Merge branches 'acpi', 'idle', 'mrst-pmu' and 'pm-tools' into next

arch/arm/mach-at91/cpuidle.c

@@ -33,7 +33,8 @@ static struct cpuidle_driver at91_idle_driver = {
 
 /* Actual code that puts the SoC in different idle states */
 static int at91_enter_idle(struct cpuidle_device *dev,
-			       struct cpuidle_state *state)
+			struct cpuidle_driver *drv,
+			       int index)
 {
 	struct timeval before, after;
 	int idle_time;
@@ -41,10 +42,10 @@ static int at91_enter_idle(struct cpuidle_device *dev,
 
 	local_irq_disable();
 	do_gettimeofday(&before);
-	if (state == &dev->states[0])
+	if (index == 0)
 		/* Wait for interrupt state */
 		cpu_do_idle();
-	else if (state == &dev->states[1]) {
+	else if (index == 1) {
 		asm("b 1f; .align 5; 1:");
 		asm("mcr p15, 0, r0, c7, c10, 4");	/* drain write buffer */
 		saved_lpr = sdram_selfrefresh_enable();
@@ -55,34 +56,38 @@ static int at91_enter_idle(struct cpuidle_device *dev,
 	local_irq_enable();
 	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
 			(after.tv_usec - before.tv_usec);
-	return idle_time;
+
+	dev->last_residency = idle_time;
+	return index;
 }
 
 /* Initialize CPU idle by registering the idle states */
 static int at91_init_cpuidle(void)
 {
 	struct cpuidle_device *device;
-
-	cpuidle_register_driver(&at91_idle_driver);
+	struct cpuidle_driver *driver = &at91_idle_driver;
 
 	device = &per_cpu(at91_cpuidle_device, smp_processor_id());
 	device->state_count = AT91_MAX_STATES;
+	driver->state_count = AT91_MAX_STATES;
 
 	/* Wait for interrupt state */
-	device->states[0].enter = at91_enter_idle;
-	device->states[0].exit_latency = 1;
-	device->states[0].target_residency = 10000;
-	device->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(device->states[0].name, "WFI");
-	strcpy(device->states[0].desc, "Wait for interrupt");
+	driver->states[0].enter = at91_enter_idle;
+	driver->states[0].exit_latency = 1;
+	driver->states[0].target_residency = 10000;
+	driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
+	strcpy(driver->states[0].name, "WFI");
+	strcpy(driver->states[0].desc, "Wait for interrupt");
 
 	/* Wait for interrupt and RAM self refresh state */
-	device->states[1].enter = at91_enter_idle;
-	device->states[1].exit_latency = 10;
-	device->states[1].target_residency = 10000;
-	device->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(device->states[1].name, "RAM_SR");
-	strcpy(device->states[1].desc, "WFI and RAM Self Refresh");
+	driver->states[1].enter = at91_enter_idle;
+	driver->states[1].exit_latency = 10;
+	driver->states[1].target_residency = 10000;
+	driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
+	strcpy(driver->states[1].name, "RAM_SR");
+	strcpy(driver->states[1].desc, "WFI and RAM Self Refresh");
+
+	cpuidle_register_driver(&at91_idle_driver);
 
 	if (cpuidle_register_device(device)) {
 		printk(KERN_ERR "at91_init_cpuidle: Failed registering\n");

arch/arm/mach-davinci/cpuidle.c

@@ -78,9 +78,11 @@ static struct davinci_ops davinci_states[DAVINCI_CPUIDLE_MAX_STATES] = {
 
 /* Actual code that puts the SoC in different idle states */
 static int davinci_enter_idle(struct cpuidle_device *dev,
-						struct cpuidle_state *state)
+				struct cpuidle_driver *drv,
+						int index)
 {
-	struct davinci_ops *ops = cpuidle_get_statedata(state);
+	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
+	struct davinci_ops *ops = cpuidle_get_statedata(state_usage);
 	struct timeval before, after;
 	int idle_time;
 
@@ -98,13 +100,17 @@ static int davinci_enter_idle(struct cpuidle_device *dev,
 	local_irq_enable();
 	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
 			(after.tv_usec - before.tv_usec);
-	return idle_time;
+
+	dev->last_residency = idle_time;
+
+	return index;
 }
 
 static int __init davinci_cpuidle_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct cpuidle_device *device;
+	struct cpuidle_driver *driver = &davinci_idle_driver;
 	struct davinci_cpuidle_config *pdata = pdev->dev.platform_data;
 
 	device = &per_cpu(davinci_cpuidle_device, smp_processor_id());
@@ -116,32 +122,33 @@ static int __init davinci_cpuidle_probe(struct platform_device *pdev)
 
 	ddr2_reg_base = pdata->ddr2_ctlr_base;
 
-	ret = cpuidle_register_driver(&davinci_idle_driver);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register driver\n");
-		return ret;
-	}
-
 	/* Wait for interrupt state */
-	device->states[0].enter = davinci_enter_idle;
-	device->states[0].exit_latency = 1;
-	device->states[0].target_residency = 10000;
-	device->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(device->states[0].name, "WFI");
-	strcpy(device->states[0].desc, "Wait for interrupt");
+	driver->states[0].enter = davinci_enter_idle;
+	driver->states[0].exit_latency = 1;
+	driver->states[0].target_residency = 10000;
+	driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
+	strcpy(driver->states[0].name, "WFI");
+	strcpy(driver->states[0].desc, "Wait for interrupt");
 
 	/* Wait for interrupt and DDR self refresh state */
-	device->states[1].enter = davinci_enter_idle;
-	device->states[1].exit_latency = 10;
-	device->states[1].target_residency = 10000;
-	device->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(device->states[1].name, "DDR SR");
-	strcpy(device->states[1].desc, "WFI and DDR Self Refresh");
+	driver->states[1].enter = davinci_enter_idle;
+	driver->states[1].exit_latency = 10;
+	driver->states[1].target_residency = 10000;
+	driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
+	strcpy(driver->states[1].name, "DDR SR");
+	strcpy(driver->states[1].desc, "WFI and DDR Self Refresh");
 	if (pdata->ddr2_pdown)
 		davinci_states[1].flags |= DAVINCI_CPUIDLE_FLAGS_DDR2_PWDN;
-	cpuidle_set_statedata(&device->states[1], &davinci_states[1]);
+	cpuidle_set_statedata(&device->states_usage[1], &davinci_states[1]);
 
