i386/x86_64: move headers to include/asm-x86

Move the headers to include/asm-x86 and fixup the
header install make rules

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

521 files changed, 37717 insertions, 0 deletions

diff --git a/include/asm-x86/8253pit.h b/include/asm-x86/8253pit.h
new file mode 100644
index 000000000000..d3c2b38a6618
--- /dev/null
+++ b/include/asm-x86/8253pit.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "8253pit_32.h"
+#else
+# include "8253pit_64.h"
+#endif
diff --git a/include/asm-x86/8253pit_32.h b/include/asm-x86/8253pit_32.h
new file mode 100644
index 000000000000..96c7c3592daf
--- /dev/null
+++ b/include/asm-x86/8253pit_32.h
@@ -0,0 +1,12 @@
+/*
+ * 8253/8254 Programmable Interval Timer
+ */
+
+#ifndef _8253PIT_H
+#define _8253PIT_H
+
+#include <asm/timex.h>
+
+#define PIT_TICK_RATE   CLOCK_TICK_RATE
+
+#endif
diff --git a/include/asm-x86/8253pit_64.h b/include/asm-x86/8253pit_64.h
new file mode 100644
index 000000000000..285f78488ccb
--- /dev/null
+++ b/include/asm-x86/8253pit_64.h
@@ -0,0 +1,10 @@
+/*
+ * 8253/8254 Programmable Interval Timer
+ */
+
+#ifndef _8253PIT_H
+#define _8253PIT_H
+
+#define PIT_TICK_RATE   1193182UL
+
+#endif
diff --git a/include/asm-x86/Kbuild b/include/asm-x86/Kbuild
new file mode 100644
index 000000000000..c5e43cb39874
--- /dev/null
+++ b/include/asm-x86/Kbuild
@@ -0,0 +1,88 @@
+include include/asm-generic/Kbuild.asm
+
+header-y += boot.h
+header-y += bootsetup.h
+header-y += debugreg_32.h
+header-y += debugreg_64.h
+header-y += debugreg.h
+header-y += ldt_32.h
+header-y += ldt_64.h
+header-y += ldt.h
+header-y += msr-index.h
+header-y += prctl.h
+header-y += ptrace-abi_32.h
+header-y += ptrace-abi_64.h
+header-y += ptrace-abi.h
+header-y += sigcontext32.h
+header-y += ucontext_32.h
+header-y += ucontext_64.h
+header-y += ucontext.h
+header-y += vsyscall32.h
+
+unifdef-y += a.out_32.h
+unifdef-y += a.out_64.h
+unifdef-y += auxvec_32.h
+unifdef-y += auxvec_64.h
+unifdef-y += byteorder_32.h
+unifdef-y += byteorder_64.h
+unifdef-y += elf_32.h
+unifdef-y += elf_64.h
+unifdef-y += errno_32.h
+unifdef-y += errno_64.h
+unifdef-y += ioctls_32.h
+unifdef-y += ioctls_64.h
+unifdef-y += ipcbuf_32.h
+unifdef-y += ipcbuf_64.h
+unifdef-y += mce.h
+unifdef-y += mman_32.h
+unifdef-y += mman_64.h
+unifdef-y += msgbuf_32.h
+unifdef-y += msgbuf_64.h
+unifdef-y += msr_32.h
+unifdef-y += msr_64.h
+unifdef-y += msr.h
+unifdef-y += mtrr_32.h
+unifdef-y += mtrr_64.h
+unifdef-y += mtrr.h
+unifdef-y += page_32.h
+unifdef-y += page_64.h
+unifdef-y += param_32.h
+unifdef-y += param_64.h
+unifdef-y += posix_types_32.h
+unifdef-y += posix_types_64.h
+unifdef-y += ptrace_32.h
+unifdef-y += ptrace_64.h
+unifdef-y += resource_32.h
+unifdef-y += resource_64.h
+unifdef-y += sembuf_32.h
+unifdef-y += sembuf_64.h
+unifdef-y += setup_32.h
+unifdef-y += setup_64.h
+unifdef-y += shmbuf_32.h
+unifdef-y += shmbuf_64.h
+unifdef-y += shmparam_32.h
+unifdef-y += shmparam_64.h
+unifdef-y += sigcontext_32.h
+unifdef-y += sigcontext_64.h
+unifdef-y += siginfo_32.h
+unifdef-y += siginfo_64.h
+unifdef-y += signal_32.h
+unifdef-y += signal_64.h
+unifdef-y += sockios_32.h
+unifdef-y += sockios_64.h
+unifdef-y += stat_32.h
+unifdef-y += stat_64.h
+unifdef-y += statfs_32.h
+unifdef-y += statfs_64.h
+unifdef-y += termbits_32.h
+unifdef-y += termbits_64.h
+unifdef-y += termios_32.h
+unifdef-y += termios_64.h
+unifdef-y += types_32.h
+unifdef-y += types_64.h
+unifdef-y += unistd_32.h
+unifdef-y += unistd_64.h
+unifdef-y += user_32.h
+unifdef-y += user_64.h
+unifdef-y += vm86.h
+unifdef-y += vsyscall.h
diff --git a/include/asm-x86/a.out.h b/include/asm-x86/a.out.h
new file mode 100644
index 000000000000..5bc9b1d3b227
--- /dev/null
+++ b/include/asm-x86/a.out.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "a.out_32.h"
+# else
+#  include "a.out_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "a.out_32.h"
+# else
+#  include "a.out_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/a.out_32.h b/include/asm-x86/a.out_32.h
new file mode 100644
index 000000000000..851a60f8258c
--- /dev/null
+++ b/include/asm-x86/a.out_32.h
@@ -0,0 +1,27 @@
+#ifndef __I386_A_OUT_H__
+#define __I386_A_OUT_H__
+
+struct exec
+{
+  unsigned long a_info;         /* Use macros N_MAGIC, etc for access */
+  unsigned a_text;              /* length of text, in bytes */
+  unsigned a_data;              /* length of data, in bytes */
+  unsigned a_bss;               /* length of uninitialized data area for file, in bytes */
+  unsigned a_syms;              /* length of symbol table data in file, in bytes */
+  unsigned a_entry;             /* start address */
+  unsigned a_trsize;            /* length of relocation info for text, in bytes */
+  unsigned a_drsize;            /* length of relocation info for data, in bytes */
+};
+
+#define N_TRSIZE(a)     ((a).a_trsize)
+#define N_DRSIZE(a)     ((a).a_drsize)
+#define N_SYMSIZE(a)    ((a).a_syms)
+
+#ifdef __KERNEL__
+
+#define STACK_TOP       TASK_SIZE
+#define STACK_TOP_MAX   STACK_TOP
+
+#endif
+
+#endif /* __A_OUT_GNU_H__ */
diff --git a/include/asm-x86/a.out_64.h b/include/asm-x86/a.out_64.h
new file mode 100644
index 000000000000..e789300e41a5
--- /dev/null
+++ b/include/asm-x86/a.out_64.h
@@ -0,0 +1,28 @@
+#ifndef __X8664_A_OUT_H__
+#define __X8664_A_OUT_H__
+
+/* 32bit a.out */
+
+struct exec
+{
+  unsigned int a_info;          /* Use macros N_MAGIC, etc for access */
+  unsigned a_text;              /* length of text, in bytes */
+  unsigned a_data;              /* length of data, in bytes */
+  unsigned a_bss;               /* length of uninitialized data area for file, in bytes */
+  unsigned a_syms;              /* length of symbol table data in file, in bytes */
+  unsigned a_entry;             /* start address */
+  unsigned a_trsize;            /* length of relocation info for text, in bytes */
+  unsigned a_drsize;            /* length of relocation info for data, in bytes */
+};
+
+#define N_TRSIZE(a)     ((a).a_trsize)
+#define N_DRSIZE(a)     ((a).a_drsize)
+#define N_SYMSIZE(a)    ((a).a_syms)
+
+#ifdef __KERNEL__
+#include <linux/thread_info.h>
+#define STACK_TOP       TASK_SIZE
+#define STACK_TOP_MAX   TASK_SIZE64
+#endif
+
+#endif /* __A_OUT_GNU_H__ */
diff --git a/include/asm-x86/acpi.h b/include/asm-x86/acpi.h
new file mode 100644
index 000000000000..0693689d4146
--- /dev/null
+++ b/include/asm-x86/acpi.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "acpi_32.h"
+#else
+# include "acpi_64.h"
+#endif
diff --git a/include/asm-x86/acpi_32.h b/include/asm-x86/acpi_32.h
new file mode 100644
index 000000000000..125179adf044
--- /dev/null
+++ b/include/asm-x86/acpi_32.h
@@ -0,0 +1,147 @@
+/*
+ *  asm-i386/acpi.h
+ *
+ *  Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2001 Patrick Mochel <mochel@osdl.org>
+  *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#ifndef _ASM_ACPI_H
+#define _ASM_ACPI_H
+
+#ifdef __KERNEL__
+
+#include <acpi/pdc_intel.h>
+
+#include <asm/system.h>         /* defines cmpxchg */
+
+#define COMPILER_DEPENDENT_INT64   long long
+#define COMPILER_DEPENDENT_UINT64  unsigned long long
+
+/*
+ * Calling conventions:
+ *
+ * ACPI_SYSTEM_XFACE        - Interfaces to host OS (handlers, threads)
+ * ACPI_EXTERNAL_XFACE      - External ACPI interfaces
+ * ACPI_INTERNAL_XFACE      - Internal ACPI interfaces
+ * ACPI_INTERNAL_VAR_XFACE  - Internal variable-parameter list interfaces
+ */
+#define ACPI_SYSTEM_XFACE
+#define ACPI_EXTERNAL_XFACE
+#define ACPI_INTERNAL_XFACE
+#define ACPI_INTERNAL_VAR_XFACE
+
+/* Asm macros */
+
+#define ACPI_ASM_MACROS
+#define BREAKPOINT3
+#define ACPI_DISABLE_IRQS() local_irq_disable()
+#define ACPI_ENABLE_IRQS()  local_irq_enable()
+#define ACPI_FLUSH_CPU_CACHE()  wbinvd()
+
+int __acpi_acquire_global_lock(unsigned int *lock);
+int __acpi_release_global_lock(unsigned int *lock);
+
+#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \
+        ((Acq) = __acpi_acquire_global_lock(&facs->global_lock))
+
+#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \
+        ((Acq) = __acpi_release_global_lock(&facs->global_lock))
+
+/*
+ * Math helper asm macros
+ */
+#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \
+        asm("divl %2;"        \
+        :"=a"(q32), "=d"(r32) \
+        :"r"(d32),            \
+        "0"(n_lo), "1"(n_hi))
+
+
+#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \
+    asm("shrl   $1,%2;"             \
+        "rcrl   $1,%3;"             \
+        :"=r"(n_hi), "=r"(n_lo)     \
+        :"0"(n_hi), "1"(n_lo))
+
+#ifdef CONFIG_X86_IO_APIC
+extern void check_acpi_pci(void);
+#else
+static inline void check_acpi_pci(void) { }
+#endif
+
+#ifdef CONFIG_ACPI
+extern int acpi_lapic;
+extern int acpi_ioapic;
+extern int acpi_noirq;
+extern int acpi_strict;
+extern int acpi_disabled;
+extern int acpi_ht;
+extern int acpi_pci_disabled;
+static inline void disable_acpi(void)
+{
+        acpi_disabled = 1;
+        acpi_ht = 0;
+        acpi_pci_disabled = 1;
+        acpi_noirq = 1;
+}
+
+/* Fixmap pages to reserve for ACPI boot-time tables (see fixmap.h) */
+#define FIX_ACPI_PAGES 4
+
+extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
+
+#ifdef CONFIG_X86_IO_APIC
+extern int acpi_skip_timer_override;
+extern int acpi_use_timer_override;
+#endif
+
+static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
+static inline void acpi_disable_pci(void)
+{
+        acpi_pci_disabled = 1;
+        acpi_noirq_set();
+}
+extern int acpi_irq_balance_set(char *str);
+
+/* routines for saving/restoring kernel state */
+extern int acpi_save_state_mem(void);
+extern void acpi_restore_state_mem(void);
+
+extern unsigned long acpi_wakeup_address;
+
+/* early initialization routine */
+extern void acpi_reserve_bootmem(void);
+
+#else   /* !CONFIG_ACPI */
+
+#define acpi_lapic 0
+#define acpi_ioapic 0
+static inline void acpi_noirq_set(void) { }
+static inline void acpi_disable_pci(void) { }
+static inline void disable_acpi(void) { }
+
+#endif  /* !CONFIG_ACPI */
+
+#define ARCH_HAS_POWER_INIT     1
+
+#endif /*__KERNEL__*/
+
+#endif /*_ASM_ACPI_H*/
diff --git a/include/asm-x86/acpi_64.h b/include/asm-x86/acpi_64.h
new file mode 100644
index 000000000000..98173357dd89
--- /dev/null
+++ b/include/asm-x86/acpi_64.h
@@ -0,0 +1,153 @@
+/*
+ *  asm-x86_64/acpi.h
+ *
+ *  Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2001 Patrick Mochel <mochel@osdl.org>
+  *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#ifndef _ASM_ACPI_H
+#define _ASM_ACPI_H
+
+#ifdef __KERNEL__
+
+#include <acpi/pdc_intel.h>
+#include <asm/numa.h>
+
+#define COMPILER_DEPENDENT_INT64   long long
+#define COMPILER_DEPENDENT_UINT64  unsigned long long
+
+/*
+ * Calling conventions:
+ *
+ * ACPI_SYSTEM_XFACE        - Interfaces to host OS (handlers, threads)
+ * ACPI_EXTERNAL_XFACE      - External ACPI interfaces
+ * ACPI_INTERNAL_XFACE      - Internal ACPI interfaces
+ * ACPI_INTERNAL_VAR_XFACE  - Internal variable-parameter list interfaces
+ */
+#define ACPI_SYSTEM_XFACE
+#define ACPI_EXTERNAL_XFACE
+#define ACPI_INTERNAL_XFACE
+#define ACPI_INTERNAL_VAR_XFACE
+
+/* Asm macros */
+
+#define ACPI_ASM_MACROS
+#define BREAKPOINT3
+#define ACPI_DISABLE_IRQS() local_irq_disable()
+#define ACPI_ENABLE_IRQS()  local_irq_enable()
+#define ACPI_FLUSH_CPU_CACHE()  wbinvd()
+
+int __acpi_acquire_global_lock(unsigned int *lock);
+int __acpi_release_global_lock(unsigned int *lock);
+
+#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \
+        ((Acq) = __acpi_acquire_global_lock(&facs->global_lock))
+
+#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \
+        ((Acq) = __acpi_release_global_lock(&facs->global_lock))
+
+/*
+ * Math helper asm macros
+ */
+#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \
+        asm("divl %2;"        \
+        :"=a"(q32), "=d"(r32) \
+        :"r"(d32),            \
+        "0"(n_lo), "1"(n_hi))
+
+
+#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \
+    asm("shrl   $1,%2;"             \
+        "rcrl   $1,%3;"             \
+        :"=r"(n_hi), "=r"(n_lo)     \
+        :"0"(n_hi), "1"(n_lo))
+
+#ifdef CONFIG_ACPI
+extern int acpi_lapic;
+extern int acpi_ioapic;
+extern int acpi_noirq;
+extern int acpi_strict;
+extern int acpi_disabled;
+extern int acpi_pci_disabled;
+extern int acpi_ht;
+static inline void disable_acpi(void)
+{
+        acpi_disabled = 1;
+        acpi_ht = 0;
+        acpi_pci_disabled = 1;
+        acpi_noirq = 1;
+}
+
+/* Fixmap pages to reserve for ACPI boot-time tables (see fixmap.h) */
+#define FIX_ACPI_PAGES 4
+
+extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
+static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
+static inline void acpi_disable_pci(void)
+{
+        acpi_pci_disabled = 1;
+        acpi_noirq_set();
+}
+extern int acpi_irq_balance_set(char *str);
+
+/* routines for saving/restoring kernel state */
+extern int acpi_save_state_mem(void);
+extern void acpi_restore_state_mem(void);
+
+extern unsigned long acpi_wakeup_address;
+
+/* early initialization routine */
+extern void acpi_reserve_bootmem(void);
+
+#else   /* !CONFIG_ACPI */
+
+#define acpi_lapic 0
+#define acpi_ioapic 0
+static inline void acpi_noirq_set(void) { }
+static inline void acpi_disable_pci(void) { }
+
+#endif /* !CONFIG_ACPI */
+
+extern int acpi_numa;
+extern int acpi_scan_nodes(unsigned long start, unsigned long end);
+#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
+
+extern int acpi_disabled;
+extern int acpi_pci_disabled;
+
+#define ARCH_HAS_POWER_INIT 1
+
+extern int acpi_skip_timer_override;
+extern int acpi_use_timer_override;
+
+#ifdef CONFIG_ACPI_NUMA
+extern void __init acpi_fake_nodes(const struct bootnode *fake_nodes,
+                                   int num_nodes);
+#else
+static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
+                                   int num_nodes)
+{
+}
+#endif
+
+#endif /*__KERNEL__*/
+
+#endif /*_ASM_ACPI_H*/
diff --git a/include/asm-x86/agp.h b/include/asm-x86/agp.h
new file mode 100644
index 000000000000..9348f1e4f6f1
--- /dev/null
+++ b/include/asm-x86/agp.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "agp_32.h"
+#else
+# include "agp_64.h"
+#endif
diff --git a/include/asm-x86/agp_32.h b/include/asm-x86/agp_32.h
new file mode 100644
index 000000000000..6af173dbf123
--- /dev/null
+++ b/include/asm-x86/agp_32.h
@@ -0,0 +1,36 @@
+#ifndef AGP_H
+#define AGP_H 1
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+/* 
+ * Functions to keep the agpgart mappings coherent with the MMU.
+ * The GART gives the CPU a physical alias of pages in memory. The alias region is
+ * mapped uncacheable. Make sure there are no conflicting mappings
+ * with different cachability attributes for the same page. This avoids
+ * data corruption on some CPUs.
+ */
+
+/* Caller's responsibility to call global_flush_tlb() for
+ * performance reasons */
+#define map_page_into_agp(page) change_page_attr(page, 1, PAGE_KERNEL_NOCACHE)
+#define unmap_page_from_agp(page) change_page_attr(page, 1, PAGE_KERNEL)
+#define flush_agp_mappings() global_flush_tlb()
+
+/* Could use CLFLUSH here if the cpu supports it. But then it would
+   need to be called for each cacheline of the whole page so it may not be 
+   worth it. Would need a page for it. */
+#define flush_agp_cache() wbinvd()
+
+/* Convert a physical address to an address suitable for the GART. */
+#define phys_to_gart(x) (x)
+#define gart_to_phys(x) (x)
+
+/* GATT allocation. Returns/accepts GATT kernel virtual address. */
+#define alloc_gatt_pages(order)         \
+        ((char *)__get_free_pages(GFP_KERNEL, (order)))
+#define free_gatt_pages(table, order)   \
+        free_pages((unsigned long)(table), (order))
+
+#endif
diff --git a/include/asm-x86/agp_64.h b/include/asm-x86/agp_64.h
new file mode 100644
index 000000000000..de338666f3f9
--- /dev/null
+++ b/include/asm-x86/agp_64.h
@@ -0,0 +1,34 @@
+#ifndef AGP_H
+#define AGP_H 1
+
+#include <asm/cacheflush.h>
+
+/* 
+ * Functions to keep the agpgart mappings coherent.
+ * The GART gives the CPU a physical alias of memory. The alias is
+ * mapped uncacheable. Make sure there are no conflicting mappings
+ * with different cachability attributes for the same page.
+ */
+
+/* Caller's responsibility to call global_flush_tlb() for
+ * performance reasons */
+#define map_page_into_agp(page) change_page_attr(page, 1, PAGE_KERNEL_NOCACHE)
+#define unmap_page_from_agp(page) change_page_attr(page, 1, PAGE_KERNEL)
+#define flush_agp_mappings() global_flush_tlb()
+
+/* Could use CLFLUSH here if the cpu supports it. But then it would
+   need to be called for each cacheline of the whole page so it may not be 
+   worth it. Would need a page for it. */
+#define flush_agp_cache() asm volatile("wbinvd":::"memory")
+
+/* Convert a physical address to an address suitable for the GART. */
+#define phys_to_gart(x) (x)
+#define gart_to_phys(x) (x)
+
+/* GATT allocation. Returns/accepts GATT kernel virtual address. */
+#define alloc_gatt_pages(order)         \
+        ((char *)__get_free_pages(GFP_KERNEL, (order)))
+#define free_gatt_pages(table, order)   \
+        free_pages((unsigned long)(table), (order))
+
+#endif
diff --git a/include/asm-x86/alternative-asm.i b/include/asm-x86/alternative-asm.i
new file mode 100644
index 000000000000..4f360cd3c888
--- /dev/null
+++ b/include/asm-x86/alternative-asm.i
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "alternative-asm_32.i"
+#else
+# include "alternative-asm_64.i"
+#endif
diff --git a/include/asm-x86/alternative-asm_32.i b/include/asm-x86/alternative-asm_32.i
new file mode 100644
index 000000000000..f0510209ccbe
--- /dev/null
+++ b/include/asm-x86/alternative-asm_32.i
@@ -0,0 +1,12 @@
+#ifdef CONFIG_SMP
+        .macro LOCK_PREFIX
+1:      lock
+        .section .smp_locks,"a"
+        .align 4
+        .long 1b
+        .previous
+        .endm
+#else
+        .macro LOCK_PREFIX
+        .endm
+#endif
diff --git a/include/asm-x86/alternative-asm_64.i b/include/asm-x86/alternative-asm_64.i
new file mode 100644
index 000000000000..0b3f1a2bb2cb
--- /dev/null
+++ b/include/asm-x86/alternative-asm_64.i
@@ -0,0 +1,12 @@
+#ifdef CONFIG_SMP
+        .macro LOCK_PREFIX
+1:      lock
+        .section .smp_locks,"a"
+        .align 8
+        .quad 1b
+        .previous
+        .endm
+#else
+        .macro LOCK_PREFIX
+        .endm
+#endif
diff --git a/include/asm-x86/alternative.h b/include/asm-x86/alternative.h
new file mode 100644
index 000000000000..9eef6a32a130
--- /dev/null
+++ b/include/asm-x86/alternative.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "alternative_32.h"
+#else
+# include "alternative_64.h"
+#endif
diff --git a/include/asm-x86/alternative_32.h b/include/asm-x86/alternative_32.h
new file mode 100644
index 000000000000..bda6c810c0f4
--- /dev/null
+++ b/include/asm-x86/alternative_32.h
@@ -0,0 +1,154 @@
+#ifndef _I386_ALTERNATIVE_H
+#define _I386_ALTERNATIVE_H
+
+#include <asm/types.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+struct alt_instr {
+        u8 *instr;              /* original instruction */
+        u8 *replacement;
+        u8  cpuid;              /* cpuid bit set for replacement */
+        u8  instrlen;           /* length of original instruction */
+        u8  replacementlen;     /* length of new instruction, <= instrlen */
+        u8  pad;
+};
+
+extern void alternative_instructions(void);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+
+struct module;
+#ifdef CONFIG_SMP
+extern void alternatives_smp_module_add(struct module *mod, char *name,
+                                        void *locks, void *locks_end,
+                                        void *text, void *text_end);
+extern void alternatives_smp_module_del(struct module *mod);
+extern void alternatives_smp_switch(int smp);
+#else
+static inline void alternatives_smp_module_add(struct module *mod, char *name,
+                                        void *locks, void *locks_end,
+                                        void *text, void *text_end) {}
+static inline void alternatives_smp_module_del(struct module *mod) {}
+static inline void alternatives_smp_switch(int smp) {}
+#endif  /* CONFIG_SMP */
+
+/*
+ * Alternative instructions for different CPU types or capabilities.
+ *
+ * This allows to use optimized instructions even on generic binary
+ * kernels.
+ *
+ * length of oldinstr must be longer or equal the length of newinstr
+ * It can be padded with nops as needed.
+ *
+ * For non barrier like inlines please define new variants
+ * without volatile and memory clobber.
+ */
+#define alternative(oldinstr, newinstr, feature)                        \
+        asm volatile ("661:\n\t" oldinstr "\n662:\n"                    \
+                      ".section .altinstructions,\"a\"\n"               \
+                      "  .align 4\n"                                    \
+                      "  .long 661b\n"            /* label */           \
+                      "  .long 663f\n"            /* new instruction */ \
+                      "  .byte %c0\n"             /* feature bit */     \
+                      "  .byte 662b-661b\n"       /* sourcelen */       \
+                      "  .byte 664f-663f\n"       /* replacementlen */  \
+                      ".previous\n"                                     \
+                      ".section .altinstr_replacement,\"ax\"\n"         \
+                      "663:\n\t" newinstr "\n664:\n"   /* replacement */\
+                      ".previous" :: "i" (feature) : "memory")
+
+/*
+ * Alternative inline assembly with input.
+ *
+ * Pecularities:
+ * No memory clobber here.
+ * Argument numbers start with 1.
+ * Best is to use constraints that are fixed size (like (%1) ... "r")
+ * If you use variable sized constraints like "m" or "g" in the
+ * replacement maake sure to pad to the worst case length.
+ */
+#define alternative_input(oldinstr, newinstr, feature, input...)        \
+        asm volatile ("661:\n\t" oldinstr "\n662:\n"                    \
+                      ".section .altinstructions,\"a\"\n"               \
+                      "  .align 4\n"                                    \
+                      "  .long 661b\n"            /* label */           \
+                      "  .long 663f\n"            /* new instruction */ \
+                      "  .byte %c0\n"             /* feature bit */     \
+                      "  .byte 662b-661b\n"       /* sourcelen */       \
+                      "  .byte 664f-663f\n"       /* replacementlen */  \
+                      ".previous\n"                                     \
+                      ".section .altinstr_replacement,\"ax\"\n"         \
+                      "663:\n\t" newinstr "\n664:\n"   /* replacement */\
+                      ".previous" :: "i" (feature), ##input)
+
+/* Like alternative_input, but with a single output argument */
+#define alternative_io(oldinstr, newinstr, feature, output, input...) \
+        asm volatile ("661:\n\t" oldinstr "\n662:\n"                    \
+                      ".section .altinstructions,\"a\"\n"               \
+                      "  .align 4\n"                                    \
+                      "  .long 661b\n"            /* label */           \
+                      "  .long 663f\n"            /* new instruction */ \
+                      "  .byte %c[feat]\n"        /* feature bit */     \
+                      "  .byte 662b-661b\n"       /* sourcelen */       \
+                      "  .byte 664f-663f\n"       /* replacementlen */  \
+                      ".previous\n"                                     \
+                      ".section .altinstr_replacement,\"ax\"\n"         \
+                      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
+                      ".previous" : output : [feat] "i" (feature), ##input)
+
+/*
+ * use this macro(s) if you need more than one output parameter
+ * in alternative_io
+ */
+#define ASM_OUTPUT2(a, b) a, b
+
+/*
+ * Alternative inline assembly for SMP.
+ *
+ * The LOCK_PREFIX macro defined here replaces the LOCK and
+ * LOCK_PREFIX macros used everywhere in the source tree.
+ *
+ * SMP alternatives use the same data structures as the other
+ * alternatives and the X86_FEATURE_UP flag to indicate the case of a
+ * UP system running a SMP kernel.  The existing apply_alternatives()
+ * works fine for patching a SMP kernel for UP.
+ *
+ * The SMP alternative tables can be kept after boot and contain both
+ * UP and SMP versions of the instructions to allow switching back to
+ * SMP at runtime, when hotplugging in a new CPU, which is especially
+ * useful in virtualized environments.
+ *
+ * The very common lock prefix is handled as special case in a
+ * separate table which is a pure address list without replacement ptr
+ * and size information.  That keeps the table sizes small.
+ */
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX \
+                ".section .smp_locks,\"a\"\n"   \
+                "  .align 4\n"                  \
+                "  .long 661f\n" /* address */  \
+                ".previous\n"                   \
+                "661:\n\tlock; "
+
+#else /* ! CONFIG_SMP */
+#define LOCK_PREFIX ""
+#endif
+
+struct paravirt_patch_site;
+#ifdef CONFIG_PARAVIRT
+void apply_paravirt(struct paravirt_patch_site *start,
+                    struct paravirt_patch_site *end);
+#else
+static inline void
+apply_paravirt(struct paravirt_patch_site *start,
+               struct paravirt_patch_site *end)
+{}
+#define __parainstructions      NULL
+#define __parainstructions_end  NULL
+#endif
+
+extern void text_poke(void *addr, unsigned char *opcode, int len);
+
+#endif /* _I386_ALTERNATIVE_H */
diff --git a/include/asm-x86/alternative_64.h b/include/asm-x86/alternative_64.h
new file mode 100644
index 000000000000..ab161e810151
--- /dev/null
+++ b/include/asm-x86/alternative_64.h
@@ -0,0 +1,159 @@
+#ifndef _X86_64_ALTERNATIVE_H
+#define _X86_64_ALTERNATIVE_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+
+/*
+ * Alternative inline assembly for SMP.
+ *
+ * The LOCK_PREFIX macro defined here replaces the LOCK and
+ * LOCK_PREFIX macros used everywhere in the source tree.
+ *
+ * SMP alternatives use the same data structures as the other
+ * alternatives and the X86_FEATURE_UP flag to indicate the case of a
+ * UP system running a SMP kernel.  The existing apply_alternatives()
+ * works fine for patching a SMP kernel for UP.
+ *
+ * The SMP alternative tables can be kept after boot and contain both
+ * UP and SMP versions of the instructions to allow switching back to
+ * SMP at runtime, when hotplugging in a new CPU, which is especially
+ * useful in virtualized environments.
+ *
+ * The very common lock prefix is handled as special case in a
+ * separate table which is a pure address list without replacement ptr
+ * and size information.  That keeps the table sizes small.
+ */
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX \
+                ".section .smp_locks,\"a\"\n"   \
+                "  .align 8\n"                  \
+                "  .quad 661f\n" /* address */  \
+                ".previous\n"                   \
+                "661:\n\tlock; "
+
+#else /* ! CONFIG_SMP */
+#define LOCK_PREFIX ""
+#endif
+
+/* This must be included *after* the definition of LOCK_PREFIX */
+#include <asm/cpufeature.h>
+
+struct alt_instr {
+        u8 *instr;              /* original instruction */
+        u8 *replacement;
+        u8  cpuid;              /* cpuid bit set for replacement */
+        u8  instrlen;           /* length of original instruction */
+        u8  replacementlen;     /* length of new instruction, <= instrlen */
+        u8  pad[5];
+};
+
+extern void alternative_instructions(void);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+
+struct module;
+
+#ifdef CONFIG_SMP
+extern void alternatives_smp_module_add(struct module *mod, char *name,
+                                        void *locks, void *locks_end,
+                                        void *text, void *text_end);
+extern void alternatives_smp_module_del(struct module *mod);
+extern void alternatives_smp_switch(int smp);
+#else
+static inline void alternatives_smp_module_add(struct module *mod, char *name,
+                                        void *locks, void *locks_end,
+                                        void *text, void *text_end) {}
+static inline void alternatives_smp_module_del(struct module *mod) {}
+static inline void alternatives_smp_switch(int smp) {}
+#endif
+
+#endif
+
+/*
+ * Alternative instructions for different CPU types or capabilities.
+ *
+ * This allows to use optimized instructions even on generic binary
+ * kernels.
+ *
+ * length of oldinstr must be longer or equal the length of newinstr
+ * It can be padded with nops as needed.
+ *
+ * For non barrier like inlines please define new variants
+ * without volatile and memory clobber.
+ */
+#define alternative(oldinstr, newinstr, feature)        \
+        asm volatile ("661:\n\t" oldinstr "\n662:\n"                 \
+                      ".section .altinstructions,\"a\"\n"            \
+                      "  .align 8\n"                                   \
+                      "  .quad 661b\n"            /* label */          \
+                      "  .quad 663f\n"            /* new instruction */ \
+                      "  .byte %c0\n"             /* feature bit */    \
+                      "  .byte 662b-661b\n"       /* sourcelen */      \
+                      "  .byte 664f-663f\n"       /* replacementlen */ \
+                      ".previous\n"                                     \
+                      ".section .altinstr_replacement,\"ax\"\n"         \
+                      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
+                      ".previous" :: "i" (feature) : "memory")
+
+/*
+ * Alternative inline assembly with input.
+ *
+ * Pecularities:
+ * No memory clobber here.
+ * Argument numbers start with 1.
+ * Best is to use constraints that are fixed size (like (%1) ... "r")
+ * If you use variable sized constraints like "m" or "g" in the
+ * replacement make sure to pad to the worst case length.
+ */
+#define alternative_input(oldinstr, newinstr, feature, input...)        \
+        asm volatile ("661:\n\t" oldinstr "\n662:\n"                    \
+                      ".section .altinstructions,\"a\"\n"               \
+                      "  .align 8\n"                                    \
+                      "  .quad 661b\n"            /* label */           \
+                      "  .quad 663f\n"            /* new instruction */ \
+                      "  .byte %c0\n"             /* feature bit */     \
+                      "  .byte 662b-661b\n"       /* sourcelen */       \
+                      "  .byte 664f-663f\n"       /* replacementlen */  \
+                      ".previous\n"                                     \
+                      ".section .altinstr_replacement,\"ax\"\n"         \
+                      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
+                      ".previous" :: "i" (feature), ##input)
+
+/* Like alternative_input, but with a single output argument */
+#define alternative_io(oldinstr, newinstr, feature, output, input...) \
+        asm volatile ("661:\n\t" oldinstr "\n662:\n"                    \
+                      ".section .altinstructions,\"a\"\n"               \
+                      "  .align 8\n"                                    \
+                      "  .quad 661b\n"            /* label */           \
+                      "  .quad 663f\n"            /* new instruction */ \
+                      "  .byte %c[feat]\n"        /* feature bit */     \
+                      "  .byte 662b-661b\n"       /* sourcelen */       \
+                      "  .byte 664f-663f\n"       /* replacementlen */  \
+                      ".previous\n"                                     \
+                      ".section .altinstr_replacement,\"ax\"\n"         \
+                      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
+                      ".previous" : output : [feat] "i" (feature), ##input)
+
+/*
+ * use this macro(s) if you need more than one output parameter
+ * in alternative_io
+ */
+#define ASM_OUTPUT2(a, b) a, b
+
+struct paravirt_patch;
+#ifdef CONFIG_PARAVIRT
+void apply_paravirt(struct paravirt_patch *start, struct paravirt_patch *end);
+#else
+static inline void
+apply_paravirt(struct paravirt_patch *start, struct paravirt_patch *end)
+{}
+#define __parainstructions NULL
+#define __parainstructions_end NULL
+#endif
+
+extern void text_poke(void *addr, unsigned char *opcode, int len);
+
+#endif /* _X86_64_ALTERNATIVE_H */
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
new file mode 100644
index 000000000000..9fbcc0bd2ac4
--- /dev/null
+++ b/include/asm-x86/apic.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "apic_32.h"
+#else
+# include "apic_64.h"
+#endif
diff --git a/include/asm-x86/apic_32.h b/include/asm-x86/apic_32.h
new file mode 100644
index 000000000000..4091b33dcb10
--- /dev/null
+++ b/include/asm-x86/apic_32.h
@@ -0,0 +1,126 @@
+#ifndef __ASM_APIC_H
+#define __ASM_APIC_H
+
+#include <linux/pm.h>
+#include <linux/delay.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+
+#define Dprintk(x...)
+
+/*
+ * Debugging macros
+ */
+#define APIC_QUIET   0
+#define APIC_VERBOSE 1
+#define APIC_DEBUG   2
+
+extern int apic_verbosity;
+
+/*
+ * Define the default level of output to be very little
+ * This can be turned up by using apic=verbose for more
+ * information and apic=debug for _lots_ of information.
+ * apic_verbosity is defined in apic.c
+ */
+#define apic_printk(v, s, a...) do {       \
+                if ((v) <= apic_verbosity) \
+                        printk(s, ##a);    \
+        } while (0)
+
+
+extern void generic_apic_probe(void);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+/*
+ * Basic functions accessing APICs.
+ */
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define apic_write native_apic_write
+#define apic_write_atomic native_apic_write_atomic
+#define apic_read native_apic_read
+#define setup_boot_clock setup_boot_APIC_clock
+#define setup_secondary_clock setup_secondary_APIC_clock
+#endif
+
+static __inline fastcall void native_apic_write(unsigned long reg,
+                                                unsigned long v)
+{
+        *((volatile unsigned long *)(APIC_BASE+reg)) = v;
+}
+
+static __inline fastcall void native_apic_write_atomic(unsigned long reg,
+                                                       unsigned long v)
+{
+        xchg((volatile unsigned long *)(APIC_BASE+reg), v);
+}
+
+static __inline fastcall unsigned long native_apic_read(unsigned long reg)
+{
+        return *((volatile unsigned long *)(APIC_BASE+reg));
+}
+
+void apic_wait_icr_idle(void);
+unsigned long safe_apic_wait_icr_idle(void);
+int get_physical_broadcast(void);
+
+#ifdef CONFIG_X86_GOOD_APIC
+# define FORCE_READ_AROUND_WRITE 0
+# define apic_read_around(x)
+# define apic_write_around(x,y) apic_write((x),(y))
+#else
+# define FORCE_READ_AROUND_WRITE 1
+# define apic_read_around(x) apic_read(x)
+# define apic_write_around(x,y) apic_write_atomic((x),(y))
+#endif
+
+static inline void ack_APIC_irq(void)
+{
+        /*
+         * ack_APIC_irq() actually gets compiled as a single instruction:
+         * - a single rmw on Pentium/82489DX
+         * - a single write on P6+ cores (CONFIG_X86_GOOD_APIC)
+         * ... yummie.
+         */
+
+        /* Docs say use 0 for future compatibility */
+        apic_write_around(APIC_EOI, 0);
+}
+
+extern int lapic_get_maxlvt(void);
+extern void clear_local_APIC(void);
+extern void connect_bsp_APIC (void);
+extern void disconnect_bsp_APIC (int virt_wire_setup);
+extern void disable_local_APIC (void);
+extern void lapic_shutdown (void);
+extern int verify_local_APIC (void);
+extern void cache_APIC_registers (void);
+extern void sync_Arb_IDs (void);
+extern void init_bsp_APIC (void);
+extern void setup_local_APIC (void);
+extern void init_apic_mappings (void);
+extern void smp_local_timer_interrupt (void);
+extern void setup_boot_APIC_clock (void);
+extern void setup_secondary_APIC_clock (void);
+extern int APIC_init_uniprocessor (void);
+
+extern void enable_NMI_through_LVT0 (void * dummy);
+
+#define ARCH_APICTIMER_STOPS_ON_C3      1
+
+extern int timer_over_8254;
+extern int local_apic_timer_c2_ok;
+
+extern int local_apic_timer_disabled;
+
+#else /* !CONFIG_X86_LOCAL_APIC */
+static inline void lapic_shutdown(void) { }
+
+#endif /* !CONFIG_X86_LOCAL_APIC */
+
+#endif /* __ASM_APIC_H */
diff --git a/include/asm-x86/apic_64.h b/include/asm-x86/apic_64.h
new file mode 100644
index 000000000000..85125ef3c414
--- /dev/null
+++ b/include/asm-x86/apic_64.h
@@ -0,0 +1,107 @@
+#ifndef __ASM_APIC_H
+#define __ASM_APIC_H
+
+#include <linux/pm.h>
+#include <linux/delay.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <asm/system.h>
+
+#define Dprintk(x...)
+
+/*
+ * Debugging macros
+ */
+#define APIC_QUIET   0
+#define APIC_VERBOSE 1
+#define APIC_DEBUG   2
+
+extern int apic_verbosity;
+extern int apic_runs_main_timer;
+extern int ioapic_force;
+extern int apic_mapped;
+
+/*
+ * Define the default level of output to be very little
+ * This can be turned up by using apic=verbose for more
+ * information and apic=debug for _lots_ of information.
+ * apic_verbosity is defined in apic.c
+ */
+#define apic_printk(v, s, a...) do {       \
+                if ((v) <= apic_verbosity) \
+                        printk(s, ##a);    \
+        } while (0)
+
+struct pt_regs;
+
+/*
+ * Basic functions accessing APICs.
+ */
+
+static __inline void apic_write(unsigned long reg, unsigned int v)
+{
+        *((volatile unsigned int *)(APIC_BASE+reg)) = v;
+}
+
+static __inline unsigned int apic_read(unsigned long reg)
+{
+        return *((volatile unsigned int *)(APIC_BASE+reg));
+}
+
+extern void apic_wait_icr_idle(void);
+extern unsigned int safe_apic_wait_icr_idle(void);
+
+static inline void ack_APIC_irq(void)
+{
+        /*
+         * ack_APIC_irq() actually gets compiled as a single instruction:
+         * - a single rmw on Pentium/82489DX
+         * - a single write on P6+ cores (CONFIG_X86_GOOD_APIC)
+         * ... yummie.
+         */
+
+        /* Docs say use 0 for future compatibility */
+        apic_write(APIC_EOI, 0);
+}
+
+extern int get_maxlvt (void);
+extern void clear_local_APIC (void);
+extern void connect_bsp_APIC (void);
+extern void disconnect_bsp_APIC (int virt_wire_setup);
+extern void disable_local_APIC (void);
+extern int verify_local_APIC (void);
+extern void cache_APIC_registers (void);
+extern void sync_Arb_IDs (void);
+extern void init_bsp_APIC (void);
+extern void setup_local_APIC (void);
+extern void init_apic_mappings (void);
+extern void smp_local_timer_interrupt (void);
+extern void setup_boot_APIC_clock (void);
+extern void setup_secondary_APIC_clock (void);
+extern int APIC_init_uniprocessor (void);
+extern void disable_APIC_timer(void);
+extern void enable_APIC_timer(void);
+extern void setup_apic_routing(void);
+
+extern void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
+                                    unsigned char msg_type, unsigned char mask);
+
+extern int apic_is_clustered_box(void);
+
+#define K8_APIC_EXT_LVT_BASE    0x500
+#define K8_APIC_EXT_INT_MSG_FIX 0x0
+#define K8_APIC_EXT_INT_MSG_SMI 0x2
+#define K8_APIC_EXT_INT_MSG_NMI 0x4
+#define K8_APIC_EXT_INT_MSG_EXT 0x7
+#define K8_APIC_EXT_LVT_ENTRY_THRESHOLD    0
+
+void smp_send_timer_broadcast_ipi(void);
+void switch_APIC_timer_to_ipi(void *cpumask);
+void switch_ipi_to_APIC_timer(void *cpumask);
+
+#define ARCH_APICTIMER_STOPS_ON_C3      1
+
+extern unsigned boot_cpu_id;
+extern int local_apic_timer_c2_ok;
+
+#endif /* __ASM_APIC_H */
diff --git a/include/asm-x86/apicdef.h b/include/asm-x86/apicdef.h
new file mode 100644
index 000000000000..4542c220bf4d
--- /dev/null
+++ b/include/asm-x86/apicdef.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "apicdef_32.h"
+#else
+# include "apicdef_64.h"
+#endif
diff --git a/include/asm-x86/apicdef_32.h b/include/asm-x86/apicdef_32.h
new file mode 100644
index 000000000000..9f6995341fdc
--- /dev/null
+++ b/include/asm-x86/apicdef_32.h
@@ -0,0 +1,375 @@
+#ifndef __ASM_APICDEF_H
+#define __ASM_APICDEF_H
+
+/*
+ * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
+ *
+ * Alan Cox <Alan.Cox@linux.org>, 1995.
+ * Ingo Molnar <mingo@redhat.com>, 1999, 2000
+ */
+
+#define         APIC_DEFAULT_PHYS_BASE  0xfee00000
+ 
+#define         APIC_ID         0x20
+#define         APIC_LVR        0x30
+#define                 APIC_LVR_MASK           0xFF00FF
+#define                 GET_APIC_VERSION(x)     ((x)&0xFF)
+#define                 GET_APIC_MAXLVT(x)      (((x)>>16)&0xFF)
+#define                 APIC_INTEGRATED(x)      ((x)&0xF0)
+#define                 APIC_XAPIC(x)           ((x) >= 0x14)
+#define         APIC_TASKPRI    0x80
+#define                 APIC_TPRI_MASK          0xFF
+#define         APIC_ARBPRI     0x90
+#define                 APIC_ARBPRI_MASK        0xFF
+#define         APIC_PROCPRI    0xA0
+#define         APIC_EOI        0xB0
+#define                 APIC_EIO_ACK            0x0             /* Write this to the EOI register */
+#define         APIC_RRR        0xC0
+#define         APIC_LDR        0xD0
+#define                 APIC_LDR_MASK           (0xFF<<24)
+#define                 GET_APIC_LOGICAL_ID(x)  (((x)>>24)&0xFF)
+#define                 SET_APIC_LOGICAL_ID(x)  (((x)<<24))
+#define                 APIC_ALL_CPUS           0xFF
+#define         APIC_DFR        0xE0
+#define                 APIC_DFR_CLUSTER                0x0FFFFFFFul
+#define                 APIC_DFR_FLAT                   0xFFFFFFFFul
+#define         APIC_SPIV       0xF0
+#define                 APIC_SPIV_FOCUS_DISABLED        (1<<9)
+#define                 APIC_SPIV_APIC_ENABLED          (1<<8)
+#define         APIC_ISR        0x100
+#define         APIC_ISR_NR     0x8     /* Number of 32 bit ISR registers. */
+#define         APIC_TMR        0x180
+#define         APIC_IRR        0x200
+#define         APIC_ESR        0x280
+#define                 APIC_ESR_SEND_CS        0x00001
+#define                 APIC_ESR_RECV_CS        0x00002
+#define                 APIC_ESR_SEND_ACC       0x00004
+#define                 APIC_ESR_RECV_ACC       0x00008
+#define                 APIC_ESR_SENDILL        0x00020
+#define                 APIC_ESR_RECVILL        0x00040
+#define                 APIC_ESR_ILLREGA        0x00080
+#define         APIC_ICR        0x300
+#define                 APIC_DEST_SELF          0x40000
+#define                 APIC_DEST_ALLINC        0x80000
+#define                 APIC_DEST_ALLBUT        0xC0000
+#define                 APIC_ICR_RR_MASK        0x30000
+#define                 APIC_ICR_RR_INVALID     0x00000
+#define                 APIC_ICR_RR_INPROG      0x10000
+#define                 APIC_ICR_RR_VALID       0x20000
+#define                 APIC_INT_LEVELTRIG      0x08000
+#define                 APIC_INT_ASSERT         0x04000
+#define                 APIC_ICR_BUSY           0x01000
+#define                 APIC_DEST_LOGICAL       0x00800
+#define                 APIC_DM_FIXED           0x00000
+#define                 APIC_DM_LOWEST          0x00100
+#define                 APIC_DM_SMI             0x00200
+#define                 APIC_DM_REMRD           0x00300
+#define                 APIC_DM_NMI             0x00400
+#define                 APIC_DM_INIT            0x00500
+#define                 APIC_DM_STARTUP         0x00600
+#define                 APIC_DM_EXTINT          0x00700
+#define                 APIC_VECTOR_MASK        0x000FF
+#define         APIC_ICR2       0x310
+#define                 GET_APIC_DEST_FIELD(x)  (((x)>>24)&0xFF)
+#define                 SET_APIC_DEST_FIELD(x)  ((x)<<24)
+#define         APIC_LVTT       0x320
+#define         APIC_LVTTHMR    0x330
+#define         APIC_LVTPC      0x340
+#define         APIC_LVT0       0x350
+#define                 APIC_LVT_TIMER_BASE_MASK        (0x3<<18)
+#define                 GET_APIC_TIMER_BASE(x)          (((x)>>18)&0x3)
+#define                 SET_APIC_TIMER_BASE(x)          (((x)<<18))
+#define                 APIC_TIMER_BASE_CLKIN           0x0
+#define                 APIC_TIMER_BASE_TMBASE          0x1
+#define                 APIC_TIMER_BASE_DIV             0x2
+#define                 APIC_LVT_TIMER_PERIODIC         (1<<17)
+#define                 APIC_LVT_MASKED                 (1<<16)
+#define                 APIC_LVT_LEVEL_TRIGGER          (1<<15)
+#define                 APIC_LVT_REMOTE_IRR             (1<<14)
+#define                 APIC_INPUT_POLARITY             (1<<13)
+#define                 APIC_SEND_PENDING               (1<<12)
+#define                 APIC_MODE_MASK                  0x700
+#define                 GET_APIC_DELIVERY_MODE(x)       (((x)>>8)&0x7)
+#define                 SET_APIC_DELIVERY_MODE(x,y)     (((x)&~0x700)|((y)<<8))
+#define                         APIC_MODE_FIXED         0x0
+#define                         APIC_MODE_NMI           0x4
+#define                         APIC_MODE_EXTINT        0x7
+#define         APIC_LVT1       0x360
+#define         APIC_LVTERR     0x370
+#define         APIC_TMICT      0x380
+#define         APIC_TMCCT      0x390
+#define         APIC_TDCR       0x3E0
+#define                 APIC_TDR_DIV_TMBASE     (1<<2)
+#define                 APIC_TDR_DIV_1          0xB
+#define                 APIC_TDR_DIV_2          0x0
+#define                 APIC_TDR_DIV_4          0x1
+#define                 APIC_TDR_DIV_8          0x2
+#define                 APIC_TDR_DIV_16         0x3
+#define                 APIC_TDR_DIV_32         0x8
+#define                 APIC_TDR_DIV_64         0x9
+#define                 APIC_TDR_DIV_128        0xA
+
+#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
+
+#define MAX_IO_APICS 64
+
+/*
+ * the local APIC register structure, memory mapped. Not terribly well
+ * tested, but we might eventually use this one in the future - the
+ * problem why we cannot use it right now is the P5 APIC, it has an
+ * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
+ */
+#define u32 unsigned int
+
+
+struct local_apic {
+
+/*000*/ struct { u32 __reserved[4]; } __reserved_01;
+
+/*010*/ struct { u32 __reserved[4]; } __reserved_02;
+
+/*020*/ struct { /* APIC ID Register */
+                u32   __reserved_1      : 24,
+                        phys_apic_id    :  4,
+                        __reserved_2    :  4;
+                u32 __reserved[3];
+        } id;
+
+/*030*/ const
+        struct { /* APIC Version Register */
+                u32   version           :  8,
+                        __reserved_1    :  8,
+                        max_lvt         :  8,
+                        __reserved_2    :  8;
+                u32 __reserved[3];
+        } version;
+
+/*040*/ struct { u32 __reserved[4]; } __reserved_03;
+
+/*050*/ struct { u32 __reserved[4]; } __reserved_04;
+
+/*060*/ struct { u32 __reserved[4]; } __reserved_05;
+
+/*070*/ struct { u32 __reserved[4]; } __reserved_06;
+
+/*080*/ struct { /* Task Priority Register */
+                u32   priority  :  8,
+                        __reserved_1    : 24;
+                u32 __reserved_2[3];
+        } tpr;
+
+/*090*/ const
+        struct { /* Arbitration Priority Register */
+                u32   priority  :  8,
+                        __reserved_1    : 24;
+                u32 __reserved_2[3];
+        } apr;
+
+/*0A0*/ const
+        struct { /* Processor Priority Register */
+                u32   priority  :  8,
+                        __reserved_1    : 24;
+                u32 __reserved_2[3];
+        } ppr;
+
+/*0B0*/ struct { /* End Of Interrupt Register */
+                u32   eoi;
+                u32 __reserved[3];
+        } eoi;
+
+/*0C0*/ struct { u32 __reserved[4]; } __reserved_07;
+
+/*0D0*/ struct { /* Logical Destination Register */
+                u32   __reserved_1      : 24,
+                        logical_dest    :  8;
+                u32 __reserved_2[3];
+        } ldr;
+
+/*0E0*/ struct { /* Destination Format Register */
+                u32   __reserved_1      : 28,
+                        model           :  4;
+                u32 __reserved_2[3];
+        } dfr;
+
+/*0F0*/ struct { /* Spurious Interrupt Vector Register */
+                u32     spurious_vector :  8,
+                        apic_enabled    :  1,
+                        focus_cpu       :  1,
+                        __reserved_2    : 22;
+                u32 __reserved_3[3];
+        } svr;
+
+/*100*/ struct { /* In Service Register */
+/*170*/         u32 bitfield;
+                u32 __reserved[3];
+        } isr [8];
+
+/*180*/ struct { /* Trigger Mode Register */
+/*1F0*/         u32 bitfield;
+                u32 __reserved[3];
+        } tmr [8];
+
+/*200*/ struct { /* Interrupt Request Register */
+/*270*/         u32 bitfield;
+                u32 __reserved[3];
+        } irr [8];
+
+/*280*/ union { /* Error Status Register */
+                struct {
+                        u32   send_cs_error                     :  1,
+                                receive_cs_error                :  1,
+                                send_accept_error               :  1,
+                                receive_accept_error            :  1,
+                                __reserved_1                    :  1,
+                                send_illegal_vector             :  1,
+                                receive_illegal_vector          :  1,
+                                illegal_register_address        :  1,
+                                __reserved_2                    : 24;
+                        u32 __reserved_3[3];
+                } error_bits;
+                struct {
+                        u32 errors;
+                        u32 __reserved_3[3];
+                } all_errors;
+        } esr;
+
+/*290*/ struct { u32 __reserved[4]; } __reserved_08;
+
+/*2A0*/ struct { u32 __reserved[4]; } __reserved_09;
+
+/*2B0*/ struct { u32 __reserved[4]; } __reserved_10;
+
+/*2C0*/ struct { u32 __reserved[4]; } __reserved_11;
+
+/*2D0*/ struct { u32 __reserved[4]; } __reserved_12;
+
+/*2E0*/ struct { u32 __reserved[4]; } __reserved_13;
+
+/*2F0*/ struct { u32 __reserved[4]; } __reserved_14;
+
+/*300*/ struct { /* Interrupt Command Register 1 */
+                u32   vector                    :  8,
+                        delivery_mode           :  3,
+                        destination_mode        :  1,
+                        delivery_status         :  1,
+                        __reserved_1            :  1,
+                        level                   :  1,
+                        trigger                 :  1,
+                        __reserved_2            :  2,
+                        shorthand               :  2,
+                        __reserved_3            :  12;
+                u32 __reserved_4[3];
+        } icr1;
+
+/*310*/ struct { /* Interrupt Command Register 2 */
+                union {
+                        u32   __reserved_1      : 24,
+                                phys_dest       :  4,
+                                __reserved_2    :  4;
+                        u32   __reserved_3      : 24,
+                                logical_dest    :  8;
+                } dest;
+                u32 __reserved_4[3];
+        } icr2;
+
+/*320*/ struct { /* LVT - Timer */
+                u32   vector            :  8,
+                        __reserved_1    :  4,
+                        delivery_status :  1,
+                        __reserved_2    :  3,
+                        mask            :  1,
+                        timer_mode      :  1,
+                        __reserved_3    : 14;
+                u32 __reserved_4[3];
+        } lvt_timer;
+
+/*330*/ struct { /* LVT - Thermal Sensor */
+                u32  vector             :  8,
+                        delivery_mode   :  3,
+                        __reserved_1    :  1,
+                        delivery_status :  1,
+                        __reserved_2    :  3,
+                        mask            :  1,
+                        __reserved_3    : 15;
+                u32 __reserved_4[3];
+        } lvt_thermal;
+
+/*340*/ struct { /* LVT - Performance Counter */
+                u32   vector            :  8,
+                        delivery_mode   :  3,
+                        __reserved_1    :  1,
+                        delivery_status :  1,
+                        __reserved_2    :  3,
+                        mask            :  1,
+                        __reserved_3    : 15;
+                u32 __reserved_4[3];
+        } lvt_pc;
+
+/*350*/ struct { /* LVT - LINT0 */
+                u32   vector            :  8,
+                        delivery_mode   :  3,
+                        __reserved_1    :  1,
+                        delivery_status :  1,
+                        polarity        :  1,
+                        remote_irr      :  1,
+                        trigger         :  1,
+                        mask            :  1,
+                        __reserved_2    : 15;
+                u32 __reserved_3[3];
+        } lvt_lint0;
+
+/*360*/ struct { /* LVT - LINT1 */
+                u32   vector            :  8,
+                        delivery_mode   :  3,
+                        __reserved_1    :  1,
+                        delivery_status :  1,
+                        polarity        :  1,
+                        remote_irr      :  1,
+                        trigger         :  1,
+                        mask            :  1,
+                        __reserved_2    : 15;
+                u32 __reserved_3[3];
+        } lvt_lint1;
+
+/*370*/ struct { /* LVT - Error */
+                u32   vector            :  8,
+                        __reserved_1    :  4,
+                        delivery_status :  1,
+                        __reserved_2    :  3,
+                        mask            :  1,
+                        __reserved_3    : 15;
+                u32 __reserved_4[3];
+        } lvt_error;
+
+/*380*/ struct { /* Timer Initial Count Register */
+                u32   initial_count;
+                u32 __reserved_2[3];
+        } timer_icr;
+
+/*390*/ const
+        struct { /* Timer Current Count Register */
+                u32   curr_count;
+                u32 __reserved_2[3];
+        } timer_ccr;
+
+/*3A0*/ struct { u32 __reserved[4]; } __reserved_16;
+
+/*3B0*/ struct { u32 __reserved[4]; } __reserved_17;
+
+/*3C0*/ struct { u32 __reserved[4]; } __reserved_18;
+
+/*3D0*/ struct { u32 __reserved[4]; } __reserved_19;
+
+/*3E0*/ struct { /* Timer Divide Configuration Register */
+                u32   divisor           :  4,
+                        __reserved_1    : 28;
+                u32 __reserved_2[3];
+        } timer_dcr;
+
+/*3F0*/ struct { u32 __reserved[4]; } __reserved_20;
+
+} __attribute__ ((packed));
+
+#undef u32
+
+#endif
diff --git a/include/asm-x86/apicdef_64.h b/include/asm-x86/apicdef_64.h
new file mode 100644
index 000000000000..1dd40067c67c
--- /dev/null
+++ b/include/asm-x86/apicdef_64.h
@@ -0,0 +1,392 @@
+#ifndef __ASM_APICDEF_H
+#define __ASM_APICDEF_H
+
+/*
+ * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
+ *
+ * Alan Cox <Alan.Cox@linux.org>, 1995.
+ * Ingo Molnar <mingo@redhat.com>, 1999, 2000
+ */
+
+#define         APIC_DEFAULT_PHYS_BASE  0xfee00000
+ 
+#define         APIC_ID         0x20
+#define                 APIC_ID_MASK            (0xFFu<<24)
+#define                 GET_APIC_ID(x)          (((x)>>24)&0xFFu)
+#define                 SET_APIC_ID(x)          (((x)<<24))
+#define         APIC_LVR        0x30
+#define                 APIC_LVR_MASK           0xFF00FF
+#define                 GET_APIC_VERSION(x)     ((x)&0xFFu)
+#define                 GET_APIC_MAXLVT(x)      (((x)>>16)&0xFFu)
+#define                 APIC_INTEGRATED(x)      ((x)&0xF0u)
+#define         APIC_TASKPRI    0x80
+#define                 APIC_TPRI_MASK          0xFFu
+#define         APIC_ARBPRI     0x90
+#define                 APIC_ARBPRI_MASK        0xFFu
+#define         APIC_PROCPRI    0xA0
+#define         APIC_EOI        0xB0
+#define                 APIC_EIO_ACK            0x0             /* Write this to the EOI register */
+#define         APIC_RRR        0xC0
+#define         APIC_LDR        0xD0
+#define                 APIC_LDR_MASK           (0xFFu<<24)
+#define                 GET_APIC_LOGICAL_ID(x)  (((x)>>24)&0xFFu)
+#define                 SET_APIC_LOGICAL_ID(x)  (((x)<<24))
+#define                 APIC_ALL_CPUS           0xFFu
+#define         APIC_DFR        0xE0
+#define                 APIC_DFR_CLUSTER                0x0FFFFFFFul
+#define                 APIC_DFR_FLAT                   0xFFFFFFFFul
+#define         APIC_SPIV       0xF0
+#define                 APIC_SPIV_FOCUS_DISABLED        (1<<9)
+#define                 APIC_SPIV_APIC_ENABLED          (1<<8)
+#define         APIC_ISR        0x100
+#define         APIC_ISR_NR     0x8     /* Number of 32 bit ISR registers. */
+#define         APIC_TMR        0x180
+#define         APIC_IRR        0x200
+#define         APIC_ESR        0x280
+#define                 APIC_ESR_SEND_CS        0x00001
+#define                 APIC_ESR_RECV_CS        0x00002
+#define                 APIC_ESR_SEND_ACC       0x00004
+#define                 APIC_ESR_RECV_ACC       0x00008
+#define                 APIC_ESR_SENDILL        0x00020
+#define                 APIC_ESR_RECVILL        0x00040
+#define                 APIC_ESR_ILLREGA        0x00080
+#define         APIC_ICR        0x300
+#define                 APIC_DEST_SELF          0x40000
+#define                 APIC_DEST_ALLINC        0x80000
+#define                 APIC_DEST_ALLBUT        0xC0000
+#define                 APIC_ICR_RR_MASK        0x30000
+#define                 APIC_ICR_RR_INVALID     0x00000
+#define                 APIC_ICR_RR_INPROG      0x10000
+#define                 APIC_ICR_RR_VALID       0x20000
+#define                 APIC_INT_LEVELTRIG      0x08000
+#define                 APIC_INT_ASSERT         0x04000
+#define                 APIC_ICR_BUSY           0x01000
+#define                 APIC_DEST_LOGICAL       0x00800
+#define                 APIC_DEST_PHYSICAL      0x00000
+#define                 APIC_DM_FIXED           0x00000
+#define                 APIC_DM_LOWEST          0x00100
+#define                 APIC_DM_SMI             0x00200
+#define                 APIC_DM_REMRD           0x00300
+#define                 APIC_DM_NMI             0x00400
+#define                 APIC_DM_INIT            0x00500
+#define                 APIC_DM_STARTUP         0x00600
+#define                 APIC_DM_EXTINT          0x00700
+#define                 APIC_VECTOR_MASK        0x000FF
+#define         APIC_ICR2       0x310
+#define                 GET_APIC_DEST_FIELD(x)  (((x)>>24)&0xFF)
+#define                 SET_APIC_DEST_FIELD(x)  ((x)<<24)
+#define         APIC_LVTT       0x320
+#define         APIC_LVTTHMR    0x330
+#define         APIC_LVTPC      0x340
+#define         APIC_LVT0       0x350
+#define                 APIC_LVT_TIMER_BASE_MASK        (0x3<<18)
+#define                 GET_APIC_TIMER_BASE(x)          (((x)>>18)&0x3)
+#define                 SET_APIC_TIMER_BASE(x)          (((x)<<18))
+#define                 APIC_TIMER_BASE_CLKIN           0x0
+#define                 APIC_TIMER_BASE_TMBASE          0x1
+#define                 APIC_TIMER_BASE_DIV             0x2
+#define                 APIC_LVT_TIMER_PERIODIC         (1<<17)
+#define                 APIC_LVT_MASKED                 (1<<16)
+#define                 APIC_LVT_LEVEL_TRIGGER          (1<<15)
+#define                 APIC_LVT_REMOTE_IRR             (1<<14)
+#define                 APIC_INPUT_POLARITY             (1<<13)
+#define                 APIC_SEND_PENDING               (1<<12)
+#define                 APIC_MODE_MASK                  0x700
+#define                 GET_APIC_DELIVERY_MODE(x)       (((x)>>8)&0x7)
+#define                 SET_APIC_DELIVERY_MODE(x,y)     (((x)&~0x700)|((y)<<8))
+#define                         APIC_MODE_FIXED         0x0
+#define                         APIC_MODE_NMI           0x4
+#define                         APIC_MODE_EXTINT        0x7
+#define         APIC_LVT1       0x360
+#define         APIC_LVTERR     0x370
+#define         APIC_TMICT      0x380
+#define         APIC_TMCCT      0x390
+#define         APIC_TDCR       0x3E0
+#define                 APIC_TDR_DIV_TMBASE     (1<<2)
+#define                 APIC_TDR_DIV_1          0xB
+#define                 APIC_TDR_DIV_2          0x0
+#define                 APIC_TDR_DIV_4          0x1
+#define                 APIC_TDR_DIV_8          0x2
+#define                 APIC_TDR_DIV_16         0x3
+#define                 APIC_TDR_DIV_32         0x8
+#define                 APIC_TDR_DIV_64         0x9
+#define                 APIC_TDR_DIV_128        0xA
+
+#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
+
+#define MAX_IO_APICS 128
+#define MAX_LOCAL_APIC 256
+
+/*
+ * All x86-64 systems are xAPIC compatible.
+ * In the following, "apicid" is a physical APIC ID.
+ */
+#define XAPIC_DEST_CPUS_SHIFT   4
+#define XAPIC_DEST_CPUS_MASK    ((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
+#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
+#define APIC_CLUSTER(apicid)    ((apicid) & XAPIC_DEST_CLUSTER_MASK)
+#define APIC_CLUSTERID(apicid)  (APIC_CLUSTER(apicid) >> XAPIC_DEST_CPUS_SHIFT)
+#define APIC_CPUID(apicid)      ((apicid) & XAPIC_DEST_CPUS_MASK)
+#define NUM_APIC_CLUSTERS       ((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT)
+
+/*
+ * the local APIC register structure, memory mapped. Not terribly well
+ * tested, but we might eventually use this one in the future - the
+ * problem why we cannot use it right now is the P5 APIC, it has an
+ * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
+ */
+#define u32 unsigned int
+
+struct local_apic {
+
+/*000*/ struct { u32 __reserved[4]; } __reserved_01;
+
+/*010*/ struct { u32 __reserved[4]; } __reserved_02;
+
+/*020*/ struct { /* APIC ID Register */
+                u32   __reserved_1      : 24,
+                        phys_apic_id    :  4,
+                        __reserved_2    :  4;
+                u32 __reserved[3];
+        } id;
+
+/*030*/ const
+        struct { /* APIC Version Register */
+                u32   version           :  8,
+                        __reserved_1    :  8,
+                        max_lvt         :  8,
+                        __reserved_2    :  8;
+                u32 __reserved[3];
+        } version;
+
+/*040*/ struct { u32 __reserved[4]; } __reserved_03;
+
+/*050*/ struct { u32 __reserved[4]; } __reserved_04;
+
+/*060*/ struct { u32 __reserved[4]; } __reserved_05;
+
+/*070*/ struct { u32 __reserved[4]; } __reserved_06;
+
+/*080*/ struct { /* Task Priority Register */
+                u32   priority  :  8,
+                        __reserved_1    : 24;
+                u32 __reserved_2[3];
+        } tpr;
+
+/*090*/ const
+        struct { /* Arbitration Priority Register */
+                u32   priority  :  8,
+                        __reserved_1    : 24;
+                u32 __reserved_2[3];
+        } apr;
+
+/*0A0*/ const
+        struct { /* Processor Priority Register */
+                u32   priority  :  8,
+                        __reserved_1    : 24;
+                u32 __reserved_2[3];
+        } ppr;
+
+/*0B0*/ struct { /* End Of Interrupt Register */
+                u32   eoi;
+                u32 __reserved[3];
+        } eoi;
+
+/*0C0*/ struct { u32 __reserved[4]; } __reserved_07;
+
+/*0D0*/ struct { /* Logical Destination Register */
+                u32   __reserved_1      : 24,
+                        logical_dest    :  8;
+                u32 __reserved_2[3];
+        } ldr;
+
+/*0E0*/ struct { /* Destination Format Register */
+                u32   __reserved_1      : 28,
+                        model           :  4;
+                u32 __reserved_2[3];
+        } dfr;
+
+/*0F0*/ struct { /* Spurious Interrupt Vector Register */
+                u32     spurious_vector :  8,
+                        apic_enabled    :  1,
+                        focus_cpu       :  1,
+                        __reserved_2    : 22;
+                u32 __reserved_3[3];
+        } svr;
+
+/*100*/ struct { /* In Service Register */
+/*170*/         u32 bitfield;
+                u32 __reserved[3];
+        } isr [8];
+
+/*180*/ struct { /* Trigger Mode Register */
+/*1F0*/         u32 bitfield;
+                u32 __reserved[3];
+        } tmr [8];
+
+/*200*/ struct { /* Interrupt Request Register */
+/*270*/         u32 bitfield;
+                u32 __reserved[3];
+        } irr [8];
+
+/*280*/ union { /* Error Status Register */
+                struct {
+                        u32   send_cs_error                     :  1,
+                                receive_cs_error                :  1,
+                                send_accept_error               :  1,
+                                receive_accept_error            :  1,
+                                __reserved_1                    :  1,
+                                send_illegal_vector             :  1,
+                                receive_illegal_vector          :  1,
+                                illegal_register_address        :  1,
+                                __reserved_2                    : 24;
+                        u32 __reserved_3[3];
+                } error_bits;
+                struct {
+                        u32 errors;
+                        u32 __reserved_3[3];
+                } all_errors;
+        } esr;
+
+/*290*/ struct { u32 __reserved[4]; } __reserved_08;
+
+/*2A0*/ struct { u32 __reserved[4]; } __reserved_09;
+
+/*2B0*/ struct { u32 __reserved[4]; } __reserved_10;
+
+/*2C0*/ struct { u32 __reserved[4]; } __reserved_11;
+
+/*2D0*/ struct { u32 __reserved[4]; } __reserved_12;
+
+/*2E0*/ struct { u32 __reserved[4]; } __reserved_13;
+
+/*2F0*/ struct { u32 __reserved[4]; } __reserved_14;
+
+/*300*/ struct { /* Interrupt Command Register 1 */
+                u32   vector                    :  8,
+                        delivery_mode           :  3,
+                        destination_mode        :  1,
+                        delivery_status         :  1,
+                        __reserved_1            :  1,
+                        level                   :  1,
+                        trigger                 :  1,
+                        __reserved_2            :  2,
+                        shorthand               :  2,
+                        __reserved_3            :  12;
+                u32 __reserved_4[3];
+        } icr1;
+
+/*310*/ struct { /* Interrupt Command Register 2 */
+                union {
+                        u32   __reserved_1      : 24,
+                                phys_dest       :  4,
+                                __reserved_2    :  4;
+                        u32   __reserved_3      : 24,
+                                logical_dest    :  8;
+                } dest;
+                u32 __reserved_4[3];
+        } icr2;
+
+/*320*/ struct { /* LVT - Timer */
+                u32   vector            :  8,
+                        __reserved_1    :  4,
+                        delivery_status :  1,
+                        __reserved_2    :  3,
+                        mask            :  1,
+                        timer_mode      :  1,
+                        __reserved_3    : 14;
+                u32 __reserved_4[3];
+        } lvt_timer;
+
+/*330*/ struct { /* LVT - Thermal Sensor */
+                u32  vector             :  8,
+                        delivery_mode   :  3,
+                        __reserved_1    :  1,
+                        delivery_status :  1,
+                        __reserved_2    :  3,
+                        mask            :  1,
+                        __reserved_3    : 15;
+                u32 __reserved_4[3];
+        } lvt_thermal;
+
+/*340*/ struct { /* LVT - Performance Counter */
+                u32   vector            :  8,
+                        delivery_mode   :  3,
+                        __reserved_1    :  1,
+                        delivery_status :  1,
+                        __reserved_2    :  3,
+                        mask            :  1,
+                        __reserved_3    : 15;
+                u32 __reserved_4[3];
+        } lvt_pc;
+
+/*350*/ struct { /* LVT - LINT0 */
+                u32   vector            :  8,
+                        delivery_mode   :  3,
+                        __reserved_1    :  1,
+                        delivery_status :  1,
+                        polarity        :  1,
+                        remote_irr      :  1,
+                        trigger         :  1,
+                        mask            :  1,
+                        __reserved_2    : 15;
+                u32 __reserved_3[3];
+        } lvt_lint0;
+
+/*360*/ struct { /* LVT - LINT1 */
+                u32   vector            :  8,
+                        delivery_mode   :  3,
+                        __reserved_1    :  1,
+                        delivery_status :  1,
+                        polarity        :  1,
+                        remote_irr      :  1,
+                        trigger         :  1,
+                        mask            :  1,
+                        __reserved_2    : 15;
+                u32 __reserved_3[3];
+        } lvt_lint1;
+
+/*370*/ struct { /* LVT - Error */
+                u32   vector            :  8,
+                        __reserved_1    :  4,
+                        delivery_status :  1,
+                        __reserved_2    :  3,
+                        mask            :  1,
+                        __reserved_3    : 15;
+                u32 __reserved_4[3];
+        } lvt_error;
+
+/*380*/ struct { /* Timer Initial Count Register */
+                u32   initial_count;
+                u32 __reserved_2[3];
+        } timer_icr;
+
+/*390*/ const
+        struct { /* Timer Current Count Register */
+                u32   curr_count;
+                u32 __reserved_2[3];
+        } timer_ccr;
+
+/*3A0*/ struct { u32 __reserved[4]; } __reserved_16;
+
+/*3B0*/ struct { u32 __reserved[4]; } __reserved_17;
+
+/*3C0*/ struct { u32 __reserved[4]; } __reserved_18;
+
+/*3D0*/ struct { u32 __reserved[4]; } __reserved_19;
+
+/*3E0*/ struct { /* Timer Divide Configuration Register */
+                u32   divisor           :  4,
+                        __reserved_1    : 28;
+                u32 __reserved_2[3];
+        } timer_dcr;
+
+/*3F0*/ struct { u32 __reserved[4]; } __reserved_20;
+
+} __attribute__ ((packed));
+
+#undef u32
+
+#define BAD_APICID 0xFFu
+
+#endif
diff --git a/include/asm-x86/arch_hooks.h b/include/asm-x86/arch_hooks.h
new file mode 100644
index 000000000000..a8c1fca9726d
--- /dev/null
+++ b/include/asm-x86/arch_hooks.h
@@ -0,0 +1,30 @@
+#ifndef _ASM_ARCH_HOOKS_H
+#define _ASM_ARCH_HOOKS_H
+
+#include <linux/interrupt.h>
+
+/*
+ *      linux/include/asm/arch_hooks.h
+ *
+ *      define the architecture specific hooks 
+ */
+
+/* these aren't arch hooks, they are generic routines
+ * that can be used by the hooks */
+extern void init_ISA_irqs(void);
+extern void apic_intr_init(void);
+extern void smp_intr_init(void);
+extern irqreturn_t timer_interrupt(int irq, void *dev_id);
+
+/* these are the defined hooks */
+extern void intr_init_hook(void);
+extern void pre_intr_init_hook(void);
+extern void pre_setup_arch_hook(void);
+extern void trap_init_hook(void);
+extern void time_init_hook(void);
+extern void mca_nmi_hook(void);
+
+extern int setup_early_printk(char *);
+extern void early_printk(const char *fmt, ...) __attribute__((format(printf,1,2)));
+
+#endif
diff --git a/include/asm-x86/atomic.h b/include/asm-x86/atomic.h
new file mode 100644
index 000000000000..4e1b8873c474
--- /dev/null
+++ b/include/asm-x86/atomic.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "atomic_32.h"
+#else
+# include "atomic_64.h"
+#endif
diff --git a/include/asm-x86/atomic_32.h b/include/asm-x86/atomic_32.h
new file mode 100644
index 000000000000..437aac801711
--- /dev/null
+++ b/include/asm-x86/atomic_32.h
@@ -0,0 +1,266 @@
+#ifndef __ARCH_I386_ATOMIC__
+#define __ARCH_I386_ATOMIC__
+
+#include <linux/compiler.h>
+#include <asm/processor.h>
+#include <asm/cmpxchg.h>
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+/*
+ * 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,
+ * not some alias that contains the same information.
+ */
+typedef struct { int counter; } atomic_t;
+
+#define ATOMIC_INIT(i)  { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically reads the value of @v.
+ */ 
+#define atomic_read(v)          ((v)->counter)
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ * 
+ * Atomically sets the value of @v to @i.
+ */ 
+#define atomic_set(v,i)         (((v)->counter) = (i))
+
+/**
+ * atomic_add - add integer to atomic variable
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically adds @i to @v.
+ */
+static __inline__ void atomic_add(int i, atomic_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "addl %1,%0"
+                :"+m" (v->counter)
+                :"ir" (i));
+}
+
+/**
+ * atomic_sub - subtract integer from atomic variable
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically subtracts @i from @v.
+ */
+static __inline__ void atomic_sub(int i, atomic_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "subl %1,%0"
+                :"+m" (v->counter)
+                :"ir" (i));
+}
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int atomic_sub_and_test(int i, atomic_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "subl %2,%0; sete %1"
+                :"+m" (v->counter), "=qm" (c)
+                :"ir" (i) : "memory");
+        return c;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically increments @v by 1.
+ */ 
+static __inline__ void atomic_inc(atomic_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "incl %0"
+                :"+m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically decrements @v by 1.
+ */ 
+static __inline__ void atomic_dec(atomic_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "decl %0"
+                :"+m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */ 
+static __inline__ int atomic_dec_and_test(atomic_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "decl %0; sete %1"
+                :"+m" (v->counter), "=qm" (c)
+                : : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic_inc_and_test - increment and test 
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */ 
+static __inline__ int atomic_inc_and_test(atomic_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "incl %0; sete %1"
+                :"+m" (v->counter), "=qm" (c)
+                : : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @v: pointer of type atomic_t
+ * @i: integer value to add
+ * 
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */ 
+static __inline__ int atomic_add_negative(int i, atomic_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "addl %2,%0; sets %1"
+                :"+m" (v->counter), "=qm" (c)
+                :"ir" (i) : "memory");
+        return c;
+}
+
+/**
+ * atomic_add_return - add integer and return
+ * @v: pointer of type atomic_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static __inline__ int atomic_add_return(int i, atomic_t *v)
+{
+        int __i;
+#ifdef CONFIG_M386
+        unsigned long flags;
+        if(unlikely(boot_cpu_data.x86 <= 3))
+                goto no_xadd;
+#endif
+        /* Modern 486+ processor */
+        __i = i;
+        __asm__ __volatile__(
+                LOCK_PREFIX "xaddl %0, %1"
+                :"+r" (i), "+m" (v->counter)
+                : : "memory");
+        return i + __i;
+
+#ifdef CONFIG_M386
+no_xadd: /* Legacy 386 processor */
+        local_irq_save(flags);
+        __i = atomic_read(v);
+        atomic_set(v, i + __i);
+        local_irq_restore(flags);
+        return i + __i;
+#endif
+}
+
+/**
+ * atomic_sub_return - subtract integer and return
+ * @v: pointer of type atomic_t
+ * @i: integer value to subtract
+ *
+ * Atomically subtracts @i from @v and returns @v - @i
+ */
+static __inline__ int atomic_sub_return(int i, atomic_t *v)
+{
+        return atomic_add_return(-i,v);
+}
+
+#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
+#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+
+/**
+ * atomic_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as @v was not already @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
+{
+        int c, old;
+        c = atomic_read(v);
+        for (;;) {
+                if (unlikely(c == (u)))
+                        break;
+                old = atomic_cmpxchg((v), c, c + (a));
+                if (likely(old == c))
+                        break;
+                c = old;
+        }
+        return c != (u);
+}
+
+#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
+#define atomic_inc_return(v)  (atomic_add_return(1,v))
+#define atomic_dec_return(v)  (atomic_sub_return(1,v))
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr) \
+__asm__ __volatile__(LOCK_PREFIX "andl %0,%1" \
+: : "r" (~(mask)),"m" (*addr) : "memory")
+
+#define atomic_set_mask(mask, addr) \
+__asm__ __volatile__(LOCK_PREFIX "orl %0,%1" \
+: : "r" (mask),"m" (*(addr)) : "memory")
+
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic_dec()     barrier()
+#define smp_mb__after_atomic_dec()      barrier()
+#define smp_mb__before_atomic_inc()     barrier()
+#define smp_mb__after_atomic_inc()      barrier()
+
+#include <asm-generic/atomic.h>
+#endif
diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h
new file mode 100644
index 000000000000..f2e64634fa48
--- /dev/null
+++ b/include/asm-x86/atomic_64.h
@@ -0,0 +1,466 @@
+#ifndef __ARCH_X86_64_ATOMIC__
+#define __ARCH_X86_64_ATOMIC__
+
+#include <asm/alternative.h>
+#include <asm/cmpxchg.h>
+
+/* atomic_t should be 32 bit signed type */
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * 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,
+ * not some alias that contains the same information.
+ */
+typedef struct { int counter; } atomic_t;
+
+#define ATOMIC_INIT(i)  { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically reads the value of @v.
+ */ 
+#define atomic_read(v)          ((v)->counter)
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ * 
+ * Atomically sets the value of @v to @i.
+ */ 
+#define atomic_set(v,i)         (((v)->counter) = (i))
+
+/**
+ * atomic_add - add integer to atomic variable
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically adds @i to @v.
+ */
+static __inline__ void atomic_add(int i, atomic_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "addl %1,%0"
+                :"=m" (v->counter)
+                :"ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic_sub - subtract the atomic variable
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically subtracts @i from @v.
+ */
+static __inline__ void atomic_sub(int i, atomic_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "subl %1,%0"
+                :"=m" (v->counter)
+                :"ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int atomic_sub_and_test(int i, atomic_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "subl %2,%0; sete %1"
+                :"=m" (v->counter), "=qm" (c)
+                :"ir" (i), "m" (v->counter) : "memory");
+        return c;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically increments @v by 1.
+ */ 
+static __inline__ void atomic_inc(atomic_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "incl %0"
+                :"=m" (v->counter)
+                :"m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically decrements @v by 1.
+ */ 
+static __inline__ void atomic_dec(atomic_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "decl %0"
+                :"=m" (v->counter)
+                :"m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */ 
+static __inline__ int atomic_dec_and_test(atomic_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "decl %0; sete %1"
+                :"=m" (v->counter), "=qm" (c)
+                :"m" (v->counter) : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic_inc_and_test - increment and test 
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */ 
+static __inline__ int atomic_inc_and_test(atomic_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "incl %0; sete %1"
+                :"=m" (v->counter), "=qm" (c)
+                :"m" (v->counter) : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ * 
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */ 
+static __inline__ int atomic_add_negative(int i, atomic_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "addl %2,%0; sets %1"
+                :"=m" (v->counter), "=qm" (c)
+                :"ir" (i), "m" (v->counter) : "memory");
+        return c;
+}
+
+/**
+ * atomic_add_return - add and return
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static __inline__ int atomic_add_return(int i, atomic_t *v)
+{
+        int __i = i;
+        __asm__ __volatile__(
+                LOCK_PREFIX "xaddl %0, %1"
+                :"+r" (i), "+m" (v->counter)
+                : : "memory");
+        return i + __i;
+}
+
+static __inline__ int atomic_sub_return(int i, atomic_t *v)
+{
+        return atomic_add_return(-i,v);
+}
+
+#define atomic_inc_return(v)  (atomic_add_return(1,v))
+#define atomic_dec_return(v)  (atomic_sub_return(1,v))
+
+/* An 64bit atomic type */
+
+typedef struct { volatile long counter; } atomic64_t;
+
+#define ATOMIC64_INIT(i)        { (i) }
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically reads the value of @v.
+ * Doesn't imply a read memory barrier.
+ */
+#define atomic64_read(v)                ((v)->counter)
+
+/**
+ * atomic64_set - set atomic64 variable
+ * @v: pointer to type atomic64_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+#define atomic64_set(v,i)               (((v)->counter) = (i))
+
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v.
+ */
+static __inline__ void atomic64_add(long i, atomic64_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "addq %1,%0"
+                :"=m" (v->counter)
+                :"ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static __inline__ void atomic64_sub(long i, atomic64_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "subq %1,%0"
+                :"=m" (v->counter)
+                :"ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int atomic64_sub_and_test(long i, atomic64_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "subq %2,%0; sete %1"
+                :"=m" (v->counter), "=qm" (c)
+                :"ir" (i), "m" (v->counter) : "memory");
+        return c;
+}
+
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1.
+ */
+static __inline__ void atomic64_inc(atomic64_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "incq %0"
+                :"=m" (v->counter)
+                :"m" (v->counter));
+}
+
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static __inline__ void atomic64_dec(atomic64_t *v)
+{
+        __asm__ __volatile__(
+                LOCK_PREFIX "decq %0"
+                :"=m" (v->counter)
+                :"m" (v->counter));
+}
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static __inline__ int atomic64_dec_and_test(atomic64_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "decq %0; sete %1"
+                :"=m" (v->counter), "=qm" (c)
+                :"m" (v->counter) : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int atomic64_inc_and_test(atomic64_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "incq %0; sete %1"
+                :"=m" (v->counter), "=qm" (c)
+                :"m" (v->counter) : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static __inline__ int atomic64_add_negative(long i, atomic64_t *v)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                LOCK_PREFIX "addq %2,%0; sets %1"
+                :"=m" (v->counter), "=qm" (c)
+                :"ir" (i), "m" (v->counter) : "memory");
+        return c;
+}
+
+/**
+ * atomic64_add_return - add and return
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static __inline__ long atomic64_add_return(long i, atomic64_t *v)
+{
+        long __i = i;
+        __asm__ __volatile__(
+                LOCK_PREFIX "xaddq %0, %1;"
+                :"+r" (i), "+m" (v->counter)
+                : : "memory");
+        return i + __i;
+}
+
+static __inline__ long atomic64_sub_return(long i, atomic64_t *v)
+{
+        return atomic64_add_return(-i,v);
+}
+
+#define atomic64_inc_return(v)  (atomic64_add_return(1,v))
+#define atomic64_dec_return(v)  (atomic64_sub_return(1,v))
+
+#define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
+#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+
+#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+/**
+ * atomic_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
+{
+        int c, old;
+        c = atomic_read(v);
+        for (;;) {
+                if (unlikely(c == (u)))
+                        break;
+                old = atomic_cmpxchg((v), c, c + (a));
+                if (likely(old == c))
+                        break;
+                c = old;
+        }
+        return c != (u);
+}
+
+#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+        long c, old;
+        c = atomic64_read(v);
+        for (;;) {
+                if (unlikely(c == (u)))
+                        break;
+                old = atomic64_cmpxchg((v), c, c + (a));
+                if (likely(old == c))
+                        break;
+                c = old;
+        }
+        return c != (u);
+}
+
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr) \
+__asm__ __volatile__(LOCK_PREFIX "andl %0,%1" \
+: : "r" (~(mask)),"m" (*addr) : "memory")
+
+#define atomic_set_mask(mask, addr) \
+__asm__ __volatile__(LOCK_PREFIX "orl %0,%1" \
+: : "r" ((unsigned)mask),"m" (*(addr)) : "memory")
+
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic_dec()     barrier()
+#define smp_mb__after_atomic_dec()      barrier()
+#define smp_mb__before_atomic_inc()     barrier()
+#define smp_mb__after_atomic_inc()      barrier()
+
+#include <asm-generic/atomic.h>
+#endif
diff --git a/include/asm-x86/auxvec.h b/include/asm-x86/auxvec.h
new file mode 100644
index 000000000000..7ff866f829ca
--- /dev/null
+++ b/include/asm-x86/auxvec.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "auxvec_32.h"
+# else
+#  include "auxvec_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "auxvec_32.h"
+# else
+#  include "auxvec_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/auxvec_32.h b/include/asm-x86/auxvec_32.h
new file mode 100644
index 000000000000..395e13016bfb
--- /dev/null
+++ b/include/asm-x86/auxvec_32.h
@@ -0,0 +1,11 @@
+#ifndef __ASMi386_AUXVEC_H
+#define __ASMi386_AUXVEC_H
+
+/*
+ * Architecture-neutral AT_ values in 0-17, leave some room
+ * for more of them, start the x86-specific ones at 32.
+ */
+#define AT_SYSINFO              32
+#define AT_SYSINFO_EHDR         33
+
+#endif
diff --git a/include/asm-x86/auxvec_64.h b/include/asm-x86/auxvec_64.h
new file mode 100644
index 000000000000..1d5ab0d03950
--- /dev/null
+++ b/include/asm-x86/auxvec_64.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_X86_64_AUXVEC_H
+#define __ASM_X86_64_AUXVEC_H
+
+#define AT_SYSINFO_EHDR         33
+
+#endif
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
new file mode 100644
index 000000000000..07e3f6d4fe47
--- /dev/null
+++ b/include/asm-x86/bitops.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "bitops_32.h"
+#else
+# include "bitops_64.h"
+#endif
diff --git a/include/asm-x86/bitops_32.h b/include/asm-x86/bitops_32.h
new file mode 100644
index 000000000000..a20fe9822f60
--- /dev/null
+++ b/include/asm-x86/bitops_32.h
@@ -0,0 +1,423 @@
+#ifndef _I386_BITOPS_H
+#define _I386_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+#include <linux/compiler.h>
+#include <asm/alternative.h>
+
+/*
+ * These have to be done with inline assembly: that way the bit-setting
+ * is guaranteed to be atomic. All bit operations return 0 if the bit
+ * was cleared before the operation and != 0 if it was not.
+ *
+ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
+ */
+
+#define ADDR (*(volatile long *) addr)
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered.  See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * 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 unsigned long * addr)
+{
+        __asm__ __volatile__( LOCK_PREFIX
+                "btsl %1,%0"
+                :"+m" (ADDR)
+                :"Ir" (nr));
+}
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * 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 unsigned long * addr)
+{
+        __asm__(
+                "btsl %1,%0"
+                :"+m" (ADDR)
+                :"Ir" (nr));
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered.  However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * 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 unsigned long * addr)
+{
+        __asm__ __volatile__( LOCK_PREFIX
+                "btrl %1,%0"
+                :"+m" (ADDR)
+                :"Ir" (nr));
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long * addr)
+{
+        __asm__ __volatile__(
+                "btrl %1,%0"
+                :"+m" (ADDR)
+                :"Ir" (nr));
+}
+#define smp_mb__before_clear_bit()      barrier()
+#define smp_mb__after_clear_bit()       barrier()
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * 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 unsigned long * addr)
+{
+        __asm__ __volatile__(
+                "btcl %1,%0"
+                :"+m" (ADDR)
+                :"Ir" (nr));
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered. It may be
+ * reordered on other architectures than x86.
+ * 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 unsigned long * addr)
+{
+        __asm__ __volatile__( LOCK_PREFIX
+                "btcl %1,%0"
+                :"+m" (ADDR)
+                :"Ir" (nr));
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.  
+ * It may be reordered on other architectures than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long * addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__( LOCK_PREFIX
+                "btsl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),"+m" (ADDR)
+                :"Ir" (nr) : "memory");
+        return oldbit;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.  
+ * 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 unsigned long * addr)
+{
+        int oldbit;
+
+        __asm__(
+                "btsl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),"+m" (ADDR)
+                :"Ir" (nr));
+        return oldbit;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It can be reorderdered on other architectures other than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long * addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__( LOCK_PREFIX
+                "btrl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),"+m" (ADDR)
+                :"Ir" (nr) : "memory");
+        return oldbit;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.  
+ * 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 unsigned long *addr)
+{
+        int oldbit;
+
+        __asm__(
+                "btrl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),"+m" (ADDR)
+                :"Ir" (nr));
+        return oldbit;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__(
+                "btcl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),"+m" (ADDR)
+                :"Ir" (nr) : "memory");
+        return oldbit;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.  
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long* addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__( LOCK_PREFIX
+                "btcl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),"+m" (ADDR)
+                :"Ir" (nr) : "memory");
+        return oldbit;
+}
+
+#if 0 /* Fool kernel-doc since it doesn't do macros yet */
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static int test_bit(int nr, const volatile void * addr);
+#endif
+
+static __always_inline int constant_test_bit(int nr, const volatile unsigned long *addr)
+{
+        return ((1UL << (nr & 31)) & (addr[nr >> 5])) != 0;
+}
+
+static inline int variable_test_bit(int nr, const volatile unsigned long * addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__(
+                "btl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit)
+                :"m" (ADDR),"Ir" (nr));
+        return oldbit;
+}
+
+#define test_bit(nr,addr) \
+(__builtin_constant_p(nr) ? \
+ constant_test_bit((nr),(addr)) : \
+ variable_test_bit((nr),(addr)))
+
+#undef ADDR
+
+/**
+ * find_first_zero_bit - find the first zero bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit-number of the first zero bit, not the number of the byte
+ * containing a bit.
+ */
+static inline int find_first_zero_bit(const unsigned long *addr, unsigned size)
+{
+        int d0, d1, d2;
+        int res;
+
+        if (!size)
+                return 0;
+        /* This looks at memory. Mark it volatile to tell gcc not to move it around */
+        __asm__ __volatile__(
+                "movl $-1,%%eax\n\t"
+                "xorl %%edx,%%edx\n\t"
+                "repe; scasl\n\t"
+                "je 1f\n\t"
+                "xorl -4(%%edi),%%eax\n\t"
+                "subl $4,%%edi\n\t"
+                "bsfl %%eax,%%edx\n"
+                "1:\tsubl %%ebx,%%edi\n\t"
+                "shll $3,%%edi\n\t"
+                "addl %%edi,%%edx"
+                :"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2)
+                :"1" ((size + 31) >> 5), "2" (addr), "b" (addr) : "memory");
+        return res;
+}
+
+/**
+ * find_next_zero_bit - find the first zero bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+int find_next_zero_bit(const unsigned long *addr, int size, int offset);
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __ffs(unsigned long word)
+{
+        __asm__("bsfl %1,%0"
+                :"=r" (word)
+                :"rm" (word));
+        return word;
+}
+
+/**
+ * find_first_bit - find the first set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit-number of the first set bit, not the number of the byte
+ * containing a bit.
+ */
+static inline unsigned find_first_bit(const unsigned long *addr, unsigned size)
+{
+        unsigned x = 0;
+
+        while (x < size) {
+                unsigned long val = *addr++;
+                if (val)
+                        return __ffs(val) + x;
+                x += (sizeof(*addr)<<3);
+        }
+        return x;
+}
+
+/**
+ * find_next_bit - find the first set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+int find_next_bit(const unsigned long *addr, int size, int offset);
+
+/**
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static inline unsigned long ffz(unsigned long word)
+{
+        __asm__("bsfl %1,%0"
+                :"=r" (word)
+                :"r" (~word));
+        return word;
+}
+
+#ifdef __KERNEL__
+
+#include <asm-generic/bitops/sched.h>
+
+/**
+ * ffs - find first bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as
+ * the libc and compiler builtin ffs routines, therefore
+ * differs in spirit from the above ffz() (man ffs).
+ */
+static inline int ffs(int x)
+{
+        int r;
+
+        __asm__("bsfl %1,%0\n\t"
+                "jnz 1f\n\t"
+                "movl $-1,%0\n"
+                "1:" : "=r" (r) : "rm" (x));
+        return r+1;
+}
+
+/**
+ * fls - find last bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs().
+ */
+static inline int fls(int x)
+{
+        int r;
+
+        __asm__("bsrl %1,%0\n\t"
+                "jnz 1f\n\t"
+                "movl $-1,%0\n"
+                "1:" : "=r" (r) : "rm" (x));
+        return r+1;
+}
+
+#include <asm-generic/bitops/hweight.h>
+
+#endif /* __KERNEL__ */
+
+#include <asm-generic/bitops/fls64.h>
+
+#ifdef __KERNEL__
+
+#include <asm-generic/bitops/ext2-non-atomic.h>
+
+#define ext2_set_bit_atomic(lock,nr,addr) \
+        test_and_set_bit((nr),(unsigned long*)addr)
+#define ext2_clear_bit_atomic(lock,nr, addr) \
+                test_and_clear_bit((nr),(unsigned long*)addr)
+
+#include <asm-generic/bitops/minix.h>
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_BITOPS_H */
diff --git a/include/asm-x86/bitops_64.h b/include/asm-x86/bitops_64.h
new file mode 100644
index 000000000000..d4dbbe5f7bd9
--- /dev/null
+++ b/include/asm-x86/bitops_64.h
@@ -0,0 +1,427 @@
+#ifndef _X86_64_BITOPS_H
+#define _X86_64_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+#include <asm/alternative.h>
+
+#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)
+#else
+#define ADDR "+m" (*(volatile long *) addr)
+#endif
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered.  See __set_bit()
+ * if you do not require the atomic guarantees.
+ * 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)
+{
+        __asm__ __volatile__( LOCK_PREFIX
+                "btsl %1,%0"
+                :ADDR
+                :"dIr" (nr) : "memory");
+}
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * 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)
+{
+        __asm__ volatile(
+                "btsl %1,%0"
+                :ADDR
+                :"dIr" (nr) : "memory");
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered.  However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * 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)
+{
+        __asm__ __volatile__( LOCK_PREFIX
+                "btrl %1,%0"
+                :ADDR
+                :"dIr" (nr));
+}
+
+static __inline__ void __clear_bit(int nr, volatile void * addr)
+{
+        __asm__ __volatile__(
+                "btrl %1,%0"
+                :ADDR
+                :"dIr" (nr));
+}
+
+#define smp_mb__before_clear_bit()      barrier()
+#define smp_mb__after_clear_bit()       barrier()
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * 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)
+{
+        __asm__ __volatile__(
+                "btcl %1,%0"
+                :ADDR
+                :"dIr" (nr));
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered.
+ * 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)
+{
+        __asm__ __volatile__( LOCK_PREFIX
+                "btcl %1,%0"
+                :ADDR
+                :"dIr" (nr));
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * 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)
+{
+        int oldbit;
+
+        __asm__ __volatile__( LOCK_PREFIX
+                "btsl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),ADDR
+                :"dIr" (nr) : "memory");
+        return oldbit;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.  
+ * 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)
+{
+        int oldbit;
+
+        __asm__(
+                "btsl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),ADDR
+                :"dIr" (nr));
+        return oldbit;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * 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)
+{
+        int oldbit;
+
+        __asm__ __volatile__( LOCK_PREFIX
+                "btrl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),ADDR
+                :"dIr" (nr) : "memory");
+        return oldbit;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.  
+ * 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)
+{
+        int oldbit;
+
+        __asm__(
+                "btrl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),ADDR
+                :"dIr" (nr));
+        return oldbit;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static __inline__ int __test_and_change_bit(int nr, volatile void * addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__(
+                "btcl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),ADDR
+                :"dIr" (nr) : "memory");
+        return oldbit;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * 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)
+{
+        int oldbit;
+
+        __asm__ __volatile__( LOCK_PREFIX
+                "btcl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit),ADDR
+                :"dIr" (nr) : "memory");
+        return oldbit;
+}
+
+#if 0 /* Fool kernel-doc since it doesn't do macros yet */
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static int test_bit(int nr, const volatile void * addr);
+#endif
+
+static __inline__ int constant_test_bit(int nr, const volatile void * addr)
+{
+        return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
+}
+
+static __inline__ int variable_test_bit(int nr, volatile const void * addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__(
+                "btl %2,%1\n\tsbbl %0,%0"
+                :"=r" (oldbit)
+                :"m" (*(volatile long *)addr),"dIr" (nr));
+        return oldbit;
+}
+
+#define test_bit(nr,addr) \
+(__builtin_constant_p(nr) ? \
+ constant_test_bit((nr),(addr)) : \
+ variable_test_bit((nr),(addr)))
+
+#undef ADDR
+
+extern long find_first_zero_bit(const unsigned long * addr, unsigned long size);
+extern long find_next_zero_bit (const unsigned long * addr, long size, long offset);
+extern long find_first_bit(const unsigned long * addr, unsigned long size);
+extern long find_next_bit(const unsigned long * addr, long size, long offset);
+
+/* return index of first bet set in val or max when no bit is set */
+static inline unsigned long __scanbit(unsigned long val, unsigned long max)
+{
+        asm("bsfq %1,%0 ; cmovz %2,%0" : "=&r" (val) : "r" (val), "r" (max));
+        return val;
+}
+
+#define find_first_bit(addr,size) \
+((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? \
+  (__scanbit(*(unsigned long *)addr,(size))) : \
+  find_first_bit(addr,size)))
+
+#define find_next_bit(addr,size,off) \
+((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ?         \
+  ((off) + (__scanbit((*(unsigned long *)addr) >> (off),(size)-(off)))) : \
+        find_next_bit(addr,size,off)))
+
+#define find_first_zero_bit(addr,size) \
+((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? \
+  (__scanbit(~*(unsigned long *)addr,(size))) : \
+        find_first_zero_bit(addr,size)))
+        
+#define find_next_zero_bit(addr,size,off) \
+((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ?         \
+  ((off)+(__scanbit(~(((*(unsigned long *)addr)) >> (off)),(size)-(off)))) : \
+        find_next_zero_bit(addr,size,off)))
+
+/* 
+ * Find string of zero bits in a bitmap. -1 when not found.
+ */ 
+extern unsigned long 
+find_next_zero_string(unsigned long *bitmap, long start, long nbits, int len);
+
+static inline void set_bit_string(unsigned long *bitmap, unsigned long i, 
+                                  int len) 
+{ 
+        unsigned long end = i + len; 
+        while (i < end) {
+                __set_bit(i, bitmap); 
+                i++;
+        }
+} 
+
+static inline void __clear_bit_string(unsigned long *bitmap, unsigned long i, 
+                                    int len) 
+{ 
+        unsigned long end = i + len; 
+        while (i < end) {
+                __clear_bit(i, bitmap); 
+                i++;
+        }
+} 
+
+/**
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static __inline__ unsigned long ffz(unsigned long word)
+{
+        __asm__("bsfq %1,%0"
+                :"=r" (word)
+                :"r" (~word));
+        return word;
+}
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __inline__ unsigned long __ffs(unsigned long word)
+{
+        __asm__("bsfq %1,%0"
+                :"=r" (word)
+                :"rm" (word));
+        return word;
+}
+
+/*
+ * __fls: find last bit set.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static __inline__ unsigned long __fls(unsigned long word)
+{
+        __asm__("bsrq %1,%0"
+                :"=r" (word)
+                :"rm" (word));
+        return word;
+}
+
+#ifdef __KERNEL__
+
+#include <asm-generic/bitops/sched.h>
+
+/**
+ * ffs - find first bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as
+ * the libc and compiler builtin ffs routines, therefore
+ * differs in spirit from the above ffz (man ffs).
+ */
+static __inline__ int ffs(int x)
+{
+        int r;
+
+        __asm__("bsfl %1,%0\n\t"
+                "cmovzl %2,%0" 
+                : "=r" (r) : "rm" (x), "r" (-1));
+        return r+1;
+}
+
+/**
+ * fls64 - find last bit set in 64 bit word
+ * @x: the word to search
+ *
+ * This is defined the same way as fls.
+ */
+static __inline__ int fls64(__u64 x)
+{
+        if (x == 0)
+                return 0;
+        return __fls(x) + 1;
+}
+
+/**
+ * fls - find last bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ */
+static __inline__ int fls(int x)
+{
+        int r;
+
+        __asm__("bsrl %1,%0\n\t"
+                "cmovzl %2,%0"
+                : "=&r" (r) : "rm" (x), "rm" (-1));
+        return r+1;
+}
+
+#define ARCH_HAS_FAST_MULTIPLIER 1
+
+#include <asm-generic/bitops/hweight.h>
+
+#endif /* __KERNEL__ */
+
+#ifdef __KERNEL__
+
+#include <asm-generic/bitops/ext2-non-atomic.h>
+
+#define ext2_set_bit_atomic(lock,nr,addr) \
+                test_and_set_bit((nr),(unsigned long*)addr)
+#define ext2_clear_bit_atomic(lock,nr,addr) \
+                test_and_clear_bit((nr),(unsigned long*)addr)
+
+#include <asm-generic/bitops/minix.h>
+
+#endif /* __KERNEL__ */
+
+#endif /* _X86_64_BITOPS_H */
diff --git a/include/asm-x86/boot.h b/include/asm-x86/boot.h
new file mode 100644
index 000000000000..ed8affbf96cb
--- /dev/null
+++ b/include/asm-x86/boot.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_BOOT_H
+#define _ASM_BOOT_H
+
+/* Don't touch these, unless you really know what you're doing. */
+#define DEF_INITSEG     0x9000
+#define DEF_SYSSEG      0x1000
+#define DEF_SETUPSEG    0x9020
+#define DEF_SYSSIZE     0x7F00
+
+/* Internal svga startup constants */
+#define NORMAL_VGA      0xffff          /* 80x25 mode */
+#define EXTENDED_VGA    0xfffe          /* 80x50 mode */
+#define ASK_VGA         0xfffd          /* ask for it at bootup */
+
+/* Physical address where kernel should be loaded. */
+#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
+                                + (CONFIG_PHYSICAL_ALIGN - 1)) \
+                                & ~(CONFIG_PHYSICAL_ALIGN - 1))
+
+#endif /* _ASM_BOOT_H */
diff --git a/include/asm-x86/bootparam.h b/include/asm-x86/bootparam.h
new file mode 100644
index 000000000000..b91b01783e4b
--- /dev/null
+++ b/include/asm-x86/bootparam.h
@@ -0,0 +1,86 @@
+#ifndef _ASM_BOOTPARAM_H
+#define _ASM_BOOTPARAM_H
+
+#include <linux/types.h>
+#include <linux/screen_info.h>
+#include <linux/apm_bios.h>
+#include <linux/edd.h>
+#include <asm/e820.h>
+#include <asm/ist.h>
+#include <video/edid.h>
+
+struct setup_header {
+        u8      setup_sects;
+        u16     root_flags;
+        u32     syssize;
+        u16     ram_size;
+        u16     vid_mode;
+        u16     root_dev;
+        u16     boot_flag;
+        u16     jump;
+        u32     header;
+        u16     version;
+        u32     realmode_swtch;
+        u16     start_sys;
+        u16     kernel_version;
+        u8      type_of_loader;
+        u8      loadflags;
+#define LOADED_HIGH     0x01
+#define CAN_USE_HEAP    0x80
+        u16     setup_move_size;
+        u32     code32_start;
+        u32     ramdisk_image;
+        u32     ramdisk_size;
+        u32     bootsect_kludge;
+        u16     heap_end_ptr;
+        u16     _pad1;
+        u32     cmd_line_ptr;
+        u32     initrd_addr_max;
+        u32     kernel_alignment;
+        u8      relocatable_kernel;
+} __attribute__((packed));
+
+struct sys_desc_table {
+        u16 length;
+        u8  table[14];
+};
+
+struct efi_info {
+        u32 _pad1;
+        u32 efi_systab;
+        u32 efi_memdesc_size;
+        u32 efi_memdesc_version;
+        u32 efi_memmap;
+        u32 efi_memmap_size;
+        u32 _pad2[2];
+};
+
+/* The so-called "zeropage" */
+struct boot_params {
+        struct screen_info screen_info;                 /* 0x000 */
+        struct apm_bios_info apm_bios_info;             /* 0x040 */
+        u8  _pad2[12];                                  /* 0x054 */
+        struct ist_info ist_info;                       /* 0x060 */
+        u8  _pad3[16];                                  /* 0x070 */
+        u8  hd0_info[16];       /* obsolete! */         /* 0x080 */
+        u8  hd1_info[16];       /* obsolete! */         /* 0x090 */
+        struct sys_desc_table sys_desc_table;           /* 0x0a0 */
+        u8  _pad4[144];                                 /* 0x0b0 */
+        struct edid_info edid_info;                     /* 0x140 */
+        struct efi_info efi_info;                       /* 0x1c0 */
+        u32 alt_mem_k;                                  /* 0x1e0 */
+        u32 scratch;            /* Scratch field! */    /* 0x1e4 */
+        u8  e820_entries;                               /* 0x1e8 */
+        u8  eddbuf_entries;                             /* 0x1e9 */
+        u8  edd_mbr_sig_buf_entries;                    /* 0x1ea */
+        u8  _pad6[6];                                   /* 0x1eb */
+        struct setup_header hdr;    /* setup header */  /* 0x1f1 */
+        u8  _pad7[0x290-0x1f1-sizeof(struct setup_header)];
+        u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX];        /* 0x290 */
+        struct e820entry e820_map[E820MAX];             /* 0x2d0 */
+        u8  _pad8[48];                                  /* 0xcd0 */
+        struct edd_info eddbuf[EDDMAXNR];               /* 0xd00 */
+        u8  _pad9[276];                                 /* 0xeec */
+} __attribute__((packed));
+
+#endif /* _ASM_BOOTPARAM_H */
diff --git a/include/asm-x86/bootsetup.h b/include/asm-x86/bootsetup.h
new file mode 100644
index 000000000000..7b1c3ad155fd
--- /dev/null
+++ b/include/asm-x86/bootsetup.h
@@ -0,0 +1,40 @@
+
+#ifndef _X86_64_BOOTSETUP_H
+#define _X86_64_BOOTSETUP_H 1
+
+#define BOOT_PARAM_SIZE         4096
+extern char x86_boot_params[BOOT_PARAM_SIZE];
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+#define PARAM   ((unsigned char *)x86_boot_params)
+#define SCREEN_INFO (*(struct screen_info *) (PARAM+0))
+#define EXT_MEM_K (*(unsigned short *) (PARAM+2))
+#define ALT_MEM_K (*(unsigned int *) (PARAM+0x1e0))
+#define E820_MAP_NR (*(char*) (PARAM+E820NR))
+#define E820_MAP    ((struct e820entry *) (PARAM+E820MAP))
+#define APM_BIOS_INFO (*(struct apm_bios_info *) (PARAM+0x40))
+#define DRIVE_INFO (*(struct drive_info_struct *) (PARAM+0x80))
+#define SYS_DESC_TABLE (*(struct sys_desc_table_struct*)(PARAM+0xa0))
+#define MOUNT_ROOT_RDONLY (*(unsigned short *) (PARAM+0x1F2))
+#define RAMDISK_FLAGS (*(unsigned short *) (PARAM+0x1F8))
+#define SAVED_VIDEO_MODE (*(unsigned short *) (PARAM+0x1FA))
+#define ORIG_ROOT_DEV (*(unsigned short *) (PARAM+0x1FC))
+#define AUX_DEVICE_INFO (*(unsigned char *) (PARAM+0x1FF))
+#define LOADER_TYPE (*(unsigned char *) (PARAM+0x210))
+#define KERNEL_START (*(unsigned int *) (PARAM+0x214))
+#define INITRD_START (*(unsigned int *) (PARAM+0x218))
+#define INITRD_SIZE (*(unsigned int *) (PARAM+0x21c))
+#define EDID_INFO (*(struct edid_info *) (PARAM+0x140))
+#define EDD_NR     (*(unsigned char *) (PARAM+EDDNR))
+#define EDD_MBR_SIG_NR (*(unsigned char *) (PARAM+EDD_MBR_SIG_NR_BUF))
+#define EDD_MBR_SIGNATURE ((unsigned int *) (PARAM+EDD_MBR_SIG_BUF))
+#define EDD_BUF     ((struct edd_info *) (PARAM+EDDBUF))
+#define COMMAND_LINE boot_command_line
+
+#define RAMDISK_IMAGE_START_MASK        0x07FF
+#define RAMDISK_PROMPT_FLAG             0x8000
+#define RAMDISK_LOAD_FLAG               0x4000  
+
+#endif
diff --git a/include/asm-x86/bug.h b/include/asm-x86/bug.h
new file mode 100644
index 000000000000..c655d7f3a5e0
--- /dev/null
+++ b/include/asm-x86/bug.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "bug_32.h"
+#else
+# include "bug_64.h"
+#endif
diff --git a/include/asm-x86/bug_32.h b/include/asm-x86/bug_32.h
new file mode 100644
index 000000000000..b0fd78ca2619
--- /dev/null
+++ b/include/asm-x86/bug_32.h
@@ -0,0 +1,37 @@
+#ifndef _I386_BUG_H
+#define _I386_BUG_H
+
+
+/*
+ * Tell the user there is some problem.
+ * The offending file and line are encoded encoded in the __bug_table section.
+ */
+
+#ifdef CONFIG_BUG
+#define HAVE_ARCH_BUG
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define BUG()                                                           \
+        do {                                                            \
+                asm volatile("1:\tud2\n"                                \
+                             ".pushsection __bug_table,\"a\"\n"         \
+                             "2:\t.long 1b, %c0\n"                      \
+                             "\t.word %c1, 0\n"                         \
+                             "\t.org 2b+%c2\n"                          \
+                             ".popsection"                              \
+                             : : "i" (__FILE__), "i" (__LINE__),        \
+                             "i" (sizeof(struct bug_entry)));           \
+                for(;;) ;                                               \
+        } while(0)
+
+#else
+#define BUG()                                                           \
+        do {                                                            \
+                asm volatile("ud2");                                    \
+                for(;;) ;                                               \
+        } while(0)
+#endif
+#endif
+
+#include <asm-generic/bug.h>
+#endif
diff --git a/include/asm-x86/bug_64.h b/include/asm-x86/bug_64.h
new file mode 100644
index 000000000000..682606414913
--- /dev/null
+++ b/include/asm-x86/bug_64.h
@@ -0,0 +1,34 @@
+#ifndef __ASM_X8664_BUG_H
+#define __ASM_X8664_BUG_H 1
+
+#ifdef CONFIG_BUG
+#define HAVE_ARCH_BUG
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define BUG()                                                           \
+        do {                                                            \
+                asm volatile("1:\tud2\n"                                \
+                             ".pushsection __bug_table,\"a\"\n"         \
+                             "2:\t.quad 1b, %c0\n"                      \
+                             "\t.word %c1, 0\n"                         \
+                             "\t.org 2b+%c2\n"                          \
+                             ".popsection"                              \
+                             : : "i" (__FILE__), "i" (__LINE__),        \
+                                "i" (sizeof(struct bug_entry)));        \
+                for(;;) ;                                               \
+        } while(0)
+#else
+#define BUG()                                                           \
+        do {                                                            \
+                asm volatile("ud2");                                    \
+                for(;;) ;                                               \
+        } while(0)
+#endif
+
+void out_of_line_bug(void);
+#else
+static inline void out_of_line_bug(void) { }
+#endif
+
+#include <asm-generic/bug.h>
+#endif
diff --git a/include/asm-x86/bugs.h b/include/asm-x86/bugs.h
new file mode 100644
index 000000000000..ddf42d36dd50
--- /dev/null
+++ b/include/asm-x86/bugs.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "bugs_32.h"
+#else
+# include "bugs_64.h"
+#endif
diff --git a/include/asm-x86/bugs_32.h b/include/asm-x86/bugs_32.h
new file mode 100644
index 000000000000..d28979ff73be
--- /dev/null
+++ b/include/asm-x86/bugs_32.h
@@ -0,0 +1,12 @@
+/*
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Needs:
+ *      void check_bugs(void);
+ */
+#ifndef _ASM_I386_BUG_H
+#define _ASM_I386_BUG_H
+
+void check_bugs(void);
+
+#endif  /* _ASM_I386_BUG_H */
diff --git a/include/asm-x86/bugs_64.h b/include/asm-x86/bugs_64.h
new file mode 100644
index 000000000000..b33dc04d8f42
--- /dev/null
+++ b/include/asm-x86/bugs_64.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_X86_64_BUGS_H
+#define _ASM_X86_64_BUGS_H
+
+void check_bugs(void);
+
+#endif  /* _ASM_X86_64_BUGS_H */
diff --git a/include/asm-x86/byteorder.h b/include/asm-x86/byteorder.h
new file mode 100644
index 000000000000..eb14b1870ed7
--- /dev/null
+++ b/include/asm-x86/byteorder.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "byteorder_32.h"
+# else
+#  include "byteorder_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "byteorder_32.h"
+# else
+#  include "byteorder_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/byteorder_32.h b/include/asm-x86/byteorder_32.h
new file mode 100644
index 000000000000..a45470a8b74a
--- /dev/null
+++ b/include/asm-x86/byteorder_32.h
@@ -0,0 +1,58 @@
+#ifndef _I386_BYTEORDER_H
+#define _I386_BYTEORDER_H
+
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+#ifdef __GNUC__
+
+/* For avoiding bswap on i386 */
+#ifdef __KERNEL__
+#endif
+
+static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 x)
+{
+#ifdef CONFIG_X86_BSWAP
+        __asm__("bswap %0" : "=r" (x) : "0" (x));
+#else
+        __asm__("xchgb %b0,%h0\n\t"     /* swap lower bytes     */
+                "rorl $16,%0\n\t"       /* swap words           */
+                "xchgb %b0,%h0"         /* swap higher bytes    */
+                :"=q" (x)
+                : "0" (x));
+#endif
+        return x;
+}
+
+static __inline__ __attribute_const__ __u64 ___arch__swab64(__u64 val)
+{ 
+        union { 
+                struct { __u32 a,b; } s;
+                __u64 u;
+        } v;
+        v.u = val;
+#ifdef CONFIG_X86_BSWAP
+        asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1" 
+            : "=r" (v.s.a), "=r" (v.s.b) 
+            : "0" (v.s.a), "1" (v.s.b)); 
+#else
+   v.s.a = ___arch__swab32(v.s.a); 
+        v.s.b = ___arch__swab32(v.s.b); 
+        asm("xchgl %0,%1" : "=r" (v.s.a), "=r" (v.s.b) : "0" (v.s.a), "1" (v.s.b));
+#endif
+        return v.u;     
+} 
+
+/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
+   convert it into rotation or exhange.  */
+
+#define __arch__swab64(x) ___arch__swab64(x)
+#define __arch__swab32(x) ___arch__swab32(x)
+
+#define __BYTEORDER_HAS_U64__
+
+#endif /* __GNUC__ */
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* _I386_BYTEORDER_H */
diff --git a/include/asm-x86/byteorder_64.h b/include/asm-x86/byteorder_64.h
new file mode 100644
index 000000000000..5e86c868c75e
--- /dev/null
+++ b/include/asm-x86/byteorder_64.h
@@ -0,0 +1,33 @@
+#ifndef _X86_64_BYTEORDER_H
+#define _X86_64_BYTEORDER_H
+
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+#ifdef __GNUC__
+
+static __inline__ __attribute_const__ __u64 ___arch__swab64(__u64 x)
+{
+        __asm__("bswapq %0" : "=r" (x) : "0" (x));
+        return x;
+}
+
+static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 x)
+{
+        __asm__("bswapl %0" : "=r" (x) : "0" (x));
+        return x;
+}
+
+/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
+   convert it into rotation or exhange.  */
+
+#define __arch__swab32(x) ___arch__swab32(x)
+#define __arch__swab64(x) ___arch__swab64(x)
+
+#endif /* __GNUC__ */
+
+#define __BYTEORDER_HAS_U64__
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* _X86_64_BYTEORDER_H */
diff --git a/include/asm-x86/cache.h b/include/asm-x86/cache.h
new file mode 100644
index 000000000000..c36d190ac9d8
--- /dev/null
+++ b/include/asm-x86/cache.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "cache_32.h"
+#else
+# include "cache_64.h"
+#endif
diff --git a/include/asm-x86/cache_32.h b/include/asm-x86/cache_32.h
new file mode 100644
index 000000000000..57c62f414158
--- /dev/null
+++ b/include/asm-x86/cache_32.h
@@ -0,0 +1,14 @@
+/*
+ * include/asm-i386/cache.h
+ */
+#ifndef __ARCH_I386_CACHE_H
+#define __ARCH_I386_CACHE_H
+
+
+/* L1 cache line size */
+#define L1_CACHE_SHIFT  (CONFIG_X86_L1_CACHE_SHIFT)
+#define L1_CACHE_BYTES  (1 << L1_CACHE_SHIFT)
+
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
+#endif
diff --git a/include/asm-x86/cache_64.h b/include/asm-x86/cache_64.h
new file mode 100644
index 000000000000..052df758ae61
--- /dev/null
+++ b/include/asm-x86/cache_64.h
@@ -0,0 +1,26 @@
+/*
+ * include/asm-x86_64/cache.h
+ */
+#ifndef __ARCH_X8664_CACHE_H
+#define __ARCH_X8664_CACHE_H
+
+
+/* L1 cache line size */
+#define L1_CACHE_SHIFT  (CONFIG_X86_L1_CACHE_SHIFT)
+#define L1_CACHE_BYTES  (1 << L1_CACHE_SHIFT)
+
+#ifdef CONFIG_X86_VSMP
+
+/* vSMP Internode cacheline shift */
+#define INTERNODE_CACHE_SHIFT (12)
+#ifdef CONFIG_SMP
+#define __cacheline_aligned_in_smp                                      \
+       __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))         \
+       __attribute__((__section__(".data.page_aligned")))
+#endif
+
+#endif
+
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
+#endif
diff --git a/include/asm-x86/cacheflush.h b/include/asm-x86/cacheflush.h
new file mode 100644
index 000000000000..e2df3b55034a
--- /dev/null
+++ b/include/asm-x86/cacheflush.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "cacheflush_32.h"
+#else
+# include "cacheflush_64.h"
+#endif
diff --git a/include/asm-x86/cacheflush_32.h b/include/asm-x86/cacheflush_32.h
new file mode 100644
index 000000000000..74e03c8f2e51
--- /dev/null
+++ b/include/asm-x86/cacheflush_32.h
@@ -0,0 +1,39 @@
+#ifndef _I386_CACHEFLUSH_H
+#define _I386_CACHEFLUSH_H
+
+/* Keep includes the same across arches.  */
+#include <linux/mm.h>
+
+/* Caches aren't brain-dead on the intel. */
+#define flush_cache_all()                       do { } while (0)
+#define flush_cache_mm(mm)                      do { } while (0)
+#define flush_cache_dup_mm(mm)                  do { } while (0)
+#define flush_cache_range(vma, start, end)      do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn)      do { } while (0)
+#define flush_dcache_page(page)                 do { } while (0)
+#define flush_dcache_mmap_lock(mapping)         do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)       do { } while (0)
+#define flush_icache_range(start, end)          do { } while (0)
+#define flush_icache_page(vma,pg)               do { } while (0)
+#define flush_icache_user_range(vma,pg,adr,len) do { } while (0)
+#define flush_cache_vmap(start, end)            do { } while (0)
+#define flush_cache_vunmap(start, end)          do { } while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+        memcpy(dst, src, len)
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+        memcpy(dst, src, len)
+
+void global_flush_tlb(void); 
+int change_page_attr(struct page *page, int numpages, pgprot_t prot);
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+/* internal debugging function */
+void kernel_map_pages(struct page *page, int numpages, int enable);
+#endif
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+#endif
+
+#endif /* _I386_CACHEFLUSH_H */
diff --git a/include/asm-x86/cacheflush_64.h b/include/asm-x86/cacheflush_64.h
new file mode 100644
index 000000000000..ab1cb5c7dc92
--- /dev/null
+++ b/include/asm-x86/cacheflush_64.h
@@ -0,0 +1,35 @@
+#ifndef _X8664_CACHEFLUSH_H
+#define _X8664_CACHEFLUSH_H
+
+/* Keep includes the same across arches.  */
+#include <linux/mm.h>
+
+/* Caches aren't brain-dead on the intel. */
+#define flush_cache_all()                       do { } while (0)
+#define flush_cache_mm(mm)                      do { } while (0)
+#define flush_cache_dup_mm(mm)                  do { } while (0)
+#define flush_cache_range(vma, start, end)      do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn)      do { } while (0)
+#define flush_dcache_page(page)                 do { } while (0)
+#define flush_dcache_mmap_lock(mapping)         do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)       do { } while (0)
+#define flush_icache_range(start, end)          do { } while (0)
+#define flush_icache_page(vma,pg)               do { } while (0)
+#define flush_icache_user_range(vma,pg,adr,len) do { } while (0)
+#define flush_cache_vmap(start, end)            do { } while (0)
+#define flush_cache_vunmap(start, end)          do { } while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+        memcpy(dst, src, len)
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+        memcpy(dst, src, len)
+
+void global_flush_tlb(void); 
+int change_page_attr(struct page *page, int numpages, pgprot_t prot);
+int change_page_attr_addr(unsigned long addr, int numpages, pgprot_t prot);
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+#endif
+
+#endif /* _X8664_CACHEFLUSH_H */
diff --git a/include/asm-x86/calgary.h b/include/asm-x86/calgary.h
new file mode 100644
index 000000000000..67f60406e2d8
--- /dev/null
+++ b/include/asm-x86/calgary.h
@@ -0,0 +1,72 @@
+/*
+ * Derived from include/asm-powerpc/iommu.h
+ *
+ * Copyright IBM Corporation, 2006-2007
+ *
+ * Author: Jon Mason <jdmason@us.ibm.com>
+ * Author: Muli Ben-Yehuda <muli@il.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef _ASM_X86_64_CALGARY_H
+#define _ASM_X86_64_CALGARY_H
+
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/timer.h>
+#include <asm/types.h>
+
+struct iommu_table {
+        struct cal_chipset_ops *chip_ops; /* chipset specific funcs */
+        unsigned long  it_base;      /* mapped address of tce table */
+        unsigned long  it_hint;      /* Hint for next alloc */
+        unsigned long *it_map;       /* A simple allocation bitmap for now */
+        void __iomem  *bbar;         /* Bridge BAR */
+        u64            tar_val;      /* Table Address Register */
+        struct timer_list watchdog_timer;
+        spinlock_t     it_lock;      /* Protects it_map */
+        unsigned int   it_size;      /* Size of iommu table in entries */
+        unsigned char  it_busno;     /* Bus number this table belongs to */
+};
+
+struct cal_chipset_ops {
+        void (*handle_quirks)(struct iommu_table *tbl, struct pci_dev *dev);
+        void (*tce_cache_blast)(struct iommu_table *tbl);
+        void (*dump_error_regs)(struct iommu_table *tbl);
+};
+
+#define TCE_TABLE_SIZE_UNSPECIFIED      ~0
+#define TCE_TABLE_SIZE_64K              0
+#define TCE_TABLE_SIZE_128K             1
+#define TCE_TABLE_SIZE_256K             2
+#define TCE_TABLE_SIZE_512K             3
+#define TCE_TABLE_SIZE_1M               4
+#define TCE_TABLE_SIZE_2M               5
+#define TCE_TABLE_SIZE_4M               6
+#define TCE_TABLE_SIZE_8M               7
+
+extern int use_calgary;
+
+#ifdef CONFIG_CALGARY_IOMMU
+extern int calgary_iommu_init(void);
+extern void detect_calgary(void);
+#else
+static inline int calgary_iommu_init(void) { return 1; }
+static inline void detect_calgary(void) { return; }
+#endif
+
+#endif /* _ASM_X86_64_CALGARY_H */
diff --git a/include/asm-x86/calling.h b/include/asm-x86/calling.h
new file mode 100644
index 000000000000..6f4f63af96e1
--- /dev/null
+++ b/include/asm-x86/calling.h
@@ -0,0 +1,162 @@
+/* 
+ * Some macros to handle stack frames in assembly.
+ */ 
+
+
+#define R15 0
+#define R14 8
+#define R13 16
+#define R12 24
+#define RBP 32
+#define RBX 40
+/* arguments: interrupts/non tracing syscalls only save upto here*/
+#define R11 48
+#define R10 56  
+#define R9 64
+#define R8 72
+#define RAX 80
+#define RCX 88
+#define RDX 96
+#define RSI 104
+#define RDI 112
+#define ORIG_RAX 120       /* + error_code */ 
+/* end of arguments */  
+/* cpu exception frame or undefined in case of fast syscall. */
+#define RIP 128
+#define CS 136
+#define EFLAGS 144
+#define RSP 152
+#define SS 160
+#define ARGOFFSET R11
+#define SWFRAME ORIG_RAX
+
+        .macro SAVE_ARGS addskip=0,norcx=0,nor891011=0
+        subq  $9*8+\addskip,%rsp
+        CFI_ADJUST_CFA_OFFSET   9*8+\addskip
+        movq  %rdi,8*8(%rsp) 
+        CFI_REL_OFFSET  rdi,8*8
+        movq  %rsi,7*8(%rsp) 
+        CFI_REL_OFFSET  rsi,7*8
+        movq  %rdx,6*8(%rsp)
+        CFI_REL_OFFSET  rdx,6*8
+        .if \norcx
+        .else
+        movq  %rcx,5*8(%rsp)
+        CFI_REL_OFFSET  rcx,5*8
+        .endif
+        movq  %rax,4*8(%rsp) 
+        CFI_REL_OFFSET  rax,4*8
+        .if \nor891011
+        .else
+        movq  %r8,3*8(%rsp) 
+        CFI_REL_OFFSET  r8,3*8
+        movq  %r9,2*8(%rsp) 
+        CFI_REL_OFFSET  r9,2*8
+        movq  %r10,1*8(%rsp) 
+        CFI_REL_OFFSET  r10,1*8
+        movq  %r11,(%rsp) 
+        CFI_REL_OFFSET  r11,0*8
+        .endif
+        .endm
+
+#define ARG_SKIP 9*8
+        .macro RESTORE_ARGS skiprax=0,addskip=0,skiprcx=0,skipr11=0,skipr8910=0,skiprdx=0
+        .if \skipr11
+        .else
+        movq (%rsp),%r11
+        CFI_RESTORE r11
+        .endif
+        .if \skipr8910
+        .else
+        movq 1*8(%rsp),%r10
+        CFI_RESTORE r10
+        movq 2*8(%rsp),%r9
+        CFI_RESTORE r9
+        movq 3*8(%rsp),%r8
+        CFI_RESTORE r8
+        .endif
+        .if \skiprax
+        .else
+        movq 4*8(%rsp),%rax
+        CFI_RESTORE rax
+        .endif
+        .if \skiprcx
+        .else
+        movq 5*8(%rsp),%rcx
+        CFI_RESTORE rcx
+        .endif
+        .if \skiprdx
+        .else
+        movq 6*8(%rsp),%rdx
+        CFI_RESTORE rdx
+        .endif
+        movq 7*8(%rsp),%rsi
+        CFI_RESTORE rsi
+        movq 8*8(%rsp),%rdi
+        CFI_RESTORE rdi
+        .if ARG_SKIP+\addskip > 0
+        addq $ARG_SKIP+\addskip,%rsp
+        CFI_ADJUST_CFA_OFFSET   -(ARG_SKIP+\addskip)
+        .endif
+        .endm   
+
+        .macro LOAD_ARGS offset
+        movq \offset(%rsp),%r11
+        movq \offset+8(%rsp),%r10
+        movq \offset+16(%rsp),%r9
+        movq \offset+24(%rsp),%r8
+        movq \offset+40(%rsp),%rcx
+        movq \offset+48(%rsp),%rdx
+        movq \offset+56(%rsp),%rsi
+        movq \offset+64(%rsp),%rdi
+        movq \offset+72(%rsp),%rax
+        .endm
+                        
+#define REST_SKIP 6*8                   
+        .macro SAVE_REST
+        subq $REST_SKIP,%rsp
+        CFI_ADJUST_CFA_OFFSET   REST_SKIP
+        movq %rbx,5*8(%rsp) 
+        CFI_REL_OFFSET  rbx,5*8
+        movq %rbp,4*8(%rsp) 
+        CFI_REL_OFFSET  rbp,4*8
+        movq %r12,3*8(%rsp) 
+        CFI_REL_OFFSET  r12,3*8
+        movq %r13,2*8(%rsp) 
+        CFI_REL_OFFSET  r13,2*8
+        movq %r14,1*8(%rsp) 
+        CFI_REL_OFFSET  r14,1*8
+        movq %r15,(%rsp) 
+        CFI_REL_OFFSET  r15,0*8
+        .endm           
+
+        .macro RESTORE_REST
+        movq (%rsp),%r15
+        CFI_RESTORE r15
+        movq 1*8(%rsp),%r14
+        CFI_RESTORE r14
+        movq 2*8(%rsp),%r13
+        CFI_RESTORE r13
+        movq 3*8(%rsp),%r12
+        CFI_RESTORE r12
+        movq 4*8(%rsp),%rbp
+        CFI_RESTORE rbp
+        movq 5*8(%rsp),%rbx
+        CFI_RESTORE rbx
+        addq $REST_SKIP,%rsp
+        CFI_ADJUST_CFA_OFFSET   -(REST_SKIP)
+        .endm
+                
+        .macro SAVE_ALL
+        SAVE_ARGS
+        SAVE_REST
+        .endm
+                
+        .macro RESTORE_ALL addskip=0
+        RESTORE_REST
+        RESTORE_ARGS 0,\addskip
+        .endm
+
+        .macro icebp
+        .byte 0xf1
+        .endm
diff --git a/include/asm-x86/checksum.h b/include/asm-x86/checksum.h
new file mode 100644
index 000000000000..848850fd7d62
--- /dev/null
+++ b/include/asm-x86/checksum.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "checksum_32.h"
+#else
+# include "checksum_64.h"
+#endif
diff --git a/include/asm-x86/checksum_32.h b/include/asm-x86/checksum_32.h
new file mode 100644
index 000000000000..75194abbe8ee
--- /dev/null
+++ b/include/asm-x86/checksum_32.h
@@ -0,0 +1,191 @@
+#ifndef _I386_CHECKSUM_H
+#define _I386_CHECKSUM_H
+
+#include <linux/in6.h>
+
+#include <asm/uaccess.h>
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum);
+
+/*
+ * the same as csum_partial, but copies from src while it
+ * checksums, and handles user-space pointer exceptions correctly, when needed.
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+
+asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
+                                                  int len, __wsum sum, int *src_err_ptr, int *dst_err_ptr);
+
+/*
+ *      Note: when you get a NULL pointer exception here this means someone
+ *      passed in an incorrect kernel address to one of these functions.
+ *
+ *      If you use these functions directly please don't forget the
+ *      access_ok().
+ */
+static __inline__
+__wsum csum_partial_copy_nocheck (const void *src, void *dst,
+                                        int len, __wsum sum)
+{
+        return csum_partial_copy_generic ( src, dst, len, sum, NULL, NULL);
+}
+
+static __inline__
+__wsum csum_partial_copy_from_user(const void __user *src, void *dst,
+                                                int len, __wsum sum, int *err_ptr)
+{
+        might_sleep();
+        return csum_partial_copy_generic((__force void *)src, dst,
+                                        len, sum, err_ptr, NULL);
+}
+
+/*
+ *      This is a version of ip_compute_csum() optimized for IP headers,
+ *      which always checksum on 4 octet boundaries.
+ *
+ *      By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
+ *      Arnt Gulbrandsen.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+        unsigned int sum;
+
+        __asm__ __volatile__(
+            "movl (%1), %0      ;\n"
+            "subl $4, %2        ;\n"
+            "jbe 2f             ;\n"
+            "addl 4(%1), %0     ;\n"
+            "adcl 8(%1), %0     ;\n"
+            "adcl 12(%1), %0    ;\n"
+"1:         adcl 16(%1), %0     ;\n"
+            "lea 4(%1), %1      ;\n"
+            "decl %2            ;\n"
+            "jne 1b             ;\n"
+            "adcl $0, %0        ;\n"
+            "movl %0, %2        ;\n"
+            "shrl $16, %0       ;\n"
+            "addw %w2, %w0      ;\n"
+            "adcl $0, %0        ;\n"
+            "notl %0            ;\n"
+"2:                             ;\n"
+        /* Since the input registers which are loaded with iph and ihl
+           are modified, we must also specify them as outputs, or gcc
+           will assume they contain their original values. */
+        : "=r" (sum), "=r" (iph), "=r" (ihl)
+        : "1" (iph), "2" (ihl)
+        : "memory");
+        return (__force __sum16)sum;
+}
+
+/*
+ *      Fold a partial checksum
+ */
+
+static inline __sum16 csum_fold(__wsum sum)
+{
+        __asm__(
+                "addl %1, %0            ;\n"
+                "adcl $0xffff, %0       ;\n"
+                : "=r" (sum)
+                : "r" ((__force u32)sum << 16),
+                  "0" ((__force u32)sum & 0xffff0000)
+        );
+        return (__force __sum16)(~(__force u32)sum >> 16);
+}
+
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+                                           unsigned short len,
+                                           unsigned short proto,
+                                           __wsum sum)
+{
+    __asm__(
+        "addl %1, %0    ;\n"
+        "adcl %2, %0    ;\n"
+        "adcl %3, %0    ;\n"
+        "adcl $0, %0    ;\n"
+        : "=r" (sum)
+        : "g" (daddr), "g"(saddr), "g"((len + proto) << 8), "0"(sum));
+    return sum;
+}
+
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+                                                   unsigned short len,
+                                                   unsigned short proto,
+                                                   __wsum sum)
+{
+        return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
+}
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+
+static inline __sum16 ip_compute_csum(const void *buff, int len)
+{
+    return csum_fold (csum_partial(buff, len, 0));
+}
+
+#define _HAVE_ARCH_IPV6_CSUM
+static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+                                          const struct in6_addr *daddr,
+                                          __u32 len, unsigned short proto,
+                                          __wsum sum)
+{
+        __asm__(
+                "addl 0(%1), %0         ;\n"
+                "adcl 4(%1), %0         ;\n"
+                "adcl 8(%1), %0         ;\n"
+                "adcl 12(%1), %0        ;\n"
+                "adcl 0(%2), %0         ;\n"
+                "adcl 4(%2), %0         ;\n"
+                "adcl 8(%2), %0         ;\n"
+                "adcl 12(%2), %0        ;\n"
+                "adcl %3, %0            ;\n"
+                "adcl %4, %0            ;\n"
+                "adcl $0, %0            ;\n"
+                : "=&r" (sum)
+                : "r" (saddr), "r" (daddr),
+                  "r"(htonl(len)), "r"(htonl(proto)), "0"(sum));
+
+        return csum_fold(sum);
+}
+
+/*
+ *      Copy and checksum to user
+ */
+#define HAVE_CSUM_COPY_USER
+static __inline__ __wsum csum_and_copy_to_user(const void *src,
+                                                     void __user *dst,
+                                                     int len, __wsum sum,
+                                                     int *err_ptr)
+{
+        might_sleep();
+        if (access_ok(VERIFY_WRITE, dst, len))
+                return csum_partial_copy_generic(src, (__force void *)dst, len, sum, NULL, err_ptr);
+
+        if (len)
+                *err_ptr = -EFAULT;
+
+        return (__force __wsum)-1; /* invalid checksum */
+}
+
+#endif
diff --git a/include/asm-x86/checksum_64.h b/include/asm-x86/checksum_64.h
new file mode 100644
index 000000000000..419fe88a0342
--- /dev/null
+++ b/include/asm-x86/checksum_64.h
@@ -0,0 +1,195 @@
+#ifndef _X86_64_CHECKSUM_H
+#define _X86_64_CHECKSUM_H
+
+/* 
+ * Checksums for x86-64 
+ * Copyright 2002 by Andi Kleen, SuSE Labs 
+ * with some code from asm-i386/checksum.h
+ */ 
+
+#include <linux/compiler.h>
+#include <asm/uaccess.h>
+#include <asm/byteorder.h>
+
+/** 
+ * csum_fold - Fold and invert a 32bit checksum.
+ * sum: 32bit unfolded sum
+ * 
+ * Fold a 32bit running checksum to 16bit and invert it. This is usually
+ * the last step before putting a checksum into a packet.
+ * Make sure not to mix with 64bit checksums.
+ */
+static inline __sum16 csum_fold(__wsum sum)
+{
+        __asm__(
+                "  addl %1,%0\n"
+                "  adcl $0xffff,%0"
+                : "=r" (sum)
+                : "r" ((__force u32)sum << 16),
+                  "0" ((__force u32)sum & 0xffff0000)
+        );
+        return (__force __sum16)(~(__force u32)sum >> 16);
+}
+
+/*
+ *      This is a version of ip_compute_csum() optimized for IP headers,
+ *      which always checksum on 4 octet boundaries.
+ *
+ *      By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
+ *      Arnt Gulbrandsen.
+ */
+
+/**
+ * ip_fast_csum - Compute the IPv4 header checksum efficiently.
+ * iph: ipv4 header
+ * ihl: length of header / 4
+ */ 
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+        unsigned int sum;
+
+        asm(    "  movl (%1), %0\n"
+                "  subl $4, %2\n"
+                "  jbe 2f\n"
+                "  addl 4(%1), %0\n"
+                "  adcl 8(%1), %0\n"
+                "  adcl 12(%1), %0\n"
+                "1: adcl 16(%1), %0\n"
+                "  lea 4(%1), %1\n"
+                "  decl %2\n"
+                "  jne  1b\n"
+                "  adcl $0, %0\n"
+                "  movl %0, %2\n"
+                "  shrl $16, %0\n"
+                "  addw %w2, %w0\n"
+                "  adcl $0, %0\n"
+                "  notl %0\n"
+                "2:"
+        /* Since the input registers which are loaded with iph and ihl
+           are modified, we must also specify them as outputs, or gcc
+           will assume they contain their original values. */
+        : "=r" (sum), "=r" (iph), "=r" (ihl)
+        : "1" (iph), "2" (ihl)
+        : "memory");
+        return (__force __sum16)sum;
+}
+
+/** 
+ * csum_tcpup_nofold - Compute an IPv4 pseudo header checksum.
+ * @saddr: source address
+ * @daddr: destination address
+ * @len: length of packet
+ * @proto: ip protocol of packet
+ * @sum: initial sum to be added in (32bit unfolded) 
+ * 
+ * Returns the pseudo header checksum the input data. Result is 
+ * 32bit unfolded.
+ */
+static inline __wsum
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
+                   unsigned short proto, __wsum sum)
+{
+        asm("  addl %1, %0\n"
+            "  adcl %2, %0\n"
+            "  adcl %3, %0\n"
+            "  adcl $0, %0\n"
+                : "=r" (sum)
+            : "g" (daddr), "g" (saddr),
+              "g" ((len + proto)<<8), "0" (sum));
+    return sum;
+}
+
+
+/** 
+ * csum_tcpup_magic - Compute an IPv4 pseudo header checksum.
+ * @saddr: source address
+ * @daddr: destination address
+ * @len: length of packet
+ * @proto: ip protocol of packet
+ * @sum: initial sum to be added in (32bit unfolded) 
+ * 
+ * Returns the 16bit pseudo header checksum the input data already
+ * complemented and ready to be filled in.
+ */
+static inline __sum16
+csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+                  unsigned short len, unsigned short proto, __wsum sum)
+{
+        return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
+}
+
+/** 
+ * csum_partial - Compute an internet checksum.
+ * @buff: buffer to be checksummed
+ * @len: length of buffer.
+ * @sum: initial sum to be added in (32bit unfolded)
+ *
+ * Returns the 32bit unfolded internet checksum of the buffer.
+ * Before filling it in it needs to be csum_fold()'ed.
+ * buff should be aligned to a 64bit boundary if possible.
+ */ 
+extern __wsum csum_partial(const void *buff, int len, __wsum sum);
+
+#define  _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
+#define HAVE_CSUM_COPY_USER 1
+
+
+/* Do not call this directly. Use the wrappers below */
+extern __wsum csum_partial_copy_generic(const void *src, const void *dst,
+                                               int len,
+                                               __wsum sum,
+                                               int *src_err_ptr, int *dst_err_ptr);
+
+
+extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
+                                       int len, __wsum isum, int *errp);
+extern __wsum csum_partial_copy_to_user(const void *src, void __user *dst,
+                                      int len, __wsum isum, int *errp);
+extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len,
+                                              __wsum sum);
+
+/* Old names. To be removed. */
+#define csum_and_copy_to_user csum_partial_copy_to_user
+#define csum_and_copy_from_user csum_partial_copy_from_user
+
+/** 
+ * ip_compute_csum - Compute an 16bit IP checksum.
+ * @buff: buffer address.
+ * @len: length of buffer.
+ *
+ * Returns the 16bit folded/inverted checksum of the passed buffer.
+ * Ready to fill in.
+ */
+extern __sum16 ip_compute_csum(const void *buff, int len);
+
+/**
+ * csum_ipv6_magic - Compute checksum of an IPv6 pseudo header.
+ * @saddr: source address
+ * @daddr: destination address
+ * @len: length of packet
+ * @proto: protocol of packet
+ * @sum: initial sum (32bit unfolded) to be added in
+ *
+ * Computes an IPv6 pseudo header checksum. This sum is added the checksum 
+ * into UDP/TCP packets and contains some link layer information.
+ * Returns the unfolded 32bit checksum.
+ */
+
+struct in6_addr;
+
+#define _HAVE_ARCH_IPV6_CSUM 1
+extern __sum16
+csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr,
+                __u32 len, unsigned short proto, __wsum sum);
+
+static inline unsigned add32_with_carry(unsigned a, unsigned b)
+{
+        asm("addl %2,%0\n\t"
+            "adcl $0,%0" 
+            : "=r" (a) 
+            : "0" (a), "r" (b));
+        return a;
+}
+
+#endif
+
diff --git a/include/asm-x86/cmpxchg.h b/include/asm-x86/cmpxchg.h
new file mode 100644
index 000000000000..a460fa088d4c
--- /dev/null
+++ b/include/asm-x86/cmpxchg.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "cmpxchg_32.h"
+#else
+# include "cmpxchg_64.h"
+#endif
diff --git a/include/asm-x86/cmpxchg_32.h b/include/asm-x86/cmpxchg_32.h
new file mode 100644
index 000000000000..f86ede28f6dc
--- /dev/null
+++ b/include/asm-x86/cmpxchg_32.h
@@ -0,0 +1,289 @@
+#ifndef __ASM_CMPXCHG_H
+#define __ASM_CMPXCHG_H
+
+#include <linux/bitops.h> /* for LOCK_PREFIX */
+
+/*
+ * Note: if you use set64_bit(), __cmpxchg64(), or their variants, you
+ *       you need to test for the feature in boot_cpu_data.
+ */
+
+#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((struct __xchg_dummy *)(x))
+
+/*
+ * The semantics of XCHGCMP8B are a bit strange, this is why
+ * there is a loop and the loading of %%eax and %%edx has to
+ * be inside. This inlines well in most cases, the cached
+ * cost is around ~38 cycles. (in the future we might want
+ * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
+ * might have an implicit FPU-save as a cost, so it's not
+ * clear which path to go.)
+ *
+ * cmpxchg8b must be used with the lock prefix here to allow
+ * the instruction to be executed atomically, see page 3-102
+ * of the instruction set reference 24319102.pdf. We need
+ * the reader side to see the coherent 64bit value.
+ */
+static inline void __set_64bit (unsigned long long * ptr,
+                unsigned int low, unsigned int high)
+{
+        __asm__ __volatile__ (
+                "\n1:\t"
+                "movl (%0), %%eax\n\t"
+                "movl 4(%0), %%edx\n\t"
+                LOCK_PREFIX "cmpxchg8b (%0)\n\t"
+                "jnz 1b"
+                : /* no outputs */
+                :       "D"(ptr),
+                        "b"(low),
+                        "c"(high)
+                :       "ax","dx","memory");
+}
+
+static inline void __set_64bit_constant (unsigned long long *ptr,
+                                                 unsigned long long value)
+{
+        __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
+}
+#define ll_low(x)       *(((unsigned int*)&(x))+0)
+#define ll_high(x)      *(((unsigned int*)&(x))+1)
+
+static inline void __set_64bit_var (unsigned long long *ptr,
+                         unsigned long long value)
+{
+        __set_64bit(ptr,ll_low(value), ll_high(value));
+}
+
+#define set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit_constant(ptr, value) : \
+ __set_64bit_var(ptr, value) )
+
+#define _set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
+ __set_64bit(ptr, ll_low(value), ll_high(value)) )
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ *        but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+        switch (size) {
+                case 1:
+                        __asm__ __volatile__("xchgb %b0,%1"
+                                :"=q" (x)
+                                :"m" (*__xg(ptr)), "0" (x)
+                                :"memory");
+                        break;
+                case 2:
+                        __asm__ __volatile__("xchgw %w0,%1"
+                                :"=r" (x)
+                                :"m" (*__xg(ptr)), "0" (x)
+                                :"memory");
+                        break;
+                case 4:
+                        __asm__ __volatile__("xchgl %0,%1"
+                                :"=r" (x)
+                                :"m" (*__xg(ptr)), "0" (x)
+                                :"memory");
+                        break;
+        }
+        return x;
+}
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#ifdef CONFIG_X86_CMPXCHG
+#define __HAVE_ARCH_CMPXCHG 1
+#define cmpxchg(ptr,o,n)\
+        ((__typeof__(*(ptr)))__cmpxchg((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 cmpxchg_local(ptr,o,n)\
+        ((__typeof__(*(ptr)))__cmpxchg_local((ptr),(unsigned long)(o),\
+                                        (unsigned long)(n),sizeof(*(ptr))))
+#endif
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+                                      unsigned long new, int size)
+{
+        unsigned long prev;
+        switch (size) {
+        case 1:
+                __asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
+                                     : "=a"(prev)
+                                     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 2:
+                __asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 4:
+                __asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        }
+        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)
+{
+        unsigned long prev;
+        switch (size) {
+        case 1:
+                __asm__ __volatile__("cmpxchgb %b1,%2"
+                                     : "=a"(prev)
+                                     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 2:
+                __asm__ __volatile__("cmpxchgw %w1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 4:
+                __asm__ __volatile__("cmpxchgl %1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        }
+        return old;
+}
+
+#ifndef CONFIG_X86_CMPXCHG
+/*
+ * Building a kernel capable running on 80386. It may be necessary to
+ * simulate the cmpxchg on the 80386 CPU. For that purpose we define
+ * a function for each of the sizes we support.
