Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

10 files changed, 2758 insertions, 792 deletions

diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index cbccf9a3cee4..3647e114d0e7 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,8 +1,8 @@
-obj-$(CONFIG_PM)        += sysfs.o
+obj-$(CONFIG_PM)        += sysfs.o generic_ops.o
 obj-$(CONFIG_PM_SLEEP)  += main.o wakeup.o
 obj-$(CONFIG_PM_RUNTIME)        += runtime.o
-obj-$(CONFIG_PM_OPS)    += generic_ops.o
 obj-$(CONFIG_PM_TRACE_RTC)      += trace.o
+obj-$(CONFIG_PM_OPP)    += opp.o
+obj-$(CONFIG_HAVE_CLK)  += clock_ops.o
 
-ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
-ccflags-$(CONFIG_PM_VERBOSE)   += -DDEBUG
+ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
\ No newline at end of file
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
new file mode 100644
index 000000000000..ad367c4139b1
--- /dev/null
+++ b/drivers/base/power/clock_ops.c
@@ -0,0 +1,431 @@
+/*
+ * drivers/base/power/clock_ops.c - Generic clock manipulation PM callbacks
+ *
+ * Copyright (c) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/clk.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+
+#ifdef CONFIG_PM_RUNTIME
+
+struct pm_runtime_clk_data {
+        struct list_head clock_list;
+        struct mutex lock;
+};
+
+enum pce_status {
+        PCE_STATUS_NONE = 0,
+        PCE_STATUS_ACQUIRED,
+        PCE_STATUS_ENABLED,
+        PCE_STATUS_ERROR,
+};
+
+struct pm_clock_entry {
+        struct list_head node;
+        char *con_id;
+        struct clk *clk;
+        enum pce_status status;
+};
+
+static struct pm_runtime_clk_data *__to_prd(struct device *dev)
+{
+        return dev ? dev->power.subsys_data : NULL;
+}
+
+/**
+ * pm_runtime_clk_add - Start using a device clock for runtime PM.
+ * @dev: Device whose clock is going to be used for runtime PM.
+ * @con_id: Connection ID of the clock.
+ *
+ * Add the clock represented by @con_id to the list of clocks used for
+ * the runtime PM of @dev.
+ */
+int pm_runtime_clk_add(struct device *dev, const char *con_id)
+{
+        struct pm_runtime_clk_data *prd = __to_prd(dev);
+        struct pm_clock_entry *ce;
+
+        if (!prd)
+                return -EINVAL;
+
+        ce = kzalloc(sizeof(*ce), GFP_KERNEL);
+        if (!ce) {
+                dev_err(dev, "Not enough memory for clock entry.\n");
+                return -ENOMEM;
+        }
+
+        if (con_id) {
+                ce->con_id = kstrdup(con_id, GFP_KERNEL);
+                if (!ce->con_id) {
+                        dev_err(dev,
+                                "Not enough memory for clock connection ID.\n");
+                        kfree(ce);
+                        return -ENOMEM;
+                }
+        }
+
+        mutex_lock(&prd->lock);
+        list_add_tail(&ce->node, &prd->clock_list);
+        mutex_unlock(&prd->lock);
+        return 0;
+}
+
+/**
+ * __pm_runtime_clk_remove - Destroy runtime PM clock entry.
+ * @ce: Runtime PM clock entry to destroy.
+ *
+ * This routine must be called under the mutex protecting the runtime PM list
+ * of clocks corresponding the the @ce's device.
+ */
+static void __pm_runtime_clk_remove(struct pm_clock_entry *ce)
+{
+        if (!ce)
+                return;
+
+        list_del(&ce->node);
+
+        if (ce->status < PCE_STATUS_ERROR) {
+                if (ce->status == PCE_STATUS_ENABLED)
+                        clk_disable(ce->clk);
+
+                if (ce->status >= PCE_STATUS_ACQUIRED)
+                        clk_put(ce->clk);
+        }
+
+        if (ce->con_id)
+                kfree(ce->con_id);
+
+        kfree(ce);
+}
+
+/**
+ * pm_runtime_clk_remove - Stop using a device clock for runtime PM.
+ * @dev: Device whose clock should not be used for runtime PM any more.
+ * @con_id: Connection ID of the clock.
+ *
+ * Remove the clock represented by @con_id from the list of clocks used for
+ * the runtime PM of @dev.
+ */
+void pm_runtime_clk_remove(struct device *dev, const char *con_id)
+{
+        struct pm_runtime_clk_data *prd = __to_prd(dev);
+        struct pm_clock_entry *ce;
+
+        if (!prd)
+                return;
+
+        mutex_lock(&prd->lock);
+
+        list_for_each_entry(ce, &prd->clock_list, node) {
+                if (!con_id && !ce->con_id) {
+                        __pm_runtime_clk_remove(ce);
+                        break;
+                } else if (!con_id || !ce->con_id) {
+                        continue;
+                } else if (!strcmp(con_id, ce->con_id)) {
+                        __pm_runtime_clk_remove(ce);
+                        break;
+                }
+        }
+
+        mutex_unlock(&prd->lock);
+}
+
+/**
+ * pm_runtime_clk_init - Initialize a device's list of runtime PM clocks.
+ * @dev: Device to initialize the list of runtime PM clocks for.
+ *
+ * Allocate a struct pm_runtime_clk_data object, initialize its lock member and
+ * make the @dev's power.subsys_data field point to it.
+ */
+int pm_runtime_clk_init(struct device *dev)
+{
+        struct pm_runtime_clk_data *prd;
+
+        prd = kzalloc(sizeof(*prd), GFP_KERNEL);
+        if (!prd) {
+                dev_err(dev, "Not enough memory fo runtime PM data.\n");
+                return -ENOMEM;
+        }
+
+        INIT_LIST_HEAD(&prd->clock_list);
+        mutex_init(&prd->lock);
+        dev->power.subsys_data = prd;
+        return 0;
+}
+
+/**
+ * pm_runtime_clk_destroy - Destroy a device's list of runtime PM clocks.
+ * @dev: Device to destroy the list of runtime PM clocks for.
+ *
+ * Clear the @dev's power.subsys_data field, remove the list of clock entries
+ * from the struct pm_runtime_clk_data object pointed to by it before and free
+ * that object.
+ */
+void pm_runtime_clk_destroy(struct device *dev)
+{
+        struct pm_runtime_clk_data *prd = __to_prd(dev);
+        struct pm_clock_entry *ce, *c;
+
+        if (!prd)
+                return;
+
+        dev->power.subsys_data = NULL;
+
+        mutex_lock(&prd->lock);
+
+        list_for_each_entry_safe_reverse(ce, c, &prd->clock_list, node)
+                __pm_runtime_clk_remove(ce);
+
+        mutex_unlock(&prd->lock);
+
+        kfree(prd);
+}
+
+/**
+ * pm_runtime_clk_acquire - Acquire a device clock.
+ * @dev: Device whose clock is to be acquired.
+ * @con_id: Connection ID of the clock.
+ */
+static void pm_runtime_clk_acquire(struct device *dev,
+                                    struct pm_clock_entry *ce)
+{
+        ce->clk = clk_get(dev, ce->con_id);
+        if (IS_ERR(ce->clk)) {
+                ce->status = PCE_STATUS_ERROR;
+        } else {
+                ce->status = PCE_STATUS_ACQUIRED;
+                dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+        }
+}
+
+/**
+ * pm_runtime_clk_suspend - Disable clocks in a device's runtime PM clock list.
+ * @dev: Device to disable the clocks for.
+ */
+int pm_runtime_clk_suspend(struct device *dev)
+{
+        struct pm_runtime_clk_data *prd = __to_prd(dev);
+        struct pm_clock_entry *ce;
+
+        dev_dbg(dev, "%s()\n", __func__);
+
+        if (!prd)
+                return 0;
+
+        mutex_lock(&prd->lock);
+
+        list_for_each_entry_reverse(ce, &prd->clock_list, node) {
+                if (ce->status == PCE_STATUS_NONE)
+                        pm_runtime_clk_acquire(dev, ce);
+
+                if (ce->status < PCE_STATUS_ERROR) {
+                        clk_disable(ce->clk);
+                        ce->status = PCE_STATUS_ACQUIRED;
+                }
+        }
+
+        mutex_unlock(&prd->lock);
+
+        return 0;
+}
+
+/**
+ * pm_runtime_clk_resume - Enable clocks in a device's runtime PM clock list.
+ * @dev: Device to enable the clocks for.
+ */
+int pm_runtime_clk_resume(struct device *dev)
+{
+        struct pm_runtime_clk_data *prd = __to_prd(dev);
+        struct pm_clock_entry *ce;
+
+        dev_dbg(dev, "%s()\n", __func__);
+
+        if (!prd)
+                return 0;
+
+        mutex_lock(&prd->lock);
+
+        list_for_each_entry(ce, &prd->clock_list, node) {
+                if (ce->status == PCE_STATUS_NONE)
+                        pm_runtime_clk_acquire(dev, ce);
+
+                if (ce->status < PCE_STATUS_ERROR) {
+                        clk_enable(ce->clk);
+                        ce->status = PCE_STATUS_ENABLED;
+                }
+        }
+
+        mutex_unlock(&prd->lock);
+
+        return 0;
+}
+
+/**
+ * pm_runtime_clk_notify - Notify routine for device addition and removal.
+ * @nb: Notifier block object this function is a member of.
+ * @action: Operation being carried out by the caller.
+ * @data: Device the routine is being run for.
+ *
+ * For this function to work, @nb must be a member of an object of type
+ * struct pm_clk_notifier_block containing all of the requisite data.
+ * Specifically, the pwr_domain member of that object is copied to the device's
+ * pwr_domain field and its con_ids member is used to populate the device's list
+ * of runtime PM clocks, depending on @action.
+ *
+ * If the device's pwr_domain field is already populated with a value different
+ * from the one stored in the struct pm_clk_notifier_block object, the function
+ * does nothing.
+ */
+static int pm_runtime_clk_notify(struct notifier_block *nb,
+                                 unsigned long action, void *data)
+{
+        struct pm_clk_notifier_block *clknb;
+        struct device *dev = data;
+        char **con_id;
+        int error;
+
+        dev_dbg(dev, "%s() %ld\n", __func__, action);
+
+        clknb = container_of(nb, struct pm_clk_notifier_block, nb);
+
+        switch (action) {
+        case BUS_NOTIFY_ADD_DEVICE:
+                if (dev->pwr_domain)
+                        break;
+
+                error = pm_runtime_clk_init(dev);
+                if (error)
+                        break;
+
+                dev->pwr_domain = clknb->pwr_domain;
+                if (clknb->con_ids[0]) {
+                        for (con_id = clknb->con_ids; *con_id; con_id++)
+                                pm_runtime_clk_add(dev, *con_id);
+                } else {
+                        pm_runtime_clk_add(dev, NULL);
+                }
+
+                break;
+        case BUS_NOTIFY_DEL_DEVICE:
+                if (dev->pwr_domain != clknb->pwr_domain)
+                        break;
+
+                dev->pwr_domain = NULL;
+                pm_runtime_clk_destroy(dev);
+                break;
+        }
+
+        return 0;
+}
+
+#else /* !CONFIG_PM_RUNTIME */
+
+/**
+ * enable_clock - Enable a device clock.
+ * @dev: Device whose clock is to be enabled.
+ * @con_id: Connection ID of the clock.
+ */
+static void enable_clock(struct device *dev, const char *con_id)
+{
+        struct clk *clk;
+
+        clk = clk_get(dev, con_id);
+        if (!IS_ERR(clk)) {
+                clk_enable(clk);
+                clk_put(clk);
+                dev_info(dev, "Runtime PM disabled, clock forced on.\n");
+        }
+}
+
+/**
+ * disable_clock - Disable a device clock.
+ * @dev: Device whose clock is to be disabled.
+ * @con_id: Connection ID of the clock.
+ */
+static void disable_clock(struct device *dev, const char *con_id)
+{
+        struct clk *clk;
+
+        clk = clk_get(dev, con_id);
+        if (!IS_ERR(clk)) {
+                clk_disable(clk);
+                clk_put(clk);
+                dev_info(dev, "Runtime PM disabled, clock forced off.\n");
+        }
+}
+
+/**
+ * pm_runtime_clk_notify - Notify routine for device addition and removal.
+ * @nb: Notifier block object this function is a member of.
+ * @action: Operation being carried out by the caller.
+ * @data: Device the routine is being run for.
+ *
+ * For this function to work, @nb must be a member of an object of type
+ * struct pm_clk_notifier_block containing all of the requisite data.
+ * Specifically, the con_ids member of that object is used to enable or disable
+ * the device's clocks, depending on @action.
+ */
+static int pm_runtime_clk_notify(struct notifier_block *nb,
+                                 unsigned long action, void *data)
+{
+        struct pm_clk_notifier_block *clknb;
+        struct device *dev = data;
+        char **con_id;
+
+        dev_dbg(dev, "%s() %ld\n", __func__, action);
+
+        clknb = container_of(nb, struct pm_clk_notifier_block, nb);
+
+        switch (action) {
+        case BUS_NOTIFY_BIND_DRIVER:
+                if (clknb->con_ids[0]) {
+                        for (con_id = clknb->con_ids; *con_id; con_id++)
+                                enable_clock(dev, *con_id);
+                } else {
+                        enable_clock(dev, NULL);
+                }
+                break;
+        case BUS_NOTIFY_UNBOUND_DRIVER:
+                if (clknb->con_ids[0]) {
+                        for (con_id = clknb->con_ids; *con_id; con_id++)
+                                disable_clock(dev, *con_id);
+                } else {
+                        disable_clock(dev, NULL);
+                }
+                break;
+        }
+
+        return 0;
+}
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+/**
+ * pm_runtime_clk_add_notifier - Add bus type notifier for runtime PM clocks.
+ * @bus: Bus type to add the notifier to.
+ * @clknb: Notifier to be added to the given bus type.
+ *
+ * The nb member of @clknb is not expected to be initialized and its
+ * notifier_call member will be replaced with pm_runtime_clk_notify().  However,
+ * the remaining members of @clknb should be populated prior to calling this
+ * routine.
+ */
+void pm_runtime_clk_add_notifier(struct bus_type *bus,
+                                 struct pm_clk_notifier_block *clknb)
+{
+        if (!bus || !clknb)
+                return;
+
+        clknb->nb.notifier_call = pm_runtime_clk_notify;
+        bus_register_notifier(bus, &clknb->nb);
+}
diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c
index 4b29d4981253..cb3bb368681c 100644
--- a/drivers/base/power/generic_ops.c
+++ b/drivers/base/power/generic_ops.c
@@ -39,14 +39,14 @@ EXPORT_SYMBOL_GPL(pm_generic_runtime_idle);
  *
  * If PM operations are defined for the @dev's driver and they include
  * ->runtime_suspend(), execute it and return its error code.  Otherwise,
- * return -EINVAL.
+ * return 0.
  */
 int pm_generic_runtime_suspend(struct device *dev)
 {
         const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
         int ret;
 
-        ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : -EINVAL;
+        ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : 0;
 
         return ret;
 }
@@ -58,14 +58,14 @@ EXPORT_SYMBOL_GPL(pm_generic_runtime_suspend);
  *
  * If PM operations are defined for the @dev's driver and they include
  * ->runtime_resume(), execute it and return its error code.  Otherwise,
- * return -EINVAL.
+ * return 0.
  */
 int pm_generic_runtime_resume(struct device *dev)
 {
         const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
         int ret;
 
-        ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : -EINVAL;
+        ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : 0;
 
         return ret;
 }
@@ -74,6 +74,23 @@ EXPORT_SYMBOL_GPL(pm_generic_runtime_resume);
 
 #ifdef CONFIG_PM_SLEEP
 /**
+ * pm_generic_prepare - Generic routine preparing a device for power transition.
+ * @dev: Device to prepare.
+ *
+ * Prepare a device for a system-wide power transition.
+ */
+int pm_generic_prepare(struct device *dev)
+{
+        struct device_driver *drv = dev->driver;
+        int ret = 0;
+
+        if (drv && drv->pm && drv->pm->prepare)
+                ret = drv->pm->prepare(dev);
+
+        return ret;
+}
+
+/**
  * __pm_generic_call - Generic suspend/freeze/poweroff/thaw subsystem callback.
  * @dev: Device to handle.
  * @event: PM transition of the system under way.
@@ -185,7 +202,7 @@ static int __pm_generic_resume(struct device *dev, int event)
                 return 0;
 
         ret = callback(dev);
-        if (!ret) {
+        if (!ret && pm_runtime_enabled(dev)) {
                 pm_runtime_disable(dev);
                 pm_runtime_set_active(dev);
                 pm_runtime_enable(dev);
@@ -213,16 +230,38 @@ int pm_generic_restore(struct device *dev)
         return __pm_generic_resume(dev, PM_EVENT_RESTORE);
 }
 EXPORT_SYMBOL_GPL(pm_generic_restore);
+
+/**
+ * pm_generic_complete - Generic routine competing a device power transition.
+ * @dev: Device to handle.
+ *
+ * Complete a device power transition during a system-wide power transition.
+ */
+void pm_generic_complete(struct device *dev)
+{
+        struct device_driver *drv = dev->driver;
+
+        if (drv && drv->pm && drv->pm->complete)
+                drv->pm->complete(dev);
+
+        /*
+         * Let runtime PM try to suspend devices that haven't been in use before
+         * going into the system-wide sleep state we're resuming from.
+         */
+        pm_runtime_idle(dev);
+}
 #endif /* CONFIG_PM_SLEEP */
 
 struct dev_pm_ops generic_subsys_pm_ops = {
 #ifdef CONFIG_PM_SLEEP
+        .prepare = pm_generic_prepare,
         .suspend = pm_generic_suspend,
         .resume = pm_generic_resume,
         .freeze = pm_generic_freeze,
         .thaw = pm_generic_thaw,
         .poweroff = pm_generic_poweroff,
         .restore = pm_generic_restore,
+        .complete = pm_generic_complete,
 #endif
 #ifdef CONFIG_PM_RUNTIME
         .runtime_suspend = pm_generic_runtime_suspend,
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 276d5a701dc3..06f09bf89cb2 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -8,7 +8,7 @@
  *
  *
  * The driver model core calls device_pm_add() when a device is registered.
- * This will intialize the embedded device_pm_info object in the device
+ * This will initialize the embedded device_pm_info object in the device
  * and add it to the list of power-controlled devices. sysfs entries for
  * controlling device power management will also be added.
  *
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/async.h>
+#include <linux/suspend.h>
 
