1 files changed, 437 insertions, 195 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index fdc432f18022..c7876e9e024f 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -8,10 +8,13 @@
  * This code is licenced under the GPL.
  */
 
+#include "linux/percpu-defs.h"
 #include <linux/clockchips.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/sched/idle.h>
 #include <linux/notifier.h>
 #include <linux/pm_qos.h>
 #include <linux/cpu.h>
@@ -19,6 +22,10 @@
 #include <linux/ktime.h>
 #include <linux/hrtimer.h>
 #include <linux/module.h>
+#include <linux/suspend.h>
+#include <linux/tick.h>
+#include <linux/mmu_context.h>
+#include <linux/context_tracking.h>
 #include <trace/events/power.h>
 
 #include "cpuidle.h"
@@ -42,7 +49,11 @@ void disable_cpuidle(void)
 	off = 1;
 }
 
-static int __cpuidle_register_device(struct cpuidle_device *dev);
+bool cpuidle_not_available(struct cpuidle_driver *drv,
+			   struct cpuidle_device *dev)
+{
+	return off || !initialized || !drv || !dev || !dev->enabled;
+}
 
 /**
  * cpuidle_play_dead - cpu off-lining
@@ -58,115 +69,395 @@ int cpuidle_play_dead(void)
 	if (!drv)
 		return -ENODEV;
 
-	/* Find lowest-power state that supports long-term idle */
-	for (i = drv->state_count - 1; i >= CPUIDLE_DRIVER_STATE_START; i--)
+	for (i = drv->state_count - 1; i >= 0; i--) {
 		if (drv->states[i].enter_dead)
-			return drv->states[i].enter_dead(dev, i);
+			drv->states[i].enter_dead(dev, i);
+	}
 
+	/*
+	 * If :enter_dead() is successful, it will never return, so reaching
+	 * here means that all of them failed above or were not present.
+	 */
 	return -ENODEV;
 }
 
+static int find_deepest_state(struct cpuidle_driver *drv,
+			      struct cpuidle_device *dev,
+			      u64 max_latency_ns,
+			      unsigned int forbidden_flags,
+			      bool s2idle)
+{
+	u64 latency_req = 0;
+	int i, ret = 0;
+
+	for (i = 1; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
+
+		if (dev->states_usage[i].disable ||
+		    s->exit_latency_ns <= latency_req ||
+		    s->exit_latency_ns > max_latency_ns ||
+		    (s->flags & forbidden_flags) ||
+		    (s2idle && !s->enter_s2idle))
+			continue;
+
+		latency_req = s->exit_latency_ns;
+		ret = i;
+	}
+	return ret;
+}
+
+/**
+ * cpuidle_use_deepest_state - Set/unset governor override mode.
+ * @latency_limit_ns: Idle state exit latency limit (or no override if 0).
+ *
+ * If @latency_limit_ns is nonzero, set the current CPU to use the deepest idle
+ * state with exit latency within @latency_limit_ns (override governors going
+ * forward), or do not override governors if it is zero.
+ */
+void cpuidle_use_deepest_state(u64 latency_limit_ns)
+{
+	struct cpuidle_device *dev;
+
+	preempt_disable();
+	dev = cpuidle_get_device();
+	if (dev)
+		dev->forced_idle_latency_limit_ns = latency_limit_ns;
+	preempt_enable();
+}
+
+/**
+ * cpuidle_find_deepest_state - Find the deepest available idle state.
+ * @drv: cpuidle driver for the given CPU.
+ * @dev: cpuidle device for the given CPU.
+ * @latency_limit_ns: Idle state exit latency limit
+ *
+ * Return: the index of the deepest available idle state.
+ */
+int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
+			       struct cpuidle_device *dev,
+			       u64 latency_limit_ns)
+{
+	return find_deepest_state(drv, dev, latency_limit_ns, 0, false);
+}
+
+#ifdef CONFIG_SUSPEND
+static noinstr void enter_s2idle_proper(struct cpuidle_driver *drv,
+					 struct cpuidle_device *dev, int index)
+{
+	struct cpuidle_state *target_state = &drv->states[index];
+	ktime_t time_start, time_end;
+
+	instrumentation_begin();
+
+	time_start = ns_to_ktime(local_clock_noinstr());
+
+	tick_freeze();
+	/*
+	 * The state used here cannot be a "coupled" one, because the "coupled"
+	 * cpuidle mechanism enables interrupts and doing that with timekeeping
+	 * suspended is generally unsafe.
+	 */
+	stop_critical_timings();
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
+		ct_cpuidle_enter();
+		/* Annotate away the indirect call */
+		instrumentation_begin();
+	}
+	target_state->enter_s2idle(dev, drv, index);
+	if (WARN_ON_ONCE(!irqs_disabled()))
+		raw_local_irq_disable();
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
+		instrumentation_end();
+		ct_cpuidle_exit();
+	}
+	tick_unfreeze();
+	start_critical_timings();
+
+	time_end = ns_to_ktime(local_clock_noinstr());
+
+	dev->states_usage[index].s2idle_time += ktime_us_delta(time_end, time_start);
+	dev->states_usage[index].s2idle_usage++;
+	instrumentation_end();
+}
+
+/**
+ * cpuidle_enter_s2idle - Enter an idle state suitable for suspend-to-idle.
+ * @drv: cpuidle driver for the given CPU.
+ * @dev: cpuidle device for the given CPU.
+ * @latency_limit_ns: Idle state exit latency limit
+ *
+ * If there are states with the ->enter_s2idle callback, find the deepest of
+ * them and enter it with frozen tick.
+ */
+int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+			 u64 latency_limit_ns)
+{
+	int index;
+
+	/*
+	 * Find the deepest state with ->enter_s2idle present that meets the
+	 * specified latency limit, which guarantees that interrupts won't be
+	 * enabled when it exits and allows the tick to be frozen safely.
+	 */
+	index = find_deepest_state(drv, dev, latency_limit_ns, 0, true);
+	if (index > 0) {
+		enter_s2idle_proper(drv, dev, index);
+		local_irq_enable();
+	}
+	return index;
+}
+#endif /* CONFIG_SUSPEND */
+
 /**
  * cpuidle_enter_state - enter the state and update stats
  * @dev: cpuidle device for this cpu
  * @drv: cpuidle driver for this cpu
- * @next_state: index into drv->states of the state to enter
+ * @index: index into the states table in @drv of the state to enter
  */
-int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
-			int index)
+noinstr int cpuidle_enter_state(struct cpuidle_device *dev,
+				 struct cpuidle_driver *drv,
+				 int index)
 {
 	int entered_state;
 
