Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:
	Documentation/feature-removal-schedule.txt
	drivers/scsi/fcoe/fcoe.c
	net/core/drop_monitor.c
	net/core/net-traces.c

10 files changed, 672 insertions, 604 deletions

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index f2870920f24..8c7c042ecad 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -14,6 +14,7 @@
  *	Mikael Pettersson	:	PM converted to driver model.
  */
 
+#include <linux/perf_counter.h>
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/acpi_pmtmr.h>
@@ -34,6 +35,7 @@
 #include <linux/smp.h>
 #include <linux/mm.h>
 
+#include <asm/perf_counter.h>
 #include <asm/pgalloc.h>
 #include <asm/atomic.h>
 #include <asm/mpspec.h>
@@ -98,6 +100,29 @@ early_param("lapic", parse_lapic);
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
 static int enabled_via_apicbase;
 
+/*
+ * Handle interrupt mode configuration register (IMCR).
+ * This register controls whether the interrupt signals
+ * that reach the BSP come from the master PIC or from the
+ * local APIC. Before entering Symmetric I/O Mode, either
+ * the BIOS or the operating system must switch out of
+ * PIC Mode by changing the IMCR.
+ */
+static inline void imcr_pic_to_apic(void)
+{
+	/* select IMCR register */
+	outb(0x70, 0x22);
+	/* NMI and 8259 INTR go through APIC */
+	outb(0x01, 0x23);
+}
+
+static inline void imcr_apic_to_pic(void)
+{
+	/* select IMCR register */
+	outb(0x70, 0x22);
+	/* NMI and 8259 INTR go directly to BSP */
+	outb(0x00, 0x23);
+}
 #endif
 
 #ifdef CONFIG_X86_64
@@ -111,13 +136,19 @@ static __init int setup_apicpmtimer(char *s)
 __setup("apicpmtimer", setup_apicpmtimer);
 #endif
 
+int x2apic_mode;
 #ifdef CONFIG_X86_X2APIC
-int x2apic;
 /* x2apic enabled before OS handover */
 static int x2apic_preenabled;
 static int disable_x2apic;
 static __init int setup_nox2apic(char *str)
 {
+	if (x2apic_enabled()) {
+		pr_warning("Bios already enabled x2apic, "
+			   "can't enforce nox2apic");
+		return 0;
+	}
+
 	disable_x2apic = 1;
 	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 	return 0;
@@ -209,6 +240,31 @@ static int modern_apic(void)
 	return lapic_get_version() >= 0x14;
 }
 
+/*
+ * bare function to substitute write operation
+ * and it's _that_ fast :)
+ */
+static void native_apic_write_dummy(u32 reg, u32 v)
+{
+	WARN_ON_ONCE((cpu_has_apic || !disable_apic));
+}
+
+static u32 native_apic_read_dummy(u32 reg)
+{
+	WARN_ON_ONCE((cpu_has_apic && !disable_apic));
+	return 0;
+}
+
+/*
+ * right after this call apic->write/read doesn't do anything
+ * note that there is no restore operation it works one way
+ */
+void apic_disable(void)
+{
+	apic->read = native_apic_read_dummy;
+	apic->write = native_apic_write_dummy;
+}
+
 void native_apic_wait_icr_idle(void)
 {
 	while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
@@ -348,7 +404,7 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 
 static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
 {
-	unsigned long reg = (lvt_off << 4) + APIC_EILVT0;
+	unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
 	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
 
 	apic_write(reg, v);
@@ -815,7 +871,7 @@ void clear_local_APIC(void)
 	u32 v;
 
 	/* APIC hasn't been mapped yet */
-	if (!x2apic && !apic_phys)
+	if (!x2apic_mode && !apic_phys)
 		return;
 
 	maxlvt = lapic_get_maxlvt();
@@ -843,7 +899,7 @@ void clear_local_APIC(void)
 	}
 
 	/* lets not touch this if we didn't frob it */
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
+#ifdef CONFIG_X86_THERMAL_VECTOR
 	if (maxlvt >= 5) {
 		v = apic_read(APIC_LVTTHMR);
 		apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
@@ -1133,6 +1189,7 @@ void __cpuinit setup_local_APIC(void)
 		apic_write(APIC_ESR, 0);
 	}
 #endif
+	perf_counters_lapic_init();
 
 	preempt_disable();
 
@@ -1287,7 +1344,7 @@ void check_x2apic(void)
 {
 	if (x2apic_enabled()) {
 		pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
-		x2apic_preenabled = x2apic = 1;
+		x2apic_preenabled = x2apic_mode = 1;
 	}
 }
 
@@ -1295,7 +1352,7 @@ void enable_x2apic(void)
 {
 	int msr, msr2;
 
-	if (!x2apic)
+	if (!x2apic_mode)
 		return;
 
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
@@ -1304,6 +1361,7 @@ void enable_x2apic(void)
 		wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
 	}
 }
+#endif /* CONFIG_X86_X2APIC */
 
 void __init enable_IR_x2apic(void)
 {
@@ -1312,32 +1370,21 @@ void __init enable_IR_x2apic(void)
 	unsigned long flags;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
-	if (!cpu_has_x2apic)
-		return;
-
-	if (!x2apic_preenabled && disable_x2apic) {
-		pr_info("Skipped enabling x2apic and Interrupt-remapping "
-			"because of nox2apic\n");
-		return;
+	ret = dmar_table_init();
+	if (ret) {
+		pr_debug("dmar_table_init() failed with %d:\n", ret);
+		goto ir_failed;
 	}
 
-	if (x2apic_preenabled && disable_x2apic)
-		panic("Bios already enabled x2apic, can't enforce nox2apic");
-
-	if (!x2apic_preenabled && skip_ioapic_setup) {
-		pr_info("Skipped enabling x2apic and Interrupt-remapping "
-			"because of skipping io-apic setup\n");
-		return;
+	if (!intr_remapping_supported()) {
+		pr_debug("intr-remapping not supported\n");
+		goto ir_failed;
 	}
 
-	ret = dmar_table_init();
-	if (ret) {
-		pr_info("dmar_table_init() failed with %d:\n", ret);
 
-		if (x2apic_preenabled)
-			panic("x2apic enabled by bios. But IR enabling failed");
-		else
-			pr_info("Not enabling x2apic,Intr-remapping\n");
+	if (!x2apic_preenabled && skip_ioapic_setup) {
+		pr_info("Skipped enabling intr-remap because of skipping "
+			"io-apic setup\n");
 		return;
 	}
 
@@ -1357,19 +1404,16 @@ void __init enable_IR_x2apic(void)
 	mask_IO_APIC_setup(ioapic_entries);
 	mask_8259A();
 
-	ret = enable_intr_remapping(EIM_32BIT_APIC_ID);
-
-	if (ret && x2apic_preenabled) {
-		local_irq_restore(flags);
-		panic("x2apic enabled by bios. But IR enabling failed");
-	}
-
+	ret = enable_intr_remapping(x2apic_supported());
 	if (ret)
 		goto end_restore;
 
