1 files changed, 1100 insertions, 402 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a38aafaefc2..ef1b93f18ed 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1,261 +1,587 @@
-#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/linkage.h>
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
 #include <linux/string.h>
 #include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kprobes.h>
+#include <linux/kgdb.h>
 #include <linux/smp.h>
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/bootmem.h>
-#include <asm/semaphore.h>
+#include <linux/io.h>
+
+#include <asm/stackprotector.h>
+#include <asm/perf_event.h>
+#include <asm/mmu_context.h>
+#include <asm/archrandom.h>
+#include <asm/hypervisor.h>
 #include <asm/processor.h>
+#include <asm/debugreg.h>
+#include <asm/sections.h>
+#include <asm/vsyscall.h>
+#include <linux/topology.h>
+#include <linux/cpumask.h>
+#include <asm/pgtable.h>
+#include <linux/atomic.h>
+#include <asm/proto.h>
+#include <asm/setup.h>
+#include <asm/apic.h>
+#include <asm/desc.h>
 #include <asm/i387.h>
-#include <asm/msr.h>
-#include <asm/io.h>
-#include <asm/mmu_context.h>
+#include <asm/fpu-internal.h>
 #include <asm/mtrr.h>
+#include <linux/numa.h>
+#include <asm/asm.h>
+#include <asm/cpu.h>
 #include <asm/mce.h>
+#include <asm/msr.h>
+#include <asm/pat.h>
+#include <asm/microcode.h>
+#include <asm/microcode_intel.h>
+
 #ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#include <mach_apic.h>
+#include <asm/uv/uv.h>
 #endif
 
 #include "cpu.h"
 
-DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
-	[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
-	[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
-	[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
-	[GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff200 } } },
+/* all of these masks are initialized in setup_cpu_local_masks() */
+cpumask_var_t cpu_initialized_mask;
+cpumask_var_t cpu_callout_mask;
+cpumask_var_t cpu_callin_mask;
+
+/* representing cpus for which sibling maps can be computed */
+cpumask_var_t cpu_sibling_setup_mask;
+
+/* correctly size the local cpu masks */
+void __init setup_cpu_local_masks(void)
+{
+	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
+	alloc_bootmem_cpumask_var(&cpu_callin_mask);
+	alloc_bootmem_cpumask_var(&cpu_callout_mask);
+	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+}
+
+static void default_init(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+	cpu_detect_cache_sizes(c);
+#else
+	/* Not much we can do here... */
+	/* Check if at least it has cpuid */
+	if (c->cpuid_level == -1) {
+		/* No cpuid. It must be an ancient CPU */
+		if (c->x86 == 4)
+			strcpy(c->x86_model_id, "486");
+		else if (c->x86 == 3)
+			strcpy(c->x86_model_id, "386");
+	}
+#endif
+}
+
+static const struct cpu_dev default_cpu = {
+	.c_init		= default_init,
+	.c_vendor	= "Unknown",
+	.c_x86_vendor	= X86_VENDOR_UNKNOWN,
+};
+
+static const struct cpu_dev *this_cpu = &default_cpu;
+
+DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
+#ifdef CONFIG_X86_64
+	/*
+	 * We need valid kernel segments for data and code in long mode too
+	 * IRET will check the segment types  kkeil 2000/10/28
+	 * Also sysret mandates a special GDT layout
+	 *
+	 * TLS descriptors are currently at a different place compared to i386.
+	 * Hopefully nobody expects them at a fixed place (Wine?)
+	 */
+	[GDT_ENTRY_KERNEL32_CS]		= GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER32_CS]	= GDT_ENTRY_INIT(0xc0fb, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(0xc0f3, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(0xa0fb, 0, 0xfffff),
+#else
+	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(0xc09a, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(0xc0fa, 0, 0xfffff),
+	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(0xc0f2, 0, 0xfffff),
 	/*
 	 * Segments used for calling PnP BIOS have byte granularity.
 	 * They code segments and data segments have fixed 64k limits,
 	 * the transfer segment sizes are set at run time.
 	 */
 	/* 32-bit code */
-	[GDT_ENTRY_PNPBIOS_CS32] = { { { 0x0000ffff, 0x00409a00 } } },
+	[GDT_ENTRY_PNPBIOS_CS32]	= GDT_ENTRY_INIT(0x409a, 0, 0xffff),
 	/* 16-bit code */
-	[GDT_ENTRY_PNPBIOS_CS16] = { { { 0x0000ffff, 0x00009a00 } } },
+	[GDT_ENTRY_PNPBIOS_CS16]	= GDT_ENTRY_INIT(0x009a, 0, 0xffff),
 	/* 16-bit data */
-	[GDT_ENTRY_PNPBIOS_DS] = { { { 0x0000ffff, 0x00009200 } } },
+	[GDT_ENTRY_PNPBIOS_DS]		= GDT_ENTRY_INIT(0x0092, 0, 0xffff),
 	/* 16-bit data */
-	[GDT_ENTRY_PNPBIOS_TS1] = { { { 0x00000000, 0x00009200 } } },
+	[GDT_ENTRY_PNPBIOS_TS1]		= GDT_ENTRY_INIT(0x0092, 0, 0),
 	/* 16-bit data */
-	[GDT_ENTRY_PNPBIOS_TS2] = { { { 0x00000000, 0x00009200 } } },
+	[GDT_ENTRY_PNPBIOS_TS2]		= GDT_ENTRY_INIT(0x0092, 0, 0),
 	/*
 	 * The APM segments have byte granularity and their bases
 	 * are set at run time.  All have 64k limits.
 	 */
 	/* 32-bit code */
-	[GDT_ENTRY_APMBIOS_BASE] = { { { 0x0000ffff, 0x00409a00 } } },
+	[GDT_ENTRY_APMBIOS_BASE]	= GDT_ENTRY_INIT(0x409a, 0, 0xffff),
 	/* 16-bit code */
-	[GDT_ENTRY_APMBIOS_BASE+1] = { { { 0x0000ffff, 0x00009a00 } } },
+	[GDT_ENTRY_APMBIOS_BASE+1]	= GDT_ENTRY_INIT(0x009a, 0, 0xffff),
 	/* data */
-	[GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } },
+	[GDT_ENTRY_APMBIOS_BASE+2]	= GDT_ENTRY_INIT(0x4092, 0, 0xffff),
 
-	[GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
-	[GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } },
+	[GDT_ENTRY_ESPFIX_SS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
+	[GDT_ENTRY_PERCPU]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
+	GDT_STACK_CANARY_INIT
+#endif
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+static int __init x86_xsave_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_AVX);
+	setup_clear_cpu_cap(X86_FEATURE_AVX2);
+	return 1;
+}
+__setup("noxsave", x86_xsave_setup);
+
+static int __init x86_xsaveopt_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	return 1;
+}
+__setup("noxsaveopt", x86_xsaveopt_setup);
 
-static int cachesize_override __cpuinitdata = -1;
-static int disable_x86_serial_nr __cpuinitdata = 1;
+#ifdef CONFIG_X86_32
+static int cachesize_override = -1;
+static int disable_x86_serial_nr = 1;
 
-struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {};
+static int __init cachesize_setup(char *str)
+{
+	get_option(&str, &cachesize_override);
+	return 1;
+}
+__setup("cachesize=", cachesize_setup);
 
-static void __cpuinit default_init(struct cpuinfo_x86 * c)
+static int __init x86_fxsr_setup(char *s)
 {
-	/* Not much we can do here... */
-	/* Check if at least it has cpuid */
-	if (c->cpuid_level == -1) {
-		/* No cpuid. It must be an ancient CPU */
-		if (c->x86 == 4)
-			strcpy(c->x86_model_id, "486");
-		else if (c->x86 == 3)
-			strcpy(c->x86_model_id, "386");
+	setup_clear_cpu_cap(X86_FEATURE_FXSR);
+	setup_clear_cpu_cap(X86_FEATURE_XMM);
+	return 1;
+}
+__setup("nofxsr", x86_fxsr_setup);
+
+static int __init x86_sep_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_SEP);
+	return 1;
+}
+__setup("nosep", x86_sep_setup);
+
+/* Standard macro to see if a specific flag is changeable */
+static inline int flag_is_changeable_p(u32 flag)
+{
+	u32 f1, f2;
+
+	/*
+	 * Cyrix and IDT cpus allow disabling of CPUID
+	 * so the code below may return different results
+	 * when it is executed before and after enabling
+	 * the CPUID. Add "volatile" to not allow gcc to
+	 * optimize the subsequent calls to this function.
+	 */
+	asm volatile ("pushfl		\n\t"
+		      "pushfl		\n\t"
+		      "popl %0		\n\t"
+		      "movl %0, %1	\n\t"
+		      "xorl %2, %0	\n\t"
+		      "pushl %0		\n\t"
+		      "popfl		\n\t"
+		      "pushfl		\n\t"
+		      "popl %0		\n\t"
+		      "popfl		\n\t"
+
+		      : "=&r" (f1), "=&r" (f2)
+		      : "ir" (flag));
+
+	return ((f1^f2) & flag) != 0;
+}
+
+/* Probe for the CPUID instruction */
+int have_cpuid_p(void)
+{
+	return flag_is_changeable_p(X86_EFLAGS_ID);
+}
+
+static void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+{
+	unsigned long lo, hi;
+
+	if (!cpu_has(c, X86_FEATURE_PN) || !disable_x86_serial_nr)
+		return;
+
+	/* Disable processor serial number: */
+
+	rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
+	lo |= 0x200000;
+	wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
+
+	printk(KERN_NOTICE "CPU serial number disabled.\n");
+	clear_cpu_cap(c, X86_FEATURE_PN);
+
+	/* Disabling the serial number may affect the cpuid level */
+	c->cpuid_level = cpuid_eax(0);
+}
+
+static int __init x86_serial_nr_setup(char *s)
+{
+	disable_x86_serial_nr = 0;
+	return 1;
+}
+__setup("serialnumber", x86_serial_nr_setup);
+#else
+static inline int flag_is_changeable_p(u32 flag)
+{
+	return 1;
+}
+static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+{
+}
+#endif
+
+static __init int setup_disable_smep(char *arg)
+{
+	setup_clear_cpu_cap(X86_FEATURE_SMEP);
+	return 1;
+}
+__setup("nosmep", setup_disable_smep);
+
+static __always_inline void setup_smep(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_SMEP))
+		set_in_cr4(X86_CR4_SMEP);
+}
+
+static __init int setup_disable_smap(char *arg)
+{
+	setup_clear_cpu_cap(X86_FEATURE_SMAP);
+	return 1;
+}
+__setup("nosmap", setup_disable_smap);
+
+static __always_inline void setup_smap(struct cpuinfo_x86 *c)
+{
+	unsigned long eflags;
+
+	/* This should have been cleared long ago */
+	raw_local_save_flags(eflags);
+	BUG_ON(eflags & X86_EFLAGS_AC);
+
+	if (cpu_has(c, X86_FEATURE_SMAP)) {
+#ifdef CONFIG_X86_SMAP
+		set_in_cr4(X86_CR4_SMAP);
+#else
+		clear_in_cr4(X86_CR4_SMAP);
+#endif
 	}
 }
 
-static struct cpu_dev __cpuinitdata default_cpu = {
-	.c_init	= default_init,
-	.c_vendor = "Unknown",
+/*
+ * Some CPU features depend on higher CPUID levels, which may not always
+ * be available due to CPUID level capping or broken virtualization
+ * software.  Add those features to this table to auto-disable them.
+ */
+struct cpuid_dependent_feature {
+	u32 feature;
+	u32 level;
 };
-static struct cpu_dev * this_cpu __cpuinitdata = &default_cpu;
 
-static int __init cachesize_setup(char *str)
+static const struct cpuid_dependent_feature
+cpuid_dependent_features[] = {
+	{ X86_FEATURE_MWAIT,		0x00000005 },
+	{ X86_FEATURE_DCA,		0x00000009 },
+	{ X86_FEATURE_XSAVE,		0x0000000d },
+	{ 0, 0 }
+};
+
+static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
 {
-	get_option (&str, &cachesize_override);
-	return 1;
+	const struct cpuid_dependent_feature *df;
+
+	for (df = cpuid_dependent_features; df->feature; df++) {
+
+		if (!cpu_has(c, df->feature))
+			continue;
+		/*
+		 * Note: cpuid_level is set to -1 if unavailable, but
+		 * extended_extended_level is set to 0 if unavailable
+		 * and the legitimate extended levels are all negative
+		 * when signed; hence the weird messing around with
+		 * signs here...
+		 */
+		if (!((s32)df->level < 0 ?
+		     (u32)df->level > (u32)c->extended_cpuid_level :
+		     (s32)df->level > (s32)c->cpuid_level))
+			continue;
+
+		clear_cpu_cap(c, df->feature);
+		if (!warn)
+			continue;
+
+		printk(KERN_WARNING
+		       "CPU: CPU feature %s disabled, no CPUID level 0x%x\n",
+				x86_cap_flags[df->feature], df->level);
+	}
+}
+
+/*
+ * Naming convention should be: <Name> [(<Codename>)]
+ * This table only is used unless init_<vendor>() below doesn't set it;
+ * in particular, if CPUID levels 0x80000002..4 are supported, this
+ * isn't used
+ */
+
+/* Look up CPU names by table lookup. */
+static const char *table_lookup_model(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_32
+	const struct legacy_cpu_model_info *info;
+
+	if (c->x86_model >= 16)
+		return NULL;	/* Range check */
+
+	if (!this_cpu)
+		return NULL;
+
+	info = this_cpu->legacy_models;
+
+	while (info->family) {
+		if (info->family == c->x86)
+			return info->model_names[c->x86_model];
+		info++;
+	}
+#endif
+	return NULL;		/* Not found */
 }
-__setup("cachesize=", cachesize_setup);
 