+ */
+
+extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
+extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
+extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
+
+static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
+                                      unsigned long new, int size)
+{
+        switch (size) {
+        case 1:
+                return cmpxchg_386_u8(ptr, old, new);
+        case 2:
+                return cmpxchg_386_u16(ptr, old, new);
+        case 4:
+                return cmpxchg_386_u32(ptr, old, new);
+        }
+        return old;
+}
+
+#define cmpxchg(ptr,o,n)                                                \
+({                                                                      \
+        __typeof__(*(ptr)) __ret;                                       \
+        if (likely(boot_cpu_data.x86 > 3))                              \
+                __ret = __cmpxchg((ptr), (unsigned long)(o),            \
+                                        (unsigned long)(n), sizeof(*(ptr))); \
+        else                                                            \
+                __ret = cmpxchg_386((ptr), (unsigned long)(o),          \
+                                        (unsigned long)(n), sizeof(*(ptr))); \
+        __ret;                                                          \
+})
+#define cmpxchg_local(ptr,o,n)                                          \
+({                                                                      \
+        __typeof__(*(ptr)) __ret;                                       \
+        if (likely(boot_cpu_data.x86 > 3))                              \
+                __ret = __cmpxchg_local((ptr), (unsigned long)(o),      \
+                                        (unsigned long)(n), sizeof(*(ptr))); \
+        else                                                            \
+                __ret = cmpxchg_386((ptr), (unsigned long)(o),          \
+                                        (unsigned long)(n), sizeof(*(ptr))); \
+        __ret;                                                          \
+})
+#endif
+
+static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long long old,
+                                      unsigned long long new)
+{
+        unsigned long long prev;
+        __asm__ __volatile__(LOCK_PREFIX "cmpxchg8b %3"
+                             : "=A"(prev)
+                             : "b"((unsigned long)new),
+                               "c"((unsigned long)(new >> 32)),
+                               "m"(*__xg(ptr)),
+                               "0"(old)
+                             : "memory");
+        return prev;
+}
+
+static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
+                        unsigned long long old, unsigned long long new)
+{
+        unsigned long long prev;
+        __asm__ __volatile__("cmpxchg8b %3"
+                             : "=A"(prev)
+                             : "b"((unsigned long)new),
+                               "c"((unsigned long)(new >> 32)),
+                               "m"(*__xg(ptr)),
+                               "0"(old)
+                             : "memory");
+        return prev;
+}
+
+#define cmpxchg64(ptr,o,n)\
+        ((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\
+                                        (unsigned long long)(n)))
+#define cmpxchg64_local(ptr,o,n)\
+        ((__typeof__(*(ptr)))__cmpxchg64_local((ptr),(unsigned long long)(o),\
+                                        (unsigned long long)(n)))
+#endif
diff --git a/include/asm-x86/cmpxchg_64.h b/include/asm-x86/cmpxchg_64.h
new file mode 100644
index 000000000000..5e182062e6ec
--- /dev/null
+++ b/include/asm-x86/cmpxchg_64.h
@@ -0,0 +1,134 @@
+#ifndef __ASM_CMPXCHG_H
+#define __ASM_CMPXCHG_H
+
+#include <asm/alternative.h> /* Provides LOCK_PREFIX */
+
+#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))
+
+#define __xg(x) ((volatile long *)(x))
+
+static inline void set_64bit(volatile unsigned long *ptr, unsigned long val)
+{
+        *ptr = val;
+}
+
+#define _set_64bit set_64bit
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ *        but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+        switch (size) {
+                case 1:
+                        __asm__ __volatile__("xchgb %b0,%1"
+                                :"=q" (x)
+                                :"m" (*__xg(ptr)), "0" (x)
+                                :"memory");
+                        break;
+                case 2:
+                        __asm__ __volatile__("xchgw %w0,%1"
+                                :"=r" (x)
+                                :"m" (*__xg(ptr)), "0" (x)
+                                :"memory");
+                        break;
+                case 4:
+                        __asm__ __volatile__("xchgl %k0,%1"
+                                :"=r" (x)
+                                :"m" (*__xg(ptr)), "0" (x)
+                                :"memory");
+                        break;
+                case 8:
+                        __asm__ __volatile__("xchgq %0,%1"
+                                :"=r" (x)
+                                :"m" (*__xg(ptr)), "0" (x)
+                                :"memory");
+                        break;
+        }
+        return x;
+}
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+                                      unsigned long new, int size)
+{
+        unsigned long prev;
+        switch (size) {
+        case 1:
+                __asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
+                                     : "=a"(prev)
+                                     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 2:
+                __asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 4:
+                __asm__ __volatile__(LOCK_PREFIX "cmpxchgl %k1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 8:
+                __asm__ __volatile__(LOCK_PREFIX "cmpxchgq %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)
+{
+        unsigned long prev;
+        switch (size) {
+        case 1:
+                __asm__ __volatile__("cmpxchgb %b1,%2"
+                                     : "=a"(prev)
+                                     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 2:
+                __asm__ __volatile__("cmpxchgw %w1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 4:
+                __asm__ __volatile__("cmpxchgl %k1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        case 8:
+                __asm__ __volatile__("cmpxchgq %1,%2"
+                                     : "=a"(prev)
+                                     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                                     : "memory");
+                return prev;
+        }
+        return old;
+}
+
+#define cmpxchg(ptr,o,n)\
+        ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+                                        (unsigned long)(n),sizeof(*(ptr))))
+#define cmpxchg_local(ptr,o,n)\
+        ((__typeof__(*(ptr)))__cmpxchg_local((ptr),(unsigned long)(o),\
+                                        (unsigned long)(n),sizeof(*(ptr))))
+
+#endif
diff --git a/include/asm-x86/compat.h b/include/asm-x86/compat.h
new file mode 100644
index 000000000000..53cb96b68a62
--- /dev/null
+++ b/include/asm-x86/compat.h
@@ -0,0 +1,212 @@
+#ifndef _ASM_X86_64_COMPAT_H
+#define _ASM_X86_64_COMPAT_H
+
+/*
+ * Architecture specific compatibility types
+ */
+#include <linux/types.h>
+#include <linux/sched.h>
+
+#define COMPAT_USER_HZ  100
+
+typedef u32             compat_size_t;
+typedef s32             compat_ssize_t;
+typedef s32             compat_time_t;
+typedef s32             compat_clock_t;
+typedef s32             compat_pid_t;
+typedef u16             __compat_uid_t;
+typedef u16             __compat_gid_t;
+typedef u32             __compat_uid32_t;
+typedef u32             __compat_gid32_t;
+typedef u16             compat_mode_t;
+typedef u32             compat_ino_t;
+typedef u16             compat_dev_t;
+typedef s32             compat_off_t;
+typedef s64             compat_loff_t;
+typedef u16             compat_nlink_t;
+typedef u16             compat_ipc_pid_t;
+typedef s32             compat_daddr_t;
+typedef u32             compat_caddr_t;
+typedef __kernel_fsid_t compat_fsid_t;
+typedef s32             compat_timer_t;
+typedef s32             compat_key_t;
+
+typedef s32             compat_int_t;
+typedef s32             compat_long_t;
+typedef s64 __attribute__((aligned(4))) compat_s64;
+typedef u32             compat_uint_t;
+typedef u32             compat_ulong_t;
+typedef u64 __attribute__((aligned(4))) compat_u64;
+
+struct compat_timespec {
+        compat_time_t   tv_sec;
+        s32             tv_nsec;
+};
+
+struct compat_timeval {
+        compat_time_t   tv_sec;
+        s32             tv_usec;
+};
+
+struct compat_stat {
+        compat_dev_t    st_dev;
+        u16             __pad1;
+        compat_ino_t    st_ino;
+        compat_mode_t   st_mode;
+        compat_nlink_t  st_nlink;
+        __compat_uid_t  st_uid;
+        __compat_gid_t  st_gid;
+        compat_dev_t    st_rdev;
+        u16             __pad2;
+        u32             st_size;
+        u32             st_blksize;
+        u32             st_blocks;
+        u32             st_atime;
+        u32             st_atime_nsec;
+        u32             st_mtime;
+        u32             st_mtime_nsec;
+        u32             st_ctime;
+        u32             st_ctime_nsec;
+        u32             __unused4;
+        u32             __unused5;
+};
+
+struct compat_flock {
+        short           l_type;
+        short           l_whence;
+        compat_off_t    l_start;
+        compat_off_t    l_len;
+        compat_pid_t    l_pid;
+};
+
+#define F_GETLK64       12      /*  using 'struct flock64' */
+#define F_SETLK64       13
+#define F_SETLKW64      14
+
+/*
+ * IA32 uses 4 byte alignment for 64 bit quantities,
+ * so we need to pack this structure.
+ */
+struct compat_flock64 {
+        short           l_type;
+        short           l_whence;
+        compat_loff_t   l_start;
+        compat_loff_t   l_len;
+        compat_pid_t    l_pid;
+} __attribute__((packed));
+
+struct compat_statfs {
+        int             f_type;
+        int             f_bsize;
+        int             f_blocks;
+        int             f_bfree;
+        int             f_bavail;
+        int             f_files;
+        int             f_ffree;
+        compat_fsid_t   f_fsid;
+        int             f_namelen;      /* SunOS ignores this field. */
+        int             f_frsize;
+        int             f_spare[5];
+};
+
+#define COMPAT_RLIM_OLD_INFINITY        0x7fffffff
+#define COMPAT_RLIM_INFINITY            0xffffffff
+
+typedef u32             compat_old_sigset_t;    /* at least 32 bits */
+
+#define _COMPAT_NSIG            64
+#define _COMPAT_NSIG_BPW        32
+
+typedef u32               compat_sigset_word;
+
+#define COMPAT_OFF_T_MAX        0x7fffffff
+#define COMPAT_LOFF_T_MAX       0x7fffffffffffffffL
+
+struct compat_ipc64_perm {
+        compat_key_t key;
+        __compat_uid32_t uid;
+        __compat_gid32_t gid;
+        __compat_uid32_t cuid;
+        __compat_gid32_t cgid;
+        unsigned short mode;
+        unsigned short __pad1;
+        unsigned short seq;
+        unsigned short __pad2;
+        compat_ulong_t unused1;
+        compat_ulong_t unused2;
+};
+
+struct compat_semid64_ds {
+        struct compat_ipc64_perm sem_perm;
+        compat_time_t  sem_otime;
+        compat_ulong_t __unused1;
+        compat_time_t  sem_ctime;
+        compat_ulong_t __unused2;
+        compat_ulong_t sem_nsems;
+        compat_ulong_t __unused3;
+        compat_ulong_t __unused4;
+};
+
+struct compat_msqid64_ds {
+        struct compat_ipc64_perm msg_perm;
+        compat_time_t  msg_stime;
+        compat_ulong_t __unused1;
+        compat_time_t  msg_rtime;
+        compat_ulong_t __unused2;
+        compat_time_t  msg_ctime;
+        compat_ulong_t __unused3;
+        compat_ulong_t msg_cbytes;
+        compat_ulong_t msg_qnum;
+        compat_ulong_t msg_qbytes;
+        compat_pid_t   msg_lspid;
+        compat_pid_t   msg_lrpid;
+        compat_ulong_t __unused4;
+        compat_ulong_t __unused5;
+};
+
+struct compat_shmid64_ds {
+        struct compat_ipc64_perm shm_perm;
+        compat_size_t  shm_segsz;
+        compat_time_t  shm_atime;
+        compat_ulong_t __unused1;
+        compat_time_t  shm_dtime;
+        compat_ulong_t __unused2;
+        compat_time_t  shm_ctime;
+        compat_ulong_t __unused3;
+        compat_pid_t   shm_cpid;
+        compat_pid_t   shm_lpid;
+        compat_ulong_t shm_nattch;
+        compat_ulong_t __unused4;
+        compat_ulong_t __unused5;
+};
+
+/*
+ * A pointer passed in from user mode. This should not
+ * be used for syscall parameters, just declare them
+ * as pointers because the syscall entry code will have
+ * appropriately comverted them already.
+ */
+typedef u32             compat_uptr_t;
+
+static inline void __user *compat_ptr(compat_uptr_t uptr)
+{
+        return (void __user *)(unsigned long)uptr;
+}
+
+static inline compat_uptr_t ptr_to_compat(void __user *uptr)
+{
+        return (u32)(unsigned long)uptr;
+}
+
+static __inline__ void __user *compat_alloc_user_space(long len)
+{
+        struct pt_regs *regs = task_pt_regs(current);
+        return (void __user *)regs->rsp - len; 
+}
+
+static inline int is_compat_task(void)
+{
+        return current_thread_info()->status & TS_COMPAT;
+}
+
+#endif /* _ASM_X86_64_COMPAT_H */
diff --git a/include/asm-x86/cpu.h b/include/asm-x86/cpu.h
new file mode 100644
index 000000000000..9d914e1e4aad
--- /dev/null
+++ b/include/asm-x86/cpu.h
@@ -0,0 +1,22 @@
+#ifndef _ASM_I386_CPU_H_
+#define _ASM_I386_CPU_H_
+
+#include <linux/device.h>
+#include <linux/cpu.h>
+#include <linux/topology.h>
+#include <linux/nodemask.h>
+#include <linux/percpu.h>
+
+struct i386_cpu {
+        struct cpu cpu;
+};
+extern int arch_register_cpu(int num);
+#ifdef CONFIG_HOTPLUG_CPU
+extern void arch_unregister_cpu(int);
+extern int enable_cpu_hotplug;
+#else
+#define enable_cpu_hotplug      0
+#endif
+
+DECLARE_PER_CPU(int, cpu_state);
+#endif /* _ASM_I386_CPU_H_ */
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
new file mode 100644
index 000000000000..b7160a4598d7
--- /dev/null
+++ b/include/asm-x86/cpufeature.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "cpufeature_32.h"
+#else
+# include "cpufeature_64.h"
+#endif
diff --git a/include/asm-x86/cpufeature_32.h b/include/asm-x86/cpufeature_32.h
new file mode 100644
index 000000000000..7b3aa28ebc6e
--- /dev/null
+++ b/include/asm-x86/cpufeature_32.h
@@ -0,0 +1,175 @@
+/*
+ * cpufeature.h
+ *
+ * Defines x86 CPU feature bits
+ */
+
+#ifndef __ASM_I386_CPUFEATURE_H
+#define __ASM_I386_CPUFEATURE_H
+
+#ifndef __ASSEMBLY__
+#include <linux/bitops.h>
+#endif
+#include <asm/required-features.h>
+
+#define NCAPINTS        8       /* N 32-bit words worth of info */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
+#define X86_FEATURE_FPU         (0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME         (0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE          (0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE         (0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC         (0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR         (0*32+ 5) /* Model-Specific Registers, RDMSR, WRMSR */
+#define X86_FEATURE_PAE         (0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE         (0*32+ 7) /* Machine Check Architecture */
+#define X86_FEATURE_CX8         (0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC        (0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP         (0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR        (0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE         (0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA         (0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV        (0*32+15) /* CMOV instruction (FCMOVCC and FCOMI too if FPU present) */
+#define X86_FEATURE_PAT         (0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36       (0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN          (0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLSH      (0*32+19) /* Supports the CLFLUSH instruction */
+#define X86_FEATURE_DS          (0*32+21) /* Debug Store */
+#define X86_FEATURE_ACPI        (0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX         (0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR        (0*32+24) /* FXSAVE and FXRSTOR instructions (fast save and restore */
+                                          /* of FPU context), and CR4.OSFXSR available */
+#define X86_FEATURE_XMM         (0*32+25) /* Streaming SIMD Extensions */
+#define X86_FEATURE_XMM2        (0*32+26) /* Streaming SIMD Extensions-2 */
+#define X86_FEATURE_SELFSNOOP   (0*32+27) /* CPU self snoop */
+#define X86_FEATURE_HT          (0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC         (0*32+29) /* Automatic clock control */
+#define X86_FEATURE_IA64        (0*32+30) /* IA-64 processor */
+
+/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
+/* Don't duplicate feature flags which are redundant with Intel! */
+#define X86_FEATURE_SYSCALL     (1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP          (1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX          (1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT      (1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_RDTSCP      (1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM          (1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT    (1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW       (1*32+31) /* 3DNow! */
+
+/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
+#define X86_FEATURE_RECOVERY    (2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN     (2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI        (2*32+ 3) /* LongRun table interface */
+
+/* Other features, Linux-defined mapping, word 3 */
+/* This range is used for feature bits which conflict or are synthesized */
+#define X86_FEATURE_CXMMX       (3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR     (3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR   (3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */
+/* cpu types for specific tunings: */
+#define X86_FEATURE_K8          (3*32+ 4) /* Opteron, Athlon64 */
+#define X86_FEATURE_K7          (3*32+ 5) /* Athlon */
+#define X86_FEATURE_P3          (3*32+ 6) /* P3 */
+#define X86_FEATURE_P4          (3*32+ 7) /* P4 */
+#define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP          (3*32+ 9) /* smp kernel running on up */
+#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* FXSAVE leaks FOP/FIP/FOP */
+#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 */
+#define X86_FEATURE_SYNC_RDTSC  (3*32+15)  /* RDTSC synchronizes the CPU */
+#define X86_FEATURE_REP_GOOD   (3*32+16) /* rep microcode works well on this CPU */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
+#define X86_FEATURE_XMM3        (4*32+ 0) /* Streaming SIMD Extensions-3 */
+#define X86_FEATURE_MWAIT       (4*32+ 3) /* Monitor/Mwait support */
+#define X86_FEATURE_DSCPL       (4*32+ 4) /* CPL Qualified Debug Store */
+#define X86_FEATURE_EST         (4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2         (4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_CID         (4*32+10) /* Context ID */
+#define X86_FEATURE_CX16        (4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR        (4*32+14) /* Send Task Priority Messages */
+
+/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
+#define X86_FEATURE_XSTORE      (5*32+ 2) /* on-CPU RNG present (xstore insn) */
+#define X86_FEATURE_XSTORE_EN   (5*32+ 3) /* on-CPU RNG enabled */
+#define X86_FEATURE_XCRYPT      (5*32+ 6) /* on-CPU crypto (xcrypt insn) */
+#define X86_FEATURE_XCRYPT_EN   (5*32+ 7) /* on-CPU crypto enabled */
+#define X86_FEATURE_ACE2        (5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN     (5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE         (5*32+ 10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN      (5*32+ 11) /* PHE enabled */
+#define X86_FEATURE_PMM         (5*32+ 12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN      (5*32+ 13) /* PMM enabled */
+
+/* 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 */
+
+/*
+ * Auxiliary flags: Linux defined - For features scattered in various
+ * CPUID levels like 0x6, 0xA etc
+ */
+#define X86_FEATURE_IDA         (7*32+ 0) /* Intel Dynamic Acceleration */
+
+#define cpu_has(c, bit)                                                 \
+        (__builtin_constant_p(bit) &&                                   \
+         ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||     \
+           (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||     \
+           (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||     \
+           (((bit)>>5)==3 && (1UL<<((bit)&31) & REQUIRED_MASK3)) ||     \
+           (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) ||     \
+           (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) ||     \
+           (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||     \
+           (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) )      \
+          ? 1 :                                                         \
+          test_bit(bit, (c)->x86_capability))
+#define boot_cpu_has(bit)       cpu_has(&boot_cpu_data, bit)
+
+#define cpu_has_fpu             boot_cpu_has(X86_FEATURE_FPU)
+#define cpu_has_vme             boot_cpu_has(X86_FEATURE_VME)
+#define cpu_has_de              boot_cpu_has(X86_FEATURE_DE)
+#define cpu_has_pse             boot_cpu_has(X86_FEATURE_PSE)
+#define cpu_has_tsc             boot_cpu_has(X86_FEATURE_TSC)
+#define cpu_has_pae             boot_cpu_has(X86_FEATURE_PAE)
+#define cpu_has_pge             boot_cpu_has(X86_FEATURE_PGE)
+#define cpu_has_apic            boot_cpu_has(X86_FEATURE_APIC)
+#define cpu_has_sep             boot_cpu_has(X86_FEATURE_SEP)
+#define cpu_has_mtrr            boot_cpu_has(X86_FEATURE_MTRR)
+#define cpu_has_mmx             boot_cpu_has(X86_FEATURE_MMX)
+#define cpu_has_fxsr            boot_cpu_has(X86_FEATURE_FXSR)
+#define cpu_has_xmm             boot_cpu_has(X86_FEATURE_XMM)
+#define cpu_has_xmm2            boot_cpu_has(X86_FEATURE_XMM2)
+#define cpu_has_xmm3            boot_cpu_has(X86_FEATURE_XMM3)
+#define cpu_has_ht              boot_cpu_has(X86_FEATURE_HT)
+#define cpu_has_mp              boot_cpu_has(X86_FEATURE_MP)
+#define cpu_has_nx              boot_cpu_has(X86_FEATURE_NX)
+#define cpu_has_k6_mtrr         boot_cpu_has(X86_FEATURE_K6_MTRR)
+#define cpu_has_cyrix_arr       boot_cpu_has(X86_FEATURE_CYRIX_ARR)
+#define cpu_has_centaur_mcr     boot_cpu_has(X86_FEATURE_CENTAUR_MCR)
+#define cpu_has_xstore          boot_cpu_has(X86_FEATURE_XSTORE)
+#define cpu_has_xstore_enabled  boot_cpu_has(X86_FEATURE_XSTORE_EN)
+#define cpu_has_xcrypt          boot_cpu_has(X86_FEATURE_XCRYPT)
+#define cpu_has_xcrypt_enabled  boot_cpu_has(X86_FEATURE_XCRYPT_EN)
+#define cpu_has_ace2            boot_cpu_has(X86_FEATURE_ACE2)
+#define cpu_has_ace2_enabled    boot_cpu_has(X86_FEATURE_ACE2_EN)
+#define cpu_has_phe             boot_cpu_has(X86_FEATURE_PHE)
+#define cpu_has_phe_enabled     boot_cpu_has(X86_FEATURE_PHE_EN)
+#define cpu_has_pmm             boot_cpu_has(X86_FEATURE_PMM)
+#define cpu_has_pmm_enabled     boot_cpu_has(X86_FEATURE_PMM_EN)
+#define cpu_has_ds              boot_cpu_has(X86_FEATURE_DS)
+#define cpu_has_pebs            boot_cpu_has(X86_FEATURE_PEBS)
+#define cpu_has_clflush         boot_cpu_has(X86_FEATURE_CLFLSH)
+#define cpu_has_bts             boot_cpu_has(X86_FEATURE_BTS)
+
+#endif /* __ASM_I386_CPUFEATURE_H */
+
+/* 
+ * Local Variables:
+ * mode:c
+ * comment-column:42
+ * End:
+ */
diff --git a/include/asm-x86/cpufeature_64.h b/include/asm-x86/cpufeature_64.h
new file mode 100644
index 000000000000..2983501e8b3e
--- /dev/null
+++ b/include/asm-x86/cpufeature_64.h
@@ -0,0 +1,30 @@
+/*
+ * cpufeature_32.h
+ *
+ * Defines x86 CPU feature bits
+ */
+
+#ifndef __ASM_X8664_CPUFEATURE_H
+#define __ASM_X8664_CPUFEATURE_H
+
+#include <asm/cpufeature_32.h>
+
+#undef  cpu_has_vme
+#define cpu_has_vme            0
+
+#undef  cpu_has_pae
+#define cpu_has_pae            ___BUG___
+
+#undef  cpu_has_mp
+#define cpu_has_mp             1 /* XXX */
+
+#undef  cpu_has_k6_mtrr
+#define cpu_has_k6_mtrr        0
+
+#undef  cpu_has_cyrix_arr
+#define cpu_has_cyrix_arr      0
+
+#undef  cpu_has_centaur_mcr
+#define cpu_has_centaur_mcr    0
+
+#endif /* __ASM_X8664_CPUFEATURE_H */
diff --git a/include/asm-x86/cputime.h b/include/asm-x86/cputime.h
new file mode 100644
index 000000000000..87c37cf6b707
--- /dev/null
+++ b/include/asm-x86/cputime.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "cputime_32.h"
+#else
+# include "cputime_64.h"
+#endif
diff --git a/include/asm-x86/cputime_32.h b/include/asm-x86/cputime_32.h
new file mode 100644
index 000000000000..398ed7cd171d
--- /dev/null
+++ b/include/asm-x86/cputime_32.h
@@ -0,0 +1,6 @@
+#ifndef __I386_CPUTIME_H
+#define __I386_CPUTIME_H
+
+#include <asm-generic/cputime.h>
+
+#endif /* __I386_CPUTIME_H */
diff --git a/include/asm-x86/cputime_64.h b/include/asm-x86/cputime_64.h
new file mode 100644
index 000000000000..a07012dc5a3c
--- /dev/null
+++ b/include/asm-x86/cputime_64.h
@@ -0,0 +1,6 @@
+#ifndef __X86_64_CPUTIME_H
+#define __X86_64_CPUTIME_H
+
+#include <asm-generic/cputime.h>
+
+#endif /* __X86_64_CPUTIME_H */
diff --git a/include/asm-x86/current.h b/include/asm-x86/current.h
new file mode 100644
index 000000000000..d2526d3f7346
--- /dev/null
+++ b/include/asm-x86/current.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "current_32.h"
+#else
+# include "current_64.h"
+#endif
diff --git a/include/asm-x86/current_32.h b/include/asm-x86/current_32.h
new file mode 100644
index 000000000000..d35248539912
--- /dev/null
+++ b/include/asm-x86/current_32.h
@@ -0,0 +1,17 @@
+#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
new file mode 100644
index 000000000000..bc8adecee66d
--- /dev/null
+++ b/include/asm-x86/current_64.h
@@ -0,0 +1,27 @@
+#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/debugreg.h b/include/asm-x86/debugreg.h
new file mode 100644
index 000000000000..b6ce7e4fa002
--- /dev/null
+++ b/include/asm-x86/debugreg.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "debugreg_32.h"
+# else
+#  include "debugreg_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "debugreg_32.h"
+# else
+#  include "debugreg_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/debugreg_32.h b/include/asm-x86/debugreg_32.h
new file mode 100644
index 000000000000..f0b2b06ae0f7
--- /dev/null
+++ b/include/asm-x86/debugreg_32.h
@@ -0,0 +1,64 @@
+#ifndef _I386_DEBUGREG_H
+#define _I386_DEBUGREG_H
+
+
+/* Indicate the register numbers for a number of the specific
+   debug registers.  Registers 0-3 contain the addresses we wish to trap on */
+#define DR_FIRSTADDR 0        /* u_debugreg[DR_FIRSTADDR] */
+#define DR_LASTADDR 3         /* u_debugreg[DR_LASTADDR]  */
+
+#define DR_STATUS 6           /* u_debugreg[DR_STATUS]     */
+#define DR_CONTROL 7          /* u_debugreg[DR_CONTROL] */
+
+/* Define a few things for the status register.  We can use this to determine
+   which debugging register was responsible for the trap.  The other bits
+   are either reserved or not of interest to us. */
+
+#define DR_TRAP0        (0x1)           /* db0 */
+#define DR_TRAP1        (0x2)           /* db1 */
+#define DR_TRAP2        (0x4)           /* db2 */
+#define DR_TRAP3        (0x8)           /* db3 */
+
+#define DR_STEP         (0x4000)        /* single-step */
+#define DR_SWITCH       (0x8000)        /* task switch */
+
+/* Now define a bunch of things for manipulating the control register.
+   The top two bytes of the control register consist of 4 fields of 4
+   bits - each field corresponds to one of the four debug registers,
+   and indicates what types of access we trap on, and how large the data
+   field is that we are looking at */
+
+#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
+#define DR_CONTROL_SIZE 4   /* 4 control bits per register */
+
+#define DR_RW_EXECUTE (0x0)   /* Settings for the access types to trap on */
+#define DR_RW_WRITE (0x1)
+#define DR_RW_READ (0x3)
+
+#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
+#define DR_LEN_2 (0x4)
+#define DR_LEN_4 (0xC)
+
+/* The low byte to the control register determine which registers are
+   enabled.  There are 4 fields of two bits.  One bit is "local", meaning
+   that the processor will reset the bit after a task switch and the other
+   is global meaning that we have to explicitly reset the bit.  With linux,
+   you can use either one, since we explicitly zero the register when we enter
+   kernel mode. */
+
+#define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
+#define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
+#define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
+
+#define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
+#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
+
+/* The second byte to the control register has a few special things.
+   We can slow the instruction pipeline for instructions coming via the
+   gdt or the ldt if we want to.  I am not sure why this is an advantage */
+
+#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
+#define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
+#define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
+
+#endif
diff --git a/include/asm-x86/debugreg_64.h b/include/asm-x86/debugreg_64.h
new file mode 100644
index 000000000000..bd1aab1d8c4a
--- /dev/null
+++ b/include/asm-x86/debugreg_64.h
@@ -0,0 +1,65 @@
+#ifndef _X86_64_DEBUGREG_H
+#define _X86_64_DEBUGREG_H
+
+
+/* Indicate the register numbers for a number of the specific
+   debug registers.  Registers 0-3 contain the addresses we wish to trap on */
+#define DR_FIRSTADDR 0        /* u_debugreg[DR_FIRSTADDR] */
+#define DR_LASTADDR 3         /* u_debugreg[DR_LASTADDR]  */
+
+#define DR_STATUS 6           /* u_debugreg[DR_STATUS]     */
+#define DR_CONTROL 7          /* u_debugreg[DR_CONTROL] */
+
+/* Define a few things for the status register.  We can use this to determine
+   which debugging register was responsible for the trap.  The other bits
+   are either reserved or not of interest to us. */
+
+#define DR_TRAP0        (0x1)           /* db0 */
+#define DR_TRAP1        (0x2)           /* db1 */
+#define DR_TRAP2        (0x4)           /* db2 */
+#define DR_TRAP3        (0x8)           /* db3 */
+
+#define DR_STEP         (0x4000)        /* single-step */
+#define DR_SWITCH       (0x8000)        /* task switch */
+
+/* Now define a bunch of things for manipulating the control register.
+   The top two bytes of the control register consist of 4 fields of 4
+   bits - each field corresponds to one of the four debug registers,
+   and indicates what types of access we trap on, and how large the data
+   field is that we are looking at */
+
+#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
+#define DR_CONTROL_SIZE 4   /* 4 control bits per register */
+
+#define DR_RW_EXECUTE (0x0)   /* Settings for the access types to trap on */
+#define DR_RW_WRITE (0x1)
+#define DR_RW_READ (0x3)
+
+#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
+#define DR_LEN_2 (0x4)
+#define DR_LEN_4 (0xC)
+#define DR_LEN_8 (0x8)
+
+/* The low byte to the control register determine which registers are
+   enabled.  There are 4 fields of two bits.  One bit is "local", meaning
+   that the processor will reset the bit after a task switch and the other
+   is global meaning that we have to explicitly reset the bit.  With linux,
+   you can use either one, since we explicitly zero the register when we enter
+   kernel mode. */
+
+#define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
+#define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
+#define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
+
+#define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
+#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
+
+/* The second byte to the control register has a few special things.
+   We can slow the instruction pipeline for instructions coming via the
+   gdt or the ldt if we want to.  I am not sure why this is an advantage */
+
+#define DR_CONTROL_RESERVED (0xFFFFFFFF0000FC00UL) /* Reserved */
+#define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
+#define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
+
+#endif
diff --git a/include/asm-x86/delay.h b/include/asm-x86/delay.h
new file mode 100644
index 000000000000..10f2c71d622b
--- /dev/null
+++ b/include/asm-x86/delay.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "delay_32.h"
+#else
+# include "delay_64.h"
+#endif
diff --git a/include/asm-x86/delay_32.h b/include/asm-x86/delay_32.h
new file mode 100644
index 000000000000..9ae5e3782ed8
--- /dev/null
+++ b/include/asm-x86/delay_32.h
@@ -0,0 +1,31 @@
+#ifndef _I386_DELAY_H
+#define _I386_DELAY_H
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines calling functions in arch/i386/lib/delay.c
+ */
+ 
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long usecs);
+extern void __delay(unsigned long loops);
+
+/* 0x10c7 is 2**32 / 1000000 (rounded up) */
+#define udelay(n) (__builtin_constant_p(n) ? \
+        ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
+        __udelay(n))
+
+/* 0x5 is 2**32 / 1000000000 (rounded up) */
+#define ndelay(n) (__builtin_constant_p(n) ? \
+        ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
+        __ndelay(n))
+
+void use_tsc_delay(void);
+
+#endif /* defined(_I386_DELAY_H) */
diff --git a/include/asm-x86/delay_64.h b/include/asm-x86/delay_64.h
new file mode 100644
index 000000000000..c2669f1f5529
--- /dev/null
+++ b/include/asm-x86/delay_64.h
@@ -0,0 +1,30 @@
+#ifndef _X8664_DELAY_H
+#define _X8664_DELAY_H
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines calling functions in arch/x86_64/lib/delay.c
+ */
+ 
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long usecs);
+extern void __delay(unsigned long loops);
+
+/* 0x10c7 is 2**32 / 1000000 (rounded up) */
+#define udelay(n) (__builtin_constant_p(n) ? \
+        ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
+        __udelay(n))
+
+/* 0x5 is 2**32 / 1000000000 (rounded up) */
+#define ndelay(n) (__builtin_constant_p(n) ? \
+       ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
+       __ndelay(n))
+
+
+#endif /* defined(_X8664_DELAY_H) */
diff --git a/include/asm-x86/desc.h b/include/asm-x86/desc.h
new file mode 100644
index 000000000000..6065c5092265
--- /dev/null
+++ b/include/asm-x86/desc.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "desc_32.h"
+#else
+# include "desc_64.h"
+#endif
diff --git a/include/asm-x86/desc_32.h b/include/asm-x86/desc_32.h
new file mode 100644
index 000000000000..c547403f341d
--- /dev/null
+++ b/include/asm-x86/desc_32.h
@@ -0,0 +1,244 @@
+#ifndef __ARCH_DESC_H
+#define __ARCH_DESC_H
+
+#include <asm/ldt.h>
+#include <asm/segment.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/preempt.h>
+#include <linux/smp.h>
+#include <linux/percpu.h>
+
+#include <asm/mmu.h>
+
+struct Xgt_desc_struct {
+        unsigned short size;
+        unsigned long address __attribute__((packed));
+        unsigned short pad;
+} __attribute__ ((packed));
+
+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;
+}
+
+extern struct Xgt_desc_struct idt_descr;
+extern struct desc_struct idt_table[];
+extern void set_intr_gate(unsigned int irq, void * addr);
+
+static inline void pack_descriptor(__u32 *a, __u32 *b,
+        unsigned long base, unsigned long limit, unsigned char type, unsigned char flags)
+{
+        *a = ((base & 0xffff) << 16) | (limit & 0xffff);
+        *b = (base & 0xff000000) | ((base & 0xff0000) >> 16) |
+                (limit & 0x000f0000) | ((type & 0xff) << 8) | ((flags & 0xf) << 20);
+}
+
+static inline void pack_gate(__u32 *a, __u32 *b,
+        unsigned long base, unsigned short seg, unsigned char type, unsigned char flags)
+{
+        *a = (seg << 16) | (base & 0xffff);
+        *b = (base & 0xffff0000) | ((type & 0xff) << 8) | (flags & 0xff);
+}
+
+#define DESCTYPE_LDT    0x82    /* present, system, DPL-0, LDT */
+#define DESCTYPE_TSS    0x89    /* present, system, DPL-0, 32-bit TSS */
+#define DESCTYPE_TASK   0x85    /* present, system, DPL-0, task gate */
+#define DESCTYPE_INT    0x8e    /* present, system, DPL-0, interrupt gate */
+#define DESCTYPE_TRAP   0x8f    /* present, system, DPL-0, trap gate */
+#define DESCTYPE_DPL3   0x60    /* DPL-3 */
+#define DESCTYPE_S      0x10    /* !system */
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define load_TR_desc() native_load_tr_desc()
+#define load_gdt(dtr) native_load_gdt(dtr)
+#define load_idt(dtr) native_load_idt(dtr)
+#define load_tr(tr) __asm__ __volatile("ltr %0"::"m" (tr))
+#define load_ldt(ldt) __asm__ __volatile("lldt %0"::"m" (ldt))
+
+#define store_gdt(dtr) native_store_gdt(dtr)
+#define store_idt(dtr) native_store_idt(dtr)
+#define store_tr(tr) (tr = native_store_tr())
+#define store_ldt(ldt) __asm__ ("sldt %0":"=m" (ldt))
+
+#define load_TLS(t, cpu) native_load_tls(t, cpu)
+#define set_ldt native_set_ldt
+
+#define write_ldt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b)
+#define write_gdt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b)
+#define write_idt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b)
+#endif
+
+static inline void write_dt_entry(struct desc_struct *dt,
+                                  int entry, u32 entry_low, u32 entry_high)
+{
+        dt[entry].a = entry_low;
+        dt[entry].b = entry_high;
+}
+
+static inline void native_set_ldt(const void *addr, unsigned int entries)
+{
+        if (likely(entries == 0))
+                __asm__ __volatile__("lldt %w0"::"q" (0));
+        else {
+                unsigned cpu = smp_processor_id();
+                __u32 a, b;
+
+                pack_descriptor(&a, &b, (unsigned long)addr,
+                                entries * sizeof(struct desc_struct) - 1,
+                                DESCTYPE_LDT, 0);
+                write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, a, b);
+                __asm__ __volatile__("lldt %w0"::"q" (GDT_ENTRY_LDT*8));
+        }
+}
+
+
+static inline void native_load_tr_desc(void)
+{
+        asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
+}
+
+static inline void native_load_gdt(const struct Xgt_desc_struct *dtr)
+{
+        asm volatile("lgdt %0"::"m" (*dtr));
+}
+
+static inline void native_load_idt(const struct Xgt_desc_struct *dtr)
+{
+        asm volatile("lidt %0"::"m" (*dtr));
+}
+
+static inline void native_store_gdt(struct Xgt_desc_struct *dtr)
+{
+        asm ("sgdt %0":"=m" (*dtr));
+}
+
+static inline void native_store_idt(struct Xgt_desc_struct *dtr)
+{
+        asm ("sidt %0":"=m" (*dtr));
+}
+
+static inline unsigned long native_store_tr(void)
+{
+        unsigned long tr;
+        asm ("str %0":"=r" (tr));
+        return tr;
+}
+
+static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
+{
+        unsigned int i;
+        struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+
+        for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
+                gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
+}
+
+static inline void _set_gate(int gate, unsigned int type, void *addr, unsigned short seg)
+{
+        __u32 a, b;
+        pack_gate(&a, &b, (unsigned long)addr, seg, type, 0);
+        write_idt_entry(idt_table, gate, a, b);
+}
+
+static inline void __set_tss_desc(unsigned int cpu, unsigned int entry, const void *addr)
+{
+        __u32 a, b;
+        pack_descriptor(&a, &b, (unsigned long)addr,
+                        offsetof(struct tss_struct, __cacheline_filler) - 1,
+                        DESCTYPE_TSS, 0);
+        write_gdt_entry(get_cpu_gdt_table(cpu), entry, a, b);
+}
+
+
+#define set_tss_desc(cpu,addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr)
+
+#define LDT_entry_a(info) \
+        ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
+
+#define LDT_entry_b(info) \
+        (((info)->base_addr & 0xff000000) | \
+        (((info)->base_addr & 0x00ff0000) >> 16) | \
+        ((info)->limit & 0xf0000) | \
+        (((info)->read_exec_only ^ 1) << 9) | \
+        ((info)->contents << 10) | \
+        (((info)->seg_not_present ^ 1) << 15) | \
+        ((info)->seg_32bit << 22) | \
+        ((info)->limit_in_pages << 23) | \
+        ((info)->useable << 20) | \
+        0x7000)
+
+#define LDT_empty(info) (\
+        (info)->base_addr       == 0    && \
+        (info)->limit           == 0    && \
+        (info)->contents        == 0    && \
+        (info)->read_exec_only  == 1    && \
+        (info)->seg_32bit       == 0    && \
+        (info)->limit_in_pages  == 0    && \
+        (info)->seg_not_present == 1    && \
+        (info)->useable         == 0    )
+
+static inline void clear_LDT(void)
+{
+        set_ldt(NULL, 0);
+}
+
+/*
+ * load one particular LDT into the current CPU
+ */
+static inline void load_LDT_nolock(mm_context_t *pc)
+{
+        set_ldt(pc->ldt, pc->size);
+}
+
+static inline void load_LDT(mm_context_t *pc)
+{
+        preempt_disable();
+        load_LDT_nolock(pc);
+        preempt_enable();
+}
+
+static inline unsigned long get_desc_base(unsigned long *desc)
+{
+        unsigned long base;
+        base = ((desc[0] >> 16)  & 0x0000ffff) |
+                ((desc[1] << 16) & 0x00ff0000) |
+                (desc[1] & 0xff000000);
+        return base;
+}
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * GET_DESC_BASE reads the descriptor base of the specified segment.
+ *
+ * Args:
+ *    idx - descriptor index
+ *    gdt - GDT pointer
+ *    base - 32bit register to which the base will be written
+ *    lo_w - lo word of the "base" register
+ *    lo_b - lo byte of the "base" register
+ *    hi_b - hi byte of the low word of the "base" register
+ *
+ * Example:
+ *    GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah)
+ *    Will read the base address of GDT_ENTRY_ESPFIX_SS and put it into %eax.
+ */
+#define GET_DESC_BASE(idx, gdt, base, lo_w, lo_b, hi_b) \
+        movb idx*8+4(gdt), lo_b; \
+        movb idx*8+7(gdt), hi_b; \
+        shll $16, base; \
+        movw idx*8+2(gdt), lo_w;
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/include/asm-x86/desc_64.h b/include/asm-x86/desc_64.h
new file mode 100644
index 000000000000..ac991b5ca0fd
--- /dev/null
+++ b/include/asm-x86/desc_64.h
@@ -0,0 +1,174 @@
+/* Written 2000 by Andi Kleen */ 
+#ifndef __ARCH_DESC_H
+#define __ARCH_DESC_H
+
+#include <linux/threads.h>
+#include <asm/ldt.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/string.h>
+#include <linux/smp.h>
+#include <asm/desc_defs.h>
+
+#include <asm/segment.h>
+#include <asm/mmu.h>
+
+extern struct desc_struct cpu_gdt_table[GDT_ENTRIES];
+
+#define load_TR_desc() asm volatile("ltr %w0"::"r" (GDT_ENTRY_TSS*8))
+#define load_LDT_desc() asm volatile("lldt %w0"::"r" (GDT_ENTRY_LDT*8))
+#define clear_LDT()  asm volatile("lldt %w0"::"r" (0))
+
+/*
+ * This is the ldt that every process will get unless we need
+ * something other than this.
+ */
+extern struct desc_struct default_ldt[];
+extern struct gate_struct idt_table[]; 
+extern struct desc_ptr cpu_gdt_descr[];
+
+/* the cpu gdt accessor */
+#define cpu_gdt(_cpu) ((struct desc_struct *)cpu_gdt_descr[_cpu].address)
+
+static inline void _set_gate(void *adr, unsigned type, unsigned long func, unsigned dpl, unsigned ist)  
+{
+        struct gate_struct s;   
+        s.offset_low = PTR_LOW(func); 
+        s.segment = __KERNEL_CS;
+        s.ist = ist; 
+        s.p = 1;
+        s.dpl = dpl; 
+        s.zero0 = 0;
+        s.zero1 = 0; 
+        s.type = type; 
+        s.offset_middle = PTR_MIDDLE(func); 
+        s.offset_high = PTR_HIGH(func); 
+        /* does not need to be atomic because it is only done once at setup time */ 
+        memcpy(adr, &s, 16); 
+} 
+
+static inline void set_intr_gate(int nr, void *func) 
+{ 
+        BUG_ON((unsigned)nr > 0xFF);
+        _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, 0); 
+} 
+
+static inline void set_intr_gate_ist(int nr, void *func, unsigned ist) 
+{ 
+        BUG_ON((unsigned)nr > 0xFF);
+        _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, ist); 
+} 
+
+static inline void set_system_gate(int nr, void *func) 
+{ 
+        BUG_ON((unsigned)nr > 0xFF);
+        _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0); 
+} 
+
+static inline void set_system_gate_ist(int nr, void *func, unsigned ist)
+{
+        _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, ist);
+}
+
+static inline void set_tssldt_descriptor(void *ptr, unsigned long tss, unsigned type, 
+                                         unsigned size) 
+{ 
+        struct ldttss_desc d;
+        memset(&d,0,sizeof(d)); 
+        d.limit0 = size & 0xFFFF;
+        d.base0 = PTR_LOW(tss); 
+        d.base1 = PTR_MIDDLE(tss) & 0xFF; 
+        d.type = type;
+        d.p = 1; 
+        d.limit1 = (size >> 16) & 0xF;
+        d.base2 = (PTR_MIDDLE(tss) >> 8) & 0xFF; 
+        d.base3 = PTR_HIGH(tss); 
+        memcpy(ptr, &d, 16); 
+}
+
+static inline void set_tss_desc(unsigned cpu, void *addr)
+{ 
+        /*
+         * sizeof(unsigned long) coming from an extra "long" at the end
+         * of the iobitmap. See tss_struct definition in processor.h
+         *
+         * -1? seg base+limit should be pointing to the address of the
+         * last valid byte
+         */
+        set_tssldt_descriptor(&cpu_gdt(cpu)[GDT_ENTRY_TSS],
+                (unsigned long)addr, DESC_TSS,
+                IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1);
+} 
+
+static inline void set_ldt_desc(unsigned cpu, void *addr, int size)
+{ 
+        set_tssldt_descriptor(&cpu_gdt(cpu)[GDT_ENTRY_LDT], (unsigned long)addr,
+                              DESC_LDT, size * 8 - 1);
+}
+
+#define LDT_entry_a(info) \
+        ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
+/* Don't allow setting of the lm bit. It is useless anyways because 
+   64bit system calls require __USER_CS. */ 
+#define LDT_entry_b(info) \
+        (((info)->base_addr & 0xff000000) | \
+        (((info)->base_addr & 0x00ff0000) >> 16) | \
+        ((info)->limit & 0xf0000) | \
+        (((info)->read_exec_only ^ 1) << 9) | \
+        ((info)->contents << 10) | \
+        (((info)->seg_not_present ^ 1) << 15) | \
+        ((info)->seg_32bit << 22) | \
+        ((info)->limit_in_pages << 23) | \
+        ((info)->useable << 20) | \
+        /* ((info)->lm << 21) | */ \
+        0x7000)
+
+#define LDT_empty(info) (\
+        (info)->base_addr       == 0    && \
+        (info)->limit           == 0    && \
+        (info)->contents        == 0    && \
+        (info)->read_exec_only  == 1    && \
+        (info)->seg_32bit       == 0    && \
+        (info)->limit_in_pages  == 0    && \
+        (info)->seg_not_present == 1    && \
+        (info)->useable         == 0    && \
+        (info)->lm              == 0)
+
+static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
+{
+        unsigned int i;
+        u64 *gdt = (u64 *)(cpu_gdt(cpu) + GDT_ENTRY_TLS_MIN);
+
+        for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
+                gdt[i] = t->tls_array[i];
+} 
+
+/*
+ * load one particular LDT into the current CPU
+ */
+static inline void load_LDT_nolock (mm_context_t *pc, int cpu)
+{
+        int count = pc->size;
+
+        if (likely(!count)) {
+                clear_LDT();
+                return;
+        }
+                
+        set_ldt_desc(cpu, pc->ldt, count);
+        load_LDT_desc();
+}
+
+static inline void load_LDT(mm_context_t *pc)
+{
+        int cpu = get_cpu();
+        load_LDT_nolock(pc, cpu);
+        put_cpu();
+}
+
+extern struct desc_ptr idt_descr;
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/include/asm-x86/desc_defs.h b/include/asm-x86/desc_defs.h
new file mode 100644
index 000000000000..089004070099
--- /dev/null
+++ b/include/asm-x86/desc_defs.h
@@ -0,0 +1,69 @@
+/* Written 2000 by Andi Kleen */
+#ifndef __ARCH_DESC_DEFS_H
+#define __ARCH_DESC_DEFS_H
+
+/*
+ * Segment descriptor structure definitions, usable from both x86_64 and i386
+ * archs.
+ */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+// 8 byte segment descriptor
+struct desc_struct {
+        u16 limit0;
+        u16 base0;
+        unsigned base1 : 8, type : 4, s : 1, dpl : 2, p : 1;
+        unsigned limit : 4, avl : 1, l : 1, d : 1, g : 1, base2 : 8;
+} __attribute__((packed));
+
+struct n_desc_struct {
+        unsigned int a,b;
+};
+
+enum {
+        GATE_INTERRUPT = 0xE,
+        GATE_TRAP = 0xF,
+        GATE_CALL = 0xC,
+};
+
+// 16byte gate
+struct gate_struct {
+        u16 offset_low;
+        u16 segment;
+        unsigned ist : 3, zero0 : 5, type : 5, dpl : 2, p : 1;
+        u16 offset_middle;
+        u32 offset_high;
+        u32 zero1;
+} __attribute__((packed));
+
+#define PTR_LOW(x) ((unsigned long)(x) & 0xFFFF)
+#define PTR_MIDDLE(x) (((unsigned long)(x) >> 16) & 0xFFFF)
+#define PTR_HIGH(x) ((unsigned long)(x) >> 32)
+
+enum {
+        DESC_TSS = 0x9,
+        DESC_LDT = 0x2,
+};
+
+// LDT or TSS descriptor in the GDT. 16 bytes.
+struct ldttss_desc {
+        u16 limit0;
+        u16 base0;
+        unsigned base1 : 8, type : 5, dpl : 2, p : 1;
+        unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8;
+        u32 base3;
+        u32 zero1;
+} __attribute__((packed));
+
+struct desc_ptr {
+        unsigned short size;
+        unsigned long address;
+} __attribute__((packed)) ;
+
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/include/asm-x86/device.h b/include/asm-x86/device.h
new file mode 100644
index 000000000000..e2bcf7c7dcee
--- /dev/null
+++ b/include/asm-x86/device.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "device_32.h"
+#else
+# include "device_64.h"
+#endif
diff --git a/include/asm-x86/device_32.h b/include/asm-x86/device_32.h
new file mode 100644
index 000000000000..849604c70e6b
--- /dev/null
+++ b/include/asm-x86/device_32.h
@@ -0,0 +1,15 @@
+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#ifndef _ASM_I386_DEVICE_H
+#define _ASM_I386_DEVICE_H
+
+struct dev_archdata {
+#ifdef CONFIG_ACPI
+        void    *acpi_handle;
+#endif
+};
+
+#endif /* _ASM_I386_DEVICE_H */
diff --git a/include/asm-x86/device_64.h b/include/asm-x86/device_64.h
new file mode 100644
index 000000000000..3afa03f33a36
--- /dev/null
+++ b/include/asm-x86/device_64.h
@@ -0,0 +1,15 @@
+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#ifndef _ASM_X86_64_DEVICE_H
+#define _ASM_X86_64_DEVICE_H
+
+struct dev_archdata {
+#ifdef CONFIG_ACPI
+        void    *acpi_handle;
+#endif
+};
+
+#endif /* _ASM_X86_64_DEVICE_H */
diff --git a/include/asm-x86/div64.h b/include/asm-x86/div64.h
new file mode 100644
index 000000000000..8ac7da6ca284
--- /dev/null
+++ b/include/asm-x86/div64.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "div64_32.h"
+#else
+# include "div64_64.h"
+#endif
diff --git a/include/asm-x86/div64_32.h b/include/asm-x86/div64_32.h
new file mode 100644
index 000000000000..438e980068bd
--- /dev/null
+++ b/include/asm-x86/div64_32.h
@@ -0,0 +1,52 @@
+#ifndef __I386_DIV64
+#define __I386_DIV64
+
+#include <linux/types.h>
+
+/*
+ * do_div() is NOT a C function. It wants to return
+ * two values (the quotient and the remainder), but
+ * since that doesn't work very well in C, what it
+ * does is:
+ *
+ * - modifies the 64-bit dividend _in_place_
+ * - returns the 32-bit remainder
+ *
+ * This ends up being the most efficient "calling
+ * convention" on x86.
+ */
+#define do_div(n,base) ({ \
+        unsigned long __upper, __low, __high, __mod, __base; \
+        __base = (base); \
+        asm("":"=a" (__low), "=d" (__high):"A" (n)); \
+        __upper = __high; \
+        if (__high) { \
+                __upper = __high % (__base); \
+                __high = __high / (__base); \
+        } \
+        asm("divl %2":"=a" (__low), "=d" (__mod):"rm" (__base), "0" (__low), "1" (__upper)); \
+        asm("":"=A" (n):"a" (__low),"d" (__high)); \
+        __mod; \
+})
+
+/*
+ * (long)X = ((long long)divs) / (long)div
+ * (long)rem = ((long long)divs) % (long)div
+ *
+ * Warning, this will do an exception if X overflows.
+ */
+#define div_long_long_rem(a,b,c) div_ll_X_l_rem(a,b,c)
+
+static inline long
+div_ll_X_l_rem(long long divs, long div, long *rem)
+{
+        long dum2;
+      __asm__("divl %2":"=a"(dum2), "=d"(*rem)
+      : "rm"(div), "A"(divs));
+
+        return dum2;
+
+}
+
+extern uint64_t div64_64(uint64_t dividend, uint64_t divisor);
+#endif
diff --git a/include/asm-x86/div64_64.h b/include/asm-x86/div64_64.h
new file mode 100644
index 000000000000..6cd978cefb28
--- /dev/null
+++ b/include/asm-x86/div64_64.h
@@ -0,0 +1 @@
+#include <asm-generic/div64.h>
diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
new file mode 100644
index 000000000000..58f790f4df52
--- /dev/null
+++ b/include/asm-x86/dma-mapping.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "dma-mapping_32.h"
+#else
+# include "dma-mapping_64.h"
+#endif
diff --git a/include/asm-x86/dma-mapping_32.h b/include/asm-x86/dma-mapping_32.h
new file mode 100644
index 000000000000..f1d72d177f68
--- /dev/null
+++ b/include/asm-x86/dma-mapping_32.h
@@ -0,0 +1,186 @@
+#ifndef _ASM_I386_DMA_MAPPING_H
+#define _ASM_I386_DMA_MAPPING_H
+
+#include <linux/mm.h>
+
+#include <asm/cache.h>
+#include <asm/io.h>
+#include <asm/scatterlist.h>
+#include <asm/bug.h>
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+void *dma_alloc_coherent(struct device *dev, size_t size,
+                           dma_addr_t *dma_handle, gfp_t flag);
+
+void dma_free_coherent(struct device *dev, size_t size,
+                         void *vaddr, dma_addr_t dma_handle);
+
+static inline dma_addr_t
+dma_map_single(struct device *dev, void *ptr, size_t size,
+               enum dma_data_direction direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        WARN_ON(size == 0);
+        flush_write_buffers();
+        return virt_to_phys(ptr);
+}
+
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+                 enum dma_data_direction direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+}
+
+static inline int
+dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+           enum dma_data_direction direction)
+{
+        int i;
+
+        BUG_ON(!valid_dma_direction(direction));
+        WARN_ON(nents == 0 || sg[0].length == 0);
+
+        for (i = 0; i < nents; i++ ) {
+                BUG_ON(!sg[i].page);
+
+                sg[i].dma_address = page_to_phys(sg[i].page) + sg[i].offset;
+        }
+
+        flush_write_buffers();
+        return nents;
+}
+
+static inline dma_addr_t
+dma_map_page(struct device *dev, struct page *page, unsigned long offset,
+             size_t size, enum dma_data_direction direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        return page_to_phys(page) + offset;
+}
+
+static inline void
+dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
+               enum dma_data_direction direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+}
+
+
+static inline void
+dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
+             enum dma_data_direction direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+}
+
+static inline void
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
+                        enum dma_data_direction direction)
+{
+}
+
+static inline void
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
+                        enum dma_data_direction direction)
+{
+        flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
+                              unsigned long offset, size_t size,
+                              enum dma_data_direction direction)
+{
+}
+
+static inline void
+dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
+                                 unsigned long offset, size_t size,
+                                 enum dma_data_direction direction)
+{
+        flush_write_buffers();
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+                    enum dma_data_direction direction)
+{
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
+                    enum dma_data_direction direction)
+{
+        flush_write_buffers();
+}
+
+static inline int
+dma_mapping_error(dma_addr_t dma_addr)
+{
+        return 0;
+}
+
+extern int forbid_dac;
+
+static inline int
+dma_supported(struct device *dev, u64 mask)
+{
+        /*
+         * we fall back to GFP_DMA when the mask isn't all 1s,
+         * so we can't guarantee allocations that must be
+         * within a tighter range than GFP_DMA..
+         */
+        if(mask < 0x00ffffff)
+                return 0;
+
+        /* Work around chipset bugs */
+        if (forbid_dac > 0 && mask > 0xffffffffULL)
+                return 0;
+
+        return 1;
+}
+
+static inline int
+dma_set_mask(struct device *dev, u64 mask)
+{
+        if(!dev->dma_mask || !dma_supported(dev, mask))
+                return -EIO;
+
+        *dev->dma_mask = mask;
+
+        return 0;
+}
+
+static inline int
+dma_get_cache_alignment(void)
+{
+        /* no easy way to get cache size on all x86, so return the
+         * maximum possible, to be safe */
+        return (1 << INTERNODE_CACHE_SHIFT);
+}
+
+#define dma_is_consistent(d, h) (1)
+
+static inline void
+dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+               enum dma_data_direction direction)
+{
+        flush_write_buffers();
+}
+
+#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+extern int
+dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+                            dma_addr_t device_addr, size_t size, int flags);
+
+extern void
+dma_release_declared_memory(struct device *dev);
+
+extern void *
+dma_mark_declared_memory_occupied(struct device *dev,
+                                  dma_addr_t device_addr, size_t size);
+
+#endif
diff --git a/include/asm-x86/dma-mapping_64.h b/include/asm-x86/dma-mapping_64.h
new file mode 100644
index 000000000000..6897e2a436e5
--- /dev/null
+++ b/include/asm-x86/dma-mapping_64.h
@@ -0,0 +1,203 @@
+#ifndef _X8664_DMA_MAPPING_H
+#define _X8664_DMA_MAPPING_H 1
+
+/*
+ * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for
+ * documentation.
+ */
+
+
+#include <asm/scatterlist.h>
+#include <asm/io.h>
+#include <asm/swiotlb.h>
+
+struct dma_mapping_ops {
+        int             (*mapping_error)(dma_addr_t dma_addr);
+        void*           (*alloc_coherent)(struct device *dev, size_t size,
+                                dma_addr_t *dma_handle, gfp_t gfp);
+        void            (*free_coherent)(struct device *dev, size_t size,
+                                void *vaddr, dma_addr_t dma_handle);
+        dma_addr_t      (*map_single)(struct device *hwdev, void *ptr,
+                                size_t size, int direction);
+        /* like map_single, but doesn't check the device mask */
+        dma_addr_t      (*map_simple)(struct device *hwdev, char *ptr,
+                                size_t size, int direction);
+        void            (*unmap_single)(struct device *dev, dma_addr_t addr,
+                                size_t size, int direction);
+        void            (*sync_single_for_cpu)(struct device *hwdev,
+                                dma_addr_t dma_handle, size_t size,
+                                int direction);
+        void            (*sync_single_for_device)(struct device *hwdev,
+                                dma_addr_t dma_handle, size_t size,
+                                int direction);
+        void            (*sync_single_range_for_cpu)(struct device *hwdev,
+                                dma_addr_t dma_handle, unsigned long offset,
+                                size_t size, int direction);
+        void            (*sync_single_range_for_device)(struct device *hwdev,
+                                dma_addr_t dma_handle, unsigned long offset,
+                                size_t size, int direction);
+        void            (*sync_sg_for_cpu)(struct device *hwdev,
+                                struct scatterlist *sg, int nelems,
+                                int direction);
+        void            (*sync_sg_for_device)(struct device *hwdev,
+                                struct scatterlist *sg, int nelems,
+                                int direction);
+        int             (*map_sg)(struct device *hwdev, struct scatterlist *sg,
+                                int nents, int direction);
+        void            (*unmap_sg)(struct device *hwdev,
+                                struct scatterlist *sg, int nents,
+                                int direction);
+        int             (*dma_supported)(struct device *hwdev, u64 mask);
+        int             is_phys;
+};
+
+extern dma_addr_t bad_dma_address;
+extern const struct dma_mapping_ops* dma_ops;
+extern int iommu_merge;
+
+static inline int dma_mapping_error(dma_addr_t dma_addr)
+{
+        if (dma_ops->mapping_error)
+                return dma_ops->mapping_error(dma_addr);
+
+        return (dma_addr == bad_dma_address);
+}
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+extern void *dma_alloc_coherent(struct device *dev, size_t size,
+                                dma_addr_t *dma_handle, gfp_t gfp);
+extern void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
+                              dma_addr_t dma_handle);
+
+static inline dma_addr_t
+dma_map_single(struct device *hwdev, void *ptr, size_t size,
+               int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        return dma_ops->map_single(hwdev, ptr, size, direction);
+}
+
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
+                 int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        dma_ops->unmap_single(dev, addr, size, direction);
+}
+
+#define dma_map_page(dev,page,offset,size,dir) \
+        dma_map_single((dev), page_address(page)+(offset), (size), (dir))
+
+#define dma_unmap_page dma_unmap_single
+
+static inline void
+dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
+                        size_t size, int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        if (dma_ops->sync_single_for_cpu)
+                dma_ops->sync_single_for_cpu(hwdev, dma_handle, size,
+                                             direction);
+        flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
+                           size_t size, int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        if (dma_ops->sync_single_for_device)
+                dma_ops->sync_single_for_device(hwdev, dma_handle, size,
+                                                direction);
+        flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
+                              unsigned long offset, size_t size, int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        if (dma_ops->sync_single_range_for_cpu) {
+                dma_ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, size, direction);
+        }
+
+        flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
+                                 unsigned long offset, size_t size, int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        if (dma_ops->sync_single_range_for_device)
+                dma_ops->sync_single_range_for_device(hwdev, dma_handle,
+                                                      offset, size, direction);
+
+        flush_write_buffers();
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+                    int nelems, int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        if (dma_ops->sync_sg_for_cpu)
+                dma_ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
+        flush_write_buffers();
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+                       int nelems, int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        if (dma_ops->sync_sg_for_device) {
+                dma_ops->sync_sg_for_device(hwdev, sg, nelems, direction);
+        }
+
+        flush_write_buffers();
+}
+
+static inline int
+dma_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        return dma_ops->map_sg(hwdev, sg, nents, direction);
+}
+
+static inline void
+dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
+             int direction)
+{
+        BUG_ON(!valid_dma_direction(direction));
+        dma_ops->unmap_sg(hwdev, sg, nents, direction);
+}
+
+extern int dma_supported(struct device *hwdev, u64 mask);
+
+/* same for gart, swiotlb, and nommu */
+static inline int dma_get_cache_alignment(void)
+{
+        return boot_cpu_data.x86_clflush_size;
+}
+
+#define dma_is_consistent(d, h) 1
+
+extern int dma_set_mask(struct device *dev, u64 mask);
+
+static inline void
+dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+        enum dma_data_direction dir)
+{
+        flush_write_buffers();
+}
+
+extern struct device fallback_dev;
+extern int panic_on_overflow;
+
+#endif /* _X8664_DMA_MAPPING_H */
diff --git a/include/asm-x86/dma.h b/include/asm-x86/dma.h
new file mode 100644
index 000000000000..9f936c61a4e5
--- /dev/null
+++ b/include/asm-x86/dma.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "dma_32.h"
+#else
+# include "dma_64.h"
+#endif
diff --git a/include/asm-x86/dma_32.h b/include/asm-x86/dma_32.h
new file mode 100644
index 000000000000..d23aac8e1a50
--- /dev/null
+++ b/include/asm-x86/dma_32.h
@@ -0,0 +1,297 @@
+/* $Id: dma.h,v 1.7 1992/12/14 00:29:34 root Exp root $
+ * linux/include/asm/dma.h: Defines for using and allocating dma channels.
+ * Written by Hennus Bergman, 1992.
+ * High DMA channel support & info by Hannu Savolainen
+ * and John Boyd, Nov. 1992.
+ */
+
+#ifndef _ASM_DMA_H
+#define _ASM_DMA_H
+
+#include <linux/spinlock.h>     /* And spinlocks */
+#include <asm/io.h>             /* need byte IO */
+#include <linux/delay.h>
+
+
+#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
+#define dma_outb        outb_p
+#else
+#define dma_outb        outb
+#endif
+
+#define dma_inb         inb
+
+/*
+ * NOTES about DMA transfers:
+ *
+ *  controller 1: channels 0-3, byte operations, ports 00-1F
+ *  controller 2: channels 4-7, word operations, ports C0-DF
+ *
+ *  - ALL registers are 8 bits only, regardless of transfer size
+ *  - channel 4 is not used - cascades 1 into 2.
+ *  - channels 0-3 are byte - addresses/counts are for physical bytes
+ *  - channels 5-7 are word - addresses/counts are for physical words
+ *  - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
+ *  - transfer count loaded to registers is 1 less than actual count
+ *  - controller 2 offsets are all even (2x offsets for controller 1)
+ *  - page registers for 5-7 don't use data bit 0, represent 128K pages
+ *  - page registers for 0-3 use bit 0, represent 64K pages
+ *
+ * DMA transfers are limited to the lower 16MB of _physical_ memory.  
+ * Note that addresses loaded into registers must be _physical_ addresses,
+ * not logical addresses (which may differ if paging is active).
+ *
+ *  Address mapping for channels 0-3:
+ *
+ *   A23 ... A16 A15 ... A8  A7 ... A0    (Physical addresses)
+ *    |  ...  |   |  ... |   |  ... |
+ *    |  ...  |   |  ... |   |  ... |
+ *    |  ...  |   |  ... |   |  ... |
+ *   P7  ...  P0  A7 ... A0  A7 ... A0   
+ * |    Page    | Addr MSB | Addr LSB |   (DMA registers)
+ *
+ *  Address mapping for channels 5-7:
+ *
+ *   A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0    (Physical addresses)
+ *    |  ...  |   \   \   ... \  \  \  ... \  \
+ *    |  ...  |    \   \   ... \  \  \  ... \  (not used)
+ *    |  ...  |     \   \   ... \  \  \  ... \
+ *   P7  ...  P1 (0) A7 A6  ... A0 A7 A6 ... A0   
+ * |      Page      |  Addr MSB   |  Addr LSB  |   (DMA registers)
+ *
+ * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
+ * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
+ * the hardware level, so odd-byte transfers aren't possible).
+ *
+ * Transfer count (_not # bytes_) is limited to 64K, represented as actual
+ * count - 1 : 64K => 0xFFFF, 1 => 0x0000.  Thus, count is always 1 or more,
+ * and up to 128K bytes may be transferred on channels 5-7 in one operation. 
+ *
+ */
+
+#define MAX_DMA_CHANNELS        8
+
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS      (PAGE_OFFSET+0x1000000)
+
+/* 8237 DMA controllers */
+#define IO_DMA1_BASE    0x00    /* 8 bit slave DMA, channels 0..3 */
+#define IO_DMA2_BASE    0xC0    /* 16 bit master DMA, ch 4(=slave input)..7 */
+
+/* DMA controller registers */
+#define DMA1_CMD_REG            0x08    /* command register (w) */
+#define DMA1_STAT_REG           0x08    /* status register (r) */
+#define DMA1_REQ_REG            0x09    /* request register (w) */
+#define DMA1_MASK_REG           0x0A    /* single-channel mask (w) */
+#define DMA1_MODE_REG           0x0B    /* mode register (w) */
+#define DMA1_CLEAR_FF_REG       0x0C    /* clear pointer flip-flop (w) */
+#define DMA1_TEMP_REG           0x0D    /* Temporary Register (r) */
+#define DMA1_RESET_REG          0x0D    /* Master Clear (w) */
+#define DMA1_CLR_MASK_REG       0x0E    /* Clear Mask */
+#define DMA1_MASK_ALL_REG       0x0F    /* all-channels mask (w) */
+
+#define DMA2_CMD_REG            0xD0    /* command register (w) */
+#define DMA2_STAT_REG           0xD0    /* status register (r) */
+#define DMA2_REQ_REG            0xD2    /* request register (w) */
+#define DMA2_MASK_REG           0xD4    /* single-channel mask (w) */
+#define DMA2_MODE_REG           0xD6    /* mode register (w) */
+#define DMA2_CLEAR_FF_REG       0xD8    /* clear pointer flip-flop (w) */
+#define DMA2_TEMP_REG           0xDA    /* Temporary Register (r) */
+#define DMA2_RESET_REG          0xDA    /* Master Clear (w) */
+#define DMA2_CLR_MASK_REG       0xDC    /* Clear Mask */
+#define DMA2_MASK_ALL_REG       0xDE    /* all-channels mask (w) */
+
+#define DMA_ADDR_0              0x00    /* DMA address registers */
+#define DMA_ADDR_1              0x02
+#define DMA_ADDR_2              0x04
+#define DMA_ADDR_3              0x06
+#define DMA_ADDR_4              0xC0
+#define DMA_ADDR_5              0xC4
+#define DMA_ADDR_6              0xC8
+#define DMA_ADDR_7              0xCC
+
+#define DMA_CNT_0               0x01    /* DMA count registers */
+#define DMA_CNT_1               0x03
+#define DMA_CNT_2               0x05
+#define DMA_CNT_3               0x07
+#define DMA_CNT_4               0xC2
+#define DMA_CNT_5               0xC6
+#define DMA_CNT_6               0xCA
+#define DMA_CNT_7               0xCE
+
+#define DMA_PAGE_0              0x87    /* DMA page registers */
+#define DMA_PAGE_1              0x83
+#define DMA_PAGE_2              0x81
+#define DMA_PAGE_3              0x82
+#define DMA_PAGE_5              0x8B
+#define DMA_PAGE_6              0x89
+#define DMA_PAGE_7              0x8A
+
+#define DMA_MODE_READ   0x44    /* I/O to memory, no autoinit, increment, single mode */
+#define DMA_MODE_WRITE  0x48    /* memory to I/O, no autoinit, increment, single mode */
+#define DMA_MODE_CASCADE 0xC0   /* pass thru DREQ->HRQ, DACK<-HLDA only */
+
+#define DMA_AUTOINIT    0x10
+
+
+extern spinlock_t  dma_spin_lock;
+
+static __inline__ unsigned long claim_dma_lock(void)
+{
+        unsigned long flags;
+        spin_lock_irqsave(&dma_spin_lock, flags);
+        return flags;
+}
+
+static __inline__ void release_dma_lock(unsigned long flags)
+{
+        spin_unlock_irqrestore(&dma_spin_lock, flags);
+}
+
+/* enable/disable a specific DMA channel */
+static __inline__ void enable_dma(unsigned int dmanr)
+{
+        if (dmanr<=3)
+                dma_outb(dmanr,  DMA1_MASK_REG);
+        else
+                dma_outb(dmanr & 3,  DMA2_MASK_REG);
+}
+
+static __inline__ void disable_dma(unsigned int dmanr)
+{
+        if (dmanr<=3)
+                dma_outb(dmanr | 4,  DMA1_MASK_REG);
+        else
+                dma_outb((dmanr & 3) | 4,  DMA2_MASK_REG);
+}
+
+/* Clear the 'DMA Pointer Flip Flop'.
+ * Write 0 for LSB/MSB, 1 for MSB/LSB access.
+ * Use this once to initialize the FF to a known state.
+ * After that, keep track of it. :-)
+ * --- In order to do that, the DMA routines below should ---
+ * --- only be used while holding the DMA lock ! ---
+ */
+static __inline__ void clear_dma_ff(unsigned int dmanr)
+{
+        if (dmanr<=3)
+                dma_outb(0,  DMA1_CLEAR_FF_REG);
+        else
+                dma_outb(0,  DMA2_CLEAR_FF_REG);
+}
+
+/* set mode (above) for a specific DMA channel */
+static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
+{
+        if (dmanr<=3)
+                dma_outb(mode | dmanr,  DMA1_MODE_REG);
+        else
+                dma_outb(mode | (dmanr&3),  DMA2_MODE_REG);
+}
+
+/* Set only the page register bits of the transfer address.
+ * This is used for successive transfers when we know the contents of
+ * the lower 16 bits of the DMA current address register, but a 64k boundary
+ * may have been crossed.
+ */
+static __inline__ void set_dma_page(unsigned int dmanr, char pagenr)
+{
+        switch(dmanr) {
+                case 0:
+                        dma_outb(pagenr, DMA_PAGE_0);
+                        break;
+                case 1:
+                        dma_outb(pagenr, DMA_PAGE_1);
+                        break;
+                case 2:
+                        dma_outb(pagenr, DMA_PAGE_2);
+                        break;
+                case 3:
+                        dma_outb(pagenr, DMA_PAGE_3);
+                        break;
+                case 5:
+                        dma_outb(pagenr & 0xfe, DMA_PAGE_5);
+                        break;
+                case 6:
+                        dma_outb(pagenr & 0xfe, DMA_PAGE_6);
+                        break;
+                case 7:
+                        dma_outb(pagenr & 0xfe, DMA_PAGE_7);
+                        break;
+        }
+}
+
+
+/* Set transfer address & page bits for specific DMA channel.
+ * Assumes dma flipflop is clear.
+ */
+static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+        set_dma_page(dmanr, a>>16);
+        if (dmanr <= 3)  {
+            dma_outb( a & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
+            dma_outb( (a>>8) & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
+        }  else  {
+            dma_outb( (a>>1) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
+            dma_outb( (a>>9) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
+        }
+}
+
+
+/* Set transfer size (max 64k for DMA0..3, 128k for DMA5..7) for
+ * a specific DMA channel.
+ * You must ensure the parameters are valid.
+ * NOTE: from a manual: "the number of transfers is one more
+ * than the initial word count"! This is taken into account.
+ * Assumes dma flip-flop is clear.
+ * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
+ */
+static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
+{
+        count--;
+        if (dmanr <= 3)  {
+            dma_outb( count & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
+            dma_outb( (count>>8) & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
+        } else {
+            dma_outb( (count>>1) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
+            dma_outb( (count>>9) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
+        }
+}
+
+
+/* Get DMA residue count. After a DMA transfer, this
+ * should return zero. Reading this while a DMA transfer is
+ * still in progress will return unpredictable results.
+ * If called before the channel has been used, it may return 1.
+ * Otherwise, it returns the number of _bytes_ left to transfer.
+ *
+ * Assumes DMA flip-flop is clear.
+ */
+static __inline__ int get_dma_residue(unsigned int dmanr)
+{
+        unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE
+                                         : ((dmanr&3)<<2) + 2 + IO_DMA2_BASE;
+
+        /* using short to get 16-bit wrap around */
+        unsigned short count;
+
+        count = 1 + dma_inb(io_port);
+        count += dma_inb(io_port) << 8;
+        
+        return (dmanr<=3)? count : (count<<1);
+}
+
+
+/* These are in kernel/dma.c: */
+extern int request_dma(unsigned int dmanr, const char * device_id);     /* reserve a DMA channel */
+extern void free_dma(unsigned int dmanr);       /* release it again */
+
+/* From PCI */
+
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy    (0)
+#endif
+
+#endif /* _ASM_DMA_H */
diff --git a/include/asm-x86/dma_64.h b/include/asm-x86/dma_64.h
new file mode 100644
index 000000000000..a37c16f06289
--- /dev/null
+++ b/include/asm-x86/dma_64.h
@@ -0,0 +1,304 @@
+/*
+ * linux/include/asm/dma.h: Defines for using and allocating dma channels.
+ * Written by Hennus Bergman, 1992.
+ * High DMA channel support & info by Hannu Savolainen
+ * and John Boyd, Nov. 1992.
+ */
+
+#ifndef _ASM_DMA_H
+#define _ASM_DMA_H
+
+#include <linux/spinlock.h>     /* And spinlocks */
+#include <asm/io.h>             /* need byte IO */
+#include <linux/delay.h>
+
+
+#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
+#define dma_outb        outb_p
+#else
+#define dma_outb        outb
+#endif
+
+#define dma_inb         inb
+
+/*
+ * NOTES about DMA transfers:
+ *
+ *  controller 1: channels 0-3, byte operations, ports 00-1F
+ *  controller 2: channels 4-7, word operations, ports C0-DF
+ *
+ *  - ALL registers are 8 bits only, regardless of transfer size
+ *  - channel 4 is not used - cascades 1 into 2.
+ *  - channels 0-3 are byte - addresses/counts are for physical bytes
+ *  - channels 5-7 are word - addresses/counts are for physical words
+ *  - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
+ *  - transfer count loaded to registers is 1 less than actual count
+ *  - controller 2 offsets are all even (2x offsets for controller 1)
+ *  - page registers for 5-7 don't use data bit 0, represent 128K pages
+ *  - page registers for 0-3 use bit 0, represent 64K pages
+ *
+ * DMA transfers are limited to the lower 16MB of _physical_ memory.  
+ * Note that addresses loaded into registers must be _physical_ addresses,
+ * not logical addresses (which may differ if paging is active).
+ *
+ *  Address mapping for channels 0-3:
+ *
+ *   A23 ... A16 A15 ... A8  A7 ... A0    (Physical addresses)
+ *    |  ...  |   |  ... |   |  ... |
+ *    |  ...  |   |  ... |   |  ... |
+ *    |  ...  |   |  ... |   |  ... |
+ *   P7  ...  P0  A7 ... A0  A7 ... A0   
+ * |    Page    | Addr MSB | Addr LSB |   (DMA registers)
+ *
+ *  Address mapping for channels 5-7:
+ *
+ *   A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0    (Physical addresses)
+ *    |  ...  |   \   \   ... \  \  \  ... \  \
+ *    |  ...  |    \   \   ... \  \  \  ... \  (not used)
+ *    |  ...  |     \   \   ... \  \  \  ... \
+ *   P7  ...  P1 (0) A7 A6  ... A0 A7 A6 ... A0   
+ * |      Page      |  Addr MSB   |  Addr LSB  |   (DMA registers)
+ *
+ * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
+ * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
+ * the hardware level, so odd-byte transfers aren't possible).
+ *
+ * Transfer count (_not # bytes_) is limited to 64K, represented as actual
+ * count - 1 : 64K => 0xFFFF, 1 => 0x0000.  Thus, count is always 1 or more,
+ * and up to 128K bytes may be transferred on channels 5-7 in one operation. 
+ *
+ */
+
+#define MAX_DMA_CHANNELS        8
+
+
+/* 16MB ISA DMA zone */
+#define MAX_DMA_PFN   ((16*1024*1024) >> PAGE_SHIFT)
+
+/* 4GB broken PCI/AGP hardware bus master zone */
+#define MAX_DMA32_PFN ((4UL*1024*1024*1024) >> PAGE_SHIFT)
+
+/* Compat define for old dma zone */
+#define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
+
+/* 8237 DMA controllers */
+#define IO_DMA1_BASE    0x00    /* 8 bit slave DMA, channels 0..3 */
+#define IO_DMA2_BASE    0xC0    /* 16 bit master DMA, ch 4(=slave input)..7 */
+
+/* DMA controller registers */
+#define DMA1_CMD_REG            0x08    /* command register (w) */
+#define DMA1_STAT_REG           0x08    /* status register (r) */
+#define DMA1_REQ_REG            0x09    /* request register (w) */
+#define DMA1_MASK_REG           0x0A    /* single-channel mask (w) */
+#define DMA1_MODE_REG           0x0B    /* mode register (w) */
+#define DMA1_CLEAR_FF_REG       0x0C    /* clear pointer flip-flop (w) */
+#define DMA1_TEMP_REG           0x0D    /* Temporary Register (r) */
+#define DMA1_RESET_REG          0x0D    /* Master Clear (w) */
+#define DMA1_CLR_MASK_REG       0x0E    /* Clear Mask */
+#define DMA1_MASK_ALL_REG       0x0F    /* all-channels mask (w) */
+
+#define DMA2_CMD_REG            0xD0    /* command register (w) */
+#define DMA2_STAT_REG           0xD0    /* status register (r) */
+#define DMA2_REQ_REG            0xD2    /* request register (w) */
+#define DMA2_MASK_REG           0xD4    /* single-channel mask (w) */
+#define DMA2_MODE_REG           0xD6    /* mode register (w) */
+#define DMA2_CLEAR_FF_REG       0xD8    /* clear pointer flip-flop (w) */
+#define DMA2_TEMP_REG           0xDA    /* Temporary Register (r) */
+#define DMA2_RESET_REG          0xDA    /* Master Clear (w) */
+#define DMA2_CLR_MASK_REG       0xDC    /* Clear Mask */
+#define DMA2_MASK_ALL_REG       0xDE    /* all-channels mask (w) */
+
+#define DMA_ADDR_0              0x00    /* DMA address registers */
+#define DMA_ADDR_1              0x02
+#define DMA_ADDR_2              0x04
+#define DMA_ADDR_3              0x06
+#define DMA_ADDR_4              0xC0
+#define DMA_ADDR_5              0xC4
+#define DMA_ADDR_6              0xC8
+#define DMA_ADDR_7              0xCC
+
+#define DMA_CNT_0               0x01    /* DMA count registers */
+#define DMA_CNT_1               0x03
+#define DMA_CNT_2               0x05
+#define DMA_CNT_3               0x07
+#define DMA_CNT_4               0xC2
+#define DMA_CNT_5               0xC6
+#define DMA_CNT_6               0xCA
+#define DMA_CNT_7               0xCE
+
+#define DMA_PAGE_0              0x87    /* DMA page registers */
+#define DMA_PAGE_1              0x83
+#define DMA_PAGE_2              0x81
+#define DMA_PAGE_3              0x82
+#define DMA_PAGE_5              0x8B
+#define DMA_PAGE_6              0x89
+#define DMA_PAGE_7              0x8A
+
+#define DMA_MODE_READ   0x44    /* I/O to memory, no autoinit, increment, single mode */
+#define DMA_MODE_WRITE  0x48    /* memory to I/O, no autoinit, increment, single mode */
+#define DMA_MODE_CASCADE 0xC0   /* pass thru DREQ->HRQ, DACK<-HLDA only */
+
+#define DMA_AUTOINIT    0x10
+
+
+extern spinlock_t  dma_spin_lock;
+
+static __inline__ unsigned long claim_dma_lock(void)
+{
+        unsigned long flags;
+        spin_lock_irqsave(&dma_spin_lock, flags);
+        return flags;
+}
+
+static __inline__ void release_dma_lock(unsigned long flags)
+{
+        spin_unlock_irqrestore(&dma_spin_lock, flags);
+}
+
+/* enable/disable a specific DMA channel */
+static __inline__ void enable_dma(unsigned int dmanr)
+{
+        if (dmanr<=3)
+                dma_outb(dmanr,  DMA1_MASK_REG);
+        else
+                dma_outb(dmanr & 3,  DMA2_MASK_REG);
+}
+
+static __inline__ void disable_dma(unsigned int dmanr)
+{
+        if (dmanr<=3)
+                dma_outb(dmanr | 4,  DMA1_MASK_REG);
+        else
+                dma_outb((dmanr & 3) | 4,  DMA2_MASK_REG);
+}
+
+/* Clear the 'DMA Pointer Flip Flop'.
+ * Write 0 for LSB/MSB, 1 for MSB/LSB access.
+ * Use this once to initialize the FF to a known state.
+ * After that, keep track of it. :-)
+ * --- In order to do that, the DMA routines below should ---
+ * --- only be used while holding the DMA lock ! ---
+ */
+static __inline__ void clear_dma_ff(unsigned int dmanr)
+{
+        if (dmanr<=3)
+                dma_outb(0,  DMA1_CLEAR_FF_REG);
+        else
+                dma_outb(0,  DMA2_CLEAR_FF_REG);
+}
+
+/* set mode (above) for a specific DMA channel */
+static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
+{
+        if (dmanr<=3)
+                dma_outb(mode | dmanr,  DMA1_MODE_REG);
+        else
+                dma_outb(mode | (dmanr&3),  DMA2_MODE_REG);
+}
+
+/* Set only the page register bits of the transfer address.
+ * This is used for successive transfers when we know the contents of
+ * the lower 16 bits of the DMA current address register, but a 64k boundary
+ * may have been crossed.
+ */
+static __inline__ void set_dma_page(unsigned int dmanr, char pagenr)
+{
+        switch(dmanr) {
+                case 0:
+                        dma_outb(pagenr, DMA_PAGE_0);
+                        break;
+                case 1:
+                        dma_outb(pagenr, DMA_PAGE_1);
+                        break;
+                case 2:
+                        dma_outb(pagenr, DMA_PAGE_2);
+                        break;
+                case 3:
+                        dma_outb(pagenr, DMA_PAGE_3);
+                        break;
+                case 5:
+                        dma_outb(pagenr & 0xfe, DMA_PAGE_5);
+                        break;
+                case 6:
+                        dma_outb(pagenr & 0xfe, DMA_PAGE_6);
+                        break;
+                case 7:
+                        dma_outb(pagenr & 0xfe, DMA_PAGE_7);
+                        break;
+        }
+}
+
+
+/* Set transfer address & page bits for specific DMA channel.
+ * Assumes dma flipflop is clear.
+ */
+static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+        set_dma_page(dmanr, a>>16);
+        if (dmanr <= 3)  {
+            dma_outb( a & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
+            dma_outb( (a>>8) & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
+        }  else  {
+            dma_outb( (a>>1) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
+            dma_outb( (a>>9) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
+        }
+}
+
+
+/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for
+ * a specific DMA channel.
+ * You must ensure the parameters are valid.
+ * NOTE: from a manual: "the number of transfers is one more
+ * than the initial word count"! This is taken into account.
+ * Assumes dma flip-flop is clear.
+ * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
+ */
+static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
+{
+        count--;
+        if (dmanr <= 3)  {
+            dma_outb( count & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
+            dma_outb( (count>>8) & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
+        } else {
+            dma_outb( (count>>1) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
+            dma_outb( (count>>9) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
+        }
+}
+
+
+/* Get DMA residue count. After a DMA transfer, this
+ * should return zero. Reading this while a DMA transfer is
+ * still in progress will return unpredictable results.
+ * If called before the channel has been used, it may return 1.
+ * Otherwise, it returns the number of _bytes_ left to transfer.
+ *
+ * Assumes DMA flip-flop is clear.
+ */
+static __inline__ int get_dma_residue(unsigned int dmanr)
+{
+        unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE
+                                         : ((dmanr&3)<<2) + 2 + IO_DMA2_BASE;
+
+        /* using short to get 16-bit wrap around */
+        unsigned short count;
+
+        count = 1 + dma_inb(io_port);
+        count += dma_inb(io_port) << 8;
+        
+        return (dmanr<=3)? count : (count<<1);
+}
+
+
+/* These are in kernel/dma.c: */
+extern int request_dma(unsigned int dmanr, const char * device_id);     /* reserve a DMA channel */
+extern void free_dma(unsigned int dmanr);       /* release it again */
+
+/* From PCI */
+
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy    (0)
+#endif
+
+#endif /* _ASM_DMA_H */
diff --git a/include/asm-x86/dmi.h b/include/asm-x86/dmi.h
new file mode 100644
index 000000000000..c9e4e8ebc270
--- /dev/null
+++ b/include/asm-x86/dmi.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "dmi_32.h"
+#else
+# include "dmi_64.h"
+#endif
diff --git a/include/asm-x86/dmi_32.h b/include/asm-x86/dmi_32.h
new file mode 100644
index 000000000000..38d4eeb7fc7e
--- /dev/null
+++ b/include/asm-x86/dmi_32.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_DMI_H
+#define _ASM_DMI_H 1
+
+#include <asm/io.h>
+
+/* Use early IO mappings for DMI because it's initialized early */
+#define dmi_ioremap bt_ioremap
+#define dmi_iounmap bt_iounmap
+#define dmi_alloc alloc_bootmem
+
+#endif
diff --git a/include/asm-x86/dmi_64.h b/include/asm-x86/dmi_64.h
new file mode 100644
index 000000000000..d02e32e3c3f0
--- /dev/null
+++ b/include/asm-x86/dmi_64.h
@@ -0,0 +1,24 @@
+#ifndef _ASM_DMI_H
+#define _ASM_DMI_H 1
+
+#include <asm/io.h>
+
+#define DMI_MAX_DATA 2048
+
+extern int dmi_alloc_index;
+extern char dmi_alloc_data[DMI_MAX_DATA];
+
+/* This is so early that there is no good way to allocate dynamic memory.
+   Allocate data in an BSS array. */
+static inline void *dmi_alloc(unsigned len)
+{
+        int idx = dmi_alloc_index;
+        if ((dmi_alloc_index += len) > DMI_MAX_DATA)
+                return NULL;
+        return dmi_alloc_data + idx;
+}
+
+#define dmi_ioremap early_ioremap
+#define dmi_iounmap early_iounmap
+
+#endif
diff --git a/include/asm-x86/dwarf2.h b/include/asm-x86/dwarf2.h
new file mode 100644
index 000000000000..b3cbb0ccae18
--- /dev/null
+++ b/include/asm-x86/dwarf2.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "dwarf2_32.h"
+#else
+# include "dwarf2_64.h"
+#endif
diff --git a/include/asm-x86/dwarf2_32.h b/include/asm-x86/dwarf2_32.h
new file mode 100644
index 000000000000..6d66398a307d
--- /dev/null
+++ b/include/asm-x86/dwarf2_32.h
@@ -0,0 +1,61 @@
+#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
new file mode 100644
index 000000000000..eedc08526b0b
--- /dev/null
+++ b/include/asm-x86/dwarf2_64.h
@@ -0,0 +1,57 @@
+#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
new file mode 100644
index 000000000000..5d4d2183e5db
--- /dev/null
+++ b/include/asm-x86/e820.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "e820_32.h"
+#else
+# include "e820_64.h"
+#endif
diff --git a/include/asm-x86/e820_32.h b/include/asm-x86/e820_32.h
new file mode 100644
index 000000000000..cf67dbb1db79
--- /dev/null
+++ b/include/asm-x86/e820_32.h
@@ -0,0 +1,60 @@
+/*
+ * 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
+
+#define E820MAP 0x2d0           /* our map */
+#define E820MAX 128             /* number of entries in E820MAP */
+#define E820NR  0x1e8           /* # entries in E820MAP */
+
+#define E820_RAM        1
+#define E820_RESERVED   2
+#define E820_ACPI       3
+#define E820_NVS        4
+
+#define HIGH_MEMORY     (1024*1024)
+
+#ifndef __ASSEMBLY__
+
+struct e820entry {
+        u64 addr;       /* start of memory segment */
+        u64 size;       /* size of memory segment */
+        u32 type;       /* type of memory segment */
+} __attribute__((packed));
+
+struct e820map {
+        u32 nr_map;
+        struct e820entry map[E820MAX];
+};
+
+extern struct e820map e820;
+
+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 find_max_pfn(void);
+extern void register_bootmem_low_pages(unsigned long max_low_pfn);
+extern void e820_register_memory(void);
+extern void limit_regions(unsigned long long size);
+extern void print_memory_map(char *who);
+
+#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
new file mode 100644
index 000000000000..3486e701bd86
--- /dev/null
+++ b/include/asm-x86/e820_64.h
@@ -0,0 +1,61 @@
+/*
+ * 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
+
+#define E820MAP 0x2d0           /* our map */
+#define E820MAX 128             /* number of entries in E820MAP */
+#define E820NR  0x1e8           /* # entries in E820MAP */
+
+#define E820_RAM        1
+#define E820_RESERVED   2
+#define E820_ACPI       3
+#define E820_NVS        4
+
+#ifndef __ASSEMBLY__
+struct e820entry {
+        u64 addr;       /* start of memory segment */
+        u64 size;       /* size of memory segment */
+        u32 type;       /* type of memory segment */
+} __attribute__((packed));
+
+struct e820map {
+        u32 nr_map;
+        struct e820entry map[E820MAX];
+};
+
+extern unsigned long find_e820_area(unsigned long start, unsigned long end, 
+                                    unsigned size);
+extern void add_memory_region(unsigned long start, unsigned long size, 
+                              int 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 void e820_print_map(char *who);
+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 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 unsigned ebda_addr, ebda_size;
+extern unsigned long nodemap_addr, nodemap_size;
+#endif/*!__ASSEMBLY__*/
+
+#endif/*__E820_HEADER*/
diff --git a/include/asm-x86/edac.h b/include/asm-x86/edac.h
new file mode 100644
index 000000000000..f8b888e140b0
--- /dev/null
+++ b/include/asm-x86/edac.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "edac_32.h"
+#else
+# include "edac_64.h"
+#endif
diff --git a/include/asm-x86/edac_32.h b/include/asm-x86/edac_32.h
new file mode 100644
index 000000000000..3e7dd0ab68ce
--- /dev/null
+++ b/include/asm-x86/edac_32.h
@@ -0,0 +1,18 @@
+#ifndef ASM_EDAC_H
+#define ASM_EDAC_H
+
+/* ECC atomic, DMA, SMP and interrupt safe scrub function */
+
+static __inline__ void atomic_scrub(void *va, u32 size)
+{
+        unsigned long *virt_addr = va;
+        u32 i;
+
+        for (i = 0; i < size / 4; i++, virt_addr++)
+                /* Very carefully read and write to memory atomically
+                 * so we are interrupt, DMA and SMP safe.
+                 */
+                __asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
+}
+
+#endif
diff --git a/include/asm-x86/edac_64.h b/include/asm-x86/edac_64.h
new file mode 100644
index 000000000000..cad1cd42b4ee
--- /dev/null
+++ b/include/asm-x86/edac_64.h
@@ -0,0 +1,18 @@
+#ifndef ASM_EDAC_H
+#define ASM_EDAC_H
+
+/* ECC atomic, DMA, SMP and interrupt safe scrub function */
+
+static __inline__ void atomic_scrub(void *va, u32 size)
+{
+        unsigned int *virt_addr = va;
+        u32 i;
+
+        for (i = 0; i < size / 4; i++, virt_addr++)
+                /* Very carefully read and write to memory atomically
+                 * so we are interrupt, DMA and SMP safe.
+                 */
+                __asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
+}
+
+#endif
diff --git a/include/asm-x86/elf.h b/include/asm-x86/elf.h
new file mode 100644
index 000000000000..ed6bb6e546b9
--- /dev/null
+++ b/include/asm-x86/elf.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "elf_32.h"
+# else
+#  include "elf_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "elf_32.h"
+# else
+#  include "elf_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/elf_32.h b/include/asm-x86/elf_32.h
new file mode 100644
index 000000000000..b32df3a332da
--- /dev/null
+++ b/include/asm-x86/elf_32.h
@@ -0,0 +1,163 @@
+#ifndef __ASMi386_ELF_H
+#define __ASMi386_ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+#include <asm/user.h>
+#include <asm/auxvec.h>
+
+#define R_386_NONE      0
+#define R_386_32        1
+#define R_386_PC32      2
+#define R_386_GOT32     3
+#define R_386_PLT32     4
+#define R_386_COPY      5
+#define R_386_GLOB_DAT  6
+#define R_386_JMP_SLOT  7
+#define R_386_RELATIVE  8
+#define R_386_GOTOFF    9
+#define R_386_GOTPC     10
+#define R_386_NUM       11
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+typedef struct user_fxsr_struct elf_fpxregset_t;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+        (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS       ELFCLASS32
+#define ELF_DATA        ELFDATA2LSB
+#define ELF_ARCH        EM_386
+
+#ifdef __KERNEL__
+
+#include <asm/processor.h>
+#include <asm/system.h>         /* for savesegment */
+#include <asm/desc.h>
+
+/* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx
+   contains a pointer to a function which might be registered using `atexit'.
+   This provides a mean for the dynamic linker to call DT_FINI functions for
+   shared libraries that have been loaded before the code runs.
+
+   A value of 0 tells we have no such handler. 
+
+   We might as well make sure everything else is cleared too (except for %esp),
+   just to make things more deterministic.
+ */
+#define ELF_PLAT_INIT(_r, load_addr)    do { \
+        _r->ebx = 0; _r->ecx = 0; _r->edx = 0; \
+        _r->esi = 0; _r->edi = 0; _r->ebp = 0; \
+        _r->eax = 0; \
+} while (0)
+
+#define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE       4096
+
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk.  */
+
+#define ELF_ET_DYN_BASE         (TASK_SIZE / 3 * 2)
+
+/* regs is struct pt_regs, pr_reg is elf_gregset_t (which is
+   now struct_user_regs, they are different) */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs)                \
+        pr_reg[0] = regs->ebx;                          \
+        pr_reg[1] = regs->ecx;                          \
+        pr_reg[2] = regs->edx;                          \
+        pr_reg[3] = regs->esi;                          \
+        pr_reg[4] = regs->edi;                          \
+        pr_reg[5] = regs->ebp;                          \
+        pr_reg[6] = regs->eax;                          \
+        pr_reg[7] = regs->xds & 0xffff;                 \
+        pr_reg[8] = regs->xes & 0xffff;                 \
+        pr_reg[9] = regs->xfs & 0xffff;                 \
+        savesegment(gs,pr_reg[10]);                     \
+        pr_reg[11] = regs->orig_eax;                    \
+        pr_reg[12] = regs->eip;                         \
+        pr_reg[13] = regs->xcs & 0xffff;                \
+        pr_reg[14] = regs->eflags;                      \
+        pr_reg[15] = regs->esp;                         \
+        pr_reg[16] = regs->xss & 0xffff;
+
+/* This yields a mask that user programs can use to figure out what
+   instruction set this CPU supports.  This could be done in user space,
+   but it's not easy, and we've already done it here.  */
+
+#define ELF_HWCAP       (boot_cpu_data.x86_capability[0])
+
+/* This yields a string that ld.so will use to load implementation
+   specific libraries for optimization.  This is more specific in
+   intent than poking at uname or /proc/cpuinfo.
+
+   For the moment, we have only optimizations for the Intel generations,
+   but that could change... */
+
+#define ELF_PLATFORM  (utsname()->machine)
+
+#define SET_PERSONALITY(ex, ibcs2) do { } while (0)
+
+/*
+ * An executable for which elf_read_implies_exec() returns TRUE will
+ * have the READ_IMPLIES_EXEC personality flag set automatically.
+ */
+#define elf_read_implies_exec(ex, executable_stack)     (executable_stack != EXSTACK_DISABLE_X)
+
+struct task_struct;
+
+extern int dump_task_regs (struct task_struct *, elf_gregset_t *);
+extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
+extern int dump_task_extended_fpu (struct task_struct *, struct user_fxsr_struct *);
+
+#define ELF_CORE_COPY_TASK_REGS(tsk, elf_regs) dump_task_regs(tsk, elf_regs)
+#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
+#define ELF_CORE_COPY_XFPREGS(tsk, elf_xfpregs) dump_task_extended_fpu(tsk, elf_xfpregs)
+
+#define VDSO_HIGH_BASE          (__fix_to_virt(FIX_VDSO))
+#define VDSO_CURRENT_BASE       ((unsigned long)current->mm->context.vdso)
+#define VDSO_PRELINK            0
+
+#define VDSO_SYM(x) \
+                (VDSO_CURRENT_BASE + (unsigned long)(x) - VDSO_PRELINK)
+
+#define VDSO_HIGH_EHDR          ((const struct elfhdr *) VDSO_HIGH_BASE)
+#define VDSO_EHDR               ((const struct elfhdr *) VDSO_CURRENT_BASE)
+
+extern void __kernel_vsyscall;
+
+#define VDSO_ENTRY              VDSO_SYM(&__kernel_vsyscall)
+
+struct linux_binprm;
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+                                       int executable_stack);
+
+extern unsigned int vdso_enabled;
+
+#define ARCH_DLINFO                                                     \
+do if (vdso_enabled) {                                                  \
+                NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY);                    \
+                NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);        \
+} while (0)
+
+#endif
+
+#endif
diff --git a/include/asm-x86/elf_64.h b/include/asm-x86/elf_64.h
new file mode 100644
index 000000000000..b4fbe47f6ccd
--- /dev/null
+++ b/include/asm-x86/elf_64.h
@@ -0,0 +1,180 @@
+#ifndef __ASM_X86_64_ELF_H
+#define __ASM_X86_64_ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+/* x86-64 relocation types */
+#define R_X86_64_NONE           0       /* No reloc */
+#define R_X86_64_64             1       /* Direct 64 bit  */
+#define R_X86_64_PC32           2       /* PC relative 32 bit signed */
+#define R_X86_64_GOT32          3       /* 32 bit GOT entry */
+#define R_X86_64_PLT32          4       /* 32 bit PLT address */
+#define R_X86_64_COPY           5       /* Copy symbol at runtime */
+#define R_X86_64_GLOB_DAT       6       /* Create GOT entry */
+#define R_X86_64_JUMP_SLOT      7       /* Create PLT entry */
+#define R_X86_64_RELATIVE       8       /* Adjust by program base */
+#define R_X86_64_GOTPCREL       9       /* 32 bit signed pc relative
+                                           offset to GOT */
+#define R_X86_64_32             10      /* Direct 32 bit zero extended */
+#define R_X86_64_32S            11      /* Direct 32 bit sign extended */
+#define R_X86_64_16             12      /* Direct 16 bit zero extended */
+#define R_X86_64_PC16           13      /* 16 bit sign extended pc relative */
+#define R_X86_64_8              14      /* Direct 8 bit sign extended  */
+#define R_X86_64_PC8            15      /* 8 bit sign extended pc relative */
+
+#define R_X86_64_NUM            16
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS       ELFCLASS64
+#define ELF_DATA        ELFDATA2LSB
+#define ELF_ARCH        EM_X86_64
+
+#ifdef __KERNEL__
+#include <asm/processor.h>
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+        ((x)->e_machine == EM_X86_64)
+
+
+/* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx
+   contains a pointer to a function which might be registered using `atexit'.
+   This provides a mean for the dynamic linker to call DT_FINI functions for
+   shared libraries that have been loaded before the code runs.
+
+   A value of 0 tells we have no such handler. 
+
+   We might as well make sure everything else is cleared too (except for %esp),
+   just to make things more deterministic.
+ */
+#define ELF_PLAT_INIT(_r, load_addr)    do { \
+        struct task_struct *cur = current; \
+        (_r)->rbx = 0; (_r)->rcx = 0; (_r)->rdx = 0; \
+        (_r)->rsi = 0; (_r)->rdi = 0; (_r)->rbp = 0; \
+        (_r)->rax = 0;                          \
+        (_r)->r8 = 0;                           \
+        (_r)->r9 = 0;                           \
+        (_r)->r10 = 0;                          \
+        (_r)->r11 = 0;                          \
+        (_r)->r12 = 0;                          \
+        (_r)->r13 = 0;                          \
+        (_r)->r14 = 0;                          \
+        (_r)->r15 = 0;                          \
+        cur->thread.fs = 0; cur->thread.gs = 0; \
+        cur->thread.fsindex = 0; cur->thread.gsindex = 0; \
+        cur->thread.ds = 0; cur->thread.es = 0;  \
+        clear_thread_flag(TIF_IA32); \
+} while (0)
+
+#define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE       4096
+
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk.  */
+
+#define ELF_ET_DYN_BASE         (2 * TASK_SIZE / 3)
+
+/* regs is struct pt_regs, pr_reg is elf_gregset_t (which is
+   now struct_user_regs, they are different). Assumes current is the process
+   getting dumped. */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs)  do { \
+        unsigned v;                                             \
+        (pr_reg)[0] = (regs)->r15;                              \
+        (pr_reg)[1] = (regs)->r14;                              \
+        (pr_reg)[2] = (regs)->r13;                              \
+        (pr_reg)[3] = (regs)->r12;                              \
+        (pr_reg)[4] = (regs)->rbp;                              \
+        (pr_reg)[5] = (regs)->rbx;                              \
+        (pr_reg)[6] = (regs)->r11;                              \
+        (pr_reg)[7] = (regs)->r10;                              \
+        (pr_reg)[8] = (regs)->r9;                               \
+        (pr_reg)[9] = (regs)->r8;                               \
+        (pr_reg)[10] = (regs)->rax;                             \
+        (pr_reg)[11] = (regs)->rcx;                             \
+        (pr_reg)[12] = (regs)->rdx;                             \
+        (pr_reg)[13] = (regs)->rsi;                             \
+        (pr_reg)[14] = (regs)->rdi;                             \
+        (pr_reg)[15] = (regs)->orig_rax;                        \
+        (pr_reg)[16] = (regs)->rip;                     \
+        (pr_reg)[17] = (regs)->cs;                      \
+        (pr_reg)[18] = (regs)->eflags;                  \
+        (pr_reg)[19] = (regs)->rsp;                     \
+        (pr_reg)[20] = (regs)->ss;                      \
+        (pr_reg)[21] = current->thread.fs;                      \
+        (pr_reg)[22] = current->thread.gs;                      \
+        asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;       \
+        asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;       \
+        asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;       \
+        asm("movl %%gs,%0" : "=r" (v)); (pr_reg)[26] = v;       \
+} while(0);
+
+/* This yields a mask that user programs can use to figure out what
+   instruction set this CPU supports.  This could be done in user space,
+   but it's not easy, and we've already done it here.  */
+
+#define ELF_HWCAP       (boot_cpu_data.x86_capability[0])
+
+/* This yields a string that ld.so will use to load implementation
+   specific libraries for optimization.  This is more specific in
+   intent than poking at uname or /proc/cpuinfo.
+
+   For the moment, we have only optimizations for the Intel generations,
+   but that could change... */
+
+/* I'm not sure if we can use '-' here */
+#define ELF_PLATFORM  ("x86_64")
+
+extern void set_personality_64bit(void);
+#define SET_PERSONALITY(ex, ibcs2) set_personality_64bit()
+/*
+ * An executable for which elf_read_implies_exec() returns TRUE will
+ * have the READ_IMPLIES_EXEC personality flag set automatically.
+ */
+#define elf_read_implies_exec(ex, executable_stack)     (executable_stack != EXSTACK_DISABLE_X)
+
+struct task_struct;
+
+extern int dump_task_regs (struct task_struct *, elf_gregset_t *);
+extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
+
+#define ELF_CORE_COPY_TASK_REGS(tsk, elf_regs) dump_task_regs(tsk, elf_regs)
+#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
+
+/* 1GB for 64bit, 8MB for 32bit */
+#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
+
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+                                       int executable_stack);
+
+extern int vdso_enabled;
+
+#define ARCH_DLINFO                                             \
+do if (vdso_enabled) {                                          \
+        NEW_AUX_ENT(AT_SYSINFO_EHDR,(unsigned long)current->mm->context.vdso);\
+} while (0)
+
+#endif
+
+#endif
diff --git a/include/asm-x86/emergency-restart.h b/include/asm-x86/emergency-restart.h
new file mode 100644
index 000000000000..680c39563345
--- /dev/null
+++ b/include/asm-x86/emergency-restart.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_EMERGENCY_RESTART_H
+#define _ASM_EMERGENCY_RESTART_H
+
+extern void machine_emergency_restart(void);
+
+#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/include/asm-x86/errno.h b/include/asm-x86/errno.h
new file mode 100644
index 000000000000..9d511be8e573
--- /dev/null
+++ b/include/asm-x86/errno.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "errno_32.h"
+# else
+#  include "errno_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "errno_32.h"
+# else
+#  include "errno_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/errno_32.h b/include/asm-x86/errno_32.h
new file mode 100644
index 000000000000..969b34374728
--- /dev/null
+++ b/include/asm-x86/errno_32.h
@@ -0,0 +1,6 @@
+#ifndef _I386_ERRNO_H
+#define _I386_ERRNO_H
+
+#include <asm-generic/errno.h>
+
+#endif
diff --git a/include/asm-x86/errno_64.h b/include/asm-x86/errno_64.h
new file mode 100644
index 000000000000..311182129e32
--- /dev/null
+++ b/include/asm-x86/errno_64.h
@@ -0,0 +1,6 @@
+#ifndef _X8664_ERRNO_H
+#define _X8664_ERRNO_H
+
+#include <asm-generic/errno.h>
+
+#endif
diff --git a/include/asm-x86/fb.h b/include/asm-x86/fb.h
new file mode 100644
index 000000000000..238c7ca45877
--- /dev/null
+++ b/include/asm-x86/fb.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "fb_32.h"
+#else
+# include "fb_64.h"
+#endif
diff --git a/include/asm-x86/fb_32.h b/include/asm-x86/fb_32.h
new file mode 100644
index 000000000000..d1c6297d4a61
--- /dev/null
+++ b/include/asm-x86/fb_32.h
@@ -0,0 +1,17 @@
+#ifndef _ASM_FB_H_
+#define _ASM_FB_H_
+
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+
+extern int fb_is_primary_device(struct fb_info *info);
+
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+                                unsigned long off)
+{
+        if (boot_cpu_data.x86 > 3)
+                pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
+}
+
+#endif /* _ASM_FB_H_ */
diff --git a/include/asm-x86/fb_64.h b/include/asm-x86/fb_64.h
new file mode 100644
index 000000000000..60548e651d12
--- /dev/null
+++ b/include/asm-x86/fb_64.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_FB_H_
+#define _ASM_FB_H_
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+                                unsigned long off)
+{
+        if (boot_cpu_data.x86 > 3)
+                pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
+}
+
+static inline int fb_is_primary_device(struct fb_info *info)
+{
+        return 0;
+}
+
+#endif /* _ASM_FB_H_ */
diff --git a/include/asm-x86/fcntl.h b/include/asm-x86/fcntl.h
new file mode 100644
index 000000000000..46ab12db5739
--- /dev/null
+++ b/include/asm-x86/fcntl.h
@@ -0,0 +1 @@
+#include <asm-generic/fcntl.h>
diff --git a/include/asm-x86/fixmap.h b/include/asm-x86/fixmap.h
new file mode 100644
index 000000000000..382eb271a892
--- /dev/null
+++ b/include/asm-x86/fixmap.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "fixmap_32.h"
+#else
+# include "fixmap_64.h"
+#endif
diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h
new file mode 100644
index 000000000000..249e753ac805
--- /dev/null
+++ b/include/asm-x86/fixmap_32.h
@@ -0,0 +1,157 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * 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.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+
+/* used by vmalloc.c, vsyscall.lds.S.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap.
+ */
+extern unsigned long __FIXADDR_TOP;
+#define FIXADDR_USER_START     __fix_to_virt(FIX_VDSO)
+#define FIXADDR_USER_END       __fix_to_virt(FIX_VDSO - 1)
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/acpi.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#ifdef CONFIG_HIGHMEM
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#endif
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+enum fixed_addresses {
+        FIX_HOLE,
+        FIX_VDSO,
+        FIX_DBGP_BASE,
+        FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_X86_LOCAL_APIC
+        FIX_APIC_BASE,  /* local (CPU) APIC) -- required for SMP or not */
+#endif
+#ifdef CONFIG_X86_IO_APIC
+        FIX_IO_APIC_BASE_0,
+        FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1,
+#endif
+#ifdef CONFIG_X86_VISWS_APIC
+        FIX_CO_CPU,     /* Cobalt timer */
+        FIX_CO_APIC,    /* Cobalt APIC Redirection Table */ 
+        FIX_LI_PCIA,    /* Lithium PCI Bridge A */
+        FIX_LI_PCIB,    /* Lithium PCI Bridge B */
+#endif
+#ifdef CONFIG_X86_F00F_BUG
+        FIX_F00F_IDT,   /* Virtual mapping for IDT */
+#endif
+#ifdef CONFIG_X86_CYCLONE_TIMER
+        FIX_CYCLONE_TIMER, /*cyclone timer register*/
+#endif 
+#ifdef CONFIG_HIGHMEM
+        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
+#ifdef CONFIG_PARAVIRT
+        FIX_PARAVIRT_BOOTMAP,
+#endif
+        __end_of_permanent_fixed_addresses,
+        /* temporary boot-time mappings, used before ioremap() is functional */
+#define NR_FIX_BTMAPS   16
+        FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+        FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS - 1,
+        FIX_WP_TEST,
+        __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 clear_fixmap(idx) \
+                __set_fixmap(idx, 0, __pgprot(0))
+
+#define FIXADDR_TOP     ((unsigned long)__FIXADDR_TOP)
+
+#define __FIXADDR_SIZE  (__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define __FIXADDR_BOOT_SIZE     (__end_of_fixed_addresses << PAGE_SHIFT)
+#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
new file mode 100644
index 000000000000..cdfbe4a6ae6f
--- /dev/null
+++ b/include/asm-x86/fixmap_64.h
@@ -0,0 +1,92 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * 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.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#include <linux/kernel.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#include <asm/vsyscall.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ *
+ * These 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages (or larger if used with an increment
+ * higher than 1). Use set_fixmap(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+
+enum fixed_addresses {
+        VSYSCALL_LAST_PAGE,
+        VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
+        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,
+        __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)
+
+/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
+#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/floppy.h b/include/asm-x86/floppy.h
new file mode 100644
index 000000000000..aecbb6dca21d
--- /dev/null
+++ b/include/asm-x86/floppy.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "floppy_32.h"
+#else
+# include "floppy_64.h"
+#endif
diff --git a/include/asm-x86/floppy_32.h b/include/asm-x86/floppy_32.h
new file mode 100644
index 000000000000..44ef2f55a8e9
--- /dev/null
+++ b/include/asm-x86/floppy_32.h
@@ -0,0 +1,284 @@
+/*
+ * Architecture specific parts of the Floppy driver
+ *
+ * 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.
+ *
+ * Copyright (C) 1995
+ */
+#ifndef __ASM_I386_FLOPPY_H
+#define __ASM_I386_FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+
+/*
+ * The DMA channel used by the floppy controller cannot access data at
+ * addresses >= 16MB
+ *
+ * Went back to the 1MB limit, as some people had problems with the floppy
+ * driver otherwise. It doesn't matter much for performance anyway, as most
+ * floppy accesses go through the track buffer.
+ */
+#define _CROSS_64KB(a,s,vdma) \
+(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+
+#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
+
+
+#define SW fd_routine[use_virtual_dma&1]
+#define CSW fd_routine[can_use_virtual_dma & 1]
+
+
+#define fd_inb(port)                    inb_p(port)
+#define fd_outb(value,port)             outb_p(value,port)
+
+#define fd_request_dma()        CSW._request_dma(FLOPPY_DMA,"floppy")
+#define fd_free_dma()           CSW._free_dma(FLOPPY_DMA)
+#define fd_enable_irq()         enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
+#define fd_free_irq()           free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue()    SW._get_dma_residue(FLOPPY_DMA)
+#define fd_dma_mem_alloc(size)  SW._dma_mem_alloc(size)
+#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
+
+#define FLOPPY_CAN_FALLBACK_ON_NODMA
+
+static int virtual_dma_count;
+static int virtual_dma_residue;
+static char *virtual_dma_addr;
+static int virtual_dma_mode;
+static int doing_pdma;
+
+static irqreturn_t floppy_hardint(int irq, void *dev_id)
+{
+        register unsigned char st;
+
+#undef TRACE_FLPY_INT
+
+#ifdef TRACE_FLPY_INT
+        static int calls=0;
+        static int bytes=0;
+        static int dma_wait=0;
+#endif
+        if (!doing_pdma)
+                return floppy_interrupt(irq, dev_id);
+
+#ifdef TRACE_FLPY_INT
+        if(!calls)
+                bytes = virtual_dma_count;
+#endif
+
+        {
+                register int lcount;
+                register char *lptr;
+
+                st = 1;
+                for(lcount=virtual_dma_count, lptr=virtual_dma_addr; 
+                    lcount; lcount--, lptr++) {
+                        st=inb(virtual_dma_port+4) & 0xa0 ;
+                        if(st != 0xa0) 
+                                break;
+                        if(virtual_dma_mode)
+                                outb_p(*lptr, virtual_dma_port+5);
+                        else
+                                *lptr = inb_p(virtual_dma_port+5);
+                }
+                virtual_dma_count = lcount;
+                virtual_dma_addr = lptr;
+                st = inb(virtual_dma_port+4);
+        }
+
+#ifdef TRACE_FLPY_INT
+        calls++;
+#endif
+        if(st == 0x20)
+                return IRQ_HANDLED;
+        if(!(st & 0x20)) {
+                virtual_dma_residue += virtual_dma_count;
+                virtual_dma_count=0;
+#ifdef TRACE_FLPY_INT
+                printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", 
+                       virtual_dma_count, virtual_dma_residue, calls, bytes,
+                       dma_wait);
+                calls = 0;
+                dma_wait=0;
+#endif
+                doing_pdma = 0;
+                floppy_interrupt(irq, dev_id);
+                return IRQ_HANDLED;
+        }
+#ifdef TRACE_FLPY_INT
+        if(!virtual_dma_count)
+                dma_wait++;
+#endif
+        return IRQ_HANDLED;
+}
+
+static void fd_disable_dma(void)
+{
+        if(! (can_use_virtual_dma & 1))
+                disable_dma(FLOPPY_DMA);
+        doing_pdma = 0;
+        virtual_dma_residue += virtual_dma_count;
+        virtual_dma_count=0;
+}
+
+static int vdma_request_dma(unsigned int dmanr, const char * device_id)
+{
+        return 0;
+}
+
+static void vdma_nop(unsigned int dummy)
+{
+}
+
+
+static int vdma_get_dma_residue(unsigned int dummy)
+{
+        return virtual_dma_count + virtual_dma_residue;
+}
+
+
+static int fd_request_irq(void)
+{
+        if(can_use_virtual_dma)
+                return request_irq(FLOPPY_IRQ, floppy_hardint,
+                                   IRQF_DISABLED, "floppy", NULL);
+        else
+                return request_irq(FLOPPY_IRQ, floppy_interrupt,
+                                   IRQF_DISABLED, "floppy", NULL);
+
+}
+
+static unsigned long dma_mem_alloc(unsigned long size)
+{
+        return __get_dma_pages(GFP_KERNEL,get_order(size));
+}
+
+
+static unsigned long vdma_mem_alloc(unsigned long size)
+{
+        return (unsigned long) vmalloc(size);
+
+}
+
+#define nodma_mem_alloc(size) vdma_mem_alloc(size)
+
+static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
+{
+        if((unsigned int) addr >= (unsigned int) high_memory)
+                vfree((void *)addr);
+        else
+                free_pages(addr, get_order(size));              
+}
+
+#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size) 
+
+static void _fd_chose_dma_mode(char *addr, unsigned long size)
+{
+        if(can_use_virtual_dma == 2) {
+                if((unsigned int) addr >= (unsigned int) high_memory ||
+                   isa_virt_to_bus(addr) >= 0x1000000 ||
+                   _CROSS_64KB(addr, size, 0))
+                        use_virtual_dma = 1;
+                else
+                        use_virtual_dma = 0;
+        } else {
+                use_virtual_dma = can_use_virtual_dma & 1;
+        }
+}
+
+#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
+
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+        doing_pdma = 1;
+        virtual_dma_port = io;
+        virtual_dma_mode = (mode  == DMA_MODE_WRITE);
+        virtual_dma_addr = addr;
+        virtual_dma_count = size;
+        virtual_dma_residue = 0;
+        return 0;
+}
+
+static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+#ifdef FLOPPY_SANITY_CHECK
+        if (CROSS_64KB(addr, size)) {
+                printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
+                return -1;
+        }
+#endif
+        /* actual, physical DMA */
+        doing_pdma = 0;
+        clear_dma_ff(FLOPPY_DMA);
+        set_dma_mode(FLOPPY_DMA,mode);
+        set_dma_addr(FLOPPY_DMA,isa_virt_to_bus(addr));
+        set_dma_count(FLOPPY_DMA,size);
+        enable_dma(FLOPPY_DMA);
+        return 0;
+}
+
+static struct fd_routine_l {
+        int (*_request_dma)(unsigned int dmanr, const char * device_id);
+        void (*_free_dma)(unsigned int dmanr);
+        int (*_get_dma_residue)(unsigned int dummy);
+        unsigned long (*_dma_mem_alloc) (unsigned long size);
+        int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
+} fd_routine[] = {
+        {
+                request_dma,
+                free_dma,
+                get_dma_residue,
+                dma_mem_alloc,
+                hard_dma_setup
+        },
+        {
+                vdma_request_dma,
+                vdma_nop,
+                vdma_get_dma_residue,
+                vdma_mem_alloc,
+                vdma_dma_setup
+        }
+};
+
+
+static int FDC1 = 0x3f0;
+static int FDC2 = -1;
+
+/*
+ * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
+ * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
+ * coincides with another rtc CMOS user.                Paul G.
+ */
+#define FLOPPY0_TYPE    ({                              \
+        unsigned long flags;                            \
+        unsigned char val;                              \
+        spin_lock_irqsave(&rtc_lock, flags);            \
+        val = (CMOS_READ(0x10) >> 4) & 15;              \
+        spin_unlock_irqrestore(&rtc_lock, flags);       \
+        val;                                            \
+})
+
+#define FLOPPY1_TYPE    ({                              \
+        unsigned long flags;                            \
+        unsigned char val;                              \
+        spin_lock_irqsave(&rtc_lock, flags);            \
+        val = CMOS_READ(0x10) & 15;                     \
+        spin_unlock_irqrestore(&rtc_lock, flags);       \
+        val;                                            \
+})
+
+#define N_FDC 2
+#define N_DRIVE 8
+
+#define FLOPPY_MOTOR_MASK 0xf0
+
+#define AUTO_DMA
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* __ASM_I386_FLOPPY_H */
diff --git a/include/asm-x86/floppy_64.h b/include/asm-x86/floppy_64.h
new file mode 100644
index 000000000000..6ea13c3806f3
--- /dev/null
+++ b/include/asm-x86/floppy_64.h
@@ -0,0 +1,283 @@
+/*
+ * Architecture specific parts of the Floppy driver
+ *
+ * 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.
+ *
+ * Copyright (C) 1995
+ */
+#ifndef __ASM_X86_64_FLOPPY_H
+#define __ASM_X86_64_FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+
+/*
+ * The DMA channel used by the floppy controller cannot access data at
+ * addresses >= 16MB
+ *
+ * Went back to the 1MB limit, as some people had problems with the floppy
+ * driver otherwise. It doesn't matter much for performance anyway, as most
+ * floppy accesses go through the track buffer.
+ */
+#define _CROSS_64KB(a,s,vdma) \
+(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+
+#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
+
+
+#define SW fd_routine[use_virtual_dma&1]
+#define CSW fd_routine[can_use_virtual_dma & 1]
+
+
+#define fd_inb(port)                    inb_p(port)
+#define fd_outb(value,port)             outb_p(value,port)
+
+#define fd_request_dma()        CSW._request_dma(FLOPPY_DMA,"floppy")
+#define fd_free_dma()           CSW._free_dma(FLOPPY_DMA)
+#define fd_enable_irq()         enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
+#define fd_free_irq()           free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue()    SW._get_dma_residue(FLOPPY_DMA)
+#define fd_dma_mem_alloc(size)  SW._dma_mem_alloc(size)
+#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
+
+#define FLOPPY_CAN_FALLBACK_ON_NODMA
+
+static int virtual_dma_count;
+static int virtual_dma_residue;
+static char *virtual_dma_addr;
+static int virtual_dma_mode;
+static int doing_pdma;
+
+static irqreturn_t floppy_hardint(int irq, void *dev_id)
+{
+        register unsigned char st;
+
+#undef TRACE_FLPY_INT
+
+#ifdef TRACE_FLPY_INT
+        static int calls=0;
+        static int bytes=0;
+        static int dma_wait=0;
+#endif
+        if (!doing_pdma)
+                return floppy_interrupt(irq, dev_id);
+
+#ifdef TRACE_FLPY_INT
+        if(!calls)
+                bytes = virtual_dma_count;
+#endif
+
+        {
+                register int lcount;
+                register char *lptr;
+
+                st = 1;
+                for(lcount=virtual_dma_count, lptr=virtual_dma_addr; 
+                    lcount; lcount--, lptr++) {
+                        st=inb(virtual_dma_port+4) & 0xa0 ;
+                        if(st != 0xa0) 
+                                break;
+                        if(virtual_dma_mode)
+                                outb_p(*lptr, virtual_dma_port+5);
+                        else
+                                *lptr = inb_p(virtual_dma_port+5);
+                }
+                virtual_dma_count = lcount;
+                virtual_dma_addr = lptr;
+                st = inb(virtual_dma_port+4);
+        }
+
+#ifdef TRACE_FLPY_INT
+        calls++;
+#endif
+        if(st == 0x20)
+                return IRQ_HANDLED;
+        if(!(st & 0x20)) {
+                virtual_dma_residue += virtual_dma_count;
+                virtual_dma_count=0;
+#ifdef TRACE_FLPY_INT
+                printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", 
+                       virtual_dma_count, virtual_dma_residue, calls, bytes,
+                       dma_wait);
+                calls = 0;
+                dma_wait=0;
+#endif
+                doing_pdma = 0;
+                floppy_interrupt(irq, dev_id);
+                return IRQ_HANDLED;
+        }
+#ifdef TRACE_FLPY_INT
+        if(!virtual_dma_count)
+                dma_wait++;
+#endif
+        return IRQ_HANDLED;
+}
+
+static void fd_disable_dma(void)
+{
+        if(! (can_use_virtual_dma & 1))
+                disable_dma(FLOPPY_DMA);
+        doing_pdma = 0;
+        virtual_dma_residue += virtual_dma_count;
+        virtual_dma_count=0;
+}
+
+static int vdma_request_dma(unsigned int dmanr, const char * device_id)
+{
+        return 0;
+}
+
+static void vdma_nop(unsigned int dummy)
+{
+}
+
+
+static int vdma_get_dma_residue(unsigned int dummy)
+{
+        return virtual_dma_count + virtual_dma_residue;
+}
+
+
+static int fd_request_irq(void)
+{
+        if(can_use_virtual_dma)
+                return request_irq(FLOPPY_IRQ, floppy_hardint,
+                                   IRQF_DISABLED, "floppy", NULL);
+        else
+                return request_irq(FLOPPY_IRQ, floppy_interrupt,
+                                   IRQF_DISABLED, "floppy", NULL);
+}
+
+static unsigned long dma_mem_alloc(unsigned long size)
+{
+        return __get_dma_pages(GFP_KERNEL|__GFP_NORETRY,get_order(size));
+}
+
+
+static unsigned long vdma_mem_alloc(unsigned long size)
+{
+        return (unsigned long) vmalloc(size);
+
+}
+
+#define nodma_mem_alloc(size) vdma_mem_alloc(size)
+
+static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
+{
+        if((unsigned long) addr >= (unsigned long) high_memory)
+                vfree((void *)addr);
+        else
+                free_pages(addr, get_order(size));              
+}
+
+#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size) 
+
+static void _fd_chose_dma_mode(char *addr, unsigned long size)
+{
+        if(can_use_virtual_dma == 2) {
+                if((unsigned long) addr >= (unsigned long) high_memory ||
+                   isa_virt_to_bus(addr) >= 0x1000000 ||
+                   _CROSS_64KB(addr, size, 0))
+                        use_virtual_dma = 1;
+                else
+                        use_virtual_dma = 0;
+        } else {
+                use_virtual_dma = can_use_virtual_dma & 1;
+        }
+}
+
+#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
+
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+        doing_pdma = 1;
+        virtual_dma_port = io;
+        virtual_dma_mode = (mode  == DMA_MODE_WRITE);
+        virtual_dma_addr = addr;
+        virtual_dma_count = size;
+        virtual_dma_residue = 0;
+        return 0;
+}
+
+static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+#ifdef FLOPPY_SANITY_CHECK
+        if (CROSS_64KB(addr, size)) {
+                printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
+                return -1;
+        }
+#endif
+        /* actual, physical DMA */
+        doing_pdma = 0;
+        clear_dma_ff(FLOPPY_DMA);
+        set_dma_mode(FLOPPY_DMA,mode);
+        set_dma_addr(FLOPPY_DMA,isa_virt_to_bus(addr));
+        set_dma_count(FLOPPY_DMA,size);
+        enable_dma(FLOPPY_DMA);
+        return 0;
+}
+
+static struct fd_routine_l {
+        int (*_request_dma)(unsigned int dmanr, const char * device_id);
+        void (*_free_dma)(unsigned int dmanr);
+        int (*_get_dma_residue)(unsigned int dummy);
+        unsigned long (*_dma_mem_alloc) (unsigned long size);
+        int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
+} fd_routine[] = {
+        {
+                request_dma,
+                free_dma,
+                get_dma_residue,
+                dma_mem_alloc,
+                hard_dma_setup
+        },
+        {
+                vdma_request_dma,
+                vdma_nop,
+                vdma_get_dma_residue,
+                vdma_mem_alloc,
+                vdma_dma_setup
+        }
+};
+
+
+static int FDC1 = 0x3f0;
+static int FDC2 = -1;
+
+/*
+ * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
+ * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
+ * coincides with another rtc CMOS user.                Paul G.
+ */
+#define FLOPPY0_TYPE    ({                              \
+        unsigned long flags;                            \
+        unsigned char val;                              \
+        spin_lock_irqsave(&rtc_lock, flags);            \
+        val = (CMOS_READ(0x10) >> 4) & 15;              \
+        spin_unlock_irqrestore(&rtc_lock, flags);       \
+        val;                                            \
+})
+
+#define FLOPPY1_TYPE    ({                              \
+        unsigned long flags;                            \
+        unsigned char val;                              \
+        spin_lock_irqsave(&rtc_lock, flags);            \
+        val = CMOS_READ(0x10) & 15;                     \
+        spin_unlock_irqrestore(&rtc_lock, flags);       \
+        val;                                            \
+})
+
+#define N_FDC 2
+#define N_DRIVE 8
+
+#define FLOPPY_MOTOR_MASK 0xf0
+
+#define AUTO_DMA
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* __ASM_X86_64_FLOPPY_H */
diff --git a/include/asm-x86/fpu32.h b/include/asm-x86/fpu32.h
new file mode 100644
index 000000000000..4153db5c0c31
--- /dev/null
+++ b/include/asm-x86/fpu32.h
@@ -0,0 +1,10 @@
+#ifndef _FPU32_H
+#define _FPU32_H 1
+
+struct _fpstate_ia32;
+
+int restore_i387_ia32(struct task_struct *tsk, struct _fpstate_ia32 __user *buf, int fsave);
+int save_i387_ia32(struct task_struct *tsk, struct _fpstate_ia32 __user *buf, 
+                   struct pt_regs *regs, int fsave);
+
+#endif
diff --git a/include/asm-x86/frame.i b/include/asm-x86/frame.i
new file mode 100644
index 000000000000..03620251ae17
--- /dev/null
+++ b/include/asm-x86/frame.i
@@ -0,0 +1,23 @@
+#include <asm/dwarf2.h>
+
+/* The annotation hides the frame from the unwinder and makes it look
+   like a ordinary ebp save/restore. This avoids some special cases for
+   frame pointer later */
+#ifdef CONFIG_FRAME_POINTER
+        .macro FRAME
+        pushl %ebp
+        CFI_ADJUST_CFA_OFFSET 4
+        CFI_REL_OFFSET ebp,0
+        movl %esp,%ebp
+        .endm
+        .macro ENDFRAME
+        popl %ebp
+        CFI_ADJUST_CFA_OFFSET -4
+        CFI_RESTORE ebp
+        .endm
+#else
+        .macro FRAME
+        .endm
+        .macro ENDFRAME
+        .endm
+#endif
diff --git a/include/asm-x86/futex.h b/include/asm-x86/futex.h
new file mode 100644
index 000000000000..1f4610e0c613
--- /dev/null
+++ b/include/asm-x86/futex.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "futex_32.h"
+#else
+# include "futex_64.h"
+#endif
diff --git a/include/asm-x86/futex_32.h b/include/asm-x86/futex_32.h
new file mode 100644
index 000000000000..438ef0ec7101
--- /dev/null
+++ b/include/asm-x86/futex_32.h
@@ -0,0 +1,135 @@
+#ifndef _ASM_FUTEX_H
+#define _ASM_FUTEX_H
+
+#ifdef __KERNEL__
+
+#include <linux/futex.h>
+#include <asm/errno.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/uaccess.h>
+
+#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \
+  __asm__ __volatile (                                          \
+"1:     " insn "\n"                                             \
+"2:     .section .fixup,\"ax\"\n\
+3:      mov     %3, %1\n\
+        jmp     2b\n\
+        .previous\n\
+        .section __ex_table,\"a\"\n\
+        .align  8\n\
+        .long   1b,3b\n\
+        .previous"                                              \
+        : "=r" (oldval), "=r" (ret), "+m" (*uaddr)              \
+        : "i" (-EFAULT), "0" (oparg), "1" (0))
+
+#define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg) \
+  __asm__ __volatile (                                          \
+"1:     movl    %2, %0\n\
+        movl    %0, %3\n"                                       \
+        insn "\n"                                               \
+"2:     " LOCK_PREFIX "cmpxchgl %3, %2\n\
+        jnz     1b\n\
+3:      .section .fixup,\"ax\"\n\
+4:      mov     %5, %1\n\
+        jmp     3b\n\
+        .previous\n\
+        .section __ex_table,\"a\"\n\
+        .align  8\n\
+        .long   1b,4b,2b,4b\n\
+        .previous"                                              \
+        : "=&a" (oldval), "=&r" (ret), "+m" (*uaddr),           \
+          "=&r" (tem)                                           \
+        : "r" (oparg), "i" (-EFAULT), "1" (0))
+
+static inline int
+futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+{
+        int op = (encoded_op >> 28) & 7;
+        int cmp = (encoded_op >> 24) & 15;
+        int oparg = (encoded_op << 8) >> 20;
+        int cmparg = (encoded_op << 20) >> 20;
+        int oldval = 0, ret, tem;
+        if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+                oparg = 1 << oparg;
+
+        if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+                return -EFAULT;
+
+        pagefault_disable();
+
+        if (op == FUTEX_OP_SET)
+                __futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg);
+        else {
+#ifndef CONFIG_X86_BSWAP
+                if (boot_cpu_data.x86 == 3)
+                        ret = -ENOSYS;
+                else
+#endif
+                switch (op) {
+                case FUTEX_OP_ADD:
+                        __futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret,
+                                           oldval, uaddr, oparg);
+                        break;
+                case FUTEX_OP_OR:
+                        __futex_atomic_op2("orl %4, %3", ret, oldval, uaddr,
+                                           oparg);
+                        break;
+                case FUTEX_OP_ANDN:
+                        __futex_atomic_op2("andl %4, %3", ret, oldval, uaddr,
+                                           ~oparg);
+                        break;
+                case FUTEX_OP_XOR:
+                        __futex_atomic_op2("xorl %4, %3", ret, oldval, uaddr,
+                                           oparg);
+                        break;
+                default:
+                        ret = -ENOSYS;
+                }
+        }
+
+        pagefault_enable();
+
+        if (!ret) {
+                switch (cmp) {
+                case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+                case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+                case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+                case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+                case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+                case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+                default: ret = -ENOSYS;
+                }
+        }
+        return ret;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+{
+        if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+                return -EFAULT;
+
+        __asm__ __volatile__(
+                "1:     " LOCK_PREFIX "cmpxchgl %3, %1          \n"
+
+                "2:     .section .fixup, \"ax\"                 \n"
+                "3:     mov     %2, %0                          \n"
+                "       jmp     2b                              \n"
+                "       .previous                               \n"
+
+                "       .section __ex_table, \"a\"              \n"
+                "       .align  8                               \n"
+                "       .long   1b,3b                           \n"
+                "       .previous                               \n"
+
+                : "=a" (oldval), "+m" (*uaddr)
+                : "i" (-EFAULT), "r" (newval), "0" (oldval)
+                : "memory"
+        );
+
+        return oldval;
+}
+
+#endif
+#endif
diff --git a/include/asm-x86/futex_64.h b/include/asm-x86/futex_64.h
new file mode 100644
index 000000000000..5cdfb08013c3
--- /dev/null
+++ b/include/asm-x86/futex_64.h
@@ -0,0 +1,125 @@
+#ifndef _ASM_FUTEX_H
+#define _ASM_FUTEX_H
+
+#ifdef __KERNEL__
+
+#include <linux/futex.h>
+#include <asm/errno.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+
+#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \
+  __asm__ __volatile (                                          \
+"1:     " insn "\n"                                             \
+"2:     .section .fixup,\"ax\"\n\
+3:      mov     %3, %1\n\
+        jmp     2b\n\
+        .previous\n\
+        .section __ex_table,\"a\"\n\
+        .align  8\n\
+        .quad   1b,3b\n\
+        .previous"                                              \
+        : "=r" (oldval), "=r" (ret), "=m" (*uaddr)              \
+        : "i" (-EFAULT), "m" (*uaddr), "0" (oparg), "1" (0))
+
+#define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg) \
+  __asm__ __volatile (                                          \
+"1:     movl    %2, %0\n\
+        movl    %0, %3\n"                                       \
+        insn "\n"                                               \
+"2:     " LOCK_PREFIX "cmpxchgl %3, %2\n\
+        jnz     1b\n\
+3:      .section .fixup,\"ax\"\n\
+4:      mov     %5, %1\n\
+        jmp     3b\n\
+        .previous\n\
+        .section __ex_table,\"a\"\n\
+        .align  8\n\
+        .quad   1b,4b,2b,4b\n\
+        .previous"                                              \
+        : "=&a" (oldval), "=&r" (ret), "=m" (*uaddr),           \
+          "=&r" (tem)                                           \
+        : "r" (oparg), "i" (-EFAULT), "m" (*uaddr), "1" (0))
+
+static inline int
+futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+{
+        int op = (encoded_op >> 28) & 7;
+        int cmp = (encoded_op >> 24) & 15;
+        int oparg = (encoded_op << 8) >> 20;
+        int cmparg = (encoded_op << 20) >> 20;
+        int oldval = 0, ret, tem;
+        if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+                oparg = 1 << oparg;
+
+        if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+                return -EFAULT;
+
+        pagefault_disable();
+
+        switch (op) {
+        case FUTEX_OP_SET:
+                __futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg);
+                break;
+        case FUTEX_OP_ADD:
+                __futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval,
+                                   uaddr, oparg);
+                break;
+        case FUTEX_OP_OR:
+                __futex_atomic_op2("orl %4, %3", ret, oldval, uaddr, oparg);
+                break;
+        case FUTEX_OP_ANDN:
+                __futex_atomic_op2("andl %4, %3", ret, oldval, uaddr, ~oparg);
+                break;
+        case FUTEX_OP_XOR:
+                __futex_atomic_op2("xorl %4, %3", ret, oldval, uaddr, oparg);
+                break;
+        default:
+                ret = -ENOSYS;
+        }
+
+        pagefault_enable();
+
+        if (!ret) {
+                switch (cmp) {
+                case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+                case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+                case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+                case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+                case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+                case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+                default: ret = -ENOSYS;
+                }
+        }
+        return ret;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+{
+        if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+                return -EFAULT;
+
+        __asm__ __volatile__(
+                "1:     " LOCK_PREFIX "cmpxchgl %3, %1          \n"
+
+                "2:     .section .fixup, \"ax\"                 \n"
+                "3:     mov     %2, %0                          \n"
+                "       jmp     2b                              \n"
+                "       .previous                               \n"
+
+                "       .section __ex_table, \"a\"              \n"
+                "       .align  8                               \n"
+                "       .quad   1b,3b                           \n"
+                "       .previous                               \n"
+
+                : "=a" (oldval), "=m" (*uaddr)
+                : "i" (-EFAULT), "r" (newval), "0" (oldval)
+                : "memory"
+        );
+
+        return oldval;
+}
+
+#endif
+#endif
diff --git a/include/asm-x86/genapic.h b/include/asm-x86/genapic.h
new file mode 100644
index 000000000000..d48bee663a6f
--- /dev/null
+++ b/include/asm-x86/genapic.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "genapic_32.h"
+#else
+# include "genapic_64.h"
+#endif
diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h
new file mode 100644
index 000000000000..33e3ffe1766c
--- /dev/null
+++ b/include/asm-x86/genapic_32.h
@@ -0,0 +1,127 @@
+#ifndef _ASM_GENAPIC_H
+#define _ASM_GENAPIC_H 1
+
+#include <asm/mpspec.h>
+
+/*
+ * Generic APIC driver interface.
+ *
+ * An straight forward mapping of the APIC related parts of the
+ * x86 subarchitecture interface to a dynamic object.
+ *
+ * This is used by the "generic" x86 subarchitecture.
+ *
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ */
+
+struct mpc_config_translation;
+struct mpc_config_bus;
+struct mp_config_table;
+struct mpc_config_processor;
+
+struct genapic { 
+        char *name; 
+        int (*probe)(void); 
+
+        int (*apic_id_registered)(void);
+        cpumask_t (*target_cpus)(void);
+        int int_delivery_mode;
+        int int_dest_mode; 
+        int ESR_DISABLE;
+        int apic_destination_logical;
+        unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
+        unsigned long (*check_apicid_present)(int apicid); 
+        int no_balance_irq;
+        int no_ioapic_check;
+        void (*init_apic_ldr)(void);
+        physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
+
+        void (*setup_apic_routing)(void);
+        int (*multi_timer_check)(int apic, int irq);
+        int (*apicid_to_node)(int logical_apicid); 
+        int (*cpu_to_logical_apicid)(int cpu);
+        int (*cpu_present_to_apicid)(int mps_cpu);
+        physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
+        int (*mpc_apic_id)(struct mpc_config_processor *m, 
+                           struct mpc_config_translation *t); 
+        void (*setup_portio_remap)(void); 
+        int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
+        void (*enable_apic_mode)(void);
+        u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
+
+        /* mpparse */
+        void (*mpc_oem_bus_info)(struct mpc_config_bus *, char *, 
+                                 struct mpc_config_translation *);
+        void (*mpc_oem_pci_bus)(struct mpc_config_bus *, 
+                                struct mpc_config_translation *); 
+
+        /* When one of the next two hooks returns 1 the genapic
+           is switched to this. Essentially they are additional probe 
+           functions. */
+        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);
+
+        unsigned (*get_apic_id)(unsigned long x);
+        unsigned long apic_id_mask;
+        unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
+
+#ifdef CONFIG_SMP
+        /* ipi */
+        void (*send_IPI_mask)(cpumask_t mask, int vector);
+        void (*send_IPI_allbutself)(int vector);
+        void (*send_IPI_all)(int vector);
+#endif
+}; 
+
+#define APICFUNC(x) .x = x,
+
+/* More functions could be probably marked IPIFUNC and save some space
+   in UP GENERICARCH kernels, but I don't have the nerve right now
+   to untangle this mess. -AK  */
+#ifdef CONFIG_SMP
+#define IPIFUNC(x) APICFUNC(x)
+#else
+#define IPIFUNC(x)
+#endif
+
+#define APIC_INIT(aname, aprobe) { \
+        .name = aname, \
+        .probe = aprobe, \
+        .int_delivery_mode = INT_DELIVERY_MODE, \
+        .int_dest_mode = INT_DEST_MODE, \
+        .no_balance_irq = NO_BALANCE_IRQ, \
+        .ESR_DISABLE = esr_disable, \
+        .apic_destination_logical = APIC_DEST_LOGICAL, \
+        APICFUNC(apic_id_registered) \
+        APICFUNC(target_cpus) \
+        APICFUNC(check_apicid_used) \
+        APICFUNC(check_apicid_present) \
+        APICFUNC(init_apic_ldr) \
+        APICFUNC(ioapic_phys_id_map) \
+        APICFUNC(setup_apic_routing) \
+        APICFUNC(multi_timer_check) \
+        APICFUNC(apicid_to_node) \
+        APICFUNC(cpu_to_logical_apicid) \
+        APICFUNC(cpu_present_to_apicid) \
+        APICFUNC(apicid_to_cpu_present) \
+        APICFUNC(mpc_apic_id) \
+        APICFUNC(setup_portio_remap) \
+        APICFUNC(check_phys_apicid_present) \
+        APICFUNC(mpc_oem_bus_info) \
+        APICFUNC(mpc_oem_pci_bus) \
+        APICFUNC(mps_oem_check) \
+        APICFUNC(get_apic_id) \
+        .apic_id_mask = APIC_ID_MASK, \
+        APICFUNC(cpu_mask_to_apicid) \
+        APICFUNC(acpi_madt_oem_check) \
+        IPIFUNC(send_IPI_mask) \
+        IPIFUNC(send_IPI_allbutself) \
+        IPIFUNC(send_IPI_all) \
+        APICFUNC(enable_apic_mode) \
+        APICFUNC(phys_pkg_id) \
+        }
+
+extern struct genapic *genapic;
+
+#endif
diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h
new file mode 100644
index 000000000000..d7e516ccbaa4
--- /dev/null
+++ b/include/asm-x86/genapic_64.h
@@ -0,0 +1,37 @@
+#ifndef _ASM_GENAPIC_H
+#define _ASM_GENAPIC_H 1
+
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC sub-arch data struct.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+
+struct genapic {
+        char *name;
+        u32 int_delivery_mode;
+        u32 int_dest_mode;
+        int (*apic_id_registered)(void);
+        cpumask_t (*target_cpus)(void);
+        cpumask_t (*vector_allocation_domain)(int cpu);
+        void (*init_apic_ldr)(void);
+        /* ipi */
+        void (*send_IPI_mask)(cpumask_t mask, int vector);
+        void (*send_IPI_allbutself)(int vector);
+        void (*send_IPI_all)(int vector);
+        /* */
+        unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
+        unsigned int (*phys_pkg_id)(int index_msb);
+};
+
+extern struct genapic *genapic;
+
+extern struct genapic apic_flat;
+extern struct genapic apic_physflat;
+
+#endif
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
new file mode 100644
index 000000000000..6da4bbbea3dc
--- /dev/null
+++ b/include/asm-x86/geode.h
@@ -0,0 +1,159 @@
+/*
+ * AMD Geode definitions
+ * Copyright (C) 2006, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_GEODE_H_
+#define _ASM_GEODE_H_
+
+#include <asm/processor.h>
+#include <linux/io.h>
+
+/* Generic southbridge functions */
+
+#define GEODE_DEV_PMS 0
+#define GEODE_DEV_ACPI 1
+#define GEODE_DEV_GPIO 2
+#define GEODE_DEV_MFGPT 3
+
+extern int geode_get_dev_base(unsigned int dev);
+
+/* Useful macros */
+#define geode_pms_base()        geode_get_dev_base(GEODE_DEV_PMS)
+#define geode_acpi_base()       geode_get_dev_base(GEODE_DEV_ACPI)
+#define geode_gpio_base()       geode_get_dev_base(GEODE_DEV_GPIO)
+#define geode_mfgpt_base()      geode_get_dev_base(GEODE_DEV_MFGPT)
+
+/* MSRS */
+
+#define GX_GLCP_SYS_RSTPLL      0x4C000014
+
+#define MSR_LBAR_SMB            0x5140000B
+#define MSR_LBAR_GPIO           0x5140000C
+#define MSR_LBAR_MFGPT          0x5140000D
+#define MSR_LBAR_ACPI           0x5140000E
+#define MSR_LBAR_PMS            0x5140000F
+
+#define MSR_PIC_YSEL_LOW        0x51400020
+#define MSR_PIC_YSEL_HIGH       0x51400021
+#define MSR_PIC_ZSEL_LOW        0x51400022
+#define MSR_PIC_ZSEL_HIGH       0x51400023
+
+#define MFGPT_IRQ_MSR           0x51400028
+#define MFGPT_NR_MSR            0x51400029
+
+/* Resource Sizes */
+
+#define LBAR_GPIO_SIZE          0xFF
+#define LBAR_MFGPT_SIZE         0x40
+#define LBAR_ACPI_SIZE          0x40
+#define LBAR_PMS_SIZE           0x80
+
+/* ACPI registers (PMS block) */
+
+/*
+ * PM1_EN is only valid when VSA is enabled for 16 bit reads.
