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: (34 commits)
  PM: Introduce generic prepare and complete callbacks for subsystems
  PM: Allow drivers to allocate memory from .prepare() callbacks safely
  PM: Remove CONFIG_PM_VERBOSE
  Revert "PM / Hibernate: Reduce autotuned default image size"
  PM / Hibernate: Add sysfs knob to control size of memory for drivers
  PM / Wakeup: Remove useless synchronize_rcu() call
  kmod: always provide usermodehelper_disable()
  PM / ACPI: Remove acpi_sleep=s4_nonvs
  PM / Wakeup: Fix build warning related to the "wakeup" sysfs file
  PM: Print a warning if firmware is requested when tasks are frozen
  PM / Runtime: Rework runtime PM handling during driver removal
  Freezer: Use SMP barriers
  PM / Suspend: Do not ignore error codes returned by suspend_enter()
  PM: Fix build issue in clock_ops.c for CONFIG_PM_RUNTIME unset
  PM: Revert "driver core: platform_bus: allow runtime override of dev_pm_ops"
  OMAP1 / PM: Use generic clock manipulation routines for runtime PM
  PM: Remove sysdev suspend, resume and shutdown operations
  PM / PowerPC: Use struct syscore_ops instead of sysdevs for PM
  PM / UNICORE32: Use struct syscore_ops instead of sysdevs for PM
  PM / AVR32: Use struct syscore_ops instead of sysdevs for PM
  ...

10 files changed, 85 insertions, 63 deletions

diff --git a/kernel/freezer.c b/kernel/freezer.c
index 66ecd2ead215..7b01de98bb6a 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -17,7 +17,7 @@ static inline void frozen_process(void)
 {
 	if (!unlikely(current->flags & PF_NOFREEZE)) {
 		current->flags |= PF_FROZEN;
-		wmb();
+		smp_wmb();
 	}
 	clear_freeze_flag(current);
 }
@@ -93,7 +93,7 @@ bool freeze_task(struct task_struct *p, bool sig_only)
 	 * the task as frozen and next clears its TIF_FREEZE.
 	 */
 	if (!freezing(p)) {
-		rmb();
+		smp_rmb();
 		if (frozen(p))
 			return false;
 
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 87b77de03dd3..8d814cbc8109 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1531,13 +1531,7 @@ int kernel_kexec(void)
 		if (error)
 			goto Enable_cpus;
 		local_irq_disable();
-		/* Suspend system devices */
-		error = sysdev_suspend(PMSG_FREEZE);
-		if (!error) {
-			error = syscore_suspend();
-			if (error)
-				sysdev_resume();
-		}
+		error = syscore_suspend();
 		if (error)
 			goto Enable_irqs;
 	} else
@@ -1553,7 +1547,6 @@ int kernel_kexec(void)
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
 		syscore_resume();
-		sysdev_resume();
  Enable_irqs:
 		local_irq_enable();
  Enable_cpus:
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 9cd0591c96a2..5ae0ff38425f 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -245,7 +245,6 @@ static void __call_usermodehelper(struct work_struct *work)
 	}
 }
 
-#ifdef CONFIG_PM_SLEEP
 /*
  * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
  * (used for preventing user land processes from being created after the user
@@ -301,6 +300,15 @@ void usermodehelper_enable(void)
 	usermodehelper_disabled = 0;
 }
 
+/**
+ * usermodehelper_is_disabled - check if new helpers are allowed to be started
+ */
+bool usermodehelper_is_disabled(void)
+{
+	return usermodehelper_disabled;
+}
+EXPORT_SYMBOL_GPL(usermodehelper_is_disabled);
+
 static void helper_lock(void)
 {
 	atomic_inc(&running_helpers);
@@ -312,12 +320,6 @@ static void helper_unlock(void)
 	if (atomic_dec_and_test(&running_helpers))
 		wake_up(&running_helpers_waitq);
 }
-#else /* CONFIG_PM_SLEEP */
-#define usermodehelper_disabled	0
-
-static inline void helper_lock(void) {}
-static inline void helper_unlock(void) {}
-#endif /* CONFIG_PM_SLEEP */
 
 /**
  * call_usermodehelper_setup - prepare to call a usermode helper
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 6de9a8fc3417..87f4d24b55b0 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -125,12 +125,6 @@ config PM_DEBUG
 	code. This is helpful when debugging and reporting PM bugs, like
 	suspend support.
 
