Merge branch 'genirq-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

This merges branches irq/genirq, irq/sparseirq-v4, timers/hpet-percpu
and x86/uv.

The sparseirq branch is just preliminary groundwork: no sparse IRQs are
actually implemented by this tree anymore - just the new APIs are added
while keeping the old way intact as well (the new APIs map 1:1 to
irq_desc[]).  The 'real' sparse IRQ support will then be a relatively
small patch ontop of this - with a v2.6.29 merge target.

* 'genirq-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (178 commits)
  genirq: improve include files
  intr_remapping: fix typo
  io_apic: make irq_mis_count available on 64-bit too
  genirq: fix name space collisions of nr_irqs in arch/*
  genirq: fix name space collision of nr_irqs in autoprobe.c
  genirq: use iterators for irq_desc loops
  proc: fixup irq iterator
  genirq: add reverse iterator for irq_desc
  x86: move ack_bad_irq() to irq.c
  x86: unify show_interrupts() and proc helpers
  x86: cleanup show_interrupts
  genirq: cleanup the sparseirq modifications
  genirq: remove artifacts from sparseirq removal
  genirq: revert dynarray
  genirq: remove irq_to_desc_alloc
  genirq: remove sparse irq code
  genirq: use inline function for irq_to_desc
  genirq: consolidate nr_irqs and for_each_irq_desc()
  x86: remove sparse irq from Kconfig
  genirq: define nr_irqs for architectures with GENERIC_HARDIRQS=n
  ...

41 files changed, 2855 insertions, 5665 deletions

diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c
index 99a7f19da13a..a4555f497639 100644
--- a/arch/alpha/kernel/sys_sable.c
+++ b/arch/alpha/kernel/sys_sable.c
@@ -47,7 +47,7 @@ typedef struct irq_swizzle_struct
 
 static irq_swizzle_t *sable_lynx_irq_swizzle;
 
-static void sable_lynx_init_irq(int nr_irqs);
+static void sable_lynx_init_irq(int nr_of_irqs);
 
 #if defined(CONFIG_ALPHA_GENERIC) || defined(CONFIG_ALPHA_SABLE)
 
@@ -530,11 +530,11 @@ sable_lynx_srm_device_interrupt(unsigned long vector)
 }
 
 static void __init
-sable_lynx_init_irq(int nr_irqs)
+sable_lynx_init_irq(int nr_of_irqs)
 {
 	long i;
 
-	for (i = 0; i < nr_irqs; ++i) {
+	for (i = 0; i < nr_of_irqs; ++i) {
 		irq_desc[i].status = IRQ_DISABLED | IRQ_LEVEL;
 		irq_desc[i].chip = &sable_lynx_irq_type;
 	}
diff --git a/arch/arm/mach-ixp2000/ixdp2x00.c b/arch/arm/mach-ixp2000/ixdp2x00.c
index b0653a87159a..30451300751b 100644
--- a/arch/arm/mach-ixp2000/ixdp2x00.c
+++ b/arch/arm/mach-ixp2000/ixdp2x00.c
@@ -143,7 +143,7 @@ static struct irq_chip ixdp2x00_cpld_irq_chip = {
 	.unmask	= ixdp2x00_irq_unmask
 };
 
-void __init ixdp2x00_init_irq(volatile unsigned long *stat_reg, volatile unsigned long *mask_reg, unsigned long nr_irqs)
+void __init ixdp2x00_init_irq(volatile unsigned long *stat_reg, volatile unsigned long *mask_reg, unsigned long nr_of_irqs)
 {
 	unsigned int irq;
 
@@ -154,7 +154,7 @@ void __init ixdp2x00_init_irq(volatile unsigned long *stat_reg, volatile unsigne
 
 	board_irq_stat = stat_reg;
 	board_irq_mask = mask_reg;
-	board_irq_count = nr_irqs;
+	board_irq_count = nr_of_irqs;
 