+ * When VSA is not enabled, *always* read both PM1_STS and PM1_EN
+ * with a 32 bit read at offset 0x0
+ */
+
+#define PM1_STS                 0x00
+#define PM1_EN                  0x02
+#define PM1_CNT                 0x08
+#define PM2_CNT                 0x0C
+#define PM_TMR                  0x10
+#define PM_GPE0_STS             0x18
+#define PM_GPE0_EN              0x1C
+
+/* PMC registers (PMS block) */
+
+#define PM_SSD                  0x00
+#define PM_SCXA                 0x04
+#define PM_SCYA                 0x08
+#define PM_OUT_SLPCTL           0x0C
+#define PM_SCLK                 0x10
+#define PM_SED                  0x1
+#define PM_SCXD                 0x18
+#define PM_SCYD                 0x1C
+#define PM_IN_SLPCTL            0x20
+#define PM_WKD                  0x30
+#define PM_WKXD                 0x34
+#define PM_RD                   0x38
+#define PM_WKXA                 0x3C
+#define PM_FSD                  0x40
+#define PM_TSD                  0x44
+#define PM_PSD                  0x48
+#define PM_NWKD                 0x4C
+#define PM_AWKD                 0x50
+#define PM_SSC                  0x54
+
+/* GPIO */
+
+#define GPIO_OUTPUT_VAL         0x00
+#define GPIO_OUTPUT_ENABLE      0x04
+#define GPIO_OUTPUT_OPEN_DRAIN  0x08
+#define GPIO_OUTPUT_INVERT      0x0C
+#define GPIO_OUTPUT_AUX1        0x10
+#define GPIO_OUTPUT_AUX2        0x14
+#define GPIO_PULL_UP            0x18
+#define GPIO_PULL_DOWN          0x1C
+#define GPIO_INPUT_ENABLE       0x20
+#define GPIO_INPUT_INVERT       0x24
+#define GPIO_INPUT_FILTER       0x28
+#define GPIO_INPUT_EVENT_COUNT  0x2C
+#define GPIO_READ_BACK          0x30
+#define GPIO_INPUT_AUX1         0x34
+#define GPIO_EVENTS_ENABLE      0x38
+#define GPIO_LOCK_ENABLE        0x3C
+#define GPIO_POSITIVE_EDGE_EN   0x40
+#define GPIO_NEGATIVE_EDGE_EN   0x44
+#define GPIO_POSITIVE_EDGE_STS  0x48
+#define GPIO_NEGATIVE_EDGE_STS  0x4C
+
+#define GPIO_MAP_X              0xE0
+#define GPIO_MAP_Y              0xE4
+#define GPIO_MAP_Z              0xE8
+#define GPIO_MAP_W              0xEC
+
+extern void geode_gpio_set(unsigned int, unsigned int);
+extern void geode_gpio_clear(unsigned int, unsigned int);
+extern int geode_gpio_isset(unsigned int, unsigned int);
+extern void geode_gpio_setup_event(unsigned int, int, int);
+extern void geode_gpio_set_irq(unsigned int, unsigned int);
+
+static inline void geode_gpio_event_irq(unsigned int gpio, int pair)
+{
+        geode_gpio_setup_event(gpio, pair, 0);
+}
+
+static inline void geode_gpio_event_pme(unsigned int gpio, int pair)
+{
+        geode_gpio_setup_event(gpio, pair, 1);
+}
+
+/* Specific geode tests */
+
+static inline int is_geode_gx(void)
+{
+        return ((boot_cpu_data.x86_vendor == X86_VENDOR_NSC) &&
+                (boot_cpu_data.x86 == 5) &&
+                (boot_cpu_data.x86_model == 5));
+}
+
+static inline int is_geode_lx(void)
+{
+        return ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) &&
+                (boot_cpu_data.x86 == 5) &&
+                (boot_cpu_data.x86_model == 10));
+}
+
+static inline int is_geode(void)
+{
+        return (is_geode_gx() || is_geode_lx());
+}
+
+#endif
diff --git a/include/asm-x86/hardirq.h b/include/asm-x86/hardirq.h
new file mode 100644
index 000000000000..314434d664e7
--- /dev/null
+++ b/include/asm-x86/hardirq.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "hardirq_32.h"
+#else
+# include "hardirq_64.h"
+#endif
diff --git a/include/asm-x86/hardirq_32.h b/include/asm-x86/hardirq_32.h
new file mode 100644
index 000000000000..0e358dc405f8
--- /dev/null
+++ b/include/asm-x86/hardirq_32.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_HARDIRQ_H
+#define __ASM_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+        unsigned int __softirq_pending;
+        unsigned long idle_timestamp;
+        unsigned int __nmi_count;       /* arch dependent */
+        unsigned int apic_timer_irqs;   /* arch dependent */
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+extern irq_cpustat_t irq_stat[];
+
+#define __ARCH_IRQ_STAT
+#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
+
+void ack_bad_irq(unsigned int irq);
+#include <linux/irq_cpustat.h>
+
+#endif /* __ASM_HARDIRQ_H */
diff --git a/include/asm-x86/hardirq_64.h b/include/asm-x86/hardirq_64.h
new file mode 100644
index 000000000000..95d5e090ed89
--- /dev/null
+++ b/include/asm-x86/hardirq_64.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_HARDIRQ_H
+#define __ASM_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+#include <asm/pda.h>
+#include <asm/apic.h>
+
+/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
+#define MAX_HARDIRQS_PER_CPU NR_VECTORS
+
+#define __ARCH_IRQ_STAT 1
+
+#define local_softirq_pending() read_pda(__softirq_pending)
+
+#define __ARCH_SET_SOFTIRQ_PENDING 1
+
+#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
+#define or_softirq_pending(x)  or_pda(__softirq_pending, (x))
+
+extern void ack_bad_irq(unsigned int irq);
+
+#endif /* __ASM_HARDIRQ_H */
diff --git a/include/asm-x86/highmem.h b/include/asm-x86/highmem.h
new file mode 100644
index 000000000000..13cdcd66fff2
--- /dev/null
+++ b/include/asm-x86/highmem.h
@@ -0,0 +1,85 @@
+/*
+ * highmem.h: virtual kernel memory mappings for high memory
+ *
+ * Used in CONFIG_HIGHMEM systems for memory pages which
+ * are not addressable by direct kernel virtual addresses.
+ *
+ * Copyright (C) 1999 Gerhard Wichert, Siemens AG
+ *                    Gerhard.Wichert@pdb.siemens.de
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with 
+ * up to 16 Terabyte physical memory. With current x86 CPUs
+ * we now support up to 64 Gigabytes physical RAM.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+#ifndef _ASM_HIGHMEM_H
+#define _ASM_HIGHMEM_H
+
+#ifdef __KERNEL__
+
+#include <linux/interrupt.h>
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#include <asm/tlbflush.h>
+#include <asm/paravirt.h>
+
+/* declarations for highmem.c */
+extern unsigned long highstart_pfn, highend_pfn;
+
+extern pte_t *kmap_pte;
+extern pgprot_t kmap_prot;
+extern pte_t *pkmap_page_table;
+
+/*
+ * Right now we initialize only a single pte table. It can be extended
+ * easily, subsequent pte tables have to be allocated in one physical
+ * chunk of RAM.
+ */
+#ifdef CONFIG_X86_PAE
+#define LAST_PKMAP 512
+#else
+#define LAST_PKMAP 1024
+#endif
+/*
+ * Ordering is:
+ *
+ * FIXADDR_TOP
+ *                      fixed_addresses
+ * FIXADDR_START
+ *                      temp fixed addresses
+ * FIXADDR_BOOT_START
+ *                      Persistent kmap area
+ * PKMAP_BASE
+ * VMALLOC_END
+ *                      Vmalloc area
+ * VMALLOC_START
+ * high_memory
+ */
+#define PKMAP_BASE ( (FIXADDR_BOOT_START - PAGE_SIZE*(LAST_PKMAP + 1)) & PMD_MASK )
+#define LAST_PKMAP_MASK (LAST_PKMAP-1)
+#define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)
+#define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
+
+extern void * FASTCALL(kmap_high(struct page *page));
+extern void FASTCALL(kunmap_high(struct page *page));
+
+void *kmap(struct page *page);
+void kunmap(struct page *page);
+void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
+void *kmap_atomic(struct page *page, enum km_type type);
+void kunmap_atomic(void *kvaddr, enum km_type type);
+void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
+struct page *kmap_atomic_to_page(void *ptr);
+
+#ifndef CONFIG_PARAVIRT
+#define kmap_atomic_pte(page, type)     kmap_atomic(page, type)
+#endif
+
+#define flush_cache_kmaps()     do { } while (0)
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_HIGHMEM_H */
diff --git a/include/asm-x86/hpet.h b/include/asm-x86/hpet.h
new file mode 100644
index 000000000000..9eff48601254
--- /dev/null
+++ b/include/asm-x86/hpet.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "hpet_32.h"
+#else
+# include "hpet_64.h"
+#endif
diff --git a/include/asm-x86/hpet_32.h b/include/asm-x86/hpet_32.h
new file mode 100644
index 000000000000..c82dc7ed96b3
--- /dev/null
+++ b/include/asm-x86/hpet_32.h
@@ -0,0 +1,90 @@
+
+#ifndef _I386_HPET_H
+#define _I386_HPET_H
+
+#ifdef CONFIG_HPET_TIMER
+
+/*
+ * Documentation on HPET can be found at:
+ *      http://www.intel.com/ial/home/sp/pcmmspec.htm
+ *      ftp://download.intel.com/ial/home/sp/mmts098.pdf
+ */
+
+#define HPET_MMAP_SIZE          1024
+
+#define HPET_ID                 0x000
+#define HPET_PERIOD             0x004
+#define HPET_CFG                0x010
+#define HPET_STATUS             0x020
+#define HPET_COUNTER            0x0f0
+#define HPET_T0_CFG             0x100
+#define HPET_T0_CMP             0x108
+#define HPET_T0_ROUTE           0x110
+#define HPET_T1_CFG             0x120
+#define HPET_T1_CMP             0x128
+#define HPET_T1_ROUTE           0x130
+#define HPET_T2_CFG             0x140
+#define HPET_T2_CMP             0x148
+#define HPET_T2_ROUTE           0x150
+
+#define HPET_ID_REV             0x000000ff
+#define HPET_ID_NUMBER          0x00001f00
+#define HPET_ID_64BIT           0x00002000
+#define HPET_ID_LEGSUP          0x00008000
+#define HPET_ID_VENDOR          0xffff0000
+#define HPET_ID_NUMBER_SHIFT    8
+#define HPET_ID_VENDOR_SHIFT    16
+
+#define HPET_ID_VENDOR_8086     0x8086
+
+#define HPET_CFG_ENABLE         0x001
+#define HPET_CFG_LEGACY         0x002
+#define HPET_LEGACY_8254        2
+#define HPET_LEGACY_RTC         8
+
+#define HPET_TN_LEVEL           0x0002
+#define HPET_TN_ENABLE          0x0004
+#define HPET_TN_PERIODIC        0x0008
+#define HPET_TN_PERIODIC_CAP    0x0010
+#define HPET_TN_64BIT_CAP       0x0020
+#define HPET_TN_SETVAL          0x0040
+#define HPET_TN_32BIT           0x0100
+#define HPET_TN_ROUTE           0x3e00
+#define HPET_TN_FSB             0x4000
+#define HPET_TN_FSB_CAP         0x8000
+#define HPET_TN_ROUTE_SHIFT     9
+
+/* Max HPET Period is 10^8 femto sec as in HPET spec */
+#define HPET_MAX_PERIOD         100000000UL
+/*
+ * Min HPET period is 10^5 femto sec just for safety. If it is less than this,
+ * then 32 bit HPET counter wrapsaround in less than 0.5 sec.
+ */
+#define HPET_MIN_PERIOD         100000UL
+
+/* hpet memory map physical address */
+extern unsigned long hpet_address;
+extern int is_hpet_enabled(void);
+extern int hpet_enable(void);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+
+#include <linux/interrupt.h>
+
+extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask);
+extern int hpet_set_rtc_irq_bit(unsigned long bit_mask);
+extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
+                               unsigned char sec);
+extern int hpet_set_periodic_freq(unsigned long freq);
+extern int hpet_rtc_dropped_irq(void);
+extern int hpet_rtc_timer_init(void);
+extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id);
+
+#endif /* CONFIG_HPET_EMULATE_RTC */
+
+#else
+
+static inline int hpet_enable(void) { return 0; }
+
+#endif /* CONFIG_HPET_TIMER */
+#endif /* _I386_HPET_H */
diff --git a/include/asm-x86/hpet_64.h b/include/asm-x86/hpet_64.h
new file mode 100644
index 000000000000..fd4decac93a8
--- /dev/null
+++ b/include/asm-x86/hpet_64.h
@@ -0,0 +1,18 @@
+#ifndef _ASM_X8664_HPET_H
+#define _ASM_X8664_HPET_H 1
+
+#include <asm/hpet_32.h>
+
+#define HPET_TICK_RATE (HZ * 100000UL)
+
+extern int hpet_rtc_timer_init(void);
+extern int hpet_arch_init(void);
+extern int hpet_timer_stop_set_go(unsigned long tick);
+extern int hpet_reenable(void);
+extern unsigned int hpet_calibrate_tsc(void);
+
+extern int hpet_use_timer;
+extern unsigned long hpet_period;
+extern unsigned long hpet_tick;
+
+#endif
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
new file mode 100644
index 000000000000..bf025399d939
--- /dev/null
+++ b/include/asm-x86/hw_irq.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "hw_irq_32.h"
+#else
+# include "hw_irq_64.h"
+#endif
diff --git a/include/asm-x86/hw_irq_32.h b/include/asm-x86/hw_irq_32.h
new file mode 100644
index 000000000000..0bedbdf5e907
--- /dev/null
+++ b/include/asm-x86/hw_irq_32.h
@@ -0,0 +1,66 @@
+#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 (*interrupt[NR_IRQS])(void);
+
+#ifdef CONFIG_SMP
+fastcall void reschedule_interrupt(void);
+fastcall void invalidate_interrupt(void);
+fastcall void call_function_interrupt(void);
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+fastcall void apic_timer_interrupt(void);
+fastcall void error_interrupt(void);
+fastcall void spurious_interrupt(void);
+fastcall 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 FASTCALL(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
new file mode 100644
index 000000000000..09dfc18a6dd0
--- /dev/null
+++ b/include/asm-x86/hw_irq_64.h
@@ -0,0 +1,175 @@
+#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 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 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))
+
+#define __STR(x) #x
+#define STR(x) __STR(x)
+
+#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/hypertransport.h b/include/asm-x86/hypertransport.h
new file mode 100644
index 000000000000..c16c6ff4bdd7
--- /dev/null
+++ b/include/asm-x86/hypertransport.h
@@ -0,0 +1,42 @@
+#ifndef ASM_HYPERTRANSPORT_H
+#define ASM_HYPERTRANSPORT_H
+
+/*
+ * Constants for x86 Hypertransport Interrupts.
+ */
+
+#define HT_IRQ_LOW_BASE                 0xf8000000
+
+#define HT_IRQ_LOW_VECTOR_SHIFT         16
+#define  HT_IRQ_LOW_VECTOR_MASK         0x00ff0000
+#define  HT_IRQ_LOW_VECTOR(v)           (((v) << HT_IRQ_LOW_VECTOR_SHIFT) & HT_IRQ_LOW_VECTOR_MASK)
+
+#define HT_IRQ_LOW_DEST_ID_SHIFT        8
+#define  HT_IRQ_LOW_DEST_ID_MASK        0x0000ff00
+#define  HT_IRQ_LOW_DEST_ID(v)          (((v) << HT_IRQ_LOW_DEST_ID_SHIFT) & HT_IRQ_LOW_DEST_ID_MASK)
+
+#define HT_IRQ_LOW_DM_PHYSICAL          0x0000000
+#define HT_IRQ_LOW_DM_LOGICAL           0x0000040
+
+#define HT_IRQ_LOW_RQEOI_EDGE           0x0000000
+#define HT_IRQ_LOW_RQEOI_LEVEL          0x0000020
+
+
+#define HT_IRQ_LOW_MT_FIXED             0x0000000
+#define HT_IRQ_LOW_MT_ARBITRATED        0x0000004
+#define HT_IRQ_LOW_MT_SMI               0x0000008
+#define HT_IRQ_LOW_MT_NMI               0x000000c
+#define HT_IRQ_LOW_MT_INIT              0x0000010
+#define HT_IRQ_LOW_MT_STARTUP           0x0000014
+#define HT_IRQ_LOW_MT_EXTINT            0x0000018
+#define HT_IRQ_LOW_MT_LINT1             0x000008c
+#define HT_IRQ_LOW_MT_LINT0             0x0000098
+
+#define HT_IRQ_LOW_IRQ_MASKED           0x0000001
+
+
+#define HT_IRQ_HIGH_DEST_ID_SHIFT       0
+#define  HT_IRQ_HIGH_DEST_ID_MASK       0x00ffffff
+#define  HT_IRQ_HIGH_DEST_ID(v)         ((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK)
+
+#endif /* ASM_HYPERTRANSPORT_H */
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
new file mode 100644
index 000000000000..a8bbed349664
--- /dev/null
+++ b/include/asm-x86/i387.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "i387_32.h"
+#else
+# include "i387_64.h"
+#endif
diff --git a/include/asm-x86/i387_32.h b/include/asm-x86/i387_32.h
new file mode 100644
index 000000000000..cdd1e248e3b4
--- /dev/null
+++ b/include/asm-x86/i387_32.h
@@ -0,0 +1,151 @@
+/*
+ * include/asm-i386/i387.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *      Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#ifndef __ASM_I386_I387_H
+#define __ASM_I386_I387_H
+
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+
+extern void mxcsr_feature_mask_init(void);
+extern void init_fpu(struct task_struct *);
+
+/*
+ * FPU lazy state save handling...
+ */
+
+/*
+ * The "nop" is needed to make the instructions the same
+ * length.
+ */
+#define restore_fpu(tsk)                        \
+        alternative_input(                      \
+                "nop ; frstor %1",              \
+                "fxrstor %1",                   \
+                X86_FEATURE_FXSR,               \
+                "m" ((tsk)->thread.i387.fxsave))
+
+extern void kernel_fpu_begin(void);
+#define kernel_fpu_end() do { stts(); preempt_enable(); } while(0)
+
+/* We need a safe address that is cheap to find and that is already
+   in L1 during context switch. The best choices are unfortunately
+   different for UP and SMP */
+#ifdef CONFIG_SMP
+#define safe_address (__per_cpu_offset[0])
+#else
+#define safe_address (kstat_cpu(0).cpustat.user)
+#endif
+
+/*
+ * These must be called with preempt disabled
+ */
+static inline void __save_init_fpu( struct task_struct *tsk )
+{
+        /* Use more nops than strictly needed in case the compiler
+           varies code */
+        alternative_input(
+                "fnsave %[fx] ;fwait;" GENERIC_NOP8 GENERIC_NOP4,
+                "fxsave %[fx]\n"
+                "bt $7,%[fsw] ; jnc 1f ; fnclex\n1:",
+                X86_FEATURE_FXSR,
+                [fx] "m" (tsk->thread.i387.fxsave),
+                [fsw] "m" (tsk->thread.i387.fxsave.swd) : "memory");
+        /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+           is pending.  Clear the x87 state here by setting it to fixed
+           values. safe_address is a random variable that should be in L1 */
+        alternative_input(
+                GENERIC_NOP8 GENERIC_NOP2,
+                "emms\n\t"              /* clear stack tags */
+                "fildl %[addr]",        /* set F?P to defined value */
+                X86_FEATURE_FXSAVE_LEAK,
+                [addr] "m" (safe_address));
+        task_thread_info(tsk)->status &= ~TS_USEDFPU;
+}
+
+#define __unlazy_fpu( tsk ) do {                                \
+        if (task_thread_info(tsk)->status & TS_USEDFPU) {       \
+                __save_init_fpu(tsk);                           \
+                stts();                                         \
+        } else                                                  \
+                tsk->fpu_counter = 0;                           \
+} while (0)
+
+#define __clear_fpu( tsk )                                      \
+do {                                                            \
+        if (task_thread_info(tsk)->status & TS_USEDFPU) {       \
+                asm volatile("fnclex ; fwait");                 \
+                task_thread_info(tsk)->status &= ~TS_USEDFPU;   \
+                stts();                                         \
+        }                                                       \
+} while (0)
+
+
+/*
+ * These disable preemption on their own and are safe
+ */
+static inline void save_init_fpu( struct task_struct *tsk )
+{
+        preempt_disable();
+        __save_init_fpu(tsk);
+        stts();
+        preempt_enable();
+}
+
+#define unlazy_fpu( tsk ) do {  \
+        preempt_disable();      \
+        __unlazy_fpu(tsk);      \
+        preempt_enable();       \
+} while (0)
+
+#define clear_fpu( tsk ) do {   \
+        preempt_disable();      \
+        __clear_fpu( tsk );     \
+        preempt_enable();       \
+} while (0)
+
+/*
+ * FPU state interaction...
+ */
+extern unsigned short get_fpu_cwd( struct task_struct *tsk );
+extern unsigned short get_fpu_swd( struct task_struct *tsk );
+extern unsigned short get_fpu_mxcsr( struct task_struct *tsk );
+extern asmlinkage void math_state_restore(void);
+
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387( struct _fpstate __user *buf );
+extern int restore_i387( struct _fpstate __user *buf );
+
+/*
+ * ptrace request handers...
+ */
+extern int get_fpregs( struct user_i387_struct __user *buf,
+                       struct task_struct *tsk );
+extern int set_fpregs( struct task_struct *tsk,
+                       struct user_i387_struct __user *buf );
+
+extern int get_fpxregs( struct user_fxsr_struct __user *buf,
+                        struct task_struct *tsk );
+extern int set_fpxregs( struct task_struct *tsk,
+                        struct user_fxsr_struct __user *buf );
+
+/*
+ * FPU state for core dumps...
+ */
+extern int dump_fpu( struct pt_regs *regs,
+                     struct user_i387_struct *fpu );
+
+#endif /* __ASM_I386_I387_H */
diff --git a/include/asm-x86/i387_64.h b/include/asm-x86/i387_64.h
new file mode 100644
index 000000000000..0217b74cc9fc
--- /dev/null
+++ b/include/asm-x86/i387_64.h
@@ -0,0 +1,209 @@
+/*
+ * include/asm-x86_64/i387.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *      Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef __ASM_X86_64_I387_H
+#define __ASM_X86_64_I387_H
+
+#include <linux/sched.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+#include <asm/thread_info.h>
+#include <asm/uaccess.h>
+
+extern void fpu_init(void);
+extern unsigned int mxcsr_feature_mask;
+extern void mxcsr_feature_mask_init(void);
+extern void init_fpu(struct task_struct *child);
+extern int save_i387(struct _fpstate __user *buf);
+extern asmlinkage void math_state_restore(void);
+
+/*
+ * FPU lazy state save handling...
+ */
+
+#define unlazy_fpu(tsk) do { \
+        if (task_thread_info(tsk)->status & TS_USEDFPU) \
+                save_init_fpu(tsk);                     \
+        else                                            \
+                tsk->fpu_counter = 0;                   \
+} while (0)
+
+/* Ignore delayed exceptions from user space */
+static inline void tolerant_fwait(void)
+{
+        asm volatile("1: fwait\n"
+                     "2:\n"
+                     "   .section __ex_table,\"a\"\n"
+                     "  .align 8\n"
+                     "  .quad 1b,2b\n"
+                     "  .previous\n");
+}
+
+#define clear_fpu(tsk) do { \
+        if (task_thread_info(tsk)->status & TS_USEDFPU) {       \
+                tolerant_fwait();                               \
+                task_thread_info(tsk)->status &= ~TS_USEDFPU;   \
+                stts();                                         \
+        }                                                       \
+} while (0)
+
+/*
+ * ptrace request handers...
+ */
+extern int get_fpregs(struct user_i387_struct __user *buf,
+                      struct task_struct *tsk);
+extern int set_fpregs(struct task_struct *tsk,
+                      struct user_i387_struct __user *buf);
+
+/*
+ * i387 state interaction
+ */
+#define get_fpu_mxcsr(t) ((t)->thread.i387.fxsave.mxcsr)
+#define get_fpu_cwd(t) ((t)->thread.i387.fxsave.cwd)
+#define get_fpu_fxsr_twd(t) ((t)->thread.i387.fxsave.twd)
+#define get_fpu_swd(t) ((t)->thread.i387.fxsave.swd)
+#define set_fpu_cwd(t,val) ((t)->thread.i387.fxsave.cwd = (val))
+#define set_fpu_swd(t,val) ((t)->thread.i387.fxsave.swd = (val))
+#define set_fpu_fxsr_twd(t,val) ((t)->thread.i387.fxsave.twd = (val))
+
+#define X87_FSW_ES (1 << 7)     /* Exception Summary */
+
+/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
+   is pending. Clear the x87 state here by setting it to fixed
+   values. The kernel data segment can be sometimes 0 and sometimes
+   new user value. Both should be ok.
+   Use the PDA as safe address because it should be already in L1. */
+static inline void clear_fpu_state(struct i387_fxsave_struct *fx)
+{
+        if (unlikely(fx->swd & X87_FSW_ES))
+                 asm volatile("fnclex");
+        alternative_input(ASM_NOP8 ASM_NOP2,
+                     "    emms\n"               /* clear stack tags */
+                     "    fildl %%gs:0",        /* load to clear state */
+                     X86_FEATURE_FXSAVE_LEAK);
+}
+
+static inline int restore_fpu_checking(struct i387_fxsave_struct *fx) 
+{ 
+        int err;
+
+        asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
+                     "2:\n"
+                     ".section .fixup,\"ax\"\n"
+                     "3:  movl $-1,%[err]\n"
+                     "    jmp  2b\n"
+                     ".previous\n"
+                     ".section __ex_table,\"a\"\n"
+                     "   .align 8\n"
+                     "   .quad  1b,3b\n"
+                     ".previous"
+                     : [err] "=r" (err)
+#if 0 /* See comment in __fxsave_clear() below. */
+                     : [fx] "r" (fx), "m" (*fx), "0" (0));
+#else
+                     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
+#endif
+        if (unlikely(err))
+                init_fpu(current);
+        return err;
+} 
+
+static inline int save_i387_checking(struct i387_fxsave_struct __user *fx) 
+{ 
+        int err;
+
+        asm volatile("1:  rex64/fxsave (%[fx])\n\t"
+                     "2:\n"
+                     ".section .fixup,\"ax\"\n"
+                     "3:  movl $-1,%[err]\n"
+                     "    jmp  2b\n"
+                     ".previous\n"
+                     ".section __ex_table,\"a\"\n"
+                     "   .align 8\n"
+                     "   .quad  1b,3b\n"
+                     ".previous"
+                     : [err] "=r" (err), "=m" (*fx)
+#if 0 /* See comment in __fxsave_clear() below. */
+                     : [fx] "r" (fx), "0" (0));
+#else
+                     : [fx] "cdaSDb" (fx), "0" (0));
+#endif
+        if (unlikely(err) && __clear_user(fx, sizeof(struct i387_fxsave_struct)))
+                err = -EFAULT;
+        /* No need to clear here because the caller clears USED_MATH */
+        return err;
+} 
+
+static inline void __fxsave_clear(struct task_struct *tsk)
+{
+        /* Using "rex64; fxsave %0" is broken because, if the memory operand
+           uses any extended registers for addressing, a second REX prefix
+           will be generated (to the assembler, rex64 followed by semicolon
+           is a separate instruction), and hence the 64-bitness is lost. */
+#if 0
+        /* Using "fxsaveq %0" would be the ideal choice, but is only supported
+           starting with gas 2.16. */
+        __asm__ __volatile__("fxsaveq %0"
+                             : "=m" (tsk->thread.i387.fxsave));
+#elif 0
+        /* Using, as a workaround, the properly prefixed form below isn't
+           accepted by any binutils version so far released, complaining that
+           the same type of prefix is used twice if an extended register is
+           needed for addressing (fix submitted to mainline 2005-11-21). */
+        __asm__ __volatile__("rex64/fxsave %0"
+                             : "=m" (tsk->thread.i387.fxsave));
+#else
+        /* This, however, we can work around by forcing the compiler to select
+           an addressing mode that doesn't require extended registers. */
+        __asm__ __volatile__("rex64/fxsave %P2(%1)"
+                             : "=m" (tsk->thread.i387.fxsave)
+                             : "cdaSDb" (tsk),
+                                "i" (offsetof(__typeof__(*tsk),
+                                              thread.i387.fxsave)));
+#endif
+        clear_fpu_state(&tsk->thread.i387.fxsave);
+}
+
+static inline void kernel_fpu_begin(void)
+{
+        struct thread_info *me = current_thread_info();
+        preempt_disable();
+        if (me->status & TS_USEDFPU) {
+                __fxsave_clear(me->task);
+                me->status &= ~TS_USEDFPU;
+                return;
+        }
+        clts();
+}
+
+static inline void kernel_fpu_end(void)
+{
+        stts();
+        preempt_enable();
+}
+
+static inline void save_init_fpu(struct task_struct *tsk)
+{
+        __fxsave_clear(tsk);
+        task_thread_info(tsk)->status &= ~TS_USEDFPU;
+        stts();
+}
+
+/* 
+ * This restores directly out of user space. Exceptions are handled.
+ */
+static inline int restore_i387(struct _fpstate __user *buf)
+{
+        return restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+}
+
+#endif /* __ASM_X86_64_I387_H */
diff --git a/include/asm-x86/i8253.h b/include/asm-x86/i8253.h
new file mode 100644
index 000000000000..b2a4f995a33f
--- /dev/null
+++ b/include/asm-x86/i8253.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "i8253_32.h"
+#else
+# include "i8253_64.h"
+#endif
diff --git a/include/asm-x86/i8253_32.h b/include/asm-x86/i8253_32.h
new file mode 100644
index 000000000000..7577d058d86e
--- /dev/null
+++ b/include/asm-x86/i8253_32.h
@@ -0,0 +1,17 @@
+#ifndef __ASM_I8253_H__
+#define __ASM_I8253_H__
+
+#include <linux/clockchips.h>
+
+/* i8253A PIT registers */
+#define PIT_MODE                0x43
+#define PIT_CH0                 0x40
+#define PIT_CH2                 0x42
+
+extern spinlock_t i8253_lock;
+
+extern struct clock_event_device *global_clock_event;
+
+extern void setup_pit_timer(void);
+
+#endif  /* __ASM_I8253_H__ */
diff --git a/include/asm-x86/i8253_64.h b/include/asm-x86/i8253_64.h
new file mode 100644
index 000000000000..015d8df07690
--- /dev/null
+++ b/include/asm-x86/i8253_64.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_I8253_H__
+#define __ASM_I8253_H__
+
+extern spinlock_t i8253_lock;
+
+#endif  /* __ASM_I8253_H__ */
diff --git a/include/asm-x86/i8259.h b/include/asm-x86/i8259.h
new file mode 100644
index 000000000000..29d8f9a6b3fc
--- /dev/null
+++ b/include/asm-x86/i8259.h
@@ -0,0 +1,17 @@
+#ifndef __ASM_I8259_H__
+#define __ASM_I8259_H__
+
+extern unsigned int cached_irq_mask;
+
+#define __byte(x,y)             (((unsigned char *) &(y))[x])
+#define cached_master_mask      (__byte(0, cached_irq_mask))
+#define cached_slave_mask       (__byte(1, cached_irq_mask))
+
+extern spinlock_t i8259A_lock;
+
+extern void init_8259A(int auto_eoi);
+extern void enable_8259A_irq(unsigned int irq);
+extern void disable_8259A_irq(unsigned int irq);
+extern unsigned int startup_8259A_irq(unsigned int irq);
+
+#endif  /* __ASM_I8259_H__ */
diff --git a/include/asm-x86/ia32.h b/include/asm-x86/ia32.h
new file mode 100644
index 000000000000..0190b7c4e319
--- /dev/null
+++ b/include/asm-x86/ia32.h
@@ -0,0 +1,178 @@
+#ifndef _ASM_X86_64_IA32_H
+#define _ASM_X86_64_IA32_H
+
+
+#ifdef CONFIG_IA32_EMULATION
+
+#include <linux/compat.h>
+
+/*
+ * 32 bit structures for IA32 support.
+ */
+
+#include <asm/sigcontext32.h>
+
+/* signal.h */
+struct sigaction32 {
+       unsigned int  sa_handler;        /* Really a pointer, but need to deal 
+                                             with 32 bits */
+       unsigned int sa_flags;
+       unsigned int sa_restorer;        /* Another 32 bit pointer */
+       compat_sigset_t sa_mask;         /* A 32 bit mask */
+};
+
+struct old_sigaction32 {
+       unsigned int  sa_handler;        /* Really a pointer, but need to deal 
+                                             with 32 bits */
+       compat_old_sigset_t sa_mask;             /* A 32 bit mask */
+       unsigned int sa_flags;
+       unsigned int sa_restorer;        /* Another 32 bit pointer */
+};
+
+typedef struct sigaltstack_ia32 {
+        unsigned int    ss_sp;
+        int             ss_flags;
+        unsigned int    ss_size;
+} stack_ia32_t;
+
+struct ucontext_ia32 {
+        unsigned int      uc_flags;
+        unsigned int      uc_link;
+        stack_ia32_t      uc_stack;
+        struct sigcontext_ia32 uc_mcontext;
+        compat_sigset_t   uc_sigmask;   /* mask last for extensibility */
+};
+
+/* This matches struct stat64 in glibc2.2, hence the absolutely
+ * insane amounts of padding around dev_t's.
+ */
+struct stat64 {
+        unsigned long long      st_dev;
+        unsigned char           __pad0[4];
+
+#define STAT64_HAS_BROKEN_ST_INO        1
+        unsigned int            __st_ino;
+
+        unsigned int            st_mode;
+        unsigned int            st_nlink;
+
+        unsigned int            st_uid;
+        unsigned int            st_gid;
+
+        unsigned long long      st_rdev;
+        unsigned char           __pad3[4];
+
+        long long               st_size;
+        unsigned int            st_blksize;
+
+        long long               st_blocks;/* Number 512-byte blocks allocated. */
+
+        unsigned                st_atime;
+        unsigned                st_atime_nsec;
+        unsigned                st_mtime;
+        unsigned                st_mtime_nsec;
+        unsigned                st_ctime;
+        unsigned                st_ctime_nsec;
+
+        unsigned long long      st_ino;
+} __attribute__((packed));
+
+typedef struct compat_siginfo{
+        int si_signo;
+        int si_errno;
+        int si_code;
+
+        union {
+                int _pad[((128/sizeof(int)) - 3)];
+
+                /* kill() */
+                struct {
+                        unsigned int _pid;      /* sender's pid */
+                        unsigned int _uid;      /* sender's uid */
+                } _kill;
+
+                /* POSIX.1b timers */
+                struct {
+                        compat_timer_t _tid;    /* timer id */
+                        int _overrun;           /* overrun count */
+                        compat_sigval_t _sigval;        /* same as below */
+                        int _sys_private;       /* not to be passed to user */
+                        int _overrun_incr;      /* amount to add to overrun */
+                } _timer;
+
+                /* POSIX.1b signals */
+                struct {
+                        unsigned int _pid;      /* sender's pid */
+                        unsigned int _uid;      /* sender's uid */
+                        compat_sigval_t _sigval;
+                } _rt;
+
+                /* SIGCHLD */
+                struct {
+                        unsigned int _pid;      /* which child */
+                        unsigned int _uid;      /* sender's uid */
+                        int _status;            /* exit code */
+                        compat_clock_t _utime;
+                        compat_clock_t _stime;
+                } _sigchld;
+
+                /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
+                struct {
+                        unsigned int _addr;     /* faulting insn/memory ref. */
+                } _sigfault;
+
+                /* SIGPOLL */
+                struct {
+                        int _band;      /* POLL_IN, POLL_OUT, POLL_MSG */
+                        int _fd;
+                } _sigpoll;
+        } _sifields;
+} compat_siginfo_t;
+
+struct sigframe32
+{
+        u32 pretcode;
+        int sig;
+        struct sigcontext_ia32 sc;
+        struct _fpstate_ia32 fpstate;
+        unsigned int extramask[_COMPAT_NSIG_WORDS-1];
+};
+
+struct rt_sigframe32
+{
+        u32 pretcode;
+        int sig;
+        u32 pinfo;
+        u32 puc;
+        compat_siginfo_t info;
+        struct ucontext_ia32 uc;
+        struct _fpstate_ia32 fpstate;
+};
+
+struct ustat32 {
+        __u32   f_tfree;
+        compat_ino_t            f_tinode;
+        char                    f_fname[6];
+        char                    f_fpack[6];
+};
+
+#define IA32_STACK_TOP IA32_PAGE_OFFSET
+
+#ifdef __KERNEL__
+struct user_desc;
+struct siginfo_t;
+int do_get_thread_area(struct thread_struct *t, struct user_desc __user *info);
+int do_set_thread_area(struct thread_struct *t, struct user_desc __user *info);
+int ia32_child_tls(struct task_struct *p, struct pt_regs *childregs);
+
+struct linux_binprm;
+extern int ia32_setup_arg_pages(struct linux_binprm *bprm,
+                                unsigned long stack_top, int exec_stack);
+struct mm_struct;
+extern void ia32_pick_mmap_layout(struct mm_struct *mm);
+
+#endif
+
+#endif /* !CONFIG_IA32_SUPPORT */
+ 
+#endif 
diff --git a/include/asm-x86/ia32_unistd.h b/include/asm-x86/ia32_unistd.h
new file mode 100644
index 000000000000..5b52ce507338
--- /dev/null
+++ b/include/asm-x86/ia32_unistd.h
@@ -0,0 +1,18 @@
+#ifndef _ASM_X86_64_IA32_UNISTD_H_
+#define _ASM_X86_64_IA32_UNISTD_H_
+
+/*
+ * This file contains the system call numbers of the ia32 port,
+ * this is for the kernel only.
+ * Only add syscalls here where some part of the kernel needs to know
+ * the number. This should be otherwise in sync with asm-i386/unistd.h. -AK
+ */
+
+#define __NR_ia32_restart_syscall 0
+#define __NR_ia32_exit            1
+#define __NR_ia32_read            3
+#define __NR_ia32_write           4
+#define __NR_ia32_sigreturn     119
+#define __NR_ia32_rt_sigreturn  173
+
+#endif /* _ASM_X86_64_IA32_UNISTD_H_ */
diff --git a/include/asm-x86/ide.h b/include/asm-x86/ide.h
new file mode 100644
index 000000000000..e7817a3d6578
--- /dev/null
+++ b/include/asm-x86/ide.h
@@ -0,0 +1,78 @@
+/*
+ *  linux/include/asm-i386/ide.h
+ *
+ *  Copyright (C) 1994-1996  Linus Torvalds & authors
+ */
+
+/*
+ *  This file contains the i386 architecture specific IDE code.
+ */
+
+#ifndef __ASMi386_IDE_H
+#define __ASMi386_IDE_H
+
+#ifdef __KERNEL__
+
+
+#ifndef MAX_HWIFS
+# ifdef CONFIG_BLK_DEV_IDEPCI
+#define MAX_HWIFS       10
+# else
+#define MAX_HWIFS       6
+# endif
+#endif
+
+#define IDE_ARCH_OBSOLETE_DEFAULTS
+
+static __inline__ int ide_default_irq(unsigned long base)
+{
+        switch (base) {
+                case 0x1f0: return 14;
+                case 0x170: return 15;
+                case 0x1e8: return 11;
+                case 0x168: return 10;
+                case 0x1e0: return 8;
+                case 0x160: return 12;
+                default:
+                        return 0;
+        }
+}
+
+static __inline__ unsigned long ide_default_io_base(int index)
+{
+        /*
+         *      If PCI is present then it is not safe to poke around
+         *      the other legacy IDE ports. Only 0x1f0 and 0x170 are
+         *      defined compatibility mode ports for PCI. A user can 
+         *      override this using ide= but we must default safe.
+         */
+        if (no_pci_devices()) {
+                switch(index) {
+                        case 2: return 0x1e8;
+                        case 3: return 0x168;
+                        case 4: return 0x1e0;
+                        case 5: return 0x160;
+                }
+        }
+        switch (index) {
+                case 0: return 0x1f0;
+                case 1: return 0x170;
+                default:
+                        return 0;
+        }
+}
+
+#define IDE_ARCH_OBSOLETE_INIT
+#define ide_default_io_ctl(base)        ((base) + 0x206) /* obsolete */
+
+#ifdef CONFIG_BLK_DEV_IDEPCI
+#define ide_init_default_irq(base)      (0)
+#else
+#define ide_init_default_irq(base)      ide_default_irq(base)
+#endif
+
+#include <asm-generic/ide_iops.h>
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASMi386_IDE_H */
diff --git a/include/asm-x86/idle.h b/include/asm-x86/idle.h
new file mode 100644
index 000000000000..6bd47dcf2067
--- /dev/null
+++ b/include/asm-x86/idle.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_X86_64_IDLE_H
+#define _ASM_X86_64_IDLE_H 1
+
+#define IDLE_START 1
+#define IDLE_END 2
+
+struct notifier_block;
+void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
+
+void enter_idle(void);
+void exit_idle(void);
+
+#endif
diff --git a/include/asm-x86/intel_arch_perfmon.h b/include/asm-x86/intel_arch_perfmon.h
new file mode 100644
index 000000000000..4f6d4e6bf57e
--- /dev/null
+++ b/include/asm-x86/intel_arch_perfmon.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "intel_arch_perfmon_32.h"
+#else
+# include "intel_arch_perfmon_64.h"
+#endif
diff --git a/include/asm-x86/intel_arch_perfmon_32.h b/include/asm-x86/intel_arch_perfmon_32.h
new file mode 100644
index 000000000000..b52cd60a075b
--- /dev/null
+++ b/include/asm-x86/intel_arch_perfmon_32.h
@@ -0,0 +1,31 @@
+#ifndef X86_INTEL_ARCH_PERFMON_H
+#define X86_INTEL_ARCH_PERFMON_H 1
+
+#define MSR_ARCH_PERFMON_PERFCTR0               0xc1
+#define MSR_ARCH_PERFMON_PERFCTR1               0xc2
+
+#define MSR_ARCH_PERFMON_EVENTSEL0              0x186
+#define MSR_ARCH_PERFMON_EVENTSEL1              0x187
+
+#define ARCH_PERFMON_EVENTSEL0_ENABLE      (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_INT          (1 << 20)
+#define ARCH_PERFMON_EVENTSEL_OS           (1 << 17)
+#define ARCH_PERFMON_EVENTSEL_USR          (1 << 16)
+
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL   (0x3c)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
+                                (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+
+union cpuid10_eax {
+        struct {
+                unsigned int version_id:8;
+                unsigned int num_counters:8;
+                unsigned int bit_width:8;
+                unsigned int mask_length:8;
+        } split;
+        unsigned int full;
+};
+
+#endif  /* X86_INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-x86/intel_arch_perfmon_64.h b/include/asm-x86/intel_arch_perfmon_64.h
new file mode 100644
index 000000000000..8633331420ec
--- /dev/null
+++ b/include/asm-x86/intel_arch_perfmon_64.h
@@ -0,0 +1,31 @@
+#ifndef X86_64_INTEL_ARCH_PERFMON_H
+#define X86_64_INTEL_ARCH_PERFMON_H 1
+
+#define MSR_ARCH_PERFMON_PERFCTR0               0xc1
+#define MSR_ARCH_PERFMON_PERFCTR1               0xc2
+
+#define MSR_ARCH_PERFMON_EVENTSEL0              0x186
+#define MSR_ARCH_PERFMON_EVENTSEL1              0x187
+
+#define ARCH_PERFMON_EVENTSEL0_ENABLE      (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_INT          (1 << 20)
+#define ARCH_PERFMON_EVENTSEL_OS           (1 << 17)
+#define ARCH_PERFMON_EVENTSEL_USR          (1 << 16)
+
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL   (0x3c)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
+                                (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+
+union cpuid10_eax {
+        struct {
+                unsigned int version_id:8;
+                unsigned int num_counters:8;
+                unsigned int bit_width:8;
+                unsigned int mask_length:8;
+        } split;
+        unsigned int full;
+};
+
+#endif  /* X86_64_INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h
new file mode 100644
index 000000000000..5a58b176dd61
--- /dev/null
+++ b/include/asm-x86/io.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "io_32.h"
+#else
+# include "io_64.h"
+#endif
diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h
new file mode 100644
index 000000000000..e8e0bd641120
--- /dev/null
+++ b/include/asm-x86/io_32.h
@@ -0,0 +1,349 @@
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+#include <linux/string.h>
+#include <linux/compiler.h>
+
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ *              Linus
+ */
+
+ /*
+  *  Bit simplified and optimized by Jan Hubicka
+  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+  *
+  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+  *  isa_read[wl] and isa_write[wl] fixed
+  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+  */
+
+#define IO_SPACE_LIMIT 0xffff
+
+#define XQUAD_PORTIO_BASE 0xfe400000
+#define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
+
+#ifdef __KERNEL__
+
+#include <asm-generic/iomap.h>
+
+#include <linux/vmalloc.h>
+
+/*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+#define xlate_dev_mem_ptr(p)    __va(p)
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)   p
+
+/**
+ *      virt_to_phys    -       map virtual addresses to physical
+ *      @address: address to remap
+ *
+ *      The returned physical address is the physical (CPU) mapping for
+ *      the memory address given. It is only valid to use this function on
+ *      addresses directly mapped or allocated via kmalloc. 
+ *
+ *      This function does not give bus mappings for DMA transfers. In
+ *      almost all conceivable cases a device driver should not be using
+ *      this function
+ */
+ 
+static inline unsigned long virt_to_phys(volatile void * address)
+{
+        return __pa(address);
+}
+
+/**
+ *      phys_to_virt    -       map physical address to virtual
+ *      @address: address to remap
+ *
+ *      The returned virtual address is a current CPU mapping for
+ *      the memory address given. It is only valid to use this function on
+ *      addresses that have a kernel mapping
+ *
+ *      This function does not handle bus mappings for DMA transfers. In
+ *      almost all conceivable cases a device driver should not be using
+ *      this function
+ */
+
+static inline void * phys_to_virt(unsigned long address)
+{
+        return __va(address);
+}
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+
+extern void __iomem * __ioremap(unsigned long offset, unsigned long size, unsigned long flags);
+
+/**
+ * ioremap     -   map bus memory into CPU space
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address. 
+ *
+ * If the area you are trying to map is a PCI BAR you should have a
+ * look at pci_iomap().
+ */
+
+static inline void __iomem * ioremap(unsigned long offset, unsigned long size)
+{
+        return __ioremap(offset, size, 0);
+}
+
+extern void __iomem * ioremap_nocache(unsigned long offset, unsigned long size);
+extern void iounmap(volatile void __iomem *addr);
+
+/*
+ * bt_ioremap() and bt_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 *bt_ioremap(unsigned long offset, unsigned long size);
+extern void bt_iounmap(void *addr, unsigned long size);
+extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
+
+/* Use early IO mappings for DMI because it's initialized early */
+#define dmi_ioremap bt_ioremap
+#define dmi_iounmap bt_iounmap
+#define dmi_alloc alloc_bootmem
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ */
+#define isa_virt_to_bus virt_to_phys
+#define isa_page_to_bus page_to_phys
+#define isa_bus_to_virt phys_to_virt
+
+/*
+ * However PCI ones are not necessarily 1:1 and therefore these interfaces
+ * are forbidden in portable PCI drivers.
+ *
+ * Allow them on x86 for legacy drivers, though.
+ */
+#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)
+{
+        memset((void __force *) addr, val, count);
+}
+static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
+{
+        __memcpy(dst, (void __force *) src, count);
+}
+static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count)
+{
+        __memcpy((void __force *) dst, src, count);
+}
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
+
+/*
+ *      Cache management
+ *
+ *      This needed for two cases
+ *      1. Out of order aware processors
+ *      2. Accidentally out of order processors (PPro errata #51)
+ */
+ 
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+static inline void flush_write_buffers(void)
+{
+        __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory");
+}
+
+#define dma_cache_inv(_start,_size)             flush_write_buffers()
+#define dma_cache_wback(_start,_size)           flush_write_buffers()
+#define dma_cache_wback_inv(_start,_size)       flush_write_buffers()
+
+#else
+
+/* Nothing to do */
+
+#define dma_cache_inv(_start,_size)             do { } while (0)
+#define dma_cache_wback(_start,_size)           do { } while (0)
+#define dma_cache_wback_inv(_start,_size)       do { } while (0)
+#define flush_write_buffers()
+
+#endif
+
+#endif /* __KERNEL__ */
+
+static inline void native_io_delay(void)
+{
+        asm volatile("outb %%al,$0x80" : : : "memory");
+}
+
+#if defined(CONFIG_PARAVIRT)
+#include <asm/paravirt.h>
+#else
+
+static inline void slow_down_io(void) {
+        native_io_delay();
+#ifdef REALLY_SLOW_IO
+        native_io_delay();
+        native_io_delay();
+        native_io_delay();
+#endif
+}
+
+#endif
+
+#ifdef CONFIG_X86_NUMAQ
+extern void *xquad_portio;    /* Where the IO area was mapped */
+#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port)
+#define __BUILDIO(bwl,bw,type) \
+static inline void out##bwl##_quad(unsigned type value, int port, int quad) { \
+        if (xquad_portio) \
+                write##bwl(value, XQUAD_PORT_ADDR(port, quad)); \
+        else \
+                out##bwl##_local(value, port); \
+} \
+static inline void out##bwl(unsigned type value, int port) { \
+        out##bwl##_quad(value, port, 0); \
+} \
+static inline unsigned type in##bwl##_quad(int port, int quad) { \
+        if (xquad_portio) \
+                return read##bwl(XQUAD_PORT_ADDR(port, quad)); \
+        else \
+                return in##bwl##_local(port); \
+} \
+static inline unsigned type in##bwl(int port) { \
+        return in##bwl##_quad(port, 0); \
+}
+#else
+#define __BUILDIO(bwl,bw,type) \
+static inline void out##bwl(unsigned type value, int port) { \
+        out##bwl##_local(value, port); \
+} \
+static inline unsigned type in##bwl(int port) { \
+        return in##bwl##_local(port); \
+}
+#endif
+
+
+#define BUILDIO(bwl,bw,type) \
+static inline void out##bwl##_local(unsigned type value, int port) { \
+        __asm__ __volatile__("out" #bwl " %" #bw "0, %w1" : : "a"(value), "Nd"(port)); \
+} \
+static inline unsigned type in##bwl##_local(int port) { \
+        unsigned type value; \
+        __asm__ __volatile__("in" #bwl " %w1, %" #bw "0" : "=a"(value) : "Nd"(port)); \
+        return value; \
+} \
+static inline void out##bwl##_local_p(unsigned type value, int port) { \
+        out##bwl##_local(value, port); \
+        slow_down_io(); \
+} \
+static inline unsigned type in##bwl##_local_p(int port) { \
+        unsigned type value = in##bwl##_local(port); \
+        slow_down_io(); \
+        return value; \
+} \
+__BUILDIO(bwl,bw,type) \
+static inline void out##bwl##_p(unsigned type value, int port) { \
+        out##bwl(value, port); \
+        slow_down_io(); \
+} \
+static inline unsigned type in##bwl##_p(int port) { \
+        unsigned type value = in##bwl(port); \
+        slow_down_io(); \
+        return value; \
+} \
+static inline void outs##bwl(int port, const void *addr, unsigned long count) { \
+        __asm__ __volatile__("rep; outs" #bwl : "+S"(addr), "+c"(count) : "d"(port)); \
+} \
+static inline void ins##bwl(int port, void *addr, unsigned long count) { \
+        __asm__ __volatile__("rep; ins" #bwl : "+D"(addr), "+c"(count) : "d"(port)); \
+}
+
+BUILDIO(b,b,char)
+BUILDIO(w,w,short)
+BUILDIO(l,,int)
+
+#endif
diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h
new file mode 100644
index 000000000000..7475095c5061
--- /dev/null
+++ b/include/asm-x86/io_64.h
@@ -0,0 +1,276 @@
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ *              Linus
+ */
+
+ /*
+  *  Bit simplified and optimized by Jan Hubicka
+  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+  *
+  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+  *  isa_read[wl] and isa_write[wl] fixed
+  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+  */
+
+#define __SLOW_DOWN_IO "\noutb %%al,$0x80"
+
+#ifdef REALLY_SLOW_IO
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
+#else
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO
+#endif
+
+/*
+ * Talk about misusing macros..
+ */
+#define __OUT1(s,x) \
+static inline void out##s(unsigned x value, unsigned short port) {
+
+#define __OUT2(s,s1,s2) \
+__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1"
+
+#define __OUT(s,s1,x) \
+__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
+__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));} \
+
+#define __IN1(s) \
+static inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v;
+
+#define __IN2(s,s1,s2) \
+__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0"
+
+#define __IN(s,s1,i...) \
+__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+
+#define __INS(s) \
+static inline void ins##s(unsigned short port, void * addr, unsigned long count) \
+{ __asm__ __volatile__ ("rep ; ins" #s \
+: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define __OUTS(s) \
+static inline void outs##s(unsigned short port, const void * addr, unsigned long count) \
+{ __asm__ __volatile__ ("rep ; outs" #s \
+: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define RETURN_TYPE unsigned char
+__IN(b,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned short
+__IN(w,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned int
+__IN(l,"")
+#undef RETURN_TYPE
+
+__OUT(b,"b",char)
+__OUT(w,"w",short)
+__OUT(l,,int)
+
+__INS(b)
+__INS(w)
+__INS(l)
+
+__OUTS(b)
+__OUTS(w)
+__OUTS(l)
+
+#define IO_SPACE_LIMIT 0xffff
+
+#if defined(__KERNEL__) && defined(__x86_64__)
+
+#include <linux/vmalloc.h>
+
+#ifndef __i386__
+/*
+ * Change virtual addresses to physical addresses and vv.
+ * These are pretty trivial
+ */
+static inline unsigned long virt_to_phys(volatile void * address)
+{
+        return __pa(address);
+}
+
+static inline void * phys_to_virt(unsigned long address)
+{
+        return __va(address);
+}
+#endif
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+
+#include <asm-generic/iomap.h>
+
+extern void __iomem *__ioremap(unsigned long offset, unsigned long size, unsigned long flags);
+
+static inline void __iomem * ioremap (unsigned long offset, unsigned long size)
+{
+        return __ioremap(offset, size, 0);
+}
+
+extern void *early_ioremap(unsigned long addr, unsigned long size);
+extern void early_iounmap(void *addr, unsigned long size);
+
+/*
+ * This one maps high address device memory and turns off caching for that area.
+ * it's useful if some control registers are in such an area and write combining
+ * or read caching is not desirable:
+ */
+extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size);
+extern void iounmap(volatile void __iomem *addr);
+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
+#define isa_page_to_bus page_to_phys
+#define isa_bus_to_virt phys_to_virt
+
+/*
+ * However PCI ones are not necessarily 1:1 and therefore these interfaces
+ * are forbidden in portable PCI drivers.
+ *
+ * Allow them on x86 for legacy drivers, though.
+ */
+#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);
+
+static inline void memcpy_fromio(void *to, const volatile void __iomem *from, unsigned len)
+{
+        __memcpy_fromio(to,(unsigned long)from,len);
+}
+static inline void memcpy_toio(volatile void __iomem *to, const void *from, unsigned len)
+{
+        __memcpy_toio((unsigned long)to,from,len);
+}
+
+void memset_io(volatile void __iomem *a, int b, size_t c);
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
+
+/* Nothing to do */
+
+#define dma_cache_inv(_start,_size)             do { } while (0)
+#define dma_cache_wback(_start,_size)           do { } while (0)
+#define dma_cache_wback_inv(_start,_size)       do { } while (0)
+
+#define flush_write_buffers() 
+
+extern int iommu_bio_merge;
+#define BIO_VMERGE_BOUNDARY iommu_bio_merge
+
+/*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+#define xlate_dev_mem_ptr(p)    __va(p)
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)   p
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h
new file mode 100644
index 000000000000..88494966beeb
--- /dev/null
+++ b/include/asm-x86/io_apic.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "io_apic_32.h"
+#else
+# include "io_apic_64.h"
+#endif
diff --git a/include/asm-x86/io_apic_32.h b/include/asm-x86/io_apic_32.h
new file mode 100644
index 000000000000..dbe734ddf2af
--- /dev/null
+++ b/include/asm-x86/io_apic_32.h
@@ -0,0 +1,155 @@
+#ifndef __ASM_IO_APIC_H
+#define __ASM_IO_APIC_H
+
+#include <asm/types.h>
+#include <asm/mpspec.h>
+#include <asm/apicdef.h>
+
+/*
+ * Intel IO-APIC support for SMP and UP systems.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
+ */
+
+#ifdef CONFIG_X86_IO_APIC
+
+/*
+ * The structure of the IO-APIC:
+ */
+union IO_APIC_reg_00 {
+        u32     raw;
+        struct {
+                u32     __reserved_2    : 14,
+                        LTS             :  1,
+                        delivery_type   :  1,
+                        __reserved_1    :  8,
+                        ID              :  8;
+        } __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_01 {
+        u32     raw;
+        struct {
+                u32     version         :  8,
+                        __reserved_2    :  7,
+                        PRQ             :  1,
+                        entries         :  8,
+                        __reserved_1    :  8;
+        } __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_02 {
+        u32     raw;
+        struct {
+                u32     __reserved_2    : 24,
+                        arbitration     :  4,
+                        __reserved_1    :  4;
+        } __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_03 {
+        u32     raw;
+        struct {
+                u32     boot_DT         :  1,
+                        __reserved_1    : 31;
+        } __attribute__ ((packed)) bits;
+};
+
+/*
+ * # of IO-APICs and # of IRQ routing registers
+ */
+extern int nr_ioapics;
+extern int nr_ioapic_registers[MAX_IO_APICS];
+
+enum ioapic_irq_destination_types {
+        dest_Fixed = 0,
+        dest_LowestPrio = 1,
+        dest_SMI = 2,
+        dest__reserved_1 = 3,
+        dest_NMI = 4,
+        dest_INIT = 5,
+        dest__reserved_2 = 6,
+        dest_ExtINT = 7
+};
+
+struct IO_APIC_route_entry {
+        __u32   vector          :  8,
+                delivery_mode   :  3,   /* 000: FIXED
+                                         * 001: lowest prio
+                                         * 111: ExtINT
+                                         */
+                dest_mode       :  1,   /* 0: physical, 1: logical */
+                delivery_status :  1,
+                polarity        :  1,
+                irr             :  1,
+                trigger         :  1,   /* 0: edge, 1: level */
+                mask            :  1,   /* 0: enabled, 1: disabled */
+                __reserved_2    : 15;
+
+        union {         struct { __u32
+                                        __reserved_1    : 24,
+                                        physical_dest   :  4,
+                                        __reserved_2    :  4;
+                        } physical;
+
+                        struct { __u32
+                                        __reserved_1    : 24,
+                                        logical_dest    :  8;
+                        } logical;
+        } dest;
+
+} __attribute__ ((packed));
+
+/*
+ * MP-BIOS irq configuration table structures:
+ */
+
+/* I/O APIC entries */
+extern struct mpc_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];
+
+/* non-0 if default (table-less) MP configuration */
+extern int mpc_default_type;
+
+/* Older SiS APIC requires we rewrite the index register */
+extern int sis_apic_bug;
+
+/* 1 if "noapic" boot option passed */
+extern int skip_ioapic_setup;
+
+static inline void disable_ioapic_setup(void)
+{
+        skip_ioapic_setup = 1;
+}
+
+static inline int ioapic_setup_disabled(void)
+{
+        return skip_ioapic_setup;
+}
+
+/*
+ * If we use the IO-APIC for IRQ routing, disable automatic
+ * assignment of PCI IRQ's.
+ */
+#define io_apic_assign_pci_irqs (mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
+
+#ifdef CONFIG_ACPI
+extern int io_apic_get_unique_id (int ioapic, int apic_id);
+extern int io_apic_get_version (int ioapic);
+extern int io_apic_get_redir_entries (int ioapic);
+extern int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low);
+extern int timer_uses_ioapic_pin_0;
+#endif /* CONFIG_ACPI */
+
+extern int (*ioapic_renumber_irq)(int ioapic, int irq);
+
+#else  /* !CONFIG_X86_IO_APIC */
+#define io_apic_assign_pci_irqs 0
+#endif
+
+#endif
diff --git a/include/asm-x86/io_apic_64.h b/include/asm-x86/io_apic_64.h
new file mode 100644
index 000000000000..d9f2e54324d5
--- /dev/null
+++ b/include/asm-x86/io_apic_64.h
@@ -0,0 +1,136 @@
+#ifndef __ASM_IO_APIC_H
+#define __ASM_IO_APIC_H
+
+#include <asm/types.h>
+#include <asm/mpspec.h>
+#include <asm/apicdef.h>
+
+/*
+ * Intel IO-APIC support for SMP and UP systems.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
+ */
+
+#define APIC_MISMATCH_DEBUG
+
+/*
+ * The structure of the IO-APIC:
+ */
+union IO_APIC_reg_00 {
+        u32     raw;
+        struct {
+                u32     __reserved_2    : 14,
+                        LTS             :  1,
+                        delivery_type   :  1,
+                        __reserved_1    :  8,
+                        ID              :  8;
+        } __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_01 {
+        u32     raw;
+        struct {
+                u32     version         :  8,
+                __reserved_2    :  7,
+                PRQ             :  1,
+                entries         :  8,
+                __reserved_1    :  8;
+        } __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_02 {
+        u32     raw;
+        struct {
+                u32     __reserved_2    : 24,
+                arbitration     :  4,
+                __reserved_1    :  4;
+        } __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_03 {
+        u32     raw;
+        struct {
+                u32     boot_DT         :  1,
+                        __reserved_1    : 31;
+        } __attribute__ ((packed)) bits;
+};
+
+/*
+ * # of IO-APICs and # of IRQ routing registers
+ */
+extern int nr_ioapics;
+extern int nr_ioapic_registers[MAX_IO_APICS];
+
+enum ioapic_irq_destination_types {
+        dest_Fixed = 0,
+        dest_LowestPrio = 1,
+        dest_SMI = 2,
+        dest__reserved_1 = 3,
+        dest_NMI = 4,
+        dest_INIT = 5,
+        dest__reserved_2 = 6,
+        dest_ExtINT = 7
+};
+
+struct IO_APIC_route_entry {
+        __u32   vector          :  8,
+                delivery_mode   :  3,   /* 000: FIXED
+                                         * 001: lowest prio
+                                         * 111: ExtINT
+                                         */
+                dest_mode       :  1,   /* 0: physical, 1: logical */
+                delivery_status :  1,
+                polarity        :  1,
+                irr             :  1,
+                trigger         :  1,   /* 0: edge, 1: level */
+                mask            :  1,   /* 0: enabled, 1: disabled */
+                __reserved_2    : 15;
+
+        __u32   __reserved_3    : 24,
+                dest            :  8;
+} __attribute__ ((packed));
+
+/*
+ * MP-BIOS irq configuration table structures:
+ */
+
+/* I/O APIC entries */
+extern struct mpc_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];
+
+/* non-0 if default (table-less) MP configuration */
+extern int mpc_default_type;
+
+/* 1 if "noapic" boot option passed */
+extern int skip_ioapic_setup;
+
+static inline void disable_ioapic_setup(void)
+{
+        skip_ioapic_setup = 1;
+}
+
+
+/*
+ * If we use the IO-APIC for IRQ routing, disable automatic
+ * assignment of PCI IRQ's.
+ */
+#define io_apic_assign_pci_irqs (mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
+
+#ifdef CONFIG_ACPI
+extern int io_apic_get_version (int ioapic);
+extern int io_apic_get_redir_entries (int ioapic);
+extern int io_apic_set_pci_routing (int ioapic, int pin, int irq, int, int);
+#endif
+
+extern int sis_apic_bug; /* dummy */ 
+
+void enable_NMI_through_LVT0 (void * dummy);
+
+extern spinlock_t i8259A_lock;
+
+#endif
diff --git a/include/asm-x86/ioctl.h b/include/asm-x86/ioctl.h
new file mode 100644
index 000000000000..b279fe06dfe5
--- /dev/null
+++ b/include/asm-x86/ioctl.h
@@ -0,0 +1 @@
+#include <asm-generic/ioctl.h>
diff --git a/include/asm-x86/ioctls.h b/include/asm-x86/ioctls.h
new file mode 100644
index 000000000000..1e0fd48f18bc
--- /dev/null
+++ b/include/asm-x86/ioctls.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "ioctls_32.h"
+# else
+#  include "ioctls_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "ioctls_32.h"
+# else
+#  include "ioctls_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/ioctls_32.h b/include/asm-x86/ioctls_32.h
new file mode 100644
index 000000000000..ef5878762dc9
--- /dev/null
+++ b/include/asm-x86/ioctls_32.h
@@ -0,0 +1,87 @@
+#ifndef __ARCH_I386_IOCTLS_H__
+#define __ARCH_I386_IOCTLS_H__
+
+#include <asm/ioctl.h>
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS          0x5401
+#define TCSETS          0x5402 /* Clashes with SNDCTL_TMR_START sound ioctl */
+#define TCSETSW         0x5403
+#define TCSETSF         0x5404
+#define TCGETA          0x5405
+#define TCSETA          0x5406
+#define TCSETAW         0x5407
+#define TCSETAF         0x5408
+#define TCSBRK          0x5409
+#define TCXONC          0x540A
+#define TCFLSH          0x540B
+#define TIOCEXCL        0x540C
+#define TIOCNXCL        0x540D
+#define TIOCSCTTY       0x540E
+#define TIOCGPGRP       0x540F
+#define TIOCSPGRP       0x5410
+#define TIOCOUTQ        0x5411
+#define TIOCSTI         0x5412
+#define TIOCGWINSZ      0x5413
+#define TIOCSWINSZ      0x5414
+#define TIOCMGET        0x5415
+#define TIOCMBIS        0x5416
+#define TIOCMBIC        0x5417
+#define TIOCMSET        0x5418
+#define TIOCGSOFTCAR    0x5419
+#define TIOCSSOFTCAR    0x541A
+#define FIONREAD        0x541B
+#define TIOCINQ         FIONREAD
+#define TIOCLINUX       0x541C
+#define TIOCCONS        0x541D
+#define TIOCGSERIAL     0x541E
+#define TIOCSSERIAL     0x541F
+#define TIOCPKT         0x5420
+#define FIONBIO         0x5421
+#define TIOCNOTTY       0x5422
+#define TIOCSETD        0x5423
+#define TIOCGETD        0x5424
+#define TCSBRKP         0x5425  /* Needed for POSIX tcsendbreak() */
+/* #define TIOCTTYGSTRUCT 0x5426 - Former debugging-only ioctl */
+#define TIOCSBRK        0x5427  /* BSD compatibility */
+#define TIOCCBRK        0x5428  /* BSD compatibility */
+#define TIOCGSID        0x5429  /* Return the session ID of FD */
+#define TCGETS2         _IOR('T',0x2A, struct termios2)
+#define TCSETS2         _IOW('T',0x2B, struct termios2)
+#define TCSETSW2        _IOW('T',0x2C, struct termios2)
+#define TCSETSF2        _IOW('T',0x2D, struct termios2)
+#define TIOCGPTN        _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK      _IOW('T',0x31, int)  /* Lock/unlock Pty */
+
+#define FIONCLEX        0x5450
+#define FIOCLEX         0x5451
+#define FIOASYNC        0x5452
+#define TIOCSERCONFIG   0x5453
+#define TIOCSERGWILD    0x5454
+#define TIOCSERSWILD    0x5455
+#define TIOCGLCKTRMIOS  0x5456
+#define TIOCSLCKTRMIOS  0x5457
+#define TIOCSERGSTRUCT  0x5458 /* For debugging only */
+#define TIOCSERGETLSR   0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT      0x545C  /* wait for a change on serial input line(s) */
+#define TIOCGICOUNT     0x545D  /* read serial port inline interrupt counts */
+#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
+#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
+#define FIOQSIZE        0x5460
+
+/* Used for packet mode */
+#define TIOCPKT_DATA             0
+#define TIOCPKT_FLUSHREAD        1
+#define TIOCPKT_FLUSHWRITE       2
+#define TIOCPKT_STOP             4
+#define TIOCPKT_START            8
+#define TIOCPKT_NOSTOP          16
+#define TIOCPKT_DOSTOP          32
+
+#define TIOCSER_TEMT    0x01    /* Transmitter physically empty */
+
+#endif
diff --git a/include/asm-x86/ioctls_64.h b/include/asm-x86/ioctls_64.h
new file mode 100644
index 000000000000..3fc0b15a0d7e
--- /dev/null
+++ b/include/asm-x86/ioctls_64.h
@@ -0,0 +1,86 @@
+#ifndef __ARCH_X8664_IOCTLS_H__
+#define __ARCH_X8664_IOCTLS_H__
+
+#include <asm/ioctl.h>
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS          0x5401
+#define TCSETS          0x5402
+#define TCSETSW         0x5403
+#define TCSETSF         0x5404
+#define TCGETA          0x5405
+#define TCSETA          0x5406
+#define TCSETAW         0x5407
+#define TCSETAF         0x5408
+#define TCSBRK          0x5409
+#define TCXONC          0x540A
+#define TCFLSH          0x540B
+#define TIOCEXCL        0x540C
+#define TIOCNXCL        0x540D
+#define TIOCSCTTY       0x540E
+#define TIOCGPGRP       0x540F
+#define TIOCSPGRP       0x5410
+#define TIOCOUTQ        0x5411
+#define TIOCSTI         0x5412
+#define TIOCGWINSZ      0x5413
+#define TIOCSWINSZ      0x5414
+#define TIOCMGET        0x5415
+#define TIOCMBIS        0x5416
+#define TIOCMBIC        0x5417
+#define TIOCMSET        0x5418
+#define TIOCGSOFTCAR    0x5419
+#define TIOCSSOFTCAR    0x541A
+#define FIONREAD        0x541B
+#define TIOCINQ         FIONREAD
+#define TIOCLINUX       0x541C
+#define TIOCCONS        0x541D
+#define TIOCGSERIAL     0x541E
+#define TIOCSSERIAL     0x541F
+#define TIOCPKT         0x5420
+#define FIONBIO         0x5421
+#define TIOCNOTTY       0x5422
+#define TIOCSETD        0x5423
+#define TIOCGETD        0x5424
+#define TCSBRKP         0x5425  /* Needed for POSIX tcsendbreak() */
+#define TIOCSBRK        0x5427  /* BSD compatibility */
+#define TIOCCBRK        0x5428  /* BSD compatibility */
+#define TIOCGSID        0x5429  /* Return the session ID of FD */
+#define TCGETS2         _IOR('T',0x2A, struct termios2)
+#define TCSETS2         _IOW('T',0x2B, struct termios2)
+#define TCSETSW2        _IOW('T',0x2C, struct termios2)
+#define TCSETSF2        _IOW('T',0x2D, struct termios2)
+#define TIOCGPTN        _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK      _IOW('T',0x31, int)  /* Lock/unlock Pty */
+
+#define FIONCLEX        0x5450  /* these numbers need to be adjusted. */
+#define FIOCLEX         0x5451
+#define FIOASYNC        0x5452
+#define TIOCSERCONFIG   0x5453
+#define TIOCSERGWILD    0x5454
+#define TIOCSERSWILD    0x5455
+#define TIOCGLCKTRMIOS  0x5456
+#define TIOCSLCKTRMIOS  0x5457
+#define TIOCSERGSTRUCT  0x5458 /* For debugging only */
+#define TIOCSERGETLSR   0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT      0x545C  /* wait for a change on serial input line(s) */
+#define TIOCGICOUNT     0x545D  /* read serial port inline interrupt counts */
+#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
+#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
+#define FIOQSIZE       0x5460
+
+/* Used for packet mode */
+#define TIOCPKT_DATA             0
+#define TIOCPKT_FLUSHREAD        1
+#define TIOCPKT_FLUSHWRITE       2
+#define TIOCPKT_STOP             4
+#define TIOCPKT_START            8
+#define TIOCPKT_NOSTOP          16
+#define TIOCPKT_DOSTOP          32
+
+#define TIOCSER_TEMT    0x01    /* Transmitter physically empty */
+
+#endif
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
new file mode 100644
index 000000000000..5af471f228ee
--- /dev/null
+++ b/include/asm-x86/iommu.h
@@ -0,0 +1,29 @@
+#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
+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;
+#else
+#define iommu_aperture 0
+#define iommu_aperture_allowed 0
+
+static inline void gart_iommu_shutdown(void)
+{
+}
+
+#endif
+
+#endif
diff --git a/include/asm-x86/ipc.h b/include/asm-x86/ipc.h
new file mode 100644
index 000000000000..a46e3d9c2a3f
--- /dev/null
+++ b/include/asm-x86/ipc.h
@@ -0,0 +1 @@
+#include <asm-generic/ipc.h>
diff --git a/include/asm-x86/ipcbuf.h b/include/asm-x86/ipcbuf.h
new file mode 100644
index 000000000000..eb2e448c6e28
--- /dev/null
+++ b/include/asm-x86/ipcbuf.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "ipcbuf_32.h"
+# else
+#  include "ipcbuf_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "ipcbuf_32.h"
+# else
+#  include "ipcbuf_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/ipcbuf_32.h b/include/asm-x86/ipcbuf_32.h
new file mode 100644
index 000000000000..0dcad4f84c2a
--- /dev/null
+++ b/include/asm-x86/ipcbuf_32.h
@@ -0,0 +1,29 @@
+#ifndef __i386_IPCBUF_H__
+#define __i386_IPCBUF_H__
+
+/*
+ * The ipc64_perm structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 32-bit mode_t and seq
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct ipc64_perm
+{
+        __kernel_key_t          key;
+        __kernel_uid32_t        uid;
+        __kernel_gid32_t        gid;
+        __kernel_uid32_t        cuid;
+        __kernel_gid32_t        cgid;
+        __kernel_mode_t         mode;
+        unsigned short          __pad1;
+        unsigned short          seq;
+        unsigned short          __pad2;
+        unsigned long           __unused1;
+        unsigned long           __unused2;
+};
+
+#endif /* __i386_IPCBUF_H__ */
diff --git a/include/asm-x86/ipcbuf_64.h b/include/asm-x86/ipcbuf_64.h
new file mode 100644
index 000000000000..470cf85e3ba8
--- /dev/null
+++ b/include/asm-x86/ipcbuf_64.h
@@ -0,0 +1,29 @@
+#ifndef __x86_64_IPCBUF_H__
+#define __x86_64_IPCBUF_H__
+
+/*
+ * The ipc64_perm structure for x86_64 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 32-bit mode_t and seq
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct ipc64_perm
+{
+        __kernel_key_t          key;
+        __kernel_uid32_t        uid;
+        __kernel_gid32_t        gid;
+        __kernel_uid32_t        cuid;
+        __kernel_gid32_t        cgid;
+        __kernel_mode_t         mode;
+        unsigned short          __pad1;
+        unsigned short          seq;
+        unsigned short          __pad2;
+        unsigned long           __unused1;
+        unsigned long           __unused2;
+};
+
+#endif /* __x86_64_IPCBUF_H__ */
diff --git a/include/asm-x86/ipi.h b/include/asm-x86/ipi.h
new file mode 100644
index 000000000000..a7c75ea408a8
--- /dev/null
+++ b/include/asm-x86/ipi.h
@@ -0,0 +1,128 @@
+#ifndef __ASM_IPI_H
+#define __ASM_IPI_H
+
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC InterProcessor Interrupt code.
+ *
+ * Moved to include file by James Cleverdon from
+ * arch/x86-64/kernel/smp.c
+ *
+ * Copyrights from kernel/smp.c:
+ *
+ * (c) 1995 Alan Cox, Building #3 <alan@redhat.com>
+ * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com>
+ * (c) 2002,2003 Andi Kleen, SuSE Labs.
+ * Subject to the GNU Public License, v.2
+ */
+
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+
+/*
+ * the following functions deal with sending IPIs between CPUs.
+ *
+ * We use 'broadcast', CPU->CPU IPIs and self-IPIs too.
+ */
+
+static inline unsigned int __prepare_ICR (unsigned int shortcut, int vector, unsigned int dest)
+{
+        unsigned int icr = shortcut | dest;
+
+        switch (vector) {
+        default:
+                icr |= APIC_DM_FIXED | vector;
+                break;
+        case NMI_VECTOR:
+                icr |= APIC_DM_NMI;
+                break;
+        }
+        return icr;
+}
+
+static inline int __prepare_ICR2 (unsigned int mask)
+{
+        return SET_APIC_DEST_FIELD(mask);
+}
+
+static inline void __send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
+{
+        /*
+         * Subtle. In the case of the 'never do double writes' workaround
+         * we have to lock out interrupts to be safe.  As we don't care
+         * of the value read we use an atomic rmw access to avoid costly
+         * cli/sti.  Otherwise we use an even cheaper single atomic write
+         * to the APIC.
+         */
+        unsigned int cfg;
+
+        /*
+         * Wait for idle.
+         */
+        apic_wait_icr_idle();
+
+        /*
+         * No need to touch the target chip field
+         */
+        cfg = __prepare_ICR(shortcut, vector, dest);
+
+        /*
+         * Send the IPI. The write to APIC_ICR fires this off.
+         */
+        apic_write(APIC_ICR, cfg);
+}
+
+/*
+ * This is used to send an IPI with no shorthand notation (the destination is
+ * specified in bits 56 to 63 of the ICR).
+ */
+static inline void __send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest)
+{
+        unsigned long cfg;
+
+        /*
+         * Wait for idle.
+         */
+        if (unlikely(vector == NMI_VECTOR))
+                safe_apic_wait_icr_idle();
+        else
+                apic_wait_icr_idle();
+
+        /*
+         * prepare target chip field
+         */
+        cfg = __prepare_ICR2(mask);
+        apic_write(APIC_ICR2, cfg);
+
+        /*
+         * program the ICR
+         */
+        cfg = __prepare_ICR(0, vector, dest);
+
+        /*
+         * Send the IPI. The write to APIC_ICR fires this off.
+         */
+        apic_write(APIC_ICR, cfg);
+}
+
+static inline void send_IPI_mask_sequence(cpumask_t mask, int vector)
+{
+        unsigned long flags;
+        unsigned long query_cpu;
+
+        /*
+         * Hack. The clustered APIC addressing mode doesn't allow us to send
+         * to an arbitrary mask, so I do a unicast to each CPU instead.
+         * - mbligh
+         */
+        local_irq_save(flags);
+        for_each_cpu_mask(query_cpu, mask) {
+                __send_IPI_dest_field(x86_cpu_to_apicid[query_cpu],
+                                      vector, APIC_DEST_PHYSICAL);
+        }
+        local_irq_restore(flags);
+}
+
+#endif /* __ASM_IPI_H */
diff --git a/include/asm-x86/irq.h b/include/asm-x86/irq.h
new file mode 100644
index 000000000000..7ba905465a53
--- /dev/null
+++ b/include/asm-x86/irq.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "irq_32.h"
+#else
+# include "irq_64.h"
+#endif
diff --git a/include/asm-x86/irq_32.h b/include/asm-x86/irq_32.h
new file mode 100644
index 000000000000..36f310632c49
--- /dev/null
+++ b/include/asm-x86/irq_32.h
@@ -0,0 +1,48 @@
+#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);
+
+#endif /* _ASM_IRQ_H */
diff --git a/include/asm-x86/irq_64.h b/include/asm-x86/irq_64.h
new file mode 100644
index 000000000000..5006c6e75656
--- /dev/null
+++ b/include/asm-x86/irq_64.h
@@ -0,0 +1,51 @@
+#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_regs.h b/include/asm-x86/irq_regs.h
new file mode 100644
index 000000000000..89c898ab298b
--- /dev/null
+++ b/include/asm-x86/irq_regs.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "irq_regs_32.h"
+#else
+# include "irq_regs_64.h"
+#endif
diff --git a/include/asm-x86/irq_regs_32.h b/include/asm-x86/irq_regs_32.h
new file mode 100644
index 000000000000..3368b20c0b48
--- /dev/null
+++ b/include/asm-x86/irq_regs_32.h
@@ -0,0 +1,29 @@
+/*
+ * Per-cpu current frame pointer - the location of the last exception frame on
+ * the stack, stored in the per-cpu area.
+ *
+ * Jeremy Fitzhardinge <jeremy@goop.org>
+ */
+#ifndef _ASM_I386_IRQ_REGS_H
+#define _ASM_I386_IRQ_REGS_H
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU(struct pt_regs *, irq_regs);
+
+static inline struct pt_regs *get_irq_regs(void)
+{
+        return x86_read_percpu(irq_regs);
+}
+
+static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
+{
+        struct pt_regs *old_regs;
+
+        old_regs = get_irq_regs();
+        x86_write_percpu(irq_regs, new_regs);
+
+        return old_regs;
+}
+
+#endif /* _ASM_I386_IRQ_REGS_H */
diff --git a/include/asm-x86/irq_regs_64.h b/include/asm-x86/irq_regs_64.h
new file mode 100644
index 000000000000..3dd9c0b70270
--- /dev/null
+++ b/include/asm-x86/irq_regs_64.h
@@ -0,0 +1 @@
+#include <asm-generic/irq_regs.h>
diff --git a/include/asm-x86/irqflags.h b/include/asm-x86/irqflags.h
new file mode 100644
index 000000000000..1b695ff52687
--- /dev/null
+++ b/include/asm-x86/irqflags.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "irqflags_32.h"
+#else
+# include "irqflags_64.h"
+#endif
diff --git a/include/asm-x86/irqflags_32.h b/include/asm-x86/irqflags_32.h
new file mode 100644
index 000000000000..eff8585cb741
--- /dev/null
+++ b/include/asm-x86/irqflags_32.h
@@ -0,0 +1,163 @@
+/*
+ * include/asm-i386/irqflags.h
+ *
+ * IRQ flags handling
+ *
+ * This file gets included from lowlevel asm headers too, to provide
+ * wrapped versions of the local_irq_*() APIs, based on the
+ * raw_local_irq_*() functions from the lowlevel headers.
+ */
+#ifndef _ASM_IRQFLAGS_H
+#define _ASM_IRQFLAGS_H
+#include <asm/processor-flags.h>
+
+#ifndef __ASSEMBLY__
+static inline unsigned long native_save_fl(void)
+{
+        unsigned long f;
+        asm volatile("pushfl ; popl %0":"=g" (f): /* no input */);
+        return f;
+}
+
+static inline void native_restore_fl(unsigned long f)
+{
+        asm volatile("pushl %0 ; popfl": /* no output */
+                             :"g" (f)
+                             :"memory", "cc");
+}
+
+static inline void native_irq_disable(void)
+{
+        asm volatile("cli": : :"memory");
+}
+
+static inline void native_irq_enable(void)
+{
+        asm volatile("sti": : :"memory");
+}
+
+static inline void native_safe_halt(void)
+{
+        asm volatile("sti; hlt": : :"memory");
+}
+
+static inline void native_halt(void)
+{
+        asm volatile("hlt": : :"memory");
+}
+#endif  /* __ASSEMBLY__ */
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#ifndef __ASSEMBLY__
+
+static inline unsigned long __raw_local_save_flags(void)
+{
+        return native_save_fl();
+}
+
+static inline void raw_local_irq_restore(unsigned long flags)
+{
+        native_restore_fl(flags);
+}
+
+static inline void raw_local_irq_disable(void)
+{
+        native_irq_disable();
+}
+
+static inline void raw_local_irq_enable(void)
+{
+        native_irq_enable();
+}
+
+/*
+ * Used in the idle loop; sti takes one instruction cycle
+ * to complete:
+ */
+static inline void raw_safe_halt(void)
+{
+        native_safe_halt();
+}
+
+/*
+ * Used when interrupts are already enabled or to
+ * shutdown the processor:
+ */
+static inline void halt(void)
+{
+        native_halt();
+}
+
+/*
+ * For spinlocks, etc:
+ */
+static inline unsigned long __raw_local_irq_save(void)
+{
+        unsigned long flags = __raw_local_save_flags();
+
+        raw_local_irq_disable();
+
+        return flags;
+}
+
+#else
+#define DISABLE_INTERRUPTS(clobbers)    cli
+#define ENABLE_INTERRUPTS(clobbers)     sti
+#define ENABLE_INTERRUPTS_SYSEXIT       sti; sysexit
+#define INTERRUPT_RETURN                iret
+#define GET_CR0_INTO_EAX                movl %cr0, %eax
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_PARAVIRT */
+
+#ifndef __ASSEMBLY__
+#define raw_local_save_flags(flags) \
+                do { (flags) = __raw_local_save_flags(); } while (0)
+
+#define raw_local_irq_save(flags) \
+                do { (flags) = __raw_local_irq_save(); } while (0)
+
+static inline int raw_irqs_disabled_flags(unsigned long flags)
+{
+        return !(flags & X86_EFLAGS_IF);
+}
+
+static inline int raw_irqs_disabled(void)
+{
+        unsigned long flags = __raw_local_save_flags();
+
+        return raw_irqs_disabled_flags(flags);
+}
+#endif /* __ASSEMBLY__ */
+
+/*
+ * Do the CPU's IRQ-state tracing from assembly code. We call a
+ * C function, so save all the C-clobbered registers:
+ */
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+# define TRACE_IRQS_ON                          \
+        pushl %eax;                             \
+        pushl %ecx;                             \
+        pushl %edx;                             \
+        call trace_hardirqs_on;                 \
+        popl %edx;                              \
+        popl %ecx;                              \
+        popl %eax;
+
+# define TRACE_IRQS_OFF                         \
+        pushl %eax;                             \
+        pushl %ecx;                             \
+        pushl %edx;                             \
+        call trace_hardirqs_off;                \
+        popl %edx;                              \
+        popl %ecx;                              \
+        popl %eax;
+
+#else
+# define TRACE_IRQS_ON
+# define TRACE_IRQS_OFF
+#endif
+
+#endif
diff --git a/include/asm-x86/irqflags_64.h b/include/asm-x86/irqflags_64.h
new file mode 100644
index 000000000000..86e70fe23659
--- /dev/null
+++ b/include/asm-x86/irqflags_64.h
@@ -0,0 +1,142 @@
+/*
+ * include/asm-x86_64/irqflags.h
+ *
+ * IRQ flags handling
+ *
+ * This file gets included from lowlevel asm headers too, to provide
+ * wrapped versions of the local_irq_*() APIs, based on the
+ * raw_local_irq_*() functions from the lowlevel headers.
+ */
+#ifndef _ASM_IRQFLAGS_H
+#define _ASM_IRQFLAGS_H
+#include <asm/processor-flags.h>
+
+#ifndef __ASSEMBLY__
+/*
+ * Interrupt control:
+ */
+
+static inline unsigned long __raw_local_save_flags(void)
+{
+        unsigned long flags;
+
+        __asm__ __volatile__(
+                "# __raw_save_flags\n\t"
+                "pushfq ; popq %q0"
+                : "=g" (flags)
+                : /* no input */
+                : "memory"
+        );
+
+        return flags;
+}
+
+#define raw_local_save_flags(flags) \
+                do { (flags) = __raw_local_save_flags(); } while (0)
+
+static inline void raw_local_irq_restore(unsigned long flags)
+{
+        __asm__ __volatile__(
+                "pushq %0 ; popfq"
+                : /* no output */
+                :"g" (flags)
+                :"memory", "cc"
+        );
+}
+
+#ifdef CONFIG_X86_VSMP
+
+/*
+ * Interrupt control for the VSMP architecture:
+ */
+
+static inline void raw_local_irq_disable(void)
+{
+        unsigned long flags = __raw_local_save_flags();
+
+        raw_local_irq_restore((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC);
+}
+
+static inline void raw_local_irq_enable(void)
+{
+        unsigned long flags = __raw_local_save_flags();
+
+        raw_local_irq_restore((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC));
+}
+
+static inline int raw_irqs_disabled_flags(unsigned long flags)
+{
+        return !(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC);
+}
+
+#else /* CONFIG_X86_VSMP */
+
+static inline void raw_local_irq_disable(void)
+{
+        __asm__ __volatile__("cli" : : : "memory");
+}
+
+static inline void raw_local_irq_enable(void)
+{
+        __asm__ __volatile__("sti" : : : "memory");
+}
+
+static inline int raw_irqs_disabled_flags(unsigned long flags)
+{
+        return !(flags & X86_EFLAGS_IF);
+}
+
+#endif
+
+/*
+ * For spinlocks, etc.:
+ */
+
+static inline unsigned long __raw_local_irq_save(void)
+{
+        unsigned long flags = __raw_local_save_flags();
+
+        raw_local_irq_disable();
+
+        return flags;
+}
+
+#define raw_local_irq_save(flags) \
+                do { (flags) = __raw_local_irq_save(); } while (0)
+
+static inline int raw_irqs_disabled(void)
+{
+        unsigned long flags = __raw_local_save_flags();
+
+        return raw_irqs_disabled_flags(flags);
+}
+
+/*
+ * Used in the idle loop; sti takes one instruction cycle
+ * to complete:
+ */
+static inline void raw_safe_halt(void)
+{
+        __asm__ __volatile__("sti; hlt" : : : "memory");
+}
+
+/*
+ * Used when interrupts are already enabled or to
+ * shutdown the processor:
+ */
+static inline void halt(void)
+{
+        __asm__ __volatile__("hlt": : :"memory");
+}
+
+#else /* __ASSEMBLY__: */
+# ifdef CONFIG_TRACE_IRQFLAGS
+#  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
+# endif
+#endif
+
+#endif
diff --git a/include/asm-x86/ist.h b/include/asm-x86/ist.h
new file mode 100644
index 000000000000..ef2003ebc6f9
--- /dev/null
+++ b/include/asm-x86/ist.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_IST_H
+#define _ASM_IST_H
+
+/*
+ * Include file for the interface to IST BIOS
+ * Copyright 2002 Andy Grover <andrew.grover@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+
+struct ist_info {
+        u32 signature;
+        u32 command;
+        u32 event;
+        u32 perf_level;
+};
+
+extern struct ist_info ist_info;
+
+#endif  /* __KERNEL__ */
+#endif  /* _ASM_IST_H */
diff --git a/include/asm-x86/k8.h b/include/asm-x86/k8.h
new file mode 100644
index 000000000000..699dd6961eda
--- /dev/null
+++ b/include/asm-x86/k8.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_K8_H
+#define _ASM_K8_H 1
+
+#include <linux/pci.h>
+
+extern struct pci_device_id k8_nb_ids[];
+
+extern int early_is_k8_nb(u32 value);
+extern struct pci_dev **k8_northbridges;
+extern int num_k8_northbridges;
+extern int cache_k8_northbridges(void);
+extern void k8_flush_garts(void);
+
+#endif
diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h
new file mode 100644
index 000000000000..38479106c259
--- /dev/null
+++ b/include/asm-x86/kdebug.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "kdebug_32.h"
+#else
+# include "kdebug_64.h"
+#endif
diff --git a/include/asm-x86/kdebug_32.h b/include/asm-x86/kdebug_32.h
new file mode 100644
index 000000000000..a185b5f73e7f
--- /dev/null
+++ b/include/asm-x86/kdebug_32.h
@@ -0,0 +1,33 @@
+#ifndef _I386_KDEBUG_H
+#define _I386_KDEBUG_H 1
+
+/*
+ * Aug-05 2004 Ported by Prasanna S Panchamukhi <prasanna@in.ibm.com>
+ * from x86_64 architecture.
+ */
+#include <linux/notifier.h>
+
+struct pt_regs;
+
+extern int register_page_fault_notifier(struct notifier_block *);
+extern int unregister_page_fault_notifier(struct notifier_block *);
+
+
+/* Grossly misnamed. */
+enum die_val {
+        DIE_OOPS = 1,
+        DIE_INT3,
+        DIE_DEBUG,
+        DIE_PANIC,
+        DIE_NMI,
+        DIE_DIE,
+        DIE_NMIWATCHDOG,
+        DIE_KERNELDEBUG,
+        DIE_TRAP,
+        DIE_GPF,
+        DIE_CALL,
+        DIE_NMI_IPI,
+        DIE_PAGE_FAULT,
+};
+
+#endif
diff --git a/include/asm-x86/kdebug_64.h b/include/asm-x86/kdebug_64.h
new file mode 100644
index 000000000000..d7e2bcf49e4f
--- /dev/null
+++ b/include/asm-x86/kdebug_64.h
@@ -0,0 +1,36 @@
+#ifndef _X86_64_KDEBUG_H
+#define _X86_64_KDEBUG_H 1
+
+#include <linux/notifier.h>
+
+struct pt_regs;
+
+extern int register_page_fault_notifier(struct notifier_block *);
+extern int unregister_page_fault_notifier(struct notifier_block *);
+
+/* Grossly misnamed. */
+enum die_val {
+        DIE_OOPS = 1,
+        DIE_INT3,
+        DIE_DEBUG,
+        DIE_PANIC,
+        DIE_NMI,
+        DIE_DIE,
+        DIE_NMIWATCHDOG,
+        DIE_KERNELDEBUG,
+        DIE_TRAP,
+        DIE_GPF,
+        DIE_CALL,
+        DIE_NMI_IPI,
+        DIE_PAGE_FAULT,
+};
+
+extern void printk_address(unsigned long address);
+extern void die(const char *,struct pt_regs *,long);
+extern void __die(const char *,struct pt_regs *,long);
+extern void show_registers(struct pt_regs *regs);
+extern void dump_pagetable(unsigned long);
+extern unsigned long oops_begin(void);
+extern void oops_end(unsigned long);
+
+#endif
diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h
new file mode 100644
index 000000000000..718ddbfb9516
--- /dev/null
+++ b/include/asm-x86/kexec.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "kexec_32.h"
+#else
+# include "kexec_64.h"
+#endif
diff --git a/include/asm-x86/kexec_32.h b/include/asm-x86/kexec_32.h
new file mode 100644
index 000000000000..4b9dc9e6b701
--- /dev/null
+++ b/include/asm-x86/kexec_32.h
@@ -0,0 +1,99 @@
+#ifndef _I386_KEXEC_H
+#define _I386_KEXEC_H
+
+#define PA_CONTROL_PAGE  0
+#define VA_CONTROL_PAGE  1
+#define PA_PGD           2
+#define VA_PGD           3
+#define PA_PTE_0         4
+#define VA_PTE_0         5
+#define PA_PTE_1         6
+#define VA_PTE_1         7
+#ifdef CONFIG_X86_PAE
+#define PA_PMD_0         8
+#define VA_PMD_0         9
+#define PA_PMD_1         10
+#define VA_PMD_1         11
+#define PAGES_NR         12
+#else
+#define PAGES_NR         8
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <asm/ptrace.h>
+#include <asm/string.h>
+
+/*
+ * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
+ * I.e. Maximum page that is mapped directly into kernel memory,
+ * and kmap is not required.
+ */
+
+/* Maximum physical address we can use pages from */
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+/* Maximum address we can reach in physical address mode */
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+/* Maximum address we can use for the control code buffer */
+#define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
+
+#define KEXEC_CONTROL_CODE_SIZE 4096
+
+/* The native architecture */
+#define KEXEC_ARCH KEXEC_ARCH_386
+
+/* We can also handle crash dumps from 64 bit kernel. */
+#define vmcore_elf_check_arch_cross(x) ((x)->e_machine == EM_X86_64)
+
+/* CPU does not save ss and esp on stack if execution is already
+ * running in kernel mode at the time of NMI occurrence. This code
+ * fixes it.
+ */
+static inline void crash_fixup_ss_esp(struct pt_regs *newregs,
+                                        struct pt_regs *oldregs)
+{
+        memcpy(newregs, oldregs, sizeof(*newregs));
+        newregs->esp = (unsigned long)&(oldregs->esp);
+        __asm__ __volatile__(
+                        "xorl %%eax, %%eax\n\t"
+                        "movw %%ss, %%ax\n\t"
+                        :"=a"(newregs->xss));
+}
+
+/*
+ * This function is responsible for capturing register states if coming
+ * via panic otherwise just fix up the ss and esp if coming via kernel
+ * mode exception.
+ */
+static inline void crash_setup_regs(struct pt_regs *newregs,
+                                       struct pt_regs *oldregs)
+{
+       if (oldregs)
+               crash_fixup_ss_esp(newregs, oldregs);
+       else {
+               __asm__ __volatile__("movl %%ebx,%0" : "=m"(newregs->ebx));
+               __asm__ __volatile__("movl %%ecx,%0" : "=m"(newregs->ecx));
+               __asm__ __volatile__("movl %%edx,%0" : "=m"(newregs->edx));
+               __asm__ __volatile__("movl %%esi,%0" : "=m"(newregs->esi));
+               __asm__ __volatile__("movl %%edi,%0" : "=m"(newregs->edi));
+               __asm__ __volatile__("movl %%ebp,%0" : "=m"(newregs->ebp));
+               __asm__ __volatile__("movl %%eax,%0" : "=m"(newregs->eax));
+               __asm__ __volatile__("movl %%esp,%0" : "=m"(newregs->esp));
+               __asm__ __volatile__("movw %%ss, %%ax;" :"=a"(newregs->xss));
+               __asm__ __volatile__("movw %%cs, %%ax;" :"=a"(newregs->xcs));
+               __asm__ __volatile__("movw %%ds, %%ax;" :"=a"(newregs->xds));
+               __asm__ __volatile__("movw %%es, %%ax;" :"=a"(newregs->xes));
+               __asm__ __volatile__("pushfl; popl %0" :"=m"(newregs->eflags));
+
+               newregs->eip = (unsigned long)current_text_addr();
+       }
+}
+asmlinkage NORET_TYPE void
+relocate_kernel(unsigned long indirection_page,
+                unsigned long control_page,
+                unsigned long start_address,
+                unsigned int has_pae) ATTRIB_NORET;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _I386_KEXEC_H */
diff --git a/include/asm-x86/kexec_64.h b/include/asm-x86/kexec_64.h
new file mode 100644
index 000000000000..738e581b67f8
--- /dev/null
+++ b/include/asm-x86/kexec_64.h
@@ -0,0 +1,94 @@
+#ifndef _X86_64_KEXEC_H
+#define _X86_64_KEXEC_H
+
+#define PA_CONTROL_PAGE  0
+#define VA_CONTROL_PAGE  1
+#define PA_PGD           2
+#define VA_PGD           3
+#define PA_PUD_0         4
+#define VA_PUD_0         5
+#define PA_PMD_0         6
+#define VA_PMD_0         7
+#define PA_PTE_0         8
+#define VA_PTE_0         9
+#define PA_PUD_1         10
+#define VA_PUD_1         11
+#define PA_PMD_1         12
+#define VA_PMD_1         13
+#define PA_PTE_1         14
+#define VA_PTE_1         15
+#define PA_TABLE_PAGE    16
+#define PAGES_NR         17
+
+#ifndef __ASSEMBLY__
+
+#include <linux/string.h>
+
+#include <asm/page.h>
+#include <asm/ptrace.h>
+
+/*
+ * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
+ * I.e. Maximum page that is mapped directly into kernel memory,
+ * and kmap is not required.
+ *
+ * So far x86_64 is limited to 40 physical address bits.
+ */
+
+/* Maximum physical address we can use pages from */
+#define KEXEC_SOURCE_MEMORY_LIMIT      (0xFFFFFFFFFFUL)
+/* Maximum address we can reach in physical address mode */
+#define KEXEC_DESTINATION_MEMORY_LIMIT (0xFFFFFFFFFFUL)
+/* Maximum address we can use for the control pages */
+#define KEXEC_CONTROL_MEMORY_LIMIT     (0xFFFFFFFFFFUL)
+
+/* Allocate one page for the pdp and the second for the code */
+#define KEXEC_CONTROL_CODE_SIZE  (4096UL + 4096UL)
+
+/* The native architecture */
+#define KEXEC_ARCH KEXEC_ARCH_X86_64
+
+/*
+ * Saving the registers of the cpu on which panic occured in
+ * crash_kexec to save a valid sp. The registers of other cpus
+ * will be saved in machine_crash_shutdown while shooting down them.
+ */
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+                                                struct pt_regs *oldregs)
+{
+        if (oldregs)
+                memcpy(newregs, oldregs, sizeof(*newregs));
+        else {
+                __asm__ __volatile__("movq %%rbx,%0" : "=m"(newregs->rbx));
+                __asm__ __volatile__("movq %%rcx,%0" : "=m"(newregs->rcx));
+                __asm__ __volatile__("movq %%rdx,%0" : "=m"(newregs->rdx));
+                __asm__ __volatile__("movq %%rsi,%0" : "=m"(newregs->rsi));
+                __asm__ __volatile__("movq %%rdi,%0" : "=m"(newregs->rdi));
+                __asm__ __volatile__("movq %%rbp,%0" : "=m"(newregs->rbp));
+                __asm__ __volatile__("movq %%rax,%0" : "=m"(newregs->rax));
+                __asm__ __volatile__("movq %%rsp,%0" : "=m"(newregs->rsp));
+                __asm__ __volatile__("movq %%r8,%0" : "=m"(newregs->r8));
+                __asm__ __volatile__("movq %%r9,%0" : "=m"(newregs->r9));
+                __asm__ __volatile__("movq %%r10,%0" : "=m"(newregs->r10));
+                __asm__ __volatile__("movq %%r11,%0" : "=m"(newregs->r11));
+                __asm__ __volatile__("movq %%r12,%0" : "=m"(newregs->r12));
+                __asm__ __volatile__("movq %%r13,%0" : "=m"(newregs->r13));
+                __asm__ __volatile__("movq %%r14,%0" : "=m"(newregs->r14));
+                __asm__ __volatile__("movq %%r15,%0" : "=m"(newregs->r15));
+                __asm__ __volatile__("movl %%ss, %%eax;" :"=a"(newregs->ss));
+                __asm__ __volatile__("movl %%cs, %%eax;" :"=a"(newregs->cs));
+                __asm__ __volatile__("pushfq; popq %0" :"=m"(newregs->eflags));
+
+                newregs->rip = (unsigned long)current_text_addr();
+        }
+}
+
+NORET_TYPE void
+relocate_kernel(unsigned long indirection_page,
+                unsigned long page_list,
+                unsigned long start_address) ATTRIB_NORET;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _X86_64_KEXEC_H */
diff --git a/include/asm-x86/kmap_types.h b/include/asm-x86/kmap_types.h
new file mode 100644
index 000000000000..e4ec724b298e
--- /dev/null
+++ b/include/asm-x86/kmap_types.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "kmap_types_32.h"
+#else
+# include "kmap_types_64.h"
+#endif
diff --git a/include/asm-x86/kmap_types_32.h b/include/asm-x86/kmap_types_32.h
new file mode 100644
index 000000000000..806aae3c5338
--- /dev/null
+++ b/include/asm-x86/kmap_types_32.h
@@ -0,0 +1,30 @@
+#ifndef _ASM_KMAP_TYPES_H
+#define _ASM_KMAP_TYPES_H
+
+
+#ifdef CONFIG_DEBUG_HIGHMEM
+# define D(n) __KM_FENCE_##n ,
+#else
+# define D(n)
+#endif
+
+enum km_type {
+D(0)    KM_BOUNCE_READ,
+D(1)    KM_SKB_SUNRPC_DATA,
+D(2)    KM_SKB_DATA_SOFTIRQ,
+D(3)    KM_USER0,
+D(4)    KM_USER1,
+D(5)    KM_BIO_SRC_IRQ,
+D(6)    KM_BIO_DST_IRQ,
+D(7)    KM_PTE0,
+D(8)    KM_PTE1,
+D(9)    KM_IRQ0,
+D(10)   KM_IRQ1,
+D(11)   KM_SOFTIRQ0,
+D(12)   KM_SOFTIRQ1,
+D(13)   KM_TYPE_NR
+};
+
+#undef D
+
+#endif
diff --git a/include/asm-x86/kmap_types_64.h b/include/asm-x86/kmap_types_64.h
new file mode 100644
index 000000000000..7486338c6cea
--- /dev/null
+++ b/include/asm-x86/kmap_types_64.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_KMAP_TYPES_H
+#define _ASM_KMAP_TYPES_H
+
+enum km_type {
+        KM_BOUNCE_READ,
+        KM_SKB_SUNRPC_DATA,
+        KM_SKB_DATA_SOFTIRQ,
+        KM_USER0,
+        KM_USER1,
+        KM_BIO_SRC_IRQ,
+        KM_BIO_DST_IRQ,
+        KM_IRQ0,
+        KM_IRQ1,
+        KM_SOFTIRQ0,
+        KM_SOFTIRQ1,
+        KM_TYPE_NR
+};
+
+#endif
diff --git a/include/asm-x86/kprobes.h b/include/asm-x86/kprobes.h
new file mode 100644
index 000000000000..b7bbd25ba2a6
--- /dev/null
+++ b/include/asm-x86/kprobes.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "kprobes_32.h"
+#else
+# include "kprobes_64.h"
+#endif
diff --git a/include/asm-x86/kprobes_32.h b/include/asm-x86/kprobes_32.h
new file mode 100644
index 000000000000..06f7303c30ca
--- /dev/null
+++ b/include/asm-x86/kprobes_32.h
@@ -0,0 +1,92 @@
+#ifndef _ASM_KPROBES_H
+#define _ASM_KPROBES_H
+/*
+ *  Kernel Probes (KProbes)
+ *  include/asm-i386/kprobes.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ *
+ * 2002-Oct     Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
+ *              Probes initial implementation ( includes suggestions from
+ *              Rusty Russell).
+ */
+#include <linux/types.h>
+#include <linux/ptrace.h>
+
+#define  __ARCH_WANT_KPROBES_INSN_SLOT
+
+struct kprobe;
+struct pt_regs;
+
+typedef u8 kprobe_opcode_t;
+#define BREAKPOINT_INSTRUCTION  0xcc
+#define RELATIVEJUMP_INSTRUCTION 0xe9
+#define MAX_INSN_SIZE 16
+#define MAX_STACK_SIZE 64
+#define MIN_STACK_SIZE(ADDR) (((MAX_STACK_SIZE) < \
+        (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) \
+        ? (MAX_STACK_SIZE) \
+        : (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR)))
+
+#define ARCH_SUPPORTS_KRETPROBES
+#define  ARCH_INACTIVE_KPROBE_COUNT 0
+#define flush_insn_slot(p)      do { } while (0)
+
+void arch_remove_kprobe(struct kprobe *p);
+void kretprobe_trampoline(void);
+
+/* Architecture specific copy of original instruction*/
+struct arch_specific_insn {
+        /* copy of the original instruction */
+        kprobe_opcode_t *insn;
+        /*
+         * If this flag is not 0, this kprobe can be boost when its
+         * post_handler and break_handler is not set.
+         */
+        int boostable;
+};
+
+struct prev_kprobe {
+        struct kprobe *kp;
+        unsigned long status;
+        unsigned long old_eflags;
+        unsigned long saved_eflags;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+        unsigned long kprobe_status;
+        unsigned long kprobe_old_eflags;
+        unsigned long kprobe_saved_eflags;
+        long *jprobe_saved_esp;
+        struct pt_regs jprobe_saved_regs;
+        kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
+        struct prev_kprobe prev_kprobe;
+};
+
+/* trap3/1 are intr gates for kprobes.  So, restore the status of IF,
+ * if necessary, before executing the original int3/1 (trap) handler.
+ */
+static inline void restore_interrupts(struct pt_regs *regs)
+{
+        if (regs->eflags & IF_MASK)
+                local_irq_enable();
+}
+
+extern int kprobe_exceptions_notify(struct notifier_block *self,
+                                    unsigned long val, void *data);
+#endif                          /* _ASM_KPROBES_H */
diff --git a/include/asm-x86/kprobes_64.h b/include/asm-x86/kprobes_64.h
new file mode 100644
index 000000000000..7db825403e01
--- /dev/null
+++ b/include/asm-x86/kprobes_64.h
@@ -0,0 +1,90 @@
+#ifndef _ASM_KPROBES_H
+#define _ASM_KPROBES_H
+/*
+ *  Kernel Probes (KProbes)
+ *  include/asm-x86_64/kprobes.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ *
+ * 2004-Oct     Prasanna S Panchamukhi <prasanna@in.ibm.com> and Jim Keniston
+ *              kenistoj@us.ibm.com adopted from i386.
+ */
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define  __ARCH_WANT_KPROBES_INSN_SLOT
+
+struct pt_regs;
+struct kprobe;
+
+typedef u8 kprobe_opcode_t;
+#define BREAKPOINT_INSTRUCTION  0xcc
+#define MAX_INSN_SIZE 15
+#define MAX_STACK_SIZE 64
+#define MIN_STACK_SIZE(ADDR) (((MAX_STACK_SIZE) < \
+        (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) \
+        ? (MAX_STACK_SIZE) \
+        : (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR)))
+
+#define ARCH_SUPPORTS_KRETPROBES
+#define  ARCH_INACTIVE_KPROBE_COUNT 1
+
+void kretprobe_trampoline(void);
+extern void arch_remove_kprobe(struct kprobe *p);
+#define flush_insn_slot(p)      do { } while (0)
+
+/* Architecture specific copy of original instruction*/
+struct arch_specific_insn {
+        /* copy of the original instruction */
+        kprobe_opcode_t *insn;
+};
+
+struct prev_kprobe {
+        struct kprobe *kp;
+        unsigned long status;
+        unsigned long old_rflags;
+        unsigned long saved_rflags;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+        unsigned long kprobe_status;
+        unsigned long kprobe_old_rflags;
+        unsigned long kprobe_saved_rflags;
+        long *jprobe_saved_rsp;
+        struct pt_regs jprobe_saved_regs;
+        kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
+        struct prev_kprobe prev_kprobe;
+};
+
+/* trap3/1 are intr gates for kprobes.  So, restore the status of IF,
+ * if necessary, before executing the original int3/1 (trap) handler.
+ */
+static inline void restore_interrupts(struct pt_regs *regs)
+{
+        if (regs->eflags & IF_MASK)
+                local_irq_enable();
+}
+
+extern int post_kprobe_handler(struct pt_regs *regs);
+extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
+extern int kprobe_handler(struct pt_regs *regs);
+
+extern int kprobe_exceptions_notify(struct notifier_block *self,
+                                    unsigned long val, void *data);
+#endif                          /* _ASM_KPROBES_H */
diff --git a/include/asm-x86/ldt.h b/include/asm-x86/ldt.h
new file mode 100644
index 000000000000..3d9cc20d2ba4
--- /dev/null
+++ b/include/asm-x86/ldt.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "ldt_32.h"
+# else
+#  include "ldt_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "ldt_32.h"
+# else
+#  include "ldt_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/ldt_32.h b/include/asm-x86/ldt_32.h
new file mode 100644
index 000000000000..e9d3de1dee6c
--- /dev/null
+++ b/include/asm-x86/ldt_32.h
@@ -0,0 +1,32 @@
+/*
+ * ldt.h
+ *
+ * Definitions of structures used with the modify_ldt system call.
+ */
+#ifndef _LINUX_LDT_H
+#define _LINUX_LDT_H
+
+/* Maximum number of LDT entries supported. */
+#define LDT_ENTRIES     8192
+/* The size of each LDT entry. */
+#define LDT_ENTRY_SIZE  8
+
+#ifndef __ASSEMBLY__
+struct user_desc {
+        unsigned int  entry_number;
+        unsigned long base_addr;
+        unsigned int  limit;
+        unsigned int  seg_32bit:1;
+        unsigned int  contents:2;
+        unsigned int  read_exec_only:1;
+        unsigned int  limit_in_pages:1;
+        unsigned int  seg_not_present:1;
+        unsigned int  useable:1;
+};
+
+#define MODIFY_LDT_CONTENTS_DATA        0
+#define MODIFY_LDT_CONTENTS_STACK       1
+#define MODIFY_LDT_CONTENTS_CODE        2
+
+#endif /* !__ASSEMBLY__ */
+#endif
diff --git a/include/asm-x86/ldt_64.h b/include/asm-x86/ldt_64.h
new file mode 100644
index 000000000000..9ef647b890d2
--- /dev/null
+++ b/include/asm-x86/ldt_64.h
@@ -0,0 +1,36 @@
+/*
+ * ldt.h
+ *
+ * Definitions of structures used with the modify_ldt system call.
+ */
+#ifndef _LINUX_LDT_H
+#define _LINUX_LDT_H
+
+/* Maximum number of LDT entries supported. */
+#define LDT_ENTRIES     8192
+/* The size of each LDT entry. */
+#define LDT_ENTRY_SIZE  8
+
+#ifndef __ASSEMBLY__
+/* Note on 64bit base and limit is ignored and you cannot set
+   DS/ES/CS not to the default values if you still want to do syscalls. This
+   call is more for 32bit mode therefore. */
+struct user_desc {
+        unsigned int  entry_number;
+        unsigned int  base_addr;
+        unsigned int  limit;
+        unsigned int  seg_32bit:1;
+        unsigned int  contents:2;
+        unsigned int  read_exec_only:1;
+        unsigned int  limit_in_pages:1;
+        unsigned int  seg_not_present:1;
+        unsigned int  useable:1;
+        unsigned int  lm:1;
+};
+
+#define MODIFY_LDT_CONTENTS_DATA        0
+#define MODIFY_LDT_CONTENTS_STACK       1
+#define MODIFY_LDT_CONTENTS_CODE        2
+
+#endif /* !__ASSEMBLY__ */
+#endif
diff --git a/include/asm-x86/linkage.h b/include/asm-x86/linkage.h
new file mode 100644
index 000000000000..94b257fa8701
--- /dev/null
+++ b/include/asm-x86/linkage.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "linkage_32.h"
+#else
+# include "linkage_64.h"
+#endif
diff --git a/include/asm-x86/linkage_32.h b/include/asm-x86/linkage_32.h
new file mode 100644
index 000000000000..f4a6ebac0247
--- /dev/null
+++ b/include/asm-x86/linkage_32.h
@@ -0,0 +1,15 @@
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
+#define FASTCALL(x)     x __attribute__((regparm(3)))
+#define fastcall        __attribute__((regparm(3)))
+
+#define prevent_tail_call(ret) __asm__ ("" : "=r" (ret) : "0" (ret))
+
+#ifdef CONFIG_X86_ALIGNMENT_16
+#define __ALIGN .align 16,0x90
+#define __ALIGN_STR ".align 16,0x90"
+#endif
+
+#endif
diff --git a/include/asm-x86/linkage_64.h b/include/asm-x86/linkage_64.h
new file mode 100644
index 000000000000..b5f39d0189ce
--- /dev/null
+++ b/include/asm-x86/linkage_64.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#define __ALIGN .p2align 4,,15
+
+#endif
diff --git a/include/asm-x86/local.h b/include/asm-x86/local.h
new file mode 100644
index 000000000000..c7a1b1c66c96
--- /dev/null
+++ b/include/asm-x86/local.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "local_32.h"
+#else
+# include "local_64.h"
+#endif
diff --git a/include/asm-x86/local_32.h b/include/asm-x86/local_32.h
new file mode 100644
index 000000000000..6e85975b9ed2
--- /dev/null
+++ b/include/asm-x86/local_32.h
@@ -0,0 +1,233 @@
+#ifndef _ARCH_I386_LOCAL_H
+#define _ARCH_I386_LOCAL_H
+
+#include <linux/percpu.h>
+#include <asm/system.h>
+#include <asm/atomic.h>
+
+typedef struct
+{
+        atomic_long_t a;
+} local_t;
+
+#define LOCAL_INIT(i)   { ATOMIC_LONG_INIT(i) }
+
+#define local_read(l)   atomic_long_read(&(l)->a)
+#define local_set(l,i)  atomic_long_set(&(l)->a, (i))
+
+static __inline__ void local_inc(local_t *l)
+{
+        __asm__ __volatile__(
+                "incl %0"
+                :"+m" (l->a.counter));
+}
+
+static __inline__ void local_dec(local_t *l)
+{
+        __asm__ __volatile__(
+                "decl %0"
+                :"+m" (l->a.counter));
+}
+
+static __inline__ void local_add(long i, local_t *l)
+{
+        __asm__ __volatile__(
+                "addl %1,%0"
+                :"+m" (l->a.counter)
+                :"ir" (i));
+}
+
+static __inline__ void local_sub(long i, local_t *l)
+{
+        __asm__ __volatile__(
+                "subl %1,%0"
+                :"+m" (l->a.counter)
+                :"ir" (i));
+}
+
+/**
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer of type local_t
+ *
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_sub_and_test(long i, local_t *l)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                "subl %2,%0; sete %1"
+                :"+m" (l->a.counter), "=qm" (c)
+                :"ir" (i) : "memory");
+        return c;
+}
+
+/**
+ * local_dec_and_test - decrement and test
+ * @l: pointer of type local_t
+ *
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static __inline__ int local_dec_and_test(local_t *l)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                "decl %0; sete %1"
+                :"+m" (l->a.counter), "=qm" (c)
+                : : "memory");
+        return c != 0;
+}
+
+/**
+ * local_inc_and_test - increment and test
+ * @l: pointer of type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_inc_and_test(local_t *l)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                "incl %0; sete %1"
+                :"+m" (l->a.counter), "=qm" (c)
+                : : "memory");
+        return c != 0;
+}
+
+/**
+ * local_add_negative - add and test if negative
+ * @l: pointer of type local_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static __inline__ int local_add_negative(long i, local_t *l)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                "addl %2,%0; sets %1"
+                :"+m" (l->a.counter), "=qm" (c)
+                :"ir" (i) : "memory");
+        return c;
+}
+
+/**
+ * local_add_return - add and return
+ * @l: pointer of type local_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @l and returns @i + @l
+ */
+static __inline__ long local_add_return(long i, local_t *l)
+{
+        long __i;
+#ifdef CONFIG_M386
+        unsigned long flags;
+        if(unlikely(boot_cpu_data.x86 <= 3))
+                goto no_xadd;
+#endif
+        /* Modern 486+ processor */
+        __i = i;
+        __asm__ __volatile__(
+                "xaddl %0, %1;"
+                :"+r" (i), "+m" (l->a.counter)
+                : : "memory");
+        return i + __i;
+
+#ifdef CONFIG_M386
+no_xadd: /* Legacy 386 processor */
+        local_irq_save(flags);
+        __i = local_read(l);
+        local_set(l, i + __i);
+        local_irq_restore(flags);
+        return i + __i;
+#endif
+}
+
+static __inline__ long local_sub_return(long i, local_t *l)
+{
+        return local_add_return(-i,l);
+}
+
+#define local_inc_return(l)  (local_add_return(1,l))
+#define local_dec_return(l)  (local_sub_return(1,l))
+
+#define local_cmpxchg(l, o, n) \
+        (cmpxchg_local(&((l)->a.counter), (o), (n)))
+/* Always has a lock prefix */
+#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)                               \
+({                                                              \
+        long c, old;                                            \
+        c = local_read(l);                                      \
+        for (;;) {                                              \
+                if (unlikely(c == (u)))                         \
+                        break;                                  \
+                old = local_cmpxchg((l), c, c + (a));   \
+                if (likely(old == c))                           \
+                        break;                                  \
+                c = old;                                        \
+        }                                                       \
+        c != (u);                                               \
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+/* On x86, these are no better than the atomic variants. */
+#define __local_inc(l)          local_inc(l)
+#define __local_dec(l)          local_dec(l)
+#define __local_add(i,l)        local_add((i),(l))
+#define __local_sub(i,l)        local_sub((i),(l))
+
+/* Use these for per-cpu local_t variables: on some archs they are
+ * much more efficient than these naive implementations.  Note they take
+ * a variable, not an address.
+ */
+
+/* Need to disable preemption for the cpu local counters otherwise we could
+   still access a variable of a previous CPU in a non atomic way. */
+#define cpu_local_wrap_v(l)             \
+        ({ local_t res__;               \
+           preempt_disable();           \
+           res__ = (l);                 \
+           preempt_enable();            \
+           res__; })
+#define cpu_local_wrap(l)               \
+        ({ preempt_disable();           \
+           l;                           \
+           preempt_enable(); })         \
+
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
+
+#define __cpu_local_inc(l)      cpu_local_inc(l)
+#define __cpu_local_dec(l)      cpu_local_dec(l)
+#define __cpu_local_add(i, l)   cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)   cpu_local_sub((i), (l))
+
+#endif /* _ARCH_I386_LOCAL_H */
diff --git a/include/asm-x86/local_64.h b/include/asm-x86/local_64.h
new file mode 100644
index 000000000000..e87492bb0693
--- /dev/null
+++ b/include/asm-x86/local_64.h
@@ -0,0 +1,222 @@
+#ifndef _ARCH_X8664_LOCAL_H
+#define _ARCH_X8664_LOCAL_H
+
+#include <linux/percpu.h>
+#include <asm/atomic.h>
+
+typedef struct
+{
+        atomic_long_t a;
+} local_t;
+
+#define LOCAL_INIT(i)   { ATOMIC_LONG_INIT(i) }
+
+#define local_read(l)   atomic_long_read(&(l)->a)
+#define local_set(l,i)  atomic_long_set(&(l)->a, (i))
+
+static inline void local_inc(local_t *l)
+{
+        __asm__ __volatile__(
+                "incq %0"
+                :"=m" (l->a.counter)
+                :"m" (l->a.counter));
+}
+
+static inline void local_dec(local_t *l)
+{
+        __asm__ __volatile__(
+                "decq %0"
+                :"=m" (l->a.counter)
+                :"m" (l->a.counter));
+}
+
+static inline void local_add(long i, local_t *l)
+{
+        __asm__ __volatile__(
+                "addq %1,%0"
+                :"=m" (l->a.counter)
+                :"ir" (i), "m" (l->a.counter));
+}
+
+static inline void local_sub(long i, local_t *l)
+{
+        __asm__ __volatile__(
+                "subq %1,%0"
+                :"=m" (l->a.counter)
+                :"ir" (i), "m" (l->a.counter));
+}
+
+/**
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer to type local_t
+ *
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_sub_and_test(long i, local_t *l)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                "subq %2,%0; sete %1"
+                :"=m" (l->a.counter), "=qm" (c)
+                :"ir" (i), "m" (l->a.counter) : "memory");
+        return c;
+}
+
+/**
+ * local_dec_and_test - decrement and test
+ * @l: pointer to type local_t
+ *
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static __inline__ int local_dec_and_test(local_t *l)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                "decq %0; sete %1"
+                :"=m" (l->a.counter), "=qm" (c)
+                :"m" (l->a.counter) : "memory");
+        return c != 0;
+}
+
+/**
+ * local_inc_and_test - increment and test
+ * @l: pointer to type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_inc_and_test(local_t *l)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                "incq %0; sete %1"
+                :"=m" (l->a.counter), "=qm" (c)
+                :"m" (l->a.counter) : "memory");
+        return c != 0;
+}
+
+/**
+ * local_add_negative - add and test if negative
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static __inline__ int local_add_negative(long i, local_t *l)
+{
+        unsigned char c;
+
+        __asm__ __volatile__(
+                "addq %2,%0; sets %1"
+                :"=m" (l->a.counter), "=qm" (c)
+                :"ir" (i), "m" (l->a.counter) : "memory");
+        return c;
+}
+
+/**
+ * local_add_return - add and return
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns @i + @l
+ */
+static __inline__ long local_add_return(long i, local_t *l)
+{
+        long __i = i;
+        __asm__ __volatile__(
+                "xaddq %0, %1;"
+                :"+r" (i), "+m" (l->a.counter)
+                : : "memory");
+        return i + __i;
+}
+
+static __inline__ long local_sub_return(long i, local_t *l)
+{
+        return local_add_return(-i,l);
+}
+
+#define local_inc_return(l)  (local_add_return(1,l))
+#define local_dec_return(l)  (local_sub_return(1,l))
+
+#define local_cmpxchg(l, o, n) \
+        (cmpxchg_local(&((l)->a.counter), (o), (n)))
+/* Always has a lock prefix */
+#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
+
+/**
+ * atomic_up_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)                               \
+({                                                              \
+        long c, old;                                            \
+        c = local_read(l);                                      \
+        for (;;) {                                              \
+                if (unlikely(c == (u)))                         \
+                        break;                                  \
+                old = local_cmpxchg((l), c, c + (a));   \
+                if (likely(old == c))                           \
+                        break;                                  \
+                c = old;                                        \
+        }                                                       \
+        c != (u);                                               \
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+/* On x86-64 these are better than the atomic variants on SMP kernels
+   because they dont use a lock prefix. */
+#define __local_inc(l)          local_inc(l)
+#define __local_dec(l)          local_dec(l)
+#define __local_add(i,l)        local_add((i),(l))
+#define __local_sub(i,l)        local_sub((i),(l))
+
+/* Use these for per-cpu local_t variables: on some archs they are
+ * much more efficient than these naive implementations.  Note they take
+ * a variable, not an address.
+ *
+ * This could be done better if we moved the per cpu data directly
+ * after GS.
+ */
+
+/* Need to disable preemption for the cpu local counters otherwise we could
+   still access a variable of a previous CPU in a non atomic way. */
+#define cpu_local_wrap_v(l)             \
+        ({ local_t res__;               \
+           preempt_disable();           \
+           res__ = (l);                 \
+           preempt_enable();            \
+           res__; })
+#define cpu_local_wrap(l)               \
+        ({ preempt_disable();           \
+           l;                           \
+           preempt_enable(); })         \
+
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
+
+#define __cpu_local_inc(l)      cpu_local_inc(l)
+#define __cpu_local_dec(l)      cpu_local_dec(l)
+#define __cpu_local_add(i, l)   cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)   cpu_local_sub((i), (l))
+
+#endif /* _ARCH_X8664_LOCAL_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_apic.h b/include/asm-x86/mach-bigsmp/mach_apic.h
new file mode 100644
index 000000000000..ebd319f838ab
--- /dev/null
+++ b/include/asm-x86/mach-bigsmp/mach_apic.h
@@ -0,0 +1,158 @@
+#ifndef __ASM_MACH_APIC_H
+#define __ASM_MACH_APIC_H
+
+
+extern u8 bios_cpu_apicid[];
+
+#define xapic_phys_to_log_apicid(cpu) (bios_cpu_apicid[cpu])
+#define esr_disable (1)
+
+static inline int apic_id_registered(void)
+{
+        return (1);
+}
+
+/* Round robin the irqs amoung the online cpus */
+static inline cpumask_t target_cpus(void)
+{ 
+        static unsigned long cpu = NR_CPUS;
+        do {
+                if (cpu >= NR_CPUS)
+                        cpu = first_cpu(cpu_online_map);
+                else
+                        cpu = next_cpu(cpu, cpu_online_map);
+        } while (cpu >= NR_CPUS);
+        return cpumask_of_cpu(cpu);
+}
+
+#undef APIC_DEST_LOGICAL
+#define APIC_DEST_LOGICAL       0
+#define TARGET_CPUS             (target_cpus())
+#define APIC_DFR_VALUE          (APIC_DFR_FLAT)
+#define INT_DELIVERY_MODE       (dest_Fixed)
+#define INT_DEST_MODE           (0)    /* phys delivery to target proc */
+#define NO_BALANCE_IRQ          (0)
+#define WAKE_SECONDARY_VIA_INIT
+
+
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+        return (0);
+}
+
+static inline unsigned long check_apicid_present(int bit)
+{
+        return (1);
+}
+
+static inline unsigned long calculate_ldr(int cpu)
+{
+        unsigned long val, id;
+        val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+        id = xapic_phys_to_log_apicid(cpu);
+        val |= SET_APIC_LOGICAL_ID(id);
+        return val;
+}
+
+/*
+ * 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;
+        int cpu = smp_processor_id();
+
+        apic_write_around(APIC_DFR, APIC_DFR_VALUE);
+        val = calculate_ldr(cpu);
+        apic_write_around(APIC_LDR, val);
+}
+
+static inline void setup_apic_routing(void)
+{
+        printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
+                "Physflat", nr_ioapics);
+}
+
+static inline int multi_timer_check(int apic, int irq)
+{
+        return (0);
+}
+
+static inline int apicid_to_node(int logical_apicid)
+{
+        return (0);
+}
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+        if (mps_cpu < NR_CPUS)
+                return (int) bios_cpu_apicid[mps_cpu];
+
+        return BAD_APICID;
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
+{
+        return physid_mask_of_physid(phys_apicid);
+}
+
+extern u8 cpu_2_logical_apicid[];
+/* Mapping from cpu number to logical apicid */
+static inline int cpu_to_logical_apicid(int cpu)
+{
+        if (cpu >= NR_CPUS)
+                return BAD_APICID;
+        return cpu_physical_id(cpu);
+}
+
+static inline int mpc_apic_id(struct mpc_config_processor *m,
+                        struct mpc_config_translation *translation_record)
+{
+        printk("Processor #%d %ld:%ld APIC version %d\n",
+                m->mpc_apicid,
+                (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
+                (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
+                m->mpc_apicver);
+        return m->mpc_apicid;
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
+{
+        /* For clustered we don't have a good way to do this yet - hack */
+        return physids_promote(0xFFL);
+}
+
+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 (1);
+}
+
+/* As we are using single CPU as destination, pick only one CPU here */
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+        int cpu;
+        int apicid;     
+
+        cpu = first_cpu(cpumask);
+        apicid = cpu_to_logical_apicid(cpu);
+        return apicid;
+}
+
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+        return cpuid_apic >> index_msb;
+}
+
+#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_apicdef.h b/include/asm-x86/mach-bigsmp/mach_apicdef.h
new file mode 100644
index 000000000000..a58ab5a75c8c
--- /dev/null
+++ b/include/asm-x86/mach-bigsmp/mach_apicdef.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_MACH_APICDEF_H
+#define __ASM_MACH_APICDEF_H
+
+#define         APIC_ID_MASK            (0xFF<<24)
+
+static inline unsigned get_apic_id(unsigned long x) 
+{ 
+        return (((x)>>24)&0xFF);
+} 
+
+#define         GET_APIC_ID(x)  get_apic_id(x)
+
+#endif
diff --git a/include/asm-x86/mach-bigsmp/mach_ipi.h b/include/asm-x86/mach-bigsmp/mach_ipi.h
new file mode 100644
index 000000000000..9404c535b7ec
--- /dev/null
+++ b/include/asm-x86/mach-bigsmp/mach_ipi.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_MACH_IPI_H
+#define __ASM_MACH_IPI_H
+
+void send_IPI_mask_sequence(cpumask_t mask, int vector);
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+        send_IPI_mask_sequence(mask, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+        cpumask_t mask = cpu_online_map;
+        cpu_clear(smp_processor_id(), mask);
+
+        if (!cpus_empty(mask))
+                send_IPI_mask(mask, vector);
+}
+
+static inline void send_IPI_all(int vector)
+{
+        send_IPI_mask(cpu_online_map, vector);
+}
+
+#endif /* __ASM_MACH_IPI_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_mpspec.h b/include/asm-x86/mach-bigsmp/mach_mpspec.h
new file mode 100644
index 000000000000..6b5dadcf1d0e
--- /dev/null
+++ b/include/asm-x86/mach-bigsmp/mach_mpspec.h
@@ -0,0 +1,8 @@
+#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/apm.h b/include/asm-x86/mach-default/apm.h
new file mode 100644
index 000000000000..1f730b8bd1fd
--- /dev/null
+++ b/include/asm-x86/mach-default/apm.h
@@ -0,0 +1,75 @@
+/*
+ *  include/asm-i386/mach-default/apm.h
+ *
+ *  Machine specific APM BIOS functions for generic.
+ *  Split out from apm.c by Osamu Tomita <tomita@cinet.co.jp>
+ */
+
+#ifndef _ASM_APM_H
+#define _ASM_APM_H
+
+#ifdef APM_ZERO_SEGS
+#       define APM_DO_ZERO_SEGS \
+                "pushl %%ds\n\t" \
+                "pushl %%es\n\t" \
+                "xorl %%edx, %%edx\n\t" \
+                "mov %%dx, %%ds\n\t" \
+                "mov %%dx, %%es\n\t" \
+                "mov %%dx, %%fs\n\t" \
+                "mov %%dx, %%gs\n\t"
+#       define APM_DO_POP_SEGS \
+                "popl %%es\n\t" \
+                "popl %%ds\n\t"
+#else
+#       define APM_DO_ZERO_SEGS
+#       define APM_DO_POP_SEGS
+#endif
+
+static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
+                                        u32 *eax, u32 *ebx, u32 *ecx,
+                                        u32 *edx, u32 *esi)
+{
+        /*
+         * N.B. We do NOT need a cld after the BIOS call
+         * because we always save and restore the flags.
+         */
+        __asm__ __volatile__(APM_DO_ZERO_SEGS
+                "pushl %%edi\n\t"
+                "pushl %%ebp\n\t"
+                "lcall *%%cs:apm_bios_entry\n\t"
+                "setc %%al\n\t"
+                "popl %%ebp\n\t"
+                "popl %%edi\n\t"
+                APM_DO_POP_SEGS
+                : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx),
+                  "=S" (*esi)
+                : "a" (func), "b" (ebx_in), "c" (ecx_in)
+                : "memory", "cc");
+}
+
+static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
+                                                u32 ecx_in, u32 *eax)
+{
+        int     cx, dx, si;
+        u8      error;
+
+        /*
+         * N.B. We do NOT need a cld after the BIOS call
+         * because we always save and restore the flags.
+         */
+        __asm__ __volatile__(APM_DO_ZERO_SEGS
+                "pushl %%edi\n\t"
+                "pushl %%ebp\n\t"
+                "lcall *%%cs:apm_bios_entry\n\t"
+                "setc %%bl\n\t"
+                "popl %%ebp\n\t"
+                "popl %%edi\n\t"
+                APM_DO_POP_SEGS
+                : "=a" (*eax), "=b" (error), "=c" (cx), "=d" (dx),
+                  "=S" (si)
+                : "a" (func), "b" (ebx_in), "c" (ecx_in)
+                : "memory", "cc");
+        return error;
+}
+
+#endif /* _ASM_APM_H */
diff --git a/include/asm-x86/mach-default/bios_ebda.h b/include/asm-x86/mach-default/bios_ebda.h
new file mode 100644
index 000000000000..9cbd9a668af8
--- /dev/null
+++ b/include/asm-x86/mach-default/bios_ebda.h
@@ -0,0 +1,15 @@
+#ifndef _MACH_BIOS_EBDA_H
+#define _MACH_BIOS_EBDA_H
+
+/*
+ * there is a real-mode segmented pointer pointing to the
+ * 4K EBDA area at 0x40E.
+ */
+static inline unsigned int get_bios_ebda(void)
+{
+        unsigned int address = *(unsigned short *)phys_to_virt(0x40E);
+        address <<= 4;
+        return address; /* 0 means none */
+}
+
+#endif /* _MACH_BIOS_EBDA_H */
diff --git a/include/asm-x86/mach-default/do_timer.h b/include/asm-x86/mach-default/do_timer.h
new file mode 100644
index 000000000000..23ecda0b28a0
--- /dev/null
+++ b/include/asm-x86/mach-default/do_timer.h
@@ -0,0 +1,16 @@
+/* defines for inline arch setup functions */
+#include <linux/clockchips.h>
+
+#include <asm/i8259.h>
+#include <asm/i8253.h>
+
+/**
+ * do_timer_interrupt_hook - hook into timer tick
+ *
+ * Call the pit clock event handler. see asm/i8253.h
+ **/
+
+static inline void do_timer_interrupt_hook(void)
+{
+        global_clock_event->event_handler(global_clock_event);
+}
diff --git a/include/asm-x86/mach-default/entry_arch.h b/include/asm-x86/mach-default/entry_arch.h
new file mode 100644
index 000000000000..bc861469bdba
--- /dev/null
+++ b/include/asm-x86/mach-default/entry_arch.h
@@ -0,0 +1,34 @@
+/*
+ * This file is designed to contain the BUILD_INTERRUPT specifications for
+ * all of the extra named interrupt vectors used by the architecture.
+ * Usually this is the Inter Process Interrupts (IPIs)
+ */
+
+/*
+ * 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)
+ */
+#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)
+
+#ifdef CONFIG_X86_MCE_P4THERMAL
+BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
+#endif
+
+#endif
diff --git a/include/asm-x86/mach-default/io_ports.h b/include/asm-x86/mach-default/io_ports.h
new file mode 100644
index 000000000000..48540ba97166
--- /dev/null
+++ b/include/asm-x86/mach-default/io_ports.h
@@ -0,0 +1,25 @@
+/*
+ *  arch/i386/mach-generic/io_ports.h
+ *
+ *  Machine specific IO port address definition for generic.
+ *  Written by Osamu Tomita <tomita@cinet.co.jp>
+ */
+#ifndef _MACH_IO_PORTS_H
+#define _MACH_IO_PORTS_H
+
+/* i8259A PIC registers */
+#define PIC_MASTER_CMD          0x20
+#define PIC_MASTER_IMR          0x21
+#define PIC_MASTER_ISR          PIC_MASTER_CMD
+#define PIC_MASTER_POLL         PIC_MASTER_ISR
+#define PIC_MASTER_OCW3         PIC_MASTER_ISR
+#define PIC_SLAVE_CMD           0xa0
+#define PIC_SLAVE_IMR           0xa1
+
+/* i8259A PIC related value */
+#define PIC_CASCADE_IR          2
+#define MASTER_ICW4_DEFAULT     0x01
+#define SLAVE_ICW4_DEFAULT      0x01
+#define PIC_ICW4_AEOI           2
+
+#endif /* !_MACH_IO_PORTS_H */
diff --git a/include/asm-x86/mach-default/irq_vectors.h b/include/asm-x86/mach-default/irq_vectors.h
new file mode 100644
index 000000000000..881c63ca61ad
--- /dev/null
+++ b/include/asm-x86/mach-default/irq_vectors.h
@@ -0,0 +1,96 @@
+/*
+ * 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
new file mode 100644
index 000000000000..a90c7a60109f
--- /dev/null
+++ b/include/asm-x86/mach-default/irq_vectors_limits.h
@@ -0,0 +1,16 @@
+#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
new file mode 100644
index 000000000000..6db1c3babe9a
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_apic.h
@@ -0,0 +1,131 @@
+#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)
+
+static inline cpumask_t target_cpus(void)
+{ 
+#ifdef CONFIG_SMP
+        return cpu_online_map;
+#else
+        return cpumask_of_cpu(0);
+#endif
+} 
+#define TARGET_CPUS (target_cpus())
+
+#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 */
+
+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);
+}
+
+/*
+ * 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 physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
+{
+        return phys_map;
+}
+
+static inline void setup_apic_routing(void)
+{
+        printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
+                                        "Flat", nr_ioapics);
+}
+
+static inline int multi_timer_check(int apic, int irq)
+{
+        return 0;
+}
+
+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 phys_apicid)
+{
+        return physid_mask_of_physid(phys_apicid);
+}
+
+static inline int mpc_apic_id(struct mpc_config_processor *m, 
+                        struct mpc_config_translation *translation_record)
+{
+        printk("Processor #%d %ld:%ld APIC version %d\n",
+                        m->mpc_apicid,
+                        (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
+                        (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
+                        m->mpc_apicver);
+        return (m->mpc_apicid);
+}
+
+static inline void setup_portio_remap(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 int apic_id_registered(void)
+{
+        return physid_isset(GET_APIC_ID(apic_read(APIC_ID)), phys_cpu_present_map);
+}
+
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+        return cpus_addr(cpumask)[0];
+}
+
+static inline void enable_apic_mode(void)
+{
+}
+
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+        return cpuid_apic >> index_msb;
+}
+
+#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/mach-default/mach_apicdef.h b/include/asm-x86/mach-default/mach_apicdef.h
new file mode 100644
index 000000000000..7bcb350c3ee8
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_apicdef.h
@@ -0,0 +1,13 @@
+#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
diff --git a/include/asm-x86/mach-default/mach_ipi.h b/include/asm-x86/mach-default/mach_ipi.h
new file mode 100644
index 000000000000..0dba244c86db
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_ipi.h
@@ -0,0 +1,54 @@
+#ifndef __ASM_MACH_IPI_H
+#define __ASM_MACH_IPI_H
+
+/* Avoid include hell */
+#define NMI_VECTOR 0x02
+
+void send_IPI_mask_bitmask(cpumask_t mask, int vector);
+void __send_IPI_shortcut(unsigned int shortcut, int vector);
+
+extern int no_broadcast;
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+        send_IPI_mask_bitmask(mask, vector);
+}
+
+static inline void __local_send_IPI_allbutself(int vector)
+{
+        if (no_broadcast || vector == NMI_VECTOR) {
+                cpumask_t mask = cpu_online_map;
+
+                cpu_clear(smp_processor_id(), mask);
+                send_IPI_mask(mask, vector);
+        } else
+                __send_IPI_shortcut(APIC_DEST_ALLBUT, vector);
+}
+
+static inline void __local_send_IPI_all(int vector)
+{
+        if (no_broadcast || vector == NMI_VECTOR)
+                send_IPI_mask(cpu_online_map, vector);
+        else
+                __send_IPI_shortcut(APIC_DEST_ALLINC, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+        /*
+         * if there are no other CPUs in the system then we get an APIC send 
+         * error if we try to broadcast, thus avoid sending IPIs in this case.
+         */
+        if (!(num_online_cpus() > 1))
+                return;
+
+        __local_send_IPI_allbutself(vector);
+        return;
+}
+
+static inline void send_IPI_all(int vector)
+{
+        __local_send_IPI_all(vector);
+}
+
+#endif /* __ASM_MACH_IPI_H */
diff --git a/include/asm-x86/mach-default/mach_mpparse.h b/include/asm-x86/mach-default/mach_mpparse.h
new file mode 100644
index 000000000000..1d3832482580
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_mpparse.h
@@ -0,0 +1,28 @@
+#ifndef __ASM_MACH_MPPARSE_H
+#define __ASM_MACH_MPPARSE_H
+
+static inline void mpc_oem_bus_info(struct mpc_config_bus *m, char *name, 
+                                struct mpc_config_translation *translation)
+{
+//      Dprintk("Bus #%d is %s\n", m->mpc_busid, name);
+}
+
+static inline void mpc_oem_pci_bus(struct mpc_config_bus *m, 
+                                struct mpc_config_translation *translation)
+{
+}
+
+static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, 
+                char *productid)
+{
+        return 0;
+}
+
+/* Hook from generic ACPI tables.c */
+static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+        return 0;
+}
+
+
+#endif /* __ASM_MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-default/mach_mpspec.h b/include/asm-x86/mach-default/mach_mpspec.h
new file mode 100644
index 000000000000..51c9a9775932
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_mpspec.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_MACH_MPSPEC_H
+#define __ASM_MACH_MPSPEC_H
+
+#define MAX_IRQ_SOURCES 256
+
+#if CONFIG_BASE_SMALL == 0
+#define MAX_MP_BUSSES 256
+#else
+#define MAX_MP_BUSSES 32
+#endif
+
+#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-default/mach_reboot.h b/include/asm-x86/mach-default/mach_reboot.h
new file mode 100644
index 000000000000..e23fd9fbebb3
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_reboot.h
@@ -0,0 +1,61 @@
+/*
+ *  arch/i386/mach-generic/mach_reboot.h
+ *
+ *  Machine specific reboot functions for generic.
+ *  Split out from reboot.c by Osamu Tomita <tomita@cinet.co.jp>
+ */
+#ifndef _MACH_REBOOT_H
+#define _MACH_REBOOT_H
+
+static inline void kb_wait(void)
+{
+        int i;
+
+        for (i = 0; i < 0x10000; i++)
+                if ((inb_p(0x64) & 0x02) == 0)
+                        break;
+}
+
+static inline void mach_reboot(void)
+{
+        int i;
+
+        /* old method, works on most machines */
+        for (i = 0; i < 10; i++) {
+                kb_wait();
+                udelay(50);
+                outb(0xfe, 0x64);       /* pulse reset low */
+                udelay(50);
+        }
+
+        /* New method: sets the "System flag" which, when set, indicates
+         * successful completion of the keyboard controller self-test (Basic
+         * Assurance Test, BAT).  This is needed for some machines with no
+         * keyboard plugged in.  This read-modify-write sequence sets only the
+         * system flag
+         */
+        for (i = 0; i < 10; i++) {
+                int cmd;
+
+                outb(0x20, 0x64);       /* read Controller Command Byte */
+                udelay(50);
+                kb_wait();
+                udelay(50);
+                cmd = inb(0x60);
+                udelay(50);
+                kb_wait();
+                udelay(50);
+                outb(0x60, 0x64);       /* write Controller Command Byte */
+                udelay(50);
+                kb_wait();
+                udelay(50);
+                outb(cmd | 0x04, 0x60); /* set "System flag" */
+                udelay(50);
+                kb_wait();
+                udelay(50);
+                outb(0xfe, 0x64);       /* pulse reset low */
+                udelay(50);
+        }
+}
+
+#endif /* !_MACH_REBOOT_H */
diff --git a/include/asm-x86/mach-default/mach_time.h b/include/asm-x86/mach-default/mach_time.h
new file mode 100644
index 000000000000..31eb5de6f3dc
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_time.h
@@ -0,0 +1,111 @@
+/*
+ *  include/asm-i386/mach-default/mach_time.h
+ *
+ *  Machine specific set RTC function for generic.
+ *  Split out from time.c by Osamu Tomita <tomita@cinet.co.jp>
+ */
+#ifndef _MACH_TIME_H
+#define _MACH_TIME_H
+
+#include <linux/mc146818rtc.h>
+
+/* for check timing call set_rtc_mmss() 500ms     */
+/* used in arch/i386/time.c::do_timer_interrupt() */
+#define USEC_AFTER      500000
+#define USEC_BEFORE     500000
+
+/*
+ * In order to set the CMOS clock precisely, set_rtc_mmss has to be
+ * called 500 ms after the second nowtime has started, because when
+ * nowtime is written into the registers of the CMOS clock, it will
+ * jump to the next second precisely 500 ms later. Check the Motorola
+ * MC146818A or Dallas DS12887 data sheet for details.
+ *
+ * BUG: This routine does not handle hour overflow properly; it just
+ *      sets the minutes. Usually you'll only notice that after reboot!
+ */
+static inline int mach_set_rtc_mmss(unsigned long nowtime)
+{
+        int retval = 0;
+        int real_seconds, real_minutes, cmos_minutes;
+        unsigned char save_control, save_freq_select;
+
+        save_control = CMOS_READ(RTC_CONTROL); /* tell the clock it's being set */
+        CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
+
+        save_freq_select = CMOS_READ(RTC_FREQ_SELECT); /* stop and reset prescaler */
+        CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
+
+        cmos_minutes = CMOS_READ(RTC_MINUTES);
+        if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
+                BCD_TO_BIN(cmos_minutes);
+
+        /*
+         * since we're only adjusting minutes and seconds,
+         * don't interfere with hour overflow. This avoids
+         * messing with unknown time zones but requires your
+         * RTC not to be off by more than 15 minutes
+         */
+        real_seconds = nowtime % 60;
+        real_minutes = nowtime / 60;
+        if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1)
+                real_minutes += 30;             /* correct for half hour time zone */
+        real_minutes %= 60;
+
+        if (abs(real_minutes - cmos_minutes) < 30) {
+                if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+                        BIN_TO_BCD(real_seconds);
+                        BIN_TO_BCD(real_minutes);
+                }
+                CMOS_WRITE(real_seconds,RTC_SECONDS);
+                CMOS_WRITE(real_minutes,RTC_MINUTES);
+        } else {
+                printk(KERN_WARNING
+                       "set_rtc_mmss: can't update from %d to %d\n",
+                       cmos_minutes, real_minutes);
+                retval = -1;
+        }
+
+        /* The following flags have to be released exactly in this order,
+         * otherwise the DS12887 (popular MC146818A clone with integrated
+         * battery and quartz) will not reset the oscillator and will not
+         * update precisely 500 ms later. You won't find this mentioned in
+         * the Dallas Semiconductor data sheets, but who believes data
+         * sheets anyway ...                           -- Markus Kuhn
+         */
+        CMOS_WRITE(save_control, RTC_CONTROL);
+        CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+
+        return retval;
+}
+
+static inline unsigned long mach_get_cmos_time(void)
+{
+        unsigned int year, mon, day, hour, min, sec;
+
+        do {
+                sec = CMOS_READ(RTC_SECONDS);
+                min = CMOS_READ(RTC_MINUTES);
+                hour = CMOS_READ(RTC_HOURS);
+                day = CMOS_READ(RTC_DAY_OF_MONTH);
+                mon = CMOS_READ(RTC_MONTH);
+                year = CMOS_READ(RTC_YEAR);
+        } while (sec != CMOS_READ(RTC_SECONDS));
+
+        if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+                BCD_TO_BIN(sec);
+                BCD_TO_BIN(min);
+                BCD_TO_BIN(hour);
+                BCD_TO_BIN(day);
+                BCD_TO_BIN(mon);
+                BCD_TO_BIN(year);
+        }
+
+        year += 1900;
+        if (year < 1970)
+                year += 100;
+
+        return mktime(year, mon, day, hour, min, sec);
+}
+
+#endif /* !_MACH_TIME_H */
diff --git a/include/asm-x86/mach-default/mach_timer.h b/include/asm-x86/mach-default/mach_timer.h
new file mode 100644
index 000000000000..807992fd4171
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_timer.h
@@ -0,0 +1,50 @@
+/*
+ *  include/asm-i386/mach-default/mach_timer.h
+ *
+ *  Machine specific calibrate_tsc() for generic.
+ *  Split out from timer_tsc.c by Osamu Tomita <tomita@cinet.co.jp>
+ */
+/* ------ Calibrate the TSC ------- 
+ * Return 2^32 * (1 / (TSC clocks per usec)) for do_fast_gettimeoffset().
+ * Too much 64-bit arithmetic here to do this cleanly in C, and for
+ * accuracy's sake we want to keep the overhead on the CTC speaker (channel 2)
+ * output busy loop as low as possible. We avoid reading the CTC registers
+ * directly because of the awkward 8-bit access mechanism of the 82C54
+ * device.
+ */
+#ifndef _MACH_TIMER_H
+#define _MACH_TIMER_H
+
+#define CALIBRATE_TIME_MSEC 30 /* 30 msecs */
+#define CALIBRATE_LATCH \
+        ((CLOCK_TICK_RATE * CALIBRATE_TIME_MSEC + 1000/2)/1000)
+
+static inline void mach_prepare_counter(void)
+{
+       /* Set the Gate high, disable speaker */
+        outb((inb(0x61) & ~0x02) | 0x01, 0x61);
+
+        /*
+         * Now let's take care of CTC channel 2
+         *
+         * Set the Gate high, program CTC channel 2 for mode 0,
+         * (interrupt on terminal count mode), binary count,
+         * load 5 * LATCH count, (LSB and MSB) to begin countdown.
