Re: [PATCH v2 net-next] net/tcp: trace all TCP/IP state transition with tcp_set_state tracepoint

From: Song Liu
Date: Sat Nov 18 2017 - 13:49:54 EST



> On Nov 18, 2017, at 7:32 AM, Yafang Shao <laoar.shao@xxxxxxxxx> wrote:
>
> The TCP/IP transition from TCP_LISTEN to TCP_SYN_RECV and some other
> transitions are not traced with tcp_set_state tracepoint.
>
> In order to trace the whole tcp lifespans, two helpers are introduced,
> void __tcp_set_state(struct sock *sk, int state)
> void __sk_state_store(struct sock *sk, int newstate)
>
> When do TCP/IP state transition, we should use these two helpers or use
> tcp_set_state() other than assigning a value to sk_state directly.
>
> Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
> ---
> include/net/tcp.h | 2 ++
> net/ipv4/inet_connection_sock.c | 6 +++---
> net/ipv4/inet_hashtables.c | 2 +-
> net/ipv4/tcp.c | 12 ++++++++++++
> 4 files changed, 18 insertions(+), 4 deletions(-)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 85ea578..4f2d015 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -1247,6 +1247,8 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
> "Close Wait","Last ACK","Listen","Closing"
> };
> #endif
> +void __sk_state_store(struct sock *sk, int newstate);
> +void __tcp_set_state(struct sock *sk, int state);
> void tcp_set_state(struct sock *sk, int state);
>
> void tcp_done(struct sock *sk);
> diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
> index 4ca46dc..f3967f1 100644
> --- a/net/ipv4/inet_connection_sock.c
> +++ b/net/ipv4/inet_connection_sock.c
> @@ -783,7 +783,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
> if (newsk) {
> struct inet_connection_sock *newicsk = inet_csk(newsk);
>
> - newsk->sk_state = TCP_SYN_RECV;
> + __tcp_set_state(newsk, TCP_SYN_RECV);
> newicsk->icsk_bind_hash = NULL;
>
> inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
> @@ -877,7 +877,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
> * It is OK, because this socket enters to hash table only
> * after validation is complete.
> */
> - sk_state_store(sk, TCP_LISTEN);
> + __sk_state_store(sk, TCP_LISTEN);
> if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
> inet->inet_sport = htons(inet->inet_num);
>
> @@ -888,7 +888,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
> return 0;
> }
>
> - sk->sk_state = TCP_CLOSE;
> + __tcp_set_state(sk, TCP_CLOSE);
> return err;
> }
> EXPORT_SYMBOL_GPL(inet_csk_listen_start);
> diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
> index e7d15fb..72c15b6 100644
> --- a/net/ipv4/inet_hashtables.c
> +++ b/net/ipv4/inet_hashtables.c
> @@ -430,7 +430,7 @@ bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
> sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
> } else {
> percpu_counter_inc(sk->sk_prot->orphan_count);
> - sk->sk_state = TCP_CLOSE;
> + __tcp_set_state(sk, TCP_CLOSE);
> sock_set_flag(sk, SOCK_DEAD);
> inet_csk_destroy_sock(sk);
> }
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index bf97317..2bc7e04 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -2036,6 +2036,18 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
> }
> EXPORT_SYMBOL(tcp_recvmsg);
>
> +void __sk_state_store(struct sock *sk, int newstate)
> +{
> + trace_tcp_set_state(sk, sk->sk_state, newstate);
> + sk_state_store(sk, newstate);
> +}
> +
> +void __tcp_set_state(struct sock *sk, int state)
> +{
> + trace_tcp_set_state(sk, sk->sk_state, state);
> + sk->sk_state = state;
> +}
> +
> void tcp_set_state(struct sock *sk, int state)
> {
> int oldstate = sk->sk_state;
> --
> 1.8.3.1
>

+ Brendan