Merge branch 'linus' into x86/amd-iommu

140 files changed, 4132 insertions, 3242 deletions

diff --git a/include/asm-x86/acpi.h b/include/asm-x86/acpi.h
index 14411c9de46f..635d764dc13e 100644
--- a/include/asm-x86/acpi.h
+++ b/include/asm-x86/acpi.h
@@ -28,6 +28,7 @@
 #include <asm/numa.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
+#include <asm/mpspec.h>
 
 #define COMPILER_DEPENDENT_INT64   long long
 #define COMPILER_DEPENDENT_UINT64  unsigned long long
@@ -160,9 +161,7 @@ struct bootnode;
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
 extern int acpi_scan_nodes(unsigned long start, unsigned long end);
-#ifdef CONFIG_X86_64
-# define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-#endif
+#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
 extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
 				   int num_nodes);
 #else
diff --git a/include/asm-x86/alternative.h b/include/asm-x86/alternative.h
index 1f6a9ca10126..f6aa18eadf71 100644
--- a/include/asm-x86/alternative.h
+++ b/include/asm-x86/alternative.h
@@ -72,6 +72,8 @@ static inline void alternatives_smp_module_del(struct module *mod) {}
 static inline void alternatives_smp_switch(int smp) {}
 #endif	/* CONFIG_SMP */
 
+const unsigned char *const *find_nop_table(void);
+
 /*
  * Alternative instructions for different CPU types or capabilities.
  *
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index be9639a9a186..4e2c1e517f06 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -36,15 +36,11 @@ extern void generic_apic_probe(void);
 #ifdef CONFIG_X86_LOCAL_APIC
 
 extern int apic_verbosity;
-extern int timer_over_8254;
 extern int local_apic_timer_c2_ok;
-extern int local_apic_timer_disabled;
 
-extern int apic_runs_main_timer;
 extern int ioapic_force;
-extern int disable_apic;
-extern int disable_apic_timer;
 
+extern int disable_apic;
 /*
  * Basic functions accessing APICs.
  */
@@ -125,16 +121,22 @@ extern void enable_NMI_through_LVT0(void);
  */
 #ifdef CONFIG_X86_64
 extern void early_init_lapic_mapping(void);
+extern int apic_is_clustered_box(void);
+#else
+static inline int apic_is_clustered_box(void)
+{
+	return 0;
+}
 #endif
 
 extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
 extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
 
-extern int apic_is_clustered_box(void);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
+static inline void init_apic_mappings(void) { }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
diff --git a/include/asm-x86/asm.h b/include/asm-x86/asm.h
index 90dec0c23646..97220321f39d 100644
--- a/include/asm-x86/asm.h
+++ b/include/asm-x86/asm.h
@@ -1,37 +1,40 @@
 #ifndef _ASM_X86_ASM_H
 #define _ASM_X86_ASM_H
 
-#ifdef CONFIG_X86_32
-/* 32 bits */
-
-# define _ASM_PTR	" .long "
-# define _ASM_ALIGN	" .balign 4 "
-# define _ASM_MOV_UL	" movl "
-
-# define _ASM_INC	" incl "
-# define _ASM_DEC	" decl "
-# define _ASM_ADD	" addl "
-# define _ASM_SUB	" subl "
-# define _ASM_XADD	" xaddl "
-
+#ifdef __ASSEMBLY__
+# define __ASM_FORM(x)	x
+# define __ASM_EX_SEC	.section __ex_table
 #else
-/* 64 bits */
+# define __ASM_FORM(x)	" " #x " "
+# define __ASM_EX_SEC	" .section __ex_table,\"a\"\n"
+#endif
 
-# define _ASM_PTR	" .quad "
-# define _ASM_ALIGN	" .balign 8 "
-# define _ASM_MOV_UL	" movq "
-
-# define _ASM_INC	" incq "
-# define _ASM_DEC	" decq "
-# define _ASM_ADD	" addq "
-# define _ASM_SUB	" subq "
-# define _ASM_XADD	" xaddq "
-
-#endif /* CONFIG_X86_32 */
+#ifdef CONFIG_X86_32
+# define __ASM_SEL(a,b) __ASM_FORM(a)
+#else
+# define __ASM_SEL(a,b) __ASM_FORM(b)
+#endif
+
+#define __ASM_SIZE(inst)	__ASM_SEL(inst##l, inst##q)
+#define __ASM_REG(reg)		__ASM_SEL(e##reg, r##reg)
+
+#define _ASM_PTR	__ASM_SEL(.long, .quad)
+#define _ASM_ALIGN	__ASM_SEL(.balign 4, .balign 8)
+#define _ASM_MOV_UL	__ASM_SIZE(mov)
+
+#define _ASM_INC	__ASM_SIZE(inc)
+#define _ASM_DEC	__ASM_SIZE(dec)
+#define _ASM_ADD	__ASM_SIZE(add)
+#define _ASM_SUB	__ASM_SIZE(sub)
+#define _ASM_XADD	__ASM_SIZE(xadd)
+#define _ASM_AX		__ASM_REG(ax)
+#define _ASM_BX		__ASM_REG(bx)
+#define _ASM_CX		__ASM_REG(cx)
+#define _ASM_DX		__ASM_REG(dx)
 
 /* Exception table entry */
 # define _ASM_EXTABLE(from,to) \
-	" .section __ex_table,\"a\"\n" \
+	__ASM_EX_SEC	\
 	_ASM_ALIGN "\n" \
 	_ASM_PTR #from "," #to "\n" \
 	" .previous\n"
diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h
index 3e0cd7d38335..a0095191c02e 100644
--- a/include/asm-x86/atomic_64.h
+++ b/include/asm-x86/atomic_64.h
@@ -11,12 +11,6 @@
  * resource counting etc..
  */
 
-#ifdef CONFIG_SMP
-#define LOCK "lock ; "
-#else
-#define LOCK ""
-#endif
-
 /*
  * Make sure gcc doesn't try to be clever and move things around
  * on us. We need to use _exactly_ the address the user gave us,
@@ -431,6 +425,32 @@ static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
 	return c != (u);
 }
 
+/**
+ * atomic_inc_short - increment of a short integer
+ * @v: pointer to type int
+ *
+ * Atomically adds 1 to @v
+ * Returns the new value of @u
+ */
+static inline short int atomic_inc_short(short int *v)
+{
+	asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
+	return *v;
+}
+
+/**
+ * atomic_or_long - OR of two long integers
+ * @v1: pointer to type unsigned long
+ * @v2: pointer to type unsigned long
+ *
+ * Atomically ORs @v1 and @v2
+ * Returns the result of the OR
+ */
+static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
+{
+	asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
+}
+
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
 
 /* These are x86-specific, used by some header files */
diff --git a/include/asm-x86/bios_ebda.h b/include/asm-x86/bios_ebda.h
index b4a46b7be794..0033e50c13b2 100644
--- a/include/asm-x86/bios_ebda.h
+++ b/include/asm-x86/bios_ebda.h
@@ -14,4 +14,6 @@ static inline unsigned int get_bios_ebda(void)
 	return address;	/* 0 means none */
 }
 
+void reserve_ebda_region(void);
+
 #endif /* _MACH_BIOS_EBDA_H */
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index ee4b3ead6a43..96b1829cea15 100644
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -23,11 +23,21 @@
 #if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1)
 /* Technically wrong, but this avoids compilation errors on some gcc
    versions. */
-#define ADDR "=m" (*(volatile long *) addr)
+#define BITOP_ADDR(x) "=m" (*(volatile long *) (x))
 #else
-#define ADDR "+m" (*(volatile long *) addr)
+#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
 #endif
 
+#define ADDR				BITOP_ADDR(addr)
+
+/*
+ * We do the locked ops that don't return the old value as
+ * a mask operation on a byte.
+ */
+#define IS_IMMEDIATE(nr)		(__builtin_constant_p(nr))
+#define CONST_MASK_ADDR(nr, addr)	BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK(nr)			(1 << ((nr) & 7))
+
 /**
  * set_bit - Atomically set a bit in memory
  * @nr: the bit to set
@@ -43,9 +53,17 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(int nr, volatile void *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *addr)
 {
-	asm volatile(LOCK_PREFIX "bts %1,%0" : ADDR : "Ir" (nr) : "memory");
+	if (IS_IMMEDIATE(nr)) {
+		asm volatile(LOCK_PREFIX "orb %1,%0"
+			: CONST_MASK_ADDR(nr, addr)
+			: "iq" ((u8)CONST_MASK(nr))
+			: "memory");
+	} else {
+		asm volatile(LOCK_PREFIX "bts %1,%0"
+			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+	}
 }
 
 /**
@@ -57,7 +75,7 @@ static inline void set_bit(int nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile void *addr)
+static inline void __set_bit(int nr, volatile unsigned long *addr)
 {
 	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
@@ -72,9 +90,17 @@ static inline void __set_bit(int nr, volatile void *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void clear_bit(int nr, volatile void *addr)
+static inline void clear_bit(int nr, volatile unsigned long *addr)
 {
-	asm volatile(LOCK_PREFIX "btr %1,%0" : ADDR : "Ir" (nr));
+	if (IS_IMMEDIATE(nr)) {
+		asm volatile(LOCK_PREFIX "andb %1,%0"
+			: CONST_MASK_ADDR(nr, addr)
+			: "iq" ((u8)~CONST_MASK(nr)));
+	} else {
+		asm volatile(LOCK_PREFIX "btr %1,%0"
+			: BITOP_ADDR(addr)
+			: "Ir" (nr));
+	}
 }
 
 /*
@@ -85,13 +111,13 @@ static inline void clear_bit(int nr, volatile void *addr)
  * clear_bit() is atomic and implies release semantics before the memory
  * operation. It can be used for an unlock.
  */
-static inline void clear_bit_unlock(unsigned nr, volatile void *addr)
+static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
 {
 	barrier();
 	clear_bit(nr, addr);
 }
 
-static inline void __clear_bit(int nr, volatile void *addr)
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
 {
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
@@ -108,7 +134,7 @@ static inline void __clear_bit(int nr, volatile void *addr)
  * No memory barrier is required here, because x86 cannot reorder stores past
  * older loads. Same principle as spin_unlock.
  */
-static inline void __clear_bit_unlock(unsigned nr, volatile void *addr)
+static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
 {
 	barrier();
 	__clear_bit(nr, addr);
@@ -126,7 +152,7 @@ static inline void __clear_bit_unlock(unsigned nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile void *addr)
+static inline void __change_bit(int nr, volatile unsigned long *addr)
 {
 	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -140,7 +166,7 @@ static inline void __change_bit(int nr, volatile void *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(int nr, volatile void *addr)
+static inline void change_bit(int nr, volatile unsigned long *addr)
 {
 	asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -153,7 +179,7 @@ static inline void change_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_set_bit(int nr, volatile void *addr)
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -170,7 +196,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
  *
  * This is the same as test_and_set_bit on x86.
  */
-static inline int test_and_set_bit_lock(int nr, volatile void *addr)
+static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
 }
@@ -184,7 +210,7 @@ static inline int test_and_set_bit_lock(int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile void *addr)
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -203,7 +229,7 @@ static inline int __test_and_set_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_clear_bit(int nr, volatile void *addr)
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -223,7 +249,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile void *addr)
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -235,7 +261,7 @@ static inline int __test_and_clear_bit(int nr, volatile void *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile void *addr)
+static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -255,7 +281,7 @@ static inline int __test_and_change_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_change_bit(int nr, volatile void *addr)
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -266,13 +292,13 @@ static inline int test_and_change_bit(int nr, volatile void *addr)
 	return oldbit;
 }
 
-static inline int constant_test_bit(int nr, const volatile void *addr)
+static inline int constant_test_bit(int nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
 		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
 }
 
-static inline int variable_test_bit(int nr, volatile const void *addr)
+static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
 {
 	int oldbit;
 
diff --git a/include/asm-x86/bootparam.h b/include/asm-x86/bootparam.h
index f62f4733606b..ae22bdf0ab14 100644
--- a/include/asm-x86/bootparam.h
+++ b/include/asm-x86/bootparam.h
@@ -11,6 +11,7 @@
 
 /* setup data types */
 #define SETUP_NONE			0
+#define SETUP_E820_EXT			1
 
 /* extensible setup data list node */
 struct setup_data {
@@ -40,6 +41,7 @@ struct setup_header {
 	__u8	type_of_loader;
 	__u8	loadflags;
 #define LOADED_HIGH	(1<<0)
+#define QUIET_FLAG	(1<<5)
 #define KEEP_SEGMENTS	(1<<6)
 #define CAN_USE_HEAP	(1<<7)
 	__u16	setup_move_size;
diff --git a/include/asm-x86/cmpxchg_64.h b/include/asm-x86/cmpxchg_64.h
index d9b26b9a28cf..17463ccf8166 100644
--- a/include/asm-x86/cmpxchg_64.h
+++ b/include/asm-x86/cmpxchg_64.h
@@ -93,6 +93,39 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return old;
 }
 
+/*
+ * Always use locked operations when touching memory shared with a
+ * hypervisor, since the system may be SMP even if the guest kernel
+ * isn't.
+ */
+static inline unsigned long __sync_cmpxchg(volatile void *ptr,
+					   unsigned long old,
+					   unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		asm volatile("lock; cmpxchgb %b1,%2"
+			     : "=a"(prev)
+			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 2:
+		asm volatile("lock; cmpxchgw %w1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 4:
+		asm volatile("lock; cmpxchgl %1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	}
+	return old;
+}
+
 static inline unsigned long __cmpxchg_local(volatile void *ptr,
 					    unsigned long old,
 					    unsigned long new, int size)
@@ -139,6 +172,10 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
 					     (unsigned long)(n),	\
 					     sizeof(*(ptr))))
+#define sync_cmpxchg(ptr, o, n)						\
+	((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),	\
+					    (unsigned long)(n),		\
+					    sizeof(*(ptr))))
 #define cmpxchg64_local(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index 0d609c837a41..75ef959db329 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -74,8 +74,8 @@
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
 #define X86_FEATURE_PEBS	(3*32+12)  /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS		(3*32+13)  /* Branch Trace Store */
-/* 14 free */
-/* 15 free */
+#define X86_FEATURE_SYSCALL32	(3*32+14)  /* syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	(3*32+15)  /* sysenter in ia32 userspace */
 #define X86_FEATURE_REP_GOOD	(3*32+16) /* rep microcode works well on this CPU */
 #define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* Mfence synchronizes RDTSC */
 #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* Lfence synchronizes RDTSC */
@@ -106,6 +106,7 @@
 /* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
 #define X86_FEATURE_LAHF_LM	(6*32+ 0) /* LAHF/SAHF in long mode */
 #define X86_FEATURE_CMP_LEGACY	(6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_IBS		(6*32+ 10) /* Instruction Based Sampling */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -142,11 +143,11 @@ extern const char * const x86_power_flags[32];
 #define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
 #define setup_clear_cpu_cap(bit) do { \
 	clear_cpu_cap(&boot_cpu_data, bit);	\
-	set_bit(bit, cleared_cpu_caps); 	\
+	set_bit(bit, (unsigned long *)cleared_cpu_caps); \
 } while (0)
 #define setup_force_cpu_cap(bit) do { \
 	set_cpu_cap(&boot_cpu_data, bit);	\
-	clear_bit(bit, cleared_cpu_caps); 	\
+	clear_bit(bit, (unsigned long *)cleared_cpu_caps); 	\
 } while (0)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
diff --git a/include/asm-x86/current.h b/include/asm-x86/current.h
index d2526d3f7346..7515c19d4988 100644
--- a/include/asm-x86/current.h
+++ b/include/asm-x86/current.h
@@ -1,5 +1,39 @@
+#ifndef _X86_CURRENT_H
+#define _X86_CURRENT_H
+
 #ifdef CONFIG_X86_32
-# include "current_32.h"
-#else
-# include "current_64.h"
-#endif
+#include <linux/compiler.h>
+#include <asm/percpu.h>
+
+struct task_struct;
+
+DECLARE_PER_CPU(struct task_struct *, current_task);
+static __always_inline struct task_struct *get_current(void)
+{
+	return x86_read_percpu(current_task);
+}
+
+#else /* X86_32 */
+
+#ifndef __ASSEMBLY__
+#include <asm/pda.h>
+
+struct task_struct;
+
+static __always_inline struct task_struct *get_current(void)
+{
+	return read_pda(pcurrent);
+}
+
+#else /* __ASSEMBLY__ */
+
+#include <asm/asm-offsets.h>
+#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* X86_32 */
+
+#define current get_current()
+
+#endif /* X86_CURRENT_H */
diff --git a/include/asm-x86/current_32.h b/include/asm-x86/current_32.h
deleted file mode 100644
index 5af9bdb97a16..000000000000
--- a/include/asm-x86/current_32.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _I386_CURRENT_H
-#define _I386_CURRENT_H
-
-#include <linux/compiler.h>
-#include <asm/percpu.h>
-
-struct task_struct;
-
-DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
-	return x86_read_percpu(current_task);
-}
-
-#define current get_current()
-
-#endif /* !(_I386_CURRENT_H) */
diff --git a/include/asm-x86/current_64.h b/include/asm-x86/current_64.h
deleted file mode 100644
index 2d368ede2fc1..000000000000
--- a/include/asm-x86/current_64.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef _X86_64_CURRENT_H
-#define _X86_64_CURRENT_H
-
-#if !defined(__ASSEMBLY__)
-struct task_struct;
-
-#include <asm/pda.h>
-
-static inline struct task_struct *get_current(void)
-{
-	struct task_struct *t = read_pda(pcurrent);
-	return t;
-}
-
-#define current get_current()
-
-#else
-
-#ifndef ASM_OFFSET_H
-#include <asm/asm-offsets.h>
-#endif
-
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
-
-#endif
-
-#endif /* !(_X86_64_CURRENT_H) */
diff --git a/include/asm-x86/desc.h b/include/asm-x86/desc.h
index 268a012bcd79..a44c4dc70590 100644
--- a/include/asm-x86/desc.h
+++ b/include/asm-x86/desc.h
@@ -29,11 +29,17 @@ static inline void fill_ldt(struct desc_struct *desc,
 extern struct desc_ptr idt_descr;
 extern gate_desc idt_table[];
 
+struct gdt_page {
+	struct desc_struct gdt[GDT_ENTRIES];
+} __attribute__((aligned(PAGE_SIZE)));
+DECLARE_PER_CPU(struct gdt_page, gdt_page);
+
+static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
+{
+	return per_cpu(gdt_page, cpu).gdt;
+}
+
 #ifdef CONFIG_X86_64
-extern struct desc_struct cpu_gdt_table[GDT_ENTRIES];
-extern struct desc_ptr cpu_gdt_descr[];
-/* the cpu gdt accessor */
-#define get_cpu_gdt_table(x) ((struct desc_struct *)cpu_gdt_descr[x].address)
 
 static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
 			     unsigned dpl, unsigned ist, unsigned seg)
@@ -51,16 +57,6 @@ static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
 }
 
 #else
-struct gdt_page {
-	struct desc_struct gdt[GDT_ENTRIES];
-} __attribute__((aligned(PAGE_SIZE)));
-DECLARE_PER_CPU(struct gdt_page, gdt_page);
-
-static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
-{
-	return per_cpu(gdt_page, cpu).gdt;
-}
-
 static inline void pack_gate(gate_desc *gate, unsigned char type,
 			     unsigned long base, unsigned dpl, unsigned flags,
 			     unsigned short seg)
@@ -192,8 +188,8 @@ static inline void native_set_ldt(const void *addr, unsigned int entries)
 		unsigned cpu = smp_processor_id();
 		ldt_desc ldt;
 
-		set_tssldt_descriptor(&ldt, (unsigned long)addr,
-				      DESC_LDT, entries * sizeof(ldt) - 1);
+		set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT,
+				      entries * LDT_ENTRY_SIZE - 1);
 		write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT,
 				&ldt, DESC_LDT);
 		asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8));
@@ -311,6 +307,28 @@ static inline void set_intr_gate(unsigned int n, void *addr)
 	_set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS);
 }
 
+#define SYS_VECTOR_FREE		0
+#define SYS_VECTOR_ALLOCED	1
+
+extern int first_system_vector;
+extern char system_vectors[];
+
+static inline void alloc_system_vector(int vector)
+{
+	if (system_vectors[vector] == SYS_VECTOR_FREE) {
+		system_vectors[vector] = SYS_VECTOR_ALLOCED;
+		if (first_system_vector > vector)
+			first_system_vector = vector;
+	} else
+		BUG();
+}
+
+static inline void alloc_intr_gate(unsigned int n, void *addr)
+{
+	alloc_system_vector(n);
+	set_intr_gate(n, addr);
+}
+
 /*
  * This routine sets up an interrupt gate at directory privilege level 3.
  */
diff --git a/include/asm-x86/desc_defs.h b/include/asm-x86/desc_defs.h
index eccb4ea1f918..f7bacf357dac 100644
--- a/include/asm-x86/desc_defs.h
+++ b/include/asm-x86/desc_defs.h
@@ -75,10 +75,14 @@ struct ldttss_desc64 {
 typedef struct gate_struct64 gate_desc;
 typedef struct ldttss_desc64 ldt_desc;
 typedef struct ldttss_desc64 tss_desc;
+#define gate_offset(g) ((g).offset_low | ((unsigned long)(g).offset_middle << 16) | ((unsigned long)(g).offset_high << 32))
+#define gate_segment(g) ((g).segment)
 #else
 typedef struct desc_struct gate_desc;
 typedef struct desc_struct ldt_desc;
 typedef struct desc_struct tss_desc;
+#define gate_offset(g)		(((g).b & 0xffff0000) | ((g).a & 0x0000ffff))
+#define gate_segment(g)		((g).a >> 16)
 #endif
 
 struct desc_ptr {
diff --git a/include/asm-x86/dmi.h b/include/asm-x86/dmi.h
index 4edf7514a750..58a86571fe0f 100644
--- a/include/asm-x86/dmi.h
+++ b/include/asm-x86/dmi.h
@@ -3,12 +3,6 @@
 
 #include <asm/io.h>
 
-#ifdef CONFIG_X86_32
-
-#define dmi_alloc alloc_bootmem
-
-#else /* CONFIG_X86_32 */
-
 #define DMI_MAX_DATA 2048
 
 extern int dmi_alloc_index;
@@ -25,8 +19,6 @@ static inline void *dmi_alloc(unsigned len)
 	return dmi_alloc_data + idx;
 }
 
-#endif
-
 /* Use early IO mappings for DMI because it's initialized early */
 #define dmi_ioremap early_ioremap
 #define dmi_iounmap early_iounmap
diff --git a/include/asm-x86/dwarf2.h b/include/asm-x86/dwarf2.h
index b3cbb0ccae18..738bb9fb3e53 100644
--- a/include/asm-x86/dwarf2.h
+++ b/include/asm-x86/dwarf2.h
@@ -1,5 +1,61 @@
-#ifdef CONFIG_X86_32
-# include "dwarf2_32.h"
+#ifndef _DWARF2_H
+#define _DWARF2_H
+
+#ifndef __ASSEMBLY__
+#warning "asm/dwarf2.h should be only included in pure assembly files"
+#endif
+
+/*
+   Macros for dwarf2 CFI unwind table entries.
+   See "as.info" for details on these pseudo ops. Unfortunately
+   they are only supported in very new binutils, so define them
+   away for older version.
+ */
+
+#ifdef CONFIG_AS_CFI
+
+#define CFI_STARTPROC .cfi_startproc
+#define CFI_ENDPROC .cfi_endproc
+#define CFI_DEF_CFA .cfi_def_cfa
+#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
+#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
+#define CFI_OFFSET .cfi_offset
+#define CFI_REL_OFFSET .cfi_rel_offset
+#define CFI_REGISTER .cfi_register
+#define CFI_RESTORE .cfi_restore
+#define CFI_REMEMBER_STATE .cfi_remember_state
+#define CFI_RESTORE_STATE .cfi_restore_state
+#define CFI_UNDEFINED .cfi_undefined
+
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
+
 #else
-# include "dwarf2_64.h"
+
+/* Due to the structure of pre-exisiting code, don't use assembler line
+   comment character # to ignore the arguments. Instead, use a dummy macro. */
+.macro cfi_ignore a=0, b=0, c=0, d=0
+.endm
+
+#define CFI_STARTPROC	cfi_ignore
+#define CFI_ENDPROC	cfi_ignore
+#define CFI_DEF_CFA	cfi_ignore
+#define CFI_DEF_CFA_REGISTER	cfi_ignore
+#define CFI_DEF_CFA_OFFSET	cfi_ignore
+#define CFI_ADJUST_CFA_OFFSET	cfi_ignore
+#define CFI_OFFSET	cfi_ignore
+#define CFI_REL_OFFSET	cfi_ignore
+#define CFI_REGISTER	cfi_ignore
+#define CFI_RESTORE	cfi_ignore
+#define CFI_REMEMBER_STATE cfi_ignore
+#define CFI_RESTORE_STATE cfi_ignore
+#define CFI_UNDEFINED cfi_ignore
+#define CFI_SIGNAL_FRAME cfi_ignore
+
+#endif
+
 #endif
diff --git a/include/asm-x86/dwarf2_32.h b/include/asm-x86/dwarf2_32.h
deleted file mode 100644
index 6d66398a307d..000000000000
--- a/include/asm-x86/dwarf2_32.h
+++ /dev/null
@@ -1,61 +0,0 @@
-#ifndef _DWARF2_H
-#define _DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
- */
-
-#ifdef CONFIG_UNWIND_INFO
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#else
-
-/* Due to the structure of pre-exisiting code, don't use assembler line
-   comment character # to ignore the arguments. Instead, use a dummy macro. */
-.macro ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC	ignore
-#define CFI_ENDPROC	ignore
-#define CFI_DEF_CFA	ignore
-#define CFI_DEF_CFA_REGISTER	ignore
-#define CFI_DEF_CFA_OFFSET	ignore
-#define CFI_ADJUST_CFA_OFFSET	ignore
-#define CFI_OFFSET	ignore
-#define CFI_REL_OFFSET	ignore
-#define CFI_REGISTER	ignore
-#define CFI_RESTORE	ignore
-#define CFI_REMEMBER_STATE ignore
-#define CFI_RESTORE_STATE ignore
-#define CFI_UNDEFINED ignore
-#define CFI_SIGNAL_FRAME ignore
-
-#endif
-
-#endif
diff --git a/include/asm-x86/dwarf2_64.h b/include/asm-x86/dwarf2_64.h
deleted file mode 100644
index c950519a264d..000000000000
--- a/include/asm-x86/dwarf2_64.h
+++ /dev/null
@@ -1,56 +0,0 @@
-#ifndef _DWARF2_H
-#define _DWARF2_H 1
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#else
-
-/* use assembler line comment character # to ignore the arguments. */
-#define CFI_STARTPROC	#
-#define CFI_ENDPROC	#
-#define CFI_DEF_CFA	#
-#define CFI_DEF_CFA_REGISTER	#
-#define CFI_DEF_CFA_OFFSET	#
-#define CFI_ADJUST_CFA_OFFSET	#
-#define CFI_OFFSET	#
-#define CFI_REL_OFFSET	#
-#define CFI_REGISTER	#
-#define CFI_RESTORE	#
-#define CFI_REMEMBER_STATE	#
-#define CFI_RESTORE_STATE	#
-#define CFI_UNDEFINED	#
-#define CFI_SIGNAL_FRAME	#
-
-#endif
-
-#endif
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
index 7004251fc66b..06633b01dd5b 100644
--- a/include/asm-x86/e820.h
+++ b/include/asm-x86/e820.h
@@ -2,6 +2,41 @@
 #define __ASM_E820_H
 #define E820MAP	0x2d0		/* our map */
 #define E820MAX	128		/* number of entries in E820MAP */
+
+/*
+ * Legacy E820 BIOS limits us to 128 (E820MAX) nodes due to the
+ * constrained space in the zeropage.  If we have more nodes than
+ * that, and if we've booted off EFI firmware, then the EFI tables
+ * passed us from the EFI firmware can list more nodes.  Size our
+ * internal memory map tables to have room for these additional
+ * nodes, based on up to three entries per node for which the
+ * kernel was built: MAX_NUMNODES == (1 << CONFIG_NODES_SHIFT),
+ * plus E820MAX, allowing space for the possible duplicate E820
+ * entries that might need room in the same arrays, prior to the
+ * call to sanitize_e820_map() to remove duplicates.  The allowance
+ * of three memory map entries per node is "enough" entries for
+ * the initial hardware platform motivating this mechanism to make
+ * use of additional EFI map entries.  Future platforms may want
+ * to allow more than three entries per node or otherwise refine
+ * this size.
+ */
+
+/*
+ * Odd: 'make headers_check' complains about numa.h if I try
+ * to collapse the next two #ifdef lines to a single line:
+ *	#if defined(__KERNEL__) && defined(CONFIG_EFI)
+ */
+#ifdef __KERNEL__
+#ifdef CONFIG_EFI
+#include <linux/numa.h>
+#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
+#else	/* ! CONFIG_EFI */
+#define E820_X_MAX E820MAX
+#endif
+#else	/* ! __KERNEL__ */
+#define E820_X_MAX E820MAX
+#endif
+
 #define E820NR	0x1e8		/* # entries in E820MAP */
 
 #define E820_RAM	1
@@ -9,6 +44,9 @@
 #define E820_ACPI	3
 #define E820_NVS	4
 
+/* reserved RAM used by kernel itself */
+#define E820_RESERVED_KERN        128
+
 #ifndef __ASSEMBLY__
 struct e820entry {
 	__u64 addr;	/* start of memory segment */
@@ -18,22 +56,80 @@ struct e820entry {
 
 struct e820map {
 	__u32 nr_map;
-	struct e820entry map[E820MAX];
+	struct e820entry map[E820_X_MAX];
 };
+
+#ifdef __KERNEL__
+/* see comment in arch/x86/kernel/e820.c */
+extern struct e820map e820;
+extern struct e820map e820_saved;
+
+extern int e820_any_mapped(u64 start, u64 end, unsigned type);
+extern int e820_all_mapped(u64 start, u64 end, unsigned type);
+extern void e820_add_region(u64 start, u64 size, int type);
+extern void e820_print_map(char *who);
+extern int
+sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map);
+extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
+			       unsigned new_type);
+extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
+			     int checktype);
+extern void update_e820(void);
+extern void e820_setup_gap(void);
+extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
+			unsigned long start_addr, unsigned long long end_addr);
+struct setup_data;
+extern void parse_e820_ext(struct setup_data *data, unsigned long pa_data);
+
+#if defined(CONFIG_X86_64) || \
+	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
+extern void e820_mark_nosave_regions(unsigned long limit_pfn);
+#else
+static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
+{
+}
+#endif
+
+extern unsigned long end_user_pfn;
+
+extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
+extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
+extern void reserve_early(u64 start, u64 end, char *name);
+extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
+extern void free_early(u64 start, u64 end);
+extern void early_res_to_bootmem(u64 start, u64 end);
+extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+
+extern unsigned long e820_end_of_ram_pfn(void);
+extern unsigned long e820_end_of_low_ram_pfn(void);
+extern int e820_find_active_region(const struct e820entry *ei,
+				  unsigned long start_pfn,
+				  unsigned long last_pfn,
+				  unsigned long *ei_startpfn,
+				  unsigned long *ei_endpfn);
+extern void e820_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long end_pfn);
+extern u64 e820_hole_size(u64 start, u64 end);
+extern void finish_e820_parsing(void);
+extern void e820_reserve_resources(void);
+extern void setup_memory_map(void);
+extern char *default_machine_specific_memory_setup(void);
+extern char *machine_specific_memory_setup(void);
+extern char *memory_setup(void);
+#endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 
 #define ISA_START_ADDRESS	0xa0000
 #define ISA_END_ADDRESS		0x100000
+#define is_ISA_range(s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS)
 
 #define BIOS_BEGIN		0x000a0000
 #define BIOS_END		0x00100000
 
 #ifdef __KERNEL__
-#ifdef CONFIG_X86_32
-# include "e820_32.h"
-#else
-# include "e820_64.h"
-#endif
+#include <linux/ioport.h>
+
+#define HIGH_MEMORY	(1024*1024)
 #endif /* __KERNEL__ */
 
 #endif  /* __ASM_E820_H */
diff --git a/include/asm-x86/e820_32.h b/include/asm-x86/e820_32.h
deleted file mode 100644
index a9f7c6ec32bf..000000000000
--- a/include/asm-x86/e820_32.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * structures and definitions for the int 15, ax=e820 memory map
- * scheme.
- *
- * In a nutshell, arch/i386/boot/setup.S populates a scratch table
- * in the empty_zero_block that contains a list of usable address/size
- * duples.   In arch/i386/kernel/setup.c, this information is
- * transferred into the e820map, and in arch/i386/mm/init.c, that
- * new information is used to mark pages reserved or not.
- *
- */
-#ifndef __E820_HEADER
-#define __E820_HEADER
-
-#include <linux/ioport.h>
-
-#define HIGH_MEMORY	(1024*1024)
-
-#ifndef __ASSEMBLY__
-
-extern struct e820map e820;
-extern void update_e820(void);
-
-extern int e820_all_mapped(unsigned long start, unsigned long end,
-			   unsigned type);
-extern int e820_any_mapped(u64 start, u64 end, unsigned type);
-extern void propagate_e820_map(void);
-extern void register_bootmem_low_pages(unsigned long max_low_pfn);
-extern void add_memory_region(unsigned long long start,
-			      unsigned long long size, int type);
-extern void update_memory_range(u64 start, u64 size, unsigned old_type,
-				unsigned new_type);
-extern void e820_register_memory(void);
-extern void limit_regions(unsigned long long size);
-extern void print_memory_map(char *who);
-extern void init_iomem_resources(struct resource *code_resource,
-				 struct resource *data_resource,
-				 struct resource *bss_resource);
-
-#if defined(CONFIG_PM) && defined(CONFIG_HIBERNATION)
-extern void e820_mark_nosave_regions(void);
-#else
-static inline void e820_mark_nosave_regions(void)
-{
-}
-#endif
-
-
-#endif/*!__ASSEMBLY__*/
-#endif/*__E820_HEADER*/
diff --git a/include/asm-x86/e820_64.h b/include/asm-x86/e820_64.h
deleted file mode 100644
index 71c4d685d30d..000000000000
--- a/include/asm-x86/e820_64.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * structures and definitions for the int 15, ax=e820 memory map
- * scheme.
- *
- * In a nutshell, setup.S populates a scratch table in the
- * empty_zero_block that contains a list of usable address/size
- * duples.  setup.c, this information is transferred into the e820map,
- * and in init.c/numa.c, that new information is used to mark pages
- * reserved or not.
- */
-#ifndef __E820_HEADER
-#define __E820_HEADER
-
-#include <linux/ioport.h>
-
-#ifndef __ASSEMBLY__
-extern unsigned long find_e820_area(unsigned long start, unsigned long end,
-				    unsigned long size, unsigned long align);
-extern unsigned long find_e820_area_size(unsigned long start,
-					 unsigned long *sizep,
-					 unsigned long align);
-extern void add_memory_region(unsigned long start, unsigned long size,
-			      int type);
-extern void update_memory_range(u64 start, u64 size, unsigned old_type,
-				unsigned new_type);
-extern void setup_memory_region(void);
-extern void contig_e820_setup(void);
-extern unsigned long e820_end_of_ram(void);
-extern void e820_reserve_resources(void);
-extern void e820_mark_nosave_regions(void);
-extern int e820_any_mapped(unsigned long start, unsigned long end,
-			   unsigned type);
-extern int e820_all_mapped(unsigned long start, unsigned long end,
-			   unsigned type);
-extern int e820_any_non_reserved(unsigned long start, unsigned long end);
-extern int is_memory_any_valid(unsigned long start, unsigned long end);
-extern int e820_all_non_reserved(unsigned long start, unsigned long end);
-extern int is_memory_all_valid(unsigned long start, unsigned long end);
-extern unsigned long e820_hole_size(unsigned long start, unsigned long end);
-
-extern void e820_setup_gap(void);
-extern void e820_register_active_regions(int nid, unsigned long start_pfn,
-					 unsigned long end_pfn);
-
-extern void finish_e820_parsing(void);
-
-extern struct e820map e820;
-extern void update_e820(void);
-
-extern void reserve_early(unsigned long start, unsigned long end, char *name);
-extern void free_early(unsigned long start, unsigned long end);
-extern void early_res_to_bootmem(unsigned long start, unsigned long end);
-
-#endif/*!__ASSEMBLY__*/
-
-#endif/*__E820_HEADER*/
diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h
index d53004b855cc..7ed2bd7a7f51 100644
--- a/include/asm-x86/efi.h
+++ b/include/asm-x86/efi.h
@@ -90,7 +90,7 @@ extern void *efi_ioremap(unsigned long addr, unsigned long size);
 
 #endif /* CONFIG_X86_32 */
 
-extern void efi_reserve_bootmem(void);
+extern void efi_reserve_early(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
diff --git a/include/asm-x86/elf.h b/include/asm-x86/elf.h
index 8f232dc5b5fe..7be4733c793e 100644
--- a/include/asm-x86/elf.h
+++ b/include/asm-x86/elf.h
@@ -83,9 +83,9 @@ extern unsigned int vdso_enabled;
 	(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
 
 #include <asm/processor.h>
+#include <asm/system.h>
 
 #ifdef CONFIG_X86_32
-#include <asm/system.h>		/* for savesegment */
 #include <asm/desc.h>
 
 #define elf_check_arch(x)	elf_check_arch_ia32(x)
diff --git a/include/asm-x86/fixmap.h b/include/asm-x86/fixmap.h
index 5bd206973dca..44d4f8217349 100644
--- a/include/asm-x86/fixmap.h
+++ b/include/asm-x86/fixmap.h
@@ -7,7 +7,62 @@
 # include "fixmap_64.h"
 #endif
 
+extern int fixmaps_set;
+
+void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
+void native_set_fixmap(enum fixed_addresses idx,
+		       unsigned long phys, pgprot_t flags);
+
+#ifndef CONFIG_PARAVIRT
+static inline void __set_fixmap(enum fixed_addresses idx,
+				unsigned long phys, pgprot_t flags)
+{
+	native_set_fixmap(idx, phys, flags);
+}
+#endif
+
+#define set_fixmap(idx, phys)				\
+	__set_fixmap(idx, phys, PAGE_KERNEL)
+
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys)			\
+	__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+
 #define clear_fixmap(idx)			\
 	__set_fixmap(idx, 0, __pgprot(0))
 
