Merge branch 'x86/x2apic' into x86/core

Conflicts:

	include/asm-x86/i8259.h
	include/asm-x86/msidef.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

26 files changed, 1462 insertions, 156 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e3cba0b4560..4d621eb90bb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1652,6 +1652,14 @@ config DMAR_FLOPPY_WA
 	 workaround will setup a 1:1 mapping for the first
 	 16M to make floppy (an ISA device) work.
 
+config INTR_REMAP
+	bool "Support for Interrupt Remapping (EXPERIMENTAL)"
+	depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL
+	help
+	 Supports Interrupt remapping for IO-APIC and MSI devices.
+	 To use x2apic mode in the CPU's which support x2APIC enhancements or
+	 to support platforms with CPU's having > 8 bit APIC ID, say Y.
+
 source "drivers/pci/pcie/Kconfig"
 
 source "drivers/pci/Kconfig"
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 3db651fc8ec..a07ec14f331 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -104,6 +104,8 @@ obj-$(CONFIG_OLPC)		+= olpc.o
 ifeq ($(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				+= genx2apic_cluster.o
+        obj-y				+= genx2apic_phys.o
         obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
         obj-$(CONFIG_AUDIT)		+= audit_64.o
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index fa88a1d7129..12e260e8fb2 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -761,7 +761,7 @@ static void __init acpi_register_lapic_address(unsigned long address)
 
 	set_fixmap_nocache(FIX_APIC_BASE, address);
 	if (boot_cpu_physical_apicid == -1U) {
-		boot_cpu_physical_apicid  = GET_APIC_ID(read_apic_id());
+		boot_cpu_physical_apicid  = read_apic_id();
 #ifdef CONFIG_X86_32
 		apic_version[boot_cpu_physical_apicid] =
 			 GET_APIC_VERSION(apic_read(APIC_LVR));
@@ -1337,7 +1337,9 @@ static void __init acpi_process_madt(void)
 				acpi_ioapic = 1;
 
 				smp_found_config = 1;
+#ifdef CONFIG_X86_32
 				setup_apic_routing();
+#endif
 			}
 		}
 		if (error == -EINVAL) {
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index d6c89835837..f93c18f5b79 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -145,13 +145,18 @@ static int modern_apic(void)
 	return lapic_get_version() >= 0x14;
 }
 
-void apic_wait_icr_idle(void)
+/*
+ * Paravirt kernels also might be using these below ops. So we still
+ * use generic apic_read()/apic_write(), which might be pointing to different
+ * ops in PARAVIRT case.
+ */
+void xapic_wait_icr_idle(void)
 {
 	while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
 		cpu_relax();
 }
 
-u32 safe_apic_wait_icr_idle(void)
+u32 safe_xapic_wait_icr_idle(void)
 {
 	u32 send_status;
 	int timeout;
@@ -167,6 +172,34 @@ u32 safe_apic_wait_icr_idle(void)
 	return send_status;
 }
 
+void xapic_icr_write(u32 low, u32 id)
+{
+	apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
+	apic_write(APIC_ICR, low);
+}
+
+u64 xapic_icr_read(void)
+{
+	u32 icr1, icr2;
+
+	icr2 = apic_read(APIC_ICR2);
+	icr1 = apic_read(APIC_ICR);
+
+	return icr1 | ((u64)icr2 << 32);
+}
+
+static struct apic_ops xapic_ops = {
+	.read = native_apic_mem_read,
+	.write = native_apic_mem_write,
+	.icr_read = xapic_icr_read,
+	.icr_write = xapic_icr_write,
+	.wait_icr_idle = xapic_wait_icr_idle,
+	.safe_wait_icr_idle = safe_xapic_wait_icr_idle,
+};
+
+struct apic_ops __read_mostly *apic_ops = &xapic_ops;
+EXPORT_SYMBOL_GPL(apic_ops);
+
 /**
  * enable_NMI_through_LVT0 - enable NMI through local vector table 0
  */
@@ -1205,7 +1238,7 @@ void __init init_apic_mappings(void)
 	 * default configuration (or the MP table is broken).
 	 */
 	if (boot_cpu_physical_apicid == -1U)
-		boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+		boot_cpu_physical_apicid = read_apic_id();
 
 }
 
@@ -1242,7 +1275,7 @@ int __init APIC_init_uniprocessor(void)
 	 * might be zero if read from MP tables. Get it from LAPIC.
 	 */
 #ifdef CONFIG_CRASH_DUMP
-	boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+	boot_cpu_physical_apicid = read_apic_id();
 #endif
 	physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
 
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 7f1f030da7e..cd63c0bc618 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -27,6 +27,7 @@
 #include <linux/clockchips.h>
 #include <linux/acpi_pmtmr.h>
 #include <linux/module.h>
+#include <linux/dmar.h>
 
 #include <asm/atomic.h>
 #include <asm/smp.h>
@@ -39,6 +40,7 @@
 #include <asm/proto.h>
 #include <asm/timex.h>
 #include <asm/apic.h>
+#include <asm/i8259.h>
 
 #include <mach_ipi.h>
 #include <mach_apic.h>
@@ -46,6 +48,11 @@
 static int disable_apic_timer __cpuinitdata;
 static int apic_calibrate_pmtmr __initdata;
 int disable_apic;
+int disable_x2apic;
+int x2apic;
+
+/* x2apic enabled before OS handover */
+int x2apic_preenabled;
 
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
@@ -119,13 +126,13 @@ static int modern_apic(void)
 	return lapic_get_version() >= 0x14;
 }
 
-void apic_wait_icr_idle(void)
+void xapic_wait_icr_idle(void)
 {
 	while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
 		cpu_relax();
 }
 
-u32 safe_apic_wait_icr_idle(void)
+u32 safe_xapic_wait_icr_idle(void)
 {
 	u32 send_status;
 	int timeout;
@@ -141,6 +148,69 @@ u32 safe_apic_wait_icr_idle(void)
 	return send_status;
 }
 
+void xapic_icr_write(u32 low, u32 id)
+{
+	apic_write(APIC_ICR2, id << 24);
+	apic_write(APIC_ICR, low);
+}
+
+u64 xapic_icr_read(void)
+{
+	u32 icr1, icr2;
+
+	icr2 = apic_read(APIC_ICR2);
+	icr1 = apic_read(APIC_ICR);
+
+	return (icr1 | ((u64)icr2 << 32));
+}
+
+static struct apic_ops xapic_ops = {
+	.read = native_apic_mem_read,
+	.write = native_apic_mem_write,
+	.icr_read = xapic_icr_read,
+	.icr_write = xapic_icr_write,
+	.wait_icr_idle = xapic_wait_icr_idle,
+	.safe_wait_icr_idle = safe_xapic_wait_icr_idle,
+};
+
+struct apic_ops __read_mostly *apic_ops = &xapic_ops;
+
+EXPORT_SYMBOL_GPL(apic_ops);
+
+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,
+};
+
 /**
  * enable_NMI_through_LVT0 - enable NMI through local vector table 0
  */
@@ -630,10 +700,10 @@ int __init verify_local_APIC(void)
 	/*
 	 * The ID register is read/write in a real APIC.
 	 */
-	reg0 = read_apic_id();
+	reg0 = apic_read(APIC_ID);
 	apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
 	apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
-	reg1 = read_apic_id();
+	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))
@@ -834,6 +904,125 @@ void __cpuinit end_local_APIC_setup(void)
 	apic_pm_activate();
 }
 
+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();
+	save_mask_IO_APIC_setup();
+
+	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;
+
+	if (!x2apic) {
+		x2apic = 1;
+		apic_ops = &x2apic_ops;
+		enable_x2apic();
+	}
+end:
+	if (ret)
+		/*
+		 * IR enabling failed
+		 */
+		restore_IO_APIC_setup();
+	else
+		reinit_intr_remapped_IO_APIC(x2apic_preenabled);
+
+	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
+		       "Failed to enable Interrupt-remapping and x2apic\n");
+#else
+	if (!cpu_has_x2apic)
+		return;
+
+	if (x2apic_preenabled)
+		panic("x2apic enabled prior OS handover,"
+		      " enable CONFIG_INTR_REMAP");
+
+	printk(KERN_INFO "Enable CONFIG_INTR_REMAP for enabling intr-remapping "
+	       " and x2apic\n");
+#endif
+
+	return;
+}
+
 /*
  * Detect and enable local APICs on non-SMP boards.
  * Original code written by Keir Fraser.
@@ -873,7 +1062,7 @@ void __init early_init_lapic_mapping(void)
 	 * Fetch the APIC ID of the BSP in case we have a
 	 * default configuration (or the MP table is broken).
 	 */
-	boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+	boot_cpu_physical_apicid = read_apic_id();
 }
 
