Merge branch 'master' into next

39 files changed, 615 insertions, 310 deletions

diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
index 85b46fba422..8cb9c814e12 100644
--- a/arch/x86/include/asm/atomic_32.h
+++ b/arch/x86/include/asm/atomic_32.h
@@ -247,5 +247,241 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 #define smp_mb__before_atomic_inc()	barrier()
 #define smp_mb__after_atomic_inc()	barrier()
 
-#include <asm-generic/atomic.h>
+/* An 64bit atomic type */
+
+typedef struct {
+	unsigned long long counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(val)	{ (val) }
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically reads the value of @v.
+ * Doesn't imply a read memory barrier.
+ */
+#define __atomic64_read(ptr)		((ptr)->counter)
+
+static inline unsigned long long
+cmpxchg8b(unsigned long long *ptr, unsigned long long old, unsigned long long new)
+{
+	asm volatile(
+
+		LOCK_PREFIX "cmpxchg8b (%[ptr])\n"
+
+		     :		"=A" (old)
+
+		     : [ptr]	"D" (ptr),
+				"A" (old),
+				"b" (ll_low(new)),
+				"c" (ll_high(new))
+
+		     : "memory");
+
+	return old;
+}
+
+static inline unsigned long long
+atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val,
+		 unsigned long long new_val)
+{
+	return cmpxchg8b(&ptr->counter, old_val, new_val);
+}
+
+/**
+ * atomic64_xchg - xchg atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ * @new_val:  value to assign
+ * @old_val:  old value that was there
+ *
+ * Atomically xchgs the value of @ptr to @new_val and returns
+ * the old value.
+ */
+
+static inline unsigned long long
+atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
+{
+	unsigned long long old_val;
+
+	do {
+		old_val = atomic_read(ptr);
+	} while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
+
+	return old_val;
+}
+
+/**
+ * atomic64_set - set atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ * @new_val:  value to assign
+ *
+ * Atomically sets the value of @ptr to @new_val.
+ */
+static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
+{
+	atomic64_xchg(ptr, new_val);
+}
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ *
+ * Atomically reads the value of @ptr and returns it.
+ */
+static inline unsigned long long atomic64_read(atomic64_t *ptr)
+{
+	unsigned long long curr_val;
+
+	do {
+		curr_val = __atomic64_read(ptr);
+	} while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val);
+
+	return curr_val;
+}
+
+/**
+ * atomic64_add_return - add and return
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr and returns @delta + *@ptr
+ */
+static inline unsigned long long
+atomic64_add_return(unsigned long long delta, atomic64_t *ptr)
+{
+	unsigned long long old_val, new_val;
+
+	do {
+		old_val = atomic_read(ptr);
+		new_val = old_val + delta;
+
+	} while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
+
+	return new_val;
+}
+
+static inline long atomic64_sub_return(unsigned long long delta, atomic64_t *ptr)
+{
+	return atomic64_add_return(-delta, ptr);
+}
+
+static inline long atomic64_inc_return(atomic64_t *ptr)
+{
+	return atomic64_add_return(1, ptr);
+}
+
+static inline long atomic64_dec_return(atomic64_t *ptr)
+{
+	return atomic64_sub_return(1, ptr);
+}
+
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr.
+ */
+static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
+{
+	atomic64_add_return(delta, ptr);
+}
+
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @delta: integer value to subtract
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically subtracts @delta from @ptr.
+ */
+static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
+{
+	atomic64_add(-delta, ptr);
+}
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @delta: integer value to subtract
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically subtracts @delta from @ptr and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int
+atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
+{
+	unsigned long long old_val = atomic64_sub_return(delta, ptr);
+
+	return old_val == 0;
+}
+
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically increments @ptr by 1.
+ */
+static inline void atomic64_inc(atomic64_t *ptr)
+{
+	atomic64_add(1, ptr);
+}
+
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically decrements @ptr by 1.
+ */
+static inline void atomic64_dec(atomic64_t *ptr)
+{
+	atomic64_sub(1, ptr);
+}
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically decrements @ptr by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic64_dec_and_test(atomic64_t *ptr)
+{
+	return atomic64_sub_and_test(1, ptr);
+}
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically increments @ptr by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_inc_and_test(atomic64_t *ptr)
+{
+	return atomic64_sub_and_test(-1, ptr);
+}
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int
+atomic64_add_negative(unsigned long long delta, atomic64_t *ptr)
+{
+	long long old_val = atomic64_add_return(delta, ptr);
+
+	return old_val < 0;
+}
+
+#include <asm-generic/atomic-long.h>
 #endif /* _ASM_X86_ATOMIC_32_H */
diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h
index 8c21731984d..0d636022000 100644
--- a/arch/x86/include/asm/atomic_64.h
+++ b/arch/x86/include/asm/atomic_64.h
@@ -455,5 +455,5 @@ static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
 #define smp_mb__before_atomic_inc()	barrier()
 #define smp_mb__after_atomic_inc()	barrier()
 
-#include <asm-generic/atomic.h>
+#include <asm-generic/atomic-long.h>
 #endif /* _ASM_X86_ATOMIC_64_H */
diff --git a/arch/x86/include/asm/bitsperlong.h b/arch/x86/include/asm/bitsperlong.h
new file mode 100644
index 00000000000..b0ae1c4dc79
--- /dev/null
+++ b/arch/x86/include/asm/bitsperlong.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_X86_BITSPERLONG_H
+#define __ASM_X86_BITSPERLONG_H
+
+#ifdef __x86_64__
+# define __BITS_PER_LONG 64
+#else
+# define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_X86_BITSPERLONG_H */
+
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 19af42138f7..4a28d22d479 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -116,6 +116,8 @@
 #define X86_FEATURE_XMM4_1	(4*32+19) /* "sse4_1" SSE-4.1 */
 #define X86_FEATURE_XMM4_2	(4*32+20) /* "sse4_2" SSE-4.2 */
 #define X86_FEATURE_X2APIC	(4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE	(4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT      (4*32+23) /* POPCNT instruction */
 #define X86_FEATURE_AES		(4*32+25) /* AES instructions */
 #define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
 #define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index f82fdc412c6..1c3f9435f1c 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -6,6 +6,7 @@
  * Documentation/DMA-API.txt for documentation.
  */
 
