linux/kernel/power/suspend.c
Rafael J. Wysocki 3810631332 PM / sleep: Re-implement suspend-to-idle handling
In preparation for adding support for quiescing timers in the final
stage of suspend-to-idle transitions, rework the freeze_enter()
function making the system wait on a wakeup event, the freeze_wake()
function terminating the suspend-to-idle loop and the mechanism by
which deep idle states are entered during suspend-to-idle.

First of all, introduce a simple state machine for suspend-to-idle
and make the code in question use it.

Second, prevent freeze_enter() from losing wakeup events due to race
conditions and ensure that the number of online CPUs won't change
while it is being executed.  In addition to that, make it force
all of the CPUs re-enter the idle loop in case they are in idle
states already (so they can enter deeper idle states if possible).

Next, drop cpuidle_use_deepest_state() and replace use_deepest_state
checks in cpuidle_select() and cpuidle_reflect() with a single
suspend-to-idle state check in cpuidle_idle_call().

Finally, introduce cpuidle_enter_freeze() that will simply find the
deepest idle state available to the given CPU and enter it using
cpuidle_enter().

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2015-02-13 23:49:36 +01:00

528 lines
13 KiB
C

/*
* kernel/power/suspend.c - Suspend to RAM and standby functionality.
*
* Copyright (c) 2003 Patrick Mochel
* Copyright (c) 2003 Open Source Development Lab
* Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
*
* This file is released under the GPLv2.
*/
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/errno.h>
#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>
#include <linux/kernel.h>
#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 *pm_labels[] = { "mem", "standby", "freeze", NULL };
const char *pm_states[PM_SUSPEND_MAX];
static const struct platform_suspend_ops *suspend_ops;
static const struct platform_freeze_ops *freeze_ops;
static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head);
enum freeze_state __read_mostly suspend_freeze_state;
static DEFINE_SPINLOCK(suspend_freeze_lock);
void freeze_set_ops(const struct platform_freeze_ops *ops)
{
lock_system_sleep();
freeze_ops = ops;
unlock_system_sleep();
}
static void freeze_begin(void)
{
suspend_freeze_state = FREEZE_STATE_NONE;
}
static void freeze_enter(void)
{
spin_lock_irq(&suspend_freeze_lock);
if (pm_wakeup_pending())
goto out;
suspend_freeze_state = FREEZE_STATE_ENTER;
spin_unlock_irq(&suspend_freeze_lock);
get_online_cpus();
cpuidle_resume();
/* Push all the CPUs into the idle loop. */
wake_up_all_idle_cpus();
pr_debug("PM: suspend-to-idle\n");
/* Make the current CPU wait so it can enter the idle loop too. */
wait_event(suspend_freeze_wait_head,
suspend_freeze_state == FREEZE_STATE_WAKE);
pr_debug("PM: resume from suspend-to-idle\n");
cpuidle_pause();
put_online_cpus();
spin_lock_irq(&suspend_freeze_lock);
out:
suspend_freeze_state = FREEZE_STATE_NONE;
spin_unlock_irq(&suspend_freeze_lock);
}
void freeze_wake(void)
{
unsigned long flags;
spin_lock_irqsave(&suspend_freeze_lock, flags);
if (suspend_freeze_state > FREEZE_STATE_NONE) {
suspend_freeze_state = FREEZE_STATE_WAKE;
wake_up(&suspend_freeze_wait_head);
}
spin_unlock_irqrestore(&suspend_freeze_lock, flags);
}
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);
pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2];
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 = 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];
unlock_system_sleep();
}
EXPORT_SYMBOL_GPL(suspend_set_ops);
/**
* 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.
*/
int suspend_valid_only_mem(suspend_state_t state)
{
return state == PM_SUSPEND_MEM;
}
EXPORT_SYMBOL_GPL(suspend_valid_only_mem);
static bool sleep_state_supported(suspend_state_t state)
{
return state == PM_SUSPEND_FREEZE || (suspend_ops && suspend_ops->enter);
}
static int platform_suspend_prepare(suspend_state_t state)
{
return state != PM_SUSPEND_FREEZE && suspend_ops->prepare ?
suspend_ops->prepare() : 0;
}
static int platform_suspend_prepare_late(suspend_state_t state)
{
return state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->prepare ?
freeze_ops->prepare() : 0;
}
static int platform_suspend_prepare_noirq(suspend_state_t state)
{
return state != PM_SUSPEND_FREEZE && suspend_ops->prepare_late ?
suspend_ops->prepare_late() : 0;
}
static void platform_resume_noirq(suspend_state_t state)
{
if (state != PM_SUSPEND_FREEZE && suspend_ops->wake)
suspend_ops->wake();
}
static void platform_resume_early(suspend_state_t state)
{
if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->restore)
freeze_ops->restore();
}
static void platform_resume_finish(suspend_state_t state)
{
if (state != PM_SUSPEND_FREEZE && suspend_ops->finish)
suspend_ops->finish();
