Merge commit 'linus/master' into HEAD

Conflicts:
	MAINTAINERS

Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
This commit is contained in:
Vegard Nossum
2009-06-15 15:50:49 +02:00
2130 changed files with 172928 additions and 37398 deletions

View File

@@ -45,7 +45,7 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
static void __init init_irq_default_affinity(void)
{
alloc_bootmem_cpumask_var(&irq_default_affinity);
alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
cpumask_setall(irq_default_affinity);
}
#else

View File

@@ -30,12 +30,16 @@
#define all_var 0
#endif
/* These will be re-linked against their real values during the second link stage */
/*
* These will be re-linked against their real values
* during the second link stage.
*/
extern const unsigned long kallsyms_addresses[] __attribute__((weak));
extern const u8 kallsyms_names[] __attribute__((weak));
/* tell the compiler that the count isn't in the small data section if the arch
* has one (eg: FRV)
/*
* Tell the compiler that the count isn't in the small data section if the arch
* has one (eg: FRV).
*/
extern const unsigned long kallsyms_num_syms
__attribute__((weak, section(".rodata")));
@@ -75,31 +79,37 @@ static int is_ksym_addr(unsigned long addr)
return is_kernel_text(addr) || is_kernel_inittext(addr);
}
/* expand a compressed symbol data into the resulting uncompressed string,
given the offset to where the symbol is in the compressed stream */
/*
* Expand a compressed symbol data into the resulting uncompressed string,
* given the offset to where the symbol is in the compressed stream.
*/
static unsigned int kallsyms_expand_symbol(unsigned int off, char *result)
{
int len, skipped_first = 0;
const u8 *tptr, *data;
/* get the compressed symbol length from the first symbol byte */
/* Get the compressed symbol length from the first symbol byte. */
data = &kallsyms_names[off];
len = *data;
data++;
/* update the offset to return the offset for the next symbol on
* the compressed stream */
/*
* Update the offset to return the offset for the next symbol on
* the compressed stream.
*/
off += len + 1;
/* for every byte on the compressed symbol data, copy the table
entry for that byte */
while(len) {
tptr = &kallsyms_token_table[ kallsyms_token_index[*data] ];
/*
* For every byte on the compressed symbol data, copy the table
* entry for that byte.
*/
while (len) {
tptr = &kallsyms_token_table[kallsyms_token_index[*data]];
data++;
len--;
while (*tptr) {
if(skipped_first) {
if (skipped_first) {
*result = *tptr;
result++;
} else
@@ -110,36 +120,46 @@ static unsigned int kallsyms_expand_symbol(unsigned int off, char *result)
*result = '\0';
/* return to offset to the next symbol */
/* Return to offset to the next symbol. */
return off;
}
/* get symbol type information. This is encoded as a single char at the
* begining of the symbol name */
/*
* Get symbol type information. This is encoded as a single char at the
* beginning of the symbol name.
*/
static char kallsyms_get_symbol_type(unsigned int off)
{
/* get just the first code, look it up in the token table, and return the
* first char from this token */
return kallsyms_token_table[ kallsyms_token_index[ kallsyms_names[off+1] ] ];
/*
* Get just the first code, look it up in the token table,
* and return the first char from this token.
*/
return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]];
}
/* find the offset on the compressed stream given and index in the
* kallsyms array */
/*
* Find the offset on the compressed stream given and index in the
* kallsyms array.
*/
static unsigned int get_symbol_offset(unsigned long pos)
{
const u8 *name;
int i;
/* use the closest marker we have. We have markers every 256 positions,
* so that should be close enough */
name = &kallsyms_names[ kallsyms_markers[pos>>8] ];
/*
* Use the closest marker we have. We have markers every 256 positions,
* so that should be close enough.
*/
name = &kallsyms_names[kallsyms_markers[pos >> 8]];
/* sequentially scan all the symbols up to the point we're searching for.
* Every symbol is stored in a [<len>][<len> bytes of data] format, so we
* just need to add the len to the current pointer for every symbol we
* wish to skip */
for(i = 0; i < (pos&0xFF); i++)
/*
* Sequentially scan all the symbols up to the point we're searching
* for. Every symbol is stored in a [<len>][<len> bytes of data] format,
* so we just need to add the len to the current pointer for every
* symbol we wish to skip.
*/
for (i = 0; i < (pos & 0xFF); i++)
name = name + (*name) + 1;
return name - kallsyms_names;
@@ -190,7 +210,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
/* This kernel should never had been booted. */
BUG_ON(!kallsyms_addresses);
/* do a binary search on the sorted kallsyms_addresses array */
