Merge branch 'perf/urgent' into perf/core

Merge reason: queue up dependent patch, update to -rc4

Signed-off-by: Ingo Molnar <mingo@elte.hu>

59 files changed, 509 insertions, 565 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 55298e891571..cbcbfdee3ee0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -49,6 +49,7 @@ config X86
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
+	select HAVE_KERNEL_LZO
 	select HAVE_HW_BREAKPOINT
 	select PERF_EVENTS
 	select ANON_INODES
@@ -1246,6 +1247,11 @@ config ARCH_MEMORY_PROBE
 	def_bool X86_64
 	depends on MEMORY_HOTPLUG
 
+config ILLEGAL_POINTER_VALUE
+       hex
+       default 0 if X86_32
+       default 0xdead000000000000 if X86_64
+
 source "mm/Kconfig"
 
 config HIGHPTE
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 08e442bc3ab9..f20ddf84a893 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -396,7 +396,7 @@ config X86_TSC
 
 config X86_CMPXCHG64
 	def_bool y
-	depends on !M386 && !M486
+	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index f8ed0658404c..fbb47daf2459 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -4,11 +4,12 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
-targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma head_$(BITS).o misc.o piggy.o
+targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o piggy.o
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
 KBUILD_CFLAGS += $(cflags-y)
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
@@ -48,10 +49,13 @@ $(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,bzip2)
 $(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzma)
+$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,lzo)
 
 suffix-$(CONFIG_KERNEL_GZIP)	:= gz
 suffix-$(CONFIG_KERNEL_BZIP2)	:= bz2
 suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
+suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 
 quiet_cmd_mkpiggy = MKPIGGY $@
       cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 842b2a36174a..3b22fe8ab91b 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -162,6 +162,10 @@ static int lines, cols;
 #include "../../../../lib/decompress_unlzma.c"
 #endif
 
+#ifdef CONFIG_KERNEL_LZO
+#include "../../../../lib/decompress_unlzo.c"
+#endif
+
 static void scroll(void)
 {
 	int i;
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b31cc54b4641..93e689f4bd86 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -16,7 +16,7 @@
  */
 
 #include <asm/segment.h>
-#include <linux/utsrelease.h>
+#include <generated/utsrelease.h>
 #include <asm/boot.h>
 #include <asm/e820.h>
 #include <asm/page_types.h>
diff --git a/arch/x86/boot/version.c b/arch/x86/boot/version.c
index 2723d9b5ce43..2b15aa488ffb 100644
--- a/arch/x86/boot/version.c
+++ b/arch/x86/boot/version.c
@@ -13,8 +13,8 @@
  */
 
 #include "boot.h"
-#include <linux/utsrelease.h>
-#include <linux/compile.h>
+#include <generated/utsrelease.h>
+#include <generated/compile.h>
 
 const char kernel_version[] =
 	UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") "
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 60d2b2db0bc5..56f462cf22d2 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -142,6 +142,32 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 		return max_cstate;
 }
 
+static inline bool arch_has_acpi_pdc(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+	return (c->x86_vendor == X86_VENDOR_INTEL ||
+		c->x86_vendor == X86_VENDOR_CENTAUR);
+}
+
+static inline void arch_acpi_set_pdc_bits(u32 *buf)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	buf[2] |= ACPI_PDC_C_CAPABILITY_SMP;
+
+	if (cpu_has(c, X86_FEATURE_EST))
+		buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP;
+
+	if (cpu_has(c, X86_FEATURE_ACPI))
+		buf[2] |= ACPI_PDC_T_FFH;
+
+	/*
+	 * If mwait/monitor is unsupported, C2/C3_FFH will be disabled
+	 */
+	if (!cpu_has(c, X86_FEATURE_MWAIT))
+		buf[2] &= ~(ACPI_PDC_C_C2C3_FFH);
+}
+
 #else /* !CONFIG_ACPI */
 
 #define acpi_lapic 0
diff --git a/arch/x86/include/asm/asm-offsets.h b/arch/x86/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/x86/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 613700f27a4a..637e1ec963c3 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -153,6 +153,7 @@
 #define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
 #define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
+#define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 08c48a81841f..eeac829a0f44 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -103,7 +103,8 @@ extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
 extern void send_cleanup_vector(struct irq_cfg *);
 
 struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *);
+extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
+				      unsigned int *dest_id);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 950df434763f..f46b79f6c16c 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -254,6 +254,10 @@ struct kvm_reinject_control {
 	__u8 reserved[31];
 };
 
+/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
+#define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
+#define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
+
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
 	struct {
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4ffe09b2ad75..1cd58cdbc03f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -12,6 +12,7 @@
 #define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
 #define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
 #define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX		0xc0000103 /* Auxiliary TSC */
 
 /* EFER bits: */
 #define _EFER_SCE		0  /* SYSCALL/SYSRET */
@@ -123,6 +124,7 @@
 #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffff
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
+#define MSR_FAM10H_NODE_ID		0xc001100c
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 2d228fc9b4b7..c5bc4c2d33f5 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -27,6 +27,18 @@ struct msr {
 	};
 };
 
+struct msr_info {
+	u32 msr_no;
+	struct msr reg;
+	struct msr *msrs;
+	int err;
+};
+
+struct msr_regs_info {
+	u32 *regs;
+	int err;
+};
+
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
 	unsigned long low, high;
@@ -240,9 +252,9 @@ do {                                                            \
 #define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val),		\
 					     (u32)((val) >> 32))
 
-#define write_tsc(val1, val2) wrmsr(0x10, (val1), (val2))
+#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))
 
-#define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
+#define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0)
 
 struct msr *msrs_alloc(void);
 void msrs_free(struct msr *msrs);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6f8ec1c37e0a..fc801bab1b3b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -181,7 +181,7 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
 				unsigned int *ecx, unsigned int *edx)
 {
 	/* ecx is often an input as well as an output. */
-	asm("cpuid"
+	asm volatile("cpuid"
 	    : "=a" (*eax),
 	      "=b" (*ebx),
 	      "=c" (*ecx),
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 0c9825e97f36..088d09fb1615 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -205,14 +205,13 @@ static inline unsigned long __must_check copy_from_user(void *to,
 					  unsigned long n)
 {
 	int sz = __compiletime_object_size(to);
-	int ret = -EFAULT;
 
 	if (likely(sz == -1 || sz >= n))
-		ret = _copy_from_user(to, from, n);
+		n = _copy_from_user(to, from, n);
 	else
 		copy_from_user_overflow();
 
-	return ret;
+	return n;
 }
 
 long __must_check strncpy_from_user(char *dst, const char __user *src,
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 46324c6a4f6e..535e421498f6 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -30,16 +30,15 @@ static inline unsigned long __must_check copy_from_user(void *to,
 					  unsigned long n)
 {
 	int sz = __compiletime_object_size(to);
-	int ret = -EFAULT;
 
 	might_fault();
 	if (likely(sz == -1 || sz >= n))
-		ret = _copy_from_user(to, from, n);
+		n = _copy_from_user(to, from, n);
 #ifdef CONFIG_DEBUG_VM
 	else
 		WARN(1, "Buffer overflow detected!\n");
 #endif
-	return ret;
+	return n;
 }
 