 	struct cpuidle_state *target_state = &drv->states[index];
+	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
 	ktime_t time_start, time_end;
-	s64 diff;
 
-	time_start = ktime_get();
+	instrumentation_begin();
+
+	/*
+	 * Tell the time framework to switch to a broadcast timer because our
+	 * local timer will be shut down.  If a local timer is used from another
+	 * CPU as a broadcast timer, this call may fail if it is not available.
+	 */
+	if (broadcast && tick_broadcast_enter()) {
+		index = find_deepest_state(drv, dev, target_state->exit_latency_ns,
+					   CPUIDLE_FLAG_TIMER_STOP, false);
+
+		target_state = &drv->states[index];
+		broadcast = false;
+	}
+
+	if (target_state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
+		leave_mm();
+
+	/* Take note of the planned idle state. */
+	sched_idle_set_state(target_state);
+
+	trace_cpu_idle(index, dev->cpu);
+	time_start = ns_to_ktime(local_clock_noinstr());
 
+	stop_critical_timings();
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
+		ct_cpuidle_enter();
+		/* Annotate away the indirect call */
+		instrumentation_begin();
+	}
+
+	/*
+	 * NOTE!!
+	 *
+	 * For cpuidle_state::enter() methods that do *NOT* set
+	 * CPUIDLE_FLAG_RCU_IDLE RCU will be disabled here and these functions
+	 * must be marked either noinstr or __cpuidle.
+	 *
+	 * For cpuidle_state::enter() methods that *DO* set
+	 * CPUIDLE_FLAG_RCU_IDLE this isn't required, but they must mark the
+	 * function calling ct_cpuidle_enter() as noinstr/__cpuidle and all
+	 * functions called within the RCU-idle region.
+	 */
 	entered_state = target_state->enter(dev, drv, index);
 
-	time_end = ktime_get();
+	if (WARN_ONCE(!irqs_disabled(), "%ps leaked IRQ state", target_state->enter))
+		raw_local_irq_disable();
+
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
+		instrumentation_end();
+		ct_cpuidle_exit();
+	}
+	start_critical_timings();
 
-	local_irq_enable();
+	sched_clock_idle_wakeup_event();
+	time_end = ns_to_ktime(local_clock_noinstr());
+	trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
 
