp and tcp
reset, at PREROUTING stage.

The need for this patch comes from the requirement of some
forwarding devices to reject traffic before the natting and
routing decisions.

The main use case is to be able to send a graceful termination
to legitimate clients that, under any circumstances, the NATed
endpoints are not available. This option allows clients to
decide either to perform a reconnection or manage the error in
their side, instead of just dropping the connection and let
them die due to timeout.

It is supported ipv4, ipv6 and inet families for nft
infrastructure.

Signed-off-by: Laura Garcia Liebana <nevola@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

net/ipv4/netfilter/nf_reject_ipv4.c

@@ -96,6 +96,21 @@ void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb,
 }
 EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put);
 
+static int nf_reject_fill_skb_dst(struct sk_buff *skb_in)
+{
+	struct dst_entry *dst = NULL;
+	struct flowi fl;
+
+	memset(&fl, 0, sizeof(struct flowi));
+	fl.u.ip4.daddr = ip_hdr(skb_in)->saddr;
+	nf_ip_route(dev_net(skb_in->dev), &dst, &fl, false);
+	if (!dst)
+		return -1;
+
+	skb_dst_set(skb_in, dst);
+	return 0;
+}
+
 /* Send RST reply */
 void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 {
@@ -109,6 +124,9 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	if (!oth)
 		return;
 
+	if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(oldskb))
+		return;
+
 	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
 		return;
 
@@ -175,6 +193,9 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
 	if (iph->frag_off & htons(IP_OFFSET))
 		return;
 
+	if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(skb_in))
+		return;
+
 	if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(proto)) {
 		icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
 		return;

net/ipv6/netfilter/nf_reject_ipv6.c

@@ -126,6 +126,21 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb,
 }
 EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_put);
 
+static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
+{
+	struct dst_entry *dst = NULL;
+	struct flowi fl;
+
+	memset(&fl, 0, sizeof(struct flowi));
+	fl.u.ip6.daddr = ipv6_hdr(skb_in)->saddr;
+	nf_ip6_route(dev_net(skb_in->dev), &dst, &fl, false);
+	if (!dst)
+		return -1;
+
+	skb_dst_set(skb_in, dst);
+	return 0;
+}
+
 void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 {
 	struct net_device *br_indev __maybe_unused;
@@ -154,6 +169,14 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 	fl6.daddr = oip6h->saddr;
 	fl6.fl6_sport = otcph->dest;
 	fl6.fl6_dport = otcph->source;
+
+	if (hook == NF_INET_PRE_ROUTING) {
+		nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
+		if (!dst)
+			return;
+		skb_dst_set(oldskb, dst);
+	}
+
 	fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev);
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark);
 	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
@@ -245,6 +268,9 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
 	if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
 		skb_in->dev = net->loopback_dev;
 
+	if (hooknum == NF_INET_PRE_ROUTING && nf_reject6_fill_skb_dst(skb_in))
+		return;
+
 	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
 }
 EXPORT_SYMBOL_GPL(nf_send_unreach6);

net/netfilter/nft_reject.c

@@ -30,7 +30,8 @@ int nft_reject_validate(const struct nft_ctx *ctx,
 	return nft_chain_validate_hooks(ctx->chain,
 					(1 << NF_INET_LOCAL_IN) |
 					(1 << NF_INET_FORWARD) |
-					(1 << NF_INET_LOCAL_OUT));
+					(1 << NF_INET_LOCAL_OUT) |
+					(1 << NF_INET_PRE_ROUTING));
 }
 EXPORT_SYMBOL_GPL(nft_reject_validate);