1 files changed, 213 insertions, 81 deletions

diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 7335952ee47..ed35a4790af 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/cpu.h>
+#include <linux/cpuidle.h>
 #include <linux/syscalls.h>
 #include <linux/gfp.h>
 #include <linux/io.h>
@@ -21,48 +22,128 @@
 #include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 #include <linux/suspend.h>
+#include <linux/syscore_ops.h>
+#include <linux/ftrace.h>
+#include <trace/events/power.h>
+#include <linux/compiler.h>
 
 #include "power.h"
 
-const char *const pm_states[PM_SUSPEND_MAX] = {
-	[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 struct platform_suspend_ops *suspend_ops;
+static const struct platform_suspend_ops *suspend_ops;
+static const struct platform_freeze_ops *freeze_ops;
 
-/**
- *	suspend_set_ops - Set the global suspend method table.
- *	@ops:	Pointer to ops structure.
- */
-void suspend_set_ops(struct platform_suspend_ops *ops)
+static bool need_suspend_ops(suspend_state_t state)
 {
-	mutex_lock(&pm_mutex);
-	suspend_ops = ops;
-	mutex_unlock(&pm_mutex);
+	return state > PM_SUSPEND_FREEZE;
+}
+
+static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head);
+static bool suspend_freeze_wake;
+
+void freeze_set_ops(const struct platform_freeze_ops *ops)
+{
+	lock_system_sleep();
+	freeze_ops = ops;
+	unlock_system_sleep();
 }
 
-bool valid_state(suspend_state_t state)
+static void freeze_begin(void)
+{
+	suspend_freeze_wake = false;
+}
+
+static void freeze_enter(void)
+{
+	cpuidle_use_deepest_state(true);
+	cpuidle_resume();
+	wait_event(suspend_freeze_wait_head, suspend_freeze_wake);
+	cpuidle_pause();
+	cpuidle_use_deepest_state(false);
+}
+
+void freeze_wake(void)
+{
+	suspend_freeze_wake = true;
+	wake_up(&suspend_freeze_wait_head);
+}
+EXPORT_SYMBOL_GPL(freeze_wake);
+
+static bool valid_state(suspend_state_t state)
 {
 	/*
-	 * All states need lowlevel support and need to be valid to the lowlevel
+	 * 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);
+
 /**
- * suspend_valid_only_mem - generic memory-only valid callback
+ * suspend_valid_only_mem - Generic memory-only valid callback.
  *
- * Platform drivers that implement mem suspend only and only need
- * to check for that in their .valid callback can use this instead
- * of rolling their own .valid callback.
+ * Platform drivers that implement mem suspend only and only need to check for
+ * that in their .valid() callback can use this instead of rolling their own
+ * .valid() callback.
  */
 int suspend_valid_only_mem(suspend_state_t state)
 {
 	return state == PM_SUSPEND_MEM;
 }
+EXPORT_SYMBOL_GPL(suspend_valid_only_mem);
 
 static int suspend_test(int level)
 {
@@ -77,16 +158,17 @@ static int suspend_test(int level)
 }
 
 /**
- *	suspend_prepare - Do prep work before entering low-power state.
+ * suspend_prepare - Prepare for entering system sleep state.
  *
- *	This is common code that is called for each state that we're entering.
- *	Run suspend notifiers, allocate a console and stop all processes.
+ * Common code run for every system sleep state that can be entered (except for
+ * hibernation).  Run suspend notifiers, allocate the "suspend" console and
+ * freeze processes.
  */
-static int suspend_prepare(void)
+static int suspend_prepare(suspend_state_t state)
 {
 	int error;
 
-	if (!suspend_ops || !suspend_ops->enter)
+	if (need_suspend_ops(state) && (!suspend_ops || !suspend_ops->enter))
 		return -EPERM;
 
 	pm_prepare_console();
@@ -95,16 +177,14 @@ static int suspend_prepare(void)
 	if (error)
 		goto Finish;
 
-	error = usermodehelper_disable();
-	if (error)
-		goto Finish;
-
+	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
+	trace_suspend_resume(TPS("freeze_processes"), 0, false);
 	if (!error)
 		return 0;
 
-	suspend_thaw_processes();
-	usermodehelper_enable();
+	suspend_stats.failed_freeze++;
+	dpm_save_failed_step(SUSPEND_FREEZE);
  Finish:
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
@@ -112,40 +192,41 @@ static int suspend_prepare(void)
 }
 
 /* default implementation */
-void __attribute__ ((weak)) arch_suspend_disable_irqs(void)
+void __weak arch_suspend_disable_irqs(void)
 {
 	local_irq_disable();
 }
 