 	*board_irq_mask = 0xffffffff;
 
diff --git a/arch/arm/mach-omap2/irq.c b/arch/arm/mach-omap2/irq.c
index d354e0fe4477..c40fc378a251 100644
--- a/arch/arm/mach-omap2/irq.c
+++ b/arch/arm/mach-omap2/irq.c
@@ -119,7 +119,7 @@ static void __init omap_irq_bank_init_one(struct omap_irq_bank *bank)
 
 void __init omap_init_irq(void)
 {
-	unsigned long nr_irqs = 0;
+	unsigned long nr_of_irqs = 0;
 	unsigned int nr_banks = 0;
 	int i;
 
@@ -133,14 +133,14 @@ void __init omap_init_irq(void)
 
 		omap_irq_bank_init_one(bank);
 
-		nr_irqs += bank->nr_irqs;
+		nr_of_irqs += bank->nr_irqs;
 		nr_banks++;
 	}
 
 	printk(KERN_INFO "Total of %ld interrupts on %d active controller%s\n",
-	       nr_irqs, nr_banks, nr_banks > 1 ? "s" : "");
+	       nr_of_irqs, nr_banks, nr_banks > 1 ? "s" : "");
 
-	for (i = 0; i < nr_irqs; i++) {
+	for (i = 0; i < nr_of_irqs; i++) {
 		set_irq_chip(i, &omap_irq_chip);
 		set_irq_handler(i, handle_level_irq);
 		set_irq_flags(i, IRQF_VALID);
diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c
index c36a6d59d6f0..310477ba1bbf 100644
--- a/arch/avr32/mach-at32ap/extint.c
+++ b/arch/avr32/mach-at32ap/extint.c
@@ -191,7 +191,7 @@ static int __init eic_probe(struct platform_device *pdev)
 	struct eic *eic;
 	struct resource *regs;
 	unsigned int i;
-	unsigned int nr_irqs;
+	unsigned int nr_of_irqs;
 	unsigned int int_irq;
 	int ret;
 	u32 pattern;
@@ -224,7 +224,7 @@ static int __init eic_probe(struct platform_device *pdev)
 	eic_writel(eic, IDR, ~0UL);
 	eic_writel(eic, MODE, ~0UL);
 	pattern = eic_readl(eic, MODE);
-	nr_irqs = fls(pattern);
+	nr_of_irqs = fls(pattern);
 
 	/* Trigger on low level unless overridden by driver */
 	eic_writel(eic, EDGE, 0UL);
@@ -232,7 +232,7 @@ static int __init eic_probe(struct platform_device *pdev)
 
 	eic->chip = &eic_chip;
 
-	for (i = 0; i < nr_irqs; i++) {
+	for (i = 0; i < nr_of_irqs; i++) {
 		set_irq_chip_and_handler(eic->first_irq + i, &eic_chip,
 					 handle_level_irq);
 		set_irq_chip_data(eic->first_irq + i, eic);
@@ -256,7 +256,7 @@ static int __init eic_probe(struct platform_device *pdev)
 		 eic->regs, int_irq);
 	dev_info(&pdev->dev,
 		 "Handling %u external IRQs, starting with IRQ %u\n",
-		 nr_irqs, eic->first_irq);
+		 nr_of_irqs, eic->first_irq);
 
 	return 0;
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 49349ba77d80..739668968390 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1242,14 +1242,6 @@ config EFI
   	resultant kernel should continue to boot on existing non-EFI
   	platforms.
 
-config IRQBALANCE
-	def_bool y
-	prompt "Enable kernel irq balancing"
-	depends on X86_32 && SMP && X86_IO_APIC
-	help
-	  The default yes will allow the kernel to do irq load balancing.
-	  Saying no will keep the kernel from doing irq load balancing.
-
 config SECCOMP
 	def_bool y
 	prompt "Enable seccomp to safely compute untrusted bytecode"
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 52d0359719d7..13b8c86ae985 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -287,7 +287,6 @@ CONFIG_MTRR=y
 # CONFIG_MTRR_SANITIZER is not set
 CONFIG_X86_PAT=y
 CONFIG_EFI=y
-# CONFIG_IRQBALANCE is not set
 CONFIG_SECCOMP=y
 # CONFIG_HZ_100 is not set
 # CONFIG_HZ_250 is not set
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0d41f0343dc0..d7e5a58ee22f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -23,7 +23,7 @@ CFLAGS_hpet.o		:= $(nostackp)
 CFLAGS_tsc.o		:= $(nostackp)
 
