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:
  PCI PM: Make pci_prepare_to_sleep() disable wake-up if needed
  radeonfb: Use __pci_complete_power_transition()
  PCI PM: Introduce __pci_[start|complete]_power_transition() (rev. 2)
  PCI PM: Restore config spaces of all devices during early resume
  PCI PM: Make pci_set_power_state() handle devices with no PM support
  PCI PM: Put devices into low power states during late suspend (rev. 2)
  PCI PM: Move pci_restore_standard_config to pci-driver.c
  PCI PM: Use pci_set_power_state during early resume
  PCI PM: Consistently use variable name "error" for pm call return values
  kexec: Change kexec jump code ordering
  PM: Change hibernation code ordering
  PM: Change suspend code ordering
  PM: Rework handling of interrupts during suspend-resume
  PM: Introduce functions for suspending and resuming device interrupts

arch/x86/kernel/apm_32.c

@@ -1190,8 +1190,10 @@ static int suspend(int vetoable)
 	struct apm_user	*as;
 
 	device_suspend(PMSG_SUSPEND);
-	local_irq_disable();
+
 	device_power_down(PMSG_SUSPEND);
+
+	local_irq_disable();
 	sysdev_suspend(PMSG_SUSPEND);
 
 	local_irq_enable();
@@ -1209,9 +1211,12 @@ static int suspend(int vetoable)
 	if (err != APM_SUCCESS)
 		apm_error("suspend", err);
 	err = (err == APM_SUCCESS) ? 0 : -EIO;
+
 	sysdev_resume();
-	device_power_up(PMSG_RESUME);
 	local_irq_enable();
+
+	device_power_up(PMSG_RESUME);
+
 	device_resume(PMSG_RESUME);
 	queue_event(APM_NORMAL_RESUME, NULL);
 	spin_lock(&user_list_lock);
@@ -1228,8 +1233,9 @@ static void standby(void)
 {
 	int err;
 
-	local_irq_disable();
 	device_power_down(PMSG_SUSPEND);
+
+	local_irq_disable();
 	sysdev_suspend(PMSG_SUSPEND);
 	local_irq_enable();
 
@@ -1239,8 +1245,9 @@ static void standby(void)
 
 	local_irq_disable();
 	sysdev_resume();
-	device_power_up(PMSG_RESUME);
 	local_irq_enable();
+
+	device_power_up(PMSG_RESUME);
 }
 
 static apm_event_t get_event(void)

drivers/base/power/main.c

@@ -23,6 +23,7 @@
 #include <linux/pm.h>
 #include <linux/resume-trace.h>
 #include <linux/rwsem.h>
+#include <linux/interrupt.h>
 
 #include "../base.h"
 #include "power.h"
@@ -349,7 +350,8 @@ static int resume_device_noirq(struct device *dev, pm_message_t state)
  *	Execute the appropriate "noirq resume" callback for all devices marked
  *	as DPM_OFF_IRQ.
  *
- *	Must be called with interrupts disabled and only one CPU running.
+ *	Must be called under dpm_list_mtx.  Device drivers should not receive
+ *	interrupts while it's being executed.
  */
 static void dpm_power_up(pm_message_t state)
 {
@@ -370,14 +372,13 @@ static void dpm_power_up(pm_message_t state)
  *	device_power_up - Turn on all devices that need special attention.
  *	@state: PM transition of the system being carried out.
  *
- *	Power on system devices, then devices that required we shut them down
+ *	Call the "early" resume handlers and enable device drivers to receive
- *	with interrupts disabled.
+ *	interrupts.
- *
- *	Must be called with interrupts disabled.
  */
 void device_power_up(pm_message_t state)
 {
 	dpm_power_up(state);
+	resume_device_irqs();
 }
 EXPORT_SYMBOL_GPL(device_power_up);
 
@@ -602,16 +603,17 @@ static int suspend_device_noirq(struct device *dev, pm_message_t state)
  *	device_power_down - Shut down special devices.
  *	@state: PM transition of the system being carried out.
  *
- *	Power down devices that require interrupts to be disabled.
+ *	Prevent device drivers from receiving interrupts and call the "late"
- *	Then power down system devices.
+ *	suspend handlers.
  *
- *	Must be called with interrupts disabled and only one CPU running.
+ *	Must be called under dpm_list_mtx.
  */
 int device_power_down(pm_message_t state)
 {
 	struct device *dev;
 	int error = 0;
 
+	suspend_device_irqs();
 	list_for_each_entry_reverse(dev, &dpm_list, power.entry) {
 		error = suspend_device_noirq(dev, state);
 		if (error) {
@@ -621,7 +623,7 @@ int device_power_down(pm_message_t state)
 		dev->power.status = DPM_OFF_IRQ;
 	}
 	if (error)
-		dpm_power_up(resume_event(state));
+		device_power_up(resume_event(state));
 	return error;
 }
 EXPORT_SYMBOL_GPL(device_power_down);

drivers/base/sys.c

@@ -22,6 +22,7 @@
 #include <linux/pm.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
+#include <linux/interrupt.h>
 
 #include "base.h"
 
@@ -369,6 +370,13 @@ int sysdev_suspend(pm_message_t state)
 	struct sysdev_driver *drv, *err_drv;
 	int ret;
 
