--- Documentation/cpuidle/core.txt | 17 Documentation/cpuidle/driver.txt | 29 + Documentation/cpuidle/governor.txt | 28 + Documentation/cpuidle/sysfs.txt | 35 + arch/i386/Kconfig | 2 arch/i386/kernel/process.c | 3 arch/x86_64/Kconfig | 2 drivers/Makefile | 1 drivers/acpi/osl.c | 11 drivers/acpi/processor_core.c | 5 drivers/acpi/processor_idle.c | 904 ++++++++++++++----------------------- drivers/cpuidle/Kconfig | 39 + drivers/cpuidle/Makefile | 5 drivers/cpuidle/cpuidle.c | 306 ++++++++++++ drivers/cpuidle/cpuidle.h | 50 ++ drivers/cpuidle/driver.c | 276 +++++++++++ drivers/cpuidle/governor.c | 187 +++++++ drivers/cpuidle/governors/Makefile | 6 drivers/cpuidle/governors/ladder.c | 228 +++++++++ drivers/cpuidle/governors/menu.c | 181 +++++++ drivers/cpuidle/sysfs.c | 393 ++++++++++++++++ include/acpi/processor.h | 3 include/linux/acpi.h | 7 include/linux/cpuidle.h | 190 +++++++ include/linux/tick.h | 10 kernel/softirq.c | 5 kernel/time/tick-sched.c | 26 + 27 files changed, 2399 insertions(+), 550 deletions(-) Index: linux-2.6.22/arch/i386/Kconfig =================================================================== --- linux-2.6.22.orig/arch/i386/Kconfig 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/arch/i386/Kconfig 2007-07-15 17:13:44.000000000 +0200 @@ -1053,6 +1053,8 @@ endif # APM source "arch/i386/kernel/cpu/cpufreq/Kconfig" +source "drivers/cpuidle/Kconfig" + endmenu menu "Bus options (PCI, PCMCIA, EISA, MCA, ISA)" Index: linux-2.6.22/arch/x86_64/Kconfig =================================================================== --- linux-2.6.22.orig/arch/x86_64/Kconfig 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/arch/x86_64/Kconfig 2007-07-15 17:13:44.000000000 +0200 @@ -698,6 +698,8 @@ source "drivers/acpi/Kconfig" source "arch/x86_64/kernel/cpufreq/Kconfig" +source "drivers/cpuidle/Kconfig" + endmenu menu "Bus options (PCI etc.)" Index: linux-2.6.22/drivers/Makefile =================================================================== --- linux-2.6.22.orig/drivers/Makefile 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/drivers/Makefile 2007-07-15 17:13:44.000000000 +0200 @@ -70,6 +70,7 @@ obj-$(CONFIG_EDAC) += edac/ obj-$(CONFIG_MCA) += mca/ obj-$(CONFIG_EISA) += eisa/ obj-$(CONFIG_CPU_FREQ) += cpufreq/ +obj-$(CONFIG_CPU_IDLE) += cpuidle/ obj-$(CONFIG_MMC) += mmc/ obj-$(CONFIG_NEW_LEDS) += leds/ obj-$(CONFIG_INFINIBAND) += infiniband/ Index: linux-2.6.22/drivers/cpuidle/Kconfig =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/Kconfig 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,39 @@ +menu "CPU idle PM support" + +config CPU_IDLE + bool "CPU idle PM support" + help + CPU idle is a generic framework for supporting software-controlled + idle processor power management. It includes modular cross-platform + governors that can be swapped during runtime. + + If you're using a mobile platform that supports CPU idle PM (e.g. + an ACPI-capable notebook), you should say Y here. + +if CPU_IDLE + +comment "Governors" + +config CPU_IDLE_GOV_LADDER + tristate "'ladder' governor" + depends on CPU_IDLE + default y + help + This cpuidle governor promotes and demotes through the supported idle + states using residency time and bus master activity as metrics. This + algorithm was originally introduced in the old ACPI processor driver. + +config CPU_IDLE_GOV_MENU + tristate "'menu' governor" + depends on CPU_IDLE && NO_HZ + default y + help + This cpuidle governor evaluates all available states and chooses the + deepest state that meets all of the following constraints: BM activity, + expected time until next timer interrupt, and last break event time + delta. It is designed to minimize power consumption. Currently + dynticks is required. + +endif # CPU_IDLE + +endmenu Index: linux-2.6.22/drivers/cpuidle/Makefile =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/Makefile 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,5 @@ +# +# Makefile for cpuidle. +# + +obj-y += cpuidle.o driver.o governor.o sysfs.o governors/ Index: linux-2.6.22/drivers/cpuidle/cpuidle.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/cpuidle.c 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,306 @@ +/* + * cpuidle.c - core cpuidle infrastructure + * + * (C) 2006-2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "cpuidle.h" + +DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices); +EXPORT_PER_CPU_SYMBOL_GPL(cpuidle_devices); + +DEFINE_MUTEX(cpuidle_lock); +LIST_HEAD(cpuidle_detected_devices); +static void (*pm_idle_old)(void); + +/** + * cpuidle_idle_call - the main idle loop + * + * NOTE: no locks or semaphores should be used here + */ +static void cpuidle_idle_call(void) +{ + struct cpuidle_device *dev = __get_cpu_var(cpuidle_devices); + struct cpuidle_state *target_state; + int next_state; + + /* check if the device is ready */ + if (!dev || dev->status != CPUIDLE_STATUS_DOIDLE) { + if (pm_idle_old) + pm_idle_old(); + else + local_irq_enable(); + return; + } + + /* ask the governor for the next state */ + next_state = cpuidle_curr_governor->select(dev); + if (need_resched()) + return; + target_state = &dev->states[next_state]; + + /* enter the state and update stats */ + dev->last_residency = target_state->enter(dev, target_state); + dev->last_state = target_state; + target_state->time += dev->last_residency; + target_state->usage++; + + /* give the governor an opportunity to reflect on the outcome */ + if (cpuidle_curr_governor->reflect) + cpuidle_curr_governor->reflect(dev); +} + +/** + * cpuidle_install_idle_handler - installs the cpuidle idle loop handler + */ +void cpuidle_install_idle_handler(void) +{ + if (pm_idle != cpuidle_idle_call) { + /* Make sure all changes finished before we switch to new idle */ + smp_wmb(); + pm_idle = cpuidle_idle_call; + } +} + +/** + * cpuidle_uninstall_idle_handler - uninstalls the cpuidle idle loop handler + */ +void cpuidle_uninstall_idle_handler(void) +{ + if (pm_idle != pm_idle_old) { + pm_idle = pm_idle_old; + cpu_idle_wait(); + } +} + +/** + * cpuidle_rescan_device - prepares for a new state configuration + * @dev: the target device + * + * Must be called with cpuidle_lock aquired. + */ +void cpuidle_rescan_device(struct cpuidle_device *dev) +{ + int i; + + if (cpuidle_curr_governor->scan) + cpuidle_curr_governor->scan(dev); + + for (i = 0; i < dev->state_count; i++) { + dev->states[i].usage = 0; + dev->states[i].time = 0; + } +} + +/** + * cpuidle_add_device - attaches the driver to a CPU instance + * @sys_dev: the system device (driver model CPU representation) + */ +static int cpuidle_add_device(struct sys_device *sys_dev) +{ + int cpu = sys_dev->id; + struct cpuidle_device *dev; + + dev = per_cpu(cpuidle_devices, cpu); + + mutex_lock(&cpuidle_lock); + if (cpu_is_offline(cpu)) { + mutex_unlock(&cpuidle_lock); + return 0; + } + + if (!dev) { + dev = kzalloc(sizeof(struct cpuidle_device), GFP_KERNEL); + if (!dev) { + mutex_unlock(&cpuidle_lock); + return -ENOMEM; + } + init_completion(&dev->kobj_unregister); + per_cpu(cpuidle_devices, cpu) = dev; + } + dev->cpu = cpu; + + if (dev->status & CPUIDLE_STATUS_DETECTED) { + mutex_unlock(&cpuidle_lock); + return 0; + } + + cpuidle_add_sysfs(sys_dev); + + if (cpuidle_curr_driver) { + if (cpuidle_attach_driver(dev)) + goto err_ret; + } + + if (cpuidle_curr_governor) { + if (cpuidle_attach_governor(dev)) { + cpuidle_detach_driver(dev); + goto err_ret; + } + } + + if (cpuidle_device_can_idle(dev)) + cpuidle_install_idle_handler(); + + list_add(&dev->device_list, &cpuidle_detected_devices); + dev->status |= CPUIDLE_STATUS_DETECTED; + +err_ret: + mutex_unlock(&cpuidle_lock); + + return 0; +} + +/** + * __cpuidle_remove_device - detaches the driver from a CPU instance + * @sys_dev: the system device (driver model CPU representation) + * + * Must be called with cpuidle_lock aquired. + */ +static int __cpuidle_remove_device(struct sys_device *sys_dev) +{ + struct cpuidle_device *dev; + + dev = per_cpu(cpuidle_devices, sys_dev->id); + + if (!(dev->status & CPUIDLE_STATUS_DETECTED)) { + return 0; + } + dev->status &= ~CPUIDLE_STATUS_DETECTED; + /* NOTE: we don't wait because the cpu is already offline */ + if (cpuidle_curr_governor) + cpuidle_detach_governor(dev); + if (cpuidle_curr_driver) + cpuidle_detach_driver(dev); + cpuidle_remove_sysfs(sys_dev); + list_del(&dev->device_list); + wait_for_completion(&dev->kobj_unregister); + per_cpu(cpuidle_devices, sys_dev->id) = NULL; + kfree(dev); + + return 0; +} + +/** + * cpuidle_remove_device - detaches the driver from a CPU instance + * @sys_dev: the system device (driver model CPU representation) + */ +static int cpuidle_remove_device(struct sys_device *sys_dev) +{ + int ret; + mutex_lock(&cpuidle_lock); + ret = __cpuidle_remove_device(sys_dev); + mutex_unlock(&cpuidle_lock); + + return ret; +} + +static struct sysdev_driver cpuidle_sysdev_driver = { + .add = cpuidle_add_device, + .remove = cpuidle_remove_device, +}; + +static int cpuidle_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + struct sys_device *sys_dev; + + sys_dev = get_cpu_sysdev((unsigned long)hcpu); + + switch (action) { + case CPU_ONLINE: + cpuidle_add_device(sys_dev); + break; + case CPU_DOWN_PREPARE: + mutex_lock(&cpuidle_lock); + break; + case CPU_DEAD: + __cpuidle_remove_device(sys_dev); + mutex_unlock(&cpuidle_lock); + break; + case CPU_DOWN_FAILED: + mutex_unlock(&cpuidle_lock); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata cpuidle_cpu_notifier = +{ + .notifier_call = cpuidle_cpu_callback, +}; + +#ifdef CONFIG_SMP + +static void smp_callback(void *v) +{ + /* we already woke the CPU up, nothing more to do */ +} + +/* + * This function gets called when a part of the kernel has a new latency + * requirement. This means we need to get all processors out of their C-state, + * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that + * wakes them all right up. + */ +static int cpuidle_latency_notify(struct notifier_block *b, + unsigned long l, void *v) +{ + smp_call_function(smp_callback, NULL, 0, 1); + return NOTIFY_OK; +} + +static struct notifier_block cpuidle_latency_notifier = { + .notifier_call = cpuidle_latency_notify, +}; + +#define latency_notifier_init(x) do { register_latency_notifier(x); } while (0) + +#else /* CONFIG_SMP */ + +#define latency_notifier_init(x) do { } while (0) + +#endif /* CONFIG_SMP */ + +/** + * cpuidle_init - core initializer + */ +static int __init cpuidle_init(void) +{ + int ret; + + pm_idle_old = pm_idle; + + ret = cpuidle_add_class_sysfs(&cpu_sysdev_class); + if (ret) + return ret; + + register_hotcpu_notifier(&cpuidle_cpu_notifier); + + ret = sysdev_driver_register(&cpu_sysdev_class, &cpuidle_sysdev_driver); + + if (ret) { + cpuidle_remove_class_sysfs(&cpu_sysdev_class); + printk(KERN_ERR "cpuidle: failed to