 obj-y			:= process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
-obj-y			+= traps.o irq_$(BITS).o dumpstack_$(BITS).o
+obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o
 obj-y			+= setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
@@ -60,8 +60,8 @@ obj-$(CONFIG_X86_32_SMP)	+= smpcommon.o
 obj-$(CONFIG_X86_64_SMP)	+= tsc_sync.o smpcommon.o
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline_$(BITS).o
 obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
-obj-$(CONFIG_X86_LOCAL_APIC)	+= apic_$(BITS).o nmi.o
-obj-$(CONFIG_X86_IO_APIC)	+= io_apic_$(BITS).o
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o nmi.o
+obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
@@ -108,7 +108,7 @@ obj-$(CONFIG_MICROCODE)			+= microcode.o
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
         obj-y				+= genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
-	obj-y				+= bios_uv.o
+	obj-y				+= bios_uv.o uv_irq.o uv_sysfs.o
         obj-y				+= genx2apic_cluster.o
         obj-y				+= genx2apic_phys.o
         obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index eb875cdc7367..0d1c26a583c5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1256,7 +1256,7 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr,
-				  NR_IRQ_VECTORS);
+				  nr_irqs);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX
 		       "Error parsing interrupt source overrides entry\n");
@@ -1276,7 +1276,7 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_parse_nmi_src,
-				  NR_IRQ_VECTORS);
+				  nr_irqs);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic.c
index 21c831d96af3..04a7f960bbc0 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic.c
@@ -23,11 +23,13 @@
 #include <linux/mc146818rtc.h>
 #include <linux/kernel_stat.h>
 #include <linux/sysdev.h>
+#include <linux/ioport.h>
 #include <linux/cpu.h>
 #include <linux/clockchips.h>
 #include <linux/acpi_pmtmr.h>
 #include <linux/module.h>
 #include <linux/dmi.h>
+#include <linux/dmar.h>
 
 #include <asm/atomic.h>
 #include <asm/smp.h>
@@ -36,8 +38,14 @@
 #include <asm/desc.h>
 #include <asm/arch_hooks.h>
 #include <asm/hpet.h>
+#include <asm/pgalloc.h>
 #include <asm/i8253.h>
 #include <asm/nmi.h>
+#include <asm/idle.h>
+#include <asm/proto.h>
+#include <asm/timex.h>
+#include <asm/apic.h>
+#include <asm/i8259.h>
 
 #include <mach_apic.h>
 #include <mach_apicdef.h>
@@ -50,16 +58,58 @@
 # error SPURIOUS_APIC_VECTOR definition error
 #endif
 
-unsigned long mp_lapic_addr;
-
+#ifdef CONFIG_X86_32
 /*
  * Knob to control our willingness to enable the local APIC.
  *
  * +1=force-enable
  */
 static int force_enable_local_apic;
-int disable_apic;
+/*
+ * APIC command line parameters
+ */
+static int __init parse_lapic(char *arg)
+{
+	force_enable_local_apic = 1;
+	return 0;
+}
+early_param("lapic", parse_lapic);
+/* Local APIC was disabled by the BIOS and enabled by the kernel */
+static int enabled_via_apicbase;
+
+#endif
+
+#ifdef CONFIG_X86_64
+static int apic_calibrate_pmtmr __initdata;
+static __init int setup_apicpmtimer(char *s)
+{
+	apic_calibrate_pmtmr = 1;
+	notsc_setup(NULL);
+	return 0;
+}
+__setup("apicpmtimer", setup_apicpmtimer);
+#endif
+
+#ifdef CONFIG_X86_64
+#define HAVE_X2APIC
+#endif
+
+#ifdef HAVE_X2APIC
+int x2apic;
+/* x2apic enabled before OS handover */
+int x2apic_preenabled;
+int disable_x2apic;
+static __init int setup_nox2apic(char *str)
+{
+	disable_x2apic = 1;
+	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
+	return 0;
+}
+early_param("nox2apic", setup_nox2apic);
+#endif
 