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without translation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
+{
+	/*
+	 * this branch gets completely eliminated after inlining,
+	 * except when someone tries to use fixaddr indices in an
+	 * illegal way. (such as mixing up address types or using
+	 * out-of-range indices).
+	 *
+	 * If it doesn't get removed, the linker will complain
+	 * loudly with a reasonably clear error message..
+	 */
+	if (idx >= __end_of_fixed_addresses)
+		__this_fixmap_does_not_exist();
+
+	return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+	return __virt_to_fix(vaddr);
+}
 #endif
diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h
index 4b96148e90c1..aae2f0501a40 100644
--- a/include/asm-x86/fixmap_32.h
+++ b/include/asm-x86/fixmap_32.h
@@ -79,10 +79,6 @@ enum fixed_addresses {
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
 #endif
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
 #ifdef CONFIG_PCI_MMCONFIG
 	FIX_PCIE_MCFG,
 #endif
@@ -103,23 +99,18 @@ enum fixed_addresses {
 			(__end_of_permanent_fixed_addresses & 511),
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_NESTING - 1,
 	FIX_WP_TEST,
+#ifdef CONFIG_ACPI
+	FIX_ACPI_BEGIN,
+	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
 	FIX_OHCI1394_BASE,
 #endif
 	__end_of_fixed_addresses
 };
 
-extern void __set_fixmap(enum fixed_addresses idx,
-			 unsigned long phys, pgprot_t flags);
 extern void reserve_top_address(unsigned long reserve);
 
-#define set_fixmap(idx, phys)				\
-	__set_fixmap(idx, phys, PAGE_KERNEL)
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys)			\
-	__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
 
 #define FIXADDR_TOP	((unsigned long)__FIXADDR_TOP)
 
@@ -128,38 +119,5 @@ extern void reserve_top_address(unsigned long reserve);
 #define FIXADDR_START		(FIXADDR_TOP - __FIXADDR_SIZE)
 #define FIXADDR_BOOT_START	(FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
 
-#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
-#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without tranlation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static __always_inline unsigned long fix_to_virt(const unsigned int idx)
-{
-	/*
-	 * this branch gets completely eliminated after inlining,
-	 * except when someone tries to use fixaddr indices in an
-	 * illegal way. (such as mixing up address types or using
-	 * out-of-range indices).
-	 *
-	 * If it doesn't get removed, the linker will complain
-	 * loudly with a reasonably clear error message..
-	 */
-	if (idx >= __end_of_fixed_addresses)
-		__this_fixmap_does_not_exist();
-
-	return __fix_to_virt(idx);
-}
-
-static inline unsigned long virt_to_fix(const unsigned long vaddr)
-{
-	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
-	return __virt_to_fix(vaddr);
-}
-
 #endif /* !__ASSEMBLY__ */
 #endif
diff --git a/include/asm-x86/fixmap_64.h b/include/asm-x86/fixmap_64.h
index 355d26a75a82..00f3d74a0524 100644
--- a/include/asm-x86/fixmap_64.h
+++ b/include/asm-x86/fixmap_64.h
@@ -12,6 +12,7 @@
 #define _ASM_FIXMAP_64_H
 
 #include <linux/kernel.h>
+#include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
 #include <asm/vsyscall.h>
@@ -39,30 +40,38 @@ enum fixed_addresses {
 	VSYSCALL_HPET,
 	FIX_DBGP_BASE,
 	FIX_EARLYCON_MEM_BASE,
-	FIX_HPET_BASE,
 	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
 	FIX_IO_APIC_BASE_0,
 	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
 	FIX_EFI_IO_MAP_LAST_PAGE,
 	FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE
 				  + MAX_EFI_IO_PAGES - 1,
+#ifdef CONFIG_PARAVIRT
+	FIX_PARAVIRT_BOOTMAP,
+#endif
+#ifdef CONFIG_ACPI
+	FIX_ACPI_BEGIN,
+	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
 	FIX_OHCI1394_BASE,
 #endif
+	__end_of_permanent_fixed_addresses,
+	/*
+	 * 256 temporary boot-time mappings, used by early_ioremap(),
+	 * before ioremap() is functional.
+	 *
+	 * We round it up to the next 512 pages boundary so that we
+	 * can have a single pgd entry and a single pte table:
+	 */
+#define NR_FIX_BTMAPS		64
+#define FIX_BTMAPS_NESTING	4
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 512 -
+			(__end_of_permanent_fixed_addresses & 511),
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_NESTING - 1,
 	__end_of_fixed_addresses
 };
 
-extern void __set_fixmap(enum fixed_addresses idx,
-			 unsigned long phys, pgprot_t flags);
-
-#define set_fixmap(idx, phys)			\
-	__set_fixmap(idx, phys, PAGE_KERNEL)
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys)			\
-	__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
-
 #define FIXADDR_TOP	(VSYSCALL_END-PAGE_SIZE)
 #define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
 #define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
@@ -71,30 +80,4 @@ extern void __set_fixmap(enum fixed_addresses idx,
 #define FIXADDR_USER_START	((unsigned long)VSYSCALL32_VSYSCALL)
 #define FIXADDR_USER_END	(FIXADDR_USER_START + PAGE_SIZE)
 
-#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without translation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static __always_inline unsigned long fix_to_virt(const unsigned int idx)
-{
-	/*
-	 * this branch gets completely eliminated after inlining,
-	 * except when someone tries to use fixaddr indices in an
-	 * illegal way. (such as mixing up address types or using
-	 * out-of-range indices).
-	 *
-	 * If it doesn't get removed, the linker will complain
-	 * loudly with a reasonably clear error message..
-	 */
-	if (idx >= __end_of_fixed_addresses)
-		__this_fixmap_does_not_exist();
-
-	return __fix_to_virt(idx);
-}
-
 #endif
diff --git a/include/asm-x86/ftrace.h b/include/asm-x86/ftrace.h
new file mode 100644
index 000000000000..c184441133f2
--- /dev/null
+++ b/include/asm-x86/ftrace.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_X86_FTRACE
+#define _ASM_SPARC64_FTRACE
+
+#ifdef CONFIG_FTRACE
+#define MCOUNT_ADDR		((long)(mcount))
+#define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
+
+#ifndef __ASSEMBLY__
+extern void mcount(void);
+#endif
+
+#endif /* CONFIG_FTRACE */
+
+#endif /* _ASM_X86_FTRACE */
diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h
index ec5785c6e2fd..33b9aeeb35a2 100644
--- a/include/asm-x86/gart.h
+++ b/include/asm-x86/gart.h
@@ -1,35 +1,72 @@
-#ifndef _ASM_X8664_IOMMU_H
-#define _ASM_X8664_IOMMU_H 1
-
-extern void pci_iommu_shutdown(void);
-extern void no_iommu_init(void);
-extern int force_iommu, no_iommu;
-extern int iommu_detected;
-#ifdef CONFIG_GART_IOMMU
-extern void gart_iommu_init(void);
-extern void gart_iommu_shutdown(void);
-extern void __init gart_parse_options(char *);
-extern void early_gart_iommu_check(void);
-extern void gart_iommu_hole_init(void);
+#ifndef _ASM_X8664_GART_H
+#define _ASM_X8664_GART_H 1
+
+#include <asm/e820.h>
+#include <asm/iommu.h>
+
+extern void set_up_gart_resume(u32, u32);
+
 extern int fallback_aper_order;
 extern int fallback_aper_force;
-extern int gart_iommu_aperture;
-extern int gart_iommu_aperture_allowed;
-extern int gart_iommu_aperture_disabled;
 extern int fix_aperture;
-#else
-#define gart_iommu_aperture		0
-#define gart_iommu_aperture_allowed	0
-#define gart_iommu_aperture_disabled	1
 
-static inline void early_gart_iommu_check(void)
+/* PTE bits. */
+#define GPTE_VALID	1
+#define GPTE_COHERENT	2
+
+/* Aperture control register bits. */
+#define GARTEN		(1<<0)
+#define DISGARTCPU	(1<<4)
+#define DISGARTIO	(1<<5)
+
+/* GART cache control register bits. */
+#define INVGART		(1<<0)
+#define GARTPTEERR	(1<<1)
+
+/* K8 On-cpu GART registers */
+#define AMD64_GARTAPERTURECTL	0x90
+#define AMD64_GARTAPERTUREBASE	0x94
+#define AMD64_GARTTABLEBASE	0x98
+#define AMD64_GARTCACHECTL	0x9c
+#define AMD64_GARTEN		(1<<0)
+
+static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
 {
+	u32 tmp, ctl;
+
+        /* address of the mappings table */
+        addr >>= 12;
+        tmp = (u32) addr<<4;
+        tmp &= ~0xf;
+        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+
+        /* Enable GART translation for this hammer. */
+        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+        ctl |= GARTEN;
+        ctl &= ~(DISGARTCPU | DISGARTIO);
+        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
 
-static inline void gart_iommu_shutdown(void)
+static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
 {
-}
+	if (!aper_base)
+		return 0;
 
-#endif
+	if (aper_base + aper_size > 0x100000000ULL) {
+		printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n");
+		return 0;
+	}
+	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+		printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
+		return 0;
+	}
+	if (aper_size < min_size) {
+		printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n",
+				 aper_size>>20, min_size>>20);
+		return 0;
+	}
+
+	return 1;
+}
 
 #endif
diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h
index 1de931b263ce..0f8504627c41 100644
--- a/include/asm-x86/genapic_64.h
+++ b/include/asm-x86/genapic_64.h
@@ -44,4 +44,6 @@ DECLARE_PER_CPU(int, x2apic_extra_bits);
 extern void uv_cpu_init(void);
 extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
 
+extern void setup_apic_routing(void);
+
 #endif
diff --git a/include/asm-x86/hardirq.h b/include/asm-x86/hardirq.h
index 314434d664e7..000787df66e6 100644
--- a/include/asm-x86/hardirq.h
+++ b/include/asm-x86/hardirq.h
@@ -3,3 +3,9 @@
 #else
 # include "hardirq_64.h"
 #endif
+
+extern u64 arch_irq_stat_cpu(unsigned int cpu);
+#define arch_irq_stat_cpu	arch_irq_stat_cpu
+
+extern u64 arch_irq_stat(void);
+#define arch_irq_stat		arch_irq_stat
diff --git a/include/asm-x86/highmem.h b/include/asm-x86/highmem.h
index e153f3b44774..4514b16cc723 100644
--- a/include/asm-x86/highmem.h
+++ b/include/asm-x86/highmem.h
@@ -74,6 +74,9 @@ struct page *kmap_atomic_to_page(void *ptr);
 
 #define flush_cache_kmaps()	do { } while (0)
 
+extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn,
+					unsigned long end_pfn);
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_HIGHMEM_H */
diff --git a/include/asm-x86/hpet.h b/include/asm-x86/hpet.h
index 6a9b4ac59bf7..82f1ac641bd7 100644
--- a/include/asm-x86/hpet.h
+++ b/include/asm-x86/hpet.h
@@ -86,8 +86,8 @@ extern void hpet_unregister_irq_handler(rtc_irq_handler handler);
 #else /* CONFIG_HPET_TIMER */
 
 static inline int hpet_enable(void) { return 0; }
-static inline unsigned long hpet_readl(unsigned long a) { return 0; }
 static inline int is_hpet_enabled(void) { return 0; }
+#define hpet_readl(a) 0
 
 #endif
 #endif /* ASM_X86_HPET_H */
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
index bf025399d939..77ba51df5668 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -1,5 +1,107 @@
+#ifndef _ASM_HW_IRQ_H
+#define _ASM_HW_IRQ_H
+
+/*
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * moved some of the old arch/i386/kernel/irq.h to here. VY
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@informatik.tu-chemnitz.de>
+ *
+ * hacked by Andi Kleen for x86-64.
+ * unified by tglx
+ */
+
+#include <asm/irq_vectors.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/smp.h>
+
+#include <asm/atomic.h>
+#include <asm/irq.h>
+#include <asm/sections.h>
+
+#define platform_legacy_irq(irq)	((irq) < 16)
+
+/* Interrupt handlers registered during init_IRQ */
+extern void apic_timer_interrupt(void);
+extern void error_interrupt(void);
+extern void spurious_interrupt(void);
+extern void thermal_interrupt(void);
+extern void reschedule_interrupt(void);
+
+extern void invalidate_interrupt(void);
+extern void invalidate_interrupt0(void);
+extern void invalidate_interrupt1(void);
+extern void invalidate_interrupt2(void);
+extern void invalidate_interrupt3(void);
+extern void invalidate_interrupt4(void);
+extern void invalidate_interrupt5(void);
+extern void invalidate_interrupt6(void);
+extern void invalidate_interrupt7(void);
+
+extern void irq_move_cleanup_interrupt(void);
+extern void threshold_interrupt(void);
+
+extern void call_function_interrupt(void);
+extern void call_function_single_interrupt(void);
+
+/* PIC specific functions */
+extern void disable_8259A_irq(unsigned int irq);
+extern void enable_8259A_irq(unsigned int irq);
+extern int i8259A_irq_pending(unsigned int irq);
+extern void make_8259A_irq(unsigned int irq);
+extern void init_8259A(int aeoi);
+
+/* IOAPIC */
+#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
+extern unsigned long io_apic_irqs;
+
+extern void init_VISWS_APIC_irqs(void);
+extern void setup_IO_APIC(void);
+extern void disable_IO_APIC(void);
+extern void print_IO_APIC(void);
+extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
+extern void setup_ioapic_dest(void);
+
+#ifdef CONFIG_X86_64
+extern void enable_IO_APIC(void);
+#endif
+
+/* IPI functions */
+extern void send_IPI_self(int vector);
+extern void send_IPI(int dest, int vector);
+
+/* Statistics */
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
+
+/* EISA */
+extern void eisa_set_level_irq(unsigned int irq);
+
+/* Voyager functions */
+extern asmlinkage void vic_cpi_interrupt(void);
+extern asmlinkage void vic_sys_interrupt(void);
+extern asmlinkage void vic_cmn_interrupt(void);
+extern asmlinkage void qic_timer_interrupt(void);
+extern asmlinkage void qic_invalidate_interrupt(void);
+extern asmlinkage void qic_reschedule_interrupt(void);
+extern asmlinkage void qic_enable_irq_interrupt(void);
+extern asmlinkage void qic_call_function_interrupt(void);
+
 #ifdef CONFIG_X86_32
-# include "hw_irq_32.h"
+extern void (*const interrupt[NR_IRQS])(void);
 #else
-# include "hw_irq_64.h"
+typedef int vector_irq_t[NR_VECTORS];
+DECLARE_PER_CPU(vector_irq_t, vector_irq);
+extern spinlock_t vector_lock;
+#endif
+extern void setup_vector_irq(int cpu);
+
+#endif /* !ASSEMBLY_ */
+
 #endif
diff --git a/include/asm-x86/hw_irq_32.h b/include/asm-x86/hw_irq_32.h
deleted file mode 100644
index ea88054e03f3..000000000000
--- a/include/asm-x86/hw_irq_32.h
+++ /dev/null
@@ -1,66 +0,0 @@
-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
-
-/*
- *	linux/include/asm/hw_irq.h
- *
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	moved some of the old arch/i386/kernel/irq.h to here. VY
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- */
-
-#include <linux/profile.h>
-#include <asm/atomic.h>
-#include <asm/irq.h>
-#include <asm/sections.h>
-
-#define NMI_VECTOR		0x02
-
-/*
- * Various low-level irq details needed by irq.c, process.c,
- * time.c, io_apic.c and smp.c
- *
- * Interrupt entry/exit code at both C and assembly level
- */
-
-extern void (*const interrupt[NR_IRQS])(void);
-
-#ifdef CONFIG_SMP
-void reschedule_interrupt(void);
-void invalidate_interrupt(void);
-void call_function_interrupt(void);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-void apic_timer_interrupt(void);
-void error_interrupt(void);
-void spurious_interrupt(void);
-void thermal_interrupt(void);
-#define platform_legacy_irq(irq)	((irq) < 16)
-#endif
-
-void disable_8259A_irq(unsigned int irq);
-void enable_8259A_irq(unsigned int irq);
-int i8259A_irq_pending(unsigned int irq);
-void make_8259A_irq(unsigned int irq);
-void init_8259A(int aeoi);
-void send_IPI_self(int vector);
-void init_VISWS_APIC_irqs(void);
-void setup_IO_APIC(void);
-void disable_IO_APIC(void);
-void print_IO_APIC(void);
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
-void send_IPI(int dest, int vector);
-void setup_ioapic_dest(void);
-
-extern unsigned long io_apic_irqs;
-
-extern atomic_t irq_err_count;
-extern atomic_t irq_mis_count;
-
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
-
-#endif /* _ASM_HW_IRQ_H */
diff --git a/include/asm-x86/hw_irq_64.h b/include/asm-x86/hw_irq_64.h
deleted file mode 100644
index 0062ef390f67..000000000000
--- a/include/asm-x86/hw_irq_64.h
+++ /dev/null
@@ -1,173 +0,0 @@
-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
-
-/*
- *	linux/include/asm/hw_irq.h
- *
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	moved some of the old arch/i386/kernel/irq.h to here. VY
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- *
- *	hacked by Andi Kleen for x86-64.
- */
-
-#ifndef __ASSEMBLY__
-#include <asm/atomic.h>
-#include <asm/irq.h>
-#include <linux/profile.h>
-#include <linux/smp.h>
-#include <linux/percpu.h>
-#endif
-
-#define NMI_VECTOR		0x02
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR	0x20
-
-#define IA32_SYSCALL_VECTOR	0x80
-
-
-/* Reserve the lowest usable priority level 0x20 - 0x2f for triggering
- * cleanup after irq migration.
- */
-#define IRQ_MOVE_CLEANUP_VECTOR	FIRST_EXTERNAL_VECTOR
-
-/*
- * Vectors 0x30-0x3f are used for ISA interrupts.
- */
-#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR + 0x10)
-#define IRQ1_VECTOR		(IRQ0_VECTOR + 1)
-#define IRQ2_VECTOR		(IRQ0_VECTOR + 2)
-#define IRQ3_VECTOR		(IRQ0_VECTOR + 3)
-#define IRQ4_VECTOR		(IRQ0_VECTOR + 4)
-#define IRQ5_VECTOR		(IRQ0_VECTOR + 5)
-#define IRQ6_VECTOR		(IRQ0_VECTOR + 6)
-#define IRQ7_VECTOR		(IRQ0_VECTOR + 7)
-#define IRQ8_VECTOR		(IRQ0_VECTOR + 8)
-#define IRQ9_VECTOR		(IRQ0_VECTOR + 9)
-#define IRQ10_VECTOR		(IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR		(IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR		(IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR		(IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR		(IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR		(IRQ0_VECTOR + 15)
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- */
-#define SPURIOUS_APIC_VECTOR	0xff
-#define ERROR_APIC_VECTOR	0xfe
-#define RESCHEDULE_VECTOR	0xfd
-#define CALL_FUNCTION_VECTOR	0xfc
-/* fb free - please don't readd KDB here because it's useless
-   (hint - think what a NMI bit does to a vector) */
-#define THERMAL_APIC_VECTOR	0xfa
-#define THRESHOLD_APIC_VECTOR   0xf9
-/* f8 free */
-#define INVALIDATE_TLB_VECTOR_END	0xf7
-#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
-
-#define NUM_INVALIDATE_TLB_VECTORS	8
-
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR	0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x41 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
-#define FIRST_SYSTEM_VECTOR	0xef   /* duplicated in irq.h */
-
-
-#ifndef __ASSEMBLY__
-
-/* Interrupt handlers registered during init_IRQ */
-void apic_timer_interrupt(void);
-void spurious_interrupt(void);
-void error_interrupt(void);
-void reschedule_interrupt(void);
-void call_function_interrupt(void);
-void irq_move_cleanup_interrupt(void);
-void invalidate_interrupt0(void);
-void invalidate_interrupt1(void);
-void invalidate_interrupt2(void);
-void invalidate_interrupt3(void);
-void invalidate_interrupt4(void);
-void invalidate_interrupt5(void);
-void invalidate_interrupt6(void);
-void invalidate_interrupt7(void);
-void thermal_interrupt(void);
-void threshold_interrupt(void);
-void i8254_timer_resume(void);
-
-typedef int vector_irq_t[NR_VECTORS];
-DECLARE_PER_CPU(vector_irq_t, vector_irq);
-extern void __setup_vector_irq(int cpu);
-extern spinlock_t vector_lock;
-
-/*
- * Various low-level irq details needed by irq.c, process.c,
- * time.c, io_apic.c and smp.c
- *
- * Interrupt entry/exit code at both C and assembly level
- */
-
-extern void disable_8259A_irq(unsigned int irq);
-extern void enable_8259A_irq(unsigned int irq);
-extern int i8259A_irq_pending(unsigned int irq);
-extern void make_8259A_irq(unsigned int irq);
-extern void init_8259A(int aeoi);
-extern void send_IPI_self(int vector);
-extern void init_VISWS_APIC_irqs(void);
-extern void setup_IO_APIC(void);
-extern void enable_IO_APIC(void);
-extern void disable_IO_APIC(void);
-extern void print_IO_APIC(void);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
-extern void send_IPI(int dest, int vector);
-extern void setup_ioapic_dest(void);
-extern void native_init_IRQ(void);
-
-extern unsigned long io_apic_irqs;
-
-extern atomic_t irq_err_count;
-extern atomic_t irq_mis_count;
-
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
-
-#include <asm/ptrace.h>
-
-#define IRQ_NAME2(nr) nr##_interrupt(void)
-#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
-
-/*
- *	SMP has a few special interrupts for IPI messages
- */
-
-#define BUILD_IRQ(nr)				\
-	asmlinkage void IRQ_NAME(nr);		\
-	asm("\n.p2align\n"			\
-	    "IRQ" #nr "_interrupt:\n\t"		\
-	    "push $~(" #nr ") ; "		\
-	    "jmp common_interrupt");
-
-#define platform_legacy_irq(irq)	((irq) < 16)
-
-#endif
-
-#endif /* _ASM_HW_IRQ_H */
diff --git a/include/asm-x86/i8259.h b/include/asm-x86/i8259.h
index 45d4df3e51e6..2f98df91f1f2 100644
--- a/include/asm-x86/i8259.h
+++ b/include/asm-x86/i8259.h
@@ -55,4 +55,6 @@ static inline void outb_pic(unsigned char value, unsigned int port)
 	udelay(2);
 }
 
+extern struct irq_chip i8259A_chip;
+
 #endif	/* __ASM_I8259_H__ */
diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h
index d5b11f60dbd0..bf5d629b3a39 100644
--- a/include/asm-x86/io.h
+++ b/include/asm-x86/io.h
@@ -3,6 +3,76 @@
 
 #define ARCH_HAS_IOREMAP_WC
 
+#include <linux/compiler.h>
+
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ * A boot-time mapping is currently limited to at most 16 pages.
+ */
+#ifndef __ASSEMBLY__
+extern void early_ioremap_init(void);
+extern void early_ioremap_clear(void);
+extern void early_ioremap_reset(void);
+extern void *early_ioremap(unsigned long offset, unsigned long size);
+extern void early_iounmap(void *addr, unsigned long size);
+extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
+#endif
+
+#define build_mmio_read(name, size, type, reg, barrier) \
+static inline type name(const volatile void __iomem *addr) \
+{ type ret; asm volatile("mov" size " %1,%0":"=" reg (ret) \
+:"m" (*(volatile type __force *)addr) barrier); return ret; }
+
+#define build_mmio_write(name, size, type, reg, barrier) \
+static inline void name(type val, volatile void __iomem *addr) \
+{ asm volatile("mov" size " %0,%1": :reg (val), \
+"m" (*(volatile type __force *)addr) barrier); }
+
+build_mmio_read(readb, "b", unsigned char, "q", :"memory")
+build_mmio_read(readw, "w", unsigned short, "r", :"memory")
+build_mmio_read(readl, "l", unsigned int, "r", :"memory")
+
+build_mmio_read(__readb, "b", unsigned char, "q", )
+build_mmio_read(__readw, "w", unsigned short, "r", )
+build_mmio_read(__readl, "l", unsigned int, "r", )
+
+build_mmio_write(writeb, "b", unsigned char, "q", :"memory")
+build_mmio_write(writew, "w", unsigned short, "r", :"memory")
+build_mmio_write(writel, "l", unsigned int, "r", :"memory")
+
+build_mmio_write(__writeb, "b", unsigned char, "q", )
+build_mmio_write(__writew, "w", unsigned short, "r", )
+build_mmio_write(__writel, "l", unsigned int, "r", )
+
+#define readb_relaxed(a) __readb(a)
+#define readw_relaxed(a) __readw(a)
+#define readl_relaxed(a) __readl(a)
+#define __raw_readb __readb
+#define __raw_readw __readw
+#define __raw_readl __readl
+
+#define __raw_writeb __writeb
+#define __raw_writew __writew
+#define __raw_writel __writel
+
+#define mmiowb() barrier()
+
+#ifdef CONFIG_X86_64
+build_mmio_read(readq, "q", unsigned long, "r", :"memory")
+build_mmio_read(__readq, "q", unsigned long, "r", )
+build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
+build_mmio_write(__writeq, "q", unsigned long, "r", )
+
+#define readq_relaxed(a) __readq(a)
+#define __raw_readq __readq
+#define __raw_writeq writeq
+
+/* Let people know we have them */
+#define readq readq
+#define writeq writeq
+#endif
+
 #ifdef CONFIG_X86_32
 # include "io_32.h"
 #else
@@ -16,4 +86,17 @@ extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 				unsigned long prot_val);
 extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
 
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ * A boot-time mapping is currently limited to at most 16 pages.
+ */
+extern void early_ioremap_init(void);
+extern void early_ioremap_clear(void);
+extern void early_ioremap_reset(void);
+extern void *early_ioremap(unsigned long offset, unsigned long size);
+extern void early_iounmap(void *addr, unsigned long size);
+extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
+
+
 #endif /* _ASM_X86_IO_H */
diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h
index 049e81e797a0..4df44ed54077 100644
--- a/include/asm-x86/io_32.h
+++ b/include/asm-x86/io_32.h
@@ -122,18 +122,6 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
 extern void iounmap(volatile void __iomem *addr);
 
 /*
- * early_ioremap() and early_iounmap() are for temporary early boot-time
- * mappings, before the real ioremap() is functional.
- * A boot-time mapping is currently limited to at most 16 pages.
- */
-extern void early_ioremap_init(void);
-extern void early_ioremap_clear(void);
-extern void early_ioremap_reset(void);
-extern void *early_ioremap(unsigned long offset, unsigned long size);
-extern void early_iounmap(void *addr, unsigned long size);
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
-
-/*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
 #define isa_virt_to_bus virt_to_phys
@@ -149,55 +137,6 @@ extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 #define virt_to_bus virt_to_phys
 #define bus_to_virt phys_to_virt
 
-/*
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the x86 architecture, we just read/write the
- * memory location directly.
- */
-
-static inline unsigned char readb(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned char __force *)addr;
-}
-
-static inline unsigned short readw(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned short __force *)addr;
-}
-
-static inline unsigned int readl(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned int __force *) addr;
-}
-
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
-#define __raw_readb readb
-#define __raw_readw readw
-#define __raw_readl readl
-
-static inline void writeb(unsigned char b, volatile void __iomem *addr)
-{
-	*(volatile unsigned char __force *)addr = b;
-}
-
-static inline void writew(unsigned short b, volatile void __iomem *addr)
-{
-	*(volatile unsigned short __force *)addr = b;
-}
-
-static inline void writel(unsigned int b, volatile void __iomem *addr)
-{
-	*(volatile unsigned int __force *)addr = b;
-}
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
-
-#define mmiowb()
-
 static inline void
 memset_io(volatile void __iomem *addr, unsigned char val, int count)
 {
diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h
index 0930bedf9e4d..ddd8058a5026 100644
--- a/include/asm-x86/io_64.h
+++ b/include/asm-x86/io_64.h
@@ -204,77 +204,6 @@ extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 #define virt_to_bus virt_to_phys
 #define bus_to_virt phys_to_virt
 
-/*
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the x86 architecture, we just read/write the
- * memory location directly.
- */
-
-static inline __u8 __readb(const volatile void __iomem *addr)
-{
-	return *(__force volatile __u8 *)addr;
-}
-
-static inline __u16 __readw(const volatile void __iomem *addr)
-{
-	return *(__force volatile __u16 *)addr;
-}
-
-static __always_inline __u32 __readl(const volatile void __iomem *addr)
-{
-	return *(__force volatile __u32 *)addr;
-}
-
-static inline __u64 __readq(const volatile void __iomem *addr)
-{
-	return *(__force volatile __u64 *)addr;
-}
-
-#define readb(x) __readb(x)
-#define readw(x) __readw(x)
-#define readl(x) __readl(x)
-#define readq(x) __readq(x)
-#define readb_relaxed(a) readb(a)
-#define readw_relaxed(a) readw(a)
-#define readl_relaxed(a) readl(a)
-#define readq_relaxed(a) readq(a)
-#define __raw_readb readb
-#define __raw_readw readw
-#define __raw_readl readl
-#define __raw_readq readq
-
-#define mmiowb()
-
-static inline void __writel(__u32 b, volatile void __iomem *addr)
-{
-	*(__force volatile __u32 *)addr = b;
-}
-
-static inline void __writeq(__u64 b, volatile void __iomem *addr)
-{
-	*(__force volatile __u64 *)addr = b;
-}
-
-static inline void __writeb(__u8 b, volatile void __iomem *addr)
-{
-	*(__force volatile __u8 *)addr = b;
-}
-
-static inline void __writew(__u16 b, volatile void __iomem *addr)
-{
-	*(__force volatile __u16 *)addr = b;
-}
-
-#define writeq(val, addr) __writeq((val), (addr))
-#define writel(val, addr) __writel((val), (addr))
-#define writew(val, addr) __writew((val), (addr))
-#define writeb(val, addr) __writeb((val), (addr))
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
-#define __raw_writeq writeq
-
 void __memcpy_fromio(void *, unsigned long, unsigned);
 void __memcpy_toio(unsigned long, const void *, unsigned);
 
diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h
index d593e14f0341..14f82bbcb5fd 100644
--- a/include/asm-x86/io_apic.h
+++ b/include/asm-x86/io_apic.h
@@ -11,6 +11,15 @@
  * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
  */
 
+/* I/O Unit Redirection Table */
+#define IO_APIC_REDIR_VECTOR_MASK	0x000FF
+#define IO_APIC_REDIR_DEST_LOGICAL	0x00800
+#define IO_APIC_REDIR_DEST_PHYSICAL	0x00000
+#define IO_APIC_REDIR_SEND_PENDING	(1 << 12)
+#define IO_APIC_REDIR_REMOTE_IRR	(1 << 14)
+#define IO_APIC_REDIR_LEVEL_TRIGGER	(1 << 15)
+#define IO_APIC_REDIR_MASKED		(1 << 16)
+
 /*
  * The structure of the IO-APIC:
  */
@@ -112,21 +121,32 @@ extern int nr_ioapic_registers[MAX_IO_APICS];
 
 #define MP_MAX_IOAPIC_PIN 127
 
-struct mp_ioapic_routing {
-	int apic_id;
-	int gsi_base;
-	int gsi_end;
-	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+struct mp_config_ioapic {
+	unsigned long mp_apicaddr;
+	unsigned int mp_apicid;
+	unsigned char mp_type;
+	unsigned char mp_apicver;
+	unsigned char mp_flags;
+};
+
+struct mp_config_intsrc {
+	unsigned int mp_dstapic;
+	unsigned char mp_type;
+	unsigned char mp_irqtype;
+	unsigned short mp_irqflag;
+	unsigned char mp_srcbus;
+	unsigned char mp_srcbusirq;
+	unsigned char mp_dstirq;
 };
 
 /* I/O APIC entries */
-extern struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
 
 /* MP IRQ source entries */
-extern struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
 /* non-0 if default (table-less) MP configuration */
 extern int mpc_default_type;
@@ -137,6 +157,9 @@ extern int sis_apic_bug;
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
+/* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
+extern int timer_through_8259;
+
 static inline void disable_ioapic_setup(void)
 {
 	skip_ioapic_setup = 1;
@@ -162,6 +185,8 @@ extern void ioapic_init_mappings(void);
 
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
+static const int timer_through_8259 = 0;
+static inline void ioapic_init_mappings(void) { }
 #endif
 
 #endif
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
index 07862fdd23c0..068c9a40aa5b 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -1,29 +1,34 @@
-#ifndef _ASM_X8664_GART_H
-#define _ASM_X8664_GART_H 1
+#ifndef _ASM_X8664_IOMMU_H
+#define _ASM_X8664_IOMMU_H 1
 
 extern void pci_iommu_shutdown(void);
 extern void no_iommu_init(void);
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
-#ifdef CONFIG_IOMMU
+
+#ifdef CONFIG_GART_IOMMU
+extern int gart_iommu_aperture;
+extern int gart_iommu_aperture_allowed;
+extern int gart_iommu_aperture_disabled;
+
+extern void early_gart_iommu_check(void);
 extern void gart_iommu_init(void);
 extern void gart_iommu_shutdown(void);
 extern void __init gart_parse_options(char *);
-extern void iommu_hole_init(void);
-extern int fallback_aper_order;
-extern int fallback_aper_force;
-extern int iommu_aperture;
-extern int iommu_aperture_allowed;
-extern int iommu_aperture_disabled;
-extern int fix_aperture;
+extern void gart_iommu_hole_init(void);
+
 #else
-#define iommu_aperture 0
-#define iommu_aperture_allowed 0
+#define gart_iommu_aperture            0
+#define gart_iommu_aperture_allowed    0
+#define gart_iommu_aperture_disabled   1
 
-static inline void gart_iommu_shutdown(void)
+static inline void early_gart_iommu_check(void)
 {
 }
 
+static inline void gart_iommu_shutdown(void)
+{
+}
 #endif
 
 #endif
diff --git a/include/asm-x86/ipi.h b/include/asm-x86/ipi.h
index ecc80f341f37..196d63c28aa4 100644
--- a/include/asm-x86/ipi.h
+++ b/include/asm-x86/ipi.h
@@ -20,6 +20,7 @@
 
