Merge branch 'master' into for-upstream

Conflicts:

	Documentation/ABI/testing/sysfs-bus-usb
	drivers/Makefile

27 files changed, 1997 insertions, 2003 deletions

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index ee76eaad3001..7f0b45a5d788 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -3,22 +3,30 @@
 #
 
 obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
-obj-y			+= proc.o feature_names.o
-
-obj-$(CONFIG_X86_32)	+= common.o bugs.o
-obj-$(CONFIG_X86_64)	+= common_64.o bugs_64.o
-obj-$(CONFIG_X86_32)	+= amd.o
-obj-$(CONFIG_X86_64)	+= amd_64.o
-obj-$(CONFIG_X86_32)	+= cyrix.o
-obj-$(CONFIG_X86_32)	+= centaur.o
-obj-$(CONFIG_X86_64)	+= centaur_64.o
-obj-$(CONFIG_X86_32)	+= transmeta.o
-obj-$(CONFIG_X86_32)	+= intel.o
-obj-$(CONFIG_X86_64)	+= intel_64.o
-obj-$(CONFIG_X86_32)	+= umc.o
+obj-y			+= proc.o capflags.o powerflags.o common.o
+
+obj-$(CONFIG_X86_32)	+= bugs.o cmpxchg.o
+obj-$(CONFIG_X86_64)	+= bugs_64.o
+
+obj-$(CONFIG_CPU_SUP_INTEL)		+= intel.o
+obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
+obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
+obj-$(CONFIG_CPU_SUP_CENTAUR_32)	+= centaur.o
+obj-$(CONFIG_CPU_SUP_CENTAUR_64)	+= centaur_64.o
+obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
+obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
 obj-$(CONFIG_X86_MCE)	+= mcheck/
 obj-$(CONFIG_MTRR)	+= mtrr/
 obj-$(CONFIG_CPU_FREQ)	+= cpufreq/
 
 obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
+
+quiet_cmd_mkcapflags = MKCAP   $@
+      cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@
+
+cpufeature = $(src)/../../../../include/asm-x86/cpufeature.h
+
+targets += capflags.c
+$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.pl FORCE
+	$(call if_changed,mkcapflags)
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index a6ef672adbba..0d9c993aa93e 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -7,6 +7,8 @@
 #include <asm/pat.h>
 #include <asm/processor.h>
 
+#include <mach_apic.h>
+
 struct cpuid_bit {
 	u16 feature;
 	u8 reg;
@@ -48,6 +50,92 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 	}
 }
 
+/* leaf 0xb SMT level */
+#define SMT_LEVEL	0
+
+/* leaf 0xb sub-leaf types */
+#define INVALID_TYPE	0
+#define SMT_TYPE	1
+#define CORE_TYPE	2
+
+#define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
+#define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
+#define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
+
+/*
+ * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * exists, use it for populating initial_apicid and cpu topology
+ * detection.
+ */
+void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int eax, ebx, ecx, edx, sub_index;
+	unsigned int ht_mask_width, core_plus_mask_width;
+	unsigned int core_select_mask, core_level_siblings;
+
+	if (c->cpuid_level < 0xb)
+		return;
+
+	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+
+	/*
+	 * check if the cpuid leaf 0xb is actually implemented.
+	 */
+	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
+		return;
+
+	set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
+
+	/*
+	 * initial apic id, which also represents 32-bit extended x2apic id.
+	 */
+	c->initial_apicid = edx;
+
+	/*
+	 * Populate HT related information from sub-leaf level 0.
+	 */
+	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+
+	sub_index = 1;
+	do {
+		cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
+
+		/*
+		 * Check for the Core type in the implemented sub leaves.
+		 */
+		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
+			core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+			core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+			break;
+		}
+
+		sub_index++;
+	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+
+	core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
+
+#ifdef CONFIG_X86_32
+	c->cpu_core_id = phys_pkg_id(c->initial_apicid, ht_mask_width)
+						 & core_select_mask;
+	c->phys_proc_id = phys_pkg_id(c->initial_apicid, core_plus_mask_width);
+#else
+	c->cpu_core_id = phys_pkg_id(ht_mask_width) & core_select_mask;
+	c->phys_proc_id = phys_pkg_id(core_plus_mask_width);
+#endif
+	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
+
+
+	printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
+	       c->phys_proc_id);
+	if (c->x86_max_cores > 1)
+		printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
+		       c->cpu_core_id);
+	return;
+#endif
+}
+
 #ifdef CONFIG_X86_PAT
 void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
 {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 18514ed26104..32e73520adf7 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1,13 +1,22 @@
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/mm.h>
+
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 
+#ifdef CONFIG_X86_64
+# include <asm/numa_64.h>
+# include <asm/mmconfig.h>
+# include <asm/cacheflush.h>
+#endif
+
 #include <mach_apic.h>
+
 #include "cpu.h"
 
+#ifdef CONFIG_X86_32
 /*
  *	B step AMD K6 before B 9730xxxx have hardware bugs that can cause
  *	misexecution of code under Linux. Owners of such processors should
@@ -24,26 +33,273 @@
 extern void vide(void);
 __asm__(".align 4\nvide: ret");
 
-static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+static void __cpuinit init_amd_k5(struct cpuinfo_x86 *c)
 {
-	if (cpuid_eax(0x80000000) >= 0x80000007) {
-		c->x86_power = cpuid_edx(0x80000007);
-		if (c->x86_power & (1<<8))
-			set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+/*
+ * General Systems BIOSen alias the cpu frequency registers
+ * of the Elan at 0x000df000. Unfortuantly, one of the Linux
+ * drivers subsequently pokes it, and changes the CPU speed.
+ * Workaround : Remove the unneeded alias.
+ */
+#define CBAR		(0xfffc) /* Configuration Base Address  (32-bit) */
+#define CBAR_ENB	(0x80000000)
+#define CBAR_KEY	(0X000000CB)
+	if (c->x86_model == 9 || c->x86_model == 10) {
+		if (inl (CBAR) & CBAR_ENB)
+			outl (0 | CBAR_KEY, CBAR);
 	}
-
-	/*  Set MTRR capability flag if appropriate */
-	if (c->x86_model == 13 || c->x86_model == 9 ||
-	   (c->x86_model == 8 && c->x86_mask >= 8))
-		set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 }
 
-static void __cpuinit init_amd(struct cpuinfo_x86 *c)
+
+static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
 	int mbytes = num_physpages >> (20-PAGE_SHIFT);
-	int r;
 
+	if (c->x86_model < 6) {
+		/* Based on AMD doc 20734R - June 2000 */
+		if (c->x86_model == 0) {
+			clear_cpu_cap(c, X86_FEATURE_APIC);
+			set_cpu_cap(c, X86_FEATURE_PGE);
+		}
+		return;
+	}
+
+	if (c->x86_model == 6 && c->x86_mask == 1) {
+		const int K6_BUG_LOOP = 1000000;
+		int n;
+		void (*f_vide)(void);
+		unsigned long d, d2;
+
+		printk(KERN_INFO "AMD K6 stepping B detected - ");
+
+		/*
+		 * It looks like AMD fixed the 2.6.2 bug and improved indirect
+		 * calls at the same time.
+		 */
+
+		n = K6_BUG_LOOP;
+		f_vide = vide;
+		rdtscl(d);
+		while (n--)
+			f_vide();
+		rdtscl(d2);
+		d = d2-d;
+
+		if (d > 20*K6_BUG_LOOP)
+			printk("system stability may be impaired when more than 32 MB are used.\n");
+		else
+			printk("probably OK (after B9730xxxx).\n");
+		printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
+	}
+
+	/* K6 with old style WHCR */
+	if (c->x86_model < 8 ||
+	   (c->x86_model == 8 && c->x86_mask < 8)) {
+		/* We can only write allocate on the low 508Mb */
+		if (mbytes > 508)
+			mbytes = 508;
+
+		rdmsr(MSR_K6_WHCR, l, h);
+		if ((l&0x0000FFFF) == 0) {
+			unsigned long flags;
+			l = (1<<0)|((mbytes/4)<<1);
+			local_irq_save(flags);
+			wbinvd();
+			wrmsr(MSR_K6_WHCR, l, h);
+			local_irq_restore(flags);
+			printk(KERN_INFO "Enabling old style K6 write allocation for %d Mb\n",
+				mbytes);
+		}
+		return;
+	}
+
+	if ((c->x86_model == 8 && c->x86_mask > 7) ||
+	     c->x86_model == 9 || c->x86_model == 13) {
+		/* The more serious chips .. */
+
+		if (mbytes > 4092)
+			mbytes = 4092;
+
+		rdmsr(MSR_K6_WHCR, l, h);
+		if ((l&0xFFFF0000) == 0) {
+			unsigned long flags;
+			l = ((mbytes>>2)<<22)|(1<<16);
+			local_irq_save(flags);
+			wbinvd();
+			wrmsr(MSR_K6_WHCR, l, h);
+			local_irq_restore(flags);
+			printk(KERN_INFO "Enabling new style K6 write allocation for %d Mb\n",
+				mbytes);
+		}
+
+		return;
+	}
+
+	if (c->x86_model == 10) {
+		/* AMD Geode LX is model 10 */
+		/* placeholder for any needed mods */
+		return;
+	}
+}
+
+static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
+{
+	u32 l, h;
+
+	/*
+	 * Bit 15 of Athlon specific MSR 15, needs to be 0
+	 * to enable SSE on Palomino/Morgan/Barton CPU's.
+	 * If the BIOS didn't enable it already, enable it here.
+	 */
+	if (c->x86_model >= 6 && c->x86_model <= 10) {
+		if (!cpu_has(c, X86_FEATURE_XMM)) {
+			printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
+			rdmsr(MSR_K7_HWCR, l, h);
+			l &= ~0x00008000;
+			wrmsr(MSR_K7_HWCR, l, h);
+			set_cpu_cap(c, X86_FEATURE_XMM);
+		}
+	}
+
+	/*
+	 * It's been determined by AMD that Athlons since model 8 stepping 1
+	 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
+	 * As per AMD technical note 27212 0.2
+	 */
+	if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
+		rdmsr(MSR_K7_CLK_CTL, l, h);
+		if ((l & 0xfff00000) != 0x20000000) {
+			printk ("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", l,
+				((l & 0x000fffff)|0x20000000));
+			wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
+		}
+	}
+
+	set_cpu_cap(c, X86_FEATURE_K7);
+}
+#endif
+
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+static int __cpuinit nearby_node(int apicid)
+{
+	int i, node;
+
+	for (i = apicid - 1; i >= 0; i--) {
+		node = apicid_to_node[i];
+		if (node != NUMA_NO_NODE && node_online(node))
+			return node;
+	}
+	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
+		node = apicid_to_node[i];
+		if (node != NUMA_NO_NODE && node_online(node))
+			return node;
+	}
+	return first_node(node_online_map); /* Shouldn't happen */
+}
+#endif
+
+/*
+ * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
+ * Assumes number of cores is a power of two.
+ */
+static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_HT
+	unsigned bits;
+
+	bits = c->x86_coreid_bits;
+
+	/* Low order bits define the core id (index of core in socket) */
+	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+	/* Convert the initial APIC ID into the socket ID */
+	c->phys_proc_id = c->initial_apicid >> bits;
+#endif
+}
+
+static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
+{
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+	int cpu = smp_processor_id();
+	int node;
+	unsigned apicid = hard_smp_processor_id();
+
+	node = c->phys_proc_id;
+	if (apicid_to_node[apicid] != NUMA_NO_NODE)
+		node = apicid_to_node[apicid];
+	if (!node_online(node)) {
+		/* Two possibilities here:
+		   - The CPU is missing memory and no node was created.
+		   In that case try picking one from a nearby CPU
+		   - The APIC IDs differ from the HyperTransport node IDs
+		   which the K8 northbridge parsing fills in.
+		   Assume they are all increased by a constant offset,
+		   but in the same order as the HT nodeids.
+		   If that doesn't result in a usable node fall back to the
+		   path for the previous case.  */
+
+		int ht_nodeid = c->initial_apicid;
+
+		if (ht_nodeid >= 0 &&
+		    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+			node = apicid_to_node[ht_nodeid];
+		/* Pick a nearby node */
+		if (!node_online(node))
+			node = nearby_node(apicid);
+	}
+	numa_set_node(cpu, node);
+
+	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+}
+
+static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_HT
+	unsigned bits, ecx;
+
+	/* Multi core CPU? */
+	if (c->extended_cpuid_level < 0x80000008)
+		return;
+
+	ecx = cpuid_ecx(0x80000008);
+
+	c->x86_max_cores = (ecx & 0xff) + 1;
+
+	/* CPU telling us the core id bits shift? */
+	bits = (ecx >> 12) & 0xF;
+
+	/* Otherwise recompute */
+	if (bits == 0) {
+		while ((1 << bits) < c->x86_max_cores)
+			bits++;
+	}
+
+	c->x86_coreid_bits = bits;
+#endif
+}
+
+static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+{
+	early_init_amd_mc(c);
+
+	/* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
+	if (c->x86_power & (1<<8))
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+
+#ifdef CONFIG_X86_64
+	set_cpu_cap(c, X86_FEATURE_SYSCALL32);
+#else
+	/*  Set MTRR capability flag if appropriate */
+	if (c->x86 == 5)
+		if (c->x86_model == 13 || c->x86_model == 9 ||
+		    (c->x86_model == 8 && c->x86_mask >= 8))
+			set_cpu_cap(c, X86_FEATURE_K6_MTRR);
+#endif
+}
+
+static void __cpuinit init_amd(struct cpuinfo_x86 *c)
+{
 #ifdef CONFIG_SMP
 	unsigned long long value;
 
@@ -54,7 +310,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	 * Errata 63 for SH-B3 steppings
 	 * Errata 122 for all steppings (F+ have it disabled by default)
 	 */
-	if (c->x86 == 15) {
+	if (c->x86 == 0xf) {
 		rdmsrl(MSR_K7_HWCR, value);
 		value |= 1 << 6;
 		wrmsrl(MSR_K7_HWCR, value);
@@ -64,209 +320,119 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	early_init_amd(c);
 
 	/*
-	 *	FIXME: We should handle the K5 here. Set up the write
-	 *	range and also turn on MSR 83 bits 4 and 31 (write alloc,
-	 *	no bus pipeline)
-	 */
-
-	/*
 	 * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
 	 * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
 	 */
 	clear_cpu_cap(c, 0*32+31);
 
-	r = get_model_name(c);
+#ifdef CONFIG_X86_64
+	/* On C+ stepping K8 rep microcode works well for copy/memset */
+	if (c->x86 == 0xf) {
+		u32 level;
 
-	switch (c->x86) {
-	case 4:
-		/*
-		 * General Systems BIOSen alias the cpu frequency registers
-		 * of the Elan at 0x000df000. Unfortuantly, one of the Linux
-		 * drivers subsequently pokes it, and changes the CPU speed.
-		 * Workaround : Remove the unneeded alias.
-		 */
-#define CBAR		(0xfffc) /* Configuration Base Address  (32-bit) */
-#define CBAR_ENB	(0x80000000)
-#define CBAR_KEY	(0X000000CB)
-			if (c->x86_model == 9 || c->x86_model == 10) {
-				if (inl (CBAR) & CBAR_ENB)
-					outl (0 | CBAR_KEY, CBAR);
-			}
-			break;
-	case 5:
-			if (c->x86_model < 6) {
-				/* Based on AMD doc 20734R - June 2000 */
-				if (c->x86_model == 0) {
-					clear_cpu_cap(c, X86_FEATURE_APIC);
-					set_cpu_cap(c, X86_FEATURE_PGE);
-				}
-				break;
-			}
-
-			if (c->x86_model == 6 && c->x86_mask == 1) {
-				const int K6_BUG_LOOP = 1000000;
-				int n;
-				void (*f_vide)(void);
-				unsigned long d, d2;
-
-				printk(KERN_INFO "AMD K6 stepping B detected - ");
-
-				/*
-				 * It looks like AMD fixed the 2.6.2 bug and improved indirect
-				 * calls at the same time.
-				 */
-
-				n = K6_BUG_LOOP;
-				f_vide = vide;
-				rdtscl(d);
-				while (n--)
-					f_vide();
-				rdtscl(d2);
-				d = d2-d;
-
-				if (d > 20*K6_BUG_LOOP)
-					printk("system stability may be impaired when more than 32 MB are used.\n");
-				else
-					printk("probably OK (after B9730xxxx).\n");
-				printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
-			}
-
-			/* K6 with old style WHCR */
-			if (c->x86_model < 8 ||
-			   (c->x86_model == 8 && c->x86_mask < 8)) {
-				/* We can only write allocate on the low 508Mb */
-				if (mbytes > 508)
-					mbytes = 508;
-
-				rdmsr(MSR_K6_WHCR, l, h);
-				if ((l&0x0000FFFF) == 0) {
-					unsigned long flags;
-					l = (1<<0)|((mbytes/4)<<1);
-					local_irq_save(flags);
-					wbinvd();
-					wrmsr(MSR_K6_WHCR, l, h);
-					local_irq_restore(flags);
-					printk(KERN_INFO "Enabling old style K6 write allocation for %d Mb\n",
-						mbytes);
-				}
-				break;
-			}
-
-			if ((c->x86_model == 8 && c->x86_mask > 7) ||
-			     c->x86_model == 9 || c->x86_model == 13) {
-				/* The more serious chips .. */
-
-				if (mbytes > 4092)
-					mbytes = 4092;
-
-				rdmsr(MSR_K6_WHCR, l, h);
-				if ((l&0xFFFF0000) == 0) {
-					unsigned long flags;
-					l = ((mbytes>>2)<<22)|(1<<16);
-					local_irq_save(flags);
-					wbinvd();
-					wrmsr(MSR_K6_WHCR, l, h);
-					local_irq_restore(flags);
-					printk(KERN_INFO "Enabling new style K6 write allocation for %d Mb\n",
-						mbytes);
-				}
-
-				break;
-			}
-
-			if (c->x86_model == 10) {
-				/* AMD Geode LX is model 10 */
-				/* placeholder for any needed mods */
-				break;
-			}
-			break;
-	case 6: /* An Athlon/Duron */
-
-			/*
-			 * Bit 15 of Athlon specific MSR 15, needs to be 0
-			 * to enable SSE on Palomino/Morgan/Barton CPU's.
-			 * If the BIOS didn't enable it already, enable it here.
-			 */
-			if (c->x86_model >= 6 && c->x86_model <= 10) {
-				if (!cpu_has(c, X86_FEATURE_XMM)) {
-					printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
-					rdmsr(MSR_K7_HWCR, l, h);
-					l &= ~0x00008000;
-					wrmsr(MSR_K7_HWCR, l, h);
-					set_cpu_cap(c, X86_FEATURE_XMM);
-				}
-			}
-
-			/*
-			 * It's been determined by AMD that Athlons since model 8 stepping 1
-			 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
-			 * As per AMD technical note 27212 0.2
-			 */
-			if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
-				rdmsr(MSR_K7_CLK_CTL, l, h);
-				if ((l & 0xfff00000) != 0x20000000) {
-					printk ("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", l,
-						((l & 0x000fffff)|0x20000000));
-					wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
-				}
-			}
-			break;
+		level = cpuid_eax(1);
+		if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
+			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 	}
+	if (c->x86 == 0x10 || c->x86 == 0x11)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+#else
+
+	/*
+	 *	FIXME: We should handle the K5 here. Set up the write
+	 *	range and also turn on MSR 83 bits 4 and 31 (write alloc,
+	 *	no bus pipeline)
+	 */
 
 	switch (c->x86) {
-	case 15:
-	/* Use K8 tuning for Fam10h and Fam11h */
-	case 0x10:
-	case 0x11:
-		set_cpu_cap(c, X86_FEATURE_K8);
+	case 4:
+		init_amd_k5(c);
 		break;
-	case 6:
-		set_cpu_cap(c, X86_FEATURE_K7);
+	case 5:
+		init_amd_k6(c);
+		break;
+	case 6: /* An Athlon/Duron */
+		init_amd_k7(c);
 		break;
 	}
+
+	/* K6s reports MCEs but don't actually have all the MSRs */
+	if (c->x86 < 6)
+		clear_cpu_cap(c, X86_FEATURE_MCE);
+#endif
+
+	/* Enable workaround for FXSAVE leak */
 	if (c->x86 >= 6)
 		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
 
