bpf, sockmap: Allow inserting listening TCP sockets into sockmap

In order for sockmap/sockhash types to become generic collections for
storing TCP sockets we need to loosen the checks during map update, while
tightening the checks in redirect helpers.

Currently sock{map,hash} require the TCP socket to be in established state,
which prevents inserting listening sockets.

Change the update pre-checks so the socket can also be in listening state.

Since it doesn't make sense to redirect with sock{map,hash} to listening
sockets, add appropriate socket state checks to BPF redirect helpers too.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200218171023.844439-5-jakub@cloudflare.com

net/core/sock_map.c

@@ -391,7 +391,8 @@ out_free:
 static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops)
 {
 	return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB ||
-	       ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB;
+	       ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB ||
+	       ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB;
 }
 
 static bool sock_map_sk_is_suitable(const struct sock *sk)
@@ -400,6 +401,16 @@ static bool sock_map_sk_is_suitable(const struct sock *sk)
 	       sk->sk_protocol == IPPROTO_TCP;
 }
 
+static bool sock_map_sk_state_allowed(const struct sock *sk)
+{
+	return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
+}
+
+static bool sock_map_redirect_allowed(const struct sock *sk)
+{
+	return sk->sk_state != TCP_LISTEN;
+}
+
 static int sock_map_update_elem(struct bpf_map *map, void *key,
 				void *value, u64 flags)
 {
@@ -423,7 +434,7 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
 	}
 
 	sock_map_sk_acquire(sk);
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (!sock_map_sk_state_allowed(sk))
 		ret = -EOPNOTSUPP;
 	else
 		ret = sock_map_update_common(map, idx, sk, flags);
@@ -460,13 +471,17 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
 	   struct bpf_map *, map, u32, key, u64, flags)
 {
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+	struct sock *sk;
 
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
-	tcb->bpf.flags = flags;
-	tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key);
-	if (!tcb->bpf.sk_redir)
+
+	sk = __sock_map_lookup_elem(map, key);
+	if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
 		return SK_DROP;
+
+	tcb->bpf.flags = flags;
+	tcb->bpf.sk_redir = sk;
 	return SK_PASS;
 }
 
@@ -483,12 +498,17 @@ const struct bpf_func_proto bpf_sk_redirect_map_proto = {
 BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg,
 	   struct bpf_map *, map, u32, key, u64, flags)
 {
+	struct sock *sk;
+
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
-	msg->flags = flags;
-	msg->sk_redir = __sock_map_lookup_elem(map, key);
-	if (!msg->sk_redir)
+
+	sk = __sock_map_lookup_elem(map, key);
+	if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
 		return SK_DROP;
+
+	msg->flags = flags;
+	msg->sk_redir = sk;
 	return SK_PASS;
 }
 
@@ -748,7 +768,7 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key,
 	}
 
 	sock_map_sk_acquire(sk);
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (!sock_map_sk_state_allowed(sk))
 		ret = -EOPNOTSUPP;
 	else
 		ret = sock_hash_update_common(map, key, sk, flags);
@@ -916,13 +936,17 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+	struct sock *sk;
 
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
-	tcb->bpf.flags = flags;
-	tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key);
-	if (!tcb->bpf.sk_redir)
+
+	sk = __sock_hash_lookup_elem(map, key);
+	if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
 		return SK_DROP;
+
+	tcb->bpf.flags = flags;
+	tcb->bpf.sk_redir = sk;
 	return SK_PASS;
 }
 
@@ -939,12 +963,17 @@ const struct bpf_func_proto bpf_sk_redirect_hash_proto = {
 BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
+	struct sock *sk;
+
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
-	msg->flags = flags;
-	msg->sk_redir = __sock_hash_lookup_elem(map, key);
-	if (!msg->sk_redir)
+
+	sk = __sock_hash_lookup_elem(map, key);
+	if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
 		return SK_DROP;
+
+	msg->flags = flags;
+	msg->sk_redir = sk;
 	return SK_PASS;
 }
 

tools/testing/selftests/bpf/test_maps.c

@@ -756,11 +756,7 @@ static void test_sockmap(unsigned int tasks, void *data)
 	/* Test update without programs */
 	for (i = 0; i < 6; i++) {
 		err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
-		if (i < 2 && !err) {
-			printf("Allowed update sockmap '%i:%i' not in ESTABLISHED\n",
-			       i, sfd[i]);
-			goto out_sockmap;
-		} else if (i >= 2 && err) {
+		if (err) {
 			printf("Failed noprog update sockmap '%i:%i'\n",
 			       i, sfd[i]);
 			goto out_sockmap;