 #include "../base.h"
 #include "power.h"
@@ -41,15 +42,14 @@
  */
 
 LIST_HEAD(dpm_list);
+LIST_HEAD(dpm_prepared_list);
+LIST_HEAD(dpm_suspended_list);
+LIST_HEAD(dpm_noirq_list);
 
 static DEFINE_MUTEX(dpm_list_mtx);
 static pm_message_t pm_transition;
 
-/*
- * Set once the preparation of devices for a PM transition has started, reset
- * before starting to resume devices.  Protected by dpm_list_mtx.
- */
-static bool transition_started;
+static int async_error;
 
 /**
  * device_pm_init - Initialize the PM-related part of a device object.
@@ -57,11 +57,14 @@ static bool transition_started;
  */
 void device_pm_init(struct device *dev)
 {
-        dev->power.status = DPM_ON;
+        dev->power.is_prepared = false;
+        dev->power.is_suspended = false;
         init_completion(&dev->power.completion);
         complete_all(&dev->power.completion);
-        dev->power.wakeup_count = 0;
+        dev->power.wakeup = NULL;
+        spin_lock_init(&dev->power.lock);
         pm_runtime_init(dev);
+        INIT_LIST_HEAD(&dev->power.entry);
 }
 
 /**
@@ -87,22 +90,11 @@ void device_pm_unlock(void)
 void device_pm_add(struct device *dev)
 {
         pr_debug("PM: Adding info for %s:%s\n",
-                 dev->bus ? dev->bus->name : "No Bus",
-                 kobject_name(&dev->kobj));
+                 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
         mutex_lock(&dpm_list_mtx);
-        if (dev->parent) {
-                if (dev->parent->power.status >= DPM_SUSPENDING)
-                        dev_warn(dev, "parent %s should not be sleeping\n",
-                                 dev_name(dev->parent));
-        } else if (transition_started) {
-                /*
-                 * We refuse to register parentless devices while a PM
-                 * transition is in progress in order to avoid leaving them
-                 * unhandled down the road
-                 */
-                dev_WARN(dev, "Parentless device registered during a PM transaction\n");
-        }
-
+        if (dev->parent && dev->parent->power.is_prepared)
+                dev_warn(dev, "parent %s should not be sleeping\n",
+                        dev_name(dev->parent));
         list_add_tail(&dev->power.entry, &dpm_list);
         mutex_unlock(&dpm_list_mtx);
 }
@@ -114,12 +106,12 @@ void device_pm_add(struct device *dev)
 void device_pm_remove(struct device *dev)
 {
         pr_debug("PM: Removing info for %s:%s\n",
-                 dev->bus ? dev->bus->name : "No Bus",
-                 kobject_name(&dev->kobj));
+                 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
         complete_all(&dev->power.completion);
         mutex_lock(&dpm_list_mtx);
         list_del_init(&dev->power.entry);
         mutex_unlock(&dpm_list_mtx);
+        device_wakeup_disable(dev);
         pm_runtime_remove(dev);
 }
 
@@ -131,10 +123,8 @@ void device_pm_remove(struct device *dev)
 void device_pm_move_before(struct device *deva, struct device *devb)
 {
         pr_debug("PM: Moving %s:%s before %s:%s\n",
-                 deva->bus ? deva->bus->name : "No Bus",
-                 kobject_name(&deva->kobj),
-                 devb->bus ? devb->bus->name : "No Bus",
-                 kobject_name(&devb->kobj));
+                 deva->bus ? deva->bus->name : "No Bus", dev_name(deva),
+                 devb->bus ? devb->bus->name : "No Bus", dev_name(devb));
         /* Delete deva from dpm_list and reinsert before devb. */
         list_move_tail(&deva->power.entry, &devb->power.entry);
 }
@@ -147,10 +137,8 @@ void device_pm_move_before(struct device *deva, struct device *devb)
 void device_pm_move_after(struct device *deva, struct device *devb)
 {
         pr_debug("PM: Moving %s:%s after %s:%s\n",
-                 deva->bus ? deva->bus->name : "No Bus",
-                 kobject_name(&deva->kobj),
-                 devb->bus ? devb->bus->name : "No Bus",
-                 kobject_name(&devb->kobj));
+                 deva->bus ? deva->bus->name : "No Bus", dev_name(deva),
+                 devb->bus ? devb->bus->name : "No Bus", dev_name(devb));
         /* Delete deva from dpm_list and reinsert after devb. */
         list_move(&deva->power.entry, &devb->power.entry);
 }
@@ -162,8 +150,7 @@ void device_pm_move_after(struct device *deva, struct device *devb)
 void device_pm_move_last(struct device *dev)
 {
         pr_debug("PM: Moving %s:%s to end of list\n",
-                 dev->bus ? dev->bus->name : "No Bus",
-                 kobject_name(&dev->kobj));
+                 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
         list_move_tail(&dev->power.entry, &dpm_list);
 }
 
@@ -248,7 +235,7 @@ static int pm_op(struct device *dev,
                 }
                 break;
 #endif /* CONFIG_SUSPEND */
-#ifdef CONFIG_HIBERNATION
+#ifdef CONFIG_HIBERNATE_CALLBACKS
         case PM_EVENT_FREEZE:
         case PM_EVENT_QUIESCE:
                 if (ops->freeze) {
@@ -275,7 +262,7 @@ static int pm_op(struct device *dev,
                         suspend_report_result(ops->restore, error);
                 }
                 break;
-#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
         default:
                 error = -EINVAL;
         }
@@ -299,7 +286,7 @@ static int pm_noirq_op(struct device *dev,
                         pm_message_t state)
 {
         int error = 0;
-        ktime_t calltime, delta, rettime;
+        ktime_t calltime = ktime_set(0, 0), delta, rettime;
 
         if (initcall_debug) {
                 pr_info("calling  %s+ @ %i, parent: %s\n",
@@ -323,7 +310,7 @@ static int pm_noirq_op(struct device *dev,
                 }
                 break;
 #endif /* CONFIG_SUSPEND */
-#ifdef CONFIG_HIBERNATION
+#ifdef CONFIG_HIBERNATE_CALLBACKS
         case PM_EVENT_FREEZE:
         case PM_EVENT_QUIESCE:
                 if (ops->freeze_noirq) {
@@ -350,7 +337,7 @@ static int pm_noirq_op(struct device *dev,
                         suspend_report_result(ops->restore_noirq, error);
                 }
                 break;
-#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
         default:
                 error = -EINVAL;
         }
@@ -401,13 +388,13 @@ static void pm_dev_err(struct device *dev, pm_message_t state, char *info,
                         int error)
 {
         printk(KERN_ERR "PM: Device %s failed to %s%s: error %d\n",
-                kobject_name(&dev->kobj), pm_verb(state.event), info, error);
+                dev_name(dev), pm_verb(state.event), info, error);
 }
 
 static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info)
 {
         ktime_t calltime;
-        s64 usecs64;
+        u64 usecs64;
         int usecs;
 
         calltime = ktime_get();
@@ -438,26 +425,20 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
         TRACE_DEVICE(dev);
         TRACE_RESUME(0);
 
-        if (dev->bus && dev->bus->pm) {
-                pm_dev_dbg(dev, state, "EARLY ");
-                error = pm_noirq_op(dev, dev->bus->pm, state);
-                if (error)
-                        goto End;
-        }
-
-        if (dev->type && dev->type->pm) {
+        if (dev->pwr_domain) {
+                pm_dev_dbg(dev, state, "EARLY power domain ");
+                error = pm_noirq_op(dev, &dev->pwr_domain->ops, state);
+        } else if (dev->type && dev->type->pm) {
                 pm_dev_dbg(dev, state, "EARLY type ");
                 error = pm_noirq_op(dev, dev->type->pm, state);
-                if (error)
-                        goto End;
-        }
-
-        if (dev->class && dev->class->pm) {
+        } else if (dev->class && dev->class->pm) {
                 pm_dev_dbg(dev, state, "EARLY class ");
                 error = pm_noirq_op(dev, dev->class->pm, state);
+        } else if (dev->bus && dev->bus->pm) {
+                pm_dev_dbg(dev, state, "EARLY ");
+                error = pm_noirq_op(dev, dev->bus->pm, state);
         }
 
-End:
         TRACE_RESUME(error);
         return error;
 }
@@ -471,20 +452,24 @@ End:
  */
 void dpm_resume_noirq(pm_message_t state)
 {
-        struct device *dev;
         ktime_t starttime = ktime_get();
 
         mutex_lock(&dpm_list_mtx);
-        transition_started = false;
-        list_for_each_entry(dev, &dpm_list, power.entry)
-                if (dev->power.status > DPM_OFF) {
-                        int error;
+        while (!list_empty(&dpm_noirq_list)) {
+                struct device *dev = to_device(dpm_noirq_list.next);
+                int error;
 
-                        dev->power.status = DPM_OFF;
-                        error = device_resume_noirq(dev, state);
-                        if (error)
-                                pm_dev_err(dev, state, " early", error);
-                }
+                get_device(dev);
+                list_move_tail(&dev->power.entry, &dpm_suspended_list);
+                mutex_unlock(&dpm_list_mtx);
+
+                error = device_resume_noirq(dev, state);
+                if (error)
+                        pm_dev_err(dev, state, " early", error);
+
+                mutex_lock(&dpm_list_mtx);
+                put_device(dev);
+        }
         mutex_unlock(&dpm_list_mtx);
         dpm_show_time(starttime, state, "early");
         resume_device_irqs();
@@ -527,39 +512,53 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
         dpm_wait(dev->parent, async);
         device_lock(dev);
 
-        dev->power.status = DPM_RESUMING;
+        /*
+         * This is a fib.  But we'll allow new children to be added below
+         * a resumed device, even if the device hasn't been completed yet.
+         */
+        dev->power.is_prepared = false;
 
-        if (dev->bus) {
-                if (dev->bus->pm) {
-                        pm_dev_dbg(dev, state, "");
-                        error = pm_op(dev, dev->bus->pm, state);
-                } else if (dev->bus->resume) {
-                        pm_dev_dbg(dev, state, "legacy ");
-                        error = legacy_resume(dev, dev->bus->resume);
-                }
-                if (error)
-                        goto End;
+        if (!dev->power.is_suspended)
+                goto Unlock;
+
+        if (dev->pwr_domain) {
+                pm_dev_dbg(dev, state, "power domain ");
+                error = pm_op(dev, &dev->pwr_domain->ops, state);
+                goto End;
         }
 
-        if (dev->type) {
-                if (dev->type->pm) {
-                        pm_dev_dbg(dev, state, "type ");
-                        error = pm_op(dev, dev->type->pm, state);
-                }
-                if (error)
-                        goto End;
+        if (dev->type && dev->type->pm) {
+                pm_dev_dbg(dev, state, "type ");
+                error = pm_op(dev, dev->type->pm, state);
+                goto End;
         }
 
         if (dev->class) {
                 if (dev->class->pm) {
                         pm_dev_dbg(dev, state, "class ");
                         error = pm_op(dev, dev->class->pm, state);
+                        goto End;
                 } else if (dev->class->resume) {
                         pm_dev_dbg(dev, state, "legacy class ");
                         error = legacy_resume(dev, dev->class->resume);
+                        goto End;
                 }
         }
+
+        if (dev->bus) {
+                if (dev->bus->pm) {
+                        pm_dev_dbg(dev, state, "");
+                        error = pm_op(dev, dev->bus->pm, state);
+                } else if (dev->bus->resume) {
+                        pm_dev_dbg(dev, state, "legacy ");
+                        error = legacy_resume(dev, dev->bus->resume);
+                }
+        }
+
  End:
+        dev->power.is_suspended = false;
+
+ Unlock:
         device_unlock(dev);
         complete_all(&dev->power.completion);
 
@@ -591,20 +590,18 @@ static bool is_async(struct device *dev)
  * Execute the appropriate "resume" callback for all devices whose status
  * indicates that they are suspended.
  */
-static void dpm_resume(pm_message_t state)
+void dpm_resume(pm_message_t state)
 {
-        struct list_head list;
         struct device *dev;
         ktime_t starttime = ktime_get();
 
-        INIT_LIST_HEAD(&list);
+        might_sleep();
+
         mutex_lock(&dpm_list_mtx);
         pm_transition = state;
+        async_error = 0;
 
-        list_for_each_entry(dev, &dpm_list, power.entry) {
-                if (dev->power.status < DPM_OFF)
-                        continue;
-
+        list_for_each_entry(dev, &dpm_suspended_list, power.entry) {
                 INIT_COMPLETION(dev->power.completion);
                 if (is_async(dev)) {
                         get_device(dev);
@@ -612,28 +609,24 @@ static void dpm_resume(pm_message_t state)
                 }
         }
 
-        while (!list_empty(&dpm_list)) {
-                dev = to_device(dpm_list.next);
+        while (!list_empty(&dpm_suspended_list)) {
+                dev = to_device(dpm_suspended_list.next);
                 get_device(dev);
-                if (dev->power.status >= DPM_OFF && !is_async(dev)) {
+                if (!is_async(dev)) {
                         int error;
 
                         mutex_unlock(&dpm_list_mtx);
 
                         error = device_resume(dev, state, false);
-
-                        mutex_lock(&dpm_list_mtx);
                         if (error)
                                 pm_dev_err(dev, state, "", error);
-                } else if (dev->power.status == DPM_SUSPENDING) {
-                        /* Allow new children of the device to be registered */
-                        dev->power.status = DPM_RESUMING;
+
+                        mutex_lock(&dpm_list_mtx);
                 }
                 if (!list_empty(&dev->power.entry))
-                        list_move_tail(&dev->power.entry, &list);
+                        list_move_tail(&dev->power.entry, &dpm_prepared_list);
                 put_device(dev);
         }
-        list_splice(&list, &dpm_list);
         mutex_unlock(&dpm_list_mtx);
         async_synchronize_full();
         dpm_show_time(starttime, state, NULL);
@@ -648,19 +641,22 @@ static void device_complete(struct device *dev, pm_message_t state)
 {
         device_lock(dev);
 
-        if (dev->class && dev->class->pm && dev->class->pm->complete) {
-                pm_dev_dbg(dev, state, "completing class ");
-                dev->class->pm->complete(dev);
-        }
-
-        if (dev->type && dev->type->pm && dev->type->pm->complete) {
+        if (dev->pwr_domain) {
+                pm_dev_dbg(dev, state, "completing power domain ");
+                if (dev->pwr_domain->ops.complete)
+                        dev->pwr_domain->ops.complete(dev);
+        } else if (dev->type && dev->type->pm) {
                 pm_dev_dbg(dev, state, "completing type ");
-                dev->type->pm->complete(dev);
-        }
-
-        if (dev->bus && dev->bus->pm && dev->bus->pm->complete) {
+                if (dev->type->pm->complete)
+                        dev->type->pm->complete(dev);
+        } else if (dev->class && dev->class->pm) {
+                pm_dev_dbg(dev, state, "completing class ");
+                if (dev->class->pm->complete)
+                        dev->class->pm->complete(dev);
+        } else if (dev->bus && dev->bus->pm) {
                 pm_dev_dbg(dev, state, "completing ");
-                dev->bus->pm->complete(dev);
+                if (dev->bus->pm->complete)
+                        dev->bus->pm->complete(dev);
         }
 
         device_unlock(dev);
@@ -673,28 +669,25 @@ static void device_complete(struct device *dev, pm_message_t state)
  * Execute the ->complete() callbacks for all devices whose PM status is not
  * DPM_ON (this allows new devices to be registered).
  */
-static void dpm_complete(pm_message_t state)
+void dpm_complete(pm_message_t state)
 {
         struct list_head list;
 
+        might_sleep();
+
         INIT_LIST_HEAD(&list);
         mutex_lock(&dpm_list_mtx);
-        transition_started = false;
-        while (!list_empty(&dpm_list)) {
-                struct device *dev = to_device(dpm_list.prev);
+        while (!list_empty(&dpm_prepared_list)) {
+                struct device *dev = to_device(dpm_prepared_list.prev);
 
                 get_device(dev);
-                if (dev->power.status > DPM_ON) {
-                        dev->power.status = DPM_ON;
-                        mutex_unlock(&dpm_list_mtx);
+                dev->power.is_prepared = false;
+                list_move(&dev->power.entry, &list);
+                mutex_unlock(&dpm_list_mtx);
 
-                        device_complete(dev, state);
-                        pm_runtime_put_sync(dev);
+                device_complete(dev, state);
 
-                        mutex_lock(&dpm_list_mtx);
-                }
-                if (!list_empty(&dev->power.entry))
-                        list_move(&dev->power.entry, &list);
+                mutex_lock(&dpm_list_mtx);
                 put_device(dev);
         }
         list_splice(&list, &dpm_list);
@@ -710,7 +703,6 @@ static void dpm_complete(pm_message_t state)
  */
 void dpm_resume_end(pm_message_t state)
 {
-        might_sleep();
         dpm_resume(state);
         dpm_complete(state);
 }
@@ -750,29 +742,31 @@ static pm_message_t resume_event(pm_message_t sleep_state)
  */
 static int device_suspend_noirq(struct device *dev, pm_message_t state)
 {
-        int error = 0;
+        int error;
 
-        if (dev->class && dev->class->pm) {
-                pm_dev_dbg(dev, state, "LATE class ");
-                error = pm_noirq_op(dev, dev->class->pm, state);
+        if (dev->pwr_domain) {
+                pm_dev_dbg(dev, state, "LATE power domain ");
+                error = pm_noirq_op(dev, &dev->pwr_domain->ops, state);
                 if (error)
-                        goto End;
-        }
-
-        if (dev->type && dev->type->pm) {
+                        return error;
+        } else if (dev->type && dev->type->pm) {
                 pm_dev_dbg(dev, state, "LATE type ");
                 error = pm_noirq_op(dev, dev->type->pm, state);
                 if (error)
-                        goto End;
-        }
-
-        if (dev->bus && dev->bus->pm) {
+                        return error;
+        } else if (dev->class && dev->class->pm) {
+                pm_dev_dbg(dev, state, "LATE class ");
+                error = pm_noirq_op(dev, dev->class->pm, state);
+                if (error)
+                        return error;
+        } else if (dev->bus && dev->bus->pm) {
                 pm_dev_dbg(dev, state, "LATE ");
                 error = pm_noirq_op(dev, dev->bus->pm, state);
+                if (error)
+                        return error;
         }
 
