Linux-2.6.12-rc2v2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

140 files changed, 13947 insertions, 0 deletions

diff --git a/include/asm-x86_64/8253pit.h b/include/asm-x86_64/8253pit.h
new file mode 100644
index 000000000000..285f78488ccb
--- /dev/null
+++ b/include/asm-x86_64/8253pit.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_64/a.out.h b/include/asm-x86_64/a.out.h
new file mode 100644
index 000000000000..5952914f4121
--- /dev/null
+++ b/include/asm-x86_64/a.out.h
@@ -0,0 +1,27 @@
+#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 (test_thread_flag(TIF_IA32) ? IA32_PAGE_OFFSET : TASK_SIZE)
+#endif
+
+#endif /* __A_OUT_GNU_H__ */
diff --git a/include/asm-x86_64/acpi.h b/include/asm-x86_64/acpi.h
new file mode 100644
index 000000000000..a6b41b892062
--- /dev/null
+++ b/include/asm-x86_64/acpi.h
@@ -0,0 +1,176 @@
+/*
+ *  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__
+
+#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()
+
+
+static inline int
+__acpi_acquire_global_lock (unsigned int *lock)
+{
+	unsigned int old, new, val;
+	do {
+		old = *lock;
+		new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1));
+		val = cmpxchg(lock, old, new);
+	} while (unlikely (val != old));
+	return (new < 3) ? -1 : 0;
+}
+
+static inline int
+__acpi_release_global_lock (unsigned int *lock)
+{
+	unsigned int old, new, val;
+	do {
+		old = *lock;
+		new = old & ~0x3;
+		val = cmpxchg(lock, old, new);
+	} while (unlikely (val != old));
+	return old & 0x1;
+}
+
+#define ACPI_ACQUIRE_GLOBAL_LOCK(GLptr, Acq) \
+	((Acq) = __acpi_acquire_global_lock((unsigned int *) GLptr))
+
+#define ACPI_RELEASE_GLOBAL_LOCK(GLptr, Acq) \
+	((Acq) = __acpi_release_global_lock((unsigned int *) GLptr))
+
+/*
+ * 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))
+
+/*
+ * Refer Intel ACPI _PDC support document for bit definitions
+ */
+#define ACPI_PDC_EST_CAPABILITY_SMP 	0xa
+#define ACPI_PDC_EST_CAPABILITY_MSR	0x1
+
+#ifdef CONFIG_ACPI_BOOT
+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);
+
+#else	/* !CONFIG_ACPI_BOOT */
+#define acpi_lapic 0
+#define acpi_ioapic 0
+#endif /* !CONFIG_ACPI_BOOT */
+
+extern int acpi_numa;
+extern int acpi_scan_nodes(unsigned long start, unsigned long end);
+#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
+
+#ifdef CONFIG_ACPI_PCI
+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);
+#else
+static inline void acpi_noirq_set(void) { }
+static inline void acpi_disable_pci(void) { }
+static inline int acpi_irq_balance_set(char *str) { return 0; }
+#endif
+
+#ifdef CONFIG_ACPI_SLEEP
+
+/* 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);
+
+#endif /*CONFIG_ACPI_SLEEP*/
+
+#define boot_cpu_physical_apicid boot_cpu_id
+
+extern int acpi_disabled;
+extern int acpi_pci_disabled;
+
+extern u8 x86_acpiid_to_apicid[];
+
+extern int acpi_skip_timer_override;
+
+#endif /*__KERNEL__*/
+
+#endif /*_ASM_ACPI_H*/
diff --git a/include/asm-x86_64/agp.h b/include/asm-x86_64/agp.h
new file mode 100644
index 000000000000..0bb9019d58aa
--- /dev/null
+++ b/include/asm-x86_64/agp.h
@@ -0,0 +1,22 @@
+#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.
+ */
+
+int map_page_into_agp(struct page *page);
+int unmap_page_from_agp(struct page *page);
+#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")
+
+#endif
diff --git a/include/asm-x86_64/apic.h b/include/asm-x86_64/apic.h
new file mode 100644
index 000000000000..c025cc3ef789
--- /dev/null
+++ b/include/asm-x86_64/apic.h
@@ -0,0 +1,118 @@
+#ifndef __ASM_APIC_H
+#define __ASM_APIC_H
+
+#include <linux/config.h>
+#include <linux/pm.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;
+
+/*
+ * 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)
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+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 void apic_write_atomic(unsigned long reg, unsigned int v)
+{
+	xchg((volatile unsigned int *)(APIC_BASE+reg), v);
+}
+
+static __inline unsigned int apic_read(unsigned long reg)
+{
+	return *((volatile unsigned int *)(APIC_BASE+reg));
+}
+
+static __inline__ void apic_wait_icr_idle(void)
+{
+	while ( apic_read( APIC_ICR ) & APIC_ICR_BUSY );
+}
+
+#define FORCE_READ_AROUND_WRITE 0
+#define apic_read_around(x)
+#define apic_write_around(x,y) apic_write((x),(y))
+
+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 get_maxlvt (void);
+extern void clear_local_APIC (void);
+extern void connect_bsp_APIC (void);
+extern void disconnect_bsp_APIC (void);
+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 (struct pt_regs * regs);
+extern void setup_boot_APIC_clock (void);
+extern void setup_secondary_APIC_clock (void);
+extern void setup_apic_nmi_watchdog (void);
+extern int reserve_lapic_nmi(void);
+extern void release_lapic_nmi(void);
+extern void disable_timer_nmi_watchdog(void);
+extern void enable_timer_nmi_watchdog(void);
+extern void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
+extern int APIC_init_uniprocessor (void);
+extern void disable_APIC_timer(void);
+extern void enable_APIC_timer(void);
+extern void clustered_apic_check(void);
+
+extern int check_nmi_watchdog(void);
+extern void nmi_watchdog_default(void);
+extern int setup_nmi_watchdog(char *);
+
+extern unsigned int nmi_watchdog;
+#define NMI_DEFAULT	-1
+#define NMI_NONE	0
+#define NMI_IO_APIC	1
+#define NMI_LOCAL_APIC	2
+#define NMI_INVALID	3
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#define esr_disable 0
+extern unsigned boot_cpu_id;
+
+#endif /* __ASM_APIC_H */
diff --git a/include/asm-x86_64/apicdef.h b/include/asm-x86_64/apicdef.h
new file mode 100644
index 000000000000..3d7627ffe67d
--- /dev/null
+++ b/include/asm-x86_64/apicdef.h
@@ -0,0 +1,391 @@
+#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		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_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_EXINT		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 32
+
+/*
+ * 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
+
+#define lapic ((volatile struct local_apic *)APIC_BASE)
+
+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_64/atomic.h b/include/asm-x86_64/atomic.h
new file mode 100644
index 000000000000..fc4c5956e1ea
--- /dev/null
+++ b/include/asm-x86_64/atomic.h
@@ -0,0 +1,381 @@
+#ifndef __ARCH_X86_64_ATOMIC__
+#define __ARCH_X86_64_ATOMIC__
+
+#include <linux/config.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 { volatile 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 "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 "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 "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 "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 "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 "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 "incl %0; sete %1"
+		:"=m" (v->counter), "=qm" (c)
+		:"m" (v->counter) : "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 "addl %2,%0; sets %1"
+		:"=m" (v->counter), "=qm" (c)
+		:"ir" (i), "m" (v->counter) : "memory");
+	return c;
+}
+
+/* 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 "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 "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 "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 "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 "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 "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 "incq %0; sete %1"
+		:"=m" (v->counter), "=qm" (c)
+		:"m" (v->counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @v: pointer to atomic64_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__ long atomic64_add_negative(long i, atomic64_t *v)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		LOCK "addq %2,%0; sets %1"
+		:"=m" (v->counter), "=qm" (c)
+		:"ir" (i), "m" (v->counter) : "memory");
+	return c;
+}
+
+/**
+ * atomic_add_return - add 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 = i;
+	__asm__ __volatile__(
+		LOCK "xaddl %0, %1;"
+		:"=r"(i)
+		:"m"(v->counter), "0"(i));
+	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))
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr) \
+__asm__ __volatile__(LOCK "andl %0,%1" \
+: : "r" (~(mask)),"m" (*addr) : "memory")
+
+#define atomic_set_mask(mask, addr) \
+__asm__ __volatile__(LOCK "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()
+
+#endif
diff --git a/include/asm-x86_64/bitops.h b/include/asm-x86_64/bitops.h
new file mode 100644
index 000000000000..5dd7727c756b
--- /dev/null
+++ b/include/asm-x86_64/bitops.h
@@ -0,0 +1,418 @@
+#ifndef _X86_64_BITOPS_H
+#define _X86_64_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+#include <linux/config.h>
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX "lock ; "
+#else
+#define LOCK_PREFIX ""
+#endif
+
+#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 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"
+		:"=m" (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"
+		:"=m" (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"
+		:"=m" (ADDR)
+		:"dIr" (nr));
+}
+
+static __inline__ void __clear_bit(int nr, volatile void * addr)
+{
+	__asm__ __volatile__(
+		"btrl %1,%0"
+		:"=m" (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"
+		:"=m" (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"
+		:"=m" (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),"=m" (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),"=m" (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),"=m" (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),"=m" (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),"=m" (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),"=m" (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" (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;
+}
+
+#ifdef __KERNEL__
+
+static inline int sched_find_first_bit(const unsigned long *b)
+{
+	if (b[0])
+		return __ffs(b[0]);
+	if (b[1])
+		return __ffs(b[1]) + 64;
+	if (b[2])
+		return __ffs(b[2]) + 128;
+}
+
+/**
+ * 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;
+}
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+#define hweight64(x) generic_hweight64(x)
+#define hweight32(x) generic_hweight32(x)
+#define hweight16(x) generic_hweight16(x)
+#define hweight8(x) generic_hweight8(x)
+
+#endif /* __KERNEL__ */
+
+#ifdef __KERNEL__
+
+#define ext2_set_bit(nr,addr) \
+	__test_and_set_bit((nr),(unsigned long*)addr)
+#define ext2_set_bit_atomic(lock,nr,addr) \
+	        test_and_set_bit((nr),(unsigned long*)addr)
+#define ext2_clear_bit(nr, addr) \
+	__test_and_clear_bit((nr),(unsigned long*)addr)
+#define ext2_clear_bit_atomic(lock,nr,addr) \
+	        test_and_clear_bit((nr),(unsigned long*)addr)
+#define ext2_test_bit(nr, addr)      test_bit((nr),(unsigned long*)addr)
+#define ext2_find_first_zero_bit(addr, size) \
+	find_first_zero_bit((unsigned long*)addr, size)
+#define ext2_find_next_zero_bit(addr, size, off) \
+	find_next_zero_bit((unsigned long*)addr, size, off)
+
+/* Bitmap functions for the minix filesystem.  */
+#define minix_test_and_set_bit(nr,addr) __test_and_set_bit(nr,(void*)addr)
+#define minix_set_bit(nr,addr) __set_bit(nr,(void*)addr)
+#define minix_test_and_clear_bit(nr,addr) __test_and_clear_bit(nr,(void*)addr)
+#define minix_test_bit(nr,addr) test_bit(nr,(void*)addr)
+#define minix_find_first_zero_bit(addr,size) \
+	find_first_zero_bit((void*)addr,size)
+
+/* find last set bit */
+#define fls(x) generic_fls(x)
+
+#define ARCH_HAS_ATOMIC_UNSIGNED 1
+
+#endif /* __KERNEL__ */
+
+#endif /* _X86_64_BITOPS_H */
diff --git a/include/asm-x86_64/boot.h b/include/asm-x86_64/boot.h
new file mode 100644
index 000000000000..96b228e6e79c
--- /dev/null
+++ b/include/asm-x86_64/boot.h
@@ -0,0 +1,15 @@
+#ifndef _LINUX_BOOT_H
+#define _LINUX_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 */
+
+#endif
diff --git a/include/asm-x86_64/bootsetup.h b/include/asm-x86_64/bootsetup.h
new file mode 100644
index 000000000000..b570a484dc50
--- /dev/null
+++ b/include/asm-x86_64/bootsetup.h
@@ -0,0 +1,39 @@
+
+#ifndef _X86_64_BOOTSETUP_H
+#define _X86_64_BOOTSETUP_H 1
+
+extern char x86_boot_params[2048];
+
+/*
+ * 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 saved_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_64/bug.h b/include/asm-x86_64/bug.h
new file mode 100644
index 000000000000..d2032f56e87c
--- /dev/null
+++ b/include/asm-x86_64/bug.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_X8664_BUG_H
+#define __ASM_X8664_BUG_H 1
+
+#include <linux/stringify.h>
+
+/*
+ * Tell the user there is some problem.  The exception handler decodes 
+ * this frame.
+ */
+struct bug_frame {
+       unsigned char ud2[2];
+	/* should use 32bit offset instead, but the assembler doesn't 
+	   like it */
+	char *filename;
+	unsigned short line;
+} __attribute__((packed));
+
+#define HAVE_ARCH_BUG
+#define BUG() \
+	asm volatile("ud2 ; .quad %c1 ; .short %c0" :: \
+		     "i"(__LINE__), "i" (__stringify(KBUILD_BASENAME)))
+void out_of_line_bug(void);
+#include <asm-generic/bug.h>
+
+#endif
diff --git a/include/asm-x86_64/bugs.h b/include/asm-x86_64/bugs.h
new file mode 100644
index 000000000000..59bc68925d0f
--- /dev/null
+++ b/include/asm-x86_64/bugs.h
@@ -0,0 +1,29 @@
+/*
+ *  include/asm-x86_64/bugs.h
+ *
+ *  Copyright (C) 1994  Linus Torvalds
+ *  Copyright (C) 2000  SuSE
+ *
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Needs:
+ *	void check_bugs(void);
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/msr.h>
+#include <asm/pda.h>
+
+extern void alternative_instructions(void);
+
+static void __init check_bugs(void)
+{
+	identify_cpu(&boot_cpu_data);
+#if !defined(CONFIG_SMP)
+	printk("CPU: ");
+	print_cpu_info(&boot_cpu_data);
+#endif
+	alternative_instructions(); 
+}
diff --git a/include/asm-x86_64/byteorder.h b/include/asm-x86_64/byteorder.h
new file mode 100644
index 000000000000..5e86c868c75e
--- /dev/null
+++ b/include/asm-x86_64/byteorder.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_64/cache.h b/include/asm-x86_64/cache.h
new file mode 100644
index 000000000000..eda62bae1240
--- /dev/null
+++ b/include/asm-x86_64/cache.h
@@ -0,0 +1,14 @@
+/*
+ * include/asm-x8664/cache.h
+ */
+#ifndef __ARCH_X8664_CACHE_H
+#define __ARCH_X8664_CACHE_H
+
+#include <linux/config.h>
+
+/* L1 cache line size */
+#define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
+#define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
+#define L1_CACHE_SHIFT_MAX 6	/* largest L1 which this arch supports */
+
+#endif
diff --git a/include/asm-x86_64/cacheflush.h b/include/asm-x86_64/cacheflush.h
new file mode 100644
index 000000000000..b3189fb229d1
--- /dev/null
+++ b/include/asm-x86_64/cacheflush.h
@@ -0,0 +1,30 @@
+#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_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);
+
+#endif /* _X8664_CACHEFLUSH_H */
diff --git a/include/asm-x86_64/calling.h b/include/asm-x86_64/calling.h
new file mode 100644
index 000000000000..0bc12655fa5b
--- /dev/null
+++ b/include/asm-x86_64/calling.h
@@ -0,0 +1,156 @@
+/* 
+ * Some macros to handle stack frames in assembly.
+ */ 
+
+#include <linux/config.h>
+
+#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
+	.endif
+	.if \skipr8910
+	.else
+	movq 1*8(%rsp),%r10
+	movq 2*8(%rsp),%r9
+	movq 3*8(%rsp),%r8
+	.endif
+	.if \skiprax
+	.else
+	movq 4*8(%rsp),%rax
+	.endif
+	.if \skiprcx
+	.else
+	movq 5*8(%rsp),%rcx
+	.endif
+	.if \skiprdx
+	.else
+	movq 6*8(%rsp),%rdx
+	.endif
+	movq 7*8(%rsp),%rsi
+	movq 8*8(%rsp),%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
+	movq 1*8(%rsp),%r14
+	movq 2*8(%rsp),%r13
+	movq 3*8(%rsp),%r12
+	movq 4*8(%rsp),%rbp
+	movq 5*8(%rsp),%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
+
+#ifdef CONFIG_FRAME_POINTER
+#define ENTER enter
+#define LEAVE leave
+#else
+#define ENTER
+#define LEAVE
+#endif
diff --git a/include/asm-x86_64/checksum.h b/include/asm-x86_64/checksum.h
new file mode 100644
index 000000000000..d01356f01448
--- /dev/null
+++ b/include/asm-x86_64/checksum.h
@@ -0,0 +1,193 @@
+#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 unsigned int csum_fold(unsigned int sum)
+{
+	__asm__(
+		"  addl %1,%0\n"
+		"  adcl $0xffff,%0"
+		: "=r" (sum)
+		: "r" (sum << 16), "0" (sum & 0xffff0000)
+	);
+	return (~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 unsigned short ip_fast_csum(unsigned char *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 ipl
+	   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(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 unsigned long 
+csum_tcpudp_nofold(unsigned saddr, unsigned daddr, unsigned short len,
+		   unsigned short proto, unsigned int 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" ((ntohs(len)<<16)+proto*256), "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 unsigned short int 
+csum_tcpudp_magic(unsigned long saddr, unsigned long daddr,
+		  unsigned short len, unsigned short proto, unsigned int 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 unsigned int csum_partial(const unsigned char *buff, unsigned len, unsigned int 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 unsigned long csum_partial_copy_generic(const unsigned char *src, const unsigned char *dst,
+					       unsigned len,
+					       unsigned sum, 
+					       int *src_err_ptr, int *dst_err_ptr);
+
+
+extern unsigned int csum_partial_copy_from_user(const unsigned char __user *src, unsigned char *dst,
+				       int len, unsigned int isum, int *errp);
+extern unsigned int csum_partial_copy_to_user(const unsigned char *src, unsigned char __user *dst,
+				      int len, unsigned int isum, int *errp);
+extern unsigned int csum_partial_copy_nocheck(const unsigned char *src, unsigned char *dst, int len,
+					      unsigned int 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 unsigned short ip_compute_csum(unsigned char * 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 unsigned short 
+csum_ipv6_magic(struct in6_addr *saddr, struct in6_addr *daddr,
+		__u32 len, unsigned short proto, unsigned int 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_64/compat.h b/include/asm-x86_64/compat.h
new file mode 100644
index 000000000000..d0f453c5adfc
--- /dev/null
+++ b/include/asm-x86_64/compat.h
@@ -0,0 +1,205 @@
+#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 u32		compat_uint_t;
+typedef u32		compat_ulong_t;
+
+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 = (void *)current->thread.rsp0 - sizeof(struct pt_regs); 
+	return (void __user *)regs->rsp - len; 
+}
+
+#endif /* _ASM_X86_64_COMPAT_H */
diff --git a/include/asm-x86_64/cpu.h b/include/asm-x86_64/cpu.h
new file mode 100644
index 000000000000..8eea076525a4
--- /dev/null
+++ b/include/asm-x86_64/cpu.h
@@ -0,0 +1 @@
+#include <asm-i386/cpu.h>
diff --git a/include/asm-x86_64/cpufeature.h b/include/asm-x86_64/cpufeature.h
new file mode 100644
index 000000000000..0e47a6d53726
--- /dev/null
+++ b/include/asm-x86_64/cpufeature.h
@@ -0,0 +1,104 @@
+/*
+ * cpufeature.h
+ *
+ * Defines x86 CPU feature bits
+ */
+
+#ifndef __ASM_X8664_CPUFEATURE_H
+#define __ASM_X8664_CPUFEATURE_H
+
+#define NCAPINTS	6
+
+/* Intel-defined CPU features, CPUID level 0x00000001, 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_DTES	(0*32+21) /* Debug Trace 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_MMXEXT	(1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT	(1*32+25) /* FXSR optimizations */
+#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) */
+#define X86_FEATURE_K8_C	(3*32+ 4) /* C stepping K8 */
+
+/* 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 */
+
+/* More extended AMD flags: CPUID level 0x80000001, ecx, word 5 */
+#define X86_FEATURE_LAHF_LM	(5*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY	(5*32+ 1) /* If yes HyperThreading not valid */
+
+#define cpu_has(c, bit)                test_bit(bit, (c)->x86_capability)
+#define boot_cpu_has(bit)      test_bit(bit, boot_cpu_data.x86_capability)
+
+#define cpu_has_fpu            1
+#define cpu_has_vme            0
+#define cpu_has_de             1
+#define cpu_has_pse            1
+#define cpu_has_tsc            1
+#define cpu_has_pae            ___BUG___
+#define cpu_has_pge            1
+#define cpu_has_apic           boot_cpu_has(X86_FEATURE_APIC)
+#define cpu_has_mtrr           1
+#define cpu_has_mmx            1
+#define cpu_has_fxsr           1
+#define cpu_has_xmm            1
+#define cpu_has_xmm2           1
+#define cpu_has_xmm3           boot_cpu_has(X86_FEATURE_XMM3)
+#define cpu_has_ht             boot_cpu_has(X86_FEATURE_HT)
+#define cpu_has_mp             1 /* XXX */
+#define cpu_has_k6_mtrr        0
+#define cpu_has_cyrix_arr      0
+#define cpu_has_centaur_mcr    0
+#define cpu_has_clflush	       boot_cpu_has(X86_FEATURE_CLFLSH)
+
+#endif /* __ASM_X8664_CPUFEATURE_H */
diff --git a/include/asm-x86_64/cputime.h b/include/asm-x86_64/cputime.h
new file mode 100644
index 000000000000..a07012dc5a3c
--- /dev/null
+++ b/include/asm-x86_64/cputime.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_64/current.h b/include/asm-x86_64/current.h
new file mode 100644
index 000000000000..7db560ee6f70
--- /dev/null
+++ b/include/asm-x86_64/current.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/offset.h> 
+#endif
+
+#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
+
+#endif
+
+#endif /* !(_X86_64_CURRENT_H) */
diff --git a/include/asm-x86_64/debugreg.h b/include/asm-x86_64/debugreg.h
new file mode 100644
index 000000000000..bd1aab1d8c4a
--- /dev/null
+++ b/include/asm-x86_64/debugreg.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_64/delay.h b/include/asm-x86_64/delay.h
new file mode 100644
index 000000000000..65f64acc5319
--- /dev/null
+++ b/include/asm-x86_64/delay.h
@@ -0,0 +1,27 @@
+#ifndef _X8664_DELAY_H
+#define _X8664_DELAY_H
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines calling functions in arch/x86_64/lib/delay.c
+ */
+ 
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long usecs);
+extern void __const_udelay(unsigned long usecs);
+extern void __delay(unsigned long loops);
+
+#define udelay(n) (__builtin_constant_p(n) ? \
+	((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c6ul)) : \
+	__udelay(n))
+
+#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_64/desc.h b/include/asm-x86_64/desc.h
new file mode 100644
index 000000000000..6aefb9c0280d
--- /dev/null
+++ b/include/asm-x86_64/desc.h
@@ -0,0 +1,217 @@
+/* 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 <asm/segment.h>
+#include <asm/mmu.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;
+}; 	
+
+extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES];
+
+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)) ;
+
+#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[]; 
+
+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) 
+{ 
+	_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) 
+{ 
+	_set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, ist); 
+} 
+
+static inline void set_system_gate(int nr, void *func) 
+{ 
+	_set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0); 
+} 
+
+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)
+{ 
+	set_tssldt_descriptor(&cpu_gdt_table[cpu][GDT_ENTRY_TSS], (unsigned long)addr, 
+			      DESC_TSS,
+			      sizeof(struct tss_struct) - 1);
+} 
+
+static inline void set_ldt_desc(unsigned cpu, void *addr, int size)
+{ 
+	set_tssldt_descriptor(&cpu_gdt_table[cpu][GDT_ENTRY_LDT], (unsigned long)addr, 
+			      DESC_LDT, size * 8 - 1);
+}
+
+static inline void set_seg_base(unsigned cpu, int entry, void *base)
+{ 
+	struct desc_struct *d = &cpu_gdt_table[cpu][entry];
+	u32 addr = (u32)(u64)base;
+	BUG_ON((u64)base >> 32); 
+	d->base0 = addr & 0xffff;
+	d->base1 = (addr >> 16) & 0xff;
+	d->base2 = (addr >> 24) & 0xff;
+} 
+
+#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)
+
+#if TLS_SIZE != 24
+# error update this code.
