Fixed MTP to work with TWRP

arch/x86/kernel/apic/Makefile

@@ -0,0 +1,24 @@
+#
+# Makefile for local APIC drivers and for the IO-APIC code
+#
+
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o ipi.o
+obj-y				+= hw_nmi.o
+
+obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
+obj-$(CONFIG_SMP)		+= ipi.o
+
+ifeq ($(CONFIG_X86_64),y)
+# APIC probe will depend on the listing order here
+obj-$(CONFIG_X86_NUMACHIP)	+= apic_numachip.o
+obj-$(CONFIG_X86_UV)		+= x2apic_uv_x.o
+obj-$(CONFIG_X86_X2APIC)	+= x2apic_phys.o
+obj-$(CONFIG_X86_X2APIC)	+= x2apic_cluster.o
+obj-y				+= apic_flat_64.o
+endif
+
+# APIC probe will depend on the listing order here
+obj-$(CONFIG_X86_BIGSMP)	+= bigsmp_32.o
+
+# For 32bit, probe_32 need to be listed last
+obj-$(CONFIG_X86_LOCAL_APIC)	+= probe_$(BITS).o

arch/x86/kernel/apic/apic_flat_64.c

@@ -0,0 +1,317 @@
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Flat APIC subarch code.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+#include <linux/errno.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/hardirq.h>
+#include <linux/module.h>
+#include <asm/smp.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+
+#include <linux/acpi.h>
+
+static struct apic apic_physflat;
+static struct apic apic_flat;
+
+struct apic __read_mostly *apic = &apic_flat;
+EXPORT_SYMBOL_GPL(apic);
+
+static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return 1;
+}
+
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116).  So here it goes...
+ */
+void flat_init_apic_ldr(void)
+{
+	unsigned long val;
+	unsigned long num, id;
+
+	num = smp_processor_id();
+	id = 1UL << num;
+	apic_write(APIC_DFR, APIC_DFR_FLAT);
+	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+	val |= SET_APIC_LOGICAL_ID(id);
+	apic_write(APIC_LDR, val);
+}
+
+static inline void _flat_send_IPI_mask(unsigned long mask, int vector)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__default_send_IPI_dest_field(mask, vector, apic->dest_logical);
+	local_irq_restore(flags);
+}
+
+static void flat_send_IPI_mask(const struct cpumask *cpumask, int vector)
+{
+	unsigned long mask = cpumask_bits(cpumask)[0];
+
+	_flat_send_IPI_mask(mask, vector);
+}
+
+static void
+flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
+{
+	unsigned long mask = cpumask_bits(cpumask)[0];
+	int cpu = smp_processor_id();
+
+	if (cpu < BITS_PER_LONG)
+		clear_bit(cpu, &mask);
+
+	_flat_send_IPI_mask(mask, vector);
+}
+
+static void flat_send_IPI_allbutself(int vector)
+{
+	int cpu = smp_processor_id();
+#ifdef	CONFIG_HOTPLUG_CPU
+	int hotplug = 1;
+#else
+	int hotplug = 0;
+#endif
+	if (hotplug || vector == NMI_VECTOR) {
+		if (!cpumask_equal(cpu_online_mask, cpumask_of(cpu))) {
+			unsigned long mask = cpumask_bits(cpu_online_mask)[0];
+
+			if (cpu < BITS_PER_LONG)
+				clear_bit(cpu, &mask);
+
+			_flat_send_IPI_mask(mask, vector);
+		}
+	} else if (num_online_cpus() > 1) {
+		__default_send_IPI_shortcut(APIC_DEST_ALLBUT,
+					    vector, apic->dest_logical);
+	}
+}
+
+static void flat_send_IPI_all(int vector)
+{
+	if (vector == NMI_VECTOR) {
+		flat_send_IPI_mask(cpu_online_mask, vector);
+	} else {
+		__default_send_IPI_shortcut(APIC_DEST_ALLINC,
+					    vector, apic->dest_logical);
+	}
+}
+
+static unsigned int flat_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 = flat_get_apic_id(apic_read(APIC_ID));
+	return id;
+}
+
+static int flat_apic_id_registered(void)
+{
+	return physid_isset(read_xapic_id(), phys_cpu_present_map);
+}
+
+static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
+{
+	return initial_apic_id >> index_msb;
+}
+
+static int flat_probe(void)
+{
+	return 1;
+}
+
+static struct apic apic_flat =  {
+	.name				= "flat",
+	.probe				= flat_probe,
+	.acpi_madt_oem_check		= flat_acpi_madt_oem_check,
+	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_registered		= flat_apic_id_registered,
+
+	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_dest_mode			= 1, /* logical */
+
+	.target_cpus			= online_target_cpus,
+	.disable_esr			= 0,
+	.dest_logical			= APIC_DEST_LOGICAL,
+	.check_apicid_used		= NULL,
+
+	.vector_allocation_domain	= flat_vector_allocation_domain,
+	.init_apic_ldr			= flat_init_apic_ldr,
+
+	.ioapic_phys_id_map		= NULL,
+	.setup_apic_routing		= NULL,
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= NULL,
+	.check_phys_apicid_present	= default_check_phys_apicid_present,
+	.phys_pkg_id			= flat_phys_pkg_id,
+
+	.get_apic_id			= flat_get_apic_id,
+	.set_apic_id			= set_apic_id,
+	.apic_id_mask			= 0xFFu << 24,
+
+	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,
+
+	.send_IPI_mask			= flat_send_IPI_mask,
+	.send_IPI_mask_allbutself	= flat_send_IPI_mask_allbutself,
+	.send_IPI_allbutself		= flat_send_IPI_allbutself,
+	.send_IPI_all			= flat_send_IPI_all,
+	.send_IPI_self			= apic_send_IPI_self,
+
+	.wait_for_init_deassert		= false,
+	.inquire_remote_apic		= default_inquire_remote_apic,
+
+	.read				= native_apic_mem_read,
+	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
+	.icr_read			= native_apic_icr_read,
+	.icr_write			= native_apic_icr_write,
+	.wait_icr_idle			= native_apic_wait_icr_idle,
+	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+};
+
+/*
+ * Physflat mode is used when there are more than 8 CPUs on a system.
+ * We cannot use logical delivery in this case because the mask
+ * overflows, so use physical mode.
+ */
+static int 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)) {
+		printk(KERN_DEBUG "system APIC only can use physical flat");
+		return 1;
+	}
+
+	if (!strncmp(oem_id, "IBM", 3) && !strncmp(oem_table_id, "EXA", 3)) {
+		printk(KERN_DEBUG "IBM Summit detected, will use apic physical");
+		return 1;
+	}
+#endif
+
+	return 0;
+}
+
+static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector)
+{
+	default_send_IPI_mask_sequence_phys(cpumask, vector);
+}
+
+static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask,
+					      int vector)
+{
+	default_send_IPI_mask_allbutself_phys(cpumask, vector);
+}
+
+static void physflat_send_IPI_allbutself(int vector)
+{
+	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
+}
+
+static void physflat_send_IPI_all(int vector)
+{
+	physflat_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static int physflat_probe(void)
+{
+	if (apic == &apic_physflat || num_possible_cpus() > 8)
+		return 1;
+
+	return 0;
+}
+
+static struct apic apic_physflat =  {
+
+	.name				= "physical flat",
+	.probe				= physflat_probe,
+	.acpi_madt_oem_check		= physflat_acpi_madt_oem_check,
+	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_registered		= flat_apic_id_registered,
+
+	.irq_delivery_mode		= dest_Fixed,
+	.irq_dest_mode			= 0, /* physical */
+
+	.target_cpus			= online_target_cpus,
+	.disable_esr			= 0,
+	.dest_logical			= 0,
+	.check_apicid_used		= NULL,
+
+	.vector_allocation_domain	= default_vector_allocation_domain,
+	/* not needed, but shouldn't hurt: */
+	.init_apic_ldr			= flat_init_apic_ldr,
+
+	.ioapic_phys_id_map		= NULL,
+	.setup_apic_routing		= NULL,
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= NULL,
+	.check_phys_apicid_present	= default_check_phys_apicid_present,
+	.phys_pkg_id			= flat_phys_pkg_id,
+
+	.get_apic_id			= flat_get_apic_id,
+	.set_apic_id			= set_apic_id,
+	.apic_id_mask			= 0xFFu << 24,
+
+	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
+
+	.send_IPI_mask			= physflat_send_IPI_mask,
+	.send_IPI_mask_allbutself	= physflat_send_IPI_mask_allbutself,
+	.send_IPI_allbutself		= physflat_send_IPI_allbutself,
+	.send_IPI_all			= physflat_send_IPI_all,
+	.send_IPI_self			= apic_send_IPI_self,
+
+	.wait_for_init_deassert		= false,
+	.inquire_remote_apic		= default_inquire_remote_apic,
+
+	.read				= native_apic_mem_read,
+	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
+	.icr_read			= native_apic_icr_read,
+	.icr_write			= native_apic_icr_write,
+	.wait_icr_idle			= native_apic_wait_icr_idle,
+	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+};
+
+/*
+ * We need to check for physflat first, so this order is important.
+ */
+apic_drivers(apic_physflat, apic_flat);

