On Thu, Nov 09, 2017 at 02:01:38PM +0800, Yafang Shao wrote: > With this newly introduced TRACE_EVENT, it will be very easy to minotor > TCP/IPv4 state transition. > > A new TRACE_SYSTEM named tcp is added, in which we can trace other TCP > event as well. > > Two helpers are added, > static inline void __tcp_set_state(struct sock *sk, int state) > static inline void __sk_state_store(struct sock *sk, int newstate) > > When do TCP/IPv4 state transition, we should use these two helpers or > use tcp_set_state() instead of assign a value to sk_state directly. > > Signed-off-by: Yafang Shao <laoar.s...@gmail.com>
when you submit a patch pls make it clear which tree this patch is targeting. In this case it should have been net-next, but the patch clearly conflicts with it. Make sure to rebase. > +/* > + * To trace TCP state transition. > + */ > +static inline void __tcp_set_state(struct sock *sk, int state) > +{ > + trace_tcp_set_state(sk, sk->sk_state, state); > + sk->sk_state = state; > +} > + > +static inline 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_done(struct sock *sk); > > int tcp_abort(struct sock *sk, int err); > diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h > new file mode 100644 > index 0000000..abf65af > --- /dev/null > +++ b/include/trace/events/tcp.h > @@ -0,0 +1,58 @@ > +#undef TRACE_SYSTEM > +#define TRACE_SYSTEM tcp > + > +#if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ) > +#define _TRACE_TCP_H > + > +#include <linux/tracepoint.h> > +#include <net/sock.h> > +#include <net/inet_timewait_sock.h> > +#include <net/request_sock.h> > +#include <net/inet_sock.h> > +#include <net/tcp_states.h> > + > +TRACE_EVENT(tcp_set_state, > + TP_PROTO(struct sock *sk, int oldstate, int newstate), > + TP_ARGS(sk, oldstate, newstate), > + > + TP_STRUCT__entry( > + __field(__be32, dst) > + __field(__be32, src) > + __field(__u16, dport) > + __field(__u16, sport) > + __field(int, oldstate) > + __field(int, newstate) > + ), > + > + TP_fast_assign( > + if (oldstate == TCP_TIME_WAIT) { > + __entry->dst = inet_twsk(sk)->tw_daddr; > + __entry->src = inet_twsk(sk)->tw_rcv_saddr; > + __entry->dport = ntohs(inet_twsk(sk)->tw_dport); > + __entry->sport = ntohs(inet_twsk(sk)->tw_sport); > + } else if (oldstate == TCP_NEW_SYN_RECV) { > + __entry->dst = inet_rsk(inet_reqsk(sk))->ir_rmt_addr; > + __entry->src = inet_rsk(inet_reqsk(sk))->ir_loc_addr; > + __entry->dport = > + ntohs(inet_rsk(inet_reqsk(sk))->ir_rmt_port); > + __entry->sport = inet_rsk(inet_reqsk(sk))->ir_num; > + } else { > + __entry->dst = inet_sk(sk)->inet_daddr; > + __entry->src = inet_sk(sk)->inet_rcv_saddr; > + __entry->dport = ntohs(inet_sk(sk)->inet_dport); > + __entry->sport = ntohs(inet_sk(sk)->inet_sport); > + } > + > + __entry->oldstate = oldstate; > + __entry->newstate = newstate; > + ), > + > + TP_printk("%08X:%04X %08X:%04X, %02x %02x", > + __entry->src, __entry->sport, __entry->dst, __entry->dport, > + __entry->oldstate, __entry->newstate) direct %x of state is not allowed. This has to use show_tcp_state_name() like it's done in trace_tcp_set_state Also I'm missing the reason to introduce another tracepoint that looks just like trace_tcp_set_state.