+#endif
+
+static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
+{
+	u64 *gdt = (u64 *)(cpu_gdt_table[cpu] + GDT_ENTRY_TLS_MIN);
+	gdt[0] = t->tls_array[0];
+	gdt[1] = t->tls_array[1];
+	gdt[2] = t->tls_array[2];
+} 
+
+/*
+ * load one particular LDT into the current CPU
+ */
+extern 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_64/div64.h b/include/asm-x86_64/div64.h
new file mode 100644
index 000000000000..6cd978cefb28
--- /dev/null
+++ b/include/asm-x86_64/div64.h
@@ -0,0 +1 @@
+#include <asm-generic/div64.h>
diff --git a/include/asm-x86_64/dma-mapping.h b/include/asm-x86_64/dma-mapping.h
new file mode 100644
index 000000000000..a416dc31634a
--- /dev/null
+++ b/include/asm-x86_64/dma-mapping.h
@@ -0,0 +1,138 @@
+#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 <linux/config.h>
+
+#include <asm/scatterlist.h>
+#include <asm/io.h>
+#include <asm/swiotlb.h>
+
+extern dma_addr_t bad_dma_address;
+#define dma_mapping_error(x) \
+	(swiotlb ? swiotlb_dma_mapping_error(x) : ((x) == bad_dma_address))
+
+void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+			 unsigned gfp);
+void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
+			 dma_addr_t dma_handle);
+
+#ifdef CONFIG_GART_IOMMU
+
+extern dma_addr_t dma_map_single(struct device *hwdev, void *ptr, size_t size,
+				 int direction);
+extern void dma_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
+			     int direction);
+
+#else
+
+/* No IOMMU */
+
+static inline dma_addr_t dma_map_single(struct device *hwdev, void *ptr,
+					size_t size, int direction)
+{
+	dma_addr_t addr;
+
+	if (direction == DMA_NONE)
+		out_of_line_bug();
+	addr = virt_to_bus(ptr);
+
+	if ((addr+size) & ~*hwdev->dma_mask)
+		out_of_line_bug();
+	return addr;
+}
+
+static inline void dma_unmap_single(struct device *hwdev, dma_addr_t dma_addr,
+				    size_t size, int direction)
+{
+	if (direction == DMA_NONE)
+		out_of_line_bug();
+	/* Nothing to do */
+}
+
+#endif
+
+#define dma_map_page(dev,page,offset,size,dir) \
+	dma_map_single((dev), page_address(page)+(offset), (size), (dir))
+
+static inline void dma_sync_single_for_cpu(struct device *hwdev,
+					       dma_addr_t dma_handle,
+					       size_t size, int direction)
+{
+	if (direction == DMA_NONE)
+		out_of_line_bug();
+
+	if (swiotlb)
+		return swiotlb_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)
+{
+        if (direction == DMA_NONE)
+		out_of_line_bug();
+
+	if (swiotlb)
+		return swiotlb_sync_single_for_device(hwdev,dma_handle,size,direction);
+
+	flush_write_buffers();
+}
+
+static inline void dma_sync_sg_for_cpu(struct device *hwdev,
+				       struct scatterlist *sg,
+				       int nelems, int direction)
+{
+	if (direction == DMA_NONE)
+		out_of_line_bug();
+
+	if (swiotlb)
+		return swiotlb_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)
+{
+	if (direction == DMA_NONE)
+		out_of_line_bug();
+
+	if (swiotlb)
+		return swiotlb_sync_sg_for_device(hwdev,sg,nelems,direction);
+
+	flush_write_buffers();
+}
+
+extern int dma_map_sg(struct device *hwdev, struct scatterlist *sg,
+		      int nents, int direction);
+extern void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg,
+			 int nents, int direction);
+
+#define dma_unmap_page dma_unmap_single
+
+extern int dma_supported(struct device *hwdev, u64 mask);
+extern int dma_get_cache_alignment(void);
+#define dma_is_consistent(h) 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 void dma_cache_sync(void *vaddr, size_t size, enum dma_data_direction dir)
+{
+	flush_write_buffers();
+}
+
+#endif
diff --git a/include/asm-x86_64/dma.h b/include/asm-x86_64/dma.h
new file mode 100644
index 000000000000..16fa3a064d0c
--- /dev/null
+++ b/include/asm-x86_64/dma.h
@@ -0,0 +1,298 @@
+/* $Id: dma.h,v 1.1.1.1 2001/04/19 20:00:38 ak Exp $
+ * 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/config.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 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_64/dwarf2.h b/include/asm-x86_64/dwarf2.h
new file mode 100644
index 000000000000..afd4212e860b
--- /dev/null
+++ b/include/asm-x86_64/dwarf2.h
@@ -0,0 +1,42 @@
+#ifndef _DWARF2_H
+#define _DWARF2_H 1
+
+#include <linux/config.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_DEBUG_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
+
+#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	#
+
+#endif
+
+#endif
diff --git a/include/asm-x86_64/e820.h b/include/asm-x86_64/e820.h
new file mode 100644
index 000000000000..5b376e42b153
--- /dev/null
+++ b/include/asm-x86_64/e820.h
@@ -0,0 +1,59 @@
+/*
+ * structures and definitions for the int 15, ax=e820 memory map
+ * scheme.
+ *
+ * In a nutshell, setup.S populates a scratch table in the
+ * empty_zero_block that contains a list of usable address/size
+ * duples.  setup.c, this information is transferred into the e820map,
+ * and in init.c/numa.c, that new information is used to mark pages
+ * reserved or not.
+ */
+#ifndef __E820_HEADER
+#define __E820_HEADER
+
+#include <linux/mmzone.h>
+
+#define E820MAP	0x2d0		/* our map */
+#define E820MAX	32		/* number of entries in E820MAP */
+#define E820NR	0x1e8		/* # entries in E820MAP */
+
+#define E820_RAM	1
+#define E820_RESERVED	2
+#define E820_ACPI	3 /* usable as RAM once ACPI tables have been read */
+#define E820_NVS	4
+
+#define HIGH_MEMORY	(1024*1024)
+
+#define LOWMEMSIZE()	(0x9f000)
+
+#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 {
+    int 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_print_map(char *who);
+extern int e820_mapped(unsigned long start, unsigned long end, unsigned type);
+
+extern void e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end);
+
+extern void __init parse_memopt(char *p, char **end);
+
+extern struct e820map e820;
+#endif/*!__ASSEMBLY__*/
+
+#endif/*__E820_HEADER*/
diff --git a/include/asm-x86_64/elf.h b/include/asm-x86_64/elf.h
new file mode 100644
index 000000000000..a60a35e79222
--- /dev/null
+++ b/include/asm-x86_64/elf.h
@@ -0,0 +1,160 @@
+#ifndef __ASM_X86_64_ELF_H
+#define __ASM_X86_64_ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+#include <asm/user.h>
+#include <asm/processor.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;
+
+/*
+ * 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)
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS64
+#define ELF_DATA	ELFDATA2LSB
+#define ELF_ARCH	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")
+
+#ifdef __KERNEL__
+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)
+
+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)
+
+#endif
+
+#endif
diff --git a/include/asm-x86_64/errno.h b/include/asm-x86_64/errno.h
new file mode 100644
index 000000000000..311182129e32
--- /dev/null
+++ b/include/asm-x86_64/errno.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_64/fcntl.h b/include/asm-x86_64/fcntl.h
new file mode 100644
index 000000000000..4411f221c037
--- /dev/null
+++ b/include/asm-x86_64/fcntl.h
@@ -0,0 +1,76 @@
+#ifndef _X86_64_FCNTL_H
+#define _X86_64_FCNTL_H
+
+/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
+   located on an ext2 file system */
+#define O_ACCMODE	   0003
+#define O_RDONLY	     00
+#define O_WRONLY	     01
+#define O_RDWR		     02
+#define O_CREAT		   0100	/* not fcntl */
+#define O_EXCL		   0200	/* not fcntl */
+#define O_NOCTTY	   0400	/* not fcntl */
+#define O_TRUNC		  01000	/* not fcntl */
+#define O_APPEND	  02000
+#define O_NONBLOCK	  04000
+#define O_NDELAY	O_NONBLOCK
+#define O_SYNC		 010000
+#define FASYNC		 020000	/* fcntl, for BSD compatibility */
+#define O_DIRECT	 040000	/* direct disk access hint */
+#define O_LARGEFILE	0100000
+#define O_DIRECTORY	0200000	/* must be a directory */
+#define O_NOFOLLOW	0400000 /* don't follow links */
+#define O_NOATIME	01000000
+
+#define F_DUPFD		0	/* dup */
+#define F_GETFD		1	/* get close_on_exec */
+#define F_SETFD		2	/* set/clear close_on_exec */
+#define F_GETFL		3	/* get file->f_flags */
+#define F_SETFL		4	/* set file->f_flags */
+#define F_GETLK		5
+#define F_SETLK		6
+#define F_SETLKW	7
+
+#define F_SETOWN	8	/*  for sockets. */
+#define F_GETOWN	9	/*  for sockets. */
+#define F_SETSIG	10	/*  for sockets. */
+#define F_GETSIG	11	/*  for sockets. */
+
+/* for F_[GET|SET]FL */
+#define FD_CLOEXEC	1	/* actually anything with low bit set goes */
+
+/* for posix fcntl() and lockf() */
+#define F_RDLCK		0
+#define F_WRLCK		1
+#define F_UNLCK		2
+
+/* for old implementation of bsd flock () */
+#define F_EXLCK		4	/* or 3 */
+#define F_SHLCK		8	/* or 4 */
+
+/* for leases */
+#define F_INPROGRESS	16
+
+/* operations for bsd flock(), also used by the kernel implementation */
+#define LOCK_SH		1	/* shared lock */
+#define LOCK_EX		2	/* exclusive lock */
+#define LOCK_NB		4	/* or'd with one of the above to prevent
+				   blocking */
+#define LOCK_UN		8	/* remove lock */
+
+#define LOCK_MAND	32	/* This is a mandatory flock */
+#define LOCK_READ	64	/* ... Which allows concurrent read operations */
+#define LOCK_WRITE	128	/* ... Which allows concurrent write operations */
+#define LOCK_RW		192	/* ... Which allows concurrent read & write ops */
+
+struct flock {
+	short  l_type;
+	short  l_whence;
+	off_t l_start;
+	off_t l_len;
+	pid_t  l_pid;
+};
+
+#define F_LINUX_SPECIFIC_BASE	1024
+
+#endif /* !_X86_64_FCNTL_H */
diff --git a/include/asm-x86_64/fixmap.h b/include/asm-x86_64/fixmap.h
new file mode 100644
index 000000000000..cf8b16cbe8db
--- /dev/null
+++ b/include/asm-x86_64/fixmap.h
@@ -0,0 +1,96 @@
+/*
+ * 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/config.h>
+#include <linux/kernel.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#include <asm/vsyscall.h>
+#include <asm/vsyscall32.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
+ * 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 {
+	VSYSCALL_LAST_PAGE,
+	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
+	VSYSCALL_HPET,
+	FIX_HPET_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
+	__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.
+ */
+extern 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_64/floppy.h b/include/asm-x86_64/floppy.h
new file mode 100644
index 000000000000..bca9b28a1a0a
--- /dev/null
+++ b/include/asm-x86_64/floppy.h
@@ -0,0 +1,285 @@
+/*
+ * 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, struct pt_regs * regs)
+{
+	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, regs);
+
+#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, regs);
+		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,SA_INTERRUPT,
+						   "floppy", NULL);
+	else
+		return request_irq(FLOPPY_IRQ, floppy_interrupt,
+						   SA_INTERRUPT|SA_SAMPLE_RANDOM,
+						   "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 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;
+}
+
+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_64/fpu32.h b/include/asm-x86_64/fpu32.h
new file mode 100644
index 000000000000..4153db5c0c31
--- /dev/null
+++ b/include/asm-x86_64/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_64/genapic.h b/include/asm-x86_64/genapic.h
new file mode 100644
index 000000000000..50b38e7c58e4
--- /dev/null
+++ b/include/asm-x86_64/genapic.h
@@ -0,0 +1,35 @@
+#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;
+	u32 int_delivery_dest;	/* for quick IPIs */
+	int (*apic_id_registered)(void);
+	cpumask_t (*target_cpus)(void);
+	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;
+
+#endif
diff --git a/include/asm-x86_64/hardirq.h b/include/asm-x86_64/hardirq.h
new file mode 100644
index 000000000000..27c381fa1c9d
--- /dev/null
+++ b/include/asm-x86_64/hardirq.h
@@ -0,0 +1,37 @@
+#ifndef __ASM_HARDIRQ_H
+#define __ASM_HARDIRQ_H
+
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/irq.h>
+#include <asm/pda.h>
+#include <asm/apic.h>
+
+#define __ARCH_IRQ_STAT 1
+
+/* Generate a lvalue for a pda member. Should fix softirq.c instead to use
+   special access macros. This would generate better code. */ 
+#define __IRQ_STAT(cpu,member) (read_pda(me)->member)
+
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+
+/*
+ * 'what should we do if we get a hw irq event on an illegal vector'.
+ * each architecture has to answer this themselves.
+ */
+static inline void ack_bad_irq(unsigned int irq)
+{
+	printk("unexpected IRQ trap at vector %02x\n", irq);
+#ifdef CONFIG_X86_LOCAL_APIC
+	/*
+	 * Currently unexpected vectors happen only on SMP and APIC.
+	 * We _must_ ack these because every local APIC has only N
+	 * irq slots per priority level, and a 'hanging, unacked' IRQ
+	 * holds up an irq slot - in excessive cases (when multiple
+	 * unexpected vectors occur) that might lock up the APIC
+	 * completely.
+	 */
+	ack_APIC_irq();
+#endif
+}
+#endif /* __ASM_HARDIRQ_H */
diff --git a/include/asm-x86_64/hdreg.h b/include/asm-x86_64/hdreg.h
new file mode 100644
index 000000000000..5989bbc97cbf
--- /dev/null
+++ b/include/asm-x86_64/hdreg.h
@@ -0,0 +1 @@
+#warning this file is obsolete, please do not use it
diff --git a/include/asm-x86_64/hpet.h b/include/asm-x86_64/hpet.h
new file mode 100644
index 000000000000..a3877f570998
--- /dev/null
+++ b/include/asm-x86_64/hpet.h
@@ -0,0 +1,60 @@
+#ifndef _ASM_X8664_HPET_H
+#define _ASM_X8664_HPET_H 1
+
+/*
+ * 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_VENDOR	0xffff0000
+#define HPET_ID_LEGSUP	0x00008000
+#define HPET_ID_NUMBER	0x00001f00
+#define HPET_ID_REV	0x000000ff
+#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_ENABLE		0x004
+#define HPET_TN_PERIODIC	0x008
+#define HPET_TN_PERIODIC_CAP	0x010
+#define HPET_TN_SETVAL		0x040
+#define HPET_TN_32BIT		0x100
+
+extern int is_hpet_enabled(void);
+extern int hpet_rtc_timer_init(void);
+extern int oem_force_hpet_timer(void);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+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);
+#endif /* CONFIG_HPET_EMULATE_RTC */
+
+#endif
diff --git a/include/asm-x86_64/hw_irq.h b/include/asm-x86_64/hw_irq.h
new file mode 100644
index 000000000000..2b5cb2865d21
--- /dev/null
+++ b/include/asm-x86_64/hw_irq.h
@@ -0,0 +1,144 @@
+#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.
+ * 
+ *  $Id: hw_irq.h,v 1.24 2001/09/14 20:55:03 vojtech Exp $
+ */
+
+#ifndef __ASSEMBLY__
+#include <linux/config.h>
+#include <asm/atomic.h>
+#include <asm/irq.h>
+#include <linux/profile.h>
+#include <linux/smp.h>
+
+struct hw_interrupt_type;
+#endif
+
+/*
+ * IDT vectors usable for external interrupt sources start
+ * at 0x20:
+ */
+#define FIRST_EXTERNAL_VECTOR	0x20
+
+#define IA32_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 0xf0-0xf9 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 TASK_MIGRATION_VECTOR	0xfb
+#define CALL_FUNCTION_VECTOR	0xfa
+#define KDB_VECTOR	0xf9
+
+#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   /* duplicated in irq.h */
+
+
+#ifndef __ASSEMBLY__
+extern u8 irq_vector[NR_IRQ_VECTORS];
+#define IO_APIC_VECTOR(irq)	(irq_vector[irq])
+#define AUTO_ASSIGN		-1
+
+/*
+ * 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 FASTCALL(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 "-256 ; " \
+	"jmp common_interrupt");
+
+#if defined(CONFIG_X86_IO_APIC)
+static inline void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i) {
+	if (IO_APIC_IRQ(i))
+		send_IPI_self(IO_APIC_VECTOR(i));
+}
+#else
+static inline void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i) {}
+#endif
+
+#define platform_legacy_irq(irq)	((irq) < 16)
+
+#endif
+
+#endif /* _ASM_HW_IRQ_H */
diff --git a/include/asm-x86_64/i387.h b/include/asm-x86_64/i387.h
new file mode 100644
index 000000000000..aa39cfd0e001
--- /dev/null
+++ b/include/asm-x86_64/i387.h
@@ -0,0 +1,150 @@
+/*
+ * 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);
+
+/*
+ * FPU lazy state save handling...
+ */
+
+#define unlazy_fpu(tsk) do { \
+	if ((tsk)->thread_info->status & TS_USEDFPU) \
+		save_init_fpu(tsk); \
+} 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 ((tsk)->thread_info->status & TS_USEDFPU) {		\
+		tolerant_fwait();				\
+		(tsk)->thread_info->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))
+
+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)
+		     : [fx] "r" (fx), "0" (0)); 
+	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)
+		     : [fx] "r" (fx), "0" (0)); 
+	if (unlikely(err))
+		__clear_user(fx, sizeof(struct i387_fxsave_struct));
+	return err;
+} 
+
+static inline void kernel_fpu_begin(void)
+{
+	struct thread_info *me = current_thread_info();
+	preempt_disable();
+	if (me->status & TS_USEDFPU) { 
+		asm volatile("rex64 ; fxsave %0 ; fnclex"
+			      : "=m" (me->task->thread.i387.fxsave));
+		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 )
+{
+	asm volatile( "rex64 ; fxsave %0 ; fnclex"
+		      : "=m" (tsk->thread.i387.fxsave));
+	tsk->thread_info->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_64/ia32.h b/include/asm-x86_64/ia32.h
new file mode 100644
index 000000000000..c0a7717923ed
--- /dev/null
+++ b/include/asm-x86_64/ia32.h
@@ -0,0 +1,172 @@
+#ifndef _ASM_X86_64_IA32_H
+#define _ASM_X86_64_IA32_H
+
+#include <linux/config.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 {
+			int _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);
+#endif
+
+#endif /* !CONFIG_IA32_SUPPORT */
+ 
+#endif 
diff --git a/include/asm-x86_64/ia32_unistd.h b/include/asm-x86_64/ia32_unistd.h
new file mode 100644
index 000000000000..f3b7111cf33d
--- /dev/null
+++ b/include/asm-x86_64/ia32_unistd.h
@@ -0,0 +1,300 @@
+#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.