-	if (!x2apic) {
-		x2apic = 1;
+	pr_info("Enabled Interrupt-remapping\n");
+
+	if (x2apic_supported() && !x2apic_mode) {
+		x2apic_mode = 1;
 		enable_x2apic();
+		pr_info("Enabled x2apic\n");
 	}
 
 end_restore:
@@ -1378,37 +1422,34 @@ end_restore:
 		 * IR enabling failed
 		 */
 		restore_IO_APIC_setup(ioapic_entries);
-	else
-		reinit_intr_remapped_IO_APIC(x2apic_preenabled, ioapic_entries);
 
 	unmask_8259A();
 	local_irq_restore(flags);
 
 end:
-	if (!ret) {
-		if (!x2apic_preenabled)
-			pr_info("Enabled x2apic and interrupt-remapping\n");
-		else
-			pr_info("Enabled Interrupt-remapping\n");
-	} else
-		pr_err("Failed to enable Interrupt-remapping and x2apic\n");
 	if (ioapic_entries)
 		free_ioapic_entries(ioapic_entries);
+
+	if (!ret)
+		return;
+
+ir_failed:
+	if (x2apic_preenabled)
+		panic("x2apic enabled by bios. But IR enabling failed");
+	else if (cpu_has_x2apic)
+		pr_info("Not enabling x2apic,Intr-remapping\n");
 #else
 	if (!cpu_has_x2apic)
 		return;
 
 	if (x2apic_preenabled)
 		panic("x2apic enabled prior OS handover,"
-		      " enable CONFIG_INTR_REMAP");
-
-	pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
-		" and x2apic\n");
+		      " enable CONFIG_X86_X2APIC, CONFIG_INTR_REMAP");
 #endif
 
 	return;
 }
-#endif /* CONFIG_X86_X2APIC */
+
 
 #ifdef CONFIG_X86_64
 /*
@@ -1425,7 +1466,6 @@ static int __init detect_init_APIC(void)
 	}
 
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-	boot_cpu_physical_apicid = 0;
 	return 0;
 }
 #else
@@ -1539,32 +1579,49 @@ void __init early_init_lapic_mapping(void)
  */
 void __init init_apic_mappings(void)
 {
-	if (x2apic) {
+	unsigned int new_apicid;
+
+	if (x2apic_mode) {
 		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
-	 * one for the IO-APIC.
-	 */
+	/* If no local APIC can be found return early */
 	if (!smp_found_config && detect_init_APIC()) {
-		apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
-		apic_phys = __pa(apic_phys);
-	} else
+		/* lets NOP'ify apic operations */
+		pr_info("APIC: disable apic facility\n");
+		apic_disable();
+	} else {
 		apic_phys = mp_lapic_addr;
 
-	set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
-	apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
-				APIC_BASE, apic_phys);
+		/*
+		 * acpi lapic path already maps that address in
+		 * acpi_register_lapic_address()
+		 */
+		if (!acpi_lapic)
+			set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+
+		apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
+					APIC_BASE, apic_phys);
+	}
 
 	/*
 	 * Fetch the APIC ID of the BSP in case we have a
 	 * default configuration (or the MP table is broken).
 	 */
-	if (boot_cpu_physical_apicid == -1U)
-		boot_cpu_physical_apicid = read_apic_id();
+	new_apicid = read_apic_id();
+	if (boot_cpu_physical_apicid != new_apicid) {
+		boot_cpu_physical_apicid = new_apicid;
+		/*
+		 * yeah -- we lie about apic_version
+		 * in case if apic was disabled via boot option
+		 * but it's not a problem for SMP compiled kernel
+		 * since smp_sanity_check is prepared for such a case
+		 * and disable smp mode
+		 */
+		apic_version[new_apicid] =
+			 GET_APIC_VERSION(apic_read(APIC_LVR));
+	}
 }
 
 /*
@@ -1733,8 +1790,7 @@ void __init connect_bsp_APIC(void)
 		 */
 		apic_printk(APIC_VERBOSE, "leaving PIC mode, "
 				"enabling APIC mode.\n");
-		outb(0x70, 0x22);
-		outb(0x01, 0x23);
+		imcr_pic_to_apic();
 	}
 #endif
 	if (apic->enable_apic_mode)
@@ -1762,8 +1818,7 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 		 */
 		apic_printk(APIC_VERBOSE, "disabling APIC mode, "
 				"entering PIC mode.\n");
-		outb(0x70, 0x22);
-		outb(0x00, 0x23);
+		imcr_apic_to_pic();
 		return;
 	}
 #endif
@@ -1962,17 +2017,17 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 	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);
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
+#ifdef CONFIG_X86_THERMAL_VECTOR
 	if (maxlvt >= 5)
 		apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
 #endif
 
 	local_irq_save(flags);
 	disable_local_APIC();
-#ifdef CONFIG_INTR_REMAP
+
 	if (intr_remapping_enabled)
 		disable_intr_remapping();
-#endif
+
 	local_irq_restore(flags);
 	return 0;
 }
@@ -1982,42 +2037,34 @@ static int lapic_resume(struct sys_device *dev)
 	unsigned int l, h;
 	unsigned long flags;
 	int maxlvt;
-
-#ifdef CONFIG_INTR_REMAP
-	int ret;
+	int ret = 0;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
 	if (!apic_pm_state.active)
 		return 0;
 
 	local_irq_save(flags);
-	if (x2apic) {
+	if (intr_remapping_enabled) {
 		ioapic_entries = alloc_ioapic_entries();
 		if (!ioapic_entries) {
 			WARN(1, "Alloc ioapic_entries in lapic resume failed.");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto restore;
 		}
 
 		ret = save_IO_APIC_setup(ioapic_entries);
 		if (ret) {
 			WARN(1, "Saving IO-APIC state failed: %d\n", ret);
 			free_ioapic_entries(ioapic_entries);
-			return ret;
+			goto restore;
 		}
 
 		mask_IO_APIC_setup(ioapic_entries);
 		mask_8259A();
-		enable_x2apic();
 	}
-#else
-	if (!apic_pm_state.active)
-		return 0;
 
-	local_irq_save(flags);
-	if (x2apic)
+	if (x2apic_mode)
 		enable_x2apic();
-#endif
-
 	else {
 		/*
 		 * Make sure the APICBASE points to the right address
@@ -2055,21 +2102,16 @@ static int lapic_resume(struct sys_device *dev)
 	apic_write(APIC_ESR, 0);
 	apic_read(APIC_ESR);
 
-#ifdef CONFIG_INTR_REMAP
-	if (intr_remapping_enabled)
-		reenable_intr_remapping(EIM_32BIT_APIC_ID);
-
-	if (x2apic) {
+	if (intr_remapping_enabled) {
+		reenable_intr_remapping(x2apic_mode);
 		unmask_8259A();
 		restore_IO_APIC_setup(ioapic_entries);
 		free_ioapic_entries(ioapic_entries);
 	}
-#endif
-
+restore:
 	local_irq_restore(flags);
 
-
-	return 0;
+	return ret;
 }
 
 /*
@@ -2117,31 +2159,14 @@ static void apic_pm_activate(void) { }
 #endif	/* CONFIG_PM */
 
 #ifdef CONFIG_X86_64
-/*
- * apic_is_clustered_box() -- Check if we can expect good TSC
- *
- * Thus far, the major user of this is IBM's Summit2 series:
- *
- * Clustered boxes may have unsynced TSC problems if they are
- * multi-chassis. Use available data to take a good guess.
- * If in doubt, go HPET.
- */
-__cpuinit int apic_is_clustered_box(void)
+
+static int __cpuinit apic_cluster_num(void)
 {
 	int i, clusters, zeros;
 	unsigned id;
 	u16 *bios_cpu_apicid;
 	DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
 