initialize\n"); + return ret; + } + + latency_notifier_init(&cpuidle_latency_notifier); + + return 0; +} + +core_initcall(cpuidle_init); Index: linux-2.6.22/drivers/cpuidle/cpuidle.h =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/cpuidle.h 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,50 @@ +/* + * cpuidle.h - The internal header file + */ + +#ifndef __DRIVER_CPUIDLE_H +#define __DRIVER_CPUIDLE_H + +#include + +/* For internal use only */ +extern struct cpuidle_governor *cpuidle_curr_governor; +extern struct cpuidle_driver *cpuidle_curr_driver; +extern struct list_head cpuidle_drivers; +extern struct list_head cpuidle_governors; +extern struct list_head cpuidle_detected_devices; +extern struct mutex cpuidle_lock; + +/* idle loop */ +extern void cpuidle_install_idle_handler(void); +extern void cpuidle_uninstall_idle_handler(void); +extern void cpuidle_rescan_device(struct cpuidle_device *dev); + +/* drivers */ +extern int cpuidle_attach_driver(struct cpuidle_device *dev); +extern void cpuidle_detach_driver(struct cpuidle_device *dev); +extern int cpuidle_switch_driver(struct cpuidle_driver *drv); + +/* governors */ +extern int cpuidle_attach_governor(struct cpuidle_device *dev); +extern void cpuidle_detach_governor(struct cpuidle_device *dev); +extern int cpuidle_switch_governor(struct cpuidle_governor *gov); + +/* sysfs */ +extern int cpuidle_add_class_sysfs(struct sysdev_class *cls); +extern void cpuidle_remove_class_sysfs(struct sysdev_class *cls); +extern int cpuidle_add_driver_sysfs(struct cpuidle_device *device); +extern void cpuidle_remove_driver_sysfs(struct cpuidle_device *device); +extern int cpuidle_add_sysfs(struct sys_device *sysdev); +extern void cpuidle_remove_sysfs(struct sys_device *sysdev); + +/** + * cpuidle_device_can_idle - determines if a CPU can utilize the idle loop + * @dev: the target CPU + */ +static inline int cpuidle_device_can_idle(struct cpuidle_device *dev) +{ + return (dev->status == CPUIDLE_STATUS_DOIDLE); +} + +#endif /* __DRIVER_CPUIDLE_H */ Index: linux-2.6.22/drivers/cpuidle/driver.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/driver.c 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,276 @@ +/* + * driver.c - driver support + * + * (C) 2006-2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include + +#include "cpuidle.h" + +LIST_HEAD(cpuidle_drivers); +struct cpuidle_driver *cpuidle_curr_driver; + + +/** + * cpuidle_attach_driver - attaches a driver to a CPU + * @dev: the target CPU + * + * Must be called with cpuidle_lock aquired. + */ +int cpuidle_attach_driver(struct cpuidle_device *dev) +{ + int ret; + + if (dev->status & CPUIDLE_STATUS_DRIVER_ATTACHED) + return -EIO; + + if (!try_module_get(cpuidle_curr_driver->owner)) + return -EINVAL; + + ret = cpuidle_curr_driver->init(dev); + if (ret) { + module_put(cpuidle_curr_driver->owner); + printk(KERN_INFO "cpuidle: driver %s failed to attach to " + "cpu %d\n", cpuidle_curr_driver->name, dev->cpu); + } else { + if (dev->status & CPUIDLE_STATUS_GOVERNOR_ATTACHED) + cpuidle_rescan_device(dev); + smp_wmb(); + dev->status |= CPUIDLE_STATUS_DRIVER_ATTACHED; + cpuidle_add_driver_sysfs(dev); + } + + return ret; +} + +/** + * cpuidle_detach_govenor - detaches a driver from a CPU + * @dev: the target CPU + * + * Must be called with cpuidle_lock aquired. + */ +void cpuidle_detach_driver(struct cpuidle_device *dev) +{ + if (dev->status & CPUIDLE_STATUS_DRIVER_ATTACHED) { + cpuidle_remove_driver_sysfs(dev); + dev->status &= ~CPUIDLE_STATUS_DRIVER_ATTACHED; + if (cpuidle_curr_driver->exit) + cpuidle_curr_driver->exit(dev); + module_put(cpuidle_curr_driver->owner); + } +} + +/** + * __cpuidle_find_driver - finds a driver of the specified name + * @str: the name + * + * Must be called with cpuidle_lock aquired. + */ +static struct cpuidle_driver * __cpuidle_find_driver(const char *str) +{ + struct cpuidle_driver *drv; + + list_for_each_entry(drv, &cpuidle_drivers, driver_list) + if (!strnicmp(str, drv->name, CPUIDLE_NAME_LEN)) + return drv; + + return NULL; +} + +/** + * cpuidle_switch_driver - changes the driver + * @drv: the new target driver + * + * NOTE: "drv" can be NULL to specify disabled + * Must be called with cpuidle_lock aquired. + */ +int cpuidle_switch_driver(struct cpuidle_driver *drv) +{ + struct cpuidle_device *dev; + + if (drv == cpuidle_curr_driver) + return -EINVAL; + + cpuidle_uninstall_idle_handler(); + + if (cpuidle_curr_driver) + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + cpuidle_detach_driver(dev); + + cpuidle_curr_driver = drv; + + if (drv) { + int ret = 1; + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + if (cpuidle_attach_driver(dev) == 0) + ret = 0; + + /* If attach on all devices fail, switch to NULL driver */ + if (ret) + cpuidle_curr_driver = NULL; + + if (cpuidle_curr_driver && cpuidle_curr_governor) { + printk(KERN_INFO "cpuidle: using driver %s\n", + drv->name); + cpuidle_install_idle_handler(); + } + } + + return 0; +} + +/** + * cpuidle_register_driver - registers a driver + * @drv: the driver + */ +int cpuidle_register_driver(struct cpuidle_driver *drv) +{ + int ret = -EEXIST; + + if (!drv || !drv->init) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + if (__cpuidle_find_driver(drv->name) == NULL) { + ret = 0; + list_add_tail(&drv->driver_list, &cpuidle_drivers); + if (!cpuidle_curr_driver) + cpuidle_switch_driver(drv); + } + mutex_unlock(&cpuidle_lock); + + return ret; +} + +EXPORT_SYMBOL_GPL(cpuidle_register_driver); + +/** + * cpuidle_unregister_driver - unregisters a driver + * @drv: the driver + */ +void cpuidle_unregister_driver(struct cpuidle_driver *drv) +{ + if (!drv) + return; + + mutex_lock(&cpuidle_lock); + if (drv == cpuidle_curr_driver) + cpuidle_switch_driver(NULL); + list_del(&drv->driver_list); + mutex_unlock(&cpuidle_lock); +} + +EXPORT_SYMBOL_GPL(cpuidle_unregister_driver); + +static void __cpuidle_force_redetect(struct cpuidle_device *dev) +{ + cpuidle_remove_driver_sysfs(dev); + cpuidle_curr_driver->redetect(dev); + cpuidle_add_driver_sysfs(dev); +} + +/** + * cpuidle_force_redetect - redetects the idle states of a CPU + * + * @dev: the CPU to redetect + * @drv: the target driver + * + * Generally, the driver will call this when the supported states set has + * changed. (e.g. as the result of an ACPI transition to battery power) + */ +int cpuidle_force_redetect(struct cpuidle_device *dev, + struct cpuidle_driver *drv) +{ + int uninstalled = 0; + + mutex_lock(&cpuidle_lock); + + if (drv != cpuidle_curr_driver) { + mutex_unlock(&cpuidle_lock); + return 0; + } + + if (!(dev->status & CPUIDLE_STATUS_DRIVER_ATTACHED) || + !cpuidle_curr_driver->redetect) { + mutex_unlock(&cpuidle_lock); + return -EIO; + } + + if (cpuidle_device_can_idle(dev)) { + uninstalled = 1; + cpuidle_uninstall_idle_handler(); + } + + __cpuidle_force_redetect(dev); + + if (cpuidle_device_can_idle(dev)) { + cpuidle_rescan_device(dev); + cpuidle_install_idle_handler(); + } + + /* other devices are still ok */ + if (uninstalled) + cpuidle_install_idle_handler(); + + mutex_unlock(&cpuidle_lock); + + return 0; +} + +EXPORT_SYMBOL_GPL(cpuidle_force_redetect); + +/** + * cpuidle_force_redetect_devices - redetects the idle states of all CPUs + * + * @drv: the target driver + * + * Generally, the driver will call this when the supported states set has + * changed. (e.g. as the result of an ACPI transition to battery power) + */ +int cpuidle_force_redetect_devices(struct cpuidle_driver *drv) +{ + struct cpuidle_device *dev; + int ret = 0; + + mutex_lock(&cpuidle_lock); + + if (drv != cpuidle_curr_driver) + goto out; + + if (!cpuidle_curr_driver->redetect) { + ret = -EIO; + goto out; + } + + cpuidle_uninstall_idle_handler(); + + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + __cpuidle_force_redetect(dev); + + cpuidle_install_idle_handler(); +out: + mutex_unlock(&cpuidle_lock); + return ret; +} + +EXPORT_SYMBOL_GPL(cpuidle_force_redetect_devices); + +/** + * cpuidle_get_bm_activity - determines if BM activity has occured + */ +int cpuidle_get_bm_activity(void) +{ + if (cpuidle_curr_driver->bm_check) + return cpuidle_curr_driver->bm_check(); + else + return 0; +} +EXPORT_SYMBOL_GPL(cpuidle_get_bm_activity); + Index: linux-2.6.22/drivers/cpuidle/governor.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/governor.c 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,187 @@ +/* + * governor.c - governor support + * + * (C) 2006-2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include + +#include "cpuidle.h" + +LIST_HEAD(cpuidle_governors); +struct cpuidle_governor *cpuidle_curr_governor; + + +/** + * cpuidle_attach_governor - attaches a governor to a CPU + * @dev: the target CPU + * + * Must be called with cpuidle_lock aquired. + */ +int cpuidle_attach_governor(struct cpuidle_device *dev) +{ + int ret = 0; + + if(dev->status & CPUIDLE_STATUS_GOVERNOR_ATTACHED) + return -EIO; + + if (!try_module_get(cpuidle_curr_governor->owner)) + return -EINVAL; + + if (cpuidle_curr_governor->init) + ret = cpuidle_curr_governor->init(dev); + if (ret) { + module_put(cpuidle_curr_governor->owner); + printk(KERN_ERR "cpuidle: governor %s failed to attach to cpu %d\n", + cpuidle_curr_governor->name, dev->cpu); + } else { + if (dev->status & CPUIDLE_STATUS_DRIVER_ATTACHED) + cpuidle_rescan_device(dev); + smp_wmb(); + dev->status |= CPUIDLE_STATUS_GOVERNOR_ATTACHED; + } + + return ret; +} + +/** + * cpuidle_detach_govenor - detaches a governor from a CPU + * @dev: the target CPU + * + * Must be called with cpuidle_lock aquired. + */ +void cpuidle_detach_governor(struct cpuidle_device *dev) +{ + if (dev->status & CPUIDLE_STATUS_GOVERNOR_ATTACHED) { + dev->status &= ~CPUIDLE_STATUS_GOVERNOR_ATTACHED; + if (cpuidle_curr_governor->exit) + cpuidle_curr_governor->exit(dev); + module_put(cpuidle_curr_governor->owner); + } +} + +/** + * __cpuidle_find_governor - finds a governor of the specified name + * @str: the name + * + * Must be called with cpuidle_lock aquired. + */ +static struct cpuidle_governor * __cpuidle_find_governor(const char *str) +{ + struct cpuidle_governor *gov; + + list_for_each_entry(gov, &cpuidle_governors, governor_list) + if (!strnicmp(str, gov->name, CPUIDLE_NAME_LEN)) + return gov; + + return NULL; +} + +/** + * cpuidle_switch_governor - changes the governor + * @gov: the new target governor + * + * NOTE: "gov" can be NULL to specify disabled + * Must be called with cpuidle_lock aquired. + */ +int cpuidle_switch_governor(struct cpuidle_governor *gov) +{ + struct cpuidle_device *dev; + + if (gov == cpuidle_curr_governor) + return -EINVAL; + + cpuidle_uninstall_idle_handler(); + + if (cpuidle_curr_governor) + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + cpuidle_detach_governor(dev); + + cpuidle_curr_governor = gov; + + if (gov) { + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + cpuidle_attach_governor(dev); + if (cpuidle_curr_driver) + cpuidle_install_idle_handler(); + printk(KERN_INFO "cpuidle: using governor %s\n", gov->name); + } + + return 0; +} + +/** + * cpuidle_register_governor - registers a governor + * @gov: the governor + */ +int cpuidle_register_governor(struct cpuidle_governor *gov) +{ + int ret = -EEXIST; + + if (!gov || !gov->select) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + if (__cpuidle_find_governor(gov->name) == NULL) { + ret = 0; + list_add_tail(&gov->governor_list, &cpuidle_governors); + if (!cpuidle_curr_governor || + cpuidle_curr_governor->rating < gov->rating) + cpuidle_switch_governor(gov); + } + mutex_unlock(&cpuidle_lock); + + return ret; +} + +EXPORT_SYMBOL_GPL(cpuidle_register_governor); + +/** + * cpuidle_replace_governor - find a replacement governor + * @exclude_rating: the rating that will be skipped while looking for + * new governor. + */ +struct cpuidle_governor *cpuidle_replace_governor(int exclude_rating) +{ + struct cpuidle_governor *gov; + struct cpuidle_governor *ret_gov = NULL; + unsigned int max_rating = 0; + + list_for_each_entry(gov, &cpuidle_governors, governor_list) { + if (gov->rating == exclude_rating) + continue; + if (gov->rating > max_rating) { + max_rating = gov->rating; + ret_gov = gov; + } + } + + return ret_gov; +} + +/** + * cpuidle_unregister_governor - unregisters a governor + * @gov: the governor + */ +void cpuidle_unregister_governor(struct cpuidle_governor *gov) +{ + if (!gov) + return; + + mutex_lock(&cpuidle_lock); + if (gov == cpuidle_curr_governor) { + struct cpuidle_governor *new_gov; + new_gov = cpuidle_replace_governor(gov->rating); + cpuidle_switch_governor(new_gov); + } + list_del(&gov->governor_list); + mutex_unlock(&cpuidle_lock); +} + +EXPORT_SYMBOL_GPL(cpuidle_unregister_governor); Index: linux-2.6.22/drivers/cpuidle/governors/Makefile =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/governors/Makefile 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,6 @@ +# +# Makefile for cpuidle governors. +# + +obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o +obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o Index: linux-2.6.22/drivers/cpuidle/governors/ladder.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/governors/ladder.c 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,228 @@ +/* + * ladder.c - the residency ladder algorithm + * + * Copyright (C) 2001, 2002 Andy Grover + * Copyright (C) 2001, 2002 Paul Diefenbaugh + * Copyright (C) 2004, 2005 Dominik Brodowski + * + * (C) 2006-2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include +#include +#include + +#include +#include + +#define PROMOTION_COUNT 4 +#define DEMOTION_COUNT 1 + +/* + * bm_history -- bit-mask with a bit per jiffy of bus-master activity + * 1000 HZ: 0xFFFFFFFF: 32 jiffies = 32ms + * 800 HZ: 0xFFFFFFFF: 32 jiffies = 40ms + * 100 HZ: 0x0000000F: 4 jiffies = 40ms + * reduce history for more aggressive entry into C3 + */ +static unsigned int bm_history __read_mostly = + (HZ >= 800 ? 0xFFFFFFFF : ((1U << (HZ / 25)) - 1)); +module_param(bm_history, uint, 0644); + +struct ladder_device_state { + struct { + u32 promotion_count; + u32 demotion_count; + u32 promotion_time; + u32 demotion_time; + u32 bm; + } threshold; + struct { + int promotion_count; + int demotion_count; + } stats; +}; + +struct ladder_device { + struct ladder_device_state states[CPUIDLE_STATE_MAX]; + unsigned int bm_check:1; + unsigned long bm_check_timestamp; + unsigned long bm_activity; /* FIXME: bm activity should be global */ + int last_state_idx; +}; + +/** + * ladder_do_selection - prepares private data for a state change + * @ldev: the ladder device + * @old_idx: the current state index + * @new_idx: the new target state index + */ +static inline void ladder_do_selection(struct ladder_device *ldev, + int old_idx, int new_idx) +{ + ldev->states[old_idx].stats.promotion_count = 0; + ldev->states[old_idx].stats.demotion_count = 0; + ldev->last_state_idx = new_idx; +} + +/** + * ladder_select_state - selects the next state to enter + * @dev: the CPU + */ +static int ladder_select_state(struct cpuidle_device *dev) +{ + struct ladder_device *ldev = dev->governor_data; + struct ladder_device_state *last_state; + int last_residency, last_idx = ldev->last_state_idx; + + if (unlikely(!ldev)) + return 0; + + last_state = &ldev->states[last_idx]; + + /* demote if within BM threshold */ + if (ldev->bm_check) { + unsigned long diff; + + diff = jiffies - ldev->bm_check_timestamp; + if (diff > 31) + diff = 31; + + ldev->bm_activity <<= diff; + if (cpuidle_get_bm_activity()) + ldev->bm_activity |= ((1 << diff) - 1); + + ldev->bm_check_timestamp = jiffies; + if ((last_idx > 0) && + (last_state->threshold.bm & ldev->bm_activity)) { + ladder_do_selection(ldev, last_idx, last_idx - 1); + return last_idx - 1; + } + } + + if (dev->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) + last_residency = cpuidle_get_last_residency(dev) - dev->states[last_idx].exit_latency; + else + last_residency = last_state->threshold.promotion_time + 1; + + /* consider promotion */ + if (last_idx < dev->state_count - 1 && + last_residency > last_state->threshold.promotion_time && + dev->states[last_idx + 1].exit_latency <= system_latency_constraint()) { + last_state->stats.promotion_count++; + last_state->stats.demotion_count = 0; + if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) { + ladder_do_selection(ldev, last_idx, last_idx + 1); + return last_idx + 1; + } + } + + /* consider demotion */ + if (last_idx > 0 && + last_residency < last_state->threshold.demotion_time) { + last_state->stats.demotion_count++; + last_state->stats.promotion_count = 0; + if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) { + ladder_do_selection(ldev, last_idx, last_idx - 1); + return last_idx - 1; + } + } + + /* otherwise remain at the current state */ + return last_idx; +} + +/** + * ladder_scan_device - scans a CPU's states and does setup + * @dev: the CPU + */ +static void ladder_scan_device(struct cpuidle_device *dev) +{ + int i, bm_check = 0; + struct ladder_device *ldev = dev->governor_data; + struct ladder_device_state *lstate; + struct cpuidle_state *state; + + ldev->last_state_idx = 0; + ldev->bm_check_timestamp = 0; + ldev->bm_activity = 0; + + for (i = 0; i < dev->state_count; i++) { + state = &dev->states[i]; + lstate = &ldev->states[i]; + + lstate->stats.promotion_count = 0; + lstate->stats.demotion_count = 0; + + lstate->threshold.promotion_count = PROMOTION_COUNT; + lstate->threshold.demotion_count = DEMOTION_COUNT; + + if (i < dev->state_count - 1) + lstate->threshold.promotion_time = state->exit_latency; + if (i > 0) + lstate->threshold.demotion_time = state->exit_latency; + if (state->flags & CPUIDLE_FLAG_CHECK_BM) { + lstate->threshold.bm = bm_history; + bm_check = 1; + } else + lstate->threshold.bm = 0; + } + + ldev->bm_check = bm_check; +} + +/** + * ladder_init_device - initializes a CPU-instance + * @dev: the CPU + */ +static int ladder_init_device(struct cpuidle_device *dev) +{ + dev->governor_data = kmalloc(sizeof(struct ladder_device), GFP_KERNEL); + + return !dev->governor_data; +} + +/** + * ladder_exit_device - exits a CPU-instance + * @dev: the CPU + */ +static void ladder_exit_device(struct cpuidle_device *dev) +{ + kfree(dev->governor_data); +} + +static struct cpuidle_governor ladder_governor = { + .name = "ladder", + .rating = 10, + .init = ladder_init_device, + .exit = ladder_exit_device, + .scan = ladder_scan_device, + .select = ladder_select_state, + .owner = THIS_MODULE, +}; + +/** + * init_ladder - initializes the governor + */ +static int __init init_ladder(void) +{ + return cpuidle_register_governor(&ladder_governor); +} + +/** + * exit_ladder - exits the governor + */ +static void __exit exit_ladder(void) +{ + cpuidle_unregister_governor(&ladder_governor); +} + +MODULE_LICENSE("GPL"); +module_init(init_ladder); +module_exit(exit_ladder); Index: linux-2.6.22/drivers/cpuidle/sysfs.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/sysfs.c 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,393 @@ +/* + * sysfs.c - sysfs support + * + * (C) 2006-2007 Shaohua Li + * + * This code is licenced under the GPL. + */ + +#include +#include +#include +#include + +#include "cpuidle.h" + +static unsigned int sysfs_switch; +static int __init cpuidle_sysfs_setup(char *unused) +{ + sysfs_switch = 1; + return 1; +} +__setup("cpuidle_sysfs_switch", cpuidle_sysfs_setup); + +static ssize_t show_available_drivers(struct sys_device *dev, char *buf) +{ + ssize_t i = 0; + struct cpuidle_driver *tmp; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_drivers, driver_list) { + if (i >= (ssize_t)((PAGE_SIZE/sizeof(char)) - CPUIDLE_NAME_LEN - 2)) + goto out; + i += scnprintf(&buf[i], CPUIDLE_NAME_LEN, "%s ", tmp->name); + } +out: + i+= sprintf(&buf[i], "\n"); + mutex_unlock(&cpuidle_lock); + return i; +} + +static ssize_t show_available_governors(struct sys_device *dev, char *buf) +{ + ssize_t i = 0; + struct cpuidle_governor *tmp; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_governors, governor_list) { + if (i >= (ssize_t)((PAGE_SIZE/sizeof(char)) - CPUIDLE_NAME_LEN - 2)) + goto out; + i += scnprintf(&buf[i], CPUIDLE_NAME_LEN, "%s ", tmp->name); + } + if (list_empty(&cpuidle_governors)) + i+= sprintf(&buf[i], "no governors"); +out: + i+= sprintf(&buf[i], "\n"); + mutex_unlock(&cpuidle_lock); + return i; +} + +static ssize_t show_current_driver(struct sys_device *dev, char *buf) +{ + ssize_t ret; + + mutex_lock(&cpuidle_lock); + ret = sprintf(buf, "%s\n", cpuidle_curr_driver->name); + mutex_unlock(&cpuidle_lock); + return ret; +} + +static ssize_t store_current_driver(struct sys_device *dev, + const char *buf, size_t count) +{ + char str[CPUIDLE_NAME_LEN]; + int len = count; + struct cpuidle_driver *tmp, *found = NULL; + + if (len > CPUIDLE_NAME_LEN) + len = CPUIDLE_NAME_LEN; + + if (sscanf(buf, "%s", str) != 1) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_drivers, driver_list) { + if (strncmp(tmp->name, str, CPUIDLE_NAME_LEN) == 0) { + found = tmp; + break; + } + } + if (found) + cpuidle_switch_driver(found); + mutex_unlock(&cpuidle_lock); + + return count; +} + +static ssize_t show_current_governor(struct sys_device *dev, char *buf) +{ + ssize_t i; + + mutex_lock(&cpuidle_lock); + if (cpuidle_curr_governor) + i = sprintf(buf, "%s\n", cpuidle_curr_governor->name); + else + i = sprintf(buf, "no governor\n"); + mutex_unlock(&cpuidle_lock); + + return i; +} + +static ssize_t store_current_governor(struct sys_device *dev, + const char *buf, size_t count) +{ + char str[CPUIDLE_NAME_LEN]; + int len = count; + struct cpuidle_governor *tmp, *found = NULL; + + if (len > CPUIDLE_NAME_LEN) + len = CPUIDLE_NAME_LEN; + + if (sscanf(buf, "%s", str) != 1) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_governors, governor_list) { + if (strncmp(tmp->name, str, CPUIDLE_NAME_LEN) == 0) { + found = tmp; + break; + } + } + if (found) + cpuidle_switch_governor(found); + mutex_unlock(&cpuidle_lock); + + return count; +} + +static SYSDEV_ATTR(current_driver_ro, 0444, show_current_driver, NULL); +static SYSDEV_ATTR(current_governor_ro, 0444, show_current_governor, NULL); + +static struct attribute *cpuclass_default_attrs[] = { + &attr_current_driver_ro.attr, + &attr_current_governor_ro.attr, + NULL +}; + +static SYSDEV_ATTR(available_drivers, 0444, show_available_drivers, NULL); +static SYSDEV_ATTR(available_governors, 0444, show_available_governors, NULL); +static SYSDEV_ATTR(current_driver, 0644, show_current_driver, + store_current_driver); +static SYSDEV_ATTR(current_governor, 0644, show_current_governor, + store_current_governor); + +static struct attribute *cpuclass_switch_attrs[] = { + &attr_available_drivers.attr, + &attr_available_governors.attr, + &attr_current_driver.attr, + &attr_current_governor.attr, + NULL +}; + +static struct attribute_group cpuclass_attr_group = { + .attrs = cpuclass_default_attrs, + .name = "cpuidle", +}; + +/** + * cpuidle_add_class_sysfs - add CPU global sysfs attributes + */ +int cpuidle_add_class_sysfs(struct sysdev_class *cls) +{ + if (sysfs_switch) + cpuclass_attr_group.attrs = cpuclass_switch_attrs; + + return sysfs_create_group(&cls->kset.kobj, &cpuclass_attr_group); +} + +/** + * cpuidle_remove_class_sysfs - remove CPU global sysfs attributes + */ +void cpuidle_remove_class_sysfs(struct sysdev_class *cls) +{ + sysfs_remove_group(&cls->kset.kobj, &cpuclass_attr_group); +} + +struct cpuidle_attr { + struct attribute attr; + ssize_t (*show)(struct cpuidle_device *, char *); + ssize_t (*store)(struct cpuidle_device *, const char *, size_t count); +}; + +#define define_one_ro(_name, show) \ + static struct cpuidle_attr attr_##_name = __ATTR(_name, 0444, show, NULL) +#define define_one_rw(_name, show, store) \ + static struct cpuidle_attr attr_##_name = __ATTR(_name, 0644, show, store) + +#define kobj_to_cpuidledev(k) container_of(k, struct cpuidle_device, kobj) +#define attr_to_cpuidleattr(a) container_of(a, struct cpuidle_attr, attr) +static ssize_t cpuidle_show(struct kobject * kobj, struct attribute * attr ,char * buf) +{ + int ret = -EIO; + struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + struct cpuidle_attr * cattr = attr_to_cpuidleattr(attr); + + if (cattr->show) { + mutex_lock(&cpuidle_lock); + ret = cattr->show(dev, buf); + mutex_unlock(&cpuidle_lock); + } + return ret; +} + +static ssize_t cpuidle_store(struct kobject * kobj, struct attribute * attr, + const char * buf, size_t count) +{ + int ret = -EIO; + struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + struct cpuidle_attr * cattr = attr_to_cpuidleattr(attr); + + if (cattr->store) { + mutex_lock(&cpuidle_lock); + ret = cattr->store(dev, buf, count); + mutex_unlock(&cpuidle_lock); + } + return ret; +} + +static struct sysfs_ops cpuidle_sysfs_ops = { + .show = cpuidle_show, + .store = cpuidle_store, +}; + +static void cpuidle_sysfs_release(struct kobject *kobj) +{ + struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + + complete(&dev->kobj_unregister); +} + +static struct kobj_type ktype_cpuidle = { + .sysfs_ops = &cpuidle_sysfs_ops, + .release = cpuidle_sysfs_release, +}; + +struct cpuidle_state_attr { + struct attribute attr; + ssize_t (*show)(struct cpuidle_state *, char *); + ssize_t (*store)(struct cpuidle_state *, const char *, size_t); +}; + +#define define_one_state_ro(_name, show) \ +static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0444, show, NULL) + +#define define_show_state_function(_name) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \ +{ \ + return sprintf(buf, "%d\n", state->_name);\ +} + +define_show_state_function(exit_latency) +define_show_state_function(power_usage) +define_show_state_function(usage) +define_show_state_function(time) +define_one_state_ro(latency, show_state_exit_latency); +define_one_state_ro(power, show_state_power_usage); +define_one_state_ro(usage, show_state_usage); +define_one_state_ro(time, show_state_time); + +static struct attribute *cpuidle_state_default_attrs[] = { + &attr_latency.attr, + &attr_power.attr, + &attr_usage.attr, + &attr_time.attr, + NULL +}; + +#define kobj_to_state_obj(k) container_of(k, struct cpuidle_state_kobj, kobj) +#define kobj_to_state(k) (kobj_to_state_obj(k)->state) +#define attr_to_stateattr(a) container_of(a, struct cpuidle_state_attr, attr) +static ssize_t cpuidle_state_show(struct kobject * kobj, + struct attribute * attr ,char * buf) +{ + int ret = -EIO; + struct cpuidle_state *state = kobj_to_state(kobj); + struct cpuidle_state_attr * cattr = attr_to_stateattr(attr); + + if (cattr->show) + ret = cattr->show(state, buf); + + return ret; +} + +static struct sysfs_ops cpuidle_state_sysfs_ops = { + .show = cpuidle_state_show, +}; + +static void cpuidle_state_sysfs_release(struct kobject *kobj) +{ + struct cpuidle_state_kobj *state_obj = kobj_to_state_obj(kobj); + + complete(&state_obj->kobj_unregister); +} + +static struct kobj_type ktype_state_cpuidle = { + .sysfs_ops = &cpuidle_state_sysfs_ops, + .default_attrs = cpuidle_state_default_attrs, + .release = cpuidle_state_sysfs_release, +}; + +static void inline cpuidle_free_state_kobj(struct cpuidle_device *device, int i) +{ + kobject_unregister(&device->kobjs[i]->kobj); + wait_for_completion(&device->kobjs[i]->kobj_unregister); + kfree(device->kobjs[i]); + device->kobjs[i] = NULL; +} + +/** + * cpuidle_add_driver_sysfs - adds driver-specific sysfs attributes + * @device: the target device + */ +int cpuidle_add_driver_sysfs(struct cpuidle_device *device) +{ + int i, ret = -ENOMEM; + struct cpuidle_state_kobj *kobj; + + /* 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]; + init_completion(&kobj->kobj_unregister); + + kobj->kobj.parent = &device->kobj; + kobj->kobj.ktype = &ktype_state_cpuidle; + kobject_set_name(&kobj->kobj, "state%d", i); + ret = kobject_register(&kobj->kobj); + if (ret) { + kfree(kobj); + goto error_state; + } + device->kobjs[i] = kobj; + } + + return 0; + +error_state: + for (i = i - 1; i >= 0; i--) + cpuidle_free_state_kobj(device, i); + return ret; +} + +/** + * cpuidle_remove_driver_sysfs - removes driver-specific sysfs attributes + * @device: the target device + */ +void cpuidle_remove_driver_sysfs(struct cpuidle_device *device) +{ + int i; + + for (i = 0; i < device->state_count; i++) + cpuidle_free_state_kobj(device, i); +} + +/** + * cpuidle_add_sysfs - creates a sysfs instance for the target device + * @sysdev: the target device + */ +int cpuidle_add_sysfs(struct sys_device *sysdev) +{ + int cpu = sysdev->id; + struct cpuidle_device *dev; + + dev = per_cpu(cpuidle_devices, cpu); + dev->kobj.parent = &sysdev->kobj; + dev->kobj.ktype = &ktype_cpuidle; + kobject_set_name(&dev->kobj, "%s", "cpuidle"); + return kobject_register(&dev->kobj); +} + +/** + * cpuidle_remove_sysfs - deletes a sysfs instance on the target device + * @sysdev: the target device + */ +void cpuidle_remove_sysfs(struct sys_device *sysdev) +{ + int cpu = sysdev->id; + struct cpuidle_device *dev; + + dev = per_cpu(cpuidle_devices, cpu); + kobject_unregister(&dev->kobj); +} Index: linux-2.6.22/include/linux/cpuidle.h =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/include/linux/cpuidle.h 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,190 @@ +/* + * cpuidle.h - a generic framework for CPU idle power management + * + * (C) 2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#ifndef _LINUX_CPUIDLE_H +#define _LINUX_CPUIDLE_H + +#include +#include +#include +#include +#include + +#define CPUIDLE_STATE_MAX 8 +#define CPUIDLE_NAME_LEN 16 + +struct cpuidle_device; + + +/**************************** + * CPUIDLE DEVICE INTERFACE * + ****************************/ + +struct cpuidle_state { + char name[CPUIDLE_NAME_LEN]; + void *driver_data; + + unsigned int flags; + unsigned int exit_latency; /* in US */ + unsigned int power_usage; /* in mW */ + unsigned int target_residency; /* in US */ + + unsigned int usage; + unsigned int time; /* in US */ + + int (*enter) (struct cpuidle_device *dev, + struct cpuidle_state *state); +}; + +/* Idle State Flags */ +#define CPUIDLE_FLAG_TIME_VALID (0x01) /* is residency time measurable? */ +#define CPUIDLE_FLAG_CHECK_BM (0x02) /* BM activity will exit state */ +#define CPUIDLE_FLAG_SHALLOW (0x10) /* low latency, minimal savings */ +#define CPUIDLE_FLAG_BALANCED (0x20) /* medium latency, moderate savings */ +#define CPUIDLE_FLAG_DEEP (0x40) /* high latency, large savings */ + +#define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) + +/** + * cpuidle_get_statedata - retrieves private driver state data + * @state: the state + */ +static inline void * cpuidle_get_statedata(struct cpuidle_state *state) +{ + return state->driver_data; +} + +/** + * cpuidle_set_statedata - stores private driver state data + * @state: the state + * @data: the private data + */ +static inline void +cpuidle_set_statedata(struct cpuidle_state *state, void *data) +{ + state->driver_data = data; +} + +struct cpuidle_state_kobj { + struct cpuidle_state *state; + struct completion kobj_unregister; + struct kobject kobj; +}; + +struct cpuidle_device { + unsigned int status; + int cpu; + + int last_residency; + int state_count; + struct cpuidle_state states[CPUIDLE_STATE_MAX]; + struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; + struct cpuidle_state *last_state; + + struct list_head device_list; + struct kobject kobj; + struct completion kobj_unregister; + void *governor_data; +}; + +DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices); + +/* Device Status Flags */ +#define CPUIDLE_STATUS_DETECTED (0x1) +#define CPUIDLE_STATUS_DRIVER_ATTACHED (0x2) +#define CPUIDLE_STATUS_GOVERNOR_ATTACHED (0x4) +#define CPUIDLE_STATUS_DOIDLE (CPUIDLE_STATUS_DETECTED | \ + CPUIDLE_STATUS_DRIVER_ATTACHED | \ + CPUIDLE_STATUS_GOVERNOR_ATTACHED) + +/** + * cpuidle_get_last_residency - retrieves the last state's residency time + * @dev: the target CPU + * + * NOTE: this value is invalid if CPUIDLE_FLAG_TIME_VALID isn't set + */ +static inline int cpuidle_get_last_residency(struct cpuidle_device *dev) +{ + return dev->last_residency; +} + + +/**************************** + * CPUIDLE DRIVER INTERFACE * + ****************************/ + +struct cpuidle_driver { + char name[CPUIDLE_NAME_LEN]; + struct list_head driver_list; + + int (*init) (struct cpuidle_device *dev); + void (*exit) (struct cpuidle_device *dev); + int (*redetect) (struct cpuidle_device *dev); + + int (*bm_check) (void); + + struct module *owner; +}; + +#ifdef CONFIG_CPU_IDLE + +extern int cpuidle_register_driver(struct cpuidle_driver *drv); +extern void cpuidle_unregister_driver(struct cpuidle_driver *drv); +extern int cpuidle_force_redetect(struct cpuidle_device *dev, struct cpuidle_driver *drv); +extern int cpuidle_force_redetect_devices(struct cpuidle_driver *drv); + +#else + +static inline int cpuidle_register_driver(struct cpuidle_driver *drv) +{return 0;} +static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { } +static inline int cpuidle_force_redetect(struct cpuidle_device *dev, struct cpuidle_driver *drv) +{return 0;} +static inline int cpuidle_force_redetect_devices(struct cpuidle_driver *drv) +{return 0;} + +#endif + +/****************************** + * CPUIDLE GOVERNOR INTERFACE * + ******************************/ + +struct cpuidle_governor { + char name[CPUIDLE_NAME_LEN]; + struct list_head governor_list; + unsigned int rating; + + int (*init) (struct cpuidle_device *dev); + void (*exit) (struct cpuidle_device *dev); + void (*scan) (struct cpuidle_device *dev); + + int (*select) (struct cpuidle_device *dev); + void (*reflect) (struct cpuidle_device *dev); + + struct module *owner; +}; + +#ifdef CONFIG_CPU_IDLE + +extern int cpuidle_register_governor(struct cpuidle_governor *gov); +extern void cpuidle_unregister_governor(struct cpuidle_governor *gov); +extern int cpuidle_get_bm_activity(void); + +#else + +static inline int cpuidle_register_governor(struct cpuidle_governor *gov) +{return 0;} +static inline void cpuidle_unregister_governor(struct cpuidle_governor *gov) { } +static inline int cpuidle_get_bm_activity(void) +{return 0;} + +#endif + +#endif /* _LINUX_CPUIDLE_H */ Index: linux-2.6.22/drivers/acpi/processor_idle.c =================================================================== --- linux-2.6.22.orig/drivers/acpi/processor_idle.c 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/drivers/acpi/processor_idle.c 2007-07-15 17:13:44.000000000 +0200 @@ -40,6 +40,7 @@ #include /* need_resched() */ #include #include +#include /* * Include the apic definitions for x86 to have the APIC timer related defines @@ -62,25 +63,34 @@ #define _COMPONENT ACPI_PROCESSOR_COMPONENT ACPI_MODULE_NAME("processor_idle"); #define ACPI_PROCESSOR_FILE_POWER "power" -#define US_TO_PM_TIMER_TICKS(t) ((t * (PM_TIMER_FREQUENCY/1000)) / 1000) -#define C2_OVERHEAD 4 /* 1us (3.579 ticks per us) */ -#define C3_OVERHEAD 4 /* 1us (3.579 ticks per us) */ -static void (*pm_idle_save) (void) __read_mostly; -module_param(max_cstate, uint, 0644); +#define PM_TIMER_TICKS_TO_US(p) (((p) * 1000)/(PM_TIMER_FREQUENCY/1000)) +#define C2_OVERHEAD 1 /* 1us */ +#define C3_OVERHEAD 1 /* 1us */ + +void acpi_max_cstate_changed(void) +{ + /* Driver will reset devices' max cstate limit */ + cpuidle_force_redetect_devices(&acpi_idle_driver); +} + +static int change_max_cstate(const char *val, struct kernel_param *kp) +{ + int max; + + max = simple_strtol(val, NULL, 0); + if (!max) + return -EINVAL; + max_cstate = max; + if (acpi_do_set_cstate_limit) + acpi_do_set_cstate_limit(); + return 0; +} + +module_param_call(max_cstate, change_max_cstate, param_get_uint, &max_cstate, 0644); static unsigned int nocst __read_mostly; module_param(nocst, uint, 0000); -/* - * bm_history -- bit-mask with a bit per jiffy of bus-master activity - * 1000 HZ: 0xFFFFFFFF: 32 jiffies = 32ms - * 800 HZ: 0xFFFFFFFF: 32 jiffies = 40ms - * 100 HZ: 0x0000000F: 4 jiffies = 40ms - * reduce history for more aggressive entry into C3 - */ -static unsigned int bm_history __read_mostly = - (HZ >= 800 ? 0xFFFFFFFF : ((1U << (HZ / 25)) - 1)); -module_param(bm_history, uint, 0644); /* -------------------------------------------------------------------------- Power Management -------------------------------------------------------------------------- */ @@ -166,88 +176,6 @@ static struct dmi_system_id __cpuinitdat {}, }; -static inline u32 ticks_elapsed(u32 t1, u32 t2) -{ - if (t2 >= t1) - return (t2 - t1); - else if (!(acpi_gbl_FADT.flags & ACPI_FADT_32BIT_TIMER)) - return (((0x00FFFFFF - t1) + t2) & 0x00FFFFFF); - else - return ((0xFFFFFFFF - t1) + t2); -} - -static void -acpi_processor_power_activate(struct acpi_processor *pr, - struct acpi_processor_cx *new) -{ - struct acpi_processor_cx *old; - - if (!pr || !new) - return; - - old = pr->power.state; - - if (old) - old->promotion.count = 0; - new->demotion.count = 0; - - /* Cleanup from old state. */ - if (old) { - switch (old->type) { - case ACPI_STATE_C3: - /* Disable bus master reload */ - if (new->type != ACPI_STATE_C3 && pr->flags.bm_check) - acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0); - break; - } - } - - /* Prepare to use new state. */ - switch (new->type) { - case ACPI_STATE_C3: - /* Enable bus master reload */ - if (old->type != ACPI_STATE_C3 && pr->flags.bm_check) - acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 1); - break; - } - - pr->power.state = new; - - return; -} - -static void acpi_safe_halt(void) -{ - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - if (!need_resched()) - safe_halt(); - current_thread_info()->status |= TS_POLLING; -} - -static atomic_t c3_cpu_count; - -/* Common C-state entry for C2, C3, .. */ -static void acpi_cstate_enter(struct acpi_processor_cx *cstate) -{ - if (cstate->space_id == ACPI_CSTATE_FFH) { - /* Call into architectural FFH based C-state */ - acpi_processor_ffh_cstate_enter(cstate); - } else { - int unused; - /* IO port based C-state */ - inb(cstate->address); - /* Dummy wait op - must do something useless after P_LVL2 read - because chipsets cannot guarantee that STPCLK# signal - gets asserted in time to freeze execution properly. */ - unused = inl(acpi_gbl_FADT.xpm_timer_block.address); - } -} - #ifdef ARCH_APICTIMER_STOPS_ON_C3 /* @@ -323,378 +251,6 @@ static void acpi_state_timer_broadcast(s } #endif - -static void acpi_processor_idle(void) -{ - struct acpi_processor *pr = NULL; - struct acpi_processor_cx *cx = NULL; - struct acpi_processor_cx *next_state = NULL; - int sleep_ticks = 0; - u32 t1, t2 = 0; - - /* - * Interrupts must be disabled during bus mastering calculations and - * for C2/C3 transitions. - */ - local_irq_disable(); - - pr = processors[smp_processor_id()]; - if (!pr) { - local_irq_enable(); - return; - } - - /* - * Check whether we truly need to go idle, or should - * reschedule: - */ - if (unlikely(need_resched())) { - local_irq_enable(); - return; - } - - cx = pr->power.state; - if (!cx) { - if (pm_idle_save) - pm_idle_save(); - else - acpi_safe_halt(); - return; - } - - /* - * Check BM Activity - * ----------------- - * Check for bus mastering activity (if required), record, and check - * for demotion. - */ - if (pr->flags.bm_check) { - u32 bm_status = 0; - unsigned long diff = jiffies - pr->power.bm_check_timestamp; - - if (diff > 31) - diff = 31; - - pr->power.bm_activity <<= diff; - - acpi_get_register(ACPI_BITREG_BUS_MASTER_STATUS, &bm_status); - if (bm_status) { - pr->power.bm_activity |= 0x1; - acpi_set_register(ACPI_BITREG_BUS_MASTER_STATUS, 1); - } - /* - * PIIX4 Erratum #18: Note that BM_STS doesn't always reflect - * the true state of bus mastering activity; forcing us to - * manually check the BMIDEA bit of each IDE channel. - */ - else if (errata.piix4.bmisx) { - if ((inb_p(errata.piix4.bmisx + 0x02) & 0x01) - || (inb_p(errata.piix4.bmisx + 0x0A) & 0x01)) - pr->power.bm_activity |= 0x1; - } - - pr->power.bm_check_timestamp = jiffies; - - /* - * If bus mastering is or was active this jiffy, demote - * to avoid a faulty transition. Note that the processor - * won't enter a low-power state during this call (to this - * function) but should upon the next. - * - * TBD: A better policy might be to fallback to the demotion - * state (use it for this quantum only) istead of - * demoting -- and rely on duration as our sole demotion - * qualification. This may, however, introduce DMA - * issues (e.g. floppy DMA transfer overrun/underrun). - */ - if ((pr->power.bm_activity & 0x1) && - cx->demotion.threshold.bm) { - local_irq_enable(); - next_state = cx->demotion.state; - goto end; - } - } - -#ifdef CONFIG_HOTPLUG_CPU - /* - * Check for P_LVL2_UP flag before entering C2 and above on - * an SMP system. We do it here instead of doing it at _CST/P_LVL - * detection phase, to work cleanly with logical CPU hotplug. - */ - if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) && - !pr->flags.has_cst && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) - cx = &pr->power.states[ACPI_STATE_C1]; -#endif - - /* - * Sleep: - * ------ - * Invoke the current Cx state to put the processor to sleep. - */ - if (cx->type == ACPI_STATE_C2 || cx->type == ACPI_STATE_C3) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - if (need_resched()) { - current_thread_info()->status |= TS_POLLING; - local_irq_enable(); - return; - } - } - - switch (cx->type) { - - case ACPI_STATE_C1: - /* - * Invoke C1. - * Use the appropriate idle routine, the one that would - * be used without acpi C-states. - */ - if (pm_idle_save) - pm_idle_save(); - else - acpi_safe_halt(); - - /* - * TBD: Can't get time duration while in C1, as resumes - * go to an ISR rather than here. Need to instrument - * base interrupt handler. - */ - sleep_ticks = 0xFFFFFFFF; - break; - - case ACPI_STATE_C2: - /* Get start time (ticks) */ - t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); - /* Invoke C2 */ - acpi_state_timer_broadcast(pr, cx, 1); - acpi_cstate_enter(cx); - /* Get end time (ticks) */ - t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); - -#ifdef CONFIG_GENERIC_TIME - /* TSC halts in C2, so notify users */ - mark_tsc_unstable("possible TSC halt in C2"); -#endif - /* Re-enable interrupts */ - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - /* Compute time (ticks) that we were actually asleep */ - sleep_ticks = - ticks_elapsed(t1, t2) - cx->latency_ticks - C2_OVERHEAD; - acpi_state_timer_broadcast(pr, cx, 0); - break; - - case ACPI_STATE_C3: - - if (pr->flags.bm_check) { - if (atomic_inc_return(&c3_cpu_count) == - num_online_cpus()) { - /* - * All CPUs are trying to go to C3 - * Disable bus master arbitration - */ - acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1); - } - } else { - /* SMP with no shared cache... Invalidate cache */ - ACPI_FLUSH_CPU_CACHE(); - } - - /* Get start time (ticks) */ - t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); - /* Invoke C3 */ - acpi_state_timer_broadcast(pr, cx, 1); - acpi_cstate_enter(cx); - /* Get end time (ticks) */ - t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); - if (pr->flags.bm_check) { - /* Enable bus master arbitration */ - atomic_dec(&c3_cpu_count); - acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0); - } - -#ifdef