+ */
+
+#define __NR_ia32_restart_syscall 0
+#define __NR_ia32_exit		  1
+#define __NR_ia32_fork		  2
+#define __NR_ia32_read		  3
+#define __NR_ia32_write		  4
+#define __NR_ia32_open		  5
+#define __NR_ia32_close		  6
+#define __NR_ia32_waitpid		  7
+#define __NR_ia32_creat		  8
+#define __NR_ia32_link		  9
+#define __NR_ia32_unlink		 10
+#define __NR_ia32_execve		 11
+#define __NR_ia32_chdir		 12
+#define __NR_ia32_time		 13
+#define __NR_ia32_mknod		 14
+#define __NR_ia32_chmod		 15
+#define __NR_ia32_lchown		 16
+#define __NR_ia32_break		 17
+#define __NR_ia32_oldstat		 18
+#define __NR_ia32_lseek		 19
+#define __NR_ia32_getpid		 20
+#define __NR_ia32_mount		 21
+#define __NR_ia32_umount		 22
+#define __NR_ia32_setuid		 23
+#define __NR_ia32_getuid		 24
+#define __NR_ia32_stime		 25
+#define __NR_ia32_ptrace		 26
+#define __NR_ia32_alarm		 27
+#define __NR_ia32_oldfstat		 28
+#define __NR_ia32_pause		 29
+#define __NR_ia32_utime		 30
+#define __NR_ia32_stty		 31
+#define __NR_ia32_gtty		 32
+#define __NR_ia32_access		 33
+#define __NR_ia32_nice		 34
+#define __NR_ia32_ftime		 35
+#define __NR_ia32_sync		 36
+#define __NR_ia32_kill		 37
+#define __NR_ia32_rename		 38
+#define __NR_ia32_mkdir		 39
+#define __NR_ia32_rmdir		 40
+#define __NR_ia32_dup		 41
+#define __NR_ia32_pipe		 42
+#define __NR_ia32_times		 43
+#define __NR_ia32_prof		 44
+#define __NR_ia32_brk		 45
+#define __NR_ia32_setgid		 46
+#define __NR_ia32_getgid		 47
+#define __NR_ia32_signal		 48
+#define __NR_ia32_geteuid		 49
+#define __NR_ia32_getegid		 50
+#define __NR_ia32_acct		 51
+#define __NR_ia32_umount2		 52
+#define __NR_ia32_lock		 53
+#define __NR_ia32_ioctl		 54
+#define __NR_ia32_fcntl		 55
+#define __NR_ia32_mpx		 56
+#define __NR_ia32_setpgid		 57
+#define __NR_ia32_ulimit		 58
+#define __NR_ia32_oldolduname	 59
+#define __NR_ia32_umask		 60
+#define __NR_ia32_chroot		 61
+#define __NR_ia32_ustat		 62
+#define __NR_ia32_dup2		 63
+#define __NR_ia32_getppid		 64
+#define __NR_ia32_getpgrp		 65
+#define __NR_ia32_setsid		 66
+#define __NR_ia32_sigaction		 67
+#define __NR_ia32_sgetmask		 68
+#define __NR_ia32_ssetmask		 69
+#define __NR_ia32_setreuid		 70
+#define __NR_ia32_setregid		 71
+#define __NR_ia32_sigsuspend		 72
+#define __NR_ia32_sigpending		 73
+#define __NR_ia32_sethostname	 74
+#define __NR_ia32_setrlimit		 75
+#define __NR_ia32_getrlimit		 76	/* Back compatible 2Gig limited rlimit */
+#define __NR_ia32_getrusage		 77
+#define __NR_ia32_gettimeofday	 78
+#define __NR_ia32_settimeofday	 79
+#define __NR_ia32_getgroups		 80
+#define __NR_ia32_setgroups		 81
+#define __NR_ia32_select		 82
+#define __NR_ia32_symlink		 83
+#define __NR_ia32_oldlstat		 84
+#define __NR_ia32_readlink		 85
+#define __NR_ia32_uselib		 86
+#define __NR_ia32_swapon		 87
+#define __NR_ia32_reboot		 88
+#define __NR_ia32_readdir		 89
+#define __NR_ia32_mmap		 90
+#define __NR_ia32_munmap		 91
+#define __NR_ia32_truncate		 92
+#define __NR_ia32_ftruncate		 93
+#define __NR_ia32_fchmod		 94
+#define __NR_ia32_fchown		 95
+#define __NR_ia32_getpriority	 96
+#define __NR_ia32_setpriority	 97
+#define __NR_ia32_profil		 98
+#define __NR_ia32_statfs		 99
+#define __NR_ia32_fstatfs		100
+#define __NR_ia32_ioperm		101
+#define __NR_ia32_socketcall		102
+#define __NR_ia32_syslog		103
+#define __NR_ia32_setitimer		104
+#define __NR_ia32_getitimer		105
+#define __NR_ia32_stat		106
+#define __NR_ia32_lstat		107
+#define __NR_ia32_fstat		108
+#define __NR_ia32_olduname		109
+#define __NR_ia32_iopl		110
+#define __NR_ia32_vhangup		111
+#define __NR_ia32_idle		112
+#define __NR_ia32_vm86old		113
+#define __NR_ia32_wait4		114
+#define __NR_ia32_swapoff		115
+#define __NR_ia32_sysinfo		116
+#define __NR_ia32_ipc		117
+#define __NR_ia32_fsync		118
+#define __NR_ia32_sigreturn		119
+#define __NR_ia32_clone		120
+#define __NR_ia32_setdomainname	121
+#define __NR_ia32_uname		122
+#define __NR_ia32_modify_ldt		123
+#define __NR_ia32_adjtimex		124
+#define __NR_ia32_mprotect		125
+#define __NR_ia32_sigprocmask	126
+#define __NR_ia32_create_module	127
+#define __NR_ia32_init_module	128
+#define __NR_ia32_delete_module	129
+#define __NR_ia32_get_kernel_syms	130
+#define __NR_ia32_quotactl		131
+#define __NR_ia32_getpgid		132
+#define __NR_ia32_fchdir		133
+#define __NR_ia32_bdflush		134
+#define __NR_ia32_sysfs		135
+#define __NR_ia32_personality	136
+#define __NR_ia32_afs_syscall	137 /* Syscall for Andrew File System */
+#define __NR_ia32_setfsuid		138
+#define __NR_ia32_setfsgid		139
+#define __NR_ia32__llseek		140
+#define __NR_ia32_getdents		141
+#define __NR_ia32__newselect		142
+#define __NR_ia32_flock		143
+#define __NR_ia32_msync		144
+#define __NR_ia32_readv		145
+#define __NR_ia32_writev		146
+#define __NR_ia32_getsid		147
+#define __NR_ia32_fdatasync		148
+#define __NR_ia32__sysctl		149
+#define __NR_ia32_mlock		150
+#define __NR_ia32_munlock		151
+#define __NR_ia32_mlockall		152
+#define __NR_ia32_munlockall		153
+#define __NR_ia32_sched_setparam		154
+#define __NR_ia32_sched_getparam		155
+#define __NR_ia32_sched_setscheduler		156
+#define __NR_ia32_sched_getscheduler		157
+#define __NR_ia32_sched_yield		158
+#define __NR_ia32_sched_get_priority_max	159
+#define __NR_ia32_sched_get_priority_min	160
+#define __NR_ia32_sched_rr_get_interval	161
+#define __NR_ia32_nanosleep		162
+#define __NR_ia32_mremap		163
+#define __NR_ia32_setresuid		164
+#define __NR_ia32_getresuid		165
+#define __NR_ia32_vm86		166
+#define __NR_ia32_query_module	167
+#define __NR_ia32_poll		168
+#define __NR_ia32_nfsservctl		169
+#define __NR_ia32_setresgid		170
+#define __NR_ia32_getresgid		171
+#define __NR_ia32_prctl              172
+#define __NR_ia32_rt_sigreturn	173
+#define __NR_ia32_rt_sigaction	174
+#define __NR_ia32_rt_sigprocmask	175
+#define __NR_ia32_rt_sigpending	176
+#define __NR_ia32_rt_sigtimedwait	177
+#define __NR_ia32_rt_sigqueueinfo	178
+#define __NR_ia32_rt_sigsuspend	179
+#define __NR_ia32_pread		180
+#define __NR_ia32_pwrite		181
+#define __NR_ia32_chown		182
+#define __NR_ia32_getcwd		183
+#define __NR_ia32_capget		184
+#define __NR_ia32_capset		185
+#define __NR_ia32_sigaltstack	186
+#define __NR_ia32_sendfile		187
+#define __NR_ia32_getpmsg		188	/* some people actually want streams */
+#define __NR_ia32_putpmsg		189	/* some people actually want streams */
+#define __NR_ia32_vfork		190
+#define __NR_ia32_ugetrlimit		191	/* SuS compliant getrlimit */
+#define __NR_ia32_mmap2		192
+#define __NR_ia32_truncate64		193
+#define __NR_ia32_ftruncate64	194
+#define __NR_ia32_stat64		195
+#define __NR_ia32_lstat64		196
+#define __NR_ia32_fstat64		197
+#define __NR_ia32_lchown32		198
+#define __NR_ia32_getuid32		199
+#define __NR_ia32_getgid32		200
+#define __NR_ia32_geteuid32		201
+#define __NR_ia32_getegid32		202
+#define __NR_ia32_setreuid32		203
+#define __NR_ia32_setregid32		204
+#define __NR_ia32_getgroups32	205
+#define __NR_ia32_setgroups32	206
+#define __NR_ia32_fchown32		207
+#define __NR_ia32_setresuid32	208
+#define __NR_ia32_getresuid32	209
+#define __NR_ia32_setresgid32	210
+#define __NR_ia32_getresgid32	211
+#define __NR_ia32_chown32		212
+#define __NR_ia32_setuid32		213
+#define __NR_ia32_setgid32		214
+#define __NR_ia32_setfsuid32		215
+#define __NR_ia32_setfsgid32		216
+#define __NR_ia32_pivot_root		217
+#define __NR_ia32_mincore		218
+#define __NR_ia32_madvise		219
+#define __NR_ia32_madvise1		219	/* delete when C lib stub is removed */
+#define __NR_ia32_getdents64		220
+#define __NR_ia32_fcntl64		221
+#define __NR_ia32_tuxcall		222
+#define __NR_ia32_security		223
+#define __NR_ia32_gettid		224
+#define __NR_ia32_readahead		225
+#define __NR_ia32_setxattr		226
+#define __NR_ia32_lsetxattr		227
+#define __NR_ia32_fsetxattr		228
+#define __NR_ia32_getxattr		229
+#define __NR_ia32_lgetxattr		230
+#define __NR_ia32_fgetxattr		231
+#define __NR_ia32_listxattr		232
+#define __NR_ia32_llistxattr		233
+#define __NR_ia32_flistxattr		234
+#define __NR_ia32_removexattr	235
+#define __NR_ia32_lremovexattr	236
+#define __NR_ia32_fremovexattr	237
+#define __NR_ia32_tkill		238
+#define __NR_ia32_sendfile64		239
+#define __NR_ia32_futex		240
+#define __NR_ia32_sched_setaffinity	241
+#define __NR_ia32_sched_getaffinity	242
+#define __NR_ia32_set_thread_area   243
+#define __NR_ia32_get_thread_area	244
+#define __NR_ia32_io_setup		245
+#define __NR_ia32_io_destroy		246
+#define __NR_ia32_io_getevents	247
+#define __NR_ia32_io_submit		248
+#define __NR_ia32_io_cancel		249
+#define __NR_ia32_exit_group		252
+#define __NR_ia32_lookup_dcookie	253
+#define __NR_ia32_sys_epoll_create	254
+#define __NR_ia32_sys_epoll_ctl	255
+#define __NR_ia32_sys_epoll_wait	256
+#define __NR_ia32_remap_file_pages	257
+#define __NR_ia32_set_tid_address	258
+#define __NR_ia32_timer_create		259
+#define __NR_ia32_timer_settime	(__NR_ia32_timer_create+1)
+#define __NR_ia32_timer_gettime	(__NR_ia32_timer_create+2)
+#define __NR_ia32_timer_getoverrun	(__NR_ia32_timer_create+3)
+#define __NR_ia32_timer_delete	(__NR_ia32_timer_create+4)
+#define __NR_ia32_clock_settime	(__NR_ia32_timer_create+5)
+#define __NR_ia32_clock_gettime	(__NR_ia32_timer_create+6)
+#define __NR_ia32_clock_getres	(__NR_ia32_timer_create+7)
+#define __NR_ia32_clock_nanosleep	(__NR_ia32_timer_create+8)
+#define __NR_ia32_statfs64		268
+#define __NR_ia32_fstatfs64		269
+#define __NR_ia32_tgkill		270
+#define __NR_ia32_utimes		271
+#define __NR_ia32_fadvise64_64		272
+#define __NR_ia32_vserver		273
+#define __NR_ia32_mbind		274
+#define __NR_ia32_get_mempolicy	275
+#define __NR_ia32_set_mempolicy	276
+#define __NR_ia32_mq_open 		277
+#define __NR_ia32_mq_unlink		(__NR_ia32_mq_open+1)
+#define __NR_ia32_mq_timedsend	(__NR_ia32_mq_open+2)
+#define __NR_ia32_mq_timedreceive	(__NR_ia32_mq_open+3)
+#define __NR_ia32_mq_notify		(__NR_ia32_mq_open+4)
+#define __NR_ia32_mq_getsetattr	(__NR_ia32_mq_open+5)
+#define __NR_ia32_kexec		283
+#define __NR_ia32_waitid		284
+/* #define __NR_sys_setaltroot	285 */
+#define __NR_ia32_add_key		286
+#define __NR_ia32_request_key	287
+#define __NR_ia32_keyctl		288
+
+#define IA32_NR_syscalls 290	/* must be > than biggest syscall! */
+
+#endif /* _ASM_X86_64_IA32_UNISTD_H_ */
diff --git a/include/asm-x86_64/ide.h b/include/asm-x86_64/ide.h
new file mode 100644
index 000000000000..4cef0ef61878
--- /dev/null
+++ b/include/asm-x86_64/ide.h
@@ -0,0 +1 @@
+#include <asm-i386/ide.h>
diff --git a/include/asm-x86_64/io.h b/include/asm-x86_64/io.h
new file mode 100644
index 000000000000..94202703fae2
--- /dev/null
+++ b/include/asm-x86_64/io.h
@@ -0,0 +1,341 @@
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+#include <linux/config.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) \
+extern 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) \
+extern 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) \
+extern 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) \
+extern 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__) && __x86_64__
+
+#include <linux/vmalloc.h>
+
+#ifndef __i386__
+/*
+ * Change virtual addresses to physical addresses and vv.
+ * These are pretty trivial
+ */
+extern inline unsigned long virt_to_phys(volatile void * address)
+{
+	return __pa(address);
+}
+
+extern inline void * phys_to_virt(unsigned long address)
+{
+	return __va(address);
+}
+#endif
+
+/*
+ * Change "struct page" to physical address.
+ */
+#ifdef CONFIG_DISCONTIGMEM
+#include <asm/mmzone.h>
+#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+#else
+#define page_to_phys(page)	((page - mem_map) << PAGE_SHIFT)
+#endif
+
+#include <asm-generic/iomap.h>
+
+extern void __iomem *__ioremap(unsigned long offset, unsigned long size, unsigned long flags);
+
+extern inline void __iomem * ioremap (unsigned long offset, unsigned long size)
+{
+	return __ioremap(offset, size, 0);
+}
+
+/*
+ * 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);
+
+/*
+ * 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 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()
+
+#ifdef CONFIG_UNORDERED_IO
+static inline void __writel(__u32 val, volatile void __iomem *addr)
+{
+	volatile __u32 __iomem *target = addr;
+	asm volatile("movnti %1,%0"
+		     : "=m" (*target)
+		     : "r" (val) : "memory");
+}
+
+static inline void __writeq(__u64 val, volatile void __iomem *addr)
+{
+	volatile __u64 __iomem *target = addr;
+	asm volatile("movnti %1,%0"
+		     : "=m" (*target)
+		     : "r" (val) : "memory");
+}
+#else
+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;
+}
+#endif
+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))
+
+#define isa_readb(a) readb(__ISA_IO_base + (a))
+#define isa_readw(a) readw(__ISA_IO_base + (a))
+#define isa_readl(a) readl(__ISA_IO_base + (a))
+#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
+#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
+#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
+#define isa_memset_io(a,b,c)		memset_io(__ISA_IO_base + (a),(b),(c))
+#define isa_memcpy_fromio(a,b,c)	memcpy_fromio((a),__ISA_IO_base + (b),(c))
+#define isa_memcpy_toio(a,b,c)		memcpy_toio(__ISA_IO_base + (a),(b),(c))
+
+
+/*
+ * Again, x86-64 does not require mem IO specific function.
+ */
+
+#define eth_io_copy_and_sum(a,b,c,d)		eth_copy_and_sum((a),(void *)(b),(c),(d))
+#define isa_eth_io_copy_and_sum(a,b,c,d)	eth_copy_and_sum((a),(void *)(__ISA_IO_base + (b)),(c),(d))
+
+/**
+ *	check_signature		-	find BIOS signatures
+ *	@io_addr: mmio address to check 
+ *	@signature:  signature block
+ *	@length: length of signature
+ *
+ *	Perform a signature comparison with the mmio address io_addr. This
+ *	address should have been obtained by ioremap.
+ *	Returns 1 on a match.
+ */
+ 
+static inline int check_signature(void __iomem *io_addr,
+	const unsigned char *signature, int length)
+{
+	int retval = 0;
+	do {
+		if (readb(io_addr) != *signature)
+			goto out;
+		io_addr++;
+		signature++;
+		length--;
+	} while (length);
+	retval = 1;
+out:
+	return retval;
+}
+
+/* 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_64/io_apic.h b/include/asm-x86_64/io_apic.h
new file mode 100644
index 000000000000..7efc932e8f0b
--- /dev/null
+++ b/include/asm-x86_64/io_apic.h
@@ -0,0 +1,221 @@
+#ifndef __ASM_IO_APIC_H
+#define __ASM_IO_APIC_H
+
+#include <linux/config.h>
+#include <asm/types.h>
+#include <asm/mpspec.h>
+
+/*
+ * Intel IO-APIC support for SMP and UP systems.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
+ */
+
+#ifdef CONFIG_X86_IO_APIC
+
+#ifdef CONFIG_PCI_MSI
+static inline int use_pci_vector(void)	{return 1;}
+static inline void disable_edge_ioapic_vector(unsigned int vector) { }
+static inline void mask_and_ack_level_ioapic_vector(unsigned int vector) { }
+static inline void end_edge_ioapic_vector (unsigned int vector) { }
+#define startup_level_ioapic	startup_level_ioapic_vector
+#define shutdown_level_ioapic	mask_IO_APIC_vector
+#define enable_level_ioapic	unmask_IO_APIC_vector
+#define disable_level_ioapic	mask_IO_APIC_vector
+#define mask_and_ack_level_ioapic mask_and_ack_level_ioapic_vector
+#define end_level_ioapic	end_level_ioapic_vector
+#define set_ioapic_affinity	set_ioapic_affinity_vector
+
+#define startup_edge_ioapic 	startup_edge_ioapic_vector
+#define shutdown_edge_ioapic 	disable_edge_ioapic_vector
+#define enable_edge_ioapic 	unmask_IO_APIC_vector
+#define disable_edge_ioapic 	disable_edge_ioapic_vector
+#define ack_edge_ioapic 	ack_edge_ioapic_vector
+#define end_edge_ioapic 	end_edge_ioapic_vector
+#else
+static inline int use_pci_vector(void)	{return 0;}
+static inline void disable_edge_ioapic_irq(unsigned int irq) { }
+static inline void mask_and_ack_level_ioapic_irq(unsigned int irq) { }
+static inline void end_edge_ioapic_irq (unsigned int irq) { }
+#define startup_level_ioapic	startup_level_ioapic_irq
+#define shutdown_level_ioapic	mask_IO_APIC_irq
+#define enable_level_ioapic	unmask_IO_APIC_irq
+#define disable_level_ioapic	mask_IO_APIC_irq
+#define mask_and_ack_level_ioapic mask_and_ack_level_ioapic_irq
+#define end_level_ioapic	end_level_ioapic_irq
+#define set_ioapic_affinity	set_ioapic_affinity_irq
+
+#define startup_edge_ioapic 	startup_edge_ioapic_irq
+#define shutdown_edge_ioapic 	disable_edge_ioapic_irq
+#define enable_edge_ioapic 	unmask_IO_APIC_irq
+#define disable_edge_ioapic 	disable_edge_ioapic_irq
+#define ack_edge_ioapic 	ack_edge_ioapic_irq
+#define end_edge_ioapic 	end_edge_ioapic_irq
+#endif
+
+#define APIC_MISMATCH_DEBUG
+
+#define IO_APIC_BASE(idx) \
+		((volatile int *)(__fix_to_virt(FIX_IO_APIC_BASE_0 + idx) \
+		+ (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK)))
+
+/*
+ * 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;
+
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+	*IO_APIC_BASE(apic) = reg;
+	return *(IO_APIC_BASE(apic)+4);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+	*IO_APIC_BASE(apic) = reg;
+	*(IO_APIC_BASE(apic)+4) = value;
+}
+
+/*
+ * Re-write a value: to be used for read-modify-write
+ * cycles where the read already set up the index register.
+ */
+static inline void io_apic_modify(unsigned int apic, unsigned int value)
+{
+	*(IO_APIC_BASE(apic)+4) = value;
+}
+
+/*
+ * Synchronize the IO-APIC and the CPU by doing
+ * a dummy read from the IO-APIC
+ */
+static inline void io_apic_sync(unsigned int apic)
+{
+	(void) *(IO_APIC_BASE(apic)+4);
+}
+
+/* 1 if "noapic" boot option passed */
+extern int 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_BOOT
+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, int);
+#endif
+
+extern int sis_apic_bug; /* dummy */ 
+
+#else  /* !CONFIG_X86_IO_APIC */
+#define io_apic_assign_pci_irqs 0
+#endif
+
+extern int assign_irq_vector(int irq);
+
+void enable_NMI_through_LVT0 (void * dummy);
+
+#endif
diff --git a/include/asm-x86_64/ioctl.h b/include/asm-x86_64/ioctl.h
new file mode 100644
index 000000000000..609b663b6bf4
--- /dev/null
+++ b/include/asm-x86_64/ioctl.h
@@ -0,0 +1,75 @@
+/* $Id: ioctl.h,v 1.2 2001/07/04 09:08:13 ak Exp $
+ *
+ * linux/ioctl.h for Linux by H.H. Bergman.
+ */
+
+#ifndef _ASMX8664_IOCTL_H
+#define _ASMX8664_IOCTL_H
+
+/* ioctl command encoding: 32 bits total, command in lower 16 bits,
+ * size of the parameter structure in the lower 14 bits of the
+ * upper 16 bits.
+ * Encoding the size of the parameter structure in the ioctl request
+ * is useful for catching programs compiled with old versions
+ * and to avoid overwriting user space outside the user buffer area.
+ * The highest 2 bits are reserved for indicating the ``access mode''.
+ * NOTE: This limits the max parameter size to 16kB -1 !
+ */
+
+/*
+ * The following is for compatibility across the various Linux
+ * platforms.  The i386 ioctl numbering scheme doesn't really enforce
+ * a type field.  De facto, however, the top 8 bits of the lower 16
+ * bits are indeed used as a type field, so we might just as well make
+ * this explicit here.  Please be sure to use the decoding macros
+ * below from now on.
+ */
+#define _IOC_NRBITS	8
+#define _IOC_TYPEBITS	8
+#define _IOC_SIZEBITS	14
+#define _IOC_DIRBITS	2
+
+#define _IOC_NRMASK	((1 << _IOC_NRBITS)-1)
+#define _IOC_TYPEMASK	((1 << _IOC_TYPEBITS)-1)
+#define _IOC_SIZEMASK	((1 << _IOC_SIZEBITS)-1)
+#define _IOC_DIRMASK	((1 << _IOC_DIRBITS)-1)
+
+#define _IOC_NRSHIFT	0
+#define _IOC_TYPESHIFT	(_IOC_NRSHIFT+_IOC_NRBITS)
+#define _IOC_SIZESHIFT	(_IOC_TYPESHIFT+_IOC_TYPEBITS)
+#define _IOC_DIRSHIFT	(_IOC_SIZESHIFT+_IOC_SIZEBITS)
+
+/*
+ * Direction bits.
+ */
+#define _IOC_NONE	0U
+#define _IOC_WRITE	1U
+#define _IOC_READ	2U
+
+#define _IOC(dir,type,nr,size) \
+	(((dir)  << _IOC_DIRSHIFT) | \
+	 ((type) << _IOC_TYPESHIFT) | \
+	 ((nr)   << _IOC_NRSHIFT) | \
+	 ((size) << _IOC_SIZESHIFT))
+
+/* used to create numbers */
+#define _IO(type,nr)		_IOC(_IOC_NONE,(type),(nr),0)
+#define _IOR(type,nr,size)	_IOC(_IOC_READ,(type),(nr),sizeof(size))
+#define _IOW(type,nr,size)	_IOC(_IOC_WRITE,(type),(nr),sizeof(size))
+#define _IOWR(type,nr,size)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(size))
+
+/* used to decode ioctl numbers.. */
+#define _IOC_DIR(nr)		(((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)
+#define _IOC_TYPE(nr)		(((nr) >> _IOC_TYPESHIFT) & _IOC_TYPEMASK)
+#define _IOC_NR(nr)		(((nr) >> _IOC_NRSHIFT) & _IOC_NRMASK)
+#define _IOC_SIZE(nr)		(((nr) >> _IOC_SIZESHIFT) & _IOC_SIZEMASK)
+
+/* ...and for the drivers/sound files... */
+
+#define IOC_IN		(_IOC_WRITE << _IOC_DIRSHIFT)
+#define IOC_OUT		(_IOC_READ << _IOC_DIRSHIFT)
+#define IOC_INOUT	((_IOC_WRITE|_IOC_READ) << _IOC_DIRSHIFT)
+#define IOCSIZE_MASK	(_IOC_SIZEMASK << _IOC_SIZESHIFT)
+#define IOCSIZE_SHIFT	(_IOC_SIZESHIFT)
+
+#endif /* _ASMX8664_IOCTL_H */
diff --git a/include/asm-x86_64/ioctl32.h b/include/asm-x86_64/ioctl32.h
new file mode 100644
index 000000000000..d0d227f45e05
--- /dev/null
+++ b/include/asm-x86_64/ioctl32.h
@@ -0,0 +1 @@
+#include <linux/ioctl32.h>
diff --git a/include/asm-x86_64/ioctls.h b/include/asm-x86_64/ioctls.h
new file mode 100644
index 000000000000..62caf8b6e4e1
--- /dev/null
+++ b/include/asm-x86_64/ioctls.h
@@ -0,0 +1,82 @@
+#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 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_64/ipcbuf.h b/include/asm-x86_64/ipcbuf.h
new file mode 100644
index 000000000000..470cf85e3ba8
--- /dev/null
+++ b/include/asm-x86_64/ipcbuf.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_64/ipi.h b/include/asm-x86_64/ipi.h
new file mode 100644
index 000000000000..d1841847ed89
--- /dev/null
+++ b/include/asm-x86_64/ipi.h
@@ -0,0 +1,113 @@
+#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/fixmap.h>
+#include <asm/hw_irq.h>
+#include <asm/apicdef.h>
+#include <asm/genapic.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 =  APIC_DM_FIXED | shortcut | vector | dest;
+	if (vector == KDB_VECTOR)
+		icr = (icr & (~APIC_VECTOR_MASK)) | APIC_DM_NMI;
+	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_around(APIC_ICR, cfg);
+}
+
+
+static inline void send_IPI_mask_sequence(cpumask_t mask, int vector)
+{
+	unsigned long cfg, 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 (query_cpu = 0; query_cpu < NR_CPUS; ++query_cpu) {
+		if (cpu_isset(query_cpu, mask)) {
+
+			/*
+			 * Wait for idle.
