diff options
Diffstat (limited to 'arch')
28 files changed, 118 insertions, 350 deletions
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index c6dec5fc20aa..047d3e40e470 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -172,14 +172,9 @@ static void default_idle(void) local_irq_enable(); } -void (*pm_idle)(void) = default_idle; -EXPORT_SYMBOL(pm_idle); - /* - * The idle thread, has rather strange semantics for calling pm_idle, - * but this is what x86 does and we need to do the same, so that - * things like cpuidle get called in the same way. The only difference - * is that we always respect 'hlt_counter' to prevent low power idle. + * The idle thread. + * We always respect 'hlt_counter' to prevent low power idle. */ void cpu_idle(void) { @@ -210,10 +205,10 @@ void cpu_idle(void) } else if (!need_resched()) { stop_critical_timings(); if (cpuidle_idle_call()) - pm_idle(); + default_idle(); start_critical_timings(); /* - * pm_idle functions must always + * default_idle functions must always * return with IRQs enabled. */ WARN_ON(irqs_disabled()); diff --git a/arch/arm/mach-davinci/cpuidle.c b/arch/arm/mach-davinci/cpuidle.c index 9107691adbdb..5ac9e9384b15 100644 --- a/arch/arm/mach-davinci/cpuidle.c +++ b/arch/arm/mach-davinci/cpuidle.c @@ -25,35 +25,44 @@ #define DAVINCI_CPUIDLE_MAX_STATES 2 -struct davinci_ops { - void (*enter) (u32 flags); - void (*exit) (u32 flags); - u32 flags; -}; +static DEFINE_PER_CPU(struct cpuidle_device, davinci_cpuidle_device); +static void __iomem *ddr2_reg_base; +static bool ddr2_pdown; + +static void davinci_save_ddr_power(int enter, bool pdown) +{ + u32 val; + + val = __raw_readl(ddr2_reg_base + DDR2_SDRCR_OFFSET); + + if (enter) { + if (pdown) + val |= DDR2_SRPD_BIT; + else + val &= ~DDR2_SRPD_BIT; + val |= DDR2_LPMODEN_BIT; + } else { + val &= ~(DDR2_SRPD_BIT | DDR2_LPMODEN_BIT); + } + + __raw_writel(val, ddr2_reg_base + DDR2_SDRCR_OFFSET); +} /* Actual code that puts the SoC in different idle states */ static int davinci_enter_idle(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { - struct cpuidle_state_usage *state_usage = &dev->states_usage[index]; - struct davinci_ops *ops = cpuidle_get_statedata(state_usage); - - if (ops && ops->enter) - ops->enter(ops->flags); + davinci_save_ddr_power(1, ddr2_pdown); index = cpuidle_wrap_enter(dev, drv, index, arm_cpuidle_simple_enter); - if (ops && ops->exit) - ops->exit(ops->flags); + davinci_save_ddr_power(0, ddr2_pdown); return index; } -/* fields in davinci_ops.flags */ -#define DAVINCI_CPUIDLE_FLAGS_DDR2_PWDN BIT(0) - static struct cpuidle_driver davinci_idle_driver = { .name = "cpuidle-davinci", .owner = THIS_MODULE, @@ -70,45 +79,6 @@ static struct cpuidle_driver davinci_idle_driver = { .state_count = DAVINCI_CPUIDLE_MAX_STATES, }; -static DEFINE_PER_CPU(struct cpuidle_device, davinci_cpuidle_device); -static void __iomem *ddr2_reg_base; - -static void davinci_save_ddr_power(int enter, bool pdown) -{ - u32 val; - - val = __raw_readl(ddr2_reg_base + DDR2_SDRCR_OFFSET); - - if (enter) { - if (pdown) - val |= DDR2_SRPD_BIT; - else - val &= ~DDR2_SRPD_BIT; - val |= DDR2_LPMODEN_BIT; - } else { - val &= ~(DDR2_SRPD_BIT | DDR2_LPMODEN_BIT); - } - - __raw_writel(val, ddr2_reg_base + DDR2_SDRCR_OFFSET); -} - -static void davinci_c2state_enter(u32 flags) -{ - davinci_save_ddr_power(1, !!(flags & DAVINCI_CPUIDLE_FLAGS_DDR2_PWDN)); -} - -static void davinci_c2state_exit(u32 flags) -{ - davinci_save_ddr_power(0, !!