Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6:
  PM / Runtime: Add runtime PM statistics (v3)
  PM / Runtime: Make runtime_status attribute not debug-only (v. 2)
  PM: Do not use dynamically allocated objects in pm_wakeup_event()
  PM / Suspend: Fix ordering of calls in suspend error paths
  PM / Hibernate: Fix snapshot error code path
  PM / Hibernate: Fix hibernation_platform_enter()
  pm_qos: Get rid of the allocation in pm_qos_add_request()
  pm_qos: Reimplement using plists
  plist: Add plist_last
  PM: Make it possible to avoid races between wakeup and system sleep
  PNPACPI: Add support for remote wakeup
  PM: describe kernel policy regarding wakeup defaults (v. 2)
  PM / Hibernate: Fix typos in comments in kernel/power/swap.c

5 files changed, 374 insertions, 28 deletions

diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index 89de75325cea..cbccf9a3cee4 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_PM)	+= sysfs.o
-obj-$(CONFIG_PM_SLEEP)	+= main.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
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 941fcb87e52a..5419a49ff135 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -59,6 +59,7 @@ void device_pm_init(struct device *dev)
 {
 	dev->power.status = DPM_ON;
 	init_completion(&dev->power.completion);
+	dev->power.wakeup_count = 0;
 	pm_runtime_init(dev);
 }
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index b0ec0e9f27e9..b78c401ffa73 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -123,6 +123,45 @@ int pm_runtime_idle(struct device *dev)
 }
 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;
+
+	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_suspend - Carry out run-time suspend of given device.
  * @dev: Device to suspend.
@@ -197,7 +236,7 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
 		goto repeat;
 	}
 
-	dev->power.runtime_status = RPM_SUSPENDING;
+	__update_runtime_status(dev, RPM_SUSPENDING);
 	dev->power.deferred_resume = false;
 
 	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend) {
@@ -228,7 +267,7 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
 	}
 
 	if (retval) {
-		dev->power.runtime_status = RPM_ACTIVE;
+		__update_runtime_status(dev, RPM_ACTIVE);
 		if (retval == -EAGAIN || retval == -EBUSY) {
 			if (dev->power.timer_expires == 0)
 				notify = true;
@@ -237,7 +276,7 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq)
 			pm_runtime_cancel_pending(dev);
 		}
 	} else {
-		dev->power.runtime_status = RPM_SUSPENDED;
+		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_deactivate_timer(dev);
 
 		if (dev->parent) {
@@ -381,7 +420,7 @@ int __pm_runtime_resume(struct device *dev, bool from_wq)
 		goto repeat;
 	}
 
-	dev->power.runtime_status = RPM_RESUMING;
+	__update_runtime_status(dev, RPM_RESUMING);
 
 	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume) {
 		spin_unlock_irq(&dev->power.lock);
@@ -411,10 +450,10 @@ int __pm_runtime_resume(struct device *dev, bool from_wq)
 	}
 
 	if (retval) {
-		dev->power.runtime_status = RPM_SUSPENDED;
+		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_cancel_pending(dev);
 	} else {
-		dev->power.runtime_status = RPM_ACTIVE;
+		__update_runtime_status(dev, RPM_ACTIVE);
 		if (parent)
 			atomic_inc(&parent->power.child_count);
 	}
@@ -848,7 +887,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status)
 	}
 
  out_set:
-	dev->power.runtime_status = status;
+	__update_runtime_status(dev, status);
 	dev->power.runtime_error = 0;
  out:
 	spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -1077,6 +1116,7 @@ void pm_runtime_init(struct device *dev)
 	dev->power.request_pending = false;
 	dev->power.request = RPM_REQ_NONE;
 	dev->power.deferred_resume = false;
+	dev->power.accounting_timestamp = jiffies;
 	INIT_WORK(&dev->power.work, pm_runtime_work);
 
 	dev->power.timer_expires = 0;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index a4c33bc51257..e56b4388fe61 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -6,6 +6,7 @@
 #include <linux/string.h>
 #include <linux/pm_runtime.h>
 #include <asm/atomic.h>
+#include <linux/jiffies.h>
 #include "power.h"
 