 /**
@@ -881,6 +1070,11 @@ void __init early_init_lapic_mapping(void)
  */
 void __init init_apic_mappings(void)
 {
+	if (x2apic) {
+		boot_cpu_physical_apicid = read_apic_id();
+		return;
+	}
+
 	/*
 	 * If no local APIC can be found then set up a fake all
 	 * zeroes page to simulate the local APIC and another
@@ -900,7 +1094,7 @@ void __init init_apic_mappings(void)
 	 * Fetch the APIC ID of the BSP in case we have a
 	 * default configuration (or the MP table is broken).
 	 */
-	boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+	boot_cpu_physical_apicid = read_apic_id();
 }
 
 /*
@@ -919,6 +1113,9 @@ int __init APIC_init_uniprocessor(void)
 		return -1;
 	}
 
+	enable_IR_x2apic();
+	setup_apic_routing();
+
 	verify_local_APIC();
 
 	connect_bsp_APIC();
@@ -1100,6 +1297,11 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	cpu_set(cpu, cpu_present_map);
 }
 
+int hard_smp_processor_id(void)
+{
+	return read_apic_id();
+}
+
 /*
  * Power management
  */
@@ -1136,7 +1338,7 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 
 	maxlvt = lapic_get_maxlvt();
 
-	apic_pm_state.apic_id = read_apic_id();
+	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);
@@ -1171,10 +1373,14 @@ static int lapic_resume(struct sys_device *dev)
 	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);
+	if (!x2apic) {
+		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);
+	} else
+		enable_x2apic();
+
 	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);
@@ -1314,6 +1520,15 @@ __cpuinit int apic_is_clustered_box(void)
 	return (clusters > 2);
 }
 
+static __init int setup_nox2apic(char *str)
+{
+	disable_x2apic = 1;
+	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_X2APIC);
+	return 0;
+}
+early_param("nox2apic", setup_nox2apic);
+
+
 /*
  * APIC command line parameters
  */
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index dd6e3f15017..6f9b8924bdc 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -597,6 +597,8 @@ void __cpuinit cpu_init(void)
 	barrier();
 
 	check_efer();
+	if (cpu != 0 && x2apic)
+		enable_x2apic();
 
 	/*
 	 * set up and load the per-CPU TSS
diff --git a/arch/x86/kernel/cpu/feature_names.c b/arch/x86/kernel/cpu/feature_names.c
index e43ad4ad4cb..0bf4d37a048 100644
--- a/arch/x86/kernel/cpu/feature_names.c
+++ b/arch/x86/kernel/cpu/feature_names.c
@@ -45,7 +45,7 @@ const char * const x86_cap_flags[NCAPINTS*32] = {
 	/* Intel-defined (#2) */
 	"pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est",
 	"tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
-	NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt",
+	NULL, NULL, "dca", "sse4_1", "sse4_2", "x2apic", NULL, "popcnt",
 	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 
 	/* VIA/Cyrix/Centaur-defined */
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 1fa8be5bd21..b3ba969c50d 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -21,81 +21,52 @@
 #include <asm/ipi.h>
 #include <asm/genapic.h>
 
-#ifdef CONFIG_ACPI
-#include <acpi/acpi_bus.h>
-#endif
-
-DEFINE_PER_CPU(int, x2apic_extra_bits);
+extern struct genapic apic_flat;
+extern struct genapic apic_physflat;
+extern struct genapic apic_x2xpic_uv_x;
+extern struct genapic apic_x2apic_phys;
+extern struct genapic apic_x2apic_cluster;
 
 struct genapic __read_mostly *genapic = &apic_flat;
 
-static enum uv_system_type uv_system_type;
+static struct genapic *apic_probe[] __initdata = {
+	&apic_x2apic_uv_x,
+	&apic_x2apic_phys,
+	&apic_x2apic_cluster,
+	&apic_physflat,
+	NULL,
+};
 
 /*
  * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode.
  */
 void __init setup_apic_routing(void)
 {
-	if (uv_system_type == UV_NON_UNIQUE_APIC)
-		genapic = &apic_x2apic_uv_x;
-	else
-#ifdef CONFIG_ACPI
-	/*
-	 * Quirk: some x86_64 machines can only use physical APIC mode
-	 * regardless of how many processors are present (x86_64 ES7000
-	 * is an example).
-	 */
-	if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
-			(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL))
-		genapic = &apic_physflat;
-	else
-#endif
-
-	if (max_physical_apicid < 8)
-		genapic = &apic_flat;
-	else
-		genapic = &apic_physflat;
-
-	printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
+	if (genapic == &apic_flat) {
+		if (max_physical_apicid >= 8)
+			genapic = &apic_physflat;
+		printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
+	}
 }
 
 /* Same for both flat and physical. */
 
-void send_IPI_self(int vector)
+void apic_send_IPI_self(int vector)
 {
 	__send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
 }
 
 int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-	if (!strcmp(oem_id, "SGI")) {
-		if (!strcmp(oem_table_id, "UVL"))
-			uv_system_type = UV_LEGACY_APIC;
-		else if (!strcmp(oem_table_id, "UVX"))
-			uv_system_type = UV_X2APIC;
-		else if (!strcmp(oem_table_id, "UVH"))
-			uv_system_type = UV_NON_UNIQUE_APIC;
+	int i;
+
+	for (i = 0; apic_probe[i]; ++i) {
+		if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) {
+			genapic = apic_probe[i];
+			printk(KERN_INFO "Setting APIC routing to %s.\n",
+				genapic->name);
+			return 1;
+		}
 	}
 	return 0;
 }
-
-unsigned int read_apic_id(void)
-{
-	unsigned int id;
-
-	WARN_ON(preemptible() && num_online_cpus() > 1);
-	id = apic_read(APIC_ID);
-	if (uv_system_type >= UV_X2APIC)
-		id  |= __get_cpu_var(x2apic_extra_bits);
-	return id;
-}
-
-enum uv_system_type get_uv_system_type(void)
-{
-	return uv_system_type;
-}
-
-int is_uv_system(void)
-{
-	return uv_system_type != UV_NONE;
-}
diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c
index 786548a62d3..9eca5ba7a6b 100644
--- a/arch/x86/kernel/genapic_flat_64.c
+++ b/arch/x86/kernel/genapic_flat_64.c
@@ -15,9 +15,20 @@
 #include <linux/kernel.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
+#include <linux/hardirq.h>
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
+#include <mach_apicdef.h>
+
+#ifdef CONFIG_ACPI
+#include <acpi/acpi_bus.h>
+#endif
+
+static int __init flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return 1;
+}
 
 static cpumask_t flat_target_cpus(void)
 {
@@ -95,9 +106,33 @@ static void flat_send_IPI_all(int vector)
 		__send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL);
 }
 
+static unsigned int get_apic_id(unsigned long x)
+{
+	unsigned int id;
+
+	id = (((x)>>24) & 0xFFu);
+	return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+	unsigned long x;
+
+	x = ((id & 0xFFu)<<24);
+	return x;
+}
+
+static unsigned int read_xapic_id(void)
+{
+	unsigned int id;
+
+	id = get_apic_id(apic_read(APIC_ID));
+	return id;
+}
+
 static int flat_apic_id_registered(void)
 {
-	return physid_isset(GET_APIC_ID(read_apic_id()), phys_cpu_present_map);
+	return physid_isset(read_xapic_id(), phys_cpu_present_map);
 }
 
 static unsigned int flat_cpu_mask_to_apicid(cpumask_t cpumask)
@@ -112,6 +147,7 @@ static unsigned int phys_pkg_id(int index_msb)
 
 struct genapic apic_flat =  {
 	.name = "flat",
+	.acpi_madt_oem_check = flat_acpi_madt_oem_check,
 	.int_delivery_mode = dest_LowestPrio,
 	.int_dest_mode = (APIC_DEST_LOGICAL != 0),
 	.target_cpus = flat_target_cpus,
@@ -121,8 +157,12 @@ struct genapic apic_flat =  {
 	.send_IPI_all = flat_send_IPI_all,
 	.send_IPI_allbutself = flat_send_IPI_allbutself,
 	.send_IPI_mask = flat_send_IPI_mask,
+	.send_IPI_self = apic_send_IPI_self,
 	.cpu_mask_to_apicid = flat_cpu_mask_to_apicid,
 	.phys_pkg_id = phys_pkg_id,
+	.get_apic_id = get_apic_id,
+	.set_apic_id = set_apic_id,
+	.apic_id_mask = (0xFFu<<24),
 };
 