+			 */
+			apic_wait_icr_idle();
+
+			/*
+			 * prepare target chip field
+			 */
+			cfg = __prepare_ICR2(x86_cpu_to_apicid[query_cpu]);
+			apic_write_around(APIC_ICR2, cfg);
+
+			/*
+			 * program the ICR
+			 */
+			cfg = __prepare_ICR(0, vector, APIC_DEST_PHYSICAL);
+
+			/*
+			 * Send the IPI. The write to APIC_ICR fires this off.
+			 */
+			apic_write_around(APIC_ICR, cfg);
+		}
+	}
+	local_irq_restore(flags);
+}
+
+#endif /* __ASM_IPI_H */
diff --git a/include/asm-x86_64/irq.h b/include/asm-x86_64/irq.h
new file mode 100644
index 000000000000..3af50b3c3b05
--- /dev/null
+++ b/include/asm-x86_64/irq.h
@@ -0,0 +1,55 @@
+#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 */
+
+#ifdef CONFIG_PCI_MSI
+#define NR_IRQS FIRST_SYSTEM_VECTOR
+#define NR_IRQ_VECTORS NR_IRQS
+#else
+#define NR_IRQS 224
+#define NR_IRQ_VECTORS 1024
+#endif
+
+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
+
+struct irqaction;
+struct pt_regs;
+int handle_IRQ_event(unsigned int, struct pt_regs *, struct irqaction *);
+
+#endif /* _ASM_IRQ_H */
diff --git a/include/asm-x86_64/kdebug.h b/include/asm-x86_64/kdebug.h
new file mode 100644
index 000000000000..adb6f918d3ad
--- /dev/null
+++ b/include/asm-x86_64/kdebug.h
@@ -0,0 +1,53 @@
+#ifndef _X86_64_KDEBUG_H
+#define _X86_64_KDEBUG_H 1
+
+#include <linux/notifier.h>
+
+struct pt_regs;
+
+struct die_args { 
+	struct pt_regs *regs;
+	const char *str;
+	long err; 
+	int trapnr;
+	int signr;
+}; 
+
+/* Note - you should never unregister because that can race with NMIs.
+   If you really want to do it first unregister - then synchronize_kernel - then free. 
+  */
+int register_die_notifier(struct notifier_block *nb);
+extern struct notifier_block *die_chain;
+/* Grossly misnamed. */
+enum die_val { 
+	DIE_OOPS = 1,
+	DIE_INT3,
+	DIE_DEBUG,
+	DIE_DEBUGSTEP,
+	DIE_PANIC,
+	DIE_NMI,
+	DIE_DIE,
+	DIE_NMIWATCHDOG,
+	DIE_KERNELDEBUG,
+	DIE_TRAP,
+	DIE_GPF,
+	DIE_CALL,
+	DIE_NMI_IPI,
+	DIE_PAGE_FAULT,
+}; 
+	
+static inline int notify_die(enum die_val val,char *str,struct pt_regs *regs,long err,int trap, int sig)
+{ 
+	struct die_args args = { .regs=regs, .str=str, .err=err, .trapnr=trap,.signr=sig }; 
+	return notifier_call_chain(&die_chain, val, &args); 
+} 
+
+extern int 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 void oops_begin(void);
+extern void oops_end(void);
+
+#endif
diff --git a/include/asm-x86_64/kmap_types.h b/include/asm-x86_64/kmap_types.h
new file mode 100644
index 000000000000..7486338c6cea
--- /dev/null
+++ b/include/asm-x86_64/kmap_types.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_64/kprobes.h b/include/asm-x86_64/kprobes.h
new file mode 100644
index 000000000000..bfea52d516f8
--- /dev/null
+++ b/include/asm-x86_64/kprobes.h
@@ -0,0 +1,63 @@
+#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>
+
+struct pt_regs;
+
+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 JPROBE_ENTRY(pentry)	(kprobe_opcode_t *)pentry
+
+/* Architecture specific copy of original instruction*/
+struct arch_specific_insn {
+	/* copy of the original instruction */
+	kprobe_opcode_t *insn;
+};
+
+/* 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_64/ldt.h b/include/asm-x86_64/ldt.h
new file mode 100644
index 000000000000..9ef647b890d2
--- /dev/null
+++ b/include/asm-x86_64/ldt.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_64/linkage.h b/include/asm-x86_64/linkage.h
new file mode 100644
index 000000000000..291c2d01c44f
--- /dev/null
+++ b/include/asm-x86_64/linkage.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+/* Nothing to see here... */
+
+#endif
diff --git a/include/asm-x86_64/local.h b/include/asm-x86_64/local.h
new file mode 100644
index 000000000000..169c223a8452
--- /dev/null
+++ b/include/asm-x86_64/local.h
@@ -0,0 +1,73 @@
+#ifndef _ARCH_X8664_LOCAL_H
+#define _ARCH_X8664_LOCAL_H
+
+#include <linux/percpu.h>
+
+typedef struct
+{
+	volatile unsigned int counter;
+} local_t;
+
+#define LOCAL_INIT(i)	{ (i) }
+
+#define local_read(v)	((v)->counter)
+#define local_set(v,i)	(((v)->counter) = (i))
+
+static __inline__ void local_inc(local_t *v)
+{
+	__asm__ __volatile__(
+		"incl %0"
+		:"=m" (v->counter)
+		:"m" (v->counter));
+}
+
+static __inline__ void local_dec(local_t *v)
+{
+	__asm__ __volatile__(
+		"decl %0"
+		:"=m" (v->counter)
+		:"m" (v->counter));
+}
+
+static __inline__ void local_add(unsigned long i, local_t *v)
+{
+	__asm__ __volatile__(
+		"addl %1,%0"
+		:"=m" (v->counter)
+		:"ir" (i), "m" (v->counter));
+}
+
+static __inline__ void local_sub(unsigned long i, local_t *v)
+{
+	__asm__ __volatile__(
+		"subl %1,%0"
+		:"=m" (v->counter)
+		:"ir" (i), "m" (v->counter));
+}
+
+/* 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.
+ *
+ * This could be done better if we moved the per cpu data directly
+ * after GS.
+ */
+#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
+#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
+#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
+#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
+#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
+#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
+
+#define __cpu_local_inc(v)	cpu_local_inc(v)
+#define __cpu_local_dec(v)	cpu_local_dec(v)
+#define __cpu_local_add(i, v)	cpu_local_add((i), (v))
+#define __cpu_local_sub(i, v)	cpu_local_sub((i), (v))
+
+#endif /* _ARCH_I386_LOCAL_H */
diff --git a/include/asm-x86_64/mach_apic.h b/include/asm-x86_64/mach_apic.h
new file mode 100644
index 000000000000..0acea44c9377
--- /dev/null
+++ b/include/asm-x86_64/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 INT_DELIVERY_DEST (genapic->int_delivery_dest)
+#define TARGET_CPUS	  (genapic->target_cpus())
+#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_64/mc146818rtc.h b/include/asm-x86_64/mc146818rtc.h
new file mode 100644
index 000000000000..d6e3009430c1
--- /dev/null
+++ b/include/asm-x86_64/mc146818rtc.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_64/mce.h b/include/asm-x86_64/mce.h
new file mode 100644
index 000000000000..869249db6795
--- /dev/null
+++ b/include/asm-x86_64/mce.h
@@ -0,0 +1,80 @@
+#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
+
+void mce_log(struct mce *m);
+#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
+
+#endif
diff --git a/include/asm-x86_64/mman.h b/include/asm-x86_64/mman.h
new file mode 100644
index 000000000000..78e60a4fd4ee
--- /dev/null
+++ b/include/asm-x86_64/mman.h
@@ -0,0 +1,44 @@
+#ifndef __X8664_MMAN_H__
+#define __X8664_MMAN_H__
+
+#define PROT_READ	0x1		/* page can be read */
+#define PROT_WRITE	0x2		/* page can be written */
+#define PROT_EXEC	0x4		/* page can be executed */
+#define PROT_NONE	0x0		/* page can not be accessed */
+#define PROT_SEM	0x8
+#define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
+#define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
+
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_TYPE	0x0f		/* Mask for type of mapping */
+#define MAP_FIXED	0x10		/* Interpret addr exactly */
+#define MAP_ANONYMOUS	0x20		/* don't use a file */
+#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 MS_ASYNC	1		/* sync memory asynchronously */
+#define MS_INVALIDATE	2		/* invalidate the caches */
+#define MS_SYNC		4		/* synchronous memory sync */
+
+#define MCL_CURRENT	1		/* lock all current mappings */
+#define MCL_FUTURE	2		/* lock all future mappings */
+
+#define MADV_NORMAL	0x0		/* default page-in behavior */
+#define MADV_RANDOM	0x1		/* page-in minimum required */
+#define MADV_SEQUENTIAL	0x2		/* read-ahead aggressively */
+#define MADV_WILLNEED	0x3		/* pre-fault pages */
+#define MADV_DONTNEED	0x4		/* discard these pages */
+
+/* compatibility flags */
+#define MAP_ANON	MAP_ANONYMOUS
+#define MAP_FILE	0
+
+#endif
diff --git a/include/asm-x86_64/mmsegment.h b/include/asm-x86_64/mmsegment.h
new file mode 100644
index 000000000000..d3f80c996330
--- /dev/null
+++ b/include/asm-x86_64/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_64/mmu.h b/include/asm-x86_64/mmu.h
new file mode 100644
index 000000000000..5dc6ed79859a
--- /dev/null
+++ b/include/asm-x86_64/mmu.h
@@ -0,0 +1,20 @@
+#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; 
+} mm_context_t;
+
+#endif
diff --git a/include/asm-x86_64/mmu_context.h b/include/asm-x86_64/mmu_context.h
new file mode 100644
index 000000000000..b630d52bdfb1
--- /dev/null
+++ b/include/asm-x86_64/mmu_context.h
@@ -0,0 +1,79 @@
+#ifndef __X86_64_MMU_CONTEXT_H
+#define __X86_64_MMU_CONTEXT_H
+
+#include <linux/config.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>
+
+/*
+ * 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);
+
+#ifdef CONFIG_SMP
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	if (read_pda(mmu_state) == TLBSTATE_OK) 
+		write_pda(mmu_state, TLBSTATE_LAZY);
+}
+#else
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+}
+#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 */
+		clear_bit(cpu, &prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+		write_pda(mmu_state, TLBSTATE_OK);
+		write_pda(active_mm, next);
+#endif
+		set_bit(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(!test_and_set_bit(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_64/mmx.h b/include/asm-x86_64/mmx.h
new file mode 100644
index 000000000000..46b71da99869
--- /dev/null
+++ b/include/asm-x86_64/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_64/mmzone.h b/include/asm-x86_64/mmzone.h
new file mode 100644
index 000000000000..d95b7c240831
--- /dev/null
+++ b/include/asm-x86_64/mmzone.h
@@ -0,0 +1,63 @@
+/* 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
+
+#include <linux/config.h>
+
+#ifdef CONFIG_DISCONTIGMEM
+
+#define VIRTUAL_BUG_ON(x) 
+
+#include <asm/smp.h>
+
+#define NODEMAPSIZE 0xff
+
+/* Simple perfect hash to map physical addresses to node numbers */
+extern int memnode_shift; 
+extern u8  memnodemap[NODEMAPSIZE]; 
+extern int maxnode;
+
+extern struct pglist_data *node_data[];
+
+static inline __attribute__((pure)) int phys_to_nid(unsigned long addr) 
+{ 
+	int nid; 
+	VIRTUAL_BUG_ON((addr >> memnode_shift) >= NODEMAPSIZE);
+	nid = memnodemap[addr >> memnode_shift]; 
+	VIRTUAL_BUG_ON(nid > maxnode); 
+	return nid; 
+} 
+
+#define pfn_to_nid(pfn) phys_to_nid((unsigned long)(pfn) << PAGE_SHIFT)
+
+#define kvaddr_to_nid(kaddr)	phys_to_nid(__pa(kaddr))
+#define NODE_DATA(nid)		(node_data[nid])
+
+#define node_mem_map(nid)	(NODE_DATA(nid)->node_mem_map)
+
+#define node_mem_map(nid)	(NODE_DATA(nid)->node_mem_map)
+#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)
+
+#define local_mapnr(kvaddr) \
+	( (__pa(kvaddr) >> PAGE_SHIFT) - node_start_pfn(kvaddr_to_nid(kvaddr)) )
+
+/* AK: this currently doesn't deal with invalid addresses. We'll see 
+   if the 2.5 kernel doesn't pass them
+   (2.4 used to). */
+#define pfn_to_page(pfn) ({ \
+	int nid = phys_to_nid(((unsigned long)(pfn)) << PAGE_SHIFT); 	\
+	((pfn) - node_start_pfn(nid)) + node_mem_map(nid);		\
+})
+
+#define page_to_pfn(page) \
+	(long)(((page) - page_zone(page)->zone_mem_map) + page_zone(page)->zone_start_pfn)
+
+#define pfn_valid(pfn) ((pfn) >= num_physpages ? 0 : \
+			({ u8 nid__ = pfn_to_nid(pfn); \
+			   nid__ != 0xff && (pfn) >= node_start_pfn(nid__) && (pfn) <= node_end_pfn(nid__); }))
+#endif
+#endif
diff --git a/include/asm-x86_64/module.h b/include/asm-x86_64/module.h
new file mode 100644
index 000000000000..67f8f69fa7b1
--- /dev/null
+++ b/include/asm-x86_64/module.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_64/mpspec.h b/include/asm-x86_64/mpspec.h
new file mode 100644
index 000000000000..331f6a3c72a2
--- /dev/null
+++ b/include/asm-x86_64/mpspec.h
@@ -0,0 +1,241 @@
+#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 128
+
+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] __attribute((packed));
+};
+
+/* 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
+#define MAX_IRQ_SOURCES 256
+enum mp_bustype {
+	MP_BUS_ISA = 1,
+	MP_BUS_EISA,
+	MP_BUS_PCI,
+	MP_BUS_MCA
+};
+extern unsigned char mp_bus_id_to_type [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 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_BOOT
+extern void mp_register_lapic (u8 id, u8 enabled);
+extern void mp_register_lapic_address (u64 address);
+
+#ifdef CONFIG_X86_IO_APIC
+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_X86_IO_APIC*/
+#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_64/msgbuf.h b/include/asm-x86_64/msgbuf.h
new file mode 100644
index 000000000000..cd6f95dd54da
--- /dev/null
+++ b/include/asm-x86_64/msgbuf.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_64/msi.h b/include/asm-x86_64/msi.h
new file mode 100644
index 000000000000..85c427e472bf
--- /dev/null
+++ b/include/asm-x86_64/msi.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2003-2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#ifndef ASM_MSI_H
+#define ASM_MSI_H
+
+#include <asm/desc.h>
+#include <asm/mach_apic.h>
+#include <asm/smp.h>
+
+#define LAST_DEVICE_VECTOR		232
+#define MSI_DEST_MODE			MSI_LOGICAL_MODE
+#define MSI_TARGET_CPU_SHIFT		12
+#define MSI_TARGET_CPU			logical_smp_processor_id()
+
+#endif /* ASM_MSI_H */
diff --git a/include/asm-x86_64/msr.h b/include/asm-x86_64/msr.h
new file mode 100644
index 000000000000..66f0be191ab4
--- /dev/null
+++ b/include/asm-x86_64/msr.h
@@ -0,0 +1,387 @@
+#ifndef X86_64_MSR_H
+#define X86_64_MSR_H 1
+
+#ifndef __ASSEMBLY__
+/*
+ * 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 rdtsc(low,high) \
+     __asm__ __volatile__("rdtsc" : "=a" (low), "=d" (high))
+
+#define rdtscl(low) \
+     __asm__ __volatile__ ("rdtsc" : "=a" (low) : : "edx")
+
+#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 rdpmc(counter,low,high) \
+     __asm__ __volatile__("rdpmc" \
+			  : "=a" (low), "=d" (high) \
+			  : "c" (counter))
+
+#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
+
+#define rdpmc(counter,low,high) \
+     __asm__ __volatile__("rdpmc" \
+			  : "=a" (low), "=d" (high) \
+			  : "c" (counter))
+
+extern 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
+ */
+extern inline unsigned int cpuid_eax(unsigned int op)
+{
+	unsigned int eax;
+
+	__asm__("cpuid"
+		: "=a" (eax)
+		: "0" (op)
+		: "bx", "cx", "dx");
+	return eax;
+}
+extern inline unsigned int cpuid_ebx(unsigned int op)
+{
+	unsigned int eax, ebx;
+
+	__asm__("cpuid"
+		: "=a" (eax), "=b" (ebx)
+		: "0" (op)
+		: "cx", "dx" );
+	return ebx;
+}
+extern inline unsigned int cpuid_ecx(unsigned int op)
+{
+	unsigned int eax, ecx;
+
+	__asm__("cpuid"
+		: "=a" (eax), "=c" (ecx)
+		: "0" (op)
+		: "bx", "dx" );
+	return ecx;
+}
+extern inline unsigned int cpuid_edx(unsigned int op)
+{
+	unsigned int eax, edx;
+
+	__asm__("cpuid"
+		: "=a" (eax), "=d" (edx)
+		: "0" (op)
+		: "bx", "cx");
+	return edx;
+}
+
+#define MSR_IA32_UCODE_WRITE		0x79
+#define MSR_IA32_UCODE_REV		0x8b
+
+
+#endif
+
+/* AMD/K8 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		/* compatibility mode SYSCALL target */
+#define MSR_SYSCALL_MASK 0xc0000084	/* EFLAGS mask for syscall */
+#define MSR_FS_BASE 0xc0000100		/* 64bit GS base */
+#define MSR_GS_BASE 0xc0000101		/* 64bit FS base */
+#define MSR_KERNEL_GS_BASE  0xc0000102	/* SwapGS GS shadow (or USER_GS from kernel) */ 
+/* 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_PLATFORM_ID	0x17
+
+#define MSR_IA32_PERFCTR0      0xc1
+#define MSR_IA32_PERFCTR1      0xc2
+
+#define MSR_MTRRcap		0x0fe
+#define MSR_IA32_BBL_CR_CTL        0x119
+
+#define MSR_IA32_SYSENTER_CS	0x174
+#define MSR_IA32_SYSENTER_ESP	0x175
+#define MSR_IA32_SYSENTER_EIP	0x176
+
+#define MSR_IA32_MCG_CAP       0x179
+#define MSR_IA32_MCG_STATUS        0x17a
+#define MSR_IA32_MCG_CTL       0x17b
+
+#define MSR_IA32_EVNTSEL0      0x186
+#define MSR_IA32_EVNTSEL1      0x187
+
+#define MSR_IA32_DEBUGCTLMSR       0x1d9
+#define MSR_IA32_LASTBRANCHFROMIP  0x1db
+#define MSR_IA32_LASTBRANCHTOIP        0x1dc
+#define MSR_IA32_LASTINTFROMIP     0x1dd
+#define MSR_IA32_LASTINTTOIP       0x1de
+
+#define MSR_MTRRfix64K_00000	0x250
+#define MSR_MTRRfix16K_80000	0x258
+#define MSR_MTRRfix16K_A0000	0x259
+#define MSR_MTRRfix4K_C0000	0x268
+#define MSR_MTRRfix4K_C8000	0x269
+#define MSR_MTRRfix4K_D0000	0x26a
+#define MSR_MTRRfix4K_D8000	0x26b
+#define MSR_MTRRfix4K_E0000	0x26c
+#define MSR_MTRRfix4K_E8000	0x26d
+#define MSR_MTRRfix4K_F0000	0x26e
+#define MSR_MTRRfix4K_F8000	0x26f
+#define MSR_MTRRdefType		0x2ff
+
+#define MSR_IA32_MC0_CTL       0x400
+#define MSR_IA32_MC0_STATUS        0x401
+#define MSR_IA32_MC0_ADDR      0x402
+#define MSR_IA32_MC0_MISC      0x403
+
+#define MSR_P6_PERFCTR0			0xc1
+#define MSR_P6_PERFCTR1			0xc2
+#define MSR_P6_EVNTSEL0			0x186
+#define MSR_P6_EVNTSEL1			0x187
+
+/* 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_K8_TOP_MEM2		   0xC001001D
+#define MSR_K8_SYSCFG		   0xC0000010	
+
+/* 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_PSOR			0xC0000087
+#define MSR_K6_PFIR			0xC0000088
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1			0x107
+#define MSR_IDT_FCR2			0x108
+#define MSR_IDT_FCR3			0x109
+#define MSR_IDT_FCR4			0x10a
+
+#define MSR_IDT_MCR0			0x110
+#define MSR_IDT_MCR1			0x111
+#define MSR_IDT_MCR2			0x112
+#define MSR_IDT_MCR3			0x113
+#define MSR_IDT_MCR4			0x114
+#define MSR_IDT_MCR5			0x115
+#define MSR_IDT_MCR6			0x116
+#define MSR_IDT_MCR7			0x117
+#define MSR_IDT_MCR_CTRL		0x120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR			0x1107
+#define MSR_VIA_LONGHAUL		0x110a
+#define MSR_VIA_RNG			0x110b
+#define MSR_VIA_BCR2			0x1147
+
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR		0
+#define MSR_IA32_P5_MC_TYPE		1
+#define MSR_IA32_PLATFORM_ID		0x17
+#define MSR_IA32_EBL_CR_POWERON		0x2a
+
+#define MSR_IA32_APICBASE               0x1b
+#define MSR_IA32_APICBASE_BSP           (1<<8)
+#define MSR_IA32_APICBASE_ENABLE        (1<<11)
+#define MSR_IA32_APICBASE_BASE          (0xfffff<<12)
+
+/* P4/Xeon+ specific */
+#define MSR_IA32_MCG_EAX		0x180
+#define MSR_IA32_MCG_EBX		0x181
+#define MSR_IA32_MCG_ECX		0x182
+#define MSR_IA32_MCG_EDX		0x183
+#define MSR_IA32_MCG_ESI		0x184
+#define MSR_IA32_MCG_EDI		0x185
+#define MSR_IA32_MCG_EBP		0x186
+#define MSR_IA32_MCG_ESP		0x187
+#define MSR_IA32_MCG_EFLAGS		0x188
+#define MSR_IA32_MCG_EIP		0x189
+#define MSR_IA32_MCG_RESERVED		0x18A
+
+#define MSR_P6_EVNTSEL0			0x186
+#define MSR_P6_EVNTSEL1			0x187
+
+#define MSR_IA32_PERF_STATUS		0x198
+#define MSR_IA32_PERF_CTL		0x199
+
+#define MSR_IA32_THERM_CONTROL		0x19a
+#define MSR_IA32_THERM_INTERRUPT	0x19b
+#define MSR_IA32_THERM_STATUS		0x19c
+#define MSR_IA32_MISC_ENABLE		0x1a0
+
+#define MSR_IA32_DEBUGCTLMSR		0x1d9
+#define MSR_IA32_LASTBRANCHFROMIP	0x1db
+#define MSR_IA32_LASTBRANCHTOIP		0x1dc
+#define MSR_IA32_LASTINTFROMIP		0x1dd
+#define MSR_IA32_LASTINTTOIP		0x1de
+
+#define MSR_IA32_MC0_CTL		0x400
+#define MSR_IA32_MC0_STATUS		0x401
+#define MSR_IA32_MC0_ADDR		0x402
+#define MSR_IA32_MC0_MISC		0x403
+
+/* Pentium IV performance counter MSRs */
+#define MSR_P4_BPU_PERFCTR0 		0x300
+#define MSR_P4_BPU_PERFCTR1 		0x301
+#define MSR_P4_BPU_PERFCTR2 		0x302
+#define MSR_P4_BPU_PERFCTR3 		0x303
+#define MSR_P4_MS_PERFCTR0 		0x304
+#define MSR_P4_MS_PERFCTR1 		0x305
+#define MSR_P4_MS_PERFCTR2 		0x306
+#define MSR_P4_MS_PERFCTR3 		0x307
+#define MSR_P4_FLAME_PERFCTR0 		0x308
+#define MSR_P4_FLAME_PERFCTR1 		0x309