arch/x86/kernel/apic/apic_noop.c

@@ -0,0 +1,169 @@
+/*
+ * NOOP APIC driver.
+ *
+ * Does almost nothing and should be substituted by a real apic driver via
+ * probe routine.
+ *
+ * Though in case if apic is disabled (for some reason) we try
+ * to not uglify the caller's code and allow to call (some) apic routines
+ * like self-ipi, etc...
+ */
+
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <asm/fixmap.h>
+#include <asm/mpspec.h>
+#include <asm/apicdef.h>
+#include <asm/apic.h>
+#include <asm/setup.h>
+
+#include <linux/smp.h>
+#include <asm/ipi.h>
+
+#include <linux/interrupt.h>
+#include <asm/acpi.h>
+#include <asm/e820.h>
+
+static void noop_init_apic_ldr(void) { }
+static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { }
+static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { }
+static void noop_send_IPI_allbutself(int vector) { }
+static void noop_send_IPI_all(int vector) { }
+static void noop_send_IPI_self(int vector) { }
+static void noop_apic_wait_icr_idle(void) { }
+static void noop_apic_icr_write(u32 low, u32 id) { }
+
+static int noop_wakeup_secondary_cpu(int apicid, unsigned long start_eip)
+{
+	return -1;
+}
+
+static u32 noop_safe_apic_wait_icr_idle(void)
+{
+	return 0;
+}
+
+static u64 noop_apic_icr_read(void)
+{
+	return 0;
+}
+
+static int noop_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+	return 0;
+}
+
+static unsigned int noop_get_apic_id(unsigned long x)
+{
+	return 0;
+}
+
+static int noop_probe(void)
+{
+	/*
+	 * NOOP apic should not ever be
+	 * enabled via probe routine
+	 */
+	return 0;
+}
+
+static int noop_apic_id_registered(void)
+{
+	/*
+	 * if we would be really "pedantic"
+	 * we should pass read_apic_id() here
+	 * but since NOOP suppose APIC ID = 0
+	 * lets save a few cycles
+	 */
+	return physid_isset(0, phys_cpu_present_map);
+}
+
+static const struct cpumask *noop_target_cpus(void)
+{
+	/* only BSP here */
+	return cpumask_of(0);
+}
+
+static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask,
+					  const struct cpumask *mask)
+{
+	if (cpu != 0)
+		pr_warning("APIC: Vector allocated for non-BSP cpu\n");
+	cpumask_copy(retmask, cpumask_of(cpu));
+}
+
+static u32 noop_apic_read(u32 reg)
+{
+	WARN_ON_ONCE((cpu_has_apic && !disable_apic));
+	return 0;
+}
+
+static void noop_apic_write(u32 reg, u32 v)
+{
+	WARN_ON_ONCE(cpu_has_apic && !disable_apic);
+}
+
+struct apic apic_noop = {
+	.name				= "noop",
+	.probe				= noop_probe,
+	.acpi_madt_oem_check		= NULL,
+
+	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_registered		= noop_apic_id_registered,
+
+	.irq_delivery_mode		= dest_LowestPrio,
+	/* logical delivery broadcast to all CPUs: */
+	.irq_dest_mode			= 1,
+
+	.target_cpus			= noop_target_cpus,
+	.disable_esr			= 0,
+	.dest_logical			= APIC_DEST_LOGICAL,
+	.check_apicid_used		= default_check_apicid_used,
+
+	.vector_allocation_domain	= noop_vector_allocation_domain,
+	.init_apic_ldr			= noop_init_apic_ldr,
+
+	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
+	.setup_apic_routing		= NULL,
+
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= physid_set_mask_of_physid,
+
+	.check_phys_apicid_present	= default_check_phys_apicid_present,
+
+	.phys_pkg_id			= noop_phys_pkg_id,
+
+	.get_apic_id			= noop_get_apic_id,
+	.set_apic_id			= NULL,
+	.apic_id_mask			= 0x0F << 24,
+
+	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,
+
+	.send_IPI_mask			= noop_send_IPI_mask,
+	.send_IPI_mask_allbutself	= noop_send_IPI_mask_allbutself,
+	.send_IPI_allbutself		= noop_send_IPI_allbutself,
+	.send_IPI_all			= noop_send_IPI_all,
+	.send_IPI_self			= noop_send_IPI_self,
+
+	.wakeup_secondary_cpu		= noop_wakeup_secondary_cpu,
+
+	.wait_for_init_deassert		= false,
+	.inquire_remote_apic		= NULL,
+
+	.read				= noop_apic_read,
+	.write				= noop_apic_write,
+	.eoi_write			= noop_apic_write,
+	.icr_read			= noop_apic_icr_read,
+	.icr_write			= noop_apic_icr_write,
+	.wait_icr_idle			= noop_apic_wait_icr_idle,
+	.safe_wait_icr_idle		= noop_safe_apic_wait_icr_idle,
+
+#ifdef CONFIG_X86_32
+	.x86_32_early_logical_apicid	= noop_x86_32_early_logical_apicid,
+#endif
+};