 /*
@@ -130,6 +170,21 @@ struct genapic apic_flat =  {
  * We cannot use logical delivery in this case because the mask
  * overflows, so use physical mode.
  */
+static int __init physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+#ifdef CONFIG_ACPI
+	/*
+	 * Quirk: some x86_64 machines can only use physical APIC mode
+	 * regardless of how many processors are present (x86_64 ES7000
+	 * is an example).
+	 */
+	if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL))
+		return 1;
+#endif
+
+	return 0;
+}
 
 static cpumask_t physflat_target_cpus(void)
 {
@@ -176,6 +231,7 @@ static unsigned int physflat_cpu_mask_to_apicid(cpumask_t cpumask)
 
 struct genapic apic_physflat =  {
 	.name = "physical flat",
+	.acpi_madt_oem_check = physflat_acpi_madt_oem_check,
 	.int_delivery_mode = dest_Fixed,
 	.int_dest_mode = (APIC_DEST_PHYSICAL != 0),
 	.target_cpus = physflat_target_cpus,
@@ -185,6 +241,10 @@ struct genapic apic_physflat =  {
 	.send_IPI_all = physflat_send_IPI_all,
 	.send_IPI_allbutself = physflat_send_IPI_allbutself,
 	.send_IPI_mask = physflat_send_IPI_mask,
+	.send_IPI_self = apic_send_IPI_self,
 	.cpu_mask_to_apicid = physflat_cpu_mask_to_apicid,
 	.phys_pkg_id = phys_pkg_id,
+	.get_apic_id = get_apic_id,
+	.set_apic_id = set_apic_id,
+	.apic_id_mask = (0xFFu<<24),
 };
diff --git a/arch/x86/kernel/genx2apic_cluster.c b/arch/x86/kernel/genx2apic_cluster.c
new file mode 100644
index 00000000000..ef3f3182d50
--- /dev/null
+++ b/arch/x86/kernel/genx2apic_cluster.c
@@ -0,0 +1,164 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/dmar.h>
+
+#include <asm/smp.h>
+#include <asm/ipi.h>
+#include <asm/genapic.h>
+
+DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+
+static int __init x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	if (cpu_has_x2apic && intr_remapping_enabled)
+		return 1;
+
+	return 0;
+}
+
+/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
+
+static cpumask_t x2apic_target_cpus(void)
+{
+	return cpumask_of_cpu(0);
+}
+
+/*
+ * for now each logical cpu is in its own vector allocation domain.
+ */
+static cpumask_t x2apic_vector_allocation_domain(int cpu)
+{
+	cpumask_t domain = CPU_MASK_NONE;
+	cpu_set(cpu, domain);
+	return domain;
+}
+
+static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
+				   unsigned int dest)
+{
+	unsigned long cfg;
+
+	cfg = __prepare_ICR(0, vector, dest);
+
+	/*
+	 * send the IPI.
+	 */
+	x2apic_icr_write(cfg, apicid);
+}
+
+/*
+ * for now, we send the IPI's one by one in the cpumask.
+ * TBD: Based on the cpu mask, we can send the IPI's to the cluster group
+ * at once. We have 16 cpu's in a cluster. This will minimize IPI register
+ * writes.
+ */
+static void x2apic_send_IPI_mask(cpumask_t mask, int vector)
+{
+	unsigned long flags;
+	unsigned long query_cpu;
+
+	local_irq_save(flags);
+	for_each_cpu_mask(query_cpu, mask) {
+		__x2apic_send_IPI_dest(per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+				       vector, APIC_DEST_LOGICAL);
+	}
+	local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_allbutself(int vector)
+{
+	cpumask_t mask = cpu_online_map;
+
+	cpu_clear(smp_processor_id(), mask);
+
+	if (!cpus_empty(mask))
+		x2apic_send_IPI_mask(mask, vector);
+}
+
+static void x2apic_send_IPI_all(int vector)
+{
+	x2apic_send_IPI_mask(cpu_online_map, vector);
+}
+
+static int x2apic_apic_id_registered(void)
+{
+	return 1;
+}
+
+static unsigned int x2apic_cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	int cpu;
+
+	/*
+	 * We're using fixed IRQ delivery, can only return one phys APIC ID.
+	 * May as well be the first.
+	 */
+	cpu = first_cpu(cpumask);
+	if ((unsigned)cpu < NR_CPUS)
+		return per_cpu(x86_cpu_to_logical_apicid, cpu);
+	else
+		return BAD_APICID;
+}
+
+static unsigned int get_apic_id(unsigned long x)
+{
+	unsigned int id;
+
+	id = x;
+	return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+	unsigned long x;
+
+	x = id;
+	return x;
+}
+
+static unsigned int x2apic_read_id(void)
+{
+	return apic_read(APIC_ID);
+}
+
+static unsigned int phys_pkg_id(int index_msb)
+{
+	return x2apic_read_id() >> index_msb;
+}
+
+static void x2apic_send_IPI_self(int vector)
+{
+	apic_write(APIC_SELF_IPI, vector);
+}
+
+static void init_x2apic_ldr(void)
+{
+	int cpu = smp_processor_id();
+
+	per_cpu(x86_cpu_to_logical_apicid, cpu) = apic_read(APIC_LDR);
+	return;
+}
+
+struct genapic apic_x2apic_cluster = {
+	.name = "cluster x2apic",
+	.acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
+	.int_delivery_mode = dest_LowestPrio,
+	.int_dest_mode = (APIC_DEST_LOGICAL != 0),
+	.target_cpus = x2apic_target_cpus,
+	.vector_allocation_domain = x2apic_vector_allocation_domain,
+	.apic_id_registered = x2apic_apic_id_registered,
+	.init_apic_ldr = init_x2apic_ldr,
+	.send_IPI_all = x2apic_send_IPI_all,
+	.send_IPI_allbutself = x2apic_send_IPI_allbutself,
+	.send_IPI_mask = x2apic_send_IPI_mask,
+	.send_IPI_self = x2apic_send_IPI_self,
+	.cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+	.phys_pkg_id = phys_pkg_id,
+	.get_apic_id = get_apic_id,
+	.set_apic_id = set_apic_id,
+	.apic_id_mask = (0xFFFFFFFFu),
+};
diff --git a/arch/x86/kernel/genx2apic_phys.c b/arch/x86/kernel/genx2apic_phys.c
new file mode 100644
index 00000000000..3229c68aedd
--- /dev/null
+++ b/arch/x86/kernel/genx2apic_phys.c
@@ -0,0 +1,159 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/dmar.h>
+
+#include <asm/smp.h>
+#include <asm/ipi.h>
+#include <asm/genapic.h>
+
+static int x2apic_phys;
+
+static int set_x2apic_phys_mode(char *arg)
+{
+	x2apic_phys = 1;
+	return 0;
+}
+early_param("x2apic_phys", set_x2apic_phys_mode);
+
+static int __init x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	if (cpu_has_x2apic && intr_remapping_enabled && x2apic_phys)
+		return 1;
+
+	return 0;
+}
+
+/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
+
+static cpumask_t x2apic_target_cpus(void)
+{
+	return cpumask_of_cpu(0);
+}
+
+static cpumask_t x2apic_vector_allocation_domain(int cpu)
+{
+	cpumask_t domain = CPU_MASK_NONE;
+	cpu_set(cpu, domain);
+	return domain;
+}
+
+static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
+				   unsigned int dest)
+{
+	unsigned long cfg;
+
+	cfg = __prepare_ICR(0, vector, dest);
+
+	/*
+	 * send the IPI.
+	 */
+	x2apic_icr_write(cfg, apicid);
+}
+
+static void x2apic_send_IPI_mask(cpumask_t mask, int vector)
+{
+	unsigned long flags;
+	unsigned long query_cpu;
+
+	local_irq_save(flags);
+	for_each_cpu_mask(query_cpu, mask) {
+		__x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu),
+				       vector, APIC_DEST_PHYSICAL);
+	}
+	local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_allbutself(int vector)
+{
+	cpumask_t mask = cpu_online_map;
+
+	cpu_clear(smp_processor_id(), mask);
+
+	if (!cpus_empty(mask))
+		x2apic_send_IPI_mask(mask, vector);
+}
+
+static void x2apic_send_IPI_all(int vector)
+{
+	x2apic_send_IPI_mask(cpu_online_map, vector);
+}
+
+static int x2apic_apic_id_registered(void)
+{
+	return 1;
+}
+
+static unsigned int x2apic_cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	int cpu;
+
+	/*
+	 * We're using fixed IRQ delivery, can only return one phys APIC ID.
+	 * May as well be the first.
+	 */
+	cpu = first_cpu(cpumask);
+	if ((unsigned)cpu < NR_CPUS)
+		return per_cpu(x86_cpu_to_apicid, cpu);
+	else
+		return BAD_APICID;
+}
+
+static unsigned int get_apic_id(unsigned long x)
+{
+	unsigned int id;
+
+	id = x;
+	return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+	unsigned long x;
+
+	x = id;
+	return x;
+}
+
+static unsigned int x2apic_read_id(void)
+{
+	return apic_read(APIC_ID);
+}
+
+static unsigned int phys_pkg_id(int index_msb)
+{
+	return x2apic_read_id() >> index_msb;
+}
+
+void x2apic_send_IPI_self(int vector)
+{
+	apic_write(APIC_SELF_IPI, vector);
+}
+
+void init_x2apic_ldr(void)
+{
+	return;
+}
+
+struct genapic apic_x2apic_phys = {
+	.name = "physical x2apic",
+	.acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
+	.int_delivery_mode = dest_Fixed,
+	.int_dest_mode = (APIC_DEST_PHYSICAL != 0),
+	.target_cpus = x2apic_target_cpus,
+	.vector_allocation_domain = x2apic_vector_allocation_domain,
+	.apic_id_registered = x2apic_apic_id_registered,
+	.init_apic_ldr = init_x2apic_ldr,
+	.send_IPI_all = x2apic_send_IPI_all,
+	.send_IPI_allbutself = x2apic_send_IPI_allbutself,
+	.send_IPI_mask = x2apic_send_IPI_mask,
+	.send_IPI_self = x2apic_send_IPI_self,
+	.cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+	.phys_pkg_id = phys_pkg_id,
+	.get_apic_id = get_apic_id,
+	.set_apic_id = set_apic_id,
+	.apic_id_mask = (0xFFFFFFFFu),
+};
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index 2cfcbded888..3fe472223a9 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -12,12 +12,12 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/string.h>
-#include <linux/kernel.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/bootmem.h>
 #include <linux/module.h>
+#include <linux/hardirq.h>
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
@@ -26,6 +26,35 @@
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/bios.h>
 