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
+#include <asm/smp.h>
 
 /*
  * the following functions deal with sending IPIs between CPUs.
diff --git a/include/asm-x86/irq.h b/include/asm-x86/irq.h
index 7ba905465a53..1a2925757317 100644
--- a/include/asm-x86/irq.h
+++ b/include/asm-x86/irq.h
@@ -1,5 +1,50 @@
-#ifdef CONFIG_X86_32
-# include "irq_32.h"
+#ifndef _ASM_IRQ_H
+#define _ASM_IRQ_H
+/*
+ *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ *	IRQ/IPI changes taken from work by Thomas Radke
+ *	<tomsoft@informatik.tu-chemnitz.de>
+ */
+
+#include <asm/apicdef.h>
+#include <asm/irq_vectors.h>
+
+static inline int irq_canonicalize(int irq)
+{
+	return ((irq == 2) ? 9 : irq);
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+# define ARCH_HAS_NMI_WATCHDOG
+#endif
+
+#ifdef CONFIG_4KSTACKS
+  extern void irq_ctx_init(int cpu);
+  extern void irq_ctx_exit(int cpu);
+# define __ARCH_HAS_DO_SOFTIRQ
 #else
-# include "irq_64.h"
+# define irq_ctx_init(cpu) do { } while (0)
+# define irq_ctx_exit(cpu) do { } while (0)
+# ifdef CONFIG_X86_64
+#  define __ARCH_HAS_DO_SOFTIRQ
+# endif
+#endif
+
+#ifdef CONFIG_IRQBALANCE
+extern int irqbalance_disable(char *str);
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+#include <linux/cpumask.h>
+extern void fixup_irqs(cpumask_t map);
 #endif
+
+extern unsigned int do_IRQ(struct pt_regs *regs);
+extern void init_IRQ(void);
+extern void native_init_IRQ(void);
+
+/* Interrupt vector management */
+extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
+
+#endif /* _ASM_IRQ_H */
diff --git a/include/asm-x86/irq_32.h b/include/asm-x86/irq_32.h
deleted file mode 100644
index 0b79f3185243..000000000000
--- a/include/asm-x86/irq_32.h
+++ /dev/null
@@ -1,51 +0,0 @@
-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
-
-/*
- *	linux/include/asm/irq.h
- *
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- */
-
-#include <linux/sched.h>
-/* include comes from machine specific directory */
-#include "irq_vectors.h"
-#include <asm/thread_info.h>
-
-static inline int irq_canonicalize(int irq)
-{
-	return ((irq == 2) ? 9 : irq);
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-# define ARCH_HAS_NMI_WATCHDOG		/* See include/linux/nmi.h */
-#endif
-
-#ifdef CONFIG_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
-#else
-# define irq_ctx_init(cpu) do { } while (0)
-# define irq_ctx_exit(cpu) do { } while (0)
-#endif
-
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
-
-#ifdef CONFIG_HOTPLUG_CPU
-extern void fixup_irqs(cpumask_t map);
-#endif
-
-unsigned int do_IRQ(struct pt_regs *regs);
-void init_IRQ(void);
-void __init native_init_IRQ(void);
-
-/* Interrupt vector management */
-extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
-
-#endif /* _ASM_IRQ_H */
diff --git a/include/asm-x86/irq_64.h b/include/asm-x86/irq_64.h
deleted file mode 100644
index 083d35a62c94..000000000000
--- a/include/asm-x86/irq_64.h
+++ /dev/null
@@ -1,51 +0,0 @@
-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
-
-/*
- *	linux/include/asm/irq.h
- *
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- */
-
-#define TIMER_IRQ 0
-
-/*
- * 16 8259A IRQ's, 208 potential APIC interrupt sources.
- * Right now the APIC is mostly only used for SMP.
- * 256 vectors is an architectural limit. (we can have
- * more than 256 devices theoretically, but they will
- * have to use shared interrupts)
- * Since vectors 0x00-0x1f are used/reserved for the CPU,
- * the usable vector space is 0x20-0xff (224 vectors)
- */
-
-/*
- * The maximum number of vectors supported by x86_64 processors
- * is limited to 256. For processors other than x86_64, NR_VECTORS
- * should be changed accordingly.
- */
-#define NR_VECTORS 256
-
-#define FIRST_SYSTEM_VECTOR	0xef   /* duplicated in hw_irq.h */
-
-#define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
-#define NR_IRQ_VECTORS NR_IRQS
-
-static inline int irq_canonicalize(int irq)
-{
-	return ((irq == 2) ? 9 : irq);
-}
-
-#define ARCH_HAS_NMI_WATCHDOG		/* See include/linux/nmi.h */
-
-#ifdef CONFIG_HOTPLUG_CPU
-#include <linux/cpumask.h>
-extern void fixup_irqs(cpumask_t map);
-#endif
-
-#define __ARCH_HAS_DO_SOFTIRQ 1
-
-#endif /* _ASM_IRQ_H */
diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h
new file mode 100644
index 000000000000..90b1d1f12f08
--- /dev/null
+++ b/include/asm-x86/irq_vectors.h
@@ -0,0 +1,173 @@
+#ifndef _ASM_IRQ_VECTORS_H
+#define _ASM_IRQ_VECTORS_H
+
+#include <linux/threads.h>
+
+#define NMI_VECTOR		0x02
+
+/*
+ * IDT vectors usable for external interrupt sources start
+ * at 0x20:
+ */
+#define FIRST_EXTERNAL_VECTOR	0x20
+
+#ifdef CONFIG_X86_32
+# define SYSCALL_VECTOR		0x80
+#else
+# define IA32_SYSCALL_VECTOR	0x80
+#endif
+
+/*
+ * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
+ * cleanup after irq migration on 64 bit.
+ */
+#define IRQ_MOVE_CLEANUP_VECTOR	FIRST_EXTERNAL_VECTOR
+
+/*
+ * Vectors 0x20-0x2f are used for ISA interrupts on 32 bit.
+ * Vectors 0x30-0x3f are used for ISA interrupts on 64 bit.
+ */
+#ifdef CONFIG_X86_32
+#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR)
+#else
+#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR + 0x10)
+#endif
+#define IRQ1_VECTOR		(IRQ0_VECTOR + 1)
+#define IRQ2_VECTOR		(IRQ0_VECTOR + 2)
+#define IRQ3_VECTOR		(IRQ0_VECTOR + 3)
+#define IRQ4_VECTOR		(IRQ0_VECTOR + 4)
+#define IRQ5_VECTOR		(IRQ0_VECTOR + 5)
+#define IRQ6_VECTOR		(IRQ0_VECTOR + 6)
+#define IRQ7_VECTOR		(IRQ0_VECTOR + 7)
+#define IRQ8_VECTOR		(IRQ0_VECTOR + 8)
+#define IRQ9_VECTOR		(IRQ0_VECTOR + 9)
+#define IRQ10_VECTOR		(IRQ0_VECTOR + 10)
+#define IRQ11_VECTOR		(IRQ0_VECTOR + 11)
+#define IRQ12_VECTOR		(IRQ0_VECTOR + 12)
+#define IRQ13_VECTOR		(IRQ0_VECTOR + 13)
+#define IRQ14_VECTOR		(IRQ0_VECTOR + 14)
+#define IRQ15_VECTOR		(IRQ0_VECTOR + 15)
+
+/*
+ * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
+ *
+ *  some of the following vectors are 'rare', they are merged
+ *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
+ *  TLB, reschedule and local APIC vectors are performance-critical.
+ *
+ *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
+ */
+#ifdef CONFIG_X86_32
+
+# define SPURIOUS_APIC_VECTOR		0xff
+# define ERROR_APIC_VECTOR		0xfe
+# define INVALIDATE_TLB_VECTOR		0xfd
+# define RESCHEDULE_VECTOR		0xfc
+# define CALL_FUNCTION_VECTOR		0xfb
+# define CALL_FUNCTION_SINGLE_VECTOR	0xfa
+# define THERMAL_APIC_VECTOR		0xf0
+
+#else
+
+#define SPURIOUS_APIC_VECTOR		0xff
+#define ERROR_APIC_VECTOR		0xfe
+#define RESCHEDULE_VECTOR		0xfd
+#define CALL_FUNCTION_VECTOR		0xfc
+#define CALL_FUNCTION_SINGLE_VECTOR	0xfb
+#define THERMAL_APIC_VECTOR		0xfa
+#define THRESHOLD_APIC_VECTOR		0xf9
+#define INVALIDATE_TLB_VECTOR_END	0xf7
+#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
+
+#define NUM_INVALIDATE_TLB_VECTORS	8
+
+#endif
+
+/*
+ * Local APIC timer IRQ vector is on a different priority level,
+ * to work around the 'lost local interrupt if more than 2 IRQ
+ * sources per level' errata.
+ */
+#define LOCAL_TIMER_VECTOR	0xef
+
+/*
+ * First APIC vector available to drivers: (vectors 0x30-0xee) we
+ * start at 0x31(0x41) to spread out vectors evenly between priority
+ * levels. (0x80 is the syscall vector)
+ */
+#ifdef CONFIG_X86_32
+# define FIRST_DEVICE_VECTOR	0x31
+#else
+# define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
+#endif
+
+#define NR_VECTORS		256
+
+#define FPU_IRQ			13
+
+#define	FIRST_VM86_IRQ		3
+#define LAST_VM86_IRQ		15
+#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
+
+#if !defined(CONFIG_X86_VOYAGER)
+
+# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
+
+#  define NR_IRQS		224
+
+#  if (224 >= 32 * NR_CPUS)
+#   define NR_IRQ_VECTORS	NR_IRQS
+#  else
+#   define NR_IRQ_VECTORS	(32 * NR_CPUS)
+#  endif
+
+# else /* IO_APIC || PARAVIRT */
+
+#  define NR_IRQS		16
+#  define NR_IRQ_VECTORS	NR_IRQS
+
+# endif
+
+#else /* !VISWS && !VOYAGER */
+
+# define NR_IRQS		224
+# define NR_IRQ_VECTORS		NR_IRQS
+
+#endif /* VISWS */
+
+/* Voyager specific defines */
+/* These define the CPIs we use in linux */
+#define VIC_CPI_LEVEL0			0
+#define VIC_CPI_LEVEL1			1
+/* now the fake CPIs */
+#define VIC_TIMER_CPI			2
+#define VIC_INVALIDATE_CPI		3
+#define VIC_RESCHEDULE_CPI		4
+#define VIC_ENABLE_IRQ_CPI		5
+#define VIC_CALL_FUNCTION_CPI		6
+#define VIC_CALL_FUNCTION_SINGLE_CPI	7
+
+/* Now the QIC CPIs:  Since we don't need the two initial levels,
+ * these are 2 less than the VIC CPIs */
+#define QIC_CPI_OFFSET			1
+#define QIC_TIMER_CPI			(VIC_TIMER_CPI - QIC_CPI_OFFSET)
+#define QIC_INVALIDATE_CPI		(VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
+#define QIC_RESCHEDULE_CPI		(VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
+#define QIC_ENABLE_IRQ_CPI		(VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_CPI		(VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_SINGLE_CPI	(VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
+
+#define VIC_START_FAKE_CPI		VIC_TIMER_CPI
+#define VIC_END_FAKE_CPI		VIC_CALL_FUNCTION_SINGLE_CPI
+
+/* this is the SYS_INT CPI. */
+#define VIC_SYS_INT			8
+#define VIC_CMN_INT			15
+
+/* This is the boot CPI for alternate processors.  It gets overwritten
+ * by the above once the system has activated all available processors */
+#define VIC_CPU_BOOT_CPI		VIC_CPI_LEVEL0
+#define VIC_CPU_BOOT_ERRATA_CPI		(VIC_CPI_LEVEL0 + 8)
+
+
+#endif /* _ASM_IRQ_VECTORS_H */
diff --git a/include/asm-x86/irqflags.h b/include/asm-x86/irqflags.h
index c242527f970e..424acb48cd61 100644
--- a/include/asm-x86/irqflags.h
+++ b/include/asm-x86/irqflags.h
@@ -111,14 +111,35 @@ static inline unsigned long __raw_local_irq_save(void)
 #define DISABLE_INTERRUPTS(x)	cli
 
 #ifdef CONFIG_X86_64
+#define SWAPGS	swapgs
+/*
+ * Currently paravirt can't handle swapgs nicely when we
+ * don't have a stack we can rely on (such as a user space
+ * stack).  So we either find a way around these or just fault
+ * and emulate if a guest tries to call swapgs directly.
+ *
+ * Either way, this is a good way to document that we don't
+ * have a reliable stack. x86_64 only.
+ */
+#define SWAPGS_UNSAFE_STACK	swapgs
+
+#define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
+
 #define INTERRUPT_RETURN	iretq
-#define ENABLE_INTERRUPTS_SYSCALL_RET			\
-			movq	%gs:pda_oldrsp, %rsp;	\
-			swapgs;				\
-			sysretq;
+#define USERGS_SYSRET64				\
+	swapgs;					\
+	sysretq;
+#define USERGS_SYSRET32				\
+	swapgs;					\
+	sysretl
+#define ENABLE_INTERRUPTS_SYSEXIT32		\
+	swapgs;					\
+	sti;					\
+	sysexit
+
 #else
 #define INTERRUPT_RETURN		iret
-#define ENABLE_INTERRUPTS_SYSCALL_RET	sti; sysexit
+#define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit
 #define GET_CR0_INTO_EAX		movl %cr0, %eax
 #endif
 
@@ -169,18 +190,6 @@ static inline void trace_hardirqs_fixup(void)
 #else
 
 #ifdef CONFIG_X86_64
-/*
- * Currently paravirt can't handle swapgs nicely when we
- * don't have a stack we can rely on (such as a user space
- * stack).  So we either find a way around these or just fault
- * and emulate if a guest tries to call swapgs directly.
- *
- * Either way, this is a good way to document that we don't
- * have a reliable stack. x86_64 only.
- */
-#define SWAPGS_UNSAFE_STACK	swapgs
-#define ARCH_TRACE_IRQS_ON		call trace_hardirqs_on_thunk
-#define ARCH_TRACE_IRQS_OFF		call trace_hardirqs_off_thunk
 #define ARCH_LOCKDEP_SYS_EXIT		call lockdep_sys_exit_thunk
 #define ARCH_LOCKDEP_SYS_EXIT_IRQ	\
 	TRACE_IRQS_ON; \
@@ -192,24 +201,6 @@ static inline void trace_hardirqs_fixup(void)
 	TRACE_IRQS_OFF;
 
 #else
-#define ARCH_TRACE_IRQS_ON			\
-	pushl %eax;				\
-	pushl %ecx;				\
-	pushl %edx;				\
-	call trace_hardirqs_on;			\
-	popl %edx;				\
-	popl %ecx;				\
-	popl %eax;
-
-#define ARCH_TRACE_IRQS_OFF			\
-	pushl %eax;				\
-	pushl %ecx;				\
-	pushl %edx;				\
-	call trace_hardirqs_off;		\
-	popl %edx;				\
-	popl %ecx;				\
-	popl %eax;
-
 #define ARCH_LOCKDEP_SYS_EXIT			\
 	pushl %eax;				\
 	pushl %ecx;				\
@@ -223,8 +214,8 @@ static inline void trace_hardirqs_fixup(void)
 #endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
-#  define TRACE_IRQS_ON		ARCH_TRACE_IRQS_ON
-#  define TRACE_IRQS_OFF	ARCH_TRACE_IRQS_OFF
+#  define TRACE_IRQS_ON		call trace_hardirqs_on_thunk;
+#  define TRACE_IRQS_OFF	call trace_hardirqs_off_thunk;
 #else
 #  define TRACE_IRQS_ON
 #  define TRACE_IRQS_OFF
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
index bfd9900742bf..76f392146daa 100644
--- a/include/asm-x86/kvm_para.h
+++ b/include/asm-x86/kvm_para.h
@@ -71,7 +71,8 @@ static inline long kvm_hypercall0(unsigned int nr)
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr));
+		     : "a"(nr)
+		     : "memory");
 	return ret;
 }
 
@@ -80,7 +81,8 @@ static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr), "b"(p1));
+		     : "a"(nr), "b"(p1)
+		     : "memory");
 	return ret;
 }
 
@@ -90,7 +92,8 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2));
+		     : "a"(nr), "b"(p1), "c"(p2)
+		     : "memory");
 	return ret;
 }
 
@@ -100,7 +103,8 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3));
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
+		     : "memory");
 	return ret;
 }
 
@@ -111,7 +115,8 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 	long ret;
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4));
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)
+		     : "memory");
 	return ret;
 }
 
diff --git a/include/asm-x86/mach-bigsmp/mach_apic.h b/include/asm-x86/mach-bigsmp/mach_apic.h
index 8327907c79bf..017c8c19ad8f 100644
--- a/include/asm-x86/mach-bigsmp/mach_apic.h
+++ b/include/asm-x86/mach-bigsmp/mach_apic.h
@@ -81,7 +81,7 @@ static inline int multi_timer_check(int apic, int irq)
 
 static inline int apicid_to_node(int logical_apicid)
 {
-	return (0);
+	return apicid_2_node[hard_smp_processor_id()];
 }
 
 static inline int cpu_present_to_apicid(int mps_cpu)
diff --git a/include/asm-x86/mach-bigsmp/mach_mpspec.h b/include/asm-x86/mach-bigsmp/mach_mpspec.h
deleted file mode 100644
index 6b5dadcf1d0e..000000000000
--- a/include/asm-x86/mach-bigsmp/mach_mpspec.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-#define MAX_MP_BUSSES 32
-
-#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-default/entry_arch.h b/include/asm-x86/mach-default/entry_arch.h
index bc861469bdba..9283b60a1dd2 100644
--- a/include/asm-x86/mach-default/entry_arch.h
+++ b/include/asm-x86/mach-default/entry_arch.h
@@ -13,6 +13,7 @@
 BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
 BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
+BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 #endif
 
 /*
diff --git a/include/asm-x86/mach-default/irq_vectors.h b/include/asm-x86/mach-default/irq_vectors.h
deleted file mode 100644
index 881c63ca61ad..000000000000
--- a/include/asm-x86/mach-default/irq_vectors.h
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * This file should contain #defines for all of the interrupt vector
- * numbers used by this architecture.
- *
- * In addition, there are some standard defines:
- *
- *	FIRST_EXTERNAL_VECTOR:
- *		The first free place for external interrupts
- *
- *	SYSCALL_VECTOR:
- *		The IRQ vector a syscall makes the user to kernel transition
- *		under.
- *
- *	TIMER_IRQ:
- *		The IRQ number the timer interrupt comes in at.
- *
- *	NR_IRQS:
- *		The total number of interrupt vectors (including all the
- *		architecture specific interrupts) needed.
- *
- */			
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR	0x20
-
-#define SYSCALL_VECTOR		0x80
-
-/*
- * Vectors 0x20-0x2f are used for ISA interrupts.
- */
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
- */
-#define SPURIOUS_APIC_VECTOR	0xff
-#define ERROR_APIC_VECTOR	0xfe
-#define INVALIDATE_TLB_VECTOR	0xfd
-#define RESCHEDULE_VECTOR	0xfc
-#define CALL_FUNCTION_VECTOR	0xfb
-
-#define THERMAL_APIC_VECTOR	0xf0
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR	0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x31 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR	0x31
-#define FIRST_SYSTEM_VECTOR	0xef
-
-#define TIMER_IRQ 0
-
-/*
- * 16 8259A IRQ's, 208 potential APIC interrupt sources.
- * Right now the APIC is mostly only used for SMP.
- * 256 vectors is an architectural limit. (we can have
- * more than 256 devices theoretically, but they will
- * have to use shared interrupts)
- * Since vectors 0x00-0x1f are used/reserved for the CPU,
- * the usable vector space is 0x20-0xff (224 vectors)
- */
-
-/*
- * The maximum number of vectors supported by i386 processors
- * is limited to 256. For processors other than i386, NR_VECTORS
- * should be changed accordingly.
- */
-#define NR_VECTORS 256
-
-#include "irq_vectors_limits.h"
-
-#define FPU_IRQ			13
-
-#define	FIRST_VM86_IRQ		3
-#define LAST_VM86_IRQ		15
-#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
-
-
-#endif /* _ASM_IRQ_VECTORS_H */
diff --git a/include/asm-x86/mach-default/irq_vectors_limits.h b/include/asm-x86/mach-default/irq_vectors_limits.h
deleted file mode 100644
index a90c7a60109f..000000000000
--- a/include/asm-x86/mach-default/irq_vectors_limits.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
-
-#if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT)
-#define NR_IRQS 224
-# if (224 >= 32 * NR_CPUS)
-# define NR_IRQ_VECTORS NR_IRQS
-# else
-# define NR_IRQ_VECTORS (32 * NR_CPUS)
-# endif
-#else
-#define NR_IRQS 16
-#define NR_IRQ_VECTORS NR_IRQS
-#endif
-
-#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/mach-default/mach_apic.h b/include/asm-x86/mach-default/mach_apic.h
index 21003b56ae95..0b2cde5e1b74 100644
--- a/include/asm-x86/mach-default/mach_apic.h
+++ b/include/asm-x86/mach-default/mach_apic.h
@@ -77,7 +77,11 @@ static inline void setup_apic_routing(void)
 
 static inline int apicid_to_node(int logical_apicid)
 {
+#ifdef CONFIG_SMP
+	return apicid_2_node[hard_smp_processor_id()];
+#else
 	return 0;
+#endif
 }
 #endif
 
diff --git a/include/asm-x86/mach-default/setup_arch.h b/include/asm-x86/mach-default/setup_arch.h
index 605e3ccb991b..38846208b548 100644
--- a/include/asm-x86/mach-default/setup_arch.h
+++ b/include/asm-x86/mach-default/setup_arch.h
@@ -1,7 +1,3 @@
 /* Hook to call BIOS initialisation function */
 
 /* no action for generic */
-
-#ifndef ARCH_SETUP
-#define ARCH_SETUP
-#endif
diff --git a/include/asm-x86/mach-default/smpboot_hooks.h b/include/asm-x86/mach-default/smpboot_hooks.h
index 56d0e1fa0258..56d001b9dce4 100644
--- a/include/asm-x86/mach-default/smpboot_hooks.h
+++ b/include/asm-x86/mach-default/smpboot_hooks.h
@@ -3,7 +3,9 @@
 
 static inline void smpboot_clear_io_apic_irqs(void)
 {
+#ifdef CONFIG_X86_IO_APIC
 	io_apic_irqs = 0;
+#endif
 }
 
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
@@ -35,17 +37,23 @@ static inline void smpboot_restore_warm_reset_vector(void)
 
 static inline void __init smpboot_setup_io_apic(void)
 {
+#ifdef CONFIG_X86_IO_APIC
 	/*
 	 * Here we can be sure that there is an IO-APIC in the system. Let's
 	 * go and set it up:
 	 */
 	if (!skip_ioapic_setup && nr_ioapics)
 		setup_IO_APIC();
-	else
+	else {
 		nr_ioapics = 0;
+		localise_nmi_watchdog();
+	}
+#endif
 }
 
 static inline void smpboot_clear_io_apic(void)
 {
+#ifdef CONFIG_X86_IO_APIC
 	nr_ioapics = 0;
+#endif
 }
diff --git a/include/asm-x86/mach-es7000/mach_mpspec.h b/include/asm-x86/mach-es7000/mach_mpspec.h
deleted file mode 100644
index b1f5039d4506..000000000000
--- a/include/asm-x86/mach-es7000/mach_mpspec.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-#define MAX_MP_BUSSES 256
-
-#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-generic/mach_mpparse.h b/include/asm-x86/mach-generic/mach_mpparse.h
index 0d0b5ba2e9d1..586cadbf3787 100644
--- a/include/asm-x86/mach-generic/mach_mpparse.h
+++ b/include/asm-x86/mach-generic/mach_mpparse.h
@@ -1,7 +1,10 @@
 #ifndef _MACH_MPPARSE_H
 #define _MACH_MPPARSE_H 1
 
-int mps_oem_check(struct mp_config_table *mpc, char *oem, char *productid); 
-int acpi_madt_oem_check(char *oem_id, char *oem_table_id); 
+
+extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
+			 char *productid);
+
+extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
 
 #endif
diff --git a/include/asm-x86/mach-numaq/mach_apic.h b/include/asm-x86/mach-numaq/mach_apic.h
index 75a56e5afbe7..d802465e026a 100644
--- a/include/asm-x86/mach-numaq/mach_apic.h
+++ b/include/asm-x86/mach-numaq/mach_apic.h
@@ -20,8 +20,14 @@ static inline cpumask_t target_cpus(void)
 #define INT_DELIVERY_MODE dest_LowestPrio
 #define INT_DEST_MODE 0     /* physical delivery on LOCAL quad */
  
-#define check_apicid_used(bitmap, apicid) physid_isset(apicid, bitmap)
-#define check_apicid_present(bit) physid_isset(bit, phys_cpu_present_map)
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+	return physid_isset(apicid, bitmap);
+}
+static inline unsigned long check_apicid_present(int bit)
+{
+	return physid_isset(bit, phys_cpu_present_map);
+}
 #define apicid_cluster(apicid) (apicid & 0xF0)
 
 static inline int apic_id_registered(void)
@@ -77,11 +83,6 @@ static inline int cpu_present_to_apicid(int mps_cpu)
 		return BAD_APICID;
 }
 
-static inline int generate_logical_apicid(int quad, int phys_apicid)
-{
-	return (quad << 4) + (phys_apicid ? phys_apicid << 1 : 1);
-}
-
 static inline int apicid_to_node(int logical_apicid) 
 {
 	return logical_apicid >> 4;
@@ -95,30 +96,6 @@ static inline physid_mask_t apicid_to_cpu_present(int logical_apicid)
 	return physid_mask_of_physid(cpu + 4*node);
 }
 
-struct mpc_config_translation {
-	unsigned char mpc_type;
-	unsigned char trans_len;
-	unsigned char trans_type;
-	unsigned char trans_quad;
-	unsigned char trans_global;
-	unsigned char trans_local;
-	unsigned short trans_reserved;
-};
-
-static inline int mpc_apic_id(struct mpc_config_processor *m, 
-			struct mpc_config_translation *translation_record)
-{
-	int quad = translation_record->trans_quad;
-	int logical_apicid = generate_logical_apicid(quad, m->mpc_apicid);
-
-	printk("Processor #%d %u:%u APIC version %d (quad %d, apic %d)\n",
-	       m->mpc_apicid,
-	       (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
-	       (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
-	       m->mpc_apicver, quad, logical_apicid);
-	return logical_apicid;
-}
-
 extern void *xquad_portio;
 
 static inline void setup_portio_remap(void)
diff --git a/include/asm-x86/mach-numaq/mach_mpparse.h b/include/asm-x86/mach-numaq/mach_mpparse.h
index 459b12401187..626aef6b155f 100644
--- a/include/asm-x86/mach-numaq/mach_mpparse.h
+++ b/include/asm-x86/mach-numaq/mach_mpparse.h
@@ -1,14 +1,7 @@
 #ifndef __ASM_MACH_MPPARSE_H
 #define __ASM_MACH_MPPARSE_H
 
-extern void mpc_oem_bus_info(struct mpc_config_bus *m, char *name,
-			     struct mpc_config_translation *translation);
-extern void mpc_oem_pci_bus(struct mpc_config_bus *m,
-	struct mpc_config_translation *translation);
-
-/* Hook from generic ACPI tables.c */
-static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-}
+extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
+				char *productid);
 
 #endif /* __ASM_MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-numaq/mach_mpspec.h b/include/asm-x86/mach-numaq/mach_mpspec.h
deleted file mode 100644
index dffb09856f8f..000000000000
--- a/include/asm-x86/mach-numaq/mach_mpspec.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 512
-
-#define MAX_MP_BUSSES 32
-
-#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-summit/mach_mpspec.h b/include/asm-x86/mach-summit/mach_mpspec.h
deleted file mode 100644
index bd765523511a..000000000000
--- a/include/asm-x86/mach-summit/mach_mpspec.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-/* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */
-#define MAX_MP_BUSSES 260
-
-#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-visws/entry_arch.h b/include/asm-x86/mach-visws/entry_arch.h
index b183fa6d83d9..86be554342d4 100644
--- a/include/asm-x86/mach-visws/entry_arch.h
+++ b/include/asm-x86/mach-visws/entry_arch.h
@@ -1,23 +1,5 @@
 /*
- * The following vectors are part of the Linux architecture, there
- * is no hardware IRQ pin equivalent for them, they are triggered
- * through the ICC by us (IPIs)
+ * VISWS uses the standard Linux entry points:
  */
-#ifdef CONFIG_X86_SMP
-BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
-BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
-#endif
 
-/*
- * every pentium local APIC has two 'local interrupts', with a
- * soft-definable vector attached to both interrupts, one of
- * which is a timer interrupt, the other one is error counter
- * overflow. Linux uses the local APIC timer interrupt to get
- * a much simpler SMP time architecture:
- */
-#ifdef CONFIG_X86_LOCAL_APIC
-BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
-BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
-BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
-#endif
+#include "../mach-default/entry_arch.h"
diff --git a/include/asm-x86/mach-visws/irq_vectors.h b/include/asm-x86/mach-visws/irq_vectors.h
deleted file mode 100644
index cb572d8db505..000000000000
--- a/include/asm-x86/mach-visws/irq_vectors.h
+++ /dev/null
@@ -1,62 +0,0 @@
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR	0x20
-
-#define SYSCALL_VECTOR		0x80
-
-/*
- * Vectors 0x20-0x2f are used for ISA interrupts.
- */
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
- */
-#define SPURIOUS_APIC_VECTOR	0xff
-#define ERROR_APIC_VECTOR	0xfe
-#define INVALIDATE_TLB_VECTOR	0xfd
-#define RESCHEDULE_VECTOR	0xfc
-#define CALL_FUNCTION_VECTOR	0xfb
-
-#define THERMAL_APIC_VECTOR	0xf0
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR	0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x31 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR	0x31
-#define FIRST_SYSTEM_VECTOR	0xef
-
-#define TIMER_IRQ 0
-
-/*
- * IRQ definitions
- */
-#define NR_VECTORS 256
-#define NR_IRQS 224
-#define NR_IRQ_VECTORS NR_IRQS
-
-#define FPU_IRQ			13
-
-#define	FIRST_VM86_IRQ		3
-#define LAST_VM86_IRQ		15
-#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
-
-#endif /* _ASM_IRQ_VECTORS_H */
diff --git a/include/asm-x86/mach-visws/mach_apic.h b/include/asm-x86/mach-visws/mach_apic.h
index a9ef33a8a995..6943e7a1d0e6 100644
--- a/include/asm-x86/mach-visws/mach_apic.h
+++ b/include/asm-x86/mach-visws/mach_apic.h
@@ -1,103 +1 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
-
-#include <mach_apicdef.h>
-#include <asm/smp.h>
-
-#define APIC_DFR_VALUE	(APIC_DFR_FLAT)
-
-#define no_balance_irq (0)
-#define esr_disable (0)
-
-#define INT_DELIVERY_MODE dest_LowestPrio
-#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-
-#ifdef CONFIG_SMP
- #define TARGET_CPUS cpu_online_map
-#else
- #define TARGET_CPUS cpumask_of_cpu(0)
-#endif
-
-#define check_apicid_used(bitmap, apicid)	physid_isset(apicid, bitmap)
-#define check_apicid_present(bit)		physid_isset(bit, phys_cpu_present_map)
-
-static inline int apic_id_registered(void)
-{
-	return physid_isset(GET_APIC_ID(read_apic_id()), phys_cpu_present_map);
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-
-	apic_write_around(APIC_DFR, APIC_DFR_VALUE);
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
-	apic_write_around(APIC_LDR, val);
-}
-
-static inline void summit_check(char *oem, char *productid) 
-{
-}
-
-static inline void setup_apic_routing(void)
-{
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-	return 0;
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-	return 1 << cpu;
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < get_physical_broadcast())
-		return mps_cpu;
-	else
-		return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int apicid)
-{
-	return physid_mask_of_physid(apicid);
-}
-
-#define WAKE_SECONDARY_VIA_INIT
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
-}
-
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
-{
-	return cpus_addr(cpumask)[0];
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_MACH_APIC_H */
+#include "../mach-default/mach_apic.h"
diff --git a/include/asm-x86/mach-visws/mach_apicdef.h b/include/asm-x86/mach-visws/mach_apicdef.h
index 826cfa97d778..42711d152a93 100644
--- a/include/asm-x86/mach-visws/mach_apicdef.h
+++ b/include/asm-x86/mach-visws/mach_apicdef.h
@@ -1,12 +1 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
-
-#define         APIC_ID_MASK            (0xF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	        return (((x)>>24)&0xF);
-}
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
+#include "../mach-default/mach_apicdef.h"
diff --git a/include/asm-x86/mach-visws/setup_arch.h b/include/asm-x86/mach-visws/setup_arch.h
index 33f700ef6831..fa4766ca2d10 100644
--- a/include/asm-x86/mach-visws/setup_arch.h
+++ b/include/asm-x86/mach-visws/setup_arch.h
@@ -1,8 +1 @@
-/* Hook to call BIOS initialisation function */
-
-extern unsigned long sgivwfb_mem_phys;
-extern unsigned long sgivwfb_mem_size;
-
-/* no action for visws */
-
-#define ARCH_SETUP
+#include "../mach-default/setup_arch.h"
diff --git a/include/asm-x86/mach-visws/smpboot_hooks.h b/include/asm-x86/mach-visws/smpboot_hooks.h
index c9b83e395a2e..e4433ca88715 100644
--- a/include/asm-x86/mach-visws/smpboot_hooks.h
+++ b/include/asm-x86/mach-visws/smpboot_hooks.h
@@ -1,28 +1 @@
-static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
-{
-	CMOS_WRITE(0xa, 0xf);
-	local_flush_tlb();
-	Dprintk("1.\n");
-	*((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
-	Dprintk("2.\n");
-	*((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
-	Dprintk("3.\n");
-}
-
-/* for visws do nothing for any of these */
-
-static inline void smpboot_clear_io_apic_irqs(void)
-{
-}
-
-static inline void smpboot_restore_warm_reset_vector(void)
-{
-}
-
-static inline void smpboot_setup_io_apic(void)
-{
-}
-
-static inline void smpboot_clear_io_apic(void)
-{
-}
+#include "../mach-default/smpboot_hooks.h"
diff --git a/include/asm-x86/mach-voyager/entry_arch.h b/include/asm-x86/mach-voyager/entry_arch.h
index 4a1e1e8c10b6..ae52624b5937 100644
--- a/include/asm-x86/mach-voyager/entry_arch.h
+++ b/include/asm-x86/mach-voyager/entry_arch.h
@@ -23,4 +23,4 @@ BUILD_INTERRUPT(qic_invalidate_interrupt, QIC_INVALIDATE_CPI);
 BUILD_INTERRUPT(qic_reschedule_interrupt, QIC_RESCHEDULE_CPI);
 BUILD_INTERRUPT(qic_enable_irq_interrupt, QIC_ENABLE_IRQ_CPI);
 BUILD_INTERRUPT(qic_call_function_interrupt, QIC_CALL_FUNCTION_CPI);
-
+BUILD_INTERRUPT(qic_call_function_single_interrupt, QIC_CALL_FUNCTION_SINGLE_CPI);
diff --git a/include/asm-x86/mach-voyager/irq_vectors.h b/include/asm-x86/mach-voyager/irq_vectors.h
deleted file mode 100644
index 165421f5821c..000000000000
--- a/include/asm-x86/mach-voyager/irq_vectors.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 2002
- *
- * Author: James.Bottomley@HansenPartnership.com
- *
- * linux/arch/i386/voyager/irq_vectors.h
- *
- * This file provides definitions for the VIC and QIC CPIs
- */
-
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR	0x20
-
-#define SYSCALL_VECTOR		0x80
-
-/*
- * Vectors 0x20-0x2f are used for ISA interrupts.
- */
-
-/* These define the CPIs we use in linux */
-#define VIC_CPI_LEVEL0			0
-#define VIC_CPI_LEVEL1			1
-/* now the fake CPIs */
-#define VIC_TIMER_CPI			2
-#define VIC_INVALIDATE_CPI		3
-#define VIC_RESCHEDULE_CPI		4
-#define VIC_ENABLE_IRQ_CPI		5
-#define VIC_CALL_FUNCTION_CPI		6
-
-/* Now the QIC CPIs:  Since we don't need the two initial levels,
- * these are 2 less than the VIC CPIs */
-#define QIC_CPI_OFFSET			1
-#define QIC_TIMER_CPI			(VIC_TIMER_CPI - QIC_CPI_OFFSET)
-#define QIC_INVALIDATE_CPI		(VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
-#define QIC_RESCHEDULE_CPI		(VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
-#define QIC_ENABLE_IRQ_CPI		(VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_CPI		(VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
-
-#define VIC_START_FAKE_CPI		VIC_TIMER_CPI
-#define VIC_END_FAKE_CPI		VIC_CALL_FUNCTION_CPI
-
-/* this is the SYS_INT CPI. */
-#define VIC_SYS_INT			8
-#define VIC_CMN_INT			15
-
-/* This is the boot CPI for alternate processors.  It gets overwritten
- * by the above once the system has activated all available processors */
-#define VIC_CPU_BOOT_CPI		VIC_CPI_LEVEL0
-#define VIC_CPU_BOOT_ERRATA_CPI		(VIC_CPI_LEVEL0 + 8)
-
-#define NR_VECTORS 256
-#define NR_IRQS 224
-#define NR_IRQ_VECTORS NR_IRQS
-
-#define FPU_IRQ				13
-
-#define	FIRST_VM86_IRQ		3
-#define LAST_VM86_IRQ		15
-#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
-
-#ifndef __ASSEMBLY__
-extern asmlinkage void vic_cpi_interrupt(void);
-extern asmlinkage void vic_sys_interrupt(void);
-extern asmlinkage void vic_cmn_interrupt(void);
-extern asmlinkage void qic_timer_interrupt(void);
-extern asmlinkage void qic_invalidate_interrupt(void);
-extern asmlinkage void qic_reschedule_interrupt(void);
-extern asmlinkage void qic_enable_irq_interrupt(void);
-extern asmlinkage void qic_call_function_interrupt(void);
-#endif /* !__ASSEMBLY__ */
-
-#endif /* _ASM_IRQ_VECTORS_H */
diff --git a/include/asm-x86/mmconfig.h b/include/asm-x86/mmconfig.h
new file mode 100644
index 000000000000..95beda07c6fa
--- /dev/null
+++ b/include/asm-x86/mmconfig.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_MMCONFIG_H
+#define _ASM_MMCONFIG_H
+
+#ifdef CONFIG_PCI_MMCONFIG
+extern void __cpuinit fam10h_check_enable_mmcfg(void);
+extern void __init check_enable_amd_mmconf_dmi(void);
+#else
+static inline void fam10h_check_enable_mmcfg(void) { }
+static inline void check_enable_amd_mmconf_dmi(void) { }
+#endif
+
+#endif
diff --git a/include/asm-x86/mmu_context.h b/include/asm-x86/mmu_context.h
index 6598450da6c6..fac57014e7c6 100644
--- a/include/asm-x86/mmu_context.h
+++ b/include/asm-x86/mmu_context.h
@@ -1,5 +1,37 @@
+#ifndef __ASM_X86_MMU_CONTEXT_H
+#define __ASM_X86_MMU_CONTEXT_H
+
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/paravirt.h>
+#ifndef CONFIG_PARAVIRT
+#include <asm-generic/mm_hooks.h>
+
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+					struct mm_struct *next)
+{
+}
+#endif	/* !CONFIG_PARAVIRT */
+
+/*
+ * Used for LDT copy/destruction.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
+
 #ifdef CONFIG_X86_32
 # include "mmu_context_32.h"
 #else
 # include "mmu_context_64.h"
 #endif
+
+#define activate_mm(prev, next)			\
+do {						\
+	paravirt_activate_mm((prev), (next));	\
+	switch_mm((prev), (next), NULL);	\
+} while (0);
+
+
+#endif /* __ASM_X86_MMU_CONTEXT_H */
diff --git a/include/asm-x86/mmu_context_32.h b/include/asm-x86/mmu_context_32.h
index 9756ae0f1dd3..824fc575c6d8 100644
--- a/include/asm-x86/mmu_context_32.h
+++ b/include/asm-x86/mmu_context_32.h
@@ -1,28 +1,6 @@
 #ifndef __I386_SCHED_H
 #define __I386_SCHED_H
 
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/paravirt.h>
-#ifndef CONFIG_PARAVIRT
-#include <asm-generic/mm_hooks.h>
-
-static inline void paravirt_activate_mm(struct mm_struct *prev,
-					struct mm_struct *next)
-{
-}
-#endif	/* !CONFIG_PARAVIRT */
-
-
-/*
- * Used for LDT copy/destruction.
- */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
-
-
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 #ifdef CONFIG_SMP
@@ -75,10 +53,4 @@ static inline void switch_mm(struct mm_struct *prev,
 #define deactivate_mm(tsk, mm)			\
 	asm("movl %0,%%gs": :"r" (0));
 
-#define activate_mm(prev, next)			\
-do {						\
-	paravirt_activate_mm((prev), (next));	\
-	switch_mm((prev), (next), NULL);	\
-} while (0);
-
 #endif
diff --git a/include/asm-x86/mmu_context_64.h b/include/asm-x86/mmu_context_64.h
index ca44c71e7fb3..c7000634ccae 100644
--- a/include/asm-x86/mmu_context_64.h
+++ b/include/asm-x86/mmu_context_64.h
@@ -1,21 +1,7 @@
 #ifndef __X86_64_MMU_CONTEXT_H
 #define __X86_64_MMU_CONTEXT_H
 
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/pgalloc.h>
 #include <asm/pda.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#ifndef CONFIG_PARAVIRT
-#include <asm-generic/mm_hooks.h>
-#endif
-
-/*
- * possibly do the LDT unload here?
- */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
@@ -65,8 +51,4 @@ do {						\
 	asm volatile("movl %0,%%fs"::"r"(0));	\
 } while (0)
 
-#define activate_mm(prev, next)			\
-	switch_mm((prev), (next), NULL)
-
-
 #endif
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
index cb2cad0b65a7..b2298a227567 100644
--- a/include/asm-x86/mmzone_32.h
+++ b/include/asm-x86/mmzone_32.h
@@ -12,11 +12,9 @@
 extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)	(node_data[nid])
 
-#ifdef CONFIG_X86_NUMAQ
-	#include <asm/numaq.h>
-#elif defined(CONFIG_ACPI_SRAT)/* summit or generic arch */
-	#include <asm/srat.h>
-#endif
+#include <asm/numaq.h>
+/* summit or generic arch */
+#include <asm/srat.h>
 
 extern int get_memcfg_numa_flat(void);
 /*
@@ -26,28 +24,20 @@ extern int get_memcfg_numa_flat(void);
  */
 static inline void get_memcfg_numa(void)
 {
-#ifdef CONFIG_X86_NUMAQ
+
 	if (get_memcfg_numaq())
 		return;
-#elif defined(CONFIG_ACPI_SRAT)
 	if (get_memcfg_from_srat())
 		return;
-#endif
-
 	get_memcfg_numa_flat();
 }
 
 extern int early_pfn_to_nid(unsigned long pfn);
-extern void numa_kva_reserve(void);
 
 #else /* !CONFIG_NUMA */
 
 #define get_memcfg_numa get_memcfg_numa_flat
-#define get_zholes_size(n) (0)
 
