[RFC PATCH V5 4/4] cpuidle: Single/Global registration of idle states

From: Trinabh Gupta
Date: Mon Jun 06 2011 - 09:40:17 EST

This patch makes the cpuidle_states structure global (single copy)
instead of per-cpu. The statistics needed on per-cpu basis
by the governor are kept per-cpu. This simplifies the cpuidle
subsystem as state registration is done by single cpu only.
Having single copy of cpuidle_states saves memory. Rare case
of asymmetric C-states can be handled within the cpuidle driver
and architectures such as POWER do not have asymmetric C-states.

ToDo:
1. Handle the case when idle states may change at run time
and acpi_processor_cst_has_changed() routine is called in a
better way than the current solution in this patch.
Ref: https://lkml.org/lkml/2011/4/25/83

Signed-off-by: Trinabh Gupta <trinabh@xxxxxxxxxxxxxxxxxx>
---

arch/arm/mach-at91/cpuidle.c | 31 +++--
arch/arm/mach-davinci/cpuidle.c | 39 ++++---
arch/arm/mach-exynos4/cpuidle.c | 23 ++--
arch/arm/mach-kirkwood/cpuidle.c | 30 +++--
arch/arm/mach-omap2/cpuidle34xx.c | 73 ++++++++----
arch/sh/kernel/cpu/shmobile/cpuidle.c | 18 ++-
drivers/acpi/processor_driver.c | 20 +--
drivers/acpi/processor_idle.c | 193 +++++++++++++++++++++++++++++----
drivers/cpuidle/cpuidle.c | 45 ++------
drivers/cpuidle/driver.c | 25 ++++
drivers/cpuidle/governors/ladder.c | 26 +++-
drivers/cpuidle/governors/menu.c | 20 ++-
drivers/cpuidle/sysfs.c | 3 -
drivers/idle/intel_idle.c | 80 ++++++++++----
include/acpi/processor.h | 1
include/linux/cpuidle.h | 19 ++-
16 files changed, 439 insertions(+), 207 deletions(-)

diff --git a/arch/arm/mach-at91/cpuidle.c b/arch/arm/mach-at91/cpuidle.c
index 4696a0d..93178f6 100644
--- a/arch/arm/mach-at91/cpuidle.c
+++ b/arch/arm/mach-at91/cpuidle.c
@@ -33,6 +33,7 @@ static struct cpuidle_driver at91_idle_driver = {

/* Actual code that puts the SoC in different idle states */
static int at91_enter_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index)
{
struct timeval before, after;
@@ -64,27 +65,29 @@ static int at91_enter_idle(struct cpuidle_device *dev,
static int at91_init_cpuidle(void)
{
struct cpuidle_device *device;
-
- cpuidle_register_driver(&at91_idle_driver);
+ struct cpuidle_driver *driver = &at91_idle_driver;

device = &per_cpu(at91_cpuidle_device, smp_processor_id());
device->state_count = AT91_MAX_STATES;
+ driver->state_count = AT91_MAX_STATES;

/* Wait for interrupt state */
- device->states[0].enter = at91_enter_idle;
- device->states[0].exit_latency = 1;
- device->states[0].target_residency = 10000;
- device->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
- strcpy(device->states[0].name, "WFI");
- strcpy(device->states[0].desc, "Wait for interrupt");
+ driver->states[0].enter = at91_enter_idle;
+ driver->states[0].exit_latency = 1;
+ driver->states[0].target_residency = 10000;
+ driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
+ strcpy(driver->states[0].name, "WFI");
+ strcpy(driver->states[0].desc, "Wait for interrupt");

/* Wait for interrupt and RAM self refresh state */
- device->states[1].enter = at91_enter_idle;
- device->states[1].exit_latency = 10;
- device->states[1].target_residency = 10000;
- device->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
- strcpy(device->states[1].name, "RAM_SR");
- strcpy(device->states[1].desc, "WFI and RAM Self Refresh");
+ driver->states[1].enter = at91_enter_idle;
+ driver->states[1].exit_latency = 10;
+ driver->states[1].target_residency = 10000;
+ driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
+ strcpy(driver->states[1].name, "RAM_SR");
+ strcpy(driver->states[1].desc, "WFI and RAM Self Refresh");
+
+ cpuidle_register_driver(&at91_idle_driver);

if (cpuidle_register_device(device)) {
printk(KERN_ERR "at91_init_cpuidle: Failed registering\n");
diff --git a/arch/arm/mach-davinci/cpuidle.c b/arch/arm/mach-davinci/cpuidle.c
index f2d2f34..dbeeccd 100644
--- a/arch/arm/mach-davinci/cpuidle.c
+++ b/arch/arm/mach-davinci/cpuidle.c
@@ -78,6 +78,7 @@ static struct davinci_ops davinci_states[DAVINCI_CPUIDLE_MAX_STATES] = {

/* Actual code that puts the SoC in different idle states */
static int davinci_enter_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index)
{
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
@@ -109,6 +110,7 @@ static int __init davinci_cpuidle_probe(struct platform_device *pdev)
{
int ret;
struct cpuidle_device *device;
+ struct cpuidle_driver *driver = &davinci_idle_driver;
struct davinci_cpuidle_config *pdata = pdev->dev.platform_data;

device = &per_cpu(davinci_cpuidle_device, smp_processor_id());
@@ -120,32 +122,33 @@ static int __init davinci_cpuidle_probe(struct platform_device *pdev)

ddr2_reg_base = pdata->ddr2_ctlr_base;

- ret = cpuidle_register_driver(&davinci_idle_driver);
- if (ret) {
- dev_err(&pdev->dev, "failed to register driver\n");
- return ret;
- }
-
/* Wait for interrupt state */
- device->states[0].enter = davinci_enter_idle;
- device->states[0].exit_latency = 1;
- device->states[0].target_residency = 10000;
- device->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
- strcpy(device->states[0].name, "WFI");
- strcpy(device->states[0].desc, "Wait for interrupt");
+ driver->states[0].enter = davinci_enter_idle;
+ driver->states[0].exit_latency = 1;
+ driver->states[0].target_residency = 10000;
+ driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
+ strcpy(driver->states[0].name, "WFI");
+ strcpy(driver->states[0].desc, "Wait for interrupt");