+DEFINE_PER_CPU(int, x2apic_extra_bits);
+
+static enum uv_system_type uv_system_type;
+
+static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	if (!strcmp(oem_id, "SGI")) {
+		if (!strcmp(oem_table_id, "UVL"))
+			uv_system_type = UV_LEGACY_APIC;
+		else if (!strcmp(oem_table_id, "UVX"))
+			uv_system_type = UV_X2APIC;
+		else if (!strcmp(oem_table_id, "UVH")) {
+			uv_system_type = UV_NON_UNIQUE_APIC;
+			return 1;
+		}
+	}
+	return 0;
+}
+
+enum uv_system_type get_uv_system_type(void)
+{
+	return uv_system_type;
+}
+
+int is_uv_system(void)
+{
+	return uv_system_type != UV_NONE;
+}
+
 DEFINE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 EXPORT_PER_CPU_SYMBOL_GPL(__uv_hub_info);
 
@@ -123,6 +152,10 @@ static int uv_apic_id_registered(void)
 	return 1;
 }
 
+static void uv_init_apic_ldr(void)
+{
+}
+
 static unsigned int uv_cpu_mask_to_apicid(cpumask_t cpumask)
 {
 	int cpu;
@@ -138,9 +171,34 @@ static unsigned int uv_cpu_mask_to_apicid(cpumask_t cpumask)
 		return BAD_APICID;
 }
 
+static unsigned int get_apic_id(unsigned long x)
+{
+	unsigned int id;
+
+	WARN_ON(preemptible() && num_online_cpus() > 1);
+	id = x | __get_cpu_var(x2apic_extra_bits);
+
+	return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+	unsigned long x;
+
+	/* maskout x2apic_extra_bits ? */
+	x = id;
+	return x;
+}
+
+static unsigned int uv_read_apic_id(void)
+{
+
+	return get_apic_id(apic_read(APIC_ID));
+}
+
 static unsigned int phys_pkg_id(int index_msb)
 {
-	return GET_APIC_ID(read_apic_id()) >> index_msb;
+	return uv_read_apic_id() >> index_msb;
 }
 
 #ifdef ZZZ		/* Needs x2apic patch */
@@ -152,17 +210,22 @@ static void uv_send_IPI_self(int vector)
 
 struct genapic apic_x2apic_uv_x = {
 	.name = "UV large system",
+	.acpi_madt_oem_check = uv_acpi_madt_oem_check,
 	.int_delivery_mode = dest_Fixed,
 	.int_dest_mode = (APIC_DEST_PHYSICAL != 0),
 	.target_cpus = uv_target_cpus,
 	.vector_allocation_domain = uv_vector_allocation_domain,/* Fixme ZZZ */
 	.apic_id_registered = uv_apic_id_registered,
+	.init_apic_ldr = uv_init_apic_ldr,
 	.send_IPI_all = uv_send_IPI_all,
 	.send_IPI_allbutself = uv_send_IPI_allbutself,
 	.send_IPI_mask = uv_send_IPI_mask,
 	/* ZZZ.send_IPI_self = uv_send_IPI_self, */
 	.cpu_mask_to_apicid = uv_cpu_mask_to_apicid,
 	.phys_pkg_id = phys_pkg_id,	/* Fixme ZZZ */
+	.get_apic_id = get_apic_id,
+	.set_apic_id = set_apic_id,
+	.apic_id_mask = (0xFFFFFFFFu),
 };
 
 static __cpuinit void set_x2apic_extra_bits(int pnode)
@@ -399,3 +462,5 @@ void __cpuinit uv_cpu_init(void)
 	if (get_uv_system_type() == UV_NON_UNIQUE_APIC)
 		set_x2apic_extra_bits(uv_hub_info->pnode);
 }
+
+
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index dc92b49d920..4b8a53d841f 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -282,6 +282,30 @@ static int __init i8259A_init_sysfs(void)
 
 device_initcall(i8259A_init_sysfs);
 
+void mask_8259A(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&i8259A_lock, flags);
+
+	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
+	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
+
+	spin_unlock_irqrestore(&i8259A_lock, flags);
+}
+
+void unmask_8259A(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&i8259A_lock, flags);
+
+	outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
+	outb(cached_slave_mask, PIC_SLAVE_IMR);	  /* restore slave IRQ mask */
+
+	spin_unlock_irqrestore(&i8259A_lock, flags);
+}
+
 void init_8259A(int auto_eoi)
 {
 	unsigned long flags;
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index de9aa0e3a9c..98e4db5373f 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1494,7 +1494,7 @@ void /*__init*/ print_local_APIC(void *dummy)
 		smp_processor_id(), hard_smp_processor_id());
 	v = apic_read(APIC_ID);
 	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v,
-			GET_APIC_ID(read_apic_id()));
+			GET_APIC_ID(v));
 	v = apic_read(APIC_LVR);
 	printk(KERN_INFO "... APIC VERSION: %08x\n", v);
 	ver = GET_APIC_VERSION(v);
@@ -1702,8 +1702,7 @@ void disable_IO_APIC(void)
 		entry.dest_mode       = 0; /* Physical */
 		entry.delivery_mode   = dest_ExtINT; /* ExtInt */
 		entry.vector          = 0;
-		entry.dest.physical.physical_dest =
-					GET_APIC_ID(read_apic_id());
+		entry.dest.physical.physical_dest = read_apic_id();
 
 		/*
 		 * Add it to the IO-APIC irq-routing table:
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 8269434d170..b9950dae59b 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -37,6 +37,7 @@
 #include <acpi/acpi_bus.h>
 #endif
 #include <linux/bootmem.h>
+#include <linux/dmar.h>
 
 #include <asm/idle.h>
 #include <asm/io.h>
@@ -49,6 +50,7 @@
 #include <asm/nmi.h>
 #include <asm/msidef.h>
 #include <asm/hypertransport.h>
+#include <asm/irq_remapping.h>
 
 #include <mach_ipi.h>
 #include <mach_apic.h>
@@ -108,6 +110,9 @@ DEFINE_SPINLOCK(vector_lock);
  */
 int nr_ioapic_registers[MAX_IO_APICS];
 
+/* I/O APIC RTE contents at the OS boot up */
+struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS];
+
 /* I/O APIC entries */
 struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
 int nr_ioapics;
@@ -303,7 +308,12 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 		pin = entry->pin;
 		if (pin == -1)
 			break;
-		io_apic_write(apic, 0x11 + pin*2, dest);
+		/*
+		 * With interrupt-remapping, destination information comes
+		 * from interrupt-remapping table entry.
+		 */
+		if (!irq_remapped(irq))
+			io_apic_write(apic, 0x11 + pin*2, dest);
 		reg = io_apic_read(apic, 0x10 + pin*2);
 		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
 		reg |= vector;
@@ -440,6 +450,69 @@ static void clear_IO_APIC (void)
 			clear_IO_APIC_pin(apic, pin);
 }
 