 	device->state_count = DAVINCI_CPUIDLE_MAX_STATES;
+	driver->state_count = DAVINCI_CPUIDLE_MAX_STATES;
+
+	ret = cpuidle_register_driver(&davinci_idle_driver);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register driver\n");
+		return ret;
+	}
 
 	ret = cpuidle_register_device(device);
 	if (ret) {

arch/arm/mach-exynos4/cpuidle.c

@@ -16,7 +16,8 @@
 #include <asm/proc-fns.h>
 
 static int exynos4_enter_idle(struct cpuidle_device *dev,
-			      struct cpuidle_state *state);
+			struct cpuidle_driver *drv,
+			      int index);
 
 static struct cpuidle_state exynos4_cpuidle_set[] = {
 	[0] = {
@@ -37,7 +38,8 @@ static struct cpuidle_driver exynos4_idle_driver = {
 };
 
 static int exynos4_enter_idle(struct cpuidle_device *dev,
-			      struct cpuidle_state *state)
+				struct cpuidle_driver *drv,
+			      int index)
 {
 	struct timeval before, after;
 	int idle_time;
@@ -52,29 +54,31 @@ static int exynos4_enter_idle(struct cpuidle_device *dev,
 	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
 		    (after.tv_usec - before.tv_usec);
 
-	return idle_time;
+	dev->last_residency = idle_time;
+	return index;
 }
 
 static int __init exynos4_init_cpuidle(void)
 {
 	int i, max_cpuidle_state, cpu_id;
 	struct cpuidle_device *device;
+	struct cpuidle_driver *drv = &exynos4_idle_driver;
 
+	/* Setup cpuidle driver */
+	drv->state_count = (sizeof(exynos4_cpuidle_set) /
+				       sizeof(struct cpuidle_state));
+	max_cpuidle_state = drv->state_count;
+	for (i = 0; i < max_cpuidle_state; i++) {
+		memcpy(&drv->states[i], &exynos4_cpuidle_set[i],
+				sizeof(struct cpuidle_state));
+	}
 	cpuidle_register_driver(&exynos4_idle_driver);
 
 	for_each_cpu(cpu_id, cpu_online_mask) {
 		device = &per_cpu(exynos4_cpuidle_device, cpu_id);
 		device->cpu = cpu_id;
 
-		device->state_count = (sizeof(exynos4_cpuidle_set) /
-					       sizeof(struct cpuidle_state));
-
-		max_cpuidle_state = device->state_count;
-
-		for (i = 0; i < max_cpuidle_state; i++) {
-			memcpy(&device->states[i], &exynos4_cpuidle_set[i],
-					sizeof(struct cpuidle_state));
-		}
+		device->state_count = drv->state_count;
 
 		if (cpuidle_register_device(device)) {
 			printk(KERN_ERR "CPUidle register device failed\n,");

arch/arm/mach-kirkwood/cpuidle.c

@@ -32,17 +32,18 @@ static DEFINE_PER_CPU(struct cpuidle_device, kirkwood_cpuidle_device);
 
 /* Actual code that puts the SoC in different idle states */
 static int kirkwood_enter_idle(struct cpuidle_device *dev,
-			       struct cpuidle_state *state)
+				struct cpuidle_driver *drv,
+			       int index)
 {
 	struct timeval before, after;
 	int idle_time;
 
 	local_irq_disable();
 	do_gettimeofday(&before);
-	if (state == &dev->states[0])
+	if (index == 0)
 		/* Wait for interrupt state */
 		cpu_do_idle();
-	else if (state == &dev->states[1]) {
+	else if (index == 1) {
 		/*
 		 * Following write will put DDR in self refresh.
 		 * Note that we have 256 cycles before DDR puts it
@@ -57,35 +58,40 @@ static int kirkwood_enter_idle(struct cpuidle_device *dev,
 	local_irq_enable();
 	idle_time = (after.tv_sec - before.tv_sec) * USEC_PER_SEC +
 			(after.tv_usec - before.tv_usec);
-	return idle_time;
+
+	/* Update last residency */
+	dev->last_residency = idle_time;
+
+	return index;
 }
 
 /* Initialize CPU idle by registering the idle states */
 static int kirkwood_init_cpuidle(void)
 {
 	struct cpuidle_device *device;
-
-	cpuidle_register_driver(&kirkwood_idle_driver);
+	struct cpuidle_driver *driver = &kirkwood_idle_driver;
 
 	device = &per_cpu(kirkwood_cpuidle_device, smp_processor_id());
 	device->state_count = KIRKWOOD_MAX_STATES;
+	driver->state_count = KIRKWOOD_MAX_STATES;
 
 	/* Wait for interrupt state */
-	device->states[0].enter = kirkwood_enter_idle;
-	device->states[0].exit_latency = 1;
-	device->states[0].target_residency = 10000;
-	device->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(device->states[0].name, "WFI");
-	strcpy(device->states[0].desc, "Wait for interrupt");
+	driver->states[0].enter = kirkwood_enter_idle;
+	driver->states[0].exit_latency = 1;
+	driver->states[0].target_residency = 10000;
+	driver->states[0].flags = CPUIDLE_FLAG_TIME_VALID;
+	strcpy(driver->states[0].name, "WFI");
+	strcpy(driver->states[0].desc, "Wait for interrupt");
 
 	/* Wait for interrupt and DDR self refresh state */
-	device->states[1].enter = kirkwood_enter_idle;
-	device->states[1].exit_latency = 10;
-	device->states[1].target_residency = 10000;
-	device->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
-	strcpy(device->states[1].name, "DDR SR");
-	strcpy(device->states[1].desc, "WFI and DDR Self Refresh");
+	driver->states[1].enter = kirkwood_enter_idle;
+	driver->states[1].exit_latency = 10;
+	driver->states[1].target_residency = 10000;
+	driver->states[1].flags = CPUIDLE_FLAG_TIME_VALID;
+	strcpy(driver->states[1].name, "DDR SR");
+	strcpy(driver->states[1].desc, "WFI and DDR Self Refresh");
 
+	cpuidle_register_driver(&kirkwood_idle_driver);
 	if (cpuidle_register_device(device)) {
 		printk(KERN_ERR "kirkwood_init_cpuidle: Failed registering\n");
 		return -EIO;

arch/sh/kernel/cpu/shmobile/cpuidle.c

@@ -25,11 +25,12 @@ static unsigned long cpuidle_mode[] = {
 };
 
 static int cpuidle_sleep_enter(struct cpuidle_device *dev,
-			       struct cpuidle_state *state)
+				struct cpuidle_driver *drv,
+				int index)
 {
 	unsigned long allowed_mode = arch_hwblk_sleep_mode();
 	ktime_t before, after;
-	int requested_state = state - &dev->states[0];
+	int requested_state = index;
 	int allowed_state;
 	int k;
 