+	pr_debug("Checking wake-up interrupts\n");
+
+	/* Return error code if there are any wake-up interrupts pending */
+	ret = check_wakeup_irqs();
+	if (ret)
+		return ret;
+
 	pr_debug("Suspending System Devices\n");
 
 	list_for_each_entry_reverse(cls, &system_kset->list, kset.kobj.entry) {

drivers/pci/pci-driver.c

@@ -352,53 +352,60 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state)
 {
 	struct pci_dev * pci_dev = to_pci_dev(dev);
 	struct pci_driver * drv = pci_dev->driver;
-	int i = 0;
+
+	pci_dev->state_saved = false;
 
 	if (drv && drv->suspend) {
 		pci_power_t prev = pci_dev->current_state;
+		int error;
 
-		pci_dev->state_saved = false;
+		error = drv->suspend(pci_dev, state);
+		suspend_report_result(drv->suspend, error);
+		if (error)
+			return error;
 
-		i = drv->suspend(pci_dev, state);
+		if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
-		suspend_report_result(drv->suspend, i);
-		if (i)
-			return i;
-
-		if (pci_dev->state_saved)
-			goto Fixup;
-
-		if (pci_dev->current_state != PCI_D0
 		    && pci_dev->current_state != PCI_UNKNOWN) {
 			WARN_ONCE(pci_dev->current_state != prev,
 				"PCI PM: Device state not saved by %pF\n",
 				drv->suspend);
-			goto Fixup;
 		}
 	}
 
-	pci_save_state(pci_dev);
-	/*
-	 * This is for compatibility with existing code with legacy PM support.
-	 */
-	pci_pm_set_unknown_state(pci_dev);
-
- Fixup:
 	pci_fixup_device(pci_fixup_suspend, pci_dev);
 
-	return i;
+	return 0;
 }
 
 static int pci_legacy_suspend_late(struct device *dev, pm_message_t state)
 {
 	struct pci_dev * pci_dev = to_pci_dev(dev);
 	struct pci_driver * drv = pci_dev->driver;
-	int i = 0;
 
 	if (drv && drv->suspend_late) {
-		i = drv->suspend_late(pci_dev, state);
+		pci_power_t prev = pci_dev->current_state;
-		suspend_report_result(drv->suspend_late, i);
+		int error;
+
+		error = drv->suspend_late(pci_dev, state);
+		suspend_report_result(drv->suspend_late, error);
+		if (error)
+			return error;
+
+		if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+		    && pci_dev->current_state != PCI_UNKNOWN) {
+			WARN_ONCE(pci_dev->current_state != prev,
+				"PCI PM: Device state not saved by %pF\n",
+				drv->suspend_late);
+			return 0;
+		}
 	}
-	return i;
+
+	if (!pci_dev->state_saved)
+		pci_save_state(pci_dev);
+
+	pci_pm_set_unknown_state(pci_dev);
+
+	return 0;
 }
 
 static int pci_legacy_resume_early(struct device *dev)
@@ -423,6 +430,23 @@ static int pci_legacy_resume(struct device *dev)
 
 /* Auxiliary functions used by the new power management framework */
 
+/**
+ * pci_restore_standard_config - restore standard config registers of PCI device
+ * @pci_dev: PCI device to handle
+ */
+static int pci_restore_standard_config(struct pci_dev *pci_dev)
+{
+	pci_update_current_state(pci_dev, PCI_UNKNOWN);
+
+	if (pci_dev->current_state != PCI_D0) {
+		int error = pci_set_power_state(pci_dev, PCI_D0);
+		if (error)
+			return error;
+	}
+
+	return pci_dev->state_saved ? pci_restore_state(pci_dev) : 0;
+}
+
 static void pci_pm_default_resume_noirq(struct pci_dev *pci_dev)
 {
 	pci_restore_standard_config(pci_dev);
@@ -443,7 +467,6 @@ static void pci_pm_default_suspend(struct pci_dev *pci_dev)
 	/* Disable non-bridge devices without PM support */
 	if (!pci_is_bridge(pci_dev))
 		pci_disable_enabled_device(pci_dev);
-	pci_save_state(pci_dev);
 }
 
 static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev)
@@ -493,13 +516,13 @@ static int pci_pm_suspend(struct device *dev)
 	if (pci_has_legacy_pm_support(pci_dev))
 		return pci_legacy_suspend(dev, PMSG_SUSPEND);
 
+	pci_dev->state_saved = false;
+
 	if (!pm) {
 		pci_pm_default_suspend(pci_dev);
 		goto Fixup;
 	}
 
-	pci_dev->state_saved = false;
-
 	if (pm->suspend) {
 		pci_power_t prev = pci_dev->current_state;
 		int error;
@@ -509,24 +532,14 @@ static int pci_pm_suspend(struct device *dev)
 		if (error)
 			return error;
 
-		if (pci_dev->state_saved)
+		if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
-			goto Fixup;
-
-		if (pci_dev->current_state != PCI_D0
 		    && pci_dev->current_state != PCI_UNKNOWN) {
 			WARN_ONCE(pci_dev->current_state != prev,
 				"PCI PM: State of device not saved by %pF\n",
 				pm->suspend);
-			goto Fixup;
 		}
 	}
 