-int __cpuinit get_model_name(struct cpuinfo_x86 *c)
+__u32 cpu_caps_cleared[NCAPINTS];
+__u32 cpu_caps_set[NCAPINTS];
+
+void load_percpu_segment(int cpu)
+{
+#ifdef CONFIG_X86_32
+	loadsegment(fs, __KERNEL_PERCPU);
+#else
+	loadsegment(gs, 0);
+	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
+#endif
+	load_stack_canary_segment();
+}
+
+/*
+ * Current gdt points %fs at the "master" per-cpu area: after this,
+ * it's on the real one.
+ */
+void switch_to_new_gdt(int cpu)
+{
+	struct desc_ptr gdt_descr;
+
+	gdt_descr.address = (long)get_cpu_gdt_table(cpu);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+	/* Reload the per-cpu base */
+
+	load_percpu_segment(cpu);
+}
+
+static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
+
+static void get_model_name(struct cpuinfo_x86 *c)
 {
 	unsigned int *v;
 	char *p, *q;
 
-	if (cpuid_eax(0x80000000) < 0x80000004)
-		return 0;
+	if (c->extended_cpuid_level < 0x80000004)
+		return;
 
-	v = (unsigned int *) c->x86_model_id;
+	v = (unsigned int *)c->x86_model_id;
 	cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
 	cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
 	cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
 	c->x86_model_id[48] = 0;
 
-	/* Intel chips right-justify this string for some dumb reason;
-	   undo that brain damage */
+	/*
+	 * Intel chips right-justify this string for some dumb reason;
+	 * undo that brain damage:
+	 */
 	p = q = &c->x86_model_id[0];
-	while ( *p == ' ' )
-	     p++;
-	if ( p != q ) {
-	     while ( *p )
-		  *q++ = *p++;
-	     while ( q <= &c->x86_model_id[48] )
-		  *q++ = '\0';	/* Zero-pad the rest */
+	while (*p == ' ')
+		p++;
+	if (p != q) {
+		while (*p)
+			*q++ = *p++;
+		while (q <= &c->x86_model_id[48])
+			*q++ = '\0';	/* Zero-pad the rest */
 	}
-
-	return 1;
 }
 
-
-void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
+void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 {
-	unsigned int n, dummy, ecx, edx, l2size;
+	unsigned int n, dummy, ebx, ecx, edx, l2size;
 
-	n = cpuid_eax(0x80000000);
+	n = c->extended_cpuid_level;
 
 	if (n >= 0x80000005) {
-		cpuid(0x80000005, &dummy, &dummy, &ecx, &edx);
-		printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n",
-			edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
-		c->x86_cache_size=(ecx>>24)+(edx>>24);	
+		cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
+		c->x86_cache_size = (ecx>>24) + (edx>>24);
+#ifdef CONFIG_X86_64
+		/* On K8 L1 TLB is inclusive, so don't count it */
+		c->x86_tlbsize = 0;
+#endif
 	}
 
 	if (n < 0x80000006)	/* Some chips just has a large L1. */
 		return;
 
-	ecx = cpuid_ecx(0x80000006);
+	cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
 	l2size = ecx >> 16;
-	
+
+#ifdef CONFIG_X86_64
+	c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
+#else
 	/* do processor-specific cache resizing */
-	if (this_cpu->c_size_cache)
-		l2size = this_cpu->c_size_cache(c,l2size);
+	if (this_cpu->legacy_cache_size)
+		l2size = this_cpu->legacy_cache_size(c, l2size);
 
 	/* Allow user to override all this if necessary. */
 	if (cachesize_override != -1)
 		l2size = cachesize_override;
 
-	if ( l2size == 0 )
+	if (l2size == 0)
 		return;		/* Again, no L2 cache is possible */
+#endif
 
 	c->x86_cache_size = l2size;
-
-	printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
-	       l2size, ecx & 0xFF);
 }
 
-/* Naming convention should be: <Name> [(<Codename>)] */
-/* This table only is used unless init_<vendor>() below doesn't set it; */
-/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */
+u16 __read_mostly tlb_lli_4k[NR_INFO];
+u16 __read_mostly tlb_lli_2m[NR_INFO];
+u16 __read_mostly tlb_lli_4m[NR_INFO];
+u16 __read_mostly tlb_lld_4k[NR_INFO];
+u16 __read_mostly tlb_lld_2m[NR_INFO];
+u16 __read_mostly tlb_lld_4m[NR_INFO];
+u16 __read_mostly tlb_lld_1g[NR_INFO];
 
-/* Look up CPU names by table lookup. */
-static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
+/*
+ * tlb_flushall_shift shows the balance point in replacing cr3 write
+ * with multiple 'invlpg'. It will do this replacement when
+ *   flush_tlb_lines <= active_lines/2^tlb_flushall_shift.
+ * If tlb_flushall_shift is -1, means the replacement will be disabled.
+ */
+s8  __read_mostly tlb_flushall_shift = -1;
+
+void cpu_detect_tlb(struct cpuinfo_x86 *c)
 {
-	struct cpu_model_info *info;
+	if (this_cpu->c_detect_tlb)
+		this_cpu->c_detect_tlb(c);
+
+	printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n"
+		"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n"
+		"tlb_flushall_shift: %d\n",
+		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
+		tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
+		tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
+		tlb_lld_1g[ENTRIES], tlb_flushall_shift);
+}
 
-	if ( c->x86_model >= 16 )
-		return NULL;	/* Range check */
+void detect_ht(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_HT
+	u32 eax, ebx, ecx, edx;
+	int index_msb, core_bits;
+	static bool printed;
 
-	if (!this_cpu)
-		return NULL;
+	if (!cpu_has(c, X86_FEATURE_HT))
+		return;
 
-	info = this_cpu->c_models;
+	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
+		goto out;
 
-	while (info && info->family) {
-		if (info->family == c->x86)
-			return info->model_names[c->x86_model];
-		info++;
-	}
-	return NULL;		/* Not found */
-}
+	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
+		return;
 
+	cpuid(1, &eax, &ebx, &ecx, &edx);
 
-static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early)
-{
-	char *v = c->x86_vendor_id;
-	int i;
-	static int printed;
+	smp_num_siblings = (ebx & 0xff0000) >> 16;
 
-	for (i = 0; i < X86_VENDOR_NUM; i++) {
-		if (cpu_devs[i]) {
-			if (!strcmp(v,cpu_devs[i]->c_ident[0]) ||
-			    (cpu_devs[i]->c_ident[1] && 
-			     !strcmp(v,cpu_devs[i]->c_ident[1]))) {
-				c->x86_vendor = i;
-				if (!early)
-					this_cpu = cpu_devs[i];
-				return;
-			}
-		}
-	}
-	if (!printed) {
-		printed++;
-		printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n");
-		printk(KERN_ERR "CPU: Your system may be unstable.\n");
+	if (smp_num_siblings == 1) {
+		printk_once(KERN_INFO "CPU0: Hyper-Threading is disabled\n");
+		goto out;
 	}
-	c->x86_vendor = X86_VENDOR_UNKNOWN;
-	this_cpu = &default_cpu;
-}
 
+	if (smp_num_siblings <= 1)
+		goto out;
 