@@ -46,11 +47,13 @@ static int cpuidle_sleep_enter(struct cpuidle_device *dev,
 	 */
 	k = min_t(int, allowed_state, requested_state);
 
-	dev->last_state = &dev->states[k];
 	before = ktime_get();
 	sh_mobile_call_standby(cpuidle_mode[k]);
 	after = ktime_get();
-	return ktime_to_ns(ktime_sub(after, before)) >> 10;
+
+	dev->last_residency = (int)ktime_to_ns(ktime_sub(after, before)) >> 10;
+
+	return k;
 }
 
 static struct cpuidle_device cpuidle_dev;
@@ -62,19 +65,19 @@ static struct cpuidle_driver cpuidle_driver = {
 void sh_mobile_setup_cpuidle(void)
 {
 	struct cpuidle_device *dev = &cpuidle_dev;
+	struct cpuidle_driver *drv = &cpuidle_driver;
 	struct cpuidle_state *state;
 	int i;
 
-	cpuidle_register_driver(&cpuidle_driver);
 
 	for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
-		dev->states[i].name[0] = '\0';
-		dev->states[i].desc[0] = '\0';
+		drv->states[i].name[0] = '\0';
+		drv->states[i].desc[0] = '\0';
 	}
 
 	i = CPUIDLE_DRIVER_STATE_START;
 
-	state = &dev->states[i++];
+	state = &drv->states[i++];
 	snprintf(state->name, CPUIDLE_NAME_LEN, "C1");
 	strncpy(state->desc, "SuperH Sleep Mode", CPUIDLE_DESC_LEN);
 	state->exit_latency = 1;
@@ -84,10 +87,10 @@ void sh_mobile_setup_cpuidle(void)
 	state->flags |= CPUIDLE_FLAG_TIME_VALID;
 	state->enter = cpuidle_sleep_enter;
 
-	dev->safe_state = state;
+	drv->safe_state_index = i-1;
 
 	if (sh_mobile_sleep_supported & SUSP_SH_SF) {
-		state = &dev->states[i++];
+		state = &drv->states[i++];
 		snprintf(state->name, CPUIDLE_NAME_LEN, "C2");
 		strncpy(state->desc, "SuperH Sleep Mode [SF]",
 			CPUIDLE_DESC_LEN);
@@ -100,7 +103,7 @@ void sh_mobile_setup_cpuidle(void)
 	}
 
 	if (sh_mobile_sleep_supported & SUSP_SH_STANDBY) {
-		state = &dev->states[i++];
+		state = &drv->states[i++];
 		snprintf(state->name, CPUIDLE_NAME_LEN, "C3");
 		strncpy(state->desc, "SuperH Mobile Standby Mode [SF]",
 			CPUIDLE_DESC_LEN);
@@ -112,7 +115,10 @@ void sh_mobile_setup_cpuidle(void)
 		state->enter = cpuidle_sleep_enter;
 	}
 
+	drv->state_count = i;
 	dev->state_count = i;
 
+	cpuidle_register_driver(&cpuidle_driver);
+
 	cpuidle_register_device(dev);
 }

arch/x86/platform/mrst/pmu.c

@@ -70,7 +70,7 @@ static struct mrst_device mrst_devs[] = {
 /* 24 */ { 0x4110, 0 },			/* Lincroft */
 };
 
-/* n.b. We ignore PCI-id 0x815 in LSS9 b/c MeeGo has no driver for it */
+/* n.b. We ignore PCI-id 0x815 in LSS9 b/c Linux has no driver for it */
 static u16 mrst_lss9_pci_ids[] = {0x080a, 0x0814, 0};
 static u16 mrst_lss10_pci_ids[] = {0x0800, 0x0801, 0x0802, 0x0803,
 					0x0804, 0x0805, 0x080f, 0};

drivers/acpi/processor_driver.c

@@ -426,7 +426,7 @@ static int acpi_cpu_soft_notify(struct notifier_block *nfb,
 
 	if (action == CPU_ONLINE && pr) {
 		acpi_processor_ppc_has_changed(pr, 0);
-		acpi_processor_cst_has_changed(pr);
+		acpi_processor_hotplug(pr);
 		acpi_processor_reevaluate_tstate(pr, action);
 		acpi_processor_tstate_has_changed(pr);
 	}
@@ -503,8 +503,7 @@ static int __cpuinit acpi_processor_add(struct acpi_device *device)
 	acpi_processor_get_throttling_info(pr);
 	acpi_processor_get_limit_info(pr);
 
-
-	if (cpuidle_get_driver() == &acpi_idle_driver)
+	if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver)
 		acpi_processor_power_init(pr, device);
 
 	pr->cdev = thermal_cooling_device_register("Processor", device,
@@ -800,17 +799,9 @@ static int __init acpi_processor_init(void)
 
 	memset(&errata, 0, sizeof(errata));
 
-	if (!cpuidle_register_driver(&acpi_idle_driver)) {
-		printk(KERN_DEBUG "ACPI: %s registered with cpuidle\n",
-			acpi_idle_driver.name);
-	} else {
-		printk(KERN_DEBUG "ACPI: acpi_idle yielding to %s\n",
-			cpuidle_get_driver()->name);
-	}
-
 	result = acpi_bus_register_driver(&acpi_processor_driver);
 	if (result < 0)
-		goto out_cpuidle;
+		return result;
 
 	acpi_processor_install_hotplug_notify();
 
@@ -821,11 +812,6 @@ static int __init acpi_processor_init(void)
 	acpi_processor_throttling_init();
 
 	return 0;
-
-out_cpuidle:
-	cpuidle_unregister_driver(&acpi_idle_driver);
-
-	return result;
 }
 
 static void __exit acpi_processor_exit(void)

drivers/cpuidle/cpuidle.c

@@ -61,8 +61,9 @@ static int __cpuidle_register_device(struct cpuidle_device *dev);
 int cpuidle_idle_call(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_driver *drv = cpuidle_get_driver();
 	struct cpuidle_state *target_state;
-	int next_state;
+	int next_state, entered_state;
 
 	if (off)
 		return -ENODEV;
@@ -83,45 +84,36 @@ int cpuidle_idle_call(void)
 	hrtimer_peek_ahead_timers();
 #endif
 