arch/x86/kernel/apic/apic_numachip.c

@@ -0,0 +1,256 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Numascale NumaConnect-Specific APIC Code
+ *
+ * Copyright (C) 2011 Numascale AS. All rights reserved.
+ *
+ * Send feedback to <support@numascale.com>
+ *
+ */
+
+#include <linux/errno.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/hardirq.h>
+#include <linux/delay.h>
+
+#include <asm/numachip/numachip.h>
+#include <asm/numachip/numachip_csr.h>
+#include <asm/smp.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+#include <asm/apic_flat_64.h>
+#include <asm/pgtable.h>
+
+static int numachip_system __read_mostly;
+
+static const struct apic apic_numachip;
+
+static unsigned int get_apic_id(unsigned long x)
+{
+	unsigned long value;
+	unsigned int id;
+
+	rdmsrl(MSR_FAM10H_NODE_ID, value);
+	id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
+
+	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)
+{
+	return get_apic_id(apic_read(APIC_ID));
+}
+
+static int numachip_apic_id_valid(int apicid)
+{
+	/* Trust what bootloader passes in MADT */
+	return 1;
+}
+
+static int numachip_apic_id_registered(void)
+{
+	return physid_isset(read_xapic_id(), phys_cpu_present_map);
+}
+
+static int numachip_phys_pkg_id(int initial_apic_id, int index_msb)
+{
+	return initial_apic_id >> index_msb;
+}
+
+static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+{
+	union numachip_csr_g3_ext_irq_gen int_gen;
+
+	int_gen.s._destination_apic_id = phys_apicid;
+	int_gen.s._vector = 0;
+	int_gen.s._msgtype = APIC_DM_INIT >> 8;
+	int_gen.s._index = 0;
+
+	write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v);
+
+	int_gen.s._msgtype = APIC_DM_STARTUP >> 8;
+	int_gen.s._vector = start_rip >> 12;
+
+	write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v);
+
+	atomic_set(&init_deasserted, 1);
+	return 0;
+}
+
+static void numachip_send_IPI_one(int cpu, int vector)
+{
+	union numachip_csr_g3_ext_irq_gen int_gen;
+	int apicid = per_cpu(x86_cpu_to_apicid, cpu);
+
+	int_gen.s._destination_apic_id = apicid;
+	int_gen.s._vector = vector;
+	int_gen.s._msgtype = (vector == NMI_VECTOR ? APIC_DM_NMI : APIC_DM_FIXED) >> 8;
+	int_gen.s._index = 0;
+
+	write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v);
+}
+
+static void numachip_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, mask)
+		numachip_send_IPI_one(cpu, vector);
+}
+
+static void numachip_send_IPI_mask_allbutself(const struct cpumask *mask,
+						int vector)
+{
+	unsigned int this_cpu = smp_processor_id();
+	unsigned int cpu;
+
+	for_each_cpu(cpu, mask) {
+		if (cpu != this_cpu)
+			numachip_send_IPI_one(cpu, vector);
+	}
+}
+
+static void numachip_send_IPI_allbutself(int vector)
+{
+	unsigned int this_cpu = smp_processor_id();
+	unsigned int cpu;
+
+	for_each_online_cpu(cpu) {
+		if (cpu != this_cpu)
+			numachip_send_IPI_one(cpu, vector);
+	}
+}
+
+static void numachip_send_IPI_all(int vector)
+{
+	numachip_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static void numachip_send_IPI_self(int vector)
+{
+	__default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
+}
+
+static int __init numachip_probe(void)
+{
+	return apic == &apic_numachip;
+}
+
+static void __init map_csrs(void)
+{
+	printk(KERN_INFO "NumaChip: Mapping local CSR space (%016llx - %016llx)\n",
+		NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_BASE + NUMACHIP_LCSR_SIZE - 1);
+	init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE);
+
+	printk(KERN_INFO "NumaChip: Mapping global CSR space (%016llx - %016llx)\n",
+		NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_BASE + NUMACHIP_GCSR_SIZE - 1);
+	init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE);
+}
+
+static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
+{
+
+	if (c->phys_proc_id != node) {
+		c->phys_proc_id = node;
+		per_cpu(cpu_llc_id, smp_processor_id()) = node;
+	}
+}
+
+static int __init numachip_system_init(void)
+{
+	unsigned int val;
+
+	if (!numachip_system)
+		return 0;
+
+	x86_cpuinit.fixup_cpu_id = fixup_cpu_id;
+	x86_init.pci.arch_init = pci_numachip_init;
+
+	map_csrs();
+
+	val = read_lcsr(CSR_G0_NODE_IDS);
+	printk(KERN_INFO "NumaChip: Local NodeID = %08x\n", val);
+
+	return 0;
+}
+early_initcall(numachip_system_init);
+
+static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	if (!strncmp(oem_id, "NUMASC", 6)) {
+		numachip_system = 1;
+		return 1;
+	}
+
+	return 0;
+}
+
+static const struct apic apic_numachip __refconst = {
+
+	.name				= "NumaConnect system",
+	.probe				= numachip_probe,
+	.acpi_madt_oem_check		= numachip_acpi_madt_oem_check,
+	.apic_id_valid			= numachip_apic_id_valid,
+	.apic_id_registered		= numachip_apic_id_registered,
+
+	.irq_delivery_mode		= dest_Fixed,
+	.irq_dest_mode			= 0, /* physical */
+
+	.target_cpus			= online_target_cpus,
+	.disable_esr			= 0,
+	.dest_logical			= 0,
+	.check_apicid_used		= NULL,
+
+	.vector_allocation_domain	= default_vector_allocation_domain,
+	.init_apic_ldr			= flat_init_apic_ldr,
+
+	.ioapic_phys_id_map		= NULL,
+	.setup_apic_routing		= NULL,
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= NULL,
+	.check_phys_apicid_present	= default_check_phys_apicid_present,
+	.phys_pkg_id			= numachip_phys_pkg_id,
+
+	.get_apic_id			= get_apic_id,
+	.set_apic_id			= set_apic_id,
+	.apic_id_mask			= 0xffU << 24,
+
+	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
+
+	.send_IPI_mask			= numachip_send_IPI_mask,
+	.send_IPI_mask_allbutself	= numachip_send_IPI_mask_allbutself,
+	.send_IPI_allbutself		= numachip_send_IPI_allbutself,
+	.send_IPI_all			= numachip_send_IPI_all,
+	.send_IPI_self			= numachip_send_IPI_self,
+
+	.wakeup_secondary_cpu		= numachip_wakeup_secondary,
+	.wait_for_init_deassert		= false,
+	.inquire_remote_apic		= NULL, /* REMRD not supported */
+
+	.read				= native_apic_mem_read,
+	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
+	.icr_read			= native_apic_icr_read,
+	.icr_write			= native_apic_icr_write,
+	.wait_icr_idle			= native_apic_wait_icr_idle,
+	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+};
+apic_driver(apic_numachip);
+