/* Do a binary search on the sorted kallsyms_addresses array. */
low = 0;
high = kallsyms_num_syms;
@@ -203,15 +223,15 @@ static unsigned long get_symbol_pos(unsigned long addr,
}
/*
* search for the first aliased symbol. Aliased
* symbols are symbols with the same address
* Search for the first aliased symbol. Aliased
* symbols are symbols with the same address.
*/
while (low && kallsyms_addresses[low-1] == kallsyms_addresses[low])
--low;
symbol_start = kallsyms_addresses[low];
/* Search for next non-aliased symbol */
/* Search for next non-aliased symbol. */
for (i = low + 1; i < kallsyms_num_syms; i++) {
if (kallsyms_addresses[i] > symbol_start) {
symbol_end = kallsyms_addresses[i];
@@ -219,7 +239,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
}
}
/* if we found no next symbol, we use the end of the section */
/* If we found no next symbol, we use the end of the section. */
if (!symbol_end) {
if (is_kernel_inittext(addr))
symbol_end = (unsigned long)_einittext;
@@ -252,10 +272,10 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
/*
* Lookup an address
* - modname is set to NULL if it's in the kernel
* - we guarantee that the returned name is valid until we reschedule even if
* it resides in a module
* - we also guarantee that modname will be valid until rescheduled
* - modname is set to NULL if it's in the kernel.
* - We guarantee that the returned name is valid until we reschedule even if.
* It resides in a module.
* - We also guarantee that modname will be valid until rescheduled.
*/
const char *kallsyms_lookup(unsigned long addr,
unsigned long *symbolsize,
@@ -276,7 +296,7 @@ const char *kallsyms_lookup(unsigned long addr,
return namebuf;
}
/* see if it's in a module */
/* See if it's in a module. */
return module_address_lookup(addr, symbolsize, offset, modname,
namebuf);
}
@@ -294,7 +314,7 @@ int lookup_symbol_name(unsigned long addr, char *symname)
kallsyms_expand_symbol(get_symbol_offset(pos), symname);
return 0;
}
/* see if it's in a module */
/* See if it's in a module. */
return lookup_module_symbol_name(addr, symname);
}
@@ -313,7 +333,7 @@ int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
modname[0] = '\0';
return 0;
}
/* see if it's in a module */
/* See if it's in a module. */
return lookup_module_symbol_attrs(addr, size, offset, modname, name);
}
@@ -342,6 +362,7 @@ int sprint_symbol(char *buffer, unsigned long address)
return len;
}
EXPORT_SYMBOL_GPL(sprint_symbol);
/* Look up a kernel symbol and print it to the kernel messages. */
void __print_symbol(const char *fmt, unsigned long address)
@@ -352,13 +373,13 @@ void __print_symbol(const char *fmt, unsigned long address)
printk(fmt, buffer);
}
EXPORT_SYMBOL(__print_symbol);
/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
struct kallsym_iter
{
struct kallsym_iter {
loff_t pos;
unsigned long value;
unsigned int nameoff; /* If iterating in core kernel symbols */
unsigned int nameoff; /* If iterating in core kernel symbols. */
char type;
char name[KSYM_NAME_LEN];
char module_name[MODULE_NAME_LEN];
@@ -404,7 +425,7 @@ static int update_iter(struct kallsym_iter *iter, loff_t pos)
iter->pos = pos;
return get_ksymbol_mod(iter);
}
/* If we're not on the desired position, reset to new position. */
if (pos != iter->pos)
reset_iter(iter, pos);
@@ -439,23 +460,25 @@ static int s_show(struct seq_file *m, void *p)
{
struct kallsym_iter *iter = m->private;
/* Some debugging symbols have no name. Ignore them. */
/* Some debugging symbols have no name. Ignore them. */
if (!iter->name[0])
return 0;
if (iter->module_name[0]) {
char type;
/* Label it "global" if it is exported,
* "local" if not exported. */
/*
* Label it "global" if it is exported,
* "local" if not exported.
*/
type = iter->exported ? toupper(iter->type) :
tolower(iter->type);
seq_printf(m, "%0*lx %c %s\t[%s]\n",
(int)(2*sizeof(void*)),
(int)(2 * sizeof(void *)),
iter->value, type, iter->name, iter->module_name);
} else
seq_printf(m, "%0*lx %c %s\n",
(int)(2*sizeof(void*)),
(int)(2 * sizeof(void *)),
iter->value, iter->type, iter->name);
return 0;
}
@@ -469,9 +492,11 @@ static const struct seq_operations kallsyms_op = {
static int kallsyms_open(struct inode *inode, struct file *file)
{
/* We keep iterator in m->private, since normal case is to
/*
* We keep iterator in m->private, since normal case is to
* s_start from where we left off, so we avoid doing
* using get_symbol_offset for every symbol */
* using get_symbol_offset for every symbol.
*/
struct kallsym_iter *iter;
int ret;
@@ -500,7 +525,4 @@ static int __init kallsyms_init(void)
proc_create("kallsyms", 0444, NULL, &kallsyms_operations);
return 0;
}
__initcall(kallsyms_init);
EXPORT_SYMBOL(__print_symbol);
EXPORT_SYMBOL_GPL(sprint_symbol);
device_initcall(kallsyms_init);