-static inline void numa_kva_reserve(void)
-{
-}
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DISCONTIGMEM
@@ -55,14 +45,14 @@ static inline void numa_kva_reserve(void)
 /*
  * generic node memory support, the following assumptions apply:
  *
- * 1) memory comes in 256Mb contigious chunks which are either present or not
+ * 1) memory comes in 64Mb contigious chunks which are either present or not
  * 2) we will not have more than 64Gb in total
  *
  * for now assume that 64Gb is max amount of RAM for whole system
  *    64Gb / 4096bytes/page = 16777216 pages
  */
 #define MAX_NR_PAGES 16777216
-#define MAX_ELEMENTS 256
+#define MAX_ELEMENTS 1024
 #define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
 
 extern s8 physnode_map[];
@@ -87,9 +77,6 @@ static inline int pfn_to_nid(unsigned long pfn)
 	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
 })
 
-#ifdef CONFIG_X86_NUMAQ            /* we have contiguous memory on NUMA-Q */
-#define pfn_valid(pfn)          ((pfn) < num_physpages)
-#else
 static inline int pfn_valid(int pfn)
 {
 	int nid = pfn_to_nid(pfn);
@@ -98,7 +85,6 @@ static inline int pfn_valid(int pfn)
 		return (pfn < node_end_pfn(nid));
 	return 0;
 }
-#endif /* CONFIG_X86_NUMAQ */
 
 #endif /* CONFIG_DISCONTIGMEM */
 
diff --git a/include/asm-x86/mpspec.h b/include/asm-x86/mpspec.h
index 57a991b9c053..b6995e567fcc 100644
--- a/include/asm-x86/mpspec.h
+++ b/include/asm-x86/mpspec.h
@@ -13,6 +13,12 @@ extern int apic_version[MAX_APICS];
 extern u8 apicid_2_node[];
 extern int pic_mode;
 
+#ifdef CONFIG_X86_NUMAQ
+extern int mp_bus_id_to_node[MAX_MP_BUSSES];
+extern int mp_bus_id_to_local[MAX_MP_BUSSES];
+extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
+#endif
+
 #define MAX_APICID 256
 
 #else
@@ -21,26 +27,30 @@ extern int pic_mode;
 /* Each PCI slot may be a combo card with its own bus.  4 IRQ pins per slot. */
 #define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4)
 
+#endif
+
 extern void early_find_smp_config(void);
 extern void early_get_smp_config(void);
 
-#endif
-
 #if defined(CONFIG_MCA) || defined(CONFIG_EISA)
 extern int mp_bus_id_to_type[MAX_MP_BUSSES];
 #endif
 
 extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
-extern int mp_bus_id_to_pci_bus[MAX_MP_BUSSES];
-
 extern unsigned int boot_cpu_physical_apicid;
+extern unsigned int max_physical_apicid;
 extern int smp_found_config;
 extern int mpc_default_type;
 extern unsigned long mp_lapic_addr;
 
 extern void find_smp_config(void);
 extern void get_smp_config(void);
+#ifdef CONFIG_X86_MPPARSE
+extern void early_reserve_e820_mpc_new(void);
+#else
+static inline void early_reserve_e820_mpc_new(void) { }
+#endif
 
 void __cpuinit generic_processor_info(int apicid, int version);
 #ifdef CONFIG_ACPI
@@ -49,6 +59,17 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 				   u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
 extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+#ifdef CONFIG_X86_IO_APIC
+extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
+				u32 gsi, int triggering, int polarity);
+#else
+static inline int
+mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
+		   u32 gsi, int triggering, int polarity)
+{
+	return 0;
+}
+#endif
 #endif /* CONFIG_ACPI */
 
 #define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_APICS)
@@ -101,6 +122,7 @@ typedef struct physid_mask physid_mask_t;
 		__physid_mask;						\
 	})
 
+/* Note: will create very large stack frames if physid_mask_t is big */
 #define physid_mask_of_physid(physid)					\
 	({								\
 		physid_mask_t __physid_mask = PHYSID_MASK_NONE;		\
@@ -108,6 +130,12 @@ typedef struct physid_mask physid_mask_t;
 		__physid_mask;						\
 	})
 
+static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
+{
+	physids_clear(*map);
+	physid_set(physid, *map);
+}
+
 #define PHYSID_MASK_ALL		{ {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} }
 #define PHYSID_MASK_NONE	{ {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} }
 
diff --git a/include/asm-x86/mpspec_def.h b/include/asm-x86/mpspec_def.h
index dc6ef85e3624..38d1e73b49e4 100644
--- a/include/asm-x86/mpspec_def.h
+++ b/include/asm-x86/mpspec_def.h
@@ -17,10 +17,11 @@
 # define MAX_MPC_ENTRY 1024
 # define MAX_APICS      256
 #else
-/*
- * A maximum of 255 APICs with the current APIC ID architecture.
- */
-# define MAX_APICS 255
+# if NR_CPUS <= 255
+#  define MAX_APICS     255
+# else
+#  define MAX_APICS   32768
+# endif
 #endif
 
 struct intel_mp_floating {
diff --git a/include/asm-x86/msr-index.h b/include/asm-x86/msr-index.h
index 09413ad39d3c..44bce773012e 100644
--- a/include/asm-x86/msr-index.h
+++ b/include/asm-x86/msr-index.h
@@ -111,7 +111,9 @@
 #define MSR_K8_TOP_MEM2			0xc001001d
 #define MSR_K8_SYSCFG			0xc0010010
 #define MSR_K8_HWCR			0xc0010015
-#define MSR_K8_ENABLE_C1E		0xc0010055
+#define MSR_K8_INT_PENDING_MSG		0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK		0x18000000
 #define MSR_K8_TSEG_ADDR		0xc0010112
 #define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
 #define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
index 3707650a169b..ca110ee73f07 100644
--- a/include/asm-x86/msr.h
+++ b/include/asm-x86/msr.h
@@ -18,7 +18,7 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
 	unsigned long low, high;
 	asm volatile(".byte 0x0f,0x01,0xf9"
 		     : "=a" (low), "=d" (high), "=c" (*aux));
-	return low | ((u64)high >> 32);
+	return low | ((u64)high << 32);
 }
 
 /*
@@ -66,7 +66,7 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 static inline void native_write_msr(unsigned int msr,
 				    unsigned low, unsigned high)
 {
-	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high));
+	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
 }
 
 static inline int native_write_msr_safe(unsigned int msr,
@@ -81,7 +81,8 @@ static inline int native_write_msr_safe(unsigned int msr,
 		     _ASM_EXTABLE(2b, 3b)
 		     : "=a" (err)
 		     : "c" (msr), "0" (low), "d" (high),
-		     "i" (-EFAULT));
+		       "i" (-EFAULT)
+		     : "memory");
 	return err;
 }
 
diff --git a/include/asm-x86/nmi.h b/include/asm-x86/nmi.h
index 1e363021e72f..21f8d0202a82 100644
--- a/include/asm-x86/nmi.h
+++ b/include/asm-x86/nmi.h
@@ -15,38 +15,13 @@
  */
 int do_nmi_callback(struct pt_regs *regs, int cpu);
 
-#ifdef CONFIG_PM
-
-/** Replace the PM callback routine for NMI. */
-struct pm_dev *set_nmi_pm_callback(pm_callback callback);
-
-/** Unset the PM callback routine back to the default. */
-void unset_nmi_pm_callback(struct pm_dev *dev);
-
-#else
-
-static inline struct pm_dev *set_nmi_pm_callback(pm_callback callback)
-{
-	return 0;
-}
-
-static inline void unset_nmi_pm_callback(struct pm_dev *dev)
-{
-}
-
-#endif /* CONFIG_PM */
-
 #ifdef CONFIG_X86_64
 extern void default_do_nmi(struct pt_regs *);
-extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
-extern void nmi_watchdog_default(void);
-#else
-#define nmi_watchdog_default() do {} while (0)
 #endif
 
+extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int check_nmi_watchdog(void);
 extern int nmi_watchdog_enabled;
-extern int unknown_nmi_panic;
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int avail_to_resrv_perfctr_nmi(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
@@ -62,12 +37,10 @@ extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
 
 extern atomic_t nmi_active;
 extern unsigned int nmi_watchdog;
-#define NMI_DISABLED    -1
 #define NMI_NONE	0
 #define NMI_IO_APIC	1
 #define NMI_LOCAL_APIC	2
 #define NMI_INVALID	3
-#define NMI_DEFAULT	NMI_DISABLED
 
 struct ctl_table;
 struct file;
@@ -78,6 +51,24 @@ extern int unknown_nmi_panic;
 void __trigger_all_cpu_backtrace(void);
 #define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
 
+static inline void localise_nmi_watchdog(void)
+{
+	if (nmi_watchdog == NMI_IO_APIC)
+		nmi_watchdog = NMI_LOCAL_APIC;
+}
+
+/* check if nmi_watchdog is active (ie was specified at boot) */
+static inline int nmi_watchdog_active(void)
+{
+	/*
+	 * actually it should be:
+	 * 	return (nmi_watchdog == NMI_LOCAL_APIC ||
+	 * 		nmi_watchdog == NMI_IO_APIC)
+	 * but since they are power of two we could use a
+	 * cheaper way --cvg
+	 */
+	return nmi_watchdog & 0x3;
+}
 #endif
 
 void lapic_watchdog_stop(void);
diff --git a/include/asm-x86/numa_32.h b/include/asm-x86/numa_32.h
index 03d0f7a9bf02..220d7b7707a0 100644
--- a/include/asm-x86/numa_32.h
+++ b/include/asm-x86/numa_32.h
@@ -2,14 +2,10 @@
 #define _ASM_X86_32_NUMA_H 1
 
 extern int pxm_to_nid(int pxm);
+extern void numa_remove_cpu(int cpu);
 
 #ifdef CONFIG_NUMA
-extern void __init remap_numa_kva(void);
-extern void set_highmem_pages_init(int);
-#else
-static inline void remap_numa_kva(void)
-{
-}
+extern void set_highmem_pages_init(void);
 #endif
 
 #endif /* _ASM_X86_32_NUMA_H */
diff --git a/include/asm-x86/numa_64.h b/include/asm-x86/numa_64.h
index 22e87c9f6a80..3830094434a9 100644
--- a/include/asm-x86/numa_64.h
+++ b/include/asm-x86/numa_64.h
@@ -14,32 +14,30 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,
 
 #define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
-extern void numa_add_cpu(int cpu);
 extern void numa_init_array(void);
 extern int numa_off;
 
-extern void numa_set_node(int cpu, int node);
 extern void srat_reserve_add_area(int nodeid);
 extern int hotadd_percent;
 
 extern s16 apicid_to_node[MAX_LOCAL_APIC];
 
-extern void numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn);
 extern unsigned long numa_free_all_bootmem(void);
 extern void setup_node_bootmem(int nodeid, unsigned long start,
 			       unsigned long end);
 
 #ifdef CONFIG_NUMA
 extern void __init init_cpu_to_node(void);
-
-static inline void clear_node_cpumask(int cpu)
-{
-	clear_bit(cpu, (unsigned long *)&node_to_cpumask_map[cpu_to_node(cpu)]);
-}
-
+extern void __cpuinit numa_set_node(int cpu, int node);
+extern void __cpuinit numa_clear_node(int cpu);
+extern void __cpuinit numa_add_cpu(int cpu);
+extern void __cpuinit numa_remove_cpu(int cpu);
 #else
-#define init_cpu_to_node() do {} while (0)
-#define clear_node_cpumask(cpu) do {} while (0)
+static inline void init_cpu_to_node(void)		{ }
+static inline void numa_set_node(int cpu, int node)	{ }
+static inline void numa_clear_node(int cpu)		{ }
+static inline void numa_add_cpu(int cpu, int node)	{ }
+static inline void numa_remove_cpu(int cpu)		{ }
 #endif
 
 #endif
diff --git a/include/asm-x86/numaq.h b/include/asm-x86/numaq.h
index 94b86c31239a..34b92d581fa3 100644
--- a/include/asm-x86/numaq.h
+++ b/include/asm-x86/numaq.h
@@ -28,6 +28,7 @@
 
 #ifdef CONFIG_X86_NUMAQ
 
+extern int found_numaq;
 extern int get_memcfg_numaq(void);
 
 /*
@@ -156,9 +157,12 @@ struct sys_cfg_data {
 	struct		eachquadmem eq[MAX_NUMNODES];	/* indexed by quad id */
 };
 
-static inline unsigned long *get_zholes_size(int nid)
+void numaq_tsc_disable(void);
+
+#else
+static inline int get_memcfg_numaq(void)
 {
-	return NULL;
+	return 0;
 }
 #endif /* CONFIG_X86_NUMAQ */
 #endif /* NUMAQ_H */
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
index dc936dddf161..28d7b4533b1a 100644
--- a/include/asm-x86/page.h
+++ b/include/asm-x86/page.h
@@ -51,9 +51,17 @@
 
 #ifndef __ASSEMBLY__
 
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pgprotval_t pgprot; } pgprot_t;
+
 extern int page_is_ram(unsigned long pagenr);
 extern int devmem_is_allowed(unsigned long pagenr);
+extern void map_devmem(unsigned long pfn, unsigned long size,
+		       pgprot_t vma_prot);
+extern void unmap_devmem(unsigned long pfn, unsigned long size,
+			 pgprot_t vma_prot);
 
+extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
 struct page;
@@ -74,9 +82,6 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
-typedef struct { pgdval_t pgd; } pgd_t;
-typedef struct { pgprotval_t pgprot; } pgprot_t;
-
 static inline pgd_t native_make_pgd(pgdval_t val)
 {
 	return (pgd_t) { val };
@@ -160,6 +165,7 @@ static inline pteval_t native_pte_val(pte_t pte)
 #endif
 
 #define pte_val(x)	native_pte_val(x)
+#define pte_flags(x)	native_pte_val(x)
 #define __pte(x)	native_make_pte(x)
 
 #endif	/* CONFIG_PARAVIRT */
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
index ccf0ba3c3aba..ab8528793f08 100644
--- a/include/asm-x86/page_32.h
+++ b/include/asm-x86/page_32.h
@@ -13,6 +13,14 @@
  */
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
+#ifdef CONFIG_4KSTACKS
+#define THREAD_ORDER	0
+#else
+#define THREAD_ORDER	1
+#endif
+#define THREAD_SIZE 	(PAGE_SIZE << THREAD_ORDER)
+
+
 #ifdef CONFIG_X86_PAE
 /* 44=32+12, the limit we can fit into an unsigned long pfn */
 #define __PHYSICAL_MASK_SHIFT	44
@@ -84,6 +92,13 @@ extern int sysctl_legacy_va_layout;
 #define VMALLOC_RESERVE		((unsigned long)__VMALLOC_RESERVE)
 #define MAXMEM			(-__PAGE_OFFSET - __VMALLOC_RESERVE)
 
+extern void find_low_pfn_range(void);
+extern unsigned long init_memory_mapping(unsigned long start,
+					 unsigned long end);
+extern void initmem_init(unsigned long, unsigned long);
+extern void setup_bootmem_allocator(void);
+
+
 #ifdef CONFIG_X86_USE_3DNOW
 #include <asm/mmx.h>
 
diff --git a/include/asm-x86/page_64.h b/include/asm-x86/page_64.h
index 6ea72859c491..c6916c83e6b1 100644
--- a/include/asm-x86/page_64.h
+++ b/include/asm-x86/page_64.h
@@ -26,7 +26,13 @@
 #define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
 
-#define __PAGE_OFFSET           _AC(0xffff810000000000, UL)
+/*
+ * Set __PAGE_OFFSET to the most negative possible address +
+ * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
+ * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
+ * what Xen requires.
+ */
+#define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
 
 #define __PHYSICAL_START	CONFIG_PHYSICAL_START
 #define __KERNEL_ALIGN		0x200000
@@ -58,7 +64,8 @@
 void clear_page(void *page);
 void copy_page(void *to, void *from);
 
-extern unsigned long end_pfn;
+/* duplicated to the one in bootmem.h */
+extern unsigned long max_pfn;
 extern unsigned long phys_base;
 
 extern unsigned long __phys_addr(unsigned long);
@@ -83,10 +90,15 @@ typedef struct { pteval_t pte; } pte_t;
 extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 
+extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+
+extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
+extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
+
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_FLATMEM
-#define pfn_valid(pfn)          ((pfn) < end_pfn)
+#define pfn_valid(pfn)          ((pfn) < max_pfn)
 #endif
 
 
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index 0f13b945e240..ef5e8ec6a6ab 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -84,7 +84,7 @@ struct pv_time_ops {
 	int (*set_wallclock)(unsigned long);
 
 	unsigned long long (*sched_clock)(void);
-	unsigned long (*get_cpu_khz)(void);
+	unsigned long (*get_tsc_khz)(void);
 };
 
 struct pv_cpu_ops {
@@ -115,6 +115,9 @@ struct pv_cpu_ops {
 	void (*set_ldt)(const void *desc, unsigned entries);
 	unsigned long (*store_tr)(void);
 	void (*load_tls)(struct thread_struct *t, unsigned int cpu);
+#ifdef CONFIG_X86_64
+	void (*load_gs_index)(unsigned int idx);
+#endif
 	void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum,
 				const void *desc);
 	void (*write_gdt_entry)(struct desc_struct *,
@@ -141,8 +144,32 @@ struct pv_cpu_ops {
 	u64 (*read_pmc)(int counter);
 	unsigned long long (*read_tscp)(unsigned int *aux);
 
-	/* These two are jmp to, not actually called. */
-	void (*irq_enable_syscall_ret)(void);
+	/*
+	 * Atomically enable interrupts and return to userspace.  This
+	 * is only ever used to return to 32-bit processes; in a
+	 * 64-bit kernel, it's used for 32-on-64 compat processes, but
+	 * never native 64-bit processes.  (Jump, not call.)
+	 */
+	void (*irq_enable_sysexit)(void);
+
+	/*
+	 * Switch to usermode gs and return to 64-bit usermode using
+	 * sysret.  Only used in 64-bit kernels to return to 64-bit
+	 * processes.  Usermode register state, including %rsp, must
+	 * already be restored.
+	 */
+	void (*usergs_sysret64)(void);
+
+	/*
+	 * Switch to usermode gs and return to 32-bit usermode using
+	 * sysret.  Used to return to 32-on-64 compat processes.
+	 * Other usermode register state, including %esp, must already
+	 * be restored.
+	 */
+	void (*usergs_sysret32)(void);
+
+	/* Normal iret.  Jump to this with the standard iret stack
+	   frame set up. */
 	void (*iret)(void);
 
 	void (*swapgs)(void);
@@ -165,6 +192,10 @@ struct pv_irq_ops {
 	void (*irq_enable)(void);
 	void (*safe_halt)(void);
 	void (*halt)(void);
+
+#ifdef CONFIG_X86_64
+	void (*adjust_exception_frame)(void);
+#endif
 };
 
 struct pv_apic_ops {
@@ -219,7 +250,14 @@ struct pv_mmu_ops {
 	void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
 				 unsigned long va);
 
-	/* Hooks for allocating/releasing pagetable pages */
+	/* Hooks for allocating and freeing a pagetable top-level */
+	int  (*pgd_alloc)(struct mm_struct *mm);
+	void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd);
+
+	/*
+	 * Hooks for allocating/releasing pagetable pages when they're
+	 * attached to a pagetable
+	 */
 	void (*alloc_pte)(struct mm_struct *mm, u32 pfn);
 	void (*alloc_pmd)(struct mm_struct *mm, u32 pfn);
 	void (*alloc_pmd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count);
@@ -238,7 +276,13 @@ struct pv_mmu_ops {
 	void (*pte_update_defer)(struct mm_struct *mm,
 				 unsigned long addr, pte_t *ptep);
 
+	pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
+					pte_t *ptep);
+	void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
+					pte_t *ptep, pte_t pte);
+
 	pteval_t (*pte_val)(pte_t);
+	pteval_t (*pte_flags)(pte_t);
 	pte_t (*make_pte)(pteval_t pte);
 
 	pgdval_t (*pgd_val)(pgd_t);
@@ -273,6 +317,13 @@ struct pv_mmu_ops {
 #endif
 
 	struct pv_lazy_ops lazy_mode;
+
+	/* dom0 ops */
+
+	/* Sometimes the physical address is a pfn, and sometimes its
+	   an mfn.  We can tell which is which from the index. */
+	void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
+			   unsigned long phys, pgprot_t flags);
 };
 
 /* This contains all the paravirt structures: we get a convenient
@@ -439,10 +490,17 @@ int paravirt_disable_iospace(void);
 #define VEXTRA_CLOBBERS	 , "rax", "r8", "r9", "r10", "r11"
 #endif
 
+#ifdef CONFIG_PARAVIRT_DEBUG
+#define PVOP_TEST_NULL(op)	BUG_ON(op == NULL)
+#else
+#define PVOP_TEST_NULL(op)	((void)op)
+#endif
+
 #define __PVOP_CALL(rettype, op, pre, post, ...)			\
 	({								\
 		rettype __ret;						\
 		PVOP_CALL_ARGS;					\
+		PVOP_TEST_NULL(op);					\
 		/* This is 32-bit specific, but is okay in 64-bit */	\
 		/* since this condition will never hold */		\
 		if (sizeof(rettype) > sizeof(unsigned long)) {		\
@@ -471,6 +529,7 @@ int paravirt_disable_iospace(void);
 #define __PVOP_VCALL(op, pre, post, ...)				\
 	({								\
 		PVOP_VCALL_ARGS;					\
+		PVOP_TEST_NULL(op);					\
 		asm volatile(pre					\
 			     paravirt_alt(PARAVIRT_CALL)		\
 			     post					\
@@ -720,7 +779,7 @@ static inline unsigned long long paravirt_sched_clock(void)
 {
 	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
-#define calculate_cpu_khz() (pv_time_ops.get_cpu_khz())
+#define calibrate_tsc() (pv_time_ops.get_tsc_khz())
 
 static inline unsigned long long paravirt_read_pmc(int counter)
 {
@@ -789,6 +848,13 @@ static inline void load_TLS(struct thread_struct *t, unsigned cpu)
 	PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
 }
 
+#ifdef CONFIG_X86_64
+static inline void load_gs_index(unsigned int gs)
+{
+	PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs);
+}
+#endif
+
 static inline void write_ldt_entry(struct desc_struct *dt, int entry,
 				   const void *desc)
 {
@@ -912,6 +978,16 @@ static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
 }
 
+static inline int paravirt_pgd_alloc(struct mm_struct *mm)
+{
+	return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
+}
+
+static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
+}
+
 static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned pfn)
 {
 	PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
@@ -996,6 +1072,20 @@ static inline pteval_t pte_val(pte_t pte)
 	return ret;
 }
 
+static inline pteval_t pte_flags(pte_t pte)
+{
+	pteval_t ret;
+
+	if (sizeof(pteval_t) > sizeof(long))
+		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
+				 pte.pte, (u64)pte.pte >> 32);
+	else
+		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
+				 pte.pte);
+
+	return ret;
+}
+
 static inline pgd_t __pgd(pgdval_t val)
 {
 	pgdval_t ret;
@@ -1024,6 +1114,29 @@ static inline pgdval_t pgd_val(pgd_t pgd)
 	return ret;
 }
 
+#define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+					   pte_t *ptep)
+{
+	pteval_t ret;
+
+	ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start,
+			 mm, addr, ptep);
+
+	return (pte_t) { .pte = ret };
+}
+
+static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+					   pte_t *ptep, pte_t pte)
+{
+	if (sizeof(pteval_t) > sizeof(long))
+		/* 5 arg words */
+		pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
+	else
+		PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit,
+			    mm, addr, ptep, pte.pte);
+}
+
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	if (sizeof(pteval_t) > sizeof(long))
@@ -1252,6 +1365,12 @@ static inline void arch_flush_lazy_mmu_mode(void)
 	}
 }
 
+static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
+				unsigned long phys, pgprot_t flags)
+{
+	pv_mmu_ops.set_fixmap(idx, phys, flags);
+}
+
 void _paravirt_nop(void);
 #define paravirt_nop	((void *)_paravirt_nop)
 
@@ -1374,54 +1493,86 @@ static inline unsigned long __raw_local_irq_save(void)
 #define PV_RESTORE_REGS popq %rdx; popq %rcx; popq %rdi; popq %rax
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 8)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
+#define PARA_INDIRECT(addr)	*addr(%rip)
 #else
 #define PV_SAVE_REGS   pushl %eax; pushl %edi; pushl %ecx; pushl %edx
 #define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 4)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
+#define PARA_INDIRECT(addr)	*%cs:addr
 #endif
 
 #define INTERRUPT_RETURN						\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,	\
-		  jmp *%cs:pv_cpu_ops+PV_CPU_iret)
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))
 
 #define DISABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
-		  PV_SAVE_REGS;			\
-		  call *%cs:pv_irq_ops+PV_IRQ_irq_disable;		\
+		  PV_SAVE_REGS;						\
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);	\
 		  PV_RESTORE_REGS;)			\
 
 #define ENABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
-		  PV_SAVE_REGS;			\
-		  call *%cs:pv_irq_ops+PV_IRQ_irq_enable;		\
+		  PV_SAVE_REGS;						\
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
 		  PV_RESTORE_REGS;)
 
-#define ENABLE_INTERRUPTS_SYSCALL_RET					\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_syscall_ret),\
+#define USERGS_SYSRET32							\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),	\
 		  CLBR_NONE,						\
-		  jmp *%cs:pv_cpu_ops+PV_CPU_irq_enable_syscall_ret)
-
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32))
 
 #ifdef CONFIG_X86_32
-#define GET_CR0_INTO_EAX			\
-	push %ecx; push %edx;			\
-	call *pv_cpu_ops+PV_CPU_read_cr0;	\
+#define GET_CR0_INTO_EAX				\
+	push %ecx; push %edx;				\
+	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
 	pop %edx; pop %ecx
-#else
+
+#define ENABLE_INTERRUPTS_SYSEXIT					\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
+		  CLBR_NONE,						\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
+
+
+#else	/* !CONFIG_X86_32 */
+
+/*
+ * If swapgs is used while the userspace stack is still current,
+ * there's no way to call a pvop.  The PV replacement *must* be
+ * inlined, or the swapgs instruction must be trapped and emulated.
+ */
+#define SWAPGS_UNSAFE_STACK						\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
+		  swapgs)
+
 #define SWAPGS								\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
 		  PV_SAVE_REGS;						\
-		  call *pv_cpu_ops+PV_CPU_swapgs;			\
+		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);		\
 		  PV_RESTORE_REGS					\
 		 )
 
-#define GET_CR2_INTO_RCX			\
-	call *pv_mmu_ops+PV_MMU_read_cr2;	\
-	movq %rax, %rcx;			\
+#define GET_CR2_INTO_RCX				\
+	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);	\
+	movq %rax, %rcx;				\
 	xorq %rax, %rax;
 
-#endif
+#define PARAVIRT_ADJUST_EXCEPTION_FRAME					\
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \
+		  CLBR_NONE,						\
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame))
+
+#define USERGS_SYSRET64							\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
+		  CLBR_NONE,						\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#define ENABLE_INTERRUPTS_SYSEXIT32					\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
+		  CLBR_NONE,						\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
+#endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_PARAVIRT */
diff --git a/include/asm-x86/pat.h b/include/asm-x86/pat.h
index 88f60cc6a227..7edc47307217 100644
--- a/include/asm-x86/pat.h
+++ b/include/asm-x86/pat.h
@@ -1,14 +1,13 @@
-
 #ifndef _ASM_PAT_H
-#define _ASM_PAT_H 1
+#define _ASM_PAT_H
 
 #include <linux/types.h>
 
 #ifdef CONFIG_X86_PAT
-extern int pat_wc_enabled;
+extern int pat_enabled;
 extern void validate_pat_support(struct cpuinfo_x86 *c);
 #else
-static const int pat_wc_enabled = 0;
+static const int pat_enabled;
 static inline void validate_pat_support(struct cpuinfo_x86 *c) { }
 #endif
 
@@ -21,4 +20,3 @@ extern int free_memtype(u64 start, u64 end);
 extern void pat_disable(char *reason);
 
 #endif
-
diff --git a/include/asm-x86/pci-direct.h b/include/asm-x86/pci-direct.h
index 5b21485be573..80c775d9fe20 100644
--- a/include/asm-x86/pci-direct.h
+++ b/include/asm-x86/pci-direct.h
@@ -11,7 +11,11 @@ extern u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset);
 extern u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset);
 extern void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset, u32 val);
 extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val);
+extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val);
 
 extern int early_pci_allowed(void);
 
+extern unsigned int pci_early_dump_regs;
+extern void early_dump_pci_device(u8 bus, u8 slot, u8 func);
+extern void early_dump_pci_devices(void);
 #endif
diff --git a/include/asm-x86/pci.h b/include/asm-x86/pci.h
index 30bbde0cb34b..2db14cf17db8 100644
--- a/include/asm-x86/pci.h
+++ b/include/asm-x86/pci.h
@@ -18,6 +18,8 @@ struct pci_sysdata {
 #endif
 };
 
+extern int pci_routeirq;
+
 /* scan a bus after allocating a pci_sysdata for it */
 extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
 					    int node);
diff --git a/include/asm-x86/pci_32.h b/include/asm-x86/pci_32.h
index 8c4c3a0368e2..a50d46851285 100644
--- a/include/asm-x86/pci_32.h
+++ b/include/asm-x86/pci_32.h
@@ -18,12 +18,14 @@ struct pci_dev;
 #define PCI_DMA_BUS_IS_PHYS	(1)
 
 /* pci_unmap_{page,single} is a nop so... */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
-#define pci_unmap_addr(PTR, ADDR_NAME)		(0)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)	do { } while (0)
-#define pci_unmap_len(PTR, LEN_NAME)		(0)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)	do { } while (0)
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	dma_addr_t ADDR_NAME[0];
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)	unsigned LEN_NAME[0];
+#define pci_unmap_addr(PTR, ADDR_NAME)	sizeof((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+	do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
+#define pci_unmap_len(PTR, LEN_NAME)		sizeof((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
+	do { break; } while (pci_unmap_len(PTR, LEN_NAME))
 
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-x86/pda.h b/include/asm-x86/pda.h
index 101fb9e11954..b34e9a7cc80b 100644
--- a/include/asm-x86/pda.h
+++ b/include/asm-x86/pda.h
@@ -22,6 +22,8 @@ struct x8664_pda {
 					   offset 40!!! */
 #endif
 	char *irqstackptr;
+	short nodenumber;		/* number of current node (32k max) */
+	short in_bootmem;		/* pda lives in bootmem */
 	unsigned int __softirq_pending;
 	unsigned int __nmi_count;	/* number of NMI on this CPUs */
 	short mmu_state;
@@ -37,8 +39,7 @@ struct x8664_pda {
 	unsigned irq_spurious_count;
 } ____cacheline_aligned_in_smp;
 
-extern struct x8664_pda *_cpu_pda[];
-extern struct x8664_pda boot_cpu_pda[];
+extern struct x8664_pda **_cpu_pda;
 extern void pda_init(int);
 
 #define cpu_pda(i) (_cpu_pda[i])
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
index 736fc3bb8e1e..912a3a17b9db 100644
--- a/include/asm-x86/percpu.h
+++ b/include/asm-x86/percpu.h
@@ -143,4 +143,50 @@ do {							\
 #define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
 #endif /* !__ASSEMBLY__ */
 #endif /* !CONFIG_X86_64 */
+
+#ifdef CONFIG_SMP
+
+/*
+ * Define the "EARLY_PER_CPU" macros.  These are used for some per_cpu
+ * variables that are initialized and accessed before there are per_cpu
+ * areas allocated.
+ */
+
+#define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)			\
+	DEFINE_PER_CPU(_type, _name) = _initvalue;			\
+	__typeof__(_type) _name##_early_map[NR_CPUS] __initdata =	\
+				{ [0 ... NR_CPUS-1] = _initvalue };	\
+	__typeof__(_type) *_name##_early_ptr = _name##_early_map
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
+	EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name)			\
+	DECLARE_PER_CPU(_type, _name);				\
+	extern __typeof__(_type) *_name##_early_ptr;		\
+	extern __typeof__(_type)  _name##_early_map[]
+
+#define	early_per_cpu_ptr(_name) (_name##_early_ptr)
+#define	early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
+#define	early_per_cpu(_name, _cpu) 				\
+	(early_per_cpu_ptr(_name) ?				\
+		early_per_cpu_ptr(_name)[_cpu] :		\
+		per_cpu(_name, _cpu))
+
+#else	/* !CONFIG_SMP */
+#define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)		\
+	DEFINE_PER_CPU(_type, _name) = _initvalue
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
+	EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name)			\
+	DECLARE_PER_CPU(_type, _name)
+
+#define	early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
+#define	early_per_cpu_ptr(_name) NULL
+/* no early_per_cpu_map() */
+
+#endif	/* !CONFIG_SMP */
+
 #endif /* _ASM_X86_PERCPU_H_ */
diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h
index 91e4641f3f31..d63ea431cb3b 100644
--- a/include/asm-x86/pgalloc.h
+++ b/include/asm-x86/pgalloc.h
@@ -5,9 +5,13 @@
 #include <linux/mm.h>		/* for struct page */
 #include <linux/pagemap.h>
 
+static inline int  __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
+#define paravirt_pgd_alloc(mm)	__paravirt_pgd_alloc(mm)
+static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {}
 static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)	{}
 static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)	{}
 static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index 97c271b2910b..49cbd76b9547 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -20,30 +20,25 @@
 #define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
-/*
- * Note: we use _AC(1, L) instead of _AC(1, UL) so that we get a
- * sign-extended value on 32-bit with all 1's in the upper word,
- * which preserves the upper pte values on 64-bit ptes:
- */
-#define _PAGE_PRESENT	(_AC(1, L)<<_PAGE_BIT_PRESENT)
-#define _PAGE_RW	(_AC(1, L)<<_PAGE_BIT_RW)
-#define _PAGE_USER	(_AC(1, L)<<_PAGE_BIT_USER)
-#define _PAGE_PWT	(_AC(1, L)<<_PAGE_BIT_PWT)
-#define _PAGE_PCD	(_AC(1, L)<<_PAGE_BIT_PCD)
-#define _PAGE_ACCESSED	(_AC(1, L)<<_PAGE_BIT_ACCESSED)
-#define _PAGE_DIRTY	(_AC(1, L)<<_PAGE_BIT_DIRTY)
-#define _PAGE_PSE	(_AC(1, L)<<_PAGE_BIT_PSE)	/* 2MB page */
-#define _PAGE_GLOBAL	(_AC(1, L)<<_PAGE_BIT_GLOBAL)	/* Global TLB entry */
-#define _PAGE_UNUSED1	(_AC(1, L)<<_PAGE_BIT_UNUSED1)
-#define _PAGE_UNUSED2	(_AC(1, L)<<_PAGE_BIT_UNUSED2)
-#define _PAGE_UNUSED3	(_AC(1, L)<<_PAGE_BIT_UNUSED3)
-#define _PAGE_PAT	(_AC(1, L)<<_PAGE_BIT_PAT)
-#define _PAGE_PAT_LARGE (_AC(1, L)<<_PAGE_BIT_PAT_LARGE)
+#define _PAGE_PRESENT	(_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
+#define _PAGE_RW	(_AT(pteval_t, 1) << _PAGE_BIT_RW)
+#define _PAGE_USER	(_AT(pteval_t, 1) << _PAGE_BIT_USER)
+#define _PAGE_PWT	(_AT(pteval_t, 1) << _PAGE_BIT_PWT)
+#define _PAGE_PCD	(_AT(pteval_t, 1) << _PAGE_BIT_PCD)
+#define _PAGE_ACCESSED	(_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
+#define _PAGE_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
+#define _PAGE_PSE	(_AT(pteval_t, 1) << _PAGE_BIT_PSE)
+#define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
+#define _PAGE_UNUSED1	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
+#define _PAGE_UNUSED2	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED2)
+#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)
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-#define _PAGE_NX	(_AC(1, ULL) << _PAGE_BIT_NX)
+#define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else
-#define _PAGE_NX	0
+#define _PAGE_NX	(_AT(pteval_t, 0))
 #endif
 
 /* If _PAGE_PRESENT is clear, we use these: */
@@ -83,19 +78,9 @@
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
 					 _PAGE_ACCESSED)
 
-#ifdef CONFIG_X86_32
-#define _PAGE_KERNEL_EXEC \
-	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
-#define _PAGE_KERNEL (_PAGE_KERNEL_EXEC | _PAGE_NX)
-
-#ifndef __ASSEMBLY__
-extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
-#endif	/* __ASSEMBLY__ */
-#else
 #define __PAGE_KERNEL_EXEC						\
-	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
 #define __PAGE_KERNEL		(__PAGE_KERNEL_EXEC | _PAGE_NX)
-#endif
 
 #define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
 #define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
@@ -106,26 +91,22 @@ extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
 #define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
 #define __PAGE_KERNEL_VSYSCALL_NOCACHE	(__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
 #define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_NOCACHE	(__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
 
-#ifdef CONFIG_X86_32
-# define MAKE_GLOBAL(x)			__pgprot((x))
-#else
-# define MAKE_GLOBAL(x)			__pgprot((x) | _PAGE_GLOBAL)
-#endif
-
-#define PAGE_KERNEL			MAKE_GLOBAL(__PAGE_KERNEL)
-#define PAGE_KERNEL_RO			MAKE_GLOBAL(__PAGE_KERNEL_RO)
-#define PAGE_KERNEL_EXEC		MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
-#define PAGE_KERNEL_RX			MAKE_GLOBAL(__PAGE_KERNEL_RX)
-#define PAGE_KERNEL_WC			MAKE_GLOBAL(__PAGE_KERNEL_WC)
-#define PAGE_KERNEL_NOCACHE		MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
-#define PAGE_KERNEL_UC_MINUS		MAKE_GLOBAL(__PAGE_KERNEL_UC_MINUS)
-#define PAGE_KERNEL_EXEC_NOCACHE	MAKE_GLOBAL(__PAGE_KERNEL_EXEC_NOCACHE)
-#define PAGE_KERNEL_LARGE		MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
-#define PAGE_KERNEL_LARGE_EXEC		MAKE_GLOBAL(__PAGE_KERNEL_LARGE_EXEC)
-#define PAGE_KERNEL_VSYSCALL		MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_VSYSCALL_NOCACHE	MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+#define PAGE_KERNEL			__pgprot(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO			__pgprot(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_EXEC		__pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RX			__pgprot(__PAGE_KERNEL_RX)
+#define PAGE_KERNEL_WC			__pgprot(__PAGE_KERNEL_WC)
+#define PAGE_KERNEL_NOCACHE		__pgprot(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_UC_MINUS		__pgprot(__PAGE_KERNEL_UC_MINUS)
+#define PAGE_KERNEL_EXEC_NOCACHE	__pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
+#define PAGE_KERNEL_LARGE		__pgprot(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_LARGE_NOCACHE	__pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
+#define PAGE_KERNEL_LARGE_EXEC		__pgprot(__PAGE_KERNEL_LARGE_EXEC)
+#define PAGE_KERNEL_VSYSCALL		__pgprot(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_VSYSCALL_NOCACHE	__pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
 