/* Wait for interrupt and DDR self refresh state */
- device->states[1].enter = davinci_enter_idle;
- device->states[1].exit_latency = 10;
- device->states[1].target_residency = 10000;
- device->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
- strcpy(device->states[1].name, "DDR SR");
- strcpy(device->states[1].desc, "WFI and DDR Self Refresh");
+ driver->states[1].enter = davinci_enter_idle;
+ driver->states[1].exit_latency = 10;
+ driver->states[1].target_residency = 10000;
+ driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
+ strcpy(driver->states[1].name, "DDR SR");
+ strcpy(driver->states[1].desc, "WFI and DDR Self Refresh");
if (pdata->ddr2_pdown)
davinci_states[1].flags |= DAVINCI_CPUIDLE_FLAGS_DDR2_PWDN;
cpuidle_set_statedata(&device->states_usage[1], &davinci_states[1]);

device->state_count = DAVINCI_CPUIDLE_MAX_STATES;
+ driver->state_count = DAVINCI_CPUIDLE_MAX_STATES;
+
+ ret = cpuidle_register_driver(&davinci_idle_driver);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to register driver\n");
+ return ret;
+ }

ret = cpuidle_register_device(device);
if (ret) {
diff --git a/arch/arm/mach-exynos4/cpuidle.c b/arch/arm/mach-exynos4/cpuidle.c
index ea026e7..35f6502 100644
--- a/arch/arm/mach-exynos4/cpuidle.c
+++ b/arch/arm/mach-exynos4/cpuidle.c
@@ -16,6 +16,7 @@
#include <asm/proc-fns.h>

static int exynos4_enter_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index);

static struct cpuidle_state exynos4_cpuidle_set[] = {
@@ -37,6 +38,7 @@ static struct cpuidle_driver exynos4_idle_driver = {
};

static int exynos4_enter_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index)
{
struct timeval before, after;
@@ -60,22 +62,23 @@ static int __init exynos4_init_cpuidle(void)
{
int i, max_cpuidle_state, cpu_id;
struct cpuidle_device *device;
-
+ struct cpuidle_driver *drv = &exynos4_idle_driver;
+
+ /* Setup cpuidle driver */
+ drv->state_count = (sizeof(exynos4_cpuidle_set) /
+ sizeof(struct cpuidle_state));
+ max_cpuidle_state = drv->state_count;
+ for (i = 0; i < max_cpuidle_state; i++) {
+ memcpy(&drv->states[i], &exynos4_cpuidle_set[i],
+ sizeof(struct cpuidle_state));
+ }
cpuidle_register_driver(&exynos4_idle_driver);

for_each_cpu(cpu_id, cpu_online_mask) {
device = &per_cpu(exynos4_cpuidle_device, cpu_id);
device->cpu = cpu_id;

- device->state_count = (sizeof(exynos4_cpuidle_set) /
- sizeof(struct cpuidle_state));
-
- max_cpuidle_state = device->state_count;
-
- for (i = 0; i < max_cpuidle_state; i++) {
- memcpy(&device->states[i], &exynos4_cpuidle_set[i],
- sizeof(struct cpuidle_state));
- }
+ device->state_count = drv->state_count;

if (cpuidle_register_device(device)) {
printk(KERN_ERR "CPUidle register device failed\n,");
diff --git a/arch/arm/mach-kirkwood/cpuidle.c b/arch/arm/mach-kirkwood/cpuidle.c
index 358dd80..ffd690d 100644
--- a/arch/arm/mach-kirkwood/cpuidle.c
+++ b/arch/arm/mach-kirkwood/cpuidle.c
@@ -32,6 +32,7 @@ static DEFINE_PER_CPU(struct cpuidle_device, kirkwood_cpuidle_device);

/* Actual code that puts the SoC in different idle states */
static int kirkwood_enter_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index)
{
struct timeval before, after;
@@ -68,28 +69,29 @@ static int kirkwood_enter_idle(struct cpuidle_device *dev,
static int kirkwood_init_cpuidle(void)
{
struct cpuidle_device *device;
-
- cpuidle_register_driver(&kirkwood_idle_driver);
+ struct cpuidle_driver *driver = &kirkwood_idle_driver;

device = &per_cpu(kirkwood_cpuidle_device, smp_processor_id());
device->state_count = KIRKWOOD_MAX_STATES;
+ driver->state_count = KIRKWOOD_MAX_STATES;

/* Wait for interrupt state */
- device->states[0].enter = kirkwood_enter_idle;
- device->states[0].exit_latency = 1;
- device->states[0].target_residency = 10000;
- device->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
- strcpy(device->states[0].name, "WFI");
- strcpy(device->states[0].desc, "Wait for interrupt");
+ driver->states[0].enter = kirkwood_enter_idle;
+ driver->states[0].exit_latency = 1;
+ driver->states[0].target_residency = 10000;
+ driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
+ strcpy(driver->states[0].name, "WFI");
+ strcpy(driver->states[0].desc, "Wait for interrupt");

/* Wait for interrupt and DDR self refresh state */
- device->states[1].enter = kirkwood_enter_idle;
- device->states[1].exit_latency = 10;
- device->states[1].target_residency = 10000;
- device->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
- strcpy(device->states[1].name, "DDR SR");
- strcpy(device->states[1].desc, "WFI and DDR Self Refresh");
+ driver->states[1].enter = kirkwood_enter_idle;
+ driver->states[1].exit_latency = 10;
+ driver->states[1].target_residency = 10000;
+ driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
+ strcpy(driver->states[1].name, "DDR SR");
+ strcpy(driver->states[1].desc, "WFI and DDR Self Refresh");

+ cpuidle_register_driver(&kirkwood_idle_driver);
if (cpuidle_register_device(device)) {
printk(KERN_ERR "kirkwood_init_cpuidle: Failed registering\n");
return -EIO;
diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c
index 6bbddbc..2732253 100644
--- a/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/arch/arm/mach-omap2/cpuidle34xx.c
@@ -88,12 +88,14 @@ static int _cpuidle_deny_idle(struct powerdomain *pwrdm,
/**
* omap3_enter_idle - Programs OMAP3 to enter the specified state
* @dev: cpuidle device
+ * @drv: cpuidle driver
* @index: the index of state to be entered
*
* Called from the CPUidle framework to program the device to the
* specified target state selected by the governor.
*/
static int omap3_enter_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index)
{
struct omap3_idle_statedata *cx =
@@ -147,6 +149,7 @@ return_sleep_time:
/**
* next_valid_state - Find next valid C-state
* @dev: cpuidle device
+ * @drv: cpuidle driver
* @index: Index of currently selected c-state
*
* If the state corresponding to index is valid, index is returned back
@@ -157,10 +160,11 @@ return_sleep_time:
* if it satisfies the enable_off_mode condition.
*/
static int next_valid_state(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index)
{
struct cpuidle_state_usage *curr_usage = &dev->states_usage[index];
- struct cpuidle_state *curr = &dev->states[index];
+ struct cpuidle_state *curr = &drv->states[index];
struct omap3_idle_statedata *cx = cpuidle_get_statedata(curr_usage);
u32 mpu_deepest_state = PWRDM_POWER_RET;
u32 core_deepest_state = PWRDM_POWER_RET;
@@ -187,7 +191,7 @@ static int next_valid_state(struct cpuidle_device *dev,