+         *
+         * Some devices need a delay here.
+         */
+        outb(0xb0, 0x43);                       /* binary, mode 0, LSB/MSB, Ch 2 */
+        outb_p(CALIBRATE_LATCH & 0xff, 0x42);   /* LSB of count */
+        outb_p(CALIBRATE_LATCH >> 8, 0x42);       /* MSB of count */
+}
+
+static inline void mach_countup(unsigned long *count_p)
+{
+        unsigned long count = 0;
+        do {
+                count++;
+        } while ((inb_p(0x61) & 0x20) == 0);
+        *count_p = count;
+}
+
+#endif /* !_MACH_TIMER_H */
diff --git a/include/asm-x86/mach-default/mach_traps.h b/include/asm-x86/mach-default/mach_traps.h
new file mode 100644
index 000000000000..625438b8a6eb
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_traps.h
@@ -0,0 +1,41 @@
+/*
+ *  include/asm-i386/mach-default/mach_traps.h
+ *
+ *  Machine specific NMI handling for generic.
+ *  Split out from traps.c by Osamu Tomita <tomita@cinet.co.jp>
+ */
+#ifndef _MACH_TRAPS_H
+#define _MACH_TRAPS_H
+
+#include <asm/mc146818rtc.h>
+
+static inline void clear_mem_error(unsigned char reason)
+{
+        reason = (reason & 0xf) | 4;
+        outb(reason, 0x61);
+}
+
+static inline unsigned char get_nmi_reason(void)
+{
+        return inb(0x61);
+}
+
+static inline void reassert_nmi(void)
+{
+        int old_reg = -1;
+
+        if (do_i_have_lock_cmos())
+                old_reg = current_lock_cmos_reg();
+        else
+                lock_cmos(0); /* register doesn't matter here */
+        outb(0x8f, 0x70);
+        inb(0x71);              /* dummy */
+        outb(0x0f, 0x70);
+        inb(0x71);              /* dummy */
+        if (old_reg >= 0)
+                outb(old_reg, 0x70);
+        else
+                unlock_cmos();
+}
+
+#endif /* !_MACH_TRAPS_H */
diff --git a/include/asm-x86/mach-default/mach_wakecpu.h b/include/asm-x86/mach-default/mach_wakecpu.h
new file mode 100644
index 000000000000..3ebb17893aa5
--- /dev/null
+++ b/include/asm-x86/mach-default/mach_wakecpu.h
@@ -0,0 +1,42 @@
+#ifndef __ASM_MACH_WAKECPU_H
+#define __ASM_MACH_WAKECPU_H
+
+/* 
+ * This file copes with machines that wakeup secondary CPUs by the
+ * INIT, INIT, STARTUP sequence.
+ */
+
+#define WAKE_SECONDARY_VIA_INIT
+
+#define TRAMPOLINE_LOW phys_to_virt(0x467)
+#define TRAMPOLINE_HIGH phys_to_virt(0x469)
+
+#define boot_cpu_apicid boot_cpu_physical_apicid
+
+static inline void wait_for_init_deassert(atomic_t *deassert)
+{
+        while (!atomic_read(deassert))
+                cpu_relax();
+        return;
+}
+
+/* Nothing to do for most platforms, since cleared by the INIT cycle */
+static inline void smp_callin_clear_local_apic(void)
+{
+}
+
+static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
+{
+}
+
+static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
+{
+}
+
+#if APIC_DEBUG
+ #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid)
+#else
+ #define inquire_remote_apic(apicid) {}
+#endif
+
+#endif /* __ASM_MACH_WAKECPU_H */
diff --git a/include/asm-x86/mach-default/pci-functions.h b/include/asm-x86/mach-default/pci-functions.h
new file mode 100644
index 000000000000..ed0bab427354
--- /dev/null
+++ b/include/asm-x86/mach-default/pci-functions.h
@@ -0,0 +1,19 @@
+/*
+ *      PCI BIOS function numbering for conventional PCI BIOS 
+ *      systems
+ */
+
+#define PCIBIOS_PCI_FUNCTION_ID         0xb1XX
+#define PCIBIOS_PCI_BIOS_PRESENT        0xb101
+#define PCIBIOS_FIND_PCI_DEVICE         0xb102
+#define PCIBIOS_FIND_PCI_CLASS_CODE     0xb103
+#define PCIBIOS_GENERATE_SPECIAL_CYCLE  0xb106
+#define PCIBIOS_READ_CONFIG_BYTE        0xb108
+#define PCIBIOS_READ_CONFIG_WORD        0xb109
+#define PCIBIOS_READ_CONFIG_DWORD       0xb10a
+#define PCIBIOS_WRITE_CONFIG_BYTE       0xb10b
+#define PCIBIOS_WRITE_CONFIG_WORD       0xb10c
+#define PCIBIOS_WRITE_CONFIG_DWORD      0xb10d
+#define PCIBIOS_GET_ROUTING_OPTIONS     0xb10e
+#define PCIBIOS_SET_PCI_HW_INT          0xb10f
+
diff --git a/include/asm-x86/mach-default/setup_arch.h b/include/asm-x86/mach-default/setup_arch.h
new file mode 100644
index 000000000000..605e3ccb991b
--- /dev/null
+++ b/include/asm-x86/mach-default/setup_arch.h
@@ -0,0 +1,7 @@
+/* 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
new file mode 100644
index 000000000000..7f45f6311059
--- /dev/null
+++ b/include/asm-x86/mach-default/smpboot_hooks.h
@@ -0,0 +1,44 @@
+/* two abstractions specific to kernel/smpboot.c, mainly to cater to visws
+ * which needs to alter them. */
+
+static inline void smpboot_clear_io_apic_irqs(void)
+{
+        io_apic_irqs = 0;
+}
+
+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");
+}
+
+static inline void smpboot_restore_warm_reset_vector(void)
+{
+        /*
+         * Install writable page 0 entry to set BIOS data area.
+         */
+        local_flush_tlb();
+
+        /*
+         * Paranoid:  Set warm reset code and vector here back
+         * to default values.
+         */
+        CMOS_WRITE(0, 0xf);
+
+        *((volatile long *) phys_to_virt(0x467)) = 0;
+}
+
+static inline void smpboot_setup_io_apic(void)
+{
+        /*
+         * 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();
+}
diff --git a/include/asm-x86/mach-es7000/mach_apic.h b/include/asm-x86/mach-es7000/mach_apic.h
new file mode 100644
index 000000000000..caec64be516d
--- /dev/null
+++ b/include/asm-x86/mach-es7000/mach_apic.h
@@ -0,0 +1,206 @@
+#ifndef __ASM_MACH_APIC_H
+#define __ASM_MACH_APIC_H
+
+extern u8 bios_cpu_apicid[];
+
+#define xapic_phys_to_log_apicid(cpu) (bios_cpu_apicid[cpu])
+#define esr_disable (1)
+
+static inline int apic_id_registered(void)
+{
+                return (1);
+}
+
+static inline cpumask_t target_cpus(void)
+{ 
+#if defined CONFIG_ES7000_CLUSTERED_APIC
+        return CPU_MASK_ALL;
+#else
+        return cpumask_of_cpu(smp_processor_id());
+#endif
+}
+#define TARGET_CPUS     (target_cpus())
+
+#if defined CONFIG_ES7000_CLUSTERED_APIC
+#define APIC_DFR_VALUE          (APIC_DFR_CLUSTER)
+#define INT_DELIVERY_MODE       (dest_LowestPrio)
+#define INT_DEST_MODE           (1)    /* logical delivery broadcast to all procs */
+#define NO_BALANCE_IRQ          (1)
+#undef  WAKE_SECONDARY_VIA_INIT
+#define WAKE_SECONDARY_VIA_MIP
+#else
+#define APIC_DFR_VALUE          (APIC_DFR_FLAT)
+#define INT_DELIVERY_MODE       (dest_Fixed)
+#define INT_DEST_MODE           (0)    /* phys delivery to target procs */
+#define NO_BALANCE_IRQ          (0)
+#undef  APIC_DEST_LOGICAL
+#define APIC_DEST_LOGICAL       0x0
+#define WAKE_SECONDARY_VIA_INIT
+#endif
+
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{ 
+        return 0;
+} 
+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 unsigned long calculate_ldr(int cpu)
+{
+        unsigned long id;
+        id = xapic_phys_to_log_apicid(cpu);
+        return (SET_APIC_LOGICAL_ID(id));
+}
+
+/*
+ * 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;
+        int cpu = smp_processor_id();
+
+        apic_write_around(APIC_DFR, APIC_DFR_VALUE);
+        val = calculate_ldr(cpu);
+        apic_write_around(APIC_LDR, val);
+}
+
+#ifndef CONFIG_X86_GENERICARCH
+extern void enable_apic_mode(void);
+#endif
+
+extern int apic_version [MAX_APICS];
+static inline void setup_apic_routing(void)
+{
+        int apic = bios_cpu_apicid[smp_processor_id()];
+        printk("Enabling APIC mode:  %s.  Using %d I/O APICs, target cpus %lx\n",
+                (apic_version[apic] == 0x14) ? 
+                "Physical Cluster" : "Logical Cluster", nr_ioapics, cpus_addr(TARGET_CPUS)[0]);
+}
+
+static inline int multi_timer_check(int apic, int irq)
+{
+        return 0;
+}
+
+static inline int apicid_to_node(int logical_apicid)
+{
+        return 0;
+}
+
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+        if (!mps_cpu)
+                return boot_cpu_physical_apicid;
+        else if (mps_cpu < NR_CPUS)
+                return (int) bios_cpu_apicid[mps_cpu];
+        else
+                return BAD_APICID;
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
+{
+        static int id = 0;
+        physid_mask_t mask;
+        mask = physid_mask_of_physid(id);
+        ++id;
+        return mask;
+}
+
+extern u8 cpu_2_logical_apicid[];
+/* Mapping from cpu number to logical apicid */
+static inline int cpu_to_logical_apicid(int cpu)
+{
+#ifdef CONFIG_SMP
+       if (cpu >= NR_CPUS)
+               return BAD_APICID;
+       return (int)cpu_2_logical_apicid[cpu];
+#else
+        return logical_smp_processor_id();
+#endif
+}
+
+static inline int mpc_apic_id(struct mpc_config_processor *m, struct mpc_config_translation *unused)
+{
+        printk("Processor #%d %ld:%ld APIC version %d\n",
+                m->mpc_apicid,
+                (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
+                (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
+                m->mpc_apicver);
+        return (m->mpc_apicid);
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
+{
+        /* For clustered we don't have a good way to do this yet - hack */
+        return physids_promote(0xff);
+}
+
+
+static inline void setup_portio_remap(void)
+{
+}
+
+extern unsigned int boot_cpu_physical_apicid;
+static inline int check_phys_apicid_present(int cpu_physical_apicid)
+{
+        boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID));
+        return (1);
+}
+
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+        int num_bits_set;
+        int cpus_found = 0;
+        int cpu;
+        int apicid;     
+
+        num_bits_set = cpus_weight(cpumask);
+        /* Return id to all */
+        if (num_bits_set == NR_CPUS)
+#if defined CONFIG_ES7000_CLUSTERED_APIC
+                return 0xFF;
+#else
+                return cpu_to_logical_apicid(0);
+#endif
+        /* 
+         * The cpus in the mask must all be on the apic cluster.  If are not 
+         * on the same apicid cluster return default value of TARGET_CPUS. 
+         */
+        cpu = first_cpu(cpumask);
+        apicid = cpu_to_logical_apicid(cpu);
+        while (cpus_found < num_bits_set) {
+                if (cpu_isset(cpu, cpumask)) {
+                        int new_apicid = cpu_to_logical_apicid(cpu);
+                        if (apicid_cluster(apicid) != 
+                                        apicid_cluster(new_apicid)){
+                                printk ("%s: Not a valid mask!\n",__FUNCTION__);
+#if defined CONFIG_ES7000_CLUSTERED_APIC
+                                return 0xFF;
+#else
+                                return cpu_to_logical_apicid(0);
+#endif
+                        }
+                        apicid = new_apicid;
+                        cpus_found++;
+                }
+                cpu++;
+        }
+        return apicid;
+}
+
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+        return cpuid_apic >> index_msb;
+}
+
+#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/mach-es7000/mach_apicdef.h b/include/asm-x86/mach-es7000/mach_apicdef.h
new file mode 100644
index 000000000000..a58ab5a75c8c
--- /dev/null
+++ b/include/asm-x86/mach-es7000/mach_apicdef.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_MACH_APICDEF_H
+#define __ASM_MACH_APICDEF_H
+
+#define         APIC_ID_MASK            (0xFF<<24)
+
+static inline unsigned get_apic_id(unsigned long x) 
+{ 
+        return (((x)>>24)&0xFF);
+} 
+
+#define         GET_APIC_ID(x)  get_apic_id(x)
+
+#endif
diff --git a/include/asm-x86/mach-es7000/mach_ipi.h b/include/asm-x86/mach-es7000/mach_ipi.h
new file mode 100644
index 000000000000..5e61bd220b06
--- /dev/null
+++ b/include/asm-x86/mach-es7000/mach_ipi.h
@@ -0,0 +1,24 @@
+#ifndef __ASM_MACH_IPI_H
+#define __ASM_MACH_IPI_H
+
+void send_IPI_mask_sequence(cpumask_t mask, int vector);
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+        send_IPI_mask_sequence(mask, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+        cpumask_t mask = cpu_online_map;
+        cpu_clear(smp_processor_id(), mask);
+        if (!cpus_empty(mask))
+                send_IPI_mask(mask, vector);
+}
+
+static inline void send_IPI_all(int vector)
+{
+        send_IPI_mask(cpu_online_map, vector);
+}
+
+#endif /* __ASM_MACH_IPI_H */
diff --git a/include/asm-x86/mach-es7000/mach_mpparse.h b/include/asm-x86/mach-es7000/mach_mpparse.h
new file mode 100644
index 000000000000..8aa10547b4b1
--- /dev/null
+++ b/include/asm-x86/mach-es7000/mach_mpparse.h
@@ -0,0 +1,40 @@
+#ifndef __ASM_MACH_MPPARSE_H
+#define __ASM_MACH_MPPARSE_H
+
+#include <linux/acpi.h>
+
+static inline void mpc_oem_bus_info(struct mpc_config_bus *m, char *name,
+                                struct mpc_config_translation *translation)
+{
+        Dprintk("Bus #%d is %s\n", m->mpc_busid, name);
+}
+
+static inline void mpc_oem_pci_bus(struct mpc_config_bus *m,
+                                struct mpc_config_translation *translation)
+{
+}
+
+extern int parse_unisys_oem (char *oemptr);
+extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
+extern void setup_unisys(void);
+
+#ifndef CONFIG_X86_GENERICARCH
+extern 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);
+#endif
+
+#ifdef CONFIG_ACPI
+
+static inline int es7000_check_dsdt(void)
+{
+        struct acpi_table_header header;
+        memcpy(&header, 0, sizeof(struct acpi_table_header));
+        acpi_get_table_header(ACPI_SIG_DSDT, 0, &header);
+        if (!strncmp(header.oem_id, "UNISYS", 6))
+                return 1;
+        return 0;
+}
+#endif
+
+#endif /* __ASM_MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-es7000/mach_mpspec.h b/include/asm-x86/mach-es7000/mach_mpspec.h
new file mode 100644
index 000000000000..b1f5039d4506
--- /dev/null
+++ b/include/asm-x86/mach-es7000/mach_mpspec.h
@@ -0,0 +1,8 @@
+#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-es7000/mach_wakecpu.h b/include/asm-x86/mach-es7000/mach_wakecpu.h
new file mode 100644
index 000000000000..84ff58314501
--- /dev/null
+++ b/include/asm-x86/mach-es7000/mach_wakecpu.h
@@ -0,0 +1,59 @@
+#ifndef __ASM_MACH_WAKECPU_H
+#define __ASM_MACH_WAKECPU_H
+
+/* 
+ * This file copes with machines that wakeup secondary CPUs by the
+ * INIT, INIT, STARTUP sequence.
+ */
+
+#ifdef CONFIG_ES7000_CLUSTERED_APIC
+#define WAKE_SECONDARY_VIA_MIP
+#else
+#define WAKE_SECONDARY_VIA_INIT
+#endif
+
+#ifdef WAKE_SECONDARY_VIA_MIP
+extern int es7000_start_cpu(int cpu, unsigned long eip);
+static inline int
+wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
+{
+        int boot_error = 0;
+        boot_error = es7000_start_cpu(phys_apicid, start_eip);
+        return boot_error;
+}
+#endif
+
+#define TRAMPOLINE_LOW phys_to_virt(0x467)
+#define TRAMPOLINE_HIGH phys_to_virt(0x469)
+
+#define boot_cpu_apicid boot_cpu_physical_apicid
+
+static inline void wait_for_init_deassert(atomic_t *deassert)
+{
+#ifdef WAKE_SECONDARY_VIA_INIT
+        while (!atomic_read(deassert))
+                cpu_relax();
+#endif
+        return;
+}
+
+/* Nothing to do for most platforms, since cleared by the INIT cycle */
+static inline void smp_callin_clear_local_apic(void)
+{
+}
+
+static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
+{
+}
+
+static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
+{
+}
+
+#if APIC_DEBUG
+ #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid)
+#else
+ #define inquire_remote_apic(apicid) {}
+#endif
+
+#endif /* __ASM_MACH_WAKECPU_H */
diff --git a/include/asm-x86/mach-generic/irq_vectors_limits.h b/include/asm-x86/mach-generic/irq_vectors_limits.h
new file mode 100644
index 000000000000..890ce3f5e09a
--- /dev/null
+++ b/include/asm-x86/mach-generic/irq_vectors_limits.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_IRQ_VECTORS_LIMITS_H
+#define _ASM_IRQ_VECTORS_LIMITS_H
+
+/*
+ * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
+ * even with uni-proc kernels, so use a big array.
+ *
+ * This value should be the same in both the generic and summit subarches.
+ * Change one, change 'em both.
+ */
+#define NR_IRQS 224
+#define NR_IRQ_VECTORS  1024
+
+#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/mach-generic/mach_apic.h b/include/asm-x86/mach-generic/mach_apic.h
new file mode 100644
index 000000000000..a236e7021528
--- /dev/null
+++ b/include/asm-x86/mach-generic/mach_apic.h
@@ -0,0 +1,33 @@
+#ifndef __ASM_MACH_APIC_H
+#define __ASM_MACH_APIC_H
+
+#include <asm/genapic.h>
+
+#define esr_disable (genapic->ESR_DISABLE)
+#define NO_BALANCE_IRQ (genapic->no_balance_irq)
+#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
+#define INT_DEST_MODE (genapic->int_dest_mode)
+#undef APIC_DEST_LOGICAL
+#define APIC_DEST_LOGICAL (genapic->apic_destination_logical)
+#define TARGET_CPUS       (genapic->target_cpus())
+#define apic_id_registered (genapic->apic_id_registered)
+#define init_apic_ldr (genapic->init_apic_ldr)
+#define ioapic_phys_id_map (genapic->ioapic_phys_id_map)
+#define setup_apic_routing (genapic->setup_apic_routing)
+#define multi_timer_check (genapic->multi_timer_check)
+#define apicid_to_node (genapic->apicid_to_node)
+#define cpu_to_logical_apicid (genapic->cpu_to_logical_apicid) 
+#define cpu_present_to_apicid (genapic->cpu_present_to_apicid)
+#define apicid_to_cpu_present (genapic->apicid_to_cpu_present)
+#define mpc_apic_id (genapic->mpc_apic_id) 
+#define setup_portio_remap (genapic->setup_portio_remap)
+#define check_apicid_present (genapic->check_apicid_present)
+#define check_phys_apicid_present (genapic->check_phys_apicid_present)
+#define check_apicid_used (genapic->check_apicid_used)
+#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
+#define enable_apic_mode (genapic->enable_apic_mode)
+#define phys_pkg_id (genapic->phys_pkg_id)
+
+extern void generic_bigsmp_probe(void);
+
+#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/mach-generic/mach_apicdef.h b/include/asm-x86/mach-generic/mach_apicdef.h
new file mode 100644
index 000000000000..28ed98972ca8
--- /dev/null
+++ b/include/asm-x86/mach-generic/mach_apicdef.h
@@ -0,0 +1,11 @@
+#ifndef _GENAPIC_MACH_APICDEF_H
+#define _GENAPIC_MACH_APICDEF_H 1
+
+#ifndef APIC_DEFINITION
+#include <asm/genapic.h>
+
+#define GET_APIC_ID (genapic->get_apic_id)
+#define APIC_ID_MASK (genapic->apic_id_mask)
+#endif
+
+#endif
diff --git a/include/asm-x86/mach-generic/mach_ipi.h b/include/asm-x86/mach-generic/mach_ipi.h
new file mode 100644
index 000000000000..441b0fe3ed1d
--- /dev/null
+++ b/include/asm-x86/mach-generic/mach_ipi.h
@@ -0,0 +1,10 @@
+#ifndef _MACH_IPI_H
+#define _MACH_IPI_H 1
+
+#include <asm/genapic.h>
+
+#define send_IPI_mask (genapic->send_IPI_mask)
+#define send_IPI_allbutself (genapic->send_IPI_allbutself)
+#define send_IPI_all (genapic->send_IPI_all)
+
+#endif
diff --git a/include/asm-x86/mach-generic/mach_mpparse.h b/include/asm-x86/mach-generic/mach_mpparse.h
new file mode 100644
index 000000000000..dbd9fce54f4d
--- /dev/null
+++ b/include/asm-x86/mach-generic/mach_mpparse.h
@@ -0,0 +1,12 @@
+#ifndef _MACH_MPPARSE_H
+#define _MACH_MPPARSE_H 1
+
+#include <asm/genapic.h>
+
+#define mpc_oem_bus_info (genapic->mpc_oem_bus_info)
+#define mpc_oem_pci_bus (genapic->mpc_oem_pci_bus)
+
+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); 
+
+#endif
diff --git a/include/asm-x86/mach-generic/mach_mpspec.h b/include/asm-x86/mach-generic/mach_mpspec.h
new file mode 100644
index 000000000000..9ef0b941bb22
--- /dev/null
+++ b/include/asm-x86/mach-generic/mach_mpspec.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_MACH_MPSPEC_H
+#define __ASM_MACH_MPSPEC_H
+
+#define MAX_IRQ_SOURCES 256
+
+/* Summit or generic (i.e. installer) kernels need lots of bus entries. */
+/* 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-numaq/mach_apic.h b/include/asm-x86/mach-numaq/mach_apic.h
new file mode 100644
index 000000000000..5e5e7dd2692e
--- /dev/null
+++ b/include/asm-x86/mach-numaq/mach_apic.h
@@ -0,0 +1,149 @@
+#ifndef __ASM_MACH_APIC_H
+#define __ASM_MACH_APIC_H
+
+#include <asm/io.h>
+#include <linux/mmzone.h>
+#include <linux/nodemask.h>
+
+#define APIC_DFR_VALUE  (APIC_DFR_CLUSTER)
+
+static inline cpumask_t target_cpus(void)
+{
+        return CPU_MASK_ALL;
+}
+
+#define TARGET_CPUS (target_cpus())
+
+#define NO_BALANCE_IRQ (1)
+#define esr_disable (1)
+
+#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)
+#define apicid_cluster(apicid) (apicid & 0xF0)
+
+static inline int apic_id_registered(void)
+{
+        return 1;
+}
+
+static inline void init_apic_ldr(void)
+{
+        /* Already done in NUMA-Q firmware */
+}
+
+static inline void setup_apic_routing(void)
+{
+        printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
+                "NUMA-Q", nr_ioapics);
+}
+
+/*
+ * Skip adding the timer int on secondary nodes, which causes
+ * a small but painful rift in the time-space continuum.
+ */
+static inline int multi_timer_check(int apic, int irq)
+{
+        return apic != 0 && irq == 0;
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
+{
+        /* We don't have a good way to do this yet - hack */
+        return physids_promote(0xFUL);
+}
+
+/* Mapping from cpu number to logical apicid */
+extern u8 cpu_2_logical_apicid[];
+static inline int cpu_to_logical_apicid(int cpu)
+{
+       if (cpu >= NR_CPUS)
+               return BAD_APICID;
+        return (int)cpu_2_logical_apicid[cpu];
+}
+
+/*
+ * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
+ * cpu to APIC ID relation to properly interact with the intelligent
+ * mode of the cluster controller.
+ */
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+        if (mps_cpu < 60)
+                return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3));
+        else
+                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;
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int logical_apicid)
+{
+        int node = apicid_to_node(logical_apicid);
+        int cpu = __ffs(logical_apicid & 0xf);
+
+        return physid_mask_of_physid(cpu + 4*node);
+}
+
+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 %ld:%ld 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;
+}
+
+static inline void setup_portio_remap(void)
+{
+        int num_quads = num_online_nodes();
+
+        if (num_quads <= 1)
+                return;
+
+        printk("Remapping cross-quad port I/O for %d quads\n", num_quads);
+        xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD);
+        printk("xquad_portio vaddr 0x%08lx, len %08lx\n",
+                (u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD);
+}
+
+static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+        return (1);
+}
+
+static inline void enable_apic_mode(void)
+{
+}
+
+/*
+ * We use physical apicids here, not logical, so just return the default
+ * physical broadcast to stop people from breaking us
+ */
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+        return (int) 0xF;
+}
+
+/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+        return cpuid_apic >> index_msb;
+}
+
+#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/mach-numaq/mach_apicdef.h b/include/asm-x86/mach-numaq/mach_apicdef.h
new file mode 100644
index 000000000000..bf439d0690f5
--- /dev/null
+++ b/include/asm-x86/mach-numaq/mach_apicdef.h
@@ -0,0 +1,14 @@
+#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)&0x0F);
+}
+
+#define         GET_APIC_ID(x)  get_apic_id(x)
+
+#endif
diff --git a/include/asm-x86/mach-numaq/mach_ipi.h b/include/asm-x86/mach-numaq/mach_ipi.h
new file mode 100644
index 000000000000..c6044488e9e6
--- /dev/null
+++ b/include/asm-x86/mach-numaq/mach_ipi.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_MACH_IPI_H
+#define __ASM_MACH_IPI_H
+
+void send_IPI_mask_sequence(cpumask_t, int vector);
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+        send_IPI_mask_sequence(mask, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+        cpumask_t mask = cpu_online_map;
+        cpu_clear(smp_processor_id(), mask);
+
+        if (!cpus_empty(mask))
+                send_IPI_mask(mask, vector);
+}
+
+static inline void send_IPI_all(int vector)
+{
+        send_IPI_mask(cpu_online_map, vector);
+}
+
+#endif /* __ASM_MACH_IPI_H */
diff --git a/include/asm-x86/mach-numaq/mach_mpparse.h b/include/asm-x86/mach-numaq/mach_mpparse.h
new file mode 100644
index 000000000000..51bbac8fc0c2
--- /dev/null
+++ b/include/asm-x86/mach-numaq/mach_mpparse.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_MACH_MPPARSE_H
+#define __ASM_MACH_MPPARSE_H
+
+static inline void mpc_oem_bus_info(struct mpc_config_bus *m, char *name, 
+                                struct mpc_config_translation *translation)
+{
+        int quad = translation->trans_quad;
+        int local = translation->trans_local;
+
+        mp_bus_id_to_node[m->mpc_busid] = quad;
+        mp_bus_id_to_local[m->mpc_busid] = local;
+        printk("Bus #%d is %s (node %d)\n", m->mpc_busid, name, quad);
+}
+
+static inline void mpc_oem_pci_bus(struct mpc_config_bus *m, 
+                                struct mpc_config_translation *translation)
+{
+        int quad = translation->trans_quad;
+        int local = translation->trans_local;
+
+        quad_local_to_mp_bus_id[quad][local] = m->mpc_busid;
+}
+
+/* Hook from generic ACPI tables.c */
+static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+}
+
+#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
new file mode 100644
index 000000000000..dffb09856f8f
--- /dev/null
+++ b/include/asm-x86/mach-numaq/mach_mpspec.h
@@ -0,0 +1,8 @@
+#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-numaq/mach_wakecpu.h b/include/asm-x86/mach-numaq/mach_wakecpu.h
new file mode 100644
index 000000000000..00530041a991
--- /dev/null
+++ b/include/asm-x86/mach-numaq/mach_wakecpu.h
@@ -0,0 +1,43 @@
+#ifndef __ASM_MACH_WAKECPU_H
+#define __ASM_MACH_WAKECPU_H
+
+/* This file copes with machines that wakeup secondary CPUs by NMIs */
+
+#define WAKE_SECONDARY_VIA_NMI
+
+#define TRAMPOLINE_LOW phys_to_virt(0x8)
+#define TRAMPOLINE_HIGH phys_to_virt(0xa)
+
+#define boot_cpu_apicid boot_cpu_logical_apicid
+
+/* We don't do anything here because we use NMI's to boot instead */
+static inline void wait_for_init_deassert(atomic_t *deassert)
+{
+}
+
+/*
+ * Because we use NMIs rather than the INIT-STARTUP sequence to
+ * bootstrap the CPUs, the APIC may be in a weird state. Kick it.
+ */
+static inline void smp_callin_clear_local_apic(void)
+{
+        clear_local_APIC();
+}
+
+static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
+{
+        printk("Storing NMI vector\n");
+        *high = *((volatile unsigned short *) TRAMPOLINE_HIGH);
+        *low = *((volatile unsigned short *) TRAMPOLINE_LOW);
+}
+
+static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
+{
+        printk("Restoring NMI vector\n");
+        *((volatile unsigned short *) TRAMPOLINE_HIGH) = *high;
+        *((volatile unsigned short *) TRAMPOLINE_LOW) = *low;
+}
+
+#define inquire_remote_apic(apicid) {}
+
+#endif /* __ASM_MACH_WAKECPU_H */
diff --git a/include/asm-x86/mach-summit/irq_vectors_limits.h b/include/asm-x86/mach-summit/irq_vectors_limits.h
new file mode 100644
index 000000000000..890ce3f5e09a
--- /dev/null
+++ b/include/asm-x86/mach-summit/irq_vectors_limits.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_IRQ_VECTORS_LIMITS_H
+#define _ASM_IRQ_VECTORS_LIMITS_H
+
+/*
+ * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
+ * even with uni-proc kernels, so use a big array.
+ *
+ * This value should be the same in both the generic and summit subarches.
+ * Change one, change 'em both.
+ */
+#define NR_IRQS 224
+#define NR_IRQ_VECTORS  1024
+
+#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/mach-summit/mach_apic.h b/include/asm-x86/mach-summit/mach_apic.h
new file mode 100644
index 000000000000..732f776aab8e
--- /dev/null
+++ b/include/asm-x86/mach-summit/mach_apic.h
@@ -0,0 +1,197 @@
+#ifndef __ASM_MACH_APIC_H
+#define __ASM_MACH_APIC_H
+
+#include <asm/smp.h>
+
+#define esr_disable (1)
+#define NO_BALANCE_IRQ (0)
+
+/* In clustered mode, the high nibble of APIC ID is a cluster number.
+ * The low nibble is a 4-bit bitmap. */
+#define XAPIC_DEST_CPUS_SHIFT   4
+#define XAPIC_DEST_CPUS_MASK    ((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
+#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
+
+#define APIC_DFR_VALUE  (APIC_DFR_CLUSTER)
+
+static inline cpumask_t target_cpus(void)
+{
+        /* CPU_MASK_ALL (0xff) has undefined behaviour with
+         * dest_LowestPrio mode logical clustered apic interrupt routing
+         * Just start on cpu 0.  IRQ balancing will spread load
+         */
+        return cpumask_of_cpu(0);
+} 
+#define TARGET_CPUS     (target_cpus())
+
+#define INT_DELIVERY_MODE (dest_LowestPrio)
+#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
+
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+        return 0;
+} 
+
+/* we don't use the phys_cpu_present_map to indicate apicid presence */
+static inline unsigned long check_apicid_present(int bit) 
+{
+        return 1;
+}
+
+#define apicid_cluster(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK)
+
+extern u8 bios_cpu_apicid[];
+extern u8 cpu_2_logical_apicid[];
+
+static inline void init_apic_ldr(void)
+{
+        unsigned long val, id;
+        int count = 0;
+        u8 my_id = (u8)hard_smp_processor_id();
+        u8 my_cluster = (u8)apicid_cluster(my_id);
+#ifdef CONFIG_SMP
+        u8 lid;
+        int i;
+
+        /* Create logical APIC IDs by counting CPUs already in cluster. */
+        for (count = 0, i = NR_CPUS; --i >= 0; ) {
+                lid = cpu_2_logical_apicid[i];
+                if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
+                        ++count;
+        }
+#endif
+        /* We only have a 4 wide bitmap in cluster mode.  If a deranged
+         * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
+        BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
+        id = my_cluster | (1UL << count);
+        apic_write_around(APIC_DFR, APIC_DFR_VALUE);
+        val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+        val |= SET_APIC_LOGICAL_ID(id);
+        apic_write_around(APIC_LDR, val);
+}
+
+static inline int multi_timer_check(int apic, int irq)
+{
+        return 0;
+}
+
+static inline int apic_id_registered(void)
+{
+        return 1;
+}
+
+static inline void setup_apic_routing(void)
+{
+        printk("Enabling APIC mode:  Summit.  Using %d I/O APICs\n",
+                                                nr_ioapics);
+}
+
+static inline int apicid_to_node(int logical_apicid)
+{
+#ifdef CONFIG_SMP
+        return apicid_2_node[hard_smp_processor_id()];
+#else
+        return 0;
+#endif
+}
+
+/* Mapping from cpu number to logical apicid */
+static inline int cpu_to_logical_apicid(int cpu)
+{
+#ifdef CONFIG_SMP
+       if (cpu >= NR_CPUS)
+               return BAD_APICID;
+        return (int)cpu_2_logical_apicid[cpu];
+#else
+        return logical_smp_processor_id();
+#endif
+}
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+        if (mps_cpu < NR_CPUS)
+                return (int)bios_cpu_apicid[mps_cpu];
+        else
+                return BAD_APICID;
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_id_map)
+{
+        /* For clustered we don't have a good way to do this yet - hack */
+        return physids_promote(0x0F);
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int apicid)
+{
+        return physid_mask_of_physid(0);
+}
+
+static inline int mpc_apic_id(struct mpc_config_processor *m, 
+                        struct mpc_config_translation *translation_record)
+{
+        printk("Processor #%d %ld:%ld APIC version %d\n",
+                        m->mpc_apicid,
+                        (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
+                        (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
+                        m->mpc_apicver);
+        return (m->mpc_apicid);
+}
+
+static inline void setup_portio_remap(void)
+{
+}
+
+static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+        return 1;
+}
+
+static inline void enable_apic_mode(void)
+{
+}
+
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+        int num_bits_set;
+        int cpus_found = 0;
+        int cpu;
+        int apicid;     
+
+        num_bits_set = cpus_weight(cpumask);
+        /* Return id to all */
+        if (num_bits_set == NR_CPUS)
+                return (int) 0xFF;
+        /* 
+         * The cpus in the mask must all be on the apic cluster.  If are not 
+         * on the same apicid cluster return default value of TARGET_CPUS. 
+         */
+        cpu = first_cpu(cpumask);
+        apicid = cpu_to_logical_apicid(cpu);
+        while (cpus_found < num_bits_set) {
+                if (cpu_isset(cpu, cpumask)) {
+                        int new_apicid = cpu_to_logical_apicid(cpu);
+                        if (apicid_cluster(apicid) != 
+                                        apicid_cluster(new_apicid)){
+                                printk ("%s: Not a valid mask!\n",__FUNCTION__);
+                                return 0xFF;
+                        }
+                        apicid = apicid | new_apicid;
+                        cpus_found++;
+                }
+                cpu++;
+        }
+        return apicid;
+}
+
+/* cpuid returns the value latched in the HW at reset, not the APIC ID
+ * register's value.  For any box whose BIOS changes APIC IDs, like
+ * clustered APIC systems, we must use hard_smp_processor_id.
+ *
+ * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
+ */
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+        return hard_smp_processor_id() >> index_msb;
+}
+
+#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/mach-summit/mach_apicdef.h b/include/asm-x86/mach-summit/mach_apicdef.h
new file mode 100644
index 000000000000..a58ab5a75c8c
--- /dev/null
+++ b/include/asm-x86/mach-summit/mach_apicdef.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_MACH_APICDEF_H
+#define __ASM_MACH_APICDEF_H
+
+#define         APIC_ID_MASK            (0xFF<<24)
+
+static inline unsigned get_apic_id(unsigned long x) 
+{ 
+        return (((x)>>24)&0xFF);
+} 
+
+#define         GET_APIC_ID(x)  get_apic_id(x)
+
+#endif
diff --git a/include/asm-x86/mach-summit/mach_ipi.h b/include/asm-x86/mach-summit/mach_ipi.h
new file mode 100644
index 000000000000..9404c535b7ec
--- /dev/null
+++ b/include/asm-x86/mach-summit/mach_ipi.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_MACH_IPI_H
+#define __ASM_MACH_IPI_H
+
+void send_IPI_mask_sequence(cpumask_t mask, int vector);
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+        send_IPI_mask_sequence(mask, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+        cpumask_t mask = cpu_online_map;
+        cpu_clear(smp_processor_id(), mask);
+
+        if (!cpus_empty(mask))
+                send_IPI_mask(mask, vector);
+}
+
+static inline void send_IPI_all(int vector)
+{
+        send_IPI_mask(cpu_online_map, vector);
+}
+
+#endif /* __ASM_MACH_IPI_H */
diff --git a/include/asm-x86/mach-summit/mach_mpparse.h b/include/asm-x86/mach-summit/mach_mpparse.h
new file mode 100644
index 000000000000..c2520539d934
--- /dev/null
+++ b/include/asm-x86/mach-summit/mach_mpparse.h
@@ -0,0 +1,121 @@
+#ifndef __ASM_MACH_MPPARSE_H
+#define __ASM_MACH_MPPARSE_H
+
+#include <mach_apic.h>
+#include <asm/tsc.h>
+
+extern int use_cyclone;
+
+#ifdef CONFIG_X86_SUMMIT_NUMA
+extern void setup_summit(void);
+#else
+#define setup_summit()  {}
+#endif
+
+static inline void mpc_oem_bus_info(struct mpc_config_bus *m, char *name, 
+                                struct mpc_config_translation *translation)
+{
+        Dprintk("Bus #%d is %s\n", m->mpc_busid, name);
+}
+
+static inline void mpc_oem_pci_bus(struct mpc_config_bus *m, 
+                                struct mpc_config_translation *translation)
+{
+}
+
+static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, 
+                char *productid)
+{
+        if (!strncmp(oem, "IBM ENSW", 8) && 
+                        (!strncmp(productid, "VIGIL SMP", 9) 
+                         || !strncmp(productid, "EXA", 3)
+                         || !strncmp(productid, "RUTHLESS SMP", 12))){
+                mark_tsc_unstable("Summit based system");
+                use_cyclone = 1; /*enable cyclone-timer*/
+                setup_summit();
+                return 1;
+        }
+        return 0;
+}
+
+/* Hook from generic ACPI tables.c */
+static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+        if (!strncmp(oem_id, "IBM", 3) &&
+            (!strncmp(oem_table_id, "SERVIGIL", 8)
+             || !strncmp(oem_table_id, "EXA", 3))){
+                mark_tsc_unstable("Summit based system");
+                use_cyclone = 1; /*enable cyclone-timer*/
+                setup_summit();
+                return 1;
+        }
+        return 0;
+}
+
+struct rio_table_hdr {
+        unsigned char version;      /* Version number of this data structure           */
+                                    /* Version 3 adds chassis_num & WP_index           */
+        unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil)   */
+        unsigned char num_rio_dev;  /* # of RIO I/O devices (Cyclones and Winnipegs)   */
+} __attribute__((packed));
+
+struct scal_detail {
+        unsigned char node_id;      /* Scalability Node ID                             */
+        unsigned long CBAR;         /* Address of 1MB register space                   */
+        unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
+        unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+        unsigned char port1node;    /* Node ID port connected to: 0xFF = None          */
+        unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+        unsigned char port2node;    /* Node ID port connected to: 0xFF = None          */
+        unsigned char port2port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+        unsigned char chassis_num;  /* 1 based Chassis number (1 = boot node)          */
+} __attribute__((packed));
+
+struct rio_detail {
+        unsigned char node_id;      /* RIO Node ID                                     */
+        unsigned long BBAR;         /* Address of 1MB register space                   */
+        unsigned char type;         /* Type of device                                  */
+        unsigned char owner_id;     /* For WPEG: Node ID of Cyclone that owns this WPEG*/
+                                    /* For CYC:  Node ID of Twister that owns this CYC */
+        unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
+        unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+        unsigned char port1node;    /* Node ID port connected to: 0xFF=None            */
+        unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+        unsigned char first_slot;   /* For WPEG: Lowest slot number below this WPEG    */
+                                    /* For CYC:  0                                     */
+        unsigned char status;       /* For WPEG: Bit 0 = 1 : the XAPIC is used         */
+                                    /*                 = 0 : the XAPIC is not used, ie:*/
+                                    /*                     ints fwded to another XAPIC */
+                                    /*           Bits1:7 Reserved                      */
+                                    /* For CYC:  Bits0:7 Reserved                      */
+        unsigned char WP_index;     /* For WPEG: WPEG instance index - lower ones have */
+                                    /*           lower slot numbers/PCI bus numbers    */
+                                    /* For CYC:  No meaning                            */
+        unsigned char chassis_num;  /* 1 based Chassis number                          */
+                                    /* For LookOut WPEGs this field indicates the      */
+                                    /* Expansion Chassis #, enumerated from Boot       */
+                                    /* Node WPEG external port, then Boot Node CYC     */
+                                    /* external port, then Next Vigil chassis WPEG     */
+                                    /* external port, etc.                             */
+                                    /* Shared Lookouts have only 1 chassis number (the */
+                                    /* first one assigned)                             */
+} __attribute__((packed));
+
+
+typedef enum {
+        CompatTwister = 0,  /* Compatibility Twister               */
+        AltTwister    = 1,  /* Alternate Twister of internal 8-way */
+        CompatCyclone = 2,  /* Compatibility Cyclone               */
+        AltCyclone    = 3,  /* Alternate Cyclone of internal 8-way */
+        CompatWPEG    = 4,  /* Compatibility WPEG                  */
+        AltWPEG       = 5,  /* Second Planar WPEG                  */
+        LookOutAWPEG  = 6,  /* LookOut WPEG                        */
+        LookOutBWPEG  = 7,  /* LookOut WPEG                        */
+} node_type;
+
+static inline int is_WPEG(struct rio_detail *rio){
+        return (rio->type == CompatWPEG || rio->type == AltWPEG ||
+                rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
+}
+
+#endif /* __ASM_MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-summit/mach_mpspec.h b/include/asm-x86/mach-summit/mach_mpspec.h
new file mode 100644
index 000000000000..bd765523511a
--- /dev/null
+++ b/include/asm-x86/mach-summit/mach_mpspec.h
@@ -0,0 +1,9 @@
+#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/cobalt.h b/include/asm-x86/mach-visws/cobalt.h
new file mode 100644
index 000000000000..33c36225a042
--- /dev/null
+++ b/include/asm-x86/mach-visws/cobalt.h
@@ -0,0 +1,125 @@
+#ifndef __I386_SGI_COBALT_H
+#define __I386_SGI_COBALT_H
+
+#include <asm/fixmap.h>
+
+/*
+ * Cobalt SGI Visual Workstation system ASIC
+ */ 
+
+#define CO_CPU_NUM_PHYS 0x1e00
+#define CO_CPU_TAB_PHYS (CO_CPU_NUM_PHYS + 2)
+
+#define CO_CPU_MAX 4
+
+#define CO_CPU_PHYS             0xc2000000
+#define CO_APIC_PHYS            0xc4000000
+
+/* see set_fixmap() and asm/fixmap.h */
+#define CO_CPU_VADDR            (fix_to_virt(FIX_CO_CPU))
+#define CO_APIC_VADDR           (fix_to_virt(FIX_CO_APIC))
+
+/* Cobalt CPU registers -- relative to CO_CPU_VADDR, use co_cpu_*() */
+#define CO_CPU_REV              0x08
+#define CO_CPU_CTRL             0x10
+#define CO_CPU_STAT             0x20
+#define CO_CPU_TIMEVAL          0x30
+
+/* CO_CPU_CTRL bits */
+#define CO_CTRL_TIMERUN         0x04            /* 0 == disabled */
+#define CO_CTRL_TIMEMASK        0x08            /* 0 == unmasked */
+
+/* CO_CPU_STATUS bits */
+#define CO_STAT_TIMEINTR        0x02    /* (r) 1 == int pend, (w) 0 == clear */
+
+/* CO_CPU_TIMEVAL value */
+#define CO_TIME_HZ              100000000       /* Cobalt core rate */
+
+/* Cobalt APIC registers -- relative to CO_APIC_VADDR, use co_apic_*() */
+#define CO_APIC_HI(n)           (((n) * 0x10) + 4)
+#define CO_APIC_LO(n)           ((n) * 0x10)
+#define CO_APIC_ID              0x0ffc
+
+/* CO_APIC_ID bits */
+#define CO_APIC_ENABLE          0x00000100
+
+/* CO_APIC_LO bits */
+#define CO_APIC_MASK            0x00010000      /* 0 = enabled */
+#define CO_APIC_LEVEL           0x00008000      /* 0 = edge */
+
+/*
+ * Where things are physically wired to Cobalt
+ * #defines with no board _<type>_<rev>_ are common to all (thus far)
+ */
+#define CO_APIC_IDE0            4
+#define CO_APIC_IDE1            2               /* Only on 320 */
+
+#define CO_APIC_8259            12              /* serial, floppy, par-l-l */
+
+/* Lithium PCI Bridge A -- "the one with 82557 Ethernet" */
+#define CO_APIC_PCIA_BASE0      0 /* and 1 */   /* slot 0, line 0 */
+#define CO_APIC_PCIA_BASE123    5 /* and 6 */   /* slot 0, line 1 */
+
+#define CO_APIC_PIIX4_USB       7               /* this one is weird */
+
+/* Lithium PCI Bridge B -- "the one with PIIX4" */
+#define CO_APIC_PCIB_BASE0      8 /* and 9-12 *//* slot 0, line 0 */
+#define CO_APIC_PCIB_BASE123    13 /* 14.15 */  /* slot 0, line 1 */
+
+#define CO_APIC_VIDOUT0         16
+#define CO_APIC_VIDOUT1         17
+#define CO_APIC_VIDIN0          18
+#define CO_APIC_VIDIN1          19
+
+#define CO_APIC_LI_AUDIO        22
+
+#define CO_APIC_AS              24
+#define CO_APIC_RE              25
+
+#define CO_APIC_CPU             28              /* Timer and Cache interrupt */
+#define CO_APIC_NMI             29
+#define CO_APIC_LAST            CO_APIC_NMI
+
+/*
+ * This is how irqs are assigned on the Visual Workstation.
+ * Legacy devices get irq's 1-15 (system clock is 0 and is CO_APIC_CPU).
+ * All other devices (including PCI) go to Cobalt and are irq's 16 on up.
+ */
+#define CO_IRQ_APIC0    16                      /* irq of apic entry 0 */
+#define IS_CO_APIC(irq) ((irq) >= CO_IRQ_APIC0)
+#define CO_IRQ(apic)    (CO_IRQ_APIC0 + (apic)) /* apic ent to irq */
+#define CO_APIC(irq)    ((irq) - CO_IRQ_APIC0)  /* irq to apic ent */
+#define CO_IRQ_IDE0     14                      /* knowledge of... */
+#define CO_IRQ_IDE1     15                      /* ... ide driver defaults! */
+#define CO_IRQ_8259     CO_IRQ(CO_APIC_8259)
+
+#ifdef CONFIG_X86_VISWS_APIC
+extern __inline void co_cpu_write(unsigned long reg, unsigned long v)
+{
+        *((volatile unsigned long *)(CO_CPU_VADDR+reg))=v;
+}
+
+extern __inline unsigned long co_cpu_read(unsigned long reg)
+{
+        return *((volatile unsigned long *)(CO_CPU_VADDR+reg));
+}            
+             
+extern __inline void co_apic_write(unsigned long reg, unsigned long v)
+{
+        *((volatile unsigned long *)(CO_APIC_VADDR+reg))=v;
+}            
+             
+extern __inline unsigned long co_apic_read(unsigned long reg)
+{
+        return *((volatile unsigned long *)(CO_APIC_VADDR+reg));
+}
+#endif
+
+extern char visws_board_type;
+
+#define VISWS_320       0
+#define VISWS_540       1
+
+extern char visws_board_rev;
+
+#endif /* __I386_SGI_COBALT_H */
diff --git a/include/asm-x86/mach-visws/entry_arch.h b/include/asm-x86/mach-visws/entry_arch.h
new file mode 100644
index 000000000000..b183fa6d83d9
--- /dev/null
+++ b/include/asm-x86/mach-visws/entry_arch.h
@@ -0,0 +1,23 @@
+/*
+ * 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)
+ */
+#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
diff --git a/include/asm-x86/mach-visws/irq_vectors.h b/include/asm-x86/mach-visws/irq_vectors.h
new file mode 100644
index 000000000000..cb572d8db505
--- /dev/null
+++ b/include/asm-x86/mach-visws/irq_vectors.h
@@ -0,0 +1,62 @@
+#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/lithium.h b/include/asm-x86/mach-visws/lithium.h
new file mode 100644
index 000000000000..d443e68d0066
--- /dev/null
+++ b/include/asm-x86/mach-visws/lithium.h
@@ -0,0 +1,53 @@
+#ifndef __I386_SGI_LITHIUM_H
+#define __I386_SGI_LITHIUM_H
+
+#include <asm/fixmap.h>
+
+/*
+ * Lithium is the SGI Visual Workstation I/O ASIC
+ */
+
+#define LI_PCI_A_PHYS           0xfc000000      /* Enet is dev 3 */
+#define LI_PCI_B_PHYS           0xfd000000      /* PIIX4 is here */
+
+/* see set_fixmap() and asm/fixmap.h */
+#define LI_PCIA_VADDR   (fix_to_virt(FIX_LI_PCIA))
+#define LI_PCIB_VADDR   (fix_to_virt(FIX_LI_PCIB))
+
+/* Not a standard PCI? (not in linux/pci.h) */
+#define LI_PCI_BUSNUM   0x44                    /* lo8: primary, hi8: sub */
+#define LI_PCI_INTEN    0x46
+
+/* LI_PCI_INTENT bits */
+#define LI_INTA_0       0x0001
+#define LI_INTA_1       0x0002
+#define LI_INTA_2       0x0004
+#define LI_INTA_3       0x0008
+#define LI_INTA_4       0x0010
+#define LI_INTB         0x0020
+#define LI_INTC         0x0040
+#define LI_INTD         0x0080
+
+/* More special purpose macros... */
+extern __inline void li_pcia_write16(unsigned long reg, unsigned short v)
+{
+        *((volatile unsigned short *)(LI_PCIA_VADDR+reg))=v;
+}
+
+extern __inline unsigned short li_pcia_read16(unsigned long reg)
+{
+         return *((volatile unsigned short *)(LI_PCIA_VADDR+reg));
+}
+
+extern __inline void li_pcib_write16(unsigned long reg, unsigned short v)
+{
+        *((volatile unsigned short *)(LI_PCIB_VADDR+reg))=v;
+}
+
+extern __inline unsigned short li_pcib_read16(unsigned long reg)
+{
+        return *((volatile unsigned short *)(LI_PCIB_VADDR+reg));
+}
+
+#endif
+
diff --git a/include/asm-x86/mach-visws/mach_apic.h b/include/asm-x86/mach-visws/mach_apic.h
new file mode 100644
index 000000000000..efac6f0d139f
--- /dev/null
+++ b/include/asm-x86/mach-visws/mach_apic.h
@@ -0,0 +1,103 @@
+#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(apic_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 */
diff --git a/include/asm-x86/mach-visws/mach_apicdef.h b/include/asm-x86/mach-visws/mach_apicdef.h
new file mode 100644
index 000000000000..826cfa97d778
--- /dev/null
+++ b/include/asm-x86/mach-visws/mach_apicdef.h
@@ -0,0 +1,12 @@
+#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
diff --git a/include/asm-x86/mach-visws/piix4.h b/include/asm-x86/mach-visws/piix4.h
new file mode 100644
index 000000000000..83ea4f46e419
--- /dev/null
+++ b/include/asm-x86/mach-visws/piix4.h
@@ -0,0 +1,107 @@
+#ifndef __I386_SGI_PIIX_H
+#define __I386_SGI_PIIX_H
+
+/*
+ * PIIX4 as used on SGI Visual Workstations
+ */
+
+#define PIIX_PM_START           0x0F80
+
+#define SIO_GPIO_START          0x0FC0
+
+#define SIO_PM_START            0x0FC8
+
+#define PMBASE                  PIIX_PM_START
+#define GPIREG0                 (PMBASE+0x30)
+#define GPIREG(x)               (GPIREG0+((x)/8))
+#define GPIBIT(x)               (1 << ((x)%8))
+
+#define PIIX_GPI_BD_ID1         18
+#define PIIX_GPI_BD_ID2         19
+#define PIIX_GPI_BD_ID3         20
+#define PIIX_GPI_BD_ID4         21
+#define PIIX_GPI_BD_REG         GPIREG(PIIX_GPI_BD_ID1)
+#define PIIX_GPI_BD_MASK        (GPIBIT(PIIX_GPI_BD_ID1) | \
+                                GPIBIT(PIIX_GPI_BD_ID2) | \
+                                GPIBIT(PIIX_GPI_BD_ID3) | \
+                                GPIBIT(PIIX_GPI_BD_ID4) )
+
+#define PIIX_GPI_BD_SHIFT       (PIIX_GPI_BD_ID1 % 8)
+
+#define SIO_INDEX               0x2e
+#define SIO_DATA                0x2f
+
+#define SIO_DEV_SEL             0x7
+#define SIO_DEV_ENB             0x30
+#define SIO_DEV_MSB             0x60
+#define SIO_DEV_LSB             0x61
+
+#define SIO_GP_DEV              0x7
+
+#define SIO_GP_BASE             SIO_GPIO_START
+#define SIO_GP_MSB              (SIO_GP_BASE>>8)
+#define SIO_GP_LSB              (SIO_GP_BASE&0xff)
+
+#define SIO_GP_DATA1            (SIO_GP_BASE+0)
+
+#define SIO_PM_DEV              0x8
+
+#define SIO_PM_BASE             SIO_PM_START
+#define SIO_PM_MSB              (SIO_PM_BASE>>8)
+#define SIO_PM_LSB              (SIO_PM_BASE&0xff)
+#define SIO_PM_INDEX            (SIO_PM_BASE+0)
+#define SIO_PM_DATA             (SIO_PM_BASE+1)
+
+#define SIO_PM_FER2             0x1
+
+#define SIO_PM_GP_EN            0x80
+
+
+
+/*
+ * This is the dev/reg where generating a config cycle will
+ * result in a PCI special cycle.
+ */
+#define SPECIAL_DEV             0xff
+#define SPECIAL_REG             0x00
+
+/*
+ * PIIX4 needs to see a special cycle with the following data
+ * to be convinced the processor has gone into the stop grant
+ * state.  PIIX4 insists on seeing this before it will power
+ * down a system.
+ */
+#define PIIX_SPECIAL_STOP               0x00120002
+
+#define PIIX4_RESET_PORT        0xcf9
+#define PIIX4_RESET_VAL         0x6
+
+#define PMSTS_PORT              0xf80   // 2 bytes      PM Status
+#define PMEN_PORT               0xf82   // 2 bytes      PM Enable
+#define PMCNTRL_PORT            0xf84   // 2 bytes      PM Control
+
+#define PM_SUSPEND_ENABLE       0x2000  // start sequence to suspend state
+
+/*
+ * PMSTS and PMEN I/O bit definitions.
+ * (Bits are the same in both registers)
+ */
+#define PM_STS_RSM              (1<<15) // Resume Status
+#define PM_STS_PWRBTNOR         (1<<11) // Power Button Override
+#define PM_STS_RTC              (1<<10) // RTC status
+#define PM_STS_PWRBTN           (1<<8)  // Power Button Pressed?
+#define PM_STS_GBL              (1<<5)  // Global Status
+#define PM_STS_BM               (1<<4)  // Bus Master Status
+#define PM_STS_TMROF            (1<<0)  // Timer Overflow Status.
+
+/*
+ * Stop clock GPI register
+ */
+#define PIIX_GPIREG0                    (0xf80 + 0x30)
+
+/*
+ * Stop clock GPI bit in GPIREG0
+ */
+#define PIIX_GPI_STPCLK         0x4     // STPCLK signal routed back in
+
+#endif
diff --git a/include/asm-x86/mach-visws/setup_arch.h b/include/asm-x86/mach-visws/setup_arch.h
new file mode 100644
index 000000000000..33f700ef6831
--- /dev/null
+++ b/include/asm-x86/mach-visws/setup_arch.h
@@ -0,0 +1,8 @@
+/* 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
diff --git a/include/asm-x86/mach-visws/smpboot_hooks.h b/include/asm-x86/mach-visws/smpboot_hooks.h
new file mode 100644
index 000000000000..d926471fa359
--- /dev/null
+++ b/include/asm-x86/mach-visws/smpboot_hooks.h
@@ -0,0 +1,24 @@
+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)
+{
+}
diff --git a/include/asm-x86/mach-voyager/do_timer.h b/include/asm-x86/mach-voyager/do_timer.h
new file mode 100644
index 000000000000..bc2b58926308
--- /dev/null
+++ b/include/asm-x86/mach-voyager/do_timer.h
@@ -0,0 +1,18 @@
+/* defines for inline arch setup functions */
+#include <linux/clockchips.h>
+
+#include <asm/voyager.h>
+#include <asm/i8253.h>
+
+/**
+ * do_timer_interrupt_hook - hook into timer tick
+ * @regs:     standard registers from interrupt
+ *
+ * Call the pit clock event handler. see asm/i8253.h
+ **/
+static inline void do_timer_interrupt_hook(void)
+{
+        global_clock_event->event_handler(global_clock_event);
+        voyager_timer_interrupt();
+}
+
diff --git a/include/asm-x86/mach-voyager/entry_arch.h b/include/asm-x86/mach-voyager/entry_arch.h
new file mode 100644
index 000000000000..4a1e1e8c10b6
--- /dev/null
+++ b/include/asm-x86/mach-voyager/entry_arch.h
@@ -0,0 +1,26 @@
+/* -*- mode: c; c-basic-offset: 8 -*- */
+
+/* Copyright (C) 2002
+ *
+ * Author: James.Bottomley@HansenPartnership.com
+ *
+ * linux/arch/i386/voyager/entry_arch.h
+ *
+ * This file builds the VIC and QIC CPI gates
+ */
+
+/* initialise the voyager interrupt gates 
+ *
+ * This uses the macros in irq.h to set up assembly jump gates.  The
+ * calls are then redirected to the same routine with smp_ prefixed */
+BUILD_INTERRUPT(vic_sys_interrupt, VIC_SYS_INT)
+BUILD_INTERRUPT(vic_cmn_interrupt, VIC_CMN_INT)
+BUILD_INTERRUPT(vic_cpi_interrupt, VIC_CPI_LEVEL0);
+
+/* do all the QIC interrupts */
+BUILD_INTERRUPT(qic_timer_interrupt, QIC_TIMER_CPI);
+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);
+
diff --git a/include/asm-x86/mach-voyager/irq_vectors.h b/include/asm-x86/mach-voyager/irq_vectors.h
new file mode 100644
index 000000000000..165421f5821c
--- /dev/null
+++ b/include/asm-x86/mach-voyager/irq_vectors.h
@@ -0,0 +1,79 @@
+/* -*- 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/mach-voyager/setup_arch.h b/include/asm-x86/mach-voyager/setup_arch.h
new file mode 100644
index 000000000000..84d01ad33459
--- /dev/null
+++ b/include/asm-x86/mach-voyager/setup_arch.h
@@ -0,0 +1,10 @@
+#include <asm/voyager.h>
+#define VOYAGER_BIOS_INFO ((struct voyager_bios_info *)(PARAM+0x40))
+
+/* Hook to call BIOS initialisation function */
+
+/* for voyager, pass the voyager BIOS/SUS info area to the detection
+ * routines */
+
+#define ARCH_SETUP      voyager_detect(VOYAGER_BIOS_INFO);
+
diff --git a/include/asm-x86/mach_apic.h b/include/asm-x86/mach_apic.h
new file mode 100644
index 000000000000..7b7115a0c1c9
--- /dev/null
+++ b/include/asm-x86/mach_apic.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_MACH_APIC_H
+#define __ASM_MACH_APIC_H
+
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC sub-arch defines.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+
+#include <asm/genapic.h>
+
+#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
+#define INT_DEST_MODE (genapic->int_dest_mode)
+#define TARGET_CPUS       (genapic->target_cpus())
+#define vector_allocation_domain        (genapic->vector_allocation_domain)
+#define apic_id_registered (genapic->apic_id_registered)
+#define init_apic_ldr (genapic->init_apic_ldr)
+#define send_IPI_mask (genapic->send_IPI_mask)
+#define send_IPI_allbutself (genapic->send_IPI_allbutself)
+#define send_IPI_all (genapic->send_IPI_all)
+#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
+#define phys_pkg_id     (genapic->phys_pkg_id)
+
+#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/math_emu.h b/include/asm-x86/math_emu.h
new file mode 100644
index 000000000000..a4b0aa3320e6
--- /dev/null
+++ b/include/asm-x86/math_emu.h
@@ -0,0 +1,36 @@
+#ifndef _I386_MATH_EMU_H
+#define _I386_MATH_EMU_H
+
+#include <asm/sigcontext.h>
+
+int restore_i387_soft(void *s387, struct _fpstate __user *buf);
+int save_i387_soft(void *s387, struct _fpstate __user *buf);
+
+/* This structure matches the layout of the data saved to the stack
+   following a device-not-present interrupt, part of it saved
+   automatically by the 80386/80486.
+   */
+struct info {
+        long ___orig_eip;
+        long ___ebx;
+        long ___ecx;
+        long ___edx;
+        long ___esi;
+        long ___edi;
+        long ___ebp;
+        long ___eax;
+        long ___ds;
+        long ___es;
+        long ___fs;
+        long ___orig_eax;
+        long ___eip;
+        long ___cs;
+        long ___eflags;
+        long ___esp;
+        long ___ss;
+        long ___vm86_es; /* This and the following only in vm86 mode */
+        long ___vm86_ds;
+        long ___vm86_fs;
+        long ___vm86_gs;
+};
+#endif
diff --git a/include/asm-x86/mc146818rtc.h b/include/asm-x86/mc146818rtc.h
new file mode 100644
index 000000000000..5c2bb66caf17
--- /dev/null
+++ b/include/asm-x86/mc146818rtc.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mc146818rtc_32.h"
+#else
+# include "mc146818rtc_64.h"
+#endif
diff --git a/include/asm-x86/mc146818rtc_32.h b/include/asm-x86/mc146818rtc_32.h
new file mode 100644
index 000000000000..1613b42eaf58
--- /dev/null
+++ b/include/asm-x86/mc146818rtc_32.h
@@ -0,0 +1,97 @@
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _ASM_MC146818RTC_H
+#define _ASM_MC146818RTC_H
+
+#include <asm/io.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <linux/mc146818rtc.h>
+
+#ifndef RTC_PORT
+#define RTC_PORT(x)     (0x70 + (x))
+#define RTC_ALWAYS_BCD  1       /* RTC operates in binary mode */
+#endif
+
+#ifdef __HAVE_ARCH_CMPXCHG
+/*
+ * This lock provides nmi access to the CMOS/RTC registers.  It has some
+ * special properties.  It is owned by a CPU and stores the index register
+ * currently being accessed (if owned).  The idea here is that it works
+ * like a normal lock (normally).  However, in an NMI, the NMI code will
+ * first check to see if its CPU owns the lock, meaning that the NMI
+ * interrupted during the read/write of the device.  If it does, it goes ahead
+ * and performs the access and then restores the index register.  If it does
+ * not, it locks normally.
+ *
+ * Note that since we are working with NMIs, we need this lock even in
+ * a non-SMP machine just to mark that the lock is owned.
+ *
+ * This only works with compare-and-swap.  There is no other way to
+ * atomically claim the lock and set the owner.
+ */
+#include <linux/smp.h>
+extern volatile unsigned long cmos_lock;
+
+/*
+ * All of these below must be called with interrupts off, preempt
+ * disabled, etc.
+ */
+
+static inline void lock_cmos(unsigned char reg)
+{
+        unsigned long new;
+        new = ((smp_processor_id()+1) << 8) | reg;
+        for (;;) {
+                if (cmos_lock) {
+                        cpu_relax();
+                        continue;
+                }
+                if (__cmpxchg(&cmos_lock, 0, new, sizeof(cmos_lock)) == 0)
+                        return;
+        }
+}
+
+static inline void unlock_cmos(void)
+{
+        cmos_lock = 0;
+}
+static inline int do_i_have_lock_cmos(void)
+{
+        return (cmos_lock >> 8) == (smp_processor_id()+1);
+}
+static inline unsigned char current_lock_cmos_reg(void)
+{
+        return cmos_lock & 0xff;
+}
+#define lock_cmos_prefix(reg) \
+        do {                                    \
+                unsigned long cmos_flags;       \
+                local_irq_save(cmos_flags);     \
+                lock_cmos(reg)
+#define lock_cmos_suffix(reg) \
+                unlock_cmos();                  \
+                local_irq_restore(cmos_flags);  \
+        } while (0)
+#else
+#define lock_cmos_prefix(reg) do {} while (0)
+#define lock_cmos_suffix(reg) do {} while (0)
+#define lock_cmos(reg)
+#define unlock_cmos()
+#define do_i_have_lock_cmos() 0
+#define current_lock_cmos_reg() 0
+#endif
+
+/*
+ * The yet supported machines all access the RTC index register via
+ * an ISA port access but the way to access the date register differs ...
+ */
+#define CMOS_READ(addr) rtc_cmos_read(addr)
+#define CMOS_WRITE(val, addr) rtc_cmos_write(val, addr)
+unsigned char rtc_cmos_read(unsigned char addr);
+void rtc_cmos_write(unsigned char val, unsigned char addr);
+
+#define RTC_IRQ 8
+
+#endif /* _ASM_MC146818RTC_H */
diff --git a/include/asm-x86/mc146818rtc_64.h b/include/asm-x86/mc146818rtc_64.h
new file mode 100644
index 000000000000..d6e3009430c1
--- /dev/null
+++ b/include/asm-x86/mc146818rtc_64.h
@@ -0,0 +1,29 @@
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _ASM_MC146818RTC_H
+#define _ASM_MC146818RTC_H
+
+#include <asm/io.h>
+
+#ifndef RTC_PORT
+#define RTC_PORT(x)     (0x70 + (x))
+#define RTC_ALWAYS_BCD  1       /* RTC operates in binary mode */
+#endif
+
+/*
+ * The yet supported machines all access the RTC index register via
+ * an ISA port access but the way to access the date register differs ...
+ */
+#define CMOS_READ(addr) ({ \
+outb_p((addr),RTC_PORT(0)); \
+inb_p(RTC_PORT(1)); \
+})
+#define CMOS_WRITE(val, addr) ({ \
+outb_p((addr),RTC_PORT(0)); \
+outb_p((val),RTC_PORT(1)); \
+})
+
+#define RTC_IRQ 8
+
+#endif /* _ASM_MC146818RTC_H */
diff --git a/include/asm-x86/mca.h b/include/asm-x86/mca.h
new file mode 100644
index 000000000000..09adf2eac4dc
--- /dev/null
+++ b/include/asm-x86/mca.h
@@ -0,0 +1,43 @@
+/* -*- mode: c; c-basic-offset: 8 -*- */
+
+/* Platform specific MCA defines */
+#ifndef _ASM_MCA_H
+#define _ASM_MCA_H
+
+/* Maximal number of MCA slots - actually, some machines have less, but
+ * they all have sufficient number of POS registers to cover 8.
+ */
+#define MCA_MAX_SLOT_NR  8
+
+/* Most machines have only one MCA bus.  The only multiple bus machines
+ * I know have at most two */
+#define MAX_MCA_BUSSES 2
+
+#define MCA_PRIMARY_BUS         0
+#define MCA_SECONDARY_BUS       1
+
+/* Dummy slot numbers on primary MCA for integrated functions */
+#define MCA_INTEGSCSI   (MCA_MAX_SLOT_NR)
+#define MCA_INTEGVIDEO  (MCA_MAX_SLOT_NR+1)
+#define MCA_MOTHERBOARD (MCA_MAX_SLOT_NR+2)
+
+/* Dummy POS values for integrated functions */
+#define MCA_DUMMY_POS_START     0x10000
+#define MCA_INTEGSCSI_POS       (MCA_DUMMY_POS_START+1)
+#define MCA_INTEGVIDEO_POS      (MCA_DUMMY_POS_START+2)
+#define MCA_MOTHERBOARD_POS     (MCA_DUMMY_POS_START+3)
+
+/* MCA registers */
+
+#define MCA_MOTHERBOARD_SETUP_REG       0x94
+#define MCA_ADAPTER_SETUP_REG           0x96
+#define MCA_POS_REG(n)                  (0x100+(n))
+
+#define MCA_ENABLED     0x01    /* POS 2, set if adapter enabled */
+
+/* Max number of adapters, including both slots and various integrated
+ * things.
+ */
+#define MCA_NUMADAPTERS (MCA_MAX_SLOT_NR+3)
+
+#endif
diff --git a/include/asm-x86/mca_dma.h b/include/asm-x86/mca_dma.h
new file mode 100644
index 000000000000..fbb1f3b71279
--- /dev/null
+++ b/include/asm-x86/mca_dma.h
@@ -0,0 +1,201 @@
+#ifndef MCA_DMA_H
+#define MCA_DMA_H
+
+#include <asm/io.h>
+#include <linux/ioport.h>
+
+/*
+ * Microchannel specific DMA stuff.  DMA on an MCA machine is fairly similar to
+ *   standard PC dma, but it certainly has its quirks.  DMA register addresses
+ *   are in a different place and there are some added functions.  Most of this
+ *   should be pretty obvious on inspection.  Note that the user must divide
+ *   count by 2 when using 16-bit dma; that is not handled by these functions.
+ *
+ * Ramen Noodles are yummy.
+ * 
+ *  1998 Tymm Twillman <tymm@computer.org>  
+ */
+
+/*
+ * Registers that are used by the DMA controller; FN is the function register 
+ *   (tell the controller what to do) and EXE is the execution register (how
+ *   to do it)
+ */
+
+#define MCA_DMA_REG_FN  0x18
+#define MCA_DMA_REG_EXE 0x1A 
+
+/*
+ * Functions that the DMA controller can do
+ */
+
+#define MCA_DMA_FN_SET_IO       0x00
+#define MCA_DMA_FN_SET_ADDR     0x20
+#define MCA_DMA_FN_GET_ADDR     0x30
+#define MCA_DMA_FN_SET_COUNT    0x40
+#define MCA_DMA_FN_GET_COUNT    0x50
+#define MCA_DMA_FN_GET_STATUS   0x60
+#define MCA_DMA_FN_SET_MODE     0x70
+#define MCA_DMA_FN_SET_ARBUS    0x80
+#define MCA_DMA_FN_MASK         0x90
+#define MCA_DMA_FN_RESET_MASK   0xA0
+#define MCA_DMA_FN_MASTER_CLEAR 0xD0
+
+/*
+ * Modes (used by setting MCA_DMA_FN_MODE in the function register)
+ * 
+ * Note that the MODE_READ is read from memory (write to device), and
+ *   MODE_WRITE is vice-versa.  
+ */
+
+#define MCA_DMA_MODE_XFER  0x04  /* read by default */
+#define MCA_DMA_MODE_READ  0x04  /* same as XFER */
+#define MCA_DMA_MODE_WRITE 0x08  /* OR with MODE_XFER to use */
+#define MCA_DMA_MODE_IO    0x01  /* DMA from IO register */
+#define MCA_DMA_MODE_16    0x40  /* 16 bit xfers */
+
+
+/**
+ *      mca_enable_dma  -       channel to enable DMA on
+ *      @dmanr: DMA channel
+ *
+ *      Enable the MCA bus DMA on a channel. This can be called from
+ *      IRQ context.
+ */
+
+static __inline__ void mca_enable_dma(unsigned int dmanr)
+{
+        outb(MCA_DMA_FN_RESET_MASK | dmanr, MCA_DMA_REG_FN);
+}
+
+/**
+ *      mca_disble_dma  -       channel to disable DMA on
+ *      @dmanr: DMA channel
+ *
+ *      Enable the MCA bus DMA on a channel. This can be called from
+ *      IRQ context.
+ */
+
+static __inline__ void mca_disable_dma(unsigned int dmanr)
+{
+        outb(MCA_DMA_FN_MASK | dmanr, MCA_DMA_REG_FN);
+}
+
+/**
+ *      mca_set_dma_addr -      load a 24bit DMA address
+ *      @dmanr: DMA channel
+ *      @a: 24bit bus address
+ *
+ *      Load the address register in the DMA controller. This has a 24bit
+ *      limitation (16Mb). 
+ */
+
+static __inline__ void mca_set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+        outb(MCA_DMA_FN_SET_ADDR | dmanr, MCA_DMA_REG_FN);
+        outb(a & 0xff, MCA_DMA_REG_EXE);
+        outb((a >> 8) & 0xff, MCA_DMA_REG_EXE);
+        outb((a >> 16) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ *      mca_get_dma_addr -      load a 24bit DMA address
+ *      @dmanr: DMA channel
+ *
+ *      Read the address register in the DMA controller. This has a 24bit
+ *      limitation (16Mb). The return is a bus address.
+ */
+
+static __inline__ unsigned int mca_get_dma_addr(unsigned int dmanr)
+{
+        unsigned int addr;
+
+        outb(MCA_DMA_FN_GET_ADDR | dmanr, MCA_DMA_REG_FN);
+        addr = inb(MCA_DMA_REG_EXE);
+        addr |= inb(MCA_DMA_REG_EXE) << 8;
+        addr |= inb(MCA_DMA_REG_EXE) << 16;  
+
+        return addr;
+}
+
+/**
+ *      mca_set_dma_count -     load a 16bit transfer count
+ *      @dmanr: DMA channel
+ *      @count: count
+ *
+ *      Set the DMA count for this channel. This can be up to 64Kbytes.
+ *      Setting a count of zero will not do what you expect.
+ */
+
+static __inline__ void mca_set_dma_count(unsigned int dmanr, unsigned int count)
+{
+        count--;  /* transfers one more than count -- correct for this */
+
+        outb(MCA_DMA_FN_SET_COUNT | dmanr, MCA_DMA_REG_FN);
+        outb(count & 0xff, MCA_DMA_REG_EXE);
+        outb((count >> 8) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ *      mca_get_dma_residue -   get the remaining bytes to transfer
+ *      @dmanr: DMA channel
+ *
+ *      This function returns the number of bytes left to transfer
+ *      on this DMA channel.
+ */
+
+static __inline__ unsigned int mca_get_dma_residue(unsigned int dmanr)
+{
+        unsigned short count;
+
+        outb(MCA_DMA_FN_GET_COUNT | dmanr, MCA_DMA_REG_FN);
+        count = 1 + inb(MCA_DMA_REG_EXE);
+        count += inb(MCA_DMA_REG_EXE) << 8;
+
+        return count;
+}
+
+/**
+ *      mca_set_dma_io -        set the port for an I/O transfer
+ *      @dmanr: DMA channel
+ *      @io_addr: an I/O port number
+ *
+ *      Unlike the ISA bus DMA controllers the DMA on MCA bus can transfer
+ *      with an I/O port target.
+ */
+
+static __inline__ void mca_set_dma_io(unsigned int dmanr, unsigned int io_addr)
+{
+        /*
+         * DMA from a port address -- set the io address
+         */
+        
+        outb(MCA_DMA_FN_SET_IO | dmanr, MCA_DMA_REG_FN);
+        outb(io_addr & 0xff, MCA_DMA_REG_EXE);
+        outb((io_addr >>  8) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ *      mca_set_dma_mode -      set the DMA mode
+ *      @dmanr: DMA channel
+ *      @mode: mode to set
+ *
+ *      The DMA controller supports several modes. The mode values you can
+ *      set are-
+ *
+ *      %MCA_DMA_MODE_READ when reading from the DMA device.
+ *
+ *      %MCA_DMA_MODE_WRITE to writing to the DMA device.
+ *
+ *      %MCA_DMA_MODE_IO to do DMA to or from an I/O port.
+ *
+ *      %MCA_DMA_MODE_16 to do 16bit transfers.
+ */
+
+static __inline__ void mca_set_dma_mode(unsigned int dmanr, unsigned int mode)
+{
+        outb(MCA_DMA_FN_SET_MODE | dmanr, MCA_DMA_REG_FN);
+        outb(mode, MCA_DMA_REG_EXE);
+}
+
+#endif /* MCA_DMA_H */
diff --git a/include/asm-x86/mce.h b/include/asm-x86/mce.h
new file mode 100644
index 000000000000..cc8ca389912e
--- /dev/null
+++ b/include/asm-x86/mce.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mce_32.h"
+#else
+# include "mce_64.h"
+#endif
diff --git a/include/asm-x86/mce_32.h b/include/asm-x86/mce_32.h
new file mode 100644
index 000000000000..d56d89742e8f
--- /dev/null
+++ b/include/asm-x86/mce_32.h
@@ -0,0 +1,11 @@
+#ifdef CONFIG_X86_MCE
+extern void mcheck_init(struct cpuinfo_x86 *c);
+#else
+#define mcheck_init(c) do {} while(0)
+#endif
+
+extern int mce_disabled;
+
+extern void stop_mce(void);
+extern void restart_mce(void);
+
diff --git a/include/asm-x86/mce_64.h b/include/asm-x86/mce_64.h
new file mode 100644
index 000000000000..7bc030a1996d
--- /dev/null
+++ b/include/asm-x86/mce_64.h
@@ -0,0 +1,115 @@
+#ifndef _ASM_MCE_H
+#define _ASM_MCE_H 1
+
+#include <asm/ioctls.h>
+#include <asm/types.h>
+
+/* 
+ * Machine Check support for x86
+ */
+
+#define MCG_CTL_P        (1UL<<8)   /* MCG_CAP register available */
+
+#define MCG_STATUS_RIPV  (1UL<<0)   /* restart ip valid */
+#define MCG_STATUS_EIPV  (1UL<<1)   /* eip points to correct instruction */
+#define MCG_STATUS_MCIP  (1UL<<2)   /* machine check in progress */
+
+#define MCI_STATUS_VAL   (1UL<<63)  /* valid error */
+#define MCI_STATUS_OVER  (1UL<<62)  /* previous errors lost */
+#define MCI_STATUS_UC    (1UL<<61)  /* uncorrected error */
+#define MCI_STATUS_EN    (1UL<<60)  /* error enabled */
+#define MCI_STATUS_MISCV (1UL<<59)  /* misc error reg. valid */
+#define MCI_STATUS_ADDRV (1UL<<58)  /* addr reg. valid */
+#define MCI_STATUS_PCC   (1UL<<57)  /* processor context corrupt */
+
+/* Fields are zero when not available */
+struct mce {
+        __u64 status;
+        __u64 misc;
+        __u64 addr;
+        __u64 mcgstatus;
+        __u64 rip;      
+        __u64 tsc;      /* cpu time stamp counter */
+        __u64 res1;     /* for future extension */      
+        __u64 res2;     /* dito. */
+        __u8  cs;               /* code segment */
+        __u8  bank;     /* machine check bank */
+        __u8  cpu;      /* cpu that raised the error */
+        __u8  finished;   /* entry is valid */
+        __u32 pad;   
+};
+
+/* 
+ * This structure contains all data related to the MCE log.
+ * Also carries a signature to make it easier to find from external debugging tools.
+ * Each entry is only valid when its finished flag is set.
+ */
+
+#define MCE_LOG_LEN 32
+
+struct mce_log { 
+        char signature[12]; /* "MACHINECHECK" */ 
+        unsigned len;       /* = MCE_LOG_LEN */ 
+        unsigned next;
+        unsigned flags;
+        unsigned pad0; 
+        struct mce entry[MCE_LOG_LEN];
+};
+
+#define MCE_OVERFLOW 0          /* bit 0 in flags means overflow */
+
+#define MCE_LOG_SIGNATURE       "MACHINECHECK"
+
+#define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
+#define MCE_GET_LOG_LEN      _IOR('M', 2, int)
+#define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
+
+/* Software defined banks */
+#define MCE_EXTENDED_BANK       128
+#define MCE_THERMAL_BANK        MCE_EXTENDED_BANK + 0
+
+#define K8_MCE_THRESHOLD_BASE      (MCE_EXTENDED_BANK + 1)      /* MCE_AMD */
+#define K8_MCE_THRESHOLD_BANK_0    (MCE_THRESHOLD_BASE + 0 * 9)
+#define K8_MCE_THRESHOLD_BANK_1    (MCE_THRESHOLD_BASE + 1 * 9)
+#define K8_MCE_THRESHOLD_BANK_2    (MCE_THRESHOLD_BASE + 2 * 9)
+#define K8_MCE_THRESHOLD_BANK_3    (MCE_THRESHOLD_BASE + 3 * 9)
+#define K8_MCE_THRESHOLD_BANK_4    (MCE_THRESHOLD_BASE + 4 * 9)
+#define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
+#define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
+
+#ifdef __KERNEL__
+#include <asm/atomic.h>
+
+void mce_log(struct mce *m);
+DECLARE_PER_CPU(struct sys_device, device_mce);
+
+#ifdef CONFIG_X86_MCE_INTEL
+void mce_intel_feature_init(struct cpuinfo_x86 *c);
+#else
+static inline void mce_intel_feature_init(struct cpuinfo_x86 *c)
+{
+}
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+void mce_amd_feature_init(struct cpuinfo_x86 *c);
+#else
+static inline void mce_amd_feature_init(struct cpuinfo_x86 *c)
+{
+}
+#endif
+
+void mce_log_therm_throt_event(unsigned int cpu, __u64 status);
+
+extern atomic_t mce_entry;
+
+extern void do_machine_check(struct pt_regs *, long);
+
+extern int mce_notify_user(void);
+
+extern void stop_mce(void);
+extern void restart_mce(void);
+
+#endif
+
+#endif
diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h
new file mode 100644
index 000000000000..322db07e82c3
--- /dev/null
+++ b/include/asm-x86/mman.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "mman_32.h"
+# else
+#  include "mman_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "mman_32.h"
+# else
+#  include "mman_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/mman_32.h b/include/asm-x86/mman_32.h
new file mode 100644
index 000000000000..8fd9d7ab7faf
--- /dev/null
+++ b/include/asm-x86/mman_32.h
@@ -0,0 +1,17 @@
+#ifndef __I386_MMAN_H__
+#define __I386_MMAN_H__
+
+#include <asm-generic/mman.h>
+
+#define MAP_GROWSDOWN   0x0100          /* stack-like segment */
+#define MAP_DENYWRITE   0x0800          /* ETXTBSY */
+#define MAP_EXECUTABLE  0x1000          /* mark it as an executable */
+#define MAP_LOCKED      0x2000          /* pages are locked */
+#define MAP_NORESERVE   0x4000          /* don't check for reservations */
+#define MAP_POPULATE    0x8000          /* populate (prefault) pagetables */
+#define MAP_NONBLOCK    0x10000         /* do not block on IO */
+
+#define MCL_CURRENT     1               /* lock all current mappings */
+#define MCL_FUTURE      2               /* lock all future mappings */
+
+#endif /* __I386_MMAN_H__ */
diff --git a/include/asm-x86/mman_64.h b/include/asm-x86/mman_64.h
new file mode 100644
index 000000000000..dd5cb0534d37
--- /dev/null
+++ b/include/asm-x86/mman_64.h
@@ -0,0 +1,19 @@
+#ifndef __X8664_MMAN_H__
+#define __X8664_MMAN_H__
+
+#include <asm-generic/mman.h>
+
+#define MAP_32BIT       0x40            /* only give out 32bit addresses */
+
+#define MAP_GROWSDOWN   0x0100          /* stack-like segment */
+#define MAP_DENYWRITE   0x0800          /* ETXTBSY */
+#define MAP_EXECUTABLE  0x1000          /* mark it as an executable */
+#define MAP_LOCKED      0x2000          /* pages are locked */
+#define MAP_NORESERVE   0x4000          /* don't check for reservations */
+#define MAP_POPULATE    0x8000          /* populate (prefault) pagetables */
+#define MAP_NONBLOCK    0x10000         /* do not block on IO */
+
+#define MCL_CURRENT     1               /* lock all current mappings */
+#define MCL_FUTURE      2               /* lock all future mappings */
+
+#endif
diff --git a/include/asm-x86/mmsegment.h b/include/asm-x86/mmsegment.h
new file mode 100644
index 000000000000..d3f80c996330
--- /dev/null
+++ b/include/asm-x86/mmsegment.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_MMSEGMENT_H
+#define _ASM_MMSEGMENT_H 1
+
+typedef struct {
+        unsigned long seg;
+} mm_segment_t;
+
+#endif
diff --git a/include/asm-x86/mmu.h b/include/asm-x86/mmu.h
new file mode 100644
index 000000000000..9c628cd70e23
--- /dev/null
+++ b/include/asm-x86/mmu.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mmu_32.h"
+#else
+# include "mmu_64.h"
+#endif
diff --git a/include/asm-x86/mmu_32.h b/include/asm-x86/mmu_32.h
new file mode 100644
index 000000000000..8358dd3df7aa
--- /dev/null
+++ b/include/asm-x86/mmu_32.h
@@ -0,0 +1,18 @@
+#ifndef __i386_MMU_H
+#define __i386_MMU_H
+
+#include <asm/semaphore.h>
+/*
+ * The i386 doesn't have a mmu context, but
+ * we put the segment information here.
+ *
+ * cpu_vm_mask is used to optimize ldt flushing.
+ */
+typedef struct { 
+        int size;
+        struct semaphore sem;
+        void *ldt;
+        void *vdso;
+} mm_context_t;
+
+#endif
diff --git a/include/asm-x86/mmu_64.h b/include/asm-x86/mmu_64.h
new file mode 100644
index 000000000000..d2cd4a9d984d
--- /dev/null
+++ b/include/asm-x86/mmu_64.h
@@ -0,0 +1,21 @@
+#ifndef __x86_64_MMU_H
+#define __x86_64_MMU_H
+
+#include <linux/spinlock.h>
+#include <asm/semaphore.h>
+
+/*
+ * The x86_64 doesn't have a mmu context, but
+ * we put the segment information here.
+ *
+ * cpu_vm_mask is used to optimize ldt flushing.
+ */
+typedef struct { 
+        void *ldt;
+        rwlock_t ldtlock; 
+        int size;
+        struct semaphore sem; 
+        void *vdso;
+} mm_context_t;
+
+#endif
diff --git a/include/asm-x86/mmu_context.h b/include/asm-x86/mmu_context.h
new file mode 100644
index 000000000000..6598450da6c6
--- /dev/null
+++ b/include/asm-x86/mmu_context.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mmu_context_32.h"
+#else
+# include "mmu_context_64.h"
+#endif
diff --git a/include/asm-x86/mmu_context_32.h b/include/asm-x86/mmu_context_32.h
new file mode 100644
index 000000000000..7eb0b0b1fb3c
--- /dev/null
+++ b/include/asm-x86/mmu_context_32.h
@@ -0,0 +1,86 @@
+#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
+        unsigned cpu = smp_processor_id();
+        if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
+                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY;
+#endif
+}
+
+void leave_mm(unsigned long cpu);
+
+static inline void switch_mm(struct mm_struct *prev,
+                             struct mm_struct *next,
+                             struct task_struct *tsk)
+{
+        int cpu = smp_processor_id();
+
+        if (likely(prev != next)) {
+                /* stop flush ipis for the previous mm */
+                cpu_clear(cpu, prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
+                per_cpu(cpu_tlbstate, cpu).active_mm = next;
+#endif
+                cpu_set(cpu, next->cpu_vm_mask);
+
+                /* Re-load page tables */
+                load_cr3(next->pgd);
+
+                /*
+                 * load the LDT, if the LDT is different:
+                 */
+                if (unlikely(prev->context.ldt != next->context.ldt))
+                        load_LDT_nolock(&next->context);
+        }
+#ifdef CONFIG_SMP
+        else {
+                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
+                BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next);
+
+                if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+                        /* We were in lazy tlb mode and leave_mm disabled 
+                         * tlb flush IPI delivery. We must reload %cr3.
+                         */
+                        load_cr3(next->pgd);
+                        load_LDT_nolock(&next->context);
+                }
+        }
+#endif
+}
+
+#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
new file mode 100644
index 000000000000..0cce83a78378
--- /dev/null
+++ b/include/asm-x86/mmu_context_64.h
@@ -0,0 +1,74 @@
+#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>
+#include <asm-generic/mm_hooks.h>
+
+/*
+ * 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)
+{
+#ifdef CONFIG_SMP
+        if (read_pda(mmu_state) == TLBSTATE_OK) 
+                write_pda(mmu_state, TLBSTATE_LAZY);
+#endif
+}
+
+static inline void load_cr3(pgd_t *pgd)
+{
+        asm volatile("movq %0,%%cr3" :: "r" (__pa(pgd)) : "memory");
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, 
+                             struct task_struct *tsk)
+{
+        unsigned cpu = smp_processor_id();
+        if (likely(prev != next)) {
+                /* stop flush ipis for the previous mm */
+                cpu_clear(cpu, prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+                write_pda(mmu_state, TLBSTATE_OK);
+                write_pda(active_mm, next);
+#endif
+                cpu_set(cpu, next->cpu_vm_mask);
+                load_cr3(next->pgd);
+
+                if (unlikely(next->context.ldt != prev->context.ldt)) 
+                        load_LDT_nolock(&next->context, cpu);
+        }
+#ifdef CONFIG_SMP
+        else {
+                write_pda(mmu_state, TLBSTATE_OK);
+                if (read_pda(active_mm) != next)
+                        out_of_line_bug();
+                if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+                        /* We were in lazy tlb mode and leave_mm disabled 
+                         * tlb flush IPI delivery. We must reload CR3
+                         * to make sure to use no freed page tables.
+                         */
+                        load_cr3(next->pgd);
+                        load_LDT_nolock(&next->context, cpu);
+                }
+        }
+#endif
+}
+
+#define deactivate_mm(tsk,mm)   do { \
+        load_gs_index(0); \
+        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/mmx.h b/include/asm-x86/mmx.h
new file mode 100644
index 000000000000..46b71da99869
--- /dev/null
+++ b/include/asm-x86/mmx.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_MMX_H
+#define _ASM_MMX_H
+
+/*
+ *      MMX 3Dnow! helper operations
+ */
+
+#include <linux/types.h>
+ 
+extern void *_mmx_memcpy(void *to, const void *from, size_t size);
+extern void mmx_clear_page(void *page);
+extern void mmx_copy_page(void *to, void *from);
+
+#endif
diff --git a/include/asm-x86/mmzone.h b/include/asm-x86/mmzone.h
new file mode 100644
index 000000000000..64217ea16a36
--- /dev/null
+++ b/include/asm-x86/mmzone.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mmzone_32.h"
+#else
+# include "mmzone_64.h"
+#endif
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
new file mode 100644
index 000000000000..118e9812778f
--- /dev/null
+++ b/include/asm-x86/mmzone_32.h
@@ -0,0 +1,145 @@
+/*
+ * Written by Pat Gaughen (gone@us.ibm.com) Mar 2002
+ *
+ */
+
+#ifndef _ASM_MMZONE_H_
+#define _ASM_MMZONE_H_
+
+#include <asm/smp.h>
+
+#ifdef CONFIG_NUMA
+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
+
+extern int get_memcfg_numa_flat(void );
+/*
+ * This allows any one NUMA architecture to be compiled
+ * for, and still fall back to the flat function if it
+ * fails.
+ */
+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
+
+/*
+ * generic node memory support, the following assumptions apply:
+ *
+ * 1) memory comes in 256Mb 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 PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
+
+extern s8 physnode_map[];
+
+static inline int pfn_to_nid(unsigned long pfn)
+{
+#ifdef CONFIG_NUMA
+        return((int) physnode_map[(pfn) / PAGES_PER_ELEMENT]);
+#else
+        return 0;
+#endif
+}
+
+/*
+ * Following are macros that each numa implmentation must define.
+ */
+
+#define node_start_pfn(nid)     (NODE_DATA(nid)->node_start_pfn)
+#define node_end_pfn(nid)                                               \
+({                                                                      \
+        pg_data_t *__pgdat = NODE_DATA(nid);                            \
+        __pgdat->node_start_pfn + __pgdat->node_spanned_pages;          \
+})
+
+/* XXX: FIXME -- wli */
+#define kern_addr_valid(kaddr)  (0)
+
+#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);
+
+        if (nid >= 0)
+                return (pfn < node_end_pfn(nid));
+        return 0;
+}
+#endif /* CONFIG_X86_NUMAQ */
+
+#endif /* CONFIG_DISCONTIGMEM */
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+
+/*
+ * Following are macros that are specific to this numa platform.
+ */
+#define reserve_bootmem(addr, size) \
+        reserve_bootmem_node(NODE_DATA(0), (addr), (size))
+#define alloc_bootmem(x) \
+        __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_low(x) \
+        __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
+#define alloc_bootmem_pages(x) \
+        __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_low_pages(x) \
+        __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
+#define alloc_bootmem_node(pgdat, x)                                    \
+({                                                                      \
+        struct pglist_data  __maybe_unused                      \
+                                *__alloc_bootmem_node__pgdat = (pgdat); \
+        __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES,        \
+                                                __pa(MAX_DMA_ADDRESS)); \
+})
+#define alloc_bootmem_pages_node(pgdat, x)                              \
+({                                                                      \
+        struct pglist_data  __maybe_unused                      \
+                                *__alloc_bootmem_node__pgdat = (pgdat); \
+        __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE,              \
+                                                __pa(MAX_DMA_ADDRESS))  \
+})
+#define alloc_bootmem_low_pages_node(pgdat, x)                          \
+({                                                                      \
+        struct pglist_data  __maybe_unused                      \
+                                *__alloc_bootmem_node__pgdat = (pgdat); \
+        __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0);          \
+})
+#endif /* CONFIG_NEED_MULTIPLE_NODES */
+
+#endif /* _ASM_MMZONE_H_ */
diff --git a/include/asm-x86/mmzone_64.h b/include/asm-x86/mmzone_64.h
new file mode 100644
index 000000000000..19a89377b123
--- /dev/null
+++ b/include/asm-x86/mmzone_64.h
@@ -0,0 +1,56 @@
+/* K8 NUMA support */
+/* Copyright 2002,2003 by Andi Kleen, SuSE Labs */
+/* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */
+#ifndef _ASM_X86_64_MMZONE_H
+#define _ASM_X86_64_MMZONE_H 1
+
+
+#ifdef CONFIG_NUMA
+
+#define VIRTUAL_BUG_ON(x) 
+
+#include <asm/smp.h>
+
+/* Simple perfect hash to map physical addresses to node numbers */
+struct memnode {
+        int shift;
+        unsigned int mapsize;
+        u8 *map;
+        u8 embedded_map[64-16];
+} ____cacheline_aligned; /* total size = 64 bytes */
+extern struct memnode memnode;
+#define memnode_shift memnode.shift
+#define memnodemap memnode.map
+#define memnodemapsize memnode.mapsize
+
+extern struct pglist_data *node_data[];
+
+static inline __attribute__((pure)) int phys_to_nid(unsigned long addr) 
+{ 
+        unsigned nid; 
+        VIRTUAL_BUG_ON(!memnodemap);
+        VIRTUAL_BUG_ON((addr >> memnode_shift) >= memnodemapsize);
+        nid = memnodemap[addr >> memnode_shift]; 
+        VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]); 
+        return nid; 
+} 
+
+#define NODE_DATA(nid)          (node_data[nid])
+
+#define node_start_pfn(nid)     (NODE_DATA(nid)->node_start_pfn)
+#define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn + \
+                                 NODE_DATA(nid)->node_spanned_pages)
+
+#ifdef CONFIG_DISCONTIGMEM
+#define pfn_to_nid(pfn) phys_to_nid((unsigned long)(pfn) << PAGE_SHIFT)
+
+extern int pfn_valid(unsigned long pfn);
+#endif
+
+#ifdef CONFIG_NUMA_EMU
+#define FAKE_NODE_MIN_SIZE      (64*1024*1024)
+#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1uL))
+#endif
+
+#endif
+#endif
diff --git a/include/asm-x86/module.h b/include/asm-x86/module.h
new file mode 100644
index 000000000000..2b2f18d8a531
--- /dev/null
+++ b/include/asm-x86/module.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "module_32.h"
+#else
+# include "module_64.h"
+#endif
diff --git a/include/asm-x86/module_32.h b/include/asm-x86/module_32.h
new file mode 100644
index 000000000000..7e5fda6c3976
--- /dev/null
+++ b/include/asm-x86/module_32.h
@@ -0,0 +1,75 @@
+#ifndef _ASM_I386_MODULE_H
+#define _ASM_I386_MODULE_H
+
+/* x86 is simple */
+struct mod_arch_specific
+{
+};
+
+#define Elf_Shdr Elf32_Shdr
+#define Elf_Sym Elf32_Sym
+#define Elf_Ehdr Elf32_Ehdr
+
+#ifdef CONFIG_M386
+#define MODULE_PROC_FAMILY "386 "
+#elif defined CONFIG_M486
+#define MODULE_PROC_FAMILY "486 "
+#elif defined CONFIG_M586
+#define MODULE_PROC_FAMILY "586 "
+#elif defined CONFIG_M586TSC
+#define MODULE_PROC_FAMILY "586TSC "
+#elif defined CONFIG_M586MMX
+#define MODULE_PROC_FAMILY "586MMX "
+#elif defined CONFIG_MCORE2
+#define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_M686
+#define MODULE_PROC_FAMILY "686 "
+#elif defined CONFIG_MPENTIUMII
+#define MODULE_PROC_FAMILY "PENTIUMII "
+#elif defined CONFIG_MPENTIUMIII
+#define MODULE_PROC_FAMILY "PENTIUMIII "
+#elif defined CONFIG_MPENTIUMM
+#define MODULE_PROC_FAMILY "PENTIUMM "
+#elif defined CONFIG_MPENTIUM4
+#define MODULE_PROC_FAMILY "PENTIUM4 "
+#elif defined CONFIG_MK6
+#define MODULE_PROC_FAMILY "K6 "
+#elif defined CONFIG_MK7
+#define MODULE_PROC_FAMILY "K7 "
+#elif defined CONFIG_MK8
+#define MODULE_PROC_FAMILY "K8 "
+#elif defined CONFIG_X86_ELAN
+#define MODULE_PROC_FAMILY "ELAN "
+#elif defined CONFIG_MCRUSOE
+#define MODULE_PROC_FAMILY "CRUSOE "
+#elif defined CONFIG_MEFFICEON
+#define MODULE_PROC_FAMILY "EFFICEON "
+#elif defined CONFIG_MWINCHIPC6
+#define MODULE_PROC_FAMILY "WINCHIPC6 "
+#elif defined CONFIG_MWINCHIP2
+#define MODULE_PROC_FAMILY "WINCHIP2 "
+#elif defined CONFIG_MWINCHIP3D
+#define MODULE_PROC_FAMILY "WINCHIP3D "
+#elif defined CONFIG_MCYRIXIII
+#define MODULE_PROC_FAMILY "CYRIXIII "
+#elif defined CONFIG_MVIAC3_2
+#define MODULE_PROC_FAMILY "VIAC3-2 "
+#elif defined CONFIG_MVIAC7
+#define MODULE_PROC_FAMILY "VIAC7 "
+#elif defined CONFIG_MGEODEGX1
+#define MODULE_PROC_FAMILY "GEODEGX1 "
+#elif defined CONFIG_MGEODE_LX
+#define MODULE_PROC_FAMILY "GEODE "
+#else
+#error unknown processor family
+#endif
+
+#ifdef CONFIG_4KSTACKS
+#define MODULE_STACKSIZE "4KSTACKS "
+#else
+#define MODULE_STACKSIZE ""
+#endif
+
+#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
+
+#endif /* _ASM_I386_MODULE_H */
diff --git a/include/asm-x86/module_64.h b/include/asm-x86/module_64.h
new file mode 100644
index 000000000000..67f8f69fa7b1
--- /dev/null
+++ b/include/asm-x86/module_64.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_X8664_MODULE_H
+#define _ASM_X8664_MODULE_H
+
+struct mod_arch_specific {}; 
+
+#define Elf_Shdr Elf64_Shdr
+#define Elf_Sym Elf64_Sym
+#define Elf_Ehdr Elf64_Ehdr
+
+#endif 
diff --git a/include/asm-x86/mpspec.h b/include/asm-x86/mpspec.h
new file mode 100644
index 000000000000..8f268e8fd2e9
--- /dev/null
+++ b/include/asm-x86/mpspec.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mpspec_32.h"
+#else
+# include "mpspec_64.h"
+#endif
diff --git a/include/asm-x86/mpspec_32.h b/include/asm-x86/mpspec_32.h
new file mode 100644
index 000000000000..f21349399d14
--- /dev/null
+++ b/include/asm-x86/mpspec_32.h
@@ -0,0 +1,81 @@
+#ifndef __ASM_MPSPEC_H
+#define __ASM_MPSPEC_H
+
+#include <linux/cpumask.h>
+#include <asm/mpspec_def.h>
+#include <mach_mpspec.h>
+
+extern int mp_bus_id_to_type [MAX_MP_BUSSES];
+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];
+extern int mp_bus_id_to_pci_bus [MAX_MP_BUSSES];
+
+extern unsigned int def_to_bigsmp;
+extern unsigned int boot_cpu_physical_apicid;
+extern int smp_found_config;
+extern void find_smp_config (void);
+extern void get_smp_config (void);
+extern int nr_ioapics;
+extern int apic_version [MAX_APICS];
+extern int mp_irq_entries;
+extern struct mpc_config_intsrc mp_irqs [MAX_IRQ_SOURCES];
+extern int mpc_default_type;
+extern unsigned long mp_lapic_addr;
+extern int pic_mode;
+
+#ifdef CONFIG_ACPI
+extern void mp_register_lapic (u8 id, u8 enabled);
+extern void mp_register_lapic_address (u64 address);
+extern void mp_register_ioapic (u8 id, u32 address, u32 gsi_base);
+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);
+#endif /* CONFIG_ACPI */
+
+#define PHYSID_ARRAY_SIZE       BITS_TO_LONGS(MAX_APICS)
+
+struct physid_mask
+{
+        unsigned long mask[PHYSID_ARRAY_SIZE];
+};
+
+typedef struct physid_mask physid_mask_t;
+
+#define physid_set(physid, map)                 set_bit(physid, (map).mask)
+#define physid_clear(physid, map)               clear_bit(physid, (map).mask)
+#define physid_isset(physid, map)               test_bit(physid, (map).mask)
+#define physid_test_and_set(physid, map)        test_and_set_bit(physid, (map).mask)
+
+#define physids_and(dst, src1, src2)            bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+#define physids_or(dst, src1, src2)             bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+#define physids_clear(map)                      bitmap_zero((map).mask, MAX_APICS)
+#define physids_complement(dst, src)            bitmap_complement((dst).mask,(src).mask, MAX_APICS)
+#define physids_empty(map)                      bitmap_empty((map).mask, MAX_APICS)
+#define physids_equal(map1, map2)               bitmap_equal((map1).mask, (map2).mask, MAX_APICS)
+#define physids_weight(map)                     bitmap_weight((map).mask, MAX_APICS)
+#define physids_shift_right(d, s, n)            bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS)
+#define physids_shift_left(d, s, n)             bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS)
+#define physids_coerce(map)                     ((map).mask[0])
+
+#define physids_promote(physids)                                                \
+        ({                                                                      \
+                physid_mask_t __physid_mask = PHYSID_MASK_NONE;                 \
+                __physid_mask.mask[0] = physids;                                \
+                __physid_mask;                                                  \
+        })
+
+#define physid_mask_of_physid(physid)                                           \
+        ({                                                                      \
+                physid_mask_t __physid_mask = PHYSID_MASK_NONE;                 \
+                physid_set(physid, __physid_mask);                              \
+                __physid_mask;                                                  \
+        })
+
+#define PHYSID_MASK_ALL         { {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} }
+#define PHYSID_MASK_NONE        { {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} }
+
+extern physid_mask_t phys_cpu_present_map;
+
+#endif
+
diff --git a/include/asm-x86/mpspec_64.h b/include/asm-x86/mpspec_64.h
new file mode 100644
index 000000000000..017fddb61dc5
--- /dev/null
+++ b/include/asm-x86/mpspec_64.h
@@ -0,0 +1,233 @@
+#ifndef __ASM_MPSPEC_H
+#define __ASM_MPSPEC_H
+
+/*
+ * Structure definitions for SMP machines following the
+ * Intel Multiprocessing Specification 1.1 and 1.4.
+ */
+
+/*
+ * This tag identifies where the SMP configuration
+ * information is. 
+ */
+ 
+#define SMP_MAGIC_IDENT (('_'<<24)|('P'<<16)|('M'<<8)|'_')
+
+/*
+ * A maximum of 255 APICs with the current APIC ID architecture.
+ */
+#define MAX_APICS 255
+
+struct intel_mp_floating
+{
+        char mpf_signature[4];          /* "_MP_"                       */
+        unsigned int mpf_physptr;       /* Configuration table address  */
+        unsigned char mpf_length;       /* Our length (paragraphs)      */
+        unsigned char mpf_specification;/* Specification version        */
+        unsigned char mpf_checksum;     /* Checksum (makes sum 0)       */
+        unsigned char mpf_feature1;     /* Standard or configuration ?  */
+        unsigned char mpf_feature2;     /* Bit7 set for IMCR|PIC        */
+        unsigned char mpf_feature3;     /* Unused (0)                   */
+        unsigned char mpf_feature4;     /* Unused (0)                   */
+        unsigned char mpf_feature5;     /* Unused (0)                   */
+};
+
+struct mp_config_table
+{
+        char mpc_signature[4];
+#define MPC_SIGNATURE "PCMP"
+        unsigned short mpc_length;      /* Size of table */
+        char  mpc_spec;                 /* 0x01 */
+        char  mpc_checksum;
+        char  mpc_oem[8];
+        char  mpc_productid[12];
+        unsigned int mpc_oemptr;        /* 0 if not present */
+        unsigned short mpc_oemsize;     /* 0 if not present */
+        unsigned short mpc_oemcount;
+        unsigned int mpc_lapic; /* APIC address */
+        unsigned int reserved;
+};
+
+/* Followed by entries */
+
+#define MP_PROCESSOR    0
+#define MP_BUS          1
+#define MP_IOAPIC       2
+#define MP_INTSRC       3
+#define MP_LINTSRC      4
+
+struct mpc_config_processor
+{
+        unsigned char mpc_type;
+        unsigned char mpc_apicid;       /* Local APIC number */
+        unsigned char mpc_apicver;      /* Its versions */
+        unsigned char mpc_cpuflag;
+#define CPU_ENABLED             1       /* Processor is available */
+#define CPU_BOOTPROCESSOR       2       /* Processor is the BP */
+        unsigned int mpc_cpufeature;            
+#define CPU_STEPPING_MASK 0x0F
+#define CPU_MODEL_MASK  0xF0
+#define CPU_FAMILY_MASK 0xF00
+        unsigned int mpc_featureflag;   /* CPUID feature value */
+        unsigned int mpc_reserved[2];
+};
+
+struct mpc_config_bus
+{
+        unsigned char mpc_type;
+        unsigned char mpc_busid;
+        unsigned char mpc_bustype[6];
+};
+
+/* List of Bus Type string values, Intel MP Spec. */
+#define BUSTYPE_EISA    "EISA"
+#define BUSTYPE_ISA     "ISA"
+#define BUSTYPE_INTERN  "INTERN"        /* Internal BUS */
+#define BUSTYPE_MCA     "MCA"
+#define BUSTYPE_VL      "VL"            /* Local bus */
+#define BUSTYPE_PCI     "PCI"
+#define BUSTYPE_PCMCIA  "PCMCIA"
+#define BUSTYPE_CBUS    "CBUS"
+#define BUSTYPE_CBUSII  "CBUSII"
+#define BUSTYPE_FUTURE  "FUTURE"
+#define BUSTYPE_MBI     "MBI"
+#define BUSTYPE_MBII    "MBII"
+#define BUSTYPE_MPI     "MPI"
+#define BUSTYPE_MPSA    "MPSA"
+#define BUSTYPE_NUBUS   "NUBUS"
+#define BUSTYPE_TC      "TC"
+#define BUSTYPE_VME     "VME"
+#define BUSTYPE_XPRESS  "XPRESS"
+
+struct mpc_config_ioapic
+{
+        unsigned char mpc_type;
+        unsigned char mpc_apicid;
+        unsigned char mpc_apicver;
+        unsigned char mpc_flags;
+#define MPC_APIC_USABLE         0x01
+        unsigned int mpc_apicaddr;
+};
+
+struct mpc_config_intsrc
+{
+        unsigned char mpc_type;
+        unsigned char mpc_irqtype;
+        unsigned short mpc_irqflag;
+        unsigned char mpc_srcbus;
+        unsigned char mpc_srcbusirq;
+        unsigned char mpc_dstapic;
+        unsigned char mpc_dstirq;
+};
+
+enum mp_irq_source_types {
+        mp_INT = 0,
+        mp_NMI = 1,
+        mp_SMI = 2,
+        mp_ExtINT = 3
+};
+
+#define MP_IRQDIR_DEFAULT       0
+#define MP_IRQDIR_HIGH          1
+#define MP_IRQDIR_LOW           3
+
+
+struct mpc_config_lintsrc
+{
+        unsigned char mpc_type;
+        unsigned char mpc_irqtype;
+        unsigned short mpc_irqflag;
+        unsigned char mpc_srcbusid;
+        unsigned char mpc_srcbusirq;
+        unsigned char mpc_destapic;     
+#define MP_APIC_ALL     0xFF
+        unsigned char mpc_destapiclint;
+};
+
+/*
+ *      Default configurations
+ *
+ *      1       2 CPU ISA 82489DX
+ *      2       2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining
+ *      3       2 CPU EISA 82489DX
+ *      4       2 CPU MCA 82489DX
+ *      5       2 CPU ISA+PCI
+ *      6       2 CPU EISA+PCI
+ *      7       2 CPU MCA+PCI
+ */
+
+#define MAX_MP_BUSSES 256
+/* 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)
+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 int smp_found_config;
+extern void find_smp_config (void);
+extern void get_smp_config (void);
+extern int nr_ioapics;
+extern unsigned char apic_version [MAX_APICS];
+extern int mp_irq_entries;
+extern struct mpc_config_intsrc mp_irqs [MAX_IRQ_SOURCES];
+extern int mpc_default_type;
+extern unsigned long mp_lapic_addr;
+
+#ifdef CONFIG_ACPI
+extern void mp_register_lapic (u8 id, u8 enabled);
+extern void mp_register_lapic_address (u64 address);
+
+extern void mp_register_ioapic (u8 id, u32 address, u32 gsi_base);
+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 triggering, int polarity);
+#endif
+
+extern int using_apic_timer;
+
+#define PHYSID_ARRAY_SIZE       BITS_TO_LONGS(MAX_APICS)
+
+struct physid_mask
+{
+        unsigned long mask[PHYSID_ARRAY_SIZE];
+};
+
+typedef struct physid_mask physid_mask_t;
+
+#define physid_set(physid, map)                 set_bit(physid, (map).mask)
+#define physid_clear(physid, map)               clear_bit(physid, (map).mask)
+#define physid_isset(physid, map)               test_bit(physid, (map).mask)
+#define physid_test_and_set(physid, map)        test_and_set_bit(physid, (map).mask)
+
+#define physids_and(dst, src1, src2)            bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+#define physids_or(dst, src1, src2)             bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+#define physids_clear(map)                      bitmap_zero((map).mask, MAX_APICS)
+#define physids_complement(dst, src)            bitmap_complement((dst).mask, (src).mask, MAX_APICS)
+#define physids_empty(map)                      bitmap_empty((map).mask, MAX_APICS)
+#define physids_equal(map1, map2)               bitmap_equal((map1).mask, (map2).mask, MAX_APICS)
+#define physids_weight(map)                     bitmap_weight((map).mask, MAX_APICS)
+#define physids_shift_right(d, s, n)            bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS)
+#define physids_shift_left(d, s, n)             bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS)
+#define physids_coerce(map)                     ((map).mask[0])
+
+#define physids_promote(physids)                                                \
+        ({                                                                      \
+                physid_mask_t __physid_mask = PHYSID_MASK_NONE;                 \
+                __physid_mask.mask[0] = physids;                                \
+                __physid_mask;                                                  \
+        })
+
+#define physid_mask_of_physid(physid)                                           \
+        ({                                                                      \
+                physid_mask_t __physid_mask = PHYSID_MASK_NONE;                 \
+                physid_set(physid, __physid_mask);                              \
+                __physid_mask;                                                  \
+        })
+
+#define PHYSID_MASK_ALL         { {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} }
+#define PHYSID_MASK_NONE        { {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} }
+
+extern physid_mask_t phys_cpu_present_map;
+
+#endif
+
diff --git a/include/asm-x86/mpspec_def.h b/include/asm-x86/mpspec_def.h
new file mode 100644
index 000000000000..13bafb16e7af
--- /dev/null
+++ b/include/asm-x86/mpspec_def.h
@@ -0,0 +1,186 @@
+#ifndef __ASM_MPSPEC_DEF_H
+#define __ASM_MPSPEC_DEF_H
+
+/*
+ * Structure definitions for SMP machines following the
+ * Intel Multiprocessing Specification 1.1 and 1.4.
+ */
+
+/*
+ * This tag identifies where the SMP configuration
+ * information is. 
+ */
+ 
+#define SMP_MAGIC_IDENT (('_'<<24)|('P'<<16)|('M'<<8)|'_')
+
+#define MAX_MPC_ENTRY 1024
+#define MAX_APICS      256
+
+struct intel_mp_floating
+{
+        char mpf_signature[4];          /* "_MP_"                       */
+        unsigned long mpf_physptr;      /* Configuration table address  */
+        unsigned char mpf_length;       /* Our length (paragraphs)      */
+        unsigned char mpf_specification;/* Specification version        */
+        unsigned char mpf_checksum;     /* Checksum (makes sum 0)       */
+        unsigned char mpf_feature1;     /* Standard or configuration ?  */
+        unsigned char mpf_feature2;     /* Bit7 set for IMCR|PIC        */
+        unsigned char mpf_feature3;     /* Unused (0)                   */
+        unsigned char mpf_feature4;     /* Unused (0)                   */
+        unsigned char mpf_feature5;     /* Unused (0)                   */
+};
+
+struct mp_config_table
+{
+        char mpc_signature[4];
+#define MPC_SIGNATURE "PCMP"
+        unsigned short mpc_length;      /* Size of table */
+        char  mpc_spec;                 /* 0x01 */
+        char  mpc_checksum;
+        char  mpc_oem[8];
+        char  mpc_productid[12];
+        unsigned long mpc_oemptr;       /* 0 if not present */
+        unsigned short mpc_oemsize;     /* 0 if not present */
+        unsigned short mpc_oemcount;
+        unsigned long mpc_lapic;        /* APIC address */
+        unsigned long reserved;
+};
+
+/* Followed by entries */
+
+#define MP_PROCESSOR    0
+#define MP_BUS          1
+#define MP_IOAPIC       2
+#define MP_INTSRC       3
+#define MP_LINTSRC      4
+#define MP_TRANSLATION  192  /* Used by IBM NUMA-Q to describe node locality */
+
+struct mpc_config_processor
+{
+        unsigned char mpc_type;
+        unsigned char mpc_apicid;       /* Local APIC number */
+        unsigned char mpc_apicver;      /* Its versions */
+        unsigned char mpc_cpuflag;
+#define CPU_ENABLED             1       /* Processor is available */
+#define CPU_BOOTPROCESSOR       2       /* Processor is the BP */
+        unsigned long mpc_cpufeature;           
+#define CPU_STEPPING_MASK 0x0F
+#define CPU_MODEL_MASK  0xF0
+#define CPU_FAMILY_MASK 0xF00
+        unsigned long mpc_featureflag;  /* CPUID feature value */
+        unsigned long mpc_reserved[2];
+};
+
+struct mpc_config_bus
+{
+        unsigned char mpc_type;
+        unsigned char mpc_busid;
+        unsigned char mpc_bustype[6];
+};
+
+/* List of Bus Type string values, Intel MP Spec. */
+#define BUSTYPE_EISA    "EISA"
+#define BUSTYPE_ISA     "ISA"
+#define BUSTYPE_INTERN  "INTERN"        /* Internal BUS */
+#define BUSTYPE_MCA     "MCA"
+#define BUSTYPE_VL      "VL"            /* Local bus */
+#define BUSTYPE_PCI     "PCI"
+#define BUSTYPE_PCMCIA  "PCMCIA"
+#define BUSTYPE_CBUS    "CBUS"
+#define BUSTYPE_CBUSII  "CBUSII"
+#define BUSTYPE_FUTURE  "FUTURE"
+#define BUSTYPE_MBI     "MBI"
+#define BUSTYPE_MBII    "MBII"
+#define BUSTYPE_MPI     "MPI"
+#define BUSTYPE_MPSA    "MPSA"
+#define BUSTYPE_NUBUS   "NUBUS"
+#define BUSTYPE_TC      "TC"
+#define BUSTYPE_VME     "VME"
+#define BUSTYPE_XPRESS  "XPRESS"
+
+struct mpc_config_ioapic
+{
+        unsigned char mpc_type;
+        unsigned char mpc_apicid;
+        unsigned char mpc_apicver;
+        unsigned char mpc_flags;
+#define MPC_APIC_USABLE         0x01
+        unsigned long mpc_apicaddr;
+};
+
+struct mpc_config_intsrc
+{
+        unsigned char mpc_type;
+        unsigned char mpc_irqtype;
+        unsigned short mpc_irqflag;
+        unsigned char mpc_srcbus;
+        unsigned char mpc_srcbusirq;
+        unsigned char mpc_dstapic;
+        unsigned char mpc_dstirq;
+};
+
+enum mp_irq_source_types {
+        mp_INT = 0,
+        mp_NMI = 1,
+        mp_SMI = 2,
+        mp_ExtINT = 3
+};
+
+#define MP_IRQDIR_DEFAULT       0
+#define MP_IRQDIR_HIGH          1
+#define MP_IRQDIR_LOW           3
+
+
+struct mpc_config_lintsrc
+{
+        unsigned char mpc_type;
+        unsigned char mpc_irqtype;
+        unsigned short mpc_irqflag;
+        unsigned char mpc_srcbusid;
+        unsigned char mpc_srcbusirq;
+        unsigned char mpc_destapic;     
+#define MP_APIC_ALL     0xFF
+        unsigned char mpc_destapiclint;
+};
+
+struct mp_config_oemtable
+{
+        char oem_signature[4];
+#define MPC_OEM_SIGNATURE "_OEM"
+        unsigned short oem_length;      /* Size of table */
+        char  oem_rev;                  /* 0x01 */
+        char  oem_checksum;
+        char  mpc_oem[8];
+};
+
+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;
+};
+
+/*
+ *      Default configurations
+ *
+ *      1       2 CPU ISA 82489DX
+ *      2       2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining
+ *      3       2 CPU EISA 82489DX
+ *      4       2 CPU MCA 82489DX
+ *      5       2 CPU ISA+PCI
+ *      6       2 CPU EISA+PCI
+ *      7       2 CPU MCA+PCI
+ */
+
+enum mp_bustype {
+        MP_BUS_ISA = 1,
+        MP_BUS_EISA,
+        MP_BUS_PCI,
+        MP_BUS_MCA,
+};
+#endif
+
diff --git a/include/asm-x86/msgbuf.h b/include/asm-x86/msgbuf.h
new file mode 100644
index 000000000000..154f7d64e862
--- /dev/null
+++ b/include/asm-x86/msgbuf.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "msgbuf_32.h"
+# else
+#  include "msgbuf_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "msgbuf_32.h"
+# else
+#  include "msgbuf_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/msgbuf_32.h b/include/asm-x86/msgbuf_32.h
new file mode 100644
index 000000000000..b8d659c157ae
--- /dev/null
+++ b/include/asm-x86/msgbuf_32.h
@@ -0,0 +1,31 @@
+#ifndef _I386_MSGBUF_H
+#define _I386_MSGBUF_H
+
+/* 
+ * The msqid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct msqid64_ds {
+        struct ipc64_perm msg_perm;
+        __kernel_time_t msg_stime;      /* last msgsnd time */
+        unsigned long   __unused1;
+        __kernel_time_t msg_rtime;      /* last msgrcv time */
+        unsigned long   __unused2;
+        __kernel_time_t msg_ctime;      /* last change time */
+        unsigned long   __unused3;
+        unsigned long  msg_cbytes;      /* current number of bytes on queue */
+        unsigned long  msg_qnum;        /* number of messages in queue */
+        unsigned long  msg_qbytes;      /* max number of bytes on queue */
+        __kernel_pid_t msg_lspid;       /* pid of last msgsnd */
+        __kernel_pid_t msg_lrpid;       /* last receive pid */
+        unsigned long  __unused4;
+        unsigned long  __unused5;
+};
+
+#endif /* _I386_MSGBUF_H */
diff --git a/include/asm-x86/msgbuf_64.h b/include/asm-x86/msgbuf_64.h
new file mode 100644
index 000000000000..cd6f95dd54da
--- /dev/null
+++ b/include/asm-x86/msgbuf_64.h
@@ -0,0 +1,27 @@
+#ifndef _X8664_MSGBUF_H
+#define _X8664_MSGBUF_H
+
+/* 
+ * The msqid64_ds structure for x86-64 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 2 miscellaneous 64-bit values
+ */
+
+struct msqid64_ds {
+        struct ipc64_perm msg_perm;
+        __kernel_time_t msg_stime;      /* last msgsnd time */
+        __kernel_time_t msg_rtime;      /* last msgrcv time */
+        __kernel_time_t msg_ctime;      /* last change time */
+        unsigned long  msg_cbytes;      /* current number of bytes on queue */
+        unsigned long  msg_qnum;        /* number of messages in queue */
+        unsigned long  msg_qbytes;      /* max number of bytes on queue */
+        __kernel_pid_t msg_lspid;       /* pid of last msgsnd */
+        __kernel_pid_t msg_lrpid;       /* last receive pid */
+        unsigned long  __unused4;
+        unsigned long  __unused5;
+};
+
+#endif
diff --git a/include/asm-x86/msidef.h b/include/asm-x86/msidef.h
new file mode 100644
index 000000000000..5b8acddb70fb
--- /dev/null
+++ b/include/asm-x86/msidef.h
@@ -0,0 +1,47 @@
+#ifndef ASM_MSIDEF_H
+#define ASM_MSIDEF_H
+
+/*
+ * Constants for Intel APIC based MSI messages.
+ */
+
+/*
+ * Shifts for MSI data
+ */
+
+#define MSI_DATA_VECTOR_SHIFT           0
+#define  MSI_DATA_VECTOR_MASK           0x000000ff
+#define  MSI_DATA_VECTOR(v)             (((v) << MSI_DATA_VECTOR_SHIFT) & MSI_DATA_VECTOR_MASK)
+
+#define MSI_DATA_DELIVERY_MODE_SHIFT    8
+#define  MSI_DATA_DELIVERY_FIXED        (0 << MSI_DATA_DELIVERY_MODE_SHIFT)
+#define  MSI_DATA_DELIVERY_LOWPRI       (1 << MSI_DATA_DELIVERY_MODE_SHIFT)
+
+#define MSI_DATA_LEVEL_SHIFT            14
+#define  MSI_DATA_LEVEL_DEASSERT        (0 << MSI_DATA_LEVEL_SHIFT)
+#define  MSI_DATA_LEVEL_ASSERT          (1 << MSI_DATA_LEVEL_SHIFT)
+
+#define MSI_DATA_TRIGGER_SHIFT          15
+#define  MSI_DATA_TRIGGER_EDGE          (0 << MSI_DATA_TRIGGER_SHIFT)
+#define  MSI_DATA_TRIGGER_LEVEL         (1 << MSI_DATA_TRIGGER_SHIFT)
+
+/*
+ * Shift/mask fields for msi address
+ */
+
+#define MSI_ADDR_BASE_HI                0
+#define MSI_ADDR_BASE_LO                0xfee00000
+
+#define MSI_ADDR_DEST_MODE_SHIFT        2
+#define  MSI_ADDR_DEST_MODE_PHYSICAL    (0 << MSI_ADDR_DEST_MODE_SHIFT)
+#define  MSI_ADDR_DEST_MODE_LOGICAL     (1 << MSI_ADDR_DEST_MODE_SHIFT)
+
+#define MSI_ADDR_REDIRECTION_SHIFT      3
+#define  MSI_ADDR_REDIRECTION_CPU       (0 << MSI_ADDR_REDIRECTION_SHIFT) /* dedicated cpu */
+#define  MSI_ADDR_REDIRECTION_LOWPRI    (1 << MSI_ADDR_REDIRECTION_SHIFT) /* lowest priority */
+
+#define MSI_ADDR_DEST_ID_SHIFT          12
+#define  MSI_ADDR_DEST_ID_MASK          0x00ffff0
+#define  MSI_ADDR_DEST_ID(dest)         (((dest) << MSI_ADDR_DEST_ID_SHIFT) & MSI_ADDR_DEST_ID_MASK)
+
+#endif /* ASM_MSIDEF_H */
diff --git a/include/asm-x86/msr-index.h b/include/asm-x86/msr-index.h
new file mode 100644
index 000000000000..a02eb2991349
--- /dev/null
+++ b/include/asm-x86/msr-index.h
@@ -0,0 +1,278 @@
+#ifndef __ASM_MSR_INDEX_H
+#define __ASM_MSR_INDEX_H
+
+/* CPU model specific register (MSR) numbers */
+
+/* x86-64 specific MSRs */
+#define MSR_EFER                0xc0000080 /* extended feature register */
+#define MSR_STAR                0xc0000081 /* legacy mode SYSCALL target */
+#define MSR_LSTAR               0xc0000082 /* long mode SYSCALL target */
+#define MSR_CSTAR               0xc0000083 /* compat mode SYSCALL target */
+#define MSR_SYSCALL_MASK        0xc0000084 /* EFLAGS mask for syscall */
+#define MSR_FS_BASE             0xc0000100 /* 64bit FS base */
+#define MSR_GS_BASE             0xc0000101 /* 64bit GS base */
+#define MSR_KERNEL_GS_BASE      0xc0000102 /* SwapGS GS shadow */
+
+/* EFER bits: */
+#define _EFER_SCE               0  /* SYSCALL/SYSRET */
+#define _EFER_LME               8  /* Long mode enable */
+#define _EFER_LMA               10 /* Long mode active (read-only) */
+#define _EFER_NX                11 /* No execute enable */
+
+#define EFER_SCE                (1<<_EFER_SCE)
+#define EFER_LME                (1<<_EFER_LME)
+#define EFER_LMA                (1<<_EFER_LMA)
+#define EFER_NX                 (1<<_EFER_NX)
+
+/* Intel MSRs. Some also available on other CPUs */
+#define MSR_IA32_PERFCTR0               0x000000c1
+#define MSR_IA32_PERFCTR1               0x000000c2
+#define MSR_FSB_FREQ                    0x000000cd
+
+#define MSR_MTRRcap                     0x000000fe
+#define MSR_IA32_BBL_CR_CTL             0x00000119
+
+#define MSR_IA32_SYSENTER_CS            0x00000174
+#define MSR_IA32_SYSENTER_ESP           0x00000175
+#define MSR_IA32_SYSENTER_EIP           0x00000176
+
+#define MSR_IA32_MCG_CAP                0x00000179
+#define MSR_IA32_MCG_STATUS             0x0000017a
+#define MSR_IA32_MCG_CTL                0x0000017b
+
+#define MSR_IA32_PEBS_ENABLE            0x000003f1
+#define MSR_IA32_DS_AREA                0x00000600
+#define MSR_IA32_PERF_CAPABILITIES      0x00000345
+
+#define MSR_MTRRfix64K_00000            0x00000250
+#define MSR_MTRRfix16K_80000            0x00000258
+#define MSR_MTRRfix16K_A0000            0x00000259
+#define MSR_MTRRfix4K_C0000             0x00000268
+#define MSR_MTRRfix4K_C8000             0x00000269
+#define MSR_MTRRfix4K_D0000             0x0000026a
+#define MSR_MTRRfix4K_D8000             0x0000026b
+#define MSR_MTRRfix4K_E0000             0x0000026c
+#define MSR_MTRRfix4K_E8000             0x0000026d
+#define MSR_MTRRfix4K_F0000             0x0000026e
+#define MSR_MTRRfix4K_F8000             0x0000026f
+#define MSR_MTRRdefType                 0x000002ff
+
+#define MSR_IA32_DEBUGCTLMSR            0x000001d9
+#define MSR_IA32_LASTBRANCHFROMIP       0x000001db
+#define MSR_IA32_LASTBRANCHTOIP         0x000001dc
+#define MSR_IA32_LASTINTFROMIP          0x000001dd
+#define MSR_IA32_LASTINTTOIP            0x000001de
+
+#define MSR_IA32_MC0_CTL                0x00000400
+#define MSR_IA32_MC0_STATUS             0x00000401
+#define MSR_IA32_MC0_ADDR               0x00000402
+#define MSR_IA32_MC0_MISC               0x00000403
+
+#define MSR_P6_PERFCTR0                 0x000000c1
+#define MSR_P6_PERFCTR1                 0x000000c2
+#define MSR_P6_EVNTSEL0                 0x00000186
+#define MSR_P6_EVNTSEL1                 0x00000187
+
+/* K7/K8 MSRs. Not complete. See the architecture manual for a more
+   complete list. */
+#define MSR_K7_EVNTSEL0                 0xc0010000
+#define MSR_K7_PERFCTR0                 0xc0010004
+#define MSR_K7_EVNTSEL1                 0xc0010001
+#define MSR_K7_PERFCTR1                 0xc0010005
+#define MSR_K7_EVNTSEL2                 0xc0010002
+#define MSR_K7_PERFCTR2                 0xc0010006
+#define MSR_K7_EVNTSEL3                 0xc0010003
+#define MSR_K7_PERFCTR3                 0xc0010007
+#define MSR_K8_TOP_MEM1                 0xc001001a
+#define MSR_K7_CLK_CTL                  0xc001001b
+#define MSR_K8_TOP_MEM2                 0xc001001d
+#define MSR_K8_SYSCFG                   0xc0010010
+
+#define K8_MTRRFIXRANGE_DRAM_ENABLE     0x00040000 /* MtrrFixDramEn bit    */
+#define K8_MTRRFIXRANGE_DRAM_MODIFY     0x00080000 /* MtrrFixDramModEn bit */
+#define K8_MTRR_RDMEM_WRMEM_MASK        0x18181818 /* Mask: RdMem|WrMem    */
+
+#define MSR_K7_HWCR                     0xc0010015
+#define MSR_K8_HWCR                     0xc0010015
+#define MSR_K7_FID_VID_CTL              0xc0010041
+#define MSR_K7_FID_VID_STATUS           0xc0010042
+#define MSR_K8_ENABLE_C1E               0xc0010055
+
+/* K6 MSRs */
+#define MSR_K6_EFER                     0xc0000080
+#define MSR_K6_STAR                     0xc0000081
+#define MSR_K6_WHCR                     0xc0000082
+#define MSR_K6_UWCCR                    0xc0000085
+#define MSR_K6_EPMR                     0xc0000086
+#define MSR_K6_PSOR                     0xc0000087
+#define MSR_K6_PFIR                     0xc0000088
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1                    0x00000107
+#define MSR_IDT_FCR2                    0x00000108
+#define MSR_IDT_FCR3                    0x00000109
+#define MSR_IDT_FCR4                    0x0000010a
+
+#define MSR_IDT_MCR0                    0x00000110
+#define MSR_IDT_MCR1                    0x00000111
+#define MSR_IDT_MCR2                    0x00000112
+#define MSR_IDT_MCR3                    0x00000113
+#define MSR_IDT_MCR4                    0x00000114
+#define MSR_IDT_MCR5                    0x00000115
+#define MSR_IDT_MCR6                    0x00000116
+#define MSR_IDT_MCR7                    0x00000117
+#define MSR_IDT_MCR_CTRL                0x00000120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR                     0x00001107
+#define MSR_VIA_LONGHAUL                0x0000110a
+#define MSR_VIA_RNG                     0x0000110b
+#define MSR_VIA_BCR2                    0x00001147
+
+/* Transmeta defined MSRs */
+#define MSR_TMTA_LONGRUN_CTRL           0x80868010
+#define MSR_TMTA_LONGRUN_FLAGS          0x80868011
+#define MSR_TMTA_LRTI_READOUT           0x80868018
+#define MSR_TMTA_LRTI_VOLT_MHZ          0x8086801a
+
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR             0x00000000
+#define MSR_IA32_P5_MC_TYPE             0x00000001
+#define MSR_IA32_TSC                    0x00000010
+#define MSR_IA32_PLATFORM_ID            0x00000017
+#define MSR_IA32_EBL_CR_POWERON         0x0000002a
+
+#define MSR_IA32_APICBASE               0x0000001b
+#define MSR_IA32_APICBASE_BSP           (1<<8)
+#define MSR_IA32_APICBASE_ENABLE        (1<<11)
+#define MSR_IA32_APICBASE_BASE          (0xfffff<<12)
+
+#define MSR_IA32_UCODE_WRITE            0x00000079
+#define MSR_IA32_UCODE_REV              0x0000008b
+
+#define MSR_IA32_PERF_STATUS            0x00000198
+#define MSR_IA32_PERF_CTL               0x00000199
+
+#define MSR_IA32_MPERF                  0x000000e7
+#define MSR_IA32_APERF                  0x000000e8
+
+#define MSR_IA32_THERM_CONTROL          0x0000019a
+#define MSR_IA32_THERM_INTERRUPT        0x0000019b
+#define MSR_IA32_THERM_STATUS           0x0000019c
+#define MSR_IA32_MISC_ENABLE            0x000001a0
+
+/* Intel Model 6 */
+#define MSR_P6_EVNTSEL0                 0x00000186
+#define MSR_P6_EVNTSEL1                 0x00000187
+
+/* P4/Xeon+ specific */
+#define MSR_IA32_MCG_EAX                0x00000180
+#define MSR_IA32_MCG_EBX                0x00000181
+#define MSR_IA32_MCG_ECX                0x00000182
+#define MSR_IA32_MCG_EDX                0x00000183
+#define MSR_IA32_MCG_ESI                0x00000184
+#define MSR_IA32_MCG_EDI                0x00000185
+#define MSR_IA32_MCG_EBP                0x00000186
+#define MSR_IA32_MCG_ESP                0x00000187
+#define MSR_IA32_MCG_EFLAGS             0x00000188
+#define MSR_IA32_MCG_EIP                0x00000189
+#define MSR_IA32_MCG_RESERVED           0x0000018a
+
+/* Pentium IV performance counter MSRs */
+#define MSR_P4_BPU_PERFCTR0             0x00000300
+#define MSR_P4_BPU_PERFCTR1             0x00000301
+#define MSR_P4_BPU_PERFCTR2             0x00000302
+#define MSR_P4_BPU_PERFCTR3             0x00000303
+#define MSR_P4_MS_PERFCTR0              0x00000304
+#define MSR_P4_MS_PERFCTR1              0x00000305
+#define MSR_P4_MS_PERFCTR2              0x00000306
+#define MSR_P4_MS_PERFCTR3              0x00000307
+#define MSR_P4_FLAME_PERFCTR0           0x00000308
+#define MSR_P4_FLAME_PERFCTR1           0x00000309
+#define MSR_P4_FLAME_PERFCTR2           0x0000030a
+#define MSR_P4_FLAME_PERFCTR3           0x0000030b
+#define MSR_P4_IQ_PERFCTR0              0x0000030c
+#define MSR_P4_IQ_PERFCTR1              0x0000030d
+#define MSR_P4_IQ_PERFCTR2              0x0000030e
+#define MSR_P4_IQ_PERFCTR3              0x0000030f
+#define MSR_P4_IQ_PERFCTR4              0x00000310
+#define MSR_P4_IQ_PERFCTR5              0x00000311
+#define MSR_P4_BPU_CCCR0                0x00000360
+#define MSR_P4_BPU_CCCR1                0x00000361
+#define MSR_P4_BPU_CCCR2                0x00000362
+#define MSR_P4_BPU_CCCR3                0x00000363
+#define MSR_P4_MS_CCCR0                 0x00000364
+#define MSR_P4_MS_CCCR1                 0x00000365
+#define MSR_P4_MS_CCCR2                 0x00000366
+#define MSR_P4_MS_CCCR3                 0x00000367
+#define MSR_P4_FLAME_CCCR0              0x00000368
+#define MSR_P4_FLAME_CCCR1              0x00000369
+#define MSR_P4_FLAME_CCCR2              0x0000036a
+#define MSR_P4_FLAME_CCCR3              0x0000036b
+#define MSR_P4_IQ_CCCR0                 0x0000036c
+#define MSR_P4_IQ_CCCR1                 0x0000036d
+#define MSR_P4_IQ_CCCR2                 0x0000036e
+#define MSR_P4_IQ_CCCR3                 0x0000036f
+#define MSR_P4_IQ_CCCR4                 0x00000370
+#define MSR_P4_IQ_CCCR5                 0x00000371
+#define MSR_P4_ALF_ESCR0                0x000003ca
+#define MSR_P4_ALF_ESCR1                0x000003cb
+#define MSR_P4_BPU_ESCR0                0x000003b2
+#define MSR_P4_BPU_ESCR1                0x000003b3
+#define MSR_P4_BSU_ESCR0                0x000003a0
+#define MSR_P4_BSU_ESCR1                0x000003a1
+#define MSR_P4_CRU_ESCR0                0x000003b8
+#define MSR_P4_CRU_ESCR1                0x000003b9
+#define MSR_P4_CRU_ESCR2                0x000003cc
+#define MSR_P4_CRU_ESCR3                0x000003cd
+#define MSR_P4_CRU_ESCR4                0x000003e0
+#define MSR_P4_CRU_ESCR5                0x000003e1
+#define MSR_P4_DAC_ESCR0                0x000003a8
+#define MSR_P4_DAC_ESCR1                0x000003a9
+#define MSR_P4_FIRM_ESCR0               0x000003a4
+#define MSR_P4_FIRM_ESCR1               0x000003a5
+#define MSR_P4_FLAME_ESCR0              0x000003a6
+#define MSR_P4_FLAME_ESCR1              0x000003a7
+#define MSR_P4_FSB_ESCR0                0x000003a2
+#define MSR_P4_FSB_ESCR1                0x000003a3
+#define MSR_P4_IQ_ESCR0                 0x000003ba
+#define MSR_P4_IQ_ESCR1                 0x000003bb
+#define MSR_P4_IS_ESCR0                 0x000003b4
+#define MSR_P4_IS_ESCR1                 0x000003b5
+#define MSR_P4_ITLB_ESCR0               0x000003b6
+#define MSR_P4_ITLB_ESCR1               0x000003b7
+#define MSR_P4_IX_ESCR0                 0x000003c8
+#define MSR_P4_IX_ESCR1                 0x000003c9
+#define MSR_P4_MOB_ESCR0                0x000003aa
+#define MSR_P4_MOB_ESCR1                0x000003ab
+#define MSR_P4_MS_ESCR0                 0x000003c0
+#define MSR_P4_MS_ESCR1                 0x000003c1
+#define MSR_P4_PMH_ESCR0                0x000003ac
+#define MSR_P4_PMH_ESCR1                0x000003ad
+#define MSR_P4_RAT_ESCR0                0x000003bc
+#define MSR_P4_RAT_ESCR1                0x000003bd
+#define MSR_P4_SAAT_ESCR0               0x000003ae
+#define MSR_P4_SAAT_ESCR1               0x000003af
+#define MSR_P4_SSU_ESCR0                0x000003be
+#define MSR_P4_SSU_ESCR1                0x000003bf /* guess: not in manual */
+
+#define MSR_P4_TBPU_ESCR0               0x000003c2
+#define MSR_P4_TBPU_ESCR1               0x000003c3
+#define MSR_P4_TC_ESCR0                 0x000003c4
+#define MSR_P4_TC_ESCR1                 0x000003c5
+#define MSR_P4_U2L_ESCR0                0x000003b0
+#define MSR_P4_U2L_ESCR1                0x000003b1
+
+/* Intel Core-based CPU performance counters */
+#define MSR_CORE_PERF_FIXED_CTR0        0x00000309
+#define MSR_CORE_PERF_FIXED_CTR1        0x0000030a
+#define MSR_CORE_PERF_FIXED_CTR2        0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR_CTRL    0x0000038d
+#define MSR_CORE_PERF_GLOBAL_STATUS     0x0000038e
+#define MSR_CORE_PERF_GLOBAL_CTRL       0x0000038f
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL   0x00000390
+
+/* Geode defined MSRs */
+#define MSR_GEODE_BUSCONT_CONF0         0x00001900
+
+#endif /* __ASM_MSR_INDEX_H */
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
new file mode 100644
index 000000000000..2f87ce007002
--- /dev/null
+++ b/include/asm-x86/msr.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "msr_32.h"
+# else
+#  include "msr_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "msr_32.h"
+# else
+#  include "msr_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/msr_32.h b/include/asm-x86/msr_32.h
new file mode 100644
index 000000000000..df21ea049369
--- /dev/null
+++ b/include/asm-x86/msr_32.h
@@ -0,0 +1,161 @@
+#ifndef __ASM_MSR_H
+#define __ASM_MSR_H
+
+#include <asm/msr-index.h>
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#include <asm/errno.h>
+
+static inline unsigned long long native_read_msr(unsigned int msr)
+{
+        unsigned long long val;
+
+        asm volatile("rdmsr" : "=A" (val) : "c" (msr));
+        return val;
+}
+
+static inline unsigned long long native_read_msr_safe(unsigned int msr,
+                                                      int *err)
+{
+        unsigned long long val;
+
+        asm volatile("2: rdmsr ; xorl %0,%0\n"
+                     "1:\n\t"
+                     ".section .fixup,\"ax\"\n\t"
+                     "3:  movl %3,%0 ; jmp 1b\n\t"
+                     ".previous\n\t"
+                     ".section __ex_table,\"a\"\n"
+                     "   .align 4\n\t"
+                     "   .long  2b,3b\n\t"
+                     ".previous"
+                     : "=r" (*err), "=A" (val)
+                     : "c" (msr), "i" (-EFAULT));
+
+        return val;
+}
+
+static inline void native_write_msr(unsigned int msr, unsigned long long val)
+{
+        asm volatile("wrmsr" : : "c" (msr), "A"(val));
+}
+
+static inline int native_write_msr_safe(unsigned int msr,
+                                        unsigned long long val)
+{
+        int err;
+        asm volatile("2: wrmsr ; xorl %0,%0\n"
+                     "1:\n\t"
+                     ".section .fixup,\"ax\"\n\t"
+                     "3:  movl %4,%0 ; jmp 1b\n\t"
+                     ".previous\n\t"
+                     ".section __ex_table,\"a\"\n"
+                     "   .align 4\n\t"
+                     "   .long  2b,3b\n\t"
+                     ".previous"
+                     : "=a" (err)
+                     : "c" (msr), "0" ((u32)val), "d" ((u32)(val>>32)),
+                       "i" (-EFAULT));
+        return err;
+}
+
+static inline unsigned long long native_read_tsc(void)
+{
+        unsigned long long val;
+        asm volatile("rdtsc" : "=A" (val));
+        return val;
+}
+
+static inline unsigned long long native_read_pmc(void)
+{
+        unsigned long long val;
+        asm volatile("rdpmc" : "=A" (val));
+        return val;
+}
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#include <linux/errno.h>
+/*
+ * Access to machine-specific registers (available on 586 and better only)
+ * Note: the rd* operations modify the parameters directly (without using
+ * pointer indirection), this allows gcc to optimize better
+ */
+
+#define rdmsr(msr,val1,val2)                                            \
+        do {                                                            \
+                u64 __val = native_read_msr(msr);                       \
+                (val1) = (u32)__val;                                    \
+                (val2) = (u32)(__val >> 32);                            \
+        } while(0)
+
+static inline void wrmsr(u32 __msr, u32 __low, u32 __high)
+{
+        native_write_msr(__msr, ((u64)__high << 32) | __low);
+}
+
+#define rdmsrl(msr,val)                                                 \
+        ((val) = native_read_msr(msr))
+
+#define wrmsrl(msr,val) native_write_msr(msr, val)
+
+/* wrmsr with exception handling */
+static inline int wrmsr_safe(u32 __msr, u32 __low, u32 __high)
+{
+        return native_write_msr_safe(__msr, ((u64)__high << 32) | __low);
+}
+
+/* rdmsr with exception handling */
+#define rdmsr_safe(msr,p1,p2)                                           \
+        ({                                                              \
+                int __err;                                              \
+                u64 __val = native_read_msr_safe(msr, &__err);          \
+                (*p1) = (u32)__val;                                     \
+                (*p2) = (u32)(__val >> 32);                             \
+                __err;                                                  \
+        })
+
+#define rdtscl(low)                                             \
+        ((low) = (u32)native_read_tsc())
+
+#define rdtscll(val)                                            \
+        ((val) = native_read_tsc())
+
+#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
+
+#define rdpmc(counter,low,high)                                 \
+        do {                                                    \
+                u64 _l = native_read_pmc();                     \
+                (low)  = (u32)_l;                               \
+                (high) = (u32)(_l >> 32);                       \
+        } while(0)
+#endif  /* !CONFIG_PARAVIRT */
+
+#ifdef CONFIG_SMP
+void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+#else  /*  CONFIG_SMP  */
+static inline void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+        rdmsr(msr_no, *l, *h);
+}
+static inline void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+        wrmsr(msr_no, l, h);
+}
+static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+        return rdmsr_safe(msr_no, l, h);
+}
+static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+        return wrmsr_safe(msr_no, l, h);
+}
+#endif  /*  CONFIG_SMP  */
+#endif
+#endif
+#endif /* __ASM_MSR_H */
diff --git a/include/asm-x86/msr_64.h b/include/asm-x86/msr_64.h
new file mode 100644
index 000000000000..d5c55b80da54
--- /dev/null
+++ b/include/asm-x86/msr_64.h
@@ -0,0 +1,187 @@
+#ifndef X86_64_MSR_H
+#define X86_64_MSR_H 1
+
+#include <asm/msr-index.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/errno.h>
+/*
+ * Access to machine-specific registers (available on 586 and better only)
+ * Note: the rd* operations modify the parameters directly (without using
+ * pointer indirection), this allows gcc to optimize better
+ */
+
+#define rdmsr(msr,val1,val2) \
+       __asm__ __volatile__("rdmsr" \
+                            : "=a" (val1), "=d" (val2) \
+                            : "c" (msr))
+
+
+#define rdmsrl(msr,val) do { unsigned long a__,b__; \
+       __asm__ __volatile__("rdmsr" \
+                            : "=a" (a__), "=d" (b__) \
+                            : "c" (msr)); \
+       val = a__ | (b__<<32); \
+} while(0)
+
+#define wrmsr(msr,val1,val2) \
+     __asm__ __volatile__("wrmsr" \
+                          : /* no outputs */ \
+                          : "c" (msr), "a" (val1), "d" (val2))
+
+#define wrmsrl(msr,val) wrmsr(msr,(__u32)((__u64)(val)),((__u64)(val))>>32) 
+
+/* wrmsr with exception handling */
+#define wrmsr_safe(msr,a,b) ({ int ret__;                       \
+        asm volatile("2: wrmsr ; xorl %0,%0\n"                  \
+                     "1:\n\t"                                   \
+                     ".section .fixup,\"ax\"\n\t"               \
+                     "3:  movl %4,%0 ; jmp 1b\n\t"              \
+                     ".previous\n\t"                            \
+                     ".section __ex_table,\"a\"\n"              \
+                     "   .align 8\n\t"                          \
+                     "   .quad  2b,3b\n\t"                      \
+                     ".previous"                                \
+                     : "=a" (ret__)                             \
+                     : "c" (msr), "0" (a), "d" (b), "i" (-EFAULT)); \
+        ret__; })
+
+#define checking_wrmsrl(msr,val) wrmsr_safe(msr,(u32)(val),(u32)((val)>>32))
+
+#define rdmsr_safe(msr,a,b) \
+        ({ int ret__;                                           \
+          asm volatile ("1:       rdmsr\n"                      \
+                      "2:\n"                                    \
+                      ".section .fixup,\"ax\"\n"                \
+                      "3:       movl %4,%0\n"                   \
+                      " jmp 2b\n"                               \
+                      ".previous\n"                             \
+                      ".section __ex_table,\"a\"\n"             \
+                      " .align 8\n"                             \
+                      " .quad 1b,3b\n"                          \
+                      ".previous":"=&bDS" (ret__), "=a"(*(a)), "=d"(*(b))\
+                      :"c"(msr), "i"(-EIO), "0"(0));            \
+          ret__; })             
+
+#define rdtsc(low,high) \
+     __asm__ __volatile__("rdtsc" : "=a" (low), "=d" (high))
+
+#define rdtscl(low) \
+     __asm__ __volatile__ ("rdtsc" : "=a" (low) : : "edx")
+
+#define rdtscp(low,high,aux) \
+     asm volatile (".byte 0x0f,0x01,0xf9" : "=a" (low), "=d" (high), "=c" (aux))
+
+#define rdtscll(val) do { \
+     unsigned int __a,__d; \
+     asm volatile("rdtsc" : "=a" (__a), "=d" (__d)); \
+     (val) = ((unsigned long)__a) | (((unsigned long)__d)<<32); \
+} while(0)
+
+#define rdtscpll(val, aux) do { \
+     unsigned long __a, __d; \
+     asm volatile (".byte 0x0f,0x01,0xf9" : "=a" (__a), "=d" (__d), "=c" (aux)); \
+     (val) = (__d << 32) | __a; \
+} while (0)
+
+#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
+
+#define write_rdtscp_aux(val) wrmsr(0xc0000103, val, 0)
+
+#define rdpmc(counter,low,high) \
+     __asm__ __volatile__("rdpmc" \
+                          : "=a" (low), "=d" (high) \
+                          : "c" (counter))
+
+static inline void cpuid(int op, unsigned int *eax, unsigned int *ebx,
+                         unsigned int *ecx, unsigned int *edx)
+{
+        __asm__("cpuid"
+                : "=a" (*eax),
+                  "=b" (*ebx),
+                  "=c" (*ecx),
+                  "=d" (*edx)
+                : "0" (op));
+}
+
+/* Some CPUID calls want 'count' to be placed in ecx */
+static inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx,
+                int *edx)
+{
+        __asm__("cpuid"
+                : "=a" (*eax),
+                  "=b" (*ebx),
+                  "=c" (*ecx),
+                  "=d" (*edx)
+                : "0" (op), "c" (count));
+}
+
+/*
+ * CPUID functions returning a single datum
+ */
+static inline unsigned int cpuid_eax(unsigned int op)
+{
+        unsigned int eax;
+
+        __asm__("cpuid"
+                : "=a" (eax)
+                : "0" (op)
+                : "bx", "cx", "dx");
+        return eax;
+}
+static inline unsigned int cpuid_ebx(unsigned int op)
+{
+        unsigned int eax, ebx;
+
+        __asm__("cpuid"
+                : "=a" (eax), "=b" (ebx)
+                : "0" (op)
+                : "cx", "dx" );
+        return ebx;
+}
+static inline unsigned int cpuid_ecx(unsigned int op)
+{
+        unsigned int eax, ecx;
+
+        __asm__("cpuid"
+                : "=a" (eax), "=c" (ecx)
+                : "0" (op)
+                : "bx", "dx" );
+        return ecx;
+}
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+        unsigned int eax, edx;
+
+        __asm__("cpuid"
+                : "=a" (eax), "=d" (edx)
+                : "0" (op)
+                : "bx", "cx");
+        return edx;
+}
+
+#ifdef CONFIG_SMP
+void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+#else  /*  CONFIG_SMP  */
+static inline void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+        rdmsr(msr_no, *l, *h);
+}
+static inline void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+        wrmsr(msr_no, l, h);
+}
+static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+        return rdmsr_safe(msr_no, l, h);
+}
+static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+        return wrmsr_safe(msr_no, l, h);
+}
+#endif  /* CONFIG_SMP */
+#endif /* __ASSEMBLY__ */
+#endif  /* X86_64_MSR_H */
diff --git a/include/asm-x86/mtrr.h b/include/asm-x86/mtrr.h
new file mode 100644
index 000000000000..34f633b3e00c
--- /dev/null
+++ b/include/asm-x86/mtrr.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "mtrr_32.h"
+# else
+#  include "mtrr_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "mtrr_32.h"
+# else
+#  include "mtrr_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/mtrr_32.h b/include/asm-x86/mtrr_32.h
new file mode 100644
index 000000000000..7e9c7ccbdcfe
--- /dev/null
+++ b/include/asm-x86/mtrr_32.h
@@ -0,0 +1,115 @@
+/*  Generic MTRR (Memory Type Range Register) ioctls.