-	/*
-	 * there is not this kind of box with AMD CPU yet.
-	 * Some AMD box with quadcore cpu and 8 sockets apicid
-	 * will be [4, 0x23] or [8, 0x27] could be thought to
-	 * vsmp box still need checking...
-	 */
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
-		return 0;
-
 	bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
 
@@ -2177,18 +2202,67 @@ __cpuinit int apic_is_clustered_box(void)
 			++zeros;
 	}
 
-	/* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
-	 * not guaranteed to be synced between boards
-	 */
-	if (is_vsmp_box() && clusters > 1)
+	return clusters;
+}
+
+static int __cpuinitdata multi_checked;
+static int __cpuinitdata multi;
+
+static int __cpuinit set_multi(const struct dmi_system_id *d)
+{
+	if (multi)
+		return 0;
+	pr_info("APIC: %s detected, Multi Chassis\n", d->ident);
+	multi = 1;
+	return 0;
+}
+
+static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
+	{
+		.callback = set_multi,
+		.ident = "IBM System Summit2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Summit2"),
+		},
+	},
+	{}
+};
+
+static void __cpuinit dmi_check_multi(void)
+{
+	if (multi_checked)
+		return;
+
+	dmi_check_system(multi_dmi_table);
+	multi_checked = 1;
+}
+
+/*
+ * apic_is_clustered_box() -- Check if we can expect good TSC
+ *
+ * Thus far, the major user of this is IBM's Summit2 series:
+ * Clustered boxes may have unsynced TSC problems if they are
+ * multi-chassis.
+ * Use DMI to check them
+ */
+__cpuinit int apic_is_clustered_box(void)
+{
+	dmi_check_multi();
+	if (multi)
 		return 1;
 
+	if (!is_vsmp_box())
+		return 0;
+
 	/*
-	 * If clusters > 2, then should be multi-chassis.
-	 * May have to revisit this when multi-core + hyperthreaded CPUs come
-	 * out, but AFAIK this will work even for them.
+	 * ScaleMP vSMPowered boxes have one cluster per board and TSCs are
+	 * not guaranteed to be synced between boards
 	 */
-	return (clusters > 2);
+	if (apic_cluster_num() > 1)
+		return 1;
+
+	return 0;
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 306e5e88fb6..d0c99abc26c 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -161,7 +161,7 @@ static int flat_apic_id_registered(void)
 
 static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
 {
-	return hard_smp_processor_id() >> index_msb;
+	return initial_apic_id >> index_msb;
 }
 
 struct apic apic_flat =  {
@@ -235,7 +235,7 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	 * regardless of how many processors are present (x86_64 ES7000
 	 * is an example).
 	 */
-	if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
 		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
 		printk(KERN_DEBUG "system APIC only can use physical flat");
 		return 1;
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 1c11b819f24..69328ac8de9 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -145,7 +145,7 @@ es7000_rename_gsi(int ioapic, int gsi)
 	return gsi;
 }
 
-static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
 {
 	unsigned long vect = 0, psaival = 0;
 
@@ -254,7 +254,7 @@ static int parse_unisys_oem(char *oemptr)
 }
 
 #ifdef CONFIG_ACPI
-static int find_unisys_acpi_oem_table(unsigned long *oem_addr)
+static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
 {
 	struct acpi_table_header *header = NULL;
 	struct es7000_oem_table *table;
@@ -285,7 +285,7 @@ static int find_unisys_acpi_oem_table(unsigned long *oem_addr)
 	return 0;
 }
 
-static void unmap_unisys_acpi_oem_table(unsigned long oem_addr)
+static void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
 {
 	if (!oem_addr)
 		return;
@@ -306,7 +306,7 @@ static int es7000_check_dsdt(void)
 static int es7000_acpi_ret;
 
 /* Hook from generic ACPI tables.c */
-static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	unsigned long oem_addr = 0;
 	int check_dsdt;
@@ -717,7 +717,7 @@ struct apic apic_es7000_cluster = {
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
 };
 
-struct apic apic_es7000 = {
+struct apic __refdata apic_es7000 = {
 
 	.name				= "es7000",
 	.probe				= probe_es7000,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 30da617d18e..ef8d9290c7e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -59,6 +59,7 @@
 #include <asm/setup.h>
 #include <asm/irq_remapping.h>
 #include <asm/hpet.h>
+#include <asm/hw_irq.h>
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/uv_irq.h>
 
@@ -129,12 +130,9 @@ struct irq_pin_list {
 	struct irq_pin_list *next;
 };
 
-static struct irq_pin_list *get_one_free_irq_2_pin(int cpu)
+static struct irq_pin_list *get_one_free_irq_2_pin(int node)
 {
 	struct irq_pin_list *pin;
-	int node;
-
-	node = cpu_to_node(cpu);
 
 	pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
 
@@ -148,9 +146,6 @@ struct irq_cfg {
 	unsigned move_cleanup_count;
 	u8 vector;
 	u8 move_in_progress : 1;
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-	u8 move_desc_pending : 1;
-#endif
 };
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -182,16 +177,18 @@ int __init arch_early_irq_init(void)
 	struct irq_cfg *cfg;
 	struct irq_desc *desc;
 	int count;
+	int node;
 	int i;
 
 	cfg = irq_cfgx;
 	count = ARRAY_SIZE(irq_cfgx);
+	node= cpu_to_node(boot_cpu_id);
 
 	for (i = 0; i < count; i++) {
 		desc = irq_to_desc(i);
 		desc->chip_data = &cfg[i];
-		alloc_bootmem_cpumask_var(&cfg[i].domain);
-		alloc_bootmem_cpumask_var(&cfg[i].old_domain);
+		zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
+		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
 		if (i < NR_IRQS_LEGACY)
 			cpumask_setall(cfg[i].domain);
 	}
@@ -212,12 +209,9 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
 	return cfg;
 }
 
-static struct irq_cfg *get_one_free_irq_cfg(int cpu)
+static struct irq_cfg *get_one_free_irq_cfg(int node)
 {
 	struct irq_cfg *cfg;
-	int node;
-
-	node = cpu_to_node(cpu);
 
 	cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
 	if (cfg) {
@@ -238,13 +232,13 @@ static struct irq_cfg *get_one_free_irq_cfg(int cpu)
 	return cfg;
 }
 
-int arch_init_chip_data(struct irq_desc *desc, int cpu)
+int arch_init_chip_data(struct irq_desc *desc, int node)
 {
 	struct irq_cfg *cfg;
 
 	cfg = desc->chip_data;
 	if (!cfg) {
-		desc->chip_data = get_one_free_irq_cfg(cpu);
+		desc->chip_data = get_one_free_irq_cfg(node);
 		if (!desc->chip_data) {
 			printk(KERN_ERR "can not alloc irq_cfg\n");
 			BUG_ON(1);
@@ -254,10 +248,9 @@ int arch_init_chip_data(struct irq_desc *desc, int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-
+/* for move_irq_desc */
 static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
+init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
 {
 	struct irq_pin_list *old_entry, *head, *tail, *entry;
 
