Pull cpuidle into test branch

arch/i386/Kconfig

@@ -1069,6 +1069,8 @@ endif # APM
 
 source "arch/i386/kernel/cpu/cpufreq/Kconfig"
 
+source "drivers/cpuidle/Kconfig"
+
 endmenu
 
 menu "Bus options (PCI, PCMCIA, EISA, MCA, ISA)"

arch/x86_64/Kconfig

@@ -706,6 +706,8 @@ source "drivers/acpi/Kconfig"
 
 source "arch/x86_64/kernel/cpufreq/Kconfig"
 
+source "drivers/cpuidle/Kconfig"
+
 endmenu
 
 menu "Bus options (PCI etc.)"

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/

drivers/acpi/osl.c

@@ -1042,14 +1042,6 @@ 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.
  *

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;

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 +1298,366 @@ 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 (acpi_idle_suspend)
+		return(acpi_idle_enter_c1(dev, state));
+
+	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;
+
+	if (acpi_idle_suspend)
+		return(acpi_idle_enter_c1(dev, state));
+
+	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 +1675,7 @@ 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 +1693,7 @@ 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 +1701,13 @@ 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 +1715,12 @@ 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 +1734,24 @@ 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 +1766,7 @@ int acpi_processor_power_exit(struct acpi_processor *pr,
 		unregister_latency_notifier(&acpi_processor_latency_notifier);
 #endif
 	}
+#endif
 
 	return 0;
 }

drivers/cpuidle/Kconfig

+
+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

drivers/cpuidle/Makefile

+#
+# Makefile for cpuidle.
+#
+
+obj-y += cpuidle.o driver.o governor.o sysfs.o governors/

drivers/cpuidle/cpuidle.c

+/*
+ * 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_initcall(cpuidle_init);

drivers/cpuidle/cpuidle.h

+/*
+ * cpuidle.h - The internal header file
+ */
+
+#ifndef __DRIVER_CPUIDLE_H
+#define __DRIVER_CPUIDLE_H
+
+#include <linux/sysdev.h>
+
+/* For internal use only */
+extern struct cpuidle_governor *cpuidle_curr_governor;
+extern struct cpuidle_driver *cpuidle_curr_driver;
+extern struct list_head cpuidle_governors;
+extern struct list_head cpuidle_detected_devices;
+extern struct mutex cpuidle_lock;
+extern spinlock_t cpuidle_driver_lock;
+
+/* idle loop */
+extern void cpuidle_install_idle_handler(void);
+extern void cpuidle_uninstall_idle_handler(void);
+
+/* governors */
+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_state_sysfs(struct cpuidle_device *device);
+extern void cpuidle_remove_state_sysfs(struct cpuidle_device *device);
+extern int cpuidle_add_sysfs(struct sys_device *sysdev);
+extern void cpuidle_remove_sysfs(struct sys_device *sysdev);
+
+#endif /* __DRIVER_CPUIDLE_H */

drivers/cpuidle/driver.c

+/*
+ * driver.c - driver support
+ *
+ * (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/mutex.h>
+#include <linux/module.h>
+#include <linux/cpuidle.h>
+
+#include "cpuidle.h"
+
+struct cpuidle_driver *cpuidle_curr_driver;
+DEFINE_SPINLOCK(cpuidle_driver_lock);
+
+/**
+ * cpuidle_register_driver - registers a driver
+ * @drv: the driver
+ */
+int cpuidle_register_driver(struct cpuidle_driver *drv)
+{
+	if (!drv)
+		return -EINVAL;
+
+	spin_lock(&cpuidle_driver_lock);
+	if (cpuidle_curr_driver) {
+		spin_unlock(&cpuidle_driver_lock);
+		return -EBUSY;
+	}
+	cpuidle_curr_driver = drv;
+	spin_unlock(&cpuidle_driver_lock);
+
+	return 0;
+}
+
+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;
+
+	spin_lock(&cpuidle_driver_lock);
+	cpuidle_curr_driver = NULL;
+	spin_unlock(&cpuidle_driver_lock);
+}
+
+EXPORT_SYMBOL_GPL(cpuidle_unregister_driver);

