Some scheduler changes for sched-devel

Index: linux-2.6-sched-devel/kernel/sched.c
===================================================================
@@ -555,16 +555,13 @@ static inline void finish_lock_switch(st
 static inline struct rq *__task_rq_lock(struct task_struct *p)
 	__acquires(rq->lock)
 {
-	struct rq *rq;
-
-repeat_lock_task:
-	rq = task_rq(p);
-	spin_lock(&rq->lock);
-	if (unlikely(rq != task_rq(p))) {
+	for (;;) {
+		struct rq *rq = task_rq(p);
+		spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p)))
+			return rq;
 		spin_unlock(&rq->lock);
-		goto repeat_lock_task;
 	}
-	return rq;
 }
 
 /*

@@ -577,15 +574,14 @@ static struct rq *task_rq_lock(struct ta
 {
 	struct rq *rq;
 
-repeat_lock_task:
-	local_irq_save(*flags);
-	rq = task_rq(p);
-	spin_lock(&rq->lock);
-	if (unlikely(rq != task_rq(p))) {
+	for (;;) {
+		local_irq_save(*flags);
+		rq = task_rq(p);
+		spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p)))
+			return rq;
 		spin_unlock_irqrestore(&rq->lock, *flags);
-		goto repeat_lock_task;
 	}
-	return rq;
 }
 
 static void __task_rq_unlock(struct rq *rq)

@@ -1076,69 +1072,71 @@ void wait_task_inactive(struct task_stru
 	int running, on_rq;
 	struct rq *rq;
 
-repeat:
-	/*
-	 * We do the initial early heuristics without holding
-	 * any task-queue locks at all. We'll only try to get
-	 * the runqueue lock when things look like they will
-	 * work out!
-	 */
-	rq = task_rq(p);
+	for (;;) {
+		/*
+		 * We do the initial early heuristics without holding
+		 * any task-queue locks at all. We'll only try to get
+		 * the runqueue lock when things look like they will
+		 * work out!
+		 */
+		rq = task_rq(p);
 
-	/*
-	 * If the task is actively running on another CPU
-	 * still, just relax and busy-wait without holding
-	 * any locks.
-	 *
-	 * NOTE! Since we don't hold any locks, it's not
-	 * even sure that "rq" stays as the right runqueue!
-	 * But we don't care, since "task_running()" will
-	 * return false if the runqueue has changed and p
-	 * is actually now running somewhere else!
-	 */
-	while (task_running(rq, p))
-		cpu_relax();
+		/*
+		 * If the task is actively running on another CPU
+		 * still, just relax and busy-wait without holding
+		 * any locks.
+		 *
+		 * NOTE! Since we don't hold any locks, it's not
+		 * even sure that "rq" stays as the right runqueue!
+		 * But we don't care, since "task_running()" will
+		 * return false if the runqueue has changed and p
+		 * is actually now running somewhere else!
+		 */
+		while (task_running(rq, p))
+			cpu_relax();
 
-	/*
-	 * Ok, time to look more closely! We need the rq
-	 * lock now, to be *sure*. If we're wrong, we'll
-	 * just go back and repeat.
-	 */
-	rq = task_rq_lock(p, &flags);
-	running = task_running(rq, p);
-	on_rq = p->se.on_rq;
-	task_rq_unlock(rq, &flags);
+		/*
+		 * Ok, time to look more closely! We need the rq
+		 * lock now, to be *sure*. If we're wrong, we'll
+		 * just go back and repeat.
+		 */
+		rq = task_rq_lock(p, &flags);
+		running = task_running(rq, p);
+		on_rq = p->se.on_rq;
+		task_rq_unlock(rq, &flags);
 
-	/*
-	 * Was it really running after all now that we
-	 * checked with the proper locks actually held?
-	 *
-	 * Oops. Go back and try again..
-	 */
-	if (unlikely(running)) {
-		cpu_relax();
-		goto repeat;
-	}
+		/*
+		 * Was it really running after all now that we
+		 * checked with the proper locks actually held?
+		 *
+		 * Oops. Go back and try again..
+		 */
+		if (unlikely(running)) {
+			cpu_relax();
+			continue;
+		}
 
-	/*
-	 * It's not enough that it's not actively running,
-	 * it must be off the runqueue _entirely_, and not
-	 * preempted!
-	 *
-	 * So if it wa still runnable (but just not actively
-	 * running right now), it's preempted, and we should
-	 * yield - it could be a while.
-	 */
-	if (unlikely(on_rq)) {
-		schedule_timeout_uninterruptible(1);
-		goto repeat;
-	}
+		/*
+		 * It's not enough that it's not actively running,
+		 * it must be off the runqueue _entirely_, and not
+		 * preempted!
+		 *
+		 * So if it wa still runnable (but just not actively
+		 * running right now), it's preempted, and we should
+		 * yield - it could be a while.
+		 */
+		if (unlikely(on_rq)) {
+			schedule_timeout_uninterruptible(1);
+			continue;
+		}
 
-	/*
-	 * Ahh, all good. It wasn't running, and it wasn't
-	 * runnable, which means that it will never become
-	 * running in the future either. We're all done!
-	 */
+		/*
+		 * Ahh, all good. It wasn't running, and it wasn't
+		 * runnable, which means that it will never become
+		 * running in the future either. We're all done!
+		 */
+		break;
+	}
 }
 
 /***

@@ -1229,7 +1227,7 @@ find_idlest_group(struct sched_domain *s
 
 		/* Skip over this group if it has no CPUs allowed */
 		if (!cpus_intersects(group->cpumask, p->cpus_allowed))
-			goto nextgroup;
+			continue;
 
 		local_group = cpu_isset(this_cpu, group->cpumask);
 

@@ -1257,9 +1255,7 @@ find_idlest_group(struct sched_domain *s
 			min_load = avg_load;
 			idlest = group;
 		}
-nextgroup:
-		group = group->next;
-	} while (group != sd->groups);
+	} while (group = group->next, group != sd->groups);
 
 	if (!idlest || 100*this_load < imbalance*min_load)
 		return NULL;

@@ -3510,27 +3506,30 @@ asmlinkage void __sched preempt_schedule
 	if (likely(ti->preempt_count || irqs_disabled()))
 		return;
 
-need_resched:
-	add_preempt_count(PREEMPT_ACTIVE);
-	/*
-	 * We keep the big kernel semaphore locked, but we
-	 * clear ->lock_depth so that schedule() doesnt
-	 * auto-release the semaphore:
-	 */
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * We keep the big kernel semaphore locked, but we
+		 * clear ->lock_depth so that schedule() doesnt
+		 * auto-release the semaphore:
+		 */
 #ifdef CONFIG_PREEMPT_BKL
-	saved_lock_depth = task->lock_depth;
-	task->lock_depth = -1;
+		saved_lock_depth = task->lock_depth;
+		task->lock_depth = -1;
 #endif
-	schedule();
+		schedule();
 #ifdef CONFIG_PREEMPT_BKL
-	task->lock_depth = saved_lock_depth;
+		task->lock_depth = saved_lock_depth;
 #endif
-	sub_preempt_count(PREEMPT_ACTIVE);
+		sub_preempt_count(PREEMPT_ACTIVE);
 
