x86: prepare merging arch/x86/kernel/apic_32/64.c

Shuffle code around, so we get a readable diff.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/apic_32.c

@@ -563,6 +563,9 @@ static void local_apic_timer_interrupt(void)
 		return;
 	}
 
+	/*
+	 * the NMI deadlock-detector uses this.
+	 */
 	per_cpu(irq_stat, cpu).apic_timer_irqs++;
 
 	evt->event_handler(evt);
@@ -617,7 +620,7 @@ int setup_profiling_timer(unsigned int multiplier)
 void clear_local_APIC(void)
 {
 	int maxlvt = lapic_get_maxlvt();
-	unsigned long v;
+	u32 v;
 
 	/*
 	 * Masking an LVT entry can trigger a local APIC error
@@ -1209,50 +1212,6 @@ int __init APIC_init_uniprocessor (void)
 	return 0;
 }
 
-/*
- * APIC command line parameters
- */
-static int __init parse_lapic(char *arg)
-{
-	enable_local_apic = 1;
-	return 0;
-}
-early_param("lapic", parse_lapic);
-
-static int __init parse_nolapic(char *arg)
-{
-	enable_local_apic = -1;
-	clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
-	return 0;
-}
-early_param("nolapic", parse_nolapic);
-
-static int __init parse_disable_lapic_timer(char *arg)
-{
-	local_apic_timer_disabled = 1;
-	return 0;
-}
-early_param("nolapic_timer", parse_disable_lapic_timer);
-
-static int __init parse_lapic_timer_c2_ok(char *arg)
-{
-	local_apic_timer_c2_ok = 1;
-	return 0;
-}
-early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
-
-static int __init apic_set_verbosity(char *str)
-{
-	if (strcmp("debug", str) == 0)
-		apic_verbosity = APIC_DEBUG;
-	else if (strcmp("verbose", str) == 0)
-		apic_verbosity = APIC_VERBOSE;
-	return 1;
-}
-
-__setup("apic=", apic_set_verbosity);
-
-
 /*
  * Local APIC interrupts
  */
@@ -1565,3 +1524,46 @@ device_initcall(init_lapic_sysfs);
 static void apic_pm_activate(void) { }
 
 #endif	/* CONFIG_PM */
+
+/*
+ * APIC command line parameters
+ */
+static int __init parse_lapic(char *arg)
+{
+	enable_local_apic = 1;
+	return 0;
+}
+early_param("lapic", parse_lapic);
+
+static int __init parse_nolapic(char *arg)
+{
+	enable_local_apic = -1;
+	clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
+	return 0;
+}
+early_param("nolapic", parse_nolapic);
+
+static int __init parse_disable_lapic_timer(char *arg)
+{
+	local_apic_timer_disabled = 1;
+	return 0;
+}
+early_param("nolapic_timer", parse_disable_lapic_timer);
+
+static int __init parse_lapic_timer_c2_ok(char *arg)
+{
+	local_apic_timer_c2_ok = 1;
+	return 0;
+}
+early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
+
+static int __init apic_set_verbosity(char *str)
+{
+	if (strcmp("debug", str) == 0)
+		apic_verbosity = APIC_DEBUG;
+	else if (strcmp("verbose", str) == 0)
+		apic_verbosity = APIC_VERBOSE;
+	return 1;
+}
+__setup("apic=", apic_set_verbosity);
+

arch/x86/kernel/apic_64.c

@@ -44,6 +44,7 @@
 int apic_verbosity;
 int disable_apic_timer __cpuinitdata;
 static int apic_calibrate_pmtmr __initdata;
+int disable_apic;
 
 /* Local APIC timer works in C2? */
 int local_apic_timer_c2_ok;
@@ -60,10 +61,8 @@ static int lapic_next_event(unsigned long delta,
 			    struct clock_event_device *evt);
 static void lapic_timer_setup(enum clock_event_mode mode,
 			      struct clock_event_device *evt);
-
 static void lapic_timer_broadcast(cpumask_t mask);
-
-static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen);
+static void apic_pm_activate(void);
 
 static struct clock_event_device lapic_clockevent = {
 	.name		= "lapic",
@@ -78,57 +77,34 @@ static struct clock_event_device lapic_clockevent = {
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
-static int lapic_next_event(unsigned long delta,
-			    struct clock_event_device *evt)
+/*
+ * Get the LAPIC version
+ */
+static inline int lapic_get_version(void)
 {
-	apic_write(APIC_TMICT, delta);
-	return 0;
+	return GET_APIC_VERSION(apic_read(APIC_LVR));
 }
 
-static void lapic_timer_setup(enum clock_event_mode mode,
-			      struct clock_event_device *evt)
+/*
+ * Check, if the APIC is integrated or a seperate chip
+ */
+static inline int lapic_is_integrated(void)
 {
-	unsigned long flags;
-	unsigned int v;
-
-	/* Lapic used as dummy for broadcast ? */
-	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
-		return;
-
-	local_irq_save(flags);
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_ONESHOT:
-		__setup_APIC_LVTT(calibration_result,
-				  mode != CLOCK_EVT_MODE_PERIODIC, 1);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		v = apic_read(APIC_LVTT);
-		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
-		apic_write(APIC_LVTT, v);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do here */
-		break;
-	}
-
-	local_irq_restore(flags);
+	return 1;
 }
 
 /*
- * Local APIC timer broadcast function
+ * Check, whether this is a modern or a first generation APIC
  */
-static void lapic_timer_broadcast(cpumask_t mask)
+static int modern_apic(void)
 {
-#ifdef CONFIG_SMP
-	send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
-#endif
+	/* AMD systems use old APIC versions, so check the CPU */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
+	    boot_cpu_data.x86 >= 0xf)
+		return 1;
+	return lapic_get_version() >= 0x14;
 }
 
-static void apic_pm_activate(void);
-
 void apic_wait_icr_idle(void)
 {
 	while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
@@ -151,7 +127,10 @@ u32 safe_apic_wait_icr_idle(void)
 	return send_status;
 }
 
-void enable_NMI_through_LVT0 (void * dummy)
+/**
+ * enable_NMI_through_LVT0 - enable NMI through local vector table 0
+ */
+void enable_NMI_through_LVT0(void *dummy)
 {
 	unsigned int v;
 
@@ -160,6 +139,9 @@ void enable_NMI_through_LVT0 (void * dummy)
 	apic_write(APIC_LVT0, v);
 }
 