 static __always_inline __must_check
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 811bfabc80b7..bc54fa965af3 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -31,20 +31,20 @@
  *		  contiguous (although various IO spaces may punch holes in
  *		  it)..
  *
- * 	N	- Number of bits in the node portion of a socket physical
- * 		  address.
+ *	N	- Number of bits in the node portion of a socket physical
+ *		  address.
  *
- * 	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
- * 	 	  routers always have low bit of 1, C/MBricks have low bit
- * 		  equal to 0. Most addressing macros that target UV hub chips
- * 		  right shift the NASID by 1 to exclude the always-zero bit.
- * 		  NASIDs contain up to 15 bits.
+ *	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
+ *		  routers always have low bit of 1, C/MBricks have low bit
+ *		  equal to 0. Most addressing macros that target UV hub chips
+ *		  right shift the NASID by 1 to exclude the always-zero bit.
+ *		  NASIDs contain up to 15 bits.
  *
  *	GNODE   - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
  *		  of nasids.
  *
- * 	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
- * 		  of the nasid for socket usage.
+ *	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
+ *		  of the nasid for socket usage.
  *
  *
  *  NumaLink Global Physical Address Format:
@@ -71,12 +71,12 @@
  *
  *
  * APICID format
- * 	NOTE!!!!!! This is the current format of the APICID. However, code
- * 	should assume that this will change in the future. Use functions
- * 	in this file for all APICID bit manipulations and conversion.
+ *	NOTE!!!!!! This is the current format of the APICID. However, code
+ *	should assume that this will change in the future. Use functions
+ *	in this file for all APICID bit manipulations and conversion.
  *
- * 		1111110000000000
- * 		5432109876543210
+ *		1111110000000000
+ *		5432109876543210
  *		pppppppppplc0cch
  *		sssssssssss
  *
@@ -89,9 +89,9 @@
  *	Note: Processor only supports 12 bits in the APICID register. The ACPI
  *	      tables hold all 16 bits. Software needs to be aware of this.
  *
- * 	      Unless otherwise specified, all references to APICID refer to
- * 	      the FULL value contained in ACPI tables, not the subset in the
- * 	      processor APICID register.
+ *	      Unless otherwise specified, all references to APICID refer to
+ *	      the FULL value contained in ACPI tables, not the subset in the
+ *	      processor APICID register.
  */
 
 
@@ -151,16 +151,16 @@ struct uv_hub_info_s {
 };
 
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info		(&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
  * Local & Global MMR space macros.
- * 	Note: macros are intended to be used ONLY by inline functions
- * 	in this file - not by other kernel code.
- * 		n -  NASID (full 15-bit global nasid)
- * 		g -  GNODE (full 15-bit global nasid, right shifted 1)
- * 		p -  PNODE (local part of nsids, right shifted 1)
+ *	Note: macros are intended to be used ONLY by inline functions
+ *	in this file - not by other kernel code.
+ *		n -  NASID (full 15-bit global nasid)
+ *		g -  GNODE (full 15-bit global nasid, right shifted 1)
+ *		p -  PNODE (local part of nsids, right shifted 1)
  */
 #define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
 #define UV_PNODE_TO_GNODE(p)		((p) |uv_hub_info->gnode_extra)
@@ -215,8 +215,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 /*
  * Macros for converting between kernel virtual addresses, socket local physical
  * addresses, and UV global physical addresses.
- * 	Note: use the standard __pa() & __va() macros for converting
- * 	      between socket virtual and socket physical addresses.
+ *	Note: use the standard __pa() & __va() macros for converting
+ *	      between socket virtual and socket physical addresses.
  */
 
 /* socket phys RAM --> UV global physical address */
@@ -287,21 +287,18 @@ static inline int uv_apicid_to_pnode(int apicid)
  * Access global MMRs using the low memory MMR32 space. This region supports
  * faster MMR access but not all MMRs are accessible in this space.
  */
-static inline unsigned long *uv_global_mmr32_address(int pnode,
-				unsigned long offset)
+static inline unsigned long *uv_global_mmr32_address(int pnode, unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR32_BASE |
 		       UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
-				 unsigned long val)
+static inline void uv_write_global_mmr32(int pnode, unsigned long offset, unsigned long val)
 {
 	writeq(val, uv_global_mmr32_address(pnode, offset));
 }
 
-static inline unsigned long uv_read_global_mmr32(int pnode,
-						 unsigned long offset)
+static inline unsigned long uv_read_global_mmr32(int pnode, unsigned long offset)
 {
 	return readq(uv_global_mmr32_address(pnode, offset));
 }
@@ -310,21 +307,18 @@ static inline unsigned long uv_read_global_mmr32(int pnode,
  * Access Global MMR space using the MMR space located at the top of physical
  * memory.
  */
-static inline unsigned long *uv_global_mmr64_address(int pnode,
-				unsigned long offset)
+static inline unsigned long *uv_global_mmr64_address(int pnode, unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR64_BASE |
 		    UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
-				unsigned long val)
+static inline void uv_write_global_mmr64(int pnode, unsigned long offset, unsigned long val)
 {
 	writeq(val, uv_global_mmr64_address(pnode, offset));
 }
 
-static inline unsigned long uv_read_global_mmr64(int pnode,
-						 unsigned long offset)
+static inline unsigned long uv_read_global_mmr64(int pnode, unsigned long offset)
 {
 	return readq(uv_global_mmr64_address(pnode, offset));
 }
@@ -338,6 +332,16 @@ static inline unsigned long uv_global_gru_mmr_address(int pnode, unsigned long o
 	return UV_GLOBAL_GRU_MMR_BASE | offset | (pnode << uv_hub_info->m_val);
 }
 
+static inline void uv_write_global_mmr8(int pnode, unsigned long offset, unsigned char val)
+{
+	writeb(val, uv_global_mmr64_address(pnode, offset));
+}
+
+static inline unsigned char uv_read_global_mmr8(int pnode, unsigned long offset)
+{
+	return readb(uv_global_mmr64_address(pnode, offset));
+}
+
 /*
  * Access hub local MMRs. Faster than using global space but only local MMRs
  * are accessible.
@@ -457,11 +461,17 @@ static inline void uv_set_scir_bits(unsigned char value)
 	}
 }
 
+static inline unsigned long uv_scir_offset(int apicid)
+{
+	return SCIR_LOCAL_MMR_BASE | (apicid & 0x3f);
+}
+
 static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 {
 	if (uv_cpu_hub_info(cpu)->scir.state != value) {
+		uv_write_global_mmr8(uv_cpu_to_pnode(cpu),
+				uv_cpu_hub_info(cpu)->scir.offset, value);
 		uv_cpu_hub_info(cpu)->scir.state = value;
-		uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
 	}
 }
 
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index fd5ca97a2ad5..6f35260bb3ef 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -4,7 +4,7 @@ obj-$(CONFIG_ACPI)		+= boot.o
 obj-$(CONFIG_ACPI_SLEEP)	+= sleep.o wakeup_rm.o wakeup_$(BITS).o
 
 ifneq ($(CONFIG_ACPI_PROCESSOR),)
-obj-y				+= cstate.o processor.o
+obj-y				+= cstate.o
 endif
 