-	if (!pci_dev->state_saved) {
-		pci_save_state(pci_dev);
-		if (!pci_is_bridge(pci_dev))
-			pci_prepare_to_sleep(pci_dev);
-	}
-
  Fixup:
 	pci_fixup_device(pci_fixup_suspend, pci_dev);
 
@@ -536,21 +549,43 @@ static int pci_pm_suspend(struct device *dev)
 static int pci_pm_suspend_noirq(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct device_driver *drv = dev->driver;
+	struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-	int error = 0;
 
 	if (pci_has_legacy_pm_support(pci_dev))
 		return pci_legacy_suspend_late(dev, PMSG_SUSPEND);
 
-	if (drv && drv->pm && drv->pm->suspend_noirq) {
+	if (!pm) {
-		error = drv->pm->suspend_noirq(dev);
+		pci_save_state(pci_dev);
-		suspend_report_result(drv->pm->suspend_noirq, error);
+		return 0;
 	}
 
-	if (!error)
+	if (pm->suspend_noirq) {
-		pci_pm_set_unknown_state(pci_dev);
+		pci_power_t prev = pci_dev->current_state;
+		int error;
 
-	return error;
+		error = pm->suspend_noirq(dev);
+		suspend_report_result(pm->suspend_noirq, error);
+		if (error)
+			return error;
+
+		if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+		    && pci_dev->current_state != PCI_UNKNOWN) {
+			WARN_ONCE(pci_dev->current_state != prev,
+				"PCI PM: State of device not saved by %pF\n",
+				pm->suspend_noirq);
+			return 0;
+		}
+	}
+
+	if (!pci_dev->state_saved) {
+		pci_save_state(pci_dev);
+		if (!pci_is_bridge(pci_dev))
+			pci_prepare_to_sleep(pci_dev);
+	}
+
+	pci_pm_set_unknown_state(pci_dev);
+
+	return 0;
 }
 
 static int pci_pm_resume_noirq(struct device *dev)
@@ -617,13 +652,13 @@ static int pci_pm_freeze(struct device *dev)
 	if (pci_has_legacy_pm_support(pci_dev))
 		return pci_legacy_suspend(dev, PMSG_FREEZE);
 
+	pci_dev->state_saved = false;
+
 	if (!pm) {
 		pci_pm_default_suspend(pci_dev);
 		return 0;
 	}
 
-	pci_dev->state_saved = false;
-
 	if (pm->freeze) {
 		int error;
 
@@ -633,9 +668,6 @@ static int pci_pm_freeze(struct device *dev)
 			return error;
 	}
 
-	if (!pci_dev->state_saved)
-		pci_save_state(pci_dev);
-
 	return 0;
 }
 
@@ -643,20 +675,25 @@ static int pci_pm_freeze_noirq(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct device_driver *drv = dev->driver;
-	int error = 0;
 
 	if (pci_has_legacy_pm_support(pci_dev))
 		return pci_legacy_suspend_late(dev, PMSG_FREEZE);
 
 	if (drv && drv->pm && drv->pm->freeze_noirq) {
+		int error;
+
 		error = drv->pm->freeze_noirq(dev);
 		suspend_report_result(drv->pm->freeze_noirq, error);
+		if (error)
+			return error;
 	}
 
-	if (!error)
+	if (!pci_dev->state_saved)
-		pci_pm_set_unknown_state(pci_dev);
+		pci_save_state(pci_dev);
 
-	return error;
+	pci_pm_set_unknown_state(pci_dev);
+
+	return 0;
 }
 
 static int pci_pm_thaw_noirq(struct device *dev)
@@ -699,46 +736,56 @@ static int pci_pm_poweroff(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-	int error = 0;
 
 	if (pci_has_legacy_pm_support(pci_dev))
 		return pci_legacy_suspend(dev, PMSG_HIBERNATE);
 
+	pci_dev->state_saved = false;
+
 	if (!pm) {
 		pci_pm_default_suspend(pci_dev);
 		goto Fixup;
 	}
 
-	pci_dev->state_saved = false;
-
 	if (pm->poweroff) {
+		int error;
+
 		error = pm->poweroff(dev);
 		suspend_report_result(pm->poweroff, error);
+		if (error)
+			return error;
+	}
+
+ Fixup:
+	pci_fixup_device(pci_fixup_suspend, pci_dev);
+
+	return 0;
+}
+
+static int pci_pm_poweroff_noirq(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct device_driver *drv = dev->driver;
+
+	if (pci_has_legacy_pm_support(to_pci_dev(dev)))
+		return pci_legacy_suspend_late(dev, PMSG_HIBERNATE);
+
+	if (!drv || !drv->pm)
+		return 0;
+
+	if (drv->pm->poweroff_noirq) {
+		int error;
+
+		error = drv->pm->poweroff_noirq(dev);
+		suspend_report_result(drv->pm->poweroff_noirq, error);
+		if (error)
+			return error;
 	}
 
 	if (!pci_dev->state_saved && !pci_is_bridge(pci_dev))
 		pci_prepare_to_sleep(pci_dev);
 