+/**
+ * lapic_get_maxlvt - get the maximum number of local vector table entries
+ */
 int lapic_get_maxlvt(void)
 {
 	unsigned int v, maxlvt;
@@ -169,184 +151,476 @@ int lapic_get_maxlvt(void)
 	return maxlvt;
 }
 
-void clear_local_APIC(void)
+/*
+ * This function sets up the local APIC timer, with a timeout of
+ * 'clocks' APIC bus clock. During calibration we actually call
+ * this function twice on the boot CPU, once with a bogus timeout
+ * value, second time for real. The other (noncalibrating) CPUs
+ * call this function only once, with the real, calibrated value.
+ *
+ * We do reads before writes even if unnecessary, to get around the
+ * P5 APIC double write bug.
+ */
+
+static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 {
-	int maxlvt;
-	unsigned int v;
+	unsigned int lvtt_value, tmp_value;
 
-	maxlvt = lapic_get_maxlvt();
+	lvtt_value = LOCAL_TIMER_VECTOR;
+	if (!oneshot)
+		lvtt_value |= APIC_LVT_TIMER_PERIODIC;
+	if (!irqen)
+		lvtt_value |= APIC_LVT_MASKED;
 
-	/*
-	 * Masking an LVT entry can trigger a local APIC error
-	 * if the vector is zero. Mask LVTERR first to prevent this.
-	 */
-	if (maxlvt >= 3) {
-		v = ERROR_APIC_VECTOR; /* any non-zero vector will do */
-		apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
-	}
-	/*
-	 * Careful: we have to set masks only first to deassert
-	 * any level-triggered sources.
-	 */
-	v = apic_read(APIC_LVTT);
-	apic_write(APIC_LVTT, v | APIC_LVT_MASKED);
-	v = apic_read(APIC_LVT0);
-	apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
-	v = apic_read(APIC_LVT1);
-	apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
-	if (maxlvt >= 4) {
-		v = apic_read(APIC_LVTPC);
-		apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
-	}
+	apic_write(APIC_LVTT, lvtt_value);
 
 	/*
-	 * Clean APIC state for other OSs:
+	 * Divide PICLK by 16
 	 */
-	apic_write(APIC_LVTT, APIC_LVT_MASKED);
-	apic_write(APIC_LVT0, APIC_LVT_MASKED);
-	apic_write(APIC_LVT1, APIC_LVT_MASKED);
-	if (maxlvt >= 3)
-		apic_write(APIC_LVTERR, APIC_LVT_MASKED);
-	if (maxlvt >= 4)
-		apic_write(APIC_LVTPC, APIC_LVT_MASKED);
-	apic_write(APIC_ESR, 0);
-	apic_read(APIC_ESR);
+	tmp_value = apic_read(APIC_TDCR);
+	apic_write(APIC_TDCR, (tmp_value
+				& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
+				| APIC_TDR_DIV_16);
+
+	if (!oneshot)
+		apic_write(APIC_TMICT, clocks);
 }
 
-void disconnect_bsp_APIC(int virt_wire_setup)
+/*
+ * Setup extended LVT (K8 specific)
+ */
+void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
+			     unsigned char msg_type, unsigned char mask)
 {
-	/* Go back to Virtual Wire compatibility mode */
-	unsigned long value;
-
-	/* For the spurious interrupt use vector F, and enable it */
-	value = apic_read(APIC_SPIV);
-	value &= ~APIC_VECTOR_MASK;
-	value |= APIC_SPIV_APIC_ENABLED;
-	value |= 0xf;
-	apic_write(APIC_SPIV, value);
-
-	if (!virt_wire_setup) {
-		/*
-		 * For LVT0 make it edge triggered, active high,
-		 * external and enabled
-		 */
-		value = apic_read(APIC_LVT0);
-		value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
-			APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
-			APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED );
-		value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
-		value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
-		apic_write(APIC_LVT0, value);
-	} else {
-		/* Disable LVT0 */
-		apic_write(APIC_LVT0, APIC_LVT_MASKED);
-	}
+	unsigned long reg = (lvt_off << 4) + K8_APIC_EXT_LVT_BASE;
+	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
 
-	/* For LVT1 make it edge triggered, active high, nmi and enabled */
-	value = apic_read(APIC_LVT1);
-	value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
-			APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
-			APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
-	value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
-	value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
-	apic_write(APIC_LVT1, value);
+	apic_write(reg, v);
 }
 
-void disable_local_APIC(void)
+/*
+ * Program the next event, relative to now
+ */
+static int lapic_next_event(unsigned long delta,
+			    struct clock_event_device *evt)
 {
-	unsigned int value;
-
-	clear_local_APIC();
-
-	/*
-	 * Disable APIC (implies clearing of registers
-	 * for 82489DX!).
-	 */
-	value = apic_read(APIC_SPIV);
-	value &= ~APIC_SPIV_APIC_ENABLED;
-	apic_write(APIC_SPIV, value);
+	apic_write(APIC_TMICT, delta);
+	return 0;
 }
 
-void lapic_shutdown(void)
+/*
+ * Setup the lapic timer in periodic or oneshot mode
+ */
+static void lapic_timer_setup(enum clock_event_mode mode,
+			      struct clock_event_device *evt)
 {
 	unsigned long flags;
+	unsigned int v;
 
-	if (!cpu_has_apic)
+	/* Lapic used as dummy for broadcast ? */
+	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
 		return;
 
 	local_irq_save(flags);
 
-	disable_local_APIC();
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+	case CLOCK_EVT_MODE_ONESHOT:
+		__setup_APIC_LVTT(calibration_result,
+				  mode != CLOCK_EVT_MODE_PERIODIC, 1);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		v = apic_read(APIC_LVTT);
+		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+		apic_write(APIC_LVTT, v);
+		break;
+	case CLOCK_EVT_MODE_RESUME:
+		/* Nothing to do here */
+		break;
+	}
 
 	local_irq_restore(flags);
 }
 
 /*
- * This is to verify that we're looking at a real local APIC.
- * Check these against your board if the CPUs aren't getting
- * started for no apparent reason.
+ * Local APIC timer broadcast function
  */
-int __init verify_local_APIC(void)
+static void lapic_timer_broadcast(cpumask_t mask)
 {
-	unsigned int reg0, reg1;
-
-	/*
-	 * The version register is read-only in a real APIC.
-	 */
-	reg0 = apic_read(APIC_LVR);
-	apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0);
-	apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK);
-	reg1 = apic_read(APIC_LVR);
-	apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1);
+#ifdef CONFIG_SMP
+	send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
+#endif
+}
 