-	/*
-	 * Call the device's prepare function before calling the
-	 * governor's select function.  ->prepare gives the device's
-	 * cpuidle driver a chance to update any dynamic information
-	 * of its cpuidle states for the current idle period, e.g.
-	 * state availability, latencies, residencies, etc.
-	 */
-	if (dev->prepare)
-		dev->prepare(dev);
-
 	/* ask the governor for the next state */
-	next_state = cpuidle_curr_governor->select(dev);
+	next_state = cpuidle_curr_governor->select(drv, dev);
 	if (need_resched()) {
 		local_irq_enable();
 		return 0;
 	}
 
-	target_state = &dev->states[next_state];
-
-	/* enter the state and update stats */
-	dev->last_state = target_state;
+	target_state = &drv->states[next_state];
 
 	trace_power_start(POWER_CSTATE, next_state, dev->cpu);
 	trace_cpu_idle(next_state, dev->cpu);
 
-	dev->last_residency = target_state->enter(dev, target_state);
+	entered_state = target_state->enter(dev, drv, next_state);
 
 	trace_power_end(dev->cpu);
 	trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
 
-	if (dev->last_state)
-		target_state = dev->last_state;
-
-	target_state->time += (unsigned long long)dev->last_residency;
-	target_state->usage++;
+	if (entered_state >= 0) {
+		/* Update cpuidle counters */
+		/* This can be moved to within driver enter routine
+		 * but that results in multiple copies of same code.
+		 */
+		dev->states_usage[entered_state].time +=
+				(unsigned long long)dev->last_residency;
+		dev->states_usage[entered_state].usage++;
+	}
 
 	/* give the governor an opportunity to reflect on the outcome */
 	if (cpuidle_curr_governor->reflect)
-		cpuidle_curr_governor->reflect(dev);
+		cpuidle_curr_governor->reflect(dev, entered_state);
 
 	return 0;
 }
@@ -172,11 +164,11 @@ void cpuidle_resume_and_unlock(void)
 EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock);
 
 #ifdef CONFIG_ARCH_HAS_CPU_RELAX
-static int poll_idle(struct cpuidle_device *dev, struct cpuidle_state *st)
+static int poll_idle(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index)
 {
 	ktime_t	t1, t2;
 	s64 diff;
-	int ret;
 
 	t1 = ktime_get();
 	local_irq_enable();
@@ -188,15 +180,14 @@ static int poll_idle(struct cpuidle_device *dev, struct cpuidle_state *st)
 	if (diff > INT_MAX)
 		diff = INT_MAX;
 
-	ret = (int) diff;
-	return ret;
+	dev->last_residency = (int) diff;
+
+	return index;
 }
 
-static void poll_idle_init(struct cpuidle_device *dev)
+static void poll_idle_init(struct cpuidle_driver *drv)
 {
-	struct cpuidle_state *state = &dev->states[0];
-
-	cpuidle_set_statedata(state, NULL);
+	struct cpuidle_state *state = &drv->states[0];
 
 	snprintf(state->name, CPUIDLE_NAME_LEN, "POLL");
 	snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE");
@@ -207,7 +198,7 @@ static void poll_idle_init(struct cpuidle_device *dev)
 	state->enter = poll_idle;
 }
 #else
-static void poll_idle_init(struct cpuidle_device *dev) {}
+static void poll_idle_init(struct cpuidle_driver *drv) {}
 #endif /* CONFIG_ARCH_HAS_CPU_RELAX */
 
 /**
@@ -234,21 +225,20 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 			return ret;
 	}
 
-	poll_idle_init(dev);
+	poll_idle_init(cpuidle_get_driver());
 
 	if ((ret = cpuidle_add_state_sysfs(dev)))
 		return ret;
 
 	if (cpuidle_curr_governor->enable &&
-	    (ret = cpuidle_curr_governor->enable(dev)))
+	    (ret = cpuidle_curr_governor->enable(cpuidle_get_driver(), dev)))
 		goto fail_sysfs;
 
 	for (i = 0; i < dev->state_count; i++) {
-		dev->states[i].usage = 0;
-		dev->states[i].time = 0;
+		dev->states_usage[i].usage = 0;
+		dev->states_usage[i].time = 0;
 	}
 	dev->last_residency = 0;
-	dev->last_state = NULL;
 
 	smp_wmb();
 
@@ -282,7 +272,7 @@ void cpuidle_disable_device(struct cpuidle_device *dev)
 	dev->enabled = 0;
 
 	if (cpuidle_curr_governor->disable)
-		cpuidle_curr_governor->disable(dev);
+		cpuidle_curr_governor->disable(cpuidle_get_driver(), dev);
 
 	cpuidle_remove_state_sysfs(dev);
 	enabled_devices--;
@@ -310,26 +300,6 @@ static int __cpuidle_register_device(struct cpuidle_device *dev)
 
 	init_completion(&dev->kobj_unregister);
 
-	/*
-	 * cpuidle driver should set the dev->power_specified bit
-	 * before registering the device if the driver provides
-	 * power_usage numbers.
-	 *
-	 * For those devices whose ->power_specified is not set,
-	 * we fill in power_usage with decreasing values as the
-	 * cpuidle code has an implicit assumption that state Cn
-	 * uses less power than C(n-1).
-	 *
-	 * With CONFIG_ARCH_HAS_CPU_RELAX, C0 is already assigned
-	 * an power value of -1.  So we use -2, -3, etc, for other
-	 * c-states.
-	 */
-	if (!dev->power_specified) {
-		int i;
-		for (i = CPUIDLE_DRIVER_STATE_START; i < dev->state_count; i++)
-			dev->states[i].power_usage = -1 - i;
-	}
-
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
 	list_add(&dev->device_list, &cpuidle_detected_devices);
 	if ((ret = cpuidle_add_sysfs(sys_dev))) {

drivers/cpuidle/driver.c

@@ -17,6 +17,30 @@
 static struct cpuidle_driver *cpuidle_curr_driver;
 DEFINE_SPINLOCK(cpuidle_driver_lock);
 
