linux/kernel/power/main.c

368 lines
7.6 KiB
C
Raw Normal View History

/*
* kernel/power/main.c - PM subsystem core functionality.
*
* Copyright (c) 2003 Patrick Mochel
* Copyright (c) 2003 Open Source Development Lab
*
* This file is released under the GPLv2
*
*/
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/kobject.h>
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/pm.h>
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/resume-trace.h>
#include <linux/freezer.h>
#include <linux/vmstat.h>
#include "power.h"
/*This is just an arbitrary number */
#define FREE_PAGE_NUMBER (100)
DEFINE_MUTEX(pm_mutex);
struct pm_ops *pm_ops;
rework pm_ops pm_disk_mode, kill misuse This patch series cleans up some misconceptions about pm_ops. Some users of the pm_ops structure attempt to use it to stop the user from entering suspend to disk, this, however, is not possible since the user can always use "shutdown" in /sys/power/disk and then the pm_ops are never invoked. Also, platforms that don't support suspend to disk simply should not allow configuring SOFTWARE_SUSPEND (read the help text on it, it only selects suspend to disk and nothing else, all the other stuff depends on PM). The pm_ops structure is actually intended to provide a way to enter platform-defined sleep states (currently supported states are "standby" and "mem" (suspend to ram)) and additionally (if SOFTWARE_SUSPEND is configured) allows a platform to support a platform specific way to enter low-power mode once everything has been saved to disk. This is currently only used by ACPI (S4). This patch: The pm_ops.pm_disk_mode is used in totally bogus ways since nobody really seems to understand what it actually does. This patch clarifies the pm_disk_mode description. It also removes all the arm and sh users that think they can veto suspend to disk via pm_ops; not so since the user can always do echo shutdown > /sys/power/disk, they need to find a better way involving Kconfig or such. ACPI is the only user left with a non-zero pm_disk_mode. The patch also sets the default mode to shutdown again, but when a new pm_ops is registered its pm_disk_mode is selected as default, that way the default stays for ACPI where it is apparently required. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Cc: David Brownell <david-b@pacbell.net> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: <linux-pm@lists.linux-foundation.org> Cc: Len Brown <lenb@kernel.org> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Greg KH <greg@kroah.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-01 06:09:51 +08:00
suspend_disk_method_t pm_disk_mode = PM_DISK_SHUTDOWN;
/**
* pm_set_ops - Set the global power method table.
* @ops: Pointer to ops structure.
*/
void pm_set_ops(struct pm_ops * ops)
{
mutex_lock(&pm_mutex);
pm_ops = ops;
rework pm_ops pm_disk_mode, kill misuse This patch series cleans up some misconceptions about pm_ops. Some users of the pm_ops structure attempt to use it to stop the user from entering suspend to disk, this, however, is not possible since the user can always use "shutdown" in /sys/power/disk and then the pm_ops are never invoked. Also, platforms that don't support suspend to disk simply should not allow configuring SOFTWARE_SUSPEND (read the help text on it, it only selects suspend to disk and nothing else, all the other stuff depends on PM). The pm_ops structure is actually intended to provide a way to enter platform-defined sleep states (currently supported states are "standby" and "mem" (suspend to ram)) and additionally (if SOFTWARE_SUSPEND is configured) allows a platform to support a platform specific way to enter low-power mode once everything has been saved to disk. This is currently only used by ACPI (S4). This patch: The pm_ops.pm_disk_mode is used in totally bogus ways since nobody really seems to understand what it actually does. This patch clarifies the pm_disk_mode description. It also removes all the arm and sh users that think they can veto suspend to disk via pm_ops; not so since the user can always do echo shutdown > /sys/power/disk, they need to find a better way involving Kconfig or such. ACPI is the only user left with a non-zero pm_disk_mode. The patch also sets the default mode to shutdown again, but when a new pm_ops is registered its pm_disk_mode is selected as default, that way the default stays for ACPI where it is apparently required. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Cc: David Brownell <david-b@pacbell.net> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: <linux-pm@lists.linux-foundation.org> Cc: Len Brown <lenb@kernel.org> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Greg KH <greg@kroah.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-01 06:09:51 +08:00
if (ops && ops->pm_disk_mode != PM_DISK_INVALID) {
pm_disk_mode = ops->pm_disk_mode;
