--- linux-2.6.3-ck1pre/kernel/sched.c	2004-02-16 16:35:17.099160238 +1100
+++ linux-2.6.3-ck1/kernel/sched.c	2004-02-16 16:34:21.925816443 +1100
@@ -1294,8 +1294,9 @@ int can_migrate_task(task_t *tsk, runque
 		return 0;
 	if (!cpu_isset(this_cpu, tsk->cpus_allowed))
 		return 0;
-	if (!idle && (delta <= JIFFIES_TO_NS(cache_decay_ticks)))
-		return 0;
+	if (!idle && (delta <= JIFFIES_TO_NS(cache_decay_ticks)) &&
+		!SMT_SIBLINGS(this_cpu, task_cpu(tsk)))
+			return 0;
 	return 1;
 }
 
@@ -1327,15 +1328,23 @@ 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 (SMT_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: */
@@ -1346,9 +1355,16 @@ 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 (SMT_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;
 	}