-static int __init x86_fxsr_setup(char * s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FXSR);
-	setup_clear_cpu_cap(X86_FEATURE_XMM);
-	return 1;
-}
-__setup("nofxsr", x86_fxsr_setup);
+	index_msb = get_count_order(smp_num_siblings);
+	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
 
+	smp_num_siblings = smp_num_siblings / c->x86_max_cores;
 
-static int __init x86_sep_setup(char * s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_SEP);
-	return 1;
-}
-__setup("nosep", x86_sep_setup);
+	index_msb = get_count_order(smp_num_siblings);
 
+	core_bits = get_count_order(c->x86_max_cores);
 
-/* Standard macro to see if a specific flag is changeable */
-static inline int flag_is_changeable_p(u32 flag)
+	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
+				       ((1 << core_bits) - 1);
+
+out:
+	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
+		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
+		       c->phys_proc_id);
+		printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
+		       c->cpu_core_id);
+		printed = 1;
+	}
+#endif
+}
+
+static void get_cpu_vendor(struct cpuinfo_x86 *c)
 {
-	u32 f1, f2;
+	char *v = c->x86_vendor_id;
+	int i;
 
-	asm("pushfl\n\t"
-	    "pushfl\n\t"
-	    "popl %0\n\t"
-	    "movl %0,%1\n\t"
-	    "xorl %2,%0\n\t"
-	    "pushl %0\n\t"
-	    "popfl\n\t"
-	    "pushfl\n\t"
-	    "popl %0\n\t"
-	    "popfl\n\t"
-	    : "=&r" (f1), "=&r" (f2)
-	    : "ir" (flag));
+	for (i = 0; i < X86_VENDOR_NUM; i++) {
+		if (!cpu_devs[i])
+			break;
 
-	return ((f1^f2) & flag) != 0;
-}
+		if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
+		    (cpu_devs[i]->c_ident[1] &&
+		     !strcmp(v, cpu_devs[i]->c_ident[1]))) {
 
+			this_cpu = cpu_devs[i];
+			c->x86_vendor = this_cpu->c_x86_vendor;
+			return;
+		}
+	}
 
-/* Probe for the CPUID instruction */
-static int __cpuinit have_cpuid_p(void)
-{
-	return flag_is_changeable_p(X86_EFLAGS_ID);
+	printk_once(KERN_ERR
+			"CPU: vendor_id '%s' unknown, using generic init.\n" \
+			"CPU: Your system may be unstable.\n", v);
+
+	c->x86_vendor = X86_VENDOR_UNKNOWN;
+	this_cpu = &default_cpu;
 }
 
-void __init cpu_detect(struct cpuinfo_x86 *c)
+void cpu_detect(struct cpuinfo_x86 *c)
 {
 	/* Get vendor name */
 	cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
@@ -264,199 +590,281 @@ void __init cpu_detect(struct cpuinfo_x86 *c)
 	      (unsigned int *)&c->x86_vendor_id[4]);
 
 	c->x86 = 4;
+	/* Intel-defined flags: level 0x00000001 */
 	if (c->cpuid_level >= 0x00000001) {
 		u32 junk, tfms, cap0, misc;
+
 		cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
-		c->x86 = (tfms >> 8) & 15;
-		c->x86_model = (tfms >> 4) & 15;
+		c->x86 = (tfms >> 8) & 0xf;
+		c->x86_model = (tfms >> 4) & 0xf;
+		c->x86_mask = tfms & 0xf;
+
 		if (c->x86 == 0xf)
 			c->x86 += (tfms >> 20) & 0xff;
 		if (c->x86 >= 0x6)
-			c->x86_model += ((tfms >> 16) & 0xF) << 4;
-		c->x86_mask = tfms & 15;
+			c->x86_model += ((tfms >> 16) & 0xf) << 4;
+
 		if (cap0 & (1<<19)) {
-			c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
 			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
+			c->x86_cache_alignment = c->x86_clflush_size;
 		}
 	}
 }
-static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
+
+void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 tfms, xlvl;
-	unsigned int ebx;
+	u32 ebx;
 
-	memset(&c->x86_capability, 0, sizeof c->x86_capability);
-	if (have_cpuid_p()) {
-		/* Intel-defined flags: level 0x00000001 */
-		if (c->cpuid_level >= 0x00000001) {
-			u32 capability, excap;
-			cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
-			c->x86_capability[0] = capability;
-			c->x86_capability[4] = excap;
-		}
+	/* Intel-defined flags: level 0x00000001 */
+	if (c->cpuid_level >= 0x00000001) {
+		u32 capability, excap;
 
-		/* AMD-defined flags: level 0x80000001 */
-		xlvl = cpuid_eax(0x80000000);
-		if ((xlvl & 0xffff0000) == 0x80000000) {
-			if (xlvl >= 0x80000001) {
-				c->x86_capability[1] = cpuid_edx(0x80000001);
-				c->x86_capability[6] = cpuid_ecx(0x80000001);
-			}
+		cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
+		c->x86_capability[0] = capability;
+		c->x86_capability[4] = excap;
+	}
+
+	/* Additional Intel-defined flags: level 0x00000007 */
+	if (c->cpuid_level >= 0x00000007) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
+
+		c->x86_capability[9] = ebx;
+	}
+
+	/* AMD-defined flags: level 0x80000001 */
+	xlvl = cpuid_eax(0x80000000);
+	c->extended_cpuid_level = xlvl;
+
+	if ((xlvl & 0xffff0000) == 0x80000000) {
+		if (xlvl >= 0x80000001) {
+			c->x86_capability[1] = cpuid_edx(0x80000001);
+			c->x86_capability[6] = cpuid_ecx(0x80000001);
 		}
+	}
 
+	if (c->extended_cpuid_level >= 0x80000008) {
+		u32 eax = cpuid_eax(0x80000008);
+
+		c->x86_virt_bits = (eax >> 8) & 0xff;
+		c->x86_phys_bits = eax & 0xff;
 	}
+#ifdef CONFIG_X86_32
+	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
+		c->x86_phys_bits = 36;
+#endif
 
-}
+	if (c->extended_cpuid_level >= 0x80000007)
+		c->x86_power = cpuid_edx(0x80000007);
 
-/* Do minimum CPU detection early.
-   Fields really needed: vendor, cpuid_level, family, model, mask, cache alignment.
-   The others are not touched to avoid unwanted side effects.
+	init_scattered_cpuid_features(c);
+}
 
-   WARNING: this function is only called on the BP.  Don't add code here
-   that is supposed to run on all CPUs. */
-static void __init early_cpu_detect(void)
+static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 {
-	struct cpuinfo_x86 *c = &boot_cpu_data;
+#ifdef CONFIG_X86_32
+	int i;
+
+	/*
+	 * First of all, decide if this is a 486 or higher
+	 * It's a 486 if we can modify the AC flag
+	 */
+	if (flag_is_changeable_p(X86_EFLAGS_AC))
+		c->x86 = 4;
+	else
+		c->x86 = 3;
+
+	for (i = 0; i < X86_VENDOR_NUM; i++)
+		if (cpu_devs[i] && cpu_devs[i]->c_identify) {
+			c->x86_vendor_id[0] = 0;
+			cpu_devs[i]->c_identify(c);
+			if (c->x86_vendor_id[0]) {
+				get_cpu_vendor(c);
+				break;
+			}
+		}
+#endif
+}
 
