Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux: (35 commits)
  PM idle: remove global declaration of pm_idle
  unicore32 idle: delete stray pm_idle comment
  openrisc idle: delete pm_idle
  mn10300 idle: delete pm_idle
  microblaze idle: delete pm_idle
  m32r idle: delete pm_idle, and other dead idle code
  ia64 idle: delete pm_idle
  cris idle: delete idle and pm_idle
  ARM64 idle: delete pm_idle
  ARM idle: delete pm_idle
  blackfin idle: delete pm_idle
  sparc idle: rename pm_idle to sparc_idle
  sh idle: rename global pm_idle to static sh_idle
  x86 idle: rename global pm_idle to static x86_idle
  APM idle: register apm_cpu_idle via cpuidle
  tools/power turbostat: display SMI count by default
  intel_idle: export both C1 and C1E
  cpuidle: remove vestage definition of cpuidle_state_usage.driver_data
  x86 idle: remove 32-bit-only "no-hlt" parameter, hlt_works_ok flag
  x86 idle: remove mwait_idle() and "idle=mwait" cmdline param
  ...

Conflicts:
	arch/x86/kernel/process.c (with PM / tracing commit 43720bd)
	drivers/acpi/processor_idle.c (with ACPICA commit 4f84291)

2 files changed, 187 insertions, 140 deletions

diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index e606e3603d8..fc95308e9a1 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -28,19 +28,12 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
-#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/dmi.h>
-#include <linux/moduleparam.h>
-#include <linux/sched.h>	/* need_resched() */
-#include <linux/pm_qos.h>
+#include <linux/sched.h>       /* need_resched() */
 #include <linux/clockchips.h>
 #include <linux/cpuidle.h>
-#include <linux/irqflags.h>
 
 /*
  * Include the apic definitions for x86 to have the APIC timer related defines
@@ -52,23 +45,14 @@
 #include <asm/apic.h>
 #endif
 
-#include <asm/io.h>
-#include <asm/uaccess.h>
-
 #include <acpi/acpi_bus.h>
 #include <acpi/processor.h>
-#include <asm/processor.h>
 
 #define PREFIX "ACPI: "
 
 #define ACPI_PROCESSOR_CLASS            "processor"
 #define _COMPONENT              ACPI_PROCESSOR_COMPONENT
 ACPI_MODULE_NAME("processor_idle");
-#define PM_TIMER_TICK_NS		(1000000000ULL/ACPI_PM_TIMER_FREQUENCY)
-#define C2_OVERHEAD			1	/* 1us */
-#define C3_OVERHEAD			1	/* 1us */
-#define PM_TIMER_TICKS_TO_US(p)		\
-	(((p) * 1000)/(ACPI_PM_TIMER_FREQUENCY/1000))
 
 static unsigned int max_cstate __read_mostly = ACPI_PROCESSOR_MAX_POWER;
 module_param(max_cstate, uint, 0000);
@@ -82,10 +66,11 @@ module_param(latency_factor, uint, 0644);
 
 static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device);
 
+static struct acpi_processor_cx *acpi_cstate[CPUIDLE_STATE_MAX];
+
 static int disabled_by_idle_boot_param(void)
 {
 	return boot_option_idle_override == IDLE_POLL ||
-		boot_option_idle_override == IDLE_FORCE_MWAIT ||
 		boot_option_idle_override == IDLE_HALT;
 }
 
@@ -737,8 +722,7 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 		struct cpuidle_driver *drv, int index)
 {
 	struct acpi_processor *pr;
-	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
-	struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
+	struct acpi_processor_cx *cx = acpi_cstate[index];
 
 	pr = __this_cpu_read(processors);
 
@@ -761,8 +745,7 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
  */
 static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 {
-	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
-	struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
+	struct acpi_processor_cx *cx = acpi_cstate[index];
 
 	ACPI_FLUSH_CPU_CACHE();
 
@@ -792,8 +775,7 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 		struct cpuidle_driver *drv, int index)
 {
 	struct acpi_processor *pr;
-	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
-	struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
+	struct acpi_processor_cx *cx = acpi_cstate[index];
 
 	pr = __this_cpu_read(processors);
 
@@ -851,8 +833,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 		struct cpuidle_driver *drv, int index)
 {
 	struct acpi_processor *pr;
-	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
-	struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
+	struct acpi_processor_cx *cx = acpi_cstate[index];
 
 	pr = __this_cpu_read(processors);
 