/* Reach the current state starting at highest C-state */
for (; idx >= 0; idx--) {
- if (&dev->states[idx] == curr) {
+ if (&drv->states[idx] == curr) {
next_index = idx;
break;
}
@@ -222,12 +226,14 @@ static int next_valid_state(struct cpuidle_device *dev,
/**
* omap3_enter_idle_bm - Checks for any bus activity
* @dev: cpuidle device
+ * @drv: cpuidle driver
* @index: array index of target state to be programmed
*
* This function checks for any pending activity and then programs
* the device to the specified or a safer state.
*/
static int omap3_enter_idle_bm(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index)
{
int new_state_idx;
@@ -236,7 +242,7 @@ static int omap3_enter_idle_bm(struct cpuidle_device *dev,
int ret;

if (!omap3_can_sleep()) {
- new_state_idx = dev->safe_state_index;
+ new_state_idx = drv->safe_state_index;
goto select_state;
}

@@ -246,7 +252,7 @@ static int omap3_enter_idle_bm(struct cpuidle_device *dev,
*/
cam_state = pwrdm_read_pwrst(cam_pd);
if (cam_state == PWRDM_POWER_ON) {
- new_state_idx = dev->safe_state_index;
+ new_state_idx = drv->safe_state_index;
goto select_state;
}

@@ -273,10 +279,10 @@ static int omap3_enter_idle_bm(struct cpuidle_device *dev,
if (per_next_state != per_saved_state)
pwrdm_set_next_pwrst(per_pd, per_next_state);

- new_state_idx = next_valid_state(dev, index);
+ new_state_idx = next_valid_state(dev, drv, index);

select_state:
- ret = omap3_enter_idle(dev, new_state_idx);
+ ret = omap3_enter_idle(dev, drv, new_state_idx);

/* Restore original PER state if it was modified */
if (per_next_state != per_saved_state)
@@ -309,22 +315,30 @@ struct cpuidle_driver omap3_idle_driver = {
.owner = THIS_MODULE,
};

-/* Helper to fill the C-state common data and register the driver_data */
-static inline struct omap3_idle_statedata *_fill_cstate(
- struct cpuidle_device *dev,
+/* Helper to fill the C-state common data*/
+static inline void _fill_cstate(struct cpuidle_driver *drv,
int idx, const char *descr)
{
- struct omap3_idle_statedata *cx = &omap3_idle_data[idx];
- struct cpuidle_state *state = &dev->states[idx];
- struct cpuidle_state_usage *state_usage = &dev->states_usage[idx];
+ struct cpuidle_state *state = &drv->states[idx];

state->exit_latency = cpuidle_params_table[idx].exit_latency;
state->target_residency = cpuidle_params_table[idx].target_residency;
state->flags = CPUIDLE_FLAG_TIME_VALID;
state->enter = omap3_enter_idle_bm;
- cx->valid = cpuidle_params_table[idx].valid;
sprintf(state->name, "C%d", idx + 1);
strncpy(state->desc, descr, CPUIDLE_DESC_LEN);
+
+}
+
+/* Helper to register the driver_data */
+static inline struct omap3_idle_statedata *_fill_cstate_usage(
+ struct cpuidle_device *dev,
+ int idx)
+{
+ struct omap3_idle_statedata *cx = &omap3_idle_data[idx];
+ struct cpuidle_state_usage *state_usage = &dev->states_usage[idx];
+
+ cx->valid = cpuidle_params_table[idx].valid;
cpuidle_set_statedata(state_usage, cx);

return cx;
@@ -339,6 +353,7 @@ static inline struct omap3_idle_statedata *_fill_cstate(
int __init omap3_idle_init(void)
{
struct cpuidle_device *dev;
+ struct cpuidle_driver *drv = &omap3_idle_driver;
struct omap3_idle_statedata *cx;

mpu_pd = pwrdm_lookup("mpu_pwrdm");
@@ -346,45 +361,52 @@ int __init omap3_idle_init(void)
per_pd = pwrdm_lookup("per_pwrdm");
cam_pd = pwrdm_lookup("cam_pwrdm");

- cpuidle_register_driver(&omap3_idle_driver);
+
+ drv->safe_state_index = -1;
dev = &per_cpu(omap3_idle_dev, smp_processor_id());
- dev->safe_state_index = -1;

/* C1 . MPU WFI + Core active */
- cx = _fill_cstate(dev, 0, "MPU ON + CORE ON");
- (&dev->states[0])->enter = omap3_enter_idle;
- dev->safe_state_index = 0;
+ _fill_cstate(drv, 0, "MPU ON + CORE ON");
+ (&drv->states[0])->enter = omap3_enter_idle;
+ drv->safe_state_index = 0;
+ cx = _fill_cstate_usage(dev, 0);
cx->valid = 1; /* C1 is always valid */
cx->mpu_state = PWRDM_POWER_ON;
cx->core_state = PWRDM_POWER_ON;

/* C2 . MPU WFI + Core inactive */
- cx = _fill_cstate(dev, 1, "MPU ON + CORE ON");
+ _fill_cstate(drv, 1, "MPU ON + CORE ON");
+ cx = _fill_cstate_usage(dev, 1);
cx->mpu_state = PWRDM_POWER_ON;
cx->core_state = PWRDM_POWER_ON;

/* C3 . MPU CSWR + Core inactive */
- cx = _fill_cstate(dev, 2, "MPU RET + CORE ON");
+ _fill_cstate(drv, 2, "MPU RET + CORE ON");
+ cx = _fill_cstate_usage(dev, 2);
cx->mpu_state = PWRDM_POWER_RET;
cx->core_state = PWRDM_POWER_ON;

/* C4 . MPU OFF + Core inactive */
- cx = _fill_cstate(dev, 3, "MPU OFF + CORE ON");
+ _fill_cstate(drv, 3, "MPU OFF + CORE ON");
+ cx = _fill_cstate_usage(dev, 3);
cx->mpu_state = PWRDM_POWER_OFF;
cx->core_state = PWRDM_POWER_ON;

/* C5 . MPU RET + Core RET */
- cx = _fill_cstate(dev, 4, "MPU RET + CORE RET");
+ _fill_cstate(drv, 4, "MPU RET + CORE RET");
+ cx = _fill_cstate_usage(dev, 4);
cx->mpu_state = PWRDM_POWER_RET;
cx->core_state = PWRDM_POWER_RET;

/* C6 . MPU OFF + Core RET */
- cx = _fill_cstate(dev, 5, "MPU OFF + CORE RET");
+ _fill_cstate(drv, 5, "MPU OFF + CORE RET");
+ cx = _fill_cstate_usage(dev, 5);
cx->mpu_state = PWRDM_POWER_OFF;
cx->core_state = PWRDM_POWER_RET;