- Fixup:
+	return 0;
-	pci_fixup_device(pci_fixup_suspend, pci_dev);
-
-	return error;
-}
-
-static int pci_pm_poweroff_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int error = 0;
-
-	if (pci_has_legacy_pm_support(to_pci_dev(dev)))
-		return pci_legacy_suspend_late(dev, PMSG_HIBERNATE);
-
-	if (drv && drv->pm && drv->pm->poweroff_noirq) {
-		error = drv->pm->poweroff_noirq(dev);
-		suspend_report_result(drv->pm->poweroff_noirq, error);
-	}
-
-	return error;
 }
 
 static int pci_pm_restore_noirq(struct device *dev)

drivers/pci/pci.c

@@ -426,7 +426,6 @@ static inline int platform_pci_sleep_wake(struct pci_dev *dev, bool enable)
  *                           given PCI device
  * @dev: PCI device to handle.
  * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
- * @wait: If 'true', wait for the device to change its power state
  *
  * RETURN VALUE:
  * -EINVAL if the requested state is invalid.
@@ -435,12 +434,15 @@ static inline int platform_pci_sleep_wake(struct pci_dev *dev, bool enable)
  * 0 if device already is in the requested state.
  * 0 if device's power state has been successfully changed.
  */
-static int
+static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
-pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
 {
 	u16 pmcsr;
 	bool need_restore = false;
 
+	/* Check if we're already there */
+	if (dev->current_state == state)
+		return 0;
+
 	if (!dev->pm_cap)
 		return -EIO;
 
@@ -451,10 +453,7 @@ pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
 	 * Can enter D0 from any state, but if we can only go deeper 
 	 * to sleep if we're already in a low power state
 	 */
-	if (dev->current_state == state) {
+	if (state != PCI_D0 && dev->current_state <= PCI_D3cold
-		/* we're already there */
-		return 0;
-	} else if (state != PCI_D0 && dev->current_state <= PCI_D3cold
 	    && dev->current_state > state) {
 		dev_err(&dev->dev, "invalid power transition "
 			"(from state %d to %d)\n", dev->current_state, state);
@@ -481,10 +480,8 @@ pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
 		break;
 	case PCI_UNKNOWN: /* Boot-up */
 		if ((pmcsr & PCI_PM_CTRL_STATE_MASK) == PCI_D3hot
-		 && !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET)) {
+		 && !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET))
 			need_restore = true;
-			wait = true;
-		}
 		/* Fall-through: force to D0 */
 	default:
 		pmcsr = 0;
@@ -494,9 +491,6 @@ pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
 	/* enter specified state */
 	pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
 
-	if (!wait)
-		return 0;
-
 	/* Mandatory power management transition delays */
 	/* see PCI PM 1.1 5.6.1 table 18 */
 	if (state == PCI_D3hot || dev->current_state == PCI_D3hot)
@@ -521,7 +515,7 @@ pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
 	if (need_restore)
 		pci_restore_bars(dev);
 
-	if (wait && dev->bus->self)
+	if (dev->bus->self)
 		pcie_aspm_pm_state_change(dev->bus->self);
 
 	return 0;
@@ -545,6 +539,53 @@ void pci_update_current_state(struct pci_dev *dev, pci_power_t state)
 	}
 }
 
+/**
+ * pci_platform_power_transition - Use platform to change device power state
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ */
+static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+	int error;
+
+	if (platform_pci_power_manageable(dev)) {
+		error = platform_pci_set_power_state(dev, state);
+		if (!error)
+			pci_update_current_state(dev, state);
+	} else {
+		error = -ENODEV;
+		/* Fall back to PCI_D0 if native PM is not supported */
+		pci_update_current_state(dev, PCI_D0);
+	}
+
+	return error;
+}
+
+/**
+ * __pci_start_power_transition - Start power transition of a PCI device
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ */
+static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+	if (state == PCI_D0)
+		pci_platform_power_transition(dev, PCI_D0);
+}
+
+/**
+ * __pci_complete_power_transition - Complete power transition of a PCI device
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ *
+ * This function should not be called directly by device drivers.
+ */
+int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+	return state > PCI_D0 ?
+			pci_platform_power_transition(dev, state) : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(__pci_complete_power_transition);
+
 /**
  * pci_set_power_state - Set the power state of a PCI device
  * @dev: PCI device to handle.
@@ -577,30 +618,21 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		 */
 		return 0;
 
-	if (state == PCI_D0 && platform_pci_power_manageable(dev)) {
+	/* Check if we're already there */
-		/*
+	if (dev->current_state == state)
-		 * Allow the platform to change the state, for example via ACPI
+		return 0;
-		 * _PR0, _PS0 and some such, but do not trust it.
+
-		 */
+	__pci_start_power_transition(dev, state);
-		int ret = platform_pci_set_power_state(dev, PCI_D0);
+
-		if (!ret)
-			pci_update_current_state(dev, PCI_D0);
-	}
 	/* This device is quirked not to be put into D3, so
 	   don't put it in D3 */
 	if (state == PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
 		return 0;
 
-	error = pci_raw_set_power_state(dev, state, true);
+	error = pci_raw_set_power_state(dev, state);
 
-	if (state > PCI_D0 && platform_pci_power_manageable(dev)) {
+	if (!__pci_complete_power_transition(dev, state))
-		/* Allow the platform to finalize the transition */
+		error = 0;
-		int ret = platform_pci_set_power_state(dev, state);
-		if (!ret) {
-			pci_update_current_state(dev, state);
-			error = 0;
-		}
-	}
 
 	return error;
 }
@@ -1231,7 +1263,7 @@ int pci_prepare_to_sleep(struct pci_dev *dev)
 	if (target_state == PCI_POWER_ERROR)
 		return -EIO;
 