 /* default implementation */
-void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
+void __weak arch_suspend_enable_irqs(void)
 {
 	local_irq_enable();
 }
 
 /**
- *	suspend_enter - enter the desired system sleep state.
- *	@state:		state to enter
+ * suspend_enter - Make the system enter the given sleep state.
+ * @state: System sleep state to enter.
+ * @wakeup: Returns information that the sleep state should not be re-entered.
  *
- *	This function should be called after devices have been suspended.
+ * This function should be called after devices have been suspended.
  */
-static int suspend_enter(suspend_state_t state)
+static int suspend_enter(suspend_state_t state, bool *wakeup)
 {
 	int error;
 
-	if (suspend_ops->prepare) {
+	if (need_suspend_ops(state) && suspend_ops->prepare) {
 		error = suspend_ops->prepare();
 		if (error)
 			goto Platform_finish;
 	}
 
-	error = dpm_suspend_noirq(PMSG_SUSPEND);
+	error = dpm_suspend_end(PMSG_SUSPEND);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down\n");
 		goto Platform_finish;
 	}
 
-	if (suspend_ops->prepare_late) {
+	if (need_suspend_ops(state) && suspend_ops->prepare_late) {
 		error = suspend_ops->prepare_late();
 		if (error)
 			goto Platform_wake;
@@ -154,6 +235,20 @@ static int suspend_enter(suspend_state_t state)
 	if (suspend_test(TEST_PLATFORM))
 		goto Platform_wake;
 
+	/*
+	 * PM_SUSPEND_FREEZE equals
+	 * frozen processes + suspended devices + idle processors.
+	 * Thus we should invoke freeze_enter() soon after
+	 * all the devices are suspended.
+	 */
+	if (state == PM_SUSPEND_FREEZE) {
+		trace_suspend_resume(TPS("machine_suspend"), state, true);
+		freeze_enter();
+		trace_suspend_resume(TPS("machine_suspend"), state, false);
+		goto Platform_wake;
+	}
+
+	ftrace_stop();
 	error = disable_nonboot_cpus();
 	if (error || suspend_test(TEST_CPUS))
 		goto Enable_cpus;
@@ -161,13 +256,18 @@ static int suspend_enter(suspend_state_t state)
 	arch_suspend_disable_irqs();
 	BUG_ON(!irqs_disabled());
 
-	error = sysdev_suspend(PMSG_SUSPEND);
+	error = syscore_suspend();
 	if (!error) {
-		if (!suspend_test(TEST_CORE) && pm_check_wakeup_events()) {
+		*wakeup = pm_wakeup_pending();
+		if (!(suspend_test(TEST_CORE) || *wakeup)) {
+			trace_suspend_resume(TPS("machine_suspend"),
+				state, true);
 			error = suspend_ops->enter(state);
+			trace_suspend_resume(TPS("machine_suspend"),
+				state, false);
 			events_check_enabled = false;
 		}
-		sysdev_resume();
+		syscore_resume();
 	}
 
 	arch_suspend_enable_irqs();
@@ -175,117 +275,139 @@ static int suspend_enter(suspend_state_t state)
 
  Enable_cpus:
 	enable_nonboot_cpus();
+	ftrace_start();
 
  Platform_wake:
-	if (suspend_ops->wake)
+	if (need_suspend_ops(state) && suspend_ops->wake)
 		suspend_ops->wake();
 
-	dpm_resume_noirq(PMSG_RESUME);
+	dpm_resume_start(PMSG_RESUME);
 
  Platform_finish:
-	if (suspend_ops->finish)
+	if (need_suspend_ops(state) && suspend_ops->finish)
 		suspend_ops->finish();
 
 	return error;
 }
 
 /**
- *	suspend_devices_and_enter - suspend devices and enter the desired system
- *				    sleep state.
- *	@state:		  state to enter
+ * suspend_devices_and_enter - Suspend devices and enter system sleep state.
+ * @state: System sleep state to enter.
  */
 int suspend_devices_and_enter(suspend_state_t state)
 {
 	int error;
-	gfp_t saved_mask;
+	bool wakeup = false;
 
-	if (!suspend_ops)
+	if (need_suspend_ops(state) && !suspend_ops)
 		return -ENOSYS;
 