-	/*
-	 * The two version reads above should print the same
-	 * numbers.  If the second one is different, then we
-	 * poke at a non-APIC.
-	 */
-	if (reg1 != reg0)
-		return 0;
+/*
+ * Setup the local APIC timer for this CPU. Copy the initilized values
+ * of the boot CPU and register the clock event in the framework.
+ */
+static void setup_APIC_timer(void)
+{
+	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
-	/*
-	 * Check if the version looks reasonably.
-	 */
-	reg1 = GET_APIC_VERSION(reg0);
-	if (reg1 == 0x00 || reg1 == 0xff)
-		return 0;
-	reg1 = lapic_get_maxlvt();
-	if (reg1 < 0x02 || reg1 == 0xff)
-		return 0;
+	memcpy(levt, &lapic_clockevent, sizeof(*levt));
+	levt->cpumask = cpumask_of_cpu(smp_processor_id());
 
-	/*
-	 * The ID register is read/write in a real APIC.
-	 */
-	reg0 = apic_read(APIC_ID);
-	apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
-	apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
-	reg1 = apic_read(APIC_ID);
-	apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
-	apic_write(APIC_ID, reg0);
-	if (reg1 != (reg0 ^ APIC_ID_MASK))
-		return 0;
+	clockevents_register_device(levt);
+}
 