 $(obj)/wakeup_rm.o:    $(obj)/realmode/wakeup.bin
diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c
deleted file mode 100644
index d85d1b2432ba..000000000000
--- a/arch/x86/kernel/acpi/processor.c
+++ /dev/null
@@ -1,101 +0,0 @@
-/*
- * Copyright (C) 2005 Intel Corporation
- * 	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
- * 	- Added _PDC for platforms with Intel CPUs
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/acpi.h>
-
-#include <acpi/processor.h>
-#include <asm/acpi.h>
-
-static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c)
-{
-	struct acpi_object_list *obj_list;
-	union acpi_object *obj;
-	u32 *buf;
-
-	/* allocate and initialize pdc. It will be used later. */
-	obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL);
-	if (!obj_list) {
-		printk(KERN_ERR "Memory allocation error\n");
-		return;
-	}
-
-	obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL);
-	if (!obj) {
-		printk(KERN_ERR "Memory allocation error\n");
-		kfree(obj_list);
-		return;
-	}
-
-	buf = kmalloc(12, GFP_KERNEL);
-	if (!buf) {
-		printk(KERN_ERR "Memory allocation error\n");
-		kfree(obj);
-		kfree(obj_list);
-		return;
-	}
-
-	buf[0] = ACPI_PDC_REVISION_ID;
-	buf[1] = 1;
-	buf[2] = ACPI_PDC_C_CAPABILITY_SMP;
-
-	/*
-	 * The default of PDC_SMP_T_SWCOORD bit is set for intel x86 cpu so
-	 * that OSPM is capable of native ACPI throttling software
-	 * coordination using BIOS supplied _TSD info.
-	 */
-	buf[2] |= ACPI_PDC_SMP_T_SWCOORD;
-	if (cpu_has(c, X86_FEATURE_EST))
-		buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP;
-
-	if (cpu_has(c, X86_FEATURE_ACPI))
-		buf[2] |= ACPI_PDC_T_FFH;
-
-	/*
-	 * If mwait/monitor is unsupported, C2/C3_FFH will be disabled
-	 */
-	if (!cpu_has(c, X86_FEATURE_MWAIT))
-		buf[2] &= ~(ACPI_PDC_C_C2C3_FFH);
-
-	obj->type = ACPI_TYPE_BUFFER;
-	obj->buffer.length = 12;
-	obj->buffer.pointer = (u8 *) buf;
-	obj_list->count = 1;
-	obj_list->pointer = obj;
-	pr->pdc = obj_list;
-
-	return;
-}
-
-
-/* Initialize _PDC data based on the CPU vendor */
-void arch_acpi_processor_init_pdc(struct acpi_processor *pr)
-{
-	struct cpuinfo_x86 *c = &cpu_data(pr->id);
-
-	pr->pdc = NULL;
-	if (c->x86_vendor == X86_VENDOR_INTEL ||
-	    c->x86_vendor == X86_VENDOR_CENTAUR)
-		init_intel_pdc(pr, c);
-
-	return;
-}
-
-EXPORT_SYMBOL(arch_acpi_processor_init_pdc);
-
-void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr)
-{
-	if (pr->pdc) {
-		kfree(pr->pdc->pointer->buffer.pointer);
-		kfree(pr->pdc->pointer);
-		kfree(pr->pdc);
-		pr->pdc = NULL;
-	}
-}
-
-EXPORT_SYMBOL(arch_acpi_processor_cleanup_pdc);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 82e508677b91..f9961034e557 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -162,6 +162,8 @@ static int __init acpi_sleep_setup(char *str)
 #endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
+		if (strncmp(str, "sci_force_enable", 16) == 0)
+			acpi_set_sci_en_on_resume();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 1dca9c34eaeb..fb490ce7dd55 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -138,6 +138,11 @@ int amd_iommus_present;
 bool amd_iommu_np_cache __read_mostly;
 
 /*
+ * Set to true if ACPI table parsing and hardware intialization went properly
+ */
+static bool amd_iommu_initialized;
+
+/*
  * List of protection domains - used during resume
  */
 LIST_HEAD(amd_iommu_pd_list);
@@ -929,6 +934,8 @@ static int __init init_iommu_all(struct acpi_table_header *table)
 	}
 	WARN_ON(p != end);
 
+	amd_iommu_initialized = true;
+
 	return 0;
 }
 
@@ -1263,6 +1270,9 @@ static int __init amd_iommu_init(void)
 	if (acpi_table_parse("IVRS", init_iommu_all) != 0)
 		goto free;
 
+	if (!amd_iommu_initialized)
+		goto free;
+
 	if (acpi_table_parse("IVRS", init_memory_definitions) != 0)
 		goto free;
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index aa57c079c98f..e80f291472a4 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -62,7 +62,7 @@ unsigned int boot_cpu_physical_apicid = -1U;
 /*
  * The highest APIC ID seen during enumeration.
  *
- * On AMD, this determines the messaging protocol we can use: if all APIC IDs
+ * This determines the messaging protocol we can use: if all APIC IDs
  * are in the 0 ... 7 range, then we can use logical addressing which
  * has some performance advantages (better broadcasting).
  *
@@ -1898,14 +1898,24 @@ void __cpuinit generic_processor_info(int apicid, int version)
 		max_physical_apicid = apicid;
 
 #ifdef CONFIG_X86_32
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_INTEL:
-		if (num_processors > 8)
-			def_to_bigsmp = 1;
-		break;
-	case X86_VENDOR_AMD:
-		if (max_physical_apicid >= 8)
+	/*
+	 * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y
+	 * but we need to work other dependencies like SMP_SUSPEND etc
+	 * before this can be done without some confusion.
+	 * if (CPU_HOTPLUG_ENABLED || num_processors > 8)
+	 *       - Ashok Raj <ashok.raj@intel.com>
+	 */
+	if (max_physical_apicid >= 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
 
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index d0c99abc26c3..eacbd2b31d27 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -306,10 +306,7 @@ physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
 		if (cpumask_test_cpu(cpu, cpu_online_mask))
 			break;
 	}
-	if (cpu < nr_cpu_ids)
-		return per_cpu(x86_cpu_to_apicid, cpu);
-
-	return BAD_APICID;
+	return per_cpu(x86_cpu_to_apicid, cpu);
 }
 
 struct apic apic_physflat =  {
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 38dcecfa5818..cb804c5091b9 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -131,10 +131,7 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
 		if (cpumask_test_cpu(cpu, cpu_online_mask))
 			break;
 	}
-	if (cpu < nr_cpu_ids)
-		return bigsmp_cpu_to_logical_apicid(cpu);
-
-	return BAD_APICID;
+	return bigsmp_cpu_to_logical_apicid(cpu);
 }
 
 static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 11a5851f1f50..53243ca7816d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2276,26 +2276,28 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
 
 /*
  * Either sets desc->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
  * leaves desc->affinity untouched.
  */
 unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask,
+		  unsigned int *dest_id)
 {
 	struct irq_cfg *cfg;
 	unsigned int irq;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
-		return BAD_APICID;
+		return -1;
 
 	irq = desc->irq;
 	cfg = desc->chip_data;
 	if (assign_irq_vector(irq, cfg, mask))
-		return BAD_APICID;
+		return -1;
 
 	cpumask_copy(desc->affinity, mask);
 
-	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+	*dest_id = apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+	return 0;
 }
 
 static int
@@ -2311,12 +2313,11 @@ set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 	cfg = desc->chip_data;
 
 	spin_lock_irqsave(&ioapic_lock, flags);
-	dest = set_desc_affinity(desc, mask);
-	if (dest != BAD_APICID) {
+	ret = set_desc_affinity(desc, mask, &dest);
+	if (!ret) {
 		/* Only the high 8 bits are valid. */
 		dest = SET_APIC_LOGICAL_ID(dest);
 		__target_IO_APIC_irq(irq, dest, cfg);
-		ret = 0;
 	}
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 
@@ -2433,6 +2434,13 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 		cfg = irq_cfg(irq);
 		raw_spin_lock(&desc->lock);
 
+		/*
+		 * Check if the irq migration is in progress. If so, we
+		 * haven't received the cleanup request yet for this irq.
+		 */
+		if (cfg->move_in_progress)
+			goto unlock;
+
 		if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
 			goto unlock;
 
@@ -3351,8 +3359,7 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	struct msi_msg msg;
 	unsigned int dest;
 
-	dest = set_desc_affinity(desc, mask);
-	if (dest == BAD_APICID)
+	if (set_desc_affinity(desc, mask, &dest))
 		return -1;
 
 	cfg = desc->chip_data;
@@ -3384,8 +3391,7 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	if (get_irte(irq, &irte))
 		return -1;
 