@@ -266,7 +259,7 @@ init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
 	if (!old_entry)
 		return;
 
-	entry = get_one_free_irq_2_pin(cpu);
+	entry = get_one_free_irq_2_pin(node);
 	if (!entry)
 		return;
 
@@ -276,7 +269,7 @@ init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
 	tail		= entry;
 	old_entry	= old_entry->next;
 	while (old_entry) {
-		entry = get_one_free_irq_2_pin(cpu);
+		entry = get_one_free_irq_2_pin(node);
 		if (!entry) {
 			entry = head;
 			while (entry) {
@@ -316,12 +309,12 @@ static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
 }
 
 void arch_init_copy_chip_data(struct irq_desc *old_desc,
-				 struct irq_desc *desc, int cpu)
+				 struct irq_desc *desc, int node)
 {
 	struct irq_cfg *cfg;
 	struct irq_cfg *old_cfg;
 
-	cfg = get_one_free_irq_cfg(cpu);
+	cfg = get_one_free_irq_cfg(node);
 
 	if (!cfg)
 		return;
@@ -332,7 +325,7 @@ void arch_init_copy_chip_data(struct irq_desc *old_desc,
 
 	memcpy(cfg, old_cfg, sizeof(struct irq_cfg));
 
-	init_copy_irq_2_pin(old_cfg, cfg, cpu);
+	init_copy_irq_2_pin(old_cfg, cfg, node);
 }
 
 static void free_irq_cfg(struct irq_cfg *old_cfg)
@@ -356,19 +349,7 @@ void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
 		old_desc->chip_data = NULL;
 	}
 }
-
-static void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg = desc->chip_data;
-
-	if (!cfg->move_in_progress) {
-		/* it means that domain is not changed */
-		if (!cpumask_intersects(desc->affinity, mask))
-			cfg->move_desc_pending = 1;
-	}
-}
-#endif
+/* end for move_irq_desc */
 
 #else
 static struct irq_cfg *irq_cfg(unsigned int irq)
@@ -378,13 +359,6 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
 
 #endif
 
-#ifndef CONFIG_NUMA_MIGRATE_IRQ_DESC
-static inline void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-}
-#endif
-
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -518,132 +492,18 @@ static void ioapic_mask_entry(int apic, int pin)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-#ifdef CONFIG_SMP
-static void send_cleanup_vector(struct irq_cfg *cfg)
-{
-	cpumask_var_t cleanup_mask;
-
-	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
-		unsigned int i;
-		cfg->move_cleanup_count = 0;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			cfg->move_cleanup_count++;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
-	} else {
-		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
-		cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
-		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
-		free_cpumask_var(cleanup_mask);
-	}
-	cfg->move_in_progress = 0;
-}
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-	u8 vector = cfg->vector;
-
-	entry = cfg->irq_2_pin;
-	for (;;) {
-		unsigned int reg;
-
-		if (!entry)
-			break;
-
-		apic = entry->apic;
-		pin = entry->pin;
-		/*
-		 * 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;
-		io_apic_modify(apic, 0x10 + pin*2, reg);
-		if (!entry->next)
-			break;
-		entry = entry->next;
-	}
-}
-
-static int
-assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
-
-/*
- * Either sets desc->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
- * leaves desc->affinity untouched.
- */
-static unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg;
-	unsigned int irq;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return BAD_APICID;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-	if (assign_irq_vector(irq, cfg, mask))
-		return BAD_APICID;
-
-	/* check that before desc->addinity get updated */
-	set_extra_move_desc(desc, mask);
-
-	cpumask_copy(desc->affinity, mask);
-
-	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
-}
-
-static void
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int dest;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	dest = set_desc_affinity(desc, mask);
-	if (dest != BAD_APICID) {
-		/* Only the high 8 bits are valid. */
-		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, cfg);
-	}
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	set_ioapic_affinity_irq_desc(desc, mask);
-}
-#endif /* CONFIG_SMP */
-
 /*
  * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
+static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list *entry;
 
 	entry = cfg->irq_2_pin;
 	if (!entry) {
-		entry = get_one_free_irq_2_pin(cpu);
+		entry = get_one_free_irq_2_pin(node);
 		if (!entry) {
 			printk(KERN_ERR "can not alloc irq_2_pin to add %d - %d\n",
 					apic, pin);
@@ -663,7 +523,7 @@ static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
 		entry = entry->next;
 	}
 
-	entry->next = get_one_free_irq_2_pin(cpu);
+	entry->next = get_one_free_irq_2_pin(node);
 	entry = entry->next;
 	entry->apic = apic;
 	entry->pin = pin;
@@ -672,7 +532,7 @@ static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
 /*
  * Reroute an IRQ to a different pin.
  */
-static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
+static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
 				      int oldapic, int oldpin,
 				      int newapic, int newpin)
 {
@@ -692,7 +552,7 @@ static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
 
 	/* why? call replace before add? */
 	if (!replaced)
-		add_pin_to_irq_cpu(cfg, cpu, newapic, newpin);
+		add_pin_to_irq_node(cfg, node, newapic, newpin);
 }
 
 static inline void io_apic_modify_irq(struct irq_cfg *cfg,
@@ -850,7 +710,6 @@ static int __init ioapic_pirq_setup(char *str)
 __setup("pirq=", ioapic_pirq_setup);
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_INTR_REMAP
 struct IO_APIC_route_entry **alloc_ioapic_entries(void)
 {
 	int apic;
@@ -948,20 +807,6 @@ int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries)
 	return 0;
 }
 
-void reinit_intr_remapped_IO_APIC(int intr_remapping,
-	struct IO_APIC_route_entry **ioapic_entries)
-
-{
-	/*
-	 * 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(ioapic_entries);
-}
-
 void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
 {
 	int apic;
@@ -971,7 +816,6 @@ void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
 
 	kfree(ioapic_entries);
 }
-#endif
 
 /*
  * Find the IRQ entry number of a certain pin.
@@ -1032,54 +876,6 @@ static int __init find_isa_irq_apic(int irq, int type)
 	return -1;
 }
 
-/*
- * Find a specific PCI IRQ entry.
- * Not an __init, possibly needed by modules
- */
-static int pin_2_irq(int idx, int apic, int pin);
-
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
-{
-	int apic, i, best_guess = -1;
-
-	apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
-		bus, slot, pin);
-	if (test_bit(bus, mp_bus_not_pci)) {
-		apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
-		return -1;
-	}
-	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].srcbus;
-
-		for (apic = 0; apic < nr_ioapics; apic++)
-			if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
-			    mp_irqs[i].dstapic == MP_APIC_ALL)
-				break;
-
-		if (!test_bit(lbus, mp_bus_not_pci) &&
-		    !mp_irqs[i].irqtype &&
-		    (bus == lbus) &&
-		    (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
-			int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
-
-			if (!(apic || IO_APIC_IRQ(irq)))
-				continue;
-
-			if (pin == (mp_irqs[i].srcbusirq & 3))
-				return irq;
-			/*
-			 * Use the first all-but-pin matching entry as a
-			 * best-guess fuzzy result for broken mptables.
-			 */
-			if (best_guess < 0)
-				best_guess = irq;
-		}
-	}
-	return best_guess;
-}
-
-EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
 /*
  * EISA Edge/Level control register, ELCR
@@ -1298,6 +1094,64 @@ static int pin_2_irq(int idx, int apic, int pin)
 	return irq;
 }
 