-	display_cacheinfo(c);
-
-	if (cpuid_eax(0x80000000) >= 0x80000008)
-		c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
+	if (!c->x86_model_id[0]) {
+		switch (c->x86) {
+		case 0xf:
+			/* Should distinguish Models here, but this is only
+			   a fallback anyways. */
+			strcpy(c->x86_model_id, "Hammer");
+			break;
+		}
+	}
 
-#ifdef CONFIG_X86_HT
-	/*
-	 * On a AMD multi core setup the lower bits of the APIC id
-	 * distinguish the cores.
-	 */
-	if (c->x86_max_cores > 1) {
-		int cpu = smp_processor_id();
-		unsigned bits = (cpuid_ecx(0x80000008) >> 12) & 0xf;
+	display_cacheinfo(c);
 
-		if (bits == 0) {
-			while ((1 << bits) < c->x86_max_cores)
-				bits++;
-		}
-		c->cpu_core_id = c->phys_proc_id & ((1<<bits)-1);
-		c->phys_proc_id >>= bits;
-		printk(KERN_INFO "CPU %d(%d) -> Core %d\n",
-		       cpu, c->x86_max_cores, c->cpu_core_id);
+	/* Multi core CPU? */
+	if (c->extended_cpuid_level >= 0x80000008) {
+		amd_detect_cmp(c);
+		srat_detect_node(c);
 	}
+
+#ifdef CONFIG_X86_32
+	detect_ht(c);
 #endif
 
-	if (cpuid_eax(0x80000000) >= 0x80000006) {
-		if ((c->x86 == 0x10) && (cpuid_edx(0x80000006) & 0xf000))
+	if (c->extended_cpuid_level >= 0x80000006) {
+		if ((c->x86 >= 0x0f) && (cpuid_edx(0x80000006) & 0xf000))
 			num_cache_leaves = 4;
 		else
 			num_cache_leaves = 3;
 	}
 
-	/* K6s reports MCEs but don't actually have all the MSRs */
-	if (c->x86 < 6)
-		clear_cpu_cap(c, X86_FEATURE_MCE);
+	if (c->x86 >= 0xf && c->x86 <= 0x11)
+		set_cpu_cap(c, X86_FEATURE_K8);
 
-	if (cpu_has_xmm2)
+	if (cpu_has_xmm2) {
+		/* MFENCE stops RDTSC speculation */
 		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+	}
+
+#ifdef CONFIG_X86_64
+	if (c->x86 == 0x10) {
+		/* do this for boot cpu */
+		if (c == &boot_cpu_data)
+			check_enable_amd_mmconf_dmi();
+
+		fam10h_check_enable_mmcfg();
+	}
+
+	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
+		unsigned long long tseg;
+
+		/*
+		 * Split up direct mapping around the TSEG SMM area.
+		 * Don't do it for gbpages because there seems very little
+		 * benefit in doing so.
+		 */
+		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+		    printk(KERN_DEBUG "tseg: %010llx\n", tseg);
+		    if ((tseg>>PMD_SHIFT) <
+				(max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
+			((tseg>>PMD_SHIFT) <
+				(max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
+			 (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
+			set_memory_4k((unsigned long)__va(tseg), 1);
+		}
+	}
+#endif
 }
 
+#ifdef CONFIG_X86_32
 static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 {
 	/* AMD errata T13 (order #21922) */
@@ -279,10 +445,12 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int
 	}
 	return size;
 }
+#endif
 
 static struct cpu_dev amd_cpu_dev __cpuinitdata = {
 	.c_vendor	= "AMD",
 	.c_ident	= { "AuthenticAMD" },
+#ifdef CONFIG_X86_32
 	.c_models = {
 		{ .vendor = X86_VENDOR_AMD, .family = 4, .model_names =
 		  {
@@ -295,9 +463,11 @@ static struct cpu_dev amd_cpu_dev __cpuinitdata = {
 		  }
 		},
 	},
+	.c_size_cache	= amd_size_cache,
+#endif
 	.c_early_init   = early_init_amd,
 	.c_init		= init_amd,
-	.c_size_cache	= amd_size_cache,
+	.c_x86_vendor	= X86_VENDOR_AMD,
 };
 
-cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev);
+cpu_dev_register(amd_cpu_dev);
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
deleted file mode 100644
index d1692b2a41ff..000000000000
--- a/arch/x86/kernel/cpu/amd_64.c
+++ /dev/null
@@ -1,224 +0,0 @@
-#include <linux/init.h>
-#include <linux/mm.h>
-
-#include <asm/numa_64.h>
-#include <asm/mmconfig.h>
-#include <asm/cacheflush.h>
-
-#include <mach_apic.h>
-
-#include "cpu.h"
-
-int force_mwait __cpuinitdata;
-
-#ifdef CONFIG_NUMA
-static int __cpuinit nearby_node(int apicid)
-{
-	int i, node;
-
-	for (i = apicid - 1; i >= 0; i--) {
-		node = apicid_to_node[i];
-		if (node != NUMA_NO_NODE && node_online(node))
-			return node;
-	}
-	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
-		node = apicid_to_node[i];
-		if (node != NUMA_NO_NODE && node_online(node))
-			return node;
-	}
-	return first_node(node_online_map); /* Shouldn't happen */
-}
-#endif
-
-/*
- * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
- * Assumes number of cores is a power of two.
- */
-static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	unsigned bits;
-#ifdef CONFIG_NUMA
-	int cpu = smp_processor_id();
-	int node = 0;
-	unsigned apicid = hard_smp_processor_id();
-#endif
-	bits = c->x86_coreid_bits;
-
-	/* Low order bits define the core id (index of core in socket) */
-	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
-	/* Convert the initial APIC ID into the socket ID */
-	c->phys_proc_id = c->initial_apicid >> bits;
-
-#ifdef CONFIG_NUMA
-	node = c->phys_proc_id;
-	if (apicid_to_node[apicid] != NUMA_NO_NODE)
-		node = apicid_to_node[apicid];
-	if (!node_online(node)) {
-		/* Two possibilities here:
-		   - The CPU is missing memory and no node was created.
-		   In that case try picking one from a nearby CPU
-		   - The APIC IDs differ from the HyperTransport node IDs
-		   which the K8 northbridge parsing fills in.
-		   Assume they are all increased by a constant offset,
-		   but in the same order as the HT nodeids.
-		   If that doesn't result in a usable node fall back to the
-		   path for the previous case.  */
-
-		int ht_nodeid = c->initial_apicid;
-
-		if (ht_nodeid >= 0 &&
-		    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
-			node = apicid_to_node[ht_nodeid];
-		/* Pick a nearby node */
-		if (!node_online(node))
-			node = nearby_node(apicid);
-	}
-	numa_set_node(cpu, node);
-
-	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
-#endif
-#endif
-}
-
-static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	unsigned bits, ecx;
-
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level < 0x80000008)
-		return;
-
-	ecx = cpuid_ecx(0x80000008);
-
-	c->x86_max_cores = (ecx & 0xff) + 1;
-
-	/* CPU telling us the core id bits shift? */
-	bits = (ecx >> 12) & 0xF;
-
-	/* Otherwise recompute */
-	if (bits == 0) {
-		while ((1 << bits) < c->x86_max_cores)
-			bits++;
-	}
-
-	c->x86_coreid_bits = bits;
-
-#endif
-}
-
-static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
-{
-	early_init_amd_mc(c);
-
-	/* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
-	if (c->x86_power & (1<<8))
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-
-	set_cpu_cap(c, X86_FEATURE_SYSCALL32);
-}
-
-static void __cpuinit init_amd(struct cpuinfo_x86 *c)
-{
-	unsigned level;
-
-#ifdef CONFIG_SMP
-	unsigned long value;
-
-	/*
-	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
-	 * bit 6 of msr C001_0015
-	 *
-	 * Errata 63 for SH-B3 steppings
-	 * Errata 122 for all steppings (F+ have it disabled by default)
-	 */
-	if (c->x86 == 0xf) {
-		rdmsrl(MSR_K8_HWCR, value);
-		value |= 1 << 6;
-		wrmsrl(MSR_K8_HWCR, value);
-	}
-#endif
-
-	/* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
-	   3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
-	clear_cpu_cap(c, 0*32+31);
-
-	/* On C+ stepping K8 rep microcode works well for copy/memset */
-	if (c->x86 == 0xf) {
-		level = cpuid_eax(1);
-		if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
-			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-	}
-	if (c->x86 == 0x10 || c->x86 == 0x11)
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-
-	/* Enable workaround for FXSAVE leak */
-	if (c->x86 >= 6)
-		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
-
-	level = get_model_name(c);
-	if (!level) {
-		switch (c->x86) {
-		case 0xf:
-			/* Should distinguish Models here, but this is only
-			   a fallback anyways. */
-			strcpy(c->x86_model_id, "Hammer");
-			break;
-		}
-	}
-	display_cacheinfo(c);
-
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level >= 0x80000008)
-		amd_detect_cmp(c);
-
-	if (c->extended_cpuid_level >= 0x80000006 &&
-		(cpuid_edx(0x80000006) & 0xf000))
-		num_cache_leaves = 4;
-	else
-		num_cache_leaves = 3;
-
-	if (c->x86 >= 0xf && c->x86 <= 0x11)
-		set_cpu_cap(c, X86_FEATURE_K8);
-
-	/* MFENCE stops RDTSC speculation */
-	set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
-
-	if (c->x86 == 0x10) {
-		/* do this for boot cpu */
-		if (c == &boot_cpu_data)
-			check_enable_amd_mmconf_dmi();
-
-		fam10h_check_enable_mmcfg();
-	}
-
-	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
-		unsigned long long tseg;
-
-		/*
-		 * Split up direct mapping around the TSEG SMM area.
-		 * Don't do it for gbpages because there seems very little
-		 * benefit in doing so.
-		 */
-		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
-		    printk(KERN_DEBUG "tseg: %010llx\n", tseg);
-		    if ((tseg>>PMD_SHIFT) <
-				(max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
-			((tseg>>PMD_SHIFT) <
-				(max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
-			 (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
-			set_memory_4k((unsigned long)__va(tseg), 1);
-		}
-	}
-}
-
-static struct cpu_dev amd_cpu_dev __cpuinitdata = {
-	.c_vendor	= "AMD",
-	.c_ident	= { "AuthenticAMD" },
-	.c_early_init   = early_init_amd,
-	.c_init		= init_amd,
-};
-
-cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev);
-
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index a0534c04d38a..89bfdd9cacc6 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -289,7 +289,6 @@ static void __cpuinit init_c3(struct cpuinfo_x86 *c)
 	if (c->x86_model >= 6 && c->x86_model < 9)
 		set_cpu_cap(c, X86_FEATURE_3DNOW);
 
-	get_model_name(c);
 	display_cacheinfo(c);
 }
 
@@ -475,6 +474,7 @@ static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
 	.c_early_init	= early_init_centaur,
 	.c_init		= init_centaur,
 	.c_size_cache	= centaur_size_cache,
+	.c_x86_vendor	= X86_VENDOR_CENTAUR,
 };
 
-cpu_vendor_dev_register(X86_VENDOR_CENTAUR, &centaur_cpu_dev);
+cpu_dev_register(centaur_cpu_dev);
diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c
index 1d181c40e2e1..a1625f5a1e78 100644
--- a/arch/x86/kernel/cpu/centaur_64.c
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -16,9 +16,10 @@ static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
 
 static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
 {
+	early_init_centaur(c);
+
 	if (c->x86 == 0x6 && c->x86_model >= 0xf) {
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 	}
 	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
@@ -29,7 +30,8 @@ static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
 	.c_ident	= { "CentaurHauls" },
 	.c_early_init	= early_init_centaur,
 	.c_init		= init_centaur,
+	.c_x86_vendor	= X86_VENDOR_CENTAUR,
 };
 
-cpu_vendor_dev_register(X86_VENDOR_CENTAUR, &centaur_cpu_dev);
+cpu_dev_register(centaur_cpu_dev);
 
diff --git a/arch/x86/kernel/cpu/cmpxchg.c b/arch/x86/kernel/cpu/cmpxchg.c
new file mode 100644
index 000000000000..2056ccf572cc
--- /dev/null
+++ b/arch/x86/kernel/cpu/cmpxchg.c
@@ -0,0 +1,72 @@
+/*
+ * cmpxchg*() fallbacks for CPU not supporting these instructions
+ */
+
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#ifndef CONFIG_X86_CMPXCHG
+unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new)
+{
+	u8 prev;
+	unsigned long flags;
+
+	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
+	local_irq_save(flags);
+	prev = *(u8 *)ptr;
+	if (prev == old)
+		*(u8 *)ptr = new;
+	local_irq_restore(flags);
+	return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u8);
+
+unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new)
+{
+	u16 prev;
+	unsigned long flags;
+
+	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
+	local_irq_save(flags);
+	prev = *(u16 *)ptr;
+	if (prev == old)
+		*(u16 *)ptr = new;
+	local_irq_restore(flags);
+	return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u16);
+
+unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
+{
+	u32 prev;
+	unsigned long flags;
+
+	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
+	local_irq_save(flags);
+	prev = *(u32 *)ptr;
+	if (prev == old)
+		*(u32 *)ptr = new;
+	local_irq_restore(flags);
+	return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u32);
+#endif
+
+#ifndef CONFIG_X86_CMPXCHG64
+unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new)
+{
+	u64 prev;
+	unsigned long flags;
+
+	/* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */
+	local_irq_save(flags);
+	prev = *(u64 *)ptr;
+	if (prev == old)
+		*(u64 *)ptr = new;
+	local_irq_restore(flags);
+	return prev;
+}
+EXPORT_SYMBOL(cmpxchg_486_u64);
+#endif
+
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4e456bd955bb..25581dcb280e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1,28 +1,62 @@
 #include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
 #include <linux/string.h>
+#include <linux/bootmem.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/kgdb.h>
+#include <linux/topology.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
-#include <linux/module.h>
 #include <linux/percpu.h>
-#include <linux/bootmem.h>
-#include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/msr.h>
 #include <asm/io.h>
+#include <asm/linkage.h>
 #include <asm/mmu_context.h>
 #include <asm/mtrr.h>
 #include <asm/mce.h>
 #include <asm/pat.h>
 #include <asm/asm.h>
+#include <asm/numa.h>
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/mpspec.h>
 #include <asm/apic.h>
 #include <mach_apic.h>
+#include <asm/genapic.h>
 #endif
 
+#include <asm/pda.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/proto.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+
 #include "cpu.h"
 
