Commit b2597f78 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'replace-tcp_set_state-tracepoint-with-inet_sock_set_state' 

Yafang Shao says:

====================
replace tcp_set_state tracepoint with inet_sock_set_state

According to the discussion in the mail thread
https://patchwork.kernel.org/patch/10099243/

,
tcp_set_state tracepoint is renamed to inet_sock_set_state tracepoint and is
moved to include/trace/events/sock.h.

With this new tracepoint, we can trace AF_INET/AF_INET6 sock state transitions.
As there's only one single tracepoint for inet, so I didn't create a new trace
file named trace/events/inet_sock.h, and just place it in
include/trace/events/sock.h

Currently TCP/DCCP/SCTP state transitions are traced with this tracepoint.

- Why not more protocol ?
If we really think that anonter protocol should be traced, I will modify the
code to trace it.
I just want to make the code easy and not output useless information.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 9ee1942c cbabf463

include/net/inet_sock.h

+25 −0
Original line number Diff line number Diff line
@@ -291,6 +291,31 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, 


int inet_sk_rebuild_header(struct sock *sk);



/**

 * inet_sk_state_load - read sk->sk_state for lockless contexts

 * @sk: socket pointer

 *

 * Paired with inet_sk_state_store(). Used in places we don't hold socket lock:

 * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ...

 */

static inline int inet_sk_state_load(const struct sock *sk)

{

	/* state change might impact lockless readers. */

	return smp_load_acquire(&sk->sk_state);

}



/**

 * inet_sk_state_store - update sk->sk_state

 * @sk: socket pointer

 * @newstate: new state

 *

 * Paired with inet_sk_state_load(). Should be used in contexts where

 * state change might impact lockless readers.

 */

void inet_sk_state_store(struct sock *sk, int newstate);



void inet_sk_set_state(struct sock *sk, int state);



static inline unsigned int __inet_ehashfn(const __be32 laddr,

					  const __u16 lport,

					  const __be32 faddr,

include/net/sock.h

+0 −25
Original line number Diff line number Diff line
@@ -2333,31 +2333,6 @@ static inline bool sk_listener(const struct sock *sk) 
	return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);

}



/**

 * sk_state_load - read sk->sk_state for lockless contexts

 * @sk: socket pointer

 *

 * Paired with sk_state_store(). Used in places we do not hold socket lock :

 * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ...

 */

static inline int sk_state_load(const struct sock *sk)

{

	return smp_load_acquire(&sk->sk_state);

}



/**

 * sk_state_store - update sk->sk_state

 * @sk: socket pointer

 * @newstate: new state

 *

 * Paired with sk_state_load(). Should be used in contexts where

 * state change might impact lockless readers.

 */

static inline void sk_state_store(struct sock *sk, int newstate)

{

	smp_store_release(&sk->sk_state, newstate);

}



void sock_enable_timestamp(struct sock *sk, int flag);

int sock_get_timestamp(struct sock *, struct timeval __user *);

int sock_get_timestampns(struct sock *, struct timespec __user *);

include/trace/events/sock.h

+107 −0
Original line number Diff line number Diff line
@@ -6,7 +6,50 @@ 
#define _TRACE_SOCK_H



#include <net/sock.h>

#include <net/ipv6.h>

#include <linux/tracepoint.h>

#include <linux/ipv6.h>

#include <linux/tcp.h>



/* The protocol traced by sock_set_state */

#define inet_protocol_names		\

		EM(IPPROTO_TCP)			\

		EM(IPPROTO_DCCP)		\

		EMe(IPPROTO_SCTP)



#define tcp_state_names			\

		EM(TCP_ESTABLISHED)		\

		EM(TCP_SYN_SENT)		\

		EM(TCP_SYN_RECV)		\

		EM(TCP_FIN_WAIT1)		\

		EM(TCP_FIN_WAIT2)		\

		EM(TCP_TIME_WAIT)		\

		EM(TCP_CLOSE)			\

		EM(TCP_CLOSE_WAIT)		\

		EM(TCP_LAST_ACK)		\

		EM(TCP_LISTEN)			\

		EM(TCP_CLOSING)			\

		EMe(TCP_NEW_SYN_RECV)



/* enums need to be exported to user space */

#undef EM

#undef EMe

#define EM(a)       TRACE_DEFINE_ENUM(a);

