[v7 PATCH 0/7]: cpuidle/x86/POWER: Cleanup idle power management code in x86, cleanup drivers/cpuidle/cpuidle.c and introduce cpuidle to POWER.

@@ -24,10 +24,6 @@
 DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
 
 DEFINE_MUTEX(cpuidle_lock);
-LIST_HEAD(cpuidle_detected_devices);
-static void (*pm_idle_old)(void);
-
-static int enabled_devices;
 
 #if defined(CONFIG_ARCH_HAS_CPU_IDLE_WAIT)
 static void cpuidle_kick_cpus(void)

@@ -47,7 +43,7 @@ static int __cpuidle_register_device(str
  *
  * NOTE: no locks or semaphores should be used here
  */
-static void cpuidle_idle_call(void)
+void cpuidle_idle_call(void)
 {
 	struct cpuidle_device *dev = __get_cpu_var(cpuidle_devices);
 	struct cpuidle_state *target_state;

@@ -55,13 +51,10 @@ static void cpuidle_idle_call(void)
 
 	/* check if the device is ready */
 	if (!dev || !dev->enabled) {
-		if (pm_idle_old)
-			pm_idle_old();
-		else
 #if defined(CONFIG_ARCH_HAS_DEFAULT_IDLE)
-			default_idle();
+		default_idle();
 #else
-			local_irq_enable();
+		local_irq_enable();
 #endif
 		return;
 	}

@@ -75,7 +68,11 @@ static void cpuidle_idle_call(void)
 	hrtimer_peek_ahead_timers();
 #endif
 	/* ask the governor for the next state */
-	next_state = cpuidle_curr_governor->select(dev);
+	if (dev->state_count > 1)
+		next_state = cpuidle_curr_governor->select(dev);
+	else
+		next_state = 0;
+
 	if (need_resched())
 		return;
 	target_state = &dev->states[next_state];

@@ -96,35 +93,11 @@ static void cpuidle_idle_call(void)
 }
 
 /**
- * cpuidle_install_idle_handler - installs the cpuidle idle loop handler
- */
-void cpuidle_install_idle_handler(void)
-{
-	if (enabled_devices && (pm_idle != cpuidle_idle_call)) {
-		/* Make sure all changes finished before we switch to new idle */
-		smp_wmb();
-		pm_idle = cpuidle_idle_call;
-	}
-}
-
-/**
- * cpuidle_uninstall_idle_handler - uninstalls the cpuidle idle loop handler
- */
-void cpuidle_uninstall_idle_handler(void)
-{
-	if (enabled_devices && pm_idle_old && (pm_idle != pm_idle_old)) {
-		pm_idle = pm_idle_old;
-		cpuidle_kick_cpus();
-	}
-}
-
-/**
  * cpuidle_pause_and_lock - temporarily disables CPUIDLE
  */
 void cpuidle_pause_and_lock(void)
 {
 	mutex_lock(&cpuidle_lock);
-	cpuidle_uninstall_idle_handler();
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_pause_and_lock);

@@ -134,7 +107,6 @@ EXPORT_SYMBOL_GPL(cpuidle_pause_and_lock
  */
 void cpuidle_resume_and_unlock(void)
 {
-	cpuidle_install_idle_handler();
 	mutex_unlock(&cpuidle_lock);
 }
 

@@ -182,7 +154,6 @@ int cpuidle_enable_device(struct cpuidle
 
 	dev->enabled = 1;
 
-	enabled_devices++;
 	return 0;
 
 fail_sysfs:

@@ -213,7 +184,6 @@ void cpuidle_disable_device(struct cpuid
 		cpuidle_curr_governor->disable(dev);
 
 	cpuidle_remove_state_sysfs(dev);
-	enabled_devices--;
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_disable_device);

@@ -266,7 +236,6 @@ static void poll_idle_init(struct cpuidl
  */
 static int __cpuidle_register_device(struct cpuidle_device *dev)
 {
-	int ret;
 	struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu);
 
 	if (!sys_dev)

@@ -274,16 +243,9 @@ static int __cpuidle_register_device(str
 	if (!try_module_get(cpuidle_curr_driver->owner))
 		return -EINVAL;
 
-	init_completion(&dev->kobj_unregister);
-
 	poll_idle_init(dev);
 
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
-	list_add(&dev->device_list, &cpuidle_detected_devices);
-	if ((ret = cpuidle_add_sysfs(sys_dev))) {
-		module_put(cpuidle_curr_driver->owner);
-		return ret;
-	}
 
 	dev->registered = 1;
 	return 0;

@@ -305,7 +267,6 @@ int cpuidle_register_device(struct cpuid
 	}
 
 	cpuidle_enable_device(dev);
-	cpuidle_install_idle_handler();
 
 	mutex_unlock(&cpuidle_lock);
 

@@ -321,8 +282,6 @@ EXPORT_SYMBOL_GPL(cpuidle_register_devic
  */
 void cpuidle_unregister_device(struct cpuidle_device *dev)
 {
-	struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu);
-
 	if (dev->registered == 0)
 		return;
 