/* C7 . MPU OFF + Core OFF */
- cx = _fill_cstate(dev, 6, "MPU OFF + CORE OFF");
+ _fill_cstate(drv, 6, "MPU OFF + CORE OFF");
+ cx = _fill_cstate_usage(dev, 6);
/*
* Erratum i583: implementation for ES rev < Es1.2 on 3630. We cannot
* enable OFF mode in a stable form for previous revisions.
@@ -398,6 +420,9 @@ int __init omap3_idle_init(void)
cx->mpu_state = PWRDM_POWER_OFF;
cx->core_state = PWRDM_POWER_OFF;

+ drv->state_count = OMAP3_NUM_STATES;
+ cpuidle_register_driver(&omap3_idle_driver);
+
dev->state_count = OMAP3_NUM_STATES;
if (cpuidle_register_device(dev)) {
printk(KERN_ERR "%s: CPUidle register device failed\n",
diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c
index 7be50d4..ad1012a 100644
--- a/arch/sh/kernel/cpu/shmobile/cpuidle.c
+++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c
@@ -25,6 +25,7 @@ static unsigned long cpuidle_mode[] = {
};

static int cpuidle_sleep_enter(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index)
{
unsigned long allowed_mode = arch_hwblk_sleep_mode();
@@ -64,19 +65,19 @@ static struct cpuidle_driver cpuidle_driver = {
void sh_mobile_setup_cpuidle(void)
{
struct cpuidle_device *dev = &cpuidle_dev;
+ struct cpuidle_driver *drv = &cpuidle_driver;
struct cpuidle_state *state;
int i;

- cpuidle_register_driver(&cpuidle_driver);

for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
- dev->states[i].name[0] = '\0';
- dev->states[i].desc[0] = '\0';
+ drv->states[i].name[0] = '\0';
+ drv->states[i].desc[0] = '\0';
}

i = CPUIDLE_DRIVER_STATE_START;

- state = &dev->states[i++];
+ state = &drv->states[i++];
snprintf(state->name, CPUIDLE_NAME_LEN, "C1");
strncpy(state->desc, "SuperH Sleep Mode", CPUIDLE_DESC_LEN);
state->exit_latency = 1;
@@ -86,10 +87,10 @@ void sh_mobile_setup_cpuidle(void)
state->flags |= CPUIDLE_FLAG_TIME_VALID;
state->enter = cpuidle_sleep_enter;

- dev->safe_state_index = i-1;
+ drv->safe_state_index = i-1;

if (sh_mobile_sleep_supported & SUSP_SH_SF) {
- state = &dev->states[i++];
+ state = &drv->states[i++];
snprintf(state->name, CPUIDLE_NAME_LEN, "C2");
strncpy(state->desc, "SuperH Sleep Mode [SF]",
CPUIDLE_DESC_LEN);
@@ -102,7 +103,7 @@ void sh_mobile_setup_cpuidle(void)
}

if (sh_mobile_sleep_supported & SUSP_SH_STANDBY) {
- state = &dev->states[i++];
+ state = &drv->states[i++];
snprintf(state->name, CPUIDLE_NAME_LEN, "C3");
strncpy(state->desc, "SuperH Mobile Standby Mode [SF]",
CPUIDLE_DESC_LEN);
@@ -114,7 +115,10 @@ void sh_mobile_setup_cpuidle(void)
state->enter = cpuidle_sleep_enter;
}

+ drv->state_count = i;
dev->state_count = i;

+ cpuidle_register_driver(&cpuidle_driver);
+
cpuidle_register_device(dev);
}
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index a4e0f1b..9d7bc9f 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -426,7 +426,7 @@ static int acpi_cpu_soft_notify(struct notifier_block *nfb,

if (action == CPU_ONLINE && pr) {
acpi_processor_ppc_has_changed(pr, 0);
- acpi_processor_cst_has_changed(pr);
+ acpi_processor_hotplug(pr);
acpi_processor_reevaluate_tstate(pr, action);
acpi_processor_tstate_has_changed(pr);
}
@@ -503,8 +503,7 @@ static int __cpuinit acpi_processor_add(struct acpi_device *device)
acpi_processor_get_throttling_info(pr);
acpi_processor_get_limit_info(pr);

-
- if (cpuidle_get_driver() == &acpi_idle_driver)
+ if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver)
acpi_processor_power_init(pr, device);

pr->cdev = thermal_cooling_device_register("Processor", device,
@@ -800,17 +799,9 @@ static int __init acpi_processor_init(void)

memset(&errata, 0, sizeof(errata));

- if (!cpuidle_register_driver(&acpi_idle_driver)) {
- printk(KERN_DEBUG "ACPI: %s registered with cpuidle\n",
- acpi_idle_driver.name);
- } else {
- printk(KERN_DEBUG "ACPI: acpi_idle yielding to %s\n",
- cpuidle_get_driver()->name);
- }
-
result = acpi_bus_register_driver(&acpi_processor_driver);
if (result < 0)
- goto out_cpuidle;
+ return result;

acpi_processor_install_hotplug_notify();

@@ -821,11 +812,6 @@ static int __init acpi_processor_init(void)
acpi_processor_throttling_init();

return 0;
-
-out_cpuidle:
- cpuidle_unregister_driver(&acpi_idle_driver);
-
- return result;
}

static void __exit acpi_processor_exit(void)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index b98c752..7a31d87 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -741,11 +741,13 @@ static inline void acpi_idle_do_entry(struct acpi_processor_cx *cx)
/**
* acpi_idle_enter_c1 - enters an ACPI C1 state-type
* @dev: the target CPU
+ * @drv: cpuidle driver containing cpuidle state info
* @index: index of target state
*
* This is equivalent to the HALT instruction.
*/
-static int acpi_idle_enter_c1(struct cpuidle_device *dev, int index)
+static int acpi_idle_enter_c1(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
{
ktime_t kt1, kt2;
s64 idle_time;
@@ -787,9 +789,11 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev, int index)
/**
* acpi_idle_enter_simple - enters an ACPI state without BM handling
* @dev: the target CPU
+ * @drv: cpuidle driver with cpuidle state information
* @index: the index of suggested state
*/
-static int acpi_idle_enter_simple(struct cpuidle_device *dev, int index)
+static int acpi_idle_enter_simple(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
{
struct acpi_processor *pr;
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
@@ -869,11 +873,13 @@ static DEFINE_SPINLOCK(c3_lock);
/**
* acpi_idle_enter_bm - enters C3 with proper BM handling
* @dev: the target CPU
+ * @drv: cpuidle driver containing state data
* @index: the index of suggested state
*
* If BM is detected, the deepest non-C3 idle state is entered instead.
*/
-static int acpi_idle_enter_bm(struct cpuidle_device *dev, int index)
+static int acpi_idle_enter_bm(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
{
struct acpi_processor *pr;
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
@@ -896,9 +902,9 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, int index)
}

if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
- if (dev->safe_state_index >= 0) {
- return dev->states[dev->safe_state_index].enter(dev,
- dev->safe_state_index);
+ if (drv->safe_state_index >= 0) {
+ return drv->states[drv->safe_state_index].enter(dev,
+ drv, drv->safe_state_index);
} else {
local_irq_disable();
acpi_safe_halt();
@@ -993,14 +999,15 @@ struct cpuidle_driver acpi_idle_driver = {
};