+unsigned long mp_lapic_addr;
+int disable_apic;
 /* Disable local APIC timer from the kernel commandline or via dmi quirk */
 static int disable_apic_timer __cpuinitdata;
 /* Local APIC timer works in C2 */
@@ -110,9 +160,6 @@ static struct clock_event_device lapic_clockevent = {
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
-/* Local APIC was disabled by the BIOS and enabled by the kernel */
-static int enabled_via_apicbase;
-
 static unsigned long apic_phys;
 
 /*
@@ -202,6 +249,42 @@ static struct apic_ops xapic_ops = {
 struct apic_ops __read_mostly *apic_ops = &xapic_ops;
 EXPORT_SYMBOL_GPL(apic_ops);
 
+#ifdef HAVE_X2APIC
+static void x2apic_wait_icr_idle(void)
+{
+	/* no need to wait for icr idle in x2apic */
+	return;
+}
+
+static u32 safe_x2apic_wait_icr_idle(void)
+{
+	/* no need to wait for icr idle in x2apic */
+	return 0;
+}
+
+void x2apic_icr_write(u32 low, u32 id)
+{
+	wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+}
+
+u64 x2apic_icr_read(void)
+{
+	unsigned long val;
+
+	rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+	return val;
+}
+
+static struct apic_ops x2apic_ops = {
+	.read = native_apic_msr_read,
+	.write = native_apic_msr_write,
+	.icr_read = x2apic_icr_read,
+	.icr_write = x2apic_icr_write,
+	.wait_icr_idle = x2apic_wait_icr_idle,
+	.safe_wait_icr_idle = safe_x2apic_wait_icr_idle,
+};
+#endif
+
 /**
  * enable_NMI_through_LVT0 - enable NMI through local vector table 0
  */
@@ -219,6 +302,7 @@ void __cpuinit enable_NMI_through_LVT0(void)
 	apic_write(APIC_LVT0, v);
 }
 
+#ifdef CONFIG_X86_32
 /**
  * get_physical_broadcast - Get number of physical broadcast IDs
  */
@@ -226,6 +310,7 @@ int get_physical_broadcast(void)
 {
 	return modern_apic() ? 0xff : 0xf;
 }
+#endif
 
 /**
  * lapic_get_maxlvt - get the maximum number of local vector table entries
@@ -247,11 +332,7 @@ int lapic_get_maxlvt(void)
  */
 
 /* Clock divisor */
-#ifdef CONFG_X86_64
-#define APIC_DIVISOR 1
-#else
 #define APIC_DIVISOR 16
-#endif
 
 /*
  * This function sets up the local APIC timer, with a timeout of
@@ -383,7 +464,7 @@ static void lapic_timer_broadcast(cpumask_t mask)
  * 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 __devinit setup_APIC_timer(void)
+static void __cpuinit setup_APIC_timer(void)
 {
 	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
@@ -453,14 +534,51 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
 	}
 }
 
+static int __init calibrate_by_pmtimer(long deltapm, long *delta)
+{
+	const long pm_100ms = PMTMR_TICKS_PER_SEC / 10;
+	const long pm_thresh = pm_100ms / 100;
+	unsigned long mult;
+	u64 res;
+
+#ifndef CONFIG_X86_PM_TIMER
+	return -1;
+#endif
+
+	apic_printk(APIC_VERBOSE, "... PM timer delta = %ld\n", deltapm);
+
+	/* Check, if the PM timer is available */
+	if (!deltapm)
+		return -1;
+
+	mult = clocksource_hz2mult(PMTMR_TICKS_PER_SEC, 22);
+
+	if (deltapm > (pm_100ms - pm_thresh) &&
+	    deltapm < (pm_100ms + pm_thresh)) {
+		apic_printk(APIC_VERBOSE, "... PM timer result ok\n");
+	} else {
+		res = (((u64)deltapm) *  mult) >> 22;
+		do_div(res, 1000000);
+		printk(KERN_WARNING "APIC calibration not consistent "
+			"with PM Timer: %ldms instead of 100ms\n",
+			(long)res);
+		/* Correct the lapic counter value */
+		res = (((u64)(*delta)) * pm_100ms);
+		do_div(res, deltapm);
+		printk(KERN_INFO "APIC delta adjusted to PM-Timer: "
+			"%lu (%ld)\n", (unsigned long)res, *delta);
+		*delta = (long)res;
+	}
+
+	return 0;
+}
+
 static int __init calibrate_APIC_clock(void)
 {
 	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
-	const long pm_100ms = PMTMR_TICKS_PER_SEC/10;
-	const long pm_thresh = pm_100ms/100;
 	void (*real_handler)(struct clock_event_device *dev);
 	unsigned long deltaj;
-	long delta, deltapm;
+	long delta;
 	int pm_referenced = 0;
 