 /*         xwr */
 #define __P000	PAGE_NONE
@@ -164,37 +145,37 @@ extern struct list_head pgd_list;
  */
 static inline int pte_dirty(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_DIRTY;
+	return pte_flags(pte) & _PAGE_DIRTY;
 }
 
 static inline int pte_young(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_ACCESSED;
+	return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
 static inline int pte_write(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_RW;
+	return pte_flags(pte) & _PAGE_RW;
 }
 
 static inline int pte_file(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_FILE;
+	return pte_flags(pte) & _PAGE_FILE;
 }
 
 static inline int pte_huge(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_PSE;
+	return pte_flags(pte) & _PAGE_PSE;
 }
 
 static inline int pte_global(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_GLOBAL;
+	return pte_flags(pte) & _PAGE_GLOBAL;
 }
 
 static inline int pte_exec(pte_t pte)
 {
-	return !(pte_val(pte) & _PAGE_NX);
+	return !(pte_flags(pte) & _PAGE_NX);
 }
 
 static inline int pte_special(pte_t pte)
@@ -210,22 +191,22 @@ static inline int pmd_large(pmd_t pte)
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_DIRTY);
+	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_ACCESSED);
+	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
 }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_RW);
+	return __pte(pte_val(pte) & ~_PAGE_RW);
 }
 
 static inline pte_t pte_mkexec(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_NX);
+	return __pte(pte_val(pte) & ~_PAGE_NX);
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
@@ -250,7 +231,7 @@ static inline pte_t pte_mkhuge(pte_t pte)
 
 static inline pte_t pte_clrhuge(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_PSE);
+	return __pte(pte_val(pte) & ~_PAGE_PSE);
 }
 
 static inline pte_t pte_mkglobal(pte_t pte)
@@ -260,7 +241,7 @@ static inline pte_t pte_mkglobal(pte_t pte)
 
 static inline pte_t pte_clrglobal(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_GLOBAL);
+	return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
@@ -305,7 +286,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 	return __pgprot(preservebits | addbits);
 }
 
-#define pte_pgprot(x) __pgprot(pte_val(x) & ~PTE_MASK)
+#define pte_pgprot(x) __pgprot(pte_flags(x) & ~PTE_MASK)
 
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 
@@ -318,6 +299,9 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
                               unsigned long size, pgprot_t *vma_prot);
 #endif
 
+/* Install a pte for a particular vaddr in kernel space. */
+void set_pte_vaddr(unsigned long vaddr, pte_t pte);
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT */
@@ -359,6 +343,26 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 # include "pgtable_64.h"
 #endif
 
+/*
+ * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
+ *
+ * this macro returns the index of the entry in the pgd page which would
+ * control the given virtual address
+ */
+#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
+
+/*
+ * pgd_offset() returns a (pgd_t *)
+ * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
+ */
+#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+/*
+ * a shortcut which implies the use of the kernel's pgd, instead
+ * of a process's
+ */
+#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
+
+
 #define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
 #define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
 
@@ -369,8 +373,15 @@ enum {
 	PG_LEVEL_4K,
 	PG_LEVEL_2M,
 	PG_LEVEL_1G,
+	PG_LEVEL_NUM
 };
 
+#ifdef CONFIG_PROC_FS
+extern void update_page_count(int level, unsigned long pages);
+#else
+static inline void update_page_count(int level, unsigned long pages) { }
+#endif
+
 /*
  * Helper function that returns the kernel pagetable entry controlling
  * the virtual address 'address'. NULL means no pagetable entry present.
@@ -420,6 +431,8 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
  * race with other CPU's that might be updating the dirty
  * bit at the same time.
  */
+struct vm_area_struct;
+
 #define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pte_t *ptep,
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
index 32ca03109a4c..ec871c420d7e 100644
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -113,26 +113,6 @@ extern unsigned long pg0[];
  */
 #define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
 
-/*
- * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
- *
- * this macro returns the index of the entry in the pgd page which would
- * control the given virtual address
- */
-#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
-#define pgd_index_k(addr) pgd_index((addr))
-
-/*
- * pgd_offset() returns a (pgd_t *)
- * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
- */
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
-
-/*
- * a shortcut which implies the use of the kernel's pgd, instead
- * of a process's
- */
-#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
 
 static inline int pud_large(pud_t pud) { return 0; }
 
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index 1cc50d22d735..fa7208b483ca 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -70,6 +70,9 @@ extern void paging_init(void);
 
 struct mm_struct;
 
+void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
+
+
 static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
 				    pte_t *ptep)
 {
@@ -190,12 +193,9 @@ static inline int pmd_bad(pmd_t pmd)
 #define pgd_page_vaddr(pgd)						\
 	((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_MASK))
 #define pgd_page(pgd)		(pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT))
-#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
-#define pgd_offset(mm, address)	((mm)->pgd + pgd_index((address)))
-#define pgd_offset_k(address) (init_level4_pgt + pgd_index((address)))
 #define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
 static inline int pgd_large(pgd_t pgd) { return 0; }
-#define mk_kernel_pgd(address) ((pgd_t){ (address) | _KERNPG_TABLE })
+#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
 
 /* PUD - Level3 access */
 /* to find an entry in a page-table-directory. */
diff --git a/include/asm-x86/processor-flags.h b/include/asm-x86/processor-flags.h
index 199cab107d85..092b39b3a7e6 100644
--- a/include/asm-x86/processor-flags.h
+++ b/include/asm-x86/processor-flags.h
@@ -88,4 +88,10 @@
 #define CX86_ARR_BASE	0xc4
 #define CX86_RCR_BASE	0xdc
 
+#ifdef CONFIG_VM86
+#define X86_VM_MASK	X86_EFLAGS_VM
+#else
+#define X86_VM_MASK	0 /* No VM86 support */
+#endif
+
 #endif	/* __ASM_I386_PROCESSOR_FLAGS_H */
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 559105220a47..55402d2ab938 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -153,7 +153,7 @@ static inline int hlt_works(int cpu)
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
 
-extern void identify_cpu(struct cpuinfo_x86 *);
+extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
@@ -263,15 +263,11 @@ struct tss_struct {
 	struct thread_struct	*io_bitmap_owner;
 
 	/*
-	 * Pad the TSS to be cacheline-aligned (size is 0x100):
-	 */
-	unsigned long		__cacheline_filler[35];
-	/*
 	 * .. and then another 0x100 bytes for the emergency kernel stack:
 	 */
 	unsigned long		stack[64];
 
-} __attribute__((packed));
+} ____cacheline_aligned;
 
 DECLARE_PER_CPU(struct tss_struct, init_tss);
 
@@ -535,7 +531,6 @@ static inline void load_sp0(struct tss_struct *tss,
 }
 
 #define set_iopl_mask native_set_iopl_mask
-#define SWAPGS	swapgs
 #endif /* CONFIG_PARAVIRT */
 
 /*
@@ -732,6 +727,8 @@ extern int			force_mwait;
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
 
 extern unsigned long		boot_option_idle_override;
+extern unsigned long		idle_halt;
+extern unsigned long		idle_nomwait;
 
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
diff --git a/include/asm-x86/proto.h b/include/asm-x86/proto.h
index 6c8b41b03f6d..3dd458c385c0 100644
--- a/include/asm-x86/proto.h
+++ b/include/asm-x86/proto.h
@@ -14,8 +14,6 @@ extern void ia32_syscall(void);
 extern void ia32_cstar_target(void);
 extern void ia32_sysenter_target(void);
 
-extern void reserve_bootmem_generic(unsigned long phys, unsigned len);
-
 extern void syscall32_cpu_init(void);
 
 extern void check_efer(void);
diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h
index 9f922b0b95d6..8a71db803da6 100644
--- a/include/asm-x86/ptrace.h
+++ b/include/asm-x86/ptrace.h
@@ -3,7 +3,12 @@
 
 #include <linux/compiler.h>	/* For __user */
 #include <asm/ptrace-abi.h>
+#include <asm/processor-flags.h>
 
+#ifdef __KERNEL__
+#include <asm/ds.h>		/* the DS BTS struct is used for ptrace too */
+#include <asm/segment.h>
+#endif
 
 #ifndef __ASSEMBLY__
 
@@ -55,9 +60,6 @@ struct pt_regs {
 	unsigned long ss;
 };
 
-#include <asm/vm86.h>
-#include <asm/segment.h>
-
 #endif /* __KERNEL__ */
 
 #else /* __i386__ */
diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h
index e63741f19392..206f355786dc 100644
--- a/include/asm-x86/reboot.h
+++ b/include/asm-x86/reboot.h
@@ -14,8 +14,8 @@ struct machine_ops {
 
 extern struct machine_ops machine_ops;
 
-void machine_real_restart(unsigned char *code, int length);
 void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
+void machine_real_restart(const unsigned char *code, int length);
 
 #endif	/* _ASM_REBOOT_H */
diff --git a/include/asm-x86/required-features.h b/include/asm-x86/required-features.h
index 7400d3ad75c6..adec887dd7cd 100644
--- a/include/asm-x86/required-features.h
+++ b/include/asm-x86/required-features.h
@@ -19,9 +19,13 @@
 
 #if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
 # define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
-# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_PAE	0
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
+#else
 # define NEED_CX8	0
 #endif
 
@@ -38,7 +42,7 @@
 #endif
 
 #ifdef CONFIG_X86_64
-#define NEED_PSE	(1<<(X86_FEATURE_PSE & 31))
+#define NEED_PSE	0
 #define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
 #define NEED_PGE	(1<<(X86_FEATURE_PGE & 31))
 #define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
diff --git a/include/asm-x86/resume-trace.h b/include/asm-x86/resume-trace.h
index 2557514d7ef6..8d9f0b41ee86 100644
--- a/include/asm-x86/resume-trace.h
+++ b/include/asm-x86/resume-trace.h
@@ -6,7 +6,7 @@
 #define TRACE_RESUME(user)					\
 do {								\
 	if (pm_trace_enabled) {					\
-		void *tracedata;				\
+		const void *tracedata;				\
 		asm volatile(_ASM_MOV_UL " $1f,%0\n"		\
 			     ".section .tracedata,\"a\"\n"	\
 			     "1:\t.word %c1\n\t"		\
diff --git a/include/asm-x86/seccomp_32.h b/include/asm-x86/seccomp_32.h
index 18da19e89bff..36e71c5f306f 100644
--- a/include/asm-x86/seccomp_32.h
+++ b/include/asm-x86/seccomp_32.h
@@ -1,4 +1,5 @@
 #ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
 
 #include <linux/thread_info.h>
 
diff --git a/include/asm-x86/seccomp_64.h b/include/asm-x86/seccomp_64.h
index 553af65a2287..76cfe69aa63c 100644
--- a/include/asm-x86/seccomp_64.h
+++ b/include/asm-x86/seccomp_64.h
@@ -1,4 +1,5 @@
 #ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
 
 #include <linux/thread_info.h>
 
diff --git a/include/asm-x86/segment.h b/include/asm-x86/segment.h
index ed5131dd7d92..dfc8601c0892 100644
--- a/include/asm-x86/segment.h
+++ b/include/asm-x86/segment.h
@@ -61,18 +61,14 @@
 #define GDT_ENTRY_TLS_MAX 	(GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)
 
 #define GDT_ENTRY_DEFAULT_USER_CS	14
-#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS * 8 + 3)
 
 #define GDT_ENTRY_DEFAULT_USER_DS	15
-#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS * 8 + 3)
 
 #define GDT_ENTRY_KERNEL_BASE	12
 
 #define GDT_ENTRY_KERNEL_CS		(GDT_ENTRY_KERNEL_BASE + 0)
-#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS * 8)
 
 #define GDT_ENTRY_KERNEL_DS		(GDT_ENTRY_KERNEL_BASE + 1)
-#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS * 8)
 
 #define GDT_ENTRY_TSS			(GDT_ENTRY_KERNEL_BASE + 4)
 #define GDT_ENTRY_LDT			(GDT_ENTRY_KERNEL_BASE + 5)
@@ -139,10 +135,11 @@
 #else
 #include <asm/cache.h>
 
-#define __KERNEL_CS	0x10
-#define __KERNEL_DS	0x18
+#define GDT_ENTRY_KERNEL32_CS 1
+#define GDT_ENTRY_KERNEL_CS 2
+#define GDT_ENTRY_KERNEL_DS 3
 
-#define __KERNEL32_CS   0x08
+#define __KERNEL32_CS   (GDT_ENTRY_KERNEL32_CS * 8)
 
 /*
  * we cannot use the same code segment descriptor for user and kernel
@@ -150,10 +147,10 @@
  * The segment offset needs to contain a RPL. Grr. -AK
  * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets)
  */
-
-#define __USER32_CS   0x23   /* 4*8+3 */
-#define __USER_DS     0x2b   /* 5*8+3 */
-#define __USER_CS     0x33   /* 6*8+3 */
+#define GDT_ENTRY_DEFAULT_USER32_CS 4
+#define GDT_ENTRY_DEFAULT_USER_DS 5
+#define GDT_ENTRY_DEFAULT_USER_CS 6
+#define __USER32_CS   (GDT_ENTRY_DEFAULT_USER32_CS * 8 + 3)
 #define __USER32_DS	__USER_DS
 
 #define GDT_ENTRY_TSS 8	/* needs two entries */
@@ -175,6 +172,10 @@
 
 #endif
 
+#define __KERNEL_CS	(GDT_ENTRY_KERNEL_CS * 8)
+#define __KERNEL_DS	(GDT_ENTRY_KERNEL_DS * 8)
+#define __USER_DS     (GDT_ENTRY_DEFAULT_USER_DS* 8 + 3)
+#define __USER_CS     (GDT_ENTRY_DEFAULT_USER_CS* 8 + 3)
 #ifndef CONFIG_PARAVIRT
 #define get_kernel_rpl()  0
 #endif
diff --git a/include/asm-x86/setup.h b/include/asm-x86/setup.h
index fa6763af8d26..90ab2225e71b 100644
--- a/include/asm-x86/setup.h
+++ b/include/asm-x86/setup.h
@@ -8,7 +8,25 @@
 /* Interrupt control for vSMPowered x86_64 systems */
 void vsmp_init(void);
 
-char *machine_specific_memory_setup(void);
+#ifdef CONFIG_X86_VISWS
+extern void visws_early_detect(void);
+extern int is_visws_box(void);
+#else
+static inline void visws_early_detect(void) { }
+static inline int is_visws_box(void) { return 0; }
+#endif
+
+/*
+ * Any setup quirks to be performed?
+ */
+extern int (*arch_time_init_quirk)(void);
+extern int (*arch_pre_intr_init_quirk)(void);
+extern int (*arch_intr_init_quirk)(void);
+extern int (*arch_trap_init_quirk)(void);
+extern char * (*arch_memory_setup_quirk)(void);
+extern int (*mach_get_smp_config_quirk)(unsigned int early);
+extern int (*mach_find_smp_config_quirk)(unsigned int reserve);
+
 #ifndef CONFIG_PARAVIRT
 #define paravirt_post_allocator_init()	do {} while (0)
 #endif
@@ -43,26 +61,23 @@ char *machine_specific_memory_setup(void);
  */
 extern struct boot_params boot_params;
 
-#ifdef __i386__
 /*
  * Do NOT EVER look at the BIOS memory size location.
  * It does not work on many machines.
  */
 #define LOWMEMSIZE()	(0x9f000)
 
-struct e820entry;
-
-char * __init machine_specific_memory_setup(void);
-char *memory_setup(void);
+#ifdef __i386__
 
-int __init copy_e820_map(struct e820entry *biosmap, int nr_map);
-int __init sanitize_e820_map(struct e820entry *biosmap, char *pnr_map);
-void __init add_memory_region(unsigned long long start,
-			      unsigned long long size, int type);
+void __init i386_start_kernel(void);
+extern void probe_roms(void);
 
+extern unsigned long init_pg_tables_start;
 extern unsigned long init_pg_tables_end;
 
-
+#else
+void __init x86_64_start_kernel(char *real_mode);
+void __init x86_64_start_reservations(char *real_mode_data);
 
 #endif /* __i386__ */
 #endif /* _SETUP */
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
index 1ebaa5cd3112..c2784b3e0b77 100644
--- a/include/asm-x86/smp.h
+++ b/include/asm-x86/smp.h
@@ -29,21 +29,12 @@ extern int smp_num_siblings;
 extern unsigned int num_processors;
 extern cpumask_t cpu_initialized;
 
-#ifdef CONFIG_SMP
-extern u16 x86_cpu_to_apicid_init[];
-extern u16 x86_bios_cpu_apicid_init[];
-extern void *x86_cpu_to_apicid_early_ptr;
-extern void *x86_bios_cpu_apicid_early_ptr;
-#else
-#define x86_cpu_to_apicid_early_ptr NULL
-#define x86_bios_cpu_apicid_early_ptr NULL
-#endif
-
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
-DECLARE_PER_CPU(u16, x86_cpu_to_apicid);
-DECLARE_PER_CPU(u16, x86_bios_cpu_apicid);
+
+DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
 
 /* Static state in head.S used to set up a CPU */
 extern struct {
@@ -59,9 +50,9 @@ struct smp_ops {
 
 	void (*smp_send_stop)(void);
 	void (*smp_send_reschedule)(int cpu);
-	int (*smp_call_function_mask)(cpumask_t mask,
-				      void (*func)(void *info), void *info,
-				      int wait);
+
+	void (*send_call_func_ipi)(cpumask_t mask);
+	void (*send_call_func_single_ipi)(int cpu);
 };
 
 /* Globals due to paravirt */
@@ -103,23 +94,26 @@ static inline void smp_send_reschedule(int cpu)
 	smp_ops.smp_send_reschedule(cpu);
 }
 
-static inline int smp_call_function_mask(cpumask_t mask,
-					 void (*func) (void *info), void *info,
-					 int wait)
+static inline void arch_send_call_function_single_ipi(int cpu)
+{
+	smp_ops.send_call_func_single_ipi(cpu);
+}
+
+static inline void arch_send_call_function_ipi(cpumask_t mask)
 {
-	return smp_ops.smp_call_function_mask(mask, func, info, wait);
+	smp_ops.send_call_func_ipi(mask);
 }
 
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void native_smp_cpus_done(unsigned int max_cpus);
 int native_cpu_up(unsigned int cpunum);
+void native_send_call_func_ipi(cpumask_t mask);
+void native_send_call_func_single_ipi(int cpu);
 
 extern int __cpu_disable(void);
 extern void __cpu_die(unsigned int cpu);
 
-extern void prefill_possible_map(void);
-
 void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
 
@@ -130,6 +124,14 @@ static inline int num_booting_cpus(void)
 }
 #endif /* CONFIG_SMP */
 
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_CPU)
+extern void prefill_possible_map(void);
+#else
+static inline void prefill_possible_map(void)
+{
+}
+#endif
+
 extern unsigned disabled_cpus __cpuinitdata;
 
 #ifdef CONFIG_X86_32_SMP
@@ -197,12 +199,8 @@ static inline int hard_smp_processor_id(void)
 #endif /* CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_HOTPLUG_CPU
-extern void cpu_exit_clear(void);
 extern void cpu_uninit(void);
 #endif
 
-extern void smp_alloc_memory(void);
-extern void lock_ipi_call_lock(void);
-extern void unlock_ipi_call_lock(void);
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/include/asm-x86/srat.h b/include/asm-x86/srat.h
index f4bba131d068..774c919dc232 100644
--- a/include/asm-x86/srat.h
+++ b/include/asm-x86/srat.h
@@ -27,11 +27,13 @@
 #ifndef _ASM_SRAT_H_
 #define _ASM_SRAT_H_
 
-#ifndef CONFIG_ACPI_SRAT
-#error CONFIG_ACPI_SRAT not defined, and srat.h header has been included
-#endif
-
+#ifdef CONFIG_ACPI_NUMA
 extern int get_memcfg_from_srat(void);
-extern unsigned long *get_zholes_size(int);
+#else
+static inline int get_memcfg_from_srat(void)
+{
+	return 0;
+}
+#endif
 
 #endif /* _ASM_SRAT_H_ */
diff --git a/include/asm-x86/string_32.h b/include/asm-x86/string_32.h
index b49369ad9a61..193578cd1fd9 100644
--- a/include/asm-x86/string_32.h
+++ b/include/asm-x86/string_32.h
@@ -29,81 +29,116 @@ extern char *strchr(const char *s, int c);
 #define __HAVE_ARCH_STRLEN
 extern size_t strlen(const char *s);
 
-static __always_inline void * __memcpy(void * to, const void * from, size_t n)
+static __always_inline void *__memcpy(void *to, const void *from, size_t n)
 {
-int d0, d1, d2;
-__asm__ __volatile__(
-	"rep ; movsl\n\t"
-	"movl %4,%%ecx\n\t"
-	"andl $3,%%ecx\n\t"
-	"jz 1f\n\t"
-	"rep ; movsb\n\t"
-	"1:"
-	: "=&c" (d0), "=&D" (d1), "=&S" (d2)
-	: "0" (n/4), "g" (n), "1" ((long) to), "2" ((long) from)
-	: "memory");
-return (to);
+	int d0, d1, d2;
+	asm volatile("rep ; movsl\n\t"
+		     "movl %4,%%ecx\n\t"
+		     "andl $3,%%ecx\n\t"
+		     "jz 1f\n\t"
+		     "rep ; movsb\n\t"
+		     "1:"
+		     : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		     : "0" (n / 4), "g" (n), "1" ((long)to), "2" ((long)from)
+		     : "memory");
+	return to;
 }
 
 /*
  * This looks ugly, but the compiler can optimize it totally,
  * as the count is constant.
  */
-static __always_inline void * __constant_memcpy(void * to, const void * from, size_t n)
+static __always_inline void *__constant_memcpy(void *to, const void *from,
+					       size_t n)
 {
 	long esi, edi;
-	if (!n) return to;
-#if 1	/* want to do small copies with non-string ops? */
+	if (!n)
+		return to;
+
 	switch (n) {
-		case 1: *(char*)to = *(char*)from; return to;
-		case 2: *(short*)to = *(short*)from; return to;
-		case 4: *(int*)to = *(int*)from; return to;
-#if 1	/* including those doable with two moves? */
-		case 3: *(short*)to = *(short*)from;
-			*((char*)to+2) = *((char*)from+2); return to;
-		case 5: *(int*)to = *(int*)from;
-			*((char*)to+4) = *((char*)from+4); return to;
-		case 6: *(int*)to = *(int*)from;
-			*((short*)to+2) = *((short*)from+2); return to;
-		case 8: *(int*)to = *(int*)from;
-			*((int*)to+1) = *((int*)from+1); return to;
-#endif
+	case 1:
+		*(char *)to = *(char *)from;
+		return to;
+	case 2:
+		*(short *)to = *(short *)from;
+		return to;
+	case 4:
+		*(int *)to = *(int *)from;
+		return to;
+
+	case 3:
+		*(short *)to = *(short *)from;
+		*((char *)to + 2) = *((char *)from + 2);
+		return to;
+	case 5:
+		*(int *)to = *(int *)from;
+		*((char *)to + 4) = *((char *)from + 4);
+		return to;
+	case 6:
+		*(int *)to = *(int *)from;
+		*((short *)to + 2) = *((short *)from + 2);
+		return to;
+	case 8:
+		*(int *)to = *(int *)from;
+		*((int *)to + 1) = *((int *)from + 1);
+		return to;
 	}
-#endif
-	esi = (long) from;
-	edi = (long) to;
-	if (n >= 5*4) {
+
+	esi = (long)from;
+	edi = (long)to;
+	if (n >= 5 * 4) {
 		/* large block: use rep prefix */
 		int ecx;
-		__asm__ __volatile__(
-			"rep ; movsl"
-			: "=&c" (ecx), "=&D" (edi), "=&S" (esi)
-			: "0" (n/4), "1" (edi),"2" (esi)
-			: "memory"
+		asm volatile("rep ; movsl"
+			     : "=&c" (ecx), "=&D" (edi), "=&S" (esi)
+			     : "0" (n / 4), "1" (edi), "2" (esi)
+			     : "memory"
 		);
 	} else {
 		/* small block: don't clobber ecx + smaller code */
-		if (n >= 4*4) __asm__ __volatile__("movsl"
-			:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-		if (n >= 3*4) __asm__ __volatile__("movsl"
-			:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-		if (n >= 2*4) __asm__ __volatile__("movsl"
-			:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-		if (n >= 1*4) __asm__ __volatile__("movsl"
-			:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
+		if (n >= 4 * 4)
+			asm volatile("movsl"
+				     : "=&D"(edi), "=&S"(esi)
+				     : "0"(edi), "1"(esi)
+				     : "memory");
+		if (n >= 3 * 4)
+			asm volatile("movsl"
+				     : "=&D"(edi), "=&S"(esi)
+				     : "0"(edi), "1"(esi)
+				     : "memory");
+		if (n >= 2 * 4)
+			asm volatile("movsl"
+				     : "=&D"(edi), "=&S"(esi)
+				     : "0"(edi), "1"(esi)
+				     : "memory");
+		if (n >= 1 * 4)
+			asm volatile("movsl"
+				     : "=&D"(edi), "=&S"(esi)
+				     : "0"(edi), "1"(esi)
+				     : "memory");
 	}
 	switch (n % 4) {
 		/* tail */
-		case 0: return to;
-		case 1: __asm__ __volatile__("movsb"
-			:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-			return to;
-		case 2: __asm__ __volatile__("movsw"
-			:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-			return to;
-		default: __asm__ __volatile__("movsw\n\tmovsb"
-			:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-			return to;
+	case 0:
+		return to;
+	case 1:
+		asm volatile("movsb"
+			     : "=&D"(edi), "=&S"(esi)
+			     : "0"(edi), "1"(esi)
+			     : "memory");
+		return to;
+	case 2:
+		asm volatile("movsw"
+			     : "=&D"(edi), "=&S"(esi)
+			     : "0"(edi), "1"(esi)
+			     : "memory");
+		return to;
+	default:
+		asm volatile("movsw\n\tmovsb"
+			     : "=&D"(edi), "=&S"(esi)
+			     : "0"(edi), "1"(esi)
+			     : "memory");
+		return to;
 	}
 }
 
@@ -117,87 +152,86 @@ static __always_inline void * __constant_memcpy(void * to, const void * from, si
  *	This CPU favours 3DNow strongly (eg AMD Athlon)
  */
 
-static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
+static inline void *__constant_memcpy3d(void *to, const void *from, size_t len)
 {
 	if (len < 512)
 		return __constant_memcpy(to, from, len);
 	return _mmx_memcpy(to, from, len);
 }
 
-static __inline__ void *__memcpy3d(void *to, const void *from, size_t len)
+static inline void *__memcpy3d(void *to, const void *from, size_t len)
 {
 	if (len < 512)
 		return __memcpy(to, from, len);
 	return _mmx_memcpy(to, from, len);
 }
 
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy3d((t),(f),(n)) : \
- __memcpy3d((t),(f),(n)))
+#define memcpy(t, f, n)				\
+	(__builtin_constant_p((n))		\
+	 ? __constant_memcpy3d((t), (f), (n))	\
+	 : __memcpy3d((t), (f), (n)))
 
 #else
 
 /*
  *	No 3D Now!
  */
- 
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy((t),(f),(n)) : \
- __memcpy((t),(f),(n)))
+
+#define memcpy(t, f, n)				\
+	(__builtin_constant_p((n))		\
+	 ? __constant_memcpy((t), (f), (n))	\
+	 : __memcpy((t), (f), (n)))
 
 #endif
 
 #define __HAVE_ARCH_MEMMOVE
-void *memmove(void * dest,const void * src, size_t n);
+void *memmove(void *dest, const void *src, size_t n);
 
 #define memcmp __builtin_memcmp
 
 #define __HAVE_ARCH_MEMCHR
-extern void *memchr(const void * cs,int c,size_t count);
+extern void *memchr(const void *cs, int c, size_t count);
 
-static inline void * __memset_generic(void * s, char c,size_t count)
+static inline void *__memset_generic(void *s, char c, size_t count)
 {
-int d0, d1;
-__asm__ __volatile__(
-	"rep\n\t"
-	"stosb"
-	: "=&c" (d0), "=&D" (d1)
-	:"a" (c),"1" (s),"0" (count)
-	:"memory");
-return s;
+	int d0, d1;
+	asm volatile("rep\n\t"
+		     "stosb"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (c), "1" (s), "0" (count)
+		     : "memory");
+	return s;
 }
 
 /* we might want to write optimized versions of these later */
-#define __constant_count_memset(s,c,count) __memset_generic((s),(c),(count))
+#define __constant_count_memset(s, c, count) __memset_generic((s), (c), (count))
 
 /*
- * memset(x,0,y) is a reasonably common thing to do, so we want to fill
+ * memset(x, 0, y) is a reasonably common thing to do, so we want to fill
  * things 32 bits at a time even when we don't know the size of the
  * area at compile-time..
  */
-static __always_inline void * __constant_c_memset(void * s, unsigned long c, size_t count)
+static __always_inline
+void *__constant_c_memset(void *s, unsigned long c, size_t count)
 {
-int d0, d1;
-__asm__ __volatile__(
-	"rep ; stosl\n\t"
-	"testb $2,%b3\n\t"
-	"je 1f\n\t"
-	"stosw\n"
-	"1:\ttestb $1,%b3\n\t"
-	"je 2f\n\t"
-	"stosb\n"
-	"2:"
-	:"=&c" (d0), "=&D" (d1)
-	:"a" (c), "q" (count), "0" (count/4), "1" ((long) s)
-	:"memory");
-return (s);	
+	int d0, d1;
+	asm volatile("rep ; stosl\n\t"
+		     "testb $2,%b3\n\t"
+		     "je 1f\n\t"
+		     "stosw\n"
+		     "1:\ttestb $1,%b3\n\t"
+		     "je 2f\n\t"
+		     "stosb\n"
+		     "2:"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (c), "q" (count), "0" (count/4), "1" ((long)s)
+		     : "memory");
+	return s;
 }
 
 /* Added by Gertjan van Wingerde to make minix and sysv module work */
 #define __HAVE_ARCH_STRNLEN
-extern size_t strnlen(const char * s, size_t count);
+extern size_t strnlen(const char *s, size_t count);
 /* end of additional stuff */
 
 #define __HAVE_ARCH_STRSTR
@@ -207,66 +241,85 @@ extern char *strstr(const char *cs, const char *ct);
  * This looks horribly ugly, but the compiler can optimize it totally,
  * as we by now know that both pattern and count is constant..
  */
-static __always_inline void * __constant_c_and_count_memset(void * s, unsigned long pattern, size_t count)
+static __always_inline
+void *__constant_c_and_count_memset(void *s, unsigned long pattern,
+				    size_t count)
 {
 	switch (count) {
+	case 0:
+		return s;
+	case 1:
+		*(unsigned char *)s = pattern & 0xff;
+		return s;
+	case 2:
+		*(unsigned short *)s = pattern & 0xffff;
+		return s;
+	case 3:
+		*(unsigned short *)s = pattern & 0xffff;
+		*((unsigned char *)s + 2) = pattern & 0xff;
+		return s;
+	case 4:
+		*(unsigned long *)s = pattern;
+		return s;
+	}
+
+#define COMMON(x)							\
+	asm volatile("rep ; stosl"					\
+		     x							\
+		     : "=&c" (d0), "=&D" (d1)				\
+		     : "a" (eax), "0" (count/4), "1" ((long)s)	\
+		     : "memory")
+
+	{
+		int d0, d1;
+#if __GNUC__ == 4 && __GNUC_MINOR__ == 0
+		/* Workaround for broken gcc 4.0 */
+		register unsigned long eax asm("%eax") = pattern;
+#else
+		unsigned long eax = pattern;
+#endif
+
+		switch (count % 4) {
 		case 0:
+			COMMON("");
 			return s;
 		case 1:
-			*(unsigned char *)s = pattern & 0xff;
+			COMMON("\n\tstosb");
 			return s;
 		case 2:
-			*(unsigned short *)s = pattern & 0xffff;
+			COMMON("\n\tstosw");
 			return s;
-		case 3:
-			*(unsigned short *)s = pattern & 0xffff;
-			*(2+(unsigned char *)s) = pattern & 0xff;
-			return s;
-		case 4:
-			*(unsigned long *)s = pattern;
+		default:
+			COMMON("\n\tstosw\n\tstosb");
 			return s;
+		}
 	}
-#define COMMON(x) \
-__asm__  __volatile__( \
-	"rep ; stosl" \
-	x \
-	: "=&c" (d0), "=&D" (d1) \
-	: "a" (pattern),"0" (count/4),"1" ((long) s) \
-	: "memory")
-{
-	int d0, d1;
-	switch (count % 4) {
-		case 0: COMMON(""); return s;
-		case 1: COMMON("\n\tstosb"); return s;
-		case 2: COMMON("\n\tstosw"); return s;
-		default: COMMON("\n\tstosw\n\tstosb"); return s;
-	}
-}
-  
+
 #undef COMMON
 }
 
-#define __constant_c_x_memset(s, c, count) \
-(__builtin_constant_p(count) ? \
- __constant_c_and_count_memset((s),(c),(count)) : \
- __constant_c_memset((s),(c),(count)))
+#define __constant_c_x_memset(s, c, count)			\
+	(__builtin_constant_p(count)				\
+	 ? __constant_c_and_count_memset((s), (c), (count))	\
+	 : __constant_c_memset((s), (c), (count)))
 
-#define __memset(s, c, count) \
-(__builtin_constant_p(count) ? \
- __constant_count_memset((s),(c),(count)) : \
- __memset_generic((s),(c),(count)))
+#define __memset(s, c, count)				\
+	(__builtin_constant_p(count)			\
+	 ? __constant_count_memset((s), (c), (count))	\
+	 : __memset_generic((s), (c), (count)))
 
 #define __HAVE_ARCH_MEMSET
-#define memset(s, c, count) \
-(__builtin_constant_p(c) ? \
- __constant_c_x_memset((s),(0x01010101UL*(unsigned char)(c)),(count)) : \
- __memset((s),(c),(count)))
+#define memset(s, c, count)						\
+	(__builtin_constant_p(c)					\
+	 ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \
+				 (count))				\
+	 : __memset((s), (c), (count)))
 
 /*
  * find the first occurrence of byte 'c', or 1 past the area if none
  */
 #define __HAVE_ARCH_MEMSCAN
-extern void *memscan(void * addr, int c, size_t size);
+extern void *memscan(void *addr, int c, size_t size);
 
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-x86/suspend_32.h b/include/asm-x86/suspend_32.h
index 24e1c080aa8a..8675c6782a7d 100644
--- a/include/asm-x86/suspend_32.h
+++ b/include/asm-x86/suspend_32.h
@@ -3,6 +3,9 @@
  * Based on code
  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
  */
+#ifndef __ASM_X86_32_SUSPEND_H
+#define __ASM_X86_32_SUSPEND_H
+
 #include <asm/desc.h>
 #include <asm/i387.h>
 
@@ -44,3 +47,5 @@ static inline void acpi_save_register_state(unsigned long return_point)
 /* routines for saving/restoring kernel state */
 extern int acpi_save_state_mem(void);
 #endif
+
+#endif /* __ASM_X86_32_SUSPEND_H */
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
index a2f04cd79b29..983ce37c491f 100644
--- a/include/asm-x86/system.h
+++ b/include/asm-x86/system.h
@@ -136,7 +136,7 @@ __asm__ __volatile__ ("movw %%dx,%1\n\t" \
 #define set_base(ldt, base) _set_base(((char *)&(ldt)) , (base))
 #define set_limit(ldt, limit) _set_limit(((char *)&(ldt)) , ((limit)-1))
 
-extern void load_gs_index(unsigned);
+extern void native_load_gs_index(unsigned);
 
 /*
  * Load a segment. Fall back on loading the zero
@@ -153,14 +153,14 @@ extern void load_gs_index(unsigned);
 		     "jmp 2b\n"			\
 		     ".previous\n"		\
 		     _ASM_EXTABLE(1b,3b)	\
-		     : :"r" (value), "r" (0))
+		     : :"r" (value), "r" (0) : "memory")
 
 
 /*
  * Save a segment register away
  */
 #define savesegment(seg, value)				\
-	asm volatile("mov %%" #seg ",%0":"=rm" (value))
+	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
 static inline unsigned long get_limit(unsigned long segment)
 {
@@ -282,6 +282,7 @@ static inline void native_wbinvd(void)
 #ifdef CONFIG_X86_64
 #define read_cr8()	(native_read_cr8())
 #define write_cr8(x)	(native_write_cr8(x))
+#define load_gs_index   native_load_gs_index
 #endif
 
 /* Clear the 'TS' bit */
@@ -289,7 +290,7 @@ static inline void native_wbinvd(void)
 
 #endif/* CONFIG_PARAVIRT */
 
-#define stts() write_cr0(8 | read_cr0())
+#define stts() write_cr0(read_cr0() | X86_CR0_TS)
 
 #endif /* __KERNEL__ */
 
@@ -303,7 +304,6 @@ static inline void clflush(volatile void *__p)
 void disable_hlt(void);
 void enable_hlt(void);
 