-	dest = set_desc_affinity(desc, mask);
-	if (dest == BAD_APICID)
+	if (set_desc_affinity(desc, mask, &dest))
 		return -1;
 
 	irte.vector = cfg->vector;
@@ -3567,8 +3573,7 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	struct msi_msg msg;
 	unsigned int dest;
 
-	dest = set_desc_affinity(desc, mask);
-	if (dest == BAD_APICID)
+	if (set_desc_affinity(desc, mask, &dest))
 		return -1;
 
 	cfg = desc->chip_data;
@@ -3623,8 +3628,7 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	struct msi_msg msg;
 	unsigned int dest;
 
-	dest = set_desc_affinity(desc, mask);
-	if (dest == BAD_APICID)
+	if (set_desc_affinity(desc, mask, &dest))
 		return -1;
 
 	cfg = desc->chip_data;
@@ -3730,8 +3734,7 @@ static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	struct irq_cfg *cfg;
 	unsigned int dest;
 
-	dest = set_desc_affinity(desc, mask);
-	if (dest == BAD_APICID)
+	if (set_desc_affinity(desc, mask, &dest))
 		return -1;
 
 	cfg = desc->chip_data;
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index c4cbd3080c1c..65edc180fc82 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -64,23 +64,16 @@ void __init default_setup_apic_routing(void)
 			apic = &apic_x2apic_phys;
 		else
 			apic = &apic_x2apic_cluster;
+		printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
 	}
 #endif
 
 	if (apic == &apic_flat) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_INTEL:
-			if (num_processors > 8)
-				apic = &apic_physflat;
-			break;
-		case X86_VENDOR_AMD:
-			if (max_physical_apicid >= 8)
-				apic = &apic_physflat;
-		}
+		if (max_physical_apicid >= 8)
+			apic = &apic_physflat;
+		printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
 	}
 
-	printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
-
 	if (is_vsmp_box()) {
 		/* need to update phys_pkg_id */
 		apic->phys_pkg_id = apicid_phys_pkg_id;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index a5371ec36776..cf69c59f4910 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -148,10 +148,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
 			break;
 	}
 
-	if (cpu < nr_cpu_ids)
-		return per_cpu(x86_cpu_to_logical_apicid, cpu);
-
-	return BAD_APICID;
+	return per_cpu(x86_cpu_to_logical_apicid, cpu);
 }
 
 static unsigned int x2apic_cluster_phys_get_apic_id(unsigned long x)
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index a8989aadc99a..8972f38c5ced 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -146,10 +146,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
 			break;
 	}
 
-	if (cpu < nr_cpu_ids)
-		return per_cpu(x86_cpu_to_apicid, cpu);
-
-	return BAD_APICID;
+	return per_cpu(x86_cpu_to_apicid, cpu);
 }
 
 static unsigned int x2apic_phys_get_apic_id(unsigned long x)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index b684bb303cbf..5f92494dab61 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -225,10 +225,7 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
 		if (cpumask_test_cpu(cpu, cpu_online_mask))
 			break;
 	}
-	if (cpu < nr_cpu_ids)
-		return per_cpu(x86_cpu_to_apicid, cpu);
-
-	return BAD_APICID;
+	return per_cpu(x86_cpu_to_apicid, cpu);
 }
 
 static unsigned int x2apic_get_apic_id(unsigned long x)
@@ -632,8 +629,10 @@ void __init uv_system_init(void)
 	uv_rtc_init();
 
 	for_each_present_cpu(cpu) {
+		int apicid = per_cpu(x86_cpu_to_apicid, cpu);
+
 		nid = cpu_to_node(cpu);
-		pnode = uv_apicid_to_pnode(per_cpu(x86_cpu_to_apicid, cpu));
+		pnode = uv_apicid_to_pnode(apicid);
 		blade = boot_pnode_to_blade(pnode);
 		lcpu = uv_blade_info[blade].nr_possible_cpus;
 		uv_blade_info[blade].nr_possible_cpus++;
@@ -654,15 +653,13 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
 		uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
-		uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
+		uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid);
 		uv_node_to_blade[nid] = blade;
 		uv_cpu_to_blade[cpu] = blade;
 		max_pnode = max(pnode, max_pnode);
 
-		printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, "
-			"lcpu %d, blade %d\n",
-			cpu, per_cpu(x86_cpu_to_apicid, cpu), pnode, nid,
-			lcpu, blade);
+		printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, lcpu %d, blade %d\n",
+			cpu, apicid, pnode, nid, lcpu, blade);
 	}
 
 	/* Add blade/pnode info for nodes without cpus */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 8dc3ea145c97..e485825130d2 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -254,59 +254,36 @@ static int __cpuinit nearby_node(int apicid)
 
 /*
  * Fixup core topology information for AMD multi-node processors.
- * Assumption 1: Number of cores in each internal node is the same.
- * Assumption 2: Mixed systems with both single-node and dual-node
- *               processors are not supported.
+ * Assumption: Number of cores in each internal node is the same.
  */
 #ifdef CONFIG_X86_HT
 static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_PCI
-	u32 t, cpn;
-	u8 n, n_id;
+	unsigned long long value;
+	u32 nodes, cores_per_node;
 	int cpu = smp_processor_id();
 
+	if (!cpu_has(c, X86_FEATURE_NODEID_MSR))
+		return;
+
 	/* fixup topology information only once for a core */
 	if (cpu_has(c, X86_FEATURE_AMD_DCM))
 		return;
 
-	/* check for multi-node processor on boot cpu */
-	t = read_pci_config(0, 24, 3, 0xe8);
-	if (!(t & (1 << 29)))
+	rdmsrl(MSR_FAM10H_NODE_ID, value);
+
+	nodes = ((value >> 3) & 7) + 1;
+	if (nodes == 1)
 		return;
 
 	set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+	cores_per_node = c->x86_max_cores / nodes;
 
-	/* cores per node: each internal node has half the number of cores */
-	cpn = c->x86_max_cores >> 1;
+	/* store NodeID, use llc_shared_map to store sibling info */
+	per_cpu(cpu_llc_id, cpu) = value & 7;
 
-	/* even-numbered NB_id of this dual-node processor */
-	n = c->phys_proc_id << 1;
-
-	/*
-	 * determine internal node id and assign cores fifty-fifty to
-	 * each node of the dual-node processor
-	 */
-	t = read_pci_config(0, 24 + n, 3, 0xe8);
-	n = (t>>30) & 0x3;
-	if (n == 0) {
-		if (c->cpu_core_id < cpn)
-			n_id = 0;
-		else
-			n_id = 1;
-	} else {
-		if (c->cpu_core_id < cpn)
-			n_id = 1;
-		else
-			n_id = 0;
-	}
-
-	/* compute entire NodeID, use llc_shared_map to store sibling info */
-	per_cpu(cpu_llc_id, cpu) = (c->phys_proc_id << 1) + n_id;
-
-	/* fixup core id to be in range from 0 to cpn */
-	c->cpu_core_id = c->cpu_core_id % cpn;
-#endif
+	/* fixup core id to be in range from 0 to (cores_per_node - 1) */
+	c->cpu_core_id = c->cpu_core_id % cores_per_node;
 }
 #endif
 
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index f28decf8dde3..1b1920fa7c80 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -190,9 +190,11 @@ static void do_drv_write(void *_cmd)
 
 static void drv_read(struct drv_cmd *cmd)
 {
+	int err;
 	cmd->val = 0;
 