+static struct cpu_dev *this_cpu __cpuinitdata;
+
+#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
+ */
+/* The TLS descriptors are currently at a different place compared to i386.
+   Hopefully nobody expects them at a fixed place (Wine?) */
 DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+	[GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
+	[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
+	[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
+	[GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
+	[GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
+	[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
+} };
+#else
+DEFINE_PER_CPU_PAGE_ALIGNED(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 } } },
@@ -56,17 +90,157 @@ DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
 	[GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
 	[GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } },
 } };
+#endif
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
-
+#ifdef CONFIG_X86_32
 static int cachesize_override __cpuinitdata = -1;
 static int disable_x86_serial_nr __cpuinitdata = 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 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);
+
+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 */
+static int __cpuinit have_cpuid_p(void)
+{
+	return flag_is_changeable_p(X86_EFLAGS_ID);
+}
+
+static void __cpuinit squash_the_stupid_serial_number(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_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;
+}
+/* Probe for the CPUID instruction */
+static inline int have_cpuid_p(void)
+{
+	return 1;
+}
+static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+{
+}
+#endif
+
+/*
+ * 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 char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
+{
+	struct cpu_model_info *info;
+
+	if (c->x86_model >= 16)
+		return NULL;	/* Range check */
+
+	if (!this_cpu)
+		return NULL;
+
+	info = this_cpu->c_models;
+
+	while (info && info->family) {
+		if (info->family == c->x86)
+			return info->model_names[c->x86_model];
+		info++;
+	}
+	return NULL;		/* Not found */
+}
+
+__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+
+/* Current gdt points %fs at the "master" per-cpu area: after this,
+ * it's on the real one. */
+void switch_to_new_gdt(void)
+{
+	struct desc_ptr gdt_descr;
+
+	gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+#ifdef CONFIG_X86_32
+	asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
+#endif
+}
+
+static struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
 
 static void __cpuinit default_init(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_64
+	display_cacheinfo(c);
+#else
 	/* Not much we can do here... */
 	/* Check if at least it has cpuid */
 	if (c->cpuid_level == -1) {
@@ -76,28 +250,22 @@ static void __cpuinit default_init(struct cpuinfo_x86 *c)
 		else if (c->x86 == 3)
 			strcpy(c->x86_model_id, "386");
 	}
+#endif
 }
 
 static struct cpu_dev __cpuinitdata default_cpu = {
 	.c_init	= default_init,
 	.c_vendor = "Unknown",
+	.c_x86_vendor = X86_VENDOR_UNKNOWN,
 };
-static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
-
-static int __init cachesize_setup(char *str)
-{
-	get_option(&str, &cachesize_override);
-	return 1;
-}
-__setup("cachesize=", cachesize_setup);
 
-int __cpuinit get_model_name(struct cpuinfo_x86 *c)
+static void __cpuinit 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;
 	cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
@@ -116,30 +284,34 @@ int __cpuinit get_model_name(struct cpuinfo_x86 *c)
 	     while (q <= &c->x86_model_id[48])
 		  *q++ = '\0';	/* Zero-pad the rest */
 	}
-
-	return 1;
 }
 
-
 void __cpuinit display_cacheinfo(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);
+		cpuid(0x80000005, &dummy, &ebx, &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);
+				edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+		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);
@@ -150,116 +322,106 @@ void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
 
 	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);
+			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
- *
- */
-
-/* Look up CPU names by table lookup. */
-static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
+void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 {
-	struct cpu_model_info *info;
+#ifdef CONFIG_X86_HT
+	u32 eax, ebx, ecx, edx;
+	int index_msb, core_bits;
 
-	if (c->x86_model >= 16)
-		return NULL;	/* Range check */
+	if (!cpu_has(c, X86_FEATURE_HT))
+		return;
 
-	if (!this_cpu)
-		return NULL;
+	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
+		goto out;
 
-	info = this_cpu->c_models;
+	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
+		return;
 
-	while (info && info->family) {
-		if (info->family == c->x86)
-			return info->model_names[c->x86_model];
-		info++;
+	cpuid(1, &eax, &ebx, &ecx, &edx);
+
+	smp_num_siblings = (ebx & 0xff0000) >> 16;
+
+	if (smp_num_siblings == 1) {
+		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
+	} else if (smp_num_siblings > 1) {
+
+		if (smp_num_siblings > NR_CPUS) {
+			printk(KERN_WARNING "CPU: Unsupported number of siblings %d",
+					smp_num_siblings);
+			smp_num_siblings = 1;
+			return;
+		}
+
+		index_msb = get_count_order(smp_num_siblings);
+#ifdef CONFIG_X86_64
+		c->phys_proc_id = phys_pkg_id(index_msb);
+#else
+		c->phys_proc_id = phys_pkg_id(c->initial_apicid, index_msb);
+#endif
+
+		smp_num_siblings = smp_num_siblings / c->x86_max_cores;
+
+		index_msb = get_count_order(smp_num_siblings);
+
+		core_bits = get_count_order(c->x86_max_cores);
+
+#ifdef CONFIG_X86_64
+		c->cpu_core_id = phys_pkg_id(index_msb) &
+					       ((1 << core_bits) - 1);
+#else
+		c->cpu_core_id = phys_pkg_id(c->initial_apicid, index_msb) &
+					       ((1 << core_bits) - 1);
+#endif
 	}
-	return NULL;		/* Not found */
-}
 
+out:
+	if ((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);
+	}
+#endif
+}
 
-static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early)
+static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
 {
 	char *v = c->x86_vendor_id;
 	int i;
 	static int printed;
 
 	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 (!cpu_devs[i])
+			break;
+
+		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;
 		}
 	}
+
 	if (!printed) {
 		printed++;
-		printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n");
+		printk(KERN_ERR "CPU: vendor_id '%s' unknown, using generic init.\n", v);
 		printk(KERN_ERR "CPU: Your system may be unstable.\n");
 	}
+
 	c->x86_vendor = X86_VENDOR_UNKNOWN;
 	this_cpu = &default_cpu;
 }
 
-
-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);
-
-
-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;
-
-	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));
-
-	return ((f1^f2) & flag) != 0;
-}
-
-
-/* Probe for the CPUID instruction */
-static int __cpuinit have_cpuid_p(void)
-{
-	return flag_is_changeable_p(X86_EFLAGS_ID);
-}
-
-void __init cpu_detect(struct cpuinfo_x86 *c)
+void __cpuinit cpu_detect(struct cpuinfo_x86 *c)
 {
 	/* Get vendor name */
 	cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
@@ -268,50 +430,87 @@ 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)
+
+static void __cpuinit 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;
+		cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
+		c->x86_capability[0] = capability;
+		c->x86_capability[4] = 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);
-			}
+	/* 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);
 		}
+	}
+
+#ifdef CONFIG_X86_64
+	if (c->extended_cpuid_level >= 0x80000008) {
+		u32 eax = cpuid_eax(0x80000008);
 
+		c->x86_virt_bits = (eax >> 8) & 0xff;
+		c->x86_phys_bits = eax & 0xff;
 	}
+#endif
+
+	if (c->extended_cpuid_level >= 0x80000007)
+		c->x86_power = cpuid_edx(0x80000007);
 
 }
 
+static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
+{
+#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
+}
+
 /*
  * Do minimum CPU detection early.
  * Fields really needed: vendor, cpuid_level, family, model, mask,
@@ -321,25 +520,61 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *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 __init early_identify_cpu(struct cpuinfo_x86 *c)
 {
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	c->x86_cache_alignment = 32;
+#ifdef CONFIG_X86_64
+	c->x86_clflush_size = 64;
+#else
 	c->x86_clflush_size = 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, 1);
+	get_cpu_vendor(c);
+
+	get_cpu_cap(c);
 
-	early_get_cap(c);
+	if (this_cpu->c_early_init)
+		this_cpu->c_early_init(c);
 
-	if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
-	    cpu_devs[c->x86_vendor]->c_early_init)
-		cpu_devs[c->x86_vendor]->c_early_init(c);
+	validate_pat_support(c);
+}
+
+void __init early_cpu_init(void)
+{
+	struct cpu_dev **cdev;
+	int count = 0;
+
+	printk("KERNEL supported cpus:\n");
+	for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
+		struct cpu_dev *cpudev = *cdev;
+		unsigned int j;
+
+		if (count >= X86_VENDOR_NUM)
+			break;
+		cpu_devs[count] = cpudev;
+		count++;
+
+		for (j = 0; j < 2; j++) {
+			if (!cpudev->c_ident[j])
+				continue;
+			printk("  %s %s\n", cpudev->c_vendor,
+				cpudev->c_ident[j]);
+		}
+	}
+
+	early_identify_cpu(&boot_cpu_data);
 }
 
 /*
@@ -357,86 +592,41 @@ static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
 
 static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
 {
-	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;
-			c->initial_apicid = (ebx >> 24) & 0xFF;
-#ifdef CONFIG_X86_HT
-			c->apicid = phys_pkg_id(c->initial_apicid, 0);
-			c->phys_proc_id = c->initial_apicid;
-#else
-			c->apicid = c->initial_apicid;
-#endif
-			if (test_cpu_cap(c, X86_FEATURE_CLFLSH))
-				c->x86_clflush_size = ((ebx >> 8) & 0xff) * 8;
-		} else {
-			/* Have CPUID level 0 only - unheard of */
-			c->x86 = 4;
-		}
+	c->extended_cpuid_level = 0;
 
-		/* 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);
-			}
-			if (xlvl >= 0x80000004)
-				get_model_name(c); /* Default name */
-		}
+	if (!have_cpuid_p())
+		identify_cpu_without_cpuid(c);
 
-		init_scattered_cpuid_features(c);
-		detect_nopl(c);
-	}
-}
+	/* cyrix could have cpuid enabled via c_identify()*/
+	if (!have_cpuid_p())
+		return;
 
-static void __cpuinit squash_the_stupid_serial_number(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_cpu_cap(c, X86_FEATURE_PN);
+	cpu_detect(c);
 
-		/* Disabling the serial number may affect the cpuid level */
-		c->cpuid_level = cpuid_eax(0);
-	}
-}
+	get_cpu_vendor(c);
 
-static int __init x86_serial_nr_setup(char *s)
-{
-	disable_x86_serial_nr = 0;
-	return 1;
-}
-__setup("serialnumber", x86_serial_nr_setup);
+	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 = phys_pkg_id(c->initial_apicid, 0);
+# else
+		c->apicid = c->initial_apicid;
+# endif
+#endif
 
+#ifdef CONFIG_X86_HT
+		c->phys_proc_id = c->initial_apicid;
+#endif
+	}
 
+	get_model_name(c); /* Default name */
+
+	init_scattered_cpuid_features(c);
+	detect_nopl(c);
+}
 
 /*
  * This does the hard work of actually picking apart the CPU stuff...
@@ -448,30 +638,29 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	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;
+#else
+	c->cpuid_level = -1;	/* CPUID not detected */
 	c->x86_clflush_size = 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);
 
+#ifdef CONFIG_X86_64
+	c->apicid = phys_pkg_id(0);
+#endif
+
 	/*
 	 * Vendor-specific initialization.  In this section we
 	 * canonicalize the feature flags, meaning if there are
@@ -505,6 +694,10 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 				c->x86, c->x86_model);
 	}
 
+#ifdef CONFIG_X86_64
+	detect_ht(c);
+#endif
+
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between
 	 * all CPUs; so make sure that we indicate which features are
@@ -513,7 +706,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	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];
 	}
 
@@ -521,72 +714,91 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	for (i = 0; i < NCAPINTS; i++)
 		c->x86_capability[i] &= ~cleared_cpu_caps[i];
 
+#ifdef CONFIG_X86_MCE
 	/* Init Machine Check Exception if available. */
 	mcheck_init(c);
+#endif
 
 	select_idle_routine(c);
+
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+	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;
+}
+#endif
+
 void __init identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
+#ifdef CONFIG_X86_32
 	sysenter_setup();
 	enable_sep_cpu();
+#else
+	vgetcpu_set_mode();
+#endif
 }
 
 void __cpuinit 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);
-
-	if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		return;
-
-	smp_num_siblings = (ebx & 0xff0000) >> 16;
+struct msr_range {
+	unsigned min;
+	unsigned max;
+};
 
-	if (smp_num_siblings == 1) {
-		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
-	} else if (smp_num_siblings > 1) {
+static struct msr_range msr_range_array[] __cpuinitdata = {
+	{ 0x00000000, 0x00000418},
+	{ 0xc0000000, 0xc000040b},
+	{ 0xc0010000, 0xc0010142},
+	{ 0xc0011000, 0xc001103b},
+};
 
-		if (smp_num_siblings > NR_CPUS) {
-			printk(KERN_WARNING "CPU: Unsupported number of the "
-					"siblings %d", smp_num_siblings);
-			smp_num_siblings = 1;
-			return;
+static void __cpuinit print_cpu_msr(void)
+{
+	unsigned index;
+	u64 val;
+	int i;
+	unsigned index_min, index_max;
+
+	for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) {
+		index_min = msr_range_array[i].min;
+		index_max = msr_range_array[i].max;
+		for (index = index_min; index < index_max; index++) {
+			if (rdmsrl_amd_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(c->initial_apicid, 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) ;
-
-		core_bits = get_count_order(c->x86_max_cores);
+static int show_msr __cpuinitdata;
+static __init int setup_show_msr(char *arg)
+{
+	int num;
 
-		c->cpu_core_id = phys_pkg_id(c->initial_apicid, 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)
 {
@@ -604,18 +816,26 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
 	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", 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 " stepping %02x\n", c->x86_mask);
 	else
-		printk("\n");
+		printk(KERN_CONT "\n");
+
+#ifdef CONFIG_SMP
+	if (c->cpu_index < show_msr)
+		print_cpu_msr();
+#else
+	if (show_msr)
+		print_cpu_msr();
+#endif
 }
 
 static __init int setup_disablecpuid(char *arg)
@@ -631,19 +851,89 @@ __setup("clearcpuid=", setup_disablecpuid);
 
 cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
 
-void __init early_cpu_init(void)
+#ifdef CONFIG_X86_64
+struct x8664_pda **_cpu_pda __read_mostly;
+EXPORT_SYMBOL(_cpu_pda);
+
+struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
+
+char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+
+void __cpuinit pda_init(int cpu)
 {
-	struct cpu_vendor_dev *cvdev;
+	struct x8664_pda *pda = cpu_pda(cpu);
+
+	/* Setup up data that may be needed in __get_free_pages early */
+	loadsegment(fs, 0);
+	loadsegment(gs, 0);
+	/* Memory clobbers used to order PDA accessed */
+	mb();
+	wrmsrl(MSR_GS_BASE, pda);
+	mb();
+
+	pda->cpunumber = cpu;
+	pda->irqcount = -1;
+	pda->kernelstack = (unsigned long)stack_thread_info() -
+				 PDA_STACKOFFSET + THREAD_SIZE;
+	pda->active_mm = &init_mm;
+	pda->mmu_state = 0;
+
+	if (cpu == 0) {
+		/* others are initialized in smpboot.c */
+		pda->pcurrent = &init_task;
+		pda->irqstackptr = boot_cpu_stack;
+		pda->irqstackptr += IRQSTACKSIZE - 64;
+	} else {
+		if (!pda->irqstackptr) {
+			pda->irqstackptr = (char *)
+				__get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
+			if (!pda->irqstackptr)
+				panic("cannot allocate irqstack for cpu %d",
+				      cpu);
+			pda->irqstackptr += IRQSTACKSIZE - 64;
+		}
+
+		if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
+			pda->nodenumber = cpu_to_node(cpu);
+	}
+}
+
+char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
+			   DEBUG_STKSZ] __page_aligned_bss;
 
-	for (cvdev = __x86cpuvendor_start ;
-	     cvdev < __x86cpuvendor_end   ;
-	     cvdev++)
-		cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
+extern asmlinkage void ignore_sysret(void);
 
-	early_cpu_detect();
-	validate_pat_support(&boot_cpu_data);
+/* May not be marked __init: used by software suspend */
+void syscall_init(void)
+{
+	/*
+	 * 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);
 }
 
+unsigned long kernel_eflags;
+
+/*
+ * 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);
+
+#else
+
 /* Make sure %fs is initialized properly in idle threads */
 struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
 {
@@ -651,25 +941,136 @@ struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
 	regs->fs = __KERNEL_PERCPU;
 	return regs;
 }
-
-/* Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one. */
-void switch_to_new_gdt(void)
-{
-	struct desc_ptr gdt_descr;
-
-	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");
-}
+#endif
 
 /*
  * 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
  */
+#ifdef CONFIG_X86_64
+void __cpuinit cpu_init(void)
+{
+	int cpu = stack_smp_processor_id();
+	struct tss_struct *t = &per_cpu(init_tss, cpu);
+	struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
+	unsigned long v;
+	char *estacks = NULL;
+	struct task_struct *me;
+	int i;
+
+	/* CPU 0 is initialised in head64.c */
+	if (cpu != 0)
+		pda_init(cpu);
+	else
+		estacks = boot_exception_stacks;
+
+	me = current;
+
+	if (cpu_test_and_set(cpu, cpu_initialized))
+		panic("CPU#%d already initialized!\n", cpu);
+
+	printk(KERN_INFO "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();
+	load_idt((const struct desc_ptr *)&idt_descr);
+
+	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();
+
+	check_efer();
+	if (cpu != 0 && x2apic)
+		enable_x2apic();
+
+	/*
+	 * set up and load the per-CPU TSS
+	 */
+	if (!orig_ist->ist[0]) {
+		static const unsigned int order[N_EXCEPTION_STACKS] = {
+		  [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
+		  [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+		};
+		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
+			if (cpu) {
+				estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
+				if (!estacks)
+					panic("Cannot allocate exception "
+					      "stack %ld %d\n", v, cpu);
+			}
+			estacks += PAGE_SIZE << order[v];
+			orig_ist->ist[v] = t->x86_tss.ist[v] =
+					(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;
+	if (me->mm)
+		BUG();
+	enter_lazy_tlb(&init_mm, me);
+
+	load_sp0(t, &current->thread);
+	set_tss_desc(cpu, t);
+	load_TR_desc();
+	load_LDT(&init_mm.context);
+
+#ifdef CONFIG_KGDB
+	/*
+	 * If the kgdb is connected no debug regs should be altered.  This
+	 * is only applicable when KGDB and a KGDB I/O module are built
+	 * into the kernel and you are using early debugging with
+	 * kgdbwait. KGDB will control the kernel HW breakpoint registers.
+	 */
+	if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
+		arch_kgdb_ops.correct_hw_break();
+	else {
+#endif
+	/*
+	 * Clear all 6 debug registers:
+	 */
+
+	set_debugreg(0UL, 0);
+	set_debugreg(0UL, 1);
+	set_debugreg(0UL, 2);
+	set_debugreg(0UL, 3);
+	set_debugreg(0UL, 6);
+	set_debugreg(0UL, 7);
+#ifdef CONFIG_KGDB
+	/* If the kgdb is connected no debug regs should be altered. */
+	}
+#endif
+
+	fpu_init();
+
+	raw_local_save_flags(kernel_eflags);
+
+	if (is_uv_system())
+		uv_cpu_init();
+}
+
+#else
+
 void __cpuinit cpu_init(void)
 {
 	int cpu = smp_processor_id();
@@ -723,19 +1124,21 @@ void __cpuinit cpu_init(void)
 	/*
 	 * Force FPU initialization:
 	 */
-	current_thread_info()->status = 0;
+	if (cpu_has_xsave)
+		current_thread_info()->status = TS_XSAVE;
+	else
+		current_thread_info()->status = 0;
 	clear_used_math();
 	mxcsr_feature_mask_init();
-}
 
