UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6 

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6:
  PM: Add empty suspend/resume device irq functions
  PM/Hibernate: Move NVS routines into a seperate file (v2).
  PM/Hibernate: Rename disk.c to hibernate.c
  PM: Separate suspend to RAM functionality from core
  Driver Core: Rework platform suspend/resume, print warning
  PM: Remove device_type suspend()/resume()
  PM/Hibernate: Move memory shrinking to snapshot.c (rev. 2)
  PM/Suspend: Do not shrink memory before suspend
  PM: Remove bus_type suspend_late()/resume_early() V2
  PM core: rename suspend and resume functions
  PM: Rename device_power_down/up()
  PM: Remove unused asm/suspend.h
  x86: unify power/cpu_(32|64).c
  x86: unify power/cpu_(32|64) copyright notes
  x86: unify power/cpu_(32|64) regarding restoring processor state
  x86: unify power/cpu_(32|64) regarding saving processor state
  x86: unify power/cpu_(32|64) global variables
  x86: unify power/cpu_(32|64) headers
  PM: Warn if interrupts are enabled during suspend-resume of sysdevs
  PM/ACPI/x86: Fix sparse warning in arch/x86/kernel/acpi/sleep.c
This commit is contained in:
Linus Torvalds 2009-06-12 13:17:27 -07:00
parent c53567ad45 5818a6e251
commit 947ec0b0c1
33 changed files with 984 additions and 1122 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
Documentation/power/devices.txt
View File

@ -75,9 +75,6 @@ may need to apply in domain-specific ways to their devices:
struct bus_type {
...
int (*suspend)(struct device *dev, pm_message_t state);
int (*suspend_late)(struct device *dev, pm_message_t state);
int (*resume_early)(struct device *dev);
int (*resume)(struct device *dev);
};
@ -226,20 +223,7 @@ The phases are seen by driver notifications issued in this order:
This call should handle parts of device suspend logic that require
sleeping. It probably does work to quiesce the device which hasn't
been abstracted into class.suspend() or bus.suspend_late().
3 bus.suspend_late(dev, message) is called with IRQs disabled, and
with only one CPU active. Until the bus.resume_early() phase
completes (see later), IRQs are not enabled again. This method
won't be exposed by all busses; for message based busses like USB,
I2C, or SPI, device interactions normally require IRQs. This bus
call may be morphed into a driver call with bus-specific parameters.
This call might save low level hardware state that might otherwise
be lost in the upcoming low power state, and actually put the
device into a low power state ... so that in some cases the device
may stay partly usable until this late. This "late" call may also
help when coping with hardware that behaves badly.
been abstracted into class.suspend().
The pm_message_t parameter is currently used to refine those semantics
(described later).
@ -351,19 +335,11 @@ devices processing each phase's calls before the next phase begins.
The phases are seen by driver notifications issued in this order:
1 bus.resume_early(dev) is called with IRQs disabled, and with
only one CPU active. As with bus.suspend_late(), this method
won't be supported on busses that require IRQs in order to
interact with devices.
1 bus.resume(dev) reverses the effects of bus.suspend(). This may
be morphed into a device driver call with bus-specific parameters;
implementations may sleep.
This reverses the effects of bus.suspend_late().
2 bus.resume(dev) is called next. This may be morphed into a device
driver call with bus-specific parameters; implementations may sleep.
This reverses the effects of bus.suspend().
3 class.resume(dev) is called for devices associated with a class
2 class.resume(dev) is called for devices associated with a class
that has such a method. Implementations may sleep.
This reverses the effects of class.suspend(), and would usually

6
arch/alpha/include/asm/suspend.h
View File

@ -1,6 +0,0 @@
#ifndef __ALPHA_SUSPEND_H
#define __ALPHA_SUSPEND_H
/* Dummy include. */
#endif /* __ALPHA_SUSPEND_H */

4
arch/arm/include/asm/suspend.h
View File

@ -1,4 +0,0 @@
#ifndef _ASMARM_SUSPEND_H
#define _ASMARM_SUSPEND_H
#endif

1
arch/ia64/include/asm/suspend.h
View File

@ -1 +0,0 @@
/* dummy (must be non-empty to prevent prejudicial removal...) */

6
arch/m68k/include/asm/suspend.h
View File

@ -1,6 +0,0 @@
#ifndef _M68K_SUSPEND_H
#define _M68K_SUSPEND_H
/* Dummy include. */
#endif /* _M68K_SUSPEND_H */

6
arch/mips/include/asm/suspend.h
View File

@ -1,6 +0,0 @@
#ifndef __ASM_SUSPEND_H
#define __ASM_SUSPEND_H
/* Somewhen... Maybe :-) */
#endif /* __ASM_SUSPEND_H */

5
arch/s390/include/asm/suspend.h
View File

@ -1,5 +0,0 @@
#ifndef __ASM_S390_SUSPEND_H
#define __ASM_S390_SUSPEND_H
#endif

4
arch/um/include/asm/suspend.h
View File

@ -1,4 +0,0 @@
#ifndef __UM_SUSPEND_H
#define __UM_SUSPEND_H
#endif

2
arch/x86/kernel/acpi/sleep.c
View File

@ -104,7 +104,7 @@ int acpi_save_state_mem(void)
initial_gs = per_cpu_offset(smp_processor_id());
#endif
initial_code = (unsigned long)wakeup_long64;
saved_magic = 0x123456789abcdef0;
saved_magic = 0x123456789abcdef0L;
#endif /* CONFIG_64BIT */
return 0;

14
arch/x86/kernel/apm_32.c
View File

@ -1233,9 +1233,9 @@ static int suspend(int vetoable)
int err;
struct apm_user *as;
device_suspend(PMSG_SUSPEND);
dpm_suspend_start(PMSG_SUSPEND);
device_power_down(PMSG_SUSPEND);
dpm_suspend_noirq(PMSG_SUSPEND);
local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
@ -1259,9 +1259,9 @@ static int suspend(int vetoable)
sysdev_resume();
local_irq_enable();
device_power_up(PMSG_RESUME);
dpm_resume_noirq(PMSG_RESUME);
device_resume(PMSG_RESUME);
dpm_resume_end(PMSG_RESUME);
queue_event(APM_NORMAL_RESUME, NULL);
spin_lock(&user_list_lock);
for (as = user_list; as != NULL; as = as->next) {
@ -1277,7 +1277,7 @@ static void standby(void)
{
int err;
device_power_down(PMSG_SUSPEND);
dpm_suspend_noirq(PMSG_SUSPEND);
local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
@ -1291,7 +1291,7 @@ static void standby(void)
sysdev_resume();
local_irq_enable();
device_power_up(PMSG_RESUME);
dpm_resume_noirq(PMSG_RESUME);
}
static apm_event_t get_event(void)
@ -1376,7 +1376,7 @@ static void check_events(void)
ignore_bounce = 1;
if ((event != APM_NORMAL_RESUME)
|| (ignore_normal_resume == 0)) {
device_resume(PMSG_RESUME);
dpm_resume_end(PMSG_RESUME);
queue_event(event, NULL);
}
ignore_normal_resume = 0;

2
arch/x86/power/Makefile
View File

@ -3,5 +3,5 @@
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_cpu_$(BITS).o := $(nostackp)
obj-$(CONFIG_PM_SLEEP) += cpu_$(BITS).o
obj-$(CONFIG_PM_SLEEP) += cpu.o
obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o