-End:
-        return error;
+        return 0;
 }
 
 /**
@@ -784,19 +778,28 @@ End:
  */
 int dpm_suspend_noirq(pm_message_t state)
 {
-        struct device *dev;
         ktime_t starttime = ktime_get();
         int error = 0;
 
         suspend_device_irqs();
         mutex_lock(&dpm_list_mtx);
-        list_for_each_entry_reverse(dev, &dpm_list, power.entry) {
+        while (!list_empty(&dpm_suspended_list)) {
+                struct device *dev = to_device(dpm_suspended_list.prev);
+
+                get_device(dev);
+                mutex_unlock(&dpm_list_mtx);
+
                 error = device_suspend_noirq(dev, state);
+
+                mutex_lock(&dpm_list_mtx);
                 if (error) {
                         pm_dev_err(dev, state, " late", error);
+                        put_device(dev);
                         break;
                 }
-                dev->power.status = DPM_OFF_IRQ;
+                if (!list_empty(&dev->power.entry))
+                        list_move(&dev->power.entry, &dpm_noirq_list);
+                put_device(dev);
         }
         mutex_unlock(&dpm_list_mtx);
         if (error)
@@ -829,8 +832,6 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
         return error;
 }
 
-static int async_error;
-
 /**
  * device_suspend - Execute "suspend" callbacks for given device.
  * @dev: Device to handle.
@@ -845,27 +846,35 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
         device_lock(dev);
 
         if (async_error)
+                goto Unlock;
+
+        if (pm_wakeup_pending()) {
+                async_error = -EBUSY;
+                goto Unlock;
+        }
+
+        if (dev->pwr_domain) {
+                pm_dev_dbg(dev, state, "power domain ");
+                error = pm_op(dev, &dev->pwr_domain->ops, state);
                 goto End;
+        }
+
+        if (dev->type && dev->type->pm) {
+                pm_dev_dbg(dev, state, "type ");
+                error = pm_op(dev, dev->type->pm, state);
+                goto End;
+        }
 
         if (dev->class) {
                 if (dev->class->pm) {
                         pm_dev_dbg(dev, state, "class ");
                         error = pm_op(dev, dev->class->pm, state);
+                        goto End;
                 } else if (dev->class->suspend) {
                         pm_dev_dbg(dev, state, "legacy class ");
                         error = legacy_suspend(dev, state, dev->class->suspend);
-                }
-                if (error)
                         goto End;
-        }
-
-        if (dev->type) {
-                if (dev->type->pm) {
-                        pm_dev_dbg(dev, state, "type ");
-                        error = pm_op(dev, dev->type->pm, state);
                 }
-                if (error)
-                        goto End;
         }
 
         if (dev->bus) {
@@ -878,13 +887,16 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
                 }
         }
 
-        if (!error)
-                dev->power.status = DPM_OFF;
-
  End:
+        dev->power.is_suspended = !error;
+
+ Unlock:
         device_unlock(dev);
         complete_all(&dev->power.completion);
 
+        if (error)
+                async_error = error;
+
         return error;
 }
 
@@ -894,10 +906,8 @@ static void async_suspend(void *data, async_cookie_t cookie)
         int error;
 
         error = __device_suspend(dev, pm_transition, true);
-        if (error) {
+        if (error)
                 pm_dev_err(dev, pm_transition, " async", error);
-                async_error = error;
-        }
 
         put_device(dev);
 }
@@ -919,18 +929,18 @@ static int device_suspend(struct device *dev)
  * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices.
  * @state: PM transition of the system being carried out.
  */
-static int dpm_suspend(pm_message_t state)
+int dpm_suspend(pm_message_t state)
 {
-        struct list_head list;
         ktime_t starttime = ktime_get();
         int error = 0;
 
-        INIT_LIST_HEAD(&list);
+        might_sleep();
+
         mutex_lock(&dpm_list_mtx);
         pm_transition = state;
         async_error = 0;
-        while (!list_empty(&dpm_list)) {
-                struct device *dev = to_device(dpm_list.prev);
+        while (!list_empty(&dpm_prepared_list)) {
+                struct device *dev = to_device(dpm_prepared_list.prev);
 
                 get_device(dev);
                 mutex_unlock(&dpm_list_mtx);
@@ -944,12 +954,11 @@ static int dpm_suspend(pm_message_t state)
                         break;
                 }
                 if (!list_empty(&dev->power.entry))
-                        list_move(&dev->power.entry, &list);
+                        list_move(&dev->power.entry, &dpm_suspended_list);
                 put_device(dev);
                 if (async_error)
                         break;
         }
-        list_splice(&list, dpm_list.prev);
         mutex_unlock(&dpm_list_mtx);
         async_synchronize_full();
         if (!error)
@@ -973,27 +982,34 @@ static int device_prepare(struct device *dev, pm_message_t state)
 
         device_lock(dev);
 
-        if (dev->bus && dev->bus->pm && dev->bus->pm->prepare) {
-                pm_dev_dbg(dev, state, "preparing ");
-                error = dev->bus->pm->prepare(dev);
-                suspend_report_result(dev->bus->pm->prepare, error);
+        if (dev->pwr_domain) {
+                pm_dev_dbg(dev, state, "preparing power domain ");
+                if (dev->pwr_domain->ops.prepare)
+                        error = dev->pwr_domain->ops.prepare(dev);
+                suspend_report_result(dev->pwr_domain->ops.prepare, error);
                 if (error)
                         goto End;
-        }
-
-        if (dev->type && dev->type->pm && dev->type->pm->prepare) {
+        } else if (dev->type && dev->type->pm) {
                 pm_dev_dbg(dev, state, "preparing type ");
-                error = dev->type->pm->prepare(dev);
+                if (dev->type->pm->prepare)
+                        error = dev->type->pm->prepare(dev);
                 suspend_report_result(dev->type->pm->prepare, error);
                 if (error)
                         goto End;
-        }
-
-        if (dev->class && dev->class->pm && dev->class->pm->prepare) {
+        } else if (dev->class && dev->class->pm) {
                 pm_dev_dbg(dev, state, "preparing class ");
-                error = dev->class->pm->prepare(dev);
+                if (dev->class->pm->prepare)
+                        error = dev->class->pm->prepare(dev);
                 suspend_report_result(dev->class->pm->prepare, error);
+                if (error)
+                        goto End;
+        } else if (dev->bus && dev->bus->pm) {
+                pm_dev_dbg(dev, state, "preparing ");
+                if (dev->bus->pm->prepare)
+                        error = dev->bus->pm->prepare(dev);
+                suspend_report_result(dev->bus->pm->prepare, error);
         }
+
  End:
         device_unlock(dev);
 
@@ -1006,50 +1022,45 @@ static int device_prepare(struct device *dev, pm_message_t state)
  *
  * Execute the ->prepare() callback(s) for all devices.
  */
-static int dpm_prepare(pm_message_t state)
+int dpm_prepare(pm_message_t state)
 {
-        struct list_head list;
         int error = 0;
 
-        INIT_LIST_HEAD(&list);
+        might_sleep();
+
         mutex_lock(&dpm_list_mtx);
-        transition_started = true;
         while (!list_empty(&dpm_list)) {
                 struct device *dev = to_device(dpm_list.next);
 
                 get_device(dev);
-                dev->power.status = DPM_PREPARING;
                 mutex_unlock(&dpm_list_mtx);
 
                 pm_runtime_get_noresume(dev);
-                if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) {
-                        /* Wake-up requested during system sleep transition. */
-                        pm_runtime_put_sync(dev);
-                        error = -EBUSY;
-                } else {
-                        error = device_prepare(dev, state);
-                }
+                if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
+                        pm_wakeup_event(dev, 0);
+
+                pm_runtime_put_sync(dev);
+                error = pm_wakeup_pending() ?
+                                -EBUSY : device_prepare(dev, state);
 
                 mutex_lock(&dpm_list_mtx);
                 if (error) {
-                        dev->power.status = DPM_ON;
                         if (error == -EAGAIN) {
                                 put_device(dev);
                                 error = 0;
                                 continue;
                         }
-                        printk(KERN_ERR "PM: Failed to prepare device %s "
-                                "for power transition: error %d\n",
-                                kobject_name(&dev->kobj), error);
+                        printk(KERN_INFO "PM: Device %s not prepared "
+                                "for power transition: code %d\n",
+                                dev_name(dev), error);
                         put_device(dev);
                         break;
                 }
-                dev->power.status = DPM_SUSPENDING;
+                dev->power.is_prepared = true;
                 if (!list_empty(&dev->power.entry))
-                        list_move_tail(&dev->power.entry, &list);
+                        list_move_tail(&dev->power.entry, &dpm_prepared_list);
                 put_device(dev);
         }
-        list_splice(&list, &dpm_list);
         mutex_unlock(&dpm_list_mtx);
         return error;
 }
@@ -1065,7 +1076,6 @@ int dpm_suspend_start(pm_message_t state)
 {
         int error;
 
-        might_sleep();
         error = dpm_prepare(state);
         if (!error)
                 error = dpm_suspend(state);
@@ -1085,8 +1095,9 @@ EXPORT_SYMBOL_GPL(__suspend_report_result);
  * @dev: Device to wait for.
  * @subordinate: Device that needs to wait for @dev.
  */
-void device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
+int device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
 {
         dpm_wait(dev, subordinate->power.async_suspend);
+        return async_error;
 }
 EXPORT_SYMBOL_GPL(device_pm_wait_for_dev);
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
new file mode 100644
index 000000000000..56a6899f5e9e
--- /dev/null
+++ b/drivers/base/power/opp.c
@@ -0,0 +1,628 @@
+/*
+ * Generic OPP Interface
+ *
+ * Copyright (C) 2009-2010 Texas Instruments Incorporated.
+ *      Nishanth Menon
+ *      Romit Dasgupta
+ *      Kevin Hilman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/cpufreq.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/opp.h>
+
+/*
+ * Internal data structure organization with the OPP layer library is as
+ * follows:
+ * dev_opp_list (root)
+ *      |- device 1 (represents voltage domain 1)
+ *      |       |- opp 1 (availability, freq, voltage)
+ *      |       |- opp 2 ..
+ *      ...     ...
+ *      |       `- opp n ..
+ *      |- device 2 (represents the next voltage domain)
+ *      ...
+ *      `- device m (represents mth voltage domain)
+ * device 1, 2.. are represented by dev_opp structure while each opp
+ * is represented by the opp structure.
+ */
+
+/**
+ * struct opp - Generic OPP description structure
+ * @node:       opp list node. The nodes are maintained throughout the lifetime
+ *              of boot. It is expected only an optimal set of OPPs are
+ *              added to the library by the SoC framework.
+ *              RCU usage: opp list is traversed with RCU locks. node
+ *              modification is possible realtime, hence the modifications
+ *              are protected by the dev_opp_list_lock for integrity.
+ *              IMPORTANT: the opp nodes should be maintained in increasing
+ *              order.
+ * @available:  true/false - marks if this OPP as available or not
+ * @rate:       Frequency in hertz
+ * @u_volt:     Nominal voltage in microvolts corresponding to this OPP
+ * @dev_opp:    points back to the device_opp struct this opp belongs to
+ *
+ * This structure stores the OPP information for a given device.
+ */
+struct opp {
+        struct list_head node;
+
+        bool available;
+        unsigned long rate;
+        unsigned long u_volt;
+
+        struct device_opp *dev_opp;
+};
+
+/**
+ * struct device_opp - Device opp structure
+ * @node:       list node - contains the devices with OPPs that
+ *              have been registered. Nodes once added are not modified in this
+ *              list.
+ *              RCU usage: nodes are not modified in the list of device_opp,
+ *              however addition is possible and is secured by dev_opp_list_lock
+ * @dev:        device pointer
+ * @opp_list:   list of opps
+ *
+ * This is an internal data structure maintaining the link to opps attached to
+ * a device. This structure is not meant to be shared to users as it is
+ * meant for book keeping and private to OPP library
+ */
+struct device_opp {
+        struct list_head node;
+
+        struct device *dev;
+        struct list_head opp_list;
+};
+
+/*
+ * The root of the list of all devices. All device_opp structures branch off
+ * from here, with each device_opp containing the list of opp it supports in
+ * various states of availability.
+ */
+static LIST_HEAD(dev_opp_list);
+/* Lock to allow exclusive modification to the device and opp lists */
+static DEFINE_MUTEX(dev_opp_list_lock);
+
+/**
+ * find_device_opp() - find device_opp struct using device pointer
+ * @dev:        device pointer used to lookup device OPPs
+ *
+ * Search list of device OPPs for one containing matching device. Does a RCU
+ * reader operation to grab the pointer needed.
+ *
+ * Returns pointer to 'struct device_opp' if found, otherwise -ENODEV or
+ * -EINVAL based on type of error.
+ *
+ * Locking: This function must be called under rcu_read_lock(). device_opp
+ * is a RCU protected pointer. This means that device_opp is valid as long
+ * as we are under RCU lock.
+ */
+static struct device_opp *find_device_opp(struct device *dev)
+{
+        struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+
+        if (unlikely(IS_ERR_OR_NULL(dev))) {
+                pr_err("%s: Invalid parameters\n", __func__);
+                return ERR_PTR(-EINVAL);
+        }
+
+        list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
+                if (tmp_dev_opp->dev == dev) {
+                        dev_opp = tmp_dev_opp;
+                        break;
+                }
+        }
+
+        return dev_opp;
+}
+
+/**
+ * opp_get_voltage() - Gets the voltage corresponding to an available opp
+ * @opp:        opp for which voltage has to be returned for
+ *
+ * Return voltage in micro volt corresponding to the opp, else
+ * return 0
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+unsigned long opp_get_voltage(struct opp *opp)
+{
+        struct opp *tmp_opp;
+        unsigned long v = 0;
+
+        tmp_opp = rcu_dereference(opp);
+        if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+                pr_err("%s: Invalid parameters\n", __func__);
+        else
+                v = tmp_opp->u_volt;
+
+        return v;
+}
+
+/**
+ * opp_get_freq() - Gets the frequency corresponding to an available opp
+ * @opp:        opp for which frequency has to be returned for
+ *
+ * Return frequency in hertz corresponding to the opp, else
+ * return 0
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+unsigned long opp_get_freq(struct opp *opp)
+{
+        struct opp *tmp_opp;
+        unsigned long f = 0;
+
+        tmp_opp = rcu_dereference(opp);
+        if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+                pr_err("%s: Invalid parameters\n", __func__);
+        else
+                f = tmp_opp->rate;
+
+        return f;
+}
+
+/**
+ * opp_get_opp_count() - Get number of opps available in the opp list
+ * @dev:        device for which we do this operation
+ *
+ * This function returns the number of available opps if there are any,
+ * else returns 0 if none or the corresponding error value.
+ *
+ * Locking: This function must be called under rcu_read_lock(). This function
+ * internally references two RCU protected structures: device_opp and opp which
+ * are safe as long as we are under a common RCU locked section.
+ */
+int opp_get_opp_count(struct device *dev)
+{
+        struct device_opp *dev_opp;
+        struct opp *temp_opp;
+        int count = 0;
+
+        dev_opp = find_device_opp(dev);
+        if (IS_ERR(dev_opp)) {
+                int r = PTR_ERR(dev_opp);
+                dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+                return r;
+        }
+
+        list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+                if (temp_opp->available)
+                        count++;
+        }
+
+        return count;
+}
+
+/**
+ * opp_find_freq_exact() - search for an exact frequency
+ * @dev:                device for which we do this operation
+ * @freq:               frequency to search for
+ * @available:          true/false - match for available opp
+ *
+ * Searches for exact match in the opp list and returns pointer to the matching
+ * opp if found, else returns ERR_PTR in case of error and should be handled
+ * using IS_ERR.
+ *
+ * Note: available is a modifier for the search. if available=true, then the
+ * match is for exact matching frequency and is available in the stored OPP
+ * table. if false, the match is for exact frequency which is not available.
+ *
+ * This provides a mechanism to enable an opp which is not available currently
+ * or the opposite as well.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
+                                bool available)
+{
+        struct device_opp *dev_opp;
+        struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+        dev_opp = find_device_opp(dev);
+        if (IS_ERR(dev_opp)) {
+                int r = PTR_ERR(dev_opp);
+                dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+                return ERR_PTR(r);
+        }
+
+        list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+                if (temp_opp->available == available &&
+                                temp_opp->rate == freq) {
+                        opp = temp_opp;
+                        break;
+                }
+        }
+
+        return opp;
+}
+
+/**
+ * opp_find_freq_ceil() - Search for an rounded ceil freq
+ * @dev:        device for which we do this operation
+ * @freq:       Start frequency
+ *
+ * Search for the matching ceil *available* OPP from a starting freq
+ * for a device.
+ *
+ * Returns matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq)
+{
+        struct device_opp *dev_opp;
+        struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+        if (!dev || !freq) {
+                dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
+                return ERR_PTR(-EINVAL);
+        }
+
+        dev_opp = find_device_opp(dev);
+        if (IS_ERR(dev_opp))
+                return opp;
+
+        list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+                if (temp_opp->available && temp_opp->rate >= *freq) {
+                        opp = temp_opp;
+                        *freq = opp->rate;
+                        break;
+                }
+        }
+
+        return opp;
+}
+
+/**
+ * opp_find_freq_floor() - Search for a rounded floor freq
+ * @dev:        device for which we do this operation
+ * @freq:       Start frequency
+ *
+ * Search for the matching floor *available* OPP from a starting freq
+ * for a device.
+ *
+ * Returns matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq)
+{
+        struct device_opp *dev_opp;
+        struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+        if (!dev || !freq) {
+                dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
+                return ERR_PTR(-EINVAL);
+        }
+
+        dev_opp = find_device_opp(dev);
+        if (IS_ERR(dev_opp))
+                return opp;
+
+        list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+                if (temp_opp->available) {
+                        /* go to the next node, before choosing prev */
+                        if (temp_opp->rate > *freq)
+                                break;
+                        else
+                                opp = temp_opp;
+                }
+        }
+        if (!IS_ERR(opp))
+                *freq = opp->rate;
+
+        return opp;
+}
+
+/**
+ * opp_add()  - Add an OPP table from a table definitions
+ * @dev:        device for which we do this operation
+ * @freq:       Frequency in Hz for this OPP
+ * @u_volt:     Voltage in uVolts for this OPP
+ *
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * opp_enable/disable functions.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+{
+        struct device_opp *dev_opp = NULL;
+        struct opp *opp, *new_opp;
+        struct list_head *head;
+
+        /* allocate new OPP node */
+        new_opp = kzalloc(sizeof(struct opp), GFP_KERNEL);
+        if (!new_opp) {
+                dev_warn(dev, "%s: Unable to create new OPP node\n", __func__);
+                return -ENOMEM;
+        }
+
+        /* Hold our list modification lock here */
+        mutex_lock(&dev_opp_list_lock);
+
+        /* Check for existing list for 'dev' */
+        dev_opp = find_device_opp(dev);
+        if (IS_ERR(dev_opp)) {
+                /*
+                 * Allocate a new device OPP table. In the infrequent case
+                 * where a new device is needed to be added, we pay this
+                 * penalty.
+                 */
+                dev_opp = kzalloc(sizeof(struct device_opp), GFP_KERNEL);
+                if (!dev_opp) {
+                        mutex_unlock(&dev_opp_list_lock);
+                        kfree(new_opp);
+                        dev_warn(dev,
+                                "%s: Unable to create device OPP structure\n",
+                                __func__);
+                        return -ENOMEM;
+                }
+
+                dev_opp->dev = dev;
+                INIT_LIST_HEAD(&dev_opp->opp_list);
+
+                /* Secure the device list modification */
+                list_add_rcu(&dev_opp->node, &dev_opp_list);
+        }
+
+        /* populate the opp table */
+        new_opp->dev_opp = dev_opp;
+        new_opp->rate = freq;
+        new_opp->u_volt = u_volt;
+        new_opp->available = true;
+
+        /* Insert new OPP in order of increasing frequency */
+        head = &dev_opp->opp_list;
+        list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+                if (new_opp->rate < opp->rate)
+                        break;
+                else
+                        head = &opp->node;
+        }
+
+        list_add_rcu(&new_opp->node, head);
+        mutex_unlock(&dev_opp_list_lock);
+
+        return 0;
+}
+
+/**
+ * opp_set_availability() - helper to set the availability of an opp
+ * @dev:                device for which we do this operation
+ * @freq:               OPP frequency to modify availability
+ * @availability_req:   availability status requested for this opp
+ *
+ * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
+ * share a common logic which is isolated here.
+ *
+ * Returns -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks to
+ * keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+static int opp_set_availability(struct device *dev, unsigned long freq,
+                bool availability_req)
+{
+        struct device_opp *tmp_dev_opp, *dev_opp = NULL;
+        struct opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+        int r = 0;
+
+        /* keep the node allocated */
+        new_opp = kmalloc(sizeof(struct opp), GFP_KERNEL);
+        if (!new_opp) {
+                dev_warn(dev, "%s: Unable to create OPP\n", __func__);
+                return -ENOMEM;
+        }
+
+        mutex_lock(&dev_opp_list_lock);
+
+        /* Find the device_opp */
+        list_for_each_entry(tmp_dev_opp, &dev_opp_list, node) {
+                if (dev == tmp_dev_opp->dev) {
+                        dev_opp = tmp_dev_opp;
+                        break;
+                }
+        }
+        if (IS_ERR(dev_opp)) {
+                r = PTR_ERR(dev_opp);
+                dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+                goto unlock;
+        }
+
+        /* Do we have the frequency? */
+        list_for_each_entry(tmp_opp, &dev_opp->opp_list, node) {
+                if (tmp_opp->rate == freq) {
+                        opp = tmp_opp;
+                        break;
+                }
+        }
+        if (IS_ERR(opp)) {
+                r = PTR_ERR(opp);
+                goto unlock;
+        }
+
+        /* Is update really needed? */
+        if (opp->available == availability_req)
+                goto unlock;
+        /* copy the old data over */
+        *new_opp = *opp;
+
+        /* plug in new node */
+        new_opp->available = availability_req;
+
+        list_replace_rcu(&opp->node, &new_opp->node);
+        mutex_unlock(&dev_opp_list_lock);
+        synchronize_rcu();
+
+        /* clean up old opp */
+        new_opp = opp;
+        goto out;
+
+unlock:
+        mutex_unlock(&dev_opp_list_lock);
+out:
+        kfree(new_opp);
+        return r;
+}
+
+/**
+ * opp_enable() - Enable a specific OPP
+ * @dev:        device for which we do this operation
+ * @freq:       OPP frequency to enable
+ *
+ * Enables a provided opp. If the operation is valid, this returns 0, else the
+ * corresponding error value. It is meant to be used for users an OPP available
+ * after being temporarily made unavailable with opp_disable.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU and mutex locks to keep the
+ * integrity of the internal data structures. Callers should ensure that
+ * this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+int opp_enable(struct device *dev, unsigned long freq)
+{
+        return opp_set_availability(dev, freq, true);
+}
+
+/**
+ * opp_disable() - Disable a specific OPP
+ * @dev:        device for which we do this operation
+ * @freq:       OPP frequency to disable
+ *
+ * Disables a provided opp. If the operation is valid, this returns
+ * 0, else the corresponding error value. It is meant to be a temporary
+ * control by users to make this OPP not available until the circumstances are
+ * right to make it available again (with a call to opp_enable).
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU and mutex locks to keep the
+ * integrity of the internal data structures. Callers should ensure that
+ * this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+int opp_disable(struct device *dev, unsigned long freq)
+{
+        return opp_set_availability(dev, freq, false);
+}
+
+#ifdef CONFIG_CPU_FREQ
+/**
+ * opp_init_cpufreq_table() - create a cpufreq table for a device
+ * @dev:        device for which we do this operation
+ * @table:      Cpufreq table returned back to caller
+ *
+ * Generate a cpufreq table for a provided device- this assumes that the
+ * opp list is already initialized and ready for usage.
+ *
+ * This function allocates required memory for the cpufreq table. It is
+ * expected that the caller does the required maintenance such as freeing
+ * the table as required.
+ *
+ * Returns -EINVAL for bad pointers, -ENODEV if the device is not found, -ENOMEM
+ * if no memory available for the operation (table is not populated), returns 0
+ * if successful and table is populated.
+ *
+ * WARNING: It is  important for the callers to ensure refreshing their copy of
+ * the table if any of the mentioned functions have been invoked in the interim.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * To simplify the logic, we pretend we are updater and hold relevant mutex here
+ * Callers should ensure that this function is *NOT* called under RCU protection
+ * or in contexts where mutex locking cannot be used.
+ */
+int opp_init_cpufreq_table(struct device *dev,
+                            struct cpufreq_frequency_table **table)
+{
+        struct device_opp *dev_opp;
+        struct opp *opp;
+        struct cpufreq_frequency_table *freq_table;
+        int i = 0;
+
+        /* Pretend as if I am an updater */
+        mutex_lock(&dev_opp_list_lock);
+
+        dev_opp = find_device_opp(dev);
+        if (IS_ERR(dev_opp)) {
+                int r = PTR_ERR(dev_opp);
+                mutex_unlock(&dev_opp_list_lock);
+                dev_err(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+                return r;
+        }
+
+        freq_table = kzalloc(sizeof(struct cpufreq_frequency_table) *
+                             (opp_get_opp_count(dev) + 1), GFP_KERNEL);
+        if (!freq_table) {
+                mutex_unlock(&dev_opp_list_lock);
+                dev_warn(dev, "%s: Unable to allocate frequency table\n",
+                        __func__);
+                return -ENOMEM;
+        }
+
+        list_for_each_entry(opp, &dev_opp->opp_list, node) {
+                if (opp->available) {
+                        freq_table[i].index = i;
+                        freq_table[i].frequency = opp->rate / 1000;
+                        i++;
+                }
+        }
+        mutex_unlock(&dev_opp_list_lock);
+
+        freq_table[i].index = i;
+        freq_table[i].frequency = CPUFREQ_TABLE_END;
+
+        *table = &freq_table[0];
+
+        return 0;
+}
+#endif          /* CONFIG_CPU_FREQ */
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index c0bd03c83b9c..f2a25f18fde7 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -34,6 +34,7 @@ extern void device_pm_move_last(struct device *);
 