-	pci_enable_wake(dev, target_state, true);
+	pci_enable_wake(dev, target_state, device_may_wakeup(&dev->dev));
 
 	error = pci_set_power_state(dev, target_state);
 
@@ -1380,50 +1412,6 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev)
 			"unable to preallocate PCI-X save buffer\n");
 }
 
-/**
- * pci_restore_standard_config - restore standard config registers of PCI device
- * @dev: PCI device to handle
- *
- * This function assumes that the device's configuration space is accessible.
- * If the device needs to be powered up, the function will wait for it to
- * change the state.
- */
-int pci_restore_standard_config(struct pci_dev *dev)
-{
-	pci_power_t prev_state;
-	int error;
-
-	pci_update_current_state(dev, PCI_D0);
-
-	prev_state = dev->current_state;
-	if (prev_state == PCI_D0)
-		goto Restore;
-
-	error = pci_raw_set_power_state(dev, PCI_D0, false);
-	if (error)
-		return error;
-
-	/*
-	 * This assumes that we won't get a bus in B2 or B3 from the BIOS, but
-	 * we've made this assumption forever and it appears to be universally
-	 * satisfied.
-	 */
-	switch(prev_state) {
-	case PCI_D3cold:
-	case PCI_D3hot:
-		mdelay(pci_pm_d3_delay);
-		break;
-	case PCI_D2:
-		udelay(PCI_PM_D2_DELAY);
-		break;
-	}
-
-	pci_update_current_state(dev, PCI_D0);
-
- Restore:
-	return dev->state_saved ? pci_restore_state(dev) : 0;
-}
-
 /**
  * pci_enable_ari - enable ARI forwarding if hardware support it
  * @dev: the PCI device

drivers/pci/pci.h

@@ -49,7 +49,6 @@ extern void pci_disable_enabled_device(struct pci_dev *dev);
 extern void pci_pm_init(struct pci_dev *dev);
 extern void platform_pci_wakeup_init(struct pci_dev *dev);
 extern void pci_allocate_cap_save_buffers(struct pci_dev *dev);
-extern int pci_restore_standard_config(struct pci_dev *dev);
 
 static inline bool pci_is_bridge(struct pci_dev *pci_dev)
 {

drivers/video/aty/radeon_pm.c

@@ -2582,7 +2582,7 @@ static void radeon_set_suspend(struct radeonfb_info *rinfo, int suspend)
 		 * calling pci_set_power_state()
 		 */
 		radeonfb_whack_power_state(rinfo, PCI_D2);
-		pci_set_power_state(rinfo->pdev, PCI_D2);
+		__pci_complete_power_transition(rinfo->pdev, PCI_D2);
 	} else {
 		printk(KERN_DEBUG "radeonfb (%s): switching to D0 state...\n",
 		       pci_name(rinfo->pdev));

drivers/xen/manage.c

@@ -39,12 +39,6 @@ static int xen_suspend(void *data)
 
 	BUG_ON(!irqs_disabled());
 
-	err = device_power_down(PMSG_SUSPEND);
-	if (err) {
-		printk(KERN_ERR "xen_suspend: device_power_down failed: %d\n",
-		       err);
-		return err;
-	}
 	err = sysdev_suspend(PMSG_SUSPEND);
 	if (err) {
 		printk(KERN_ERR "xen_suspend: sysdev_suspend failed: %d\n",
@@ -69,7 +63,6 @@ static int xen_suspend(void *data)
 	xen_mm_unpin_all();
 
 	sysdev_resume();
-	device_power_up(PMSG_RESUME);
 
 	if (!*cancelled) {
 		xen_irq_resume();
@@ -108,6 +101,12 @@ static void do_suspend(void)
 	/* XXX use normal device tree? */
 	xenbus_suspend();
 
+	err = device_power_down(PMSG_SUSPEND);
+	if (err) {
+		printk(KERN_ERR "device_power_down failed: %d\n", err);
+		goto resume_devices;
+	}
+
 	err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
 	if (err) {
 		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
@@ -120,6 +119,9 @@ static void do_suspend(void)
 	} else
 		xenbus_suspend_cancel();
 
+	device_power_up(PMSG_RESUME);
+
+resume_devices:
 	device_resume(PMSG_RESUME);
 
 	/* Make sure timer events get retriggered on all CPUs */

include/linux/interrupt.h

@@ -117,6 +117,15 @@ extern void disable_irq_nosync(unsigned int irq);
 extern void disable_irq(unsigned int irq);
 extern void enable_irq(unsigned int irq);
 
+/* The following three functions are for the core kernel use only. */
+extern void suspend_device_irqs(void);
+extern void resume_device_irqs(void);
+#ifdef CONFIG_PM_SLEEP
+extern int check_wakeup_irqs(void);
+#else
+static inline int check_wakeup_irqs(void) { return 0; }
+#endif
+
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
 
 extern cpumask_var_t irq_default_affinity;

include/linux/irq.h

@@ -67,6 +67,7 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_SPURIOUS_DISABLED	0x00800000	/* IRQ was disabled by the spurious trap */
 #define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
 #define IRQ_AFFINITY_SET	0x02000000	/* IRQ affinity was set from userspace*/
+#define IRQ_SUSPENDED		0x04000000	/* IRQ has gone through suspend sequence */
 
