Merge commit 'v2.6.33' into perf/core

Merge reason:
	__percpu annotations need the corresponding sparse address
space definition upstream.

Conflicts:
	tools/perf/util/probe-event.c (trivial)

43 files changed, 353 insertions, 1135 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cbcbfdee3ee0..eb4092568f9e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -989,12 +989,6 @@ config X86_CPUID
 	  with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
 	  /dev/cpu/31/cpuid.
 
-config X86_CPU_DEBUG
-	tristate "/sys/kernel/debug/x86/cpu/* - CPU Debug support"
-	---help---
-	  If you select this option, this will provide various x86 CPUs
-	  information through debugfs.
-
 choice
 	prompt "High Memory Support"
 	default HIGHMEM4G if !X86_NUMAQ
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 2a4d073d2cf1..f9f472462753 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -308,14 +308,15 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (retval)
 		return retval;
 
-	regs->cs = __USER32_CS;
-	regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
-		regs->r13 = regs->r14 = regs->r15 = 0;
-
 	/* OK, This is the point of no return */
 	set_personality(PER_LINUX);
 	set_thread_flag(TIF_IA32);
-	clear_thread_flag(TIF_ABI_PENDING);
+
+	setup_new_exec(bprm);
+
+	regs->cs = __USER32_CS;
+	regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
+		regs->r13 = regs->r14 = regs->r15 = 0;
 
 	current->mm->end_code = ex.a_text +
 		(current->mm->start_code = N_TXTADDR(ex));
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index 4d817f9e6e77..d2544f1d705d 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -31,6 +31,7 @@ extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
 extern int amd_iommu_init_devices(void);
 extern void amd_iommu_uninit_devices(void);
 extern void amd_iommu_init_notifier(void);
+extern void amd_iommu_init_api(void);
 #ifndef CONFIG_AMD_IOMMU_STATS
 
 static inline void amd_iommu_stats_init(void) { }
diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
deleted file mode 100644
index d96c1ee3a95c..000000000000
--- a/arch/x86/include/asm/cpu_debug.h
+++ /dev/null
@@ -1,127 +0,0 @@
-#ifndef _ASM_X86_CPU_DEBUG_H
-#define _ASM_X86_CPU_DEBUG_H
-
-/*
- * CPU x86 architecture debug
- *
- * Copyright(C) 2009 Jaswinder Singh Rajput
- */
-
-/* Register flags */
-enum cpu_debug_bit {
-/* Model Specific Registers (MSRs)					*/
-	CPU_MC_BIT,				/* Machine Check	*/
-	CPU_MONITOR_BIT,			/* Monitor		*/
-	CPU_TIME_BIT,				/* Time			*/
-	CPU_PMC_BIT,				/* Performance Monitor	*/
-	CPU_PLATFORM_BIT,			/* Platform		*/
-	CPU_APIC_BIT,				/* APIC			*/
-	CPU_POWERON_BIT,			/* Power-on		*/
-	CPU_CONTROL_BIT,			/* Control		*/
-	CPU_FEATURES_BIT,			/* Features control	*/
-	CPU_LBRANCH_BIT,			/* Last Branch		*/
-	CPU_BIOS_BIT,				/* BIOS			*/
-	CPU_FREQ_BIT,				/* Frequency		*/
-	CPU_MTTR_BIT,				/* MTRR			*/
-	CPU_PERF_BIT,				/* Performance		*/
-	CPU_CACHE_BIT,				/* Cache		*/
-	CPU_SYSENTER_BIT,			/* Sysenter		*/
-	CPU_THERM_BIT,				/* Thermal		*/
-	CPU_MISC_BIT,				/* Miscellaneous	*/
-	CPU_DEBUG_BIT,				/* Debug		*/
-	CPU_PAT_BIT,				/* PAT			*/
-	CPU_VMX_BIT,				/* VMX			*/
-	CPU_CALL_BIT,				/* System Call		*/
-	CPU_BASE_BIT,				/* BASE Address		*/
-	CPU_VER_BIT,				/* Version ID		*/
-	CPU_CONF_BIT,				/* Configuration	*/
-	CPU_SMM_BIT,				/* System mgmt mode	*/
-	CPU_SVM_BIT,				/*Secure Virtual Machine*/
-	CPU_OSVM_BIT,				/* OS-Visible Workaround*/
-/* Standard Registers							*/
-	CPU_TSS_BIT,				/* Task Stack Segment	*/
-	CPU_CR_BIT,				/* Control Registers	*/
-	CPU_DT_BIT,				/* Descriptor Table	*/
-/* End of Registers flags						*/
-	CPU_REG_ALL_BIT,			/* Select all Registers	*/
-};
-
-#define	CPU_REG_ALL		(~0)		/* Select all Registers	*/
-
-#define	CPU_MC			(1 << CPU_MC_BIT)
-#define	CPU_MONITOR		(1 << CPU_MONITOR_BIT)
-#define	CPU_TIME		(1 << CPU_TIME_BIT)
-#define	CPU_PMC			(1 << CPU_PMC_BIT)
-#define	CPU_PLATFORM		(1 << CPU_PLATFORM_BIT)
-#define	CPU_APIC		(1 << CPU_APIC_BIT)
-#define	CPU_POWERON		(1 << CPU_POWERON_BIT)
-#define	CPU_CONTROL		(1 << CPU_CONTROL_BIT)
-#define	CPU_FEATURES		(1 << CPU_FEATURES_BIT)
-#define	CPU_LBRANCH		(1 << CPU_LBRANCH_BIT)
-#define	CPU_BIOS		(1 << CPU_BIOS_BIT)
-#define	CPU_FREQ		(1 << CPU_FREQ_BIT)
-#define	CPU_MTRR		(1 << CPU_MTTR_BIT)
-#define	CPU_PERF		(1 << CPU_PERF_BIT)
-#define	CPU_CACHE		(1 << CPU_CACHE_BIT)
-#define	CPU_SYSENTER		(1 << CPU_SYSENTER_BIT)
-#define	CPU_THERM		(1 << CPU_THERM_BIT)
-#define	CPU_MISC		(1 << CPU_MISC_BIT)
-#define	CPU_DEBUG		(1 << CPU_DEBUG_BIT)
-#define	CPU_PAT			(1 << CPU_PAT_BIT)
-#define	CPU_VMX			(1 << CPU_VMX_BIT)
-#define	CPU_CALL		(1 << CPU_CALL_BIT)
-#define	CPU_BASE		(1 << CPU_BASE_BIT)
-#define	CPU_VER			(1 << CPU_VER_BIT)
-#define	CPU_CONF		(1 << CPU_CONF_BIT)
-#define	CPU_SMM			(1 << CPU_SMM_BIT)
-#define	CPU_SVM			(1 << CPU_SVM_BIT)
-#define	CPU_OSVM		(1 << CPU_OSVM_BIT)
-#define	CPU_TSS			(1 << CPU_TSS_BIT)
-#define	CPU_CR			(1 << CPU_CR_BIT)
-#define	CPU_DT			(1 << CPU_DT_BIT)
-
-/* Register file flags */
-enum cpu_file_bit {
-	CPU_INDEX_BIT,				/* index		*/
-	CPU_VALUE_BIT,				/* value		*/
-};
-
-#define	CPU_FILE_VALUE		(1 << CPU_VALUE_BIT)
-
-#define MAX_CPU_FILES		512
-
-struct cpu_private {
-	unsigned		cpu;
-	unsigned		type;
-	unsigned		reg;
-	unsigned		file;
-};
-
-struct cpu_debug_base {
-	char			*name;		/* Register name	*/
-	unsigned		flag;		/* Register flag	*/
-	unsigned		write;		/* Register write flag	*/
-};
-
-/*
- * Currently it looks similar to cpu_debug_base but once we add more files
- * cpu_file_base will go in different direction
- */
-struct cpu_file_base {
-	char			*name;		/* Register file name	*/
-	unsigned		flag;		/* Register file flag	*/
-	unsigned		write;		/* Register write flag	*/
-};
-
-struct cpu_cpuX_base {
-	struct dentry		*dentry;	/* Register dentry	*/
-	int			init;		/* Register index file	*/
-};
-
-struct cpu_debug_range {
-	unsigned		min;		/* Register range min	*/
-	unsigned		max;		/* Register range max	*/
-	unsigned		flag;		/* Supported flags	*/
-};
-
-#endif /* _ASM_X86_CPU_DEBUG_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index b4501ee223ad..f2ad2163109d 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -170,10 +170,7 @@ static inline void elf_common_init(struct thread_struct *t,
 }
 
 #define ELF_PLAT_INIT(_r, load_addr)			\
-do {							\
-	elf_common_init(&current->thread, _r, 0);	\
-	clear_thread_flag(TIF_IA32);			\
-} while (0)
+	elf_common_init(&current->thread, _r, 0)
 
 #define	COMPAT_ELF_PLAT_INIT(regs, load_addr)		\
 	elf_common_init(&current->thread, regs, __USER_DS)
@@ -181,14 +178,8 @@ do {							\
 void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
 #define compat_start_thread start_thread_ia32
 
