sched/fair: Introduce {en,de}queue_load_avg()

Analogous to the existing {en,de}queue_runnable_load_avg() add helpers
for {en,de}queue_load_avg(). More users will follow.

Includes some code movement to avoid fwd declarations.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -2692,6 +2692,90 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	cfs_rq->nr_running--;
 }
 
+/*
+ * Signed add and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define add_positive(_ptr, _val) do {                           \
+	typeof(_ptr) ptr = (_ptr);                              \
+	typeof(_val) val = (_val);                              \
+	typeof(*ptr) res, var = READ_ONCE(*ptr);                \
+								\
+	res = var + val;                                        \
+								\
+	if (val < 0 && res > var)                               \
+		res = 0;                                        \
+								\
+	WRITE_ONCE(*ptr, res);                                  \
+} while (0)
+
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	typeof(*ptr) val = (_val);				\
+	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
+	res = var - val;					\
+	if (res > var)						\
+		res = 0;					\
+	WRITE_ONCE(*ptr, res);					\
+} while (0)
+
+#ifdef CONFIG_SMP
+/*
+ * XXX we want to get rid of this helper and use the full load resolution.
+ */
+static inline long se_weight(struct sched_entity *se)
+{
+	return scale_load_down(se->load.weight);
+}
+
+static inline void
+enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	cfs_rq->runnable_load_avg += se->avg.load_avg;
+	cfs_rq->runnable_load_sum += se_weight(se) * se->avg.load_sum;
+}
+
+static inline void
+dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	sub_positive(&cfs_rq->runnable_load_avg, se->avg.load_avg);
+	sub_positive(&cfs_rq->runnable_load_sum, se_weight(se) * se->avg.load_sum);
+}
+
+static inline void
+enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	cfs_rq->avg.load_avg += se->avg.load_avg;
+	cfs_rq->avg.load_sum += se_weight(se) * se->avg.load_sum;
+}
+
+static inline void
+dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+	sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum);
+}
+#else
+static inline void
+enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
+static inline void
+dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
+static inline void
+enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
+static inline void
+dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
+#endif
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 # ifdef CONFIG_SMP
 /*
@@ -3084,14 +3168,6 @@ ___update_load_avg(struct sched_avg *sa, unsigned long weight, struct cfs_rq *cf
 	sa->util_avg = sa->util_sum / divider;
 }
 
-/*
- * XXX we want to get rid of this helper and use the full load resolution.
- */
-static inline long se_weight(struct sched_entity *se)
-{
-	return scale_load_down(se->load.weight);
-}
-
 /*
  * sched_entity:
  *
@@ -3141,26 +3217,6 @@ __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
 	return 0;
 }
 
-/*
- * Signed add and clamp on underflow.
- *
- * Explicitly do a load-store to ensure the intermediate value never hits
- * memory. This allows lockless observations without ever seeing the negative
- * values.
- */
-#define add_positive(_ptr, _val) do {                           \
-	typeof(_ptr) ptr = (_ptr);                              \
-	typeof(_val) val = (_val);                              \
-	typeof(*ptr) res, var = READ_ONCE(*ptr);                \
-								\
-	res = var + val;                                        \
-								\
-	if (val < 0 && res > var)                               \
-		res = 0;                                        \
-								\
-	WRITE_ONCE(*ptr, res);                                  \
-} while (0)
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /**
  * update_tg_load_avg - update the tg's load avg
@@ -3405,23 +3461,6 @@ static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-/*
- * Unsigned subtract and clamp on underflow.
- *
- * Explicitly do a load-store to ensure the intermediate value never hits
- * memory. This allows lockless observations without ever seeing the negative
- * values.
- */
-#define sub_positive(_ptr, _val) do {				\
-	typeof(_ptr) ptr = (_ptr);				\
-	typeof(*ptr) val = (_val);				\
-	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
-	res = var - val;					\
-	if (res > var)						\
-		res = 0;					\
-	WRITE_ONCE(*ptr, res);					\
-} while (0)
-
 /**
  * update_cfs_rq_load_avg - update the cfs_rq's load/util averages
  * @now: current time, as per cfs_rq_clock_task()
@@ -3484,8 +3523,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	se->avg.last_update_time = cfs_rq->avg.last_update_time;
-	cfs_rq->avg.load_avg += se->avg.load_avg;
+	enqueue_load_avg(cfs_rq, se);
-	cfs_rq->avg.load_sum += se_weight(se) * se->avg.load_sum;
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;
 	set_tg_cfs_propagate(cfs_rq);
@@ -3503,9 +3541,7 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
  */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-
+	dequeue_load_avg(cfs_rq, se);
-	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
-	sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
 	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
 	set_tg_cfs_propagate(cfs_rq);
@@ -3547,22 +3583,6 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 		update_tg_load_avg(cfs_rq, 0);
 }
 
-/* Add the load generated by se into cfs_rq's load average */
-static inline void
-enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	cfs_rq->runnable_load_avg += se->avg.load_avg;
-	cfs_rq->runnable_load_sum += se_weight(se) * se->avg.load_sum;
-}
-
-/* Remove the runnable load generated by se from cfs_rq's runnable load average */
-static inline void
-dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	sub_positive(&cfs_rq->runnable_load_avg, se->avg.load_avg);
-	sub_positive(&cfs_rq->runnable_load_sum, se_weight(se) * se->avg.load_sum);
-}
-
 #ifndef CONFIG_64BIT
 static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
 {
@@ -3649,10 +3669,6 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	cfs_rq_util_change(cfs_rq);
 }
 
-static inline void
-enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
-static inline void
-dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void remove_entity_load_avg(struct sched_entity *se) {}
 
 static inline void