/**
- * acpi_processor_setup_cpuidle - prepares and configures CPUIDLE
+ * acpi_processor_setup_cpuidle_cx - prepares and configures CPUIDLE
+ * device i.e. per-cpu data
+ *
* @pr: the ACPI processor
*/
-static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
+static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr)
{
int i, count = CPUIDLE_DRIVER_STATE_START;
struct acpi_processor_cx *cx;
- struct cpuidle_state *state;
struct cpuidle_state_usage *state_usage;
struct cpuidle_device *dev = &pr->power.dev;

@@ -1012,18 +1019,12 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
}

dev->cpu = pr->id;
- dev->safe_state_index = -1;
- for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
- dev->states[i].name[0] = '\0';
- dev->states[i].desc[0] = '\0';
- }

if (max_cstate == 0)
max_cstate = 1;

for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) {
cx = &pr->power.states[i];
- state = &dev->states[count];
state_usage = &dev->states_usage[count];

if (!cx->valid)
@@ -1035,8 +1036,65 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
!(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
continue;
#endif
+
cpuidle_set_statedata(state_usage, cx);

+ count++;
+ if (count == CPUIDLE_STATE_MAX)
+ break;
+ }
+
+ dev->state_count = count;
+
+ if (!count)
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * acpi_processor_setup_cpuidle states- prepares and configures cpuidle
+ * global state data i.e. idle routines
+ *
+ * @pr: the ACPI processor
+ */
+static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
+{
+ int i, count = CPUIDLE_DRIVER_STATE_START;
+ struct acpi_processor_cx *cx;
+ struct cpuidle_state *state;
+ struct cpuidle_driver *drv = &acpi_idle_driver;
+
+ if (!pr->flags.power_setup_done)
+ return -EINVAL;
+
+ if (pr->flags.power == 0) {
+ return -EINVAL;
+ }
+
+ drv->safe_state_index = -1;
+ for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
+ drv->states[i].name[0] = '\0';
+ drv->states[i].desc[0] = '\0';
+ }
+
+ if (max_cstate == 0)
+ max_cstate = 1;
+
+ for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) {
+ cx = &pr->power.states[i];
+
+ if (!cx->valid)
+ continue;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) &&
+ !pr->flags.has_cst &&
+ !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
+ continue;
+#endif
+
+ state = &drv->states[count];
snprintf(state->name, CPUIDLE_NAME_LEN, "C%d", i);
strncpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
state->exit_latency = cx->latency;
@@ -1049,13 +1107,13 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
state->flags |= CPUIDLE_FLAG_TIME_VALID;

state->enter = acpi_idle_enter_c1;
- dev->safe_state_index = count;
+ drv->safe_state_index = count;
break;

case ACPI_STATE_C2:
state->flags |= CPUIDLE_FLAG_TIME_VALID;
state->enter = acpi_idle_enter_simple;
- dev->safe_state_index = count;
+ drv->safe_state_index = count;
break;

case ACPI_STATE_C3:
@@ -1071,7 +1129,7 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
break;
}

- dev->state_count = count;
+ drv->state_count = count;

if (!count)
return -EINVAL;
@@ -1079,7 +1137,7 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
return 0;
}

-int acpi_processor_cst_has_changed(struct acpi_processor *pr)
+int acpi_processor_hotplug(struct acpi_processor *pr)
{
int ret = 0;

@@ -1100,7 +1158,7 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
cpuidle_disable_device(&pr->power.dev);
acpi_processor_get_power_info(pr);
if (pr->flags.power) {
- acpi_processor_setup_cpuidle(pr);
+ acpi_processor_setup_cpuidle_cx(pr);
ret = cpuidle_enable_device(&pr->power.dev);
}
cpuidle_resume_and_unlock();
@@ -1108,10 +1166,73 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
return ret;
}

+int acpi_processor_cst_has_changed(struct acpi_processor *pr)
+{
+ int cpu;
+ struct acpi_processor *_pr;
+
+ if (disabled_by_idle_boot_param())
+ return 0;
+
+ if (!pr)
+ return -EINVAL;
+
+ if (nocst) {
+ return -ENODEV;
+ }
+
+ if (!pr->flags.power_setup_done)
+ return -ENODEV;
+
+ /*
+ * FIXME: Design the ACPI notification to make it once per
+ * system instead of once per-cpu. This condition is a hack
+ * to make the code that updates C-States be called once.
+ */
+
+ if (smp_processor_id() == 0 &&
+ cpuidle_get_driver() == &acpi_idle_driver) {
+
+ cpuidle_pause_and_lock();
+ /* Protect against cpu-hotplug */
+ get_online_cpus();
+
+ /* Disable all cpuidle devices */
+ for_each_online_cpu(cpu) {
+ _pr = per_cpu(processors, cpu);
+ if (!_pr || !_pr->flags.power_setup_done)
+ continue;
+ cpuidle_disable_device(&_pr->power.dev);
+ }
+
+ /* Populate Updated C-state information */
+ acpi_processor_setup_cpuidle_states(pr);
+
+ /* Enable all cpuidle devices */
+ for_each_online_cpu(cpu) {
+ _pr = per_cpu(processors, cpu);
+ if (!_pr || !_pr->flags.power_setup_done)
+ continue;
+ acpi_processor_get_power_info(_pr);
+ if (_pr->flags.power) {
+ acpi_processor_setup_cpuidle_cx(_pr);
+ cpuidle_enable_device(&_pr->power.dev);
+ }
+ }
+ put_online_cpus();
+ cpuidle_resume_and_unlock();
+ }
+
+ return 0;
+}
+
+static int acpi_processor_registered;
+
int __cpuinit acpi_processor_power_init(struct acpi_processor *pr,
struct acpi_device *device)
{
acpi_status status = 0;
+ int retval;
static int first_run;