+#include <linux/kmemcheck.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-debug.h>
 #include <linux/dma-attrs.h>
@@ -32,6 +33,8 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 #endif
 }
 
+#include <asm-generic/dma-mapping-common.h>
+
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
@@ -52,171 +55,6 @@ extern int dma_set_mask(struct device *dev, u64 mask);
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_addr, gfp_t flag);
 
-static inline dma_addr_t
-dma_map_single(struct device *hwdev, void *ptr, size_t size,
-	       enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-	dma_addr_t addr;
-
-	BUG_ON(!valid_dma_direction(dir));
-	addr = ops->map_page(hwdev, virt_to_page(ptr),
-			     (unsigned long)ptr & ~PAGE_MASK, size,
-			     dir, NULL);
-	debug_dma_map_page(hwdev, virt_to_page(ptr),
-			   (unsigned long)ptr & ~PAGE_MASK, size,
-			   dir, addr, true);
-	return addr;
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size,
-		 enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, NULL);
-	debug_dma_unmap_page(dev, addr, size, dir, true);
-}
-
-static inline int
-dma_map_sg(struct device *hwdev, struct scatterlist *sg,
-	   int nents, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-	int ents;
-
-	BUG_ON(!valid_dma_direction(dir));
-	ents = ops->map_sg(hwdev, sg, nents, dir, NULL);
-	debug_dma_map_sg(hwdev, sg, nents, ents, dir);
-
-	return ents;
-}
-
-static inline void
-dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
-	     enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	debug_dma_unmap_sg(hwdev, sg, nents, dir);
-	if (ops->unmap_sg)
-		ops->unmap_sg(hwdev, sg, nents, dir, NULL);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-			size_t size, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(hwdev, dma_handle, size, dir);
-	debug_dma_sync_single_for_cpu(hwdev, dma_handle, size, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
-		ops->sync_single_for_device(hwdev, dma_handle, size, dir);
-	debug_dma_sync_single_for_device(hwdev, dma_handle, size, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_range_for_cpu)
-		ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
-					       size, dir);
-	debug_dma_sync_single_range_for_cpu(hwdev, dma_handle,
-					    offset, size, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_range_for_device)
-		ops->sync_single_range_for_device(hwdev, dma_handle,
-						  offset, size, dir);
-	debug_dma_sync_single_range_for_device(hwdev, dma_handle,
-					       offset, size, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-		    int nelems, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_cpu)
-		ops->sync_sg_for_cpu(hwdev, sg, nelems, dir);
-	debug_dma_sync_sg_for_cpu(hwdev, sg, nelems, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-		       int nelems, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_device)
-		ops->sync_sg_for_device(hwdev, sg, nelems, dir);
-	debug_dma_sync_sg_for_device(hwdev, sg, nelems, dir);
-
-	flush_write_buffers();
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	BUG_ON(!valid_dma_direction(dir));
-	addr = ops->map_page(dev, page, offset, size, dir, NULL);
-	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
-
-	return addr;
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
-				  size_t size, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, NULL);
-	debug_dma_unmap_page(dev, addr, size, dir, false);
-}
-
 static inline void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	enum dma_data_direction dir)
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index c2e6bedaf25..ff8cbfa0785 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -14,6 +14,7 @@ BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
 BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
+BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
 
 BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
 		 smp_invalidate_interrupt)
@@ -49,11 +50,19 @@ BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
 #ifdef CONFIG_PERF_COUNTERS
-BUILD_INTERRUPT(perf_counter_interrupt, LOCAL_PERF_VECTOR)
+BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR)
 #endif
 
-#ifdef CONFIG_X86_MCE_P4THERMAL
+#ifdef CONFIG_X86_THERMAL_VECTOR
 BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
 #endif
 
+#ifdef CONFIG_X86_MCE_THRESHOLD
+BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
+#endif
+
+#ifdef CONFIG_X86_NEW_MCE
+BUILD_INTERRUPT(mce_self_interrupt,MCE_SELF_VECTOR)
+#endif
+
 #endif
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 37555e52f98..82e3e8f0104 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -13,6 +13,8 @@ typedef struct {
 	unsigned int irq_spurious_count;
 #endif
 	unsigned int generic_irqs;	/* arch dependent */
+	unsigned int apic_perf_irqs;
+	unsigned int apic_pending_irqs;
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
@@ -20,7 +22,7 @@ typedef struct {
 #endif
 #ifdef CONFIG_X86_MCE
 	unsigned int irq_thermal_count;
-# ifdef CONFIG_X86_64
+# ifdef CONFIG_X86_MCE_THRESHOLD
 	unsigned int irq_threshold_count;
 # endif
 #endif
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 3bd1777a4c8..ba180d93b08 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,9 +29,12 @@
 extern void apic_timer_interrupt(void);
 extern void generic_interrupt(void);
 extern void error_interrupt(void);
+extern void perf_pending_interrupt(void);
+
 extern void spurious_interrupt(void);
 extern void thermal_interrupt(void);
 extern void reschedule_interrupt(void);
+extern void mce_self_interrupt(void);
 
 extern void invalidate_interrupt(void);
 extern void invalidate_interrupt0(void);
@@ -44,6 +47,7 @@ extern void invalidate_interrupt6(void);
 extern void invalidate_interrupt7(void);
 
 extern void irq_move_cleanup_interrupt(void);
+extern void reboot_interrupt(void);
 extern void threshold_interrupt(void);
 
