>From ee54c2849f1d9d7f7f8faeb474a61074cae868b9 Mon Sep 17 00:00:00 2001
From: Tommaso Cucinotta <tommaso@lyx.org>
Date: Thu, 12 May 2016 19:06:37 +0200
Subject: [PATCH 1/2] Make deadline max-heap faster and fix deadline
 wrap-around bug.

---
 kernel/sched/cpudeadline.c | 122 ++++++++++++++++++++++++++++-----------------
 1 file changed, 77 insertions(+), 45 deletions(-)

diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5a75b08..245d929 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -31,55 +31,91 @@ static inline int right_child(int i)
 	return (i << 1) + 2;
 }
 
-static void cpudl_exchange(struct cpudl *cp, int a, int b)
-{
-	int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
-
-	swap(cp->elements[a].cpu, cp->elements[b].cpu);
-	swap(cp->elements[a].dl , cp->elements[b].dl );
-
-	swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx);
-}
-
-static void cpudl_heapify(struct cpudl *cp, int idx)
+static void cpudl_heapify_down(struct cpudl *cp, int idx)
 {
 	int l, r, largest;
 
+	int orig_cpu = cp->elements[idx].cpu;
+	u64 orig_dl = cp->elements[idx].dl;
+
 	/* adapted from lib/prio_heap.c */
 	while(1) {
+		u64 largest_dl;
 		l = left_child(idx);
 		r = right_child(idx);
 		largest = idx;
+		largest_dl = orig_dl;
 
-		if ((l < cp->size) && dl_time_before(cp->elements[idx].dl,
-							cp->elements[l].dl))
+		if ((l < cp->size) && dl_time_before(orig_dl, cp->elements[l].dl)) {
 			largest = l;
-		if ((r < cp->size) && dl_time_before(cp->elements[largest].dl,
-							cp->elements[r].dl))
+			largest_dl = cp->elements[l].dl;
+		}
+		if ((r < cp->size) && dl_time_before(largest_dl, cp->elements[r].dl))
 			largest = r;
+
 		if (largest == idx)
 			break;
 
-		/* Push idx down the heap one level and bump one up */
-		cpudl_exchange(cp, largest, idx);
+		/* pull largest child onto idx */
+		cp->elements[idx].cpu = cp->elements[largest].cpu;
+		cp->elements[idx].dl = cp->elements[largest].dl;
+		cp->elements[cp->elements[idx].cpu].idx = idx;
 		idx = largest;
 	}
+	/* actual push down of saved original values orig_* */
+	cp->elements[idx].cpu = orig_cpu;
+	cp->elements[idx].dl = orig_dl;
+	cp->elements[cp->elements[idx].cpu].idx = idx;
+}
+
+static void cpudl_heapify_up(struct cpudl *cp, int idx)
+{
+	int p;
+
+	int orig_cpu = cp->elements[idx].cpu;
+	u64 orig_dl = cp->elements[idx].dl;
+
+	while (idx != 0) {
+		p = parent(idx);
+		if (dl_time_before(cp->elements[idx].dl, cp->elements[p].dl))
+			break;
+		/* pull parent onto idx */
+		cp->elements[idx].cpu = cp->elements[p].cpu;
+		cp->elements[idx].dl = cp->elements[p].dl;
+		cp->elements[cp->elements[idx].cpu].idx = idx;
+		idx = p;
+	}
+	/* actual push up of saved original values orig_* */
+	cp->elements[idx].cpu = orig_cpu;
+	cp->elements[idx].dl = orig_dl;
+	cp->elements[cp->elements[idx].cpu].idx = idx;
+}
+
+static void cpudl_heapify(struct cpudl *cp, int idx)
+{
+	WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
+	if (idx == IDX_INVALID)
+		return;
+
+	if (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl, cp->elements[idx].dl)) {
+		cpudl_heapify_up(cp, idx);
+	} else {
+		cpudl_heapify_down(cp, idx);
+	}
 }
 
 static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
 {
 	WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
+	if (idx == IDX_INVALID)
+	  return;
 
 	if (dl_time_before(new_dl, cp->elements[idx].dl)) {
 		cp->elements[idx].dl = new_dl;
-		cpudl_heapify(cp, idx);
+		cpudl_heapify_down(cp, idx);
 	} else {
 		cp->elements[idx].dl = new_dl;
-		while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl,
-					cp->elements[idx].dl)) {
-			cpudl_exchange(cp, idx, parent(idx));
-			idx = parent(idx);
-		}
+		cpudl_heapify_up(cp, idx);
 	}
 }
 
@@ -148,33 +184,29 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 			 */
 			goto out;
 		}
-		new_cpu = cp->elements[cp->size - 1].cpu;
-		cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
-		cp->elements[old_idx].cpu = new_cpu;
 		cp->size--;
-		cp->elements[new_cpu].idx = old_idx;
 		cp->elements[cpu].idx = IDX_INVALID;
-		while (old_idx > 0 && dl_time_before(
-				cp->elements[parent(old_idx)].dl,
-				cp->elements[old_idx].dl)) {
-			cpudl_exchange(cp, old_idx, parent(old_idx));
-			old_idx = parent(old_idx);
+		if (old_idx != cp->size) {
+			new_cpu = cp->elements[cp->size].cpu;
+			cp->elements[old_idx].dl = cp->elements[cp->size].dl;
+			cp->elements[old_idx].cpu = new_cpu;
+			cp->elements[new_cpu].idx = old_idx;
+			cpudl_heapify(cp, old_idx);
 		}
-		cpumask_set_cpu(cpu, cp->free_cpus);
-                cpudl_heapify(cp, old_idx);
-
-		goto out;
-	}
 
-	if (old_idx == IDX_INVALID) {
-		cp->size++;
-		cp->elements[cp->size - 1].dl = 0;
-		cp->elements[cp->size - 1].cpu = cpu;
-		cp->elements[cpu].idx = cp->size - 1;
-		cpudl_change_key(cp, cp->size - 1, dl);
-		cpumask_clear_cpu(cpu, cp->free_cpus);
+		cpumask_set_cpu(cpu, cp->free_cpus);
 	} else {
-		cpudl_change_key(cp, old_idx, dl);
+		if (old_idx == IDX_INVALID) {
+			int sz1 = cp->size++;
+			cp->elements[sz1].dl = dl;
+			cp->elements[sz1].cpu = cpu;
+			cp->elements[cpu].idx = sz1;
+			cpudl_heapify_up(cp, sz1);
+
+			cpumask_clear_cpu(cpu, cp->free_cpus);
+		} else {
+			cpudl_change_key(cp, old_idx, dl);
+		}
 	}
 
 out:
-- 
2.7.4