 static inline void device_pm_init(struct device *dev)
 {
+        spin_lock_init(&dev->power.lock);
         pm_runtime_init(dev);
 }
 
@@ -57,18 +58,18 @@ static inline void device_pm_move_last(struct device *dev) {}
  * sysfs.c
  */
 
-extern int dpm_sysfs_add(struct device *);
-extern void dpm_sysfs_remove(struct device *);
+extern int dpm_sysfs_add(struct device *dev);
+extern void dpm_sysfs_remove(struct device *dev);
+extern void rpm_sysfs_remove(struct device *dev);
+extern int wakeup_sysfs_add(struct device *dev);
+extern void wakeup_sysfs_remove(struct device *dev);
 
 #else /* CONFIG_PM */
 
-static inline int dpm_sysfs_add(struct device *dev)
-{
-        return 0;
-}
-
-static inline void dpm_sysfs_remove(struct device *dev)
-{
-}
+static inline int dpm_sysfs_add(struct device *dev) { return 0; }
+static inline void dpm_sysfs_remove(struct device *dev) {}
+static inline void rpm_sysfs_remove(struct device *dev) {}
+static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
+static inline void wakeup_sysfs_remove(struct device *dev) {}
 
 #endif
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index b78c401ffa73..0d4587b15c55 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -2,17 +2,55 @@
  * drivers/base/power/runtime.c - Helper functions for device run-time PM
  *
  * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu>
  *
  * This file is released under the GPLv2.
  */
 
 #include <linux/sched.h>
 #include <linux/pm_runtime.h>
-#include <linux/jiffies.h>
+#include "power.h"
 
-static int __pm_runtime_resume(struct device *dev, bool from_wq);
-static int __pm_request_idle(struct device *dev);
-static int __pm_request_resume(struct device *dev);
+static int rpm_resume(struct device *dev, int rpmflags);
+static int rpm_suspend(struct device *dev, int rpmflags);
+
+/**
+ * update_pm_runtime_accounting - Update the time accounting of power states
+ * @dev: Device to update the accounting for
+ *
+ * In order to be able to have time accounting of the various power states
+ * (as used by programs such as PowerTOP to show the effectiveness of runtime
+ * PM), we need to track the time spent in each state.
+ * update_pm_runtime_accounting must be called each time before the
+ * runtime_status field is updated, to account the time in the old state
+ * correctly.
+ */
+void update_pm_runtime_accounting(struct device *dev)
+{
+        unsigned long now = jiffies;
+        int delta;
+
+        delta = now - dev->power.accounting_timestamp;
+
+        if (delta < 0)
+                delta = 0;
+
+        dev->power.accounting_timestamp = now;
+
+        if (dev->power.disable_depth > 0)
+                return;
+
+        if (dev->power.runtime_status == RPM_SUSPENDED)
+                dev->power.suspended_jiffies += delta;
+        else
+                dev->power.active_jiffies += delta;
+}
+
+static void __update_runtime_status(struct device *dev, enum rpm_status status)
+{
+        update_pm_runtime_accounting(dev);
+        dev->power.runtime_status = status;
+}
 
 /**
  * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
@@ -40,62 +78,156 @@ static void pm_runtime_cancel_pending(struct device *dev)
         dev->power.request = RPM_REQ_NONE;
 }
 
-/**
- * __pm_runtime_idle - Notify device bus type if the device can be suspended.
- * @dev: Device to notify the bus type about.
+/*
+ * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time.
+ * @dev: Device to handle.
  *
- * This function must be called under dev->power.lock with interrupts disabled.
+ * Compute the autosuspend-delay expiration time based on the device's
+ * power.last_busy time.  If the delay has already expired or is disabled
+ * (negative) or the power.use_autosuspend flag isn't set, return 0.
+ * Otherwise return the expiration time in jiffies (adjusted to be nonzero).
+ *
+ * This function may be called either with or without dev->power.lock held.
+ * Either way it can be racy, since power.last_busy may be updated at any time.
  */
-static int __pm_runtime_idle(struct device *dev)
-        __releases(&dev->power.lock) __acquires(&dev->power.lock)
+unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
+{
+        int autosuspend_delay;
+        long elapsed;
+        unsigned long last_busy;
+        unsigned long expires = 0;
+
+        if (!dev->power.use_autosuspend)
+                goto out;
+
+        autosuspend_delay = ACCESS_ONCE(dev->power.autosuspend_delay);
+        if (autosuspend_delay < 0)
+                goto out;
+
+        last_busy = ACCESS_ONCE(dev->power.last_busy);
+        elapsed = jiffies - last_busy;
+        if (elapsed < 0)
+                goto out;       /* jiffies has wrapped around. */
+
+        /*
+         * If the autosuspend_delay is >= 1 second, align the timer by rounding
+         * up to the nearest second.
+         */
+        expires = last_busy + msecs_to_jiffies(autosuspend_delay);
+        if (autosuspend_delay >= 1000)
+                expires = round_jiffies(expires);
+        expires += !expires;
+        if (elapsed >= expires - last_busy)
+                expires = 0;    /* Already expired. */
+
+ out:
+        return expires;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
+
+/**
+ * rpm_check_suspend_allowed - Test whether a device may be suspended.
+ * @dev: Device to test.
+ */
+static int rpm_check_suspend_allowed(struct device *dev)
 {
         int retval = 0;
 
         if (dev->power.runtime_error)
                 retval = -EINVAL;
-        else if (dev->power.idle_notification)
-                retval = -EINPROGRESS;
         else if (atomic_read(&dev->power.usage_count) > 0
-            || dev->power.disable_depth > 0
-            || dev->power.runtime_status != RPM_ACTIVE)
+            || dev->power.disable_depth > 0)
                 retval = -EAGAIN;
         else if (!pm_children_suspended(dev))
                 retval = -EBUSY;
+
+        /* Pending resume requests take precedence over suspends. */
+        else if ((dev->power.deferred_resume
+                        && dev->power.runtime_status == RPM_SUSPENDING)
+            || (dev->power.request_pending
+                        && dev->power.request == RPM_REQ_RESUME))
+                retval = -EAGAIN;
+        else if (dev->power.runtime_status == RPM_SUSPENDED)
+                retval = 1;
+
+        return retval;
+}
+
+/**
+ * rpm_idle - Notify device bus type if the device can be suspended.
+ * @dev: Device to notify the bus type about.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's run-time PM status allows it to be suspended.  If
+ * another idle notification has been started earlier, return immediately.  If
+ * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise
+ * run the ->runtime_idle() callback directly.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static int rpm_idle(struct device *dev, int rpmflags)
+{
+        int (*callback)(struct device *);
+        int retval;
+
+        retval = rpm_check_suspend_allowed(dev);
+        if (retval < 0)
+                ;       /* Conditions are wrong. */
+
+        /* Idle notifications are allowed only in the RPM_ACTIVE state. */
+        else if (dev->power.runtime_status != RPM_ACTIVE)
+                retval = -EAGAIN;
+
+        /*
+         * Any pending request other than an idle notification takes
+         * precedence over us, except that the timer may be running.
+         */
+        else if (dev->power.request_pending &&
+            dev->power.request > RPM_REQ_IDLE)
+                retval = -EAGAIN;
+
+        /* Act as though RPM_NOWAIT is always set. */
+        else if (dev->power.idle_notification)
+                retval = -EINPROGRESS;
         if (retval)
                 goto out;
 
-        if (dev->power.request_pending) {
-                /*
-                 * If an idle notification request is pending, cancel it.  Any
-                 * other pending request takes precedence over us.
-                 */
-                if (dev->power.request == RPM_REQ_IDLE) {
-                        dev->power.request = RPM_REQ_NONE;
-                } else if (dev->power.request != RPM_REQ_NONE) {
-                        retval = -EAGAIN;
-                        goto out;
+        /* Pending requests need to be canceled. */
+        dev->power.request = RPM_REQ_NONE;
+
+        if (dev->power.no_callbacks) {
+                /* Assume ->runtime_idle() callback would have suspended. */
+                retval = rpm_suspend(dev, rpmflags);
+                goto out;
+        }
+
+        /* Carry out an asynchronous or a synchronous idle notification. */
+        if (rpmflags & RPM_ASYNC) {
+                dev->power.request = RPM_REQ_IDLE;
+                if (!dev->power.request_pending) {
+                        dev->power.request_pending = true;
+                        queue_work(pm_wq, &dev->power.work);
                 }
+                goto out;
         }
 
         dev->power.idle_notification = true;
 
-        if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_idle) {
-                spin_unlock_irq(&dev->power.lock);
-
-                dev->bus->pm->runtime_idle(dev);
-
-                spin_lock_irq(&dev->power.lock);
-        } else if (dev->type && dev->type->pm && dev->type->pm->runtime_idle) {
-                spin_unlock_irq(&dev->power.lock);
-
-                dev->type->pm->runtime_idle(dev);
+        if (dev->pwr_domain)
+                callback = dev->pwr_domain->ops.runtime_idle;
+        else if (dev->type && dev->type->pm)
+                callback = dev->type->pm->runtime_idle;
+        else if (dev->class && dev->class->pm)
+                callback = dev->class->pm->runtime_idle;
+        else if (dev->bus && dev->bus->pm)
+                callback = dev->bus->pm->runtime_idle;
+        else
+                callback = NULL;
 
-                spin_lock_irq(&dev->power.lock);
-        } else if (dev->class && dev->class->pm
-            && dev->class->pm->runtime_idle) {
+        if (callback) {
                 spin_unlock_irq(&dev->power.lock);
 
-                dev->class->pm->runtime_idle(dev);
+                callback(dev);
 
                 spin_lock_irq(&dev->power.lock);
         }
@@ -108,113 +240,102 @@ static int __pm_runtime_idle(struct device *dev)
 }
 
 /**
- * pm_runtime_idle - Notify device bus type if the device can be suspended.
- * @dev: Device to notify the bus type about.
+ * rpm_callback - Run a given runtime PM callback for a given device.
+ * @cb: Runtime PM callback to run.
+ * @dev: Device to run the callback for.
  */
-int pm_runtime_idle(struct device *dev)
+static int rpm_callback(int (*cb)(struct device *), struct device *dev)
+        __releases(&dev->power.lock) __acquires(&dev->power.lock)
 {
         int retval;
 
-        spin_lock_irq(&dev->power.lock);
-        retval = __pm_runtime_idle(dev);
-        spin_unlock_irq(&dev->power.lock);
-
-        return retval;
-}
-EXPORT_SYMBOL_GPL(pm_runtime_idle);
-
-
-/**
- * update_pm_runtime_accounting - Update the time accounting of power states
- * @dev: Device to update the accounting for
- *
- * In order to be able to have time accounting of the various power states
- * (as used by programs such as PowerTOP to show the effectiveness of runtime
- * PM), we need to track the time spent in each state.
- * update_pm_runtime_accounting must be called each time before the
- * runtime_status field is updated, to account the time in the old state
- * correctly.
- */
-void update_pm_runtime_accounting(struct device *dev)
-{
-        unsigned long now = jiffies;
-        int delta;
-
-        delta = now - dev->power.accounting_timestamp;
-
-        if (delta < 0)
-                delta = 0;
+        if (!cb)
+                return -ENOSYS;
 