165
arch/x86/power/cpu_64.c → arch/x86/power/cpu.c
View File

@ -1,5 +1,5 @@
/*
* Suspend and hibernation support for x86-64
* Suspend support specific for i386/x86-64.
*
* Distribute under GPLv2
*
@ -8,18 +8,28 @@
* Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
*/
#include <linux/smp.h>
#include <linux/suspend.h>
#include <asm/proto.h>
#include <asm/page.h>
#include <linux/smp.h>
#include <asm/pgtable.h>
#include <asm/proto.h>
#include <asm/mtrr.h>
#include <asm/page.h>
#include <asm/mce.h>
#include <asm/xcr.h>
#include <asm/suspend.h>
static void fix_processor_context(void);
#ifdef CONFIG_X86_32
static struct saved_context saved_context;
unsigned long saved_context_ebx;
unsigned long saved_context_esp, saved_context_ebp;
unsigned long saved_context_esi, saved_context_edi;
unsigned long saved_context_eflags;
#else
/* CONFIG_X86_64 */
struct saved_context saved_context;
#endif
/**
* __save_processor_state - save CPU registers before creating a
@ -38,19 +48,35 @@ struct saved_context saved_context;
*/
static void __save_processor_state(struct saved_context *ctxt)
{
#ifdef CONFIG_X86_32
mtrr_save_fixed_ranges(NULL);
#endif
kernel_fpu_begin();
/*
* descriptor tables
*/
#ifdef CONFIG_X86_32
store_gdt(&ctxt->gdt);
store_idt(&ctxt->idt);
#else
/* CONFIG_X86_64 */
store_gdt((struct desc_ptr *)&ctxt->gdt_limit);
store_idt((struct desc_ptr *)&ctxt->idt_limit);
#endif
store_tr(ctxt->tr);
/* XMM0..XMM15 should be handled by kernel_fpu_begin(). */
/*
* segment registers
*/
#ifdef CONFIG_X86_32
savesegment(es, ctxt->es);
savesegment(fs, ctxt->fs);
savesegment(gs, ctxt->gs);
savesegment(ss, ctxt->ss);
#else
/* CONFIG_X86_64 */
asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
@ -62,30 +88,87 @@ static void __save_processor_state(struct saved_context *ctxt)
rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
mtrr_save_fixed_ranges(NULL);
rdmsrl(MSR_EFER, ctxt->efer);
#endif
/*
* control registers
*/
rdmsrl(MSR_EFER, ctxt->efer);
ctxt->cr0 = read_cr0();
ctxt->cr2 = read_cr2();
ctxt->cr3 = read_cr3();
#ifdef CONFIG_X86_32
ctxt->cr4 = read_cr4_safe();
#else
/* CONFIG_X86_64 */
ctxt->cr4 = read_cr4();
ctxt->cr8 = read_cr8();
#endif
}
/* Needed by apm.c */
void save_processor_state(void)
{
__save_processor_state(&saved_context);
}
#ifdef CONFIG_X86_32
EXPORT_SYMBOL(save_processor_state);
#endif
static void do_fpu_end(void)
{
/*
* Restore FPU regs if necessary
* Restore FPU regs if necessary.
*/
kernel_fpu_end();
}
static void fix_processor_context(void)
{
int cpu = smp_processor_id();
struct tss_struct *t = &per_cpu(init_tss, cpu);
set_tss_desc(cpu, t); /*
* This just modifies memory; should not be
* necessary. But... This is necessary, because
* 386 hardware has concept of busy TSS or some
* similar stupidity.
*/
#ifdef CONFIG_X86_64
get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9;
syscall_init(); /* This sets MSR_*STAR and related */
#endif
load_TR_desc(); /* This does ltr */
load_LDT(&current->active_mm->context); /* This does lldt */
/*
* Now maybe reload the debug registers
*/
if (current->thread.debugreg7) {
#ifdef CONFIG_X86_32
set_debugreg(current->thread.debugreg0, 0);
set_debugreg(current->thread.debugreg1, 1);
set_debugreg(current->thread.debugreg2, 2);
set_debugreg(current->thread.debugreg3, 3);
/* no 4 and 5 */
set_debugreg(current->thread.debugreg6, 6);
set_debugreg(current->thread.debugreg7, 7);
#else
/* CONFIG_X86_64 */
loaddebug(&current->thread, 0);
loaddebug(&current->thread, 1);
loaddebug(&current->thread, 2);
loaddebug(&current->thread, 3);
/* no 4 and 5 */
loaddebug(&current->thread, 6);
loaddebug(&current->thread, 7);
#endif
}
}
/**
* __restore_processor_state - restore the contents of CPU registers saved
* by __save_processor_state()
@ -96,9 +179,16 @@ static void __restore_processor_state(struct saved_context *ctxt)
/*
* control registers
*/
/* cr4 was introduced in the Pentium CPU */
#ifdef CONFIG_X86_32
if (ctxt->cr4)
write_cr4(ctxt->cr4);
#else
/* CONFIG X86_64 */
wrmsrl(MSR_EFER, ctxt->efer);
write_cr8(ctxt->cr8);
write_cr4(ctxt->cr4);
#endif
write_cr3(ctxt->cr3);
write_cr2(ctxt->cr2);
write_cr0(ctxt->cr0);
@ -107,13 +197,31 @@ static void __restore_processor_state(struct saved_context *ctxt)
* now restore the descriptor tables to their proper values
* ltr is done i fix_processor_context().
*/
#ifdef CONFIG_X86_32
load_gdt(&ctxt->gdt);
load_idt(&ctxt->idt);
#else
/* CONFIG_X86_64 */
load_gdt((const struct desc_ptr *)&ctxt->gdt_limit);
load_idt((const struct desc_ptr *)&ctxt->idt_limit);
#endif
/*
* segment registers
*/
#ifdef CONFIG_X86_32
loadsegment(es, ctxt->es);
loadsegment(fs, ctxt->fs);
loadsegment(gs, ctxt->gs);
loadsegment(ss, ctxt->ss);
/*
* sysenter MSRs
*/
if (boot_cpu_has(X86_FEATURE_SEP))
enable_sep_cpu();
#else
/* CONFIG_X86_64 */
asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
@ -123,6 +231,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
wrmsrl(MSR_FS_BASE, ctxt->fs_base);
wrmsrl(MSR_GS_BASE, ctxt->gs_base);
wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
#endif
/*
* restore XCR0 for xsave capable cpu's.
@ -134,41 +243,17 @@ static void __restore_processor_state(struct saved_context *ctxt)
do_fpu_end();
mtrr_ap_init();
#ifdef CONFIG_X86_32
mcheck_init(&boot_cpu_data);
#endif
}
/* Needed by apm.c */
void restore_processor_state(void)
{
__restore_processor_state(&saved_context);
}
static void fix_processor_context(void)
{
int cpu = smp_processor_id();
struct tss_struct *t = &per_cpu(init_tss, cpu);
/*
* This just modifies memory; should not be necessary. But... This
* is necessary, because 386 hardware has concept of busy TSS or some
* similar stupidity.
*/
set_tss_desc(cpu, t);
get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9;
syscall_init(); /* This sets MSR_*STAR and related */
load_TR_desc(); /* This does ltr */
load_LDT(&current->active_mm->context); /* This does lldt */
/*
* Now maybe reload the debug registers
*/
if (current->thread.debugreg7){
loaddebug(&current->thread, 0);
loaddebug(&current->thread, 1);
loaddebug(&current->thread, 2);
loaddebug(&current->thread, 3);
/* no 4 and 5 */
loaddebug(&current->thread, 6);
loaddebug(&current->thread, 7);
}
}
#ifdef CONFIG_X86_32
EXPORT_SYMBOL(restore_processor_state);
#endif

148
arch/x86/power/cpu_32.c
View File

@ -1,148 +0,0 @@
/*
* Suspend support specific for i386.
*
* Distribute under GPLv2
*
* Copyright (c) 2002 Pavel Machek <pavel@suse.cz>
* Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
*/
#include <linux/module.h>
#include <linux/suspend.h>
#include <asm/mtrr.h>
#include <asm/mce.h>
#include <asm/xcr.h>
#include <asm/suspend.h>
static struct saved_context saved_context;
unsigned long saved_context_ebx;
unsigned long saved_context_esp, saved_context_ebp;
unsigned long saved_context_esi, saved_context_edi;
unsigned long saved_context_eflags;
static void __save_processor_state(struct saved_context *ctxt)
{
mtrr_save_fixed_ranges(NULL);
kernel_fpu_begin();
/*
* descriptor tables
*/
store_gdt(&ctxt->gdt);
store_idt(&ctxt->idt);
store_tr(ctxt->tr);
/*
* segment registers
*/
savesegment(es, ctxt->es);
savesegment(fs, ctxt->fs);
savesegment(gs, ctxt->gs);
savesegment(ss, ctxt->ss);
/*
* control registers
*/
ctxt->cr0 = read_cr0();
ctxt->cr2 = read_cr2();
ctxt->cr3 = read_cr3();
ctxt->cr4 = read_cr4_safe();
}
/* Needed by apm.c */
void save_processor_state(void)
{
__save_processor_state(&saved_context);
}
EXPORT_SYMBOL(save_processor_state);
static void do_fpu_end(void)
{
/*
* Restore FPU regs if necessary.
*/
kernel_fpu_end();
}
static void fix_processor_context(void)
{
int cpu = smp_processor_id();
struct tss_struct *t = &per_cpu(init_tss, cpu);
set_tss_desc(cpu, t); /*
* This just modifies memory; should not be
* necessary. But... This is necessary, because
* 386 hardware has concept of busy TSS or some
* similar stupidity.
*/
load_TR_desc(); /* This does ltr */
load_LDT(&current->active_mm->context); /* This does lldt */
/*
* Now maybe reload the debug registers
*/
if (current->thread.debugreg7) {
set_debugreg(current->thread.debugreg0, 0);
set_debugreg(current->thread.debugreg1, 1);
set_debugreg(current->thread.debugreg2, 2);
set_debugreg(current->thread.debugreg3, 3);
/* no 4 and 5 */
set_debugreg(current->thread.debugreg6, 6);
set_debugreg(current->thread.debugreg7, 7);
}
}
static void __restore_processor_state(struct saved_context *ctxt)
{
/*
* control registers
*/
/* cr4 was introduced in the Pentium CPU */
if (ctxt->cr4)
write_cr4(ctxt->cr4);
write_cr3(ctxt->cr3);
write_cr2(ctxt->cr2);
write_cr0(ctxt->cr0);
/*
* now restore the descriptor tables to their proper values
* ltr is done i fix_processor_context().
*/
load_gdt(&ctxt->gdt);
load_idt(&ctxt->idt);
/*
* segment registers
*/
loadsegment(es, ctxt->es);
loadsegment(fs, ctxt->fs);
loadsegment(gs, ctxt->gs);
loadsegment(ss, ctxt->ss);
/*
* sysenter MSRs
*/
if (boot_cpu_has(X86_FEATURE_SEP))
enable_sep_cpu();
/*
* restore XCR0 for xsave capable cpu's.
*/
if (cpu_has_xsave)
xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
fix_processor_context();
do_fpu_end();
mtrr_ap_init();
mcheck_init(&boot_cpu_data);
}
/* Needed by apm.c */
void restore_processor_state(void)
{
__restore_processor_state(&saved_context);
}
EXPORT_SYMBOL(restore_processor_state);