-	diff = ktime_to_us(ktime_sub(time_end, time_start));
-	if (diff > INT_MAX)
-		diff = INT_MAX;
+	/* The cpu is no longer idle or about to enter idle. */
+	sched_idle_set_state(NULL);
 
-	dev->last_residency = (int) diff;
+	if (broadcast)
+		tick_broadcast_exit();
+
+	if (!cpuidle_state_is_coupled(drv, index))
+		local_irq_enable();
 
 	if (entered_state >= 0) {
-		/* Update cpuidle counters */
-		/* This can be moved to within driver enter routine
+		s64 diff, delay = drv->states[entered_state].exit_latency_ns;
+		int i;
+
+		/*
+		 * Update cpuidle counters
+		 * This can be moved to within driver enter routine,
 		 * but that results in multiple copies of same code.
 		 */
-		dev->states_usage[entered_state].time += dev->last_residency;
+		diff = ktime_sub(time_end, time_start);
+
+		dev->last_residency_ns = diff;
+		dev->states_usage[entered_state].time_ns += diff;
 		dev->states_usage[entered_state].usage++;
+
+		if (diff < drv->states[entered_state].target_residency_ns) {
+			for (i = entered_state - 1; i >= 0; i--) {
+				if (dev->states_usage[i].disable)
+					continue;
+
+				/* Shallower states are enabled, so update. */
+				dev->states_usage[entered_state].above++;
+				trace_cpu_idle_miss(dev->cpu, entered_state, false);
+				break;
+			}
+		} else if (diff > delay) {
+			for (i = entered_state + 1; i < drv->state_count; i++) {
+				if (dev->states_usage[i].disable)
+					continue;
+
+				/*
+				 * Update if a deeper state would have been a
+				 * better match for the observed idle duration.
+				 */
+				if (diff - delay >= drv->states[i].target_residency_ns) {
+					dev->states_usage[entered_state].below++;
+					trace_cpu_idle_miss(dev->cpu, entered_state, true);
+				}
+
+				break;
+			}
+		}
 	} else {
-		dev->last_residency = 0;
+		dev->last_residency_ns = 0;
+		dev->states_usage[index].rejected++;
 	}
 
+	instrumentation_end();
+
 	return entered_state;
 }
 
 /**
- * cpuidle_idle_call - the main idle loop
+ * cpuidle_select - ask the cpuidle framework to choose an idle state
+ *
+ * @drv: the cpuidle driver
+ * @dev: the cpuidle device
+ * @stop_tick: indication on whether or not to stop the tick
+ *
+ * Returns the index of the idle state.  The return value must not be negative.
  *
- * NOTE: no locks or semaphores should be used here
- * return non-zero on failure
+ * The memory location pointed to by @stop_tick is expected to be written the
+ * 'false' boolean value if the scheduler tick should not be stopped before
+ * entering the returned state.
  */
-int cpuidle_idle_call(void)
+int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+		   bool *stop_tick)
 {
-	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
-	struct cpuidle_driver *drv;
-	int next_state, entered_state;
+	return cpuidle_curr_governor->select(drv, dev, stop_tick);
+}
 
-	if (off)
-		return -ENODEV;
+/**
+ * cpuidle_enter - enter into the specified idle state
+ *
+ * @drv:   the cpuidle driver tied with the cpu
+ * @dev:   the cpuidle device
+ * @index: the index in the idle state table
+ *
+ * Returns the index in the idle state, < 0 in case of error.
+ * The error code depends on the backend driver
+ */
+int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+		  int index)
+{
+	int ret = 0;
+
+	/*
+	 * Store the next hrtimer, which becomes either next tick or the next
+	 * timer event, whatever expires first. Additionally, to make this data
+	 * useful for consumers outside cpuidle, we rely on that the governor's
+	 * ->select() callback have decided, whether to stop the tick or not.
+	 */
+	WRITE_ONCE(dev->next_hrtimer, tick_nohz_get_next_hrtimer());
+
+	if (cpuidle_state_is_coupled(drv, index))
+		ret = cpuidle_enter_state_coupled(dev, drv, index);
+	else
+		ret = cpuidle_enter_state(dev, drv, index);
 
-	if (!initialized)
-		return -ENODEV;
+	WRITE_ONCE(dev->next_hrtimer, 0);
+	return ret;
+}
 
-	/* check if the device is ready */
-	if (!dev || !dev->enabled)
-		return -EBUSY;
+/**
+ * cpuidle_reflect - tell the underlying governor what was the state
+ * we were in
+ *
+ * @dev  : the cpuidle device
+ * @index: the index in the idle state table
+ *
+ */
+void cpuidle_reflect(struct cpuidle_device *dev, int index)
+{
+	if (cpuidle_curr_governor->reflect && index >= 0)
+		cpuidle_curr_governor->reflect(dev, index);
+}
 