arch/x86/kernel/apic/bigsmp_32.c

@@ -0,0 +1,223 @@
+/*
+ * APIC driver for "bigsmp" xAPIC machines with more than 8 virtual CPUs.
+ *
+ * Drives the local APIC in "clustered mode".
+ */
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/dmi.h>
+#include <linux/smp.h>
+
+#include <asm/apicdef.h>
+#include <asm/fixmap.h>
+#include <asm/mpspec.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+
+static unsigned bigsmp_get_apic_id(unsigned long x)
+{
+	return (x >> 24) & 0xFF;
+}
+
+static int bigsmp_apic_id_registered(void)
+{
+	return 1;
+}
+
+static unsigned long bigsmp_check_apicid_used(physid_mask_t *map, int apicid)
+{
+	return 0;
+}
+
+static int bigsmp_early_logical_apicid(int cpu)
+{
+	/* on bigsmp, logical apicid is the same as physical */
+	return early_per_cpu(x86_cpu_to_apicid, cpu);
+}
+
+static inline unsigned long calculate_ldr(int cpu)
+{
+	unsigned long val, id;
+
+	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+	id = per_cpu(x86_bios_cpu_apicid, cpu);
+	val |= SET_APIC_LOGICAL_ID(id);
+
+	return val;
+}
+
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116).  So here it goes...
+ */
+static void bigsmp_init_apic_ldr(void)
+{
+	unsigned long val;
+	int cpu = smp_processor_id();
+
+	apic_write(APIC_DFR, APIC_DFR_FLAT);
+	val = calculate_ldr(cpu);
+	apic_write(APIC_LDR, val);
+}
+
+static void bigsmp_setup_apic_routing(void)
+{
+	printk(KERN_INFO
+		"Enabling APIC mode:  Physflat.  Using %d I/O APICs\n",
+		nr_ioapics);
+}
+
+static int bigsmp_cpu_present_to_apicid(int mps_cpu)
+{
+	if (mps_cpu < nr_cpu_ids)
+		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
+
+	return BAD_APICID;
+}
+
+static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
+{
+	/* For clustered we don't have a good way to do this yet - hack */
+	physids_promote(0xFFL, retmap);
+}
+
+static int bigsmp_check_phys_apicid_present(int phys_apicid)
+{
+	return 1;
+}
+
+static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+	return cpuid_apic >> index_msb;
+}
+
+static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+	default_send_IPI_mask_sequence_phys(mask, vector);
+}
+
+static void bigsmp_send_IPI_allbutself(int vector)
+{
+	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
+}
+
+static void bigsmp_send_IPI_all(int vector)
+{
+	bigsmp_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static int dmi_bigsmp; /* can be set by dmi scanners */
+
+static int hp_ht_bigsmp(const struct dmi_system_id *d)
+{
+	printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident);
+	dmi_bigsmp = 1;
+
+	return 0;
+}
+
+
+static const struct dmi_system_id bigsmp_dmi_table[] = {
+	{ hp_ht_bigsmp, "HP ProLiant DL760 G2",
+		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
+			DMI_MATCH(DMI_BIOS_VERSION, "P44-"),
+		}
+	},
+
+	{ hp_ht_bigsmp, "HP ProLiant DL740",
+		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
+			DMI_MATCH(DMI_BIOS_VERSION, "P47-"),
+		}
+	},
+	{ } /* NULL entry stops DMI scanning */
+};
+
+static int probe_bigsmp(void)
+{
+	if (def_to_bigsmp)
+		dmi_bigsmp = 1;
+	else
+		dmi_check_system(bigsmp_dmi_table);
+
+	return dmi_bigsmp;
+}
+
+static struct apic apic_bigsmp = {
+
+	.name				= "bigsmp",
+	.probe				= probe_bigsmp,
+	.acpi_madt_oem_check		= NULL,
+	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_registered		= bigsmp_apic_id_registered,
+
+	.irq_delivery_mode		= dest_Fixed,
+	/* phys delivery to target CPU: */
+	.irq_dest_mode			= 0,
+
+	.target_cpus			= default_target_cpus,
+	.disable_esr			= 1,
+	.dest_logical			= 0,
+	.check_apicid_used		= bigsmp_check_apicid_used,
+
+	.vector_allocation_domain	= default_vector_allocation_domain,
+	.init_apic_ldr			= bigsmp_init_apic_ldr,
+
+	.ioapic_phys_id_map		= bigsmp_ioapic_phys_id_map,
+	.setup_apic_routing		= bigsmp_setup_apic_routing,
+	.cpu_present_to_apicid		= bigsmp_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= physid_set_mask_of_physid,
+	.check_phys_apicid_present	= bigsmp_check_phys_apicid_present,
+	.phys_pkg_id			= bigsmp_phys_pkg_id,
+
+	.get_apic_id			= bigsmp_get_apic_id,
+	.set_apic_id			= NULL,
+	.apic_id_mask			= 0xFF << 24,
+
+	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
+
+	.send_IPI_mask			= bigsmp_send_IPI_mask,
+	.send_IPI_mask_allbutself	= NULL,
+	.send_IPI_allbutself		= bigsmp_send_IPI_allbutself,
+	.send_IPI_all			= bigsmp_send_IPI_all,
+	.send_IPI_self			= default_send_IPI_self,
+
+	.wait_for_init_deassert		= true,
+	.inquire_remote_apic		= default_inquire_remote_apic,
+
+	.read				= native_apic_mem_read,
+	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
+	.icr_read			= native_apic_icr_read,
+	.icr_write			= native_apic_icr_write,
+	.wait_icr_idle			= native_apic_wait_icr_idle,
+	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= bigsmp_early_logical_apicid,
+};
+
+void __init generic_bigsmp_probe(void)
+{
+	unsigned int cpu;
+
+	if (!probe_bigsmp())
+		return;
+
+	apic = &apic_bigsmp;
+
+	for_each_possible_cpu(cpu) {
+		if (early_per_cpu(x86_cpu_to_logical_apicid,
+				  cpu) == BAD_APICID)
+			continue;
+		early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+			bigsmp_early_logical_apicid(cpu);
+	}
+
+	pr_info("Overriding APIC driver with %s\n", apic_bigsmp.name);
+}
+
+apic_driver(apic_bigsmp);