-	/* we could miss a preemption opportunity between schedule and now */
-	barrier();
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
-		goto need_resched;
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
 }
 EXPORT_SYMBOL(preempt_schedule);
 

@@ -3550,29 +3549,32 @@ asmlinkage void __sched preempt_schedule
 	/* Catch callers which need to be fixed */
 	BUG_ON(ti->preempt_count || !irqs_disabled());
 
-need_resched:
-	add_preempt_count(PREEMPT_ACTIVE);
-	/*
-	 * We keep the big kernel semaphore locked, but we
-	 * clear ->lock_depth so that schedule() doesnt
-	 * auto-release the semaphore:
-	 */
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * We keep the big kernel semaphore locked, but we
+		 * clear ->lock_depth so that schedule() doesnt
+		 * auto-release the semaphore:
+		 */
 #ifdef CONFIG_PREEMPT_BKL
-	saved_lock_depth = task->lock_depth;
-	task->lock_depth = -1;
+		saved_lock_depth = task->lock_depth;
+		task->lock_depth = -1;
 #endif
-	local_irq_enable();
-	schedule();
-	local_irq_disable();
+		local_irq_enable();
+		schedule();
+		local_irq_disable();
 #ifdef CONFIG_PREEMPT_BKL
-	task->lock_depth = saved_lock_depth;
+		task->lock_depth = saved_lock_depth;
 #endif
-	sub_preempt_count(PREEMPT_ACTIVE);
+		sub_preempt_count(PREEMPT_ACTIVE);
 
-	/* we could miss a preemption opportunity between schedule and now */
-	barrier();
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
-		goto need_resched;
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
 }
 
 #endif /* CONFIG_PREEMPT */

@@ -4317,10 +4319,10 @@ asmlinkage long sys_sched_setparam(pid_t
 asmlinkage long sys_sched_getscheduler(pid_t pid)
 {
 	struct task_struct *p;
-	int retval = -EINVAL;
+	int retval;
 
 	if (pid < 0)
-		goto out_nounlock;
+		return -EINVAL;
 
 	retval = -ESRCH;
 	read_lock(&tasklist_lock);

@@ -4331,8 +4333,6 @@ asmlinkage long sys_sched_getscheduler(p
 			retval = p->policy;
 	}
 	read_unlock(&tasklist_lock);
-
-out_nounlock:
 	return retval;
 }
 

@@ -4345,10 +4345,10 @@ asmlinkage long sys_sched_getparam(pid_t
 {
 	struct sched_param lp;
 	struct task_struct *p;
-	int retval = -EINVAL;
+	int retval;
 
 	if (!param || pid < 0)
-		goto out_nounlock;
+		return -EINVAL;
 
 	read_lock(&tasklist_lock);
 	p = find_process_by_pid(pid);

@@ -4368,7 +4368,6 @@ asmlinkage long sys_sched_getparam(pid_t
 	 */
 	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
 
-out_nounlock:
 	return retval;
 
 out_unlock:

@@ -4724,11 +4723,11 @@ long sys_sched_rr_get_interval(pid_t pid
 {
 	struct task_struct *p;
 	unsigned int time_slice;
-	int retval = -EINVAL;
+	int retval;
 	struct timespec t;
 
 	if (pid < 0)
-		goto out_nounlock;
+		return -EINVAL;
 
 	retval = -ESRCH;
 	read_lock(&tasklist_lock);

@@ -4756,8 +4755,8 @@ long sys_sched_rr_get_interval(pid_t pid
 	read_unlock(&tasklist_lock);
 	jiffies_to_timespec(time_slice, &t);
 	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
-out_nounlock:
 	return retval;
+
 out_unlock:
 	read_unlock(&tasklist_lock);
 	return retval;

@@ -5063,35 +5062,34 @@ static void move_task_off_dead_cpu(int d
 	struct rq *rq;
 	int dest_cpu;
 
-restart:
-	/* On same node? */
-	mask = node_to_cpumask(cpu_to_node(dead_cpu));
-	cpus_and(mask, mask, p->cpus_allowed);
-	dest_cpu = any_online_cpu(mask);
-
-	/* On any allowed CPU? */
-	if (dest_cpu == NR_CPUS)
-		dest_cpu = any_online_cpu(p->cpus_allowed);
-
-	/* No more Mr. Nice Guy. */
-	if (dest_cpu == NR_CPUS) {
-		rq = task_rq_lock(p, &flags);
-		cpus_setall(p->cpus_allowed);
-		dest_cpu = any_online_cpu(p->cpus_allowed);
-		task_rq_unlock(rq, &flags);
+	do {
+		/* On same node? */
+		mask = node_to_cpumask(cpu_to_node(dead_cpu));
+		cpus_and(mask, mask, p->cpus_allowed);
+		dest_cpu = any_online_cpu(mask);
+
+		/* On any allowed CPU? */
+		if (dest_cpu == NR_CPUS)
+			dest_cpu = any_online_cpu(p->cpus_allowed);
+
+		/* No more Mr. Nice Guy. */
+		if (dest_cpu == NR_CPUS) {
+			rq = task_rq_lock(p, &flags);
+			cpus_setall(p->cpus_allowed);
+			dest_cpu = any_online_cpu(p->cpus_allowed);
+			task_rq_unlock(rq, &flags);
 
-		/*
-		 * Don't tell them about moving exiting tasks or
-		 * kernel threads (both mm NULL), since they never
-		 * leave kernel.
-		 */
-		if (p->mm && printk_ratelimit())
-			printk(KERN_INFO "process %d (%s) no "
-			       "longer affine to cpu%d\n",
-			       p->pid, p->comm, dead_cpu);
-	}
-	if (!__migrate_task(p, dead_cpu, dest_cpu))
-		goto restart;
+			/*
+			 * Don't tell them about moving exiting tasks or
+			 * kernel threads (both mm NULL), since they never
+			 * leave kernel.
+			 */
+			if (p->mm && printk_ratelimit())
+				printk(KERN_INFO "process %d (%s) no "
+				       "longer affine to cpu%d\n",
+				       p->pid, p->comm, dead_cpu);
+		}
+	} while (!__migrate_task(p, dead_cpu, dest_cpu));
 }
 
 /*

@@ -5906,24 +5904,23 @@ static void init_numa_sched_groups_power
 
 	if (!sg)
 		return;
-next_sg:
-	for_each_cpu_mask(j, sg->cpumask) {
-		struct sched_domain *sd;
+	do {
+		for_each_cpu_mask(j, sg->cpumask) {
+			struct sched_domain *sd;
 