-	smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1);
+	err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1);
+	WARN_ON_ONCE(err);	/* smp_call_function_any() was buggy? */
 }
 
 static void drv_write(struct drv_cmd *cmd)
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index a9df9441a9a2..f125e5c551c0 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1136,7 +1136,7 @@ static int powernowk8_target(struct cpufreq_policy *pol,
 	if (!alloc_cpumask_var(&oldmask, GFP_KERNEL))
 		return -ENOMEM;
 
-	cpumask_copy(oldmask, tsk_cpumask(current));
+	cpumask_copy(oldmask, tsk_cpus_allowed(current));
 	set_cpus_allowed_ptr(current, cpumask_of(pol->cpu));
 
 	if (smp_processor_id() != pol->cpu) {
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 9c31e8b09d2c..879666f4d871 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -70,7 +70,6 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
 		sched_clock_stable = 1;
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c223b7e895d9..d616c06e99b4 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2347,7 +2347,7 @@ perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 	callchain_store(entry, PERF_CONTEXT_KERNEL);
 	callchain_store(entry, regs->ip);
 
-	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
+	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
 }
 
 /*
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 7ef24a796992..cb27fd6136c9 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -187,7 +187,8 @@ static int __init cpuid_init(void)
 	int i, err = 0;
 	i = 0;
 
-	if (register_chrdev(CPUID_MAJOR, "cpu/cpuid", &cpuid_fops)) {
+	if (__register_chrdev(CPUID_MAJOR, 0, NR_CPUS,
+			      "cpu/cpuid", &cpuid_fops)) {
 		printk(KERN_ERR "cpuid: unable to get major %d for cpuid\n",
 		       CPUID_MAJOR);
 		err = -EBUSY;
@@ -216,7 +217,7 @@ out_class:
 	}
 	class_destroy(cpuid_class);
 out_chrdev:
-	unregister_chrdev(CPUID_MAJOR, "cpu/cpuid");
+	__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
 out:
 	return err;
 }
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index c56bc2873030..6d817554780a 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -123,13 +123,15 @@ print_context_stack_bp(struct thread_info *tinfo,
 	while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
 		unsigned long addr = *ret_addr;
 
-		if (__kernel_text_address(addr)) {
-			ops->address(data, addr, 1);
-			frame = frame->next_frame;
-			ret_addr = &frame->return_address;
-			print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
-		}
+		if (!__kernel_text_address(addr))
+			break;
+
+		ops->address(data, addr, 1);
+		frame = frame->next_frame;
+		ret_addr = &frame->return_address;
+		print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
 	}
+
 	return (unsigned long)frame;
 }
 EXPORT_SYMBOL_GPL(print_context_stack_bp);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index f50447d961c0..a1a7876cadcb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -724,7 +724,7 @@ core_initcall(e820_mark_nvs_memory);
 /*
  * Early reserved memory areas.
  */
-#define MAX_EARLY_RES 20
+#define MAX_EARLY_RES 32
 
 struct early_res {
 	u64 start, end;
@@ -733,13 +733,13 @@ struct early_res {
 };
 static struct early_res early_res[MAX_EARLY_RES] __initdata = {
 	{ 0, PAGE_SIZE, "BIOS data page", 1 },	/* BIOS data page */
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE)
 	/*
 	 * But first pinch a few for the stack/trampoline stuff
 	 * FIXME: Don't need the extra page at 4K, but need to fix
 	 * trampoline before removing it. (see the GDT stuff)
 	 */
-	{ PAGE_SIZE, PAGE_SIZE, "EX TRAMPOLINE", 1 },
+	{ PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 },
 #endif
 
 	{}
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 844c02c65fcb..0c8632433090 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -394,7 +394,7 @@ static enum ucode_state microcode_update_cpu(int cpu)
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	enum ucode_state ustate;
 
-	if (uci->valid && uci->mc)
+	if (uci->valid)
 		ustate = microcode_resume_cpu(cpu);
 	else
 		ustate = microcode_init_cpu(cpu);
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 572b07eee3f4..4bd93c9b2b27 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -246,7 +246,7 @@ static int __init msr_init(void)
 	int i, err = 0;
 	i = 0;
 
-	if (register_chrdev(MSR_MAJOR, "cpu/msr", &msr_fops)) {
+	if (__register_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr", &msr_fops)) {
 		printk(KERN_ERR "msr: unable to get major %d for msr\n",
 		       MSR_MAJOR);
 		err = -EBUSY;
@@ -274,7 +274,7 @@ out_class:
 		msr_device_destroy(i);
 	class_destroy(msr_class);
 out_chrdev:
-	unregister_chrdev(MSR_MAJOR, "cpu/msr");
+	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
 out:
 	return err;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 98c2cdeb599e..c6ee241c8a98 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -103,8 +103,8 @@ void show_regs_common(void)
 	if (!product)
 		product = "";
 
-	printk("\n");
-	printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n",
+	printk(KERN_CONT "\n");
+	printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n",
 		current->pid, current->comm, print_tainted(),
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 9c517b5858f0..37ad1e046aae 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -139,16 +139,16 @@ void __show_regs(struct pt_regs *regs, int all)
 
 	show_regs_common();
 
-	printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
+	printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
 			(u16)regs->cs, regs->ip, regs->flags,
 			smp_processor_id());
 	print_symbol("EIP is at %s\n", regs->ip);
 
-	printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
+	printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
 		regs->ax, regs->bx, regs->cx, regs->dx);
-	printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
+	printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
 		regs->si, regs->di, regs->bp, sp);
-	printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
+	printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
 	       (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss);
 
 	if (!all)
@@ -158,19 +158,19 @@ void __show_regs(struct pt_regs *regs, int all)
 	cr2 = read_cr2();
 	cr3 = read_cr3();
 	cr4 = read_cr4_safe();
-	printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
+	printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
 			cr0, cr2, cr3, cr4);
 
 	get_debugreg(d0, 0);
 	get_debugreg(d1, 1);
 	get_debugreg(d2, 2);
 	get_debugreg(d3, 3);
-	printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
+	printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
 			d0, d1, d2, d3);
 
 	get_debugreg(d6, 6);
 	get_debugreg(d7, 7);
-	printk("DR6: %08lx DR7: %08lx\n",
+	printk(KERN_DEFAULT "DR6: %08lx DR7: %08lx\n",
 			d6, d7);
 }
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 52fbd0c60198..f9e033150cdf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -161,19 +161,19 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned int ds, cs, es;
 
 	show_regs_common();
-	printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
+	printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
 	printk_address(regs->ip, 1);
-	printk(KERN_INFO "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
+	printk(KERN_DEFAULT "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
 			regs->sp, regs->flags);
-	printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
+	printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n",
 	       regs->ax, regs->bx, regs->cx);
-	printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n",
+	printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n",
 	       regs->dx, regs->si, regs->di);
-	printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n",
+	printk(KERN_DEFAULT "RBP: %016lx R08: %016lx R09: %016lx\n",
 	       regs->bp, regs->r8, regs->r9);
-	printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n",
+	printk(KERN_DEFAULT "R10: %016lx R11: %016lx R12: %016lx\n",
 	       regs->r10, regs->r11, regs->r12);
-	printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n",
+	printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
 	       regs->r13, regs->r14, regs->r15);
 
 	asm("movl %%ds,%0" : "=r" (ds));
@@ -194,21 +194,21 @@ void __show_regs(struct pt_regs *regs, int all)
 	cr3 = read_cr3();
 	cr4 = read_cr4();
 