-	c->x86_cache_alignment = 32;
+/*
+ * Do minimum CPU detection early.
+ * Fields really needed: vendor, cpuid_level, family, model, mask,
+ * cache alignment.
+ * The others are not touched to avoid unwanted side effects.
+ *
+ * WARNING: this function is only called on the BP.  Don't add code here
+ * that is supposed to run on all CPUs.
+ */
+static void __init early_identify_cpu(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+	c->x86_clflush_size = 64;
+	c->x86_phys_bits = 36;
+	c->x86_virt_bits = 48;
+#else
 	c->x86_clflush_size = 32;
+	c->x86_phys_bits = 32;
+	c->x86_virt_bits = 32;
+#endif
+	c->x86_cache_alignment = c->x86_clflush_size;
+
+	memset(&c->x86_capability, 0, sizeof c->x86_capability);
+	c->extended_cpuid_level = 0;
 
 	if (!have_cpuid_p())
+		identify_cpu_without_cpuid(c);
+
+	/* cyrix could have cpuid enabled via c_identify()*/
+	if (!have_cpuid_p())
 		return;
 
 	cpu_detect(c);
+	get_cpu_vendor(c);
+	get_cpu_cap(c);
+	fpu_detect(c);
 
-	get_cpu_vendor(c, 1);
+	if (this_cpu->c_early_init)
+		this_cpu->c_early_init(c);
 
-	switch (c->x86_vendor) {
-	case X86_VENDOR_AMD:
-		early_init_amd(c);
-		break;
-	case X86_VENDOR_INTEL:
-		early_init_intel(c);
-		break;
-	}
+	c->cpu_index = 0;
+	filter_cpuid_features(c, false);
+
+	if (this_cpu->c_bsp_init)
+		this_cpu->c_bsp_init(c);
 
-	early_get_cap(c);
+	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 }
 
-static void __cpuinit generic_identify(struct cpuinfo_x86 * c)
+void __init early_cpu_init(void)
 {
-	u32 tfms, xlvl;
-	unsigned int ebx;
-
-	if (have_cpuid_p()) {
-		/* Get vendor name */
-		cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
-		      (unsigned int *)&c->x86_vendor_id[0],
-		      (unsigned int *)&c->x86_vendor_id[8],
-		      (unsigned int *)&c->x86_vendor_id[4]);
-		
-		get_cpu_vendor(c, 0);
-		/* Initialize the standard set of capabilities */
-		/* Note that the vendor-specific code below might override */
-	
-		/* Intel-defined flags: level 0x00000001 */
-		if ( c->cpuid_level >= 0x00000001 ) {
-			u32 capability, excap;
-			cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
-			c->x86_capability[0] = capability;
-			c->x86_capability[4] = excap;
-			c->x86 = (tfms >> 8) & 15;
-			c->x86_model = (tfms >> 4) & 15;
-			if (c->x86 == 0xf)
-				c->x86 += (tfms >> 20) & 0xff;
-			if (c->x86 >= 0x6)
-				c->x86_model += ((tfms >> 16) & 0xF) << 4;
-			c->x86_mask = tfms & 15;
-#ifdef CONFIG_X86_HT
-			c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0);
-#else
-			c->apicid = (ebx >> 24) & 0xFF;
+	const struct cpu_dev *const *cdev;
+	int count = 0;
+
+#ifdef CONFIG_PROCESSOR_SELECT
+	printk(KERN_INFO "KERNEL supported cpus:\n");
 #endif
-			if (c->x86_capability[0] & (1<<19))
-				c->x86_clflush_size = ((ebx >> 8) & 0xff) * 8;
-		} else {
-			/* Have CPUID level 0 only - unheard of */
-			c->x86 = 4;
-		}
 
-		/* AMD-defined flags: level 0x80000001 */
-		xlvl = cpuid_eax(0x80000000);
-		if ( (xlvl & 0xffff0000) == 0x80000000 ) {
-			if ( xlvl >= 0x80000001 ) {
-				c->x86_capability[1] = cpuid_edx(0x80000001);
-				c->x86_capability[6] = cpuid_ecx(0x80000001);
+	for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
+		const struct cpu_dev *cpudev = *cdev;
+
+		if (count >= X86_VENDOR_NUM)
+			break;
+		cpu_devs[count] = cpudev;
+		count++;
+
+#ifdef CONFIG_PROCESSOR_SELECT
+		{
+			unsigned int j;
+
+			for (j = 0; j < 2; j++) {
+				if (!cpudev->c_ident[j])
+					continue;
+				printk(KERN_INFO "  %s %s\n", cpudev->c_vendor,
+					cpudev->c_ident[j]);
 			}
-			if ( xlvl >= 0x80000004 )
-				get_model_name(c); /* Default name */
 		}
-
-		init_scattered_cpuid_features(c);
+#endif
 	}
+	early_identify_cpu(&boot_cpu_data);
+}
 
-#ifdef CONFIG_X86_HT
-	c->phys_proc_id = (cpuid_ebx(1) >> 24) & 0xff;
+/*
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
+ * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
+ */
+static void detect_nopl(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_32
+	clear_cpu_cap(c, X86_FEATURE_NOPL);
+#else
+	set_cpu_cap(c, X86_FEATURE_NOPL);
 #endif
 }
 
-static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+static void generic_identify(struct cpuinfo_x86 *c)
 {
-	if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr ) {
-		/* Disable processor serial number */
-		unsigned long lo,hi;
-		rdmsr(MSR_IA32_BBL_CR_CTL,lo,hi);
-		lo |= 0x200000;
-		wrmsr(MSR_IA32_BBL_CR_CTL,lo,hi);
-		printk(KERN_NOTICE "CPU serial number disabled.\n");
-		clear_bit(X86_FEATURE_PN, c->x86_capability);
+	c->extended_cpuid_level = 0;
 
-		/* Disabling the serial number may affect the cpuid level */
-		c->cpuid_level = cpuid_eax(0);
-	}
-}
+	if (!have_cpuid_p())
+		identify_cpu_without_cpuid(c);
 
-static int __init x86_serial_nr_setup(char *s)
-{
-	disable_x86_serial_nr = 0;
-	return 1;
-}
-__setup("serialnumber", x86_serial_nr_setup);
+	/* cyrix could have cpuid enabled via c_identify()*/
+	if (!have_cpuid_p())
+		return;
+
+	cpu_detect(c);
+
+	get_cpu_vendor(c);
+
+	get_cpu_cap(c);
 
+	if (c->cpuid_level >= 0x00000001) {
+		c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_X86_HT
+		c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+# else
+		c->apicid = c->initial_apicid;
+# endif
+#endif
+		c->phys_proc_id = c->initial_apicid;
+	}
+
+	get_model_name(c); /* Default name */
 