arch/x86/kernel/apic/hw_nmi.c

@@ -0,0 +1,102 @@
+/*
+ *  HW NMI watchdog support
+ *
+ *  started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ *  Arch specific calls to support NMI watchdog
+ *
+ *  Bits copied from original nmi.c file
+ *
+ */
+#include <asm/apic.h>
+#include <asm/nmi.h>
+
+#include <linux/cpumask.h>
+#include <linux/kdebug.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/nmi.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+u64 hw_nmi_get_sample_period(int watchdog_thresh)
+{
+	return (u64)(cpu_khz) * 1000 * watchdog_thresh;
+}
+#endif
+
+#ifdef arch_trigger_all_cpu_backtrace
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
+
+void arch_trigger_all_cpu_backtrace(bool include_self)
+{
+	int i;
+	int cpu = get_cpu();
+
+	if (test_and_set_bit(0, &backtrace_flag)) {
+		/*
+		 * If there is already a trigger_all_cpu_backtrace() in progress
+		 * (backtrace_flag == 1), don't output double cpu dump infos.
+		 */
+		put_cpu();
+		return;
+	}
+
+	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
+	if (!include_self)
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+
+	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
+		pr_info("sending NMI to %s CPUs:\n",
+			(include_self ? "all" : "other"));
+		apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR);
+	}
+
+	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
+	for (i = 0; i < 10 * 1000; i++) {
+		if (cpumask_empty(to_cpumask(backtrace_mask)))
+			break;
+		mdelay(1);
+		touch_softlockup_watchdog();
+	}
+
+	clear_bit(0, &backtrace_flag);
+	smp_mb__after_atomic();
+	put_cpu();
+}
+
+static int
+arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
+{
+	int cpu;
+
+	cpu = smp_processor_id();
+
+	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
+		static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+		arch_spin_lock(&lock);
+		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
+		show_regs(regs);
+		arch_spin_unlock(&lock);
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+		return NMI_HANDLED;
+	}
+
+	return NMI_DONE;
+}
+NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler);
+
+static int __init register_trigger_all_cpu_backtrace(void)
+{
+	register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler,
+				0, "arch_bt");
+	return 0;
+}
+early_initcall(register_trigger_all_cpu_backtrace);
+#endif

arch/x86/kernel/apic/ipi.c

@@ -0,0 +1,166 @@
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/kernel_stat.h>
+#include <linux/mc146818rtc.h>
+#include <linux/cache.h>
+#include <linux/cpu.h>
+#include <linux/module.h>
+
+#include <asm/smp.h>
+#include <asm/mtrr.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <asm/apic.h>
+#include <asm/proto.h>
+#include <asm/ipi.h>
+
+void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector)
+{
+	unsigned long query_cpu;
+	unsigned long flags;
+
+	/*
+	 * Hack. The clustered APIC addressing mode doesn't allow us to send
+	 * to an arbitrary mask, so I do a unicast to each CPU instead.
+	 * - mbligh
+	 */
+	local_irq_save(flags);
+	for_each_cpu(query_cpu, mask) {
+		__default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid,
+				query_cpu), vector, APIC_DEST_PHYSICAL);
+	}
+	local_irq_restore(flags);
+}
+
+void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
+						 int vector)
+{
+	unsigned int this_cpu = smp_processor_id();
+	unsigned int query_cpu;
+	unsigned long flags;
+
+	/* See Hack comment above */
+
+	local_irq_save(flags);
+	for_each_cpu(query_cpu, mask) {
+		if (query_cpu == this_cpu)
+			continue;
+		__default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid,
+				 query_cpu), vector, APIC_DEST_PHYSICAL);
+	}
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_X86_32
+
+void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+						 int vector)
+{
+	unsigned long flags;
+	unsigned int query_cpu;
+
+	/*
+	 * Hack. The clustered APIC addressing mode doesn't allow us to send
+	 * to an arbitrary mask, so I do a unicasts to each CPU instead. This
+	 * should be modified to do 1 message per cluster ID - mbligh
+	 */
+
+	local_irq_save(flags);
+	for_each_cpu(query_cpu, mask)
+		__default_send_IPI_dest_field(
+			early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+			vector, apic->dest_logical);
+	local_irq_restore(flags);
+}
+
+void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+						 int vector)
+{
+	unsigned long flags;
+	unsigned int query_cpu;
+	unsigned int this_cpu = smp_processor_id();
+
+	/* See Hack comment above */
+
+	local_irq_save(flags);
+	for_each_cpu(query_cpu, mask) {
+		if (query_cpu == this_cpu)
+			continue;
+		__default_send_IPI_dest_field(
+			early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+			vector, apic->dest_logical);
+		}
+	local_irq_restore(flags);
+}
+
+/*
+ * This is only used on smaller machines.
+ */
+void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
+{
+	unsigned long mask = cpumask_bits(cpumask)[0];
+	unsigned long flags;
+
+	if (!mask)
+		return;
+
+	local_irq_save(flags);
+	WARN_ON(mask & ~cpumask_bits(cpu_online_mask)[0]);
+	__default_send_IPI_dest_field(mask, vector, apic->dest_logical);
+	local_irq_restore(flags);
+}
+
+void default_send_IPI_allbutself(int vector)
+{
+	/*
+	 * if there are no other CPUs in the system then we get an APIC send
+	 * error if we try to broadcast, thus avoid sending IPIs in this case.
+	 */
+	if (!(num_online_cpus() > 1))
+		return;
+
+	__default_local_send_IPI_allbutself(vector);
+}
+
+void default_send_IPI_all(int vector)
+{
+	__default_local_send_IPI_all(vector);
+}
+
+void default_send_IPI_self(int vector)
+{
+	__default_send_IPI_shortcut(APIC_DEST_SELF, vector, apic->dest_logical);
+}
+
+/* must come after the send_IPI functions above for inlining */
+static int convert_apicid_to_cpu(int apic_id)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		if (per_cpu(x86_cpu_to_apicid, i) == apic_id)
+			return i;
+	}
+	return -1;
+}
+
+int safe_smp_processor_id(void)
+{
+	int apicid, cpuid;
+
+	if (!cpu_has_apic)
+		return 0;
+
+	apicid = hard_smp_processor_id();
+	if (apicid == BAD_APICID)
+		return 0;
+
+	cpuid = convert_apicid_to_cpu(apicid);
+
+	return cpuid >= 0 ? cpuid : 0;
+}
+#endif