#define EMe(a)      TRACE_DEFINE_ENUM(a);



inet_protocol_names

tcp_state_names



#undef EM

#undef EMe

#define EM(a)       { a, #a },

#define EMe(a)      { a, #a }



#define show_inet_protocol_name(val)    \

	__print_symbolic(val, inet_protocol_names)



#define show_tcp_state_name(val)        \

	__print_symbolic(val, tcp_state_names)



TRACE_EVENT(sock_rcvqueue_full,
@@ -63,6 +106,70 @@ TRACE_EVENT(sock_exceed_buf_limit, 
		__entry->rmem_alloc)

);



TRACE_EVENT(inet_sock_set_state,



	TP_PROTO(const struct sock *sk, const int oldstate, const int newstate),



	TP_ARGS(sk, oldstate, newstate),



	TP_STRUCT__entry(

		__field(const void *, skaddr)

		__field(int, oldstate)

		__field(int, newstate)

		__field(__u16, sport)

		__field(__u16, dport)

		__field(__u8, protocol)

		__array(__u8, saddr, 4)

		__array(__u8, daddr, 4)

		__array(__u8, saddr_v6, 16)

		__array(__u8, daddr_v6, 16)

	),



	TP_fast_assign(

		struct inet_sock *inet = inet_sk(sk);

		struct in6_addr *pin6;

		__be32 *p32;



		__entry->skaddr = sk;

		__entry->oldstate = oldstate;

		__entry->newstate = newstate;



		__entry->protocol = sk->sk_protocol;

		__entry->sport = ntohs(inet->inet_sport);

		__entry->dport = ntohs(inet->inet_dport);



		p32 = (__be32 *) __entry->saddr;

		*p32 = inet->inet_saddr;



		p32 = (__be32 *) __entry->daddr;

		*p32 =  inet->inet_daddr;



#if IS_ENABLED(CONFIG_IPV6)

		if (sk->sk_family == AF_INET6) {

			pin6 = (struct in6_addr *)__entry->saddr_v6;

			*pin6 = sk->sk_v6_rcv_saddr;

			pin6 = (struct in6_addr *)__entry->daddr_v6;

			*pin6 = sk->sk_v6_daddr;

		} else

#endif

		{

			pin6 = (struct in6_addr *)__entry->saddr_v6;

			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);

			pin6 = (struct in6_addr *)__entry->daddr_v6;

			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);

		}

	),



	TP_printk("protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4"

			"saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s",

			show_inet_protocol_name(__entry->protocol),

			__entry->sport, __entry->dport,

			__entry->saddr, __entry->daddr,

			__entry->saddr_v6, __entry->daddr_v6,

			show_tcp_state_name(__entry->oldstate),

			show_tcp_state_name(__entry->newstate))

);



#endif /* _TRACE_SOCK_H */



/* This part must be outside protection */

include/trace/events/tcp.h

+0 −16
Original line number Diff line number Diff line
@@ -9,22 +9,6 @@ 
#include <linux/tracepoint.h>

#include <net/ipv6.h>



#define tcp_state_name(state)	{ state, #state }

#define show_tcp_state_name(val)			\

	__print_symbolic(val,				\

		tcp_state_name(TCP_ESTABLISHED),	\

		tcp_state_name(TCP_SYN_SENT),		\

		tcp_state_name(TCP_SYN_RECV),		\

		tcp_state_name(TCP_FIN_WAIT1),		\

		tcp_state_name(TCP_FIN_WAIT2),		\

		tcp_state_name(TCP_TIME_WAIT),		\

		tcp_state_name(TCP_CLOSE),		\

		tcp_state_name(TCP_CLOSE_WAIT),		\

		tcp_state_name(TCP_LAST_ACK),		\

		tcp_state_name(TCP_LISTEN),		\

		tcp_state_name(TCP_CLOSING),		\

		tcp_state_name(TCP_NEW_SYN_RECV))



/*

 * tcp event with arguments sk and skb

 *

net/dccp/proto.c

+1 −1
Original line number Diff line number Diff line
@@ -110,7 +110,7 @@ void dccp_set_state(struct sock *sk, const int state) 
	/* Change state AFTER socket is unhashed to avoid closed

	 * socket sitting in hash tables.

	 */

	sk->sk_state = state;

	inet_sk_set_state(sk, state);

}



EXPORT_SYMBOL_GPL(dccp_set_state);

CRA Git | Maintained and supported by SUSTech CRA and CCSE