} else
pm_disk_mode = PM_DISK_SHUTDOWN;
mutex_unlock(&pm_mutex);
}
/**
* pm_valid_only_mem - generic memory-only valid callback
*
* pm_ops 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 pm_valid_only_mem(suspend_state_t state)
{
return state == PM_SUSPEND_MEM;
}
[PATCH] PM: Change code ordering in main.c As indicated in a recent thread on Linux-PM, it's necessary to call pm_ops->finish() before devce_resume(), but enable_nonboot_cpus() has to be called before pm_ops->finish() (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). For consistency, it seems reasonable to call disable_nonboot_cpus() after device_suspend(). This way the suspend code will remain symmetrical with respect to the resume code and it may allow us to speed up things in the future by suspending and resuming devices and/or saving the suspend image in many threads. The following series of patches reorders the suspend and resume code so that nonboot CPUs are disabled after devices have been suspended and enabled before the devices are resumed. It also causes pm_ops->finish() to be called after enable_nonboot_cpus() wherever necessary. This patch: Change the ordering of code in kernel/power/main.c so that device_suspend() is called before disable_nonboot_cpus() and pm_ops->finish() is called after enable_nonboot_cpus() and before device_resume(), as indicated by recent discussion on Linux-PM (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: Greg KH <greg@kroah.com> Cc: Nigel Cunningham <nigel@suspend2.net> Cc: Patrick Mochel <mochel@digitalimplant.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:43:31 +08:00
static inline void pm_finish(suspend_state_t state)
{
if (pm_ops->finish)
pm_ops->finish(state);
}
/**
* suspend_prepare - Do prep work before entering low-power state.
* @state: State we're entering.
*
* This is common code that is called for each state that we're
* entering. Allocate a console, stop all processes, then make sure
* the platform can enter the requested state.
*/
static int suspend_prepare(suspend_state_t state)
{
int error;
unsigned int free_pages;
if (!pm_ops || !pm_ops->enter)
return -EPERM;
pm_prepare_console();
if (freeze_processes()) {
error = -EAGAIN;
goto Thaw;
}
if ((free_pages = global_page_state(NR_FREE_PAGES))
< FREE_PAGE_NUMBER) {
pr_debug("PM: free some memory\n");
shrink_all_memory(FREE_PAGE_NUMBER - free_pages);
if (nr_free_pages() < FREE_PAGE_NUMBER) {
error = -ENOMEM;
printk(KERN_ERR "PM: No enough memory\n");
goto Thaw;
}
}
if (pm_ops->prepare) {
if ((error = pm_ops->prepare(state)))
goto Thaw;
}
suspend_console();
[PATCH] PM: Change code ordering in main.c As indicated in a recent thread on Linux-PM, it's necessary to call pm_ops->finish() before devce_resume(), but enable_nonboot_cpus() has to be called before pm_ops->finish() (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). For consistency, it seems reasonable to call disable_nonboot_cpus() after device_suspend(). This way the suspend code will remain symmetrical with respect to the resume code and it may allow us to speed up things in the future by suspending and resuming devices and/or saving the suspend image in many threads. The following series of patches reorders the suspend and resume code so that nonboot CPUs are disabled after devices have been suspended and enabled before the devices are resumed. It also causes pm_ops->finish() to be called after enable_nonboot_cpus() wherever necessary. This patch: Change the ordering of code in kernel/power/main.c so that device_suspend() is called before disable_nonboot_cpus() and pm_ops->finish() is called after enable_nonboot_cpus() and before device_resume(), as indicated by recent discussion on Linux-PM (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: Greg KH <greg@kroah.com> Cc: Nigel Cunningham <nigel@suspend2.net> Cc: Patrick Mochel <mochel@digitalimplant.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:43:31 +08:00
error = device_suspend(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "Some devices failed to suspend\n");
[PATCH] PM: Change code ordering in main.c As indicated in a recent thread on Linux-PM, it's necessary to call pm_ops->finish() before devce_resume(), but enable_nonboot_cpus() has to be called before pm_ops->finish() (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). For consistency, it seems reasonable to call disable_nonboot_cpus() after device_suspend(). This way the suspend code will remain symmetrical with respect to the resume code and it may allow us to speed up things in the future by suspending and resuming devices and/or saving the suspend image in many threads. The following series of patches reorders the suspend and resume code so that nonboot CPUs are disabled after devices have been suspended and enabled before the devices are resumed. It also causes pm_ops->finish() to be called after enable_nonboot_cpus() wherever necessary. This patch: Change the ordering of code in kernel/power/main.c so that device_suspend() is called before disable_nonboot_cpus() and pm_ops->finish() is called after enable_nonboot_cpus() and before device_resume(), as indicated by recent discussion on Linux-PM (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: Greg KH <greg@kroah.com> Cc: Nigel Cunningham <nigel@suspend2.net> Cc: Patrick Mochel <mochel@digitalimplant.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:43:31 +08:00