-	/*
+/*
+ * In this function we calibrate APIC bus clocks to the external
+ * timer. Unfortunately we cannot use jiffies and the timer irq
+ * to calibrate, since some later bootup code depends on getting
+ * the first irq? Ugh.
+ *
+ * We want to do the calibration only once since we
+ * want to have local timer irqs syncron. CPUs connected
+ * by the same APIC bus have the very same bus frequency.
+ * And we want to have irqs off anyways, no accidental
+ * APIC irq that way.
+ */
+
+#define TICK_COUNT 100000000
+
+static void __init calibrate_APIC_clock(void)
+{
+	unsigned apic, apic_start;
+	unsigned long tsc, tsc_start;
+	int result;
+
+	local_irq_disable();
+
+	/*
+	 * Put whatever arbitrary (but long enough) timeout
+	 * value into the APIC clock, we just want to get the
+	 * counter running for calibration.
+	 *
+	 * No interrupt enable !
+	 */
+	__setup_APIC_LVTT(250000000, 0, 0);
+
+	apic_start = apic_read(APIC_TMCCT);
+#ifdef CONFIG_X86_PM_TIMER
+	if (apic_calibrate_pmtmr && pmtmr_ioport) {
+		pmtimer_wait(5000);  /* 5ms wait */
+		apic = apic_read(APIC_TMCCT);
+		result = (apic_start - apic) * 1000L / 5;
+	} else
+#endif
+	{
+		rdtscll(tsc_start);
+
+		do {
+			apic = apic_read(APIC_TMCCT);
+			rdtscll(tsc);
+		} while ((tsc - tsc_start) < TICK_COUNT &&
+				(apic_start - apic) < TICK_COUNT);
+
+		result = (apic_start - apic) * 1000L * tsc_khz /
+					(tsc - tsc_start);
+	}
+
+	local_irq_enable();
+
+	printk(KERN_DEBUG "APIC timer calibration result %d\n", result);
+
+	printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n",
+		result / 1000 / 1000, result / 1000 % 1000);
+
+	/* Calculate the scaled math multiplication factor */
+	lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32);
+	lapic_clockevent.max_delta_ns =
+		clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+	lapic_clockevent.min_delta_ns =
+		clockevent_delta2ns(0xF, &lapic_clockevent);
+
+	calibration_result = result / HZ;
+}
+
+void __init setup_boot_APIC_clock(void)
+{
+	/*
+	 * The local apic timer can be disabled via the kernel commandline.
+	 * Register the lapic timer as a dummy clock event source on SMP
+	 * systems, so the broadcast mechanism is used. On UP systems simply
+	 * ignore it.
+	 */
+	if (disable_apic_timer) {
+		printk(KERN_INFO "Disabling APIC timer\n");
+		/* No broadcast on UP ! */
+		if (num_possible_cpus() > 1)
+			setup_APIC_timer();
+		return;
+	}
+
+	printk(KERN_INFO "Using local APIC timer interrupts.\n");
+	calibrate_APIC_clock();
+
+	/*
+	 * If nmi_watchdog is set to IO_APIC, we need the
+	 * PIT/HPET going.  Otherwise register lapic as a dummy
+	 * device.
+	 */
+	if (nmi_watchdog != NMI_IO_APIC)
+		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+	else
+		printk(KERN_WARNING "APIC timer registered as dummy,"
+		       " due to nmi_watchdog=1!\n");
+
+	setup_APIC_timer();
+}
+
+/*
+ * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
+ * C1E flag only in the secondary CPU, so when we detect the wreckage
+ * we already have enabled the boot CPU local apic timer. Check, if
+ * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
+ * set the DUMMY flag again and force the broadcast mode in the
+ * clockevents layer.
+ */
+void __cpuinit check_boot_apic_timer_broadcast(void)
+{
+	if (!disable_apic_timer ||
+	    (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
+		return;
+
+	printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
+	lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
+
+	local_irq_enable();
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &boot_cpu_id);
+	local_irq_disable();
+}
+
+void __cpuinit setup_secondary_APIC_clock(void)
+{
+	check_boot_apic_timer_broadcast();
+	setup_APIC_timer();
+}
+
+/*
+ * The guts of the apic timer interrupt
+ */
+static void local_apic_timer_interrupt(void)
+{
+	int cpu = smp_processor_id();
+	struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
+
+	/*
+	 * Normally we should not be here till LAPIC has been initialized but
+	 * in some cases like kdump, its possible that there is a pending LAPIC
+	 * timer interrupt from previous kernel's context and is delivered in
+	 * new kernel the moment interrupts are enabled.
+	 *
+	 * Interrupts are enabled early and LAPIC is setup much later, hence
+	 * its possible that when we get here evt->event_handler is NULL.
+	 * Check for event_handler being NULL and discard the interrupt as
+	 * spurious.
+	 */
+	if (!evt->event_handler) {
+		printk(KERN_WARNING
+		       "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
+		/* Switch it off */
+		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+		return;
+	}
+
+	/*
+	 * the NMI deadlock-detector uses this.
+	 */
+	add_pda(apic_timer_irqs, 1);
+
+	evt->event_handler(evt);
+}
+
+/*
+ * Local APIC timer interrupt. This is the most natural way for doing
+ * local interrupts, but local timer interrupts can be emulated by
+ * broadcast interrupts too. [in case the hw doesn't support APIC timers]
+ *
+ * [ if a single-CPU system runs an SMP kernel then we call the local
+ *   interrupt as well. Thus we cannot inline the local irq ... ]
+ */
+void smp_apic_timer_interrupt(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	/*
+	 * NOTE! We'd better ACK the irq immediately,
+	 * because timer handling can be slow.
+	 */
+	ack_APIC_irq();
+	/*
+	 * update_process_times() expects us to have done irq_enter().
+	 * Besides, if we don't timer interrupts ignore the global
+	 * interrupt lock, which is the WrongThing (tm) to do.
+	 */
+	exit_idle();
+	irq_enter();
+	local_apic_timer_interrupt();
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+int setup_profiling_timer(unsigned int multiplier)
+{
+	return -EINVAL;
+}
+
+
+/*
+ * Local APIC start and shutdown
+ */
+
+/**
+ * clear_local_APIC - shutdown the local APIC
+ *
+ * This is called, when a CPU is disabled and before rebooting, so the state of
+ * the local APIC has no dangling leftovers. Also used to cleanout any BIOS
+ * leftovers during boot.
+ */
+void clear_local_APIC(void)
+{
+	int maxlvt = lapic_get_maxlvt();
+	u32 v;
+
+	/*
+	 * Masking an LVT entry can trigger a local APIC error
+	 * if the vector is zero. Mask LVTERR first to prevent this.
+	 */
+	if (maxlvt >= 3) {
+		v = ERROR_APIC_VECTOR; /* any non-zero vector will do */
+		apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
+	}
+	/*
+	 * Careful: we have to set masks only first to deassert
+	 * any level-triggered sources.
+	 */
+	v = apic_read(APIC_LVTT);
+	apic_write(APIC_LVTT, v | APIC_LVT_MASKED);
+	v = apic_read(APIC_LVT0);
+	apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
+	v = apic_read(APIC_LVT1);
+	apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
+	if (maxlvt >= 4) {
+		v = apic_read(APIC_LVTPC);
+		apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
+	}
+
+	/*
+	 * Clean APIC state for other OSs:
+	 */
+	apic_write(APIC_LVTT, APIC_LVT_MASKED);
+	apic_write(APIC_LVT0, APIC_LVT_MASKED);
+	apic_write(APIC_LVT1, APIC_LVT_MASKED);
+	if (maxlvt >= 3)
+		apic_write(APIC_LVTERR, APIC_LVT_MASKED);
+	if (maxlvt >= 4)
+		apic_write(APIC_LVTPC, APIC_LVT_MASKED);
+	apic_write(APIC_ESR, 0);
+	apic_read(APIC_ESR);
+}
+
+/**
+ * disable_local_APIC - clear and disable the local APIC
+ */
+void disable_local_APIC(void)
+{
+	unsigned int value;
+
+	clear_local_APIC();
+
+	/*
+	 * Disable APIC (implies clearing of registers
+	 * for 82489DX!).
+	 */
+	value = apic_read(APIC_SPIV);
+	value &= ~APIC_SPIV_APIC_ENABLED;
+	apic_write(APIC_SPIV, value);
+}
+
+void lapic_shutdown(void)
+{
+	unsigned long flags;
+
+	if (!cpu_has_apic)
+		return;
+
+	local_irq_save(flags);
+
+	disable_local_APIC();
+
+	local_irq_restore(flags);
+}
+
+/*
+ * This is to verify that we're looking at a real local APIC.
+ * Check these against your board if the CPUs aren't getting
+ * started for no apparent reason.
+ */
+int __init verify_local_APIC(void)
+{
+	unsigned int reg0, reg1;
+
+	/*
+	 * The version register is read-only in a real APIC.
+	 */
+	reg0 = apic_read(APIC_LVR);
+	apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0);
+	apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK);
+	reg1 = apic_read(APIC_LVR);
+	apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1);
+
+	/*
+	 * The two version reads above should print the same
+	 * numbers.  If the second one is different, then we
+	 * poke at a non-APIC.
+	 */
+	if (reg1 != reg0)
+		return 0;
+
+	/*
+	 * Check if the version looks reasonably.
+	 */
+	reg1 = GET_APIC_VERSION(reg0);
+	if (reg1 == 0x00 || reg1 == 0xff)
+		return 0;
+	reg1 = lapic_get_maxlvt();
+	if (reg1 < 0x02 || reg1 == 0xff)
+		return 0;
+
+	/*
+	 * The ID register is read/write in a real APIC.
+	 */
+	reg0 = apic_read(APIC_ID);
+	apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
+	apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
+	reg1 = apic_read(APIC_ID);
+	apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
+	apic_write(APIC_ID, reg0);
+	if (reg1 != (reg0 ^ APIC_ID_MASK))
+		return 0;
+
+	/*
 	 * The next two are just to see if we have sane values.
 	 * They're only really relevant if we're in Virtual Wire
 	 * compatibility mode, but most boxes are anymore.
 	 */
 	reg0 = apic_read(APIC_LVT0);
-	apic_printk(APIC_DEBUG,"Getting LVT0: %x\n", reg0);
+	apic_printk(APIC_DEBUG, "Getting LVT0: %x\n", reg0);
 	reg1 = apic_read(APIC_LVT1);
 	apic_printk(APIC_DEBUG, "Getting LVT1: %x\n", reg1);
 
 	return 1;
 }
 
+/**
+ * sync_Arb_IDs - synchronize APIC bus arbitration IDs
+ */
 void __init sync_Arb_IDs(void)
 {
 	/* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */
-	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
-	if (ver >= 0x14)	/* P4 or higher */
+	if (modern_apic())
 		return;
 
 	/*
@@ -398,7 +672,10 @@ void __init init_bsp_APIC(void)
 	apic_write(APIC_LVT1, value);
 }
 