-        dev->power.accounting_timestamp = now;
-
-        if (dev->power.disable_depth > 0)
-                return;
+        if (dev->power.irq_safe) {
+                retval = cb(dev);
+        } else {
+                spin_unlock_irq(&dev->power.lock);
 
-        if (dev->power.runtime_status == RPM_SUSPENDED)
-                dev->power.suspended_jiffies += delta;
-        else
-                dev->power.active_jiffies += delta;
-}
+                retval = cb(dev);
 
-static void __update_runtime_status(struct device *dev, enum rpm_status status)
-{
-        update_pm_runtime_accounting(dev);
-        dev->power.runtime_status = status;
+                spin_lock_irq(&dev->power.lock);
+        }
+        dev->power.runtime_error = retval;
+        return retval;
 }
 
 /**
- * __pm_runtime_suspend - Carry out run-time suspend of given device.
+ * rpm_suspend - Carry out run-time suspend of given device.
  * @dev: Device to suspend.
- * @from_wq: If set, the function has been called via pm_wq.
+ * @rpmflags: Flag bits.
  *
- * Check if the device can be suspended and run the ->runtime_suspend() callback
- * provided by its bus type.  If another suspend has been started earlier, wait
- * for it to finish.  If an idle notification or suspend request is pending or
- * scheduled, cancel it.
+ * Check if the device's run-time PM status allows it to be suspended.  If
+ * another suspend has been started earlier, either return immediately or wait
+ * for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC flags.  Cancel a
+ * pending idle notification.  If the RPM_ASYNC flag is set then queue a
+ * suspend request; otherwise run the ->runtime_suspend() callback directly.
+ * If a deferred resume was requested while the callback was running then carry
+ * it out; otherwise send an idle notification for the device (if the suspend
+ * failed) or for its parent (if the suspend succeeded).
  *
  * This function must be called under dev->power.lock with interrupts disabled.
  */
-int __pm_runtime_suspend(struct device *dev, bool from_wq)
+static int rpm_suspend(struct device *dev, int rpmflags)
         __releases(&dev->power.lock) __acquires(&dev->power.lock)
 {
+        int (*callback)(struct device *);
         struct device *parent = NULL;
-        bool notify = false;
-        int retval = 0;
+        int retval;
 
-        dev_dbg(dev, "__pm_runtime_suspend()%s!\n",
-                from_wq ? " from workqueue" : "");
+        dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags);
 
  repeat:
-        if (dev->power.runtime_error) {
-                retval = -EINVAL;
-                goto out;
-        }
+        retval = rpm_check_suspend_allowed(dev);
 
-        /* Pending resume requests take precedence over us. */
-        if (dev->power.request_pending
-            && dev->power.request == RPM_REQ_RESUME) {
+        if (retval < 0)
+                ;       /* Conditions are wrong. */
+
+        /* Synchronous suspends are not allowed in the RPM_RESUMING state. */
+        else if (dev->power.runtime_status == RPM_RESUMING &&
+            !(rpmflags & RPM_ASYNC))
                 retval = -EAGAIN;
+        if (retval)
                 goto out;
+
+        /* If the autosuspend_delay time hasn't expired yet, reschedule. */
+        if ((rpmflags & RPM_AUTO)
+            && dev->power.runtime_status != RPM_SUSPENDING) {
+                unsigned long expires = pm_runtime_autosuspend_expiration(dev);
+
+                if (expires != 0) {
+                        /* Pending requests need to be canceled. */
+                        dev->power.request = RPM_REQ_NONE;
+
+                        /*
+                         * Optimization: If the timer is already running and is
+                         * set to expire at or before the autosuspend delay,
+                         * avoid the overhead of resetting it.  Just let it
+                         * expire; pm_suspend_timer_fn() will take care of the
+                         * rest.
+                         */
+                        if (!(dev->power.timer_expires && time_before_eq(
+                            dev->power.timer_expires, expires))) {
+                                dev->power.timer_expires = expires;
+                                mod_timer(&dev->power.suspend_timer, expires);
+                        }
+                        dev->power.timer_autosuspends = 1;
+                        goto out;
+                }
         }
 
         /* Other scheduled or pending requests need to be canceled. */
         pm_runtime_cancel_pending(dev);
 
-        if (dev->power.runtime_status == RPM_SUSPENDED)
-                retval = 1;
-        else if (dev->power.runtime_status == RPM_RESUMING
-            || dev->power.disable_depth > 0
-            || atomic_read(&dev->power.usage_count) > 0)
-                retval = -EAGAIN;
-        else if (!pm_children_suspended(dev))
-                retval = -EBUSY;
-        if (retval)
-                goto out;
-
         if (dev->power.runtime_status == RPM_SUSPENDING) {
                 DEFINE_WAIT(wait);
 
-                if (from_wq) {
+                if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
                         retval = -EINPROGRESS;
                         goto out;
                 }
@@ -236,46 +357,44 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
                 goto repeat;
         }
 
-        __update_runtime_status(dev, RPM_SUSPENDING);
         dev->power.deferred_resume = false;
+        if (dev->power.no_callbacks)
+                goto no_callback;       /* Assume success. */
+
+        /* Carry out an asynchronous or a synchronous suspend. */
+        if (rpmflags & RPM_ASYNC) {
+                dev->power.request = (rpmflags & RPM_AUTO) ?
+                    RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND;
+                if (!dev->power.request_pending) {
+                        dev->power.request_pending = true;
+                        queue_work(pm_wq, &dev->power.work);
+                }
+                goto out;
+        }
 
-        if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend) {
-                spin_unlock_irq(&dev->power.lock);
-
-                retval = dev->bus->pm->runtime_suspend(dev);
-
-                spin_lock_irq(&dev->power.lock);
-                dev->power.runtime_error = retval;
-        } else if (dev->type && dev->type->pm
-            && dev->type->pm->runtime_suspend) {
-                spin_unlock_irq(&dev->power.lock);
-
-                retval = dev->type->pm->runtime_suspend(dev);
-
-                spin_lock_irq(&dev->power.lock);
-                dev->power.runtime_error = retval;
-        } else if (dev->class && dev->class->pm
-            && dev->class->pm->runtime_suspend) {
-                spin_unlock_irq(&dev->power.lock);
-
-                retval = dev->class->pm->runtime_suspend(dev);
+        __update_runtime_status(dev, RPM_SUSPENDING);
 
-                spin_lock_irq(&dev->power.lock);
-                dev->power.runtime_error = retval;
-        } else {
-                retval = -ENOSYS;
-        }
+        if (dev->pwr_domain)
+                callback = dev->pwr_domain->ops.runtime_suspend;
+        else if (dev->type && dev->type->pm)
+                callback = dev->type->pm->runtime_suspend;
+        else if (dev->class && dev->class->pm)
+                callback = dev->class->pm->runtime_suspend;
+        else if (dev->bus && dev->bus->pm)
+                callback = dev->bus->pm->runtime_suspend;
+        else
+                callback = NULL;
 
+        retval = rpm_callback(callback, dev);
         if (retval) {
                 __update_runtime_status(dev, RPM_ACTIVE);
-                if (retval == -EAGAIN || retval == -EBUSY) {
-                        if (dev->power.timer_expires == 0)
-                                notify = true;
+                dev->power.deferred_resume = 0;
+                if (retval == -EAGAIN || retval == -EBUSY)
                         dev->power.runtime_error = 0;
-                } else {
+                else
                         pm_runtime_cancel_pending(dev);
-                }
         } else {
+ no_callback:
                 __update_runtime_status(dev, RPM_SUSPENDED);
                 pm_runtime_deactivate_timer(dev);
 
@@ -287,89 +406,86 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
         wake_up_all(&dev->power.wait_queue);
 
         if (dev->power.deferred_resume) {
-                __pm_runtime_resume(dev, false);
+                rpm_resume(dev, 0);
                 retval = -EAGAIN;
                 goto out;
         }
 
-        if (notify)
-                __pm_runtime_idle(dev);
-
-        if (parent && !parent->power.ignore_children) {
-                spin_unlock_irq(&dev->power.lock);
+        /* Maybe the parent is now able to suspend. */
+        if (parent && !parent->power.ignore_children && !dev->power.irq_safe) {
+                spin_unlock(&dev->power.lock);
 
-                pm_request_idle(parent);
+                spin_lock(&parent->power.lock);
+                rpm_idle(parent, RPM_ASYNC);
+                spin_unlock(&parent->power.lock);
 
-                spin_lock_irq(&dev->power.lock);
+                spin_lock(&dev->power.lock);
         }
 
  out:
-        dev_dbg(dev, "__pm_runtime_suspend() returns %d!\n", retval);
+        dev_dbg(dev, "%s returns %d\n", __func__, retval);
 
         return retval;
 }
 
 /**
- * pm_runtime_suspend - Carry out run-time suspend of given device.
- * @dev: Device to suspend.
- */
-int pm_runtime_suspend(struct device *dev)
-{
-        int retval;
-
-        spin_lock_irq(&dev->power.lock);
-        retval = __pm_runtime_suspend(dev, false);
-        spin_unlock_irq(&dev->power.lock);
-
-        return retval;
-}
-EXPORT_SYMBOL_GPL(pm_runtime_suspend);
-
-/**
- * __pm_runtime_resume - Carry out run-time resume of given device.
+ * rpm_resume - Carry out run-time resume of given device.
  * @dev: Device to resume.
- * @from_wq: If set, the function has been called via pm_wq.
+ * @rpmflags: Flag bits.
  *
- * Check if the device can be woken up and run the ->runtime_resume() callback
- * provided by its bus type.  If another resume has been started earlier, wait
- * for it to finish.  If there's a suspend running in parallel with this
- * function, wait for it to finish and resume the device.  Cancel any scheduled
- * or pending requests.
+ * Check if the device's run-time PM status allows it to be resumed.  Cancel
+ * any scheduled or pending requests.  If another resume has been started
+ * earlier, either return immediately or wait for it to finish, depending on the
+ * RPM_NOWAIT and RPM_ASYNC flags.  Similarly, if there's a suspend running in
+ * parallel with this function, either tell the other process to resume after
+ * suspending (deferred_resume) or wait for it to finish.  If the RPM_ASYNC
+ * flag is set then queue a resume request; otherwise run the
+ * ->runtime_resume() callback directly.  Queue an idle notification for the
+ * device if the resume succeeded.
  *
  * This function must be called under dev->power.lock with interrupts disabled.
  */
-int __pm_runtime_resume(struct device *dev, bool from_wq)
+static int rpm_resume(struct device *dev, int rpmflags)
         __releases(&dev->power.lock) __acquires(&dev->power.lock)
 {
+        int (*callback)(struct device *);
         struct device *parent = NULL;
         int retval = 0;
 
-        dev_dbg(dev, "__pm_runtime_resume()%s!\n",
-                from_wq ? " from workqueue" : "");
+        dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags);
 
  repeat:
-        if (dev->power.runtime_error) {
+        if (dev->power.runtime_error)
                 retval = -EINVAL;
+        else if (dev->power.disable_depth > 0)
+                retval = -EAGAIN;
+        if (retval)
                 goto out;
-        }
 
-        pm_runtime_cancel_pending(dev);
+        /*
+         * Other scheduled or pending requests need to be canceled.  Small
+         * optimization: If an autosuspend timer is running, leave it running
+         * rather than cancelling it now only to restart it again in the near
+         * future.
+         */
+        dev->power.request = RPM_REQ_NONE;
+        if (!dev->power.timer_autosuspends)
+                pm_runtime_deactivate_timer(dev);
 
-        if (dev->power.runtime_status == RPM_ACTIVE)
+        if (dev->power.runtime_status == RPM_ACTIVE) {
                 retval = 1;
-        else if (dev->power.disable_depth > 0)
-                retval = -EAGAIN;
-        if (retval)
                 goto out;
+        }
 
         if (dev->power.runtime_status == RPM_RESUMING
             || dev->power.runtime_status == RPM_SUSPENDING) {
                 DEFINE_WAIT(wait);
 
-                if (from_wq) {
+                if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
                         if (dev->power.runtime_status == RPM_SUSPENDING)
                                 dev->power.deferred_resume = true;
-                        retval = -EINPROGRESS;
+                        else
+                                retval = -EINPROGRESS;
                         goto out;
                 }
 
@@ -391,12 +507,43 @@ int __pm_runtime_resume(struct device *dev, bool from_wq)
                 goto repeat;
         }
 
+        /*
+         * See if we can skip waking up the parent.  This is safe only if
+         * power.no_callbacks is set, because otherwise we don't know whether
+         * the resume will actually succeed.
+         */
+        if (dev->power.no_callbacks && !parent && dev->parent) {
+                spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING);
+                if (dev->parent->power.disable_depth > 0
+                    || dev->parent->power.ignore_children
+                    || dev->parent->power.runtime_status == RPM_ACTIVE) {
+                        atomic_inc(&dev->parent->power.child_count);
+                        spin_unlock(&dev->parent->power.lock);
+                        goto no_callback;       /* Assume success. */
+                }
+                spin_unlock(&dev->parent->power.lock);
+        }
+
+        /* Carry out an asynchronous or a synchronous resume. */
+        if (rpmflags & RPM_ASYNC) {
+                dev->power.request = RPM_REQ_RESUME;
+                if (!dev->power.request_pending) {
+                        dev->power.request_pending = true;
+                        queue_work(pm_wq, &dev->power.work);
+                }
+                retval = 0;
+                goto out;
+        }
+
         if (!parent && dev->parent) {
                 /*
-                 * Increment the parent's resume counter and resume it if
-                 * necessary.
+                 * Increment the parent's usage counter and resume it if
+                 * necessary.  Not needed if dev is irq-safe; then the
+                 * parent is permanently resumed.
                  */
                 parent = dev->parent;
+                if (dev->power.irq_safe)
+                        goto skip_parent;
                 spin_unlock(&dev->power.lock);
 
                 pm_runtime_get_noresume(parent);
@@ -408,7 +555,7 @@ int __pm_runtime_resume(struct device *dev, bool from_wq)
                  */
                 if (!parent->power.disable_depth
                     && !parent->power.ignore_children) {
-                        __pm_runtime_resume(parent, false);
+                        rpm_resume(parent, 0);
                         if (parent->power.runtime_status != RPM_ACTIVE)
                                 retval = -EBUSY;
                 }
@@ -419,40 +566,30 @@ int __pm_runtime_resume(struct device *dev, bool from_wq)
                         goto out;
                 goto repeat;
         }
+ skip_parent:
 
-        __update_runtime_status(dev, RPM_RESUMING);
-
-        if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume) {
-                spin_unlock_irq(&dev->power.lock);
-
-                retval = dev->bus->pm->runtime_resume(dev);
-
-                spin_lock_irq(&dev->power.lock);
-                dev->power.runtime_error = retval;
-        } else if (dev->type && dev->type->pm
-            && dev->type->pm->runtime_resume) {
-                spin_unlock_irq(&dev->power.lock);
-
-                retval = dev->type->pm->runtime_resume(dev);
-
-                spin_lock_irq(&dev->power.lock);
-                dev->power.runtime_error = retval;
-        } else if (dev->class && dev->class->pm
-            && dev->class->pm->runtime_resume) {
-                spin_unlock_irq(&dev->power.lock);
+        if (dev->power.no_callbacks)
+                goto no_callback;       /* Assume success. */
 
-                retval = dev->class->pm->runtime_resume(dev);
+        __update_runtime_status(dev, RPM_RESUMING);
 
-                spin_lock_irq(&dev->power.lock);
-                dev->power.runtime_error = retval;
-        } else {
-                retval = -ENOSYS;
-        }
+        if (dev->pwr_domain)
+                callback = dev->pwr_domain->ops.runtime_resume;
+        else if (dev->type && dev->type->pm)
+                callback = dev->type->pm->runtime_resume;
+        else if (dev->class && dev->class->pm)
+                callback = dev->class->pm->runtime_resume;
+        else if (dev->bus && dev->bus->pm)
+                callback = dev->bus->pm->runtime_resume;
+        else
+                callback = NULL;
 
+        retval = rpm_callback(callback, dev);
         if (retval) {
                 __update_runtime_status(dev, RPM_SUSPENDED);
                 pm_runtime_cancel_pending(dev);
         } else {
+ no_callback:
                 __update_runtime_status(dev, RPM_ACTIVE);
                 if (parent)
                         atomic_inc(&parent->power.child_count);
@@ -460,10 +597,10 @@ int __pm_runtime_resume(struct device *dev, bool from_wq)
         wake_up_all(&dev->power.wait_queue);
 
         if (!retval)
-                __pm_request_idle(dev);
+                rpm_idle(dev, RPM_ASYNC);
 
  out:
-        if (parent) {
+        if (parent && !dev->power.irq_safe) {
                 spin_unlock_irq(&dev->power.lock);
 
                 pm_runtime_put(parent);
@@ -471,28 +608,12 @@ int __pm_runtime_resume(struct device *dev, bool from_wq)
                 spin_lock_irq(&dev->power.lock);
         }
 
-        dev_dbg(dev, "__pm_runtime_resume() returns %d!\n", retval);
+        dev_dbg(dev, "%s returns %d\n", __func__, retval);
 
         return retval;
 }
 
 /**
- * pm_runtime_resume - Carry out run-time resume of given device.
- * @dev: Device to suspend.
- */
-int pm_runtime_resume(struct device *dev)
-{
-        int retval;
-
-        spin_lock_irq(&dev->power.lock);
-        retval = __pm_runtime_resume(dev, false);
-        spin_unlock_irq(&dev->power.lock);
-
-        return retval;
-}
-EXPORT_SYMBOL_GPL(pm_runtime_resume);
-
-/**
  * pm_runtime_work - Universal run-time PM work function.
  * @work: Work structure used for scheduling the execution of this function.
  *
@@ -517,13 +638,16 @@ static void pm_runtime_work(struct work_struct *work)
         case RPM_REQ_NONE:
                 break;
         case RPM_REQ_IDLE:
-                __pm_runtime_idle(dev);
+                rpm_idle(dev, RPM_NOWAIT);
                 break;
         case RPM_REQ_SUSPEND:
-                __pm_runtime_suspend(dev, true);
+                rpm_suspend(dev, RPM_NOWAIT);
+                break;
+        case RPM_REQ_AUTOSUSPEND:
+                rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO);
                 break;
         case RPM_REQ_RESUME:
-                __pm_runtime_resume(dev, true);
+                rpm_resume(dev, RPM_NOWAIT);
                 break;
         }
 
