Merge branch 'acpi-pm' into pm-sleep
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 64c9276..f455181 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -7,19 +7,30 @@
 		subsystem.
 
 What:		/sys/power/state
-Date:		August 2006
+Date:		May 2014
 Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
-		The /sys/power/state file controls the system power state.
-		Reading from this file returns what states are supported,
-		which is hard-coded to 'freeze' (Low-Power Idle), 'standby'
-		(Power-On Suspend), 'mem' (Suspend-to-RAM), and 'disk'
-		(Suspend-to-Disk).
+		The /sys/power/state file controls system sleep states.
+		Reading from this file returns the available sleep state
+		labels, which may be "mem", "standby", "freeze" and "disk"
+		(hibernation).  The meanings of the first three labels depend on
+		the relative_sleep_states command line argument as follows:
+		 1) relative_sleep_states = 1
+		    "mem", "standby", "freeze" represent non-hibernation sleep
+		    states from the deepest ("mem", always present) to the
+		    shallowest ("freeze").  "standby" and "freeze" may or may
+		    not be present depending on the capabilities of the
+		    platform.  "freeze" can only be present if "standby" is
+		    present.
+		 2) relative_sleep_states = 0 (default)
+		    "mem" - "suspend-to-RAM", present if supported.
+		    "standby" - "power-on suspend", present if supported.
+		    "freeze" - "suspend-to-idle", always present.
 
 		Writing to this file one of these strings causes the system to
-		transition into that state. Please see the file
-		Documentation/power/states.txt for a description of each of
-		these states.
+		transition into the corresponding state, if available.  See
+		Documentation/power/states.txt for a description of what
+		"suspend-to-RAM", "power-on suspend" and "suspend-to-idle" mean.
 
 What:		/sys/power/disk
 Date:		September 2006
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 4384217..e19a88b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2889,6 +2889,13 @@
 			[KNL, SMP] Set scheduler's default relax_domain_level.
 			See Documentation/cgroups/cpusets.txt.
 
+	relative_sleep_states=
+			[SUSPEND] Use sleep state labeling where the deepest
+			state available other than hibernation is always "mem".
+			Format: { "0" | "1" }
+			0 -- Traditional sleep state labels.
+			1 -- Relative sleep state labels.
+
 	reserve=	[KNL,BUGS] Force the kernel to ignore some iomem area
 
 	reservetop=	[X86-32]
diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt
index 442d43d..50f3ef9 100644
--- a/Documentation/power/states.txt
+++ b/Documentation/power/states.txt
@@ -1,62 +1,87 @@
+System Power Management Sleep States
 
-System Power Management States
+(C) 2014 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
+The kernel supports up to four system sleep states generically, although three
+of them depend on the platform support code to implement the low-level details
+for each state.
 
-The kernel supports four power management states generically, though
-one is generic and the other three are dependent on platform support
-code to implement the low-level details for each state.
-This file describes each state, what they are
-commonly called, what ACPI state they map to, and what string to write
-to /sys/power/state to enter that state
+The states are represented by strings that can be read or written to the
+/sys/power/state file.  Those strings may be "mem", "standby", "freeze" and
+"disk", where the last one always represents hibernation (Suspend-To-Disk) and
+the meaning of the remaining ones depends on the relative_sleep_states command
+line argument.
 
-state:		Freeze / Low-Power Idle
+For relative_sleep_states=1, the strings "mem", "standby" and "freeze" label the
+available non-hibernation sleep states from the deepest to the shallowest,
+respectively.  In that case, "mem" is always present in /sys/power/state,
+because there is at least one non-hibernation sleep state in every system.  If
+the given system supports two non-hibernation sleep states, "standby" is present
+in /sys/power/state in addition to "mem".  If the system supports three
+non-hibernation sleep states, "freeze" will be present in /sys/power/state in
+addition to "mem" and "standby".
+
+For relative_sleep_states=0, which is the default, the following descriptions
+apply.
+
+state:		Suspend-To-Idle
 ACPI state:	S0
-String:		"freeze"
+Label:		"freeze"
 
-This state is a generic, pure software, light-weight, low-power state.
-It allows more energy to be saved relative to idle by freezing user
+This state is a generic, pure software, light-weight, system sleep state.
+It allows more energy to be saved relative to runtime idle by freezing user
 space and putting all I/O devices into low-power states (possibly
 lower-power than available at run time), such that the processors can
 spend more time in their idle states.
-This state can be used for platforms without Standby/Suspend-to-RAM
+
+This state can be used for platforms without Power-On Suspend/Suspend-to-RAM
 support, or it can be used in addition to Suspend-to-RAM (memory sleep)
-to provide reduced resume latency.
+to provide reduced resume latency.  It is always supported.
 