-void __cpuinit setup_local_APIC (void)
+/**
+ * setup_local_APIC - setup the local APIC
+ */
+void __cpuinit setup_local_APIC(void)
 {
 	unsigned int value, maxlvt;
 	int i, j;
@@ -517,162 +794,8 @@ void __cpuinit setup_local_APIC (void)
 
 	nmi_watchdog_default();
 	setup_apic_nmi_watchdog(NULL);
-	apic_pm_activate();
-}
-
-#ifdef CONFIG_PM
-
-static struct {
-	/* 'active' is true if the local APIC was enabled by us and
-	   not the BIOS; this signifies that we are also responsible
-	   for disabling it before entering apm/acpi suspend */
-	int active;
-	/* r/w apic fields */
-	unsigned int apic_id;
-	unsigned int apic_taskpri;
-	unsigned int apic_ldr;
-	unsigned int apic_dfr;
-	unsigned int apic_spiv;
-	unsigned int apic_lvtt;
-	unsigned int apic_lvtpc;
-	unsigned int apic_lvt0;
-	unsigned int apic_lvt1;
-	unsigned int apic_lvterr;
-	unsigned int apic_tmict;
-	unsigned int apic_tdcr;
-	unsigned int apic_thmr;
-} apic_pm_state;
-
-static int lapic_suspend(struct sys_device *dev, pm_message_t state)
-{
-	unsigned long flags;
-	int maxlvt;
-
-	if (!apic_pm_state.active)
-		return 0;
-
-	maxlvt = lapic_get_maxlvt();
-
-	apic_pm_state.apic_id = apic_read(APIC_ID);
-	apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
-	apic_pm_state.apic_ldr = apic_read(APIC_LDR);
-	apic_pm_state.apic_dfr = apic_read(APIC_DFR);
-	apic_pm_state.apic_spiv = apic_read(APIC_SPIV);
-	apic_pm_state.apic_lvtt = apic_read(APIC_LVTT);
-	if (maxlvt >= 4)
-		apic_pm_state.apic_lvtpc = apic_read(APIC_LVTPC);
-	apic_pm_state.apic_lvt0 = apic_read(APIC_LVT0);
-	apic_pm_state.apic_lvt1 = apic_read(APIC_LVT1);
-	apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
-	apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
-	apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
-#ifdef CONFIG_X86_MCE_INTEL
-	if (maxlvt >= 5)
-		apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
-#endif
-	local_irq_save(flags);
-	disable_local_APIC();
-	local_irq_restore(flags);
-	return 0;
-}
-
-static int lapic_resume(struct sys_device *dev)
-{
-	unsigned int l, h;
-	unsigned long flags;
-	int maxlvt;
-
-	if (!apic_pm_state.active)
-		return 0;
-
-	maxlvt = lapic_get_maxlvt();
-
-	local_irq_save(flags);
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	l &= ~MSR_IA32_APICBASE_BASE;
-	l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
-	wrmsr(MSR_IA32_APICBASE, l, h);
-	apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
-	apic_write(APIC_ID, apic_pm_state.apic_id);
-	apic_write(APIC_DFR, apic_pm_state.apic_dfr);
-	apic_write(APIC_LDR, apic_pm_state.apic_ldr);
-	apic_write(APIC_TASKPRI, apic_pm_state.apic_taskpri);
-	apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
-	apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
-	apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
-#ifdef CONFIG_X86_MCE_INTEL
-	if (maxlvt >= 5)
-		apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
-#endif
-	if (maxlvt >= 4)
-		apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
-	apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
-	apic_write(APIC_TDCR, apic_pm_state.apic_tdcr);
-	apic_write(APIC_TMICT, apic_pm_state.apic_tmict);
-	apic_write(APIC_ESR, 0);
-	apic_read(APIC_ESR);
-	apic_write(APIC_LVTERR, apic_pm_state.apic_lvterr);
-	apic_write(APIC_ESR, 0);
-	apic_read(APIC_ESR);
-	local_irq_restore(flags);
-	return 0;
-}
-
-static struct sysdev_class lapic_sysclass = {
-	.name		= "lapic",
-	.resume		= lapic_resume,
-	.suspend	= lapic_suspend,
-};
-
-static struct sys_device device_lapic = {
-	.id		= 0,
-	.cls		= &lapic_sysclass,
-};
-
-static void __cpuinit apic_pm_activate(void)
-{
-	apic_pm_state.active = 1;
-}
-
-static int __init init_lapic_sysfs(void)
-{
-	int error;
-	if (!cpu_has_apic)
-		return 0;
-	/* XXX: remove suspend/resume procs if !apic_pm_state.active? */
-	error = sysdev_class_register(&lapic_sysclass);
-	if (!error)
-		error = sysdev_register(&device_lapic);
-	return error;
-}
-device_initcall(init_lapic_sysfs);
-
-#else	/* CONFIG_PM */
-
-static void apic_pm_activate(void) { }
-
-#endif	/* CONFIG_PM */
-
-static int __init apic_set_verbosity(char *str)
-{
-	if (str == NULL)  {
-		skip_ioapic_setup = 0;
-		ioapic_force = 1;
-		return 0;
-	}
-	if (strcmp("debug", str) == 0)
-		apic_verbosity = APIC_DEBUG;
-	else if (strcmp("verbose", str) == 0)
-		apic_verbosity = APIC_VERBOSE;
-	else {
-		printk(KERN_WARNING "APIC Verbosity level %s not recognised"
-				" use apic=verbose or apic=debug\n", str);
-		return -EINVAL;
-	}
-
-	return 0;
+	apic_pm_activate();
 }
-early_param("apic", apic_set_verbosity);
 
 /*
  * Detect and enable local APICs on non-SMP boards.
@@ -680,8 +803,7 @@ early_param("apic", apic_set_verbosity);
  * On AMD64 we trust the BIOS - if it says no APIC it is likely
  * not correctly set up (usually the APIC timer won't work etc.)
  */
-
-static int __init detect_init_APIC (void)
+static int __init detect_init_APIC(void)
 {
 	if (!cpu_has_apic) {
 		printk(KERN_INFO "No local APIC present\n");
@@ -693,6 +815,9 @@ static int __init detect_init_APIC (void)
 	return 0;
 }
 
+/**
+ * init_apic_mappings - initialize APIC mappings
+ */
 void __init init_apic_mappings(void)
 {
 	unsigned long apic_phys;
@@ -725,264 +850,267 @@ void __init init_apic_mappings(void)
 }
 
