--- linux-2.6.1/kernel/sched.c	2004-01-27 16:31:25.943252960 +1100
+++ linux-2.6.1-ck1/kernel/sched.c	2004-01-27 16:31:41.487889816 +1100
@@ -1164,8 +1164,9 @@ can_migrate_task(task_t *tsk, runqueue_t
 {
 	unsigned long delta = sched_clock() - tsk->timestamp;
 
-	if (!idle && (delta <= JIFFIES_TO_NS(cache_decay_ticks)))
-		return 0;
+	if (!idle && (delta <= JIFFIES_TO_NS(cache_decay_ticks)) &&
+		!ht_siblings(this_cpu, task_cpu(tsk)))
+			return 0;
 	if (task_running(rq, tsk))
 		return 0;
 	if (!cpu_isset(this_cpu, tsk->cpus_allowed))
@@ -1200,15 +1201,23 @@ static void load_balance(runqueue_t *thi
 	imbalance /= 2;
 
 	/*
+	 * For hyperthread siblings take tasks from the active array
+	 * to get cache-warm tasks since they share caches.
+	 */
+	if (ht_siblings(this_cpu, busiest->cpu))
+		array = busiest->active;
+	/*
 	 * We first consider expired tasks. Those will likely not be
 	 * executed in the near future, and they are most likely to
 	 * be cache-cold, thus switching CPUs has the least effect
 	 * on them.
 	 */
-	if (busiest->expired->nr_active)
-		array = busiest->expired;
-	else
-		array = busiest->active;
+	else {
+		if (busiest->expired->nr_active)
+			array = busiest->expired;
+		else
+			array = busiest->active;
+	}
 
 new_array:
 	/* Start searching at priority 0: */
@@ -1219,9 +1228,16 @@ skip_bitmap:
 	else
 		idx = find_next_bit(array->bitmap, MAX_PRIO, idx);
 	if (idx >= MAX_PRIO) {
-		if (array == busiest->expired) {
-			array = busiest->active;
-			goto new_array;
+		if (ht_siblings(this_cpu, busiest->cpu)){
+			if (array == busiest->active) {
+				array = busiest->expired;
+				goto new_array;
+			}
+		} else {
+			if (array == busiest->expired) {
+				array = busiest->active;
+				goto new_array;
+			}
 		}
 		goto out_unlock;
 	}