 	local_irq_disable();
@@ -470,10 +588,10 @@ static int __init calibrate_APIC_clock(void)
 	global_clock_event->event_handler = lapic_cal_handler;
 
 	/*
-	 * Setup the APIC counter to 1e9. There is no way the lapic
+	 * Setup the APIC counter to maximum. There is no way the lapic
 	 * can underflow in the 100ms detection time frame
 	 */
-	__setup_APIC_LVTT(1000000000, 0, 0);
+	__setup_APIC_LVTT(0xffffffff, 0, 0);
 
 	/* Let the interrupts run */
 	local_irq_enable();
@@ -490,34 +608,9 @@ static int __init calibrate_APIC_clock(void)
 	delta = lapic_cal_t1 - lapic_cal_t2;
 	apic_printk(APIC_VERBOSE, "... lapic delta = %ld\n", delta);
 
-	/* Check, if the PM timer is available */
-	deltapm = lapic_cal_pm2 - lapic_cal_pm1;
-	apic_printk(APIC_VERBOSE, "... PM timer delta = %ld\n", deltapm);
-
-	if (deltapm) {
-		unsigned long mult;
-		u64 res;
-
-		mult = clocksource_hz2mult(PMTMR_TICKS_PER_SEC, 22);
-
-		if (deltapm > (pm_100ms - pm_thresh) &&
-		    deltapm < (pm_100ms + pm_thresh)) {
-			apic_printk(APIC_VERBOSE, "... PM timer result ok\n");
-		} else {
-			res = (((u64) deltapm) *  mult) >> 22;
-			do_div(res, 1000000);
-			printk(KERN_WARNING "APIC calibration not consistent "
-			       "with PM Timer: %ldms instead of 100ms\n",
-			       (long)res);
-			/* Correct the lapic counter value */
-			res = (((u64) delta) * pm_100ms);
-			do_div(res, deltapm);
-			printk(KERN_INFO "APIC delta adjusted to PM-Timer: "
-			       "%lu (%ld)\n", (unsigned long) res, delta);
-			delta = (long) res;
-		}
-		pm_referenced = 1;
-	}
+	/* we trust the PM based calibration if possible */
+	pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
+					&delta);
 
 	/* Calculate the scaled math multiplication factor */
 	lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
@@ -559,7 +652,10 @@ static int __init calibrate_APIC_clock(void)
 
 	levt->features &= ~CLOCK_EVT_FEAT_DUMMY;
 
-	/* We trust the pm timer based calibration */
+	/*
+	 * PM timer calibration failed or not turned on
+	 * so lets try APIC timer based calibration
+	 */
 	if (!pm_referenced) {
 		apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
 
@@ -652,7 +748,7 @@ void __init setup_boot_APIC_clock(void)
 	setup_APIC_timer();
 }
 
-void __devinit setup_secondary_APIC_clock(void)
+void __cpuinit setup_secondary_APIC_clock(void)
 {
 	setup_APIC_timer();
 }
@@ -718,6 +814,9 @@ void smp_apic_timer_interrupt(struct pt_regs *regs)
 	 * Besides, if we don't timer interrupts ignore the global
 	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
+#ifdef CONFIG_X86_64
+	exit_idle();
+#endif
 	irq_enter();
 	local_apic_timer_interrupt();
 	irq_exit();
@@ -991,40 +1090,43 @@ void __init init_bsp_APIC(void)
 