 /*
- * This function sets up the local APIC timer, with a timeout of
- * 'clocks' APIC bus clock. During calibration we actually call
- * this function twice on the boot CPU, once with a bogus timeout
- * value, second time for real. The other (noncalibrating) CPUs
- * call this function only once, with the real, calibrated value.
- *
- * We do reads before writes even if unnecessary, to get around the
- * P5 APIC double write bug.
+ * This initializes the IO-APIC and APIC hardware if this is
+ * a UP kernel.
  */
-
-static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
+int __init APIC_init_uniprocessor(void)
 {
-	unsigned int lvtt_value, tmp_value;
-
-	lvtt_value = LOCAL_TIMER_VECTOR;
-	if (!oneshot)
-		lvtt_value |= APIC_LVT_TIMER_PERIODIC;
-	if (!irqen)
-		lvtt_value |= APIC_LVT_MASKED;
-
-	apic_write(APIC_LVTT, lvtt_value);
-
-	/*
-	 * Divide PICLK by 16
-	 */
-	tmp_value = apic_read(APIC_TDCR);
-	apic_write(APIC_TDCR, (tmp_value
-				& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
-				| APIC_TDR_DIV_16);
+	if (disable_apic) {
+		printk(KERN_INFO "Apic disabled\n");
+		return -1;
+	}
+	if (!cpu_has_apic) {
+		disable_apic = 1;
+		printk(KERN_INFO "Apic disabled by BIOS\n");
+		return -1;
+	}
 
-	if (!oneshot)
-		apic_write(APIC_TMICT, clocks);
-}
+	verify_local_APIC();
 
-static void setup_APIC_timer(void)
-{
-	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
+	apic_write(APIC_ID, SET_APIC_ID(boot_cpu_id));
 
-	memcpy(levt, &lapic_clockevent, sizeof(*levt));
-	levt->cpumask = cpumask_of_cpu(smp_processor_id());
+	setup_local_APIC();
 
-	clockevents_register_device(levt);
+	if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
+		setup_IO_APIC();
+	else
+		nr_ioapics = 0;
+	setup_boot_APIC_clock();
+	check_nmi_watchdog();
+	return 0;
 }
 
 /*
- * In this function we calibrate APIC bus clocks to the external
- * timer. Unfortunately we cannot use jiffies and the timer irq
- * to calibrate, since some later bootup code depends on getting
- * the first irq? Ugh.
- *
- * We want to do the calibration only once since we
- * want to have local timer irqs syncron. CPUs connected
- * by the same APIC bus have the very same bus frequency.
- * And we want to have irqs off anyways, no accidental
- * APIC irq that way.
+ * Local APIC interrupts
  */
 
-#define TICK_COUNT 100000000
-
-static void __init calibrate_APIC_clock(void)
+/*
+ * This interrupt should _never_ happen with our APIC/SMP architecture
+ */
+asmlinkage void smp_spurious_interrupt(void)
 {
-	unsigned apic, apic_start;
-	unsigned long tsc, tsc_start;
-	int result;
-
-	local_irq_disable();
-
+	unsigned int v;
+	exit_idle();
+	irq_enter();
 	/*
-	 * Put whatever arbitrary (but long enough) timeout
-	 * value into the APIC clock, we just want to get the
-	 * counter running for calibration.
-	 *
-	 * No interrupt enable !
+	 * Check if this really is a spurious interrupt and ACK it
+	 * if it is a vectored one.  Just in case...
+	 * Spurious interrupts should not be ACKed.
 	 */
-	__setup_APIC_LVTT(250000000, 0, 0);
-
-	apic_start = apic_read(APIC_TMCCT);
-#ifdef CONFIG_X86_PM_TIMER
-	if (apic_calibrate_pmtmr && pmtmr_ioport) {
-		pmtimer_wait(5000);  /* 5ms wait */
-		apic = apic_read(APIC_TMCCT);
-		result = (apic_start - apic) * 1000L / 5;
-	} else
-#endif
-	{
-		rdtscll(tsc_start);
-
-		do {
-			apic = apic_read(APIC_TMCCT);
-			rdtscll(tsc);
-		} while ((tsc - tsc_start) < TICK_COUNT &&
-				(apic_start - apic) < TICK_COUNT);
-
-		result = (apic_start - apic) * 1000L * tsc_khz /
-					(tsc - tsc_start);
-	}
-
-	local_irq_enable();
+	v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
+	if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
+		ack_APIC_irq();
 
-	printk(KERN_DEBUG "APIC timer calibration result %d\n", result);
+	add_pda(irq_spurious_count, 1);
+	irq_exit();
+}
 
-	printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n",
-		result / 1000 / 1000, result / 1000 % 1000);
+/*
+ * This interrupt should never happen with our APIC/SMP architecture
+ */
+asmlinkage void smp_error_interrupt(void)
+{
+	unsigned int v, v1;
 
-	/* Calculate the scaled math multiplication factor */
-	lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32);
-	lapic_clockevent.max_delta_ns =
-		clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
-	lapic_clockevent.min_delta_ns =
-		clockevent_delta2ns(0xF, &lapic_clockevent);
+	exit_idle();
+	irq_enter();
+	/* First tickle the hardware, only then report what went on. -- REW */
+	v = apic_read(APIC_ESR);
+	apic_write(APIC_ESR, 0);
+	v1 = apic_read(APIC_ESR);
+	ack_APIC_irq();
+	atomic_inc(&irq_err_count);
 
-	calibration_result = result / HZ;
+	/* Here is what the APIC error bits mean:
+	   0: Send CS error
+	   1: Receive CS error
+	   2: Send accept error
+	   3: Receive accept error
+	   4: Reserved
+	   5: Send illegal vector
+	   6: Received illegal vector
+	   7: Illegal register address
+	*/
+	printk(KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
+		smp_processor_id(), v , v1);
+	irq_exit();
 }
 
-void __init setup_boot_APIC_clock (void)
+void disconnect_bsp_APIC(int virt_wire_setup)
 {
-	/*
-	 * The local apic timer can be disabled via the kernel commandline.
-	 * Register the lapic timer as a dummy clock event source on SMP
-	 * systems, so the broadcast mechanism is used. On UP systems simply
-	 * ignore it.
-	 */
-	if (disable_apic_timer) {
-		printk(KERN_INFO "Disabling APIC timer\n");
-		/* No broadcast on UP ! */
-		if (num_possible_cpus() > 1)
-			setup_APIC_timer();
-		return;
-	}
+	/* Go back to Virtual Wire compatibility mode */
+	unsigned long value;
 
