--- linux-2.6.0-test11-base/kernel/sched.c	2003-11-24 22:18:56.000000000 +1100
+++ linux-2.6.0-test11-ht3/kernel/sched.c	2003-12-15 23:38:33.250059542 +1100
@@ -204,6 +204,7 @@ struct runqueue {
 	struct mm_struct *prev_mm;
 	prio_array_t *active, *expired, arrays[2];
 	int prev_cpu_load[NR_CPUS];
+	unsigned long cpu;
 #ifdef CONFIG_NUMA
 	atomic_t *node_nr_running;
 	int prev_node_load[MAX_NUMNODES];
@@ -221,6 +222,10 @@ static DEFINE_PER_CPU(struct runqueue, r
 #define task_rq(p)		cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 
+#define ht_active		(cpu_has_ht && smp_num_siblings > 1)
+#define ht_siblings(cpu1, cpu2)	(ht_active && \
+	cpu_sibling_map[(cpu1)] == (cpu2))
+
 /*
  * Default context-switch locking:
  */
@@ -1157,8 +1162,9 @@ 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))
@@ -1193,15 +1199,23 @@ 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: */
@@ -1212,9 +1226,16 @@ 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;
 	}
@@ -2812,6 +2833,7 @@ void __init sched_init(void)
 		prio_array_t *array;
 
 		rq = cpu_rq(i);
+		rq->cpu = (unsigned long)(i);
 		rq->active = rq->arrays;
 		rq->expired = rq->arrays + 1;
 		spin_lock_init(&rq->lock);