+/*
+ * Saves and masks all the unmasked IO-APIC RTE's
+ */
+int save_mask_IO_APIC_setup(void)
+{
+	union IO_APIC_reg_01 reg_01;
+	unsigned long flags;
+	int apic, pin;
+
+	/*
+	 * The number of IO-APIC IRQ registers (== #pins):
+	 */
+	for (apic = 0; apic < nr_ioapics; apic++) {
+		spin_lock_irqsave(&ioapic_lock, flags);
+		reg_01.raw = io_apic_read(apic, 1);
+		spin_unlock_irqrestore(&ioapic_lock, flags);
+		nr_ioapic_registers[apic] = reg_01.bits.entries+1;
+	}
+
+	for (apic = 0; apic < nr_ioapics; apic++) {
+		early_ioapic_entries[apic] =
+			kzalloc(sizeof(struct IO_APIC_route_entry) *
+				nr_ioapic_registers[apic], GFP_KERNEL);
+		if (!early_ioapic_entries[apic])
+			return -ENOMEM;
+	}
+
+	for (apic = 0; apic < nr_ioapics; apic++)
+		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+			struct IO_APIC_route_entry entry;
+
+			entry = early_ioapic_entries[apic][pin] =
+				ioapic_read_entry(apic, pin);
+			if (!entry.mask) {
+				entry.mask = 1;
+				ioapic_write_entry(apic, pin, entry);
+			}
+		}
+	return 0;
+}
+
+void restore_IO_APIC_setup(void)
+{
+	int apic, pin;
+
+	for (apic = 0; apic < nr_ioapics; apic++)
+		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+			ioapic_write_entry(apic, pin,
+					   early_ioapic_entries[apic][pin]);
+}
+
+void reinit_intr_remapped_IO_APIC(int intr_remapping)
+{
+	/*
+	 * for now plain restore of previous settings.
+	 * TBD: In the case of OS enabling interrupt-remapping,
+	 * IO-APIC RTE's need to be setup to point to interrupt-remapping
+	 * table entries. for now, do a plain restore, and wait for
+	 * the setup_IO_APIC_irqs() to do proper initialization.
+	 */
+	restore_IO_APIC_setup();
+}
+
 int skip_ioapic_setup;
 int ioapic_force;
 
@@ -834,18 +907,98 @@ void setup_vector_irq(int cpu)
 
 
 static struct irq_chip ioapic_chip;
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip;
+#endif
 
 static void ioapic_register_intr(int irq, unsigned long trigger)
 {
-	if (trigger) {
+	if (trigger)
 		irq_desc[irq].status |= IRQ_LEVEL;
-		set_irq_chip_and_handler_name(irq, &ioapic_chip,
-					      handle_fasteoi_irq, "fasteoi");
-	} else {
+	else
 		irq_desc[irq].status &= ~IRQ_LEVEL;
+
+#ifdef CONFIG_INTR_REMAP
+	if (irq_remapped(irq)) {
+		irq_desc[irq].status |= IRQ_MOVE_PCNTXT;
+		if (trigger)
+			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+						      handle_fasteoi_irq,
+						     "fasteoi");
+		else
+			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+						      handle_edge_irq, "edge");
+		return;
+	}
+#endif
+	if (trigger)
+		set_irq_chip_and_handler_name(irq, &ioapic_chip,
+					      handle_fasteoi_irq,
+					      "fasteoi");
+	else
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					      handle_edge_irq, "edge");
+}
+
+static int setup_ioapic_entry(int apic, int irq,
+			      struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int trigger,
+			      int polarity, int vector)
+{
+	/*
+	 * add it to the IO-APIC irq-routing table:
+	 */
+	memset(entry,0,sizeof(*entry));
+
+#ifdef CONFIG_INTR_REMAP
+	if (intr_remapping_enabled) {
+		struct intel_iommu *iommu = map_ioapic_to_ir(apic);
+		struct irte irte;
+		struct IR_IO_APIC_route_entry *ir_entry =
+			(struct IR_IO_APIC_route_entry *) entry;
+		int index;
+
+		if (!iommu)
+			panic("No mapping iommu for ioapic %d\n", apic);
+
+		index = alloc_irte(iommu, irq, 1);
+		if (index < 0)
+			panic("Failed to allocate IRTE for ioapic %d\n", apic);
+
+		memset(&irte, 0, sizeof(irte));
+
+		irte.present = 1;
+		irte.dst_mode = INT_DEST_MODE;
+		irte.trigger_mode = trigger;
+		irte.dlvry_mode = INT_DELIVERY_MODE;
+		irte.vector = vector;
+		irte.dest_id = IRTE_DEST(destination);
+
+		modify_irte(irq, &irte);
+
+		ir_entry->index2 = (index >> 15) & 0x1;
+		ir_entry->zero = 0;
+		ir_entry->format = 1;
+		ir_entry->index = (index & 0x7fff);
+	} else
+#endif
+	{
+		entry->delivery_mode = INT_DELIVERY_MODE;
+		entry->dest_mode = INT_DEST_MODE;
+		entry->dest = destination;
 	}
+
+	entry->mask = 0;				/* enable IRQ */
+	entry->trigger = trigger;
+	entry->polarity = polarity;
+	entry->vector = vector;
+
+	/* Mask level triggered irqs.
+	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
+	 */
+	if (trigger)
+		entry->mask = 1;
+	return 0;
 }
 
 static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
@@ -870,24 +1023,15 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
 		    apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
 		    irq, trigger, polarity);
 
-	/*
-	 * add it to the IO-APIC irq-routing table:
-	 */
-	memset(&entry,0,sizeof(entry));
 
-	entry.delivery_mode = INT_DELIVERY_MODE;
-	entry.dest_mode = INT_DEST_MODE;
-	entry.dest = cpu_mask_to_apicid(mask);
-	entry.mask = 0;				/* enable IRQ */
-	entry.trigger = trigger;
-	entry.polarity = polarity;
-	entry.vector = cfg->vector;
-
-	/* Mask level triggered irqs.
-	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
-	 */
-	if (trigger)
-		entry.mask = 1;
+	if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
+			       cpu_mask_to_apicid(mask), trigger, polarity,
+			       cfg->vector)) {
+		printk("Failed to setup ioapic entry for ioapic  %d, pin %d\n",
+		       mp_ioapics[apic].mp_apicid, pin);
+		__clear_irq_vector(irq);
+		return;
+	}
 
 	ioapic_register_intr(irq, trigger);
 	if (irq < 16)
@@ -939,6 +1083,9 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 {
 	struct IO_APIC_route_entry entry;
 
+	if (intr_remapping_enabled)
+		return;
+
 	memset(&entry, 0, sizeof(entry));
 
 	/*
@@ -1085,6 +1232,7 @@ static __apicdebuginit void print_APIC_bitfield (int base)
 void __apicdebuginit print_local_APIC(void * dummy)
 {
 	unsigned int v, ver, maxlvt;
+	unsigned long icr;
 
 	if (apic_verbosity == APIC_QUIET)
 		return;
@@ -1092,7 +1240,7 @@ void __apicdebuginit print_local_APIC(void * dummy)
 	printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
 		smp_processor_id(), hard_smp_processor_id());
 	v = apic_read(APIC_ID);
-	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
+	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, read_apic_id());
 	v = apic_read(APIC_LVR);
 	printk(KERN_INFO "... APIC VERSION: %08x\n", v);
 	ver = GET_APIC_VERSION(v);
@@ -1128,10 +1276,9 @@ void __apicdebuginit print_local_APIC(void * dummy)
 	v = apic_read(APIC_ESR);
 	printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
 
-	v = apic_read(APIC_ICR);
-	printk(KERN_DEBUG "... APIC ICR: %08x\n", v);
-	v = apic_read(APIC_ICR2);
-	printk(KERN_DEBUG "... APIC ICR2: %08x\n", v);
+	icr = apic_icr_read();
+	printk(KERN_DEBUG "... APIC ICR: %08x\n", icr);
+	printk(KERN_DEBUG "... APIC ICR2: %08x\n", icr >> 32);
 
 	v = apic_read(APIC_LVTT);
 	printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
@@ -1286,7 +1433,7 @@ void disable_IO_APIC(void)
 		entry.dest_mode       = 0; /* Physical */
 		entry.delivery_mode   = dest_ExtINT; /* ExtInt */
 		entry.vector          = 0;
-		entry.dest          = GET_APIC_ID(read_apic_id());
+		entry.dest            = read_apic_id();
 
 		/*
 		 * Add it to the IO-APIC irq-routing table:
@@ -1392,6 +1539,147 @@ static int ioapic_retrigger_irq(unsigned int irq)
  */
 