-	printk(KERN_INFO "Using local APIC timer interrupts.\n");
-	calibrate_APIC_clock();
+	/* For the spurious interrupt use vector F, and enable it */
+	value = apic_read(APIC_SPIV);
+	value &= ~APIC_VECTOR_MASK;
+	value |= APIC_SPIV_APIC_ENABLED;
+	value |= 0xf;
+	apic_write(APIC_SPIV, value);
 
-	/*
-	 * If nmi_watchdog is set to IO_APIC, we need the
-	 * PIT/HPET going.  Otherwise register lapic as a dummy
-	 * device.
-	 */
-	if (nmi_watchdog != NMI_IO_APIC)
-		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
-	else
-		printk(KERN_WARNING "APIC timer registered as dummy,"
-		       " due to nmi_watchdog=1!\n");
+	if (!virt_wire_setup) {
+		/*
+		 * For LVT0 make it edge triggered, active high,
+		 * external and enabled
+		 */
+		value = apic_read(APIC_LVT0);
+		value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
+			APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
+			APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
+		value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
+		value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
+		apic_write(APIC_LVT0, value);
+	} else {
+		/* Disable LVT0 */
+		apic_write(APIC_LVT0, APIC_LVT_MASKED);
+	}
 
-	setup_APIC_timer();
+	/* For LVT1 make it edge triggered, active high, nmi and enabled */
+	value = apic_read(APIC_LVT1);
+	value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
+			APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
+			APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
+	value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
+	value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
+	apic_write(APIC_LVT1, value);
 }
 
 /*
- * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
- * C1E flag only in the secondary CPU, so when we detect the wreckage
- * we already have enabled the boot CPU local apic timer. Check, if
- * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
- * set the DUMMY flag again and force the broadcast mode in the
- * clockevents layer.
+ * Power management
  */
-void __cpuinit check_boot_apic_timer_broadcast(void)
-{
-	if (!disable_apic_timer ||
-	    (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
-		return;
+#ifdef CONFIG_PM
+
+static struct {
+	/* 'active' is true if the local APIC was enabled by us and
+	   not the BIOS; this signifies that we are also responsible
+	   for disabling it before entering apm/acpi suspend */
+	int active;
+	/* r/w apic fields */
+	unsigned int apic_id;
+	unsigned int apic_taskpri;
+	unsigned int apic_ldr;
+	unsigned int apic_dfr;
+	unsigned int apic_spiv;
+	unsigned int apic_lvtt;
+	unsigned int apic_lvtpc;
+	unsigned int apic_lvt0;
+	unsigned int apic_lvt1;
+	unsigned int apic_lvterr;
+	unsigned int apic_tmict;
+	unsigned int apic_tdcr;
+	unsigned int apic_thmr;
+} apic_pm_state;
+
+static int lapic_suspend(struct sys_device *dev, pm_message_t state)
+{
+	unsigned long flags;
+	int maxlvt;
 
-	printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
-	lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
+	if (!apic_pm_state.active)
+		return 0;
 
-	local_irq_enable();
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &boot_cpu_id);
-	local_irq_disable();
-}
+	maxlvt = lapic_get_maxlvt();
 
-void __cpuinit setup_secondary_APIC_clock(void)
-{
-	check_boot_apic_timer_broadcast();
-	setup_APIC_timer();
+	apic_pm_state.apic_id = apic_read(APIC_ID);
+	apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
+	apic_pm_state.apic_ldr = apic_read(APIC_LDR);
+	apic_pm_state.apic_dfr = apic_read(APIC_DFR);
+	apic_pm_state.apic_spiv = apic_read(APIC_SPIV);
+	apic_pm_state.apic_lvtt = apic_read(APIC_LVTT);
+	if (maxlvt >= 4)
+		apic_pm_state.apic_lvtpc = apic_read(APIC_LVTPC);
+	apic_pm_state.apic_lvt0 = apic_read(APIC_LVT0);
+	apic_pm_state.apic_lvt1 = apic_read(APIC_LVT1);
+	apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
+	apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
+	apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
+#ifdef CONFIG_X86_MCE_INTEL
+	if (maxlvt >= 5)
+		apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
+#endif
+	local_irq_save(flags);
+	disable_local_APIC();
+	local_irq_restore(flags);
+	return 0;
 }
 
-int setup_profiling_timer(unsigned int multiplier)
+static int lapic_resume(struct sys_device *dev)
 {
-	return -EINVAL;
-}
+	unsigned int l, h;
+	unsigned long flags;
+	int maxlvt;
 
-void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
-			     unsigned char msg_type, unsigned char mask)
-{
-	unsigned long reg = (lvt_off << 4) + K8_APIC_EXT_LVT_BASE;
-	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
-	apic_write(reg, v);
-}
+	if (!apic_pm_state.active)
+		return 0;
 
-/*
- * Local timer interrupt handler. It does both profiling and
- * process statistics/rescheduling.
- *
- * We do profiling in every local tick, statistics/rescheduling
- * happen only every 'profiling multiplier' ticks. The default
- * multiplier is 1 and it can be changed by writing the new multiplier
- * value into /proc/profile.
- */
+	maxlvt = lapic_get_maxlvt();
 
-static void smp_local_timer_interrupt(void)
-{
-	int cpu = smp_processor_id();
-	struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
+	local_irq_save(flags);
+	rdmsr(MSR_IA32_APICBASE, l, h);
+	l &= ~MSR_IA32_APICBASE_BASE;
+	l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+	wrmsr(MSR_IA32_APICBASE, l, h);
+	apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
+	apic_write(APIC_ID, apic_pm_state.apic_id);
+	apic_write(APIC_DFR, apic_pm_state.apic_dfr);
+	apic_write(APIC_LDR, apic_pm_state.apic_ldr);
+	apic_write(APIC_TASKPRI, apic_pm_state.apic_taskpri);
+	apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
+	apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
+	apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
+#ifdef CONFIG_X86_MCE_INTEL
+	if (maxlvt >= 5)
+		apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
+#endif
+	if (maxlvt >= 4)
+		apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
+	apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
+	apic_write(APIC_TDCR, apic_pm_state.apic_tdcr);
+	apic_write(APIC_TMICT, apic_pm_state.apic_tmict);
+	apic_write(APIC_ESR, 0);
+	apic_read(APIC_ESR);
+	apic_write(APIC_LVTERR, apic_pm_state.apic_lvterr);
+	apic_write(APIC_ESR, 0);
+	apic_read(APIC_ESR);
+	local_irq_restore(flags);
+	return 0;
+}
 
