Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/core

Pull perf optimizations from Steve Rostedt.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 28 insertions, 27 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index e5586caff67a..2e7d9947a10d 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -57,7 +57,7 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 
 	TP_PROTO(struct task_struct *p, int success),
 
-	TP_ARGS(p, success),
+	TP_ARGS(__perf_task(p), success),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -73,9 +73,6 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 		__entry->prio		= p->prio;
 		__entry->success	= success;
 		__entry->target_cpu	= task_cpu(p);
-	)
-	TP_perf_assign(
-		__perf_task(p);
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
@@ -313,7 +310,7 @@ DECLARE_EVENT_CLASS(sched_stat_template,
 
 	TP_PROTO(struct task_struct *tsk, u64 delay),
 
-	TP_ARGS(tsk, delay),
+	TP_ARGS(__perf_task(tsk), __perf_count(delay)),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
@@ -325,10 +322,6 @@ DECLARE_EVENT_CLASS(sched_stat_template,
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid	= tsk->pid;
 		__entry->delay	= delay;
-	)
-	TP_perf_assign(
-		__perf_count(delay);
-		__perf_task(tsk);
 	),
 
 	TP_printk("comm=%s pid=%d delay=%Lu [ns]",
@@ -372,11 +365,11 @@ DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
  * Tracepoint for accounting runtime (time the task is executing
  * on a CPU).
  */
-TRACE_EVENT(sched_stat_runtime,
+DECLARE_EVENT_CLASS(sched_stat_runtime,
 
 	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
 
-	TP_ARGS(tsk, runtime, vruntime),
+	TP_ARGS(tsk, __perf_count(runtime), vruntime),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
@@ -390,9 +383,6 @@ TRACE_EVENT(sched_stat_runtime,
 		__entry->pid		= tsk->pid;
 		__entry->runtime	= runtime;
 		__entry->vruntime	= vruntime;
-	)
-	TP_perf_assign(
-		__perf_count(runtime);
 	),
 
 	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
@@ -401,6 +391,10 @@ TRACE_EVENT(sched_stat_runtime,
 			(unsigned long long)__entry->vruntime)
 );
 
+DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
+	     TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
+	     TP_ARGS(tsk, runtime, vruntime));
+
 /*
  * Tracepoint for showing priority inheritance modifying a tasks
  * priority.
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 41a6643e2136..5c7ab17cbb02 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -507,8 +507,14 @@ static inline notrace int ftrace_get_offsets_##call(			\
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
 
-#undef TP_perf_assign
-#define TP_perf_assign(args...)
+#undef __perf_addr
+#define __perf_addr(a)	(a)
+
+#undef __perf_count
+#define __perf_count(c)	(c)
+
+#undef __perf_task
+#define __perf_task(t)	(t)
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
@@ -636,16 +642,13 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 #define __get_str(field) (char *)__get_dynamic_array(field)
 
 #undef __perf_addr
-#define __perf_addr(a) __addr = (a)
+#define __perf_addr(a)	(__addr = (a))
 
 #undef __perf_count
-#define __perf_count(c) __count = (c)
+#define __perf_count(c)	(__count = (c))
 
 #undef __perf_task
-#define __perf_task(t) __task = (t)
-
-#undef TP_perf_assign
-#define TP_perf_assign(args...) args
+#define __perf_task(t)	(__task = (t))
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
@@ -663,15 +666,20 @@ perf_trace_##call(void *__data, proto)					\
 	int __data_size;						\
 	int rctx;							\
 									\
-	perf_fetch_caller_regs(&__regs);				\
-									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+									\
+	head = this_cpu_ptr(event_call->perf_events);			\
+	if (__builtin_constant_p(!__task) && !__task &&			\
+				hlist_empty(head))			\
+		return;							\
+									\
 	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(	\
-		__entry_size, event_call->event.type, &__regs, &rctx);	\
+	perf_fetch_caller_regs(&__regs);				\
+	entry = perf_trace_buf_prepare(__entry_size,			\
+			event_call->event.type, &__regs, &rctx);	\
 	if (!entry)							\
 		return;							\
 									\
@@ -679,7 +687,6 @@ perf_trace_##call(void *__data, proto)					\
 									\
 	{ assign; }							\
 									\
-	head = this_cpu_ptr(event_call->perf_events);			\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
 		__count, &__regs, head, __task);			\
 }