(flags & DAVINCI_CPUIDLE_FLAGS_DDR2_PWDN)); -} - -static struct davinci_ops davinci_states[DAVINCI_CPUIDLE_MAX_STATES] = { - [1] = { - .enter = davinci_c2state_enter, - .exit = davinci_c2state_exit, - }, -}; - static int __init davinci_cpuidle_probe(struct platform_device *pdev) { int ret; @@ -124,11 +94,7 @@ static int __init davinci_cpuidle_probe(struct platform_device *pdev) ddr2_reg_base = pdata->ddr2_ctlr_base; - if (pdata->ddr2_pdown) - davinci_states[1].flags |= DAVINCI_CPUIDLE_FLAGS_DDR2_PWDN; - cpuidle_set_statedata(&device->states_usage[1], &davinci_states[1]); - - device->state_count = DAVINCI_CPUIDLE_MAX_STATES; + ddr2_pdown = pdata->ddr2_pdown; ret = cpuidle_register_driver(&davinci_idle_driver); if (ret) { diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index cb0956bc96ed..c7002d40a9b0 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -97,14 +97,9 @@ static void default_idle(void) local_irq_enable(); } -void (*pm_idle)(void) = default_idle; -EXPORT_SYMBOL_GPL(pm_idle); - /* - * The idle thread, has rather strange semantics for calling pm_idle, - * but this is what x86 does and we need to do the same, so that - * things like cpuidle get called in the same way. The only difference - * is that we always respect 'hlt_counter' to prevent low power idle. + * The idle thread. + * We always respect 'hlt_counter' to prevent low power idle. */ void cpu_idle(void) { @@ -122,10 +117,10 @@ void cpu_idle(void) local_irq_disable(); if (!need_resched()) { stop_critical_timings(); - pm_idle(); + default_idle(); start_critical_timings(); /* - * pm_idle functions should always return + * default_idle functions should always return * with IRQs enabled. */ WARN_ON(irqs_disabled()); diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 3e16ad9b0a99..8061426b7df5 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -39,12 +39,6 @@ int nr_l1stack_tasks; void *l1_stack_base; unsigned long l1_stack_len; -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void) = NULL; -EXPORT_SYMBOL(pm_idle); - void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); @@ -81,7 +75,6 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { - void (*idle)(void) = pm_idle; #ifdef CONFIG_HOTPLUG_CPU if (cpu_is_offline(smp_processor_id())) diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index 7f65be6f7f17..104ff4dd9b98 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -54,11 +54,6 @@ void enable_hlt(void) EXPORT_SYMBOL(enable_hlt); -/* - * The following aren't currently used. - */ -void (*pm_idle)(void); - extern void default_idle(void); void (*pm_power_off)(void); @@ -77,16 +72,12 @@ void cpu_idle (void) while (1) { rcu_idle_enter(); while (!need_resched()) { - void (*idle)(void); /* * Mark this as an RCU critical section so that * synchronize_kernel() in the unload path waits * for our completion. */ - idle = pm_idle; - if (!idle) - idle = default_idle; - idle(); + default_idle(); } rcu_idle_exit(); schedule_preempt_disabled(); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 31360cbbd5f8..e34f565f595a 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -57,8 +57,6 @@ void (*ia64_mark_idle)(int); unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); -void (*pm_idle) (void); -EXPORT_SYMBOL(pm_idle); void (*pm_power_off) (void); EXPORT_SYMBOL(pm_power_off); @@ -301,7 +299,6 @@ cpu_idle (void) if (mark_idle) (*mark_idle)(1); - idle = pm_idle; if (!idle) idle = default_idle; (*idle)(); diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index aaefd9b94f2f..2029cc0d2fc6 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1051,7 +1051,6 @@ cpu_init (void) max_num_phys_stacked = num_phys_stacked; } platform_cpu_init(); - pm_idle = default_idle; } void __init diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 765d0f57c787..bde899e155d3 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -44,36 +44,10 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return tsk->thread.lr; } -/* - * Powermanagement idle function, if any.. - */ -static void (*pm_idle)(void) = NULL; - void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); /* - * We use this is we don't have any better - * idle routine.. - */ -static void default_idle(void) -{ - /* M32R_FIXME: Please use "cpu_sleep" mode. */ - cpu_relax(); -} - -/* - * On SMP it's slightly faster (but much more power-consuming!) - * to poll the ->work.need_resched flag instead of waiting for the - * cross-CPU IPI to arrive. Use this option with caution. - */ -static void poll_idle (void) -{ - /* M32R_FIXME */ - cpu_relax(); -} - -/* * The idle thread. There's no useful work to be * done, so just try to conserve power and have a * low exit latency (ie sit in a loop waiting for @@ -84,14 +58,8 @@ void cpu_idle (void) /* endless idle loop with no priority at all */ while (1) { rcu_idle_enter(); - while (!need_resched()) { - void (*idle)(void) = pm_idle; - - if (!idle) - idle = default_idle; - - idle(); - } + while (!need_resched()) + cpu_relax(); rcu_idle_exit(); schedule_preempt_disabled(); } @@ -120,21 +88,6 @@ void machine_power_off(void) /* M32R_FIXME */ } -static int __init idle_setup (char *str) -{ - if (!strncmp(str, "poll", 4)) { - printk("using poll in idle threads.\n"); - pm_idle = poll_idle; - } else if (!strncmp(str, "sleep", 4)) { - printk("using sleep in idle threads.\n"); - pm_idle = default_idle; - } - - return 1; -} - -__setup("idle=", idle_setup); - void show_regs(struct pt_regs * regs) { printk("\n"); diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index a5b74f729e5b..6ff2dcff3410 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -41,7 +41,6 @@ void show_regs(struct pt_regs *regs) regs->msr, regs->ear, regs->esr, regs->fsr); } -void (*pm_idle)(void); void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); @@ -98,8 +97,6 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - void (*idle)(void) = pm_idle; - if (!idle) idle = default_idle; diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index eb09f5a552ff..84f4e97e3074 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -37,12 +37,6 @@ #include "internal.h" /* - * power management idle function, if any.. - */ -void (*pm_idle)(void); -EXPORT_SYMBOL(pm_idle); - -/* * return saved PC of a blocked thread. */ unsigned long thread_saved_pc(struct task_struct *tsk) @@ -113,7 +107,6 @@ void cpu_idle(void) void (*idle)(void); smp_rmb(); - idle = pm_idle; if (!idle) { #if defined(CONFIG_SMP) && !defined(CONFIG_HOTPLUG_CPU) idle = poll_idle; diff --git a/arch/openrisc/kernel/idle.c b/arch/openrisc/kernel/idle.c index 7d618feb1b72..5e8a3b6d6bc6 100644 --- a/arch/openrisc/kernel/idle.c +++ b/arch/openrisc/kernel/idle.c @@ -39,11 +39,6 @@ void (*powersave) (void) = NULL; -static inline void pm_idle(void) -{ - barrier(); -} - void cpu_idle(void) { set_thread_flag(TIF_POLLING_NRFLAG); diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 0c910163caa3..3d5a1b387cc0 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -22,7 +22,7 @@ #include <asm/smp.h> #include <asm/bl_bit.h> -void (*pm_idle)(void); +static void (*sh_idle)(void); static int