 
 State:		Standby / Power-On Suspend
 ACPI State:	S1
-String:		"standby"
+Label:		"standby"
 
-This state offers minimal, though real, power savings, while providing
-a very low-latency transition back to a working system. No operating
-state is lost (the CPU retains power), so the system easily starts up
+This state, if supported, offers moderate, though real, power savings, while
+providing a relatively low-latency transition back to a working system.  No
+operating state is lost (the CPU retains power), so the system easily starts up
 again where it left off. 
 
-We try to put devices in a low-power state equivalent to D1, which
-also offers low power savings, but low resume latency. Not all devices
-support D1, and those that don't are left on. 
+In addition to freezing user space and putting all I/O devices into low-power
+states, which is done for Suspend-To-Idle too, nonboot CPUs are taken offline
+and all low-level system functions are suspended during transitions into this
+state.  For this reason, it should allow more energy to be saved relative to
+Suspend-To-Idle, but the resume latency will generally be greater than for that
+state.
 
 
 State:		Suspend-to-RAM
 ACPI State:	S3
-String:		"mem"
+Label:		"mem"
 
-This state offers significant power savings as everything in the
-system is put into a low-power state, except for memory, which is
-placed in self-refresh mode to retain its contents. 
+This state, if supported, offers significant power savings as everything in the
+system is put into a low-power state, except for memory, which should be placed
+into the self-refresh mode to retain its contents.  All of the steps carried out
+when entering Power-On Suspend are also carried out during transitions to STR.
+Additional operations may take place depending on the platform capabilities.  In
+particular, on ACPI systems the kernel passes control to the BIOS (platform
+firmware) as the last step during STR transitions and that usually results in
+powering down some more low-level components that aren't directly controlled by
+the kernel.
 
-System and device state is saved and kept in memory. All devices are
-suspended and put into D3. In many cases, all peripheral buses lose
-power when entering STR, so devices must be able to handle the
-transition back to the On state. 
+System and device state is saved and kept in memory.  All devices are suspended
+and put into low-power states.  In many cases, all peripheral buses lose power
+when entering STR, so devices must be able to handle the transition back to the
+"on" state.
 
-For at least ACPI, STR requires some minimal boot-strapping code to
-resume the system from STR. This may be true on other platforms. 
+For at least ACPI, STR requires some minimal boot-strapping code to resume the
+system from it.  This may be the case on other platforms too.
 
 
 State:		Suspend-to-disk
 ACPI State:	S4
-String:		"disk"
+Label:		"disk"
 
 This state offers the greatest power savings, and can be used even in
 the absence of low-level platform support for power management. This
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 2d56f41..eb1bd2e 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -318,10 +318,16 @@
 {
 	int ret = 0;
 
+	if (!dev)
+		return -EINVAL;
+
 	if (enable) {
 		device_set_wakeup_capable(dev, true);
 		ret = device_wakeup_enable(dev);
 	} else {
+		if (dev->power.can_wakeup)
+			device_wakeup_disable(dev);
+
 		device_set_wakeup_capable(dev, false);
 	}
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 6271bc4..573410d 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -279,26 +279,26 @@
 struct kobject *power_kobj;
 
 /**
- *	state - control system power state.
+ * state - control system sleep states.
  *
- *	show() returns what states are supported, which is hard-coded to
- *	'freeze' (Low-Power Idle), 'standby' (Power-On Suspend),
- *	'mem' (Suspend-to-RAM), and 'disk' (Suspend-to-Disk).
+ * show() returns available sleep state labels, which may be "mem", "standby",
+ * "freeze" and "disk" (hibernation).  See Documentation/power/states.txt for a
+ * description of what they mean.
  *
- *	store() accepts one of those strings, translates it into the
- *	proper enumerated value, and initiates a suspend transition.
+ * store() accepts one of those strings, translates it into the proper
+ * enumerated value, and initiates a suspend transition.
  */
 static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
 			  char *buf)
 {
 	char *s = buf;
 #ifdef CONFIG_SUSPEND
-	int i;
+	suspend_state_t i;
 