-#define COMPAT_SET_PERSONALITY(ex)			\
-do {							\
-	if (test_thread_flag(TIF_IA32))			\
-		clear_thread_flag(TIF_ABI_PENDING);	\
-	else						\
-		set_thread_flag(TIF_ABI_PENDING);	\
-	current->personality |= force_personality32;	\
-} while (0)
+void set_personality_ia32(void);
+#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32()
 
 #define COMPAT_ELF_PLATFORM			("i686")
 
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 5d89fd2a3690..1d5c08a1bdfd 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -67,6 +67,7 @@ extern unsigned long hpet_address;
 extern unsigned long force_hpet_address;
 extern u8 hpet_blockid;
 extern int hpet_force_user;
+extern u8 hpet_msi_disable;
 extern int is_hpet_enabled(void);
 extern int hpet_enable(void);
 extern void hpet_disable(void);
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index c24ca9a56458..ef51b501e22a 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -12,8 +12,6 @@ struct device;
 enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
 
 struct microcode_ops {
-	void (*init)(struct device *device);
-	void (*fini)(void);
 	enum ucode_state (*request_microcode_user) (int cpu,
 				const void __user *buf, size_t size);
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index fc801bab1b3b..b753ea59703a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -450,6 +450,8 @@ struct thread_struct {
 	struct perf_event	*ptrace_bps[HBP_NUM];
 	/* Debug status used for traps, single steps, etc... */
 	unsigned long           debugreg6;
+	/* Keep track of the exact dr7 value set by the user */
+	unsigned long           ptrace_dr7;
 	/* Fault info: */
 	unsigned long		cr2;
 	unsigned long		trap_no;
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index ecb544e65382..e04740f7a0bb 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -11,9 +11,9 @@
 #include <linux/irqflags.h>
 
 /* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
+#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
 # define AT_VECTOR_SIZE_ARCH 2
-#else
+#else /* else it's non-compat x86-64 */
 # define AT_VECTOR_SIZE_ARCH 1
 #endif
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 375c917c37d2..e0d28901e969 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -87,7 +87,6 @@ struct thread_info {
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* 32bit process */
 #define TIF_FORK		18	/* ret_from_fork */
-#define TIF_ABI_PENDING		19
 #define TIF_MEMDIE		20
 #define TIF_DEBUG		21	/* uses debug registers */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
@@ -112,7 +111,6 @@ struct thread_info {
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
-#define _TIF_ABI_PENDING	(1 << TIF_ABI_PENDING)
 #define _TIF_DEBUG		(1 << TIF_DEBUG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FREEZE		(1 << TIF_FREEZE)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 036d28adf59d..af1c5833ff23 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1185,9 +1185,6 @@ static void __init acpi_process_madt(void)
 		if (!error) {
 			acpi_lapic = 1;
 
-#ifdef CONFIG_X86_BIGSMP
-			generic_bigsmp_probe();
-#endif
 			/*
 			 * Parse MADT IO-APIC entries
 			 */
@@ -1197,8 +1194,6 @@ static void __init acpi_process_madt(void)
 				acpi_ioapic = 1;
 
 				smp_found_config = 1;
-				if (apic->setup_apic_routing)
-					apic->setup_apic_routing();
 			}
 		}
 		if (error == -EINVAL) {
@@ -1349,14 +1344,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = {
 	 },
 	{
 	 .callback = force_acpi_ht,
-	 .ident = "ASUS P2B-DS",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
-		     DMI_MATCH(DMI_BOARD_NAME, "P2B-DS"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
 	 .ident = "ASUS CUR-DLS",
 	 .matches = {
 		     DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 23824fef789c..adb0ba025702 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -980,7 +980,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
 {
 	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
 	struct amd_iommu *iommu;
-	int i;
+	unsigned long i;
 
 #ifdef CONFIG_IOMMU_STRESS
 	populate = false;
@@ -1489,11 +1489,14 @@ static void __detach_device(struct device *dev)
 {
 	struct iommu_dev_data *dev_data = get_dev_data(dev);
 	struct iommu_dev_data *alias_data;
+	struct protection_domain *domain;
 	unsigned long flags;
 
 	BUG_ON(!dev_data->domain);
 
-	spin_lock_irqsave(&dev_data->domain->lock, flags);
+	domain = dev_data->domain;
+
+	spin_lock_irqsave(&domain->lock, flags);
 
 	if (dev_data->alias != dev) {
 		alias_data = get_dev_data(dev_data->alias);
@@ -1504,13 +1507,15 @@ static void __detach_device(struct device *dev)
 	if (atomic_dec_and_test(&dev_data->bind))
 		do_detach(dev);
 
-	spin_unlock_irqrestore(&dev_data->domain->lock, flags);
+	spin_unlock_irqrestore(&domain->lock, flags);
 
 	/*
 	 * If we run in passthrough mode the device must be assigned to the
-	 * passthrough domain if it is detached from any other domain
+	 * passthrough domain if it is detached from any other domain.
+	 * Make sure we can deassign from the pt_domain itself.
 	 */
-	if (iommu_pass_through && dev_data->domain == NULL)
+	if (iommu_pass_through &&
+	    (dev_data->domain == NULL && domain != pt_domain))
 		__attach_device(dev, pt_domain);
 }
 
@@ -2218,6 +2223,12 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 /*
  * The function which clues the AMD IOMMU driver into dma_ops.
  */
+
+void __init amd_iommu_init_api(void)
+{
+	register_iommu(&amd_iommu_ops);
+}
+
 int __init amd_iommu_init_dma_ops(void)
 {
 	struct amd_iommu *iommu;
@@ -2253,8 +2264,6 @@ int __init amd_iommu_init_dma_ops(void)
 	/* Make the driver finally visible to the drivers */
 	dma_ops = &amd_iommu_dma_ops;
 
-	register_iommu(&amd_iommu_ops);
-
 	amd_iommu_stats_init();
 
 	return 0;
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index fb490ce7dd55..9dc91b431470 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1292,9 +1292,12 @@ static int __init amd_iommu_init(void)
 		ret = amd_iommu_init_passthrough();
 	else
 		ret = amd_iommu_init_dma_ops();
+
 	if (ret)
 		goto free;
 
+	amd_iommu_init_api();
+
 	amd_iommu_init_notifier();
 
 	enable_iommus();
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 3987e4408f75..dfca210f6a10 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1641,9 +1641,7 @@ int __init APIC_init_uniprocessor(void)
 #endif
 
 	enable_IR_x2apic();
-#ifdef CONFIG_X86_64
 	default_setup_apic_routing();
-#endif
 
 	verify_local_APIC();
 	connect_bsp_APIC();
@@ -1891,21 +1889,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	if (apicid > max_physical_apicid)
 		max_physical_apicid = apicid;
 
-#ifdef CONFIG_X86_32
-	if (num_processors > 8) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_INTEL:
-			if (!APIC_XAPIC(version)) {
-				def_to_bigsmp = 0;
-				break;
-			}
-			/* If P4 and above fall through */
-		case X86_VENDOR_AMD:
-			def_to_bigsmp = 1;
-		}
-	}
-#endif
-
 #if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
 	early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
 	early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 1a6559f6768c..99d2fe016084 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -52,7 +52,32 @@ static int __init print_ipi_mode(void)
 }
 late_initcall(print_ipi_mode);
 
-void default_setup_apic_routing(void)
+void __init default_setup_apic_routing(void)
+{
+	int version = apic_version[boot_cpu_physical_apicid];
+
+	if (num_possible_cpus() > 8) {
+		switch (boot_cpu_data.x86_vendor) {
+		case X86_VENDOR_INTEL:
+			if (!APIC_XAPIC(version)) {
+				def_to_bigsmp = 0;
+				break;
+			}
+			/* If P4 and above fall through */
+		case X86_VENDOR_AMD:
+			def_to_bigsmp = 1;
+		}
+	}
+
+#ifdef CONFIG_X86_BIGSMP
+	generic_bigsmp_probe();
+#endif
+
+	if (apic->setup_apic_routing)
+		apic->setup_apic_routing();
+}
+
+static void setup_apic_flat_routing(void)
 {
 #ifdef CONFIG_X86_IO_APIC
 	printk(KERN_INFO
@@ -103,7 +128,7 @@ struct apic apic_default = {
 	.init_apic_ldr			= default_init_apic_ldr,
 
 	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
-	.setup_apic_routing		= default_setup_apic_routing,
+	.setup_apic_routing		= setup_apic_flat_routing,
 	.multi_timer_check		= NULL,
 	.apicid_to_node			= default_apicid_to_node,
 	.cpu_to_logical_apicid		= default_cpu_to_logical_apicid,
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 450fe2064a14..83e9be4778e2 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -67,7 +67,7 @@ void __init default_setup_apic_routing(void)
 	}
 #endif
 
-	if (apic == &apic_flat && num_processors > 8)
+	if (apic == &apic_flat && num_possible_cpus() > 8)
 			apic = &apic_physflat;
 
 	printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 1d2cb383410e..c202b62f3671 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -19,8 +19,6 @@ obj-y			+= vmware.o hypervisor.o sched.o
 obj-$(CONFIG_X86_32)	+= bugs.o cmpxchg.o
 obj-$(CONFIG_X86_64)	+= bugs_64.o
 
