bpf: Add bpf_get_listener_sock(struct bpf_sock *sk) helper

Add a new helper "struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)"
which returns a bpf_sock in TCP_LISTEN state.  It will trace back to
the listener sk from a request_sock if possible.  It returns NULL
for all other cases.

No reference is taken because the helper ensures the sk is
in SOCK_RCU_FREE (where the TCP_LISTEN sock should be in).
Hence, bpf_sk_release() is unnecessary and the verifier does not
allow bpf_sk_release(listen_sk) to be called either.

The following is also allowed because the bpf_prog is run under
rcu_read_lock():

	sk = bpf_sk_lookup_tcp();
	/* if (!sk) { ... } */
	listen_sk = bpf_get_listener_sock(sk);
	/* if (!listen_sk) { ... } */
	bpf_sk_release(sk);
	src_port = listen_sk->src_port; /* Allowed */

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3c38ac9..983b25c 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2366,6 +2366,14 @@ union bpf_attr {
  *             current value is ect (ECN capable). Works with IPv6 and IPv4.
  *     Return
  *             1 if set, 0 if not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ *     Description
+ *             Return a **struct bpf_sock** pointer in TCP_LISTEN state.
+ *             bpf_sk_release() is unnecessary and not allowed.
+ *     Return
+ *             A **struct bpf_sock** pointer on success, or NULL in
+ *             case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)          \
        FN(unspec),                     \
@@ -2465,7 +2473,8 @@ union bpf_attr {
        FN(spin_unlock),                \
        FN(sk_fullsock),                \
        FN(tcp_sock),                   \
-       FN(skb_ecn_set_ce),
+       FN(skb_ecn_set_ce),             \
+       FN(get_listener_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

diff --git a/net/core/filter.c b/net/core/filter.c
index 36b6afa..647c63a 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5418,6 +5418,23 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = {
        .arg1_type      = ARG_PTR_TO_SOCK_COMMON,
 };
 
+BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk)
+{
+       sk = sk_to_full_sk(sk);
+
+       if (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE))
+               return (unsigned long)sk;
+
+       return (unsigned long)NULL;
+}
+
+static const struct bpf_func_proto bpf_get_listener_sock_proto = {
+       .func           = bpf_get_listener_sock,
+       .gpl_only       = false,
+       .ret_type       = RET_PTR_TO_SOCKET_OR_NULL,
+       .arg1_type      = ARG_PTR_TO_SOCK_COMMON,
+};
+
 BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
 {
        unsigned int iphdr_len;
@@ -5603,6 +5620,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #ifdef CONFIG_INET
        case BPF_FUNC_tcp_sock:
                return &bpf_tcp_sock_proto;
+       case BPF_FUNC_get_listener_sock:
+               return &bpf_get_listener_sock_proto;
        case BPF_FUNC_skb_ecn_set_ce:
                return &bpf_skb_ecn_set_ce_proto;
 #endif
@@ -5698,6 +5717,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
                return &bpf_sk_release_proto;
        case BPF_FUNC_tcp_sock:
                return &bpf_tcp_sock_proto;
+       case BPF_FUNC_get_listener_sock:
+               return &bpf_get_listener_sock_proto;
 #endif
        default:
                return bpf_base_func_proto(func_id);