PM / sleep: System sleep state selection interface rework

There are systems in which the platform doesn't support any special
sleep states, so suspend-to-idle (PM_SUSPEND_FREEZE) is the only
available system sleep state.  However, some user space frameworks
only use the "mem" and (sometimes) "standby" sleep state labels, so
the users of those systems need to modify user space in order to be
able to use system suspend at all and that may be a pain in practice.

Commit 0399d4db3edf (PM / sleep: Introduce command line argument for
sleep state enumeration) attempted to address this problem by adding
a command line argument to change the meaning of the "mem" string in
/sys/power/state to make it trigger suspend-to-idle (instead of
suspend-to-RAM).

However, there also are systems in which the platform does support
special sleep states, but suspend-to-idle is the preferred one anyway
(it even may save more energy than the platform-provided sleep states
in some cases) and the above commit doesn't help in those cases.

For this reason, rework the system sleep state selection interface
again (but preserve backwards compatibiliby).  Namely, add a new
sysfs file, /sys/power/mem_sleep, that will control the system
suspend mode triggered by writing "mem" to /sys/power/state (in
analogy with what /sys/power/disk does for hibernation).  Make it
select suspend-to-RAM ("deep" sleep) by default (if supported) and
fall back to suspend-to-idle ("s2idle") otherwise and add a new
command line argument, mem_sleep_default, allowing that default to
be overridden if need be.

At the same time, drop the relative_sleep_states command line
argument that doesn't make sense any more.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Mario Limonciello <mario.limonciello@dell.com>

3 files changed, 132 insertions, 31 deletions

diff --git a/kernel/power/main.c b/kernel/power/main.c
index 281a697fd458..d401c21136d1 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -78,6 +78,78 @@ static ssize_t pm_async_store(struct kobject *kobj, struct kobj_attribute *attr,
 
 power_attr(pm_async);
 
+#ifdef CONFIG_SUSPEND
+static ssize_t mem_sleep_show(struct kobject *kobj, struct kobj_attribute *attr,
+			      char *buf)
+{
+	char *s = buf;
+	suspend_state_t i;
+
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (mem_sleep_states[i]) {
+			const char *label = mem_sleep_states[i];
+
+			if (mem_sleep_current == i)
+				s += sprintf(s, "[%s] ", label);
+			else
+				s += sprintf(s, "%s ", label);
+		}
+
+	/* Convert the last space to a newline if needed. */
+	if (s != buf)
+		*(s-1) = '\n';
+
+	return (s - buf);
+}
+
+static suspend_state_t decode_suspend_state(const char *buf, size_t n)
+{
+	suspend_state_t state;
+	char *p;
+	int len;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	for (state = PM_SUSPEND_MIN; state < PM_SUSPEND_MAX; state++) {
+		const char *label = mem_sleep_states[state];
+
+		if (label && len == strlen(label) && !strncmp(buf, label, len))
+			return state;
+	}
+
+	return PM_SUSPEND_ON;
+}
+
+static ssize_t mem_sleep_store(struct kobject *kobj, struct kobj_attribute *attr,
+			       const char *buf, size_t n)
+{
+	suspend_state_t state;
+	int error;
+
+	error = pm_autosleep_lock();
+	if (error)
+		return error;
+
+	if (pm_autosleep_state() > PM_SUSPEND_ON) {
+		error = -EBUSY;
+		goto out;
+	}
+
+	state = decode_suspend_state(buf, n);
+	if (state < PM_SUSPEND_MAX && state > PM_SUSPEND_ON)
+		mem_sleep_current = state;
+	else
+		error = -EINVAL;
+
+ out:
+	pm_autosleep_unlock();
+	return error ? error : n;
+}
+
+power_attr(mem_sleep);
+#endif /* CONFIG_SUSPEND */
+
 #ifdef CONFIG_PM_DEBUG
 int pm_test_level = TEST_NONE;
 
@@ -368,12 +440,16 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
 	}
 
 	state = decode_state(buf, n);
-	if (state < PM_SUSPEND_MAX)
+	if (state < PM_SUSPEND_MAX) {
+		if (state == PM_SUSPEND_MEM)
+			state = mem_sleep_current;
+
 		error = pm_suspend(state);
-	else if (state == PM_SUSPEND_MAX)
+	} else if (state == PM_SUSPEND_MAX) {
 		error = hibernate();
-	else
+	} else {
 		error = -EINVAL;
+	}
 
  out:
 	pm_autosleep_unlock();
@@ -485,6 +561,9 @@ static ssize_t autosleep_store(struct kobject *kobj,
 	    && strcmp(buf, "off") && strcmp(buf, "off\n"))
 		return -EINVAL;
 