-obj-$(CONFIG_X86_CPU_DEBUG)		+= cpu_debug.o
-
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel.o
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
 obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
deleted file mode 100644
index b368cd862997..000000000000
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ /dev/null
@@ -1,688 +0,0 @@
-/*
- * CPU x86 architecture debug code
- *
- * Copyright(C) 2009 Jaswinder Singh Rajput
- *
- * For licencing details see kernel-base/COPYING
- */
-
-#include <linux/interrupt.h>
-#include <linux/compiler.h>
-#include <linux/seq_file.h>
-#include <linux/debugfs.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/signal.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-
-#include <asm/cpu_debug.h>
-#include <asm/paravirt.h>
-#include <asm/system.h>
-#include <asm/traps.h>
-#include <asm/apic.h>
-#include <asm/desc.h>
-
-static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpud_arr);
-static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], cpud_priv_arr);
-static DEFINE_PER_CPU(int, cpud_priv_count);
-
-static DEFINE_MUTEX(cpu_debug_lock);
-
-static struct dentry *cpu_debugfs_dir;
-
-static struct cpu_debug_base cpu_base[] = {
-	{ "mc",		CPU_MC,		0	},
-	{ "monitor",	CPU_MONITOR,	0	},
-	{ "time",	CPU_TIME,	0	},
-	{ "pmc",	CPU_PMC,	1	},
-	{ "platform",	CPU_PLATFORM,	0	},
-	{ "apic",	CPU_APIC,	0	},
-	{ "poweron",	CPU_POWERON,	0	},
-	{ "control",	CPU_CONTROL,	0	},
-	{ "features",	CPU_FEATURES,	0	},
-	{ "lastbranch",	CPU_LBRANCH,	0	},
-	{ "bios",	CPU_BIOS,	0	},
-	{ "freq",	CPU_FREQ,	0	},
-	{ "mtrr",	CPU_MTRR,	0	},
-	{ "perf",	CPU_PERF,	0	},
-	{ "cache",	CPU_CACHE,	0	},
-	{ "sysenter",	CPU_SYSENTER,	0	},
-	{ "therm",	CPU_THERM,	0	},
-	{ "misc",	CPU_MISC,	0	},
-	{ "debug",	CPU_DEBUG,	0	},
-	{ "pat",	CPU_PAT,	0	},
-	{ "vmx",	CPU_VMX,	0	},
-	{ "call",	CPU_CALL,	0	},
-	{ "base",	CPU_BASE,	0	},
-	{ "ver",	CPU_VER,	0	},
-	{ "conf",	CPU_CONF,	0	},
-	{ "smm",	CPU_SMM,	0	},
-	{ "svm",	CPU_SVM,	0	},
-	{ "osvm",	CPU_OSVM,	0	},
-	{ "tss",	CPU_TSS,	0	},
-	{ "cr",		CPU_CR,		0	},
-	{ "dt",		CPU_DT,		0	},
-	{ "registers",	CPU_REG_ALL,	0	},
-};
-
-static struct cpu_file_base cpu_file[] = {
-	{ "index",	CPU_REG_ALL,	0	},
-	{ "value",	CPU_REG_ALL,	1	},
-};
-
-/* CPU Registers Range */
-static struct cpu_debug_range cpu_reg_range[] = {
-	{ 0x00000000, 0x00000001, CPU_MC,	},
-	{ 0x00000006, 0x00000007, CPU_MONITOR,	},
-	{ 0x00000010, 0x00000010, CPU_TIME,	},
-	{ 0x00000011, 0x00000013, CPU_PMC,	},
-	{ 0x00000017, 0x00000017, CPU_PLATFORM,	},
-	{ 0x0000001B, 0x0000001B, CPU_APIC,	},
-	{ 0x0000002A, 0x0000002B, CPU_POWERON,	},
-	{ 0x0000002C, 0x0000002C, CPU_FREQ,	},
-	{ 0x0000003A, 0x0000003A, CPU_CONTROL,	},
-	{ 0x00000040, 0x00000047, CPU_LBRANCH,	},
-	{ 0x00000060, 0x00000067, CPU_LBRANCH,	},
-	{ 0x00000079, 0x00000079, CPU_BIOS,	},
-	{ 0x00000088, 0x0000008A, CPU_CACHE,	},
-	{ 0x0000008B, 0x0000008B, CPU_BIOS,	},
-	{ 0x0000009B, 0x0000009B, CPU_MONITOR,	},
-	{ 0x000000C1, 0x000000C4, CPU_PMC,	},
-	{ 0x000000CD, 0x000000CD, CPU_FREQ,	},
-	{ 0x000000E7, 0x000000E8, CPU_PERF,	},
-	{ 0x000000FE, 0x000000FE, CPU_MTRR,	},
-
-	{ 0x00000116, 0x0000011E, CPU_CACHE,	},
-	{ 0x00000174, 0x00000176, CPU_SYSENTER,	},
-	{ 0x00000179, 0x0000017B, CPU_MC,	},
-	{ 0x00000186, 0x00000189, CPU_PMC,	},
-	{ 0x00000198, 0x00000199, CPU_PERF,	},
-	{ 0x0000019A, 0x0000019A, CPU_TIME,	},
-	{ 0x0000019B, 0x0000019D, CPU_THERM,	},
-	{ 0x000001A0, 0x000001A0, CPU_MISC,	},
-	{ 0x000001C9, 0x000001C9, CPU_LBRANCH,	},
-	{ 0x000001D7, 0x000001D8, CPU_LBRANCH,	},
-	{ 0x000001D9, 0x000001D9, CPU_DEBUG,	},
-	{ 0x000001DA, 0x000001E0, CPU_LBRANCH,	},
-
-	{ 0x00000200, 0x0000020F, CPU_MTRR,	},
-	{ 0x00000250, 0x00000250, CPU_MTRR,	},
-	{ 0x00000258, 0x00000259, CPU_MTRR,	},
-	{ 0x00000268, 0x0000026F, CPU_MTRR,	},
-	{ 0x00000277, 0x00000277, CPU_PAT,	},
-	{ 0x000002FF, 0x000002FF, CPU_MTRR,	},
-
-	{ 0x00000300, 0x00000311, CPU_PMC,	},
-	{ 0x00000345, 0x00000345, CPU_PMC,	},
-	{ 0x00000360, 0x00000371, CPU_PMC,	},
-	{ 0x0000038D, 0x00000390, CPU_PMC,	},
-	{ 0x000003A0, 0x000003BE, CPU_PMC,	},
-	{ 0x000003C0, 0x000003CD, CPU_PMC,	},
-	{ 0x000003E0, 0x000003E1, CPU_PMC,	},
-	{ 0x000003F0, 0x000003F2, CPU_PMC,	},
-
-	{ 0x00000400, 0x00000417, CPU_MC,	},
-	{ 0x00000480, 0x0000048B, CPU_VMX,	},
-
-	{ 0x00000600, 0x00000600, CPU_DEBUG,	},
-	{ 0x00000680, 0x0000068F, CPU_LBRANCH,	},
-	{ 0x000006C0, 0x000006CF, CPU_LBRANCH,	},
-
-	{ 0x000107CC, 0x000107D3, CPU_PMC,	},
-
-	{ 0xC0000080, 0xC0000080, CPU_FEATURES,	},
-	{ 0xC0000081, 0xC0000084, CPU_CALL,	},
-	{ 0xC0000100, 0xC0000102, CPU_BASE,	},
-	{ 0xC0000103, 0xC0000103, CPU_TIME,	},
-
-	{ 0xC0010000, 0xC0010007, CPU_PMC,	},
-	{ 0xC0010010, 0xC0010010, CPU_CONF,	},
-	{ 0xC0010015, 0xC0010015, CPU_CONF,	},
-	{ 0xC0010016, 0xC001001A, CPU_MTRR,	},
-	{ 0xC001001D, 0xC001001D, CPU_MTRR,	},
-	{ 0xC001001F, 0xC001001F, CPU_CONF,	},
-	{ 0xC0010030, 0xC0010035, CPU_BIOS,	},
-	{ 0xC0010044, 0xC0010048, CPU_MC,	},
-	{ 0xC0010050, 0xC0010056, CPU_SMM,	},
-	{ 0xC0010058, 0xC0010058, CPU_CONF,	},
-	{ 0xC0010060, 0xC0010060, CPU_CACHE,	},
-	{ 0xC0010061, 0xC0010068, CPU_SMM,	},
-	{ 0xC0010069, 0xC001006B, CPU_SMM,	},
-	{ 0xC0010070, 0xC0010071, CPU_SMM,	},
-	{ 0xC0010111, 0xC0010113, CPU_SMM,	},
-	{ 0xC0010114, 0xC0010118, CPU_SVM,	},
-	{ 0xC0010140, 0xC0010141, CPU_OSVM,	},
-	{ 0xC0011022, 0xC0011023, CPU_CONF,	},
-};
-
-static int is_typeflag_valid(unsigned cpu, unsigned flag)
-{
-	int i;
-
-	/* Standard Registers should be always valid */
-	if (flag >= CPU_TSS)
-		return 1;
-
-	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
-		if (cpu_reg_range[i].flag == flag)
-			return 1;
-	}
-
-	/* Invalid */
-	return 0;
-}
-
-static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max,
-			      int index, unsigned flag)
-{
-	if (cpu_reg_range[index].flag == flag) {
-		*min = cpu_reg_range[index].min;
-		*max = cpu_reg_range[index].max;
-	} else
-		*max = 0;
-
-	return *max;
-}
-
-/* This function can also be called with seq = NULL for printk */
-static void print_cpu_data(struct seq_file *seq, unsigned type,
-			   u32 low, u32 high)
-{
-	struct cpu_private *priv;
-	u64 val = high;
-
-	if (seq) {
-		priv = seq->private;
-		if (priv->file) {
-			val = (val << 32) | low;
-			seq_printf(seq, "0x%llx\n", val);
-		} else
-			seq_printf(seq, " %08x: %08x_%08x\n",
-				   type, high, low);
