Merge branch 'linus' into release

Conflicts:
	arch/x86/kernel/cpu/cpufreq/longhaul.c

Signed-off-by: Len Brown <len.brown@intel.com>

168 files changed, 3855 insertions, 5296 deletions

diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h
index 3c601f8224be..bb70e397aa84 100644
--- a/arch/x86/include/asm/a.out-core.h
+++ b/arch/x86/include/asm/a.out-core.h
@@ -55,7 +55,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
         dump->regs.ds = (u16)regs->ds;
         dump->regs.es = (u16)regs->es;
         dump->regs.fs = (u16)regs->fs;
-        savesegment(gs, dump->regs.gs);
+        dump->regs.gs = get_user_gs(regs);
         dump->regs.orig_ax = regs->orig_ax;
         dump->regs.ip = regs->ip;
         dump->regs.cs = (u16)regs->cs;
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 9830681446ad..4518dc500903 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -102,9 +102,6 @@ static inline void disable_acpi(void)
         acpi_noirq = 1;
 }
 
-/* Fixmap pages to reserve for ACPI boot-time tables (see fixmap.h) */
-#define FIX_ACPI_PAGES 4
-
 extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
 
 static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
diff --git a/arch/x86/include/asm/aes.h b/arch/x86/include/asm/aes.h
new file mode 100644
index 000000000000..80545a1cbe39
--- /dev/null
+++ b/arch/x86/include/asm/aes.h
@@ -0,0 +1,11 @@
+#ifndef ASM_X86_AES_H
+#define ASM_X86_AES_H
+
+#include <linux/crypto.h>
+#include <crypto/aes.h>
+
+void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst,
+                            const u8 *src);
+void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst,
+                            const u8 *src);
+#endif
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index ab1d51a8855e..df8a300dfe6c 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -1,15 +1,18 @@
 #ifndef _ASM_X86_APIC_H
 #define _ASM_X86_APIC_H
 
-#include <linux/pm.h>
+#include <linux/cpumask.h>
 #include <linux/delay.h>
+#include <linux/pm.h>
 
 #include <asm/alternative.h>
-#include <asm/fixmap.h>
-#include <asm/apicdef.h>
+#include <asm/cpufeature.h>
 #include <asm/processor.h>
+#include <asm/apicdef.h>
+#include <asm/atomic.h>
+#include <asm/fixmap.h>
+#include <asm/mpspec.h>
 #include <asm/system.h>
-#include <asm/cpufeature.h>
 #include <asm/msr.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3      1
@@ -33,7 +36,13 @@
         } while (0)
 
 
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
 extern void generic_apic_probe(void);
+#else
+static inline void generic_apic_probe(void)
+{
+}
+#endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
@@ -41,6 +50,21 @@ extern unsigned int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
+
+#ifdef CONFIG_SMP
+extern void __inquire_remote_apic(int apicid);
+#else /* CONFIG_SMP */
+static inline void __inquire_remote_apic(int apicid)
+{
+}
+#endif /* CONFIG_SMP */
+
+static inline void default_inquire_remote_apic(int apicid)
+{
+        if (apic_verbosity >= APIC_DEBUG)
+                __inquire_remote_apic(apicid);
+}
+
 /*
  * Basic functions accessing APICs.
  */
@@ -51,7 +75,14 @@ extern int disable_apic;
 #define setup_secondary_clock setup_secondary_APIC_clock
 #endif
 
+#ifdef CONFIG_X86_64
 extern int is_vsmp_box(void);
+#else
+static inline int is_vsmp_box(void)
+{
+        return 0;
+}
+#endif
 extern void xapic_wait_icr_idle(void);
 extern u32 safe_xapic_wait_icr_idle(void);
 extern void xapic_icr_write(u32, u32);
@@ -71,6 +102,22 @@ static inline u32 native_apic_mem_read(u32 reg)
         return *((volatile u32 *)(APIC_BASE + reg));
 }
 
+extern void native_apic_wait_icr_idle(void);
+extern u32 native_safe_apic_wait_icr_idle(void);
+extern void native_apic_icr_write(u32 low, u32 id);
+extern u64 native_apic_icr_read(void);
+
+#ifdef CONFIG_X86_X2APIC
+/*
+ * Make previous memory operations globally visible before
+ * sending the IPI through x2apic wrmsr. We need a serializing instruction or
+ * mfence for this.
+ */
+static inline void x2apic_wrmsr_fence(void)
+{
+        asm volatile("mfence" : : : "memory");
+}
+
 static inline void native_apic_msr_write(u32 reg, u32 v)
 {
         if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||
@@ -91,8 +138,32 @@ static inline u32 native_apic_msr_read(u32 reg)
         return low;
 }
 
-#ifndef CONFIG_X86_32
-extern int x2apic;
+static inline void native_x2apic_wait_icr_idle(void)
+{
+        /* no need to wait for icr idle in x2apic */
+        return;
+}
+
+static inline u32 native_safe_x2apic_wait_icr_idle(void)
+{
+        /* no need to wait for icr idle in x2apic */
+        return 0;
+}
+
+static inline void native_x2apic_icr_write(u32 low, u32 id)
+{
+        wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+}
+
+static inline u64 native_x2apic_icr_read(void)
+{
+        unsigned long val;
+
+        rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+        return val;
+}
+
+extern int x2apic, x2apic_phys;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
 extern void enable_IR_x2apic(void);
@@ -110,30 +181,27 @@ static inline int x2apic_enabled(void)
         return 0;
 }
 #else
-#define x2apic_enabled()        0
-#endif
-
-struct apic_ops {
-        u32 (*read)(u32 reg);
-        void (*write)(u32 reg, u32 v);
-        u64 (*icr_read)(void);
-        void (*icr_write)(u32 low, u32 high);
-        void (*wait_icr_idle)(void);
-        u32 (*safe_wait_icr_idle)(void);
-};
+static inline void check_x2apic(void)
+{
+}
+static inline void enable_x2apic(void)
+{
+}
+static inline void enable_IR_x2apic(void)
+{
+}
+static inline int x2apic_enabled(void)
+{
+        return 0;
+}
 
-extern struct apic_ops *apic_ops;
+#define x2apic  0
 
-#define apic_read (apic_ops->read)
-#define apic_write (apic_ops->write)
-#define apic_icr_read (apic_ops->icr_read)
-#define apic_icr_write (apic_ops->icr_write)
-#define apic_wait_icr_idle (apic_ops->wait_icr_idle)
-#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle)
+#endif
 
 extern int get_physical_broadcast(void);
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_X2APIC
 static inline void ack_x2APIC_irq(void)
 {
         /* Docs say use 0 for future compatibility */
@@ -141,18 +209,6 @@ static inline void ack_x2APIC_irq(void)
 }
 #endif
 
-
-static inline void ack_APIC_irq(void)
-{
-        /*
-         * ack_APIC_irq() actually gets compiled as a single instruction
-         * ... yummie.
-         */
-
-        /* Docs say use 0 for future compatibility */
-        apic_write(APIC_EOI, 0);
-}
-
 extern int lapic_get_maxlvt(void);
 extern void clear_local_APIC(void);
 extern void connect_bsp_APIC(void);
@@ -196,4 +252,329 @@ static inline void disable_local_APIC(void) { }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
+#ifdef CONFIG_X86_64
+#define SET_APIC_ID(x)          (apic->set_apic_id(x))
+#else
+
+#endif
+
+/*
+ * 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 apic {
+        char *name;
+
+        int (*probe)(void);
+        int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+        int (*apic_id_registered)(void);
+
+        u32 irq_delivery_mode;
+        u32 irq_dest_mode;
+
+        const struct cpumask *(*target_cpus)(void);
+
+        int disable_esr;
+
+        int dest_logical;
+        unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
+        unsigned long (*check_apicid_present)(int apicid);
+
+        void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
+        void (*init_apic_ldr)(void);
+
+        physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
+
+        void (*setup_apic_routing)(void);
+        int (*multi_timer_check)(int apic, int irq);
+        int (*apicid_to_node)(int logical_apicid);
+        int (*cpu_to_logical_apicid)(int cpu);
+        int (*cpu_present_to_apicid)(int mps_cpu);
+        physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
+        void (*setup_portio_remap)(void);
+        int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
+        void (*enable_apic_mode)(void);
+        int (*phys_pkg_id)(int cpuid_apic, int index_msb);
+
+        /*
+         * When one of the next two hooks returns 1 the apic
+         * is switched to this. Essentially they are additional
+         * probe functions:
+         */
+        int (*mps_oem_check)(struct mpc_table *mpc, char *oem, char *productid);
+
+        unsigned int (*get_apic_id)(unsigned long x);
+        unsigned long (*set_apic_id)(unsigned int id);
+        unsigned long apic_id_mask;
+
+        unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
+        unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
+                                               const struct cpumask *andmask);
+
+        /* ipi */
+        void (*send_IPI_mask)(const struct cpumask *mask, int vector);
+        void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
+                                         int vector);
+        void (*send_IPI_allbutself)(int vector);
+        void (*send_IPI_all)(int vector);
+        void (*send_IPI_self)(int vector);
+
+        /* wakeup_secondary_cpu */
+        int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
+
+        int trampoline_phys_low;
+        int trampoline_phys_high;
+
+        void (*wait_for_init_deassert)(atomic_t *deassert);
+        void (*smp_callin_clear_local_apic)(void);
+        void (*inquire_remote_apic)(int apicid);
+
+        /* apic ops */
+        u32 (*read)(u32 reg);
+        void (*write)(u32 reg, u32 v);
+        u64 (*icr_read)(void);
+        void (*icr_write)(u32 low, u32 high);
+        void (*wait_icr_idle)(void);
+        u32 (*safe_wait_icr_idle)(void);
+};
+
+/*
+ * Pointer to the local APIC driver in use on this system (there's
+ * always just one such driver in use - the kernel decides via an
+ * early probing process which one it picks - and then sticks to it):
+ */
+extern struct apic *apic;
+
+/*
+ * APIC functionality to boot other CPUs - only used on SMP:
+ */
+#ifdef CONFIG_SMP
+extern atomic_t init_deasserted;
+extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
+#endif
+
+static inline u32 apic_read(u32 reg)
+{
+        return apic->read(reg);
+}
+
+static inline void apic_write(u32 reg, u32 val)
+{
+        apic->write(reg, val);
+}
+
+static inline u64 apic_icr_read(void)
+{
+        return apic->icr_read();
+}
+
+static inline void apic_icr_write(u32 low, u32 high)
+{
+        apic->icr_write(low, high);
+}
+
+static inline void apic_wait_icr_idle(void)
+{
+        apic->wait_icr_idle();
+}
+
+static inline u32 safe_apic_wait_icr_idle(void)
+{
+        return apic->safe_wait_icr_idle();
+}
+
+
+static inline void ack_APIC_irq(void)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+        /*
+         * ack_APIC_irq() actually gets compiled as a single instruction
+         * ... yummie.
+         */
+
+        /* Docs say use 0 for future compatibility */
+        apic_write(APIC_EOI, 0);
+#endif
+}
+
+static inline unsigned default_get_apic_id(unsigned long x)
+{
+        unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
+
+        if (APIC_XAPIC(ver))
+                return (x >> 24) & 0xFF;
+        else
+                return (x >> 24) & 0x0F;
+}
+
+/*
+ * Warm reset vector default position:
+ */
+#define DEFAULT_TRAMPOLINE_PHYS_LOW             0x467
+#define DEFAULT_TRAMPOLINE_PHYS_HIGH            0x469
+
+#ifdef CONFIG_X86_64
+extern struct apic apic_flat;
+extern struct apic apic_physflat;
+extern struct apic apic_x2apic_cluster;
+extern struct apic apic_x2apic_phys;
+extern int default_acpi_madt_oem_check(char *, char *);
+
+extern void apic_send_IPI_self(int vector);
+
+extern struct apic apic_x2apic_uv_x;
+DECLARE_PER_CPU(int, x2apic_extra_bits);
+
+extern int default_cpu_present_to_apicid(int mps_cpu);
+extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid);
+#endif
+
+static inline void default_wait_for_init_deassert(atomic_t *deassert)
+{
+        while (!atomic_read(deassert))
+                cpu_relax();
+        return;
+}
+
+extern void generic_bigsmp_probe(void);
+
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+#include <asm/smp.h>
+
+#define APIC_DFR_VALUE  (APIC_DFR_FLAT)
+
+static inline const struct cpumask *default_target_cpus(void)
+{
+#ifdef CONFIG_SMP
+        return cpu_online_mask;
+#else
+        return cpumask_of(0);
+#endif
+}
+
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+
+
+static inline unsigned int read_apic_id(void)
+{
+        unsigned int reg;
+
+        reg = apic_read(APIC_ID);
+
+        return apic->get_apic_id(reg);
+}
+
+extern void default_setup_apic_routing(void);
+
+#ifdef CONFIG_X86_32
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116).  So here it goes...
+ */
+extern void default_init_apic_ldr(void);
+
+static inline int default_apic_id_registered(void)
+{
+        return physid_isset(read_apic_id(), phys_cpu_present_map);
+}
+
+static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+        return cpuid_apic >> index_msb;
+}
+
+extern int default_apicid_to_node(int logical_apicid);
+
+#endif
+
+static inline unsigned int
+default_cpu_mask_to_apicid(const struct cpumask *cpumask)
+{
+        return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS;
+}
+
+static inline unsigned int
+default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+                               const struct cpumask *andmask)
+{
+        unsigned long mask1 = cpumask_bits(cpumask)[0];
+        unsigned long mask2 = cpumask_bits(andmask)[0];
+        unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
+
+        return (unsigned int)(mask1 & mask2 & mask3);
+}
+
+static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+        return physid_isset(apicid, bitmap);
+}
+
+static inline unsigned long default_check_apicid_present(int bit)
+{
+        return physid_isset(bit, phys_cpu_present_map);
+}
+
+static inline physid_mask_t default_ioapic_phys_id_map(physid_mask_t phys_map)
+{
+        return phys_map;
+}
+
+/* Mapping from cpu number to logical apicid */
+static inline int default_cpu_to_logical_apicid(int cpu)
+{
+        return 1 << cpu;
+}
+
+static inline int __default_cpu_present_to_apicid(int mps_cpu)
+{
+        if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
+                return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
+        else
+                return BAD_APICID;
+}
+
+static inline int
+__default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+        return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
+}
+
+#ifdef CONFIG_X86_32
+static inline int default_cpu_present_to_apicid(int mps_cpu)
+{
+        return __default_cpu_present_to_apicid(mps_cpu);
+}
+
+static inline int
+default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+        return __default_check_phys_apicid_present(boot_cpu_physical_apicid);
+}
+#else
+extern int default_cpu_present_to_apicid(int mps_cpu);
+extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid);
+#endif
+
+static inline physid_mask_t default_apicid_to_cpu_present(int phys_apicid)
+{
+        return physid_mask_of_physid(phys_apicid);
+}
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#ifdef CONFIG_X86_32
+extern u8 cpu_2_logical_apicid[NR_CPUS];
+#endif
+
 #endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 63134e31e8b9..bc9514fb3b13 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -53,6 +53,7 @@
 #define         APIC_ESR_SENDILL        0x00020
 #define         APIC_ESR_RECVILL        0x00040
 #define         APIC_ESR_ILLREGA        0x00080
+#define         APIC_LVTCMCI    0x2f0
 #define APIC_ICR        0x300
 #define         APIC_DEST_SELF          0x40000
 #define         APIC_DEST_ALLINC        0x80000
diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h
new file mode 100644
index 000000000000..82f613c607ce
--- /dev/null
+++ b/arch/x86/include/asm/apicnum.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_APICNUM_H
+#define _ASM_X86_APICNUM_H
+
+/* define MAX_IO_APICS */
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+#endif /* _ASM_X86_APICNUM_H */
diff --git a/arch/x86/include/asm/mach-default/apm.h b/arch/x86/include/asm/apm.h
index 20370c6db74b..20370c6db74b 100644
--- a/arch/x86/include/asm/mach-default/apm.h
+++ b/arch/x86/include/asm/apm.h
diff --git a/arch/x86/include/asm/arch_hooks.h b/arch/x86/include/asm/arch_hooks.h
deleted file mode 100644
index cbd4957838a6..000000000000
--- a/arch/x86/include/asm/arch_hooks.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef _ASM_X86_ARCH_HOOKS_H
-#define _ASM_X86_ARCH_HOOKS_H
-
-#include <linux/interrupt.h>
-
-/*
- *      linux/include/asm/arch_hooks.h
- *
- *      define the architecture specific hooks
- */
-
-/* these aren't arch hooks, they are generic routines
- * that can be used by the hooks */
-extern void init_ISA_irqs(void);
-extern irqreturn_t timer_interrupt(int irq, void *dev_id);
-
-/* these are the defined hooks */
-extern void intr_init_hook(void);
-extern void pre_intr_init_hook(void);
-extern void pre_setup_arch_hook(void);
-extern void trap_init_hook(void);
-extern void pre_time_init_hook(void);
-extern void time_init_hook(void);
-extern void mca_nmi_hook(void);
-
-#endif /* _ASM_X86_ARCH_HOOKS_H */
diff --git a/arch/x86/include/asm/bigsmp/apic.h b/arch/x86/include/asm/bigsmp/apic.h
deleted file mode 100644
index d8dd9f537911..000000000000
--- a/arch/x86/include/asm/bigsmp/apic.h
+++ /dev/null
@@ -1,155 +0,0 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
-
-#define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu))
-#define esr_disable (1)
-
-static inline int apic_id_registered(void)
-{
-        return (1);
-}
-
-static inline const cpumask_t *target_cpus(void)
-{
-#ifdef CONFIG_SMP
-        return &cpu_online_map;
-#else
-        return &cpumask_of_cpu(0);
-#endif
-}
-
-#undef APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL       0
-#define APIC_DFR_VALUE          (APIC_DFR_FLAT)
-#define INT_DELIVERY_MODE       (dest_Fixed)
-#define INT_DEST_MODE           (0)    /* phys delivery to target proc */
-#define NO_BALANCE_IRQ          (0)
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-        return (0);
-}
-
-static inline unsigned long check_apicid_present(int bit)
-{
-        return (1);
-}
-
-static inline unsigned long calculate_ldr(int cpu)
-{
-        unsigned long val, id;
-        val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-        id = xapic_phys_to_log_apicid(cpu);
-        val |= SET_APIC_LOGICAL_ID(id);
-        return val;
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-        unsigned long val;
-        int cpu = smp_processor_id();
-
-        apic_write(APIC_DFR, APIC_DFR_VALUE);
-        val = calculate_ldr(cpu);
-        apic_write(APIC_LDR, val);
-}
-
-static inline void setup_apic_routing(void)
-{
-        printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-                "Physflat", nr_ioapics);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-        return (0);
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-        return apicid_2_node[hard_smp_processor_id()];
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-        if (mps_cpu < nr_cpu_ids)
-                return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
-
-        return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-        return physid_mask_of_physid(phys_apicid);
-}
-
-extern u8 cpu_2_logical_apicid[];
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-        if (cpu >= nr_cpu_ids)
-                return BAD_APICID;
-        return cpu_physical_id(cpu);
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-        /* For clustered we don't have a good way to do this yet - hack */
-        return physids_promote(0xFFL);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-        return (1);
-}
-
-/* As we are using single CPU as destination, pick only one CPU here */
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-        int cpu;
-        int apicid;     
-
-        cpu = first_cpu(*cpumask);
-        apicid = cpu_to_logical_apicid(cpu);
-        return apicid;
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-                                                  const struct cpumask *andmask)
-{
-        int cpu;
-
-        /*
-         * We're using fixed IRQ delivery, can only return one phys APIC ID.
-         * May as well be the first.
-         */
-        for_each_cpu_and(cpu, cpumask, andmask)
-                if (cpumask_test_cpu(cpu, cpu_online_mask))
-                        break;
-        if (cpu < nr_cpu_ids)
-                return cpu_to_logical_apicid(cpu);
-
-        return BAD_APICID;
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-        return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_MACH_APIC_H */
diff --git a/arch/x86/include/asm/bigsmp/apicdef.h b/arch/x86/include/asm/bigsmp/apicdef.h
deleted file mode 100644
index 392c3f5ef2fe..000000000000
--- a/arch/x86/include/asm/bigsmp/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
-
-#define         APIC_ID_MASK            (0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-        return (((x)>>24)&0xFF);
-}
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/arch/x86/include/asm/bigsmp/ipi.h b/arch/x86/include/asm/bigsmp/ipi.h
deleted file mode 100644
index 27fcd01b3ae6..000000000000
--- a/arch/x86/include/asm/bigsmp/ipi.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
-
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-        send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-        send_IPI_mask_allbutself(cpu_online_mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-        send_IPI_mask(cpu_online_mask, vector);
-}
-
-#endif /* __ASM_MACH_IPI_H */
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index dd61616cb73d..6ba23dd9fc92 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -1,26 +1,36 @@
 #ifndef _ASM_X86_BOOT_H
 #define _ASM_X86_BOOT_H
 
-/* Don't touch these, unless you really know what you're doing. */
-#define DEF_SYSSEG      0x1000
-#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 */
 
+#ifdef __KERNEL__
+
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
                                 + (CONFIG_PHYSICAL_ALIGN - 1)) \
                                 & ~(CONFIG_PHYSICAL_ALIGN - 1))
 
+#ifdef CONFIG_KERNEL_BZIP2
+#define BOOT_HEAP_SIZE             0x400000
+#else /* !CONFIG_KERNEL_BZIP2 */
+
 #ifdef CONFIG_X86_64
 #define BOOT_HEAP_SIZE  0x7000
-#define BOOT_STACK_SIZE 0x4000
 #else
 #define BOOT_HEAP_SIZE  0x4000
+#endif
+
+#endif /* !CONFIG_KERNEL_BZIP2 */
+
+#ifdef CONFIG_X86_64
+#define BOOT_STACK_SIZE 0x4000
+#else
 #define BOOT_STACK_SIZE 0x1000
 #endif
 
+#endif /* __KERNEL__ */
+
 #endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 2f8466540fb5..b3894bf52fcd 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -5,24 +5,43 @@
 #include <linux/mm.h>
 
 /* Caches aren't brain-dead on the intel. */
-#define flush_cache_all()                       do { } while (0)
-#define flush_cache_mm(mm)                      do { } while (0)
-#define flush_cache_dup_mm(mm)                  do { } while (0)
-#define flush_cache_range(vma, start, end)      do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)      do { } while (0)
-#define flush_dcache_page(page)                 do { } while (0)
-#define flush_dcache_mmap_lock(mapping)         do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)       do { } while (0)
-#define flush_icache_range(start, end)          do { } while (0)
-#define flush_icache_page(vma, pg)              do { } while (0)
-#define flush_icache_user_range(vma, pg, adr, len)      do { } while (0)
-#define flush_cache_vmap(start, end)            do { } while (0)
-#define flush_cache_vunmap(start, end)          do { } while (0)
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len)      \
-        memcpy((dst), (src), (len))
-#define copy_from_user_page(vma, page, vaddr, dst, src, len)    \
-        memcpy((dst), (src), (len))
+static inline void flush_cache_all(void) { }
+static inline void flush_cache_mm(struct mm_struct *mm) { }
+static inline void flush_cache_dup_mm(struct mm_struct *mm) { }
+static inline void flush_cache_range(struct vm_area_struct *vma,
+                                     unsigned long start, unsigned long end) { }
+static inline void flush_cache_page(struct vm_area_struct *vma,
+                                    unsigned long vmaddr, unsigned long pfn) { }
+static inline void flush_dcache_page(struct page *page) { }
+static inline void flush_dcache_mmap_lock(struct address_space *mapping) { }
+static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { }
+static inline void flush_icache_range(unsigned long start,
+                                      unsigned long end) { }
+static inline void flush_icache_page(struct vm_area_struct *vma,
+                                     struct page *page) { }
+static inline void flush_icache_user_range(struct vm_area_struct *vma,
+                                           struct page *page,
+                                           unsigned long addr,
+                                           unsigned long len) { }
+static inline void flush_cache_vmap(unsigned long start, unsigned long end) { }
+static inline void flush_cache_vunmap(unsigned long start,
+                                      unsigned long end) { }
+
+static inline void copy_to_user_page(struct vm_area_struct *vma,
+                                     struct page *page, unsigned long vaddr,
+                                     void *dst, const void *src,
+                                     unsigned long len)
+{
+        memcpy(dst, src, len);
+}
+
+static inline void copy_from_user_page(struct vm_area_struct *vma,
+                                       struct page *page, unsigned long vaddr,
+                                       void *dst, const void *src,
+                                       unsigned long len)
+{
+        memcpy(dst, src, len);
+}
 
 #define PG_non_WB                               PG_arch_1
 PAGEFLAG(NonWB, non_WB)
@@ -71,6 +90,9 @@ int set_memory_4k(unsigned long addr, int numpages);
 int set_memory_array_uc(unsigned long *addr, int addrinarray);
 int set_memory_array_wb(unsigned long *addr, int addrinarray);
 
+int set_pages_array_uc(struct page **pages, int addrinarray);
+int set_pages_array_wb(struct page **pages, int addrinarray);
+
 /*
  * For legacy compatibility with the old APIs, a few functions
  * are provided that work on a "struct page".
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 2bc162e0ec6e..0e63c9a2a8d0 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -1,5 +1,55 @@
 /*
- * Some macros to handle stack frames in assembly.
+
+ x86 function call convention, 64-bit:
+ -------------------------------------
+  arguments           |  callee-saved      | extra caller-saved | return
+ [callee-clobbered]   |                    | [callee-clobbered] |
+ ---------------------------------------------------------------------------
+ rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11             | rax, rdx [**]
+
+ ( rsp is obviously invariant across normal function calls. (gcc can 'merge'
+   functions when it sees tail-call optimization possibilities) rflags is
+   clobbered. Leftover arguments are passed over the stack frame.)
+
+ [*]  In the frame-pointers case rbp is fixed to the stack frame.
+
+ [**] for struct return values wider than 64 bits the return convention is a
+      bit more complex: up to 128 bits width we return small structures
+      straight in rax, rdx. For structures larger than that (3 words or
+      larger) the caller puts a pointer to an on-stack return struct
+      [allocated in the caller's stack frame] into the first argument - i.e.
+      into rdi. All other arguments shift up by one in this case.
+      Fortunately this case is rare in the kernel.
+
+For 32-bit we have the following conventions - kernel is built with
+-mregparm=3 and -freg-struct-return:
+
+ x86 function calling convention, 32-bit:
+ ----------------------------------------
+  arguments         | callee-saved        | extra caller-saved | return
+ [callee-clobbered] |                     | [callee-clobbered] |
+ -------------------------------------------------------------------------
+ eax edx ecx        | ebx edi esi ebp [*] | <none>             | eax, edx [**]
+
+ ( here too esp is obviously invariant across normal function calls. eflags
+   is clobbered. Leftover arguments are passed over the stack frame. )
+
+ [*]  In the frame-pointers case ebp is fixed to the stack frame.
+
+ [**] We build with -freg-struct-return, which on 32-bit means similar
+      semantics as on 64-bit: edx can be used for a second return value
+      (i.e. covering integer and structure sizes up to 64 bits) - after that
+      it gets more complex and more expensive: 3-word or larger struct returns
+      get done in the caller's frame and the pointer to the return struct goes
+      into regparm0, i.e. eax - the other arguments shift up and the
+      function's register parameters degenerate to regparm=2 in essence.
+
+*/
+
+
+/*
+ * 64-bit system call stack frame layout defines and helpers,
+ * for assembly code:
  */
 
 #define R15               0
@@ -9,7 +59,7 @@
 #define RBP              32
 #define RBX              40
 
-/* arguments: interrupts/non tracing syscalls only save upto here*/
+/* arguments: interrupts/non tracing syscalls only save up to here: */
 #define R11              48
 #define R10              56
 #define R9               64
@@ -22,7 +72,7 @@
 #define ORIG_RAX        120       /* + error_code */
 /* end of arguments */
 
-/* cpu exception frame or undefined in case of fast syscall. */
+/* cpu exception frame or undefined in case of fast syscall: */
 #define RIP             128
 #define CS              136
 #define EFLAGS          144
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index bae482df6039..b185091bf19c 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -7,6 +7,20 @@
 #include <linux/nodemask.h>
 #include <linux/percpu.h>
 
+#ifdef CONFIG_SMP
+
+extern void prefill_possible_map(void);
+
+#else /* CONFIG_SMP */
+
+static inline void prefill_possible_map(void) {}
+
+#define cpu_physical_id(cpu)                    boot_cpu_physical_apicid
+#define safe_smp_processor_id()                 0
+#define stack_smp_processor_id()                0
+
+#endif /* CONFIG_SMP */
+
 struct x86_cpu {
         struct cpu cpu;
 };
@@ -17,4 +31,7 @@ extern void arch_unregister_cpu(int);
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
+
+extern unsigned int boot_cpu_id;
+
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
new file mode 100755
index 000000000000..222802029fa6
--- /dev/null
+++ b/arch/x86/include/asm/cpu_debug.h
@@ -0,0 +1,226 @@
+#ifndef _ASM_X86_CPU_DEBUG_H
+#define _ASM_X86_CPU_DEBUG_H
+
+/*
+ * CPU x86 architecture debug
+ *
+ * Copyright(C) 2009 Jaswinder Singh Rajput
+ */
+
+/* Register flags */
+enum cpu_debug_bit {
+/* Model Specific Registers (MSRs)                                      */
+        CPU_MC_BIT,                             /* Machine Check        */
+        CPU_MONITOR_BIT,                        /* Monitor              */
+        CPU_TIME_BIT,                           /* Time                 */
+        CPU_PMC_BIT,                            /* Performance Monitor  */
+        CPU_PLATFORM_BIT,                       /* Platform             */
+        CPU_APIC_BIT,                           /* APIC                 */
+        CPU_POWERON_BIT,                        /* Power-on             */
+        CPU_CONTROL_BIT,                        /* Control              */
+        CPU_FEATURES_BIT,                       /* Features control     */
+        CPU_LBRANCH_BIT,                        /* Last Branch          */
+        CPU_BIOS_BIT,                           /* BIOS                 */
+        CPU_FREQ_BIT,                           /* Frequency            */
+        CPU_MTTR_BIT,                           /* MTRR                 */
+        CPU_PERF_BIT,                           /* Performance          */
+        CPU_CACHE_BIT,                          /* Cache                */
+        CPU_SYSENTER_BIT,                       /* Sysenter             */
+        CPU_THERM_BIT,                          /* Thermal              */
+        CPU_MISC_BIT,                           /* Miscellaneous        */
+        CPU_DEBUG_BIT,                          /* Debug                */
+        CPU_PAT_BIT,                            /* PAT                  */
+        CPU_VMX_BIT,                            /* VMX                  */
+        CPU_CALL_BIT,                           /* System Call          */
+        CPU_BASE_BIT,                           /* BASE Address         */
+        CPU_VER_BIT,                            /* Version ID           */
+        CPU_CONF_BIT,                           /* Configuration        */
+        CPU_SMM_BIT,                            /* System mgmt mode     */
+        CPU_SVM_BIT,                            /*Secure Virtual Machine*/
+        CPU_OSVM_BIT,                           /* OS-Visible Workaround*/
+/* Standard Registers                                                   */
+        CPU_TSS_BIT,                            /* Task Stack Segment   */
+        CPU_CR_BIT,                             /* Control Registers    */
+        CPU_DT_BIT,                             /* Descriptor Table     */
+/* End of Registers flags                                               */
+        CPU_REG_ALL_BIT,                        /* Select all Registers */
+};
+
+#define CPU_REG_ALL             (~0)            /* Select all Registers */
+
+#define CPU_MC                  (1 << CPU_MC_BIT)
+#define CPU_MONITOR             (1 << CPU_MONITOR_BIT)
+#define CPU_TIME                (1 << CPU_TIME_BIT)
+#define CPU_PMC                 (1 << CPU_PMC_BIT)
+#define CPU_PLATFORM            (1 << CPU_PLATFORM_BIT)
+#define CPU_APIC                (1 << CPU_APIC_BIT)
+#define CPU_POWERON             (1 << CPU_POWERON_BIT)
+#define CPU_CONTROL             (1 << CPU_CONTROL_BIT)
+#define CPU_FEATURES            (1 << CPU_FEATURES_BIT)
+#define CPU_LBRANCH             (1 << CPU_LBRANCH_BIT)
+#define CPU_BIOS                (1 << CPU_BIOS_BIT)
+#define CPU_FREQ                (1 << CPU_FREQ_BIT)
+#define CPU_MTRR                (1 << CPU_MTTR_BIT)
+#define CPU_PERF                (1 << CPU_PERF_BIT)
+#define CPU_CACHE               (1 << CPU_CACHE_BIT)
+#define CPU_SYSENTER            (1 << CPU_SYSENTER_BIT)
+#define CPU_THERM               (1 << CPU_THERM_BIT)
+#define CPU_MISC                (1 << CPU_MISC_BIT)
+#define CPU_DEBUG               (1 << CPU_DEBUG_BIT)
+#define CPU_PAT                 (1 << CPU_PAT_BIT)
+#define CPU_VMX                 (1 << CPU_VMX_BIT)
+#define CPU_CALL                (1 << CPU_CALL_BIT)
+#define CPU_BASE                (1 << CPU_BASE_BIT)
+#define CPU_VER                 (1 << CPU_VER_BIT)
+#define CPU_CONF                (1 << CPU_CONF_BIT)
+#define CPU_SMM                 (1 << CPU_SMM_BIT)
+#define CPU_SVM                 (1 << CPU_SVM_BIT)
+#define CPU_OSVM                (1 << CPU_OSVM_BIT)
+#define CPU_TSS                 (1 << CPU_TSS_BIT)
+#define CPU_CR                  (1 << CPU_CR_BIT)
+#define CPU_DT                  (1 << CPU_DT_BIT)
+
+/* Register file flags */
+enum cpu_file_bit {
+        CPU_INDEX_BIT,                          /* index                */
+        CPU_VALUE_BIT,                          /* value                */
+};
+
+#define CPU_FILE_VALUE                  (1 << CPU_VALUE_BIT)
+
+/*
+ * DisplayFamily_DisplayModel   Processor Families/Processor Number Series
+ * --------------------------   ------------------------------------------
+ * 05_01, 05_02, 05_04          Pentium, Pentium with MMX
+ *
+ * 06_01                        Pentium Pro
+ * 06_03, 06_05                 Pentium II Xeon, Pentium II
+ * 06_07, 06_08, 06_0A, 06_0B   Pentium III Xeon, Pentum III
+ *
+ * 06_09, 060D                  Pentium M
+ *
+ * 06_0E                        Core Duo, Core Solo
+ *
+ * 06_0F                        Xeon 3000, 3200, 5100, 5300, 7300 series,
+ *                              Core 2 Quad, Core 2 Extreme, Core 2 Duo,
+ *                              Pentium dual-core
+ * 06_17                        Xeon 5200, 5400 series, Core 2 Quad Q9650
+ *
+ * 06_1C                        Atom
+ *
+ * 0F_00, 0F_01, 0F_02          Xeon, Xeon MP, Pentium 4
+ * 0F_03, 0F_04                 Xeon, Xeon MP, Pentium 4, Pentium D
+ *
+ * 0F_06                        Xeon 7100, 5000 Series, Xeon MP,
+ *                              Pentium 4, Pentium D
+ */
+
+/* Register processors bits */
+enum cpu_processor_bit {
+        CPU_NONE,
+/* Intel */
+        CPU_INTEL_PENTIUM_BIT,
+        CPU_INTEL_P6_BIT,
+        CPU_INTEL_PENTIUM_M_BIT,
+        CPU_INTEL_CORE_BIT,
+        CPU_INTEL_CORE2_BIT,
+        CPU_INTEL_ATOM_BIT,
+        CPU_INTEL_XEON_P4_BIT,
+        CPU_INTEL_XEON_MP_BIT,
+/* AMD */
+        CPU_AMD_K6_BIT,
+        CPU_AMD_K7_BIT,
+        CPU_AMD_K8_BIT,
+        CPU_AMD_0F_BIT,
+        CPU_AMD_10_BIT,
+        CPU_AMD_11_BIT,
+};
+
+#define CPU_INTEL_PENTIUM       (1 << CPU_INTEL_PENTIUM_BIT)
+#define CPU_INTEL_P6            (1 << CPU_INTEL_P6_BIT)
+#define CPU_INTEL_PENTIUM_M     (1 << CPU_INTEL_PENTIUM_M_BIT)
+#define CPU_INTEL_CORE          (1 << CPU_INTEL_CORE_BIT)
+#define CPU_INTEL_CORE2         (1 << CPU_INTEL_CORE2_BIT)
+#define CPU_INTEL_ATOM          (1 << CPU_INTEL_ATOM_BIT)
+#define CPU_INTEL_XEON_P4       (1 << CPU_INTEL_XEON_P4_BIT)
+#define CPU_INTEL_XEON_MP       (1 << CPU_INTEL_XEON_MP_BIT)
+
+#define CPU_INTEL_PX            (CPU_INTEL_P6 | CPU_INTEL_PENTIUM_M)
+#define CPU_INTEL_COREX         (CPU_INTEL_CORE | CPU_INTEL_CORE2)
+#define CPU_INTEL_XEON          (CPU_INTEL_XEON_P4 | CPU_INTEL_XEON_MP)
+#define CPU_CO_AT               (CPU_INTEL_CORE | CPU_INTEL_ATOM)
+#define CPU_C2_AT               (CPU_INTEL_CORE2 | CPU_INTEL_ATOM)
+#define CPU_CX_AT               (CPU_INTEL_COREX | CPU_INTEL_ATOM)
+#define CPU_CX_XE               (CPU_INTEL_COREX | CPU_INTEL_XEON)
+#define CPU_P6_XE               (CPU_INTEL_P6 | CPU_INTEL_XEON)
+#define CPU_PM_CO_AT            (CPU_INTEL_PENTIUM_M | CPU_CO_AT)
+#define CPU_C2_AT_XE            (CPU_C2_AT | CPU_INTEL_XEON)
+#define CPU_CX_AT_XE            (CPU_CX_AT | CPU_INTEL_XEON)
+#define CPU_P6_CX_AT            (CPU_INTEL_P6 | CPU_CX_AT)
+#define CPU_P6_CX_XE            (CPU_P6_XE | CPU_INTEL_COREX)
+#define CPU_P6_CX_AT_XE         (CPU_INTEL_P6 | CPU_CX_AT_XE)
+#define CPU_PM_CX_AT_XE         (CPU_INTEL_PENTIUM_M | CPU_CX_AT_XE)
+#define CPU_PM_CX_AT            (CPU_INTEL_PENTIUM_M | CPU_CX_AT)
+#define CPU_PM_CX_XE            (CPU_INTEL_PENTIUM_M | CPU_CX_XE)
+#define CPU_PX_CX_AT            (CPU_INTEL_PX | CPU_CX_AT)
+#define CPU_PX_CX_AT_XE         (CPU_INTEL_PX | CPU_CX_AT_XE)
+
+/* Select all supported Intel CPUs */
+#define CPU_INTEL_ALL           (CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE)
+
+#define CPU_AMD_K6              (1 << CPU_AMD_K6_BIT)
+#define CPU_AMD_K7              (1 << CPU_AMD_K7_BIT)
+#define CPU_AMD_K8              (1 << CPU_AMD_K8_BIT)
+#define CPU_AMD_0F              (1 << CPU_AMD_0F_BIT)
+#define CPU_AMD_10              (1 << CPU_AMD_10_BIT)
+#define CPU_AMD_11              (1 << CPU_AMD_11_BIT)
+
+#define CPU_K10_PLUS            (CPU_AMD_10 | CPU_AMD_11)
+#define CPU_K0F_PLUS            (CPU_AMD_0F | CPU_K10_PLUS)
+#define CPU_K8_PLUS             (CPU_AMD_K8 | CPU_K0F_PLUS)
+#define CPU_K7_PLUS             (CPU_AMD_K7 | CPU_K8_PLUS)
+
+/* Select all supported AMD CPUs */
+#define CPU_AMD_ALL             (CPU_AMD_K6 | CPU_K7_PLUS)
+
+/* Select all supported CPUs */
+#define CPU_ALL                 (CPU_INTEL_ALL | CPU_AMD_ALL)
+
+#define MAX_CPU_FILES           512
+
+struct cpu_private {
+        unsigned                cpu;
+        unsigned                type;
+        unsigned                reg;
+        unsigned                file;
+};
+
+struct cpu_debug_base {
+        char                    *name;          /* Register name        */
+        unsigned                flag;           /* Register flag        */
+        unsigned                write;          /* Register write flag  */
+};
+
+/*
+ * Currently it looks similar to cpu_debug_base but once we add more files
+ * cpu_file_base will go in different direction
+ */
+struct cpu_file_base {
+        char                    *name;          /* Register file name   */
+        unsigned                flag;           /* Register file flag   */
+        unsigned                write;          /* Register write flag  */
+};
+
+struct cpu_cpuX_base {
+        struct dentry           *dentry;        /* Register dentry      */
+        int                     init;           /* Register index file  */
+};
+
+struct cpu_debug_range {
+        unsigned                min;            /* Register range min   */
+        unsigned                max;            /* Register range max   */
+        unsigned                flag;           /* Supported flags      */
+        unsigned                model;          /* Supported models     */
+};
+
+#endif /* _ASM_X86_CPU_DEBUG_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 7301e60dc4a8..0beba0d1468d 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -213,6 +213,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xmm             boot_cpu_has(X86_FEATURE_XMM)
 #define cpu_has_xmm2            boot_cpu_has(X86_FEATURE_XMM2)
 #define cpu_has_xmm3            boot_cpu_has(X86_FEATURE_XMM3)
+#define cpu_has_aes             boot_cpu_has(X86_FEATURE_AES)
 #define cpu_has_ht              boot_cpu_has(X86_FEATURE_HT)
 #define cpu_has_mp              boot_cpu_has(X86_FEATURE_MP)
 #define cpu_has_nx              boot_cpu_has(X86_FEATURE_NX)
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
new file mode 100644
index 000000000000..a7f3c75f8ad7
--- /dev/null
+++ b/arch/x86/include/asm/cpumask.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_X86_CPUMASK_H
+#define _ASM_X86_CPUMASK_H
+#ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_X86_64
+
+extern cpumask_var_t cpu_callin_mask;
+extern cpumask_var_t cpu_callout_mask;
+extern cpumask_var_t cpu_initialized_mask;
+extern cpumask_var_t cpu_sibling_setup_mask;
+
+extern void setup_cpu_local_masks(void);
+
+#else /* CONFIG_X86_32 */
+
+extern cpumask_t cpu_callin_map;
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_initialized;
+extern cpumask_t cpu_sibling_setup_map;
+
+#define cpu_callin_mask         ((struct cpumask *)&cpu_callin_map)
+#define cpu_callout_mask        ((struct cpumask *)&cpu_callout_map)
+#define cpu_initialized_mask    ((struct cpumask *)&cpu_initialized)
+#define cpu_sibling_setup_mask  ((struct cpumask *)&cpu_sibling_setup_map)
+
+static inline void setup_cpu_local_masks(void) { }
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 0930b4f8d672..c68c361697e1 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -1,39 +1,21 @@
 #ifndef _ASM_X86_CURRENT_H
 #define _ASM_X86_CURRENT_H
 
-#ifdef CONFIG_X86_32
 #include <linux/compiler.h>
 #include <asm/percpu.h>
 
+#ifndef __ASSEMBLY__
 struct task_struct;
 
 DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
-        return x86_read_percpu(current_task);
-}
-
-#else /* X86_32 */
-
-#ifndef __ASSEMBLY__
-#include <asm/pda.h>
-
-struct task_struct;
 
 static __always_inline struct task_struct *get_current(void)
 {
-        return read_pda(pcurrent);
+        return percpu_read(current_task);
 }
 
-#else /* __ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
+#define current get_current()
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* X86_32 */
-
-#define current get_current()
-
 #endif /* _ASM_X86_CURRENT_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index dc27705f5443..5623c50d67b2 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -91,7 +91,6 @@ static inline int desc_empty(const void *ptr)
 #define store_gdt(dtr) native_store_gdt(dtr)
 #define store_idt(dtr) native_store_idt(dtr)
 #define store_tr(tr) (tr = native_store_tr())
-#define store_ldt(ldt) asm("sldt %0":"=m" (ldt))
 
 #define load_TLS(t, cpu) native_load_tls(t, cpu)
 #define set_ldt native_set_ldt
@@ -112,6 +111,8 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
 }
 #endif  /* CONFIG_PARAVIRT */
 
+#define store_ldt(ldt) asm("sldt %0" : "=m"(ldt))
+
 static inline void native_write_idt_entry(gate_desc *idt, int entry,
                                           const gate_desc *gate)
 {
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 3c034f48fdb0..4994a20acbcb 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -6,7 +6,7 @@ struct dev_archdata {
         void    *acpi_handle;
 #endif
 #ifdef CONFIG_X86_64
-struct dma_mapping_ops *dma_ops;
+struct dma_map_ops *dma_ops;
 #endif
 #ifdef CONFIG_DMAR
         void *iommu; /* hook for IOMMU specific extension */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 132a134d12f2..cea7b74963e9 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -7,6 +7,8 @@
  */
 
 #include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
+#include <linux/dma-attrs.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
@@ -16,47 +18,9 @@ extern int iommu_merge;
 extern struct device x86_dma_fallback_dev;
 extern int panic_on_overflow;
 
-struct dma_mapping_ops {
-        int             (*mapping_error)(struct device *dev,
-                                         dma_addr_t dma_addr);
-        void*           (*alloc_coherent)(struct device *dev, size_t size,
-                                dma_addr_t *dma_handle, gfp_t gfp);
-        void            (*free_coherent)(struct device *dev, size_t size,
-                                void *vaddr, dma_addr_t dma_handle);
-        dma_addr_t      (*map_single)(struct device *hwdev, phys_addr_t ptr,
-                                size_t size, int direction);
-        void            (*unmap_single)(struct device *dev, dma_addr_t addr,
-                                size_t size, int direction);
-        void            (*sync_single_for_cpu)(struct device *hwdev,
-                                dma_addr_t dma_handle, size_t size,
-                                int direction);
-        void            (*sync_single_for_device)(struct device *hwdev,
-                                dma_addr_t dma_handle, size_t size,
-                                int direction);
-        void            (*sync_single_range_for_cpu)(struct device *hwdev,
-                                dma_addr_t dma_handle, unsigned long offset,
-                                size_t size, int direction);
-        void            (*sync_single_range_for_device)(struct device *hwdev,
-                                dma_addr_t dma_handle, unsigned long offset,
-                                size_t size, int direction);
-        void            (*sync_sg_for_cpu)(struct device *hwdev,
-                                struct scatterlist *sg, int nelems,
-                                int direction);
-        void            (*sync_sg_for_device)(struct device *hwdev,
-                                struct scatterlist *sg, int nelems,
-                                int direction);
-        int             (*map_sg)(struct device *hwdev, struct scatterlist *sg,
-                                int nents, int direction);
-        void            (*unmap_sg)(struct device *hwdev,
-                                struct scatterlist *sg, int nents,
-                                int direction);
-        int             (*dma_supported)(struct device *hwdev, u64 mask);
-        int             is_phys;
-};
-
-extern struct dma_mapping_ops *dma_ops;
-
-static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
+extern struct dma_map_ops *dma_ops;
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
 #ifdef CONFIG_X86_32
         return dma_ops;
@@ -71,7 +35,7 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(dev);
+        struct dma_map_ops *ops = get_dma_ops(dev);
         if (ops->mapping_error)
                 return ops->mapping_error(dev, dma_addr);
 
@@ -90,137 +54,167 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 
 static inline dma_addr_t
 dma_map_single(struct device *hwdev, void *ptr, size_t size,
-               int direction)
+               enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-        BUG_ON(!valid_dma_direction(direction));
-        return ops->map_single(hwdev, virt_to_phys(ptr), size, direction);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
+        dma_addr_t addr;
+
+        BUG_ON(!valid_dma_direction(dir));
+        addr = ops->map_page(hwdev, virt_to_page(ptr),
+                             (unsigned long)ptr & ~PAGE_MASK, size,
+                             dir, NULL);
+        debug_dma_map_page(hwdev, virt_to_page(ptr),
+                           (unsigned long)ptr & ~PAGE_MASK, size,
+                           dir, addr, true);
+        return addr;
 }
 
 static inline void
 dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size,
-                 int direction)
+                 enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(dev);
+        struct dma_map_ops *ops = get_dma_ops(dev);
 
-        BUG_ON(!valid_dma_direction(direction));
-        if (ops->unmap_single)
-                ops->unmap_single(dev, addr, size, direction);
+        BUG_ON(!valid_dma_direction(dir));
+        if (ops->unmap_page)
+                ops->unmap_page(dev, addr, size, dir, NULL);
+        debug_dma_unmap_page(dev, addr, size, dir, true);
 }
 
 static inline int
 dma_map_sg(struct device *hwdev, struct scatterlist *sg,
-           int nents, int direction)
+           int nents, enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
+        int ents;
+
+        BUG_ON(!valid_dma_direction(dir));
+        ents = ops->map_sg(hwdev, sg, nents, dir, NULL);
+        debug_dma_map_sg(hwdev, sg, nents, ents, dir);
 
-        BUG_ON(!valid_dma_direction(direction));
-        return ops->map_sg(hwdev, sg, nents, direction);
+        return ents;
 }
 
 static inline void
 dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
-             int direction)
+             enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
 
-        BUG_ON(!valid_dma_direction(direction));
+        BUG_ON(!valid_dma_direction(dir));
+        debug_dma_unmap_sg(hwdev, sg, nents, dir);
         if (ops->unmap_sg)
-                ops->unmap_sg(hwdev, sg, nents, direction);
+                ops->unmap_sg(hwdev, sg, nents, dir, NULL);
 }
 
 static inline void
 dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-                        size_t size, int direction)
+                        size_t size, enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
 
-        BUG_ON(!valid_dma_direction(direction));
+        BUG_ON(!valid_dma_direction(dir));
         if (ops->sync_single_for_cpu)
-                ops->sync_single_for_cpu(hwdev, dma_handle, size, direction);
+                ops->sync_single_for_cpu(hwdev, dma_handle, size, dir);
+        debug_dma_sync_single_for_cpu(hwdev, dma_handle, size, dir);
         flush_write_buffers();
 }
 
 static inline void
 dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
-                           size_t size, int direction)
+                           size_t size, enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
 
-        BUG_ON(!valid_dma_direction(direction));
+        BUG_ON(!valid_dma_direction(dir));
         if (ops->sync_single_for_device)
-                ops->sync_single_for_device(hwdev, dma_handle, size, direction);
+                ops->sync_single_for_device(hwdev, dma_handle, size, dir);
+        debug_dma_sync_single_for_device(hwdev, dma_handle, size, dir);
         flush_write_buffers();
 }
 
 static inline void
 dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-                              unsigned long offset, size_t size, int direction)
+                              unsigned long offset, size_t size,
+                              enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
 
-        BUG_ON(!valid_dma_direction(direction));
+        BUG_ON(!valid_dma_direction(dir));
         if (ops->sync_single_range_for_cpu)
                 ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
-                                               size, direction);
+                                               size, dir);
+        debug_dma_sync_single_range_for_cpu(hwdev, dma_handle,
+                                            offset, size, dir);
         flush_write_buffers();
 }
 
 static inline void
 dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
                                  unsigned long offset, size_t size,
-                                 int direction)
+                                 enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
 
-        BUG_ON(!valid_dma_direction(direction));
+        BUG_ON(!valid_dma_direction(dir));
         if (ops->sync_single_range_for_device)
                 ops->sync_single_range_for_device(hwdev, dma_handle,
-                                                  offset, size, direction);
+                                                  offset, size, dir);
+        debug_dma_sync_single_range_for_device(hwdev, dma_handle,
+                                               offset, size, dir);
         flush_write_buffers();
 }
 
 static inline void
 dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-                    int nelems, int direction)
+                    int nelems, enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
 
-        BUG_ON(!valid_dma_direction(direction));
+        BUG_ON(!valid_dma_direction(dir));
         if (ops->sync_sg_for_cpu)
-                ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
+                ops->sync_sg_for_cpu(hwdev, sg, nelems, dir);
+        debug_dma_sync_sg_for_cpu(hwdev, sg, nelems, dir);
         flush_write_buffers();
 }
 
 static inline void
 dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-                       int nelems, int direction)
+                       int nelems, enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+        struct dma_map_ops *ops = get_dma_ops(hwdev);
 
-        BUG_ON(!valid_dma_direction(direction));
+        BUG_ON(!valid_dma_direction(dir));
         if (ops->sync_sg_for_device)
-                ops->sync_sg_for_device(hwdev, sg, nelems, direction);
+                ops->sync_sg_for_device(hwdev, sg, nelems, dir);
+        debug_dma_sync_sg_for_device(hwdev, sg, nelems, dir);
 
         flush_write_buffers();
 }
 
 static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
                                       size_t offset, size_t size,
-                                      int direction)
+                                      enum dma_data_direction dir)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(dev);
+        struct dma_map_ops *ops = get_dma_ops(dev);
+        dma_addr_t addr;
 
-        BUG_ON(!valid_dma_direction(direction));
-        return ops->map_single(dev, page_to_phys(page) + offset,
-                               size, direction);
+        BUG_ON(!valid_dma_direction(dir));
+        addr = ops->map_page(dev, page, offset, size, dir, NULL);
+        debug_dma_map_page(dev, page, offset, size, dir, addr, false);
+
+        return addr;
 }
 
 static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
-                                  size_t size, int direction)
+                                  size_t size, enum dma_data_direction dir)
 {
-        dma_unmap_single(dev, addr, size, direction);
+        struct dma_map_ops *ops = get_dma_ops(dev);
+
+        BUG_ON(!valid_dma_direction(dir));
+        if (ops->unmap_page)
+                ops->unmap_page(dev, addr, size, dir, NULL);
+        debug_dma_unmap_page(dev, addr, size, dir, false);
 }
 
 static inline void
@@ -266,7 +260,7 @@ static inline void *
 dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
                 gfp_t gfp)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(dev);
+        struct dma_map_ops *ops = get_dma_ops(dev);
         void *memory;
 
         gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
@@ -285,20 +279,24 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
         if (!ops->alloc_coherent)
                 return NULL;
 
-        return ops->alloc_coherent(dev, size, dma_handle,
-                                   dma_alloc_coherent_gfp_flags(dev, gfp));
+        memory = ops->alloc_coherent(dev, size, dma_handle,
+                                     dma_alloc_coherent_gfp_flags(dev, gfp));
+        debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
+
+        return memory;
 }
 
 static inline void dma_free_coherent(struct device *dev, size_t size,
                                      void *vaddr, dma_addr_t bus)
 {
-        struct dma_mapping_ops *ops = get_dma_ops(dev);
+        struct dma_map_ops *ops = get_dma_ops(dev);
 
         WARN_ON(irqs_disabled());       /* for portability */
 
         if (dma_release_from_coherent(dev, get_order(size), vaddr))
                 return;
 
+        debug_dma_free_coherent(dev, size, vaddr, bus);
         if (ops->free_coherent)
                 ops->free_coherent(dev, size, vaddr, bus);
 }
diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h
index bc68212c6bc0..fd8f9e2ca35f 100644
--- a/arch/x86/include/asm/dmi.h
+++ b/arch/x86/include/asm/dmi.h
@@ -1,22 +1,15 @@
 #ifndef _ASM_X86_DMI_H
 #define _ASM_X86_DMI_H
 
-#include <asm/io.h>
-
-#define DMI_MAX_DATA 2048
+#include <linux/compiler.h>
+#include <linux/init.h>
 
-extern int dmi_alloc_index;
-extern char dmi_alloc_data[DMI_MAX_DATA];
+#include <asm/io.h>
+#include <asm/setup.h>
 
-/* This is so early that there is no good way to allocate dynamic memory.
-   Allocate data in an BSS array. */
-static inline void *dmi_alloc(unsigned len)
+static __always_inline __init void *dmi_alloc(unsigned len)
 {
-        int idx = dmi_alloc_index;
-        if ((dmi_alloc_index + len) > DMI_MAX_DATA)
-                return NULL;
-        dmi_alloc_index += len;
-        return dmi_alloc_data + idx;
+        return extend_brk(len, sizeof(int));
 }
 
 /* Use early IO mappings for DMI because it's initialized early */
diff --git a/arch/x86/include/asm/mach-default/do_timer.h b/arch/x86/include/asm/do_timer.h
index 23ecda0b28a0..23ecda0b28a0 100644
--- a/arch/x86/include/asm/mach-default/do_timer.h
+++ b/arch/x86/include/asm/do_timer.h
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 00d41ce4c844..7ecba4d85089 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -72,7 +72,7 @@ extern int e820_all_mapped(u64 start, u64 end, unsigned type);
 extern void e820_add_region(u64 start, u64 size, int type);
 extern void e820_print_map(char *who);
 extern int
-sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map);
+sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map);
 extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
                                unsigned new_type);
 extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index f51a3ddde01a..83c1bc8d2e8a 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -112,7 +112,7 @@ extern unsigned int vdso_enabled;
  * now struct_user_regs, they are different)
  */
 
-#define ELF_CORE_COPY_REGS(pr_reg, regs)        \
+#define ELF_CORE_COPY_REGS_COMMON(pr_reg, regs) \
 do {                                            \
         pr_reg[0] = regs->bx;                   \
         pr_reg[1] = regs->cx;                   \
@@ -124,7 +124,6 @@ do {						\
         pr_reg[7] = regs->ds & 0xffff;          \
         pr_reg[8] = regs->es & 0xffff;          \
         pr_reg[9] = regs->fs & 0xffff;          \
-        savesegment(gs, pr_reg[10]);            \
         pr_reg[11] = regs->orig_ax;             \
         pr_reg[12] = regs->ip;                  \
         pr_reg[13] = regs->cs & 0xffff;         \
@@ -133,6 +132,18 @@ do {						\
         pr_reg[16] = regs->ss & 0xffff;         \
 } while (0);
 
+#define ELF_CORE_COPY_REGS(pr_reg, regs)        \
+do {                                            \
+        ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\
+        pr_reg[10] = get_user_gs(regs);         \
+} while (0);
+
+#define ELF_CORE_COPY_KERNEL_REGS(pr_reg, regs) \
+do {                                            \
+        ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\
+        savesegment(gs, pr_reg[10]);            \
+} while (0);
+
 #define ELF_PLATFORM    (utsname()->machine)
 #define set_personality_64bit() do { } while (0)
 
diff --git a/arch/x86/include/asm/mach-default/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 6b1add8e31dd..c2e6bedaf258 100644
--- a/arch/x86/include/asm/mach-default/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -9,14 +9,32 @@
  * is no hardware IRQ pin equivalent for them, they are triggered
  * through the ICC by us (IPIs)
  */
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
 BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
 BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
+
+BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
+                 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
+                 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
+                 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
+                 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
+                 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
+                 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
+                 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
+                 smp_invalidate_interrupt)
 #endif
 
+BUILD_INTERRUPT(generic_interrupt, GENERIC_INTERRUPT_VECTOR)
+
 /*
  * every pentium local APIC has two 'local interrupts', with a
  * soft-definable vector attached to both interrupts, one of
@@ -25,10 +43,15 @@ BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
  * a much simpler SMP time architecture:
  */
 #ifdef CONFIG_X86_LOCAL_APIC
+
 BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
 BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
+#ifdef CONFIG_PERF_COUNTERS
+BUILD_INTERRUPT(perf_counter_interrupt, LOCAL_PERF_VECTOR)
+#endif
+
 #ifdef CONFIG_X86_MCE_P4THERMAL
 BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
 #endif
diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h
deleted file mode 100644
index c58b9cc74465..000000000000
--- a/arch/x86/include/asm/es7000/apic.h
+++ /dev/null
@@ -1,242 +0,0 @@
-#ifndef __ASM_ES7000_APIC_H
-#define __ASM_ES7000_APIC_H
-
-#include <linux/gfp.h>
-
-#define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
-#define esr_disable (1)
-
-static inline int apic_id_registered(void)
-{
-                return (1);
-}
-
-static inline const cpumask_t *target_cpus_cluster(void)
-{
-        return &CPU_MASK_ALL;
-}
-
-static inline const cpumask_t *target_cpus(void)
-{
-        return &cpumask_of_cpu(smp_processor_id());
-}
-
-#define APIC_DFR_VALUE_CLUSTER          (APIC_DFR_CLUSTER)
-#define INT_DELIVERY_MODE_CLUSTER       (dest_LowestPrio)
-#define INT_DEST_MODE_CLUSTER           (1) /* logical delivery broadcast to all procs */
-#define NO_BALANCE_IRQ_CLUSTER          (1)
-
-#define APIC_DFR_VALUE          (APIC_DFR_FLAT)
-#define INT_DELIVERY_MODE       (dest_Fixed)
-#define INT_DEST_MODE           (0)    /* phys delivery to target procs */
-#define NO_BALANCE_IRQ          (0)
-#undef  APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL       0x0
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-        return 0;
-}
-static inline unsigned long check_apicid_present(int bit)
-{
-        return physid_isset(bit, phys_cpu_present_map);
-}
-
-#define apicid_cluster(apicid) (apicid & 0xF0)
-
-static inline unsigned long calculate_ldr(int cpu)
-{
-        unsigned long id;
-        id = xapic_phys_to_log_apicid(cpu);
-        return (SET_APIC_LOGICAL_ID(id));
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LdR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr_cluster(void)
-{
-        unsigned long val;
-        int cpu = smp_processor_id();
-
-        apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER);
-        val = calculate_ldr(cpu);
-        apic_write(APIC_LDR, val);
-}
-
-static inline void init_apic_ldr(void)
-{
-        unsigned long val;
-        int cpu = smp_processor_id();
-
-        apic_write(APIC_DFR, APIC_DFR_VALUE);
-        val = calculate_ldr(cpu);
-        apic_write(APIC_LDR, val);
-}
-
-extern int apic_version [MAX_APICS];
-static inline void setup_apic_routing(void)
-{
-        int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
-        printk("Enabling APIC mode:  %s. Using %d I/O APICs, target cpus %lx\n",
-                (apic_version[apic] == 0x14) ?
-                        "Physical Cluster" : "Logical Cluster",
-                        nr_ioapics, cpus_addr(*target_cpus())[0]);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-        return 0;
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-        return 0;
-}
-
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-        if (!mps_cpu)
-                return boot_cpu_physical_apicid;
-        else if (mps_cpu < nr_cpu_ids)
-                return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
-        else
-                return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-        static int id = 0;
-        physid_mask_t mask;
-        mask = physid_mask_of_physid(id);
-        ++id;
-        return mask;
-}
-
-extern u8 cpu_2_logical_apicid[];
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-        if (cpu >= nr_cpu_ids)
-                return BAD_APICID;
-        return (int)cpu_2_logical_apicid[cpu];
-#else
-        return logical_smp_processor_id();
-#endif
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-        /* For clustered we don't have a good way to do this yet - hack */
-        return physids_promote(0xff);
-}
-
-
-static inline void setup_portio_remap(void)
-{
-}
-
-extern unsigned int boot_cpu_physical_apicid;
-static inline int check_phys_apicid_present(int cpu_physical_apicid)
-{
-        boot_cpu_physical_apicid = read_apic_id();
-        return (1);
-}
-
-static inline unsigned int
-cpu_mask_to_apicid_cluster(const struct cpumask *cpumask)
-{
-        int num_bits_set;
-        int cpus_found = 0;
-        int cpu;
-        int apicid;
-
-        num_bits_set = cpumask_weight(cpumask);
-        /* Return id to all */
-        if (num_bits_set == nr_cpu_ids)
-                return 0xFF;
-        /*
-         * The cpus in the mask must all be on the apic cluster.  If are not
-         * on the same apicid cluster return default value of TARGET_CPUS.
-         */
-        cpu = cpumask_first(cpumask);
-        apicid = cpu_to_logical_apicid(cpu);
-        while (cpus_found < num_bits_set) {
-                if (cpumask_test_cpu(cpu, cpumask)) {
-                        int new_apicid = cpu_to_logical_apicid(cpu);
-                        if (apicid_cluster(apicid) !=
-                                        apicid_cluster(new_apicid)){
-                                printk ("%s: Not a valid mask!\n", __func__);
-                                return 0xFF;
-                        }
-                        apicid = new_apicid;
-                        cpus_found++;
-                }
-                cpu++;
-        }
-        return apicid;
-}
-
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-        int num_bits_set;
-        int cpus_found = 0;
-        int cpu;
-        int apicid;
-
-        num_bits_set = cpus_weight(*cpumask);
-        /* Return id to all */
-        if (num_bits_set == nr_cpu_ids)
-                return cpu_to_logical_apicid(0);
-        /*
-         * The cpus in the mask must all be on the apic cluster.  If are not
-         * on the same apicid cluster return default value of TARGET_CPUS.
-         */
-        cpu = first_cpu(*cpumask);
-        apicid = cpu_to_logical_apicid(cpu);
-        while (cpus_found < num_bits_set) {
-                if (cpu_isset(cpu, *cpumask)) {
-                        int new_apicid = cpu_to_logical_apicid(cpu);
-                        if (apicid_cluster(apicid) !=
-                                        apicid_cluster(new_apicid)){
-                                printk ("%s: Not a valid mask!\n", __func__);
-                                return cpu_to_logical_apicid(0);
-                        }
-                        apicid = new_apicid;
-                        cpus_found++;
-                }
-                cpu++;
-        }
-        return apicid;
-}
-
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask,
-                                                  const struct cpumask *andmask)
-{
-        int apicid = cpu_to_logical_apicid(0);
-        cpumask_var_t cpumask;
-
-        if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
-                return apicid;
-
-        cpumask_and(cpumask, inmask, andmask);
-        cpumask_and(cpumask, cpumask, cpu_online_mask);
-        apicid = cpu_mask_to_apicid(cpumask);
-
-        free_cpumask_var(cpumask);
-        return apicid;
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-        return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_ES7000_APIC_H */
diff --git a/arch/x86/include/asm/es7000/apicdef.h b/arch/x86/include/asm/es7000/apicdef.h
deleted file mode 100644
index 8b234a3cb851..000000000000
--- a/arch/x86/include/asm/es7000/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_ES7000_APICDEF_H
-#define __ASM_ES7000_APICDEF_H
-
-#define         APIC_ID_MASK            (0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-        return (((x)>>24)&0xFF);
-}
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/arch/x86/include/asm/es7000/ipi.h b/arch/x86/include/asm/es7000/ipi.h
deleted file mode 100644
index 7e8ed24d4b8a..000000000000
--- a/arch/x86/include/asm/es7000/ipi.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef __ASM_ES7000_IPI_H
-#define __ASM_ES7000_IPI_H
-
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-        send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-        send_IPI_mask_allbutself(cpu_online_mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-        send_IPI_mask(cpu_online_mask, vector);
-}
-
-#endif /* __ASM_ES7000_IPI_H */
diff --git a/arch/x86/include/asm/es7000/mpparse.h b/arch/x86/include/asm/es7000/mpparse.h
deleted file mode 100644
index c1629b090ec2..000000000000
--- a/arch/x86/include/asm/es7000/mpparse.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __ASM_ES7000_MPPARSE_H
-#define __ASM_ES7000_MPPARSE_H
-
-#include <linux/acpi.h>
-
-extern int parse_unisys_oem (char *oemptr);
-extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
-extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr);
-extern void setup_unisys(void);
-
-#ifndef CONFIG_X86_GENERICARCH
-extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
-extern int mps_oem_check(struct mpc_table *mpc, char *oem, char *productid);
-#endif
-
-#ifdef CONFIG_ACPI
-
-static inline int es7000_check_dsdt(void)
-{
-        struct acpi_table_header header;
-
-        if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) &&
-            !strncmp(header.oem_id, "UNISYS", 6))
-                return 1;
-        return 0;
-}
-#endif
-
-#endif /* __ASM_MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/es7000/wakecpu.h b/arch/x86/include/asm/es7000/wakecpu.h
deleted file mode 100644
index 78f0daaee436..000000000000
--- a/arch/x86/include/asm/es7000/wakecpu.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef __ASM_ES7000_WAKECPU_H
-#define __ASM_ES7000_WAKECPU_H
-
-#define TRAMPOLINE_PHYS_LOW     0x467
-#define TRAMPOLINE_PHYS_HIGH    0x469
-
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-#ifndef CONFIG_ES7000_CLUSTERED_APIC
-        while (!atomic_read(deassert))
-                cpu_relax();
-#endif
-        return;
-}
-
-/* Nothing to do for most platforms, since cleared by the INIT cycle */
-static inline void smp_callin_clear_local_apic(void)
-{
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-extern void __inquire_remote_apic(int apicid);
-
-static inline void inquire_remote_apic(int apicid)
-{
-        if (apic_verbosity >= APIC_DEBUG)
-                __inquire_remote_apic(apicid);
-}
-
-#endif /* __ASM_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 23696d44a0af..63a79c77d220 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -1,11 +1,145 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ * x86_32 and x86_64 integration by Gustavo F. Padovan, February 2009
+ */
+
 #ifndef _ASM_X86_FIXMAP_H
 #define _ASM_X86_FIXMAP_H
 
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/acpi.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#ifdef CONFIG_X86_32
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#else
+#include <asm/vsyscall.h>
+#endif
+
+/*
+ * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall
+ * uses fixmaps that relies on FIXADDR_TOP for proper address calculation.
+ * Because of this, FIXADDR_TOP x86 integration was left as later work.
+ */
+#ifdef CONFIG_X86_32
+/* used by vmalloc.c, vsyscall.lds.S.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap.
+ */
+extern unsigned long __FIXADDR_TOP;
+#define FIXADDR_TOP     ((unsigned long)__FIXADDR_TOP)
+
+#define FIXADDR_USER_START     __fix_to_virt(FIX_VDSO)
+#define FIXADDR_USER_END       __fix_to_virt(FIX_VDSO - 1)
+#else
+#define FIXADDR_TOP     (VSYSCALL_END-PAGE_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)
+#endif
+
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ * for x86_32: We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * These 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages (or larger if used with an increment
+ * higher than 1). Use set_fixmap(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+enum fixed_addresses {
 #ifdef CONFIG_X86_32
-# include "fixmap_32.h"
+        FIX_HOLE,
+        FIX_VDSO,
 #else
-# include "fixmap_64.h"
+        VSYSCALL_LAST_PAGE,
+        VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
+                            + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
+        VSYSCALL_HPET,
 #endif
+        FIX_DBGP_BASE,
+        FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_X86_LOCAL_APIC
+        FIX_APIC_BASE,  /* local (CPU) APIC) -- required for SMP or not */
+#endif
+#ifdef CONFIG_X86_IO_APIC
+        FIX_IO_APIC_BASE_0,
+        FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
+#endif
+#ifdef CONFIG_X86_VISWS_APIC
+        FIX_CO_CPU,     /* Cobalt timer */
+        FIX_CO_APIC,    /* Cobalt APIC Redirection Table */
+        FIX_LI_PCIA,    /* Lithium PCI Bridge A */
+        FIX_LI_PCIB,    /* Lithium PCI Bridge B */
+#endif
+#ifdef CONFIG_X86_F00F_BUG
+        FIX_F00F_IDT,   /* Virtual mapping for IDT */
+#endif
+#ifdef CONFIG_X86_CYCLONE_TIMER
+        FIX_CYCLONE_TIMER, /*cyclone timer register*/
+#endif
+#ifdef CONFIG_X86_32
+        FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
+        FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+#ifdef CONFIG_PCI_MMCONFIG
+        FIX_PCIE_MCFG,
+#endif
+#endif
+#ifdef CONFIG_PARAVIRT
+        FIX_PARAVIRT_BOOTMAP,
+#endif
+        __end_of_permanent_fixed_addresses,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+        FIX_OHCI1394_BASE,
+#endif
+        /*
+         * 256 temporary boot-time mappings, used by early_ioremap(),
+         * before ioremap() is functional.
+         *
+         * We round it up to the next 256 pages boundary so that we
+         * can have a single pgd entry and a single pte table:
+         */
+#define NR_FIX_BTMAPS           64
+#define FIX_BTMAPS_SLOTS        4
+        FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
+                        (__end_of_permanent_fixed_addresses & 255),
+        FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
+#ifdef CONFIG_X86_32
+        FIX_WP_TEST,
+#endif
+        __end_of_fixed_addresses
+};
+
+
+extern void reserve_top_address(unsigned long reserve);
+
+#define FIXADDR_SIZE    (__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_BOOT_SIZE       (__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START           (FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_BOOT_START      (FIXADDR_TOP - FIXADDR_BOOT_SIZE)
 
 extern int fixmaps_set;
 
@@ -69,4 +203,5 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr)
         BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
         return __virt_to_fix(vaddr);
 }
+#endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_FIXMAP_H */
diff --git a/arch/x86/include/asm/fixmap_32.h b/arch/x86/include/asm/fixmap_32.h
deleted file mode 100644
index c7115c1d7217..000000000000
--- a/arch/x86/include/asm/fixmap_32.h
+++ /dev/null
@@ -1,119 +0,0 @@
-/*
- * fixmap.h: compile-time virtual memory allocation
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1998 Ingo Molnar
- *
- * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
- */
-
-#ifndef _ASM_X86_FIXMAP_32_H
-#define _ASM_X86_FIXMAP_32_H
-
-
-/* used by vmalloc.c, vsyscall.lds.S.
- *
- * Leave one empty page between vmalloc'ed areas and
- * the start of the fixmap.
- */
-extern unsigned long __FIXADDR_TOP;
-#define FIXADDR_USER_START     __fix_to_virt(FIX_VDSO)
-#define FIXADDR_USER_END       __fix_to_virt(FIX_VDSO - 1)
-
-#ifndef __ASSEMBLY__
-#include <linux/kernel.h>
-#include <asm/acpi.h>
-#include <asm/apicdef.h>
-#include <asm/page.h>
-#include <linux/threads.h>
-#include <asm/kmap_types.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. We allocate these special addresses
- * from the end of virtual memory (0xfffff000) backwards.
- * Also this lets us do fail-safe vmalloc(), we
- * can guarantee that these special addresses and
- * vmalloc()-ed addresses never overlap.
- *
- * these 'compile-time allocated' memory buffers are
- * fixed-size 4k pages. (or larger if used with an increment
- * highger than 1) use fixmap_set(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-enum fixed_addresses {
-        FIX_HOLE,
-        FIX_VDSO,
-        FIX_DBGP_BASE,
-        FIX_EARLYCON_MEM_BASE,
-#ifdef CONFIG_X86_LOCAL_APIC
-        FIX_APIC_BASE,  /* local (CPU) APIC) -- required for SMP or not */
-#endif
-#ifdef CONFIG_X86_IO_APIC
-        FIX_IO_APIC_BASE_0,
-        FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1,
-#endif
-#ifdef CONFIG_X86_VISWS_APIC
-        FIX_CO_CPU,     /* Cobalt timer */
-        FIX_CO_APIC,    /* Cobalt APIC Redirection Table */
-        FIX_LI_PCIA,    /* Lithium PCI Bridge A */
-        FIX_LI_PCIB,    /* Lithium PCI Bridge B */
-#endif
-#ifdef CONFIG_X86_F00F_BUG
-        FIX_F00F_IDT,   /* Virtual mapping for IDT */
-#endif
-#ifdef CONFIG_X86_CYCLONE_TIMER
-        FIX_CYCLONE_TIMER, /*cyclone timer register*/
-#endif
-        FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
-        FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-#ifdef CONFIG_PCI_MMCONFIG
-        FIX_PCIE_MCFG,
-#endif
-#ifdef CONFIG_PARAVIRT
-        FIX_PARAVIRT_BOOTMAP,
-#endif
-        __end_of_permanent_fixed_addresses,
-        /*
-         * 256 temporary boot-time mappings, used by early_ioremap(),
-         * before ioremap() is functional.
-         *
-         * We round it up to the next 256 pages boundary so that we
-         * can have a single pgd entry and a single pte table:
-         */
-#define NR_FIX_BTMAPS           64
-#define FIX_BTMAPS_SLOTS        4
-        FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
-                        (__end_of_permanent_fixed_addresses & 255),
-        FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-        FIX_WP_TEST,
-#ifdef CONFIG_ACPI
-        FIX_ACPI_BEGIN,
-        FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-        FIX_OHCI1394_BASE,
-#endif
-        __end_of_fixed_addresses
-};
-
-extern void reserve_top_address(unsigned long reserve);
-
-
-#define FIXADDR_TOP     ((unsigned long)__FIXADDR_TOP)
-
-#define __FIXADDR_SIZE  (__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define __FIXADDR_BOOT_SIZE     (__end_of_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START           (FIXADDR_TOP - __FIXADDR_SIZE)
-#define FIXADDR_BOOT_START      (FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
-
-#endif /* !__ASSEMBLY__ */
-#endif /* _ASM_X86_FIXMAP_32_H */
diff --git a/arch/x86/include/asm/fixmap_64.h b/arch/x86/include/asm/fixmap_64.h
deleted file mode 100644
index 8be740977db8..000000000000
--- a/arch/x86/include/asm/fixmap_64.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * 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_X86_FIXMAP_64_H
-#define _ASM_X86_FIXMAP_64_H
-
-#include <linux/kernel.h>
-#include <asm/acpi.h>
-#include <asm/apicdef.h>
-#include <asm/page.h>
-#include <asm/vsyscall.h>
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process.
- *
- * These 'compile-time allocated' memory buffers are
- * fixed-size 4k pages (or larger if used with an increment
- * higher than 1). Use set_fixmap(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-
-enum fixed_addresses {
-        VSYSCALL_LAST_PAGE,
-        VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
-                            + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
-        VSYSCALL_HPET,
-        FIX_DBGP_BASE,
-        FIX_EARLYCON_MEM_BASE,
-        FIX_APIC_BASE,  /* local (CPU) APIC) -- required for SMP or not */
-        FIX_IO_APIC_BASE_0,
-        FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
-#ifdef CONFIG_PARAVIRT
-        FIX_PARAVIRT_BOOTMAP,
-#endif
-        __end_of_permanent_fixed_addresses,
-#ifdef CONFIG_ACPI
-        FIX_ACPI_BEGIN,
-        FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-        FIX_OHCI1394_BASE,
-#endif
-        /*
-         * 256 temporary boot-time mappings, used by early_ioremap(),
-         * before ioremap() is functional.
-         *
-         * We round it up to the next 256 pages boundary so that we
-         * can have a single pgd entry and a single pte table:
-         */
-#define NR_FIX_BTMAPS           64
-#define FIX_BTMAPS_SLOTS        4
-        FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
-                        (__end_of_permanent_fixed_addresses & 255),
-        FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-        __end_of_fixed_addresses
-};
-
-#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)
-
-#endif /* _ASM_X86_FIXMAP_64_H */
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index b55b4a7fbefd..db24c2278be0 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -55,29 +55,4 @@ struct dyn_arch_ftrace {
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-#ifndef __ASSEMBLY__
-
-/*
- * Stack of return addresses for functions
- * of a thread.
- * Used in struct thread_info
- */
-struct ftrace_ret_stack {
-        unsigned long ret;
-        unsigned long func;
-        unsigned long long calltime;
-};
-
-/*
- * Primary handler of a function return.
- * It relays on ftrace_return_to_handler.
- * Defined in entry_32/64.S
- */
-extern void return_to_handler(void);
-
-#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/genapic.h b/arch/x86/include/asm/genapic.h
index d48bee663a6f..4b8b98fa7f25 100644
--- a/arch/x86/include/asm/genapic.h
+++ b/arch/x86/include/asm/genapic.h
@@ -1,5 +1 @@
-#ifdef CONFIG_X86_32
-# include "genapic_32.h"
-#else
-# include "genapic_64.h"
-#endif
+#include <asm/apic.h>
diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h
deleted file mode 100644
index 2c05b737ee22..000000000000
--- a/arch/x86/include/asm/genapic_32.h
+++ /dev/null
@@ -1,148 +0,0 @@
-#ifndef _ASM_X86_GENAPIC_32_H
-#define _ASM_X86_GENAPIC_32_H
-
-#include <asm/mpspec.h>
-#include <asm/atomic.h>
-
-/*
- * Generic APIC driver interface.
- *
- * An straight forward mapping of the APIC related parts of the
- * x86 subarchitecture interface to a dynamic object.
- *
- * This is used by the "generic" x86 subarchitecture.
- *
- * Copyright 2003 Andi Kleen, SuSE Labs.
- */
-
-struct mpc_bus;
-struct mpc_table;
-struct mpc_cpu;
-
-struct genapic {
-        char *name;
-        int (*probe)(void);
-
-        int (*apic_id_registered)(void);
-        const struct cpumask *(*target_cpus)(void);
-        int int_delivery_mode;
-        int int_dest_mode;
-        int ESR_DISABLE;
-        int apic_destination_logical;
-        unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
-        unsigned long (*check_apicid_present)(int apicid);
-        int no_balance_irq;
-        int no_ioapic_check;
-        void (*init_apic_ldr)(void);
-        physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
-
-        void (*setup_apic_routing)(void);
-        int (*multi_timer_check)(int apic, int irq);
-        int (*apicid_to_node)(int logical_apicid);
-        int (*cpu_to_logical_apicid)(int cpu);
-        int (*cpu_present_to_apicid)(int mps_cpu);
-        physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
-        void (*setup_portio_remap)(void);
-        int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
-        void (*enable_apic_mode)(void);
-        u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
-
-        /* mpparse */
-        /* When one of the next two hooks returns 1 the genapic
-           is switched to this. Essentially they are additional probe
-           functions. */
-        int (*mps_oem_check)(struct mpc_table *mpc, char *oem,
-                             char *productid);
-        int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-
-        unsigned (*get_apic_id)(unsigned long x);
-        unsigned long apic_id_mask;
-        unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
-        unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
-                                               const struct cpumask *andmask);
-        void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
-
-#ifdef CONFIG_SMP
-        /* ipi */
-        void (*send_IPI_mask)(const struct cpumask *mask, int vector);
-        void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
-                                         int vector);
-        void (*send_IPI_allbutself)(int vector);
-        void (*send_IPI_all)(int vector);
-#endif
-        int (*wakeup_cpu)(int apicid, unsigned long start_eip);
-        int trampoline_phys_low;
-        int trampoline_phys_high;
-        void (*wait_for_init_deassert)(atomic_t *deassert);
-        void (*smp_callin_clear_local_apic)(void);
-        void (*store_NMI_vector)(unsigned short *high, unsigned short *low);
-        void (*restore_NMI_vector)(unsigned short *high, unsigned short *low);
-        void (*inquire_remote_apic)(int apicid);
-};
-
-#define APICFUNC(x) .x = x,
-
-/* More functions could be probably marked IPIFUNC and save some space
-   in UP GENERICARCH kernels, but I don't have the nerve right now
-   to untangle this mess. -AK  */
-#ifdef CONFIG_SMP
-#define IPIFUNC(x) APICFUNC(x)
-#else
-#define IPIFUNC(x)
-#endif
-
-#define APIC_INIT(aname, aprobe)                        \
-{                                                       \
-        .name = aname,                                  \
-        .probe = aprobe,                                \
-        .int_delivery_mode = INT_DELIVERY_MODE,         \
-        .int_dest_mode = INT_DEST_MODE,                 \
-        .no_balance_irq = NO_BALANCE_IRQ,               \
-        .ESR_DISABLE = esr_disable,                     \
-        .apic_destination_logical = APIC_DEST_LOGICAL,  \
-        APICFUNC(apic_id_registered)                    \
-        APICFUNC(target_cpus)                           \
-        APICFUNC(check_apicid_used)                     \
-        APICFUNC(check_apicid_present)                  \
-        APICFUNC(init_apic_ldr)                         \
-        APICFUNC(ioapic_phys_id_map)                    \
-        APICFUNC(setup_apic_routing)                    \
-        APICFUNC(multi_timer_check)                     \
-        APICFUNC(apicid_to_node)                        \
-        APICFUNC(cpu_to_logical_apicid)                 \
-        APICFUNC(cpu_present_to_apicid)                 \
-        APICFUNC(apicid_to_cpu_present)                 \
-        APICFUNC(setup_portio_remap)                    \
-        APICFUNC(check_phys_apicid_present)             \
-        APICFUNC(mps_oem_check)                         \
-        APICFUNC(get_apic_id)                           \
-        .apic_id_mask = APIC_ID_MASK,                   \
-        APICFUNC(cpu_mask_to_apicid)                    \
-        APICFUNC(cpu_mask_to_apicid_and)                \
-        APICFUNC(vector_allocation_domain)              \
-        APICFUNC(acpi_madt_oem_check)                   \
-        IPIFUNC(send_IPI_mask)                          \
-        IPIFUNC(send_IPI_allbutself)                    \
-        IPIFUNC(send_IPI_all)                           \
-        APICFUNC(enable_apic_mode)                      \
-        APICFUNC(phys_pkg_id)                           \
-        .trampoline_phys_low = TRAMPOLINE_PHYS_LOW,             \
-        .trampoline_phys_high = TRAMPOLINE_PHYS_HIGH,           \
-        APICFUNC(wait_for_init_deassert)                \
-        APICFUNC(smp_callin_clear_local_apic)           \
-        APICFUNC(store_NMI_vector)                      \
-        APICFUNC(restore_NMI_vector)                    \
-        APICFUNC(inquire_remote_apic)                   \
-}
-
-extern struct genapic *genapic;
-extern void es7000_update_genapic_to_cluster(void);
-
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-#define get_uv_system_type()            UV_NONE
-#define is_uv_system()                  0
-#define uv_wakeup_secondary(a, b)       1
-#define uv_system_init()                do {} while (0)
-
-
-#endif /* _ASM_X86_GENAPIC_32_H */
diff --git a/arch/x86/include/asm/genapic_64.h b/arch/x86/include/asm/genapic_64.h
deleted file mode 100644
index adf32fb56aa6..000000000000
--- a/arch/x86/include/asm/genapic_64.h
+++ /dev/null
@@ -1,66 +0,0 @@
-#ifndef _ASM_X86_GENAPIC_64_H
-#define _ASM_X86_GENAPIC_64_H
-
-#include <linux/cpumask.h>
-
-/*
- * 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;
-        int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-        u32 int_delivery_mode;
-        u32 int_dest_mode;
-        int (*apic_id_registered)(void);
-        const struct cpumask *(*target_cpus)(void);
-        void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
-        void (*init_apic_ldr)(void);
-        /* ipi */
-        void (*send_IPI_mask)(const struct cpumask *mask, int vector);
-        void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
-                                         int vector);
-        void (*send_IPI_allbutself)(int vector);
-        void (*send_IPI_all)(int vector);
-        void (*send_IPI_self)(int vector);
-        /* */
-        unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
-        unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
-                                               const struct cpumask *andmask);
-        unsigned int (*phys_pkg_id)(int index_msb);
-        unsigned int (*get_apic_id)(unsigned long x);
-        unsigned long (*set_apic_id)(unsigned int id);
-        unsigned long apic_id_mask;
-        /* wakeup_secondary_cpu */
-        int (*wakeup_cpu)(int apicid, unsigned long start_eip);
-};
-
-extern struct genapic *genapic;
-
-extern struct genapic apic_flat;
-extern struct genapic apic_physflat;
-extern struct genapic apic_x2apic_cluster;
-extern struct genapic apic_x2apic_phys;
-extern int acpi_madt_oem_check(char *, char *);
-
-extern void apic_send_IPI_self(int vector);
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-extern enum uv_system_type get_uv_system_type(void);
-extern int is_uv_system(void);
-
-extern struct genapic apic_x2apic_uv_x;
-DECLARE_PER_CPU(int, x2apic_extra_bits);
-extern void uv_cpu_init(void);
-extern void uv_system_init(void);
-extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
-
-extern void setup_apic_routing(void);
-
-#endif /* _ASM_X86_GENAPIC_64_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 000787df66e6..039db6aa8e02 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -1,11 +1,53 @@
-#ifdef CONFIG_X86_32
-# include "hardirq_32.h"
-#else
-# include "hardirq_64.h"
+#ifndef _ASM_X86_HARDIRQ_H
+#define _ASM_X86_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+        unsigned int __softirq_pending;
+        unsigned int __nmi_count;       /* arch dependent */
+        unsigned int irq0_irqs;
+#ifdef CONFIG_X86_LOCAL_APIC
+        unsigned int apic_timer_irqs;   /* arch dependent */
+        unsigned int irq_spurious_count;
+#endif
+        unsigned int generic_irqs;      /* arch dependent */
+#ifdef CONFIG_SMP
+        unsigned int irq_resched_count;
+        unsigned int irq_call_count;
+        unsigned int irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+        unsigned int irq_thermal_count;
+# ifdef CONFIG_X86_64
+        unsigned int irq_threshold_count;
+# endif
 #endif
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+
+/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
+#define MAX_HARDIRQS_PER_CPU NR_VECTORS
+
+#define __ARCH_IRQ_STAT
+
+#define inc_irq_stat(member)    percpu_add(irq_stat.member, 1)
+
+#define local_softirq_pending() percpu_read(irq_stat.__softirq_pending)
+
+#define __ARCH_SET_SOFTIRQ_PENDING
+
+#define set_softirq_pending(x)  percpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x)   percpu_or(irq_stat.__softirq_pending, (x))
+
+extern void ack_bad_irq(unsigned int irq);
 
 extern u64 arch_irq_stat_cpu(unsigned int cpu);
 #define arch_irq_stat_cpu       arch_irq_stat_cpu
 