-	drv = cpuidle_get_cpu_driver(dev);
+/*
+ * Min polling interval of 10usec is a guess. It is assuming that
+ * for most users, the time for a single ping-pong workload like
+ * perf bench pipe would generally complete within 10usec but
+ * this is hardware dependent. Actual time can be estimated with
+ *
+ * perf bench sched pipe -l 10000
+ *
+ * Run multiple times to avoid cpufreq effects.
+ */
+#define CPUIDLE_POLL_MIN 10000
+#define CPUIDLE_POLL_MAX (TICK_NSEC / 16)
 
-	/* ask the governor for the next state */
-	next_state = cpuidle_curr_governor->select(drv, dev);
-	if (need_resched()) {
-		dev->last_residency = 0;
-		/* give the governor an opportunity to reflect on the outcome */
-		if (cpuidle_curr_governor->reflect)
-			cpuidle_curr_governor->reflect(dev, next_state);
-		local_irq_enable();
-		return 0;
-	}
+/**
+ * cpuidle_poll_time - return amount of time to poll for,
+ * governors can override dev->poll_limit_ns if necessary
+ *
+ * @drv:   the cpuidle driver tied with the cpu
+ * @dev:   the cpuidle device
+ *
+ */
+__cpuidle u64 cpuidle_poll_time(struct cpuidle_driver *drv,
+		      struct cpuidle_device *dev)
+{
+	int i;
+	u64 limit_ns;
 
-	trace_cpu_idle_rcuidle(next_state, dev->cpu);
+	BUILD_BUG_ON(CPUIDLE_POLL_MIN > CPUIDLE_POLL_MAX);
 
-	if (drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP)
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
-				   &dev->cpu);
+	if (dev->poll_limit_ns)
+		return dev->poll_limit_ns;
 
-	if (cpuidle_state_is_coupled(dev, drv, next_state))
-		entered_state = cpuidle_enter_state_coupled(dev, drv,
-							    next_state);
-	else
-		entered_state = cpuidle_enter_state(dev, drv, next_state);
+	limit_ns = CPUIDLE_POLL_MAX;
+	for (i = 1; i < drv->state_count; i++) {
+		u64 state_limit;
 
-	if (drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP)
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
-				   &dev->cpu);
+		if (dev->states_usage[i].disable)
+			continue;
 
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
+		state_limit = drv->states[i].target_residency_ns;
+		if (state_limit < CPUIDLE_POLL_MIN)
+			continue;
 
-	/* give the governor an opportunity to reflect on the outcome */
-	if (cpuidle_curr_governor->reflect)
-		cpuidle_curr_governor->reflect(dev, entered_state);
+		limit_ns = min_t(u64, state_limit, CPUIDLE_POLL_MAX);
+		break;
+	}
 
-	return 0;
+	dev->poll_limit_ns = limit_ns;
+
+	return dev->poll_limit_ns;
 }
 
 /**
@@ -188,8 +479,14 @@ void cpuidle_uninstall_idle_handler(void)
 {
 	if (enabled_devices) {
 		initialized = 0;
-		kick_all_cpus_sync();
+		wake_up_all_idle_cpus();
 	}
+
+	/*
+	 * Make sure external observers (such as the scheduler)
+	 * are done looking at pointed idle states.
+	 */
+	synchronize_rcu();
 }
 
 /**
@@ -230,45 +527,6 @@ void cpuidle_resume(void)
 	mutex_unlock(&cpuidle_lock);
 }
 