@@ -944,13 +925,13 @@ struct cpuidle_driver acpi_idle_driver = {
  * device i.e. per-cpu data
  *
  * @pr: the ACPI processor
+ * @dev : the cpuidle device
  */
-static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr)
+static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr,
+					   struct cpuidle_device *dev)
 {
 	int i, count = CPUIDLE_DRIVER_STATE_START;
 	struct acpi_processor_cx *cx;
-	struct cpuidle_state_usage *state_usage;
-	struct cpuidle_device *dev = per_cpu(acpi_cpuidle_device, pr->id);
 
 	if (!pr->flags.power_setup_done)
 		return -EINVAL;
@@ -969,7 +950,6 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr)
 
 	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) {
 		cx = &pr->power.states[i];
-		state_usage = &dev->states_usage[count];
 
 		if (!cx->valid)
 			continue;
@@ -980,8 +960,7 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr)
 		    !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
 			continue;
 #endif
-
-		cpuidle_set_statedata(state_usage, cx);
+		acpi_cstate[count] = cx;
 
 		count++;
 		if (count == CPUIDLE_STATE_MAX)
@@ -1105,7 +1084,7 @@ int acpi_processor_hotplug(struct acpi_processor *pr)
 	cpuidle_disable_device(dev);
 	acpi_processor_get_power_info(pr);
 	if (pr->flags.power) {
-		acpi_processor_setup_cpuidle_cx(pr);
+		acpi_processor_setup_cpuidle_cx(pr, dev);
 		ret = cpuidle_enable_device(dev);
 	}
 	cpuidle_resume_and_unlock();
@@ -1163,8 +1142,8 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 				continue;
 			acpi_processor_get_power_info(_pr);
 			if (_pr->flags.power) {
-				acpi_processor_setup_cpuidle_cx(_pr);
 				dev = per_cpu(acpi_cpuidle_device, cpu);
+				acpi_processor_setup_cpuidle_cx(_pr, dev);
 				cpuidle_enable_device(dev);
 			}
 		}
@@ -1233,7 +1212,7 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr)
 			return -ENOMEM;
 		per_cpu(acpi_cpuidle_device, pr->id) = dev;
 
-		acpi_processor_setup_cpuidle_cx(pr);
+		acpi_processor_setup_cpuidle_cx(pr, dev);
 
 		/* Register per-cpu cpuidle_device. Cpuidle driver
 		 * must already be registered before registering device
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 2df9414a72f..5d667501386 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -74,7 +74,7 @@ static struct cpuidle_driver intel_idle_driver = {
 	.en_core_tk_irqen = 1,
 };
 /* intel_idle.max_cstate=0 disables driver */
-static int max_cstate = MWAIT_MAX_NUM_CSTATES - 1;
+static int max_cstate = CPUIDLE_STATE_MAX - 1;
 
 static unsigned int mwait_substates;
 
@@ -90,6 +90,7 @@ struct idle_cpu {
 	 * Indicate which enable bits to clear here.
 	 */
 	unsigned long auto_demotion_disable_flags;
+	bool disable_promotion_to_c1e;
 };
 
 static const struct idle_cpu *icpu;
@@ -109,162 +110,206 @@ static struct cpuidle_state *cpuidle_state_table;
 #define CPUIDLE_FLAG_TLB_FLUSHED	0x10000
 
 /*
+ * MWAIT takes an 8-bit "hint" in EAX "suggesting"
+ * the C-state (top nibble) and sub-state (bottom nibble)
+ * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
+ *
+ * We store the hint at the top of our "flags" for each state.
+ */
+#define flg2MWAIT(flags) (((flags) >> 24) & 0xFF)
+#define MWAIT2flg(eax) ((eax & 0xFF) << 24)
+
+/*
  * States are indexed by the cstate number,
  * which is also the index into the MWAIT hint array.
  * Thus C0 is a dummy.
  */
-static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = {
-	{ /* MWAIT C0 */ },
-	{ /* MWAIT C1 */
+static struct cpuidle_state nehalem_cstates[CPUIDLE_STATE_MAX] = {
+	{
 		.name = "C1-NHM",
 		.desc = "MWAIT 0x00",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 3,
 		.target_residency = 6,
 		.enter = &intel_idle },
-	{ /* MWAIT C2 */
+	{
+		.name = "C1E-NHM",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 20,
+		.enter = &intel_idle },
+	{
 		.name = "C3-NHM",
 		.desc = "MWAIT 0x10",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 20,
 		.target_residency = 80,
 		.enter = &intel_idle },
-	{ /* MWAIT C3 */
+	{
 		.name = "C6-NHM",
 		.desc = "MWAIT 0x20",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 200,
 		.target_residency = 800,
 		.enter = &intel_idle },
+	{
+		.enter = NULL }
 };
 