-		sd = &per_cpu(phys_domains, j);
-		if (j != first_cpu(sd->groups->cpumask)) {
-			/*
-			 * Only add "power" once for each
-			 * physical package.
-			 */
-			continue;
-		}
+			sd = &per_cpu(phys_domains, j);
+			if (j != first_cpu(sd->groups->cpumask)) {
+				/*
+				 * Only add "power" once for each
+				 * physical package.
+				 */
+				continue;
+			}
 
-		sg_inc_cpu_power(sg, sd->groups->__cpu_power);
-	}
-	sg = sg->next;
-	if (sg != group_head)
-		goto next_sg;
+			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+		}
+		sg = sg->next;
+	} while (sg != group_head);
 }
 #endif
 

Index: linux-2.6-sched-devel/kernel/sched.c
===================================================================
@@ -555,16 +555,13 @@ static inline void finish_lock_switch(st
 static inline struct rq *__task_rq_lock(struct task_struct *p)
 	__acquires(rq->lock)
 {
-	struct rq *rq;
-
-repeat_lock_task:
-	rq = task_rq(p);
-	spin_lock(&rq->lock);
-	if (unlikely(rq != task_rq(p))) {
+	for (;;) {
+		struct rq *rq = task_rq(p);
+		spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p)))
+			return rq;
 		spin_unlock(&rq->lock);
-		goto repeat_lock_task;
 	}
-	return rq;
 }
 
 /*

@@ -577,15 +574,14 @@ static struct rq *task_rq_lock(struct ta
 {
 	struct rq *rq;
 
-repeat_lock_task:
-	local_irq_save(*flags);
-	rq = task_rq(p);
-	spin_lock(&rq->lock);
-	if (unlikely(rq != task_rq(p))) {
+	for (;;) {
+		local_irq_save(*flags);
+		rq = task_rq(p);
+		spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p)))
+			return rq;
 		spin_unlock_irqrestore(&rq->lock, *flags);
-		goto repeat_lock_task;
 	}
-	return rq;
 }
 
 static void __task_rq_unlock(struct rq *rq)

@@ -1076,69 +1072,71 @@ void wait_task_inactive(struct task_stru
 	int running, on_rq;
 	struct rq *rq;
 
-repeat:
-	/*
-	 * We do the initial early heuristics without holding
-	 * any task-queue locks at all. We'll only try to get
-	 * the runqueue lock when things look like they will
-	 * work out!
-	 */
-	rq = task_rq(p);
+	for (;;) {
+		/*
+		 * We do the initial early heuristics without holding
+		 * any task-queue locks at all. We'll only try to get
+		 * the runqueue lock when things look like they will
+		 * work out!
+		 */
+		rq = task_rq(p);
 
-	/*
-	 * If the task is actively running on another CPU
-	 * still, just relax and busy-wait without holding
-	 * any locks.
-	 *
-	 * NOTE! Since we don't hold any locks, it's not
-	 * even sure that "rq" stays as the right runqueue!
-	 * But we don't care, since "task_running()" will
-	 * return false if the runqueue has changed and p
-	 * is actually now running somewhere else!
-	 */
-	while (task_running(rq, p))
-		cpu_relax();
+		/*
+		 * If the task is actively running on another CPU
+		 * still, just relax and busy-wait without holding
+		 * any locks.
+		 *
+		 * NOTE! Since we don't hold any locks, it's not
+		 * even sure that "rq" stays as the right runqueue!
+		 * But we don't care, since "task_running()" will
+		 * return false if the runqueue has changed and p
+		 * is actually now running somewhere else!
+		 */
+		while (task_running(rq, p))
+			cpu_relax();
 
-	/*
-	 * Ok, time to look more closely! We need the rq
-	 * lock now, to be *sure*. If we're wrong, we'll
-	 * just go back and repeat.
-	 */
-	rq = task_rq_lock(p, &flags);
-	running = task_running(rq, p);
-	on_rq = p->se.on_rq;
-	task_rq_unlock(rq, &flags);
+		/*
+		 * Ok, time to look more closely! We need the rq
+		 * lock now, to be *sure*. If we're wrong, we'll
+		 * just go back and repeat.
+		 */
+		rq = task_rq_lock(p, &flags);
+		running = task_running(rq, p);
+		on_rq = p->se.on_rq;
+		task_rq_unlock(rq, &flags);
 
-	/*
-	 * Was it really running after all now that we
-	 * checked with the proper locks actually held?
-	 *
-	 * Oops. Go back and try again..
-	 */
-	if (unlikely(running)) {
-		cpu_relax();
-		goto repeat;
-	}
+		/*
+		 * Was it really running after all now that we
+		 * checked with the proper locks actually held?
+		 *
+		 * Oops. Go back and try again..
+		 */
+		if (unlikely(running)) {
+			cpu_relax();
+			continue;
+		}
 
-	/*
-	 * It's not enough that it's not actively running,
-	 * it must be off the runqueue _entirely_, and not
-	 * preempted!
-	 *
-	 * So if it wa still runnable (but just not actively
-	 * running right now), it's preempted, and we should
-	 * yield - it could be a while.
-	 */
-	if (unlikely(on_rq)) {
-		schedule_timeout_uninterruptible(1);
-		goto repeat;
-	}
+		/*
+		 * It's not enough that it's not actively running,
+		 * it must be off the runqueue _entirely_, and not
+		 * preempted!
+		 *
+		 * So if it wa still runnable (but just not actively
+		 * running right now), it's preempted, and we should
+		 * yield - it could be a while.
+		 */
+		if (unlikely(on_rq)) {
+			schedule_timeout_uninterruptible(1);
+			continue;
+		}
 
-	/*
-	 * Ahh, all good. It wasn't running, and it wasn't
-	 * runnable, which means that it will never become
-	 * running in the future either. We're all done!
-	 */
+		/*
+		 * Ahh, all good. It wasn't running, and it wasn't
+		 * runnable, which means that it will never become
+		 * running in the future either. We're all done!
+		 */
+		break;
+	}
 }
 
 /***

@@ -1229,7 +1227,7 @@ find_idlest_group(struct sched_domain *s
 
 		/* Skip over this group if it has no CPUs allowed */
 		if (!cpus_intersects(group->cpumask, p->cpus_allowed))
-			goto nextgroup;
+			continue;
 
 		local_group = cpu_isset(this_cpu, group->cpumask);
 

@@ -1257,9 +1255,7 @@ find_idlest_group(struct sched_domain *s
 			min_load = avg_load;
 			idlest = group;
 		}
-nextgroup:
-		group = group->next;
-	} while (group != sd->groups);
+	} while (group = group->next, group != sd->groups);
 
 	if (!idlest || 100*this_load < imbalance*min_load)
 		return NULL;

@@ -3510,27 +3506,30 @@ asmlinkage void __sched preempt_schedule
 	if (likely(ti->preempt_count || irqs_disabled()))
 		return;
 