-#ifdef CONFIG_ARCH_HAS_CPU_RELAX
-static int poll_idle(struct cpuidle_device *dev,
-		struct cpuidle_driver *drv, int index)
-{
-	ktime_t	t1, t2;
-	s64 diff;
-
-	t1 = ktime_get();
-	local_irq_enable();
-	while (!need_resched())
-		cpu_relax();
-
-	t2 = ktime_get();
-	diff = ktime_to_us(ktime_sub(t2, t1));
-	if (diff > INT_MAX)
-		diff = INT_MAX;
-
-	dev->last_residency = (int) diff;
-
-	return index;
-}
-
-static void poll_idle_init(struct cpuidle_driver *drv)
-{
-	struct cpuidle_state *state = &drv->states[0];
-
-	snprintf(state->name, CPUIDLE_NAME_LEN, "POLL");
-	snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE");
-	state->exit_latency = 0;
-	state->target_residency = 0;
-	state->power_usage = -1;
-	state->flags = 0;
-	state->enter = poll_idle;
-	state->disabled = false;
-}
-#else
-static void poll_idle_init(struct cpuidle_driver *drv) {}
-#endif /* CONFIG_ARCH_HAS_CPU_RELAX */
-
 /**
  * cpuidle_enable_device - enables idle PM for a CPU
  * @dev: the CPU
@@ -278,7 +536,7 @@ static void poll_idle_init(struct cpuidle_driver *drv) {}
  */
 int cpuidle_enable_device(struct cpuidle_device *dev)
 {
-	int ret, i;
+	int ret;
 	struct cpuidle_driver *drv;
 
 	if (!dev)
@@ -287,35 +545,26 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 	if (dev->enabled)
 		return 0;
 
-	drv = cpuidle_get_cpu_driver(dev);
-
-	if (!drv || !cpuidle_curr_governor)
+	if (!cpuidle_curr_governor)
 		return -EIO;
 
-	if (!dev->state_count)
-		dev->state_count = drv->state_count;
+	drv = cpuidle_get_cpu_driver(dev);
 
-	if (dev->registered == 0) {
-		ret = __cpuidle_register_device(dev);
-		if (ret)
-			return ret;
-	}
+	if (!drv)
+		return -EIO;
 
-	poll_idle_init(drv);
+	if (!dev->registered)
+		return -EINVAL;
 
 	ret = cpuidle_add_device_sysfs(dev);
 	if (ret)
 		return ret;
 
-	if (cpuidle_curr_governor->enable &&
-	    (ret = cpuidle_curr_governor->enable(drv, dev)))
-		goto fail_sysfs;
-
-	for (i = 0; i < dev->state_count; i++) {
-		dev->states_usage[i].usage = 0;
-		dev->states_usage[i].time = 0;
+	if (cpuidle_curr_governor->enable) {
+		ret = cpuidle_curr_governor->enable(drv, dev);
+		if (ret)
+			goto fail_sysfs;
 	}
-	dev->last_residency = 0;
 
 	smp_wmb();
 
@@ -360,6 +609,24 @@ void cpuidle_disable_device(struct cpuidle_device *dev)
 
 EXPORT_SYMBOL_GPL(cpuidle_disable_device);
 
+static void __cpuidle_unregister_device(struct cpuidle_device *dev)
+{
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+
+	list_del(&dev->device_list);
+	per_cpu(cpuidle_devices, dev->cpu) = NULL;
+	module_put(drv->owner);
+
+	dev->registered = 0;
+}
+
+static void __cpuidle_device_init(struct cpuidle_device *dev)
+{
+	memset(dev->states_usage, 0, sizeof(dev->states_usage));
+	dev->last_residency_ns = 0;
+	dev->next_hrtimer = 0;
+}
+
 /**
  * __cpuidle_register_device - internal register function called before register
  * and enable routines
@@ -369,31 +636,35 @@ EXPORT_SYMBOL_GPL(cpuidle_disable_device);
  */
 static int __cpuidle_register_device(struct cpuidle_device *dev)
 {
-	int ret;
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	unsigned int cpu = dev->cpu;
+	int i, ret;
+
+	if (per_cpu(cpuidle_devices, cpu)) {
+		pr_info("CPU%d: cpuidle device already registered\n", cpu);
+		return -EEXIST;
+	}
 
 	if (!try_module_get(drv->owner))
 		return -EINVAL;
 
-	per_cpu(cpuidle_devices, dev->cpu) = dev;
+	for (i = 0; i < drv->state_count; i++) {
+		if (drv->states[i].flags & CPUIDLE_FLAG_UNUSABLE)
+			dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER;
+
+		if (drv->states[i].flags & CPUIDLE_FLAG_OFF)
+			dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_USER;
+	}
+
+	per_cpu(cpuidle_devices, cpu) = dev;
 	list_add(&dev->device_list, &cpuidle_detected_devices);
-	ret = cpuidle_add_sysfs(dev);
-	if (ret)
-		goto err_sysfs;
 
 	ret = cpuidle_coupled_register_device(dev);
 	if (ret)
-		goto err_coupled;
-
-	dev->registered = 1;
-	return 0;
+		__cpuidle_unregister_device(dev);
+	else
+		dev->registered = 1;
 