-	if (suspend_ops->begin) {
+	if (need_suspend_ops(state) && suspend_ops->begin) {
 		error = suspend_ops->begin(state);
 		if (error)
 			goto Close;
+	} else if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin) {
+		error = freeze_ops->begin();
+		if (error)
+			goto Close;
 	}
 	suspend_console();
-	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
 	suspend_test_start();
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
-		printk(KERN_ERR "PM: Some devices failed to suspend\n");
+		pr_err("PM: Some devices failed to suspend, or early wake event detected\n");
 		goto Recover_platform;
 	}
 	suspend_test_finish("suspend devices");
 	if (suspend_test(TEST_DEVICES))
 		goto Recover_platform;
 
-	suspend_enter(state);
+	do {
+		error = suspend_enter(state, &wakeup);
+	} while (!error && !wakeup && need_suspend_ops(state)
+		&& suspend_ops->suspend_again && suspend_ops->suspend_again());
 
  Resume_devices:
 	suspend_test_start();
 	dpm_resume_end(PMSG_RESUME);
 	suspend_test_finish("resume devices");
-	set_gfp_allowed_mask(saved_mask);
 	resume_console();
  Close:
-	if (suspend_ops->end)
+	if (need_suspend_ops(state) && suspend_ops->end)
 		suspend_ops->end();
+	else if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end)
+		freeze_ops->end();
+
 	return error;
 
  Recover_platform:
-	if (suspend_ops->recover)
+	if (need_suspend_ops(state) && suspend_ops->recover)
 		suspend_ops->recover();
 	goto Resume_devices;
 }
 
 /**
- *	suspend_finish - Do final work before exiting suspend sequence.
+ * suspend_finish - Clean up before finishing the suspend sequence.
  *
- *	Call platform code to clean up, restart processes, and free the
- *	console that we've allocated. This is not called for suspend-to-disk.
+ * Call platform code to clean up, restart processes, and free the console that
+ * we've allocated. This routine is not called for hibernation.
  */
 static void suspend_finish(void)
 {
 	suspend_thaw_processes();
-	usermodehelper_enable();
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
 }
 
 /**
- *	enter_state - Do common work of entering low-power state.
- *	@state:		pm_state structure for state we're entering.
+ * enter_state - Do common work needed to enter system sleep state.
+ * @state: System sleep state to enter.
  *
- *	Make sure we're the only ones trying to enter a sleep state. Fail
- *	if someone has beat us to it, since we don't want anything weird to
- *	happen when we wake up.
- *	Then, do the setup for suspend, enter the state, and cleaup (after
- *	we've woken up).
+ * Make sure that no one else is trying to put the system into a sleep state.
+ * Fail if that's not the case.  Otherwise, prepare for system suspend, make the
+ * system enter the given sleep state and clean up after wakeup.
  */
-int enter_state(suspend_state_t state)
+static int enter_state(suspend_state_t state)
 {
 	int error;
 
-	if (!valid_state(state))
-		return -ENODEV;
-
+	trace_suspend_resume(TPS("suspend_enter"), state, true);
+	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;
 
+	if (state == PM_SUSPEND_FREEZE)
+		freeze_begin();
+
+	trace_suspend_resume(TPS("sync_filesystems"), 0, true);
 	printk(KERN_INFO "PM: Syncing filesystems ... ");
 	sys_sync();
 	printk("done.\n");
+	trace_suspend_resume(TPS("sync_filesystems"), 0, false);
 
-	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
-	error = suspend_prepare();
+	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label);
+	error = suspend_prepare(state);
 	if (error)
 		goto Unlock;
 
 	if (suspend_test(TEST_FREEZER))
 		goto Finish;
 
-	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	trace_suspend_resume(TPS("suspend_enter"), state, false);
+	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();
 
  Finish:
 	pr_debug("PM: Finishing wakeup.\n");
@@ -296,16 +418,26 @@ int enter_state(suspend_state_t state)
 }
 
 /**
- *	pm_suspend - Externally visible function for suspending system.
- *	@state:		Enumerated value of state to enter.
+ * pm_suspend - Externally visible function for suspending the system.
+ * @state: System sleep state to enter.
  *
- *	Determine whether or not value is within range, get state
- *	structure, and enter (above).
+ * Check if the value of @state represents one of the supported states,
+ * execute enter_state() and update system suspend statistics.
  */
 int pm_suspend(suspend_state_t state)
 {
-	if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
-		return enter_state(state);
-	return -EINVAL;
+	int error;
+
+	if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
+		return -EINVAL;
+
+	error = enter_state(state);
+	if (error) {
+		suspend_stats.fail++;
+		dpm_save_failed_errno(error);
+	} else {
+		suspend_stats.success++;
+	}
+	return error;
 }
 EXPORT_SYMBOL(pm_suspend);