-	for (i = 0; i < PM_SUSPEND_MAX; i++) {
-		if (pm_states[i] && valid_state(i))
-			s += sprintf(s,"%s ", pm_states[i]);
-	}
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (pm_states[i].state)
+			s += sprintf(s,"%s ", pm_states[i].label);
+
 #endif
 #ifdef CONFIG_HIBERNATION
 	s += sprintf(s, "%s\n", "disk");
@@ -314,7 +314,7 @@
 {
 #ifdef CONFIG_SUSPEND
 	suspend_state_t state = PM_SUSPEND_MIN;
-	const char * const *s;
+	struct pm_sleep_state *s;
 #endif
 	char *p;
 	int len;
@@ -328,8 +328,9 @@
 
 #ifdef CONFIG_SUSPEND
 	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++)
-		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
-			return state;
+		if (s->state && len == strlen(s->label)
+		    && !strncmp(buf, s->label, len))
+			return s->state;
 #endif
 
 	return PM_SUSPEND_ON;
@@ -447,8 +448,8 @@
 
 #ifdef CONFIG_SUSPEND
 	if (state < PM_SUSPEND_MAX)
-		return sprintf(buf, "%s\n", valid_state(state) ?
-						pm_states[state] : "error");
+		return sprintf(buf, "%s\n", pm_states[state].state ?
+					pm_states[state].label : "error");
 #endif
 #ifdef CONFIG_HIBERNATION
 	return sprintf(buf, "disk\n");
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 15f37ea..c60f13b 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -178,17 +178,20 @@
 				unsigned int, char *);
 
 #ifdef CONFIG_SUSPEND
-/* kernel/power/suspend.c */
-extern const char *const pm_states[];
+struct pm_sleep_state {
+	const char *label;
+	suspend_state_t state;
+};
 
-extern bool valid_state(suspend_state_t state);
+/* kernel/power/suspend.c */
+extern struct pm_sleep_state pm_states[];
+
 extern int suspend_devices_and_enter(suspend_state_t state);
 #else /* !CONFIG_SUSPEND */
 static inline int suspend_devices_and_enter(suspend_state_t state)
 {
 	return -ENOSYS;
 }
-static inline bool valid_state(suspend_state_t state) { return false; }
 #endif /* !CONFIG_SUSPEND */
 
 #ifdef CONFIG_PM_TEST_SUSPEND
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index b62bea0..963e6d0 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -31,10 +31,10 @@
 
 #include "power.h"
 
-const char *const pm_states[PM_SUSPEND_MAX] = {
-	[PM_SUSPEND_FREEZE]	= "freeze",
-	[PM_SUSPEND_STANDBY]	= "standby",
-	[PM_SUSPEND_MEM]	= "mem",
+struct pm_sleep_state pm_states[PM_SUSPEND_MAX] = {
+	[PM_SUSPEND_FREEZE] = { .label = "freeze", .state = PM_SUSPEND_FREEZE },
+	[PM_SUSPEND_STANDBY] = { .label = "standby", },
+	[PM_SUSPEND_MEM] = { .label = "mem", },
 };
 
 static const struct platform_suspend_ops *suspend_ops;
@@ -76,42 +76,62 @@
 }
 EXPORT_SYMBOL_GPL(freeze_wake);
 
+static bool valid_state(suspend_state_t state)
+{
+	/*
+	 * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level
+	 * support and need to be valid to the low level
+	 * implementation, no valid callback implies that none are valid.
+	 */
+	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
+}
+
+/*
+ * If this is set, the "mem" label always corresponds to the deepest sleep state
+ * available, the "standby" label corresponds to the second deepest sleep state
+ * available (if any), and the "freeze" label corresponds to the remaining
+ * available sleep state (if there is one).
+ */
+static bool relative_states;
+
+static int __init sleep_states_setup(char *str)
+{
+	relative_states = !strncmp(str, "1", 1);
+	if (relative_states) {
+		pm_states[PM_SUSPEND_MEM].state = PM_SUSPEND_FREEZE;
+		pm_states[PM_SUSPEND_FREEZE].state = 0;
+	}
+	return 1;
+}
+
+__setup("relative_sleep_states=", sleep_states_setup);
+
 /**
  * suspend_set_ops - Set the global suspend method table.
  * @ops: Suspend operations to use.
  */
 void suspend_set_ops(const struct platform_suspend_ops *ops)
 {
+	suspend_state_t i;
+	int j = PM_SUSPEND_MAX - 1;
+
 	lock_system_sleep();
+
 	suspend_ops = ops;
+	for (i = PM_SUSPEND_MEM; i >= PM_SUSPEND_STANDBY; i--)
+		if (valid_state(i))
+			pm_states[j--].state = i;
+		else if (!relative_states)
+			pm_states[j--].state = 0;
+
+	pm_states[j--].state = PM_SUSPEND_FREEZE;
+	while (j >= PM_SUSPEND_MIN)
+		pm_states[j--].state = 0;
+
 	unlock_system_sleep();
 }
 EXPORT_SYMBOL_GPL(suspend_set_ops);
 