@@ -330,9 +289,6 @@ void cpuidle_unregister_device(struct cp
 
 	cpuidle_disable_device(dev);
 
-	cpuidle_remove_sysfs(sys_dev);
-	list_del(&dev->device_list);
-	wait_for_completion(&dev->kobj_unregister);
 	per_cpu(cpuidle_devices, dev->cpu) = NULL;
 
 	cpuidle_resume_and_unlock();

@@ -384,8 +340,6 @@ static int __init cpuidle_init(void)
 {
 	int ret;
 
-	pm_idle_old = pm_idle;
-
 	ret = cpuidle_add_class_sysfs(&cpu_sysdev_class);
 	if (ret)
 		return ret;

@@ -43,16 +43,14 @@ static struct cpuidle_governor * __cpuid
  */
 int cpuidle_switch_governor(struct cpuidle_governor *gov)
 {
-	struct cpuidle_device *dev;
+	int cpu;
 
 	if (gov == cpuidle_curr_governor)
 		return 0;
 
-	cpuidle_uninstall_idle_handler();
-
 	if (cpuidle_curr_governor) {
-		list_for_each_entry(dev, &cpuidle_detected_devices, device_list)
-			cpuidle_disable_device(dev);
+		for_each_online_cpu(cpu)
+			cpuidle_disable_device(per_cpu(cpuidle_devices, cpu));
 		module_put(cpuidle_curr_governor->owner);
 	}
 

@@ -61,9 +59,8 @@ int cpuidle_switch_governor(struct cpuid
 	if (gov) {
 		if (!try_module_get(cpuidle_curr_governor->owner))
 			return -EINVAL;
-		list_for_each_entry(dev, &cpuidle_detected_devices, device_list)
-			cpuidle_enable_device(dev);
-		cpuidle_install_idle_handler();
+		for_each_online_cpu(cpu)
+			cpuidle_enable_device(per_cpu(cpuidle_devices, cpu));
 		printk(KERN_INFO "cpuidle: using governor %s\n", gov->name);
 	}
 

@@ -92,7 +92,6 @@ struct cpuidle_device {
 	struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];
 	struct cpuidle_state	*last_state;
 
-	struct list_head 	device_list;
 	struct kobject		kobj;
 	struct completion	kobj_unregister;
 	void			*governor_data;

@@ -112,6 +111,9 @@ static inline int cpuidle_get_last_resid
 	return dev->last_residency;
 }
 
+extern void cpuidle_idle_call(void);
+extern struct cpuidle_driver *cpuidle_curr_driver;
+
 
 /****************************
  * CPUIDLE DRIVER INTERFACE *

@@ -9,9 +9,7 @@
 
 /* For internal use only */
 extern struct cpuidle_governor *cpuidle_curr_governor;
-extern struct cpuidle_driver *cpuidle_curr_driver;
 extern struct list_head cpuidle_governors;
-extern struct list_head cpuidle_detected_devices;
 extern struct mutex cpuidle_lock;
 extern spinlock_t cpuidle_driver_lock;
 

@@ -27,7 +25,7 @@ extern int cpuidle_add_class_sysfs(struc
 extern void cpuidle_remove_class_sysfs(struct sysdev_class *cls);
 extern int cpuidle_add_state_sysfs(struct cpuidle_device *device);
 extern void cpuidle_remove_state_sysfs(struct cpuidle_device *device);
-extern int cpuidle_add_sysfs(struct sys_device *sysdev);
-extern void cpuidle_remove_sysfs(struct sys_device *sysdev);
+extern int cpuidle_add_sysfs(struct cpuidle_device *device);
+extern void cpuidle_remove_sysfs(struct cpuidle_device *device);
 
 #endif /* __DRIVER_CPUIDLE_H */

@@ -311,6 +311,13 @@ int cpuidle_add_state_sysfs(struct cpuid
 	int i, ret = -ENOMEM;
 	struct cpuidle_state_kobj *kobj;
 
+	init_completion(&device->kobj_unregister);
+
+	ret = cpuidle_add_sysfs(device);
+	if (ret) {
+		module_put(cpuidle_curr_driver->owner);
+		return ret;
+	}
 	/* state statistics */
 	for (i = 0; i < device->state_count; i++) {
 		kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL);

@@ -347,35 +354,32 @@ void cpuidle_remove_state_sysfs(struct c
 
 	for (i = 0; i < device->state_count; i++)
 		cpuidle_free_state_kobj(device, i);
+
+	cpuidle_remove_sysfs(device);
 }
 
 /**
  * cpuidle_add_sysfs - creates a sysfs instance for the target device
- * @sysdev: the target device
+ * @device: the target device
  */
-int cpuidle_add_sysfs(struct sys_device *sysdev)
+int cpuidle_add_sysfs(struct cpuidle_device *device)
 {
-	int cpu = sysdev->id;
-	struct cpuidle_device *dev;
 	int error;
+	struct sys_device *sysdev = get_cpu_sysdev((unsigned long)device->cpu);
 
