net: bpf: Don't leak time wait and request sockets

It's possible to leak time wait and request sockets via the following
BPF pseudo code:
 
  sk = bpf_skc_lookup_tcp(...)
  if (sk)
    bpf_sk_release(sk)

If sk->sk_state is TCP_NEW_SYN_RECV or TCP_TIME_WAIT the refcount taken
by bpf_skc_lookup_tcp is not undone by bpf_sk_release. This is because
sk_flags is re-used for other data in both kinds of sockets. The check

  !sock_flag(sk, SOCK_RCU_FREE)

therefore returns a bogus result. Check that sk_flags is valid by calling
sk_fullsock. Skip checking SOCK_RCU_FREE if we already know that sk is
not a full socket.

Fixes: edbf8c01de5a ("bpf: add skc_lookup_tcp helper")
Fixes: f7355a6c0497 ("bpf: Check sk_fullsock() before returning from bpf_sk_lookup()")
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200110132336.26099-1-lmb@cloudflare.com

diff --git a/net/core/filter.c b/net/core/filter.c
index 28b3c25..d22d108 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5318,8 +5318,7 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
        if (sk) {
                sk = sk_to_full_sk(sk);
                if (!sk_fullsock(sk)) {
-                       if (!sock_flag(sk, SOCK_RCU_FREE))
-                               sock_gen_put(sk);
+                       sock_gen_put(sk);
                        return NULL;
                }
        }
@@ -5356,8 +5355,7 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
        if (sk) {
                sk = sk_to_full_sk(sk);
                if (!sk_fullsock(sk)) {
-                       if (!sock_flag(sk, SOCK_RCU_FREE))
-                               sock_gen_put(sk);
+                       sock_gen_put(sk);
                        return NULL;
                }
        }
@@ -5424,7 +5422,8 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-       if (!sock_flag(sk, SOCK_RCU_FREE))
+       /* Only full sockets have sk->sk_flags. */
+       if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE))
                sock_gen_put(sk);
        return 0;
 }