 extern void call_function_interrupt(void);
diff --git a/arch/x86/include/asm/intel_arch_perfmon.h b/arch/x86/include/asm/intel_arch_perfmon.h
deleted file mode 100644
index fa0fd068bc2..00000000000
--- a/arch/x86/include/asm/intel_arch_perfmon.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef _ASM_X86_INTEL_ARCH_PERFMON_H
-#define _ASM_X86_INTEL_ARCH_PERFMON_H
-
-#define MSR_ARCH_PERFMON_PERFCTR0		0xc1
-#define MSR_ARCH_PERFMON_PERFCTR1		0xc2
-
-#define MSR_ARCH_PERFMON_EVENTSEL0		0x186
-#define MSR_ARCH_PERFMON_EVENTSEL1		0x187
-
-#define ARCH_PERFMON_EVENTSEL0_ENABLE	(1 << 22)
-#define ARCH_PERFMON_EVENTSEL_INT	(1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS	(1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR	(1 << 16)
-
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL	(0x3c)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK	(0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
-	(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
-
-union cpuid10_eax {
-	struct {
-		unsigned int version_id:8;
-		unsigned int num_counters:8;
-		unsigned int bit_width:8;
-		unsigned int mask_length:8;
-	} split;
-	unsigned int full;
-};
-
-#endif /* _ASM_X86_INTEL_ARCH_PERFMON_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 910b5a3d675..5b21f0ec3df 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -25,6 +25,7 @@
  */
 
 #define NMI_VECTOR			0x02
+#define MCE_VECTOR			0x12
 
 /*
  * IDT vectors usable for external interrupt sources start
@@ -87,13 +88,8 @@
 #define CALL_FUNCTION_VECTOR		0xfc
 #define CALL_FUNCTION_SINGLE_VECTOR	0xfb
 #define THERMAL_APIC_VECTOR		0xfa
-
-#ifdef CONFIG_X86_32
-/* 0xf8 - 0xf9 : free */
-#else
-# define THRESHOLD_APIC_VECTOR		0xf9
-# define UV_BAU_MESSAGE			0xf8
-#endif
+#define THRESHOLD_APIC_VECTOR		0xf9
+#define REBOOT_VECTOR			0xf8
 
 /* f0-f7 used for spreading out TLB flushes: */
 #define INVALIDATE_TLB_VECTOR_END	0xf7
@@ -108,14 +104,21 @@
 #define LOCAL_TIMER_VECTOR		0xef
 
 /*
- * Performance monitoring interrupt vector:
+ * Generic system vector for platform specific use
+ */
+#define GENERIC_INTERRUPT_VECTOR	0xed
+
+/*
+ * Performance monitoring pending work vector:
  */
-#define LOCAL_PERF_VECTOR		0xee
+#define LOCAL_PENDING_VECTOR		0xec
+
+#define UV_BAU_MESSAGE			0xec
 
 /*
- * Generic system vector for platform specific use
+ * Self IPI vector for machine checks
  */
-#define GENERIC_INTERRUPT_VECTOR	0xed
+#define MCE_SELF_VECTOR			0xeb
 
 /*
  * First APIC vector available to drivers: (vectors 0x30-0xee) we
diff --git a/arch/x86/include/asm/kmap_types.h b/arch/x86/include/asm/kmap_types.h
index 5759c165a5c..9e00a731a7f 100644
--- a/arch/x86/include/asm/kmap_types.h
+++ b/arch/x86/include/asm/kmap_types.h
@@ -2,28 +2,11 @@
 #define _ASM_X86_KMAP_TYPES_H
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_DEBUG_HIGHMEM)
-# define D(n) __KM_FENCE_##n ,
-#else
-# define D(n)
+#define  __WITH_KM_FENCE
 #endif
 
-enum km_type {
-D(0)	KM_BOUNCE_READ,
-D(1)	KM_SKB_SUNRPC_DATA,
-D(2)	KM_SKB_DATA_SOFTIRQ,
-D(3)	KM_USER0,
-D(4)	KM_USER1,
-D(5)	KM_BIO_SRC_IRQ,
-D(6)	KM_BIO_DST_IRQ,
-D(7)	KM_PTE0,
-D(8)	KM_PTE1,
-D(9)	KM_IRQ0,
-D(10)	KM_IRQ1,
-D(11)	KM_SOFTIRQ0,
-D(12)	KM_SOFTIRQ1,
-D(13)	KM_TYPE_NR
-};
+#include <asm-generic/kmap_types.h>
 
-#undef D
+#undef __WITH_KM_FENCE
 
 #endif /* _ASM_X86_KMAP_TYPES_H */
diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h
new file mode 100644
index 00000000000..ed01518f297
--- /dev/null
+++ b/arch/x86/include/asm/kmemcheck.h
@@ -0,0 +1,42 @@
+#ifndef ASM_X86_KMEMCHECK_H
+#define ASM_X86_KMEMCHECK_H
+
+#include <linux/types.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_KMEMCHECK
+bool kmemcheck_active(struct pt_regs *regs);
+
+void kmemcheck_show(struct pt_regs *regs);
+void kmemcheck_hide(struct pt_regs *regs);
+
+bool kmemcheck_fault(struct pt_regs *regs,
+	unsigned long address, unsigned long error_code);
+bool kmemcheck_trap(struct pt_regs *regs);
+#else
+static inline bool kmemcheck_active(struct pt_regs *regs)
+{
+	return false;
+}
+
+static inline void kmemcheck_show(struct pt_regs *regs)
+{
+}
+
+static inline void kmemcheck_hide(struct pt_regs *regs)
+{
+}
+
+static inline bool kmemcheck_fault(struct pt_regs *regs,
+	unsigned long address, unsigned long error_code)
+{
+	return false;
+}
+
+static inline bool kmemcheck_trap(struct pt_regs *regs)
+{
+	return false;
+}
+#endif /* CONFIG_KMEMCHECK */
+
+#endif
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index dc3f6cf1170..125be8b1956 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -16,6 +16,7 @@
 #define __KVM_HAVE_MSI
 #define __KVM_HAVE_USER_NMI
 #define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_MSIX
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f0faf58044f..eabdc1cfab5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -185,6 +185,7 @@ union kvm_mmu_page_role {
 		unsigned access:3;
 		unsigned invalid:1;
 		unsigned cr4_pge:1;
+		unsigned nxe:1;
 	};
 };
 