-	dev = per_cpu(cpuidle_devices, cpu);
-	error = kobject_init_and_add(&dev->kobj, &ktype_cpuidle, &sysdev->kobj,
-				     "cpuidle");
+	error = kobject_init_and_add(&device->kobj, &ktype_cpuidle,
+				&sysdev->kobj, "cpuidle");
 	if (!error)
-		kobject_uevent(&dev->kobj, KOBJ_ADD);
+		kobject_uevent(&device->kobj, KOBJ_ADD);
 	return error;
 }
 
 /**
  * cpuidle_remove_sysfs - deletes a sysfs instance on the target device
- * @sysdev: the target device
+ * @device: the target device
  */
-void cpuidle_remove_sysfs(struct sys_device *sysdev)
+void cpuidle_remove_sysfs(struct cpuidle_device *device)
 {
-	int cpu = sysdev->id;
-	struct cpuidle_device *dev;
-
-	dev = per_cpu(cpuidle_devices, cpu);
-	kobject_put(&dev->kobj);
+	kobject_put(&device->kobj);
+	wait_for_completion(&device->kobj_unregister);
 }

@@ -27,10 +27,6 @@ int cpuidle_register_driver(struct cpuid
 		return -EINVAL;
 
 	spin_lock(&cpuidle_driver_lock);
-	if (cpuidle_curr_driver) {
-		spin_unlock(&cpuidle_driver_lock);
-		return -EBUSY;
-	}
 	cpuidle_curr_driver = drv;
 	spin_unlock(&cpuidle_driver_lock);
 

@@ -22,6 +22,7 @@
 #include "cpuidle.h"
 
 DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
+DEFINE_PER_CPU(struct list_head, cpuidle_devices_list);
 
 DEFINE_MUTEX(cpuidle_lock);
 

@@ -112,6 +113,45 @@ void cpuidle_resume_and_unlock(void)
 
 EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock);
 
+int cpuidle_add_to_list(struct cpuidle_device *dev)
+{
+	int ret, cpu = dev->cpu;
+	struct cpuidle_device *old_dev;
+
+	if (!list_empty(&per_cpu(cpuidle_devices_list, cpu))) {
+		old_dev = list_first_entry(&per_cpu(cpuidle_devices_list, cpu),
+				struct cpuidle_device, idle_list);
+		cpuidle_remove_state_sysfs(old_dev);
+	}
+
+	list_add(&dev->idle_list, &per_cpu(cpuidle_devices_list, cpu));
+	ret = cpuidle_add_state_sysfs(dev);
+	return ret;
+}
+
+void cpuidle_remove_from_list(struct cpuidle_device *dev)
+{
+	struct cpuidle_device *temp_dev;
+	struct list_head *pos;
+	int ret, cpu = dev->cpu;
+
+	list_for_each(pos, &per_cpu(cpuidle_devices_list, cpu)) {
+		temp_dev = container_of(pos, struct cpuidle_device, idle_list);
+		if (dev == temp_dev) {
+			list_del(&temp_dev->idle_list);
+			cpuidle_remove_state_sysfs(temp_dev);
+			break;
+		}
+	}
+
+	if (!list_empty(&per_cpu(cpuidle_devices_list, cpu))) {
+		temp_dev = list_first_entry(&per_cpu(cpuidle_devices_list, cpu),
+					struct cpuidle_device, idle_list);
+		ret = cpuidle_add_state_sysfs(temp_dev);
+	}
+	cpuidle_kick_cpus();
+}
+
 /**
  * cpuidle_enable_device - enables idle PM for a CPU
  * @dev: the CPU

@@ -136,9 +176,6 @@ int cpuidle_enable_device(struct cpuidle
 			return ret;
 	}
 
-	if ((ret = cpuidle_add_state_sysfs(dev)))
-		return ret;
-
 	if (cpuidle_curr_governor->enable &&
 	    (ret = cpuidle_curr_governor->enable(dev)))
 		goto fail_sysfs;

@@ -157,7 +194,7 @@ int cpuidle_enable_device(struct cpuidle
 	return 0;
 
 fail_sysfs:
-	cpuidle_remove_state_sysfs(dev);
+	cpuidle_remove_from_list(dev);
 
 	return ret;
 }

@@ -182,8 +219,6 @@ void cpuidle_disable_device(struct cpuid
 
 	if (cpuidle_curr_governor->disable)
 		cpuidle_curr_governor->disable(dev);
-
-	cpuidle_remove_state_sysfs(dev);
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_disable_device);

@@ -267,6 +302,7 @@ int cpuidle_register_device(struct cpuid
 	}
 
 	cpuidle_enable_device(dev);
+	cpuidle_add_to_list(dev);
 
 	mutex_unlock(&cpuidle_lock);
 

@@ -288,6 +324,7 @@ void cpuidle_unregister_device(struct cp
 	cpuidle_pause_and_lock();
 
 	cpuidle_disable_device(dev);
+	cpuidle_remove_from_list(dev);
 
 	per_cpu(cpuidle_devices, dev->cpu) = NULL;
 

