ANDROID: sched/events: Introduce cfs_rq load tracking trace event

The following trace event keys are mapped to:

 (1) load     : cfs_rq->avg.load_avg

 (2) rbl_load : cfs_rq->avg.runnable_load_avg

 (2) util     : cfs_rq->avg.util_avg

To let this trace event work for configurations w/ and w/o group
scheduling support for cfs (CONFIG_FAIR_GROUP_SCHED) the following
special handling is necessary for a non-existent key=value pair:

 path = "(null)" : In case of !CONFIG_FAIR_GROUP_SCHED.

The following list shows examples of the key=value pairs in different
configurations for:

 (1) a root task_group:

     cpu=4 path=/ load=6 rbl_load=6 util=331

 (2) a task_group:

     cpu=1 path=/tg1/tg11/tg111 load=538 rbl_load=538 util=522

 (3) an autogroup:

     cpu=3 path=/autogroup-18 load=997 rbl_load=997 util=517

 (4) w/o CONFIG_FAIR_GROUP_SCHED:

     cpu=0 path=(null) load=314 rbl_load=314 util=289

The trace event is only defined for CONFIG_SMP.

The helper function __trace_sched_path() can be used to get the length
parameter of the dynamic array (path == NULL) and to copy the path into
it (path != NULL).

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
[ Fixed issues related to the new pelt.c file ]
Signed-off-by: Quentin Perret <quentin.perret@arm.com>
Change-Id: I1107044c52b74ecb3df69f3a45c1e530f0e59b1b

include/trace/events/sched.h

@@ -572,6 +572,72 @@ TRACE_EVENT(sched_wake_idle_without_ipi,
 
 	TP_printk("cpu=%d", __entry->cpu)
 );
+
+#ifdef CONFIG_SMP
+#ifdef CREATE_TRACE_POINTS
+static inline
+int __trace_sched_cpu(struct cfs_rq *cfs_rq)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	struct rq *rq = cfs_rq->rq;
+#else
+	struct rq *rq = container_of(cfs_rq, struct rq, cfs);
+#endif
+	return cpu_of(rq);
+}
+
+static inline
+int __trace_sched_path(struct cfs_rq *cfs_rq, char *path, int len)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	int l = path ? len : 0;
+
+	if (task_group_is_autogroup(cfs_rq->tg))
+		return autogroup_path(cfs_rq->tg, path, l) + 1;
+	else
+		return cgroup_path(cfs_rq->tg->css.cgroup, path, l) + 1;
+#else
+	if (path)
+		strcpy(path, "(null)");
+
+	return strlen("(null)");
+#endif
+}
+
+#endif /* CREATE_TRACE_POINTS */
+
+/*
+ * Tracepoint for cfs_rq load tracking:
+ */
+TRACE_EVENT(sched_load_cfs_rq,
+
+	TP_PROTO(struct cfs_rq *cfs_rq),
+
+	TP_ARGS(cfs_rq),
+
+	TP_STRUCT__entry(
+		__field(	int,		cpu			)
+		__dynamic_array(char,		path,
+				__trace_sched_path(cfs_rq, NULL, 0)	)
+		__field(	unsigned long,	load			)
+		__field(	unsigned long,	rbl_load		)
+		__field(	unsigned long,	util			)
+	),
+
+	TP_fast_assign(
+		__entry->cpu		= __trace_sched_cpu(cfs_rq);
+		__trace_sched_path(cfs_rq, __get_dynamic_array(path),
+				   __get_dynamic_array_len(path));
+		__entry->load		= cfs_rq->avg.load_avg;
+		__entry->rbl_load 	= cfs_rq->avg.runnable_load_avg;
+		__entry->util		= cfs_rq->avg.util_avg;
+	),
+
+	TP_printk("cpu=%d path=%s load=%lu rbl_load=%lu util=%lu",
+		  __entry->cpu, __get_str(path), __entry->load,
+		  __entry->rbl_load,__entry->util)
+);
+#endif /* CONFIG_SMP */
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */

kernel/sched/fair.c

@@ -3338,6 +3338,8 @@ static inline int propagate_entity_load_avg(struct sched_entity *se)
 	update_tg_cfs_util(cfs_rq, se, gcfs_rq);
 	update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
 
+	trace_sched_load_cfs_rq(cfs_rq);
+
 	return 1;
 }
 
@@ -3490,6 +3492,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
 
 	cfs_rq_util_change(cfs_rq, flags);
+
+	trace_sched_load_cfs_rq(cfs_rq);
 }
 
 /**
@@ -3509,6 +3513,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
 
 	cfs_rq_util_change(cfs_rq, 0);
+
+	trace_sched_load_cfs_rq(cfs_rq);
 }
 
 /*

kernel/sched/pelt.c

@@ -29,6 +29,8 @@
 #include "sched-pelt.h"
 #include "pelt.h"
 
+#include <trace/events/sched.h>
+
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
@@ -304,6 +306,9 @@ int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
 				cfs_rq->curr != NULL)) {
 
 		___update_load_avg(&cfs_rq->avg, 1, 1);
+
+		trace_sched_load_cfs_rq(cfs_rq);
+
 		return 1;
 	}