-need_resched:
-	add_preempt_count(PREEMPT_ACTIVE);
-	/*
-	 * We keep the big kernel semaphore locked, but we
-	 * clear ->lock_depth so that schedule() doesnt
-	 * auto-release the semaphore:
-	 */
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * We keep the big kernel semaphore locked, but we
+		 * clear ->lock_depth so that schedule() doesnt
+		 * auto-release the semaphore:
+		 */
 #ifdef CONFIG_PREEMPT_BKL
-	saved_lock_depth = task->lock_depth;
-	task->lock_depth = -1;
+		saved_lock_depth = task->lock_depth;
+		task->lock_depth = -1;
 #endif
-	schedule();
+		schedule();
 #ifdef CONFIG_PREEMPT_BKL
-	task->lock_depth = saved_lock_depth;
+		task->lock_depth = saved_lock_depth;
 #endif
-	sub_preempt_count(PREEMPT_ACTIVE);
+		sub_preempt_count(PREEMPT_ACTIVE);
 
-	/* we could miss a preemption opportunity between schedule and now */
-	barrier();
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
-		goto need_resched;
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
 }
 EXPORT_SYMBOL(preempt_schedule);
 

@@ -3550,29 +3549,32 @@ asmlinkage void __sched preempt_schedule
 	/* Catch callers which need to be fixed */
 	BUG_ON(ti->preempt_count || !irqs_disabled());
 
-need_resched:
-	add_preempt_count(PREEMPT_ACTIVE);
-	/*
-	 * We keep the big kernel semaphore locked, but we
-	 * clear ->lock_depth so that schedule() doesnt
-	 * auto-release the semaphore:
-	 */
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * We keep the big kernel semaphore locked, but we
+		 * clear ->lock_depth so that schedule() doesnt
+		 * auto-release the semaphore:
+		 */
 #ifdef CONFIG_PREEMPT_BKL
-	saved_lock_depth = task->lock_depth;
-	task->lock_depth = -1;
+		saved_lock_depth = task->lock_depth;
+		task->lock_depth = -1;
 #endif
-	local_irq_enable();
-	schedule();
-	local_irq_disable();
+		local_irq_enable();
+		schedule();
+		local_irq_disable();
 #ifdef CONFIG_PREEMPT_BKL
-	task->lock_depth = saved_lock_depth;
+		task->lock_depth = saved_lock_depth;
 #endif
-	sub_preempt_count(PREEMPT_ACTIVE);
+		sub_preempt_count(PREEMPT_ACTIVE);
 
-	/* we could miss a preemption opportunity between schedule and now */
-	barrier();
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
-		goto need_resched;
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
 }
 
 #endif /* CONFIG_PREEMPT */

@@ -4317,10 +4319,10 @@ asmlinkage long sys_sched_setparam(pid_t
 asmlinkage long sys_sched_getscheduler(pid_t pid)
 {
 	struct task_struct *p;
-	int retval = -EINVAL;
+	int retval;
 
 	if (pid < 0)
-		goto out_nounlock;
+		return -EINVAL;
 
 	retval = -ESRCH;
 	read_lock(&tasklist_lock);

@@ -4331,8 +4333,6 @@ asmlinkage long sys_sched_getscheduler(p
 			retval = p->policy;
 	}
 	read_unlock(&tasklist_lock);
-
-out_nounlock:
 	return retval;
 }
 

@@ -4345,10 +4345,10 @@ asmlinkage long sys_sched_getparam(pid_t
 {
 	struct sched_param lp;
 	struct task_struct *p;
-	int retval = -EINVAL;
+	int retval;
 
 	if (!param || pid < 0)
-		goto out_nounlock;
+		return -EINVAL;
 
 	read_lock(&tasklist_lock);
 	p = find_process_by_pid(pid);

@@ -4368,7 +4368,6 @@ asmlinkage long sys_sched_getparam(pid_t
 	 */
 	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
 
-out_nounlock:
 	return retval;
 
 out_unlock:

@@ -4724,11 +4723,11 @@ long sys_sched_rr_get_interval(pid_t pid
 {
 	struct task_struct *p;
 	unsigned int time_slice;
-	int retval = -EINVAL;
+	int retval;
 	struct timespec t;
 
 	if (pid < 0)
-		goto out_nounlock;
+		return -EINVAL;
 
 	retval = -ESRCH;
 	read_lock(&tasklist_lock);

@@ -4756,8 +4755,8 @@ long sys_sched_rr_get_interval(pid_t pid
 	read_unlock(&tasklist_lock);
 	jiffies_to_timespec(time_slice, &t);
 	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
-out_nounlock:
 	return retval;
+
 out_unlock:
 	read_unlock(&tasklist_lock);
 	return retval;

@@ -5063,35 +5062,34 @@ static void move_task_off_dead_cpu(int d
 	struct rq *rq;
 	int dest_cpu;
 
-restart:
-	/* On same node? */
-	mask = node_to_cpumask(cpu_to_node(dead_cpu));
-	cpus_and(mask, mask, p->cpus_allowed);
-	dest_cpu = any_online_cpu(mask);
-
-	/* On any allowed CPU? */
-	if (dest_cpu == NR_CPUS)
-		dest_cpu = any_online_cpu(p->cpus_allowed);
-
-	/* No more Mr. Nice Guy. */
-	if (dest_cpu == NR_CPUS) {
-		rq = task_rq_lock(p, &flags);
-		cpus_setall(p->cpus_allowed);
-		dest_cpu = any_online_cpu(p->cpus_allowed);
-		task_rq_unlock(rq, &flags);
+	do {
+		/* On same node? */
+		mask = node_to_cpumask(cpu_to_node(dead_cpu));
+		cpus_and(mask, mask, p->cpus_allowed);
+		dest_cpu = any_online_cpu(mask);
+
+		/* On any allowed CPU? */
+		if (dest_cpu == NR_CPUS)
+			dest_cpu = any_online_cpu(p->cpus_allowed);
+
+		/* No more Mr. Nice Guy. */
+		if (dest_cpu == NR_CPUS) {
+			rq = task_rq_lock(p, &flags);
+			cpus_setall(p->cpus_allowed);
+			dest_cpu = any_online_cpu(p->cpus_allowed);
+			task_rq_unlock(rq, &flags);
 
-		/*
-		 * Don't tell them about moving exiting tasks or
-		 * kernel threads (both mm NULL), since they never
-		 * leave kernel.
-		 */
-		if (p->mm && printk_ratelimit())
-			printk(KERN_INFO "process %d (%s) no "
-			       "longer affine to cpu%d\n",
-			       p->pid, p->comm, dead_cpu);
-	}
-	if (!__migrate_task(p, dead_cpu, dest_cpu))
-		goto restart;
+			/*
+			 * Don't tell them about moving exiting tasks or
+			 * kernel threads (both mm NULL), since they never
+			 * leave kernel.
+			 */
+			if (p->mm && printk_ratelimit())
+				printk(KERN_INFO "process %d (%s) no "
+				       "longer affine to cpu%d\n",
+				       p->pid, p->comm, dead_cpu);
+		}
+	} while (!__migrate_task(p, dead_cpu, dest_cpu));
 }
 