+
+    Copyright (C) 1997-1999  Richard Gooch
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Library General Public
+    License as published by the Free Software Foundation; either
+    version 2 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Library General Public License for more details.
+
+    You should have received a copy of the GNU Library General Public
+    License along with this library; if not, write to the Free
+    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+    Richard Gooch may be reached by email at  rgooch@atnf.csiro.au
+    The postal address is:
+      Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
+*/
+#ifndef _LINUX_MTRR_H
+#define _LINUX_MTRR_H
+
+#include <linux/ioctl.h>
+#include <linux/errno.h>
+
+#define MTRR_IOCTL_BASE 'M'
+
+struct mtrr_sentry
+{
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int type;     /*  Type of region   */
+};
+
+struct mtrr_gentry
+{
+    unsigned int regnum;   /*  Register number  */
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int type;     /*  Type of region   */
+};
+
+/*  These are the various ioctls  */
+#define MTRRIOC_ADD_ENTRY        _IOW(MTRR_IOCTL_BASE,  0, struct mtrr_sentry)
+#define MTRRIOC_SET_ENTRY        _IOW(MTRR_IOCTL_BASE,  1, struct mtrr_sentry)
+#define MTRRIOC_DEL_ENTRY        _IOW(MTRR_IOCTL_BASE,  2, struct mtrr_sentry)
+#define MTRRIOC_GET_ENTRY        _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry)
+#define MTRRIOC_KILL_ENTRY       _IOW(MTRR_IOCTL_BASE,  4, struct mtrr_sentry)
+#define MTRRIOC_ADD_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  5, struct mtrr_sentry)
+#define MTRRIOC_SET_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  6, struct mtrr_sentry)
+#define MTRRIOC_DEL_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  7, struct mtrr_sentry)
+#define MTRRIOC_GET_PAGE_ENTRY   _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
+#define MTRRIOC_KILL_PAGE_ENTRY  _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry)
+
+/*  These are the region types  */
+#define MTRR_TYPE_UNCACHABLE 0
+#define MTRR_TYPE_WRCOMB     1
+/*#define MTRR_TYPE_         2*/
+/*#define MTRR_TYPE_         3*/
+#define MTRR_TYPE_WRTHROUGH  4
+#define MTRR_TYPE_WRPROT     5
+#define MTRR_TYPE_WRBACK     6
+#define MTRR_NUM_TYPES       7
+
+#ifdef __KERNEL__
+
+/*  The following functions are for use by other drivers  */
+# ifdef CONFIG_MTRR
+extern void mtrr_save_fixed_ranges(void *);
+extern void mtrr_save_state(void);
+extern int mtrr_add (unsigned long base, unsigned long size,
+                     unsigned int type, char increment);
+extern int mtrr_add_page (unsigned long base, unsigned long size,
+                     unsigned int type, char increment);
+extern int mtrr_del (int reg, unsigned long base, unsigned long size);
+extern int mtrr_del_page (int reg, unsigned long base, unsigned long size);
+extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
+extern void mtrr_ap_init(void);
+extern void mtrr_bp_init(void);
+#  else
+#define mtrr_save_fixed_ranges(arg) do {} while (0)
+#define mtrr_save_state() do {} while (0)
+static __inline__ int mtrr_add (unsigned long base, unsigned long size,
+                                unsigned int type, char increment)
+{
+    return -ENODEV;
+}
+static __inline__ int mtrr_add_page (unsigned long base, unsigned long size,
+                                unsigned int type, char increment)
+{
+    return -ENODEV;
+}
+static __inline__ int mtrr_del (int reg, unsigned long base,
+                                unsigned long size)
+{
+    return -ENODEV;
+}
+static __inline__ int mtrr_del_page (int reg, unsigned long base,
+                                unsigned long size)
+{
+    return -ENODEV;
+}
+
+static __inline__ void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) {;}
+
+#define mtrr_ap_init() do {} while (0)
+#define mtrr_bp_init() do {} while (0)
+#  endif
+
+#endif
+
+#endif  /*  _LINUX_MTRR_H  */
diff --git a/include/asm-x86/mtrr_64.h b/include/asm-x86/mtrr_64.h
new file mode 100644
index 000000000000..b557c486bef8
--- /dev/null
+++ b/include/asm-x86/mtrr_64.h
@@ -0,0 +1,152 @@
+/*  Generic MTRR (Memory Type Range Register) ioctls.
+
+    Copyright (C) 1997-1999  Richard Gooch
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Library General Public
+    License as published by the Free Software Foundation; either
+    version 2 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Library General Public License for more details.
+
+    You should have received a copy of the GNU Library General Public
+    License along with this library; if not, write to the Free
+    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+    Richard Gooch may be reached by email at  rgooch@atnf.csiro.au
+    The postal address is:
+      Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
+*/
+#ifndef _LINUX_MTRR_H
+#define _LINUX_MTRR_H
+
+#include <linux/ioctl.h>
+
+#define MTRR_IOCTL_BASE 'M'
+
+struct mtrr_sentry
+{
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int type;     /*  Type of region   */
+};
+
+/* Warning: this structure has a different order from i386
+   on x86-64. The 32bit emulation code takes care of that.
+   But you need to use this for 64bit, otherwise your X server
+   will break. */
+struct mtrr_gentry
+{
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int regnum;   /*  Register number  */
+    unsigned int type;     /*  Type of region   */
+};
+
+/*  These are the various ioctls  */
+#define MTRRIOC_ADD_ENTRY        _IOW(MTRR_IOCTL_BASE,  0, struct mtrr_sentry)
+#define MTRRIOC_SET_ENTRY        _IOW(MTRR_IOCTL_BASE,  1, struct mtrr_sentry)
+#define MTRRIOC_DEL_ENTRY        _IOW(MTRR_IOCTL_BASE,  2, struct mtrr_sentry)
+#define MTRRIOC_GET_ENTRY        _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry)
+#define MTRRIOC_KILL_ENTRY       _IOW(MTRR_IOCTL_BASE,  4, struct mtrr_sentry)
+#define MTRRIOC_ADD_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  5, struct mtrr_sentry)
+#define MTRRIOC_SET_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  6, struct mtrr_sentry)
+#define MTRRIOC_DEL_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  7, struct mtrr_sentry)
+#define MTRRIOC_GET_PAGE_ENTRY   _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
+#define MTRRIOC_KILL_PAGE_ENTRY  _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry)
+
+/*  These are the region types  */
+#define MTRR_TYPE_UNCACHABLE 0
+#define MTRR_TYPE_WRCOMB     1
+/*#define MTRR_TYPE_         2*/
+/*#define MTRR_TYPE_         3*/
+#define MTRR_TYPE_WRTHROUGH  4
+#define MTRR_TYPE_WRPROT     5
+#define MTRR_TYPE_WRBACK     6
+#define MTRR_NUM_TYPES       7
+
+#ifdef __KERNEL__
+
+/*  The following functions are for use by other drivers  */
+# ifdef CONFIG_MTRR
+extern int mtrr_add (unsigned long base, unsigned long size,
+                     unsigned int type, char increment);
+extern int mtrr_add_page (unsigned long base, unsigned long size,
+                     unsigned int type, char increment);
+extern int mtrr_del (int reg, unsigned long base, unsigned long size);
+extern int mtrr_del_page (int reg, unsigned long base, unsigned long size);
+#  else
+static __inline__ int mtrr_add (unsigned long base, unsigned long size,
+                                unsigned int type, char increment)
+{
+    return -ENODEV;
+}
+static __inline__ int mtrr_add_page (unsigned long base, unsigned long size,
+                                unsigned int type, char increment)
+{
+    return -ENODEV;
+}
+static __inline__ int mtrr_del (int reg, unsigned long base,
+                                unsigned long size)
+{
+    return -ENODEV;
+}
+static __inline__ int mtrr_del_page (int reg, unsigned long base,
+                                unsigned long size)
+{
+    return -ENODEV;
+}
+
+#endif /* CONFIG_MTRR */
+
+#ifdef CONFIG_COMPAT
+#include <linux/compat.h>
+
+struct mtrr_sentry32
+{
+    compat_ulong_t base;    /*  Base address     */
+    compat_uint_t size;    /*  Size of region   */
+    compat_uint_t type;     /*  Type of region   */
+};
+
+struct mtrr_gentry32
+{
+    compat_ulong_t regnum;   /*  Register number  */
+    compat_uint_t base;    /*  Base address     */
+    compat_uint_t size;    /*  Size of region   */
+    compat_uint_t type;     /*  Type of region   */
+};
+
+#define MTRR_IOCTL_BASE 'M'
+
+#define MTRRIOC32_ADD_ENTRY        _IOW(MTRR_IOCTL_BASE,  0, struct mtrr_sentry32)
+#define MTRRIOC32_SET_ENTRY        _IOW(MTRR_IOCTL_BASE,  1, struct mtrr_sentry32)
+#define MTRRIOC32_DEL_ENTRY        _IOW(MTRR_IOCTL_BASE,  2, struct mtrr_sentry32)
+#define MTRRIOC32_GET_ENTRY        _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry32)
+#define MTRRIOC32_KILL_ENTRY       _IOW(MTRR_IOCTL_BASE,  4, struct mtrr_sentry32)
+#define MTRRIOC32_ADD_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  5, struct mtrr_sentry32)
+#define MTRRIOC32_SET_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  6, struct mtrr_sentry32)
+#define MTRRIOC32_DEL_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  7, struct mtrr_sentry32)
+#define MTRRIOC32_GET_PAGE_ENTRY   _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry32)
+#define MTRRIOC32_KILL_PAGE_ENTRY  _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry32)
+
+#endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_MTRR
+extern void mtrr_ap_init(void);
+extern void mtrr_bp_init(void);
+extern void mtrr_save_fixed_ranges(void *);
+extern void mtrr_save_state(void);
+#else
+#define mtrr_ap_init() do {} while (0)
+#define mtrr_bp_init() do {} while (0)
+#define mtrr_save_fixed_ranges(arg) do {} while (0)
+#define mtrr_save_state() do {} while (0)
+#endif
+
+#endif /* __KERNEL__ */
+
+#endif  /*  _LINUX_MTRR_H  */
diff --git a/include/asm-x86/mutex.h b/include/asm-x86/mutex.h
new file mode 100644
index 000000000000..a731b9c573a6
--- /dev/null
+++ b/include/asm-x86/mutex.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mutex_32.h"
+#else
+# include "mutex_64.h"
+#endif
diff --git a/include/asm-x86/mutex_32.h b/include/asm-x86/mutex_32.h
new file mode 100644
index 000000000000..7a17d9e58ad6
--- /dev/null
+++ b/include/asm-x86/mutex_32.h
@@ -0,0 +1,130 @@
+/*
+ * Assembly implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef _ASM_MUTEX_H
+#define _ASM_MUTEX_H
+
+#include "asm/alternative.h"
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fn> if it
+ * wasn't 1 originally. This function MUST leave the value lower than 1
+ * even when the "1" assertion wasn't true.
+ */
+#define __mutex_fastpath_lock(count, fail_fn)                           \
+do {                                                                    \
+        unsigned int dummy;                                             \
+                                                                        \
+        typecheck(atomic_t *, count);                                   \
+        typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);           \
+                                                                        \
+        __asm__ __volatile__(                                           \
+                LOCK_PREFIX "   decl (%%eax)    \n"                     \
+                        "   jns 1f              \n"                     \
+                        "   call "#fail_fn"     \n"                     \
+                        "1:                     \n"                     \
+                                                                        \
+                :"=a" (dummy)                                           \
+                : "a" (count)                                           \
+                : "memory", "ecx", "edx");                              \
+} while (0)
+
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
+ * wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count,
+                             int fastcall (*fail_fn)(atomic_t *))
+{
+        if (unlikely(atomic_dec_return(count) < 0))
+                return fail_fn(count);
+        else
+                return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * try to promote the mutex from 0 to 1. if it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value
+ * to 1, or to set it to a value lower than 1.
+ *
+ * If the implementation sets it to a value of lower than 1, the
+ * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
+ * to return 0 otherwise.
+ */
+#define __mutex_fastpath_unlock(count, fail_fn)                         \
+do {                                                                    \
+        unsigned int dummy;                                             \
+                                                                        \
+        typecheck(atomic_t *, count);                                   \
+        typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);           \
+                                                                        \
+        __asm__ __volatile__(                                           \
+                LOCK_PREFIX "   incl (%%eax)    \n"                     \
+                        "   jg  1f              \n"                     \
+                        "   call "#fail_fn"     \n"                     \
+                        "1:                     \n"                     \
+                                                                        \
+                :"=a" (dummy)                                           \
+                : "a" (count)                                           \
+                : "memory", "ecx", "edx");                              \
+} while (0)
+
+#define __mutex_slowpath_needs_to_unlock()      1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to a value lower than 1, and return 0 (failure)
+ * if it wasn't 1 originally, or return 1 (success) otherwise. This function
+ * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
+ * Additionally, if the value was < 0 originally, this function must not leave
+ * it to 0 on failure.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+        /*
+         * We have two variants here. The cmpxchg based one is the best one
+         * because it never induce a false contention state.  It is included
+         * here because architectures using the inc/dec algorithms over the
+         * xchg ones are much more likely to support cmpxchg natively.
+         *
+         * If not we fall back to the spinlock based variant - that is
+         * just as efficient (and simpler) as a 'destructive' probing of
+         * the mutex state would be.
+         */
+#ifdef __HAVE_ARCH_CMPXCHG
+        if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+                return 1;
+        return 0;
+#else
+        return fail_fn(count);
+#endif
+}
+
+#endif
diff --git a/include/asm-x86/mutex_64.h b/include/asm-x86/mutex_64.h
new file mode 100644
index 000000000000..6c2949a3c677
--- /dev/null
+++ b/include/asm-x86/mutex_64.h
@@ -0,0 +1,105 @@
+/*
+ * Assembly implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef _ASM_MUTEX_H
+#define _ASM_MUTEX_H
+
+/**
+ * __mutex_fastpath_lock - decrement and call function if negative
+ * @v: pointer of type atomic_t
+ * @fail_fn: function to call if the result is negative
+ *
+ * Atomically decrements @v and calls <fail_fn> if the result is negative.
+ */
+#define __mutex_fastpath_lock(v, fail_fn)                               \
+do {                                                                    \
+        unsigned long dummy;                                            \
+                                                                        \
+        typecheck(atomic_t *, v);                                       \
+        typecheck_fn(void (*)(atomic_t *), fail_fn);                    \
+                                                                        \
+        __asm__ __volatile__(                                           \
+                LOCK_PREFIX "   decl (%%rdi)    \n"                     \
+                        "   jns 1f              \n"                     \
+                        "   call "#fail_fn"     \n"                     \
+                        "1:"                                            \
+                                                                        \
+                :"=D" (dummy)                                           \
+                : "D" (v)                                               \
+                : "rax", "rsi", "rdx", "rcx",                           \
+                  "r8", "r9", "r10", "r11", "memory");                  \
+} while (0)
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count,
+                             int (*fail_fn)(atomic_t *))
+{
+        if (unlikely(atomic_dec_return(count) < 0))
+                return fail_fn(count);
+        else
+                return 0;
+}
+
+/**
+ * __mutex_fastpath_unlock - increment and call function if nonpositive
+ * @v: pointer of type atomic_t
+ * @fail_fn: function to call if the result is nonpositive
+ *
+ * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
+ */
+#define __mutex_fastpath_unlock(v, fail_fn)                             \
+do {                                                                    \
+        unsigned long dummy;                                            \
+                                                                        \
+        typecheck(atomic_t *, v);                                       \
+        typecheck_fn(void (*)(atomic_t *), fail_fn);                    \
+                                                                        \
+        __asm__ __volatile__(                                           \
+                LOCK_PREFIX "   incl (%%rdi)    \n"                     \
+                        "   jg 1f               \n"                     \
+                        "   call "#fail_fn"     \n"                     \
+                        "1:                       "                     \
+                                                                        \
+                :"=D" (dummy)                                           \
+                : "D" (v)                                               \
+                : "rax", "rsi", "rdx", "rcx",                           \
+                  "r8", "r9", "r10", "r11", "memory");                  \
+} while (0)
+
+#define __mutex_slowpath_needs_to_unlock()      1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to 0 and return 1 (success), or return 0 (failure)
+ * if it wasn't 1 originally. [the fallback function is never used on
+ * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.]
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+        if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+                return 1;
+        else
+                return 0;
+}
+
+#endif
diff --git a/include/asm-x86/namei.h b/include/asm-x86/namei.h
new file mode 100644
index 000000000000..732f8f0b3dcd
--- /dev/null
+++ b/include/asm-x86/namei.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "namei_32.h"
+#else
+# include "namei_64.h"
+#endif
diff --git a/include/asm-x86/namei_32.h b/include/asm-x86/namei_32.h
new file mode 100644
index 000000000000..814865088617
--- /dev/null
+++ b/include/asm-x86/namei_32.h
@@ -0,0 +1,17 @@
+/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $
+ * linux/include/asm-i386/namei.h
+ *
+ * Included from linux/fs/namei.c
+ */
+
+#ifndef __I386_NAMEI_H
+#define __I386_NAMEI_H
+
+/* This dummy routine maybe changed to something useful
+ * for /usr/gnemul/ emulation stuff.
+ * Look at asm-sparc/namei.h for details.
+ */
+
+#define __emul_prefix() NULL
+
+#endif /* __I386_NAMEI_H */
diff --git a/include/asm-x86/namei_64.h b/include/asm-x86/namei_64.h
new file mode 100644
index 000000000000..bef239f5318f
--- /dev/null
+++ b/include/asm-x86/namei_64.h
@@ -0,0 +1,11 @@
+#ifndef __X8664_NAMEI_H
+#define __X8664_NAMEI_H
+
+/* This dummy routine maybe changed to something useful
+ * for /usr/gnemul/ emulation stuff.
+ * Look at asm-sparc/namei.h for details.
+ */
+
+#define __emul_prefix() NULL
+
+#endif
diff --git a/include/asm-x86/nmi.h b/include/asm-x86/nmi.h
new file mode 100644
index 000000000000..53ccac14cead
--- /dev/null
+++ b/include/asm-x86/nmi.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "nmi_32.h"
+#else
+# include "nmi_64.h"
+#endif
diff --git a/include/asm-x86/nmi_32.h b/include/asm-x86/nmi_32.h
new file mode 100644
index 000000000000..70a958a8e381
--- /dev/null
+++ b/include/asm-x86/nmi_32.h
@@ -0,0 +1,64 @@
+/*
+ *  linux/include/asm-i386/nmi.h
+ */
+#ifndef ASM_NMI_H
+#define ASM_NMI_H
+
+#include <linux/pm.h>
+#include <asm/irq.h>
+
+#ifdef ARCH_HAS_NMI_WATCHDOG
+
+/**
+ * do_nmi_callback
+ *
+ * Check to see if a callback exists and execute it.  Return 1
+ * if the handler exists and was handled successfully.
+ */
+int do_nmi_callback(struct pt_regs *regs, int cpu);
+
+extern int nmi_watchdog_enabled;
+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);
+extern void release_perfctr_nmi(unsigned int);
+extern int reserve_evntsel_nmi(unsigned int);
+extern void release_evntsel_nmi(unsigned int);
+
+extern void setup_apic_nmi_watchdog (void *);
+extern void stop_apic_nmi_watchdog (void *);
+extern void disable_timer_nmi_watchdog(void);
+extern void enable_timer_nmi_watchdog(void);
+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;
+extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
+                        void __user *, size_t *, loff_t *);
+extern int unknown_nmi_panic;
+
+void __trigger_all_cpu_backtrace(void);
+#define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
+
+#endif
+
+void lapic_watchdog_stop(void);
+int lapic_watchdog_init(unsigned nmi_hz);
+int lapic_wd_event(unsigned nmi_hz);
+unsigned lapic_adjust_nmi_hz(unsigned hz);
+int lapic_watchdog_ok(void);
+void disable_lapic_nmi_watchdog(void);
+void enable_lapic_nmi_watchdog(void);
+void stop_nmi(void);
+void restart_nmi(void);
+
+#endif /* ASM_NMI_H */
diff --git a/include/asm-x86/nmi_64.h b/include/asm-x86/nmi_64.h
new file mode 100644
index 000000000000..65b6acf3bb59
--- /dev/null
+++ b/include/asm-x86/nmi_64.h
@@ -0,0 +1,95 @@
+/*
+ *  linux/include/asm-i386/nmi.h
+ */
+#ifndef ASM_NMI_H
+#define ASM_NMI_H
+
+#include <linux/pm.h>
+#include <asm/io.h>
+ 
+/**
+ * do_nmi_callback
+ *
+ * Check to see if a callback exists and execute it.  Return 1
+ * if the handler exists and was handled successfully.
+ */
+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 */
+ 
+extern void default_do_nmi(struct pt_regs *);
+extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
+
+#define get_nmi_reason() inb(0x61)
+
+extern int panic_on_timeout;
+extern int unknown_nmi_panic;
+extern int nmi_watchdog_enabled;
+
+extern int check_nmi_watchdog(void);
+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);
+extern void release_perfctr_nmi(unsigned int);
+extern int reserve_evntsel_nmi(unsigned int);
+extern void release_evntsel_nmi(unsigned int);
+
+extern void setup_apic_nmi_watchdog (void *);
+extern void stop_apic_nmi_watchdog (void *);
+extern void disable_timer_nmi_watchdog(void);
+extern void enable_timer_nmi_watchdog(void);
+extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
+
+extern void nmi_watchdog_default(void);
+extern int setup_nmi_watchdog(char *);
+
+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;
+extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
+                        void __user *, size_t *, loff_t *);
+
+extern int unknown_nmi_panic;
+
+void __trigger_all_cpu_backtrace(void);
+#define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
+
+
+void lapic_watchdog_stop(void);
+int lapic_watchdog_init(unsigned nmi_hz);
+int lapic_wd_event(unsigned nmi_hz);
+unsigned lapic_adjust_nmi_hz(unsigned hz);
+int lapic_watchdog_ok(void);
+void disable_lapic_nmi_watchdog(void);
+void enable_lapic_nmi_watchdog(void);
+void stop_nmi(void);
+void restart_nmi(void);
+
+#endif /* ASM_NMI_H */
diff --git a/include/asm-x86/numa.h b/include/asm-x86/numa.h
new file mode 100644
index 000000000000..27da400d3138
--- /dev/null
+++ b/include/asm-x86/numa.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "numa_32.h"
+#else
+# include "numa_64.h"
+#endif
diff --git a/include/asm-x86/numa_32.h b/include/asm-x86/numa_32.h
new file mode 100644
index 000000000000..96fcb157db1d
--- /dev/null
+++ b/include/asm-x86/numa_32.h
@@ -0,0 +1,3 @@
+
+int pxm_to_nid(int pxm);
+
diff --git a/include/asm-x86/numa_64.h b/include/asm-x86/numa_64.h
new file mode 100644
index 000000000000..933ff11ece15
--- /dev/null
+++ b/include/asm-x86/numa_64.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_X8664_NUMA_H 
+#define _ASM_X8664_NUMA_H 1
+
+#include <linux/nodemask.h>
+
+struct bootnode {
+        u64 start,end; 
+};
+
+extern int compute_hash_shift(struct bootnode *nodes, int numnodes);
+
+#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 unsigned char apicid_to_node[256];
+#ifdef CONFIG_NUMA
+extern void __init init_cpu_to_node(void);
+
+static inline void clear_node_cpumask(int cpu)
+{
+        clear_bit(cpu, &node_to_cpumask[cpu_to_node(cpu)]);
+}
+
+#else
+#define init_cpu_to_node() do {} while (0)
+#define clear_node_cpumask(cpu) do {} while (0)
+#endif
+
+#define NUMA_NO_NODE 0xff
+
+#endif
diff --git a/include/asm-x86/numaq.h b/include/asm-x86/numaq.h
new file mode 100644
index 000000000000..38f710dc37f2
--- /dev/null
+++ b/include/asm-x86/numaq.h
@@ -0,0 +1,164 @@
+/*
+ * Written by: Patricia Gaughen, IBM Corporation
+ *
+ * Copyright (C) 2002, IBM Corp.
+ *
+ * All rights reserved.          
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gone@us.ibm.com>
+ */
+
+#ifndef NUMAQ_H
+#define NUMAQ_H
+
+#ifdef CONFIG_X86_NUMAQ
+
+extern int get_memcfg_numaq(void);
+
+/*
+ * SYS_CFG_DATA_PRIV_ADDR, struct eachquadmem, and struct sys_cfg_data are the
+ */
+#define SYS_CFG_DATA_PRIV_ADDR          0x0009d000 /* place for scd in private quad space */
+
+/*
+ * Communication area for each processor on lynxer-processor tests.
+ *
+ * NOTE: If you change the size of this eachproc structure you need
+ *       to change the definition for EACH_QUAD_SIZE.
+ */
+struct eachquadmem {
+        unsigned int    priv_mem_start;         /* Starting address of this */
+                                                /* quad's private memory. */
+                                                /* This is always 0. */
+                                                /* In MB. */
+        unsigned int    priv_mem_size;          /* Size of this quad's */
+                                                /* private memory. */
+                                                /* In MB. */
+        unsigned int    low_shrd_mem_strp_start;/* Starting address of this */
+                                                /* quad's low shared block */
+                                                /* (untranslated). */
+                                                /* In MB. */
+        unsigned int    low_shrd_mem_start;     /* Starting address of this */
+                                                /* quad's low shared memory */
+                                                /* (untranslated). */
+                                                /* In MB. */
+        unsigned int    low_shrd_mem_size;      /* Size of this quad's low */
+                                                /* shared memory. */
+                                                /* In MB. */
+        unsigned int    lmmio_copb_start;       /* Starting address of this */
+                                                /* quad's local memory */
+                                                /* mapped I/O in the */
+                                                /* compatibility OPB. */
+                                                /* In MB. */
+        unsigned int    lmmio_copb_size;        /* Size of this quad's local */
+                                                /* memory mapped I/O in the */
+                                                /* compatibility OPB. */
+                                                /* In MB. */
+        unsigned int    lmmio_nopb_start;       /* Starting address of this */
+                                                /* quad's local memory */
+                                                /* mapped I/O in the */
+                                                /* non-compatibility OPB. */
+                                                /* In MB. */
+        unsigned int    lmmio_nopb_size;        /* Size of this quad's local */
+                                                /* memory mapped I/O in the */
+                                                /* non-compatibility OPB. */
+                                                /* In MB. */
+        unsigned int    io_apic_0_start;        /* Starting address of I/O */
+                                                /* APIC 0. */
+        unsigned int    io_apic_0_sz;           /* Size I/O APIC 0. */
+        unsigned int    io_apic_1_start;        /* Starting address of I/O */
+                                                /* APIC 1. */
+        unsigned int    io_apic_1_sz;           /* Size I/O APIC 1. */
+        unsigned int    hi_shrd_mem_start;      /* Starting address of this */
+                                                /* quad's high shared memory.*/
+                                                /* In MB. */
+        unsigned int    hi_shrd_mem_size;       /* Size of this quad's high */
+                                                /* shared memory. */
+                                                /* In MB. */
+        unsigned int    mps_table_addr;         /* Address of this quad's */
+                                                /* MPS tables from BIOS, */
+                                                /* in system space.*/
+        unsigned int    lcl_MDC_pio_addr;       /* Port-I/O address for */
+                                                /* local access of MDC. */
+        unsigned int    rmt_MDC_mmpio_addr;     /* MM-Port-I/O address for */
+                                                /* remote access of MDC. */
+        unsigned int    mm_port_io_start;       /* Starting address of this */
+                                                /* quad's memory mapped Port */
+                                                /* I/O space. */
+        unsigned int    mm_port_io_size;        /* Size of this quad's memory*/
+                                                /* mapped Port I/O space. */
+        unsigned int    mm_rmt_io_apic_start;   /* Starting address of this */
+                                                /* quad's memory mapped */
+                                                /* remote I/O APIC space. */
+        unsigned int    mm_rmt_io_apic_size;    /* Size of this quad's memory*/
+                                                /* mapped remote I/O APIC */
+                                                /* space. */
+        unsigned int    mm_isa_start;           /* Starting address of this */
+                                                /* quad's memory mapped ISA */
+                                                /* space (contains MDC */
+                                                /* memory space). */
+        unsigned int    mm_isa_size;            /* Size of this quad's memory*/
+                                                /* mapped ISA space (contains*/
+                                                /* MDC memory space). */
+        unsigned int    rmt_qmi_addr;           /* Remote addr to access QMI.*/
+        unsigned int    lcl_qmi_addr;           /* Local addr to access QMI. */
+};
+
+/*
+ * Note: This structure must be NOT be changed unless the multiproc and
+ * OS are changed to reflect the new structure.
+ */
+struct sys_cfg_data {
+        unsigned int    quad_id;
+        unsigned int    bsp_proc_id; /* Boot Strap Processor in this quad. */
+        unsigned int    scd_version; /* Version number of this table. */
+        unsigned int    first_quad_id;
+        unsigned int    quads_present31_0; /* 1 bit for each quad */
+        unsigned int    quads_present63_32; /* 1 bit for each quad */
+        unsigned int    config_flags;
+        unsigned int    boot_flags;
+        unsigned int    csr_start_addr; /* Absolute value (not in MB) */
+        unsigned int    csr_size; /* Absolute value (not in MB) */
+        unsigned int    lcl_apic_start_addr; /* Absolute value (not in MB) */
+        unsigned int    lcl_apic_size; /* Absolute value (not in MB) */
+        unsigned int    low_shrd_mem_base; /* 0 or 512MB or 1GB */
+        unsigned int    low_shrd_mem_quad_offset; /* 0,128M,256M,512M,1G */
+                                        /* may not be totally populated */
+        unsigned int    split_mem_enbl; /* 0 for no low shared memory */ 
+        unsigned int    mmio_sz; /* Size of total system memory mapped I/O */
+                                 /* (in MB). */
+        unsigned int    quad_spin_lock; /* Spare location used for quad */
+                                        /* bringup. */
+        unsigned int    nonzero55; /* For checksumming. */
+        unsigned int    nonzeroaa; /* For checksumming. */
+        unsigned int    scd_magic_number;
+        unsigned int    system_type;
+        unsigned int    checksum;
+        /*
+         *      memory configuration area for each quad
+         */
+        struct  eachquadmem eq[MAX_NUMNODES];   /* indexed by quad id */
+};
+
+static inline unsigned long *get_zholes_size(int nid)
+{
+        return NULL;
+}
+#endif /* CONFIG_X86_NUMAQ */
+#endif /* NUMAQ_H */
+
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
new file mode 100644
index 000000000000..a757eb26141d
--- /dev/null
+++ b/include/asm-x86/page.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "page_32.h"
+# else
+#  include "page_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "page_32.h"
+# else
+#  include "page_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
new file mode 100644
index 000000000000..80ecc66b6d86
--- /dev/null
+++ b/include/asm-x86/page_32.h
@@ -0,0 +1,206 @@
+#ifndef _I386_PAGE_H
+#define _I386_PAGE_H
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT      12
+#define PAGE_SIZE       (1UL << PAGE_SHIFT)
+#define PAGE_MASK       (~(PAGE_SIZE-1))
+
+#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1))
+#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT)
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+#define clear_page(page)        mmx_clear_page((void *)(page))
+#define copy_page(to,from)      mmx_copy_page(to,from)
+
+#else
+
+/*
+ *      On older X86 processors it's not a win to use MMX here it seems.
+ *      Maybe the K6-III ?
+ */
+ 
+#define clear_page(page)        memset((void *)(page), 0, PAGE_SIZE)
+#define copy_page(to,from)      memcpy((void *)(to), (void *)(from), PAGE_SIZE)
+
+#endif
+
+#define clear_user_page(page, vaddr, pg)        clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
+
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+
+/*
+ * These are used to make use of C type-checking..
+ */
+extern int nx_enabled;
+
+#ifdef CONFIG_X86_PAE
+typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long long pmd; } pmd_t;
+typedef struct { unsigned long long pgd; } pgd_t;
+typedef struct { unsigned long long pgprot; } pgprot_t;
+
+static inline unsigned long long native_pgd_val(pgd_t pgd)
+{
+        return pgd.pgd;
+}
+
+static inline unsigned long long native_pmd_val(pmd_t pmd)
+{
+        return pmd.pmd;
+}
+
+static inline unsigned long long native_pte_val(pte_t pte)
+{
+        return pte.pte_low | ((unsigned long long)pte.pte_high << 32);
+}
+
+static inline pgd_t native_make_pgd(unsigned long long val)
+{
+        return (pgd_t) { val };
+}
+
+static inline pmd_t native_make_pmd(unsigned long long val)
+{
+        return (pmd_t) { val };
+}
+
+static inline pte_t native_make_pte(unsigned long long val)
+{
+        return (pte_t) { .pte_low = val, .pte_high = (val >> 32) } ;
+}
+
+#ifndef CONFIG_PARAVIRT
+#define pmd_val(x)      native_pmd_val(x)
+#define __pmd(x)        native_make_pmd(x)
+#endif
+
+#define HPAGE_SHIFT     21
+#include <asm-generic/pgtable-nopud.h>
+#else  /* !CONFIG_X86_PAE */
+typedef struct { unsigned long pte_low; } pte_t;
+typedef struct { unsigned long pgd; } pgd_t;
+typedef struct { unsigned long pgprot; } pgprot_t;
+#define boot_pte_t pte_t /* or would you rather have a typedef */
+
+static inline unsigned long native_pgd_val(pgd_t pgd)
+{
+        return pgd.pgd;
+}
+
+static inline unsigned long native_pte_val(pte_t pte)
+{
+        return pte.pte_low;
+}
+
+static inline pgd_t native_make_pgd(unsigned long val)
+{
+        return (pgd_t) { val };
+}
+
+static inline pte_t native_make_pte(unsigned long val)
+{
+        return (pte_t) { .pte_low = val };
+}
+
+#define HPAGE_SHIFT     22
+#include <asm-generic/pgtable-nopmd.h>
+#endif  /* CONFIG_X86_PAE */
+
+#define PTE_MASK        PAGE_MASK
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define HPAGE_SIZE      ((1UL) << HPAGE_SHIFT)
+#define HPAGE_MASK      (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
+
+#define pgprot_val(x)   ((x).pgprot)
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#ifndef CONFIG_PARAVIRT
+#define pgd_val(x)      native_pgd_val(x)
+#define __pgd(x)        native_make_pgd(x)
+#define pte_val(x)      native_pte_val(x)
+#define __pte(x)        native_make_pte(x)
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr)        (((addr)+PAGE_SIZE-1)&PAGE_MASK)
+
+/*
+ * This handles the memory map.. We could make this a config
+ * option, but too many people screw it up, and too few need
+ * it.
+ *
+ * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
+ * a virtual address space of one gigabyte, which limits the
+ * amount of physical memory you can use to about 950MB. 
+ *
+ * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
+ * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ */
+
+#ifndef __ASSEMBLY__
+
+struct vm_area_struct;
+
+/*
+ * This much address space is reserved for vmalloc() and iomap()
+ * as well as fixmap mappings.
+ */
+extern unsigned int __VMALLOC_RESERVE;
+
+extern int sysctl_legacy_va_layout;
+
+extern int page_is_ram(unsigned long pagenr);
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef __ASSEMBLY__
+#define __PAGE_OFFSET           CONFIG_PAGE_OFFSET
+#else
+#define __PAGE_OFFSET           ((unsigned long)CONFIG_PAGE_OFFSET)
+#endif
+
+
+#define PAGE_OFFSET             ((unsigned long)__PAGE_OFFSET)
+#define VMALLOC_RESERVE         ((unsigned long)__VMALLOC_RESERVE)
+#define MAXMEM                  (-__PAGE_OFFSET-__VMALLOC_RESERVE)
+#define __pa(x)                 ((unsigned long)(x)-PAGE_OFFSET)
+/* __pa_symbol should be used for C visible symbols.
+   This seems to be the official gcc blessed way to do such arithmetic. */
+#define __pa_symbol(x)          __pa(RELOC_HIDE((unsigned long)(x),0))
+#define __va(x)                 ((void *)((unsigned long)(x)+PAGE_OFFSET))
+#define pfn_to_kaddr(pfn)      __va((pfn) << PAGE_SHIFT)
+#ifdef CONFIG_FLATMEM
+#define pfn_valid(pfn)          ((pfn) < max_mapnr)
+#endif /* CONFIG_FLATMEM */
+#define virt_to_page(kaddr)     pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+
+#define virt_addr_valid(kaddr)  pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+
+#define VM_DATA_DEFAULT_FLAGS \
+        (VM_READ | VM_WRITE | \
+        ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+                 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/page.h>
+
+#define __HAVE_ARCH_GATE_AREA 1
+#endif /* __KERNEL__ */
+
+#endif /* _I386_PAGE_H */
diff --git a/include/asm-x86/page_64.h b/include/asm-x86/page_64.h
new file mode 100644
index 000000000000..88adf1afb0a2
--- /dev/null
+++ b/include/asm-x86/page_64.h
@@ -0,0 +1,143 @@
+#ifndef _X86_64_PAGE_H
+#define _X86_64_PAGE_H
+
+#include <linux/const.h>
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT      12
+#define PAGE_SIZE       (_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_MASK       (~(PAGE_SIZE-1))
+#define PHYSICAL_PAGE_MASK      (~(PAGE_SIZE-1) & __PHYSICAL_MASK)
+
+#define THREAD_ORDER 1 
+#define THREAD_SIZE  (PAGE_SIZE << THREAD_ORDER)
+#define CURRENT_MASK (~(THREAD_SIZE-1))
+
+#define EXCEPTION_STACK_ORDER 0
+#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
+
+#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
+#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
+
+#define IRQSTACK_ORDER 2
+#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
+
+#define STACKFAULT_STACK 1
+#define DOUBLEFAULT_STACK 2
+#define NMI_STACK 3
+#define DEBUG_STACK 4
+#define MCE_STACK 5
+#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
+
+#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1))
+#define LARGE_PAGE_SIZE (_AC(1,UL) << PMD_SHIFT)
+
+#define HPAGE_SHIFT PMD_SHIFT
+#define HPAGE_SIZE      (_AC(1,UL) << HPAGE_SHIFT)
+#define HPAGE_MASK      (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+extern unsigned long end_pfn;
+
+void clear_page(void *);
+void copy_page(void *, void *);
+
+#define clear_user_page(page, vaddr, pg)        clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
+
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+        alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { unsigned long pte; } pte_t;
+typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pud; } pud_t;
+typedef struct { unsigned long pgd; } pgd_t;
+#define PTE_MASK        PHYSICAL_PAGE_MASK
+
+typedef struct { unsigned long pgprot; } pgprot_t;
+
+extern unsigned long phys_base;
+
+#define pte_val(x)      ((x).pte)
+#define pmd_val(x)      ((x).pmd)
+#define pud_val(x)      ((x).pud)
+#define pgd_val(x)      ((x).pgd)
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x) ((pte_t) { (x) } )
+#define __pmd(x) ((pmd_t) { (x) } )
+#define __pud(x) ((pud_t) { (x) } )
+#define __pgd(x) ((pgd_t) { (x) } )
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#endif /* !__ASSEMBLY__ */
+
+#define __PHYSICAL_START        CONFIG_PHYSICAL_START
+#define __KERNEL_ALIGN          0x200000
+
+/*
+ * Make sure kernel is aligned to 2MB address. Catching it at compile
+ * time is better. Change your config file and compile the kernel
+ * for a 2MB aligned address (CONFIG_PHYSICAL_START)
+ */
+#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
+#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
+#endif
+
+#define __START_KERNEL          (__START_KERNEL_map + __PHYSICAL_START)
+#define __START_KERNEL_map      _AC(0xffffffff80000000, UL)
+#define __PAGE_OFFSET           _AC(0xffff810000000000, UL)
+
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr)        (((addr)+PAGE_SIZE-1)&PAGE_MASK)
+
+/* See Documentation/x86_64/mm.txt for a description of the memory map. */
+#define __PHYSICAL_MASK_SHIFT   46
+#define __PHYSICAL_MASK         ((_AC(1,UL) << __PHYSICAL_MASK_SHIFT) - 1)
+#define __VIRTUAL_MASK_SHIFT    48
+#define __VIRTUAL_MASK          ((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - 1)
+
+#define KERNEL_TEXT_SIZE  (40*1024*1024)
+#define KERNEL_TEXT_START _AC(0xffffffff80000000, UL)
+#define PAGE_OFFSET             __PAGE_OFFSET
+
+#ifndef __ASSEMBLY__
+
+#include <asm/bug.h>
+
+extern unsigned long __phys_addr(unsigned long);
+
+#endif /* __ASSEMBLY__ */
+
+#define __pa(x)         __phys_addr((unsigned long)(x))
+#define __pa_symbol(x)  __phys_addr((unsigned long)(x))
+
+#define __va(x)                 ((void *)((unsigned long)(x)+PAGE_OFFSET))
+#define __boot_va(x)            __va(x)
+#define __boot_pa(x)            __pa(x)
+#ifdef CONFIG_FLATMEM
+#define pfn_valid(pfn)          ((pfn) < end_pfn)
+#endif
+
+#define virt_to_page(kaddr)     pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define virt_addr_valid(kaddr)  pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define pfn_to_kaddr(pfn)      __va((pfn) << PAGE_SHIFT)
+
+#define VM_DATA_DEFAULT_FLAGS \
+        (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+         VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#define __HAVE_ARCH_GATE_AREA 1 
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/page.h>
+
+#endif /* __KERNEL__ */
+
+#endif /* _X86_64_PAGE_H */
diff --git a/include/asm-x86/param.h b/include/asm-x86/param.h
new file mode 100644
index 000000000000..640851bab124
--- /dev/null
+++ b/include/asm-x86/param.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "param_32.h"
+# else
+#  include "param_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "param_32.h"
+# else
+#  include "param_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/param_32.h b/include/asm-x86/param_32.h
new file mode 100644
index 000000000000..21b32466fcdc
--- /dev/null
+++ b/include/asm-x86/param_32.h
@@ -0,0 +1,22 @@
+#ifndef _ASMi386_PARAM_H
+#define _ASMi386_PARAM_H
+
+#ifdef __KERNEL__
+# define HZ             CONFIG_HZ       /* Internal kernel timer frequency */
+# define USER_HZ        100             /* .. some user interfaces are in "ticks" */
+# define CLOCKS_PER_SEC         (USER_HZ)       /* like times() */
+#endif
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE   4096
+
+#ifndef NOGROUP
+#define NOGROUP         (-1)
+#endif
+
+#define MAXHOSTNAMELEN  64      /* max length of hostname */
+
+#endif
diff --git a/include/asm-x86/param_64.h b/include/asm-x86/param_64.h
new file mode 100644
index 000000000000..a728786c3c7c
--- /dev/null
+++ b/include/asm-x86/param_64.h
@@ -0,0 +1,22 @@
+#ifndef _ASMx86_64_PARAM_H
+#define _ASMx86_64_PARAM_H
+
+#ifdef __KERNEL__
+# define HZ            CONFIG_HZ        /* Internal kernel timer frequency */
+# define USER_HZ       100              /* .. some user interfaces are in "ticks */
+#define CLOCKS_PER_SEC        (USER_HZ)       /* like times() */
+#endif
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE   4096
+
+#ifndef NOGROUP
+#define NOGROUP         (-1)
+#endif
+
+#define MAXHOSTNAMELEN  64      /* max length of hostname */
+
+#endif
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
new file mode 100644
index 000000000000..9fa3fa9e62d1
--- /dev/null
+++ b/include/asm-x86/paravirt.h
@@ -0,0 +1,1085 @@
+#ifndef __ASM_PARAVIRT_H
+#define __ASM_PARAVIRT_H
+/* Various instructions on x86 need to be replaced for
+ * para-virtualization: those hooks are defined here. */
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/page.h>
+
+/* Bitmask of what can be clobbered: usually at least eax. */
+#define CLBR_NONE 0x0
+#define CLBR_EAX 0x1
+#define CLBR_ECX 0x2
+#define CLBR_EDX 0x4
+#define CLBR_ANY 0x7
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#include <linux/cpumask.h>
+#include <asm/kmap_types.h>
+
+struct page;
+struct thread_struct;
+struct Xgt_desc_struct;
+struct tss_struct;
+struct mm_struct;
+struct desc_struct;
+
+/* Lazy mode for batching updates / context switch */
+enum paravirt_lazy_mode {
+        PARAVIRT_LAZY_NONE = 0,
+        PARAVIRT_LAZY_MMU = 1,
+        PARAVIRT_LAZY_CPU = 2,
+        PARAVIRT_LAZY_FLUSH = 3,
+};
+
+struct paravirt_ops
+{
+        unsigned int kernel_rpl;
+        int shared_kernel_pmd;
+        int paravirt_enabled;
+        const char *name;
+
+        /*
+         * Patch may replace one of the defined code sequences with arbitrary
+         * code, subject to the same register constraints.  This generally
+         * means the code is not free to clobber any registers other than EAX.
+         * The patch function should return the number of bytes of code
+         * generated, as we nop pad the rest in generic code.
+         */
+        unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
+                          unsigned long addr, unsigned len);
+
+        /* Basic arch-specific setup */
+        void (*arch_setup)(void);
+        char *(*memory_setup)(void);
+        void (*post_allocator_init)(void);
+
+        void (*init_IRQ)(void);
+        void (*time_init)(void);
+
+        /*
+         * Called before/after init_mm pagetable setup. setup_start
+         * may reset %cr3, and may pre-install parts of the pagetable;
+         * pagetable setup is expected to preserve any existing
+         * mapping.
+         */
+        void (*pagetable_setup_start)(pgd_t *pgd_base);
+        void (*pagetable_setup_done)(pgd_t *pgd_base);
+
+        /* Print a banner to identify the environment */
+        void (*banner)(void);
+
+        /* Set and set time of day */
+        unsigned long (*get_wallclock)(void);
+        int (*set_wallclock)(unsigned long);
+
+        /* cpuid emulation, mostly so that caps bits can be disabled */
+        void (*cpuid)(unsigned int *eax, unsigned int *ebx,
+                      unsigned int *ecx, unsigned int *edx);
+
+        /* hooks for various privileged instructions */
+        unsigned long (*get_debugreg)(int regno);
+        void (*set_debugreg)(int regno, unsigned long value);
+
+        void (*clts)(void);
+
+        unsigned long (*read_cr0)(void);
+        void (*write_cr0)(unsigned long);
+
+        unsigned long (*read_cr2)(void);
+        void (*write_cr2)(unsigned long);
+
+        unsigned long (*read_cr3)(void);
+        void (*write_cr3)(unsigned long);
+
+        unsigned long (*read_cr4_safe)(void);
+        unsigned long (*read_cr4)(void);
+        void (*write_cr4)(unsigned long);
+
+        /*
+         * Get/set interrupt state.  save_fl and restore_fl are only
+         * expected to use X86_EFLAGS_IF; all other bits
+         * returned from save_fl are undefined, and may be ignored by
+         * restore_fl.
+         */
+        unsigned long (*save_fl)(void);
+        void (*restore_fl)(unsigned long);
+        void (*irq_disable)(void);
+        void (*irq_enable)(void);
+        void (*safe_halt)(void);
+        void (*halt)(void);
+
+        void (*wbinvd)(void);
+
+        /* MSR, PMC and TSR operations.
+           err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
+        u64 (*read_msr)(unsigned int msr, int *err);
+        int (*write_msr)(unsigned int msr, u64 val);
+
+        u64 (*read_tsc)(void);
+        u64 (*read_pmc)(void);
+        unsigned long long (*sched_clock)(void);
+        unsigned long (*get_cpu_khz)(void);
+
+        /* Segment descriptor handling */
+        void (*load_tr_desc)(void);
+        void (*load_gdt)(const struct Xgt_desc_struct *);
+        void (*load_idt)(const struct Xgt_desc_struct *);
+        void (*store_gdt)(struct Xgt_desc_struct *);
+        void (*store_idt)(struct Xgt_desc_struct *);
+        void (*set_ldt)(const void *desc, unsigned entries);
+        unsigned long (*store_tr)(void);
+        void (*load_tls)(struct thread_struct *t, unsigned int cpu);
+        void (*write_ldt_entry)(struct desc_struct *,
+                                int entrynum, u32 low, u32 high);
+        void (*write_gdt_entry)(struct desc_struct *,
+                                int entrynum, u32 low, u32 high);
+        void (*write_idt_entry)(struct desc_struct *,
+                                int entrynum, u32 low, u32 high);
+        void (*load_esp0)(struct tss_struct *tss, struct thread_struct *t);
+
+        void (*set_iopl_mask)(unsigned mask);
+        void (*io_delay)(void);
+
+        /*
+         * Hooks for intercepting the creation/use/destruction of an
+         * mm_struct.
+         */
+        void (*activate_mm)(struct mm_struct *prev,
+                            struct mm_struct *next);
+        void (*dup_mmap)(struct mm_struct *oldmm,
+                         struct mm_struct *mm);
+        void (*exit_mmap)(struct mm_struct *mm);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+        /*
+         * Direct APIC operations, principally for VMI.  Ideally
+         * these shouldn't be in this interface.
+         */
+        void (*apic_write)(unsigned long reg, unsigned long v);
+        void (*apic_write_atomic)(unsigned long reg, unsigned long v);
+        unsigned long (*apic_read)(unsigned long reg);
+        void (*setup_boot_clock)(void);
+        void (*setup_secondary_clock)(void);
+
+        void (*startup_ipi_hook)(int phys_apicid,
+                                 unsigned long start_eip,
+                                 unsigned long start_esp);
+#endif
+
+        /* TLB operations */
+        void (*flush_tlb_user)(void);
+        void (*flush_tlb_kernel)(void);
+        void (*flush_tlb_single)(unsigned long addr);
+        void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
+                                 unsigned long va);
+
+        /* Hooks for allocating/releasing pagetable pages */
+        void (*alloc_pt)(struct mm_struct *mm, u32 pfn);
+        void (*alloc_pd)(u32 pfn);
+        void (*alloc_pd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count);
+        void (*release_pt)(u32 pfn);
+        void (*release_pd)(u32 pfn);
+
+        /* Pagetable manipulation functions */
+        void (*set_pte)(pte_t *ptep, pte_t pteval);
+        void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
+                           pte_t *ptep, pte_t pteval);
+        void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
+        void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+        void (*pte_update_defer)(struct mm_struct *mm,
+                                 unsigned long addr, pte_t *ptep);
+
+#ifdef CONFIG_HIGHPTE
+        void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
+#endif
+
+#ifdef CONFIG_X86_PAE
+        void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
+        void (*set_pte_present)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+        void (*set_pud)(pud_t *pudp, pud_t pudval);
+        void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+        void (*pmd_clear)(pmd_t *pmdp);
+
+        unsigned long long (*pte_val)(pte_t);
+        unsigned long long (*pmd_val)(pmd_t);
+        unsigned long long (*pgd_val)(pgd_t);
+
+        pte_t (*make_pte)(unsigned long long pte);
+        pmd_t (*make_pmd)(unsigned long long pmd);
+        pgd_t (*make_pgd)(unsigned long long pgd);
+#else
+        unsigned long (*pte_val)(pte_t);
+        unsigned long (*pgd_val)(pgd_t);
+
+        pte_t (*make_pte)(unsigned long pte);
+        pgd_t (*make_pgd)(unsigned long pgd);
+#endif
+
+        /* Set deferred update mode, used for batching operations. */
+        void (*set_lazy_mode)(enum paravirt_lazy_mode mode);
+
+        /* These two are jmp to, not actually called. */
+        void (*irq_enable_sysexit)(void);
+        void (*iret)(void);
+};
+
+extern struct paravirt_ops paravirt_ops;
+
+#define PARAVIRT_PATCH(x)                                       \
+        (offsetof(struct paravirt_ops, x) / sizeof(void *))
+
+#define paravirt_type(type)                                     \
+        [paravirt_typenum] "i" (PARAVIRT_PATCH(type))
+#define paravirt_clobber(clobber)               \
+        [paravirt_clobber] "i" (clobber)
+
+/*
+ * Generate some code, and mark it as patchable by the
+ * apply_paravirt() alternate instruction patcher.
+ */
+#define _paravirt_alt(insn_string, type, clobber)       \
+        "771:\n\t" insn_string "\n" "772:\n"            \
+        ".pushsection .parainstructions,\"a\"\n"        \
+        "  .long 771b\n"                                \
+        "  .byte " type "\n"                            \
+        "  .byte 772b-771b\n"                           \
+        "  .short " clobber "\n"                        \
+        ".popsection\n"
+
+/* Generate patchable code, with the default asm parameters. */
+#define paravirt_alt(insn_string)                                       \
+        _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
+
+unsigned paravirt_patch_nop(void);
+unsigned paravirt_patch_ignore(unsigned len);
+unsigned paravirt_patch_call(void *insnbuf,
+                             const void *target, u16 tgt_clobbers,
+                             unsigned long addr, u16 site_clobbers,
+                             unsigned len);
+unsigned paravirt_patch_jmp(const void *target, void *insnbuf,
+                            unsigned long addr, unsigned len);
+unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
+                                unsigned long addr, unsigned len);
+
+unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
+                              const char *start, const char *end);
+
+int paravirt_disable_iospace(void);
+
+/*
+ * This generates an indirect call based on the operation type number.
+ * The type number, computed in PARAVIRT_PATCH, is derived from the
+ * offset into the paravirt_ops structure, and can therefore be freely
+ * converted back into a structure offset.
+ */
+#define PARAVIRT_CALL   "call *(paravirt_ops+%c[paravirt_typenum]*4);"
+
+/*
+ * These macros are intended to wrap calls into a paravirt_ops
+ * operation, so that they can be later identified and patched at
+ * runtime.
+ *
+ * Normally, a call to a pv_op function is a simple indirect call:
+ * (paravirt_ops.operations)(args...).
+ *
+ * Unfortunately, this is a relatively slow operation for modern CPUs,
+ * because it cannot necessarily determine what the destination
+ * address is.  In this case, the address is a runtime constant, so at
+ * the very least we can patch the call to e a simple direct call, or
+ * ideally, patch an inline implementation into the callsite.  (Direct
+ * calls are essentially free, because the call and return addresses
+ * are completely predictable.)
+ *
+ * These macros rely on the standard gcc "regparm(3)" calling
+ * convention, in which the first three arguments are placed in %eax,
+ * %edx, %ecx (in that order), and the remaining arguments are placed
+ * on the stack.  All caller-save registers (eax,edx,ecx) are expected
+ * to be modified (either clobbered or used for return values).
+ *
+ * The call instruction itself is marked by placing its start address
+ * and size into the .parainstructions section, so that
+ * apply_paravirt() in arch/i386/kernel/alternative.c can do the
+ * appropriate patching under the control of the backend paravirt_ops
+ * implementation.
+ *
+ * Unfortunately there's no way to get gcc to generate the args setup
+ * for the call, and then allow the call itself to be generated by an
+ * inline asm.  Because of this, we must do the complete arg setup and
+ * return value handling from within these macros.  This is fairly
+ * cumbersome.
+ *
+ * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments.
+ * It could be extended to more arguments, but there would be little
+ * to be gained from that.  For each number of arguments, there are
+ * the two VCALL and CALL variants for void and non-void functions.
+ *
+ * When there is a return value, the invoker of the macro must specify
+ * the return type.  The macro then uses sizeof() on that type to
+ * determine whether its a 32 or 64 bit value, and places the return
+ * in the right register(s) (just %eax for 32-bit, and %edx:%eax for
+ * 64-bit).
+ *
+ * 64-bit arguments are passed as a pair of adjacent 32-bit arguments
+ * in low,high order.
+ *
+ * Small structures are passed and returned in registers.  The macro
+ * calling convention can't directly deal with this, so the wrapper
+ * functions must do this.
+ *
+ * These PVOP_* macros are only defined within this header.  This
+ * means that all uses must be wrapped in inline functions.  This also
+ * makes sure the incoming and outgoing types are always correct.
+ */
+#define __PVOP_CALL(rettype, op, pre, post, ...)                        \
+        ({                                                              \
+                rettype __ret;                                          \
+                unsigned long __eax, __edx, __ecx;                      \
+                if (sizeof(rettype) > sizeof(unsigned long)) {          \
+                        asm volatile(pre                                \
+                                     paravirt_alt(PARAVIRT_CALL)        \
+                                     post                               \
+                                     : "=a" (__eax), "=d" (__edx),      \
+                                       "=c" (__ecx)                     \
+                                     : paravirt_type(op),               \
+                                       paravirt_clobber(CLBR_ANY),      \
+                                       ##__VA_ARGS__                    \
+                                     : "memory", "cc");                 \
+                        __ret = (rettype)((((u64)__edx) << 32) | __eax); \
+                } else {                                                \
+                        asm volatile(pre                                \
+                                     paravirt_alt(PARAVIRT_CALL)        \
+                                     post                               \
+                                     : "=a" (__eax), "=d" (__edx),      \
+                                       "=c" (__ecx)                     \
+                                     : paravirt_type(op),               \
+                                       paravirt_clobber(CLBR_ANY),      \
+                                       ##__VA_ARGS__                    \
+                                     : "memory", "cc");                 \
+                        __ret = (rettype)__eax;                         \
+                }                                                       \
+                __ret;                                                  \
+        })
+#define __PVOP_VCALL(op, pre, post, ...)                                \
+        ({                                                              \
+                unsigned long __eax, __edx, __ecx;                      \
+                asm volatile(pre                                        \
+                             paravirt_alt(PARAVIRT_CALL)                \
+                             post                                       \
+                             : "=a" (__eax), "=d" (__edx), "=c" (__ecx) \
+                             : paravirt_type(op),                       \
+                               paravirt_clobber(CLBR_ANY),              \
+                               ##__VA_ARGS__                            \
+                             : "memory", "cc");                         \
+        })
+
+#define PVOP_CALL0(rettype, op)                                         \
+        __PVOP_CALL(rettype, op, "", "")
+#define PVOP_VCALL0(op)                                                 \
+        __PVOP_VCALL(op, "", "")
+
+#define PVOP_CALL1(rettype, op, arg1)                                   \
+        __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1)))
+#define PVOP_VCALL1(op, arg1)                                           \
+        __PVOP_VCALL(op, "", "", "0" ((u32)(arg1)))
+
+#define PVOP_CALL2(rettype, op, arg1, arg2)                             \
+        __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1)), "1" ((u32)(arg2)))
+#define PVOP_VCALL2(op, arg1, arg2)                                     \
+        __PVOP_VCALL(op, "", "", "0" ((u32)(arg1)), "1" ((u32)(arg2)))
+
+#define PVOP_CALL3(rettype, op, arg1, arg2, arg3)                       \
+        __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1)),             \
+                    "1"((u32)(arg2)), "2"((u32)(arg3)))
+#define PVOP_VCALL3(op, arg1, arg2, arg3)                               \
+        __PVOP_VCALL(op, "", "", "0" ((u32)(arg1)), "1"((u32)(arg2)),   \
+                     "2"((u32)(arg3)))
+
+#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)                 \
+        __PVOP_CALL(rettype, op,                                        \
+                    "push %[_arg4];", "lea 4(%%esp),%%esp;",            \
+                    "0" ((u32)(arg1)), "1" ((u32)(arg2)),               \
+                    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)                         \
+        __PVOP_VCALL(op,                                                \
+                    "push %[_arg4];", "lea 4(%%esp),%%esp;",            \
+                    "0" ((u32)(arg1)), "1" ((u32)(arg2)),               \
+                    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+
+static inline int paravirt_enabled(void)
+{
+        return paravirt_ops.paravirt_enabled;
+}
+
+static inline void load_esp0(struct tss_struct *tss,
+                             struct thread_struct *thread)
+{
+        PVOP_VCALL2(load_esp0, tss, thread);
+}
+
+#define ARCH_SETUP                      paravirt_ops.arch_setup();
+static inline unsigned long get_wallclock(void)
+{
+        return PVOP_CALL0(unsigned long, get_wallclock);
+}
+
+static inline int set_wallclock(unsigned long nowtime)
+{
+        return PVOP_CALL1(int, set_wallclock, nowtime);
+}
+
+static inline void (*choose_time_init(void))(void)
+{
+        return paravirt_ops.time_init;
+}
+
+/* The paravirtualized CPUID instruction. */
+static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
+                           unsigned int *ecx, unsigned int *edx)
+{
+        PVOP_VCALL4(cpuid, eax, ebx, ecx, edx);
+}
+
+/*
+ * These special macros can be used to get or set a debugging register
+ */
+static inline unsigned long paravirt_get_debugreg(int reg)
+{
+        return PVOP_CALL1(unsigned long, get_debugreg, reg);
+}
+#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
+static inline void set_debugreg(unsigned long val, int reg)
+{
+        PVOP_VCALL2(set_debugreg, reg, val);
+}
+
+static inline void clts(void)
+{
+        PVOP_VCALL0(clts);
+}
+
+static inline unsigned long read_cr0(void)
+{
+        return PVOP_CALL0(unsigned long, read_cr0);
+}
+
+static inline void write_cr0(unsigned long x)
+{
+        PVOP_VCALL1(write_cr0, x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+        return PVOP_CALL0(unsigned long, read_cr2);
+}
+
+static inline void write_cr2(unsigned long x)
+{
+        PVOP_VCALL1(write_cr2, x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+        return PVOP_CALL0(unsigned long, read_cr3);
+}
+
+static inline void write_cr3(unsigned long x)
+{
+        PVOP_VCALL1(write_cr3, x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+        return PVOP_CALL0(unsigned long, read_cr4);
+}
+static inline unsigned long read_cr4_safe(void)
+{
+        return PVOP_CALL0(unsigned long, read_cr4_safe);
+}
+
+static inline void write_cr4(unsigned long x)
+{
+        PVOP_VCALL1(write_cr4, x);
+}
+
+static inline void raw_safe_halt(void)
+{
+        PVOP_VCALL0(safe_halt);
+}
+
+static inline void halt(void)
+{
+        PVOP_VCALL0(safe_halt);
+}
+
+static inline void wbinvd(void)
+{
+        PVOP_VCALL0(wbinvd);
+}
+
+#define get_kernel_rpl()  (paravirt_ops.kernel_rpl)
+
+static inline u64 paravirt_read_msr(unsigned msr, int *err)
+{
+        return PVOP_CALL2(u64, read_msr, msr, err);
+}
+static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
+{
+        return PVOP_CALL3(int, write_msr, msr, low, high);
+}
+
+/* These should all do BUG_ON(_err), but our headers are too tangled. */
+#define rdmsr(msr,val1,val2) do {               \
+        int _err;                               \
+        u64 _l = paravirt_read_msr(msr, &_err); \
+        val1 = (u32)_l;                         \
+        val2 = _l >> 32;                        \
+} while(0)
+
+#define wrmsr(msr,val1,val2) do {               \
+        paravirt_write_msr(msr, val1, val2);    \
+} while(0)
+
+#define rdmsrl(msr,val) do {                    \
+        int _err;                               \
+        val = paravirt_read_msr(msr, &_err);    \
+} while(0)
+
+#define wrmsrl(msr,val)         wrmsr(msr, (u32)((u64)(val)), ((u64)(val))>>32)
+#define wrmsr_safe(msr,a,b)     paravirt_write_msr(msr, a, b)
+
+/* rdmsr with exception handling */
+#define rdmsr_safe(msr,a,b) ({                  \
+        int _err;                               \
+        u64 _l = paravirt_read_msr(msr, &_err); \
+        (*a) = (u32)_l;                         \
+        (*b) = _l >> 32;                        \
+        _err; })
+
+
+static inline u64 paravirt_read_tsc(void)
+{
+        return PVOP_CALL0(u64, read_tsc);
+}
+
+#define rdtscl(low) do {                        \
+        u64 _l = paravirt_read_tsc();           \
+        low = (int)_l;                          \
+} while(0)
+
+#define rdtscll(val) (val = paravirt_read_tsc())
+
+static inline unsigned long long paravirt_sched_clock(void)
+{
+        return PVOP_CALL0(unsigned long long, sched_clock);
+}
+#define calculate_cpu_khz() (paravirt_ops.get_cpu_khz())
+
+#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
+
+static inline unsigned long long paravirt_read_pmc(int counter)
+{
+        return PVOP_CALL1(u64, read_pmc, counter);
+}
+
+#define rdpmc(counter,low,high) do {            \
+        u64 _l = paravirt_read_pmc(counter);    \
+        low = (u32)_l;                          \
+        high = _l >> 32;                        \
+} while(0)
+
+static inline void load_TR_desc(void)
+{
+        PVOP_VCALL0(load_tr_desc);
+}
+static inline void load_gdt(const struct Xgt_desc_struct *dtr)
+{
+        PVOP_VCALL1(load_gdt, dtr);
+}
+static inline void load_idt(const struct Xgt_desc_struct *dtr)
+{
+        PVOP_VCALL1(load_idt, dtr);
+}
+static inline void set_ldt(const void *addr, unsigned entries)
+{
+        PVOP_VCALL2(set_ldt, addr, entries);
+}
+static inline void store_gdt(struct Xgt_desc_struct *dtr)
+{
+        PVOP_VCALL1(store_gdt, dtr);
+}
+static inline void store_idt(struct Xgt_desc_struct *dtr)
+{
+        PVOP_VCALL1(store_idt, dtr);
+}
+static inline unsigned long paravirt_store_tr(void)
+{
+        return PVOP_CALL0(unsigned long, store_tr);
+}
+#define store_tr(tr)    ((tr) = paravirt_store_tr())
+static inline void load_TLS(struct thread_struct *t, unsigned cpu)
+{
+        PVOP_VCALL2(load_tls, t, cpu);
+}
+static inline void write_ldt_entry(void *dt, int entry, u32 low, u32 high)
+{
+        PVOP_VCALL4(write_ldt_entry, dt, entry, low, high);
+}
+static inline void write_gdt_entry(void *dt, int entry, u32 low, u32 high)
+{
+        PVOP_VCALL4(write_gdt_entry, dt, entry, low, high);
+}
+static inline void write_idt_entry(void *dt, int entry, u32 low, u32 high)
+{
+        PVOP_VCALL4(write_idt_entry, dt, entry, low, high);
+}
+static inline void set_iopl_mask(unsigned mask)
+{
+        PVOP_VCALL1(set_iopl_mask, mask);
+}
+
+/* The paravirtualized I/O functions */
+static inline void slow_down_io(void) {
+        paravirt_ops.io_delay();
+#ifdef REALLY_SLOW_IO
+        paravirt_ops.io_delay();
+        paravirt_ops.io_delay();
+        paravirt_ops.io_delay();
+#endif
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+/*
+ * Basic functions accessing APICs.
+ */
+static inline void apic_write(unsigned long reg, unsigned long v)
+{
+        PVOP_VCALL2(apic_write, reg, v);
+}
+
+static inline void apic_write_atomic(unsigned long reg, unsigned long v)
+{
+        PVOP_VCALL2(apic_write_atomic, reg, v);
+}
+
+static inline unsigned long apic_read(unsigned long reg)
+{
+        return PVOP_CALL1(unsigned long, apic_read, reg);
+}
+
+static inline void setup_boot_clock(void)
+{
+        PVOP_VCALL0(setup_boot_clock);
+}
+
+static inline void setup_secondary_clock(void)
+{
+        PVOP_VCALL0(setup_secondary_clock);
+}
+#endif
+
+static inline void paravirt_post_allocator_init(void)
+{
+        if (paravirt_ops.post_allocator_init)
+                (*paravirt_ops.post_allocator_init)();
+}
+
+static inline void paravirt_pagetable_setup_start(pgd_t *base)
+{
+        if (paravirt_ops.pagetable_setup_start)
+                (*paravirt_ops.pagetable_setup_start)(base);
+}
+
+static inline void paravirt_pagetable_setup_done(pgd_t *base)
+{
+        if (paravirt_ops.pagetable_setup_done)
+                (*paravirt_ops.pagetable_setup_done)(base);
+}
+
+#ifdef CONFIG_SMP
+static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
+                                    unsigned long start_esp)
+{
+        PVOP_VCALL3(startup_ipi_hook, phys_apicid, start_eip, start_esp);
+}
+#endif
+
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+                                        struct mm_struct *next)
+{
+        PVOP_VCALL2(activate_mm, prev, next);
+}
+
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+                                 struct mm_struct *mm)
+{
+        PVOP_VCALL2(dup_mmap, oldmm, mm);
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+        PVOP_VCALL1(exit_mmap, mm);
+}
+
+static inline void __flush_tlb(void)
+{
+        PVOP_VCALL0(flush_tlb_user);
+}
+static inline void __flush_tlb_global(void)
+{
+        PVOP_VCALL0(flush_tlb_kernel);
+}
+static inline void __flush_tlb_single(unsigned long addr)
+{
+        PVOP_VCALL1(flush_tlb_single, addr);
+}
+
+static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+                                    unsigned long va)
+{
+        PVOP_VCALL3(flush_tlb_others, &cpumask, mm, va);
+}
+
+static inline void paravirt_alloc_pt(struct mm_struct *mm, unsigned pfn)
+{
+        PVOP_VCALL2(alloc_pt, mm, pfn);
+}
+static inline void paravirt_release_pt(unsigned pfn)
+{
+        PVOP_VCALL1(release_pt, pfn);
+}
+
+static inline void paravirt_alloc_pd(unsigned pfn)
+{
+        PVOP_VCALL1(alloc_pd, pfn);
+}
+
+static inline void paravirt_alloc_pd_clone(unsigned pfn, unsigned clonepfn,
+                                           unsigned start, unsigned count)
+{
+        PVOP_VCALL4(alloc_pd_clone, pfn, clonepfn, start, count);
+}
+static inline void paravirt_release_pd(unsigned pfn)
+{
+        PVOP_VCALL1(release_pd, pfn);
+}
+
+#ifdef CONFIG_HIGHPTE
+static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
+{
+        unsigned long ret;
+        ret = PVOP_CALL2(unsigned long, kmap_atomic_pte, page, type);
+        return (void *)ret;
+}
+#endif
+
+static inline void pte_update(struct mm_struct *mm, unsigned long addr,
+                              pte_t *ptep)
+{
+        PVOP_VCALL3(pte_update, mm, addr, ptep);
+}
+
+static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
+                                    pte_t *ptep)
+{
+        PVOP_VCALL3(pte_update_defer, mm, addr, ptep);
+}
+
+#ifdef CONFIG_X86_PAE
+static inline pte_t __pte(unsigned long long val)
+{
+        unsigned long long ret = PVOP_CALL2(unsigned long long, make_pte,
+                                            val, val >> 32);
+        return (pte_t) { ret, ret >> 32 };
+}
+
+static inline pmd_t __pmd(unsigned long long val)
+{
+        return (pmd_t) { PVOP_CALL2(unsigned long long, make_pmd, val, val >> 32) };
+}
+
+static inline pgd_t __pgd(unsigned long long val)
+{
+        return (pgd_t) { PVOP_CALL2(unsigned long long, make_pgd, val, val >> 32) };
+}
+
+static inline unsigned long long pte_val(pte_t x)
+{
+        return PVOP_CALL2(unsigned long long, pte_val, x.pte_low, x.pte_high);
+}
+
+static inline unsigned long long pmd_val(pmd_t x)
+{
+        return PVOP_CALL2(unsigned long long, pmd_val, x.pmd, x.pmd >> 32);
+}
+
+static inline unsigned long long pgd_val(pgd_t x)
+{
+        return PVOP_CALL2(unsigned long long, pgd_val, x.pgd, x.pgd >> 32);
+}
+
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+        PVOP_VCALL3(set_pte, ptep, pteval.pte_low, pteval.pte_high);
+}
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+                              pte_t *ptep, pte_t pteval)
+{
+        /* 5 arg words */
+        paravirt_ops.set_pte_at(mm, addr, ptep, pteval);
+}
+
+static inline void set_pte_atomic(pte_t *ptep, pte_t pteval)
+{
+        PVOP_VCALL3(set_pte_atomic, ptep, pteval.pte_low, pteval.pte_high);
+}
+
+static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
+                                   pte_t *ptep, pte_t pte)
+{
+        /* 5 arg words */
+        paravirt_ops.set_pte_present(mm, addr, ptep, pte);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval)
+{
+        PVOP_VCALL3(set_pmd, pmdp, pmdval.pmd, pmdval.pmd >> 32);
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pudval)
+{
+        PVOP_VCALL3(set_pud, pudp, pudval.pgd.pgd, pudval.pgd.pgd >> 32);
+}
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+        PVOP_VCALL3(pte_clear, mm, addr, ptep);
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+        PVOP_VCALL1(pmd_clear, pmdp);
+}
+
+#else  /* !CONFIG_X86_PAE */
+
+static inline pte_t __pte(unsigned long val)
+{
+        return (pte_t) { PVOP_CALL1(unsigned long, make_pte, val) };
+}
+
+static inline pgd_t __pgd(unsigned long val)
+{
+        return (pgd_t) { PVOP_CALL1(unsigned long, make_pgd, val) };
+}
+
+static inline unsigned long pte_val(pte_t x)
+{
+        return PVOP_CALL1(unsigned long, pte_val, x.pte_low);
+}
+
+static inline unsigned long pgd_val(pgd_t x)
+{
+        return PVOP_CALL1(unsigned long, pgd_val, x.pgd);
+}
+
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+        PVOP_VCALL2(set_pte, ptep, pteval.pte_low);
+}
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+                              pte_t *ptep, pte_t pteval)
+{
+        PVOP_VCALL4(set_pte_at, mm, addr, ptep, pteval.pte_low);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval)
+{
+        PVOP_VCALL2(set_pmd, pmdp, pmdval.pud.pgd.pgd);
+}
+#endif  /* CONFIG_X86_PAE */
+
+#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
+static inline void arch_enter_lazy_cpu_mode(void)
+{
+        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_CPU);
+}
+
+static inline void arch_leave_lazy_cpu_mode(void)
+{
+        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_NONE);
+}
+
+static inline void arch_flush_lazy_cpu_mode(void)
+{
+        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_FLUSH);
+}
+
+
+#define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+static inline void arch_enter_lazy_mmu_mode(void)
+{
+        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_MMU);
+}
+
+static inline void arch_leave_lazy_mmu_mode(void)
+{
+        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_NONE);
+}
+
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_FLUSH);
+}
+
+void _paravirt_nop(void);
+#define paravirt_nop    ((void *)_paravirt_nop)
+
+/* These all sit in the .parainstructions section to tell us what to patch. */
+struct paravirt_patch_site {
+        u8 *instr;              /* original instructions */
+        u8 instrtype;           /* type of this instruction */
+        u8 len;                 /* length of original instruction */
+        u16 clobbers;           /* what registers you may clobber */
+};
+
+extern struct paravirt_patch_site __parainstructions[],
+        __parainstructions_end[];
+
+static inline unsigned long __raw_local_save_flags(void)
+{
+        unsigned long f;
+
+        asm volatile(paravirt_alt("pushl %%ecx; pushl %%edx;"
+                                  PARAVIRT_CALL
+                                  "popl %%edx; popl %%ecx")
+                     : "=a"(f)
+                     : paravirt_type(save_fl),
+                       paravirt_clobber(CLBR_EAX)
+                     : "memory", "cc");
+        return f;
+}
+
+static inline void raw_local_irq_restore(unsigned long f)
+{
+        asm volatile(paravirt_alt("pushl %%ecx; pushl %%edx;"
+                                  PARAVIRT_CALL
+                                  "popl %%edx; popl %%ecx")
+                     : "=a"(f)
+                     : "0"(f),
+                       paravirt_type(restore_fl),
+                       paravirt_clobber(CLBR_EAX)
+                     : "memory", "cc");
+}
+
+static inline void raw_local_irq_disable(void)
+{
+        asm volatile(paravirt_alt("pushl %%ecx; pushl %%edx;"
+                                  PARAVIRT_CALL
+                                  "popl %%edx; popl %%ecx")
+                     :
+                     : paravirt_type(irq_disable),
+                       paravirt_clobber(CLBR_EAX)
+                     : "memory", "eax", "cc");
+}
+
+static inline void raw_local_irq_enable(void)
+{
+        asm volatile(paravirt_alt("pushl %%ecx; pushl %%edx;"
+                                  PARAVIRT_CALL
+                                  "popl %%edx; popl %%ecx")
+                     :
+                     : paravirt_type(irq_enable),
+                       paravirt_clobber(CLBR_EAX)
+                     : "memory", "eax", "cc");
+}
+
+static inline unsigned long __raw_local_irq_save(void)
+{
+        unsigned long f;
+
+        f = __raw_local_save_flags();
+        raw_local_irq_disable();
+        return f;
+}
+
+#define CLI_STRING                                                      \
+        _paravirt_alt("pushl %%ecx; pushl %%edx;"                       \
+                      "call *paravirt_ops+%c[paravirt_cli_type]*4;"     \
+                      "popl %%edx; popl %%ecx",                         \
+                      "%c[paravirt_cli_type]", "%c[paravirt_clobber]")
+
+#define STI_STRING                                                      \
+        _paravirt_alt("pushl %%ecx; pushl %%edx;"                       \
+                      "call *paravirt_ops+%c[paravirt_sti_type]*4;"     \
+                      "popl %%edx; popl %%ecx",                         \
+                      "%c[paravirt_sti_type]", "%c[paravirt_clobber]")
+
+#define CLI_STI_CLOBBERS , "%eax"
+#define CLI_STI_INPUT_ARGS                                              \
+        ,                                                               \
+        [paravirt_cli_type] "i" (PARAVIRT_PATCH(irq_disable)),          \
+        [paravirt_sti_type] "i" (PARAVIRT_PATCH(irq_enable)),           \
+        paravirt_clobber(CLBR_EAX)
+
+/* Make sure as little as possible of this mess escapes. */
+#undef PARAVIRT_CALL
+#undef __PVOP_CALL
+#undef __PVOP_VCALL
+#undef PVOP_VCALL0
+#undef PVOP_CALL0
+#undef PVOP_VCALL1
+#undef PVOP_CALL1
+#undef PVOP_VCALL2
+#undef PVOP_CALL2
+#undef PVOP_VCALL3
+#undef PVOP_CALL3
+#undef PVOP_VCALL4
+#undef PVOP_CALL4
+
+#else  /* __ASSEMBLY__ */
+
+#define PARA_PATCH(off) ((off) / 4)
+
+#define PARA_SITE(ptype, clobbers, ops)         \
+771:;                                           \
+        ops;                                    \
+772:;                                           \
+        .pushsection .parainstructions,"a";     \
+         .long 771b;                            \
+         .byte ptype;                           \
+         .byte 772b-771b;                       \
+         .short clobbers;                       \
+        .popsection
+
+#define INTERRUPT_RETURN                                        \
+        PARA_SITE(PARA_PATCH(PARAVIRT_iret), CLBR_NONE,         \
+                  jmp *%cs:paravirt_ops+PARAVIRT_iret)
+
+#define DISABLE_INTERRUPTS(clobbers)                                    \
+        PARA_SITE(PARA_PATCH(PARAVIRT_irq_disable), clobbers,           \
+                  pushl %eax; pushl %ecx; pushl %edx;                   \
+                  call *%cs:paravirt_ops+PARAVIRT_irq_disable;          \
+                  popl %edx; popl %ecx; popl %eax)                      \
+
+#define ENABLE_INTERRUPTS(clobbers)                                     \
+        PARA_SITE(PARA_PATCH(PARAVIRT_irq_enable), clobbers,            \
+                  pushl %eax; pushl %ecx; pushl %edx;                   \
+                  call *%cs:paravirt_ops+PARAVIRT_irq_enable;           \
+                  popl %edx; popl %ecx; popl %eax)
+
+#define ENABLE_INTERRUPTS_SYSEXIT                                       \
+        PARA_SITE(PARA_PATCH(PARAVIRT_irq_enable_sysexit), CLBR_NONE,   \
+                  jmp *%cs:paravirt_ops+PARAVIRT_irq_enable_sysexit)
+
+#define GET_CR0_INTO_EAX                        \
+        push %ecx; push %edx;                   \
+        call *paravirt_ops+PARAVIRT_read_cr0;   \
+        pop %edx; pop %ecx
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_PARAVIRT */
+#endif  /* __ASM_PARAVIRT_H */
diff --git a/include/asm-x86/parport.h b/include/asm-x86/parport.h
new file mode 100644
index 000000000000..2a31157349c9
--- /dev/null
+++ b/include/asm-x86/parport.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "parport_32.h"
+#else
+# include "parport_64.h"
+#endif
diff --git a/include/asm-x86/parport_32.h b/include/asm-x86/parport_32.h
new file mode 100644
index 000000000000..fa0e321e498e
--- /dev/null
+++ b/include/asm-x86/parport_32.h
@@ -0,0 +1,18 @@
+/*
+ * parport.h: ia32-specific parport initialisation
+ *
+ * Copyright (C) 1999, 2000  Tim Waugh <tim@cyberelk.demon.co.uk>
+ *
+ * This file should only be included by drivers/parport/parport_pc.c.
+ */
+
+#ifndef _ASM_I386_PARPORT_H
+#define _ASM_I386_PARPORT_H 1
+
+static int __devinit parport_pc_find_isa_ports (int autoirq, int autodma);
+static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
+{
+        return parport_pc_find_isa_ports (autoirq, autodma);
+}
+
+#endif /* !(_ASM_I386_PARPORT_H) */
diff --git a/include/asm-x86/parport_64.h b/include/asm-x86/parport_64.h
new file mode 100644
index 000000000000..7135ef977c96
--- /dev/null
+++ b/include/asm-x86/parport_64.h
@@ -0,0 +1,18 @@
+/*
+ * parport.h: ia32-specific parport initialisation
+ *
+ * Copyright (C) 1999, 2000  Tim Waugh <tim@cyberelk.demon.co.uk>
+ *
+ * This file should only be included by drivers/parport/parport_pc.c.
+ */
+
+#ifndef _ASM_X8664_PARPORT_H
+#define _ASM_X8664_PARPORT_H 1
+
+static int __devinit parport_pc_find_isa_ports (int autoirq, int autodma);
+static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
+{
+        return parport_pc_find_isa_ports (autoirq, autodma);
+}
+
+#endif 
diff --git a/include/asm-x86/pci-direct.h b/include/asm-x86/pci-direct.h
new file mode 100644
index 000000000000..6823fa4f1afa
--- /dev/null
+++ b/include/asm-x86/pci-direct.h
@@ -0,0 +1,17 @@
+#ifndef ASM_PCI_DIRECT_H
+#define ASM_PCI_DIRECT_H 1
+
+#include <linux/types.h>
+
+/* Direct PCI access. This is used for PCI accesses in early boot before
+   the PCI subsystem works. */ 
+
+extern u32 read_pci_config(u8 bus, u8 slot, u8 func, u8 offset);
+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 int early_pci_allowed(void);
+
+#endif
diff --git a/include/asm-x86/pci.h b/include/asm-x86/pci.h
new file mode 100644
index 000000000000..a8cac8c2cde7
--- /dev/null
+++ b/include/asm-x86/pci.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "pci_32.h"
+#else
+# include "pci_64.h"
+#endif
diff --git a/include/asm-x86/pci_32.h b/include/asm-x86/pci_32.h
new file mode 100644
index 000000000000..4fcacc711385
--- /dev/null
+++ b/include/asm-x86/pci_32.h
@@ -0,0 +1,90 @@
+#ifndef __i386_PCI_H
+#define __i386_PCI_H
+
+
+#ifdef __KERNEL__
+
+struct pci_sysdata {
+        int             node;           /* NUMA node */
+};
+
+/* scan a bus after allocating a pci_sysdata for it */
+extern struct pci_bus *pci_scan_bus_with_sysdata(int busno);
+
+#include <linux/mm.h>           /* for struct page */
+
+/* Can be used to override the logic in pci_scan_bus for skipping
+   already-configured bus numbers - to be used for buggy BIOSes
+   or architectures with incomplete PCI setup by the loader */
+
+#ifdef CONFIG_PCI
+extern unsigned int pcibios_assign_all_busses(void);
+#else
+#define pcibios_assign_all_busses()     0
+#endif
+#define pcibios_scan_all_fns(a, b)      0
+
+extern unsigned long pci_mem_start;
+#define PCIBIOS_MIN_IO          0x1000
+#define PCIBIOS_MIN_MEM         (pci_mem_start)
+
+#define PCIBIOS_MIN_CARDBUS_IO  0x4000
+
+void pcibios_config_init(void);
+struct pci_bus * pcibios_scan_root(int bus);
+
+void pcibios_set_master(struct pci_dev *dev);
+void pcibios_penalize_isa_irq(int irq, int active);
+struct irq_routing_table *pcibios_get_irq_routing_table(void);
+int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
+
+/* Dynamic DMA mapping stuff.
+ * i386 has everything mapped statically.
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <asm/scatterlist.h>
+#include <linux/string.h>
+#include <asm/io.h>
+
+struct pci_dev;
+
+/* The PCI address space does equal the physical memory
+ * address space.  The networking and block device layers use
+ * this boolean for bounce buffer decisions.
+ */
+#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 HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+                               enum pci_mmap_state mmap_state, int write_combine);
+
+
+#ifdef CONFIG_PCI
+static inline void pci_dma_burst_advice(struct pci_dev *pdev,
+                                        enum pci_dma_burst_strategy *strat,
+                                        unsigned long *strategy_parameter)
+{
+        *strat = PCI_DMA_BURST_INFINITY;
+        *strategy_parameter = ~0UL;
+}
+#endif
+
+#endif /* __KERNEL__ */
+
+/* implement the pci_ DMA API in terms of the generic device dma_ one */
+#include <asm-generic/pci-dma-compat.h>
+
+/* generic pci stuff */
+#include <asm-generic/pci.h>
+
+#endif /* __i386_PCI_H */
diff --git a/include/asm-x86/pci_64.h b/include/asm-x86/pci_64.h
new file mode 100644
index 000000000000..5da8cb0c0599
--- /dev/null
+++ b/include/asm-x86/pci_64.h
@@ -0,0 +1,126 @@
+#ifndef __x8664_PCI_H
+#define __x8664_PCI_H
+
+#include <asm/io.h>
+
+#ifdef __KERNEL__
+
+struct pci_sysdata {
+        int             node;           /* NUMA node */
+        void*           iommu;          /* IOMMU private data */
+};
+
+extern struct pci_bus *pci_scan_bus_with_sysdata(int busno);
+
+#ifdef CONFIG_CALGARY_IOMMU
+static inline void* pci_iommu(struct pci_bus *bus)
+{
+        struct pci_sysdata *sd = bus->sysdata;
+        return sd->iommu;
+}
+
+static inline void set_pci_iommu(struct pci_bus *bus, void *val)
+{
+        struct pci_sysdata *sd = bus->sysdata;
+        sd->iommu = val;
+}
+#endif /* CONFIG_CALGARY_IOMMU */
+
+#include <linux/mm.h> /* for struct page */
+
+/* Can be used to override the logic in pci_scan_bus for skipping
+   already-configured bus numbers - to be used for buggy BIOSes
+   or architectures with incomplete PCI setup by the loader */
+
+#ifdef CONFIG_PCI
+extern unsigned int pcibios_assign_all_busses(void);
+#else
+#define pcibios_assign_all_busses()     0
+#endif
+#define pcibios_scan_all_fns(a, b)      0
+
+extern unsigned long pci_mem_start;
+#define PCIBIOS_MIN_IO          0x1000
+#define PCIBIOS_MIN_MEM         (pci_mem_start)
+
+#define PCIBIOS_MIN_CARDBUS_IO  0x4000
+
+void pcibios_config_init(void);
+struct pci_bus * pcibios_scan_root(int bus);
+extern int (*pci_config_read)(int seg, int bus, int dev, int fn, int reg, int len, u32 *value);
+extern int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int len, u32 value);
+
+void pcibios_set_master(struct pci_dev *dev);
+void pcibios_penalize_isa_irq(int irq, int active);
+struct irq_routing_table *pcibios_get_irq_routing_table(void);
+int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <asm/scatterlist.h>
+#include <linux/string.h>
+#include <asm/page.h>
+
+extern void pci_iommu_alloc(void);
+extern int iommu_setup(char *opt);
+
+/* The PCI address space does equal the physical memory
+ * address space.  The networking and block device layers use
+ * this boolean for bounce buffer decisions
+ *
+ * On AMD64 it mostly equals, but we set it to zero if a hardware
+ * IOMMU (gart) of sotware IOMMU (swiotlb) is available.
+ */
+#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
+
+#if defined(CONFIG_IOMMU) || defined(CONFIG_CALGARY_IOMMU)
+
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
+        dma_addr_t ADDR_NAME;
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)         \
+        __u32 LEN_NAME;
+#define pci_unmap_addr(PTR, ADDR_NAME)                  \
+        ((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)         \
+        (((PTR)->ADDR_NAME) = (VAL))
+#define pci_unmap_len(PTR, LEN_NAME)                    \
+        ((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL)           \
+        (((PTR)->LEN_NAME) = (VAL))
+
+#else
+/* No IOMMU */
+
+#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)
+
+#endif
+
+#include <asm-generic/pci-dma-compat.h>
+
+#ifdef CONFIG_PCI
+static inline void pci_dma_burst_advice(struct pci_dev *pdev,
+                                        enum pci_dma_burst_strategy *strat,
+                                        unsigned long *strategy_parameter)
+{
+        *strat = PCI_DMA_BURST_INFINITY;
+        *strategy_parameter = ~0UL;
+}
+#endif
+
+#define HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+                               enum pci_mmap_state mmap_state, int write_combine);
+
+#endif /* __KERNEL__ */
+
+/* generic pci stuff */
+#ifdef CONFIG_PCI
+#include <asm-generic/pci.h>
+#endif
+
+#endif /* __x8664_PCI_H */
diff --git a/include/asm-x86/pda.h b/include/asm-x86/pda.h
new file mode 100644
index 000000000000..5642634843c4
--- /dev/null
+++ b/include/asm-x86/pda.h
@@ -0,0 +1,125 @@
+#ifndef X86_64_PDA_H
+#define X86_64_PDA_H
+
+#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/cache.h>
+#include <asm/page.h>
+
+/* Per processor datastructure. %gs points to it while the kernel runs */ 
+struct x8664_pda {
+        struct task_struct *pcurrent;   /* 0  Current process */
+        unsigned long data_offset;      /* 8 Per cpu data offset from linker
+                                           address */
+        unsigned long kernelstack;  /* 16 top of kernel stack for current */
+        unsigned long oldrsp;       /* 24 user rsp for system call */
+        int irqcount;               /* 32 Irq nesting counter. Starts with -1 */
+        int cpunumber;              /* 36 Logical CPU number */
+#ifdef CONFIG_CC_STACKPROTECTOR
+        unsigned long stack_canary;     /* 40 stack canary value */
+                                        /* gcc-ABI: this canary MUST be at
+                                           offset 40!!! */
+#endif
+        char *irqstackptr;
+        int nodenumber;             /* number of current node */
+        unsigned int __softirq_pending;
+        unsigned int __nmi_count;       /* number of NMI on this CPUs */
+        short mmu_state;
+        short isidle;
+        struct mm_struct *active_mm;
+        unsigned apic_timer_irqs;
+} ____cacheline_aligned_in_smp;
+
+extern struct x8664_pda *_cpu_pda[];
+extern struct x8664_pda boot_cpu_pda[];
+
+#define cpu_pda(i) (_cpu_pda[i])
+
+/* 
+ * There is no fast way to get the base address of the PDA, all the accesses
+ * have to mention %fs/%gs.  So it needs to be done this Torvaldian way.
+ */ 
+extern void __bad_pda_field(void) __attribute__((noreturn));
+
+/*
+ * proxy_pda doesn't actually exist, but tell gcc it is accessed for
+ * all PDA accesses so it gets read/write dependencies right.
+ */
+extern struct x8664_pda _proxy_pda;
+
+#define pda_offset(field) offsetof(struct x8664_pda, field)
+
+#define pda_to_op(op,field,val) do {            \
+        typedef typeof(_proxy_pda.field) T__;   \
+        if (0) { T__ tmp__; tmp__ = (val); }    /* type checking */ \
+        switch (sizeof(_proxy_pda.field)) {     \
+        case 2:                                 \
+                asm(op "w %1,%%gs:%c2" :        \
+                    "+m" (_proxy_pda.field) :   \
+                    "ri" ((T__)val),            \
+                    "i"(pda_offset(field)));    \
+                break;                          \
+        case 4:                                 \
+                asm(op "l %1,%%gs:%c2" :        \
+                    "+m" (_proxy_pda.field) :   \
+                    "ri" ((T__)val),            \
+                    "i" (pda_offset(field)));   \
+                break;                          \
+        case 8:                                 \
+                asm(op "q %1,%%gs:%c2":         \
+                    "+m" (_proxy_pda.field) :   \
+                    "ri" ((T__)val),            \
+                    "i"(pda_offset(field)));    \
+                break;                          \
+       default:                                 \
+                __bad_pda_field();              \
+       }                                        \
+       } while (0)
+
+#define pda_from_op(op,field) ({                \
+        typeof(_proxy_pda.field) ret__;         \
+        switch (sizeof(_proxy_pda.field)) {     \
+        case 2:                                 \
+                asm(op "w %%gs:%c1,%0" :        \
+                    "=r" (ret__) :              \
+                    "i" (pda_offset(field)),    \
+                    "m" (_proxy_pda.field));    \
+                 break;                         \
+        case 4:                                 \
+                asm(op "l %%gs:%c1,%0":         \
+                    "=r" (ret__):               \
+                    "i" (pda_offset(field)),    \
+                    "m" (_proxy_pda.field));    \
+                 break;                         \
+       case 8:                                  \
+                asm(op "q %%gs:%c1,%0":         \
+                    "=r" (ret__) :              \
+                    "i" (pda_offset(field)),    \
+                    "m" (_proxy_pda.field));    \
+                 break;                         \
+       default:                                 \
+                __bad_pda_field();              \
+       }                                        \
+       ret__; })
+
+#define read_pda(field) pda_from_op("mov",field)
+#define write_pda(field,val) pda_to_op("mov",field,val)
+#define add_pda(field,val) pda_to_op("add",field,val)
+#define sub_pda(field,val) pda_to_op("sub",field,val)
+#define or_pda(field,val) pda_to_op("or",field,val)
+
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define test_and_clear_bit_pda(bit,field) ({            \
+        int old__;                                              \
+        asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"            \
+            : "=r" (old__), "+m" (_proxy_pda.field)             \
+            : "dIr" (bit), "i" (pda_offset(field)) : "memory"); \
+        old__;                                                  \
+})
+
+#endif
+
+#define PDA_STACKOFFSET (5*8)
+
+#endif
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
new file mode 100644
index 000000000000..a1aaad274cca
--- /dev/null
+++ b/include/asm-x86/percpu.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "percpu_32.h"
+#else
+# include "percpu_64.h"
+#endif
diff --git a/include/asm-x86/percpu_32.h b/include/asm-x86/percpu_32.h
new file mode 100644
index 000000000000..a7ebd436f3cc
--- /dev/null
+++ b/include/asm-x86/percpu_32.h
@@ -0,0 +1,154 @@
+#ifndef __ARCH_I386_PERCPU__
+#define __ARCH_I386_PERCPU__
+
+#ifdef __ASSEMBLY__
+
+/*
+ * PER_CPU finds an address of a per-cpu variable.
+ *
+ * Args:
+ *    var - variable name
+ *    reg - 32bit register
+ *
+ * The resulting address is stored in the "reg" argument.
+ *
+ * Example:
+ *    PER_CPU(cpu_gdt_descr, %ebx)
+ */
+#ifdef CONFIG_SMP
+#define PER_CPU(var, reg)                               \
+        movl %fs:per_cpu__##this_cpu_off, reg;          \
+        lea per_cpu__##var(reg), reg
+#define PER_CPU_VAR(var)        %fs:per_cpu__##var
+#else /* ! SMP */
+#define PER_CPU(var, reg)                       \
+        movl $per_cpu__##var, reg
+#define PER_CPU_VAR(var)        per_cpu__##var
+#endif  /* SMP */
+
+#else /* ...!ASSEMBLY */
+
+/*
+ * PER_CPU finds an address of a per-cpu variable.
+ *
+ * Args:
+ *    var - variable name
+ *    cpu - 32bit register containing the current CPU number
+ *
+ * The resulting address is stored in the "cpu" argument.
+ *
+ * Example:
+ *    PER_CPU(cpu_gdt_descr, %ebx)
+ */
+#ifdef CONFIG_SMP
+/* Same as generic implementation except for optimized local access. */
+#define __GENERIC_PER_CPU
+
+/* This is used for other cpus to find our section. */
+extern unsigned long __per_cpu_offset[];
+
+#define per_cpu_offset(x) (__per_cpu_offset[x])
+
+/* Separate out the type, so (int[3], foo) works. */
+#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU(type, name) \
+    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
+
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)               \
+    __attribute__((__section__(".data.percpu.shared_aligned"))) \
+    __typeof__(type) per_cpu__##name                            \
+    ____cacheline_aligned_in_smp
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
+/* var is in discarded region: offset to particular copy we want */
+#define per_cpu(var, cpu) (*({                          \
+        extern int simple_indentifier_##var(void);      \
+        RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]); }))
+
+#define __raw_get_cpu_var(var) (*({                                     \
+        extern int simple_indentifier_##var(void);                      \
+        RELOC_HIDE(&per_cpu__##var, x86_read_percpu(this_cpu_off));     \
+}))
+
+#define __get_cpu_var(var) __raw_get_cpu_var(var)
+
+/* A macro to avoid #include hell... */
+#define percpu_modcopy(pcpudst, src, size)                      \
+do {                                                            \
+        unsigned int __i;                                       \
+        for_each_possible_cpu(__i)                              \
+                memcpy((pcpudst)+__per_cpu_offset[__i],         \
+                       (src), (size));                          \
+} while (0)
+
+#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+
+/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
+#define __percpu_seg "%%fs:"
+#else  /* !SMP */
+#include <asm-generic/percpu.h>
+#define __percpu_seg ""
+#endif  /* SMP */
+
+/* For arch-specific code, we can use direct single-insn ops (they
+ * don't give an lvalue though). */
+extern void __bad_percpu_size(void);
+
+#define percpu_to_op(op,var,val)                                \
+        do {                                                    \
+                typedef typeof(var) T__;                        \
+                if (0) { T__ tmp__; tmp__ = (val); }            \
+                switch (sizeof(var)) {                          \
+                case 1:                                         \
+                        asm(op "b %1,"__percpu_seg"%0"          \
+                            : "+m" (var)                        \
+                            :"ri" ((T__)val));                  \
+                        break;                                  \
+                case 2:                                         \
+                        asm(op "w %1,"__percpu_seg"%0"          \
+                            : "+m" (var)                        \
+                            :"ri" ((T__)val));                  \
+                        break;                                  \
+                case 4:                                         \
+                        asm(op "l %1,"__percpu_seg"%0"          \
+                            : "+m" (var)                        \
+                            :"ri" ((T__)val));                  \
+                        break;                                  \
+                default: __bad_percpu_size();                   \
+                }                                               \
+        } while (0)
+
+#define percpu_from_op(op,var)                                  \
+        ({                                                      \
+                typeof(var) ret__;                              \
+                switch (sizeof(var)) {                          \
+                case 1:                                         \
+                        asm(op "b "__percpu_seg"%1,%0"          \
+                            : "=r" (ret__)                      \
+                            : "m" (var));                       \
+                        break;                                  \
+                case 2:                                         \
+                        asm(op "w "__percpu_seg"%1,%0"          \
+                            : "=r" (ret__)                      \
+                            : "m" (var));                       \
+                        break;                                  \
+                case 4:                                         \
+                        asm(op "l "__percpu_seg"%1,%0"          \
+                            : "=r" (ret__)                      \
+                            : "m" (var));                       \
+                        break;                                  \
+                default: __bad_percpu_size();                   \
+                }                                               \
+                ret__; })
+
+#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
+#define x86_write_percpu(var,val) percpu_to_op("mov", per_cpu__##var, val)
+#define x86_add_percpu(var,val) percpu_to_op("add", per_cpu__##var, val)
+#define x86_sub_percpu(var,val) percpu_to_op("sub", per_cpu__##var, val)
+#define x86_or_percpu(var,val) percpu_to_op("or", per_cpu__##var, val)
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ARCH_I386_PERCPU__ */
diff --git a/include/asm-x86/percpu_64.h b/include/asm-x86/percpu_64.h
new file mode 100644
index 000000000000..5abd48270101
--- /dev/null
+++ b/include/asm-x86/percpu_64.h
@@ -0,0 +1,68 @@
+#ifndef _ASM_X8664_PERCPU_H_
+#define _ASM_X8664_PERCPU_H_
+#include <linux/compiler.h>
+
+/* Same as asm-generic/percpu.h, except that we store the per cpu offset
+   in the PDA. Longer term the PDA and every per cpu variable
+   should be just put into a single section and referenced directly
+   from %gs */
+
+#ifdef CONFIG_SMP
+
+#include <asm/pda.h>
+
+#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
+#define __my_cpu_offset() read_pda(data_offset)
+
+#define per_cpu_offset(x) (__per_cpu_offset(x))
+
+/* Separate out the type, so (int[3], foo) works. */
+#define DEFINE_PER_CPU(type, name) \
+    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
+
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)               \
+    __attribute__((__section__(".data.percpu.shared_aligned"))) \
+    __typeof__(type) per_cpu__##name                            \
+    ____cacheline_internodealigned_in_smp
+
+/* var is in discarded region: offset to particular copy we want */
+#define per_cpu(var, cpu) (*({                          \
+        extern int simple_identifier_##var(void);       \
+        RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)); }))
+#define __get_cpu_var(var) (*({                         \
+        extern int simple_identifier_##var(void);       \
+        RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()); }))
+#define __raw_get_cpu_var(var) (*({                     \
+        extern int simple_identifier_##var(void);       \
+        RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()); }))
+
+/* A macro to avoid #include hell... */
+#define percpu_modcopy(pcpudst, src, size)                      \
+do {                                                            \
+        unsigned int __i;                                       \
+        for_each_possible_cpu(__i)                              \
+                memcpy((pcpudst)+__per_cpu_offset(__i),         \
+                       (src), (size));                          \
+} while (0)
+
+extern void setup_per_cpu_areas(void);
+
+#else /* ! SMP */
+
+#define DEFINE_PER_CPU(type, name) \
+    __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)       \
+    DEFINE_PER_CPU(type, name)
+
+#define per_cpu(var, cpu)                       (*((void)(cpu), &per_cpu__##var))
+#define __get_cpu_var(var)                      per_cpu__##var
+#define __raw_get_cpu_var(var)                  per_cpu__##var
+
+#endif  /* SMP */
+
+#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
+
+#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+
+#endif /* _ASM_X8664_PERCPU_H_ */
diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h
new file mode 100644
index 000000000000..5886eed05886
--- /dev/null
+++ b/include/asm-x86/pgalloc.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "pgalloc_32.h"
+#else
+# include "pgalloc_64.h"
+#endif
diff --git a/include/asm-x86/pgalloc_32.h b/include/asm-x86/pgalloc_32.h
new file mode 100644
index 000000000000..f2fc33ceb9f2
--- /dev/null
+++ b/include/asm-x86/pgalloc_32.h
@@ -0,0 +1,68 @@
+#ifndef _I386_PGALLOC_H
+#define _I386_PGALLOC_H
+
+#include <linux/threads.h>
+#include <linux/mm.h>           /* for struct page */
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define paravirt_alloc_pt(mm, pfn) do { } while (0)
+#define paravirt_alloc_pd(pfn) do { } while (0)
+#define paravirt_alloc_pd(pfn) do { } while (0)
+#define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) do { } while (0)
+#define paravirt_release_pt(pfn) do { } while (0)
+#define paravirt_release_pd(pfn) do { } while (0)
+#endif
+
+#define pmd_populate_kernel(mm, pmd, pte)                       \
+do {                                                            \
+        paravirt_alloc_pt(mm, __pa(pte) >> PAGE_SHIFT);         \
+        set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte)));           \
+} while (0)
+
+#define pmd_populate(mm, pmd, pte)                              \
+do {                                                            \
+        paravirt_alloc_pt(mm, page_to_pfn(pte));                \
+        set_pmd(pmd, __pmd(_PAGE_TABLE +                        \
+                ((unsigned long long)page_to_pfn(pte) <<        \
+                        (unsigned long long) PAGE_SHIFT)));     \
+} while (0)
+
+/*
+ * Allocate and free page tables.
+ */
+extern pgd_t *pgd_alloc(struct mm_struct *);
+extern void pgd_free(pgd_t *pgd);
+
+extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
+extern struct page *pte_alloc_one(struct mm_struct *, unsigned long);
+
+static inline void pte_free_kernel(pte_t *pte)
+{
+        free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct page *pte)
+{
+        __free_page(pte);
+}
+
+
+#define __pte_free_tlb(tlb,pte)                                         \
+do {                                                                    \
+        paravirt_release_pt(page_to_pfn(pte));                          \
+        tlb_remove_page((tlb),(pte));                                   \
+} while (0)
+
+#ifdef CONFIG_X86_PAE
+/*
+ * In the PAE case we free the pmds as part of the pgd.
+ */
+#define pmd_alloc_one(mm, addr)         ({ BUG(); ((pmd_t *)2); })
+#define pmd_free(x)                     do { } while (0)
+#define __pmd_free_tlb(tlb,x)           do { } while (0)
+#define pud_populate(mm, pmd, pte)      BUG()
+#endif
+
+#endif /* _I386_PGALLOC_H */
diff --git a/include/asm-x86/pgalloc_64.h b/include/asm-x86/pgalloc_64.h
new file mode 100644
index 000000000000..8bb564687860
--- /dev/null
+++ b/include/asm-x86/pgalloc_64.h
@@ -0,0 +1,119 @@
+#ifndef _X86_64_PGALLOC_H
+#define _X86_64_PGALLOC_H
+
+#include <asm/pda.h>
+#include <linux/threads.h>
+#include <linux/mm.h>
+
+#define pmd_populate_kernel(mm, pmd, pte) \
+                set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte)))
+#define pud_populate(mm, pud, pmd) \
+                set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd)))
+#define pgd_populate(mm, pgd, pud) \
+                set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)))
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte)
+{
+        set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT)));
+}
+
+static inline void pmd_free(pmd_t *pmd)
+{
+        BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+        free_page((unsigned long)pmd);
+}
+
+static inline pmd_t *pmd_alloc_one (struct mm_struct *mm, unsigned long addr)
+{
+        return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+        return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free (pud_t *pud)
+{
+        BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+        free_page((unsigned long)pud);
+}
+
+static inline void pgd_list_add(pgd_t *pgd)
+{
+        struct page *page = virt_to_page(pgd);
+
+        spin_lock(&pgd_lock);
+        list_add(&page->lru, &pgd_list);
+        spin_unlock(&pgd_lock);
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+        struct page *page = virt_to_page(pgd);
+
+        spin_lock(&pgd_lock);
+        list_del(&page->lru);
+        spin_unlock(&pgd_lock);
+}
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+        unsigned boundary;
+        pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+        if (!pgd)
+                return NULL;
+        pgd_list_add(pgd);
+        /*
+         * Copy kernel pointers in from init.
+         * Could keep a freelist or slab cache of those because the kernel
+         * part never changes.
+         */
+        boundary = pgd_index(__PAGE_OFFSET);
+        memset(pgd, 0, boundary * sizeof(pgd_t));
+        memcpy(pgd + boundary,
+               init_level4_pgt + boundary,
+               (PTRS_PER_PGD - boundary) * sizeof(pgd_t));
+        return pgd;
+}
+
+static inline void pgd_free(pgd_t *pgd)
+{
+        BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
+        pgd_list_del(pgd);
+        free_page((unsigned long)pgd);
+}
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
+{
+        return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+        void *p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+        if (!p)
+                return NULL;
+        return virt_to_page(p);
+}
+
+/* Should really implement gc for free page table pages. This could be
+   done with a reference count in struct page. */
+
+static inline void pte_free_kernel(pte_t *pte)
+{
+        BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
+        free_page((unsigned long)pte); 
+}
+
+static inline void pte_free(struct page *pte)
+{
+        __free_page(pte);
+} 
+
+#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+
+#define __pmd_free_tlb(tlb,x)   tlb_remove_page((tlb),virt_to_page(x))
+#define __pud_free_tlb(tlb,x)   tlb_remove_page((tlb),virt_to_page(x))
+
+#endif /* _X86_64_PGALLOC_H */
diff --git a/include/asm-x86/pgtable-2level-defs.h b/include/asm-x86/pgtable-2level-defs.h
new file mode 100644
index 000000000000..0f71c9f13da4
--- /dev/null
+++ b/include/asm-x86/pgtable-2level-defs.h
@@ -0,0 +1,20 @@
+#ifndef _I386_PGTABLE_2LEVEL_DEFS_H
+#define _I386_PGTABLE_2LEVEL_DEFS_H
+
+#define SHARED_KERNEL_PMD       0
+
+/*
+ * traditional i386 two-level paging structure:
+ */
+
+#define PGDIR_SHIFT     22
+#define PTRS_PER_PGD    1024
+
+/*
+ * the i386 is two-level, so we don't really have any
+ * PMD directory physically.
+ */
+
+#define PTRS_PER_PTE    1024
+
+#endif /* _I386_PGTABLE_2LEVEL_DEFS_H */
diff --git a/include/asm-x86/pgtable-2level.h b/include/asm-x86/pgtable-2level.h
new file mode 100644
index 000000000000..84b03cf56a79
--- /dev/null
+++ b/include/asm-x86/pgtable-2level.h
@@ -0,0 +1,86 @@
+#ifndef _I386_PGTABLE_2LEVEL_H
+#define _I386_PGTABLE_2LEVEL_H
+
+#define pte_ERROR(e) \
+        printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+#define pgd_ERROR(e) \
+        printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * Certain architectures need to do special things when PTEs
+ * within a page table are directly modified.  Thus, the following
+ * hook is made available.
+ */
+static inline void native_set_pte(pte_t *ptep , pte_t pte)
+{
+        *ptep = pte;
+}
+static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
+                                     pte_t *ptep , pte_t pte)
+{
+        native_set_pte(ptep, pte);
+}
+static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+        *pmdp = pmd;
+}
+#ifndef CONFIG_PARAVIRT
+#define set_pte(pteptr, pteval)         native_set_pte(pteptr, pteval)
+#define set_pte_at(mm,addr,ptep,pteval) native_set_pte_at(mm, addr, ptep, pteval)
+#define set_pmd(pmdptr, pmdval)         native_set_pmd(pmdptr, pmdval)
+#endif
+
+#define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval)
+#define set_pte_present(mm,addr,ptep,pteval) set_pte_at(mm,addr,ptep,pteval)
+
+#define pte_clear(mm,addr,xp)   do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
+#define pmd_clear(xp)   do { set_pmd(xp, __pmd(0)); } while (0)
+
+static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *xp)
+{
+        *xp = __pte(0);
+}
+
+#ifdef CONFIG_SMP
+static inline pte_t native_ptep_get_and_clear(pte_t *xp)
+{
+        return __pte(xchg(&xp->pte_low, 0));
+}
+#else
+#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
+#endif
+
+#define pte_page(x)             pfn_to_page(pte_pfn(x))
+#define pte_none(x)             (!(x).pte_low)
+#define pte_pfn(x)              (pte_val(x) >> PAGE_SHIFT)
+#define pfn_pte(pfn, prot)      __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define pfn_pmd(pfn, prot)      __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+/*
+ * All present pages are kernel-executable:
+ */
+static inline int pte_exec_kernel(pte_t pte)
+{
+        return 1;
+}
+
+/*
+ * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
+ * into this range:
+ */
+#define PTE_FILE_MAX_BITS       29
+
+#define pte_to_pgoff(pte) \
+        ((((pte).pte_low >> 1) & 0x1f ) + (((pte).pte_low >> 8) << 5 ))
+
+#define pgoff_to_pte(off) \
+        ((pte_t) { (((off) & 0x1f) << 1) + (((off) >> 5) << 8) + _PAGE_FILE })
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x)                   (((x).val >> 1) & 0x1f)
+#define __swp_offset(x)                 ((x).val >> 8)
+#define __swp_entry(type, offset)       ((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
+#define __pte_to_swp_entry(pte)         ((swp_entry_t) { (pte).pte_low })
+#define __swp_entry_to_pte(x)           ((pte_t) { (x).val })
+
+#endif /* _I386_PGTABLE_2LEVEL_H */
diff --git a/include/asm-x86/pgtable-3level-defs.h b/include/asm-x86/pgtable-3level-defs.h
new file mode 100644
index 000000000000..c0df89f66e8b
--- /dev/null
+++ b/include/asm-x86/pgtable-3level-defs.h
@@ -0,0 +1,28 @@
+#ifndef _I386_PGTABLE_3LEVEL_DEFS_H
+#define _I386_PGTABLE_3LEVEL_DEFS_H
+
+#ifdef CONFIG_PARAVIRT
+#define SHARED_KERNEL_PMD       (paravirt_ops.shared_kernel_pmd)
+#else
+#define SHARED_KERNEL_PMD       1
+#endif
+
+/*
+ * PGDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PGDIR_SHIFT     30
+#define PTRS_PER_PGD    4
+
+/*
+ * PMD_SHIFT determines the size of the area a middle-level
+ * page table can map
+ */
+#define PMD_SHIFT       21
+#define PTRS_PER_PMD    512
+
+/*
+ * entries per page directory level
+ */
+#define PTRS_PER_PTE    512
+
+#endif /* _I386_PGTABLE_3LEVEL_DEFS_H */
diff --git a/include/asm-x86/pgtable-3level.h b/include/asm-x86/pgtable-3level.h
new file mode 100644
index 000000000000..948a33414118
--- /dev/null
+++ b/include/asm-x86/pgtable-3level.h
@@ -0,0 +1,192 @@
+#ifndef _I386_PGTABLE_3LEVEL_H
+#define _I386_PGTABLE_3LEVEL_H
+
+/*
+ * Intel Physical Address Extension (PAE) Mode - three-level page
+ * tables on PPro+ CPUs.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+#define pte_ERROR(e) \
+        printk("%s:%d: bad pte %p(%08lx%08lx).\n", __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
+#define pmd_ERROR(e) \
+        printk("%s:%d: bad pmd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
+#define pgd_ERROR(e) \
+        printk("%s:%d: bad pgd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
+
+#define pud_none(pud)                           0
+#define pud_bad(pud)                            0
+#define pud_present(pud)                        1
+
+/*
+ * All present pages with !NX bit are kernel-executable:
+ */
+static inline int pte_exec_kernel(pte_t pte)
+{
+        return !(pte_val(pte) & _PAGE_NX);
+}
+
+/* Rules for using set_pte: the pte being assigned *must* be
+ * either not present or in a state where the hardware will
+ * not attempt to update the pte.  In places where this is
+ * not possible, use pte_get_and_clear to obtain the old pte
+ * value and then use set_pte to update it.  -ben
+ */
+static inline void native_set_pte(pte_t *ptep, pte_t pte)
+{
+        ptep->pte_high = pte.pte_high;
+        smp_wmb();
+        ptep->pte_low = pte.pte_low;
+}
+static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
+                                     pte_t *ptep , pte_t pte)
+{
+        native_set_pte(ptep, pte);
+}
+
+/*
+ * Since this is only called on user PTEs, and the page fault handler
+ * must handle the already racy situation of simultaneous page faults,
+ * we are justified in merely clearing the PTE present bit, followed
+ * by a set.  The ordering here is important.
+ */
+static inline void native_set_pte_present(struct mm_struct *mm, unsigned long addr,
+                                          pte_t *ptep, pte_t pte)
+{
+        ptep->pte_low = 0;
+        smp_wmb();
+        ptep->pte_high = pte.pte_high;
+        smp_wmb();
+        ptep->pte_low = pte.pte_low;
+}
+
+static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+        set_64bit((unsigned long long *)(ptep),native_pte_val(pte));
+}
+static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+        set_64bit((unsigned long long *)(pmdp),native_pmd_val(pmd));
+}
+static inline void native_set_pud(pud_t *pudp, pud_t pud)
+{
+        *pudp = pud;
+}
+
+/*
+ * For PTEs and PDEs, we must clear the P-bit first when clearing a page table
+ * entry, so clear the bottom half first and enforce ordering with a compiler
+ * barrier.
+ */
+static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+        ptep->pte_low = 0;
+        smp_wmb();
+        ptep->pte_high = 0;
+}
+
+static inline void native_pmd_clear(pmd_t *pmd)
+{
+        u32 *tmp = (u32 *)pmd;
+        *tmp = 0;
+        smp_wmb();
+        *(tmp + 1) = 0;
+}
+
+#ifndef CONFIG_PARAVIRT
+#define set_pte(ptep, pte)                      native_set_pte(ptep, pte)
+#define set_pte_at(mm, addr, ptep, pte)         native_set_pte_at(mm, addr, ptep, pte)
+#define set_pte_present(mm, addr, ptep, pte)    native_set_pte_present(mm, addr, ptep, pte)
+#define set_pte_atomic(ptep, pte)               native_set_pte_atomic(ptep, pte)
+#define set_pmd(pmdp, pmd)                      native_set_pmd(pmdp, pmd)
+#define set_pud(pudp, pud)                      native_set_pud(pudp, pud)
+#define pte_clear(mm, addr, ptep)               native_pte_clear(mm, addr, ptep)
+#define pmd_clear(pmd)                          native_pmd_clear(pmd)
+#endif
+
+/*
+ * Pentium-II erratum A13: in PAE mode we explicitly have to flush
+ * the TLB via cr3 if the top-level pgd is changed...
+ * We do not let the generic code free and clear pgd entries due to
+ * this erratum.
+ */
+static inline void pud_clear (pud_t * pud) { }
+
+#define pud_page(pud) \
+((struct page *) __va(pud_val(pud) & PAGE_MASK))
+
+#define pud_page_vaddr(pud) \
+((unsigned long) __va(pud_val(pud) & PAGE_MASK))
+
+
+/* Find an entry in the second-level page table.. */
+#define pmd_offset(pud, address) ((pmd_t *) pud_page(*(pud)) + \
+                        pmd_index(address))
+
+#ifdef CONFIG_SMP
+static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
+{
+        pte_t res;
+
+        /* xchg acts as a barrier before the setting of the high bits */
+        res.pte_low = xchg(&ptep->pte_low, 0);
+        res.pte_high = ptep->pte_high;
+        ptep->pte_high = 0;
+
+        return res;
+}
+#else
+#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
+#endif
+
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t a, pte_t b)
+{
+        return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
+}
+
+#define pte_page(x)     pfn_to_page(pte_pfn(x))
+
+static inline int pte_none(pte_t pte)
+{
+        return !pte.pte_low && !pte.pte_high;
+}
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+        return pte_val(pte) >> PAGE_SHIFT;
+}
+
+extern unsigned long long __supported_pte_mask;
+
+static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+        return __pte((((unsigned long long)page_nr << PAGE_SHIFT) |
+                      pgprot_val(pgprot)) & __supported_pte_mask);
+}
+
+static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
+{
+        return __pmd((((unsigned long long)page_nr << PAGE_SHIFT) |
+                      pgprot_val(pgprot)) & __supported_pte_mask);
+}
+
+/*
+ * Bits 0, 6 and 7 are taken in the low part of the pte,
+ * put the 32 bits of offset into the high part.
+ */
+#define pte_to_pgoff(pte) ((pte).pte_high)
+#define pgoff_to_pte(off) ((pte_t) { _PAGE_FILE, (off) })
+#define PTE_FILE_MAX_BITS       32
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x)                   (((x).val) & 0x1f)
+#define __swp_offset(x)                 ((x).val >> 5)
+#define __swp_entry(type, offset)       ((swp_entry_t){(type) | (offset) << 5})
+#define __pte_to_swp_entry(pte)         ((swp_entry_t){ (pte).pte_high })
+#define __swp_entry_to_pte(x)           ((pte_t){ 0, (x).val })
+
+#define __pmd_free_tlb(tlb, x)          do { } while (0)
+
+#endif /* _I386_PGTABLE_3LEVEL_H */
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
new file mode 100644
index 000000000000..1039140652af
--- /dev/null
+++ b/include/asm-x86/pgtable.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "pgtable_32.h"
+#else
+# include "pgtable_64.h"
+#endif
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
new file mode 100644
index 000000000000..c7fefa6b12fd
--- /dev/null
+++ b/include/asm-x86/pgtable_32.h
@@ -0,0 +1,512 @@
+#ifndef _I386_PGTABLE_H
+#define _I386_PGTABLE_H
+
+
+/*
+ * The Linux memory management assumes a three-level page table setup. On
+ * the i386, we use that, but "fold" the mid level into the top-level page
+ * table, so that we physically have the same two-level page table as the
+ * i386 mmu expects.
+ *
+ * This file contains the functions and defines necessary to modify and use
+ * the i386 page table tree.
+ */
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <linux/threads.h>
+#include <asm/paravirt.h>
+
+#ifndef _I386_BITOPS_H
+#include <asm/bitops.h>
+#endif
+
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+struct mm_struct;
+struct vm_area_struct;
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+extern unsigned long empty_zero_page[1024];
+extern pgd_t swapper_pg_dir[1024];
+extern struct kmem_cache *pmd_cache;
+extern spinlock_t pgd_lock;
+extern struct page *pgd_list;
+void check_pgt_cache(void);
+
+void pmd_ctor(void *, struct kmem_cache *, unsigned long);
+void pgtable_cache_init(void);
+void paging_init(void);
+
+
+/*
+ * The Linux x86 paging architecture is 'compile-time dual-mode', it
+ * implements both the traditional 2-level x86 page tables and the
+ * newer 3-level PAE-mode page tables.
+ */
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level-defs.h>
+# define PMD_SIZE       (1UL << PMD_SHIFT)
+# define PMD_MASK       (~(PMD_SIZE-1))
+#else
+# include <asm/pgtable-2level-defs.h>
+#endif
+
+#define PGDIR_SIZE      (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK      (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD       (TASK_SIZE/PGDIR_SIZE)
+#define FIRST_USER_ADDRESS      0
+
+#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
+#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
+
+#define TWOLEVEL_PGDIR_SHIFT    22
+#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
+#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)
+
+/* Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 8MB value just means that there will be a 8MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ */
+#define VMALLOC_OFFSET  (8*1024*1024)
+#define VMALLOC_START   (((unsigned long) high_memory + \
+                        2*VMALLOC_OFFSET-1) & ~(VMALLOC_OFFSET-1))
+#ifdef CONFIG_HIGHMEM
+# define VMALLOC_END    (PKMAP_BASE-2*PAGE_SIZE)
+#else
+# define VMALLOC_END    (FIXADDR_START-2*PAGE_SIZE)
+#endif
+
+/*
+ * _PAGE_PSE set in the page directory entry just means that
+ * the page directory entry points directly to a 4MB-aligned block of
+ * memory. 
+ */
+#define _PAGE_BIT_PRESENT       0
+#define _PAGE_BIT_RW            1
+#define _PAGE_BIT_USER          2
+#define _PAGE_BIT_PWT           3
+#define _PAGE_BIT_PCD           4
+#define _PAGE_BIT_ACCESSED      5
+#define _PAGE_BIT_DIRTY         6
+#define _PAGE_BIT_PSE           7       /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_BIT_GLOBAL        8       /* Global TLB entry PPro+ */
+#define _PAGE_BIT_UNUSED1       9       /* available for programmer */
+#define _PAGE_BIT_UNUSED2       10
+#define _PAGE_BIT_UNUSED3       11
+#define _PAGE_BIT_NX            63
+
+#define _PAGE_PRESENT   0x001
+#define _PAGE_RW        0x002
+#define _PAGE_USER      0x004
+#define _PAGE_PWT       0x008
+#define _PAGE_PCD       0x010
+#define _PAGE_ACCESSED  0x020
+#define _PAGE_DIRTY     0x040
+#define _PAGE_PSE       0x080   /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_GLOBAL    0x100   /* Global TLB entry PPro+ */
+#define _PAGE_UNUSED1   0x200   /* available for programmer */
+#define _PAGE_UNUSED2   0x400
+#define _PAGE_UNUSED3   0x800
+
+/* If _PAGE_PRESENT is clear, we use these: */
+#define _PAGE_FILE      0x040   /* nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_PROTNONE  0x080   /* if the user mapped it with PROT_NONE;
+                                   pte_present gives true */
+#ifdef CONFIG_X86_PAE
+#define _PAGE_NX        (1ULL<<_PAGE_BIT_NX)
+#else
+#define _PAGE_NX        0
+#endif
+
+#define _PAGE_TABLE     (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE   (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK  (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define PAGE_NONE \
+        __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED \
+        __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+
+#define PAGE_SHARED_EXEC \
+        __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY_NOEXEC \
+        __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_COPY_EXEC \
+        __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY \
+        PAGE_COPY_NOEXEC
+#define PAGE_READONLY \
+        __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_READONLY_EXEC \
+        __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+
+#define _PAGE_KERNEL \
+        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
+#define _PAGE_KERNEL_EXEC \
+        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+
+extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
+#define __PAGE_KERNEL_RO                (__PAGE_KERNEL & ~_PAGE_RW)
+#define __PAGE_KERNEL_RX                (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
+#define __PAGE_KERNEL_NOCACHE           (__PAGE_KERNEL | _PAGE_PCD)
+#define __PAGE_KERNEL_LARGE             (__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_EXEC        (__PAGE_KERNEL_EXEC | _PAGE_PSE)
+
+#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_NOCACHE     __pgprot(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_LARGE       __pgprot(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_LARGE_EXEC  __pgprot(__PAGE_KERNEL_LARGE_EXEC)
+
+/*
+ * The i386 can't do page protection for execute, and considers that
+ * the same are read. Also, write permissions imply read permissions.
+ * This is the closest we can get..
+ */
+#define __P000  PAGE_NONE
+#define __P001  PAGE_READONLY
+#define __P010  PAGE_COPY
+#define __P011  PAGE_COPY
+#define __P100  PAGE_READONLY_EXEC
+#define __P101  PAGE_READONLY_EXEC
+#define __P110  PAGE_COPY_EXEC
+#define __P111  PAGE_COPY_EXEC
+
+#define __S000  PAGE_NONE
+#define __S001  PAGE_READONLY
+#define __S010  PAGE_SHARED
+#define __S011  PAGE_SHARED
+#define __S100  PAGE_READONLY_EXEC
+#define __S101  PAGE_READONLY_EXEC
+#define __S110  PAGE_SHARED_EXEC
+#define __S111  PAGE_SHARED_EXEC
+
+/*
+ * Define this if things work differently on an i386 and an i486:
+ * it will (on an i486) warn about kernel memory accesses that are
+ * done without a 'access_ok(VERIFY_WRITE,..)'
+ */
+#undef TEST_ACCESS_OK
+
+/* The boot page tables (all created as a single array) */
+extern unsigned long pg0[];
+
+#define pte_present(x)  ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
+
+/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
+#define pmd_none(x)     (!(unsigned long)pmd_val(x))
+#define pmd_present(x)  (pmd_val(x) & _PAGE_PRESENT)
+#define pmd_bad(x)      ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+
+
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_dirty(pte_t pte)          { return (pte).pte_low & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)          { return (pte).pte_low & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte)          { return (pte).pte_low & _PAGE_RW; }
+static inline int pte_huge(pte_t pte)           { return (pte).pte_low & _PAGE_PSE; }
+
+/*
+ * The following only works if pte_present() is not true.
+ */
+static inline int pte_file(pte_t pte)           { return (pte).pte_low & _PAGE_FILE; }
+
+static inline pte_t pte_mkclean(pte_t pte)      { (pte).pte_low &= ~_PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkold(pte_t pte)        { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte)    { (pte).pte_low &= ~_PAGE_RW; return pte; }
+static inline pte_t pte_mkdirty(pte_t pte)      { (pte).pte_low |= _PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkyoung(pte_t pte)      { (pte).pte_low |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte)      { (pte).pte_low |= _PAGE_RW; return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)       { (pte).pte_low |= _PAGE_PSE; return pte; }
+
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level.h>
+#else
+# include <asm/pgtable-2level.h>
+#endif
+
+#ifndef CONFIG_PARAVIRT
+/*
+ * Rules for using pte_update - it must be called after any PTE update which
+ * has not been done using the set_pte / clear_pte interfaces.  It is used by
+ * shadow mode hypervisors to resynchronize the shadow page tables.  Kernel PTE
+ * updates should either be sets, clears, or set_pte_atomic for P->P
+ * transitions, which means this hook should only be called for user PTEs.
+ * This hook implies a P->P protection or access change has taken place, which
+ * requires a subsequent TLB flush.  The notification can optionally be delayed
+ * until the TLB flush event by using the pte_update_defer form of the
+ * interface, but care must be taken to assure that the flush happens while
+ * still holding the same page table lock so that the shadow and primary pages
+ * do not become out of sync on SMP.
+ */
+#define pte_update(mm, addr, ptep)              do { } while (0)
+#define pte_update_defer(mm, addr, ptep)        do { } while (0)
+#endif
+
+/* local pte updates need not use xchg for locking */
+static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
+{
+        pte_t res = *ptep;
+
+        /* Pure native function needs no input for mm, addr */
+        native_pte_clear(NULL, 0, ptep);
+        return res;
+}
+
+/*
+ * We only update the dirty/accessed state if we set
+ * the dirty bit by hand in the kernel, since the hardware
+ * will do the accessed bit for us, and we don't want to
+ * race with other CPU's that might be updating the dirty
+ * bit at the same time.
+ */
+#define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(vma, address, ptep, entry, dirty)         \
+({                                                                      \
+        int __changed = !pte_same(*(ptep), entry);                      \
+        if (__changed && dirty) {                                       \
+                (ptep)->pte_low = (entry).pte_low;                      \
+                pte_update_defer((vma)->vm_mm, (address), (ptep));      \
+                flush_tlb_page(vma, address);                           \
+        }                                                               \
+        __changed;                                                      \
+})
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define ptep_test_and_clear_young(vma, addr, ptep) ({                   \
+        int __ret = 0;                                                  \
+        if (pte_young(*(ptep)))                                         \
+                __ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,          \
+                                                &(ptep)->pte_low);      \
+        if (__ret)                                                      \
+                pte_update((vma)->vm_mm, addr, ptep);                   \
+        __ret;                                                          \
+})
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define ptep_clear_flush_young(vma, address, ptep)                      \
+({                                                                      \
+        int __young;                                                    \
+        __young = ptep_test_and_clear_young((vma), (address), (ptep));  \
+        if (__young)                                                    \
+                flush_tlb_page(vma, address);                           \
+        __young;                                                        \
+})
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+        pte_t pte = native_ptep_get_and_clear(ptep);
+        pte_update(mm, addr, ptep);
+        return pte;
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
+static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
+{
+        pte_t pte;
+        if (full) {
+                /*
+                 * Full address destruction in progress; paravirt does not
+                 * care about updates and native needs no locking
+                 */
+                pte = native_local_ptep_get_and_clear(ptep);
+        } else {
+                pte = ptep_get_and_clear(mm, addr, ptep);
+        }
+        return pte;
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+        clear_bit(_PAGE_BIT_RW, &ptep->pte_low);
+        pte_update(mm, addr, ptep);
+}
+
+/*
+ * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
+ *
+ *  dst - pointer to pgd range anwhere on a pgd page
+ *  src - ""
+ *  count - the number of pgds to copy.
+ *
+ * dst and src can be on the same page, but the range must not overlap,
+ * and must not cross a page boundary.
+ */
+static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
+{
+       memcpy(dst, src, count * sizeof(pgd_t));
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".  On processors which do not support
+ * it, this is a no-op.
+ */
+#define pgprot_noncached(prot)  ((boot_cpu_data.x86 > 3)                                          \
+                                 ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) : (prot))
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define mk_pte(page, pgprot)    pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+        pte.pte_low &= _PAGE_CHG_MASK;
+        pte.pte_low |= pgprot_val(newprot);
+#ifdef CONFIG_X86_PAE
+        /*
+         * Chop off the NX bit (if present), and add the NX portion of
+         * the newprot (if present):
+         */
+        pte.pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
+        pte.pte_high |= (pgprot_val(newprot) >> 32) & \
+                                        (__supported_pte_mask >> 32);
+#endif
+        return pte;
+}
+
+#define pmd_large(pmd) \
+((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT))
+
+/*
+ * 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)
+
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+#define pmd_index(address) \
+                (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this macro returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+#define pte_index(address) \
+                (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address) \
+        ((pte_t *) pmd_page_vaddr(*(dir)) +  pte_index(address))
+
+#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+
+#define pmd_page_vaddr(pmd) \
+                ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+
+/*
+ * Helper function that returns the kernel pagetable entry controlling
+ * the virtual address 'address'. NULL means no pagetable entry present.
+ * NOTE: the return type is pte_t but if the pmd is PSE then we return it
+ * as a pte too.
+ */
+extern pte_t *lookup_address(unsigned long address);
+
+/*
+ * Make a given kernel text page executable/non-executable.
+ * Returns the previous executability setting of that page (which
+ * is used to restore the previous state). Used by the SMP bootup code.
+ * NOTE: this is an __init function for security reasons.
+ */
+#ifdef CONFIG_X86_PAE
+ extern int set_kernel_exec(unsigned long vaddr, int enable);
+#else
+ static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;}
+#endif
+
+#if defined(CONFIG_HIGHPTE)
+#define pte_offset_map(dir, address) \
+        ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE0) + pte_index(address))
+#define pte_offset_map_nested(dir, address) \
+        ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE1) + pte_index(address))
+#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0)
+#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1)
+#else
+#define pte_offset_map(dir, address) \
+        ((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address))
+#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address)
+#define pte_unmap(pte) do { } while (0)
+#define pte_unmap_nested(pte) do { } while (0)
+#endif
+
+/* Clear a kernel PTE and flush it from the TLB */
+#define kpte_clear_flush(ptep, vaddr)                                   \
+do {                                                                    \
+        pte_clear(&init_mm, vaddr, ptep);                               \
+        __flush_tlb_one(vaddr);                                         \
+} while (0)
+
+/*
+ * The i386 doesn't have any external MMU info: the kernel page
+ * tables contain all the necessary information.
+ */
+#define update_mmu_cache(vma,address,pte) do { } while (0)
+
+void native_pagetable_setup_start(pgd_t *base);
+void native_pagetable_setup_done(pgd_t *base);
+
+#ifndef CONFIG_PARAVIRT
+static inline void paravirt_pagetable_setup_start(pgd_t *base)
+{
+        native_pagetable_setup_start(base);
+}
+
+static inline void paravirt_pagetable_setup_done(pgd_t *base)
+{
+        native_pagetable_setup_done(base);
+}
+#endif  /* !CONFIG_PARAVIRT */
+
+#endif /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_FLATMEM
+#define kern_addr_valid(addr)   (1)
+#endif /* CONFIG_FLATMEM */
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)         \
+                remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#include <asm-generic/pgtable.h>
+
+#endif /* _I386_PGTABLE_H */
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
new file mode 100644
index 000000000000..57dd6b3107ea
--- /dev/null
+++ b/include/asm-x86/pgtable_64.h
@@ -0,0 +1,432 @@
+#ifndef _X86_64_PGTABLE_H
+#define _X86_64_PGTABLE_H
+
+#include <linux/const.h>
+#ifndef __ASSEMBLY__
+
+/*
+ * This file contains the functions and defines necessary to modify and use
+ * the x86-64 page table tree.
+ */
+#include <asm/processor.h>
+#include <asm/bitops.h>
+#include <linux/threads.h>
+#include <asm/pda.h>
+
+extern pud_t level3_kernel_pgt[512];
+extern pud_t level3_ident_pgt[512];
+extern pmd_t level2_kernel_pgt[512];
+extern pgd_t init_level4_pgt[];
+extern unsigned long __supported_pte_mask;
+
+#define swapper_pg_dir init_level4_pgt
+
+extern void paging_init(void);
+extern void clear_kernel_mapping(unsigned long addr, unsigned long size);
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * PGDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PGDIR_SHIFT     39
+#define PTRS_PER_PGD    512
+
+/*
+ * 3rd level page
+ */
+#define PUD_SHIFT       30
+#define PTRS_PER_PUD    512
+
+/*
+ * PMD_SHIFT determines the size of the area a middle-level
+ * page table can map
+ */
+#define PMD_SHIFT       21
+#define PTRS_PER_PMD    512
+
+/*
+ * entries per page directory level
+ */
+#define PTRS_PER_PTE    512
+
+#ifndef __ASSEMBLY__
+
+#define pte_ERROR(e) \
+        printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), pte_val(e))
+#define pmd_ERROR(e) \
+        printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
+#define pud_ERROR(e) \
+        printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), pud_val(e))
+#define pgd_ERROR(e) \
+        printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
+
+#define pgd_none(x)     (!pgd_val(x))
+#define pud_none(x)     (!pud_val(x))
+
+static inline void set_pte(pte_t *dst, pte_t val)
+{
+        pte_val(*dst) = pte_val(val);
+} 
+#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+
+static inline void set_pmd(pmd_t *dst, pmd_t val)
+{
+        pmd_val(*dst) = pmd_val(val); 
+} 
+
+static inline void set_pud(pud_t *dst, pud_t val)
+{
+        pud_val(*dst) = pud_val(val);
+}
+
+static inline void pud_clear (pud_t *pud)
+{
+        set_pud(pud, __pud(0));
+}
+
+static inline void set_pgd(pgd_t *dst, pgd_t val)
+{
+        pgd_val(*dst) = pgd_val(val); 
+} 
+
+static inline void pgd_clear (pgd_t * pgd)
+{
+        set_pgd(pgd, __pgd(0));
+}
+
+#define ptep_get_and_clear(mm,addr,xp)  __pte(xchg(&(xp)->pte, 0))
+
+struct mm_struct;
+
+static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
+{
+        pte_t pte;
+        if (full) {
+                pte = *ptep;
+                *ptep = __pte(0);
+        } else {
+                pte = ptep_get_and_clear(mm, addr, ptep);
+        }
+        return pte;
+}
+
+#define pte_same(a, b)          ((a).pte == (b).pte)
+
+#define pte_pgprot(a)   (__pgprot((a).pte & ~PHYSICAL_PAGE_MASK))
+
+#endif /* !__ASSEMBLY__ */
+
+#define PMD_SIZE        (_AC(1,UL) << PMD_SHIFT)
+#define PMD_MASK        (~(PMD_SIZE-1))
+#define PUD_SIZE        (_AC(1,UL) << PUD_SHIFT)
+#define PUD_MASK        (~(PUD_SIZE-1))
+#define PGDIR_SIZE      (_AC(1,UL) << PGDIR_SHIFT)
+#define PGDIR_MASK      (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD       ((TASK_SIZE-1)/PGDIR_SIZE+1)
+#define FIRST_USER_ADDRESS      0
+
+#define MAXMEM           _AC(0x3fffffffffff, UL)
+#define VMALLOC_START    _AC(0xffffc20000000000, UL)
+#define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
+#define MODULES_VADDR    _AC(0xffffffff88000000, UL)
+#define MODULES_END      _AC(0xfffffffffff00000, UL)
+#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+
+#define _PAGE_BIT_PRESENT       0
+#define _PAGE_BIT_RW            1
+#define _PAGE_BIT_USER          2
+#define _PAGE_BIT_PWT           3
+#define _PAGE_BIT_PCD           4
+#define _PAGE_BIT_ACCESSED      5
+#define _PAGE_BIT_DIRTY         6
+#define _PAGE_BIT_PSE           7       /* 4 MB (or 2MB) page */
+#define _PAGE_BIT_GLOBAL        8       /* Global TLB entry PPro+ */
+#define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
+
+#define _PAGE_PRESENT   0x001
+#define _PAGE_RW        0x002
+#define _PAGE_USER      0x004
+#define _PAGE_PWT       0x008
+#define _PAGE_PCD       0x010
+#define _PAGE_ACCESSED  0x020
+#define _PAGE_DIRTY     0x040
+#define _PAGE_PSE       0x080   /* 2MB page */
+#define _PAGE_FILE      0x040   /* nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_GLOBAL    0x100   /* Global TLB entry */
+
+#define _PAGE_PROTNONE  0x080   /* If not present */
+#define _PAGE_NX        (_AC(1,UL)<<_PAGE_BIT_NX)
+
+#define _PAGE_TABLE     (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE   (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define _PAGE_CHG_MASK  (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define PAGE_NONE       __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED     __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_COPY PAGE_COPY_NOEXEC
+#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_READONLY   __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define __PAGE_KERNEL \
+        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
+#define __PAGE_KERNEL_EXEC \
+        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_NOCACHE \
+        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED | _PAGE_NX)
+#define __PAGE_KERNEL_RO \
+        (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
+#define __PAGE_KERNEL_VSYSCALL \
+        (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_VSYSCALL_NOCACHE \
+        (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_PCD)
+#define __PAGE_KERNEL_LARGE \
+        (__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_EXEC \
+        (__PAGE_KERNEL_EXEC | _PAGE_PSE)
+
+#define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)
+
+#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
+#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_VSYSCALL32 __pgprot(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+
+/*         xwr */
+#define __P000  PAGE_NONE
+#define __P001  PAGE_READONLY
+#define __P010  PAGE_COPY
+#define __P011  PAGE_COPY
+#define __P100  PAGE_READONLY_EXEC
+#define __P101  PAGE_READONLY_EXEC
+#define __P110  PAGE_COPY_EXEC
+#define __P111  PAGE_COPY_EXEC
+
+#define __S000  PAGE_NONE
+#define __S001  PAGE_READONLY
+#define __S010  PAGE_SHARED
+#define __S011  PAGE_SHARED
+#define __S100  PAGE_READONLY_EXEC
+#define __S101  PAGE_READONLY_EXEC
+#define __S110  PAGE_SHARED_EXEC
+#define __S111  PAGE_SHARED_EXEC
+
+#ifndef __ASSEMBLY__
+
+static inline unsigned long pgd_bad(pgd_t pgd)
+{
+        return pgd_val(pgd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+}
+
+static inline unsigned long pud_bad(pud_t pud)
+{
+        return pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+}
+
+static inline unsigned long pmd_bad(pmd_t pmd)
+{
+        return pmd_val(pmd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+}
+
+#define pte_none(x)     (!pte_val(x))
+#define pte_present(x)  (pte_val(x) & (_PAGE_PRESENT | _PAGE_PROTNONE))
+#define pte_clear(mm,addr,xp)   do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
+
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) /* FIXME: is this
+                                                   right? */
+#define pte_page(x)     pfn_to_page(pte_pfn(x))
+#define pte_pfn(x)  ((pte_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)
+
+static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+        pte_t pte;
+        pte_val(pte) = (page_nr << PAGE_SHIFT);
+        pte_val(pte) |= pgprot_val(pgprot);
+        pte_val(pte) &= __supported_pte_mask;
+        return pte;
+}
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT)
+static inline int pte_dirty(pte_t pte)          { return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)          { return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte)          { return pte_val(pte) & _PAGE_RW; }
+static inline int pte_file(pte_t pte)           { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_huge(pte_t pte)           { return pte_val(pte) & _PAGE_PSE; }
+
+static inline pte_t pte_mkclean(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkold(pte_t pte)        { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_wrprotect(pte_t pte)    { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
+static inline pte_t pte_mkexec(pte_t pte)       { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_NX)); return pte; }
+static inline pte_t pte_mkdirty(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkyoung(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_mkwrite(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)       { set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
+static inline pte_t pte_clrhuge(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }
+
+struct vm_area_struct;
+
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+        if (!pte_young(*ptep))
+                return 0;
+        return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte);
+}
+
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+        clear_bit(_PAGE_BIT_RW, &ptep->pte);
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+#define pgprot_noncached(prot)  (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))
+
+static inline int pmd_large(pmd_t pte) { 
+        return (pmd_val(pte) & __LARGE_PTE) == __LARGE_PTE; 
+}       
+
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+/*
+ * Level 4 access.