+/*
+ * Find a specific PCI IRQ entry.
+ * Not an __init, possibly needed by modules
+ */
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
+				struct io_apic_irq_attr *irq_attr)
+{
+	int apic, i, best_guess = -1;
+
+	apic_printk(APIC_DEBUG,
+		    "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
+		    bus, slot, pin);
+	if (test_bit(bus, mp_bus_not_pci)) {
+		apic_printk(APIC_VERBOSE,
+			    "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
+		return -1;
+	}
+	for (i = 0; i < mp_irq_entries; i++) {
+		int lbus = mp_irqs[i].srcbus;
+
+		for (apic = 0; apic < nr_ioapics; apic++)
+			if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+			    mp_irqs[i].dstapic == MP_APIC_ALL)
+				break;
+
+		if (!test_bit(lbus, mp_bus_not_pci) &&
+		    !mp_irqs[i].irqtype &&
+		    (bus == lbus) &&
+		    (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+			int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
+
+			if (!(apic || IO_APIC_IRQ(irq)))
+				continue;
+
+			if (pin == (mp_irqs[i].srcbusirq & 3)) {
+				set_io_apic_irq_attr(irq_attr, apic,
+						     mp_irqs[i].dstirq,
+						     irq_trigger(i),
+						     irq_polarity(i));
+				return irq;
+			}
+			/*
+			 * Use the first all-but-pin matching entry as a
+			 * best-guess fuzzy result for broken mptables.
+			 */
+			if (best_guess < 0) {
+				set_io_apic_irq_attr(irq_attr, apic,
+						     mp_irqs[i].dstirq,
+						     irq_trigger(i),
+						     irq_polarity(i));
+				best_guess = irq;
+			}
+		}
+	}
+	return best_guess;
+}
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+
 void lock_vector_lock(void)
 {
 	/* Used to the online set of cpus does not change
@@ -1628,58 +1482,70 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
 	ioapic_write_entry(apic_id, pin, entry);
 }
 
+static struct {
+	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+} mp_ioapic_routing[MAX_IO_APICS];
+
 static void __init setup_IO_APIC_irqs(void)
 {
-	int apic_id, pin, idx, irq;
+	int apic_id = 0, pin, idx, irq;
 	int notcon = 0;
 	struct irq_desc *desc;
 	struct irq_cfg *cfg;
-	int cpu = boot_cpu_id;
+	int node = cpu_to_node(boot_cpu_id);
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
-	for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
-		for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
-
-			idx = find_irq_entry(apic_id, pin, mp_INT);
-			if (idx == -1) {
-				if (!notcon) {
-					notcon = 1;
-					apic_printk(APIC_VERBOSE,
-						KERN_DEBUG " %d-%d",
-						mp_ioapics[apic_id].apicid, pin);
-				} else
-					apic_printk(APIC_VERBOSE, " %d-%d",
-						mp_ioapics[apic_id].apicid, pin);
-				continue;
-			}
-			if (notcon) {
-				apic_printk(APIC_VERBOSE,
-					" (apicid-pin) not connected\n");
-				notcon = 0;
-			}
+#ifdef CONFIG_ACPI
+	if (!acpi_disabled && acpi_ioapic) {
+		apic_id = mp_find_ioapic(0);
+		if (apic_id < 0)
+			apic_id = 0;
+	}
+#endif
 
-			irq = pin_2_irq(idx, apic_id, pin);
+	for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
+		idx = find_irq_entry(apic_id, pin, mp_INT);
+		if (idx == -1) {
+			if (!notcon) {
+				notcon = 1;
+				apic_printk(APIC_VERBOSE,
+					KERN_DEBUG " %d-%d",
+					mp_ioapics[apic_id].apicid, pin);
+			} else
+				apic_printk(APIC_VERBOSE, " %d-%d",
+					mp_ioapics[apic_id].apicid, pin);
+			continue;
+		}
+		if (notcon) {
+			apic_printk(APIC_VERBOSE,
+				" (apicid-pin) not connected\n");
+			notcon = 0;
+		}
 
-			/*
-			 * Skip the timer IRQ if there's a quirk handler
-			 * installed and if it returns 1:
-			 */
-			if (apic->multi_timer_check &&
-					apic->multi_timer_check(apic_id, irq))
-				continue;
+		irq = pin_2_irq(idx, apic_id, pin);
 
-			desc = irq_to_desc_alloc_cpu(irq, cpu);
-			if (!desc) {
-				printk(KERN_INFO "can not get irq_desc for %d\n", irq);
-				continue;
-			}
-			cfg = desc->chip_data;
-			add_pin_to_irq_cpu(cfg, cpu, apic_id, pin);
+		/*
+		 * Skip the timer IRQ if there's a quirk handler
+		 * installed and if it returns 1:
+		 */
+		if (apic->multi_timer_check &&
+				apic->multi_timer_check(apic_id, irq))
+			continue;
 
-			setup_IO_APIC_irq(apic_id, pin, irq, desc,
-					irq_trigger(idx), irq_polarity(idx));
+		desc = irq_to_desc_alloc_node(irq, node);
+		if (!desc) {
+			printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+			continue;
 		}
+		cfg = desc->chip_data;
+		add_pin_to_irq_node(cfg, node, apic_id, pin);
+		/*
+		 * don't mark it in pin_programmed, so later acpi could
+		 * set it correctly when irq < 16
+		 */
+		setup_IO_APIC_irq(apic_id, pin, irq, desc,
+				irq_trigger(idx), irq_polarity(idx));
 	}
 
 	if (notcon)
@@ -1869,7 +1735,7 @@ __apicdebuginit(void) print_APIC_bitfield(int base)
 
 __apicdebuginit(void) print_local_APIC(void *dummy)
 {
-	unsigned int v, ver, maxlvt;
+	unsigned int i, v, ver, maxlvt;
 	u64 icr;
 
 	if (apic_verbosity == APIC_QUIET)
@@ -1957,6 +1823,18 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
 	printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
 	v = apic_read(APIC_TDCR);
 	printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
+
+	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+		v = apic_read(APIC_EFEAT);
+		maxlvt = (v >> 16) & 0xff;
+		printk(KERN_DEBUG "... APIC EFEAT: %08x\n", v);
+		v = apic_read(APIC_ECTRL);
+		printk(KERN_DEBUG "... APIC ECTRL: %08x\n", v);
+		for (i = 0; i < maxlvt; i++) {
+			v = apic_read(APIC_EILVTn(i));
+			printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v);
+		}
+	}
 	printk("\n");
 }
 
@@ -2005,6 +1883,11 @@ __apicdebuginit(void) print_PIC(void)
 __apicdebuginit(int) print_all_ICs(void)
 {
 	print_PIC();
+
+	/* don't print out if apic is not there */
+	if (!cpu_has_apic || disable_apic)
+		return 0;
+
 	print_all_local_APICs();
 	print_IO_APIC();
 
