Merge branch 'idle-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6

* 'idle-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6:
  cpuidle/x86/perf: fix power:cpu_idle double end events and throw cpu_idle events from the cpuidle layer
  intel_idle: open broadcast clock event
  cpuidle: CPUIDLE_FLAG_CHECK_BM is omap3_idle specific
  cpuidle: CPUIDLE_FLAG_TLB_FLUSHED is specific to intel_idle
  cpuidle: delete unused CPUIDLE_FLAG_SHALLOW, BALANCED, DEEP definitions
  SH, cpuidle: delete use of NOP CPUIDLE_FLAGS_SHALLOW
  cpuidle: delete NOP CPUIDLE_FLAG_POLL
  ACPI: processor_idle: delete use of NOP CPUIDLE_FLAGs
  cpuidle: Rename X86 specific idle poll state[0] from C0 to POLL
  ACPI, intel_idle: Cleanup idle= internal variables
  cpuidle: Make cpuidle_enable_device() call poll_idle_init()
  intel_idle: update Sandy Bridge core C-state residency targets

4 files changed, 124 insertions, 69 deletions

diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index bec561c..3c1a2fe 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -23,7 +23,7 @@ static int set_no_mwait(const struct dmi_system_id *id)
 {
 	printk(KERN_NOTICE PREFIX "%s detected - "
 		"disabling mwait for CPU C-states\n", id->ident);
-	idle_nomwait = 1;
+	boot_option_idle_override = IDLE_NOMWAIT;
 	return 0;
 }
 
@@ -283,7 +283,7 @@ acpi_processor_eval_pdc(acpi_handle handle, struct acpi_object_list *pdc_in)
 {
 	acpi_status status = AE_OK;
 
-	if (idle_nomwait) {
+	if (boot_option_idle_override == IDLE_NOMWAIT) {
 		/*
 		 * If mwait is disabled for CPU C-states, the C2C3_FFH access
 		 * mode will be disabled in the parameter of _PDC object.
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index a765b82..d615b7d 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -79,6 +79,13 @@ module_param(bm_check_disable, uint, 0000);
 static unsigned int latency_factor __read_mostly = 2;
 module_param(latency_factor, uint, 0644);
 
+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;
+}
+
 /*
  * IBM ThinkPad R40e crashes mysteriously when going into C2 or C3.
  * For now disable this. Probably a bug somewhere else.
@@ -455,7 +462,7 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
 				continue;
 			}
 			if (cx.type == ACPI_STATE_C1 &&
-					(idle_halt || idle_nomwait)) {
+			    (boot_option_idle_override == IDLE_NOMWAIT)) {
 				/*
 				 * In most cases the C1 space_id obtained from
 				 * _CST object is FIXED_HARDWARE access mode.
@@ -1016,7 +1023,6 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
 		state->flags = 0;
 		switch (cx->type) {
 			case ACPI_STATE_C1:
-			state->flags |= CPUIDLE_FLAG_SHALLOW;
 			if (cx->entry_method == ACPI_CSTATE_FFH)
 				state->flags |= CPUIDLE_FLAG_TIME_VALID;
 
@@ -1025,16 +1031,13 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
 			break;
 
 			case ACPI_STATE_C2:
-			state->flags |= CPUIDLE_FLAG_BALANCED;
 			state->flags |= CPUIDLE_FLAG_TIME_VALID;
 			state->enter = acpi_idle_enter_simple;
 			dev->safe_state = state;
 			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;
@@ -1058,7 +1061,7 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 {
 	int ret = 0;
 
-	if (boot_option_idle_override)
+	if (disabled_by_idle_boot_param())
 		return 0;
 
 	if (!pr)
@@ -1089,19 +1092,10 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr,
 	acpi_status status = 0;
 	static int first_run;
 
-	if (boot_option_idle_override)
+	if (disabled_by_idle_boot_param())
 		return 0;
 
 	if (!first_run) {
-		if (idle_halt) {
-			/*
-			 * When the boot option of "idle=halt" is added, halt
-			 * is used for CPU IDLE.
-			 * In such case C2/C3 is meaningless. So the max_cstate
-			 * is set to one.
-			 */
-			max_cstate = 1;
-		}
 		dmi_check_system(processor_power_dmi_table);
 		max_cstate = acpi_processor_cstate_check(max_cstate);
 		if (max_cstate < ACPI_C_STATES_MAX)
@@ -1142,7 +1136,7 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr,
 int acpi_processor_power_exit(struct acpi_processor *pr,
 			      struct acpi_device *device)
 {
-	if (boot_option_idle_override)
+	if (disabled_by_idle_boot_param())
 		return 0;
 
 	cpuidle_unregister_device(&pr->power.dev);
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 386888f..bf50924 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -96,7 +96,15 @@ static void cpuidle_idle_call(void)
 