drivers/cpuidle/governor.c

+/*
+ * governor.c - governor support
+ *
+ * (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/mutex.h>
+#include <linux/module.h>
+#include <linux/cpuidle.h>
+
+#include "cpuidle.h"
+
+LIST_HEAD(cpuidle_governors);
+struct cpuidle_governor *cpuidle_curr_governor;
+
+/**
+ * __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 0;
+
+	cpuidle_uninstall_idle_handler();
+
+	if (cpuidle_curr_governor) {
+		list_for_each_entry(dev, &cpuidle_detected_devices, device_list)
+			cpuidle_disable_device(dev);
+		module_put(cpuidle_curr_governor->owner);
+	}
+
+	cpuidle_curr_governor = gov;
+
+	if (gov) {
+		if (!try_module_get(cpuidle_curr_governor->owner))
+			return -EINVAL;
+		list_for_each_entry(dev, &cpuidle_detected_devices, device_list)
+			cpuidle_enable_device(dev);
+		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.
+ */
+static 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);

drivers/cpuidle/governors/Makefile

+#
+# Makefile for cpuidle governors.
+#
+
+obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o
+obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o

drivers/cpuidle/governors/ladder.c

+/*
+ * ladder.c - the residency ladder algorithm
+ *
+ *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
+ *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2004, 2005 Dominik Brodowski <linux@brodo.de>
+ *
+ * (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/cpuidle.h>
+#include <linux/latency.h>
+#include <linux/moduleparam.h>
+#include <linux/jiffies.h>
+
+#include <asm/io.h>
+#include <asm/uaccess.h>
+
+#define PROMOTION_COUNT 4
+#define DEMOTION_COUNT 1
+
+struct ladder_device_state {
+	struct {
+		u32 promotion_count;
+		u32 demotion_count;
+		u32 promotion_time;
+		u32 demotion_time;
+	} threshold;
+	struct {
+		int promotion_count;
+		int demotion_count;
+	} stats;
+};
+
+struct ladder_device {
+	struct ladder_device_state states[CPUIDLE_STATE_MAX];
+	int last_state_idx;
+};
+
+static DEFINE_PER_CPU(struct ladder_device, ladder_devices);
+
+/**
+ * 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 = &__get_cpu_var(ladder_devices);
+	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];
+
+	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_enable_device - setup for the governor
+ * @dev: the CPU
+ */
+static int ladder_enable_device(struct cpuidle_device *dev)
+{
+	int i;
+	struct ladder_device *ldev = &per_cpu(ladder_devices, dev->cpu);
+	struct ladder_device_state *lstate;
+	struct cpuidle_state *state;
+
+	ldev->last_state_idx = 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;
+	}
+
+	return 0;
+}
+
+static struct cpuidle_governor ladder_governor = {
+	.name =		"ladder",
+	.rating =	10,
+	.enable =	ladder_enable_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);