@@ -2360,6 +2243,118 @@ static int ioapic_retrigger_irq(unsigned int irq)
  */
 
 #ifdef CONFIG_SMP
+static void send_cleanup_vector(struct irq_cfg *cfg)
+{
+	cpumask_var_t cleanup_mask;
+
+	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+		unsigned int i;
+		cfg->move_cleanup_count = 0;
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			cfg->move_cleanup_count++;
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
+	} else {
+		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+		cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
+		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		free_cpumask_var(cleanup_mask);
+	}
+	cfg->move_in_progress = 0;
+}
+
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
+{
+	int apic, pin;
+	struct irq_pin_list *entry;
+	u8 vector = cfg->vector;
+
+	entry = cfg->irq_2_pin;
+	for (;;) {
+		unsigned int reg;
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		/*
+		 * 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;
+		io_apic_modify(apic, 0x10 + pin*2, reg);
+		if (!entry->next)
+			break;
+		entry = entry->next;
+	}
+}
+
+static int
+assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
+
+/*
+ * Either sets desc->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * leaves desc->affinity untouched.
+ */
+static unsigned int
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+{
+	struct irq_cfg *cfg;
+	unsigned int irq;
+
+	if (!cpumask_intersects(mask, cpu_online_mask))
+		return BAD_APICID;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+	if (assign_irq_vector(irq, cfg, mask))
+		return BAD_APICID;
+
+	cpumask_copy(desc->affinity, mask);
+
+	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+}
+
+static int
+set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int dest;
+	unsigned int irq;
+	int ret = -1;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	dest = set_desc_affinity(desc, mask);
+	if (dest != BAD_APICID) {
+		/* Only the high 8 bits are valid. */
+		dest = SET_APIC_LOGICAL_ID(dest);
+		__target_IO_APIC_irq(irq, dest, cfg);
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+
+	return ret;
+}
+
+static int
+set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+
+	return set_ioapic_affinity_irq_desc(desc, mask);
+}
 
 #ifdef CONFIG_INTR_REMAP
 
@@ -2374,26 +2369,25 @@ static int ioapic_retrigger_irq(unsigned int irq)
  * Real vector that is used for interrupting cpu will be coming from
  * the interrupt-remapping table entry.
  */
-static void
+static int
 migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 {
 	struct irq_cfg *cfg;
 	struct irte irte;
 	unsigned int dest;
 	unsigned int irq;
+	int ret = -1;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
-		return;
+		return ret;
 
 	irq = desc->irq;
 	if (get_irte(irq, &irte))
-		return;
+		return ret;
 
 	cfg = desc->chip_data;
 	if (assign_irq_vector(irq, cfg, mask))
-		return;
-
-	set_extra_move_desc(desc, mask);
+		return ret;
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
 
@@ -2409,27 +2403,30 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 		send_cleanup_vector(cfg);
 
 	cpumask_copy(desc->affinity, mask);
+
+	return 0;
 }
 
 /*
  * Migrates the IRQ destination in the process context.
  */
-static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
 					    const struct cpumask *mask)
 {
-	migrate_ioapic_irq_desc(desc, mask);
+	return migrate_ioapic_irq_desc(desc, mask);
 }
-static void set_ir_ioapic_affinity_irq(unsigned int irq,
+static int set_ir_ioapic_affinity_irq(unsigned int irq,
 				       const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	set_ir_ioapic_affinity_irq_desc(desc, mask);
+	return set_ir_ioapic_affinity_irq_desc(desc, mask);
 }
 #else
-static inline void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
 						   const struct cpumask *mask)
 {
+	return 0;
 }
 #endif
 
@@ -2491,86 +2488,19 @@ static void irq_complete_move(struct irq_desc **descp)
 	struct irq_cfg *cfg = desc->chip_data;
 	unsigned vector, me;
 
-	if (likely(!cfg->move_in_progress)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-		if (likely(!cfg->move_desc_pending))
-			return;
-
-		/* domain has not changed, but affinity did */
-		me = smp_processor_id();
-		if (cpumask_test_cpu(me, desc->affinity)) {
-			*descp = desc = move_irq_desc(desc, me);
-			/* get the new one */
-			cfg = desc->chip_data;
-			cfg->move_desc_pending = 0;
-		}
-#endif
+	if (likely(!cfg->move_in_progress))
 		return;
-	}
 
 	vector = ~get_irq_regs()->orig_ax;
 	me = smp_processor_id();
 
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-		*descp = desc = move_irq_desc(desc, me);
-		/* get the new one */
-		cfg = desc->chip_data;
-#endif
+	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
 		send_cleanup_vector(cfg);
-	}
 }
 #else
 static inline void irq_complete_move(struct irq_desc **descp) {}
 #endif
 
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-
-	entry = cfg->irq_2_pin;
-	for (;;) {
-
-		if (!entry)
-			break;
-
-		apic = entry->apic;
-		pin = entry->pin;
-		io_apic_eoi(apic, pin);
-		entry = entry->next;
-	}
-}
-
-static void
-eoi_ioapic_irq(struct irq_desc *desc)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	__eoi_ioapic_irq(irq, cfg);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-#ifdef CONFIG_X86_X2APIC
-static void ack_x2apic_level(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	ack_x2APIC_irq();
-	eoi_ioapic_irq(desc);
-}
-
-static void ack_x2apic_edge(unsigned int irq)
-{
-	ack_x2APIC_irq();
-}
-#endif
-
 static void ack_apic_edge(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -2634,9 +2564,6 @@ static void ack_apic_level(unsigned int irq)
 	 */
 	ack_APIC_irq();
 
-	if (irq_remapped(irq))
-		eoi_ioapic_irq(desc);
-
 	/* Now we can move and renable the irq */
 	if (unlikely(do_unmask_irq)) {
 		/* Only migrate the irq if the ack has been received.
@@ -2683,22 +2610,50 @@ static void ack_apic_level(unsigned int irq)
 }
 
 #ifdef CONFIG_INTR_REMAP
+static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+{
+	int apic, pin;
+	struct irq_pin_list *entry;
+
+	entry = cfg->irq_2_pin;
+	for (;;) {
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		io_apic_eoi(apic, pin);
+		entry = entry->next;
+	}
+}
+
+static void
+eoi_ioapic_irq(struct irq_desc *desc)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int irq;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	__eoi_ioapic_irq(irq, cfg);
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
 static void ir_ack_apic_edge(unsigned int irq)
 {
-#ifdef CONFIG_X86_X2APIC
-       if (x2apic_enabled())
-               return ack_x2apic_edge(irq);
-#endif
-       return ack_apic_edge(irq);
+	ack_APIC_irq();
 }
 
 static void ir_ack_apic_level(unsigned int irq)
 {
-#ifdef CONFIG_X86_X2APIC
-       if (x2apic_enabled())
-               return ack_x2apic_level(irq);
-#endif
-       return ack_apic_level(irq);
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	ack_APIC_irq();
+	eoi_ioapic_irq(desc);
 }
 #endif /* CONFIG_INTR_REMAP */
 