hlt_counter; @@ -103,9 +103,9 @@ void cpu_idle(void) /* Don't trace irqs off for idle */ stop_critical_timings(); if (cpuidle_idle_call()) - pm_idle(); + sh_idle(); /* - * Sanity check to ensure that pm_idle() returns + * Sanity check to ensure that sh_idle() returns * with IRQs enabled */ WARN_ON(irqs_disabled()); @@ -123,13 +123,13 @@ void __init select_idle_routine(void) /* * If a platform has set its own idle routine, leave it alone. */ - if (pm_idle) + if (sh_idle) return; if (hlt_works()) - pm_idle = default_idle; + sh_idle = default_idle; else - pm_idle = poll_idle; + sh_idle = poll_idle; } void stop_this_cpu(void *unused) diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index c1e01914fd98..2c7baa4c4505 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -118,6 +118,7 @@ extern unsigned long get_wchan(struct task_struct *); extern struct task_struct *last_task_used_math; #define cpu_relax() barrier() +extern void (*sparc_idle)(void); #endif diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index 348fa1aeabce..eefda32b595e 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -20,6 +20,7 @@ #include <asm/uaccess.h> #include <asm/auxio.h> #include <asm/apc.h> +#include <asm/processor.h> /* Debugging * @@ -158,7 +159,7 @@ static int apc_probe(struct platform_device *op) /* Assign power management IDLE handler */ if (!apc_no_idle) - pm_idle = apc_swift_idle; + sparc_idle = apc_swift_idle; printk(KERN_INFO "%s: power management initialized%s\n", APC_DEVNAME, apc_no_idle ? " (CPU idle disabled)" : ""); diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c index 4e174321097d..708bca435219 100644 --- a/arch/sparc/kernel/leon_pmc.c +++ b/arch/sparc/kernel/leon_pmc.c @@ -9,6 +9,7 @@ #include <asm/leon_amba.h> #include <asm/cpu_type.h> #include <asm/leon.h> +#include <asm/processor.h> /* List of Systems that need fixup instructions around power-down instruction */ unsigned int pmc_leon_fixup_ids[] = { @@ -69,9 +70,9 @@ static int __init leon_pmc_install(void) if (sparc_cpu_model == sparc_leon) { /* Assign power management IDLE handler */ if (pmc_leon_need_fixup()) - pm_idle = pmc_leon_idle_fixup; + sparc_idle = pmc_leon_idle_fixup; else - pm_idle = pmc_leon_idle; + sparc_idle = pmc_leon_idle; printk(KERN_INFO "leon: power management initialized\n"); } diff --git a/arch/sparc/kernel/pmc.c b/arch/sparc/kernel/pmc.c index dcbb62f63068..8b7297faca79 100644 --- a/arch/sparc/kernel/pmc.c +++ b/arch/sparc/kernel/pmc.c @@ -17,6 +17,7 @@ #include <asm/oplib.h> #include <asm/uaccess.h> #include <asm/auxio.h> +#include <asm/processor.h> /* Debug * @@ -63,7 +64,7 @@ static int pmc_probe(struct platform_device *op) #ifndef PMC_NO_IDLE /* Assign power management IDLE handler */ - pm_idle = pmc_swift_idle; + sparc_idle = pmc_swift_idle; #endif printk(KERN_INFO "%s: power management initialized\n", PMC_DEVNAME); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index be8e862badaf..62eede13831a 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -43,8 +43,7 @@ * Power management idle function * Set in pm platform drivers (apc.c and pmc.c) */ -void (*pm_idle)(void); -EXPORT_SYMBOL(pm_idle); +void (*sparc_idle)(void); /* * Power-off handler instantiation for pm.h compliance @@ -75,8 +74,8 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ for (;;) { while (!need_resched()) { - if (pm_idle) - (*pm_idle)(); + if (sparc_idle) + (*sparc_idle)(); else cpu_relax(); } diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c index 62bad9fed03e..872d7e22d847 100644 --- a/arch/unicore32/kernel/process.c +++ b/arch/unicore32/kernel/process.c @@ -45,11 +45,6 @@ static const char * const processor_modes[] = { "UK18", "UK19", "UK1A", "EXTN", "UK1C", "UK1D", "UK1E", "SUSR" }; -/* - * The idle thread, has rather strange semantics for calling pm_idle, - * but this is what x86 does and we need to do the same, so that - * things like cpuidle get called in the same way. - */ void cpu_idle(void) { /* endless idle loop with no priority at all */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4f7c2da2f9f8..c03309f697f1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1922,6 +1922,7 @@ config APM_DO_ENABLE this feature. config APM_CPU_IDLE + depends on CPU_IDLE bool "Make CPU Idle calls when idle" ---help--- Enable calls to APM CPU Idle/CPU Busy inside the kernel's idle loop. diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index bcdff997668c..2f366d0ac6b4 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -4,7 +4,8 @@ #define MWAIT_SUBSTATE_MASK 0xf #define MWAIT_CSTATE_MASK 0xf #define MWAIT_SUBSTATE_SIZE 4 -#define MWAIT_MAX_NUM_CSTATES 8 +#define MWAIT_HINT2CSTATE(hint) (((hint) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) +#define MWAIT_HINT2SUBSTATE(hint) ((hint) & MWAIT_CSTATE_MASK) #define CPUID_MWAIT_LEAF 5 #define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1 diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 888184b2fc85..b9e7d279f8ef 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -89,7 +89,6 @@ struct cpuinfo_x86 { char wp_works_ok; /* It doesn't on 386's */ /* Problems on some 486Dx4's and old 386's: */ - char hlt_works_ok; char hard_math; char rfu; char fdiv_bug; @@ -165,15 +164,6 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); extern const struct seq_operations cpuinfo_op; -static inline int hlt_works(int cpu) -{ -#ifdef CONFIG_X86_32 - return cpu_data(cpu).hlt_works_ok; -#else - return 1; -#endif -} - #define cache_line_size() (boot_cpu_data.x86_cache_alignment) extern void cpu_detect(struct cpuinfo_x86 *c); @@ -725,7 +715,7 @@ extern unsigned long boot_option_idle_override; extern bool amd_e400_c1e_detected; enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, - IDLE_POLL, IDLE_FORCE_MWAIT}; + IDLE_POLL}; extern void enable_sep_cpu(void); extern int sysenter_setup(void); @@ -998,7 +988,11 @@ extern unsigned long arch_align_stack(unsigned long sp); extern void free_init_pages(char *what, unsigned long begin, unsigned long end); void default_idle(void); -bool set_pm_idle_to_default(void); +#ifdef CONFIG_XEN +bool xen_set_default_idle(void); +#else +#define xen_set_default_idle 0 +#endif void stop_this_cpu(void *dummy); diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 433a59fb1a74..8d013f5153bc 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -103,6 +103,8 @@ #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define MSR_IA32_POWER_CTL 0x000001fc + #define MSR_IA32_MC0_CTL 0x00000400 #define MSR_IA32_MC0_STATUS 0x00000401 #define MSR_IA32_MC0_ADDR 0x00000402 @@ -272,6 +274,7 @@ #define MSR_IA32_PLATFORM_ID 0x00000017 #define MSR_IA32_EBL_CR_POWERON 0x0000002a #define MSR_EBC_FREQUENCY_ID 0x0000002c +#define MSR_SMI_COUNT 0x00000034 #define MSR_IA32_FEATURE_CONTROL 0x0000003a #define MSR_IA32_TSC_ADJUST 0x0000003b diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index d65464e43503..9f4bc6a1164d 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -232,6 +232,7 @@ #include <linux/acpi.h> #include <linux/syscore_ops.h> #include <linux/i8253.h> +#include <linux/cpuidle.h> #include <asm/uaccess.h> #include <asm/desc.h> @@ -360,13 +361,35 @@ struct apm_user { * idle percentage above which bios idle calls are done */ #ifdef CONFIG_APM_CPU_IDLE -#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012 #define DEFAULT_IDLE_THRESHOLD 95 #else #define DEFAULT_IDLE_THRESHOLD 100 #endif #define DEFAULT_IDLE_PERIOD (100 / 3) +static int apm_cpu_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index); + +static struct cpuidle_driver apm_idle_driver = { + .name = "apm_idle", + .owner = THIS_MODULE, + .en_core_tk_irqen = 1, + .states = { + { /* entry 0 is for polling */ }, + { /* entry 1 is for APM idle */ + .name = "APM", + .desc = "APM idle", + .flags = CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 250, /* WAG */ + .target_residency = 500, /* WAG */ + .enter = &apm_cpu_idle + }, + }, + .state_count = 2, +}; + +static struct cpuidle_device apm_cpuidle_device; + /* * Local variables */ @@ -377,7 +400,6 @@ static struct { static int clock_slowed; static int idle_threshold __read_mostly = DEFAULT_IDLE_THRESHOLD; static int idle_period __read_mostly = DEFAULT_IDLE_PERIOD; -static int set_pm_idle; static int suspends_pending; static int standbys_pending; static int ignore_sys_suspend; @@ -884,8 +906,6 @@ static void apm_do_busy(void) #define IDLE_CALC_LIMIT (HZ * 100) #define IDLE_LEAKY_MAX 16 -static void (*original_pm_idle)(void) __read_mostly; - /** * apm_cpu_idle - cpu idling for APM capable Linux * @@ -894,7 +914,8 @@ static void (*original_pm_idle)(void) __read_mostly; * Furthermore it calls the system default idle routine. */ -static void apm_cpu_idle(void) +static int apm_cpu_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ @@ -904,7 +925,6 @@ static void apm_cpu_idle(void) unsigned int jiffies_since_last_check = jiffies - last_jiffies; unsigned int bucket; - WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012"); recalc: if (jiffies_since_last_check > IDLE_CALC_LIMIT) { use_apm_idle = 0; @@ -950,10 +970,7 @@ recalc: break; } } - if (original_pm_idle) - original_pm_idle(); - else - default_idle(); + default_idle(); local_irq_disable(); jiffies_since_last_check = jiffies - last_jiffies; if (jiffies_since_last_check > idle_period) @@ -963,7 +980,7 @@ recalc: if (apm_idle_done) apm_do_busy(); - local_irq_enable(); + return index; } /** @@ -2381,9 +2398,9 @@ static int __init apm_init(void) if (HZ != 100) idle_period = (idle_period * HZ) / 100; if (idle_threshold < 100) { - original_pm_idle = pm_idle; - pm_idle = apm_cpu_idle; - set_pm_idle = 1; + if (!cpuidle_register_driver(&apm_idle_driver)) + if (cpuidle_register_device(&apm_cpuidle_device)) + cpuidle_unregister_driver(&apm_idle_driver); } return 0; @@ -2393,15 +2410,9 @@ static void __exit apm_exit(void) { int error; - if (set_pm_idle) { - pm_idle = original_pm_idle; - /* - * 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. - */ - kick_all_cpus_sync(); - } + cpuidle_unregister_device(&apm_cpuidle_device); + cpuidle_unregister_driver(&apm_idle_driver); + if (((apm_info.bios.flags & APM_BIOS_DISENGAGED) == 0) && (apm_info.connection_version > 0x0100)) { error = apm_engage_power_management(APM_DEVICE_ALL, 0); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 92dfec986a48..af6455e3fcc9 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -17,15 +17,6 @@ #include <asm/paravirt.h> #include <asm/alternative.h> -static int __init no_halt(char *s) -{ - WARN_ONCE(1, "\"no-hlt\" is deprecated, please use \"idle=poll\"\n"); - boot_cpu_data.hlt_works_ok = 0; - return 1; -} - -__setup("no-hlt", no_halt); - static int __init no_387(char *s) { boot_cpu_data.hard_math = 0; @@ -89,23 +80,6 @@ static void __init check_fpu(void) pr_warn("Hmm, FPU with FDIV bug\n"); } -static void __init check_hlt(void) -{ - if (boot_cpu_data.x86 >= 5 || paravirt_enabled()) - return; - - pr_info("Checking 'hlt' instruction... "); - if (!boot_cpu_data.hlt_works_ok) { - pr_cont("disabled\n"); - return; - } - halt(); - halt(); - halt(); - halt(); - pr_cont("OK\n"); -} - /* * Check whether we are able to run this kernel safely on SMP. * @@ -129,7 +103,6 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); #endif check_config(); - check_hlt(); init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 3286a92e662a..e280253f6f94 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -28,7 +28,6 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) { seq_printf(m, "fdiv_bug\t: %s\n" - "hlt_bug\t\t: %s\n" "f00f_bug\t: %s\n" "coma_bug\t: %s\n" "fpu\t\t: %s\n" @@ -36,7 +35,6 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) "cpuid level\t: %d\n" "wp\t\t: %s\n", c->fdiv_bug ? "yes" : "no", - c->hlt_works_ok ? "no" : "yes", c->f00f_bug ? "yes" : "no", c->coma_bug ? "yes" : "no", c->hard_math ? "yes" : "no", diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index dcfc1f410dc4..14ae10031ff0 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -268,13 +268,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void); -#ifdef CONFIG_APM_MODULE -EXPORT_SYMBOL(pm_idle); -#endif +static void (*x86_idle)(void); #ifndef CONFIG_SMP static inline void play_dead(void) @@ -351,7 +345,7 @@ void cpu_idle(void) rcu_idle_enter(); if (cpuidle_idle_call()) - pm_idle(); + x86_idle(); rcu_idle_exit(); start_critical_timings(); @@ -394,14 +388,16 @@ void default_idle(void) EXPORT_SYMBOL(default_idle); #endif -bool set_pm_idle_to_default(void) +#ifdef CONFIG_XEN +bool xen_set_default_idle(void) { - bool ret = !!pm_idle; + bool ret = !!x86_idle; - pm_idle = default_idle; + x86_idle = default_idle; return ret; } +#endif void stop_this_cpu(void *dummy) { local_irq_disable(); @@ -411,29 +407,8 @@ void stop_this_cpu(void *dummy) set_cpu_online(smp_processor_id(), false); disable_local_APIC(); - for (;;) { - if (hlt_works(smp_processor_id())) - halt(); - } -} - -/* Default MONITOR/MWAIT with no hints, used for default C1 state */ -static void mwait_idle(void) -{ - if (!need_resched()) { - trace_cpu_idle_rcuidle(1, smp_processor_id()); - if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) - clflush((void *)¤t_thread_info()->flags); - - __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); - if (!need_resched()) - __sti_mwait(0, 0); - else - local_irq_enable(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); - } else - local_irq_enable(); + for (;;) + halt(); } /* @@ -450,53 +425,6 @@ static void poll_idle(void) trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } -/* - * mwait selection logic: - * - * It depends on the CPU. For AMD CPUs that support MWAIT this is - * wrong. Family 0x10 and 0x11 CPUs will enter C1 on HLT. Powersavings - * then depend on a clock divisor and current Pstate of the core. If - * all cores of a processor are in halt state (C1) the processor can - * enter the C1E (C1 enhanced) state. If mwait is used this will never - * happen. - * - * idle=mwait overrides this decision and forces the usage of mwait. - */ - -#define MWAIT_INFO 0x05 -#define MWAIT_ECX_EXTENDED_INFO 0x01 -#define MWAIT_EDX_C1 0xf0 - -int mwait_usable(const struct cpuinfo_x86 *c) -{ - u32 eax, ebx, ecx, edx; - - /* Use mwait if idle=mwait boot option is given */ - if (boot_option_idle_override == IDLE_FORCE_MWAIT) - return 1; - - /* - * Any idle= boot option other than idle=mwait means that we must not - * use mwait. Eg: idle=halt or idle=poll or idle=nomwait - */ - if (boot_option_idle_override != IDLE_NO_OVERRIDE) - return 0; - - if (c->cpuid_level < MWAIT_INFO) - return 0; - - cpuid(MWAIT_INFO, &eax, &ebx, &ecx, &edx); - /* Check, whether EDX has extended info about MWAIT */ - if (!(ecx & MWAIT_ECX_EXTENDED_INFO)) - return 1; - - /* - * edx enumeratios MONITOR/MWAIT extensions. Check, whether - * C1 supports MWAIT - */ - return (edx & MWAIT_EDX_C1); -} - bool amd_e400_c1e_detected; EXPORT_SYMBOL(amd_e400_c1e_detected); @@ -561,31 +489,24 @@ static void amd_e400_idle(void) void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - if (pm_idle == poll_idle && smp_num_siblings > 1) { + if (x86_idle == poll_idle && smp_num_siblings > 1) pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); - } #endif - if (pm_idle) + if (x86_idle) return; - if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) { - /* - * One CPU supports mwait => All CPUs supports mwait - */ - pr_info("using mwait in idle threads\n"); - pm_idle = mwait_idle; - } else if (cpu_has_amd_erratum(amd_erratum_400)) { + if (cpu_has_amd_erratum(amd_erratum_400)) { /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); - pm_idle = amd_e400_idle; + x86_idle = amd_e400_idle; } else - pm_idle = default_idle; + x86_idle = default_idle; } void __init init_amd_e400_c1e_mask(void) { /* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */ - if (pm_idle == amd_e400_idle) + if (x86_idle == amd_e400_idle) zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL); } @@ -596,11 +517,8 @@ static int __init idle_setup(char *str) if (!strcmp(str, "poll")) { pr_info("using polling idle threads\n"); - pm_idle = poll_idle; + x86_idle = poll_idle; boot_option_idle_override = IDLE_POLL; - } else if (!strcmp(str, "mwait")) { - boot_option_idle_override = IDLE_FORCE_MWAIT; - WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n"); } else if (!strcmp(str, "halt")) { /* * When the boot option of idle=halt is added, halt is @@ -609,7 +527,7 @@ static int __init idle_setup(char *str) * To continue to load the CPU idle driver, don't touch * the boot_option_idle_override. */ - pm_idle = default_idle; + x86_idle = default_idle; boot_option_idle_override = IDLE_HALT; } else if (!strcmp(str, "nomwait")) { /* diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ed0fe385289d..a6ceaedc396a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1369,7 +1369,7 @@ static inline void mwait_play_dead(void) void *mwait_ptr; struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info); - if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))) + if (!this_cpu_has(X86_FEATURE_MWAIT)) return; if (!this_cpu_has(X86_FEATURE_CLFLSH)) return; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 8971a26d21ab..94eac5c85cdc 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -556,12 +556,9 @@ void __init xen_arch_setup(void) COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE); /* Set up idle, making sure it calls safe_halt() pvop */ -#ifdef CONFIG_X86_32 - boot_cpu_data.hlt_works_ok = 1; -#endif disable_cpuidle(); disable_cpufreq(); - WARN_ON(set_pm_idle_to_default()); + WARN_ON(xen_set_default_idle()); fiddle_vdso(); #ifdef CONFIG_NUMA numa_off = 1; |