if (disabled_by_idle_boot_param())
@@ -1148,9 +1269,26 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr,
* platforms that only support C1.
*/
if (pr->flags.power) {
- acpi_processor_setup_cpuidle(pr);
- if (cpuidle_register_device(&pr->power.dev))
- return -EIO;
+ /* Register acpi_idle_driver if not already registered */
+ if (!acpi_processor_registered) {
+ acpi_processor_setup_cpuidle_states(pr);
+ retval = cpuidle_register_driver(&acpi_idle_driver);
+ if (retval)
+ return retval;
+ printk(KERN_DEBUG "ACPI: %s registered with cpuidle\n",
+ acpi_idle_driver.name);
+ }
+ /* Register per-cpu cpuidle_device. Cpuidle driver
+ * must already be registered before registering device
+ */
+ acpi_processor_setup_cpuidle_cx(pr);
+ retval = cpuidle_register_device(&pr->power.dev);
+ if (retval) {
+ if (acpi_processor_registered == 0)
+ cpuidle_unregister_driver(&acpi_idle_driver);
+ return retval;
+ }
+ acpi_processor_registered++;
}
return 0;
}
@@ -1161,8 +1299,13 @@ int acpi_processor_power_exit(struct acpi_processor *pr,
if (disabled_by_idle_boot_param())
return 0;

- cpuidle_unregister_device(&pr->power.dev);
- pr->flags.power_setup_done = 0;
+ if (pr->flags.power) {
+ cpuidle_unregister_device(&pr->power.dev);
+ acpi_processor_registered--;
+ if (acpi_processor_registered == 0)
+ cpuidle_unregister_driver(&acpi_idle_driver);
+ }

+ pr->flags.power_setup_done = 0;
return 0;
}
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 40352fb..406be83 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -50,6 +50,7 @@ static int __cpuidle_register_device(struct cpuidle_device *dev);
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+ struct cpuidle_driver *drv = cpuidle_get_driver();
struct cpuidle_state *target_state;
int next_state, entered_state;

@@ -76,18 +77,18 @@ static void cpuidle_idle_call(void)
#endif

/* ask the governor for the next state */
- next_state = cpuidle_curr_governor->select(dev);
+ next_state = cpuidle_curr_governor->select(drv, dev);
if (need_resched()) {
local_irq_enable();
return;
}

- target_state = &dev->states[next_state];
+ target_state = &drv->states[next_state];

trace_power_start(POWER_CSTATE, next_state, dev->cpu);
trace_cpu_idle(next_state, dev->cpu);

- entered_state = target_state->enter(dev, next_state);
+ entered_state = target_state->enter(dev, drv, next_state);

trace_power_end(dev->cpu);
trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
@@ -153,7 +154,8 @@ void cpuidle_resume_and_unlock(void)
EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock);

#ifdef CONFIG_ARCH_HAS_CPU_RELAX
-static int poll_idle(struct cpuidle_device *dev, int index)
+static int poll_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
{
ktime_t t1, t2;
s64 diff;
@@ -173,12 +175,9 @@ static int poll_idle(struct cpuidle_device *dev, int index)
return index;
}

-static void poll_idle_init(struct cpuidle_device *dev)
+static void poll_idle_init(struct cpuidle_driver *drv)
{
- struct cpuidle_state *state = &dev->states[0];
- struct cpuidle_state_usage *state_usage = &dev->states_usage[0];
-
- cpuidle_set_statedata(state_usage, NULL);
+ struct cpuidle_state *state = &drv->states[0];

snprintf(state->name, CPUIDLE_NAME_LEN, "POLL");
snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE");
@@ -189,7 +188,7 @@ static void poll_idle_init(struct cpuidle_device *dev)
state->enter = poll_idle;
}
#else
-static void poll_idle_init(struct cpuidle_device *dev) {}
+static void poll_idle_init(struct cpuidle_driver *drv) {}
#endif /* CONFIG_ARCH_HAS_CPU_RELAX */

/**
@@ -216,13 +215,13 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
return ret;
}

- poll_idle_init(dev);
+ poll_idle_init(cpuidle_get_driver());

if ((ret = cpuidle_add_state_sysfs(dev)))
return ret;

if (cpuidle_curr_governor->enable &&
- (ret = cpuidle_curr_governor->enable(dev)))
+ (ret = cpuidle_curr_governor->enable(cpuidle_get_driver(), dev)))
goto fail_sysfs;

for (i = 0; i < dev->state_count; i++) {
@@ -263,7 +262,7 @@ void cpuidle_disable_device(struct cpuidle_device *dev)
dev->enabled = 0;

if (cpuidle_curr_governor->disable)
- cpuidle_curr_governor->disable(dev);
+ cpuidle_curr_governor->disable(cpuidle_get_driver(), dev);

cpuidle_remove_state_sysfs(dev);
enabled_devices--;
@@ -291,26 +290,6 @@ static int __cpuidle_register_device(struct cpuidle_device *dev)

init_completion(&dev->kobj_unregister);

- /*
- * cpuidle driver should set the dev->power_specified bit
- * before registering the device if the driver provides
- * power_usage numbers.
- *
- * For those devices whose ->power_specified is not set,
- * we fill in power_usage with decreasing values as the
- * cpuidle code has an implicit assumption that state Cn
- * uses less power than C(n-1).
- *
- * With CONFIG_ARCH_HAS_CPU_RELAX, C0 is already assigned
- * an power value of -1. So we use -2, -3, etc, for other
- * c-states.
- */
- if (!dev->power_specified) {
- int i;
- for (i = CPUIDLE_DRIVER_STATE_START; i < dev->state_count; i++)
- dev->states[i].power_usage = -1 - i;
- }
-
per_cpu(cpuidle_devices, dev->cpu) = dev;
list_add(&dev->device_list, &cpuidle_detected_devices);
if ((ret = cpuidle_add_sysfs(sys_dev))) {
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index fd1601e..33e3189 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -17,6 +17,30 @@
static struct cpuidle_driver *cpuidle_curr_driver;
DEFINE_SPINLOCK(cpuidle_driver_lock);

+static void __cpuidle_register_driver(struct cpuidle_driver *drv)
+{
+ int i;
+ /*
+ * cpuidle driver should set the drv->power_specified bit
+ * before registering if the driver provides
+ * power_usage numbers.
+ *
+ * If power_specified is not set,
+ * we fill in power_usage with decreasing values as the
+ * cpuidle code has an implicit assumption that state Cn
+ * uses less power than C(n-1).
+ *
+ * With CONFIG_ARCH_HAS_CPU_RELAX, C0 is already assigned
+ * an power value of -1. So we use -2, -3, etc, for other
+ * c-states.
+ */
+ if (!drv->power_specified) {
+ for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++)
+ drv->states[i].power_usage = -1 - i;
+ }
+}
+
+
/**
* cpuidle_register_driver - registers a driver
* @drv: the driver
@@ -31,6 +55,7 @@ int cpuidle_register_driver(struct cpuidle_driver *drv)
spin_unlock(&cpuidle_driver_lock);
return -EBUSY;
}
+ __cpuidle_register_driver(drv);
cpuidle_curr_driver = drv;
spin_unlock(&cpuidle_driver_lock);

diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 6a686a7..988d813 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -60,9 +60,11 @@ static inline void ladder_do_selection(struct ladder_device *ldev,