 #ifdef CONFIG_SMP
+
+#ifdef CONFIG_INTR_REMAP
+static void ir_irq_migration(struct work_struct *work);
+
+static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
+
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For edge triggered, irq migration is a simple atomic update(of vector
+ * and cpu destination) of IRTE and flush the hardware cache.
+ *
+ * For level triggered, we need to modify the io-apic RTE aswell with the update
+ * vector information, along with modifying IRTE with vector and destination.
+ * So irq migration for level triggered is little  bit more complex compared to
+ * edge triggered migration. But the good news is, we use the same algorithm
+ * for level triggered migration as we have today, only difference being,
+ * we now initiate the irq migration from process context instead of the
+ * interrupt context.
+ *
+ * In future, when we do a directed EOI (combined with cpu EOI broadcast
+ * suppression) to the IO-APIC, level triggered irq migration will also be
+ * as simple as edge triggered migration and we can do the irq migration
+ * with a simple atomic update to IO-APIC RTE.
+ */
+static void migrate_ioapic_irq(int irq, cpumask_t mask)
+{
+	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_desc *desc = irq_desc + irq;
+	cpumask_t tmp, cleanup_mask;
+	struct irte irte;
+	int modify_ioapic_rte = desc->status & IRQ_LEVEL;
+	unsigned int dest;
+	unsigned long flags;
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		return;
+
+	if (get_irte(irq, &irte))
+		return;
+
+	if (assign_irq_vector(irq, mask))
+		return;
+
+	cpus_and(tmp, cfg->domain, mask);
+	dest = cpu_mask_to_apicid(tmp);
+
+	if (modify_ioapic_rte) {
+		spin_lock_irqsave(&ioapic_lock, flags);
+		__target_IO_APIC_irq(irq, dest, cfg->vector);
+		spin_unlock_irqrestore(&ioapic_lock, flags);
+	}
+
+	irte.vector = cfg->vector;
+	irte.dest_id = IRTE_DEST(dest);
+
+	/*
+	 * Modified the IRTE and flushes the Interrupt entry cache.
+	 */
+	modify_irte(irq, &irte);
+
+	if (cfg->move_in_progress) {
+		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+		cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+		send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		cfg->move_in_progress = 0;
+	}
+
+	irq_desc[irq].affinity = mask;
+}
+
+static int migrate_irq_remapped_level(int irq)
+{
+	int ret = -1;
+
+	mask_IO_APIC_irq(irq);
+
+	if (io_apic_level_ack_pending(irq)) {
+		/*
+	 	 * Interrupt in progress. Migrating irq now will change the
+		 * vector information in the IO-APIC RTE and that will confuse
+		 * the EOI broadcast performed by cpu.
+		 * So, delay the irq migration to the next instance.
+		 */
+		schedule_delayed_work(&ir_migration_work, 1);
+		goto unmask;
+	}
+
+	/* everthing is clear. we have right of way */
+	migrate_ioapic_irq(irq, irq_desc[irq].pending_mask);
+
+	ret = 0;
+	irq_desc[irq].status &= ~IRQ_MOVE_PENDING;
+	cpus_clear(irq_desc[irq].pending_mask);
+
+unmask:
+	unmask_IO_APIC_irq(irq);
+	return ret;
+}
+
+static void ir_irq_migration(struct work_struct *work)
+{
+	int irq;
+
+	for (irq = 0; irq < NR_IRQS; irq++) {
+		struct irq_desc *desc = irq_desc + irq;
+		if (desc->status & IRQ_MOVE_PENDING) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&desc->lock, flags);
+			if (!desc->chip->set_affinity ||
+			    !(desc->status & IRQ_MOVE_PENDING)) {
+				desc->status &= ~IRQ_MOVE_PENDING;
+				spin_unlock_irqrestore(&desc->lock, flags);
+				continue;
+			}
+
+			desc->chip->set_affinity(irq,
+					         irq_desc[irq].pending_mask);
+			spin_unlock_irqrestore(&desc->lock, flags);
+		}
+	}
+}
+
+/*
+ * Migrates the IRQ destination in the process context.
+ */
+static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+	if (irq_desc[irq].status & IRQ_LEVEL) {
+		irq_desc[irq].status |= IRQ_MOVE_PENDING;
+		irq_desc[irq].pending_mask = mask;
+		migrate_irq_remapped_level(irq);
+		return;
+	}
+
+	migrate_ioapic_irq(irq, mask);
+}
+#endif
+
 asmlinkage void smp_irq_move_cleanup_interrupt(void)
 {
 	unsigned vector, me;
@@ -1448,6 +1736,17 @@ static void irq_complete_move(unsigned int irq)
 #else
 static inline void irq_complete_move(unsigned int irq) {}
 #endif
+#ifdef CONFIG_INTR_REMAP
+static void ack_x2apic_level(unsigned int irq)
+{
+	ack_x2APIC_irq();
+}
+
+static void ack_x2apic_edge(unsigned int irq)
+{
+	ack_x2APIC_irq();
+}
+#endif
 
 static void ack_apic_edge(unsigned int irq)
 {
@@ -1522,6 +1821,21 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.retrigger	= ioapic_retrigger_irq,
 };
 
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip __read_mostly = {
+	.name 		= "IR-IO-APIC",
+	.startup 	= startup_ioapic_irq,
+	.mask	 	= mask_IO_APIC_irq,
+	.unmask	 	= unmask_IO_APIC_irq,
+	.ack 		= ack_x2apic_edge,
+	.eoi 		= ack_x2apic_level,
+#ifdef CONFIG_SMP
+	.set_affinity 	= set_ir_ioapic_affinity_irq,
+#endif
+	.retrigger	= ioapic_retrigger_irq,
+};
+#endif
+
 static inline void init_IO_APIC_traps(void)
 {
 	int irq;
@@ -1707,6 +2021,8 @@ static inline void __init check_timer(void)
 	 * 8259A.
 	 */
 	if (pin1 == -1) {
+		if (intr_remapping_enabled)
+			panic("BIOS bug: timer not connected to IO-APIC");
 		pin1 = pin2;
 		apic1 = apic2;
 		no_pin1 = 1;
@@ -1733,6 +2049,8 @@ static inline void __init check_timer(void)
 				clear_IO_APIC_pin(0, pin1);
 			goto out;
 		}
+		if (intr_remapping_enabled)
+			panic("timer doesn't work through Interrupt-remapped IO-APIC");
 		clear_IO_APIC_pin(apic1, pin1);
 		if (!no_pin1)
 			apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: "
@@ -1972,6 +2290,9 @@ void destroy_irq(unsigned int irq)
 
 	dynamic_irq_cleanup(irq);
 
+#ifdef CONFIG_INTR_REMAP
+	free_irte(irq);
+#endif
 	spin_lock_irqsave(&vector_lock, flags);
 	__clear_irq_vector(irq);
 	spin_unlock_irqrestore(&vector_lock, flags);
@@ -1990,11 +2311,42 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 
 	tmp = TARGET_CPUS;
 	err = assign_irq_vector(irq, tmp);
-	if (!err) {
-		cpus_and(tmp, cfg->domain, tmp);
-		dest = cpu_mask_to_apicid(tmp);
+	if (err)
+		return err;
+
+	cpus_and(tmp, cfg->domain, tmp);
+	dest = cpu_mask_to_apicid(tmp);
+
+#ifdef CONFIG_INTR_REMAP
+	if (irq_remapped(irq)) {
+		struct irte irte;
+		int ir_index;
+		u16 sub_handle;
+
+		ir_index = map_irq_to_irte_handle(irq, &sub_handle);
+		BUG_ON(ir_index == -1);
+
+		memset (&irte, 0, sizeof(irte));
+
+		irte.present = 1;
+		irte.dst_mode = INT_DEST_MODE;
+		irte.trigger_mode = 0; /* edge */
+		irte.dlvry_mode = INT_DELIVERY_MODE;
+		irte.vector = cfg->vector;
+		irte.dest_id = IRTE_DEST(dest);
+
+		modify_irte(irq, &irte);
 
 		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->data = sub_handle;
+		msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+				  MSI_ADDR_IR_SHV |
+				  MSI_ADDR_IR_INDEX1(ir_index) |
+				  MSI_ADDR_IR_INDEX2(ir_index);
+	} else
+#endif
+	{
+		msg->address_hi = MSI_ADDR_BASE_HI;
 		msg->address_lo =
 			MSI_ADDR_BASE_LO |
 			((INT_DEST_MODE == 0) ?
@@ -2044,6 +2396,55 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	write_msi_msg(irq, &msg);
 	irq_desc[irq].affinity = mask;
 }
+
+#ifdef CONFIG_INTR_REMAP
+/*
+ * Migrate the MSI irq to another cpumask. This migration is
+ * done in the process context using interrupt-remapping hardware.
+ */
+static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+{
+	struct irq_cfg *cfg = irq_cfg + irq;
+	unsigned int dest;
+	cpumask_t tmp, cleanup_mask;
+	struct irte irte;
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		return;
+
+	if (get_irte(irq, &irte))
+		return;
+
+	if (assign_irq_vector(irq, mask))
+		return;
+
+	cpus_and(tmp, cfg->domain, mask);
+	dest = cpu_mask_to_apicid(tmp);
+
+	irte.vector = cfg->vector;
+	irte.dest_id = IRTE_DEST(dest);
+
+	/*
+	 * atomically update the IRTE with the new destination and vector.
+	 */
+	modify_irte(irq, &irte);
+
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	if (cfg->move_in_progress) {
+		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+		cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+		send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		cfg->move_in_progress = 0;
+	}
+
+	irq_desc[irq].affinity = mask;
+}
+#endif
 #endif /* CONFIG_SMP */
 