arch/x86/kernel/apic/probe_32.c

@@ -0,0 +1,227 @@
+/*
+ * Default generic APIC driver. This handles up to 8 CPUs.
+ *
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic x86 APIC driver probe layer.
+ */
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <asm/fixmap.h>
+#include <asm/mpspec.h>
+#include <asm/apicdef.h>
+#include <asm/apic.h>
+#include <asm/setup.h>
+
+#include <linux/smp.h>
+#include <asm/ipi.h>
+
+#include <linux/interrupt.h>
+#include <asm/acpi.h>
+#include <asm/e820.h>
+
+#ifdef CONFIG_HOTPLUG_CPU
+#define DEFAULT_SEND_IPI	(1)
+#else
+#define DEFAULT_SEND_IPI	(0)
+#endif
+
+int no_broadcast = DEFAULT_SEND_IPI;
+
+static __init int no_ipi_broadcast(char *str)
+{
+	get_option(&str, &no_broadcast);
+	pr_info("Using %s mode\n",
+		no_broadcast ? "No IPI Broadcast" : "IPI Broadcast");
+	return 1;
+}
+__setup("no_ipi_broadcast=", no_ipi_broadcast);
+
+static int __init print_ipi_mode(void)
+{
+	pr_info("Using IPI %s mode\n",
+		no_broadcast ? "No-Shortcut" : "Shortcut");
+	return 0;
+}
+late_initcall(print_ipi_mode);
+
+static int default_x86_32_early_logical_apicid(int cpu)
+{
+	return 1 << cpu;
+}
+
+static void setup_apic_flat_routing(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+	printk(KERN_INFO
+		"Enabling APIC mode:  Flat.  Using %d I/O APICs\n",
+		nr_ioapics);
+#endif
+}
+
+/* should be called last. */
+static int probe_default(void)
+{
+	return 1;
+}
+
+static struct apic apic_default = {
+
+	.name				= "default",
+	.probe				= probe_default,
+	.acpi_madt_oem_check		= NULL,
+	.apic_id_valid			= default_apic_id_valid,
+	.apic_id_registered		= default_apic_id_registered,
+
+	.irq_delivery_mode		= dest_LowestPrio,
+	/* logical delivery broadcast to all CPUs: */
+	.irq_dest_mode			= 1,
+
+	.target_cpus			= default_target_cpus,
+	.disable_esr			= 0,
+	.dest_logical			= APIC_DEST_LOGICAL,
+	.check_apicid_used		= default_check_apicid_used,
+
+	.vector_allocation_domain	= flat_vector_allocation_domain,
+	.init_apic_ldr			= default_init_apic_ldr,
+
+	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
+	.setup_apic_routing		= setup_apic_flat_routing,
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= physid_set_mask_of_physid,
+	.check_phys_apicid_present	= default_check_phys_apicid_present,
+	.phys_pkg_id			= default_phys_pkg_id,
+
+	.get_apic_id			= default_get_apic_id,
+	.set_apic_id			= NULL,
+	.apic_id_mask			= 0x0F << 24,
+
+	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,
+
+	.send_IPI_mask			= default_send_IPI_mask_logical,
+	.send_IPI_mask_allbutself	= default_send_IPI_mask_allbutself_logical,
+	.send_IPI_allbutself		= default_send_IPI_allbutself,
+	.send_IPI_all			= default_send_IPI_all,
+	.send_IPI_self			= default_send_IPI_self,
+
+	.wait_for_init_deassert		= true,
+	.inquire_remote_apic		= default_inquire_remote_apic,
+
+	.read				= native_apic_mem_read,
+	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
+	.icr_read			= native_apic_icr_read,
+	.icr_write			= native_apic_icr_write,
+	.wait_icr_idle			= native_apic_wait_icr_idle,
+	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= default_x86_32_early_logical_apicid,
+};
+
+apic_driver(apic_default);
+
+struct apic *apic = &apic_default;
+EXPORT_SYMBOL_GPL(apic);
+
+static int cmdline_apic __initdata;
+static int __init parse_apic(char *arg)
+{
+	struct apic **drv;
+
+	if (!arg)
+		return -EINVAL;
+
+	for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) {
+		if (!strcmp((*drv)->name, arg)) {
+			apic = *drv;
+			cmdline_apic = 1;
+			return 0;
+		}
+	}
+
+	/* Parsed again by __setup for debug/verbose */
+	return 0;
+}
+early_param("apic", parse_apic);
+
+void __init default_setup_apic_routing(void)
+{
+	int version = apic_version[boot_cpu_physical_apicid];
+
+	if (num_possible_cpus() > 8) {
+		switch (boot_cpu_data.x86_vendor) {
+		case X86_VENDOR_INTEL:
+			if (!APIC_XAPIC(version)) {
+				def_to_bigsmp = 0;
+				break;
+			}
+			/* If P4 and above fall through */
+		case X86_VENDOR_AMD:
+			def_to_bigsmp = 1;
+		}
+	}
+
+#ifdef CONFIG_X86_BIGSMP
+	/*
+	 * This is used to switch to bigsmp mode when
+	 * - There is no apic= option specified by the user
+	 * - generic_apic_probe() has chosen apic_default as the sub_arch
+	 * - we find more than 8 CPUs in acpi LAPIC listing with xAPIC support
+	 */
+
+	if (!cmdline_apic && apic == &apic_default)
+		generic_bigsmp_probe();
+#endif
+
+	if (apic->setup_apic_routing)
+		apic->setup_apic_routing();
+
+	if (x86_platform.apic_post_init)
+		x86_platform.apic_post_init();
+}
+
+void __init generic_apic_probe(void)
+{
+	if (!cmdline_apic) {
+		struct apic **drv;
+
+		for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) {
+			if ((*drv)->probe()) {
+				apic = *drv;
+				break;
+			}
+		}
+		/* Not visible without early console */
+		if (drv == __apicdrivers_end)
+			panic("Didn't find an APIC driver");
+	}
+	printk(KERN_INFO "Using APIC driver %s\n", apic->name);
+}
+
+/* This function can switch the APIC even after the initial ->probe() */
+int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	struct apic **drv;
+
+	for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) {
+		if (!(*drv)->acpi_madt_oem_check)
+			continue;
+		if (!(*drv)->acpi_madt_oem_check(oem_id, oem_table_id))
+			continue;
+
+		if (!cmdline_apic) {
+			apic = *drv;
+			printk(KERN_INFO "Switched to APIC driver `%s'.\n",
+			       apic->name);
+		}
+		return 1;
+	}
+	return 0;
+}

