PM / Sleep: Add user space interface for manipulating wakeup sources, v3

Android allows user space to manipulate wakelocks using two
sysfs file located in /sys/power/, wake_lock and wake_unlock.
Writing a wakelock name and optionally a timeout to the wake_lock
file causes the wakelock whose name was written to be acquired (it
is created before is necessary), optionally with the given timeout.
Writing the name of a wakelock to wake_unlock causes that wakelock
to be released.

Implement an analogous interface for user space using wakeup sources.
Add the /sys/power/wake_lock and /sys/power/wake_unlock files
allowing user space to create, activate and deactivate wakeup
sources, such that writing a name and optionally a timeout to
wake_lock causes the wakeup source of that name to be activated,
optionally with the given timeout.  If that wakeup source doesn't
exist, it will be created and then activated.  Writing a name to
wake_unlock causes the wakeup source of that name, if there is one,
to be deactivated.  Wakeup sources created with the help of
wake_lock that haven't been used for more than 5 minutes are garbage
collected and destroyed.  Moreover, there can be only WL_NUMBER_LIMIT
wakeup sources created with the help of wake_lock present at a time.

The data type used to track wakeup sources created by user space is
called "struct wakelock" to indicate the origins of this feature.

This version of the patch includes an rbtree manipulation fix from John Stultz.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: NeilBrown <neilb@suse.de>

7 files changed, 317 insertions, 0 deletions

diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 237c735db6c9..31725ffeeb3a 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -189,3 +189,45 @@ Description:
 
 		Reading from this file causes the last string successfully
 		written to it to be returned.
+
+What:		/sys/power/wake_lock
+Date:		February 2012
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/wake_lock file allows user space to create
+		wakeup source objects and activate them on demand (if one of
+		those wakeup sources is active, reads from the
+		/sys/power/wakeup_count file block or return false).  When a
+		string without white space is written to /sys/power/wake_lock,
+		it will be assumed to represent a wakeup source name.  If there
+		is a wakeup source object with that name, it will be activated
+		(unless active already).  Otherwise, a new wakeup source object
+		will be registered, assigned the given name and activated.
+		If a string written to /sys/power/wake_lock contains white
+		space, the part of the string preceding the white space will be
+		regarded as a wakeup source name and handled as descrived above.
+		The other part of the string will be regarded as a timeout (in
+		nanoseconds) such that the wakeup source will be automatically
+		deactivated after it has expired.  The timeout, if present, is
+		set regardless of the current state of the wakeup source object
+		in question.
+
+		Reads from this file return a string consisting of the names of
+		wakeup sources created with the help of it that are active at
+		the moment, separated with spaces.
+
+
+What:		/sys/power/wake_unlock
+Date:		February 2012
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/wake_unlock file allows user space to deactivate
+		wakeup sources created with the help of /sys/power/wake_lock.
+		When a string is written to /sys/power/wake_unlock, it will be
+		assumed to represent the name of a wakeup source to deactivate.
+		If a wakeup source object of that name exists and is active at
+		the moment, it will be deactivated.
+
+		Reads from this file return a string consisting of the names of
+		wakeup sources created with the help of /sys/power/wake_lock
+		that are inactive at the moment, separated with spaces.
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 2595b8d8fe1f..cbb463b3a750 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -133,6 +133,7 @@ void wakeup_source_add(struct wakeup_source *ws)
 	spin_lock_init(&ws->lock);
 	setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws);
 	ws->active = false;
+	ws->last_time = ktime_get();
 
 	spin_lock_irq(&events_lock);
 	list_add_rcu(&ws->entry, &wakeup_sources);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 67947083f842..1d534076d33a 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -111,6 +111,14 @@ config PM_AUTOSLEEP
 	Allow the kernel to trigger a system transition into a global sleep
 	state automatically whenever there are no active wakeup sources.
 