-	printk(KERN_INFO "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
+	printk(KERN_DEFAULT "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
 	       fs, fsindex, gs, gsindex, shadowgs);
-	printk(KERN_INFO "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
+	printk(KERN_DEFAULT "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
 			es, cr0);
-	printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
+	printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
 			cr4);
 
 	get_debugreg(d0, 0);
 	get_debugreg(d1, 1);
 	get_debugreg(d2, 2);
-	printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
+	printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
 	get_debugreg(d3, 3);
 	get_debugreg(d6, 6);
 	get_debugreg(d7, 7);
-	printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
+	printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
 }
 
 void show_regs(struct pt_regs *regs)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 2779321046bd..017d937639fe 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -509,14 +509,14 @@ static int genregs_get(struct task_struct *target,
 {
 	if (kbuf) {
 		unsigned long *k = kbuf;
-		while (count > 0) {
+		while (count >= sizeof(*k)) {
 			*k++ = getreg(target, pos);
 			count -= sizeof(*k);
 			pos += sizeof(*k);
 		}
 	} else {
 		unsigned long __user *u = ubuf;
-		while (count > 0) {
+		while (count >= sizeof(*u)) {
 			if (__put_user(getreg(target, pos), u++))
 				return -EFAULT;
 			count -= sizeof(*u);
@@ -535,14 +535,14 @@ static int genregs_set(struct task_struct *target,
 	int ret = 0;
 	if (kbuf) {
 		const unsigned long *k = kbuf;
-		while (count > 0 && !ret) {
+		while (count >= sizeof(*k) && !ret) {
 			ret = putreg(target, pos, *k++);
 			count -= sizeof(*k);
 			pos += sizeof(*k);
 		}
 	} else {
 		const unsigned long  __user *u = ubuf;
-		while (count > 0 && !ret) {
+		while (count >= sizeof(*u) && !ret) {
 			unsigned long word;
 			ret = __get_user(word, u++);
 			if (ret)
@@ -1458,14 +1458,14 @@ static int genregs32_get(struct task_struct *target,
 {
 	if (kbuf) {
 		compat_ulong_t *k = kbuf;
-		while (count > 0) {
+		while (count >= sizeof(*k)) {
 			getreg32(target, pos, k++);
 			count -= sizeof(*k);
 			pos += sizeof(*k);
 		}
 	} else {
 		compat_ulong_t __user *u = ubuf;
-		while (count > 0) {
+		while (count >= sizeof(*u)) {
 			compat_ulong_t word;
 			getreg32(target, pos, &word);
 			if (__put_user(word, u++))
@@ -1486,14 +1486,14 @@ static int genregs32_set(struct task_struct *target,
 	int ret = 0;
 	if (kbuf) {
 		const compat_ulong_t *k = kbuf;
-		while (count > 0 && !ret) {
+		while (count >= sizeof(*k) && !ret) {
 			ret = putreg32(target, pos, *k++);
 			count -= sizeof(*k);
 			pos += sizeof(*k);
 		}
 	} else {
 		const compat_ulong_t __user *u = ubuf;
-		while (count > 0 && !ret) {
+		while (count >= sizeof(*u) && !ret) {
 			compat_ulong_t word;
 			ret = __get_user(word, u++);
 			if (ret)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cd982f48e23e..597683aa5ba0 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -763,6 +763,7 @@ void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
+		sched_clock_stable = 0;
 		printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
 		/* Change only the rating, when not registered */
 		if (clocksource_tsc.mult)
diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c
index 61d805df4c91..ece73d8e3240 100644
--- a/arch/x86/kernel/uv_irq.c
+++ b/arch/x86/kernel/uv_irq.c
@@ -215,8 +215,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	unsigned long mmr_offset;
 	unsigned mmr_pnode;
 
-	dest = set_desc_affinity(desc, mask);
-	if (dest == BAD_APICID)
+	if (set_desc_affinity(desc, mask, &dest))
 		return -1;
 
 	mmr_value = 0;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index cd60c0bd1b32..3063a0c4858b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1150,6 +1150,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
 	hrtimer_cancel(&apic->lapic_timer.timer);
 	update_divide_count(apic);
 	start_apic_timer(apic);
+	apic->irr_pending = true;
 }
 
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index a6017132fba8..58a0f1e88596 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -455,8 +455,6 @@ out_unlock:
 static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	pt_element_t gpte;
-	gpa_t pte_gpa = -1;
 	int level;
 	u64 *sptep;
 	int need_flush = 0;
@@ -470,10 +468,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 		if (level == PT_PAGE_TABLE_LEVEL  ||
 		    ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
 		    ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {
-			struct kvm_mmu_page *sp = page_header(__pa(sptep));
-
-			pte_gpa = (sp->gfn << PAGE_SHIFT);
-			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
 
 			if (is_shadow_present_pte(*sptep)) {
 				rmap_remove(vcpu->kvm, sptep);
@@ -492,18 +486,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 	if (need_flush)
 		kvm_flush_remote_tlbs(vcpu->kvm);
 	spin_unlock(&vcpu->kvm->mmu_lock);
-
-	if (pte_gpa == -1)
-		return;
-	if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
-				  sizeof(pt_element_t)))
-		return;
-	if (is_present_gpte(gpte) && (gpte & PT_ACCESSED_MASK)) {
-		if (mmu_topup_memory_caches(vcpu))
-			return;
-		kvm_mmu_pte_write(vcpu, pte_gpa, (const u8 *)&gpte,
-				  sizeof(pt_element_t), 0);
-	}
 }
 
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9d068966fb2a..6651dbf58675 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1913,7 +1913,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 
 	events->sipi_vector = vcpu->arch.sipi_vector;
 
-	events->flags = 0;
+	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
+			 | KVM_VCPUEVENT_VALID_SIPI_VECTOR);
 
 	vcpu_put(vcpu);
 }
@@ -1921,7 +1922,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
 {
-	if (events->flags)
+	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
+			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR))
 		return -EINVAL;
 
 	vcpu_load(vcpu);
@@ -1938,10 +1940,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		kvm_pic_clear_isr_ack(vcpu->kvm);
 
 	vcpu->arch.nmi_injected = events->nmi.injected;
-	vcpu->arch.nmi_pending = events->nmi.pending;
+	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
+		vcpu->arch.nmi_pending = events->nmi.pending;
 	kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
 
-	vcpu->arch.sipi_vector = events->sipi_vector;
+	if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR)
+		vcpu->arch.sipi_vector = events->sipi_vector;
 
 	vcpu_put(vcpu);
 
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 45b20e486c2f..cffd754f3039 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -14,7 +14,7 @@ $(obj)/inat.o: $(obj)/inat-tables.c
 
 clean-files := inat-tables.c
 
-obj-$(CONFIG_SMP) := msr.o
+obj-$(CONFIG_SMP) += msr-smp.o
 
 lib-y := delay.o
 lib-y += thunk_$(BITS).o
@@ -22,7 +22,7 @@ lib-y += usercopy_$(BITS).o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_KPROBES) += insn.o inat.o
 