+	detect_nopl(c);
+}
 
 /*
  * This does the hard work of actually picking apart the CPU stuff...
  */
-void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
+static void identify_cpu(struct cpuinfo_x86 *c)
 {
 	int i;
 
 	c->loops_per_jiffy = loops_per_jiffy;
 	c->x86_cache_size = -1;
 	c->x86_vendor = X86_VENDOR_UNKNOWN;
-	c->cpuid_level = -1;	/* CPUID not detected */
 	c->x86_model = c->x86_mask = 0;	/* So far unknown... */
 	c->x86_vendor_id[0] = '\0'; /* Unset */
 	c->x86_model_id[0] = '\0';  /* Unset */
 	c->x86_max_cores = 1;
+	c->x86_coreid_bits = 0;
+#ifdef CONFIG_X86_64
+	c->x86_clflush_size = 64;
+	c->x86_phys_bits = 36;
+	c->x86_virt_bits = 48;
+#else
+	c->cpuid_level = -1;	/* CPUID not detected */
 	c->x86_clflush_size = 32;
+	c->x86_phys_bits = 32;
+	c->x86_virt_bits = 32;
+#endif
+	c->x86_cache_alignment = c->x86_clflush_size;
 	memset(&c->x86_capability, 0, sizeof c->x86_capability);
 
-	if (!have_cpuid_p()) {
-		/* First of all, decide if this is a 486 or higher */
-		/* It's a 486 if we can modify the AC flag */
-		if ( flag_is_changeable_p(X86_EFLAGS_AC) )
-			c->x86 = 4;
-		else
-			c->x86 = 3;
-	}
-
 	generic_identify(c);
 
 	if (this_cpu->c_identify)
 		this_cpu->c_identify(c);
 
+	/* Clear/Set all flags overriden by options, after probe */
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+
+#ifdef CONFIG_X86_64
+	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+#endif
+
 	/*
 	 * Vendor-specific initialization.  In this section we
 	 * canonicalize the feature flags, meaning if there are
@@ -473,16 +881,23 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	/* Disable the PN if appropriate */
 	squash_the_stupid_serial_number(c);
 
+	/* Set up SMEP/SMAP */
+	setup_smep(c);
+	setup_smap(c);
+
 	/*
-	 * The vendor-specific functions might have changed features.  Now
-	 * we do "generic changes."
+	 * The vendor-specific functions might have changed features.
+	 * Now we do "generic changes."
 	 */
 
+	/* Filter out anything that depends on CPUID levels we don't have */
+	filter_cpuid_features(c, true);
+
 	/* If the model name is still unset, do table lookup. */
-	if ( !c->x86_model_id[0] ) {
-		char *p;
+	if (!c->x86_model_id[0]) {
+		const char *p;
 		p = table_lookup_model(c);
-		if ( p )
+		if (p)
 			strcpy(c->x86_model_id, p);
 		else
 			/* Last resort... */
@@ -490,188 +905,480 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 				c->x86, c->x86_model);
 	}
 
+#ifdef CONFIG_X86_64
+	detect_ht(c);
+#endif
+
+	init_hypervisor(c);
+	x86_init_rdrand(c);
+
+	/*
+	 * Clear/Set all flags overriden by options, need do it
+	 * before following smp all cpus cap AND.
+	 */
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between
 	 * all CPUs; so make sure that we indicate which features are
 	 * common between the CPUs.  The first time this routine gets
 	 * executed, c == &boot_cpu_data.
 	 */
-	if ( c != &boot_cpu_data ) {
+	if (c != &boot_cpu_data) {
 		/* AND the already accumulated flags with these */
-		for ( i = 0 ; i < NCAPINTS ; i++ )
+		for (i = 0; i < NCAPINTS; i++)
 			boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
-	}
 
-	/* Clear all flags overriden by options */
-	for (i = 0; i < NCAPINTS; i++)
-		c->x86_capability[i] &= ~cleared_cpu_caps[i];
+		/* OR, i.e. replicate the bug flags */
+		for (i = NCAPINTS; i < NCAPINTS + NBUGINTS; i++)
+			c->x86_capability[i] |= boot_cpu_data.x86_capability[i];
+	}
 
 	/* Init Machine Check Exception if available. */
-	mcheck_init(c);
+	mcheck_cpu_init(c);
 
 	select_idle_routine(c);
+
+#ifdef CONFIG_NUMA
+	numa_add_cpu(smp_processor_id());
+#endif
+}
+
+#ifdef CONFIG_X86_64
+static void vgetcpu_set_mode(void)
+{
+	if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
+		vgetcpu_mode = VGETCPU_RDTSCP;
+	else
+		vgetcpu_mode = VGETCPU_LSL;
+}
+
+/* May not be __init: called during resume */
+static void syscall32_cpu_init(void)
+{
+	/* Load these always in case some future AMD CPU supports
+	   SYSENTER from compat mode too. */
+	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+
+	wrmsrl(MSR_CSTAR, ia32_cstar_target);
 }
+#endif
+
+#ifdef CONFIG_X86_32
+void enable_sep_cpu(void)
+{
+	int cpu = get_cpu();
+	struct tss_struct *tss = &per_cpu(init_tss, cpu);
+
+	if (!boot_cpu_has(X86_FEATURE_SEP)) {
+		put_cpu();
+		return;
+	}
+
+	tss->x86_tss.ss1 = __KERNEL_CS;
+	tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss;
+	wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
+	wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0);
+	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0);
+	put_cpu();
+}
+#endif
 
 void __init identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
+	init_amd_e400_c1e_mask();
+#ifdef CONFIG_X86_32
 	sysenter_setup();
 	enable_sep_cpu();
+#else
+	vgetcpu_set_mode();
+#endif
+	cpu_detect_tlb(&boot_cpu_data);
 }
 
-void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
+void identify_secondary_cpu(struct cpuinfo_x86 *c)
 {
 	BUG_ON(c == &boot_cpu_data);
 	identify_cpu(c);
+#ifdef CONFIG_X86_32
 	enable_sep_cpu();
+#endif
 	mtrr_ap_init();
 }
 
-#ifdef CONFIG_X86_HT
-void __cpuinit detect_ht(struct cpuinfo_x86 *c)
-{
-	u32 	eax, ebx, ecx, edx;
-	int 	index_msb, core_bits;
-
-	cpuid(1, &eax, &ebx, &ecx, &edx);
+struct msr_range {
+	unsigned	min;
+	unsigned	max;
+};
 
-	if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		return;
+static const struct msr_range msr_range_array[] = {
+	{ 0x00000000, 0x00000418},
+	{ 0xc0000000, 0xc000040b},
+	{ 0xc0010000, 0xc0010142},
+	{ 0xc0011000, 0xc001103b},
+};
 
-	smp_num_siblings = (ebx & 0xff0000) >> 16;
+static void __print_cpu_msr(void)
+{
+	unsigned index_min, index_max;
+	unsigned index;
+	u64 val;
+	int i;
 
-	if (smp_num_siblings == 1) {
-		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
-	} else if (smp_num_siblings > 1 ) {
+	for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) {
+		index_min = msr_range_array[i].min;
+		index_max = msr_range_array[i].max;
 
