sched/events: Introduce sched_entity load tracking trace event

The following trace event keys are mapped to:

 (1) load     : se->avg.load_avg

 (2) rbl_load : se->avg.runnable_load_avg

 (3) util     : se->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 non-existent key=value pairs:

 path = "(null)" : In case of !CONFIG_FAIR_GROUP_SCHED or the
                   sched_entity represents a task.

 comm = "(null)" : In case sched_entity represents a task_group.

 pid = -1        : In case sched_entity represents a task_group.

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

 (1) a task:

     cpu=0 path=(null) comm=sshd pid=2206 load=102 rbl_load=102  util=102

 (2) a taskgroup:

     cpu=1 path=/tg1/tg11/tg111 comm=(null) pid=-1 load=882 rbl_load=882 util=510

 (3) an autogroup:

     cpu=0 path=/autogroup-13 comm=(null) pid=-1 load=49 rbl_load=49 util=48

 (4) w/o CONFIG_FAIR_GROUP_SCHED:

     cpu=0 path=(null) comm=sshd pid=2211 load=301 rbl_load=301 util=265

The trace event is only defined for CONFIG_SMP.

The helper functions __trace_sched_cpu(), __trace_sched_path() and
__trace_sched_id() are extended to deal with sched_entities as well.

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>

2 files changed, 65 insertions, 9 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index f1a062ca1239..9342a91f3e65 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -574,14 +574,15 @@ TRACE_EVENT(sched_wake_idle_without_ipi,
 #ifdef CONFIG_SMP
 #ifdef CREATE_TRACE_POINTS
 static inline
-int __trace_sched_cpu(struct cfs_rq *cfs_rq)
+int __trace_sched_cpu(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	struct rq *rq = cfs_rq->rq;
+	struct rq *rq = cfs_rq ? cfs_rq->rq : NULL;
 #else
-	struct rq *rq = container_of(cfs_rq, struct rq, cfs);
+	struct rq *rq = cfs_rq ? container_of(cfs_rq, struct rq, cfs) : NULL;
 #endif
-	return cpu_of(rq);
+	return rq ? cpu_of(rq)
+		  : task_cpu((container_of(se, struct task_struct, se)));
 }
 
 static inline
@@ -590,18 +591,26 @@ 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))
+	if (cfs_rq && task_group_is_autogroup(cfs_rq->tg))
 		return autogroup_path(cfs_rq->tg, path, l) + 1;
-	else
+	else if (cfs_rq && cfs_rq->tg->css.cgroup)
 		return cgroup_path(cfs_rq->tg->css.cgroup, path, l) + 1;
-#else
+#endif
 	if (path)
 		strcpy(path, "(null)");
 
 	return strlen("(null)");
-#endif
 }
 
+static inline
+struct cfs_rq *__trace_sched_group_cfs_rq(struct sched_entity *se)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	return se->my_q;
+#else
+	return NULL;
+#endif
+}
 #endif /* CREATE_TRACE_POINTS */
 
 /*
@@ -623,7 +632,7 @@ TRACE_EVENT(sched_load_cfs_rq,
 	),
 
 	TP_fast_assign(
-		__entry->cpu		= __trace_sched_cpu(cfs_rq);
+		__entry->cpu		= __trace_sched_cpu(cfs_rq, NULL);
 		__trace_sched_path(cfs_rq, __get_dynamic_array(path),
 				   __get_dynamic_array_len(path));
 		__entry->load		= cfs_rq->avg.load_avg;
@@ -635,6 +644,46 @@ TRACE_EVENT(sched_load_cfs_rq,
 		  __entry->cpu, __get_str(path), __entry->load,
 		  __entry->rbl_load,__entry->util)
 );
+
+/*
+ * Tracepoint for sched_entity load tracking:
+ */
+TRACE_EVENT(sched_load_se,
+
+	TP_PROTO(struct sched_entity *se),
+
+	TP_ARGS(se),
+
+	TP_STRUCT__entry(
+		__field(	int,		cpu			      )
+		__dynamic_array(char,		path,
+		  __trace_sched_path(__trace_sched_group_cfs_rq(se), NULL, 0) )
+		__array(	char,		comm,	TASK_COMM_LEN	      )
+		__field(	pid_t,		pid			      )
+		__field(	unsigned long,	load			      )
+		__field(	unsigned long,	rbl_load		      )
+		__field(	unsigned long,	util			      )
+	),
+
+	TP_fast_assign(
+		struct cfs_rq *gcfs_rq = __trace_sched_group_cfs_rq(se);
+		struct task_struct *p = gcfs_rq ? NULL
+				    : container_of(se, struct task_struct, se);
+
+		__entry->cpu		= __trace_sched_cpu(gcfs_rq, se);
+		__trace_sched_path(gcfs_rq, __get_dynamic_array(path),
+				   __get_dynamic_array_len(path));
+		memcpy(__entry->comm, p ? p->comm : "(null)", TASK_COMM_LEN);
+		__entry->pid = p ? p->pid : -1;
+		__entry->load = se->avg.load_avg;
+		__entry->rbl_load = se->avg.runnable_load_avg;
+		__entry->util = se->avg.util_avg;
+	),
+
+	TP_printk("cpu=%d path=%s comm=%s pid=%d load=%lu rbl_load=%lu util=%lu",
+		  __entry->cpu, __get_str(path), __entry->comm, __entry->pid,
+		  __entry->load, __entry->rbl_load, __entry->util)
+);
 #endif /* CONFIG_SMP */
 #endif /* _TRACE_SCHED_H */
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 44e15e331048..e17aa1efeb0a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3284,6 +3284,9 @@ __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
 
 	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
 		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+
+		trace_sched_load_se(se);
+
 		return 1;
 	}
 
@@ -3300,6 +3303,9 @@ __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entit
 				cfs_rq->curr == se)) {
 
 		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+
+		trace_sched_load_se(se);
+
 		return 1;
 	}
 
@@ -3552,6 +3558,7 @@ static inline int propagate_entity_load_avg(struct sched_entity *se)
 	update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
 
 	trace_sched_load_cfs_rq(cfs_rq);
+	trace_sched_load_se(se);
 
 	return 1;
 }