 /*

@@ -5906,24 +5904,23 @@ static void init_numa_sched_groups_power
 
 	if (!sg)
 		return;
-next_sg:
-	for_each_cpu_mask(j, sg->cpumask) {
-		struct sched_domain *sd;
+	do {
+		for_each_cpu_mask(j, sg->cpumask) {
+			struct sched_domain *sd;
 
-		sd = &per_cpu(phys_domains, j);
-		if (j != first_cpu(sd->groups->cpumask)) {
-			/*
-			 * Only add "power" once for each
-			 * physical package.
-			 */
-			continue;
-		}
+			sd = &per_cpu(phys_domains, j);
+			if (j != first_cpu(sd->groups->cpumask)) {
+				/*
+				 * Only add "power" once for each
+				 * physical package.
+				 */
+				continue;
+			}
 
-		sg_inc_cpu_power(sg, sd->groups->__cpu_power);
-	}
-	sg = sg->next;
-	if (sg != group_head)
-		goto next_sg;
+			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+		}
+		sg = sg->next;
+	} while (sg != group_head);
 }
 #endif
 

Index: linux-2.6-sched-devel/kernel/sched.c
===================================================================
@@ -3689,206 +3689,115 @@ void fastcall complete_all(struct comple
 }
 EXPORT_SYMBOL(complete_all);
 
-void fastcall __sched wait_for_completion(struct completion *x)
+static inline long __sched
+do_wait_for_common(struct completion *x, long timeout, int state)
 {
-	might_sleep();
-
-	spin_lock_irq(&x->wait.lock);
 	if (!x->done) {
 		DECLARE_WAITQUEUE(wait, current);
 
 		wait.flags |= WQ_FLAG_EXCLUSIVE;
 		__add_wait_queue_tail(&x->wait, &wait);
 		do {
-			__set_current_state(TASK_UNINTERRUPTIBLE);
-			spin_unlock_irq(&x->wait.lock);
-			schedule();
-			spin_lock_irq(&x->wait.lock);
-		} while (!x->done);
-		__remove_wait_queue(&x->wait, &wait);
-	}
-	x->done--;
-	spin_unlock_irq(&x->wait.lock);
-}
-EXPORT_SYMBOL(wait_for_completion);
-
-unsigned long fastcall __sched
-wait_for_completion_timeout(struct completion *x, unsigned long timeout)
-{
-	might_sleep();
-
-	spin_lock_irq(&x->wait.lock);
-	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		wait.flags |= WQ_FLAG_EXCLUSIVE;
-		__add_wait_queue_tail(&x->wait, &wait);
-		do {
-			__set_current_state(TASK_UNINTERRUPTIBLE);
+			if (state == TASK_INTERRUPTIBLE &&
+			    signal_pending(current)) {
+				__remove_wait_queue(&x->wait, &wait);
+				return -ERESTARTSYS;
+			}
+			__set_current_state(state);
 			spin_unlock_irq(&x->wait.lock);
 			timeout = schedule_timeout(timeout);
 			spin_lock_irq(&x->wait.lock);
 			if (!timeout) {
 				__remove_wait_queue(&x->wait, &wait);
-				goto out;
+				return timeout;
 			}
 		} while (!x->done);
 		__remove_wait_queue(&x->wait, &wait);
 	}
 	x->done--;
-out:
-	spin_unlock_irq(&x->wait.lock);
 	return timeout;
 }
-EXPORT_SYMBOL(wait_for_completion_timeout);
 
-int fastcall __sched wait_for_completion_interruptible(struct completion *x)
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
 {
-	int ret = 0;
-
 	might_sleep();
 
 	spin_lock_irq(&x->wait.lock);
-	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		wait.flags |= WQ_FLAG_EXCLUSIVE;
-		__add_wait_queue_tail(&x->wait, &wait);
-		do {
-			if (signal_pending(current)) {
-				ret = -ERESTARTSYS;
-				__remove_wait_queue(&x->wait, &wait);
-				goto out;
-			}
-			__set_current_state(TASK_INTERRUPTIBLE);
-			spin_unlock_irq(&x->wait.lock);
-			schedule();
-			spin_lock_irq(&x->wait.lock);
-		} while (!x->done);
-		__remove_wait_queue(&x->wait, &wait);
-	}
-	x->done--;
-out:
+	timeout = do_wait_for_common(x, timeout, state);
 	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
 
-	return ret;
+void fastcall __sched wait_for_completion(struct completion *x)
+{
+	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
 }
-EXPORT_SYMBOL(wait_for_completion_interruptible);
+EXPORT_SYMBOL(wait_for_completion);
 
 unsigned long fastcall __sched
-wait_for_completion_interruptible_timeout(struct completion *x,
-					  unsigned long timeout)
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 {
-	might_sleep();
-
-	spin_lock_irq(&x->wait.lock);
-	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		wait.flags |= WQ_FLAG_EXCLUSIVE;
-		__add_wait_queue_tail(&x->wait, &wait);
-		do {
-			if (signal_pending(current)) {
-				timeout = -ERESTARTSYS;
-				__remove_wait_queue(&x->wait, &wait);
-				goto out;
-			}
-			__set_current_state(TASK_INTERRUPTIBLE);
-			spin_unlock_irq(&x->wait.lock);
-			timeout = schedule_timeout(timeout);
-			spin_lock_irq(&x->wait.lock);
-			if (!timeout) {
-				__remove_wait_queue(&x->wait, &wait);
-				goto out;
-			}
-		} while (!x->done);
-		__remove_wait_queue(&x->wait, &wait);
-	}
-	x->done--;
-out:
-	spin_unlock_irq(&x->wait.lock);
-	return timeout;
+	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
 }
-EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+EXPORT_SYMBOL(wait_for_completion_timeout);
 
-static inline void
-sleep_on_head(wait_queue_head_t *q, wait_queue_t *wait, unsigned long *flags)
+int __sched wait_for_completion_interruptible(struct completion *x)
 {
-	spin_lock_irqsave(&q->lock, *flags);
-	__add_wait_queue(q, wait);
-	spin_unlock(&q->lock);
+	return wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
 }
+EXPORT_SYMBOL(wait_for_completion_interruptible);
 
-static inline void
-sleep_on_tail(wait_queue_head_t *q, wait_queue_t *wait, unsigned long *flags)
+unsigned long fastcall __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+					  unsigned long timeout)
 {
-	spin_lock_irq(&q->lock);
-	__remove_wait_queue(q, wait);
-	spin_unlock_irqrestore(&q->lock, *flags);
+	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
 }
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
 
-void __sched interruptible_sleep_on(wait_queue_head_t *q)
+static long sleep_on_common(wait_queue_head_t *q, int state, long timeout)
 {
 	unsigned long flags;
 	wait_queue_t wait;
 
 	init_waitqueue_entry(&wait, current);
 