-	/*
-	 * Normally we should not be here till LAPIC has been initialized but
-	 * in some cases like kdump, its possible that there is a pending LAPIC
-	 * timer interrupt from previous kernel's context and is delivered in
-	 * new kernel the moment interrupts are enabled.
-	 *
-	 * Interrupts are enabled early and LAPIC is setup much later, hence
-	 * its possible that when we get here evt->event_handler is NULL.
-	 * Check for event_handler being NULL and discard the interrupt as
-	 * spurious.
-	 */
-	if (!evt->event_handler) {
-		printk(KERN_WARNING
-		       "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
-		/* Switch it off */
-		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
-		return;
-	}
+static struct sysdev_class lapic_sysclass = {
+	.name		= "lapic",
+	.resume		= lapic_resume,
+	.suspend	= lapic_suspend,
+};
 
-	/*
-	 * the NMI deadlock-detector uses this.
-	 */
-	add_pda(apic_timer_irqs, 1);
+static struct sys_device device_lapic = {
+	.id		= 0,
+	.cls		= &lapic_sysclass,
+};
 
-	evt->event_handler(evt);
+static void __cpuinit apic_pm_activate(void)
+{
+	apic_pm_state.active = 1;
 }
 
-/*
- * Local APIC timer interrupt. This is the most natural way for doing
- * local interrupts, but local timer interrupts can be emulated by
- * broadcast interrupts too. [in case the hw doesn't support APIC timers]
- *
- * [ if a single-CPU system runs an SMP kernel then we call the local
- *   interrupt as well. Thus we cannot inline the local irq ... ]
- */
-void smp_apic_timer_interrupt(struct pt_regs *regs)
+static int __init init_lapic_sysfs(void)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	/*
-	 * NOTE! We'd better ACK the irq immediately,
-	 * because timer handling can be slow.
-	 */
-	ack_APIC_irq();
-	/*
-	 * update_process_times() expects us to have done irq_enter().
-	 * Besides, if we don't timer interrupts ignore the global
-	 * interrupt lock, which is the WrongThing (tm) to do.
-	 */
-	exit_idle();
-	irq_enter();
-	smp_local_timer_interrupt();
-	irq_exit();
-	set_irq_regs(old_regs);
+	int error;
+	if (!cpu_has_apic)
+		return 0;
+	/* XXX: remove suspend/resume procs if !apic_pm_state.active? */
+	error = sysdev_class_register(&lapic_sysclass);
+	if (!error)
+		error = sysdev_register(&device_lapic);
+	return error;
 }
+device_initcall(init_lapic_sysfs);
+
+#else	/* CONFIG_PM */
+
+static void apic_pm_activate(void) { }
+
+#endif	/* CONFIG_PM */
 
 /*
  * apic_is_clustered_box() -- Check if we can expect good TSC
@@ -1032,91 +1160,28 @@ __cpuinit int apic_is_clustered_box(void)
 }
 
 /*
- * This interrupt should _never_ happen with our APIC/SMP architecture
- */
-asmlinkage void smp_spurious_interrupt(void)
-{
-	unsigned int v;
-	exit_idle();
-	irq_enter();
-	/*
-	 * Check if this really is a spurious interrupt and ACK it
-	 * if it is a vectored one.  Just in case...
-	 * Spurious interrupts should not be ACKed.
-	 */
-	v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
-	if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
-		ack_APIC_irq();
-
-	add_pda(irq_spurious_count, 1);
-	irq_exit();
-}
-
-/*
- * This interrupt should never happen with our APIC/SMP architecture
- */
-
-asmlinkage void smp_error_interrupt(void)
-{
-	unsigned int v, v1;
-
-	exit_idle();
-	irq_enter();
-	/* First tickle the hardware, only then report what went on. -- REW */
-	v = apic_read(APIC_ESR);
-	apic_write(APIC_ESR, 0);
-	v1 = apic_read(APIC_ESR);
-	ack_APIC_irq();
-	atomic_inc(&irq_err_count);
-
-	/* Here is what the APIC error bits mean:
-	   0: Send CS error
-	   1: Receive CS error
-	   2: Send accept error
-	   3: Receive accept error
-	   4: Reserved
-	   5: Send illegal vector
-	   6: Received illegal vector
-	   7: Illegal register address
-	*/
-	printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
-		smp_processor_id(), v , v1);
-	irq_exit();
-}
-
-int disable_apic;
-
-/*
- * This initializes the IO-APIC and APIC hardware if this is
- * a UP kernel.
+ * APIC command line parameters
  */
-int __init APIC_init_uniprocessor (void)
+static int __init apic_set_verbosity(char *str)
 {
-	if (disable_apic) {
-		printk(KERN_INFO "Apic disabled\n");
-		return -1;
+	if (str == NULL)  {
+		skip_ioapic_setup = 0;
+		ioapic_force = 1;
+		return 0;
 	}
-	if (!cpu_has_apic) {
-		disable_apic = 1;
-		printk(KERN_INFO "Apic disabled by BIOS\n");
-		return -1;
+	if (strcmp("debug", str) == 0)
+		apic_verbosity = APIC_DEBUG;
+	else if (strcmp("verbose", str) == 0)
+		apic_verbosity = APIC_VERBOSE;
+	else {
+		printk(KERN_WARNING "APIC Verbosity level %s not recognised"
+				" use apic=verbose or apic=debug\n", str);
+		return -EINVAL;
 	}
 
-	verify_local_APIC();
-
-	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
-	apic_write(APIC_ID, SET_APIC_ID(boot_cpu_id));
-
-	setup_local_APIC();
-
-	if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
-		setup_IO_APIC();
-	else
-		nr_ioapics = 0;
-	setup_boot_APIC_clock();
-	check_nmi_watchdog();
 	return 0;
 }
+early_param("apic", apic_set_verbosity);
 
 static __init int setup_disableapic(char *str)
 {