 	/* enter the state and update stats */
 	dev->last_state = target_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);
+
+	trace_power_end(dev->cpu);
+	trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
+
 	if (dev->last_state)
 		target_state = dev->last_state;
 
@@ -106,8 +114,6 @@ static void cpuidle_idle_call(void)
 	/* give the governor an opportunity to reflect on the outcome */
 	if (cpuidle_curr_governor->reflect)
 		cpuidle_curr_governor->reflect(dev);
-	trace_power_end(smp_processor_id());
-	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 /**
@@ -155,6 +161,45 @@ 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)
+{
+	ktime_t	t1, t2;
+	s64 diff;
+	int ret;
+
+	t1 = ktime_get();
+	local_irq_enable();
+	while (!need_resched())
+		cpu_relax();
+
+	t2 = ktime_get();
+	diff = ktime_to_us(ktime_sub(t2, t1));
+	if (diff > INT_MAX)
+		diff = INT_MAX;
+
+	ret = (int) diff;
+	return ret;
+}
+
+static void poll_idle_init(struct cpuidle_device *dev)
+{
+	struct cpuidle_state *state = &dev->states[0];
+
+	cpuidle_set_statedata(state, NULL);
+
+	snprintf(state->name, CPUIDLE_NAME_LEN, "POLL");
+	snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE");
+	state->exit_latency = 0;
+	state->target_residency = 0;
+	state->power_usage = -1;
+	state->flags = 0;
+	state->enter = poll_idle;
+}
+#else
+static void poll_idle_init(struct cpuidle_device *dev) {}
+#endif /* CONFIG_ARCH_HAS_CPU_RELAX */
+
 /**
  * cpuidle_enable_device - enables idle PM for a CPU
  * @dev: the CPU
@@ -179,6 +224,8 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 			return ret;
 	}
 
+	poll_idle_init(dev);
+
 	if ((ret = cpuidle_add_state_sysfs(dev)))
 		return ret;
 
@@ -233,45 +280,6 @@ void cpuidle_disable_device(struct cpuidle_device *dev)
 
 EXPORT_SYMBOL_GPL(cpuidle_disable_device);
 
-#ifdef CONFIG_ARCH_HAS_CPU_RELAX
-static int poll_idle(struct cpuidle_device *dev, struct cpuidle_state *st)
-{
-	ktime_t	t1, t2;
-	s64 diff;
-	int ret;
-
-	t1 = ktime_get();
-	local_irq_enable();
-	while (!need_resched())
-		cpu_relax();
-
-	t2 = ktime_get();
-	diff = ktime_to_us(ktime_sub(t2, t1));
-	if (diff > INT_MAX)
-		diff = INT_MAX;
-
-	ret = (int) diff;
-	return ret;
-}
-
-static void poll_idle_init(struct cpuidle_device *dev)
-{
-	struct cpuidle_state *state = &dev->states[0];
-
-	cpuidle_set_statedata(state, NULL);
-
-	snprintf(state->name, CPUIDLE_NAME_LEN, "C0");
-	snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE");
-	state->exit_latency = 0;
-	state->target_residency = 0;
-	state->power_usage = -1;
-	state->flags = CPUIDLE_FLAG_POLL;
-	state->enter = poll_idle;
-}
-#else
-static void poll_idle_init(struct cpuidle_device *dev) {}
-#endif /* CONFIG_ARCH_HAS_CPU_RELAX */
-
 /**
  * __cpuidle_register_device - internal register function called before register
  * and enable routines
@@ -292,8 +300,6 @@ static int __cpuidle_register_device(struct cpuidle_device *dev)
 
 	init_completion(&dev->kobj_unregister);
 
-	poll_idle_init(dev);
-
 	/*
 	 * cpuidle driver should set the dev->power_specified bit
 	 * before registering the device if the driver provides
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 56ac09d..7acb32e 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -59,6 +59,8 @@
 #include <linux/hrtimer.h>	/* ktime_get_real() */
 #include <trace/events/power.h>
 #include <linux/sched.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
 #include <asm/mwait.h>
 
 #define INTEL_IDLE_VERSION "0.4"
@@ -73,6 +75,7 @@ static int max_cstate = MWAIT_MAX_NUM_CSTATES - 1;
 
 static unsigned int mwait_substates;
 