 static void __cpuinit lapic_setup_esr(void)
 {
-	unsigned long oldvalue, value, maxlvt;
-	if (lapic_is_integrated() && !esr_disable) {
-		if (esr_disable) {
-			/*
-			 * Something untraceable is creating bad interrupts on
-			 * secondary quads ... for the moment, just leave the
-			 * ESR disabled - we can't do anything useful with the
-			 * errors anyway - mbligh
-			 */
-			printk(KERN_INFO "Leaving ESR disabled.\n");
-			return;
-		}
-		/* !82489DX */
-		maxlvt = lapic_get_maxlvt();
-		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP. */
-			apic_write(APIC_ESR, 0);
-		oldvalue = apic_read(APIC_ESR);
+	unsigned int oldvalue, value, maxlvt;
+
+	if (!lapic_is_integrated()) {
+		printk(KERN_INFO "No ESR for 82489DX.\n");
+		return;
+	}
 
-		/* enables sending errors */
-		value = ERROR_APIC_VECTOR;
-		apic_write(APIC_LVTERR, value);
+	if (esr_disable) {
 		/*
-		 * spec says clear errors after enabling vector.
+		 * Something untraceable is creating bad interrupts on
+		 * secondary quads ... for the moment, just leave the
+		 * ESR disabled - we can't do anything useful with the
+		 * errors anyway - mbligh
 		 */
-		if (maxlvt > 3)
-			apic_write(APIC_ESR, 0);
-		value = apic_read(APIC_ESR);
-		if (value != oldvalue)
-			apic_printk(APIC_VERBOSE, "ESR value before enabling "
-				"vector: 0x%08lx  after: 0x%08lx\n",
-				oldvalue, value);
-	} else {
-		printk(KERN_INFO "No ESR for 82489DX.\n");
+		printk(KERN_INFO "Leaving ESR disabled.\n");
+		return;
 	}
+
+	maxlvt = lapic_get_maxlvt();
+	if (maxlvt > 3)		/* Due to the Pentium erratum 3AP. */
+		apic_write(APIC_ESR, 0);
+	oldvalue = apic_read(APIC_ESR);
+
+	/* enables sending errors */
+	value = ERROR_APIC_VECTOR;
+	apic_write(APIC_LVTERR, value);
+
+	/*
+	 * spec says clear errors after enabling vector.
+	 */
+	if (maxlvt > 3)
+		apic_write(APIC_ESR, 0);
+	value = apic_read(APIC_ESR);
+	if (value != oldvalue)
+		apic_printk(APIC_VERBOSE, "ESR value before enabling "
+			"vector: 0x%08x  after: 0x%08x\n",
+			oldvalue, value);
 }
 
 
@@ -1033,24 +1135,27 @@ static void __cpuinit lapic_setup_esr(void)
  */
 void __cpuinit setup_local_APIC(void)
 {
-	unsigned long value, integrated;
+	unsigned int value;
 	int i, j;
 
+#ifdef CONFIG_X86_32
 	/* Pound the ESR really hard over the head with a big hammer - mbligh */
-	if (esr_disable) {
+	if (lapic_is_integrated() && esr_disable) {
 		apic_write(APIC_ESR, 0);
 		apic_write(APIC_ESR, 0);
 		apic_write(APIC_ESR, 0);
 		apic_write(APIC_ESR, 0);
 	}
+#endif
 
-	integrated = lapic_is_integrated();
+	preempt_disable();
 
 	/*
 	 * Double-check whether this APIC is really registered.
+	 * This is meaningless in clustered apic mode, so we skip it.
 	 */
 	if (!apic_id_registered())
-		WARN_ON_ONCE(1);
+		BUG();
 
 	/*
 	 * Intel recommends to set DFR, LDR and TPR before enabling
@@ -1096,6 +1201,7 @@ void __cpuinit setup_local_APIC(void)
 	 */
 	value |= APIC_SPIV_APIC_ENABLED;
 
+#ifdef CONFIG_X86_32
 	/*
 	 * Some unknown Intel IO/APIC (or APIC) errata is biting us with
 	 * certain networking cards. If high frequency interrupts are
@@ -1116,8 +1222,13 @@ void __cpuinit setup_local_APIC(void)
 	 * See also the comment in end_level_ioapic_irq().  --macro
 	 */
 