36
drivers/base/platform.c
View File

@ -469,22 +469,6 @@ static void platform_drv_shutdown(struct device *_dev)
drv->shutdown(dev);
}
static int platform_drv_suspend(struct device *_dev, pm_message_t state)
{
struct platform_driver *drv = to_platform_driver(_dev->driver);
struct platform_device *dev = to_platform_device(_dev);
return drv->suspend(dev, state);
}
static int platform_drv_resume(struct device *_dev)
{
struct platform_driver *drv = to_platform_driver(_dev->driver);
struct platform_device *dev = to_platform_device(_dev);
return drv->resume(dev);
}
/**
* platform_driver_register
* @drv: platform driver structure
@ -498,10 +482,10 @@ int platform_driver_register(struct platform_driver *drv)
drv->driver.remove = platform_drv_remove;
if (drv->shutdown)
drv->driver.shutdown = platform_drv_shutdown;
if (drv->suspend)
drv->driver.suspend = platform_drv_suspend;
if (drv->resume)
drv->driver.resume = platform_drv_resume;
if (drv->suspend || drv->resume)
pr_warning("Platform driver '%s' needs updating - please use "
"dev_pm_ops\n", drv->driver.name);
return driver_register(&drv->driver);
}
EXPORT_SYMBOL_GPL(platform_driver_register);
@ -633,10 +617,12 @@ static int platform_match(struct device *dev, struct device_driver *drv)
static int platform_legacy_suspend(struct device *dev, pm_message_t mesg)
{
struct platform_driver *pdrv = to_platform_driver(dev->driver);
struct platform_device *pdev = to_platform_device(dev);
int ret = 0;
if (dev->driver && dev->driver->suspend)
ret = dev->driver->suspend(dev, mesg);
if (dev->driver && pdrv->suspend)
ret = pdrv->suspend(pdev, mesg);
return ret;
}
@ -667,10 +653,12 @@ static int platform_legacy_resume_early(struct device *dev)
static int platform_legacy_resume(struct device *dev)
{
struct platform_driver *pdrv = to_platform_driver(dev->driver);
struct platform_device *pdev = to_platform_device(dev);
int ret = 0;
if (dev->driver && dev->driver->resume)
ret = dev->driver->resume(dev);
if (dev->driver && pdrv->resume)
ret = pdrv->resume(pdev);
return ret;
}

94
drivers/base/power/main.c
View File

@ -315,13 +315,13 @@ static void pm_dev_err(struct device *dev, pm_message_t state, char *info,
/*------------------------- Resume routines -------------------------*/
/**
* resume_device_noirq - Power on one device (early resume).
* device_resume_noirq - Power on one device (early resume).
* @dev: Device.
* @state: PM transition of the system being carried out.
*
* Must be called with interrupts disabled.
*/
static int resume_device_noirq(struct device *dev, pm_message_t state)
static int device_resume_noirq(struct device *dev, pm_message_t state)
{
int error = 0;
@ -334,9 +334,6 @@ static int resume_device_noirq(struct device *dev, pm_message_t state)
if (dev->bus->pm) {
pm_dev_dbg(dev, state, "EARLY ");
error = pm_noirq_op(dev, dev->bus->pm, state);
} else if (dev->bus->resume_early) {
pm_dev_dbg(dev, state, "legacy EARLY ");
error = dev->bus->resume_early(dev);
}
End:
TRACE_RESUME(error);
@ -344,16 +341,16 @@ static int resume_device_noirq(struct device *dev, pm_message_t state)
}
/**
* dpm_power_up - Power on all regular (non-sysdev) devices.
* dpm_resume_noirq - Power on all regular (non-sysdev) devices.
* @state: PM transition of the system being carried out.
*
* Execute the appropriate "noirq resume" callback for all devices marked
* as DPM_OFF_IRQ.
* Call the "noirq" resume handlers for all devices marked as
* DPM_OFF_IRQ and enable device drivers to receive interrupts.
*
* Must be called under dpm_list_mtx. Device drivers should not receive
* interrupts while it's being executed.
*/
static void dpm_power_up(pm_message_t state)
void dpm_resume_noirq(pm_message_t state)
{
struct device *dev;
@ -363,33 +360,21 @@ static void dpm_power_up(pm_message_t state)
int error;
dev->power.status = DPM_OFF;
error = resume_device_noirq(dev, state);
error = device_resume_noirq(dev, state);
if (error)
pm_dev_err(dev, state, " early", error);
}
mutex_unlock(&dpm_list_mtx);
}
/**
* device_power_up - Turn on all devices that need special attention.
* @state: PM transition of the system being carried out.
*
* Call the "early" resume handlers and enable device drivers to receive
* interrupts.
*/
void device_power_up(pm_message_t state)
{
dpm_power_up(state);
resume_device_irqs();
}
EXPORT_SYMBOL_GPL(device_power_up);
EXPORT_SYMBOL_GPL(dpm_resume_noirq);
/**
* resume_device - Restore state for one device.
* device_resume - Restore state for one device.
* @dev: Device.
* @state: PM transition of the system being carried out.
*/
static int resume_device(struct device *dev, pm_message_t state)
static int device_resume(struct device *dev, pm_message_t state)
{
int error = 0;
@ -414,9 +399,6 @@ static int resume_device(struct device *dev, pm_message_t state)
if (dev->type->pm) {
pm_dev_dbg(dev, state, "type ");
error = pm_op(dev, dev->type->pm, state);
} else if (dev->type->resume) {
pm_dev_dbg(dev, state, "legacy type ");
error = dev->type->resume(dev);
}
if (error)
goto End;
@ -462,7 +444,7 @@ static void dpm_resume(pm_message_t state)
dev->power.status = DPM_RESUMING;
mutex_unlock(&dpm_list_mtx);
error = resume_device(dev, state);
error = device_resume(dev, state);
mutex_lock(&dpm_list_mtx);
if (error)
@ -480,11 +462,11 @@ static void dpm_resume(pm_message_t state)
}
/**
* complete_device - Complete a PM transition for given device
* device_complete - Complete a PM transition for given device
* @dev: Device.
* @state: PM transition of the system being carried out.
*/
static void complete_device(struct device *dev, pm_message_t state)
static void device_complete(struct device *dev, pm_message_t state)
{
down(&dev->sem);
@ -527,7 +509,7 @@ static void dpm_complete(pm_message_t state)
dev->power.status = DPM_ON;
mutex_unlock(&dpm_list_mtx);
complete_device(dev, state);
device_complete(dev, state);
mutex_lock(&dpm_list_mtx);
}
@ -540,19 +522,19 @@ static void dpm_complete(pm_message_t state)
}
/**
* device_resume - Restore state of each device in system.
* dpm_resume_end - Restore state of each device in system.
* @state: PM transition of the system being carried out.
*
* Resume all the devices, unlock them all, and allow new
* devices to be registered once again.
*/
void device_resume(pm_message_t state)
void dpm_resume_end(pm_message_t state)
{
might_sleep();
dpm_resume(state);
dpm_complete(state);
}
EXPORT_SYMBOL_GPL(device_resume);
EXPORT_SYMBOL_GPL(dpm_resume_end);
/*------------------------- Suspend routines -------------------------*/
@ -577,13 +559,13 @@ static pm_message_t resume_event(pm_message_t sleep_state)
}
/**
* suspend_device_noirq - Shut down one device (late suspend).
* device_suspend_noirq - Shut down one device (late suspend).
* @dev: Device.
* @state: PM transition of the system being carried out.
*
* This is called with interrupts off and only a single CPU running.
*/
static int suspend_device_noirq(struct device *dev, pm_message_t state)
static int device_suspend_noirq(struct device *dev, pm_message_t state)
{
int error = 0;
@ -593,24 +575,20 @@ static int suspend_device_noirq(struct device *dev, pm_message_t state)
if (dev->bus->pm) {
pm_dev_dbg(dev, state, "LATE ");
error = pm_noirq_op(dev, dev->bus->pm, state);
} else if (dev->bus->suspend_late) {
pm_dev_dbg(dev, state, "legacy LATE ");
error = dev->bus->suspend_late(dev, state);
suspend_report_result(dev->bus->suspend_late, error);
}
return error;
}
/**
* device_power_down - Shut down special devices.
* dpm_suspend_noirq - Power down all regular (non-sysdev) devices.
* @state: PM transition of the system being carried out.
*
* Prevent device drivers from receiving interrupts and call the "late"
* Prevent device drivers from receiving interrupts and call the "noirq"
* suspend handlers.
*
* Must be called under dpm_list_mtx.
*/
int device_power_down(pm_message_t state)
int dpm_suspend_noirq(pm_message_t state)
{
struct device *dev;
int error = 0;
@ -618,7 +596,7 @@ int device_power_down(pm_message_t state)
suspend_device_irqs();
mutex_lock(&dpm_list_mtx);
list_for_each_entry_reverse(dev, &dpm_list, power.entry) {
error = suspend_device_noirq(dev, state);
error = device_suspend_noirq(dev, state);
if (error) {
pm_dev_err(dev, state, " late", error);
break;
@ -627,17 +605,17 @@ int device_power_down(pm_message_t state)
}
mutex_unlock(&dpm_list_mtx);
if (error)
device_power_up(resume_event(state));
dpm_resume_noirq(resume_event(state));
return error;
}
EXPORT_SYMBOL_GPL(device_power_down);
EXPORT_SYMBOL_GPL(dpm_suspend_noirq);
/**
* suspend_device - Save state of one device.
* device_suspend - Save state of one device.
* @dev: Device.
* @state: PM transition of the system being carried out.
*/
static int suspend_device(struct device *dev, pm_message_t state)
static int device_suspend(struct device *dev, pm_message_t state)
{
int error = 0;
@ -660,10 +638,6 @@ static int suspend_device(struct device *dev, pm_message_t state)
if (dev->type->pm) {
pm_dev_dbg(dev, state, "type ");
error = pm_op(dev, dev->type->pm, state);
} else if (dev->type->suspend) {
pm_dev_dbg(dev, state, "legacy type ");
error = dev->type->suspend(dev, state);
suspend_report_result(dev->type->suspend, error);
}
if (error)
goto End;
@ -704,7 +678,7 @@ static int dpm_suspend(pm_message_t state)
get_device(dev);
mutex_unlock(&dpm_list_mtx);
error = suspend_device(dev, state);
error = device_suspend(dev, state);
mutex_lock(&dpm_list_mtx);
if (error) {
@ -723,11 +697,11 @@ static int dpm_suspend(pm_message_t state)
}
/**
* prepare_device - Execute the ->prepare() callback(s) for given device.
* device_prepare - Execute the ->prepare() callback(s) for given device.
* @dev: Device.
* @state: PM transition of the system being carried out.
*/
static int prepare_device(struct device *dev, pm_message_t state)
static int device_prepare(struct device *dev, pm_message_t state)
{
int error = 0;
@ -781,7 +755,7 @@ static int dpm_prepare(pm_message_t state)
dev->power.status = DPM_PREPARING;
mutex_unlock(&dpm_list_mtx);
error = prepare_device(dev, state);
error = device_prepare(dev, state);
mutex_lock(&dpm_list_mtx);
if (error) {
@ -807,12 +781,12 @@ static int dpm_prepare(pm_message_t state)
}
/**
* device_suspend - Save state and stop all devices in system.
* dpm_suspend_start - Save state and stop all devices in system.
* @state: PM transition of the system being carried out.
*
* Prepare and suspend all devices.
*/
int device_suspend(pm_message_t state)
int dpm_suspend_start(pm_message_t state)
{
int error;
@ -822,7 +796,7 @@ int device_suspend(pm_message_t state)
error = dpm_suspend(state);
return error;
}
EXPORT_SYMBOL_GPL(device_suspend);
EXPORT_SYMBOL_GPL(dpm_suspend_start);
void __suspend_report_result(const char *function, void *fn, int ret)
{