 #ifdef CONFIG_IRQ_PER_CPU
 # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)

include/linux/pci.h

@@ -689,6 +689,7 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size);
 /* Power management related routines */
 int pci_save_state(struct pci_dev *dev);
 int pci_restore_state(struct pci_dev *dev);
+int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state);
 int pci_set_power_state(struct pci_dev *dev, pci_power_t state);
 pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state);
 bool pci_pme_capable(struct pci_dev *dev, pci_power_t state);

kernel/irq/Makefile

@@ -4,3 +4,4 @@ obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
 obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o
+obj-$(CONFIG_PM_SLEEP) += pm.o

kernel/irq/internals.h

@@ -12,6 +12,8 @@ extern void compat_irq_chip_set_default_handler(struct irq_desc *desc);
 
 extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
+extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
+extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
 extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);

kernel/irq/manage.c

@@ -162,6 +162,20 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *desc)
 }
 #endif
 
+void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
+{
+	if (suspend) {
+		if (!desc->action || (desc->action->flags & IRQF_TIMER))
+			return;
+		desc->status |= IRQ_SUSPENDED;
+	}
+
+	if (!desc->depth++) {
+		desc->status |= IRQ_DISABLED;
+		desc->chip->disable(irq);
+	}
+}
+
 /**
  *	disable_irq_nosync - disable an irq without waiting
  *	@irq: Interrupt to disable
@@ -182,10 +196,7 @@ void disable_irq_nosync(unsigned int irq)
 		return;
 
 	spin_lock_irqsave(&desc->lock, flags);
-	if (!desc->depth++) {
+	__disable_irq(desc, irq, false);
-		desc->status |= IRQ_DISABLED;
-		desc->chip->disable(irq);
-	}
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
@@ -215,15 +226,21 @@ void disable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(disable_irq);
 
-static void __enable_irq(struct irq_desc *desc, unsigned int irq)
+void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 {
+	if (resume)
+		desc->status &= ~IRQ_SUSPENDED;
+
 	switch (desc->depth) {
 	case 0:
+ err_out:
 		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
 		break;
 	case 1: {
 		unsigned int status = desc->status & ~IRQ_DISABLED;
 
+		if (desc->status & IRQ_SUSPENDED)
+			goto err_out;
 		/* Prevent probing on this irq: */
 		desc->status = status | IRQ_NOPROBE;
 		check_irq_resend(desc, irq);
@@ -253,7 +270,7 @@ void enable_irq(unsigned int irq)
 		return;
 
 	spin_lock_irqsave(&desc->lock, flags);
-	__enable_irq(desc, irq);
+	__enable_irq(desc, irq, false);
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
 EXPORT_SYMBOL(enable_irq);
@@ -511,7 +528,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	 */
 	if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) {
 		desc->status &= ~IRQ_SPURIOUS_DISABLED;
-		__enable_irq(desc, irq);
+		__enable_irq(desc, irq, false);
 	}
 
 	spin_unlock_irqrestore(&desc->lock, flags);

kernel/irq/pm.c

@@ -0,0 +1,79 @@
+/*
+ * linux/kernel/irq/pm.c
+ *
+ * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file contains power management functions related to interrupts.
+ */
+
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+
+#include "internals.h"
+
+/**
+ * suspend_device_irqs - disable all currently enabled interrupt lines
+ *
+ * During system-wide suspend or hibernation device interrupts need to be
+ * disabled at the chip level and this function is provided for this purpose.
+ * It disables all interrupt lines that are enabled at the moment and sets the
+ * IRQ_SUSPENDED flag for them.
+ */
+void suspend_device_irqs(void)
+{
+	struct irq_desc *desc;
+	int irq;
+
+	for_each_irq_desc(irq, desc) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&desc->lock, flags);
+		__disable_irq(desc, irq, true);
+		spin_unlock_irqrestore(&desc->lock, flags);
+	}
+
+	for_each_irq_desc(irq, desc)
+		if (desc->status & IRQ_SUSPENDED)
+			synchronize_irq(irq);
+}
+EXPORT_SYMBOL_GPL(suspend_device_irqs);
+
+/**
+ * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
+ *
+ * Enable all interrupt lines previously disabled by suspend_device_irqs() that
+ * have the IRQ_SUSPENDED flag set.
+ */
+void resume_device_irqs(void)
+{
+	struct irq_desc *desc;
+	int irq;
+
+	for_each_irq_desc(irq, desc) {
+		unsigned long flags;
+
+		if (!(desc->status & IRQ_SUSPENDED))
+			continue;
+
+		spin_lock_irqsave(&desc->lock, flags);
+		__enable_irq(desc, irq, true);
+		spin_unlock_irqrestore(&desc->lock, flags);
+	}
+}
+EXPORT_SYMBOL_GPL(resume_device_irqs);
+
+/**
+ * check_wakeup_irqs - check if any wake-up interrupts are pending
+ */
+int check_wakeup_irqs(void)
+{
+	struct irq_desc *desc;
+	int irq;
+
+	for_each_irq_desc(irq, desc)
+		if ((desc->status & IRQ_WAKEUP) && (desc->status & IRQ_PENDING))
+			return -EBUSY;
+
+	return 0;
+}