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat           arch_irq_stat
+
+#endif /* _ASM_X86_HARDIRQ_H */
diff --git a/arch/x86/include/asm/hardirq_32.h b/arch/x86/include/asm/hardirq_32.h
deleted file mode 100644
index cf7954d1405f..000000000000
--- a/arch/x86/include/asm/hardirq_32.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_32_H
-#define _ASM_X86_HARDIRQ_32_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-typedef struct {
-        unsigned int __softirq_pending;
-        unsigned long idle_timestamp;
-        unsigned int __nmi_count;       /* arch dependent */
-        unsigned int apic_timer_irqs;   /* arch dependent */
-        unsigned int irq0_irqs;
-        unsigned int irq_resched_count;
-        unsigned int irq_call_count;
-        unsigned int irq_tlb_count;
-        unsigned int irq_thermal_count;
-        unsigned int irq_spurious_count;
-} ____cacheline_aligned irq_cpustat_t;
-
-DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
-
-#define __ARCH_IRQ_STAT
-#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
-
-#define inc_irq_stat(member)    (__get_cpu_var(irq_stat).member++)
-
-void ack_bad_irq(unsigned int irq);
-#include <linux/irq_cpustat.h>
-
-#endif /* _ASM_X86_HARDIRQ_32_H */
diff --git a/arch/x86/include/asm/hardirq_64.h b/arch/x86/include/asm/hardirq_64.h
deleted file mode 100644
index b5a6b5d56704..000000000000
--- a/arch/x86/include/asm/hardirq_64.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_64_H
-#define _ASM_X86_HARDIRQ_64_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-#include <asm/pda.h>
-#include <asm/apic.h>
-
-/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
-#define MAX_HARDIRQS_PER_CPU NR_VECTORS
-
-#define __ARCH_IRQ_STAT 1
-
-#define inc_irq_stat(member)    add_pda(member, 1)
-
-#define local_softirq_pending() read_pda(__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING 1
-
-#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
-#define or_softirq_pending(x)  or_pda(__softirq_pending, (x))
-
-extern void ack_bad_irq(unsigned int irq);
-
-#endif /* _ASM_X86_HARDIRQ_64_H */
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index bf9276bea660..014c2b85ae45 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -63,6 +63,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
 void *kmap_atomic(struct page *page, enum km_type type);
 void kunmap_atomic(void *kvaddr, enum km_type type);
 void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
+void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
 struct page *kmap_atomic_to_page(void *ptr);
 
 #ifndef CONFIG_PARAVIRT
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 8de644b6b959..b762ea49bd70 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -25,10 +25,9 @@
 #include <asm/irq.h>
 #include <asm/sections.h>
 
-#define platform_legacy_irq(irq)        ((irq) < 16)
-
 /* Interrupt handlers registered during init_IRQ */
 extern void apic_timer_interrupt(void);
+extern void generic_interrupt(void);
 extern void error_interrupt(void);
 extern void spurious_interrupt(void);
 extern void thermal_interrupt(void);
@@ -58,7 +57,7 @@ extern void make_8259A_irq(unsigned int irq);
 extern void init_8259A(int aeoi);
 
 /* IOAPIC */
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
+#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs))
 extern unsigned long io_apic_irqs;
 
 extern void init_VISWS_APIC_irqs(void);
@@ -67,15 +66,7 @@ extern void disable_IO_APIC(void);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
 extern void setup_ioapic_dest(void);
 
-#ifdef CONFIG_X86_64
 extern void enable_IO_APIC(void);
-#endif
-
-/* IPI functions */
-#ifdef CONFIG_X86_32
-extern void send_IPI_self(int vector);
-#endif
-extern void send_IPI(int dest, int vector);
 
 /* Statistics */
 extern atomic_t irq_err_count;
@@ -84,21 +75,11 @@ extern atomic_t irq_mis_count;
 /* EISA */
 extern void eisa_set_level_irq(unsigned int irq);
 
-/* Voyager functions */
-extern asmlinkage void vic_cpi_interrupt(void);
-extern asmlinkage void vic_sys_interrupt(void);
-extern asmlinkage void vic_cmn_interrupt(void);
-extern asmlinkage void qic_timer_interrupt(void);
-extern asmlinkage void qic_invalidate_interrupt(void);
-extern asmlinkage void qic_reschedule_interrupt(void);
-extern asmlinkage void qic_enable_irq_interrupt(void);
-extern asmlinkage void qic_call_function_interrupt(void);
-
 /* SMP */
 extern void smp_apic_timer_interrupt(struct pt_regs *);
 extern void smp_spurious_interrupt(struct pt_regs *);
 extern void smp_error_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
 extern void smp_reschedule_interrupt(struct pt_regs *);
 extern void smp_call_function_interrupt(struct pt_regs *);
 extern void smp_call_function_single_interrupt(struct pt_regs *);
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 58d7091eeb1f..1a99e6c092af 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -60,4 +60,8 @@ extern struct irq_chip i8259A_chip;
 extern void mask_8259A(void);
 extern void unmask_8259A(void);
 
+#ifdef CONFIG_X86_32
+extern void init_ISA_irqs(void);
+#endif
+
 #endif /* _ASM_X86_I8259_H */
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 50ca486fd88c..1f7e62517284 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -129,13 +129,6 @@ typedef struct compat_siginfo {
         } _sifields;
 } compat_siginfo_t;
 
-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__
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
new file mode 100644
index 000000000000..36fb1a6a5109
--- /dev/null
+++ b/arch/x86/include/asm/init.h
@@ -0,0 +1,18 @@
+#ifndef _ASM_X86_INIT_32_H
+#define _ASM_X86_INIT_32_H
+
+#ifdef CONFIG_X86_32
+extern void __init early_ioremap_page_table_range_init(void);
+#endif
+
+extern unsigned long __init
+kernel_physical_mapping_init(unsigned long start,
+                             unsigned long end,
+                             unsigned long page_size_mask);
+
+
+extern unsigned long __initdata e820_table_start;
+extern unsigned long __meminitdata e820_table_end;
+extern unsigned long __meminitdata e820_table_top;
+
+#endif /* _ASM_X86_INIT_32_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 1dbbdf4be9b4..e5383e3d2f8c 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -5,6 +5,7 @@
 
 #include <linux/compiler.h>
 #include <asm-generic/int-ll64.h>
+#include <asm/page.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -80,6 +81,98 @@ static inline void writeq(__u64 val, volatile void __iomem *addr)
 #define readq                   readq
 #define writeq                  writeq
 
+/**
+ *      virt_to_phys    -       map virtual addresses to physical
+ *      @address: address to remap
+ *
+ *      The returned physical address is the physical (CPU) mapping for
+ *      the memory address given. It is only valid to use this function on
+ *      addresses directly mapped or allocated via kmalloc.
+ *
+ *      This function does not give bus mappings for DMA transfers. In
+ *      almost all conceivable cases a device driver should not be using
+ *      this function
+ */
+
+static inline phys_addr_t virt_to_phys(volatile void *address)
+{
+        return __pa(address);
+}
+
+/**
+ *      phys_to_virt    -       map physical address to virtual
+ *      @address: address to remap
+ *
+ *      The returned virtual address is a current CPU mapping for
+ *      the memory address given. It is only valid to use this function on
+ *      addresses that have a kernel mapping
+ *
+ *      This function does not handle bus mappings for DMA transfers. In
+ *      almost all conceivable cases a device driver should not be using
+ *      this function
+ */
+
+static inline void *phys_to_virt(phys_addr_t address)
+{
+        return __va(address);
+}
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ * However, we truncate the address to unsigned int to avoid undesirable
+ * promitions in legacy drivers.
+ */
+static inline unsigned int isa_virt_to_bus(volatile void *address)
+{
+        return (unsigned int)virt_to_phys(address);
+}
+#define isa_page_to_bus(page)   ((unsigned int)page_to_phys(page))
+#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
+
+/**
+ * ioremap     -   map bus memory into CPU space
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * If the area you are trying to map is a PCI BAR you should have a
+ * look at pci_iomap().
+ */
+extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+                                unsigned long prot_val);
+
+/*
+ * The default ioremap() behavior is non-cached:
+ */
+static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
+{
+        return ioremap_nocache(offset, size);
+}
+
+extern void iounmap(volatile void __iomem *addr);
+
+
 #ifdef CONFIG_X86_32
 # include "io_32.h"
 #else
@@ -91,7 +184,7 @@ extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
 
 extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
                                 unsigned long prot_val);
-extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
+extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
 
 /*
  * early_ioremap() and early_iounmap() are for temporary early boot-time
@@ -103,7 +196,7 @@ extern void early_ioremap_reset(void);
 extern void __iomem *early_ioremap(unsigned long offset, unsigned long size);
 extern void __iomem *early_memremap(unsigned long offset, unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 
+#define IO_SPACE_LIMIT 0xffff
 
 #endif /* _ASM_X86_IO_H */
diff --git a/arch/x86/include/asm/io_32.h b/arch/x86/include/asm/io_32.h
index d8e242e1b396..a299900f5920 100644
--- a/arch/x86/include/asm/io_32.h
+++ b/arch/x86/include/asm/io_32.h
@@ -37,8 +37,6 @@
   *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
   */
 
-#define IO_SPACE_LIMIT 0xffff
-
 #define XQUAD_PORTIO_BASE 0xfe400000
 #define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
 
@@ -53,92 +51,6 @@
  */
 #define xlate_dev_kmem_ptr(p)   p
 
-/**
- *      virt_to_phys    -       map virtual addresses to physical
- *      @address: address to remap
- *
- *      The returned physical address is the physical (CPU) mapping for
- *      the memory address given. It is only valid to use this function on
- *      addresses directly mapped or allocated via kmalloc.
- *
- *      This function does not give bus mappings for DMA transfers. In
- *      almost all conceivable cases a device driver should not be using
- *      this function
- */
-
-static inline unsigned long virt_to_phys(volatile void *address)
-{
-        return __pa(address);
-}
-
-/**
- *      phys_to_virt    -       map physical address to virtual
- *      @address: address to remap
- *
- *      The returned virtual address is a current CPU mapping for
- *      the memory address given. It is only valid to use this function on
- *      addresses that have a kernel mapping
- *
- *      This function does not handle bus mappings for DMA transfers. In
- *      almost all conceivable cases a device driver should not be using
- *      this function
- */
-
-static inline void *phys_to_virt(unsigned long address)
-{
-        return __va(address);
-}
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
-/**
- * ioremap     -   map bus memory into CPU space
- * @offset:    bus address of the memory
- * @size:      size of the resource to map
- *
- * ioremap performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- *
- * If the area you are trying to map is a PCI BAR you should have a
- * look at pci_iomap().
- */
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-                                unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
-static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
-{
-        return ioremap_nocache(offset, 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
-
 static inline void
 memset_io(volatile void __iomem *addr, unsigned char val, int count)
 {
diff --git a/arch/x86/include/asm/io_64.h b/arch/x86/include/asm/io_64.h
index 563c16270ba6..244067893af4 100644
--- a/arch/x86/include/asm/io_64.h
+++ b/arch/x86/include/asm/io_64.h
@@ -136,73 +136,12 @@ __OUTS(b)
 __OUTS(w)
 __OUTS(l)
 
-#define IO_SPACE_LIMIT 0xffff
-
 #if defined(__KERNEL__) && defined(__x86_64__)
 
 #include <linux/vmalloc.h>
 
-#ifndef __i386__
-/*
- * Change virtual addresses to physical addresses and vv.
- * These are pretty trivial
- */
-static inline unsigned long virt_to_phys(volatile void *address)
-{
-        return __pa(address);
-}
-
-static inline void *phys_to_virt(unsigned long address)
-{
-        return __va(address);
-}
-#endif
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
 #include <asm-generic/iomap.h>
 
-/*
- * 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(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-                                unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
-static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
-{
-        return ioremap_nocache(offset, size);
-}
-
-extern void iounmap(volatile void __iomem *addr);
-
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
-
-/*
- * ISA I/O bus memory addresses are 1:1 with the physical address.
- */
-#define isa_virt_to_bus virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
-
-/*
- * However PCI ones are not necessarily 1:1 and therefore these interfaces
- * are forbidden in portable PCI drivers.
- *
- * Allow them on x86 for legacy drivers, though.
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
 void __memcpy_fromio(void *, unsigned long, unsigned);
 void __memcpy_toio(unsigned long, const void *, unsigned);
 
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 7a1f44ac1f17..373cc2bbcad2 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -114,38 +114,16 @@ struct IR_IO_APIC_route_entry {
 extern int nr_ioapics;
 extern int nr_ioapic_registers[MAX_IO_APICS];
 
-/*
- * MP-BIOS irq configuration table structures:
- */
-
 #define MP_MAX_IOAPIC_PIN 127
 
-struct mp_config_ioapic {
-        unsigned long mp_apicaddr;
-        unsigned int mp_apicid;
-        unsigned char mp_type;
-        unsigned char mp_apicver;
-        unsigned char mp_flags;
-};
-
-struct mp_config_intsrc {
-        unsigned int mp_dstapic;
-        unsigned char mp_type;
-        unsigned char mp_irqtype;
-        unsigned short mp_irqflag;
-        unsigned char mp_srcbus;
-        unsigned char mp_srcbusirq;
-        unsigned char mp_dstirq;
-};
-
 /* I/O APIC entries */
-extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+extern struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
 
 /* MP IRQ source entries */
-extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
 /* non-0 if default (table-less) MP configuration */
 extern int mpc_default_type;
@@ -165,15 +143,6 @@ extern int noioapicreroute;
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 
-static inline void disable_ioapic_setup(void)
-{
-#ifdef CONFIG_PCI
-        noioapicquirk = 1;
-        noioapicreroute = -1;
-#endif
-        skip_ioapic_setup = 1;
-}
-
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.
@@ -193,13 +162,20 @@ extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
 
 #ifdef CONFIG_X86_64
-extern int save_mask_IO_APIC_setup(void);
+extern int save_IO_APIC_setup(void);
+extern void mask_IO_APIC_setup(void);
 extern void restore_IO_APIC_setup(void);
 extern void reinit_intr_remapped_IO_APIC(int);
 #endif
 
 extern void probe_nr_irqs_gsi(void);
 
+extern int setup_ioapic_entry(int apic, int irq,
+                              struct IO_APIC_route_entry *entry,
+                              unsigned int destination, int trigger,
+                              int polarity, int vector, int pin);
+extern void ioapic_write_entry(int apic, int pin,
+                               struct IO_APIC_route_entry e);
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
 static const int timer_through_8259 = 0;
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index a6ee9e6f530f..af326a2975b5 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -3,7 +3,7 @@
 
 extern void pci_iommu_shutdown(void);
 extern void no_iommu_init(void);
-extern struct dma_mapping_ops nommu_dma_ops;
+extern struct dma_map_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
index c745a306f7d3..0b7228268a63 100644
--- a/arch/x86/include/asm/ipi.h
+++ b/arch/x86/include/asm/ipi.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_IPI_H
 #define _ASM_X86_IPI_H
 
+#ifdef CONFIG_X86_LOCAL_APIC
+
 /*
  * Copyright 2004 James Cleverdon, IBM.
  * Subject to the GNU Public License, v.2
@@ -55,8 +57,8 @@ static inline void __xapic_wait_icr_idle(void)
                 cpu_relax();
 }
 
-static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
-                                       unsigned int dest)
+static inline void
+__default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
 {
         /*
          * Subtle. In the case of the 'never do double writes' workaround
@@ -87,8 +89,8 @@ static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
  * This is used to send an IPI with no shorthand notation (the destination is
  * specified in bits 56 to 63 of the ICR).
  */
-static inline void __send_IPI_dest_field(unsigned int mask, int vector,
-                                         unsigned int dest)
+static inline void
+ __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest)
 {
         unsigned long cfg;
 
@@ -117,41 +119,44 @@ static inline void __send_IPI_dest_field(unsigned int mask, int vector,
         native_apic_mem_write(APIC_ICR, cfg);
 }
 
-static inline void send_IPI_mask_sequence(const struct cpumask *mask,
-                                          int vector)
-{
-        unsigned long flags;
-        unsigned long query_cpu;
+extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask,
+                                                 int vector);
+extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
+                                                         int vector);
+extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+                                                         int vector);
+extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+                                                         int vector);
 
-        /*
-         * Hack. The clustered APIC addressing mode doesn't allow us to send
-         * to an arbitrary mask, so I do a unicast to each CPU instead.
-         * - mbligh
-         */
-        local_irq_save(flags);
-        for_each_cpu(query_cpu, mask) {
-                __send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu),
-                                      vector, APIC_DEST_PHYSICAL);
-        }
-        local_irq_restore(flags);
+/* Avoid include hell */
+#define NMI_VECTOR 0x02
+
+extern int no_broadcast;
+
+static inline void __default_local_send_IPI_allbutself(int vector)
+{
+        if (no_broadcast || vector == NMI_VECTOR)
+                apic->send_IPI_mask_allbutself(cpu_online_mask, vector);
+        else
+                __default_send_IPI_shortcut(APIC_DEST_ALLBUT, vector, apic->dest_logical);
 }
 
-static inline void send_IPI_mask_allbutself(const struct cpumask *mask,
-                                            int vector)
+static inline void __default_local_send_IPI_all(int vector)
 {
-        unsigned long flags;
-        unsigned int query_cpu;
-        unsigned int this_cpu = smp_processor_id();
-
-        /* See Hack comment above */
-
-        local_irq_save(flags);
-        for_each_cpu(query_cpu, mask)
-                if (query_cpu != this_cpu)
-                        __send_IPI_dest_field(
-                                per_cpu(x86_cpu_to_apicid, query_cpu),
-                                vector, APIC_DEST_PHYSICAL);
-        local_irq_restore(flags);
+        if (no_broadcast || vector == NMI_VECTOR)
+                apic->send_IPI_mask(cpu_online_mask, vector);
+        else
+                __default_send_IPI_shortcut(APIC_DEST_ALLINC, vector, apic->dest_logical);
 }
 
+#ifdef CONFIG_X86_32
+extern void default_send_IPI_mask_logical(const struct cpumask *mask,
+                                                 int vector);
+extern void default_send_IPI_allbutself(int vector);
+extern void default_send_IPI_all(int vector);
+extern void default_send_IPI_self(int vector);
+#endif
+
+#endif
+
 #endif /* _ASM_X86_IPI_H */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 592688ed04d3..f38481bcd455 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -36,9 +36,12 @@ static inline int irq_canonicalize(int irq)
 extern void fixup_irqs(void);
 #endif
 
-extern unsigned int do_IRQ(struct pt_regs *regs);
+extern void (*generic_interrupt_extension)(void);
 extern void init_IRQ(void);
 extern void native_init_IRQ(void);
+extern bool handle_irq(unsigned irq, struct pt_regs *regs);
+
+extern unsigned int do_IRQ(struct pt_regs *regs);
 
 /* Interrupt vector management */
 extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h
index 89c898ab298b..77843225b7ea 100644
--- a/arch/x86/include/asm/irq_regs.h
+++ b/arch/x86/include/asm/irq_regs.h
@@ -1,5 +1,31 @@
-#ifdef CONFIG_X86_32
-# include "irq_regs_32.h"
-#else
-# include "irq_regs_64.h"
-#endif
+/*
+ * Per-cpu current frame pointer - the location of the last exception frame on
+ * the stack, stored in the per-cpu area.
+ *
+ * Jeremy Fitzhardinge <jeremy@goop.org>
+ */
+#ifndef _ASM_X86_IRQ_REGS_H
+#define _ASM_X86_IRQ_REGS_H
+
+#include <asm/percpu.h>
+
+#define ARCH_HAS_OWN_IRQ_REGS
+
+DECLARE_PER_CPU(struct pt_regs *, irq_regs);
+
+static inline struct pt_regs *get_irq_regs(void)
+{
+        return percpu_read(irq_regs);
+}
+
+static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
+{
+        struct pt_regs *old_regs;
+
+        old_regs = get_irq_regs();
+        percpu_write(irq_regs, new_regs);
+
+        return old_regs;
+}
+
+#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
deleted file mode 100644
index 86afd7473457..000000000000
--- a/arch/x86/include/asm/irq_regs_32.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Per-cpu current frame pointer - the location of the last exception frame on
- * the stack, stored in the per-cpu area.
- *
- * Jeremy Fitzhardinge <jeremy@goop.org>
- */
-#ifndef _ASM_X86_IRQ_REGS_32_H
-#define _ASM_X86_IRQ_REGS_32_H
-
-#include <asm/percpu.h>
-
-#define ARCH_HAS_OWN_IRQ_REGS
-
-DECLARE_PER_CPU(struct pt_regs *, irq_regs);
-
-static inline struct pt_regs *get_irq_regs(void)
-{
-        return x86_read_percpu(irq_regs);
-}
-
-static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
-{
-        struct pt_regs *old_regs;
-
-        old_regs = get_irq_regs();
-        x86_write_percpu(irq_regs, new_regs);
-
-        return old_regs;
-}
-
-#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_64.h b/arch/x86/include/asm/irq_regs_64.h
deleted file mode 100644
index 3dd9c0b70270..000000000000
--- a/arch/x86/include/asm/irq_regs_64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 20e1fd588dbf..0396760fccb8 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -1,8 +1,6 @@
 #ifndef _ASM_X86_IRQ_REMAPPING_H
 #define _ASM_X86_IRQ_REMAPPING_H
 
-extern int x2apic;
-
 #define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8)
 
 #endif  /* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index f7ff65032b9d..3cbd79bbb47c 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -1,47 +1,69 @@
 #ifndef _ASM_X86_IRQ_VECTORS_H
 #define _ASM_X86_IRQ_VECTORS_H
 
-#include <linux/threads.h>
+/*
+ * Linux IRQ vector layout.
+ *
+ * There are 256 IDT entries (per CPU - each entry is 8 bytes) which can
+ * be defined by Linux. They are used as a jump table by the CPU when a
+ * given vector is triggered - by a CPU-external, CPU-internal or
+ * software-triggered event.
+ *
+ * Linux sets the kernel code address each entry jumps to early during
+ * bootup, and never changes them. This is the general layout of the
+ * IDT entries:
+ *
+ *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
+ *  Vectors  32 ... 127 : device interrupts
+ *  Vector  128         : legacy int80 syscall interface
+ *  Vectors 129 ... 237 : device interrupts
+ *  Vectors 238 ... 255 : special interrupts
+ *
+ * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
+ *
+ * This file enumerates the exact layout of them:
+ */
 
-#define NMI_VECTOR              0x02
+#define NMI_VECTOR                      0x02
 
 /*
  * IDT vectors usable for external interrupt sources start
  * at 0x20:
  */
-#define FIRST_EXTERNAL_VECTOR   0x20
+#define FIRST_EXTERNAL_VECTOR           0x20
 
 #ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR         0x80
+# define SYSCALL_VECTOR                 0x80
 #else
-# define IA32_SYSCALL_VECTOR    0x80
+# define IA32_SYSCALL_VECTOR            0x80
 #endif
 
 /*
  * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
  * cleanup after irq migration.
  */
-#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR
+#define IRQ_MOVE_CLEANUP_VECTOR         FIRST_EXTERNAL_VECTOR
 
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.
  */
-#define IRQ0_VECTOR             (FIRST_EXTERNAL_VECTOR + 0x10)
-#define IRQ1_VECTOR             (IRQ0_VECTOR + 1)
-#define IRQ2_VECTOR             (IRQ0_VECTOR + 2)
-#define IRQ3_VECTOR             (IRQ0_VECTOR + 3)
-#define IRQ4_VECTOR             (IRQ0_VECTOR + 4)
-#define IRQ5_VECTOR             (IRQ0_VECTOR + 5)
-#define IRQ6_VECTOR             (IRQ0_VECTOR + 6)
-#define IRQ7_VECTOR             (IRQ0_VECTOR + 7)
-#define IRQ8_VECTOR             (IRQ0_VECTOR + 8)
-#define IRQ9_VECTOR             (IRQ0_VECTOR + 9)
-#define IRQ10_VECTOR            (IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR            (IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR            (IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR            (IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR            (IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR            (IRQ0_VECTOR + 15)
+#define IRQ0_VECTOR                     (FIRST_EXTERNAL_VECTOR + 0x10)
+
+#define IRQ1_VECTOR                     (IRQ0_VECTOR +  1)
+#define IRQ2_VECTOR                     (IRQ0_VECTOR +  2)
+#define IRQ3_VECTOR                     (IRQ0_VECTOR +  3)
+#define IRQ4_VECTOR                     (IRQ0_VECTOR +  4)
+#define IRQ5_VECTOR                     (IRQ0_VECTOR +  5)
+#define IRQ6_VECTOR                     (IRQ0_VECTOR +  6)
+#define IRQ7_VECTOR                     (IRQ0_VECTOR +  7)
+#define IRQ8_VECTOR                     (IRQ0_VECTOR +  8)
+#define IRQ9_VECTOR                     (IRQ0_VECTOR +  9)
+#define IRQ10_VECTOR                    (IRQ0_VECTOR + 10)
+#define IRQ11_VECTOR                    (IRQ0_VECTOR + 11)
+#define IRQ12_VECTOR                    (IRQ0_VECTOR + 12)
+#define IRQ13_VECTOR                    (IRQ0_VECTOR + 13)
+#define IRQ14_VECTOR                    (IRQ0_VECTOR + 14)
+#define IRQ15_VECTOR                    (IRQ0_VECTOR + 15)
 
 /*
  * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
@@ -49,119 +71,103 @@
  *  some of the following vectors are 'rare', they are merged
  *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
  *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
  */
-#ifdef CONFIG_X86_32
-
-# define SPURIOUS_APIC_VECTOR           0xff
-# define ERROR_APIC_VECTOR              0xfe
-# define INVALIDATE_TLB_VECTOR          0xfd
-# define RESCHEDULE_VECTOR              0xfc
-# define CALL_FUNCTION_VECTOR           0xfb
-# define CALL_FUNCTION_SINGLE_VECTOR    0xfa
-# define THERMAL_APIC_VECTOR            0xf0
-
-#else
 
 #define SPURIOUS_APIC_VECTOR            0xff
+/*
+ * Sanity check
+ */
+#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F)
+# error SPURIOUS_APIC_VECTOR definition error
+#endif
+
 #define ERROR_APIC_VECTOR               0xfe
 #define RESCHEDULE_VECTOR               0xfd
 #define CALL_FUNCTION_VECTOR            0xfc
 #define CALL_FUNCTION_SINGLE_VECTOR     0xfb
 #define THERMAL_APIC_VECTOR             0xfa
-#define THRESHOLD_APIC_VECTOR           0xf9
-#define UV_BAU_MESSAGE                  0xf8
-#define INVALIDATE_TLB_VECTOR_END       0xf7
-#define INVALIDATE_TLB_VECTOR_START     0xf0    /* f0-f7 used for TLB flush */
-
-#define NUM_INVALIDATE_TLB_VECTORS      8
 
+#ifdef CONFIG_X86_32
+/* 0xf8 - 0xf9 : free */
+#else
+# define THRESHOLD_APIC_VECTOR          0xf9
+# define UV_BAU_MESSAGE                 0xf8
 #endif
 
+/* f0-f7 used for spreading out TLB flushes: */
+#define INVALIDATE_TLB_VECTOR_END       0xf7
+#define INVALIDATE_TLB_VECTOR_START     0xf0
+#define NUM_INVALIDATE_TLB_VECTORS         8
+
 /*
  * Local APIC timer IRQ vector is on a different priority level,
  * to work around the 'lost local interrupt if more than 2 IRQ
  * sources per level' errata.
  */
-#define LOCAL_TIMER_VECTOR      0xef
+#define LOCAL_TIMER_VECTOR              0xef
+
+/*
+ * Performance monitoring interrupt vector:
+ */
+#define LOCAL_PERF_VECTOR               0xee
+
+/*
+ * Generic system vector for platform specific use
+ */
+#define GENERIC_INTERRUPT_VECTOR        0xed
 
 /*
  * First APIC vector available to drivers: (vectors 0x30-0xee) we
  * start at 0x31(0x41) to spread out vectors evenly between priority
  * levels. (0x80 is the syscall vector)
  */
-#define FIRST_DEVICE_VECTOR     (IRQ15_VECTOR + 2)
+#define FIRST_DEVICE_VECTOR             (IRQ15_VECTOR + 2)
 
-#define NR_VECTORS              256
+#define NR_VECTORS                       256
 
-#define FPU_IRQ                 13
+#define FPU_IRQ                           13
 
-#define FIRST_VM86_IRQ          3
-#define LAST_VM86_IRQ           15
-#define invalid_vm86_irq(irq)   ((irq) < 3 || (irq) > 15)
+#define FIRST_VM86_IRQ                     3
+#define LAST_VM86_IRQ                     15
 
-#define NR_IRQS_LEGACY          16
-
-#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
-
-#ifndef CONFIG_SPARSE_IRQ
-# if NR_CPUS < MAX_IO_APICS
-#  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
-# else
-#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
-#else
-# if (8 * NR_CPUS) > (32 * MAX_IO_APICS)
-#  define NR_IRQS (NR_VECTORS + (8 * NR_CPUS))
-# else
-#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
+#ifndef __ASSEMBLY__
+static inline int invalid_vm86_irq(int irq)
+{
+        return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ;
+}
 #endif
 
-#elif defined(CONFIG_X86_VOYAGER)
-
-# define NR_IRQS                224
+/*
+ * Size the maximum number of interrupts.
+ *
+ * If the irq_desc[] array has a sparse layout, we can size things
+ * generously - it scales up linearly with the maximum number of CPUs,
+ * and the maximum number of IO-APICs, whichever is higher.
+ *
+ * In other cases we size more conservatively, to not create too large
+ * static arrays.
+ */
 
-#else /* IO_APIC || VOYAGER */
+#define NR_IRQS_LEGACY                    16
 
-# define NR_IRQS                16
+#define CPU_VECTOR_LIMIT                (  8 * NR_CPUS      )
+#define IO_APIC_VECTOR_LIMIT            ( 32 * MAX_IO_APICS )
 
+#ifdef CONFIG_X86_IO_APIC
+# ifdef CONFIG_SPARSE_IRQ
+#  define NR_IRQS                                       \
+        (CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ?      \
+                (NR_VECTORS + CPU_VECTOR_LIMIT)  :      \
+                (NR_VECTORS + IO_APIC_VECTOR_LIMIT))
+# else
+#  if NR_CPUS < MAX_IO_APICS
+#   define NR_IRQS                      (NR_VECTORS + 4*CPU_VECTOR_LIMIT)
+#  else
+#   define NR_IRQS                      (NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#  endif
+# endif
+#else /* !CONFIG_X86_IO_APIC: */
+# define NR_IRQS                        NR_IRQS_LEGACY
 #endif
 
-/* Voyager specific defines */
-/* These define the CPIs we use in linux */
-#define VIC_CPI_LEVEL0                  0
-#define VIC_CPI_LEVEL1                  1
-/* now the fake CPIs */
-#define VIC_TIMER_CPI                   2
-#define VIC_INVALIDATE_CPI              3
-#define VIC_RESCHEDULE_CPI              4
-#define VIC_ENABLE_IRQ_CPI              5
-#define VIC_CALL_FUNCTION_CPI           6
-#define VIC_CALL_FUNCTION_SINGLE_CPI    7
-
-/* Now the QIC CPIs:  Since we don't need the two initial levels,
- * these are 2 less than the VIC CPIs */
-#define QIC_CPI_OFFSET                  1
-#define QIC_TIMER_CPI                   (VIC_TIMER_CPI - QIC_CPI_OFFSET)
-#define QIC_INVALIDATE_CPI              (VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
-#define QIC_RESCHEDULE_CPI              (VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
-#define QIC_ENABLE_IRQ_CPI              (VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_CPI           (VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_SINGLE_CPI    (VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
-
-#define VIC_START_FAKE_CPI              VIC_TIMER_CPI
-#define VIC_END_FAKE_CPI                VIC_CALL_FUNCTION_SINGLE_CPI
-
-/* this is the SYS_INT CPI. */
-#define VIC_SYS_INT                     8
-#define VIC_CMN_INT                     15
-
-/* This is the boot CPI for alternate processors.  It gets overwritten
- * by the above once the system has activated all available processors */
-#define VIC_CPU_BOOT_CPI                VIC_CPI_LEVEL0
-#define VIC_CPU_BOOT_ERRATA_CPI         (VIC_CPI_LEVEL0 + 8)
-
-
 #endif /* _ASM_X86_IRQ_VECTORS_H */
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index c61d8b2ab8b9..317ff1703d0b 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -10,27 +10,12 @@
 #else
 # define PA_CONTROL_PAGE        0
 # define VA_CONTROL_PAGE        1
-# define PA_PGD                 2
-# define VA_PGD                 3
-# define PA_PUD_0               4
-# define VA_PUD_0               5
-# define PA_PMD_0               6
-# define VA_PMD_0               7
-# define PA_PTE_0               8
-# define VA_PTE_0               9
-# define PA_PUD_1               10
-# define VA_PUD_1               11
-# define PA_PMD_1               12
-# define VA_PMD_1               13
-# define PA_PTE_1               14
-# define VA_PTE_1               15
-# define PA_TABLE_PAGE          16
-# define PAGES_NR               17
+# define PA_TABLE_PAGE          2
+# define PA_SWAP_PAGE           3
+# define PAGES_NR               4
 #endif
 
-#ifdef CONFIG_X86_32
 # define KEXEC_CONTROL_CODE_MAX_SIZE    2048
-#endif
 
 #ifndef __ASSEMBLY__
 
@@ -151,15 +136,16 @@ relocate_kernel(unsigned long indirection_page,
                 unsigned int has_pae,
                 unsigned int preserve_context);
 #else
-NORET_TYPE void
+unsigned long
 relocate_kernel(unsigned long indirection_page,
                 unsigned long page_list,
-                unsigned long start_address) ATTRIB_NORET;
+                unsigned long start_address,
+                unsigned int preserve_context);
 #endif
 
-#ifdef CONFIG_X86_32
 #define ARCH_HAS_KIMAGE_ARCH
 
+#ifdef CONFIG_X86_32
 struct kimage_arch {
         pgd_t *pgd;
 #ifdef CONFIG_X86_PAE
@@ -169,6 +155,12 @@ struct kimage_arch {
         pte_t *pte0;
         pte_t *pte1;
 };
+#else
+struct kimage_arch {
+        pud_t *pud;
+        pmd_t *pmd;
+        pte_t *pte;
+};
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 886c9402ec45..dc3f6cf11704 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -15,6 +15,7 @@
 #define __KVM_HAVE_DEVICE_ASSIGNMENT
 #define __KVM_HAVE_MSI
 #define __KVM_HAVE_USER_NMI
+#define __KVM_HAVE_GUEST_DEBUG
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -212,7 +213,30 @@ struct kvm_pit_channel_state {
         __s64 count_load_time;
 };
 
+struct kvm_debug_exit_arch {
+        __u32 exception;
+        __u32 pad;
+        __u64 pc;
+        __u64 dr6;
+        __u64 dr7;
+};
+
+#define KVM_GUESTDBG_USE_SW_BP          0x00010000
+#define KVM_GUESTDBG_USE_HW_BP          0x00020000
+#define KVM_GUESTDBG_INJECT_DB          0x00040000
+#define KVM_GUESTDBG_INJECT_BP          0x00080000
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+        __u64 debugreg[8];
+};
+
 struct kvm_pit_state {
         struct kvm_pit_channel_state channels[3];
 };
+
+struct kvm_reinject_control {
+        __u8 pit_reinject;
+        __u8 reserved[31];
+};
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 730843d1d2fb..f0faf58044ff 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -22,6 +22,7 @@
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
+#include <asm/msr-index.h>
 
 #define KVM_MAX_VCPUS 16
 #define KVM_MEMORY_SLOTS 32
@@ -134,11 +135,18 @@ enum {
 
 #define KVM_NR_MEM_OBJS 40
 
-struct kvm_guest_debug {
-        int enabled;
-        unsigned long bp[4];
-        int singlestep;
-};
+#define KVM_NR_DB_REGS  4
+
+#define DR6_BD          (1 << 13)
+#define DR6_BS          (1 << 14)
+#define DR6_FIXED_1     0xffff0ff0
+#define DR6_VOLATILE    0x0000e00f
+
+#define DR7_BP_EN_MASK  0x000000ff
+#define DR7_GE          (1 << 9)
+#define DR7_GD          (1 << 13)
+#define DR7_FIXED_1     0x00000400
+#define DR7_VOLATILE    0xffff23ff
 
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
@@ -162,7 +170,8 @@ struct kvm_pte_chain {
  *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
  *   bits 4:7 - page table level for this shadow (1-4)
  *   bits 8:9 - page table quadrant for 2-level guests
- *   bit   16 - "metaphysical" - gfn is not a real page (huge page/real mode)
+ *   bit   16 - direct mapping of virtual to physical mapping at gfn
+ *              used for real mode and two-dimensional paging
  *   bits 17:19 - common access permissions for all ptes in this shadow page
  */
 union kvm_mmu_page_role {
@@ -172,9 +181,10 @@ union kvm_mmu_page_role {
                 unsigned level:4;
                 unsigned quadrant:2;
                 unsigned pad_for_nice_hex_output:6;
-                unsigned metaphysical:1;
+                unsigned direct:1;
                 unsigned access:3;
                 unsigned invalid:1;
+                unsigned cr4_pge:1;
         };
 };
 
@@ -218,6 +228,18 @@ struct kvm_pv_mmu_op_buffer {
         char buf[512] __aligned(sizeof(long));
 };
 
+struct kvm_pio_request {
+        unsigned long count;
+        int cur_count;
+        gva_t guest_gva;
+        int in;
+        int port;
+        int size;
+        int string;
+        int down;
+        int rep;
+};
+
 /*
  * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
  * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
@@ -236,6 +258,7 @@ struct kvm_mmu {
         hpa_t root_hpa;
         int root_level;
         int shadow_root_level;
+        union kvm_mmu_page_role base_role;
 
         u64 *pae_root;
 };
@@ -258,6 +281,7 @@ struct kvm_vcpu_arch {
         unsigned long cr3;
         unsigned long cr4;
         unsigned long cr8;
+        u32 hflags;
         u64 pdptrs[4]; /* pae */
         u64 shadow_efer;
         u64 apic_base;
@@ -338,6 +362,15 @@ struct kvm_vcpu_arch {
 
         struct mtrr_state_type mtrr_state;
         u32 pat;
+
+        int switch_db_regs;
+        unsigned long host_db[KVM_NR_DB_REGS];
+        unsigned long host_dr6;
+        unsigned long host_dr7;
+        unsigned long db[KVM_NR_DB_REGS];
+        unsigned long dr6;
+        unsigned long dr7;
+        unsigned long eff_db[KVM_NR_DB_REGS];
 };
 
 struct kvm_mem_alias {
@@ -378,6 +411,7 @@ struct kvm_arch{
 
         unsigned long irq_sources_bitmap;
         unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
+        u64 vm_init_tsc;
 };
 
 struct kvm_vm_stat {
@@ -446,8 +480,7 @@ struct kvm_x86_ops {
         void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
         int (*set_guest_debug)(struct kvm_vcpu *vcpu,
-                               struct kvm_debug_guest *dbg);
-        void (*guest_debug_pre)(struct kvm_vcpu *vcpu);
+                               struct kvm_guest_debug *dbg);
         int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
         int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
         u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
@@ -583,16 +616,12 @@ void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
                            u32 error_code);
 
-void kvm_pic_set_irq(void *opaque, int irq, int level);
+int kvm_pic_set_irq(void *opaque, int irq, int level);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
 void fx_init(struct kvm_vcpu *vcpu);
 
-int emulator_read_std(unsigned long addr,
-                      void *val,
-                      unsigned int bytes,
-                      struct kvm_vcpu *vcpu);
 int emulator_write_emulated(unsigned long addr,
                             const void *val,
                             unsigned int bytes,
@@ -737,6 +766,10 @@ enum {
         TASK_SWITCH_GATE = 3,
 };
 
+#define HF_GIF_MASK             (1 << 0)
+#define HF_HIF_MASK             (1 << 1)
+#define HF_VINTR_MASK           (1 << 2)
+
 /*
  * Hardware virtualization extension instructions may fault if a
  * reboot turns off virtualization while processes are running.
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index 43894428c3c2..0f4ee7148afe 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -26,36 +26,20 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/hw_irq.h>
+#include <asm/kvm_para.h>
 