+	if (state == PM_SUSPEND_MEM)
+		state = mem_sleep_current;
+
 	error = pm_autosleep_set_state(state);
 	return error ? error : n;
 }
@@ -602,6 +681,9 @@ static struct attribute * g[] = {
 #ifdef CONFIG_PM_SLEEP
 	&pm_async_attr.attr,
 	&wakeup_count_attr.attr,
+#ifdef CONFIG_SUSPEND
+	&mem_sleep_attr.attr,
+#endif
 #ifdef CONFIG_PM_AUTOSLEEP
 	&autosleep_attr.attr,
 #endif
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 56d1d0dedf76..1dfa0da827d3 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -189,11 +189,15 @@ extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *);
 
 #ifdef CONFIG_SUSPEND
 /* kernel/power/suspend.c */
-extern const char *pm_labels[];
+extern const char * const pm_labels[];
 extern const char *pm_states[];
+extern const char *mem_sleep_states[];
+extern suspend_state_t mem_sleep_current;
 
 extern int suspend_devices_and_enter(suspend_state_t state);
 #else /* !CONFIG_SUSPEND */
+#define mem_sleep_current	PM_SUSPEND_ON
+
 static inline int suspend_devices_and_enter(suspend_state_t state)
 {
 	return -ENOSYS;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6ccb08f57fcb..15e6baef5c73 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -32,8 +32,21 @@
 
 #include "power.h"
 
-const char *pm_labels[] = { "mem", "standby", "freeze", NULL };
+const char * const pm_labels[] = {
+	[PM_SUSPEND_FREEZE] = "freeze",
+	[PM_SUSPEND_STANDBY] = "standby",
+	[PM_SUSPEND_MEM] = "mem",
+};
 const char *pm_states[PM_SUSPEND_MAX];
+static const char * const mem_sleep_labels[] = {
+	[PM_SUSPEND_FREEZE] = "s2idle",
+	[PM_SUSPEND_STANDBY] = "shallow",
+	[PM_SUSPEND_MEM] = "deep",
+};
+const char *mem_sleep_states[PM_SUSPEND_MAX];
+
+suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE;
+static suspend_state_t mem_sleep_default = PM_SUSPEND_MEM;
 
 unsigned int pm_suspend_global_flags;
 EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
@@ -110,30 +123,32 @@ static bool valid_state(suspend_state_t state)
 	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;
-
 void __init pm_states_init(void)
 {
+	/* "mem" and "freeze" are always present in /sys/power/state. */
+	pm_states[PM_SUSPEND_MEM] = pm_labels[PM_SUSPEND_MEM];
+	pm_states[PM_SUSPEND_FREEZE] = pm_labels[PM_SUSPEND_FREEZE];
 	/*
-	 * freeze state should be supported even without any suspend_ops,
-	 * initialize pm_states accordingly here
+	 * Suspend-to-idle should be supported even without any suspend_ops,
+	 * initialize mem_sleep_states[] accordingly here.
 	 */
-	pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2];
+	mem_sleep_states[PM_SUSPEND_FREEZE] = mem_sleep_labels[PM_SUSPEND_FREEZE];
 }
 
-static int __init sleep_states_setup(char *str)
+static int __init mem_sleep_default_setup(char *str)
 {
-	relative_states = !strncmp(str, "1", 1);
+	suspend_state_t state;
+
+	for (state = PM_SUSPEND_FREEZE; state <= PM_SUSPEND_MEM; state++)
+		if (mem_sleep_labels[state] &&
+		    !strcmp(str, mem_sleep_labels[state])) {
+			mem_sleep_default = state;
+			break;
+		}
+
 	return 1;
 }
-
-__setup("relative_sleep_states=", sleep_states_setup);
+__setup("mem_sleep_default=", mem_sleep_default_setup);
 
 /**
  * suspend_set_ops - Set the global suspend method table.
@@ -141,21 +156,21 @@ __setup("relative_sleep_states=", sleep_states_setup);
  */
 void suspend_set_ops(const struct platform_suspend_ops *ops)
 {
-	suspend_state_t i;
-	int j = 0;
-
 	lock_system_sleep();
 
 	suspend_ops = ops;
-	for (i = PM_SUSPEND_MEM; i >= PM_SUSPEND_STANDBY; i--)
-		if (valid_state(i)) {
-			pm_states[i] = pm_labels[j++];
-		} else if (!relative_states) {
-			pm_states[i] = NULL;
-			j++;
-		}
 
-	pm_states[PM_SUSPEND_FREEZE] = pm_labels[j];
+	if (valid_state(PM_SUSPEND_STANDBY)) {
+		mem_sleep_states[PM_SUSPEND_STANDBY] = mem_sleep_labels[PM_SUSPEND_STANDBY];
+		pm_states[PM_SUSPEND_STANDBY] = pm_labels[PM_SUSPEND_STANDBY];
+		if (mem_sleep_default == PM_SUSPEND_STANDBY)
+			mem_sleep_current = PM_SUSPEND_STANDBY;
+	}
+	if (valid_state(PM_SUSPEND_MEM)) {
+		mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM];
+		if (mem_sleep_default == PM_SUSPEND_MEM)
+			mem_sleep_current = PM_SUSPEND_MEM;
+	}
 
 	unlock_system_sleep();
 }