CONFIG_GENERIC_TIME - /* TSC halts in C3, so notify users */ - mark_tsc_unstable("TSC halts in C3"); -#endif - /* Re-enable interrupts */ - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - /* Compute time (ticks) that we were actually asleep */ - sleep_ticks = - ticks_elapsed(t1, t2) - cx->latency_ticks - C3_OVERHEAD; - acpi_state_timer_broadcast(pr, cx, 0); - break; - - default: - local_irq_enable(); - return; - } - cx->usage++; - if ((cx->type != ACPI_STATE_C1) && (sleep_ticks > 0)) - cx->time += sleep_ticks; - - next_state = pr->power.state; - -#ifdef CONFIG_HOTPLUG_CPU - /* Don't do promotion/demotion */ - if ((cx->type == ACPI_STATE_C1) && (num_online_cpus() > 1) && - !pr->flags.has_cst && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) { - next_state = cx; - goto end; - } -#endif - - /* - * Promotion? - * ---------- - * Track the number of longs (time asleep is greater than threshold) - * and promote when the count threshold is reached. Note that bus - * mastering activity may prevent promotions. - * Do not promote above max_cstate. - */ - if (cx->promotion.state && - ((cx->promotion.state - pr->power.states) <= max_cstate)) { - if (sleep_ticks > cx->promotion.threshold.ticks && - cx->promotion.state->latency <= system_latency_constraint()) { - cx->promotion.count++; - cx->demotion.count = 0; - if (cx->promotion.count >= - cx->promotion.threshold.count) { - if (pr->flags.bm_check) { - if (! - (pr->power.bm_activity & cx-> - promotion.threshold.bm)) { - next_state = - cx->promotion.state; - goto end; - } - } else { - next_state = cx->promotion.state; - goto end; - } - } - } - } - - /* - * Demotion? - * --------- - * Track the number of shorts (time asleep is less than time threshold) - * and demote when the usage threshold is reached. - */ - if (cx->demotion.state) { - if (sleep_ticks < cx->demotion.threshold.ticks) { - cx->demotion.count++; - cx->promotion.count = 0; - if (cx->demotion.count >= cx->demotion.threshold.count) { - next_state = cx->demotion.state; - goto end; - } - } - } - - end: - /* - * Demote if current state exceeds max_cstate - * or if the latency of the current state is unacceptable - */ - if ((pr->power.state - pr->power.states) > max_cstate || - pr->power.state->latency > system_latency_constraint()) { - if (cx->demotion.state) - next_state = cx->demotion.state; - } - - /* - * New Cx State? - * ------------- - * If we're going to start using a new Cx state we must clean up - * from the previous and prepare to use the new. - */ - if (next_state != pr->power.state) - acpi_processor_power_activate(pr, next_state); -} - -static int acpi_processor_set_power_policy(struct acpi_processor *pr) -{ - unsigned int i; - unsigned int state_is_set = 0; - struct acpi_processor_cx *lower = NULL; - struct acpi_processor_cx *higher = NULL; - struct acpi_processor_cx *cx; - - - if (!pr) - return -EINVAL; - - /* - * This function sets the default Cx state policy (OS idle handler). - * Our scheme is to promote quickly to C2 but more conservatively - * to C3. We're favoring C2 for its characteristics of low latency - * (quick response), good power savings, and ability to allow bus - * mastering activity. Note that the Cx state policy is completely - * customizable and can be altered dynamically. - */ - - /* startup state */ - for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) { - cx = &pr->power.states[i]; - if (!cx->valid) - continue; - - if (!state_is_set) - pr->power.state = cx; - state_is_set++; - break; - } - - if (!state_is_set) - return -ENODEV; - - /* demotion */ - for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) { - cx = &pr->power.states[i]; - if (!cx->valid) - continue; - - if (lower) { - cx->demotion.state = lower; - cx->demotion.threshold.ticks = cx->latency_ticks; - cx->demotion.threshold.count = 1; - if (cx->type == ACPI_STATE_C3) - cx->demotion.threshold.bm = bm_history; - } - - lower = cx; - } - - /* promotion */ - for (i = (ACPI_PROCESSOR_MAX_POWER - 1); i > 0; i--) { - cx = &pr->power.states[i]; - if (!cx->valid) - continue; - - if (higher) { - cx->promotion.state = higher; - cx->promotion.threshold.ticks = cx->latency_ticks; - if (cx->type >= ACPI_STATE_C2) - cx->promotion.threshold.count = 4; - else - cx->promotion.threshold.count = 10; - if (higher->type == ACPI_STATE_C3) - cx->promotion.threshold.bm = bm_history; - } - - higher = cx; - } - - return 0; -} - static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr) { @@ -912,7 +468,7 @@ static void acpi_processor_power_verify_ * Normalize the C2 latency to expidite policy */ cx->valid = 1; - cx->latency_ticks = US_TO_PM_TIMER_TICKS(cx->latency); + cx->latency_ticks = cx->latency; return; } @@ -986,7 +542,7 @@ static void acpi_processor_power_verify_ * use this in our C3 policy */ cx->valid = 1; - cx->latency_ticks = US_TO_PM_TIMER_TICKS(cx->latency); + cx->latency_ticks = cx->latency; return; } @@ -1052,18 +608,6 @@ static int acpi_processor_get_power_info pr->power.count = acpi_processor_power_verify(pr); /* - * Set Default Policy - * ------------------ - * Now that we know which states are supported, set the default - * policy. Note that this policy can be changed dynamically - * (e.g. encourage deeper sleeps to conserve battery life when - * not on AC). - */ - result = acpi_processor_set_power_policy(pr); - if (result) - return result; - - /* * if one state of type C2 or C3 is available, mark this * CPU as being "idle manageable" */ @@ -1080,9 +624,6 @@ static int acpi_processor_get_power_info int acpi_processor_cst_has_changed(struct acpi_processor *pr) { - int result = 0; - - if (!pr) return -EINVAL; @@ -1093,16 +634,9 @@ int acpi_processor_cst_has_changed(struc if (!pr->flags.power_setup_done) return -ENODEV; - /* Fall back to the default idle loop */ - pm_idle = pm_idle_save; - synchronize_sched(); /* Relies on interrupts forcing exit from idle. */ - - pr->flags.power = 0; - result = acpi_processor_get_power_info(pr); - if ((pr->flags.power == 1) && (pr->flags.power_setup_done)) - pm_idle = acpi_processor_idle; - - return result; + acpi_processor_get_power_info(pr); + return cpuidle_force_redetect(per_cpu(cpuidle_devices, pr->id), + &acpi_idle_driver); } /* proc interface */ @@ -1188,30 +722,6 @@ static const struct file_operations acpi .release = single_release, }; -#ifdef CONFIG_SMP -static void smp_callback(void *v) -{ - /* we already woke the CPU up, nothing more to do */ -} - -/* - * This function gets called when a part of the kernel has a new latency - * requirement. This means we need to get all processors out of their C-state, - * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that - * wakes them all right up. - */ -static int acpi_processor_latency_notify(struct notifier_block *b, - unsigned long l, void *v) -{ - smp_call_function(smp_callback, NULL, 0, 1); - return NOTIFY_OK; -} - -static struct notifier_block acpi_processor_latency_notifier = { - .notifier_call = acpi_processor_latency_notify, -}; -#endif - int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, struct acpi_device *device) { @@ -1228,9 +738,6 @@ int __cpuinit acpi_processor_power_init( "ACPI: processor limited to max C-state %d\n", max_cstate); first_run++; -#ifdef CONFIG_SMP - register_latency_notifier(&acpi_processor_latency_notifier); -#endif } if (!pr) @@ -1247,6 +754,7 @@ int __cpuinit acpi_processor_power_init( acpi_processor_get_power_info(pr); + /* * Install the idle handler if processor power management is supported. * Note that we use previously set idle handler will be used on @@ -1259,11 +767,6 @@ int __cpuinit acpi_processor_power_init( printk(" C%d[C%d]", i, pr->power.states[i].type); printk(")\n"); - - if (pr->id == 0) { - pm_idle_save = pm_idle; - pm_idle = acpi_processor_idle; - } } /* 'power' [R] */ @@ -1291,21 +794,344 @@ int acpi_processor_power_exit(struct acp if (acpi_device_dir(device)) remove_proc_entry(ACPI_PROCESSOR_FILE_POWER, acpi_device_dir(device)); + return 0; +} - /* Unregister the idle handler when processor #0 is removed. */ - if (pr->id == 0) { - pm_idle = pm_idle_save; +/** + * ticks_elapsed - a helper function that determines how many ticks (in US) + * have elapsed between two PM Timer timestamps + * @t1: the start time + * @t2: the end time + */ +static inline u32 ticks_elapsed_in_us(u32 t1, u32 t2) +{ + if (t2 >= t1) + return PM_TIMER_TICKS_TO_US(t2 - t1); + else if (!(acpi_gbl_FADT.flags & ACPI_FADT_32BIT_TIMER)) + return PM_TIMER_TICKS_TO_US(((0x00FFFFFF - t1) + t2) & 0x00FFFFFF); + else + return PM_TIMER_TICKS_TO_US((0xFFFFFFFF - t1) + t2); +} - /* - * We are about to unload the current idle thread pm callback - * (pm_idle), Wait for all processors to update cached/local - * copies of pm_idle before proceeding. - */ - cpu_idle_wait(); -#ifdef CONFIG_SMP - unregister_latency_notifier(&acpi_processor_latency_notifier); +static inline u32 ticks_elapsed(u32 t1, u32 t2) +{ + if (t2 >= t1) + return (t2 - t1); + else if (!(acpi_gbl_FADT.flags & ACPI_FADT_32BIT_TIMER)) + return (((0x00FFFFFF - t1) + t2) & 0x00FFFFFF); + else + return ((0xFFFFFFFF - t1) + t2); +} + +/** + * acpi_idle_update_bm_rld - updates the BM_RLD bit depending on target state + * @pr: the processor + * @target: the new target state + */ +static inline void acpi_idle_update_bm_rld(struct acpi_processor *pr, + struct acpi_processor_cx *target) +{ + if (pr->flags.bm_rld_set && target->type != ACPI_STATE_C3) { + acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0); + pr->flags.bm_rld_set = 0; + } + + if (!pr->flags.bm_rld_set && target->type == ACPI_STATE_C3) { + acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 1); + pr->flags.bm_rld_set = 1; + } +} + +/** + * acpi_idle_do_entry - a helper function that does C2 and C3 type entry + * @cx: cstate data + */ +static inline void acpi_idle_do_entry(struct acpi_processor_cx *cx) +{ + if (cx->space_id == ACPI_CSTATE_FFH) { + /* Call into architectural FFH based C-state */ + acpi_processor_ffh_cstate_enter(cx); + } else { + int unused; + /* IO port based C-state */ + inb(cx->address); + /* Dummy wait op - must do something useless after P_LVL2 read + because chipsets cannot guarantee that STPCLK# signal + gets asserted in time to freeze execution properly. */ + unused = inl(acpi_gbl_FADT.xpm_timer_block.address); + } +} + +/** + * acpi_idle_enter_c1 - enters an ACPI C1 state-type + * @dev: the target CPU + * @state: the state data + * + * This is equivalent to the HALT instruction. + */ +static int acpi_idle_enter_c1(struct cpuidle_device *dev, + struct cpuidle_state *state) +{ + struct acpi_processor *pr; + struct acpi_processor_cx *cx = cpuidle_get_statedata(state); + pr = processors[smp_processor_id()]; + + if (unlikely(!pr)) + return 0; + + if (pr->flags.bm_check) + acpi_idle_update_bm_rld(pr, cx); + + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we test + * NEED_RESCHED: + */ + smp_mb(); + if (!need_resched()) + safe_halt(); + current_thread_info()->status |= TS_POLLING; + + cx->usage++; + + return 0; +} + +/** + * acpi_idle_enter_c2 - enters an ACPI C2 state-type + * @dev: the target CPU + * @state: the state data + */ +static int acpi_idle_enter_c2(struct cpuidle_device *dev, + struct cpuidle_state *state) +{ + struct acpi_processor *pr; + struct acpi_processor_cx *cx = cpuidle_get_statedata(state); + u32 t1, t2; + pr = processors[smp_processor_id()]; + + if (unlikely(!pr)) + return 0; + + if (pr->flags.bm_check) + acpi_idle_update_bm_rld(pr, cx); + + local_irq_disable(); + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we test + * NEED_RESCHED: + */ + smp_mb(); + + if (unlikely(need_resched())) { + current_thread_info()->status |= TS_POLLING; + local_irq_enable(); + return 0; + } + + t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); + acpi_state_timer_broadcast(pr, cx, 1); + acpi_idle_do_entry(cx); + t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); + +#ifdef CONFIG_GENERIC_TIME + /* TSC halts in C2, so notify users */ + mark_tsc_unstable("possible TSC halt in C2"); #endif + + local_irq_enable(); + current_thread_info()->status |= TS_POLLING; + + cx->usage++; + + acpi_state_timer_broadcast(pr, cx, 0); + cx->time += ticks_elapsed(t1, t2); + return ticks_elapsed_in_us(t1, t2); +} + +static int c3_cpu_count; +static DEFINE_SPINLOCK(c3_lock); + +/** + * acpi_idle_enter_c3 - enters an ACPI C3 state-type + * @dev: the target CPU + * @state: the state data + * + * Similar to C2 entry, except special bus master handling is needed. + */ +static int acpi_idle_enter_c3(struct cpuidle_device *dev, + struct cpuidle_state *state) +{ + struct acpi_processor *pr; + struct acpi_processor_cx *cx = cpuidle_get_statedata(state); + u32 t1, t2; + pr = processors[smp_processor_id()]; + + if (unlikely(!pr)) + return 0; + + if (pr->flags.bm_check) + acpi_idle_update_bm_rld(pr, cx); + + local_irq_disable(); + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we test + * NEED_RESCHED: + */ + smp_mb(); + + if (unlikely(need_resched())) { + current_thread_info()->status |= TS_POLLING; + local_irq_enable(); + return 0; } + /* disable bus master */ + if (pr->flags.bm_check) { + spin_lock(&c3_lock); + c3_cpu_count++; + if (c3_cpu_count == num_online_cpus()) { + /* + * All CPUs are trying to go to C3 + * Disable bus master arbitration + */ + acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1); + } + spin_unlock(&c3_lock); + } else { + /* SMP with no shared cache... Invalidate cache */ + ACPI_FLUSH_CPU_CACHE(); + } + + /* Get start time (ticks) */ + t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); + acpi_state_timer_broadcast(pr, cx, 1); + acpi_idle_do_entry(cx); + t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); + + if (pr->flags.bm_check) { + spin_lock(&c3_lock); + /* Enable bus master arbitration */ + if (c3_cpu_count == num_online_cpus()) + acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0); + c3_cpu_count--; + spin_unlock(&c3_lock); + } + +#ifdef CONFIG_GENERIC_TIME + /* TSC halts in C3, so notify users */ + mark_tsc_unstable("TSC halts in C3"); +#endif + + local_irq_enable(); + current_thread_info()->status |= TS_POLLING; + + cx->usage++; + + acpi_state_timer_broadcast(pr, cx, 0); + cx->time += ticks_elapsed(t1, t2); + return ticks_elapsed_in_us(t1, t2); +} + +/** + * acpi_idle_bm_check - checks if bus master activity was detected + */ +static int acpi_idle_bm_check(void) +{ + u32 bm_status = 0; + + acpi_get_register(ACPI_BITREG_BUS_MASTER_STATUS, &bm_status); + if (bm_status) + acpi_set_register(ACPI_BITREG_BUS_MASTER_STATUS, 1); + /* + * PIIX4 Erratum #18: Note that BM_STS doesn't always reflect + * the true state of bus mastering activity; forcing us to + * manually check the BMIDEA bit of each IDE channel. + */ + else if (errata.piix4.bmisx) { + if ((inb_p(errata.piix4.bmisx + 0x02) & 0x01) + || (inb_p(errata.piix4.bmisx + 0x0A) & 0x01)) + bm_status = 1; + } + return bm_status; +} + +/** + * acpi_idle_init - attaches the driver to a CPU + * @dev: the CPU + */ +static int acpi_idle_init(struct cpuidle_device *dev) +{ + int cpu = dev->cpu; + int i, count = 0; + struct acpi_processor_cx *cx; + struct cpuidle_state *state; + + struct acpi_processor *pr = processors[cpu]; + + if (!pr->flags.power_setup_done) + return -EINVAL; + + if (pr->flags.power == 0) { + return -EINVAL; + } + + for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) { + cx = &pr->power.states[i]; + state = &dev->states[count]; + + 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 + cpuidle_set_statedata(state, cx); + + state->exit_latency = cx->latency; + state->target_residency = cx->latency * 6; + state->power_usage = cx->power; + + state->flags = 0; + switch (cx->type) { + case ACPI_STATE_C1: + state->flags |= CPUIDLE_FLAG_SHALLOW; + state->enter = acpi_idle_enter_c1; + break; + + case ACPI_STATE_C2: + state->flags |= CPUIDLE_FLAG_BALANCED; + state->flags |= CPUIDLE_FLAG_TIME_VALID; + state->enter = acpi_idle_enter_c2; + break; + + case ACPI_STATE_C3: + state->flags |= CPUIDLE_FLAG_DEEP; + state->flags |= CPUIDLE_FLAG_TIME_VALID; + state->flags |= CPUIDLE_FLAG_CHECK_BM; + state->enter = acpi_idle_enter_c3; + break; + } + + count++; + } + + if (!count) + return -EINVAL; + + dev->state_count = count; return 0; } + +struct cpuidle_driver acpi_idle_driver = { + .name = "acpi_idle", + .init = acpi_idle_init, + .redetect = acpi_idle_init, + .bm_check = acpi_idle_bm_check, + .owner = THIS_MODULE, +}; Index: linux-2.6.22/drivers/acpi/processor_core.c =================================================================== --- linux-2.6.22.orig/drivers/acpi/processor_core.c 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/drivers/acpi/processor_core.c 2007-07-15 17:13:44.000000000 +0200 @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -1022,11 +1023,15 @@ static int __init acpi_processor_init(vo acpi_processor_ppc_init(); + cpuidle_register_driver(&acpi_idle_driver); + acpi_do_set_cstate_limit = acpi_max_cstate_changed; return 0; } static void __exit acpi_processor_exit(void) { + acpi_do_set_cstate_limit = NULL; + cpuidle_unregister_driver(&acpi_idle_driver); acpi_processor_ppc_exit(); Index: linux-2.6.22/include/acpi/processor.h =================================================================== --- linux-2.6.22.orig/include/acpi/processor.h 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/include/acpi/processor.h 2007-07-15 17:13:44.000000000 +0200 @@ -161,6 +161,7 @@ struct acpi_processor_flags { u8 bm_check:1; u8 has_cst:1; u8 power_setup_done:1; + u8 bm_rld_set:1; }; struct acpi_processor { @@ -279,6 +280,8 @@ int acpi_processor_power_init(struct acp int acpi_processor_cst_has_changed(struct acpi_processor *pr); int acpi_processor_power_exit(struct acpi_processor *pr, struct acpi_device *device); +extern struct cpuidle_driver acpi_idle_driver; +void acpi_max_cstate_changed(void); /* in processor_thermal.c */ int acpi_processor_get_limit_info(struct acpi_processor *pr); Index: linux-2.6.22/Documentation/cpuidle/core.txt =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/Documentation/cpuidle/core.txt 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,17 @@ + + Supporting multiple CPU idle levels in kernel + + cpuidle + +General Information: + +Various CPUs today support multiple idle levels that are differentiated +by varying exit latencies and power consumption during idle. +cpuidle is a generic in-kernel infrastructure that separates +idle policy (governor) from idle mechanism (driver) and provides a +standardized infrastructure to support independent development of +governors and drivers. + +cpuidle resides under drivers/cpuidle. + + Index: linux-2.6.22/Documentation/cpuidle/driver.txt =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/Documentation/cpuidle/driver.txt 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,29 @@ + + + Supporting multiple CPU idle levels in kernel + + cpuidle drivers + + + + +cpuidle driver hooks into the cpuidle infrastructure and does the +architecture/platform dependent part of CPU idle states. Driver +provides the platform idle state detection capability and also +has mechanisms in place to support actusl entry-exit into a CPU idle state. + +cpuidle driver supports capability detection for a platform using the +init and exit routines. They will be called for each online CPU, with a +percpu cpuidle_driver object and driver should fill in cpuidle_states +inside cpuidle_driver depending on the CPU capability. + +Driver can handle dynamic state changes (like battery<->AC), by calling +force_redetect interface. + +It is possible to have more than one driver registered at the same time and +user can switch between drivers using /sysfs interface (when enabled). + +Interfaces: +int cpuidle_register_driver(struct cpuidle_driver *drv); +void cpuidle_unregister_driver(struct cpuidle_driver *drv); +int cpuidle_force_redetect(struct cpuidle_device *dev); Index: linux-2.6.22/Documentation/cpuidle/governor.txt =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/Documentation/cpuidle/governor.txt 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,28 @@ + + + + Supporting multiple CPU idle levels in kernel + + cpuidle governors + + + + +cpuidle governor is policy routine that decides what idle state to enter at +any given time. cpuidle core uses different callbacks to governor while +handling idle entry. +* select_state() callback where governor can determine next idle state to enter +* prepare_idle() callback is called before entering an idle state +* scan() callback is called after a driver forces redetection of the states + +More than one governor can be registered at the same time and +user can switch between drivers using /sysfs interface (when supported). + +More than one governor part is supported for developers to easily experiment +with different governors. By default, most optimal governor based on your +kernel configuration and platform will be selected by cpuidle. + +Interfaces: +int cpuidle_register_governor(struct cpuidle_governor *gov); +void cpuidle_unregister_governor(struct cpuidle_governor *gov); + Index: linux-2.6.22/Documentation/cpuidle/sysfs.txt =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/Documentation/cpuidle/sysfs.txt 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,35 @@ + + + Supporting multiple CPU idle levels in kernel + + cpuidle sysfs + +System global cpuidle related information and tunables are under +/sys/devices/system/cpu/cpuidle + +The current interfaces in this directory has self-explanatory names: +* current_driver_ro +* current_governor_ro + +With cpuidle_sysfs_switch boot option (meant for developer testing) +following objects are visible instead. +* available_drivers +* available_governors +* current_driver +* current_governor +In this case user can switch the driver, governor at run time by writing +onto current_driver and current_governor. + + +Per logical CPU specific cpuidle information are under +/sys/devices/system/cpu/cpuX/cpuidle +for each online cpu X + +Under this percpu directory, there is a directory for each idle state supported +by the driver, which in turn has +* latency : Latency to exit out of this idle state (in microseconds) +* power : Power consumed while in this idle state (in milliwatts) +* time : Total time spent in this idle state (in microseconds) +* usage : Number of times this state was entered (count) + + Index: linux-2.6.22/drivers/acpi/osl.c =================================================================== --- linux-2.6.22.orig/drivers/acpi/osl.c 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/drivers/acpi/osl.c 2007-07-15 17:13:44.000000000 +0200 @@ -1056,6 +1056,17 @@ unsigned int max_cstate = ACPI_PROCESSOR EXPORT_SYMBOL(max_cstate); +void (*acpi_do_set_cstate_limit)(void); +EXPORT_SYMBOL(acpi_do_set_cstate_limit); + +void acpi_set_cstate_limit(unsigned int new_limit) +{ + max_cstate = new_limit; + if (acpi_do_set_cstate_limit) + acpi_do_set_cstate_limit(); +} +EXPORT_SYMBOL(acpi_set_cstate_limit); + /* * Acquire a spinlock. * Index: linux-2.6.22/include/linux/acpi.h =================================================================== --- linux-2.6.22.orig/include/linux/acpi.h 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/include/linux/acpi.h 2007-07-15 17:13:44.000000000 +0200 @@ -206,11 +206,8 @@ static inline unsigned int acpi_get_csta { return max_cstate; } -static inline void acpi_set_cstate_limit(unsigned int new_limit) -{ - max_cstate = new_limit; - return; -} +extern void (*acpi_do_set_cstate_limit)(void); +extern void acpi_set_cstate_limit(unsigned int new_limit); #else static inline unsigned int acpi_get_cstate_limit(void) { return 0; } static inline void acpi_set_cstate_limit(unsigned int new_limit) { return; } Index: linux-2.6.22/arch/i386/kernel/process.c =================================================================== --- linux-2.6.22.orig/arch/i386/kernel/process.c 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/arch/i386/kernel/process.c 2007-07-15 17:13:44.000000000 +0200 @@ -179,13 +179,14 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(); while (!need_resched()) { void (*idle)(void); if (__get_cpu_var(cpu_idle_state)) __get_cpu_var(cpu_idle_state) = 0; + tick_nohz_stop_sched_tick(); + check_pgt_cache(); rmb(); idle = pm_idle; Index: linux-2.6.22/include/linux/tick.h =================================================================== --- linux-2.6.22.orig/include/linux/tick.h 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/include/linux/tick.h 2007-07-15 17:13:44.000000000 +0200 @@ -40,6 +40,7 @@ enum tick_nohz_mode { * @idle_sleeps: Number of idle calls, where the sched tick was stopped * @idle_entrytime: Time when the idle call was entered * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped + * @sleep_length: Duration of the current idle sleep */ struct tick_sched { struct hrtimer sched_timer; @@ -52,6 +53,7 @@ struct tick_sched { unsigned long idle_sleeps; ktime_t idle_entrytime; ktime_t idle_sleeptime; + ktime_t sleep_length; unsigned long last_jiffies; unsigned long next_jiffies; ktime_t idle_expires; @@ -100,10 +102,18 @@ static inline int tick_check_oneshot_cha extern void tick_nohz_stop_sched_tick(void); extern void tick_nohz_restart_sched_tick(void); extern void tick_nohz_update_jiffies(void); +extern ktime_t tick_nohz_get_sleep_length(void); +extern unsigned long tick_nohz_get_idle_jiffies(void); # else static inline void tick_nohz_stop_sched_tick(void) { } static inline void tick_nohz_restart_sched_tick(void) { } static inline void tick_nohz_update_jiffies(void) { } +static inline ktime_t tick_nohz_get_sleep_length(void) +{ + ktime_t len = { .tv64 = NSEC_PER_SEC/HZ }; + + return len; +} # endif /* !NO_HZ */ #endif Index: linux-2.6.22/kernel/softirq.c =================================================================== --- linux-2.6.22.orig/kernel/softirq.c 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/kernel/softirq.c 2007-07-15 17:13:44.000000000 +0200 @@ -303,11 +303,6 @@ void irq_exit(void) if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); -#ifdef CONFIG_NO_HZ - /* Make sure that timer wheel updates are propagated */ - if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched()) - tick_nohz_stop_sched_tick(); -#endif preempt_enable_no_resched(); } Index: linux-2.6.22/kernel/time/tick-sched.c =================================================================== --- linux-2.6.22.orig/kernel/time/tick-sched.c 2007-07-15 17:13:44.000000000 +0200 +++ linux-2.6.22/kernel/time/tick-sched.c 2007-07-15 17:13:44.000000000 +0200 @@ -153,6 +153,7 @@ void tick_nohz_stop_sched_tick(void) unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags; struct tick_sched *ts; ktime_t last_update, expires, now, delta; + struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; int cpu; local_irq_save(flags); @@ -290,11 +291,36 @@ void tick_nohz_stop_sched_tick(void) out: ts->next_jiffies = next_jiffies; ts->last_jiffies = last_jiffies; + ts->sleep_length = ktime_sub(dev->next_event, now); end: local_irq_restore(flags); } /** + * tick_nohz_get_sleep_length - return the length of the current sleep + * + * Called from power state control code with interrupts disabled + */ +ktime_t tick_nohz_get_sleep_length(void) +{ + struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); + + return ts->sleep_length; +} +EXPORT_SYMBOL_GPL(tick_nohz_get_sleep_length); + +/** + * tick_nohz_get_idle_jiffies - returns the current idle jiffie count + */ +unsigned long tick_nohz_get_idle_jiffies(void) +{ + struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); + + return ts->idle_jiffies; +} +EXPORT_SYMBOL_GPL(tick_nohz_get_idle_jiffies); + +/** * nohz_restart_sched_tick - restart the idle tick from the idle task * * Restart the idle tick when the CPU is woken up from idle Index: linux-2.6.22/drivers/cpuidle/governors/menu.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.22/drivers/cpuidle/governors/menu.c 2007-07-15 17:13:44.000000000 +0200 @@ -0,0 +1,181 @@ +/* + * menu.c - the menu idle governor + * + * Copyright (C) 2006-2007 Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define BM_HOLDOFF 20000 /* 20 ms */ +#define DEMOTION_THRESHOLD 5 +#define DEMOTION_TIMEOUT_MULTIPLIER 1000 + +struct menu_device { + int last_state_idx; + + int deepest_break_state; + struct timespec break_expire_time_ts; + int break_last_cnt; + + int deepest_bm_state; + int bm_elapsed_us; + int bm_holdoff_us; +}; + +static DEFINE_PER_CPU(struct menu_device, menu_devices); + +/** + * menu_select - selects the next idle state to enter + * @dev: the CPU + */ +static int menu_select(struct cpuidle_device *dev) +{ + struct menu_device *data = &__get_cpu_var(menu_devices); + int i, expected_us, max_state = dev->state_count; + + /* discard BM history because it is sticky */ + cpuidle_get_bm_activity(); + + /* determine the expected residency time */ + expected_us = (s32) ktime_to_ns(tick_nohz_get_sleep_length()) / 1000; + + /* determine the maximum state compatible with current BM status */ + if (cpuidle_get_bm_activity()) + data->bm_elapsed_us = 0; + if (data->bm_elapsed_us <= data->bm_holdoff_us) + max_state = data->deepest_bm_state + 1; + + /* determine the maximum state compatible with recent idle breaks */ + if (data->deepest_break_state >= 0) { + struct timespec now; + ktime_get_ts(&now); + if (timespec_compare(&data->break_expire_time_ts, &now) > 0) { + max_state = min(max_state, + data->deepest_break_state + 1); + } else { + data->deepest_break_state = -1; + } + } + + /* find the deepest idle state that satisfies our constraints */ + for (i = 1; i < max_state; i++) { + struct cpuidle_state *s = &dev->states[i]; + + if (s->target_residency > expected_us) + break; + + if (s->exit_latency > system_latency_constraint()) + break; + } + + if (data->last_state_idx != i - 1) + data->break_last_cnt = 0; + + data->last_state_idx = i - 1; + return i - 1; +} + +/** + * menu_reflect - attempts to guess what happened after entry + * @dev: the CPU + * + * NOTE: it's important to be fast here because this operation will add to + * the overall exit latency. + */ +static void menu_reflect(struct cpuidle_device *dev) +{ + struct menu_device *data = &__get_cpu_var(menu_devices); + int last_idx = data->last_state_idx; + int measured_us = cpuidle_get_last_residency(dev); + struct cpuidle_state *target = &dev->states[last_idx]; + + /* + * Ugh, this idle state doesn't support residency measurements, so we + * are basically lost in the dark. As a compromise, assume we slept + * for one full standard timer tick. However, be aware that this + * could potentially result in a suboptimal state transition. + */ + if (!(target->flags & CPUIDLE_FLAG_TIME_VALID)) + measured_us = USEC_PER_SEC / HZ; + + data->bm_elapsed_us += measured_us; + + if (data->last_state_idx == 0) + return; + + /* + * Did something other than the timer interrupt + * cause an early break event? + */ + if (unlikely(measured_us < target->target_residency)) { + if (data->break_last_cnt > DEMOTION_THRESHOLD) { + data->deepest_break_state = data->last_state_idx - 1; + ktime_get_ts(&data->break_expire_time_ts); + timespec_add_ns(&data->break_expire_time_ts, + target->target_residency * + DEMOTION_TIMEOUT_MULTIPLIER); + } else { + data->break_last_cnt++; + } + } else { + if (data->break_last_cnt > 0) + data->break_last_cnt--; + } +} + +/** + * menu_scan_device - scans a CPU's states and does setup + * @dev: the CPU + */ +static void menu_scan_device(struct cpuidle_device *dev) +{ + struct menu_device *data = &per_cpu(menu_devices, dev->cpu); + int i; + + data->last_state_idx = 0; + data->bm_elapsed_us = 0; + data->bm_holdoff_us = BM_HOLDOFF; + data->deepest_break_state = -1; + + for (i = 1; i < dev->state_count; i++) + if (dev->states[i].flags & CPUIDLE_FLAG_CHECK_BM) + break; + data->deepest_bm_state = i - 1; +} + +struct cpuidle_governor menu_governor = { + .name = "menu", + .rating = 20, + .scan = menu_scan_device, + .select = menu_select, + .reflect = menu_reflect, + .owner = THIS_MODULE, +}; + +/** + * init_menu - initializes the governor + */ +static int __init init_menu(void) +{ + return cpuidle_register_governor(&menu_governor); +} + +/** + * exit_menu - exits the governor + */ +static void __exit exit_menu(void) +{ + cpuidle_unregister_governor(&menu_governor); +} + +MODULE_LICENSE("GPL"); +module_init(init_menu); +module_exit(exit_menu);