@@ -212,7 +213,6 @@ struct kvm_mmu_page {
 	int multimapped;         /* More than one parent_pte? */
 	int root_count;          /* Currently serving as active root */
 	bool unsync;
-	bool global;
 	unsigned int unsync_children;
 	union {
 		u64 *parent_pte;               /* !multimapped */
@@ -261,13 +261,11 @@ struct kvm_mmu {
 	union kvm_mmu_page_role base_role;
 
 	u64 *pae_root;
+	u64 rsvd_bits_mask[2][4];
 };
 
 struct kvm_vcpu_arch {
 	u64 host_tsc;
-	int interrupt_window_open;
-	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
-	DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
 	/*
 	 * rip and regs accesses must go through
 	 * kvm_{register,rip}_{read,write} functions.
@@ -286,6 +284,7 @@ struct kvm_vcpu_arch {
 	u64 shadow_efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
+	int32_t apic_arb_prio;
 	int mp_state;
 	int sipi_vector;
 	u64 ia32_misc_enable_msr;
@@ -320,6 +319,8 @@ struct kvm_vcpu_arch {
 	struct kvm_pio_request pio;
 	void *pio_data;
 
+	u8 event_exit_inst_len;
+
 	struct kvm_queued_exception {
 		bool pending;
 		bool has_error_code;
@@ -329,11 +330,12 @@ struct kvm_vcpu_arch {
 
 	struct kvm_queued_interrupt {
 		bool pending;
+		bool soft;
 		u8 nr;
 	} interrupt;
 
 	struct {
-		int active;
+		int vm86_active;
 		u8 save_iopl;
 		struct kvm_save_segment {
 			u16 selector;
@@ -356,9 +358,9 @@ struct kvm_vcpu_arch {
 	unsigned int time_offset;
 	struct page *time_page;
 
+	bool singlestep; /* guest is single stepped by KVM */
 	bool nmi_pending;
 	bool nmi_injected;
-	bool nmi_window_open;
 
 	struct mtrr_state_type mtrr_state;
 	u32 pat;
@@ -392,15 +394,14 @@ struct kvm_arch{
 	 */
 	struct list_head active_mmu_pages;
 	struct list_head assigned_dev_head;
-	struct list_head oos_global_pages;
 	struct iommu_domain *iommu_domain;
+	int iommu_flags;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
 	struct hlist_head irq_ack_notifier_list;
 	int vapics_in_nmi_mode;
 
-	int round_robin_prev_vcpu;
 	unsigned int tss_addr;
 	struct page *apic_access_page;
 
@@ -423,7 +424,6 @@ struct kvm_vm_stat {
 	u32 mmu_recycled;
 	u32 mmu_cache_miss;
 	u32 mmu_unsync;
-	u32 mmu_unsync_global;
 	u32 remote_tlb_flush;
 	u32 lpages;
 };
@@ -443,7 +443,6 @@ struct kvm_vcpu_stat {
 	u32 halt_exits;
 	u32 halt_wakeup;
 	u32 request_irq_exits;
-	u32 request_nmi_exits;
 	u32 irq_exits;
 	u32 host_state_reload;
 	u32 efer_reload;
@@ -511,20 +510,22 @@ struct kvm_x86_ops {
 	void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
 	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
+	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
 	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
 				unsigned char *hypercall_addr);
-	int (*get_irq)(struct kvm_vcpu *vcpu);
-	void (*set_irq)(struct kvm_vcpu *vcpu, int vec);
+	void (*set_irq)(struct kvm_vcpu *vcpu);
+	void (*set_nmi)(struct kvm_vcpu *vcpu);
 	void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
 				bool has_error_code, u32 error_code);
-	bool (*exception_injected)(struct kvm_vcpu *vcpu);
-	void (*inject_pending_irq)(struct kvm_vcpu *vcpu);
-	void (*inject_pending_vectors)(struct kvm_vcpu *vcpu,
-				       struct kvm_run *run);
-
+	int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
+	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
+	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
+	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
-	int (*get_mt_mask_shift)(void);
+	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 };
 
 extern struct kvm_x86_ops *kvm_x86_ops;
@@ -538,7 +539,7 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
 void kvm_mmu_set_base_ptes(u64 base_pte);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask);
+		u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
@@ -552,6 +553,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
 int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
 		  gpa_t addr, unsigned long *ret);
+u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 extern bool tdp_enabled;
 
@@ -563,6 +565,7 @@ enum emulation_result {
 
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
+#define EMULTYPE_SKIP		    (1 << 2)
 int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			unsigned long cr2, u16 error_code, int emulation_type);
 void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
@@ -638,7 +641,6 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-void kvm_mmu_sync_global(struct kvm_vcpu *vcpu);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
@@ -769,6 +771,8 @@ enum {
 #define HF_GIF_MASK		(1 << 0)
 #define HF_HIF_MASK		(1 << 1)
 #define HF_VINTR_MASK		(1 << 2)
+#define HF_NMI_MASK		(1 << 3)
+#define HF_IRET_MASK		(1 << 4)
 
 /*
  * Hardware virtualization extension instructions may fault if a
@@ -791,5 +795,6 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_x86_emulate.h b/arch/x86/include/asm/kvm_x86_emulate.h
index 6a159732881..b7ed2c42311 100644
--- a/arch/x86/include/asm/kvm_x86_emulate.h
+++ b/arch/x86/include/asm/kvm_x86_emulate.h
@@ -143,6 +143,9 @@ struct decode_cache {
 	struct fetch_cache fetch;
 };
 