-	/* Enable focus processor (bit==0) */
+	/*
+	 * - enable focus processor (bit==0)
+	 * - 64bit mode always use processor focus
+	 *   so no need to set it
+	 */
 	value &= ~APIC_SPIV_FOCUS_DISABLED;
+#endif
 
 	/*
 	 * Set spurious IRQ vector
@@ -1154,9 +1265,11 @@ void __cpuinit setup_local_APIC(void)
 		value = APIC_DM_NMI;
 	else
 		value = APIC_DM_NMI | APIC_LVT_MASKED;
-	if (!integrated)		/* 82489DX */
+	if (!lapic_is_integrated())		/* 82489DX */
 		value |= APIC_LVT_LEVEL_TRIGGER;
 	apic_write(APIC_LVT1, value);
+
+	preempt_enable();
 }
 
 void __cpuinit end_local_APIC_setup(void)
@@ -1177,6 +1290,153 @@ void __cpuinit end_local_APIC_setup(void)
 	apic_pm_activate();
 }
 
+#ifdef HAVE_X2APIC
+void check_x2apic(void)
+{
+	int msr, msr2;
+
+	rdmsr(MSR_IA32_APICBASE, msr, msr2);
+
+	if (msr & X2APIC_ENABLE) {
+		printk("x2apic enabled by BIOS, switching to x2apic ops\n");
+		x2apic_preenabled = x2apic = 1;
+		apic_ops = &x2apic_ops;
+	}
+}
+
+void enable_x2apic(void)
+{
+	int msr, msr2;
+
+	rdmsr(MSR_IA32_APICBASE, msr, msr2);
+	if (!(msr & X2APIC_ENABLE)) {
+		printk("Enabling x2apic\n");
+		wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
+	}
+}
+
+void enable_IR_x2apic(void)
+{
+#ifdef CONFIG_INTR_REMAP
+	int ret;
+	unsigned long flags;
+
+	if (!cpu_has_x2apic)
+		return;
+
+	if (!x2apic_preenabled && disable_x2apic) {
+		printk(KERN_INFO
+		       "Skipped enabling x2apic and Interrupt-remapping "
+		       "because of nox2apic\n");
+		return;
+	}
+
+	if (x2apic_preenabled && disable_x2apic)
+		panic("Bios already enabled x2apic, can't enforce nox2apic");
+
+	if (!x2apic_preenabled && skip_ioapic_setup) {
+		printk(KERN_INFO
+		       "Skipped enabling x2apic and Interrupt-remapping "
+		       "because of skipping io-apic setup\n");
+		return;
+	}
+
+	ret = dmar_table_init();
+	if (ret) {
+		printk(KERN_INFO
+		       "dmar_table_init() failed with %d:\n", ret);
+
+		if (x2apic_preenabled)
+			panic("x2apic enabled by bios. But IR enabling failed");
+		else
+			printk(KERN_INFO
+			       "Not enabling x2apic,Intr-remapping\n");
+		return;
+	}
+
+	local_irq_save(flags);
+	mask_8259A();
+
+	ret = save_mask_IO_APIC_setup();
+	if (ret) {
+		printk(KERN_INFO "Saving IO-APIC state failed: %d\n", ret);
+		goto end;
+	}
+
+	ret = enable_intr_remapping(1);
+
+	if (ret && x2apic_preenabled) {
+		local_irq_restore(flags);
+		panic("x2apic enabled by bios. But IR enabling failed");
+	}
+
+	if (ret)
+		goto end_restore;
+
+	if (!x2apic) {
+		x2apic = 1;
+		apic_ops = &x2apic_ops;
+		enable_x2apic();
+	}
+
+end_restore:
+	if (ret)
+		/*
+		 * IR enabling failed
+		 */
+		restore_IO_APIC_setup();
+	else
+		reinit_intr_remapped_IO_APIC(x2apic_preenabled);
+
+end:
+	unmask_8259A();
+	local_irq_restore(flags);
+
+	if (!ret) {
+		if (!x2apic_preenabled)
+			printk(KERN_INFO
+			       "Enabled x2apic and interrupt-remapping\n");
+		else
+			printk(KERN_INFO
+			       "Enabled Interrupt-remapping\n");
+	} else
+		printk(KERN_ERR