+static void __cpuidle_register_driver(struct cpuidle_driver *drv)
+{
+	int i;
+	/*
+	 * cpuidle driver should set the drv->power_specified bit
+	 * before registering if the driver provides
+	 * power_usage numbers.
+	 *
+	 * If power_specified is not set,
+	 * we fill in power_usage with decreasing values as the
+	 * cpuidle code has an implicit assumption that state Cn
+	 * uses less power than C(n-1).
+	 *
+	 * With CONFIG_ARCH_HAS_CPU_RELAX, C0 is already assigned
+	 * an power value of -1.  So we use -2, -3, etc, for other
+	 * c-states.
+	 */
+	if (!drv->power_specified) {
+		for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++)
+			drv->states[i].power_usage = -1 - i;
+	}
+}
+
+
 /**
  * cpuidle_register_driver - registers a driver
  * @drv: the driver
@@ -34,6 +58,7 @@ int cpuidle_register_driver(struct cpuidle_driver *drv)
 		spin_unlock(&cpuidle_driver_lock);
 		return -EBUSY;
 	}
+	__cpuidle_register_driver(drv);
 	cpuidle_curr_driver = drv;
 	spin_unlock(&cpuidle_driver_lock);
 

drivers/cpuidle/governors/ladder.c

@@ -60,9 +60,11 @@ static inline void ladder_do_selection(struct ladder_device *ldev,
 
 /**
  * ladder_select_state - selects the next state to enter
+ * @drv: cpuidle driver
  * @dev: the CPU
  */
-static int ladder_select_state(struct cpuidle_device *dev)
+static int ladder_select_state(struct cpuidle_driver *drv,
+				struct cpuidle_device *dev)
 {
 	struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
 	struct ladder_device_state *last_state;
@@ -77,15 +79,17 @@ static int ladder_select_state(struct cpuidle_device *dev)
 
 	last_state = &ldev->states[last_idx];
 
-	if (dev->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID)
-		last_residency = cpuidle_get_last_residency(dev) - dev->states[last_idx].exit_latency;
+	if (drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) {
+		last_residency = cpuidle_get_last_residency(dev) - \
+					 drv->states[last_idx].exit_latency;
+	}
 	else
 		last_residency = last_state->threshold.promotion_time + 1;
 
 	/* consider promotion */
-	if (last_idx < dev->state_count - 1 &&
+	if (last_idx < drv->state_count - 1 &&
 	    last_residency > last_state->threshold.promotion_time &&
-	    dev->states[last_idx + 1].exit_latency <= latency_req) {
+	    drv->states[last_idx + 1].exit_latency <= latency_req) {
 		last_state->stats.promotion_count++;
 		last_state->stats.demotion_count = 0;
 		if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) {
@@ -96,11 +100,11 @@ static int ladder_select_state(struct cpuidle_device *dev)
 
 	/* consider demotion */
 	if (last_idx > CPUIDLE_DRIVER_STATE_START &&
-	    dev->states[last_idx].exit_latency > latency_req) {
+	    drv->states[last_idx].exit_latency > latency_req) {
 		int i;
 
 		for (i = last_idx - 1; i > CPUIDLE_DRIVER_STATE_START; i--) {
-			if (dev->states[i].exit_latency <= latency_req)
+			if (drv->states[i].exit_latency <= latency_req)
 				break;
 		}
 		ladder_do_selection(ldev, last_idx, i);
@@ -123,9 +127,11 @@ static int ladder_select_state(struct cpuidle_device *dev)
 
 /**
  * ladder_enable_device - setup for the governor
+ * @drv: cpuidle driver
  * @dev: the CPU
  */
-static int ladder_enable_device(struct cpuidle_device *dev)
+static int ladder_enable_device(struct cpuidle_driver *drv,
+				struct cpuidle_device *dev)
 {
 	int i;
 	struct ladder_device *ldev = &per_cpu(ladder_devices, dev->cpu);
@@ -134,8 +140,8 @@ static int ladder_enable_device(struct cpuidle_device *dev)
 
 	ldev->last_state_idx = CPUIDLE_DRIVER_STATE_START;
 
-	for (i = 0; i < dev->state_count; i++) {
-		state = &dev->states[i];
+	for (i = 0; i < drv->state_count; i++) {
+		state = &drv->states[i];
 		lstate = &ldev->states[i];
 
 		lstate->stats.promotion_count = 0;
@@ -144,7 +150,7 @@ static int ladder_enable_device(struct cpuidle_device *dev)
 		lstate->threshold.promotion_count = PROMOTION_COUNT;
 		lstate->threshold.demotion_count = DEMOTION_COUNT;
 
-		if (i < dev->state_count - 1)
+		if (i < drv->state_count - 1)
 			lstate->threshold.promotion_time = state->exit_latency;
 		if (i > 0)
 			lstate->threshold.demotion_time = state->exit_latency;
@@ -153,11 +159,24 @@ static int ladder_enable_device(struct cpuidle_device *dev)
 	return 0;
 }
 
+/**
+ * ladder_reflect - update the correct last_state_idx
+ * @dev: the CPU
+ * @index: the index of actual state entered
+ */
+static void ladder_reflect(struct cpuidle_device *dev, int index)
+{
+	struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+	if (index > 0)
+		ldev->last_state_idx = index;
+}
+
 static struct cpuidle_governor ladder_governor = {
 	.name =		"ladder",
 	.rating =	10,
 	.enable =	ladder_enable_device,
 	.select =	ladder_select_state,
+	.reflect =	ladder_reflect,
 	.owner =	THIS_MODULE,
 };
 

drivers/cpuidle/governors/menu.c

@@ -182,7 +182,7 @@ static inline int performance_multiplier(void)
 
 static DEFINE_PER_CPU(struct menu_device, menu_devices);
 
-static void menu_update(struct cpuidle_device *dev);
+static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
 
 /* This implements DIV_ROUND_CLOSEST but avoids 64 bit division */
 static u64 div_round64(u64 dividend, u32 divisor)
@@ -228,9 +228,10 @@ static void detect_repeating_patterns(struct menu_device *data)
 
 /**
  * menu_select - selects the next idle state to enter
+ * @drv: cpuidle driver containing state data
  * @dev: the CPU
  */
-static int menu_select(struct cpuidle_device *dev)
+static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = &__get_cpu_var(menu_devices);
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
@@ -240,7 +241,7 @@ static int menu_select(struct cpuidle_device *dev)
 	struct timespec t;
 
 	if (data->needs_update) {
-		menu_update(dev);
+		menu_update(drv, dev);
 		data->needs_update = 0;
 	}
 
@@ -285,11 +286,9 @@ static int menu_select(struct cpuidle_device *dev)
 	 * Find the idle state with the lowest power while satisfying
 	 * our constraints.
 	 */
-	for (i = CPUIDLE_DRIVER_STATE_START; i < dev->state_count; i++) {
-		struct cpuidle_state *s = &dev->states[i];
+	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
 
