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, 194 insertions, 117 deletions

diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index f42d3f737a33..996a4dec5f96 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -48,59 +48,49 @@
  * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
  * held, taken with _irqsave.  One lock to rule them all
  */
-struct pm_qos_request_list {
-	struct list_head list;
-	union {
-		s32 value;
-		s32 usec;
-		s32 kbps;
-	};
-	int pm_qos_class;
+enum pm_qos_type {
+	PM_QOS_MAX,		/* return the largest value */
+	PM_QOS_MIN		/* return the smallest value */
 };
 
-static s32 max_compare(s32 v1, s32 v2);
-static s32 min_compare(s32 v1, s32 v2);
-
 struct pm_qos_object {
-	struct pm_qos_request_list requests;
+	struct plist_head requests;
 	struct blocking_notifier_head *notifiers;
 	struct miscdevice pm_qos_power_miscdev;
 	char *name;
 	s32 default_value;
-	atomic_t target_value;
-	s32 (*comparitor)(s32, s32);
+	enum pm_qos_type type;
 };
 
+static DEFINE_SPINLOCK(pm_qos_lock);
+
 static struct pm_qos_object null_pm_qos;
 static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier);
 static struct pm_qos_object cpu_dma_pm_qos = {
-	.requests = {LIST_HEAD_INIT(cpu_dma_pm_qos.requests.list)},
+	.requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock),
 	.notifiers = &cpu_dma_lat_notifier,
 	.name = "cpu_dma_latency",
 	.default_value = 2000 * USEC_PER_SEC,
-	.target_value = ATOMIC_INIT(2000 * USEC_PER_SEC),
-	.comparitor = min_compare
+	.type = PM_QOS_MIN,
 };
 
 static BLOCKING_NOTIFIER_HEAD(network_lat_notifier);
 static struct pm_qos_object network_lat_pm_qos = {
-	.requests = {LIST_HEAD_INIT(network_lat_pm_qos.requests.list)},
+	.requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_lat_notifier,
 	.name = "network_latency",
 	.default_value = 2000 * USEC_PER_SEC,
-	.target_value = ATOMIC_INIT(2000 * USEC_PER_SEC),
-	.comparitor = min_compare
+	.type = PM_QOS_MIN
 };
 
 
 static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier);
 static struct pm_qos_object network_throughput_pm_qos = {
-	.requests = {LIST_HEAD_INIT(network_throughput_pm_qos.requests.list)},
+	.requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_throughput_notifier,
 	.name = "network_throughput",
 	.default_value = 0,
-	.target_value = ATOMIC_INIT(0),
-	.comparitor = max_compare
+	.type = PM_QOS_MAX,
 };
 
 
@@ -111,8 +101,6 @@ static struct pm_qos_object *pm_qos_array[] = {
 	&network_throughput_pm_qos
 };
 
-static DEFINE_SPINLOCK(pm_qos_lock);
-
 static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 		size_t count, loff_t *f_pos);
 static int pm_qos_power_open(struct inode *inode, struct file *filp);
@@ -124,46 +112,55 @@ static const struct file_operations pm_qos_power_fops = {
 	.release = pm_qos_power_release,
 };
 
-/* static helper functions */
-static s32 max_compare(s32 v1, s32 v2)
+/* unlocked internal variant */
+static inline int pm_qos_get_value(struct pm_qos_object *o)
 {
-	return max(v1, v2);
-}
+	if (plist_head_empty(&o->requests))
+		return o->default_value;
 
-static s32 min_compare(s32 v1, s32 v2)
-{
-	return min(v1, v2);
-}
+	switch (o->type) {
+	case PM_QOS_MIN:
+		return plist_last(&o->requests)->prio;
 
+	case PM_QOS_MAX:
+		return plist_first(&o->requests)->prio;
 