 /*G:031 But first, how does our Guest contact the Host to ask for privileged
  * operations?  There are two ways: the direct way is to make a "hypercall",
  * to make requests of the Host Itself.
  *
- * Our hypercall mechanism uses the highest unused trap code (traps 32 and
- * above are used by real hardware interrupts).  Fifteen hypercalls are
+ * We use the KVM hypercall mechanism. Eighteen hypercalls are
  * available: the hypercall number is put in the %eax register, and the
- * arguments (when required) are placed in %edx, %ebx and %ecx.  If a return
+ * arguments (when required) are placed in %ebx, %ecx and %edx.  If a return
  * value makes sense, it's returned in %eax.
  *
  * Grossly invalid calls result in Sudden Death at the hands of the vengeful
  * Host, rather than returning failure.  This reflects Winston Churchill's
  * definition of a gentleman: "someone who is only rude intentionally". */
-static inline unsigned long
-hcall(unsigned long call,
-      unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
-        /* "int" is the Intel instruction to trigger a trap. */
-        asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY)
-                     /* The call in %eax (aka "a") might be overwritten */
-                     : "=a"(call)
-                       /* The arguments are in %eax, %edx, %ebx & %ecx */
-                     : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3)
-                       /* "memory" means this might write somewhere in memory.
-                        * This isn't true for all calls, but it's safe to tell
-                        * gcc that it might happen so it doesn't get clever. */
-                     : "memory");
-        return call;
-}
 /*:*/
 
 /* Can't use our min() macro here: needs to be a constant */
@@ -64,7 +48,7 @@ hcall(unsigned long call,
 #define LHCALL_RING_SIZE 64
 struct hcall_args {
         /* These map directly onto eax, ebx, ecx, edx in struct lguest_regs */
-        unsigned long arg0, arg2, arg3, arg1;
+        unsigned long arg0, arg1, arg2, arg3;
 };
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 5d98d0b68ffc..12d55e773eb6 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -1,14 +1,11 @@
 #ifndef _ASM_X86_LINKAGE_H
 #define _ASM_X86_LINKAGE_H
 
+#include <linux/stringify.h>
+
 #undef notrace
 #define notrace __attribute__((no_instrument_function))
 
-#ifdef CONFIG_X86_64
-#define __ALIGN .p2align 4,,15
-#define __ALIGN_STR ".p2align 4,,15"
-#endif
-
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
 /*
@@ -50,72 +47,20 @@
         __asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
                               "g" (arg4), "g" (arg5), "g" (arg6))
 
-#endif
-
-#ifdef CONFIG_X86_ALIGNMENT_16
-#define __ALIGN .align 16,0x90
-#define __ALIGN_STR ".align 16,0x90"
-#endif
-
-/*
- * to check ENTRY_X86/END_X86 and
- * KPROBE_ENTRY_X86/KPROBE_END_X86
- * unbalanced-missed-mixed appearance
- */
-#define __set_entry_x86         .set ENTRY_X86_IN, 0
-#define __unset_entry_x86       .set ENTRY_X86_IN, 1
-#define __set_kprobe_x86        .set KPROBE_X86_IN, 0
-#define __unset_kprobe_x86      .set KPROBE_X86_IN, 1
-
-#define __macro_err_x86 .error "ENTRY_X86/KPROBE_X86 unbalanced,missed,mixed"
-
-#define __check_entry_x86       \
-        .ifdef ENTRY_X86_IN;    \
-        .ifeq ENTRY_X86_IN;     \
-        __macro_err_x86;        \
-        .abort;                 \
-        .endif;                 \
-        .endif
-
-#define __check_kprobe_x86      \
-        .ifdef KPROBE_X86_IN;   \
-        .ifeq KPROBE_X86_IN;    \
-        __macro_err_x86;        \
-        .abort;                 \
-        .endif;                 \
-        .endif
+#endif /* CONFIG_X86_32 */
 
-#define __check_entry_kprobe_x86        \
-        __check_entry_x86;              \
-        __check_kprobe_x86
+#ifdef __ASSEMBLY__
 
-#define ENTRY_KPROBE_FINAL_X86 __check_entry_kprobe_x86
-
-#define ENTRY_X86(name)                 \
-        __check_entry_kprobe_x86;       \
-        __set_entry_x86;                \
-        .globl name;                    \
-        __ALIGN;                        \
+#define GLOBAL(name)    \
+        .globl name;    \
         name:
 
-#define END_X86(name)                   \
-        __unset_entry_x86;              \
-        __check_entry_kprobe_x86;       \
-        .size name, .-name
-
-#define KPROBE_ENTRY_X86(name)          \
-        __check_entry_kprobe_x86;       \
-        __set_kprobe_x86;               \
-        .pushsection .kprobes.text, "ax"; \
-        .globl name;                    \
-        __ALIGN;                        \
-        name:
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16)
+#define __ALIGN         .p2align 4, 0x90
+#define __ALIGN_STR     __stringify(__ALIGN)
+#endif
 
-#define KPROBE_END_X86(name)            \
-        __unset_kprobe_x86;             \
-        __check_entry_kprobe_x86;       \
-        .size name, .-name;             \
-        .popsection
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_LINKAGE_H */
 
diff --git a/arch/x86/include/asm/mach-default/mach_apic.h b/arch/x86/include/asm/mach-default/mach_apic.h
deleted file mode 100644
index cc09cbbee27e..000000000000
--- a/arch/x86/include/asm/mach-default/mach_apic.h
+++ /dev/null
@@ -1,168 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_APIC_H
-#define _ASM_X86_MACH_DEFAULT_MACH_APIC_H
-
-#ifdef CONFIG_X86_LOCAL_APIC
-
-#include <mach_apicdef.h>
-#include <asm/smp.h>
-
-#define APIC_DFR_VALUE  (APIC_DFR_FLAT)
-
-static inline const struct cpumask *target_cpus(void)
-{ 
-#ifdef CONFIG_SMP
-        return cpu_online_mask;
-#else
-        return cpumask_of(0);
-#endif
-} 
-
-#define NO_BALANCE_IRQ (0)
-#define esr_disable (0)
-
-#ifdef CONFIG_X86_64
-#include <asm/genapic.h>
-#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
-#define INT_DEST_MODE (genapic->int_dest_mode)
-#define TARGET_CPUS       (genapic->target_cpus())
-#define apic_id_registered (genapic->apic_id_registered)
-#define init_apic_ldr (genapic->init_apic_ldr)
-#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
-#define cpu_mask_to_apicid_and (genapic->cpu_mask_to_apicid_and)
-#define phys_pkg_id     (genapic->phys_pkg_id)
-#define vector_allocation_domain    (genapic->vector_allocation_domain)
-#define read_apic_id()  (GET_APIC_ID(apic_read(APIC_ID)))
-#define send_IPI_self (genapic->send_IPI_self)
-#define wakeup_secondary_cpu (genapic->wakeup_cpu)
-extern void setup_apic_routing(void);
-#else
-#define INT_DELIVERY_MODE dest_LowestPrio
-#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-#define TARGET_CPUS (target_cpus())
-#define wakeup_secondary_cpu wakeup_secondary_cpu_via_init
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-        unsigned long val;
-
-        apic_write(APIC_DFR, APIC_DFR_VALUE);
-        val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-        val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
-        apic_write(APIC_LDR, val);
-}
-
-static inline int apic_id_registered(void)
-{
-        return physid_isset(read_apic_id(), phys_cpu_present_map);
-}
-
-static inline unsigned int cpu_mask_to_apicid(const struct cpumask *cpumask)
-{
-        return cpumask_bits(cpumask)[0];
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-                                                  const struct cpumask *andmask)
-{
-        unsigned long mask1 = cpumask_bits(cpumask)[0];
-        unsigned long mask2 = cpumask_bits(andmask)[0];
-        unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
-
-        return (unsigned int)(mask1 & mask2 & mask3);
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-        return cpuid_apic >> index_msb;
-}
-
-static inline void setup_apic_routing(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-        printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-                                        "Flat", nr_ioapics);
-#endif
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
-        return apicid_2_node[hard_smp_processor_id()];
-#else
-        return 0;
-#endif
-}
-
-static inline void vector_allocation_domain(int cpu, struct cpumask *retmask)
-{
-        /* Careful. Some cpus do not strictly honor the set of cpus
-         * specified in the interrupt destination when using lowest
-         * priority interrupt delivery mode.
-         *
-         * In particular there was a hyperthreading cpu observed to
-         * deliver interrupts to the wrong hyperthread when only one
-         * hyperthread was specified in the interrupt desitination.
-         */
-        *retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } };
-}
-#endif
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-        return physid_isset(apicid, bitmap);
-}
-
-static inline unsigned long check_apicid_present(int bit)
-{
-        return physid_isset(bit, phys_cpu_present_map);
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-        return phys_map;
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-        return 0;
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-        return 1 << cpu;
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-        if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
-                return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
-        else
-                return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-        return physid_mask_of_physid(phys_apicid);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-        return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-#endif /* CONFIG_X86_LOCAL_APIC */
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_APIC_H */
diff --git a/arch/x86/include/asm/mach-default/mach_apicdef.h b/arch/x86/include/asm/mach-default/mach_apicdef.h
deleted file mode 100644
index 53179936d6c6..000000000000
--- a/arch/x86/include/asm/mach-default/mach_apicdef.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H
-#define _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H
-
-#include <asm/apic.h>
-
-#ifdef CONFIG_X86_64
-#define APIC_ID_MASK            (genapic->apic_id_mask)
-#define GET_APIC_ID(x)          (genapic->get_apic_id(x))
-#define SET_APIC_ID(x)          (genapic->set_apic_id(x))
-#else
-#define         APIC_ID_MASK            (0xF<<24)
-static inline unsigned get_apic_id(unsigned long x) 
-{
-        unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
-        if (APIC_XAPIC(ver))
-                return (((x)>>24)&0xFF);
-        else
-                return (((x)>>24)&0xF);
-} 
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-#endif
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H */
diff --git a/arch/x86/include/asm/mach-default/mach_ipi.h b/arch/x86/include/asm/mach-default/mach_ipi.h
deleted file mode 100644
index 191312d155da..000000000000
--- a/arch/x86/include/asm/mach-default/mach_ipi.h
+++ /dev/null
@@ -1,64 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_IPI_H
-#define _ASM_X86_MACH_DEFAULT_MACH_IPI_H
-
-/* Avoid include hell */
-#define NMI_VECTOR 0x02
-
-void send_IPI_mask_bitmask(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-void __send_IPI_shortcut(unsigned int shortcut, int vector);
-
-extern int no_broadcast;
-
-#ifdef CONFIG_X86_64
-#include <asm/genapic.h>
-#define send_IPI_mask (genapic->send_IPI_mask)
-#define send_IPI_mask_allbutself (genapic->send_IPI_mask_allbutself)
-#else
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-        send_IPI_mask_bitmask(mask, vector);
-}
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-#endif
-
-static inline void __local_send_IPI_allbutself(int vector)
-{
-        if (no_broadcast || vector == NMI_VECTOR)
-                send_IPI_mask_allbutself(cpu_online_mask, vector);
-        else
-                __send_IPI_shortcut(APIC_DEST_ALLBUT, vector);
-}
-
-static inline void __local_send_IPI_all(int vector)
-{
-        if (no_broadcast || vector == NMI_VECTOR)
-                send_IPI_mask(cpu_online_mask, vector);
-        else
-                __send_IPI_shortcut(APIC_DEST_ALLINC, vector);
-}
-
-#ifdef CONFIG_X86_64
-#define send_IPI_allbutself (genapic->send_IPI_allbutself)
-#define send_IPI_all (genapic->send_IPI_all)
-#else
-static inline void send_IPI_allbutself(int vector)
-{
-        /*
-         * if there are no other CPUs in the system then we get an APIC send 
-         * error if we try to broadcast, thus avoid sending IPIs in this case.
-         */
-        if (!(num_online_cpus() > 1))
-                return;
-
-        __local_send_IPI_allbutself(vector);
-        return;
-}
-
-static inline void send_IPI_all(int vector)
-{
-        __local_send_IPI_all(vector);
-}
-#endif
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_IPI_H */
diff --git a/arch/x86/include/asm/mach-default/mach_mpparse.h b/arch/x86/include/asm/mach-default/mach_mpparse.h
deleted file mode 100644
index c70a263d68cd..000000000000
--- a/arch/x86/include/asm/mach-default/mach_mpparse.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H
-#define _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H
-
-static inline int
-mps_oem_check(struct mpc_table *mpc, char *oem, char *productid)
-{
-        return 0;
-}
-
-/* Hook from generic ACPI tables.c */
-static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-        return 0;
-}
-
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/mach-default/mach_mpspec.h b/arch/x86/include/asm/mach-default/mach_mpspec.h
deleted file mode 100644
index e85ede686be8..000000000000
--- a/arch/x86/include/asm/mach-default/mach_mpspec.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H
-#define _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-#if CONFIG_BASE_SMALL == 0
-#define MAX_MP_BUSSES 256
-#else
-#define MAX_MP_BUSSES 32
-#endif
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H */
diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h
deleted file mode 100644
index 89897a6a65b9..000000000000
--- a/arch/x86/include/asm/mach-default/mach_wakecpu.h
+++ /dev/null
@@ -1,41 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
-#define _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
-
-#define TRAMPOLINE_PHYS_LOW (0x467)
-#define TRAMPOLINE_PHYS_HIGH (0x469)
-
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-        while (!atomic_read(deassert))
-                cpu_relax();
-        return;
-}
-
-/* Nothing to do for most platforms, since cleared by the INIT cycle */
-static inline void smp_callin_clear_local_apic(void)
-{
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-#ifdef CONFIG_SMP
-extern void __inquire_remote_apic(int apicid);
-#else /* CONFIG_SMP */
-static inline void __inquire_remote_apic(int apicid)
-{
-}
-#endif /* CONFIG_SMP */
-
-static inline void inquire_remote_apic(int apicid)
-{
-        if (apic_verbosity >= APIC_DEBUG)
-                __inquire_remote_apic(apicid);
-}
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/mach-generic/gpio.h b/arch/x86/include/asm/mach-generic/gpio.h
deleted file mode 100644
index 995c45efdb33..000000000000
--- a/arch/x86/include/asm/mach-generic/gpio.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_GPIO_H
-#define _ASM_X86_MACH_GENERIC_GPIO_H
-
-int gpio_request(unsigned gpio, const char *label);
-void gpio_free(unsigned gpio);
-int gpio_direction_input(unsigned gpio);
-int gpio_direction_output(unsigned gpio, int value);
-int gpio_get_value(unsigned gpio);
-void gpio_set_value(unsigned gpio, int value);
-int gpio_to_irq(unsigned gpio);
-int irq_to_gpio(unsigned irq);
-
-#include <asm-generic/gpio.h>           /* cansleep wrappers */
-
-#endif /* _ASM_X86_MACH_GENERIC_GPIO_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_apic.h b/arch/x86/include/asm/mach-generic/mach_apic.h
deleted file mode 100644
index 48553e958ad5..000000000000
--- a/arch/x86/include/asm/mach-generic/mach_apic.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_APIC_H
-#define _ASM_X86_MACH_GENERIC_MACH_APIC_H
-
-#include <asm/genapic.h>
-
-#define esr_disable (genapic->ESR_DISABLE)
-#define NO_BALANCE_IRQ (genapic->no_balance_irq)
-#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
-#define INT_DEST_MODE (genapic->int_dest_mode)
-#undef APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL (genapic->apic_destination_logical)
-#define TARGET_CPUS       (genapic->target_cpus())
-#define apic_id_registered (genapic->apic_id_registered)
-#define init_apic_ldr (genapic->init_apic_ldr)
-#define ioapic_phys_id_map (genapic->ioapic_phys_id_map)
-#define setup_apic_routing (genapic->setup_apic_routing)
-#define multi_timer_check (genapic->multi_timer_check)
-#define apicid_to_node (genapic->apicid_to_node)
-#define cpu_to_logical_apicid (genapic->cpu_to_logical_apicid) 
-#define cpu_present_to_apicid (genapic->cpu_present_to_apicid)
-#define apicid_to_cpu_present (genapic->apicid_to_cpu_present)
-#define setup_portio_remap (genapic->setup_portio_remap)
-#define check_apicid_present (genapic->check_apicid_present)
-#define check_phys_apicid_present (genapic->check_phys_apicid_present)
-#define check_apicid_used (genapic->check_apicid_used)
-#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
-#define cpu_mask_to_apicid_and (genapic->cpu_mask_to_apicid_and)
-#define vector_allocation_domain (genapic->vector_allocation_domain)
-#define enable_apic_mode (genapic->enable_apic_mode)
-#define phys_pkg_id (genapic->phys_pkg_id)
-#define wakeup_secondary_cpu (genapic->wakeup_cpu)
-
-extern void generic_bigsmp_probe(void);
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_apicdef.h b/arch/x86/include/asm/mach-generic/mach_apicdef.h
deleted file mode 100644
index 68041f3802f4..000000000000
--- a/arch/x86/include/asm/mach-generic/mach_apicdef.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_APICDEF_H
-#define _ASM_X86_MACH_GENERIC_MACH_APICDEF_H
-
-#ifndef APIC_DEFINITION
-#include <asm/genapic.h>
-
-#define GET_APIC_ID (genapic->get_apic_id)
-#define APIC_ID_MASK (genapic->apic_id_mask)
-#endif
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_APICDEF_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_ipi.h b/arch/x86/include/asm/mach-generic/mach_ipi.h
deleted file mode 100644
index ffd637e3c3d9..000000000000
--- a/arch/x86/include/asm/mach-generic/mach_ipi.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_IPI_H
-#define _ASM_X86_MACH_GENERIC_MACH_IPI_H
-
-#include <asm/genapic.h>
-
-#define send_IPI_mask (genapic->send_IPI_mask)
-#define send_IPI_allbutself (genapic->send_IPI_allbutself)
-#define send_IPI_all (genapic->send_IPI_all)
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_IPI_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_mpparse.h b/arch/x86/include/asm/mach-generic/mach_mpparse.h
deleted file mode 100644
index 9444ab8dca94..000000000000
--- a/arch/x86/include/asm/mach-generic/mach_mpparse.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H
-#define _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H
-
-
-extern int mps_oem_check(struct mpc_table *, char *, char *);
-
-extern int acpi_madt_oem_check(char *, char *);
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_mpspec.h b/arch/x86/include/asm/mach-generic/mach_mpspec.h
deleted file mode 100644
index 3bc407226578..000000000000
--- a/arch/x86/include/asm/mach-generic/mach_mpspec.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H
-#define _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-/* Summit or generic (i.e. installer) kernels need lots of bus entries. */
-/* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */
-#define MAX_MP_BUSSES 260
-
-extern void numaq_mps_oem_check(struct mpc_table *, char *, char *);
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_wakecpu.h b/arch/x86/include/asm/mach-generic/mach_wakecpu.h
deleted file mode 100644
index 1ab16b168c8a..000000000000
--- a/arch/x86/include/asm/mach-generic/mach_wakecpu.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
-#define _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
-
-#define TRAMPOLINE_PHYS_LOW (genapic->trampoline_phys_low)
-#define TRAMPOLINE_PHYS_HIGH (genapic->trampoline_phys_high)
-#define wait_for_init_deassert (genapic->wait_for_init_deassert)
-#define smp_callin_clear_local_apic (genapic->smp_callin_clear_local_apic)
-#define store_NMI_vector (genapic->store_NMI_vector)
-#define restore_NMI_vector (genapic->restore_NMI_vector)
-#define inquire_remote_apic (genapic->inquire_remote_apic)
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */
diff --git a/arch/x86/include/asm/mach-rdc321x/gpio.h b/arch/x86/include/asm/mach-rdc321x/gpio.h
deleted file mode 100644
index c210ab5788b0..000000000000
--- a/arch/x86/include/asm/mach-rdc321x/gpio.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef _ASM_X86_MACH_RDC321X_GPIO_H
-#define _ASM_X86_MACH_RDC321X_GPIO_H
-
-#include <linux/kernel.h>
-
-extern int rdc_gpio_get_value(unsigned gpio);
-extern void rdc_gpio_set_value(unsigned gpio, int value);
-extern int rdc_gpio_direction_input(unsigned gpio);
-extern int rdc_gpio_direction_output(unsigned gpio, int value);
-extern int rdc_gpio_request(unsigned gpio, const char *label);
-extern void rdc_gpio_free(unsigned gpio);
-extern void __init rdc321x_gpio_setup(void);
-
-/* Wrappers for the arch-neutral GPIO API */
-
-static inline int gpio_request(unsigned gpio, const char *label)
-{
-        return rdc_gpio_request(gpio, label);
-}
-
-static inline void gpio_free(unsigned gpio)
-{
-        might_sleep();
-        rdc_gpio_free(gpio);
-}
-
-static inline int gpio_direction_input(unsigned gpio)
-{
-        return rdc_gpio_direction_input(gpio);
-}
-
-static inline int gpio_direction_output(unsigned gpio, int value)
-{
-        return rdc_gpio_direction_output(gpio, value);
-}
-
-static inline int gpio_get_value(unsigned gpio)
-{
-        return rdc_gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(unsigned gpio, int value)
-{
-        rdc_gpio_set_value(gpio, value);
-}
-
-static inline int gpio_to_irq(unsigned gpio)
-{
-        return gpio;
-}
-
-static inline int irq_to_gpio(unsigned irq)
-{
-        return irq;
-}
-
-/* For cansleep */
-#include <asm-generic/gpio.h>
-
-#endif /* _ASM_X86_MACH_RDC321X_GPIO_H */
diff --git a/arch/x86/include/asm/mach-voyager/do_timer.h b/arch/x86/include/asm/mach-voyager/do_timer.h
deleted file mode 100644
index 9e5a459fd15b..000000000000
--- a/arch/x86/include/asm/mach-voyager/do_timer.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* defines for inline arch setup functions */
-#include <linux/clockchips.h>
-
-#include <asm/voyager.h>
-#include <asm/i8253.h>
-
-/**
- * do_timer_interrupt_hook - hook into timer tick
- *
- * Call the pit clock event handler. see asm/i8253.h
- **/
-static inline void do_timer_interrupt_hook(void)
-{
-        global_clock_event->event_handler(global_clock_event);
-        voyager_timer_interrupt();
-}
-
diff --git a/arch/x86/include/asm/mach-voyager/entry_arch.h b/arch/x86/include/asm/mach-voyager/entry_arch.h
deleted file mode 100644
index ae52624b5937..000000000000
--- a/arch/x86/include/asm/mach-voyager/entry_arch.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 2002
- *
- * Author: James.Bottomley@HansenPartnership.com
- *
- * linux/arch/i386/voyager/entry_arch.h
- *
- * This file builds the VIC and QIC CPI gates
- */
-
-/* initialise the voyager interrupt gates 
- *
- * This uses the macros in irq.h to set up assembly jump gates.  The
- * calls are then redirected to the same routine with smp_ prefixed */
-BUILD_INTERRUPT(vic_sys_interrupt, VIC_SYS_INT)
-BUILD_INTERRUPT(vic_cmn_interrupt, VIC_CMN_INT)
-BUILD_INTERRUPT(vic_cpi_interrupt, VIC_CPI_LEVEL0);
-
-/* do all the QIC interrupts */
-BUILD_INTERRUPT(qic_timer_interrupt, QIC_TIMER_CPI);
-BUILD_INTERRUPT(qic_invalidate_interrupt, QIC_INVALIDATE_CPI);
-BUILD_INTERRUPT(qic_reschedule_interrupt, QIC_RESCHEDULE_CPI);
-BUILD_INTERRUPT(qic_enable_irq_interrupt, QIC_ENABLE_IRQ_CPI);
-BUILD_INTERRUPT(qic_call_function_interrupt, QIC_CALL_FUNCTION_CPI);
-BUILD_INTERRUPT(qic_call_function_single_interrupt, QIC_CALL_FUNCTION_SINGLE_CPI);
diff --git a/arch/x86/include/asm/mach-voyager/setup_arch.h b/arch/x86/include/asm/mach-voyager/setup_arch.h
deleted file mode 100644
index 71729ca05cd7..000000000000
--- a/arch/x86/include/asm/mach-voyager/setup_arch.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#include <asm/voyager.h>
-#include <asm/setup.h>
-#define VOYAGER_BIOS_INFO ((struct voyager_bios_info *) \
-                        (&boot_params.apm_bios_info))
-
-/* Hook to call BIOS initialisation function */
-
-/* for voyager, pass the voyager BIOS/SUS info area to the detection
- * routines */
-
-#define ARCH_SETUP      voyager_detect(VOYAGER_BIOS_INFO);
-
diff --git a/arch/x86/include/asm/mach-default/mach_timer.h b/arch/x86/include/asm/mach_timer.h
index 853728519ae9..853728519ae9 100644
--- a/arch/x86/include/asm/mach-default/mach_timer.h
+++ b/arch/x86/include/asm/mach_timer.h
diff --git a/arch/x86/include/asm/mach-default/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index f7920601e472..f7920601e472 100644
--- a/arch/x86/include/asm/mach-default/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 32c6e17b960b..563933e06a35 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -11,6 +11,8 @@
  */
 
 #define MCG_CTL_P        (1UL<<8)   /* MCG_CAP register available */
+#define MCG_EXT_P        (1ULL<<9)   /* Extended registers available */
+#define MCG_CMCI_P       (1ULL<<10)  /* CMCI supported */
 
 #define MCG_STATUS_RIPV  (1UL<<0)   /* restart ip valid */
 #define MCG_STATUS_EIPV  (1UL<<1)   /* ip points to correct instruction */
@@ -90,14 +92,29 @@ extern int mce_disabled;
 
 #include <asm/atomic.h>
 
+void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, device_mce);
 extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
+/*
+ * To support more than 128 would need to escape the predefined
+ * Linux defined extended banks first.
+ */
+#define MAX_NR_BANKS (MCE_EXTENDED_BANK - 1)
+
 #ifdef CONFIG_X86_MCE_INTEL
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
+void cmci_clear(void);
+void cmci_reenable(void);
+void cmci_rediscover(int dying);
+void cmci_recheck(void);
 #else
 static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
+static inline void cmci_clear(void) {}
+static inline void cmci_reenable(void) {}
+static inline void cmci_rediscover(int dying) {}
+static inline void cmci_recheck(void) {}
 #endif
 
 #ifdef CONFIG_X86_MCE_AMD
@@ -106,11 +123,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c);
 static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
 #endif
 
-void mce_log_therm_throt_event(unsigned int cpu, __u64 status);
+extern int mce_available(struct cpuinfo_x86 *c);
+
+void mce_log_therm_throt_event(__u64 status);
 
 extern atomic_t mce_entry;
 
 extern void do_machine_check(struct pt_regs *, long);
+
+typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
+DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
+
+enum mcp_flags {
+        MCP_TIMESTAMP = (1 << 0),       /* log time stamp */
+        MCP_UC = (1 << 1),              /* log uncorrected errors */
+};
+extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
+
 extern int mce_notify_user(void);
 
 #endif /* !CONFIG_X86_32 */
@@ -120,8 +149,8 @@ extern void mcheck_init(struct cpuinfo_x86 *c);
 #else
 #define mcheck_init(c) do { } while (0)
 #endif
-extern void stop_mce(void);
-extern void restart_mce(void);
+
+extern void (*mce_threshold_vector)(void);
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 8aeeb3fd73db..f923203dc39a 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -21,11 +21,54 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
-#ifdef CONFIG_X86_32
-# include "mmu_context_32.h"
-#else
-# include "mmu_context_64.h"
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+#ifdef CONFIG_SMP
+        if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+                percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
+#endif
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+                             struct task_struct *tsk)
+{
+        unsigned cpu = smp_processor_id();
+
+        if (likely(prev != next)) {
+                /* stop flush ipis for the previous mm */
+                cpu_clear(cpu, prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+                percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+                percpu_write(cpu_tlbstate.active_mm, next);
 #endif
+                cpu_set(cpu, next->cpu_vm_mask);
+
+                /* Re-load page tables */
+                load_cr3(next->pgd);
+
+                /*
+                 * load the LDT, if the LDT is different:
+                 */
+                if (unlikely(prev->context.ldt != next->context.ldt))
+                        load_LDT_nolock(&next->context);
+        }
+#ifdef CONFIG_SMP
+        else {
+                percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+                BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
+
+                if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+                        /* We were in lazy tlb mode and leave_mm disabled
+                         * tlb flush IPI delivery. We must reload CR3
+                         * to make sure to use no freed page tables.
+                         */
+                        load_cr3(next->pgd);
+                        load_LDT_nolock(&next->context);
+                }
+        }
+#endif
+}
 
 #define activate_mm(prev, next)                 \
 do {                                            \
@@ -33,5 +76,17 @@ do {						\
         switch_mm((prev), (next), NULL);        \
 } while (0);
 
+#ifdef CONFIG_X86_32
+#define deactivate_mm(tsk, mm)                  \
+do {                                            \
+        lazy_load_gs(0);                        \
+} while (0)
+#else
+#define deactivate_mm(tsk, mm)                  \
+do {                                            \
+        load_gs_index(0);                       \
+        loadsegment(fs, 0);                     \
+} while (0)
+#endif
 
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
deleted file mode 100644
index 7e98ce1d2c0e..000000000000
--- a/arch/x86/include/asm/mmu_context_32.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_32_H
-#define _ASM_X86_MMU_CONTEXT_32_H
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
-        if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK)
-                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev,
-                             struct mm_struct *next,
-                             struct task_struct *tsk)
-{
-        int cpu = smp_processor_id();
-
-        if (likely(prev != next)) {
-                /* stop flush ipis for the previous mm */
-                cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
-                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-                x86_write_percpu(cpu_tlbstate.active_mm, next);
-#endif
-                cpu_set(cpu, next->cpu_vm_mask);
-
-                /* Re-load page tables */
-                load_cr3(next->pgd);
-
-                /*
-                 * load the LDT, if the LDT is different:
-                 */
-                if (unlikely(prev->context.ldt != next->context.ldt))
-                        load_LDT_nolock(&next->context);
-        }
-#ifdef CONFIG_SMP
-        else {
-                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-                BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
-
-                if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
-                        /* We were in lazy tlb mode and leave_mm disabled
-                         * tlb flush IPI delivery. We must reload %cr3.
-                         */
-                        load_cr3(next->pgd);
-                        load_LDT_nolock(&next->context);
-                }
-        }
-#endif
-}
-
-#define deactivate_mm(tsk, mm)                  \
-        asm("movl %0,%%gs": :"r" (0));
-
-#endif /* _ASM_X86_MMU_CONTEXT_32_H */
diff --git a/arch/x86/include/asm/mmu_context_64.h b/arch/x86/include/asm/mmu_context_64.h
deleted file mode 100644
index 677d36e9540a..000000000000
--- a/arch/x86/include/asm/mmu_context_64.h
+++ /dev/null
@@ -1,54 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_64_H
-#define _ASM_X86_MMU_CONTEXT_64_H
-
-#include <asm/pda.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
-        if (read_pda(mmu_state) == TLBSTATE_OK)
-                write_pda(mmu_state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-                             struct task_struct *tsk)
-{
-        unsigned cpu = smp_processor_id();
-        if (likely(prev != next)) {
-                /* stop flush ipis for the previous mm */
-                cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
-                write_pda(mmu_state, TLBSTATE_OK);
-                write_pda(active_mm, next);
-#endif
-                cpu_set(cpu, next->cpu_vm_mask);
-                load_cr3(next->pgd);
-
-                if (unlikely(next->context.ldt != prev->context.ldt))
-                        load_LDT_nolock(&next->context);
-        }
-#ifdef CONFIG_SMP
-        else {
-                write_pda(mmu_state, TLBSTATE_OK);
-                if (read_pda(active_mm) != next)
-                        BUG();
-                if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
-                        /* We were in lazy tlb mode and leave_mm disabled
-                         * tlb flush IPI delivery. We must reload CR3
-                         * to make sure to use no freed page tables.
-                         */
-                        load_cr3(next->pgd);
-                        load_LDT_nolock(&next->context);
-                }
-        }
-#endif
-}
-
-#define deactivate_mm(tsk, mm)                  \
-do {                                            \
-        load_gs_index(0);                       \
-        asm volatile("movl %0,%%fs"::"r"(0));   \
-} while (0)
-
-#endif /* _ASM_X86_MMU_CONTEXT_64_H */
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 105fb90a0635..ede6998bd92c 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -91,46 +91,9 @@ static inline int pfn_valid(int pfn)
 #endif /* CONFIG_DISCONTIGMEM */
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-
-/*
- * Following are macros that are specific to this numa platform.
- */
-#define reserve_bootmem(addr, size, flags) \
-        reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags))
-#define alloc_bootmem(x) \
-        __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_nopanic(x) \
-        __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \
-                                __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low(x) \
-        __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
-#define alloc_bootmem_pages(x) \
-        __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_pages_nopanic(x) \
-        __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \
-                                __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low_pages(x) \
-        __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
-#define alloc_bootmem_node(pgdat, x)                                    \
-({                                                                      \
-        struct pglist_data  __maybe_unused                      \
-                                *__alloc_bootmem_node__pgdat = (pgdat); \
-        __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES,        \
-                                                __pa(MAX_DMA_ADDRESS)); \
-})
-#define alloc_bootmem_pages_node(pgdat, x)                              \
-({                                                                      \
-        struct pglist_data  __maybe_unused                      \
-                                *__alloc_bootmem_node__pgdat = (pgdat); \
-        __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE,              \
-                                                __pa(MAX_DMA_ADDRESS)); \
-})
-#define alloc_bootmem_low_pages_node(pgdat, x)                          \
-({                                                                      \
-        struct pglist_data  __maybe_unused                      \
-                                *__alloc_bootmem_node__pgdat = (pgdat); \
-        __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0);          \
-})
+/* always use node 0 for bootmem on this numa platform */
+#define bootmem_arch_preferred_node(__bdata, size, align, goal, limit)  \
+        (NODE_DATA(0)->bdata)
 #endif /* CONFIG_NEED_MULTIPLE_NODES */
 
 #endif /* _ASM_X86_MMZONE_32_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index bd22f2a3713f..642fc7fc8cdc 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -9,7 +9,18 @@ extern int apic_version[MAX_APICS];
 extern int pic_mode;
 
 #ifdef CONFIG_X86_32
-#include <mach_mpspec.h>
+
+/*
+ * Summit or generic (i.e. installer) kernels need lots of bus entries.
+ * Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets.
+ */
+#if CONFIG_BASE_SMALL == 0
+# define MAX_MP_BUSSES          260
+#else
+# define MAX_MP_BUSSES          32
+#endif
+
+#define MAX_IRQ_SOURCES         256
 
 extern unsigned int def_to_bigsmp;
 extern u8 apicid_2_node[];
@@ -20,15 +31,15 @@ extern int mp_bus_id_to_local[MAX_MP_BUSSES];
 extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
 #endif
 
-#define MAX_APICID 256
+#define MAX_APICID              256
 
-#else
+#else /* CONFIG_X86_64: */
 
-#define MAX_MP_BUSSES 256
+#define MAX_MP_BUSSES           256
 /* Each PCI slot may be a combo card with its own bus.  4 IRQ pins per slot. */
-#define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4)
+#define MAX_IRQ_SOURCES         (MAX_MP_BUSSES * 4)
 
-#endif
+#endif /* CONFIG_X86_64 */
 
 extern void early_find_smp_config(void);
 extern void early_get_smp_config(void);
@@ -45,11 +56,13 @@ extern int smp_found_config;
 extern int mpc_default_type;
 extern unsigned long mp_lapic_addr;
 
-extern void find_smp_config(void);
 extern void get_smp_config(void);
+
 #ifdef CONFIG_X86_MPPARSE
+extern void find_smp_config(void);
 extern void early_reserve_e820_mpc_new(void);
 #else
+static inline void find_smp_config(void) { }
 static inline void early_reserve_e820_mpc_new(void) { }
 #endif
 
@@ -64,6 +77,8 @@ extern int acpi_probe_gsi(void);
 #ifdef CONFIG_X86_IO_APIC
 extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
                                 u32 gsi, int triggering, int polarity);
+extern int mp_find_ioapic(int gsi);
+extern int mp_find_ioapic_pin(int ioapic, int gsi);
 #else
 static inline int
 mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
@@ -148,4 +163,8 @@ static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
 
 extern physid_mask_t phys_cpu_present_map;
 
+extern int generic_mps_oem_check(struct mpc_table *, char *, char *);
+
+extern int default_acpi_madt_oem_check(char *, char *);
+
 #endif /* _ASM_X86_MPSPEC_H */
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index 59568bc4767f..4a7f96d7c188 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -24,17 +24,18 @@
 # endif
 #endif
 
-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)                   */
+/* Intel MP Floating Pointer Structure */
+struct mpf_intel {
+        char signature[4];              /* "_MP_"                       */
+        unsigned int physptr;           /* Configuration table address  */
+        unsigned char length;           /* Our length (paragraphs)      */
+        unsigned char specification;    /* Specification version        */
+        unsigned char checksum;         /* Checksum (makes sum 0)       */
+        unsigned char feature1;         /* Standard or configuration ?  */
+        unsigned char feature2;         /* Bit7 set for IMCR|PIC        */
+        unsigned char feature3;         /* Unused (0)                   */
+        unsigned char feature4;         /* Unused (0)                   */
+        unsigned char feature5;         /* Unused (0)                   */
 };
 
 #define MPC_SIGNATURE "PCMP"
diff --git a/arch/x86/include/asm/msidef.h b/arch/x86/include/asm/msidef.h
index 6706b3006f13..4cc48af23fef 100644
--- a/arch/x86/include/asm/msidef.h
+++ b/arch/x86/include/asm/msidef.h
@@ -47,6 +47,7 @@
 #define  MSI_ADDR_DEST_ID_MASK          0x00ffff0
 #define  MSI_ADDR_DEST_ID(dest)         (((dest) << MSI_ADDR_DEST_ID_SHIFT) & \
                                          MSI_ADDR_DEST_ID_MASK)
+#define MSI_ADDR_EXT_DEST_ID(dest)      ((dest) & 0xffffff00)
 
 #define MSI_ADDR_IR_EXT_INT             (1 << 4)
 #define MSI_ADDR_IR_SHV                 (1 << 3)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 358acc59ae04..ec41fc16c167 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -18,11 +18,15 @@
 #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_SVME              12 /* Enable virtualization */
+#define _EFER_FFXSR             14 /* Enable Fast FXSAVE/FXRSTOR */
 
 #define EFER_SCE                (1<<_EFER_SCE)
 #define EFER_LME                (1<<_EFER_LME)
 #define EFER_LMA                (1<<_EFER_LMA)
 #define EFER_NX                 (1<<_EFER_NX)
+#define EFER_SVME               (1<<_EFER_SVME)
+#define EFER_FFXSR              (1<<_EFER_FFXSR)
 
 /* Intel MSRs. Some also available on other CPUs */
 #define MSR_IA32_PERFCTR0               0x000000c1
@@ -77,6 +81,11 @@
 #define MSR_IA32_MC0_ADDR               0x00000402
 #define MSR_IA32_MC0_MISC               0x00000403
 
+/* These are consecutive and not in the normal 4er MCE bank block */
+#define MSR_IA32_MC0_CTL2               0x00000280
+#define CMCI_EN                 (1ULL << 30)
+#define CMCI_THRESHOLD_MASK             0xffffULL
+
 #define MSR_P6_PERFCTR0                 0x000000c1
 #define MSR_P6_PERFCTR1                 0x000000c2
 #define MSR_P6_EVNTSEL0                 0x00000186
@@ -360,4 +369,9 @@
 #define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
 #define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
 
+/* AMD-V MSRs */
+
+#define MSR_VM_CR                       0xc0010114
+#define MSR_VM_HSAVE_PA                 0xc0010117
+
 #endif /* _ASM_X86_MSR_INDEX_H */
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
index e9f5db796244..a37229011b56 100644
--- a/arch/x86/include/asm/numa_32.h
+++ b/arch/x86/include/asm/numa_32.h
@@ -4,8 +4,12 @@
 extern int pxm_to_nid(int pxm);
 extern void numa_remove_cpu(int cpu);
 
-#ifdef CONFIG_NUMA
+#ifdef CONFIG_HIGHMEM
 extern void set_highmem_pages_init(void);
+#else
+static inline void set_highmem_pages_init(void)
+{
+}
 #endif
 
 #endif /* _ASM_X86_NUMA_32_H */
diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h
index 1e8bd30b4c16..9f0a5f5d29ec 100644
--- a/arch/x86/include/asm/numaq.h
+++ b/arch/x86/include/asm/numaq.h
@@ -31,6 +31,8 @@
 extern int found_numaq;
 extern int get_memcfg_numaq(void);
 