@@ -2903,7 +2858,7 @@ static inline void __init check_timer(void)
 {
 	struct irq_desc *desc = irq_to_desc(0);
 	struct irq_cfg *cfg = desc->chip_data;
-	int cpu = boot_cpu_id;
+	int node = cpu_to_node(boot_cpu_id);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
 	int no_pin1 = 0;
@@ -2969,7 +2924,7 @@ static inline void __init check_timer(void)
 		 * Ok, does IRQ0 through the IOAPIC work?
 		 */
 		if (no_pin1) {
-			add_pin_to_irq_cpu(cfg, cpu, apic1, pin1);
+			add_pin_to_irq_node(cfg, node, apic1, pin1);
 			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
 		} else {
 			/* for edge trigger, setup_IO_APIC_irq already
@@ -3006,7 +2961,7 @@ static inline void __init check_timer(void)
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		replace_pin_at_irq_cpu(cfg, cpu, apic1, pin1, apic2, pin2);
+		replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
@@ -3218,14 +3173,13 @@ static int nr_irqs_gsi = NR_IRQS_LEGACY;
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int irq_want)
+unsigned int create_irq_nr(unsigned int irq_want, int node)
 {
 	/* Allocate an unused irq */
 	unsigned int irq;
 	unsigned int new;
 	unsigned long flags;
 	struct irq_cfg *cfg_new = NULL;
-	int cpu = boot_cpu_id;
 	struct irq_desc *desc_new = NULL;
 
 	irq = 0;
@@ -3234,7 +3188,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 	spin_lock_irqsave(&vector_lock, flags);
 	for (new = irq_want; new < nr_irqs; new++) {
-		desc_new = irq_to_desc_alloc_cpu(new, cpu);
+		desc_new = irq_to_desc_alloc_node(new, node);
 		if (!desc_new) {
 			printk(KERN_INFO "can not get irq_desc for %d\n", new);
 			continue;
@@ -3243,6 +3197,9 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 		if (cfg_new->vector != 0)
 			continue;
+
+		desc_new = move_irq_desc(desc_new, node);
+
 		if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
 			irq = new;
 		break;
@@ -3260,11 +3217,12 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 int create_irq(void)
 {
+	int node = cpu_to_node(boot_cpu_id);
 	unsigned int irq_want;
 	int irq;
 
 	irq_want = nr_irqs_gsi;
-	irq = create_irq_nr(irq_want);
+	irq = create_irq_nr(irq_want, node);
 
 	if (irq == 0)
 		irq = -1;
@@ -3366,7 +3324,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 }
 
 #ifdef CONFIG_SMP
-static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3375,7 +3333,7 @@ static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3387,13 +3345,15 @@ static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg_desc(desc, &msg);
+
+	return 0;
 }
 #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
+static int
 ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -3402,11 +3362,11 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	struct irte irte;
 
 	if (get_irte(irq, &irte))
-		return;
+		return -1;
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	irte.vector = cfg->vector;
 	irte.dest_id = IRTE_DEST(dest);
@@ -3423,6 +3383,8 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	 */
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
+
+	return 0;
 }
 
 #endif
@@ -3518,15 +3480,17 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	unsigned int irq_want;
 	struct intel_iommu *iommu = NULL;
 	int index = 0;
+	int node;
 
 	/* x86 doesn't support multiple MSI yet */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
+	node = dev_to_node(&dev->dev);
 	irq_want = nr_irqs_gsi;
 	sub_handle = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = create_irq_nr(irq_want);
+		irq = create_irq_nr(irq_want, node);
 		if (irq == 0)
 			return -1;
 		irq_want = irq + 1;
@@ -3576,7 +3540,7 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 #if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
 #ifdef CONFIG_SMP
-static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3585,7 +3549,7 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3597,6 +3561,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	dmar_msi_write(irq, &msg);
+
+	return 0;
 }
 
 #endif /* CONFIG_SMP */
@@ -3630,7 +3596,7 @@ int arch_setup_dmar_msi(unsigned int irq)
 #ifdef CONFIG_HPET_TIMER
 
 #ifdef CONFIG_SMP
-static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3639,7 +3605,7 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3651,6 +3617,8 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	hpet_msi_write(irq, &msg);
+
+	return 0;
 }
 
 #endif /* CONFIG_SMP */
@@ -3707,7 +3675,7 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 	write_ht_irq_msg(irq, &msg);
 }
 
-static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3715,11 +3683,13 @@ static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
 	target_ht_irq(irq, dest, cfg->vector);
+
+	return 0;
 }
 
 #endif
@@ -3794,6 +3764,8 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 	unsigned long flags;
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
 	cfg = irq_cfg(irq);
 
 	err = assign_irq_vector(irq, cfg, eligible_cpu);
@@ -3807,15 +3779,13 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-	BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
-	entry->vector = cfg->vector;
-	entry->delivery_mode = apic->irq_delivery_mode;
-	entry->dest_mode = apic->irq_dest_mode;
-	entry->polarity = 0;
-	entry->trigger = 0;
-	entry->mask = 0;
-	entry->dest = apic->cpu_mask_to_apicid(eligible_cpu);
+	entry->vector		= cfg->vector;
+	entry->delivery_mode	= apic->irq_delivery_mode;
+	entry->dest_mode	= apic->irq_dest_mode;
+	entry->polarity		= 0;
+	entry->trigger		= 0;
+	entry->mask		= 0;
+	entry->dest		= apic->cpu_mask_to_apicid(eligible_cpu);
 
 	mmr_pnode = uv_blade_to_pnode(mmr_blade);
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
@@ -3833,10 +3803,10 @@ void arch_disable_uv_irq(int mmr_blade, unsigned long mmr_offset)
 	struct uv_IO_APIC_route_entry *entry;
 	int mmr_pnode;
 
+	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-	BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
 	entry->mask = 1;
 
 	mmr_pnode = uv_blade_to_pnode(mmr_blade);
@@ -3900,6 +3870,71 @@ int __init arch_probe_nr_irqs(void)
 }
 #endif
 
+static int __io_apic_set_pci_routing(struct device *dev, int irq,
+				struct io_apic_irq_attr *irq_attr)
+{
+	struct irq_desc *desc;
+	struct irq_cfg *cfg;
+	int node;
+	int ioapic, pin;
+	int trigger, polarity;
+
+	ioapic = irq_attr->ioapic;
+	if (!IO_APIC_IRQ(irq)) {
+		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
+			ioapic);
+		return -EINVAL;
+	}
+
+	if (dev)
+		node = dev_to_node(dev);
+	else
+		node = cpu_to_node(boot_cpu_id);
+
+	desc = irq_to_desc_alloc_node(irq, node);
+	if (!desc) {
+		printk(KERN_INFO "can not get irq_desc %d\n", irq);
+		return 0;
+	}
+
+	pin = irq_attr->ioapic_pin;
+	trigger = irq_attr->trigger;
+	polarity = irq_attr->polarity;
+
+	/*
+	 * IRQs < 16 are already in the irq_2_pin[] map
+	 */
+	if (irq >= NR_IRQS_LEGACY) {
+		cfg = desc->chip_data;
+		add_pin_to_irq_node(cfg, node, ioapic, pin);
+	}
+
+	setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+
+	return 0;
+}
+
+int io_apic_set_pci_routing(struct device *dev, int irq,
+				struct io_apic_irq_attr *irq_attr)
+{
+	int ioapic, pin;
+	/*
+	 * Avoid pin reprogramming.  PRTs typically include entries
+	 * with redundant pin->gsi mappings (but unique PCI devices);
+	 * we only program the IOAPIC on the first.
+	 */
+	ioapic = irq_attr->ioapic;
+	pin = irq_attr->ioapic_pin;
+	if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
+		pr_debug("Pin %d-%d already programmed\n",
+			 mp_ioapics[ioapic].apicid, pin);
+		return 0;
+	}
+	set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
+
+	return __io_apic_set_pci_routing(dev, irq, irq_attr);
+}
+
 /* --------------------------------------------------------------------------
                           ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
@@ -3980,6 +4015,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
 