}
static int platform_suspend_begin(suspend_state_t state)
{
if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin)
return freeze_ops->begin();
else if (suspend_ops->begin)
return suspend_ops->begin(state);
else
return 0;
}
static void platform_resume_end(suspend_state_t state)
{
if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end)
freeze_ops->end();
else if (suspend_ops->end)
suspend_ops->end();
}
static void platform_recover(suspend_state_t state)
{
if (state != PM_SUSPEND_FREEZE && suspend_ops->recover)
suspend_ops->recover();
}
static bool platform_suspend_again(suspend_state_t state)
{
return state != PM_SUSPEND_FREEZE && suspend_ops->suspend_again ?
suspend_ops->suspend_again() : false;
}
static int suspend_test(int level)
{
#ifdef CONFIG_PM_DEBUG
if (pm_test_level == level) {
printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
mdelay(5000);
return 1;
}
#endif /* !CONFIG_PM_DEBUG */
return 0;
}
/**
* suspend_prepare - Prepare for entering system sleep state.
*
* 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(suspend_state_t state)
{
int error;
if (!sleep_state_supported(state))
return -EPERM;
pm_prepare_console();
error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
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_stats.failed_freeze++;
dpm_save_failed_step(SUSPEND_FREEZE);
Finish:
pm_notifier_call_chain(PM_POST_SUSPEND);
pm_restore_console();
return error;
}
/* default implementation */
void __weak arch_suspend_disable_irqs(void)
{
local_irq_disable();
}
/* default implementation */
void __weak arch_suspend_enable_irqs(void)
{
local_irq_enable();
}
/**
* 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.
*/
static int suspend_enter(suspend_state_t state, bool *wakeup)
{
int error;
error = platform_suspend_prepare(state);
if (error)
goto Platform_finish;
error = dpm_suspend_late(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: late suspend of devices failed\n");
goto Platform_finish;
}
error = platform_suspend_prepare_late(state);
if (error)
goto Devices_early_resume;
error = dpm_suspend_noirq(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: noirq suspend of devices failed\n");
goto Platform_early_resume;
}
error = platform_suspend_prepare_noirq(state);
if (error)
goto Platform_wake;
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;
}
error = disable_nonboot_cpus();
if (error || suspend_test(TEST_CPUS))
goto Enable_cpus;
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
error = syscore_suspend();
if (!error) {
*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;
}
syscore_resume();
}
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
Enable_cpus:
enable_nonboot_cpus();
Platform_wake:
platform_resume_noirq(state);
dpm_resume_noirq(PMSG_RESUME);
Platform_early_resume:
platform_resume_early(state);
Devices_early_resume:
dpm_resume_early(PMSG_RESUME);
Platform_finish:
platform_resume_finish(state);
return error;
}
/**
* 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;
bool wakeup = false;
if (!sleep_state_supported(state))
return -ENOSYS;
error = platform_suspend_begin(state);
if (error)
goto Close;
suspend_console();
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
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;
do {
error = suspend_enter(state, &wakeup);
} while (!error && !wakeup && platform_suspend_again(state));
Resume_devices:
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
trace_suspend_resume(TPS("resume_console"), state, true);
resume_console();
trace_suspend_resume(TPS("resume_console"), state, false);
Close:
platform_resume_end(state);
return error;
Recover_platform:
platform_recover(state);
goto Resume_devices;
}
/**
* 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 routine is not called for hibernation.
*/
static void suspend_finish(void)
{
suspend_thaw_processes();
pm_notifier_call_chain(PM_POST_SUSPEND);
pm_restore_console();
}
/**
* enter_state - Do common work needed to enter system sleep state.
* @state: System sleep state to enter.
*
* 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.
*/
static int enter_state(suspend_state_t state)
{
int error;
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(state);
if (error)
goto Unlock;
if (suspend_test(TEST_FREEZER))
goto Finish;
trace_suspend_resume(TPS("suspend_enter"), state, false);
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
pm_restrict_gfp_mask();
error = suspend_devices_and_enter(state);
pm_restore_gfp_mask();
Finish:
pr_debug("PM: Finishing wakeup.\n");
suspend_finish();
Unlock:
mutex_unlock(&pm_mutex);
return error;
}
/**
* pm_suspend - Externally visible function for suspending the system.
* @state: System sleep state to enter.
*
* 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)
{
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);