@@ -338,12 +375,15 @@ static inline void latency_notifier_init
  */
 static int __init cpuidle_init(void)
 {
-	int ret;
+	int ret, cpu;
 
 	ret = cpuidle_add_class_sysfs(&cpu_sysdev_class);
 	if (ret)
 		return ret;
 
+	for_each_possible_cpu(cpu)
+		INIT_LIST_HEAD(&per_cpu(cpuidle_devices_list, cpu));
+
 	latency_notifier_init(&cpuidle_latency_notifier);
 
 	return 0;

@@ -92,6 +92,7 @@ struct cpuidle_device {
 	struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];
 	struct cpuidle_state	*last_state;
 
+	struct list_head	idle_list;
 	struct kobject		kobj;
 	struct completion	kobj_unregister;
 	void			*governor_data;

@@ -9,6 +9,7 @@
 #include <linux/pm.h>
 #include <linux/clockchips.h>
 #include <linux/random.h>
+#include <linux/cpuidle.h>
 #include <trace/events/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>

@@ -244,12 +245,6 @@ int sys_vfork(struct pt_regs *regs)
 unsigned long boot_option_idle_override = 0;
 EXPORT_SYMBOL(boot_option_idle_override);
 
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-EXPORT_SYMBOL(pm_idle);
-
 #ifdef CONFIG_X86_32
 /*
  * This halt magic was a workaround for ancient floppy DMA

@@ -329,17 +324,15 @@ static void do_nothing(void *unused)
 }
 
 /*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
+ * cpu_idle_wait - Required while changing idle routine handler on SMP systems.
  *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
+ * Caller must have changed idle routine to the new value before the call. Old
+ * value will not be used by any CPU after the return of this function.
  */
 void cpu_idle_wait(void)
 {
 	smp_mb();
-	/* kick all the CPUs so that they exit out of pm_idle */
+	/* kick all the CPUs so that they exit out of idle loop */
 	smp_call_function(do_nothing, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);

@@ -518,15 +511,59 @@ static void c1e_idle(void)
 		default_idle();
 }
 
+static void (*local_idle)(void);
+DEFINE_PER_CPU(struct cpuidle_device, idle_devices);
+
+struct cpuidle_driver cpuidle_default_driver = {
+	.name =         "cpuidle_default",
+};
+
+static int local_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st)
+{
+	ktime_t t1, t2;
+	s64 diff;
+	int ret;
+
+	t1 = ktime_get();
+	local_idle();
+	t2 = ktime_get();
+
+	diff = ktime_to_us(ktime_sub(t2, t1));
+	if (diff > INT_MAX)
+		diff = INT_MAX;
+	ret = (int) diff;
+
+	return ret;
+}
+
+static int setup_cpuidle_simple(void)
+{
+	struct cpuidle_device *dev;
+	int cpu;
+
+	if (!cpuidle_curr_driver)
+		cpuidle_register_driver(&cpuidle_default_driver);
+
+	for_each_online_cpu(cpu) {
+		dev = &per_cpu(idle_devices, cpu);
+		dev->cpu = cpu;
+		dev->states[0].enter = local_idle_loop;
+		dev->state_count = 1;
+		cpuidle_register_device(dev);
+	}
+	return 0;
+}
+device_initcall(setup_cpuidle_simple);
+
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
-	if (pm_idle == poll_idle && smp_num_siblings > 1) {
+	if (local_idle == poll_idle && smp_num_siblings > 1) {
 		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
 			" performance may degrade.\n");
 	}
 #endif
-	if (pm_idle)
+	if (local_idle)
 		return;
 
 	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {

@@ -534,18 +571,20 @@ void __cpuinit select_idle_routine(const
 		 * One CPU supports mwait => All CPUs supports mwait
 		 */
 		printk(KERN_INFO "using mwait in idle threads.\n");
-		pm_idle = mwait_idle;
+		local_idle = mwait_idle;
 	} else if (check_c1e_idle(c)) {
 		printk(KERN_INFO "using C1E aware idle routine\n");
-		pm_idle = c1e_idle;
+		local_idle = c1e_idle;
 	} else
-		pm_idle = default_idle;
+		local_idle = default_idle;
+
+	return;
 }
 
 void __init init_c1e_mask(void)
 {
 	/* If we're using c1e_idle, we need to allocate c1e_mask. */
-	if (pm_idle == c1e_idle)
+	if (local_idle == c1e_idle)
 		zalloc_cpumask_var(&c1e_mask, GFP_KERNEL);
 }
 

@@ -556,7 +595,7 @@ static int __init idle_setup(char *str)
 
 	if (!strcmp(str, "poll")) {
 		printk("using polling idle threads.\n");
-		pm_idle = poll_idle;
+		local_idle = poll_idle;
 	} else if (!strcmp(str, "mwait"))
 		force_mwait = 1;
 	else if (!strcmp(str, "halt")) {