-config PM_VERBOSE
-	bool "Verbose Power Management debugging"
-	depends on PM_DEBUG
-	---help---
-	This option enables verbose messages from the Power Management code.
-
 config PM_ADVANCED_DEBUG
 	bool "Extra PM attributes in sysfs for low-level debugging/testing"
 	depends on PM_DEBUG
@@ -229,3 +223,7 @@ config PM_OPP
 	  representing individual voltage domains and provides SOC
 	  implementations a ready to use framework to manage OPPs.
 	  For more information, read <file:Documentation/power/opp.txt>
+
+config PM_RUNTIME_CLK
+	def_bool y
+	depends on PM_RUNTIME && HAVE_CLK
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 50aae660174d..f9bec56d8825 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -272,12 +272,7 @@ static int create_image(int platform_mode)
 
 	local_irq_disable();
 
-	error = sysdev_suspend(PMSG_FREEZE);
-	if (!error) {
-		error = syscore_suspend();
-		if (error)
-			sysdev_resume();
-	}
+	error = syscore_suspend();
 	if (error) {
 		printk(KERN_ERR "PM: Some system devices failed to power down, "
 			"aborting hibernation\n");
@@ -302,7 +297,6 @@ static int create_image(int platform_mode)
 
  Power_up:
 	syscore_resume();
-	sysdev_resume();
 	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
@@ -333,20 +327,25 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
+	pm_message_t msg = PMSG_RECOVER;
 	int error;
 
 	error = platform_begin(platform_mode);
 	if (error)
 		goto Close;
 
+	error = dpm_prepare(PMSG_FREEZE);
+	if (error)
+		goto Complete_devices;
+
 	/* Preallocate image memory before shutting down devices. */
 	error = hibernate_preallocate_memory();
 	if (error)
-		goto Close;
+		goto Complete_devices;
 
 	suspend_console();
 	pm_restrict_gfp_mask();
-	error = dpm_suspend_start(PMSG_FREEZE);
+	error = dpm_suspend(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
 
@@ -364,13 +363,17 @@ int hibernation_snapshot(int platform_mode)
 	if (error || !in_suspend)
 		swsusp_free();
 
-	dpm_resume_end(in_suspend ?
-		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+	msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE;
+	dpm_resume(msg);
 
 	if (error || !in_suspend)
 		pm_restore_gfp_mask();
 
 	resume_console();
+
+ Complete_devices:
+	dpm_complete(msg);
+
  Close:
 	platform_end(platform_mode);
 	return error;
@@ -409,12 +412,7 @@ static int resume_target_kernel(bool platform_mode)
 
 	local_irq_disable();
 
-	error = sysdev_suspend(PMSG_QUIESCE);
-	if (!error) {
-		error = syscore_suspend();
-		if (error)
-			sysdev_resume();
-	}
+	error = syscore_suspend();
 	if (error)
 		goto Enable_irqs;
 
@@ -442,7 +440,6 @@ static int resume_target_kernel(bool platform_mode)
 	touch_softlockup_watchdog();
 
 	syscore_resume();
-	sysdev_resume();
 
  Enable_irqs:
 	local_irq_enable();
@@ -528,7 +525,6 @@ int hibernation_platform_enter(void)
 		goto Platform_finish;
 
 	local_irq_disable();
-	sysdev_suspend(PMSG_HIBERNATE);
 	syscore_suspend();
 	if (pm_wakeup_pending()) {
 		error = -EAGAIN;
@@ -541,7 +537,6 @@ int hibernation_platform_enter(void)
 
  Power_up:
 	syscore_resume();
-	sysdev_resume();
 	local_irq_enable();
 	enable_nonboot_cpus();
 
@@ -982,10 +977,33 @@ static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *att
 
 power_attr(image_size);
 
+static ssize_t reserved_size_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%lu\n", reserved_size);
+}
+
+static ssize_t reserved_size_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t n)
+{
+	unsigned long size;
+
+	if (sscanf(buf, "%lu", &size) == 1) {
+		reserved_size = size;
+		return n;
+	}
+
+	return -EINVAL;
+}
+
+power_attr(reserved_size);
+
 static struct attribute * g[] = {
 	&disk_attr.attr,
 	&resume_attr.attr,
 	&image_size_attr.attr,
+	&reserved_size_attr.attr,
 	NULL,
 };
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index de9aef8742f4..2981af4ce7cb 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -337,6 +337,7 @@ static int __init pm_init(void)
 	if (error)
 		return error;
 	hibernate_image_size_init();
+	hibernate_reserved_size_init();
 	power_kobj = kobject_create_and_add("power", NULL);
 	if (!power_kobj)
 		return -ENOMEM;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 03634be55f62..9a00a0a26280 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -15,6 +15,7 @@ struct swsusp_info {
 
 #ifdef CONFIG_HIBERNATION
 /* kernel/power/snapshot.c */
+extern void __init hibernate_reserved_size_init(void);
 extern void __init hibernate_image_size_init(void);
 