16
drivers/base/sys.c
View File

@ -343,11 +343,15 @@ static void __sysdev_resume(struct sys_device *dev)
/* First, call the class-specific one */
if (cls->resume)
cls->resume(dev);
WARN_ONCE(!irqs_disabled(),
"Interrupts enabled after %pF\n", cls->resume);
/* Call auxillary drivers next. */
list_for_each_entry(drv, &cls->drivers, entry) {
if (drv->resume)
drv->resume(dev);
WARN_ONCE(!irqs_disabled(),
"Interrupts enabled after %pF\n", drv->resume);
}
}
@ -377,6 +381,9 @@ int sysdev_suspend(pm_message_t state)
if (ret)
return ret;
WARN_ONCE(!irqs_disabled(),
"Interrupts enabled while suspending system devices\n");
pr_debug("Suspending System Devices\n");
list_for_each_entry_reverse(cls, &system_kset->list, kset.kobj.entry) {
@ -393,6 +400,9 @@ int sysdev_suspend(pm_message_t state)
if (ret)
goto aux_driver;
}
WARN_ONCE(!irqs_disabled(),
"Interrupts enabled after %pF\n",
drv->suspend);
}
/* Now call the generic one */
@ -400,6 +410,9 @@ int sysdev_suspend(pm_message_t state)
ret = cls->suspend(sysdev, state);
if (ret)
goto cls_driver;
WARN_ONCE(!irqs_disabled(),
"Interrupts enabled after %pF\n",
cls->suspend);
}
}
}
@ -452,6 +465,9 @@ int sysdev_resume(void)
{
struct sysdev_class *cls;
WARN_ONCE(!irqs_disabled(),
"Interrupts enabled while resuming system devices\n");
pr_debug("Resuming System Devices\n");
list_for_each_entry(cls, &system_kset->list, kset.kobj.entry) {

16
drivers/xen/manage.c
View File

@ -43,7 +43,7 @@ static int xen_suspend(void *data)
if (err) {
printk(KERN_ERR "xen_suspend: sysdev_suspend failed: %d\n",
err);
device_power_up(PMSG_RESUME);
dpm_resume_noirq(PMSG_RESUME);
return err;
}
@ -69,7 +69,7 @@ static int xen_suspend(void *data)
}
sysdev_resume();
device_power_up(PMSG_RESUME);
dpm_resume_noirq(PMSG_RESUME);
return 0;
}
@ -92,18 +92,18 @@ static void do_suspend(void)
}
#endif
err = device_suspend(PMSG_SUSPEND);
err = dpm_suspend_start(PMSG_SUSPEND);
if (err) {
printk(KERN_ERR "xen suspend: device_suspend %d\n", err);
printk(KERN_ERR "xen suspend: dpm_suspend_start %d\n", err);
goto out;
}
printk(KERN_DEBUG "suspending xenstore...\n");
xs_suspend();
err = device_power_down(PMSG_SUSPEND);
err = dpm_suspend_noirq(PMSG_SUSPEND);
if (err) {
printk(KERN_ERR "device_power_down failed: %d\n", err);
printk(KERN_ERR "dpm_suspend_noirq failed: %d\n", err);
goto resume_devices;
}
@ -119,10 +119,10 @@ static void do_suspend(void)
} else
xs_suspend_cancel();
device_power_up(PMSG_RESUME);
dpm_resume_noirq(PMSG_RESUME);
resume_devices:
device_resume(PMSG_RESUME);
dpm_resume_end(PMSG_RESUME);
/* Make sure timer events get retriggered on all CPUs */
clock_was_set();

5
include/linux/device.h
View File

@ -62,8 +62,6 @@ struct bus_type {
void (*shutdown)(struct device *dev);
int (*suspend)(struct device *dev, pm_message_t state);
int (*suspend_late)(struct device *dev, pm_message_t state);
int (*resume_early)(struct device *dev);
int (*resume)(struct device *dev);
struct dev_pm_ops *pm;
@ -291,9 +289,6 @@ struct device_type {
int (*uevent)(struct device *dev, struct kobj_uevent_env *env);
void (*release)(struct device *dev);
int (*suspend)(struct device *dev, pm_message_t state);
int (*resume)(struct device *dev);
struct dev_pm_ops *pm;
};

6
include/linux/interrupt.h
View File

@ -183,6 +183,7 @@ extern void disable_irq(unsigned int irq);
extern void enable_irq(unsigned int irq);
/* The following three functions are for the core kernel use only. */
#ifdef CONFIG_GENERIC_HARDIRQS
extern void suspend_device_irqs(void);
extern void resume_device_irqs(void);
#ifdef CONFIG_PM_SLEEP
@ -190,6 +191,11 @@ extern int check_wakeup_irqs(void);
#else
static inline int check_wakeup_irqs(void) { return 0; }
#endif
#else
static inline void suspend_device_irqs(void) { };
static inline void resume_device_irqs(void) { };
static inline int check_wakeup_irqs(void) { return 0; }
#endif
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)

11
include/linux/pm.h
View File

@ -382,14 +382,13 @@ struct dev_pm_info {
#ifdef CONFIG_PM_SLEEP
extern void device_pm_lock(void);
extern int sysdev_resume(void);
extern void device_power_up(pm_message_t state);
extern void device_resume(pm_message_t state);
extern void dpm_resume_noirq(pm_message_t state);
extern void dpm_resume_end(pm_message_t state);
extern void device_pm_unlock(void);
extern int sysdev_suspend(pm_message_t state);
extern int device_power_down(pm_message_t state);
extern int device_suspend(pm_message_t state);
extern int device_prepare_suspend(pm_message_t state);
extern int dpm_suspend_noirq(pm_message_t state);
extern int dpm_suspend_start(pm_message_t state);
extern void __suspend_report_result(const char *function, void *fn, int ret);
@ -403,7 +402,7 @@ extern void __suspend_report_result(const char *function, void *fn, int ret);
#define device_pm_lock() do {} while (0)
#define device_pm_unlock() do {} while (0)
static inline int device_suspend(pm_message_t state)
static inline int dpm_suspend_start(pm_message_t state)
{
return 0;
}

18
include/linux/suspend.h
View File

@ -245,11 +245,6 @@ extern unsigned long get_safe_page(gfp_t gfp_mask);
extern void hibernation_set_ops(struct platform_hibernation_ops *ops);
extern int hibernate(void);
extern int hibernate_nvs_register(unsigned long start, unsigned long size);
extern int hibernate_nvs_alloc(void);
extern void hibernate_nvs_free(void);
extern void hibernate_nvs_save(void);
extern void hibernate_nvs_restore(void);
extern bool system_entering_hibernation(void);
#else /* CONFIG_HIBERNATION */
static inline int swsusp_page_is_forbidden(struct page *p) { return 0; }
@ -258,6 +253,16 @@ static inline void swsusp_unset_page_free(struct page *p) {}
static inline void hibernation_set_ops(struct platform_hibernation_ops *ops) {}
static inline int hibernate(void) { return -ENOSYS; }
static inline bool system_entering_hibernation(void) { return false; }
#endif /* CONFIG_HIBERNATION */
#ifdef CONFIG_HIBERNATION_NVS
extern int hibernate_nvs_register(unsigned long start, unsigned long size);
extern int hibernate_nvs_alloc(void);
extern void hibernate_nvs_free(void);
extern void hibernate_nvs_save(void);
extern void hibernate_nvs_restore(void);
#else /* CONFIG_HIBERNATION_NVS */
static inline int hibernate_nvs_register(unsigned long a, unsigned long b)
{
return 0;
@ -266,8 +271,7 @@ static inline int hibernate_nvs_alloc(void) { return 0; }
static inline void hibernate_nvs_free(void) {}
static inline void hibernate_nvs_save(void) {}
static inline void hibernate_nvs_restore(void) {}
static inline bool system_entering_hibernation(void) { return false; }
#endif /* CONFIG_HIBERNATION */
#endif /* CONFIG_HIBERNATION_NVS */
#ifdef CONFIG_PM_SLEEP
void save_processor_state(void);