-		if (smp_num_siblings > NR_CPUS) {
-			printk(KERN_WARNING "CPU: Unsupported number of the "
-					"siblings %d", smp_num_siblings);
-			smp_num_siblings = 1;
-			return;
+		for (index = index_min; index < index_max; index++) {
+			if (rdmsrl_safe(index, &val))
+				continue;
+			printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
 		}
+	}
+}
 
-		index_msb = get_count_order(smp_num_siblings);
-		c->phys_proc_id = phys_pkg_id((ebx >> 24) & 0xFF, index_msb);
-
-		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
-		       c->phys_proc_id);
-
-		smp_num_siblings = smp_num_siblings / c->x86_max_cores;
-
-		index_msb = get_count_order(smp_num_siblings) ;
+static int show_msr;
 
-		core_bits = get_count_order(c->x86_max_cores);
+static __init int setup_show_msr(char *arg)
+{
+	int num;
 
-		c->cpu_core_id = phys_pkg_id((ebx >> 24) & 0xFF, index_msb) &
-					       ((1 << core_bits) - 1);
+	get_option(&arg, &num);
 
-		if (c->x86_max_cores > 1)
-			printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
-			       c->cpu_core_id);
-	}
+	if (num > 0)
+		show_msr = num;
+	return 1;
 }
-#endif
+__setup("show_msr=", setup_show_msr);
 
 static __init int setup_noclflush(char *arg)
 {
-	setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
+	setup_clear_cpu_cap(X86_FEATURE_CLFLUSH);
+	setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT);
 	return 1;
 }
 __setup("noclflush", setup_noclflush);
 
-void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
+void print_cpu_info(struct cpuinfo_x86 *c)
 {
-	char *vendor = NULL;
+	const char *vendor = NULL;
 
-	if (c->x86_vendor < X86_VENDOR_NUM)
+	if (c->x86_vendor < X86_VENDOR_NUM) {
 		vendor = this_cpu->c_vendor;
-	else if (c->cpuid_level >= 0)
-		vendor = c->x86_vendor_id;
+	} else {
+		if (c->cpuid_level >= 0)
+			vendor = c->x86_vendor_id;
+	}
 
-	if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
-		printk("%s ", vendor);
+	if (vendor && !strstr(c->x86_model_id, vendor))
+		printk(KERN_CONT "%s ", vendor);
 
-	if (!c->x86_model_id[0])
-		printk("%d86", c->x86);
+	if (c->x86_model_id[0])
+		printk(KERN_CONT "%s", strim(c->x86_model_id));
 	else
-		printk("%s", c->x86_model_id);
+		printk(KERN_CONT "%d86", c->x86);
 
-	if (c->x86_mask || c->cpuid_level >= 0) 
-		printk(" stepping %02x\n", c->x86_mask);
+	printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model);
+
+	if (c->x86_mask || c->cpuid_level >= 0)
+		printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask);
 	else
-		printk("\n");
+		printk(KERN_CONT ")\n");
+
+	print_cpu_msr(c);
+}
+
+void print_cpu_msr(struct cpuinfo_x86 *c)
+{
+	if (c->cpu_index < show_msr)
+		__print_cpu_msr();
 }
 
 static __init int setup_disablecpuid(char *arg)
 {
 	int bit;
+
 	if (get_option(&arg, &bit) && bit < NCAPINTS*32)
 		setup_clear_cpu_cap(bit);
 	else
 		return 0;
+
 	return 1;
 }
 __setup("clearcpuid=", setup_disablecpuid);
 
-cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
+DEFINE_PER_CPU(unsigned long, kernel_stack) =
+	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(kernel_stack);
+
+#ifdef CONFIG_X86_64
+struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
+struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
+				    (unsigned long) debug_idt_table };
 
-/* This is hacky. :)
- * We're emulating future behavior.
- * In the future, the cpu-specific init functions will be called implicitly
- * via the magic of initcalls.
- * They will insert themselves into the cpu_devs structure.
- * Then, when cpu_init() is called, we can just iterate over that array.
+DEFINE_PER_CPU_FIRST(union irq_stack_union,
+		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
+
+/*
+ * The following four percpu variables are hot.  Align current_task to
+ * cacheline size such that all four fall in the same cacheline.
  */
-void __init early_cpu_init(void)
+DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
+	&init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+
+DEFINE_PER_CPU(char *, irq_stack_ptr) =
+	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
+
+DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
+
+DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
+
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
+	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
+};
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+
+/* May not be marked __init: used by software suspend */
+void syscall_init(void)
 {
-	intel_cpu_init();
-	cyrix_init_cpu();
-	nsc_init_cpu();
-	amd_init_cpu();
-	centaur_init_cpu();
-	transmeta_init_cpu();
-	nexgen_init_cpu();
-	umc_init_cpu();
-	early_cpu_detect();
+	/*
+	 * LSTAR and STAR live in a bit strange symbiosis.
+	 * They both write to the same internal register. STAR allows to
+	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
+	 */
+	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
+	wrmsrl(MSR_LSTAR, system_call);
+	wrmsrl(MSR_CSTAR, ignore_sysret);
+
+#ifdef CONFIG_IA32_EMULATION
+	syscall32_cpu_init();
+#endif
+
+	/* Flags to clear on syscall */
+	wrmsrl(MSR_SYSCALL_MASK,
+	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
+	       X86_EFLAGS_IOPL|X86_EFLAGS_AC);
 }
 
-/* Make sure %fs is initialized properly in idle threads */
-struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
+/*
+ * Copies of the original ist values from the tss are only accessed during
+ * debugging, no special alignment required.
+ */
+DEFINE_PER_CPU(struct orig_ist, orig_ist);
+
+static DEFINE_PER_CPU(unsigned long, debug_stack_addr);
+DEFINE_PER_CPU(int, debug_stack_usage);
+
+int is_debug_stack(unsigned long addr)
 {
-	memset(regs, 0, sizeof(struct pt_regs));
-	regs->fs = __KERNEL_PERCPU;
-	return regs;
+	return __get_cpu_var(debug_stack_usage) ||
+		(addr <= __get_cpu_var(debug_stack_addr) &&
+		 addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
 }
+NOKPROBE_SYMBOL(is_debug_stack);
 
-/* Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one. */
-void switch_to_new_gdt(void)
+DEFINE_PER_CPU(u32, debug_idt_ctr);
+
+void debug_stack_set_zero(void)
 {
-	struct desc_ptr gdt_descr;
+	this_cpu_inc(debug_idt_ctr);
+	load_current_idt();
+}
+NOKPROBE_SYMBOL(debug_stack_set_zero);
 