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();

View File

@@ -2455,6 +2455,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
mutex_lock(&module_mutex);
/* Drop initial reference. */
module_put(mod);
trim_init_extable(mod);
module_free(mod, mod->module_init);
mod->module_init = NULL;
mod->init_size = 0;

View File

@@ -24,9 +24,6 @@
#include <linux/err.h>
#include <linux/slab.h>
/* We abuse the high bits of "perm" to record whether we kmalloc'ed. */
#define KPARAM_KMALLOCED 0x80000000
#if 0
#define DEBUGP printk
#else
@@ -220,13 +217,13 @@ int param_set_charp(const char *val, struct kernel_param *kp)
return -ENOSPC;
}
if (kp->perm & KPARAM_KMALLOCED)
if (kp->flags & KPARAM_KMALLOCED)
kfree(*(char **)kp->arg);
/* This is a hack. We can't need to strdup in early boot, and we
* don't need to; this mangled commandline is preserved. */
if (slab_is_available()) {
kp->perm |= KPARAM_KMALLOCED;
kp->flags |= KPARAM_KMALLOCED;
*(char **)kp->arg = kstrdup(val, GFP_KERNEL);
if (!kp->arg)
return -ENOMEM;
@@ -241,44 +238,63 @@ int param_get_charp(char *buffer, struct kernel_param *kp)
return sprintf(buffer, "%s", *((char **)kp->arg));
}
/* Actually could be a bool or an int, for historical reasons. */
int param_set_bool(const char *val, struct kernel_param *kp)
{
bool v;
/* No equals means "set"... */
if (!val) val = "1";
/* One of =[yYnN01] */
switch (val[0]) {
case 'y': case 'Y': case '1':
*(int *)kp->arg = 1;
return 0;
v = true;
break;
case 'n': case 'N': case '0':
*(int *)kp->arg = 0;
return 0;
v = false;
break;
default:
return -EINVAL;
}
return -EINVAL;
if (kp->flags & KPARAM_ISBOOL)
*(bool *)kp->arg = v;
else
*(int *)kp->arg = v;
return 0;
}
int param_get_bool(char *buffer, struct kernel_param *kp)
{
bool val;
if (kp->flags & KPARAM_ISBOOL)
val = *(bool *)kp->arg;
else
val = *(int *)kp->arg;
/* Y and N chosen as being relatively non-coder friendly */
return sprintf(buffer, "%c", (*(int *)kp->arg) ? 'Y' : 'N');
return sprintf(buffer, "%c", val ? 'Y' : 'N');
}
/* This one must be bool. */
int param_set_invbool(const char *val, struct kernel_param *kp)
{
int boolval, ret;
int ret;
bool boolval;
struct kernel_param dummy;
dummy.arg = &boolval;
dummy.flags = KPARAM_ISBOOL;
ret = param_set_bool(val, &dummy);
if (ret == 0)
*(int *)kp->arg = !boolval;
*(bool *)kp->arg = !boolval;
return ret;
}
int param_get_invbool(char *buffer, struct kernel_param *kp)
{
return sprintf(buffer, "%c", (*(int *)kp->arg) ? 'N' : 'Y');
return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y');
}
/* We break the rule and mangle the string. */
@@ -591,7 +607,7 @@ void destroy_params(const struct kernel_param *params, unsigned num)
unsigned int i;
for (i = 0; i < num; i++)
if (params[i].perm & KPARAM_KMALLOCED)
if (params[i].flags & KPARAM_KMALLOCED)
kfree(*(char **)params[i].arg);
}