-extern int es7000_plat;
 void cpu_idle_wait(void);
 
 extern unsigned long arch_align_stack(unsigned long sp);
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
index 77244f17993f..895339d2bc0b 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -1,9 +1,253 @@
+/* thread_info.h: low-level thread information
+ *
+ * Copyright (C) 2002  David Howells (dhowells@redhat.com)
+ * - Incorporating suggestions made by Linus Torvalds and Dave Miller
+ */
+
 #ifndef _ASM_X86_THREAD_INFO_H
+#define _ASM_X86_THREAD_INFO_H
+
+#include <linux/compiler.h>
+#include <asm/page.h>
+#include <asm/types.h>
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - this struct shares the supervisor stack pages
+ */
+#ifndef __ASSEMBLY__
+struct task_struct;
+struct exec_domain;
+#include <asm/processor.h>
+
+struct thread_info {
+	struct task_struct	*task;		/* main task structure */
+	struct exec_domain	*exec_domain;	/* execution domain */
+	unsigned long		flags;		/* low level flags */
+	__u32			status;		/* thread synchronous flags */
+	__u32			cpu;		/* current CPU */
+	int			preempt_count;	/* 0 => preemptable,
+						   <0 => BUG */
+	mm_segment_t		addr_limit;
+	struct restart_block    restart_block;
+	void __user		*sysenter_return;
+#ifdef CONFIG_X86_32
+	unsigned long           previous_esp;   /* ESP of the previous stack in
+						   case of nested (IRQ) stacks
+						*/
+	__u8			supervisor_stack[0];
+#endif
+};
+
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task		= &tsk,			\
+	.exec_domain	= &default_exec_domain,	\
+	.flags		= 0,			\
+	.cpu		= 0,			\
+	.preempt_count	= 1,			\
+	.addr_limit	= KERNEL_DS,		\
+	.restart_block = {			\
+		.fn = do_no_restart_syscall,	\
+	},					\
+}
+
+#define init_thread_info	(init_thread_union.thread_info)
+#define init_stack		(init_thread_union.stack)
+
+#else /* !__ASSEMBLY__ */
+
+#include <asm/asm-offsets.h>
+
+#endif
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files
+ *   may need to access
+ * - pending work-to-be-done flags are in LSW
+ * - other flags in MSW
+ * Warning: layout of LSW is hardcoded in entry.S
+ */
+#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_SIGPENDING		2	/* signal pending */
+#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
+#define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
+#define TIF_IRET		5	/* force IRET */
 #ifdef CONFIG_X86_32
-# include "thread_info_32.h"
+#define TIF_SYSCALL_EMU		6	/* syscall emulation active */
+#endif
+#define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
+#define TIF_SECCOMP		8	/* secure computing */
+#define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
+#define TIF_HRTICK_RESCHED	11	/* reprogram hrtick timer */
+#define TIF_NOTSC		16	/* TSC is not accessible in userland */
+#define TIF_IA32		17	/* 32bit process */
+#define TIF_FORK		18	/* ret_from_fork */
+#define TIF_ABI_PENDING		19
+#define TIF_MEMDIE		20
+#define TIF_DEBUG		21	/* uses debug registers */
+#define TIF_IO_BITMAP		22	/* uses I/O bitmap */
+#define TIF_FREEZE		23	/* is freezing for suspend */
+#define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
+#define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
+#define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
+#define TIF_BTS_TRACE_TS	27      /* record scheduling event timestamps */
+
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_IRET		(1 << TIF_IRET)
+#ifdef CONFIG_X86_32
+#define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #else
-# include "thread_info_64.h"
+#define _TIF_SYSCALL_EMU	0
 #endif
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
+#define _TIF_HRTICK_RESCHED	(1 << TIF_HRTICK_RESCHED)
+#define _TIF_NOTSC		(1 << TIF_NOTSC)
+#define _TIF_IA32		(1 << TIF_IA32)
+#define _TIF_FORK		(1 << TIF_FORK)
+#define _TIF_ABI_PENDING	(1 << TIF_ABI_PENDING)
+#define _TIF_DEBUG		(1 << TIF_DEBUG)
+#define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
+#define _TIF_FREEZE		(1 << TIF_FREEZE)
+#define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
+#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
+#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_BTS_TRACE_TS	(1 << TIF_BTS_TRACE_TS)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK							\
+	(0x0000FFFF &							\
+	 ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|	\
+	 _TIF_SECCOMP|_TIF_SYSCALL_EMU))
+
+/* work to do on any return to user space */
+#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
+
+/* Only used for 64 bit */
+#define _TIF_DO_NOTIFY_MASK						\
+	(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
+
+/* flags to check in __switch_to() */
+#define _TIF_WORK_CTXSW							\
+	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS| \
+								_TIF_NOTSC)
+
+#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
+#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
+
+#define PREEMPT_ACTIVE		0x10000000
+
+/* thread information allocation */
+#ifdef CONFIG_DEBUG_STACK_USAGE
+#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
+#else
+#define THREAD_FLAGS GFP_KERNEL
+#endif
+
+#define alloc_thread_info(tsk)						\
+	((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
+
+#ifdef CONFIG_X86_32
+
+#define STACK_WARN	(THREAD_SIZE/8)
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#ifndef __ASSEMBLY__
+
+
+/* how to get the current stack pointer from C */
+register unsigned long current_stack_pointer asm("esp") __used;
+
+/* how to get the thread information struct from C */
+static inline struct thread_info *current_thread_info(void)
+{
+	return (struct thread_info *)
+		(current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
+#else /* !__ASSEMBLY__ */
+
+/* how to get the thread information struct from ASM */
+#define GET_THREAD_INFO(reg)	 \
+	movl $-THREAD_SIZE, reg; \
+	andl %esp, reg
+
+/* use this one if reg already contains %esp */
+#define GET_THREAD_INFO_WITH_ESP(reg) \
+	andl $-THREAD_SIZE, reg
+
+#endif
+
+#else /* X86_32 */
+
+#include <asm/pda.h>
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#ifndef __ASSEMBLY__
+static inline struct thread_info *current_thread_info(void)
+{
+	struct thread_info *ti;
+	ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
+	return ti;
+}
+
+/* do not use in interrupt context */
+static inline struct thread_info *stack_thread_info(void)
+{
+	struct thread_info *ti;
+	asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
+	return ti;
+}
+
+#else /* !__ASSEMBLY__ */
+
+/* how to get the thread information struct from ASM */
+#define GET_THREAD_INFO(reg) \
+	movq %gs:pda_kernelstack,reg ; \
+	subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
+
+#endif
+
+#endif /* !X86_32 */
+
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_USEDFPU		0x0001	/* FPU was used by this task
+					   this quantum (SMP) */
+#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
+#define TS_POLLING		0x0004	/* true if in idle loop
+					   and not sleeping */
+#define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
+
+#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
+
+#ifndef __ASSEMBLY__
+#define HAVE_SET_RESTORE_SIGMASK	1
+static inline void set_restore_sigmask(void)
+{
+	struct thread_info *ti = current_thread_info();
+	ti->status |= TS_RESTORE_SIGMASK;
+	set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
+}
+#endif	/* !__ASSEMBLY__ */
 
 #ifndef __ASSEMBLY__
 extern void arch_task_cache_init(void);
diff --git a/include/asm-x86/thread_info_32.h b/include/asm-x86/thread_info_32.h
deleted file mode 100644
index b6338829d1a8..000000000000
--- a/include/asm-x86/thread_info_32.h
+++ /dev/null
@@ -1,205 +0,0 @@
-/* thread_info.h: i386 low-level thread information
- *
- * Copyright (C) 2002  David Howells (dhowells@redhat.com)
- * - Incorporating suggestions made by Linus Torvalds and Dave Miller
- */
-
-#ifndef _ASM_THREAD_INFO_H
-#define _ASM_THREAD_INFO_H
-
-#ifdef __KERNEL__
-
-#include <linux/compiler.h>
-#include <asm/page.h>
-
-#ifndef __ASSEMBLY__
-#include <asm/processor.h>
-#endif
-
-/*
- * low level task data that entry.S needs immediate access to
- * - this struct should fit entirely inside of one cache line
- * - this struct shares the supervisor stack pages
- * - if the contents of this structure are changed,
- *   the assembly constants must also be changed
- */
-#ifndef __ASSEMBLY__
-
-struct thread_info {
-	struct task_struct	*task;		/* main task structure */
-	struct exec_domain	*exec_domain;	/* execution domain */
-	unsigned long		flags;		/* low level flags */
-	unsigned long		status;		/* thread-synchronous flags */
-	__u32			cpu;		/* current CPU */
-	int			preempt_count;	/* 0 => preemptable,
-						   <0 => BUG */
-	mm_segment_t		addr_limit;	/* thread address space:
-						   0-0xBFFFFFFF user-thread
-						   0-0xFFFFFFFF kernel-thread
-						*/
-	void			*sysenter_return;
-	struct restart_block    restart_block;
-	unsigned long           previous_esp;   /* ESP of the previous stack in
-						   case of nested (IRQ) stacks
-						*/
-	__u8			supervisor_stack[0];
-};
-
-#else /* !__ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-
-#endif
-
-#define PREEMPT_ACTIVE		0x10000000
-#ifdef CONFIG_4KSTACKS
-#define THREAD_SIZE            (4096)
-#else
-#define THREAD_SIZE		(8192)
-#endif
-
-#define STACK_WARN             (THREAD_SIZE/8)
-/*
- * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
-
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.task		= &tsk,			\
-	.exec_domain	= &default_exec_domain,	\
-	.flags		= 0,			\
-	.cpu		= 0,			\
-	.preempt_count	= 1,			\
-	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
-}
-
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
-
-/* how to get the current stack pointer from C */
-register unsigned long current_stack_pointer asm("esp") __used;
-
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	return (struct thread_info *)
-		(current_stack_pointer & ~(THREAD_SIZE - 1));
-}
-
-/* thread information allocation */
-#ifdef CONFIG_DEBUG_STACK_USAGE
-#define alloc_thread_info(tsk) ((struct thread_info *)			\
-	__get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(THREAD_SIZE)))
-#else
-#define alloc_thread_info(tsk) ((struct thread_info *)			\
-	__get_free_pages(GFP_KERNEL, get_order(THREAD_SIZE)))
-#endif
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg)	 \
-	movl $-THREAD_SIZE, reg; \
-	andl %esp, reg
-
-/* use this one if reg already contains %esp */
-#define GET_THREAD_INFO_WITH_ESP(reg) \
-	andl $-THREAD_SIZE, reg
-
-#endif
-
-/*
- * thread information flags
- * - these are process state flags that various
- *   assembly files may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- */
-#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
-#define TIF_SIGPENDING		1	/* signal pending */
-#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_SINGLESTEP		3	/* restore singlestep on return to
-					   user mode */
-#define TIF_IRET		4	/* return with iret */
-#define TIF_SYSCALL_EMU		5	/* syscall emulation active */
-#define TIF_SYSCALL_AUDIT	6	/* syscall auditing active */
-#define TIF_SECCOMP		7	/* secure computing */
-#define TIF_HRTICK_RESCHED	9	/* reprogram hrtick timer */
-#define TIF_MEMDIE		16
-#define TIF_DEBUG		17	/* uses debug registers */
-#define TIF_IO_BITMAP		18	/* uses I/O bitmap */
-#define TIF_FREEZE		19	/* is freezing for suspend */
-#define TIF_NOTSC		20	/* TSC is not accessible in userland */
-#define TIF_FORCED_TF		21	/* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR		22	/* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR 	23      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS        24      /* record scheduling event timestamps */
-
-#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
-#define _TIF_IRET		(1 << TIF_IRET)
-#define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
-#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
-#define _TIF_HRTICK_RESCHED	(1 << TIF_HRTICK_RESCHED)
-#define _TIF_DEBUG		(1 << TIF_DEBUG)
-#define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
-#define _TIF_NOTSC		(1 << TIF_NOTSC)
-#define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
-#define _TIF_BTS_TRACE_TS	(1 << TIF_BTS_TRACE_TS)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK							\
-	(0x0000FFFF & ~(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |	\
-			_TIF_SECCOMP | _TIF_SYSCALL_EMU))
-/* work to do on any return to u-space */
-#define _TIF_ALLWORK_MASK	(0x0000FFFF & ~_TIF_SECCOMP)
-
-/* flags to check in __switch_to() */
-#define _TIF_WORK_CTXSW						\
-	(_TIF_IO_BITMAP | _TIF_NOTSC | _TIF_DEBUGCTLMSR |	\
-	 _TIF_DS_AREA_MSR | _TIF_BTS_TRACE_TS)
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
-#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW | _TIF_DEBUG)
-
-
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_USEDFPU		0x0001	/* FPU was used by this task
-					   this quantum (SMP) */
-#define TS_POLLING		0x0002	/* True if in idle loop
-					   and not sleeping */
-#define TS_RESTORE_SIGMASK	0x0004	/* restore signal mask in do_signal() */
-
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	set_bit(TIF_SIGPENDING, &ti->flags);
-}
-#endif	/* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_THREAD_INFO_H */
diff --git a/include/asm-x86/thread_info_64.h b/include/asm-x86/thread_info_64.h
deleted file mode 100644
index cb69f70abba1..000000000000
--- a/include/asm-x86/thread_info_64.h
+++ /dev/null
@@ -1,195 +0,0 @@
-/* thread_info.h: x86_64 low-level thread information
- *
- * Copyright (C) 2002  David Howells (dhowells@redhat.com)
- * - Incorporating suggestions made by Linus Torvalds and Dave Miller
- */
-
-#ifndef _ASM_THREAD_INFO_H
-#define _ASM_THREAD_INFO_H
-
-#ifdef __KERNEL__
-
-#include <asm/page.h>
-#include <asm/types.h>
-#include <asm/pda.h>
-
-/*
- * low level task data that entry.S needs immediate access to
- * - this struct should fit entirely inside of one cache line
- * - this struct shares the supervisor stack pages
- */
-#ifndef __ASSEMBLY__
-struct task_struct;
-struct exec_domain;
-#include <asm/processor.h>
-
-struct thread_info {
-	struct task_struct	*task;		/* main task structure */
-	struct exec_domain	*exec_domain;	/* execution domain */
-	__u32			flags;		/* low level flags */
-	__u32			status;		/* thread synchronous flags */
-	__u32			cpu;		/* current CPU */
-	int 			preempt_count;	/* 0 => preemptable,
-						   <0 => BUG */
-	mm_segment_t		addr_limit;
-	struct restart_block    restart_block;
-#ifdef CONFIG_IA32_EMULATION
-	void __user		*sysenter_return;
-#endif
-};
-#endif
-
-/*
- * macros/functions for gaining access to the thread information structure
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.task	       = &tsk,			\
-	.exec_domain   = &default_exec_domain,	\
-	.flags	       = 0,			\
-	.cpu	       = 0,			\
-	.preempt_count = 1,			\
-	.addr_limit     = KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
-}
-
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
-static inline struct thread_info *current_thread_info(void)
-{
-	struct thread_info *ti;
-	ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
-	return ti;
-}
-
-/* do not use in interrupt context */
-static inline struct thread_info *stack_thread_info(void)
-{
-	struct thread_info *ti;
-	asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
-	return ti;
-}
-
-/* thread information allocation */
-#ifdef CONFIG_DEBUG_STACK_USAGE
-#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
-#else
-#define THREAD_FLAGS GFP_KERNEL
-#endif
-
-#define alloc_thread_info(tsk)						\
-	((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg) \
-	movq %gs:pda_kernelstack,reg ; \
-	subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
-
-#endif
-
-/*
- * thread information flags
- * - these are process state flags that various assembly files
- *   may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- * Warning: layout of LSW is hardcoded in entry.S
- */
-#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
-#define TIF_SIGPENDING		2	/* signal pending */
-#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
-#define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
-#define TIF_IRET		5	/* force IRET */
-#define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
-#define TIF_SECCOMP		8	/* secure computing */
-#define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
-#define TIF_HRTICK_RESCHED	11	/* reprogram hrtick timer */
-/* 16 free */
-#define TIF_IA32		17	/* 32bit process */
-#define TIF_FORK		18	/* ret_from_fork */
-#define TIF_ABI_PENDING		19
-#define TIF_MEMDIE		20
-#define TIF_DEBUG		21	/* uses debug registers */
-#define TIF_IO_BITMAP		22	/* uses I/O bitmap */
-#define TIF_FREEZE		23	/* is freezing for suspend */
-#define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS	27      /* record scheduling event timestamps */
-#define TIF_NOTSC		28	/* TSC is not accessible in userland */
-
-#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
-#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_IRET		(1 << TIF_IRET)
-#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
-#define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
-#define _TIF_HRTICK_RESCHED	(1 << TIF_HRTICK_RESCHED)
-#define _TIF_IA32		(1 << TIF_IA32)
-#define _TIF_FORK		(1 << TIF_FORK)
-#define _TIF_ABI_PENDING	(1 << TIF_ABI_PENDING)
-#define _TIF_DEBUG		(1 << TIF_DEBUG)
-#define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
-#define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
-#define _TIF_BTS_TRACE_TS	(1 << TIF_BTS_TRACE_TS)
-#define _TIF_NOTSC		(1 << TIF_NOTSC)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK							\
-	(0x0000FFFF &							\
-	 ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|_TIF_SECCOMP))
-/* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
-
-#define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
-
-/* flags to check in __switch_to() */
-#define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS|_TIF_NOTSC)
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
-#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
-
-#define PREEMPT_ACTIVE     0x10000000
-
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_USEDFPU		0x0001	/* FPU was used by this task
-					   this quantum (SMP) */
-#define TS_COMPAT		0x0002	/* 32bit syscall active */
-#define TS_POLLING		0x0004	/* true if in idle loop
-					   and not sleeping */
-#define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
-
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	set_bit(TIF_SIGPENDING, &ti->flags);
-}
-#endif	/* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_THREAD_INFO_H */
diff --git a/include/asm-x86/time.h b/include/asm-x86/time.h
index bce72d7a958c..a17fa473e91d 100644
--- a/include/asm-x86/time.h
+++ b/include/asm-x86/time.h
@@ -56,4 +56,6 @@ static inline int native_set_wallclock(unsigned long nowtime)
 
 #endif /* CONFIG_PARAVIRT */
 
+extern unsigned long __init calibrate_cpu(void);
+
 #endif
diff --git a/include/asm-x86/timer.h b/include/asm-x86/timer.h
index 4f6fcb050c11..fb2a4ddddf3d 100644
--- a/include/asm-x86/timer.h
+++ b/include/asm-x86/timer.h
@@ -7,14 +7,14 @@
 #define TICK_SIZE (tick_nsec / 1000)
 
 unsigned long long native_sched_clock(void);
-unsigned long native_calculate_cpu_khz(void);
+unsigned long native_calibrate_tsc(void);
 
 extern int timer_ack;
 extern int no_timer_check;
 extern int recalibrate_cpu_khz(void);
 
 #ifndef CONFIG_PARAVIRT
-#define calculate_cpu_khz() native_calculate_cpu_khz()
+#define calibrate_tsc() native_calibrate_tsc()
 #endif
 
 /* Accelerators for sched_clock()
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index dcf3f8131d6b..90ac7718469a 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -35,79 +35,93 @@
 # endif
 #endif
 
+/* Node not present */
+#define NUMA_NO_NODE	(-1)
+
 #ifdef CONFIG_NUMA
 #include <linux/cpumask.h>
 #include <asm/mpspec.h>
 
-/* Mappings between logical cpu number and node number */
 #ifdef CONFIG_X86_32
-extern int cpu_to_node_map[];
-#else
-/* Returns the number of the current Node. */
-#define numa_node_id()		(early_cpu_to_node(raw_smp_processor_id()))
-#endif
-
-DECLARE_PER_CPU(int, x86_cpu_to_node_map);
-
-#ifdef CONFIG_SMP
-extern int x86_cpu_to_node_map_init[];
-extern void *x86_cpu_to_node_map_early_ptr;
-#else
-#define x86_cpu_to_node_map_early_ptr NULL
-#endif
 
+/* Mappings between node number and cpus on that node. */
 extern cpumask_t node_to_cpumask_map[];
 
-#define NUMA_NO_NODE	(-1)
+/* Mappings between logical cpu number and node number */
+extern int cpu_to_node_map[];
 
 /* Returns the number of the node containing CPU 'cpu' */
-#ifdef CONFIG_X86_32
-#define early_cpu_to_node(cpu)	cpu_to_node(cpu)
 static inline int cpu_to_node(int cpu)
 {
 	return cpu_to_node_map[cpu];
 }
+#define early_cpu_to_node(cpu)	cpu_to_node(cpu)
 
-#else /* CONFIG_X86_64 */
-
-#ifdef CONFIG_SMP
-static inline int early_cpu_to_node(int cpu)
+/* Returns a bitmask of CPUs on Node 'node'.
+ *
+ * Side note: this function creates the returned cpumask on the stack
+ * so with a high NR_CPUS count, excessive stack space is used.  The
+ * node_to_cpumask_ptr function should be used whenever possible.
+ */
+static inline cpumask_t node_to_cpumask(int node)
 {
-	int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
-
-	if (cpu_to_node_map)
-		return cpu_to_node_map[cpu];
-	else if (per_cpu_offset(cpu))
-		return per_cpu(x86_cpu_to_node_map, cpu);
-	else
-		return NUMA_NO_NODE;
+	return node_to_cpumask_map[node];
 }
-#else
-#define	early_cpu_to_node(cpu)	cpu_to_node(cpu)
-#endif
 
+#else /* CONFIG_X86_64 */
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_t *node_to_cpumask_map;
+
+/* Mappings between logical cpu number and node number */
+DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
+
+/* Returns the number of the current Node. */
+#define numa_node_id()		read_pda(nodenumber)
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern int cpu_to_node(int cpu);
+extern int early_cpu_to_node(int cpu);
+extern const cpumask_t *_node_to_cpumask_ptr(int node);
+extern cpumask_t node_to_cpumask(int node);
+
+#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Returns the number of the node containing CPU 'cpu' */
 static inline int cpu_to_node(int cpu)
 {
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-	if (x86_cpu_to_node_map_early_ptr) {
-		printk("KERN_NOTICE cpu_to_node(%d): usage too early!\n",
-		       (int)cpu);
-		dump_stack();
-		return ((int *)x86_cpu_to_node_map_early_ptr)[cpu];
-	}
-#endif
 	return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-#ifdef	CONFIG_NUMA
+/* Same function but used if called before per_cpu areas are setup */
+static inline int early_cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map))
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
 
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+{
+	return &node_to_cpumask_map[node];
+}
+
+/* Returns a bitmask of CPUs on Node 'node'. */
+static inline cpumask_t node_to_cpumask(int node)
+{
+	return node_to_cpumask_map[node];
+}
+
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Replace default node_to_cpumask_ptr with optimized version */
 #define node_to_cpumask_ptr(v, node)		\
-		cpumask_t *v = &(node_to_cpumask_map[node])
+		const cpumask_t *v = _node_to_cpumask_ptr(node)
 
 #define node_to_cpumask_ptr_next(v, node)	\
-			   v = &(node_to_cpumask_map[node])
-#endif
+			   v = _node_to_cpumask_ptr(node)
 
 #endif /* CONFIG_X86_64 */
 
@@ -117,20 +131,6 @@ static inline int cpu_to_node(int cpu)
  */
 #define parent_node(node) (node)
 
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return node_to_cpumask_map[node];
-}
-
-/* Returns the number of the first CPU on Node 'node'. */
-static inline int node_to_first_cpu(int node)
-{
-	cpumask_t mask = node_to_cpumask(node);
-
-	return first_cpu(mask);
-}
-
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 #define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
 
@@ -180,12 +180,44 @@ extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 #endif
 
-#else /* CONFIG_NUMA */
+#else /* !CONFIG_NUMA */
 
+#define numa_node_id()		0
+#define	cpu_to_node(cpu)	0
+#define	early_cpu_to_node(cpu)	0
+
+static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+{
+	return &cpu_online_map;
+}
+static inline cpumask_t node_to_cpumask(int node)
+{
+	return cpu_online_map;
+}
+static inline int node_to_first_cpu(int node)
+{
+	return first_cpu(cpu_online_map);
+}
+
+/* Replace default node_to_cpumask_ptr with optimized version */
+#define node_to_cpumask_ptr(v, node)		\
+		const cpumask_t *v = _node_to_cpumask_ptr(node)
+
+#define node_to_cpumask_ptr_next(v, node)	\
+			   v = _node_to_cpumask_ptr(node)
 #endif
 
 #include <asm-generic/topology.h>
 
+#ifdef CONFIG_NUMA
+/* Returns the number of the first CPU on Node 'node'. */
+static inline int node_to_first_cpu(int node)
+{
+	node_to_cpumask_ptr(mask, node);
+	return first_cpu(*mask);
+}
+#endif
+
 extern cpumask_t cpu_coregroup_map(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
@@ -193,6 +225,9 @@ extern cpumask_t cpu_coregroup_map(int cpu);
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
 #define topology_core_siblings(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_thread_siblings(cpu)		(per_cpu(cpu_sibling_map, cpu))
+
+/* indicates that pointers to the topology cpumask_t maps are valid */
+#define arch_provides_topology_pointers		yes
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
@@ -220,4 +255,4 @@ static inline void set_mp_bus_to_node(int busnum, int node)
 }
 #endif
 
-#endif
+#endif /* _ASM_X86_TOPOLOGY_H */
diff --git a/include/asm-x86/tsc.h b/include/asm-x86/tsc.h
index 548873ab5fc1..cb6f6ee45b8f 100644
--- a/include/asm-x86/tsc.h
+++ b/include/asm-x86/tsc.h
@@ -48,7 +48,6 @@ static __always_inline cycles_t vget_cycles(void)
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
-extern void init_tsc_clocksource(void);
 int check_tsc_unstable(void);
 
 /*
@@ -58,7 +57,6 @@ int check_tsc_unstable(void);
 extern void check_tsc_sync_source(int cpu);
 extern void check_tsc_sync_target(void);
 
-extern void tsc_calibrate(void);
 extern int notsc_setup(char *);
 
 #endif
diff --git a/include/asm-x86/uaccess.h b/include/asm-x86/uaccess.h
index 9fefd2947e78..f6fa4d841bbc 100644
--- a/include/asm-x86/uaccess.h
+++ b/include/asm-x86/uaccess.h
@@ -1,5 +1,453 @@
+#ifndef _ASM_UACCES_H_
+#define _ASM_UACCES_H_
+/*
+ * User space memory access functions
+ */
+#include <linux/errno.h>
+#include <linux/compiler.h>
+#include <linux/thread_info.h>
+#include <linux/prefetch.h>
+#include <linux/string.h>
+#include <asm/asm.h>
+#include <asm/page.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not.  If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
+
+#define KERNEL_DS	MAKE_MM_SEG(-1UL)
+#define USER_DS		MAKE_MM_SEG(PAGE_OFFSET)
+
+#define get_ds()	(KERNEL_DS)
+#define get_fs()	(current_thread_info()->addr_limit)
+#define set_fs(x)	(current_thread_info()->addr_limit = (x))
+
+#define segment_eq(a, b)	((a).seg == (b).seg)
+
+#define __addr_ok(addr)					\
+	((unsigned long __force)(addr) <		\
+	 (current_thread_info()->addr_limit.seg))
+
+/*
+ * Test whether a block of memory is a valid user space address.
+ * Returns 0 if the range is valid, nonzero otherwise.
+ *
+ * This is equivalent to the following test:
+ * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
+ *
+ * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
+ */
+
+#define __range_not_ok(addr, size)					\
+({									\
+	unsigned long flag, roksum;					\
+	__chk_user_ptr(addr);						\
+	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
+	    : "=&r" (flag), "=r" (roksum)				\
+	    : "1" (addr), "g" ((long)(size)),				\
+	      "rm" (current_thread_info()->addr_limit.seg));		\
+	flag;								\
+})
+
+/**
+ * access_ok: - Checks if a user space pointer is valid
+ * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
+ *        %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe
+ *        to write to a block, it is always safe to read from it.
+ * @addr: User space pointer to start of block to check
+ * @size: Size of block to check
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Checks if a pointer to a block of memory in user space is valid.
+ *
+ * Returns true (nonzero) if the memory block may be valid, false (zero)
+ * if it is definitely invalid.
+ *
+ * Note that, depending on architecture, this function probably just
+ * checks that the pointer is in the user space range - after calling
+ * this function, memory access functions may still return -EFAULT.
+ */
+#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry {
+	unsigned long insn, fixup;
+};
+
+extern int fixup_exception(struct pt_regs *regs);
+
+/*
+ * These are the main single-value transfer routines.  They automatically
+ * use the right size if we just have the right pointer type.
+ *
+ * This gets kind of ugly. We want to return _two_ values in "get_user()"
+ * and yet we don't want to do any pointers, because that is too much
+ * of a performance impact. Thus we have a few rather ugly macros here,
+ * and hide all the ugliness from the user.
+ *
+ * The "__xxx" versions of the user access functions are versions that
+ * do not verify the address space, that must have been done previously
+ * with a separate "access_ok()" call (this is used when we do multiple
+ * accesses to the same area of user memory).
+ */
+
+extern int __get_user_1(void);
+extern int __get_user_2(void);
+extern int __get_user_4(void);
+extern int __get_user_8(void);
+extern int __get_user_bad(void);
+
+#define __get_user_x(size, ret, x, ptr)		      \
+	asm volatile("call __get_user_" #size	      \
+		     : "=a" (ret),"=d" (x)	      \
+		     : "0" (ptr))		      \
+
+/* Careful: we have to cast the result to the type of the pointer
+ * for sign reasons */
+
+/**
+ * get_user: - Get a simple variable from user space.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#ifdef CONFIG_X86_32
+#define __get_user_8(__ret_gu, __val_gu, ptr)				\
+		__get_user_x(X, __ret_gu, __val_gu, ptr)
+#else
+#define __get_user_8(__ret_gu, __val_gu, ptr)				\
+		__get_user_x(8, __ret_gu, __val_gu, ptr)
+#endif
+
+#define get_user(x, ptr)						\
+({									\
+	int __ret_gu;							\
+	unsigned long __val_gu;						\
+	__chk_user_ptr(ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		__get_user_x(1, __ret_gu, __val_gu, ptr);		\
+		break;							\
+	case 2:								\
+		__get_user_x(2, __ret_gu, __val_gu, ptr);		\
+		break;							\
+	case 4:								\
+		__get_user_x(4, __ret_gu, __val_gu, ptr);		\
+		break;							\
+	case 8:								\
+		__get_user_8(__ret_gu, __val_gu, ptr);			\
+		break;							\
+	default:							\
+		__get_user_x(X, __ret_gu, __val_gu, ptr);		\
+		break;							\
+	}								\
+	(x) = (__typeof__(*(ptr)))__val_gu;				\
+	__ret_gu;							\
+})
+
+#define __put_user_x(size, x, ptr, __ret_pu)			\
+	asm volatile("call __put_user_" #size : "=a" (__ret_pu)	\
+		     :"0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+
+
+
+#ifdef CONFIG_X86_32
+#define __put_user_u64(x, addr, err)					\
+	asm volatile("1:	movl %%eax,0(%2)\n"			\
+		     "2:	movl %%edx,4(%2)\n"			\
+		     "3:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "4:	movl %3,%0\n"				\
+		     "	jmp 3b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 4b)				\
+		     _ASM_EXTABLE(2b, 4b)				\
+		     : "=r" (err)					\
+		     : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
+
+#define __put_user_x8(x, ptr, __ret_pu)				\
+	asm volatile("call __put_user_8" : "=a" (__ret_pu)	\
+		     : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+#else
+#define __put_user_u64(x, ptr, retval) \
+	__put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT)
+#define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
+#endif
+
+extern void __put_user_bad(void);
+
+/*
+ * Strange magic calling convention: pointer in %ecx,
+ * value in %eax(:%edx), return value in %eax. clobbers %rbx
+ */
+extern void __put_user_1(void);
+extern void __put_user_2(void);
+extern void __put_user_4(void);
+extern void __put_user_8(void);
+
+#ifdef CONFIG_X86_WP_WORKS_OK
+
+/**
+ * put_user: - Write a simple value into user space.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define put_user(x, ptr)					\
+({								\
+	int __ret_pu;						\
+	__typeof__(*(ptr)) __pu_val;				\
+	__chk_user_ptr(ptr);					\
+	__pu_val = x;						\
+	switch (sizeof(*(ptr))) {				\
+	case 1:							\
+		__put_user_x(1, __pu_val, ptr, __ret_pu);	\
+		break;						\
+	case 2:							\
+		__put_user_x(2, __pu_val, ptr, __ret_pu);	\
+		break;						\
+	case 4:							\
+		__put_user_x(4, __pu_val, ptr, __ret_pu);	\
+		break;						\
+	case 8:							\
+		__put_user_x8(__pu_val, ptr, __ret_pu);		\
+		break;						\
+	default:						\
+		__put_user_x(X, __pu_val, ptr, __ret_pu);	\
+		break;						\
+	}							\
+	__ret_pu;						\
+})
+
+#define __put_user_size(x, ptr, size, retval, errret)			\
+do {									\
+	retval = 0;							\
+	__chk_user_ptr(ptr);						\
+	switch (size) {							\
+	case 1:								\
+		__put_user_asm(x, ptr, retval, "b", "b", "iq", errret);	\
+		break;							\
+	case 2:								\
+		__put_user_asm(x, ptr, retval, "w", "w", "ir", errret);	\
+		break;							\
+	case 4:								\
+		__put_user_asm(x, ptr, retval, "l", "k",  "ir", errret);\
+		break;							\
+	case 8:								\
+		__put_user_u64((__typeof__(*ptr))(x), ptr, retval);	\
+		break;							\
+	default:							\
+		__put_user_bad();					\
+	}								\
+} while (0)
+
+#else
+
+#define __put_user_size(x, ptr, size, retval, errret)			\
+do {									\
+	__typeof__(*(ptr))__pus_tmp = x;				\
+	retval = 0;							\
+									\
+	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0))	\
+		retval = errret;					\
+} while (0)
+
+#define put_user(x, ptr)					\
+({								\
+	int __ret_pu;						\
+	__typeof__(*(ptr))__pus_tmp = x;			\
+	__ret_pu = 0;						\
+	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp,		\
+				       sizeof(*(ptr))) != 0))	\
+		__ret_pu = -EFAULT;				\
+	__ret_pu;						\
+})
+#endif
+
+#ifdef CONFIG_X86_32
+#define __get_user_asm_u64(x, ptr, retval, errret)	(x) = __get_user_bad()
+#else
+#define __get_user_asm_u64(x, ptr, retval, errret) \
+	 __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
+#endif
+
+#define __get_user_size(x, ptr, size, retval, errret)			\
+do {									\
+	retval = 0;							\
+	__chk_user_ptr(ptr);						\
+	switch (size) {							\
+	case 1:								\
+		__get_user_asm(x, ptr, retval, "b", "b", "=q", errret);	\
+		break;							\
+	case 2:								\
+		__get_user_asm(x, ptr, retval, "w", "w", "=r", errret);	\
+		break;							\
+	case 4:								\
+		__get_user_asm(x, ptr, retval, "l", "k", "=r", errret);	\
+		break;							\
+	case 8:								\
+		__get_user_asm_u64(x, ptr, retval, errret);		\
+		break;							\
+	default:							\
+		(x) = __get_user_bad();					\
+	}								\
+} while (0)
+
+#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
+	asm volatile("1:	mov"itype" %2,%"rtype"1\n"		\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:	mov %3,%0\n"				\
+		     "	xor"itype" %"rtype"1,%"rtype"1\n"		\
+		     "	jmp 2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : "=r" (err), ltype(x)				\
+		     : "m" (__m(addr)), "i" (errret), "0" (err))
+
+#define __put_user_nocheck(x, ptr, size)			\
+({								\
+	long __pu_err;						\
+	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
+	__pu_err;						\
+})
+
+#define __get_user_nocheck(x, ptr, size)				\
+({									\
+	long __gu_err;							\
+	unsigned long __gu_val;						\
+	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	__gu_err;							\
+})
+
+/* FIXME: this hack is definitely wrong -AK */
+struct __large_struct { unsigned long buf[100]; };
+#define __m(x) (*(struct __large_struct __user *)(x))
+
+/*
+ * Tell gcc we read from memory instead of writing: this is because
+ * we do not write to any memory gcc knows about, so there are no
+ * aliasing issues.
+ */
+#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
+	asm volatile("1:	mov"itype" %"rtype"1,%2\n"		\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:	mov %3,%0\n"				\
+		     "	jmp 2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : "=r"(err)					\
+		     : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
+/**
+ * __get_user: - Get a simple variable from user space, with less checking.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+
+#define __get_user(x, ptr)						\
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+/**
+ * __put_user: - Write a simple value into user space, with less checking.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+
+#define __put_user(x, ptr)						\
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+
+#define __get_user_unaligned __get_user
+#define __put_user_unaligned __put_user
+
+/*
+ * movsl can be slow when source and dest are not both 8-byte aligned
+ */
+#ifdef CONFIG_X86_INTEL_USERCOPY
+extern struct movsl_mask {
+	int mask;
+} ____cacheline_aligned_in_smp movsl_mask;
+#endif
+
+#define ARCH_HAS_NOCACHE_UACCESS 1
+
 #ifdef CONFIG_X86_32
 # include "uaccess_32.h"
 #else
+# define ARCH_HAS_SEARCH_EXTABLE
 # include "uaccess_64.h"
 #endif
+
+#endif
diff --git a/include/asm-x86/uaccess_32.h b/include/asm-x86/uaccess_32.h
index 8e7595c1f34e..6fdef39a0bcb 100644
--- a/include/asm-x86/uaccess_32.h
+++ b/include/asm-x86/uaccess_32.h
@@ -11,426 +11,6 @@
 #include <asm/asm.h>
 #include <asm/page.h>
 