@@ -567,7 +606,7 @@ static int __init idle_setup(char *str)
 		 * To continue to load the CPU idle driver, don't touch
 		 * the boot_option_idle_override.
 		 */
-		pm_idle = default_idle;
+		local_idle = default_idle;
 		idle_halt = 1;
 		return 0;
 	} else if (!strcmp(str, "nomwait")) {

@@ -40,6 +40,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/kdebug.h>
+#include <linux/cpuidle.h>
 
 #include <asm/pgtable.h>
 #include <asm/system.h>

@@ -113,7 +114,7 @@ void cpu_idle(void)
 			local_irq_disable();
 			/* Don't trace irqs off for idle */
 			stop_critical_timings();
-			pm_idle();
+			cpuidle_idle_call();
 			start_critical_timings();
 		}
 		tick_nohz_restart_sched_tick();

@@ -39,6 +39,7 @@
 #include <linux/io.h>
 #include <linux/ftrace.h>
 #include <linux/dmi.h>
+#include <linux/cpuidle.h>
 
 #include <asm/pgtable.h>
 #include <asm/system.h>

@@ -142,7 +143,7 @@ void cpu_idle(void)
 			enter_idle();
 			/* Don't trace irqs off for idle */
 			stop_critical_timings();
-			pm_idle();
+			cpuidle_idle_call();
 			start_critical_timings();
 			/* In many cases the interrupt that ended idle
 			   has already called exit_idle. But some idle

@@ -2257,6 +2257,38 @@ static struct dmi_system_id __initdata a
 	{ }
 };
 
+DEFINE_PER_CPU(struct cpuidle_device, apm_idle_devices);
+
+struct cpuidle_driver cpuidle_apm_driver = {
+	.name =         "cpuidle_apm",
+};
+
+void __cpuinit setup_cpuidle_apm(void)
+{
+	struct cpuidle_device *dev;
+
+	if (!cpuidle_curr_driver)
+		cpuidle_register_driver(&cpuidle_apm_driver);
+
+	dev = &per_cpu(apm_idle_devices, smp_processor_id());
+	dev->cpu = smp_processor_id();
+	dev->states[0].enter = apm_cpu_idle;
+	dev->state_count = 1;
+	cpuidle_register_device(dev);
+}
+
+void exit_cpuidle_apm(void)
+{
+	struct cpuidle_device *dev;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		dev = &per_cpu(apm_idle_devices, cpu);
+		cpuidle_unregister_device(dev);
+	}
+}
+
+
 /*
  * Just start the APM thread. We do NOT want to do APM BIOS
  * calls from anything but the APM thread, if for no other reason

@@ -2394,8 +2426,7 @@ static int __init apm_init(void)
 	if (HZ != 100)
 		idle_period = (idle_period * HZ) / 100;
 	if (idle_threshold < 100) {
-		original_pm_idle = pm_idle;
-		pm_idle  = apm_cpu_idle;
+		setup_cpuidle_apm();
 		set_pm_idle = 1;
 	}
 

@@ -2407,7 +2438,7 @@ static void __exit apm_exit(void)
 	int error;
 
 	if (set_pm_idle) {
-		pm_idle = original_pm_idle;
+		exit_cpuidle_apm();
 		/*
 		 * We are about to unload the current idle thread pm callback
 		 * (pm_idle), Wait for all processors to update cached/local

@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
+#include <linux/cpuidle.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>

@@ -151,6 +152,25 @@ void __cpuinit xen_enable_syscall(void)
 #endif /* CONFIG_X86_64 */
 }
 
+DEFINE_PER_CPU(struct cpuidle_device, xen_idle_devices);
+struct cpuidle_driver cpuidle_xen_driver = {
+	.name =         "cpuidle_xen",
+};
+
+void __cpuinit setup_cpuidle_xen(void)
+{
+	struct cpuidle_device *dev;
+
+	if (!cpuidle_curr_driver)
+		cpuidle_register_driver(&cpuidle_xen_driver);
+
+	dev = &per_cpu(xen_idle_devices, smp_processor_id());
+	dev->cpu = smp_processor_id();
+	dev->states[0].enter = xen_idle;
+	dev->state_count = 1;
+	cpuidle_register_device(dev);
+}
+
 void __init xen_arch_setup(void)
 {
 	struct physdev_set_iopl set_iopl;

@@ -186,7 +206,7 @@ void __init xen_arch_setup(void)
 	       MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ?
 	       COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE);
 
-	pm_idle = xen_idle;
+	setup_cpuidle_xen();
 
 	paravirt_disable_iospace();
 

@@ -88,6 +88,9 @@ config ARCH_HAS_ILOG2_U64
 	bool
 	default y if 64BIT
 
+config ARCH_HAS_CPU_IDLE_WAIT
+	def_bool y
+
 config GENERIC_HWEIGHT
 	bool
 	default y

@@ -243,6 +246,20 @@ source "kernel/Kconfig.freezer"
 source "arch/powerpc/sysdev/Kconfig"
 source "arch/powerpc/platforms/Kconfig"
 