-	} else
-		printk(KERN_INFO " %08x: %08x_%08x\n", type, high, low);
-}
-
-/* This function can also be called with seq = NULL for printk */
-static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
-{
-	unsigned msr, msr_min, msr_max;
-	struct cpu_private *priv;
-	u32 low, high;
-	int i;
-
-	if (seq) {
-		priv = seq->private;
-		if (priv->file) {
-			if (!rdmsr_safe_on_cpu(priv->cpu, priv->reg,
-					       &low, &high))
-				print_cpu_data(seq, priv->reg, low, high);
-			return;
-		}
-	}
-
-	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
-		if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag))
-			continue;
-
-		for (msr = msr_min; msr <= msr_max; msr++) {
-			if (rdmsr_safe_on_cpu(cpu, msr, &low, &high))
-				continue;
-			print_cpu_data(seq, msr, low, high);
-		}
-	}
-}
-
-static void print_tss(void *arg)
-{
-	struct pt_regs *regs = task_pt_regs(current);
-	struct seq_file *seq = arg;
-	unsigned int seg;
-
-	seq_printf(seq, " RAX\t: %016lx\n", regs->ax);
-	seq_printf(seq, " RBX\t: %016lx\n", regs->bx);
-	seq_printf(seq, " RCX\t: %016lx\n", regs->cx);
-	seq_printf(seq, " RDX\t: %016lx\n", regs->dx);
-
-	seq_printf(seq, " RSI\t: %016lx\n", regs->si);
-	seq_printf(seq, " RDI\t: %016lx\n", regs->di);
-	seq_printf(seq, " RBP\t: %016lx\n", regs->bp);
-	seq_printf(seq, " ESP\t: %016lx\n", regs->sp);
-
-#ifdef CONFIG_X86_64
-	seq_printf(seq, " R08\t: %016lx\n", regs->r8);
-	seq_printf(seq, " R09\t: %016lx\n", regs->r9);
-	seq_printf(seq, " R10\t: %016lx\n", regs->r10);
-	seq_printf(seq, " R11\t: %016lx\n", regs->r11);
-	seq_printf(seq, " R12\t: %016lx\n", regs->r12);
-	seq_printf(seq, " R13\t: %016lx\n", regs->r13);
-	seq_printf(seq, " R14\t: %016lx\n", regs->r14);
-	seq_printf(seq, " R15\t: %016lx\n", regs->r15);
-#endif
-
-	asm("movl %%cs,%0" : "=r" (seg));
-	seq_printf(seq, " CS\t:             %04x\n", seg);
-	asm("movl %%ds,%0" : "=r" (seg));
-	seq_printf(seq, " DS\t:             %04x\n", seg);
-	seq_printf(seq, " SS\t:             %04lx\n", regs->ss & 0xffff);
-	asm("movl %%es,%0" : "=r" (seg));
-	seq_printf(seq, " ES\t:             %04x\n", seg);
-	asm("movl %%fs,%0" : "=r" (seg));
-	seq_printf(seq, " FS\t:             %04x\n", seg);
-	asm("movl %%gs,%0" : "=r" (seg));
-	seq_printf(seq, " GS\t:             %04x\n", seg);
-
-	seq_printf(seq, " EFLAGS\t: %016lx\n", regs->flags);
-
-	seq_printf(seq, " EIP\t: %016lx\n", regs->ip);
-}
-
-static void print_cr(void *arg)
-{
-	struct seq_file *seq = arg;
-
-	seq_printf(seq, " cr0\t: %016lx\n", read_cr0());
-	seq_printf(seq, " cr2\t: %016lx\n", read_cr2());
-	seq_printf(seq, " cr3\t: %016lx\n", read_cr3());
-	seq_printf(seq, " cr4\t: %016lx\n", read_cr4_safe());
-#ifdef CONFIG_X86_64
-	seq_printf(seq, " cr8\t: %016lx\n", read_cr8());
-#endif
-}
-
-static void print_desc_ptr(char *str, struct seq_file *seq, struct desc_ptr dt)
-{
-	seq_printf(seq, " %s\t: %016llx\n", str, (u64)(dt.address | dt.size));
-}
-
-static void print_dt(void *seq)
-{
-	struct desc_ptr dt;
-	unsigned long ldt;
-
-	/* IDT */
-	store_idt((struct desc_ptr *)&dt);
-	print_desc_ptr("IDT", seq, dt);
-
-	/* GDT */
-	store_gdt((struct desc_ptr *)&dt);
-	print_desc_ptr("GDT", seq, dt);
-
-	/* LDT */
-	store_ldt(ldt);
-	seq_printf(seq, " LDT\t: %016lx\n", ldt);
-
-	/* TR */
-	store_tr(ldt);
-	seq_printf(seq, " TR\t: %016lx\n", ldt);
-}
-
-static void print_dr(void *arg)
-{
-	struct seq_file *seq = arg;
-	unsigned long dr;
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		/* Ignore db4, db5 */
-		if ((i == 4) || (i == 5))
-			continue;
-		get_debugreg(dr, i);
-		seq_printf(seq, " dr%d\t: %016lx\n", i, dr);
-	}
-
-	seq_printf(seq, "\n MSR\t:\n");
-}
-
-static void print_apic(void *arg)
-{
-	struct seq_file *seq = arg;
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	seq_printf(seq, " LAPIC\t:\n");
-	seq_printf(seq, " ID\t\t: %08x\n",  apic_read(APIC_ID) >> 24);
-	seq_printf(seq, " LVR\t\t: %08x\n",  apic_read(APIC_LVR));
-	seq_printf(seq, " TASKPRI\t: %08x\n",  apic_read(APIC_TASKPRI));
-	seq_printf(seq, " ARBPRI\t\t: %08x\n",  apic_read(APIC_ARBPRI));
-	seq_printf(seq, " PROCPRI\t: %08x\n",  apic_read(APIC_PROCPRI));
-	seq_printf(seq, " LDR\t\t: %08x\n",  apic_read(APIC_LDR));
-	seq_printf(seq, " DFR\t\t: %08x\n",  apic_read(APIC_DFR));
-	seq_printf(seq, " SPIV\t\t: %08x\n",  apic_read(APIC_SPIV));
-	seq_printf(seq, " ISR\t\t: %08x\n",  apic_read(APIC_ISR));
-	seq_printf(seq, " ESR\t\t: %08x\n",  apic_read(APIC_ESR));
-	seq_printf(seq, " ICR\t\t: %08x\n",  apic_read(APIC_ICR));
-	seq_printf(seq, " ICR2\t\t: %08x\n",  apic_read(APIC_ICR2));
-	seq_printf(seq, " LVTT\t\t: %08x\n",  apic_read(APIC_LVTT));
-	seq_printf(seq, " LVTTHMR\t: %08x\n",  apic_read(APIC_LVTTHMR));
-	seq_printf(seq, " LVTPC\t\t: %08x\n",  apic_read(APIC_LVTPC));
-	seq_printf(seq, " LVT0\t\t: %08x\n",  apic_read(APIC_LVT0));
-	seq_printf(seq, " LVT1\t\t: %08x\n",  apic_read(APIC_LVT1));
-	seq_printf(seq, " LVTERR\t\t: %08x\n",  apic_read(APIC_LVTERR));
-	seq_printf(seq, " TMICT\t\t: %08x\n",  apic_read(APIC_TMICT));
-	seq_printf(seq, " TMCCT\t\t: %08x\n",  apic_read(APIC_TMCCT));
-	seq_printf(seq, " TDCR\t\t: %08x\n",  apic_read(APIC_TDCR));
-	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
-		unsigned int i, v, maxeilvt;
-
-		v = apic_read(APIC_EFEAT);
-		maxeilvt = (v >> 16) & 0xff;
-		seq_printf(seq, " EFEAT\t\t: %08x\n", v);
-		seq_printf(seq, " ECTRL\t\t: %08x\n", apic_read(APIC_ECTRL));
-
-		for (i = 0; i < maxeilvt; i++) {
-			v = apic_read(APIC_EILVTn(i));
-			seq_printf(seq, " EILVT%d\t\t: %08x\n", i, v);
-		}
-	}
-#endif /* CONFIG_X86_LOCAL_APIC */
-	seq_printf(seq, "\n MSR\t:\n");
-}
-
-static int cpu_seq_show(struct seq_file *seq, void *v)
-{
-	struct cpu_private *priv = seq->private;
-
-	if (priv == NULL)
-		return -EINVAL;
-
-	switch (cpu_base[priv->type].flag) {
-	case CPU_TSS:
-		smp_call_function_single(priv->cpu, print_tss, seq, 1);
-		break;
-	case CPU_CR:
-		smp_call_function_single(priv->cpu, print_cr, seq, 1);
-		break;
-	case CPU_DT:
-		smp_call_function_single(priv->cpu, print_dt, seq, 1);
-		break;
-	case CPU_DEBUG:
-		if (priv->file == CPU_INDEX_BIT)
-			smp_call_function_single(priv->cpu, print_dr, seq, 1);
-		print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
-		break;
-	case CPU_APIC:
-		if (priv->file == CPU_INDEX_BIT)
-			smp_call_function_single(priv->cpu, print_apic, seq, 1);