-static void update_target(int pm_qos_class)
+	default:
+		/* runtime check for not using enum */
+		BUG();
+	}
+}
+
+static void update_target(struct pm_qos_object *o, struct plist_node *node,
+			  int del, int value)
 {
-	s32 extreme_value;
-	struct pm_qos_request_list *node;
 	unsigned long flags;
-	int call_notifier = 0;
+	int prev_value, curr_value;
 
 	spin_lock_irqsave(&pm_qos_lock, flags);
-	extreme_value = pm_qos_array[pm_qos_class]->default_value;
-	list_for_each_entry(node,
-			&pm_qos_array[pm_qos_class]->requests.list, list) {
-		extreme_value = pm_qos_array[pm_qos_class]->comparitor(
-				extreme_value, node->value);
-	}
-	if (atomic_read(&pm_qos_array[pm_qos_class]->target_value) !=
-			extreme_value) {
-		call_notifier = 1;
-		atomic_set(&pm_qos_array[pm_qos_class]->target_value,
-				extreme_value);
-		pr_debug(KERN_ERR "new target for qos %d is %d\n", pm_qos_class,
-			atomic_read(&pm_qos_array[pm_qos_class]->target_value));
+	prev_value = pm_qos_get_value(o);
+	/* PM_QOS_DEFAULT_VALUE is a signal that the value is unchanged */
+	if (value != PM_QOS_DEFAULT_VALUE) {
+		/*
+		 * to change the list, we atomically remove, reinit
+		 * with new value and add, then see if the extremal
+		 * changed
+		 */
+		plist_del(node, &o->requests);
+		plist_node_init(node, value);
+		plist_add(node, &o->requests);
+	} else if (del) {
+		plist_del(node, &o->requests);
+	} else {
+		plist_add(node, &o->requests);
 	}
+	curr_value = pm_qos_get_value(o);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
-	if (call_notifier)
-		blocking_notifier_call_chain(
-				pm_qos_array[pm_qos_class]->notifiers,
-					(unsigned long) extreme_value, NULL);
+	if (prev_value != curr_value)
+		blocking_notifier_call_chain(o->notifiers,
+					     (unsigned long)curr_value,
+					     NULL);
 }
 
 static int register_pm_qos_misc(struct pm_qos_object *qos)
@@ -196,10 +193,23 @@ static int find_pm_qos_object_by_minor(int minor)
  */
 int pm_qos_request(int pm_qos_class)
 {
-	return atomic_read(&pm_qos_array[pm_qos_class]->target_value);
+	unsigned long flags;
+	int value;
+
+	spin_lock_irqsave(&pm_qos_lock, flags);
+	value = pm_qos_get_value(pm_qos_array[pm_qos_class]);
+	spin_unlock_irqrestore(&pm_qos_lock, flags);
+
+	return value;
 }
 EXPORT_SYMBOL_GPL(pm_qos_request);
 
+int pm_qos_request_active(struct pm_qos_request_list *req)
+{
+	return req->pm_qos_class != 0;
+}
+EXPORT_SYMBOL_GPL(pm_qos_request_active);
+
 /**
  * pm_qos_add_request - inserts new qos request into the list
  * @pm_qos_class: identifies which list of qos request to us
@@ -211,27 +221,23 @@ EXPORT_SYMBOL_GPL(pm_qos_request);
  * element as a handle for use in updating and removal.  Call needs to save
  * this handle for later use.
  */
-struct pm_qos_request_list *pm_qos_add_request(int pm_qos_class, s32 value)
+void pm_qos_add_request(struct pm_qos_request_list *dep,
+			int pm_qos_class, s32 value)
 {
-	struct pm_qos_request_list *dep;
-	unsigned long flags;
+	struct pm_qos_object *o =  pm_qos_array[pm_qos_class];
+	int new_value;
 