drivers/cpuidle/governors/menu.c

+/*
+ * menu.c - the menu idle governor
+ *
+ * Copyright (C) 2006-2007 Adam Belay <abelay@novell.com>
+ *
+ * This code is licenced under the GPL.
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpuidle.h>
+#include <linux/latency.h>
+#include <linux/time.h>
+#include <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+
+#define BREAK_FUZZ	4	/* 4 us */
+
+struct menu_device {
+	int		last_state_idx;
+
+	unsigned int	expected_us;
+	unsigned int	predicted_us;
+	unsigned int	last_measured_us;
+	unsigned int	elapsed_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;
+
+	/* determine the expected residency time */
+	data->expected_us =
+		(u32) ktime_to_ns(tick_nohz_get_sleep_length()) / 1000;
+
+	/* find the deepest idle state that satisfies our constraints */
+	for (i = 1; i < dev->state_count; i++) {
+		struct cpuidle_state *s = &dev->states[i];
+
+		if (s->target_residency > data->expected_us)
+			break;
+		if (s->target_residency > data->predicted_us)
+			break;
+		if (s->exit_latency > system_latency_constraint())
+			break;
+	}
+
+	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;
+	unsigned int measured_us =
+		cpuidle_get_last_residency(dev) + data->elapsed_us;
+	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;
+
+	/* Predict time remaining until next break event */
+	if (measured_us + BREAK_FUZZ < data->expected_us - target->exit_latency) {
+		data->predicted_us = max(measured_us, data->last_measured_us);
+		data->last_measured_us = measured_us;
+		data->elapsed_us = 0;
+	} else {
+		if (data->elapsed_us < data->elapsed_us + measured_us)
+			data->elapsed_us = measured_us;
+		else
+			data->elapsed_us = -1;
+		data->predicted_us = max(measured_us, data->last_measured_us);
+	}
+}
+
+/**
+ * menu_enable_device - scans a CPU's states and does setup
+ * @dev: the CPU
+ */
+static int menu_enable_device(struct cpuidle_device *dev)
+{
+	struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
+
+	memset(data, 0, sizeof(struct menu_device));
+
+	return 0;
+}
+
+static struct cpuidle_governor menu_governor = {
+	.name =		"menu",
+	.rating =	20,
+	.enable =	menu_enable_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);

drivers/cpuidle/sysfs.c

+/*
+ * sysfs.c - sysfs support
+ *
+ * (C) 2006-2007 Shaohua Li <shaohua.li@intel.com>
+ *
+ * This code is licenced under the GPL.
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpuidle.h>
+#include <linux/sysfs.h>
+#include <linux/cpu.h>
+
+#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_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);
+	}
+
+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;
+
+	spin_lock(&cpuidle_driver_lock);
+	if (cpuidle_curr_driver)
+		ret = sprintf(buf, "%s\n", cpuidle_curr_driver->name);
+	else
+		ret = sprintf(buf, "none\n");
+	spin_unlock(&cpuidle_driver_lock);
+
+	return ret;
+}
+
+static ssize_t show_current_governor(struct sys_device *dev, char *buf)
+{
+	ssize_t ret;
+
+	mutex_lock(&cpuidle_lock);
+	if (cpuidle_curr_governor)
+		ret = sprintf(buf, "%s\n", cpuidle_curr_governor->name);
+	else
+		ret = sprintf(buf, "none\n");
+	mutex_unlock(&cpuidle_lock);
+
+	return ret;
+}
+
+static ssize_t store_current_governor(struct sys_device *dev,
+	const char *buf, size_t count)
+{
+	char gov_name[CPUIDLE_NAME_LEN];
+	int ret = -EINVAL;
+	size_t len = count;
+	struct cpuidle_governor *gov;
+
+	if (!len || len >= sizeof(gov_name))
+		return -EINVAL;
+
+	memcpy(gov_name, buf, len);
+	gov_name[len] = '\0';
+	if (gov_name[len - 1] == '\n')
+		gov_name[--len] = '\0';
+
+	mutex_lock(&cpuidle_lock);
+
+	list_for_each_entry(gov, &cpuidle_governors, governor_list) {
+		if (strlen(gov->name) == len && !strcmp(gov->name, gov_name)) {
+			ret = cpuidle_switch_governor(gov);
+			break;
+		}
+	}
+
+	mutex_unlock(&cpuidle_lock);
+
+	if (ret)
+		return ret;
+	else
+		return count;
+}
+
+static SYSDEV_ATTR(current_driver, 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.attr,
+	&attr_current_governor_ro.attr,
+	NULL
+};
+
+static SYSDEV_ATTR(available_governors, 0444, show_available_governors, NULL);
+static SYSDEV_ATTR(current_governor, 0644, show_current_governor,
+	store_current_governor);
+
+static struct attribute *cpuclass_switch_attrs[] = {
+	&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, "%u\n", state->_name);\
+}
+
+static ssize_t show_state_name(struct cpuidle_state *state, char *buf)
+{
+	return sprintf(buf, "%s\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(name, show_state_name);
+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_name.attr,
+	&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_state_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_state_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);
+}

drivers/net/wireless/ipw2100.c

@@ -1858,14 +1858,6 @@ static void ipw2100_down(struct ipw2100_priv *priv)
 
 	modify_acceptable_latency("ipw2100", INFINITE_LATENCY);
 