+#define MSR_P4_FLAME_PERFCTR2 		0x30a
+#define MSR_P4_FLAME_PERFCTR3 		0x30b
+#define MSR_P4_IQ_PERFCTR0 		0x30c
+#define MSR_P4_IQ_PERFCTR1 		0x30d
+#define MSR_P4_IQ_PERFCTR2 		0x30e
+#define MSR_P4_IQ_PERFCTR3 		0x30f
+#define MSR_P4_IQ_PERFCTR4 		0x310
+#define MSR_P4_IQ_PERFCTR5 		0x311
+#define MSR_P4_BPU_CCCR0 		0x360
+#define MSR_P4_BPU_CCCR1 		0x361
+#define MSR_P4_BPU_CCCR2 		0x362
+#define MSR_P4_BPU_CCCR3 		0x363
+#define MSR_P4_MS_CCCR0 		0x364
+#define MSR_P4_MS_CCCR1 		0x365
+#define MSR_P4_MS_CCCR2 		0x366
+#define MSR_P4_MS_CCCR3 		0x367
+#define MSR_P4_FLAME_CCCR0 		0x368
+#define MSR_P4_FLAME_CCCR1 		0x369
+#define MSR_P4_FLAME_CCCR2 		0x36a
+#define MSR_P4_FLAME_CCCR3 		0x36b
+#define MSR_P4_IQ_CCCR0 		0x36c
+#define MSR_P4_IQ_CCCR1 		0x36d
+#define MSR_P4_IQ_CCCR2 		0x36e
+#define MSR_P4_IQ_CCCR3 		0x36f
+#define MSR_P4_IQ_CCCR4 		0x370
+#define MSR_P4_IQ_CCCR5 		0x371
+#define MSR_P4_ALF_ESCR0 		0x3ca
+#define MSR_P4_ALF_ESCR1 		0x3cb
+#define MSR_P4_BPU_ESCR0 		0x3b2
+#define MSR_P4_BPU_ESCR1 		0x3b3
+#define MSR_P4_BSU_ESCR0 		0x3a0
+#define MSR_P4_BSU_ESCR1 		0x3a1
+#define MSR_P4_CRU_ESCR0 		0x3b8
+#define MSR_P4_CRU_ESCR1 		0x3b9
+#define MSR_P4_CRU_ESCR2 		0x3cc
+#define MSR_P4_CRU_ESCR3 		0x3cd
+#define MSR_P4_CRU_ESCR4 		0x3e0
+#define MSR_P4_CRU_ESCR5 		0x3e1
+#define MSR_P4_DAC_ESCR0 		0x3a8
+#define MSR_P4_DAC_ESCR1 		0x3a9
+#define MSR_P4_FIRM_ESCR0 		0x3a4
+#define MSR_P4_FIRM_ESCR1 		0x3a5
+#define MSR_P4_FLAME_ESCR0 		0x3a6
+#define MSR_P4_FLAME_ESCR1 		0x3a7
+#define MSR_P4_FSB_ESCR0 		0x3a2
+#define MSR_P4_FSB_ESCR1 		0x3a3
+#define MSR_P4_IQ_ESCR0 		0x3ba
+#define MSR_P4_IQ_ESCR1 		0x3bb
+#define MSR_P4_IS_ESCR0 		0x3b4
+#define MSR_P4_IS_ESCR1 		0x3b5
+#define MSR_P4_ITLB_ESCR0 		0x3b6
+#define MSR_P4_ITLB_ESCR1 		0x3b7
+#define MSR_P4_IX_ESCR0 		0x3c8
+#define MSR_P4_IX_ESCR1 		0x3c9
+#define MSR_P4_MOB_ESCR0 		0x3aa
+#define MSR_P4_MOB_ESCR1 		0x3ab
+#define MSR_P4_MS_ESCR0 		0x3c0
+#define MSR_P4_MS_ESCR1 		0x3c1
+#define MSR_P4_PMH_ESCR0 		0x3ac
+#define MSR_P4_PMH_ESCR1 		0x3ad
+#define MSR_P4_RAT_ESCR0 		0x3bc
+#define MSR_P4_RAT_ESCR1 		0x3bd
+#define MSR_P4_SAAT_ESCR0 		0x3ae
+#define MSR_P4_SAAT_ESCR1 		0x3af
+#define MSR_P4_SSU_ESCR0 		0x3be
+#define MSR_P4_SSU_ESCR1 		0x3bf    /* guess: not defined in manual */
+#define MSR_P4_TBPU_ESCR0 		0x3c2
+#define MSR_P4_TBPU_ESCR1 		0x3c3
+#define MSR_P4_TC_ESCR0 		0x3c4
+#define MSR_P4_TC_ESCR1 		0x3c5
+#define MSR_P4_U2L_ESCR0 		0x3b0
+#define MSR_P4_U2L_ESCR1 		0x3b1
+
+#endif
diff --git a/include/asm-x86_64/mtrr.h b/include/asm-x86_64/mtrr.h
new file mode 100644
index 000000000000..c5959d6418bb
--- /dev/null
+++ b/include/asm-x86_64/mtrr.h
@@ -0,0 +1,108 @@
+/*  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/config.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
+
+#endif
+
+#endif  /*  _LINUX_MTRR_H  */
diff --git a/include/asm-x86_64/namei.h b/include/asm-x86_64/namei.h
new file mode 100644
index 000000000000..bef239f5318f
--- /dev/null
+++ b/include/asm-x86_64/namei.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_64/nmi.h b/include/asm-x86_64/nmi.h
new file mode 100644
index 000000000000..21d56b086b9d
--- /dev/null
+++ b/include/asm-x86_64/nmi.h
@@ -0,0 +1,57 @@
+/*
+ *  linux/include/asm-i386/nmi.h
+ */
+#ifndef ASM_NMI_H
+#define ASM_NMI_H
+
+#include <linux/pm.h>
+ 
+struct pt_regs;
+ 
+typedef int (*nmi_callback_t)(struct pt_regs * regs, int cpu);
+ 
+/** 
+ * set_nmi_callback
+ *
+ * Set a handler for an NMI. Only one handler may be
+ * set. Return 1 if the NMI was handled.
+ */
+void set_nmi_callback(nmi_callback_t callback);
+ 
+/** 
+ * unset_nmi_callback
+ *
+ * Remove the handler previously set.
+ */
+void unset_nmi_callback(void);
+ 
+#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);
+
+#define get_nmi_reason() inb(0x61)
+
+extern int panic_on_timeout;
+extern int unknown_nmi_panic;
+ 
+#endif /* ASM_NMI_H */
diff --git a/include/asm-x86_64/node.h b/include/asm-x86_64/node.h
new file mode 100644
index 000000000000..0ee6f88db048
--- /dev/null
+++ b/include/asm-x86_64/node.h
@@ -0,0 +1 @@
+#include <asm-i386/node.h>
diff --git a/include/asm-x86_64/numa.h b/include/asm-x86_64/numa.h
new file mode 100644
index 000000000000..5c363a1482e4
--- /dev/null
+++ b/include/asm-x86_64/numa.h
@@ -0,0 +1,21 @@
+#ifndef _ASM_X8664_NUMA_H 
+#define _ASM_X8664_NUMA_H 1
+
+#include <linux/nodemask.h>
+#include <asm/numnodes.h>
+
+struct node { 
+	u64 start,end; 
+};
+
+extern int compute_hash_shift(struct node *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;
+
+#define NUMA_NO_NODE 0xff
+
+#endif
diff --git a/include/asm-x86_64/numnodes.h b/include/asm-x86_64/numnodes.h
new file mode 100644
index 000000000000..32be16b8ae96
--- /dev/null
+++ b/include/asm-x86_64/numnodes.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X8664_NUMNODES_H
+#define _ASM_X8664_NUMNODES_H 1
+
+#include <linux/config.h>
+
+#ifdef CONFIG_NUMA
+#define NODES_SHIFT	6
+#else
+#define NODES_SHIFT	0
+#endif
+
+#endif
diff --git a/include/asm-x86_64/page.h b/include/asm-x86_64/page.h
new file mode 100644
index 000000000000..f43048035a03
--- /dev/null
+++ b/include/asm-x86_64/page.h
@@ -0,0 +1,139 @@
+#ifndef _X86_64_PAGE_H
+#define _X86_64_PAGE_H
+
+#include <linux/config.h>
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT	12
+#ifdef __ASSEMBLY__
+#define PAGE_SIZE	(0x1 << PAGE_SHIFT)
+#else
+#define PAGE_SIZE	(1UL << PAGE_SHIFT)
+#endif
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+#define PHYSICAL_PAGE_MASK	(~(PAGE_SIZE-1) & (__PHYSICAL_MASK << PAGE_SHIFT))
+
+#define THREAD_ORDER 1 
+#ifdef __ASSEMBLY__
+#define THREAD_SIZE  (1 << (PAGE_SHIFT + THREAD_ORDER))
+#else
+#define THREAD_SIZE  (1UL << (PAGE_SHIFT + THREAD_ORDER))
+#endif
+#define CURRENT_MASK (~(THREAD_SIZE-1))
+
+#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1))
+#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT)
+
+#define HPAGE_SHIFT PMD_SHIFT
+#define HPAGE_SIZE	((1UL) << HPAGE_SHIFT)
+#define HPAGE_MASK	(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+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(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, 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;
+
+#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) } )
+
+#define __START_KERNEL		0xffffffff80100000UL
+#define __START_KERNEL_map	0xffffffff80000000UL
+#define __PAGE_OFFSET           0xffff810000000000UL
+
+#else
+#define __START_KERNEL		0xffffffff80100000
+#define __START_KERNEL_map	0xffffffff80000000
+#define __PAGE_OFFSET           0xffff810000000000
+#endif /* !__ASSEMBLY__ */
+
+/* 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		((1UL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __VIRTUAL_MASK_SHIFT	48
+#define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
+
+#define KERNEL_TEXT_SIZE  (40UL*1024*1024)
+#define KERNEL_TEXT_START 0xffffffff80000000UL 
+
+#ifndef __ASSEMBLY__
+
+#include <asm/bug.h>
+
+/* Pure 2^n version of get_order */
+extern __inline__ int get_order(unsigned long size)
+{
+	int order;
+
+	size = (size-1) >> (PAGE_SHIFT-1);
+	order = -1;
+	do {
+		size >>= 1;
+		order++;
+	} while (size);
+	return order;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
+
+/* Note: __pa(&symbol_visible_to_c) should be always replaced with __pa_symbol.
+   Otherwise you risk miscompilation. */ 
+#define __pa(x)			(((unsigned long)(x)>=__START_KERNEL_map)?(unsigned long)(x) - (unsigned long)__START_KERNEL_map:(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)		\
+	({unsigned long v;  \
+	  asm("" : "=r" (v) : "0" (x)); \
+	  __pa(v); })
+
+#define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
+#ifndef CONFIG_DISCONTIGMEM
+#define pfn_to_page(pfn)	(mem_map + (pfn))
+#define page_to_pfn(page)	((unsigned long)((page) - mem_map))
+#define pfn_valid(pfn)		((pfn) < max_mapnr)
+#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	
+
+#endif /* __KERNEL__ */
+
+#endif /* _X86_64_PAGE_H */
diff --git a/include/asm-x86_64/param.h b/include/asm-x86_64/param.h
new file mode 100644
index 000000000000..b707f0568c9e
--- /dev/null
+++ b/include/asm-x86_64/param.h
@@ -0,0 +1,22 @@
+#ifndef _ASMx86_64_PARAM_H
+#define _ASMx86_64_PARAM_H
+
+#ifdef __KERNEL__
+# define HZ            1000            /* 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_64/parport.h b/include/asm-x86_64/parport.h
new file mode 100644
index 000000000000..7135ef977c96
--- /dev/null
+++ b/include/asm-x86_64/parport.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_64/pci-direct.h b/include/asm-x86_64/pci-direct.h
new file mode 100644
index 000000000000..036b6ca5b53b
--- /dev/null
+++ b/include/asm-x86_64/pci-direct.h
@@ -0,0 +1,48 @@
+#ifndef ASM_PCI_DIRECT_H
+#define ASM_PCI_DIRECT_H 1
+
+#include <linux/types.h>
+#include <asm/io.h>
+
+/* Direct PCI access. This is used for PCI accesses in early boot before
+   the PCI subsystem works. */ 
+
+#define PDprintk(x...)
+
+static inline u32 read_pci_config(u8 bus, u8 slot, u8 func, u8 offset)
+{
+	u32 v; 
+	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+	v = inl(0xcfc); 
+	if (v != 0xffffffff)
+		PDprintk("%x reading 4 from %x: %x\n", slot, offset, v);
+	return v;
+}
+
+static inline u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset)
+{
+	u8 v; 
+	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+	v = inb(0xcfc + (offset&3)); 
+	PDprintk("%x reading 1 from %x: %x\n", slot, offset, v);
+	return v;
+}
+
+static inline u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset)
+{
+	u16 v; 
+	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+	v = inw(0xcfc + (offset&2)); 
+	PDprintk("%x reading 2 from %x: %x\n", slot, offset, v);
+	return v;
+}
+
+static inline void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset,
+				    u32 val)
+{
+	PDprintk("%x writing to %x: %x\n", slot, offset, val); 
+	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+	outl(val, 0xcfc); 
+}
+
+#endif
diff --git a/include/asm-x86_64/pci.h b/include/asm-x86_64/pci.h
new file mode 100644
index 000000000000..8712520ca47f
--- /dev/null
+++ b/include/asm-x86_64/pci.h
@@ -0,0 +1,141 @@
+#ifndef __x8664_PCI_H
+#define __x8664_PCI_H
+
+#include <linux/config.h>
+#include <asm/io.h>
+
+#ifdef __KERNEL__
+
+#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 int no_iommu, force_iommu;
+
+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);
+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 int iommu_setup(char *opt);
+
+#ifdef CONFIG_GART_IOMMU
+/* 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 to tell some subsystems
+ * that an IOMMU is available.
+ */
+#define PCI_DMA_BUS_IS_PHYS	(no_iommu ? 1 : 0)
+
+/*
+ * x86-64 always supports DAC, but sometimes it is useful to force
+ * devices through the IOMMU to get automatic sg list merging.
+ * Optional right now.
+ */
+extern int iommu_sac_force;
+#define pci_dac_dma_supported(pci_dev, mask)	(!iommu_sac_force)
+
+#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 PCI_DMA_BUS_IS_PHYS	1
+#define pci_dac_dma_supported(pci_dev, mask)    1
+
+#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>
+
+static inline dma64_addr_t
+pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, unsigned long offset, int direction)
+{
+	return ((dma64_addr_t) page_to_phys(page) +
+		(dma64_addr_t) offset);
+}
+
+static inline struct page *
+pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr)
+{
+	return virt_to_page(__va(dma_addr)); 	
+}
+
+static inline unsigned long
+pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr)
+{
+	return (dma_addr & ~PAGE_MASK);
+}
+
+static inline void
+pci_dac_dma_sync_single_for_cpu(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction)
+{
+}
+
+static inline void
+pci_dac_dma_sync_single_for_device(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction)
+{
+	flush_write_buffers();
+}
+
+#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);
+
+static inline void pcibios_add_platform_entries(struct pci_dev *dev)
+{
+}
+
+#endif /* __KERNEL__ */
+
+/* generic pci stuff */
+#ifdef CONFIG_PCI
+#include <asm-generic/pci.h>
+#endif
+
+#endif /* __x8664_PCI_H */
diff --git a/include/asm-x86_64/pda.h b/include/asm-x86_64/pda.h
new file mode 100644
index 000000000000..36b766cfc4d5
--- /dev/null
+++ b/include/asm-x86_64/pda.h
@@ -0,0 +1,83 @@
+#ifndef X86_64_PDA_H
+#define X86_64_PDA_H
+
+#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/cache.h>
+
+/* Per processor datastructure. %gs points to it while the kernel runs */ 
+struct x8664_pda {
+	struct task_struct *pcurrent;	/* Current process */
+	unsigned long data_offset;	/* Per cpu data offset from linker address */
+	struct x8664_pda *me;	    /* Pointer to itself */  
+	unsigned long kernelstack;  /* top of kernel stack for current */ 
+	unsigned long oldrsp; 	    /* user rsp for system call */
+	unsigned long irqrsp;	    /* Old rsp for interrupts. */ 
+        int irqcount;		    /* Irq nesting counter. Starts with -1 */  	
+	int cpunumber;		    /* Logical CPU number */
+	char *irqstackptr;	/* top of irqstack */
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;	/* number of NMI on this CPUs */
+	struct mm_struct *active_mm;
+	int mmu_state;     
+	unsigned apic_timer_irqs;
+} ____cacheline_aligned;
+
+
+#define IRQSTACK_ORDER 2
+#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER) 
+
+extern struct x8664_pda cpu_pda[];
+
+/* 
+ * 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.
+ */ 
+#define sizeof_field(type,field)  (sizeof(((type *)0)->field))
+#define typeof_field(type,field)  typeof(((type *)0)->field)
+
+extern void __bad_pda_field(void);
+
+#define pda_offset(field) offsetof(struct x8664_pda, field)
+
+#define pda_to_op(op,field,val) do { \
+       switch (sizeof_field(struct x8664_pda, field)) { 		\
+case 2: \
+asm volatile(op "w %0,%%gs:%P1"::"r" (val),"i"(pda_offset(field)):"memory"); break; \
+case 4: \
+asm volatile(op "l %0,%%gs:%P1"::"r" (val),"i"(pda_offset(field)):"memory"); break; \
+case 8: \
+asm volatile(op "q %0,%%gs:%P1"::"r" (val),"i"(pda_offset(field)):"memory"); break; \
+       default: __bad_pda_field(); 					\
+       } \
+       } while (0)
+
+/* 
+ * AK: PDA read accesses should be neither volatile nor have an memory clobber.
+ * Unfortunately removing them causes all hell to break lose currently.
+ */
+#define pda_from_op(op,field) ({ \
+       typedef typeof_field(struct x8664_pda, field) T__; T__ ret__; \
+       switch (sizeof_field(struct x8664_pda, field)) { 		\
+case 2: \
+asm volatile(op "w %%gs:%P1,%0":"=r" (ret__):"i"(pda_offset(field)):"memory"); break;\
+case 4: \
+asm volatile(op "l %%gs:%P1,%0":"=r" (ret__):"i"(pda_offset(field)):"memory"); break;\
+case 8: \
+asm volatile(op "q %%gs:%P1,%0":"=r" (ret__):"i"(pda_offset(field)):"memory"); 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)
+
+#endif
+
+#define PDA_STACKOFFSET (5*8)
+
+#endif
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
new file mode 100644
index 000000000000..415d73f3c8ef
--- /dev/null
+++ b/include/asm-x86_64/percpu.h
@@ -0,0 +1,52 @@
+#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)
+
+/* Separate out the type, so (int[3], foo) works. */
+#define DEFINE_PER_CPU(type, name) \
+    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
+
+/* var is in discarded region: offset to particular copy we want */
+#define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
+#define __get_cpu_var(var) (*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 (__i = 0; __i < NR_CPUS; __i++)			\
+		if (cpu_possible(__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 per_cpu(var, cpu)			(*((void)cpu, &per_cpu__##var))
+#define __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_64/pgalloc.h b/include/asm-x86_64/pgalloc.h
new file mode 100644
index 000000000000..deadd146978b
--- /dev/null
+++ b/include/asm-x86_64/pgalloc.h
@@ -0,0 +1,105 @@
+#ifndef _X86_64_PGALLOC_H
+#define _X86_64_PGALLOC_H
+
+#include <asm/fixmap.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)));
+}
+
+extern __inline__ pmd_t *get_pmd(void)
+{
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL);
+}
+
+extern __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 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;
+	/*
+	 * 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));
+	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. */
+
+extern __inline__ void pte_free_kernel(pte_t *pte)
+{
+	BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
+	free_page((unsigned long)pte); 
+}
+
+extern 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_64/pgtable.h b/include/asm-x86_64/pgtable.h
new file mode 100644
index 000000000000..dc6b6f2604e8
--- /dev/null
+++ b/include/asm-x86_64/pgtable.h
@@ -0,0 +1,437 @@
+#ifndef _X86_64_PGTABLE_H
+#define _X86_64_PGTABLE_H
+
+/*
+ * This file contains the functions and defines necessary to modify and use
+ * the x86-64 page table tree.
+ */
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <asm/bitops.h>
+#include <linux/threads.h>
+#include <asm/pda.h>
+
+extern pud_t level3_kernel_pgt[512];
+extern pud_t level3_physmem_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 int nonx_setup(char *str);
+extern void paging_init(void);
+extern void clear_kernel_mapping(unsigned long addr, unsigned long size);
+
+extern unsigned long pgkern_mask;
+
+/*
+ * 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))
+
+/*
+ * 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
+
+#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);
+}
+
+extern 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); 
+} 
+
+extern inline void pgd_clear (pgd_t * pgd)
+{
+	set_pgd(pgd, __pgd(0));
+}
+
+#define pud_page(pud) \
+((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK))
+
+#define ptep_get_and_clear(mm,addr,xp)	__pte(xchg(&(xp)->pte, 0))
+#define pte_same(a, b)		((a).pte == (b).pte)
+
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+#define PUD_SIZE	(1UL << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(TASK_SIZE/PGDIR_SIZE)
+#define FIRST_USER_PGD_NR	0
+
+#ifndef __ASSEMBLY__
+#define MAXMEM		 0x3fffffffffffUL
+#define VMALLOC_START    0xffffc20000000000UL
+#define VMALLOC_END      0xffffe1ffffffffffUL
+#define MODULES_VADDR    0xffffffff88000000UL
+#define MODULES_END      0xfffffffffff00000UL
+#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	/* set:pagecache, unset:swap */
+#define _PAGE_GLOBAL	0x100	/* Global TLB entry */
+
+#define _PAGE_PROTNONE	0x080	/* If not present */
+#define _PAGE_NX        (1UL<<_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 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
+
+static inline unsigned long pgd_bad(pgd_t pgd) 
+{ 
+       unsigned long val = pgd_val(pgd);
+       val &= ~PTE_MASK; 
+       val &= ~(_PAGE_USER | _PAGE_DIRTY); 
+       return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED);      
+} 
+
+static inline unsigned long pud_bad(pud_t pud)
+{
+       unsigned long val = pud_val(pud);
+       val &= ~PTE_MASK;
+       val &= ~(_PAGE_USER | _PAGE_DIRTY);
+       return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED);
+}
+
+#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) >> PAGE_SHIFT) & __PHYSICAL_MASK)
+
+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..