-	dep = kzalloc(sizeof(struct pm_qos_request_list), GFP_KERNEL);
-	if (dep) {
-		if (value == PM_QOS_DEFAULT_VALUE)
-			dep->value = pm_qos_array[pm_qos_class]->default_value;
-		else
-			dep->value = value;
-		dep->pm_qos_class = pm_qos_class;
-
-		spin_lock_irqsave(&pm_qos_lock, flags);
-		list_add(&dep->list,
-			&pm_qos_array[pm_qos_class]->requests.list);
-		spin_unlock_irqrestore(&pm_qos_lock, flags);
-		update_target(pm_qos_class);
+	if (pm_qos_request_active(dep)) {
+		WARN(1, KERN_ERR "pm_qos_add_request() called for already added request\n");
+		return;
 	}
-
-	return dep;
+	if (value == PM_QOS_DEFAULT_VALUE)
+		new_value = o->default_value;
+	else
+		new_value = value;
+	plist_node_init(&dep->list, new_value);
+	dep->pm_qos_class = pm_qos_class;
+	update_target(o, &dep->list, 0, PM_QOS_DEFAULT_VALUE);
 }
 EXPORT_SYMBOL_GPL(pm_qos_add_request);
 
@@ -246,27 +252,28 @@ EXPORT_SYMBOL_GPL(pm_qos_add_request);
  * Attempts are made to make this code callable on hot code paths.
  */
 void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req,
-		s32 new_value)
+			   s32 new_value)
 {
-	unsigned long flags;
-	int pending_update = 0;
 	s32 temp;
+	struct pm_qos_object *o;
+
+	if (!pm_qos_req) /*guard against callers passing in null */
+		return;
 
-	if (pm_qos_req) { /*guard against callers passing in null */
-		spin_lock_irqsave(&pm_qos_lock, flags);
-		if (new_value == PM_QOS_DEFAULT_VALUE)
-			temp = pm_qos_array[pm_qos_req->pm_qos_class]->default_value;
-		else
-			temp = new_value;
-
-		if (temp != pm_qos_req->value) {
-			pending_update = 1;
-			pm_qos_req->value = temp;
-		}
-		spin_unlock_irqrestore(&pm_qos_lock, flags);
-		if (pending_update)
-			update_target(pm_qos_req->pm_qos_class);
+	if (!pm_qos_request_active(pm_qos_req)) {
+		WARN(1, KERN_ERR "pm_qos_update_request() called for unknown object\n");
+		return;
 	}
+
+	o = pm_qos_array[pm_qos_req->pm_qos_class];
+
+	if (new_value == PM_QOS_DEFAULT_VALUE)
+		temp = o->default_value;
+	else
+		temp = new_value;
+
+	if (temp != pm_qos_req->list.prio)
+		update_target(o, &pm_qos_req->list, 0, temp);
 }
 EXPORT_SYMBOL_GPL(pm_qos_update_request);
 
@@ -280,19 +287,20 @@ EXPORT_SYMBOL_GPL(pm_qos_update_request);
  */
 void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req)
 {
-	unsigned long flags;
-	int qos_class;
+	struct pm_qos_object *o;
 
 	if (pm_qos_req == NULL)
 		return;
 		/* silent return to keep pcm code cleaner */
 
-	qos_class = pm_qos_req->pm_qos_class;
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	list_del(&pm_qos_req->list);
-	kfree(pm_qos_req);
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-	update_target(qos_class);
+	if (!pm_qos_request_active(pm_qos_req)) {
+		WARN(1, KERN_ERR "pm_qos_remove_request() called for unknown object\n");
+		return;
+	}
+
+	o = pm_qos_array[pm_qos_req->pm_qos_class];
+	update_target(o, &pm_qos_req->list, 1, PM_QOS_DEFAULT_VALUE);
+	memset(pm_qos_req, 0, sizeof(*pm_qos_req));
 }
 EXPORT_SYMBOL_GPL(pm_qos_remove_request);
 
