perf_counter, sched: Add sched_stat_runtime tracepoint

This allows more precise tracking of how the scheduler accounts
(and acts upon) a task having spent N nanoseconds of CPU time.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

include/trace/events/sched.h

@@ -379,6 +379,39 @@ TRACE_EVENT(sched_stat_wait,
 			(unsigned long long)__entry->delay)
 );
 
+/*
+ * Tracepoint for accounting runtime (time the task is executing
+ * on a CPU).
+ */
+TRACE_EVENT(sched_stat_runtime,
+
+	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
+
+	TP_ARGS(tsk, runtime, vruntime),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( u64,	runtime			)
+		__field( u64,	vruntime			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		= tsk->pid;
+		__entry->runtime	= runtime;
+		__entry->vruntime	= vruntime;
+	)
+	TP_perf_assign(
+		__perf_count(runtime);
+	),
+
+	TP_printk("task: %s:%d runtime: %Lu [ns], vruntime: %Lu [ns]",
+			__entry->comm, __entry->pid,
+			(unsigned long long)__entry->runtime,
+			(unsigned long long)__entry->vruntime)
+);
+
 /*
  * Tracepoint for accounting sleep time (time the task is not runnable,
  * including iowait, see below).

kernel/sched_fair.c

@@ -513,6 +513,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	if (entity_is_task(curr)) {
 		struct task_struct *curtask = task_of(curr);
 
+		trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
 		cpuacct_charge(curtask, delta_exec);
 		account_group_exec_runtime(curtask, delta_exec);
 	}