 #ifdef CONFIG_ARCH_HIBERNATION_HEADER
@@ -55,6 +56,7 @@ extern int hibernation_platform_enter(void);
 
 #else /* !CONFIG_HIBERNATION */
 
+static inline void hibernate_reserved_size_init(void) {}
 static inline void hibernate_image_size_init(void) {}
 #endif /* !CONFIG_HIBERNATION */
 
@@ -72,6 +74,8 @@ static struct kobj_attribute _name##_attr = {	\
 
 /* Preferred image size in bytes (default 500 MB) */
 extern unsigned long image_size;
+/* Size of memory reserved for drivers (default SPARE_PAGES x PAGE_SIZE) */
+extern unsigned long reserved_size;
 extern int in_suspend;
 extern dev_t swsusp_resume_device;
 extern sector_t swsusp_resume_block;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index ca0aacc24874..ace55889f702 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -41,16 +41,28 @@ static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
 
 /*
+ * Number of bytes to reserve for memory allocations made by device drivers
+ * from their ->freeze() and ->freeze_noirq() callbacks so that they don't
+ * cause image creation to fail (tunable via /sys/power/reserved_size).
+ */
+unsigned long reserved_size;
+
+void __init hibernate_reserved_size_init(void)
+{
+	reserved_size = SPARE_PAGES * PAGE_SIZE;
+}
+
+/*
  * Preferred image size in bytes (tunable via /sys/power/image_size).
- * When it is set to N, the image creating code will do its best to
- * ensure the image size will not exceed N bytes, but if that is
- * impossible, it will try to create the smallest image possible.
+ * When it is set to N, swsusp will do its best to ensure the image
+ * size will not exceed N bytes, but if that is impossible, it will
+ * try to create the smallest image possible.
  */
 unsigned long image_size;
 
 void __init hibernate_image_size_init(void)
 {
-	image_size = (totalram_pages / 3) * PAGE_SIZE;
+	image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE;
 }
 
 /* List of PBEs needed for restoring the pages that were allocated before
@@ -1263,11 +1275,13 @@ static unsigned long minimum_image_size(unsigned long saveable)
  * frame in use.  We also need a number of page frames to be free during
  * hibernation for allocations made while saving the image and for device
  * drivers, in case they need to allocate memory from their hibernation
- * callbacks (these two numbers are given by PAGES_FOR_IO and SPARE_PAGES,
- * respectively, both of which are rough estimates).  To make this happen, we
- * compute the total number of available page frames and allocate at least
+ * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough
+ * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through
+ * /sys/power/reserved_size, respectively).  To make this happen, we compute the
+ * total number of available page frames and allocate at least
  *
- * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + 2 * SPARE_PAGES
+ * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2
+ *  + 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE)
  *
  * of them, which corresponds to the maximum size of a hibernation image.
  *
@@ -1322,7 +1336,8 @@ int hibernate_preallocate_memory(void)
 	count -= totalreserve_pages;
 
 	/* Compute the maximum number of saveable pages to leave in memory. */
-	max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES;
+	max_size = (count - (size + PAGES_FOR_IO)) / 2
+			- 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE);
 	/* Compute the desired number of image pages specified by image_size. */
 	size = DIV_ROUND_UP(image_size, PAGE_SIZE);
 	if (size > max_size)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6275970b2189..1c41ba215419 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -163,19 +163,13 @@ static int suspend_enter(suspend_state_t state)
 	arch_suspend_disable_irqs();
 	BUG_ON(!irqs_disabled());
 
-	error = sysdev_suspend(PMSG_SUSPEND);
-	if (!error) {
-		error = syscore_suspend();
-		if (error)
-			sysdev_resume();
-	}
+	error = syscore_suspend();
 	if (!error) {
 		if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) {
 			error = suspend_ops->enter(state);
 			events_check_enabled = false;
 		}
 		syscore_resume();
-		sysdev_resume();
 	}
 
 	arch_suspend_enable_irqs();
@@ -226,7 +220,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	if (suspend_test(TEST_DEVICES))
 		goto Recover_platform;
 
-	suspend_enter(state);
+	error = suspend_enter(state);
 
  Resume_devices:
 	suspend_test_start();
diff --git a/kernel/sys.c b/kernel/sys.c
index af468edf096a..f0c10385f30c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -315,7 +315,6 @@ void kernel_restart_prepare(char *cmd)
 	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
 	system_state = SYSTEM_RESTART;
 	device_shutdown();
-	sysdev_shutdown();
 	syscore_shutdown();
 }
 
@@ -354,7 +353,6 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
-	sysdev_shutdown();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -374,7 +372,6 @@ void kernel_power_off(void)
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
 	disable_nonboot_cpus();
-	sysdev_shutdown();
 	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);