 	return apic_id;
 }
+#endif
 
 int __init io_apic_get_version(int ioapic)
 {
@@ -3992,39 +4028,6 @@ int __init io_apic_get_version(int ioapic)
 
 	return reg_01.bits.version;
 }
-#endif
-
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
-{
-	struct irq_desc *desc;
-	struct irq_cfg *cfg;
-	int cpu = boot_cpu_id;
-
-	if (!IO_APIC_IRQ(irq)) {
-		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
-			ioapic);
-		return -EINVAL;
-	}
-
-	desc = irq_to_desc_alloc_cpu(irq, cpu);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc %d\n", irq);
-		return 0;
-	}
-
-	/*
-	 * IRQs < 16 are already in the irq_2_pin[] map
-	 */
-	if (irq >= NR_IRQS_LEGACY) {
-		cfg = desc->chip_data;
-		add_pin_to_irq_cpu(cfg, cpu, ioapic, pin);
-	}
-
-	setup_IO_APIC_irq(ioapic, pin, irq, desc, triggering, polarity);
-
-	return 0;
-}
-
 
 int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 {
@@ -4055,51 +4058,44 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 #ifdef CONFIG_SMP
 void __init setup_ioapic_dest(void)
 {
-	int pin, ioapic, irq, irq_entry;
+	int pin, ioapic = 0, irq, irq_entry;
 	struct irq_desc *desc;
-	struct irq_cfg *cfg;
 	const struct cpumask *mask;
 
 	if (skip_ioapic_setup == 1)
 		return;
 
-	for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
-		for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
-			irq_entry = find_irq_entry(ioapic, pin, mp_INT);
-			if (irq_entry == -1)
-				continue;
-			irq = pin_2_irq(irq_entry, ioapic, pin);
-
-			/* setup_IO_APIC_irqs could fail to get vector for some device
-			 * when you have too many devices, because at that time only boot
-			 * cpu is online.
-			 */
-			desc = irq_to_desc(irq);
-			cfg = desc->chip_data;
-			if (!cfg->vector) {
-				setup_IO_APIC_irq(ioapic, pin, irq, desc,
-						  irq_trigger(irq_entry),
-						  irq_polarity(irq_entry));
-				continue;
+#ifdef CONFIG_ACPI
+	if (!acpi_disabled && acpi_ioapic) {
+		ioapic = mp_find_ioapic(0);
+		if (ioapic < 0)
+			ioapic = 0;
+	}
+#endif
 
-			}
+	for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+		irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+		if (irq_entry == -1)
+			continue;
+		irq = pin_2_irq(irq_entry, ioapic, pin);
 
-			/*
-			 * Honour affinities which have been set in early boot
-			 */
-			if (desc->status &
-			    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-				mask = desc->affinity;
-			else
-				mask = apic->target_cpus();
+		desc = irq_to_desc(irq);
 
-			if (intr_remapping_enabled)
-				set_ir_ioapic_affinity_irq_desc(desc, mask);
-			else
-				set_ioapic_affinity_irq_desc(desc, mask);
-		}
+		/*
+		 * Honour affinities which have been set in early boot
+		 */
+		if (desc->status &
+		    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
+			mask = desc->affinity;
+		else
+			mask = apic->target_cpus();
 
+		if (intr_remapping_enabled)
+			set_ir_ioapic_affinity_irq_desc(desc, mask);
+		else
+			set_ioapic_affinity_irq_desc(desc, mask);
 	}
+
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index ce4fbfa315a..b3025b43b63 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -66,7 +66,7 @@ static inline unsigned int get_nmi_count(int cpu)
 
 static inline int mce_in_progress(void)
 {
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
+#if defined(CONFIG_X86_NEW_MCE)
 	return atomic_read(&mce_entry) > 0;
 #endif
 	return 0;
@@ -104,7 +104,7 @@ static __init void nmi_cpu_busy(void *data)
 }
 #endif
 
-static void report_broken_nmi(int cpu, int *prev_nmi_count)
+static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
 {
 	printk(KERN_CONT "\n");
 
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 01eda2ac65e..440a8bccd91 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -160,7 +160,6 @@ extern struct apic apic_summit;
 extern struct apic apic_bigsmp;
 extern struct apic apic_es7000;
 extern struct apic apic_es7000_cluster;
-extern struct apic apic_default;
 
 struct apic *apic = &apic_default;
 EXPORT_SYMBOL_GPL(apic);
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 1783652bb0e..bc3e880f9b8 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -50,7 +50,7 @@ static struct apic *apic_probe[] __initdata = {
 void __init default_setup_apic_routing(void)
 {
 #ifdef CONFIG_X86_X2APIC
-	if (x2apic && (apic != &apic_x2apic_phys &&
+	if (x2apic_mode && (apic != &apic_x2apic_phys &&
 #ifdef CONFIG_X86_UV
 		       apic != &apic_x2apic_uv_x &&
 #endif
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 9cfe1f415d8..344eee4ac0a 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -173,13 +173,6 @@ static inline int is_WPEG(struct rio_detail *rio){
 		rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
 }
 
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT	4
-#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
 #define SUMMIT_APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
 
 static const struct cpumask *summit_target_cpus(void)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 4a903e2f0d1..8e4cbb255c3 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -10,7 +10,7 @@
 #include <asm/apic.h>
 #include <asm/ipi.h>
 
-DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
 
 static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 2bda6935297..ef0ae207a7c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -105,7 +105,7 @@ static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	cpumask_set_cpu(cpu, retmask);
 }
 
-static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 {
 #ifdef CONFIG_SMP
 	unsigned long val;
@@ -562,7 +562,7 @@ void __init uv_system_init(void)
 	union uvh_node_id_u node_id;
 	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
 	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
-	int max_pnode = 0;
+	int gnode_extra, max_pnode = 0;
 	unsigned long mmr_base, present, paddr;
 	unsigned short pnode_mask;
 
@@ -574,6 +574,13 @@ void __init uv_system_init(void)
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
+	pnode_mask = (1 << n_val) - 1;
+	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+	gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
+	gnode_upper = ((unsigned long)gnode_extra  << m_val);
+	printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n",
+			n_val, m_val, gnode_upper, gnode_extra);
+
 	printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
 
 	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
@@ -583,15 +590,18 @@ void __init uv_system_init(void)
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
 	uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_blade_info);
 
 	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
 
 	bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
 	uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_node_to_blade);
 	memset(uv_node_to_blade, 255, bytes);
 
 	bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
 	uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_cpu_to_blade);
 	memset(uv_cpu_to_blade, 255, bytes);
 
 	blade = 0;
@@ -607,11 +617,6 @@ void __init uv_system_init(void)
 		}
 	}
 
-	pnode_mask = (1 << n_val) - 1;
-	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
-	gnode_upper = (((unsigned long)node_id.s.node_id) &
-		       ~((1 << n_val) - 1)) << m_val;
-
 	uv_bios_init();
 	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
 			    &sn_coherency_id, &sn_region_size);
@@ -634,6 +639,7 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
+		uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
 		uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
 		uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;