-	current->state = TASK_INTERRUPTIBLE;
+	__set_current_state(state);
 
-	sleep_on_head(q, &wait, &flags);
-	schedule();
-	sleep_on_tail(q, &wait, &flags);
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, &wait);
+	spin_unlock(&q->lock);
+	timeout = schedule_timeout(timeout);
+	spin_lock_irq(&q->lock);
+	__remove_wait_queue(q, &wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return timeout;
+}
+
+void __sched interruptible_sleep_on(wait_queue_head_t *q)
+{
+	sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 }
 EXPORT_SYMBOL(interruptible_sleep_on);
 
 long __sched
 interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
 {
-	unsigned long flags;
-	wait_queue_t wait;
-
-	init_waitqueue_entry(&wait, current);
-
-	current->state = TASK_INTERRUPTIBLE;
-
-	sleep_on_head(q, &wait, &flags);
-	timeout = schedule_timeout(timeout);
-	sleep_on_tail(q, &wait, &flags);
-
-	return timeout;
+	return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
 }
 EXPORT_SYMBOL(interruptible_sleep_on_timeout);
 
 void __sched sleep_on(wait_queue_head_t *q)
 {
-	unsigned long flags;
-	wait_queue_t wait;
-
-	init_waitqueue_entry(&wait, current);
-
-	current->state = TASK_UNINTERRUPTIBLE;
-
-	sleep_on_head(q, &wait, &flags);
-	schedule();
-	sleep_on_tail(q, &wait, &flags);
+	sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 }
 EXPORT_SYMBOL(sleep_on);
 
 long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
 {
-	unsigned long flags;
-	wait_queue_t wait;
-
-	init_waitqueue_entry(&wait, current);
-
-	current->state = TASK_UNINTERRUPTIBLE;
-
-	sleep_on_head(q, &wait, &flags);
-	timeout = schedule_timeout(timeout);
-	sleep_on_tail(q, &wait, &flags);
-
-	return timeout;
+	return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
 }
 EXPORT_SYMBOL(sleep_on_timeout);
 

Index: linux-2.6-sched-devel/kernel/sched.c
===================================================================
@@ -3690,206 +3690,116 @@ void fastcall complete_all(struct comple
 }
 EXPORT_SYMBOL(complete_all);
 
-void fastcall __sched wait_for_completion(struct completion *x)
+static inline long __sched
+do_wait_for_common(struct completion *x, long timeout, int state)
 {
-	might_sleep();
-
-	spin_lock_irq(&x->wait.lock);
 	if (!x->done) {
 		DECLARE_WAITQUEUE(wait, current);
 
 		wait.flags |= WQ_FLAG_EXCLUSIVE;
 		__add_wait_queue_tail(&x->wait, &wait);
 		do {
-			__set_current_state(TASK_UNINTERRUPTIBLE);
-			spin_unlock_irq(&x->wait.lock);
-			schedule();
-			spin_lock_irq(&x->wait.lock);
-		} while (!x->done);
-		__remove_wait_queue(&x->wait, &wait);
-	}
-	x->done--;
-	spin_unlock_irq(&x->wait.lock);
-}
-EXPORT_SYMBOL(wait_for_completion);
-
-unsigned long fastcall __sched
-wait_for_completion_timeout(struct completion *x, unsigned long timeout)
-{
-	might_sleep();
-
-	spin_lock_irq(&x->wait.lock);
-	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		wait.flags |= WQ_FLAG_EXCLUSIVE;
-		__add_wait_queue_tail(&x->wait, &wait);
-		do {
-			__set_current_state(TASK_UNINTERRUPTIBLE);
+			if (state == TASK_INTERRUPTIBLE &&
+			    signal_pending(current)) {
+				__remove_wait_queue(&x->wait, &wait);
+				return -ERESTARTSYS;
+			}
+			__set_current_state(state);
 			spin_unlock_irq(&x->wait.lock);
 			timeout = schedule_timeout(timeout);
 			spin_lock_irq(&x->wait.lock);
 			if (!timeout) {
 				__remove_wait_queue(&x->wait, &wait);
-				goto out;
+				return timeout;
 			}
 		} while (!x->done);
 		__remove_wait_queue(&x->wait, &wait);
 	}
 	x->done--;
-out:
-	spin_unlock_irq(&x->wait.lock);
 	return timeout;
 }
-EXPORT_SYMBOL(wait_for_completion_timeout);
 
-int fastcall __sched wait_for_completion_interruptible(struct completion *x)
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
 {
-	int ret = 0;
-
 	might_sleep();
 
 	spin_lock_irq(&x->wait.lock);
-	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		wait.flags |= WQ_FLAG_EXCLUSIVE;
-		__add_wait_queue_tail(&x->wait, &wait);
-		do {
-			if (signal_pending(current)) {
-				ret = -ERESTARTSYS;
-				__remove_wait_queue(&x->wait, &wait);
-				goto out;
-			}
-			__set_current_state(TASK_INTERRUPTIBLE);
-			spin_unlock_irq(&x->wait.lock);
-			schedule();
-			spin_lock_irq(&x->wait.lock);
-		} while (!x->done);
-		__remove_wait_queue(&x->wait, &wait);
-	}
-	x->done--;
-out:
+	timeout = do_wait_for_common(x, timeout, state);
 	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
 
-	return ret;
+void fastcall __sched wait_for_completion(struct completion *x)
+{
+	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
 }
-EXPORT_SYMBOL(wait_for_completion_interruptible);
+EXPORT_SYMBOL(wait_for_completion);
 
 unsigned long fastcall __sched
-wait_for_completion_interruptible_timeout(struct completion *x,
-					  unsigned long timeout)
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 {
-	might_sleep();
-
-	spin_lock_irq(&x->wait.lock);
-	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		wait.flags |= WQ_FLAG_EXCLUSIVE;
-		__add_wait_queue_tail(&x->wait, &wait);
-		do {
-			if (signal_pending(current)) {
-				timeout = -ERESTARTSYS;
-				__remove_wait_queue(&x->wait, &wait);
-				goto out;
-			}
-			__set_current_state(TASK_INTERRUPTIBLE);
-			spin_unlock_irq(&x->wait.lock);
-			timeout = schedule_timeout(timeout);
-			spin_lock_irq(&x->wait.lock);
-			if (!timeout) {
-				__remove_wait_queue(&x->wait, &wait);
-				goto out;
-			}
-		} while (!x->done);
-		__remove_wait_queue(&x->wait, &wait);
-	}
-	x->done--;
-out:
-	spin_unlock_irq(&x->wait.lock);
-	return timeout;
+	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
 }
-EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+EXPORT_SYMBOL(wait_for_completion_timeout);
 