arch/x86/kernel/apic/probe_64.c

@@ -0,0 +1,72 @@
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC sub-arch probe layer.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/hardirq.h>
+#include <linux/dmar.h>
+
+#include <asm/smp.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+#include <asm/setup.h>
+
+/*
+ * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode.
+ */
+void __init default_setup_apic_routing(void)
+{
+	struct apic **drv;
+
+	enable_IR_x2apic();
+
+	for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) {
+		if ((*drv)->probe && (*drv)->probe()) {
+			if (apic != *drv) {
+				apic = *drv;
+				pr_info("Switched APIC routing to %s.\n",
+					apic->name);
+			}
+			break;
+		}
+	}
+
+	if (x86_platform.apic_post_init)
+		x86_platform.apic_post_init();
+}
+
+/* Same for both flat and physical. */
+
+void apic_send_IPI_self(int vector)
+{
+	__default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
+}
+
+int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	struct apic **drv;
+
+	for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) {
+		if ((*drv)->acpi_madt_oem_check(oem_id, oem_table_id)) {
+			if (apic != *drv) {
+				apic = *drv;
+				pr_info("Setting APIC routing to %s.\n",
+					apic->name);
+			}
+			return 1;
+		}
+	}
+	return 0;
+}

arch/x86/kernel/apic/x2apic_cluster.c

@@ -0,0 +1,287 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/dmar.h>
+#include <linux/cpu.h>
+
+#include <asm/smp.h>
+#include <asm/x2apic.h>
+
+static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+static DEFINE_PER_CPU(cpumask_var_t, cpus_in_cluster);
+static DEFINE_PER_CPU(cpumask_var_t, ipi_mask);
+
+static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return x2apic_enabled();
+}
+
+static inline u32 x2apic_cluster(int cpu)
+{
+	return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16;
+}
+
+static void
+__x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
+{
+	struct cpumask *cpus_in_cluster_ptr;
+	struct cpumask *ipi_mask_ptr;
+	unsigned int cpu, this_cpu;
+	unsigned long flags;
+	u32 dest;
+
+	x2apic_wrmsr_fence();
+
+	local_irq_save(flags);
+
+	this_cpu = smp_processor_id();
+
+	/*
+	 * We are to modify mask, so we need an own copy
+	 * and be sure it's manipulated with irq off.
+	 */
+	ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask);
+	cpumask_copy(ipi_mask_ptr, mask);
+
+	/*
+	 * The idea is to send one IPI per cluster.
+	 */
+	for_each_cpu(cpu, ipi_mask_ptr) {
+		unsigned long i;
+
+		cpus_in_cluster_ptr = per_cpu(cpus_in_cluster, cpu);
+		dest = 0;
+
+		/* Collect cpus in cluster. */
+		for_each_cpu_and(i, ipi_mask_ptr, cpus_in_cluster_ptr) {
+			if (apic_dest == APIC_DEST_ALLINC || i != this_cpu)
+				dest |= per_cpu(x86_cpu_to_logical_apicid, i);
+		}
+
+		if (!dest)
+			continue;
+
+		__x2apic_send_IPI_dest(dest, vector, apic->dest_logical);
+		/*
+		 * Cluster sibling cpus should be discared now so
+		 * we would not send IPI them second time.
+		 */
+		cpumask_andnot(ipi_mask_ptr, ipi_mask_ptr, cpus_in_cluster_ptr);
+	}
+
+	local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+	__x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLINC);
+}
+
+static void
+x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
+{
+	__x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLBUT);
+}
+
+static void x2apic_send_IPI_allbutself(int vector)
+{
+	__x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLBUT);
+}
+
+static void x2apic_send_IPI_all(int vector)
+{
+	__x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC);
+}
+
+static int
+x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+			      const struct cpumask *andmask,
+			      unsigned int *apicid)
+{
+	u32 dest = 0;
+	u16 cluster;
+	int i;
+
+	for_each_cpu_and(i, cpumask, andmask) {
+		if (!cpumask_test_cpu(i, cpu_online_mask))
+			continue;
+		dest = per_cpu(x86_cpu_to_logical_apicid, i);
+		cluster = x2apic_cluster(i);
+		break;
+	}
+
+	if (!dest)
+		return -EINVAL;
+
+	for_each_cpu_and(i, cpumask, andmask) {
+		if (!cpumask_test_cpu(i, cpu_online_mask))
+			continue;
+		if (cluster != x2apic_cluster(i))
+			continue;
+		dest |= per_cpu(x86_cpu_to_logical_apicid, i);
+	}
+
+	*apicid = dest;
+
+	return 0;
+}
+
+static void init_x2apic_ldr(void)
+{
+	unsigned int this_cpu = smp_processor_id();
+	unsigned int cpu;
+
+	per_cpu(x86_cpu_to_logical_apicid, this_cpu) = apic_read(APIC_LDR);
+
+	__cpu_set(this_cpu, per_cpu(cpus_in_cluster, this_cpu));
+	for_each_online_cpu(cpu) {
+		if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
+			continue;
+		__cpu_set(this_cpu, per_cpu(cpus_in_cluster, cpu));
+		__cpu_set(cpu, per_cpu(cpus_in_cluster, this_cpu));
+	}
+}
+
+ /*
+  * At CPU state changes, update the x2apic cluster sibling info.
+  */
+static int
+update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+	unsigned int this_cpu = (unsigned long)hcpu;
+	unsigned int cpu;
+	int err = 0;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+		if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, this_cpu),
+					GFP_KERNEL)) {
+			err = -ENOMEM;
+		} else if (!zalloc_cpumask_var(&per_cpu(ipi_mask, this_cpu),
+					       GFP_KERNEL)) {
+			free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
+			err = -ENOMEM;
+		}
+		break;
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+	case CPU_DEAD:
+		for_each_online_cpu(cpu) {
+			if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
+				continue;
+			__cpu_clear(this_cpu, per_cpu(cpus_in_cluster, cpu));
+			__cpu_clear(cpu, per_cpu(cpus_in_cluster, this_cpu));
+		}
+		free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
+		free_cpumask_var(per_cpu(ipi_mask, this_cpu));
+		break;
+	}
+
+	return notifier_from_errno(err);
+}
+
+static struct notifier_block __refdata x2apic_cpu_notifier = {
+	.notifier_call = update_clusterinfo,
+};
+
+static int x2apic_init_cpu_notifier(void)
+{
+	int cpu = smp_processor_id();
+
+	zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL);
+	zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL);
+
+	BUG_ON(!per_cpu(cpus_in_cluster, cpu) || !per_cpu(ipi_mask, cpu));
+
+	__cpu_set(cpu, per_cpu(cpus_in_cluster, cpu));
+	register_hotcpu_notifier(&x2apic_cpu_notifier);
+	return 1;
+}
+
+static int x2apic_cluster_probe(void)
+{
+	if (x2apic_mode)
+		return x2apic_init_cpu_notifier();
+	else
+		return 0;
+}
+
+static const struct cpumask *x2apic_cluster_target_cpus(void)
+{
+	return cpu_all_mask;
+}
+
+/*
+ * Each x2apic cluster is an allocation domain.
+ */
+static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask,
+					     const struct cpumask *mask)
+{
+	/*
+	 * To minimize vector pressure, default case of boot, device bringup
+	 * etc will use a single cpu for the interrupt destination.
+	 *
+	 * On explicit migration requests coming from irqbalance etc,
+	 * interrupts will be routed to the x2apic cluster (cluster-id
+	 * derived from the first cpu in the mask) members specified
+	 * in the mask.
+	 */
+	if (mask == x2apic_cluster_target_cpus())
+		cpumask_copy(retmask, cpumask_of(cpu));
+	else
+		cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu));
+}
+
+static struct apic apic_x2apic_cluster = {
+
+	.name				= "cluster x2apic",
+	.probe				= x2apic_cluster_probe,
+	.acpi_madt_oem_check		= x2apic_acpi_madt_oem_check,
+	.apic_id_valid			= x2apic_apic_id_valid,
+	.apic_id_registered		= x2apic_apic_id_registered,
+
+	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_dest_mode			= 1, /* logical */
+
+	.target_cpus			= x2apic_cluster_target_cpus,
+	.disable_esr			= 0,
+	.dest_logical			= APIC_DEST_LOGICAL,
+	.check_apicid_used		= NULL,
+
+	.vector_allocation_domain	= cluster_vector_allocation_domain,
+	.init_apic_ldr			= init_x2apic_ldr,
+
+	.ioapic_phys_id_map		= NULL,
+	.setup_apic_routing		= NULL,
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= NULL,
+	.check_phys_apicid_present	= default_check_phys_apicid_present,
+	.phys_pkg_id			= x2apic_phys_pkg_id,
+
+	.get_apic_id			= x2apic_get_apic_id,
+	.set_apic_id			= x2apic_set_apic_id,
+	.apic_id_mask			= 0xFFFFFFFFu,
+
+	.cpu_mask_to_apicid_and		= x2apic_cpu_mask_to_apicid_and,
+
+	.send_IPI_mask			= x2apic_send_IPI_mask,
+	.send_IPI_mask_allbutself	= x2apic_send_IPI_mask_allbutself,
+	.send_IPI_allbutself		= x2apic_send_IPI_allbutself,
+	.send_IPI_all			= x2apic_send_IPI_all,
+	.send_IPI_self			= x2apic_send_IPI_self,
+
+	.wait_for_init_deassert		= false,
+	.inquire_remote_apic		= NULL,
+
+	.read				= native_apic_msr_read,
+	.write				= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
+	.icr_read			= native_x2apic_icr_read,
+	.icr_write			= native_x2apic_icr_write,
+	.wait_icr_idle			= native_x2apic_wait_icr_idle,
+	.safe_wait_icr_idle		= native_safe_x2apic_wait_icr_idle,
+};
+
+apic_driver(apic_x2apic_cluster);