/**
* ladder_select_state - selects the next state to enter
+ * @drv: cpuidle driver
* @dev: the CPU
*/
-static int ladder_select_state(struct cpuidle_device *dev)
+static int ladder_select_state(struct cpuidle_driver *drv,
+ struct cpuidle_device *dev)
{
struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
struct ladder_device_state *last_state;
@@ -77,15 +79,15 @@ static int ladder_select_state(struct cpuidle_device *dev)

last_state = &ldev->states[last_idx];

- if (dev->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID)
- last_residency = cpuidle_get_last_residency(dev) - dev->states[last_idx].exit_latency;
+ if (drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID)
+ last_residency = cpuidle_get_last_residency(dev) - drv->states[last_idx].exit_latency;
else
last_residency = last_state->threshold.promotion_time + 1;

/* consider promotion */
- if (last_idx < dev->state_count - 1 &&
+ if (last_idx < drv->state_count - 1 &&
last_residency > last_state->threshold.promotion_time &&
- dev->states[last_idx + 1].exit_latency <= latency_req) {
+ drv->states[last_idx + 1].exit_latency <= latency_req) {
last_state->stats.promotion_count++;
last_state->stats.demotion_count = 0;
if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) {
@@ -96,11 +98,11 @@ static int ladder_select_state(struct cpuidle_device *dev)

/* consider demotion */
if (last_idx > CPUIDLE_DRIVER_STATE_START &&
- dev->states[last_idx].exit_latency > latency_req) {
+ drv->states[last_idx].exit_latency > latency_req) {
int i;

for (i = last_idx - 1; i > CPUIDLE_DRIVER_STATE_START; i--) {
- if (dev->states[i].exit_latency <= latency_req)
+ if (drv->states[i].exit_latency <= latency_req)
break;
}
ladder_do_selection(ldev, last_idx, i);
@@ -123,9 +125,11 @@ static int ladder_select_state(struct cpuidle_device *dev)

/**
* ladder_enable_device - setup for the governor
+ * @drv: cpuidle driver
* @dev: the CPU
*/
-static int ladder_enable_device(struct cpuidle_device *dev)
+static int ladder_enable_device(struct cpuidle_driver *drv,
+ struct cpuidle_device *dev)
{
int i;
struct ladder_device *ldev = &per_cpu(ladder_devices, dev->cpu);
@@ -134,8 +138,8 @@ static int ladder_enable_device(struct cpuidle_device *dev)

ldev->last_state_idx = CPUIDLE_DRIVER_STATE_START;

- for (i = 0; i < dev->state_count; i++) {
- state = &dev->states[i];
+ for (i = 0; i < drv->state_count; i++) {
+ state = &drv->states[i];
lstate = &ldev->states[i];

lstate->stats.promotion_count = 0;
@@ -144,7 +148,7 @@ static int ladder_enable_device(struct cpuidle_device *dev)
lstate->threshold.promotion_count = PROMOTION_COUNT;
lstate->threshold.demotion_count = DEMOTION_COUNT;

- if (i < dev->state_count - 1)
+ if (i < drv->state_count - 1)
lstate->threshold.promotion_time = state->exit_latency;
if (i > 0)
lstate->threshold.demotion_time = state->exit_latency;
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index af724e8..bcbe881 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -182,7 +182,7 @@ static inline int performance_multiplier(void)

static DEFINE_PER_CPU(struct menu_device, menu_devices);

-static void menu_update(struct cpuidle_device *dev);
+static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);

/* This implements DIV_ROUND_CLOSEST but avoids 64 bit division */
static u64 div_round64(u64 dividend, u32 divisor)
@@ -228,9 +228,10 @@ static void detect_repeating_patterns(struct menu_device *data)

/**
* menu_select - selects the next idle state to enter
+ * @drv: cpuidle driver containing state data
* @dev: the CPU
*/
-static int menu_select(struct cpuidle_device *dev)
+static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
{
struct menu_device *data = &__get_cpu_var(menu_devices);
int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
@@ -240,7 +241,7 @@ static int menu_select(struct cpuidle_device *dev)
struct timespec t;

if (data->needs_update) {
- menu_update(dev);
+ menu_update(drv, dev);
data->needs_update = 0;
}

@@ -285,8 +286,8 @@ static int menu_select(struct cpuidle_device *dev)
* Find the idle state with the lowest power while satisfying
* our constraints.
*/
- for (i = CPUIDLE_DRIVER_STATE_START; i < dev->state_count; i++) {
- struct cpuidle_state *s = &dev->states[i];
+ for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+ struct cpuidle_state *s = &drv->states[i];

if (s->target_residency > data->predicted_us)
continue;
@@ -323,14 +324,15 @@ static void menu_reflect(struct cpuidle_device *dev, int index)

/**
* menu_update - attempts to guess what happened after entry
+ * @drv: cpuidle driver containing state data
* @dev: the CPU
*/
-static void menu_update(struct cpuidle_device *dev)
+static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
{
struct menu_device *data = &__get_cpu_var(menu_devices);
int last_idx = data->last_state_idx;
unsigned int last_idle_us = cpuidle_get_last_residency(dev);
- struct cpuidle_state *target = &dev->states[last_idx];
+ struct cpuidle_state *target = &drv->states[last_idx];
unsigned int measured_us;
u64 new_factor;

@@ -384,9 +386,11 @@ static void menu_update(struct cpuidle_device *dev)

/**
* menu_enable_device - scans a CPU's states and does setup
+ * @drv: cpuidle driver
* @dev: the CPU
*/
-static int menu_enable_device(struct cpuidle_device *dev)
+static int menu_enable_device(struct cpuidle_driver *drv,
+ struct cpuidle_device *dev)
{
struct menu_device *data = &per_cpu(menu_devices, dev->cpu);

diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 09c9c77..90be2ad 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -318,13 +318,14 @@ int cpuidle_add_state_sysfs(struct cpuidle_device *device)
{
int i, ret = -ENOMEM;
struct cpuidle_state_kobj *kobj;
+ struct cpuidle_driver *drv = cpuidle_get_driver();

/* state statistics */
for (i = 0; i < device->state_count; i++) {
kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL);
if (!kobj)
goto error_state;
- kobj->state = &device->states[i];
+ kobj->state = &drv->states[i];
kobj->state_usage = &device->states_usage[i];
init_completion(&kobj->kobj_unregister);