kernel/kexec.c

@@ -1450,11 +1450,7 @@ int kernel_kexec(void)
 		error = device_suspend(PMSG_FREEZE);
 		if (error)
 			goto Resume_console;
-		error = disable_nonboot_cpus();
-		if (error)
-			goto Resume_devices;
 		device_pm_lock();
-		local_irq_disable();
 		/* At this point, device_suspend() has been called,
 		 * but *not* device_power_down(). We *must*
 		 * device_power_down() now.  Otherwise, drivers for
@@ -1464,12 +1460,15 @@ int kernel_kexec(void)
 		 */
 		error = device_power_down(PMSG_FREEZE);
 		if (error)
-			goto Enable_irqs;
+			goto Resume_devices;
-
+		error = disable_nonboot_cpus();
+		if (error)
+			goto Enable_cpus;
+		local_irq_disable();
 		/* Suspend system devices */
 		error = sysdev_suspend(PMSG_FREEZE);
 		if (error)
-			goto Power_up_devices;
+			goto Enable_irqs;
 	} else
 #endif
 	{
@@ -1483,13 +1482,13 @@ int kernel_kexec(void)
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
 		sysdev_resume();
- Power_up_devices:
-		device_power_up(PMSG_RESTORE);
  Enable_irqs:
 		local_irq_enable();
-		device_pm_unlock();
+ Enable_cpus:
 		enable_nonboot_cpus();
+		device_power_up(PMSG_RESTORE);
  Resume_devices:
+		device_pm_unlock();
 		device_resume(PMSG_RESTORE);
  Resume_console:
 		resume_console();

kernel/power/disk.c

@@ -214,7 +214,7 @@ static int create_image(int platform_mode)
 		return error;
 
 	device_pm_lock();
-	local_irq_disable();
+
 	/* At this point, device_suspend() has been called, but *not*
 	 * device_power_down(). We *must* call device_power_down() now.
 	 * Otherwise, drivers for some devices (e.g. interrupt controllers)
@@ -225,13 +225,25 @@ static int create_image(int platform_mode)
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting hibernation\n");
-		goto Enable_irqs;
+		goto Unlock;
 	}
+
+	error = platform_pre_snapshot(platform_mode);
+	if (error || hibernation_test(TEST_PLATFORM))
+		goto Platform_finish;
+
+	error = disable_nonboot_cpus();
+	if (error || hibernation_test(TEST_CPUS)
+	    || hibernation_testmode(HIBERNATION_TEST))
+		goto Enable_cpus;
+
+	local_irq_disable();
+
 	sysdev_suspend(PMSG_FREEZE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting hibernation\n");
-		goto Power_up_devices;
+		goto Enable_irqs;
 	}
 
 	if (hibernation_test(TEST_CORE))
@@ -247,17 +259,28 @@ static int create_image(int platform_mode)
 	restore_processor_state();
 	if (!in_suspend)
 		platform_leave(platform_mode);
+
  Power_up:
 	sysdev_resume();
 	/* NOTE:  device_power_up() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
- Power_up_devices:
+
-	device_power_up(in_suspend ?
-		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
  Enable_irqs:
 	local_irq_enable();
+
+ Enable_cpus:
+	enable_nonboot_cpus();
+
+ Platform_finish:
+	platform_finish(platform_mode);
+
+	device_power_up(in_suspend ?
+		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+
+ Unlock:
 	device_pm_unlock();
+
 	return error;
 }
 
@@ -291,25 +314,9 @@ int hibernation_snapshot(int platform_mode)
 	if (hibernation_test(TEST_DEVICES))
 		goto Recover_platform;
 
-	error = platform_pre_snapshot(platform_mode);
+	error = create_image(platform_mode);
-	if (error || hibernation_test(TEST_PLATFORM))
+	/* Control returns here after successful restore */
-		goto Finish;
 
-	error = disable_nonboot_cpus();
-	if (!error) {
-		if (hibernation_test(TEST_CPUS))
-			goto Enable_cpus;
-
-		if (hibernation_testmode(HIBERNATION_TEST))
-			goto Enable_cpus;
-
-		error = create_image(platform_mode);
-		/* Control returns here after successful restore */
-	}
- Enable_cpus:
-	enable_nonboot_cpus();
- Finish:
-	platform_finish(platform_mode);
  Resume_devices:
 	device_resume(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
@@ -331,19 +338,33 @@ int hibernation_snapshot(int platform_mode)
  *	kernel.
  */
 
-static int resume_target_kernel(void)
+static int resume_target_kernel(bool platform_mode)
 {
 	int error;
 
 	device_pm_lock();
-	local_irq_disable();
+
 	error = device_power_down(PMSG_QUIESCE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting resume\n");
-		goto Enable_irqs;
+		goto Unlock;
 	}
-	sysdev_suspend(PMSG_QUIESCE);
+
+	error = platform_pre_restore(platform_mode);
+	if (error)
+		goto Cleanup;
+
+	error = disable_nonboot_cpus();
+	if (error)
+		goto Enable_cpus;
+
+	local_irq_disable();
+
+	error = sysdev_suspend(PMSG_QUIESCE);
+	if (error)
+		goto Enable_irqs;
+
 	/* We'll ignore saved state, but this gets preempt count (etc) right */
 	save_processor_state();
 	error = restore_highmem();
@@ -366,11 +387,23 @@ static int resume_target_kernel(void)
 	swsusp_free();
 	restore_processor_state();
 	touch_softlockup_watchdog();
+
 	sysdev_resume();
-	device_power_up(PMSG_RECOVER);
+
  Enable_irqs:
 	local_irq_enable();
+
+ Enable_cpus:
+	enable_nonboot_cpus();
+
+ Cleanup:
+	platform_restore_cleanup(platform_mode);
+
+	device_power_up(PMSG_RECOVER);
+
+ Unlock:
 	device_pm_unlock();
+
 	return error;
 }
 