arch/x86/kernel/apic/x2apic_phys.c

@@ -0,0 +1,141 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/dmar.h>
+
+#include <asm/smp.h>
+#include <asm/x2apic.h>
+
+int x2apic_phys;
+
+static struct apic apic_x2apic_phys;
+
+static int set_x2apic_phys_mode(char *arg)
+{
+	x2apic_phys = 1;
+	return 0;
+}
+early_param("x2apic_phys", set_x2apic_phys_mode);
+
+static bool x2apic_fadt_phys(void)
+{
+	if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
+		printk(KERN_DEBUG "System requires x2apic physical mode\n");
+		return true;
+	}
+	return false;
+}
+
+static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys());
+}
+
+static void
+__x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
+{
+	unsigned long query_cpu;
+	unsigned long this_cpu;
+	unsigned long flags;
+
+	x2apic_wrmsr_fence();
+
+	local_irq_save(flags);
+
+	this_cpu = smp_processor_id();
+	for_each_cpu(query_cpu, mask) {
+		if (apic_dest == APIC_DEST_ALLBUT && this_cpu == query_cpu)
+			continue;
+		__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_mask(const struct cpumask *mask, int vector)
+{
+	__x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLINC);
+}
+
+static void
+ x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
+{
+	__x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLBUT);
+}
+
+static void x2apic_send_IPI_allbutself(int vector)
+{
+	__x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLBUT);
+}
+
+static void x2apic_send_IPI_all(int vector)
+{
+	__x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC);
+}
+
+static void init_x2apic_ldr(void)
+{
+}
+
+static int x2apic_phys_probe(void)
+{
+	if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
+		return 1;
+
+	return apic == &apic_x2apic_phys;
+}
+
+static struct apic apic_x2apic_phys = {
+
+	.name				= "physical x2apic",
+	.probe				= x2apic_phys_probe,
+	.acpi_madt_oem_check		= x2apic_acpi_madt_oem_check,
+	.apic_id_valid			= x2apic_apic_id_valid,
+	.apic_id_registered		= x2apic_apic_id_registered,
+
+	.irq_delivery_mode		= dest_Fixed,
+	.irq_dest_mode			= 0, /* physical */
+
+	.target_cpus			= online_target_cpus,
+	.disable_esr			= 0,
+	.dest_logical			= 0,
+	.check_apicid_used		= NULL,
+
+	.vector_allocation_domain	= default_vector_allocation_domain,
+	.init_apic_ldr			= init_x2apic_ldr,
+
+	.ioapic_phys_id_map		= NULL,
+	.setup_apic_routing		= NULL,
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= NULL,
+	.check_phys_apicid_present	= default_check_phys_apicid_present,
+	.phys_pkg_id			= x2apic_phys_pkg_id,
+
+	.get_apic_id			= x2apic_get_apic_id,
+	.set_apic_id			= x2apic_set_apic_id,
+	.apic_id_mask			= 0xFFFFFFFFu,
+
+	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
+
+	.send_IPI_mask			= x2apic_send_IPI_mask,
+	.send_IPI_mask_allbutself	= x2apic_send_IPI_mask_allbutself,
+	.send_IPI_allbutself		= x2apic_send_IPI_allbutself,
+	.send_IPI_all			= x2apic_send_IPI_all,
+	.send_IPI_self			= x2apic_send_IPI_self,
+
+	.wait_for_init_deassert		= false,
+	.inquire_remote_apic		= NULL,
+
+	.read				= native_apic_msr_read,
+	.write				= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
+	.icr_read			= native_x2apic_icr_read,
+	.icr_write			= native_x2apic_icr_write,
+	.wait_icr_idle			= native_x2apic_wait_icr_idle,
+	.safe_wait_icr_idle		= native_safe_x2apic_wait_icr_idle,
+};
+
+apic_driver(apic_x2apic_phys);