netfilter: nf_flow_table: fix offload for flows that are subject to xfrm

This makes the previously added 'encap test' pass.
Because its possible that the xfrm dst entry becomes stale while such
a flow is offloaded, we need to call dst_check() -- the notifier that
handles this for non-tunneled traffic isn't sufficient, because SA or
or policies might have changed.

If dst becomes stale the flow offload entry will be tagged for teardown
and packets will be passed to 'classic' forwarding path.

Removing the entry right away is problematic, as this would
introduce a race condition with the gc worker.

In case flow is long-lived, it could eventually be offloaded again
once the gc worker removes the entry from the flow table.

Signed-off-by: Florian Westphal <[email protected]>
Signed-off-by: Pablo Neira Ayuso <[email protected]>

Author: Florian Westphal

net/netfilter/nf_flow_table_ip.c

@@ -214,6 +214,25 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
+static int nf_flow_offload_dst_check(struct dst_entry *dst)
+{
+	if (unlikely(dst_xfrm(dst)))
+		return dst_check(dst, 0) ? 0 : -1;
+
+	return 0;
+}
+
+static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
+				      const struct nf_hook_state *state,
+				      struct dst_entry *dst)
+{
+	skb_orphan(skb);
+	skb_dst_set_noref(skb, dst);
+	skb->tstamp = 0;
+	dst_output(state->net, state->sk, skb);
+	return NF_STOLEN;
+}
+
 unsigned int
 nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 			const struct nf_hook_state *state)
@@ -254,13 +273,25 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
 		return NF_ACCEPT;
 
+	if (nf_flow_offload_dst_check(&rt->dst)) {
+		flow_offload_teardown(flow);
+		return NF_ACCEPT;
+	}
+
 	if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
 		return NF_DROP;
 
 	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
 	iph = ip_hdr(skb);
 	ip_decrease_ttl(iph);
 
+	if (unlikely(dst_xfrm(&rt->dst))) {
+		memset(skb->cb, 0, sizeof(struct inet_skb_parm));
+		IPCB(skb)->iif = skb->dev->ifindex;
+		IPCB(skb)->flags = IPSKB_FORWARDED;
+		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
+	}
+
 	skb->dev = outdev;
 	nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
 	skb_dst_set_noref(skb, &rt->dst);
@@ -467,6 +498,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 				sizeof(*ip6h)))
 		return NF_ACCEPT;
 
+	if (nf_flow_offload_dst_check(&rt->dst)) {
+		flow_offload_teardown(flow);
+		return NF_ACCEPT;
+	}
+
 	if (skb_try_make_writable(skb, sizeof(*ip6h)))
 		return NF_DROP;
 
@@ -477,6 +513,13 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	ip6h = ipv6_hdr(skb);
 	ip6h->hop_limit--;
 
+	if (unlikely(dst_xfrm(&rt->dst))) {
+		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
+		IP6CB(skb)->iif = skb->dev->ifindex;
+		IP6CB(skb)->flags = IP6SKB_FORWARDED;
+		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
+	}
+
 	skb->dev = outdev;
 	nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
 	skb_dst_set_noref(skb, &rt->dst);