[PATCH] sched/core: Optimize pick_next_task().

[Tao Zhou]

---
 kernel/sched/core.c  | 113 ++++++++++++++++++++++---------------------
 kernel/sched/sched.h |   1 +
 2 files changed, 58 insertions(+), 56 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 20ffcc044134..212647ed2598 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5355,7 +5355,7 @@ static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
 static struct task_struct *
 pick_task(struct rq *rq, const struct sched_class *class, struct task_struct *max, bool in_fi)
 {
-	struct task_struct *class_pick, *cookie_pick;
+	struct task_struct *class_pick;
 	unsigned long cookie = rq->core->core_cookie;
 
 	class_pick = class->pick_task(rq);
@@ -5370,30 +5370,40 @@ pick_task(struct rq *rq, const struct sched_class *class, struct task_struct *ma
 		if (max && class_pick->core_cookie &&
 		    prio_less(class_pick, max, in_fi))
 			return idle_sched_class.pick_task(rq);
-
-		return class_pick;
 	}
 
-	/*
-	 * If class_pick is idle or matches cookie, return early.
-	 */
-	if (cookie_equals(class_pick, cookie))
-		return class_pick;
+	return class_pick;
+}
 
-	cookie_pick = sched_core_find(rq, cookie);
+static struct task_struct *
+filter_max_prio(struct rq *rq, struct task_struct *class_pick, struct task_struct *max, bool in_fi)
+{
+	unsigned long cookie = rq->core->core_cookie;
+	struct task_struct *cookie_pick = NULL;
 
-	/*
-	 * If class > max && class > cookie, it is the highest priority task on
-	 * the core (so far) and it must be selected, otherwise we must go with
-	 * the cookie pick in order to satisfy the constraint.
-	 */
-	if (prio_less(cookie_pick, class_pick, in_fi) &&
-	    (!max || prio_less(max, class_pick, in_fi)))
-		return class_pick;
+	if (cookie) {
+		if (!cookie_equals(class_pick, cookie)) {
+			cookie_pick = sched_core_find(rq, cookie);
+			/*
+			 * If class > max && class > cookie, it is the
+			 * highest priority task on the core (so far)
+			 * and it must be selected, otherwise we must
+			 * go with the cookie pick in order to satisfy
+			 * the constraint.
+			 */
+			if (prio_less(cookie_pick, class_pick, in_fi) &&
+			    (!max || prio_less(max, class_pick, in_fi)))
+				return class_pick;
+			if (!rq->core_temp)
+				swap(rq->core_temp, cookie_pick);
+		} else if (prio_less(max, class_pick, in_fi))
+			return class_pick;
+	}
 
-	return cookie_pick;
+	return NULL;
 }
 
+
 extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
 
 static struct task_struct *
@@ -5403,7 +5413,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	const struct sched_class *class;
 	const struct cpumask *smt_mask;
 	bool fi_before = false;
-	int i, j, cpu, occ = 0;
+	int i, cpu, occ = 0;
 	bool need_sync;
 
 	if (!sched_core_enabled(rq))
@@ -5508,24 +5518,43 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * order.
 	 */
 	for_each_class(class) {
-again:
+		struct task_struct *class_pick;
+		struct rq *rq_i;
+
+		for_each_cpu_wrap(i, smt_mask, cpu) {
+			rq_i = cpu_rq(i);
+			class_pick = pick_task(rq_i, class, max, fi_before);
+			rq_i->core_temp = class_pick;
+			/*
+			 * This sibling doesn't yet have a suitable task to run.
+			 */
+			if (!class_pick)
+				continue;
+
+			if (filter_max_prio(rq_i, class_pick, max, fi_before))
+				max = class_pick;
+		}
+
 		for_each_cpu_wrap(i, smt_mask, cpu) {
-			struct rq *rq_i = cpu_rq(i);
 			struct task_struct *p;
+			rq_i = cpu_rq(i);
 
 			if (rq_i->core_pick)
 				continue;
 
 			/*
-			 * If this sibling doesn't yet have a suitable task to
-			 * run; ask for the most eligible task, given the
-			 * highest priority task already selected for this
-			 * core.
+			 * This sibling doesn't yet have a suitable task to run.
 			 */
-			p = pick_task(rq_i, class, max, fi_before);
-			if (!p)
+			if (!rq_i->core_temp)
 				continue;
 
+			p = rq_i->core_temp;
+			class_pick = NULL;
+			swap(rq_i->core_temp, class_pick);
+			if (!filter_max_prio(rq_i, class_pick, max, fi_before))
+				if (rq_i->core_temp)
+					p = rq_i->core_temp;
+
 			if (!is_task_rq_idle(p))
 				occ++;
 
@@ -5535,35 +5564,6 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 				if (!fi_before)
 					rq->core->core_forceidle_seq++;
 			}
-
-			/*
-			 * If this new candidate is of higher priority than the
-			 * previous; and they're incompatible; we need to wipe
-			 * the slate and start over. pick_task makes sure that
-			 * p's priority is more than max if it doesn't match
-			 * max's cookie.
-			 *
-			 * NOTE: this is a linear max-filter and is thus bounded
-			 * in execution time.
-			 */
-			if (!max || !cookie_match(max, p)) {
-				struct task_struct *old_max = max;
-
-				rq->core->core_cookie = p->core_cookie;
-				max = p;
-
-				if (old_max) {
-					rq->core->core_forceidle = false;
-					for_each_cpu(j, smt_mask) {
-						if (j == i)
-							continue;
-
-						cpu_rq(j)->core_pick = NULL;
-					}
-					occ = 1;
-					goto again;
-				}
-			}
 		}
 	}
 
@@ -9024,6 +9024,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SCHED_CORE
 		rq->core = NULL;
 		rq->core_pick = NULL;
+		rq->core_temp = NULL;
 		rq->core_enabled = 0;
 		rq->core_tree = RB_ROOT;
 		rq->core_forceidle = false;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 14a41a243f7b..2b21a3846b8e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1089,6 +1089,7 @@ struct rq {
 	/* per rq */
 	struct rq		*core;
 	struct task_struct	*core_pick;
+	struct task_struct	*core_temp;
 	unsigned int		core_enabled;
 	unsigned int		core_sched_seq;
 	struct rb_root		core_tree;
-- 
2.31.1


Thanks,
Tao