+#define LAPIC_TIMER_ALWAYS_RELIABLE 0xFFFFFFFF
 /* Reliable LAPIC Timer States, bit 1 for C1 etc.  */
 static unsigned int lapic_timer_reliable_states = (1 << 1);	 /* Default to only C1 */
 
@@ -82,6 +85,14 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state);
 static struct cpuidle_state *cpuidle_state_table;
 
 /*
+ * Set this flag for states where the HW flushes the TLB for us
+ * and so we don't need cross-calls to keep it consistent.
+ * If this flag is set, SW flushes the TLB, so even if the
+ * HW doesn't do the flushing, this flag is safe to use.
+ */
+#define CPUIDLE_FLAG_TLB_FLUSHED	0x10000
+
+/*
  * States are indexed by the cstate number,
  * which is also the index into the MWAIT hint array.
  * Thus C0 is a dummy.
@@ -122,7 +133,7 @@ static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
 		.driver_data = (void *) 0x00,
 		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 1,
-		.target_residency = 4,
+		.target_residency = 1,
 		.enter = &intel_idle },
 	{ /* MWAIT C2 */
 		.name = "SNB-C3",
@@ -130,7 +141,7 @@ static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
 		.driver_data = (void *) 0x10,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
-		.target_residency = 160,
+		.target_residency = 211,
 		.enter = &intel_idle },
 	{ /* MWAIT C3 */
 		.name = "SNB-C6",
@@ -138,7 +149,7 @@ static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
 		.driver_data = (void *) 0x20,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 104,
-		.target_residency = 208,
+		.target_residency = 345,
 		.enter = &intel_idle },
 	{ /* MWAIT C4 */
 		.name = "SNB-C7",
@@ -146,7 +157,7 @@ static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
 		.driver_data = (void *) 0x30,
 		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 109,
-		.target_residency = 300,
+		.target_residency = 345,
 		.enter = &intel_idle },
 };
 
@@ -220,8 +231,6 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state)
 	kt_before = ktime_get_real();
 
 	stop_critical_timings();
-	trace_power_start(POWER_CSTATE, (eax >> 4) + 1, cpu);
-	trace_cpu_idle((eax >> 4) + 1, cpu);
 	if (!need_resched()) {
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
@@ -243,6 +252,39 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state)
 	return usec_delta;
 }
 
+static void __setup_broadcast_timer(void *arg)
+{
+	unsigned long reason = (unsigned long)arg;
+	int cpu = smp_processor_id();
+
+	reason = reason ?
+		CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF;
+
+	clockevents_notify(reason, &cpu);
+}
+
+static int __cpuinit setup_broadcast_cpuhp_notify(struct notifier_block *n,
+		unsigned long action, void *hcpu)
+{
+	int hotcpu = (unsigned long)hcpu;
+
+	switch (action & 0xf) {
+	case CPU_ONLINE:
+		smp_call_function_single(hotcpu, __setup_broadcast_timer,
+			(void *)true, 1);
+		break;
+	case CPU_DOWN_PREPARE:
+		smp_call_function_single(hotcpu, __setup_broadcast_timer,
+			(void *)false, 1);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata setup_broadcast_notifier = {
+	.notifier_call = setup_broadcast_cpuhp_notify,
+};
+
 /*
  * intel_idle_probe()
  */
@@ -305,7 +347,11 @@ static int intel_idle_probe(void)
 	}
 
 	if (boot_cpu_has(X86_FEATURE_ARAT))	/* Always Reliable APIC Timer */
-		lapic_timer_reliable_states = 0xFFFFFFFF;
+		lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
+	else {
+		smp_call_function(__setup_broadcast_timer, (void *)true, 1);
+		register_cpu_notifier(&setup_broadcast_notifier);
+	}
 
 	pr_debug(PREFIX "v" INTEL_IDLE_VERSION
 		" model 0x%X\n", boot_cpu_data.x86_model);
@@ -403,6 +449,10 @@ static int __init intel_idle_init(void)
 {
 	int retval;
 
+	/* Do not load intel_idle at all for now if idle= is passed */
+	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+		return -ENODEV;
+
 	retval = intel_idle_probe();
 	if (retval)
 		return retval;
@@ -428,6 +478,11 @@ static void __exit intel_idle_exit(void)
 	intel_idle_cpuidle_devices_uninit();
 	cpuidle_unregister_driver(&intel_idle_driver);
 
+	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) {
+		smp_call_function(__setup_broadcast_timer, (void *)false, 1);
+		unregister_cpu_notifier(&setup_broadcast_notifier);
+	}
+
 	return;
 }