-obj-y += msr-reg.o msr-reg-export.o
+obj-y += msr.o msr-reg.o msr-reg-export.o
 
 ifeq ($(CONFIG_X86_32),y)
         obj-y += atomic64_32.o
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
new file mode 100644
index 000000000000..a6b1b86d2253
--- /dev/null
+++ b/arch/x86/lib/msr-smp.c
@@ -0,0 +1,204 @@
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/smp.h>
+#include <asm/msr.h>
+
+static void __rdmsr_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+	struct msr *reg;
+	int this_cpu = raw_smp_processor_id();
+
+	if (rv->msrs)
+		reg = per_cpu_ptr(rv->msrs, this_cpu);
+	else
+		reg = &rv->reg;
+
+	rdmsr(rv->msr_no, reg->l, reg->h);
+}
+
+static void __wrmsr_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+	struct msr *reg;
+	int this_cpu = raw_smp_processor_id();
+
+	if (rv->msrs)
+		reg = per_cpu_ptr(rv->msrs, this_cpu);
+	else
+		reg = &rv->reg;
+
+	wrmsr(rv->msr_no, reg->l, reg->h);
+}
+
+int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+	int err;
+	struct msr_info rv;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msr_no = msr_no;
+	err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
+	*l = rv.reg.l;
+	*h = rv.reg.h;
+
+	return err;
+}
+EXPORT_SYMBOL(rdmsr_on_cpu);
+
+int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	int err;
+	struct msr_info rv;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msr_no = msr_no;
+	rv.reg.l = l;
+	rv.reg.h = h;
+	err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
+
+	return err;
+}
+EXPORT_SYMBOL(wrmsr_on_cpu);
+
+static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
+			    struct msr *msrs,
+			    void (*msr_func) (void *info))
+{
+	struct msr_info rv;
+	int this_cpu;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msrs	  = msrs;
+	rv.msr_no = msr_no;
+
+	this_cpu = get_cpu();
+
+	if (cpumask_test_cpu(this_cpu, mask))
+		msr_func(&rv);
+
+	smp_call_function_many(mask, msr_func, &rv, 1);
+	put_cpu();
+}
+
+/* rdmsr on a bunch of CPUs
+ *
+ * @mask:       which CPUs
+ * @msr_no:     which MSR
+ * @msrs:       array of MSR values
+ *
+ */
+void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+{
+	__rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu);
+}
+EXPORT_SYMBOL(rdmsr_on_cpus);
+
+/*
+ * wrmsr on a bunch of CPUs
+ *
+ * @mask:       which CPUs
+ * @msr_no:     which MSR
+ * @msrs:       array of MSR values
+ *
+ */
+void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+{
+	__rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu);
+}
+EXPORT_SYMBOL(wrmsr_on_cpus);
+
+/* These "safe" variants are slower and should be used when the target MSR
+   may not actually exist. */
+static void __rdmsr_safe_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+
+	rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h);
+}
+
+static void __wrmsr_safe_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+
+	rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h);
+}
+
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+	int err;
+	struct msr_info rv;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msr_no = msr_no;
+	err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
+	*l = rv.reg.l;
+	*h = rv.reg.h;
+
+	return err ? err : rv.err;
+}
+EXPORT_SYMBOL(rdmsr_safe_on_cpu);
+
+int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	int err;
+	struct msr_info rv;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msr_no = msr_no;
+	rv.reg.l = l;
+	rv.reg.h = h;
+	err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
+
+	return err ? err : rv.err;
+}
+EXPORT_SYMBOL(wrmsr_safe_on_cpu);
+
+/*
+ * These variants are significantly slower, but allows control over
+ * the entire 32-bit GPR set.
+ */
+static void __rdmsr_safe_regs_on_cpu(void *info)
+{
+	struct msr_regs_info *rv = info;
+
+	rv->err = rdmsr_safe_regs(rv->regs);
+}
+
+static void __wrmsr_safe_regs_on_cpu(void *info)
+{
+	struct msr_regs_info *rv = info;
+
+	rv->err = wrmsr_safe_regs(rv->regs);
+}
+
+int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
+{
+	int err;
+	struct msr_regs_info rv;
+
+	rv.regs   = regs;
+	rv.err    = -EIO;
+	err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1);
+
+	return err ? err : rv.err;
+}
+EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu);
+
+int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
+{
+	int err;
+	struct msr_regs_info rv;
+
+	rv.regs = regs;
+	rv.err  = -EIO;
+	err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1);
+
+	return err ? err : rv.err;
+}
+EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu);
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 872834177937..8f8eebdca7d4 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -1,123 +1,7 @@
 #include <linux/module.h>
 #include <linux/preempt.h>
-#include <linux/smp.h>
 #include <asm/msr.h>
 
-struct msr_info {
-	u32 msr_no;
-	struct msr reg;
-	struct msr *msrs;
-	int err;
-};
-
-static void __rdmsr_on_cpu(void *info)
-{
-	struct msr_info *rv = info;
-	struct msr *reg;
-	int this_cpu = raw_smp_processor_id();
-
-	if (rv->msrs)
-		reg = per_cpu_ptr(rv->msrs, this_cpu);
-	else
-		reg = &rv->reg;
-
-	rdmsr(rv->msr_no, reg->l, reg->h);
-}
-
-static void __wrmsr_on_cpu(void *info)
-{
-	struct msr_info *rv = info;
-	struct msr *reg;
-	int this_cpu = raw_smp_processor_id();
-
-	if (rv->msrs)
-		reg = per_cpu_ptr(rv->msrs, this_cpu);
-	else
-		reg = &rv->reg;
-
-	wrmsr(rv->msr_no, reg->l, reg->h);
-}
-
-int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-	int err;
-	struct msr_info rv;
-
-	memset(&rv, 0, sizeof(rv));
-
-	rv.msr_no = msr_no;
-	err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
-	*l = rv.reg.l;
-	*h = rv.reg.h;
-
-	return err;
-}
-EXPORT_SYMBOL(rdmsr_on_cpu);
-
-int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-	int err;
-	struct msr_info rv;
-
-	memset(&rv, 0, sizeof(rv));
-
-	rv.msr_no = msr_no;
-	rv.reg.l = l;
-	rv.reg.h = h;
-	err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
-
-	return err;
-}
-EXPORT_SYMBOL(wrmsr_on_cpu);
-
-static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
-			    struct msr *msrs,
-			    void (*msr_func) (void *info))
-{
-	struct msr_info rv;
-	int this_cpu;
-
-	memset(&rv, 0, sizeof(rv));
-
-	rv.msrs	  = msrs;
-	rv.msr_no = msr_no;
-
-	this_cpu = get_cpu();
-
-	if (cpumask_test_cpu(this_cpu, mask))
-		msr_func(&rv);
-
-	smp_call_function_many(mask, msr_func, &rv, 1);
-	put_cpu();
-}
-
-/* rdmsr on a bunch of CPUs
- *
- * @mask:       which CPUs
- * @msr_no:     which MSR
- * @msrs:       array of MSR values
- *
- */
-void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
-{
-	__rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu);
-}
-EXPORT_SYMBOL(rdmsr_on_cpus);
-
-/*
- * wrmsr on a bunch of CPUs
- *
- * @mask:       which CPUs
- * @msr_no:     which MSR
- * @msrs:       array of MSR values
- *
- */
-void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
-{
-	__rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu);
-}
-EXPORT_SYMBOL(wrmsr_on_cpus);
-
 struct msr *msrs_alloc(void)
 {
 	struct msr *msrs = NULL;
@@ -137,100 +21,3 @@ void msrs_free(struct msr *msrs)
 	free_percpu(msrs);
 }
 EXPORT_SYMBOL(msrs_free);
-
-/* These "safe" variants are slower and should be used when the target MSR
-   may not actually exist. */
-static void __rdmsr_safe_on_cpu(void *info)
-{
-	struct msr_info *rv = info;
-
-	rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h);
-}
-
-static void __wrmsr_safe_on_cpu(void *info)
-{
-	struct msr_info *rv = info;
-
-	rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h);
-}
-
-int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-	int err;
-	struct msr_info rv;
-
-	memset(&rv, 0, sizeof(rv));
-
-	rv.msr_no = msr_no;
-	err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
-	*l = rv.reg.l;
-	*h = rv.reg.h;
-
-	return err ? err : rv.err;
-}
-EXPORT_SYMBOL(rdmsr_safe_on_cpu);
-
-int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-	int err;
-	struct msr_info rv;
-
-	memset(&rv, 0, sizeof(rv));
-
-	rv.msr_no = msr_no;
-	rv.reg.l = l;
-	rv.reg.h = h;
-	err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
-
-	return err ? err : rv.err;
-}
-EXPORT_SYMBOL(wrmsr_safe_on_cpu);
-
-/*
- * These variants are significantly slower, but allows control over
- * the entire 32-bit GPR set.
- */
-struct msr_regs_info {
-	u32 *regs;
-	int err;
-};
-
-static void __rdmsr_safe_regs_on_cpu(void *info)
-{
-	struct msr_regs_info *rv = info;
-
-	rv->err = rdmsr_safe_regs(rv->regs);
-}
-
-static void __wrmsr_safe_regs_on_cpu(void *info)
-{
-	struct msr_regs_info *rv = info;
-
-	rv->err = wrmsr_safe_regs(rv->regs);
-}
-
-int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
-{
-	int err;
-	struct msr_regs_info rv;
-
-	rv.regs   = regs;
-	rv.err    = -EIO;
-	err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1);
-
-	return err ? err : rv.err;
-}
-EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu);
-
-int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
-{
-	int err;
-	struct msr_regs_info rv;
-
-	rv.regs = regs;
-	rv.err  = -EIO;
-	err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1);
-
-	return err ? err : rv.err;
-}
-EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c973f8e2a6cf..9a0c258a86be 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -892,8 +892,7 @@ void __init mem_init(void)
 		reservedpages << (PAGE_SHIFT-10),
 		datasize >> 10,
 		initsize >> 10,
-		(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
-	       );
+		totalhigh_pages << (PAGE_SHIFT-10));
 