-static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
-	{ /* MWAIT C0 */ },
-	{ /* MWAIT C1 */
+static struct cpuidle_state snb_cstates[CPUIDLE_STATE_MAX] = {
+	{
 		.name = "C1-SNB",
 		.desc = "MWAIT 0x00",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
-		.exit_latency = 1,
-		.target_residency = 1,
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 2,
+		.target_residency = 2,
 		.enter = &intel_idle },
-	{ /* MWAIT C2 */
+	{
+		.name = "C1E-SNB",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 20,
+		.enter = &intel_idle },
+	{
 		.name = "C3-SNB",
 		.desc = "MWAIT 0x10",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
 		.target_residency = 211,
 		.enter = &intel_idle },
-	{ /* MWAIT C3 */
+	{
 		.name = "C6-SNB",
 		.desc = "MWAIT 0x20",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 104,
 		.target_residency = 345,
 		.enter = &intel_idle },
-	{ /* MWAIT C4 */
+	{
 		.name = "C7-SNB",
 		.desc = "MWAIT 0x30",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 109,
 		.target_residency = 345,
 		.enter = &intel_idle },
+	{
+		.enter = NULL }
 };
 
-static struct cpuidle_state ivb_cstates[MWAIT_MAX_NUM_CSTATES] = {
-	{ /* MWAIT C0 */ },
-	{ /* MWAIT C1 */
+static struct cpuidle_state ivb_cstates[CPUIDLE_STATE_MAX] = {
+	{
 		.name = "C1-IVB",
 		.desc = "MWAIT 0x00",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 1,
 		.target_residency = 1,
 		.enter = &intel_idle },
-	{ /* MWAIT C2 */
+	{
+		.name = "C1E-IVB",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 20,
+		.enter = &intel_idle },
+	{
 		.name = "C3-IVB",
 		.desc = "MWAIT 0x10",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
 		.target_residency = 156,
 		.enter = &intel_idle },
-	{ /* MWAIT C3 */
+	{
 		.name = "C6-IVB",
 		.desc = "MWAIT 0x20",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
 		.target_residency = 300,
 		.enter = &intel_idle },
-	{ /* MWAIT C4 */
+	{
 		.name = "C7-IVB",
 		.desc = "MWAIT 0x30",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 87,
 		.target_residency = 300,
 		.enter = &intel_idle },
+	{
+		.enter = NULL }
 };
 
-static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
-	{ /* MWAIT C0 */ },
-	{ /* MWAIT C1 */
-		.name = "C1-ATM",
+static struct cpuidle_state hsw_cstates[CPUIDLE_STATE_MAX] = {
+	{
+		.name = "C1-HSW",
 		.desc = "MWAIT 0x00",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
-		.exit_latency = 1,
-		.target_residency = 4,
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 2,
+		.target_residency = 2,
+		.enter = &intel_idle },
+	{
+		.name = "C1E-HSW",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 20,
+		.enter = &intel_idle },
+	{
+		.name = "C3-HSW",
+		.desc = "MWAIT 0x10",
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 33,
+		.target_residency = 100,
+		.enter = &intel_idle },
+	{
+		.name = "C6-HSW",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 133,
+		.target_residency = 400,
+		.enter = &intel_idle },
+	{
+		.name = "C7s-HSW",
+		.desc = "MWAIT 0x32",
+		.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 166,
+		.target_residency = 500,
+		.enter = &intel_idle },
+	{
+		.enter = NULL }
+};
+
+static struct cpuidle_state atom_cstates[CPUIDLE_STATE_MAX] = {
+	{
+		.name = "C1E-ATM",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 20,
 		.enter = &intel_idle },
-	{ /* MWAIT C2 */
+	{
 		.name = "C2-ATM",
 		.desc = "MWAIT 0x10",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 20,
 		.target_residency = 80,
 		.enter = &intel_idle },
-	{ /* MWAIT C3 */ },
-	{ /* MWAIT C4 */
+	{
 		.name = "C4-ATM",
 		.desc = "MWAIT 0x30",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 100,
 		.target_residency = 400,
 		.enter = &intel_idle },
-	{ /* MWAIT C5 */ },
-	{ /* MWAIT C6 */
+	{
 		.name = "C6-ATM",
 		.desc = "MWAIT 0x52",
-		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 140,
 		.target_residency = 560,
 		.enter = &intel_idle },
+	{
+		.enter = NULL }
 };
 
-static long 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
@@ -278,8 +323,7 @@ static int intel_idle(struct cpuidle_device *dev,
 {
 	unsigned long ecx = 1; /* break on interrupt flag */
 	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 long eax = flg2MWAIT(state->flags);
 	unsigned int cstate;
 	int cpu = smp_processor_id();
 