 /*
@@ -2061,26 +2462,157 @@ static struct irq_chip msi_chip = {
 	.retrigger	= ioapic_retrigger_irq,
 };
 
-int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip msi_ir_chip = {
+	.name		= "IR-PCI-MSI",
+	.unmask		= unmask_msi_irq,
+	.mask		= mask_msi_irq,
+	.ack		= ack_x2apic_edge,
+#ifdef CONFIG_SMP
+	.set_affinity	= ir_set_msi_irq_affinity,
+#endif
+	.retrigger	= ioapic_retrigger_irq,
+};
+
+/*
+ * Map the PCI dev to the corresponding remapping hardware unit
+ * and allocate 'nvec' consecutive interrupt-remapping table entries
+ * in it.
+ */
+static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
+{
+	struct intel_iommu *iommu;
+	int index;
+
+	iommu = map_dev_to_ir(dev);
+	if (!iommu) {
+		printk(KERN_ERR
+		       "Unable to map PCI %s to iommu\n", pci_name(dev));
+		return -ENOENT;
+	}
+
+	index = alloc_irte(iommu, irq, nvec);
+	if (index < 0) {
+		printk(KERN_ERR
+		       "Unable to allocate %d IRTE for PCI %s\n", nvec,
+		        pci_name(dev));
+		return -ENOSPC;
+	}
+	return index;
+}
+#endif
+
+static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
 {
+	int ret;
 	struct msi_msg msg;
+
+	ret = msi_compose_msg(dev, irq, &msg);
+	if (ret < 0)
+		return ret;
+
+	set_irq_msi(irq, desc);
+	write_msi_msg(irq, &msg);
+
+#ifdef CONFIG_INTR_REMAP
+	if (irq_remapped(irq)) {
+		struct irq_desc *desc = irq_desc + irq;
+		/*
+		 * irq migration in process context
+		 */
+		desc->status |= IRQ_MOVE_PCNTXT;
+		set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
+	} else
+#endif
+		set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+
+	return 0;
+}
+
+int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+{
 	int irq, ret;
+
 	irq = create_irq();
 	if (irq < 0)
 		return irq;
 
-	ret = msi_compose_msg(dev, irq, &msg);
+#ifdef CONFIG_INTR_REMAP
+	if (!intr_remapping_enabled)
+		goto no_ir;
+
+	ret = msi_alloc_irte(dev, irq, 1);
+	if (ret < 0)
+		goto error;
+no_ir:
+#endif
+	ret = setup_msi_irq(dev, desc, irq);
 	if (ret < 0) {
 		destroy_irq(irq);
 		return ret;
 	}
+	return 0;
 
-	set_irq_msi(irq, desc);
-	write_msi_msg(irq, &msg);
+#ifdef CONFIG_INTR_REMAP
+error:
+	destroy_irq(irq);
+	return ret;
+#endif
+}
 
-	set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	int irq, ret, sub_handle;
+	struct msi_desc *desc;
+#ifdef CONFIG_INTR_REMAP
+	struct intel_iommu *iommu = 0;
+	int index = 0;
+#endif
 
+	sub_handle = 0;
+	list_for_each_entry(desc, &dev->msi_list, list) {
+		irq = create_irq();
+		if (irq < 0)
+			return irq;
+#ifdef CONFIG_INTR_REMAP
+		if (!intr_remapping_enabled)
+			goto no_ir;
+
+		if (!sub_handle) {
+			/*
+			 * allocate the consecutive block of IRTE's
+			 * for 'nvec'
+			 */
+			index = msi_alloc_irte(dev, irq, nvec);
+			if (index < 0) {
+				ret = index;
+				goto error;
+			}
+		} else {
+			iommu = map_dev_to_ir(dev);
+			if (!iommu) {
+				ret = -ENOENT;
+				goto error;
+			}
+			/*
+			 * setup the mapping between the irq and the IRTE
+			 * base index, the sub_handle pointing to the
+			 * appropriate interrupt remap table entry.
+			 */
+			set_irte_irq(irq, iommu, index, sub_handle);
+		}
+no_ir:
+#endif
+		ret = setup_msi_irq(dev, desc, irq);
+		if (ret < 0)
+			goto error;
+		sub_handle++;
+	}
 	return 0;
+
+error:
+	destroy_irq(irq);
+	return ret;
 }
 
 void arch_teardown_msi_irq(unsigned int irq)
@@ -2328,6 +2860,10 @@ void __init setup_ioapic_dest(void)
 				setup_IO_APIC_irq(ioapic, pin, irq,
 						  irq_trigger(irq_entry),
 						  irq_polarity(irq_entry));
+#ifdef CONFIG_INTR_REMAP
+			else if (intr_remapping_enabled)
+				set_ir_ioapic_affinity_irq(irq, TARGET_CPUS);
+#endif
 			else
 				set_ioapic_affinity_irq(irq, TARGET_CPUS);
 		}
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 6ae005ccaed..e362c6ab4d3 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -397,7 +397,9 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
        generic_bigsmp_probe();
 #endif
 
+#ifdef CONFIG_X86_32
 	setup_apic_routing();
+#endif
 	if (!num_processors)
 		printk(KERN_ERR "MPTABLE: no processors registered!\n");
 	return num_processors;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 94da4d52d79..5744789a78f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -373,8 +373,6 @@ struct pv_cpu_ops pv_cpu_ops = {
 
 struct pv_apic_ops pv_apic_ops = {
 #ifdef CONFIG_X86_LOCAL_APIC
-	.apic_write = native_apic_write,
-	.apic_read = native_apic_read,
 	.setup_boot_clock = setup_boot_APIC_clock,
 	.setup_secondary_clock = setup_secondary_APIC_clock,
 	.startup_ipi_hook = paravirt_nop,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b520dae02bf..792b87853a7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -731,6 +731,8 @@ void __init setup_arch(char **cmdline_p)
 	num_physpages = max_pfn;
 
 	check_efer();
+ 	if (cpu_has_x2apic)
+ 		check_x2apic();
 
 	/* How many end-of-memory variables you have, grandma! */
 	/* need this before calling reserve_initrd */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 332512767f4..626618bf2f8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -123,7 +123,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 
 static atomic_t init_deasserted;
 
-static int boot_cpu_logical_apicid;
 
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
@@ -165,6 +164,8 @@ static void unmap_cpu_to_node(int cpu)
 #endif
 
 #ifdef CONFIG_X86_32
+static int boot_cpu_logical_apicid;
+
 u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
 					{ [0 ... NR_CPUS-1] = BAD_APICID };
 
@@ -210,7 +211,7 @@ static void __cpuinit smp_callin(void)
 	/*
 	 * (This works even if the APIC is not enabled.)
 	 */
-	phys_id = GET_APIC_ID(read_apic_id());
+	phys_id = read_apic_id();
 	cpuid = smp_processor_id();
 	if (cpu_isset(cpuid, cpu_callin_map)) {
 		panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
@@ -546,8 +547,7 @@ static inline void __inquire_remote_apic(int apicid)
 			printk(KERN_CONT
 			       "a previous APIC delivery may have failed\n");
 
-		apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
-		apic_write(APIC_ICR, APIC_DM_REMRD | regs[i]);
+		apic_icr_write(APIC_DM_REMRD | regs[i], apicid);
 
 		timeout = 0;
 		do {
@@ -579,11 +579,9 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
 	int maxlvt;
 
 	/* Target chip */
-	apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid));
-
 	/* Boot on the stack */
 	/* Kick the second */
-	apic_write(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL);
+	apic_icr_write(APIC_DM_NMI | APIC_DEST_LOGICAL, logical_apicid);
 
 	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
@@ -636,13 +634,11 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 	/*
 	 * Turn INIT on target chip
 	 */
-	apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
 	/*
 	 * Send IPI
 	 */
-	apic_write(APIC_ICR,
-		   APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT);
+	apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
+		       phys_apicid);
 
 	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
@@ -652,10 +648,8 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 	pr_debug("Deasserting INIT.\n");
 
 	/* Target chip */
-	apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
 	/* Send IPI */
-	apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
+	apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
 
 	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
@@ -698,11 +692,10 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 		 */
 
 		/* Target chip */
-		apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
 		/* Boot on the stack */
 		/* Kick the second */
-		apic_write(APIC_ICR, APIC_DM_STARTUP | (start_eip >> 12));
+		apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12),
+			       phys_apicid);
 