+#define X86_SHADOW_INT_MOV_SS  1
+#define X86_SHADOW_INT_STI     2
+
 struct x86_emulate_ctxt {
 	/* Register state before/after emulation. */
 	struct kvm_vcpu *vcpu;
@@ -152,6 +155,9 @@ struct x86_emulate_ctxt {
 	int mode;
 	u32 cs_base;
 
+	/* interruptibility state, as a result of execution of STI or MOV SS */
+	int interruptibility;
+
 	/* decode cache */
 	struct decode_cache decode;
 };
diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h
index 1caf57628b9..313389cd50d 100644
--- a/arch/x86/include/asm/lguest.h
+++ b/arch/x86/include/asm/lguest.h
@@ -17,8 +17,13 @@
 /* Pages for switcher itself, then two pages per cpu */
 #define TOTAL_SWITCHER_PAGES (SHARED_SWITCHER_PAGES + 2 * nr_cpu_ids)
 
-/* We map at -4M for ease of mapping into the guest (one PTE page). */
+/* We map at -4M (-2M when PAE is activated) for ease of mapping
+ * into the guest (one PTE page). */
+#ifdef CONFIG_X86_PAE
+#define SWITCHER_ADDR 0xFFE00000
+#else
 #define SWITCHER_ADDR 0xFFC00000
+#endif
 
 /* Found in switcher.S */
 extern unsigned long default_idt_entries[];
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index faae1996487..d31c4a68407 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -12,11 +12,13 @@
 #define LHCALL_TS		8
 #define LHCALL_SET_CLOCKEVENT	9
 #define LHCALL_HALT		10
+#define LHCALL_SET_PMD		13
 #define LHCALL_SET_PTE		14
-#define LHCALL_SET_PMD		15
+#define LHCALL_SET_PGD		15
 #define LHCALL_LOAD_TLS		16
 #define LHCALL_NOTIFY		17
 #define LHCALL_LOAD_GDT_ENTRY	18
+#define LHCALL_SEND_INTERRUPTS	19
 
 #define LGUEST_TRAP_ENTRY 0x1F
 
@@ -32,10 +34,10 @@
  * operations?  There are two ways: the direct way is to make a "hypercall",
  * to make requests of the Host Itself.
  *
- * We use the KVM hypercall mechanism. Eighteen hypercalls are
+ * We use the KVM hypercall mechanism. Seventeen hypercalls are
  * available: the hypercall number is put in the %eax register, and the
- * arguments (when required) are placed in %ebx, %ecx and %edx.  If a return
- * value makes sense, it's returned in %eax.
+ * arguments (when required) are placed in %ebx, %ecx, %edx and %esi.
+ * If a return value makes sense, it's returned in %eax.
  *
  * Grossly invalid calls result in Sudden Death at the hands of the vengeful
  * Host, rather than returning failure.  This reflects Winston Churchill's
@@ -47,8 +49,9 @@
 
 #define LHCALL_RING_SIZE 64
 struct hcall_args {
-	/* These map directly onto eax, ebx, ecx, edx in struct lguest_regs */
-	unsigned long arg0, arg1, arg2, arg3;
+	/* These map directly onto eax, ebx, ecx, edx and esi
+	 * in struct lguest_regs */
+	unsigned long arg0, arg1, arg2, arg3, arg4;
 };
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 4f8c199584e..540a466e50f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -1,8 +1,6 @@
 #ifndef _ASM_X86_MCE_H
 #define _ASM_X86_MCE_H
 
-#ifdef __x86_64__
-
 #include <linux/types.h>
 #include <asm/ioctls.h>
 
@@ -10,21 +8,35 @@
  * Machine Check support for x86
  */
 
-#define MCG_CTL_P	 (1UL<<8)   /* MCG_CAP register available */
-#define MCG_EXT_P	 (1ULL<<9)   /* Extended registers available */
-#define MCG_CMCI_P	 (1ULL<<10)  /* CMCI supported */
-
-#define MCG_STATUS_RIPV  (1UL<<0)   /* restart ip valid */
-#define MCG_STATUS_EIPV  (1UL<<1)   /* ip points to correct instruction */
-#define MCG_STATUS_MCIP  (1UL<<2)   /* machine check in progress */
-
-#define MCI_STATUS_VAL   (1UL<<63)  /* valid error */
-#define MCI_STATUS_OVER  (1UL<<62)  /* previous errors lost */
-#define MCI_STATUS_UC    (1UL<<61)  /* uncorrected error */
-#define MCI_STATUS_EN    (1UL<<60)  /* error enabled */
-#define MCI_STATUS_MISCV (1UL<<59)  /* misc error reg. valid */
-#define MCI_STATUS_ADDRV (1UL<<58)  /* addr reg. valid */
-#define MCI_STATUS_PCC   (1UL<<57)  /* processor context corrupt */
+#define MCG_BANKCNT_MASK	0xff         /* Number of Banks */
+#define MCG_CTL_P		(1ULL<<8)    /* MCG_CAP register available */
+#define MCG_EXT_P		(1ULL<<9)    /* Extended registers available */
+#define MCG_CMCI_P		(1ULL<<10)   /* CMCI supported */
+#define MCG_EXT_CNT_MASK	0xff0000     /* Number of Extended registers */
+#define MCG_EXT_CNT_SHIFT	16
+#define MCG_EXT_CNT(c)		(((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
+#define MCG_SER_P	 	(1ULL<<24)   /* MCA recovery/new status bits */
+
+#define MCG_STATUS_RIPV  (1ULL<<0)   /* restart ip valid */
+#define MCG_STATUS_EIPV  (1ULL<<1)   /* ip points to correct instruction */
+#define MCG_STATUS_MCIP  (1ULL<<2)   /* machine check in progress */
+
+#define MCI_STATUS_VAL   (1ULL<<63)  /* valid error */
+#define MCI_STATUS_OVER  (1ULL<<62)  /* previous errors lost */
+#define MCI_STATUS_UC    (1ULL<<61)  /* uncorrected error */
+#define MCI_STATUS_EN    (1ULL<<60)  /* error enabled */
+#define MCI_STATUS_MISCV (1ULL<<59)  /* misc error reg. valid */
+#define MCI_STATUS_ADDRV (1ULL<<58)  /* addr reg. valid */
+#define MCI_STATUS_PCC   (1ULL<<57)  /* processor context corrupt */
+#define MCI_STATUS_S	 (1ULL<<56)  /* Signaled machine check */
+#define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
+
+/* MISC register defines */
+#define MCM_ADDR_SEGOFF  0	/* segment offset */
+#define MCM_ADDR_LINEAR  1	/* linear address */
+#define MCM_ADDR_PHYS	 2	/* physical address */
+#define MCM_ADDR_MEM	 3	/* memory address */
+#define MCM_ADDR_GENERIC 7	/* generic */
 