-		print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
-		break;
-
-	default:
-		print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
-		break;
-	}
-	seq_printf(seq, "\n");
-
-	return 0;
-}
-
-static void *cpu_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	if (*pos == 0) /* One time is enough ;-) */
-		return seq;
-
-	return NULL;
-}
-
-static void *cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	(*pos)++;
-
-	return cpu_seq_start(seq, pos);
-}
-
-static void cpu_seq_stop(struct seq_file *seq, void *v)
-{
-}
-
-static const struct seq_operations cpu_seq_ops = {
-	.start		= cpu_seq_start,
-	.next		= cpu_seq_next,
-	.stop		= cpu_seq_stop,
-	.show		= cpu_seq_show,
-};
-
-static int cpu_seq_open(struct inode *inode, struct file *file)
-{
-	struct cpu_private *priv = inode->i_private;
-	struct seq_file *seq;
-	int err;
-
-	err = seq_open(file, &cpu_seq_ops);
-	if (!err) {
-		seq = file->private_data;
-		seq->private = priv;
-	}
-
-	return err;
-}
-
-static int write_msr(struct cpu_private *priv, u64 val)
-{
-	u32 low, high;
-
-	high = (val >> 32) & 0xffffffff;
-	low = val & 0xffffffff;
-
-	if (!wrmsr_safe_on_cpu(priv->cpu, priv->reg, low, high))
-		return 0;
-
-	return -EPERM;
-}
-
-static int write_cpu_register(struct cpu_private *priv, const char *buf)
-{
-	int ret = -EPERM;
-	u64 val;
-
-	ret = strict_strtoull(buf, 0, &val);
-	if (ret < 0)
-		return ret;
-
-	/* Supporting only MSRs */
-	if (priv->type < CPU_TSS_BIT)
-		return write_msr(priv, val);
-
-	return ret;
-}
-
-static ssize_t cpu_write(struct file *file, const char __user *ubuf,
-			     size_t count, loff_t *off)
-{
-	struct seq_file *seq = file->private_data;
-	struct cpu_private *priv = seq->private;
-	char buf[19];
-
-	if ((priv == NULL) || (count >= sizeof(buf)))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, count))
-		return -EFAULT;
-
-	buf[count] = 0;
-
-	if ((cpu_base[priv->type].write) && (cpu_file[priv->file].write))
-		if (!write_cpu_register(priv, buf))
-			return count;
-
-	return -EACCES;
-}
-
-static const struct file_operations cpu_fops = {
-	.owner		= THIS_MODULE,
-	.open		= cpu_seq_open,
-	.read		= seq_read,
-	.write		= cpu_write,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
-			   unsigned file, struct dentry *dentry)
-{
-	struct cpu_private *priv = NULL;
-
-	/* Already intialized */
-	if (file == CPU_INDEX_BIT)
-		if (per_cpu(cpud_arr[type].init, cpu))
-			return 0;
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (priv == NULL)
-		return -ENOMEM;
-
-	priv->cpu = cpu;
-	priv->type = type;
-	priv->reg = reg;
-	priv->file = file;
-	mutex_lock(&cpu_debug_lock);
-	per_cpu(cpud_priv_arr[type], cpu) = priv;
-	per_cpu(cpud_priv_count, cpu)++;
-	mutex_unlock(&cpu_debug_lock);
-
-	if (file)
-		debugfs_create_file(cpu_file[file].name, S_IRUGO,
-				    dentry, (void *)priv, &cpu_fops);
-	else {
-		debugfs_create_file(cpu_base[type].name, S_IRUGO,
-				    per_cpu(cpud_arr[type].dentry, cpu),
-				    (void *)priv, &cpu_fops);
-		mutex_lock(&cpu_debug_lock);
-		per_cpu(cpud_arr[type].init, cpu) = 1;
-		mutex_unlock(&cpu_debug_lock);
-	}
-
-	return 0;
-}
-
-static int cpu_init_regfiles(unsigned cpu, unsigned int type, unsigned reg,
-			     struct dentry *dentry)
-{
-	unsigned file;
-	int err = 0;
-
-	for (file = 0; file <  ARRAY_SIZE(cpu_file); file++) {
-		err = cpu_create_file(cpu, type, reg, file, dentry);
-		if (err)
-			return err;
-	}
-
-	return err;
-}
-
-static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry)
-{
-	struct dentry *cpu_dentry = NULL;
-	unsigned reg, reg_min, reg_max;
-	int i, err = 0;
-	char reg_dir[12];
-	u32 low, high;
-
-	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
-		if (!get_cpu_range(cpu, &reg_min, &reg_max, i,
-				   cpu_base[type].flag))
-			continue;
-
-		for (reg = reg_min; reg <= reg_max; reg++) {
-			if (rdmsr_safe_on_cpu(cpu, reg, &low, &high))
-				continue;
-
-			sprintf(reg_dir, "0x%x", reg);
-			cpu_dentry = debugfs_create_dir(reg_dir, dentry);
-			err = cpu_init_regfiles(cpu, type, reg, cpu_dentry);
-			if (err)
-				return err;
-		}
-	}
-
-	return err;
-}
-
-static int cpu_init_allreg(unsigned cpu, struct dentry *dentry)
-{
-	struct dentry *cpu_dentry = NULL;
-	unsigned type;
-	int err = 0;
-
-	for (type = 0; type <  ARRAY_SIZE(cpu_base) - 1; type++) {
-		if (!is_typeflag_valid(cpu, cpu_base[type].flag))
-			continue;
-		cpu_dentry = debugfs_create_dir(cpu_base[type].name, dentry);
-		per_cpu(cpud_arr[type].dentry, cpu) = cpu_dentry;
-
-		if (type < CPU_TSS_BIT)
-			err = cpu_init_msr(cpu, type, cpu_dentry);
-		else
-			err = cpu_create_file(cpu, type, 0, CPU_INDEX_BIT,
-					      cpu_dentry);
-		if (err)
-			return err;
-	}
-
-	return err;
-}
-
-static int cpu_init_cpu(void)
-{
-	struct dentry *cpu_dentry = NULL;
-	struct cpuinfo_x86 *cpui;
-	char cpu_dir[12];
-	unsigned cpu;
-	int err = 0;
-
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
-		cpui = &cpu_data(cpu);
-		if (!cpu_has(cpui, X86_FEATURE_MSR))
-			continue;
-
-		sprintf(cpu_dir, "cpu%d", cpu);
-		cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir);
-		err = cpu_init_allreg(cpu, cpu_dentry);
-
-		pr_info("cpu%d(%d) debug files %d\n",
-			cpu, nr_cpu_ids, per_cpu(cpud_priv_count, cpu));
-		if (per_cpu(cpud_priv_count, cpu) > MAX_CPU_FILES) {
-			pr_err("Register files count %d exceeds limit %d\n",
-				per_cpu(cpud_priv_count, cpu), MAX_CPU_FILES);
-			per_cpu(cpud_priv_count, cpu) = MAX_CPU_FILES;
-			err = -ENFILE;
-		}
-		if (err)
-			return err;
-	}
-
-	return err;
-}
-
-static int __init cpu_debug_init(void)
-{
-	cpu_debugfs_dir = debugfs_create_dir("cpu", arch_debugfs_dir);
-
-	return cpu_init_cpu();
-}
-
-static void __exit cpu_debug_exit(void)
-{
-	int i, cpu;
-
-	if (cpu_debugfs_dir)
-		debugfs_remove_recursive(cpu_debugfs_dir);
-
-	for (cpu = 0; cpu <  nr_cpu_ids; cpu++)
-		for (i = 0; i < per_cpu(cpud_priv_count, cpu); i++)
-			kfree(per_cpu(cpud_priv_arr[i], cpu));
-}
-
-module_init(cpu_debug_init);
-module_exit(cpu_debug_exit);
-
-MODULE_AUTHOR("Jaswinder Singh Rajput");
-MODULE_DESCRIPTION("CPU Debug module");
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index f125e5c551c0..6e44519960c8 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1356,6 +1356,7 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol)
 