-#ifdef CONFIG_HOTPLUG_CPU
-void __cpuinit cpu_uninit(void)
-{
-	int cpu = raw_smp_processor_id();
-	cpu_clear(cpu, cpu_initialized);
+	/*
+	 * Boot processor to setup the FP and extended state context info.
+	 */
+	if (!smp_processor_id())
+		init_thread_xstate();
 
-	/* lazy TLB state */
-	per_cpu(cpu_tlbstate, cpu).state = 0;
-	per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
+	xsave_init();
 }
+
+
 #endif
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
deleted file mode 100644
index a11f5d4477cd..000000000000
--- a/arch/x86/kernel/cpu/common_64.c
+++ /dev/null
@@ -1,712 +0,0 @@
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/bootmem.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/kgdb.h>
-#include <linux/topology.h>
-#include <linux/delay.h>
-#include <linux/smp.h>
-#include <linux/percpu.h>
-#include <asm/i387.h>
-#include <asm/msr.h>
-#include <asm/io.h>
-#include <asm/linkage.h>
-#include <asm/mmu_context.h>
-#include <asm/mtrr.h>
-#include <asm/mce.h>
-#include <asm/pat.h>
-#include <asm/asm.h>
-#include <asm/numa.h>
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#include <mach_apic.h>
-#endif
-#include <asm/pda.h>
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/proto.h>
-#include <asm/sections.h>
-#include <asm/setup.h>
-#include <asm/genapic.h>
-
-#include "cpu.h"
-
-/* 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
- */
-/* The TLS descriptors are currently at a different place compared to i386.
-   Hopefully nobody expects them at a fixed place (Wine?) */
-DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
-	[GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
-	[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
-	[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
-	[GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
-	[GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
-	[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
-} };
-EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
-
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
-
-/* Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one. */
-void switch_to_new_gdt(void)
-{
-	struct desc_ptr gdt_descr;
-
-	gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
-	gdt_descr.size = GDT_SIZE - 1;
-	load_gdt(&gdt_descr);
-}
-
-struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
-
-static void __cpuinit default_init(struct cpuinfo_x86 *c)
-{
-	display_cacheinfo(c);
-}
-
-static struct cpu_dev __cpuinitdata default_cpu = {
-	.c_init	= default_init,
-	.c_vendor = "Unknown",
-};
-static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
-
-int __cpuinit get_model_name(struct cpuinfo_x86 *c)
-{
-	unsigned int *v;
-
-	if (c->extended_cpuid_level < 0x80000004)
-		return 0;
-
-	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;
-	return 1;
-}
-
-
-void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
-{
-	unsigned int n, dummy, ebx, ecx, edx;
-
-	n = c->extended_cpuid_level;
-
-	if (n >= 0x80000005) {
-		cpuid(0x80000005, &dummy, &ebx, &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);
-		/* On K8 L1 TLB is inclusive, so don't count it */
-		c->x86_tlbsize = 0;
-	}
-
-	if (n >= 0x80000006) {
-		cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
-		ecx = cpuid_ecx(0x80000006);
-		c->x86_cache_size = ecx >> 16;
-		c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
-
-		printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
-		c->x86_cache_size, ecx & 0xFF);
-	}
-}
-
-void __cpuinit detect_ht(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	u32 eax, ebx, ecx, edx;
-	int index_msb, core_bits;
-
-	cpuid(1, &eax, &ebx, &ecx, &edx);
-
-
-	if (!cpu_has(c, X86_FEATURE_HT))
-		return;
-	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		goto out;
-
-	smp_num_siblings = (ebx & 0xff0000) >> 16;
-
-	if (smp_num_siblings == 1) {
-		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
-	} else if (smp_num_siblings > 1) {
-
-		if (smp_num_siblings > NR_CPUS) {
-			printk(KERN_WARNING "CPU: Unsupported number of "
-			       "siblings %d", smp_num_siblings);
-			smp_num_siblings = 1;
-			return;
-		}
-
-		index_msb = get_count_order(smp_num_siblings);
-		c->phys_proc_id = phys_pkg_id(index_msb);
-
-		smp_num_siblings = smp_num_siblings / c->x86_max_cores;
-
-		index_msb = get_count_order(smp_num_siblings);
-
-		core_bits = get_count_order(c->x86_max_cores);
-
-		c->cpu_core_id = phys_pkg_id(index_msb) &
-					       ((1 << core_bits) - 1);
-	}
-out:
-	if ((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);
-	}
-
-#endif
-}
-
-static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
-{
-	char *v = c->x86_vendor_id;
-	int i;
-	static int printed;
-
-	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;
-				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");
-	}
-	c->x86_vendor = X86_VENDOR_UNKNOWN;
-}
-
-static void __init early_cpu_support_print(void)
-{
-	int i,j;
-	struct cpu_dev *cpu_devx;
-
-	printk("KERNEL supported cpus:\n");
-	for (i = 0; i < X86_VENDOR_NUM; i++) {
-		cpu_devx = cpu_devs[i];
-		if (!cpu_devx)
-			continue;
-		for (j = 0; j < 2; j++) {
-			if (!cpu_devx->c_ident[j])
-				continue;
-			printk("  %s %s\n", cpu_devx->c_vendor,
-				cpu_devx->c_ident[j]);
-		}
-	}
-}
-
-/*
- * The NOPL instruction is supposed to exist on all CPUs with
- * 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.  Hence, probe for it based on first
- * principles.
- *
- * Note: no 64-bit chip is known to lack these, but put the code here
- * for consistency with 32 bits, and to make it utterly trivial to
- * diagnose the problem should it ever surface.
- */
-static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
-{
-	const u32 nopl_signature = 0x888c53b1; /* Random number */
-	u32 has_nopl = nopl_signature;
-
-	clear_cpu_cap(c, X86_FEATURE_NOPL);
-	if (c->x86 >= 6) {
-		asm volatile("\n"
-			     "1:      .byte 0x0f,0x1f,0xc0\n" /* nopl %eax */
-			     "2:\n"
-			     "        .section .fixup,\"ax\"\n"
-			     "3:      xor %0,%0\n"
-			     "        jmp 2b\n"
-			     "        .previous\n"
-			     _ASM_EXTABLE(1b,3b)
-			     : "+a" (has_nopl));
-
-		if (has_nopl == nopl_signature)
-			set_cpu_cap(c, X86_FEATURE_NOPL);
-	}
-}
-
-static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c);
-
-void __init early_cpu_init(void)
-{
-        struct cpu_vendor_dev *cvdev;
-
-        for (cvdev = __x86cpuvendor_start ;
-             cvdev < __x86cpuvendor_end   ;
-             cvdev++)
-                cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
-	early_cpu_support_print();
-	early_identify_cpu(&boot_cpu_data);
-}
-
-/* Do some early cpuid on the boot CPU to get some parameter that are
-   needed before check_bugs. Everything advanced is in identify_cpu
-   below. */
-static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
-{
-	u32 tfms, xlvl;
-
-	c->loops_per_jiffy = loops_per_jiffy;
-	c->x86_cache_size = -1;
-	c->x86_vendor = X86_VENDOR_UNKNOWN;
-	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_clflush_size = 64;
-	c->x86_cache_alignment = c->x86_clflush_size;
-	c->x86_max_cores = 1;
-	c->x86_coreid_bits = 0;
-	c->extended_cpuid_level = 0;
-	memset(&c->x86_capability, 0, sizeof c->x86_capability);
-
-	/* 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);
-
-	/* 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 misc;
-		cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4],
-		      &c->x86_capability[0]);
-		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;
-		if (test_cpu_cap(c, X86_FEATURE_CLFLSH))
-			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
-	} else {
-		/* Have CPUID level 0 only - unheard of */
-		c->x86 = 4;
-	}
-
-	c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xff;
-#ifdef CONFIG_SMP
-	c->phys_proc_id = c->initial_apicid;
-#endif
-	/* 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 (xlvl >= 0x80000004)
-			get_model_name(c); /* Default name */
-	}
-
-	/* Transmeta-defined flags: level 0x80860001 */
-	xlvl = cpuid_eax(0x80860000);
-	if ((xlvl & 0xffff0000) == 0x80860000) {
-		/* Don't set x86_cpuid_level here for now to not confuse. */
-		if (xlvl >= 0x80860001)
-			c->x86_capability[2] = cpuid_edx(0x80860001);
-	}
-
-	if (c->extended_cpuid_level >= 0x80000007)
-		c->x86_power = cpuid_edx(0x80000007);
-
-	if (c->extended_cpuid_level >= 0x80000008) {
-		u32 eax = cpuid_eax(0x80000008);
-
-		c->x86_virt_bits = (eax >> 8) & 0xff;
-		c->x86_phys_bits = eax & 0xff;
-	}
-
-	detect_nopl(c);
-
-	if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
-	    cpu_devs[c->x86_vendor]->c_early_init)
-		cpu_devs[c->x86_vendor]->c_early_init(c);
-
-	validate_pat_support(c);
-}
-
-/*
- * This does the hard work of actually picking apart the CPU stuff...
- */
-static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
-{
-	int i;
-
-	early_identify_cpu(c);
-
-	init_scattered_cpuid_features(c);
-
-	c->apicid = phys_pkg_id(0);
-
-	/*
-	 * Vendor-specific initialization.  In this section we
-	 * canonicalize the feature flags, meaning if there are
-	 * features a certain CPU supports which CPUID doesn't
-	 * tell us, CPUID claiming incorrect flags, or other bugs,
-	 * we handle them here.
-	 *
-	 * At the end of this section, c->x86_capability better
-	 * indicate the features this CPU genuinely supports!
-	 */
-	if (this_cpu->c_init)
-		this_cpu->c_init(c);
-
-	detect_ht(c);
-
-	/*
-	 * 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) {
-		/* AND the already accumulated flags with these */
-		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];
-
-#ifdef CONFIG_X86_MCE
-	mcheck_init(c);
-#endif
-	select_idle_routine(c);
-
-#ifdef CONFIG_NUMA
-	numa_add_cpu(smp_processor_id());
-#endif
-
-}
-
-void __cpuinit identify_boot_cpu(void)
-{
-	identify_cpu(&boot_cpu_data);
-}
-
-void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
-{
-	BUG_ON(c == &boot_cpu_data);
-	identify_cpu(c);
-	mtrr_ap_init();
-}
-
-static __init int setup_noclflush(char *arg)
-{
-	setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
-	return 1;
-}
-__setup("noclflush", setup_noclflush);
-
-void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
-{
-	if (c->x86_model_id[0])
-		printk(KERN_CONT "%s", c->x86_model_id);
-
-	if (c->x86_mask || c->cpuid_level >= 0)
-		printk(KERN_CONT " stepping %02x\n", c->x86_mask);
-	else
-		printk(KERN_CONT "\n");
-}
-
-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;
-
-struct x8664_pda **_cpu_pda __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
-
-struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
-
-char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
-
-unsigned long __supported_pte_mask __read_mostly = ~0UL;
-EXPORT_SYMBOL_GPL(__supported_pte_mask);
-
-static int do_not_nx __cpuinitdata;
-
-/* noexec=on|off
-Control non executable mappings for 64bit processes.
-
-on	Enable(default)
-off	Disable
-*/
-static int __init nonx_setup(char *str)
-{
-	if (!str)
-		return -EINVAL;
-	if (!strncmp(str, "on", 2)) {
-		__supported_pte_mask |= _PAGE_NX;
-		do_not_nx = 0;
-	} else if (!strncmp(str, "off", 3)) {
-		do_not_nx = 1;
-		__supported_pte_mask &= ~_PAGE_NX;
-	}
-	return 0;
-}
-early_param("noexec", nonx_setup);
-
-int force_personality32;
-
-/* noexec32=on|off
-Control non executable heap for 32bit processes.
-To control the stack too use noexec=off
-
-on	PROT_READ does not imply PROT_EXEC for 32bit processes (default)
-off	PROT_READ implies PROT_EXEC
-*/
-static int __init nonx32_setup(char *str)
-{
-	if (!strcmp(str, "on"))
-		force_personality32 &= ~READ_IMPLIES_EXEC;
-	else if (!strcmp(str, "off"))
-		force_personality32 |= READ_IMPLIES_EXEC;
-	return 1;
-}
-__setup("noexec32=", nonx32_setup);
-
-void pda_init(int cpu)
-{
-	struct x8664_pda *pda = cpu_pda(cpu);
-
-	/* Setup up data that may be needed in __get_free_pages early */
-	loadsegment(fs, 0);
-	loadsegment(gs, 0);
-	/* Memory clobbers used to order PDA accessed */
-	mb();
-	wrmsrl(MSR_GS_BASE, pda);
-	mb();
-
-	pda->cpunumber = cpu;
-	pda->irqcount = -1;
-	pda->kernelstack = (unsigned long)stack_thread_info() -
-				 PDA_STACKOFFSET + THREAD_SIZE;
-	pda->active_mm = &init_mm;
-	pda->mmu_state = 0;
-
-	if (cpu == 0) {
-		/* others are initialized in smpboot.c */
-		pda->pcurrent = &init_task;
-		pda->irqstackptr = boot_cpu_stack;
-		pda->irqstackptr += IRQSTACKSIZE - 64;
-	} else {
-		if (!pda->irqstackptr) {
-			pda->irqstackptr = (char *)
-				__get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
-			if (!pda->irqstackptr)
-				panic("cannot allocate irqstack for cpu %d",
-				      cpu);
-			pda->irqstackptr += IRQSTACKSIZE - 64;
-		}
-
-		if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
-			pda->nodenumber = cpu_to_node(cpu);
-	}
-}
-
-char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
-			   DEBUG_STKSZ] __page_aligned_bss;
-
-extern asmlinkage void ignore_sysret(void);
-
-/* May not be marked __init: used by software suspend */
-void syscall_init(void)
-{
-	/*
-	 * 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);
-}
-
-void __cpuinit check_efer(void)
-{
-	unsigned long efer;
-
-	rdmsrl(MSR_EFER, efer);
-	if (!(efer & EFER_NX) || do_not_nx)
-		__supported_pte_mask &= ~_PAGE_NX;
-}
-
-unsigned long kernel_eflags;
-
-/*
- * 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);
-
-/*
- * 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.
- */
-void __cpuinit cpu_init(void)
-{
-	int cpu = stack_smp_processor_id();
-	struct tss_struct *t = &per_cpu(init_tss, cpu);
-	struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
-	unsigned long v;
-	char *estacks = NULL;
-	struct task_struct *me;
-	int i;
-
-	/* CPU 0 is initialised in head64.c */
-	if (cpu != 0)
-		pda_init(cpu);
-	else
-		estacks = boot_exception_stacks;
-
-	me = current;
-
-	if (cpu_test_and_set(cpu, cpu_initialized))
-		panic("CPU#%d already initialized!\n", cpu);
-
-	printk(KERN_INFO "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();
-	load_idt((const struct desc_ptr *)&idt_descr);
-
-	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();
-
-	check_efer();
-
-	/*
-	 * set up and load the per-CPU TSS
-	 */
-	if (!orig_ist->ist[0]) {
-		static const unsigned int order[N_EXCEPTION_STACKS] = {
-		  [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
-		  [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
-		};
-		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
-			if (cpu) {
-				estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
-				if (!estacks)
-					panic("Cannot allocate exception "
-					      "stack %ld %d\n", v, cpu);
-			}
-			estacks += PAGE_SIZE << order[v];
-			orig_ist->ist[v] = t->x86_tss.ist[v] =
-					(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;
-	if (me->mm)
-		BUG();
-	enter_lazy_tlb(&init_mm, me);
-
-	load_sp0(t, &current->thread);
-	set_tss_desc(cpu, t);
-	load_TR_desc();
-	load_LDT(&init_mm.context);
-
-#ifdef CONFIG_KGDB
-	/*
-	 * If the kgdb is connected no debug regs should be altered.  This
-	 * is only applicable when KGDB and a KGDB I/O module are built
-	 * into the kernel and you are using early debugging with
-	 * kgdbwait. KGDB will control the kernel HW breakpoint registers.
-	 */
-	if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
-		arch_kgdb_ops.correct_hw_break();
-	else {
-#endif
-	/*
-	 * Clear all 6 debug registers:
-	 */
-
-	set_debugreg(0UL, 0);
-	set_debugreg(0UL, 1);
-	set_debugreg(0UL, 2);
-	set_debugreg(0UL, 3);
-	set_debugreg(0UL, 6);
-	set_debugreg(0UL, 7);
-#ifdef CONFIG_KGDB
-	/* If the kgdb is connected no debug regs should be altered. */
-	}
-#endif
-
-	fpu_init();
-
-	raw_local_save_flags(kernel_eflags);
-
-	if (is_uv_system())
-		uv_cpu_init();
-}
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 4d894e8565fe..de4094a39210 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -21,23 +21,16 @@ struct cpu_dev {
 	void		(*c_init)(struct cpuinfo_x86 * c);
 	void		(*c_identify)(struct cpuinfo_x86 * c);
 	unsigned int	(*c_size_cache)(struct cpuinfo_x86 * c, unsigned int size);
+	int	c_x86_vendor;
 };
 