@@ -532,117 +656,10 @@ static void pm_runtime_work(struct work_struct *work)
 }
 
 /**
- * __pm_request_idle - Submit an idle notification request for given device.
- * @dev: Device to handle.
- *
- * Check if the device's run-time PM status is correct for suspending the device
- * and queue up a request to run __pm_runtime_idle() for it.
- *
- * This function must be called under dev->power.lock with interrupts disabled.
- */
-static int __pm_request_idle(struct device *dev)
-{
-        int retval = 0;
-
-        if (dev->power.runtime_error)
-                retval = -EINVAL;
-        else if (atomic_read(&dev->power.usage_count) > 0
-            || dev->power.disable_depth > 0
-            || dev->power.runtime_status == RPM_SUSPENDED
-            || dev->power.runtime_status == RPM_SUSPENDING)
-                retval = -EAGAIN;
-        else if (!pm_children_suspended(dev))
-                retval = -EBUSY;
-        if (retval)
-                return retval;
-
-        if (dev->power.request_pending) {
-                /* Any requests other then RPM_REQ_IDLE take precedence. */
-                if (dev->power.request == RPM_REQ_NONE)
-                        dev->power.request = RPM_REQ_IDLE;
-                else if (dev->power.request != RPM_REQ_IDLE)
-                        retval = -EAGAIN;
-                return retval;
-        }
-
-        dev->power.request = RPM_REQ_IDLE;
-        dev->power.request_pending = true;
-        queue_work(pm_wq, &dev->power.work);
-
-        return retval;
-}
-
-/**
- * pm_request_idle - Submit an idle notification request for given device.
- * @dev: Device to handle.
- */
-int pm_request_idle(struct device *dev)
-{
-        unsigned long flags;
-        int retval;
-
-        spin_lock_irqsave(&dev->power.lock, flags);
-        retval = __pm_request_idle(dev);
-        spin_unlock_irqrestore(&dev->power.lock, flags);
-
-        return retval;
-}
-EXPORT_SYMBOL_GPL(pm_request_idle);
-
-/**
- * __pm_request_suspend - Submit a suspend request for given device.
- * @dev: Device to suspend.
- *
- * This function must be called under dev->power.lock with interrupts disabled.
- */
-static int __pm_request_suspend(struct device *dev)
-{
-        int retval = 0;
-
-        if (dev->power.runtime_error)
-                return -EINVAL;
-
-        if (dev->power.runtime_status == RPM_SUSPENDED)
-                retval = 1;
-        else if (atomic_read(&dev->power.usage_count) > 0
-            || dev->power.disable_depth > 0)
-                retval = -EAGAIN;
-        else if (dev->power.runtime_status == RPM_SUSPENDING)
-                retval = -EINPROGRESS;
-        else if (!pm_children_suspended(dev))
-                retval = -EBUSY;
-        if (retval < 0)
-                return retval;
-
-        pm_runtime_deactivate_timer(dev);
-
-        if (dev->power.request_pending) {
-                /*
-                 * Pending resume requests take precedence over us, but we can
-                 * overtake any other pending request.
-                 */
-                if (dev->power.request == RPM_REQ_RESUME)
-                        retval = -EAGAIN;
-                else if (dev->power.request != RPM_REQ_SUSPEND)
-                        dev->power.request = retval ?
-                                                RPM_REQ_NONE : RPM_REQ_SUSPEND;
-                return retval;
-        } else if (retval) {
-                return retval;
-        }
-
-        dev->power.request = RPM_REQ_SUSPEND;
-        dev->power.request_pending = true;
-        queue_work(pm_wq, &dev->power.work);
-
-        return 0;
-}
-
-/**
  * pm_suspend_timer_fn - Timer function for pm_schedule_suspend().
  * @data: Device pointer passed by pm_schedule_suspend().
  *
- * Check if the time is right and execute __pm_request_suspend() in that case.
+ * Check if the time is right and queue a suspend request.
  */
 static void pm_suspend_timer_fn(unsigned long data)
 {
@@ -656,7 +673,8 @@ static void pm_suspend_timer_fn(unsigned long data)
         /* If 'expire' is after 'jiffies' we've been called too early. */
         if (expires > 0 && !time_after(expires, jiffies)) {
                 dev->power.timer_expires = 0;
-                __pm_request_suspend(dev);
+                rpm_suspend(dev, dev->power.timer_autosuspends ?
+                    (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC);
         }
 
         spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -670,47 +688,25 @@ static void pm_suspend_timer_fn(unsigned long data)
 int pm_schedule_suspend(struct device *dev, unsigned int delay)
 {
         unsigned long flags;
-        int retval = 0;
+        int retval;
 
         spin_lock_irqsave(&dev->power.lock, flags);
 
-        if (dev->power.runtime_error) {
-                retval = -EINVAL;
-                goto out;
-        }
-
         if (!delay) {
-                retval = __pm_request_suspend(dev);
+                retval = rpm_suspend(dev, RPM_ASYNC);
                 goto out;
         }
 
-        pm_runtime_deactivate_timer(dev);
-
-        if (dev->power.request_pending) {
-                /*
-                 * Pending resume requests take precedence over us, but any
-                 * other pending requests have to be canceled.
-                 */
-                if (dev->power.request == RPM_REQ_RESUME) {
-                        retval = -EAGAIN;
-                        goto out;
-                }
-                dev->power.request = RPM_REQ_NONE;
-        }
-
-        if (dev->power.runtime_status == RPM_SUSPENDED)
-                retval = 1;
-        else if (atomic_read(&dev->power.usage_count) > 0
-            || dev->power.disable_depth > 0)
-                retval = -EAGAIN;
-        else if (!pm_children_suspended(dev))
-                retval = -EBUSY;
+        retval = rpm_check_suspend_allowed(dev);
         if (retval)
                 goto out;
 
+        /* Other scheduled or pending requests need to be canceled. */
+        pm_runtime_cancel_pending(dev);
+
         dev->power.timer_expires = jiffies + msecs_to_jiffies(delay);
-        if (!dev->power.timer_expires)
-                dev->power.timer_expires = 1;
+        dev->power.timer_expires += !dev->power.timer_expires;
+        dev->power.timer_autosuspends = 0;
         mod_timer(&dev->power.suspend_timer, dev->power.timer_expires);
 
  out:
@@ -721,103 +717,88 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay)
 EXPORT_SYMBOL_GPL(pm_schedule_suspend);
 
 /**
- * pm_request_resume - Submit a resume request for given device.
- * @dev: Device to resume.
+ * __pm_runtime_idle - Entry point for run-time idle operations.
+ * @dev: Device to send idle notification for.
+ * @rpmflags: Flag bits.
  *
- * This function must be called under dev->power.lock with interrupts disabled.
+ * If the RPM_GET_PUT flag is set, decrement the device's usage count and
+ * return immediately if it is larger than zero.  Then carry out an idle
+ * notification, either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
  */
-static int __pm_request_resume(struct device *dev)
+int __pm_runtime_idle(struct device *dev, int rpmflags)
 {
-        int retval = 0;
-
-        if (dev->power.runtime_error)
-                return -EINVAL;
-
-        if (dev->power.runtime_status == RPM_ACTIVE)
-                retval = 1;
-        else if (dev->power.runtime_status == RPM_RESUMING)
-                retval = -EINPROGRESS;
-        else if (dev->power.disable_depth > 0)
-                retval = -EAGAIN;
-        if (retval < 0)
-                return retval;
-
-        pm_runtime_deactivate_timer(dev);
+        unsigned long flags;
+        int retval;
 
-        if (dev->power.runtime_status == RPM_SUSPENDING) {
-                dev->power.deferred_resume = true;
-                return retval;
-        }
-        if (dev->power.request_pending) {
-                /* If non-resume request is pending, we can overtake it. */
-                dev->power.request = retval ? RPM_REQ_NONE : RPM_REQ_RESUME;
-                return retval;
+        if (rpmflags & RPM_GET_PUT) {
+                if (!atomic_dec_and_test(&dev->power.usage_count))
+                        return 0;
         }
-        if (retval)
-                return retval;
 
-        dev->power.request = RPM_REQ_RESUME;
-        dev->power.request_pending = true;
-        queue_work(pm_wq, &dev->power.work);
+        spin_lock_irqsave(&dev->power.lock, flags);
+        retval = rpm_idle(dev, rpmflags);
+        spin_unlock_irqrestore(&dev->power.lock, flags);
 
         return retval;
 }
+EXPORT_SYMBOL_GPL(__pm_runtime_idle);
 
 /**
- * pm_request_resume - Submit a resume request for given device.
- * @dev: Device to resume.
+ * __pm_runtime_suspend - Entry point for run-time put/suspend operations.
+ * @dev: Device to suspend.
+ * @rpmflags: Flag bits.
+ *
+ * If the RPM_GET_PUT flag is set, decrement the device's usage count and
+ * return immediately if it is larger than zero.  Then carry out a suspend,
+ * either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
  */
-int pm_request_resume(struct device *dev)
+int __pm_runtime_suspend(struct device *dev, int rpmflags)
 {
         unsigned long flags;
         int retval;
 
+        if (rpmflags & RPM_GET_PUT) {
+                if (!atomic_dec_and_test(&dev->power.usage_count))
+                        return 0;
+        }
+
         spin_lock_irqsave(&dev->power.lock, flags);
-        retval = __pm_request_resume(dev);
+        retval = rpm_suspend(dev, rpmflags);
         spin_unlock_irqrestore(&dev->power.lock, flags);
 
         return retval;
 }
-EXPORT_SYMBOL_GPL(pm_request_resume);
+EXPORT_SYMBOL_GPL(__pm_runtime_suspend);
 
 /**
- * __pm_runtime_get - Reference count a device and wake it up, if necessary.
- * @dev: Device to handle.
- * @sync: If set and the device is suspended, resume it synchronously.
+ * __pm_runtime_resume - Entry point for run-time resume operations.
+ * @dev: Device to resume.
+ * @rpmflags: Flag bits.
+ *
+ * If the RPM_GET_PUT flag is set, increment the device's usage count.  Then
+ * carry out a resume, either synchronous or asynchronous.
  *
- * Increment the usage count of the device and resume it or submit a resume
- * request for it, depending on the value of @sync.
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
  */
-int __pm_runtime_get(struct device *dev, bool sync)
+int __pm_runtime_resume(struct device *dev, int rpmflags)
 {
+        unsigned long flags;
         int retval;
 
-        atomic_inc(&dev->power.usage_count);
-        retval = sync ? pm_runtime_resume(dev) : pm_request_resume(dev);
-
-        return retval;
-}
-EXPORT_SYMBOL_GPL(__pm_runtime_get);
-
-/**
- * __pm_runtime_put - Decrement the device's usage counter and notify its bus.
- * @dev: Device to handle.
- * @sync: If the device's bus type is to be notified, do that synchronously.
- *
- * Decrement the usage count of the device and if it reaches zero, carry out a
- * synchronous idle notification or submit an idle notification request for it,
- * depending on the value of @sync.
- */
-int __pm_runtime_put(struct device *dev, bool sync)
-{
-        int retval = 0;
+        if (rpmflags & RPM_GET_PUT)
+                atomic_inc(&dev->power.usage_count);
 
-        if (atomic_dec_and_test(&dev->power.usage_count))
-                retval = sync ? pm_runtime_idle(dev) : pm_request_idle(dev);
+        spin_lock_irqsave(&dev->power.lock, flags);
+        retval = rpm_resume(dev, rpmflags);
+        spin_unlock_irqrestore(&dev->power.lock, flags);
 
         return retval;
 }
-EXPORT_SYMBOL_GPL(__pm_runtime_put);
+EXPORT_SYMBOL_GPL(__pm_runtime_resume);
 
 /**
  * __pm_runtime_set_status - Set run-time PM status of a device.
@@ -968,7 +949,7 @@ int pm_runtime_barrier(struct device *dev)
 
         if (dev->power.request_pending
             && dev->power.request == RPM_REQ_RESUME) {
-                __pm_runtime_resume(dev, false);
+                rpm_resume(dev, 0);
                 retval = 1;
         }
 
@@ -1017,7 +998,7 @@ void __pm_runtime_disable(struct device *dev, bool check_resume)
                  */
                 pm_runtime_get_noresume(dev);
 
-                __pm_runtime_resume(dev, false);
+                rpm_resume(dev, 0);
 
                 pm_runtime_put_noidle(dev);
         }
@@ -1065,7 +1046,7 @@ void pm_runtime_forbid(struct device *dev)
 
         dev->power.runtime_auto = false;
         atomic_inc(&dev->power.usage_count);
-        __pm_runtime_resume(dev, false);
+        rpm_resume(dev, 0);
 
  out:
         spin_unlock_irq(&dev->power.lock);
@@ -1086,7 +1067,7 @@ void pm_runtime_allow(struct device *dev)
 
         dev->power.runtime_auto = true;
         if (atomic_dec_and_test(&dev->power.usage_count))
-                __pm_runtime_idle(dev);
+                rpm_idle(dev, RPM_AUTO);
 
  out:
         spin_unlock_irq(&dev->power.lock);
@@ -1094,13 +1075,130 @@ void pm_runtime_allow(struct device *dev)
 EXPORT_SYMBOL_GPL(pm_runtime_allow);
 
 /**
+ * pm_runtime_no_callbacks - Ignore run-time PM callbacks for a device.
+ * @dev: Device to handle.
+ *
+ * Set the power.no_callbacks flag, which tells the PM core that this
+ * device is power-managed through its parent and has no run-time PM
+ * callbacks of its own.  The run-time sysfs attributes will be removed.
+ */
+void pm_runtime_no_callbacks(struct device *dev)
+{
+        spin_lock_irq(&dev->power.lock);
+        dev->power.no_callbacks = 1;
+        spin_unlock_irq(&dev->power.lock);
+        if (device_is_registered(dev))
+                rpm_sysfs_remove(dev);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks);
+
+/**
+ * pm_runtime_irq_safe - Leave interrupts disabled during callbacks.
+ * @dev: Device to handle
+ *
+ * Set the power.irq_safe flag, which tells the PM core that the
+ * ->runtime_suspend() and ->runtime_resume() callbacks for this device should
+ * always be invoked with the spinlock held and interrupts disabled.  It also
+ * causes the parent's usage counter to be permanently incremented, preventing
+ * the parent from runtime suspending -- otherwise an irq-safe child might have
+ * to wait for a non-irq-safe parent.
+ */
+void pm_runtime_irq_safe(struct device *dev)
+{
+        if (dev->parent)
+                pm_runtime_get_sync(dev->parent);
+        spin_lock_irq(&dev->power.lock);
+        dev->power.irq_safe = 1;
+        spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_irq_safe);
+
+/**
+ * update_autosuspend - Handle a change to a device's autosuspend settings.
+ * @dev: Device to handle.
+ * @old_delay: The former autosuspend_delay value.
+ * @old_use: The former use_autosuspend value.
+ *
+ * Prevent runtime suspend if the new delay is negative and use_autosuspend is
+ * set; otherwise allow it.  Send an idle notification if suspends are allowed.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static void update_autosuspend(struct device *dev, int old_delay, int old_use)
+{
+        int delay = dev->power.autosuspend_delay;
+
+        /* Should runtime suspend be prevented now? */
+        if (dev->power.use_autosuspend && delay < 0) {
+
+                /* If it used to be allowed then prevent it. */
+                if (!old_use || old_delay >= 0) {
+                        atomic_inc(&dev->power.usage_count);
+                        rpm_resume(dev, 0);
+                }
+        }
+
+        /* Runtime suspend should be allowed now. */
+        else {
+
+                /* If it used to be prevented then allow it. */
+                if (old_use && old_delay < 0)
+                        atomic_dec(&dev->power.usage_count);
+
+                /* Maybe we can autosuspend now. */
+                rpm_idle(dev, RPM_AUTO);
+        }
+}
+
+/**
+ * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value.
+ * @dev: Device to handle.
+ * @delay: Value of the new delay in milliseconds.
+ *
+ * Set the device's power.autosuspend_delay value.  If it changes to negative
+ * and the power.use_autosuspend flag is set, prevent run-time suspends.  If it
+ * changes the other way, allow run-time suspends.
+ */
+void pm_runtime_set_autosuspend_delay(struct device *dev, int delay)
+{
+        int old_delay, old_use;
+
+        spin_lock_irq(&dev->power.lock);
+        old_delay = dev->power.autosuspend_delay;
+        old_use = dev->power.use_autosuspend;
+        dev->power.autosuspend_delay = delay;
+        update_autosuspend(dev, old_delay, old_use);
+        spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay);
+
+/**
+ * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag.
+ * @dev: Device to handle.
+ * @use: New value for use_autosuspend.
+ *
+ * Set the device's power.use_autosuspend flag, and allow or prevent run-time
+ * suspends as needed.
+ */
+void __pm_runtime_use_autosuspend(struct device *dev, bool use)
+{
+        int old_delay, old_use;
+
+        spin_lock_irq(&dev->power.lock);
+        old_delay = dev->power.autosuspend_delay;
+        old_use = dev->power.use_autosuspend;
+        dev->power.use_autosuspend = use;
+        update_autosuspend(dev, old_delay, old_use);
+        spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend);
+
+/**
  * pm_runtime_init - Initialize run-time PM fields in given device object.
  * @dev: Device object to initialize.
  */
 void pm_runtime_init(struct device *dev)
 {
-        spin_lock_init(&dev->power.lock);
-
         dev->power.runtime_status = RPM_SUSPENDED;
         dev->power.idle_notification = false;
 
@@ -1137,4 +1235,6 @@ void pm_runtime_remove(struct device *dev)
         /* Change the status back to 'suspended' to match the initial status. */
         if (dev->power.runtime_status == RPM_ACTIVE)
                 pm_runtime_set_suspended(dev);
+        if (dev->power.irq_safe && dev->parent)
+                pm_runtime_put_sync(dev->parent);
 }
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index e56b4388fe61..a9f5b8979611 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -75,12 +75,27 @@
  *      attribute is set to "enabled" by bus type code or device drivers and in
  *      that cases it should be safe to leave the default value.
  *
+ *      autosuspend_delay_ms - Report/change a device's autosuspend_delay value
+ *
+ *      Some drivers don't want to carry out a runtime suspend as soon as a
+ *      device becomes idle; they want it always to remain idle for some period
+ *      of time before suspending it.  This period is the autosuspend_delay
+ *      value (expressed in milliseconds) and it can be controlled by the user.
+ *      If the value is negative then the device will never be runtime
+ *      suspended.
+ *
+ *      NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay
+ *      value are used only if the driver calls pm_runtime_use_autosuspend().
+ *
  *      wakeup_count - Report the number of wakeup events related to the device
  */
 
 static const char enabled[] = "enabled";
 static const char disabled[] = "disabled";
 