 	kfree(data->powernow_table);
 	kfree(data);
+	per_cpu(powernow_data, pol->cpu) = NULL;
 
 	return 0;
 }
@@ -1375,7 +1376,7 @@ static unsigned int powernowk8_get(unsigned int cpu)
 	int err;
 
 	if (!data)
-		return -EINVAL;
+		return 0;
 
 	smp_call_function_single(cpu, query_values_on_cpu, &err, true);
 	if (err)
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index cb27fd6136c9..83e5e628de73 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -229,7 +229,7 @@ static void __exit cpuid_exit(void)
 	for_each_online_cpu(cpu)
 		cpuid_device_destroy(cpu);
 	class_destroy(cpuid_class);
-	unregister_chrdev(CPUID_MAJOR, "cpu/cpuid");
+	__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
 	unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
 }
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ba6e65884603..ad80a1c718c6 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -34,6 +34,8 @@
  */
 unsigned long				hpet_address;
 u8					hpet_blockid; /* OS timer block num */
+u8					hpet_msi_disable;
+
 #ifdef CONFIG_PCI_MSI
 static unsigned long			hpet_num_timers;
 #endif
@@ -596,6 +598,9 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 	unsigned int num_timers_used = 0;
 	int i;
 
+	if (hpet_msi_disable)
+		return;
+
 	if (boot_cpu_has(X86_FEATURE_ARAT))
 		return;
 	id = hpet_readl(HPET_ID);
@@ -928,6 +933,9 @@ static __init int hpet_late_init(void)
 	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
 	hpet_print_config();
 
+	if (hpet_msi_disable)
+		return 0;
+
 	if (boot_cpu_has(X86_FEATURE_ARAT))
 		return 0;
 
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index ae90b4739435..dca2802c666f 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -212,25 +212,6 @@ static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
 
-/*
- * Store a breakpoint's encoded address, length, and type.
- */
-static int arch_store_info(struct perf_event *bp)
-{
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	/*
-	 * For kernel-addresses, either the address or symbol name can be
-	 * specified.
-	 */
-	if (info->name)
-		info->address = (unsigned long)
-				kallsyms_lookup_name(info->name);
-	if (info->address)
-		return 0;
-
-	return -EINVAL;
-}
-
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
@@ -362,10 +343,13 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 		return ret;
 	}
 
-	ret = arch_store_info(bp);
-
-	if (ret < 0)
-		return ret;
+	/*
+	 * For kernel-addresses, either the address or symbol name can be
+	 * specified.
+	 */
+	if (info->name)
+		info->address = (unsigned long)
+				kallsyms_lookup_name(info->name);
 	/*
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index dd74fe7273b1..bfba6019d762 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -42,6 +42,7 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/nmi.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
@@ -204,40 +205,81 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 
 static struct hw_breakpoint {
 	unsigned		enabled;
-	unsigned		type;
-	unsigned		len;
 	unsigned long		addr;
+	int			len;
+	int			type;
+	struct perf_event	**pev;
 } breakinfo[4];
 
 static void kgdb_correct_hw_break(void)
 {
-	unsigned long dr7;
-	int correctit = 0;
-	int breakbit;
 	int breakno;
 
-	get_debugreg(dr7, 7);
 	for (breakno = 0; breakno < 4; breakno++) {
-		breakbit = 2 << (breakno << 1);
-		if (!(dr7 & breakbit) && breakinfo[breakno].enabled) {
-			correctit = 1;
-			dr7 |= breakbit;
-			dr7 &= ~(0xf0000 << (breakno << 2));
-			dr7 |= ((breakinfo[breakno].len << 2) |
-				 breakinfo[breakno].type) <<
-			       ((breakno << 2) + 16);
-			set_debugreg(breakinfo[breakno].addr, breakno);
-
-		} else {
-			if ((dr7 & breakbit) && !breakinfo[breakno].enabled) {
-				correctit = 1;
-				dr7 &= ~breakbit;
-				dr7 &= ~(0xf0000 << (breakno << 2));
-			}
-		}
+		struct perf_event *bp;
+		struct arch_hw_breakpoint *info;
+		int val;
+		int cpu = raw_smp_processor_id();
+		if (!breakinfo[breakno].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		info = counter_arch_bp(bp);
+		if (bp->attr.disabled != 1)
+			continue;
+		bp->attr.bp_addr = breakinfo[breakno].addr;
+		bp->attr.bp_len = breakinfo[breakno].len;
+		bp->attr.bp_type = breakinfo[breakno].type;
+		info->address = breakinfo[breakno].addr;
+		info->len = breakinfo[breakno].len;
+		info->type = breakinfo[breakno].type;
+		val = arch_install_hw_breakpoint(bp);
+		if (!val)
+			bp->attr.disabled = 0;
+	}
+	hw_breakpoint_restore();
+}
+
+static int hw_break_reserve_slot(int breakno)
+{
+	int cpu;
+	int cnt = 0;
+	struct perf_event **pevent;
+
+	for_each_online_cpu(cpu) {
+		cnt++;
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		if (dbg_reserve_bp_slot(*pevent))
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	for_each_online_cpu(cpu) {
+		cnt--;
+		if (!cnt)
+			break;
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		dbg_release_bp_slot(*pevent);
 	}
-	if (correctit)
-		set_debugreg(dr7, 7);
+	return -1;
+}
+
+static int hw_break_release_slot(int breakno)
+{
+	struct perf_event **pevent;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		if (dbg_release_bp_slot(*pevent))
+			/*
+			 * The debugger is responisble for handing the retry on
+			 * remove failure.
+			 */
+			return -1;
+	}
+	return 0;
 }
 
 static int
@@ -251,6 +293,10 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 	if (i == 4)
 		return -1;
 
+	if (hw_break_release_slot(i)) {
+		printk(KERN_ERR "Cannot remove hw breakpoint at %lx\n", addr);
+		return -1;
+	}
 	breakinfo[i].enabled = 0;
 
 	return 0;
@@ -259,15 +305,23 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 static void kgdb_remove_all_hw_break(void)
 {
 	int i;
+	int cpu = raw_smp_processor_id();
+	struct perf_event *bp;
 
-	for (i = 0; i < 4; i++)
-		memset(&breakinfo[i], 0, sizeof(struct hw_breakpoint));
+	for (i = 0; i < 4; i++) {
+		if (!breakinfo[i].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (bp->attr.disabled == 1)
+			continue;
+		arch_uninstall_hw_breakpoint(bp);
+		bp->attr.disabled = 1;
+	}
 }
 
 static int
 kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 {
-	unsigned type;
 	int i;
 
 	for (i = 0; i < 4; i++)
@@ -278,27 +332,42 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 
 	switch (bptype) {
 	case BP_HARDWARE_BREAKPOINT:
-		type = 0;
-		len  = 1;
+		len = 1;
+		breakinfo[i].type = X86_BREAKPOINT_EXECUTE;
 		break;
 	case BP_WRITE_WATCHPOINT:
-		type = 1;
+		breakinfo[i].type = X86_BREAKPOINT_WRITE;
 		break;
 	case BP_ACCESS_WATCHPOINT:
-		type = 3;
+		breakinfo[i].type = X86_BREAKPOINT_RW;
 		break;
 	default:
 		return -1;
 	}
-
-	if (len == 1 || len == 2 || len == 4)
-		breakinfo[i].len  = len - 1;
-	else
+	switch (len) {
+	case 1:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_1;
+		break;
+	case 2:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_2;
+		break;
+	case 4:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_4;
+		break;
+#ifdef CONFIG_X86_64
+	case 8:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_8;
+		break;
+#endif
+	default:
 		return -1;
-
-	breakinfo[i].enabled = 1;
+	}
 	breakinfo[i].addr = addr;
-	breakinfo[i].type = type;
+	if (hw_break_reserve_slot(i)) {
+		breakinfo[i].addr = 0;
+		return -1;
+	}
+	breakinfo[i].enabled = 1;
 
 	return 0;
 }
@@ -313,8 +382,21 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
  */
 void kgdb_disable_hw_debug(struct pt_regs *regs)
 {
+	int i;
+	int cpu = raw_smp_processor_id();
+	struct perf_event *bp;
+
 	/* Disable hardware debugging while we are in kgdb: */
 	set_debugreg(0UL, 7);
+	for (i = 0; i < 4; i++) {
+		if (!breakinfo[i].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (bp->attr.disabled == 1)
+			continue;
+		arch_uninstall_hw_breakpoint(bp);
+		bp->attr.disabled = 1;
+	}
 }
 
 /**
@@ -378,7 +460,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 			       struct pt_regs *linux_regs)
 {
 	unsigned long addr;
-	unsigned long dr6;
 	char *ptr;
 	int newPC;
 
@@ -404,20 +485,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 				   raw_smp_processor_id());
 		}
 
