tracing: new format for specialized trace points

Impact: clean up and enhancement

The TRACE_EVENT_FORMAT macro looks quite ugly and is limited in its
ability to save data as well as to print the record out. Working with
Ingo Molnar, we came up with a new format that is much more pleasing to
the eye of C developers. This new macro is more C style than the old
macro, and is more obvious to what it does.

Here's the example. The only updated macro in this patch is the
sched_switch trace point.

The old method looked like this:

 TRACE_EVENT_FORMAT(sched_switch,
        TP_PROTO(struct rq *rq, struct task_struct *prev,
                struct task_struct *next),
        TP_ARGS(rq, prev, next),
        TP_FMT("task %s:%d ==> %s:%d",
              prev->comm, prev->pid, next->comm, next->pid),
        TRACE_STRUCT(
                TRACE_FIELD(pid_t, prev_pid, prev->pid)
                TRACE_FIELD(int, prev_prio, prev->prio)
                TRACE_FIELD_SPECIAL(char next_comm[TASK_COMM_LEN],
                                    next_comm,
                                    TP_CMD(memcpy(TRACE_ENTRY->next_comm,
                                                 next->comm,
                                                 TASK_COMM_LEN)))
                TRACE_FIELD(pid_t, next_pid, next->pid)
                TRACE_FIELD(int, next_prio, next->prio)
        ),
        TP_RAW_FMT("prev %d:%d ==> next %s:%d:%d")
        );

The above method is hard to read and requires two format fields.

The new method:

 /*
  * Tracepoint for task switches, performed by the scheduler:
  *
  * (NOTE: the 'rq' argument is not used by generic trace events,
  *        but used by the latency tracer plugin. )
  */
 TRACE_EVENT(sched_switch,

	TP_PROTO(struct rq *rq, struct task_struct *prev,
		 struct task_struct *next),

	TP_ARGS(rq, prev, next),

	TP_STRUCT__entry(
		__array(	char,	prev_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	prev_pid			)
		__field(	int,	prev_prio			)
		__array(	char,	next_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	next_pid			)
		__field(	int,	next_prio			)
	),

	TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
		__entry->next_comm, __entry->next_pid, __entry->next_prio),

	TP_fast_assign(
		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
		__entry->prev_pid	= prev->pid;
		__entry->prev_prio	= prev->prio;
		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
		__entry->next_pid	= next->pid;
		__entry->next_prio	= next->prio;
	)
 );

This macro is called TRACE_EVENT, it is broken up into 5 parts:

 TP_PROTO:        the proto type of the trace point
 TP_ARGS:         the arguments of the trace point
 TP_STRUCT_entry: the structure layout of the entry in the ring buffer
 TP_printk:       the printk format
 TP_fast_assign:  the method used to write the entry into the ring buffer

The structure is the definition of how the event will be saved in the
ring buffer. The printk is used by the internal tracing in case of
an oops, and the kernel needs to print out the format of the record
to the console. This the TP_printk gives a means to show the records
in a human readable format. It is also used to print out the data
from the trace file.

The TP_fast_assign is executed directly. It is basically like a C function,
where the __entry is the handle to the record.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>

2 files changed, 35 insertions, 16 deletions

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 3bcc3e17144..6b4f1bb3701 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -160,4 +160,7 @@ static inline void tracepoint_synchronize_unregister(void)
 #define TRACE_EVENT_FORMAT(name, proto, args, fmt, struct, tpfmt)	\
 	TRACE_FORMAT(name, PARAMS(proto), PARAMS(args), PARAMS(fmt))
 
+#define TRACE_EVENT(name, proto, args, struct, print, assign)	\
+	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+
 #endif
diff --git a/include/trace/sched_event_types.h b/include/trace/sched_event_types.h
index 71b14828a95..aa77fb75403 100644
--- a/include/trace/sched_event_types.h
+++ b/include/trace/sched_event_types.h
@@ -62,25 +62,41 @@ TRACE_EVENT_FORMAT(sched_wakeup_new,
 	TP_RAW_FMT("task %d success=%d")
 	);
 
-TRACE_EVENT_FORMAT(sched_switch,
+/*
+ * Tracepoint for task switches, performed by the scheduler:
+ *
+ * (NOTE: the 'rq' argument is not used by generic trace events,
+ *        but used by the latency tracer plugin. )
+ */
+TRACE_EVENT(sched_switch,
+
 	TP_PROTO(struct rq *rq, struct task_struct *prev,
-		struct task_struct *next),
+		 struct task_struct *next),
+
 	TP_ARGS(rq, prev, next),
-	TP_FMT("task %s:%d ==> %s:%d",
-	      prev->comm, prev->pid, next->comm, next->pid),
-	TRACE_STRUCT(
-		TRACE_FIELD(pid_t, prev_pid, prev->pid)
-		TRACE_FIELD(int, prev_prio, prev->prio)
-		TRACE_FIELD_SPECIAL(char next_comm[TASK_COMM_LEN],
-				    next_comm,
-				    TP_CMD(memcpy(TRACE_ENTRY->next_comm,
-						 next->comm,
-						 TASK_COMM_LEN)))
-		TRACE_FIELD(pid_t, next_pid, next->pid)
-		TRACE_FIELD(int, next_prio, next->prio)
+
+	TP_STRUCT__entry(
+		__array(	char,	prev_comm,	TASK_COMM_LEN	)
+		__field(	pid_t,	prev_pid			)
+		__field(	int,	prev_prio			)
+		__array(	char,	next_comm,	TASK_COMM_LEN	)
+		__field(	pid_t,	next_pid			)
+		__field(	int,	next_prio			)
 	),
-	TP_RAW_FMT("prev %d:%d ==> next %s:%d:%d")
-	);
+
+	TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
+		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
+		__entry->next_comm, __entry->next_pid, __entry->next_prio),
+
+	TP_fast_assign(
+		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
+		__entry->prev_pid	= prev->pid;
+		__entry->prev_prio	= prev->prio;
+		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
+		__entry->next_pid	= next->pid;
+		__entry->next_prio	= next->prio;
+	)
+);
 
 TRACE_EVENT_FORMAT(sched_migrate_task,
 	TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu),