diff options
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/Makefile | 1 | ||||
| -rw-r--r-- | drivers/acpi/osl.c | 8 | ||||
| -rw-r--r-- | drivers/acpi/processor_core.c | 22 | ||||
| -rw-r--r-- | drivers/acpi/processor_idle.c | 482 | ||||
| -rw-r--r-- | drivers/cpuidle/Kconfig | 20 | ||||
| -rw-r--r-- | drivers/cpuidle/Makefile | 5 | ||||
| -rw-r--r-- | drivers/cpuidle/cpuidle.c | 295 | ||||
| -rw-r--r-- | drivers/cpuidle/cpuidle.h | 33 | ||||
| -rw-r--r-- | drivers/cpuidle/driver.c | 56 | ||||
| -rw-r--r-- | drivers/cpuidle/governor.c | 141 | ||||
| -rw-r--r-- | drivers/cpuidle/governors/Makefile | 6 | ||||
| -rw-r--r-- | drivers/cpuidle/governors/ladder.c | 166 | ||||
| -rw-r--r-- | drivers/cpuidle/governors/menu.c | 137 | ||||
| -rw-r--r-- | drivers/cpuidle/sysfs.c | 361 | ||||
| -rw-r--r-- | drivers/net/wireless/ipw2100.c | 29 | ||||
| -rw-r--r-- | drivers/net/wireless/ipw2100.h | 2 |
16 files changed, 1681 insertions, 83 deletions
diff --git a/drivers/Makefile b/drivers/Makefile index f0878b2ec55..10a9c52c910 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -76,6 +76,7 @@ obj-$(CONFIG_MCA) += mca/ obj-$(CONFIG_EISA) += eisa/ obj-$(CONFIG_LGUEST_GUEST) += lguest/ obj-$(CONFIG_CPU_FREQ) += cpufreq/ +obj-$(CONFIG_CPU_IDLE) += cpuidle/ obj-$(CONFIG_MMC) += mmc/ obj-$(CONFIG_NEW_LEDS) += leds/ obj-$(CONFIG_INFINIBAND) += infiniband/ diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 12c09fafce9..5d14d4f10b1 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -1043,14 +1043,6 @@ static int __init acpi_wake_gpes_always_on_setup(char *str) __setup("acpi_wake_gpes_always_on", acpi_wake_gpes_always_on_setup); /* - * max_cstate is defined in the base kernel so modules can - * change it w/o depending on the state of the processor module. - */ -unsigned int max_cstate = ACPI_PROCESSOR_MAX_POWER; - -EXPORT_SYMBOL(max_cstate); - -/* * Acquire a spinlock. * * handle is a pointer to the spinlock_t. diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 9f11dc296cd..a7351084f2f 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -44,6 +44,7 @@ #include <linux/seq_file.h> #include <linux/dmi.h> #include <linux/moduleparam.h> +#include <linux/cpuidle.h> #include <asm/io.h> #include <asm/system.h> @@ -1049,11 +1050,13 @@ static int __init acpi_processor_init(void) return -ENOMEM; acpi_processor_dir->owner = THIS_MODULE; + result = cpuidle_register_driver(&acpi_idle_driver); + if (result < 0) + goto out_proc; + result = acpi_bus_register_driver(&acpi_processor_driver); - if (result < 0) { - remove_proc_entry(ACPI_PROCESSOR_CLASS, acpi_root_dir); - return result; - } + if (result < 0) + goto out_cpuidle; acpi_processor_install_hotplug_notify(); @@ -1062,11 +1065,18 @@ static int __init acpi_processor_init(void) acpi_processor_ppc_init(); return 0; + +out_cpuidle: + cpuidle_unregister_driver(&acpi_idle_driver); + +out_proc: + remove_proc_entry(ACPI_PROCESSOR_CLASS, acpi_root_dir); + + return result; } static void __exit acpi_processor_exit(void) { - acpi_processor_ppc_exit(); acpi_thermal_cpufreq_exit(); @@ -1075,6 +1085,8 @@ static void __exit acpi_processor_exit(void) acpi_bus_unregister_driver(&acpi_processor_driver); + cpuidle_unregister_driver(&acpi_idle_driver); + remove_proc_entry(ACPI_PROCESSOR_CLASS, acpi_root_dir); return; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index f18261368e7..99da6a79085 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -40,6 +40,7 @@ #include <linux/sched.h> /* need_resched() */ #include <linux/latency.h> #include <linux/clockchips.h> +#include <linux/cpuidle.h> /* * Include the apic definitions for x86 to have the APIC timer related defines @@ -64,14 +65,22 @@ 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 PM_TIMER_TICK_NS (1000000000ULL/PM_TIMER_FREQUENCY) +#ifndef CONFIG_CPU_IDLE #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); +#else +#define C2_OVERHEAD 1 /* 1us */ +#define C3_OVERHEAD 1 /* 1us */ +#endif +#define PM_TIMER_TICKS_TO_US(p) (((p) * 1000)/(PM_TIMER_FREQUENCY/1000)) +static unsigned int max_cstate __read_mostly = ACPI_PROCESSOR_MAX_POWER; +module_param(max_cstate, uint, 0000); static unsigned int nocst __read_mostly; module_param(nocst, uint, 0000); +#ifndef CONFIG_CPU_IDLE /* * bm_history -- bit-mask with a bit per jiffy of bus-master activity * 1000 HZ: 0xFFFFFFFF: 32 jiffies = 32ms @@ -82,9 +91,10 @@ module_param(nocst, uint, 0000); static unsigned int bm_history __read_mostly = (HZ >= 800 ? 0xFFFFFFFF : ((1U << (HZ / 25)) - 1)); module_param(bm_history, uint, 0644); -/* -------------------------------------------------------------------------- - Power Management - -------------------------------------------------------------------------- */ + +static int acpi_processor_set_power_policy(struct acpi_processor *pr); + +#endif /* * IBM ThinkPad R40e crashes mysteriously when going into C2 or C3. @@ -177,6 +187,18 @@ static inline u32 ticks_elapsed(u32 t1, u32 t2) return ((0xFFFFFFFF - t1) + t2); } +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); +} + +#ifndef CONFIG_CPU_IDLE + static void acpi_processor_power_activate(struct acpi_processor *pr, struct acpi_processor_cx *new) @@ -248,6 +270,7 @@ static void acpi_cstate_enter(struct acpi_processor_cx *cstate) unused = inl(acpi_gbl_FADT.xpm_timer_block.address); } } +#endif /* !CONFIG_CPU_IDLE */ #ifdef ARCH_APICTIMER_STOPS_ON_C3 @@ -342,6 +365,7 @@ int acpi_processor_resume(struct acpi_device * device) return 0; } +#ifndef CONFIG_CPU_IDLE static void acpi_processor_idle(void) { struct acpi_processor *pr = NULL; @@ -439,7 +463,7 @@ static void acpi_processor_idle(void) * 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) && + 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 @@ -739,6 +763,7 @@ static int acpi_processor_set_power_policy(struct acpi_processor *pr) return 0; } +#endif /* !CONFIG_CPU_IDLE */ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr) { @@ -756,7 +781,7 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr) #ifndef CONFIG_HOTPLUG_CPU /* * Check for P_LVL2_UP flag before entering C2 and above on - * an SMP system. + * an SMP system. */ if ((num_online_cpus() > 1) && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) @@ -957,7 +982,12 @@ static void acpi_processor_power_verify_c2(struct acpi_processor_cx *cx) * Normalize the C2 latency to expidite policy */ cx->valid = 1; + +#ifndef CONFIG_CPU_IDLE cx->latency_ticks = US_TO_PM_TIMER_TICKS(cx->latency); +#else + cx->latency_ticks = cx->latency; +#endif return; } @@ -1037,7 +1067,12 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, * use this in our C3 policy */ cx->valid = 1; + +#ifndef CONFIG_CPU_IDLE cx->latency_ticks = US_TO_PM_TIMER_TICKS(cx->latency); +#else + cx->latency_ticks = cx->latency; +#endif return; } @@ -1102,6 +1137,7 @@ static int acpi_processor_get_power_info(struct acpi_processor *pr) pr->power.count = acpi_processor_power_verify(pr); +#ifndef CONFIG_CPU_IDLE /* * Set Default Policy * ------------------ @@ -1113,6 +1149,7 @@ static int acpi_processor_get_power_info(struct acpi_processor *pr) result = acpi_processor_set_power_policy(pr); if (result) return result; +#endif /* * if one state of type C2 or C3 is available, mark this @@ -1129,35 +1166,6 @@ static int acpi_processor_get_power_info(struct acpi_processor *pr) return 0; } -int acpi_processor_cst_has_changed(struct acpi_processor *pr) -{ - int result = 0; - - - if (!pr) - return -EINVAL; - - if (nocst) { - return -ENODEV; - } - - 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; -} - -/* proc interface */ - static int acpi_processor_power_seq_show(struct seq_file *seq, void *offset) { struct acpi_processor *pr = seq->private; @@ -1239,6 +1247,35 @@ static const struct file_operations acpi_processor_power_fops = { .release = single_release, }; +#ifndef CONFIG_CPU_IDLE + +int acpi_processor_cst_has_changed(struct acpi_processor *pr) +{ + int result = 0; + + + if (!pr) + return -EINVAL; + + if (nocst) { + return -ENODEV; + } + + 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; +} + #ifdef CONFIG_SMP static void smp_callback(void *v) { @@ -1261,7 +1298,360 @@ static int acpi_processor_latency_notify(struct notifier_block *b, static struct notifier_block acpi_processor_latency_notifier = { .notifier_call = acpi_processor_latency_notify, }; + +#endif + +#else /* CONFIG_CPU_IDLE */ + +/** + * 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_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_simple - enters an ACPI state without BM handling + * @dev: the target CPU + * @state: the state data + */ +static int acpi_idle_enter_simple(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; + } + + if (cx->type == ACPI_STATE_C3) + ACPI_FLUSH_CPU_CACHE(); + + 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 defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) + /* TSC could halt in idle, so notify users */ + mark_tsc_unstable("TSC halts in idle");; +#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_bm - enters C3 with proper BM handling + * @dev: the target CPU + * @state: the state data + * + * If BM is detected, the deepest non-C3 idle state is entered instead. + */ +static int acpi_idle_enter_bm(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; + + 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; + } + + /* + * Must be done before busmaster disable as we might need to + * access HPET ! + */ + acpi_state_timer_broadcast(pr, cx, 1); + + if (acpi_idle_bm_check()) { + cx = pr->power.bm_state; + + acpi_idle_update_bm_rld(pr, cx); + + t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); + acpi_idle_do_entry(cx); + t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); + } else { + acpi_idle_update_bm_rld(pr, cx); + + spin_lock(&c3_lock); + c3_cpu_count++; + /* Disable bus master arbitration when all CPUs are in C3 */ + if (c3_cpu_count == num_online_cpus()) + acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1); + spin_unlock(&c3_lock); + + t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); + acpi_idle_do_entry(cx); + t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); + + spin_lock(&c3_lock); + /* Re-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); + } + +#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) + /* TSC could halt in idle, so notify users */ + mark_tsc_unstable("TSC halts in idle"); +#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); +} + +struct cpuidle_driver acpi_idle_driver = { + .name = "acpi_idle", + .owner = THIS_MODULE, +}; + +/** + * acpi_processor_setup_cpuidle - prepares and configures CPUIDLE + * @pr: the ACPI processor + */ +static int acpi_processor_setup_cpuidle(struct acpi_processor *pr) +{ + int i, count = 0; + struct acpi_processor_cx *cx; + struct cpuidle_state *state; + struct cpuidle_device *dev = &pr->power.dev; + + 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); + + snprintf(state->name, CPUIDLE_NAME_LEN, "C%d", i); + 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_simple; + break; + + case ACPI_STATE_C3: + state->flags |= CPUIDLE_FLAG_DEEP; + state->flags |= CPUIDLE_FLAG_TIME_VALID; + state->flags |= CPUIDLE_FLAG_CHECK_BM; + state->enter = pr->flags.bm_check ? + acpi_idle_enter_bm : + acpi_idle_enter_simple; + break; + } + + count++; + } + + dev->state_count = count; + + if (!count) + return -EINVAL; + + /* find the deepest state that can handle active BM */ + if (pr->flags.bm_check) { + for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) + if (pr->power.states[i].type == ACPI_STATE_C3) + break; + pr->power.bm_state = &pr->power.states[i-1]; + } + + return 0; +} + +int acpi_processor_cst_has_changed(struct acpi_processor *pr) +{ + int ret; + + if (!pr) + return -EINVAL; + + if (nocst) { + return -ENODEV; + } + + if (!pr->flags.power_setup_done) + return -ENODEV; + + cpuidle_pause_and_lock(); + cpuidle_disable_device(&pr->power.dev); + acpi_processor_get_power_info(pr); + acpi_processor_setup_cpuidle(pr); + ret = cpuidle_enable_device(&pr->power.dev); + cpuidle_resume_and_unlock(); + + return ret; +} + +#endif /* CONFIG_CPU_IDLE */ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, struct acpi_device *device) @@ -1279,7 +1669,7 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, "ACPI: processor limited to max C-state %d\n", max_cstate); first_run++; -#ifdef CONFIG_SMP +#if !defined (CONFIG_CPU_IDLE) && defined (CONFIG_SMP) register_latency_notifier(&acpi_processor_latency_notifier); #endif } @@ -1297,6 +1687,7 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, } acpi_processor_get_power_info(pr); + pr->flags.power_setup_done = 1; /* * Install the idle handler if processor power management is supported. @@ -1304,6 +1695,13 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, * platforms that only support C1. */ if ((pr->flags.power) && (!boot_option_idle_override)) { +#ifdef CONFIG_CPU_IDLE + acpi_processor_setup_cpuidle(pr); + pr->power.dev.cpu = pr->id; + if (cpuidle_register_device(&pr->power.dev)) + return -EIO; +#endif + printk(KERN_INFO PREFIX "CPU%d (power states:", pr->id); for (i = 1; i <= pr->power.count; i++) if (pr->power.states[i].valid) @@ -1311,10 +1709,12 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, pr->power.states[i].type); printk(")\n"); +#ifndef CONFIG_CPU_IDLE if (pr->id == 0) { pm_idle_save = pm_idle; pm_idle = acpi_processor_idle; } +#endif } /* 'power' [R] */ @@ -1328,21 +1728,24 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, entry->owner = THIS_MODULE; } - pr->flags.power_setup_done = 1; - return 0; } int acpi_processor_power_exit(struct acpi_processor *pr, struct acpi_device *device) { - +#ifdef CONFIG_CPU_IDLE + if ((pr->flags.power) && (!boot_option_idle_override)) + cpuidle_unregister_device(&pr->power.dev); +#endif pr->flags.power_setup_done = 0; if (acpi_device_dir(device)) remove_proc_entry(ACPI_PROCESSOR_FILE_POWER, acpi_device_dir(device)); +#ifndef CONFIG_CPU_IDLE + /* Unregister the idle handler when processor #0 is removed. */ if (pr->id == 0) { pm_idle = pm_idle_save; @@ -1357,6 +1760,7 @@ int acpi_processor_power_exit(struct acpi_processor *pr, unregister_latency_notifier(&acpi_processor_latency_notifier); #endif } +#endif return 0; } diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig new file mode 100644 index 00000000000..3bed4127d4a --- /dev/null +++ b/drivers/cpuidle/Kconfig @@ -0,0 +1,20 @@ + +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. + +config CPU_IDLE_GOV_LADDER + bool + depends on CPU_IDLE + default y + +config CPU_IDLE_GOV_MENU + bool + depends on CPU_IDLE && NO_HZ + default y diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile new file mode 100644 index 00000000000..5634f88379d --- /dev/null +++ b/drivers/cpuidle/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for cpuidle. +# + +obj-y += cpuidle.o driver.o governor.o sysfs.o governors/ diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c new file mode 100644 index 00000000000..fdf4106b817 --- /dev/null +++ b/drivers/cpuidle/cpuidle.c @@ -0,0 +1,295 @@ +/* + * cpuidle.c - core cpuidle infrastructure + * + * (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Shaohua Li <shaohua.li@intel.com> + * Adam Belay <abelay@novell.com> + * + * This code is licenced under the GPL. + */ + +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/notifier.h> +#include <linux/latency.h> +#include <linux/cpu.h> +#include <linux/cpuidle.h> + +#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); + +static