 /* Fields are zero when not available */
 struct mce {
@@ -34,13 +46,19 @@ struct mce {
 	__u64 mcgstatus;
 	__u64 ip;
 	__u64 tsc;	/* cpu time stamp counter */
-	__u64 res1;	/* for future extension */
-	__u64 res2;	/* dito. */
+	__u64 time;	/* wall time_t when error was detected */
+	__u8  cpuvendor;	/* cpu vendor as encoded in system.h */
+	__u8  pad1;
+	__u16 pad2;
+	__u32 cpuid;	/* CPUID 1 EAX */
 	__u8  cs;		/* code segment */
 	__u8  bank;	/* machine check bank */
-	__u8  cpu;	/* cpu that raised the error */
+	__u8  cpu;	/* cpu number; obsolete; use extcpu now */
 	__u8  finished;   /* entry is valid */
-	__u32 pad;
+	__u32 extcpu;	/* linux cpu number that detected the error */
+	__u32 socketid;	/* CPU socket ID */
+	__u32 apicid;	/* CPU initial apic ID */
+	__u64 mcgcap;	/* MCGCAP MSR: machine check capabilities of CPU */
 };
 
 /*
@@ -57,7 +75,7 @@ struct mce_log {
 	unsigned len;	    /* = MCE_LOG_LEN */
 	unsigned next;
 	unsigned flags;
-	unsigned pad0;
+	unsigned recordlen;	/* length of struct mce */
 	struct mce entry[MCE_LOG_LEN];
 };
 
@@ -82,19 +100,16 @@ struct mce_log {
 #define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
 #define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
 
-#endif /* __x86_64__ */
-
 #ifdef __KERNEL__
 
-#ifdef CONFIG_X86_32
 extern int mce_disabled;
-#else /* CONFIG_X86_32 */
 
 #include <asm/atomic.h>
+#include <linux/percpu.h>
 
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
-DECLARE_PER_CPU(struct sys_device, device_mce);
+DECLARE_PER_CPU(struct sys_device, mce_dev);
 extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
 /*
@@ -104,6 +119,8 @@ extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 #define MAX_NR_BANKS (MCE_EXTENDED_BANK - 1)
 
 #ifdef CONFIG_X86_MCE_INTEL
+extern int mce_cmci_disabled;
+extern int mce_ignore_ce;
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
 void cmci_clear(void);
 void cmci_reenable(void);
@@ -123,13 +140,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c);
 static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
 #endif
 
-extern int mce_available(struct cpuinfo_x86 *c);
+int mce_available(struct cpuinfo_x86 *c);
+
+DECLARE_PER_CPU(unsigned, mce_exception_count);
+DECLARE_PER_CPU(unsigned, mce_poll_count);
 
 void mce_log_therm_throt_event(__u64 status);
 
 extern atomic_t mce_entry;
 
-extern void do_machine_check(struct pt_regs *, long);
+void do_machine_check(struct pt_regs *, long);
 
 typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
 DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
@@ -139,14 +159,16 @@ enum mcp_flags {
 	MCP_UC = (1 << 1),		/* log uncorrected errors */
 	MCP_DONTLOG = (1 << 2),		/* only clear, don't log */
 };
-extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
+void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
-extern int mce_notify_user(void);
+int mce_notify_irq(void);
+void mce_notify_process(void);
 
-#endif /* !CONFIG_X86_32 */
+DECLARE_PER_CPU(struct mce, injectm);
+extern struct file_operations mce_chrdev_ops;
 
 #ifdef CONFIG_X86_MCE
-extern void mcheck_init(struct cpuinfo_x86 *c);
+void mcheck_init(struct cpuinfo_x86 *c);
 #else
 #define mcheck_init(c) do { } while (0)
 #endif
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
index 90bc4108a4f..751af2550ed 100644
--- a/arch/x86/include/asm/mman.h
+++ b/arch/x86/include/asm/mman.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_MMAN_H
 #define _ASM_X86_MMAN_H
 
-#include <asm-generic/mman.h>
+#include <asm-generic/mman-common.h>
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4d58d04fca8..1692fb5050e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -207,7 +207,14 @@
 
 #define MSR_IA32_THERM_CONTROL		0x0000019a
 #define MSR_IA32_THERM_INTERRUPT	0x0000019b
+
+#define THERM_INT_LOW_ENABLE		(1 << 0)
+#define THERM_INT_HIGH_ENABLE		(1 << 1)
+
 #define MSR_IA32_THERM_STATUS		0x0000019c
+
+#define THERM_STATUS_PROCHOT		(1 << 0)
+
 #define MSR_IA32_MISC_ENABLE		0x000001a0
 
 /* MISC_ENABLE bits: architectural */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 638bf624180..22603764e7d 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -12,6 +12,17 @@
 
 #include <asm/asm.h>
 #include <asm/errno.h>
+#include <asm/cpumask.h>
+
+struct msr {
+	union {
+		struct {
+			u32 l;
+			u32 h;
+		};
+		u64 q;
+	};
+};
 
