bpf: Add netns cookie and enable it for bpf cgroup hooks

In Cilium we're mainly using BPF cgroup hooks today in order to implement
kube-proxy free Kubernetes service translation for ClusterIP, NodePort (*),
ExternalIP, and LoadBalancer as well as HostPort mapping [0] for all traffic
between Cilium managed nodes. While this works in its current shape and avoids
packet-level NAT for inter Cilium managed node traffic, there is one major
limitation we're facing today, that is, lack of netns awareness.

In Kubernetes, the concept of Pods (which hold one or multiple containers)
has been built around network namespaces, so while we can use the global scope
of attaching to root BPF cgroup hooks also to our advantage (e.g. for exposing
NodePort ports on loopback addresses), we also have the need to differentiate
between initial network namespaces and non-initial one. For example, ExternalIP
services mandate that non-local service IPs are not to be translated from the
host (initial) network namespace as one example. Right now, we have an ugly
work-around in place where non-local service IPs for ExternalIP services are
not xlated from connect() and friends BPF hooks but instead via less efficient
packet-level NAT on the veth tc ingress hook for Pod traffic.

On top of determining whether we're in initial or non-initial network namespace
we also have a need for a socket-cookie like mechanism for network namespaces
scope. Socket cookies have the nice property that they can be combined as part
of the key structure e.g. for BPF LRU maps without having to worry that the
cookie could be recycled. We are planning to use this for our sessionAffinity
implementation for services. Therefore, add a new bpf_get_netns_cookie() helper
which would resolve both use cases at once: bpf_get_netns_cookie(NULL) would
provide the cookie for the initial network namespace while passing the context
instead of NULL would provide the cookie from the application's network namespace.
We're using a hole, so no size increase; the assignment happens only once.
Therefore this allows for a comparison on initial namespace as well as regular
cookie usage as we have today with socket cookies. We could later on enable
this helper for other program types as well as we would see need.

  (*) Both externalTrafficPolicy={Local|Cluster} types
  [0] https://github.com/cilium/cilium/blob/master/bpf/bpf_sock.c

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/c47d2346982693a9cf9da0e12690453aded4c788.1585323121.git.daniel@iogearbox.net

2 files changed, 52 insertions, 0 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 6cb7e0e24473..e249a499cbe5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4141,6 +4141,39 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+static u64 __bpf_get_netns_cookie(struct sock *sk)
+{
+#ifdef CONFIG_NET_NS
+	return net_gen_cookie(sk ? sk->sk_net.net : &init_net);
+#else
+	return 0;
+#endif
+}
+
+BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx)
+{
+	return __bpf_get_netns_cookie(ctx);
+}
+
+static const struct bpf_func_proto bpf_get_netns_cookie_sock_proto = {
+	.func		= bpf_get_netns_cookie_sock,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX_OR_NULL,
+};
+
+BPF_CALL_1(bpf_get_netns_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx)
+{
+	return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL);
+}
+
+static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = {
+	.func		= bpf_get_netns_cookie_sock_addr,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX_OR_NULL,
+};
+
 BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
 {
 	struct sock *sk = sk_to_full_sk(skb->sk);
@@ -5968,6 +6001,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_sock_proto;
+	case BPF_FUNC_get_netns_cookie:
+		return &bpf_get_netns_cookie_sock_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
@@ -5994,6 +6029,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		}
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_sock_addr_proto;
+	case BPF_FUNC_get_netns_cookie:
+		return &bpf_get_netns_cookie_sock_addr_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_perf_event_output:
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 757cc1d084e7..190ca66a383b 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -69,6 +69,20 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem);
 
 static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;
 
+static atomic64_t cookie_gen;
+
+u64 net_gen_cookie(struct net *net)
+{
+	while (1) {
+		u64 res = atomic64_read(&net->net_cookie);
+
+		if (res)
+			return res;
+		res = atomic64_inc_return(&cookie_gen);
+		atomic64_cmpxchg(&net->net_cookie, 0, res);
+	}
+}
+
 static struct net_generic *net_alloc_generic(void)
 {
 	struct net_generic *ng;
@@ -1087,6 +1101,7 @@ static int __init net_ns_init(void)
 		panic("Could not allocate generic netns");
 
 	rcu_assign_pointer(init_net.gen, ng);
+	net_gen_cookie(&init_net);
 
 	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))