+extern void *xquad_portio;
+
 /*
  * SYS_CFG_DATA_PRIV_ADDR, struct eachquadmem, and struct sys_cfg_data are the
  */
diff --git a/arch/x86/include/asm/numaq/apic.h b/arch/x86/include/asm/numaq/apic.h
deleted file mode 100644
index bf37bc49bd8e..000000000000
--- a/arch/x86/include/asm/numaq/apic.h
+++ /dev/null
@@ -1,142 +0,0 @@
-#ifndef __ASM_NUMAQ_APIC_H
-#define __ASM_NUMAQ_APIC_H
-
-#include <asm/io.h>
-#include <linux/mmzone.h>
-#include <linux/nodemask.h>
-
-#define APIC_DFR_VALUE  (APIC_DFR_CLUSTER)
-
-static inline const cpumask_t *target_cpus(void)
-{
-        return &CPU_MASK_ALL;
-}
-
-#define NO_BALANCE_IRQ (1)
-#define esr_disable (1)
-
-#define INT_DELIVERY_MODE dest_LowestPrio
-#define INT_DEST_MODE 0     /* physical delivery on LOCAL quad */
- 
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-        return physid_isset(apicid, bitmap);
-}
-static inline unsigned long check_apicid_present(int bit)
-{
-        return physid_isset(bit, phys_cpu_present_map);
-}
-#define apicid_cluster(apicid) (apicid & 0xF0)
-
-static inline int apic_id_registered(void)
-{
-        return 1;
-}
-
-static inline void init_apic_ldr(void)
-{
-        /* Already done in NUMA-Q firmware */
-}
-
-static inline void setup_apic_routing(void)
-{
-        printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-                "NUMA-Q", nr_ioapics);
-}
-
-/*
- * Skip adding the timer int on secondary nodes, which causes
- * a small but painful rift in the time-space continuum.
- */
-static inline int multi_timer_check(int apic, int irq)
-{
-        return apic != 0 && irq == 0;
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-        /* We don't have a good way to do this yet - hack */
-        return physids_promote(0xFUL);
-}
-
-/* Mapping from cpu number to logical apicid */
-extern u8 cpu_2_logical_apicid[];
-static inline int cpu_to_logical_apicid(int cpu)
-{
-        if (cpu >= nr_cpu_ids)
-                return BAD_APICID;
-        return (int)cpu_2_logical_apicid[cpu];
-}
-
-/*
- * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
- * cpu to APIC ID relation to properly interact with the intelligent
- * mode of the cluster controller.
- */
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-        if (mps_cpu < 60)
-                return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3));
-        else
-                return BAD_APICID;
-}
-
-static inline int apicid_to_node(int logical_apicid) 
-{
-        return logical_apicid >> 4;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int logical_apicid)
-{
-        int node = apicid_to_node(logical_apicid);
-        int cpu = __ffs(logical_apicid & 0xf);
-
-        return physid_mask_of_physid(cpu + 4*node);
-}
-
-extern void *xquad_portio;
-
-static inline void setup_portio_remap(void)
-{
-        int num_quads = num_online_nodes();
-
-        if (num_quads <= 1)
-                return;
-
-        printk("Remapping cross-quad port I/O for %d quads\n", num_quads);
-        xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD);
-        printk("xquad_portio vaddr 0x%08lx, len %08lx\n",
-                (u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD);
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-        return (1);
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-/*
- * We use physical apicids here, not logical, so just return the default
- * physical broadcast to stop people from breaking us
- */
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-        return (int) 0xF;
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-                                                  const struct cpumask *andmask)
-{
-        return (int) 0xF;
-}
-
-/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-        return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_NUMAQ_APIC_H */
diff --git a/arch/x86/include/asm/numaq/apicdef.h b/arch/x86/include/asm/numaq/apicdef.h
deleted file mode 100644
index e012a46cc22a..000000000000
--- a/arch/x86/include/asm/numaq/apicdef.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef __ASM_NUMAQ_APICDEF_H
-#define __ASM_NUMAQ_APICDEF_H
-
-
-#define APIC_ID_MASK (0xF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-                return (((x)>>24)&0x0F);
-}
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/arch/x86/include/asm/numaq/ipi.h b/arch/x86/include/asm/numaq/ipi.h
deleted file mode 100644
index a8374c652778..000000000000
--- a/arch/x86/include/asm/numaq/ipi.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef __ASM_NUMAQ_IPI_H
-#define __ASM_NUMAQ_IPI_H
-
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-        send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-        send_IPI_mask_allbutself(cpu_online_mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-        send_IPI_mask(cpu_online_mask, vector);
-}
-
-#endif /* __ASM_NUMAQ_IPI_H */
diff --git a/arch/x86/include/asm/numaq/mpparse.h b/arch/x86/include/asm/numaq/mpparse.h
deleted file mode 100644
index a2eeefcd1cc7..000000000000
--- a/arch/x86/include/asm/numaq/mpparse.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_NUMAQ_MPPARSE_H
-#define __ASM_NUMAQ_MPPARSE_H
-
-extern void numaq_mps_oem_check(struct mpc_table *, char *, char *);
-
-#endif /* __ASM_NUMAQ_MPPARSE_H */
diff --git a/arch/x86/include/asm/numaq/wakecpu.h b/arch/x86/include/asm/numaq/wakecpu.h
deleted file mode 100644
index 6f499df8eddb..000000000000
--- a/arch/x86/include/asm/numaq/wakecpu.h
+++ /dev/null
@@ -1,45 +0,0 @@
-#ifndef __ASM_NUMAQ_WAKECPU_H
-#define __ASM_NUMAQ_WAKECPU_H
-
-/* This file copes with machines that wakeup secondary CPUs by NMIs */
-
-#define TRAMPOLINE_PHYS_LOW (0x8)
-#define TRAMPOLINE_PHYS_HIGH (0xa)
-
-/* We don't do anything here because we use NMI's to boot instead */
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-}
-
-/*
- * Because we use NMIs rather than the INIT-STARTUP sequence to
- * bootstrap the CPUs, the APIC may be in a weird state. Kick it.
- */
-static inline void smp_callin_clear_local_apic(void)
-{
-        clear_local_APIC();
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-        printk("Storing NMI vector\n");
-        *high =
-          *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH));
-        *low =
-          *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW));
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-        printk("Restoring NMI vector\n");
-        *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
-                                                                 *high;
-        *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
-                                                                 *low;
-}
-
-static inline void inquire_remote_apic(int apicid)
-{
-}
-
-#endif /* __ASM_NUMAQ_WAKECPU_H */
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 776579119a00..89ed9d70b0aa 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -1,42 +1,11 @@
 #ifndef _ASM_X86_PAGE_H
 #define _ASM_X86_PAGE_H
 
-#include <linux/const.h>
-
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT      12
-#define PAGE_SIZE       (_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK       (~(PAGE_SIZE-1))
+#include <linux/types.h>
 
 #ifdef __KERNEL__
 
-#define __PHYSICAL_MASK         ((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1)
-#define __VIRTUAL_MASK          ((1UL << __VIRTUAL_MASK_SHIFT) - 1)
-
-/* Cast PAGE_MASK to a signed type so that it is sign-extended if
-   virtual addresses are 32-bits but physical addresses are larger
-   (ie, 32-bit PAE). */
-#define PHYSICAL_PAGE_MASK      (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-
-/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
-#define PTE_PFN_MASK            ((pteval_t)PHYSICAL_PAGE_MASK)
-
-/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
-#define PTE_FLAGS_MASK          (~PTE_PFN_MASK)
-
-#define PMD_PAGE_SIZE           (_AC(1, UL) << PMD_SHIFT)
-#define PMD_PAGE_MASK           (~(PMD_PAGE_SIZE-1))
-
-#define HPAGE_SHIFT             PMD_SHIFT
-#define HPAGE_SIZE              (_AC(1,UL) << HPAGE_SHIFT)
-#define HPAGE_MASK              (~(HPAGE_SIZE - 1))
-#define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
-
-#define HUGE_MAX_HSTATE 2
-
-#ifndef __ASSEMBLY__
-#include <linux/types.h>
-#endif
+#include <asm/page_types.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/page_64.h>
@@ -44,38 +13,18 @@
 #include <asm/page_32.h>
 #endif  /* CONFIG_X86_64 */
 
-#define PAGE_OFFSET             ((unsigned long)__PAGE_OFFSET)
-
-#define VM_DATA_DEFAULT_FLAGS \
-        (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
-         VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-
 #ifndef __ASSEMBLY__
 
-typedef struct { pgdval_t pgd; } pgd_t;
-typedef struct { pgprotval_t pgprot; } pgprot_t;
-
-extern int page_is_ram(unsigned long pagenr);
-extern int devmem_is_allowed(unsigned long pagenr);
-extern void map_devmem(unsigned long pfn, unsigned long size,
-                       pgprot_t vma_prot);
-extern void unmap_devmem(unsigned long pfn, unsigned long size,
-                         pgprot_t vma_prot);
-
-extern unsigned long max_low_pfn_mapped;
-extern unsigned long max_pfn_mapped;
-
 struct page;
 
 static inline void clear_user_page(void *page, unsigned long vaddr,
-                                struct page *pg)
+                                   struct page *pg)
 {
         clear_page(page);
 }
 
 static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
-                                struct page *topage)
+                                  struct page *topage)
 {
         copy_page(to, from);
 }
@@ -84,99 +33,6 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
         alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
-static inline pgd_t native_make_pgd(pgdval_t val)
-{
-        return (pgd_t) { val };
-}
-
-static inline pgdval_t native_pgd_val(pgd_t pgd)
-{
-        return pgd.pgd;
-}
-
-#if PAGETABLE_LEVELS >= 3
-#if PAGETABLE_LEVELS == 4
-typedef struct { pudval_t pud; } pud_t;
-
-static inline pud_t native_make_pud(pmdval_t val)
-{
-        return (pud_t) { val };
-}
-
-static inline pudval_t native_pud_val(pud_t pud)
-{
-        return pud.pud;
-}
-#else   /* PAGETABLE_LEVELS == 3 */
-#include <asm-generic/pgtable-nopud.h>
-
-static inline pudval_t native_pud_val(pud_t pud)
-{
-        return native_pgd_val(pud.pgd);
-}
-#endif  /* PAGETABLE_LEVELS == 4 */
-
-typedef struct { pmdval_t pmd; } pmd_t;
-
-static inline pmd_t native_make_pmd(pmdval_t val)
-{
-        return (pmd_t) { val };
-}
-
-static inline pmdval_t native_pmd_val(pmd_t pmd)
-{
-        return pmd.pmd;
-}
-#else  /* PAGETABLE_LEVELS == 2 */
-#include <asm-generic/pgtable-nopmd.h>
-
-static inline pmdval_t native_pmd_val(pmd_t pmd)
-{
-        return native_pgd_val(pmd.pud.pgd);
-}
-#endif  /* PAGETABLE_LEVELS >= 3 */
-
-static inline pte_t native_make_pte(pteval_t val)
-{
-        return (pte_t) { .pte = val };
-}
-
-static inline pteval_t native_pte_val(pte_t pte)
-{
-        return pte.pte;
-}
-
-static inline pteval_t native_pte_flags(pte_t pte)
-{
-        return native_pte_val(pte) & PTE_FLAGS_MASK;
-}
-
-#define pgprot_val(x)   ((x).pgprot)
-#define __pgprot(x)     ((pgprot_t) { (x) } )
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else  /* !CONFIG_PARAVIRT */
-
-#define pgd_val(x)      native_pgd_val(x)
-#define __pgd(x)        native_make_pgd(x)
-
-#ifndef __PAGETABLE_PUD_FOLDED
-#define pud_val(x)      native_pud_val(x)
-#define __pud(x)        native_make_pud(x)
-#endif
-
-#ifndef __PAGETABLE_PMD_FOLDED
-#define pmd_val(x)      native_pmd_val(x)
-#define __pmd(x)        native_make_pmd(x)
-#endif
-
-#define pte_val(x)      native_pte_val(x)
-#define pte_flags(x)    native_pte_flags(x)
-#define __pte(x)        native_make_pte(x)
-
-#endif  /* CONFIG_PARAVIRT */
-
 #define __pa(x)         __phys_addr((unsigned long)(x))
 #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x))
 /* __pa_symbol should be used for C visible symbols.
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index bcde0d7b4325..da4e762406f7 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -1,82 +1,14 @@
 #ifndef _ASM_X86_PAGE_32_H
 #define _ASM_X86_PAGE_32_H
 
-/*
- * This handles the memory map.
- *
- * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
- * a virtual address space of one gigabyte, which limits the
- * amount of physical memory you can use to about 950MB.
- *
- * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
- * and CONFIG_HIGHMEM64G options in the kernel configuration.
- */
-#define __PAGE_OFFSET           _AC(CONFIG_PAGE_OFFSET, UL)
-
-#ifdef CONFIG_4KSTACKS
-#define THREAD_ORDER    0
-#else
-#define THREAD_ORDER    1
-#endif
-#define THREAD_SIZE     (PAGE_SIZE << THREAD_ORDER)
-
-#define STACKFAULT_STACK 0
-#define DOUBLEFAULT_STACK 1
-#define NMI_STACK 0
-#define DEBUG_STACK 0
-#define MCE_STACK 0
-#define N_EXCEPTION_STACKS 1
-
-#ifdef CONFIG_X86_PAE
-/* 44=32+12, the limit we can fit into an unsigned long pfn */
-#define __PHYSICAL_MASK_SHIFT   44
-#define __VIRTUAL_MASK_SHIFT    32
-#define PAGETABLE_LEVELS        3
-
-#ifndef __ASSEMBLY__
-typedef u64     pteval_t;
-typedef u64     pmdval_t;
-typedef u64     pudval_t;
-typedef u64     pgdval_t;
-typedef u64     pgprotval_t;
-
-typedef union {
-        struct {
-                unsigned long pte_low, pte_high;
-        };
-        pteval_t pte;
-} pte_t;
-#endif  /* __ASSEMBLY__
- */
-#else  /* !CONFIG_X86_PAE */
-#define __PHYSICAL_MASK_SHIFT   32
-#define __VIRTUAL_MASK_SHIFT    32
-#define PAGETABLE_LEVELS        2
-
-#ifndef __ASSEMBLY__
-typedef unsigned long   pteval_t;
-typedef unsigned long   pmdval_t;
-typedef unsigned long   pudval_t;
-typedef unsigned long   pgdval_t;
-typedef unsigned long   pgprotval_t;
-
-typedef union {
-        pteval_t pte;
-        pteval_t pte_low;
-} pte_t;
-
-#endif  /* __ASSEMBLY__ */
-#endif  /* CONFIG_X86_PAE */
+#include <asm/page_32_types.h>
 
 #ifndef __ASSEMBLY__
-typedef struct page *pgtable_t;
-#endif
 
 #ifdef CONFIG_HUGETLB_PAGE
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 #endif
 
-#ifndef __ASSEMBLY__
 #define __phys_addr_nodebug(x)  ((x) - PAGE_OFFSET)
 #ifdef CONFIG_DEBUG_VIRTUAL
 extern unsigned long __phys_addr(unsigned long);
@@ -89,23 +21,6 @@ extern unsigned long __phys_addr(unsigned long);
 #define pfn_valid(pfn)          ((pfn) < max_mapnr)
 #endif /* CONFIG_FLATMEM */
 
-extern int nx_enabled;
-
-/*
- * This much address space is reserved for vmalloc() and iomap()
- * as well as fixmap mappings.
- */
-extern unsigned int __VMALLOC_RESERVE;
-extern int sysctl_legacy_va_layout;
-
-extern void find_low_pfn_range(void);
-extern unsigned long init_memory_mapping(unsigned long start,
-                                         unsigned long end);
-extern void initmem_init(unsigned long, unsigned long);
-extern void free_initmem(void);
-extern void setup_bootmem_allocator(void);
-
-
 #ifdef CONFIG_X86_USE_3DNOW
 #include <asm/mmx.h>
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
new file mode 100644
index 000000000000..0f915ae649a7
--- /dev/null
+++ b/arch/x86/include/asm/page_32_types.h
@@ -0,0 +1,65 @@
+#ifndef _ASM_X86_PAGE_32_DEFS_H
+#define _ASM_X86_PAGE_32_DEFS_H
+
+#include <linux/const.h>
+
+/*
+ * This handles the memory map.
+ *
+ * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
+ * a virtual address space of one gigabyte, which limits the
+ * amount of physical memory you can use to about 950MB.
+ *
+ * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
+ * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ */
+#define __PAGE_OFFSET           _AC(CONFIG_PAGE_OFFSET, UL)
+
+#ifdef CONFIG_4KSTACKS
+#define THREAD_ORDER    0
+#else
+#define THREAD_ORDER    1
+#endif
+#define THREAD_SIZE     (PAGE_SIZE << THREAD_ORDER)
+
+#define STACKFAULT_STACK 0
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 0
+#define DEBUG_STACK 0
+#define MCE_STACK 0
+#define N_EXCEPTION_STACKS 1
+
+#ifdef CONFIG_X86_PAE
+/* 44=32+12, the limit we can fit into an unsigned long pfn */
+#define __PHYSICAL_MASK_SHIFT   44
+#define __VIRTUAL_MASK_SHIFT    32
+
+#else  /* !CONFIG_X86_PAE */
+#define __PHYSICAL_MASK_SHIFT   32
+#define __VIRTUAL_MASK_SHIFT    32
+#endif  /* CONFIG_X86_PAE */
+
+/*
+ * Kernel image size is limited to 512 MB (see in arch/x86/kernel/head_32.S)
+ */
+#define KERNEL_IMAGE_SIZE       (512 * 1024 * 1024)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * This much address space is reserved for vmalloc() and iomap()
+ * as well as fixmap mappings.
+ */
+extern unsigned int __VMALLOC_RESERVE;
+extern int sysctl_legacy_va_layout;
+
+extern void find_low_pfn_range(void);
+extern unsigned long init_memory_mapping(unsigned long start,
+                                         unsigned long end);
+extern void initmem_init(unsigned long, unsigned long);
+extern void free_initmem(void);
+extern void setup_bootmem_allocator(void);
+
+#endif  /* !__ASSEMBLY__ */
+
+#endif /* _ASM_X86_PAGE_32_DEFS_H */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 5ebca29f44f0..072694ed81a5 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -1,105 +1,6 @@
 #ifndef _ASM_X86_PAGE_64_H
 #define _ASM_X86_PAGE_64_H
 
-#define PAGETABLE_LEVELS        4
-
-#define THREAD_ORDER    1
-#define THREAD_SIZE  (PAGE_SIZE << THREAD_ORDER)
-#define CURRENT_MASK (~(THREAD_SIZE - 1))
-
-#define EXCEPTION_STACK_ORDER 0
-#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
-
-#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
-#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
-
-#define IRQSTACK_ORDER 2
-#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
-
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
-
-#define PUD_PAGE_SIZE           (_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK           (~(PUD_PAGE_SIZE-1))
-
-/*
- * Set __PAGE_OFFSET to the most negative possible address +
- * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
- * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
- * what Xen requires.
- */
-#define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
-
-#define __PHYSICAL_START        CONFIG_PHYSICAL_START
-#define __KERNEL_ALIGN          0x200000
-
-/*
- * Make sure kernel is aligned to 2MB address. Catching it at compile
- * time is better. Change your config file and compile the kernel
- * for a 2MB aligned address (CONFIG_PHYSICAL_START)
- */
-#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
-#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
-#endif
-
-#define __START_KERNEL          (__START_KERNEL_map + __PHYSICAL_START)
-#define __START_KERNEL_map      _AC(0xffffffff80000000, UL)
-
-/* See Documentation/x86_64/mm.txt for a description of the memory map. */
-#define __PHYSICAL_MASK_SHIFT   46
-#define __VIRTUAL_MASK_SHIFT    48
-
-/*
- * Kernel image size is limited to 512 MB (see level2_kernel_pgt in
- * arch/x86/kernel/head_64.S), and it is mapped here:
- */
-#define KERNEL_IMAGE_SIZE       (512 * 1024 * 1024)
-#define KERNEL_IMAGE_START      _AC(0xffffffff80000000, UL)
-
-#ifndef __ASSEMBLY__
-void clear_page(void *page);
-void copy_page(void *to, void *from);
-
-/* duplicated to the one in bootmem.h */
-extern unsigned long max_pfn;
-extern unsigned long phys_base;
-
-extern unsigned long __phys_addr(unsigned long);
-#define __phys_reloc_hide(x)    (x)
-
-/*
- * These are used to make use of C type-checking..
- */
-typedef unsigned long   pteval_t;
-typedef unsigned long   pmdval_t;
-typedef unsigned long   pudval_t;
-typedef unsigned long   pgdval_t;
-typedef unsigned long   pgprotval_t;
-
-typedef struct page *pgtable_t;
-
-typedef struct { pteval_t pte; } pte_t;
-
-#define vmemmap ((struct page *)VMEMMAP_START)
-
-extern unsigned long init_memory_mapping(unsigned long start,
-                                         unsigned long end);
-
-extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
-extern void free_initmem(void);
-
-extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
-extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
-
-#endif  /* !__ASSEMBLY__ */
-
-#ifdef CONFIG_FLATMEM
-#define pfn_valid(pfn)          ((pfn) < max_pfn)
-#endif
-
+#include <asm/page_64_types.h>
 
 #endif /* _ASM_X86_PAGE_64_H */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
new file mode 100644
index 000000000000..d38c91b70248
--- /dev/null
+++ b/arch/x86/include/asm/page_64_types.h
@@ -0,0 +1,89 @@
+#ifndef _ASM_X86_PAGE_64_DEFS_H
+#define _ASM_X86_PAGE_64_DEFS_H
+
+#define THREAD_ORDER    1
+#define THREAD_SIZE  (PAGE_SIZE << THREAD_ORDER)
+#define CURRENT_MASK (~(THREAD_SIZE - 1))
+
+#define EXCEPTION_STACK_ORDER 0
+#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
+
+#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
+#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
+
+#define IRQ_STACK_ORDER 2
+#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
+
+#define STACKFAULT_STACK 1
+#define DOUBLEFAULT_STACK 2
+#define NMI_STACK 3
+#define DEBUG_STACK 4
+#define MCE_STACK 5
+#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
+
+#define PUD_PAGE_SIZE           (_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK           (~(PUD_PAGE_SIZE-1))
+
+/*
+ * Set __PAGE_OFFSET to the most negative possible address +
+ * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
+ * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
+ * what Xen requires.
+ */
+#define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
+
+#define __PHYSICAL_START        CONFIG_PHYSICAL_START
+#define __KERNEL_ALIGN          0x200000
+
+/*
+ * Make sure kernel is aligned to 2MB address. Catching it at compile
+ * time is better. Change your config file and compile the kernel
+ * for a 2MB aligned address (CONFIG_PHYSICAL_START)
+ */
+#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
+#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
+#endif
+
+#define __START_KERNEL          (__START_KERNEL_map + __PHYSICAL_START)
+#define __START_KERNEL_map      _AC(0xffffffff80000000, UL)
+
+/* See Documentation/x86_64/mm.txt for a description of the memory map. */
+#define __PHYSICAL_MASK_SHIFT   46
+#define __VIRTUAL_MASK_SHIFT    48
+
+/*
+ * Kernel image size is limited to 512 MB (see level2_kernel_pgt in
+ * arch/x86/kernel/head_64.S), and it is mapped here:
+ */
+#define KERNEL_IMAGE_SIZE       (512 * 1024 * 1024)
+#define KERNEL_IMAGE_START      _AC(0xffffffff80000000, UL)
+
+#ifndef __ASSEMBLY__
+void clear_page(void *page);
+void copy_page(void *to, void *from);
+
+/* duplicated to the one in bootmem.h */
+extern unsigned long max_pfn;
+extern unsigned long phys_base;
+
+extern unsigned long __phys_addr(unsigned long);
+#define __phys_reloc_hide(x)    (x)
+
+#define vmemmap ((struct page *)VMEMMAP_START)
+
+extern unsigned long init_memory_mapping(unsigned long start,
+                                         unsigned long end);
+
+extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern void free_initmem(void);
+
+extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
+extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
+
+#endif  /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_FLATMEM
+#define pfn_valid(pfn)          ((pfn) < max_pfn)
+#endif
+
+#endif /* _ASM_X86_PAGE_64_DEFS_H */
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
new file mode 100644
index 000000000000..826ad37006ab
--- /dev/null
+++ b/arch/x86/include/asm/page_types.h
@@ -0,0 +1,51 @@
+#ifndef _ASM_X86_PAGE_DEFS_H
+#define _ASM_X86_PAGE_DEFS_H
+
+#include <linux/const.h>
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT      12
+#define PAGE_SIZE       (_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_MASK       (~(PAGE_SIZE-1))
+
+#define __PHYSICAL_MASK         ((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __VIRTUAL_MASK          ((1UL << __VIRTUAL_MASK_SHIFT) - 1)
+
+/* Cast PAGE_MASK to a signed type so that it is sign-extended if
+   virtual addresses are 32-bits but physical addresses are larger
+   (ie, 32-bit PAE). */
+#define PHYSICAL_PAGE_MASK      (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
+
+#define PMD_PAGE_SIZE           (_AC(1, UL) << PMD_SHIFT)
+#define PMD_PAGE_MASK           (~(PMD_PAGE_SIZE-1))
+
+#define HPAGE_SHIFT             PMD_SHIFT
+#define HPAGE_SIZE              (_AC(1,UL) << HPAGE_SHIFT)
+#define HPAGE_MASK              (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
+
+#define HUGE_MAX_HSTATE 2
+
+#define PAGE_OFFSET             ((unsigned long)__PAGE_OFFSET)
+
+#define VM_DATA_DEFAULT_FLAGS \
+        (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+         VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#ifdef CONFIG_X86_64
+#include <asm/page_64_types.h>
+#else
+#include <asm/page_32_types.h>
+#endif  /* CONFIG_X86_64 */
+
+#ifndef __ASSEMBLY__
+
+extern int page_is_ram(unsigned long pagenr);
+extern int devmem_is_allowed(unsigned long pagenr);
+
+extern unsigned long max_low_pfn_mapped;
+extern unsigned long max_pfn_mapped;
+
+#endif  /* !__ASSEMBLY__ */
+
+#endif  /* _ASM_X86_PAGE_DEFS_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index e299287e8e33..7727aa8b7dda 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -4,7 +4,7 @@
  * para-virtualization: those hooks are defined here. */
 
 #ifdef CONFIG_PARAVIRT
-#include <asm/page.h>
+#include <asm/pgtable_types.h>
 #include <asm/asm.h>
 
 /* Bitmask of what can be clobbered: usually at least eax. */
@@ -12,21 +12,38 @@
 #define CLBR_EAX  (1 << 0)
 #define CLBR_ECX  (1 << 1)
 #define CLBR_EDX  (1 << 2)
+#define CLBR_EDI  (1 << 3)
 
-#ifdef CONFIG_X86_64
-#define CLBR_RSI  (1 << 3)
-#define CLBR_RDI  (1 << 4)
+#ifdef CONFIG_X86_32
+/* CLBR_ANY should match all regs platform has. For i386, that's just it */
+#define CLBR_ANY  ((1 << 4) - 1)
+
+#define CLBR_ARG_REGS   (CLBR_EAX | CLBR_EDX | CLBR_ECX)
+#define CLBR_RET_REG    (CLBR_EAX | CLBR_EDX)
+#define CLBR_SCRATCH    (0)
+#else
+#define CLBR_RAX  CLBR_EAX
+#define CLBR_RCX  CLBR_ECX
+#define CLBR_RDX  CLBR_EDX
+#define CLBR_RDI  CLBR_EDI
+#define CLBR_RSI  (1 << 4)
 #define CLBR_R8   (1 << 5)
 #define CLBR_R9   (1 << 6)
 #define CLBR_R10  (1 << 7)
 #define CLBR_R11  (1 << 8)
+
 #define CLBR_ANY  ((1 << 9) - 1)
+
+#define CLBR_ARG_REGS   (CLBR_RDI | CLBR_RSI | CLBR_RDX | \
+                         CLBR_RCX | CLBR_R8 | CLBR_R9)
+#define CLBR_RET_REG    (CLBR_RAX)
+#define CLBR_SCRATCH    (CLBR_R10 | CLBR_R11)
+
 #include <asm/desc_defs.h>
-#else
-/* CLBR_ANY should match all regs platform has. For i386, that's just it */
-#define CLBR_ANY  ((1 << 3) - 1)
 #endif /* X86_64 */
 
+#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
+
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 #include <linux/cpumask.h>
@@ -40,6 +57,14 @@ struct tss_struct;
 struct mm_struct;
 struct desc_struct;
 
+/*
+ * Wrapper type for pointers to code which uses the non-standard
+ * calling convention.  See PV_CALL_SAVE_REGS_THUNK below.
+ */
+struct paravirt_callee_save {
+        void *func;
+};
+
 /* general info */
 struct pv_info {
         unsigned int kernel_rpl;
@@ -189,11 +214,15 @@ struct pv_irq_ops {
          * expected to use X86_EFLAGS_IF; all other bits
          * returned from save_fl are undefined, and may be ignored by
          * restore_fl.
+         *
+         * NOTE: These functions callers expect the callee to preserve
+         * more registers than the standard C calling convention.
          */
-        unsigned long (*save_fl)(void);
-        void (*restore_fl)(unsigned long);
-        void (*irq_disable)(void);
-        void (*irq_enable)(void);
+        struct paravirt_callee_save save_fl;
+        struct paravirt_callee_save restore_fl;
+        struct paravirt_callee_save irq_disable;
+        struct paravirt_callee_save irq_enable;
+
         void (*safe_halt)(void);
         void (*halt)(void);
 
@@ -244,7 +273,8 @@ struct pv_mmu_ops {
         void (*flush_tlb_user)(void);
         void (*flush_tlb_kernel)(void);
         void (*flush_tlb_single)(unsigned long addr);
-        void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
+        void (*flush_tlb_others)(const struct cpumask *cpus,
+                                 struct mm_struct *mm,
                                  unsigned long va);
 
         /* Hooks for allocating and freeing a pagetable top-level */
@@ -278,18 +308,15 @@ struct pv_mmu_ops {
         void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
                                         pte_t *ptep, pte_t pte);
 
-        pteval_t (*pte_val)(pte_t);
-        pteval_t (*pte_flags)(pte_t);
-        pte_t (*make_pte)(pteval_t pte);
+        struct paravirt_callee_save pte_val;
+        struct paravirt_callee_save make_pte;
 
-        pgdval_t (*pgd_val)(pgd_t);
-        pgd_t (*make_pgd)(pgdval_t pgd);
+        struct paravirt_callee_save pgd_val;
+        struct paravirt_callee_save make_pgd;
 
 #if PAGETABLE_LEVELS >= 3
 #ifdef CONFIG_X86_PAE
         void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
-        void (*set_pte_present)(struct mm_struct *mm, unsigned long addr,
-                                pte_t *ptep, pte_t pte);
         void (*pte_clear)(struct mm_struct *mm, unsigned long addr,
                           pte_t *ptep);
         void (*pmd_clear)(pmd_t *pmdp);
@@ -298,12 +325,12 @@ struct pv_mmu_ops {
 
         void (*set_pud)(pud_t *pudp, pud_t pudval);
 
-        pmdval_t (*pmd_val)(pmd_t);
-        pmd_t (*make_pmd)(pmdval_t pmd);
+        struct paravirt_callee_save pmd_val;
+        struct paravirt_callee_save make_pmd;
 
 #if PAGETABLE_LEVELS == 4
-        pudval_t (*pud_val)(pud_t);
-        pud_t (*make_pud)(pudval_t pud);
+        struct paravirt_callee_save pud_val;
+        struct paravirt_callee_save make_pud;
 
         void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
 #endif  /* PAGETABLE_LEVELS == 4 */
@@ -360,7 +387,7 @@ extern struct pv_lock_ops pv_lock_ops;
 
 #define paravirt_type(op)                               \
         [paravirt_typenum] "i" (PARAVIRT_PATCH(op)),    \
-        [paravirt_opptr] "m" (op)
+        [paravirt_opptr] "i" (&(op))
 #define paravirt_clobber(clobber)               \
         [paravirt_clobber] "i" (clobber)
 
@@ -388,6 +415,8 @@ extern struct pv_lock_ops pv_lock_ops;
         asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
 
 unsigned paravirt_patch_nop(void);
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len);
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len);
 unsigned paravirt_patch_ignore(unsigned len);
 unsigned paravirt_patch_call(void *insnbuf,
                              const void *target, u16 tgt_clobbers,
@@ -412,7 +441,7 @@ int paravirt_disable_iospace(void);
  * offset into the paravirt_patch_template structure, and can therefore be
  * freely converted back into a structure offset.
  */
-#define PARAVIRT_CALL   "call *%[paravirt_opptr];"
+#define PARAVIRT_CALL   "call *%c[paravirt_opptr];"
 
 /*
  * These macros are intended to wrap calls through one of the paravirt
@@ -479,25 +508,45 @@ int paravirt_disable_iospace(void);
  * makes sure the incoming and outgoing types are always correct.
  */
 #ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS                 unsigned long __eax, __edx, __ecx
+#define PVOP_VCALL_ARGS                         \
+        unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx
 #define PVOP_CALL_ARGS                  PVOP_VCALL_ARGS
+
+#define PVOP_CALL_ARG1(x)               "a" ((unsigned long)(x))
+#define PVOP_CALL_ARG2(x)               "d" ((unsigned long)(x))
+#define PVOP_CALL_ARG3(x)               "c" ((unsigned long)(x))
+
 #define PVOP_VCALL_CLOBBERS             "=a" (__eax), "=d" (__edx),     \
                                         "=c" (__ecx)
 #define PVOP_CALL_CLOBBERS              PVOP_VCALL_CLOBBERS
+
+#define PVOP_VCALLEE_CLOBBERS           "=a" (__eax), "=d" (__edx)
+#define PVOP_CALLEE_CLOBBERS            PVOP_VCALLEE_CLOBBERS
+
 #define EXTRA_CLOBBERS
 #define VEXTRA_CLOBBERS
-#else
-#define PVOP_VCALL_ARGS         unsigned long __edi, __esi, __edx, __ecx
+#else  /* CONFIG_X86_64 */
+#define PVOP_VCALL_ARGS                                 \
+        unsigned long __edi = __edi, __esi = __esi,     \
+                __edx = __edx, __ecx = __ecx
 #define PVOP_CALL_ARGS          PVOP_VCALL_ARGS, __eax
+
+#define PVOP_CALL_ARG1(x)               "D" ((unsigned long)(x))
+#define PVOP_CALL_ARG2(x)               "S" ((unsigned long)(x))
+#define PVOP_CALL_ARG3(x)               "d" ((unsigned long)(x))
+#define PVOP_CALL_ARG4(x)               "c" ((unsigned long)(x))
+
 #define PVOP_VCALL_CLOBBERS     "=D" (__edi),                           \
                                 "=S" (__esi), "=d" (__edx),             \
                                 "=c" (__ecx)
-
 #define PVOP_CALL_CLOBBERS      PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
+#define PVOP_VCALLEE_CLOBBERS   "=a" (__eax)
+#define PVOP_CALLEE_CLOBBERS    PVOP_VCALLEE_CLOBBERS
+
 #define EXTRA_CLOBBERS   , "r8", "r9", "r10", "r11"
 #define VEXTRA_CLOBBERS  , "rax", "r8", "r9", "r10", "r11"
-#endif
+#endif  /* CONFIG_X86_32 */
 
 #ifdef CONFIG_PARAVIRT_DEBUG
 #define PVOP_TEST_NULL(op)      BUG_ON(op == NULL)
@@ -505,10 +554,11 @@ int paravirt_disable_iospace(void);
 #define PVOP_TEST_NULL(op)      ((void)op)
 #endif
 
-#define __PVOP_CALL(rettype, op, pre, post, ...)                        \
+#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr,         \
+                      pre, post, ...)                                   \
         ({                                                              \
                 rettype __ret;                                          \
-                PVOP_CALL_ARGS;                                 \
+                PVOP_CALL_ARGS;                                         \
                 PVOP_TEST_NULL(op);                                     \
                 /* This is 32-bit specific, but is okay in 64-bit */    \
                 /* since this condition will never hold */              \
@@ -516,70 +566,113 @@ int paravirt_disable_iospace(void);
                         asm volatile(pre                                \
                                      paravirt_alt(PARAVIRT_CALL)        \
                                      post                               \
-                                     : PVOP_CALL_CLOBBERS               \
+                                     : call_clbr                        \
                                      : paravirt_type(op),               \
-                                       paravirt_clobber(CLBR_ANY),      \
+                                       paravirt_clobber(clbr),          \
                                        ##__VA_ARGS__                    \
-                                     : "memory", "cc" EXTRA_CLOBBERS);  \
+                                     : "memory", "cc" extra_clbr);      \
                         __ret = (rettype)((((u64)__edx) << 32) | __eax); \
                 } else {                                                \
                         asm volatile(pre                                \
                                      paravirt_alt(PARAVIRT_CALL)        \
                                      post                               \
-                                     : PVOP_CALL_CLOBBERS               \
+                                     : call_clbr                        \
                                      : paravirt_type(op),               \
-                                       paravirt_clobber(CLBR_ANY),      \
+                                       paravirt_clobber(clbr),          \
                                        ##__VA_ARGS__                    \
-                                     : "memory", "cc" EXTRA_CLOBBERS);  \
+                                     : "memory", "cc" extra_clbr);      \
                         __ret = (rettype)__eax;                         \
                 }                                                       \
                 __ret;                                                  \
         })
-#define __PVOP_VCALL(op, pre, post, ...)                                \
+
+#define __PVOP_CALL(rettype, op, pre, post, ...)                        \
+        ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS,        \
+                      EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
+
+#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...)                  \
+        ____PVOP_CALL(rettype, op.func, CLBR_RET_REG,                   \
+                      PVOP_CALLEE_CLOBBERS, ,                           \
+                      pre, post, ##__VA_ARGS__)
+
+
+#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \
         ({                                                              \
                 PVOP_VCALL_ARGS;                                        \
                 PVOP_TEST_NULL(op);                                     \
                 asm volatile(pre                                        \
                              paravirt_alt(PARAVIRT_CALL)                \
                              post                                       \
-                             : PVOP_VCALL_CLOBBERS                      \
+                             : call_clbr                                \
                              : paravirt_type(op),                       \
-                               paravirt_clobber(CLBR_ANY),              \
+                               paravirt_clobber(clbr),                  \
                                ##__VA_ARGS__                            \
-                             : "memory", "cc" VEXTRA_CLOBBERS);         \
+                             : "memory", "cc" extra_clbr);              \
         })
 
+#define __PVOP_VCALL(op, pre, post, ...)                                \
+        ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS,               \
+                       VEXTRA_CLOBBERS,                                 \
+                       pre, post, ##__VA_ARGS__)
+
+#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...)                 \
+        ____PVOP_CALL(rettype, op.func, CLBR_RET_REG,                   \
+                      PVOP_VCALLEE_CLOBBERS, ,                          \
+                      pre, post, ##__VA_ARGS__)
+
+
+
 #define PVOP_CALL0(rettype, op)                                         \
         __PVOP_CALL(rettype, op, "", "")
 #define PVOP_VCALL0(op)                                                 \
         __PVOP_VCALL(op, "", "")
 
+#define PVOP_CALLEE0(rettype, op)                                       \
+        __PVOP_CALLEESAVE(rettype, op, "", "")
+#define PVOP_VCALLEE0(op)                                               \
+        __PVOP_VCALLEESAVE(op, "", "")
+
+
 #define PVOP_CALL1(rettype, op, arg1)                                   \
-        __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)))
+        __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALL1(op, arg1)                                           \
-        __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)))
+        __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+
+#define PVOP_CALLEE1(rettype, op, arg1)                                 \
+        __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+#define PVOP_VCALLEE1(op, arg1)                                         \
+        __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+
 
 #define PVOP_CALL2(rettype, op, arg1, arg2)                             \
-        __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),   \
-        "1" ((unsigned long)(arg2)))
+        __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),          \
+                    PVOP_CALL_ARG2(arg2))
 #define PVOP_VCALL2(op, arg1, arg2)                                     \
-        __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),           \
-        "1" ((unsigned long)(arg2)))
+        __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),                  \
+                     PVOP_CALL_ARG2(arg2))
+
+#define PVOP_CALLEE2(rettype, op, arg1, arg2)                           \
+        __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1),    \
+                          PVOP_CALL_ARG2(arg2))
+#define PVOP_VCALLEE2(op, arg1, arg2)                                   \
+        __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1),            \
+                           PVOP_CALL_ARG2(arg2))
+
 
 #define PVOP_CALL3(rettype, op, arg1, arg2, arg3)                       \
-        __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),   \
-        "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
+        __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),          \
+                    PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 #define PVOP_VCALL3(op, arg1, arg2, arg3)                               \
-        __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),           \
-        "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
+        __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),                  \
+                     PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 
 /* This is the only difference in x86_64. We can make it much simpler */
 #ifdef CONFIG_X86_32
 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)                 \
         __PVOP_CALL(rettype, op,                                        \
                     "push %[_arg4];", "lea 4(%%esp),%%esp;",            \
-                    "0" ((u32)(arg1)), "1" ((u32)(arg2)),               \
-                    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+                    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),         \
+                    PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
 #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)                         \
         __PVOP_VCALL(op,                                                \
                     "push %[_arg4];", "lea 4(%%esp),%%esp;",            \
@@ -587,13 +680,13 @@ int paravirt_disable_iospace(void);
                     "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
 #else
 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)                 \
-        __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),   \
-        "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)),         \
-        "3"((unsigned long)(arg4)))
+        __PVOP_CALL(rettype, op, "", "",                                \
+                    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),         \
+                    PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)                         \
-        __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),           \
-        "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)),         \
-        "3"((unsigned long)(arg4)))
+        __PVOP_VCALL(op, "", "",                                        \
+                     PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),        \
+                     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 #endif
 
 static inline int paravirt_enabled(void)
@@ -984,10 +1077,11 @@ static inline void __flush_tlb_single(unsigned long addr)
         PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
 }
 
-static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+static inline void flush_tlb_others(const struct cpumask *cpumask,
+                                    struct mm_struct *mm,
                                     unsigned long va)
 {
-        PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
+        PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, cpumask, mm, va);
 }
 
 static inline int paravirt_pgd_alloc(struct mm_struct *mm)
@@ -1059,13 +1153,13 @@ static inline pte_t __pte(pteval_t val)
         pteval_t ret;
 
         if (sizeof(pteval_t) > sizeof(long))
-                ret = PVOP_CALL2(pteval_t,
-                                 pv_mmu_ops.make_pte,
-                                 val, (u64)val >> 32);
+                ret = PVOP_CALLEE2(pteval_t,
+                                   pv_mmu_ops.make_pte,
+                                   val, (u64)val >> 32);
         else
-                ret = PVOP_CALL1(pteval_t,
-                                 pv_mmu_ops.make_pte,
-                                 val);
+                ret = PVOP_CALLEE1(pteval_t,
+                                   pv_mmu_ops.make_pte,
+                                   val);
 
         return (pte_t) { .pte = ret };
 }
@@ -1075,29 +1169,12 @@ static inline pteval_t pte_val(pte_t pte)
         pteval_t ret;
 
         if (sizeof(pteval_t) > sizeof(long))
-                ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_val,
-                                 pte.pte, (u64)pte.pte >> 32);
-        else
-                ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_val,
-                                 pte.pte);
-
-        return ret;
-}
-
-static inline pteval_t pte_flags(pte_t pte)
-{
-        pteval_t ret;
-
-        if (sizeof(pteval_t) > sizeof(long))
-                ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
-                                 pte.pte, (u64)pte.pte >> 32);
+                ret = PVOP_CALLEE2(pteval_t, pv_mmu_ops.pte_val,
+                                   pte.pte, (u64)pte.pte >> 32);
         else
-                ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
-                                 pte.pte);
+                ret = PVOP_CALLEE1(pteval_t, pv_mmu_ops.pte_val,
+                                   pte.pte);
 
-#ifdef CONFIG_PARAVIRT_DEBUG
-        BUG_ON(ret & PTE_PFN_MASK);
-#endif
         return ret;
 }
 
