1 files changed, 145 insertions, 75 deletions

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 18767f8ab09..20bce51c2e8 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -82,7 +82,8 @@ 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;
 
@@ -110,7 +111,6 @@ 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,
@@ -118,7 +118,6 @@ 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,
@@ -126,7 +125,6 @@ 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,
@@ -138,7 +136,6 @@ 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,
@@ -146,7 +143,6 @@ 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,
@@ -154,7 +150,6 @@ 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,
@@ -162,7 +157,6 @@ 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,
@@ -174,7 +168,6 @@ 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,
@@ -182,7 +175,6 @@ 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,
@@ -191,7 +183,6 @@ 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,
@@ -200,23 +191,56 @@ 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 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
- * @state: cpuidle state
+ * @drv: cpuidle driver
+ * @index: index of cpuidle state
  *
+ * Must be called under local_irq_disable().
  */
-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;
@@ -224,8 +248,6 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state)
 
 	cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) + 1;
 
-	local_irq_disable();
-
 	/*
 	 * leave_mm() to avoid costly and often unnecessary wakeups
 	 * for flushing the user TLB's associated with the active mm.
@@ -257,7 +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)
@@ -322,7 +347,8 @@ static int intel_idle_probe(void)
 	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
 
 	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
-		!(ecx & CPUID5_ECX_INTERRUPT_BREAK))
+	    !(ecx & CPUID5_ECX_INTERRUPT_BREAK) ||
+	    !mwait_substates)
 			return -ENODEV;
 
 	pr_debug(PREFIX "MWAIT substates: 0x%x\n", mwait_substates);
@@ -368,7 +394,7 @@ static int intel_idle_probe(void)
 	if (boot_cpu_has(X86_FEATURE_ARAT))	/* Always Reliable APIC Timer */
 		lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
 	else {
-		smp_call_function(__setup_broadcast_timer, (void *)true, 1);
+		on_each_cpu(__setup_broadcast_timer, (void *)true, 1);
 		register_cpu_notifier(&setup_broadcast_notifier);
 	}
 
@@ -398,69 +424,106 @@ static void intel_idle_cpuidle_devices_uninit(void)
 	return;
 }
 /*
- * intel_idle_cpuidle_devices_init()
+ * 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)
+		on_each_cpu(auto_demotion_disable, NULL, 1);
+
+	return 0;
+}
+
+
+/*
+ * intel_idle_cpu_init()
  * allocate, initialize, register cpuidle_devices
+ * @cpu: cpu/core to initialize
  */
-static int intel_idle_cpuidle_devices_init(void)
+int intel_idle_cpu_init(int cpu)
 {
-	int i, cstate;
+	int cstate;
 	struct cpuidle_device *dev;
 
-	intel_idle_cpuidle_devices = alloc_percpu(struct cpuidle_device);
-	if (intel_idle_cpuidle_devices == NULL)
-		return -ENOMEM;
+	dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu);
 
-	for_each_online_cpu(i) {
-		dev = per_cpu_ptr(intel_idle_cpuidle_devices, i);
+	dev->state_count = 1;
 
-		dev->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");
+	for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
+		int num_substates;
 
-			dev->states[dev->state_count] =	/* structure copy */
-				cpuidle_state_table[cstate];
+		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)
+			continue;
+
+		dev->states_usage[dev->state_count].driver_data =
+			(void *)get_driver_data(cstate);
 
 			dev->state_count += 1;
 		}
+	dev->cpu = cpu;
 
-		dev->cpu = i;
-		if (cpuidle_register_device(dev)) {
-			pr_debug(PREFIX "cpuidle_register_device %d failed!\n",
-				 i);
-			intel_idle_cpuidle_devices_uninit();
-			return -EIO;
-		}
+	if (cpuidle_register_device(dev)) {
+		pr_debug(PREFIX "cpuidle_register_device %d failed!\n", cpu);
+		intel_idle_cpuidle_devices_uninit();
+		return -EIO;
 	}
+
 	if (auto_demotion_disable_flags)
-		smp_call_function(auto_demotion_disable, NULL, 1);
+		smp_call_function_single(cpu, auto_demotion_disable, NULL, 1);
 
 	return 0;
 }
@@ -468,7 +531,7 @@ static int intel_idle_cpuidle_devices_init(void)
 
 static int __init intel_idle_init(void)
 {
-	int retval;
+	int retval, i;
 
 	/* Do not load intel_idle at all for now if idle= is passed */
 	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
@@ -478,6 +541,7 @@ 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",
@@ -485,10 +549,16 @@ static int __init intel_idle_init(void)
 		return retval;
 	}
 
-	retval = intel_idle_cpuidle_devices_init();
-	if (retval) {
-		cpuidle_unregister_driver(&intel_idle_driver);
-		return retval;
+	intel_idle_cpuidle_devices = alloc_percpu(struct cpuidle_device);
+	if (intel_idle_cpuidle_devices == NULL)
+		return -ENOMEM;
+
+	for_each_online_cpu(i) {
+		retval = intel_idle_cpu_init(i);
+		if (retval) {
+			cpuidle_unregister_driver(&intel_idle_driver);
+			return retval;
+		}
 	}
 
 	return 0;
@@ -500,7 +570,7 @@ static void __exit intel_idle_exit(void)
 	cpuidle_unregister_driver(&intel_idle_driver);
 
 	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) {
-		smp_call_function(__setup_broadcast_timer, (void *)false, 1);
+		on_each_cpu(__setup_broadcast_timer, (void *)false, 1);
 		unregister_cpu_notifier(&setup_broadcast_notifier);
 	}