-extern struct cpu_dev * cpu_devs [X86_VENDOR_NUM];
+#define cpu_dev_register(cpu_devX) \
+	static struct cpu_dev *__cpu_dev_##cpu_devX __used \
+	__attribute__((__section__(".x86_cpu_dev.init"))) = \
+	&cpu_devX;
 
-struct cpu_vendor_dev {
-	int vendor;
-	struct cpu_dev *cpu_dev;
-};
-
-#define cpu_vendor_dev_register(cpu_vendor_id, cpu_dev) \
-	static struct cpu_vendor_dev __cpu_vendor_dev_##cpu_vendor_id __used \
-	__attribute__((__section__(".x86cpuvendor.init"))) = \
-	{ cpu_vendor_id, cpu_dev }
-
-extern struct cpu_vendor_dev __x86cpuvendor_start[], __x86cpuvendor_end[];
+extern struct cpu_dev *__x86_cpu_dev_start[], *__x86_cpu_dev_end[];
 
-extern int get_model_name(struct cpuinfo_x86 *c);
 extern void display_cacheinfo(struct cpuinfo_x86 *c);
 
 #endif
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index dd097b835839..c24c4a487b7c 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -256,7 +256,8 @@ static u32 get_cur_val(const cpumask_t *mask)
  * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
  * no meaning should be associated with absolute values of these MSRs.
  */
-static unsigned int get_measured_perf(unsigned int cpu)
+static unsigned int get_measured_perf(struct cpufreq_policy *policy,
+				      unsigned int cpu)
 {
 	union {
 		struct {
@@ -326,7 +327,7 @@ static unsigned int get_measured_perf(unsigned int cpu)
 
 #endif
 
-	retval = per_cpu(drv_data, cpu)->max_freq * perf_percent / 100;
+	retval = per_cpu(drv_data, policy->cpu)->max_freq * perf_percent / 100;
 
 	put_cpu();
 	set_cpus_allowed_ptr(current, &saved_mask);
@@ -785,7 +786,11 @@ static int __init acpi_cpufreq_init(void)
 	if (ret)
 		return ret;
 
-	return cpufreq_register_driver(&acpi_cpufreq_driver);
+	ret = cpufreq_register_driver(&acpi_cpufreq_driver);
+	if (ret)
+		free_percpu(acpi_perf_data);
+
+	return ret;
 }
 
 static void __exit acpi_cpufreq_exit(void)
@@ -795,8 +800,6 @@ static void __exit acpi_cpufreq_exit(void)
 	cpufreq_unregister_driver(&acpi_cpufreq_driver);
 
 	free_percpu(acpi_perf_data);
-
-	return;
 }
 
 module_param(acpi_pstate_strict, uint, 0644);
diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
index e4a4bf870e94..fe613c93b366 100644
--- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
@@ -25,8 +25,8 @@
 #include <linux/cpufreq.h>
 
 #include <asm/msr.h>
-#include <asm/timex.h>
-#include <asm/io.h>
+#include <linux/timex.h>
+#include <linux/io.h>
 
 #define REG_CSCIR 0x22		/* Chip Setup and Control Index Register    */
 #define REG_CSCDR 0x23		/* Chip Setup and Control Data  Register    */
@@ -82,7 +82,7 @@ static unsigned int elanfreq_get_cpu_frequency(unsigned int cpu)
 	u8 clockspeed_reg;    /* Clock Speed Register */
 
 	local_irq_disable();
-	outb_p(0x80,REG_CSCIR);
+	outb_p(0x80, REG_CSCIR);
 	clockspeed_reg = inb_p(REG_CSCDR);
 	local_irq_enable();
 
@@ -98,10 +98,10 @@ static unsigned int elanfreq_get_cpu_frequency(unsigned int cpu)
 	}
 
 	/* 33 MHz is not 32 MHz... */
-	if ((clockspeed_reg & 0xE0)==0xA0)
+	if ((clockspeed_reg & 0xE0) == 0xA0)
 		return 33000;
 
-	return ((1<<((clockspeed_reg & 0xE0) >> 5)) * 1000);
+	return (1<<((clockspeed_reg & 0xE0) >> 5)) * 1000;
 }
 
 
@@ -117,7 +117,7 @@ static unsigned int elanfreq_get_cpu_frequency(unsigned int cpu)
  *	There is no return value.
  */
 
-static void elanfreq_set_cpu_state (unsigned int state)
+static void elanfreq_set_cpu_state(unsigned int state)
 {
 	struct cpufreq_freqs    freqs;
 
@@ -144,20 +144,20 @@ static void elanfreq_set_cpu_state (unsigned int state)
 	 */
 
 	local_irq_disable();
-	outb_p(0x40,REG_CSCIR);		/* Disable hyperspeed mode */
-	outb_p(0x00,REG_CSCDR);
+	outb_p(0x40, REG_CSCIR);		/* Disable hyperspeed mode */
+	outb_p(0x00, REG_CSCDR);
 	local_irq_enable();		/* wait till internal pipelines and */
 	udelay(1000);			/* buffers have cleaned up          */
 
 	local_irq_disable();
 
 	/* now, set the CPU clock speed register (0x80) */
-	outb_p(0x80,REG_CSCIR);
-	outb_p(elan_multiplier[state].val80h,REG_CSCDR);
+	outb_p(0x80, REG_CSCIR);
+	outb_p(elan_multiplier[state].val80h, REG_CSCDR);
 
 	/* now, the hyperspeed bit in PMU Force Mode Register (0x40) */
-	outb_p(0x40,REG_CSCIR);
-	outb_p(elan_multiplier[state].val40h,REG_CSCDR);
+	outb_p(0x40, REG_CSCIR);
+	outb_p(elan_multiplier[state].val40h, REG_CSCDR);
 	udelay(10000);
 	local_irq_enable();
 
@@ -173,12 +173,12 @@ static void elanfreq_set_cpu_state (unsigned int state)
  *	for the hardware supported by the driver.
  */
 
-static int elanfreq_verify (struct cpufreq_policy *policy)
+static int elanfreq_verify(struct cpufreq_policy *policy)
 {
 	return cpufreq_frequency_table_verify(policy, &elanfreq_table[0]);
 }
 
-static int elanfreq_target (struct cpufreq_policy *policy,
+static int elanfreq_target(struct cpufreq_policy *policy,
 			    unsigned int target_freq,
 			    unsigned int relation)
 {
@@ -205,7 +205,7 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy)
 
 	/* capability check */
 	if ((c->x86_vendor != X86_VENDOR_AMD) ||
-	    (c->x86 != 4) || (c->x86_model!=10))
+	    (c->x86 != 4) || (c->x86_model != 10))
 		return -ENODEV;
 
 	/* max freq */
@@ -213,7 +213,7 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy)
 		max_freq = elanfreq_get_cpu_frequency(0);
 
 	/* table init */
-	for (i=0; (elanfreq_table[i].frequency != CPUFREQ_TABLE_END); i++) {
+	for (i = 0; (elanfreq_table[i].frequency != CPUFREQ_TABLE_END); i++) {
 		if (elanfreq_table[i].frequency > max_freq)
 			elanfreq_table[i].frequency = CPUFREQ_ENTRY_INVALID;
 	}
@@ -224,7 +224,7 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy)
 
 	result = cpufreq_frequency_table_cpuinfo(policy, elanfreq_table);
 	if (result)
-		return (result);
+		return result;
 
 	cpufreq_frequency_table_get_attr(elanfreq_table, policy->cpu);
 	return 0;
@@ -260,7 +260,7 @@ __setup("elanfreq=", elanfreq_setup);
 #endif
 
 
-static struct freq_attr* elanfreq_attr[] = {
+static struct freq_attr *elanfreq_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
 	NULL,
 };
@@ -284,9 +284,9 @@ static int __init elanfreq_init(void)
 
 	/* Test if we have the right hardware */
 	if ((c->x86_vendor != X86_VENDOR_AMD) ||
-		(c->x86 != 4) || (c->x86_model!=10)) {
+		(c->x86 != 4) || (c->x86_model != 10)) {
 		printk(KERN_INFO "elanfreq: error: no Elan processor found!\n");
-                return -ENODEV;
+		return -ENODEV;
 	}
 	return cpufreq_register_driver(&elanfreq_driver);
 }
@@ -298,7 +298,7 @@ static void __exit elanfreq_exit(void)
 }
 
 
-module_param (max_freq, int, 0444);
+module_param(max_freq, int, 0444);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Robert Schwebel <r.schwebel@pengutronix.de>, Sven Geggus <sven@geggus.net>");
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
index eb9b62b0830c..b5ced806a316 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
@@ -15,12 +15,11 @@
 #include <linux/slab.h>
 
 #include <asm/msr.h>
-#include <asm/timex.h>
-#include <asm/io.h>
+#include <linux/timex.h>
+#include <linux/io.h>
 
-
-#define POWERNOW_IOPORT 0xfff0         /* it doesn't matter where, as long
-					  as it is unused */
+#define POWERNOW_IOPORT 0xfff0          /* it doesn't matter where, as long
+					   as it is unused */
 
 static unsigned int                     busfreq;   /* FSB, in 10 kHz */
 static unsigned int                     max_multiplier;
@@ -53,7 +52,7 @@ static int powernow_k6_get_cpu_multiplier(void)
 
 	msrval = POWERNOW_IOPORT + 0x1;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
-	invalue=inl(POWERNOW_IOPORT + 0x8);
+	invalue = inl(POWERNOW_IOPORT + 0x8);
 	msrval = POWERNOW_IOPORT + 0x0;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
 
@@ -67,9 +66,9 @@ static int powernow_k6_get_cpu_multiplier(void)
  *
  *   Tries to change the PowerNow! multiplier
  */
-static void powernow_k6_set_state (unsigned int best_i)
+static void powernow_k6_set_state(unsigned int best_i)
 {
-	unsigned long           outvalue=0, invalue=0;
+	unsigned long           outvalue = 0, invalue = 0;
 	unsigned long           msrval;
 	struct cpufreq_freqs    freqs;
 
@@ -90,10 +89,10 @@ static void powernow_k6_set_state (unsigned int best_i)
 
 	msrval = POWERNOW_IOPORT + 0x1;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
-	invalue=inl(POWERNOW_IOPORT + 0x8);
+	invalue = inl(POWERNOW_IOPORT + 0x8);
 	invalue = invalue & 0xf;
 	outvalue = outvalue | invalue;
-	outl(outvalue ,(POWERNOW_IOPORT + 0x8));
+	outl(outvalue , (POWERNOW_IOPORT + 0x8));
 	msrval = POWERNOW_IOPORT + 0x0;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
 
@@ -124,7 +123,7 @@ static int powernow_k6_verify(struct cpufreq_policy *policy)
  *
  * sets a new CPUFreq policy
  */
-static int powernow_k6_target (struct cpufreq_policy *policy,
+static int powernow_k6_target(struct cpufreq_policy *policy,
 			       unsigned int target_freq,
 			       unsigned int relation)
 {
@@ -152,7 +151,7 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 	busfreq = cpu_khz / max_multiplier;
 
 	/* table init */
-	for (i=0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
+	for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
 		if (clock_ratio[i].index > max_multiplier)
 			clock_ratio[i].frequency = CPUFREQ_ENTRY_INVALID;
 		else
@@ -165,7 +164,7 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 
 	result = cpufreq_frequency_table_cpuinfo(policy, clock_ratio);
 	if (result)
-		return (result);
+		return result;
 
 	cpufreq_frequency_table_get_attr(clock_ratio, policy->cpu);
 
@@ -176,8 +175,8 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 static int powernow_k6_cpu_exit(struct cpufreq_policy *policy)
 {
 	unsigned int i;
-	for (i=0; i<8; i++) {
-		if (i==max_multiplier)
+	for (i = 0; i < 8; i++) {
+		if (i == max_multiplier)
 			powernow_k6_set_state(i);
 	}
 	cpufreq_frequency_table_put_attr(policy->cpu);
@@ -189,7 +188,7 @@ static unsigned int powernow_k6_get(unsigned int cpu)
 	return busfreq * powernow_k6_get_cpu_multiplier();
 }
 
-static struct freq_attr* powernow_k6_attr[] = {
+static struct freq_attr *powernow_k6_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
 	NULL,
 };
@@ -227,7 +226,7 @@ static int __init powernow_k6_init(void)
 	}
 
 	if (cpufreq_register_driver(&powernow_k6_driver)) {
-		release_region (POWERNOW_IOPORT, 16);
+		release_region(POWERNOW_IOPORT, 16);
 		return -EINVAL;
 	}
 
@@ -243,13 +242,13 @@ static int __init powernow_k6_init(void)
 static void __exit powernow_k6_exit(void)
 {
 	cpufreq_unregister_driver(&powernow_k6_driver);
-	release_region (POWERNOW_IOPORT, 16);
+	release_region(POWERNOW_IOPORT, 16);
 }
 
 
-MODULE_AUTHOR ("Arjan van de Ven <arjanv@redhat.com>, Dave Jones <davej@codemonkey.org.uk>, Dominik Brodowski <linux@brodo.de>");
-MODULE_DESCRIPTION ("PowerNow! driver for AMD K6-2+ / K6-3+ processors.");
-MODULE_LICENSE ("GPL");
+MODULE_AUTHOR("Arjan van de Ven <arjanv@redhat.com>, Dave Jones <davej@codemonkey.org.uk>, Dominik Brodowski <linux@brodo.de>");
+MODULE_DESCRIPTION("PowerNow! driver for AMD K6-2+ / K6-3+ processors.");
+MODULE_LICENSE("GPL");
 
 module_init(powernow_k6_init);
 module_exit(powernow_k6_exit);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 898a5a2002ed..ffd0f5ed071a 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -121,7 +121,7 @@ static void __cpuinit set_cx86_reorder(void)
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */
 
 	/* Load/Store Serialize to mem access disable (=reorder it) */
-	setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80);
+	setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80);
 	/* set load/store serialize from 1GB to 4GB */
 	ccr3 |= 0xe0;
 	setCx86(CX86_CCR3, ccr3);
@@ -132,11 +132,11 @@ static void __cpuinit set_cx86_memwb(void)
 	printk(KERN_INFO "Enable Memory-Write-back mode on Cyrix/NSC processor.\n");
 
 	/* CCR2 bit 2: unlock NW bit */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04);
+	setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04);
 	/* set 'Not Write-through' */
 	write_cr0(read_cr0() | X86_CR0_NW);
 	/* CCR2 bit 2: lock NW bit and set WT1 */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14);
+	setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14);
 }
 
 /*
@@ -150,14 +150,14 @@ static void __cpuinit geode_configure(void)
 	local_irq_save(flags);
 
 	/* Suspend on halt power saving and enable #SUSP pin */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+	setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88);
 
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */
 
 
 	/* FPU fast, DTE cache, Mem bypass */
-	setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38);
+	setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38);
 	setCx86(CX86_CCR3, ccr3);			/* disable MAPEN */
 
 	set_cx86_memwb();
@@ -291,7 +291,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
 		/* GXm supports extended cpuid levels 'ala' AMD */
 		if (c->cpuid_level == 2) {
 			/* Enable cxMMX extensions (GX1 Datasheet 54) */
-			setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1);
+			setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1);
 
 			/*
 			 * GXm : 0x30 ... 0x5f GXm  datasheet 51
@@ -301,7 +301,6 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
 			 */
 			if ((0x30 <= dir1 && dir1 <= 0x6f) || (0x80 <= dir1 && dir1 <= 0x8f))
 				geode_configure();
-			get_model_name(c);  /* get CPU marketing name */
 			return;
 		} else { /* MediaGX */
 			Cx86_cb[2] = (dir0_lsn & 1) ? '3' : '4';
@@ -314,7 +313,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
 		if (dir1 > 7) {
 			dir0_msn++;  /* M II */
 			/* Enable MMX extensions (App note 108) */
-			setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1);
+			setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1);
 		} else {
 			c->coma_bug = 1;      /* 6x86MX, it has the bug. */
 		}
@@ -429,7 +428,7 @@ static void __cpuinit cyrix_identify(struct cpuinfo_x86 *c)
 			local_irq_save(flags);
 			ccr3 = getCx86(CX86_CCR3);
 			setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);       /* enable MAPEN  */
-			setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80);  /* enable cpuid  */
+			setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80);  /* enable cpuid  */
 			setCx86(CX86_CCR3, ccr3);                       /* disable MAPEN */
 			local_irq_restore(flags);
 		}
@@ -442,14 +441,16 @@ static struct cpu_dev cyrix_cpu_dev __cpuinitdata = {
 	.c_early_init	= early_init_cyrix,
 	.c_init		= init_cyrix,
 	.c_identify	= cyrix_identify,
+	.c_x86_vendor	= X86_VENDOR_CYRIX,
 };
 
-cpu_vendor_dev_register(X86_VENDOR_CYRIX, &cyrix_cpu_dev);
+cpu_dev_register(cyrix_cpu_dev);
 
 static struct cpu_dev nsc_cpu_dev __cpuinitdata = {
 	.c_vendor	= "NSC",
 	.c_ident	= { "Geode by NSC" },
 	.c_init		= init_nsc,
+	.c_x86_vendor	= X86_VENDOR_NSC,
 };
 