 /*
@@ -73,6 +74,8 @@
  *	device are known to the PM core.  However, for some devices this
  *	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.
+ *
+ *	wakeup_count - Report the number of wakeup events related to the device
  */
 
 static const char enabled[] = "enabled";
@@ -108,6 +111,65 @@ static ssize_t control_store(struct device * dev, struct device_attribute *attr,
 }
 
 static DEVICE_ATTR(control, 0644, control_show, control_store);
+
+static ssize_t rtpm_active_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int ret;
+	spin_lock_irq(&dev->power.lock);
+	update_pm_runtime_accounting(dev);
+	ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies));
+	spin_unlock_irq(&dev->power.lock);
+	return ret;
+}
+
+static DEVICE_ATTR(runtime_active_time, 0444, rtpm_active_time_show, NULL);
+
+static ssize_t rtpm_suspended_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int ret;
+	spin_lock_irq(&dev->power.lock);
+	update_pm_runtime_accounting(dev);
+	ret = sprintf(buf, "%i\n",
+		jiffies_to_msecs(dev->power.suspended_jiffies));
+	spin_unlock_irq(&dev->power.lock);
+	return ret;
+}
+
+static DEVICE_ATTR(runtime_suspended_time, 0444, rtpm_suspended_time_show, NULL);
+
+static ssize_t rtpm_status_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	const char *p;
+
+	if (dev->power.runtime_error) {
+		p = "error\n";
+	} else if (dev->power.disable_depth) {
+		p = "unsupported\n";
+	} else {
+		switch (dev->power.runtime_status) {
+		case RPM_SUSPENDED:
+			p = "suspended\n";
+			break;
+		case RPM_SUSPENDING:
+			p = "suspending\n";
+			break;
+		case RPM_RESUMING:
+			p = "resuming\n";
+			break;
+		case RPM_ACTIVE:
+			p = "active\n";
+			break;
+		default:
+			return -EIO;
+		}
+	}
+	return sprintf(buf, p);
+}
+
+static DEVICE_ATTR(runtime_status, 0444, rtpm_status_show, NULL);
 #endif
 
 static ssize_t
@@ -144,6 +206,16 @@ 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);
+}
+
+static DEVICE_ATTR(wakeup_count, 0444, wakeup_count_show, NULL);
+#endif
+
 #ifdef CONFIG_PM_ADVANCED_DEBUG
 #ifdef CONFIG_PM_RUNTIME
 
@@ -172,27 +244,8 @@ static ssize_t rtpm_enabled_show(struct device *dev,
 	return sprintf(buf, "enabled\n");
 }
 
-static ssize_t rtpm_status_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	if (dev->power.runtime_error)
-		return sprintf(buf, "error\n");
-	switch (dev->power.runtime_status) {
-	case RPM_SUSPENDED:
-		return sprintf(buf, "suspended\n");
-	case RPM_SUSPENDING:
-		return sprintf(buf, "suspending\n");
-	case RPM_RESUMING:
-		return sprintf(buf, "resuming\n");
-	case RPM_ACTIVE:
-		return sprintf(buf, "active\n");
-	}
-	return -EIO;
-}
-
 static DEVICE_ATTR(runtime_usage, 0444, rtpm_usagecount_show, NULL);
 static DEVICE_ATTR(runtime_active_kids, 0444, rtpm_children_show, NULL);
-static DEVICE_ATTR(runtime_status, 0444, rtpm_status_show, NULL);
 static DEVICE_ATTR(runtime_enabled, 0444, rtpm_enabled_show, NULL);
 