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
@@ -216,6 +227,8 @@ do {                                                            \
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
+void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 #else  /*  CONFIG_SMP  */
@@ -229,6 +242,16 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 	wrmsr(msr_no, l, h);
 	return 0;
 }
+static inline void rdmsr_on_cpus(const cpumask_t *m, u32 msr_no,
+				struct msr *msrs)
+{
+       rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h));
+}
+static inline void wrmsr_on_cpus(const cpumask_t *m, u32 msr_no,
+				struct msr *msrs)
+{
+       wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h);
+}
 static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
 				    u32 *l, u32 *h)
 {
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 89ed9d70b0a..625c3f0e741 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -56,7 +56,7 @@ extern bool __virt_addr_valid(unsigned long kaddr);
 #endif	/* __ASSEMBLY__ */
 
 #include <asm-generic/memory_model.h>
-#include <asm-generic/page.h>
+#include <asm-generic/getorder.h>
 
 #define __HAVE_ARCH_GATE_AREA 1
 
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
new file mode 100644
index 00000000000..876ed97147b
--- /dev/null
+++ b/arch/x86/include/asm/perf_counter.h
@@ -0,0 +1,100 @@
+#ifndef _ASM_X86_PERF_COUNTER_H
+#define _ASM_X86_PERF_COUNTER_H
+
+/*
+ * Performance counter hw details:
+ */
+
+#define X86_PMC_MAX_GENERIC					8
+#define X86_PMC_MAX_FIXED					3
+
+#define X86_PMC_IDX_GENERIC				        0
+#define X86_PMC_IDX_FIXED				       32
+#define X86_PMC_IDX_MAX					       64
+
+#define MSR_ARCH_PERFMON_PERFCTR0			      0xc1
+#define MSR_ARCH_PERFMON_PERFCTR1			      0xc2
+
+#define MSR_ARCH_PERFMON_EVENTSEL0			     0x186
+#define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
+
+#define ARCH_PERFMON_EVENTSEL0_ENABLE			  (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
+#define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
+#define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
+
+/*
+ * Includes eventsel and unit mask as well:
+ */
+#define ARCH_PERFMON_EVENT_MASK				    0xffff
+
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 		 0
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
+		(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+
+#define ARCH_PERFMON_BRANCH_MISSES_RETIRED			 6
+
+/*
+ * Intel "Architectural Performance Monitoring" CPUID
+ * detection/enumeration details:
+ */
+union cpuid10_eax {
+	struct {
+		unsigned int version_id:8;
+		unsigned int num_counters:8;
+		unsigned int bit_width:8;
+		unsigned int mask_length:8;
+	} split;
+	unsigned int full;
+};
+
+union cpuid10_edx {
+	struct {
+		unsigned int num_counters_fixed:4;
+		unsigned int reserved:28;
+	} split;
+	unsigned int full;
+};
+
+
+/*
+ * Fixed-purpose performance counters:
+ */
+
+/*
+ * All 3 fixed-mode PMCs are configured via this single MSR:
+ */
+#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL			0x38d
+
+/*
+ * The counts are available in three separate MSRs:
+ */
+
+/* Instr_Retired.Any: */
+#define MSR_ARCH_PERFMON_FIXED_CTR0			0x309
+#define X86_PMC_IDX_FIXED_INSTRUCTIONS			(X86_PMC_IDX_FIXED + 0)
+
+/* CPU_CLK_Unhalted.Core: */
+#define MSR_ARCH_PERFMON_FIXED_CTR1			0x30a
+#define X86_PMC_IDX_FIXED_CPU_CYCLES			(X86_PMC_IDX_FIXED + 1)
+
+/* CPU_CLK_Unhalted.Ref: */
+#define MSR_ARCH_PERFMON_FIXED_CTR2			0x30b
+#define X86_PMC_IDX_FIXED_BUS_CYCLES			(X86_PMC_IDX_FIXED + 2)
+
+extern void set_perf_counter_pending(void);
+
+#define clear_perf_counter_pending()	do { } while (0)
+#define test_perf_counter_pending()	(0)
+
+#ifdef CONFIG_PERF_COUNTERS
+extern void init_hw_perf_counters(void);
+extern void perf_counters_lapic_init(void);
+#else
+static inline void init_hw_perf_counters(void)		{ }
+static inline void perf_counters_lapic_init(void)	{ }
+#endif
+
+#endif /* _ASM_X86_PERF_COUNTER_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 18ef7ebf263..3cc06e3fceb 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -317,6 +317,11 @@ static inline int pte_present(pte_t a)
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
+static inline int pte_hidden(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_HIDDEN;
+}
+
 static inline int pmd_present(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_PRESENT;
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index 2733fad45f9..5e67c153231 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -46,6 +46,10 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 # define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
 #endif
 
+#define MODULES_VADDR	VMALLOC_START
+#define MODULES_END	VMALLOC_END
+#define MODULES_LEN	(MODULES_VADDR - MODULES_END)
+
 #define MAXMEM	(VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
 
 #endif /* _ASM_X86_PGTABLE_32_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4d258ad76a0..54cb697f490 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -18,7 +18,7 @@
 #define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
 #define _PAGE_BIT_UNUSED1	9	/* available for programmer */
 #define _PAGE_BIT_IOMAP		10	/* flag used to indicate IO mapping */
-#define _PAGE_BIT_UNUSED3	11
+#define _PAGE_BIT_HIDDEN	11	/* hidden by kmemcheck */
 #define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_UNUSED1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_UNUSED1
@@ -41,13 +41,18 @@
 #define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
 #define _PAGE_UNUSED1	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
 #define _PAGE_IOMAP	(_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
-#define _PAGE_UNUSED3	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
 #define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
 #define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
 #define __HAVE_ARCH_PTE_SPECIAL
 