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-
-
-#define KERNEL_DS	MAKE_MM_SEG(0xFFFFFFFFUL)
-#define USER_DS		MAKE_MM_SEG(PAGE_OFFSET)
-
-#define get_ds()	(KERNEL_DS)
-#define get_fs()	(current_thread_info()->addr_limit)
-#define set_fs(x)	(current_thread_info()->addr_limit = (x))
-
-#define segment_eq(a, b)	((a).seg == (b).seg)
-
-/*
- * movsl can be slow when source and dest are not both 8-byte aligned
- */
-#ifdef CONFIG_X86_INTEL_USERCOPY
-extern struct movsl_mask {
-	int mask;
-} ____cacheline_aligned_in_smp movsl_mask;
-#endif
-
-#define __addr_ok(addr)					\
-	((unsigned long __force)(addr) <		\
-	 (current_thread_info()->addr_limit.seg))
-
-/*
- * Test whether a block of memory is a valid user space address.
- * Returns 0 if the range is valid, nonzero otherwise.
- *
- * This is equivalent to the following test:
- * (u33)addr + (u33)size >= (u33)current->addr_limit.seg
- *
- * This needs 33-bit arithmetic. We have a carry...
- */
-#define __range_ok(addr, size)						\
-({									\
-	unsigned long flag, roksum;					\
-	__chk_user_ptr(addr);						\
-	asm("addl %3,%1 ; sbbl %0,%0; cmpl %1,%4; sbbl $0,%0"		\
-	    :"=&r" (flag), "=r" (roksum)				\
-	    :"1" (addr), "g" ((int)(size)),				\
-	    "rm" (current_thread_info()->addr_limit.seg));		\
-	flag;								\
-})
-
-/**
- * access_ok: - Checks if a user space pointer is valid
- * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
- *        %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe
- *        to write to a block, it is always safe to read from it.
- * @addr: User space pointer to start of block to check
- * @size: Size of block to check
- *
- * Context: User context only.  This function may sleep.
- *
- * Checks if a pointer to a block of memory in user space is valid.
- *
- * Returns true (nonzero) if the memory block may be valid, false (zero)
- * if it is definitely invalid.
- *
- * Note that, depending on architecture, this function probably just
- * checks that the pointer is in the user space range - after calling
- * this function, memory access functions may still return -EFAULT.
- */
-#define access_ok(type, addr, size) (likely(__range_ok(addr, size) == 0))
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
-
-/*
- * These are the main single-value transfer routines.  They automatically
- * use the right size if we just have the right pointer type.
- *
- * This gets kind of ugly. We want to return _two_ values in "get_user()"
- * and yet we don't want to do any pointers, because that is too much
- * of a performance impact. Thus we have a few rather ugly macros here,
- * and hide all the ugliness from the user.
- *
- * The "__xxx" versions of the user access functions are versions that
- * do not verify the address space, that must have been done previously
- * with a separate "access_ok()" call (this is used when we do multiple
- * accesses to the same area of user memory).
- */
-
-extern void __get_user_1(void);
-extern void __get_user_2(void);
-extern void __get_user_4(void);
-
-#define __get_user_x(size, ret, x, ptr)	      \
-	asm volatile("call __get_user_" #size \
-		     :"=a" (ret),"=d" (x)     \
-		     :"0" (ptr))
-
-
-/* Careful: we have to cast the result to the type of the pointer
- * for sign reasons */
-
-/**
- * get_user: - Get a simple variable from user space.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define get_user(x, ptr)						\
-({									\
-	int __ret_gu;							\
-	unsigned long __val_gu;						\
-	__chk_user_ptr(ptr);						\
-	switch (sizeof(*(ptr))) {					\
-	case 1:								\
-		__get_user_x(1, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	case 2:								\
-		__get_user_x(2, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	case 4:								\
-		__get_user_x(4, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	default:							\
-		__get_user_x(X, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	}								\
-	(x) = (__typeof__(*(ptr)))__val_gu;				\
-	__ret_gu;							\
-})
-
-extern void __put_user_bad(void);
-
-/*
- * Strange magic calling convention: pointer in %ecx,
- * value in %eax(:%edx), return value in %eax, no clobbers.
- */
-extern void __put_user_1(void);
-extern void __put_user_2(void);
-extern void __put_user_4(void);
-extern void __put_user_8(void);
-
-#define __put_user_1(x, ptr)					\
-	asm volatile("call __put_user_1" : "=a" (__ret_pu)	\
-		     : "0" ((typeof(*(ptr)))(x)), "c" (ptr))
-
-#define __put_user_2(x, ptr)					\
-	asm volatile("call __put_user_2" : "=a" (__ret_pu)	\
-		     : "0" ((typeof(*(ptr)))(x)), "c" (ptr))
-
-#define __put_user_4(x, ptr)					\
-	asm volatile("call __put_user_4" : "=a" (__ret_pu)	\
-		     : "0" ((typeof(*(ptr)))(x)), "c" (ptr))
-
-#define __put_user_8(x, ptr)					\
-	asm volatile("call __put_user_8" : "=a" (__ret_pu)	\
-		     : "A" ((typeof(*(ptr)))(x)), "c" (ptr))
-
-#define __put_user_X(x, ptr)					\
-	asm volatile("call __put_user_X" : "=a" (__ret_pu)	\
-		     : "c" (ptr))
-
-/**
- * put_user: - Write a simple value into user space.
- * @x:   Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#ifdef CONFIG_X86_WP_WORKS_OK
-
-#define put_user(x, ptr)					\
-({								\
-	int __ret_pu;						\
-	__typeof__(*(ptr)) __pu_val;				\
-	__chk_user_ptr(ptr);					\
-	__pu_val = x;						\
-	switch (sizeof(*(ptr))) {				\
-	case 1:							\
-		__put_user_1(__pu_val, ptr);			\
-		break;						\
-	case 2:							\
-		__put_user_2(__pu_val, ptr);			\
-		break;						\
-	case 4:							\
-		__put_user_4(__pu_val, ptr);			\
-		break;						\
-	case 8:							\
-		__put_user_8(__pu_val, ptr);			\
-		break;						\
-	default:						\
-		__put_user_X(__pu_val, ptr);			\
-		break;						\
-	}							\
-	__ret_pu;						\
-})
-
-#else
-#define put_user(x, ptr)					\
-({								\
-	int __ret_pu;						\
-	__typeof__(*(ptr))__pus_tmp = x;			\
-	__ret_pu = 0;						\
-	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp,		\
-				       sizeof(*(ptr))) != 0))	\
-		__ret_pu = -EFAULT;				\
-	__ret_pu;						\
-})
-
-
-#endif
-
-/**
- * __get_user: - Get a simple variable from user space, with less checking.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define __get_user(x, ptr)				\
-	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
-
-
-/**
- * __put_user: - Write a simple value into user space, with less checking.
- * @x:   Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define __put_user(x, ptr)						\
-	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-
-#define __put_user_nocheck(x, ptr, size)			\
-({								\
-	long __pu_err;						\
-	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
-	__pu_err;						\
-})
-
-
-#define __put_user_u64(x, addr, err)					\
-	asm volatile("1:	movl %%eax,0(%2)\n"			\
-		     "2:	movl %%edx,4(%2)\n"			\
-		     "3:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "4:	movl %3,%0\n"				\
-		     "	jmp 3b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 4b)				\
-		     _ASM_EXTABLE(2b, 4b)				\
-		     : "=r" (err)					\
-		     : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
-
-#ifdef CONFIG_X86_WP_WORKS_OK
-
-#define __put_user_size(x, ptr, size, retval, errret)			\
-do {									\
-	retval = 0;							\
-	__chk_user_ptr(ptr);						\
-	switch (size) {							\
-	case 1:								\
-		__put_user_asm(x, ptr, retval, "b", "b", "iq", errret);	\
-		break;							\
-	case 2:								\
-		__put_user_asm(x, ptr, retval, "w", "w", "ir", errret);	\
-		break;							\
-	case 4:								\
-		__put_user_asm(x, ptr, retval, "l", "",  "ir", errret);	\
-		break;							\
-	case 8:								\
-		__put_user_u64((__typeof__(*ptr))(x), ptr, retval);	\
-		break;							\
-	default:							\
-		__put_user_bad();					\
-	}								\
-} while (0)
-
-#else
-
-#define __put_user_size(x, ptr, size, retval, errret)			\
-do {									\
-	__typeof__(*(ptr))__pus_tmp = x;				\
-	retval = 0;							\
-									\
-	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0))	\
-		retval = errret;					\
-} while (0)
-
-#endif
-struct __large_struct { unsigned long buf[100]; };
-#define __m(x) (*(struct __large_struct __user *)(x))
-
-/*
- * Tell gcc we read from memory instead of writing: this is because
- * we do not write to any memory gcc knows about, so there are no
- * aliasing issues.
- */
-#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
-	asm volatile("1:	mov"itype" %"rtype"1,%2\n"		\
-		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:	movl %3,%0\n"				\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : "=r"(err)					\
-		     : ltype (x), "m" (__m(addr)), "i" (errret), "0" (err))
-
-
-#define __get_user_nocheck(x, ptr, size)				\
-({									\
-	long __gu_err;							\
-	unsigned long __gu_val;						\
-	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
-	(x) = (__typeof__(*(ptr)))__gu_val;				\
-	__gu_err;							\
-})
-
-extern long __get_user_bad(void);
-
-#define __get_user_size(x, ptr, size, retval, errret)			\
-do {									\
-	retval = 0;							\
-	__chk_user_ptr(ptr);						\
-	switch (size) {							\
-	case 1:								\
-		__get_user_asm(x, ptr, retval, "b", "b", "=q", errret);	\
-		break;							\
-	case 2:								\
-		__get_user_asm(x, ptr, retval, "w", "w", "=r", errret);	\
-		break;							\
-	case 4:								\
-		__get_user_asm(x, ptr, retval, "l", "", "=r", errret);	\
-		break;							\
-	default:							\
-		(x) = __get_user_bad();					\
-	}								\
-} while (0)
-
-#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
-	asm volatile("1:	mov"itype" %2,%"rtype"1\n"		\
-		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:	movl %3,%0\n"				\
-		     "	xor"itype" %"rtype"1,%"rtype"1\n"		\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : "=r" (err), ltype (x)				\
-		     : "m" (__m(addr)), "i" (errret), "0" (err))
-
-
 unsigned long __must_check __copy_to_user_ll
 		(void __user *to, const void *from, unsigned long n);
 unsigned long __must_check __copy_from_user_ll
@@ -576,8 +156,6 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 	return __copy_from_user_ll(to, from, n);
 }
 
-#define ARCH_HAS_NOCACHE_UACCESS
-
 static __always_inline unsigned long __copy_from_user_nocache(void *to,
 				const void __user *from, unsigned long n)
 {
diff --git a/include/asm-x86/uaccess_64.h b/include/asm-x86/uaccess_64.h
index b8a2f4339903..515d4dce96b5 100644
--- a/include/asm-x86/uaccess_64.h
+++ b/include/asm-x86/uaccess_64.h
@@ -9,265 +9,6 @@
 #include <linux/prefetch.h>
 #include <asm/page.h>
 
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-
-#define KERNEL_DS	MAKE_MM_SEG(0xFFFFFFFFFFFFFFFFUL)
-#define USER_DS		MAKE_MM_SEG(PAGE_OFFSET)
-
-#define get_ds()	(KERNEL_DS)
-#define get_fs()	(current_thread_info()->addr_limit)
-#define set_fs(x)	(current_thread_info()->addr_limit = (x))
-
-#define segment_eq(a, b)	((a).seg == (b).seg)
-
-#define __addr_ok(addr) (!((unsigned long)(addr) &			\
-			   (current_thread_info()->addr_limit.seg)))
-
-/*
- * Uhhuh, this needs 65-bit arithmetic. We have a carry..
- */
-#define __range_not_ok(addr, size)					\
-({									\
-	unsigned long flag, roksum;					\
-	__chk_user_ptr(addr);						\
-	asm("# range_ok\n\r"						\
-	    "addq %3,%1 ; sbbq %0,%0 ; cmpq %1,%4 ; sbbq $0,%0"		\
-	    : "=&r" (flag), "=r" (roksum)				\
-	    : "1" (addr), "g" ((long)(size)),				\
-	      "g" (current_thread_info()->addr_limit.seg));		\
-	flag;								\
-})
-
-#define access_ok(type, addr, size) (__range_not_ok(addr, size) == 0)
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
-
-#define ARCH_HAS_SEARCH_EXTABLE
-
-/*
- * These are the main single-value transfer routines.  They automatically
- * use the right size if we just have the right pointer type.
- *
- * This gets kind of ugly. We want to return _two_ values in "get_user()"
- * and yet we don't want to do any pointers, because that is too much
- * of a performance impact. Thus we have a few rather ugly macros here,
- * and hide all the ugliness from the user.
- *
- * The "__xxx" versions of the user access functions are versions that
- * do not verify the address space, that must have been done previously
- * with a separate "access_ok()" call (this is used when we do multiple
- * accesses to the same area of user memory).
- */
-
-#define __get_user_x(size, ret, x, ptr)		      \
-	asm volatile("call __get_user_" #size	      \
-		     : "=a" (ret),"=d" (x)	      \
-		     : "c" (ptr)		      \
-		     : "r8")
-
-/* Careful: we have to cast the result to the type of the pointer
- * for sign reasons */
-
-#define get_user(x, ptr)						\
-({									\
-	unsigned long __val_gu;						\
-	int __ret_gu;							\
-	__chk_user_ptr(ptr);						\
-	switch (sizeof(*(ptr))) {					\
-	case 1:								\
-		__get_user_x(1, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	case 2:								\
-		__get_user_x(2, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	case 4:								\
-		__get_user_x(4, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	case 8:								\
-		__get_user_x(8, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	default:							\
-		__get_user_bad();					\
-		break;							\
-	}								\
-	(x) = (__force typeof(*(ptr)))__val_gu;				\
-	__ret_gu;							\
-})
-
-extern void __put_user_1(void);
-extern void __put_user_2(void);
-extern void __put_user_4(void);
-extern void __put_user_8(void);
-extern void __put_user_bad(void);
-
-#define __put_user_x(size, ret, x, ptr)					\
-	asm volatile("call __put_user_" #size				\
-		     :"=a" (ret)					\
-		     :"c" (ptr),"d" (x)					\
-		     :"r8")
-
-#define put_user(x, ptr)						\
-	__put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-
-#define __get_user(x, ptr)						\
-	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
-#define __put_user(x, ptr)						\
-	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-
-#define __get_user_unaligned __get_user
-#define __put_user_unaligned __put_user
-
-#define __put_user_nocheck(x, ptr, size)		\
-({							\
-	int __pu_err;					\
-	__put_user_size((x), (ptr), (size), __pu_err);	\
-	__pu_err;					\
-})
-
-
-#define __put_user_check(x, ptr, size)				\
-({								\
-	int __pu_err;						\
-	typeof(*(ptr)) __user *__pu_addr = (ptr);		\
-	switch (size) {						\
-	case 1:							\
-		__put_user_x(1, __pu_err, x, __pu_addr);	\
-		break;						\
-	case 2:							\
-		__put_user_x(2, __pu_err, x, __pu_addr);	\
-		break;						\
-	case 4:							\
-		__put_user_x(4, __pu_err, x, __pu_addr);	\
-		break;						\
-	case 8:							\
-		__put_user_x(8, __pu_err, x, __pu_addr);	\
-		break;						\
-	default:						\
-		__put_user_bad();				\
-	}							\
-	__pu_err;						\
-})
-
-#define __put_user_size(x, ptr, size, retval)				\
-do {									\
-	retval = 0;							\
-	__chk_user_ptr(ptr);						\
-	switch (size) {							\
-	case 1:								\
-		__put_user_asm(x, ptr, retval, "b", "b", "iq", -EFAULT);\
-		break;							\
-	case 2:								\
-		__put_user_asm(x, ptr, retval, "w", "w", "ir", -EFAULT);\
-		break;							\
-	case 4:								\
-		__put_user_asm(x, ptr, retval, "l", "k", "ir", -EFAULT);\
-		break;							\
-	case 8:								\
-		__put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT);	\
-		break;							\
-	default:							\
-		__put_user_bad();					\
-	}								\
-} while (0)
-
-/* FIXME: this hack is definitely wrong -AK */
-struct __large_struct { unsigned long buf[100]; };
-#define __m(x) (*(struct __large_struct __user *)(x))
-
-/*
- * Tell gcc we read from memory instead of writing: this is because
- * we do not write to any memory gcc knows about, so there are no
- * aliasing issues.
- */
-#define __put_user_asm(x, addr, err, itype, rtype, ltype, errno)	\
-	asm volatile("1:	mov"itype" %"rtype"1,%2\n"		\
-		     "2:\n"						\
-		     ".section .fixup, \"ax\"\n"			\
-		     "3:	mov %3,%0\n"				\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : "=r"(err)					\
-		     : ltype (x), "m" (__m(addr)), "i" (errno), "0" (err))
-
-
-#define __get_user_nocheck(x, ptr, size)			\
-({								\
-	int __gu_err;						\
-	unsigned long __gu_val;					\
-	__get_user_size(__gu_val, (ptr), (size), __gu_err);	\
-	(x) = (__force typeof(*(ptr)))__gu_val;			\
-	__gu_err;						\
-})
-
-extern int __get_user_1(void);
-extern int __get_user_2(void);
-extern int __get_user_4(void);
-extern int __get_user_8(void);
-extern int __get_user_bad(void);
-
-#define __get_user_size(x, ptr, size, retval)				\
-do {									\
-	retval = 0;							\
-	__chk_user_ptr(ptr);						\
-	switch (size) {							\
-	case 1:								\
-		__get_user_asm(x, ptr, retval, "b", "b", "=q", -EFAULT);\
-		break;							\
-	case 2:								\
-		__get_user_asm(x, ptr, retval, "w", "w", "=r", -EFAULT);\
-		break;							\
-	case 4:								\
-		__get_user_asm(x, ptr, retval, "l", "k", "=r", -EFAULT);\
-		break;							\
-	case 8:								\
-		__get_user_asm(x, ptr, retval, "q", "", "=r", -EFAULT);	\
-		break;							\
-	default:							\
-		(x) = __get_user_bad();					\
-	}								\
-} while (0)
-
-#define __get_user_asm(x, addr, err, itype, rtype, ltype, errno)	\
-	asm volatile("1:	mov"itype" %2,%"rtype"1\n"		\
-		     "2:\n"						\
-		     ".section .fixup, \"ax\"\n"			\
-		     "3:	mov %3,%0\n"				\
-		     "	xor"itype" %"rtype"1,%"rtype"1\n"		\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : "=r" (err), ltype (x)				\
-		     : "m" (__m(addr)), "i"(errno), "0"(err))
-
 /*
  * Copy To/From Userspace
  */
@@ -437,7 +178,6 @@ __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
 	return copy_user_generic((__force void *)dst, src, size);
 }
 
-#define ARCH_HAS_NOCACHE_UACCESS 1
 extern long __copy_user_nocache(void *dst, const void __user *src,
 				unsigned size, int zerorest);
 
@@ -455,4 +195,7 @@ static inline int __copy_from_user_inatomic_nocache(void *dst,
 	return __copy_user_nocache(dst, src, size, 0);
 }
 
+unsigned long
+copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest);
+
 #endif /* __X86_64_UACCESS_H */
diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h
index fe26e36d0f51..9c1a4a3470d9 100644
--- a/include/asm-x86/unistd_64.h
+++ b/include/asm-x86/unistd_64.h
@@ -290,7 +290,7 @@ __SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait)
 #define __NR_rt_sigqueueinfo			129
 __SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo)
 #define __NR_rt_sigsuspend			130
-__SYSCALL(__NR_rt_sigsuspend, stub_rt_sigsuspend)
+__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend)
 #define __NR_sigaltstack			131
 __SYSCALL(__NR_sigaltstack, stub_sigaltstack)
 #define __NR_utime				132
diff --git a/include/asm-x86/uv/uv_bau.h b/include/asm-x86/uv/uv_bau.h
new file mode 100644
index 000000000000..91ac0dfb7588
--- /dev/null
+++ b/include/asm-x86/uv/uv_bau.h
@@ -0,0 +1,337 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV Broadcast Assist Unit definitions
+ *
+ * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#ifndef __ASM_X86_UV_BAU__
+#define __ASM_X86_UV_BAU__
+
+#include <linux/bitmap.h>
+#define BITSPERBYTE 8
+
+/*
+ * Broadcast Assist Unit messaging structures
+ *
+ * Selective Broadcast activations are induced by software action
+ * specifying a particular 8-descriptor "set" via a 6-bit index written
+ * to an MMR.
+ * Thus there are 64 unique 512-byte sets of SB descriptors - one set for
+ * each 6-bit index value. These descriptor sets are mapped in sequence
+ * starting with set 0 located at the address specified in the
+ * BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512,
+ * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on.
+ *
+ * We will use 31 sets, one for sending BAU messages from each of the 32
+ * cpu's on the node.
+ *
+ * TLB shootdown will use the first of the 8 descriptors of each set.
+ * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
+ */
+
+#define UV_ITEMS_PER_DESCRIPTOR		8
+#define UV_CPUS_PER_ACT_STATUS		32
+#define UV_ACT_STATUS_MASK		0x3
+#define UV_ACT_STATUS_SIZE		2
+#define UV_ACTIVATION_DESCRIPTOR_SIZE	32
+#define UV_DISTRIBUTION_SIZE		256
+#define UV_SW_ACK_NPENDING		8
+#define UV_BAU_MESSAGE			200
+/*
+ * Messaging irq; see irq_64.h and include/asm-x86/hw_irq_64.h
+ * To be dynamically allocated in the future
+ */
+#define UV_NET_ENDPOINT_INTD		0x38
+#define UV_DESC_BASE_PNODE_SHIFT	49
+#define UV_PAYLOADQ_PNODE_SHIFT		49
+#define UV_PTC_BASENAME			"sgi_uv/ptc_statistics"
+#define uv_physnodeaddr(x)		((__pa((unsigned long)(x)) & uv_mmask))
+
+/*
+ * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1
+ */
+#define DESC_STATUS_IDLE		0
+#define DESC_STATUS_ACTIVE		1
+#define DESC_STATUS_DESTINATION_TIMEOUT	2
+#define DESC_STATUS_SOURCE_TIMEOUT	3
+
+/*
+ * source side threshholds at which message retries print a warning
+ */
+#define SOURCE_TIMEOUT_LIMIT		20
+#define DESTINATION_TIMEOUT_LIMIT	20
+
+/*
+ * number of entries in the destination side payload queue
+ */
+#define DEST_Q_SIZE			17
+/*
+ * number of destination side software ack resources
+ */
+#define DEST_NUM_RESOURCES		8
+#define MAX_CPUS_PER_NODE		32
+/*
+ * completion statuses for sending a TLB flush message
+ */
+#define	FLUSH_RETRY			1
+#define	FLUSH_GIVEUP			2
+#define	FLUSH_COMPLETE			3
+
+/*
+ * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
+ * If the 'multilevel' flag in the header portion of the descriptor
+ * has been set to 0, then endpoint multi-unicast mode is selected.
+ * The distribution specification (32 bytes) is interpreted as a 256-bit
+ * distribution vector. Adjacent bits correspond to consecutive even numbered
+ * nodeIDs. The result of adding the index of a given bit to the 15-bit
+ * 'base_dest_nodeid' field of the header corresponds to the
+ * destination nodeID associated with that specified bit.
+ */
+struct bau_target_nodemask {
+	unsigned long bits[BITS_TO_LONGS(256)];
+};
+
+/*
+ * mask of cpu's on a node
+ * (during initialization we need to check that unsigned long has
+ *  enough bits for max. cpu's per node)
+ */
+struct bau_local_cpumask {
+	unsigned long bits;
+};
+
+/*
+ * Payload: 16 bytes (128 bits) (bytes 0x20-0x2f of descriptor)
+ * only 12 bytes (96 bits) of the payload area are usable.
+ * An additional 3 bytes (bits 27:4) of the header address are carried
+ * to the next bytes of the destination payload queue.
+ * And an additional 2 bytes of the header Suppl_A field are also
+ * carried to the destination payload queue.
+ * But the first byte of the Suppl_A becomes bits 127:120 (the 16th byte)
+ * of the destination payload queue, which is written by the hardware
+ * with the s/w ack resource bit vector.
+ * [ effective message contents (16 bytes (128 bits) maximum), not counting
+ *   the s/w ack bit vector  ]
+ */
+
+/*
+ * The payload is software-defined for INTD transactions
+ */
+struct bau_msg_payload {
+	unsigned long address;		/* signifies a page or all TLB's
+						of the cpu */
+	/* 64 bits */
+	unsigned short sending_cpu;	/* filled in by sender */
+	/* 16 bits */
+	unsigned short acknowledge_count;/* filled in by destination */
+	/* 16 bits */
+	unsigned int reserved1:32;	/* not usable */
+};
+
+
+/*
+ * Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * see table 4.2.3.0.1 in broacast_assist spec.
+ */
+struct bau_msg_header {
+	int dest_subnodeid:6;	/* must be zero */
+	/* bits 5:0 */
+	int base_dest_nodeid:15; /* nasid>>1 (pnode) of first bit in node_map */
+	/* bits 20:6 */
+	int command:8;		/* message type */
+	/* bits 28:21 */
+				/* 0x38: SN3net EndPoint Message */
+	int rsvd_1:3;		/* must be zero */
+	/* bits 31:29 */
+				/* int will align on 32 bits */
+	int rsvd_2:9;		/* must be zero */
+	/* bits 40:32 */
+				/* Suppl_A is 56-41 */
+	int payload_2a:8;	/* becomes byte 16 of msg */
+	/* bits 48:41 */	/* not currently using */
+	int payload_2b:8;	/* becomes byte 17 of msg */
+	/* bits 56:49 */	/* not currently using */
+				/* Address field (96:57) is never used as an
+				   address (these are address bits 42:3) */
+	int rsvd_3:1;		/* must be zero */
+	/* bit 57 */
+				/* address bits 27:4 are payload */
+				/* these 24 bits become bytes 12-14 of msg */
+	int replied_to:1;	/* sent as 0 by the source to byte 12 */
+	/* bit 58 */
+
+	int payload_1a:5;	/* not currently used */
+	/* bits 63:59 */
+	int payload_1b:8;	/* not currently used */
+	/* bits 71:64 */
+	int payload_1c:8;	/* not currently used */
+	/* bits 79:72 */
+	int payload_1d:2;	/* not currently used */
+	/* bits 81:80 */
+
+	int rsvd_4:7;		/* must be zero */
+	/* bits 88:82 */
+	int sw_ack_flag:1;	/* software acknowledge flag */
+	/* bit 89 */
+				/* INTD trasactions at destination are to
+				   wait for software acknowledge */
+	int rsvd_5:6;		/* must be zero */
+	/* bits 95:90 */
+	int rsvd_6:5;		/* must be zero */
+	/* bits 100:96 */
+	int int_both:1;		/* if 1, interrupt both sockets on the blade */
+	/* bit 101*/
+	int fairness:3;		/* usually zero */
+	/* bits 104:102 */
+	int multilevel:1;	/* multi-level multicast format */
+	/* bit 105 */
+				/* 0 for TLB: endpoint multi-unicast messages */
+	int chaining:1;		/* next descriptor is part of this activation*/
+	/* bit 106 */
+	int rsvd_7:21;		/* must be zero */
+	/* bits 127:107 */
+};
+
+/*
+ * The activation descriptor:
+ * The format of the message to send, plus all accompanying control
+ * Should be 64 bytes
+ */
+struct bau_desc {
+	struct bau_target_nodemask distribution;
+	/*
+	 * message template, consisting of header and payload:
+	 */
+	struct bau_msg_header header;
+	struct bau_msg_payload payload;
+};
+/*
+ *   -payload--    ---------header------
+ *   bytes 0-11    bits 41-56  bits 58-81
+ *       A           B  (2)      C (3)
+ *
+ *            A/B/C are moved to:
+ *       A            C          B
+ *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
+ *   ------------payload queue-----------
+ */
+
+/*
+ * The payload queue on the destination side is an array of these.
+ * With BAU_MISC_CONTROL set for software acknowledge mode, the messages
+ * are 32 bytes (2 micropackets) (256 bits) in length, but contain only 17
+ * bytes of usable data, including the sw ack vector in byte 15 (bits 127:120)
+ * (12 bytes come from bau_msg_payload, 3 from payload_1, 2 from
+ *  sw_ack_vector and payload_2)
+ * "Enabling Software Acknowledgment mode (see Section 4.3.3 Software
+ *  Acknowledge Processing) also selects 32 byte (17 bytes usable) payload
+ *  operation."
+ */
+struct bau_payload_queue_entry {
+	unsigned long address;		/* signifies a page or all TLB's
+						of the cpu */
+	/* 64 bits, bytes 0-7 */
+
+	unsigned short sending_cpu;	/* cpu that sent the message */
+	/* 16 bits, bytes 8-9 */
+
+	unsigned short acknowledge_count; /* filled in by destination */
+	/* 16 bits, bytes 10-11 */
+
+	unsigned short replied_to:1;	/* sent as 0 by the source */
+	/* 1 bit */
+	unsigned short unused1:7;       /* not currently using */
+	/* 7 bits: byte 12) */
+
+	unsigned char unused2[2];	/* not currently using */
+	/* bytes 13-14 */
+
+	unsigned char sw_ack_vector;	/* filled in by the hardware */
+	/* byte 15 (bits 127:120) */
+
+	unsigned char unused4[3];	/* not currently using bytes 17-19 */
+	/* bytes 17-19 */
+
+	int number_of_cpus;		/* filled in at destination */
+	/* 32 bits, bytes 20-23 (aligned) */
+
+	unsigned char unused5[8];       /* not using */
+	/* bytes 24-31 */
+};
+
+/*
+ * one for every slot in the destination payload queue
+ */
+struct bau_msg_status {
+	struct bau_local_cpumask seen_by;	/* map of cpu's */
+};
+
+/*
+ * one for every slot in the destination software ack resources
+ */
+struct bau_sw_ack_status {
+	struct bau_payload_queue_entry *msg;	/* associated message */
+	int watcher;				/* cpu monitoring, or -1 */
+};
+
+/*
+ * one on every node and per-cpu; to locate the software tables
+ */
+struct bau_control {
+	struct bau_desc *descriptor_base;
+	struct bau_payload_queue_entry *bau_msg_head;
+	struct bau_payload_queue_entry *va_queue_first;
+	struct bau_payload_queue_entry *va_queue_last;
+	struct bau_msg_status *msg_statuses;
+	int *watching; /* pointer to array */
+};
+
+/*
+ * This structure is allocated per_cpu for UV TLB shootdown statistics.
+ */
+struct ptc_stats {
+	unsigned long ptc_i;	/* number of IPI-style flushes */
+	unsigned long requestor;	/* number of nodes this cpu sent to */
+	unsigned long requestee;	/* times cpu was remotely requested */
+	unsigned long alltlb;	/* times all tlb's on this cpu were flushed */
+	unsigned long onetlb;	/* times just one tlb on this cpu was flushed */
+	unsigned long s_retry;	/* retries on source side timeouts */
+	unsigned long d_retry;	/* retries on destination side timeouts */
+	unsigned long sflush;	/* cycles spent in uv_flush_tlb_others */
+	unsigned long dflush;	/* cycles spent on destination side */
+	unsigned long retriesok; /* successes on retries */
+	unsigned long nomsg;	/* interrupts with no message */
+	unsigned long multmsg;	/* interrupts with multiple messages */
+	unsigned long ntargeted;/* nodes targeted */
+};
+
+static inline int bau_node_isset(int node, struct bau_target_nodemask *dstp)
+{
+	return constant_test_bit(node, &dstp->bits[0]);
+}
+static inline void bau_node_set(int node, struct bau_target_nodemask *dstp)
+{
+	__set_bit(node, &dstp->bits[0]);
+}
+static inline void bau_nodes_clear(struct bau_target_nodemask *dstp, int nbits)
+{
+	bitmap_zero(&dstp->bits[0], nbits);
+}
+
+static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
+{
+	bitmap_zero(&dstp->bits, nbits);
+}
+
+#define cpubit_isset(cpu, bau_local_cpumask) \
+	test_bit((cpu), (bau_local_cpumask).bits)
+
+extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long);
+extern void uv_bau_message_intr1(void);
+extern void uv_bau_timeout_intr1(void);
+
+#endif /* __ASM_X86_UV_BAU__ */
diff --git a/include/asm-x86/uv/uv_hub.h b/include/asm-x86/uv/uv_hub.h
index 26b9240d1e23..a4ef26e5850b 100644
--- a/include/asm-x86/uv/uv_hub.h
+++ b/include/asm-x86/uv/uv_hub.h
@@ -5,7 +5,7 @@
  *
  * SGI UV architectural definitions
  *
- * Copyright (C) 2007 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef __ASM_X86_UV_HUB_H__
@@ -20,26 +20,49 @@
 /*
  * Addressing Terminology
  *
- * 	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.
+ *	M       - The low M bits of a physical address represent the offset
+ *		  into the blade local memory. RAM memory on a blade is physically
+ *		  contiguous (although various IO spaces may punch holes in
+ *		  it)..
  *
- *	SNASID - NASID right shifted by 1 bit.
+ * 	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.
+ *
+ *	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.
+ *
+ *
+ *  NumaLink Global Physical Address Format:
+ *  +--------------------------------+---------------------+
+ *  |00..000|      GNODE             |      NodeOffset     |
+ *  +--------------------------------+---------------------+
+ *          |<-------53 - M bits --->|<--------M bits ----->
+ *
+ *	M - number of node offset bits (35 .. 40)
  *
  *
  *  Memory/UV-HUB Processor Socket Address Format:
- *  +--------+---------------+---------------------+
- *  |00..0000|    SNASID     |      NodeOffset     |
- *  +--------+---------------+---------------------+
- *           <--- N bits --->|<--------M bits ----->
+ *  +----------------+---------------+---------------------+
+ *  |00..000000000000|   PNODE       |      NodeOffset     |
+ *  +----------------+---------------+---------------------+
+ *                   <--- N bits --->|<--------M bits ----->
  *
- *	M number of node offset bits (35 .. 40)
- *	N number of SNASID bits (0 .. 10)
+ *	M - number of node offset bits (35 .. 40)
+ *	N - number of PNODE bits (0 .. 10)
  *
  *		Note: M + N cannot currently exceed 44 (x86_64) or 46 (IA64).
  *		The actual values are configuration dependent and are set at
- *		boot time
+ *		boot time. M & N values are set by the hardware/BIOS at boot.
+ *
  *
  * APICID format
  * 	NOTE!!!!!! This is the current format of the APICID. However, code
@@ -48,14 +71,14 @@
  *
  * 		1111110000000000
  * 		5432109876543210
- *		nnnnnnnnnnlc0cch
+ *		pppppppppplc0cch
  *		sssssssssss
  *
- *			n  = snasid bits
+ *			p  = pnode bits
  *			l =  socket number on board
  *			c  = core
  *			h  = hyperthread
- *			s  = bits that are in the socket CSR
+ *			s  = bits that are in the SOCKET_ID CSR
  *
  *	Note: Processor only supports 12 bits in the APICID register. The ACPI
  *	      tables hold all 16 bits. Software needs to be aware of this.
@@ -74,7 +97,7 @@
  * This value is also the value of the maximum number of non-router NASIDs
  * in the numalink fabric.
  *
- * NOTE: a brick may be 1 or 2 OS nodes. Don't get these confused.
+ * NOTE: a brick may contain 1 or 2 OS nodes. Don't get these confused.
  */
 #define UV_MAX_NUMALINK_BLADES	16384
 
@@ -96,8 +119,12 @@
  */
 struct uv_hub_info_s {
 	unsigned long	global_mmr_base;
-	unsigned short	local_nasid;
-	unsigned short	gnode_upper;
+	unsigned long	gpa_mask;
+	unsigned long	gnode_upper;
+	unsigned long	lowmem_remap_top;
+	unsigned long	lowmem_remap_base;
+	unsigned short	pnode;
+	unsigned short	pnode_mask;
 	unsigned short	coherency_domain_number;
 	unsigned short	numa_blade_id;
 	unsigned char	blade_processor_id;
@@ -112,83 +139,126 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
  * 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)
  */
-#define UV_SNASID(n)			((n) >> 1)
-#define UV_NASID(n)			((n) << 1)
+#define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
+#define UV_PNODE_TO_NASID(p)		(((p) << 1) | uv_hub_info->gnode_upper)
 
 #define UV_LOCAL_MMR_BASE		0xf4000000UL
 #define UV_GLOBAL_MMR32_BASE		0xf8000000UL
 #define UV_GLOBAL_MMR64_BASE		(uv_hub_info->global_mmr_base)
+#define UV_LOCAL_MMR_SIZE		(64UL * 1024 * 1024)
+#define UV_GLOBAL_MMR32_SIZE		(64UL * 1024 * 1024)
 
-#define UV_GLOBAL_MMR32_SNASID_MASK	0x3ff
-#define UV_GLOBAL_MMR32_SNASID_SHIFT	15
-#define UV_GLOBAL_MMR64_SNASID_SHIFT	26
+#define UV_GLOBAL_MMR32_PNODE_SHIFT	15
+#define UV_GLOBAL_MMR64_PNODE_SHIFT	26
 
-#define UV_GLOBAL_MMR32_NASID_BITS(n)					\
-		(((UV_SNASID(n) & UV_GLOBAL_MMR32_SNASID_MASK)) <<	\
-		(UV_GLOBAL_MMR32_SNASID_SHIFT))
+#define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
-#define UV_GLOBAL_MMR64_NASID_BITS(n)					\
-	((unsigned long)UV_SNASID(n) << UV_GLOBAL_MMR64_SNASID_SHIFT)
+#define UV_GLOBAL_MMR64_PNODE_BITS(p)					\
+	((unsigned long)(p) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+
+#define UV_APIC_PNODE_SHIFT	6
+
+/*
+ * 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.
+ */
+
+/* socket phys RAM --> UV global physical address */
+static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
+{
+	if (paddr < uv_hub_info->lowmem_remap_top)
+		paddr += uv_hub_info->lowmem_remap_base;
+	return paddr | uv_hub_info->gnode_upper;
+}
+
+
+/* socket virtual --> UV global physical address */
+static inline unsigned long uv_gpa(void *v)
+{
+	return __pa(v) | uv_hub_info->gnode_upper;
+}
+
+/* socket virtual --> UV global physical address */
+static inline void *uv_vgpa(void *v)
+{
+	return (void *)uv_gpa(v);
+}
+
+/* UV global physical address --> socket virtual */
+static inline void *uv_va(unsigned long gpa)
+{
+	return __va(gpa & uv_hub_info->gpa_mask);
+}
+
+/* pnode, offset --> socket virtual */
+static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
+{
+	return __va(((unsigned long)pnode << uv_hub_info->m_val) | offset);
+}
 
-#define UV_APIC_NASID_SHIFT	6
 
 /*
- * Extract a NASID from an APICID (full apicid, not processor subset)
+ * Extract a PNODE from an APICID (full apicid, not processor subset)
  */
-static inline int uv_apicid_to_nasid(int apicid)
+static inline int uv_apicid_to_pnode(int apicid)
 {
-	return (UV_NASID(apicid >> UV_APIC_NASID_SHIFT));
+	return (apicid >> UV_APIC_PNODE_SHIFT);
 }
 
 /*
  * 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 nasid,
+static inline unsigned long *uv_global_mmr32_address(int pnode,
 				unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR32_BASE |
-		       UV_GLOBAL_MMR32_NASID_BITS(nasid) | offset);
+		       UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr32(int nasid, unsigned long offset,
+static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
 				 unsigned long val)
 {
-	*uv_global_mmr32_address(nasid, offset) = val;
+	*uv_global_mmr32_address(pnode, offset) = val;
 }
 
-static inline unsigned long uv_read_global_mmr32(int nasid,
+static inline unsigned long uv_read_global_mmr32(int pnode,
 						 unsigned long offset)
 {
-	return *uv_global_mmr32_address(nasid, offset);
+	return *uv_global_mmr32_address(pnode, offset);
 }
 
 /*
  * Access Global MMR space using the MMR space located at the top of physical
  * memory.
  */
-static inline unsigned long *uv_global_mmr64_address(int nasid,
+static inline unsigned long *uv_global_mmr64_address(int pnode,
 				unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR64_BASE |
-		       UV_GLOBAL_MMR64_NASID_BITS(nasid) | offset);
+		    UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr64(int nasid, unsigned long offset,
+static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
 				unsigned long val)
 {
-	*uv_global_mmr64_address(nasid, offset) = val;
+	*uv_global_mmr64_address(pnode, offset) = val;
 }
 
-static inline unsigned long uv_read_global_mmr64(int nasid,
+static inline unsigned long uv_read_global_mmr64(int pnode,
 						 unsigned long offset)
 {
-	return *uv_global_mmr64_address(nasid, offset);
+	return *uv_global_mmr64_address(pnode, offset);
 }
 
 /*
- * Access node local MMRs. Faster than using global space but only local MMRs
+ * Access hub local MMRs. Faster than using global space but only local MMRs
  * are accessible.
  */
 static inline unsigned long *uv_local_mmr_address(unsigned long offset)
@@ -207,15 +277,15 @@ static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
 }
 