+ */
+static inline int pte_user(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
+extern inline int pte_read(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
+extern inline int pte_exec(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
+extern inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
+extern inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
+extern 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; }
+
+extern inline pte_t pte_rdprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
+extern inline pte_t pte_exprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
+extern inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
+extern inline pte_t pte_mkold(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
+extern inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
+extern inline pte_t pte_mkread(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
+extern inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
+extern inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
+extern inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
+extern inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
+
+struct vm_area_struct;
+
+static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+	if (!pte_dirty(*ptep))
+		return 0;
+	return test_and_clear_bit(_PAGE_BIT_DIRTY, ptep);
+}
+
+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);
+}
+
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	clear_bit(_PAGE_BIT_RW, ptep);
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))
+
+#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT) 
+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.
+ */
+
+#define page_pte(page) page_pte_prot(page, __pgprot(0))
+
+/*
+ * Level 4 access.
+ */
+#define pgd_page(pgd) ((unsigned long) __va((unsigned long)pgd_val(pgd) & PTE_MASK))
+#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_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
+#define pud_offset(pgd, address) ((pud_t *) pgd_page(*(pgd)) + pud_index(address))
+#define pud_offset_k(pgd, addr) pud_offset(pgd, addr)
+#define pud_present(pud) (pud_val(pud) & _PAGE_PRESENT)
+
+static inline pud_t *__pud_offset_k(pud_t *pud, unsigned long address)
+{ 
+	return pud + pud_index(address);
+} 
+
+/* PMD  - Level 2 access */
+#define pmd_page_kernel(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(*(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	pmd_bad(x)	((pmd_val(x) & (~PTE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE )
+#define pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pmd_pfn(x)  ((pmd_val(x) >> PAGE_SHIFT) & __PHYSICAL_MASK)
+
+#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)
+ 
+/* physical address -> PTE */
+static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
+{ 
+	pte_t pte;
+	pte_val(pte) = physpage | pgprot_val(pgprot); 
+	return pte; 
+}
+ 
+/* Change flags of a PTE */
+extern 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_kernel(*(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) \
+	do {								  \
+		if (__dirty) {						  \
+			set_pte(__ptep, __entry);			  \
+			flush_tlb_page(__vma, __address);		  \
+		}							  \
+	} while (0)
+
+/* 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 })
+
+#endif /* !__ASSEMBLY__ */
+
+extern int kern_addr_valid(unsigned long addr); 
+
+#define io_remap_page_range(vma, vaddr, paddr, size, prot)		\
+		remap_pfn_range(vma, vaddr, (paddr) >> PAGE_SHIFT, size, prot)
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)		\
+		remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#define MK_IOSPACE_PFN(space, pfn)	(pfn)
+#define GET_IOSPACE(pfn)		0
+#define GET_PFN(pfn)			(pfn)
+
+#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_TEST_AND_CLEAR_DIRTY
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+#define __HAVE_ARCH_PTE_SAME
+#include <asm-generic/pgtable.h>
+
+#endif /* _X86_64_PGTABLE_H */
diff --git a/include/asm-x86_64/poll.h b/include/asm-x86_64/poll.h
new file mode 100644
index 000000000000..c43cbba31913
--- /dev/null
+++ b/include/asm-x86_64/poll.h
@@ -0,0 +1,26 @@
+#ifndef __x86_64_POLL_H
+#define __x86_64_POLL_H
+
+/* These are specified by iBCS2 */
+#define POLLIN		0x0001
+#define POLLPRI		0x0002
+#define POLLOUT		0x0004
+#define POLLERR		0x0008
+#define POLLHUP		0x0010
+#define POLLNVAL	0x0020
+
+/* The rest seem to be more-or-less nonstandard. Check them! */
+#define POLLRDNORM	0x0040
+#define POLLRDBAND	0x0080
+#define POLLWRNORM	0x0100
+#define POLLWRBAND	0x0200
+#define POLLMSG		0x0400
+#define POLLREMOVE	0x1000
+
+struct pollfd {
+	int fd;
+	short events;
+	short revents;
+};
+
+#endif
diff --git a/include/asm-x86_64/posix_types.h b/include/asm-x86_64/posix_types.h
new file mode 100644
index 000000000000..9926aa43775b
--- /dev/null
+++ b/include/asm-x86_64/posix_types.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_64/prctl.h b/include/asm-x86_64/prctl.h
new file mode 100644
index 000000000000..52952adef1ca
--- /dev/null
+++ b/include/asm-x86_64/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_64/processor.h b/include/asm-x86_64/processor.h
new file mode 100644
index 000000000000..45ab74e8f141
--- /dev/null
+++ b/include/asm-x86_64/processor.h
@@ -0,0 +1,462 @@
+/*
+ * 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/config.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>
+
+#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_num_cores;
+	__u8	x86_apicid;
+        __u32   x86_power; 	
+	__u32   x86_cpuid_level;	/* Max CPUID function supported */
+	unsigned long loops_per_jiffy;
+} ____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_RISE 6
+#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 unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
+
+/*
+ * 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 */
+
+/*
+ * Intel CPU features in CR4
+ */
+#define X86_CR4_VME		0x0001	/* enable vm86 extensions */
+#define X86_CR4_PVI		0x0002	/* virtual interrupts flag enable */
+#define X86_CR4_TSD		0x0004	/* disable time stamp at ipl 3 */
+#define X86_CR4_DE		0x0008	/* enable debugging extensions */
+#define X86_CR4_PSE		0x0010	/* enable page size extensions */
+#define X86_CR4_PAE		0x0020	/* enable physical address extensions */
+#define X86_CR4_MCE		0x0040	/* Machine check enable */
+#define X86_CR4_PGE		0x0080	/* enable global pages */
+#define X86_CR4_PCE		0x0100	/* enable performance counters at ipl 3 */
+#define X86_CR4_OSFXSR		0x0200	/* enable fast FPU save and restore */
+#define X86_CR4_OSXMMEXCPT	0x0400	/* enable unmasked SSE exceptions */
+
+/*
+ * 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.
+ */
+#define TASK_SIZE	(0x800000000000UL)
+
+/* 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_UNMAPPED_32 PAGE_ALIGN(IA32_PAGE_OFFSET/3)
+#define TASK_UNMAPPED_64 PAGE_ALIGN(TASK_SIZE/3) 
+#define TASK_UNMAPPED_BASE	\
+	(test_thread_flag(TIF_IA32) ? TASK_UNMAPPED_32 : TASK_UNMAPPED_64)  
+
+/*
+ * 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 = 128 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);
+
+#define ARCH_MIN_TASKALIGN	16
+
+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  {}
+
+#define INIT_MMAP \
+{ &init_mm, 0, 0, NULL, PAGE_SHARED, VM_READ | VM_WRITE | VM_EXEC, 1, NULL, NULL }
+
+#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 EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
+#define EXCEPTION_STACK_ORDER 0 
+
+#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) 
+
+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 KSTK_EIP(tsk) \
+	(((struct pt_regs *)(tsk->thread.rsp0 - sizeof(struct pt_regs)))->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];
+};
+
+/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */
+#define MICROCODE_IOCFREE	_IO('6',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. */
+extern inline void rep_nop(void)
+{
+	__asm__ __volatile__("rep;nop": : :"memory");
+}
+
+/* Stop speculative execution */
+extern inline void sync_core(void)
+{ 
+	int tmp;
+	asm volatile("cpuid" : "=a" (tmp) : "0" (1) : "ebx","ecx","edx","memory");
+} 
+
+#define cpu_has_fpu 1
+
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(void *x) 
+{ 
+	asm volatile("prefetcht0 %0" :: "m" (*(unsigned long *)x));
+} 
+
+#define ARCH_HAS_PREFETCHW 1
+static inline void prefetchw(void *x) 
+{ 
+	alternative_input(ASM_NOP5,
+			  "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()
+
+/*
+ *      NSC/Cyrix CPU configuration register indexes
+ */
+#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_DIR0 0xfe
+#define CX86_DIR1 0xff
+#define CX86_ARR_BASE 0xc4
+#define CX86_RCR_BASE 0xdc
+
+/*
+ *      NSC/Cyrix CPU indexed register access macros
+ */
+
+#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86(reg, data) do { \
+	outb((reg), 0x22); \
+	outb((data), 0x23); \
+} while (0)
+
+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));
+}
+
+#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;
+
+#endif /* __ASM_X86_64_PROCESSOR_H */
diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h
new file mode 100644
index 000000000000..c59526ee54da
--- /dev/null
+++ b/include/asm-x86_64/proto.h
@@ -0,0 +1,118 @@
+#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 get_cpu_vendor(struct cpuinfo_x86*);
+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 void iommu_hole_init(void);
+
+extern void time_init_smp(void);
+
+extern void do_softirq_thunk(void);
+
+extern int numa_setup(char *opt);
+
+extern int setup_early_printk(char *); 
+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 free_bootmem_generic(unsigned long phys, unsigned len);
+
+extern void load_gs_index(unsigned gs);
+
+extern unsigned long end_pfn_map; 
+
+extern cpumask_t cpu_initialized;
+
+extern void show_trace(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 oops_begin(void);
+extern void die(const char *,struct pt_regs *,long);
+extern void __die(const char * str, struct pt_regs * regs, long err);
+extern void __show_regs(struct pt_regs * regs);
+extern void show_regs(struct pt_regs * regs);
+
+extern int map_syscall32(struct mm_struct *mm, unsigned long address);
+extern int __map_syscall32(struct mm_struct *mm, unsigned long address);
+extern char *syscall32_page;
+extern void syscall32_cpu_init(void);
+
+extern void setup_node_bootmem(int nodeid, unsigned long start, unsigned long end);
+
+extern void check_ioapic(void);
+extern void check_efer(void);
+
+extern int unhandled_signal(struct task_struct *tsk, int sig);
+
+extern void select_idle_routine(const struct cpuinfo_x86 *c);
+extern void swiotlb_init(void);
+
+extern unsigned long max_mapnr;
+extern unsigned long end_pfn; 
+extern unsigned long table_start, table_end;
+
+extern int exception_trace;
+extern int force_iommu, no_iommu;
+extern int using_apic_timer;
+extern int disable_apic;
+extern unsigned cpu_khz;
+extern int ioapic_force;
+extern int skip_ioapic_setup;
+extern int acpi_ht;
+extern int acpi_disabled;
+
+extern int fallback_aper_order;
+extern int fallback_aper_force;
+extern int iommu_aperture;
+extern int iommu_aperture_disabled;
+extern int iommu_aperture_allowed;
+extern int fix_aperture;
+extern int force_iommu;
+
+extern int reboot_force;
+
+extern void smp_local_timer_interrupt(struct pt_regs * regs);
+
+long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
+
+#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_64/ptrace.h b/include/asm-x86_64/ptrace.h
new file mode 100644
index 000000000000..c7865cfedc1f
--- /dev/null
+++ b/include/asm-x86_64/ptrace.h
@@ -0,0 +1,114 @@
+#ifndef _X86_64_PTRACE_H
+#define _X86_64_PTRACE_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
+
+#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
+
+/* 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 */
+
+#if defined(__KERNEL__) && !defined(__ASSEMBLY__) 
+#define user_mode(regs) (!!((regs)->cs & 3))
+#define instruction_pointer(regs) ((regs)->rip)
+extern unsigned long profile_pc(struct pt_regs *regs);
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+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_64/resource.h b/include/asm-x86_64/resource.h
new file mode 100644
index 000000000000..f40b40623234
--- /dev/null
+++ b/include/asm-x86_64/resource.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_64/rtc.h b/include/asm-x86_64/rtc.h
new file mode 100644
index 000000000000..18ed713ac7de
--- /dev/null
+++ b/include/asm-x86_64/rtc.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_64/rwlock.h b/include/asm-x86_64/rwlock.h
new file mode 100644
index 000000000000..8a78a4ace53c
--- /dev/null
+++ b/include/asm-x86_64/rwlock.h
@@ -0,0 +1,86 @@
+/* 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
+
+#include <linux/stringify.h>
+
+#define RW_LOCK_BIAS		 0x01000000
+#define RW_LOCK_BIAS_STR	"0x01000000"
+
+#define __build_read_lock_ptr(rw, helper)   \
+	asm volatile(LOCK "subl $1,(%0)\n\t" \
+		     "js 2f\n" \
+		     "1:\n" \
+		    LOCK_SECTION_START("") \
+		     "2:\tcall " helper "\n\t" \
+		     "jmp 1b\n" \
+		    LOCK_SECTION_END \
+		     ::"a" (rw) : "memory")
+
+#define __build_read_lock_const(rw, helper)   \
+	asm volatile(LOCK "subl $1,%0\n\t" \
+		     "js 2f\n" \
+		     "1:\n" \
+		    LOCK_SECTION_START("") \
+		     "2:\tpushq %%rax\n\t" \
+		     "leaq %0,%%rax\n\t" \
+		     "call " helper "\n\t" \
+		     "popq %%rax\n\t" \
+		     "jmp 1b\n" \
+		    LOCK_SECTION_END \
+		     :"=m" (*((volatile int *)rw))::"memory")
+
+#define __build_read_lock(rw, helper)	do { \
+						if (__builtin_constant_p(rw)) \
+							__build_read_lock_const(rw, helper); \
+						else \
+							__build_read_lock_ptr(rw, helper); \
+					} while (0)
+
+#define __build_write_lock_ptr(rw, helper) \
+	asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
+		     "jnz 2f\n" \
+		     "1:\n" \
+		     LOCK_SECTION_START("") \
+		     "2:\tcall " helper "\n\t" \
+		     "jmp 1b\n" \
+		     LOCK_SECTION_END \
+		     ::"a" (rw) : "memory")
+
+#define __build_write_lock_const(rw, helper) \
+	asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
+		     "jnz 2f\n" \
+		     "1:\n" \
+		    LOCK_SECTION_START("") \
+		     "2:\tpushq %%rax\n\t" \
+		     "leaq %0,%%rax\n\t" \
+		     "call " helper "\n\t" \
+		     "popq %%rax\n\t" \
+		     "jmp 1b\n" \
+		    LOCK_SECTION_END \
+		     :"=m" (*((volatile long *)rw))::"memory")
+
+#define __build_write_lock(rw, helper)	do { \
+						if (__builtin_constant_p(rw)) \
+							__build_write_lock_const(rw, helper); \
+						else \
+							__build_write_lock_ptr(rw, helper); \
+					} while (0)
+
+#endif
diff --git a/include/asm-x86_64/rwsem.h b/include/asm-x86_64/rwsem.h
new file mode 100644
index 000000000000..c002175b6e82
--- /dev/null
+++ b/include/asm-x86_64/rwsem.h
@@ -0,0 +1,278 @@
+/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for x86_64+
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ * Ported by Andi Kleen <ak@suse.de> to x86-64.
+ *
+ * Derived from asm-i386/semaphore.h and asm-i386/rwsem.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 consecutive readers at the
+ * front, then they'll all be woken up, but no other readers will be.
+ */
+
+#ifndef _X8664_RWSEM_H
+#define _X8664_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>
+
+struct rwsem_waiter;
+
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+/*
+ * the semaphore definition
+ */
+struct rw_semaphore {
+	signed int		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;
+#if RWSEM_DEBUG
+	int			debug;
+#endif
+};
+
+/*
+ * initialisation
+ */
+#if RWSEM_DEBUG
+#define __RWSEM_DEBUG_INIT      , 0
+#else
+#define __RWSEM_DEBUG_INIT	/* */
+#endif
+
+#define __RWSEM_INITIALIZER(name) \
+{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, LIST_HEAD_INIT((name).wait_list) \
+	__RWSEM_DEBUG_INIT }
+
+#define DECLARE_RWSEM(name) \
+	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+static inline void init_rwsem(struct rw_semaphore *sem)
+{
+	sem->count = RWSEM_UNLOCKED_VALUE;
+	spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+#if RWSEM_DEBUG
+	sem->debug = 0;
+#endif
+}
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	__asm__ __volatile__(
+		"# beginning down_read\n\t"
+LOCK_PREFIX	"  incl      (%%rdi)\n\t" /* adds 0x00000001, returns the old value */
+		"  js        2f\n\t" /* jump if we weren't granted the lock */
+		"1:\n\t"
+		LOCK_SECTION_START("") \
+		"2:\n\t"
+		"  call      rwsem_down_read_failed_thunk\n\t"
+		"  jmp       1b\n"
+		LOCK_SECTION_END \
+		"# ending down_read\n\t"
+		: "+m"(sem->count)
+		: "D"(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(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	tmp = RWSEM_ACTIVE_WRITE_BIAS;
+	__asm__ __volatile__(
+		"# beginning down_write\n\t"
+LOCK_PREFIX	"  xaddl      %0,(%%rdi)\n\t" /* subtract 0x0000ffff, returns the old value */
+		"  testl     %0,%0\n\t" /* was the count 0 before? */
+		"  jnz       2f\n\t" /* jump if we weren't granted the lock */
+		"1:\n\t"
+		LOCK_SECTION_START("")
+		"2:\n\t"
+		"  call      rwsem_down_write_failed_thunk\n\t"
+		"  jmp       1b\n"
+		LOCK_SECTION_END
+		"# ending down_write"
+		: "=&r" (tmp) 
+		: "0"(tmp), "D"(sem)
+		: "memory", "cc");
+}
+
+/*
+ * 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	"  xaddl      %[tmp],(%%rdi)\n\t" /* subtracts 1, returns the old value */
+		"  js        2f\n\t" /* jump if the lock is being waited upon */
+		"1:\n\t"
+		LOCK_SECTION_START("")
+		"2:\n\t"
+		"  decw      %w[tmp]\n\t" /* do nothing if still outstanding active readers */
+		"  jnz       1b\n\t"
+		"  call      rwsem_wake_thunk\n\t"
+		"  jmp       1b\n"
+		LOCK_SECTION_END
+		"# ending __up_read\n"
+		: "+m"(sem->count), [tmp] "+r" (tmp)
+		: "D"(sem)
+		: "memory", "cc");
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	unsigned tmp; 
+	__asm__ __volatile__(
+		"# beginning __up_write\n\t"
+		"  movl     %[bias],%[tmp]\n\t"
+LOCK_PREFIX	"  xaddl     %[tmp],(%%rdi)\n\t" /* tries to transition 0xffff0001 -> 0x00000000 */
+		"  jnz       2f\n\t" /* jump if the lock is being waited upon */
+		"1:\n\t"
+		LOCK_SECTION_START("")
+		"2:\n\t"
+		"  decw      %w[tmp]\n\t" /* did the active count reduce to 0? */
+		"  jnz       1b\n\t" /* jump back if not */
+		"  call      rwsem_wake_thunk\n\t"
+		"  jmp       1b\n"
+		LOCK_SECTION_END
+		"# ending __up_write\n"
+		: "+m"(sem->count), [tmp] "=r" (tmp)
+		: "D"(sem), [bias] "i"(-RWSEM_ACTIVE_WRITE_BIAS)
+		: "memory", "cc");
+}
+
+/*
+ * 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      %[bias],(%%rdi)\n\t" /* transitions 0xZZZZ0001 -> 0xYYYY0001 */
+		"  js        2f\n\t" /* jump if the lock is being waited upon */
+		"1:\n\t"
+		LOCK_SECTION_START("")
+		"2:\n\t"
+		"  call	     rwsem_downgrade_thunk\n"
+		"  jmp       1b\n"
+		LOCK_SECTION_END
+		"# ending __downgrade_write\n"
+		: "=m"(sem->count)
+		: "D"(sem), [bias] "i"(-RWSEM_WAITING_BIAS), "m"(sem->count)
+		: "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), "m"(sem->count));
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+{
+	int tmp = delta;
+
+	__asm__ __volatile__(
+LOCK_PREFIX	"xaddl %0,(%2)"
+		: "=r"(tmp), "=m"(sem->count)
+		: "r"(sem), "m"(sem->count), "0" (tmp)
+		: "memory");
+
+	return tmp+delta;
+}
+
+#endif /* __KERNEL__ */
+#endif /* _X8664_RWSEM_H */
diff --git a/include/asm-x86_64/scatterlist.h b/include/asm-x86_64/scatterlist.h
new file mode 100644
index 000000000000..49d89f8129cd
--- /dev/null
+++ b/include/asm-x86_64/scatterlist.h
@@ -0,0 +1,22 @@
+#ifndef _X8664_SCATTERLIST_H
+#define _X8664_SCATTERLIST_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_64/seccomp.h b/include/asm-x86_64/seccomp.h
new file mode 100644
index 000000000000..553af65a2287
--- /dev/null
+++ b/include/asm-x86_64/seccomp.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_64/sections.h b/include/asm-x86_64/sections.h
new file mode 100644
index 000000000000..c746d9f1e70c
--- /dev/null
+++ b/include/asm-x86_64/sections.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_64/segment.h b/include/asm-x86_64/segment.h
new file mode 100644
index 000000000000..44adaf18c11e
--- /dev/null
+++ b/include/asm-x86_64/segment.h
@@ -0,0 +1,46 @@
+#ifndef _ASM_SEGMENT_H
+#define _ASM_SEGMENT_H
+
+#include <asm/cache.h>
+
+#define __KERNEL_CS	0x10
+#define __KERNEL_DS	0x18
+
+#define __KERNEL32_CS   0x38
+
+/* 
+ * 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 __KERNEL16_CS	(GDT_ENTRY_KERNELCS16 * 8)
+#define __KERNEL_COMPAT32_CS   0x8
+
+#define GDT_ENTRY_TLS 1
+#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_KERNELCS16 15
+
+#define GDT_ENTRY_TLS_ENTRIES 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_64/semaphore.h b/include/asm-x86_64/semaphore.h
new file mode 100644
index 000000000000..f325e39bf3b9
--- /dev/null
+++ b/include/asm-x86_64/semaphore.h
@@ -0,0 +1,196 @@
+#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 __MUTEX_INITIALIZER(name) \
+	__SEMAPHORE_INITIALIZER(name,1)
+
+#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 "decl %0\n\t"     /* --sem->count */
+		"js 2f\n"
+		"1:\n"
+		LOCK_SECTION_START("")
+		"2:\tcall __down_failed\n\t"
+		"jmp 1b\n"
+		LOCK_SECTION_END
+		:"=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"
+		LOCK "decl %1\n\t"     /* --sem->count */
+		"js 2f\n\t"
+		"xorl %0,%0\n"
+		"1:\n"
+		LOCK_SECTION_START("")
+		"2:\tcall __down_failed_interruptible\n\t"
+		"jmp 1b\n"
+		LOCK_SECTION_END
+		:"=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"
+		LOCK "decl %1\n\t"     /* --sem->count */
+		"js 2f\n\t"
+		"xorl %0,%0\n"
+		"1:\n"
+		LOCK_SECTION_START("")
+		"2:\tcall __down_failed_trylock\n\t"
+		"jmp 1b\n"
+		LOCK_SECTION_END
+		:"=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 "incl %0\n\t"     /* ++sem->count */
+		"jle 2f\n"
+		"1:\n"
+		LOCK_SECTION_START("")
+		"2:\tcall __up_wakeup\n\t"
+		"jmp 1b\n"
+		LOCK_SECTION_END
+		:"=m" (sem->count)
+		:"D" (sem)
+		:"memory");
+}
+#endif /* __KERNEL__ */
+#endif
diff --git a/include/asm-x86_64/sembuf.h b/include/asm-x86_64/sembuf.h
new file mode 100644
index 000000000000..63b52925ae2a
--- /dev/null
+++ b/include/asm-x86_64/sembuf.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_64/serial.h b/include/asm-x86_64/serial.h
new file mode 100644
index 000000000000..dbab232044cd
--- /dev/null
+++ b/include/asm-x86_64/serial.h
@@ -0,0 +1,130 @@
+/*
+ * include/asm-x86_64/serial.h
+ */
+
+#include <linux/config.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
+
+#ifdef CONFIG_SERIAL_MANY_PORTS
+#define FOURPORT_FLAGS ASYNC_FOURPORT
+#define ACCENT_FLAGS 0
+#define BOCA_FLAGS 0
+#define HUB6_FLAGS 0
+#endif
+
+#define MCA_COM_FLAGS	(STD_COM_FLAGS|ASYNC_BOOT_ONLYMCA)
+
+/*
+ * The following define the access methods for the HUB6 card. All
+ * access is through two ports for all 24 possible chips. The card is
+ * selected through the high 2 bits, the port on that card with the
+ * "middle" 3 bits, and the register on that port with the bottom
+ * 3 bits.