-cpu_vendor_dev_register(X86_VENDOR_NSC, &nsc_cpu_dev);
+cpu_dev_register(nsc_cpu_dev);
diff --git a/arch/x86/kernel/cpu/feature_names.c b/arch/x86/kernel/cpu/feature_names.c
deleted file mode 100644
index c9017799497c..000000000000
--- a/arch/x86/kernel/cpu/feature_names.c
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * Strings for the various x86 capability flags.
- *
- * This file must not contain any executable code.
- */
-
-#include <asm/cpufeature.h>
-
-/*
- * These flag bits must match the definitions in <asm/cpufeature.h>.
- * NULL means this bit is undefined or reserved; either way it doesn't
- * have meaning as far as Linux is concerned.  Note that it's important
- * to realize there is a difference between this table and CPUID -- if
- * applications want to get the raw CPUID data, they should access
- * /dev/cpu/<cpu_nr>/cpuid instead.
- */
-const char * const x86_cap_flags[NCAPINTS*32] = {
-	/* Intel-defined */
-	"fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
-	"cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
-	"pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx",
-	"fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", "pbe",
-
-	/* AMD-defined */
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, "mp", "nx", NULL, "mmxext", NULL,
-	NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm",
-	"3dnowext", "3dnow",
-
-	/* Transmeta-defined */
-	"recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
-	/* Other (Linux-defined) */
-	"cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr",
-	NULL, NULL, NULL, NULL,
-	"constant_tsc", "up", NULL, "arch_perfmon",
-	"pebs", "bts", NULL, NULL,
-	"rep_good", NULL, NULL, NULL,
-	"nopl", NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
-	/* Intel-defined (#2) */
-	"pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est",
-	"tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
-	NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt",
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
-	/* VIA/Cyrix/Centaur-defined */
-	NULL, NULL, "rng", "rng_en", NULL, NULL, "ace", "ace_en",
-	"ace2", "ace2_en", "phe", "phe_en", "pmm", "pmm_en", NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
-	/* AMD-defined (#2) */
-	"lahf_lm", "cmp_legacy", "svm", "extapic",
-	"cr8_legacy", "abm", "sse4a", "misalignsse",
-	"3dnowprefetch", "osvw", "ibs", "sse5",
-	"skinit", "wdt", NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
-	/* Auxiliary (Linux-defined) */
-	"ida", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-};
-
-const char *const x86_power_flags[32] = {
-	"ts",	/* temperature sensor */
-	"fid",  /* frequency id control */
-	"vid",  /* voltage id control */
-	"ttp",  /* thermal trip */
-	"tm",
-	"stc",
-	"100mhzsteps",
-	"hwpstate",
-	"",	/* tsc invariant mapped to constant_tsc */
-		/* nothing */
-};
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b75f2569b8f8..99468dbd08da 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -15,6 +15,11 @@
 #include <asm/ds.h>
 #include <asm/bugs.h>
 
+#ifdef CONFIG_X86_64
+#include <asm/topology.h>
+#include <asm/numa_64.h>
+#endif
+
 #include "cpu.h"
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -23,23 +28,22 @@
 #include <mach_apic.h>
 #endif
 
-#ifdef CONFIG_X86_INTEL_USERCOPY
-/*
- * Alignment at which movsl is preferred for bulk memory copies.
- */
-struct movsl_mask movsl_mask __read_mostly;
-#endif
-
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
-	/* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
-	if (c->x86 == 15 && c->x86_cache_alignment == 64)
-		c->x86_cache_alignment = 128;
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+
+#ifdef CONFIG_X86_64
+	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+#else
+	/* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
+	if (c->x86 == 15 && c->x86_cache_alignment == 64)
+		c->x86_cache_alignment = 128;
+#endif
 }
 
+#ifdef CONFIG_X86_32
 /*
  *	Early probe support logic for ppro memory erratum #50
  *
@@ -59,15 +63,54 @@ int __cpuinit ppro_with_ram_bug(void)
 	return 0;
 }
 
+#ifdef CONFIG_X86_F00F_BUG
+static void __cpuinit trap_init_f00f_bug(void)
+{
+	__set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
 
-/*
- * P4 Xeon errata 037 workaround.
- * Hardware prefetcher may cause stale data to be loaded into the cache.
- */
-static void __cpuinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
+	/*
+	 * Update the IDT descriptor and reload the IDT so that
+	 * it uses the read-only mapped virtual address.
+	 */
+	idt_descr.address = fix_to_virt(FIX_F00F_IDT);
+	load_idt(&idt_descr);
+}
+#endif
+
+static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
 {
 	unsigned long lo, hi;
 
+#ifdef CONFIG_X86_F00F_BUG
+	/*
+	 * All current models of Pentium and Pentium with MMX technology CPUs
+	 * have the F0 0F bug, which lets nonprivileged users lock up the system.
+	 * Note that the workaround only should be initialized once...
+	 */
+	c->f00f_bug = 0;
+	if (!paravirt_enabled() && c->x86 == 5) {
+		static int f00f_workaround_enabled;
+
+		c->f00f_bug = 1;
+		if (!f00f_workaround_enabled) {
+			trap_init_f00f_bug();
+			printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
+			f00f_workaround_enabled = 1;
+		}
+	}
+#endif
+
+	/*
+	 * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until
+	 * model 3 mask 3
+	 */
+	if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)
+		clear_cpu_cap(c, X86_FEATURE_SEP);
+
+	/*
+	 * P4 Xeon errata 037 workaround.
+	 * Hardware prefetcher may cause stale data to be loaded into the cache.
+	 */
 	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
 		rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
 		if ((lo & (1<<9)) == 0) {
@@ -77,13 +120,68 @@ static void __cpuinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
 			wrmsr (MSR_IA32_MISC_ENABLE, lo, hi);
 		}
 	}
+
+	/*
+	 * See if we have a good local APIC by checking for buggy Pentia,
+	 * i.e. all B steppings and the C2 stepping of P54C when using their
+	 * integrated APIC (see 11AP erratum in "Pentium Processor
+	 * Specification Update").
+	 */
+	if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
+	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
+		set_cpu_cap(c, X86_FEATURE_11AP);
+
+
+#ifdef CONFIG_X86_INTEL_USERCOPY
+	/*
+	 * Set up the preferred alignment for movsl bulk memory moves
+	 */
+	switch (c->x86) {
+	case 4:		/* 486: untested */
+		break;
+	case 5:		/* Old Pentia: untested */
+		break;
+	case 6:		/* PII/PIII only like movsl with 8-byte alignment */
+		movsl_mask.mask = 7;
+		break;
+	case 15:	/* P4 is OK down to 8-byte alignment */
+		movsl_mask.mask = 7;
+		break;
+	}
+#endif
+
+#ifdef CONFIG_X86_NUMAQ
+	numaq_tsc_disable();
+#endif
 }
+#else
+static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
+{
+}
+#endif
 
+static void __cpuinit srat_detect_node(void)
+{
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+	unsigned node;
+	int cpu = smp_processor_id();
+	int apicid = hard_smp_processor_id();
+
+	/* Don't do the funky fallback heuristics the AMD version employs
+	   for now. */
+	node = apicid_to_node[apicid];
+	if (node == NUMA_NO_NODE || !node_online(node))
+		node = first_node(node_online_map);
+	numa_set_node(cpu, node);
+
+	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+}
 
 /*
  * find out the number of processor cores on the die
  */
-static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c)
+static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
 {
 	unsigned int eax, ebx, ecx, edx;
 
@@ -98,45 +196,51 @@ static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c)
 		return 1;
 }
 
-#ifdef CONFIG_X86_F00F_BUG
-static void __cpuinit trap_init_f00f_bug(void)
+static void __cpuinit detect_vmx_virtcap(struct cpuinfo_x86 *c)
 {
-	__set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
-
-	/*
-	 * Update the IDT descriptor and reload the IDT so that
-	 * it uses the read-only mapped virtual address.
-	 */
-	idt_descr.address = fix_to_virt(FIX_F00F_IDT);
-	load_idt(&idt_descr);
+	/* Intel VMX MSR indicated features */
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW	0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI		0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS	0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020
+
+	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+	clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+	clear_cpu_cap(c, X86_FEATURE_VNMI);
+	clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+	clear_cpu_cap(c, X86_FEATURE_EPT);
+	clear_cpu_cap(c, X86_FEATURE_VPID);
+
+	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+	msr_ctl = vmx_msr_high | vmx_msr_low;
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+		set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+		set_cpu_cap(c, X86_FEATURE_VNMI);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+		      vmx_msr_low, vmx_msr_high);
+		msr_ctl2 = vmx_msr_high | vmx_msr_low;
+		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+			set_cpu_cap(c, X86_FEATURE_EPT);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+			set_cpu_cap(c, X86_FEATURE_VPID);
+	}
 }
-#endif
 
 static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 {
 	unsigned int l2 = 0;
-	char *p = NULL;
 
 	early_init_intel(c);
 
-#ifdef CONFIG_X86_F00F_BUG
-	/*
-	 * All current models of Pentium and Pentium with MMX technology CPUs
-	 * have the F0 0F bug, which lets nonprivileged users lock up the system.
-	 * Note that the workaround only should be initialized once...
-	 */
-	c->f00f_bug = 0;
-	if (!paravirt_enabled() && c->x86 == 5) {
-		static int f00f_workaround_enabled;
-
-		c->f00f_bug = 1;
-		if (!f00f_workaround_enabled) {
-			trap_init_f00f_bug();
-			printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
-			f00f_workaround_enabled = 1;
-		}
-	}
-#endif
+	intel_workarounds(c);
 
 	l2 = init_intel_cacheinfo(c);
 	if (c->cpuid_level > 9) {
@@ -146,16 +250,32 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
 	}
 
-	/* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until model 3 mask 3 */
-	if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)
-		clear_cpu_cap(c, X86_FEATURE_SEP);
+	if (cpu_has_xmm2)
+		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+	if (cpu_has_ds) {
+		unsigned int l1;
+		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
+		if (!(l1 & (1<<11)))
+			set_cpu_cap(c, X86_FEATURE_BTS);
+		if (!(l1 & (1<<12)))
+			set_cpu_cap(c, X86_FEATURE_PEBS);
+		ds_init_intel(c);
+	}
 
+#ifdef CONFIG_X86_64
+	if (c->x86 == 15)
+		c->x86_cache_alignment = c->x86_clflush_size * 2;
+	if (c->x86 == 6)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+#else
 	/*
 	 * Names for the Pentium II/Celeron processors
 	 * detectable only by also checking the cache size.
 	 * Dixon is NOT a Celeron.
 	 */
 	if (c->x86 == 6) {
+		char *p = NULL;
+
 		switch (c->x86_model) {
 		case 5:
 			if (c->x86_mask == 0) {
@@ -178,70 +298,41 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 				p = "Celeron (Coppermine)";
 			break;
 		}
-	}
-
-	if (p)
-		strcpy(c->x86_model_id, p);
-
-	c->x86_max_cores = num_cpu_cores(c);
-
-	detect_ht(c);
 
-	/* Work around errata */
-	Intel_errata_workarounds(c);
-
-#ifdef CONFIG_X86_INTEL_USERCOPY
-	/*
-	 * Set up the preferred alignment for movsl bulk memory moves
-	 */
-	switch (c->x86) {
-	case 4:		/* 486: untested */
-		break;
-	case 5:		/* Old Pentia: untested */
-		break;
-	case 6:		/* PII/PIII only like movsl with 8-byte alignment */
-		movsl_mask.mask = 7;
-		break;
-	case 15:	/* P4 is OK down to 8-byte alignment */
-		movsl_mask.mask = 7;
-		break;
+		if (p)
+			strcpy(c->x86_model_id, p);
 	}
-#endif
 
-	if (cpu_has_xmm2)
-		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-	if (c->x86 == 15) {
+	if (c->x86 == 15)
 		set_cpu_cap(c, X86_FEATURE_P4);
-	}
 	if (c->x86 == 6)
 		set_cpu_cap(c, X86_FEATURE_P3);
-	if (cpu_has_ds) {
-		unsigned int l1;
-		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
-		if (!(l1 & (1<<11)))
-			set_cpu_cap(c, X86_FEATURE_BTS);
-		if (!(l1 & (1<<12)))
-			set_cpu_cap(c, X86_FEATURE_PEBS);
-	}
 
 	if (cpu_has_bts)
-		ds_init_intel(c);
+		ptrace_bts_init_intel(c);
 
-	/*
-	 * See if we have a good local APIC by checking for buggy Pentia,
-	 * i.e. all B steppings and the C2 stepping of P54C when using their
-	 * integrated APIC (see 11AP erratum in "Pentium Processor
-	 * Specification Update").
-	 */
-	if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
-	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
-		set_cpu_cap(c, X86_FEATURE_11AP);
+#endif
 
-#ifdef CONFIG_X86_NUMAQ
-	numaq_tsc_disable();
+	detect_extended_topology(c);
+	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+		/*
+		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+		 * detection.
+		 */
+		c->x86_max_cores = intel_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+		detect_ht(c);
 #endif
+	}
+
+	/* Work around errata */
+	srat_detect_node();
+
+	if (cpu_has(c, X86_FEATURE_VMX))
+		detect_vmx_virtcap(c);
 }
 
+#ifdef CONFIG_X86_32
 static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 {
 	/*
@@ -254,10 +345,12 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned i
 		size = 256;
 	return size;
 }
+#endif
 
 static struct cpu_dev intel_cpu_dev __cpuinitdata = {
 	.c_vendor	= "Intel",
 	.c_ident	= { "GenuineIntel" },
+#ifdef CONFIG_X86_32
 	.c_models = {
 		{ .vendor = X86_VENDOR_INTEL, .family = 4, .model_names =
 		  {
@@ -307,76 +400,12 @@ static struct cpu_dev intel_cpu_dev __cpuinitdata = {
 		  }
 		},
 	},
+	.c_size_cache	= intel_size_cache,
+#endif
 	.c_early_init   = early_init_intel,
 	.c_init		= init_intel,
-	.c_size_cache	= intel_size_cache,
+	.c_x86_vendor	= X86_VENDOR_INTEL,
 };
 
-cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev);
-
-#ifndef CONFIG_X86_CMPXCHG
-unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new)
-{
-	u8 prev;
-	unsigned long flags;
-
-	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
-	local_irq_save(flags);
-	prev = *(u8 *)ptr;
-	if (prev == old)
-		*(u8 *)ptr = new;
-	local_irq_restore(flags);
-	return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u8);
-
-unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new)
-{
-	u16 prev;
-	unsigned long flags;
-
-	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
-	local_irq_save(flags);
-	prev = *(u16 *)ptr;
-	if (prev == old)
-		*(u16 *)ptr = new;
-	local_irq_restore(flags);
-	return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u16);
-
-unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
-{
-	u32 prev;
-	unsigned long flags;
-
-	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
-	local_irq_save(flags);
-	prev = *(u32 *)ptr;
-	if (prev == old)
-		*(u32 *)ptr = new;
-	local_irq_restore(flags);
-	return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u32);
-#endif
-
-#ifndef CONFIG_X86_CMPXCHG64
-unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new)
-{
-	u64 prev;
-	unsigned long flags;
-
-	/* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */
-	local_irq_save(flags);
-	prev = *(u64 *)ptr;
-	if (prev == old)
-		*(u64 *)ptr = new;
-	local_irq_restore(flags);
-	return prev;
-}
-EXPORT_SYMBOL(cmpxchg_486_u64);
-#endif
-
-/* arch_initcall(intel_cpu_init); */
+cpu_dev_register(intel_cpu_dev);
 
diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
deleted file mode 100644
index 1019c58d39f0..000000000000
--- a/arch/x86/kernel/cpu/intel_64.c
+++ /dev/null
@@ -1,95 +0,0 @@
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <asm/processor.h>
-#include <asm/ptrace.h>
-#include <asm/topology.h>
-#include <asm/numa_64.h>
-
-#include "cpu.h"
-
-static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
-{
-	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
-	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-
-	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
-}
-
-/*
- * find out the number of processor cores on the die
- */
-static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
-{
-	unsigned int eax, t;
-
-	if (c->cpuid_level < 4)
-		return 1;
-
-	cpuid_count(4, 0, &eax, &t, &t, &t);
-
-	if (eax & 0x1f)
-		return ((eax >> 26) + 1);
-	else
-		return 1;
-}
-
-static void __cpuinit srat_detect_node(void)
-{
-#ifdef CONFIG_NUMA
-	unsigned node;
-	int cpu = smp_processor_id();
-	int apicid = hard_smp_processor_id();
-
-	/* Don't do the funky fallback heuristics the AMD version employs
-	   for now. */
-	node = apicid_to_node[apicid];
-	if (node == NUMA_NO_NODE || !node_online(node))
-		node = first_node(node_online_map);
-	numa_set_node(cpu, node);
-
-	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
-#endif
-}
-
-static void __cpuinit init_intel(struct cpuinfo_x86 *c)
-{
-	init_intel_cacheinfo(c);
-	if (c->cpuid_level > 9) {
-		unsigned eax = cpuid_eax(10);
-		/* Check for version and the number of counters */
-		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
-			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
-	}
-
-	if (cpu_has_ds) {
-		unsigned int l1, l2;
-		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
-		if (!(l1 & (1<<11)))
-			set_cpu_cap(c, X86_FEATURE_BTS);
-		if (!(l1 & (1<<12)))
-			set_cpu_cap(c, X86_FEATURE_PEBS);
-	}
-
-
-	if (cpu_has_bts)
-		ds_init_intel(c);
-
-	if (c->x86 == 15)
-		c->x86_cache_alignment = c->x86_clflush_size * 2;
-	if (c->x86 == 6)
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-	c->x86_max_cores = intel_num_cpu_cores(c);
-
-	srat_detect_node();
-}
-
-static struct cpu_dev intel_cpu_dev __cpuinitdata = {
-	.c_vendor	= "Intel",
-	.c_ident	= { "GenuineIntel" },
-	.c_early_init   = early_init_intel,
-	.c_init		= init_intel,
-};
-cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev);
-
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6b0a10b002f1..3f46afbb1cf1 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -1,8 +1,8 @@
 /*
- *      Routines to indentify caches on Intel CPU.
+ *	Routines to indentify caches on Intel CPU.
  *
- *      Changes:
- *      Venkatesh Pallipadi	: Adding cache identification through cpuid(4)
+ *	Changes:
+ *	Venkatesh Pallipadi	: Adding cache identification through cpuid(4)
  *		Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
  *	Andi Kleen / Andreas Herrmann	: CPUID4 emulation on AMD.
  */
@@ -13,6 +13,7 @@
 #include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/pci.h>
 