 /*
- * Structures and definitions for converting between cpu, node, and blade
+ * Structures and definitions for converting between cpu, node, pnode, and blade
  * numbers.
  */
 struct uv_blade_info {
-	unsigned short	nr_posible_cpus;
+	unsigned short	nr_possible_cpus;
 	unsigned short	nr_online_cpus;
-	unsigned short	nasid;
+	unsigned short	pnode;
 };
-struct uv_blade_info *uv_blade_info;
+extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
 extern short *uv_cpu_to_blade;
 extern short uv_possible_blades;
@@ -244,16 +314,16 @@ static inline int uv_node_to_blade_id(int nid)
 	return uv_node_to_blade[nid];
 }
 
-/* Convert a blade id to the NASID of the blade */
-static inline int uv_blade_to_nasid(int bid)
+/* Convert a blade id to the PNODE of the blade */
+static inline int uv_blade_to_pnode(int bid)
 {
-	return uv_blade_info[bid].nasid;
+	return uv_blade_info[bid].pnode;
 }
 
 /* Determine the number of possible cpus on a blade */
 static inline int uv_blade_nr_possible_cpus(int bid)
 {
-	return uv_blade_info[bid].nr_posible_cpus;
+	return uv_blade_info[bid].nr_possible_cpus;
 }
 
 /* Determine the number of online cpus on a blade */
@@ -262,16 +332,16 @@ static inline int uv_blade_nr_online_cpus(int bid)
 	return uv_blade_info[bid].nr_online_cpus;
 }
 
-/* Convert a cpu id to the NASID of the blade containing the cpu */
-static inline int uv_cpu_to_nasid(int cpu)
+/* Convert a cpu id to the PNODE of the blade containing the cpu */
+static inline int uv_cpu_to_pnode(int cpu)
 {
-	return uv_blade_info[uv_cpu_to_blade_id(cpu)].nasid;
+	return uv_blade_info[uv_cpu_to_blade_id(cpu)].pnode;
 }
 
-/* Convert a node number to the NASID of the blade */
-static inline int uv_node_to_nasid(int nid)
+/* Convert a linux node number to the PNODE of the blade */
+static inline int uv_node_to_pnode(int nid)
 {
-	return uv_blade_info[uv_node_to_blade_id(nid)].nasid;
+	return uv_blade_info[uv_node_to_blade_id(nid)].pnode;
 }
 
 /* Maximum possible number of blades */
diff --git a/include/asm-x86/uv/uv_mmrs.h b/include/asm-x86/uv/uv_mmrs.h
index 3b69fe6b6376..151fd7fcb809 100644
--- a/include/asm-x86/uv/uv_mmrs.h
+++ b/include/asm-x86/uv/uv_mmrs.h
@@ -11,17 +11,290 @@
 #ifndef __ASM_X86_UV_MMRS__
 #define __ASM_X86_UV_MMRS__
 
-/*
- *       AUTO GENERATED - Do not edit
- */
+#define UV_MMR_ENABLE		(1UL << 63)
+
+/* ========================================================================= */
+/*                           UVH_BAU_DATA_CONFIG                             */
+/* ========================================================================= */
+#define UVH_BAU_DATA_CONFIG 0x61680UL
+#define UVH_BAU_DATA_CONFIG_32 0x0438
+
+#define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0
+#define UVH_BAU_DATA_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_BAU_DATA_CONFIG_DM_SHFT 8
+#define UVH_BAU_DATA_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_BAU_DATA_CONFIG_DESTMODE_SHFT 11
+#define UVH_BAU_DATA_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_BAU_DATA_CONFIG_STATUS_SHFT 12
+#define UVH_BAU_DATA_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_BAU_DATA_CONFIG_P_SHFT 13
+#define UVH_BAU_DATA_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_BAU_DATA_CONFIG_T_SHFT 15
+#define UVH_BAU_DATA_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_BAU_DATA_CONFIG_M_SHFT 16
+#define UVH_BAU_DATA_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_BAU_DATA_CONFIG_APIC_ID_SHFT 32
+#define UVH_BAU_DATA_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_bau_data_config_u {
+    unsigned long	v;
+    struct uvh_bau_data_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_EVENT_OCCURRED0                             */
+/* ========================================================================= */
+#define UVH_EVENT_OCCURRED0 0x70000UL
+#define UVH_EVENT_OCCURRED0_32 0x005e8
+
+#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UVH_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
+#define UVH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
+#define UVH_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
+#define UVH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
+#define UVH_EVENT_OCCURRED0_LH_HCERR_SHFT 3
+#define UVH_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
+#define UVH_EVENT_OCCURRED0_RH_HCERR_SHFT 4
+#define UVH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
+#define UVH_EVENT_OCCURRED0_XN_HCERR_SHFT 5
+#define UVH_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
+#define UVH_EVENT_OCCURRED0_SI_HCERR_SHFT 6
+#define UVH_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
+#define UVH_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
+#define UVH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
+#define UVH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
+#define UVH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UVH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
+#define UVH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UVH_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
+#define UVH_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
+#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UVH_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
+#define UVH_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
+#define UVH_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
+#define UVH_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
+#define UVH_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
+#define UVH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
+#define UVH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
+#define UVH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UVH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
+#define UVH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UVH_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
+#define UVH_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
+#define UVH_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
+#define UVH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
+#define UVH_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
+#define UVH_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
+#define UVH_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
+#define UVH_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
+#define UVH_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
+#define UVH_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UVH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
+#define UVH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UVH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
+#define UVH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
+#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
+#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UVH_EVENT_OCCURRED0_LTC_INT_SHFT 43
+#define UVH_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
+#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
+#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+#define UVH_EVENT_OCCURRED0_IPI_INT_SHFT 45
+#define UVH_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
+#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
+#define UVH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
+#define UVH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
+#define UVH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
+#define UVH_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
+#define UVH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC0_SHFT 51
+#define UVH_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC1_SHFT 52
+#define UVH_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC2_SHFT 53
+#define UVH_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC3_SHFT 54
+#define UVH_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
+#define UVH_EVENT_OCCURRED0_BAU_DATA_SHFT 55
+#define UVH_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
+#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
+#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+union uvh_event_occurred0_u {
+    unsigned long	v;
+    struct uvh_event_occurred0_s {
+	unsigned long	lb_hcerr             :  1;  /* RW, W1C */
+	unsigned long	gr0_hcerr            :  1;  /* RW, W1C */
+	unsigned long	gr1_hcerr            :  1;  /* RW, W1C */
+	unsigned long	lh_hcerr             :  1;  /* RW, W1C */
+	unsigned long	rh_hcerr             :  1;  /* RW, W1C */
+	unsigned long	xn_hcerr             :  1;  /* RW, W1C */
+	unsigned long	si_hcerr             :  1;  /* RW, W1C */
+	unsigned long	lb_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	gr0_aoerr0           :  1;  /* RW, W1C */
+	unsigned long	gr1_aoerr0           :  1;  /* RW, W1C */
+	unsigned long	lh_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	rh_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	xn_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	si_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	lb_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	gr0_aoerr1           :  1;  /* RW, W1C */
+	unsigned long	gr1_aoerr1           :  1;  /* RW, W1C */
+	unsigned long	lh_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	rh_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	xn_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	si_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	rh_vpi_int           :  1;  /* RW, W1C */
+	unsigned long	system_shutdown_int  :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_0         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_1         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_2         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_3         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_4         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_5         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_6         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_7         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_8         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_9         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_10        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_11        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_12        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_13        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_14        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_15        :  1;  /* RW, W1C */
+	unsigned long	l1_nmi_int           :  1;  /* RW, W1C */
+	unsigned long	stop_clock           :  1;  /* RW, W1C */
+	unsigned long	asic_to_l1           :  1;  /* RW, W1C */
+	unsigned long	l1_to_asic           :  1;  /* RW, W1C */
+	unsigned long	ltc_int              :  1;  /* RW, W1C */
+	unsigned long	la_seq_trigger       :  1;  /* RW, W1C */
+	unsigned long	ipi_int              :  1;  /* RW, W1C */
+	unsigned long	extio_int0           :  1;  /* RW, W1C */
+	unsigned long	extio_int1           :  1;  /* RW, W1C */
+	unsigned long	extio_int2           :  1;  /* RW, W1C */
+	unsigned long	extio_int3           :  1;  /* RW, W1C */
+	unsigned long	profile_int          :  1;  /* RW, W1C */
+	unsigned long	rtc0                 :  1;  /* RW, W1C */
+	unsigned long	rtc1                 :  1;  /* RW, W1C */
+	unsigned long	rtc2                 :  1;  /* RW, W1C */
+	unsigned long	rtc3                 :  1;  /* RW, W1C */
+	unsigned long	bau_data             :  1;  /* RW, W1C */
+	unsigned long	power_management_req :  1;  /* RW, W1C */
+	unsigned long	rsvd_57_63           :  7;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                        UVH_EVENT_OCCURRED0_ALIAS                          */
+/* ========================================================================= */
+#define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL
+#define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPB                                */
+/* ========================================================================= */
+#define UVH_INT_CMPB 0x22080UL
+
+#define UVH_INT_CMPB_REAL_TIME_CMPB_SHFT 0
+#define UVH_INT_CMPB_REAL_TIME_CMPB_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpb_u {
+    unsigned long	v;
+    struct uvh_int_cmpb_s {
+	unsigned long	real_time_cmpb : 56;  /* RW */
+	unsigned long	rsvd_56_63     :  8;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPC                                */
+/* ========================================================================= */
+#define UVH_INT_CMPC 0x22100UL
+
+#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0
+#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpc_u {
+    unsigned long	v;
+    struct uvh_int_cmpc_s {
+	unsigned long	real_time_cmpc : 56;  /* RW */
+	unsigned long	rsvd_56_63     :  8;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPD                                */
+/* ========================================================================= */
+#define UVH_INT_CMPD 0x22180UL
 
- #define UV_MMR_ENABLE		(1UL << 63)
+#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0
+#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpd_u {
+    unsigned long	v;
+    struct uvh_int_cmpd_s {
+	unsigned long	real_time_cmpd : 56;  /* RW */
+	unsigned long	rsvd_56_63     :  8;  /*    */
+    } s;
+};
 
 /* ========================================================================= */
 /*                               UVH_IPI_INT                                 */
 /* ========================================================================= */
 #define UVH_IPI_INT 0x60500UL
-#define UVH_IPI_INT_32 0x0360
+#define UVH_IPI_INT_32 0x0348
 
 #define UVH_IPI_INT_VECTOR_SHFT 0
 #define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL
@@ -51,7 +324,7 @@ union uvh_ipi_int_u {
 /*                   UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009f0
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009c0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -73,7 +346,7 @@ union uvh_lb_bau_intd_payload_queue_first_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009f8
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009c8
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -91,7 +364,7 @@ union uvh_lb_bau_intd_payload_queue_last_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x00a00
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x009d0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
@@ -109,6 +382,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u {
 /*                   UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE                    */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0x0a68
 
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
@@ -169,12 +443,13 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 /*                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS                 */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70
 
 /* ========================================================================= */
 /*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009d8
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009a8
 
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_MASK 0x000000000000003fUL
@@ -197,7 +472,7 @@ union uvh_lb_bau_sb_activation_control_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_0                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009e0
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009b0
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL
@@ -213,7 +488,7 @@ union uvh_lb_bau_sb_activation_status_0_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_1                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009e8
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009b8
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL
@@ -229,7 +504,7 @@ union uvh_lb_bau_sb_activation_status_1_u {
 /*                      UVH_LB_BAU_SB_DESCRIPTOR_BASE                        */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009d0
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009a0
 
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
@@ -248,6 +523,334 @@ union uvh_lb_bau_sb_descriptor_base_u {
 };
 
 /* ========================================================================= */
+/*                      UVH_LB_MCAST_AOERR0_RPT_ENABLE                       */
+/* ========================================================================= */
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE 0x50b20UL
+
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_SHFT 0
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_MASK 0x0000000000000001UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_SHFT 1
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_MASK 0x0000000000000002UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_SHFT 2
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_MASK 0x0000000000000004UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_SHFT 3
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_MASK 0x0000000000000008UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_SHFT 4
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_MASK 0x0000000000000010UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_SHFT 5
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_MASK 0x0000000000000020UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_SHFT 6
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_MASK 0x0000000000000040UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_SHFT 7
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_MASK 0x0000000000000080UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_SHFT 8
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_MASK 0x0000000000000100UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_SHFT 9
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_MASK 0x0000000000000200UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_SHFT 10
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_MASK 0x0000000000000400UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_SHFT 11
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_MASK 0x0000000000000800UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_SHFT 12
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_MASK 0x0000000000001000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_SHFT 13
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_MASK 0x0000000000002000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_SHFT 14
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_MASK 0x0000000000004000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_SHFT 15
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_MASK 0x0000000000008000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_SHFT 16
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_MASK 0x0000000000010000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_SHFT 17
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_MASK 0x0000000000020000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_SHFT 18
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_MASK 0x0000000000040000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_SHFT 19
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_MASK 0x0000000000080000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_SHFT 20
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_MASK 0x0000000000100000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_SHFT 21
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_MASK 0x0000000000200000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_SHFT 22
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_MASK 0x0000000000400000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_SHFT 23
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_MASK 0x0000000000800000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_SHFT 24
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_MASK 0x0000000001000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_SHFT 25
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_MASK 0x0000000002000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_SHFT 26
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_MASK 0x0000000004000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_SHFT 27
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_MASK 0x0000000008000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_SHFT 28
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_MASK 0x0000000010000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_SHFT 29
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_MASK 0x0000000020000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_SHFT 30
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_MASK 0x0000000040000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_SHFT 31
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_MASK 0x0000000080000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_SHFT 32
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_MASK 0x0000000100000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_SHFT 33
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_MASK 0x0000000200000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_SHFT 34
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_MASK 0x0000000400000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_SHFT 35
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_MASK 0x0000000800000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_SHFT 36
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_MASK 0x0000001000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_SHFT 37
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_MASK 0x0000002000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_SHFT 38
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_MASK 0x0000004000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_SHFT 39
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_MASK 0x0000008000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_SHFT 40
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_MASK 0x0000010000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_SHFT 41
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_MASK 0x0000020000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_SHFT 42
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_MASK 0x0000040000000000UL
+
+union uvh_lb_mcast_aoerr0_rpt_enable_u {
+    unsigned long	v;
+    struct uvh_lb_mcast_aoerr0_rpt_enable_s {
+	unsigned long	mcast_obese_msg                         :  1;  /* RW */
+	unsigned long	mcast_data_sb_err                       :  1;  /* RW */
+	unsigned long	mcast_nack_buff_parity                  :  1;  /* RW */
+	unsigned long	mcast_timeout                           :  1;  /* RW */
+	unsigned long	mcast_inactive_reply                    :  1;  /* RW */
+	unsigned long	mcast_upgrade_error                     :  1;  /* RW */
+	unsigned long	mcast_reg_count_underflow               :  1;  /* RW */
+	unsigned long	mcast_rep_obese_msg                     :  1;  /* RW */
+	unsigned long	ucache_req_runt_msg                     :  1;  /* RW */
+	unsigned long	ucache_req_obese_msg                    :  1;  /* RW */
+	unsigned long	ucache_req_data_sb_err                  :  1;  /* RW */
+	unsigned long	ucache_rep_runt_msg                     :  1;  /* RW */
+	unsigned long	ucache_rep_obese_msg                    :  1;  /* RW */
+	unsigned long	ucache_rep_data_sb_err                  :  1;  /* RW */
+	unsigned long	ucache_rep_command_err                  :  1;  /* RW */
+	unsigned long	ucache_pend_timeout                     :  1;  /* RW */
+	unsigned long	macc_req_runt_msg                       :  1;  /* RW */
+	unsigned long	macc_req_obese_msg                      :  1;  /* RW */
+	unsigned long	macc_req_data_sb_err                    :  1;  /* RW */
+	unsigned long	macc_rep_runt_msg                       :  1;  /* RW */
+	unsigned long	macc_rep_obese_msg                      :  1;  /* RW */
+	unsigned long	macc_rep_data_sb_err                    :  1;  /* RW */
+	unsigned long	macc_amo_timeout                        :  1;  /* RW */
+	unsigned long	macc_put_timeout                        :  1;  /* RW */
+	unsigned long	macc_spurious_event                     :  1;  /* RW */
+	unsigned long	ioh_destination_table_parity            :  1;  /* RW */
+	unsigned long	get_had_error_reply                     :  1;  /* RW */
+	unsigned long	get_timeout                             :  1;  /* RW */
+	unsigned long	lock_manager_had_error_reply            :  1;  /* RW */
+	unsigned long	put_had_error_reply                     :  1;  /* RW */
+	unsigned long	put_timeout                             :  1;  /* RW */
+	unsigned long	sb_activation_overrun                   :  1;  /* RW */
+	unsigned long	completed_gb_activation_had_error_reply :  1;  /* RW */
+	unsigned long	completed_gb_activation_timeout         :  1;  /* RW */
+	unsigned long	descriptor_buffer_0_parity              :  1;  /* RW */
+	unsigned long	descriptor_buffer_1_parity              :  1;  /* RW */
+	unsigned long	socket_destination_table_parity         :  1;  /* RW */
+	unsigned long	bau_reply_payload_corruption            :  1;  /* RW */
+	unsigned long	io_port_destination_table_parity        :  1;  /* RW */
+	unsigned long	intd_soft_ack_timeout                   :  1;  /* RW */
+	unsigned long	int_rep_obese_msg                       :  1;  /* RW */
+	unsigned long	int_rep_command_err                     :  1;  /* RW */
+	unsigned long	int_timeout                             :  1;  /* RW */
+	unsigned long	rsvd_43_63                              : 21;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                          UVH_LOCAL_INT0_CONFIG                            */
+/* ========================================================================= */
+#define UVH_LOCAL_INT0_CONFIG 0x61000UL
+
+#define UVH_LOCAL_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_LOCAL_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_LOCAL_INT0_CONFIG_DM_SHFT 8
+#define UVH_LOCAL_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_LOCAL_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_LOCAL_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_LOCAL_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_LOCAL_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_LOCAL_INT0_CONFIG_P_SHFT 13
+#define UVH_LOCAL_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_LOCAL_INT0_CONFIG_T_SHFT 15
+#define UVH_LOCAL_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_LOCAL_INT0_CONFIG_M_SHFT 16
+#define UVH_LOCAL_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_LOCAL_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_LOCAL_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_local_int0_config_u {
+    unsigned long	v;
+    struct uvh_local_int0_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                          UVH_LOCAL_INT0_ENABLE                            */
+/* ========================================================================= */
+#define UVH_LOCAL_INT0_ENABLE 0x65000UL
+
+#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_SHFT 0
+#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_MASK 0x0000000000000001UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_SHFT 1
+#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_MASK 0x0000000000000002UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_SHFT 2
+#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_MASK 0x0000000000000004UL
+#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_SHFT 3
+#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_MASK 0x0000000000000008UL
+#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_SHFT 4
+#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_MASK 0x0000000000000010UL
+#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_SHFT 5
+#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_MASK 0x0000000000000020UL
+#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_SHFT 6
+#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_MASK 0x0000000000000040UL
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_SHFT 7
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_MASK 0x0000000000000080UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_SHFT 8
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_SHFT 9
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_SHFT 10
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_MASK 0x0000000000000400UL
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_SHFT 11
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_MASK 0x0000000000000800UL
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_SHFT 12
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_MASK 0x0000000000001000UL
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_SHFT 13
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_MASK 0x0000000000002000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_SHFT 14
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_MASK 0x0000000000004000UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_SHFT 15
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_SHFT 16
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_SHFT 17
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_MASK 0x0000000000020000UL
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_SHFT 18
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_MASK 0x0000000000040000UL
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_SHFT 19
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_MASK 0x0000000000080000UL
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_SHFT 20
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_MASK 0x0000000000100000UL
+#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_SHFT 21
+#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_SHFT 23
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_SHFT 24
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_SHFT 25
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_SHFT 26
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_SHFT 27
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_SHFT 28
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_SHFT 29
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_SHFT 30
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_SHFT 31
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_SHFT 32
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_SHFT 33
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_SHFT 34
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_SHFT 35
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_SHFT 36
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_SHFT 37
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_SHFT 38
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_SHFT 39
+#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_SHFT 40
+#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_SHFT 41
+#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_SHFT 42
+#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LTC_INT_SHFT 43
+#define UVH_LOCAL_INT0_ENABLE_LTC_INT_MASK 0x0000080000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_SHFT 44
+#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+
+union uvh_local_int0_enable_u {
+    unsigned long	v;
+    struct uvh_local_int0_enable_s {
+	unsigned long	lb_hcerr            :  1;  /* RW */
+	unsigned long	gr0_hcerr           :  1;  /* RW */
+	unsigned long	gr1_hcerr           :  1;  /* RW */
+	unsigned long	lh_hcerr            :  1;  /* RW */
+	unsigned long	rh_hcerr            :  1;  /* RW */
+	unsigned long	xn_hcerr            :  1;  /* RW */
+	unsigned long	si_hcerr            :  1;  /* RW */
+	unsigned long	lb_aoerr0           :  1;  /* RW */
+	unsigned long	gr0_aoerr0          :  1;  /* RW */
+	unsigned long	gr1_aoerr0          :  1;  /* RW */
+	unsigned long	lh_aoerr0           :  1;  /* RW */
+	unsigned long	rh_aoerr0           :  1;  /* RW */
+	unsigned long	xn_aoerr0           :  1;  /* RW */
+	unsigned long	si_aoerr0           :  1;  /* RW */
+	unsigned long	lb_aoerr1           :  1;  /* RW */
+	unsigned long	gr0_aoerr1          :  1;  /* RW */
+	unsigned long	gr1_aoerr1          :  1;  /* RW */
+	unsigned long	lh_aoerr1           :  1;  /* RW */
+	unsigned long	rh_aoerr1           :  1;  /* RW */
+	unsigned long	xn_aoerr1           :  1;  /* RW */
+	unsigned long	si_aoerr1           :  1;  /* RW */
+	unsigned long	rh_vpi_int          :  1;  /* RW */
+	unsigned long	system_shutdown_int :  1;  /* RW */
+	unsigned long	lb_irq_int_0        :  1;  /* RW */
+	unsigned long	lb_irq_int_1        :  1;  /* RW */
+	unsigned long	lb_irq_int_2        :  1;  /* RW */
+	unsigned long	lb_irq_int_3        :  1;  /* RW */
+	unsigned long	lb_irq_int_4        :  1;  /* RW */
+	unsigned long	lb_irq_int_5        :  1;  /* RW */
+	unsigned long	lb_irq_int_6        :  1;  /* RW */
+	unsigned long	lb_irq_int_7        :  1;  /* RW */
+	unsigned long	lb_irq_int_8        :  1;  /* RW */
+	unsigned long	lb_irq_int_9        :  1;  /* RW */
+	unsigned long	lb_irq_int_10       :  1;  /* RW */
+	unsigned long	lb_irq_int_11       :  1;  /* RW */
+	unsigned long	lb_irq_int_12       :  1;  /* RW */
+	unsigned long	lb_irq_int_13       :  1;  /* RW */
+	unsigned long	lb_irq_int_14       :  1;  /* RW */
+	unsigned long	lb_irq_int_15       :  1;  /* RW */
+	unsigned long	l1_nmi_int          :  1;  /* RW */
+	unsigned long	stop_clock          :  1;  /* RW */
+	unsigned long	asic_to_l1          :  1;  /* RW */
+	unsigned long	l1_to_asic          :  1;  /* RW */
+	unsigned long	ltc_int             :  1;  /* RW */
+	unsigned long	la_seq_trigger      :  1;  /* RW */
+	unsigned long	rsvd_45_63          : 19;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
 /*                               UVH_NODE_ID                                 */
 /* ========================================================================= */
 #define UVH_NODE_ID 0x0UL
@@ -284,14 +887,101 @@ union uvh_node_id_u {
 };
 
 /* ========================================================================= */
+/*                          UVH_NODE_PRESENT_TABLE                           */
+/* ========================================================================= */
+#define UVH_NODE_PRESENT_TABLE 0x1400UL
+#define UVH_NODE_PRESENT_TABLE_DEPTH 16
+
+#define UVH_NODE_PRESENT_TABLE_NODES_SHFT 0
+#define UVH_NODE_PRESENT_TABLE_NODES_MASK 0xffffffffffffffffUL
+
+union uvh_node_present_table_u {
+    unsigned long	v;
+    struct uvh_node_present_table_s {
+	unsigned long	nodes : 64;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_redirect_config_0_mmr_s {
+	unsigned long	rsvd_0_23 : 24;  /*    */
+	unsigned long	dest_base : 22;  /* RW */
+	unsigned long	rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_redirect_config_1_mmr_s {
+	unsigned long	rsvd_0_23 : 24;  /*    */
+	unsigned long	dest_base : 22;  /* RW */
+	unsigned long	rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_redirect_config_2_mmr_s {
+	unsigned long	rsvd_0_23 : 24;  /*    */
+	unsigned long	dest_base : 22;  /* RW */
+	unsigned long	rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR                      */
+/* ========================================================================= */
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR 0x1600020UL
+
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_cfg_overlay_config_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_cfg_overlay_config_mmr_s {
+	unsigned long	rsvd_0_25: 26;  /*    */
+	unsigned long	base   : 20;  /* RW */
+	unsigned long	rsvd_46_62: 17;  /*    */
+	unsigned long	enable :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                    UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
 
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 46
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0000400000000000UL
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
@@ -302,8 +992,9 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
     struct uvh_rh_gam_gru_overlay_config_mmr_s {
 	unsigned long	rsvd_0_27: 28;  /*    */
 	unsigned long	base   : 18;  /* RW */
+	unsigned long	rsvd_46_47:  2;  /*    */
 	unsigned long	gr4    :  1;  /* RW */
-	unsigned long	rsvd_47_51:  5;  /*    */
+	unsigned long	rsvd_49_51:  3;  /*    */
 	unsigned long	n_gru  :  4;  /* RW */
 	unsigned long	rsvd_56_62:  7;  /*    */
 	unsigned long	enable :  1;  /* RW */
@@ -311,6 +1002,32 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 };
 
 /* ========================================================================= */
+/*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR                     */
+/* ========================================================================= */
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_mmioh_overlay_config_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_mmioh_overlay_config_mmr_s {
+	unsigned long	rsvd_0_29: 30;  /*    */
+	unsigned long	base   : 16;  /* RW */
+	unsigned long	m_io   :  6;  /* RW */
+	unsigned long	n_io   :  4;  /* RW */
+	unsigned long	rsvd_56_62:  7;  /*    */
+	unsigned long	enable :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                    UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
@@ -336,7 +1053,7 @@ union uvh_rh_gam_mmr_overlay_config_mmr_u {
 /* ========================================================================= */
 /*                                 UVH_RTC                                   */
 /* ========================================================================= */
-#define UVH_RTC 0x28000UL
+#define UVH_RTC 0x340000UL
 
 #define UVH_RTC_REAL_TIME_CLOCK_SHFT 0
 #define UVH_RTC_REAL_TIME_CLOCK_MASK 0x00ffffffffffffffUL
@@ -350,6 +1067,139 @@ union uvh_rtc_u {
 };
 
 /* ========================================================================= */
+/*                           UVH_RTC1_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC1_INT_CONFIG 0x615c0UL
+
+#define UVH_RTC1_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC1_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC1_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC1_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC1_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC1_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC1_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC1_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC1_INT_CONFIG_P_SHFT 13
+#define UVH_RTC1_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC1_INT_CONFIG_T_SHFT 15
+#define UVH_RTC1_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC1_INT_CONFIG_M_SHFT 16
+#define UVH_RTC1_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC1_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC1_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc1_int_config_u {
+    unsigned long	v;
+    struct uvh_rtc1_int_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_RTC2_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC2_INT_CONFIG 0x61600UL
+
+#define UVH_RTC2_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC2_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC2_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC2_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC2_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC2_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC2_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC2_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC2_INT_CONFIG_P_SHFT 13
+#define UVH_RTC2_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC2_INT_CONFIG_T_SHFT 15
+#define UVH_RTC2_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC2_INT_CONFIG_M_SHFT 16
+#define UVH_RTC2_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC2_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC2_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc2_int_config_u {
+    unsigned long	v;
+    struct uvh_rtc2_int_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_RTC3_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC3_INT_CONFIG 0x61640UL
+
+#define UVH_RTC3_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC3_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC3_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC3_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC3_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC3_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC3_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC3_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC3_INT_CONFIG_P_SHFT 13
+#define UVH_RTC3_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC3_INT_CONFIG_T_SHFT 15
+#define UVH_RTC3_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC3_INT_CONFIG_M_SHFT 16
+#define UVH_RTC3_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC3_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC3_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc3_int_config_u {
+    unsigned long	v;
+    struct uvh_rtc3_int_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                            UVH_RTC_INC_RATIO                              */
+/* ========================================================================= */
+#define UVH_RTC_INC_RATIO 0x350000UL
+
+#define UVH_RTC_INC_RATIO_FRACTION_SHFT 0
+#define UVH_RTC_INC_RATIO_FRACTION_MASK 0x00000000000fffffUL
+#define UVH_RTC_INC_RATIO_RATIO_SHFT 20
+#define UVH_RTC_INC_RATIO_RATIO_MASK 0x0000000000700000UL
+
+union uvh_rtc_inc_ratio_u {
+    unsigned long	v;
+    struct uvh_rtc_inc_ratio_s {
+	unsigned long	fraction : 20;  /* RW */
+	unsigned long	ratio    :  3;  /* RW */
+	unsigned long	rsvd_23_63: 41;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
 /*                          UVH_SI_ADDR_MAP_CONFIG                           */
 /* ========================================================================= */
 #define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL
@@ -369,5 +1219,77 @@ union uvh_si_addr_map_config_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS0_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG 0xc80008UL
+
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias0_overlay_config_u {
+    unsigned long	v;
+    struct uvh_si_alias0_overlay_config_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS1_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG 0xc80010UL
+
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias1_overlay_config_u {
+    unsigned long	v;
+    struct uvh_si_alias1_overlay_config_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS2_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG 0xc80018UL
+
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias2_overlay_config_u {
+    unsigned long	v;
+    struct uvh_si_alias2_overlay_config_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
 
 #endif /* __ASM_X86_UV_MMRS__ */
diff --git a/include/asm-x86/mach-visws/cobalt.h b/include/asm-x86/visws/cobalt.h
index 995258831b7f..995258831b7f 100644
--- a/include/asm-x86/mach-visws/cobalt.h
+++ b/include/asm-x86/visws/cobalt.h
diff --git a/include/asm-x86/mach-visws/lithium.h b/include/asm-x86/visws/lithium.h
index dfcd4f07ab85..dfcd4f07ab85 100644
--- a/include/asm-x86/mach-visws/lithium.h
+++ b/include/asm-x86/visws/lithium.h
diff --git a/include/asm-x86/mach-visws/piix4.h b/include/asm-x86/visws/piix4.h
index 83ea4f46e419..83ea4f46e419 100644
--- a/include/asm-x86/mach-visws/piix4.h
+++ b/include/asm-x86/visws/piix4.h
diff --git a/include/asm-x86/visws/sgivw.h b/include/asm-x86/visws/sgivw.h
new file mode 100644
index 000000000000..5fbf63e1003c
--- /dev/null
+++ b/include/asm-x86/visws/sgivw.h
@@ -0,0 +1,5 @@
+/*
+ * Frame buffer position and size:
+ */
+extern unsigned long sgivwfb_mem_phys;
+extern unsigned long sgivwfb_mem_size;
diff --git a/include/asm-x86/vm86.h b/include/asm-x86/vm86.h
index 074b357146df..5ce351325e01 100644
--- a/include/asm-x86/vm86.h
+++ b/include/asm-x86/vm86.h
@@ -14,12 +14,6 @@
 
 #include <asm/processor-flags.h>
 
-#ifdef CONFIG_VM86
-#define X86_VM_MASK	X86_EFLAGS_VM
-#else
-#define X86_VM_MASK	0 /* No VM86 support */
-#endif
-
 #define BIOSSEG		0x0f000
 
 #define CPU_086		0
@@ -121,7 +115,6 @@ struct vm86plus_info_struct {
 	unsigned long is_vm86pus:1;	      /* for vm86 internal use */
 	unsigned char vm86dbg_intxxtab[32];   /* for debugger */
 };
-
 struct vm86plus_struct {
 	struct vm86_regs regs;
 	unsigned long flags;
@@ -133,6 +126,9 @@ struct vm86plus_struct {
 };
 
 #ifdef __KERNEL__
+
+#include <asm/ptrace.h>
+
 /*
  * This is the (kernel) stack-layout when we have done a "SAVE_ALL" from vm86
  * mode - the main change is that the old segment descriptors aren't
@@ -141,7 +137,6 @@ struct vm86plus_struct {
  * at the end of the structure. Look at ptrace.h to see the "normal"
  * setup. For user space layout see 'struct vm86_regs' above.
  */
-#include <asm/ptrace.h>
 
 struct kernel_vm86_regs {
 /*
diff --git a/include/asm-x86/vmi_time.h b/include/asm-x86/vmi_time.h
index 478188130328..c3118c385156 100644
--- a/include/asm-x86/vmi_time.h
+++ b/include/asm-x86/vmi_time.h
@@ -50,7 +50,7 @@ extern void __init vmi_time_init(void);
 extern unsigned long vmi_get_wallclock(void);
 extern int vmi_set_wallclock(unsigned long now);
 extern unsigned long long vmi_sched_clock(void);
-extern unsigned long vmi_cpu_khz(void);
+extern unsigned long vmi_tsc_khz(void);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 extern void __devinit vmi_time_bsp_init(void);
diff --git a/include/asm-x86/vsyscall.h b/include/asm-x86/vsyscall.h
index 17b3700949bf..6b66ff905af0 100644
--- a/include/asm-x86/vsyscall.h
+++ b/include/asm-x86/vsyscall.h
@@ -24,7 +24,8 @@ enum vsyscall_num {
 	((unused, __section__ (".vsyscall_gtod_data"),aligned(16)))
 #define __section_vsyscall_clock __attribute__ \
 	((unused, __section__ (".vsyscall_clock"),aligned(16)))
-#define __vsyscall_fn __attribute__ ((unused,__section__(".vsyscall_fn")))
+#define __vsyscall_fn \
+	__attribute__ ((unused, __section__(".vsyscall_fn"))) notrace
 
 #define VGETCPU_RDTSCP	1
 #define VGETCPU_LSL	2
diff --git a/include/asm-x86/xen/events.h b/include/asm-x86/xen/events.h
index 596312a7bfc9..f8d57ea1f05f 100644
--- a/include/asm-x86/xen/events.h
+++ b/include/asm-x86/xen/events.h
@@ -4,6 +4,7 @@
 enum ipi_vector {
 	XEN_RESCHEDULE_VECTOR,
 	XEN_CALL_FUNCTION_VECTOR,
+	XEN_CALL_FUNCTION_SINGLE_VECTOR,
 
 	XEN_NR_IPIS,
 };
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
index c2ccd997ed35..2a4f9b41d684 100644
--- a/include/asm-x86/xen/hypercall.h
+++ b/include/asm-x86/xen/hypercall.h
@@ -176,9 +176,9 @@ HYPERVISOR_fpu_taskswitch(int set)
 }
 
 static inline int
-HYPERVISOR_sched_op(int cmd, unsigned long arg)
+HYPERVISOR_sched_op(int cmd, void *arg)
 {
-	return _hypercall2(int, sched_op, cmd, arg);
+	return _hypercall2(int, sched_op_new, cmd, arg);
 }
 
 static inline long
@@ -315,6 +315,13 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg)
 }
 
 static inline void
+MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
+{
+	mcl->op = __HYPERVISOR_fpu_taskswitch;
+	mcl->args[0] = set;
+}
+
+static inline void
 MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
 			pte_t new_val, unsigned long flags)
 {
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
index e11f24038b1d..377c04591c15 100644
--- a/include/asm-x86/xen/page.h
+++ b/include/asm-x86/xen/page.h
@@ -26,15 +26,20 @@ typedef struct xpaddr {
 #define FOREIGN_FRAME_BIT	(1UL<<31)
 #define FOREIGN_FRAME(m)	((m) | FOREIGN_FRAME_BIT)
 
-extern unsigned long *phys_to_machine_mapping;
+/* Maximum amount of memory we can handle in a domain in pages */
+#define MAX_DOMAIN_PAGES						\
+    ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
+
+
+extern unsigned long get_phys_to_machine(unsigned long pfn);
+extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return pfn;
 
-	return phys_to_machine_mapping[(unsigned int)(pfn)] &
-		~FOREIGN_FRAME_BIT;
+	return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
 }
 
 static inline int phys_to_machine_mapping_valid(unsigned long pfn)
@@ -42,7 +47,7 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return 1;
 
-	return (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY);
+	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
 static inline unsigned long mfn_to_pfn(unsigned long mfn)
@@ -106,20 +111,12 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
 	unsigned long pfn = mfn_to_pfn(mfn);
 	if ((pfn < max_mapnr)
 	    && !xen_feature(XENFEAT_auto_translated_physmap)
-	    && (phys_to_machine_mapping[pfn] != mfn))
+	    && (get_phys_to_machine(pfn) != mfn))
 		return max_mapnr; /* force !pfn_valid() */
+	/* XXX fixme; not true with sparsemem */
 	return pfn;
 }
 
-static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
-	if (xen_feature(XENFEAT_auto_translated_physmap)) {
-		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
-		return;
-	}
-	phys_to_machine_mapping[pfn] = mfn;
-}
-
 /* VIRT <-> MACHINE conversion */
 #define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
 #define virt_to_mfn(v)		(pfn_to_mfn(PFN_DOWN(__pa(v))))
diff --git a/include/asm-x86/xor_32.h b/include/asm-x86/xor_32.h
index 067b5c1835a3..921b45840449 100644
--- a/include/asm-x86/xor_32.h
+++ b/include/asm-x86/xor_32.h
@@ -1,3 +1,6 @@
+#ifndef ASM_X86__XOR_32_H
+#define ASM_X86__XOR_32_H
+
 /*
  * Optimized RAID-5 checksumming functions for MMX and SSE.
  *
@@ -881,3 +884,5 @@ do {							\
    deals with a load to a line that is being prefetched.  */
 #define XOR_SELECT_TEMPLATE(FASTEST)			\
 	(cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
+
+#endif /* ASM_X86__XOR_32_H */
diff --git a/include/asm-x86/xor_64.h b/include/asm-x86/xor_64.h
index 24957e39ac8a..2d3a18de295b 100644
--- a/include/asm-x86/xor_64.h
+++ b/include/asm-x86/xor_64.h
@@ -1,3 +1,6 @@
+#ifndef ASM_X86__XOR_64_H
+#define ASM_X86__XOR_64_H
+
 /*
  * Optimized RAID-5 checksumming functions for MMX and SSE.
  *
@@ -354,3 +357,5 @@ do {						\
    We may also be able to load into the L1 only depending on how the cpu
    deals with a load to a line that is being prefetched.  */
 #define XOR_SELECT_TEMPLATE(FASTEST) (&xor_block_sse)
+
+#endif /* ASM_X86__XOR_64_H */