-	gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
-	gdt_descr.size = GDT_SIZE - 1;
-	load_gdt(&gdt_descr);
-	asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
+void debug_stack_reset(void)
+{
+	if (WARN_ON(!this_cpu_read(debug_idt_ctr)))
+		return;
+	if (this_cpu_dec_return(debug_idt_ctr) == 0)
+		load_current_idt();
+}
+NOKPROBE_SYMBOL(debug_stack_reset);
+
+#else	/* CONFIG_X86_64 */
+
+DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
+#endif
+
+#endif	/* CONFIG_X86_64 */
+
+/*
+ * Clear all 6 debug registers:
+ */
+static void clear_all_debug_regs(void)
+{
+	int i;
+
+	for (i = 0; i < 8; i++) {
+		/* Ignore db4, db5 */
+		if ((i == 4) || (i == 5))
+			continue;
+
+		set_debugreg(0, i);
+	}
+}
+
+#ifdef CONFIG_KGDB
+/*
+ * Restore debug regs if using kgdbwait and you have a kernel debugger
+ * connection established.
+ */
+static void dbg_restore_debug_regs(void)
+{
+	if (unlikely(kgdb_connected && arch_kgdb_ops.correct_hw_break))
+		arch_kgdb_ops.correct_hw_break();
 }
+#else /* ! CONFIG_KGDB */
+#define dbg_restore_debug_regs()
+#endif /* ! CONFIG_KGDB */
 
 /*
  * cpu_init() initializes state that is per-CPU. Some data is already
  * initialized (naturally) in the bootstrap process, such as the GDT
  * and IDT. We reload them nevertheless, this function acts as a
  * 'CPU state barrier', nothing should get across.
+ * A lot of state is already set up in PDA init for 64 bit
  */
-void __cpuinit cpu_init(void)
+#ifdef CONFIG_X86_64
+
+void cpu_init(void)
+{
+	struct orig_ist *oist;
+	struct task_struct *me;
+	struct tss_struct *t;
+	unsigned long v;
+	int cpu;
+	int i;
+
+	/*
+	 * Load microcode on this cpu if a valid microcode is available.
+	 * This is early microcode loading procedure.
+	 */
+	load_ucode_ap();
+
+	cpu = stack_smp_processor_id();
+	t = &per_cpu(init_tss, cpu);
+	oist = &per_cpu(orig_ist, cpu);
+
+#ifdef CONFIG_NUMA
+	if (this_cpu_read(numa_node) == 0 &&
+	    early_cpu_to_node(cpu) != NUMA_NO_NODE)
+		set_numa_node(early_cpu_to_node(cpu));
+#endif
+
+	me = current;
+
+	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask))
+		panic("CPU#%d already initialized!\n", cpu);
+
+	pr_debug("Initializing CPU#%d\n", cpu);
+
+	clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+
+	/*
+	 * Initialize the per-CPU GDT with the boot GDT,
+	 * and set up the GDT descriptor:
+	 */
+
+	switch_to_new_gdt(cpu);
+	loadsegment(fs, 0);
+
+	load_current_idt();
+
+	memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
+	syscall_init();
+
+	wrmsrl(MSR_FS_BASE, 0);
+	wrmsrl(MSR_KERNEL_GS_BASE, 0);
+	barrier();
+
+	x86_configure_nx();
+	enable_x2apic();
+
+	/*
+	 * set up and load the per-CPU TSS
+	 */
+	if (!oist->ist[0]) {
+		char *estacks = per_cpu(exception_stacks, cpu);
+
+		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
+			estacks += exception_stack_sizes[v];
+			oist->ist[v] = t->x86_tss.ist[v] =
+					(unsigned long)estacks;
+			if (v == DEBUG_STACK-1)
+				per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks;
+		}
+	}
+
+	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+
+	/*
+	 * <= is required because the CPU will access up to
+	 * 8 bits beyond the end of the IO permission bitmap.
+	 */
+	for (i = 0; i <= IO_BITMAP_LONGS; i++)
+		t->io_bitmap[i] = ~0UL;
+
+	atomic_inc(&init_mm.mm_count);
+	me->active_mm = &init_mm;
+	BUG_ON(me->mm);
+	enter_lazy_tlb(&init_mm, me);
+
+	load_sp0(t, &current->thread);
+	set_tss_desc(cpu, t);
+	load_TR_desc();
+	load_LDT(&init_mm.context);
+
+	clear_all_debug_regs();
+	dbg_restore_debug_regs();
+
+	fpu_init();
+
+	if (is_uv_system())
+		uv_cpu_init();
+}
+
+#else
+
+void cpu_init(void)
 {
 	int cpu = smp_processor_id();
 	struct task_struct *curr = current;
-	struct tss_struct * t = &per_cpu(init_tss, cpu);
+	struct tss_struct *t = &per_cpu(init_tss, cpu);
 	struct thread_struct *thread = &curr->thread;
 
-	if (cpu_test_and_set(cpu, cpu_initialized)) {
+	show_ucode_info_early();
+
+	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) {
 		printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
-		for (;;) local_irq_enable();
+		for (;;)
+			local_irq_enable();
 	}
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
@@ -679,55 +1386,46 @@ void __cpuinit cpu_init(void)
 	if (cpu_has_vme || cpu_has_tsc || cpu_has_de)
 		clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
-	load_idt(&idt_descr);
-	switch_to_new_gdt();
+	load_current_idt();
+	switch_to_new_gdt(cpu);
 
 	/*
 	 * Set up and load the per-CPU TSS and LDT
 	 */
 	atomic_inc(&init_mm.mm_count);
 	curr->active_mm = &init_mm;
-	if (curr->mm)
-		BUG();
+	BUG_ON(curr->mm);
 	enter_lazy_tlb(&init_mm, curr);
 
 	load_sp0(t, thread);
-	set_tss_desc(cpu,t);
+	set_tss_desc(cpu, t);
 	load_TR_desc();
 	load_LDT(&init_mm.context);
 
+	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+
 #ifdef CONFIG_DOUBLEFAULT
 	/* Set up doublefault TSS pointer in the GDT */
 	__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
 #endif
 
-	/* Clear %gs. */
-	asm volatile ("mov %0, %%gs" : : "r" (0));
-
-	/* Clear all 6 debug registers: */
-	set_debugreg(0, 0);
-	set_debugreg(0, 1);
-	set_debugreg(0, 2);
-	set_debugreg(0, 3);
-	set_debugreg(0, 6);
-	set_debugreg(0, 7);
+	clear_all_debug_regs();
+	dbg_restore_debug_regs();
 
-	/*
-	 * Force FPU initialization:
-	 */
-	current_thread_info()->status = 0;
-	clear_used_math();
-	mxcsr_feature_mask_init();
+	fpu_init();
 }
+#endif
 
-#ifdef CONFIG_HOTPLUG_CPU
-void __cpuinit cpu_uninit(void)
+#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
+void warn_pre_alternatives(void)
 {
-	int cpu = raw_smp_processor_id();
-	cpu_clear(cpu, cpu_initialized);
-
-	/* lazy TLB state */
-	per_cpu(cpu_tlbstate, cpu).state = 0;
-	per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
+	WARN(1, "You're using static_cpu_has before alternatives have run!\n");
 }
+EXPORT_SYMBOL_GPL(warn_pre_alternatives);
 #endif
+
+inline bool __static_cpu_has_safe(u16 bit)
+{
+	return boot_cpu_has(bit);
+}
+EXPORT_SYMBOL_GPL(__static_cpu_has_safe);