View File

@@ -3570,12 +3570,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP))
goto done;
if (attr->type == PERF_TYPE_RAW) {
pmu = hw_perf_counter_init(counter);
goto done;
}
switch (attr->type) {
case PERF_TYPE_RAW:
case PERF_TYPE_HARDWARE:
case PERF_TYPE_HW_CACHE:
pmu = hw_perf_counter_init(counter);
@@ -3588,6 +3584,9 @@ perf_counter_alloc(struct perf_counter_attr *attr,
case PERF_TYPE_TRACEPOINT:
pmu = tp_perf_counter_init(counter);
break;
default:
break;
}
done:
err = 0;
@@ -3614,6 +3613,85 @@ done:
return counter;
}
static int perf_copy_attr(struct perf_counter_attr __user *uattr,
struct perf_counter_attr *attr)
{
int ret;
u32 size;
if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0))
return -EFAULT;
/*
* zero the full structure, so that a short copy will be nice.
*/
memset(attr, 0, sizeof(*attr));
ret = get_user(size, &uattr->size);
if (ret)
return ret;
if (size > PAGE_SIZE) /* silly large */
goto err_size;
if (!size) /* abi compat */
size = PERF_ATTR_SIZE_VER0;
if (size < PERF_ATTR_SIZE_VER0)
goto err_size;
/*
* If we're handed a bigger struct than we know of,
* ensure all the unknown bits are 0.
*/
if (size > sizeof(*attr)) {
unsigned long val;
unsigned long __user *addr;
unsigned long __user *end;
addr = PTR_ALIGN((void __user *)uattr + sizeof(*attr),
sizeof(unsigned long));
end = PTR_ALIGN((void __user *)uattr + size,
sizeof(unsigned long));
for (; addr < end; addr += sizeof(unsigned long)) {
ret = get_user(val, addr);
if (ret)
return ret;
if (val)
goto err_size;
}
}
ret = copy_from_user(attr, uattr, size);
if (ret)
return -EFAULT;
/*
* If the type exists, the corresponding creation will verify
* the attr->config.
*/
if (attr->type >= PERF_TYPE_MAX)
return -EINVAL;
if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3)
return -EINVAL;
if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
return -EINVAL;
if (attr->read_format & ~(PERF_FORMAT_MAX-1))
return -EINVAL;
out:
return ret;
err_size:
put_user(sizeof(*attr), &uattr->size);
ret = -E2BIG;
goto out;
}
/**
* sys_perf_counter_open - open a performance counter, associate it to a task/cpu
*
@@ -3623,7 +3701,7 @@ done:
* @group_fd: group leader counter fd
*/
SYSCALL_DEFINE5(perf_counter_open,
const struct perf_counter_attr __user *, attr_uptr,
struct perf_counter_attr __user *, attr_uptr,
pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
{
struct perf_counter *counter, *group_leader;
@@ -3639,8 +3717,9 @@ SYSCALL_DEFINE5(perf_counter_open,
if (flags)
return -EINVAL;
if (copy_from_user(&attr, attr_uptr, sizeof(attr)) != 0)
return -EFAULT;
ret = perf_copy_attr(attr_uptr, &attr);
if (ret)
return ret;
if (!attr.exclude_kernel) {
if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))

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

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

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:

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);
}

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 */

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; }

View File

@@ -34,7 +34,7 @@ static struct sysrq_key_op sysrq_poweroff_op = {
.handler = handle_poweroff,
.help_msg = "powerOff",
.action_msg = "Power Off",
.enable_mask = SYSRQ_ENABLE_BOOT,
.enable_mask = SYSRQ_ENABLE_BOOT,
};
static int pm_sysrq_init(void)

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);

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);
}

View File

@@ -902,7 +902,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
* Returns:
* 0 on success
* -EINTR when interrupted by a signal
* -ETIMEOUT when the timeout expired
* -ETIMEDOUT when the timeout expired
* -EDEADLK when the lock would deadlock (when deadlock detection is on)
*/
int

View File

@@ -2192,6 +2192,7 @@ void kick_process(struct task_struct *p)
smp_send_reschedule(cpu);
preempt_enable();
}
EXPORT_SYMBOL_GPL(kick_process);
/*
* Return a low guess at the load of a migration-source cpu weighted

View File

@@ -757,6 +757,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
wake_up_idle_cpu(cpu);
spin_unlock_irqrestore(&base->lock, flags);
}
EXPORT_SYMBOL_GPL(add_timer_on);
/**
* del_timer - deactive a timer.