+ */
+#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, addr) ((mm)->pgd + pgd_index(addr))
+#define pgd_offset_k(address) (init_level4_pgt + pgd_index(address))
+#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
+#define mk_kernel_pgd(address) ((pgd_t){ (address) | _KERNPG_TABLE })
+
+/* PUD - Level3 access */
+/* to find an entry in a page-table-directory. */
+#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK))
+#define pud_page(pud)           (pfn_to_page(pud_val(pud) >> PAGE_SHIFT))
+#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
+#define pud_offset(pgd, address) ((pud_t *) pgd_page_vaddr(*(pgd)) + pud_index(address))
+#define pud_present(pud) (pud_val(pud) & _PAGE_PRESENT)
+
+/* PMD  - Level 2 access */
+#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK))
+#define pmd_page(pmd)           (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+
+#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+#define pmd_offset(dir, address) ((pmd_t *) pud_page_vaddr(*(dir)) + \
+                        pmd_index(address))
+#define pmd_none(x)     (!pmd_val(x))
+#define pmd_present(x)  (pmd_val(x) & _PAGE_PRESENT)
+#define pmd_clear(xp)   do { set_pmd(xp, __pmd(0)); } while (0)
+#define pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pmd_pfn(x)  ((pmd_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)
+
+#define pte_to_pgoff(pte) ((pte_val(pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
+#define pgoff_to_pte(off) ((pte_t) { ((off) << PAGE_SHIFT) | _PAGE_FILE })
+#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT
+
+/* PTE - Level 1 access. */
+
+/* page, protection -> pte */
+#define mk_pte(page, pgprot)    pfn_pte(page_to_pfn(page), (pgprot))
+#define mk_pte_huge(entry) (pte_val(entry) |= _PAGE_PRESENT | _PAGE_PSE)
+ 
+/* Change flags of a PTE */
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{ 
+        pte_val(pte) &= _PAGE_CHG_MASK;
+        pte_val(pte) |= pgprot_val(newprot);
+        pte_val(pte) &= __supported_pte_mask;
+       return pte; 
+}
+
+#define pte_index(address) \
+                (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
+                        pte_index(address))
+
+/* x86-64 always has all page tables mapped. */
+#define pte_offset_map(dir,address) pte_offset_kernel(dir,address)
+#define pte_offset_map_nested(dir,address) pte_offset_kernel(dir,address)
+#define pte_unmap(pte) /* NOP */
+#define pte_unmap_nested(pte) /* NOP */ 
+
+#define update_mmu_cache(vma,address,pte) do { } while (0)
+
+/* We only update the dirty/accessed state if we set
+ * the dirty bit by hand in the kernel, since the hardware
+ * will do the accessed bit for us, and we don't want to
+ * race with other CPU's that might be updating the dirty
+ * bit at the same time. */
+#define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+({                                                                        \
+        int __changed = !pte_same(*(__ptep), __entry);                    \
+        if (__changed && __dirty) {                                       \
+                set_pte(__ptep, __entry);                                 \
+                flush_tlb_page(__vma, __address);                         \
+        }                                                                 \
+        __changed;                                                        \
+})
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x)                   (((x).val >> 1) & 0x3f)
+#define __swp_offset(x)                 ((x).val >> 8)
+#define __swp_entry(type, offset)       ((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
+#define __pte_to_swp_entry(pte)         ((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)           ((pte_t) { (x).val })
+
+extern spinlock_t pgd_lock;
+extern struct list_head pgd_list;
+
+extern int kern_addr_valid(unsigned long addr); 
+
+pte_t *lookup_address(unsigned long addr);
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)         \
+                remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#define HAVE_ARCH_UNMAPPED_AREA
+
+#define pgtable_cache_init()   do { } while (0)
+#define check_pgt_cache()      do { } while (0)
+
+#define PAGE_AGP    PAGE_KERNEL_NOCACHE
+#define HAVE_PAGE_AGP 1
+
+/* fs/proc/kcore.c */
+#define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
+#define kc_offset_to_vaddr(o) \
+   (((o) & (1UL << (__VIRTUAL_MASK_SHIFT-1))) ? ((o) | (~__VIRTUAL_MASK)) : (o))
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+#define __HAVE_ARCH_PTE_SAME
+#include <asm-generic/pgtable.h>
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _X86_64_PGTABLE_H */
diff --git a/include/asm-x86/poll.h b/include/asm-x86/poll.h
new file mode 100644
index 000000000000..c98509d3149e
--- /dev/null
+++ b/include/asm-x86/poll.h
@@ -0,0 +1 @@
+#include <asm-generic/poll.h>
diff --git a/include/asm-x86/posix_types.h b/include/asm-x86/posix_types.h
new file mode 100644
index 000000000000..bb7133dc155d
--- /dev/null
+++ b/include/asm-x86/posix_types.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "posix_types_32.h"
+# else
+#  include "posix_types_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "posix_types_32.h"
+# else
+#  include "posix_types_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/posix_types_32.h b/include/asm-x86/posix_types_32.h
new file mode 100644
index 000000000000..133e31e7dfde
--- /dev/null
+++ b/include/asm-x86/posix_types_32.h
@@ -0,0 +1,82 @@
+#ifndef __ARCH_I386_POSIX_TYPES_H
+#define __ARCH_I386_POSIX_TYPES_H
+
+/*
+ * This file is generally used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.  Also, we cannot
+ * assume GCC is being used.
+ */
+
+typedef unsigned long   __kernel_ino_t;
+typedef unsigned short  __kernel_mode_t;
+typedef unsigned short  __kernel_nlink_t;
+typedef long            __kernel_off_t;
+typedef int             __kernel_pid_t;
+typedef unsigned short  __kernel_ipc_pid_t;
+typedef unsigned short  __kernel_uid_t;
+typedef unsigned short  __kernel_gid_t;
+typedef unsigned int    __kernel_size_t;
+typedef int             __kernel_ssize_t;
+typedef int             __kernel_ptrdiff_t;
+typedef long            __kernel_time_t;
+typedef long            __kernel_suseconds_t;
+typedef long            __kernel_clock_t;
+typedef int             __kernel_timer_t;
+typedef int             __kernel_clockid_t;
+typedef int             __kernel_daddr_t;
+typedef char *          __kernel_caddr_t;
+typedef unsigned short  __kernel_uid16_t;
+typedef unsigned short  __kernel_gid16_t;
+typedef unsigned int    __kernel_uid32_t;
+typedef unsigned int    __kernel_gid32_t;
+
+typedef unsigned short  __kernel_old_uid_t;
+typedef unsigned short  __kernel_old_gid_t;
+typedef unsigned short  __kernel_old_dev_t;
+
+#ifdef __GNUC__
+typedef long long       __kernel_loff_t;
+#endif
+
+typedef struct {
+#if defined(__KERNEL__) || defined(__USE_ALL)
+        int     val[2];
+#else /* !defined(__KERNEL__) && !defined(__USE_ALL) */
+        int     __val[2];
+#endif /* !defined(__KERNEL__) && !defined(__USE_ALL) */
+} __kernel_fsid_t;
+
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+
+#undef  __FD_SET
+#define __FD_SET(fd,fdsetp) \
+                __asm__ __volatile__("btsl %1,%0": \
+                        "+m" (*(__kernel_fd_set *) (fdsetp)):"r" ((int) (fd)))
+
+#undef  __FD_CLR
+#define __FD_CLR(fd,fdsetp) \
+                __asm__ __volatile__("btrl %1,%0": \
+                        "+m" (*(__kernel_fd_set *) (fdsetp)):"r" ((int) (fd)))
+
+#undef  __FD_ISSET
+#define __FD_ISSET(fd,fdsetp) (__extension__ ({ \
+                unsigned char __result; \
+                __asm__ __volatile__("btl %1,%2 ; setb %0" \
+                        :"=q" (__result) :"r" ((int) (fd)), \
+                        "m" (*(__kernel_fd_set *) (fdsetp))); \
+                __result; }))
+
+#undef  __FD_ZERO
+#define __FD_ZERO(fdsetp) \
+do { \
+        int __d0, __d1; \
+        __asm__ __volatile__("cld ; rep ; stosl" \
+                        :"=m" (*(__kernel_fd_set *) (fdsetp)), \
+                          "=&c" (__d0), "=&D" (__d1) \
+                        :"a" (0), "1" (__FDSET_LONGS), \
+                        "2" ((__kernel_fd_set *) (fdsetp)) : "memory"); \
+} while (0)
+
+#endif /* defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) */
+
+#endif
diff --git a/include/asm-x86/posix_types_64.h b/include/asm-x86/posix_types_64.h
new file mode 100644
index 000000000000..9926aa43775b
--- /dev/null
+++ b/include/asm-x86/posix_types_64.h
@@ -0,0 +1,119 @@
+#ifndef _ASM_X86_64_POSIX_TYPES_H
+#define _ASM_X86_64_POSIX_TYPES_H
+
+/*
+ * This file is generally used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.  Also, we cannot
+ * assume GCC is being used.
+ */
+
+typedef unsigned long   __kernel_ino_t;
+typedef unsigned int    __kernel_mode_t;
+typedef unsigned long   __kernel_nlink_t;
+typedef long            __kernel_off_t;
+typedef int             __kernel_pid_t;
+typedef int             __kernel_ipc_pid_t;
+typedef unsigned int    __kernel_uid_t;
+typedef unsigned int    __kernel_gid_t;
+typedef unsigned long   __kernel_size_t;
+typedef long            __kernel_ssize_t;
+typedef long            __kernel_ptrdiff_t;
+typedef long            __kernel_time_t;
+typedef long            __kernel_suseconds_t;
+typedef long            __kernel_clock_t;
+typedef int             __kernel_timer_t;
+typedef int             __kernel_clockid_t;
+typedef int             __kernel_daddr_t;
+typedef char *          __kernel_caddr_t;
+typedef unsigned short  __kernel_uid16_t;
+typedef unsigned short  __kernel_gid16_t;
+
+#ifdef __GNUC__
+typedef long long       __kernel_loff_t;
+#endif
+
+typedef struct {
+        int     val[2];
+} __kernel_fsid_t;
+
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+typedef __kernel_uid_t __kernel_uid32_t;
+typedef __kernel_gid_t __kernel_gid32_t;
+
+typedef unsigned long   __kernel_old_dev_t;
+
+#ifdef __KERNEL__
+
+#undef __FD_SET
+static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
+{
+        unsigned long _tmp = fd / __NFDBITS;
+        unsigned long _rem = fd % __NFDBITS;
+        fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
+}
+
+#undef __FD_CLR
+static __inline__ void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
+{
+        unsigned long _tmp = fd / __NFDBITS;
+        unsigned long _rem = fd % __NFDBITS;
+        fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
+}
+
+#undef __FD_ISSET
+static __inline__ int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
+{
+        unsigned long _tmp = fd / __NFDBITS;
+        unsigned long _rem = fd % __NFDBITS;
+        return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
+}
+
+/*
+ * This will unroll the loop for the normal constant cases (8 or 32 longs,
+ * for 256 and 1024-bit fd_sets respectively)
+ */
+#undef __FD_ZERO
+static __inline__ void __FD_ZERO(__kernel_fd_set *p)
+{
+        unsigned long *tmp = p->fds_bits;
+        int i;
+
+        if (__builtin_constant_p(__FDSET_LONGS)) {
+                switch (__FDSET_LONGS) {
+                        case 32:
+                          tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
+                          tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
+                          tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
+                          tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
+                          tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
+                          tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
+                          tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
+                          tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
+                          return;
+                        case 16:
+                          tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
+                          tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
+                          tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
+                          tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
+                          return;
+                        case 8:
+                          tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
+                          tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
+                          return;
+                        case 4:
+                          tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
+                          return;
+                }
+        }
+        i = __FDSET_LONGS;
+        while (i) {
+                i--;
+                *tmp = 0;
+                tmp++;
+        }
+}
+
+#endif /* defined(__KERNEL__) */
+
+#endif
diff --git a/include/asm-x86/prctl.h b/include/asm-x86/prctl.h
new file mode 100644
index 000000000000..52952adef1ca
--- /dev/null
+++ b/include/asm-x86/prctl.h
@@ -0,0 +1,10 @@
+#ifndef X86_64_PRCTL_H
+#define X86_64_PRCTL_H 1
+
+#define ARCH_SET_GS 0x1001
+#define ARCH_SET_FS 0x1002
+#define ARCH_GET_FS 0x1003
+#define ARCH_GET_GS 0x1004
+
+
+#endif
diff --git a/include/asm-x86/processor-cyrix.h b/include/asm-x86/processor-cyrix.h
new file mode 100644
index 000000000000..97568ada1f97
--- /dev/null
+++ b/include/asm-x86/processor-cyrix.h
@@ -0,0 +1,30 @@
+/*
+ * NSC/Cyrix CPU indexed register access. Must be inlined instead of
+ * macros to ensure correct access ordering
+ * Access order is always 0x22 (=offset), 0x23 (=value)
+ *
+ * When using the old macros a line like
+ *   setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+ * gets expanded to:
+ *  do {
+ *    outb((CX86_CCR2), 0x22);
+ *    outb((({
+ *        outb((CX86_CCR2), 0x22);
+ *        inb(0x23);
+ *    }) | 0x88), 0x23);
+ *  } while (0);
+ *
+ * which in fact violates the access order (= 0x22, 0x22, 0x23, 0x23).
+ */
+
+static inline u8 getCx86(u8 reg)
+{
+        outb(reg, 0x22);
+        return inb(0x23);
+}
+
+static inline void setCx86(u8 reg, u8 data)
+{
+        outb(reg, 0x22);
+        outb(data, 0x23);
+}
diff --git a/include/asm-x86/processor-flags.h b/include/asm-x86/processor-flags.h
new file mode 100644
index 000000000000..5404e90edd57
--- /dev/null
+++ b/include/asm-x86/processor-flags.h
@@ -0,0 +1,91 @@
+#ifndef __ASM_I386_PROCESSOR_FLAGS_H
+#define __ASM_I386_PROCESSOR_FLAGS_H
+/* Various flags defined: can be included from assembler. */
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF   0x00000001 /* Carry Flag */
+#define X86_EFLAGS_PF   0x00000004 /* Parity Flag */
+#define X86_EFLAGS_AF   0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_ZF   0x00000040 /* Zero Flag */
+#define X86_EFLAGS_SF   0x00000080 /* Sign Flag */
+#define X86_EFLAGS_TF   0x00000100 /* Trap Flag */
+#define X86_EFLAGS_IF   0x00000200 /* Interrupt Flag */
+#define X86_EFLAGS_DF   0x00000400 /* Direction Flag */
+#define X86_EFLAGS_OF   0x00000800 /* Overflow Flag */
+#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */
+#define X86_EFLAGS_NT   0x00004000 /* Nested Task */
+#define X86_EFLAGS_RF   0x00010000 /* Resume Flag */
+#define X86_EFLAGS_VM   0x00020000 /* Virtual Mode */
+#define X86_EFLAGS_AC   0x00040000 /* Alignment Check */
+#define X86_EFLAGS_VIF  0x00080000 /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP  0x00100000 /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID   0x00200000 /* CPUID detection flag */
+
+/*
+ * Basic CPU control in CR0
+ */
+#define X86_CR0_PE      0x00000001 /* Protection Enable */
+#define X86_CR0_MP      0x00000002 /* Monitor Coprocessor */
+#define X86_CR0_EM      0x00000004 /* Emulation */
+#define X86_CR0_TS      0x00000008 /* Task Switched */
+#define X86_CR0_ET      0x00000010 /* Extension Type */
+#define X86_CR0_NE      0x00000020 /* Numeric Error */
+#define X86_CR0_WP      0x00010000 /* Write Protect */
+#define X86_CR0_AM      0x00040000 /* Alignment Mask */
+#define X86_CR0_NW      0x20000000 /* Not Write-through */
+#define X86_CR0_CD      0x40000000 /* Cache Disable */
+#define X86_CR0_PG      0x80000000 /* Paging */
+
+/*
+ * Paging options in CR3
+ */
+#define X86_CR3_PWT     0x00000008 /* Page Write Through */
+#define X86_CR3_PCD     0x00000010 /* Page Cache Disable */
+
+/*
+ * Intel CPU features in CR4
+ */
+#define X86_CR4_VME     0x00000001 /* enable vm86 extensions */
+#define X86_CR4_PVI     0x00000002 /* virtual interrupts flag enable */
+#define X86_CR4_TSD     0x00000004 /* disable time stamp at ipl 3 */
+#define X86_CR4_DE      0x00000008 /* enable debugging extensions */
+#define X86_CR4_PSE     0x00000010 /* enable page size extensions */
+#define X86_CR4_PAE     0x00000020 /* enable physical address extensions */
+#define X86_CR4_MCE     0x00000040 /* Machine check enable */
+#define X86_CR4_PGE     0x00000080 /* enable global pages */
+#define X86_CR4_PCE     0x00000100 /* enable performance counters at ipl 3 */
+#define X86_CR4_OSFXSR  0x00000200 /* enable fast FPU save and restore */
+#define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
+#define X86_CR4_VMXE    0x00002000 /* enable VMX virtualization */
+
+/*
+ * x86-64 Task Priority Register, CR8
+ */
+#define X86_CR8_TPR     0x00000007 /* task priority register */
+
+/*
+ * AMD and Transmeta use MSRs for configuration; see <asm/msr-index.h>
+ */
+
+/*
+ *      NSC/Cyrix CPU configuration register indexes
+ */
+#define CX86_PCR0       0x20
+#define CX86_GCR        0xb8
+#define CX86_CCR0       0xc0
+#define CX86_CCR1       0xc1
+#define CX86_CCR2       0xc2
+#define CX86_CCR3       0xc3
+#define CX86_CCR4       0xe8
+#define CX86_CCR5       0xe9
+#define CX86_CCR6       0xea
+#define CX86_CCR7       0xeb
+#define CX86_PCR1       0xf0
+#define CX86_DIR0       0xfe
+#define CX86_DIR1       0xff
+#define CX86_ARR_BASE   0xc4
+#define CX86_RCR_BASE   0xdc
+
+#endif  /* __ASM_I386_PROCESSOR_FLAGS_H */
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
new file mode 100644
index 000000000000..46e1c04e309c
--- /dev/null
+++ b/include/asm-x86/processor.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "processor_32.h"
+#else
+# include "processor_64.h"
+#endif
diff --git a/include/asm-x86/processor_32.h b/include/asm-x86/processor_32.h
new file mode 100644
index 000000000000..3845fe72383e
--- /dev/null
+++ b/include/asm-x86/processor_32.h
@@ -0,0 +1,755 @@
+/*
+ * include/asm-i386/processor.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ */
+
+#ifndef __ASM_I386_PROCESSOR_H
+#define __ASM_I386_PROCESSOR_H
+
+#include <asm/vm86.h>
+#include <asm/math_emu.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/sigcontext.h>
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
+#include <asm/system.h>
+#include <linux/cache.h>
+#include <linux/threads.h>
+#include <asm/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <asm/processor-flags.h>
+
+/* flag for disabling the tsc */
+extern int tsc_disable;
+
+struct desc_struct {
+        unsigned long a,b;
+};
+
+#define desc_empty(desc) \
+                (!((desc)->a | (desc)->b))
+
+#define desc_equal(desc1, desc2) \
+                (((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b))
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; })
+
+/*
+ *  CPU type and hardware bug flags. Kept separately for each CPU.
+ *  Members of this structure are referenced in head.S, so think twice
+ *  before touching them. [mj]
+ */
+
+struct cpuinfo_x86 {
+        __u8    x86;            /* CPU family */
+        __u8    x86_vendor;     /* CPU vendor */
+        __u8    x86_model;
+        __u8    x86_mask;
+        char    wp_works_ok;    /* It doesn't on 386's */
+        char    hlt_works_ok;   /* Problems on some 486Dx4's and old 386's */
+        char    hard_math;
+        char    rfu;
+        int     cpuid_level;    /* Maximum supported CPUID level, -1=no CPUID */
+        unsigned long   x86_capability[NCAPINTS];
+        char    x86_vendor_id[16];
+        char    x86_model_id[64];
+        int     x86_cache_size;  /* in KB - valid for CPUS which support this
+                                    call  */
+        int     x86_cache_alignment;    /* In bytes */
+        char    fdiv_bug;
+        char    f00f_bug;
+        char    coma_bug;
+        char    pad0;
+        int     x86_power;
+        unsigned long loops_per_jiffy;
+#ifdef CONFIG_SMP
+        cpumask_t llc_shared_map;       /* cpus sharing the last level cache */
+#endif
+        unsigned char x86_max_cores;    /* cpuid returned max cores value */
+        unsigned char apicid;
+        unsigned short x86_clflush_size;
+#ifdef CONFIG_SMP
+        unsigned char booted_cores;     /* number of cores as seen by OS */
+        __u8 phys_proc_id;              /* Physical processor id. */
+        __u8 cpu_core_id;               /* Core id */
+#endif
+} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+
+#define X86_VENDOR_INTEL 0
+#define X86_VENDOR_CYRIX 1
+#define X86_VENDOR_AMD 2
+#define X86_VENDOR_UMC 3
+#define X86_VENDOR_NEXGEN 4
+#define X86_VENDOR_CENTAUR 5
+#define X86_VENDOR_TRANSMETA 7
+#define X86_VENDOR_NSC 8
+#define X86_VENDOR_NUM 9
+#define X86_VENDOR_UNKNOWN 0xff
+
+/*
+ * capabilities of CPUs
+ */
+
+extern struct cpuinfo_x86 boot_cpu_data;
+extern struct cpuinfo_x86 new_cpu_data;
+extern struct tss_struct doublefault_tss;
+DECLARE_PER_CPU(struct tss_struct, init_tss);
+
+#ifdef CONFIG_SMP
+extern struct cpuinfo_x86 cpu_data[];
+#define current_cpu_data cpu_data[smp_processor_id()]
+#else
+#define cpu_data (&boot_cpu_data)
+#define current_cpu_data boot_cpu_data
+#endif
+
+extern  int cpu_llc_id[NR_CPUS];
+extern char ignore_fpu_irq;
+
+void __init cpu_detect(struct cpuinfo_x86 *c);
+
+extern void identify_boot_cpu(void);
+extern void identify_secondary_cpu(struct cpuinfo_x86 *);
+extern void print_cpu_info(struct cpuinfo_x86 *);
+extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern unsigned short num_cache_leaves;
+
+#ifdef CONFIG_X86_HT
+extern void detect_ht(struct cpuinfo_x86 *c);
+#else
+static inline void detect_ht(struct cpuinfo_x86 *c) {}
+#endif
+
+static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
+                                         unsigned int *ecx, unsigned int *edx)
+{
+        /* ecx is often an input as well as an output. */
+        __asm__("cpuid"
+                : "=a" (*eax),
+                  "=b" (*ebx),
+                  "=c" (*ecx),
+                  "=d" (*edx)
+                : "0" (*eax), "2" (*ecx));
+}
+
+#define load_cr3(pgdir) write_cr3(__pa(pgdir))
+
+/*
+ * Save the cr4 feature set we're using (ie
+ * Pentium 4MB enable and PPro Global page
+ * enable), so that any CPU's that boot up
+ * after us can get the correct flags.
+ */
+extern unsigned long mmu_cr4_features;
+
+static inline void set_in_cr4 (unsigned long mask)
+{
+        unsigned cr4;
+        mmu_cr4_features |= mask;
+        cr4 = read_cr4();
+        cr4 |= mask;
+        write_cr4(cr4);
+}
+
+static inline void clear_in_cr4 (unsigned long mask)
+{
+        unsigned cr4;
+        mmu_cr4_features &= ~mask;
+        cr4 = read_cr4();
+        cr4 &= ~mask;
+        write_cr4(cr4);
+}
+
+/* Stop speculative execution */
+static inline void sync_core(void)
+{
+        int tmp;
+        asm volatile("cpuid" : "=a" (tmp) : "0" (1) : "ebx","ecx","edx","memory");
+}
+
+static inline void __monitor(const void *eax, unsigned long ecx,
+                unsigned long edx)
+{
+        /* "monitor %eax,%ecx,%edx;" */
+        asm volatile(
+                ".byte 0x0f,0x01,0xc8;"
+                : :"a" (eax), "c" (ecx), "d"(edx));
+}
+
+static inline void __mwait(unsigned long eax, unsigned long ecx)
+{
+        /* "mwait %eax,%ecx;" */
+        asm volatile(
+                ".byte 0x0f,0x01,0xc9;"
+                : :"a" (eax), "c" (ecx));
+}
+
+extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
+
+/* from system description table in BIOS.  Mostly for MCA use, but
+others may find it useful. */
+extern unsigned int machine_id;
+extern unsigned int machine_submodel_id;
+extern unsigned int BIOS_revision;
+extern unsigned int mca_pentium_flag;
+
+/* Boot loader type from the setup header */
+extern int bootloader_type;
+
+/*
+ * User space process size: 3GB (default).
+ */
+#define TASK_SIZE       (PAGE_OFFSET)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE      (PAGE_ALIGN(TASK_SIZE / 3))
+
+#define HAVE_ARCH_PICK_MMAP_LAYOUT
+
+extern void hard_disable_TSC(void);
+extern void disable_TSC(void);
+extern void hard_enable_TSC(void);
+
+/*
+ * Size of io_bitmap.
+ */
+#define IO_BITMAP_BITS  65536
+#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8)
+#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long))
+#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap)
+#define INVALID_IO_BITMAP_OFFSET 0x8000
+#define INVALID_IO_BITMAP_OFFSET_LAZY 0x9000
+
+struct i387_fsave_struct {
+        long    cwd;
+        long    swd;
+        long    twd;
+        long    fip;
+        long    fcs;
+        long    foo;
+        long    fos;
+        long    st_space[20];   /* 8*10 bytes for each FP-reg = 80 bytes */
+        long    status;         /* software status information */
+};
+
+struct i387_fxsave_struct {
+        unsigned short  cwd;
+        unsigned short  swd;
+        unsigned short  twd;
+        unsigned short  fop;
+        long    fip;
+        long    fcs;
+        long    foo;
+        long    fos;
+        long    mxcsr;
+        long    mxcsr_mask;
+        long    st_space[32];   /* 8*16 bytes for each FP-reg = 128 bytes */
+        long    xmm_space[32];  /* 8*16 bytes for each XMM-reg = 128 bytes */
+        long    padding[56];
+} __attribute__ ((aligned (16)));
+
+struct i387_soft_struct {
+        long    cwd;
+        long    swd;
+        long    twd;
+        long    fip;
+        long    fcs;
+        long    foo;
+        long    fos;
+        long    st_space[20];   /* 8*10 bytes for each FP-reg = 80 bytes */
+        unsigned char   ftop, changed, lookahead, no_update, rm, alimit;
+        struct info     *info;
+        unsigned long   entry_eip;
+};
+
+union i387_union {
+        struct i387_fsave_struct        fsave;
+        struct i387_fxsave_struct       fxsave;
+        struct i387_soft_struct soft;
+};
+
+typedef struct {
+        unsigned long seg;
+} mm_segment_t;
+
+struct thread_struct;
+
+/* This is the TSS defined by the hardware. */
+struct i386_hw_tss {
+        unsigned short  back_link,__blh;
+        unsigned long   esp0;
+        unsigned short  ss0,__ss0h;
+        unsigned long   esp1;
+        unsigned short  ss1,__ss1h;     /* ss1 is used to cache MSR_IA32_SYSENTER_CS */
+        unsigned long   esp2;
+        unsigned short  ss2,__ss2h;
+        unsigned long   __cr3;
+        unsigned long   eip;
+        unsigned long   eflags;
+        unsigned long   eax,ecx,edx,ebx;
+        unsigned long   esp;
+        unsigned long   ebp;
+        unsigned long   esi;
+        unsigned long   edi;
+        unsigned short  es, __esh;
+        unsigned short  cs, __csh;
+        unsigned short  ss, __ssh;
+        unsigned short  ds, __dsh;
+        unsigned short  fs, __fsh;
+        unsigned short  gs, __gsh;
+        unsigned short  ldt, __ldth;
+        unsigned short  trace, io_bitmap_base;
+} __attribute__((packed));
+
+struct tss_struct {
+        struct i386_hw_tss x86_tss;
+
+        /*
+         * The extra 1 is there because the CPU will access an
+         * additional byte beyond the end of the IO permission
+         * bitmap. The extra byte must be all 1 bits, and must
+         * be within the limit.
+         */
+        unsigned long   io_bitmap[IO_BITMAP_LONGS + 1];
+        /*
+         * Cache the current maximum and the last task that used the bitmap:
+         */
+        unsigned long io_bitmap_max;
+        struct thread_struct *io_bitmap_owner;
+        /*
+         * pads the TSS to be cacheline-aligned (size is 0x100)
+         */
+        unsigned long __cacheline_filler[35];
+        /*
+         * .. and then another 0x100 bytes for emergency kernel stack
+         */
+        unsigned long stack[64];
+} __attribute__((packed));
+
+#define ARCH_MIN_TASKALIGN      16
+
+struct thread_struct {
+/* cached TLS descriptors. */
+        struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES];
+        unsigned long   esp0;
+        unsigned long   sysenter_cs;
+        unsigned long   eip;
+        unsigned long   esp;
+        unsigned long   fs;
+        unsigned long   gs;
+/* Hardware debugging registers */
+        unsigned long   debugreg[8];  /* %%db0-7 debug registers */
+/* fault info */
+        unsigned long   cr2, trap_no, error_code;
+/* floating point info */
+        union i387_union        i387;
+/* virtual 86 mode info */
+        struct vm86_struct __user * vm86_info;
+        unsigned long           screen_bitmap;
+        unsigned long           v86flags, v86mask, saved_esp0;
+        unsigned int            saved_fs, saved_gs;
+/* IO permissions */
+        unsigned long   *io_bitmap_ptr;
+        unsigned long   iopl;
+/* max allowed port in the bitmap, in bytes: */
+        unsigned long   io_bitmap_max;
+};
+
+#define INIT_THREAD  {                                                  \
+        .esp0 = sizeof(init_stack) + (long)&init_stack,                 \
+        .vm86_info = NULL,                                              \
+        .sysenter_cs = __KERNEL_CS,                                     \
+        .io_bitmap_ptr = NULL,                                          \
+        .fs = __KERNEL_PERCPU,                                          \
+}
+
+/*
+ * Note that the .io_bitmap member must be extra-big. This is because
+ * the CPU will access an additional byte beyond the end of the IO
+ * permission bitmap. The extra byte must be all 1 bits, and must
+ * be within the limit.
+ */
+#define INIT_TSS  {                                                     \
+        .x86_tss = {                                                    \
+                .esp0           = sizeof(init_stack) + (long)&init_stack, \
+                .ss0            = __KERNEL_DS,                          \
+                .ss1            = __KERNEL_CS,                          \
+                .io_bitmap_base = INVALID_IO_BITMAP_OFFSET,             \
+         },                                                             \
+        .io_bitmap      = { [ 0 ... IO_BITMAP_LONGS] = ~0 },            \
+}
+
+#define start_thread(regs, new_eip, new_esp) do {               \
+        __asm__("movl %0,%%gs": :"r" (0));                      \
+        regs->xfs = 0;                                          \
+        set_fs(USER_DS);                                        \
+        regs->xds = __USER_DS;                                  \
+        regs->xes = __USER_DS;                                  \
+        regs->xss = __USER_DS;                                  \
+        regs->xcs = __USER_CS;                                  \
+        regs->eip = new_eip;                                    \
+        regs->esp = new_esp;                                    \
+} while (0)
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+
+/* Prepare to copy thread state - unlazy all lazy status */
+extern void prepare_to_copy(struct task_struct *tsk);
+
+/*
+ * create a kernel thread without removing it from tasklists
+ */
+extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+extern unsigned long thread_saved_pc(struct task_struct *tsk);
+void show_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack);
+
+unsigned long get_wchan(struct task_struct *p);
+
+#define THREAD_SIZE_LONGS      (THREAD_SIZE/sizeof(unsigned long))
+#define KSTK_TOP(info)                                                 \
+({                                                                     \
+       unsigned long *__ptr = (unsigned long *)(info);                 \
+       (unsigned long)(&__ptr[THREAD_SIZE_LONGS]);                     \
+})
+
+/*
+ * The below -8 is to reserve 8 bytes on top of the ring0 stack.
+ * This is necessary to guarantee that the entire "struct pt_regs"
+ * is accessable even if the CPU haven't stored the SS/ESP registers
+ * on the stack (interrupt gate does not save these registers
+ * when switching to the same priv ring).
+ * Therefore beware: accessing the xss/esp fields of the
+ * "struct pt_regs" is possible, but they may contain the
+ * completely wrong values.
+ */
+#define task_pt_regs(task)                                             \
+({                                                                     \
+       struct pt_regs *__regs__;                                       \
+       __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \
+       __regs__ - 1;                                                   \
+})
+
+#define KSTK_EIP(task) (task_pt_regs(task)->eip)
+#define KSTK_ESP(task) (task_pt_regs(task)->esp)
+
+
+struct microcode_header {
+        unsigned int hdrver;
+        unsigned int rev;
+        unsigned int date;
+        unsigned int sig;
+        unsigned int cksum;
+        unsigned int ldrver;
+        unsigned int pf;
+        unsigned int datasize;
+        unsigned int totalsize;
+        unsigned int reserved[3];
+};
+
+struct microcode {
+        struct microcode_header hdr;
+        unsigned int bits[0];
+};
+
+typedef struct microcode microcode_t;
+typedef struct microcode_header microcode_header_t;
+
+/* microcode format is extended from prescott processors */
+struct extended_signature {
+        unsigned int sig;
+        unsigned int pf;
+        unsigned int cksum;
+};
+
+struct extended_sigtable {
+        unsigned int count;
+        unsigned int cksum;
+        unsigned int reserved[3];
+        struct extended_signature sigs[0];
+};
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+        __asm__ __volatile__("rep;nop": : :"memory");
+}
+
+#define cpu_relax()     rep_nop()
+
+static inline void native_load_esp0(struct tss_struct *tss, struct thread_struct *thread)
+{
+        tss->x86_tss.esp0 = thread->esp0;
+        /* This can only happen when SEP is enabled, no need to test "SEP"arately */
+        if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
+                tss->x86_tss.ss1 = thread->sysenter_cs;
+                wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+        }
+}
+
+
+static inline unsigned long native_get_debugreg(int regno)
+{
+        unsigned long val = 0;  /* Damn you, gcc! */
+
+        switch (regno) {
+        case 0:
+                asm("movl %%db0, %0" :"=r" (val)); break;
+        case 1:
+                asm("movl %%db1, %0" :"=r" (val)); break;
+        case 2:
+                asm("movl %%db2, %0" :"=r" (val)); break;
+        case 3:
+                asm("movl %%db3, %0" :"=r" (val)); break;
+        case 6:
+                asm("movl %%db6, %0" :"=r" (val)); break;
+        case 7:
+                asm("movl %%db7, %0" :"=r" (val)); break;
+        default:
+                BUG();
+        }
+        return val;
+}
+
+static inline void native_set_debugreg(int regno, unsigned long value)
+{
+        switch (regno) {
+        case 0:
+                asm("movl %0,%%db0"     : /* no output */ :"r" (value));
+                break;
+        case 1:
+                asm("movl %0,%%db1"     : /* no output */ :"r" (value));
+                break;
+        case 2:
+                asm("movl %0,%%db2"     : /* no output */ :"r" (value));
+                break;
+        case 3:
+                asm("movl %0,%%db3"     : /* no output */ :"r" (value));
+                break;
+        case 6:
+                asm("movl %0,%%db6"     : /* no output */ :"r" (value));
+                break;
+        case 7:
+                asm("movl %0,%%db7"     : /* no output */ :"r" (value));
+                break;
+        default:
+                BUG();
+        }
+}
+
+/*
+ * Set IOPL bits in EFLAGS from given mask
+ */
+static inline void native_set_iopl_mask(unsigned mask)
+{
+        unsigned int reg;
+        __asm__ __volatile__ ("pushfl;"
+                              "popl %0;"
+                              "andl %1, %0;"
+                              "orl %2, %0;"
+                              "pushl %0;"
+                              "popfl"
+                                : "=&r" (reg)
+                                : "i" (~X86_EFLAGS_IOPL), "r" (mask));
+}
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define paravirt_enabled() 0
+#define __cpuid native_cpuid
+
+static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread)
+{
+        native_load_esp0(tss, thread);
+}
+
+/*
+ * These special macros can be used to get or set a debugging register
+ */
+#define get_debugreg(var, register)                             \
+        (var) = native_get_debugreg(register)
+#define set_debugreg(value, register)                           \
+        native_set_debugreg(register, value)
+
+#define set_iopl_mask native_set_iopl_mask
+#endif /* CONFIG_PARAVIRT */
+
+/*
+ * Generic CPUID function
+ * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
+ * resulting in stale register contents being returned.
+ */
+static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx)
+{
+        *eax = op;
+        *ecx = 0;
+        __cpuid(eax, ebx, ecx, edx);
+}
+
+/* Some CPUID calls want 'count' to be placed in ecx */
+static inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx,
+                               int *edx)
+{
+        *eax = op;
+        *ecx = count;
+        __cpuid(eax, ebx, ecx, edx);
+}
+
+/*
+ * CPUID functions returning a single datum
+ */
+static inline unsigned int cpuid_eax(unsigned int op)
+{
+        unsigned int eax, ebx, ecx, edx;
+
+        cpuid(op, &eax, &ebx, &ecx, &edx);
+        return eax;
+}
+static inline unsigned int cpuid_ebx(unsigned int op)
+{
+        unsigned int eax, ebx, ecx, edx;
+
+        cpuid(op, &eax, &ebx, &ecx, &edx);
+        return ebx;
+}
+static inline unsigned int cpuid_ecx(unsigned int op)
+{
+        unsigned int eax, ebx, ecx, edx;
+
+        cpuid(op, &eax, &ebx, &ecx, &edx);
+        return ecx;
+}
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+        unsigned int eax, ebx, ecx, edx;
+
+        cpuid(op, &eax, &ebx, &ecx, &edx);
+        return edx;
+}
+
+/* generic versions from gas */
+#define GENERIC_NOP1    ".byte 0x90\n"
+#define GENERIC_NOP2            ".byte 0x89,0xf6\n"
+#define GENERIC_NOP3        ".byte 0x8d,0x76,0x00\n"
+#define GENERIC_NOP4        ".byte 0x8d,0x74,0x26,0x00\n"
+#define GENERIC_NOP5        GENERIC_NOP1 GENERIC_NOP4
+#define GENERIC_NOP6    ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
+#define GENERIC_NOP7    ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
+#define GENERIC_NOP8    GENERIC_NOP1 GENERIC_NOP7
+
+/* Opteron nops */
+#define K8_NOP1 GENERIC_NOP1
+#define K8_NOP2 ".byte 0x66,0x90\n" 
+#define K8_NOP3 ".byte 0x66,0x66,0x90\n" 
+#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n" 
+#define K8_NOP5 K8_NOP3 K8_NOP2 
+#define K8_NOP6 K8_NOP3 K8_NOP3
+#define K8_NOP7 K8_NOP4 K8_NOP3
+#define K8_NOP8 K8_NOP4 K8_NOP4
+
+/* K7 nops */
+/* uses eax dependencies (arbitary choice) */
+#define K7_NOP1  GENERIC_NOP1
+#define K7_NOP2 ".byte 0x8b,0xc0\n" 
+#define K7_NOP3 ".byte 0x8d,0x04,0x20\n"
+#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n"
+#define K7_NOP5 K7_NOP4 ASM_NOP1
+#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n"
+#define K7_NOP7        ".byte 0x8D,0x04,0x05,0,0,0,0\n"
+#define K7_NOP8        K7_NOP7 ASM_NOP1
+
+#ifdef CONFIG_MK8
+#define ASM_NOP1 K8_NOP1
+#define ASM_NOP2 K8_NOP2
+#define ASM_NOP3 K8_NOP3
+#define ASM_NOP4 K8_NOP4
+#define ASM_NOP5 K8_NOP5
+#define ASM_NOP6 K8_NOP6
+#define ASM_NOP7 K8_NOP7
+#define ASM_NOP8 K8_NOP8
+#elif defined(CONFIG_MK7)
+#define ASM_NOP1 K7_NOP1
+#define ASM_NOP2 K7_NOP2
+#define ASM_NOP3 K7_NOP3
+#define ASM_NOP4 K7_NOP4
+#define ASM_NOP5 K7_NOP5
+#define ASM_NOP6 K7_NOP6
+#define ASM_NOP7 K7_NOP7
+#define ASM_NOP8 K7_NOP8
+#else
+#define ASM_NOP1 GENERIC_NOP1
+#define ASM_NOP2 GENERIC_NOP2
+#define ASM_NOP3 GENERIC_NOP3
+#define ASM_NOP4 GENERIC_NOP4
+#define ASM_NOP5 GENERIC_NOP5
+#define ASM_NOP6 GENERIC_NOP6
+#define ASM_NOP7 GENERIC_NOP7
+#define ASM_NOP8 GENERIC_NOP8
+#endif
+
+#define ASM_NOP_MAX 8
+
+/* Prefetch instructions for Pentium III and AMD Athlon */
+/* It's not worth to care about 3dnow! prefetches for the K6
+   because they are microcoded there and very slow.
+   However we don't do prefetches for pre XP Athlons currently
+   That should be fixed. */
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(const void *x)
+{
+        alternative_input(ASM_NOP4,
+                          "prefetchnta (%1)",
+                          X86_FEATURE_XMM,
+                          "r" (x));
+}
+
+#define ARCH_HAS_PREFETCH
+#define ARCH_HAS_PREFETCHW
+#define ARCH_HAS_SPINLOCK_PREFETCH
+
+/* 3dnow! prefetch to get an exclusive cache line. Useful for 
+   spinlocks to avoid one state transition in the cache coherency protocol. */
+static inline void prefetchw(const void *x)
+{
+        alternative_input(ASM_NOP4,
+                          "prefetchw (%1)",
+                          X86_FEATURE_3DNOW,
+                          "r" (x));
+}
+#define spin_lock_prefetch(x)   prefetchw(x)
+
+extern void select_idle_routine(const struct cpuinfo_x86 *c);
+
+#define cache_line_size() (boot_cpu_data.x86_cache_alignment)
+
+extern unsigned long boot_option_idle_override;
+extern void enable_sep_cpu(void);
+extern int sysenter_setup(void);
+
+/* Defined in head.S */
+extern struct Xgt_desc_struct early_gdt_descr;
+
+extern void cpu_set_gdt(int);
+extern void switch_to_new_gdt(void);
+extern void cpu_init(void);
+extern void init_gdt(int cpu);
+
+extern int force_mwait;
+
+#endif /* __ASM_I386_PROCESSOR_H */
diff --git a/include/asm-x86/processor_64.h b/include/asm-x86/processor_64.h
new file mode 100644
index 000000000000..31f579b828f2
--- /dev/null
+++ b/include/asm-x86/processor_64.h
@@ -0,0 +1,439 @@
+/*
+ * include/asm-x86_64/processor.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ */
+
+#ifndef __ASM_X86_64_PROCESSOR_H
+#define __ASM_X86_64_PROCESSOR_H
+
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/sigcontext.h>
+#include <asm/cpufeature.h>
+#include <linux/threads.h>
+#include <asm/msr.h>
+#include <asm/current.h>
+#include <asm/system.h>
+#include <asm/mmsegment.h>
+#include <asm/percpu.h>
+#include <linux/personality.h>
+#include <linux/cpumask.h>
+#include <asm/processor-flags.h>
+
+#define TF_MASK         0x00000100
+#define IF_MASK         0x00000200
+#define IOPL_MASK       0x00003000
+#define NT_MASK         0x00004000
+#define VM_MASK         0x00020000
+#define AC_MASK         0x00040000
+#define VIF_MASK        0x00080000      /* virtual interrupt flag */
+#define VIP_MASK        0x00100000      /* virtual interrupt pending */
+#define ID_MASK         0x00200000
+
+#define desc_empty(desc) \
+               (!((desc)->a | (desc)->b))
+
+#define desc_equal(desc1, desc2) \
+               (((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b))
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ void *pc; asm volatile("leaq 1f(%%rip),%0\n1:":"=r"(pc)); pc; })
+
+/*
+ *  CPU type and hardware bug flags. Kept separately for each CPU.
+ */
+
+struct cpuinfo_x86 {
+        __u8    x86;            /* CPU family */
+        __u8    x86_vendor;     /* CPU vendor */
+        __u8    x86_model;
+        __u8    x86_mask;
+        int     cpuid_level;    /* Maximum supported CPUID level, -1=no CPUID */
+        __u32   x86_capability[NCAPINTS];
+        char    x86_vendor_id[16];
+        char    x86_model_id[64];
+        int     x86_cache_size;  /* in KB */
+        int     x86_clflush_size;
+        int     x86_cache_alignment;
+        int     x86_tlbsize;    /* number of 4K pages in DTLB/ITLB combined(in pages)*/
+        __u8    x86_virt_bits, x86_phys_bits;
+        __u8    x86_max_cores;  /* cpuid returned max cores value */
+        __u32   x86_power;      
+        __u32   extended_cpuid_level;   /* Max extended CPUID function supported */
+        unsigned long loops_per_jiffy;
+#ifdef CONFIG_SMP
+        cpumask_t llc_shared_map;       /* cpus sharing the last level cache */
+#endif
+        __u8    apicid;
+#ifdef CONFIG_SMP
+        __u8    booted_cores;   /* number of cores as seen by OS */
+        __u8    phys_proc_id;   /* Physical Processor id. */
+        __u8    cpu_core_id;    /* Core id. */
+#endif
+} ____cacheline_aligned;
+
+#define X86_VENDOR_INTEL 0
+#define X86_VENDOR_CYRIX 1
+#define X86_VENDOR_AMD 2
+#define X86_VENDOR_UMC 3
+#define X86_VENDOR_NEXGEN 4
+#define X86_VENDOR_CENTAUR 5
+#define X86_VENDOR_TRANSMETA 7
+#define X86_VENDOR_NUM 8
+#define X86_VENDOR_UNKNOWN 0xff
+
+#ifdef CONFIG_SMP
+extern struct cpuinfo_x86 cpu_data[];
+#define current_cpu_data cpu_data[smp_processor_id()]
+#else
+#define cpu_data (&boot_cpu_data)
+#define current_cpu_data boot_cpu_data
+#endif
+
+extern char ignore_irq13;
+
+extern void identify_cpu(struct cpuinfo_x86 *);
+extern void print_cpu_info(struct cpuinfo_x86 *);
+extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern unsigned short num_cache_leaves;
+
+/*
+ * Save the cr4 feature set we're using (ie
+ * Pentium 4MB enable and PPro Global page
+ * enable), so that any CPU's that boot up
+ * after us can get the correct flags.
+ */
+extern unsigned long mmu_cr4_features;
+
+static inline void set_in_cr4 (unsigned long mask)
+{
+        mmu_cr4_features |= mask;
+        __asm__("movq %%cr4,%%rax\n\t"
+                "orq %0,%%rax\n\t"
+                "movq %%rax,%%cr4\n"
+                : : "irg" (mask)
+                :"ax");
+}
+
+static inline void clear_in_cr4 (unsigned long mask)
+{
+        mmu_cr4_features &= ~mask;
+        __asm__("movq %%cr4,%%rax\n\t"
+                "andq %0,%%rax\n\t"
+                "movq %%rax,%%cr4\n"
+                : : "irg" (~mask)
+                :"ax");
+}
+
+
+/*
+ * User space process size. 47bits minus one guard page.
+ */
+#define TASK_SIZE64     (0x800000000000UL - 4096)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? 0xc0000000 : 0xFFFFe000)
+
+#define TASK_SIZE               (test_thread_flag(TIF_IA32) ? IA32_PAGE_OFFSET : TASK_SIZE64)
+#define TASK_SIZE_OF(child)     ((test_tsk_thread_flag(child, TIF_IA32)) ? IA32_PAGE_OFFSET : TASK_SIZE64)
+
+#define TASK_UNMAPPED_BASE      PAGE_ALIGN(TASK_SIZE/3)
+
+/*
+ * Size of io_bitmap.
+ */
+#define IO_BITMAP_BITS  65536
+#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8)
+#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long))
+#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap)
+#define INVALID_IO_BITMAP_OFFSET 0x8000
+
+struct i387_fxsave_struct {
+        u16     cwd;
+        u16     swd;
+        u16     twd;
+        u16     fop;
+        u64     rip;
+        u64     rdp; 
+        u32     mxcsr;
+        u32     mxcsr_mask;
+        u32     st_space[32];   /* 8*16 bytes for each FP-reg = 128 bytes */
+        u32     xmm_space[64];  /* 16*16 bytes for each XMM-reg = 256 bytes */
+        u32     padding[24];
+} __attribute__ ((aligned (16)));
+
+union i387_union {
+        struct i387_fxsave_struct       fxsave;
+};
+
+struct tss_struct {
+        u32 reserved1;
+        u64 rsp0;       
+        u64 rsp1;
+        u64 rsp2;
+        u64 reserved2;
+        u64 ist[7];
+        u32 reserved3;
+        u32 reserved4;
+        u16 reserved5;
+        u16 io_bitmap_base;
+        /*
+         * The extra 1 is there because the CPU will access an
+         * additional byte beyond the end of the IO permission
+         * bitmap. The extra byte must be all 1 bits, and must
+         * be within the limit. Thus we have:
+         *
+         * 128 bytes, the bitmap itself, for ports 0..0x3ff
+         * 8 bytes, for an extra "long" of ~0UL
+         */
+        unsigned long io_bitmap[IO_BITMAP_LONGS + 1];
+} __attribute__((packed)) ____cacheline_aligned;
+
+
+extern struct cpuinfo_x86 boot_cpu_data;
+DECLARE_PER_CPU(struct tss_struct,init_tss);
+/* Save the original ist values for checking stack pointers during debugging */
+struct orig_ist {
+        unsigned long ist[7];
+};
+DECLARE_PER_CPU(struct orig_ist, orig_ist);
+
+#ifdef CONFIG_X86_VSMP
+#define ARCH_MIN_TASKALIGN      (1 << INTERNODE_CACHE_SHIFT)
+#define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT)
+#else
+#define ARCH_MIN_TASKALIGN      16
+#define ARCH_MIN_MMSTRUCT_ALIGN 0
+#endif
+
+struct thread_struct {
+        unsigned long   rsp0;
+        unsigned long   rsp;
+        unsigned long   userrsp;        /* Copy from PDA */ 
+        unsigned long   fs;
+        unsigned long   gs;
+        unsigned short  es, ds, fsindex, gsindex;       
+/* Hardware debugging registers */
+        unsigned long   debugreg0;  
+        unsigned long   debugreg1;  
+        unsigned long   debugreg2;  
+        unsigned long   debugreg3;  
+        unsigned long   debugreg6;  
+        unsigned long   debugreg7;  
+/* fault info */
+        unsigned long   cr2, trap_no, error_code;
+/* floating point info */
+        union i387_union        i387  __attribute__((aligned(16)));
+/* IO permissions. the bitmap could be moved into the GDT, that would make
+   switch faster for a limited number of ioperm using tasks. -AK */
+        int             ioperm;
+        unsigned long   *io_bitmap_ptr;
+        unsigned io_bitmap_max;
+/* cached TLS descriptors. */
+        u64 tls_array[GDT_ENTRY_TLS_ENTRIES];
+} __attribute__((aligned(16)));
+
+#define INIT_THREAD  { \
+        .rsp0 = (unsigned long)&init_stack + sizeof(init_stack) \
+}
+
+#define INIT_TSS  { \
+        .rsp0 = (unsigned long)&init_stack + sizeof(init_stack) \
+}
+
+#define INIT_MMAP \
+{ &init_mm, 0, 0, NULL, PAGE_SHARED, VM_READ | VM_WRITE | VM_EXEC, 1, NULL, NULL }
+
+#define start_thread(regs,new_rip,new_rsp) do { \
+        asm volatile("movl %0,%%fs; movl %0,%%es; movl %0,%%ds": :"r" (0));      \
+        load_gs_index(0);                                                       \
+        (regs)->rip = (new_rip);                                                 \
+        (regs)->rsp = (new_rsp);                                                 \
+        write_pda(oldrsp, (new_rsp));                                            \
+        (regs)->cs = __USER_CS;                                                  \
+        (regs)->ss = __USER_DS;                                                  \
+        (regs)->eflags = 0x200;                                                  \
+        set_fs(USER_DS);                                                         \
+} while(0) 
+
+#define get_debugreg(var, register)                             \
+                __asm__("movq %%db" #register ", %0"            \
+                        :"=r" (var))
+#define set_debugreg(value, register)                   \
+                __asm__("movq %0,%%db" #register                \
+                        : /* no output */                       \
+                        :"r" (value))
+
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+
+/* Prepare to copy thread state - unlazy all lazy status */
+extern void prepare_to_copy(struct task_struct *tsk);
+
+/*
+ * create a kernel thread without removing it from tasklists
+ */
+extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+/*
+ * Return saved PC of a blocked thread.
+ * What is this good for? it will be always the scheduler or ret_from_fork.
+ */
+#define thread_saved_pc(t) (*(unsigned long *)((t)->thread.rsp - 8))
+
+extern unsigned long get_wchan(struct task_struct *p);
+#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.rsp0 - 1)
+#define KSTK_EIP(tsk) (task_pt_regs(tsk)->rip)
+#define KSTK_ESP(tsk) -1 /* sorry. doesn't work for syscall. */
+
+
+struct microcode_header {
+        unsigned int hdrver;
+        unsigned int rev;
+        unsigned int date;
+        unsigned int sig;
+        unsigned int cksum;
+        unsigned int ldrver;
+        unsigned int pf;
+        unsigned int datasize;
+        unsigned int totalsize;
+        unsigned int reserved[3];
+};
+
+struct microcode {
+        struct microcode_header hdr;
+        unsigned int bits[0];
+};
+
+typedef struct microcode microcode_t;
+typedef struct microcode_header microcode_header_t;
+
+/* microcode format is extended from prescott processors */
+struct extended_signature {
+        unsigned int sig;
+        unsigned int pf;
+        unsigned int cksum;
+};
+
+struct extended_sigtable {
+        unsigned int count;
+        unsigned int cksum;
+        unsigned int reserved[3];
+        struct extended_signature sigs[0];
+};
+
+
+#define ASM_NOP1 K8_NOP1
+#define ASM_NOP2 K8_NOP2
+#define ASM_NOP3 K8_NOP3
+#define ASM_NOP4 K8_NOP4
+#define ASM_NOP5 K8_NOP5
+#define ASM_NOP6 K8_NOP6
+#define ASM_NOP7 K8_NOP7
+#define ASM_NOP8 K8_NOP8
+
+/* Opteron nops */
+#define K8_NOP1 ".byte 0x90\n"
+#define K8_NOP2 ".byte 0x66,0x90\n" 
+#define K8_NOP3 ".byte 0x66,0x66,0x90\n" 
+#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n" 
+#define K8_NOP5 K8_NOP3 K8_NOP2 
+#define K8_NOP6 K8_NOP3 K8_NOP3
+#define K8_NOP7 K8_NOP4 K8_NOP3
+#define K8_NOP8 K8_NOP4 K8_NOP4
+
+#define ASM_NOP_MAX 8
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+        __asm__ __volatile__("rep;nop": : :"memory");
+}
+
+/* Stop speculative execution */
+static inline void sync_core(void)
+{ 
+        int tmp;
+        asm volatile("cpuid" : "=a" (tmp) : "0" (1) : "ebx","ecx","edx","memory");
+} 
+
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(void *x) 
+{ 
+        asm volatile("prefetcht0 (%0)" :: "r" (x));
+} 
+
+#define ARCH_HAS_PREFETCHW 1
+static inline void prefetchw(void *x) 
+{ 
+        alternative_input("prefetcht0 (%1)",
+                          "prefetchw (%1)",
+                          X86_FEATURE_3DNOW,
+                          "r" (x));
+} 
+
+#define ARCH_HAS_SPINLOCK_PREFETCH 1
+
+#define spin_lock_prefetch(x)  prefetchw(x)
+
+#define cpu_relax()   rep_nop()
+
+static inline void serialize_cpu(void)
+{
+        __asm__ __volatile__ ("cpuid" : : : "ax", "bx", "cx", "dx");
+}
+
+static inline void __monitor(const void *eax, unsigned long ecx,
+                unsigned long edx)
+{
+        /* "monitor %eax,%ecx,%edx;" */
+        asm volatile(
+                ".byte 0x0f,0x01,0xc8;"
+                : :"a" (eax), "c" (ecx), "d"(edx));
+}
+
+static inline void __mwait(unsigned long eax, unsigned long ecx)
+{
+        /* "mwait %eax,%ecx;" */
+        asm volatile(
+                ".byte 0x0f,0x01,0xc9;"
+                : :"a" (eax), "c" (ecx));
+}
+
+static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+{
+        /* "mwait %eax,%ecx;" */
+        asm volatile(
+                "sti; .byte 0x0f,0x01,0xc9;"
+                : :"a" (eax), "c" (ecx));
+}
+
+extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
+
+#define stack_current() \
+({                                                              \
+        struct thread_info *ti;                                 \
+        asm("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK));  \
+        ti->task;                                       \
+})
+
+#define cache_line_size() (boot_cpu_data.x86_cache_alignment)
+
+extern unsigned long boot_option_idle_override;
+/* Boot loader type from the setup header */
+extern int bootloader_type;
+
+#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
+
+#endif /* __ASM_X86_64_PROCESSOR_H */
diff --git a/include/asm-x86/proto.h b/include/asm-x86/proto.h
new file mode 100644
index 000000000000..31f20ad65876
--- /dev/null
+++ b/include/asm-x86/proto.h
@@ -0,0 +1,104 @@
+#ifndef _ASM_X8664_PROTO_H
+#define _ASM_X8664_PROTO_H 1
+
+#include <asm/ldt.h>
+
+/* misc architecture specific prototypes */
+
+struct cpuinfo_x86; 
+struct pt_regs;
+
+extern void start_kernel(void);
+extern void pda_init(int); 
+
+extern void early_idt_handler(void);
+
+extern void mcheck_init(struct cpuinfo_x86 *c);
+extern void init_memory_mapping(unsigned long start, unsigned long end);
+
+extern void system_call(void); 
+extern int kernel_syscall(void);
+extern void syscall_init(void);
+
+extern void ia32_syscall(void);
+extern void ia32_cstar_target(void); 
+extern void ia32_sysenter_target(void); 
+
+extern void config_acpi_tables(void);
+extern void ia32_syscall(void);
+
+extern int pmtimer_mark_offset(void);
+extern void pmtimer_resume(void);
+extern void pmtimer_wait(unsigned);
+extern unsigned int do_gettimeoffset_pm(void);
+#ifdef CONFIG_X86_PM_TIMER
+extern u32 pmtmr_ioport;
+#else
+#define pmtmr_ioport 0
+#endif
+extern int nohpet;
+
+extern void early_printk(const char *fmt, ...) __attribute__((format(printf,1,2)));
+
+extern void early_identify_cpu(struct cpuinfo_x86 *c);
+
+extern int k8_scan_nodes(unsigned long start, unsigned long end);
+
+extern void numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern unsigned long numa_free_all_bootmem(void);
+
+extern void reserve_bootmem_generic(unsigned long phys, unsigned len);
+
+extern void load_gs_index(unsigned gs);
+
+extern void stop_timer_interrupt(void);
+extern void main_timer_handler(void);
+
+extern unsigned long end_pfn_map; 
+
+extern void show_trace(struct task_struct *, struct pt_regs *, unsigned long * rsp);
+extern void show_registers(struct pt_regs *regs);
+
+extern void exception_table_check(void);
+
+extern void acpi_reserve_bootmem(void);
+
+extern void swap_low_mappings(void);
+
+extern void __show_regs(struct pt_regs * regs);
+extern void show_regs(struct pt_regs * regs);
+
+extern void syscall32_cpu_init(void);
+
+extern void setup_node_bootmem(int nodeid, unsigned long start, unsigned long end);
+
+extern void early_quirks(void);
+extern void check_efer(void);
+
+extern void select_idle_routine(const struct cpuinfo_x86 *c);
+
+extern unsigned long table_start, table_end;
+
+extern int exception_trace;
+extern unsigned cpu_khz;
+extern unsigned tsc_khz;
+
+extern int reboot_force;
+extern int notsc_setup(char *);
+
+extern int timer_over_8254;
+
+extern int gsi_irq_sharing(int gsi);
+
+extern void smp_local_timer_interrupt(void);
+
+extern int force_mwait;
+
+long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
+
+void i8254_timer_resume(void);
+
+#define round_up(x,y) (((x) + (y) - 1) & ~((y)-1))
+#define round_down(x,y) ((x) & ~((y)-1))
+
+#endif
diff --git a/include/asm-x86/ptrace-abi.h b/include/asm-x86/ptrace-abi.h
new file mode 100644
index 000000000000..6824c49def1c
--- /dev/null
+++ b/include/asm-x86/ptrace-abi.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "ptrace-abi_32.h"
+# else
+#  include "ptrace-abi_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "ptrace-abi_32.h"
+# else
+#  include "ptrace-abi_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/ptrace-abi_32.h b/include/asm-x86/ptrace-abi_32.h
new file mode 100644
index 000000000000..a44901817a26
--- /dev/null
+++ b/include/asm-x86/ptrace-abi_32.h
@@ -0,0 +1,39 @@
+#ifndef I386_PTRACE_ABI_H
+#define I386_PTRACE_ABI_H
+
+#define EBX 0
+#define ECX 1
+#define EDX 2
+#define ESI 3
+#define EDI 4
+#define EBP 5
+#define EAX 6
+#define DS 7
+#define ES 8
+#define FS 9
+#define GS 10
+#define ORIG_EAX 11
+#define EIP 12
+#define CS  13
+#define EFL 14
+#define UESP 15
+#define SS   16
+#define FRAME_SIZE 17
+
+/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
+#define PTRACE_GETREGS            12
+#define PTRACE_SETREGS            13
+#define PTRACE_GETFPREGS          14
+#define PTRACE_SETFPREGS          15
+#define PTRACE_GETFPXREGS         18
+#define PTRACE_SETFPXREGS         19
+
+#define PTRACE_OLDSETOPTIONS         21
+
+#define PTRACE_GET_THREAD_AREA    25
+#define PTRACE_SET_THREAD_AREA    26
+
+#define PTRACE_SYSEMU             31
+#define PTRACE_SYSEMU_SINGLESTEP  32
+
+#endif
diff --git a/include/asm-x86/ptrace-abi_64.h b/include/asm-x86/ptrace-abi_64.h
new file mode 100644
index 000000000000..19184b0806b1
--- /dev/null
+++ b/include/asm-x86/ptrace-abi_64.h
@@ -0,0 +1,51 @@
+#ifndef _X86_64_PTRACE_ABI_H
+#define _X86_64_PTRACE_ABI_H
+
+#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
+#define R15 0
+#define R14 8
+#define R13 16
+#define R12 24
+#define RBP 32
+#define RBX 40
+/* arguments: interrupts/non tracing syscalls only save upto here*/
+#define R11 48
+#define R10 56
+#define R9 64
+#define R8 72
+#define RAX 80
+#define RCX 88
+#define RDX 96
+#define RSI 104
+#define RDI 112
+#define ORIG_RAX 120       /* = ERROR */
+/* end of arguments */
+/* cpu exception frame or undefined in case of fast syscall. */
+#define RIP 128
+#define CS 136
+#define EFLAGS 144
+#define RSP 152
+#define SS 160
+#define ARGOFFSET R11
+#endif /* __ASSEMBLY__ */
+
+/* top of stack page */
+#define FRAME_SIZE 168
+
+#define PTRACE_OLDSETOPTIONS         21
+
+/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
+#define PTRACE_GETREGS            12
+#define PTRACE_SETREGS            13
+#define PTRACE_GETFPREGS          14
+#define PTRACE_SETFPREGS          15
+#define PTRACE_GETFPXREGS         18
+#define PTRACE_SETFPXREGS         19
+
+/* only useful for access 32bit programs */
+#define PTRACE_GET_THREAD_AREA    25
+#define PTRACE_SET_THREAD_AREA    26
+
+#define PTRACE_ARCH_PRCTL         30    /* arch_prctl for child */
+
+#endif
diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h
new file mode 100644
index 000000000000..bc4d64a87689
--- /dev/null
+++ b/include/asm-x86/ptrace.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "ptrace_32.h"
+# else
+#  include "ptrace_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "ptrace_32.h"
+# else
+#  include "ptrace_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/ptrace_32.h b/include/asm-x86/ptrace_32.h
new file mode 100644
index 000000000000..6002597b9e12
--- /dev/null
+++ b/include/asm-x86/ptrace_32.h
@@ -0,0 +1,63 @@
+#ifndef _I386_PTRACE_H
+#define _I386_PTRACE_H
+
+#include <asm/ptrace-abi.h>
+
+/* this struct defines the way the registers are stored on the 
+   stack during a system call. */
+
+struct pt_regs {
+        long ebx;
+        long ecx;
+        long edx;
+        long esi;
+        long edi;
+        long ebp;
+        long eax;
+        int  xds;
+        int  xes;
+        int  xfs;
+        /* int  xgs; */
+        long orig_eax;
+        long eip;
+        int  xcs;
+        long eflags;
+        long esp;
+        int  xss;
+};
+
+#ifdef __KERNEL__
+
+#include <asm/vm86.h>
+#include <asm/segment.h>
+
+struct task_struct;
+extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code);
+
+/*
+ * user_mode_vm(regs) determines whether a register set came from user mode.
+ * This is true if V8086 mode was enabled OR if the register set was from
+ * protected mode with RPL-3 CS value.  This tricky test checks that with
+ * one comparison.  Many places in the kernel can bypass this full check
+ * if they have already ruled out V8086 mode, so user_mode(regs) can be used.
+ */
+static inline int user_mode(struct pt_regs *regs)
+{
+        return (regs->xcs & SEGMENT_RPL_MASK) == USER_RPL;
+}
+static inline int user_mode_vm(struct pt_regs *regs)
+{
+        return ((regs->xcs & SEGMENT_RPL_MASK) | (regs->eflags & VM_MASK)) >= USER_RPL;
+}
+static inline int v8086_mode(struct pt_regs *regs)
+{
+        return (regs->eflags & VM_MASK);
+}
+
+#define instruction_pointer(regs) ((regs)->eip)
+#define regs_return_value(regs) ((regs)->eax)
+
+extern unsigned long profile_pc(struct pt_regs *regs);
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/ptrace_64.h b/include/asm-x86/ptrace_64.h
new file mode 100644
index 000000000000..7f166ccb0606
--- /dev/null
+++ b/include/asm-x86/ptrace_64.h
@@ -0,0 +1,78 @@
+#ifndef _X86_64_PTRACE_H
+#define _X86_64_PTRACE_H
+
+#include <linux/compiler.h>     /* For __user */
+#include <asm/ptrace-abi.h>
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs {
+        unsigned long r15;
+        unsigned long r14;
+        unsigned long r13;
+        unsigned long r12;
+        unsigned long rbp;
+        unsigned long rbx;
+/* arguments: non interrupts/non tracing syscalls only save upto here*/
+        unsigned long r11;
+        unsigned long r10;
+        unsigned long r9;
+        unsigned long r8;
+        unsigned long rax;
+        unsigned long rcx;
+        unsigned long rdx;
+        unsigned long rsi;
+        unsigned long rdi;
+        unsigned long orig_rax;
+/* end of arguments */
+/* cpu exception frame or undefined */
+        unsigned long rip;
+        unsigned long cs;
+        unsigned long eflags;
+        unsigned long rsp;
+        unsigned long ss;
+/* top of stack page */
+};
+
+#endif
+
+#if defined(__KERNEL__) && !defined(__ASSEMBLY__) 
+#define user_mode(regs) (!!((regs)->cs & 3))
+#define user_mode_vm(regs) user_mode(regs)
+#define instruction_pointer(regs) ((regs)->rip)
+#define regs_return_value(regs) ((regs)->rax)
+
+extern unsigned long profile_pc(struct pt_regs *regs);
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+struct task_struct;
+
+extern unsigned long
+convert_rip_to_linear(struct task_struct *child, struct pt_regs *regs);
+
+enum {
+        EF_CF   = 0x00000001,
+        EF_PF   = 0x00000004,
+        EF_AF   = 0x00000010,
+        EF_ZF   = 0x00000040,
+        EF_SF   = 0x00000080,
+        EF_TF   = 0x00000100,
+        EF_IE   = 0x00000200,
+        EF_DF   = 0x00000400,
+        EF_OF   = 0x00000800,
+        EF_IOPL = 0x00003000,
+        EF_IOPL_RING0 = 0x00000000,
+        EF_IOPL_RING1 = 0x00001000,
+        EF_IOPL_RING2 = 0x00002000,
+        EF_NT   = 0x00004000,   /* nested task */
+        EF_RF   = 0x00010000,   /* resume */
+        EF_VM   = 0x00020000,   /* virtual mode */
+        EF_AC   = 0x00040000,   /* alignment */
+        EF_VIF  = 0x00080000,   /* virtual interrupt */
+        EF_VIP  = 0x00100000,   /* virtual interrupt pending */
+        EF_ID   = 0x00200000,   /* id */
+};
+
+#endif
+
+#endif
diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h
new file mode 100644
index 000000000000..e9e3ffc22c07
--- /dev/null
+++ b/include/asm-x86/reboot.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_REBOOT_H
+#define _ASM_REBOOT_H
+
+struct pt_regs;
+
+struct machine_ops
+{
+        void (*restart)(char *cmd);
+        void (*halt)(void);
+        void (*power_off)(void);
+        void (*shutdown)(void);
+        void (*crash_shutdown)(struct pt_regs *);
+        void (*emergency_restart)(void);
+};
+
+extern struct machine_ops machine_ops;
+
+void machine_real_restart(unsigned char *code, int length);
+
+#endif  /* _ASM_REBOOT_H */
diff --git a/include/asm-x86/reboot_fixups.h b/include/asm-x86/reboot_fixups.h
new file mode 100644
index 000000000000..0cb7d87c2b68
--- /dev/null
+++ b/include/asm-x86/reboot_fixups.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_REBOOT_FIXUPS_H
+#define _LINUX_REBOOT_FIXUPS_H
+
+extern void mach_reboot_fixups(void);
+
+#endif /* _LINUX_REBOOT_FIXUPS_H */
diff --git a/include/asm-x86/required-features.h b/include/asm-x86/required-features.h
new file mode 100644
index 000000000000..8b64f3ea2b78
--- /dev/null
+++ b/include/asm-x86/required-features.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "required-features_32.h"
+#else
+# include "required-features_64.h"
+#endif
diff --git a/include/asm-x86/required-features_32.h b/include/asm-x86/required-features_32.h
new file mode 100644
index 000000000000..618feb98f9f5
--- /dev/null
+++ b/include/asm-x86/required-features_32.h
@@ -0,0 +1,55 @@
+#ifndef _ASM_REQUIRED_FEATURES_H
+#define _ASM_REQUIRED_FEATURES_H 1
+
+/* Define minimum CPUID feature set for kernel These bits are checked
+   really early to actually display a visible error message before the
+   kernel dies.  Make sure to assign features to the proper mask!
+
+   Some requirements that are not in CPUID yet are also in the
+   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
+
+   The real information is in arch/i386/Kconfig.cpu, this just converts
+   the CONFIGs into a bitmask */
+
+#ifndef CONFIG_MATH_EMULATION
+# define NEED_FPU       (1<<(X86_FEATURE_FPU & 31))
+#else
+# define NEED_FPU       0
+#endif
+
+#ifdef CONFIG_X86_PAE
+# define NEED_PAE       (1<<(X86_FEATURE_PAE & 31))
+#else
+# define NEED_PAE       0
+#endif
+
+#ifdef CONFIG_X86_CMOV
+# define NEED_CMOV      (1<<(X86_FEATURE_CMOV & 31))
+#else
+# define NEED_CMOV      0
+#endif
+
+#ifdef CONFIG_X86_PAE
+# define NEED_CX8       (1<<(X86_FEATURE_CX8 & 31))
+#else
+# define NEED_CX8       0
+#endif
+
+#define REQUIRED_MASK0  (NEED_FPU|NEED_PAE|NEED_CMOV|NEED_CX8)
+
+#ifdef CONFIG_X86_USE_3DNOW
+# define NEED_3DNOW     (1<<(X86_FEATURE_3DNOW & 31))
+#else
+# define NEED_3DNOW     0
+#endif
+
+#define REQUIRED_MASK1  (NEED_3DNOW)
+
+#define REQUIRED_MASK2  0
+#define REQUIRED_MASK3  0
+#define REQUIRED_MASK4  0
+#define REQUIRED_MASK5  0
+#define REQUIRED_MASK6  0
+#define REQUIRED_MASK7  0
+
+#endif
diff --git a/include/asm-x86/required-features_64.h b/include/asm-x86/required-features_64.h
new file mode 100644
index 000000000000..e80d5761b00a
--- /dev/null
+++ b/include/asm-x86/required-features_64.h
@@ -0,0 +1,46 @@
+#ifndef _ASM_REQUIRED_FEATURES_H
+#define _ASM_REQUIRED_FEATURES_H 1
+
+/* Define minimum CPUID feature set for kernel These bits are checked
+   really early to actually display a visible error message before the
+   kernel dies.  Make sure to assign features to the proper mask!
+
+   The real information is in arch/x86_64/Kconfig.cpu, this just converts
+   the CONFIGs into a bitmask */
+
+/* x86-64 baseline features */
+#define NEED_FPU        (1<<(X86_FEATURE_FPU & 31))
+#define NEED_PSE        (1<<(X86_FEATURE_PSE & 31))
+#define NEED_MSR        (1<<(X86_FEATURE_MSR & 31))
+#define NEED_PAE        (1<<(X86_FEATURE_PAE & 31))
+#define NEED_CX8        (1<<(X86_FEATURE_CX8 & 31))
+#define NEED_PGE        (1<<(X86_FEATURE_PGE & 31))
+#define NEED_FXSR       (1<<(X86_FEATURE_FXSR & 31))
+#define NEED_CMOV       (1<<(X86_FEATURE_CMOV & 31))
+#define NEED_XMM        (1<<(X86_FEATURE_XMM & 31))
+#define NEED_XMM2       (1<<(X86_FEATURE_XMM2 & 31))
+
+#define REQUIRED_MASK0  (NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
+                         NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
+                         NEED_XMM|NEED_XMM2)
+#define SSE_MASK        (NEED_XMM|NEED_XMM2)
+
+/* x86-64 baseline features */
+#define NEED_LM         (1<<(X86_FEATURE_LM & 31))
+
+#ifdef CONFIG_X86_USE_3DNOW
+# define NEED_3DNOW     (1<<(X86_FEATURE_3DNOW & 31))
+#else
+# define NEED_3DNOW     0
+#endif
+
+#define REQUIRED_MASK1  (NEED_LM|NEED_3DNOW)
+
+#define REQUIRED_MASK2  0
+#define REQUIRED_MASK3  0
+#define REQUIRED_MASK4  0
+#define REQUIRED_MASK5  0
+#define REQUIRED_MASK6  0
+#define REQUIRED_MASK7  0
+
+#endif
diff --git a/include/asm-x86/resource.h b/include/asm-x86/resource.h
new file mode 100644
index 000000000000..732410a8c02a
--- /dev/null
+++ b/include/asm-x86/resource.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "resource_32.h"
+# else
+#  include "resource_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "resource_32.h"
+# else
+#  include "resource_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/resource_32.h b/include/asm-x86/resource_32.h
new file mode 100644
index 000000000000..6c1ea37c7718
--- /dev/null
+++ b/include/asm-x86/resource_32.h
@@ -0,0 +1,6 @@
+#ifndef _I386_RESOURCE_H
+#define _I386_RESOURCE_H
+
+#include <asm-generic/resource.h>
+
+#endif
diff --git a/include/asm-x86/resource_64.h b/include/asm-x86/resource_64.h
new file mode 100644
index 000000000000..f40b40623234
--- /dev/null
+++ b/include/asm-x86/resource_64.h
@@ -0,0 +1,6 @@
+#ifndef _X8664_RESOURCE_H
+#define _X8664_RESOURCE_H
+
+#include <asm-generic/resource.h>
+
+#endif
diff --git a/include/asm-x86/resume-trace.h b/include/asm-x86/resume-trace.h
new file mode 100644
index 000000000000..9b6dd093a9f7
--- /dev/null
+++ b/include/asm-x86/resume-trace.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "resume-trace_32.h"
+#else
+# include "resume-trace_64.h"
+#endif
diff --git a/include/asm-x86/resume-trace_32.h b/include/asm-x86/resume-trace_32.h
new file mode 100644
index 000000000000..ec9cfd656230
--- /dev/null
+++ b/include/asm-x86/resume-trace_32.h
@@ -0,0 +1,13 @@
+#define TRACE_RESUME(user) do {                                 \
+        if (pm_trace_enabled) {                                 \
+                void *tracedata;                                \
+                asm volatile("movl $1f,%0\n"                    \
+                        ".section .tracedata,\"a\"\n"           \
+                        "1:\t.word %c1\n"                       \
+                        "\t.long %c2\n"                         \
+                        ".previous"                             \
+                        :"=r" (tracedata)                       \
+                        : "i" (__LINE__), "i" (__FILE__));      \
+                generate_resume_trace(tracedata, user);         \
+        }                                                       \
+} while (0)
diff --git a/include/asm-x86/resume-trace_64.h b/include/asm-x86/resume-trace_64.h
new file mode 100644
index 000000000000..34bf998fdf62
--- /dev/null
+++ b/include/asm-x86/resume-trace_64.h
@@ -0,0 +1,13 @@
+#define TRACE_RESUME(user) do {                                 \
+        if (pm_trace_enabled) {                                 \
+                void *tracedata;                                \
+                asm volatile("movq $1f,%0\n"                    \
+                        ".section .tracedata,\"a\"\n"           \
+                        "1:\t.word %c1\n"                       \
+                        "\t.quad %c2\n"                         \
+                        ".previous"                             \
+                        :"=r" (tracedata)                       \
+                        : "i" (__LINE__), "i" (__FILE__));      \
+                generate_resume_trace(tracedata, user);         \
+        }                                                       \
+} while (0)
diff --git a/include/asm-x86/rio.h b/include/asm-x86/rio.h
new file mode 100644
index 000000000000..c7350f6d2015
--- /dev/null
+++ b/include/asm-x86/rio.h
@@ -0,0 +1,74 @@
+/*
+ * Derived from include/asm-i386/mach-summit/mach_mpparse.h
+ *          and include/asm-i386/mach-default/bios_ebda.h
+ *
+ * Author: Laurent Vivier <Laurent.Vivier@bull.net>
+ */
+
+#ifndef __ASM_RIO_H
+#define __ASM_RIO_H
+
+#define RIO_TABLE_VERSION       3
+
+struct rio_table_hdr {
+        u8 version;      /* Version number of this data structure  */
+        u8 num_scal_dev; /* # of Scalability devices               */
+        u8 num_rio_dev;  /* # of RIO I/O devices                   */
+} __attribute__((packed));
+
+struct scal_detail {
+        u8 node_id;      /* Scalability Node ID                    */
+        u32 CBAR;        /* Address of 1MB register space          */
+        u8 port0node;    /* Node ID port connected to: 0xFF=None   */
+        u8 port0port;    /* Port num port connected to: 0,1,2, or  */
+                         /* 0xFF=None                              */
+        u8 port1node;    /* Node ID port connected to: 0xFF = None */
+        u8 port1port;    /* Port num port connected to: 0,1,2, or  */
+                         /* 0xFF=None                              */
+        u8 port2node;    /* Node ID port connected to: 0xFF = None */
+        u8 port2port;    /* Port num port connected to: 0,1,2, or  */
+                         /* 0xFF=None                              */
+        u8 chassis_num;  /* 1 based Chassis number (1 = boot node) */
+} __attribute__((packed));
+
+struct rio_detail {
+        u8 node_id;      /* RIO Node ID                            */
+        u32 BBAR;        /* Address of 1MB register space          */
+        u8 type;         /* Type of device                         */
+        u8 owner_id;     /* Node ID of Hurricane that owns this    */
+                         /* node                                   */
+        u8 port0node;    /* Node ID port connected to: 0xFF=None   */
+        u8 port0port;    /* Port num port connected to: 0,1,2, or  */
+                         /* 0xFF=None                              */
+        u8 port1node;    /* Node ID port connected to: 0xFF=None   */
+        u8 port1port;    /* Port num port connected to: 0,1,2, or  */
+                         /* 0xFF=None                              */
+        u8 first_slot;   /* Lowest slot number below this Calgary  */
+        u8 status;       /* Bit 0 = 1 : the XAPIC is used          */
+                         /*       = 0 : the XAPIC is not used, ie: */
+                         /*            ints fwded to another XAPIC */
+                         /*           Bits1:7 Reserved             */
+        u8 WP_index;     /* instance index - lower ones have       */
+                         /*     lower slot numbers/PCI bus numbers */
+        u8 chassis_num;  /* 1 based Chassis number                 */
+} __attribute__((packed));
+
+enum {
+        HURR_SCALABILTY = 0,  /* Hurricane Scalability info */
+        HURR_RIOIB      = 2,  /* Hurricane RIOIB info       */
+        COMPAT_CALGARY  = 4,  /* Compatibility Calgary      */
+        ALT_CALGARY     = 5,  /* Second Planar Calgary      */
+};
+
+/*
+ * there is a real-mode segmented pointer pointing to the
+ * 4K EBDA area at 0x40E.
+ */
+static inline unsigned long get_bios_ebda(void)
+{
+        unsigned long address = *(unsigned short *)phys_to_virt(0x40EUL);
+        address <<= 4;
+        return address;
+}
+
+#endif /* __ASM_RIO_H */
diff --git a/include/asm-x86/rtc.h b/include/asm-x86/rtc.h
new file mode 100644
index 000000000000..1f0c98eb2e38
--- /dev/null
+++ b/include/asm-x86/rtc.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "rtc_32.h"
+#else
+# include "rtc_64.h"
+#endif
diff --git a/include/asm-x86/rtc_32.h b/include/asm-x86/rtc_32.h
new file mode 100644
index 000000000000..ffd02109a0e5
--- /dev/null
+++ b/include/asm-x86/rtc_32.h
@@ -0,0 +1,10 @@
+#ifndef _I386_RTC_H
+#define _I386_RTC_H
+
+/*
+ * x86 uses the default access methods for the RTC.
+ */
+
+#include <asm-generic/rtc.h>
+
+#endif
diff --git a/include/asm-x86/rtc_64.h b/include/asm-x86/rtc_64.h
new file mode 100644
index 000000000000..18ed713ac7de
--- /dev/null
+++ b/include/asm-x86/rtc_64.h
@@ -0,0 +1,10 @@
+#ifndef _X86_64_RTC_H
+#define _X86_64_RTC_H
+
+/*
+ * x86 uses the default access methods for the RTC.
+ */
+
+#include <asm-generic/rtc.h>
+
+#endif
diff --git a/include/asm-x86/rwlock.h b/include/asm-x86/rwlock.h
new file mode 100644
index 000000000000..a3be7d8364af
--- /dev/null
+++ b/include/asm-x86/rwlock.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "rwlock_32.h"
+#else
+# include "rwlock_64.h"
+#endif
diff --git a/include/asm-x86/rwlock_32.h b/include/asm-x86/rwlock_32.h
new file mode 100644
index 000000000000..c3e5db32fa48
--- /dev/null
+++ b/include/asm-x86/rwlock_32.h
@@ -0,0 +1,25 @@
+/* include/asm-i386/rwlock.h
+ *
+ *      Helpers used by both rw spinlocks and rw semaphores.
+ *
+ *      Based in part on code from semaphore.h and
+ *      spinlock.h Copyright 1996 Linus Torvalds.
+ *
+ *      Copyright 1999 Red Hat, Inc.
+ *
+ *      Written by Benjamin LaHaise.
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_I386_RWLOCK_H
+#define _ASM_I386_RWLOCK_H
+
+#define RW_LOCK_BIAS             0x01000000
+#define RW_LOCK_BIAS_STR        "0x01000000"
+
+/* Code is in asm-i386/spinlock.h */
+
+#endif
diff --git a/include/asm-x86/rwlock_64.h b/include/asm-x86/rwlock_64.h
new file mode 100644
index 000000000000..72aeebed920b
--- /dev/null
+++ b/include/asm-x86/rwlock_64.h
@@ -0,0 +1,26 @@
+/* include/asm-x86_64/rwlock.h
+ *
+ *      Helpers used by both rw spinlocks and rw semaphores.
+ *
+ *      Based in part on code from semaphore.h and
+ *      spinlock.h Copyright 1996 Linus Torvalds.
+ *
+ *      Copyright 1999 Red Hat, Inc.
+ *      Copyright 2001,2002 SuSE labs 
+ *
+ *      Written by Benjamin LaHaise.
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_X86_64_RWLOCK_H
+#define _ASM_X86_64_RWLOCK_H
+
+#define RW_LOCK_BIAS             0x01000000
+#define RW_LOCK_BIAS_STR         "0x01000000"
+
+/* Actual code is in asm/spinlock.h or in arch/x86_64/lib/rwlock.S */
+
+#endif
diff --git a/include/asm-x86/rwsem.h b/include/asm-x86/rwsem.h
new file mode 100644
index 000000000000..041906f3c6df
--- /dev/null
+++ b/include/asm-x86/rwsem.h
@@ -0,0 +1,258 @@
+/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ *
+ * Derived from asm-i386/semaphore.h
+ *
+ *
+ * The MSW of the count is the negated number of active writers and waiting
+ * lockers, and the LSW is the total number of active locks
+ *
+ * The lock count is initialized to 0 (no active and no waiting lockers).
+ *
+ * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
+ * uncontended lock. This can be determined because XADD returns the old value.
+ * Readers increment by 1 and see a positive value when uncontended, negative
+ * if there are writers (and maybe) readers waiting (in which case it goes to
+ * sleep).
+ *
+ * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
+ * be extended to 65534 by manually checking the whole MSW rather than relying
+ * on the S flag.
+ *
+ * The value of ACTIVE_BIAS supports up to 65535 active processes.
+ *
+ * This should be totally fair - if anything is waiting, a process that wants a
+ * lock will go to the back of the queue. When the currently active lock is
+ * released, if there's a writer at the front of the queue, then that and only
+ * that will be woken up; if there's a bunch of consequtive readers at the
+ * front, then they'll all be woken up, but no other readers will be.
+ */
+
+#ifndef _I386_RWSEM_H
+#define _I386_RWSEM_H
+
+#ifndef _LINUX_RWSEM_H
+#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
+#endif
+
+#ifdef __KERNEL__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/lockdep.h>
+
+struct rwsem_waiter;
+
+extern struct rw_semaphore *FASTCALL(rwsem_down_read_failed(struct rw_semaphore *sem));
+extern struct rw_semaphore *FASTCALL(rwsem_down_write_failed(struct rw_semaphore *sem));
+extern struct rw_semaphore *FASTCALL(rwsem_wake(struct rw_semaphore *));
+extern struct rw_semaphore *FASTCALL(rwsem_downgrade_wake(struct rw_semaphore *sem));
+
+/*
+ * the semaphore definition
+ */
+struct rw_semaphore {
+        signed long             count;
+#define RWSEM_UNLOCKED_VALUE            0x00000000
+#define RWSEM_ACTIVE_BIAS               0x00000001
+#define RWSEM_ACTIVE_MASK               0x0000ffff
+#define RWSEM_WAITING_BIAS              (-0x00010000)
+#define RWSEM_ACTIVE_READ_BIAS          RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS         (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+        spinlock_t              wait_lock;
+        struct list_head        wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+        struct lockdep_map dep_map;
+#endif
+};
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
+
+#define __RWSEM_INITIALIZER(name) \
+{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
+  LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
+
+#define DECLARE_RWSEM(name) \
+        struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+                         struct lock_class_key *key);
+
+#define init_rwsem(sem)                                         \
+do {                                                            \
+        static struct lock_class_key __key;                     \
+                                                                \
+        __init_rwsem((sem), #sem, &__key);                      \
+} while (0)
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+        __asm__ __volatile__(
+                "# beginning down_read\n\t"
+LOCK_PREFIX     "  incl      (%%eax)\n\t" /* adds 0x00000001, returns the old value */
+                "  jns        1f\n"
+                "  call call_rwsem_down_read_failed\n"
+                "1:\n\t"
+                "# ending down_read\n\t"
+                : "+m" (sem->count)
+                : "a" (sem)
+                : "memory", "cc");
+}
+
+/*
+ * trylock for reading -- returns 1 if successful, 0 if contention
+ */
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+        __s32 result, tmp;
+        __asm__ __volatile__(
+                "# beginning __down_read_trylock\n\t"
+                "  movl      %0,%1\n\t"
+                "1:\n\t"
+                "  movl      %1,%2\n\t"
+                "  addl      %3,%2\n\t"
+                "  jle       2f\n\t"
+LOCK_PREFIX     "  cmpxchgl  %2,%0\n\t"
+                "  jnz       1b\n\t"
+                "2:\n\t"
+                "# ending __down_read_trylock\n\t"
+                : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
+                : "i" (RWSEM_ACTIVE_READ_BIAS)
+                : "memory", "cc");
+        return result>=0 ? 1 : 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+        int tmp;
+
+        tmp = RWSEM_ACTIVE_WRITE_BIAS;
+        __asm__ __volatile__(
+                "# beginning down_write\n\t"
+LOCK_PREFIX     "  xadd      %%edx,(%%eax)\n\t" /* subtract 0x0000ffff, returns the old value */
+                "  testl     %%edx,%%edx\n\t" /* was the count 0 before? */
+                "  jz        1f\n"
+                "  call call_rwsem_down_write_failed\n"
+                "1:\n"
+                "# ending down_write"
+                : "+m" (sem->count), "=d" (tmp)
+                : "a" (sem), "1" (tmp)
+                : "memory", "cc");
+}
+
+static inline void __down_write(struct rw_semaphore *sem)
+{
+        __down_write_nested(sem, 0);
+}
+
+/*
+ * trylock for writing -- returns 1 if successful, 0 if contention
+ */
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+        signed long ret = cmpxchg(&sem->count,
+                                  RWSEM_UNLOCKED_VALUE, 
+                                  RWSEM_ACTIVE_WRITE_BIAS);
+        if (ret == RWSEM_UNLOCKED_VALUE)
+                return 1;
+        return 0;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+        __s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
+        __asm__ __volatile__(
+                "# beginning __up_read\n\t"
+LOCK_PREFIX     "  xadd      %%edx,(%%eax)\n\t" /* subtracts 1, returns the old value */
+                "  jns        1f\n\t"
+                "  call call_rwsem_wake\n"
+                "1:\n"
+                "# ending __up_read\n"
+                : "+m" (sem->count), "=d" (tmp)
+                : "a" (sem), "1" (tmp)
+                : "memory", "cc");
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+        __asm__ __volatile__(
+                "# beginning __up_write\n\t"
+                "  movl      %2,%%edx\n\t"
+LOCK_PREFIX     "  xaddl     %%edx,(%%eax)\n\t" /* tries to transition 0xffff0001 -> 0x00000000 */
+                "  jz       1f\n"
+                "  call call_rwsem_wake\n"
+                "1:\n\t"
+                "# ending __up_write\n"
+                : "+m" (sem->count)
+                : "a" (sem), "i" (-RWSEM_ACTIVE_WRITE_BIAS)
+                : "memory", "cc", "edx");
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+        __asm__ __volatile__(
+                "# beginning __downgrade_write\n\t"
+LOCK_PREFIX     "  addl      %2,(%%eax)\n\t" /* transitions 0xZZZZ0001 -> 0xYYYY0001 */
+                "  jns       1f\n\t"
+                "  call call_rwsem_downgrade_wake\n"
+                "1:\n\t"
+                "# ending __downgrade_write\n"
+                : "+m" (sem->count)
+                : "a" (sem), "i" (-RWSEM_WAITING_BIAS)
+                : "memory", "cc");
+}
+
+/*
+ * implement atomic add functionality
+ */
+static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+{
+        __asm__ __volatile__(
+LOCK_PREFIX     "addl %1,%0"
+                : "+m" (sem->count)
+                : "ir" (delta));
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+{
+        int tmp = delta;
+
+        __asm__ __volatile__(
+LOCK_PREFIX     "xadd %0,%1"
+                : "+r" (tmp), "+m" (sem->count)
+                : : "memory");
+
+        return tmp+delta;
+}
+
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+        return (sem->count != 0);
+}
+
+#endif /* __KERNEL__ */
+#endif /* _I386_RWSEM_H */
diff --git a/include/asm-x86/scatterlist.h b/include/asm-x86/scatterlist.h
new file mode 100644
index 000000000000..3a1e76257a27
--- /dev/null
+++ b/include/asm-x86/scatterlist.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "scatterlist_32.h"
+#else
+# include "scatterlist_64.h"
+#endif
diff --git a/include/asm-x86/scatterlist_32.h b/include/asm-x86/scatterlist_32.h
new file mode 100644
index 000000000000..d7e45a8f1aae
--- /dev/null
+++ b/include/asm-x86/scatterlist_32.h
@@ -0,0 +1,23 @@
+#ifndef _I386_SCATTERLIST_H
+#define _I386_SCATTERLIST_H
+
+#include <asm/types.h>
+
+struct scatterlist {
+    struct page         *page;
+    unsigned int        offset;
+    dma_addr_t          dma_address;
+    unsigned int        length;
+};
+
+/* These macros should be used after a pci_map_sg call has been done
+ * to get bus addresses of each of the SG entries and their lengths.
+ * You should only work with the number of sg entries pci_map_sg
+ * returns.
+ */
+#define sg_dma_address(sg)      ((sg)->dma_address)
+#define sg_dma_len(sg)          ((sg)->length)
+
+#define ISA_DMA_THRESHOLD (0x00ffffff)
+
+#endif /* !(_I386_SCATTERLIST_H) */
diff --git a/include/asm-x86/scatterlist_64.h b/include/asm-x86/scatterlist_64.h
new file mode 100644
index 000000000000..eaf7ada27e14
--- /dev/null
+++ b/include/asm-x86/scatterlist_64.h
@@ -0,0 +1,24 @@
+#ifndef _X8664_SCATTERLIST_H
+#define _X8664_SCATTERLIST_H
+
+#include <asm/types.h>
+
+struct scatterlist {
+    struct page         *page;
+    unsigned int        offset;
+    unsigned int        length;
+    dma_addr_t          dma_address;
+    unsigned int        dma_length;
+};
+
+#define ISA_DMA_THRESHOLD (0x00ffffff)
+
+/* These macros should be used after a pci_map_sg call has been done
+ * to get bus addresses of each of the SG entries and their lengths.
+ * You should only work with the number of sg entries pci_map_sg
+ * returns.
+ */
+#define sg_dma_address(sg)     ((sg)->dma_address)
+#define sg_dma_len(sg)         ((sg)->dma_length)
+
+#endif 
diff --git a/include/asm-x86/seccomp.h b/include/asm-x86/seccomp.h
new file mode 100644
index 000000000000..c62e58a5a90d
--- /dev/null
+++ b/include/asm-x86/seccomp.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "seccomp_32.h"
+#else
+# include "seccomp_64.h"
+#endif
diff --git a/include/asm-x86/seccomp_32.h b/include/asm-x86/seccomp_32.h
new file mode 100644
index 000000000000..18da19e89bff
--- /dev/null
+++ b/include/asm-x86/seccomp_32.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_SECCOMP_H
+
+#include <linux/thread_info.h>
+
+#ifdef TIF_32BIT
+#error "unexpected TIF_32BIT on i386"
+#endif
+
+#include <linux/unistd.h>
+
+#define __NR_seccomp_read __NR_read
+#define __NR_seccomp_write __NR_write
+#define __NR_seccomp_exit __NR_exit
+#define __NR_seccomp_sigreturn __NR_sigreturn
+
+#endif /* _ASM_SECCOMP_H */
diff --git a/include/asm-x86/seccomp_64.h b/include/asm-x86/seccomp_64.h
new file mode 100644
index 000000000000..553af65a2287
--- /dev/null
+++ b/include/asm-x86/seccomp_64.h
@@ -0,0 +1,24 @@
+#ifndef _ASM_SECCOMP_H
+
+#include <linux/thread_info.h>
+
+#ifdef TIF_32BIT
+#error "unexpected TIF_32BIT on x86_64"
+#else
+#define TIF_32BIT TIF_IA32
+#endif
+
+#include <linux/unistd.h>
+#include <asm/ia32_unistd.h>
+
+#define __NR_seccomp_read __NR_read
+#define __NR_seccomp_write __NR_write
+#define __NR_seccomp_exit __NR_exit
+#define __NR_seccomp_sigreturn __NR_rt_sigreturn
+
+#define __NR_seccomp_read_32 __NR_ia32_read
+#define __NR_seccomp_write_32 __NR_ia32_write
+#define __NR_seccomp_exit_32 __NR_ia32_exit
+#define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn
+
+#endif /* _ASM_SECCOMP_H */
diff --git a/include/asm-x86/sections.h b/include/asm-x86/sections.h
new file mode 100644
index 000000000000..ae6c69d9be3f
--- /dev/null
+++ b/include/asm-x86/sections.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "sections_32.h"
+#else
+# include "sections_64.h"
+#endif
diff --git a/include/asm-x86/sections_32.h b/include/asm-x86/sections_32.h
new file mode 100644
index 000000000000..2dcbb92918b2
--- /dev/null
+++ b/include/asm-x86/sections_32.h
@@ -0,0 +1,7 @@
+#ifndef _I386_SECTIONS_H
+#define _I386_SECTIONS_H
+
+/* nothing to see, move along */
+#include <asm-generic/sections.h>
+
+#endif
diff --git a/include/asm-x86/sections_64.h b/include/asm-x86/sections_64.h
new file mode 100644
index 000000000000..c746d9f1e70c
--- /dev/null
+++ b/include/asm-x86/sections_64.h
@@ -0,0 +1,7 @@
+#ifndef _X8664_SECTIONS_H
+#define _X8664_SECTIONS_H
+
+/* nothing to see, move along */
+#include <asm-generic/sections.h>
+
+#endif
diff --git a/include/asm-x86/segment.h b/include/asm-x86/segment.h
new file mode 100644
index 000000000000..605068280e28
--- /dev/null
+++ b/include/asm-x86/segment.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "segment_32.h"
+#else
+# include "segment_64.h"
+#endif
diff --git a/include/asm-x86/segment_32.h b/include/asm-x86/segment_32.h
new file mode 100644
index 000000000000..597a47c2515f
--- /dev/null
+++ b/include/asm-x86/segment_32.h
@@ -0,0 +1,148 @@
+#ifndef _ASM_SEGMENT_H
+#define _ASM_SEGMENT_H
+
+/*
+ * The layout of the per-CPU GDT under Linux:
+ *
+ *   0 - null
+ *   1 - reserved
+ *   2 - reserved
+ *   3 - reserved
+ *
+ *   4 - unused                 <==== new cacheline
+ *   5 - unused
+ *
+ *  ------- start of TLS (Thread-Local Storage) segments:
+ *
+ *   6 - TLS segment #1                 [ glibc's TLS segment ]
+ *   7 - TLS segment #2                 [ Wine's %fs Win32 segment ]
+ *   8 - TLS segment #3
+ *   9 - reserved
+ *  10 - reserved
+ *  11 - reserved
+ *
+ *  ------- start of kernel segments:
+ *
+ *  12 - kernel code segment            <==== new cacheline
+ *  13 - kernel data segment
+ *  14 - default user CS
+ *  15 - default user DS
+ *  16 - TSS
+ *  17 - LDT
+ *  18 - PNPBIOS support (16->32 gate)
+ *  19 - PNPBIOS support
+ *  20 - PNPBIOS support
+ *  21 - PNPBIOS support
+ *  22 - PNPBIOS support
+ *  23 - APM BIOS support
+ *  24 - APM BIOS support
+ *  25 - APM BIOS support 
+ *
+ *  26 - ESPFIX small SS
+ *  27 - per-cpu                        [ offset to per-cpu data area ]
+ *  28 - unused
+ *  29 - unused
+ *  30 - unused
+ *  31 - TSS for double fault handler
+ */
+#define GDT_ENTRY_TLS_ENTRIES   3
+#define GDT_ENTRY_TLS_MIN       6
+#define GDT_ENTRY_TLS_MAX       (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)
+
+#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
+
+#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)
+
+#define GDT_ENTRY_PNPBIOS_BASE          (GDT_ENTRY_KERNEL_BASE + 6)
+#define GDT_ENTRY_APMBIOS_BASE          (GDT_ENTRY_KERNEL_BASE + 11)
+
+#define GDT_ENTRY_ESPFIX_SS             (GDT_ENTRY_KERNEL_BASE + 14)
+#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8)
+
+#define GDT_ENTRY_PERCPU                        (GDT_ENTRY_KERNEL_BASE + 15)
+#ifdef CONFIG_SMP
+#define __KERNEL_PERCPU (GDT_ENTRY_PERCPU * 8)
+#else
+#define __KERNEL_PERCPU 0
+#endif
+
+#define GDT_ENTRY_DOUBLEFAULT_TSS       31
+
+/*
+ * The GDT has 32 entries
+ */
+#define GDT_ENTRIES 32
+#define GDT_SIZE (GDT_ENTRIES * 8)
+
+/* Simple and small GDT entries for booting only */
+
+#define GDT_ENTRY_BOOT_CS               2
+#define __BOOT_CS       (GDT_ENTRY_BOOT_CS * 8)
+
+#define GDT_ENTRY_BOOT_DS               (GDT_ENTRY_BOOT_CS + 1)
+#define __BOOT_DS       (GDT_ENTRY_BOOT_DS * 8)
+
+/* The PnP BIOS entries in the GDT */
+#define GDT_ENTRY_PNPBIOS_CS32          (GDT_ENTRY_PNPBIOS_BASE + 0)
+#define GDT_ENTRY_PNPBIOS_CS16          (GDT_ENTRY_PNPBIOS_BASE + 1)
+#define GDT_ENTRY_PNPBIOS_DS            (GDT_ENTRY_PNPBIOS_BASE + 2)
+#define GDT_ENTRY_PNPBIOS_TS1           (GDT_ENTRY_PNPBIOS_BASE + 3)
+#define GDT_ENTRY_PNPBIOS_TS2           (GDT_ENTRY_PNPBIOS_BASE + 4)
+
+/* The PnP BIOS selectors */
+#define PNP_CS32   (GDT_ENTRY_PNPBIOS_CS32 * 8) /* segment for calling fn */
+#define PNP_CS16   (GDT_ENTRY_PNPBIOS_CS16 * 8) /* code segment for BIOS */
+#define PNP_DS     (GDT_ENTRY_PNPBIOS_DS * 8)   /* data segment for BIOS */
+#define PNP_TS1    (GDT_ENTRY_PNPBIOS_TS1 * 8)  /* transfer data segment */
+#define PNP_TS2    (GDT_ENTRY_PNPBIOS_TS2 * 8)  /* another data segment */
+
+/*
+ * The interrupt descriptor table has room for 256 idt's,
+ * the global descriptor table is dependent on the number
+ * of tasks we can have..
+ */
+#define IDT_ENTRIES 256
+
+/* Bottom two bits of selector give the ring privilege level */
+#define SEGMENT_RPL_MASK        0x3
+/* Bit 2 is table indicator (LDT/GDT) */
+#define SEGMENT_TI_MASK         0x4
+
+/* User mode is privilege level 3 */
+#define USER_RPL                0x3
+/* LDT segment has TI set, GDT has it cleared */
+#define SEGMENT_LDT             0x4
+#define SEGMENT_GDT             0x0
+
+#ifndef CONFIG_PARAVIRT
+#define get_kernel_rpl()  0
+#endif
+/*
+ * Matching rules for certain types of segments.
+ */
+
+/* Matches only __KERNEL_CS, ignoring PnP / USER / APM segments */
+#define SEGMENT_IS_KERNEL_CODE(x) (((x) & 0xfc) == GDT_ENTRY_KERNEL_CS * 8)
+
+/* Matches __KERNEL_CS and __USER_CS (they must be 2 entries apart) */
+#define SEGMENT_IS_FLAT_CODE(x)  (((x) & 0xec) == GDT_ENTRY_KERNEL_CS * 8)
+
+/* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */
+#define SEGMENT_IS_PNP_CODE(x)   (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8)
+
+#endif
diff --git a/include/asm-x86/segment_64.h b/include/asm-x86/segment_64.h
new file mode 100644
index 000000000000..04b8ab21328f
--- /dev/null
+++ b/include/asm-x86/segment_64.h
@@ -0,0 +1,53 @@
+#ifndef _ASM_SEGMENT_H
+#define _ASM_SEGMENT_H
+
+#include <asm/cache.h>
+
+/* Simple and small GDT entries for booting only */
+
+#define GDT_ENTRY_BOOT_CS               2
+#define __BOOT_CS       (GDT_ENTRY_BOOT_CS * 8)
+
+#define GDT_ENTRY_BOOT_DS               (GDT_ENTRY_BOOT_CS + 1)
+#define __BOOT_DS       (GDT_ENTRY_BOOT_DS * 8)
+
+#define __KERNEL_CS     0x10
+#define __KERNEL_DS     0x18
+
+#define __KERNEL32_CS   0x08
+
+/* 
+ * we cannot use the same code segment descriptor for user and kernel
+ * -- not even in the long flat mode, because of different DPL /kkeil 
+ * 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 __USER32_DS     __USER_DS 
+
+#define GDT_ENTRY_TSS 8 /* needs two entries */
+#define GDT_ENTRY_LDT 10 /* needs two entries */
+#define GDT_ENTRY_TLS_MIN 12
+#define GDT_ENTRY_TLS_MAX 14
+
+#define GDT_ENTRY_TLS_ENTRIES 3
+
+#define GDT_ENTRY_PER_CPU 15    /* Abused to load per CPU data from limit */
+#define __PER_CPU_SEG   (GDT_ENTRY_PER_CPU * 8 + 3)
+
+/* TLS indexes for 64bit - hardcoded in arch_prctl */
+#define FS_TLS 0        
+#define GS_TLS 1        
+
+#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3)
+#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3)
+
+#define IDT_ENTRIES 256
+#define GDT_ENTRIES 16
+#define GDT_SIZE (GDT_ENTRIES * 8)
+#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) 
+
+#endif
diff --git a/include/asm-x86/semaphore.h b/include/asm-x86/semaphore.h
new file mode 100644
index 000000000000..572c0b67a6b0
--- /dev/null
+++ b/include/asm-x86/semaphore.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "semaphore_32.h"
+#else
+# include "semaphore_64.h"
+#endif
diff --git a/include/asm-x86/semaphore_32.h b/include/asm-x86/semaphore_32.h
new file mode 100644
index 000000000000..4e34a468c383
--- /dev/null
+++ b/include/asm-x86/semaphore_32.h
@@ -0,0 +1,176 @@
+#ifndef _I386_SEMAPHORE_H
+#define _I386_SEMAPHORE_H
+
+#include <linux/linkage.h>
+
+#ifdef __KERNEL__
+
+/*
+ * SMP- and interrupt-safe semaphores..
+ *
+ * (C) Copyright 1996 Linus Torvalds
+ *
+ * Modified 1996-12-23 by Dave Grothe <dave@gcom.com> to fix bugs in
+ *                     the original code and to make semaphore waits
+ *                     interruptible so that processes waiting on
+ *                     semaphores can be killed.
+ * Modified 1999-02-14 by Andrea Arcangeli, split the sched.c helper
+ *                     functions in asm/sempahore-helper.h while fixing a
+ *                     potential and subtle race discovered by Ulrich Schmid
+ *                     in down_interruptible(). Since I started to play here I
+ *                     also implemented the `trylock' semaphore operation.
+ *          1999-07-02 Artur Skawina <skawina@geocities.com>
+ *                     Optimized "0(ecx)" -> "(ecx)" (the assembler does not
+ *                     do this). Changed calling sequences from push/jmp to
+ *                     traditional call/ret.
+ * Modified 2001-01-01 Andreas Franck <afranck@gmx.de>
+ *                     Some hacks to ensure compatibility with recent
+ *                     GCC snapshots, to avoid stack corruption when compiling
+ *                     with -fomit-frame-pointer. It's not sure if this will
+ *                     be fixed in GCC, as our previous implementation was a
+ *                     bit dubious.
+ *
+ * If you would like to see an analysis of this implementation, please
+ * ftp to gcom.com and download the file
+ * /pub/linux/src/semaphore/semaphore-2.0.24.tar.gz.
+ *
+ */
+
+#include <asm/system.h>
+#include <asm/atomic.h>
+#include <linux/wait.h>
+#include <linux/rwsem.h>
+
+struct semaphore {
+        atomic_t count;
+        int sleepers;
+        wait_queue_head_t wait;
+};
+
+
+#define __SEMAPHORE_INITIALIZER(name, n)                                \
+{                                                                       \
+        .count          = ATOMIC_INIT(n),                               \
+        .sleepers       = 0,                                            \
+        .wait           = __WAIT_QUEUE_HEAD_INITIALIZER((name).wait)    \
+}
+
+#define __DECLARE_SEMAPHORE_GENERIC(name,count) \
+        struct semaphore name = __SEMAPHORE_INITIALIZER(name,count)
+
+#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name,1)
+#define DECLARE_MUTEX_LOCKED(name) __DECLARE_SEMAPHORE_GENERIC(name,0)
+
+static inline void sema_init (struct semaphore *sem, int val)
+{
+/*
+ *      *sem = (struct semaphore)__SEMAPHORE_INITIALIZER((*sem),val);
+ *
+ * i'd rather use the more flexible initialization above, but sadly
+ * GCC 2.7.2.3 emits a bogus warning. EGCS doesn't. Oh well.
+ */
+        atomic_set(&sem->count, val);
+        sem->sleepers = 0;
+        init_waitqueue_head(&sem->wait);
+}
+
+static inline void init_MUTEX (struct semaphore *sem)
+{
+        sema_init(sem, 1);
+}
+
+static inline void init_MUTEX_LOCKED (struct semaphore *sem)
+{
+        sema_init(sem, 0);
+}
+
+fastcall void __down_failed(void /* special register calling convention */);
+fastcall int  __down_failed_interruptible(void  /* params in registers */);
+fastcall int  __down_failed_trylock(void  /* params in registers */);
+fastcall void __up_wakeup(void /* special register calling convention */);
+
+/*
+ * This is ugly, but we want the default case to fall through.
+ * "__down_failed" is a special asm handler that calls the C
+ * routine that actually waits. See arch/i386/kernel/semaphore.c
+ */
+static inline void down(struct semaphore * sem)
+{
+        might_sleep();
+        __asm__ __volatile__(
+                "# atomic down operation\n\t"
+                LOCK_PREFIX "decl %0\n\t"     /* --sem->count */
+                "jns 2f\n"
+                "\tlea %0,%%eax\n\t"
+                "call __down_failed\n"
+                "2:"
+                :"+m" (sem->count)
+                :
+                :"memory","ax");
+}
+
+/*
+ * Interruptible try to acquire a semaphore.  If we obtained
+ * it, return zero.  If we were interrupted, returns -EINTR
+ */
+static inline int down_interruptible(struct semaphore * sem)
+{
+        int result;
+
+        might_sleep();
+        __asm__ __volatile__(
+                "# atomic interruptible down operation\n\t"
+                "xorl %0,%0\n\t"
+                LOCK_PREFIX "decl %1\n\t"     /* --sem->count */
+                "jns 2f\n\t"
+                "lea %1,%%eax\n\t"
+                "call __down_failed_interruptible\n"
+                "2:"
+                :"=&a" (result), "+m" (sem->count)
+                :
+                :"memory");
+        return result;
+}
+
+/*
+ * Non-blockingly attempt to down() a semaphore.
+ * Returns zero if we acquired it
+ */
+static inline int down_trylock(struct semaphore * sem)
+{
+        int result;
+
+        __asm__ __volatile__(
+                "# atomic interruptible down operation\n\t"
+                "xorl %0,%0\n\t"
+                LOCK_PREFIX "decl %1\n\t"     /* --sem->count */
+                "jns 2f\n\t"
+                "lea %1,%%eax\n\t"
+                "call __down_failed_trylock\n\t"
+                "2:\n"
+                :"=&a" (result), "+m" (sem->count)
+                :
+                :"memory");
+        return result;
+}
+
+/*
+ * Note! This is subtle. We jump to wake people up only if
+ * the semaphore was negative (== somebody was waiting on it).
+ */
+static inline void up(struct semaphore * sem)
+{
+        __asm__ __volatile__(
+                "# atomic up operation\n\t"
+                LOCK_PREFIX "incl %0\n\t"     /* ++sem->count */
+                "jg 1f\n\t"
+                "lea %0,%%eax\n\t"
+                "call __up_wakeup\n"
+                "1:"
+                :"+m" (sem->count)
+                :
+                :"memory","ax");
+}
+
+#endif
+#endif
diff --git a/include/asm-x86/semaphore_64.h b/include/asm-x86/semaphore_64.h
new file mode 100644
index 000000000000..1194888536b9
--- /dev/null
+++ b/include/asm-x86/semaphore_64.h
@@ -0,0 +1,181 @@
+#ifndef _X86_64_SEMAPHORE_H
+#define _X86_64_SEMAPHORE_H
+
+#include <linux/linkage.h>
+
+#ifdef __KERNEL__
+
+/*
+ * SMP- and interrupt-safe semaphores..
+ *
+ * (C) Copyright 1996 Linus Torvalds
+ *
+ * Modified 1996-12-23 by Dave Grothe <dave@gcom.com> to fix bugs in
+ *                     the original code and to make semaphore waits
+ *                     interruptible so that processes waiting on
+ *                     semaphores can be killed.
+ * Modified 1999-02-14 by Andrea Arcangeli, split the sched.c helper
+ *                     functions in asm/sempahore-helper.h while fixing a
+ *                     potential and subtle race discovered by Ulrich Schmid
+ *                     in down_interruptible(). Since I started to play here I
+ *                     also implemented the `trylock' semaphore operation.
+ *          1999-07-02 Artur Skawina <skawina@geocities.com>
+ *                     Optimized "0(ecx)" -> "(ecx)" (the assembler does not
+ *                     do this). Changed calling sequences from push/jmp to
+ *                     traditional call/ret.
+ * Modified 2001-01-01 Andreas Franck <afranck@gmx.de>
+ *                     Some hacks to ensure compatibility with recent
+ *                     GCC snapshots, to avoid stack corruption when compiling
+ *                     with -fomit-frame-pointer. It's not sure if this will
+ *                     be fixed in GCC, as our previous implementation was a
+ *                     bit dubious.
+ *
+ * If you would like to see an analysis of this implementation, please
+ * ftp to gcom.com and download the file
+ * /pub/linux/src/semaphore/semaphore-2.0.24.tar.gz.
+ *
+ */
+
+#include <asm/system.h>
+#include <asm/atomic.h>
+#include <asm/rwlock.h>
+#include <linux/wait.h>
+#include <linux/rwsem.h>
+#include <linux/stringify.h>
+
+struct semaphore {
+        atomic_t count;
+        int sleepers;
+        wait_queue_head_t wait;
+};
+
+#define __SEMAPHORE_INITIALIZER(name, n)                                \
+{                                                                       \
+        .count          = ATOMIC_INIT(n),                               \
+        .sleepers       = 0,                                            \
+        .wait           = __WAIT_QUEUE_HEAD_INITIALIZER((name).wait)    \
+}
+
+#define __DECLARE_SEMAPHORE_GENERIC(name,count) \
+        struct semaphore name = __SEMAPHORE_INITIALIZER(name,count)
+
+#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name,1)
+#define DECLARE_MUTEX_LOCKED(name) __DECLARE_SEMAPHORE_GENERIC(name,0)
+
+static inline void sema_init (struct semaphore *sem, int val)
+{
+/*
+ *      *sem = (struct semaphore)__SEMAPHORE_INITIALIZER((*sem),val);
+ *
+ * i'd rather use the more flexible initialization above, but sadly
+ * GCC 2.7.2.3 emits a bogus warning. EGCS doesn't. Oh well.
+ */
+        atomic_set(&sem->count, val);
+        sem->sleepers = 0;
+        init_waitqueue_head(&sem->wait);
+}
+
+static inline void init_MUTEX (struct semaphore *sem)
+{
+        sema_init(sem, 1);
+}
+
+static inline void init_MUTEX_LOCKED (struct semaphore *sem)
+{
+        sema_init(sem, 0);
+}
+
+asmlinkage void __down_failed(void /* special register calling convention */);
+asmlinkage int  __down_failed_interruptible(void  /* params in registers */);
+asmlinkage int  __down_failed_trylock(void  /* params in registers */);
+asmlinkage void __up_wakeup(void /* special register calling convention */);
+
+asmlinkage void __down(struct semaphore * sem);
+asmlinkage int  __down_interruptible(struct semaphore * sem);
+asmlinkage int  __down_trylock(struct semaphore * sem);
+asmlinkage void __up(struct semaphore * sem);
+
+/*
+ * This is ugly, but we want the default case to fall through.
+ * "__down_failed" is a special asm handler that calls the C
+ * routine that actually waits. See arch/x86_64/kernel/semaphore.c
+ */
+static inline void down(struct semaphore * sem)
+{
+        might_sleep();
+
+        __asm__ __volatile__(
+                "# atomic down operation\n\t"
+                LOCK_PREFIX "decl %0\n\t"     /* --sem->count */
+                "jns 1f\n\t"
+                "call __down_failed\n"
+                "1:"
+                :"=m" (sem->count)
+                :"D" (sem)
+                :"memory");
+}
+
+/*
+ * Interruptible try to acquire a semaphore.  If we obtained
+ * it, return zero.  If we were interrupted, returns -EINTR
+ */
+static inline int down_interruptible(struct semaphore * sem)
+{
+        int result;
+
+        might_sleep();
+
+        __asm__ __volatile__(
+                "# atomic interruptible down operation\n\t"
+                "xorl %0,%0\n\t"
+                LOCK_PREFIX "decl %1\n\t"     /* --sem->count */
+                "jns 2f\n\t"
+                "call __down_failed_interruptible\n"
+                "2:\n"
+                :"=&a" (result), "=m" (sem->count)
+                :"D" (sem)
+                :"memory");
+        return result;
+}
+
+/*
+ * Non-blockingly attempt to down() a semaphore.
+ * Returns zero if we acquired it
+ */
+static inline int down_trylock(struct semaphore * sem)
+{
+        int result;
+
+        __asm__ __volatile__(
+                "# atomic interruptible down operation\n\t"
+                "xorl %0,%0\n\t"
+                LOCK_PREFIX "decl %1\n\t"     /* --sem->count */
+                "jns 2f\n\t"
+                "call __down_failed_trylock\n\t"
+                "2:\n"
+                :"=&a" (result), "=m" (sem->count)
+                :"D" (sem)
+                :"memory","cc");
+        return result;
+}
+
+/*
+ * Note! This is subtle. We jump to wake people up only if
+ * the semaphore was negative (== somebody was waiting on it).
+ * The default case (no contention) will result in NO
+ * jumps for both down() and up().
+ */
+static inline void up(struct semaphore * sem)
+{
+        __asm__ __volatile__(
+                "# atomic up operation\n\t"
+                LOCK_PREFIX "incl %0\n\t"     /* ++sem->count */
+                "jg 1f\n\t"
+                "call __up_wakeup\n"
+                "1:"
+                :"=m" (sem->count)
+                :"D" (sem)
+                :"memory");
+}
+#endif /* __KERNEL__ */
+#endif
diff --git a/include/asm-x86/sembuf.h b/include/asm-x86/sembuf.h
new file mode 100644
index 000000000000..e42c971e383f
--- /dev/null
+++ b/include/asm-x86/sembuf.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "sembuf_32.h"
+# else
+#  include "sembuf_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "sembuf_32.h"
+# else
+#  include "sembuf_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/sembuf_32.h b/include/asm-x86/sembuf_32.h
new file mode 100644
index 000000000000..323835166c14
--- /dev/null
+++ b/include/asm-x86/sembuf_32.h
@@ -0,0 +1,25 @@
+#ifndef _I386_SEMBUF_H
+#define _I386_SEMBUF_H
+
+/* 
+ * The semid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct semid64_ds {
+        struct ipc64_perm sem_perm;             /* permissions .. see ipc.h */
+        __kernel_time_t sem_otime;              /* last semop time */
+        unsigned long   __unused1;
+        __kernel_time_t sem_ctime;              /* last change time */
+        unsigned long   __unused2;
+        unsigned long   sem_nsems;              /* no. of semaphores in array */
+        unsigned long   __unused3;
+        unsigned long   __unused4;
+};
+
+#endif /* _I386_SEMBUF_H */
diff --git a/include/asm-x86/sembuf_64.h b/include/asm-x86/sembuf_64.h
new file mode 100644
index 000000000000..63b52925ae2a
--- /dev/null
+++ b/include/asm-x86/sembuf_64.h
@@ -0,0 +1,25 @@
+#ifndef _X86_64_SEMBUF_H
+#define _X86_64_SEMBUF_H
+
+/* 
+ * The semid64_ds structure for x86_64 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct semid64_ds {
+        struct ipc64_perm sem_perm;             /* permissions .. see ipc.h */
+        __kernel_time_t sem_otime;              /* last semop time */
+        unsigned long   __unused1;
+        __kernel_time_t sem_ctime;              /* last change time */
+        unsigned long   __unused2;
+        unsigned long   sem_nsems;              /* no. of semaphores in array */
+        unsigned long   __unused3;
+        unsigned long   __unused4;
+};
+
+#endif /* _X86_64_SEMBUF_H */
diff --git a/include/asm-x86/serial.h b/include/asm-x86/serial.h
new file mode 100644
index 000000000000..cf1b05227b29
--- /dev/null
+++ b/include/asm-x86/serial.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "serial_32.h"
+#else
+# include "serial_64.h"
+#endif
diff --git a/include/asm-x86/serial_32.h b/include/asm-x86/serial_32.h
new file mode 100644
index 000000000000..bd67480ca109
--- /dev/null
+++ b/include/asm-x86/serial_32.h
@@ -0,0 +1,29 @@
+/*
+ * include/asm-i386/serial.h
+ */
+
+
+/*
+ * This assumes you have a 1.8432 MHz clock for your UART.
+ *
+ * It'd be nice if someone built a serial card with a 24.576 MHz
+ * clock, since the 16550A is capable of handling a top speed of 1.5
+ * megabits/second; but this requires the faster clock.
+ */
+#define BASE_BAUD ( 1843200 / 16 )
+
+/* Standard COM flags (except for COM4, because of the 8514 problem) */
+#ifdef CONFIG_SERIAL_DETECT_IRQ
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
+#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
+#else
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
+#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
+#endif
+
+#define SERIAL_PORT_DFNS                        \
+        /* UART CLK   PORT IRQ     FLAGS        */                      \
+        { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },      /* ttyS0 */     \
+        { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },      /* ttyS1 */     \
+        { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },      /* ttyS2 */     \
+        { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },     /* ttyS3 */
diff --git a/include/asm-x86/serial_64.h b/include/asm-x86/serial_64.h
new file mode 100644
index 000000000000..b0496e0d72a6
--- /dev/null
+++ b/include/asm-x86/serial_64.h
@@ -0,0 +1,29 @@
+/*
+ * include/asm-x86_64/serial.h
+ */
+
+
+/*
+ * This assumes you have a 1.8432 MHz clock for your UART.
+ *
+ * It'd be nice if someone built a serial card with a 24.576 MHz
+ * clock, since the 16550A is capable of handling a top speed of 1.5
+ * megabits/second; but this requires the faster clock.
+ */
+#define BASE_BAUD ( 1843200 / 16 )
+
+/* Standard COM flags (except for COM4, because of the 8514 problem) */
+#ifdef CONFIG_SERIAL_DETECT_IRQ
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
+#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
+#else
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
+#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
+#endif
+
+#define SERIAL_PORT_DFNS                        \
+        /* UART CLK   PORT IRQ     FLAGS        */                      \
+        { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },      /* ttyS0 */     \
+        { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },      /* ttyS1 */     \
+        { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },      /* ttyS2 */     \
+        { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },     /* ttyS3 */
diff --git a/include/asm-x86/setup.h b/include/asm-x86/setup.h
new file mode 100644
index 000000000000..81c0d98bb1c8
--- /dev/null
+++ b/include/asm-x86/setup.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "setup_32.h"
+# else
+#  include "setup_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "setup_32.h"
+# else
+#  include "setup_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/setup_32.h b/include/asm-x86/setup_32.h
new file mode 100644
index 000000000000..7862fe858a9e
--- /dev/null
+++ b/include/asm-x86/setup_32.h
@@ -0,0 +1,92 @@
+/*
+ *      Just a place holder. We don't want to have to test x86 before
+ *      we include stuff
+ */
+
+#ifndef _i386_SETUP_H
+#define _i386_SETUP_H
+
+#define COMMAND_LINE_SIZE 2048
+
+#ifdef __KERNEL__
+#include <linux/pfn.h>
+
+/*
+ * Reserved space for vmalloc and iomap - defined in asm/page.h
+ */
+#define MAXMEM_PFN      PFN_DOWN(MAXMEM)
+#define MAX_NONPAE_PFN  (1 << 20)
+
+#define PARAM_SIZE 4096
+
+#define OLD_CL_MAGIC_ADDR       0x90020
+#define OLD_CL_MAGIC            0xA33F
+#define OLD_CL_BASE_ADDR        0x90000
+#define OLD_CL_OFFSET           0x90022
+#define NEW_CL_POINTER          0x228   /* Relative to real mode data */
+
+#ifndef __ASSEMBLY__
+
+#include <asm/bootparam.h>
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+extern struct boot_params boot_params;
+
+#define PARAM   ((char *)&boot_params)
+#define SCREEN_INFO (*(struct screen_info *) (PARAM+0))
+#define EXT_MEM_K (*(unsigned short *) (PARAM+2))
+#define ALT_MEM_K (*(unsigned long *) (PARAM+0x1e0))
+#define E820_MAP_NR (*(char*) (PARAM+E820NR))
+#define E820_MAP    ((struct e820entry *) (PARAM+E820MAP))
+#define APM_BIOS_INFO (*(struct apm_bios_info *) (PARAM+0x40))
+#define IST_INFO   (*(struct ist_info *) (PARAM+0x60))
+#define SYS_DESC_TABLE (*(struct sys_desc_table *)(PARAM+0xa0))
+#define EFI_SYSTAB ((efi_system_table_t *) *((unsigned long *)(PARAM+0x1c4)))
+#define EFI_MEMDESC_SIZE (*((unsigned long *) (PARAM+0x1c8)))
+#define EFI_MEMDESC_VERSION (*((unsigned long *) (PARAM+0x1cc)))
+#define EFI_MEMMAP ((void *) *((unsigned long *)(PARAM+0x1d0)))
+#define EFI_MEMMAP_SIZE (*((unsigned long *) (PARAM+0x1d4)))
+#define MOUNT_ROOT_RDONLY (*(unsigned short *) (PARAM+0x1F2))
+#define RAMDISK_FLAGS (*(unsigned short *) (PARAM+0x1F8))
+#define VIDEO_MODE (*(unsigned short *) (PARAM+0x1FA))
+#define ORIG_ROOT_DEV (*(unsigned short *) (PARAM+0x1FC))
+#define AUX_DEVICE_INFO (*(unsigned char *) (PARAM+0x1FF))
+#define LOADER_TYPE (*(unsigned char *) (PARAM+0x210))
+#define KERNEL_START (*(unsigned long *) (PARAM+0x214))
+#define INITRD_START (*(unsigned long *) (PARAM+0x218))
+#define INITRD_SIZE (*(unsigned long *) (PARAM+0x21c))
+#define EDID_INFO   (*(struct edid_info *) (PARAM+0x140))
+#define EDD_NR     (*(unsigned char *) (PARAM+EDDNR))
+#define EDD_MBR_SIG_NR (*(unsigned char *) (PARAM+EDD_MBR_SIG_NR_BUF))
+#define EDD_MBR_SIGNATURE ((unsigned int *) (PARAM+EDD_MBR_SIG_BUF))
+#define EDD_BUF     ((struct edd_info *) (PARAM+EDDBUF))
+
+/*
+ * 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);
+
+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);
+
+extern unsigned long init_pg_tables_end;
+
+#ifndef CONFIG_PARAVIRT
+#define paravirt_post_allocator_init()  do {} while (0)
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif  /*  __KERNEL__  */
+
+#endif /* _i386_SETUP_H */
diff --git a/include/asm-x86/setup_64.h b/include/asm-x86/setup_64.h
new file mode 100644
index 000000000000..eaeff73d6c10
--- /dev/null
+++ b/include/asm-x86/setup_64.h
@@ -0,0 +1,6 @@
+#ifndef _x8664_SETUP_H
+#define _x8664_SETUP_H
+
+#define COMMAND_LINE_SIZE       2048
+
+#endif
diff --git a/include/asm-x86/shmbuf.h b/include/asm-x86/shmbuf.h
new file mode 100644
index 000000000000..e85f1cb11217
--- /dev/null
+++ b/include/asm-x86/shmbuf.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "shmbuf_32.h"
+# else
+#  include "shmbuf_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "shmbuf_32.h"
+# else
+#  include "shmbuf_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/shmbuf_32.h b/include/asm-x86/shmbuf_32.h
new file mode 100644
index 000000000000..d1cdc3cb079b
--- /dev/null
+++ b/include/asm-x86/shmbuf_32.h
@@ -0,0 +1,42 @@
+#ifndef _I386_SHMBUF_H
+#define _I386_SHMBUF_H
+
+/* 
+ * The shmid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct shmid64_ds {
+        struct ipc64_perm       shm_perm;       /* operation perms */
+        size_t                  shm_segsz;      /* size of segment (bytes) */
+        __kernel_time_t         shm_atime;      /* last attach time */
+        unsigned long           __unused1;
+        __kernel_time_t         shm_dtime;      /* last detach time */
+        unsigned long           __unused2;
+        __kernel_time_t         shm_ctime;      /* last change time */
+        unsigned long           __unused3;
+        __kernel_pid_t          shm_cpid;       /* pid of creator */
+        __kernel_pid_t          shm_lpid;       /* pid of last operator */
+        unsigned long           shm_nattch;     /* no. of current attaches */
+        unsigned long           __unused4;
+        unsigned long           __unused5;
+};
+
+struct shminfo64 {
+        unsigned long   shmmax;
+        unsigned long   shmmin;
+        unsigned long   shmmni;
+        unsigned long   shmseg;
+        unsigned long   shmall;
+        unsigned long   __unused1;
+        unsigned long   __unused2;
+        unsigned long   __unused3;
+        unsigned long   __unused4;
+};
+
+#endif /* _I386_SHMBUF_H */
diff --git a/include/asm-x86/shmbuf_64.h b/include/asm-x86/shmbuf_64.h
new file mode 100644
index 000000000000..5a6d6dda7c48
--- /dev/null
+++ b/include/asm-x86/shmbuf_64.h
@@ -0,0 +1,38 @@
+#ifndef _X8664_SHMBUF_H
+#define _X8664_SHMBUF_H
+
+/* 
+ * The shmid64_ds structure for x8664 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 2 miscellaneous 64-bit values
+ */
+
+struct shmid64_ds {
+        struct ipc64_perm       shm_perm;       /* operation perms */
+        size_t                  shm_segsz;      /* size of segment (bytes) */
+        __kernel_time_t         shm_atime;      /* last attach time */
+        __kernel_time_t         shm_dtime;      /* last detach time */
+        __kernel_time_t         shm_ctime;      /* last change time */
+        __kernel_pid_t          shm_cpid;       /* pid of creator */
+        __kernel_pid_t          shm_lpid;       /* pid of last operator */
+        unsigned long           shm_nattch;     /* no. of current attaches */
+        unsigned long           __unused4;
+        unsigned long           __unused5;
+};
+
+struct shminfo64 {
+        unsigned long   shmmax;
+        unsigned long   shmmin;
+        unsigned long   shmmni;
+        unsigned long   shmseg;
+        unsigned long   shmall;
+        unsigned long   __unused1;
+        unsigned long   __unused2;
+        unsigned long   __unused3;
+        unsigned long   __unused4;
+};
+
+#endif
diff --git a/include/asm-x86/shmparam.h b/include/asm-x86/shmparam.h
new file mode 100644
index 000000000000..165627cc5345
--- /dev/null
+++ b/include/asm-x86/shmparam.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "shmparam_32.h"
+# else
+#  include "shmparam_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "shmparam_32.h"
+# else
+#  include "shmparam_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/shmparam_32.h b/include/asm-x86/shmparam_32.h
new file mode 100644
index 000000000000..786243a5b319
--- /dev/null
+++ b/include/asm-x86/shmparam_32.h
@@ -0,0 +1,6 @@
+#ifndef _ASMI386_SHMPARAM_H
+#define _ASMI386_SHMPARAM_H
+
+#define SHMLBA PAGE_SIZE                 /* attach addr a multiple of this */
+
+#endif /* _ASMI386_SHMPARAM_H */
diff --git a/include/asm-x86/shmparam_64.h b/include/asm-x86/shmparam_64.h
new file mode 100644
index 000000000000..d7021620dcb7
--- /dev/null
+++ b/include/asm-x86/shmparam_64.h
@@ -0,0 +1,6 @@
+#ifndef _ASMX8664_SHMPARAM_H
+#define _ASMX8664_SHMPARAM_H
+
+#define SHMLBA PAGE_SIZE                 /* attach addr a multiple of this */
+
+#endif /* _ASMX8664_SHMPARAM_H */
diff --git a/include/asm-x86/sigcontext.h b/include/asm-x86/sigcontext.h
new file mode 100644
index 000000000000..0d16ceff1599
--- /dev/null
+++ b/include/asm-x86/sigcontext.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "sigcontext_32.h"
+# else
+#  include "sigcontext_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "sigcontext_32.h"
+# else
+#  include "sigcontext_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/sigcontext32.h b/include/asm-x86/sigcontext32.h
new file mode 100644
index 000000000000..3d657038ab7c
--- /dev/null
+++ b/include/asm-x86/sigcontext32.h
@@ -0,0 +1,71 @@
+#ifndef _SIGCONTEXT32_H
+#define _SIGCONTEXT32_H 1
+
+/* signal context for 32bit programs. */
+
+#define X86_FXSR_MAGIC          0x0000
+
+struct _fpreg {
+        unsigned short significand[4];
+        unsigned short exponent;
+};
+
+struct _fpxreg {
+        unsigned short significand[4];
+        unsigned short exponent;
+        unsigned short padding[3];
+};
+
+struct _xmmreg {
+        __u32   element[4];
+};
+
+/* FSAVE frame with extensions */
+struct _fpstate_ia32 {
+        /* Regular FPU environment */
+        __u32   cw;
+        __u32   sw;
+        __u32   tag;    /* not compatible to 64bit twd */
+        __u32   ipoff;                  
+        __u32   cssel;
+        __u32   dataoff;
+        __u32   datasel;
+        struct _fpreg   _st[8];
+        unsigned short  status;
+        unsigned short  magic;          /* 0xffff = regular FPU data only */
+
+        /* FXSR FPU environment */
+        __u32   _fxsr_env[6];
+        __u32   mxcsr;
+        __u32   reserved;
+        struct _fpxreg  _fxsr_st[8];
+        struct _xmmreg  _xmm[8];        /* It's actually 16 */ 
+        __u32   padding[56];
+};
+
+struct sigcontext_ia32 {
+       unsigned short gs, __gsh;
+       unsigned short fs, __fsh;
+       unsigned short es, __esh;
+       unsigned short ds, __dsh;
+       unsigned int edi;
+       unsigned int esi;
+       unsigned int ebp;
+       unsigned int esp;
+       unsigned int ebx;
+       unsigned int edx;
+       unsigned int ecx;
+       unsigned int eax;
+       unsigned int trapno;
+       unsigned int err;
+       unsigned int eip;
+       unsigned short cs, __csh;
+       unsigned int eflags;
+       unsigned int esp_at_signal;
+       unsigned short ss, __ssh;
+       unsigned int fpstate;            /* really (struct _fpstate_ia32 *) */
+       unsigned int oldmask;
+       unsigned int cr2;
+};
+
+#endif
diff --git a/include/asm-x86/sigcontext_32.h b/include/asm-x86/sigcontext_32.h
new file mode 100644
index 000000000000..aaef089a7787
--- /dev/null
+++ b/include/asm-x86/sigcontext_32.h
@@ -0,0 +1,85 @@
+#ifndef _ASMi386_SIGCONTEXT_H
+#define _ASMi386_SIGCONTEXT_H
+
+#include <linux/compiler.h>
+
+/*
+ * As documented in the iBCS2 standard..
+ *
+ * The first part of "struct _fpstate" is just the normal i387
+ * hardware setup, the extra "status" word is used to save the
+ * coprocessor status word before entering the handler.
+ *
+ * Pentium III FXSR, SSE support
+ *      Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * The FPU state data structure has had to grow to accommodate the
+ * extended FPU state required by the Streaming SIMD Extensions.
+ * There is no documented standard to accomplish this at the moment.
+ */
+struct _fpreg {
+        unsigned short significand[4];
+        unsigned short exponent;
+};
+
+struct _fpxreg {
+        unsigned short significand[4];
+        unsigned short exponent;
+        unsigned short padding[3];
+};
+
+struct _xmmreg {
+        unsigned long element[4];
+};
+
+struct _fpstate {
+        /* Regular FPU environment */
+        unsigned long   cw;
+        unsigned long   sw;
+        unsigned long   tag;
+        unsigned long   ipoff;
+        unsigned long   cssel;
+        unsigned long   dataoff;
+        unsigned long   datasel;
+        struct _fpreg   _st[8];
+        unsigned short  status;
+        unsigned short  magic;          /* 0xffff = regular FPU data only */
+
+        /* FXSR FPU environment */
+        unsigned long   _fxsr_env[6];   /* FXSR FPU env is ignored */
+        unsigned long   mxcsr;
+        unsigned long   reserved;
+        struct _fpxreg  _fxsr_st[8];    /* FXSR FPU reg data is ignored */
+        struct _xmmreg  _xmm[8];
+        unsigned long   padding[56];
+};
+
+#define X86_FXSR_MAGIC          0x0000
+
+struct sigcontext {
+        unsigned short gs, __gsh;
+        unsigned short fs, __fsh;
+        unsigned short es, __esh;
+        unsigned short ds, __dsh;
+        unsigned long edi;
+        unsigned long esi;
+        unsigned long ebp;
+        unsigned long esp;
+        unsigned long ebx;
+        unsigned long edx;
+        unsigned long ecx;
+        unsigned long eax;
+        unsigned long trapno;
+        unsigned long err;
+        unsigned long eip;
+        unsigned short cs, __csh;
+        unsigned long eflags;
+        unsigned long esp_at_signal;
+        unsigned short ss, __ssh;
+        struct _fpstate __user * fpstate;
+        unsigned long oldmask;
+        unsigned long cr2;
+};
+
+
+#endif
diff --git a/include/asm-x86/sigcontext_64.h b/include/asm-x86/sigcontext_64.h
new file mode 100644
index 000000000000..b4e40236666c
--- /dev/null
+++ b/include/asm-x86/sigcontext_64.h
@@ -0,0 +1,55 @@
+#ifndef _ASM_X86_64_SIGCONTEXT_H
+#define _ASM_X86_64_SIGCONTEXT_H
+
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+/* FXSAVE frame */
+/* Note: reserved1/2 may someday contain valuable data. Always save/restore
+   them when you change signal frames. */
+struct _fpstate {
+        __u16   cwd;
+        __u16   swd;
+        __u16   twd;    /* Note this is not the same as the 32bit/x87/FSAVE twd */
+        __u16   fop;
+        __u64   rip;
+        __u64   rdp; 
+        __u32   mxcsr;
+        __u32   mxcsr_mask;
+        __u32   st_space[32];   /* 8*16 bytes for each FP-reg */
+        __u32   xmm_space[64];  /* 16*16 bytes for each XMM-reg  */
+        __u32   reserved2[24];
+};
+
+struct sigcontext { 
+        unsigned long r8;
+        unsigned long r9;
+        unsigned long r10;
+        unsigned long r11;
+        unsigned long r12;
+        unsigned long r13;
+        unsigned long r14;
+        unsigned long r15;
+        unsigned long rdi;
+        unsigned long rsi;
+        unsigned long rbp;
+        unsigned long rbx;
+        unsigned long rdx;
+        unsigned long rax;
+        unsigned long rcx;
+        unsigned long rsp;
+        unsigned long rip;
+        unsigned long eflags;           /* RFLAGS */
+        unsigned short cs;
+        unsigned short gs;
+        unsigned short fs;
+        unsigned short __pad0; 
+        unsigned long err;
+        unsigned long trapno;
+        unsigned long oldmask;
+        unsigned long cr2;
+        struct _fpstate __user *fpstate;        /* zero when no FPU context */
+        unsigned long reserved1[8];
+};
+
+#endif
diff --git a/include/asm-x86/siginfo.h b/include/asm-x86/siginfo.h
new file mode 100644
index 000000000000..0b8e4bb47d25
--- /dev/null
+++ b/include/asm-x86/siginfo.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "siginfo_32.h"
+# else
+#  include "siginfo_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "siginfo_32.h"
+# else
+#  include "siginfo_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/siginfo_32.h b/include/asm-x86/siginfo_32.h
new file mode 100644
index 000000000000..fe18f98fccfa
--- /dev/null
+++ b/include/asm-x86/siginfo_32.h
@@ -0,0 +1,6 @@
+#ifndef _I386_SIGINFO_H
+#define _I386_SIGINFO_H
+
+#include <asm-generic/siginfo.h>
+
+#endif
diff --git a/include/asm-x86/siginfo_64.h b/include/asm-x86/siginfo_64.h
new file mode 100644
index 000000000000..d09a1e6e7246
--- /dev/null
+++ b/include/asm-x86/siginfo_64.h
@@ -0,0 +1,8 @@
+#ifndef _X8664_SIGINFO_H
+#define _X8664_SIGINFO_H
+
+#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
+
+#include <asm-generic/siginfo.h>
+
+#endif
diff --git a/include/asm-x86/signal.h b/include/asm-x86/signal.h
new file mode 100644
index 000000000000..bf5a63f457da
--- /dev/null
+++ b/include/asm-x86/signal.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "signal_32.h"
+# else
+#  include "signal_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "signal_32.h"
+# else
+#  include "signal_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/signal_32.h b/include/asm-x86/signal_32.h
new file mode 100644
index 000000000000..c3e8adec5918
--- /dev/null
+++ b/include/asm-x86/signal_32.h
@@ -0,0 +1,232 @@
+#ifndef _ASMi386_SIGNAL_H
+#define _ASMi386_SIGNAL_H
+
+#include <linux/types.h>
+#include <linux/time.h>
+#include <linux/compiler.h>
+
+/* Avoid too many header ordering problems.  */
+struct siginfo;
+
+#ifdef __KERNEL__
+
+#include <linux/linkage.h>
+
+/* Most things should be clean enough to redefine this at will, if care
+   is taken to make libc match.  */
+
+#define _NSIG           64
+#define _NSIG_BPW       32
+#define _NSIG_WORDS     (_NSIG / _NSIG_BPW)
+
+typedef unsigned long old_sigset_t;             /* at least 32 bits */
+
+typedef struct {
+        unsigned long sig[_NSIG_WORDS];
+} sigset_t;
+
+#else
+/* Here we must cater to libcs that poke about in kernel headers.  */
+
+#define NSIG            32
+typedef unsigned long sigset_t;
+
+#endif /* __KERNEL__ */
+
+#define SIGHUP           1
+#define SIGINT           2
+#define SIGQUIT          3
+#define SIGILL           4
+#define SIGTRAP          5
+#define SIGABRT          6
+#define SIGIOT           6
+#define SIGBUS           7
+#define SIGFPE           8
+#define SIGKILL          9
+#define SIGUSR1         10
+#define SIGSEGV         11
+#define SIGUSR2         12
+#define SIGPIPE         13
+#define SIGALRM         14
+#define SIGTERM         15
+#define SIGSTKFLT       16
+#define SIGCHLD         17
+#define SIGCONT         18
+#define SIGSTOP         19
+#define SIGTSTP         20
+#define SIGTTIN         21
+#define SIGTTOU         22
+#define SIGURG          23
+#define SIGXCPU         24
+#define SIGXFSZ         25
+#define SIGVTALRM       26
+#define SIGPROF         27
+#define SIGWINCH        28
+#define SIGIO           29
+#define SIGPOLL         SIGIO
+/*
+#define SIGLOST         29
+*/
+#define SIGPWR          30
+#define SIGSYS          31
+#define SIGUNUSED       31
+
+/* These should not be considered constants from userland.  */
+#define SIGRTMIN        32
+#define SIGRTMAX        _NSIG
+
+/*
+ * SA_FLAGS values:
+ *
+ * SA_ONSTACK indicates that a registered stack_t will be used.
+ * SA_RESTART flag to get restarting signals (which were the default long ago)
+ * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
+ * SA_RESETHAND clears the handler when the signal is delivered.
+ * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
+ * SA_NODEFER prevents the current signal from being masked in the handler.
+ *
+ * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
+ * Unix names RESETHAND and NODEFER respectively.
+ */
+#define SA_NOCLDSTOP    0x00000001u
+#define SA_NOCLDWAIT    0x00000002u
+#define SA_SIGINFO      0x00000004u
+#define SA_ONSTACK      0x08000000u
+#define SA_RESTART      0x10000000u
+#define SA_NODEFER      0x40000000u
+#define SA_RESETHAND    0x80000000u
+
+#define SA_NOMASK       SA_NODEFER
+#define SA_ONESHOT      SA_RESETHAND
+
+#define SA_RESTORER     0x04000000
+
+/* 
+ * sigaltstack controls
+ */
+#define SS_ONSTACK      1
+#define SS_DISABLE      2
+
+#define MINSIGSTKSZ     2048
+#define SIGSTKSZ        8192
+
+#include <asm-generic/signal.h>
+
+#ifdef __KERNEL__
+struct old_sigaction {
+        __sighandler_t sa_handler;
+        old_sigset_t sa_mask;
+        unsigned long sa_flags;
+        __sigrestore_t sa_restorer;
+};
+
+struct sigaction {
+        __sighandler_t sa_handler;
+        unsigned long sa_flags;
+        __sigrestore_t sa_restorer;
+        sigset_t sa_mask;               /* mask last for extensibility */
+};
+
+struct k_sigaction {
+        struct sigaction sa;
+};
+#else
+/* Here we must cater to libcs that poke about in kernel headers.  */
+
+struct sigaction {
+        union {
+          __sighandler_t _sa_handler;
+          void (*_sa_sigaction)(int, struct siginfo *, void *);
+        } _u;
+        sigset_t sa_mask;
+        unsigned long sa_flags;
+        void (*sa_restorer)(void);
+};
+
+#define sa_handler      _u._sa_handler
+#define sa_sigaction    _u._sa_sigaction
+
+#endif /* __KERNEL__ */
+
+typedef struct sigaltstack {
+        void __user *ss_sp;
+        int ss_flags;
+        size_t ss_size;
+} stack_t;
+
+#ifdef __KERNEL__
+#include <asm/sigcontext.h>
+
+#define __HAVE_ARCH_SIG_BITOPS
+
+#define sigaddset(set,sig)                 \
+        (__builtin_constant_p(sig) ?       \
+        __const_sigaddset((set),(sig)) :   \
+        __gen_sigaddset((set),(sig)))
+
+static __inline__ void __gen_sigaddset(sigset_t *set, int _sig)
+{
+        __asm__("btsl %1,%0" : "+m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static __inline__ void __const_sigaddset(sigset_t *set, int _sig)
+{
+        unsigned long sig = _sig - 1;
+        set->sig[sig / _NSIG_BPW] |= 1 << (sig % _NSIG_BPW);
+}
+
+#define sigdelset(set,sig)                 \
+        (__builtin_constant_p(sig) ?       \
+        __const_sigdelset((set),(sig)) :   \
+        __gen_sigdelset((set),(sig)))
+
+
+static __inline__ void __gen_sigdelset(sigset_t *set, int _sig)
+{
+        __asm__("btrl %1,%0" : "+m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static __inline__ void __const_sigdelset(sigset_t *set, int _sig)
+{
+        unsigned long sig = _sig - 1;
+        set->sig[sig / _NSIG_BPW] &= ~(1 << (sig % _NSIG_BPW));
+}
+
+static __inline__ int __const_sigismember(sigset_t *set, int _sig)
+{
+        unsigned long sig = _sig - 1;
+        return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW));
+}
+
+static __inline__ int __gen_sigismember(sigset_t *set, int _sig)
+{
+        int ret;
+        __asm__("btl %2,%1\n\tsbbl %0,%0"
+                : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+        return ret;
+}
+
+#define sigismember(set,sig)                    \
+        (__builtin_constant_p(sig) ?            \
+         __const_sigismember((set),(sig)) :     \
+         __gen_sigismember((set),(sig)))
+
+static __inline__ int sigfindinword(unsigned long word)
+{
+        __asm__("bsfl %1,%0" : "=r"(word) : "rm"(word) : "cc");
+        return word;
+}
+
+struct pt_regs;
+
+#define ptrace_signal_deliver(regs, cookie)             \
+        do {                                            \
+                if (current->ptrace & PT_DTRACE) {      \
+                        current->ptrace &= ~PT_DTRACE;  \
+                        (regs)->eflags &= ~TF_MASK;     \
+                }                                       \
+        } while (0)
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/signal_64.h b/include/asm-x86/signal_64.h
new file mode 100644
index 000000000000..4581f978b299
--- /dev/null
+++ b/include/asm-x86/signal_64.h
@@ -0,0 +1,181 @@
+#ifndef _ASMx8664_SIGNAL_H
+#define _ASMx8664_SIGNAL_H
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#include <linux/time.h>
+
+/* Avoid too many header ordering problems.  */
+struct siginfo;
+
+#ifdef __KERNEL__
+#include <linux/linkage.h>
+/* Most things should be clean enough to redefine this at will, if care
+   is taken to make libc match.  */
+
+#define _NSIG           64
+#define _NSIG_BPW       64
+#define _NSIG_WORDS     (_NSIG / _NSIG_BPW)
+
+typedef unsigned long old_sigset_t;             /* at least 32 bits */
+
+typedef struct {
+        unsigned long sig[_NSIG_WORDS];
+} sigset_t;
+
+
+#else
+/* Here we must cater to libcs that poke about in kernel headers.  */
+
+#define NSIG            32
+typedef unsigned long sigset_t;
+
+#endif /* __KERNEL__ */
+#endif
+
+#define SIGHUP           1
+#define SIGINT           2
+#define SIGQUIT          3
+#define SIGILL           4
+#define SIGTRAP          5
+#define SIGABRT          6
+#define SIGIOT           6
+#define SIGBUS           7
+#define SIGFPE           8
+#define SIGKILL          9
+#define SIGUSR1         10
+#define SIGSEGV         11
+#define SIGUSR2         12
+#define SIGPIPE         13
+#define SIGALRM         14
+#define SIGTERM         15
+#define SIGSTKFLT       16
+#define SIGCHLD         17
+#define SIGCONT         18
+#define SIGSTOP         19
+#define SIGTSTP         20
+#define SIGTTIN         21
+#define SIGTTOU         22
+#define SIGURG          23
+#define SIGXCPU         24
+#define SIGXFSZ         25
+#define SIGVTALRM       26
+#define SIGPROF         27
+#define SIGWINCH        28
+#define SIGIO           29
+#define SIGPOLL         SIGIO
+/*
+#define SIGLOST         29
+*/
+#define SIGPWR          30
+#define SIGSYS          31
+#define SIGUNUSED       31
+
+/* These should not be considered constants from userland.  */
+#define SIGRTMIN        32
+#define SIGRTMAX        _NSIG
+
+/*
+ * SA_FLAGS values:
+ *
+ * SA_ONSTACK indicates that a registered stack_t will be used.