-bool valid_state(suspend_state_t state)
-{
-	if (state == PM_SUSPEND_FREEZE) {
-#ifdef CONFIG_PM_DEBUG
-		if (pm_test_level != TEST_NONE &&
-		    pm_test_level != TEST_FREEZER &&
-		    pm_test_level != TEST_DEVICES &&
-		    pm_test_level != TEST_PLATFORM) {
-			printk(KERN_WARNING "Unsupported pm_test mode for "
-					"freeze state, please choose "
-					"none/freezer/devices/platform.\n");
-			return false;
-		}
-#endif
-			return true;
-	}
-	/*
-	 * PM_SUSPEND_STANDBY and PM_SUSPEND_MEMORY states need lowlevel
-	 * support and need to be valid to the lowlevel
-	 * implementation, no valid callback implies that none are valid.
-	 */
-	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
-}
-
 /**
  * suspend_valid_only_mem - Generic memory-only valid callback.
  *
@@ -345,9 +365,17 @@
 {
 	int error;
 
-	if (!valid_state(state))
-		return -ENODEV;
-
+	if (state == PM_SUSPEND_FREEZE) {
+#ifdef CONFIG_PM_DEBUG
+		if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
+			pr_warning("PM: Unsupported test mode for freeze state,"
+				   "please choose none/freezer/devices/platform.\n");
+			return -EAGAIN;
+		}
+#endif
+	} else if (!valid_state(state)) {
+		return -EINVAL;
+	}
 	if (!mutex_trylock(&pm_mutex))
 		return -EBUSY;
 
@@ -358,7 +386,7 @@
 	sys_sync();
 	printk("done.\n");
 
-	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label);
 	error = suspend_prepare(state);
 	if (error)
 		goto Unlock;
@@ -366,7 +394,7 @@
 	if (suspend_test(TEST_FREEZER))
 		goto Finish;
 
-	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	pr_debug("PM: Entering %s sleep\n", pm_states[state].label);
 	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
 	pm_restore_gfp_mask();
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 9b2a1d5..269b097 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -92,13 +92,13 @@
 	}
 
 	if (state == PM_SUSPEND_MEM) {
-		printk(info_test, pm_states[state]);
+		printk(info_test, pm_states[state].label);
 		status = pm_suspend(state);
 		if (status == -ENODEV)
 			state = PM_SUSPEND_STANDBY;
 	}
 	if (state == PM_SUSPEND_STANDBY) {
-		printk(info_test, pm_states[state]);
+		printk(info_test, pm_states[state].label);
 		status = pm_suspend(state);
 	}
 	if (status < 0)
@@ -136,18 +136,16 @@
 
 static int __init setup_test_suspend(char *value)
 {
-	unsigned i;
+	suspend_state_t i;
 
 	/* "=mem" ==> "mem" */
 	value++;
-	for (i = 0; i < PM_SUSPEND_MAX; i++) {
-		if (!pm_states[i])
-			continue;
-		if (strcmp(pm_states[i], value) != 0)
-			continue;
-		test_state = (__force suspend_state_t) i;
-		return 0;
-	}
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (!strcmp(pm_states[i].label, value)) {
+			test_state = pm_states[i].state;
+			return 0;
+		}
+
 	printk(warn_bad_state, value);
 	return 0;
 }
@@ -164,8 +162,8 @@
 	/* PM is initialized by now; is that state testable? */
 	if (test_state == PM_SUSPEND_ON)
 		goto done;
-	if (!valid_state(test_state)) {
-		printk(warn_bad_state, pm_states[test_state]);
+	if (!pm_states[test_state].state) {
+		printk(warn_bad_state, pm_states[test_state].label);
 		goto done;
 	}
 
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 8c9a481..aaa3261 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -567,7 +567,7 @@
 
 /**
  * save_image_lzo - Save the suspend image data compressed with LZO.
- * @handle: Swap mam handle to use for saving the image.
+ * @handle: Swap map handle to use for saving the image.
  * @snapshot: Image to read data from.
  * @nr_to_write: Number of pages to save.
  */