-#ifdef ACPI_CSTATE_LIMIT_DEFINED
-	if (priv->config & CFG_C3_DISABLED) {
-		IPW_DEBUG_INFO(": Resetting C3 transitions.\n");
-		acpi_set_cstate_limit(priv->cstate_limit);
-		priv->config &= ~CFG_C3_DISABLED;
-	}
-#endif
-
 	/* We have to signal any supplicant if we are disassociating */
 	if (associated)
 		wireless_send_event(priv->net_dev, SIOCGIWAP, &wrqu, NULL);
@@ -2088,14 +2080,6 @@ static void isr_indicate_rf_kill(struct ipw2100_priv *priv, u32 status)
 	/* RF_KILL is now enabled (else we wouldn't be here) */
 	priv->status |= STATUS_RF_KILL_HW;
 
-#ifdef ACPI_CSTATE_LIMIT_DEFINED
-	if (priv->config & CFG_C3_DISABLED) {
-		IPW_DEBUG_INFO(": Resetting C3 transitions.\n");
-		acpi_set_cstate_limit(priv->cstate_limit);
-		priv->config &= ~CFG_C3_DISABLED;
-	}
-#endif
-
 	/* Make sure the RF Kill check timer is running */
 	priv->stop_rf_kill = 0;
 	cancel_delayed_work(&priv->rf_kill);
@@ -2326,23 +2310,10 @@ static void ipw2100_corruption_detected(struct ipw2100_priv *priv, int i)
 	u32 match, reg;
 	int j;
 #endif
-#ifdef ACPI_CSTATE_LIMIT_DEFINED
-	int limit;
-#endif
 
 	IPW_DEBUG_INFO(": PCI latency error detected at 0x%04zX.\n",
 		       i * sizeof(struct ipw2100_status));
 
-#ifdef ACPI_CSTATE_LIMIT_DEFINED
-	IPW_DEBUG_INFO(": Disabling C3 transitions.\n");
-	limit = acpi_get_cstate_limit();
-	if (limit > 2) {
-		priv->cstate_limit = limit;
-		acpi_set_cstate_limit(2);
-		priv->config |= CFG_C3_DISABLED;
-	}
-#endif
-
 #ifdef IPW2100_DEBUG_C3
 	/* Halt the fimrware so we can get a good image */
 	write_register(priv->net_dev, IPW_REG_RESET_REG,

drivers/net/wireless/ipw2100.h

@@ -479,7 +479,6 @@ enum {
 #define CFG_ASSOCIATE           (1<<6)
 #define CFG_FIXED_RATE          (1<<7)
 #define CFG_ADHOC_CREATE        (1<<8)
-#define CFG_C3_DISABLED         (1<<9)
 #define CFG_PASSIVE_SCAN        (1<<10)
 #ifdef CONFIG_IPW2100_MONITOR
 #define CFG_CRC_CHECK           (1<<11)
@@ -508,7 +507,6 @@ struct ipw2100_priv {
 	u8 bssid[ETH_ALEN];
 	u8 channel;
 	int last_mode;
-	int cstate_limit;
 
 	unsigned long connect_start;
 	unsigned long last_reset;

include/acpi/processor.h

@@ -3,6 +3,7 @@
 
 #include <linux/kernel.h>
 #include <linux/cpu.h>
+#include <linux/cpuidle.h>
 
 #include <asm/acpi.h>
 
@@ -75,7 +76,9 @@ struct acpi_processor_cx {
 };
 
 struct acpi_processor_power {
+	struct cpuidle_device dev;
 	struct acpi_processor_cx *state;
+	struct acpi_processor_cx *bm_state;
 	unsigned long bm_check_timestamp;
 	u32 default_state;
 	u32 bm_activity;
@@ -199,6 +202,7 @@ 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 {
@@ -322,6 +326,7 @@ int acpi_processor_power_exit(struct acpi_processor *pr,
 			      struct acpi_device *device);
 int acpi_processor_suspend(struct acpi_device * device, pm_message_t state);
 int acpi_processor_resume(struct acpi_device * device);
+extern struct cpuidle_driver acpi_idle_driver;
 