+menu "Power management options"
+
+source "drivers/cpuidle/Kconfig"
+
+config PSERIES_PROCESSOR_IDLE
+	bool "Idle Power Management Support for pSeries"
+	depends on PPC_PSERIES && CPU_IDLE
+	default y
+	help
+	  Idle Power Management Support for pSeries. This hooks onto cpuidle
+	  infrastructure to help in idle cpu power management.
+
+endmenu
+
 menu "Kernel options"
 
 config HIGHMEM

@@ -546,5 +546,7 @@ extern void account_system_vtime(struct 
 
 extern struct dentry *powerpc_debugfs_root;
 
+void cpu_idle_wait(void);
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_SYSTEM_H */

@@ -102,6 +102,25 @@ void cpu_idle(void)
 	}
 }
 
+static void do_nothing(void *unused)
+{
+}
+
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs come out of the old
+ * idle loop and start using the new idle loop.
+ * Required while changing idle handler on SMP systems.
+ * Caller must have changed idle handler to the new value before the call.
+ */
+void cpu_idle_wait(void)
+{
+	/* Ensure that new value of ppc_md.power_save is set */
+	smp_mb();
+	/* kick all the CPUs so that they exit out of ppc_md.power_save */
+	smp_call_function(do_nothing, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
+
 int powersave_nap;
 
 #ifdef CONFIG_SYSCTL

@@ -75,9 +75,6 @@ EXPORT_SYMBOL(CMO_PageSize);
 
 int fwnmi_active;  /* TRUE if an FWNMI handler is present */
 
-static void pseries_shared_idle_sleep(void);
-static void pseries_dedicated_idle_sleep(void);
-
 static struct device_node *pSeries_mpic_node;
 
 static void pSeries_show_cpuinfo(struct seq_file *m)

@@ -301,18 +298,8 @@ static void __init pSeries_setup_arch(vo
 	pSeries_nvram_init();
 
 	/* Choose an idle loop */
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+	if (firmware_has_feature(FW_FEATURE_SPLPAR))
 		vpa_init(boot_cpuid);
-		if (get_lppaca()->shared_proc) {
-			printk(KERN_DEBUG "Using shared processor idle loop\n");
-			ppc_md.power_save = pseries_shared_idle_sleep;
-		} else {
-			printk(KERN_DEBUG "Using dedicated idle loop\n");
-			ppc_md.power_save = pseries_dedicated_idle_sleep;
-		}
-	} else {
-		printk(KERN_DEBUG "Using default idle loop\n");
-	}
 
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;

@@ -500,80 +487,6 @@ static int __init pSeries_probe(void)
 	return 1;
 }
 
-
-DECLARE_PER_CPU(unsigned long, smt_snooze_delay);
-
-static void pseries_dedicated_idle_sleep(void)
-{ 
-	unsigned int cpu = smp_processor_id();
-	unsigned long start_snooze;
-	unsigned long in_purr, out_purr;
-
-	/*
-	 * Indicate to the HV that we are idle. Now would be
-	 * a good time to find other work to dispatch.
-	 */
-	get_lppaca()->idle = 1;
-	get_lppaca()->donate_dedicated_cpu = 1;
-	in_purr = mfspr(SPRN_PURR);
-
-	/*
-	 * We come in with interrupts disabled, and need_resched()
-	 * has been checked recently.  If we should poll for a little
-	 * while, do so.
-	 */
-	if (__get_cpu_var(smt_snooze_delay)) {
-		start_snooze = get_tb() +
-			__get_cpu_var(smt_snooze_delay) * tb_ticks_per_usec;
-		local_irq_enable();
-		set_thread_flag(TIF_POLLING_NRFLAG);
-
-		while (get_tb() < start_snooze) {
-			if (need_resched() || cpu_is_offline(cpu))
-				goto out;
-			ppc64_runlatch_off();
-			HMT_low();
-			HMT_very_low();
-		}
-
-		HMT_medium();
-		clear_thread_flag(TIF_POLLING_NRFLAG);
-		smp_mb();
-		local_irq_disable();
-		if (need_resched() || cpu_is_offline(cpu))
-			goto out;
-	}
-
-	cede_processor();
-
-out:
-	HMT_medium();
-	out_purr = mfspr(SPRN_PURR);
-	get_lppaca()->wait_state_cycles += out_purr - in_purr;
-	get_lppaca()->donate_dedicated_cpu = 0;
-	get_lppaca()->idle = 0;
-}
-
-static void pseries_shared_idle_sleep(void)
-{
-	/*
-	 * Indicate to the HV that we are idle. Now would be
-	 * a good time to find other work to dispatch.
-	 */
-	get_lppaca()->idle = 1;
-
-	/*
-	 * Yield the processor to the hypervisor.  We return if
-	 * an external interrupt occurs (which are driven prior
-	 * to returning here) or if a prod occurs from another
-	 * processor. When returning here, external interrupts
-	 * are enabled.
-	 */
-	cede_processor();
-
-	get_lppaca()->idle = 0;
-}
-
 static int pSeries_pci_probe_mode(struct pci_bus *bus)
 {
 	if (firmware_has_feature(FW_FEATURE_LPAR))

