sched: Add a tracepoint to track rq->nr_running

Add a bare tracepoint trace_sched_update_nr_running_tp which tracks
->nr_running CPU's rq. This is used to accurately trace this data and
provide a visualization of scheduler imbalances in, for example, the
form of a heat map.  The tracepoint is accessed by loading an external
kernel module. An example module (forked from Qais' module and including
the pelt related tracepoints) can be found at:

  https://github.com/auldp/tracepoints-helpers.git

A script to turn the trace-cmd report output into a heatmap plot can be
found at:

  https://github.com/jirvoz/plot-nr-running

The tracepoints are added to add_nr_running() and sub_nr_running() which
are in kernel/sched/sched.h. In order to avoid CREATE_TRACE_POINTS in
the header a wrapper call is used and the trace/events/sched.h include
is moved before sched.h in kernel/sched/core.

Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200629192303.GC120228@lorien.usersys.redhat.com
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4cf30e4..ff05195 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,6 +6,10 @@
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+
 #include "sched.h"
 
 #include <linux/nospec.h>
@@ -23,9 +27,6 @@
 #include "pelt.h"
 #include "smp.h"
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
-
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
  * associated with them) to allow external modules to probe them.
@@ -38,6 +39,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -8195,4 +8197,7 @@ const u32 sched_prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-#undef CREATE_TRACE_POINTS
+void call_trace_sched_update_nr_running(struct rq *rq, int count)
+{
+        trace_sched_update_nr_running_tp(rq, count);
+}