goto Resume_devices;
}
[PATCH] PM: Change code ordering in main.c As indicated in a recent thread on Linux-PM, it's necessary to call pm_ops->finish() before devce_resume(), but enable_nonboot_cpus() has to be called before pm_ops->finish() (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). For consistency, it seems reasonable to call disable_nonboot_cpus() after device_suspend(). This way the suspend code will remain symmetrical with respect to the resume code and it may allow us to speed up things in the future by suspending and resuming devices and/or saving the suspend image in many threads. The following series of patches reorders the suspend and resume code so that nonboot CPUs are disabled after devices have been suspended and enabled before the devices are resumed. It also causes pm_ops->finish() to be called after enable_nonboot_cpus() wherever necessary. This patch: Change the ordering of code in kernel/power/main.c so that device_suspend() is called before disable_nonboot_cpus() and pm_ops->finish() is called after enable_nonboot_cpus() and before device_resume(), as indicated by recent discussion on Linux-PM (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: Greg KH <greg@kroah.com> Cc: Nigel Cunningham <nigel@suspend2.net> Cc: Patrick Mochel <mochel@digitalimplant.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:43:31 +08:00
error = disable_nonboot_cpus();
if (!error)
return 0;
enable_nonboot_cpus();
Resume_devices:
pm_finish(state);
device_resume();
resume_console();
Thaw:
thaw_processes();
pm_restore_console();
return error;
}
/* default implementation */
void __attribute__ ((weak)) arch_suspend_disable_irqs(void)
{
local_irq_disable();
}
/* default implementation */
void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
{
local_irq_enable();
}
int suspend_enter(suspend_state_t state)
{
int error = 0;
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
if ((error = device_power_down(PMSG_SUSPEND))) {
printk(KERN_ERR "Some devices failed to power down\n");
goto Done;
}
error = pm_ops->enter(state);
device_power_up();
Done:
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
return error;
}
/**
* suspend_finish - Do final work before exiting suspend sequence.
* @state: State we're coming out of.
*
* Call platform code to clean up, restart processes, and free the
* console that we've allocated. This is not called for suspend-to-disk.
*/
static void suspend_finish(suspend_state_t state)
{
[PATCH] PM: Change code ordering in main.c As indicated in a recent thread on Linux-PM, it's necessary to call pm_ops->finish() before devce_resume(), but enable_nonboot_cpus() has to be called before pm_ops->finish() (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). For consistency, it seems reasonable to call disable_nonboot_cpus() after device_suspend(). This way the suspend code will remain symmetrical with respect to the resume code and it may allow us to speed up things in the future by suspending and resuming devices and/or saving the suspend image in many threads. The following series of patches reorders the suspend and resume code so that nonboot CPUs are disabled after devices have been suspended and enabled before the devices are resumed. It also causes pm_ops->finish() to be called after enable_nonboot_cpus() wherever necessary. This patch: Change the ordering of code in kernel/power/main.c so that device_suspend() is called before disable_nonboot_cpus() and pm_ops->finish() is called after enable_nonboot_cpus() and before device_resume(), as indicated by recent discussion on Linux-PM (cf. http://lists.osdl.org/pipermail/linux-pm/2006-November/004164.html). Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: Greg KH <greg@kroah.com> Cc: Nigel Cunningham <nigel@suspend2.net> Cc: Patrick Mochel <mochel@digitalimplant.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:43:31 +08:00
enable_nonboot_cpus();
pm_finish(state);
device_resume();
resume_console();
thaw_processes();
pm_restore_console();
}
static const char * const pm_states[PM_SUSPEND_MAX] = {
[PM_SUSPEND_STANDBY] = "standby",
[PM_SUSPEND_MEM] = "mem",
[PM_SUSPEND_DISK] = "disk",
};
static inline int valid_state(suspend_state_t state)
{
/* Suspend-to-disk does not really need low-level support.