-		if (s->flags & CPUIDLE_FLAG_IGNORE)
-			continue;
 		if (s->target_residency > data->predicted_us)
 			continue;
 		if (s->exit_latency > latency_req)
@@ -310,26 +309,30 @@ static int menu_select(struct cpuidle_device *dev)
 /**
  * menu_reflect - records that data structures need update
  * @dev: the CPU
+ * @index: the index of actual entered state
  *
  * 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)
+static void menu_reflect(struct cpuidle_device *dev, int index)
 {
 	struct menu_device *data = &__get_cpu_var(menu_devices);
+	data->last_state_idx = index;
+	if (index >= 0)
 		data->needs_update = 1;
 }
 
 /**
  * menu_update - attempts to guess what happened after entry
+ * @drv: cpuidle driver containing state data
  * @dev: the CPU
  */
-static void menu_update(struct cpuidle_device *dev)
+static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = &__get_cpu_var(menu_devices);
 	int last_idx = data->last_state_idx;
 	unsigned int last_idle_us = cpuidle_get_last_residency(dev);
-	struct cpuidle_state *target = &dev->states[last_idx];
+	struct cpuidle_state *target = &drv->states[last_idx];
 	unsigned int measured_us;
 	u64 new_factor;
 
@@ -383,9 +386,11 @@ static void menu_update(struct cpuidle_device *dev)
 
 /**
  * menu_enable_device - scans a CPU's states and does setup
+ * @drv: cpuidle driver
  * @dev: the CPU
  */
-static int menu_enable_device(struct cpuidle_device *dev)
+static int menu_enable_device(struct cpuidle_driver *drv,
+				struct cpuidle_device *dev)
 {
 	struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
 

drivers/cpuidle/sysfs.c

@@ -216,7 +216,8 @@ static struct kobj_type ktype_cpuidle = {
 
 struct cpuidle_state_attr {
 	struct attribute attr;
-	ssize_t (*show)(struct cpuidle_state *, char *);
+	ssize_t (*show)(struct cpuidle_state *, \
+					struct cpuidle_state_usage *, char *);
 	ssize_t (*store)(struct cpuidle_state *, const char *, size_t);
 };
 
@@ -224,19 +225,22 @@ struct cpuidle_state_attr {
 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) \
+static ssize_t show_state_##_name(struct cpuidle_state *state, \
+			 struct cpuidle_state_usage *state_usage, char *buf) \
 { \
 	return sprintf(buf, "%u\n", state->_name);\
 }
 
 #define define_show_state_ull_function(_name) \
-static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \
+static ssize_t show_state_##_name(struct cpuidle_state *state, \
+			struct cpuidle_state_usage *state_usage, char *buf) \
 { \
-	return sprintf(buf, "%llu\n", state->_name);\
+	return sprintf(buf, "%llu\n", state_usage->_name);\
 }
 
 #define define_show_state_str_function(_name) \
-static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \
+static ssize_t show_state_##_name(struct cpuidle_state *state, \
+			struct cpuidle_state_usage *state_usage, char *buf) \
 { \
 	if (state->_name[0] == '\0')\
 		return sprintf(buf, "<null>\n");\
@@ -269,16 +273,18 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 
 #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 kobj_to_state_usage(k) (kobj_to_state_obj(k)->state_usage)
 #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_usage *state_usage = kobj_to_state_usage(kobj);
 	struct cpuidle_state_attr * cattr = attr_to_stateattr(attr);
 
 	if (cattr->show)
-		ret = cattr->show(state, buf);
+		ret = cattr->show(state, state_usage, buf);
 
 	return ret;
 }
@@ -316,13 +322,15 @@ int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 {
 	int i, ret = -ENOMEM;
 	struct cpuidle_state_kobj *kobj;
+	struct cpuidle_driver *drv = cpuidle_get_driver();
 
 	/* state statistics */
 	for (i = 0; i < device->state_count; i++) {
 		kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL);
 		if (!kobj)
 			goto error_state;
-		kobj->state = &device->states[i];
+		kobj->state = &drv->states[i];
+		kobj->state_usage = &device->states_usage[i];
 		init_completion(&kobj->kobj_unregister);
 
 		ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle, &device->kobj,

drivers/idle/intel_idle.c

@@ -81,7 +81,8 @@ static unsigned int mwait_substates;
 static unsigned int lapic_timer_reliable_states = (1 << 1);	 /* Default to only C1 */
 
 static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
-static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state);
+static int intel_idle(struct cpuidle_device *dev,
+			struct cpuidle_driver *drv, int index);
 
 static struct cpuidle_state *cpuidle_state_table;
 
@@ -109,7 +110,6 @@ static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C1 */
 		.name = "C1-NHM",
 		.desc = "MWAIT 0x00",
-		.driver_data = (void *) 0x00,
 		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 3,
 		.target_residency = 6,
@@ -117,7 +117,6 @@ static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C2 */
 		.name = "C3-NHM",
 		.desc = "MWAIT 0x10",
-		.driver_data = (void *) 0x10,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 20,
 		.target_residency = 80,
@@ -125,7 +124,6 @@ static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C3 */
 		.name = "C6-NHM",
 		.desc = "MWAIT 0x20",
-		.driver_data = (void *) 0x20,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 200,
 		.target_residency = 800,
@@ -137,7 +135,6 @@ static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C1 */
 		.name = "C1-SNB",
 		.desc = "MWAIT 0x00",
-		.driver_data = (void *) 0x00,
 		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 1,
 		.target_residency = 1,
@@ -145,7 +142,6 @@ static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C2 */
 		.name = "C3-SNB",
 		.desc = "MWAIT 0x10",
-		.driver_data = (void *) 0x10,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
 		.target_residency = 211,
@@ -153,7 +149,6 @@ static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C3 */
 		.name = "C6-SNB",
 		.desc = "MWAIT 0x20",
-		.driver_data = (void *) 0x20,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 104,
 		.target_residency = 345,
@@ -161,7 +156,6 @@ static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C4 */
 		.name = "C7-SNB",
 		.desc = "MWAIT 0x30",
-		.driver_data = (void *) 0x30,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 109,
 		.target_residency = 345,
@@ -173,7 +167,6 @@ static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C1 */
 		.name = "C1-ATM",
 		.desc = "MWAIT 0x00",
-		.driver_data = (void *) 0x00,
 		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 1,
 		.target_residency = 4,
@@ -181,7 +174,6 @@ static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C2 */
 		.name = "C2-ATM",
 		.desc = "MWAIT 0x10",
-		.driver_data = (void *) 0x10,
 		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 20,
 		.target_residency = 80,
@@ -190,7 +182,6 @@ static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C4 */
 		.name = "C4-ATM",
 		.desc = "MWAIT 0x30",
-		.driver_data = (void *) 0x30,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 100,
 		.target_residency = 400,
@@ -199,23 +190,55 @@ static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C6 */
 		.name = "C6-ATM",
 		.desc = "MWAIT 0x52",
-		.driver_data = (void *) 0x52,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 140,
 		.target_residency = 560,
 		.enter = &intel_idle },
 };
 