+const char power_group_name[] = "power";
+EXPORT_SYMBOL_GPL(power_group_name);
+
 #ifdef CONFIG_PM_RUNTIME
 static const char ctrl_auto[] = "auto";
 static const char ctrl_on[] = "on";
@@ -170,8 +185,36 @@ static ssize_t rtpm_status_show(struct device *dev,
 }
 
 static DEVICE_ATTR(runtime_status, 0444, rtpm_status_show, NULL);
-#endif
 
+static ssize_t autosuspend_delay_ms_show(struct device *dev,
+                struct device_attribute *attr, char *buf)
+{
+        if (!dev->power.use_autosuspend)
+                return -EIO;
+        return sprintf(buf, "%d\n", dev->power.autosuspend_delay);
+}
+
+static ssize_t autosuspend_delay_ms_store(struct device *dev,
+                struct device_attribute *attr, const char *buf, size_t n)
+{
+        long delay;
+
+        if (!dev->power.use_autosuspend)
+                return -EIO;
+
+        if (strict_strtol(buf, 10, &delay) != 0 || delay != (int) delay)
+                return -EINVAL;
+
+        pm_runtime_set_autosuspend_delay(dev, delay);
+        return n;
+}
+
+static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
+                autosuspend_delay_ms_store);
+
+#endif /* CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM_SLEEP
 static ssize_t
 wake_show(struct device * dev, struct device_attribute *attr, char * buf)
 {
@@ -206,15 +249,125 @@ wake_store(struct device * dev, struct device_attribute *attr,
 
 static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store);
 
-#ifdef CONFIG_PM_SLEEP
 static ssize_t wakeup_count_show(struct device *dev,
                                 struct device_attribute *attr, char *buf)
 {
-        return sprintf(buf, "%lu\n", dev->power.wakeup_count);
+        unsigned long count = 0;
+        bool enabled = false;
+
+        spin_lock_irq(&dev->power.lock);
+        if (dev->power.wakeup) {
+                count = dev->power.wakeup->event_count;
+                enabled = true;
+        }
+        spin_unlock_irq(&dev->power.lock);
+        return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
 }
 
 static DEVICE_ATTR(wakeup_count, 0444, wakeup_count_show, NULL);
-#endif
+
+static ssize_t wakeup_active_count_show(struct device *dev,
+                                struct device_attribute *attr, char *buf)
+{
+        unsigned long count = 0;
+        bool enabled = false;
+
+        spin_lock_irq(&dev->power.lock);
+        if (dev->power.wakeup) {
+                count = dev->power.wakeup->active_count;
+                enabled = true;
+        }
+        spin_unlock_irq(&dev->power.lock);
+        return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active_count, 0444, wakeup_active_count_show, NULL);
+
+static ssize_t wakeup_hit_count_show(struct device *dev,
+                                struct device_attribute *attr, char *buf)
+{
+        unsigned long count = 0;
+        bool enabled = false;
+
+        spin_lock_irq(&dev->power.lock);
+        if (dev->power.wakeup) {
+                count = dev->power.wakeup->hit_count;
+                enabled = true;
+        }
+        spin_unlock_irq(&dev->power.lock);
+        return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_hit_count, 0444, wakeup_hit_count_show, NULL);
+
+static ssize_t wakeup_active_show(struct device *dev,
+                                struct device_attribute *attr, char *buf)
+{
+        unsigned int active = 0;
+        bool enabled = false;
+
+        spin_lock_irq(&dev->power.lock);
+        if (dev->power.wakeup) {
+                active = dev->power.wakeup->active;
+                enabled = true;
+        }
+        spin_unlock_irq(&dev->power.lock);
+        return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active, 0444, wakeup_active_show, NULL);
+
+static ssize_t wakeup_total_time_show(struct device *dev,
+                                struct device_attribute *attr, char *buf)
+{
+        s64 msec = 0;
+        bool enabled = false;
+
+        spin_lock_irq(&dev->power.lock);
+        if (dev->power.wakeup) {
+                msec = ktime_to_ms(dev->power.wakeup->total_time);
+                enabled = true;
+        }
+        spin_unlock_irq(&dev->power.lock);
+        return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_total_time_ms, 0444, wakeup_total_time_show, NULL);
+
+static ssize_t wakeup_max_time_show(struct device *dev,
+                                struct device_attribute *attr, char *buf)
+{
+        s64 msec = 0;
+        bool enabled = false;
+
+        spin_lock_irq(&dev->power.lock);
+        if (dev->power.wakeup) {
+                msec = ktime_to_ms(dev->power.wakeup->max_time);
+                enabled = true;
+        }
+        spin_unlock_irq(&dev->power.lock);
+        return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_max_time_ms, 0444, wakeup_max_time_show, NULL);
+
+static ssize_t wakeup_last_time_show(struct device *dev,
+                                struct device_attribute *attr, char *buf)
+{
+        s64 msec = 0;
+        bool enabled = false;
+
+        spin_lock_irq(&dev->power.lock);
+        if (dev->power.wakeup) {
+                msec = ktime_to_ms(dev->power.wakeup->last_time);
+                enabled = true;
+        }
+        spin_unlock_irq(&dev->power.lock);
+        return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_last_time_ms, 0444, wakeup_last_time_show, NULL);
+#endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_ADVANCED_DEBUG
 #ifdef CONFIG_PM_RUNTIME
@@ -278,38 +431,108 @@ static ssize_t async_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(async, 0644, async_show, async_store);
 #endif /* CONFIG_PM_ADVANCED_DEBUG */
 
-static struct attribute * power_attrs[] = {
-#ifdef CONFIG_PM_RUNTIME
-        &dev_attr_control.attr,
-        &dev_attr_runtime_status.attr,
-        &dev_attr_runtime_suspended_time.attr,
-        &dev_attr_runtime_active_time.attr,
-#endif
-        &dev_attr_wakeup.attr,
-#ifdef CONFIG_PM_SLEEP
-        &dev_attr_wakeup_count.attr,
-#endif
+static struct attribute *power_attrs[] = {
 #ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_SLEEP
         &dev_attr_async.attr,
+#endif
 #ifdef CONFIG_PM_RUNTIME
+        &dev_attr_runtime_status.attr,
         &dev_attr_runtime_usage.attr,
         &dev_attr_runtime_active_kids.attr,
         &dev_attr_runtime_enabled.attr,
 #endif
-#endif
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
         NULL,
 };
 static struct attribute_group pm_attr_group = {
-        .name   = "power",
+        .name   = power_group_name,
         .attrs  = power_attrs,
 };
 
-int dpm_sysfs_add(struct device * dev)
+static struct attribute *wakeup_attrs[] = {
+#ifdef CONFIG_PM_SLEEP
+        &dev_attr_wakeup.attr,
+        &dev_attr_wakeup_count.attr,
+        &dev_attr_wakeup_active_count.attr,
+        &dev_attr_wakeup_hit_count.attr,
+        &dev_attr_wakeup_active.attr,
+        &dev_attr_wakeup_total_time_ms.attr,
+        &dev_attr_wakeup_max_time_ms.attr,
+        &dev_attr_wakeup_last_time_ms.attr,
+#endif
+        NULL,
+};
+static struct attribute_group pm_wakeup_attr_group = {
+        .name   = power_group_name,
+        .attrs  = wakeup_attrs,
+};
+
+static struct attribute *runtime_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+#ifndef CONFIG_PM_ADVANCED_DEBUG
+        &dev_attr_runtime_status.attr,
+#endif
+        &dev_attr_control.attr,
+        &dev_attr_runtime_suspended_time.attr,
+        &dev_attr_runtime_active_time.attr,
+        &dev_attr_autosuspend_delay_ms.attr,
+#endif /* CONFIG_PM_RUNTIME */
+        NULL,
+};
+static struct attribute_group pm_runtime_attr_group = {
+        .name   = power_group_name,
+        .attrs  = runtime_attrs,
+};
+
+int dpm_sysfs_add(struct device *dev)
+{
+        int rc;
+
+        rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
+        if (rc)
+                return rc;
+
+        if (pm_runtime_callbacks_present(dev)) {
+                rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group);
+                if (rc)
+                        goto err_out;
+        }
+
+        if (device_can_wakeup(dev)) {
+                rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+                if (rc) {
+                        if (pm_runtime_callbacks_present(dev))
+                                sysfs_unmerge_group(&dev->kobj,
+                                                    &pm_runtime_attr_group);
+                        goto err_out;
+                }
+        }
+        return 0;
+
+ err_out:
+        sysfs_remove_group(&dev->kobj, &pm_attr_group);
+        return rc;
+}
+
+int wakeup_sysfs_add(struct device *dev)
+{
+        return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+}
+
+void wakeup_sysfs_remove(struct device *dev)
+{
+        sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+}
+
+void rpm_sysfs_remove(struct device *dev)
 {
-        return sysfs_create_group(&dev->kobj, &pm_attr_group);
+        sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
 }
 
-void dpm_sysfs_remove(struct device * dev)
+void dpm_sysfs_remove(struct device *dev)
 {
+        rpm_sysfs_remove(dev);
+        sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
         sysfs_remove_group(&dev->kobj, &pm_attr_group);
 }
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 0a1a2c4dbc6e..c80e138b62fe 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -112,7 +112,7 @@ static unsigned int read_magic_time(void)
         unsigned int val;
 
         get_rtc_time(&time);
-        printk("Time: %2d:%02d:%02d  Date: %02d/%02d/%02d\n",
+        pr_info("Time: %2d:%02d:%02d  Date: %02d/%02d/%02d\n",
                 time.tm_hour, time.tm_min, time.tm_sec,
                 time.tm_mon + 1, time.tm_mday, time.tm_year % 100);
         val = time.tm_year;                             /* 100 years */
@@ -179,7 +179,7 @@ static int show_file_hash(unsigned int value)
                 unsigned int hash = hash_string(lineno, file, FILEHASH);
                 if (hash != value)
                         continue;
-                printk("  hash matches %s:%u\n", file, lineno);
+                pr_info("  hash matches %s:%u\n", file, lineno);
                 match++;
         }
         return match;
@@ -188,8 +188,10 @@ static int show_file_hash(unsigned int value)
 static int show_dev_hash(unsigned int value)
 {
         int match = 0;
-        struct list_head *entry = dpm_list.prev;
+        struct list_head *entry;
 
+        device_pm_lock();
+        entry = dpm_list.prev;
         while (entry != &dpm_list) {
                 struct device * dev = to_device(entry);
                 unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH);
@@ -199,11 +201,43 @@ static int show_dev_hash(unsigned int value)
                 }
                 entry = entry->prev;
         }
+        device_pm_unlock();
         return match;
 }
 
 static unsigned int hash_value_early_read;
 
+int show_trace_dev_match(char *buf, size_t size)
+{
+        unsigned int value = hash_value_early_read / (USERHASH * FILEHASH);
+        int ret = 0;
+        struct list_head *entry;
+
+        /*
+         * It's possible that multiple devices will match the hash and we can't
+         * tell which is the culprit, so it's best to output them all.
+         */
+        device_pm_lock();
+        entry = dpm_list.prev;
+        while (size && entry != &dpm_list) {
+                struct device *dev = to_device(entry);
+                unsigned int hash = hash_string(DEVSEED, dev_name(dev),
+                                                DEVHASH);
+                if (hash == value) {
+                        int len = snprintf(buf, size, "%s\n",
+                                            dev_driver_string(dev));
+                        if (len > size)
+                                len = size;
+                        buf += len;
+                        ret += len;
+                        size -= len;
+                }
+                entry = entry->prev;
+        }
+        device_pm_unlock();
+        return ret;
+}
+
 static int early_resume_init(void)
 {
         hash_value_early_read = read_magic_time();
@@ -221,7 +255,7 @@ static int late_resume_init(void)
         val = val / FILEHASH;
         dev = val /* % DEVHASH */;
 
-        printk("  Magic number: %d:%d:%d\n", user, file, dev);
+        pr_info("  Magic number: %d:%d:%d\n", user, file, dev);
         show_file_hash(file);
         show_dev_hash(dev);
         return 0;
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index eb594facfc3f..84f7c7d5a098 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -11,7 +11,12 @@
 #include <linux/sched.h>
 #include <linux/capability.h>
 #include <linux/suspend.h>
-#include <linux/pm.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+
+#include "power.h"
+
+#define TIMEOUT         100
 
 /*
  * If set, the suspend/hibernate code will abort transitions to a sleep state
@@ -19,19 +24,287 @@
  */
 bool events_check_enabled;
 
-/* The counter of registered wakeup events. */
-static unsigned long event_count;
-/* A preserved old value of event_count. */
-static unsigned long saved_event_count;
-/* The counter of wakeup events being processed. */
-static unsigned long events_in_progress;
+/*
+ * Combined counters of registered wakeup events and wakeup events in progress.
+ * They need to be modified together atomically, so it's better to use one
+ * atomic variable to hold them both.
+ */
+static atomic_t combined_event_count = ATOMIC_INIT(0);
+
+#define IN_PROGRESS_BITS        (sizeof(int) * 4)
+#define MAX_IN_PROGRESS         ((1 << IN_PROGRESS_BITS) - 1)
+
+static void split_counters(unsigned int *cnt, unsigned int *inpr)
+{
+        unsigned int comb = atomic_read(&combined_event_count);
+
+        *cnt = (comb >> IN_PROGRESS_BITS);
+        *inpr = comb & MAX_IN_PROGRESS;
+}
+
+/* A preserved old value of the events counter. */
+static unsigned int saved_count;
 
 static DEFINE_SPINLOCK(events_lock);
 
 static void pm_wakeup_timer_fn(unsigned long data);
 
-static DEFINE_TIMER(events_timer, pm_wakeup_timer_fn, 0, 0);
-static unsigned long events_timer_expires;
+static LIST_HEAD(wakeup_sources);
+
+/**
+ * wakeup_source_create - Create a struct wakeup_source object.
+ * @name: Name of the new wakeup source.
+ */
+struct wakeup_source *wakeup_source_create(const char *name)
+{
+        struct wakeup_source *ws;
+
+        ws = kzalloc(sizeof(*ws), GFP_KERNEL);
+        if (!ws)
+                return NULL;
+
+        spin_lock_init(&ws->lock);
+        if (name)
+                ws->name = kstrdup(name, GFP_KERNEL);
+
+        return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_create);
+
+/**
+ * wakeup_source_destroy - Destroy a struct wakeup_source object.
+ * @ws: Wakeup source to destroy.
+ */
+void wakeup_source_destroy(struct wakeup_source *ws)
+{
+        if (!ws)
+                return;
+
+        spin_lock_irq(&ws->lock);
+        while (ws->active) {
+                spin_unlock_irq(&ws->lock);
+
+                schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
+
+                spin_lock_irq(&ws->lock);
+        }
+        spin_unlock_irq(&ws->lock);
+
+        kfree(ws->name);
+        kfree(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_destroy);
+
+/**
+ * wakeup_source_add - Add given object to the list of wakeup sources.
+ * @ws: Wakeup source object to add to the list.
+ */
+void wakeup_source_add(struct wakeup_source *ws)
+{
+        if (WARN_ON(!ws))
+                return;
+
+        setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws);
+        ws->active = false;
+
+        spin_lock_irq(&events_lock);
+        list_add_rcu(&ws->entry, &wakeup_sources);
+        spin_unlock_irq(&events_lock);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_add);
+
+/**
+ * wakeup_source_remove - Remove given object from the wakeup sources list.
+ * @ws: Wakeup source object to remove from the list.
+ */
+void wakeup_source_remove(struct wakeup_source *ws)
+{
+        if (WARN_ON(!ws))
+                return;
+
+        spin_lock_irq(&events_lock);
+        list_del_rcu(&ws->entry);
+        spin_unlock_irq(&events_lock);
+        synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(wakeup_source_remove);
+
+/**
+ * wakeup_source_register - Create wakeup source and add it to the list.
+ * @name: Name of the wakeup source to register.
+ */
+struct wakeup_source *wakeup_source_register(const char *name)
+{
+        struct wakeup_source *ws;
+
+        ws = wakeup_source_create(name);
+        if (ws)
+                wakeup_source_add(ws);
+
+        return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_register);
+
+/**
+ * wakeup_source_unregister - Remove wakeup source from the list and remove it.
+ * @ws: Wakeup source object to unregister.
+ */
+void wakeup_source_unregister(struct wakeup_source *ws)
+{
+        wakeup_source_remove(ws);
+        wakeup_source_destroy(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_unregister);
+
+/**
+ * device_wakeup_attach - Attach a wakeup source object to a device object.
+ * @dev: Device to handle.
+ * @ws: Wakeup source object to attach to @dev.
+ *
+ * This causes @dev to be treated as a wakeup device.
+ */
+static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws)
+{
+        spin_lock_irq(&dev->power.lock);
+        if (dev->power.wakeup) {
+                spin_unlock_irq(&dev->power.lock);
+                return -EEXIST;
+        }
+        dev->power.wakeup = ws;
+        spin_unlock_irq(&dev->power.lock);
+        return 0;
+}
+
+/**
+ * device_wakeup_enable - Enable given device to be a wakeup source.
+ * @dev: Device to handle.
+ *
+ * Create a wakeup source object, register it and attach it to @dev.
+ */
+int device_wakeup_enable(struct device *dev)
+{
+        struct wakeup_source *ws;
+        int ret;
+
+        if (!dev || !dev->power.can_wakeup)
+                return -EINVAL;
+
+        ws = wakeup_source_register(dev_name(dev));
+        if (!ws)
+                return -ENOMEM;
+
+        ret = device_wakeup_attach(dev, ws);
+        if (ret)
+                wakeup_source_unregister(ws);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_enable);
+
+/**
+ * device_wakeup_detach - Detach a device's wakeup source object from it.
+ * @dev: Device to detach the wakeup source object from.
+ *
+ * After it returns, @dev will not be treated as a wakeup device any more.
+ */
+static struct wakeup_source *device_wakeup_detach(struct device *dev)
+{
+        struct wakeup_source *ws;
+
+        spin_lock_irq(&dev->power.lock);
+        ws = dev->power.wakeup;
+        dev->power.wakeup = NULL;
+        spin_unlock_irq(&dev->power.lock);
+        return ws;
+}
+
+/**
+ * device_wakeup_disable - Do not regard a device as a wakeup source any more.
+ * @dev: Device to handle.
+ *
+ * Detach the @dev's wakeup source object from it, unregister this wakeup source
+ * object and destroy it.
+ */
+int device_wakeup_disable(struct device *dev)
+{
+        struct wakeup_source *ws;
+
+        if (!dev || !dev->power.can_wakeup)
+                return -EINVAL;
+
+        ws = device_wakeup_detach(dev);
+        if (ws)
+                wakeup_source_unregister(ws);
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_disable);
+
+/**
+ * device_set_wakeup_capable - Set/reset device wakeup capability flag.
+ * @dev: Device to handle.
+ * @capable: Whether or not @dev is capable of waking up the system from sleep.
+ *
+ * If @capable is set, set the @dev's power.can_wakeup flag and add its
+ * wakeup-related attributes to sysfs.  Otherwise, unset the @dev's
+ * power.can_wakeup flag and remove its wakeup-related attributes from sysfs.
+ *
+ * This function may sleep and it can't be called from any context where
+ * sleeping is not allowed.
+ */
+void device_set_wakeup_capable(struct device *dev, bool capable)
+{
+        if (!!dev->power.can_wakeup == !!capable)
+                return;
+
+        if (device_is_registered(dev) && !list_empty(&dev->power.entry)) {
+                if (capable) {
+                        if (wakeup_sysfs_add(dev))
+                                return;
+                } else {
+                        wakeup_sysfs_remove(dev);
+                }
+        }
+        dev->power.can_wakeup = capable;
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_capable);
+
+/**
+ * device_init_wakeup - Device wakeup initialization.
+ * @dev: Device to handle.
+ * @enable: Whether or not to enable @dev as a wakeup device.
+ *
+ * By default, most devices should leave wakeup disabled.  The exceptions are
+ * devices that everyone expects to be wakeup sources: keyboards, power buttons,
+ * possibly network interfaces, etc.
+ */
+int device_init_wakeup(struct device *dev, bool enable)
+{
+        int ret = 0;
+
+        if (enable) {
+                device_set_wakeup_capable(dev, true);
+                ret = device_wakeup_enable(dev);
+        } else {
+                device_set_wakeup_capable(dev, false);
+        }
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(device_init_wakeup);
+
+/**
+ * device_set_wakeup_enable - Enable or disable a device to wake up the system.
+ * @dev: Device to handle.
+ */
+int device_set_wakeup_enable(struct device *dev, bool enable)
+{
+        if (!dev || !dev->power.can_wakeup)
+                return -EINVAL;
+
+        return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev);
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
 