@@ -25,6 +25,7 @@
 #include <linux/cpu.h>
 #include <linux/sysctl.h>
 #include <linux/tick.h>
+#include <linux/cpuidle.h>
 
 #include <asm/system.h>
 #include <asm/processor.h>

@@ -60,35 +61,26 @@ void cpu_idle(void)
 		while (!need_resched() && !cpu_should_die()) {
 			ppc64_runlatch_off();
 
-			if (ppc_md.power_save) {
-				clear_thread_flag(TIF_POLLING_NRFLAG);
-				/*
-				 * smp_mb is so clearing of TIF_POLLING_NRFLAG
-				 * is ordered w.r.t. need_resched() test.
-				 */
-				smp_mb();
-				local_irq_disable();
-
-				/* Don't trace irqs off for idle */
-				stop_critical_timings();
-
-				/* check again after disabling irqs */
-				if (!need_resched() && !cpu_should_die())
-					ppc_md.power_save();
-
-				start_critical_timings();
-
-				local_irq_enable();
-				set_thread_flag(TIF_POLLING_NRFLAG);
-
-			} else {
-				/*
-				 * Go into low thread priority and possibly
-				 * low power mode.
-				 */
-				HMT_low();
-				HMT_very_low();
-			}
+			clear_thread_flag(TIF_POLLING_NRFLAG);
+			/*
+			 * smp_mb is so clearing of TIF_POLLING_NRFLAG
+			 * is ordered w.r.t. need_resched() test.
+			 */
+			smp_mb();
+			local_irq_disable();
+
+			/* Don't trace irqs off for idle */
+			stop_critical_timings();
+
+			/* check again after disabling irqs */
+			if (!need_resched() && !cpu_should_die())
+				cpuidle_idle_call();
+
+			start_critical_timings();
+
+			local_irq_enable();
+			set_thread_flag(TIF_POLLING_NRFLAG);
+
 		}
 
 		HMT_medium();

@@ -91,6 +91,9 @@ config ARCH_HAS_ILOG2_U64
 config ARCH_HAS_CPU_IDLE_WAIT
 	def_bool y
 
+config ARCH_HAS_DEFAULT_IDLE
+	def_bool y
+
 config GENERIC_HWEIGHT
 	bool
 	default y

@@ -218,6 +218,7 @@ extern unsigned long klimit;
 extern void *alloc_maybe_bootmem(size_t size, gfp_t mask);
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
+extern void default_idle(void);
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
 
 /*

@@ -113,6 +113,12 @@ void cpu_idle_wait(void)
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
+void default_idle(void)
+{
+	HMT_low();
+	HMT_very_low();
+}
+
 int powersave_nap;
 
 #ifdef CONFIG_SYSCTL

@@ -26,3 +26,4 @@ obj-$(CONFIG_HCALL_STATS)	+= hvCall_inst
 obj-$(CONFIG_PHYP_DUMP)	+= phyp_dump.o
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_DTL)		+= dtl.o
+obj-$(CONFIG_PSERIES_PROCESSOR_IDLE)	+= processor_idle.o

@@ -10,6 +10,8 @@
 #ifndef _PSERIES_PSERIES_H
 #define _PSERIES_PSERIES_H
 
+#include <linux/cpuidle.h>
+
 extern void __init fw_feature_init(const char *hypertas, unsigned long len);
 
 struct pt_regs;

@@ -40,4 +42,10 @@ extern unsigned long rtas_poweron_auto;
 
 extern void find_udbg_vterm(void);
 
+DECLARE_PER_CPU(unsigned long, smt_snooze_delay);
+
+#ifdef CONFIG_PSERIES_PROCESSOR_IDLE
+extern struct cpuidle_driver pseries_idle_driver;
+#endif
+
 #endif /* _PSERIES_PSERIES_H */

