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

include/linux/sched.h

@@ -2044,6 +2044,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
 const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
 
 int sched_trace_rq_cpu(struct rq *rq);
+int sched_trace_rq_nr_running(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
 

include/trace/events/sched.h

@@ -642,6 +642,10 @@ DECLARE_TRACE(sched_util_est_se_tp,
 	TP_PROTO(struct sched_entity *se),
 	TP_ARGS(se));
 
+DECLARE_TRACE(sched_update_nr_running_tp,
+	TP_PROTO(struct rq *rq, int change),
+	TP_ARGS(rq, change));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */

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);
+}

kernel/sched/fair.c

@@ -22,8 +22,6 @@
  */
 #include "sched.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Targeted preemption latency for CPU-bound tasks:
  *
@@ -11296,3 +11294,9 @@ const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
 #endif
 }
 EXPORT_SYMBOL_GPL(sched_trace_rd_span);
+
+int sched_trace_rq_nr_running(struct rq *rq)
+{
+        return rq ? rq->nr_running : -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running);

kernel/sched/pelt.c

@@ -28,8 +28,6 @@
 #include "sched.h"
 #include "pelt.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)

kernel/sched/sched.h

@@ -76,6 +76,8 @@
 #include "cpupri.h"
 #include "cpudeadline.h"
 
+#include <trace/events/sched.h>
+
 #ifdef CONFIG_SCHED_DEBUG
 # define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
@@ -97,6 +99,7 @@ extern atomic_long_t calc_load_tasks;
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
+extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
@@ -1973,6 +1976,9 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 	unsigned prev_nr = rq->nr_running;
 
 	rq->nr_running = prev_nr + count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
 
 #ifdef CONFIG_SMP
 	if (prev_nr < 2 && rq->nr_running >= 2) {
@@ -1987,6 +1993,10 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
 	rq->nr_running -= count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
+
 	/* Check if we still need preemption */
 	sched_update_tick_dependency(rq);
 }