 #include <asm/processor.h>
 #include <asm/smp.h>
@@ -130,9 +131,18 @@ struct _cpuid4_info {
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
 	unsigned long size;
+	unsigned long can_disable;
 	cpumask_t shared_cpu_map;	/* future?: only cpus/node is needed */
 };
 
+#ifdef CONFIG_PCI
+static struct pci_device_id k8_nb_id[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
+	{}
+};
+#endif
+
 unsigned short			num_cache_leaves;
 
 /* AMD doesn't have CPUID4. Emulate it here to report the same
@@ -182,9 +192,10 @@ static unsigned short assocs[] __cpuinitdata = {
 static unsigned char levels[] __cpuinitdata = { 1, 1, 2, 3 };
 static unsigned char types[] __cpuinitdata = { 1, 2, 3, 3 };
 
-static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
-		       union _cpuid4_leaf_ebx *ebx,
-		       union _cpuid4_leaf_ecx *ecx)
+static void __cpuinit
+amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
+		     union _cpuid4_leaf_ebx *ebx,
+		     union _cpuid4_leaf_ecx *ecx)
 {
 	unsigned dummy;
 	unsigned line_size, lines_per_tag, assoc, size_in_kb;
@@ -251,27 +262,40 @@ static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 		(ebx->split.ways_of_associativity + 1) - 1;
 }
 
-static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+static void __cpuinit
+amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
+{
+	if (index < 3)
+		return;
+	this_leaf->can_disable = 1;
+}
+
+static int
+__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
 {
 	union _cpuid4_leaf_eax 	eax;
 	union _cpuid4_leaf_ebx 	ebx;
 	union _cpuid4_leaf_ecx 	ecx;
 	unsigned		edx;
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 		amd_cpuid4(index, &eax, &ebx, &ecx);
-	else
-		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full,  &edx);
+		if (boot_cpu_data.x86 >= 0x10)
+			amd_check_l3_disable(index, this_leaf);
+	} else {
+		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
+	}
+
 	if (eax.split.type == CACHE_TYPE_NULL)
 		return -EIO; /* better error ? */
 
 	this_leaf->eax = eax;
 	this_leaf->ebx = ebx;
 	this_leaf->ecx = ecx;
-	this_leaf->size = (ecx.split.number_of_sets + 1) *
-		(ebx.split.coherency_line_size + 1) *
-		(ebx.split.physical_line_partition + 1) *
-		(ebx.split.ways_of_associativity + 1);
+	this_leaf->size = (ecx.split.number_of_sets          + 1) *
+			  (ebx.split.coherency_line_size     + 1) *
+			  (ebx.split.physical_line_partition + 1) *
+			  (ebx.split.ways_of_associativity   + 1);
 	return 0;
 }
 
@@ -453,7 +477,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 
 /* pointer to _cpuid4_info array (for each cache leaf) */
 static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
-#define CPUID4_INFO_IDX(x, y)    (&((per_cpu(cpuid4_info, x))[y]))
+#define CPUID4_INFO_IDX(x, y)	(&((per_cpu(cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
 static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
@@ -490,7 +514,7 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
 
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
 	for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) {
-		sibling_leaf = CPUID4_INFO_IDX(sibling, index);	
+		sibling_leaf = CPUID4_INFO_IDX(sibling, index);
 		cpu_clear(cpu, sibling_leaf->shared_cpu_map);
 	}
 }
@@ -572,7 +596,7 @@ struct _index_kobject {
 
 /* pointer to array of kobjects for cpuX/cache/indexY */
 static DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
-#define INDEX_KOBJECT_PTR(x, y)    (&((per_cpu(index_kobject, x))[y]))
+#define INDEX_KOBJECT_PTR(x, y)		(&((per_cpu(index_kobject, x))[y]))
 
 #define show_one_plus(file_name, object, val)				\
 static ssize_t show_##file_name						\
@@ -637,6 +661,99 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) {
 	}
 }
 
+#define to_object(k)	container_of(k, struct _index_kobject, kobj)
+#define to_attr(a)	container_of(a, struct _cache_attr, attr)
+
+#ifdef CONFIG_PCI
+static struct pci_dev *get_k8_northbridge(int node)
+{
+	struct pci_dev *dev = NULL;
+	int i;
+
+	for (i = 0; i <= node; i++) {
+		do {
+			dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
+			if (!dev)
+				break;
+		} while (!pci_match_id(&k8_nb_id[0], dev));
+		if (!dev)
+			break;
+	}
+	return dev;
+}
+#else
+static struct pci_dev *get_k8_northbridge(int node)
+{
+	return NULL;
+}
+#endif
+
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
+{
+	int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+	struct pci_dev *dev = NULL;
+	ssize_t ret = 0;
+	int i;
+
+	if (!this_leaf->can_disable)
+		return sprintf(buf, "Feature not enabled\n");
+
+	dev = get_k8_northbridge(node);
+	if (!dev) {
+		printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < 2; i++) {
+		unsigned int reg;
+
+		pci_read_config_dword(dev, 0x1BC + i * 4, &reg);
+
+		ret += sprintf(buf, "%sEntry: %d\n", buf, i);
+		ret += sprintf(buf, "%sReads:  %s\tNew Entries: %s\n",  
+			buf,
+			reg & 0x80000000 ? "Disabled" : "Allowed",
+			reg & 0x40000000 ? "Disabled" : "Allowed");
+		ret += sprintf(buf, "%sSubCache: %x\tIndex: %x\n",
+			buf, (reg & 0x30000) >> 16, reg & 0xfff);
+	}
+	return ret;
+}
+
+static ssize_t
+store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
+		    size_t count)
+{
+	int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+	struct pci_dev *dev = NULL;
+	unsigned int ret, index, val;
+
+	if (!this_leaf->can_disable)
+		return 0;
+
+	if (strlen(buf) > 15)
+		return -EINVAL;
+
+	ret = sscanf(buf, "%x %x", &index, &val);
+	if (ret != 2)
+		return -EINVAL;
+	if (index > 1)
+		return -EINVAL;
+
+	val |= 0xc0000000;
+	dev = get_k8_northbridge(node);
+	if (!dev) {
+		printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
+		return -EINVAL;
+	}
+
+	pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
+	wbinvd();
+	pci_write_config_dword(dev, 0x1BC + index * 4, val);
+
+	return 1;
+}
+
 struct _cache_attr {
 	struct attribute attr;
 	ssize_t (*show)(struct _cpuid4_info *, char *);
@@ -657,6 +774,8 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
+static struct _cache_attr cache_disable = __ATTR(cache_disable, 0644, show_cache_disable, store_cache_disable);
+
 static struct attribute * default_attrs[] = {
 	&type.attr,
 	&level.attr,
@@ -667,12 +786,10 @@ static struct attribute * default_attrs[] = {
 	&size.attr,
 	&shared_cpu_map.attr,
 	&shared_cpu_list.attr,
+	&cache_disable.attr,
 	NULL
 };
 
-#define to_object(k) container_of(k, struct _index_kobject, kobj)
-#define to_attr(a) container_of(a, struct _cache_attr, attr)
-
 static ssize_t show(struct kobject * kobj, struct attribute * attr, char * buf)
 {
 	struct _cache_attr *fattr = to_attr(attr);
@@ -682,14 +799,22 @@ static ssize_t show(struct kobject * kobj, struct attribute * attr, char * buf)
 	ret = fattr->show ?
 		fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
 			buf) :
-	       	0;
+		0;
 	return ret;
 }
 
 static ssize_t store(struct kobject * kobj, struct attribute * attr,
 		     const char * buf, size_t count)
 {
-	return 0;
+	struct _cache_attr *fattr = to_attr(attr);
+	struct _index_kobject *this_leaf = to_object(kobj);
+	ssize_t ret;
+
+	ret = fattr->store ?
+		fattr->store(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
+			buf, count) :
+		0;
+	return ret;
 }
 
 static struct sysfs_ops sysfs_ops = {
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 726a5fcdf341..4b031a4ac856 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -860,7 +860,7 @@ error:
 	return err;
 }
 
-static void mce_remove_device(unsigned int cpu)
+static __cpuinit void mce_remove_device(unsigned int cpu)
 {
 	int i;
 
diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl
new file mode 100644
index 000000000000..dfea390e1608
--- /dev/null
+++ b/arch/x86/kernel/cpu/mkcapflags.pl
@@ -0,0 +1,32 @@
+#!/usr/bin/perl
+#
+# Generate the x86_cap_flags[] array from include/asm-x86/cpufeature.h
+#
+
+($in, $out) = @ARGV;
+
+open(IN, "< $in\0")   or die "$0: cannot open: $in: $!\n";
+open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n";
+
+print OUT "#include <asm/cpufeature.h>\n\n";
+print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n";
+
+while (defined($line = <IN>)) {
+	if ($line =~ /^\s*\#\s*define\s+(X86_FEATURE_(\S+))\s+(.*)$/) {
+		$macro = $1;
+		$feature = $2;
+		$tail = $3;
+		if ($tail =~ /\/\*\s*\"([^"]*)\".*\*\//) {
+			$feature = $1;
+		}
+
+		if ($feature ne '') {
+			printf OUT "\t%-32s = \"%s\",\n",
+				"[$macro]", "\L$feature";
+		}
+	}
+}
+print OUT "};\n";
+
+close(IN);
+close(OUT);
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index cb7d3b6a80eb..4e8d77f01eeb 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -401,12 +401,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 		tmp |= ~((1<<(hi - 1)) - 1);
 
 		if (tmp != mask_lo) {
-			static int once = 1;
-
-			if (once) {
-				printk(KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n");
-				once = 0;
-			}
+			WARN_ONCE(1, KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n");
 			mask_lo = tmp;
 		}
 	}
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 84c480bb3715..4c4214690dd1 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -405,9 +405,9 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset)
 			}
 			/* RED-PEN: base can be > 32bit */ 
 			len += seq_printf(seq, 
-				   "reg%02i: base=0x%05lx000 (%4luMB), size=%4lu%cB: %s, count=%d\n",
+				   "reg%02i: base=0x%06lx000 (%5luMB), size=%5lu%cB, count=%d: %s\n",
 			     i, base, base >> (20 - PAGE_SHIFT), size, factor,
-			     mtrr_attrib_to_str(type), mtrr_usage_table[i]);
+			     mtrr_usage_table[i], mtrr_attrib_to_str(type));
 		}
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 885c8265e6b5..c78c04821ea1 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -729,7 +729,7 @@ struct var_mtrr_range_state {
 	mtrr_type type;
 };
 
-struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
+static struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
 static int __initdata debug_print;
 
 static int __init
@@ -759,7 +759,8 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 	/* take out UC ranges */
 	for (i = 0; i < num_var_ranges; i++) {
 		type = range_state[i].type;
-		if (type != MTRR_TYPE_UNCACHABLE)
+		if (type != MTRR_TYPE_UNCACHABLE &&
+		    type != MTRR_TYPE_WRPROT)
 			continue;
 		size = range_state[i].size_pfn;
 		if (!size)
@@ -836,6 +837,13 @@ static int __init enable_mtrr_cleanup_setup(char *str)
 }
 early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup);
 
+static int __init mtrr_cleanup_debug_setup(char *str)
+{
+	debug_print = 1;
+	return 0;
+}
+early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup);
+
 struct var_mtrr_state {
 	unsigned long	range_startk;
 	unsigned long	range_sizek;
@@ -898,6 +906,27 @@ set_var_mtrr_all(unsigned int address_bits)
 	}
 }
 
+static unsigned long to_size_factor(unsigned long sizek, char *factorp)
+{
+	char factor;
+	unsigned long base = sizek;
+
+	if (base & ((1<<10) - 1)) {
+		/* not MB alignment */
+		factor = 'K';
+	} else if (base & ((1<<20) - 1)){
+		factor = 'M';
+		base >>= 10;
+	} else {
+		factor = 'G';
+		base >>= 20;
+	}
+
+	*factorp = factor;
+
+	return base;
+}
+
 static unsigned int __init
 range_to_mtrr(unsigned int reg, unsigned long range_startk,
 	      unsigned long range_sizek, unsigned char type)
@@ -919,13 +948,21 @@ range_to_mtrr(unsigned int reg, unsigned long range_startk,
 			align = max_align;
 
 		sizek = 1 << align;
-		if (debug_print)
+		if (debug_print) {
+			char start_factor = 'K', size_factor = 'K';
+			unsigned long start_base, size_base;
+
+			start_base = to_size_factor(range_startk, &start_factor),
+			size_base = to_size_factor(sizek, &size_factor),
+
 			printk(KERN_DEBUG "Setting variable MTRR %d, "
-				"base: %ldMB, range: %ldMB, type %s\n",
-				reg, range_startk >> 10, sizek >> 10,
+				"base: %ld%cB, range: %ld%cB, type %s\n",
+				reg, start_base, start_factor,
+				size_base, size_factor,
 				(type == MTRR_TYPE_UNCACHABLE)?"UC":
 				    ((type == MTRR_TYPE_WRBACK)?"WB":"Other")
 				);
+		}
 		save_var_mtrr(reg++, range_startk, sizek, type);
 		range_startk += sizek;
 		range_sizek -= sizek;
@@ -970,6 +1007,8 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
 	/* try to append some small hole */
 	range0_basek = state->range_startk;
 	range0_sizek = ALIGN(state->range_sizek, chunk_sizek);
+
+	/* no increase */
 	if (range0_sizek == state->range_sizek) {
 		if (debug_print)
 			printk(KERN_DEBUG "rangeX: %016lx - %016lx\n",
@@ -980,13 +1019,40 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
 		return 0;
 	}
 
-	range0_sizek -= chunk_sizek;
-	if (range0_sizek && sizek) {
-	    while (range0_basek + range0_sizek > (basek + sizek)) {
-		range0_sizek -= chunk_sizek;
-		if (!range0_sizek)
-			break;
-	    }
+	/* only cut back, when it is not the last */
+	if (sizek) {
+		while (range0_basek + range0_sizek > (basek + sizek)) {
+			if (range0_sizek >= chunk_sizek)
+				range0_sizek -= chunk_sizek;
+			else
+				range0_sizek = 0;
+
+			if (!range0_sizek)
+				break;
+		}
+	}
+
+second_try:
+	range_basek = range0_basek + range0_sizek;
+
+	/* one hole in the middle */
+	if (range_basek > basek && range_basek <= (basek + sizek))
+		second_sizek = range_basek - basek;
+
+	if (range0_sizek > state->range_sizek) {
+
+		/* one hole in middle or at end */
+		hole_sizek = range0_sizek - state->range_sizek - second_sizek;
+
+		/* hole size should be less than half of range0 size */
+		if (hole_sizek >= (range0_sizek >> 1) &&
+		    range0_sizek >= chunk_sizek) {
+			range0_sizek -= chunk_sizek;
+			second_sizek = 0;
+			hole_sizek = 0;
+
+			goto second_try;
+		}
 	}
 
 	if (range0_sizek) {
@@ -996,50 +1062,28 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
 				(range0_basek + range0_sizek)<<10);
 		state->reg = range_to_mtrr(state->reg, range0_basek,
 				range0_sizek, MTRR_TYPE_WRBACK);
-
-	}
-
-	range_basek = range0_basek + range0_sizek;
-	range_sizek = chunk_sizek;
-
-	if (range_basek + range_sizek > basek &&
-	    range_basek + range_sizek <= (basek + sizek)) {
-		/* one hole */
-		second_basek = basek;
-		second_sizek = range_basek + range_sizek - basek;
 	}
 
-	/* if last piece, only could one hole near end */
-	if ((second_basek || !basek) &&
-	    range_sizek - (state->range_sizek - range0_sizek) - second_sizek <
-	    (chunk_sizek >> 1)) {
-		/*
-		 * one hole in middle (second_sizek is 0) or at end
-		 * (second_sizek is 0 )
-		 */
-		hole_sizek = range_sizek - (state->range_sizek - range0_sizek)
-				 - second_sizek;
-		hole_basek = range_basek + range_sizek - hole_sizek
-				 - second_sizek;
-	} else {
-		/* fallback for big hole, or several holes */
+	if (range0_sizek < state->range_sizek) {
+		/* need to handle left over */
 		range_sizek = state->range_sizek - range0_sizek;
-		second_basek = 0;
-		second_sizek = 0;
+
+		if (debug_print)
+			printk(KERN_DEBUG "range: %016lx - %016lx\n",
+				 range_basek<<10,
+				 (range_basek + range_sizek)<<10);
+		state->reg = range_to_mtrr(state->reg, range_basek,
+				 range_sizek, MTRR_TYPE_WRBACK);
 	}
 
