From: Song Liu <songliubraving@fb.com>
To: Yafang Shao <laoar.shao@gmail.com>
CC: David Miller <davem@davemloft.net>,
        "kuznet@ms2.inr.ac.ru" <kuznet@ms2.inr.ac.ru>,
        "yoshfuji@linux-ipv6.org" <yoshfuji@linux-ipv6.org>,
        Steven Rostedt <rostedt@goodmis.org>,
        Brendan Gregg <bgregg@netflix.com>,
        "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v2 net-next] net/tcp: trace all TCP/IP state transition
 with tcp_set_state tracepoint
Thread-Topic: [PATCH v2 net-next] net/tcp: trace all TCP/IP state transition
 with tcp_set_state tracepoint
Thread-Index: AQHTa1EgP0D+iiqvPEyCFT4Hbba4i6MzeeqA
Date: Mon, 4 Dec 2017 17:49:48 +0000
Message-ID: <A7623CF4-E512-4AAB-A046-617DA66E48CE@fb.com>
References: <1512207401-3154-1-git-send-email-laoar.shao@gmail.com>
In-Reply-To: <1512207401-3154-1-git-send-email-laoar.shao@gmail.com>
Accept-Language: en-US
Content-Language: en-US
spamdiagnosticoutput: 1:99
spamdiagnosticmetadata: NSPM
Content-Type: text/plain; charset="us-ascii"
Content-ID: <4714BF005A7D0040A5279D4B5B837915@namprd15.prod.outlook.com>
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: e20b30a0-77fe-492e-70a0-08d53b3f69ec
X-MS-Exchange-CrossTenant-originalarrivaltime: 04 Dec 2017 17:49:48.6687
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 8ae927fe-1255-47a7-a2af-5f3a069daaa2
X-MS-Exchange-Transport-CrossTenantHeadersStamped: CY4PR15MB1511
X-OriginatorOrg: fb.com
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2017-12-04_06:,,
 signatures=0
X-Proofpoint-Spam-Reason: safe
X-FB-Internal: Safe
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Transfer-Encoding: 8bit
X-MIME-Autoconverted: from quoted-printable to 8bit by nfs id vB4HoYMx008906
Content-Length: 3677
Lines: 110


> On Dec 2, 2017, at 1:36 AM, Yafang Shao <laoar.shao@gmail.com> 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@gmail.com>
> 
> ---
> v2: test
> ---
> 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
> 

Asked-by: Song Liu <songliubraving@fb.com>