-static inline void
-sleep_on_head(wait_queue_head_t *q, wait_queue_t *wait, unsigned long *flags)
+int __sched wait_for_completion_interruptible(struct completion *x)
 {
-	spin_lock_irqsave(&q->lock, *flags);
-	__add_wait_queue(q, wait);
-	spin_unlock(&q->lock);
+	return wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
 }
+EXPORT_SYMBOL(wait_for_completion_interruptible);
 
-static inline void
-sleep_on_tail(wait_queue_head_t *q, wait_queue_t *wait, unsigned long *flags)
+unsigned long fastcall __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+					  unsigned long timeout)
 {
-	spin_lock_irq(&q->lock);
-	__remove_wait_queue(q, wait);
-	spin_unlock_irqrestore(&q->lock, *flags);
+	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
 }
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
 
-void __sched interruptible_sleep_on(wait_queue_head_t *q)
+static long __sched
+sleep_on_common(wait_queue_head_t *q, int state, long timeout)
 {
 	unsigned long flags;
 	wait_queue_t wait;
 
 	init_waitqueue_entry(&wait, current);
 
-	current->state = TASK_INTERRUPTIBLE;
+	__set_current_state(state);
 
-	sleep_on_head(q, &wait, &flags);
-	schedule();
-	sleep_on_tail(q, &wait, &flags);
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, &wait);
+	spin_unlock(&q->lock);
+	timeout = schedule_timeout(timeout);
+	spin_lock_irq(&q->lock);
+	__remove_wait_queue(q, &wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return timeout;
+}
+
+void __sched interruptible_sleep_on(wait_queue_head_t *q)
+{
+	sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 }
 EXPORT_SYMBOL(interruptible_sleep_on);
 
 long __sched
 interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
 {
-	unsigned long flags;
-	wait_queue_t wait;
-
-	init_waitqueue_entry(&wait, current);
-
-	current->state = TASK_INTERRUPTIBLE;
-
-	sleep_on_head(q, &wait, &flags);
-	timeout = schedule_timeout(timeout);
-	sleep_on_tail(q, &wait, &flags);
-
-	return timeout;
+	return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
 }
 EXPORT_SYMBOL(interruptible_sleep_on_timeout);
 
 void __sched sleep_on(wait_queue_head_t *q)
 {
-	unsigned long flags;
-	wait_queue_t wait;
-
-	init_waitqueue_entry(&wait, current);
-
-	current->state = TASK_UNINTERRUPTIBLE;
-
-	sleep_on_head(q, &wait, &flags);
-	schedule();
-	sleep_on_tail(q, &wait, &flags);
+	sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 }
 EXPORT_SYMBOL(sleep_on);
 
 long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
 {
-	unsigned long flags;
-	wait_queue_t wait;
-
-	init_waitqueue_entry(&wait, current);
-
-	current->state = TASK_UNINTERRUPTIBLE;
-
-	sleep_on_head(q, &wait, &flags);
-	timeout = schedule_timeout(timeout);
-	sleep_on_tail(q, &wait, &flags);
-
-	return timeout;
+	return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
 }
 EXPORT_SYMBOL(sleep_on_timeout);
 

Index: linux-2.6-sched-devel/kernel/sched.c
===================================================================
@@ -348,11 +348,6 @@ struct rq {
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 static DEFINE_MUTEX(sched_hotcpu_mutex);
 
-static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
-{
-	rq->curr->sched_class->check_preempt_curr(rq, p);
-}
-
 static inline int cpu_of(struct rq *rq)
 {
 #ifdef CONFIG_SMP

@@ -833,6 +828,18 @@ static int balance_tasks(struct rq *this
 #define sched_class_highest (&rt_sched_class)
 
 /*
+ * Simple devirtualization:
+ * Most tasks are fair tasks. Avoid the overhead of
+ * doing indirect calls for them by checking for the fair case and doing
+ * a direct call. Use only in real fast paths since it generates larger code.
+ */
+#define __CLASS_CALL(class, name, args) \
+	((class) == &fair_sched_class ? \
+		name ## _fair args : (class)->name args)
+#define CLASS_CALL(p, name, args) \
+	__CLASS_CALL((p)->sched_class, name, args)
+
+/*
  * Update delta_exec, delta_fair fields for rq.
  *
  * delta_fair clock advances at a rate inversely proportional to

@@ -893,7 +900,7 @@ static void set_load_weight(struct task_
 static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 {
 	sched_info_queued(p);
-	p->sched_class->enqueue_task(rq, p, wakeup);
+	CLASS_CALL(p, enqueue_task, (rq, p, wakeup));
 	p->se.on_rq = 1;
 }
 

@@ -1402,6 +1409,11 @@ static inline int wake_idle(int cpu, str
 }
 #endif
 
+static void check_preempt_curr(struct rq *rq, struct task_struct *p)
+{
+	CLASS_CALL(rq->curr, check_preempt_curr, (rq, p));
+}
+
 /***
  * try_to_wake_up - wake up a thread
  * @p: the to-be-woken-up thread

@@ -1669,7 +1681,7 @@ void fastcall wake_up_new_task(struct ta
 		 * Let the scheduling class do new task startup
 		 * management (if any):
 		 */
-		p->sched_class->task_new(rq, p);
+		CLASS_CALL(p, task_new, (rq, p));
 		inc_nr_running(p, rq);
 	}
 	check_preempt_curr(rq, p);

@@ -3398,14 +3410,14 @@ pick_next_task(struct rq *rq, struct tas
 	 * the fair class we can call that function directly:
 	 */
 	if (likely(rq->nr_running == rq->cfs.nr_running)) {
-		p = fair_sched_class.pick_next_task(rq);
+		p = pick_next_task_fair(rq);
 		if (likely(p))
 			return p;
 	}
 
 	class = sched_class_highest;
 	for ( ; ; ) {
-		p = class->pick_next_task(rq);
+		p = __CLASS_CALL(class, pick_next_task, (rq));
 		if (p)
 			return p;
 		/*

@@ -3460,7 +3472,7 @@ need_resched_nonpreemptible:
 	if (unlikely(!rq->nr_running))
 		idle_balance(cpu, rq);
 
-	prev->sched_class->put_prev_task(rq, prev);
+	CLASS_CALL(prev, put_prev_task, (rq, prev));
 	next = pick_next_task(rq, prev);
 
 	sched_info_switch(prev, next);

@@ -4436,7 +4448,7 @@ asmlinkage long sys_sched_yield(void)
 	struct rq *rq = this_rq_lock();
 
 	schedstat_inc(rq, yld_count);
-	current->sched_class->yield_task(rq);
+	CLASS_CALL(current, yield_task, (rq));
 
 	/*
 	 * Since we are going to call schedule() anyway, there's

Index: linux-2.6-sched-devel/kernel/sched_fair.c
===================================================================
@@ -814,7 +814,7 @@ static void yield_task_fair(struct rq *r
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
+static void check_preempt_curr_fair(struct rq *rq, struct task_struct *p)
 {
 	struct task_struct *curr = rq->curr;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);