-err_coupled:
-	cpuidle_remove_sysfs(dev);
-err_sysfs:
-	list_del(&dev->device_list);
-	per_cpu(cpuidle_devices, dev->cpu) = NULL;
-	module_put(drv->owner);
 	return ret;
 }
 
@@ -403,25 +674,42 @@ err_sysfs:
  */
 int cpuidle_register_device(struct cpuidle_device *dev)
 {
-	int ret;
+	int ret = -EBUSY;
 
 	if (!dev)
 		return -EINVAL;
 
 	mutex_lock(&cpuidle_lock);
 
-	if ((ret = __cpuidle_register_device(dev))) {
-		mutex_unlock(&cpuidle_lock);
-		return ret;
-	}
+	if (dev->registered)
+		goto out_unlock;
+
+	__cpuidle_device_init(dev);
+
+	ret = __cpuidle_register_device(dev);
+	if (ret)
+		goto out_unlock;
+
+	ret = cpuidle_add_sysfs(dev);
+	if (ret)
+		goto out_unregister;
+
+	ret = cpuidle_enable_device(dev);
+	if (ret)
+		goto out_sysfs;
 
-	cpuidle_enable_device(dev);
 	cpuidle_install_idle_handler();
 
+out_unlock:
 	mutex_unlock(&cpuidle_lock);
 
-	return 0;
+	return ret;
 
+out_sysfs:
+	cpuidle_remove_sysfs(dev);
+out_unregister:
+	__cpuidle_unregister_device(dev);
+	goto out_unlock;
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_register_device);
@@ -432,9 +720,7 @@ EXPORT_SYMBOL_GPL(cpuidle_register_device);
  */
 void cpuidle_unregister_device(struct cpuidle_device *dev)
 {
-	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
-
-	if (dev->registered == 0)
+	if (!dev || dev->registered == 0)
 		return;
 
 	cpuidle_pause_and_lock();
@@ -442,14 +728,12 @@ void cpuidle_unregister_device(struct cpuidle_device *dev)
 	cpuidle_disable_device(dev);
 
 	cpuidle_remove_sysfs(dev);
-	list_del(&dev->device_list);
-	per_cpu(cpuidle_devices, dev->cpu) = NULL;
+
+	__cpuidle_unregister_device(dev);
 
 	cpuidle_coupled_unregister_device(dev);
 
 	cpuidle_resume_and_unlock();
-
-	module_put(drv->owner);
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_unregister_device);
@@ -504,7 +788,7 @@ int cpuidle_register(struct cpuidle_driver *drv,
 
 #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
 		/*
-		 * On multiplatform for ARM, the coupled idle states could
+		 * On multiplatform for ARM, the coupled idle states could be
 		 * enabled in the kernel even if the cpuidle driver does not
 		 * use it. Note, coupled_cpus is a struct copy.
 		 */
@@ -525,59 +809,17 @@ int cpuidle_register(struct cpuidle_driver *drv,
 }
 EXPORT_SYMBOL_GPL(cpuidle_register);
 
-#ifdef CONFIG_SMP
-
-static void smp_callback(void *v)
-{
-	/* we already woke the CPU up, nothing more to do */
-}
-
-/*
- * This function gets called when a part of the kernel has a new latency
- * requirement.  This means we need to get all processors out of their C-state,
- * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that
- * wakes them all right up.
- */
-static int cpuidle_latency_notify(struct notifier_block *b,
-		unsigned long l, void *v)
-{
-	smp_call_function(smp_callback, NULL, 1);
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpuidle_latency_notifier = {
-	.notifier_call = cpuidle_latency_notify,
-};
-
-static inline void latency_notifier_init(struct notifier_block *n)
-{
-	pm_qos_add_notifier(PM_QOS_CPU_DMA_LATENCY, n);
-}
-
-#else /* CONFIG_SMP */
-
-#define latency_notifier_init(x) do { } while (0)
-
-#endif /* CONFIG_SMP */
-
 /**
  * cpuidle_init - core initializer
  */
 static int __init cpuidle_init(void)
 {
-	int ret;
-
 	if (cpuidle_disabled())
 		return -ENODEV;
 
-	ret = cpuidle_add_interface(cpu_subsys.dev_root);
-	if (ret)
-		return ret;
-
-	latency_notifier_init(&cpuidle_latency_notifier);
-
-	return 0;
+	return cpuidle_add_interface();
 }
 
 module_param(off, int, 0444);
+module_param_string(governor, param_governor, CPUIDLE_NAME_LEN, 0444);
 core_initcall(cpuidle_init);