@@ -0,0 +1,208 @@
+/*
+ *  processor_idle - idle state cpuidle driver.
+ *  Adapted from drivers/acpi/processor_idle.c
+ *
+ *  Arun R Bharadwaj <arun@linux.vnet.ibm.com>
+ *
+ *  Copyright (C) 2009 IBM Corporation.
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or (at
+ *  your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <linux/cpuidle.h>
+
+#include <asm/paca.h>
+#include <asm/reg.h>
+#include <asm/system.h>
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+
+#include "plpar_wrappers.h"
+#include "pseries.h"
+
+MODULE_AUTHOR("Arun R Bharadwaj");
+MODULE_DESCRIPTION("pSeries Idle State Driver");
+MODULE_LICENSE("GPL");
+
+struct cpuidle_driver pseries_idle_driver = {
+	.name =		"pseries_idle",
+	.owner =	THIS_MODULE,
+};
+
+DEFINE_PER_CPU(struct cpuidle_device, pseries_dev);
+
+#define IDLE_STATE_COUNT	2
+
+/* pSeries Idle state Flags */
+#define	PSERIES_DEDICATED_SNOOZE	(0x01)
+#define	PSERIES_DEDICATED_CEDE		(0x02)
+#define	PSERIES_SHARED_CEDE		(0x03)
+
+static int pseries_idle_init(struct cpuidle_device *dev)
+{
+	return cpuidle_register_device(dev);
+}
+
+static void shared_cede_loop(void)
+{
+	get_lppaca()->idle = 1;
+	cede_processor();
+	get_lppaca()->idle = 0;
+}
+
+static void dedicated_snooze_loop(void)
+{
+	local_irq_enable();
+	set_thread_flag(TIF_POLLING_NRFLAG);
+	while (!need_resched()) {
+		ppc64_runlatch_off();
+		HMT_low();
+		HMT_very_low();
+	}
+	HMT_medium();
+	clear_thread_flag(TIF_POLLING_NRFLAG);
+	smp_mb();
+	local_irq_disable();
+}
+
+static void dedicated_cede_loop(void)
+{
+	ppc64_runlatch_off();
+	HMT_medium();
+	cede_processor();
+}
+
+static int pseries_cpuidle_loop(struct cpuidle_device *dev,
+				struct cpuidle_state *st)
+{
+	ktime_t t1, t2;
+	s64 diff;
+	int ret;
+	unsigned long in_purr, out_purr;
+
+	get_lppaca()->idle = 1;
+	get_lppaca()->donate_dedicated_cpu = 1;
+	in_purr = mfspr(SPRN_PURR);
+
+	t1 = ktime_get();
+
+	if (st->flags & PSERIES_SHARED_CEDE)
+		shared_cede_loop();
+	else if (st->flags & PSERIES_DEDICATED_SNOOZE)
+		dedicated_snooze_loop();
+	else
+		dedicated_cede_loop();
+
+	t2 = ktime_get();
+	diff = ktime_to_us(ktime_sub(t2, t1));
+	if (diff > INT_MAX)
+		diff = INT_MAX;
+
+	ret = (int) diff;
+
+	out_purr = mfspr(SPRN_PURR);
+	get_lppaca()->wait_state_cycles += out_purr - in_purr;
+	get_lppaca()->donate_dedicated_cpu = 0;
+	get_lppaca()->idle = 0;
+
+	return ret;
+}
+
+static int pseries_setup_cpuidle(struct cpuidle_device *dev, int cpu)
+{
+	int i;
+	struct cpuidle_state *state;
+
+	dev->cpu = cpu;
+
+	if (get_lppaca()->shared_proc) {
+		state = &dev->states[0];
+		snprintf(state->name, CPUIDLE_NAME_LEN, "IDLE");
+		state->enter = pseries_cpuidle_loop;
+		strncpy(state->desc, "shared_cede", CPUIDLE_DESC_LEN);
+		state->flags = PSERIES_SHARED_CEDE;
+		state->exit_latency = 0;
+		state->target_residency = 0;
+		return 0;
+	}
+
+	for (i = 0; i < IDLE_STATE_COUNT; i++) {
+		state = &dev->states[i];
+
+		snprintf(state->name, CPUIDLE_NAME_LEN, "CEDE%d", i);
+		state->enter = pseries_cpuidle_loop;
+
+		switch (i) {
+		case 0:
+			strncpy(state->desc, "snooze", CPUIDLE_DESC_LEN);
+			state->flags = PSERIES_DEDICATED_SNOOZE;
+			state->exit_latency = 0;
+			state->target_residency = 0;
+			break;
+
+		case 1:
+			strncpy(state->desc, "cede", CPUIDLE_DESC_LEN);
+			state->flags = PSERIES_DEDICATED_CEDE;
+			state->exit_latency = 1;
+			state->target_residency =
+					__get_cpu_var(smt_snooze_delay);
+			break;
+		}
+	}
+	dev->state_count = IDLE_STATE_COUNT;
+
+	return 0;
+}
+
+void update_smt_snooze_delay(int snooze)
+{
+	int cpu;
+	for_each_online_cpu(cpu)
+		per_cpu(pseries_dev, cpu).states[0].target_residency = snooze;
+}
+
+static int __init pseries_processor_idle_init(void)
+{
+	int cpu;
+	int result = cpuidle_register_driver(&pseries_idle_driver);
+
+	if (result < 0)
+		return result;
+
+	printk(KERN_DEBUG "pSeries idle driver registered\n");
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		printk(KERN_DEBUG "Using default idle\n");
+		return 0;
+	}
+
+	for_each_online_cpu(cpu) {
+		pseries_setup_cpuidle(&per_cpu(pseries_dev, cpu), cpu);
+		pseries_idle_init(&per_cpu(pseries_dev, cpu));
+	}
+
+	printk(KERN_DEBUG "Using cpuidle idle loop\n");
+
+	return 0;
+}
+
+late_initcall(pseries_processor_idle_init);