@@ -1050,6 +1050,9 @@ static void set_curr_task_fair(struct rq
 
 /*
  * All the scheduling class methods:
+ *
+ * sched.c knows about the naming conventions of this class.
+ * Always name all methods methodname_fair.
  */
 static const struct sched_class fair_sched_class = {
 	.next			= &idle_sched_class,

@@ -1057,7 +1060,7 @@ static const struct sched_class fair_sch
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
 
-	.check_preempt_curr	= check_preempt_wakeup,
+	.check_preempt_curr	= check_preempt_curr_fair,
 
 	.pick_next_task		= pick_next_task_fair,
 	.put_prev_task		= put_prev_task_fair,

Index: linux-2.6-sched-devel/kernel/sched.c
===================================================================
@@ -74,6 +74,12 @@ unsigned long long __attribute__((weak))
 	return (unsigned long long)jiffies * (1000000000 / HZ);
 }
 
+#ifdef CONFIG_SMP
+#define is_migration_thread(p, rq) ((p) == (rq)->migration_thread)
+#else
+#define is_migration_thread(p, rq) 0
+#endif
+
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],

@@ -6534,12 +6540,25 @@ EXPORT_SYMBOL(__might_sleep);
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
+static void normalize_task(struct rq *rq, struct task_struct *p)
+{
+	int on_rq;
+	update_rq_clock(rq);
+	on_rq = p->se.on_rq;
+	if (on_rq)
+		deactivate_task(rq, p, 0);
+	__setscheduler(rq, p, SCHED_NORMAL, 0);
+	if (on_rq) {
+		activate_task(rq, p, 0);
+		resched_task(rq->curr);
+	}
+}
+
 void normalize_rt_tasks(void)
 {
 	struct task_struct *g, *p;
 	unsigned long flags;
 	struct rq *rq;
-	int on_rq;
 
 	read_lock_irq(&tasklist_lock);
 	do_each_thread(g, p) {

@@ -6563,26 +6582,10 @@ void normalize_rt_tasks(void)
 
 		spin_lock_irqsave(&p->pi_lock, flags);
 		rq = __task_rq_lock(p);
-#ifdef CONFIG_SMP
-		/*
-		 * Do not touch the migration thread:
-		 */
-		if (p == rq->migration_thread)
-			goto out_unlock;
-#endif
 
-		update_rq_clock(rq);
-		on_rq = p->se.on_rq;
-		if (on_rq)
-			deactivate_task(rq, p, 0);
-		__setscheduler(rq, p, SCHED_NORMAL, 0);
-		if (on_rq) {
-			activate_task(rq, p, 0);
-			resched_task(rq->curr);
-		}
-#ifdef CONFIG_SMP
- out_unlock:
-#endif
+		if (!is_migration_thread(p, rq))
+			normalize_task(rq, p);
+
 		__task_rq_unlock(rq);
 		spin_unlock_irqrestore(&p->pi_lock, flags);
 	} while_each_thread(g, p);

Index: linux-2.6-sched-devel/include/linux/sched.h
===================================================================
@@ -1330,6 +1330,7 @@ static inline void put_task_struct(struc
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */
+#define PF_RT_PROTECTED 0x80000000	/* RT task protected from sysrq */
 
 /*
  * Only the _current_ task can read/write to tsk->flags, but other

Index: linux-2.6-sched-devel/kernel/sched.c
===================================================================
@@ -74,12 +74,6 @@ unsigned long long __attribute__((weak))
 	return (unsigned long long)jiffies * (1000000000 / HZ);
 }
 
-#ifdef CONFIG_SMP
-#define is_migration_thread(p, rq) ((p) == (rq)->migration_thread)
-#else
-#define is_migration_thread(p, rq) 0
-#endif
-
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],

@@ -5305,6 +5299,7 @@ migration_call(struct notifier_block *nf
 		kthread_bind(p, cpu);
 		/* Must be high prio: stop_machine expects to yield to it. */
 		rq = task_rq_lock(p, &flags);
+		p->flags |= PF_RT_PROTECTED;
 		__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
 		task_rq_unlock(rq, &flags);
 		cpu_rq(cpu)->migration_thread = p;

@@ -6583,7 +6578,7 @@ void normalize_rt_tasks(void)
 		spin_lock_irqsave(&p->pi_lock, flags);
 		rq = __task_rq_lock(p);
 
-		if (!is_migration_thread(p, rq))
+		if (!(p->flags & PF_RT_PROTECTED))
 			normalize_task(rq, p);
 
 		__task_rq_unlock(rq);

Index: linux-2.6-sched-devel/kernel/softlockup.c
===================================================================
@@ -116,6 +116,7 @@ static int watchdog(void * __bind_cpu)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
 
+	current->flags |= PF_RT_PROTECTED;
 	sched_setscheduler(current, SCHED_FIFO, &param);
 
 	/* initialize timestamp */

Index: linux-2.6-sched-devel/kernel/stop_machine.c
===================================================================
@@ -187,6 +187,7 @@ struct task_struct *__stop_machine_run(i
 	if (!IS_ERR(p)) {
 		struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
 
+		p->flags |= PF_RT_PROTECTED;
 		/* One high-prio thread per cpu.  We'll do this one. */
 		sched_setscheduler(p, SCHED_FIFO, &param);
 		kthread_bind(p, cpu);

Index: linux/kernel/sched.c
===================================================================
@@ -362,15 +362,6 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
-static inline int is_migration_thread(struct task_struct *p, struct rq *rq)
-{
-#ifdef CONFIG_SMP
-	return p == rq->migration_thread;
-#else
-	return 0;
-#endif
-}
-
 /*
  * Update the per-runqueue clock, as finegrained as the platform can give
  * us, but without assuming monotonicity, etc.:

@@ -6557,6 +6548,12 @@ void normalize_rt_tasks(void)
 
 	read_lock_irq(&tasklist_lock);
 	do_each_thread(g, p) {
+		/*
+		 * Only normalize user tasks:
+		 */
+		if (!p->mm)
+			continue;
+
 		p->se.exec_start		= 0;
 #ifdef CONFIG_SCHEDSTATS
 		p->se.wait_start		= 0;

@@ -6578,8 +6575,7 @@ void normalize_rt_tasks(void)
 		spin_lock_irqsave(&p->pi_lock, flags);
 		rq = __task_rq_lock(p);
 
-		if (!is_migration_thread(p, rq))
-			normalize_task(rq, p);
+		normalize_task(rq, p);
 
 		__task_rq_unlock(rq);
 		spin_unlock_irqrestore(&p->pi_lock, flags);

Index: linux-2.6-sched-devel/kernel/sched.c
===================================================================
@@ -6814,8 +6814,6 @@ int sched_group_set_shares(struct task_g
 	if (tg->shares == shares)
 		return 0;
 
-	/* return -EINVAL if the new value is not sane */
-
 	tg->shares = shares;
 	for_each_possible_cpu(i)
 		set_se_shares(tg->se[i], shares);