 	printk(KERN_INFO "virtual kernel memory layout:\n"
 		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index 4901d0dafda6..af3b6c8a436f 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -106,26 +106,25 @@ void kmemcheck_error_recall(void)
 
 	switch (e->type) {
 	case KMEMCHECK_ERROR_INVALID_ACCESS:
-		printk(KERN_ERR  "WARNING: kmemcheck: Caught %d-bit read "
-			"from %s memory (%p)\n",
+		printk(KERN_WARNING "WARNING: kmemcheck: Caught %d-bit read from %s memory (%p)\n",
 			8 * e->size, e->state < ARRAY_SIZE(desc) ?
 				desc[e->state] : "(invalid shadow state)",
 			(void *) e->address);
 
-		printk(KERN_INFO);
+		printk(KERN_WARNING);
 		for (i = 0; i < SHADOW_COPY_SIZE; ++i)
-			printk("%02x", e->memory_copy[i]);
-		printk("\n");
+			printk(KERN_CONT "%02x", e->memory_copy[i]);
+		printk(KERN_CONT "\n");
 
-		printk(KERN_INFO);
+		printk(KERN_WARNING);
 		for (i = 0; i < SHADOW_COPY_SIZE; ++i) {
 			if (e->shadow_copy[i] < ARRAY_SIZE(short_desc))
-				printk(" %c", short_desc[e->shadow_copy[i]]);
+				printk(KERN_CONT " %c", short_desc[e->shadow_copy[i]]);
 			else
-				printk(" ?");
+				printk(KERN_CONT " ?");
 		}
-		printk("\n");
-		printk(KERN_INFO "%*c\n", 2 + 2
+		printk(KERN_CONT "\n");
+		printk(KERN_WARNING "%*c\n", 2 + 2
 			* (int) (e->address & (SHADOW_COPY_SIZE - 1)), '^');
 		break;
 	case KMEMCHECK_ERROR_BUG:
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 6f8aa33031c7..9324f13492d5 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -267,6 +267,8 @@ int __init get_memcfg_from_srat(void)
 		e820_register_active_regions(chunk->nid, chunk->start_pfn,
 					     min(chunk->end_pfn, max_pfn));
 	}
+	/* for out of order entries in SRAT */
+	sort_node_map();
 
 	for_each_online_node(nid) {
 		unsigned long start = node_start_pfn[nid];
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index d89075489664..a27124185fc1 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -317,7 +317,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 		unsigned long s = nodes[i].start >> PAGE_SHIFT;
 		unsigned long e = nodes[i].end >> PAGE_SHIFT;
 		pxmram += e - s;
-		pxmram -= absent_pages_in_range(s, e);
+		pxmram -= __absent_pages_in_range(i, s, e);
 		if ((long)pxmram < 0)
 			pxmram = 0;
 	}
@@ -373,6 +373,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 	for_each_node_mask(i, nodes_parsed)
 		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
+	/* for out of order entries in SRAT */
+	sort_node_map();
 	if (!nodes_cover_memory(nodes)) {
 		bad_srat();
 		return -1;
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index 145df00e0387..f939d603adfa 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -51,7 +51,7 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 	}
 }
 
-void __init update_res(struct pci_root_info *info, size_t start,
+void __devinit update_res(struct pci_root_info *info, size_t start,
 			      size_t end, unsigned long flags, int merge)
 {
 	int i;
diff --git a/arch/x86/pci/intel_bus.c b/arch/x86/pci/intel_bus.c
index b7a55dc55d13..f81a2fa8fe25 100644
--- a/arch/x86/pci/intel_bus.c
+++ b/arch/x86/pci/intel_bus.c
@@ -49,6 +49,10 @@ static void __devinit pci_root_bus_res(struct pci_dev *dev)
 	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;
diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk
index 0d13cd9fdcff..fd1ab80be0de 100644
--- a/arch/x86/tools/chkobjdump.awk
+++ b/arch/x86/tools/chkobjdump.awk
@@ -8,14 +8,24 @@ BEGIN {
 	od_sver = 19;
 }
 
-/^GNU/ {
-	split($4, ver, ".");
+/^GNU objdump/ {
+	verstr = ""
+	for (i = 3; i <= NF; i++)
+		if (match($(i), "^[0-9]")) {
+			verstr = $(i);
+			break;
+		}
+	if (verstr == "") {
+		printf("Warning: Failed to find objdump version number.\n");
+		exit 0;
+	}
+	split(verstr, ver, ".");
 	if (ver[1] > od_ver ||
 	    (ver[1] == od_ver && ver[2] >= od_sver)) {
 		exit 1;
 	} else {
 		printf("Warning: objdump version %s is older than %d.%d\n",
-		       $4, od_ver, od_sver);
+		       verstr, od_ver, od_sver);
 		print("Warning: Skipping posttest.");
 		# Logic is inverted, because we just skip test without error.
 		exit 0;
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 7a6850683c34..eaf11f52fc0b 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -6,8 +6,6 @@
 
 # Awk implementation sanity check
 function check_awk_implement() {
-	if (!match("abc", "[[:lower:]]+"))
-		return "Your awk doesn't support charactor-class."
 	if (sprintf("%x", 0) != "0")
 		return "Your awk has a printf-format problem."
 	return ""
@@ -44,12 +42,12 @@ BEGIN {
 	delete gtable
 	delete atable
 
-	opnd_expr = "^[[:alpha:]/]"
+	opnd_expr = "^[A-Za-z/]"
 	ext_expr = "^\\("
 	sep_expr = "^\\|$"
-	group_expr = "^Grp[[:alnum:]]+"
+	group_expr = "^Grp[0-9A-Za-z]+"
 
-	imm_expr = "^[IJAO][[:lower:]]"
+	imm_expr = "^[IJAO][a-z]"
 	imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
 	imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
 	imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
@@ -62,7 +60,7 @@ BEGIN {
 	imm_flag["Ob"] = "INAT_MOFFSET"
 	imm_flag["Ov"] = "INAT_MOFFSET"
 
-	modrm_expr = "^([CDEGMNPQRSUVW/][[:lower:]]+|NTA|T[012])"
+	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
 	force64_expr = "\\([df]64\\)"
 	rex_expr = "^REX(\\.[XRWB]+)*"
 	fpu_expr = "^ESC" # TODO