14
kernel/kexec.c
View File

@ -1448,17 +1448,17 @@ int kernel_kexec(void)
goto Restore_console;
}
suspend_console();
error = device_suspend(PMSG_FREEZE);
error = dpm_suspend_start(PMSG_FREEZE);
if (error)
goto Resume_console;
/* At this point, device_suspend() has been called,
* but *not* device_power_down(). We *must*
* device_power_down() now. Otherwise, drivers for
/* At this point, dpm_suspend_start() has been called,
* but *not* dpm_suspend_noirq(). We *must* call
* dpm_suspend_noirq() now. Otherwise, drivers for
* some devices (e.g. interrupt controllers) become
* desynchronized with the actual state of the
* hardware at resume time, and evil weirdness ensues.
*/
error = device_power_down(PMSG_FREEZE);
error = dpm_suspend_noirq(PMSG_FREEZE);
if (error)
goto Resume_devices;
error = disable_nonboot_cpus();
@ -1486,9 +1486,9 @@ int kernel_kexec(void)
local_irq_enable();
Enable_cpus:
enable_nonboot_cpus();
device_power_up(PMSG_RESTORE);
dpm_resume_noirq(PMSG_RESTORE);
Resume_devices:
device_resume(PMSG_RESTORE);
dpm_resume_end(PMSG_RESTORE);
Resume_console:
resume_console();
thaw_processes();

4
kernel/power/Kconfig
View File

@ -116,9 +116,13 @@ config SUSPEND_FREEZER
Turning OFF this setting is NOT recommended! If in doubt, say Y.
config HIBERNATION_NVS
bool
config HIBERNATION
bool "Hibernation (aka 'suspend to disk')"
depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE
select HIBERNATION_NVS if HAS_IOMEM
---help---
Enable the suspend to disk (STD) functionality, which is usually
called "hibernation" in user interfaces. STD checkpoints the

5
kernel/power/Makefile
View File

@ -6,6 +6,9 @@ endif
obj-$(CONFIG_PM) += main.o
obj-$(CONFIG_PM_SLEEP) += console.o
obj-$(CONFIG_FREEZER) += process.o
obj-$(CONFIG_HIBERNATION) += swsusp.o disk.o snapshot.o swap.o user.o
obj-$(CONFIG_SUSPEND) += suspend.o
obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o
obj-$(CONFIG_HIBERNATION) += swsusp.o hibernate.o snapshot.o swap.o user.o
obj-$(CONFIG_HIBERNATION_NVS) += hibernate_nvs.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o

34
kernel/power/disk.c → kernel/power/hibernate.c
View File

@ -1,12 +1,12 @@
/*
* kernel/power/disk.c - Suspend-to-disk support.
* kernel/power/hibernate.c - Hibernation (a.k.a suspend-to-disk) support.
*
* Copyright (c) 2003 Patrick Mochel
* Copyright (c) 2003 Open Source Development Lab
* Copyright (c) 2004 Pavel Machek <pavel@suse.cz>
* Copyright (c) 2009 Rafael J. Wysocki, Novell Inc.
*
* This file is released under the GPLv2.
*
*/
#include <linux/suspend.h>
@ -215,13 +215,13 @@ static int create_image(int platform_mode)
if (error)
return error;
/* At this point, device_suspend() has been called, but *not*
* device_power_down(). We *must* call device_power_down() now.
/* At this point, dpm_suspend_start() has been called, but *not*
* dpm_suspend_noirq(). We *must* call dpm_suspend_noirq() now.
* Otherwise, drivers for some devices (e.g. interrupt controllers)
* become desynchronized with the actual state of the hardware
* at resume time, and evil weirdness ensues.
*/
error = device_power_down(PMSG_FREEZE);
error = dpm_suspend_noirq(PMSG_FREEZE);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down, "
"aborting hibernation\n");
@ -262,7 +262,7 @@ static int create_image(int platform_mode)
Power_up:
sysdev_resume();
/* NOTE: device_power_up() is just a resume() for devices
/* NOTE: dpm_resume_noirq() is just a resume() for devices
* that suspended with irqs off ... no overall powerup.
*/
@ -275,7 +275,7 @@ static int create_image(int platform_mode)
Platform_finish:
platform_finish(platform_mode);
device_power_up(in_suspend ?
dpm_resume_noirq(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
return error;
@ -304,7 +304,7 @@ int hibernation_snapshot(int platform_mode)
goto Close;
suspend_console();
error = device_suspend(PMSG_FREEZE);
error = dpm_suspend_start(PMSG_FREEZE);
if (error)
goto Recover_platform;
@ -315,7 +315,7 @@ int hibernation_snapshot(int platform_mode)
/* Control returns here after successful restore */
Resume_devices:
device_resume(in_suspend ?
dpm_resume_end(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
resume_console();
Close:
@ -339,7 +339,7 @@ static int resume_target_kernel(bool platform_mode)
{
int error;
error = device_power_down(PMSG_QUIESCE);
error = dpm_suspend_noirq(PMSG_QUIESCE);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down, "
"aborting resume\n");
@ -394,7 +394,7 @@ static int resume_target_kernel(bool platform_mode)
Cleanup:
platform_restore_cleanup(platform_mode);
device_power_up(PMSG_RECOVER);
dpm_resume_noirq(PMSG_RECOVER);
return error;
}
@ -414,10 +414,10 @@ int hibernation_restore(int platform_mode)
pm_prepare_console();
suspend_console();
error = device_suspend(PMSG_QUIESCE);
error = dpm_suspend_start(PMSG_QUIESCE);
if (!error) {
error = resume_target_kernel(platform_mode);
device_resume(PMSG_RECOVER);
dpm_resume_end(PMSG_RECOVER);
}
resume_console();
pm_restore_console();
@ -447,14 +447,14 @@ int hibernation_platform_enter(void)
entering_platform_hibernation = true;
suspend_console();
error = device_suspend(PMSG_HIBERNATE);
error = dpm_suspend_start(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
hibernation_ops->recover();
goto Resume_devices;
}
error = device_power_down(PMSG_HIBERNATE);
error = dpm_suspend_noirq(PMSG_HIBERNATE);
if (error)
goto Resume_devices;
@ -479,11 +479,11 @@ int hibernation_platform_enter(void)
Platofrm_finish:
hibernation_ops->finish();
device_power_up(PMSG_RESTORE);
dpm_suspend_noirq(PMSG_RESTORE);
Resume_devices:
entering_platform_hibernation = false;
device_resume(PMSG_RESTORE);
dpm_resume_end(PMSG_RESTORE);
resume_console();
Close:

135
kernel/power/hibernate_nvs.c Normal file
View File

@ -0,0 +1,135 @@
/*
* linux/kernel/power/hibernate_nvs.c - Routines for handling NVS memory
*
* Copyright (C) 2008,2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
*
* This file is released under the GPLv2.
*/
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/suspend.h>
/*
* Platforms, like ACPI, may want us to save some memory used by them during
* hibernation and to restore the contents of this memory during the subsequent
* resume. The code below implements a mechanism allowing us to do that.
*/
struct nvs_page {
unsigned long phys_start;
unsigned int size;
void *kaddr;
void *data;
struct list_head node;
};
static LIST_HEAD(nvs_list);
/**
* hibernate_nvs_register - register platform NVS memory region to save
* @start - physical address of the region
* @size - size of the region
*
* The NVS region need not be page-aligned (both ends) and we arrange
* things so that the data from page-aligned addresses in this region will
* be copied into separate RAM pages.
*/
int hibernate_nvs_register(unsigned long start, unsigned long size)
{
struct nvs_page *entry, *next;
while (size > 0) {
unsigned int nr_bytes;
entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
if (!entry)
goto Error;
list_add_tail(&entry->node, &nvs_list);
entry->phys_start = start;
nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
entry->size = (size < nr_bytes) ? size : nr_bytes;
start += entry->size;
size -= entry->size;
}
return 0;
Error:
list_for_each_entry_safe(entry, next, &nvs_list, node) {
list_del(&entry->node);
kfree(entry);
}
return -ENOMEM;
}
/**
* hibernate_nvs_free - free data pages allocated for saving NVS regions
*/
void hibernate_nvs_free(void)
{
struct nvs_page *entry;
list_for_each_entry(entry, &nvs_list, node)
if (entry->data) {
free_page((unsigned long)entry->data);
entry->data = NULL;
if (entry->kaddr) {
iounmap(entry->kaddr);
entry->kaddr = NULL;
}
}
}
/**
* hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
*/
int hibernate_nvs_alloc(void)
{
struct nvs_page *entry;
list_for_each_entry(entry, &nvs_list, node) {
entry->data = (void *)__get_free_page(GFP_KERNEL);
if (!entry->data) {
hibernate_nvs_free();
return -ENOMEM;
}
}
return 0;
}
/**
* hibernate_nvs_save - save NVS memory regions
*/
void hibernate_nvs_save(void)
{
struct nvs_page *entry;
printk(KERN_INFO "PM: Saving platform NVS memory\n");
list_for_each_entry(entry, &nvs_list, node)
if (entry->data) {
entry->kaddr = ioremap(entry->phys_start, entry->size);
memcpy(entry->data, entry->kaddr, entry->size);
}
}
/**
* hibernate_nvs_restore - restore NVS memory regions
*
* This function is going to be called with interrupts disabled, so it
* cannot iounmap the virtual addresses used to access the NVS region.
*/
void hibernate_nvs_restore(void)
{
struct nvs_page *entry;
printk(KERN_INFO "PM: Restoring platform NVS memory\n");
list_for_each_entry(entry, &nvs_list, node)
if (entry->data)
memcpy(entry->kaddr, entry->data, entry->size);
}