+static int get_driver_data(int cstate)
+{
+	int driver_data;
+	switch (cstate) {
+
+	case 1:	/* MWAIT C1 */
+		driver_data = 0x00;
+		break;
+	case 2:	/* MWAIT C2 */
+		driver_data = 0x10;
+		break;
+	case 3:	/* MWAIT C3 */
+		driver_data = 0x20;
+		break;
+	case 4:	/* MWAIT C4 */
+		driver_data = 0x30;
+		break;
+	case 5:	/* MWAIT C5 */
+		driver_data = 0x40;
+		break;
+	case 6:	/* MWAIT C6 */
+		driver_data = 0x52;
+		break;
+	default:
+		driver_data = 0x00;
+	}
+	return driver_data;
+}
+
 /**
  * intel_idle
  * @dev: cpuidle_device
- * @state: cpuidle state
+ * @drv: cpuidle driver
+ * @index: index of cpuidle state
  *
  */
-static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state)
+static int intel_idle(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index)
 {
 	unsigned long ecx = 1; /* break on interrupt flag */
-	unsigned long eax = (unsigned long)cpuidle_get_statedata(state);
+	struct cpuidle_state *state = &drv->states[index];
+	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
+	unsigned long eax = (unsigned long)cpuidle_get_statedata(state_usage);
 	unsigned int cstate;
 	ktime_t kt_before, kt_after;
 	s64 usec_delta;
@@ -256,7 +279,10 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state)
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
 
-	return usec_delta;
+	/* Update cpuidle counters */
+	dev->last_residency = (int)usec_delta;
+
+	return index;
 }
 
 static void __setup_broadcast_timer(void *arg)
@@ -396,6 +422,60 @@ static void intel_idle_cpuidle_devices_uninit(void)
 	free_percpu(intel_idle_cpuidle_devices);
 	return;
 }
+/*
+ * intel_idle_cpuidle_driver_init()
+ * allocate, initialize cpuidle_states
+ */
+static int intel_idle_cpuidle_driver_init(void)
+{
+	int cstate;
+	struct cpuidle_driver *drv = &intel_idle_driver;
+
+	drv->state_count = 1;
+
+	for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
+		int num_substates;
+
+		if (cstate > max_cstate) {
+			printk(PREFIX "max_cstate %d reached\n",
+				max_cstate);
+			break;
+		}
+
+		/* does the state exist in CPUID.MWAIT? */
+		num_substates = (mwait_substates >> ((cstate) * 4))
+					& MWAIT_SUBSTATE_MASK;
+		if (num_substates == 0)
+			continue;
+		/* is the state not enabled? */
+		if (cpuidle_state_table[cstate].enter == NULL) {
+			/* does the driver not know about the state? */
+			if (*cpuidle_state_table[cstate].name == '\0')
+				pr_debug(PREFIX "unaware of model 0x%x"
+					" MWAIT %d please"
+					" contact lenb@kernel.org",
+				boot_cpu_data.x86_model, cstate);
+			continue;
+		}
+
+		if ((cstate > 2) &&
+			!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+			mark_tsc_unstable("TSC halts in idle"
+					" states deeper than C2");
+
+		drv->states[drv->state_count] =	/* structure copy */
+			cpuidle_state_table[cstate];
+
+		drv->state_count += 1;
+	}
+
+	if (auto_demotion_disable_flags)
+		smp_call_function(auto_demotion_disable, NULL, 1);
+
+	return 0;
+}
+
+
 /*
  * intel_idle_cpuidle_devices_init()
  * allocate, initialize, register cpuidle_devices
@@ -430,22 +510,11 @@ static int intel_idle_cpuidle_devices_init(void)
 				continue;
 			/* is the state not enabled? */
 			if (cpuidle_state_table[cstate].enter == NULL) {
-				/* does the driver not know about the state? */
-				if (*cpuidle_state_table[cstate].name == '\0')
-					pr_debug(PREFIX "unaware of model 0x%x"
-						" MWAIT %d please"
-						" contact lenb@kernel.org",
-					boot_cpu_data.x86_model, cstate);
 				continue;
 			}
 
-			if ((cstate > 2) &&
-				!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
-				mark_tsc_unstable("TSC halts in idle"
-					" states deeper than C2");
-
-			dev->states[dev->state_count] =	/* structure copy */
-				cpuidle_state_table[cstate];
+			dev->states_usage[dev->state_count].driver_data =
+				(void *)get_driver_data(cstate);
 
 			dev->state_count += 1;
 		}
@@ -458,8 +527,6 @@ static int intel_idle_cpuidle_devices_init(void)
 			return -EIO;
 		}
 	}
-	if (auto_demotion_disable_flags)
-		smp_call_function(auto_demotion_disable, NULL, 1);
 
 	return 0;
 }
@@ -477,6 +544,7 @@ static int __init intel_idle_init(void)
 	if (retval)
 		return retval;
 
+	intel_idle_cpuidle_driver_init();
 	retval = cpuidle_register_driver(&intel_idle_driver);
 	if (retval) {
 		printk(KERN_DEBUG PREFIX "intel_idle yielding to %s",

include/acpi/processor.h

@@ -329,6 +329,7 @@ extern void acpi_processor_throttling_init(void);
 int acpi_processor_power_init(struct acpi_processor *pr,
 			      struct acpi_device *device);
 int acpi_processor_cst_has_changed(struct acpi_processor *pr);
+int acpi_processor_hotplug(struct acpi_processor *pr);
 int acpi_processor_power_exit(struct acpi_processor *pr,
 			      struct acpi_device *device);
 int acpi_processor_suspend(struct acpi_device * device, pm_message_t state);

include/linux/cpuidle.h

@@ -22,57 +22,62 @@
 #define CPUIDLE_DESC_LEN	32
 
 struct cpuidle_device;
+struct cpuidle_driver;
 