@@ -1106,11 +1183,11 @@ static inline pgd_t __pgd(pgdval_t val)
         pgdval_t ret;
 
         if (sizeof(pgdval_t) > sizeof(long))
-                ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.make_pgd,
-                                 val, (u64)val >> 32);
+                ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.make_pgd,
+                                   val, (u64)val >> 32);
         else
-                ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.make_pgd,
-                                 val);
+                ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.make_pgd,
+                                   val);
 
         return (pgd_t) { ret };
 }
@@ -1120,11 +1197,11 @@ static inline pgdval_t pgd_val(pgd_t pgd)
         pgdval_t ret;
 
         if (sizeof(pgdval_t) > sizeof(long))
-                ret =  PVOP_CALL2(pgdval_t, pv_mmu_ops.pgd_val,
-                                  pgd.pgd, (u64)pgd.pgd >> 32);
+                ret =  PVOP_CALLEE2(pgdval_t, pv_mmu_ops.pgd_val,
+                                    pgd.pgd, (u64)pgd.pgd >> 32);
         else
-                ret =  PVOP_CALL1(pgdval_t, pv_mmu_ops.pgd_val,
-                                  pgd.pgd);
+                ret =  PVOP_CALLEE1(pgdval_t, pv_mmu_ops.pgd_val,
+                                    pgd.pgd);
 
         return ret;
 }
@@ -1188,11 +1265,11 @@ static inline pmd_t __pmd(pmdval_t val)
         pmdval_t ret;
 
         if (sizeof(pmdval_t) > sizeof(long))
-                ret = PVOP_CALL2(pmdval_t, pv_mmu_ops.make_pmd,
-                                 val, (u64)val >> 32);
+                ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.make_pmd,
+                                   val, (u64)val >> 32);
         else
-                ret = PVOP_CALL1(pmdval_t, pv_mmu_ops.make_pmd,
-                                 val);
+                ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.make_pmd,
+                                   val);
 
         return (pmd_t) { ret };
 }
@@ -1202,11 +1279,11 @@ static inline pmdval_t pmd_val(pmd_t pmd)
         pmdval_t ret;
 
         if (sizeof(pmdval_t) > sizeof(long))
-                ret =  PVOP_CALL2(pmdval_t, pv_mmu_ops.pmd_val,
-                                  pmd.pmd, (u64)pmd.pmd >> 32);
+                ret =  PVOP_CALLEE2(pmdval_t, pv_mmu_ops.pmd_val,
+                                    pmd.pmd, (u64)pmd.pmd >> 32);
         else
-                ret =  PVOP_CALL1(pmdval_t, pv_mmu_ops.pmd_val,
-                                  pmd.pmd);
+                ret =  PVOP_CALLEE1(pmdval_t, pv_mmu_ops.pmd_val,
+                                    pmd.pmd);
 
         return ret;
 }
@@ -1228,11 +1305,11 @@ static inline pud_t __pud(pudval_t val)
         pudval_t ret;
 
         if (sizeof(pudval_t) > sizeof(long))
-                ret = PVOP_CALL2(pudval_t, pv_mmu_ops.make_pud,
-                                 val, (u64)val >> 32);
+                ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.make_pud,
+                                   val, (u64)val >> 32);
         else
-                ret = PVOP_CALL1(pudval_t, pv_mmu_ops.make_pud,
-                                 val);
+                ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.make_pud,
+                                   val);
 
         return (pud_t) { ret };
 }
@@ -1242,11 +1319,11 @@ static inline pudval_t pud_val(pud_t pud)
         pudval_t ret;
 
         if (sizeof(pudval_t) > sizeof(long))
-                ret =  PVOP_CALL2(pudval_t, pv_mmu_ops.pud_val,
-                                  pud.pud, (u64)pud.pud >> 32);
+                ret =  PVOP_CALLEE2(pudval_t, pv_mmu_ops.pud_val,
+                                    pud.pud, (u64)pud.pud >> 32);
         else
-                ret =  PVOP_CALL1(pudval_t, pv_mmu_ops.pud_val,
-                                  pud.pud);
+                ret =  PVOP_CALLEE1(pudval_t, pv_mmu_ops.pud_val,
+                                    pud.pud);
 
         return ret;
 }
@@ -1286,13 +1363,6 @@ static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
                     pte.pte, pte.pte >> 32);
 }
 
-static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
-                                   pte_t *ptep, pte_t pte)
-{
-        /* 5 arg words */
-        pv_mmu_ops.set_pte_present(mm, addr, ptep, pte);
-}
-
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
                              pte_t *ptep)
 {
@@ -1309,12 +1379,6 @@ static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
         set_pte(ptep, pte);
 }
 
-static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
-                                   pte_t *ptep, pte_t pte)
-{
-        set_pte(ptep, pte);
-}
-
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
                              pte_t *ptep)
 {
@@ -1374,9 +1438,10 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 }
 
 void _paravirt_nop(void);
-#define paravirt_nop    ((void *)_paravirt_nop)
+u32 _paravirt_ident_32(u32);
+u64 _paravirt_ident_64(u64);
 
-void paravirt_use_bytelocks(void);
+#define paravirt_nop    ((void *)_paravirt_nop)
 
 #ifdef CONFIG_SMP
 
@@ -1426,12 +1491,37 @@ extern struct paravirt_patch_site __parainstructions[],
         __parainstructions_end[];
 
 #ifdef CONFIG_X86_32
-#define PV_SAVE_REGS "pushl %%ecx; pushl %%edx;"
-#define PV_RESTORE_REGS "popl %%edx; popl %%ecx"
+#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
+#define PV_RESTORE_REGS "popl %edx; popl %ecx;"
+
+/* save and restore all caller-save registers, except return value */
+#define PV_SAVE_ALL_CALLER_REGS         "pushl %ecx;"
+#define PV_RESTORE_ALL_CALLER_REGS      "popl  %ecx;"
+
 #define PV_FLAGS_ARG "0"
 #define PV_EXTRA_CLOBBERS
 #define PV_VEXTRA_CLOBBERS
 #else
+/* save and restore all caller-save registers, except return value */
+#define PV_SAVE_ALL_CALLER_REGS                                         \
+        "push %rcx;"                                                    \
+        "push %rdx;"                                                    \
+        "push %rsi;"                                                    \
+        "push %rdi;"                                                    \
+        "push %r8;"                                                     \
+        "push %r9;"                                                     \
+        "push %r10;"                                                    \
+        "push %r11;"
+#define PV_RESTORE_ALL_CALLER_REGS                                      \
+        "pop %r11;"                                                     \
+        "pop %r10;"                                                     \
+        "pop %r9;"                                                      \
+        "pop %r8;"                                                      \
+        "pop %rdi;"                                                     \
+        "pop %rsi;"                                                     \
+        "pop %rdx;"                                                     \
+        "pop %rcx;"
+
 /* We save some registers, but all of them, that's too much. We clobber all
  * caller saved registers but the argument parameter */
 #define PV_SAVE_REGS "pushq %%rdi;"
@@ -1441,52 +1531,76 @@ extern struct paravirt_patch_site __parainstructions[],
 #define PV_FLAGS_ARG "D"
 #endif
 
+/*
+ * Generate a thunk around a function which saves all caller-save
+ * registers except for the return value.  This allows C functions to
+ * be called from assembler code where fewer than normal registers are
+ * available.  It may also help code generation around calls from C
+ * code if the common case doesn't use many registers.
+ *
+ * When a callee is wrapped in a thunk, the caller can assume that all
+ * arg regs and all scratch registers are preserved across the
+ * call. The return value in rax/eax will not be saved, even for void
+ * functions.
+ */
+#define PV_CALLEE_SAVE_REGS_THUNK(func)                                 \
+        extern typeof(func) __raw_callee_save_##func;                   \
+        static void *__##func##__ __used = func;                        \
+                                                                        \
+        asm(".pushsection .text;"                                       \
+            "__raw_callee_save_" #func ": "                             \
+            PV_SAVE_ALL_CALLER_REGS                                     \
+            "call " #func ";"                                           \
+            PV_RESTORE_ALL_CALLER_REGS                                  \
+            "ret;"                                                      \
+            ".popsection")
+
+/* Get a reference to a callee-save function */
+#define PV_CALLEE_SAVE(func)                                            \
+        ((struct paravirt_callee_save) { __raw_callee_save_##func })
+
+/* Promise that "func" already uses the right calling convention */
+#define __PV_IS_CALLEE_SAVE(func)                       \
+        ((struct paravirt_callee_save) { func })
+
 static inline unsigned long __raw_local_save_flags(void)
 {
         unsigned long f;
 
-        asm volatile(paravirt_alt(PV_SAVE_REGS
-                                  PARAVIRT_CALL
-                                  PV_RESTORE_REGS)
+        asm volatile(paravirt_alt(PARAVIRT_CALL)
                      : "=a"(f)
                      : paravirt_type(pv_irq_ops.save_fl),
                        paravirt_clobber(CLBR_EAX)
-                     : "memory", "cc" PV_VEXTRA_CLOBBERS);
+                     : "memory", "cc");
         return f;
 }
 
 static inline void raw_local_irq_restore(unsigned long f)
 {
-        asm volatile(paravirt_alt(PV_SAVE_REGS
-                                  PARAVIRT_CALL
-                                  PV_RESTORE_REGS)
+        asm volatile(paravirt_alt(PARAVIRT_CALL)
                      : "=a"(f)
                      : PV_FLAGS_ARG(f),
                        paravirt_type(pv_irq_ops.restore_fl),
                        paravirt_clobber(CLBR_EAX)
-                     : "memory", "cc" PV_EXTRA_CLOBBERS);
+                     : "memory", "cc");
 }
 
 static inline void raw_local_irq_disable(void)
 {
-        asm volatile(paravirt_alt(PV_SAVE_REGS
-                                  PARAVIRT_CALL
-                                  PV_RESTORE_REGS)
+        asm volatile(paravirt_alt(PARAVIRT_CALL)
                      :
                      : paravirt_type(pv_irq_ops.irq_disable),
                        paravirt_clobber(CLBR_EAX)
-                     : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
+                     : "memory", "eax", "cc");
 }
 
 static inline void raw_local_irq_enable(void)
 {
-        asm volatile(paravirt_alt(PV_SAVE_REGS
-                                  PARAVIRT_CALL
-                                  PV_RESTORE_REGS)
+        asm volatile(paravirt_alt(PARAVIRT_CALL)
                      :
                      : paravirt_type(pv_irq_ops.irq_enable),
                        paravirt_clobber(CLBR_EAX)
-                     : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
+                     : "memory", "eax", "cc");
 }
 
 static inline unsigned long __raw_local_irq_save(void)
@@ -1529,33 +1643,49 @@ static inline unsigned long __raw_local_irq_save(void)
         .popsection
 
 
+#define COND_PUSH(set, mask, reg)                       \
+        .if ((~(set)) & mask); push %reg; .endif
+#define COND_POP(set, mask, reg)                        \
+        .if ((~(set)) & mask); pop %reg; .endif
+
 #ifdef CONFIG_X86_64
-#define PV_SAVE_REGS                            \
-        push %rax;                              \
-        push %rcx;                              \
-        push %rdx;                              \
-        push %rsi;                              \
-        push %rdi;                              \
-        push %r8;                               \
-        push %r9;                               \
-        push %r10;                              \
-        push %r11
-#define PV_RESTORE_REGS                         \
-        pop %r11;                               \
-        pop %r10;                               \
-        pop %r9;                                \
-        pop %r8;                                \
-        pop %rdi;                               \
-        pop %rsi;                               \
-        pop %rdx;                               \
-        pop %rcx;                               \
-        pop %rax
+
+#define PV_SAVE_REGS(set)                       \
+        COND_PUSH(set, CLBR_RAX, rax);          \
+        COND_PUSH(set, CLBR_RCX, rcx);          \
+        COND_PUSH(set, CLBR_RDX, rdx);          \
+        COND_PUSH(set, CLBR_RSI, rsi);          \
+        COND_PUSH(set, CLBR_RDI, rdi);          \
+        COND_PUSH(set, CLBR_R8, r8);            \
+        COND_PUSH(set, CLBR_R9, r9);            \
+        COND_PUSH(set, CLBR_R10, r10);          \
+        COND_PUSH(set, CLBR_R11, r11)
+#define PV_RESTORE_REGS(set)                    \
+        COND_POP(set, CLBR_R11, r11);           \
+        COND_POP(set, CLBR_R10, r10);           \
+        COND_POP(set, CLBR_R9, r9);             \
+        COND_POP(set, CLBR_R8, r8);             \
+        COND_POP(set, CLBR_RDI, rdi);           \
+        COND_POP(set, CLBR_RSI, rsi);           \
+        COND_POP(set, CLBR_RDX, rdx);           \
+        COND_POP(set, CLBR_RCX, rcx);           \
+        COND_POP(set, CLBR_RAX, rax)
+
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 8)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
 #define PARA_INDIRECT(addr)     *addr(%rip)
 #else
-#define PV_SAVE_REGS   pushl %eax; pushl %edi; pushl %ecx; pushl %edx
-#define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax
+#define PV_SAVE_REGS(set)                       \
+        COND_PUSH(set, CLBR_EAX, eax);          \
+        COND_PUSH(set, CLBR_EDI, edi);          \
+        COND_PUSH(set, CLBR_ECX, ecx);          \
+        COND_PUSH(set, CLBR_EDX, edx)
+#define PV_RESTORE_REGS(set)                    \
+        COND_POP(set, CLBR_EDX, edx);           \
+        COND_POP(set, CLBR_ECX, ecx);           \
+        COND_POP(set, CLBR_EDI, edi);           \
+        COND_POP(set, CLBR_EAX, eax)
+
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 4)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
 #define PARA_INDIRECT(addr)     *%cs:addr
@@ -1567,15 +1697,15 @@ static inline unsigned long __raw_local_irq_save(void)
 
 #define DISABLE_INTERRUPTS(clobbers)                                    \
         PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
-                  PV_SAVE_REGS;                                         \
+                  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);            \
                   call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);    \
-                  PV_RESTORE_REGS;)                     \
+                  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #define ENABLE_INTERRUPTS(clobbers)                                     \
         PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,  \
-                  PV_SAVE_REGS;                                         \
+                  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);            \
                   call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);     \
-                  PV_RESTORE_REGS;)
+                  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #define USERGS_SYSRET32                                                 \
         PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),       \
@@ -1605,11 +1735,15 @@ static inline unsigned long __raw_local_irq_save(void)
         PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,     \
                   swapgs)
 
+/*
+ * Note: swapgs is very special, and in practise is either going to be
+ * implemented with a single "swapgs" instruction or something very
+ * special.  Either way, we don't need to save any registers for
+ * it.
+ */
 #define SWAPGS                                                          \
         PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,     \
-                  PV_SAVE_REGS;                                         \
-                  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);         \
-                  PV_RESTORE_REGS                                       \
+                  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs)          \
                  )
 
 #define GET_CR2_INTO_RCX                                \
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index b8493b3b9890..2cd07b9422f4 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -2,13 +2,12 @@
 #define _ASM_X86_PAT_H
 
 #include <linux/types.h>
+#include <asm/pgtable_types.h>
 
 #ifdef CONFIG_X86_PAT
 extern int pat_enabled;
-extern void validate_pat_support(struct cpuinfo_x86 *c);
 #else
 static const int pat_enabled;
-static inline void validate_pat_support(struct cpuinfo_x86 *c) { }
 #endif
 
 extern void pat_init(void);
@@ -17,6 +16,11 @@ extern int reserve_memtype(u64 start, u64 end,
                 unsigned long req_type, unsigned long *ret_type);
 extern int free_memtype(u64 start, u64 end);
 
-extern void pat_disable(char *reason);
+extern int kernel_map_sync_memtype(u64 base, unsigned long size,
+                unsigned long flag);
+extern void map_devmem(unsigned long pfn, unsigned long size,
+                       struct pgprot vma_prot);
+extern void unmap_devmem(unsigned long pfn, unsigned long size,
+                         struct pgprot vma_prot);
 
 #endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/mach-default/pci-functions.h b/arch/x86/include/asm/pci-functions.h
index ed0bab427354..ed0bab427354 100644
--- a/arch/x86/include/asm/mach-default/pci-functions.h
+++ b/arch/x86/include/asm/pci-functions.h
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index a977de23cb4d..e545ea01abcf 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -86,12 +86,43 @@ static inline void early_quirks(void) { }
 
 extern void pci_iommu_alloc(void);
 
-#endif  /* __KERNEL__ */
+/* MSI arch hook */
+#define arch_setup_msi_irqs arch_setup_msi_irqs
+
+#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG)
+
+#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))
 
-#ifdef CONFIG_X86_32
-# include "pci_32.h"
 #else
-# include "pci_64.h"
+
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       dma_addr_t ADDR_NAME[0];
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0];
+#define pci_unmap_addr(PTR, ADDR_NAME)  sizeof((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+                do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
+#define pci_unmap_len(PTR, LEN_NAME)            sizeof((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
+                do { break; } while (pci_unmap_len(PTR, LEN_NAME))
+
+#endif
+
+#endif  /* __KERNEL__ */
+
+#ifdef CONFIG_X86_64
+#include "pci_64.h"
 #endif
 
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
diff --git a/arch/x86/include/asm/pci_32.h b/arch/x86/include/asm/pci_32.h
deleted file mode 100644
index 6f1213a6ef4f..000000000000
--- a/arch/x86/include/asm/pci_32.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef _ASM_X86_PCI_32_H
-#define _ASM_X86_PCI_32_H
-
-
-#ifdef __KERNEL__
-
-
-/* Dynamic DMA mapping stuff.
- * i386 has everything mapped statically.
- */
-
-struct pci_dev;
-
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS     (1)
-
-/* pci_unmap_{page,single} is a nop so... */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       dma_addr_t ADDR_NAME[0];
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0];
-#define pci_unmap_addr(PTR, ADDR_NAME)  sizeof((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
-        do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
-#define pci_unmap_len(PTR, LEN_NAME)            sizeof((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
-        do { break; } while (pci_unmap_len(PTR, LEN_NAME))
-
-
-#endif /* __KERNEL__ */
-
-
-#endif /* _ASM_X86_PCI_32_H */
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index 4da207982777..ae5e40f67daf 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -24,28 +24,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
 
 extern void dma32_reserve_bootmem(void);
 
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions
- *
- * On AMD64 it mostly equals, but we set it to zero if a hardware
- * IOMMU (gart) of sotware IOMMU (swiotlb) is available.
- */
-#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
-
-#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))
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_PCI_64_H */
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
deleted file mode 100644
index 2fbfff88df37..000000000000
--- a/arch/x86/include/asm/pda.h
+++ /dev/null
@@ -1,137 +0,0 @@
-#ifndef _ASM_X86_PDA_H
-#define _ASM_X86_PDA_H
-
-#ifndef __ASSEMBLY__
-#include <linux/stddef.h>
-#include <linux/types.h>
-#include <linux/cache.h>
-#include <asm/page.h>
-
-/* Per processor datastructure. %gs points to it while the kernel runs */
-struct x8664_pda {
-        struct task_struct *pcurrent;   /* 0  Current process */
-        unsigned long data_offset;      /* 8 Per cpu data offset from linker
-                                           address */
-        unsigned long kernelstack;      /* 16 top of kernel stack for current */
-        unsigned long oldrsp;           /* 24 user rsp for system call */
-        int irqcount;                   /* 32 Irq nesting counter. Starts -1 */
-        unsigned int cpunumber;         /* 36 Logical CPU number */
-#ifdef CONFIG_CC_STACKPROTECTOR
-        unsigned long stack_canary;     /* 40 stack canary value */
-                                        /* gcc-ABI: this canary MUST be at
-                                           offset 40!!! */
-#endif
-        char *irqstackptr;
-        short nodenumber;               /* number of current node (32k max) */
-        short in_bootmem;               /* pda lives in bootmem */
-        unsigned int __softirq_pending;
-        unsigned int __nmi_count;       /* number of NMI on this CPUs */
-        short mmu_state;
-        short isidle;
-        struct mm_struct *active_mm;
-        unsigned apic_timer_irqs;
-        unsigned irq0_irqs;
-        unsigned irq_resched_count;
-        unsigned irq_call_count;
-        unsigned irq_tlb_count;
-        unsigned irq_thermal_count;
-        unsigned irq_threshold_count;
-        unsigned irq_spurious_count;
-} ____cacheline_aligned_in_smp;
-
-extern struct x8664_pda **_cpu_pda;
-extern void pda_init(int);
-
-#define cpu_pda(i) (_cpu_pda[i])
-
-/*
- * There is no fast way to get the base address of the PDA, all the accesses
- * have to mention %fs/%gs.  So it needs to be done this Torvaldian way.
- */
-extern void __bad_pda_field(void) __attribute__((noreturn));
-
-/*
- * proxy_pda doesn't actually exist, but tell gcc it is accessed for
- * all PDA accesses so it gets read/write dependencies right.
- */
-extern struct x8664_pda _proxy_pda;
-
-#define pda_offset(field) offsetof(struct x8664_pda, field)
-
-#define pda_to_op(op, field, val)                                       \
-do {                                                                    \
-        typedef typeof(_proxy_pda.field) T__;                           \
-        if (0) { T__ tmp__; tmp__ = (val); }    /* type checking */     \
-        switch (sizeof(_proxy_pda.field)) {                             \
-        case 2:                                                         \
-                asm(op "w %1,%%gs:%c2" :                                \
-                    "+m" (_proxy_pda.field) :                           \
-                    "ri" ((T__)val),                                    \
-                    "i"(pda_offset(field)));                            \
-                break;                                                  \
-        case 4:                                                         \
-                asm(op "l %1,%%gs:%c2" :                                \
-                    "+m" (_proxy_pda.field) :                           \
-                    "ri" ((T__)val),                                    \
-                    "i" (pda_offset(field)));                           \
-                break;                                                  \
-        case 8:                                                         \
-                asm(op "q %1,%%gs:%c2":                                 \
-                    "+m" (_proxy_pda.field) :                           \
-                    "ri" ((T__)val),                                    \
-                    "i"(pda_offset(field)));                            \
-                break;                                                  \
-        default:                                                        \
-                __bad_pda_field();                                      \
-        }                                                               \
-} while (0)
-
-#define pda_from_op(op, field)                  \
-({                                              \
-        typeof(_proxy_pda.field) ret__;         \
-        switch (sizeof(_proxy_pda.field)) {     \
-        case 2:                                 \
-                asm(op "w %%gs:%c1,%0" :        \
-                    "=r" (ret__) :              \
-                    "i" (pda_offset(field)),    \
-                    "m" (_proxy_pda.field));    \
-                break;                          \
-        case 4:                                 \
-                asm(op "l %%gs:%c1,%0":         \
-                    "=r" (ret__):               \
-                    "i" (pda_offset(field)),    \
-                    "m" (_proxy_pda.field));    \
-                break;                          \
-        case 8:                                 \
-                asm(op "q %%gs:%c1,%0":         \
-                    "=r" (ret__) :              \
-                    "i" (pda_offset(field)),    \
-                    "m" (_proxy_pda.field));    \
-                break;                          \
-        default:                                \
-                __bad_pda_field();              \
-        }                                       \
-        ret__;                                  \
-})
-
-#define read_pda(field)         pda_from_op("mov", field)
-#define write_pda(field, val)   pda_to_op("mov", field, val)
-#define add_pda(field, val)     pda_to_op("add", field, val)
-#define sub_pda(field, val)     pda_to_op("sub", field, val)
-#define or_pda(field, val)      pda_to_op("or", field, val)
-
-/* This is not atomic against other CPUs -- CPU preemption needs to be off */
-#define test_and_clear_bit_pda(bit, field)                              \
-({                                                                      \
-        int old__;                                                      \
-        asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"                    \
-                     : "=r" (old__), "+m" (_proxy_pda.field)            \
-                     : "dIr" (bit), "i" (pda_offset(field)) : "memory");\
-        old__;                                                          \
-})
-
-#endif
-
-#define PDA_STACKOFFSET (5*8)
-
-#endif /* _ASM_X86_PDA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ece72053ba63..aee103b26d01 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -2,53 +2,12 @@
 #define _ASM_X86_PERCPU_H
 
 #ifdef CONFIG_X86_64
-#include <linux/compiler.h>
-
-/* Same as asm-generic/percpu.h, except that we store the per cpu offset
-   in the PDA. Longer term the PDA and every per cpu variable
-   should be just put into a single section and referenced directly
-   from %gs */
-
-#ifdef CONFIG_SMP
-#include <asm/pda.h>
-
-#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
-#define __my_cpu_offset read_pda(data_offset)
-
-#define per_cpu_offset(x) (__per_cpu_offset(x))
-
+#define __percpu_seg            gs
+#define __percpu_mov_op         movq
+#else
+#define __percpu_seg            fs
+#define __percpu_mov_op         movl
 #endif
-#include <asm-generic/percpu.h>
-
-DECLARE_PER_CPU(struct x8664_pda, pda);
-
-/*
- * These are supposed to be implemented as a single instruction which
- * operates on the per-cpu data base segment.  x86-64 doesn't have
- * that yet, so this is a fairly inefficient workaround for the
- * meantime.  The single instruction is atomic with respect to
- * preemption and interrupts, so we need to explicitly disable
- * interrupts here to achieve the same effect.  However, because it
- * can be used from within interrupt-disable/enable, we can't actually
- * disable interrupts; disabling preemption is enough.
- */
-#define x86_read_percpu(var)                                            \
-        ({                                                              \
-                typeof(per_cpu_var(var)) __tmp;                         \
-                preempt_disable();                                      \
-                __tmp = __get_cpu_var(var);                             \
-                preempt_enable();                                       \
-                __tmp;                                                  \
-        })
-
-#define x86_write_percpu(var, val)                                      \
-        do {                                                            \
-                preempt_disable();                                      \
-                __get_cpu_var(var) = (val);                             \
-                preempt_enable();                                       \
-        } while(0)
-
-#else /* CONFIG_X86_64 */
 
 #ifdef __ASSEMBLY__
 
@@ -65,47 +24,48 @@ DECLARE_PER_CPU(struct x8664_pda, pda);
  *    PER_CPU(cpu_gdt_descr, %ebx)
  */
 #ifdef CONFIG_SMP
-#define PER_CPU(var, reg)                               \
-        movl %fs:per_cpu__##this_cpu_off, reg;          \
+#define PER_CPU(var, reg)                                               \
+        __percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg;       \
         lea per_cpu__##var(reg), reg
-#define PER_CPU_VAR(var)        %fs:per_cpu__##var
+#define PER_CPU_VAR(var)        %__percpu_seg:per_cpu__##var
 #else /* ! SMP */
-#define PER_CPU(var, reg)                       \
-        movl $per_cpu__##var, reg
+#define PER_CPU(var, reg)                                               \
+        __percpu_mov_op $per_cpu__##var, reg
 #define PER_CPU_VAR(var)        per_cpu__##var
 #endif  /* SMP */
 
+#ifdef CONFIG_X86_64_SMP
+#define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
+#else
+#define INIT_PER_CPU_VAR(var)  per_cpu__##var
+#endif
+
 #else /* ...!ASSEMBLY */
 
+#include <linux/stringify.h>
+
+#ifdef CONFIG_SMP
+#define __percpu_arg(x)         "%%"__stringify(__percpu_seg)":%P" #x
+#define __my_cpu_offset         percpu_read(this_cpu_off)
+#else
+#define __percpu_arg(x)         "%" #x
+#endif
+
 /*
- * PER_CPU finds an address of a per-cpu variable.
+ * Initialized pointers to per-cpu variables needed for the boot
+ * processor need to use these macros to get the proper address
+ * offset from __per_cpu_load on SMP.
  *
- * Args:
- *    var - variable name
- *    cpu - 32bit register containing the current CPU number
- *
- * The resulting address is stored in the "cpu" argument.
- *
- * Example:
- *    PER_CPU(cpu_gdt_descr, %ebx)
+ * There also must be an entry in vmlinux_64.lds.S
  */
-#ifdef CONFIG_SMP
-
-#define __my_cpu_offset x86_read_percpu(this_cpu_off)
-
-/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
-#define __percpu_seg "%%fs:"
-
-#else  /* !SMP */
-
-#define __percpu_seg ""
-
-#endif  /* SMP */
-
-#include <asm-generic/percpu.h>
+#define DECLARE_INIT_PER_CPU(var) \
+       extern typeof(per_cpu_var(var)) init_per_cpu_var(var)
 
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
+#ifdef CONFIG_X86_64_SMP
+#define init_per_cpu_var(var)  init_per_cpu__##var
+#else
+#define init_per_cpu_var(var)  per_cpu_var(var)
+#endif
 
 /* For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though). */
@@ -120,20 +80,25 @@ do {							\
         }                                               \
         switch (sizeof(var)) {                          \
         case 1:                                         \
-                asm(op "b %1,"__percpu_seg"%0"          \
+                asm(op "b %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
                     : "ri" ((T__)val));                 \
                 break;                                  \
         case 2:                                         \
-                asm(op "w %1,"__percpu_seg"%0"          \
+                asm(op "w %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
                     : "ri" ((T__)val));                 \
                 break;                                  \
         case 4:                                         \
-                asm(op "l %1,"__percpu_seg"%0"          \
+                asm(op "l %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
                     : "ri" ((T__)val));                 \
                 break;                                  \
+        case 8:                                         \
+                asm(op "q %1,"__percpu_arg(0)           \
+                    : "+m" (var)                        \
+                    : "re" ((T__)val));                 \
+                break;                                  \
         default: __bad_percpu_size();                   \
         }                                               \
 } while (0)
@@ -143,17 +108,22 @@ do {							\
         typeof(var) ret__;                              \
         switch (sizeof(var)) {                          \
         case 1:                                         \
-                asm(op "b "__percpu_seg"%1,%0"          \
+                asm(op "b "__percpu_arg(1)",%0"         \
                     : "=r" (ret__)                      \
                     : "m" (var));                       \
                 break;                                  \
         case 2:                                         \
-                asm(op "w "__percpu_seg"%1,%0"          \
+                asm(op "w "__percpu_arg(1)",%0"         \
                     : "=r" (ret__)                      \
                     : "m" (var));                       \
                 break;                                  \
         case 4:                                         \
-                asm(op "l "__percpu_seg"%1,%0"          \
+                asm(op "l "__percpu_arg(1)",%0"         \
+                    : "=r" (ret__)                      \
+                    : "m" (var));                       \
+                break;                                  \
+        case 8:                                         \
+                asm(op "q "__percpu_arg(1)",%0"         \
                     : "=r" (ret__)                      \
                     : "m" (var));                       \
                 break;                                  \
@@ -162,13 +132,30 @@ do {							\
         ret__;                                          \
 })
 
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_read(var)        percpu_from_op("mov", per_cpu__##var)
+#define percpu_write(var, val)  percpu_to_op("mov", per_cpu__##var, val)
+#define percpu_add(var, val)    percpu_to_op("add", per_cpu__##var, val)
+#define percpu_sub(var, val)    percpu_to_op("sub", per_cpu__##var, val)
+#define percpu_and(var, val)    percpu_to_op("and", per_cpu__##var, val)
+#define percpu_or(var, val)     percpu_to_op("or", per_cpu__##var, val)
+#define percpu_xor(var, val)    percpu_to_op("xor", per_cpu__##var, val)
+
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define x86_test_and_clear_bit_percpu(bit, var)                         \
+({                                                                      \
+        int old__;                                                      \
+        asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"           \
+                     : "=r" (old__), "+m" (per_cpu__##var)              \
+                     : "dIr" (bit));                                    \
+        old__;                                                          \
+})
+
+#include <asm-generic/percpu.h>
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
 #endif /* !__ASSEMBLY__ */
-#endif /* !CONFIG_X86_64 */
 
 #ifdef CONFIG_SMP
 
@@ -195,9 +182,9 @@ do {							\
 #define early_per_cpu_ptr(_name) (_name##_early_ptr)
 #define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
 #define early_per_cpu(_name, _cpu)                              \
-        (early_per_cpu_ptr(_name) ?                             \
-                early_per_cpu_ptr(_name)[_cpu] :                \
-                per_cpu(_name, _cpu))
+        *(early_per_cpu_ptr(_name) ?                            \
+                &early_per_cpu_ptr(_name)[_cpu] :               \
+                &per_cpu(_name, _cpu))
 
 #else   /* !CONFIG_SMP */
 #define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)          \
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index e0d199fe1d83..2334982b339e 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -26,13 +26,6 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
         native_set_pte(ptep, pte);
 }
 
-static inline void native_set_pte_present(struct mm_struct *mm,
-                                          unsigned long addr,
-                                          pte_t *ptep, pte_t pte)
-{
-        native_set_pte(ptep, pte);
-}
-
 static inline void native_pmd_clear(pmd_t *pmdp)
 {
         native_set_pmd(pmdp, __pmd(0));
@@ -53,8 +46,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#define pte_none(x)             (!(x).pte_low)
-
 /*
  * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
  * split up the 29 bits of offset into this range:
diff --git a/arch/x86/include/asm/pgtable-2level-defs.h b/arch/x86/include/asm/pgtable-2level_types.h
index d77db8990eaa..daacc23e3fb9 100644
--- a/arch/x86/include/asm/pgtable-2level-defs.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -1,7 +1,23 @@
 #ifndef _ASM_X86_PGTABLE_2LEVEL_DEFS_H
 #define _ASM_X86_PGTABLE_2LEVEL_DEFS_H
 
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+typedef unsigned long   pteval_t;
+typedef unsigned long   pmdval_t;
+typedef unsigned long   pudval_t;
+typedef unsigned long   pgdval_t;
+typedef unsigned long   pgprotval_t;
+
+typedef union {
+        pteval_t pte;
+        pteval_t pte_low;
+} pte_t;
+#endif  /* !__ASSEMBLY__ */
+
 #define SHARED_KERNEL_PMD       0
+#define PAGETABLE_LEVELS        2
 
 /*
  * traditional i386 two-level paging structure:
@@ -10,6 +26,7 @@
 #define PGDIR_SHIFT     22
 #define PTRS_PER_PGD    1024
 
+
 /*
  * the i386 is two-level, so we don't really have any
  * PMD directory physically.
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 447da43cddb3..177b0165ea01 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -18,21 +18,6 @@
         printk("%s:%d: bad pgd %p(%016Lx).\n",                          \
                __FILE__, __LINE__, &(e), pgd_val(e))
 
-static inline int pud_none(pud_t pud)
-{
-        return pud_val(pud) == 0;
-}
-
-static inline int pud_bad(pud_t pud)
-{
-        return (pud_val(pud) & ~(PTE_PFN_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
-}
-
-static inline int pud_present(pud_t pud)
-{
-        return pud_val(pud) & _PAGE_PRESENT;
-}
-
 /* Rules for using set_pte: the pte being assigned *must* be
  * either not present or in a state where the hardware will
  * not attempt to update the pte.  In places where this is
@@ -46,23 +31,6 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
         ptep->pte_low = pte.pte_low;
 }
 
-/*
- * Since this is only called on user PTEs, and the page fault handler
- * must handle the already racy situation of simultaneous page faults,
- * we are justified in merely clearing the PTE present bit, followed
- * by a set.  The ordering here is important.
- */
-static inline void native_set_pte_present(struct mm_struct *mm,
-                                          unsigned long addr,
-                                          pte_t *ptep, pte_t pte)
-{
-        ptep->pte_low = 0;
-        smp_wmb();
-        ptep->pte_high = pte.pte_high;
-        smp_wmb();
-        ptep->pte_low = pte.pte_low;
-}
-
 static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
         set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
@@ -120,15 +88,6 @@ static inline void pud_clear(pud_t *pudp)
                 write_cr3(pgd);
 }
 
-#define pud_page(pud) pfn_to_page(pud_val(pud) >> PAGE_SHIFT)
-
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_PFN_MASK))
-
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(pud, address) ((pmd_t *)pud_page_vaddr(*(pud)) +     \
-                                  pmd_index(address))
-
 #ifdef CONFIG_SMP
 static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 {
@@ -145,17 +104,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#define __HAVE_ARCH_PTE_SAME
-static inline int pte_same(pte_t a, pte_t b)
-{
-        return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
-}
-
-static inline int pte_none(pte_t pte)
-{
-        return !pte.pte_low && !pte.pte_high;
-}
-
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.
diff --git a/arch/x86/include/asm/pgtable-3level-defs.h b/arch/x86/include/asm/pgtable-3level_types.h
index 62561367653c..1bd5876c8649 100644
--- a/arch/x86/include/asm/pgtable-3level-defs.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -1,12 +1,31 @@
 #ifndef _ASM_X86_PGTABLE_3LEVEL_DEFS_H
 #define _ASM_X86_PGTABLE_3LEVEL_DEFS_H
 
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+typedef u64     pteval_t;
+typedef u64     pmdval_t;
+typedef u64     pudval_t;
+typedef u64     pgdval_t;
+typedef u64     pgprotval_t;
+
+typedef union {
+        struct {
+                unsigned long pte_low, pte_high;
+        };
+        pteval_t pte;
+} pte_t;
+#endif  /* !__ASSEMBLY__ */
+
 #ifdef CONFIG_PARAVIRT
 #define SHARED_KERNEL_PMD       (pv_info.shared_kernel_pmd)
 #else
 #define SHARED_KERNEL_PMD       1
 #endif
 
+#define PAGETABLE_LEVELS        3
+
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
  */
@@ -25,4 +44,5 @@
  */
 #define PTRS_PER_PTE    512
 
+
 #endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 4f5af8447d54..29d96d168bc0 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1,164 +1,9 @@
 #ifndef _ASM_X86_PGTABLE_H
 #define _ASM_X86_PGTABLE_H
 
-#define FIRST_USER_ADDRESS      0
-
-#define _PAGE_BIT_PRESENT       0       /* is present */
-#define _PAGE_BIT_RW            1       /* writeable */
-#define _PAGE_BIT_USER          2       /* userspace addressable */
-#define _PAGE_BIT_PWT           3       /* page write through */
-#define _PAGE_BIT_PCD           4       /* page cache disabled */
-#define _PAGE_BIT_ACCESSED      5       /* was accessed (raised by CPU) */
-#define _PAGE_BIT_DIRTY         6       /* was written to (raised by CPU) */
-#define _PAGE_BIT_PSE           7       /* 4 MB (or 2MB) page */
-#define _PAGE_BIT_PAT           7       /* on 4KB pages */
-#define _PAGE_BIT_GLOBAL        8       /* Global TLB entry PPro+ */
-#define _PAGE_BIT_UNUSED1       9       /* available for programmer */
-#define _PAGE_BIT_IOMAP         10      /* flag used to indicate IO mapping */
-#define _PAGE_BIT_UNUSED3       11
-#define _PAGE_BIT_PAT_LARGE     12      /* On 2MB or 1GB pages */
-#define _PAGE_BIT_SPECIAL       _PAGE_BIT_UNUSED1
-#define _PAGE_BIT_CPA_TEST      _PAGE_BIT_UNUSED1
-#define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
-
-/* If _PAGE_BIT_PRESENT is clear, we use these: */
-/* - if the user mapped it with PROT_NONE; pte_present gives true */
-#define _PAGE_BIT_PROTNONE      _PAGE_BIT_GLOBAL
-/* - set: nonlinear file mapping, saved PTE; unset:swap */
-#define _PAGE_BIT_FILE          _PAGE_BIT_DIRTY
-
-#define _PAGE_PRESENT   (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
-#define _PAGE_RW        (_AT(pteval_t, 1) << _PAGE_BIT_RW)
-#define _PAGE_USER      (_AT(pteval_t, 1) << _PAGE_BIT_USER)
-#define _PAGE_PWT       (_AT(pteval_t, 1) << _PAGE_BIT_PWT)
-#define _PAGE_PCD       (_AT(pteval_t, 1) << _PAGE_BIT_PCD)
-#define _PAGE_ACCESSED  (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
-#define _PAGE_DIRTY     (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
-#define _PAGE_PSE       (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
-#define _PAGE_GLOBAL    (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
-#define _PAGE_UNUSED1   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
-#define _PAGE_IOMAP     (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
-#define _PAGE_UNUSED3   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
-#define _PAGE_PAT       (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
-#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
-#define _PAGE_SPECIAL   (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
-#define _PAGE_CPA_TEST  (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
-#define __HAVE_ARCH_PTE_SPECIAL
-
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-#define _PAGE_NX        (_AT(pteval_t, 1) << _PAGE_BIT_NX)
-#else
-#define _PAGE_NX        (_AT(pteval_t, 0))
-#endif
+#include <asm/page.h>
 
-#define _PAGE_FILE      (_AT(pteval_t, 1) << _PAGE_BIT_FILE)
-#define _PAGE_PROTNONE  (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
-
-#define _PAGE_TABLE     (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |        \
-                         _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _KERNPG_TABLE   (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |    \
-                         _PAGE_DIRTY)
-
-/* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK  (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |         \
-                         _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
-
-#define _PAGE_CACHE_MASK        (_PAGE_PCD | _PAGE_PWT)
-#define _PAGE_CACHE_WB          (0)
-#define _PAGE_CACHE_WC          (_PAGE_PWT)
-#define _PAGE_CACHE_UC_MINUS    (_PAGE_PCD)
-#define _PAGE_CACHE_UC          (_PAGE_PCD | _PAGE_PWT)
-
-#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_EXEC          __pgprot(_PAGE_PRESENT | _PAGE_USER |   \
-                                         _PAGE_ACCESSED)
-#define PAGE_COPY               PAGE_COPY_NOEXEC
-#define PAGE_READONLY           __pgprot(_PAGE_PRESENT | _PAGE_USER |   \
-                                         _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_READONLY_EXEC      __pgprot(_PAGE_PRESENT | _PAGE_USER |   \
-                                         _PAGE_ACCESSED)
-
-#define __PAGE_KERNEL_EXEC                                              \
-        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
-#define __PAGE_KERNEL           (__PAGE_KERNEL_EXEC | _PAGE_NX)
-
-#define __PAGE_KERNEL_RO                (__PAGE_KERNEL & ~_PAGE_RW)
-#define __PAGE_KERNEL_RX                (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
-#define __PAGE_KERNEL_EXEC_NOCACHE      (__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_WC                (__PAGE_KERNEL | _PAGE_CACHE_WC)
-#define __PAGE_KERNEL_NOCACHE           (__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_UC_MINUS          (__PAGE_KERNEL | _PAGE_PCD)
-#define __PAGE_KERNEL_VSYSCALL          (__PAGE_KERNEL_RX | _PAGE_USER)
-#define __PAGE_KERNEL_VSYSCALL_NOCACHE  (__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_LARGE             (__PAGE_KERNEL | _PAGE_PSE)
-#define __PAGE_KERNEL_LARGE_NOCACHE     (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
-#define __PAGE_KERNEL_LARGE_EXEC        (__PAGE_KERNEL_EXEC | _PAGE_PSE)
-
-#define __PAGE_KERNEL_IO                (__PAGE_KERNEL | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_NOCACHE        (__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_UC_MINUS       (__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_WC             (__PAGE_KERNEL_WC | _PAGE_IOMAP)
-
-#define PAGE_KERNEL                     __pgprot(__PAGE_KERNEL)
-#define PAGE_KERNEL_RO                  __pgprot(__PAGE_KERNEL_RO)
-#define PAGE_KERNEL_EXEC                __pgprot(__PAGE_KERNEL_EXEC)
-#define PAGE_KERNEL_RX                  __pgprot(__PAGE_KERNEL_RX)
-#define PAGE_KERNEL_WC                  __pgprot(__PAGE_KERNEL_WC)
-#define PAGE_KERNEL_NOCACHE             __pgprot(__PAGE_KERNEL_NOCACHE)
-#define PAGE_KERNEL_UC_MINUS            __pgprot(__PAGE_KERNEL_UC_MINUS)
-#define PAGE_KERNEL_EXEC_NOCACHE        __pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
-#define PAGE_KERNEL_LARGE               __pgprot(__PAGE_KERNEL_LARGE)
-#define PAGE_KERNEL_LARGE_NOCACHE       __pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
-#define PAGE_KERNEL_LARGE_EXEC          __pgprot(__PAGE_KERNEL_LARGE_EXEC)
-#define PAGE_KERNEL_VSYSCALL            __pgprot(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_VSYSCALL_NOCACHE    __pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
-
-#define PAGE_KERNEL_IO                  __pgprot(__PAGE_KERNEL_IO)
-#define PAGE_KERNEL_IO_NOCACHE          __pgprot(__PAGE_KERNEL_IO_NOCACHE)
-#define PAGE_KERNEL_IO_UC_MINUS         __pgprot(__PAGE_KERNEL_IO_UC_MINUS)
-#define PAGE_KERNEL_IO_WC               __pgprot(__PAGE_KERNEL_IO_WC)
-
-/*         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
-
-/*
- * early identity mapping  pte attrib macros.
- */
-#ifdef CONFIG_X86_64
-#define __PAGE_KERNEL_IDENT_LARGE_EXEC  __PAGE_KERNEL_LARGE_EXEC
-#else
-/*
- * For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
- * bits are combined, this will alow user to access the high address mapped
- * VDSO in the presence of CONFIG_COMPAT_VDSO
- */
-#define PTE_IDENT_ATTR   0x003          /* PRESENT+RW */
-#define PDE_IDENT_ATTR   0x067          /* PRESENT+RW+USER+DIRTY+ACCESSED */
-#define PGD_IDENT_ATTR   0x001          /* PRESENT (no other attributes) */
-#endif
+#include <asm/pgtable_types.h>
 