-	if (debug_print)
-		printk(KERN_DEBUG "range: %016lx - %016lx\n", range_basek<<10,
-			 (range_basek + range_sizek)<<10);
-	state->reg = range_to_mtrr(state->reg, range_basek, range_sizek,
-					 MTRR_TYPE_WRBACK);
 	if (hole_sizek) {
+		hole_basek = range_basek - hole_sizek - second_sizek;
 		if (debug_print)
 			printk(KERN_DEBUG "hole: %016lx - %016lx\n",
-				 hole_basek<<10, (hole_basek + hole_sizek)<<10);
-		state->reg = range_to_mtrr(state->reg, hole_basek, hole_sizek,
-						 MTRR_TYPE_UNCACHABLE);
-
+				 hole_basek<<10,
+				 (hole_basek + hole_sizek)<<10);
+		state->reg = range_to_mtrr(state->reg, hole_basek,
+				 hole_sizek, MTRR_TYPE_UNCACHABLE);
 	}
 
 	return second_sizek;
@@ -1154,11 +1198,11 @@ struct mtrr_cleanup_result {
 };
 
 /*
- * gran_size: 1M, 2M, ..., 2G
- * chunk size: gran_size, ..., 4G
- * so we need (2+13)*6
+ * gran_size: 64K, 128K, 256K, 512K, 1M, 2M, ..., 2G
+ * chunk size: gran_size, ..., 2G
+ * so we need (1+16)*8
  */
-#define NUM_RESULT	90
+#define NUM_RESULT	136
 #define PSHIFT		(PAGE_SHIFT - 10)
 
 static struct mtrr_cleanup_result __initdata result[NUM_RESULT];
@@ -1168,13 +1212,14 @@ static unsigned long __initdata min_loss_pfn[RANGE_NUM];
 static int __init mtrr_cleanup(unsigned address_bits)
 {
 	unsigned long extra_remove_base, extra_remove_size;
-	unsigned long i, base, size, def, dummy;
+	unsigned long base, size, def, dummy;
 	mtrr_type type;
 	int nr_range, nr_range_new;
 	u64 chunk_size, gran_size;
 	unsigned long range_sums, range_sums_new;
 	int index_good;
 	int num_reg_good;
+	int i;
 
 	/* extra one for all 0 */
 	int num[MTRR_NUM_TYPES + 1];
@@ -1204,6 +1249,8 @@ static int __init mtrr_cleanup(unsigned address_bits)
 			continue;
 		if (!size)
 			type = MTRR_NUM_TYPES;
+		if (type == MTRR_TYPE_WRPROT)
+			type = MTRR_TYPE_UNCACHABLE;
 		num[type]++;
 	}
 
@@ -1216,23 +1263,57 @@ static int __init mtrr_cleanup(unsigned address_bits)
 		num_var_ranges - num[MTRR_NUM_TYPES])
 		return 0;
 
+	/* print original var MTRRs at first, for debugging: */
+	printk(KERN_DEBUG "original variable MTRRs\n");
+	for (i = 0; i < num_var_ranges; i++) {
+		char start_factor = 'K', size_factor = 'K';
+		unsigned long start_base, size_base;
+
+		size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
+		if (!size_base)
+			continue;
+
+		size_base = to_size_factor(size_base, &size_factor),
+		start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
+		start_base = to_size_factor(start_base, &start_factor),
+		type = range_state[i].type;
+
+		printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
+			i, start_base, start_factor,
+			size_base, size_factor,
+			(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
+			    ((type == MTRR_TYPE_WRPROT) ? "WP" :
+			     ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
+			);
+	}
+
 	memset(range, 0, sizeof(range));
 	extra_remove_size = 0;
-	if (mtrr_tom2) {
-		extra_remove_base = 1 << (32 - PAGE_SHIFT);
+	extra_remove_base = 1 << (32 - PAGE_SHIFT);
+	if (mtrr_tom2)
 		extra_remove_size =
 			(mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base;
-	}
 	nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base,
 					  extra_remove_size);
+	/*
+	 * [0, 1M) should always be coverred by var mtrr with WB
+	 * and fixed mtrrs should take effective before var mtrr for it
+	 */
+	nr_range = add_range_with_merge(range, nr_range, 0,
+					(1ULL<<(20 - PAGE_SHIFT)) - 1);
+	/* sort the ranges */
+	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+
 	range_sums = sum_ranges(range, nr_range);
 	printk(KERN_INFO "total RAM coverred: %ldM\n",
 	       range_sums >> (20 - PAGE_SHIFT));
 
 	if (mtrr_chunk_size && mtrr_gran_size) {
 		int num_reg;
+		char gran_factor, chunk_factor, lose_factor;
+		unsigned long gran_base, chunk_base, lose_base;
 
-		debug_print = 1;
+		debug_print++;
 		/* convert ranges to var ranges state */
 		num_reg = x86_setup_var_mtrrs(range, nr_range, mtrr_chunk_size,
 					      mtrr_gran_size);
@@ -1256,34 +1337,48 @@ static int __init mtrr_cleanup(unsigned address_bits)
 			result[i].lose_cover_sizek =
 				(range_sums - range_sums_new) << PSHIFT;
 
-		printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t",
-			 result[i].bad?"*BAD*":" ", result[i].gran_sizek >> 10,
-			 result[i].chunk_sizek >> 10);
-		printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ldM \n",
+		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+		printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
+			 result[i].bad?"*BAD*":" ",
+			 gran_base, gran_factor, chunk_base, chunk_factor);
+		printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
 			 result[i].num_reg, result[i].bad?"-":"",
-			 result[i].lose_cover_sizek >> 10);
+			 lose_base, lose_factor);
 		if (!result[i].bad) {
 			set_var_mtrr_all(address_bits);
 			return 1;
 		}
 		printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
 		       "will find optimal one\n");
-		debug_print = 0;
+		debug_print--;
 		memset(result, 0, sizeof(result[0]));
 	}
 
 	i = 0;
 	memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn));
 	memset(result, 0, sizeof(result));
-	for (gran_size = (1ULL<<20); gran_size < (1ULL<<32); gran_size <<= 1) {
-		for (chunk_size = gran_size; chunk_size < (1ULL<<33);
+	for (gran_size = (1ULL<<16); gran_size < (1ULL<<32); gran_size <<= 1) {
+		char gran_factor;
+		unsigned long gran_base;
+
+		if (debug_print)
+			gran_base = to_size_factor(gran_size >> 10, &gran_factor);
+
+		for (chunk_size = gran_size; chunk_size < (1ULL<<32);
 		     chunk_size <<= 1) {
 			int num_reg;
 
-			if (debug_print)
-				printk(KERN_INFO
-			       "\ngran_size: %lldM   chunk_size_size: %lldM\n",
-				       gran_size >> 20, chunk_size >> 20);
+			if (debug_print) {
+				char chunk_factor;
+				unsigned long chunk_base;
+
+				chunk_base = to_size_factor(chunk_size>>10, &chunk_factor),
+				printk(KERN_INFO "\n");
+				printk(KERN_INFO "gran_size: %ld%c   chunk_size: %ld%c \n",
+				       gran_base, gran_factor, chunk_base, chunk_factor);
+			}
 			if (i >= NUM_RESULT)
 				continue;
 
@@ -1326,12 +1421,18 @@ static int __init mtrr_cleanup(unsigned address_bits)
 
 	/* print out all */
 	for (i = 0; i < NUM_RESULT; i++) {
-		printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t",
-		       result[i].bad?"*BAD* ":" ", result[i].gran_sizek >> 10,
-		       result[i].chunk_sizek >> 10);
-		printk(KERN_CONT "num_reg: %d \tlose RAM: %s%ldM\n",
-		       result[i].num_reg, result[i].bad?"-":"",
-		       result[i].lose_cover_sizek >> 10);
+		char gran_factor, chunk_factor, lose_factor;
+		unsigned long gran_base, chunk_base, lose_base;
+
+		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+		printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
+			 result[i].bad?"*BAD*":" ",
+			 gran_base, gran_factor, chunk_base, chunk_factor);
+		printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
+			 result[i].num_reg, result[i].bad?"-":"",
+			 lose_base, lose_factor);
 	}
 
 	/* try to find the optimal index */
@@ -1339,10 +1440,8 @@ static int __init mtrr_cleanup(unsigned address_bits)
 		nr_mtrr_spare_reg = num_var_ranges - 1;
 	num_reg_good = -1;
 	for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
-		if (!min_loss_pfn[i]) {
+		if (!min_loss_pfn[i])
 			num_reg_good = i;
-			break;
-		}
 	}
 
 	index_good = -1;
@@ -1358,21 +1457,26 @@ static int __init mtrr_cleanup(unsigned address_bits)
 	}
 
 	if (index_good != -1) {
+		char gran_factor, chunk_factor, lose_factor;
+		unsigned long gran_base, chunk_base, lose_base;
+
 		printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
 		i = index_good;
-		printk(KERN_INFO "gran_size: %ldM \tchunk_size: %ldM \t",
-				result[i].gran_sizek >> 10,
-				result[i].chunk_sizek >> 10);
-		printk(KERN_CONT "num_reg: %d \tlose RAM: %ldM\n",
-				result[i].num_reg,
-				result[i].lose_cover_sizek >> 10);
+		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+		printk(KERN_INFO "gran_size: %ld%c \tchunk_size: %ld%c \t",
+			 gran_base, gran_factor, chunk_base, chunk_factor);
+		printk(KERN_CONT "num_reg: %d  \tlose RAM: %ld%c\n",
+			 result[i].num_reg, lose_base, lose_factor);
 		/* convert ranges to var ranges state */
 		chunk_size = result[i].chunk_sizek;
 		chunk_size <<= 10;
 		gran_size = result[i].gran_sizek;
 		gran_size <<= 10;
-		debug_print = 1;
+		debug_print++;
 		x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
+		debug_print--;
 		set_var_mtrr_all(address_bits);
 		return 1;
 	}
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 05cc22dbd4ff..6bff382094f5 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -295,13 +295,19 @@ static int setup_k7_watchdog(unsigned nmi_hz)
 	/* setup the timer */
 	wrmsr(evntsel_msr, evntsel, 0);
 	write_watchdog_counter(perfctr_msr, "K7_PERFCTR0",nmi_hz);
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= K7_EVNTSEL_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
 
+	/* initialize the wd struct before enabling */
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
 	wd->cccr_msr = 0;  /* unused */
+
+	/* ok, everything is initialized, announce that we're set */
+	cpu_nmi_set_wd_enabled();
+
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	evntsel |= K7_EVNTSEL_ENABLE;
+	wrmsr(evntsel_msr, evntsel, 0);
+
 	return 1;
 }
 
@@ -379,13 +385,19 @@ static int setup_p6_watchdog(unsigned nmi_hz)
 	wrmsr(evntsel_msr, evntsel, 0);
 	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
 	write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0",nmi_hz);
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= P6_EVNTSEL0_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
 
+	/* initialize the wd struct before enabling */
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
 	wd->cccr_msr = 0;  /* unused */
+
+	/* ok, everything is initialized, announce that we're set */
+	cpu_nmi_set_wd_enabled();
+
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	evntsel |= P6_EVNTSEL0_ENABLE;
+	wrmsr(evntsel_msr, evntsel, 0);
+
 	return 1;
 }
 
@@ -432,6 +444,27 @@ static const struct wd_ops p6_wd_ops = {
 #define P4_CCCR_ENABLE		(1 << 12)
 #define P4_CCCR_OVF 		(1 << 31)
 
+#define P4_CONTROLS 18
+static unsigned int p4_controls[18] = {
+	MSR_P4_BPU_CCCR0,
+	MSR_P4_BPU_CCCR1,
+	MSR_P4_BPU_CCCR2,
+	MSR_P4_BPU_CCCR3,
+	MSR_P4_MS_CCCR0,
+	MSR_P4_MS_CCCR1,
+	MSR_P4_MS_CCCR2,
+	MSR_P4_MS_CCCR3,
+	MSR_P4_FLAME_CCCR0,
+	MSR_P4_FLAME_CCCR1,
+	MSR_P4_FLAME_CCCR2,
+	MSR_P4_FLAME_CCCR3,
+	MSR_P4_IQ_CCCR0,
+	MSR_P4_IQ_CCCR1,
+	MSR_P4_IQ_CCCR2,
+	MSR_P4_IQ_CCCR3,
+	MSR_P4_IQ_CCCR4,
+	MSR_P4_IQ_CCCR5,
+};
 /*
  * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
  * CRU_ESCR0 (with any non-null event selector) through a complemented
@@ -473,6 +506,26 @@ static int setup_p4_watchdog(unsigned nmi_hz)
 		evntsel_msr = MSR_P4_CRU_ESCR0;
 		cccr_msr = MSR_P4_IQ_CCCR0;
 		cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
+
+		/*
+		 * If we're on the kdump kernel or other situation, we may
+		 * still have other performance counter registers set to
+		 * interrupt and they'll keep interrupting forever because
+		 * of the P4_CCCR_OVF quirk. So we need to ACK all the
+		 * pending interrupts and disable all the registers here,
+		 * before reenabling the NMI delivery. Refer to p4_rearm()
+		 * about the P4_CCCR_OVF quirk.
+		 */
+		if (reset_devices) {
+			unsigned int low, high;
+			int i;
+
+			for (i = 0; i < P4_CONTROLS; i++) {
+				rdmsr(p4_controls[i], low, high);
+				low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF);
+				wrmsr(p4_controls[i], low, high);
+			}
+		}
 	} else {
 		/* logical cpu 1 */
 		perfctr_msr = MSR_P4_IQ_PERFCTR1;
@@ -499,12 +552,17 @@ static int setup_p4_watchdog(unsigned nmi_hz)
 	wrmsr(evntsel_msr, evntsel, 0);
 	wrmsr(cccr_msr, cccr_val, 0);
 	write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz);
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	cccr_val |= P4_CCCR_ENABLE;
-	wrmsr(cccr_msr, cccr_val, 0);
+
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
 	wd->cccr_msr = cccr_msr;
+
+	/* ok, everything is initialized, announce that we're set */
+	cpu_nmi_set_wd_enabled();
+
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	cccr_val |= P4_CCCR_ENABLE;
+	wrmsr(cccr_msr, cccr_val, 0);
 	return 1;
 }
 
@@ -620,13 +678,17 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz)
 	wrmsr(evntsel_msr, evntsel, 0);
 	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
 	write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz);
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
 
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
 	wd->cccr_msr = 0;  /* unused */
+
+	/* ok, everything is initialized, announce that we're set */
+	cpu_nmi_set_wd_enabled();
+
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsr(evntsel_msr, evntsel, 0);
 	intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
 	return 1;
 }
diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c
new file mode 100644
index 000000000000..5abbea297e0c
--- /dev/null
+++ b/arch/x86/kernel/cpu/powerflags.c
@@ -0,0 +1,20 @@
+/*
+ * Strings for the various x86 power flags
+ *
+ * This file must not contain any executable code.
+ */
+
+#include <asm/cpufeature.h>
+
+const char *const x86_power_flags[32] = {
+	"ts",	/* temperature sensor */
+	"fid",  /* frequency id control */
+	"vid",  /* voltage id control */
+	"ttp",  /* thermal trip */
+	"tm",
+	"stc",
+	"100mhzsteps",
+	"hwpstate",
+	"",	/* tsc invariant mapped to constant_tsc */
+		/* nothing */
+};
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index b911a2c61b8f..52b3fefbd5af 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -5,6 +5,18 @@
 #include <asm/msr.h>
 #include "cpu.h"
 
+static void __cpuinit early_init_transmeta(struct cpuinfo_x86 *c)
+{
+	u32 xlvl;
+
+	/* Transmeta-defined flags: level 0x80860001 */
+	xlvl = cpuid_eax(0x80860000);
+	if ((xlvl & 0xffff0000) == 0x80860000) {
+		if (xlvl >= 0x80860001)
+			c->x86_capability[2] = cpuid_edx(0x80860001);
+	}
+}
+
 static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 {
 	unsigned int cap_mask, uk, max, dummy;
@@ -12,7 +24,8 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 	unsigned int cpu_rev, cpu_freq = 0, cpu_flags, new_cpu_rev;
 	char cpu_info[65];
 
-	get_model_name(c);	/* Same as AMD/Cyrix */
+	early_init_transmeta(c);
+
 	display_cacheinfo(c);
 
 	/* Print CMS and CPU revision */
@@ -85,23 +98,12 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 #endif
 }
 
-static void __cpuinit transmeta_identify(struct cpuinfo_x86 *c)
-{
-	u32 xlvl;
-
-	/* Transmeta-defined flags: level 0x80860001 */
-	xlvl = cpuid_eax(0x80860000);
-	if ((xlvl & 0xffff0000) == 0x80860000) {
-		if (xlvl >= 0x80860001)
-			c->x86_capability[2] = cpuid_edx(0x80860001);
-	}
-}
-
 static struct cpu_dev transmeta_cpu_dev __cpuinitdata = {
 	.c_vendor	= "Transmeta",
 	.c_ident	= { "GenuineTMx86", "TransmetaCPU" },
+	.c_early_init	= early_init_transmeta,
 	.c_init		= init_transmeta,
-	.c_identify	= transmeta_identify,
+	.c_x86_vendor	= X86_VENDOR_TRANSMETA,
 };
 
-cpu_vendor_dev_register(X86_VENDOR_TRANSMETA, &transmeta_cpu_dev);
+cpu_dev_register(transmeta_cpu_dev);
diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c
index b1fc90989d75..e777f79e0960 100644
--- a/arch/x86/kernel/cpu/umc.c
+++ b/arch/x86/kernel/cpu/umc.c
@@ -19,7 +19,8 @@ static struct cpu_dev umc_cpu_dev __cpuinitdata = {
 		  }
 		},
 	},
+	.c_x86_vendor	= X86_VENDOR_UMC,
 };
 
-cpu_vendor_dev_register(X86_VENDOR_UMC, &umc_cpu_dev);
+cpu_dev_register(umc_cpu_dev);