+#ifdef CONFIG_KMEMCHECK
+#define _PAGE_HIDDEN	(_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
+#else
+#define _PAGE_HIDDEN	(_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 7761a5d554b..598457cbd0f 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -117,7 +117,7 @@ typedef unsigned long sigset_t;
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
-#include <asm-generic/signal.h>
+#include <asm-generic/signal-defs.h>
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 0e0e3ba827f..c86f452256d 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -177,10 +177,18 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
  *	No 3D Now!
  */
 
+#ifndef CONFIG_KMEMCHECK
 #define memcpy(t, f, n)				\
 	(__builtin_constant_p((n))		\
 	 ? __constant_memcpy((t), (f), (n))	\
 	 : __memcpy((t), (f), (n)))
+#else
+/*
+ * kmemcheck becomes very happy if we use the REP instructions unconditionally,
+ * because it means that we know both memory operands in advance.
+ */
+#define memcpy(t, f, n) __memcpy((t), (f), (n))
+#endif
 
 #endif
 
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 2afe164bf1e..19e2c468fc2 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -27,6 +27,7 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t
    function. */
 
 #define __HAVE_ARCH_MEMCPY 1
+#ifndef CONFIG_KMEMCHECK
 #if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
 extern void *memcpy(void *to, const void *from, size_t len);
 #else
@@ -42,6 +43,13 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 	__ret;							\
 })
 #endif
+#else
+/*
+ * kmemcheck becomes very happy if we use the REP instructions unconditionally,
+ * because it means that we know both memory operands in advance.
+ */
+#define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len))
+#endif
 
 #define __HAVE_ARCH_MEMSET
 void *memset(void *s, int c, size_t n);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 82ada75f3eb..85574b7c1bc 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -225,6 +225,7 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_EVTINJ_VALID_ERR (1 << 11)
 
 #define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
+#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK
 
 #define	SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
 #define	SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
diff --git a/arch/x86/include/asm/termios.h b/arch/x86/include/asm/termios.h
index f72956331c4..c4ee8056bac 100644
--- a/arch/x86/include/asm/termios.h
+++ b/arch/x86/include/asm/termios.h
@@ -67,6 +67,7 @@ static inline int user_termio_to_kernel_termios(struct ktermios *termios,
 	SET_LOW_TERMIOS_BITS(termios, termio, c_oflag);
 	SET_LOW_TERMIOS_BITS(termios, termio, c_cflag);
 	SET_LOW_TERMIOS_BITS(termios, termio, c_lflag);
+	get_user(termios->c_line, &termio->c_line);
 	return copy_from_user(termios->c_cc, termio->c_cc, NCC);
 }
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 602c769fc98..b0783520988 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -154,9 +154,9 @@ struct thread_info {
 
 /* thread information allocation */
 #ifdef CONFIG_DEBUG_STACK_USAGE
-#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
+#define THREAD_FLAGS (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 #else
-#define THREAD_FLAGS GFP_KERNEL
+#define THREAD_FLAGS (GFP_KERNEL | __GFP_NOTRACK)
 #endif
 
 #define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
diff --git a/arch/x86/include/asm/timex.h b/arch/x86/include/asm/timex.h
index b5c9d45c981..1375cfc9396 100644
--- a/arch/x86/include/asm/timex.h
+++ b/arch/x86/include/asm/timex.h
@@ -4,9 +4,7 @@
 #include <asm/processor.h>
 #include <asm/tsc.h>
 
-/* The PIT ticks at this frequency (in HZ): */
-#define PIT_TICK_RATE		1193182
-
+/* Assume we use the PIT time source for the clock tick */
 #define CLOCK_TICK_RATE		PIT_TICK_RATE
 
 #define ARCH_HAS_READ_CURRENT_TIMER
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index a5ecc9c33e9..7f3eba08e7d 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -172,6 +172,6 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 	flush_tlb_all();
 }
 
-extern void zap_low_mappings(void);
+extern void zap_low_mappings(bool early);
 
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/types.h b/arch/x86/include/asm/types.h
index e6f73632007..09b97745772 100644
--- a/arch/x86/include/asm/types.h
+++ b/arch/x86/include/asm/types.h
@@ -14,12 +14,6 @@ typedef unsigned short umode_t;
  */
 #ifdef __KERNEL__
 
-#ifdef CONFIG_X86_32
-# define BITS_PER_LONG 32
-#else
-# define BITS_PER_LONG 64
-#endif
-
 #ifndef __ASSEMBLY__
 
 typedef u64 dma64_addr_t;
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index 708dae61262..732a3070615 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -341,6 +341,7 @@
 #define __NR_preadv		333
 #define __NR_pwritev		334
 #define __NR_rt_tgsigqueueinfo	335
+#define __NR_perf_counter_open	336
 
 #ifdef __KERNEL__
 
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 4e2b0540440..900e1617e67 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -659,7 +659,8 @@ __SYSCALL(__NR_preadv, sys_preadv)
 __SYSCALL(__NR_pwritev, sys_pwritev)
 #define __NR_rt_tgsigqueueinfo			297
 __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
-
+#define __NR_perf_counter_open			298
+__SYSCALL(__NR_perf_counter_open, sys_perf_counter_open)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 498f944010b..11be5ad2e0e 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -247,6 +247,7 @@ enum vmcs_field {
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MCE_DURING_VMENTRY	 41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
 #define EXIT_REASON_EPT_VIOLATION       48
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
index 11b3bb86e17..7fcf6f3dbcc 100644
--- a/arch/x86/include/asm/xor.h
+++ b/arch/x86/include/asm/xor.h
@@ -1,5 +1,10 @@
+#ifdef CONFIG_KMEMCHECK
+/* kmemcheck doesn't handle MMX/SSE/SSE2 instructions */
+# include <asm-generic/xor.h>
+#else
 #ifdef CONFIG_X86_32
 # include "xor_32.h"
 #else
 # include "xor_64.h"
 #endif
+#endif