int enabled_devices; + +/** + * 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->enabled) { + 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 (enabled_devices && (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 (enabled_devices && (pm_idle != pm_idle_old)) { + pm_idle = pm_idle_old; + cpu_idle_wait(); + } +} + +/** + * cpuidle_pause_and_lock - temporarily disables CPUIDLE + */ +void cpuidle_pause_and_lock(void) +{ + mutex_lock(&cpuidle_lock); + cpuidle_uninstall_idle_handler(); +} + +EXPORT_SYMBOL_GPL(cpuidle_pause_and_lock); + +/** + * cpuidle_resume_and_unlock - resumes CPUIDLE operation + */ +void cpuidle_resume_and_unlock(void) +{ + cpuidle_install_idle_handler(); + mutex_unlock(&cpuidle_lock); +} + +EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock); + +/** + * cpuidle_enable_device - enables idle PM for a CPU + * @dev: the CPU + * + * This function must be called between cpuidle_pause_and_lock and + * cpuidle_resume_and_unlock when used externally. + */ +int cpuidle_enable_device(struct cpuidle_device *dev) +{ + int ret, i; + + if (dev->enabled) + return 0; + if (!cpuidle_curr_driver || !cpuidle_curr_governor) + return -EIO; + if (!dev->state_count) + return -EINVAL; + + if ((ret = cpuidle_add_state_sysfs(dev))) + return ret; + + if (cpuidle_curr_governor->enable && + (ret = cpuidle_curr_governor->enable(dev))) + goto fail_sysfs; + + for (i = 0; i < dev->state_count; i++) { + dev->states[i].usage = 0; + dev->states[i].time = 0; + } + dev->last_residency = 0; + dev->last_state = NULL; + + smp_wmb(); + + dev->enabled = 1; + + enabled_devices++; + return 0; + +fail_sysfs: + cpuidle_remove_state_sysfs(dev); + + return ret; +} + +EXPORT_SYMBOL_GPL(cpuidle_enable_device); + +/** + * cpuidle_disable_device - disables idle PM for a CPU + * @dev: the CPU + * + * This function must be called between cpuidle_pause_and_lock and + * cpuidle_resume_and_unlock when used externally. + */ +void cpuidle_disable_device(struct cpuidle_device *dev) +{ + if (!dev->enabled) + return; + if (!cpuidle_curr_driver || !cpuidle_curr_governor) + return; + + dev->enabled = 0; + + if (cpuidle_curr_governor->disable) + cpuidle_curr_governor->disable(dev); + + cpuidle_remove_state_sysfs(dev); + enabled_devices--; +} + +EXPORT_SYMBOL_GPL(cpuidle_disable_device); + +/** + * cpuidle_register_device - registers a CPU's idle PM feature + * @dev: the cpu + */ +int cpuidle_register_device(struct cpuidle_device *dev) +{ + int ret; + struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu); + + if (!sys_dev) + return -EINVAL; + if (!try_module_get(cpuidle_curr_driver->owner)) + return -EINVAL; + + init_completion(&dev->kobj_unregister); + + mutex_lock(&cpuidle_lock); + + per_cpu(cpuidle_devices, dev->cpu) = dev; + list_add(&dev->device_list, &cpuidle_detected_devices); + if ((ret = cpuidle_add_sysfs(sys_dev))) { + mutex_unlock(&cpuidle_lock); + module_put(cpuidle_curr_driver->owner); + return ret; + } + + cpuidle_enable_device(dev); + cpuidle_install_idle_handler(); + + mutex_unlock(&cpuidle_lock); + + return 0; + +} + +EXPORT_SYMBOL_GPL(cpuidle_register_device); + +/** + * cpuidle_unregister_device - unregisters a CPU's idle PM feature + * @dev: the cpu + */ +void cpuidle_unregister_device(struct cpuidle_device *dev) +{ + struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu); + + cpuidle_pause_and_lock(); + + cpuidle_disable_device(dev); + + cpuidle_remove_sysfs(sys_dev); + list_del(&dev->device_list); + wait_for_completion(&dev->kobj_unregister); + per_cpu(cpuidle_devices, dev->cpu) = NULL; + + cpuidle_resume_and_unlock(); + + module_put(cpuidle_curr_driver->owner); +} + +EXPORT_SYMBOL_GPL(cpuidle_unregister_device); + +#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; + + latency_notifier_init(&cpuidle_latency_notifier); + + return 0; +} + +core_initcal |