-		get_debugreg(dr6, 6);
-		if (!(dr6 & 0x4000)) {
-			int breakno;
-
-			for (breakno = 0; breakno < 4; breakno++) {
-				if (dr6 & (1 << breakno) &&
-				    breakinfo[breakno].type == 0) {
-					/* Set restore flag: */
-					linux_regs->flags |= X86_EFLAGS_RF;
-					break;
-				}
-			}
-		}
-		set_debugreg(0UL, 6);
 		kgdb_correct_hw_break();
 
 		return 0;
@@ -485,8 +552,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 		break;
 
 	case DIE_DEBUG:
-		if (atomic_read(&kgdb_cpu_doing_single_step) ==
-		    raw_smp_processor_id()) {
+		if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
 			if (user_mode(regs))
 				return single_step_cont(regs, args);
 			break;
@@ -539,7 +605,42 @@ static struct notifier_block kgdb_notifier = {
  */
 int kgdb_arch_init(void)
 {
-	return register_die_notifier(&kgdb_notifier);
+	int i, cpu;
+	int ret;
+	struct perf_event_attr attr;
+	struct perf_event **pevent;
+
+	ret = register_die_notifier(&kgdb_notifier);
+	if (ret != 0)
+		return ret;
+	/*
+	 * Pre-allocate the hw breakpoint structions in the non-atomic
+	 * portion of kgdb because this operation requires mutexs to
+	 * complete.
+	 */
+	attr.bp_addr = (unsigned long)kgdb_arch_init;
+	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.bp_len = HW_BREAKPOINT_LEN_1;
+	attr.bp_type = HW_BREAKPOINT_W;
+	attr.disabled = 1;
+	for (i = 0; i < 4; i++) {
+		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL);
+		if (IS_ERR(breakinfo[i].pev)) {
+			printk(KERN_ERR "kgdb: Could not allocate hw breakpoints\n");
+			breakinfo[i].pev = NULL;
+			kgdb_arch_exit();
+			return -1;
+		}
+		for_each_online_cpu(cpu) {
+			pevent = per_cpu_ptr(breakinfo[i].pev, cpu);
+			pevent[0]->hw.sample_period = 1;
+			if (pevent[0]->destroy != NULL) {
+				pevent[0]->destroy = NULL;
+				release_bp_slot(*pevent);
+			}
+		}
+	}
+	return ret;
 }
 
 /**
@@ -550,6 +651,13 @@ int kgdb_arch_init(void)
  */
 void kgdb_arch_exit(void)
 {
+	int i;
+	for (i = 0; i < 4; i++) {
+		if (breakinfo[i].pev) {
+			unregister_wide_hw_breakpoint(breakinfo[i].pev);
+			breakinfo[i].pev = NULL;
+		}
+	}
 	unregister_die_notifier(&kgdb_notifier);
 }
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 37542b67c57e..e1af7c055c7d 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -36,9 +36,6 @@ MODULE_LICENSE("GPL v2");
 #define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000
 #define UCODE_UCODE_TYPE           0x00000001
 
-const struct firmware *firmware;
-static int supported_cpu;
-
 struct equiv_cpu_entry {
 	u32	installed_cpu;
 	u32	fixed_errata_mask;
@@ -77,12 +74,15 @@ static struct equiv_cpu_entry *equiv_cpu_table;
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 dummy;
 
-	if (!supported_cpu)
-		return -1;
-
 	memset(csig, 0, sizeof(*csig));
+	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
+		pr_warning("microcode: CPU%d: AMD CPU family 0x%x not "
+			   "supported\n", cpu, c->x86);
+		return -1;
+	}
 	rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy);
 	pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev);
 	return 0;
@@ -294,10 +294,14 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 {
+	const char *fw_name = "amd-ucode/microcode_amd.bin";
+	const struct firmware *firmware;
 	enum ucode_state ret;
 
-	if (firmware == NULL)
+	if (request_firmware(&firmware, fw_name, device)) {
+		printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
 		return UCODE_NFOUND;
+	}
 
 	if (*(u32 *)firmware->data != UCODE_MAGIC) {
 		pr_err("invalid UCODE_MAGIC (0x%08x)\n",
@@ -307,6 +311,8 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 
 	ret = generic_load_microcode(cpu, firmware->data, firmware->size);
 
+	release_firmware(firmware);
+
 	return ret;
 }
 
@@ -325,31 +331,7 @@ static void microcode_fini_cpu_amd(int cpu)
 	uci->mc = NULL;
 }
 
-void init_microcode_amd(struct device *device)
-{
-	const char *fw_name = "amd-ucode/microcode_amd.bin";
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	WARN_ON(c->x86_vendor != X86_VENDOR_AMD);
-
-	if (c->x86 < 0x10) {
-		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
-		return;
-	}
-	supported_cpu = 1;
-
-	if (request_firmware(&firmware, fw_name, device))
-		pr_err("failed to load file %s\n", fw_name);
-}
-
-void fini_microcode_amd(void)
-{
-	release_firmware(firmware);
-}
-
 static struct microcode_ops microcode_amd_ops = {
-	.init				  = init_microcode_amd,
-	.fini				  = fini_microcode_amd,
 	.request_microcode_user           = request_microcode_user,
 	.request_microcode_fw             = request_microcode_fw,
 	.collect_cpu_info                 = collect_cpu_info_amd,
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 0c8632433090..cceb5bc3c3c2 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -521,9 +521,6 @@ static int __init microcode_init(void)
 		return PTR_ERR(microcode_pdev);
 	}
 
-	if (microcode_ops->init)
-		microcode_ops->init(&microcode_pdev->dev);
-
 	get_online_cpus();
 	mutex_lock(&microcode_mutex);
 
@@ -566,9 +563,6 @@ static void __exit microcode_exit(void)
 
 	platform_device_unregister(microcode_pdev);
 
-	if (microcode_ops->fini)
-		microcode_ops->fini();
-
 	microcode_ops = NULL;
 
 	pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 40b54ceb68b5..a2c1edd2d3ac 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -359,13 +359,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 		x86_init.mpparse.mpc_record(1);
 	}
 
-#ifdef CONFIG_X86_BIGSMP
-	generic_bigsmp_probe();
-#endif
-
-	if (apic->setup_apic_routing)
-		apic->setup_apic_routing();
-
 	if (!num_processors)
 		printk(KERN_ERR "MPTABLE: no processors registered!\n");
 	return num_processors;
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 4bd93c9b2b27..206735ac8cbd 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -285,7 +285,7 @@ static void __exit msr_exit(void)
 	for_each_online_cpu(cpu)
 		msr_device_destroy(cpu);
 	class_destroy(msr_class);
-	unregister_chrdev(MSR_MAJOR, "cpu/msr");
+	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
 	unregister_hotcpu_notifier(&msr_class_cpu_notifier);
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 02c3ee013ccd..c9b3522b6b46 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -115,18 +115,6 @@ void flush_thread(void)
 {
 	struct task_struct *tsk = current;
 
-#ifdef CONFIG_X86_64
-	if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) {
-		clear_tsk_thread_flag(tsk, TIF_ABI_PENDING);
-		if (test_tsk_thread_flag(tsk, TIF_IA32)) {
-			clear_tsk_thread_flag(tsk, TIF_IA32);
-		} else {
-			set_tsk_thread_flag(tsk, TIF_IA32);
-			current_thread_info()->status |= TS_COMPAT;
-		}
-	}
-#endif
-
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 	/*
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index f9e033150cdf..126f0b493d04 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -521,6 +521,18 @@ void set_personality_64bit(void)
 	current->personality &= ~READ_IMPLIES_EXEC;
 }
 
+void set_personality_ia32(void)
+{
+	/* inherit personality from parent */
+
+	/* Make sure to be in 32bit mode */
+	set_thread_flag(TIF_IA32);
+	current->personality |= force_personality32;
+
+	/* Prepare the first "return" to user space */
+	current_thread_info()->status |= TS_COMPAT;
+}
+
 unsigned long get_wchan(struct task_struct *p)
 {
 	unsigned long stack;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 73554a3aae8c..d03146f71b2f 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -678,7 +678,7 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
 	} else if (n == 6) {
 		val = thread->debugreg6;
 	 } else if (n == 7) {
-		val = ptrace_get_dr7(thread->ptrace_bps);
+		val = thread->ptrace_dr7;
 	}
 	return val;
 }
@@ -754,8 +754,11 @@ int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val)
 			return rc;
 	}
 	/* All that's left is DR7 */
-	if (n == 7)
+	if (n == 7) {
 		rc = ptrace_write_dr7(tsk, val);
+		if (!rc)
+			thread->ptrace_dr7 = val;
+	}
 
 ret_path:
 	return rc;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 18093d7498f0..12e9feaa2f7a 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -491,6 +491,19 @@ void force_hpet_resume(void)
 		break;
 	}
 }
+
+/*
+ * HPET MSI on some boards (ATI SB700/SB800) has side effect on
+ * floppy DMA. Disable HPET MSI on such platforms.
+ */
+static void force_disable_hpet_msi(struct pci_dev *unused)
+{
+	hpet_msi_disable = 1;
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
+			 force_disable_hpet_msi);
+
 #endif
 
 #if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 1545bc0c9845..704bddcdf64d 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -203,6 +203,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "0T656F"),
 		},
 	},
+	{	/* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G*/
+		.callback = set_bios_reboot,
+		.ident = "Dell OptiPlex 760",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"),
+			DMI_MATCH(DMI_BOARD_NAME, "0G919G"),
+		},
+	},
 	{	/* Handle problems with rebooting on Dell 2400's */
 		.callback = set_bios_reboot,
 		.ident = "Dell PowerEdge 2400",
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f7b8b9894b22..5d9e40c58628 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -642,19 +642,27 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
 			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
 		},
 	},
-	{
 	/*
-	 * AMI BIOS with low memory corruption was found on Intel DG45ID board.
-	 * It hase different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
+	 * AMI BIOS with low memory corruption was found on Intel DG45ID and
+	 * DG45FC boards.
+	 * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
 	 * match only DMI_BOARD_NAME and see if there is more bad products
 	 * with this vendor.
 	 */
+	{
 		.callback = dmi_low_memory_corruption,
 		.ident = "AMI BIOS",
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "DG45ID"),
 		},
 	},
+	{
+		.callback = dmi_low_memory_corruption,
+		.ident = "AMI BIOS",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
+		},
+	},
 #endif
 	{}
 };
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 678d0b8c26f3..b4e870cbdc60 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1083,9 +1083,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	set_cpu_sibling_map(0);
 
 	enable_IR_x2apic();
-#ifdef CONFIG_X86_64
 	default_setup_apic_routing();
-#endif
 