+config PM_WAKELOCKS
+	bool "User space wakeup sources interface"
+	depends on PM_SLEEP
+	default n
+	---help---
+	Allow user space to create, activate and deactivate wakeup source
+	objects with the help of a sysfs-based interface.
+
 config PM_RUNTIME
 	bool "Run-time PM core functionality"
 	depends on !IA64_HP_SIM
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 010b2f7e148c..29472bff11ef 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -10,5 +10,6 @@ obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
 obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o \
 				   block_io.o
 obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
+obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/main.c b/kernel/power/main.c
index ba6a5645952d..54ec071de337 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -431,6 +431,43 @@ static ssize_t autosleep_store(struct kobject *kobj,
 
 power_attr(autosleep);
 #endif /* CONFIG_PM_AUTOSLEEP */
+
+#ifdef CONFIG_PM_WAKELOCKS
+static ssize_t wake_lock_show(struct kobject *kobj,
+			      struct kobj_attribute *attr,
+			      char *buf)
+{
+	return pm_show_wakelocks(buf, true);
+}
+
+static ssize_t wake_lock_store(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       const char *buf, size_t n)
+{
+	int error = pm_wake_lock(buf);
+	return error ? error : n;
+}
+
+power_attr(wake_lock);
+
+static ssize_t wake_unlock_show(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				char *buf)
+{
+	return pm_show_wakelocks(buf, false);
+}
+
+static ssize_t wake_unlock_store(struct kobject *kobj,
+				 struct kobj_attribute *attr,
+				 const char *buf, size_t n)
+{
+	int error = pm_wake_unlock(buf);
+	return error ? error : n;
+}
+
+power_attr(wake_unlock);
+
+#endif /* CONFIG_PM_WAKELOCKS */
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_TRACE
@@ -487,6 +524,10 @@ static struct attribute * g[] = {
 #ifdef CONFIG_PM_AUTOSLEEP
 	&autosleep_attr.attr,
 #endif
+#ifdef CONFIG_PM_WAKELOCKS
+	&wake_lock_attr.attr,
+	&wake_unlock_attr.attr,
+#endif
 #ifdef CONFIG_PM_DEBUG
 	&pm_test_attr.attr,
 #endif
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 4cf80fa115d9..b0bd4beaebfe 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -282,3 +282,12 @@ static inline void pm_autosleep_unlock(void) {}
 static inline suspend_state_t pm_autosleep_state(void) { return PM_SUSPEND_ON; }
 