521
kernel/power/main.c
View File

@ -8,20 +8,9 @@
*
*/
#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/kmod.h>
#include <linux/init.h>
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/resume-trace.h>
#include <linux/freezer.h>
#include <linux/vmstat.h>
#include <linux/syscalls.h>
#include "power.h"
@ -119,373 +108,6 @@ power_attr(pm_test);
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_SUSPEND
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;
}
#ifdef CONFIG_PM_TEST_SUSPEND
/*
* We test the system suspend code by setting an RTC wakealarm a short
* time in the future, then suspending. Suspending the devices won't
* normally take long ... some systems only need a few milliseconds.
*
* The time it takes is system-specific though, so when we test this
* during system bootup we allow a LOT of time.
*/
#define TEST_SUSPEND_SECONDS 5
static unsigned long suspend_test_start_time;
static void suspend_test_start(void)
{
/* FIXME Use better timebase than "jiffies", ideally a clocksource.
* What we want is a hardware counter that will work correctly even
* during the irqs-are-off stages of the suspend/resume cycle...
*/
suspend_test_start_time = jiffies;
}
static void suspend_test_finish(const char *label)
{
long nj = jiffies - suspend_test_start_time;
unsigned msec;
msec = jiffies_to_msecs(abs(nj));
pr_info("PM: %s took %d.%03d seconds\n", label,
msec / 1000, msec % 1000);
/* Warning on suspend means the RTC alarm period needs to be
* larger -- the system was sooo slooowwww to suspend that the
* alarm (should have) fired before the system went to sleep!
*
* Warning on either suspend or resume also means the system
* has some performance issues. The stack dump of a WARN_ON
* is more likely to get the right attention than a printk...
*/
WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
}
#else
static void suspend_test_start(void)
{
}
static void suspend_test_finish(const char *label)
{
}
#endif
/* This is just an arbitrary number */
#define FREE_PAGE_NUMBER (100)
static struct platform_suspend_ops *suspend_ops;
/**
* suspend_set_ops - Set the global suspend method table.
* @ops: Pointer to ops structure.
*/
void suspend_set_ops(struct platform_suspend_ops *ops)
{
mutex_lock(&pm_mutex);
suspend_ops = ops;
mutex_unlock(&pm_mutex);
}
/**
* 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;
}
/**
* suspend_prepare - Do prep work before entering low-power 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.
*/
static int suspend_prepare(void)
{
int error;
unsigned int free_pages;
if (!suspend_ops || !suspend_ops->enter)
return -EPERM;
pm_prepare_console();
error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
if (error)
goto Finish;
error = usermodehelper_disable();
if (error)
goto Finish;
if (suspend_freeze_processes()) {
error = -EAGAIN;
goto Thaw;
}
free_pages = global_page_state(NR_FREE_PAGES);
if (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");
}
}
if (!error)
return 0;
Thaw:
suspend_thaw_processes();
usermodehelper_enable();
Finish:
pm_notifier_call_chain(PM_POST_SUSPEND);
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();
}
/**
* suspend_enter - enter the desired system sleep state.
* @state: state to enter
*
* This function should be called after devices have been suspended.
*/
static int suspend_enter(suspend_state_t state)
{
int error;
if (suspend_ops->prepare) {
error = suspend_ops->prepare();
if (error)
return error;
}
error = device_power_down(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down\n");
goto Platfrom_finish;
}
if (suspend_ops->prepare_late) {
error = suspend_ops->prepare_late();
if (error)
goto Power_up_devices;
}
if (suspend_test(TEST_PLATFORM))
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 = sysdev_suspend(PMSG_SUSPEND);
if (!error) {
if (!suspend_test(TEST_CORE))
error = suspend_ops->enter(state);
sysdev_resume();
}
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
Enable_cpus:
enable_nonboot_cpus();
Platform_wake:
if (suspend_ops->wake)
suspend_ops->wake();
Power_up_devices:
device_power_up(PMSG_RESUME);
Platfrom_finish:
if (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
*/
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
if (!suspend_ops)
return -ENOSYS;
if (suspend_ops->begin) {
error = suspend_ops->begin(state);
if (error)
goto Close;
}
suspend_console();
suspend_test_start();
error = device_suspend(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to suspend\n");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
if (suspend_test(TEST_DEVICES))
goto Recover_platform;
suspend_enter(state);
Resume_devices:
suspend_test_start();
device_resume(PMSG_RESUME);
suspend_test_finish("resume devices");
resume_console();
Close:
if (suspend_ops->end)
suspend_ops->end();
return error;
Recover_platform:
if (suspend_ops->recover)
suspend_ops->recover();
goto Resume_devices;
}
/**
* suspend_finish - Do final work before exiting 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.
*/
static void suspend_finish(void)
{
suspend_thaw_processes();
usermodehelper_enable();
pm_notifier_call_chain(PM_POST_SUSPEND);
pm_restore_console();
}
static const char * const pm_states[PM_SUSPEND_MAX] = {
[PM_SUSPEND_STANDBY] = "standby",
[PM_SUSPEND_MEM] = "mem",
};
static inline int valid_state(suspend_state_t state)
{
/* All states need lowlevel support and need to be valid
* to the lowlevel implementation, no valid callback
* implies that none are valid. */
if (!suspend_ops || !suspend_ops->valid || !suspend_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;
printk(KERN_INFO "PM: Syncing filesystems ... ");
sys_sync();
printk("done.\n");
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
error = suspend_prepare();
if (error)
goto Unlock;
if (suspend_test(TEST_FREEZER))
goto Finish;
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
error = suspend_devices_and_enter(state);
Finish:
pr_debug("PM: Finishing wakeup.\n");
suspend_finish();
Unlock:
mutex_unlock(&pm_mutex);
return error;
}
/**
* pm_suspend - Externally visible function for suspending system.
* @state: Enumerated 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);
#endif /* CONFIG_SUSPEND */
struct kobject *power_kobj;
/**
@ -498,7 +120,6 @@ struct kobject *power_kobj;
* store() accepts one of those strings, translates it into the
* proper enumerated value, and initiates a suspend transition.
*/
static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
@ -596,7 +217,6 @@ static struct attribute_group attr_group = {
.attrs = g,
};
static int __init pm_init(void)
{
power_kobj = kobject_create_and_add("power", NULL);
@ -606,144 +226,3 @@ static int __init pm_init(void)
}
core_initcall(pm_init);
#ifdef CONFIG_PM_TEST_SUSPEND
#include <linux/rtc.h>
/*
* To test system suspend, we need a hands-off mechanism to resume the
* system. RTCs wake alarms are a common self-contained mechanism.
*/
static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
{
static char err_readtime[] __initdata =
KERN_ERR "PM: can't read %s time, err %d\n";
static char err_wakealarm [] __initdata =
KERN_ERR "PM: can't set %s wakealarm, err %d\n";
static char err_suspend[] __initdata =
KERN_ERR "PM: suspend test failed, error %d\n";
static char info_test[] __initdata =
KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
unsigned long now;
struct rtc_wkalrm alm;
int status;
/* this may fail if the RTC hasn't been initialized */
status = rtc_read_time(rtc, &alm.time);
if (status < 0) {
printk(err_readtime, dev_name(&rtc->dev), status);
return;
}
rtc_tm_to_time(&alm.time, &now);
memset(&alm, 0, sizeof alm);
rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
alm.enabled = true;
status = rtc_set_alarm(rtc, &alm);
if (status < 0) {
printk(err_wakealarm, dev_name(&rtc->dev), status);
return;
}
if (state == PM_SUSPEND_MEM) {
printk(info_test, pm_states[state]);
status = pm_suspend(state);
if (status == -ENODEV)
state = PM_SUSPEND_STANDBY;
}
if (state == PM_SUSPEND_STANDBY) {
printk(info_test, pm_states[state]);
status = pm_suspend(state);
}
if (status < 0)
printk(err_suspend, status);
/* Some platforms can't detect that the alarm triggered the
* wakeup, or (accordingly) disable it after it afterwards.
* It's supposed to give oneshot behavior; cope.
*/
alm.enabled = false;
rtc_set_alarm(rtc, &alm);
}
static int __init has_wakealarm(struct device *dev, void *name_ptr)
{
struct rtc_device *candidate = to_rtc_device(dev);
if (!candidate->ops->set_alarm)
return 0;
if (!device_may_wakeup(candidate->dev.parent))
return 0;
*(const char **)name_ptr = dev_name(dev);
return 1;
}
/*
* Kernel options like "test_suspend=mem" force suspend/resume sanity tests
* at startup time. They're normally disabled, for faster boot and because
* we can't know which states really work on this particular system.
*/
static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
static char warn_bad_state[] __initdata =
KERN_WARNING "PM: can't test '%s' suspend state\n";
static int __init setup_test_suspend(char *value)
{
unsigned i;
/* "=mem" ==> "mem" */
value++;
for (i = 0; i < PM_SUSPEND_MAX; i++) {
if (!pm_states[i])
continue;
if (strcmp(pm_states[i], value) != 0)
continue;
test_state = (__force suspend_state_t) i;
return 0;
}
printk(warn_bad_state, value);
return 0;
}
__setup("test_suspend", setup_test_suspend);
static int __init test_suspend(void)
{
static char warn_no_rtc[] __initdata =
KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
char *pony = NULL;
struct rtc_device *rtc = NULL;
/* PM is initialized by now; is that state testable? */
if (test_state == PM_SUSPEND_ON)
goto done;
if (!valid_state(test_state)) {
printk(warn_bad_state, pm_states[test_state]);
goto done;
}
/* RTCs have initialized by now too ... can we use one? */
class_find_device(rtc_class, NULL, &pony, has_wakealarm);
if (pony)
rtc = rtc_class_open(pony);
if (!rtc) {
printk(warn_no_rtc);
goto done;
}
/* go for it */
test_wakealarm(rtc, test_state);
rtc_class_close(rtc);
done:
return 0;
}
late_initcall(test_suspend);
#endif /* CONFIG_PM_TEST_SUSPEND */