+ * SA_RESTART flag to get restarting signals (which were the default long ago)
+ * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
+ * SA_RESETHAND clears the handler when the signal is delivered.
+ * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
+ * SA_NODEFER prevents the current signal from being masked in the handler.
+ *
+ * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
+ * Unix names RESETHAND and NODEFER respectively.
+ */
+#define SA_NOCLDSTOP    0x00000001
+#define SA_NOCLDWAIT    0x00000002
+#define SA_SIGINFO      0x00000004
+#define SA_ONSTACK      0x08000000
+#define SA_RESTART      0x10000000
+#define SA_NODEFER      0x40000000
+#define SA_RESETHAND    0x80000000
+
+#define SA_NOMASK       SA_NODEFER
+#define SA_ONESHOT      SA_RESETHAND
+
+#define SA_RESTORER     0x04000000
+
+/*
+ * sigaltstack controls
+ */
+#define SS_ONSTACK      1
+#define SS_DISABLE      2
+
+#define MINSIGSTKSZ     2048
+#define SIGSTKSZ        8192
+
+#include <asm-generic/signal.h>
+
+#ifndef __ASSEMBLY__
+
+struct sigaction {
+        __sighandler_t sa_handler;
+        unsigned long sa_flags;
+        __sigrestore_t sa_restorer;
+        sigset_t sa_mask;               /* mask last for extensibility */
+};
+
+struct k_sigaction {
+        struct sigaction sa;
+};
+
+typedef struct sigaltstack {
+        void __user *ss_sp;
+        int ss_flags;
+        size_t ss_size;
+} stack_t;
+
+#ifdef __KERNEL__
+#include <asm/sigcontext.h>
+
+#undef __HAVE_ARCH_SIG_BITOPS
+#if 0
+
+static inline void sigaddset(sigset_t *set, int _sig)
+{
+        __asm__("btsq %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static inline void sigdelset(sigset_t *set, int _sig)
+{
+        __asm__("btrq %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static inline int __const_sigismember(sigset_t *set, int _sig)
+{
+        unsigned long sig = _sig - 1;
+        return 1 & (set->sig[sig / _NSIG_BPW] >> (sig & ~(_NSIG_BPW-1)));
+}
+
+static inline int __gen_sigismember(sigset_t *set, int _sig)
+{
+        int ret;
+        __asm__("btq %2,%1\n\tsbbq %0,%0"
+                : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+        return ret;
+}
+
+#define sigismember(set,sig)                    \
+        (__builtin_constant_p(sig) ?            \
+         __const_sigismember((set),(sig)) :     \
+         __gen_sigismember((set),(sig)))
+
+static inline int sigfindinword(unsigned long word)
+{
+        __asm__("bsfq %1,%0" : "=r"(word) : "rm"(word) : "cc");
+        return word;
+}
+#endif
+#endif
+
+#define ptrace_signal_deliver(regs, cookie) do { } while (0)
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
new file mode 100644
index 000000000000..f2e8319a6b0b
--- /dev/null
+++ b/include/asm-x86/smp.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "smp_32.h"
+#else
+# include "smp_64.h"
+#endif
diff --git a/include/asm-x86/smp_32.h b/include/asm-x86/smp_32.h
new file mode 100644
index 000000000000..1f73bde165b1
--- /dev/null
+++ b/include/asm-x86/smp_32.h
@@ -0,0 +1,182 @@
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+/*
+ * We need the APIC definitions automatically as part of 'smp.h'
+ */
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#endif
+
+#if defined(CONFIG_X86_LOCAL_APIC) && !defined(__ASSEMBLY__)
+#include <asm/bitops.h>
+#include <asm/mpspec.h>
+#include <asm/apic.h>
+#ifdef CONFIG_X86_IO_APIC
+#include <asm/io_apic.h>
+#endif
+#endif
+
+#define BAD_APICID 0xFFu
+#ifdef CONFIG_SMP
+#ifndef __ASSEMBLY__
+
+/*
+ * Private routines/data
+ */
+ 
+extern void smp_alloc_memory(void);
+extern int pic_mode;
+extern int smp_num_siblings;
+extern cpumask_t cpu_sibling_map[];
+extern cpumask_t cpu_core_map[];
+
+extern void (*mtrr_hook) (void);
+extern void zap_low_mappings (void);
+extern void lock_ipi_call_lock(void);
+extern void unlock_ipi_call_lock(void);
+
+#define MAX_APICID 256
+extern u8 x86_cpu_to_apicid[];
+
+#define cpu_physical_id(cpu)    x86_cpu_to_apicid[cpu]
+
+extern void set_cpu_sibling_map(int cpu);
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern void cpu_exit_clear(void);
+extern void cpu_uninit(void);
+extern void remove_siblinginfo(int cpu);
+#endif
+
+struct smp_ops
+{
+        void (*smp_prepare_boot_cpu)(void);
+        void (*smp_prepare_cpus)(unsigned max_cpus);
+        int (*cpu_up)(unsigned cpu);
+        void (*smp_cpus_done)(unsigned max_cpus);
+
+        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);
+};
+
+extern struct smp_ops smp_ops;
+
+static inline void smp_prepare_boot_cpu(void)
+{
+        smp_ops.smp_prepare_boot_cpu();
+}
+static inline void smp_prepare_cpus(unsigned int max_cpus)
+{
+        smp_ops.smp_prepare_cpus(max_cpus);
+}
+static inline int __cpu_up(unsigned int cpu)
+{
+        return smp_ops.cpu_up(cpu);
+}
+static inline void smp_cpus_done(unsigned int max_cpus)
+{
+        smp_ops.smp_cpus_done(max_cpus);
+}
+
+static inline void smp_send_stop(void)
+{
+        smp_ops.smp_send_stop();
+}
+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)
+{
+        return smp_ops.smp_call_function_mask(mask, func, info, wait);
+}
+
+void native_smp_prepare_boot_cpu(void);
+void native_smp_prepare_cpus(unsigned int max_cpus);
+int native_cpu_up(unsigned int cpunum);
+void native_smp_cpus_done(unsigned int max_cpus);
+
+#ifndef CONFIG_PARAVIRT
+#define startup_ipi_hook(phys_apicid, start_eip, start_esp)             \
+do { } while (0)
+#endif
+
+/*
+ * This function is needed by all SMP systems. It must _always_ be valid
+ * from the initial startup. We map APIC_BASE very early in page_setup(),
+ * so this is correct in the x86 case.
+ */
+DECLARE_PER_CPU(int, cpu_number);
+#define raw_smp_processor_id() (x86_read_percpu(cpu_number))
+
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_callin_map;
+extern cpumask_t cpu_possible_map;
+
+/* We don't mark CPUs online until __cpu_up(), so we need another measure */
+static inline int num_booting_cpus(void)
+{
+        return cpus_weight(cpu_callout_map);
+}
+
+extern int safe_smp_processor_id(void);
+extern int __cpu_disable(void);
+extern void __cpu_die(unsigned int cpu);
+extern unsigned int num_processors;
+
+void __cpuinit smp_store_cpu_info(int id);
+
+#endif /* !__ASSEMBLY__ */
+
+#else /* CONFIG_SMP */
+
+#define safe_smp_processor_id()         0
+#define cpu_physical_id(cpu)            boot_cpu_physical_apicid
+
+#define NO_PROC_ID              0xFF            /* No processor magic marker */
+
+#endif /* CONFIG_SMP */
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+#ifdef APIC_DEFINITION
+extern int hard_smp_processor_id(void);
+#else
+#include <mach_apicdef.h>
+static inline int hard_smp_processor_id(void)
+{
+        /* we don't want to mark this access volatile - bad code generation */
+        return GET_APIC_ID(*(unsigned long *)(APIC_BASE+APIC_ID));
+}
+#endif /* APIC_DEFINITION */
+
+#else /* CONFIG_X86_LOCAL_APIC */
+
+#ifndef CONFIG_SMP
+#define hard_smp_processor_id()         0
+#endif
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+extern u8 apicid_2_node[];
+
+#ifdef CONFIG_X86_LOCAL_APIC
+static __inline int logical_smp_processor_id(void)
+{
+        /* we don't want to mark this access volatile - bad code generation */
+        return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR));
+}
+#endif
+#endif
+
+#endif
diff --git a/include/asm-x86/smp_64.h b/include/asm-x86/smp_64.h
new file mode 100644
index 000000000000..3f303d2365ed
--- /dev/null
+++ b/include/asm-x86/smp_64.h
@@ -0,0 +1,117 @@
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+/*
+ * We need the APIC definitions automatically as part of 'smp.h'
+ */
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/bitops.h>
+#include <linux/init.h>
+extern int disable_apic;
+
+#include <asm/mpspec.h>
+#include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/thread_info.h>
+
+#ifdef CONFIG_SMP
+
+#include <asm/pda.h>
+
+struct pt_regs;
+
+extern cpumask_t cpu_present_mask;
+extern cpumask_t cpu_possible_map;
+extern cpumask_t cpu_online_map;
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_initialized;
+
+/*
+ * Private routines/data
+ */
+ 
+extern void smp_alloc_memory(void);
+extern volatile unsigned long smp_invalidate_needed;
+extern void lock_ipi_call_lock(void);
+extern void unlock_ipi_call_lock(void);
+extern int smp_num_siblings;
+extern void smp_send_reschedule(int cpu);
+
+extern cpumask_t cpu_sibling_map[NR_CPUS];
+extern cpumask_t cpu_core_map[NR_CPUS];
+extern u8 cpu_llc_id[NR_CPUS];
+
+#define SMP_TRAMPOLINE_BASE 0x6000
+
+/*
+ * On x86 all CPUs are mapped 1:1 to the APIC space.
+ * This simplifies scheduling and IPI sending and
+ * compresses data structures.
+ */
+
+static inline int num_booting_cpus(void)
+{
+        return cpus_weight(cpu_callout_map);
+}
+
+#define raw_smp_processor_id() read_pda(cpunumber)
+
+extern int __cpu_disable(void);
+extern void __cpu_die(unsigned int cpu);
+extern void prefill_possible_map(void);
+extern unsigned num_processors;
+extern unsigned __cpuinitdata disabled_cpus;
+
+#define NO_PROC_ID              0xFF            /* No processor magic marker */
+
+#endif /* CONFIG_SMP */
+
+static inline int hard_smp_processor_id(void)
+{
+        /* we don't want to mark this access volatile - bad code generation */
+        return GET_APIC_ID(*(unsigned int *)(APIC_BASE+APIC_ID));
+}
+
+/*
+ * Some lowlevel functions might want to know about
+ * the real APIC ID <-> CPU # mapping.
+ */
+extern u8 x86_cpu_to_apicid[NR_CPUS];   /* physical ID */
+extern u8 x86_cpu_to_log_apicid[NR_CPUS];
+extern u8 bios_cpu_apicid[];
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+        if (mps_cpu < NR_CPUS)
+                return (int)bios_cpu_apicid[mps_cpu];
+        else
+                return BAD_APICID;
+}
+
+#ifndef CONFIG_SMP
+#define stack_smp_processor_id() 0
+#define cpu_logical_map(x) (x)
+#else
+#include <asm/thread_info.h>
+#define stack_smp_processor_id() \
+({                                                              \
+        struct thread_info *ti;                                 \
+        __asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK));      \
+        ti->cpu;                                                \
+})
+#endif
+
+static __inline int logical_smp_processor_id(void)
+{
+        /* we don't want to mark this access volatile - bad code generation */
+        return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR));
+}
+
+#ifdef CONFIG_SMP
+#define cpu_physical_id(cpu)            x86_cpu_to_apicid[cpu]
+#else
+#define cpu_physical_id(cpu)            boot_cpu_id
+#endif /* !CONFIG_SMP */
+#endif
+
diff --git a/include/asm-x86/socket.h b/include/asm-x86/socket.h
new file mode 100644
index 000000000000..99ca648b94c5
--- /dev/null
+++ b/include/asm-x86/socket.h
@@ -0,0 +1,55 @@
+#ifndef _ASM_SOCKET_H
+#define _ASM_SOCKET_H
+
+#include <asm/sockios.h>
+
+/* For setsockopt(2) */
+#define SOL_SOCKET      1
+
+#define SO_DEBUG        1
+#define SO_REUSEADDR    2
+#define SO_TYPE         3
+#define SO_ERROR        4
+#define SO_DONTROUTE    5
+#define SO_BROADCAST    6
+#define SO_SNDBUF       7
+#define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
+#define SO_KEEPALIVE    9
+#define SO_OOBINLINE    10
+#define SO_NO_CHECK     11
+#define SO_PRIORITY     12
+#define SO_LINGER       13
+#define SO_BSDCOMPAT    14
+/* To add :#define SO_REUSEPORT 15 */
+#define SO_PASSCRED     16
+#define SO_PEERCRED     17
+#define SO_RCVLOWAT     18
+#define SO_SNDLOWAT     19
+#define SO_RCVTIMEO     20
+#define SO_SNDTIMEO     21
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION              22
+#define SO_SECURITY_ENCRYPTION_TRANSPORT        23
+#define SO_SECURITY_ENCRYPTION_NETWORK          24
+
+#define SO_BINDTODEVICE 25
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER        26
+#define SO_DETACH_FILTER        27
+
+#define SO_PEERNAME             28
+#define SO_TIMESTAMP            29
+#define SCM_TIMESTAMP           SO_TIMESTAMP
+
+#define SO_ACCEPTCONN           30
+
+#define SO_PEERSEC              31
+#define SO_PASSSEC              34
+#define SO_TIMESTAMPNS          35
+#define SCM_TIMESTAMPNS         SO_TIMESTAMPNS
+
+#endif /* _ASM_SOCKET_H */
diff --git a/include/asm-x86/sockios.h b/include/asm-x86/sockios.h
new file mode 100644
index 000000000000..5a134fc70b9c
--- /dev/null
+++ b/include/asm-x86/sockios.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "sockios_32.h"
+# else
+#  include "sockios_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "sockios_32.h"
+# else
+#  include "sockios_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/sockios_32.h b/include/asm-x86/sockios_32.h
new file mode 100644
index 000000000000..ff528c7d255c
--- /dev/null
+++ b/include/asm-x86/sockios_32.h
@@ -0,0 +1,13 @@
+#ifndef __ARCH_I386_SOCKIOS__
+#define __ARCH_I386_SOCKIOS__
+
+/* Socket-level I/O control calls. */
+#define FIOSETOWN       0x8901
+#define SIOCSPGRP       0x8902
+#define FIOGETOWN       0x8903
+#define SIOCGPGRP       0x8904
+#define SIOCATMARK      0x8905
+#define SIOCGSTAMP      0x8906          /* Get stamp (timeval) */
+#define SIOCGSTAMPNS    0x8907          /* Get stamp (timespec) */
+
+#endif
diff --git a/include/asm-x86/sockios_64.h b/include/asm-x86/sockios_64.h
new file mode 100644
index 000000000000..d726ba2513e3
--- /dev/null
+++ b/include/asm-x86/sockios_64.h
@@ -0,0 +1,13 @@
+#ifndef __ARCH_X8664_SOCKIOS__
+#define __ARCH_X8664_SOCKIOS__
+
+/* Socket-level I/O control calls. */
+#define FIOSETOWN       0x8901
+#define SIOCSPGRP       0x8902
+#define FIOGETOWN       0x8903
+#define SIOCGPGRP       0x8904
+#define SIOCATMARK      0x8905
+#define SIOCGSTAMP      0x8906          /* Get stamp (timeval) */
+#define SIOCGSTAMPNS    0x8907          /* Get stamp (timespec) */
+
+#endif
diff --git a/include/asm-x86/sparsemem.h b/include/asm-x86/sparsemem.h
new file mode 100644
index 000000000000..3f203b1d9ee8
--- /dev/null
+++ b/include/asm-x86/sparsemem.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "sparsemem_32.h"
+#else
+# include "sparsemem_64.h"
+#endif
diff --git a/include/asm-x86/sparsemem_32.h b/include/asm-x86/sparsemem_32.h
new file mode 100644
index 000000000000..cfeed990585f
--- /dev/null
+++ b/include/asm-x86/sparsemem_32.h
@@ -0,0 +1,31 @@
+#ifndef _I386_SPARSEMEM_H
+#define _I386_SPARSEMEM_H
+#ifdef CONFIG_SPARSEMEM
+
+/*
+ * generic non-linear memory support:
+ *
+ * 1) we will not split memory into more chunks than will fit into the
+ *    flags field of the struct page
+ */
+
+/*
+ * SECTION_SIZE_BITS            2^N: how big each section will be
+ * MAX_PHYSADDR_BITS            2^N: how much physical address space we have
+ * MAX_PHYSMEM_BITS             2^N: how much memory we can have in that space
+ */
+#ifdef CONFIG_X86_PAE
+#define SECTION_SIZE_BITS       30
+#define MAX_PHYSADDR_BITS       36
+#define MAX_PHYSMEM_BITS        36
+#else
+#define SECTION_SIZE_BITS       26
+#define MAX_PHYSADDR_BITS       32
+#define MAX_PHYSMEM_BITS        32
+#endif
+
+/* XXX: FIXME -- wli */
+#define kern_addr_valid(kaddr)  (0)
+
+#endif /* CONFIG_SPARSEMEM */
+#endif /* _I386_SPARSEMEM_H */
diff --git a/include/asm-x86/sparsemem_64.h b/include/asm-x86/sparsemem_64.h
new file mode 100644
index 000000000000..dabb16714a71
--- /dev/null
+++ b/include/asm-x86/sparsemem_64.h
@@ -0,0 +1,26 @@
+#ifndef _ASM_X86_64_SPARSEMEM_H
+#define _ASM_X86_64_SPARSEMEM_H 1
+
+#ifdef CONFIG_SPARSEMEM
+
+/*
+ * generic non-linear memory support:
+ *
+ * 1) we will not split memory into more chunks than will fit into the flags
+ *    field of the struct page
+ *
+ * SECTION_SIZE_BITS            2^n: size of each section
+ * MAX_PHYSADDR_BITS            2^n: max size of physical address space
+ * MAX_PHYSMEM_BITS             2^n: how much memory we can have in that space
+ *
+ */
+
+#define SECTION_SIZE_BITS       27 /* matt - 128 is convenient right now */
+#define MAX_PHYSADDR_BITS       40
+#define MAX_PHYSMEM_BITS        40
+
+extern int early_pfn_to_nid(unsigned long pfn);
+
+#endif /* CONFIG_SPARSEMEM */
+
+#endif /* _ASM_X86_64_SPARSEMEM_H */
diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h
new file mode 100644
index 000000000000..d74d85e71dcb
--- /dev/null
+++ b/include/asm-x86/spinlock.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "spinlock_32.h"
+#else
+# include "spinlock_64.h"
+#endif
diff --git a/include/asm-x86/spinlock_32.h b/include/asm-x86/spinlock_32.h
new file mode 100644
index 000000000000..d3bcebed60ca
--- /dev/null
+++ b/include/asm-x86/spinlock_32.h
@@ -0,0 +1,221 @@
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/atomic.h>
+#include <asm/rwlock.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <linux/compiler.h>
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define CLI_STRING      "cli"
+#define STI_STRING      "sti"
+#define CLI_STI_CLOBBERS
+#define CLI_STI_INPUT_ARGS
+#endif /* CONFIG_PARAVIRT */
+
+/*
+ * Your basic SMP spinlocks, allowing only a single CPU anywhere
+ *
+ * Simple spin lock operations.  There are two variants, one clears IRQ's
+ * on the local processor, one does not.
+ *
+ * We make no fairness assumptions. They have a cost.
+ *
+ * (the type definitions are in asm/spinlock_types.h)
+ */
+
+static inline int __raw_spin_is_locked(raw_spinlock_t *x)
+{
+        return *(volatile signed char *)(&(x)->slock) <= 0;
+}
+
+static inline void __raw_spin_lock(raw_spinlock_t *lock)
+{
+        asm volatile("\n1:\t"
+                     LOCK_PREFIX " ; decb %0\n\t"
+                     "jns 3f\n"
+                     "2:\t"
+                     "rep;nop\n\t"
+                     "cmpb $0,%0\n\t"
+                     "jle 2b\n\t"
+                     "jmp 1b\n"
+                     "3:\n\t"
+                     : "+m" (lock->slock) : : "memory");
+}
+
+/*
+ * It is easier for the lock validator if interrupts are not re-enabled
+ * in the middle of a lock-acquire. This is a performance feature anyway
+ * so we turn it off:
+ *
+ * NOTE: there's an irqs-on section here, which normally would have to be
+ * irq-traced, but on CONFIG_TRACE_IRQFLAGS we never use this variant.
+ */
+#ifndef CONFIG_PROVE_LOCKING
+static inline void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
+{
+        asm volatile(
+                "\n1:\t"
+                LOCK_PREFIX " ; decb %[slock]\n\t"
+                "jns 5f\n"
+                "2:\t"
+                "testl $0x200, %[flags]\n\t"
+                "jz 4f\n\t"
+                STI_STRING "\n"
+                "3:\t"
+                "rep;nop\n\t"
+                "cmpb $0, %[slock]\n\t"
+                "jle 3b\n\t"
+                CLI_STRING "\n\t"
+                "jmp 1b\n"
+                "4:\t"
+                "rep;nop\n\t"
+                "cmpb $0, %[slock]\n\t"
+                "jg 1b\n\t"
+                "jmp 4b\n"
+                "5:\n\t"
+                : [slock] "+m" (lock->slock)
+                : [flags] "r" (flags)
+                  CLI_STI_INPUT_ARGS
+                : "memory" CLI_STI_CLOBBERS);
+}
+#endif
+
+static inline int __raw_spin_trylock(raw_spinlock_t *lock)
+{
+        char oldval;
+        asm volatile(
+                "xchgb %b0,%1"
+                :"=q" (oldval), "+m" (lock->slock)
+                :"0" (0) : "memory");
+        return oldval > 0;
+}
+
+/*
+ * __raw_spin_unlock based on writing $1 to the low byte.
+ * This method works. Despite all the confusion.
+ * (except on PPro SMP or if we are using OOSTORE, so we use xchgb there)
+ * (PPro errata 66, 92)
+ */
+
+#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+
+static inline void __raw_spin_unlock(raw_spinlock_t *lock)
+{
+        asm volatile("movb $1,%0" : "+m" (lock->slock) :: "memory");
+}
+
+#else
+
+static inline void __raw_spin_unlock(raw_spinlock_t *lock)
+{
+        char oldval = 1;
+
+        asm volatile("xchgb %b0, %1"
+                     : "=q" (oldval), "+m" (lock->slock)
+                     : "0" (oldval) : "memory");
+}
+
+#endif
+
+static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+{
+        while (__raw_spin_is_locked(lock))
+                cpu_relax();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers
+ * but only one writer.
+ *
+ * NOTE! it is quite common to have readers in interrupts
+ * but no interrupt writers. For those circumstances we
+ * can "mix" irq-safe locks - any writer needs to get a
+ * irq-safe write-lock, but readers can get non-irqsafe
+ * read-locks.
+ *
+ * On x86, we implement read-write locks as a 32-bit counter
+ * with the high bit (sign) being the "contended" bit.
+ *
+ * The inline assembly is non-obvious. Think about it.
+ *
+ * Changed to use the same technique as rw semaphores.  See
+ * semaphore.h for details.  -ben
+ *
+ * the helpers are in arch/i386/kernel/semaphore.c
+ */
+
+/**
+ * read_can_lock - would read_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+static inline int __raw_read_can_lock(raw_rwlock_t *x)
+{
+        return (int)(x)->lock > 0;
+}
+
+/**
+ * write_can_lock - would write_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+static inline int __raw_write_can_lock(raw_rwlock_t *x)
+{
+        return (x)->lock == RW_LOCK_BIAS;
+}
+
+static inline void __raw_read_lock(raw_rwlock_t *rw)
+{
+        asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t"
+                     "jns 1f\n"
+                     "call __read_lock_failed\n\t"
+                     "1:\n"
+                     ::"a" (rw) : "memory");
+}
+
+static inline void __raw_write_lock(raw_rwlock_t *rw)
+{
+        asm volatile(LOCK_PREFIX " subl $" RW_LOCK_BIAS_STR ",(%0)\n\t"
+                     "jz 1f\n"
+                     "call __write_lock_failed\n\t"
+                     "1:\n"
+                     ::"a" (rw) : "memory");
+}
+
+static inline int __raw_read_trylock(raw_rwlock_t *lock)
+{
+        atomic_t *count = (atomic_t *)lock;
+        atomic_dec(count);
+        if (atomic_read(count) >= 0)
+                return 1;
+        atomic_inc(count);
+        return 0;
+}
+
+static inline int __raw_write_trylock(raw_rwlock_t *lock)
+{
+        atomic_t *count = (atomic_t *)lock;
+        if (atomic_sub_and_test(RW_LOCK_BIAS, count))
+                return 1;
+        atomic_add(RW_LOCK_BIAS, count);
+        return 0;
+}
+
+static inline void __raw_read_unlock(raw_rwlock_t *rw)
+{
+        asm volatile(LOCK_PREFIX "incl %0" :"+m" (rw->lock) : : "memory");
+}
+
+static inline void __raw_write_unlock(raw_rwlock_t *rw)
+{
+        asm volatile(LOCK_PREFIX "addl $" RW_LOCK_BIAS_STR ", %0"
+                                 : "+m" (rw->lock) : : "memory");
+}
+
+#define _raw_spin_relax(lock)   cpu_relax()
+#define _raw_read_relax(lock)   cpu_relax()
+#define _raw_write_relax(lock)  cpu_relax()
+
+#endif /* __ASM_SPINLOCK_H */
diff --git a/include/asm-x86/spinlock_64.h b/include/asm-x86/spinlock_64.h
new file mode 100644
index 000000000000..88bf981e73cf
--- /dev/null
+++ b/include/asm-x86/spinlock_64.h
@@ -0,0 +1,167 @@
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/atomic.h>
+#include <asm/rwlock.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+
+/*
+ * Your basic SMP spinlocks, allowing only a single CPU anywhere
+ *
+ * Simple spin lock operations.  There are two variants, one clears IRQ's
+ * on the local processor, one does not.
+ *
+ * We make no fairness assumptions. They have a cost.
+ *
+ * (the type definitions are in asm/spinlock_types.h)
+ */
+
+static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+{
+        return *(volatile signed int *)(&(lock)->slock) <= 0;
+}
+
+static inline void __raw_spin_lock(raw_spinlock_t *lock)
+{
+        asm volatile(
+                "\n1:\t"
+                LOCK_PREFIX " ; decl %0\n\t"
+                "jns 2f\n"
+                "3:\n"
+                "rep;nop\n\t"
+                "cmpl $0,%0\n\t"
+                "jle 3b\n\t"
+                "jmp 1b\n"
+                "2:\t" : "=m" (lock->slock) : : "memory");
+}
+
+/*
+ * Same as __raw_spin_lock, but reenable interrupts during spinning.
+ */
+#ifndef CONFIG_PROVE_LOCKING
+static inline void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
+{
+        asm volatile(
+                "\n1:\t"
+                LOCK_PREFIX " ; decl %0\n\t"
+                "jns 5f\n"
+                "testl $0x200, %1\n\t"  /* interrupts were disabled? */
+                "jz 4f\n\t"
+                "sti\n"
+                "3:\t"
+                "rep;nop\n\t"
+                "cmpl $0, %0\n\t"
+                "jle 3b\n\t"
+                "cli\n\t"
+                "jmp 1b\n"
+                "4:\t"
+                "rep;nop\n\t"
+                "cmpl $0, %0\n\t"
+                "jg 1b\n\t"
+                "jmp 4b\n"
+                "5:\n\t"
+                : "+m" (lock->slock) : "r" ((unsigned)flags) : "memory");
+}
+#endif
+
+static inline int __raw_spin_trylock(raw_spinlock_t *lock)
+{
+        int oldval;
+
+        asm volatile(
+                "xchgl %0,%1"
+                :"=q" (oldval), "=m" (lock->slock)
+                :"0" (0) : "memory");
+
+        return oldval > 0;
+}
+
+static inline void __raw_spin_unlock(raw_spinlock_t *lock)
+{
+        asm volatile("movl $1,%0" :"=m" (lock->slock) :: "memory");
+}
+
+static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+{
+        while (__raw_spin_is_locked(lock))
+                cpu_relax();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers
+ * but only one writer.
+ *
+ * NOTE! it is quite common to have readers in interrupts
+ * but no interrupt writers. For those circumstances we
+ * can "mix" irq-safe locks - any writer needs to get a
+ * irq-safe write-lock, but readers can get non-irqsafe
+ * read-locks.
+ *
+ * On x86, we implement read-write locks as a 32-bit counter
+ * with the high bit (sign) being the "contended" bit.
+ */
+
+static inline int __raw_read_can_lock(raw_rwlock_t *lock)
+{
+        return (int)(lock)->lock > 0;
+}
+
+static inline int __raw_write_can_lock(raw_rwlock_t *lock)
+{
+        return (lock)->lock == RW_LOCK_BIAS;
+}
+
+static inline void __raw_read_lock(raw_rwlock_t *rw)
+{
+        asm volatile(LOCK_PREFIX "subl $1,(%0)\n\t"
+                     "jns 1f\n"
+                     "call __read_lock_failed\n"
+                     "1:\n"
+                     ::"D" (rw), "i" (RW_LOCK_BIAS) : "memory");
+}
+
+static inline void __raw_write_lock(raw_rwlock_t *rw)
+{
+        asm volatile(LOCK_PREFIX "subl %1,(%0)\n\t"
+                     "jz 1f\n"
+                     "\tcall __write_lock_failed\n\t"
+                     "1:\n"
+                     ::"D" (rw), "i" (RW_LOCK_BIAS) : "memory");
+}
+
+static inline int __raw_read_trylock(raw_rwlock_t *lock)
+{
+        atomic_t *count = (atomic_t *)lock;
+        atomic_dec(count);
+        if (atomic_read(count) >= 0)
+                return 1;
+        atomic_inc(count);
+        return 0;
+}
+
+static inline int __raw_write_trylock(raw_rwlock_t *lock)
+{
+        atomic_t *count = (atomic_t *)lock;
+        if (atomic_sub_and_test(RW_LOCK_BIAS, count))
+                return 1;
+        atomic_add(RW_LOCK_BIAS, count);
+        return 0;
+}
+
+static inline void __raw_read_unlock(raw_rwlock_t *rw)
+{
+        asm volatile(LOCK_PREFIX " ; incl %0" :"=m" (rw->lock) : : "memory");
+}
+
+static inline void __raw_write_unlock(raw_rwlock_t *rw)
+{
+        asm volatile(LOCK_PREFIX " ; addl $" RW_LOCK_BIAS_STR ",%0"
+                                : "=m" (rw->lock) : : "memory");
+}
+
+#define _raw_spin_relax(lock)   cpu_relax()
+#define _raw_read_relax(lock)   cpu_relax()
+#define _raw_write_relax(lock)  cpu_relax()
+
+#endif /* __ASM_SPINLOCK_H */
diff --git a/include/asm-x86/spinlock_types.h b/include/asm-x86/spinlock_types.h
new file mode 100644
index 000000000000..4da9345c1500
--- /dev/null
+++ b/include/asm-x86/spinlock_types.h
@@ -0,0 +1,20 @@
+#ifndef __ASM_SPINLOCK_TYPES_H
+#define __ASM_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+        unsigned int slock;
+} raw_spinlock_t;
+
+#define __RAW_SPIN_LOCK_UNLOCKED        { 1 }
+
+typedef struct {
+        unsigned int lock;
+} raw_rwlock_t;
+
+#define __RAW_RW_LOCK_UNLOCKED          { RW_LOCK_BIAS }
+
+#endif
diff --git a/include/asm-x86/srat.h b/include/asm-x86/srat.h
new file mode 100644
index 000000000000..165ab4bdc02b
--- /dev/null
+++ b/include/asm-x86/srat.h
@@ -0,0 +1,37 @@
+/*
+ * Some of the code in this file has been gleaned from the 64 bit 
+ * discontigmem support code base.
+ *
+ * Copyright (C) 2002, IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to Pat Gaughen <gone@us.ibm.com>
+ */
+
+#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
+
+extern int get_memcfg_from_srat(void);
+extern unsigned long *get_zholes_size(int);
+
+#endif /* _ASM_SRAT_H_ */
diff --git a/include/asm-x86/stacktrace.h b/include/asm-x86/stacktrace.h
new file mode 100644
index 000000000000..6f0b54594307
--- /dev/null
+++ b/include/asm-x86/stacktrace.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_STACKTRACE_H
+#define _ASM_STACKTRACE_H 1
+
+extern int kstack_depth_to_print;
+
+/* Generic stack tracer with callbacks */
+
+struct stacktrace_ops {
+        void (*warning)(void *data, char *msg);
+        /* msg must contain %s for the symbol */
+        void (*warning_symbol)(void *data, char *msg, unsigned long symbol);
+        void (*address)(void *data, unsigned long address);
+        /* On negative return stop dumping */
+        int (*stack)(void *data, char *name);
+};
+
+void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack,
+                struct stacktrace_ops *ops, void *data);
+
+#endif
diff --git a/include/asm-x86/stat.h b/include/asm-x86/stat.h
new file mode 100644
index 000000000000..3ff6b50ef833
--- /dev/null
+++ b/include/asm-x86/stat.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "stat_32.h"
+# else
+#  include "stat_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "stat_32.h"
+# else
+#  include "stat_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/stat_32.h b/include/asm-x86/stat_32.h
new file mode 100644
index 000000000000..67eae78323ba
--- /dev/null
+++ b/include/asm-x86/stat_32.h
@@ -0,0 +1,77 @@
+#ifndef _I386_STAT_H
+#define _I386_STAT_H
+
+struct __old_kernel_stat {
+        unsigned short st_dev;
+        unsigned short st_ino;
+        unsigned short st_mode;
+        unsigned short st_nlink;
+        unsigned short st_uid;
+        unsigned short st_gid;
+        unsigned short st_rdev;
+        unsigned long  st_size;
+        unsigned long  st_atime;
+        unsigned long  st_mtime;
+        unsigned long  st_ctime;
+};
+
+struct stat {
+        unsigned long  st_dev;
+        unsigned long  st_ino;
+        unsigned short st_mode;
+        unsigned short st_nlink;
+        unsigned short st_uid;
+        unsigned short st_gid;
+        unsigned long  st_rdev;
+        unsigned long  st_size;
+        unsigned long  st_blksize;
+        unsigned long  st_blocks;
+        unsigned long  st_atime;
+        unsigned long  st_atime_nsec;
+        unsigned long  st_mtime;
+        unsigned long  st_mtime_nsec;
+        unsigned long  st_ctime;
+        unsigned long  st_ctime_nsec;
+        unsigned long  __unused4;
+        unsigned long  __unused5;
+};
+
+/* This matches struct stat64 in glibc2.1, hence the absolutely
+ * insane amounts of padding around dev_t's.
+ */
+struct stat64 {
+        unsigned long long      st_dev;
+        unsigned char   __pad0[4];
+
+#define STAT64_HAS_BROKEN_ST_INO        1
+        unsigned long   __st_ino;
+
+        unsigned int    st_mode;
+        unsigned int    st_nlink;
+
+        unsigned long   st_uid;
+        unsigned long   st_gid;
+
+        unsigned long long      st_rdev;
+        unsigned char   __pad3[4];
+
+        long long       st_size;
+        unsigned long   st_blksize;
+
+        unsigned long long      st_blocks;      /* Number 512-byte blocks allocated. */
+
+        unsigned long   st_atime;
+        unsigned long   st_atime_nsec;
+
+        unsigned long   st_mtime;
+        unsigned int    st_mtime_nsec;
+
+        unsigned long   st_ctime;
+        unsigned long   st_ctime_nsec;
+
+        unsigned long long      st_ino;
+};
+
+#define STAT_HAVE_NSEC 1
+
+#endif
diff --git a/include/asm-x86/stat_64.h b/include/asm-x86/stat_64.h
new file mode 100644
index 000000000000..fd9f00d560f8
--- /dev/null
+++ b/include/asm-x86/stat_64.h
@@ -0,0 +1,44 @@
+#ifndef _ASM_X86_64_STAT_H
+#define _ASM_X86_64_STAT_H
+
+#define STAT_HAVE_NSEC 1
+
+struct stat {
+        unsigned long   st_dev;
+        unsigned long   st_ino;
+        unsigned long   st_nlink;
+
+        unsigned int    st_mode;
+        unsigned int    st_uid;
+        unsigned int    st_gid;
+        unsigned int    __pad0;
+        unsigned long   st_rdev;
+        long            st_size;
+        long            st_blksize;
+        long            st_blocks;      /* Number 512-byte blocks allocated. */
+
+        unsigned long   st_atime;
+        unsigned long   st_atime_nsec; 
+        unsigned long   st_mtime;
+        unsigned long   st_mtime_nsec;
+        unsigned long   st_ctime;
+        unsigned long   st_ctime_nsec;
+        long            __unused[3];
+};
+
+/* For 32bit emulation */
+struct __old_kernel_stat {
+        unsigned short st_dev;
+        unsigned short st_ino;
+        unsigned short st_mode;
+        unsigned short st_nlink;
+        unsigned short st_uid;
+        unsigned short st_gid;
+        unsigned short st_rdev;
+        unsigned int  st_size;
+        unsigned int  st_atime;
+        unsigned int  st_mtime;
+        unsigned int  st_ctime;
+};
+
+#endif
diff --git a/include/asm-x86/statfs.h b/include/asm-x86/statfs.h
new file mode 100644
index 000000000000..327fb5d7a148
--- /dev/null
+++ b/include/asm-x86/statfs.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "statfs_32.h"
+# else
+#  include "statfs_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "statfs_32.h"
+# else
+#  include "statfs_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/statfs_32.h b/include/asm-x86/statfs_32.h
new file mode 100644
index 000000000000..24972c175132
--- /dev/null
+++ b/include/asm-x86/statfs_32.h
@@ -0,0 +1,6 @@
+#ifndef _I386_STATFS_H
+#define _I386_STATFS_H
+
+#include <asm-generic/statfs.h>
+
+#endif
diff --git a/include/asm-x86/statfs_64.h b/include/asm-x86/statfs_64.h
new file mode 100644
index 000000000000..b3f4718af30b
--- /dev/null
+++ b/include/asm-x86/statfs_64.h
@@ -0,0 +1,58 @@
+#ifndef _X86_64_STATFS_H
+#define _X86_64_STATFS_H
+
+#ifndef __KERNEL_STRICT_NAMES
+
+#include <linux/types.h>
+
+typedef __kernel_fsid_t fsid_t;
+
+#endif
+
+/*
+ * This is ugly -- we're already 64-bit clean, so just duplicate the 
+ * definitions.
+ */
+struct statfs {
+        long f_type;
+        long f_bsize;
+        long f_blocks;
+        long f_bfree;
+        long f_bavail;
+        long f_files;
+        long f_ffree;
+        __kernel_fsid_t f_fsid;
+        long f_namelen;
+        long f_frsize;
+        long f_spare[5];
+};
+
+struct statfs64 {
+        long f_type;
+        long f_bsize;
+        long f_blocks;
+        long f_bfree;
+        long f_bavail;
+        long f_files;
+        long f_ffree;
+        __kernel_fsid_t f_fsid;
+        long f_namelen;
+        long f_frsize;
+        long f_spare[5];
+};
+
+struct compat_statfs64 {
+        __u32 f_type;
+        __u32 f_bsize;
+        __u64 f_blocks;
+        __u64 f_bfree;
+        __u64 f_bavail;
+        __u64 f_files;
+        __u64 f_ffree;
+        __kernel_fsid_t f_fsid;
+        __u32 f_namelen;
+        __u32 f_frsize;
+        __u32 f_spare[5];
+} __attribute__((packed));
+
+#endif
diff --git a/include/asm-x86/string.h b/include/asm-x86/string.h
new file mode 100644
index 000000000000..6dfd6d9373a0
--- /dev/null
+++ b/include/asm-x86/string.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "string_32.h"
+#else
+# include "string_64.h"
+#endif
diff --git a/include/asm-x86/string_32.h b/include/asm-x86/string_32.h
new file mode 100644
index 000000000000..a9b64453bdf5
--- /dev/null
+++ b/include/asm-x86/string_32.h
@@ -0,0 +1,276 @@
+#ifndef _I386_STRING_H_
+#define _I386_STRING_H_
+
+#ifdef __KERNEL__
+
+/* Let gcc decide wether to inline or use the out of line functions */
+
+#define __HAVE_ARCH_STRCPY
+extern char *strcpy(char *dest, const char *src);
+
+#define __HAVE_ARCH_STRNCPY
+extern char *strncpy(char *dest, const char *src, size_t count);
+
+#define __HAVE_ARCH_STRCAT
+extern char *strcat(char *dest, const char *src);
+
+#define __HAVE_ARCH_STRNCAT
+extern char *strncat(char *dest, const char *src, size_t count);
+
+#define __HAVE_ARCH_STRCMP
+extern int strcmp(const char *cs, const char *ct);
+
+#define __HAVE_ARCH_STRNCMP
+extern int strncmp(const char *cs, const char *ct, size_t count);
+
+#define __HAVE_ARCH_STRCHR
+extern char *strchr(const char *s, int c);
+
+#define __HAVE_ARCH_STRRCHR
+extern char *strrchr(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)
+{
+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)
+{
+        long esi, edi;
+        if (!n) return to;
+#if 1   /* want to do small copies with non-string ops? */
+        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
+        }
+#endif
+        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"
+                );
+        } 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");
+        }
+        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;
+        }
+}
+
+#define __HAVE_ARCH_MEMCPY
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+/*
+ *      This CPU favours 3DNow strongly (eg AMD Athlon)
+ */
+
+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)
+{
+        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)))
+
+#else
+
+/*
+ *      No 3D Now!
+ */
+ 
+#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);
+
+#define memcmp __builtin_memcmp
+
+#define __HAVE_ARCH_MEMCHR
+extern void *memchr(const void * cs,int 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;
+}
+
+/* we might want to write optimized versions of these later */
+#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
+ * 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)
+{
+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);
+/* end of additional stuff */
+
+#define __HAVE_ARCH_STRSTR
+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)
+{
+        switch (count) {
+                case 0:
+                        return s;
+                case 1:
+                        *(unsigned char *)s = pattern;
+                        return s;
+                case 2:
+                        *(unsigned short *)s = pattern;
+                        return s;
+                case 3:
+                        *(unsigned short *)s = pattern;
+                        *(2+(unsigned char *)s) = pattern;
+                        return s;
+                case 4:
+                        *(unsigned long *)s = pattern;
+                        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 __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)))
+
+/*
+ * 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);
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/string_64.h b/include/asm-x86/string_64.h
new file mode 100644
index 000000000000..e583da7918fb
--- /dev/null
+++ b/include/asm-x86/string_64.h
@@ -0,0 +1,60 @@
+#ifndef _X86_64_STRING_H_
+#define _X86_64_STRING_H_
+
+#ifdef __KERNEL__
+
+/* Written 2002 by Andi Kleen */ 
+
+/* Only used for special circumstances. Stolen from i386/string.h */ 
+static __always_inline void *
+__inline_memcpy(void * to, const void * from, size_t n)
+{
+unsigned long d0, d1, d2;
+__asm__ __volatile__(
+        "rep ; movsl\n\t"
+        "testb $2,%b4\n\t"
+        "je 1f\n\t"
+        "movsw\n"
+        "1:\ttestb $1,%b4\n\t"
+        "je 2f\n\t"
+        "movsb\n"
+        "2:"
+        : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+        :"0" (n/4), "q" (n),"1" ((long) to),"2" ((long) from)
+        : "memory");
+return (to);
+}
+
+/* Even with __builtin_ the compiler may decide to use the out of line
+   function. */
+
+#define __HAVE_ARCH_MEMCPY 1
+#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
+extern void *memcpy(void *to, const void *from, size_t len);
+#else
+extern void *__memcpy(void *to, const void *from, size_t len); 
+#define memcpy(dst,src,len) \
+        ({ size_t __len = (len);                                \
+           void *__ret;                                         \
+           if (__builtin_constant_p(len) && __len >= 64)        \
+                 __ret = __memcpy((dst),(src),__len);           \
+           else                                                 \
+                 __ret = __builtin_memcpy((dst),(src),__len);   \
+           __ret; }) 
+#endif
+
+#define __HAVE_ARCH_MEMSET
+void *memset(void *s, int c, size_t n);
+
+#define __HAVE_ARCH_MEMMOVE
+void * memmove(void * dest,const void *src,size_t count);
+
+int memcmp(const void * cs,const void * ct,size_t count);
+size_t strlen(const char * s);
+char *strcpy(char * dest,const char *src);
+char *strcat(char * dest, const char * src);
+int strcmp(const char * cs,const char * ct);
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/suspend.h b/include/asm-x86/suspend.h
new file mode 100644
index 000000000000..9bd521fe4570
--- /dev/null
+++ b/include/asm-x86/suspend.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "suspend_32.h"
+#else
+# include "suspend_64.h"
+#endif
diff --git a/include/asm-x86/suspend_32.h b/include/asm-x86/suspend_32.h
new file mode 100644
index 000000000000..a2520732ffd6
--- /dev/null
+++ b/include/asm-x86/suspend_32.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright 2001-2002 Pavel Machek <pavel@suse.cz>
+ * Based on code
+ * Copyright 2001 Patrick Mochel <mochel@osdl.org>
+ */
+#include <asm/desc.h>
+#include <asm/i387.h>
+
+static inline int arch_prepare_suspend(void) { return 0; }
+
+/* image of the saved processor state */
+struct saved_context {
+        u16 es, fs, gs, ss;
+        unsigned long cr0, cr2, cr3, cr4;
+        struct Xgt_desc_struct gdt;
+        struct Xgt_desc_struct idt;
+        u16 ldt;
+        u16 tss;
+        unsigned long tr;
+        unsigned long safety;
+        unsigned long return_address;
+} __attribute__((packed));
+
+#ifdef CONFIG_ACPI
+extern unsigned long saved_eip;
+extern unsigned long saved_esp;
+extern unsigned long saved_ebp;
+extern unsigned long saved_ebx;
+extern unsigned long saved_esi;
+extern unsigned long saved_edi;
+
+static inline void acpi_save_register_state(unsigned long return_point)
+{
+        saved_eip = return_point;
+        asm volatile ("movl %%esp,%0" : "=m" (saved_esp));
+        asm volatile ("movl %%ebp,%0" : "=m" (saved_ebp));
+        asm volatile ("movl %%ebx,%0" : "=m" (saved_ebx));
+        asm volatile ("movl %%edi,%0" : "=m" (saved_edi));
+        asm volatile ("movl %%esi,%0" : "=m" (saved_esi));
+}
+
+#define acpi_restore_register_state()  do {} while (0)
+
+/* routines for saving/restoring kernel state */
+extern int acpi_save_state_mem(void);
+#endif
diff --git a/include/asm-x86/suspend_64.h b/include/asm-x86/suspend_64.h
new file mode 100644
index 000000000000..b897e8cb55fb
--- /dev/null
+++ b/include/asm-x86/suspend_64.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2001-2003 Pavel Machek <pavel@suse.cz>
+ * Based on code
+ * Copyright 2001 Patrick Mochel <mochel@osdl.org>
+ */
+#include <asm/desc.h>
+#include <asm/i387.h>
+
+static inline int
+arch_prepare_suspend(void)
+{
+        return 0;
+}
+
+/* Image of the saved processor state. If you touch this, fix acpi_wakeup.S. */
+struct saved_context {
+        u16 ds, es, fs, gs, ss;
+        unsigned long gs_base, gs_kernel_base, fs_base;
+        unsigned long cr0, cr2, cr3, cr4, cr8;
+        unsigned long efer;
+        u16 gdt_pad;
+        u16 gdt_limit;
+        unsigned long gdt_base;
+        u16 idt_pad;
+        u16 idt_limit;
+        unsigned long idt_base;
+        u16 ldt;
+        u16 tss;
+        unsigned long tr;
+        unsigned long safety;
+        unsigned long return_address;
+        unsigned long eflags;
+} __attribute__((packed));
+
+/* We'll access these from assembly, so we'd better have them outside struct */
+extern unsigned long saved_context_eax, saved_context_ebx, saved_context_ecx, saved_context_edx;
+extern unsigned long saved_context_esp, saved_context_ebp, saved_context_esi, saved_context_edi;
+extern unsigned long saved_context_r08, saved_context_r09, saved_context_r10, saved_context_r11;
+extern unsigned long saved_context_r12, saved_context_r13, saved_context_r14, saved_context_r15;
+extern unsigned long saved_context_eflags;
+
+#define loaddebug(thread,register) \
+        set_debugreg((thread)->debugreg##register, register)
+
+extern void fix_processor_context(void);
+
+extern unsigned long saved_rip;
+extern unsigned long saved_rsp;
+extern unsigned long saved_rbp;
+extern unsigned long saved_rbx;
+extern unsigned long saved_rsi;
+extern unsigned long saved_rdi;
+
+/* routines for saving/restoring kernel state */
+extern int acpi_save_state_mem(void);
diff --git a/include/asm-x86/swiotlb.h b/include/asm-x86/swiotlb.h
new file mode 100644
index 000000000000..f9c589539a82
--- /dev/null
+++ b/include/asm-x86/swiotlb.h
@@ -0,0 +1,56 @@
+#ifndef _ASM_SWIOTLB_H
+#define _ASM_SWIOTLB_H 1
+
+#include <asm/dma-mapping.h>
+
+/* SWIOTLB interface */
+
+extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr,
+                                     size_t size, int dir);
+extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+                       dma_addr_t *dma_handle, gfp_t flags);
+extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+                                  size_t size, int dir);
+extern void swiotlb_sync_single_for_cpu(struct device *hwdev,
+                                         dma_addr_t dev_addr,
+                                         size_t size, int dir);
+extern void swiotlb_sync_single_for_device(struct device *hwdev,
+                                            dma_addr_t dev_addr,
+                                            size_t size, int dir);
+extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev,
+                                              dma_addr_t dev_addr,
+                                              unsigned long offset,
+                                              size_t size, int dir);
+extern void swiotlb_sync_single_range_for_device(struct device *hwdev,
+                                                 dma_addr_t dev_addr,
+                                                 unsigned long offset,
+                                                 size_t size, int dir);
+extern void swiotlb_sync_sg_for_cpu(struct device *hwdev,
+                                     struct scatterlist *sg, int nelems,
+                                     int dir);
+extern void swiotlb_sync_sg_for_device(struct device *hwdev,
+                                        struct scatterlist *sg, int nelems,
+                                        int dir);
+extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg,
+                      int nents, int direction);
+extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
+                         int nents, int direction);
+extern int swiotlb_dma_mapping_error(dma_addr_t dma_addr);
+extern void swiotlb_free_coherent (struct device *hwdev, size_t size,
+                                   void *vaddr, dma_addr_t dma_handle);
+extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
+extern void swiotlb_init(void);
+
+extern int swiotlb_force;
+
+#ifdef CONFIG_SWIOTLB
+extern int swiotlb;
+#else
+#define swiotlb 0
+#endif
+
+extern void pci_swiotlb_init(void);
+
+static inline void dma_mark_clean(void *addr, size_t size) {}
+
+#endif /* _ASM_SWIOTLB_H */
diff --git a/include/asm-x86/sync_bitops.h b/include/asm-x86/sync_bitops.h
new file mode 100644
index 000000000000..cbce08a2d135
--- /dev/null
+++ b/include/asm-x86/sync_bitops.h
@@ -0,0 +1,156 @@
+#ifndef _I386_SYNC_BITOPS_H
+#define _I386_SYNC_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+/*
+ * These have to be done with inline assembly: that way the bit-setting
+ * is guaranteed to be atomic. All bit operations return 0 if the bit
+ * was cleared before the operation and != 0 if it was not.
+ *
+ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
+ */
+
+#define ADDR (*(volatile long *) addr)
+
+/**
+ * sync_set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered.  See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non-x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void sync_set_bit(int nr, volatile unsigned long * addr)
+{
+        __asm__ __volatile__("lock; btsl %1,%0"
+                             :"+m" (ADDR)
+                             :"Ir" (nr)
+                             : "memory");
+}
+
+/**
+ * sync_clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * sync_clear_bit() is atomic and may not be reordered.  However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * 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 sync_clear_bit(int nr, volatile unsigned long * addr)
+{
+        __asm__ __volatile__("lock; btrl %1,%0"
+                             :"+m" (ADDR)
+                             :"Ir" (nr)
+                             : "memory");
+}
+
+/**
+ * sync_change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered. It may be
+ * reordered on other architectures than x86.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void sync_change_bit(int nr, volatile unsigned long * addr)
+{
+        __asm__ __volatile__("lock; btcl %1,%0"
+                             :"+m" (ADDR)
+                             :"Ir" (nr)
+                             : "memory");
+}
+
+/**
+ * sync_test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It may be reordered on other architectures than x86.
+ * It also implies a memory barrier.
+ */
+static inline int sync_test_and_set_bit(int nr, volatile unsigned long * addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__("lock; btsl %2,%1\n\tsbbl %0,%0"
+                             :"=r" (oldbit),"+m" (ADDR)
+                             :"Ir" (nr) : "memory");
+        return oldbit;
+}
+
+/**
+ * sync_test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It can be reorderdered on other architectures other than x86.
+ * It also implies a memory barrier.
+ */
+static inline int sync_test_and_clear_bit(int nr, volatile unsigned long * addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__("lock; btrl %2,%1\n\tsbbl %0,%0"
+                             :"=r" (oldbit),"+m" (ADDR)
+                             :"Ir" (nr) : "memory");
+        return oldbit;
+}
+
+/**
+ * sync_test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int sync_test_and_change_bit(int nr, volatile unsigned long* addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__("lock; btcl %2,%1\n\tsbbl %0,%0"
+                             :"=r" (oldbit),"+m" (ADDR)
+                             :"Ir" (nr) : "memory");
+        return oldbit;
+}
+
+static __always_inline int sync_constant_test_bit(int nr, const volatile unsigned long *addr)
+{
+        return ((1UL << (nr & 31)) &
+                (((const volatile unsigned int *)addr)[nr >> 5])) != 0;
+}
+
+static inline int sync_var_test_bit(int nr, const volatile unsigned long * addr)
+{
+        int oldbit;
+
+        __asm__ __volatile__("btl %2,%1\n\tsbbl %0,%0"
+                             :"=r" (oldbit)
+                             :"m" (ADDR),"Ir" (nr));
+        return oldbit;
+}
+
+#define sync_test_bit(nr,addr)                  \
+        (__builtin_constant_p(nr) ?             \
+         sync_constant_test_bit((nr),(addr)) :  \
+         sync_var_test_bit((nr),(addr)))
+
+#undef ADDR
+
+#endif /* _I386_SYNC_BITOPS_H */
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
new file mode 100644
index 000000000000..692562b48f2a
--- /dev/null
+++ b/include/asm-x86/system.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "system_32.h"
+#else
+# include "system_64.h"
+#endif
diff --git a/include/asm-x86/system_32.h b/include/asm-x86/system_32.h
new file mode 100644
index 000000000000..d69ba937e092
--- /dev/null
+++ b/include/asm-x86/system_32.h
@@ -0,0 +1,313 @@
+#ifndef __ASM_SYSTEM_H
+#define __ASM_SYSTEM_H
+
+#include <linux/kernel.h>
+#include <asm/segment.h>
+#include <asm/cpufeature.h>
+#include <asm/cmpxchg.h>
+
+#ifdef __KERNEL__
+
+struct task_struct;     /* one of the stranger aspects of C forward declarations.. */
+extern struct task_struct * FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next));
+
+/*
+ * Saving eflags is important. It switches not only IOPL between tasks,
+ * it also protects other tasks from NT leaking through sysenter etc.
+ */
+#define switch_to(prev,next,last) do {                                  \
+        unsigned long esi,edi;                                          \
+        asm volatile("pushfl\n\t"               /* Save flags */        \
+                     "pushl %%ebp\n\t"                                  \
+                     "movl %%esp,%0\n\t"        /* save ESP */          \
+                     "movl %5,%%esp\n\t"        /* restore ESP */       \
+                     "movl $1f,%1\n\t"          /* save EIP */          \
+                     "pushl %6\n\t"             /* restore EIP */       \
+                     "jmp __switch_to\n"                                \
+                     "1:\t"                                             \
+                     "popl %%ebp\n\t"                                   \
+                     "popfl"                                            \
+                     :"=m" (prev->thread.esp),"=m" (prev->thread.eip),  \
+                      "=a" (last),"=S" (esi),"=D" (edi)                 \
+                     :"m" (next->thread.esp),"m" (next->thread.eip),    \
+                      "2" (prev), "d" (next));                          \
+} while (0)
+
+#define _set_base(addr,base) do { unsigned long __pr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+        "rorl $16,%%edx\n\t" \
+        "movb %%dl,%2\n\t" \
+        "movb %%dh,%3" \
+        :"=&d" (__pr) \
+        :"m" (*((addr)+2)), \
+         "m" (*((addr)+4)), \
+         "m" (*((addr)+7)), \
+         "0" (base) \
+        ); } while(0)
+
+#define _set_limit(addr,limit) do { unsigned long __lr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+        "rorl $16,%%edx\n\t" \
+        "movb %2,%%dh\n\t" \
+        "andb $0xf0,%%dh\n\t" \
+        "orb %%dh,%%dl\n\t" \
+        "movb %%dl,%2" \
+        :"=&d" (__lr) \
+        :"m" (*(addr)), \
+         "m" (*((addr)+6)), \
+         "0" (limit) \
+        ); } while(0)
+
+#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) )
+#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1) )
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg,value)                  \
+        asm volatile("\n"                       \
+                "1:\t"                          \
+                "mov %0,%%" #seg "\n"           \
+                "2:\n"                          \
+                ".section .fixup,\"ax\"\n"      \
+                "3:\t"                          \
+                "pushl $0\n\t"                  \
+                "popl %%" #seg "\n\t"           \
+                "jmp 2b\n"                      \
+                ".previous\n"                   \
+                ".section __ex_table,\"a\"\n\t" \
+                ".align 4\n\t"                  \
+                ".long 1b,3b\n"                 \
+                ".previous"                     \
+                : :"rm" (value))
+
+/*
+ * Save a segment register away
+ */
+#define savesegment(seg, value) \
+        asm volatile("mov %%" #seg ",%0":"=rm" (value))
+
+
+static inline void native_clts(void)
+{
+        asm volatile ("clts");
+}
+
+static inline unsigned long native_read_cr0(void)
+{
+        unsigned long val;
+        asm volatile("movl %%cr0,%0\n\t" :"=r" (val));
+        return val;
+}
+
+static inline void native_write_cr0(unsigned long val)
+{
+        asm volatile("movl %0,%%cr0": :"r" (val));
+}
+
+static inline unsigned long native_read_cr2(void)
+{
+        unsigned long val;
+        asm volatile("movl %%cr2,%0\n\t" :"=r" (val));
+        return val;
+}
+
+static inline void native_write_cr2(unsigned long val)
+{
+        asm volatile("movl %0,%%cr2": :"r" (val));
+}
+
+static inline unsigned long native_read_cr3(void)
+{
+        unsigned long val;
+        asm volatile("movl %%cr3,%0\n\t" :"=r" (val));
+        return val;
+}
+
+static inline void native_write_cr3(unsigned long val)
+{
+        asm volatile("movl %0,%%cr3": :"r" (val));
+}
+
+static inline unsigned long native_read_cr4(void)
+{
+        unsigned long val;
+        asm volatile("movl %%cr4,%0\n\t" :"=r" (val));
+        return val;
+}
+
+static inline unsigned long native_read_cr4_safe(void)
+{
+        unsigned long val;
+        /* This could fault if %cr4 does not exist */
+        asm("1: movl %%cr4, %0          \n"
+                "2:                             \n"
+                ".section __ex_table,\"a\"      \n"
+                ".long 1b,2b                    \n"
+                ".previous                      \n"
+                : "=r" (val): "0" (0));
+        return val;
+}
+
+static inline void native_write_cr4(unsigned long val)
+{
+        asm volatile("movl %0,%%cr4": :"r" (val));
+}
+
+static inline void native_wbinvd(void)
+{
+        asm volatile("wbinvd": : :"memory");
+}
+
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define read_cr0()      (native_read_cr0())
+#define write_cr0(x)    (native_write_cr0(x))
+#define read_cr2()      (native_read_cr2())
+#define write_cr2(x)    (native_write_cr2(x))
+#define read_cr3()      (native_read_cr3())
+#define write_cr3(x)    (native_write_cr3(x))
+#define read_cr4()      (native_read_cr4())
+#define read_cr4_safe() (native_read_cr4_safe())
+#define write_cr4(x)    (native_write_cr4(x))
+#define wbinvd()        (native_wbinvd())
+
+/* Clear the 'TS' bit */
+#define clts()          (native_clts())
+
+#endif/* CONFIG_PARAVIRT */
+
+/* Set the 'TS' bit */
+#define stts() write_cr0(8 | read_cr0())
+
+#endif  /* __KERNEL__ */
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+        unsigned long __limit;
+        __asm__("lsll %1,%0"
+                :"=r" (__limit):"r" (segment));
+        return __limit+1;
+}
+
+#define nop() __asm__ __volatile__ ("nop")
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * For now, "wmb()" doesn't actually do anything, as all
+ * Intel CPU's follow what Intel calls a *Processor Order*,
+ * in which all writes are seen in the program order even
+ * outside the CPU.
+ *
+ * I expect future Intel CPU's to have a weaker ordering,
+ * but I'd also expect them to finally get their act together
+ * and add some real memory barriers if so.
+ *
+ * Some non intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+ 
+
+#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier.  All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads.  This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies.  See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ *      CPU 0                           CPU 1
+ *
+ *      b = 2;
+ *      memory_barrier();
+ *      p = &b;                         q = p;
+ *                                      read_barrier_depends();
+ *                                      d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends().  However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ *      CPU 0                           CPU 1
+ *
+ *      a = 2;
+ *      memory_barrier();
+ *      b = 3;                          y = b;
+ *                                      read_barrier_depends();
+ *                                      x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b".  Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
+ * in cases like this where there are no data dependencies.
+ **/
+
+#define read_barrier_depends()  do { } while(0)
+
+#ifdef CONFIG_X86_OOSTORE
+/* Actually there are no OOO store capable CPUs for now that do SSE, 
+   but make it already an possibility. */
+#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#else
+#define wmb()   __asm__ __volatile__ ("": : :"memory")
+#endif
+
+#ifdef CONFIG_SMP
+#define smp_mb()        mb()
+#define smp_rmb()       rmb()
+#define smp_wmb()       wmb()
+#define smp_read_barrier_depends()      read_barrier_depends()
+#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
+#else
+#define smp_mb()        barrier()
+#define smp_rmb()       barrier()
+#define smp_wmb()       barrier()
+#define smp_read_barrier_depends()      do { } while(0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif
+
+#include <linux/irqflags.h>
+
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+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);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+
+void default_idle(void);
+
+#endif
diff --git a/include/asm-x86/system_64.h b/include/asm-x86/system_64.h
new file mode 100644
index 000000000000..02175aa1d16a
--- /dev/null
+++ b/include/asm-x86/system_64.h
@@ -0,0 +1,180 @@
+#ifndef __ASM_SYSTEM_H
+#define __ASM_SYSTEM_H
+
+#include <linux/kernel.h>
+#include <asm/segment.h>
+#include <asm/cmpxchg.h>
+
+#ifdef __KERNEL__
+
+#define __STR(x) #x
+#define STR(x) __STR(x)
+
+#define __SAVE(reg,offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
+#define __RESTORE(reg,offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
+
+/* frame pointer must be last for get_wchan */
+#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+
+#define __EXTRA_CLOBBER  \
+        ,"rcx","rbx","rdx","r8","r9","r10","r11","r12","r13","r14","r15"
+
+/* Save restore flags to clear handle leaking NT */
+#define switch_to(prev,next,last) \
+        asm volatile(SAVE_CONTEXT                                                   \
+                     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */       \
+                     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */    \
+                     "call __switch_to\n\t"                                       \
+                     ".globl thread_return\n"                                   \
+                     "thread_return:\n\t"                                           \
+                     "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"                       \
+                     "movq %P[thread_info](%%rsi),%%r8\n\t"                       \
+                     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"        \
+                     "movq %%rax,%%rdi\n\t"                                       \
+                     "jc   ret_from_fork\n\t"                                     \
+                     RESTORE_CONTEXT                                                \
+                     : "=a" (last)                                                \
+                     : [next] "S" (next), [prev] "D" (prev),                      \
+                       [threadrsp] "i" (offsetof(struct task_struct, thread.rsp)), \
+                       [ti_flags] "i" (offsetof(struct thread_info, flags)),\
+                       [tif_fork] "i" (TIF_FORK),                         \
+                       [thread_info] "i" (offsetof(struct task_struct, stack)), \
+                       [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent))   \
+                     : "memory", "cc" __EXTRA_CLOBBER)
+    
+extern void load_gs_index(unsigned); 
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg,value)  \
+        asm volatile("\n"                       \
+                "1:\t"                          \
+                "movl %k0,%%" #seg "\n"         \
+                "2:\n"                          \
+                ".section .fixup,\"ax\"\n"      \
+                "3:\t"                          \
+                "movl %1,%%" #seg "\n\t"        \
+                "jmp 2b\n"                      \
+                ".previous\n"                   \
+                ".section __ex_table,\"a\"\n\t" \
+                ".align 8\n\t"                  \
+                ".quad 1b,3b\n"                 \
+                ".previous"                     \
+                : :"r" (value), "r" (0))
+
+/*
+ * Clear and set 'TS' bit respectively
+ */
+#define clts() __asm__ __volatile__ ("clts")
+
+static inline unsigned long read_cr0(void)
+{ 
+        unsigned long cr0;
+        asm volatile("movq %%cr0,%0" : "=r" (cr0));
+        return cr0;
+}
+
+static inline void write_cr0(unsigned long val) 
+{ 
+        asm volatile("movq %0,%%cr0" :: "r" (val));
+}
+
+static inline unsigned long read_cr2(void)
+{
+        unsigned long cr2;
+        asm("movq %%cr2,%0" : "=r" (cr2));
+        return cr2;
+}
+
+static inline void write_cr2(unsigned long val)
+{
+        asm volatile("movq %0,%%cr2" :: "r" (val));
+}
+
+static inline unsigned long read_cr3(void)
+{ 
+        unsigned long cr3;
+        asm("movq %%cr3,%0" : "=r" (cr3));
+        return cr3;
+}
+
+static inline void write_cr3(unsigned long val)
+{
+        asm volatile("movq %0,%%cr3" :: "r" (val) : "memory");
+}
+
+static inline unsigned long read_cr4(void)
+{ 
+        unsigned long cr4;
+        asm("movq %%cr4,%0" : "=r" (cr4));
+        return cr4;
+}
+
+static inline void write_cr4(unsigned long val)
+{ 
+        asm volatile("movq %0,%%cr4" :: "r" (val) : "memory");
+}
+
+static inline unsigned long read_cr8(void)
+{
+        unsigned long cr8;
+        asm("movq %%cr8,%0" : "=r" (cr8));
+        return cr8;
+}
+
+static inline void write_cr8(unsigned long val)
+{
+        asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
+}
+
+#define stts() write_cr0(8 | read_cr0())
+
+#define wbinvd() \
+        __asm__ __volatile__ ("wbinvd": : :"memory")
+
+#endif  /* __KERNEL__ */
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#ifdef CONFIG_SMP
+#define smp_mb()        mb()
+#define smp_rmb()       rmb()
+#define smp_wmb()       wmb()
+#define smp_read_barrier_depends()      do {} while(0)
+#else
+#define smp_mb()        barrier()
+#define smp_rmb()       barrier()
+#define smp_wmb()       barrier()
+#define smp_read_barrier_depends()      do {} while(0)
+#endif
+
+    
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+#define mb()    asm volatile("mfence":::"memory")
+#define rmb()   asm volatile("lfence":::"memory")
+
+#ifdef CONFIG_UNORDERED_IO
+#define wmb()   asm volatile("sfence" ::: "memory")
+#else
+#define wmb()   asm volatile("" ::: "memory")
+#endif
+#define read_barrier_depends()  do {} while(0)
+#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
+
+#define warn_if_not_ulong(x) do { unsigned long foo; (void) (&(x) == &foo); } while (0)
+
+#include <linux/irqflags.h>
+
+void cpu_idle_wait(void);
+
+extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+
+#endif
diff --git a/include/asm-x86/tce.h b/include/asm-x86/tce.h
new file mode 100644
index 000000000000..cd955d3d112f
--- /dev/null
+++ b/include/asm-x86/tce.h
@@ -0,0 +1,48 @@
+/*
+ * This file is derived from asm-powerpc/tce.h.
+ *
+ * Copyright (C) IBM Corporation, 2006
+ *
+ * Author: Muli Ben-Yehuda <muli@il.ibm.com>
+ * Author: Jon Mason <jdmason@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef _ASM_X86_64_TCE_H
+#define _ASM_X86_64_TCE_H
+
+extern unsigned int specified_table_size;
+struct iommu_table;
+
+#define TCE_ENTRY_SIZE   8   /* in bytes */
+
+#define TCE_READ_SHIFT   0
+#define TCE_WRITE_SHIFT  1
+#define TCE_HUBID_SHIFT  2   /* unused */
+#define TCE_RSVD_SHIFT   8   /* unused */
+#define TCE_RPN_SHIFT    12
+#define TCE_UNUSED_SHIFT 48  /* unused */
+
+#define TCE_RPN_MASK     0x0000fffffffff000ULL
+
+extern void tce_build(struct iommu_table *tbl, unsigned long index,
+        unsigned int npages, unsigned long uaddr, int direction);
+extern void tce_free(struct iommu_table *tbl, long index, unsigned int npages);
+extern void * __init alloc_tce_table(void);
+extern void __init free_tce_table(void *tbl);
+extern int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar);
+
+#endif /* _ASM_X86_64_TCE_H */
diff --git a/include/asm-x86/termbits.h b/include/asm-x86/termbits.h
new file mode 100644
index 000000000000..69f3080e2a1d
--- /dev/null
+++ b/include/asm-x86/termbits.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "termbits_32.h"
+# else
+#  include "termbits_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "termbits_32.h"
+# else
+#  include "termbits_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/termbits_32.h b/include/asm-x86/termbits_32.h
new file mode 100644
index 000000000000..a21700352e7b
--- /dev/null
+++ b/include/asm-x86/termbits_32.h
@@ -0,0 +1,198 @@
+#ifndef __ARCH_I386_TERMBITS_H__
+#define __ARCH_I386_TERMBITS_H__
+
+#include <linux/posix_types.h>
+
+typedef unsigned char   cc_t;
+typedef unsigned int    speed_t;
+typedef unsigned int    tcflag_t;
+
+#define NCCS 19
+struct termios {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+};
+
+struct termios2 {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+        speed_t c_ispeed;               /* input speed */
+        speed_t c_ospeed;               /* output speed */
+};
+
+struct ktermios {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+        speed_t c_ispeed;               /* input speed */
+        speed_t c_ospeed;               /* output speed */
+};
+
+/* c_cc characters */
+#define VINTR 0
+#define VQUIT 1
+#define VERASE 2
+#define VKILL 3
+#define VEOF 4
+#define VTIME 5
+#define VMIN 6
+#define VSWTC 7
+#define VSTART 8
+#define VSTOP 9
+#define VSUSP 10
+#define VEOL 11
+#define VREPRINT 12
+#define VDISCARD 13
+#define VWERASE 14
+#define VLNEXT 15
+#define VEOL2 16
+
+/* c_iflag bits */
+#define IGNBRK  0000001
+#define BRKINT  0000002
+#define IGNPAR  0000004
+#define PARMRK  0000010
+#define INPCK   0000020
+#define ISTRIP  0000040
+#define INLCR   0000100
+#define IGNCR   0000200
+#define ICRNL   0000400
+#define IUCLC   0001000
+#define IXON    0002000
+#define IXANY   0004000
+#define IXOFF   0010000
+#define IMAXBEL 0020000
+#define IUTF8   0040000
+
+/* c_oflag bits */
+#define OPOST   0000001
+#define OLCUC   0000002
+#define ONLCR   0000004
+#define OCRNL   0000010
+#define ONOCR   0000020
+#define ONLRET  0000040
+#define OFILL   0000100
+#define OFDEL   0000200
+#define NLDLY   0000400
+#define   NL0   0000000
+#define   NL1   0000400
+#define CRDLY   0003000
+#define   CR0   0000000
+#define   CR1   0001000
+#define   CR2   0002000
+#define   CR3   0003000
+#define TABDLY  0014000
+#define   TAB0  0000000
+#define   TAB1  0004000
+#define   TAB2  0010000
+#define   TAB3  0014000
+#define   XTABS 0014000
+#define BSDLY   0020000
+#define   BS0   0000000
+#define   BS1   0020000
+#define VTDLY   0040000
+#define   VT0   0000000
+#define   VT1   0040000
+#define FFDLY   0100000
+#define   FF0   0000000
+#define   FF1   0100000
+
+/* c_cflag bit meaning */
+#define CBAUD   0010017
+#define  B0     0000000         /* hang up */
+#define  B50    0000001
+#define  B75    0000002
+#define  B110   0000003
+#define  B134   0000004
+#define  B150   0000005
+#define  B200   0000006
+#define  B300   0000007
+#define  B600   0000010
+#define  B1200  0000011
+#define  B1800  0000012
+#define  B2400  0000013
+#define  B4800  0000014
+#define  B9600  0000015
+#define  B19200 0000016
+#define  B38400 0000017
+#define EXTA B19200
+#define EXTB B38400
+#define CSIZE   0000060
+#define   CS5   0000000
+#define   CS6   0000020
+#define   CS7   0000040
+#define   CS8   0000060
+#define CSTOPB  0000100
+#define CREAD   0000200
+#define PARENB  0000400
+#define PARODD  0001000
+#define HUPCL   0002000
+#define CLOCAL  0004000
+#define CBAUDEX 0010000
+#define   BOTHER  0010000
+#define    B57600 0010001
+#define   B115200 0010002
+#define   B230400 0010003
+#define   B460800 0010004
+#define   B500000 0010005
+#define   B576000 0010006
+#define   B921600 0010007
+#define  B1000000 0010010
+#define  B1152000 0010011
+#define  B1500000 0010012
+#define  B2000000 0010013
+#define  B2500000 0010014
+#define  B3000000 0010015
+#define  B3500000 0010016
+#define  B4000000 0010017
+#define CIBAUD    002003600000
+#define CMSPAR    010000000000          /* mark or space (stick) parity */
+#define CRTSCTS   020000000000          /* flow control */
+
+#define IBSHIFT   16            /* Shift from CBAUD to CIBAUD */
+
+/* c_lflag bits */
+#define ISIG    0000001
+#define ICANON  0000002
+#define XCASE   0000004
+#define ECHO    0000010
+#define ECHOE   0000020
+#define ECHOK   0000040
+#define ECHONL  0000100
+#define NOFLSH  0000200
+#define TOSTOP  0000400
+#define ECHOCTL 0001000
+#define ECHOPRT 0002000
+#define ECHOKE  0004000
+#define FLUSHO  0010000
+#define PENDIN  0040000
+#define IEXTEN  0100000
+
+/* tcflow() and TCXONC use these */
+#define TCOOFF          0
+#define TCOON           1
+#define TCIOFF          2
+#define TCION           3
+
+/* tcflush() and TCFLSH use these */
+#define TCIFLUSH        0
+#define TCOFLUSH        1
+#define TCIOFLUSH       2
+
+/* tcsetattr uses these */
+#define TCSANOW         0
+#define TCSADRAIN       1
+#define TCSAFLUSH       2
+
+#endif
diff --git a/include/asm-x86/termbits_64.h b/include/asm-x86/termbits_64.h
new file mode 100644
index 000000000000..7405756dd41b
--- /dev/null
+++ b/include/asm-x86/termbits_64.h
@@ -0,0 +1,198 @@
+#ifndef __ARCH_X8664_TERMBITS_H__
+#define __ARCH_X8664_TERMBITS_H__
+
+#include <linux/posix_types.h>
+
+typedef unsigned char   cc_t;
+typedef unsigned int    speed_t;
+typedef unsigned int    tcflag_t;
+
+#define NCCS 19
+struct termios {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+};
+
+struct termios2 {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+        speed_t c_ispeed;               /* input speed */
+        speed_t c_ospeed;               /* output speed */
+};
+
+struct ktermios {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+        speed_t c_ispeed;               /* input speed */
+        speed_t c_ospeed;               /* output speed */
+};
+
+/* c_cc characters */
+#define VINTR 0
+#define VQUIT 1
+#define VERASE 2
+#define VKILL 3
+#define VEOF 4
+#define VTIME 5
+#define VMIN 6
+#define VSWTC 7
+#define VSTART 8
+#define VSTOP 9
+#define VSUSP 10
+#define VEOL 11
+#define VREPRINT 12
+#define VDISCARD 13
+#define VWERASE 14
+#define VLNEXT 15
+#define VEOL2 16
+
+/* c_iflag bits */
+#define IGNBRK  0000001
+#define BRKINT  0000002
+#define IGNPAR  0000004
+#define PARMRK  0000010
+#define INPCK   0000020
+#define ISTRIP  0000040
+#define INLCR   0000100
+#define IGNCR   0000200
+#define ICRNL   0000400
+#define IUCLC   0001000
+#define IXON    0002000
+#define IXANY   0004000
+#define IXOFF   0010000
+#define IMAXBEL 0020000
+#define IUTF8   0040000
+
+/* c_oflag bits */
+#define OPOST   0000001
+#define OLCUC   0000002
+#define ONLCR   0000004
+#define OCRNL   0000010
+#define ONOCR   0000020
+#define ONLRET  0000040
+#define OFILL   0000100
+#define OFDEL   0000200
+#define NLDLY   0000400
+#define   NL0   0000000
+#define   NL1   0000400
+#define CRDLY   0003000
+#define   CR0   0000000
+#define   CR1   0001000
+#define   CR2   0002000
+#define   CR3   0003000
+#define TABDLY  0014000
+#define   TAB0  0000000
+#define   TAB1  0004000
+#define   TAB2  0010000
+#define   TAB3  0014000
+#define   XTABS 0014000
+#define BSDLY   0020000
+#define   BS0   0000000
+#define   BS1   0020000
+#define VTDLY   0040000
+#define   VT0   0000000
+#define   VT1   0040000
+#define FFDLY   0100000
+#define   FF0   0000000
+#define   FF1   0100000
+
+/* c_cflag bit meaning */
+#define CBAUD   0010017
+#define  B0     0000000         /* hang up */
+#define  B50    0000001
+#define  B75    0000002
+#define  B110   0000003
+#define  B134   0000004
+#define  B150   0000005
+#define  B200   0000006
+#define  B300   0000007
+#define  B600   0000010
+#define  B1200  0000011
+#define  B1800  0000012
+#define  B2400  0000013
+#define  B4800  0000014
+#define  B9600  0000015
+#define  B19200 0000016
+#define  B38400 0000017
+#define EXTA B19200
+#define EXTB B38400
+#define CSIZE   0000060
+#define   CS5   0000000
+#define   CS6   0000020
+#define   CS7   0000040
+#define   CS8   0000060
+#define CSTOPB  0000100
+#define CREAD   0000200
+#define PARENB  0000400
+#define PARODD  0001000
+#define HUPCL   0002000
+#define CLOCAL  0004000
+#define CBAUDEX 0010000
+#define    BOTHER 0010000               /* non standard rate */
+#define    B57600 0010001
+#define   B115200 0010002
+#define   B230400 0010003
+#define   B460800 0010004
+#define   B500000 0010005
+#define   B576000 0010006
+#define   B921600 0010007
+#define  B1000000 0010010
+#define  B1152000 0010011
+#define  B1500000 0010012
+#define  B2000000 0010013
+#define  B2500000 0010014
+#define  B3000000 0010015
+#define  B3500000 0010016
+#define  B4000000 0010017
+#define CIBAUD    002003600000  /* input baud rate */
+#define CMSPAR    010000000000          /* mark or space (stick) parity */
+#define CRTSCTS   020000000000          /* flow control */
+
+#define IBSHIFT   16            /* Shift from CBAUD to CIBAUD */
+
+/* c_lflag bits */
+#define ISIG    0000001
+#define ICANON  0000002
+#define XCASE   0000004
+#define ECHO    0000010
+#define ECHOE   0000020
+#define ECHOK   0000040
+#define ECHONL  0000100
+#define NOFLSH  0000200
+#define TOSTOP  0000400
+#define ECHOCTL 0001000
+#define ECHOPRT 0002000
+#define ECHOKE  0004000
+#define FLUSHO  0010000
+#define PENDIN  0040000
+#define IEXTEN  0100000
+
+/* tcflow() and TCXONC use these */
+#define TCOOFF          0
+#define TCOON           1
+#define TCIOFF          2
+#define TCION           3
+
+/* tcflush() and TCFLSH use these */
+#define TCIFLUSH        0
+#define TCOFLUSH        1
+#define TCIOFLUSH       2
+
+/* tcsetattr uses these */
+#define TCSANOW         0
+#define TCSADRAIN       1
+#define TCSAFLUSH       2
+
+#endif
diff --git a/include/asm-x86/termios.h b/include/asm-x86/termios.h
new file mode 100644
index 000000000000..a4f4ae20a591
--- /dev/null
+++ b/include/asm-x86/termios.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "termios_32.h"
+# else
+#  include "termios_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "termios_32.h"
+# else
+#  include "termios_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/termios_32.h b/include/asm-x86/termios_32.h
new file mode 100644
index 000000000000..6fdb2c841b73
--- /dev/null
+++ b/include/asm-x86/termios_32.h
@@ -0,0 +1,90 @@
+#ifndef _I386_TERMIOS_H
+#define _I386_TERMIOS_H
+
+#include <asm/termbits.h>
+#include <asm/ioctls.h>
+
+struct winsize {
+        unsigned short ws_row;
+        unsigned short ws_col;
+        unsigned short ws_xpixel;
+        unsigned short ws_ypixel;
+};
+
+#define NCC 8
+struct termio {
+        unsigned short c_iflag;         /* input mode flags */
+        unsigned short c_oflag;         /* output mode flags */
+        unsigned short c_cflag;         /* control mode flags */
+        unsigned short c_lflag;         /* local mode flags */
+        unsigned char c_line;           /* line discipline */
+        unsigned char c_cc[NCC];        /* control characters */
+};
+
+/* modem lines */
+#define TIOCM_LE        0x001
+#define TIOCM_DTR       0x002
+#define TIOCM_RTS       0x004
+#define TIOCM_ST        0x008
+#define TIOCM_SR        0x010
+#define TIOCM_CTS       0x020
+#define TIOCM_CAR       0x040
+#define TIOCM_RNG       0x080
+#define TIOCM_DSR       0x100
+#define TIOCM_CD        TIOCM_CAR
+#define TIOCM_RI        TIOCM_RNG
+#define TIOCM_OUT1      0x2000
+#define TIOCM_OUT2      0x4000
+#define TIOCM_LOOP      0x8000
+
+/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
+
+#ifdef __KERNEL__
+
+/*      intr=^C         quit=^\         erase=del       kill=^U
+        eof=^D          vtime=\0        vmin=\1         sxtc=\0
+        start=^Q        stop=^S         susp=^Z         eol=\0
+        reprint=^R      discard=^U      werase=^W       lnext=^V
+        eol2=\0
+*/
+#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
+        unsigned short __tmp; \
+        get_user(__tmp,&(termio)->x); \
+        *(unsigned short *) &(termios)->x = __tmp; \
+}
+
+#define user_termio_to_kernel_termios(termios, termio) \
+({ \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
+        copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
+})
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+#define kernel_termios_to_user_termio(termio, termios) \
+({ \
+        put_user((termios)->c_iflag, &(termio)->c_iflag); \
+        put_user((termios)->c_oflag, &(termio)->c_oflag); \
+        put_user((termios)->c_cflag, &(termio)->c_cflag); \
+        put_user((termios)->c_lflag, &(termio)->c_lflag); \
+        put_user((termios)->c_line,  &(termio)->c_line); \
+        copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
+})
+
+#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2))
+#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2))
+#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios))
+#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios))
+
+#endif  /* __KERNEL__ */
+
+#endif  /* _I386_TERMIOS_H */
diff --git a/include/asm-x86/termios_64.h b/include/asm-x86/termios_64.h
new file mode 100644
index 000000000000..35ee59b78329
--- /dev/null
+++ b/include/asm-x86/termios_64.h
@@ -0,0 +1,90 @@
+#ifndef _X8664_TERMIOS_H
+#define _X8664_TERMIOS_H
+
+#include <asm/termbits.h>
+#include <asm/ioctls.h>
+
+struct winsize {
+        unsigned short ws_row;
+        unsigned short ws_col;
+        unsigned short ws_xpixel;
+        unsigned short ws_ypixel;
+};
+
+#define NCC 8
+struct termio {
+        unsigned short c_iflag;         /* input mode flags */
+        unsigned short c_oflag;         /* output mode flags */
+        unsigned short c_cflag;         /* control mode flags */
+        unsigned short c_lflag;         /* local mode flags */
+        unsigned char c_line;           /* line discipline */
+        unsigned char c_cc[NCC];        /* control characters */
+};
+
+/* modem lines */
+#define TIOCM_LE        0x001
+#define TIOCM_DTR       0x002
+#define TIOCM_RTS       0x004
+#define TIOCM_ST        0x008
+#define TIOCM_SR        0x010
+#define TIOCM_CTS       0x020
+#define TIOCM_CAR       0x040
+#define TIOCM_RNG       0x080
+#define TIOCM_DSR       0x100
+#define TIOCM_CD        TIOCM_CAR
+#define TIOCM_RI        TIOCM_RNG
+#define TIOCM_OUT1      0x2000
+#define TIOCM_OUT2      0x4000
+#define TIOCM_LOOP      0x8000
+
+/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
+
+#ifdef __KERNEL__
+
+/*      intr=^C         quit=^\         erase=del       kill=^U
+        eof=^D          vtime=\0        vmin=\1         sxtc=\0
+        start=^Q        stop=^S         susp=^Z         eol=\0
+        reprint=^R      discard=^U      werase=^W       lnext=^V
+        eol2=\0
+*/
+#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
+        unsigned short __tmp; \
+        get_user(__tmp,&(termio)->x); \
+        *(unsigned short *) &(termios)->x = __tmp; \
+}
+
+#define user_termio_to_kernel_termios(termios, termio) \
+({ \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
+        copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
+})
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+#define kernel_termios_to_user_termio(termio, termios) \
+({ \
+        put_user((termios)->c_iflag, &(termio)->c_iflag); \
+        put_user((termios)->c_oflag, &(termio)->c_oflag); \
+        put_user((termios)->c_cflag, &(termio)->c_cflag); \
+        put_user((termios)->c_lflag, &(termio)->c_lflag); \
+        put_user((termios)->c_line,  &(termio)->c_line); \
+        copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
+})
+
+#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2))
+#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2))
+#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios))
+#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios))
+
+#endif  /* __KERNEL__ */
+
+#endif  /* _X8664_TERMIOS_H */
diff --git a/include/asm-x86/therm_throt.h b/include/asm-x86/therm_throt.h
new file mode 100644
index 000000000000..399bf6026b16
--- /dev/null
+++ b/include/asm-x86/therm_throt.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_I386_THERM_THROT_H__
+#define __ASM_I386_THERM_THROT_H__ 1
+
+#include <asm/atomic.h>
+
+extern atomic_t therm_throt_en;
+int therm_throt_process(int curr);
+
+#endif /* __ASM_I386_THERM_THROT_H__ */
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
new file mode 100644
index 000000000000..d5fd12f2abdb
--- /dev/null
+++ b/include/asm-x86/thread_info.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "thread_info_32.h"
+#else
+# include "thread_info_64.h"
+#endif
diff --git a/include/asm-x86/thread_info_32.h b/include/asm-x86/thread_info_32.h
new file mode 100644
index 000000000000..22a8cbcd35e2
--- /dev/null
+++ b/include/asm-x86/thread_info_32.h
@@ -0,0 +1,180 @@
+/* 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 for user-thead
+                                                   0-0xFFFFFFFF for 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") __attribute_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
+
+#define free_thread_info(info)  free_pages((unsigned long)(info), get_order(THREAD_SIZE))
+
+#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_RESTORE_SIGMASK     8       /* restore signal mask in do_signal() */
+#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_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_RESTORE_SIGMASK    (1<<TIF_RESTORE_SIGMASK)
+#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)
+
+/* 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_NEXT (_TIF_IO_BITMAP | _TIF_NOTSC | _TIF_DEBUG)
+#define _TIF_WORK_CTXSW_PREV (_TIF_IO_BITMAP | _TIF_NOTSC)
+
+/*
+ * 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 tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
+
+#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
new file mode 100644
index 000000000000..beae2bfb62ca
--- /dev/null
+++ b/include/asm-x86/thread_info_64.h
@@ -0,0 +1,169 @@
+/* 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/mmsegment.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;
+};
+#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 alloc_thread_info(tsk)                                  \
+    ({                                                          \
+        struct thread_info *ret;                                \
+                                                                \
+        ret = ((struct thread_info *) __get_free_pages(GFP_KERNEL,THREAD_ORDER)); \
+        if (ret)                                                \
+                memset(ret, 0, THREAD_SIZE);                    \
+        ret;                                                    \
+    })
+#else
+#define alloc_thread_info(tsk) \
+        ((struct thread_info *) __get_free_pages(GFP_KERNEL,THREAD_ORDER))
+#endif
+
+#define free_thread_info(ti) free_pages((unsigned long) (ti), 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_RESTORE_SIGMASK     9       /* restore signal mask in do_signal */
+#define TIF_MCE_NOTIFY          10      /* notify userspace of an MCE */
+/* 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_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_RESTORE_SIGMASK    (1<<TIF_RESTORE_SIGMASK)
+#define _TIF_MCE_NOTIFY         (1<<TIF_MCE_NOTIFY)
+#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)
+
+/* 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)
+
+/* flags to check in __switch_to() */
+#define _TIF_WORK_CTXSW (_TIF_DEBUG|_TIF_IO_BITMAP)
+
+#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 tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_THREAD_INFO_H */
diff --git a/include/asm-x86/time.h b/include/asm-x86/time.h
new file mode 100644
index 000000000000..eac011366dc2
--- /dev/null
+++ b/include/asm-x86/time.h
@@ -0,0 +1,44 @@
+#ifndef _ASMi386_TIME_H
+#define _ASMi386_TIME_H
+
+#include <linux/efi.h>
+#include "mach_time.h"
+
+static inline unsigned long native_get_wallclock(void)
+{
+        unsigned long retval;
+
+        if (efi_enabled)
+                retval = efi_get_time();
+        else
+                retval = mach_get_cmos_time();
+
+        return retval;
+}
+
+static inline int native_set_wallclock(unsigned long nowtime)
+{
+        int retval;
+
+        if (efi_enabled)
+                retval = efi_set_rtc_mmss(nowtime);
+        else
+                retval = mach_set_rtc_mmss(nowtime);
+
+        return retval;
+}
+
+extern void (*late_time_init)(void);
+extern void hpet_time_init(void);
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else /* !CONFIG_PARAVIRT */
+
+#define get_wallclock() native_get_wallclock()
+#define set_wallclock(x) native_set_wallclock(x)
+#define choose_time_init() hpet_time_init
+
+#endif /* CONFIG_PARAVIRT */
+
+#endif
diff --git a/include/asm-x86/timer.h b/include/asm-x86/timer.h
new file mode 100644
index 000000000000..0db7e994fb8b
--- /dev/null
+++ b/include/asm-x86/timer.h
@@ -0,0 +1,50 @@
+#ifndef _ASMi386_TIMER_H
+#define _ASMi386_TIMER_H
+#include <linux/init.h>
+#include <linux/pm.h>
+
+#define TICK_SIZE (tick_nsec / 1000)
+
+unsigned long long native_sched_clock(void);
+unsigned long native_calculate_cpu_khz(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()
+#endif
+
+/* Accellerators for sched_clock()
+ * convert from cycles(64bits) => nanoseconds (64bits)
+ *  basic equation:
+ *              ns = cycles / (freq / ns_per_sec)
+ *              ns = cycles * (ns_per_sec / freq)
+ *              ns = cycles * (10^9 / (cpu_khz * 10^3))
+ *              ns = cycles * (10^6 / cpu_khz)
+ *
+ *      Then we use scaling math (suggested by george@mvista.com) to get:
+ *              ns = cycles * (10^6 * SC / cpu_khz) / SC
+ *              ns = cycles * cyc2ns_scale / SC
+ *
+ *      And since SC is a constant power of two, we can convert the div
+ *  into a shift.
+ *
+ *  We can use khz divisor instead of mhz to keep a better percision, since
+ *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
+ *  (mathieu.desnoyers@polymtl.ca)
+ *
+ *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
+ */
+extern unsigned long cyc2ns_scale __read_mostly;
+
+#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
+
+static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+{
+        return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
+}
+
+
+#endif
diff --git a/include/asm-x86/timex.h b/include/asm-x86/timex.h
new file mode 100644
index 000000000000..d01c18cfccef
--- /dev/null
+++ b/include/asm-x86/timex.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "timex_32.h"
+#else
+# include "timex_64.h"
+#endif
diff --git a/include/asm-x86/timex_32.h b/include/asm-x86/timex_32.h
new file mode 100644
index 000000000000..3666044409f0
--- /dev/null
+++ b/include/asm-x86/timex_32.h
@@ -0,0 +1,22 @@
+/*
+ * linux/include/asm-i386/timex.h
+ *
+ * i386 architecture timex specifications
+ */
+#ifndef _ASMi386_TIMEX_H
+#define _ASMi386_TIMEX_H
+
+#include <asm/processor.h>
+#include <asm/tsc.h>
+
+#ifdef CONFIG_X86_ELAN
+#  define CLOCK_TICK_RATE 1189200 /* AMD Elan has different frequency! */
+#else
+#  define CLOCK_TICK_RATE 1193182 /* Underlying HZ */
+#endif
+
+
+extern int read_current_timer(unsigned long *timer_value);
+#define ARCH_HAS_READ_CURRENT_TIMER     1
+
+#endif
diff --git a/include/asm-x86/timex_64.h b/include/asm-x86/timex_64.h
new file mode 100644
index 000000000000..6ed21f44d308
--- /dev/null
+++ b/include/asm-x86/timex_64.h
@@ -0,0 +1,31 @@
+/*
+ * linux/include/asm-x86_64/timex.h
+ *
+ * x86-64 architecture timex specifications
+ */
+#ifndef _ASMx8664_TIMEX_H
+#define _ASMx8664_TIMEX_H
+
+#include <asm/8253pit.h>
+#include <asm/msr.h>
+#include <asm/vsyscall.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/tsc.h>
+#include <linux/compiler.h>
+
+#define CLOCK_TICK_RATE PIT_TICK_RATE   /* Underlying HZ */
+
+extern int read_current_timer(unsigned long *timer_value);
+#define ARCH_HAS_READ_CURRENT_TIMER     1
+
+#define USEC_PER_TICK (USEC_PER_SEC / HZ)
+#define NSEC_PER_TICK (NSEC_PER_SEC / HZ)
+#define FSEC_PER_TICK (FSEC_PER_SEC / HZ)
+
+#define NS_SCALE        10 /* 2^10, carefully chosen */
+#define US_SCALE        32 /* 2^32, arbitralrily chosen */
+
+extern void mark_tsc_unstable(char *msg);
+extern void set_cyc2ns_scale(unsigned long khz);
+#endif
diff --git a/include/asm-x86/tlb.h b/include/asm-x86/tlb.h
new file mode 100644
index 000000000000..7d55c3762b43
--- /dev/null
+++ b/include/asm-x86/tlb.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "tlb_32.h"
+#else
+# include "tlb_64.h"
+#endif
diff --git a/include/asm-x86/tlb_32.h b/include/asm-x86/tlb_32.h
new file mode 100644
index 000000000000..c006c5c92bea
--- /dev/null
+++ b/include/asm-x86/tlb_32.h
@@ -0,0 +1,20 @@
+#ifndef _I386_TLB_H
+#define _I386_TLB_H
+
+/*
+ * x86 doesn't need any special per-pte or
+ * per-vma handling..
+ */
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#define tlb_end_vma(tlb, vma) do { } while (0)
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+
+/*
+ * .. because we flush the whole mm when it
+ * fills up.
+ */
+#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+
+#include <asm-generic/tlb.h>
+
+#endif
diff --git a/include/asm-x86/tlb_64.h b/include/asm-x86/tlb_64.h
new file mode 100644
index 000000000000..cd4c3c590a0e
--- /dev/null
+++ b/include/asm-x86/tlb_64.h
@@ -0,0 +1,13 @@
+#ifndef TLB_H
+#define TLB_H 1
+
+
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#define tlb_end_vma(tlb, vma) do { } while (0)
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+
+#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+
+#include <asm-generic/tlb.h>
+
+#endif
diff --git a/include/asm-x86/tlbflush.h b/include/asm-x86/tlbflush.h
new file mode 100644
index 000000000000..9af4cc83a1af
--- /dev/null
+++ b/include/asm-x86/tlbflush.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "tlbflush_32.h"
+#else
+# include "tlbflush_64.h"
+#endif
diff --git a/include/asm-x86/tlbflush_32.h b/include/asm-x86/tlbflush_32.h
new file mode 100644
index 000000000000..a50fa6741486
--- /dev/null
+++ b/include/asm-x86/tlbflush_32.h
@@ -0,0 +1,175 @@
+#ifndef _I386_TLBFLUSH_H
+#define _I386_TLBFLUSH_H
+
+#include <linux/mm.h>
+#include <asm/processor.h>
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define __flush_tlb() __native_flush_tlb()
+#define __flush_tlb_global() __native_flush_tlb_global()
+#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
+#endif
+
+#define __native_flush_tlb()                                            \
+        do {                                                            \
+                unsigned int tmpreg;                                    \
+                                                                        \
+                __asm__ __volatile__(                                   \
+                        "movl %%cr3, %0;              \n"               \
+                        "movl %0, %%cr3;  # flush TLB \n"               \
+                        : "=r" (tmpreg)                                 \
+                        :: "memory");                                   \
+        } while (0)
+
+/*
+ * Global pages have to be flushed a bit differently. Not a real
+ * performance problem because this does not happen often.
+ */
+#define __native_flush_tlb_global()                                     \
+        do {                                                            \
+                unsigned int tmpreg, cr4, cr4_orig;                     \
+                                                                        \
+                __asm__ __volatile__(                                   \
+                        "movl %%cr4, %2;  # turn off PGE     \n"        \
+                        "movl %2, %1;                        \n"        \
+                        "andl %3, %1;                        \n"        \
+                        "movl %1, %%cr4;                     \n"        \
+                        "movl %%cr3, %0;                     \n"        \
+                        "movl %0, %%cr3;  # flush TLB        \n"        \
+                        "movl %2, %%cr4;  # turn PGE back on \n"        \
+                        : "=&r" (tmpreg), "=&r" (cr4), "=&r" (cr4_orig) \
+                        : "i" (~X86_CR4_PGE)                            \
+                        : "memory");                                    \
+        } while (0)
+
+#define __native_flush_tlb_single(addr)                                 \
+        __asm__ __volatile__("invlpg (%0)" ::"r" (addr) : "memory")
+
+# define __flush_tlb_all()                                              \
+        do {                                                            \
+                if (cpu_has_pge)                                        \
+                        __flush_tlb_global();                           \
+                else                                                    \
+                        __flush_tlb();                                  \
+        } while (0)
+
+#define cpu_has_invlpg  (boot_cpu_data.x86 > 3)
+
+#ifdef CONFIG_X86_INVLPG
+# define __flush_tlb_one(addr) __flush_tlb_single(addr)
+#else
+# define __flush_tlb_one(addr)                                          \
+        do {                                                            \
+                if (cpu_has_invlpg)                                     \
+                        __flush_tlb_single(addr);                       \
+                else                                                    \
+                        __flush_tlb();                                  \
+        } while (0)
+#endif
+
+/*
+ * TLB flushing:
+ *
+ *  - flush_tlb() flushes the current mm struct TLBs
+ *  - flush_tlb_all() flushes all processes TLBs
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
+ *  - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
+ *  - flush_tlb_others(cpumask, mm, va) flushes a TLBs on other cpus
+ *
+ * ..but the i386 has somewhat limited tlb flushing capabilities,
+ * and page-granular flushes are available only on i486 and up.
+ */
+
+#define TLB_FLUSH_ALL   0xffffffff
+
+
+#ifndef CONFIG_SMP
+
+#include <linux/sched.h>
+
+#define flush_tlb() __flush_tlb()
+#define flush_tlb_all() __flush_tlb_all()
+#define local_flush_tlb() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+        if (mm == current->active_mm)
+                __flush_tlb();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+        unsigned long addr)
+{
+        if (vma->vm_mm == current->active_mm)
+                __flush_tlb_one(addr);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+        unsigned long start, unsigned long end)
+{
+        if (vma->vm_mm == current->active_mm)
+                __flush_tlb();
+}
+
+static inline void native_flush_tlb_others(const cpumask_t *cpumask,
+                                           struct mm_struct *mm, unsigned long va)
+{
+}
+
+#else  /* SMP */
+
+#include <asm/smp.h>
+
+#define local_flush_tlb() \
+        __flush_tlb()
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_current_task(void);
+extern void flush_tlb_mm(struct mm_struct *);
+extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+
+#define flush_tlb()     flush_tlb_current_task()
+
+static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long start, unsigned long end)
+{
+        flush_tlb_mm(vma->vm_mm);
+}
+
+void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm,
+                             unsigned long va);
+
+#define TLBSTATE_OK     1
+#define TLBSTATE_LAZY   2
+
+struct tlb_state
+{
+        struct mm_struct *active_mm;
+        int state;
+        char __cacheline_padding[L1_CACHE_BYTES-8];
+};
+DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
+#endif  /* SMP */
+
+#ifndef CONFIG_PARAVIRT
+#define flush_tlb_others(mask, mm, va)          \
+        native_flush_tlb_others(&mask, mm, va)
+#endif
+
+static inline void flush_tlb_kernel_range(unsigned long start,
+                                        unsigned long end)
+{
+        flush_tlb_all();
+}
+
+static inline void flush_tlb_pgtables(struct mm_struct *mm,
+                                      unsigned long start, unsigned long end)
+{
+        /* i386 does not keep any page table caches in TLB */
+}
+
+#endif /* _I386_TLBFLUSH_H */
diff --git a/include/asm-x86/tlbflush_64.h b/include/asm-x86/tlbflush_64.h
new file mode 100644
index 000000000000..888eb4abdd07
--- /dev/null
+++ b/include/asm-x86/tlbflush_64.h
@@ -0,0 +1,109 @@
+#ifndef _X8664_TLBFLUSH_H
+#define _X8664_TLBFLUSH_H
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+
+static inline void __flush_tlb(void)
+{
+        write_cr3(read_cr3());
+}
+
+static inline void __flush_tlb_all(void)
+{
+        unsigned long cr4 = read_cr4();
+        write_cr4(cr4 & ~X86_CR4_PGE);  /* clear PGE */
+        write_cr4(cr4);                 /* write old PGE again and flush TLBs */
+}
+
+#define __flush_tlb_one(addr) \
+        __asm__ __volatile__("invlpg (%0)" :: "r" (addr) : "memory")
+
+
+/*
+ * TLB flushing:
+ *
+ *  - flush_tlb() flushes the current mm struct TLBs
+ *  - flush_tlb_all() flushes all processes TLBs
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
+ *  - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
+ *
+ * x86-64 can only flush individual pages or full VMs. For a range flush
+ * we always do the full VM. Might be worth trying if for a small
+ * range a few INVLPGs in a row are a win.
+ */
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb() __flush_tlb()
+#define flush_tlb_all() __flush_tlb_all()
+#define local_flush_tlb() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+        if (mm == current->active_mm)
+                __flush_tlb();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+        unsigned long addr)
+{
+        if (vma->vm_mm == current->active_mm)
+                __flush_tlb_one(addr);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+        unsigned long start, unsigned long end)
+{
+        if (vma->vm_mm == current->active_mm)
+                __flush_tlb();
+}
+
+#else
+
+#include <asm/smp.h>
+
+#define local_flush_tlb() \
+        __flush_tlb()
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_current_task(void);
+extern void flush_tlb_mm(struct mm_struct *);
+extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+
+#define flush_tlb()     flush_tlb_current_task()
+
+static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long start, unsigned long end)
+{
+        flush_tlb_mm(vma->vm_mm);
+}
+
+#define TLBSTATE_OK     1
+#define TLBSTATE_LAZY   2
+
+/* Roughly an IPI every 20MB with 4k pages for freeing page table
+   ranges. Cost is about 42k of memory for each CPU. */
+#define ARCH_FREE_PTE_NR 5350   
+
+#endif
+
+static inline void flush_tlb_kernel_range(unsigned long start,
+                                        unsigned long end)
+{
+        flush_tlb_all();
+}
+
+static inline void flush_tlb_pgtables(struct mm_struct *mm,
+                                      unsigned long start, unsigned long end)
+{
+        /* x86_64 does not keep any page table caches in a software TLB.
+           The CPUs do in their hardware TLBs, but they are handled
+           by the normal TLB flushing algorithms. */
+}
+
+#endif /* _X8664_TLBFLUSH_H */
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
new file mode 100644
index 000000000000..b10fde9798ea
--- /dev/null
+++ b/include/asm-x86/topology.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "topology_32.h"
+#else
+# include "topology_64.h"
+#endif
diff --git a/include/asm-x86/topology_32.h b/include/asm-x86/topology_32.h
new file mode 100644
index 000000000000..19b2dafd0c81
--- /dev/null
+++ b/include/asm-x86/topology_32.h
@@ -0,0 +1,121 @@
+/*
+ * linux/include/asm-i386/topology.h
+ *
+ * Written by: Matthew Dobson, IBM Corporation
+ *
+ * Copyright (C) 2002, IBM Corp.
+ *
+ * All rights reserved.          
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <colpatch@us.ibm.com>
+ */
+#ifndef _ASM_I386_TOPOLOGY_H
+#define _ASM_I386_TOPOLOGY_H
+
+#ifdef CONFIG_X86_HT
+#define topology_physical_package_id(cpu)       (cpu_data[cpu].phys_proc_id)
+#define topology_core_id(cpu)                   (cpu_data[cpu].cpu_core_id)
+#define topology_core_siblings(cpu)             (cpu_core_map[cpu])
+#define topology_thread_siblings(cpu)           (cpu_sibling_map[cpu])
+#endif
+
+#ifdef CONFIG_NUMA
+
+#include <asm/mpspec.h>
+
+#include <linux/cpumask.h>
+
+/* Mappings between logical cpu number and node number */
+extern cpumask_t node_2_cpu_mask[];
+extern int cpu_2_node[];
+
+/* Returns the number of the node containing CPU 'cpu' */
+static inline int cpu_to_node(int cpu)
+{ 
+        return cpu_2_node[cpu];
+}
+
+/* Returns the number of the node containing Node 'node'.  This architecture is flat, 
+   so it is a pretty simple function! */
+#define parent_node(node) (node)
+
+/* Returns a bitmask of CPUs on Node 'node'. */
+static inline cpumask_t node_to_cpumask(int node)
+{
+        return node_2_cpu_mask[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) ((struct pci_sysdata *)((bus)->sysdata))->node
+#define pcibus_to_cpumask(bus) node_to_cpumask(pcibus_to_node(bus))
+
+/* sched_domains SD_NODE_INIT for NUMAQ machines */
+#define SD_NODE_INIT (struct sched_domain) {            \
+        .span                   = CPU_MASK_NONE,        \
+        .parent                 = NULL,                 \
+        .child                  = NULL,                 \
+        .groups                 = NULL,                 \
+        .min_interval           = 8,                    \
+        .max_interval           = 32,                   \
+        .busy_factor            = 32,                   \
+        .imbalance_pct          = 125,                  \
+        .cache_nice_tries       = 1,                    \
+        .busy_idx               = 3,                    \
+        .idle_idx               = 1,                    \
+        .newidle_idx            = 2,                    \
+        .wake_idx               = 1,                    \
+        .flags                  = SD_LOAD_BALANCE       \
+                                | SD_BALANCE_EXEC       \
+                                | SD_BALANCE_FORK       \
+                                | SD_SERIALIZE          \
+                                | SD_WAKE_BALANCE,      \
+        .last_balance           = jiffies,              \
+        .balance_interval       = 1,                    \
+        .nr_balance_failed      = 0,                    \
+}
+
+extern unsigned long node_start_pfn[];
+extern unsigned long node_end_pfn[];
+extern unsigned long node_remap_size[];
+
+#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
+
+#else /* !CONFIG_NUMA */
+/*
+ * Other i386 platforms should define their own version of the 
+ * above macros here.
+ */
+
+#include <asm-generic/topology.h>
+
+#endif /* CONFIG_NUMA */
+
+extern cpumask_t cpu_coregroup_map(int cpu);
+
+#ifdef CONFIG_SMP
+#define mc_capable()    (boot_cpu_data.x86_max_cores > 1)
+#define smt_capable()   (smp_num_siblings > 1)
+#endif
+
+#endif /* _ASM_I386_TOPOLOGY_H */
diff --git a/include/asm-x86/topology_64.h b/include/asm-x86/topology_64.h
new file mode 100644
index 000000000000..36e52fba7960
--- /dev/null
+++ b/include/asm-x86/topology_64.h
@@ -0,0 +1,71 @@
+#ifndef _ASM_X86_64_TOPOLOGY_H
+#define _ASM_X86_64_TOPOLOGY_H
+
+
+#ifdef CONFIG_NUMA
+
+#include <asm/mpspec.h>
+#include <asm/bitops.h>
+
+extern cpumask_t cpu_online_map;
+
+extern unsigned char cpu_to_node[];
+extern cpumask_t     node_to_cpumask[];
+
+#ifdef CONFIG_ACPI_NUMA
+extern int __node_distance(int, int);
+#define node_distance(a,b) __node_distance(a,b)
+/* #else fallback version */
+#endif
+
+#define cpu_to_node(cpu)                (cpu_to_node[cpu])
+#define parent_node(node)               (node)
+#define node_to_first_cpu(node)         (first_cpu(node_to_cpumask[node]))
+#define node_to_cpumask(node)           (node_to_cpumask[node])
+#define pcibus_to_node(bus)     ((struct pci_sysdata *)((bus)->sysdata))->node
+#define pcibus_to_cpumask(bus)          node_to_cpumask(pcibus_to_node(bus));
+
+#define numa_node_id()                  read_pda(nodenumber)
+
+/* sched_domains SD_NODE_INIT for x86_64 machines */
+#define SD_NODE_INIT (struct sched_domain) {            \
+        .span                   = CPU_MASK_NONE,        \
+        .parent                 = NULL,                 \
+        .child                  = NULL,                 \
+        .groups                 = NULL,                 \
+        .min_interval           = 8,                    \
+        .max_interval           = 32,                   \
+        .busy_factor            = 32,                   \
+        .imbalance_pct          = 125,                  \
+        .cache_nice_tries       = 2,                    \
+        .busy_idx               = 3,                    \
+        .idle_idx               = 2,                    \
+        .newidle_idx            = 0,                    \
+        .wake_idx               = 1,                    \
+        .forkexec_idx           = 1,                    \
+        .flags                  = SD_LOAD_BALANCE       \
+                                | SD_BALANCE_FORK       \
+                                | SD_BALANCE_EXEC       \
+                                | SD_SERIALIZE          \
+                                | SD_WAKE_BALANCE,      \
+        .last_balance           = jiffies,              \
+        .balance_interval       = 1,                    \
+        .nr_balance_failed      = 0,                    \
+}
+
+#endif
+
+#ifdef CONFIG_SMP
+#define topology_physical_package_id(cpu)       (cpu_data[cpu].phys_proc_id)
+#define topology_core_id(cpu)                   (cpu_data[cpu].cpu_core_id)
+#define topology_core_siblings(cpu)             (cpu_core_map[cpu])
+#define topology_thread_siblings(cpu)           (cpu_sibling_map[cpu])
+#define mc_capable()                    (boot_cpu_data.x86_max_cores > 1)
+#define smt_capable()                   (smp_num_siblings > 1)
+#endif
+
+#include <asm-generic/topology.h>
+
+extern cpumask_t cpu_coregroup_map(int cpu);
+
+#endif
diff --git a/include/asm-x86/tsc.h b/include/asm-x86/tsc.h
new file mode 100644
index 000000000000..a4d806610b7f
--- /dev/null
+++ b/include/asm-x86/tsc.h
@@ -0,0 +1,75 @@
+/*
+ * linux/include/asm-i386/tsc.h
+ *
+ * i386 TSC related functions
+ */
+#ifndef _ASM_i386_TSC_H
+#define _ASM_i386_TSC_H
+
+#include <asm/processor.h>
+
+/*
+ * Standard way to access the cycle counter.
+ */
+typedef unsigned long long cycles_t;
+
+extern unsigned int cpu_khz;
+extern unsigned int tsc_khz;
+
+static inline cycles_t get_cycles(void)
+{
+        unsigned long long ret = 0;
+
+#ifndef CONFIG_X86_TSC
+        if (!cpu_has_tsc)
+                return 0;
+#endif
+
+#if defined(CONFIG_X86_GENERIC) || defined(CONFIG_X86_TSC)
+        rdtscll(ret);
+#endif
+        return ret;
+}
+
+/* Like get_cycles, but make sure the CPU is synchronized. */
+static __always_inline cycles_t get_cycles_sync(void)
+{
+        unsigned long long ret;
+        unsigned eax, edx;
+
+        /*
+         * Use RDTSCP if possible; it is guaranteed to be synchronous
+         * and doesn't cause a VMEXIT on Hypervisors
+         */
+        alternative_io(ASM_NOP3, ".byte 0x0f,0x01,0xf9", X86_FEATURE_RDTSCP,
+                       ASM_OUTPUT2("=a" (eax), "=d" (edx)),
+                       "a" (0U), "d" (0U) : "ecx", "memory");
+        ret = (((unsigned long long)edx) << 32) | ((unsigned long long)eax);
+        if (ret)
+                return ret;
+
+        /*
+         * Don't do an additional sync on CPUs where we know
+         * RDTSC is already synchronous:
+         */
+        alternative_io("cpuid", ASM_NOP2, X86_FEATURE_SYNC_RDTSC,
+                          "=a" (eax), "0" (1) : "ebx","ecx","edx","memory");
+        rdtscll(ret);
+
+        return ret;
+}
+
+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);
+
+/*
+ * Boot-time check whether the TSCs are synchronized across
+ * all CPUs/cores:
+ */
+extern void check_tsc_sync_source(int cpu);
+extern void check_tsc_sync_target(void);
+
+#endif
diff --git a/include/asm-x86/types.h b/include/asm-x86/types.h
new file mode 100644
index 000000000000..a777a9b83974
--- /dev/null
+++ b/include/asm-x86/types.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "types_32.h"
+# else
+#  include "types_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "types_32.h"
+# else
+#  include "types_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/types_32.h b/include/asm-x86/types_32.h
new file mode 100644
index 000000000000..ad0a55bd782f
--- /dev/null
+++ b/include/asm-x86/types_32.h
@@ -0,0 +1,64 @@
+#ifndef _I386_TYPES_H
+#define _I386_TYPES_H
+
+#ifndef __ASSEMBLY__
+
+typedef unsigned short umode_t;
+
+/*
+ * __xx is ok: it doesn't pollute the POSIX namespace. Use these in the
+ * header files exported to user space
+ */
+
+typedef __signed__ char __s8;
+typedef unsigned char __u8;
+
+typedef __signed__ short __s16;
+typedef unsigned short __u16;
+
+typedef __signed__ int __s32;
+typedef unsigned int __u32;
+
+#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
+typedef __signed__ long long __s64;
+typedef unsigned long long __u64;
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifdef __KERNEL__
+
+#define BITS_PER_LONG 32
+
+#ifndef __ASSEMBLY__
+
+
+typedef signed char s8;
+typedef unsigned char u8;
+
+typedef signed short s16;
+typedef unsigned short u16;
+
+typedef signed int s32;
+typedef unsigned int u32;
+
+typedef signed long long s64;
+typedef unsigned long long u64;
+
+/* DMA addresses come in generic and 64-bit flavours.  */
+
+#ifdef CONFIG_HIGHMEM64G
+typedef u64 dma_addr_t;
+#else
+typedef u32 dma_addr_t;
+#endif
+typedef u64 dma64_addr_t;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/types_64.h b/include/asm-x86/types_64.h
new file mode 100644
index 000000000000..2d4491aae281
--- /dev/null
+++ b/include/asm-x86/types_64.h
@@ -0,0 +1,55 @@
+#ifndef _X86_64_TYPES_H
+#define _X86_64_TYPES_H
+
+#ifndef __ASSEMBLY__
+
+typedef unsigned short umode_t;
+
+/*
+ * __xx is ok: it doesn't pollute the POSIX namespace. Use these in the
+ * header files exported to user space
+ */
+
+typedef __signed__ char __s8;
+typedef unsigned char __u8;
+
+typedef __signed__ short __s16;
+typedef unsigned short __u16;
+
+typedef __signed__ int __s32;
+typedef unsigned int __u32;
+
+typedef __signed__ long long __s64;
+typedef unsigned long long  __u64;
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifdef __KERNEL__
+
+#define BITS_PER_LONG 64
+
+#ifndef __ASSEMBLY__
+
+typedef signed char s8;
+typedef unsigned char u8;
+
+typedef signed short s16;
+typedef unsigned short u16;
+
+typedef signed int s32;
+typedef unsigned int u32;
+
+typedef signed long long s64;
+typedef unsigned long long u64;
+
+typedef u64 dma64_addr_t;
+typedef u64 dma_addr_t;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/uaccess.h b/include/asm-x86/uaccess.h
new file mode 100644
index 000000000000..9fefd2947e78
--- /dev/null
+++ b/include/asm-x86/uaccess.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "uaccess_32.h"
+#else
+# include "uaccess_64.h"
+#endif
diff --git a/include/asm-x86/uaccess_32.h b/include/asm-x86/uaccess_32.h
new file mode 100644
index 000000000000..d2a4f7be9c2c
--- /dev/null
+++ b/include/asm-x86/uaccess_32.h
@@ -0,0 +1,590 @@
+#ifndef __i386_UACCESS_H
+#define __i386_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/errno.h>
+#include <linux/thread_info.h>
+#include <linux/prefetch.h>
+#include <linux/string.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"                                   \
+                ".section __ex_table,\"a\"\n"                   \
+                "       .align 4\n"                             \
+                "       .long 1b,4b\n"                          \
+                "       .long 2b,4b\n"                          \
+                ".previous"                                     \
+                : "=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"                                           \
+                ".section __ex_table,\"a\"\n"                           \
+                "       .align 4\n"                                     \
+                "       .long 1b,3b\n"                                  \
+                ".previous"                                             \
+                : "=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"                                           \
+                ".section __ex_table,\"a\"\n"                           \
+                "       .align 4\n"                                     \
+                "       .long 1b,3b\n"                                  \
+                ".previous"                                             \
+                : "=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(void *to,
+                                const void __user *from, unsigned long n);
+unsigned long __must_check __copy_from_user_ll_nozero(void *to,
+                                const void __user *from, unsigned long n);
+unsigned long __must_check __copy_from_user_ll_nocache(void *to,
+                                const void __user *from, unsigned long n);
+unsigned long __must_check __copy_from_user_ll_nocache_nozero(void *to,
+                                const void __user *from, unsigned long n);
+
+/**
+ * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.
+ *
+ * Copy data from kernel space to user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ * The caller should also make sure he pins the user space address
+ * so that the we don't result in page fault and sleep.
+ *
+ * Here we special-case 1, 2 and 4-byte copy_*_user invocations.  On a fault
+ * we return the initial request size (1, 2 or 4), as copy_*_user should do.
+ * If a store crosses a page boundary and gets a fault, the x86 will not write
+ * anything, so this is accurate.
+ */
+
+static __always_inline unsigned long __must_check
+__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
+{
+        if (__builtin_constant_p(n)) {
+                unsigned long ret;
+
+                switch (n) {
+                case 1:
+                        __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret, 1);
+                        return ret;
+                case 2:
+                        __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret, 2);
+                        return ret;
+                case 4:
+                        __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret, 4);
+                        return ret;
+                }
+        }
+        return __copy_to_user_ll(to, from, n);
+}
+
+/**
+ * __copy_to_user: - Copy a block of data into user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Copy data from kernel space to user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ */
+static __always_inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+       might_sleep();
+       return __copy_to_user_inatomic(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+        /* Avoid zeroing the tail if the copy fails..
+         * If 'n' is constant and 1, 2, or 4, we do still zero on a failure,
+         * but as the zeroing behaviour is only significant when n is not
+         * constant, that shouldn't be a problem.
+         */
+        if (__builtin_constant_p(n)) {
+                unsigned long ret;
+
+                switch (n) {
+                case 1:
+                        __get_user_size(*(u8 *)to, from, 1, ret, 1);
+                        return ret;
+                case 2:
+                        __get_user_size(*(u16 *)to, from, 2, ret, 2);
+                        return ret;
+                case 4:
+                        __get_user_size(*(u32 *)to, from, 4, ret, 4);
+                        return ret;
+                }
+        }
+        return __copy_from_user_ll_nozero(to, from, n);
+}
+
+/**
+ * __copy_from_user: - Copy a block of data from user space, with less checking.
+ * @to:   Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Copy data from user space to kernel space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ *
+ * An alternate version - __copy_from_user_inatomic() - may be called from
+ * atomic context and will fail rather than sleep.  In this case the
+ * uncopied bytes will *NOT* be padded with zeros.  See fs/filemap.h
+ * for explanation of why this is needed.
+ */
+static __always_inline unsigned long
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+        might_sleep();
+        if (__builtin_constant_p(n)) {
+                unsigned long ret;
+
+                switch (n) {
+                case 1:
+                        __get_user_size(*(u8 *)to, from, 1, ret, 1);
+                        return ret;
+                case 2:
+                        __get_user_size(*(u16 *)to, from, 2, ret, 2);
+                        return ret;
+                case 4:
+                        __get_user_size(*(u32 *)to, from, 4, ret, 4);
+                        return ret;
+                }
+        }
+        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)
+{
+        might_sleep();
+        if (__builtin_constant_p(n)) {
+                unsigned long ret;
+
+                switch (n) {
+                case 1:
+                        __get_user_size(*(u8 *)to, from, 1, ret, 1);
+                        return ret;
+                case 2:
+                        __get_user_size(*(u16 *)to, from, 2, ret, 2);
+                        return ret;
+                case 4:
+                        __get_user_size(*(u32 *)to, from, 4, ret, 4);
+                        return ret;
+                }
+        }
+        return __copy_from_user_ll_nocache(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n)
+{
+       return __copy_from_user_ll_nocache_nozero(to, from, n);
+}
+
+unsigned long __must_check copy_to_user(void __user *to,
+                                const void *from, unsigned long n);
+unsigned long __must_check copy_from_user(void *to,
+                                const void __user *from, unsigned long n);
+long __must_check strncpy_from_user(char *dst, const char __user *src,
+                                long count);
+long __must_check __strncpy_from_user(char *dst,
+                                const char __user *src, long count);
+
+/**
+ * strlen_user: - Get the size of a string in user space.
+ * @str: The string to measure.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * On exception, returns 0.
+ *
+ * If there is a limit on the length of a valid string, you may wish to
+ * consider using strnlen_user() instead.
+ */
+#define strlen_user(str) strnlen_user(str, LONG_MAX)
+
+long strnlen_user(const char __user *str, long n);
+unsigned long __must_check clear_user(void __user *mem, unsigned long len);
+unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
+
+#endif /* __i386_UACCESS_H */
diff --git a/include/asm-x86/uaccess_64.h b/include/asm-x86/uaccess_64.h
new file mode 100644
index 000000000000..f4ce8768ad44
--- /dev/null
+++ b/include/asm-x86/uaccess_64.h
@@ -0,0 +1,384 @@
+#ifndef __X86_64_UACCESS_H
+#define __X86_64_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#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;
+};
+
+#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"                                   \
+                ".section __ex_table,\"a\"\n"                   \
+                "       .align 8\n"                             \
+                "       .quad 1b,3b\n"                          \
+                ".previous"                                     \
+                : "=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"                                   \
+                ".section __ex_table,\"a\"\n"                   \
+                "       .align 8\n"                             \
+                "       .quad 1b,3b\n"                          \
+                ".previous"                                     \
+                : "=r"(err), ltype (x)                          \
+                : "m"(__m(addr)), "i"(errno), "0"(err))
+
+/*
+ * Copy To/From Userspace
+ */
+
+/* Handles exceptions in both to and from, but doesn't do access_ok */
+__must_check unsigned long
+copy_user_generic(void *to, const void *from, unsigned len);
+
+__must_check unsigned long
+copy_to_user(void __user *to, const void *from, unsigned len);
+__must_check unsigned long
+copy_from_user(void *to, const void __user *from, unsigned len);
+__must_check unsigned long
+copy_in_user(void __user *to, const void __user *from, unsigned len);
+
+static __always_inline __must_check
+int __copy_from_user(void *dst, const void __user *src, unsigned size)
+{ 
+        int ret = 0;
+        if (!__builtin_constant_p(size))
+                return copy_user_generic(dst,(__force void *)src,size);
+        switch (size) { 
+        case 1:__get_user_asm(*(u8*)dst,(u8 __user *)src,ret,"b","b","=q",1); 
+                return ret;
+        case 2:__get_user_asm(*(u16*)dst,(u16 __user *)src,ret,"w","w","=r",2);
+                return ret;
+        case 4:__get_user_asm(*(u32*)dst,(u32 __user *)src,ret,"l","k","=r",4);
+                return ret;
+        case 8:__get_user_asm(*(u64*)dst,(u64 __user *)src,ret,"q","","=r",8);
+                return ret; 
+        case 10:
+                __get_user_asm(*(u64*)dst,(u64 __user *)src,ret,"q","","=r",16);
+                if (unlikely(ret)) return ret;
+                __get_user_asm(*(u16*)(8+(char*)dst),(u16 __user *)(8+(char __user *)src),ret,"w","w","=r",2);
+                return ret; 
+        case 16:
+                __get_user_asm(*(u64*)dst,(u64 __user *)src,ret,"q","","=r",16);
+                if (unlikely(ret)) return ret;
+                __get_user_asm(*(u64*)(8+(char*)dst),(u64 __user *)(8+(char __user *)src),ret,"q","","=r",8);
+                return ret; 
+        default:
+                return copy_user_generic(dst,(__force void *)src,size); 
+        }
+}       
+
+static __always_inline __must_check
+int __copy_to_user(void __user *dst, const void *src, unsigned size)
+{ 
+        int ret = 0;
+        if (!__builtin_constant_p(size))
+                return copy_user_generic((__force void *)dst,src,size);
+        switch (size) { 
+        case 1:__put_user_asm(*(u8*)src,(u8 __user *)dst,ret,"b","b","iq",1); 
+                return ret;
+        case 2:__put_user_asm(*(u16*)src,(u16 __user *)dst,ret,"w","w","ir",2);
+                return ret;
+        case 4:__put_user_asm(*(u32*)src,(u32 __user *)dst,ret,"l","k","ir",4);
+                return ret;
+        case 8:__put_user_asm(*(u64*)src,(u64 __user *)dst,ret,"q","","ir",8);
+                return ret; 
+        case 10:
+                __put_user_asm(*(u64*)src,(u64 __user *)dst,ret,"q","","ir",10);
+                if (unlikely(ret)) return ret;
+                asm("":::"memory");
+                __put_user_asm(4[(u16*)src],4+(u16 __user *)dst,ret,"w","w","ir",2);
+                return ret; 
+        case 16:
+                __put_user_asm(*(u64*)src,(u64 __user *)dst,ret,"q","","ir",16);
+                if (unlikely(ret)) return ret;
+                asm("":::"memory");
+                __put_user_asm(1[(u64*)src],1+(u64 __user *)dst,ret,"q","","ir",8);
+                return ret; 
+        default:
+                return copy_user_generic((__force void *)dst,src,size); 
+        }
+}       
+
+static __always_inline __must_check
+int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
+{ 
+        int ret = 0;
+        if (!__builtin_constant_p(size))
+                return copy_user_generic((__force void *)dst,(__force void *)src,size);
+        switch (size) { 
+        case 1: { 
+                u8 tmp;
+                __get_user_asm(tmp,(u8 __user *)src,ret,"b","b","=q",1); 
+                if (likely(!ret))
+                        __put_user_asm(tmp,(u8 __user *)dst,ret,"b","b","iq",1); 
+                return ret;
+        }
+        case 2: { 
+                u16 tmp;
+                __get_user_asm(tmp,(u16 __user *)src,ret,"w","w","=r",2); 
+                if (likely(!ret))
+                        __put_user_asm(tmp,(u16 __user *)dst,ret,"w","w","ir",2); 
+                return ret;
+        }
+
+        case 4: { 
+                u32 tmp;
+                __get_user_asm(tmp,(u32 __user *)src,ret,"l","k","=r",4); 
+                if (likely(!ret))
+                        __put_user_asm(tmp,(u32 __user *)dst,ret,"l","k","ir",4); 
+                return ret;
+        }
+        case 8: { 
+                u64 tmp;
+                __get_user_asm(tmp,(u64 __user *)src,ret,"q","","=r",8); 
+                if (likely(!ret))
+                        __put_user_asm(tmp,(u64 __user *)dst,ret,"q","","ir",8); 
+                return ret;
+        }
+        default:
+                return copy_user_generic((__force void *)dst,(__force void *)src,size); 
+        }
+}       
+
+__must_check long 
+strncpy_from_user(char *dst, const char __user *src, long count);
+__must_check long 
+__strncpy_from_user(char *dst, const char __user *src, long count);
+__must_check long strnlen_user(const char __user *str, long n);
+__must_check long __strnlen_user(const char __user *str, long n);
+__must_check long strlen_user(const char __user *str);
+__must_check unsigned long clear_user(void __user *mem, unsigned long len);
+__must_check unsigned long __clear_user(void __user *mem, unsigned long len);
+
+__must_check long __copy_from_user_inatomic(void *dst, const void __user *src, unsigned size);
+
+static __must_check __always_inline int
+__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);
+
+static inline int __copy_from_user_nocache(void *dst, const void __user *src, unsigned size)
+{
+        might_sleep();
+        return __copy_user_nocache(dst, src, size, 1);
+}
+
+static inline int __copy_from_user_inatomic_nocache(void *dst, const void __user *src, unsigned size)
+{
+        return __copy_user_nocache(dst, src, size, 0);
+}
+
+#endif /* __X86_64_UACCESS_H */
diff --git a/include/asm-x86/ucontext.h b/include/asm-x86/ucontext.h
new file mode 100644
index 000000000000..175c8cb59731
--- /dev/null
+++ b/include/asm-x86/ucontext.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "ucontext_32.h"
+# else
+#  include "ucontext_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "ucontext_32.h"
+# else
+#  include "ucontext_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/ucontext_32.h b/include/asm-x86/ucontext_32.h
new file mode 100644
index 000000000000..b0db36925f55
--- /dev/null
+++ b/include/asm-x86/ucontext_32.h
@@ -0,0 +1,12 @@
+#ifndef _ASMi386_UCONTEXT_H
+#define _ASMi386_UCONTEXT_H
+
+struct ucontext {
+        unsigned long     uc_flags;
+        struct ucontext  *uc_link;
+        stack_t           uc_stack;
+        struct sigcontext uc_mcontext;
+        sigset_t          uc_sigmask;   /* mask last for extensibility */
+};
+
+#endif /* !_ASMi386_UCONTEXT_H */
diff --git a/include/asm-x86/ucontext_64.h b/include/asm-x86/ucontext_64.h
new file mode 100644
index 000000000000..159a3da9e112
--- /dev/null
+++ b/include/asm-x86/ucontext_64.h
@@ -0,0 +1,12 @@
+#ifndef _ASMX8664_UCONTEXT_H
+#define _ASMX8664_UCONTEXT_H
+
+struct ucontext {
+        unsigned long     uc_flags;
+        struct ucontext  *uc_link;
+        stack_t           uc_stack;
+        struct sigcontext uc_mcontext;
+        sigset_t          uc_sigmask;   /* mask last for extensibility */
+};
+
+#endif
diff --git a/include/asm-x86/unaligned.h b/include/asm-x86/unaligned.h
new file mode 100644
index 000000000000..68067150fbcb
--- /dev/null
+++ b/include/asm-x86/unaligned.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "unaligned_32.h"
+#else
+# include "unaligned_64.h"
+#endif
diff --git a/include/asm-x86/unaligned_32.h b/include/asm-x86/unaligned_32.h
new file mode 100644
index 000000000000..7acd7957621e
--- /dev/null
+++ b/include/asm-x86/unaligned_32.h
@@ -0,0 +1,37 @@
+#ifndef __I386_UNALIGNED_H
+#define __I386_UNALIGNED_H
+
+/*
+ * The i386 can do unaligned accesses itself. 
+ *
+ * The strange macros are there to make sure these can't
+ * be misused in a way that makes them not work on other
+ * architectures where unaligned accesses aren't as simple.
+ */
+
+/**
+ * get_unaligned - get value from possibly mis-aligned location
+ * @ptr: pointer to value
+ *
+ * This macro should be used for accessing values larger in size than 
+ * single bytes at locations that are expected to be improperly aligned, 
+ * e.g. retrieving a u16 value from a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define get_unaligned(ptr) (*(ptr))
+
+/**
+ * put_unaligned - put value to a possibly mis-aligned location
+ * @val: value to place
+ * @ptr: pointer to location
+ *
+ * This macro should be used for placing values larger in size than 
+ * single bytes at locations that are expected to be improperly aligned, 
+ * e.g. writing a u16 value to a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
+
+#endif
diff --git a/include/asm-x86/unaligned_64.h b/include/asm-x86/unaligned_64.h
new file mode 100644
index 000000000000..d4bf78dc6f39
--- /dev/null
+++ b/include/asm-x86/unaligned_64.h
@@ -0,0 +1,37 @@
+#ifndef __X8664_UNALIGNED_H
+#define __X8664_UNALIGNED_H
+
+/*
+ * The x86-64 can do unaligned accesses itself. 
+ *
+ * The strange macros are there to make sure these can't
+ * be misused in a way that makes them not work on other
+ * architectures where unaligned accesses aren't as simple.
+ */
+
+/**
+ * get_unaligned - get value from possibly mis-aligned location
+ * @ptr: pointer to value
+ *
+ * This macro should be used for accessing values larger in size than 
+ * single bytes at locations that are expected to be improperly aligned, 
+ * e.g. retrieving a u16 value from a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define get_unaligned(ptr) (*(ptr))
+
+/**
+ * put_unaligned - put value to a possibly mis-aligned location
+ * @val: value to place
+ * @ptr: pointer to location
+ *
+ * This macro should be used for placing values larger in size than 
+ * single bytes at locations that are expected to be improperly aligned, 
+ * e.g. writing a u16 value to a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
+
+#endif
diff --git a/include/asm-x86/unistd.h b/include/asm-x86/unistd.h
new file mode 100644
index 000000000000..2a58ed3e51d8
--- /dev/null
+++ b/include/asm-x86/unistd.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "unistd_32.h"
+# else
+#  include "unistd_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "unistd_32.h"
+# else
+#  include "unistd_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h
new file mode 100644
index 000000000000..9b15545eb9b5
--- /dev/null
+++ b/include/asm-x86/unistd_32.h
@@ -0,0 +1,373 @@
+#ifndef _ASM_I386_UNISTD_H_
+#define _ASM_I386_UNISTD_H_
+
+/*
+ * This file contains the system call numbers.
+ */
+
+#define __NR_restart_syscall      0
+#define __NR_exit                 1
+#define __NR_fork                 2
+#define __NR_read                 3
+#define __NR_write                4
+#define __NR_open                 5
+#define __NR_close                6
+#define __NR_waitpid              7
+#define __NR_creat                8
+#define __NR_link                 9
+#define __NR_unlink              10
+#define __NR_execve              11
+#define __NR_chdir               12
+#define __NR_time                13
+#define __NR_mknod               14
+#define __NR_chmod               15
+#define __NR_lchown              16
+#define __NR_break               17
+#define __NR_oldstat             18
+#define __NR_lseek               19
+#define __NR_getpid              20
+#define __NR_mount               21
+#define __NR_umount              22
+#define __NR_setuid              23
+#define __NR_getuid              24
+#define __NR_stime               25
+#define __NR_ptrace              26
+#define __NR_alarm               27
+#define __NR_oldfstat            28
+#define __NR_pause               29
+#define __NR_utime               30
+#define __NR_stty                31
+#define __NR_gtty                32
+#define __NR_access              33
+#define __NR_nice                34
+#define __NR_ftime               35
+#define __NR_sync                36
+#define __NR_kill                37
+#define __NR_rename              38
+#define __NR_mkdir               39
+#define __NR_rmdir               40
+#define __NR_dup                 41
+#define __NR_pipe                42
+#define __NR_times               43
+#define __NR_prof                44
+#define __NR_brk                 45
+#define __NR_setgid              46
+#define __NR_getgid              47
+#define __NR_signal              48
+#define __NR_geteuid             49
+#define __NR_getegid             50
+#define __NR_acct                51
+#define __NR_umount2             52
+#define __NR_lock                53
+#define __NR_ioctl               54
+#define __NR_fcntl               55
+#define __NR_mpx                 56
+#define __NR_setpgid             57
+#define __NR_ulimit              58
+#define __NR_oldolduname         59
+#define __NR_umask               60
+#define __NR_chroot              61
+#define __NR_ustat               62
+#define __NR_dup2                63
+#define __NR_getppid             64
+#define __NR_getpgrp             65
+#define __NR_setsid              66
+#define __NR_sigaction           67
+#define __NR_sgetmask            68
+#define __NR_ssetmask            69
+#define __NR_setreuid            70
+#define __NR_setregid            71
+#define __NR_sigsuspend          72
+#define __NR_sigpending          73
+#define __NR_sethostname         74
+#define __NR_setrlimit           75
+#define __NR_getrlimit           76     /* Back compatible 2Gig limited rlimit */
+#define __NR_getrusage           77
+#define __NR_gettimeofday        78
+#define __NR_settimeofday        79
+#define __NR_getgroups           80
+#define __NR_setgroups           81
+#define __NR_select              82
+#define __NR_symlink             83
+#define __NR_oldlstat            84
+#define __NR_readlink            85
+#define __NR_uselib              86
+#define __NR_swapon              87
+#define __NR_reboot              88
+#define __NR_readdir             89
+#define __NR_mmap                90
+#define __NR_munmap              91
+#define __NR_truncate            92
+#define __NR_ftruncate           93
+#define __NR_fchmod              94
+#define __NR_fchown              95
+#define __NR_getpriority         96
+#define __NR_setpriority         97
+#define __NR_profil              98
+#define __NR_statfs              99
+#define __NR_fstatfs            100
+#define __NR_ioperm             101
+#define __NR_socketcall         102
+#define __NR_syslog             103
+#define __NR_setitimer          104
+#define __NR_getitimer          105
+#define __NR_stat               106
+#define __NR_lstat              107
+#define __NR_fstat              108
+#define __NR_olduname           109
+#define __NR_iopl               110
+#define __NR_vhangup            111
+#define __NR_idle               112
+#define __NR_vm86old            113
+#define __NR_wait4              114
+#define __NR_swapoff            115
+#define __NR_sysinfo            116
+#define __NR_ipc                117
+#define __NR_fsync              118
+#define __NR_sigreturn          119
+#define __NR_clone              120
+#define __NR_setdomainname      121
+#define __NR_uname              122
+#define __NR_modify_ldt         123
+#define __NR_adjtimex           124
+#define __NR_mprotect           125
+#define __NR_sigprocmask        126
+#define __NR_create_module      127
+#define __NR_init_module        128
+#define __NR_delete_module      129
+#define __NR_get_kernel_syms    130
+#define __NR_quotactl           131
+#define __NR_getpgid            132
+#define __NR_fchdir             133
+#define __NR_bdflush            134
+#define __NR_sysfs              135
+#define __NR_personality        136
+#define __NR_afs_syscall        137 /* Syscall for Andrew File System */
+#define __NR_setfsuid           138
+#define __NR_setfsgid           139
+#define __NR__llseek            140
+#define __NR_getdents           141
+#define __NR__newselect         142
+#define __NR_flock              143
+#define __NR_msync              144
+#define __NR_readv              145
+#define __NR_writev             146
+#define __NR_getsid             147
+#define __NR_fdatasync          148
+#define __NR__sysctl            149
+#define __NR_mlock              150
+#define __NR_munlock            151
+#define __NR_mlockall           152
+#define __NR_munlockall         153
+#define __NR_sched_setparam             154
+#define __NR_sched_getparam             155
+#define __NR_sched_setscheduler         156
+#define __NR_sched_getscheduler         157
+#define __NR_sched_yield                158
+#define __NR_sched_get_priority_max     159
+#define __NR_sched_get_priority_min     160
+#define __NR_sched_rr_get_interval      161
+#define __NR_nanosleep          162
+#define __NR_mremap             163
+#define __NR_setresuid          164
+#define __NR_getresuid          165
+#define __NR_vm86               166
+#define __NR_query_module       167
+#define __NR_poll               168
+#define __NR_nfsservctl         169
+#define __NR_setresgid          170
+#define __NR_getresgid          171
+#define __NR_prctl              172
+#define __NR_rt_sigreturn       173
+#define __NR_rt_sigaction       174
+#define __NR_rt_sigprocmask     175
+#define __NR_rt_sigpending      176
+#define __NR_rt_sigtimedwait    177
+#define __NR_rt_sigqueueinfo    178
+#define __NR_rt_sigsuspend      179
+#define __NR_pread64            180
+#define __NR_pwrite64           181
+#define __NR_chown              182
+#define __NR_getcwd             183
+#define __NR_capget             184
+#define __NR_capset             185
+#define __NR_sigaltstack        186
+#define __NR_sendfile           187
+#define __NR_getpmsg            188     /* some people actually want streams */
+#define __NR_putpmsg            189     /* some people actually want streams */
+#define __NR_vfork              190
+#define __NR_ugetrlimit         191     /* SuS compliant getrlimit */
+#define __NR_mmap2              192
+#define __NR_truncate64         193
+#define __NR_ftruncate64        194
+#define __NR_stat64             195
+#define __NR_lstat64            196
+#define __NR_fstat64            197
+#define __NR_lchown32           198
+#define __NR_getuid32           199
+#define __NR_getgid32           200
+#define __NR_geteuid32          201
+#define __NR_getegid32          202
+#define __NR_setreuid32         203
+#define __NR_setregid32         204
+#define __NR_getgroups32        205
+#define __NR_setgroups32        206
+#define __NR_fchown32           207
+#define __NR_setresuid32        208
+#define __NR_getresuid32        209
+#define __NR_setresgid32        210
+#define __NR_getresgid32        211
+#define __NR_chown32            212
+#define __NR_setuid32           213
+#define __NR_setgid32           214
+#define __NR_setfsuid32         215
+#define __NR_setfsgid32         216
+#define __NR_pivot_root         217
+#define __NR_mincore            218
+#define __NR_madvise            219
+#define __NR_madvise1           219     /* delete when C lib stub is removed */
+#define __NR_getdents64         220
+#define __NR_fcntl64            221
+/* 223 is unused */
+#define __NR_gettid             224
+#define __NR_readahead          225
+#define __NR_setxattr           226
+#define __NR_lsetxattr          227
+#define __NR_fsetxattr          228
+#define __NR_getxattr           229
+#define __NR_lgetxattr          230
+#define __NR_fgetxattr          231
+#define __NR_listxattr          232
+#define __NR_llistxattr         233
+#define __NR_flistxattr         234
+#define __NR_removexattr        235
+#define __NR_lremovexattr       236
+#define __NR_fremovexattr       237
+#define __NR_tkill              238
+#define __NR_sendfile64         239
+#define __NR_futex              240
+#define __NR_sched_setaffinity  241
+#define __NR_sched_getaffinity  242
+#define __NR_set_thread_area    243
+#define __NR_get_thread_area    244
+#define __NR_io_setup           245
+#define __NR_io_destroy         246
+#define __NR_io_getevents       247
+#define __NR_io_submit          248
+#define __NR_io_cancel          249
+#define __NR_fadvise64          250
+/* 251 is available for reuse (was briefly sys_set_zone_reclaim) */
+#define __NR_exit_group         252
+#define __NR_lookup_dcookie     253
+#define __NR_epoll_create       254
+#define __NR_epoll_ctl          255
+#define __NR_epoll_wait         256
+#define __NR_remap_file_pages   257
+#define __NR_set_tid_address    258
+#define __NR_timer_create       259
+#define __NR_timer_settime      (__NR_timer_create+1)
+#define __NR_timer_gettime      (__NR_timer_create+2)
+#define __NR_timer_getoverrun   (__NR_timer_create+3)
+#define __NR_timer_delete       (__NR_timer_create+4)
+#define __NR_clock_settime      (__NR_timer_create+5)
+#define __NR_clock_gettime      (__NR_timer_create+6)
+#define __NR_clock_getres       (__NR_timer_create+7)
+#define __NR_clock_nanosleep    (__NR_timer_create+8)
+#define __NR_statfs64           268
+#define __NR_fstatfs64          269
+#define __NR_tgkill             270
+#define __NR_utimes             271
+#define __NR_fadvise64_64       272
+#define __NR_vserver            273
+#define __NR_mbind              274
+#define __NR_get_mempolicy      275
+#define __NR_set_mempolicy      276
+#define __NR_mq_open            277
+#define __NR_mq_unlink          (__NR_mq_open+1)
+#define __NR_mq_timedsend       (__NR_mq_open+2)
+#define __NR_mq_timedreceive    (__NR_mq_open+3)
+#define __NR_mq_notify          (__NR_mq_open+4)
+#define __NR_mq_getsetattr      (__NR_mq_open+5)
+#define __NR_kexec_load         283
+#define __NR_waitid             284
+/* #define __NR_sys_setaltroot  285 */
+#define __NR_add_key            286
+#define __NR_request_key        287
+#define __NR_keyctl             288
+#define __NR_ioprio_set         289
+#define __NR_ioprio_get         290
+#define __NR_inotify_init       291
+#define __NR_inotify_add_watch  292
+#define __NR_inotify_rm_watch   293
+#define __NR_migrate_pages      294
+#define __NR_openat             295
+#define __NR_mkdirat            296
+#define __NR_mknodat            297
+#define __NR_fchownat           298
+#define __NR_futimesat          299
+#define __NR_fstatat64          300
+#define __NR_unlinkat           301
+#define __NR_renameat           302
+#define __NR_linkat             303
+#define __NR_symlinkat          304
+#define __NR_readlinkat         305
+#define __NR_fchmodat           306
+#define __NR_faccessat          307
+#define __NR_pselect6           308
+#define __NR_ppoll              309
+#define __NR_unshare            310
+#define __NR_set_robust_list    311
+#define __NR_get_robust_list    312
+#define __NR_splice             313
+#define __NR_sync_file_range    314
+#define __NR_tee                315
+#define __NR_vmsplice           316
+#define __NR_move_pages         317
+#define __NR_getcpu             318
+#define __NR_epoll_pwait        319
+#define __NR_utimensat          320
+#define __NR_signalfd           321
+#define __NR_timerfd            322
+#define __NR_eventfd            323
+#define __NR_fallocate          324
+
+#ifdef __KERNEL__
+
+#define NR_syscalls 325
+
+#define __ARCH_WANT_IPC_PARSE_VERSION
+#define __ARCH_WANT_OLD_READDIR
+#define __ARCH_WANT_OLD_STAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SYS_ALARM
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_SGETMASK
+#define __ARCH_WANT_SYS_SIGNAL
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_WAITPID
+#define __ARCH_WANT_SYS_SOCKETCALL
+#define __ARCH_WANT_SYS_FADVISE64
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLDUMOUNT
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_SYS_RT_SIGACTION
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
+
+/*
+ * "Conditional" syscalls
+ *
+ * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
+ * but it doesn't work on all toolchains, so we just do it by hand
+ */
+#ifndef cond_syscall
+#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_I386_UNISTD_H_ */
diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h
new file mode 100644
index 000000000000..fc4e73f5f1fa
--- /dev/null
+++ b/include/asm-x86/unistd_64.h
@@ -0,0 +1,687 @@
+#ifndef _ASM_X86_64_UNISTD_H_
+#define _ASM_X86_64_UNISTD_H_
+
+#ifndef __SYSCALL
+#define __SYSCALL(a,b) 
+#endif
+
+/*
+ * This file contains the system call numbers.
