diff --git a/include/linux/sched.h b/include/linux/sched.h
index d27be93..edb2c69 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -930,7 +930,7 @@
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void FASTCALL(sched_fork(task_t * p));
+extern void FASTCALL(sched_fork(task_t * p, int clone_flags));
 extern void FASTCALL(sched_exit(task_t * p));
 
 extern int in_group_p(gid_t);
diff --git a/kernel/fork.c b/kernel/fork.c
index a28d11e..2c78068 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1003,9 +1003,6 @@
 	p->pdeath_signal = 0;
 	p->exit_state = 0;
 
-	/* Perform scheduler related setup */
-	sched_fork(p);
-
 	/*
 	 * Ok, make it visible to the rest of the system.
 	 * We dont wake it up yet.
@@ -1014,18 +1011,24 @@
 	INIT_LIST_HEAD(&p->ptrace_children);
 	INIT_LIST_HEAD(&p->ptrace_list);
 
+	/* Perform scheduler related setup. Assign this task to a CPU. */
+	sched_fork(p, clone_flags);
+
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
 	/*
-	 * The task hasn't been attached yet, so cpus_allowed mask cannot
-	 * have changed. The cpus_allowed mask of the parent may have
-	 * changed after it was copied first time, and it may then move to
-	 * another CPU - so we re-copy it here and set the child's CPU to
-	 * the parent's CPU. This avoids alot of nasty races.
+	 * The task hasn't been attached yet, so its cpus_allowed mask will
+	 * not be changed, nor will its assigned CPU.
+	 *
+	 * The cpus_allowed mask of the parent may have changed after it was
+	 * copied first time - so re-copy it here, then check the child's CPU
+	 * to ensure it is on a valid CPU (and if not, just force it back to
+	 * parent's CPU). This avoids alot of nasty races.
 	 */
 	p->cpus_allowed = current->cpus_allowed;
-	set_task_cpu(p, smp_processor_id());
+	if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed)))
+		set_task_cpu(p, smp_processor_id());
 
 	/*
 	 * Check for pending SIGKILL! The new thread should not be allowed
diff --git a/kernel/sched.c b/kernel/sched.c
index 54ce787..579da27 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1021,8 +1021,59 @@
 	return idlest;
 }
 
+/*
+ * sched_balance_self: balance the current task (running on cpu) in domains
+ * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
+ * SD_BALANCE_EXEC.
+ *
+ * Balance, ie. select the least loaded group.
+ *
+ * Returns the target CPU number, or the same CPU if no balancing is needed.
+ *
+ * preempt must be disabled.
+ */
+static int sched_balance_self(int cpu, int flag)
+{
+	struct task_struct *t = current;
+	struct sched_domain *tmp, *sd = NULL;
 
-#endif
+	for_each_domain(cpu, tmp)
+		if (tmp->flags & flag)
+			sd = tmp;
+
+	while (sd) {
+		cpumask_t span;
+		struct sched_group *group;
+		int new_cpu;
+		int weight;
+
+		span = sd->span;
+		group = find_idlest_group(sd, t, cpu);
+		if (!group)
+			goto nextlevel;
+
+		new_cpu = find_idlest_cpu(group, cpu);
+		if (new_cpu == -1 || new_cpu == cpu)
+			goto nextlevel;
+
+		/* Now try balancing at a lower domain level */
+		cpu = new_cpu;
+nextlevel:
+		sd = NULL;
+		weight = cpus_weight(span);
+		for_each_domain(cpu, tmp) {
+			if (weight <= cpus_weight(tmp->span))
+				break;
+			if (tmp->flags & flag)
+				sd = tmp;
+		}
+		/* while loop will break here if sd == NULL */
+	}
+
+	return cpu;
+}
+
+#endif /* CONFIG_SMP */
 
 /*
  * wake_idle() will wake a task on an idle cpu if task->cpu is
@@ -1240,8 +1291,15 @@
  * Perform scheduler related setup for a newly forked process p.
  * p is forked by current.
  */
-void fastcall sched_fork(task_t *p)
+void fastcall sched_fork(task_t *p, int clone_flags)
 {
+	int cpu = get_cpu();
+
+#ifdef CONFIG_SMP
+	cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
+#endif
+	set_task_cpu(p, cpu);
+
 	/*
 	 * We mark the process as running here, but have not actually
 	 * inserted it onto the runqueue yet. This guarantees that
@@ -1282,12 +1340,10 @@
 		 * runqueue lock is not a problem.
 		 */
 		current->time_slice = 1;
-		preempt_disable();
 		scheduler_tick();
-		local_irq_enable();
-		preempt_enable();
-	} else
-		local_irq_enable();
+	}
+	local_irq_enable();
+	put_cpu();
 }
 