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 3c84aa001c11..2b75ef638dbc 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -282,10 +282,21 @@ static int uv_rtc_unset_timer(int cpu, int force)
 
 /*
  * Read the RTC.
+ *
+ * Starting with HUB rev 2.0, the UV RTC register is replicated across all
+ * cachelines of it's own page.  This allows faster simultaneous reads
+ * from a given socket.
  */
 static cycle_t uv_read_rtc(struct clocksource *cs)
 {
-	return (cycle_t)uv_read_local_mmr(UVH_RTC);
+	unsigned long offset;
+
+	if (uv_get_min_hub_revision_id() == 1)
+		offset = 0;
+	else
+		offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
+
+	return (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
 }
 
 /*
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 296aba49472a..15578f180e59 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -467,6 +467,9 @@ static int pit_ioport_read(struct kvm_io_device *this,
 		return -EOPNOTSUPP;
 
 	addr &= KVM_PIT_CHANNEL_MASK;
+	if (addr == 3)
+		return 0;
+
 	s = &pit_state->channels[addr];
 
 	mutex_lock(&pit_state->lock);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1ddcad452add..a1e1bc9d412d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -670,7 +670,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 {
 	static int version;
 	struct pvclock_wall_clock wc;
-	struct timespec now, sys, boot;
+	struct timespec boot;
 
 	if (!wall_clock)
 		return;
@@ -685,9 +685,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	 * wall clock specified here.  guest system time equals host
 	 * system time for us, thus we must fill in host boot time here.
 	 */
-	now = current_kernel_time();
-	ktime_get_ts(&sys);
-	boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys));
+	getboottime(&boot);
 
 	wc.sec = boot.tv_sec;
 	wc.nsec = boot.tv_nsec;
@@ -762,6 +760,7 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	local_irq_save(flags);
 	kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp);
 	ktime_get_ts(&ts);
+	monotonic_to_bootbased(&ts);
 	local_irq_restore(flags);
 
 	/* With all the info we got, fill in the values */
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 71da1bca13cb..738e6593799d 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -18,7 +18,7 @@ static inline pte_t gup_get_pte(pte_t *ptep)
 #else
 	/*
 	 * With get_user_pages_fast, we walk down the pagetables without taking
-	 * any locks.  For this we would like to load the pointers atoimcally,
+	 * any locks.  For this we would like to load the pointers atomically,
 	 * but that is not possible (without expensive cmpxchg8b) on PAE.  What
 	 * we do have is the guarantee that a pte will only either go from not
 	 * present to present, or present to not present or both -- it will not
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5198b9bb34ef..69ddfbd91135 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -49,6 +49,7 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 #include <asm/init.h>
+#include <linux/bootmem.h>
 
 static unsigned long dma_reserve __initdata;
 
@@ -616,6 +617,21 @@ void __init paging_init(void)
  */
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
+ * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need
+ * updating.
+ */
+static void  update_end_of_memory_vars(u64 start, u64 size)
+{
+	unsigned long end_pfn = PFN_UP(start + size);
+
+	if (end_pfn > max_pfn) {
+		max_pfn = end_pfn;
+		max_low_pfn = end_pfn;
+		high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
+	}
+}
+
+/*
  * Memory is added always to NORMAL zone. This means you will never get
  * additional DMA/DMA32 memory.
  */
@@ -634,6 +650,9 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	ret = __add_pages(nid, zone, start_pfn, nr_pages);
 	WARN_ON_ONCE(ret);
 
+	/* update max_pfn, max_low_pfn and high_memory */
+	update_end_of_memory_vars(start, size);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(arch_add_memory);
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index a27124185fc1..28c68762648f 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -229,9 +229,11 @@ update_nodes_add(int node, unsigned long start, unsigned long end)
 			printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n");
 	}
 
-	if (changed)
+	if (changed) {
+		node_set(node, cpu_nodes_parsed);
 		printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n",
 				 nd->start, nd->end);
+	}
 }
 
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index cb88b1a0bd5f..3347f696edc7 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -222,7 +222,7 @@ static void nmi_cpu_switch(void *dummy)
 
 	/* move to next set */
 	si += model->num_counters;
-	if ((si > model->num_virt_counters) || (counter_config[si].count == 0))
+	if ((si >= model->num_virt_counters) || (counter_config[si].count == 0))
 		per_cpu(switch_index, cpu) = 0;
 	else
 		per_cpu(switch_index, cpu) = si;
@@ -598,6 +598,7 @@ static int __init ppro_init(char **cpu_type)
 	case 15: case 23:
 		*cpu_type = "i386/core_2";
 		break;
+	case 0x2e:
 	case 26:
 		spec = &op_arch_perfmon_spec;
 		*cpu_type = "i386/core_i7";
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 564b008a51c7..39fba37f702f 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -15,7 +15,7 @@ obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
 
 obj-y				+= common.o early.o
 obj-y				+= amd_bus.o
-obj-$(CONFIG_X86_64)		+= bus_numa.o intel_bus.o
+obj-$(CONFIG_X86_64)		+= bus_numa.o
 
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/arch/x86/pci/intel_bus.c b/arch/x86/pci/intel_bus.c
deleted file mode 100644
index f81a2fa8fe25..000000000000
--- a/arch/x86/pci/intel_bus.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * to read io range from IOH pci conf, need to do it after mmconfig is there
- */
-
-#include <linux/delay.h>
-#include <linux/dmi.h>
-#include <linux/pci.h>
-#include <linux/init.h>
-#include <asm/pci_x86.h>
-
-#include "bus_numa.h"
-
-static inline void print_ioh_resources(struct pci_root_info *info)
-{
-	int res_num;
-	int busnum;
-	int i;
-
-	printk(KERN_DEBUG "IOH bus: [%02x, %02x]\n",
-			info->bus_min, info->bus_max);
-	res_num = info->res_num;
-	busnum = info->bus_min;
-	for (i = 0; i < res_num; i++) {
-		struct resource *res;
-
-		res = &info->res[i];
-		printk(KERN_DEBUG "IOH bus: %02x index %x %s: [%llx, %llx]\n",
-			busnum, i,
-			(res->flags & IORESOURCE_IO) ? "io port" :
-							"mmio",
-			res->start, res->end);
-	}
-}
-
-#define IOH_LIO			0x108
-#define IOH_LMMIOL		0x10c
-#define IOH_LMMIOH		0x110
-#define IOH_LMMIOH_BASEU	0x114
-#define IOH_LMMIOH_LIMITU	0x118
-#define IOH_LCFGBUS		0x11c
-
-static void __devinit pci_root_bus_res(struct pci_dev *dev)
-{
-	u16 word;
-	u32 dword;
-	struct pci_root_info *info;
-	u16 io_base, io_end;
-	u32 mmiol_base, mmiol_end;
-	u64 mmioh_base, mmioh_end;
-	int bus_base, bus_end;
-
-	/* some sys doesn't get mmconf enabled */
-	if (dev->cfg_size < 0x120)
-		return;
-
-	if (pci_root_num >= PCI_ROOT_NR) {
-		printk(KERN_DEBUG "intel_bus.c: PCI_ROOT_NR is too small\n");
-		return;
-	}
-
-	info = &pci_root_info[pci_root_num];
-	pci_root_num++;
-
-	pci_read_config_word(dev, IOH_LCFGBUS, &word);
-	bus_base = (word & 0xff);
-	bus_end = (word & 0xff00) >> 8;
-	sprintf(info->name, "PCI Bus #%02x", bus_base);
-	info->bus_min = bus_base;
-	info->bus_max = bus_end;
-
-	pci_read_config_word(dev, IOH_LIO, &word);
-	io_base = (word & 0xf0) << (12 - 4);
-	io_end = (word & 0xf000) | 0xfff;
-	update_res(info, io_base, io_end, IORESOURCE_IO, 0);
-
-	pci_read_config_dword(dev, IOH_LMMIOL, &dword);
-	mmiol_base = (dword & 0xff00) << (24 - 8);
-	mmiol_end = (dword & 0xff000000) | 0xffffff;
-	update_res(info, mmiol_base, mmiol_end, IORESOURCE_MEM, 0);
-
-	pci_read_config_dword(dev, IOH_LMMIOH, &dword);
-	mmioh_base = ((u64)(dword & 0xfc00)) << (26 - 10);
-	mmioh_end = ((u64)(dword & 0xfc000000) | 0x3ffffff);
-	pci_read_config_dword(dev, IOH_LMMIOH_BASEU, &dword);
-	mmioh_base |= ((u64)(dword & 0x7ffff)) << 32;
-	pci_read_config_dword(dev, IOH_LMMIOH_LIMITU, &dword);
-	mmioh_end |= ((u64)(dword & 0x7ffff)) << 32;
-	update_res(info, mmioh_base, mmioh_end, IORESOURCE_MEM, 0);
-
-	print_ioh_resources(info);
-}
-
-/* intel IOH */
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x342e, pci_root_bus_res);