 /*
  * Macro to mark a page protection value as UC-
@@ -170,9 +15,6 @@
 
 #ifndef __ASSEMBLY__
 
-#define pgprot_writecombine     pgprot_writecombine
-extern pgprot_t pgprot_writecombine(pgprot_t prot);
-
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -183,6 +25,64 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 extern spinlock_t pgd_lock;
 extern struct list_head pgd_list;
 
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else  /* !CONFIG_PARAVIRT */
+#define set_pte(ptep, pte)              native_set_pte(ptep, pte)
+#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
+
+#define set_pte_atomic(ptep, pte)                                       \
+        native_set_pte_atomic(ptep, pte)
+
+#define set_pmd(pmdp, pmd)              native_set_pmd(pmdp, pmd)
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define set_pgd(pgdp, pgd)              native_set_pgd(pgdp, pgd)
+#define pgd_clear(pgd)                  native_pgd_clear(pgd)
+#endif
+
+#ifndef set_pud
+# define set_pud(pudp, pud)             native_set_pud(pudp, pud)
+#endif
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define pud_clear(pud)                  native_pud_clear(pud)
+#endif
+
+#define pte_clear(mm, addr, ptep)       native_pte_clear(mm, addr, ptep)
+#define pmd_clear(pmd)                  native_pmd_clear(pmd)
+
+#define pte_update(mm, addr, ptep)              do { } while (0)
+#define pte_update_defer(mm, addr, ptep)        do { } while (0)
+
+static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
+{
+        native_pagetable_setup_start(base);
+}
+
+static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
+{
+        native_pagetable_setup_done(base);
+}
+
+#define pgd_val(x)      native_pgd_val(x)
+#define __pgd(x)        native_make_pgd(x)
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define pud_val(x)      native_pud_val(x)
+#define __pud(x)        native_make_pud(x)
+#endif
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define pmd_val(x)      native_pmd_val(x)
+#define __pmd(x)        native_make_pmd(x)
+#endif
+
+#define pte_val(x)      native_pte_val(x)
+#define __pte(x)        native_make_pte(x)
+
+#endif  /* CONFIG_PARAVIRT */
+
 /*
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
@@ -236,72 +136,84 @@ static inline unsigned long pte_pfn(pte_t pte)
 
 static inline int pmd_large(pmd_t pte)
 {
-        return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+        return (pmd_flags(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
                 (_PAGE_PSE | _PAGE_PRESENT);
 }
 
+static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
+{
+        pteval_t v = native_pte_val(pte);
+
+        return native_make_pte(v | set);
+}
+
+static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
+{
+        pteval_t v = native_pte_val(pte);
+
+        return native_make_pte(v & ~clear);
+}
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+        return pte_clear_flags(pte, _PAGE_DIRTY);
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+        return pte_clear_flags(pte, _PAGE_ACCESSED);
 }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~_PAGE_RW);
+        return pte_clear_flags(pte, _PAGE_RW);
 }
 
 static inline pte_t pte_mkexec(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~_PAGE_NX);
+        return pte_clear_flags(pte, _PAGE_NX);
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-        return __pte(pte_val(pte) | _PAGE_DIRTY);
+        return pte_set_flags(pte, _PAGE_DIRTY);
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
 {
-        return __pte(pte_val(pte) | _PAGE_ACCESSED);
+        return pte_set_flags(pte, _PAGE_ACCESSED);
 }
 
 static inline pte_t pte_mkwrite(pte_t pte)
 {
-        return __pte(pte_val(pte) | _PAGE_RW);
+        return pte_set_flags(pte, _PAGE_RW);
 }
 
 static inline pte_t pte_mkhuge(pte_t pte)
 {
-        return __pte(pte_val(pte) | _PAGE_PSE);
+        return pte_set_flags(pte, _PAGE_PSE);
 }
 
 static inline pte_t pte_clrhuge(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~_PAGE_PSE);
+        return pte_clear_flags(pte, _PAGE_PSE);
 }
 
 static inline pte_t pte_mkglobal(pte_t pte)
 {
-        return __pte(pte_val(pte) | _PAGE_GLOBAL);
+        return pte_set_flags(pte, _PAGE_GLOBAL);
 }
 
 static inline pte_t pte_clrglobal(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
+        return pte_clear_flags(pte, _PAGE_GLOBAL);
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
 {
-        return __pte(pte_val(pte) | _PAGE_SPECIAL);
+        return pte_set_flags(pte, _PAGE_SPECIAL);
 }
 
-extern pteval_t __supported_pte_mask;
-
 /*
  * Mask out unsupported bits in a present pgprot.  Non-present pgprots
  * can use those bits for other purposes, so leave them be.
@@ -374,82 +286,197 @@ static inline int is_new_memtype_allowed(unsigned long flags,
         return 1;
 }
 
-#ifndef __ASSEMBLY__
-/* Indicate that x86 has its own track and untrack pfn vma functions */
-#define __HAVE_PFNMAP_TRACKING
-
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-struct file;
-pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-                              unsigned long size, pgprot_t vma_prot);
-int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
-                              unsigned long size, pgprot_t *vma_prot);
-#endif
-
-/* Install a pte for a particular vaddr in kernel space. */
-void set_pte_vaddr(unsigned long vaddr, pte_t pte);
+pmd_t *populate_extra_pmd(unsigned long vaddr);
+pte_t *populate_extra_pte(unsigned long vaddr);
+#endif  /* __ASSEMBLY__ */
 
 #ifdef CONFIG_X86_32
-extern void native_pagetable_setup_start(pgd_t *base);
-extern void native_pagetable_setup_done(pgd_t *base);
+# include "pgtable_32.h"
 #else
-static inline void native_pagetable_setup_start(pgd_t *base) {}
-static inline void native_pagetable_setup_done(pgd_t *base) {}
+# include "pgtable_64.h"
 #endif
 
-struct seq_file;
-extern void arch_report_meminfo(struct seq_file *m);
+#ifndef __ASSEMBLY__
+#include <linux/mm_types.h>
 
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else  /* !CONFIG_PARAVIRT */
-#define set_pte(ptep, pte)              native_set_pte(ptep, pte)
-#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
+static inline int pte_none(pte_t pte)
+{
+        return !pte.pte;
+}
 
-#define set_pte_present(mm, addr, ptep, pte)                            \
-        native_set_pte_present(mm, addr, ptep, pte)
-#define set_pte_atomic(ptep, pte)                                       \
-        native_set_pte_atomic(ptep, pte)
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t a, pte_t b)
+{
+        return a.pte == b.pte;
+}
 
-#define set_pmd(pmdp, pmd)              native_set_pmd(pmdp, pmd)
+static inline int pte_present(pte_t a)
+{
+        return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
+}
 
-#ifndef __PAGETABLE_PUD_FOLDED
-#define set_pgd(pgdp, pgd)              native_set_pgd(pgdp, pgd)
-#define pgd_clear(pgd)                  native_pgd_clear(pgd)
-#endif
+static inline int pmd_present(pmd_t pmd)
+{
+        return pmd_flags(pmd) & _PAGE_PRESENT;
+}
 
-#ifndef set_pud
-# define set_pud(pudp, pud)             native_set_pud(pudp, pud)
-#endif
+static inline int pmd_none(pmd_t pmd)
+{
+        /* Only check low word on 32-bit platforms, since it might be
+           out of sync with upper half. */
+        return (unsigned long)native_pmd_val(pmd) == 0;
+}
 
-#ifndef __PAGETABLE_PMD_FOLDED
-#define pud_clear(pud)                  native_pud_clear(pud)
-#endif
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+        return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK);
+}
 
-#define pte_clear(mm, addr, ptep)       native_pte_clear(mm, addr, ptep)
-#define pmd_clear(pmd)                  native_pmd_clear(pmd)
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pmd_page(pmd)   pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
 
-#define pte_update(mm, addr, ptep)              do { } while (0)
-#define pte_update_defer(mm, addr, ptep)        do { } while (0)
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+static inline unsigned pmd_index(unsigned long address)
+{
+        return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
+}
 
-static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * (Currently stuck as a macro because of indirect forward reference
+ * to linux/mm.h:page_to_nid())
+ */
+#define mk_pte(page, pgprot)   pfn_pte(page_to_pfn(page), (pgprot))
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this function returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+static inline unsigned pte_index(unsigned long address)
 {
-        native_pagetable_setup_start(base);
+        return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
 }
 
-static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
 {
-        native_pagetable_setup_done(base);
+        return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
 }
-#endif  /* CONFIG_PARAVIRT */
 
-#endif  /* __ASSEMBLY__ */
+static inline int pmd_bad(pmd_t pmd)
+{
+        return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
+}
 
-#ifdef CONFIG_X86_32
-# include "pgtable_32.h"
+static inline unsigned long pages_to_mb(unsigned long npg)
+{
+        return npg >> (20 - PAGE_SHIFT);
+}
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
+        remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#if PAGETABLE_LEVELS > 2
+static inline int pud_none(pud_t pud)
+{
+        return native_pud_val(pud) == 0;
+}
+
+static inline int pud_present(pud_t pud)
+{
+        return pud_flags(pud) & _PAGE_PRESENT;
+}
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+        return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK);
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pud_page(pud)           pfn_to_page(pud_val(pud) >> PAGE_SHIFT)
+
+/* Find an entry in the second-level page table.. */
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+{
+        return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
+}
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+        return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
+static inline int pud_large(pud_t pud)
+{
+        return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+                (_PAGE_PSE | _PAGE_PRESENT);
+}
+
+static inline int pud_bad(pud_t pud)
+{
+        return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+}
 #else
-# include "pgtable_64.h"
-#endif
+static inline int pud_large(pud_t pud)
+{
+        return 0;
+}
+#endif  /* PAGETABLE_LEVELS > 2 */
+
+#if PAGETABLE_LEVELS > 3
+static inline int pgd_present(pgd_t pgd)
+{
+        return pgd_flags(pgd) & _PAGE_PRESENT;
+}
+
+static inline unsigned long pgd_page_vaddr(pgd_t pgd)
+{
+        return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK);
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pgd_page(pgd)           pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)
+
+/* to find an entry in a page-table-directory. */
+static inline unsigned pud_index(unsigned long address)
+{
+        return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
+}
+
+static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+{
+        return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
+}
+
+static inline int pgd_bad(pgd_t pgd)
+{
+        return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+}
+
+static inline int pgd_none(pgd_t pgd)
+{
+        return !native_pgd_val(pgd);
+}
+#endif  /* PAGETABLE_LEVELS > 3 */
+
+#endif  /* __ASSEMBLY__ */
 
 /*
  * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
@@ -476,28 +503,6 @@ static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
 
 #ifndef __ASSEMBLY__
 
-enum {
-        PG_LEVEL_NONE,
-        PG_LEVEL_4K,
-        PG_LEVEL_2M,
-        PG_LEVEL_1G,
-        PG_LEVEL_NUM
-};
-
-#ifdef CONFIG_PROC_FS
-extern void update_page_count(int level, unsigned long pages);
-#else
-static inline void update_page_count(int level, unsigned long pages) { }
-#endif
-
-/*
- * Helper function that returns the kernel pagetable entry controlling
- * the virtual address 'address'. NULL means no pagetable entry present.
- * NOTE: the return type is pte_t but if the pmd is PSE then we return it
- * as a pte too.
- */
-extern pte_t *lookup_address(unsigned long address, unsigned int *level);
-
 /* local pte updates need not use xchg for locking */
 static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
 {
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 72b020deb46b..31bd120cf2a2 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_PGTABLE_32_H
 #define _ASM_X86_PGTABLE_32_H
 
+#include <asm/pgtable_32_types.h>
 
 /*
  * The Linux memory management assumes a three-level page table setup. On
@@ -33,47 +34,6 @@ void paging_init(void);
 
 extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
 
-/*
- * The Linux x86 paging architecture is 'compile-time dual-mode', it
- * implements both the traditional 2-level x86 page tables and the
- * newer 3-level PAE-mode page tables.
- */
-#ifdef CONFIG_X86_PAE
-# include <asm/pgtable-3level-defs.h>
-# define PMD_SIZE       (1UL << PMD_SHIFT)
-# define PMD_MASK       (~(PMD_SIZE - 1))
-#else
-# include <asm/pgtable-2level-defs.h>
-#endif
-
-#define PGDIR_SIZE      (1UL << PGDIR_SHIFT)
-#define PGDIR_MASK      (~(PGDIR_SIZE - 1))
-
-/* Just any arbitrary offset to the start of the vmalloc VM area: the
- * current 8MB value just means that there will be a 8MB "hole" after the
- * physical memory until the kernel virtual memory starts.  That means that
- * any out-of-bounds memory accesses will hopefully be caught.
- * The vmalloc() routines leaves a hole of 4kB between each vmalloced
- * area for the same reason. ;)
- */
-#define VMALLOC_OFFSET  (8 * 1024 * 1024)
-#define VMALLOC_START   ((unsigned long)high_memory + VMALLOC_OFFSET)
-#ifdef CONFIG_X86_PAE
-#define LAST_PKMAP 512
-#else
-#define LAST_PKMAP 1024
-#endif
-
-#define PKMAP_BASE ((FIXADDR_BOOT_START - PAGE_SIZE * (LAST_PKMAP + 1)) \
-                    & PMD_MASK)
-
-#ifdef CONFIG_HIGHMEM
-# define VMALLOC_END    (PKMAP_BASE - 2 * PAGE_SIZE)
-#else
-# define VMALLOC_END    (FIXADDR_START - 2 * PAGE_SIZE)
-#endif
-
-#define MAXMEM  (VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
 
 /*
  * Define this if things work differently on an i386 and an i486:
@@ -82,58 +42,12 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
  */
 #undef TEST_ACCESS_OK
 
-/* The boot page tables (all created as a single array) */
-extern unsigned long pg0[];
-
-#define pte_present(x)  ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
-#define pmd_none(x)     (!(unsigned long)pmd_val((x)))
-#define pmd_present(x)  (pmd_val((x)) & _PAGE_PRESENT)
-#define pmd_bad(x) ((pmd_val(x) & (PTE_FLAGS_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
-
-#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
-
 #ifdef CONFIG_X86_PAE
 # include <asm/pgtable-3level.h>
 #else
 # include <asm/pgtable-2level.h>
 #endif
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot)    pfn_pte(page_to_pfn(page), (pgprot))
-
-
-static inline int pud_large(pud_t pud) { return 0; }
-
-/*
- * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
- *
- * this macro returns the index of the entry in the pmd page which would
- * control the given virtual address
- */
-#define pmd_index(address)                              \
-        (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-
-/*
- * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
- *
- * this macro returns the index of the entry in the pte page which would
- * control the given virtual address
- */
-#define pte_index(address)                                      \
-        (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address)                         \
-        ((pte_t *)pmd_page_vaddr(*(dir)) +  pte_index((address)))
-
-#define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
-
-#define pmd_page_vaddr(pmd)                                     \
-        ((unsigned long)__va(pmd_val((pmd)) & PTE_PFN_MASK))
-
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address)                                    \
         ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE0) +          \
@@ -176,7 +90,4 @@ do {						\
 #define kern_addr_valid(kaddr)  (0)
 #endif
 
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
-        remap_pfn_range(vma, vaddr, pfn, size, prot)
-
 #endif /* _ASM_X86_PGTABLE_32_H */
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
new file mode 100644
index 000000000000..2733fad45f98
--- /dev/null
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -0,0 +1,51 @@
+#ifndef _ASM_X86_PGTABLE_32_DEFS_H
+#define _ASM_X86_PGTABLE_32_DEFS_H
+
+/*
+ * The Linux x86 paging architecture is 'compile-time dual-mode', it
+ * implements both the traditional 2-level x86 page tables and the
+ * newer 3-level PAE-mode page tables.
+ */
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level_types.h>
+# define PMD_SIZE       (1UL << PMD_SHIFT)
+# define PMD_MASK       (~(PMD_SIZE - 1))
+#else
+# include <asm/pgtable-2level_types.h>
+#endif
+
+#define PGDIR_SIZE      (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK      (~(PGDIR_SIZE - 1))
+
+/* Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 8MB value just means that there will be a 8MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ */
+#define VMALLOC_OFFSET  (8 * 1024 * 1024)
+
+#ifndef __ASSEMBLER__
+extern bool __vmalloc_start_set; /* set once high_memory is set */
+#endif
+
+#define VMALLOC_START   ((unsigned long)high_memory + VMALLOC_OFFSET)
+#ifdef CONFIG_X86_PAE
+#define LAST_PKMAP 512
+#else
+#define LAST_PKMAP 1024
+#endif
+
+#define PKMAP_BASE ((FIXADDR_BOOT_START - PAGE_SIZE * (LAST_PKMAP + 1)) \
+                    & PMD_MASK)
+
+#ifdef CONFIG_HIGHMEM
+# define VMALLOC_END    (PKMAP_BASE - 2 * PAGE_SIZE)
+#else
+# define VMALLOC_END    (FIXADDR_START - 2 * PAGE_SIZE)
+#endif
+
+#define MAXMEM  (VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
+
+#endif /* _ASM_X86_PGTABLE_32_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index ba09289accaa..6b87bc6d5018 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -2,6 +2,8 @@
 #define _ASM_X86_PGTABLE_64_H
 
 #include <linux/const.h>
+#include <asm/pgtable_64_types.h>
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -11,7 +13,6 @@
 #include <asm/processor.h>
 #include <linux/bitops.h>
 #include <linux/threads.h>
-#include <asm/pda.h>
 
 extern pud_t level3_kernel_pgt[512];
 extern pud_t level3_ident_pgt[512];
@@ -26,32 +27,6 @@ extern void paging_init(void);
 
 #endif /* !__ASSEMBLY__ */
 
-#define SHARED_KERNEL_PMD       0
-
-/*
- * PGDIR_SHIFT determines what a top-level page table entry can map
- */
-#define PGDIR_SHIFT     39
-#define PTRS_PER_PGD    512
-
-/*
- * 3rd level page
- */
-#define PUD_SHIFT       30
-#define PTRS_PER_PUD    512
-
-/*
- * PMD_SHIFT determines the size of the area a middle-level
- * page table can map
- */
-#define PMD_SHIFT       21
-#define PTRS_PER_PMD    512
-
-/*
- * entries per page directory level
- */
-#define PTRS_PER_PTE    512
-
 #ifndef __ASSEMBLY__
 
 #define pte_ERROR(e)                                    \
@@ -67,9 +42,6 @@ extern void paging_init(void);
         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))
-
 struct mm_struct;
 
 void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
@@ -134,48 +106,6 @@ static inline void native_pgd_clear(pgd_t *pgd)
         native_set_pgd(pgd, native_make_pgd(0));
 }
 
-#define pte_same(a, b)          ((a).pte == (b).pte)
-
-#endif /* !__ASSEMBLY__ */
-
-#define PMD_SIZE        (_AC(1, UL) << PMD_SHIFT)
-#define PMD_MASK        (~(PMD_SIZE - 1))
-#define PUD_SIZE        (_AC(1, UL) << PUD_SHIFT)
-#define PUD_MASK        (~(PUD_SIZE - 1))
-#define PGDIR_SIZE      (_AC(1, UL) << PGDIR_SHIFT)
-#define PGDIR_MASK      (~(PGDIR_SIZE - 1))
-
-
-#define MAXMEM           _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
-#define VMALLOC_START    _AC(0xffffc20000000000, UL)
-#define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
-#define VMEMMAP_START    _AC(0xffffe20000000000, UL)
-#define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
-#define MODULES_END      _AC(0xffffffffff000000, UL)
-#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
-
-#ifndef __ASSEMBLY__
-
-static inline int pgd_bad(pgd_t pgd)
-{
-        return (pgd_val(pgd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-static inline int pud_bad(pud_t pud)
-{
-        return (pud_val(pud) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-static inline int pmd_bad(pmd_t pmd)
-{
-        return (pmd_val(pmd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-#define pte_none(x)     (!pte_val((x)))
-#define pte_present(x)  (pte_val((x)) & (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-#define pages_to_mb(x)  ((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
-
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
@@ -184,41 +114,12 @@ static inline int pmd_bad(pmd_t pmd)
 /*
  * Level 4 access.
  */
-#define pgd_page_vaddr(pgd)                                             \
-        ((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_PFN_MASK))
-#define pgd_page(pgd)           (pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT))
-#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
 static inline int pgd_large(pgd_t pgd) { return 0; }
 #define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
 
 /* PUD - Level3 access */
-/* to find an entry in a page-table-directory. */
-#define pud_page_vaddr(pud)                                             \
-        ((unsigned long)__va(pud_val((pud)) & PHYSICAL_PAGE_MASK))
-#define pud_page(pud)   (pfn_to_page(pud_val((pud)) >> PAGE_SHIFT))
-#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
-#define pud_offset(pgd, address)                                        \
-        ((pud_t *)pgd_page_vaddr(*(pgd)) + pud_index((address)))
-#define pud_present(pud) (pud_val((pud)) & _PAGE_PRESENT)
-
-static inline int pud_large(pud_t pte)
-{
-        return (pud_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
-                (_PAGE_PSE | _PAGE_PRESENT);
-}
 
 /* PMD  - Level 2 access */
-#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_PFN_MASK))
-#define pmd_page(pmd)           (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
-
-#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-#define pmd_offset(dir, address) ((pmd_t *)pud_page_vaddr(*(dir)) + \
-                                  pmd_index(address))
-#define pmd_none(x)     (!pmd_val((x)))
-#define pmd_present(x)  (pmd_val((x)) & _PAGE_PRESENT)
-#define pfn_pmd(nr, prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val((prot))))
-#define pmd_pfn(x)  ((pmd_val((x)) & __PHYSICAL_MASK) >> PAGE_SHIFT)
-
 #define pte_to_pgoff(pte) ((pte_val((pte)) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
 #define pgoff_to_pte(off) ((pte_t) { .pte = ((off) << PAGE_SHIFT) |     \
                                             _PAGE_FILE })
@@ -226,13 +127,6 @@ static inline int pud_large(pud_t pte)
 
 /* PTE - Level 1 access. */
 
-/* page, protection -> pte */
-#define mk_pte(page, pgprot)    pfn_pte(page_to_pfn((page)), (pgprot))
-
-#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
-                                         pte_index((address)))
-
 /* x86-64 always has all page tables mapped. */
 #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
 #define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address))
@@ -266,9 +160,6 @@ extern int direct_gbpages;
 extern int kern_addr_valid(unsigned long addr);
 extern void cleanup_highmap(void);
 
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
-        remap_pfn_range(vma, vaddr, pfn, size, prot)
-
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
new file mode 100644
index 000000000000..fbf42b8e0383
--- /dev/null
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -0,0 +1,63 @@
+#ifndef _ASM_X86_PGTABLE_64_DEFS_H
+#define _ASM_X86_PGTABLE_64_DEFS_H
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef unsigned long   pteval_t;
+typedef unsigned long   pmdval_t;
+typedef unsigned long   pudval_t;
+typedef unsigned long   pgdval_t;
+typedef unsigned long   pgprotval_t;
+
+typedef struct { pteval_t pte; } pte_t;
+
+#endif  /* !__ASSEMBLY__ */
+
+#define SHARED_KERNEL_PMD       0
+#define PAGETABLE_LEVELS        4
+
+/*
+ * 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 PMD_SIZE        (_AC(1, UL) << PMD_SHIFT)
+#define PMD_MASK        (~(PMD_SIZE - 1))
+#define PUD_SIZE        (_AC(1, UL) << PUD_SHIFT)
+#define PUD_MASK        (~(PUD_SIZE - 1))
+#define PGDIR_SIZE      (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK      (~(PGDIR_SIZE - 1))
+
+
+#define MAXMEM           _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#define VMALLOC_START    _AC(0xffffc20000000000, UL)
+#define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
+#define VMEMMAP_START    _AC(0xffffe20000000000, UL)
+#define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
+#define MODULES_END      _AC(0xffffffffff000000, UL)
+#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+
+#endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
new file mode 100644
index 000000000000..b8238dc8786d
--- /dev/null
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -0,0 +1,329 @@
+#ifndef _ASM_X86_PGTABLE_DEFS_H
+#define _ASM_X86_PGTABLE_DEFS_H
+
+#include <linux/const.h>
+#include <asm/page_types.h>
+
+#define FIRST_USER_ADDRESS      0
+
+#define _PAGE_BIT_PRESENT       0       /* is present */
+#define _PAGE_BIT_RW            1       /* writeable */
+#define _PAGE_BIT_USER          2       /* userspace addressable */
+#define _PAGE_BIT_PWT           3       /* page write through */
+#define _PAGE_BIT_PCD           4       /* page cache disabled */
+#define _PAGE_BIT_ACCESSED      5       /* was accessed (raised by CPU) */
+#define _PAGE_BIT_DIRTY         6       /* was written to (raised by CPU) */
+#define _PAGE_BIT_PSE           7       /* 4 MB (or 2MB) page */
+#define _PAGE_BIT_PAT           7       /* on 4KB pages */
+#define _PAGE_BIT_GLOBAL        8       /* Global TLB entry PPro+ */
+#define _PAGE_BIT_UNUSED1       9       /* available for programmer */
+#define _PAGE_BIT_IOMAP         10      /* flag used to indicate IO mapping */
+#define _PAGE_BIT_UNUSED3       11
+#define _PAGE_BIT_PAT_LARGE     12      /* On 2MB or 1GB pages */
+#define _PAGE_BIT_SPECIAL       _PAGE_BIT_UNUSED1
+#define _PAGE_BIT_CPA_TEST      _PAGE_BIT_UNUSED1
+#define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
+
+/* If _PAGE_BIT_PRESENT is clear, we use these: */
+/* - if the user mapped it with PROT_NONE; pte_present gives true */
+#define _PAGE_BIT_PROTNONE      _PAGE_BIT_GLOBAL
+/* - set: nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_BIT_FILE          _PAGE_BIT_DIRTY
+
+#define _PAGE_PRESENT   (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
+#define _PAGE_RW        (_AT(pteval_t, 1) << _PAGE_BIT_RW)
+#define _PAGE_USER      (_AT(pteval_t, 1) << _PAGE_BIT_USER)
+#define _PAGE_PWT       (_AT(pteval_t, 1) << _PAGE_BIT_PWT)
+#define _PAGE_PCD       (_AT(pteval_t, 1) << _PAGE_BIT_PCD)
+#define _PAGE_ACCESSED  (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
+#define _PAGE_DIRTY     (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
+#define _PAGE_PSE       (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
+#define _PAGE_GLOBAL    (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
+#define _PAGE_UNUSED1   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
+#define _PAGE_IOMAP     (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
+#define _PAGE_UNUSED3   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
+#define _PAGE_PAT       (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
+#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
+#define _PAGE_SPECIAL   (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
+#define _PAGE_CPA_TEST  (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define __HAVE_ARCH_PTE_SPECIAL
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+#define _PAGE_NX        (_AT(pteval_t, 1) << _PAGE_BIT_NX)
+#else
+#define _PAGE_NX        (_AT(pteval_t, 0))
+#endif
+
+#define _PAGE_FILE      (_AT(pteval_t, 1) << _PAGE_BIT_FILE)
+#define _PAGE_PROTNONE  (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
+
+#define _PAGE_TABLE     (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |        \
+                         _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE   (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |    \
+                         _PAGE_DIRTY)
+
+/* Set of bits not changed in pte_modify */
+#define _PAGE_CHG_MASK  (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |         \
+                         _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define _PAGE_CACHE_MASK        (_PAGE_PCD | _PAGE_PWT)
+#define _PAGE_CACHE_WB          (0)
+#define _PAGE_CACHE_WC          (_PAGE_PWT)
+#define _PAGE_CACHE_UC_MINUS    (_PAGE_PCD)
+#define _PAGE_CACHE_UC          (_PAGE_PCD | _PAGE_PWT)
+
+#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_EXEC          __pgprot(_PAGE_PRESENT | _PAGE_USER |   \
+                                         _PAGE_ACCESSED)
+#define PAGE_COPY               PAGE_COPY_NOEXEC
+#define PAGE_READONLY           __pgprot(_PAGE_PRESENT | _PAGE_USER |   \
+                                         _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_READONLY_EXEC      __pgprot(_PAGE_PRESENT | _PAGE_USER |   \
+                                         _PAGE_ACCESSED)
+
+#define __PAGE_KERNEL_EXEC                                              \
+        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
+#define __PAGE_KERNEL           (__PAGE_KERNEL_EXEC | _PAGE_NX)
+
+#define __PAGE_KERNEL_RO                (__PAGE_KERNEL & ~_PAGE_RW)
+#define __PAGE_KERNEL_RX                (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
+#define __PAGE_KERNEL_EXEC_NOCACHE      (__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_WC                (__PAGE_KERNEL | _PAGE_CACHE_WC)
+#define __PAGE_KERNEL_NOCACHE           (__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_UC_MINUS          (__PAGE_KERNEL | _PAGE_PCD)
+#define __PAGE_KERNEL_VSYSCALL          (__PAGE_KERNEL_RX | _PAGE_USER)
+#define __PAGE_KERNEL_VSYSCALL_NOCACHE  (__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_LARGE             (__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_NOCACHE     (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_EXEC        (__PAGE_KERNEL_EXEC | _PAGE_PSE)
+
+#define __PAGE_KERNEL_IO                (__PAGE_KERNEL | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_NOCACHE        (__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_UC_MINUS       (__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_WC             (__PAGE_KERNEL_WC | _PAGE_IOMAP)
+
+#define PAGE_KERNEL                     __pgprot(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO                  __pgprot(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_EXEC                __pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RX                  __pgprot(__PAGE_KERNEL_RX)
+#define PAGE_KERNEL_WC                  __pgprot(__PAGE_KERNEL_WC)
+#define PAGE_KERNEL_NOCACHE             __pgprot(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_UC_MINUS            __pgprot(__PAGE_KERNEL_UC_MINUS)
+#define PAGE_KERNEL_EXEC_NOCACHE        __pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
+#define PAGE_KERNEL_LARGE               __pgprot(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_LARGE_NOCACHE       __pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
+#define PAGE_KERNEL_LARGE_EXEC          __pgprot(__PAGE_KERNEL_LARGE_EXEC)
+#define PAGE_KERNEL_VSYSCALL            __pgprot(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_VSYSCALL_NOCACHE    __pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+
+#define PAGE_KERNEL_IO                  __pgprot(__PAGE_KERNEL_IO)
+#define PAGE_KERNEL_IO_NOCACHE          __pgprot(__PAGE_KERNEL_IO_NOCACHE)
+#define PAGE_KERNEL_IO_UC_MINUS         __pgprot(__PAGE_KERNEL_IO_UC_MINUS)
+#define PAGE_KERNEL_IO_WC               __pgprot(__PAGE_KERNEL_IO_WC)
+
+/*         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
+
+/*
+ * early identity mapping  pte attrib macros.
+ */
+#ifdef CONFIG_X86_64
+#define __PAGE_KERNEL_IDENT_LARGE_EXEC  __PAGE_KERNEL_LARGE_EXEC
+#else
+/*
+ * For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
+ * bits are combined, this will alow user to access the high address mapped
+ * VDSO in the presence of CONFIG_COMPAT_VDSO
+ */
+#define PTE_IDENT_ATTR   0x003          /* PRESENT+RW */
+#define PDE_IDENT_ATTR   0x067          /* PRESENT+RW+USER+DIRTY+ACCESSED */
+#define PGD_IDENT_ATTR   0x001          /* PRESENT (no other attributes) */
+#endif
+
+#ifdef CONFIG_X86_32
+# include "pgtable_32_types.h"
+#else
+# include "pgtable_64_types.h"
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
+#define PTE_PFN_MASK            ((pteval_t)PHYSICAL_PAGE_MASK)
+
+/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
+#define PTE_FLAGS_MASK          (~PTE_PFN_MASK)
+
+typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
+
+typedef struct { pgdval_t pgd; } pgd_t;
+
+static inline pgd_t native_make_pgd(pgdval_t val)
+{
+        return (pgd_t) { val };
+}
+
+static inline pgdval_t native_pgd_val(pgd_t pgd)
+{
+        return pgd.pgd;
+}
+
+static inline pgdval_t pgd_flags(pgd_t pgd)
+{
+        return native_pgd_val(pgd) & PTE_FLAGS_MASK;
+}
+
+#if PAGETABLE_LEVELS > 3
+typedef struct { pudval_t pud; } pud_t;
+
+static inline pud_t native_make_pud(pmdval_t val)
+{
+        return (pud_t) { val };
+}
+
+static inline pudval_t native_pud_val(pud_t pud)
+{
+        return pud.pud;
+}
+#else
+#include <asm-generic/pgtable-nopud.h>
+
+static inline pudval_t native_pud_val(pud_t pud)
+{
+        return native_pgd_val(pud.pgd);
+}
+#endif
+
+#if PAGETABLE_LEVELS > 2
+typedef struct { pmdval_t pmd; } pmd_t;
+
+static inline pmd_t native_make_pmd(pmdval_t val)
+{
+        return (pmd_t) { val };
+}
+
+static inline pmdval_t native_pmd_val(pmd_t pmd)
+{
+        return pmd.pmd;
+}
+#else
+#include <asm-generic/pgtable-nopmd.h>
+
+static inline pmdval_t native_pmd_val(pmd_t pmd)
+{
+        return native_pgd_val(pmd.pud.pgd);
+}
+#endif
+
+static inline pudval_t pud_flags(pud_t pud)
+{
+        return native_pud_val(pud) & PTE_FLAGS_MASK;
+}
+
+static inline pmdval_t pmd_flags(pmd_t pmd)
+{
+        return native_pmd_val(pmd) & PTE_FLAGS_MASK;
+}
+
+static inline pte_t native_make_pte(pteval_t val)
+{
+        return (pte_t) { .pte = val };
+}
+
+static inline pteval_t native_pte_val(pte_t pte)
+{
+        return pte.pte;
+}
+
+static inline pteval_t pte_flags(pte_t pte)
+{
+        return native_pte_val(pte) & PTE_FLAGS_MASK;
+}
+
+#define pgprot_val(x)   ((x).pgprot)
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+
+typedef struct page *pgtable_t;
+
+extern pteval_t __supported_pte_mask;
+extern int nx_enabled;
+extern void set_nx(void);
+
+#define pgprot_writecombine     pgprot_writecombine
+extern pgprot_t pgprot_writecombine(pgprot_t prot);
+
+/* Indicate that x86 has its own track and untrack pfn vma functions */
+#define __HAVE_PFNMAP_TRACKING
+
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+                              unsigned long size, pgprot_t vma_prot);
+int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
+                              unsigned long size, pgprot_t *vma_prot);
+
+/* Install a pte for a particular vaddr in kernel space. */
+void set_pte_vaddr(unsigned long vaddr, pte_t pte);
+
+#ifdef CONFIG_X86_32
+extern void native_pagetable_setup_start(pgd_t *base);
+extern void native_pagetable_setup_done(pgd_t *base);
+#else
+static inline void native_pagetable_setup_start(pgd_t *base) {}
+static inline void native_pagetable_setup_done(pgd_t *base) {}
+#endif
+
+struct seq_file;
+extern void arch_report_meminfo(struct seq_file *m);
+
+enum {
+        PG_LEVEL_NONE,
+        PG_LEVEL_4K,
+        PG_LEVEL_2M,
+        PG_LEVEL_1G,
+        PG_LEVEL_NUM
+};
+
+#ifdef CONFIG_PROC_FS
+extern void update_page_count(int level, unsigned long pages);
+#else
+static inline void update_page_count(int level, unsigned long pages) { }
+#endif
+
+/*
+ * Helper function that returns the kernel pagetable entry controlling
+ * the virtual address 'address'. NULL means no pagetable entry present.
+ * NOTE: the return type is pte_t but if the pmd is PSE then we return it
+ * as a pte too.
+ */
+extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+
+#endif  /* !__ASSEMBLY__ */
+
+#endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/include/asm/prctl.h b/arch/x86/include/asm/prctl.h
index a8894647dd9a..3ac5032fae09 100644
--- a/arch/x86/include/asm/prctl.h
+++ b/arch/x86/include/asm/prctl.h
@@ -6,8 +6,4 @@
 #define ARCH_GET_FS 0x1003
 #define ARCH_GET_GS 0x1004
 
-#ifdef CONFIG_X86_64
-extern long sys_arch_prctl(int, unsigned long);
-#endif /* CONFIG_X86_64 */
-
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3bfd5235a9eb..ae85a8d66a30 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -16,6 +16,7 @@ struct mm_struct;
 #include <asm/cpufeature.h>
 #include <asm/system.h>
 #include <asm/page.h>
+#include <asm/pgtable_types.h>
 #include <asm/percpu.h>
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
@@ -73,10 +74,10 @@ struct cpuinfo_x86 {
         char                    pad0;
 #else
         /* Number of 4K pages in DTLB/ITLB combined(in pages): */
-        int                      x86_tlbsize;
+        int                     x86_tlbsize;
+#endif
         __u8                    x86_virt_bits;
         __u8                    x86_phys_bits;
-#endif
         /* CPUID returned core id bits: */
         __u8                    x86_coreid_bits;
         /* Max extended CPUID function supported: */
@@ -247,7 +248,6 @@ struct x86_hw_tss {
 #define IO_BITMAP_LONGS                 (IO_BITMAP_BYTES/sizeof(long))
 #define IO_BITMAP_OFFSET                offsetof(struct tss_struct, io_bitmap)
 #define INVALID_IO_BITMAP_OFFSET        0x8000
-#define INVALID_IO_BITMAP_OFFSET_LAZY   0x9000
 
 struct tss_struct {
         /*
@@ -262,11 +262,6 @@ struct tss_struct {
          * be within the limit.
          */
         unsigned long           io_bitmap[IO_BITMAP_LONGS + 1];
-        /*
-         * Cache the current maximum and the last task that used the bitmap:
-         */
-        unsigned long           io_bitmap_max;
-        struct thread_struct    *io_bitmap_owner;
 
         /*
          * .. and then another 0x100 bytes for the emergency kernel stack:
@@ -378,9 +373,33 @@ union thread_xstate {
 
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(struct orig_ist, orig_ist);
+
+union irq_stack_union {
+        char irq_stack[IRQ_STACK_SIZE];
+        /*
+         * GCC hardcodes the stack canary as %gs:40.  Since the
+         * irq_stack is the object at %gs:0, we reserve the bottom
+         * 48 bytes of the irq stack for the canary.
+         */
+        struct {
+                char gs_base[40];
+                unsigned long stack_canary;
+        };
+};
+
+DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
+DECLARE_INIT_PER_CPU(irq_stack_union);
+
+DECLARE_PER_CPU(char *, irq_stack_ptr);
+DECLARE_PER_CPU(unsigned int, irq_count);
+extern unsigned long kernel_eflags;
+extern asmlinkage void ignore_sysret(void);
+#else   /* X86_64 */
+#ifdef CONFIG_CC_STACKPROTECTOR
+DECLARE_PER_CPU(unsigned long, stack_canary);
 #endif
+#endif  /* X86_64 */
 
-extern void print_cpu_info(struct cpuinfo_x86 *);
 extern unsigned int xstate_size;
 extern void free_thread_xstate(struct task_struct *);
 extern struct kmem_cache *task_xstate_cachep;
@@ -752,9 +771,9 @@ extern int sysenter_setup(void);
 extern struct desc_ptr          early_gdt_descr;
 
 extern void cpu_set_gdt(int);
-extern void switch_to_new_gdt(void);
+extern void switch_to_new_gdt(int);
+extern void load_percpu_segment(int);
 extern void cpu_init(void);
-extern void init_gdt(int cpu);
 
 static inline unsigned long get_debugctlmsr(void)
 {
@@ -839,6 +858,7 @@ static inline void spin_lock_prefetch(const void *x)
  * User space process size: 3GB (default).
  */
 #define TASK_SIZE               PAGE_OFFSET
+#define TASK_SIZE_MAX           TASK_SIZE
 #define STACK_TOP               TASK_SIZE
 #define STACK_TOP_MAX           STACK_TOP
 
@@ -898,7 +918,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 /*
  * User space process size. 47bits minus one guard page.
  */
-#define TASK_SIZE64     ((1UL << 47) - PAGE_SIZE)
+#define TASK_SIZE_MAX   ((1UL << 47) - PAGE_SIZE)
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
@@ -907,12 +927,12 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
                                         0xc0000000 : 0xFFFFe000)
 
 #define TASK_SIZE               (test_thread_flag(TIF_IA32) ? \
-                                        IA32_PAGE_OFFSET : TASK_SIZE64)
+                                        IA32_PAGE_OFFSET : TASK_SIZE_MAX)
 #define TASK_SIZE_OF(child)     ((test_tsk_thread_flag(child, TIF_IA32)) ? \
-                                        IA32_PAGE_OFFSET : TASK_SIZE64)
+                                        IA32_PAGE_OFFSET : TASK_SIZE_MAX)
 
 #define STACK_TOP               TASK_SIZE
-#define STACK_TOP_MAX           TASK_SIZE64
+#define STACK_TOP_MAX           TASK_SIZE_MAX
 
 #define INIT_THREAD  { \
         .sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index d6a22f92ba77..49fb3ecf3bb3 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -18,11 +18,7 @@ extern void syscall32_cpu_init(void);
 
 extern void check_efer(void);
 
-#ifdef CONFIG_X86_BIOS_REBOOT
 extern int reboot_force;
-#else
-static const int reboot_force = 0;
-#endif
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6d34d954c228..e304b66abeea 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -28,7 +28,7 @@ struct pt_regs {
         int  xds;
         int  xes;
         int  xfs;
-        /* int  gs; */
+        int  xgs;
         long orig_eax;
         long eip;
         int  xcs;
@@ -50,7 +50,7 @@ struct pt_regs {
         unsigned long ds;
         unsigned long es;
         unsigned long fs;
-        /* int  gs; */
+        unsigned long gs;
         unsigned long orig_ax;
         unsigned long ip;
         unsigned long cs;
diff --git a/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h b/arch/x86/include/asm/rdc321x_defs.h
index c8e9c8bed3d0..c8e9c8bed3d0 100644
--- a/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h
+++ b/arch/x86/include/asm/rdc321x_defs.h
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 2b8c5160388f..1b7ee5d673c2 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -1 +1,8 @@
+#ifndef _ASM_X86_SECTIONS_H
+#define _ASM_X86_SECTIONS_H
+
 #include <asm-generic/sections.h>
+
+extern char __brk_base[], __brk_limit[];
+
+#endif  /* _ASM_X86_SECTIONS_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 1dc1b51ac623..14e0ed86a6f9 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -61,7 +61,7 @@
  *
  *  26 - ESPFIX small SS
  *  27 - per-cpu                        [ offset to per-cpu data area ]
- *  28 - unused
+ *  28 - stack_canary-20                [ for stack protector ]
  *  29 - unused
  *  30 - unused
  *  31 - TSS for double fault handler
@@ -95,6 +95,13 @@
 #define __KERNEL_PERCPU 0
 #endif
 
+#define GDT_ENTRY_STACK_CANARY          (GDT_ENTRY_KERNEL_BASE + 16)
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __KERNEL_STACK_CANARY           (GDT_ENTRY_STACK_CANARY * 8)
+#else
+#define __KERNEL_STACK_CANARY           0
+#endif
+
 #define GDT_ENTRY_DOUBLEFAULT_TSS       31
 
 /*
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ebe858cdc8a3..bdc2ada05ae0 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -1,33 +1,19 @@
 #ifndef _ASM_X86_SETUP_H
 #define _ASM_X86_SETUP_H
 