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 3aa8d4c..5be9d59 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -81,7 +81,8 @@ static unsigned int mwait_substates;
static unsigned int lapic_timer_reliable_states = (1 << 1); /* Default to only C1 */

static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
-static int intel_idle(struct cpuidle_device *dev, int index);
+static int intel_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index);

static struct cpuidle_state *cpuidle_state_table;

@@ -227,13 +228,15 @@ static int get_driver_data(int cstate)
/**
* intel_idle
* @dev: cpuidle_device
+ * @drv: cpuidle driver
* @index: index of cpuidle state
*
*/
-static int intel_idle(struct cpuidle_device *dev, int index)
+static int intel_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
{
unsigned long ecx = 1; /* break on interrupt flag */
- struct cpuidle_state *state = &dev->states[index];
+ struct cpuidle_state *state = &drv->states[index];
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
unsigned long eax = (unsigned long)cpuidle_get_statedata(state_usage);
unsigned int cstate;
@@ -420,6 +423,60 @@ static void intel_idle_cpuidle_devices_uninit(void)
return;
}
/*
+ * intel_idle_cpuidle_driver_init()
+ * allocate, initialize cpuidle_states
+ */
+static int intel_idle_cpuidle_driver_init(void)
+{
+ int cstate;
+ struct cpuidle_driver *drv = &intel_idle_driver;
+
+ drv->state_count = 1;
+
+ for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
+ int num_substates;
+
+ if (cstate > max_cstate) {
+ printk(PREFIX "max_cstate %d reached\n",
+ max_cstate);
+ break;
+ }
+
+ /* does the state exist in CPUID.MWAIT? */
+ num_substates = (mwait_substates >> ((cstate) * 4))
+ & MWAIT_SUBSTATE_MASK;
+ if (num_substates == 0)
+ continue;
+ /* is the state not enabled? */
+ if (cpuidle_state_table[cstate].enter == NULL) {
+ /* does the driver not know about the state? */
+ if (*cpuidle_state_table[cstate].name == '\0')
+ pr_debug(PREFIX "unaware of model 0x%x"
+ " MWAIT %d please"
+ " contact lenb@xxxxxxxxxx",
+ boot_cpu_data.x86_model, cstate);
+ continue;
+ }
+
+ if ((cstate > 2) &&
+ !boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+ mark_tsc_unstable("TSC halts in idle"
+ " states deeper than C2");
+
+ drv->states[drv->state_count] = /* structure copy */
+ cpuidle_state_table[cstate];
+
+ drv->state_count += 1;
+ }
+
+ if (auto_demotion_disable_flags)
+ smp_call_function(auto_demotion_disable, NULL, 1);
+
+ return 0;
+}
+
+
+/*
* intel_idle_cpuidle_devices_init()
* allocate, initialize, register cpuidle_devices
*/
@@ -453,23 +510,9 @@ static int intel_idle_cpuidle_devices_init(void)
continue;
/* is the state not enabled? */
if (cpuidle_state_table[cstate].enter == NULL) {
- /* does the driver not know about the state? */
- if (*cpuidle_state_table[cstate].name == '\0')
- pr_debug(PREFIX "unaware of model 0x%x"
- " MWAIT %d please"
- " contact lenb@xxxxxxxxxx",
- boot_cpu_data.x86_model, cstate);
continue;
}

- if ((cstate > 2) &&
- !boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
- mark_tsc_unstable("TSC halts in idle"
- " states deeper than C2");
-
- dev->states[dev->state_count] = /* structure copy */
- cpuidle_state_table[cstate];
-
dev->states_usage[dev->state_count].driver_data =
(void *)get_driver_data(cstate);

@@ -484,8 +527,6 @@ static int intel_idle_cpuidle_devices_init(void)
return -EIO;
}
}
- if (auto_demotion_disable_flags)
- smp_call_function(auto_demotion_disable, NULL, 1);

return 0;
}
@@ -503,6 +544,7 @@ static int __init intel_idle_init(void)
if (retval)
return retval;

+ intel_idle_cpuidle_driver_init();
retval = cpuidle_register_driver(&intel_idle_driver);
if (retval) {
printk(KERN_DEBUG PREFIX "intel_idle yielding to %s",
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index ba4928c..716e97b 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -329,6 +329,7 @@ extern void acpi_processor_throttling_init(void);
int acpi_processor_power_init(struct acpi_processor *pr,
struct acpi_device *device);
int acpi_processor_cst_has_changed(struct acpi_processor *pr);
+int acpi_processor_hotplug(struct acpi_processor *pr);
int acpi_processor_power_exit(struct acpi_processor *pr,
struct acpi_device *device);
int acpi_processor_suspend(struct acpi_device * device, pm_message_t state);
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 5a1a238..1e85538 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -22,6 +22,7 @@
#define CPUIDLE_DESC_LEN 32

struct cpuidle_device;
+struct cpuidle_driver;


/****************************
@@ -45,6 +46,7 @@ struct cpuidle_state {
unsigned int target_residency; /* in US */

int (*enter) (struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
int index);
};

@@ -83,12 +85,10 @@ struct cpuidle_state_kobj {
struct cpuidle_device {
unsigned int registered:1;
unsigned int enabled:1;
- unsigned int power_specified:1;
unsigned int cpu;

int last_residency;
int state_count;
- struct cpuidle_state states[CPUIDLE_STATE_MAX];
struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX];
struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];

@@ -96,7 +96,6 @@ struct cpuidle_device {
struct kobject kobj;
struct completion kobj_unregister;
void *governor_data;
- int safe_state_index;
};

DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
@@ -120,6 +119,11 @@ static inline int cpuidle_get_last_residency(struct cpuidle_device *dev)
struct cpuidle_driver {
char name[CPUIDLE_NAME_LEN];
struct module *owner;
+
+ unsigned int power_specified:1;
+ struct cpuidle_state states[CPUIDLE_STATE_MAX];
+ int state_count;
+ int safe_state_index;
};

#ifdef CONFIG_CPU_IDLE
@@ -162,10 +166,13 @@ struct cpuidle_governor {
struct list_head governor_list;
unsigned int rating;

- int (*enable) (struct cpuidle_device *dev);
- void (*disable) (struct cpuidle_device *dev);
+ int (*enable) (struct cpuidle_driver *drv,
+ struct cpuidle_device *dev);
+ void (*disable) (struct cpuidle_driver *drv,
+ struct cpuidle_device *dev);

- int (*select) (struct cpuidle_device *dev);
+ int (*select) (struct cpuidle_driver *drv,
+ struct cpuidle_device *dev);
void (*reflect) (struct cpuidle_device *dev, int index);

struct module *owner;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/