 /*
@@ -1302,64 +1358,12 @@
 	unsigned long flags;
 	int this_cpu, cpu;
 	runqueue_t *rq, *this_rq;
-#ifdef CONFIG_SMP
-	struct sched_domain *tmp, *sd = NULL;
-#endif
 
 	rq = task_rq_lock(p, &flags);
 	BUG_ON(p->state != TASK_RUNNING);
 	this_cpu = smp_processor_id();
 	cpu = task_cpu(p);
 
-#ifdef CONFIG_SMP
-	for_each_domain(cpu, tmp)
-		if (tmp->flags & SD_BALANCE_FORK)
-			sd = tmp;
-
-	if (sd) {
-		cpumask_t span;
-		int new_cpu;
-		struct sched_group *group;
-
-again:
-		schedstat_inc(sd, sbf_cnt);
-		span = sd->span;
-		cpu = task_cpu(p);
-		group = find_idlest_group(sd, p, cpu);
-		if (!group) {
-			schedstat_inc(sd, sbf_balanced);
-			goto nextlevel;
-		}
-
-		new_cpu = find_idlest_cpu(group, cpu);
-		if (new_cpu == -1 || new_cpu == cpu) {
-			schedstat_inc(sd, sbf_balanced);
-			goto nextlevel;
-		}
-
-		if (cpu_isset(new_cpu, p->cpus_allowed)) {
-			schedstat_inc(sd, sbf_pushed);
-			set_task_cpu(p, new_cpu);
-			task_rq_unlock(rq, &flags);
-			rq = task_rq_lock(p, &flags);
-			cpu = task_cpu(p);
-		}
-
-		/* Now try balancing at a lower domain level */
-nextlevel:
-		sd = NULL;
-		for_each_domain(cpu, tmp) {
-			if (cpus_subset(span, tmp->span))
-				break;
-			if (tmp->flags & SD_BALANCE_FORK)
-				sd = tmp;
-		}
-
-		if (sd)
-			goto again;
-	}
-
-#endif
 	/*
 	 * We decrease the sleep average of forking parents
 	 * and children as well, to keep max-interactive tasks
@@ -1708,58 +1712,16 @@
 }
 
 /*
- * sched_exec(): find the highest-level, exec-balance-capable
- * domain and try to migrate the task to the least loaded CPU.
- *
- * execve() is a valuable balancing opportunity, because at this point
- * the task has the smallest effective memory and cache footprint.
+ * sched_exec - execve() is a valuable balancing opportunity, because at
+ * this point the task has the smallest effective memory and cache footprint.
  */
 void sched_exec(void)
 {
-	struct sched_domain *tmp, *sd = NULL;
 	int new_cpu, this_cpu = get_cpu();
-
-	for_each_domain(this_cpu, tmp)
-		if (tmp->flags & SD_BALANCE_EXEC)
-			sd = tmp;
-
-	if (sd) {
-		cpumask_t span;
-		struct sched_group *group;
-again:
-		schedstat_inc(sd, sbe_cnt);
-		span = sd->span;
-		group = find_idlest_group(sd, current, this_cpu);
-		if (!group) {
-			schedstat_inc(sd, sbe_balanced);
-			goto nextlevel;
-		}
-		new_cpu = find_idlest_cpu(group, this_cpu);
-		if (new_cpu == -1 || new_cpu == this_cpu) {
-			schedstat_inc(sd, sbe_balanced);
-			goto nextlevel;
-		}
-
-		schedstat_inc(sd, sbe_pushed);
-		put_cpu();
-		sched_migrate_task(current, new_cpu);
-
-		/* Now try balancing at a lower domain level */
-		this_cpu = get_cpu();
-nextlevel:
-		sd = NULL;
-		for_each_domain(this_cpu, tmp) {
-			if (cpus_subset(span, tmp->span))
-				break;
-			if (tmp->flags & SD_BALANCE_EXEC)
-				sd = tmp;
-		}
-
-		if (sd)
-			goto again;
-	}
-
+	new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
 	put_cpu();
+	if (new_cpu != this_cpu)
+		sched_migrate_task(current, new_cpu);
 }
 
 /*