25
kernel/power/power.h
View File

@ -45,7 +45,7 @@ static inline char *check_image_kernel(struct swsusp_info *info)
*/
#define SPARE_PAGES ((1024 * 1024) >> PAGE_SHIFT)
/* kernel/power/disk.c */
/* kernel/power/hibernate.c */
extern int hibernation_snapshot(int platform_mode);
extern int hibernation_restore(int platform_mode);
extern int hibernation_platform_enter(void);
@ -74,7 +74,7 @@ extern asmlinkage int swsusp_arch_resume(void);
extern int create_basic_memory_bitmaps(void);
extern void free_basic_memory_bitmaps(void);
extern unsigned int count_data_pages(void);
extern int swsusp_shrink_memory(void);
/**
* Auxiliary structure used for reading the snapshot image data and
@ -147,9 +147,8 @@ extern int swsusp_swap_in_use(void);
*/
#define SF_PLATFORM_MODE 1
/* kernel/power/disk.c */
/* kernel/power/hibernate.c */
extern int swsusp_check(void);
extern int swsusp_shrink_memory(void);
extern void swsusp_free(void);
extern int swsusp_read(unsigned int *flags_p);
extern int swsusp_write(unsigned int flags);
@ -161,22 +160,36 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *,
unsigned int, char *);
#ifdef CONFIG_SUSPEND
/* kernel/power/main.c */
/* kernel/power/suspend.c */
extern const char *const pm_states[];
extern bool valid_state(suspend_state_t state);
extern int suspend_devices_and_enter(suspend_state_t state);
extern int enter_state(suspend_state_t state);
#else /* !CONFIG_SUSPEND */
static inline int suspend_devices_and_enter(suspend_state_t state)
{
return -ENOSYS;
}
static inline int enter_state(suspend_state_t state) { return -ENOSYS; }
static inline bool valid_state(suspend_state_t state) { return false; }
#endif /* !CONFIG_SUSPEND */
#ifdef CONFIG_PM_TEST_SUSPEND
/* kernel/power/suspend_test.c */
extern void suspend_test_start(void);
extern void suspend_test_finish(const char *label);
#else /* !CONFIG_PM_TEST_SUSPEND */
static inline void suspend_test_start(void) {}
static inline void suspend_test_finish(const char *label) {}
#endif /* !CONFIG_PM_TEST_SUSPEND */
#ifdef CONFIG_PM_SLEEP
/* kernel/power/main.c */
extern int pm_notifier_call_chain(unsigned long val);
#endif
#ifdef CONFIG_HIGHMEM
unsigned int count_highmem_pages(void);
int restore_highmem(void);
#else
static inline unsigned int count_highmem_pages(void) { return 0; }

80
kernel/power/snapshot.c
View File

@ -39,6 +39,14 @@ static int swsusp_page_is_free(struct page *);
static void swsusp_set_page_forbidden(struct page *);
static void swsusp_unset_page_forbidden(struct page *);
/*
* Preferred image size in bytes (tunable via /sys/power/image_size).
* When it is set to N, swsusp will do its best to ensure the image
* size will not exceed N bytes, but if that is impossible, it will
* try to create the smallest image possible.
*/
unsigned long image_size = 500 * 1024 * 1024;
/* List of PBEs needed for restoring the pages that were allocated before
* the suspend and included in the suspend image, but have also been
* allocated by the "resume" kernel, so their contents cannot be written
@ -840,7 +848,7 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn)
* pages.
*/
unsigned int count_highmem_pages(void)
static unsigned int count_highmem_pages(void)
{
struct zone *zone;
unsigned int n = 0;
@ -902,7 +910,7 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn)
* pages.
*/
unsigned int count_data_pages(void)
static unsigned int count_data_pages(void)
{
struct zone *zone;
unsigned long pfn, max_zone_pfn;
@ -1058,6 +1066,74 @@ void swsusp_free(void)
buffer = NULL;
}
/**
* swsusp_shrink_memory - Try to free as much memory as needed
*
* ... but do not OOM-kill anyone
*
* Notice: all userland should be stopped before it is called, or
* livelock is possible.
*/
#define SHRINK_BITE 10000
static inline unsigned long __shrink_memory(long tmp)
{
if (tmp > SHRINK_BITE)
tmp = SHRINK_BITE;
return shrink_all_memory(tmp);
}
int swsusp_shrink_memory(void)
{
long tmp;
struct zone *zone;
unsigned long pages = 0;
unsigned int i = 0;
char *p = "-\\|/";
struct timeval start, stop;
printk(KERN_INFO "PM: Shrinking memory... ");
do_gettimeofday(&start);
do {
long size, highmem_size;
highmem_size = count_highmem_pages();
size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
tmp = size;
size += highmem_size;
for_each_populated_zone(zone) {
tmp += snapshot_additional_pages(zone);
if (is_highmem(zone)) {
highmem_size -=
zone_page_state(zone, NR_FREE_PAGES);
} else {
tmp -= zone_page_state(zone, NR_FREE_PAGES);
tmp += zone->lowmem_reserve[ZONE_NORMAL];
}
}
if (highmem_size < 0)
highmem_size = 0;
tmp += highmem_size;
if (tmp > 0) {
tmp = __shrink_memory(tmp);
if (!tmp)
return -ENOMEM;
pages += tmp;
} else if (size > image_size / PAGE_SIZE) {
tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
pages += tmp;
}
printk("\b%c", p[i++%4]);
} while (tmp > 0);
do_gettimeofday(&stop);
printk("\bdone (%lu pages freed)\n", pages);
swsusp_show_speed(&start, &stop, pages, "Freed");
return 0;
}
#ifdef CONFIG_HIGHMEM
/**
* count_pages_for_highmem - compute the number of non-highmem pages

300
kernel/power/suspend.c Normal file
View File

@ -0,0 +1,300 @@
/*
* 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/syscalls.h>
#include "power.h"
const char *const pm_states[PM_SUSPEND_MAX] = {
[PM_SUSPEND_STANDBY] = "standby",
[PM_SUSPEND_MEM] = "mem",
};
static struct platform_suspend_ops *suspend_ops;
/**
* suspend_set_ops - Set the global suspend method table.
* @ops: Pointer to ops structure.
*/
void suspend_set_ops(struct platform_suspend_ops *ops)
{
mutex_lock(&pm_mutex);
suspend_ops = ops;
mutex_unlock(&pm_mutex);
}
bool valid_state(suspend_state_t state)
{
/*
* All states need lowlevel support and need to be valid to the lowlevel
* implementation, no valid callback implies that none are valid.
*/
return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
}
/**
* 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;
}
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 - Do prep work before entering low-power 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.
*/
static int suspend_prepare(void)
{
int error;
if (!suspend_ops || !suspend_ops->enter)
return -EPERM;
pm_prepare_console();
error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
if (error)
goto Finish;
error = usermodehelper_disable();
if (error)
goto Finish;
error = suspend_freeze_processes();
if (!error)
return 0;
suspend_thaw_processes();
usermodehelper_enable();
Finish:
pm_notifier_call_chain(PM_POST_SUSPEND);
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();
}
/**
* suspend_enter - enter the desired system sleep state.
* @state: state to enter
*
* This function should be called after devices have been suspended.
*/
static int suspend_enter(suspend_state_t state)
{
int error;
if (suspend_ops->prepare) {
error = suspend_ops->prepare();
if (error)
return error;
}
error = dpm_suspend_noirq(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down\n");
goto Platfrom_finish;
}
if (suspend_ops->prepare_late) {
error = suspend_ops->prepare_late();
if (error)
goto Power_up_devices;
}
if (suspend_test(TEST_PLATFORM))
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 = sysdev_suspend(PMSG_SUSPEND);
if (!error) {
if (!suspend_test(TEST_CORE))
error = suspend_ops->enter(state);
sysdev_resume();
}
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
Enable_cpus:
enable_nonboot_cpus();
Platform_wake:
if (suspend_ops->wake)
suspend_ops->wake();
Power_up_devices:
dpm_resume_noirq(PMSG_RESUME);
Platfrom_finish:
if (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
*/
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
if (!suspend_ops)
return -ENOSYS;
if (suspend_ops->begin) {
error = suspend_ops->begin(state);
if (error)
goto Close;
}
suspend_console();
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to suspend\n");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
if (suspend_test(TEST_DEVICES))
goto Recover_platform;
suspend_enter(state);
Resume_devices:
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
resume_console();
Close:
if (suspend_ops->end)
suspend_ops->end();
return error;
Recover_platform:
if (suspend_ops->recover)
suspend_ops->recover();
goto Resume_devices;
}
/**
* suspend_finish - Do final work before exiting 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.
*/
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.
*
* 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).
*/
int enter_state(suspend_state_t state)
{
int error;
if (!valid_state(state))
return -ENODEV;
if (!mutex_trylock(&pm_mutex))
return -EBUSY;
printk(KERN_INFO "PM: Syncing filesystems ... ");
sys_sync();
printk("done.\n");
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
error = suspend_prepare();
if (error)
goto Unlock;
if (suspend_test(TEST_FREEZER))
goto Finish;
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
error = suspend_devices_and_enter(state);
Finish:
pr_debug("PM: Finishing wakeup.\n");
suspend_finish();
Unlock:
mutex_unlock(&pm_mutex);
return error;
}
/**
* pm_suspend - Externally visible function for suspending system.
* @state: Enumerated 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);