 /*
  * The functions below use the observation that each wakeup event starts a
@@ -55,139 +328,282 @@ static unsigned long events_timer_expires;
  * knowledge, however, may not be available to it, so it can simply specify time
  * to wait before the system can be suspended and pass it as the second
  * argument of pm_wakeup_event().
+ *
+ * It is valid to call pm_relax() after pm_wakeup_event(), in which case the
+ * "no suspend" period will be ended either by the pm_relax(), or by the timer
+ * function executed when the timer expires, whichever comes first.
+ */
+
+/**
+ * wakup_source_activate - Mark given wakeup source as active.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and, if @ws has just been activated, notify the PM
+ * core of the event by incrementing the counter of of wakeup events being
+ * processed.
  */
+static void wakeup_source_activate(struct wakeup_source *ws)
+{
+        ws->active = true;
+        ws->active_count++;
+        ws->timer_expires = jiffies;
+        ws->last_time = ktime_get();
+
+        /* Increment the counter of events in progress. */
+        atomic_inc(&combined_event_count);
+}
+
+/**
+ * __pm_stay_awake - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the source of the event.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_stay_awake(struct wakeup_source *ws)
+{
+        unsigned long flags;
+
+        if (!ws)
+                return;
+
+        spin_lock_irqsave(&ws->lock, flags);
+        ws->event_count++;
+        if (!ws->active)
+                wakeup_source_activate(ws);
+        spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_stay_awake);
 
 /**
  * pm_stay_awake - Notify the PM core that a wakeup event is being processed.
  * @dev: Device the wakeup event is related to.
  *
- * Notify the PM core of a wakeup event (signaled by @dev) by incrementing the
- * counter of wakeup events being processed.  If @dev is not NULL, the counter
- * of wakeup events related to @dev is incremented too.
+ * Notify the PM core of a wakeup event (signaled by @dev) by calling
+ * __pm_stay_awake for the @dev's wakeup source object.
  *
  * Call this function after detecting of a wakeup event if pm_relax() is going
  * to be called directly after processing the event (and possibly passing it to
  * user space for further processing).
- *
- * It is safe to call this function from interrupt context.
  */
 void pm_stay_awake(struct device *dev)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&events_lock, flags);
-        if (dev)
-                dev->power.wakeup_count++;
+        if (!dev)
+                return;
 
-        events_in_progress++;
-        spin_unlock_irqrestore(&events_lock, flags);
+        spin_lock_irqsave(&dev->power.lock, flags);
+        __pm_stay_awake(dev->power.wakeup);
+        spin_unlock_irqrestore(&dev->power.lock, flags);
 }
+EXPORT_SYMBOL_GPL(pm_stay_awake);
 
 /**
- * pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * wakup_source_deactivate - Mark given wakeup source as inactive.
+ * @ws: Wakeup source to handle.
  *
- * Notify the PM core that a wakeup event has been processed by decrementing
- * the counter of wakeup events being processed and incrementing the counter
- * of registered wakeup events.
+ * Update the @ws' statistics and notify the PM core that the wakeup source has
+ * become inactive by decrementing the counter of wakeup events being processed
+ * and incrementing the counter of registered wakeup events.
+ */
+static void wakeup_source_deactivate(struct wakeup_source *ws)
+{
+        ktime_t duration;
+        ktime_t now;
+
+        ws->relax_count++;
+        /*
+         * __pm_relax() may be called directly or from a timer function.
+         * If it is called directly right after the timer function has been
+         * started, but before the timer function calls __pm_relax(), it is
+         * possible that __pm_stay_awake() will be called in the meantime and
+         * will set ws->active.  Then, ws->active may be cleared immediately
+         * by the __pm_relax() called from the timer function, but in such a
+         * case ws->relax_count will be different from ws->active_count.
+         */
+        if (ws->relax_count != ws->active_count) {
+                ws->relax_count--;
+                return;
+        }
+
+        ws->active = false;
+
+        now = ktime_get();
+        duration = ktime_sub(now, ws->last_time);
+        ws->total_time = ktime_add(ws->total_time, duration);
+        if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time))
+                ws->max_time = duration;
+
+        del_timer(&ws->timer);
+
+        /*
+         * Increment the counter of registered wakeup events and decrement the
+         * couter of wakeup events in progress simultaneously.
+         */
+        atomic_add(MAX_IN_PROGRESS, &combined_event_count);
+}
+
+/**
+ * __pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @ws: Wakeup source object associated with the source of the event.
  *
  * Call this function for wakeup events whose processing started with calling
- * pm_stay_awake().
+ * __pm_stay_awake().
  *
  * It is safe to call it from interrupt context.
  */
-void pm_relax(void)
+void __pm_relax(struct wakeup_source *ws)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&events_lock, flags);
-        if (events_in_progress) {
-                events_in_progress--;
-                event_count++;
-        }
-        spin_unlock_irqrestore(&events_lock, flags);
+        if (!ws)
+                return;
+
+        spin_lock_irqsave(&ws->lock, flags);
+        if (ws->active)
+                wakeup_source_deactivate(ws);
+        spin_unlock_irqrestore(&ws->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__pm_relax);
+
+/**
+ * pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @dev: Device that signaled the event.
+ *
+ * Execute __pm_relax() for the @dev's wakeup source object.
+ */
+void pm_relax(struct device *dev)
+{
+        unsigned long flags;
+
+        if (!dev)
+                return;
+
+        spin_lock_irqsave(&dev->power.lock, flags);
+        __pm_relax(dev->power.wakeup);
+        spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_relax);
 
 /**
  * pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
+ * @data: Address of the wakeup source object associated with the event source.
  *
- * Decrease the counter of wakeup events being processed after it was increased
- * by pm_wakeup_event().
+ * Call __pm_relax() for the wakeup source whose address is stored in @data.
  */
 static void pm_wakeup_timer_fn(unsigned long data)
 {
+        __pm_relax((struct wakeup_source *)data);
+}
+
+/**
+ * __pm_wakeup_event - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the event source.
+ * @msec: Anticipated event processing time (in milliseconds).
+ *
+ * Notify the PM core of a wakeup event whose source is @ws that will take
+ * approximately @msec milliseconds to be processed by the kernel.  If @ws is
+ * not active, activate it.  If @msec is nonzero, set up the @ws' timer to
+ * execute pm_wakeup_timer_fn() in future.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec)
+{
         unsigned long flags;
+        unsigned long expires;
 
-        spin_lock_irqsave(&events_lock, flags);
-        if (events_timer_expires
-            && time_before_eq(events_timer_expires, jiffies)) {
-                events_in_progress--;
-                events_timer_expires = 0;
+        if (!ws)
+                return;
+
+        spin_lock_irqsave(&ws->lock, flags);
+
+        ws->event_count++;
+        if (!ws->active)
+                wakeup_source_activate(ws);
+
+        if (!msec) {
+                wakeup_source_deactivate(ws);
+                goto unlock;
         }
-        spin_unlock_irqrestore(&events_lock, flags);
+
+        expires = jiffies + msecs_to_jiffies(msec);
+        if (!expires)
+                expires = 1;
+
+        if (time_after(expires, ws->timer_expires)) {
+                mod_timer(&ws->timer, expires);
+                ws->timer_expires = expires;
+        }
+
+ unlock:
+        spin_unlock_irqrestore(&ws->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__pm_wakeup_event);
+
 
 /**
  * pm_wakeup_event - Notify the PM core of a wakeup event.
  * @dev: Device the wakeup event is related to.
  * @msec: Anticipated event processing time (in milliseconds).
  *
- * Notify the PM core of a wakeup event (signaled by @dev) that will take
- * approximately @msec milliseconds to be processed by the kernel.  Increment
- * the counter of registered wakeup events and (if @msec is nonzero) set up
- * the wakeup events timer to execute pm_wakeup_timer_fn() in future (if the
- * timer has not been set up already, increment the counter of wakeup events
- * being processed).  If @dev is not NULL, the counter of wakeup events related
- * to @dev is incremented too.
- *
- * It is safe to call this function from interrupt context.
+ * Call __pm_wakeup_event() for the @dev's wakeup source object.
  */
 void pm_wakeup_event(struct device *dev, unsigned int msec)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&events_lock, flags);
-        event_count++;
-        if (dev)
-                dev->power.wakeup_count++;
-
-        if (msec) {
-                unsigned long expires;
+        if (!dev)
+                return;
 
-                expires = jiffies + msecs_to_jiffies(msec);
-                if (!expires)
-                        expires = 1;
+        spin_lock_irqsave(&dev->power.lock, flags);
+        __pm_wakeup_event(dev->power.wakeup, msec);
+        spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_wakeup_event);
 
-                if (!events_timer_expires
-                    || time_after(expires, events_timer_expires)) {
-                        if (!events_timer_expires)
-                                events_in_progress++;
+/**
+ * pm_wakeup_update_hit_counts - Update hit counts of all active wakeup sources.
+ */
+static void pm_wakeup_update_hit_counts(void)
+{
+        unsigned long flags;
+        struct wakeup_source *ws;
 
-                        mod_timer(&events_timer, expires);
-                        events_timer_expires = expires;
-                }
+        rcu_read_lock();
+        list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+                spin_lock_irqsave(&ws->lock, flags);
+                if (ws->active)
+                        ws->hit_count++;
+                spin_unlock_irqrestore(&ws->lock, flags);
         }
-        spin_unlock_irqrestore(&events_lock, flags);
+        rcu_read_unlock();
 }
 
 /**
- * pm_check_wakeup_events - Check for new wakeup events.
+ * pm_wakeup_pending - Check if power transition in progress should be aborted.
  *
  * Compare the current number of registered wakeup events with its preserved
- * value from the past to check if new wakeup events have been registered since
- * the old value was stored.  Check if the current number of wakeup events being
- * processed is zero.
+ * value from the past and return true if new wakeup events have been registered
+ * since the old value was stored.  Also return true if the current number of
+ * wakeup events being processed is different from zero.
  */
-bool pm_check_wakeup_events(void)
+bool pm_wakeup_pending(void)
 {
         unsigned long flags;
-        bool ret = true;
+        bool ret = false;
 
         spin_lock_irqsave(&events_lock, flags);
         if (events_check_enabled) {
-                ret = (event_count == saved_event_count) && !events_in_progress;
-                events_check_enabled = ret;
+                unsigned int cnt, inpr;
+
+                split_counters(&cnt, &inpr);
+                ret = (cnt != saved_count || inpr > 0);
+                events_check_enabled = !ret;
         }
         spin_unlock_irqrestore(&events_lock, flags);
+        if (ret)
+                pm_wakeup_update_hit_counts();
         return ret;
 }
 
@@ -198,29 +614,25 @@ bool pm_check_wakeup_events(void)
  * Store the number of registered wakeup events at the address in @count.  Block
  * if the current number of wakeup events being processed is nonzero.
  *
- * Return false if the wait for the number of wakeup events being processed to
+ * Return 'false' if the wait for the number of wakeup events being processed to
  * drop down to zero has been interrupted by a signal (and the current number
- * of wakeup events being processed is still nonzero).  Otherwise return true.
+ * of wakeup events being processed is still nonzero).  Otherwise return 'true'.
  */
-bool pm_get_wakeup_count(unsigned long *count)
+bool pm_get_wakeup_count(unsigned int *count)
 {
-        bool ret;
-
-        spin_lock_irq(&events_lock);
-        if (capable(CAP_SYS_ADMIN))
-                events_check_enabled = false;
-
-        while (events_in_progress && !signal_pending(current)) {
-                spin_unlock_irq(&events_lock);
+        unsigned int cnt, inpr;
 
-                schedule_timeout_interruptible(msecs_to_jiffies(100));
-
-                spin_lock_irq(&events_lock);
+        for (;;) {
+                split_counters(&cnt, &inpr);
+                if (inpr == 0 || signal_pending(current))
+                        break;
+                pm_wakeup_update_hit_counts();
+                schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
         }
-        *count = event_count;
-        ret = !events_in_progress;
-        spin_unlock_irq(&events_lock);
-        return ret;
+
+        split_counters(&cnt, &inpr);
+        *count = cnt;
+        return !inpr;
 }
 
 /**
@@ -229,19 +641,106 @@ bool pm_get_wakeup_count(unsigned long *count)
  *
  * If @count is equal to the current number of registered wakeup events and the
  * current number of wakeup events being processed is zero, store @count as the
- * old number of registered wakeup events to be used by pm_check_wakeup_events()
- * and return true.  Otherwise return false.
+ * old number of registered wakeup events for pm_check_wakeup_events(), enable
+ * wakeup events detection and return 'true'.  Otherwise disable wakeup events
+ * detection and return 'false'.
  */
-bool pm_save_wakeup_count(unsigned long count)
+bool pm_save_wakeup_count(unsigned int count)
 {
-        bool ret = false;
+        unsigned int cnt, inpr;
 
+        events_check_enabled = false;
         spin_lock_irq(&events_lock);
-        if (count == event_count && !events_in_progress) {
-                saved_event_count = count;
+        split_counters(&cnt, &inpr);
+        if (cnt == count && inpr == 0) {
+                saved_count = count;
                 events_check_enabled = true;
-                ret = true;
         }
         spin_unlock_irq(&events_lock);
+        if (!events_check_enabled)
+                pm_wakeup_update_hit_counts();
+        return events_check_enabled;
+}
+
+static struct dentry *wakeup_sources_stats_dentry;
+
+/**
+ * print_wakeup_source_stats - Print wakeup source statistics information.
+ * @m: seq_file to print the statistics into.
+ * @ws: Wakeup source object to print the statistics for.
+ */
+static int print_wakeup_source_stats(struct seq_file *m,
+                                     struct wakeup_source *ws)
+{
+        unsigned long flags;
+        ktime_t total_time;
+        ktime_t max_time;
+        unsigned long active_count;
+        ktime_t active_time;
+        int ret;
+
+        spin_lock_irqsave(&ws->lock, flags);
+
+        total_time = ws->total_time;
+        max_time = ws->max_time;
+        active_count = ws->active_count;
+        if (ws->active) {
+                active_time = ktime_sub(ktime_get(), ws->last_time);
+                total_time = ktime_add(total_time, active_time);
+                if (active_time.tv64 > max_time.tv64)
+                        max_time = active_time;
+        } else {
+                active_time = ktime_set(0, 0);
+        }
+
+        ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t"
+                        "%lld\t\t%lld\t\t%lld\t\t%lld\n",
+                        ws->name, active_count, ws->event_count, ws->hit_count,
+                        ktime_to_ms(active_time), ktime_to_ms(total_time),
+                        ktime_to_ms(max_time), ktime_to_ms(ws->last_time));
+
+        spin_unlock_irqrestore(&ws->lock, flags);
+
         return ret;
 }
+
+/**
+ * wakeup_sources_stats_show - Print wakeup sources statistics information.
+ * @m: seq_file to print the statistics into.
+ */
+static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
+{
+        struct wakeup_source *ws;
+
+        seq_puts(m, "name\t\tactive_count\tevent_count\thit_count\t"
+                "active_since\ttotal_time\tmax_time\tlast_change\n");
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+                print_wakeup_source_stats(m, ws);
+        rcu_read_unlock();
+
+        return 0;
+}
+
+static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, wakeup_sources_stats_show, NULL);
+}
+
+static const struct file_operations wakeup_sources_stats_fops = {
+        .owner = THIS_MODULE,
+        .open = wakeup_sources_stats_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = single_release,
+};
+
+static int __init wakeup_sources_debugfs_init(void)
+{
+        wakeup_sources_stats_dentry = debugfs_create_file("wakeup_sources",
+                        S_IRUGO, NULL, NULL, &wakeup_sources_stats_fops);
+        return 0;
+}
+
+postcore_initcall(wakeup_sources_debugfs_init);