+ *
+ * While the access port and interrupt is configurable, the default
+ * port locations are 0x302 for the port control register, and 0x303
+ * for the data read/write register. Normally, the interrupt is at irq3
+ * but can be anything from 3 to 7 inclusive. Note that using 3 will
+ * require disabling com2.
+ */
+
+#define C_P(card,port) (((card)<<6|(port)<<3) + 1)
+
+#define STD_SERIAL_PORT_DEFNS			\
+	/* 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 */
+
+
+#ifdef CONFIG_SERIAL_MANY_PORTS
+#define EXTRA_SERIAL_PORT_DEFNS			\
+	{ 0, BASE_BAUD, 0x1A0, 9, FOURPORT_FLAGS }, 	/* ttyS4 */	\
+	{ 0, BASE_BAUD, 0x1A8, 9, FOURPORT_FLAGS },	/* ttyS5 */	\
+	{ 0, BASE_BAUD, 0x1B0, 9, FOURPORT_FLAGS },	/* ttyS6 */	\
+	{ 0, BASE_BAUD, 0x1B8, 9, FOURPORT_FLAGS },	/* ttyS7 */	\
+	{ 0, BASE_BAUD, 0x2A0, 5, FOURPORT_FLAGS },	/* ttyS8 */	\
+	{ 0, BASE_BAUD, 0x2A8, 5, FOURPORT_FLAGS },	/* ttyS9 */	\
+	{ 0, BASE_BAUD, 0x2B0, 5, FOURPORT_FLAGS },	/* ttyS10 */	\
+	{ 0, BASE_BAUD, 0x2B8, 5, FOURPORT_FLAGS },	/* ttyS11 */	\
+	{ 0, BASE_BAUD, 0x330, 4, ACCENT_FLAGS },	/* ttyS12 */	\
+	{ 0, BASE_BAUD, 0x338, 4, ACCENT_FLAGS },	/* ttyS13 */	\
+	{ 0, BASE_BAUD, 0x000, 0, 0 },	/* ttyS14 (spare) */		\
+	{ 0, BASE_BAUD, 0x000, 0, 0 },	/* ttyS15 (spare) */		\
+	{ 0, BASE_BAUD, 0x100, 12, BOCA_FLAGS },	/* ttyS16 */	\
+	{ 0, BASE_BAUD, 0x108, 12, BOCA_FLAGS },	/* ttyS17 */	\
+	{ 0, BASE_BAUD, 0x110, 12, BOCA_FLAGS },	/* ttyS18 */	\
+	{ 0, BASE_BAUD, 0x118, 12, BOCA_FLAGS },	/* ttyS19 */	\
+	{ 0, BASE_BAUD, 0x120, 12, BOCA_FLAGS },	/* ttyS20 */	\
+	{ 0, BASE_BAUD, 0x128, 12, BOCA_FLAGS },	/* ttyS21 */	\
+	{ 0, BASE_BAUD, 0x130, 12, BOCA_FLAGS },	/* ttyS22 */	\
+	{ 0, BASE_BAUD, 0x138, 12, BOCA_FLAGS },	/* ttyS23 */	\
+	{ 0, BASE_BAUD, 0x140, 12, BOCA_FLAGS },	/* ttyS24 */	\
+	{ 0, BASE_BAUD, 0x148, 12, BOCA_FLAGS },	/* ttyS25 */	\
+	{ 0, BASE_BAUD, 0x150, 12, BOCA_FLAGS },	/* ttyS26 */	\
+	{ 0, BASE_BAUD, 0x158, 12, BOCA_FLAGS },	/* ttyS27 */	\
+	{ 0, BASE_BAUD, 0x160, 12, BOCA_FLAGS },	/* ttyS28 */	\
+	{ 0, BASE_BAUD, 0x168, 12, BOCA_FLAGS },	/* ttyS29 */	\
+	{ 0, BASE_BAUD, 0x170, 12, BOCA_FLAGS },	/* ttyS30 */	\
+	{ 0, BASE_BAUD, 0x178, 12, BOCA_FLAGS },	/* ttyS31 */
+#else
+#define EXTRA_SERIAL_PORT_DEFNS
+#endif
+
+/* You can have up to four HUB6's in the system, but I've only
+ * included two cards here for a total of twelve ports.
+ */
+#if (defined(CONFIG_HUB6) && defined(CONFIG_SERIAL_MANY_PORTS))
+#define HUB6_SERIAL_PORT_DFNS		\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,0) },  /* ttyS32 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,1) },  /* ttyS33 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,2) },  /* ttyS34 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,3) },  /* ttyS35 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,4) },  /* ttyS36 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,5) },  /* ttyS37 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,0) },  /* ttyS38 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,1) },  /* ttyS39 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,2) },  /* ttyS40 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,3) },  /* ttyS41 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,4) },  /* ttyS42 */	\
+	{ 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,5) },  /* ttyS43 */
+#else
+#define HUB6_SERIAL_PORT_DFNS
+#endif
+
+#ifdef CONFIG_MCA
+#define MCA_SERIAL_PORT_DFNS			\
+	{ 0, BASE_BAUD, 0x3220, 3, MCA_COM_FLAGS },	\
+	{ 0, BASE_BAUD, 0x3228, 3, MCA_COM_FLAGS },	\
+	{ 0, BASE_BAUD, 0x4220, 3, MCA_COM_FLAGS },	\
+	{ 0, BASE_BAUD, 0x4228, 3, MCA_COM_FLAGS },	\
+	{ 0, BASE_BAUD, 0x5220, 3, MCA_COM_FLAGS },	\
+	{ 0, BASE_BAUD, 0x5228, 3, MCA_COM_FLAGS },
+#else
+#define MCA_SERIAL_PORT_DFNS
+#endif
+
+#define SERIAL_PORT_DFNS		\
+	STD_SERIAL_PORT_DEFNS		\
+	EXTRA_SERIAL_PORT_DEFNS		\
+	HUB6_SERIAL_PORT_DFNS		\
+	MCA_SERIAL_PORT_DFNS
+
diff --git a/include/asm-x86_64/setup.h b/include/asm-x86_64/setup.h
new file mode 100644
index 000000000000..985d4e3c79da
--- /dev/null
+++ b/include/asm-x86_64/setup.h
@@ -0,0 +1,6 @@
+#ifndef _x8664_SETUP_H
+#define _x8664_SETUP_H
+
+#define COMMAND_LINE_SIZE	256
+
+#endif
diff --git a/include/asm-x86_64/shmbuf.h b/include/asm-x86_64/shmbuf.h
new file mode 100644
index 000000000000..5a6d6dda7c48
--- /dev/null
+++ b/include/asm-x86_64/shmbuf.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_64/shmparam.h b/include/asm-x86_64/shmparam.h
new file mode 100644
index 000000000000..d7021620dcb7
--- /dev/null
+++ b/include/asm-x86_64/shmparam.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_64/sigcontext.h b/include/asm-x86_64/sigcontext.h
new file mode 100644
index 000000000000..b4e40236666c
--- /dev/null
+++ b/include/asm-x86_64/sigcontext.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_64/sigcontext32.h b/include/asm-x86_64/sigcontext32.h
new file mode 100644
index 000000000000..3d657038ab7c
--- /dev/null
+++ b/include/asm-x86_64/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_64/siginfo.h b/include/asm-x86_64/siginfo.h
new file mode 100644
index 000000000000..7bc15985f124
--- /dev/null
+++ b/include/asm-x86_64/siginfo.h
@@ -0,0 +1,10 @@
+#ifndef _X8664_SIGINFO_H
+#define _X8664_SIGINFO_H
+
+#define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
+
+#define SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 4)
+
+#include <asm-generic/siginfo.h>
+
+#endif
diff --git a/include/asm-x86_64/signal.h b/include/asm-x86_64/signal.h
new file mode 100644
index 000000000000..643a20d73765
--- /dev/null
+++ b/include/asm-x86_64/signal.h
@@ -0,0 +1,213 @@
+#ifndef _ASMx8664_SIGNAL_H
+#define _ASMx8664_SIGNAL_H
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#include <linux/linkage.h>
+#include <linux/time.h>
+
+/* Avoid too many header ordering problems.  */
+struct siginfo;
+
+#ifdef __KERNEL__
+/* 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;
+
+
+struct pt_regs; 
+asmlinkage int do_signal(struct pt_regs *regs, sigset_t *oldset);
+
+
+#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_INTERRUPT is a no-op, but left due to historical reasons. Use the
+ * 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_INTERRUPT	0x20000000 /* dummy -- ignored */
+
+#define SA_RESTORER	0x04000000
+
+/*
+ * sigaltstack controls
+ */
+#define SS_ONSTACK	1
+#define SS_DISABLE	2
+
+#define MINSIGSTKSZ	2048
+#define SIGSTKSZ	8192
+
+#ifdef __KERNEL__
+
+/*
+ * These values of sa_flags are used only by the kernel as part of the
+ * irq handling routines.
+ *
+ * SA_INTERRUPT is also used by the irq handling routines.
+ * SA_SHIRQ is for shared interrupt support on PCI and EISA.
+ */
+#define SA_PROBE		SA_ONESHOT
+#define SA_SAMPLE_RANDOM	SA_RESTART
+#define SA_SHIRQ		0x04000000
+#endif
+
+#define SIG_BLOCK          0	/* for blocking signals */
+#define SIG_UNBLOCK        1	/* for unblocking signals */
+#define SIG_SETMASK        2	/* for setting the signal mask */
+
+#ifndef __ASSEMBLY__
+/* Type of a signal handler.  */
+typedef void __signalfn_t(int);
+typedef __signalfn_t __user *__sighandler_t;
+
+typedef void __restorefn_t(void);
+typedef __restorefn_t __user *__sigrestore_t;
+
+#define SIG_DFL	((__sighandler_t)0)	/* default signal handling */
+#define SIG_IGN	((__sighandler_t)1)	/* ignore signal */
+#define SIG_ERR	((__sighandler_t)-1)	/* error return from signal */
+
+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
+
+extern __inline__ void sigaddset(sigset_t *set, int _sig)
+{
+	__asm__("btsq %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+extern __inline__ void sigdelset(sigset_t *set, int _sig)
+{
+	__asm__("btrq %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+extern __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)));
+}
+
+extern __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)))
+
+extern __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_64/smp.h b/include/asm-x86_64/smp.h
new file mode 100644
index 000000000000..fe523e3e2ff4
--- /dev/null
+++ b/include/asm-x86_64/smp.h
@@ -0,0 +1,149 @@
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+/*
+ * We need the APIC definitions automatically as part of 'smp.h'
+ */
+#ifndef __ASSEMBLY__
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/bitops.h>
+extern int disable_apic;
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#ifndef __ASSEMBLY__
+#include <asm/fixmap.h>
+#include <asm/mpspec.h>
+#ifdef CONFIG_X86_IO_APIC
+#include <asm/io_apic.h>
+#endif
+#include <asm/apic.h>
+#include <asm/thread_info.h>
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+#ifndef ASSEMBLY
+
+#include <asm/pda.h>
+
+struct pt_regs;
+
+/*
+ * Private routines/data
+ */
+ 
+extern void smp_alloc_memory(void);
+extern cpumask_t cpu_online_map;
+extern volatile unsigned long smp_invalidate_needed;
+extern int pic_mode;
+extern int smp_num_siblings;
+extern void smp_flush_tlb(void);
+extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs);
+extern void smp_send_reschedule(int cpu);
+extern void smp_invalidate_rcv(void);		/* Process an NMI */
+extern void (*mtrr_hook) (void);
+extern void zap_low_mappings(void);
+void smp_stop_cpu(void);
+extern cpumask_t cpu_sibling_map[NR_CPUS];
+extern u8 phys_proc_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.
+ */
+
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_callin_map;
+#define cpu_possible_map cpu_callout_map
+
+static inline int num_booting_cpus(void)
+{
+	return cpus_weight(cpu_callout_map);
+}
+
+#define __smp_processor_id() read_pda(cpunumber)
+
+extern __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));
+}
+
+#define safe_smp_processor_id() (disable_apic ? 0 : x86_apicid_to_cpu(hard_smp_processor_id()))
+
+#endif /* !ASSEMBLY */
+
+#define NO_PROC_ID		0xFF		/* No processor magic marker */
+
+#endif
+
+#ifndef ASSEMBLY
+/*
+ * 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 unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	return cpus_addr(cpumask)[0];
+}
+
+static inline int x86_apicid_to_cpu(u8 apicid)
+{
+	int i;
+
+	for (i = 0; i < NR_CPUS; ++i)
+		if (x86_cpu_to_apicid[i] == apicid)
+			return i;
+
+	/* No entries in x86_cpu_to_apicid?  Either no MPS|ACPI,
+	 * or called too early.  Either way, we must be CPU 0. */
+      	if (x86_cpu_to_apicid[0] == BAD_APICID)
+		return 0;
+
+	return -1;
+}
+
+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;
+}
+
+#endif /* !ASSEMBLY */
+
+#ifndef CONFIG_SMP
+#define stack_smp_processor_id() 0
+#define safe_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
+
+#ifndef __ASSEMBLY__
+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
+
diff --git a/include/asm-x86_64/socket.h b/include/asm-x86_64/socket.h
new file mode 100644
index 000000000000..d9a252ea8210
--- /dev/null
+++ b/include/asm-x86_64/socket.h
@@ -0,0 +1,50 @@
+#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_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
+
+#endif /* _ASM_SOCKET_H */
diff --git a/include/asm-x86_64/sockios.h b/include/asm-x86_64/sockios.h
new file mode 100644
index 000000000000..2eefd10d4f48
--- /dev/null
+++ b/include/asm-x86_64/sockios.h
@@ -0,0 +1,12 @@
+#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 */
+
+#endif
diff --git a/include/asm-x86_64/spinlock.h b/include/asm-x86_64/spinlock.h
new file mode 100644
index 000000000000..5aeb57a3baad
--- /dev/null
+++ b/include/asm-x86_64/spinlock.h
@@ -0,0 +1,214 @@
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/atomic.h>
+#include <asm/rwlock.h>
+#include <asm/page.h>
+#include <linux/config.h>
+
+extern int printk(const char * fmt, ...)
+	__attribute__ ((format (printf, 1, 2)));
+
+/*
+ * Your basic SMP spinlocks, allowing only a single CPU anywhere
+ */
+
+typedef struct {
+	volatile unsigned int lock;
+#ifdef CONFIG_DEBUG_SPINLOCK
+	unsigned magic;
+#endif
+#ifdef CONFIG_PREEMPT
+	unsigned int break_lock;
+#endif
+} spinlock_t;
+
+#define SPINLOCK_MAGIC	0xdead4ead
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+#define SPINLOCK_MAGIC_INIT	, SPINLOCK_MAGIC
+#else
+#define SPINLOCK_MAGIC_INIT	/* */
+#endif
+
+#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT }
+
+#define spin_lock_init(x)	do { *(x) = SPIN_LOCK_UNLOCKED; } while(0)
+
+/*
+ * 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.
+ */
+
+#define spin_is_locked(x)	(*(volatile signed char *)(&(x)->lock) <= 0)
+#define spin_unlock_wait(x)	do { barrier(); } while(spin_is_locked(x))
+#define _raw_spin_lock_flags(lock, flags) _raw_spin_lock(lock)
+
+#define spin_lock_string \
+	"\n1:\t" \
+	"lock ; decb %0\n\t" \
+	"js 2f\n" \
+	LOCK_SECTION_START("") \
+	"2:\t" \
+	"rep;nop\n\t" \
+	"cmpb $0,%0\n\t" \
+	"jle 2b\n\t" \
+	"jmp 1b\n" \
+	LOCK_SECTION_END
+
+/*
+ * This works. Despite all the confusion.
+ * (except on PPro SMP or if we are using OOSTORE)
+ * (PPro errata 66, 92)
+ */
+ 
+#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+
+#define spin_unlock_string \
+	"movb $1,%0" \
+		:"=m" (lock->lock) : : "memory"
+
+
+static inline void _raw_spin_unlock(spinlock_t *lock)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	BUG_ON(lock->magic != SPINLOCK_MAGIC);
+	assert_spin_locked(lock);
+#endif
+	__asm__ __volatile__(
+		spin_unlock_string
+	);
+}
+
+#else
+
+#define spin_unlock_string \
+	"xchgb %b0, %1" \
+		:"=q" (oldval), "=m" (lock->lock) \
+		:"0" (oldval) : "memory"
+
+static inline void _raw_spin_unlock(spinlock_t *lock)
+{
+	char oldval = 1;
+#ifdef CONFIG_DEBUG_SPINLOCK
+	BUG_ON(lock->magic != SPINLOCK_MAGIC);
+	assert_spin_locked(lock);
+#endif
+	__asm__ __volatile__(
+		spin_unlock_string
+	);
+}
+
+#endif
+
+static inline int _raw_spin_trylock(spinlock_t *lock)
+{
+	char oldval;
+	__asm__ __volatile__(
+		"xchgb %b0,%1"
+		:"=q" (oldval), "=m" (lock->lock)
+		:"0" (0) : "memory");
+	return oldval > 0;
+}
+
+static inline void _raw_spin_lock(spinlock_t *lock)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	if (lock->magic != SPINLOCK_MAGIC) {
+		printk("eip: %p\n", __builtin_return_address(0));
+		BUG();
+	}
+#endif
+	__asm__ __volatile__(
+		spin_lock_string
+		:"=m" (lock->lock) : : "memory");
+}
+
+
+/*
+ * 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.