187
kernel/power/suspend_test.c Normal file
View File

@ -0,0 +1,187 @@
/*
* kernel/power/suspend_test.c - Suspend to RAM and standby test facility.
*
* Copyright (c) 2009 Pavel Machek <pavel@ucw.cz>
*
* This file is released under the GPLv2.
*/
#include <linux/init.h>
#include <linux/rtc.h>
#include "power.h"
/*
* We test the system suspend code by setting an RTC wakealarm a short
* time in the future, then suspending. Suspending the devices won't
* normally take long ... some systems only need a few milliseconds.
*
* The time it takes is system-specific though, so when we test this
* during system bootup we allow a LOT of time.
*/
#define TEST_SUSPEND_SECONDS 5
static unsigned long suspend_test_start_time;
void suspend_test_start(void)
{
/* FIXME Use better timebase than "jiffies", ideally a clocksource.
* What we want is a hardware counter that will work correctly even
* during the irqs-are-off stages of the suspend/resume cycle...
*/
suspend_test_start_time = jiffies;
}
void suspend_test_finish(const char *label)
{
long nj = jiffies - suspend_test_start_time;
unsigned msec;
msec = jiffies_to_msecs(abs(nj));
pr_info("PM: %s took %d.%03d seconds\n", label,
msec / 1000, msec % 1000);
/* Warning on suspend means the RTC alarm period needs to be
* larger -- the system was sooo slooowwww to suspend that the
* alarm (should have) fired before the system went to sleep!
*
* Warning on either suspend or resume also means the system
* has some performance issues. The stack dump of a WARN_ON
* is more likely to get the right attention than a printk...
*/
WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
}
/*
* To test system suspend, we need a hands-off mechanism to resume the
* system. RTCs wake alarms are a common self-contained mechanism.
*/
static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
{
static char err_readtime[] __initdata =
KERN_ERR "PM: can't read %s time, err %d\n";
static char err_wakealarm [] __initdata =
KERN_ERR "PM: can't set %s wakealarm, err %d\n";
static char err_suspend[] __initdata =
KERN_ERR "PM: suspend test failed, error %d\n";
static char info_test[] __initdata =
KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
unsigned long now;
struct rtc_wkalrm alm;
int status;
/* this may fail if the RTC hasn't been initialized */
status = rtc_read_time(rtc, &alm.time);
if (status < 0) {
printk(err_readtime, dev_name(&rtc->dev), status);
return;
}
rtc_tm_to_time(&alm.time, &now);
memset(&alm, 0, sizeof alm);
rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
alm.enabled = true;
status = rtc_set_alarm(rtc, &alm);
if (status < 0) {
printk(err_wakealarm, dev_name(&rtc->dev), status);
return;
}
if (state == PM_SUSPEND_MEM) {
printk(info_test, pm_states[state]);
status = pm_suspend(state);
if (status == -ENODEV)
state = PM_SUSPEND_STANDBY;
}
if (state == PM_SUSPEND_STANDBY) {
printk(info_test, pm_states[state]);
status = pm_suspend(state);
}
if (status < 0)
printk(err_suspend, status);
/* Some platforms can't detect that the alarm triggered the
* wakeup, or (accordingly) disable it after it afterwards.
* It's supposed to give oneshot behavior; cope.
*/
alm.enabled = false;
rtc_set_alarm(rtc, &alm);
}
static int __init has_wakealarm(struct device *dev, void *name_ptr)
{
struct rtc_device *candidate = to_rtc_device(dev);
if (!candidate->ops->set_alarm)
return 0;
if (!device_may_wakeup(candidate->dev.parent))
return 0;
*(const char **)name_ptr = dev_name(dev);
return 1;
}
/*
* Kernel options like "test_suspend=mem" force suspend/resume sanity tests
* at startup time. They're normally disabled, for faster boot and because
* we can't know which states really work on this particular system.
*/
static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
static char warn_bad_state[] __initdata =
KERN_WARNING "PM: can't test '%s' suspend state\n";
static int __init setup_test_suspend(char *value)
{
unsigned i;
/* "=mem" ==> "mem" */
value++;
for (i = 0; i < PM_SUSPEND_MAX; i++) {
if (!pm_states[i])
continue;
if (strcmp(pm_states[i], value) != 0)
continue;
test_state = (__force suspend_state_t) i;
return 0;
}
printk(warn_bad_state, value);
return 0;
}
__setup("test_suspend", setup_test_suspend);
static int __init test_suspend(void)
{
static char warn_no_rtc[] __initdata =
KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
char *pony = NULL;
struct rtc_device *rtc = NULL;
/* PM is initialized by now; is that state testable? */
if (test_state == PM_SUSPEND_ON)
goto done;
if (!valid_state(test_state)) {
printk(warn_bad_state, pm_states[test_state]);
goto done;
}
/* RTCs have initialized by now too ... can we use one? */
class_find_device(rtc_class, NULL, &pony, has_wakealarm);
if (pony)
rtc = rtc_class_open(pony);
if (!rtc) {
printk(warn_no_rtc);
goto done;
}
/* go for it */
test_wakealarm(rtc, test_state);
rtc_class_close(rtc);
done:
return 0;
}
late_initcall(test_suspend);

198
kernel/power/swsusp.c
View File

@ -55,14 +55,6 @@
#include "power.h"
/*
* Preferred image size in bytes (tunable via /sys/power/image_size).
* When it is set to N, swsusp will do its best to ensure the image
* size will not exceed N bytes, but if that is impossible, it will
* try to create the smallest image possible.
*/
unsigned long image_size = 500 * 1024 * 1024;
int in_suspend __nosavedata = 0;
/**
@ -194,193 +186,3 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop,
centisecs / 100, centisecs % 100,
kps / 1000, (kps % 1000) / 10);
}
/**
* swsusp_shrink_memory - Try to free as much memory as needed
*
* ... but do not OOM-kill anyone
*
* Notice: all userland should be stopped before it is called, or
* livelock is possible.
*/
#define SHRINK_BITE 10000
static inline unsigned long __shrink_memory(long tmp)
{
if (tmp > SHRINK_BITE)
tmp = SHRINK_BITE;
return shrink_all_memory(tmp);
}
int swsusp_shrink_memory(void)
{
long tmp;
struct zone *zone;
unsigned long pages = 0;
unsigned int i = 0;
char *p = "-\\|/";
struct timeval start, stop;
printk(KERN_INFO "PM: Shrinking memory... ");
do_gettimeofday(&start);
do {
long size, highmem_size;
highmem_size = count_highmem_pages();
size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
tmp = size;
size += highmem_size;
for_each_populated_zone(zone) {
tmp += snapshot_additional_pages(zone);
if (is_highmem(zone)) {
highmem_size -=
zone_page_state(zone, NR_FREE_PAGES);
} else {
tmp -= zone_page_state(zone, NR_FREE_PAGES);
tmp += zone->lowmem_reserve[ZONE_NORMAL];
}
}
if (highmem_size < 0)
highmem_size = 0;
tmp += highmem_size;
if (tmp > 0) {
tmp = __shrink_memory(tmp);
if (!tmp)
return -ENOMEM;
pages += tmp;
} else if (size > image_size / PAGE_SIZE) {
tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
pages += tmp;
}
printk("\b%c", p[i++%4]);
} while (tmp > 0);
do_gettimeofday(&stop);
printk("\bdone (%lu pages freed)\n", pages);
swsusp_show_speed(&start, &stop, pages, "Freed");
return 0;
}
/*
* Platforms, like ACPI, may want us to save some memory used by them during
* hibernation and to restore the contents of this memory during the subsequent
* resume. The code below implements a mechanism allowing us to do that.
*/
struct nvs_page {
unsigned long phys_start;
unsigned int size;
void *kaddr;
void *data;
struct list_head node;
};
static LIST_HEAD(nvs_list);
/**
* hibernate_nvs_register - register platform NVS memory region to save
* @start - physical address of the region
* @size - size of the region
*
* The NVS region need not be page-aligned (both ends) and we arrange
* things so that the data from page-aligned addresses in this region will
* be copied into separate RAM pages.
*/
int hibernate_nvs_register(unsigned long start, unsigned long size)
{
struct nvs_page *entry, *next;
while (size > 0) {
unsigned int nr_bytes;
entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
if (!entry)
goto Error;
list_add_tail(&entry->node, &nvs_list);
entry->phys_start = start;
nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
entry->size = (size < nr_bytes) ? size : nr_bytes;
start += entry->size;
size -= entry->size;
}
return 0;
Error:
list_for_each_entry_safe(entry, next, &nvs_list, node) {
list_del(&entry->node);
kfree(entry);
}
return -ENOMEM;
}
/**
* hibernate_nvs_free - free data pages allocated for saving NVS regions
*/
void hibernate_nvs_free(void)
{
struct nvs_page *entry;
list_for_each_entry(entry, &nvs_list, node)
if (entry->data) {
free_page((unsigned long)entry->data);
entry->data = NULL;
if (entry->kaddr) {
iounmap(entry->kaddr);
entry->kaddr = NULL;
}
}
}
/**
* hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
*/
int hibernate_nvs_alloc(void)
{
struct nvs_page *entry;
list_for_each_entry(entry, &nvs_list, node) {
entry->data = (void *)__get_free_page(GFP_KERNEL);
if (!entry->data) {
hibernate_nvs_free();
return -ENOMEM;
}
}
return 0;
}
/**
* hibernate_nvs_save - save NVS memory regions
*/
void hibernate_nvs_save(void)
{
struct nvs_page *entry;
printk(KERN_INFO "PM: Saving platform NVS memory\n");
list_for_each_entry(entry, &nvs_list, node)
if (entry->data) {
entry->kaddr = ioremap(entry->phys_start, entry->size);
memcpy(entry->data, entry->kaddr, entry->size);
}
}
/**
* hibernate_nvs_restore - restore NVS memory regions
*
* This function is going to be called with interrupts disabled, so it
* cannot iounmap the virtual addresses used to access the NVS region.
*/
void hibernate_nvs_restore(void)
{
struct nvs_page *entry;
printk(KERN_INFO "PM: Restoring platform NVS memory\n");
list_for_each_entry(entry, &nvs_list, node)
if (entry->data)
memcpy(entry->kaddr, entry->data, entry->size);
}

4
mm/vmscan.c
View File

@ -2056,7 +2056,7 @@ unsigned long global_lru_pages(void)
+ global_page_state(NR_INACTIVE_FILE);
}
#ifdef CONFIG_PM
#ifdef CONFIG_HIBERNATION
/*
* Helper function for shrink_all_memory(). Tries to reclaim 'nr_pages' pages
* from LRU lists system-wide, for given pass and priority.
@ -2196,7 +2196,7 @@ out:
return sc.nr_reclaimed;
}
#endif
#endif /* CONFIG_HIBERNATION */
/* It's optimal to keep kswapds on the same CPUs as their memory, but
not required for correctness. So if the last cpu in a node goes