 		/*
 		 * Give the other CPU some time to accept the IPI.
@@ -1136,10 +1129,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	 * Setup boot CPU information
 	 */
 	smp_store_cpu_info(0); /* Final full version of the data */
+#ifdef CONFIG_X86_32
 	boot_cpu_logical_apicid = logical_smp_processor_id();
+#endif
 	current_thread_info()->cpu = 0;  /* needed? */
 	set_cpu_sibling_map(0);
 
+#ifdef CONFIG_X86_64
+	enable_IR_x2apic();
+	setup_apic_routing();
+#endif
+
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
 		disable_smp();
@@ -1147,9 +1147,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	}
 
 	preempt_disable();
-	if (GET_APIC_ID(read_apic_id()) != boot_cpu_physical_apicid) {
+	if (read_apic_id() != boot_cpu_physical_apicid) {
 		panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
-		     GET_APIC_ID(read_apic_id()), boot_cpu_physical_apicid);
+		     read_apic_id(), boot_cpu_physical_apicid);
 		/* Or can we switch back to PIC here? */
 	}
 	preempt_enable();
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 0a1b1a9d922..45c27c4e2a6 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -904,8 +904,8 @@ static inline int __init activate_vmi(void)
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
-	para_fill(pv_apic_ops.apic_read, APICRead);
-	para_fill(pv_apic_ops.apic_write, APICWrite);
+       para_fill(apic_ops->read, APICRead);
+       para_fill(apic_ops->write, APICWrite);
 #endif
 
 	/*
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 0313a5eec41..756fc489652 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -55,6 +55,7 @@
 #include <linux/lguest_launcher.h>
 #include <linux/virtio_console.h>
 #include <linux/pm.h>
+#include <asm/apic.h>
 #include <asm/lguest.h>
 #include <asm/paravirt.h>
 #include <asm/param.h>
@@ -783,14 +784,44 @@ static void lguest_wbinvd(void)
  * code qualifies for Advanced.  It will also never interrupt anything.  It
  * does, however, allow us to get through the Linux boot code. */
 #ifdef CONFIG_X86_LOCAL_APIC
-static void lguest_apic_write(unsigned long reg, u32 v)
+static void lguest_apic_write(u32 reg, u32 v)
 {
 }
 
-static u32 lguest_apic_read(unsigned long reg)
+static u32 lguest_apic_read(u32 reg)
 {
 	return 0;
 }
+
+static u64 lguest_apic_icr_read(void)
+{
+	return 0;
+}
+
+static void lguest_apic_icr_write(u32 low, u32 id)
+{
+	/* Warn to see if there's any stray references */
+	WARN_ON(1);
+}
+
+static void lguest_apic_wait_icr_idle(void)
+{
+	return;
+}
+
+static u32 lguest_apic_safe_wait_icr_idle(void)
+{
+	return 0;
+}
+
+static struct apic_ops lguest_basic_apic_ops = {
+	.read = lguest_apic_read,
+	.write = lguest_apic_write,
+	.icr_read = lguest_apic_icr_read,
+	.icr_write = lguest_apic_icr_write,
+	.wait_icr_idle = lguest_apic_wait_icr_idle,
+	.safe_wait_icr_idle = lguest_apic_safe_wait_icr_idle,
+};
 #endif
 
 /* STOP!  Until an interrupt comes in. */
@@ -990,8 +1021,7 @@ __init void lguest_init(void)
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	/* apic read/write intercepts */
-	pv_apic_ops.apic_write = lguest_apic_write;
-	pv_apic_ops.apic_read = lguest_apic_read;
+	apic_ops = &lguest_basic_apic_ops;
 #endif
 
 	/* time operations */
diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c
index 59d77171455..b31f2800638 100644
--- a/arch/x86/mach-generic/bigsmp.c
+++ b/arch/x86/mach-generic/bigsmp.c
@@ -5,17 +5,16 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>
 #include <asm/apicdef.h>
 #include <linux/kernel.h>
-#include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/dmi.h>
-#include <asm/mach-bigsmp/mach_apic.h>
 #include <asm/mach-bigsmp/mach_apicdef.h>
+#include <linux/smp.h>
+#include <asm/mach-bigsmp/mach_apic.h>
 #include <asm/mach-bigsmp/mach_ipi.h>
 #include <asm/mach-default/mach_mpparse.h>
 
diff --git a/arch/x86/mach-generic/es7000.c b/arch/x86/mach-generic/es7000.c
index 4742626f08c..9b30547d746 100644
--- a/arch/x86/mach-generic/es7000.c
+++ b/arch/x86/mach-generic/es7000.c
@@ -4,16 +4,15 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>
 #include <asm/apicdef.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/smp.h>
 #include <linux/init.h>
 #include <asm/mach-es7000/mach_apicdef.h>
+#include <linux/smp.h>
 #include <asm/mach-es7000/mach_apic.h>
 #include <asm/mach-es7000/mach_ipi.h>
 #include <asm/mach-es7000/mach_mpparse.h>
diff --git a/arch/x86/mach-generic/numaq.c b/arch/x86/mach-generic/numaq.c
index 8091e68764c..95c07efff6b 100644
--- a/arch/x86/mach-generic/numaq.c
+++ b/arch/x86/mach-generic/numaq.c
@@ -4,7 +4,6 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <linux/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>
@@ -12,8 +11,9 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <asm/mach-numaq/mach_apic.h>
 #include <asm/mach-numaq/mach_apicdef.h>
+#include <linux/smp.h>
+#include <asm/mach-numaq/mach_apic.h>
 #include <asm/mach-numaq/mach_ipi.h>
 #include <asm/mach-numaq/mach_mpparse.h>
 #include <asm/mach-numaq/mach_wakecpu.h>
diff --git a/arch/x86/mach-generic/summit.c b/arch/x86/mach-generic/summit.c
index a97ea0f35b1..752edd96b1b 100644
--- a/arch/x86/mach-generic/summit.c
+++ b/arch/x86/mach-generic/summit.c
@@ -4,17 +4,16 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>
 #include <asm/apicdef.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/smp.h>
 #include <linux/init.h>
-#include <asm/mach-summit/mach_apic.h>
 #include <asm/mach-summit/mach_apicdef.h>
+#include <linux/smp.h>
+#include <asm/mach-summit/mach_apic.h>
 #include <asm/mach-summit/mach_ipi.h>
 #include <asm/mach-summit/mach_mpparse.h>
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 9ff6e3cbf08..8d28925ebed 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -36,6 +36,7 @@
 #include <xen/hvc-console.h>
 
 #include <asm/paravirt.h>
+#include <asm/apic.h>
 #include <asm/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -580,16 +581,47 @@ static void xen_io_delay(void)
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
-static u32 xen_apic_read(unsigned long reg)
+static u32 xen_apic_read(u32 reg)
 {
 	return 0;
 }
 
-static void xen_apic_write(unsigned long reg, u32 val)
+static void xen_apic_write(u32 reg, u32 val)
 {
 	/* Warn to see if there's any stray references */
 	WARN_ON(1);
 }
+
+static u64 xen_apic_icr_read(void)
+{
+	return 0;
+}
+
+static void xen_apic_icr_write(u32 low, u32 id)
+{
+	/* Warn to see if there's any stray references */
+	WARN_ON(1);
+}
+
+static void xen_apic_wait_icr_idle(void)
+{
+        return;
+}
+
+static u32 xen_safe_apic_wait_icr_idle(void)
+{
+        return 0;
+}
+
+static struct apic_ops xen_basic_apic_ops = {
+	.read = xen_apic_read,
+	.write = xen_apic_write,
+	.icr_read = xen_apic_icr_read,
+	.icr_write = xen_apic_icr_write,
+	.wait_icr_idle = xen_apic_wait_icr_idle,
+	.safe_wait_icr_idle = xen_safe_apic_wait_icr_idle,
+};
+
 #endif
 
 static void xen_flush_tlb(void)
@@ -1273,8 +1305,6 @@ static const struct pv_irq_ops xen_irq_ops __initdata = {
 
 static const struct pv_apic_ops xen_apic_ops __initdata = {
 #ifdef CONFIG_X86_LOCAL_APIC
-	.apic_write = xen_apic_write,
-	.apic_read = xen_apic_read,
 	.setup_boot_clock = paravirt_nop,
 	.setup_secondary_clock = paravirt_nop,
 	.startup_ipi_hook = paravirt_nop,
@@ -1677,6 +1707,13 @@ asmlinkage void __init xen_start_kernel(void)
 	pv_apic_ops = xen_apic_ops;
 	pv_mmu_ops = xen_mmu_ops;
 
+#ifdef CONFIG_X86_LOCAL_APIC
+	/*
+	 * set up the basic apic ops.
+	 */
+	apic_ops = &xen_basic_apic_ops;
+#endif
+
 	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
 		pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
 		pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;