 #endif /* !CONFIG_PM_AUTOSLEEP */
+
+#ifdef CONFIG_PM_WAKELOCKS
+
+/* kernel/power/wakelock.c */
+extern ssize_t pm_show_wakelocks(char *buf, bool show_active);
+extern int pm_wake_lock(const char *buf);
+extern int pm_wake_unlock(const char *buf);
+
+#endif /* !CONFIG_PM_WAKELOCKS */
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
new file mode 100644
index 000000000000..579700665e8c
--- /dev/null
+++ b/kernel/power/wakelock.c
@@ -0,0 +1,215 @@
+/*
+ * kernel/power/wakelock.c
+ *
+ * User space wakeup sources support.
+ *
+ * Copyright (C) 2012 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This code is based on the analogous interface allowing user space to
+ * manipulate wakelocks on Android.
+ */
+
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+
+#define WL_NUMBER_LIMIT	100
+#define WL_GC_COUNT_MAX	100
+#define WL_GC_TIME_SEC	300
+
+static DEFINE_MUTEX(wakelocks_lock);
+
+struct wakelock {
+	char			*name;
+	struct rb_node		node;
+	struct wakeup_source	ws;
+	struct list_head	lru;
+};
+
+static struct rb_root wakelocks_tree = RB_ROOT;
+static LIST_HEAD(wakelocks_lru_list);
+static unsigned int number_of_wakelocks;
+static unsigned int wakelocks_gc_count;
+
+ssize_t pm_show_wakelocks(char *buf, bool show_active)
+{
+	struct rb_node *node;
+	struct wakelock *wl;
+	char *str = buf;
+	char *end = buf + PAGE_SIZE;
+
+	mutex_lock(&wakelocks_lock);
+
+	for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) {
+		wl = rb_entry(node, struct wakelock, node);
+		if (wl->ws.active == show_active)
+			str += scnprintf(str, end - str, "%s ", wl->name);
+	}
+	if (str > buf)
+		str--;
+
+	str += scnprintf(str, end - str, "\n");
+
+	mutex_unlock(&wakelocks_lock);
+	return (str - buf);
+}
+
+static struct wakelock *wakelock_lookup_add(const char *name, size_t len,
+					    bool add_if_not_found)
+{
+	struct rb_node **node = &wakelocks_tree.rb_node;
+	struct rb_node *parent = *node;
+	struct wakelock *wl;
+
+	while (*node) {
+		int diff;
+
+		parent = *node;
+		wl = rb_entry(*node, struct wakelock, node);
+		diff = strncmp(name, wl->name, len);
+		if (diff == 0) {
+			if (wl->name[len])
+				diff = -1;
+			else
+				return wl;
+		}
+		if (diff < 0)
+			node = &(*node)->rb_left;
+		else
+			node = &(*node)->rb_right;
+	}
+	if (!add_if_not_found)
+		return ERR_PTR(-EINVAL);
+
+	if (number_of_wakelocks > WL_NUMBER_LIMIT)
+		return ERR_PTR(-ENOSPC);
+
+	/* Not found, we have to add a new one. */
+	wl = kzalloc(sizeof(*wl), GFP_KERNEL);
+	if (!wl)
+		return ERR_PTR(-ENOMEM);
+
+	wl->name = kstrndup(name, len, GFP_KERNEL);
+	if (!wl->name) {
+		kfree(wl);
+		return ERR_PTR(-ENOMEM);
+	}
+	wl->ws.name = wl->name;
+	wakeup_source_add(&wl->ws);
+	rb_link_node(&wl->node, parent, node);
+	rb_insert_color(&wl->node, &wakelocks_tree);
+	list_add(&wl->lru, &wakelocks_lru_list);
+	number_of_wakelocks++;
+	return wl;
+}
+
+int pm_wake_lock(const char *buf)
+{
+	const char *str = buf;
+	struct wakelock *wl;
+	u64 timeout_ns = 0;
+	size_t len;
+	int ret = 0;
+
+	while (*str && !isspace(*str))
+		str++;
+
+	len = str - buf;
+	if (!len)
+		return -EINVAL;
+
+	if (*str && *str != '\n') {
+		/* Find out if there's a valid timeout string appended. */
+		ret = kstrtou64(skip_spaces(str), 10, &timeout_ns);
+		if (ret)
+			return -EINVAL;
+	}
+
+	mutex_lock(&wakelocks_lock);
+
+	wl = wakelock_lookup_add(buf, len, true);
+	if (IS_ERR(wl)) {
+		ret = PTR_ERR(wl);
+		goto out;
+	}
+	if (timeout_ns) {
+		u64 timeout_ms = timeout_ns + NSEC_PER_MSEC - 1;
+
+		do_div(timeout_ms, NSEC_PER_MSEC);
+		__pm_wakeup_event(&wl->ws, timeout_ms);
+	} else {
+		__pm_stay_awake(&wl->ws);
+	}
+
+	list_move(&wl->lru, &wakelocks_lru_list);
+
+ out:
+	mutex_unlock(&wakelocks_lock);
+	return ret;
+}
+
+static void wakelocks_gc(void)
+{
+	struct wakelock *wl, *aux;
+	ktime_t now = ktime_get();
+
+	list_for_each_entry_safe_reverse(wl, aux, &wakelocks_lru_list, lru) {
+		u64 idle_time_ns;
+		bool active;
+
+		spin_lock_irq(&wl->ws.lock);
+		idle_time_ns = ktime_to_ns(ktime_sub(now, wl->ws.last_time));
+		active = wl->ws.active;
+		spin_unlock_irq(&wl->ws.lock);
+
+		if (idle_time_ns < ((u64)WL_GC_TIME_SEC * NSEC_PER_SEC))
+			break;
+
+		if (!active) {
+			wakeup_source_remove(&wl->ws);
+			rb_erase(&wl->node, &wakelocks_tree);
+			list_del(&wl->lru);
+			kfree(wl->name);
+			kfree(wl);
+			number_of_wakelocks--;
+		}
+	}
+	wakelocks_gc_count = 0;
+}
+
+int pm_wake_unlock(const char *buf)
+{
+	struct wakelock *wl;
+	size_t len;
+	int ret = 0;
+
+	len = strlen(buf);
+	if (!len)
+		return -EINVAL;
+
+	if (buf[len-1] == '\n')
+		len--;
+
+	if (!len)
+		return -EINVAL;
+
+	mutex_lock(&wakelocks_lock);
+
+	wl = wakelock_lookup_add(buf, len, false);
+	if (IS_ERR(wl)) {
+		ret = PTR_ERR(wl);
+		goto out;
+	}
+	__pm_relax(&wl->ws);
+	list_move(&wl->lru, &wakelocks_lru_list);
+	if (++wakelocks_gc_count > WL_GC_COUNT_MAX)
+		wakelocks_gc();
+
+ out:
+	mutex_unlock(&wakelocks_lock);
+	return ret;
+}