+ * 
+ * Note: holes are not allowed.
+ */
+
+/* at least 8 syscall per cacheline */
+#define __NR_read                                0
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write                               1
+__SYSCALL(__NR_write, sys_write)
+#define __NR_open                                2
+__SYSCALL(__NR_open, sys_open)
+#define __NR_close                               3
+__SYSCALL(__NR_close, sys_close)
+#define __NR_stat                                4
+__SYSCALL(__NR_stat, sys_newstat)
+#define __NR_fstat                               5
+__SYSCALL(__NR_fstat, sys_newfstat)
+#define __NR_lstat                               6
+__SYSCALL(__NR_lstat, sys_newlstat)
+#define __NR_poll                                7
+__SYSCALL(__NR_poll, sys_poll)
+
+#define __NR_lseek                               8
+__SYSCALL(__NR_lseek, sys_lseek)
+#define __NR_mmap                                9
+__SYSCALL(__NR_mmap, sys_mmap)
+#define __NR_mprotect                           10
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_munmap                             11
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_brk                                12
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_rt_sigaction                       13
+__SYSCALL(__NR_rt_sigaction, sys_rt_sigaction)
+#define __NR_rt_sigprocmask                     14
+__SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask)
+#define __NR_rt_sigreturn                       15
+__SYSCALL(__NR_rt_sigreturn, stub_rt_sigreturn)
+
+#define __NR_ioctl                              16
+__SYSCALL(__NR_ioctl, sys_ioctl)
+#define __NR_pread64                            17
+__SYSCALL(__NR_pread64, sys_pread64)
+#define __NR_pwrite64                           18
+__SYSCALL(__NR_pwrite64, sys_pwrite64)
+#define __NR_readv                              19
+__SYSCALL(__NR_readv, sys_readv)
+#define __NR_writev                             20
+__SYSCALL(__NR_writev, sys_writev)
+#define __NR_access                             21
+__SYSCALL(__NR_access, sys_access)
+#define __NR_pipe                               22
+__SYSCALL(__NR_pipe, sys_pipe)
+#define __NR_select                             23
+__SYSCALL(__NR_select, sys_select)
+
+#define __NR_sched_yield                        24
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_mremap                             25
+__SYSCALL(__NR_mremap, sys_mremap)
+#define __NR_msync                              26
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mincore                            27
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise                            28
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_shmget                             29
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmat                              30
+__SYSCALL(__NR_shmat, sys_shmat)
+#define __NR_shmctl                             31
+__SYSCALL(__NR_shmctl, sys_shmctl)
+
+#define __NR_dup                                32
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup2                               33
+__SYSCALL(__NR_dup2, sys_dup2)
+#define __NR_pause                              34
+__SYSCALL(__NR_pause, sys_pause)
+#define __NR_nanosleep                          35
+__SYSCALL(__NR_nanosleep, sys_nanosleep)
+#define __NR_getitimer                          36
+__SYSCALL(__NR_getitimer, sys_getitimer)
+#define __NR_alarm                              37
+__SYSCALL(__NR_alarm, sys_alarm)
+#define __NR_setitimer                          38
+__SYSCALL(__NR_setitimer, sys_setitimer)
+#define __NR_getpid                             39
+__SYSCALL(__NR_getpid, sys_getpid)
+
+#define __NR_sendfile                           40
+__SYSCALL(__NR_sendfile, sys_sendfile64)
+#define __NR_socket                             41
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_connect                            42
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_accept                             43
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_sendto                             44
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom                           45
+__SYSCALL(__NR_recvfrom, sys_recvfrom)
+#define __NR_sendmsg                            46
+__SYSCALL(__NR_sendmsg, sys_sendmsg)
+#define __NR_recvmsg                            47
+__SYSCALL(__NR_recvmsg, sys_recvmsg)
+
+#define __NR_shutdown                           48
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_bind                               49
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen                             50
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_getsockname                        51
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername                        52
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_socketpair                         53
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_setsockopt                         54
+__SYSCALL(__NR_setsockopt, sys_setsockopt)
+#define __NR_getsockopt                         55
+__SYSCALL(__NR_getsockopt, sys_getsockopt)
+
+#define __NR_clone                              56
+__SYSCALL(__NR_clone, stub_clone)
+#define __NR_fork                               57
+__SYSCALL(__NR_fork, stub_fork) 
+#define __NR_vfork                              58
+__SYSCALL(__NR_vfork, stub_vfork)
+#define __NR_execve                             59
+__SYSCALL(__NR_execve, stub_execve)
+#define __NR_exit                               60
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_wait4                              61
+__SYSCALL(__NR_wait4, sys_wait4)
+#define __NR_kill                               62
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_uname                              63
+__SYSCALL(__NR_uname, sys_uname)
+
+#define __NR_semget                             64
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semop                              65
+__SYSCALL(__NR_semop, sys_semop)
+#define __NR_semctl                             66
+__SYSCALL(__NR_semctl, sys_semctl)
+#define __NR_shmdt                              67
+__SYSCALL(__NR_shmdt, sys_shmdt)
+#define __NR_msgget                             68
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgsnd                             69
+__SYSCALL(__NR_msgsnd, sys_msgsnd)
+#define __NR_msgrcv                             70
+__SYSCALL(__NR_msgrcv, sys_msgrcv)
+#define __NR_msgctl                             71
+__SYSCALL(__NR_msgctl, sys_msgctl)
+
+#define __NR_fcntl                              72
+__SYSCALL(__NR_fcntl, sys_fcntl)
+#define __NR_flock                              73
+__SYSCALL(__NR_flock, sys_flock)
+#define __NR_fsync                              74
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync                          75
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#define __NR_truncate                           76
+__SYSCALL(__NR_truncate, sys_truncate)
+#define __NR_ftruncate                          77
+__SYSCALL(__NR_ftruncate, sys_ftruncate)
+#define __NR_getdents                           78
+__SYSCALL(__NR_getdents, sys_getdents)
+#define __NR_getcwd                             79
+__SYSCALL(__NR_getcwd, sys_getcwd)
+
+#define __NR_chdir                              80
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir                             81
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_rename                             82
+__SYSCALL(__NR_rename, sys_rename)
+#define __NR_mkdir                              83
+__SYSCALL(__NR_mkdir, sys_mkdir)
+#define __NR_rmdir                              84
+__SYSCALL(__NR_rmdir, sys_rmdir)
+#define __NR_creat                              85
+__SYSCALL(__NR_creat, sys_creat)
+#define __NR_link                               86
+__SYSCALL(__NR_link, sys_link)
+#define __NR_unlink                             87
+__SYSCALL(__NR_unlink, sys_unlink)
+
+#define __NR_symlink                            88
+__SYSCALL(__NR_symlink, sys_symlink)
+#define __NR_readlink                           89
+__SYSCALL(__NR_readlink, sys_readlink)
+#define __NR_chmod                              90
+__SYSCALL(__NR_chmod, sys_chmod)
+#define __NR_fchmod                             91
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_chown                              92
+__SYSCALL(__NR_chown, sys_chown)
+#define __NR_fchown                             93
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_lchown                             94
+__SYSCALL(__NR_lchown, sys_lchown)
+#define __NR_umask                              95
+__SYSCALL(__NR_umask, sys_umask)
+
+#define __NR_gettimeofday                       96
+__SYSCALL(__NR_gettimeofday, sys_gettimeofday)
+#define __NR_getrlimit                          97
+__SYSCALL(__NR_getrlimit, sys_getrlimit)
+#define __NR_getrusage                          98
+__SYSCALL(__NR_getrusage, sys_getrusage)
+#define __NR_sysinfo                            99
+__SYSCALL(__NR_sysinfo, sys_sysinfo)
+#define __NR_times                             100
+__SYSCALL(__NR_times, sys_times)
+#define __NR_ptrace                            101
+__SYSCALL(__NR_ptrace, sys_ptrace)
+#define __NR_getuid                            102
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_syslog                            103
+__SYSCALL(__NR_syslog, sys_syslog)
+
+/* at the very end the stuff that never runs during the benchmarks */
+#define __NR_getgid                            104
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_setuid                            105
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setgid                            106
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_geteuid                           107
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getegid                           108
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_setpgid                           109
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getppid                           110
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getpgrp                           111
+__SYSCALL(__NR_getpgrp, sys_getpgrp)
+
+#define __NR_setsid                            112
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_setreuid                          113
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setregid                          114
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_getgroups                         115
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups                         116
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_setresuid                         117
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid                         118
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid                         119
+__SYSCALL(__NR_setresgid, sys_setresgid)
+
+#define __NR_getresgid                         120
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_getpgid                           121
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_setfsuid                          122
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid                          123
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_getsid                            124
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_capget                            125
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset                            126
+__SYSCALL(__NR_capset, sys_capset)
+
+#define __NR_rt_sigpending                     127
+__SYSCALL(__NR_rt_sigpending, sys_rt_sigpending)
+#define __NR_rt_sigtimedwait                   128
+__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)
+#define __NR_sigaltstack                       131
+__SYSCALL(__NR_sigaltstack, stub_sigaltstack)
+#define __NR_utime                             132
+__SYSCALL(__NR_utime, sys_utime)
+#define __NR_mknod                             133
+__SYSCALL(__NR_mknod, sys_mknod)
+
+/* Only needed for a.out */
+#define __NR_uselib                            134
+__SYSCALL(__NR_uselib, sys_ni_syscall)
+#define __NR_personality                       135
+__SYSCALL(__NR_personality, sys_personality)
+
+#define __NR_ustat                             136
+__SYSCALL(__NR_ustat, sys_ustat)
+#define __NR_statfs                            137
+__SYSCALL(__NR_statfs, sys_statfs)
+#define __NR_fstatfs                           138
+__SYSCALL(__NR_fstatfs, sys_fstatfs)
+#define __NR_sysfs                             139
+__SYSCALL(__NR_sysfs, sys_sysfs)
+
+#define __NR_getpriority                       140
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_setpriority                       141
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_sched_setparam                    142
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_getparam                    143
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setscheduler                144
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler                145
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_get_priority_max            146
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min            147
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval             148
+__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval)
+
+#define __NR_mlock                             149
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock                           150
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall                          151
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall                        152
+__SYSCALL(__NR_munlockall, sys_munlockall)
+
+#define __NR_vhangup                           153
+__SYSCALL(__NR_vhangup, sys_vhangup)
+
+#define __NR_modify_ldt                        154
+__SYSCALL(__NR_modify_ldt, sys_modify_ldt)
+
+#define __NR_pivot_root                        155
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+
+#define __NR__sysctl                           156
+__SYSCALL(__NR__sysctl, sys_sysctl)
+
+#define __NR_prctl                             157
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_arch_prctl                        158
+__SYSCALL(__NR_arch_prctl,      sys_arch_prctl) 
+
+#define __NR_adjtimex                          159
+__SYSCALL(__NR_adjtimex, sys_adjtimex)
+
+#define __NR_setrlimit                         160
+__SYSCALL(__NR_setrlimit, sys_setrlimit)
+
+#define __NR_chroot                            161
+__SYSCALL(__NR_chroot, sys_chroot)
+
+#define __NR_sync                              162
+__SYSCALL(__NR_sync, sys_sync)
+
+#define __NR_acct                              163
+__SYSCALL(__NR_acct, sys_acct)
+
+#define __NR_settimeofday                      164
+__SYSCALL(__NR_settimeofday, sys_settimeofday)
+
+#define __NR_mount                             165
+__SYSCALL(__NR_mount, sys_mount)
+#define __NR_umount2                           166
+__SYSCALL(__NR_umount2, sys_umount)
+
+#define __NR_swapon                            167
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff                           168
+__SYSCALL(__NR_swapoff, sys_swapoff)
+
+#define __NR_reboot                            169
+__SYSCALL(__NR_reboot, sys_reboot)
+
+#define __NR_sethostname                       170
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname                     171
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+
+#define __NR_iopl                              172
+__SYSCALL(__NR_iopl, stub_iopl)
+#define __NR_ioperm                            173
+__SYSCALL(__NR_ioperm, sys_ioperm)
+
+#define __NR_create_module                     174
+__SYSCALL(__NR_create_module, sys_ni_syscall)
+#define __NR_init_module                       175
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module                     176
+__SYSCALL(__NR_delete_module, sys_delete_module)
+#define __NR_get_kernel_syms                   177
+__SYSCALL(__NR_get_kernel_syms, sys_ni_syscall)
+#define __NR_query_module                      178
+__SYSCALL(__NR_query_module, sys_ni_syscall)
+
+#define __NR_quotactl                          179
+__SYSCALL(__NR_quotactl, sys_quotactl)
+
+#define __NR_nfsservctl                        180
+__SYSCALL(__NR_nfsservctl, sys_nfsservctl)
+
+#define __NR_getpmsg                           181      /* reserved for LiS/STREAMS */
+__SYSCALL(__NR_getpmsg, sys_ni_syscall)
+#define __NR_putpmsg                           182      /* reserved for LiS/STREAMS */
+__SYSCALL(__NR_putpmsg, sys_ni_syscall)
+
+#define __NR_afs_syscall                       183      /* reserved for AFS */ 
+__SYSCALL(__NR_afs_syscall, sys_ni_syscall)
+
+#define __NR_tuxcall                    184 /* reserved for tux */
+__SYSCALL(__NR_tuxcall, sys_ni_syscall)
+
+#define __NR_security                   185
+__SYSCALL(__NR_security, sys_ni_syscall)
+
+#define __NR_gettid             186
+__SYSCALL(__NR_gettid, sys_gettid)
+
+#define __NR_readahead          187
+__SYSCALL(__NR_readahead, sys_readahead)
+#define __NR_setxattr           188
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr          189
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr          190
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr           191
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr          192
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr          193
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr) 
+#define __NR_listxattr          194
+__SYSCALL(__NR_listxattr, sys_listxattr) 
+#define __NR_llistxattr         195
+__SYSCALL(__NR_llistxattr, sys_llistxattr) 
+#define __NR_flistxattr         196
+__SYSCALL(__NR_flistxattr, sys_flistxattr) 
+#define __NR_removexattr        197
+__SYSCALL(__NR_removexattr, sys_removexattr) 
+#define __NR_lremovexattr       198
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr) 
+#define __NR_fremovexattr       199
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr) 
+#define __NR_tkill      200
+__SYSCALL(__NR_tkill, sys_tkill) 
+#define __NR_time      201
+__SYSCALL(__NR_time, sys_time)
+#define __NR_futex     202
+__SYSCALL(__NR_futex, sys_futex)
+#define __NR_sched_setaffinity    203
+__SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity)
+#define __NR_sched_getaffinity     204
+__SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity)
+#define __NR_set_thread_area    205
+__SYSCALL(__NR_set_thread_area, sys_ni_syscall) /* use arch_prctl */
+#define __NR_io_setup   206
+__SYSCALL(__NR_io_setup, sys_io_setup)
+#define __NR_io_destroy 207
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_getevents       208
+__SYSCALL(__NR_io_getevents, sys_io_getevents)
+#define __NR_io_submit  209
+__SYSCALL(__NR_io_submit, sys_io_submit)
+#define __NR_io_cancel  210
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_get_thread_area    211
+__SYSCALL(__NR_get_thread_area, sys_ni_syscall) /* use arch_prctl */
+#define __NR_lookup_dcookie     212
+__SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie)
+#define __NR_epoll_create       213
+__SYSCALL(__NR_epoll_create, sys_epoll_create)
+#define __NR_epoll_ctl_old      214
+__SYSCALL(__NR_epoll_ctl_old, sys_ni_syscall)
+#define __NR_epoll_wait_old     215
+__SYSCALL(__NR_epoll_wait_old, sys_ni_syscall)
+#define __NR_remap_file_pages   216
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_getdents64 217
+__SYSCALL(__NR_getdents64, sys_getdents64)
+#define __NR_set_tid_address    218
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_restart_syscall    219
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_semtimedop         220
+__SYSCALL(__NR_semtimedop, sys_semtimedop)
+#define __NR_fadvise64          221
+__SYSCALL(__NR_fadvise64, sys_fadvise64)
+#define __NR_timer_create               222
+__SYSCALL(__NR_timer_create, sys_timer_create)
+#define __NR_timer_settime              223
+__SYSCALL(__NR_timer_settime, sys_timer_settime)
+#define __NR_timer_gettime              224
+__SYSCALL(__NR_timer_gettime, sys_timer_gettime)
+#define __NR_timer_getoverrun           225
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_delete       226
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime      227
+__SYSCALL(__NR_clock_settime, sys_clock_settime)
+#define __NR_clock_gettime      228
+__SYSCALL(__NR_clock_gettime, sys_clock_gettime)
+#define __NR_clock_getres       229
+__SYSCALL(__NR_clock_getres, sys_clock_getres)
+#define __NR_clock_nanosleep    230
+__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep)
+#define __NR_exit_group         231
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_epoll_wait         232
+__SYSCALL(__NR_epoll_wait, sys_epoll_wait)
+#define __NR_epoll_ctl          233
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_tgkill             234
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_utimes             235
+__SYSCALL(__NR_utimes, sys_utimes)
+#define __NR_vserver            236
+__SYSCALL(__NR_vserver, sys_ni_syscall)
+#define __NR_mbind              237
+__SYSCALL(__NR_mbind, sys_mbind)
+#define __NR_set_mempolicy      238
+__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
+#define __NR_get_mempolicy      239
+__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
+#define __NR_mq_open            240
+__SYSCALL(__NR_mq_open, sys_mq_open)
+#define __NR_mq_unlink          241
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend       242
+__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend)
+#define __NR_mq_timedreceive    243
+__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive)
+#define __NR_mq_notify          244
+__SYSCALL(__NR_mq_notify, sys_mq_notify)
+#define __NR_mq_getsetattr      245
+__SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr)
+#define __NR_kexec_load         246
+__SYSCALL(__NR_kexec_load, sys_kexec_load)
+#define __NR_waitid             247
+__SYSCALL(__NR_waitid, sys_waitid)
+#define __NR_add_key            248
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key        249
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl             250
+__SYSCALL(__NR_keyctl, sys_keyctl)
+#define __NR_ioprio_set         251
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get         252
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+#define __NR_inotify_init       253
+__SYSCALL(__NR_inotify_init, sys_inotify_init)
+#define __NR_inotify_add_watch  254
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch   255
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+#define __NR_migrate_pages      256
+__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
+#define __NR_openat             257
+__SYSCALL(__NR_openat, sys_openat)
+#define __NR_mkdirat            258
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_mknodat            259
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_fchownat           260
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_futimesat          261
+__SYSCALL(__NR_futimesat, sys_futimesat)
+#define __NR_newfstatat         262
+__SYSCALL(__NR_newfstatat, sys_newfstatat)
+#define __NR_unlinkat           263
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_renameat           264
+__SYSCALL(__NR_renameat, sys_renameat)
+#define __NR_linkat             265
+__SYSCALL(__NR_linkat, sys_linkat)
+#define __NR_symlinkat          266
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_readlinkat         267
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR_fchmodat           268
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_faccessat          269
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_pselect6           270
+__SYSCALL(__NR_pselect6, sys_pselect6)
+#define __NR_ppoll              271
+__SYSCALL(__NR_ppoll,   sys_ppoll)
+#define __NR_unshare            272
+__SYSCALL(__NR_unshare, sys_unshare)
+#define __NR_set_robust_list    273
+__SYSCALL(__NR_set_robust_list, sys_set_robust_list)
+#define __NR_get_robust_list    274
+__SYSCALL(__NR_get_robust_list, sys_get_robust_list)
+#define __NR_splice             275
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee                276
+__SYSCALL(__NR_tee, sys_tee)
+#define __NR_sync_file_range    277
+__SYSCALL(__NR_sync_file_range, sys_sync_file_range)
+#define __NR_vmsplice           278
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
+#define __NR_move_pages         279
+__SYSCALL(__NR_move_pages, sys_move_pages)
+#define __NR_utimensat          280
+__SYSCALL(__NR_utimensat, sys_utimensat)
+#define __IGNORE_getcpu         /* implemented as a vsyscall */
+#define __NR_epoll_pwait        281
+__SYSCALL(__NR_epoll_pwait, sys_epoll_pwait)
+#define __NR_signalfd           282
+__SYSCALL(__NR_signalfd, sys_signalfd)
+#define __NR_timerfd            283
+__SYSCALL(__NR_timerfd, sys_timerfd)
+#define __NR_eventfd            284
+__SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate          285
+__SYSCALL(__NR_fallocate, sys_fallocate)
+
+#ifndef __NO_STUBS
+#define __ARCH_WANT_OLD_READDIR
+#define __ARCH_WANT_OLD_STAT
+#define __ARCH_WANT_SYS_ALARM
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_SGETMASK
+#define __ARCH_WANT_SYS_SIGNAL
+#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_WAITPID
+#define __ARCH_WANT_SYS_SOCKETCALL
+#define __ARCH_WANT_SYS_FADVISE64
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLDUMOUNT
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_SYS_RT_SIGACTION
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_COMPAT_SYS_TIME
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#include <linux/linkage.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/ptrace.h>
+
+asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs);
+struct sigaction;
+asmlinkage long sys_rt_sigaction(int sig,
+                                const struct sigaction __user *act,
+                                struct sigaction __user *oact,
+                                size_t sigsetsize);
+
+#endif  /* __ASSEMBLY__ */
+#endif  /* __KERNEL__ */
+#endif  /* __NO_STUBS */
+
+/*
+ * "Conditional" syscalls
+ *
+ * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
+ * but it doesn't work on all toolchains, so we just do it by hand
+ */
+#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+
+#endif /* _ASM_X86_64_UNISTD_H_ */
diff --git a/include/asm-x86/unwind.h b/include/asm-x86/unwind.h
new file mode 100644
index 000000000000..7e4d7ad55208
--- /dev/null
+++ b/include/asm-x86/unwind.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "unwind_32.h"
+#else
+# include "unwind_64.h"
+#endif
diff --git a/include/asm-x86/unwind_32.h b/include/asm-x86/unwind_32.h
new file mode 100644
index 000000000000..43c70c3de2f9
--- /dev/null
+++ b/include/asm-x86/unwind_32.h
@@ -0,0 +1,13 @@
+#ifndef _ASM_I386_UNWIND_H
+#define _ASM_I386_UNWIND_H
+
+#define UNW_PC(frame) ((void)(frame), 0)
+#define UNW_SP(frame) ((void)(frame), 0)
+#define UNW_FP(frame) ((void)(frame), 0)
+
+static inline int arch_unw_user_mode(const void *info)
+{
+        return 0;
+}
+
+#endif /* _ASM_I386_UNWIND_H */
diff --git a/include/asm-x86/unwind_64.h b/include/asm-x86/unwind_64.h
new file mode 100644
index 000000000000..02710f6a4560
--- /dev/null
+++ b/include/asm-x86/unwind_64.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_64_UNWIND_H
+#define _ASM_X86_64_UNWIND_H
+
+#define UNW_PC(frame) ((void)(frame), 0UL)
+#define UNW_SP(frame) ((void)(frame), 0UL)
+
+static inline int arch_unw_user_mode(const void *info)
+{
+        return 0;
+}
+
+#endif /* _ASM_X86_64_UNWIND_H */
diff --git a/include/asm-x86/user.h b/include/asm-x86/user.h
new file mode 100644
index 000000000000..484715abe74a
--- /dev/null
+++ b/include/asm-x86/user.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "user_32.h"
+# else
+#  include "user_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "user_32.h"
+# else
+#  include "user_64.h"
+# endif
+#endif
diff --git a/include/asm-x86/user32.h b/include/asm-x86/user32.h
new file mode 100644
index 000000000000..f769872debea
--- /dev/null
+++ b/include/asm-x86/user32.h
@@ -0,0 +1,69 @@
+#ifndef USER32_H
+#define USER32_H 1
+
+/* IA32 compatible user structures for ptrace. These should be used for 32bit coredumps too. */
+
+struct user_i387_ia32_struct {
+        u32     cwd;
+        u32     swd;
+        u32     twd;
+        u32     fip;
+        u32     fcs;
+        u32     foo;
+        u32     fos;
+        u32     st_space[20];   /* 8*10 bytes for each FP-reg = 80 bytes */
+};
+
+/* FSAVE frame with extensions */
+struct user32_fxsr_struct {
+        unsigned short  cwd;
+        unsigned short  swd;
+        unsigned short  twd;    /* not compatible to 64bit twd */
+        unsigned short  fop;
+        int     fip;
+        int     fcs;
+        int     foo;
+        int     fos;
+        int     mxcsr;
+        int     reserved;
+        int     st_space[32];   /* 8*16 bytes for each FP-reg = 128 bytes */
+        int     xmm_space[32];  /* 8*16 bytes for each XMM-reg = 128 bytes */
+        int     padding[56];
+};
+
+struct user_regs_struct32 {
+        __u32 ebx, ecx, edx, esi, edi, ebp, eax;
+        unsigned short ds, __ds, es, __es;
+        unsigned short fs, __fs, gs, __gs;
+        __u32 orig_eax, eip;
+        unsigned short cs, __cs;
+        __u32 eflags, esp;
+        unsigned short ss, __ss;
+};
+
+struct user32 {
+  struct user_regs_struct32 regs;               /* Where the registers are actually stored */
+  int u_fpvalid;                /* True if math co-processor being used. */
+                                /* for this mess. Not yet used. */
+  struct user_i387_ia32_struct i387;    /* Math Co-processor registers. */
+/* The rest of this junk is to help gdb figure out what goes where */
+  __u32 u_tsize;        /* Text segment size (pages). */
+  __u32 u_dsize;        /* Data segment size (pages). */
+  __u32 u_ssize;        /* Stack segment size (pages). */
+  __u32 start_code;     /* Starting virtual address of text. */
+  __u32 start_stack;    /* Starting virtual address of stack area.
+                                   This is actually the bottom of the stack,
+                                   the top of the stack is always found in the
+                                   esp register.  */
+  __u32 signal;                 /* Signal that caused the core dump. */
+  int reserved;                 /* No __u32er used */
+  __u32 u_ar0;  /* Used by gdb to help find the values for */
+                                /* the registers. */
+  __u32 u_fpstate;      /* Math Co-processor pointer. */
+  __u32 magic;          /* To uniquely identify a core file */
+  char u_comm[32];              /* User command that was responsible */
+  int u_debugreg[8];
+};
+
+
+#endif
diff --git a/include/asm-x86/user_32.h b/include/asm-x86/user_32.h
new file mode 100644
index 000000000000..0e85d2a5e33a
--- /dev/null
+++ b/include/asm-x86/user_32.h
@@ -0,0 +1,121 @@
+#ifndef _I386_USER_H
+#define _I386_USER_H
+
+#include <asm/page.h>
+/* Core file format: The core file is written in such a way that gdb
+   can understand it and provide useful information to the user (under
+   linux we use the 'trad-core' bfd).  There are quite a number of
+   obstacles to being able to view the contents of the floating point
+   registers, and until these are solved you will not be able to view the
+   contents of them.  Actually, you can read in the core file and look at
+   the contents of the user struct to find out what the floating point
+   registers contain.
+   The actual file contents are as follows:
+   UPAGE: 1 page consisting of a user struct that tells gdb what is present
+   in the file.  Directly after this is a copy of the task_struct, which
+   is currently not used by gdb, but it may come in useful at some point.
+   All of the registers are stored as part of the upage.  The upage should
+   always be only one page.
+   DATA: The data area is stored.  We use current->end_text to
+   current->brk to pick up all of the user variables, plus any memory
+   that may have been malloced.  No attempt is made to determine if a page
+   is demand-zero or if a page is totally unused, we just cover the entire
+   range.  All of the addresses are rounded in such a way that an integral
+   number of pages is written.
+   STACK: We need the stack information in order to get a meaningful
+   backtrace.  We need to write the data from (esp) to
+   current->start_stack, so we round each of these off in order to be able
+   to write an integer number of pages.
+   The minimum core file size is 3 pages, or 12288 bytes.
+*/
+
+/*
+ * Pentium III FXSR, SSE support
+ *      Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
+ * interacting with the FXSR-format floating point environment.  Floating
+ * point data can be accessed in the regular format in the usual manner,
+ * and both the standard and SIMD floating point data can be accessed via
+ * the new ptrace requests.  In either case, changes to the FPU environment
+ * will be reflected in the task's state as expected.
+ */
+
+struct user_i387_struct {
+        long    cwd;
+        long    swd;
+        long    twd;
+        long    fip;
+        long    fcs;
+        long    foo;
+        long    fos;
+        long    st_space[20];   /* 8*10 bytes for each FP-reg = 80 bytes */
+};
+
+struct user_fxsr_struct {
+        unsigned short  cwd;
+        unsigned short  swd;
+        unsigned short  twd;
+        unsigned short  fop;
+        long    fip;
+        long    fcs;
+        long    foo;
+        long    fos;
+        long    mxcsr;
+        long    reserved;
+        long    st_space[32];   /* 8*16 bytes for each FP-reg = 128 bytes */
+        long    xmm_space[32];  /* 8*16 bytes for each XMM-reg = 128 bytes */
+        long    padding[56];
+};
+
+/*
+ * This is the old layout of "struct pt_regs", and
+ * is still the layout used by user mode (the new
+ * pt_regs doesn't have all registers as the kernel
+ * doesn't use the extra segment registers)
+ */
+struct user_regs_struct {
+        long ebx, ecx, edx, esi, edi, ebp, eax;
+        unsigned short ds, __ds, es, __es;
+        unsigned short fs, __fs, gs, __gs;
+        long orig_eax, eip;
+        unsigned short cs, __cs;
+        long eflags, esp;
+        unsigned short ss, __ss;
+};
+
+/* When the kernel dumps core, it starts by dumping the user struct -
+   this will be used by gdb to figure out where the data and stack segments
+   are within the file, and what virtual addresses to use. */
+struct user{
+/* We start with the registers, to mimic the way that "memory" is returned
+   from the ptrace(3,...) function.  */
+  struct user_regs_struct regs;         /* Where the registers are actually stored */
+/* ptrace does not yet supply these.  Someday.... */
+  int u_fpvalid;                /* True if math co-processor being used. */
+                                /* for this mess. Not yet used. */
+  struct user_i387_struct i387; /* Math Co-processor registers. */
+/* The rest of this junk is to help gdb figure out what goes where */
+  unsigned long int u_tsize;    /* Text segment size (pages). */
+  unsigned long int u_dsize;    /* Data segment size (pages). */
+  unsigned long int u_ssize;    /* Stack segment size (pages). */
+  unsigned long start_code;     /* Starting virtual address of text. */
+  unsigned long start_stack;    /* Starting virtual address of stack area.
+                                   This is actually the bottom of the stack,
+                                   the top of the stack is always found in the
+                                   esp register.  */
+  long int signal;              /* Signal that caused the core dump. */
+  int reserved;                 /* No longer used */
+  struct user_pt_regs * u_ar0;  /* Used by gdb to help find the values for */
+                                /* the registers. */
+  struct user_i387_struct* u_fpstate;   /* Math Co-processor pointer. */
+  unsigned long magic;          /* To uniquely identify a core file */
+  char u_comm[32];              /* User command that was responsible */
+  int u_debugreg[8];
+};
+#define NBPG PAGE_SIZE
+#define UPAGES 1
+#define HOST_TEXT_START_ADDR (u.start_code)
+#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
+
+#endif /* _I386_USER_H */
diff --git a/include/asm-x86/user_64.h b/include/asm-x86/user_64.h
new file mode 100644
index 000000000000..12785c649ac5
--- /dev/null
+++ b/include/asm-x86/user_64.h
@@ -0,0 +1,114 @@
+#ifndef _X86_64_USER_H
+#define _X86_64_USER_H
+
+#include <asm/types.h>
+#include <asm/page.h>
+/* Core file format: The core file is written in such a way that gdb
+   can understand it and provide useful information to the user.
+   There are quite a number of obstacles to being able to view the
+   contents of the floating point registers, and until these are
+   solved you will not be able to view the contents of them.
+   Actually, you can read in the core file and look at the contents of
+   the user struct to find out what the floating point registers
+   contain.
+
+   The actual file contents are as follows:
+   UPAGE: 1 page consisting of a user struct that tells gdb what is present
+   in the file.  Directly after this is a copy of the task_struct, which
+   is currently not used by gdb, but it may come in useful at some point.
+   All of the registers are stored as part of the upage.  The upage should
+   always be only one page.
+   DATA: The data area is stored.  We use current->end_text to
+   current->brk to pick up all of the user variables, plus any memory
+   that may have been malloced.  No attempt is made to determine if a page
+   is demand-zero or if a page is totally unused, we just cover the entire
+   range.  All of the addresses are rounded in such a way that an integral
+   number of pages is written.
+   STACK: We need the stack information in order to get a meaningful
+   backtrace.  We need to write the data from (esp) to
+   current->start_stack, so we round each of these off in order to be able
+   to write an integer number of pages.
+   The minimum core file size is 3 pages, or 12288 bytes.  */
+
+/*
+ * Pentium III FXSR, SSE support
+ *      Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
+ * interacting with the FXSR-format floating point environment.  Floating
+ * point data can be accessed in the regular format in the usual manner,
+ * and both the standard and SIMD floating point data can be accessed via
+ * the new ptrace requests.  In either case, changes to the FPU environment
+ * will be reflected in the task's state as expected.
+ * 
+ * x86-64 support by Andi Kleen.
+ */
+
+/* This matches the 64bit FXSAVE format as defined by AMD. It is the same
+   as the 32bit format defined by Intel, except that the selector:offset pairs for
+   data and eip are replaced with flat 64bit pointers. */ 
+struct user_i387_struct {
+        unsigned short  cwd;
+        unsigned short  swd;
+        unsigned short  twd; /* Note this is not the same as the 32bit/x87/FSAVE twd */
+        unsigned short  fop;
+        __u64   rip;
+        __u64   rdp;
+        __u32   mxcsr;
+        __u32   mxcsr_mask;
+        __u32   st_space[32];   /* 8*16 bytes for each FP-reg = 128 bytes */
+        __u32   xmm_space[64];  /* 16*16 bytes for each XMM-reg = 256 bytes */
+        __u32   padding[24];
+};
+
+/*
+ * Segment register layout in coredumps.
+ */
+struct user_regs_struct {
+        unsigned long r15,r14,r13,r12,rbp,rbx,r11,r10;
+        unsigned long r9,r8,rax,rcx,rdx,rsi,rdi,orig_rax;
+        unsigned long rip,cs,eflags;
+        unsigned long rsp,ss;
+        unsigned long fs_base, gs_base;
+        unsigned long ds,es,fs,gs; 
+}; 
+
+/* When the kernel dumps core, it starts by dumping the user struct -
+   this will be used by gdb to figure out where the data and stack segments
+   are within the file, and what virtual addresses to use. */
+struct user{
+/* We start with the registers, to mimic the way that "memory" is returned
+   from the ptrace(3,...) function.  */
+  struct user_regs_struct regs;         /* Where the registers are actually stored */
+/* ptrace does not yet supply these.  Someday.... */
+  int u_fpvalid;                /* True if math co-processor being used. */
+                                /* for this mess. Not yet used. */
+  int pad0;
+  struct user_i387_struct i387; /* Math Co-processor registers. */
+/* The rest of this junk is to help gdb figure out what goes where */
+  unsigned long int u_tsize;    /* Text segment size (pages). */
+  unsigned long int u_dsize;    /* Data segment size (pages). */
+  unsigned long int u_ssize;    /* Stack segment size (pages). */
+  unsigned long start_code;     /* Starting virtual address of text. */
+  unsigned long start_stack;    /* Starting virtual address of stack area.
+                                   This is actually the bottom of the stack,
+                                   the top of the stack is always found in the
+                                   esp register.  */
+  long int signal;              /* Signal that caused the core dump. */
+  int reserved;                 /* No longer used */
+  int pad1;
+  struct user_pt_regs * u_ar0;  /* Used by gdb to help find the values for */
+                                /* the registers. */
+  struct user_i387_struct* u_fpstate;   /* Math Co-processor pointer. */
+  unsigned long magic;          /* To uniquely identify a core file */
+  char u_comm[32];              /* User command that was responsible */
+  unsigned long u_debugreg[8];
+  unsigned long error_code; /* CPU error code or 0 */
+  unsigned long fault_address; /* CR3 or 0 */
+};
+#define NBPG PAGE_SIZE
+#define UPAGES 1
+#define HOST_TEXT_START_ADDR (u.start_code)
+#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
+
+#endif /* _X86_64_USER_H */
diff --git a/include/asm-x86/vga.h b/include/asm-x86/vga.h
new file mode 100644
index 000000000000..0ecf68ac03aa
--- /dev/null
+++ b/include/asm-x86/vga.h
@@ -0,0 +1,20 @@
+/*
+ *      Access to VGA videoram
+ *
+ *      (c) 1998 Martin Mares <mj@ucw.cz>
+ */
+
+#ifndef _LINUX_ASM_VGA_H_
+#define _LINUX_ASM_VGA_H_
+
+/*
+ *      On the PC, we can just recalculate addresses and then
+ *      access the videoram directly without any black magic.
+ */
+
+#define VGA_MAP_MEM(x,s) (unsigned long)phys_to_virt(x)
+
+#define vga_readb(x) (*(x))
+#define vga_writeb(x,y) (*(y) = (x))
+
+#endif
diff --git a/include/asm-x86/vgtod.h b/include/asm-x86/vgtod.h
new file mode 100644
index 000000000000..3301f0929342
--- /dev/null
+++ b/include/asm-x86/vgtod.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_VGTOD_H
+#define _ASM_VGTOD_H 1
+
+#include <asm/vsyscall.h>
+#include <linux/clocksource.h>
+
+struct vsyscall_gtod_data {
+        seqlock_t       lock;
+
+        /* open coded 'struct timespec' */
+        time_t          wall_time_sec;
+        u32             wall_time_nsec;
+
+        int             sysctl_enabled;
+        struct timezone sys_tz;
+        struct { /* extract of a clocksource struct */
+                cycle_t (*vread)(void);
+                cycle_t cycle_last;
+                cycle_t mask;
+                u32     mult;
+                u32     shift;
+        } clock;
+        struct timespec wall_to_monotonic;
+};
+extern struct vsyscall_gtod_data __vsyscall_gtod_data
+__section_vsyscall_gtod_data;
+extern struct vsyscall_gtod_data vsyscall_gtod_data;
+
+#endif
diff --git a/include/asm-x86/vic.h b/include/asm-x86/vic.h
new file mode 100644
index 000000000000..53100f353612
--- /dev/null
+++ b/include/asm-x86/vic.h
@@ -0,0 +1,61 @@
+/* Copyright (C) 1999,2001
+ *
+ * Author: J.E.J.Bottomley@HansenPartnership.com
+ *
+ * Standard include definitions for the NCR Voyager Interrupt Controller */
+
+/* The eight CPI vectors.  To activate a CPI, you write a bit mask
+ * corresponding to the processor set to be interrupted into the
+ * relevant register.  That set of CPUs will then be interrupted with
+ * the CPI */
+static const int VIC_CPI_Registers[] =
+        {0xFC00, 0xFC01, 0xFC08, 0xFC09,
+         0xFC10, 0xFC11, 0xFC18, 0xFC19 };
+
+#define VIC_PROC_WHO_AM_I               0xfc29
+#       define  QUAD_IDENTIFIER         0xC0
+#       define  EIGHT_SLOT_IDENTIFIER   0xE0
+#define QIC_EXTENDED_PROCESSOR_SELECT   0xFC72
+#define VIC_CPI_BASE_REGISTER           0xFC41
+#define VIC_PROCESSOR_ID                0xFC21
+#       define VIC_CPU_MASQUERADE_ENABLE 0x8
+
+#define VIC_CLAIM_REGISTER_0            0xFC38
+#define VIC_CLAIM_REGISTER_1            0xFC39
+#define VIC_REDIRECT_REGISTER_0         0xFC60
+#define VIC_REDIRECT_REGISTER_1         0xFC61
+#define VIC_PRIORITY_REGISTER           0xFC20
+
+#define VIC_PRIMARY_MC_BASE             0xFC48
+#define VIC_SECONDARY_MC_BASE           0xFC49
+
+#define QIC_PROCESSOR_ID                0xFC71
+#       define  QIC_CPUID_ENABLE        0x08
+
+#define QIC_VIC_CPI_BASE_REGISTER       0xFC79
+#define QIC_CPI_BASE_REGISTER           0xFC7A
+
+#define QIC_MASK_REGISTER0              0xFC80
+/* NOTE: these are masked high, enabled low */
+#       define QIC_PERF_TIMER           0x01
+#       define QIC_LPE                  0x02
+#       define QIC_SYS_INT              0x04
+#       define QIC_CMN_INT              0x08
+/* at the moment, just enable CMN_INT, disable SYS_INT */
+#       define QIC_DEFAULT_MASK0        (~(QIC_CMN_INT /* | VIC_SYS_INT */))
+#define QIC_MASK_REGISTER1              0xFC81
+#       define QIC_BOOT_CPI_MASK        0xFE
+/* Enable CPI's 1-6 inclusive */
+#       define QIC_CPI_ENABLE           0x81
+
+#define QIC_INTERRUPT_CLEAR0            0xFC8A
+#define QIC_INTERRUPT_CLEAR1            0xFC8B
+
+/* this is where we place the CPI vectors */
+#define VIC_DEFAULT_CPI_BASE            0xC0
+/* this is where we place the QIC CPI vectors */
+#define QIC_DEFAULT_CPI_BASE            0xD0
+
+#define VIC_BOOT_INTERRUPT_MASK         0xfe
+
+extern void smp_vic_timer_interrupt(void);
diff --git a/include/asm-x86/vm86.h b/include/asm-x86/vm86.h
new file mode 100644
index 000000000000..a5edf517b992
--- /dev/null
+++ b/include/asm-x86/vm86.h
@@ -0,0 +1,215 @@
+#ifndef _LINUX_VM86_H
+#define _LINUX_VM86_H
+
+/*
+ * I'm guessing at the VIF/VIP flag usage, but hope that this is how
+ * the Pentium uses them. Linux will return from vm86 mode when both
+ * VIF and VIP is set.
+ *
+ * On a Pentium, we could probably optimize the virtual flags directly
+ * in the eflags register instead of doing it "by hand" in vflags...
+ *
+ * Linus
+ */
+
+#define TF_MASK         0x00000100
+#define IF_MASK         0x00000200
+#define IOPL_MASK       0x00003000
+#define NT_MASK         0x00004000
+#ifdef CONFIG_VM86
+#define VM_MASK         0x00020000
+#else
+#define VM_MASK         0 /* ignored */
+#endif
+#define AC_MASK         0x00040000
+#define VIF_MASK        0x00080000      /* virtual interrupt flag */
+#define VIP_MASK        0x00100000      /* virtual interrupt pending */
+#define ID_MASK         0x00200000
+
+#define BIOSSEG         0x0f000
+
+#define CPU_086         0
+#define CPU_186         1
+#define CPU_286         2
+#define CPU_386         3
+#define CPU_486         4
+#define CPU_586         5
+
+/*
+ * Return values for the 'vm86()' system call
+ */
+#define VM86_TYPE(retval)       ((retval) & 0xff)
+#define VM86_ARG(retval)        ((retval) >> 8)
+
+#define VM86_SIGNAL     0       /* return due to signal */
+#define VM86_UNKNOWN    1       /* unhandled GP fault - IO-instruction or similar */
+#define VM86_INTx       2       /* int3/int x instruction (ARG = x) */
+#define VM86_STI        3       /* sti/popf/iret instruction enabled virtual interrupts */
+
+/*
+ * Additional return values when invoking new vm86()
+ */
+#define VM86_PICRETURN  4       /* return due to pending PIC request */
+#define VM86_TRAP       6       /* return due to DOS-debugger request */
+
+/*
+ * function codes when invoking new vm86()
+ */
+#define VM86_PLUS_INSTALL_CHECK 0
+#define VM86_ENTER              1
+#define VM86_ENTER_NO_BYPASS    2
+#define VM86_REQUEST_IRQ        3
+#define VM86_FREE_IRQ           4
+#define VM86_GET_IRQ_BITS       5
+#define VM86_GET_AND_RESET_IRQ  6
+
+/*
+ * This is the stack-layout seen by the user space program when we have
+ * done a translation of "SAVE_ALL" from vm86 mode. The real kernel layout
+ * is 'kernel_vm86_regs' (see below).
+ */
+
+struct vm86_regs {
+/*
+ * normal regs, with special meaning for the segment descriptors..
+ */
+        long ebx;
+        long ecx;
+        long edx;
+        long esi;
+        long edi;
+        long ebp;
+        long eax;
+        long __null_ds;
+        long __null_es;
+        long __null_fs;
+        long __null_gs;
+        long orig_eax;
+        long eip;
+        unsigned short cs, __csh;
+        long eflags;
+        long esp;
+        unsigned short ss, __ssh;
+/*
+ * these are specific to v86 mode:
+ */
+        unsigned short es, __esh;
+        unsigned short ds, __dsh;
+        unsigned short fs, __fsh;
+        unsigned short gs, __gsh;
+};
+
+struct revectored_struct {
+        unsigned long __map[8];                 /* 256 bits */
+};
+
+struct vm86_struct {
+        struct vm86_regs regs;
+        unsigned long flags;
+        unsigned long screen_bitmap;
+        unsigned long cpu_type;
+        struct revectored_struct int_revectored;
+        struct revectored_struct int21_revectored;
+};
+
+/*
+ * flags masks
+ */
+#define VM86_SCREEN_BITMAP      0x0001
+
+struct vm86plus_info_struct {
+        unsigned long force_return_for_pic:1;
+        unsigned long vm86dbg_active:1;       /* for debugger */
+        unsigned long vm86dbg_TFpendig:1;     /* for debugger */
+        unsigned long unused:28;
+        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;
+        unsigned long screen_bitmap;
+        unsigned long cpu_type;
+        struct revectored_struct int_revectored;
+        struct revectored_struct int21_revectored;
+        struct vm86plus_info_struct vm86plus;
+};
+
+#ifdef __KERNEL__
+/*
+ * 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
+ * useful any more and are forced to be zero by the kernel (and the
+ * hardware when a trap occurs), and the real segment descriptors are
+ * 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 {
+/*
+ * normal regs, with special meaning for the segment descriptors..
+ */
+        struct pt_regs pt;
+/*
+ * these are specific to v86 mode:
+ */
+        unsigned short es, __esh;
+        unsigned short ds, __dsh;
+        unsigned short fs, __fsh;
+        unsigned short gs, __gsh;
+};
+
+struct kernel_vm86_struct {
+        struct kernel_vm86_regs regs;
+/*
+ * the below part remains on the kernel stack while we are in VM86 mode.
+ * 'tss.esp0' then contains the address of VM86_TSS_ESP0 below, and when we
+ * get forced back from VM86, the CPU and "SAVE_ALL" will restore the above
+ * 'struct kernel_vm86_regs' with the then actual values.
+ * Therefore, pt_regs in fact points to a complete 'kernel_vm86_struct'
+ * in kernelspace, hence we need not reget the data from userspace.
+ */
+#define VM86_TSS_ESP0 flags
+        unsigned long flags;
+        unsigned long screen_bitmap;
+        unsigned long cpu_type;
+        struct revectored_struct int_revectored;
+        struct revectored_struct int21_revectored;
+        struct vm86plus_info_struct vm86plus;
+        struct pt_regs *regs32;   /* here we save the pointer to the old regs */
+/*
+ * The below is not part of the structure, but the stack layout continues
+ * this way. In front of 'return-eip' may be some data, depending on
+ * compilation, so we don't rely on this and save the pointer to 'oldregs'
+ * in 'regs32' above.
+ * However, with GCC-2.7.2 and the current CFLAGS you see exactly this:
+
+        long return-eip;        from call to vm86()
+        struct pt_regs oldregs;  user space registers as saved by syscall
+ */
+};
+
+#ifdef CONFIG_VM86
+
+void handle_vm86_fault(struct kernel_vm86_regs *, long);
+int handle_vm86_trap(struct kernel_vm86_regs *, long, int);
+
+struct task_struct;
+void release_vm86_irqs(struct task_struct *);
+
+#else
+
+#define handle_vm86_fault(a, b)
+#define release_vm86_irqs(a)
+
+static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c) {
+        return 0;
+}
+
+#endif /* CONFIG_VM86 */
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86/vmi.h b/include/asm-x86/vmi.h
new file mode 100644
index 000000000000..eb8bd892c01e
--- /dev/null
+++ b/include/asm-x86/vmi.h
@@ -0,0 +1,263 @@
+/*
+ * VMI interface definition
+ *
+ * Copyright (C) 2005, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Maintained by: Zachary Amsden zach@vmware.com
+ *
+ */
+#include <linux/types.h>
+
+/*
+ *---------------------------------------------------------------------
+ *
+ *  VMI Option ROM API
+ *
+ *---------------------------------------------------------------------
+ */
+#define VMI_SIGNATURE 0x696d5663   /* "cVmi" */
+
+#define PCI_VENDOR_ID_VMWARE            0x15AD
+#define PCI_DEVICE_ID_VMWARE_VMI        0x0801
+
+/*
+ * We use two version numbers for compatibility, with the major
+ * number signifying interface breakages, and the minor number
+ * interface extensions.
+ */
+#define VMI_API_REV_MAJOR       3
+#define VMI_API_REV_MINOR       0
+
+#define VMI_CALL_CPUID                  0
+#define VMI_CALL_WRMSR                  1
+#define VMI_CALL_RDMSR                  2
+#define VMI_CALL_SetGDT                 3
+#define VMI_CALL_SetLDT                 4
+#define VMI_CALL_SetIDT                 5
+#define VMI_CALL_SetTR                  6
+#define VMI_CALL_GetGDT                 7
+#define VMI_CALL_GetLDT                 8
+#define VMI_CALL_GetIDT                 9
+#define VMI_CALL_GetTR                  10
+#define VMI_CALL_WriteGDTEntry          11
+#define VMI_CALL_WriteLDTEntry          12
+#define VMI_CALL_WriteIDTEntry          13
+#define VMI_CALL_UpdateKernelStack      14
+#define VMI_CALL_SetCR0                 15
+#define VMI_CALL_SetCR2                 16
+#define VMI_CALL_SetCR3                 17
+#define VMI_CALL_SetCR4                 18
+#define VMI_CALL_GetCR0                 19
+#define VMI_CALL_GetCR2                 20
+#define VMI_CALL_GetCR3                 21
+#define VMI_CALL_GetCR4                 22
+#define VMI_CALL_WBINVD                 23
+#define VMI_CALL_SetDR                  24
+#define VMI_CALL_GetDR                  25
+#define VMI_CALL_RDPMC                  26
+#define VMI_CALL_RDTSC                  27
+#define VMI_CALL_CLTS                   28
+#define VMI_CALL_EnableInterrupts       29
+#define VMI_CALL_DisableInterrupts      30
+#define VMI_CALL_GetInterruptMask       31
+#define VMI_CALL_SetInterruptMask       32
+#define VMI_CALL_IRET                   33
+#define VMI_CALL_SYSEXIT                34
+#define VMI_CALL_Halt                   35
+#define VMI_CALL_Reboot                 36
+#define VMI_CALL_Shutdown               37
+#define VMI_CALL_SetPxE                 38
+#define VMI_CALL_SetPxELong             39
+#define VMI_CALL_UpdatePxE              40
+#define VMI_CALL_UpdatePxELong          41
+#define VMI_CALL_MachineToPhysical      42
+#define VMI_CALL_PhysicalToMachine      43
+#define VMI_CALL_AllocatePage           44
+#define VMI_CALL_ReleasePage            45
+#define VMI_CALL_InvalPage              46
+#define VMI_CALL_FlushTLB               47
+#define VMI_CALL_SetLinearMapping       48
+
+#define VMI_CALL_SetIOPLMask            61
+#define VMI_CALL_SetInitialAPState      62
+#define VMI_CALL_APICWrite              63
+#define VMI_CALL_APICRead               64
+#define VMI_CALL_IODelay                65
+#define VMI_CALL_SetLazyMode            73
+
+/*
+ *---------------------------------------------------------------------
+ *
+ * MMU operation flags
+ *
+ *---------------------------------------------------------------------
+ */
+
+/* Flags used by VMI_{Allocate|Release}Page call */
+#define VMI_PAGE_PAE             0x10  /* Allocate PAE shadow */
+#define VMI_PAGE_CLONE           0x20  /* Clone from another shadow */
+#define VMI_PAGE_ZEROED          0x40  /* Page is pre-zeroed */
+
+
+/* Flags shared by Allocate|Release Page and PTE updates */
+#define VMI_PAGE_PT              0x01
+#define VMI_PAGE_PD              0x02
+#define VMI_PAGE_PDP             0x04
+#define VMI_PAGE_PML4            0x08
+
+#define VMI_PAGE_NORMAL          0x00 /* for debugging */
+
+/* Flags used by PTE updates */
+#define VMI_PAGE_CURRENT_AS      0x10 /* implies VMI_PAGE_VA_MASK is valid */
+#define VMI_PAGE_DEFER           0x20 /* may queue update until TLB inval */
+#define VMI_PAGE_VA_MASK         0xfffff000
+
+#ifdef CONFIG_X86_PAE
+#define VMI_PAGE_L1             (VMI_PAGE_PT | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
+#define VMI_PAGE_L2             (VMI_PAGE_PD | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
+#else
+#define VMI_PAGE_L1             (VMI_PAGE_PT | VMI_PAGE_ZEROED)
+#define VMI_PAGE_L2             (VMI_PAGE_PD | VMI_PAGE_ZEROED)
+#endif
+
+/* Flags used by VMI_FlushTLB call */
+#define VMI_FLUSH_TLB            0x01
+#define VMI_FLUSH_GLOBAL         0x02
+
+/*
+ *---------------------------------------------------------------------
+ *
+ *  VMI relocation definitions for ROM call get_reloc
+ *
+ *---------------------------------------------------------------------
+ */
+
+/* VMI Relocation types */
+#define VMI_RELOCATION_NONE     0
+#define VMI_RELOCATION_CALL_REL 1
+#define VMI_RELOCATION_JUMP_REL 2
+#define VMI_RELOCATION_NOP      3
+
+#ifndef __ASSEMBLY__
+struct vmi_relocation_info {
+        unsigned char           *eip;
+        unsigned char           type;
+        unsigned char           reserved[3];
+};
+#endif
+
+
+/*
+ *---------------------------------------------------------------------
+ *
+ *  Generic ROM structures and definitions
+ *
+ *---------------------------------------------------------------------
+ */
+
+#ifndef __ASSEMBLY__
+
+struct vrom_header {
+        u16     rom_signature;  // option ROM signature
+        u8      rom_length;     // ROM length in 512 byte chunks
+        u8      rom_entry[4];   // 16-bit code entry point
+        u8      rom_pad0;       // 4-byte align pad
+        u32     vrom_signature; // VROM identification signature
+        u8      api_version_min;// Minor version of API
+        u8      api_version_maj;// Major version of API
+        u8      jump_slots;     // Number of jump slots
+        u8      reserved1;      // Reserved for expansion
+        u32     virtual_top;    // Hypervisor virtual address start
+        u16     reserved2;      // Reserved for expansion
+        u16     license_offs;   // Offset to License string
+        u16     pci_header_offs;// Offset to PCI OPROM header
+        u16     pnp_header_offs;// Offset to PnP OPROM header
+        u32     rom_pad3;       // PnP reserverd / VMI reserved
+        u8      reserved[96];   // Reserved for headers
+        char    vmi_init[8];    // VMI_Init jump point
+        char    get_reloc[8];   // VMI_GetRelocationInfo jump point
+} __attribute__((packed));
+
+struct pnp_header {
+        char sig[4];
+        char rev;
+        char size;
+        short next;
+        short res;
+        long devID;
+        unsigned short manufacturer_offset;
+        unsigned short product_offset;
+} __attribute__((packed));
+
+struct pci_header {
+        char sig[4];
+        short vendorID;
+        short deviceID;
+        short vpdData;
+        short size;
+        char rev;
+        char class;
+        char subclass;
+        char interface;
+        short chunks;
+        char rom_version_min;
+        char rom_version_maj;
+        char codetype;
+        char lastRom;
+        short reserved;
+} __attribute__((packed));
+
+/* Function prototypes for bootstrapping */
+extern void vmi_init(void);
+extern void vmi_bringup(void);
+extern void vmi_apply_boot_page_allocations(void);
+
+/* State needed to start an application processor in an SMP system. */
+struct vmi_ap_state {
+        u32 cr0;
+        u32 cr2;
+        u32 cr3;
+        u32 cr4;
+
+        u64 efer;
+
+        u32 eip;
+        u32 eflags;
+        u32 eax;
+        u32 ebx;
+        u32 ecx;
+        u32 edx;
+        u32 esp;
+        u32 ebp;
+        u32 esi;
+        u32 edi;
+        u16 cs;
+        u16 ss;
+        u16 ds;
+        u16 es;
+        u16 fs;
+        u16 gs;
+        u16 ldtr;
+
+        u16 gdtr_limit;
+        u32 gdtr_base;
+        u32 idtr_base;
+        u16 idtr_limit;
+};
+
+#endif
diff --git a/include/asm-x86/vmi_time.h b/include/asm-x86/vmi_time.h
new file mode 100644
index 000000000000..478188130328
--- /dev/null
+++ b/include/asm-x86/vmi_time.h
@@ -0,0 +1,98 @@
+/*
+ * VMI Time wrappers
+ *
+ * Copyright (C) 2006, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to dhecht@vmware.com
+ *
+ */
+
+#ifndef __VMI_TIME_H
+#define __VMI_TIME_H
+
+/*
+ * Raw VMI call indices for timer functions
+ */
+#define VMI_CALL_GetCycleFrequency      66
+#define VMI_CALL_GetCycleCounter        67
+#define VMI_CALL_SetAlarm               68
+#define VMI_CALL_CancelAlarm            69
+#define VMI_CALL_GetWallclockTime       70
+#define VMI_CALL_WallclockUpdated       71
+
+/* Cached VMI timer operations */
+extern struct vmi_timer_ops {
+        u64 (*get_cycle_frequency)(void);
+        u64 (*get_cycle_counter)(int);
+        u64 (*get_wallclock)(void);
+        int (*wallclock_updated)(void);
+        void (*set_alarm)(u32 flags, u64 expiry, u64 period);
+        void (*cancel_alarm)(u32 flags);
+} vmi_timer_ops;
+
+/* Prototypes */
+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);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+extern void __devinit vmi_time_bsp_init(void);
+extern void __devinit vmi_time_ap_init(void);
+#endif
+
+/*
+ * When run under a hypervisor, a vcpu is always in one of three states:
+ * running, halted, or ready.  The vcpu is in the 'running' state if it
+ * is executing.  When the vcpu executes the halt interface, the vcpu
+ * enters the 'halted' state and remains halted until there is some work
+ * pending for the vcpu (e.g. an alarm expires, host I/O completes on
+ * behalf of virtual I/O).  At this point, the vcpu enters the 'ready'
+ * state (waiting for the hypervisor to reschedule it).  Finally, at any
+ * time when the vcpu is not in the 'running' state nor the 'halted'
+ * state, it is in the 'ready' state.
+ *
+ * Real time is advances while the vcpu is 'running', 'ready', or
+ * 'halted'.  Stolen time is the time in which the vcpu is in the
+ * 'ready' state.  Available time is the remaining time -- the vcpu is
+ * either 'running' or 'halted'.
+ *
+ * All three views of time are accessible through the VMI cycle
+ * counters.
+ */
+
+/* The cycle counters. */
+#define VMI_CYCLES_REAL         0
+#define VMI_CYCLES_AVAILABLE    1
+#define VMI_CYCLES_STOLEN       2
+
+/* The alarm interface 'flags' bits */
+#define VMI_ALARM_COUNTERS      2
+
+#define VMI_ALARM_COUNTER_MASK  0x000000ff
+
+#define VMI_ALARM_WIRED_IRQ0    0x00000000
+#define VMI_ALARM_WIRED_LVTT    0x00010000
+
+#define VMI_ALARM_IS_ONESHOT    0x00000000
+#define VMI_ALARM_IS_PERIODIC   0x00000100
+
+#define CONFIG_VMI_ALARM_HZ     100
+
+#endif
diff --git a/include/asm-x86/voyager.h b/include/asm-x86/voyager.h
new file mode 100644
index 000000000000..91a9932937ab
--- /dev/null
+++ b/include/asm-x86/voyager.h
@@ -0,0 +1,517 @@
+/* Copyright (C) 1999,2001
+ *
+ * Author: J.E.J.Bottomley@HansenPartnership.com
+ *
+ * Standard include definitions for the NCR Voyager system */
+
+#undef  VOYAGER_DEBUG
+#undef  VOYAGER_CAT_DEBUG
+
+#ifdef VOYAGER_DEBUG
+#define VDEBUG(x)       printk x
+#else
+#define VDEBUG(x)
+#endif
+
+/* There are three levels of voyager machine: 3,4 and 5. The rule is
+ * if it's less than 3435 it's a Level 3 except for a 3360 which is
+ * a level 4.  A 3435 or above is a Level 5 */
+#define VOYAGER_LEVEL5_AND_ABOVE        0x3435
+#define VOYAGER_LEVEL4                  0x3360
+
+/* The L4 DINO ASIC */
+#define VOYAGER_DINO                    0x43
+
+/* voyager ports in standard I/O space */
+#define VOYAGER_MC_SETUP        0x96
+
+
+#define VOYAGER_CAT_CONFIG_PORT                 0x97
+#       define VOYAGER_CAT_DESELECT             0xff
+#define VOYAGER_SSPB_RELOCATION_PORT            0x98
+
+/* Valid CAT controller commands */
+/* start instruction register cycle */
+#define VOYAGER_CAT_IRCYC                       0x01
+/* start data register cycle */
+#define VOYAGER_CAT_DRCYC                       0x02
+/* move to execute state */
+#define VOYAGER_CAT_RUN                         0x0F
+/* end operation */
+#define VOYAGER_CAT_END                         0x80
+/* hold in idle state */
+#define VOYAGER_CAT_HOLD                        0x90
+/* single step an "intest" vector */
+#define VOYAGER_CAT_STEP                        0xE0
+/* return cat controller to CLEMSON mode */
+#define VOYAGER_CAT_CLEMSON                     0xFF
+
+/* the default cat command header */
+#define VOYAGER_CAT_HEADER                      0x7F
+
+/* the range of possible CAT module ids in the system */
+#define VOYAGER_MIN_MODULE                      0x10
+#define VOYAGER_MAX_MODULE                      0x1f
+
+/* The voyager registers per asic */
+#define VOYAGER_ASIC_ID_REG                     0x00
+#define VOYAGER_ASIC_TYPE_REG                   0x01
+/* the sub address registers can be made auto incrementing on reads */
+#define VOYAGER_AUTO_INC_REG                    0x02
+#       define VOYAGER_AUTO_INC                 0x04
+#       define VOYAGER_NO_AUTO_INC              0xfb
+#define VOYAGER_SUBADDRDATA                     0x03
+#define VOYAGER_SCANPATH                        0x05
+#       define VOYAGER_CONNECT_ASIC             0x01
+#       define VOYAGER_DISCONNECT_ASIC          0xfe
+#define VOYAGER_SUBADDRLO                       0x06
+#define VOYAGER_SUBADDRHI                       0x07
+#define VOYAGER_SUBMODSELECT                    0x08
+#define VOYAGER_SUBMODPRESENT                   0x09
+
+#define VOYAGER_SUBADDR_LO                      0xff
+#define VOYAGER_SUBADDR_HI                      0xffff
+
+/* the maximum size of a scan path -- used to form instructions */
+#define VOYAGER_MAX_SCAN_PATH                   0x100
+/* the biggest possible register size (in bytes) */
+#define VOYAGER_MAX_REG_SIZE                    4
+
+/* Total number of possible modules (including submodules) */
+#define VOYAGER_MAX_MODULES                     16
+/* Largest number of asics per module */
+#define VOYAGER_MAX_ASICS_PER_MODULE            7
+
+/* the CAT asic of each module is always the first one */
+#define VOYAGER_CAT_ID                          0
+#define VOYAGER_PSI                             0x1a
+
+/* voyager instruction operations and registers */
+#define VOYAGER_READ_CONFIG                     0x1
+#define VOYAGER_WRITE_CONFIG                    0x2
+#define VOYAGER_BYPASS                          0xff
+
+typedef struct voyager_asic 
+{
+        __u8    asic_addr;      /* ASIC address; Level 4 */
+        __u8    asic_type;      /* ASIC type */
+        __u8    asic_id;        /* ASIC id */
+        __u8    jtag_id[4];     /* JTAG id */
+        __u8    asic_location;  /* Location within scan path; start w/ 0 */
+        __u8    bit_location;   /* Location within bit stream; start w/ 0 */
+        __u8    ireg_length;    /* Instruction register length */
+        __u16   subaddr;        /* Amount of sub address space */
+        struct voyager_asic *next;      /* Next asic in linked list */
+} voyager_asic_t;
+
+typedef struct voyager_module {
+        __u8    module_addr;            /* Module address */
+        __u8    scan_path_connected;    /* Scan path connected */
+        __u16   ee_size;                /* Size of the EEPROM */
+        __u16   num_asics;              /* Number of Asics */
+        __u16   inst_bits;              /* Instruction bits in the scan path */
+        __u16   largest_reg;            /* Largest register in the scan path */
+        __u16   smallest_reg;           /* Smallest register in the scan path */
+        voyager_asic_t   *asic;         /* First ASIC in scan path (CAT_I) */
+        struct   voyager_module *submodule;     /* Submodule pointer */ 
+        struct   voyager_module *next;          /* Next module in linked list */
+} voyager_module_t;
+
+typedef struct voyager_eeprom_hdr {
+         __u8  module_id[4];
+         __u8  version_id;
+         __u8  config_id;
+         __u16 boundry_id;      /* boundary scan id */
+         __u16 ee_size;         /* size of EEPROM */
+         __u8  assembly[11];    /* assembly # */
+         __u8  assembly_rev;    /* assembly rev */
+         __u8  tracer[4];       /* tracer number */
+         __u16 assembly_cksum;  /* asm checksum */
+         __u16 power_consump;   /* pwr requirements */
+         __u16 num_asics;       /* number of asics */
+         __u16 bist_time;       /* min. bist time */
+         __u16 err_log_offset;  /* error log offset */
+         __u16 scan_path_offset;/* scan path offset */
+         __u16 cct_offset;
+         __u16 log_length;      /* length of err log */
+         __u16 xsum_end;        /* offset to end of
+                                                           checksum */
+         __u8  reserved[4];
+         __u8  sflag;           /* starting sentinal */
+         __u8  part_number[13]; /* prom part number */
+         __u8  version[10];     /* version number */
+         __u8  signature[8];
+         __u16 eeprom_chksum;
+         __u32  data_stamp_offset;
+         __u8  eflag ;           /* ending sentinal */
+} __attribute__((packed)) voyager_eprom_hdr_t;
+
+
+
+#define VOYAGER_EPROM_SIZE_OFFSET   ((__u16)(&(((voyager_eprom_hdr_t *)0)->ee_size)))
+#define VOYAGER_XSUM_END_OFFSET         0x2a
+
+/* the following three definitions are for internal table layouts
+ * in the module EPROMs.  We really only care about the IDs and
+ * offsets */
+typedef struct voyager_sp_table {
+        __u8 asic_id;
+        __u8 bypass_flag;
+        __u16 asic_data_offset;
+        __u16 config_data_offset;
+} __attribute__((packed)) voyager_sp_table_t;
+
+typedef struct voyager_jtag_table {
+        __u8 icode[4];
+        __u8 runbist[4];
+        __u8 intest[4];
+        __u8 samp_preld[4];
+        __u8 ireg_len;
+} __attribute__((packed)) voyager_jtt_t;
+
+typedef struct voyager_asic_data_table {
+        __u8 jtag_id[4];
+        __u16 length_bsr;
+        __u16 length_bist_reg;
+        __u32 bist_clk;
+        __u16 subaddr_bits;
+        __u16 seed_bits;
+        __u16 sig_bits;
+        __u16 jtag_offset;
+} __attribute__((packed)) voyager_at_t;
+
+/* Voyager Interrupt Controller (VIC) registers */
+
+/* Base to add to Cross Processor Interrupts (CPIs) when triggering
+ * the CPU IRQ line */
+/* register defines for the WCBICs (one per processor) */
+#define VOYAGER_WCBIC0  0x41            /* bus A node P1 processor 0 */
+#define VOYAGER_WCBIC1  0x49            /* bus A node P1 processor 1 */
+#define VOYAGER_WCBIC2  0x51            /* bus A node P2 processor 0 */
+#define VOYAGER_WCBIC3  0x59            /* bus A node P2 processor 1 */
+#define VOYAGER_WCBIC4  0x61            /* bus B node P1 processor 0 */
+#define VOYAGER_WCBIC5  0x69            /* bus B node P1 processor 1 */
+#define VOYAGER_WCBIC6  0x71            /* bus B node P2 processor 0 */
+#define VOYAGER_WCBIC7  0x79            /* bus B node P2 processor 1 */
+
+
+/* top of memory registers */
+#define VOYAGER_WCBIC_TOM_L     0x4
+#define VOYAGER_WCBIC_TOM_H     0x5
+
+/* register defines for Voyager Memory Contol (VMC) 
+ * these are present on L4 machines only */
+#define VOYAGER_VMC1            0x81
+#define VOYAGER_VMC2            0x91
+#define VOYAGER_VMC3            0xa1
+#define VOYAGER_VMC4            0xb1
+
+/* VMC Ports */
+#define VOYAGER_VMC_MEMORY_SETUP        0x9
+#       define VMC_Interleaving         0x01
+#       define VMC_4Way                 0x02
+#       define VMC_EvenCacheLines       0x04
+#       define VMC_HighLine             0x08
+#       define VMC_Start0_Enable        0x20
+#       define VMC_Start1_Enable        0x40
+#       define VMC_Vremap               0x80
+#define VOYAGER_VMC_BANK_DENSITY        0xa
+#       define  VMC_BANK_EMPTY          0
+#       define  VMC_BANK_4MB            1
+#       define  VMC_BANK_16MB           2
+#       define  VMC_BANK_64MB           3
+#       define  VMC_BANK0_MASK          0x03
+#       define  VMC_BANK1_MASK          0x0C
+#       define  VMC_BANK2_MASK          0x30
+#       define  VMC_BANK3_MASK          0xC0
+
+/* Magellan Memory Controller (MMC) defines - present on L5 */
+#define VOYAGER_MMC_ASIC_ID             1
+/* the two memory modules corresponding to memory cards in the system */
+#define VOYAGER_MMC_MEMORY0_MODULE      0x14
+#define VOYAGER_MMC_MEMORY1_MODULE      0x15
+/* the Magellan Memory Address (MMA) defines */
+#define VOYAGER_MMA_ASIC_ID             2
+
+/* Submodule number for the Quad Baseboard */
+#define VOYAGER_QUAD_BASEBOARD          1
+
+/* ASIC defines for the Quad Baseboard */
+#define VOYAGER_QUAD_QDATA0             1
+#define VOYAGER_QUAD_QDATA1             2
+#define VOYAGER_QUAD_QABC               3
+
+/* Useful areas in extended CMOS */
+#define VOYAGER_PROCESSOR_PRESENT_MASK  0x88a
+#define VOYAGER_MEMORY_CLICKMAP         0xa23
+#define VOYAGER_DUMP_LOCATION           0xb1a
+
+/* SUS In Control bit - used to tell SUS that we don't need to be
+ * babysat anymore */
+#define VOYAGER_SUS_IN_CONTROL_PORT     0x3ff
+#       define VOYAGER_IN_CONTROL_FLAG  0x80
+
+/* Voyager PSI defines */
+#define VOYAGER_PSI_STATUS_REG          0x08
+#       define PSI_DC_FAIL              0x01
+#       define PSI_MON                  0x02
+#       define PSI_FAULT                0x04
+#       define PSI_ALARM                0x08
+#       define PSI_CURRENT              0x10
+#       define PSI_DVM                  0x20
+#       define PSI_PSCFAULT             0x40
+#       define PSI_STAT_CHG             0x80
+
+#define VOYAGER_PSI_SUPPLY_REG          0x8000
+        /* read */
+#       define PSI_FAIL_DC              0x01
+#       define PSI_FAIL_AC              0x02
+#       define PSI_MON_INT              0x04
+#       define PSI_SWITCH_OFF           0x08
+#       define PSI_HX_OFF               0x10
+#       define PSI_SECURITY             0x20
+#       define PSI_CMOS_BATT_LOW        0x40
+#       define PSI_CMOS_BATT_FAIL       0x80
+        /* write */
+#       define PSI_CLR_SWITCH_OFF       0x13
+#       define PSI_CLR_HX_OFF           0x14
+#       define PSI_CLR_CMOS_BATT_FAIL   0x17
+
+#define VOYAGER_PSI_MASK                0x8001
+#       define PSI_MASK_MASK            0x10
+
+#define VOYAGER_PSI_AC_FAIL_REG         0x8004
+#define AC_FAIL_STAT_CHANGE             0x80
+
+#define VOYAGER_PSI_GENERAL_REG         0x8007
+        /* read */
+#       define PSI_SWITCH_ON            0x01
+#       define PSI_SWITCH_ENABLED       0x02
+#       define PSI_ALARM_ENABLED        0x08
+#       define PSI_SECURE_ENABLED       0x10
+#       define PSI_COLD_RESET           0x20
+#       define PSI_COLD_START           0x80
+        /* write */
+#       define PSI_POWER_DOWN           0x10
+#       define PSI_SWITCH_DISABLE       0x01
+#       define PSI_SWITCH_ENABLE        0x11
+#       define PSI_CLEAR                0x12
+#       define PSI_ALARM_DISABLE        0x03
+#       define PSI_ALARM_ENABLE         0x13
+#       define PSI_CLEAR_COLD_RESET     0x05
+#       define PSI_SET_COLD_RESET       0x15
+#       define PSI_CLEAR_COLD_START     0x07
+#       define PSI_SET_COLD_START       0x17
+
+
+
+struct voyager_bios_info {
+        __u8    len;
+        __u8    major;
+        __u8    minor;
+        __u8    debug;
+        __u8    num_classes;
+        __u8    class_1;
+        __u8    class_2;
+};
+
+/* The following structures and definitions are for the Kernel/SUS
+ * interface these are needed to find out how SUS initialised any Quad
+ * boards in the system */
+
+#define NUMBER_OF_MC_BUSSES     2
+#define SLOTS_PER_MC_BUS        8
+#define MAX_CPUS                16      /* 16 way CPU system */
+#define MAX_PROCESSOR_BOARDS    4       /* 4 processor slot system */
+#define MAX_CACHE_LEVELS        4       /* # of cache levels supported */
+#define MAX_SHARED_CPUS         4       /* # of CPUs that can share a LARC */
+#define NUMBER_OF_POS_REGS      8
+
+typedef struct {
+        __u8    MC_Slot;
+        __u8    POS_Values[NUMBER_OF_POS_REGS];
+} __attribute__((packed)) MC_SlotInformation_t;
+
+struct QuadDescription {
+        __u8  Type;     /* for type 0 (DYADIC or MONADIC) all fields
+                         * will be zero except for slot */
+        __u8 StructureVersion;
+        __u32 CPI_BaseAddress;
+        __u32  LARC_BankSize;
+        __u32 LocalMemoryStateBits;
+        __u8  Slot; /* Processor slots 1 - 4 */
+} __attribute__((packed));
+
+struct ProcBoardInfo { 
+        __u8 Type;
+        __u8 StructureVersion;
+        __u8 NumberOfBoards;
+        struct QuadDescription QuadData[MAX_PROCESSOR_BOARDS];
+} __attribute__((packed));
+
+struct CacheDescription {
+        __u8 Level;
+        __u32 TotalSize;
+        __u16 LineSize;
+        __u8  Associativity;
+        __u8  CacheType;
+        __u8  WriteType;
+        __u8  Number_CPUs_SharedBy;
+        __u8  Shared_CPUs_Hardware_IDs[MAX_SHARED_CPUS];
+
+} __attribute__((packed));
+
+struct CPU_Description {
+        __u8 CPU_HardwareId;
+        char *FRU_String;
+        __u8 NumberOfCacheLevels;
+        struct CacheDescription CacheLevelData[MAX_CACHE_LEVELS];
+} __attribute__((packed));
+
+struct CPU_Info {
+        __u8 Type;
+        __u8 StructureVersion;
+        __u8 NumberOf_CPUs;
+        struct CPU_Description CPU_Data[MAX_CPUS];
+} __attribute__((packed));
+
+
+/*
+ * This structure will be used by SUS and the OS.
+ * The assumption about this structure is that no blank space is
+ * packed in it by our friend the compiler.
+ */
+typedef struct {
+        __u8    Mailbox_SUS;            /* Written to by SUS to give commands/response to the OS */
+        __u8    Mailbox_OS;             /* Written to by the OS to give commands/response to SUS */
+        __u8    SUS_MailboxVersion;     /* Tells the OS which iteration of the interface SUS supports */
+        __u8    OS_MailboxVersion;      /* Tells SUS which iteration of the interface the OS supports */
+        __u32   OS_Flags;               /* Flags set by the OS as info for SUS */
+        __u32   SUS_Flags;              /* Flags set by SUS as info for the OS */
+        __u32   WatchDogPeriod;         /* Watchdog period (in seconds) which the DP uses to see if the OS is dead */
+        __u32   WatchDogCount;          /* Updated by the OS on every tic. */
+        __u32   MemoryFor_SUS_ErrorLog; /* Flat 32 bit address which tells SUS where to stuff the SUS error log on a dump */
+        MC_SlotInformation_t  MC_SlotInfo[NUMBER_OF_MC_BUSSES*SLOTS_PER_MC_BUS];        /* Storage for MCA POS data */
+        /* All new SECOND_PASS_INTERFACE fields added from this point */
+        struct ProcBoardInfo    *BoardData;
+        struct CPU_Info         *CPU_Data;
+        /* All new fields must be added from this point */
+} Voyager_KernelSUS_Mbox_t;
+
+/* structure for finding the right memory address to send a QIC CPI to */
+struct voyager_qic_cpi {
+        /* Each cache line (32 bytes) can trigger a cpi.  The cpi
+         * read/write may occur anywhere in the cache line---pick the
+         * middle to be safe */
+        struct  {
+                __u32 pad1[3];
+                __u32 cpi;
+                __u32 pad2[4];
+        } qic_cpi[8];
+};
+
+struct voyager_status {
+        __u32   power_fail:1;
+        __u32   switch_off:1;
+        __u32   request_from_kernel:1;
+};
+
+struct voyager_psi_regs {
+        __u8 cat_id;
+        __u8 cat_dev;
+        __u8 cat_control;
+        __u8 subaddr;
+        __u8 dummy4;
+        __u8 checkbit;
+        __u8 subaddr_low;
+        __u8 subaddr_high;
+        __u8 intstatus;
+        __u8 stat1;
+        __u8 stat3;
+        __u8 fault;
+        __u8 tms;
+        __u8 gen;
+        __u8 sysconf;
+        __u8 dummy15;
+};
+
+struct voyager_psi_subregs {
+        __u8 supply;
+        __u8 mask;
+        __u8 present;
+        __u8 DCfail;
+        __u8 ACfail;
+        __u8 fail;
+        __u8 UPSfail;
+        __u8 genstatus;
+};
+
+struct voyager_psi {
+        struct voyager_psi_regs regs;
+        struct voyager_psi_subregs subregs;
+};
+
+struct voyager_SUS {
+#define VOYAGER_DUMP_BUTTON_NMI         0x1
+#define VOYAGER_SUS_VALID               0x2
+#define VOYAGER_SYSINT_COMPLETE         0x3
+        __u8    SUS_mbox;
+#define VOYAGER_NO_COMMAND              0x0
+#define VOYAGER_IGNORE_DUMP             0x1
+#define VOYAGER_DO_DUMP                 0x2
+#define VOYAGER_SYSINT_HANDSHAKE        0x3
+#define VOYAGER_DO_MEM_DUMP             0x4
+#define VOYAGER_SYSINT_WAS_RECOVERED    0x5
+        __u8    kernel_mbox;
+#define VOYAGER_MAILBOX_VERSION         0x10
+        __u8    SUS_version;
+        __u8    kernel_version;
+#define VOYAGER_OS_HAS_SYSINT           0x1
+#define VOYAGER_OS_IN_PROGRESS          0x2
+#define VOYAGER_UPDATING_WDPERIOD       0x4
+        __u32   kernel_flags;
+#define VOYAGER_SUS_BOOTING             0x1
+#define VOYAGER_SUS_IN_PROGRESS         0x2
+        __u32   SUS_flags;
+        __u32   watchdog_period;
+        __u32   watchdog_count;
+        __u32   SUS_errorlog;
+        /* lots of system configuration stuff under here */
+};
+        
+/* Variables exported by voyager_smp */
+extern __u32 voyager_extended_vic_processors;
+extern __u32 voyager_allowed_boot_processors;
+extern __u32 voyager_quad_processors;
+extern struct voyager_qic_cpi *voyager_quad_cpi_addr[NR_CPUS];
+extern struct voyager_SUS *voyager_SUS;
+
+/* variables exported always */
+extern struct task_struct *voyager_thread;
+extern int voyager_level;
+extern struct voyager_status voyager_status;
+
+/* functions exported by the voyager and voyager_smp modules */
+extern int voyager_cat_readb(__u8 module, __u8 asic, int reg);
+extern void voyager_cat_init(void);
+extern void voyager_detect(struct voyager_bios_info *);
+extern void voyager_trap_init(void);
+extern void voyager_setup_irqs(void);
+extern int voyager_memory_detect(int region, __u32 *addr, __u32 *length);
+extern void voyager_smp_intr_init(void);
+extern __u8 voyager_extended_cmos_read(__u16 cmos_address);
+extern void voyager_smp_dump(void);
+extern void voyager_timer_interrupt(void);
+extern void smp_local_timer_interrupt(void);
+extern void voyager_power_off(void);
+extern void smp_voyager_power_off(void *dummy);
+extern void voyager_restart(void);
+extern void voyager_cat_power_off(void);
+extern void voyager_cat_do_common_interrupt(void);
+extern void voyager_handle_nmi(void);
+/* Commands for the following are */
+#define VOYAGER_PSI_READ        0
+#define VOYAGER_PSI_WRITE       1
+#define VOYAGER_PSI_SUBREAD     2
+#define VOYAGER_PSI_SUBWRITE    3
+extern void voyager_cat_psi(__u8, __u16, __u8 *);
diff --git a/include/asm-x86/vsyscall.h b/include/asm-x86/vsyscall.h
new file mode 100644
index 000000000000..3b8ceb4af2cf
--- /dev/null
+++ b/include/asm-x86/vsyscall.h
@@ -0,0 +1,44 @@
+#ifndef _ASM_X86_64_VSYSCALL_H_
+#define _ASM_X86_64_VSYSCALL_H_
+
+enum vsyscall_num {
+        __NR_vgettimeofday,
+        __NR_vtime,
+        __NR_vgetcpu,
+};
+
+#define VSYSCALL_START (-10UL << 20)
+#define VSYSCALL_SIZE 1024
+#define VSYSCALL_END (-2UL << 20)
+#define VSYSCALL_MAPPED_PAGES 1
+#define VSYSCALL_ADDR(vsyscall_nr) (VSYSCALL_START+VSYSCALL_SIZE*(vsyscall_nr))
+
+#ifdef __KERNEL__
+#include <linux/seqlock.h>
+
+#define __section_vgetcpu_mode __attribute__ ((unused, __section__ (".vgetcpu_mode"), aligned(16)))
+#define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16)))
+
+/* Definitions for CONFIG_GENERIC_TIME definitions */
+#define __section_vsyscall_gtod_data __attribute__ \
+        ((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 VGETCPU_RDTSCP  1
+#define VGETCPU_LSL     2
+
+#define hpet_readl(a)           readl((const void __iomem *)fix_to_virt(FIX_HPET_BASE) + a)
+#define hpet_writel(d,a)        writel(d, (void __iomem *)fix_to_virt(FIX_HPET_BASE) + a)
+
+extern int __vgetcpu_mode;
+extern volatile unsigned long __jiffies;
+
+/* kernel space (writeable) */
+extern int vgetcpu_mode;
+extern struct timezone sys_tz;
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_64_VSYSCALL_H_ */
diff --git a/include/asm-x86/vsyscall32.h b/include/asm-x86/vsyscall32.h
new file mode 100644
index 000000000000..c631c082f8f7
--- /dev/null
+++ b/include/asm-x86/vsyscall32.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_VSYSCALL32_H
+#define _ASM_VSYSCALL32_H 1
+
+/* Values need to match arch/x86_64/ia32/vsyscall.lds */
+
+#ifdef __ASSEMBLY__
+#define VSYSCALL32_BASE 0xffffe000
+#define VSYSCALL32_SYSEXIT (VSYSCALL32_BASE + 0x410)
+#else
+#define VSYSCALL32_BASE 0xffffe000UL
+#define VSYSCALL32_END (VSYSCALL32_BASE + PAGE_SIZE)
+#define VSYSCALL32_EHDR ((const struct elf32_hdr *) VSYSCALL32_BASE)
+
+#define VSYSCALL32_VSYSCALL ((void *)VSYSCALL32_BASE + 0x400) 
+#define VSYSCALL32_SYSEXIT ((void *)VSYSCALL32_BASE + 0x410)
+#define VSYSCALL32_SIGRETURN ((void __user *)VSYSCALL32_BASE + 0x500) 
+#define VSYSCALL32_RTSIGRETURN ((void __user *)VSYSCALL32_BASE + 0x600) 
+#endif
+
+#endif
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
new file mode 100644
index 000000000000..bc0ee7d961ca
--- /dev/null
+++ b/include/asm-x86/xen/hypercall.h
@@ -0,0 +1,413 @@
+/******************************************************************************
+ * hypercall.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __HYPERCALL_H__
+#define __HYPERCALL_H__
+
+#include <linux/errno.h>
+#include <linux/string.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/sched.h>
+#include <xen/interface/physdev.h>
+
+extern struct { char _entry[32]; } hypercall_page[];
+
+#define _hypercall0(type, name)                                         \
+({                                                                      \
+        long __res;                                                     \
+        asm volatile (                                                  \
+                "call %[call]"                                          \
+                : "=a" (__res)                                          \
+                : [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
+                : "memory" );                                           \
+        (type)__res;                                                    \
+})
+
+#define _hypercall1(type, name, a1)                                     \
+({                                                                      \
+        long __res, __ign1;                                             \
+        asm volatile (                                                  \
+                "call %[call]"                                          \
+                : "=a" (__res), "=b" (__ign1)                           \
+                : "1" ((long)(a1)),                                     \
+                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
+                : "memory" );                                           \
+        (type)__res;                                                    \
+})
+
+#define _hypercall2(type, name, a1, a2)                                 \
+({                                                                      \
+        long __res, __ign1, __ign2;                                     \
+        asm volatile (                                                  \
+                "call %[call]"                                          \
+                : "=a" (__res), "=b" (__ign1), "=c" (__ign2)            \
+                : "1" ((long)(a1)), "2" ((long)(a2)),                   \
+                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
+                : "memory" );                                           \
+        (type)__res;                                                    \
+})
+
+#define _hypercall3(type, name, a1, a2, a3)                             \
+({                                                                      \
+        long __res, __ign1, __ign2, __ign3;                             \
+        asm volatile (                                                  \
+                "call %[call]"                                          \
+                : "=a" (__res), "=b" (__ign1), "=c" (__ign2),           \
+                "=d" (__ign3)                                           \
+                : "1" ((long)(a1)), "2" ((long)(a2)),                   \
+                  "3" ((long)(a3)),                                     \
+                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
+                : "memory" );                                           \
+        (type)__res;                                                    \
+})
+
+#define _hypercall4(type, name, a1, a2, a3, a4)                         \
+({                                                                      \
+        long __res, __ign1, __ign2, __ign3, __ign4;                     \
+        asm volatile (                                                  \
+                "call %[call]"                                          \
+                : "=a" (__res), "=b" (__ign1), "=c" (__ign2),           \
+                "=d" (__ign3), "=S" (__ign4)                            \
+                : "1" ((long)(a1)), "2" ((long)(a2)),                   \
+                  "3" ((long)(a3)), "4" ((long)(a4)),                   \
+                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
+                : "memory" );                                           \
+        (type)__res;                                                    \
+})
+
+#define _hypercall5(type, name, a1, a2, a3, a4, a5)                     \
+({                                                                      \
+        long __res, __ign1, __ign2, __ign3, __ign4, __ign5;             \
+        asm volatile (                                                  \
+                "call %[call]"                                          \
+                : "=a" (__res), "=b" (__ign1), "=c" (__ign2),           \
+                "=d" (__ign3), "=S" (__ign4), "=D" (__ign5)             \
+                : "1" ((long)(a1)), "2" ((long)(a2)),                   \
+                  "3" ((long)(a3)), "4" ((long)(a4)),                   \
+                  "5" ((long)(a5)),                                     \
+                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
+                : "memory" );                                           \
+        (type)__res;                                                    \
+})
+
+static inline int
+HYPERVISOR_set_trap_table(struct trap_info *table)
+{
+        return _hypercall1(int, set_trap_table, table);
+}
+
+static inline int
+HYPERVISOR_mmu_update(struct mmu_update *req, int count,
+                      int *success_count, domid_t domid)
+{
+        return _hypercall4(int, mmu_update, req, count, success_count, domid);
+}
+
+static inline int
+HYPERVISOR_mmuext_op(struct mmuext_op *op, int count,
+                     int *success_count, domid_t domid)
+{
+        return _hypercall4(int, mmuext_op, op, count, success_count, domid);
+}
+
+static inline int
+HYPERVISOR_set_gdt(unsigned long *frame_list, int entries)
+{
+        return _hypercall2(int, set_gdt, frame_list, entries);
+}
+
+static inline int
+HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp)
+{
+        return _hypercall2(int, stack_switch, ss, esp);
+}
+
+static inline int
+HYPERVISOR_set_callbacks(unsigned long event_selector,
+                         unsigned long event_address,
+                         unsigned long failsafe_selector,
+                         unsigned long failsafe_address)
+{
+        return _hypercall4(int, set_callbacks,
+                           event_selector, event_address,
+                           failsafe_selector, failsafe_address);
+}
+
+static inline int
+HYPERVISOR_fpu_taskswitch(int set)
+{
+        return _hypercall1(int, fpu_taskswitch, set);
+}
+
+static inline int
+HYPERVISOR_sched_op(int cmd, unsigned long arg)
+{
+        return _hypercall2(int, sched_op, cmd, arg);
+}
+
+static inline long
+HYPERVISOR_set_timer_op(u64 timeout)
+{
+        unsigned long timeout_hi = (unsigned long)(timeout>>32);
+        unsigned long timeout_lo = (unsigned long)timeout;
+        return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi);
+}
+
+static inline int
+HYPERVISOR_set_debugreg(int reg, unsigned long value)
+{
+        return _hypercall2(int, set_debugreg, reg, value);
+}
+
+static inline unsigned long
+HYPERVISOR_get_debugreg(int reg)
+{
+        return _hypercall1(unsigned long, get_debugreg, reg);
+}
+
+static inline int
+HYPERVISOR_update_descriptor(u64 ma, u64 desc)
+{
+        return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
+}
+
+static inline int
+HYPERVISOR_memory_op(unsigned int cmd, void *arg)
+{
+        return _hypercall2(int, memory_op, cmd, arg);
+}
+
+static inline int
+HYPERVISOR_multicall(void *call_list, int nr_calls)
+{
+        return _hypercall2(int, multicall, call_list, nr_calls);
+}
+
+static inline int
+HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
+                             unsigned long flags)
+{
+        unsigned long pte_hi = 0;
+#ifdef CONFIG_X86_PAE
+        pte_hi = new_val.pte_high;
+#endif
+        return _hypercall4(int, update_va_mapping, va,
+                           new_val.pte_low, pte_hi, flags);
+}
+
+static inline int
+HYPERVISOR_event_channel_op(int cmd, void *arg)
+{
+        int rc = _hypercall2(int, event_channel_op, cmd, arg);
+        if (unlikely(rc == -ENOSYS)) {
+                struct evtchn_op op;
+                op.cmd = cmd;
+                memcpy(&op.u, arg, sizeof(op.u));
+                rc = _hypercall1(int, event_channel_op_compat, &op);
+                memcpy(arg, &op.u, sizeof(op.u));
+        }
+        return rc;
+}
+
+static inline int
+HYPERVISOR_xen_version(int cmd, void *arg)
+{
+        return _hypercall2(int, xen_version, cmd, arg);
+}
+
+static inline int
+HYPERVISOR_console_io(int cmd, int count, char *str)
+{
+        return _hypercall3(int, console_io, cmd, count, str);
+}
+
+static inline int
+HYPERVISOR_physdev_op(int cmd, void *arg)
+{
+        int rc = _hypercall2(int, physdev_op, cmd, arg);
+        if (unlikely(rc == -ENOSYS)) {
+                struct physdev_op op;
+                op.cmd = cmd;
+                memcpy(&op.u, arg, sizeof(op.u));
+                rc = _hypercall1(int, physdev_op_compat, &op);
+                memcpy(arg, &op.u, sizeof(op.u));
+        }
+        return rc;
+}
+
+static inline int
+HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count)
+{
+        return _hypercall3(int, grant_table_op, cmd, uop, count);
+}
+
+static inline int
+HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val,
+                                         unsigned long flags, domid_t domid)
+{
+        unsigned long pte_hi = 0;
+#ifdef CONFIG_X86_PAE
+        pte_hi = new_val.pte_high;
+#endif
+        return _hypercall5(int, update_va_mapping_otherdomain, va,
+                           new_val.pte_low, pte_hi, flags, domid);
+}
+
+static inline int
+HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type)
+{
+        return _hypercall2(int, vm_assist, cmd, type);
+}
+
+static inline int
+HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args)
+{
+        return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args);
+}
+
+static inline int
+HYPERVISOR_suspend(unsigned long srec)
+{
+        return _hypercall3(int, sched_op, SCHEDOP_shutdown,
+                           SHUTDOWN_suspend, srec);
+}
+
+static inline int
+HYPERVISOR_nmi_op(unsigned long op, unsigned long arg)
+{
+        return _hypercall2(int, nmi_op, op, arg);
+}
+
+static inline void
+MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
+                        pte_t new_val, unsigned long flags)
+{
+        mcl->op = __HYPERVISOR_update_va_mapping;
+        mcl->args[0] = va;
+#ifdef CONFIG_X86_PAE
+        mcl->args[1] = new_val.pte_low;
+        mcl->args[2] = new_val.pte_high;
+#else
+        mcl->args[1] = new_val.pte_low;
+        mcl->args[2] = 0;
+#endif
+        mcl->args[3] = flags;
+}
+
+static inline void
+MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd,
+                     void *uop, unsigned int count)
+{
+        mcl->op = __HYPERVISOR_grant_table_op;
+        mcl->args[0] = cmd;
+        mcl->args[1] = (unsigned long)uop;
+        mcl->args[2] = count;
+}
+
+static inline void
+MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long va,
+                                    pte_t new_val, unsigned long flags,
+                                    domid_t domid)
+{
+        mcl->op = __HYPERVISOR_update_va_mapping_otherdomain;
+        mcl->args[0] = va;
+#ifdef CONFIG_X86_PAE
+        mcl->args[1] = new_val.pte_low;
+        mcl->args[2] = new_val.pte_high;
+#else
+        mcl->args[1] = new_val.pte_low;
+        mcl->args[2] = 0;
+#endif
+        mcl->args[3] = flags;
+        mcl->args[4] = domid;
+}
+
+static inline void
+MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
+                        struct desc_struct desc)
+{
+        mcl->op = __HYPERVISOR_update_descriptor;
+        mcl->args[0] = maddr;
+        mcl->args[1] = maddr >> 32;
+        mcl->args[2] = desc.a;
+        mcl->args[3] = desc.b;
+}
+
+static inline void
+MULTI_memory_op(struct multicall_entry *mcl, unsigned int cmd, void *arg)
+{
+        mcl->op = __HYPERVISOR_memory_op;
+        mcl->args[0] = cmd;
+        mcl->args[1] = (unsigned long)arg;
+}
+
+static inline void
+MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
+                 int count, int *success_count, domid_t domid)
+{
+        mcl->op = __HYPERVISOR_mmu_update;
+        mcl->args[0] = (unsigned long)req;
+        mcl->args[1] = count;
+        mcl->args[2] = (unsigned long)success_count;
+        mcl->args[3] = domid;
+}
+
+static inline void
+MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
+                int *success_count, domid_t domid)
+{
+        mcl->op = __HYPERVISOR_mmuext_op;
+        mcl->args[0] = (unsigned long)op;
+        mcl->args[1] = count;
+        mcl->args[2] = (unsigned long)success_count;
+        mcl->args[3] = domid;
+}
+
+static inline void
+MULTI_set_gdt(struct multicall_entry *mcl, unsigned long *frames, int entries)
+{
+        mcl->op = __HYPERVISOR_set_gdt;
+        mcl->args[0] = (unsigned long)frames;
+        mcl->args[1] = entries;
+}
+
+static inline void
+MULTI_stack_switch(struct multicall_entry *mcl,
+                   unsigned long ss, unsigned long esp)
+{
+        mcl->op = __HYPERVISOR_stack_switch;
+        mcl->args[0] = ss;
+        mcl->args[1] = esp;
+}
+
+#endif /* __HYPERCALL_H__ */
diff --git a/include/asm-x86/xen/hypervisor.h b/include/asm-x86/xen/hypervisor.h
new file mode 100644
index 000000000000..8e15dd28c91f
--- /dev/null
+++ b/include/asm-x86/xen/hypervisor.h
@@ -0,0 +1,73 @@
+/******************************************************************************
+ * hypervisor.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __HYPERVISOR_H__
+#define __HYPERVISOR_H__
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/version.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+
+#include <asm/ptrace.h>
+#include <asm/page.h>
+#include <asm/desc.h>
+#if defined(__i386__)
+#  ifdef CONFIG_X86_PAE
+#   include <asm-generic/pgtable-nopud.h>
+#  else
+#   include <asm-generic/pgtable-nopmd.h>
+#  endif
+#endif
+#include <asm/xen/hypercall.h>
+
+/* arch/i386/kernel/setup.c */
+extern struct shared_info *HYPERVISOR_shared_info;
+extern struct start_info *xen_start_info;
+#define is_initial_xendomain() (xen_start_info->flags & SIF_INITDOMAIN)
+
+/* arch/i386/mach-xen/evtchn.c */
+/* Force a proper event-channel callback from Xen. */
+extern void force_evtchn_callback(void);
+
+/* Turn jiffies into Xen system time. */
+u64 jiffies_to_st(unsigned long jiffies);
+
+
+#define MULTI_UVMFLAGS_INDEX 3
+#define MULTI_UVMDOMID_INDEX 4
+
+#define is_running_on_xen()     (xen_start_info ? 1 : 0)
+
+#endif /* __HYPERVISOR_H__ */
diff --git a/include/asm-x86/xen/interface.h b/include/asm-x86/xen/interface.h
new file mode 100644
index 000000000000..165c3968e138
--- /dev/null
+++ b/include/asm-x86/xen/interface.h
@@ -0,0 +1,188 @@
+/******************************************************************************
+ * arch-x86_32.h
+ *
+ * Guest OS interface to x86 32-bit Xen.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef __XEN_PUBLIC_ARCH_X86_32_H__
+#define __XEN_PUBLIC_ARCH_X86_32_H__
+
+#ifdef __XEN__
+#define __DEFINE_GUEST_HANDLE(name, type) \
+    typedef struct { type *p; } __guest_handle_ ## name
+#else
+#define __DEFINE_GUEST_HANDLE(name, type) \
+    typedef type * __guest_handle_ ## name
+#endif
+
+#define DEFINE_GUEST_HANDLE_STRUCT(name) \
+        __DEFINE_GUEST_HANDLE(name, struct name)
+#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
+#define GUEST_HANDLE(name)        __guest_handle_ ## name
+
+#ifndef __ASSEMBLY__
+/* Guest handles for primitive C types. */
+__DEFINE_GUEST_HANDLE(uchar, unsigned char);
+__DEFINE_GUEST_HANDLE(uint,  unsigned int);
+__DEFINE_GUEST_HANDLE(ulong, unsigned long);
+DEFINE_GUEST_HANDLE(char);
+DEFINE_GUEST_HANDLE(int);
+DEFINE_GUEST_HANDLE(long);
+DEFINE_GUEST_HANDLE(void);
+#endif
+
+/*
+ * SEGMENT DESCRIPTOR TABLES
+ */
+/*
+ * A number of GDT entries are reserved by Xen. These are not situated at the
+ * start of the GDT because some stupid OSes export hard-coded selector values
+ * in their ABI. These hard-coded values are always near the start of the GDT,
+ * so Xen places itself out of the way, at the far end of the GDT.
+ */
+#define FIRST_RESERVED_GDT_PAGE  14
+#define FIRST_RESERVED_GDT_BYTE  (FIRST_RESERVED_GDT_PAGE * 4096)
+#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
+
+/*
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+#define FLAT_RING1_CS 0xe019    /* GDT index 259 */
+#define FLAT_RING1_DS 0xe021    /* GDT index 260 */
+#define FLAT_RING1_SS 0xe021    /* GDT index 260 */
+#define FLAT_RING3_CS 0xe02b    /* GDT index 261 */
+#define FLAT_RING3_DS 0xe033    /* GDT index 262 */
+#define FLAT_RING3_SS 0xe033    /* GDT index 262 */
+
+#define FLAT_KERNEL_CS FLAT_RING1_CS
+#define FLAT_KERNEL_DS FLAT_RING1_DS
+#define FLAT_KERNEL_SS FLAT_RING1_SS
+#define FLAT_USER_CS    FLAT_RING3_CS
+#define FLAT_USER_DS    FLAT_RING3_DS
+#define FLAT_USER_SS    FLAT_RING3_SS
+
+/* And the trap vector is... */
+#define TRAP_INSTR "int $0x82"
+
+/*
+ * Virtual addresses beyond this are not modifiable by guest OSes. The
+ * machine->physical mapping table starts at this address, read-only.
+ */
+#ifdef CONFIG_X86_PAE
+#define __HYPERVISOR_VIRT_START 0xF5800000
+#else
+#define __HYPERVISOR_VIRT_START 0xFC000000
+#endif
+
+#ifndef HYPERVISOR_VIRT_START
+#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#endif
+
+#ifndef machine_to_phys_mapping
+#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
+#endif
+
+/* Maximum number of virtual CPUs in multi-processor guests. */
+#define MAX_VIRT_CPUS 32
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Send an array of these to HYPERVISOR_set_trap_table()
+ */
+#define TI_GET_DPL(_ti)         ((_ti)->flags & 3)
+#define TI_GET_IF(_ti)          ((_ti)->flags & 4)
+#define TI_SET_DPL(_ti, _dpl)   ((_ti)->flags |= (_dpl))
+#define TI_SET_IF(_ti, _if)     ((_ti)->flags |= ((!!(_if))<<2))
+
+struct trap_info {
+    uint8_t       vector;  /* exception vector                              */
+    uint8_t       flags;   /* 0-3: privilege level; 4: clear event enable?  */
+    uint16_t      cs;      /* code selector                                 */
+    unsigned long address; /* code offset                                   */
+};
+DEFINE_GUEST_HANDLE_STRUCT(trap_info);
+
+struct cpu_user_regs {
+    uint32_t ebx;
+    uint32_t ecx;
+    uint32_t edx;
+    uint32_t esi;
+    uint32_t edi;
+    uint32_t ebp;
+    uint32_t eax;
+    uint16_t error_code;    /* private */
+    uint16_t entry_vector;  /* private */
+    uint32_t eip;
+    uint16_t cs;
+    uint8_t  saved_upcall_mask;
+    uint8_t  _pad0;
+    uint32_t eflags;        /* eflags.IF == !saved_upcall_mask */
+    uint32_t esp;
+    uint16_t ss, _pad1;
+    uint16_t es, _pad2;
+    uint16_t ds, _pad3;
+    uint16_t fs, _pad4;
+    uint16_t gs, _pad5;
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
+
+/*
+ * The following is all CPU context. Note that the fpu_ctxt block is filled
+ * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
+ */
+struct vcpu_guest_context {
+    /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */
+    struct { char x[512]; } fpu_ctxt;       /* User-level FPU registers     */
+#define VGCF_I387_VALID (1<<0)
+#define VGCF_HVM_GUEST  (1<<1)
+#define VGCF_IN_KERNEL  (1<<2)
+    unsigned long flags;                    /* VGCF_* flags                 */
+    struct cpu_user_regs user_regs;         /* User-level CPU registers     */
+    struct trap_info trap_ctxt[256];        /* Virtual IDT                  */
+    unsigned long ldt_base, ldt_ents;       /* LDT (linear address, # ents) */
+    unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */
+    unsigned long kernel_ss, kernel_sp;     /* Virtual TSS (only SS1/SP1)   */
+    unsigned long ctrlreg[8];               /* CR0-CR7 (control registers)  */
+    unsigned long debugreg[8];              /* DB0-DB7 (debug registers)    */
+    unsigned long event_callback_cs;        /* CS:EIP of event callback     */
+    unsigned long event_callback_eip;
+    unsigned long failsafe_callback_cs;     /* CS:EIP of failsafe callback  */
+    unsigned long failsafe_callback_eip;
+    unsigned long vm_assist;                /* VMASST_TYPE_* bitmap */
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
+
+struct arch_shared_info {
+    unsigned long max_pfn;                  /* max pfn that appears in table */
+    /* Frame containing list of mfns containing list of mfns containing p2m. */
+    unsigned long pfn_to_mfn_frame_list_list;
+    unsigned long nmi_reason;
+};
+
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
+};
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * Prefix forces emulation of some non-trapping instructions.
+ * Currently only CPUID.
+ */
+#ifdef __ASSEMBLY__
+#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ;
+#define XEN_CPUID          XEN_EMULATE_PREFIX cpuid
+#else
+#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; "
+#define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
+#endif
+
+#endif
diff --git a/include/asm-x86/xor.h b/include/asm-x86/xor.h
new file mode 100644
index 000000000000..11b3bb86e17b
--- /dev/null
+++ b/include/asm-x86/xor.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "xor_32.h"
+#else
+# include "xor_64.h"
+#endif
diff --git a/include/asm-x86/xor_32.h b/include/asm-x86/xor_32.h
new file mode 100644
index 000000000000..23c86cef3b25
--- /dev/null
+++ b/include/asm-x86/xor_32.h
@@ -0,0 +1,883 @@
+/*
+ * include/asm-i386/xor.h
+ *
+ * Optimized RAID-5 checksumming functions for MMX and SSE.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * You should have received a copy of the GNU General Public License
+ * (for example /usr/src/linux/COPYING); if not, write to the Free
+ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * High-speed RAID5 checksumming functions utilizing MMX instructions.
+ * Copyright (C) 1998 Ingo Molnar.
+ */
+
+#define LD(x,y)         "       movq   8*("#x")(%1), %%mm"#y"   ;\n"
+#define ST(x,y)         "       movq %%mm"#y",   8*("#x")(%1)   ;\n"
+#define XO1(x,y)        "       pxor   8*("#x")(%2), %%mm"#y"   ;\n"
+#define XO2(x,y)        "       pxor   8*("#x")(%3), %%mm"#y"   ;\n"
+#define XO3(x,y)        "       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
+#define XO4(x,y)        "       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
+
+#include <asm/i387.h>
+
+static void
+xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+        unsigned long lines = bytes >> 7;
+
+        kernel_fpu_begin();
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+        LD(i,0)                                 \
+                LD(i+1,1)                       \
+                        LD(i+2,2)               \
+                                LD(i+3,3)       \
+        XO1(i,0)                                \
+        ST(i,0)                                 \
+                XO1(i+1,1)                      \
+                ST(i+1,1)                       \
+                        XO1(i+2,2)              \
+                        ST(i+2,2)               \
+                                XO1(i+3,3)      \
+                                ST(i+3,3)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+        BLOCK(0)
+        BLOCK(4)
+        BLOCK(8)
+        BLOCK(12)
+
+        "       addl $128, %1         ;\n"
+        "       addl $128, %2         ;\n"
+        "       decl %0               ;\n"
+        "       jnz 1b                ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2)
+        :
+        : "memory");
+
+        kernel_fpu_end();
+}
+
+static void
+xor_pII_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+              unsigned long *p3)
+{
+        unsigned long lines = bytes >> 7;
+
+        kernel_fpu_begin();
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+        LD(i,0)                                 \
+                LD(i+1,1)                       \
+                        LD(i+2,2)               \
+                                LD(i+3,3)       \
+        XO1(i,0)                                \
+                XO1(i+1,1)                      \
+                        XO1(i+2,2)              \
+                                XO1(i+3,3)      \
+        XO2(i,0)                                \
+        ST(i,0)                                 \
+                XO2(i+1,1)                      \
+                ST(i+1,1)                       \
+                        XO2(i+2,2)              \
+                        ST(i+2,2)               \
+                                XO2(i+3,3)      \
+                                ST(i+3,3)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+        BLOCK(0)
+        BLOCK(4)
+        BLOCK(8)
+        BLOCK(12)
+
+        "       addl $128, %1         ;\n"
+        "       addl $128, %2         ;\n"
+        "       addl $128, %3         ;\n"
+        "       decl %0               ;\n"
+        "       jnz 1b                ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2), "+r" (p3)
+        :
+        : "memory");
+
+        kernel_fpu_end();
+}
+
+static void
+xor_pII_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+              unsigned long *p3, unsigned long *p4)
+{
+        unsigned long lines = bytes >> 7;
+
+        kernel_fpu_begin();
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+        LD(i,0)                                 \
+                LD(i+1,1)                       \
+                        LD(i+2,2)               \
+                                LD(i+3,3)       \
+        XO1(i,0)                                \
+                XO1(i+1,1)                      \
+                        XO1(i+2,2)              \
+                                XO1(i+3,3)      \
+        XO2(i,0)                                \
+                XO2(i+1,1)                      \
+                        XO2(i+2,2)              \
+                                XO2(i+3,3)      \
+        XO3(i,0)                                \
+        ST(i,0)                                 \
+                XO3(i+1,1)                      \
+                ST(i+1,1)                       \
+                        XO3(i+2,2)              \
+                        ST(i+2,2)               \
+                                XO3(i+3,3)      \
+                                ST(i+3,3)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+        BLOCK(0)
+        BLOCK(4)
+        BLOCK(8)
+        BLOCK(12)
+
+        "       addl $128, %1         ;\n"
+        "       addl $128, %2         ;\n"
+        "       addl $128, %3         ;\n"
+        "       addl $128, %4         ;\n"
+        "       decl %0               ;\n"
+        "       jnz 1b                ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+        :
+        : "memory");
+
+        kernel_fpu_end();
+}
+
+
+static void
+xor_pII_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+              unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+        unsigned long lines = bytes >> 7;
+
+        kernel_fpu_begin();
+
+        /* Make sure GCC forgets anything it knows about p4 or p5,
+           such that it won't pass to the asm volatile below a
+           register that is shared with any other variable.  That's
+           because we modify p4 and p5 there, but we can't mark them
+           as read/write, otherwise we'd overflow the 10-asm-operands
+           limit of GCC < 3.1.  */
+        __asm__ ("" : "+r" (p4), "+r" (p5));
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+        LD(i,0)                                 \
+                LD(i+1,1)                       \
+                        LD(i+2,2)               \
+                                LD(i+3,3)       \
+        XO1(i,0)                                \
+                XO1(i+1,1)                      \
+                        XO1(i+2,2)              \
+                                XO1(i+3,3)      \
+        XO2(i,0)                                \
+                XO2(i+1,1)                      \
+                        XO2(i+2,2)              \
+                                XO2(i+3,3)      \
+        XO3(i,0)                                \
+                XO3(i+1,1)                      \
+                        XO3(i+2,2)              \
+                                XO3(i+3,3)      \
+        XO4(i,0)                                \
+        ST(i,0)                                 \
+                XO4(i+1,1)                      \
+                ST(i+1,1)                       \
+                        XO4(i+2,2)              \
+                        ST(i+2,2)               \
+                                XO4(i+3,3)      \
+                                ST(i+3,3)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+        BLOCK(0)
+        BLOCK(4)
+        BLOCK(8)
+        BLOCK(12)
+
+        "       addl $128, %1         ;\n"
+        "       addl $128, %2         ;\n"
+        "       addl $128, %3         ;\n"
+        "       addl $128, %4         ;\n"
+        "       addl $128, %5         ;\n"
+        "       decl %0               ;\n"
+        "       jnz 1b                ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2), "+r" (p3)
+        : "r" (p4), "r" (p5) 
+        : "memory");
+
+        /* p4 and p5 were modified, and now the variables are dead.
+           Clobber them just to be sure nobody does something stupid
+           like assuming they have some legal value.  */
+        __asm__ ("" : "=r" (p4), "=r" (p5));
+
+        kernel_fpu_end();
+}
+
+#undef LD
+#undef XO1
+#undef XO2
+#undef XO3
+#undef XO4
+#undef ST
+#undef BLOCK
+
+static void
+xor_p5_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+        unsigned long lines = bytes >> 6;
+
+        kernel_fpu_begin();
+
+        __asm__ __volatile__ (
+        " .align 32                  ;\n"
+        " 1:                         ;\n"
+        "       movq   (%1), %%mm0   ;\n"
+        "       movq  8(%1), %%mm1   ;\n"
+        "       pxor   (%2), %%mm0   ;\n"
+        "       movq 16(%1), %%mm2   ;\n"
+        "       movq %%mm0,   (%1)   ;\n"
+        "       pxor  8(%2), %%mm1   ;\n"
+        "       movq 24(%1), %%mm3   ;\n"
+        "       movq %%mm1,  8(%1)   ;\n"
+        "       pxor 16(%2), %%mm2   ;\n"
+        "       movq 32(%1), %%mm4   ;\n"
+        "       movq %%mm2, 16(%1)   ;\n"
+        "       pxor 24(%2), %%mm3   ;\n"
+        "       movq 40(%1), %%mm5   ;\n"
+        "       movq %%mm3, 24(%1)   ;\n"
+        "       pxor 32(%2), %%mm4   ;\n"
+        "       movq 48(%1), %%mm6   ;\n"
+        "       movq %%mm4, 32(%1)   ;\n"
+        "       pxor 40(%2), %%mm5   ;\n"
+        "       movq 56(%1), %%mm7   ;\n"
+        "       movq %%mm5, 40(%1)   ;\n"
+        "       pxor 48(%2), %%mm6   ;\n"
+        "       pxor 56(%2), %%mm7   ;\n"
+        "       movq %%mm6, 48(%1)   ;\n"
+        "       movq %%mm7, 56(%1)   ;\n"
+        
+        "       addl $64, %1         ;\n"
+        "       addl $64, %2         ;\n"
+        "       decl %0              ;\n"
+        "       jnz 1b               ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2)
+        :
+        : "memory");
+
+        kernel_fpu_end();
+}
+
+static void
+xor_p5_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+             unsigned long *p3)
+{
+        unsigned long lines = bytes >> 6;
+
+        kernel_fpu_begin();
+
+        __asm__ __volatile__ (
+        " .align 32,0x90             ;\n"
+        " 1:                         ;\n"
+        "       movq   (%1), %%mm0   ;\n"
+        "       movq  8(%1), %%mm1   ;\n"
+        "       pxor   (%2), %%mm0   ;\n"
+        "       movq 16(%1), %%mm2   ;\n"
+        "       pxor  8(%2), %%mm1   ;\n"
+        "       pxor   (%3), %%mm0   ;\n"
+        "       pxor 16(%2), %%mm2   ;\n"
+        "       movq %%mm0,   (%1)   ;\n"
+        "       pxor  8(%3), %%mm1   ;\n"
+        "       pxor 16(%3), %%mm2   ;\n"
+        "       movq 24(%1), %%mm3   ;\n"
+        "       movq %%mm1,  8(%1)   ;\n"
+        "       movq 32(%1), %%mm4   ;\n"
+        "       movq 40(%1), %%mm5   ;\n"
+        "       pxor 24(%2), %%mm3   ;\n"
+        "       movq %%mm2, 16(%1)   ;\n"
+        "       pxor 32(%2), %%mm4   ;\n"
+        "       pxor 24(%3), %%mm3   ;\n"
+        "       pxor 40(%2), %%mm5   ;\n"
+        "       movq %%mm3, 24(%1)   ;\n"
+        "       pxor 32(%3), %%mm4   ;\n"
+        "       pxor 40(%3), %%mm5   ;\n"
+        "       movq 48(%1), %%mm6   ;\n"
+        "       movq %%mm4, 32(%1)   ;\n"
+        "       movq 56(%1), %%mm7   ;\n"
+        "       pxor 48(%2), %%mm6   ;\n"
+        "       movq %%mm5, 40(%1)   ;\n"
+        "       pxor 56(%2), %%mm7   ;\n"
+        "       pxor 48(%3), %%mm6   ;\n"
+        "       pxor 56(%3), %%mm7   ;\n"
+        "       movq %%mm6, 48(%1)   ;\n"
+        "       movq %%mm7, 56(%1)   ;\n"
+      
+        "       addl $64, %1         ;\n"
+        "       addl $64, %2         ;\n"
+        "       addl $64, %3         ;\n"
+        "       decl %0              ;\n"
+        "       jnz 1b               ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2), "+r" (p3)
+        :
+        : "memory" );
+
+        kernel_fpu_end();
+}
+
+static void
+xor_p5_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+             unsigned long *p3, unsigned long *p4)
+{
+        unsigned long lines = bytes >> 6;
+
+        kernel_fpu_begin();
+
+        __asm__ __volatile__ (
+        " .align 32,0x90             ;\n"
+        " 1:                         ;\n"
+        "       movq   (%1), %%mm0   ;\n"
+        "       movq  8(%1), %%mm1   ;\n"
+        "       pxor   (%2), %%mm0   ;\n"
+        "       movq 16(%1), %%mm2   ;\n"
+        "       pxor  8(%2), %%mm1   ;\n"
+        "       pxor   (%3), %%mm0   ;\n"
+        "       pxor 16(%2), %%mm2   ;\n"
+        "       pxor  8(%3), %%mm1   ;\n"
+        "       pxor   (%4), %%mm0   ;\n"
+        "       movq 24(%1), %%mm3   ;\n"
+        "       pxor 16(%3), %%mm2   ;\n"
+        "       pxor  8(%4), %%mm1   ;\n"
+        "       movq %%mm0,   (%1)   ;\n"
+        "       movq 32(%1), %%mm4   ;\n"
+        "       pxor 24(%2), %%mm3   ;\n"
+        "       pxor 16(%4), %%mm2   ;\n"
+        "       movq %%mm1,  8(%1)   ;\n"
+        "       movq 40(%1), %%mm5   ;\n"
+        "       pxor 32(%2), %%mm4   ;\n"
+        "       pxor 24(%3), %%mm3   ;\n"
+        "       movq %%mm2, 16(%1)   ;\n"
+        "       pxor 40(%2), %%mm5   ;\n"
+        "       pxor 32(%3), %%mm4   ;\n"
+        "       pxor 24(%4), %%mm3   ;\n"
+        "       movq %%mm3, 24(%1)   ;\n"
+        "       movq 56(%1), %%mm7   ;\n"
+        "       movq 48(%1), %%mm6   ;\n"
+        "       pxor 40(%3), %%mm5   ;\n"
+        "       pxor 32(%4), %%mm4   ;\n"
+        "       pxor 48(%2), %%mm6   ;\n"
+        "       movq %%mm4, 32(%1)   ;\n"
+        "       pxor 56(%2), %%mm7   ;\n"
+        "       pxor 40(%4), %%mm5   ;\n"
+        "       pxor 48(%3), %%mm6   ;\n"
+        "       pxor 56(%3), %%mm7   ;\n"
+        "       movq %%mm5, 40(%1)   ;\n"
+        "       pxor 48(%4), %%mm6   ;\n"
+        "       pxor 56(%4), %%mm7   ;\n"
+        "       movq %%mm6, 48(%1)   ;\n"
+        "       movq %%mm7, 56(%1)   ;\n"
+      
+        "       addl $64, %1         ;\n"
+        "       addl $64, %2         ;\n"
+        "       addl $64, %3         ;\n"
+        "       addl $64, %4         ;\n"
+        "       decl %0              ;\n"
+        "       jnz 1b               ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+        :
+        : "memory");
+
+        kernel_fpu_end();
+}
+
+static void
+xor_p5_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+             unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+        unsigned long lines = bytes >> 6;
+
+        kernel_fpu_begin();
+
+        /* Make sure GCC forgets anything it knows about p4 or p5,
+           such that it won't pass to the asm volatile below a
+           register that is shared with any other variable.  That's
+           because we modify p4 and p5 there, but we can't mark them
+           as read/write, otherwise we'd overflow the 10-asm-operands
+           limit of GCC < 3.1.  */
+        __asm__ ("" : "+r" (p4), "+r" (p5));
+
+        __asm__ __volatile__ (
+        " .align 32,0x90             ;\n"
+        " 1:                         ;\n"
+        "       movq   (%1), %%mm0   ;\n"
+        "       movq  8(%1), %%mm1   ;\n"
+        "       pxor   (%2), %%mm0   ;\n"
+        "       pxor  8(%2), %%mm1   ;\n"
+        "       movq 16(%1), %%mm2   ;\n"
+        "       pxor   (%3), %%mm0   ;\n"
+        "       pxor  8(%3), %%mm1   ;\n"
+        "       pxor 16(%2), %%mm2   ;\n"
+        "       pxor   (%4), %%mm0   ;\n"
+        "       pxor  8(%4), %%mm1   ;\n"
+        "       pxor 16(%3), %%mm2   ;\n"
+        "       movq 24(%1), %%mm3   ;\n"
+        "       pxor   (%5), %%mm0   ;\n"
+        "       pxor  8(%5), %%mm1   ;\n"
+        "       movq %%mm0,   (%1)   ;\n"
+        "       pxor 16(%4), %%mm2   ;\n"
+        "       pxor 24(%2), %%mm3   ;\n"
+        "       movq %%mm1,  8(%1)   ;\n"
+        "       pxor 16(%5), %%mm2   ;\n"
+        "       pxor 24(%3), %%mm3   ;\n"
+        "       movq 32(%1), %%mm4   ;\n"
+        "       movq %%mm2, 16(%1)   ;\n"
+        "       pxor 24(%4), %%mm3   ;\n"
+        "       pxor 32(%2), %%mm4   ;\n"
+        "       movq 40(%1), %%mm5   ;\n"
+        "       pxor 24(%5), %%mm3   ;\n"
+        "       pxor 32(%3), %%mm4   ;\n"
+        "       pxor 40(%2), %%mm5   ;\n"
+        "       movq %%mm3, 24(%1)   ;\n"
+        "       pxor 32(%4), %%mm4   ;\n"
+        "       pxor 40(%3), %%mm5   ;\n"
+        "       movq 48(%1), %%mm6   ;\n"
+        "       movq 56(%1), %%mm7   ;\n"
+        "       pxor 32(%5), %%mm4   ;\n"
+        "       pxor 40(%4), %%mm5   ;\n"
+        "       pxor 48(%2), %%mm6   ;\n"
+        "       pxor 56(%2), %%mm7   ;\n"
+        "       movq %%mm4, 32(%1)   ;\n"
+        "       pxor 48(%3), %%mm6   ;\n"
+        "       pxor 56(%3), %%mm7   ;\n"
+        "       pxor 40(%5), %%mm5   ;\n"
+        "       pxor 48(%4), %%mm6   ;\n"
+        "       pxor 56(%4), %%mm7   ;\n"
+        "       movq %%mm5, 40(%1)   ;\n"
+        "       pxor 48(%5), %%mm6   ;\n"
+        "       pxor 56(%5), %%mm7   ;\n"
+        "       movq %%mm6, 48(%1)   ;\n"
+        "       movq %%mm7, 56(%1)   ;\n"
+      
+        "       addl $64, %1         ;\n"
+        "       addl $64, %2         ;\n"
+        "       addl $64, %3         ;\n"
+        "       addl $64, %4         ;\n"
+        "       addl $64, %5         ;\n"
+        "       decl %0              ;\n"
+        "       jnz 1b               ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2), "+r" (p3)
+        : "r" (p4), "r" (p5)
+        : "memory");
+
+        /* p4 and p5 were modified, and now the variables are dead.
+           Clobber them just to be sure nobody does something stupid
+           like assuming they have some legal value.  */
+        __asm__ ("" : "=r" (p4), "=r" (p5));
+
+        kernel_fpu_end();
+}
+
+static struct xor_block_template xor_block_pII_mmx = {
+        .name = "pII_mmx",
+        .do_2 = xor_pII_mmx_2,
+        .do_3 = xor_pII_mmx_3,
+        .do_4 = xor_pII_mmx_4,
+        .do_5 = xor_pII_mmx_5,
+};
+
+static struct xor_block_template xor_block_p5_mmx = {
+        .name = "p5_mmx",
+        .do_2 = xor_p5_mmx_2,
+        .do_3 = xor_p5_mmx_3,
+        .do_4 = xor_p5_mmx_4,
+        .do_5 = xor_p5_mmx_5,
+};
+
+/*
+ * Cache avoiding checksumming functions utilizing KNI instructions
+ * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
+ */
+
+#define XMMS_SAVE do {                          \
+        preempt_disable();                      \
+        cr0 = read_cr0();                       \
+        clts();                                 \
+        __asm__ __volatile__ (                  \
+                "movups %%xmm0,(%0)     ;\n\t"  \
+                "movups %%xmm1,0x10(%0) ;\n\t"  \
+                "movups %%xmm2,0x20(%0) ;\n\t"  \
+                "movups %%xmm3,0x30(%0) ;\n\t"  \
+                :                               \
+                : "r" (xmm_save)                \
+                : "memory");                    \
+} while(0)
+
+#define XMMS_RESTORE do {                       \
+        __asm__ __volatile__ (                  \
+                "sfence                 ;\n\t"  \
+                "movups (%0),%%xmm0     ;\n\t"  \
+                "movups 0x10(%0),%%xmm1 ;\n\t"  \
+                "movups 0x20(%0),%%xmm2 ;\n\t"  \
+                "movups 0x30(%0),%%xmm3 ;\n\t"  \
+                :                               \
+                : "r" (xmm_save)                \
+                : "memory");                    \
+        write_cr0(cr0);                         \
+        preempt_enable();                       \
+} while(0)
+
+#define ALIGN16 __attribute__((aligned(16)))
+
+#define OFFS(x)         "16*("#x")"
+#define PF_OFFS(x)      "256+16*("#x")"
+#define PF0(x)          "       prefetchnta "PF_OFFS(x)"(%1)            ;\n"
+#define LD(x,y)         "       movaps   "OFFS(x)"(%1), %%xmm"#y"       ;\n"
+#define ST(x,y)         "       movaps %%xmm"#y",   "OFFS(x)"(%1)       ;\n"
+#define PF1(x)          "       prefetchnta "PF_OFFS(x)"(%2)            ;\n"
+#define PF2(x)          "       prefetchnta "PF_OFFS(x)"(%3)            ;\n"
+#define PF3(x)          "       prefetchnta "PF_OFFS(x)"(%4)            ;\n"
+#define PF4(x)          "       prefetchnta "PF_OFFS(x)"(%5)            ;\n"
+#define PF5(x)          "       prefetchnta "PF_OFFS(x)"(%6)            ;\n"
+#define XO1(x,y)        "       xorps   "OFFS(x)"(%2), %%xmm"#y"        ;\n"
+#define XO2(x,y)        "       xorps   "OFFS(x)"(%3), %%xmm"#y"        ;\n"
+#define XO3(x,y)        "       xorps   "OFFS(x)"(%4), %%xmm"#y"        ;\n"
+#define XO4(x,y)        "       xorps   "OFFS(x)"(%5), %%xmm"#y"        ;\n"
+#define XO5(x,y)        "       xorps   "OFFS(x)"(%6), %%xmm"#y"        ;\n"
+
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+        unsigned long lines = bytes >> 8;
+        char xmm_save[16*4] ALIGN16;
+        int cr0;
+
+        XMMS_SAVE;
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+                LD(i,0)                                 \
+                        LD(i+1,1)                       \
+                PF1(i)                                  \
+                                PF1(i+2)                \
+                                LD(i+2,2)               \
+                                        LD(i+3,3)       \
+                PF0(i+4)                                \
+                                PF0(i+6)                \
+                XO1(i,0)                                \
+                        XO1(i+1,1)                      \
+                                XO1(i+2,2)              \
+                                        XO1(i+3,3)      \
+                ST(i,0)                                 \
+                        ST(i+1,1)                       \
+                                ST(i+2,2)               \
+                                        ST(i+3,3)       \
+
+
+                PF0(0)
+                                PF0(2)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+                BLOCK(0)
+                BLOCK(4)
+                BLOCK(8)
+                BLOCK(12)
+
+        "       addl $256, %1           ;\n"
+        "       addl $256, %2           ;\n"
+        "       decl %0                 ;\n"
+        "       jnz 1b                  ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2)
+        :
+        : "memory");
+
+        XMMS_RESTORE;
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+          unsigned long *p3)
+{
+        unsigned long lines = bytes >> 8;
+        char xmm_save[16*4] ALIGN16;
+        int cr0;
+
+        XMMS_SAVE;
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+                PF1(i)                                  \
+                                PF1(i+2)                \
+                LD(i,0)                                 \
+                        LD(i+1,1)                       \
+                                LD(i+2,2)               \
+                                        LD(i+3,3)       \
+                PF2(i)                                  \
+                                PF2(i+2)                \
+                PF0(i+4)                                \
+                                PF0(i+6)                \
+                XO1(i,0)                                \
+                        XO1(i+1,1)                      \
+                                XO1(i+2,2)              \
+                                        XO1(i+3,3)      \
+                XO2(i,0)                                \
+                        XO2(i+1,1)                      \
+                                XO2(i+2,2)              \
+                                        XO2(i+3,3)      \
+                ST(i,0)                                 \
+                        ST(i+1,1)                       \
+                                ST(i+2,2)               \
+                                        ST(i+3,3)       \
+
+
+                PF0(0)
+                                PF0(2)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+                BLOCK(0)
+                BLOCK(4)
+                BLOCK(8)
+                BLOCK(12)
+
+        "       addl $256, %1           ;\n"
+        "       addl $256, %2           ;\n"
+        "       addl $256, %3           ;\n"
+        "       decl %0                 ;\n"
+        "       jnz 1b                  ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r"(p2), "+r"(p3)
+        :
+        : "memory" );
+
+        XMMS_RESTORE;
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+          unsigned long *p3, unsigned long *p4)
+{
+        unsigned long lines = bytes >> 8;
+        char xmm_save[16*4] ALIGN16;
+        int cr0;
+
+        XMMS_SAVE;
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+                PF1(i)                                  \
+                                PF1(i+2)                \
+                LD(i,0)                                 \
+                        LD(i+1,1)                       \
+                                LD(i+2,2)               \
+                                        LD(i+3,3)       \
+                PF2(i)                                  \
+                                PF2(i+2)                \
+                XO1(i,0)                                \
+                        XO1(i+1,1)                      \
+                                XO1(i+2,2)              \
+                                        XO1(i+3,3)      \
+                PF3(i)                                  \
+                                PF3(i+2)                \
+                PF0(i+4)                                \
+                                PF0(i+6)                \
+                XO2(i,0)                                \
+                        XO2(i+1,1)                      \
+                                XO2(i+2,2)              \
+                                        XO2(i+3,3)      \
+                XO3(i,0)                                \
+                        XO3(i+1,1)                      \
+                                XO3(i+2,2)              \
+                                        XO3(i+3,3)      \
+                ST(i,0)                                 \
+                        ST(i+1,1)                       \
+                                ST(i+2,2)               \
+                                        ST(i+3,3)       \
+
+
+                PF0(0)
+                                PF0(2)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+                BLOCK(0)
+                BLOCK(4)
+                BLOCK(8)
+                BLOCK(12)
+
+        "       addl $256, %1           ;\n"
+        "       addl $256, %2           ;\n"
+        "       addl $256, %3           ;\n"
+        "       addl $256, %4           ;\n"
+        "       decl %0                 ;\n"
+        "       jnz 1b                  ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+        :
+        : "memory" );
+
+        XMMS_RESTORE;
+}
+
+static void
+xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+          unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+        unsigned long lines = bytes >> 8;
+        char xmm_save[16*4] ALIGN16;
+        int cr0;
+
+        XMMS_SAVE;
+
+        /* Make sure GCC forgets anything it knows about p4 or p5,
+           such that it won't pass to the asm volatile below a
+           register that is shared with any other variable.  That's
+           because we modify p4 and p5 there, but we can't mark them
+           as read/write, otherwise we'd overflow the 10-asm-operands
+           limit of GCC < 3.1.  */
+        __asm__ ("" : "+r" (p4), "+r" (p5));
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+                PF1(i)                                  \
+                                PF1(i+2)                \
+                LD(i,0)                                 \
+                        LD(i+1,1)                       \
+                                LD(i+2,2)               \
+                                        LD(i+3,3)       \
+                PF2(i)                                  \
+                                PF2(i+2)                \
+                XO1(i,0)                                \
+                        XO1(i+1,1)                      \
+                                XO1(i+2,2)              \
+                                        XO1(i+3,3)      \
+                PF3(i)                                  \
+                                PF3(i+2)                \
+                XO2(i,0)                                \
+                        XO2(i+1,1)                      \
+                                XO2(i+2,2)              \
+                                        XO2(i+3,3)      \
+                PF4(i)                                  \
+                                PF4(i+2)                \
+                PF0(i+4)                                \
+                                PF0(i+6)                \
+                XO3(i,0)                                \
+                        XO3(i+1,1)                      \
+                                XO3(i+2,2)              \
+                                        XO3(i+3,3)      \
+                XO4(i,0)                                \
+                        XO4(i+1,1)                      \
+                                XO4(i+2,2)              \
+                                        XO4(i+3,3)      \
+                ST(i,0)                                 \
+                        ST(i+1,1)                       \
+                                ST(i+2,2)               \
+                                        ST(i+3,3)       \
+
+
+                PF0(0)
+                                PF0(2)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+                BLOCK(0)
+                BLOCK(4)
+                BLOCK(8)
+                BLOCK(12)
+
+        "       addl $256, %1           ;\n"
+        "       addl $256, %2           ;\n"
+        "       addl $256, %3           ;\n"
+        "       addl $256, %4           ;\n"
+        "       addl $256, %5           ;\n"
+        "       decl %0                 ;\n"
+        "       jnz 1b                  ;\n"
+        : "+r" (lines),
+          "+r" (p1), "+r" (p2), "+r" (p3)
+        : "r" (p4), "r" (p5)
+        : "memory");
+
+        /* p4 and p5 were modified, and now the variables are dead.
+           Clobber them just to be sure nobody does something stupid
+           like assuming they have some legal value.  */
+        __asm__ ("" : "=r" (p4), "=r" (p5));
+
+        XMMS_RESTORE;
+}
+
+static struct xor_block_template xor_block_pIII_sse = {
+        .name = "pIII_sse",
+        .do_2 =  xor_sse_2,
+        .do_3 =  xor_sse_3,
+        .do_4 =  xor_sse_4,
+        .do_5 = xor_sse_5,
+};
+
+/* Also try the generic routines.  */
+#include <asm-generic/xor.h>
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES                               \
+        do {                                            \
+                xor_speed(&xor_block_8regs);            \
+                xor_speed(&xor_block_8regs_p);          \
+                xor_speed(&xor_block_32regs);           \
+                xor_speed(&xor_block_32regs_p);         \
+                if (cpu_has_xmm)                        \
+                        xor_speed(&xor_block_pIII_sse); \
+                if (cpu_has_mmx) {                      \
+                        xor_speed(&xor_block_pII_mmx);  \
+                        xor_speed(&xor_block_p5_mmx);   \
+                }                                       \
+        } while (0)
+
+/* We force the use of the SSE xor block because it can write around L2.
+   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) \
+        (cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
diff --git a/include/asm-x86/xor_64.h b/include/asm-x86/xor_64.h
new file mode 100644
index 000000000000..f942fcc21831
--- /dev/null
+++ b/include/asm-x86/xor_64.h
@@ -0,0 +1,354 @@
+/*
+ * include/asm-x86_64/xor.h
+ *
+ * Optimized RAID-5 checksumming functions for MMX and SSE.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * You should have received a copy of the GNU General Public License
+ * (for example /usr/src/linux/COPYING); if not, write to the Free
+ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+
+/*
+ * Cache avoiding checksumming functions utilizing KNI instructions
+ * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
+ */
+
+/*
+ * Based on
+ * High-speed RAID5 checksumming functions utilizing SSE instructions.
+ * Copyright (C) 1998 Ingo Molnar.
+ */
+
+/*
+ * x86-64 changes / gcc fixes from Andi Kleen. 
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ *
+ * This hasn't been optimized for the hammer yet, but there are likely
+ * no advantages to be gotten from x86-64 here anyways.
+ */
+
+typedef struct { unsigned long a,b; } __attribute__((aligned(16))) xmm_store_t;
+
+/* Doesn't use gcc to save the XMM registers, because there is no easy way to 
+   tell it to do a clts before the register saving. */
+#define XMMS_SAVE do {                          \
+        preempt_disable();                      \
+        asm volatile (                          \
+                "movq %%cr0,%0          ;\n\t"  \
+                "clts                   ;\n\t"  \
+                "movups %%xmm0,(%1)     ;\n\t"  \
+                "movups %%xmm1,0x10(%1) ;\n\t"  \
+                "movups %%xmm2,0x20(%1) ;\n\t"  \
+                "movups %%xmm3,0x30(%1) ;\n\t"  \
+                : "=&r" (cr0)                   \
+                : "r" (xmm_save)                \
+                : "memory");                    \
+} while(0)
+
+#define XMMS_RESTORE do {                       \
+        asm volatile (                          \
+                "sfence                 ;\n\t"  \
+                "movups (%1),%%xmm0     ;\n\t"  \
+                "movups 0x10(%1),%%xmm1 ;\n\t"  \
+                "movups 0x20(%1),%%xmm2 ;\n\t"  \
+                "movups 0x30(%1),%%xmm3 ;\n\t"  \
+                "movq   %0,%%cr0        ;\n\t"  \
+                :                               \
+                : "r" (cr0), "r" (xmm_save)     \
+                : "memory");                    \
+        preempt_enable();                       \
+} while(0)
+
+#define OFFS(x)         "16*("#x")"
+#define PF_OFFS(x)      "256+16*("#x")"
+#define PF0(x)          "       prefetchnta "PF_OFFS(x)"(%[p1])         ;\n"
+#define LD(x,y)         "       movaps   "OFFS(x)"(%[p1]), %%xmm"#y"    ;\n"
+#define ST(x,y)         "       movaps %%xmm"#y",   "OFFS(x)"(%[p1])    ;\n"
+#define PF1(x)          "       prefetchnta "PF_OFFS(x)"(%[p2])         ;\n"
+#define PF2(x)          "       prefetchnta "PF_OFFS(x)"(%[p3])         ;\n"
+#define PF3(x)          "       prefetchnta "PF_OFFS(x)"(%[p4])         ;\n"
+#define PF4(x)          "       prefetchnta "PF_OFFS(x)"(%[p5])         ;\n"
+#define PF5(x)          "       prefetchnta "PF_OFFS(x)"(%[p6])         ;\n"
+#define XO1(x,y)        "       xorps   "OFFS(x)"(%[p2]), %%xmm"#y"     ;\n"
+#define XO2(x,y)        "       xorps   "OFFS(x)"(%[p3]), %%xmm"#y"     ;\n"
+#define XO3(x,y)        "       xorps   "OFFS(x)"(%[p4]), %%xmm"#y"     ;\n"
+#define XO4(x,y)        "       xorps   "OFFS(x)"(%[p5]), %%xmm"#y"     ;\n"
+#define XO5(x,y)        "       xorps   "OFFS(x)"(%[p6]), %%xmm"#y"     ;\n"
+
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+        unsigned int lines = bytes >> 8;
+        unsigned long cr0;
+        xmm_store_t xmm_save[4];
+
+        XMMS_SAVE;
+
+        asm volatile (
+#undef BLOCK
+#define BLOCK(i) \
+                LD(i,0)                                 \
+                        LD(i+1,1)                       \
+                PF1(i)                                  \
+                                PF1(i+2)                \
+                                LD(i+2,2)               \
+                                        LD(i+3,3)       \
+                PF0(i+4)                                \
+                                PF0(i+6)                \
+                XO1(i,0)                                \
+                        XO1(i+1,1)                      \
+                                XO1(i+2,2)              \
+                                        XO1(i+3,3)      \
+                ST(i,0)                                 \
+                        ST(i+1,1)                       \
+                                ST(i+2,2)               \
+                                        ST(i+3,3)       \
+
+
+                PF0(0)
+                                PF0(2)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+                BLOCK(0)
+                BLOCK(4)
+                BLOCK(8)
+                BLOCK(12)
+
+        "       addq %[inc], %[p1]           ;\n"
+        "       addq %[inc], %[p2]           ;\n"
+                "               decl %[cnt] ; jnz 1b"
+        : [p1] "+r" (p1), [p2] "+r" (p2), [cnt] "+r" (lines)
+        : [inc] "r" (256UL) 
+        : "memory");
+
+        XMMS_RESTORE;
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+          unsigned long *p3)
+{
+        unsigned int lines = bytes >> 8;
+        xmm_store_t xmm_save[4];
+        unsigned long cr0;
+
+        XMMS_SAVE;
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+                PF1(i)                                  \
+                                PF1(i+2)                \
+                LD(i,0)                                 \
+                        LD(i+1,1)                       \
+                                LD(i+2,2)               \
+                                        LD(i+3,3)       \
+                PF2(i)                                  \
+                                PF2(i+2)                \
+                PF0(i+4)                                \
+                                PF0(i+6)                \
+                XO1(i,0)                                \
+                        XO1(i+1,1)                      \
+                                XO1(i+2,2)              \
+                                        XO1(i+3,3)      \
+                XO2(i,0)                                \
+                        XO2(i+1,1)                      \
+                                XO2(i+2,2)              \
+                                        XO2(i+3,3)      \
+                ST(i,0)                                 \
+                        ST(i+1,1)                       \
+                                ST(i+2,2)               \
+                                        ST(i+3,3)       \
+
+
+                PF0(0)
+                                PF0(2)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+                BLOCK(0)
+                BLOCK(4)
+                BLOCK(8)
+                BLOCK(12)
+
+        "       addq %[inc], %[p1]           ;\n"
+        "       addq %[inc], %[p2]          ;\n"
+        "       addq %[inc], %[p3]           ;\n"
+                "               decl %[cnt] ; jnz 1b"
+        : [cnt] "+r" (lines),
+          [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
+        : [inc] "r" (256UL)
+        : "memory"); 
+        XMMS_RESTORE;
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+          unsigned long *p3, unsigned long *p4)
+{
+        unsigned int lines = bytes >> 8;
+        xmm_store_t xmm_save[4]; 
+        unsigned long cr0;
+
+        XMMS_SAVE;
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+                PF1(i)                                  \
+                                PF1(i+2)                \
+                LD(i,0)                                 \
+                        LD(i+1,1)                       \
+                                LD(i+2,2)               \
+                                        LD(i+3,3)       \
+                PF2(i)                                  \
+                                PF2(i+2)                \
+                XO1(i,0)                                \
+                        XO1(i+1,1)                      \
+                                XO1(i+2,2)              \
+                                        XO1(i+3,3)      \
+                PF3(i)                                  \
+                                PF3(i+2)                \
+                PF0(i+4)                                \
+                                PF0(i+6)                \
+                XO2(i,0)                                \
+                        XO2(i+1,1)                      \
+                                XO2(i+2,2)              \
+                                        XO2(i+3,3)      \
+                XO3(i,0)                                \
+                        XO3(i+1,1)                      \
+                                XO3(i+2,2)              \
+                                        XO3(i+3,3)      \
+                ST(i,0)                                 \
+                        ST(i+1,1)                       \
+                                ST(i+2,2)               \
+                                        ST(i+3,3)       \
+
+
+                PF0(0)
+                                PF0(2)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+                BLOCK(0)
+                BLOCK(4)
+                BLOCK(8)
+                BLOCK(12)
+
+        "       addq %[inc], %[p1]           ;\n"
+        "       addq %[inc], %[p2]           ;\n"
+        "       addq %[inc], %[p3]           ;\n"
+        "       addq %[inc], %[p4]           ;\n"
+        "       decl %[cnt] ; jnz 1b"
+        : [cnt] "+c" (lines),
+          [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
+        : [inc] "r" (256UL)
+        : "memory" );
+
+        XMMS_RESTORE;
+}
+
+static void
+xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+          unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+        unsigned int lines = bytes >> 8;
+        xmm_store_t xmm_save[4];
+        unsigned long cr0;
+
+        XMMS_SAVE;
+
+        __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+                PF1(i)                                  \
+                                PF1(i+2)                \
+                LD(i,0)                                 \
+                        LD(i+1,1)                       \
+                                LD(i+2,2)               \
+                                        LD(i+3,3)       \
+                PF2(i)                                  \
+                                PF2(i+2)                \
+                XO1(i,0)                                \
+                        XO1(i+1,1)                      \
+                                XO1(i+2,2)              \
+                                        XO1(i+3,3)      \
+                PF3(i)                                  \
+                                PF3(i+2)                \
+                XO2(i,0)                                \
+                        XO2(i+1,1)                      \
+                                XO2(i+2,2)              \
+                                        XO2(i+3,3)      \
+                PF4(i)                                  \
+                                PF4(i+2)                \
+                PF0(i+4)                                \
+                                PF0(i+6)                \
+                XO3(i,0)                                \
+                        XO3(i+1,1)                      \
+                                XO3(i+2,2)              \
+                                        XO3(i+3,3)      \
+                XO4(i,0)                                \
+                        XO4(i+1,1)                      \
+                                XO4(i+2,2)              \
+                                        XO4(i+3,3)      \
+                ST(i,0)                                 \
+                        ST(i+1,1)                       \
+                                ST(i+2,2)               \
+                                        ST(i+3,3)       \
+
+
+                PF0(0)
+                                PF0(2)
+
+        " .align 32                     ;\n"
+        " 1:                            ;\n"
+
+                BLOCK(0)
+                BLOCK(4)
+                BLOCK(8)
+                BLOCK(12)
+
+        "       addq %[inc], %[p1]           ;\n"
+        "       addq %[inc], %[p2]           ;\n"
+        "       addq %[inc], %[p3]           ;\n"
+        "       addq %[inc], %[p4]           ;\n"
+        "       addq %[inc], %[p5]           ;\n"
+        "       decl %[cnt] ; jnz 1b"
+        : [cnt] "+c" (lines),
+          [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4), 
+          [p5] "+r" (p5)
+        : [inc] "r" (256UL)
+        : "memory");
+
+        XMMS_RESTORE;
+}
+
+static struct xor_block_template xor_block_sse = {
+        .name = "generic_sse",
+        .do_2 = xor_sse_2,
+        .do_3 = xor_sse_3,
+        .do_4 = xor_sse_4,
+        .do_5 = xor_sse_5,
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES                               \
+        do {                                            \
+                xor_speed(&xor_block_sse);      \
+        } while (0)
+
+/* We force the use of the SSE xor block because it can write around L2.
+   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)