 
 /****************************
  * CPUIDLE DEVICE INTERFACE *
  ****************************/
 
+struct cpuidle_state_usage {
+	void		*driver_data;
+
+	unsigned long long	usage;
+	unsigned long long	time; /* in US */
+};
+
 struct cpuidle_state {
 	char		name[CPUIDLE_NAME_LEN];
 	char		desc[CPUIDLE_DESC_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 long long	usage;
-	unsigned long long	time; /* in US */
-
 	int (*enter)	(struct cpuidle_device *dev,
-			 struct cpuidle_state *state);
+			struct cpuidle_driver *drv,
+			int index);
 };
 
 /* Idle State Flags */
 #define CPUIDLE_FLAG_TIME_VALID	(0x01) /* is residency time measurable? */
-#define CPUIDLE_FLAG_IGNORE	(0x100) /* ignore during this idle period */
 
 #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000)
 
 /**
  * cpuidle_get_statedata - retrieves private driver state data
- * @state: the state
+ * @st_usage: the state usage statistics
  */
-static inline void * cpuidle_get_statedata(struct cpuidle_state *state)
+static inline void *cpuidle_get_statedata(struct cpuidle_state_usage *st_usage)
 {
-	return state->driver_data;
+	return st_usage->driver_data;
 }
 
 /**
  * cpuidle_set_statedata - stores private driver state data
- * @state: the state
+ * @st_usage: the state usage statistics
  * @data: the private data
  */
 static inline void
-cpuidle_set_statedata(struct cpuidle_state *state, void *data)
+cpuidle_set_statedata(struct cpuidle_state_usage *st_usage, void *data)
 {
-	state->driver_data = data;
+	st_usage->driver_data = data;
 }
 
 struct cpuidle_state_kobj {
 	struct cpuidle_state *state;
+	struct cpuidle_state_usage *state_usage;
 	struct completion kobj_unregister;
 	struct kobject kobj;
 };
@@ -80,22 +85,17 @@ struct cpuidle_state_kobj {
 struct cpuidle_device {
 	unsigned int		registered:1;
 	unsigned int		enabled:1;
-	unsigned int		power_specified:1;
 	unsigned int		cpu;
 
 	int			last_residency;
 	int			state_count;
-	struct cpuidle_state	states[CPUIDLE_STATE_MAX];
+	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];
 	struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];
-	struct cpuidle_state	*last_state;
 
 	struct list_head 	device_list;
 	struct kobject		kobj;
 	struct completion	kobj_unregister;
 	void			*governor_data;
-	struct cpuidle_state	*safe_state;
-
-	int (*prepare)		(struct cpuidle_device *dev);
 };
 
 DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
@@ -119,6 +119,11 @@ static inline int cpuidle_get_last_residency(struct cpuidle_device *dev)
 struct cpuidle_driver {
 	char			name[CPUIDLE_NAME_LEN];
 	struct module 		*owner;
+
+	unsigned int		power_specified:1;
+	struct cpuidle_state	states[CPUIDLE_STATE_MAX];
+	int			state_count;
+	int			safe_state_index;
 };
 
 #ifdef CONFIG_CPU_IDLE
@@ -165,11 +170,14 @@ struct cpuidle_governor {
 	struct list_head 	governor_list;
 	unsigned int		rating;
 
-	int  (*enable)		(struct cpuidle_device *dev);
-	void (*disable)		(struct cpuidle_device *dev);
+	int  (*enable)		(struct cpuidle_driver *drv,
+					struct cpuidle_device *dev);
+	void (*disable)		(struct cpuidle_driver *drv,
+					struct cpuidle_device *dev);
 
-	int  (*select)		(struct cpuidle_device *dev);
-	void (*reflect)		(struct cpuidle_device *dev);
+	int  (*select)		(struct cpuidle_driver *drv,
+					struct cpuidle_device *dev);
+	void (*reflect)		(struct cpuidle_device *dev, int index);
 
 	struct module 		*owner;
 };

tools/power/x86/turbostat/turbostat.c

@@ -162,19 +162,21 @@ void print_header(void)
 
 void dump_cnt(struct counters *cnt)
 {
-	fprintf(stderr, "package: %d ", cnt->pkg);
-	fprintf(stderr, "core:: %d ", cnt->core);
-	fprintf(stderr, "CPU: %d ", cnt->cpu);
-	fprintf(stderr, "TSC: %016llX\n", cnt->tsc);
-	fprintf(stderr, "c3: %016llX\n", cnt->c3);
-	fprintf(stderr, "c6: %016llX\n", cnt->c6);
-	fprintf(stderr, "c7: %016llX\n", cnt->c7);
-	fprintf(stderr, "aperf: %016llX\n", cnt->aperf);
-	fprintf(stderr, "pc2: %016llX\n", cnt->pc2);
-	fprintf(stderr, "pc3: %016llX\n", cnt->pc3);
-	fprintf(stderr, "pc6: %016llX\n", cnt->pc6);
-	fprintf(stderr, "pc7: %016llX\n", cnt->pc7);
-	fprintf(stderr, "msr0x%x: %016llX\n", extra_msr_offset, cnt->extra_msr);
+	if (!cnt)
+		return;
+	if (cnt->pkg) fprintf(stderr, "package: %d ", cnt->pkg);
+	if (cnt->core) fprintf(stderr, "core:: %d ", cnt->core);
+	if (cnt->cpu) fprintf(stderr, "CPU: %d ", cnt->cpu);
+	if (cnt->tsc) fprintf(stderr, "TSC: %016llX\n", cnt->tsc);
+	if (cnt->c3) fprintf(stderr, "c3: %016llX\n", cnt->c3);
+	if (cnt->c6) fprintf(stderr, "c6: %016llX\n", cnt->c6);
+	if (cnt->c7) fprintf(stderr, "c7: %016llX\n", cnt->c7);
+	if (cnt->aperf) fprintf(stderr, "aperf: %016llX\n", cnt->aperf);
+	if (cnt->pc2) fprintf(stderr, "pc2: %016llX\n", cnt->pc2);
+	if (cnt->pc3) fprintf(stderr, "pc3: %016llX\n", cnt->pc3);
+	if (cnt->pc6) fprintf(stderr, "pc6: %016llX\n", cnt->pc6);
+	if (cnt->pc7) fprintf(stderr, "pc7: %016llX\n", cnt->pc7);
+	if (cnt->extra_msr) fprintf(stderr, "msr0x%x: %016llX\n", extra_msr_offset, cnt->extra_msr);
 }
 
 void dump_list(struct counters *cnt)