@@ -362,10 +406,19 @@ static void auto_demotion_disable(void *dummy)
 	msr_bits &= ~(icpu->auto_demotion_disable_flags);
 	wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
 }
+static void c1e_promotion_disable(void *dummy)
+{
+	unsigned long long msr_bits;
+
+	rdmsrl(MSR_IA32_POWER_CTL, msr_bits);
+	msr_bits &= ~0x2;
+	wrmsrl(MSR_IA32_POWER_CTL, msr_bits);
+}
 
 static const struct idle_cpu idle_cpu_nehalem = {
 	.state_table = nehalem_cstates,
 	.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
+	.disable_promotion_to_c1e = true,
 };
 
 static const struct idle_cpu idle_cpu_atom = {
@@ -379,10 +432,17 @@ static const struct idle_cpu idle_cpu_lincroft = {
 
 static const struct idle_cpu idle_cpu_snb = {
 	.state_table = snb_cstates,
+	.disable_promotion_to_c1e = true,
 };
 
 static const struct idle_cpu idle_cpu_ivb = {
 	.state_table = ivb_cstates,
+	.disable_promotion_to_c1e = true,
+};
+
+static const struct idle_cpu idle_cpu_hsw = {
+	.state_table = hsw_cstates,
+	.disable_promotion_to_c1e = true,
 };
 
 #define ICPU(model, cpu) \
@@ -402,6 +462,9 @@ static const struct x86_cpu_id intel_idle_ids[] = {
 	ICPU(0x2d, idle_cpu_snb),
 	ICPU(0x3a, idle_cpu_ivb),
 	ICPU(0x3e, idle_cpu_ivb),
+	ICPU(0x3c, idle_cpu_hsw),
+	ICPU(0x3f, idle_cpu_hsw),
+	ICPU(0x45, idle_cpu_hsw),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
@@ -484,32 +547,31 @@ static int intel_idle_cpuidle_driver_init(void)
 
 	drv->state_count = 1;
 
-	for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
-		int num_substates;
+	for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
+		int num_substates, mwait_hint, mwait_cstate, mwait_substate;
 
-		if (cstate > max_cstate) {
+		if (cpuidle_state_table[cstate].enter == NULL)
+			break;
+
+		if (cstate + 1 > max_cstate) {
 			printk(PREFIX "max_cstate %d reached\n",
 				max_cstate);
 			break;
 		}
 
+		mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags);
+		mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint);
+		mwait_substate = MWAIT_HINT2SUBSTATE(mwait_hint);
+
 		/* does the state exist in CPUID.MWAIT? */
-		num_substates = (mwait_substates >> ((cstate) * 4))
+		num_substates = (mwait_substates >> ((mwait_cstate + 1) * 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\n",
-				boot_cpu_data.x86_model, cstate);
+
+		/* if sub-state in table is not enumerated by CPUID */
+		if ((mwait_substate + 1) > num_substates)
 			continue;
-		}
 
-		if ((cstate > 2) &&
+		if (((mwait_cstate + 1) > 2) &&
 			!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 			mark_tsc_unstable("TSC halts in idle"
 					" states deeper than C2");
@@ -523,6 +585,9 @@ static int intel_idle_cpuidle_driver_init(void)
 	if (icpu->auto_demotion_disable_flags)
 		on_each_cpu(auto_demotion_disable, NULL, 1);
 
+	if (icpu->disable_promotion_to_c1e)	/* each-cpu is redundant */
+		on_each_cpu(c1e_promotion_disable, NULL, 1);
+
 	return 0;
 }
 
@@ -541,25 +606,28 @@ static int intel_idle_cpu_init(int cpu)
 
 	dev->state_count = 1;
 
-	for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
-		int num_substates;
+	for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
+		int num_substates, mwait_hint, mwait_cstate, mwait_substate;
+
+		if (cpuidle_state_table[cstate].enter == NULL)
+			continue;
 
-		if (cstate > max_cstate) {
+		if (cstate + 1 > max_cstate) {
 			printk(PREFIX "max_cstate %d reached\n", max_cstate);
 			break;
 		}
 
+		mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags);
+		mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint);
+		mwait_substate = MWAIT_HINT2SUBSTATE(mwait_hint);
+
 		/* 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)
-			continue;
+		num_substates = (mwait_substates >> ((mwait_cstate + 1) * 4))
+					& MWAIT_SUBSTATE_MASK;
 
-		dev->states_usage[dev->state_count].driver_data =
-			(void *)get_driver_data(cstate);
+		/* if sub-state in table is not enumerated by CPUID */
+		if ((mwait_substate + 1) > num_substates)
+			continue;
 
 		dev->state_count += 1;
 	}