@@ -340,8 +348,12 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp)
 
 	pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
 	if (pm_qos_class >= 0) {
-		filp->private_data = (void *) pm_qos_add_request(pm_qos_class,
-				PM_QOS_DEFAULT_VALUE);
+		struct pm_qos_request_list *req = kzalloc(GFP_KERNEL, sizeof(*req));
+		if (!req)
+			return -ENOMEM;
+
+		pm_qos_add_request(req, pm_qos_class, PM_QOS_DEFAULT_VALUE);
+		filp->private_data = req;
 
 		if (filp->private_data)
 			return 0;
@@ -353,8 +365,9 @@ static int pm_qos_power_release(struct inode *inode, struct file *filp)
 {
 	struct pm_qos_request_list *req;
 
-	req = (struct pm_qos_request_list *)filp->private_data;
+	req = filp->private_data;
 	pm_qos_remove_request(req);
+	kfree(req);
 
 	return 0;
 }
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index aa9e916da4d5..d26f04e92743 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -277,7 +277,7 @@ static int create_image(int platform_mode)
 		goto Enable_irqs;
 	}
 
-	if (hibernation_test(TEST_CORE))
+	if (hibernation_test(TEST_CORE) || !pm_check_wakeup_events())
 		goto Power_up;
 
 	in_suspend = 1;
@@ -288,8 +288,10 @@ static int create_image(int platform_mode)
 			error);
 	/* Restore control flow magically appears here */
 	restore_processor_state();
-	if (!in_suspend)
+	if (!in_suspend) {
+		events_check_enabled = false;
 		platform_leave(platform_mode);
+	}
 
  Power_up:
 	sysdev_resume();
@@ -328,7 +330,7 @@ int hibernation_snapshot(int platform_mode)
 
 	error = platform_begin(platform_mode);
 	if (error)
-		return error;
+		goto Close;
 
 	/* Preallocate image memory before shutting down devices. */
 	error = hibernate_preallocate_memory();
@@ -511,18 +513,24 @@ int hibernation_platform_enter(void)
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_HIBERNATE);
+	if (!pm_check_wakeup_events()) {
+		error = -EAGAIN;
+		goto Power_up;
+	}
+
 	hibernation_ops->enter();
 	/* We should never get here */
 	while (1);
 
-	/*
-	 * We don't need to reenable the nonboot CPUs or resume consoles, since
-	 * the system is going to be halted anyway.
-	 */
+ Power_up:
+	sysdev_resume();
+	local_irq_enable();
+	enable_nonboot_cpus();
+
  Platform_finish:
 	hibernation_ops->finish();
 
-	dpm_suspend_noirq(PMSG_RESTORE);
+	dpm_resume_noirq(PMSG_RESTORE);
 
  Resume_devices:
 	entering_platform_hibernation = false;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b58800b21fc0..62b0bc6e4983 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -204,6 +204,60 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
 
 power_attr(state);
 