 /* in processor_thermal.c */
 int acpi_processor_get_limit_info(struct acpi_processor *pr);

include/linux/acpi.h

@@ -189,32 +189,6 @@ extern int ec_transaction(u8 command,
 extern int acpi_blacklisted(void);
 extern void acpi_bios_year(char *s);
 
-#define	ACPI_CSTATE_LIMIT_DEFINED	/* for driver builds */
-#ifdef	CONFIG_ACPI
-
-/*
- * Set highest legal C-state
- * 0: C0 okay, but not C1
- * 1: C1 okay, but not C2
- * 2: C2 okay, but not C3 etc.
- */
-
-extern unsigned int max_cstate;
-
-static inline unsigned int acpi_get_cstate_limit(void)
-{
-	return max_cstate;
-}
-static inline void acpi_set_cstate_limit(unsigned int new_limit)
-{
-	max_cstate = new_limit;
-	return;
-}
-#else
-static inline unsigned int acpi_get_cstate_limit(void) { return 0; }
-static inline void acpi_set_cstate_limit(unsigned int new_limit) { return; }
-#endif
-
 #ifdef CONFIG_ACPI_NUMA
 int acpi_get_pxm(acpi_handle handle);
 int acpi_get_node(acpi_handle *handle);

include/linux/cpuidle.h

+/*
+ * cpuidle.h - a generic framework for CPU idle power management
+ *
+ * (C) 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.
+ */
+
+#ifndef _LINUX_CPUIDLE_H
+#define _LINUX_CPUIDLE_H
+
+#include <linux/percpu.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <linux/completion.h>
+
+#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 {
+	int			enabled:1;
+	unsigned 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);
+
+/**
+ * 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 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_register_device(struct cpuidle_device *dev);
+extern void cpuidle_unregister_device(struct cpuidle_device *dev);
+
+extern void cpuidle_pause_and_lock(void);
+extern void cpuidle_resume_and_unlock(void);
+extern int cpuidle_enable_device(struct cpuidle_device *dev);
+extern void cpuidle_disable_device(struct cpuidle_device *dev);
+
+#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_register_device(struct cpuidle_device *dev)
+{return 0;}
+static inline void cpuidle_unregister_device(struct cpuidle_device *dev) { }
+
+static inline void cpuidle_pause_and_lock(void) { }
+static inline void cpuidle_resume_and_unlock(void) { }
+static inline int cpuidle_enable_device(struct cpuidle_device *dev)
+{return 0;}
+static inline void cpuidle_disable_device(struct cpuidle_device *dev) { }
+
+#endif
+
+/******************************
+ * CPUIDLE GOVERNOR INTERFACE *
+ ******************************/
+
+struct cpuidle_governor {
+	char			name[CPUIDLE_NAME_LEN];
+	struct list_head 	governor_list;
+	unsigned int		rating;
+
+	int  (*enable)		(struct cpuidle_device *dev);
+	void (*disable)		(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);
+
+#else
+
+static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
+{return 0;}
+static inline void cpuidle_unregister_governor(struct cpuidle_governor *gov) { }
+
+#endif
+
+#endif /* _LINUX_CPUIDLE_H */

include/linux/tick.h

@@ -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 +102,17 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
 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);
 # 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

kernel/time/tick-sched.c

@@ -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);
@@ -302,10 +303,25 @@ 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);
+
 /**
  * nohz_restart_sched_tick - restart the idle tick from the idle task
  *