@@ -390,19 +423,10 @@ int hibernation_restore(int platform_mode)
 	pm_prepare_console();
 	suspend_console();
 	error = device_suspend(PMSG_QUIESCE);
-	if (error)
-		goto Finish;
-
-	error = platform_pre_restore(platform_mode);
 	if (!error) {
-		error = disable_nonboot_cpus();
+		error = resume_target_kernel(platform_mode);
-		if (!error)
+		device_resume(PMSG_RECOVER);
-			error = resume_target_kernel();
-		enable_nonboot_cpus();
 	}
-	platform_restore_cleanup(platform_mode);
-	device_resume(PMSG_RECOVER);
- Finish:
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -438,38 +462,46 @@ int hibernation_platform_enter(void)
 		goto Resume_devices;
 	}
 
+	device_pm_lock();
+
+	error = device_power_down(PMSG_HIBERNATE);
+	if (error)
+		goto Unlock;
+
 	error = hibernation_ops->prepare();
 	if (error)
-		goto Resume_devices;
+		goto Platofrm_finish;
 
 	error = disable_nonboot_cpus();
 	if (error)
-		goto Finish;
+		goto Platofrm_finish;
 
-	device_pm_lock();
 	local_irq_disable();
-	error = device_power_down(PMSG_HIBERNATE);
+	sysdev_suspend(PMSG_HIBERNATE);
-	if (!error) {
+	hibernation_ops->enter();
-		sysdev_suspend(PMSG_HIBERNATE);
+	/* We should never get here */
-		hibernation_ops->enter();
+	while (1);
-		/* We should never get here */
-		while (1);
-	}
-	local_irq_enable();
-	device_pm_unlock();
 
 	/*
 	 * We don't need to reenable the nonboot CPUs or resume consoles, since
 	 * the system is going to be halted anyway.
 	 */
- Finish:
+ Platofrm_finish:
 	hibernation_ops->finish();
+
+	device_power_up(PMSG_RESTORE);
+
+ Unlock:
+	device_pm_unlock();
+
  Resume_devices:
 	entering_platform_hibernation = false;
 	device_resume(PMSG_RESTORE);
 	resume_console();
+
  Close:
 	hibernation_ops->end();
+
 	return error;
 }
 

kernel/power/main.c

@@ -287,17 +287,32 @@ void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
  */
 static int suspend_enter(suspend_state_t state)
 {
-	int error = 0;
+	int error;
 
 	device_pm_lock();
-	arch_suspend_disable_irqs();
-	BUG_ON(!irqs_disabled());
 
-	if ((error = device_power_down(PMSG_SUSPEND))) {
+	error = device_power_down(PMSG_SUSPEND);
+	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down\n");
 		goto Done;
 	}
 
+	if (suspend_ops->prepare) {
+		error = suspend_ops->prepare();
+		if (error)
+			goto Power_up_devices;
+	}
+
+	if (suspend_test(TEST_PLATFORM))
+		goto Platfrom_finish;
+
+	error = disable_nonboot_cpus();
+	if (error || suspend_test(TEST_CPUS))
+		goto Enable_cpus;
+
+	arch_suspend_disable_irqs();
+	BUG_ON(!irqs_disabled());
+
 	error = sysdev_suspend(PMSG_SUSPEND);
 	if (!error) {
 		if (!suspend_test(TEST_CORE))
@@ -305,11 +320,22 @@ static int suspend_enter(suspend_state_t state)
 		sysdev_resume();
 	}
 
-	device_power_up(PMSG_RESUME);
- Done:
 	arch_suspend_enable_irqs();
 	BUG_ON(irqs_disabled());
+
+ Enable_cpus:
+	enable_nonboot_cpus();
+
+ Platfrom_finish:
+	if (suspend_ops->finish)
+		suspend_ops->finish();
+
+ Power_up_devices:
+	device_power_up(PMSG_RESUME);
+
+ Done:
 	device_pm_unlock();
+
 	return error;
 }
 
@@ -341,23 +367,8 @@ int suspend_devices_and_enter(suspend_state_t state)
 	if (suspend_test(TEST_DEVICES))
 		goto Recover_platform;
 
-	if (suspend_ops->prepare) {
+	suspend_enter(state);
-		error = suspend_ops->prepare();
-		if (error)
-			goto Resume_devices;
-	}
 
-	if (suspend_test(TEST_PLATFORM))
-		goto Finish;
-
-	error = disable_nonboot_cpus();
-	if (!error && !suspend_test(TEST_CPUS))
-		suspend_enter(state);
-
-	enable_nonboot_cpus();
- Finish:
-	if (suspend_ops->finish)
-		suspend_ops->finish();
  Resume_devices:
 	suspend_test_start();
 	device_resume(PMSG_RESUME);