1 files changed, 113 insertions, 3 deletions

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 757005458366..d35a7ee7611f 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -31,8 +31,8 @@ struct tracepoint {
                                          * Keep in sync with vmlinux.lds.h.
                                          */
 
-#define TPPROTO(args...)        args
-#define TPARGS(args...)         args
+#define TP_PROTO(args...)       args
+#define TP_ARGS(args...)                args
 
 #ifdef CONFIG_TRACEPOINTS
 
@@ -65,7 +65,7 @@ struct tracepoint {
         {                                                               \
                 if (unlikely(__tracepoint_##name.state))                \
                         __DO_TRACE(&__tracepoint_##name,                \
-                                TPPROTO(proto), TPARGS(args));          \
+                                TP_PROTO(proto), TP_ARGS(args));        \
         }                                                               \
         static inline int register_trace_##name(void (*probe)(proto))   \
         {                                                               \
@@ -153,4 +153,114 @@ static inline void tracepoint_synchronize_unregister(void)
         synchronize_sched();
 }
 
+#define PARAMS(args...) args
+#define TRACE_FORMAT(name, proto, args, fmt)            \
+        DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+
+
+/*
+ * For use with the TRACE_EVENT macro:
+ *
+ * We define a tracepoint, its arguments, its printk format
+ * and its 'fast binay record' layout.
+ *
+ * Firstly, name your tracepoint via TRACE_EVENT(name : the
+ * 'subsystem_event' notation is fine.
+ *
+ * Think about this whole construct as the
+ * 'trace_sched_switch() function' from now on.
+ *
+ *
+ *  TRACE_EVENT(sched_switch,
+ *
+ *      *
+ *      * A function has a regular function arguments
+ *      * prototype, declare it via TP_PROTO():
+ *      *
+ *
+ *      TP_PROTO(struct rq *rq, struct task_struct *prev,
+ *               struct task_struct *next),
+ *
+ *      *
+ *      * Define the call signature of the 'function'.
+ *      * (Design sidenote: we use this instead of a
+ *      *  TP_PROTO1/TP_PROTO2/TP_PROTO3 ugliness.)
+ *      *
+ *
+ *      TP_ARGS(rq, prev, next),
+ *
+ *      *
+ *      * Fast binary tracing: define the trace record via
+ *      * TP_STRUCT__entry(). You can think about it like a
+ *      * regular C structure local variable definition.
+ *      *
+ *      * This is how the trace record is structured and will
+ *      * be saved into the ring buffer. These are the fields
+ *      * that will be exposed to user-space in
+ *      * /debug/tracing/events/<*>/format.
+ *      *
+ *      * The declared 'local variable' is called '__entry'
+ *      *
+ *      * __field(pid_t, prev_prid) is equivalent to a standard declariton:
+ *      *
+ *      *       pid_t   prev_pid;
+ *      *
+ *      * __array(char, prev_comm, TASK_COMM_LEN) is equivalent to:
+ *      *
+ *      *       char    prev_comm[TASK_COMM_LEN];
+ *      *
+ *
+ *      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                       )
+ *      ),
+ *
+ *      *
+ *      * Assign the entry into the trace record, by embedding
+ *      * a full C statement block into TP_fast_assign(). You
+ *      * can refer to the trace record as '__entry' -
+ *      * otherwise you can put arbitrary C code in here.
+ *      *
+ *      * Note: this C code will execute every time a trace event
+ *      * happens, on an active tracepoint.
+ *      *
+ *
+ *      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;
+ *      )
+ *
+ *      *
+ *      * Formatted output of a trace record via TP_printk().
+ *      * This is how the tracepoint will appear under ftrace
+ *      * plugins that make use of this tracepoint.
+ *      *
+ *      * (raw-binary tracing wont actually perform this step.)
+ *      *
+ *
+ *      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),
+ *
+ * );
+ *
+ * This macro construct is thus used for the regular printk format
+ * tracing setup, it is used to construct a function pointer based
+ * tracepoint callback (this is used by programmatic plugins and
+ * can also by used by generic instrumentation like SystemTap), and
+ * it is also used to expose a structured trace record in
+ * /debug/tracing/events/.
+ */
+
+#define TRACE_EVENT(name, proto, args, struct, assign, print)   \
+        DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+
 #endif