+ */
+typedef struct {
+	volatile unsigned int lock;
+#ifdef CONFIG_DEBUG_SPINLOCK
+	unsigned magic;
+#endif
+#ifdef CONFIG_PREEMPT
+	unsigned int break_lock;
+#endif
+} rwlock_t;
+
+#define RWLOCK_MAGIC	0xdeaf1eed
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+#define RWLOCK_MAGIC_INIT	, RWLOCK_MAGIC
+#else
+#define RWLOCK_MAGIC_INIT	/* */
+#endif
+
+#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT }
+
+#define rwlock_init(x)	do { *(x) = RW_LOCK_UNLOCKED; } while(0)
+
+#define read_can_lock(x)	((int)(x)->lock > 0)
+#define write_can_lock(x)	((x)->lock == RW_LOCK_BIAS)
+
+/*
+ * 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 spinlock helpers are in arch/i386/kernel/semaphore.c */
+
+static inline void _raw_read_lock(rwlock_t *rw)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	BUG_ON(rw->magic != RWLOCK_MAGIC);
+#endif
+	__build_read_lock(rw, "__read_lock_failed");
+}
+
+static inline void _raw_write_lock(rwlock_t *rw)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	BUG_ON(rw->magic != RWLOCK_MAGIC);
+#endif
+	__build_write_lock(rw, "__write_lock_failed");
+}
+
+#define _raw_read_unlock(rw)		asm volatile("lock ; incl %0" :"=m" ((rw)->lock) : : "memory")
+#define _raw_write_unlock(rw)	asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory")
+
+static inline int _raw_read_trylock(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(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;
+}
+
+#endif /* __ASM_SPINLOCK_H */
diff --git a/include/asm-x86_64/stat.h b/include/asm-x86_64/stat.h
new file mode 100644
index 000000000000..fd9f00d560f8
--- /dev/null
+++ b/include/asm-x86_64/stat.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_64/statfs.h b/include/asm-x86_64/statfs.h
new file mode 100644
index 000000000000..b3f4718af30b
--- /dev/null
+++ b/include/asm-x86_64/statfs.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_64/string.h b/include/asm-x86_64/string.h
new file mode 100644
index 000000000000..a3493ee282bb
--- /dev/null
+++ b/include/asm-x86_64/string.h
@@ -0,0 +1,67 @@
+#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 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
+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; }) 
+
+
+#define __HAVE_ARCH_MEMSET
+#define memset __builtin_memset
+
+#define __HAVE_ARCH_MEMMOVE
+void * memmove(void * dest,const void *src,size_t count);
+
+/* Use C out of line version for memcmp */ 
+#define memcmp __builtin_memcmp
+int memcmp(const void * cs,const void * ct,size_t count);
+
+/* out of line string functions use always C versions */ 
+#define strlen __builtin_strlen
+size_t strlen(const char * s);
+
+#define strcpy __builtin_strcpy
+char * strcpy(char * dest,const char *src);
+
+#define strcat __builtin_strcat
+char * strcat(char * dest, const char * src);
+
+#define strcmp __builtin_strcmp
+int strcmp(const char * cs,const char * ct);
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86_64/suspend.h b/include/asm-x86_64/suspend.h
new file mode 100644
index 000000000000..ec745807feae
--- /dev/null
+++ b/include/asm-x86_64/suspend.h
@@ -0,0 +1,58 @@
+/*
+ * 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;
+	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) \
+               __asm__("movq %0,%%db" #register  \
+                       : /* no output */ \
+                       :"r" ((thread)->debugreg##register))
+
+extern void fix_processor_context(void);
+
+#ifdef CONFIG_ACPI_SLEEP
+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;
+
+/* routines for saving/restoring kernel state */
+extern int acpi_save_state_mem(void);
+#endif
diff --git a/include/asm-x86_64/swiotlb.h b/include/asm-x86_64/swiotlb.h
new file mode 100644
index 000000000000..36293061f4ed
--- /dev/null
+++ b/include/asm-x86_64/swiotlb.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_SWIOTLB_H
+#define _ASM_SWTIOLB_H 1
+
+#include <linux/config.h>
+
+/* SWIOTLB interface */
+
+extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr, size_t size,
+				      int dir);
+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_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_alloc_coherent (struct device *hwdev, size_t size,
+				     dma_addr_t *dma_handle, int flags);
+extern void swiotlb_free_coherent (struct device *hwdev, size_t size,
+				   void *vaddr, dma_addr_t dma_handle);
+
+#ifdef CONFIG_SWIOTLB
+extern int swiotlb;
+#else
+#define swiotlb 0
+#endif
+
+#endif
diff --git a/include/asm-x86_64/system.h b/include/asm-x86_64/system.h
new file mode 100644
index 000000000000..76165736e43a
--- /dev/null
+++ b/include/asm-x86_64/system.h
@@ -0,0 +1,343 @@
+#ifndef __ASM_SYSTEM_H
+#define __ASM_SYSTEM_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <asm/segment.h>
+
+#ifdef __KERNEL__
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX "lock ; "
+#else
+#define LOCK_PREFIX ""
+#endif
+
+#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    "pushfq ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popfq\n\t" 
+
+#define __EXTRA_CLOBBER  \
+	,"rcx","rbx","rdx","r8","r9","r10","r11","r12","r13","r14","r15"
+
+#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 "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, thread_info)), \
+		       [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))
+
+#define set_debug(value,register) \
+                __asm__("movq %0,%%db" #register  \
+		: /* no output */ \
+		:"r" ((unsigned long) value))
+
+
+#ifdef __KERNEL__
+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];
+}; 
+#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 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 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)
+
+/*
+ * 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_cr3(void)
+{ 
+	unsigned long cr3;
+	asm("movq %%cr3,%0" : "=r" (cr3));
+	return cr3;
+} 
+
+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));
+} 
+
+#define stts() write_cr0(8 | read_cr0())
+
+#define wbinvd() \
+	__asm__ __volatile__ ("wbinvd": : :"memory");
+
+#endif	/* __KERNEL__ */
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))
+
+#define tas(ptr) (xchg((ptr),1))
+
+#define __xg(x) ((volatile long *)(x))
+
+extern 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)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 4:
+		__asm__ __volatile__(LOCK_PREFIX "cmpxchgl %k1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 8:
+		__asm__ __volatile__(LOCK_PREFIX "cmpxchgq %1,%2"
+				     : "=a"(prev)
+				     : "q"(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))))
+
+#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 { xchg(&var, value); } while (0)
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+
+#define warn_if_not_ulong(x) do { unsigned long foo; (void) (&(x) == &foo); } while (0)
+
+/* interrupt control.. */
+#define local_save_flags(x)	do { warn_if_not_ulong(x); __asm__ __volatile__("# save_flags \n\t pushfq ; popq %q0":"=g" (x): /* no input */ :"memory"); } while (0)
+#define local_irq_restore(x) 	__asm__ __volatile__("# restore_flags \n\t pushq %0 ; popfq": /* no output */ :"g" (x):"memory", "cc")
+#define local_irq_disable() 	__asm__ __volatile__("cli": : :"memory")
+#define local_irq_enable()	__asm__ __volatile__("sti": : :"memory")
+/* used in the idle loop; sti takes one instruction cycle to complete */
+#define safe_halt()		__asm__ __volatile__("sti; hlt": : :"memory")
+
+#define irqs_disabled()			\
+({					\
+	unsigned long flags;		\
+	local_save_flags(flags);	\
+	!(flags & (1<<9));		\
+})
+
+/* For spinlocks etc */
+#define local_irq_save(x) 	do { warn_if_not_ulong(x); __asm__ __volatile__("# local_irq_save \n\t pushfq ; popq %0 ; cli":"=g" (x): /* no input */ :"memory"); } while (0)
+
+void cpu_idle_wait(void);
+
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+void disable_hlt(void);
+void enable_hlt(void);
+
+#define HAVE_EAT_KEY
+void eat_key(void);
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif
diff --git a/include/asm-x86_64/termbits.h b/include/asm-x86_64/termbits.h
new file mode 100644
index 000000000000..bd950946e52c
--- /dev/null
+++ b/include/asm-x86_64/termbits.h
@@ -0,0 +1,173 @@
+#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 */
+};
+
+/* 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    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 (not used) */
+#define CMSPAR	  010000000000		/* mark or space (stick) parity */
+#define CRTSCTS	  020000000000		/* flow control */
+
+/* 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_64/termios.h b/include/asm-x86_64/termios.h
new file mode 100644
index 000000000000..041a91f7ddfb
--- /dev/null
+++ b/include/asm-x86_64/termios.h
@@ -0,0 +1,106 @@
+#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 */
+
+/* line disciplines */
+#define N_TTY		0
+#define N_SLIP		1
+#define N_MOUSE		2
+#define N_PPP		3
+#define N_STRIP		4
+#define N_AX25		5
+#define N_X25		6	/* X.25 async */
+#define N_6PACK		7
+#define N_MASC		8	/* Reserved for Mobitex module <kaz@cafe.net> */
+#define N_R3964		9	/* Reserved for Simatic R3964 module */
+#define N_PROFIBUS_FDL	10	/* Reserved for Profibus <Dave@mvhi.com> */
+#define N_IRDA		11	/* Linux IR - http://irda.sourceforge.net/ */
+#define N_SMSBLOCK	12	/* SMS block mode - for talking to GSM data cards about SMS messages */
+#define N_HDLC		13	/* synchronous HDLC */
+#define N_SYNC_PPP	14	/* synchronous PPP */
+#define N_HCI		15  /* Bluetooth HCI UART */
+
+#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 termios))
+#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios))
+
+#endif	/* __KERNEL__ */
+
+#endif	/* _X8664_TERMIOS_H */
diff --git a/include/asm-x86_64/thread_info.h b/include/asm-x86_64/thread_info.h
new file mode 100644
index 000000000000..f4b3b249639c
--- /dev/null
+++ b/include/asm-x86_64/thread_info.h
@@ -0,0 +1,144 @@
+/* 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;
+
+	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 */
+#define alloc_thread_info(tsk) \
+	((struct thread_info *) __get_free_pages(GFP_KERNEL,THREAD_ORDER))
+#define free_thread_info(ti) free_pages((unsigned long) (ti), THREAD_ORDER)
+#define get_thread_info(ti) get_task_struct((ti)->task)
+#define put_thread_info(ti) put_task_struct((ti)->task)
+
+#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_NOTIFY_RESUME	1	/* resumption notification requested */
+#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_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
+#define TIF_IA32		17	/* 32bit process */ 
+#define TIF_FORK		18	/* ret_from_fork */
+#define TIF_ABI_PENDING		19
+#define TIF_MEMDIE		20
+
+#define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
+#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_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
+#define _TIF_IA32		(1<<TIF_IA32)
+#define _TIF_FORK		(1<<TIF_FORK)
+#define _TIF_ABI_PENDING	(1<<TIF_ABI_PENDING)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK \
+  (0x0000FFFF & ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|_TIF_SECCOMP))
+/* work to do on any return to user space */
+#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
+
+#define 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) */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_THREAD_INFO_H */
diff --git a/include/asm-x86_64/timex.h b/include/asm-x86_64/timex.h
new file mode 100644
index 000000000000..34f31a18f90b
--- /dev/null
+++ b/include/asm-x86_64/timex.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 <linux/config.h>
+#include <asm/8253pit.h>
+#include <asm/msr.h>
+#include <asm/vsyscall.h>
+#include <asm/hpet.h>
+
+#define CLOCK_TICK_RATE	PIT_TICK_RATE	/* Underlying HZ */
+
+typedef unsigned long long cycles_t;
+
+static inline cycles_t get_cycles (void)
+{
+	unsigned long long ret;
+
+	rdtscll(ret);
+	return ret;
+}
+
+extern unsigned int cpu_khz;
+
+extern struct vxtime_data vxtime;
+
+#endif
diff --git a/include/asm-x86_64/tlb.h b/include/asm-x86_64/tlb.h
new file mode 100644
index 000000000000..cd4c3c590a0e
--- /dev/null
+++ b/include/asm-x86_64/tlb.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_64/tlbflush.h b/include/asm-x86_64/tlbflush.h
new file mode 100644
index 000000000000..2e811ac262af
--- /dev/null
+++ b/include/asm-x86_64/tlbflush.h
@@ -0,0 +1,119 @@
+#ifndef _X8664_TLBFLUSH_H
+#define _X8664_TLBFLUSH_H
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <asm/processor.h>
+
+#define __flush_tlb()							\
+	do {								\
+		unsigned long tmpreg;					\
+									\
+		__asm__ __volatile__(					\
+			"movq %%cr3, %0;  # flush TLB \n"		\
+			"movq %0, %%cr3;              \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 __flush_tlb_global()						\
+	do {								\
+		unsigned long tmpreg;					\
+									\
+		__asm__ __volatile__(					\
+			"movq %1, %%cr4;  # turn off PGE     \n"	\
+			"movq %%cr3, %0;  # flush TLB        \n"	\
+			"movq %0, %%cr3;                     \n"	\
+			"movq %2, %%cr4;  # turn PGE back on \n"	\
+			: "=&r" (tmpreg)				\
+			: "r" (mmu_cr4_features & ~X86_CR4_PGE),	\
+			  "r" (mmu_cr4_features)			\
+			: "memory");					\
+	} while (0)
+
+extern unsigned long pgkern_mask;
+
+#define __flush_tlb_all() __flush_tlb_global()
+
+#define __flush_tlb_one(addr) \
+	__asm__ __volatile__("invlpg %0": :"m" (*(char *) addr))
+
+
+/*
+ * 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
+ *
+ * ..but the x86_64 has somewhat limited tlb flushing capabilities,
+ * and page-granular flushes are available only on i486 and up.
+ */
+
+#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
+
+#endif
+
+#define flush_tlb_kernel_range(start, 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 TLB */
+}
+
+#endif /* _X8664_TLBFLUSH_H */
diff --git a/include/asm-x86_64/topology.h b/include/asm-x86_64/topology.h
new file mode 100644
index 000000000000..67f24e0ea819
--- /dev/null
+++ b/include/asm-x86_64/topology.h
@@ -0,0 +1,68 @@
+#ifndef _ASM_X86_64_TOPOLOGY_H
+#define _ASM_X86_64_TOPOLOGY_H
+
+#include <linux/config.h>
+
+#ifdef CONFIG_DISCONTIGMEM
+
+#include <asm/mpspec.h>
+#include <asm/bitops.h>
+
+/* Map the K8 CPU local memory controllers to a simple 1:1 CPU:NODE topology */
+
+extern cpumask_t cpu_online_map;
+
+extern unsigned char cpu_to_node[];
+extern cpumask_t     node_to_cpumask[];
+extern cpumask_t pci_bus_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) 	(__ffs(node_to_cpumask[node]))
+#define node_to_cpumask(node)		(node_to_cpumask[node])
+
+static inline cpumask_t __pcibus_to_cpumask(int bus)
+{
+	cpumask_t busmask = pci_bus_to_cpumask[bus];
+	cpumask_t online = cpu_online_map;
+	cpumask_t res;
+	cpus_and(res, busmask, online);
+	return res;
+}
+#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus->number)
+
+#ifdef CONFIG_NUMA
+/* sched_domains SD_NODE_INIT for x86_64 machines */
+#define SD_NODE_INIT (struct sched_domain) {		\
+	.span			= CPU_MASK_NONE,	\
+	.parent			= NULL,			\
+	.groups			= NULL,			\
+	.min_interval		= 8,			\
+	.max_interval		= 32,			\
+	.busy_factor		= 32,			\
+	.imbalance_pct		= 125,			\
+	.cache_hot_time		= (10*1000000),		\
+	.cache_nice_tries	= 1,			\
+	.per_cpu_gain		= 100,			\
+	.flags			= SD_LOAD_BALANCE	\
+				| SD_BALANCE_NEWIDLE	\
+				| SD_BALANCE_EXEC	\
+				| SD_WAKE_IDLE		\
+				| SD_WAKE_BALANCE,	\
+	.last_balance		= jiffies,		\
+	.balance_interval	= 1,			\
+	.nr_balance_failed	= 0,			\
+}
+#endif
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif
diff --git a/include/asm-x86_64/types.h b/include/asm-x86_64/types.h
new file mode 100644
index 000000000000..32bd1426b523
--- /dev/null
+++ b/include/asm-x86_64/types.h
@@ -0,0 +1,60 @@
+#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;
+
+typedef u64 sector_t;
+#define HAVE_SECTOR_T
+
+typedef unsigned short kmem_bufctl_t;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/include/asm-x86_64/uaccess.h b/include/asm-x86_64/uaccess.h
new file mode 100644
index 000000000000..48f292752c96
--- /dev/null
+++ b/include/asm-x86_64/uaccess.h
@@ -0,0 +1,365 @@
+#ifndef __X86_64_UACCESS_H
+#define __X86_64_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/config.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/sched.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,sum; \
+	__chk_user_ptr(addr); \
+	asm("# range_ok\n\r" \
+		"addq %3,%1 ; sbbq %0,%0 ; cmpq %1,%4 ; sbbq $0,%0"  \
+		:"=&r" (flag), "=r" (sum) \
+		:"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)
+
+/* this function will go away soon - use access_ok() instead */
+extern inline int __deprecated verify_area(int type, const void __user * addr, unsigned long size)
+{
+	return access_ok(type,addr,size) ? 0 : -EFAULT;
+}
+
+
+/*
+ * 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) = (__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","","ir",-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) = (__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 */
+extern unsigned long copy_user_generic(void *to, const void *from, unsigned len); 
+
+extern unsigned long copy_to_user(void __user *to, const void *from, unsigned len); 
+extern unsigned long copy_from_user(void *to, const void __user *from, unsigned len); 
+extern unsigned long copy_in_user(void __user *to, const void __user *from, unsigned len); 
+
+static inline 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 inline 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 inline 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); 
+	}
+}	
+
+long strncpy_from_user(char *dst, const char __user *src, long count);
+long __strncpy_from_user(char *dst, const char __user *src, long count);
+long strnlen_user(const char __user *str, long n);
+long strlen_user(const char __user *str);
+unsigned long clear_user(void __user *mem, unsigned long len);
+unsigned long __clear_user(void __user *mem, unsigned long len);
+
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
+
+#endif /* __X86_64_UACCESS_H */
diff --git a/include/asm-x86_64/ucontext.h b/include/asm-x86_64/ucontext.h
new file mode 100644
index 000000000000..159a3da9e112
--- /dev/null
+++ b/include/asm-x86_64/ucontext.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_64/unaligned.h b/include/asm-x86_64/unaligned.h
new file mode 100644
index 000000000000..d4bf78dc6f39
--- /dev/null
+++ b/include/asm-x86_64/unaligned.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_64/unistd.h b/include/asm-x86_64/unistd.h
new file mode 100644
index 000000000000..a8ea0164f3ab
--- /dev/null
+++ b/include/asm-x86_64/unistd.h
@@ -0,0 +1,797 @@
+#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, wrap_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_time64)
+#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_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_ni_syscall)
+#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_syscall_max __NR_keyctl
+#ifndef __NO_STUBS
+
+/* user-visible error numbers are in the range -1 - -4095 */
+
+#define __syscall_clobber "r11","rcx","memory" 
+
+#define __syscall_return(type, res) \
+do { \
+	if ((unsigned long)(res) >= (unsigned long)(-127)) { \
+		errno = -(res); \
+		res = -1; \
+	} \
+	return (type) (res); \
+} while (0)
+
+#ifdef __KERNEL__
+#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_COMPAT_SYS_TIME
+#endif
+
+#ifndef __KERNEL_SYSCALLS__
+
+#define __syscall "syscall"
+
+#define _syscall0(type,name) \
+type name(void) \
+{ \
+long __res; \
+__asm__ volatile (__syscall \
+	: "=a" (__res) \
+	: "0" (__NR_##name) : __syscall_clobber ); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall1(type,name,type1,arg1) \
+type name(type1 arg1) \
+{ \
+long __res; \
+__asm__ volatile (__syscall \
+	: "=a" (__res) \
+	: "0" (__NR_##name),"D" ((long)(arg1)) : __syscall_clobber ); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall2(type,name,type1,arg1,type2,arg2) \
+type name(type1 arg1,type2 arg2) \
+{ \
+long __res; \
+__asm__ volatile (__syscall \
+	: "=a" (__res) \
+	: "0" (__NR_##name),"D" ((long)(arg1)),"S" ((long)(arg2)) : __syscall_clobber ); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3) \
+type name(type1 arg1,type2 arg2,type3 arg3) \
+{ \
+long __res; \
+__asm__ volatile (__syscall \
+	: "=a" (__res) \
+	: "0" (__NR_##name),"D" ((long)(arg1)),"S" ((long)(arg2)), \
+		  "d" ((long)(arg3)) : __syscall_clobber); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \
+type name (type1 arg1, type2 arg2, type3 arg3, type4 arg4) \
+{ \
+long __res; \
+__asm__ volatile ("movq %5,%%r10 ;" __syscall \
+	: "=a" (__res) \
+	: "0" (__NR_##name),"D" ((long)(arg1)),"S" ((long)(arg2)), \
+	  "d" ((long)(arg3)),"g" ((long)(arg4)) : __syscall_clobber,"r10" ); \
+__syscall_return(type,__res); \
+} 
+
+#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
+	  type5,arg5) \
+type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5) \
+{ \
+long __res; \
+__asm__ volatile ("movq %5,%%r10 ; movq %6,%%r8 ; " __syscall \
+	: "=a" (__res) \
+	: "0" (__NR_##name),"D" ((long)(arg1)),"S" ((long)(arg2)), \
+	  "d" ((long)(arg3)),"g" ((long)(arg4)),"g" ((long)(arg5)) : \
+	__syscall_clobber,"r8","r10" ); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
+	  type5,arg5,type6,arg6) \
+type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5,type6 arg6) \
+{ \
+long __res; \
+__asm__ volatile ("movq %5,%%r10 ; movq %6,%%r8 ; movq %7,%%r9 ; " __syscall \
+	: "=a" (__res) \
+	: "0" (__NR_##name),"D" ((long)(arg1)),"S" ((long)(arg2)), \
+	  "d" ((long)(arg3)), "g" ((long)(arg4)), "g" ((long)(arg5)), \
+	  "g" ((long)(arg6)) : \
+	__syscall_clobber,"r8","r10","r9" ); \
+__syscall_return(type,__res); \
+}
+
+#else /* __KERNEL_SYSCALLS__ */
+
+#include <linux/syscalls.h>
+#include <asm/ptrace.h>
+
+/*
+ * we need this inline - forking from kernel space will result
+ * in NO COPY ON WRITE (!!!), until an execve is executed. This
+ * is no problem, but for the stack. This is handled by not letting
+ * main() use the stack at all after fork(). Thus, no function
+ * calls - which means inline code for fork too, as otherwise we
+ * would use the stack upon exit from 'fork()'.
+ *
+ * Actually only pause and fork are needed inline, so that there
+ * won't be any messing with the stack from main(), but we define
+ * some others too.
+ */
+#define __NR__exit __NR_exit
+
+static inline pid_t setsid(void)
+{
+	return sys_setsid();
+}
+
+static inline ssize_t write(unsigned int fd, char * buf, size_t count)
+{
+	return sys_write(fd, buf, count);
+}
+
+static inline ssize_t read(unsigned int fd, char * buf, size_t count)
+{
+	return sys_read(fd, buf, count);
+}
+
+static inline off_t lseek(unsigned int fd, off_t offset, unsigned int origin)
+{
+	return sys_lseek(fd, offset, origin);
+}
+
+static inline long dup(unsigned int fd)
+{
+	return sys_dup(fd);
+}
+
+/* implemented in asm in arch/x86_64/kernel/entry.S */
+extern int execve(const char *, char * const *, char * const *);
+
+static inline long open(const char * filename, int flags, int mode)
+{
+	return sys_open(filename, flags, mode);
+}
+
+static inline long close(unsigned int fd)
+{
+	return sys_close(fd);
+}
+
+static inline pid_t waitpid(int pid, int * wait_stat, int flags)
+{
+	return sys_wait4(pid, wait_stat, flags, NULL);
+}
+
+extern long sys_mmap(unsigned long addr, unsigned long len,
+			unsigned long prot, unsigned long flags,
+			unsigned long fd, unsigned long off);
+
+extern int sys_modify_ldt(int func, void *ptr, unsigned long bytecount);
+
+asmlinkage long sys_execve(char *name, char **argv, char **envp,
+			struct pt_regs regs);
+asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp,
+			void *parent_tid, void *child_tid,
+			struct pt_regs regs);
+asmlinkage long sys_fork(struct pt_regs regs);
+asmlinkage long sys_vfork(struct pt_regs regs);
+asmlinkage long sys_pipe(int *fildes);
+
+#endif /* __KERNEL_SYSCALLS__ */
+
+#if !defined(__ASSEMBLY__) && defined(__KERNEL__)
+
+#include <linux/linkage.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/ptrace.h>
+
+asmlinkage long sys_ptrace(long request, long pid,
+				unsigned long addr, long data);
+asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs);
+asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on);
+struct sigaction;
+asmlinkage long sys_rt_sigaction(int sig,
+				const struct sigaction __user *act,
+				struct sigaction __user *oact,
+				size_t sigsetsize);
+
+#endif	/* __ASSEMBLY__ */
+
+#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
diff --git a/include/asm-x86_64/user.h b/include/asm-x86_64/user.h
new file mode 100644
index 000000000000..12785c649ac5
--- /dev/null
+++ b/include/asm-x86_64/user.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_64/user32.h b/include/asm-x86_64/user32.h
new file mode 100644
index 000000000000..f769872debea
--- /dev/null
+++ b/include/asm-x86_64/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_64/vga.h b/include/asm-x86_64/vga.h
new file mode 100644
index 000000000000..ef0c0e50cc95
--- /dev/null
+++ b/include/asm-x86_64/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) (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_64/vsyscall.h b/include/asm-x86_64/vsyscall.h
new file mode 100644
index 000000000000..b0c8d4339906
--- /dev/null
+++ b/include/asm-x86_64/vsyscall.h
@@ -0,0 +1,61 @@
+#ifndef _ASM_X86_64_VSYSCALL_H_
+#define _ASM_X86_64_VSYSCALL_H_
+
+#include <linux/seqlock.h>
+
+enum vsyscall_num {
+	__NR_vgettimeofday,
+	__NR_vtime,
+};
+
+#define VSYSCALL_START (-10UL << 20)
+#define VSYSCALL_SIZE 1024
+#define VSYSCALL_END (-2UL << 20)
+#define VSYSCALL_ADDR(vsyscall_nr) (VSYSCALL_START+VSYSCALL_SIZE*(vsyscall_nr))
+
+#ifdef __KERNEL__
+
+#define __section_vxtime __attribute__ ((unused, __section__ (".vxtime"), aligned(16)))
+#define __section_wall_jiffies __attribute__ ((unused, __section__ (".wall_jiffies"), aligned(16)))
+#define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16)))
+#define __section_sys_tz __attribute__ ((unused, __section__ (".sys_tz"), aligned(16)))
+#define __section_sysctl_vsyscall __attribute__ ((unused, __section__ (".sysctl_vsyscall"), aligned(16)))
+#define __section_xtime __attribute__ ((unused, __section__ (".xtime"), aligned(16)))
+#define __section_xtime_lock __attribute__ ((unused, __section__ (".xtime_lock"), aligned(16)))
+
+#define VXTIME_TSC	1
+#define VXTIME_HPET	2
+
+struct vxtime_data {
+	long hpet_address;	/* HPET base address */
+	unsigned long hz;	/* HPET clocks / sec */
+	int last;
+	unsigned long last_tsc;
+	long quot;
+	long tsc_quot;
+	int mode;
+};
+
+#define hpet_readl(a)           readl((void *)fix_to_virt(FIX_HPET_BASE) + a)
+#define hpet_writel(d,a)        writel(d, (void *)fix_to_virt(FIX_HPET_BASE) + a)
+
+/* vsyscall space (readonly) */
+extern struct vxtime_data __vxtime;
+extern struct timespec __xtime;
+extern volatile unsigned long __jiffies;
+extern unsigned long __wall_jiffies;
+extern struct timezone __sys_tz;
+extern seqlock_t __xtime_lock;
+
+/* kernel space (writeable) */
+extern struct vxtime_data vxtime;
+extern unsigned long wall_jiffies;
+extern struct timezone sys_tz;
+extern int sysctl_vsyscall;
+extern seqlock_t xtime_lock;
+
+#define ARCH_HAVE_XTIME_LOCK 1
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_64_VSYSCALL_H_ */
diff --git a/include/asm-x86_64/vsyscall32.h b/include/asm-x86_64/vsyscall32.h
new file mode 100644
index 000000000000..c631c082f8f7
--- /dev/null
+++ b/include/asm-x86_64/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_64/xor.h b/include/asm-x86_64/xor.h
new file mode 100644
index 000000000000..f942fcc21831
--- /dev/null
+++ b/include/asm-x86_64/xor.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)