 #endif
@@ -228,14 +281,19 @@ static DEVICE_ATTR(async, 0644, async_show, async_store);
 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
 #ifdef CONFIG_PM_ADVANCED_DEBUG
 	&dev_attr_async.attr,
 #ifdef CONFIG_PM_RUNTIME
 	&dev_attr_runtime_usage.attr,
 	&dev_attr_runtime_active_kids.attr,
-	&dev_attr_runtime_status.attr,
 	&dev_attr_runtime_enabled.attr,
 #endif
 #endif
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
new file mode 100644
index 000000000000..eb594facfc3f
--- /dev/null
+++ b/drivers/base/power/wakeup.c
@@ -0,0 +1,247 @@
+/*
+ * drivers/base/power/wakeup.c - System wakeup events framework
+ *
+ * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/capability.h>
+#include <linux/suspend.h>
+#include <linux/pm.h>
+
+/*
+ * If set, the suspend/hibernate code will abort transitions to a sleep state
+ * if wakeup events are registered during or immediately before the transition.
+ */
+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;
+
+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;
+
+/*
+ * The functions below use the observation that each wakeup event starts a
+ * period in which the system should not be suspended.  The moment this period
+ * will end depends on how the wakeup event is going to be processed after being
+ * detected and all of the possible cases can be divided into two distinct
+ * groups.
+ *
+ * First, a wakeup event may be detected by the same functional unit that will
+ * carry out the entire processing of it and possibly will pass it to user space
+ * for further processing.  In that case the functional unit that has detected
+ * the event may later "close" the "no suspend" period associated with it
+ * directly as soon as it has been dealt with.  The pair of pm_stay_awake() and
+ * pm_relax(), balanced with each other, is supposed to be used in such
+ * situations.
+ *
+ * Second, a wakeup event may be detected by one functional unit and processed
+ * by another one.  In that case the unit that has detected it cannot really
+ * "close" the "no suspend" period associated with it, unless it knows in
+ * advance what's going to happen to the event during processing.  This
+ * 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().
+ */
+
+/**
+ * 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.
+ *
+ * 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++;
+
+	events_in_progress++;
+	spin_unlock_irqrestore(&events_lock, flags);
+}
+
+/**
+ * pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ *
+ * 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.
+ *
+ * Call this function for wakeup events whose processing started with calling
+ * pm_stay_awake().
+ *
+ * It is safe to call it from interrupt context.
+ */
+void pm_relax(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&events_lock, flags);
+	if (events_in_progress) {
+		events_in_progress--;
+		event_count++;
+	}
+	spin_unlock_irqrestore(&events_lock, flags);
+}
+
+/**
+ * pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
+ *
+ * Decrease the counter of wakeup events being processed after it was increased
+ * by pm_wakeup_event().
+ */
+static void pm_wakeup_timer_fn(unsigned long data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&events_lock, flags);
+	if (events_timer_expires
+	    && time_before_eq(events_timer_expires, jiffies)) {
+		events_in_progress--;
+		events_timer_expires = 0;
+	}
+	spin_unlock_irqrestore(&events_lock, flags);
+}
+
+/**
+ * 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.
+ */
+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;
+
+		expires = jiffies + msecs_to_jiffies(msec);
+		if (!expires)
+			expires = 1;
+
+		if (!events_timer_expires
+		    || time_after(expires, events_timer_expires)) {
+			if (!events_timer_expires)
+				events_in_progress++;
+
+			mod_timer(&events_timer, expires);
+			events_timer_expires = expires;
+		}
+	}
+	spin_unlock_irqrestore(&events_lock, flags);
+}
+
+/**
+ * pm_check_wakeup_events - Check for new wakeup events.
+ *
+ * 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.
+ */
+bool pm_check_wakeup_events(void)
+{
+	unsigned long flags;
+	bool ret = true;
+
+	spin_lock_irqsave(&events_lock, flags);
+	if (events_check_enabled) {
+		ret = (event_count == saved_event_count) && !events_in_progress;
+		events_check_enabled = ret;
+	}
+	spin_unlock_irqrestore(&events_lock, flags);
+	return ret;
+}
+
+/**
+ * pm_get_wakeup_count - Read the number of registered wakeup events.
+ * @count: Address to store the value at.
+ *
+ * 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
+ * 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.
+ */
+bool pm_get_wakeup_count(unsigned long *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);
+
+		schedule_timeout_interruptible(msecs_to_jiffies(100));
+
+		spin_lock_irq(&events_lock);
+	}
+	*count = event_count;
+	ret = !events_in_progress;
+	spin_unlock_irq(&events_lock);
+	return ret;
+}
+
+/**
+ * pm_save_wakeup_count - Save the current number of registered wakeup events.
+ * @count: Value to compare with the current number of registered wakeup events.
+ *
+ * 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.
+ */
+bool pm_save_wakeup_count(unsigned long count)
+{
+	bool ret = false;
+
+	spin_lock_irq(&events_lock);
+	if (count == event_count && !events_in_progress) {
+		saved_event_count = count;
+		events_check_enabled = true;
+		ret = true;
+	}
+	spin_unlock_irq(&events_lock);
+	return ret;
+}