+#ifdef CONFIG_PM_SLEEP
+/*
+ * The 'wakeup_count' attribute, along with the functions defined in
+ * drivers/base/power/wakeup.c, provides a means by which wakeup events can be
+ * handled in a non-racy way.
+ *
+ * If a wakeup event occurs when the system is in a sleep state, it simply is
+ * woken up.  In turn, if an event that would wake the system up from a sleep
+ * state occurs when it is undergoing a transition to that sleep state, the
+ * transition should be aborted.  Moreover, if such an event occurs when the
+ * system is in the working state, an attempt to start a transition to the
+ * given sleep state should fail during certain period after the detection of
+ * the event.  Using the 'state' attribute alone is not sufficient to satisfy
+ * these requirements, because a wakeup event may occur exactly when 'state'
+ * is being written to and may be delivered to user space right before it is
+ * frozen, so the event will remain only partially processed until the system is
+ * woken up by another event.  In particular, it won't cause the transition to
+ * a sleep state to be aborted.
+ *
+ * This difficulty may be overcome if user space uses 'wakeup_count' before
+ * writing to 'state'.  It first should read from 'wakeup_count' and store
+ * the read value.  Then, after carrying out its own preparations for the system
+ * transition to a sleep state, it should write the stored value to
+ * 'wakeup_count'.  If that fails, at least one wakeup event has occured since
+ * 'wakeup_count' was read and 'state' should not be written to.  Otherwise, it
+ * is allowed to write to 'state', but the transition will be aborted if there
+ * are any wakeup events detected after 'wakeup_count' was written to.
+ */
+
+static ssize_t wakeup_count_show(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				char *buf)
+{
+	unsigned long val;
+
+	return pm_get_wakeup_count(&val) ? sprintf(buf, "%lu\n", val) : -EINTR;
+}
+
+static ssize_t wakeup_count_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t n)
+{
+	unsigned long val;
+
+	if (sscanf(buf, "%lu", &val) == 1) {
+		if (pm_save_wakeup_count(val))
+			return n;
+	}
+	return -EINVAL;
+}
+
+power_attr(wakeup_count);
+#endif /* CONFIG_PM_SLEEP */
+
 #ifdef CONFIG_PM_TRACE
 int pm_trace_enabled;
 
@@ -236,6 +290,7 @@ static struct attribute * g[] = {
 #endif
 #ifdef CONFIG_PM_SLEEP
 	&pm_async_attr.attr,
+	&wakeup_count_attr.attr,
 #ifdef CONFIG_PM_DEBUG
 	&pm_test_attr.attr,
 #endif
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f37cb7dd4402..7335952ee473 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -136,19 +136,19 @@ static int suspend_enter(suspend_state_t state)
 	if (suspend_ops->prepare) {
 		error = suspend_ops->prepare();
 		if (error)
-			return error;
+			goto Platform_finish;
 	}
 
 	error = dpm_suspend_noirq(PMSG_SUSPEND);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down\n");
-		goto Platfrom_finish;
+		goto Platform_finish;
 	}
 
 	if (suspend_ops->prepare_late) {
 		error = suspend_ops->prepare_late();
 		if (error)
-			goto Power_up_devices;
+			goto Platform_wake;
 	}
 
 	if (suspend_test(TEST_PLATFORM))
@@ -163,8 +163,10 @@ static int suspend_enter(suspend_state_t state)
 
 	error = sysdev_suspend(PMSG_SUSPEND);
 	if (!error) {
-		if (!suspend_test(TEST_CORE))
+		if (!suspend_test(TEST_CORE) && pm_check_wakeup_events()) {
 			error = suspend_ops->enter(state);
+			events_check_enabled = false;
+		}
 		sysdev_resume();
 	}
 
@@ -178,10 +180,9 @@ static int suspend_enter(suspend_state_t state)
 	if (suspend_ops->wake)
 		suspend_ops->wake();
 
- Power_up_devices:
 	dpm_resume_noirq(PMSG_RESUME);
 
- Platfrom_finish:
+ Platform_finish:
 	if (suspend_ops->finish)
 		suspend_ops->finish();
 
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index b0bb21778391..7c3ae83e41d7 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -32,7 +32,7 @@
 /*
  *	The swap map is a data structure used for keeping track of each page
  *	written to a swap partition.  It consists of many swap_map_page
- *	structures that contain each an array of MAP_PAGE_SIZE swap entries.
+ *	structures that contain each an array of MAP_PAGE_ENTRIES swap entries.
  *	These structures are stored on the swap and linked together with the
  *	help of the .next_swap member.
  *
@@ -148,7 +148,7 @@ sector_t alloc_swapdev_block(int swap)
 
 /**
  *	free_all_swap_pages - free swap pages allocated for saving image data.
- *	It also frees the extents used to register which swap entres had been
+ *	It also frees the extents used to register which swap entries had been
  *	allocated.
  */