* It can work with shutdown/reboot if needed. If it isn't
* configured, then it cannot be supported.
*/
if (state == PM_SUSPEND_DISK)
#ifdef CONFIG_SOFTWARE_SUSPEND
return 1;
#else
return 0;
#endif
/* all other states need lowlevel support and need to be
* valid to the lowlevel implementation, no valid callback
* implies that none are valid. */
if (!pm_ops || !pm_ops->valid || !pm_ops->valid(state))
return 0;
return 1;
}
/**
* enter_state - Do common work of entering low-power state.
* @state: pm_state structure for state we're entering.
*
* 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).
*/
static int enter_state(suspend_state_t state)
{
int error;
if (!valid_state(state))
return -ENODEV;
if (!mutex_trylock(&pm_mutex))
return -EBUSY;
if (state == PM_SUSPEND_DISK) {
error = pm_suspend_disk();
goto Unlock;
}
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
if ((error = suspend_prepare(state)))
goto Unlock;
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
error = suspend_enter(state);
pr_debug("PM: Finishing wakeup.\n");
suspend_finish(state);
Unlock:
mutex_unlock(&pm_mutex);
return error;
}
/**
* pm_suspend - Externally visible function for suspending system.
* @state: Enumarted value of state to enter.
*
* Determine whether or not value is within range, get state
* structure, and enter (above).
*/
int pm_suspend(suspend_state_t state)
{
if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
return enter_state(state);
return -EINVAL;
}
EXPORT_SYMBOL(pm_suspend);
decl_subsys(power,NULL,NULL);
/**
* state - control system power state.
*
* show() returns what states are supported, which is hard-coded to
* 'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and
* 'disk' (Suspend-to-Disk).
*
* store() accepts one of those strings, translates it into the
* proper enumerated value, and initiates a suspend transition.
*/
static ssize_t state_show(struct kset *kset, char *buf)
{
int i;
char * s = buf;
for (i = 0; i < PM_SUSPEND_MAX; i++) {
if (pm_states[i] && valid_state(i))
s += sprintf(s,"%s ", pm_states[i]);
}
s += sprintf(s,"\n");
return (s - buf);
}
static ssize_t state_store(struct kset *kset, const char *buf, size_t n)
{
suspend_state_t state = PM_SUSPEND_STANDBY;
const char * const *s;
char *p;
int error;
int len;
p = memchr(buf, '\n', n);
len = p ? p - buf : n;
for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
if (*s && !strncmp(buf, *s, len))
break;
}
if (state < PM_SUSPEND_MAX && *s)
error = enter_state(state);
else
error = -EINVAL;
return error ? error : n;
}
power_attr(state);
#ifdef CONFIG_PM_TRACE
int pm_trace_enabled;
static ssize_t pm_trace_show(struct kset *kset, char *buf)
{
return sprintf(buf, "%d\n", pm_trace_enabled);
}
static ssize_t
pm_trace_store(struct kset *kset, const char *buf, size_t n)
{
int val;
if (sscanf(buf, "%d", &val) == 1) {
pm_trace_enabled = !!val;
return n;
}
return -EINVAL;
}
power_attr(pm_trace);
static struct attribute * g[] = {
&state_attr.attr,
&pm_trace_attr.attr,
NULL,
};
#else
static struct attribute * g[] = {
&state_attr.attr,
NULL,
};
#endif /* CONFIG_PM_TRACE */
static struct attribute_group attr_group = {
.attrs = g,
};
static int __init pm_init(void)
{
int error = subsystem_register(&power_subsys);
if (!error)
error = sysfs_create_group(&power_subsys.kobj,&attr_group);
return error;
}
core_initcall(pm_init);