[XFRM]: Allow packet drops during larval state resolution.

The current IPSEC rule resolution behavior we have does not work for a
lot of people, even though technically it's an improvement from the
-EAGAIN buisness we had before.

Right now we'll block until the key manager resolves the route.  That
works for simple cases, but many folks would rather packets get
silently dropped until the key manager resolves the IPSEC rules.

We can't tell these folks to "set the socket non-blocking" because
they don't have control over the non-block setting of things like the
sockets used to resolve DNS deep inside of the resolver libraries in
libc.

With that in mind I coded up the patch below with some help from
Herbert Xu which provides packet-drop behavior during larval state
resolution, controllable via sysctl and off by default.

This lays the framework to either:

1) Make this default at some point or...

2) Move this logic into xfrm{4,6}_policy.c and implement the
   ARP-like resolution queue we've all been dreaming of.
   The idea would be to queue packets to the policy, then
   once the larval state is resolved by the key manager we
   re-resolve the route and push the packets out.  The
   packets would timeout if the rule didn't get resolved
   in a certain amount of time.

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 70 insertions, 1 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index df9fe4f2e8cc..8603cfb271f2 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2598,6 +2598,69 @@ int __ip_route_output_key(struct rtable **rp, const struct flowi *flp)
 
 EXPORT_SYMBOL_GPL(__ip_route_output_key);
 
+static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
+{
+}
+
+static struct dst_ops ipv4_dst_blackhole_ops = {
+	.family			=	AF_INET,
+	.protocol		=	__constant_htons(ETH_P_IP),
+	.destroy		=	ipv4_dst_destroy,
+	.check			=	ipv4_dst_check,
+	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
+	.entry_size		=	sizeof(struct rtable),
+};
+
+
+static int ipv4_blackhole_output(struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return 0;
+}
+
+static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp, struct sock *sk)
+{
+	struct rtable *ort = *rp;
+	struct rtable *rt = (struct rtable *)
+		dst_alloc(&ipv4_dst_blackhole_ops);
+
+	if (rt) {
+		struct dst_entry *new = &rt->u.dst;
+
+		atomic_set(&new->__refcnt, 1);
+		new->__use = 1;
+		new->input = ipv4_blackhole_output;
+		new->output = ipv4_blackhole_output;
+		memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
+
+		new->dev = ort->u.dst.dev;
+		if (new->dev)
+			dev_hold(new->dev);
+
+		rt->fl = ort->fl;
+
+		rt->idev = ort->idev;
+		if (rt->idev)
+			in_dev_hold(rt->idev);
+		rt->rt_flags = ort->rt_flags;
+		rt->rt_type = ort->rt_type;
+		rt->rt_dst = ort->rt_dst;
+		rt->rt_src = ort->rt_src;
+		rt->rt_iif = ort->rt_iif;
+		rt->rt_gateway = ort->rt_gateway;
+		rt->rt_spec_dst = ort->rt_spec_dst;
+		rt->peer = ort->peer;
+		if (rt->peer)
+			atomic_inc(&rt->peer->refcnt);
+
+		dst_free(new);
+	}
+
+	dst_release(&(*rp)->u.dst);
+	*rp = rt;
+	return (rt ? 0 : -ENOMEM);
+}
+
 int ip_route_output_flow(struct rtable **rp, struct flowi *flp, struct sock *sk, int flags)
 {
 	int err;
@@ -2610,7 +2673,11 @@ int ip_route_output_flow(struct rtable **rp, struct flowi *flp, struct sock *sk,
 			flp->fl4_src = (*rp)->rt_src;
 		if (!flp->fl4_dst)
 			flp->fl4_dst = (*rp)->rt_dst;
-		return xfrm_lookup((struct dst_entry **)rp, flp, sk, flags);
+		err = __xfrm_lookup((struct dst_entry **)rp, flp, sk, flags);
+		if (err == -EREMOTE)
+			err = ipv4_dst_blackhole(rp, flp, sk);
+
+		return err;
 	}
 
 	return 0;
@@ -3139,6 +3206,8 @@ int __init ip_rt_init(void)
 		kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0,
 				  SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
 
+	ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep;
+
 	rt_hash_table = (struct rt_hash_bucket *)
 		alloc_large_system_hash("IP route cache",
 					sizeof(struct rt_hash_bucket),