+#ifdef __KERNEL__
+
 #define COMMAND_LINE_SIZE 2048
 
 #ifndef __ASSEMBLY__
 
-/* Interrupt control for vSMPowered x86_64 systems */
-void vsmp_init(void);
-
-
-void setup_bios_corruption_check(void);
-
-
-#ifdef CONFIG_X86_VISWS
-extern void visws_early_detect(void);
-extern int is_visws_box(void);
-#else
-static inline void visws_early_detect(void) { }
-static inline int is_visws_box(void) { return 0; }
-#endif
-
-extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
-extern int wakeup_secondary_cpu_via_init(int apicid, unsigned long start_eip);
 /*
  * Any setup quirks to be performed?
  */
 struct mpc_cpu;
 struct mpc_bus;
 struct mpc_oemtable;
+
 struct x86_quirks {
         int (*arch_pre_time_init)(void);
         int (*arch_time_init)(void);
@@ -43,20 +29,19 @@ struct x86_quirks {
         void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name);
         void (*mpc_oem_pci_bus)(struct mpc_bus *m);
         void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable,
-                                    unsigned short oemsize);
+                                unsigned short oemsize);
         int (*setup_ioapic_ids)(void);
-        int (*update_genapic)(void);
 };
 
-extern struct x86_quirks *x86_quirks;
-extern unsigned long saved_video_mode;
+extern void x86_quirk_pre_intr_init(void);
+extern void x86_quirk_intr_init(void);
 
-#ifndef CONFIG_PARAVIRT
-#define paravirt_post_allocator_init()  do {} while (0)
-#endif
-#endif /* __ASSEMBLY__ */
+extern void x86_quirk_trap_init(void);
 
-#ifdef __KERNEL__
+extern void x86_quirk_pre_time_init(void);
+extern void x86_quirk_time_init(void);
+
+#endif /* __ASSEMBLY__ */
 
 #ifdef __i386__
 
@@ -78,6 +63,30 @@ extern unsigned long saved_video_mode;
 #ifndef __ASSEMBLY__
 #include <asm/bootparam.h>
 
+/* Interrupt control for vSMPowered x86_64 systems */
+#ifdef CONFIG_X86_64
+void vsmp_init(void);
+#else
+static inline void vsmp_init(void) { }
+#endif
+
+void setup_bios_corruption_check(void);
+
+#ifdef CONFIG_X86_VISWS
+extern void visws_early_detect(void);
+extern int is_visws_box(void);
+#else
+static inline void visws_early_detect(void) { }
+static inline int is_visws_box(void) { return 0; }
+#endif
+
+extern struct x86_quirks *x86_quirks;
+extern unsigned long saved_video_mode;
+
+#ifndef CONFIG_PARAVIRT
+#define paravirt_post_allocator_init()  do {} while (0)
+#endif
+
 #ifndef _SETUP
 
 /*
@@ -91,21 +100,51 @@ extern struct boot_params boot_params;
  */
 #define LOWMEMSIZE()    (0x9f000)
 
+/* exceedingly early brk-like allocator */
+extern unsigned long _brk_end;
+void *extend_brk(size_t size, size_t align);
+
+/*
+ * Reserve space in the brk section.  The name must be unique within
+ * the file, and somewhat descriptive.  The size is in bytes.  Must be
+ * used at file scope.
+ *
+ * (This uses a temp function to wrap the asm so we can pass it the
+ * size parameter; otherwise we wouldn't be able to.  We can't use a
+ * "section" attribute on a normal variable because it always ends up
+ * being @progbits, which ends up allocating space in the vmlinux
+ * executable.)
+ */
+#define RESERVE_BRK(name,sz)                                            \
+        static void __section(.discard) __used                          \
+        __brk_reservation_fn_##name##__(void) {                         \
+                asm volatile (                                          \
+                        ".pushsection .brk_reservation,\"aw\",@nobits;" \
+                        ".brk." #name ":"                               \
+                        " 1:.skip %c0;"                                 \
+                        " .size .brk." #name ", . - 1b;"                \
+                        " .popsection"                                  \
+                        : : "i" (sz));                                  \
+        }
+
 #ifdef __i386__
 
 void __init i386_start_kernel(void);
 extern void probe_roms(void);
 
-extern unsigned long init_pg_tables_start;
-extern unsigned long init_pg_tables_end;
-
 #else
-void __init x86_64_init_pda(void);
 void __init x86_64_start_kernel(char *real_mode);
 void __init x86_64_start_reservations(char *real_mode_data);
 
 #endif /* __i386__ */
 #endif /* _SETUP */
+#else
+#define RESERVE_BRK(name,sz)                            \
+        .pushsection .brk_reservation,"aw",@nobits;     \
+.brk.name:                                              \
+1:      .skip sz;                                       \
+        .size .brk.name,.-1b;                           \
+        .popsection
 #endif /* __ASSEMBLY__ */
 #endif  /*  __KERNEL__  */
 
diff --git a/arch/x86/include/asm/mach-default/setup_arch.h b/arch/x86/include/asm/setup_arch.h
index 38846208b548..38846208b548 100644
--- a/arch/x86/include/asm/mach-default/setup_arch.h
+++ b/arch/x86/include/asm/setup_arch.h
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 19953df61c52..47d0e21f2b9e 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -15,34 +15,8 @@
 #  include <asm/io_apic.h>
 # endif
 #endif
-#include <asm/pda.h>
 #include <asm/thread_info.h>
-
-#ifdef CONFIG_X86_64
-
-extern cpumask_var_t cpu_callin_mask;
-extern cpumask_var_t cpu_callout_mask;
-extern cpumask_var_t cpu_initialized_mask;
-extern cpumask_var_t cpu_sibling_setup_mask;
-
-#else /* CONFIG_X86_32 */
-
-extern cpumask_t cpu_callin_map;
-extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_sibling_setup_map;
-
-#define cpu_callin_mask         ((struct cpumask *)&cpu_callin_map)
-#define cpu_callout_mask        ((struct cpumask *)&cpu_callout_map)
-#define cpu_initialized_mask    ((struct cpumask *)&cpu_initialized)
-#define cpu_sibling_setup_mask  ((struct cpumask *)&cpu_sibling_setup_map)
-
-#endif /* CONFIG_X86_32 */
-
-extern void (*mtrr_hook)(void);
-extern void zap_low_mappings(void);
-
-extern int __cpuinit get_local_pda(int cpu);
+#include <asm/cpumask.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
@@ -50,9 +24,7 @@ extern unsigned int num_processors;
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
-#ifdef CONFIG_X86_32
 DECLARE_PER_CPU(int, cpu_number);
-#endif
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
@@ -167,8 +139,6 @@ void play_dead_common(void);
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 
-extern void prefill_possible_map(void);
-
 void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)    per_cpu(x86_cpu_to_apicid, cpu)
 
@@ -177,10 +147,6 @@ static inline int num_booting_cpus(void)
 {
         return cpumask_weight(cpu_callout_mask);
 }
-#else
-static inline void prefill_possible_map(void)
-{
-}
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus __cpuinitdata;
@@ -191,11 +157,11 @@ extern unsigned disabled_cpus __cpuinitdata;
  * from the initial startup. We map APIC_BASE very early in page_setup(),
  * so this is correct in the x86 case.
  */
-#define raw_smp_processor_id() (x86_read_percpu(cpu_number))
+#define raw_smp_processor_id() (percpu_read(cpu_number))
 extern int safe_smp_processor_id(void);
 
 #elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id()  read_pda(cpunumber)
+#define raw_smp_processor_id() (percpu_read(cpu_number))
 
 #define stack_smp_processor_id()                                        \
 ({                                                              \
@@ -205,10 +171,6 @@ extern int safe_smp_processor_id(void);
 })
 #define safe_smp_processor_id()         smp_processor_id()
 
-#else /* !CONFIG_X86_32_SMP && !CONFIG_X86_64_SMP */
-#define cpu_physical_id(cpu)            boot_cpu_physical_apicid
-#define safe_smp_processor_id()         0
-#define stack_smp_processor_id()        0
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -220,28 +182,9 @@ static inline int logical_smp_processor_id(void)
         return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
 }
 
-#include <mach_apicdef.h>
-static inline unsigned int read_apic_id(void)
-{
-        unsigned int reg;
-
-        reg = *(u32 *)(APIC_BASE + APIC_ID);
-
-        return GET_APIC_ID(reg);
-}
 #endif
 
-
-# if defined(APIC_DEFINITION) || defined(CONFIG_X86_64)
 extern int hard_smp_processor_id(void);
-# else
-#include <mach_apicdef.h>
-static inline int hard_smp_processor_id(void)
-{
-        /* we don't want to mark this access volatile - bad code generation */
-        return read_apic_id();
-}
-# endif /* APIC_DEFINITION */
 
 #else /* CONFIG_X86_LOCAL_APIC */
 
@@ -251,11 +194,5 @@ static inline int hard_smp_processor_id(void)
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
-#ifdef CONFIG_X86_HAS_BOOT_CPU_ID
-extern unsigned char boot_cpu_id;
-#else
-#define boot_cpu_id     0
-#endif
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/include/asm/mach-default/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h
index 23bf52103b89..1def60114906 100644
--- a/arch/x86/include/asm/mach-default/smpboot_hooks.h
+++ b/arch/x86/include/asm/smpboot_hooks.h
@@ -13,10 +13,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
         CMOS_WRITE(0xa, 0xf);
         local_flush_tlb();
         pr_debug("1.\n");
-        *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
+        *((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_high)) =
                                                                  start_eip >> 4;
         pr_debug("2.\n");
-        *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
+        *((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_low)) =
                                                          start_eip & 0xf;
         pr_debug("3.\n");
 }
@@ -34,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
          */
         CMOS_WRITE(0, 0xf);
 
-        *((volatile long *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
+        *((volatile long *)phys_to_virt(apic->trampoline_phys_low)) = 0;
 }
 
 static inline void __init smpboot_setup_io_apic(void)
diff --git a/arch/x86/include/asm/socket.h b/arch/x86/include/asm/socket.h
index 8ab9cc8b2ecc..ca8bf2cd0ba9 100644
--- a/arch/x86/include/asm/socket.h
+++ b/arch/x86/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK                 36
 
+#define SO_TIMESTAMPING         37
+#define SCM_TIMESTAMPING        SO_TIMESTAMPING
+
 #endif /* _ASM_X86_SOCKET_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 8247e94ac6b1..e5e6caffec87 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -172,70 +172,8 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
         return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
 }
 
-#ifdef CONFIG_PARAVIRT
-/*
- * Define virtualization-friendly old-style lock byte lock, for use in
- * pv_lock_ops if desired.
- *
- * This differs from the pre-2.6.24 spinlock by always using xchgb
- * rather than decb to take the lock; this allows it to use a
- * zero-initialized lock structure.  It also maintains a 1-byte
- * contention counter, so that we can implement
- * __byte_spin_is_contended.
- */
-struct __byte_spinlock {
-        s8 lock;
-        s8 spinners;
-};
-
-static inline int __byte_spin_is_locked(raw_spinlock_t *lock)
-{
-        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-        return bl->lock != 0;
-}
+#ifndef CONFIG_PARAVIRT
 
-static inline int __byte_spin_is_contended(raw_spinlock_t *lock)
-{
-        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-        return bl->spinners != 0;
-}
-
-static inline void __byte_spin_lock(raw_spinlock_t *lock)
-{
-        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-        s8 val = 1;
-
-        asm("1: xchgb %1, %0\n"
-            "   test %1,%1\n"
-            "   jz 3f\n"
-            "   " LOCK_PREFIX "incb %2\n"
-            "2: rep;nop\n"
-            "   cmpb $1, %0\n"
-            "   je 2b\n"
-            "   " LOCK_PREFIX "decb %2\n"
-            "   jmp 1b\n"
-            "3:"
-            : "+m" (bl->lock), "+q" (val), "+m" (bl->spinners): : "memory");
-}
-
-static inline int __byte_spin_trylock(raw_spinlock_t *lock)
-{
-        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-        u8 old = 1;
-
-        asm("xchgb %1,%0"
-            : "+m" (bl->lock), "+q" (old) : : "memory");
-
-        return old == 0;
-}
-
-static inline void __byte_spin_unlock(raw_spinlock_t *lock)
-{
-        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-        smp_wmb();
-        bl->lock = 0;
-}
-#else  /* !CONFIG_PARAVIRT */
 static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
 {
         return __ticket_spin_is_locked(lock);
@@ -268,7 +206,7 @@ static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
         __raw_spin_lock(lock);
 }
 
-#endif  /* CONFIG_PARAVIRT */
+#endif
 
 static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
 {
@@ -330,8 +268,7 @@ static inline int __raw_read_trylock(raw_rwlock_t *lock)
 {
         atomic_t *count = (atomic_t *)lock;
 
-        atomic_dec(count);
-        if (atomic_read(count) >= 0)
+        if (atomic_dec_return(count) >= 0)
                 return 1;
         atomic_inc(count);
         return 0;
@@ -358,6 +295,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
                      : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory");
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_spin_relax(lock)   cpu_relax()
 #define _raw_read_relax(lock)   cpu_relax()
 #define _raw_write_relax(lock)  cpu_relax()
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
new file mode 100644
index 000000000000..c2d742c6e15f
--- /dev/null
+++ b/arch/x86/include/asm/stackprotector.h
@@ -0,0 +1,124 @@
+/*
+ * GCC stack protector support.
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function.  The pattern is called stack canary
+ * and unfortunately gcc requires it to be at a fixed offset from %gs.
+ * On x86_64, the offset is 40 bytes and on x86_32 20 bytes.  x86_64
+ * and x86_32 use segment registers differently and thus handles this
+ * requirement differently.
+ *
+ * On x86_64, %gs is shared by percpu area and stack canary.  All
+ * percpu symbols are zero based and %gs points to the base of percpu
+ * area.  The first occupant of the percpu area is always
+ * irq_stack_union which contains stack_canary at offset 40.  Userland
+ * %gs is always saved and restored on kernel entry and exit using
+ * swapgs, so stack protector doesn't add any complexity there.
+ *
+ * On x86_32, it's slightly more complicated.  As in x86_64, %gs is
+ * used for userland TLS.  Unfortunately, some processors are much
+ * slower at loading segment registers with different value when
+ * entering and leaving the kernel, so the kernel uses %fs for percpu
+ * area and manages %gs lazily so that %gs is switched only when
+ * necessary, usually during task switch.
+ *
+ * As gcc requires the stack canary at %gs:20, %gs can't be managed
+ * lazily if stack protector is enabled, so the kernel saves and
+ * restores userland %gs on kernel entry and exit.  This behavior is
+ * controlled by CONFIG_X86_32_LAZY_GS and accessors are defined in
+ * system.h to hide the details.
+ */
+
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+
+#include <asm/tsc.h>
+#include <asm/processor.h>
+#include <asm/percpu.h>
+#include <asm/system.h>
+#include <asm/desc.h>
+#include <linux/random.h>
+
+/*
+ * 24 byte read-only segment initializer for stack canary.  Linker
+ * can't handle the address bit shifting.  Address will be set in
+ * head_32 for boot CPU and setup_per_cpu_areas() for others.
+ */
+#define GDT_STACK_CANARY_INIT                                           \
+        [GDT_ENTRY_STACK_CANARY] = { { { 0x00000018, 0x00409000 } } },
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+        u64 canary;
+        u64 tsc;
+
+#ifdef CONFIG_X86_64
+        BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
+#endif
+        /*
+         * We both use the random pool and the current TSC as a source
+         * of randomness. The TSC only matters for very early init,
+         * there it already has some randomness on most systems. Later
+         * on during the bootup the random pool has true entropy too.
+         */
+        get_random_bytes(&canary, sizeof(canary));
+        tsc = __native_read_tsc();
+        canary += tsc + (tsc << 32UL);
+
+        current->stack_canary = canary;
+#ifdef CONFIG_X86_64
+        percpu_write(irq_stack_union.stack_canary, canary);
+#else
+        percpu_write(stack_canary, canary);
+#endif
+}
+
+static inline void setup_stack_canary_segment(int cpu)
+{
+#ifdef CONFIG_X86_32
+        unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu) - 20;
+        struct desc_struct *gdt_table = get_cpu_gdt_table(cpu);
+        struct desc_struct desc;
+
+        desc = gdt_table[GDT_ENTRY_STACK_CANARY];
+        desc.base0 = canary & 0xffff;
+        desc.base1 = (canary >> 16) & 0xff;
+        desc.base2 = (canary >> 24) & 0xff;
+        write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S);
+#endif
+}
+
+static inline void load_stack_canary_segment(void)
+{
+#ifdef CONFIG_X86_32
+        asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory");
+#endif
+}
+
+#else   /* CC_STACKPROTECTOR */
+
+#define GDT_STACK_CANARY_INIT
+
+/* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */
+
+static inline void setup_stack_canary_segment(int cpu)
+{ }
+
+static inline void load_stack_canary_segment(void)
+{
+#ifdef CONFIG_X86_32
+        asm volatile ("mov %0, %%gs" : : "r" (0));
+#endif
+}
+
+#endif  /* CC_STACKPROTECTOR */
+#endif  /* _ASM_STACKPROTECTOR_H */
diff --git a/arch/x86/include/asm/summit/apic.h b/arch/x86/include/asm/summit/apic.h
deleted file mode 100644
index 93d2c8667cfe..000000000000
--- a/arch/x86/include/asm/summit/apic.h
+++ /dev/null
@@ -1,202 +0,0 @@
-#ifndef __ASM_SUMMIT_APIC_H
-#define __ASM_SUMMIT_APIC_H
-
-#include <asm/smp.h>
-#include <linux/gfp.h>
-
-#define esr_disable (1)
-#define NO_BALANCE_IRQ (0)
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT   4
-#define XAPIC_DEST_CPUS_MASK    ((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
-#define APIC_DFR_VALUE  (APIC_DFR_CLUSTER)
-
-static inline const cpumask_t *target_cpus(void)
-{
-        /* CPU_MASK_ALL (0xff) has undefined behaviour with
-         * dest_LowestPrio mode logical clustered apic interrupt routing
-         * Just start on cpu 0.  IRQ balancing will spread load
-         */
-        return &cpumask_of_cpu(0);
-}
-
-#define INT_DELIVERY_MODE (dest_LowestPrio)
-#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-        return 0;
-}
-
-/* we don't use the phys_cpu_present_map to indicate apicid presence */
-static inline unsigned long check_apicid_present(int bit)
-{
-        return 1;
-}
-
-#define apicid_cluster(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK)
-
-extern u8 cpu_2_logical_apicid[];
-
-static inline void init_apic_ldr(void)
-{
-        unsigned long val, id;
-        int count = 0;
-        u8 my_id = (u8)hard_smp_processor_id();
-        u8 my_cluster = (u8)apicid_cluster(my_id);
-#ifdef CONFIG_SMP
-        u8 lid;
-        int i;
-
-        /* Create logical APIC IDs by counting CPUs already in cluster. */
-        for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
-                lid = cpu_2_logical_apicid[i];
-                if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
-                        ++count;
-        }
-#endif
-        /* We only have a 4 wide bitmap in cluster mode.  If a deranged
-         * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
-        BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
-        id = my_cluster | (1UL << count);
-        apic_write(APIC_DFR, APIC_DFR_VALUE);
-        val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-        val |= SET_APIC_LOGICAL_ID(id);
-        apic_write(APIC_LDR, val);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-        return 0;
-}
-
-static inline int apic_id_registered(void)
-{
-        return 1;
-}
-
-static inline void setup_apic_routing(void)
-{
-        printk("Enabling APIC mode:  Summit.  Using %d I/O APICs\n",
-                                                nr_ioapics);
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
-        return apicid_2_node[hard_smp_processor_id()];
-#else
-        return 0;
-#endif
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-        if (cpu >= nr_cpu_ids)
-                return BAD_APICID;
-        return (int)cpu_2_logical_apicid[cpu];
-#else
-        return logical_smp_processor_id();
-#endif
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-        if (mps_cpu < nr_cpu_ids)
-                return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
-        else
-                return BAD_APICID;
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_id_map)
-{
-        /* For clustered we don't have a good way to do this yet - hack */
-        return physids_promote(0x0F);
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int apicid)
-{
-        return physid_mask_of_physid(0);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-        return 1;
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-        int num_bits_set;
-        int cpus_found = 0;
-        int cpu;
-        int apicid;
-
-        num_bits_set = cpus_weight(*cpumask);
-        /* Return id to all */
-        if (num_bits_set >= nr_cpu_ids)
-                return (int) 0xFF;
-        /*
-         * The cpus in the mask must all be on the apic cluster.  If are not
-         * on the same apicid cluster return default value of TARGET_CPUS.
-         */
-        cpu = first_cpu(*cpumask);
-        apicid = cpu_to_logical_apicid(cpu);
-        while (cpus_found < num_bits_set) {
-                if (cpu_isset(cpu, *cpumask)) {
-                        int new_apicid = cpu_to_logical_apicid(cpu);
-                        if (apicid_cluster(apicid) !=
-                                        apicid_cluster(new_apicid)){
-                                printk ("%s: Not a valid mask!\n", __func__);
-                                return 0xFF;
-                        }
-                        apicid = apicid | new_apicid;
-                        cpus_found++;
-                }
-                cpu++;
-        }
-        return apicid;
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask,
-                                                  const struct cpumask *andmask)
-{
-        int apicid = cpu_to_logical_apicid(0);
-        cpumask_var_t cpumask;
-
-        if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
-                return apicid;
-
-        cpumask_and(cpumask, inmask, andmask);
-        cpumask_and(cpumask, cpumask, cpu_online_mask);
-        apicid = cpu_mask_to_apicid(cpumask);
-
-        free_cpumask_var(cpumask);
-        return apicid;
-}
-
-/* cpuid returns the value latched in the HW at reset, not the APIC ID
- * register's value.  For any box whose BIOS changes APIC IDs, like
- * clustered APIC systems, we must use hard_smp_processor_id.
- *
- * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
- */
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-        return hard_smp_processor_id() >> index_msb;
-}
-
-#endif /* __ASM_SUMMIT_APIC_H */
diff --git a/arch/x86/include/asm/summit/apicdef.h b/arch/x86/include/asm/summit/apicdef.h
deleted file mode 100644
index f3fbca1f61c1..000000000000
--- a/arch/x86/include/asm/summit/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_SUMMIT_APICDEF_H
-#define __ASM_SUMMIT_APICDEF_H
-
-#define         APIC_ID_MASK            (0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-        return (x>>24)&0xFF;
-}
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/arch/x86/include/asm/summit/ipi.h b/arch/x86/include/asm/summit/ipi.h
deleted file mode 100644
index a8a2c24f50cc..000000000000
--- a/arch/x86/include/asm/summit/ipi.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef __ASM_SUMMIT_IPI_H
-#define __ASM_SUMMIT_IPI_H
-
-void send_IPI_mask_sequence(const cpumask_t *mask, int vector);
-void send_IPI_mask_allbutself(const cpumask_t *mask, int vector);
-
-static inline void send_IPI_mask(const cpumask_t *mask, int vector)
-{
-        send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-        cpumask_t mask = cpu_online_map;
-        cpu_clear(smp_processor_id(), mask);
-
-        if (!cpus_empty(mask))
-                send_IPI_mask(&mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-        send_IPI_mask(&cpu_online_map, vector);
-}
-
-#endif /* __ASM_SUMMIT_IPI_H */
diff --git a/arch/x86/include/asm/summit/mpparse.h b/arch/x86/include/asm/summit/mpparse.h
deleted file mode 100644
index 380e86c02363..000000000000
--- a/arch/x86/include/asm/summit/mpparse.h
+++ /dev/null
@@ -1,109 +0,0 @@
-#ifndef __ASM_SUMMIT_MPPARSE_H
-#define __ASM_SUMMIT_MPPARSE_H
-
-#include <asm/tsc.h>
-
-extern int use_cyclone;
-
-#ifdef CONFIG_X86_SUMMIT_NUMA
-extern void setup_summit(void);
-#else
-#define setup_summit()  {}
-#endif
-
-static inline int mps_oem_check(struct mpc_table *mpc, char *oem,
-                char *productid)
-{
-        if (!strncmp(oem, "IBM ENSW", 8) &&
-                        (!strncmp(productid, "VIGIL SMP", 9)
-                         || !strncmp(productid, "EXA", 3)
-                         || !strncmp(productid, "RUTHLESS SMP", 12))){
-                mark_tsc_unstable("Summit based system");
-                use_cyclone = 1; /*enable cyclone-timer*/
-                setup_summit();
-                return 1;
-        }
-        return 0;
-}
-
-/* Hook from generic ACPI tables.c */
-static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-        if (!strncmp(oem_id, "IBM", 3) &&
-            (!strncmp(oem_table_id, "SERVIGIL", 8)
-             || !strncmp(oem_table_id, "EXA", 3))){
-                mark_tsc_unstable("Summit based system");
-                use_cyclone = 1; /*enable cyclone-timer*/
-                setup_summit();
-                return 1;
-        }
-        return 0;
-}
-
-struct rio_table_hdr {
-        unsigned char version;      /* Version number of this data structure           */
-                                    /* Version 3 adds chassis_num & WP_index           */
-        unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil)   */
-        unsigned char num_rio_dev;  /* # of RIO I/O devices (Cyclones and Winnipegs)   */
-} __attribute__((packed));
-
-struct scal_detail {
-        unsigned char node_id;      /* Scalability Node ID                             */
-        unsigned long CBAR;         /* Address of 1MB register space                   */
-        unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
-        unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-        unsigned char port1node;    /* Node ID port connected to: 0xFF = None          */
-        unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-        unsigned char port2node;    /* Node ID port connected to: 0xFF = None          */
-        unsigned char port2port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-        unsigned char chassis_num;  /* 1 based Chassis number (1 = boot node)          */
-} __attribute__((packed));
-
-struct rio_detail {
-        unsigned char node_id;      /* RIO Node ID                                     */
-        unsigned long BBAR;         /* Address of 1MB register space                   */
-        unsigned char type;         /* Type of device                                  */
-        unsigned char owner_id;     /* For WPEG: Node ID of Cyclone that owns this WPEG*/
-                                    /* For CYC:  Node ID of Twister that owns this CYC */
-        unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
-        unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-        unsigned char port1node;    /* Node ID port connected to: 0xFF=None            */
-        unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-        unsigned char first_slot;   /* For WPEG: Lowest slot number below this WPEG    */
-                                    /* For CYC:  0                                     */
-        unsigned char status;       /* For WPEG: Bit 0 = 1 : the XAPIC is used         */
-                                    /*                 = 0 : the XAPIC is not used, ie:*/
-                                    /*                     ints fwded to another XAPIC */
-                                    /*           Bits1:7 Reserved                      */
-                                    /* For CYC:  Bits0:7 Reserved                      */
-        unsigned char WP_index;     /* For WPEG: WPEG instance index - lower ones have */
-                                    /*           lower slot numbers/PCI bus numbers    */
-                                    /* For CYC:  No meaning                            */
-        unsigned char chassis_num;  /* 1 based Chassis number                          */
-                                    /* For LookOut WPEGs this field indicates the      */
-                                    /* Expansion Chassis #, enumerated from Boot       */
-                                    /* Node WPEG external port, then Boot Node CYC     */
-                                    /* external port, then Next Vigil chassis WPEG     */
-                                    /* external port, etc.                             */
-                                    /* Shared Lookouts have only 1 chassis number (the */
-                                    /* first one assigned)                             */
-} __attribute__((packed));
-
-
-typedef enum {
-        CompatTwister = 0,  /* Compatibility Twister               */
-        AltTwister    = 1,  /* Alternate Twister of internal 8-way */
-        CompatCyclone = 2,  /* Compatibility Cyclone               */
-        AltCyclone    = 3,  /* Alternate Cyclone of internal 8-way */
-        CompatWPEG    = 4,  /* Compatibility WPEG                  */
-        AltWPEG       = 5,  /* Second Planar WPEG                  */
-        LookOutAWPEG  = 6,  /* LookOut WPEG                        */
-        LookOutBWPEG  = 7,  /* LookOut WPEG                        */
-} node_type;
-
-static inline int is_WPEG(struct rio_detail *rio){
-        return (rio->type == CompatWPEG || rio->type == AltWPEG ||
-                rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
-}
-
-#endif /* __ASM_SUMMIT_MPPARSE_H */
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index a5074bd0f8be..48dcfa62ea07 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -24,28 +24,4 @@ struct saved_context {
         unsigned long return_address;
 } __attribute__((packed));
 
-#ifdef CONFIG_ACPI
-extern unsigned long saved_eip;
-extern unsigned long saved_esp;
-extern unsigned long saved_ebp;
-extern unsigned long saved_ebx;
-extern unsigned long saved_esi;
-extern unsigned long saved_edi;
-
-static inline void acpi_save_register_state(unsigned long return_point)
-{
-        saved_eip = return_point;
-        asm volatile("movl %%esp,%0" : "=m" (saved_esp));
-        asm volatile("movl %%ebp,%0" : "=m" (saved_ebp));
-        asm volatile("movl %%ebx,%0" : "=m" (saved_ebx));
-        asm volatile("movl %%edi,%0" : "=m" (saved_edi));
-        asm volatile("movl %%esi,%0" : "=m" (saved_esi));
-}
-
-#define acpi_restore_register_state()  do {} while (0)
-
-/* routines for saving/restoring kernel state */
-extern int acpi_save_state_mem(void);
-#endif
-
 #endif /* _ASM_X86_SUSPEND_32_H */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 1b8afa78e869..82ada75f3ebf 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -174,10 +174,6 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_CPUID_FEATURE_SHIFT 2
 #define SVM_CPUID_FUNC 0x8000000a
 
-#define MSR_EFER_SVME_MASK (1ULL << 12)
-#define MSR_VM_CR       0xc0010114
-#define MSR_VM_HSAVE_PA 0xc0010117ULL
-
 #define SVM_VM_CR_SVM_DISABLE 4
 
 #define SVM_SELECTOR_S_SHIFT 4
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index ffb08be2a530..72a6dcd1299b 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -70,8 +70,6 @@ struct old_utsname;
 asmlinkage long sys32_olduname(struct oldold_utsname __user *);
 long sys32_uname(struct old_utsname __user *);
 
-long sys32_ustat(unsigned, struct ustat32 __user *);
-
 asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *,
                              compat_uptr_t __user *, struct pt_regs *);
 asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *);
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index c0b0bda754ee..7043408f6904 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -29,21 +29,21 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *);
 /* X86_32 only */
 #ifdef CONFIG_X86_32
 /* kernel/process_32.c */
-asmlinkage int sys_fork(struct pt_regs);
-asmlinkage int sys_clone(struct pt_regs);
-asmlinkage int sys_vfork(struct pt_regs);
-asmlinkage int sys_execve(struct pt_regs);
+int sys_fork(struct pt_regs *);
+int sys_clone(struct pt_regs *);
+int sys_vfork(struct pt_regs *);
+int sys_execve(struct pt_regs *);
 
 /* kernel/signal_32.c */
 asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
 asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
                              struct old_sigaction __user *);
-asmlinkage int sys_sigaltstack(unsigned long);
-asmlinkage unsigned long sys_sigreturn(unsigned long);
-asmlinkage int sys_rt_sigreturn(unsigned long);
+int sys_sigaltstack(struct pt_regs *);
+unsigned long sys_sigreturn(struct pt_regs *);
+long sys_rt_sigreturn(struct pt_regs *);
 
 /* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned long);
+long sys_iopl(struct pt_regs *);
 
 /* kernel/sys_i386_32.c */
 asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
@@ -59,8 +59,8 @@ struct oldold_utsname;
 asmlinkage int sys_olduname(struct oldold_utsname __user *);
 
 /* kernel/vm86_32.c */
-asmlinkage int sys_vm86old(struct pt_regs);
-asmlinkage int sys_vm86(struct pt_regs);
+int sys_vm86old(struct pt_regs *);
+int sys_vm86(struct pt_regs *);
 
 #else /* CONFIG_X86_32 */
 
@@ -74,6 +74,7 @@ asmlinkage long sys_vfork(struct pt_regs *);
 asmlinkage long sys_execve(char __user *, char __user * __user *,
                            char __user * __user *,
                            struct pt_regs *);
+long sys_arch_prctl(int, unsigned long);
 
 /* kernel/ioport.c */
 asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
@@ -81,7 +82,7 @@ asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
 /* kernel/signal_64.c */
 asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
                                 struct pt_regs *);
-asmlinkage long sys_rt_sigreturn(struct pt_regs *);
+long sys_rt_sigreturn(struct pt_regs *);
 
 /* kernel/sys_x86_64.c */
 asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 8e626ea33a1a..643c59b4bc6e 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -20,9 +20,26 @@
 struct task_struct; /* one of the stranger aspects of C forward declarations */
 struct task_struct *__switch_to(struct task_struct *prev,
                                 struct task_struct *next);
+struct tss_struct;
+void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
+                      struct tss_struct *tss);
 
 #ifdef CONFIG_X86_32
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary                                                 \
+        "movl %P[task_canary](%[next]), %%ebx\n\t"                      \
+        "movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
+#define __switch_canary_oparam                                          \
+        , [stack_canary] "=m" (per_cpu_var(stack_canary))
+#define __switch_canary_iparam                                          \
+        , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else   /* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif  /* CC_STACKPROTECTOR */
+
 /*
  * Saving eflags is important. It switches not only IOPL between tasks,
  * it also protects other tasks from NT leaking through sysenter etc.
@@ -44,6 +61,7 @@ do {									\
                      "movl %[next_sp],%%esp\n\t"        /* restore ESP   */ \
                      "movl $1f,%[prev_ip]\n\t"  /* save    EIP   */     \
                      "pushl %[next_ip]\n\t"     /* restore EIP   */     \
+                     __switch_canary                                    \
                      "jmp __switch_to\n"        /* regparm call  */     \
                      "1:\t"                                             \
                      "popl %%ebp\n\t"           /* restore EBP   */     \
@@ -58,6 +76,8 @@ do {									\
                        "=b" (ebx), "=c" (ecx), "=d" (edx),              \
                        "=S" (esi), "=D" (edi)                           \
                                                                         \
+                       __switch_canary_oparam                           \
+                                                                        \
                        /* input parameters: */                          \
                      : [next_sp]  "m" (next->thread.sp),                \
                        [next_ip]  "m" (next->thread.ip),                \
@@ -66,6 +86,8 @@ do {									\
                        [prev]     "a" (prev),                           \
                        [next]     "d" (next)                            \
                                                                         \
+                       __switch_canary_iparam                           \
+                                                                        \
                      : /* reloaded segment registers */                 \
                         "memory");                                      \
 } while (0)
@@ -86,27 +108,44 @@ do {									\
         , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
           "r12", "r13", "r14", "r15"
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary                                                   \
+        "movq %P[task_canary](%%rsi),%%r8\n\t"                            \
+        "movq %%r8,"__percpu_arg([gs_canary])"\n\t"
+#define __switch_canary_oparam                                            \
+        , [gs_canary] "=m" (per_cpu_var(irq_stack_union.stack_canary))
+#define __switch_canary_iparam                                            \
+        , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else   /* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif  /* CC_STACKPROTECTOR */
+
 /* Save restore flags to clear handle leaking NT */
 #define switch_to(prev, next, last) \
-        asm volatile(SAVE_CONTEXT                                                   \
+        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 "__percpu_arg([current_task])",%%rsi\n\t"              \
+             __switch_canary                                              \
              "movq %P[thread_info](%%rsi),%%r8\n\t"                       \
-             LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"        \
              "movq %%rax,%%rdi\n\t"                                       \
-             "jc   ret_from_fork\n\t"                                     \
+             "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"         \
+             "jnz   ret_from_fork\n\t"                                    \
              RESTORE_CONTEXT                                              \
              : "=a" (last)                                                \
+               __switch_canary_oparam                                     \
              : [next] "S" (next), [prev] "D" (prev),                      \
                [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
                [ti_flags] "i" (offsetof(struct thread_info, flags)),      \
-               [tif_fork] "i" (TIF_FORK),                                 \
+               [_tif_fork] "i" (_TIF_FORK),                               \
                [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-               [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent))  \
+               [current_task] "m" (per_cpu_var(current_task))             \
+               __switch_canary_iparam                                     \
              : "memory", "cc" __EXTRA_CLOBBER)
 #endif
 
@@ -165,6 +204,25 @@ extern void native_load_gs_index(unsigned);
 #define savesegment(seg, value)                         \
         asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
+/*
+ * x86_32 user gs accessors.
+ */
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_32_LAZY_GS
+#define get_user_gs(regs)       (u16)({unsigned long v; savesegment(gs, v); v;})
+#define set_user_gs(regs, v)    loadsegment(gs, (unsigned long)(v))
+#define task_user_gs(tsk)       ((tsk)->thread.gs)
+#define lazy_save_gs(v)         savesegment(gs, (v))
+#define lazy_load_gs(v)         loadsegment(gs, (v))
+#else   /* X86_32_LAZY_GS */
+#define get_user_gs(regs)       (u16)((regs)->gs)
+#define set_user_gs(regs, v)    do { (regs)->gs = (v); } while (0)
+#define task_user_gs(tsk)       (task_pt_regs(tsk)->gs)
+#define lazy_save_gs(v)         do { } while (0)
+#define lazy_load_gs(v)         do { } while (0)
+#endif  /* X86_32_LAZY_GS */
+#endif  /* X86_32 */
+
 static inline unsigned long get_limit(unsigned long segment)
 {
         unsigned long __limit;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 98789647baa9..df9d5f78385e 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -40,6 +40,7 @@ struct thread_info {
                                                 */
         __u8                    supervisor_stack[0];
 #endif
+        int                     uaccess_err;
 };
 
 #define INIT_THREAD_INFO(tsk)                   \
@@ -194,25 +195,21 @@ static inline struct thread_info *current_thread_info(void)
 
 #else /* X86_32 */
 
-#include <asm/pda.h>
+#include <asm/percpu.h>
+#define KERNEL_STACK_OFFSET (5*8)
 
 /*
  * macros/functions for gaining access to the thread information structure
  * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #ifndef __ASSEMBLY__
-static inline struct thread_info *current_thread_info(void)
-{
-        struct thread_info *ti;
-        ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
-        return ti;
-}
+DECLARE_PER_CPU(unsigned long, kernel_stack);
 
-/* do not use in interrupt context */
-static inline struct thread_info *stack_thread_info(void)
+static inline struct thread_info *current_thread_info(void)
 {
         struct thread_info *ti;
-        asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
+        ti = (void *)(percpu_read(kernel_stack) +
+                      KERNEL_STACK_OFFSET - THREAD_SIZE);
         return ti;
 }
 
@@ -220,8 +217,8 @@ static inline struct thread_info *stack_thread_info(void)
 
 /* 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
+        movq PER_CPU_VAR(kernel_stack),reg ; \
+        subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg
 
 #endif
 
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 2bb6a835c453..bd37ed444a21 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -3,6 +3,7 @@
 #include <linux/init.h>
 #include <linux/pm.h>
 #include <linux/percpu.h>
+#include <linux/interrupt.h>
 
 #define TICK_SIZE (tick_nsec / 1000)
 
@@ -11,8 +12,9 @@ unsigned long native_calibrate_tsc(void);
 
 #ifdef CONFIG_X86_32
 extern int timer_ack;
-extern int recalibrate_cpu_khz(void);
+extern irqreturn_t timer_interrupt(int irq, void *dev_id);
 #endif /* CONFIG_X86_32 */
+extern int recalibrate_cpu_khz(void);
 
 extern int no_timer_check;
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 0e7bbb549116..d3539f998f88 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -113,7 +113,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
                 __flush_tlb();
 }
 
-static inline void native_flush_tlb_others(const cpumask_t *cpumask,
+static inline void native_flush_tlb_others(const struct cpumask *cpumask,
                                            struct mm_struct *mm,
                                            unsigned long va)
 {
@@ -142,31 +142,28 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
         flush_tlb_mm(vma->vm_mm);
 }
 
-void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm,
-                             unsigned long va);
+void native_flush_tlb_others(const struct cpumask *cpumask,
+                             struct mm_struct *mm, unsigned long va);
 
 #define TLBSTATE_OK     1
 #define TLBSTATE_LAZY   2
 
-#ifdef CONFIG_X86_32
 struct tlb_state {
         struct mm_struct *active_mm;
         int state;
-        char __cacheline_padding[L1_CACHE_BYTES-8];
 };
 DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
 
-void reset_lazy_tlbstate(void);
-#else
 static inline void reset_lazy_tlbstate(void)
 {
+        percpu_write(cpu_tlbstate.state, 0);
+        percpu_write(cpu_tlbstate.active_mm, &init_mm);
 }
-#endif
 
 #endif  /* SMP */
 
 #ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, mm, va)  native_flush_tlb_others(&mask, mm, va)
+#define flush_tlb_others(mask, mm, va)  native_flush_tlb_others(mask, mm, va)
 #endif
 
 static inline void flush_tlb_kernel_range(unsigned long start,
@@ -175,4 +172,6 @@ static inline void flush_tlb_kernel_range(unsigned long start,
         flush_tlb_all();
 }
 
+extern void zap_low_mappings(void);
+
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 4e2f2e0aab27..744299c0b774 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -74,6 +74,8 @@ static inline const struct cpumask *cpumask_of_node(int node)
         return &node_to_cpumask_map[node];
 }
 
+static inline void setup_node_to_cpumask_map(void) { }
+
 #else /* CONFIG_X86_64 */
 
 /* Mappings between node number and cpus on that node. */
@@ -83,7 +85,8 @@ extern cpumask_t *node_to_cpumask_map;
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
 /* Returns the number of the current Node. */
-#define numa_node_id()          read_pda(nodenumber)
+DECLARE_PER_CPU(int, node_number);
+#define numa_node_id()          percpu_read(node_number)
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 extern int cpu_to_node(int cpu);
@@ -102,10 +105,7 @@ static inline int cpu_to_node(int cpu)
 /* Same function but used if called before per_cpu areas are setup */
 static inline int early_cpu_to_node(int cpu)
 {
-        if (early_per_cpu_ptr(x86_cpu_to_node_map))
-                return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
-        return per_cpu(x86_cpu_to_node_map, cpu);
+        return early_per_cpu(x86_cpu_to_node_map, cpu);
 }
 
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
@@ -122,6 +122,8 @@ static inline cpumask_t node_to_cpumask(int node)
 
 #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
 
+extern void setup_node_to_cpumask_map(void);
+
 /*
  * Replace default node_to_cpumask_ptr with optimized version
  * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
@@ -192,9 +194,20 @@ extern int __node_distance(int, int);
 
 #else /* !CONFIG_NUMA */
 
-#define numa_node_id()          0
-#define cpu_to_node(cpu)        0
-#define early_cpu_to_node(cpu)  0
+static inline int numa_node_id(void)
+{
+        return 0;
+}
+
+static inline int cpu_to_node(int cpu)
+{
+        return 0;
+}
+
+static inline int early_cpu_to_node(int cpu)
+{
+        return 0;
+}
 
 static inline const cpumask_t *cpumask_of_node(int node)
 {
@@ -204,10 +217,8 @@ static inline cpumask_t node_to_cpumask(int node)
 {
         return cpu_online_map;
 }
-static inline int node_to_first_cpu(int node)
-{
-        return first_cpu(cpu_online_map);
-}
+
+static inline void setup_node_to_cpumask_map(void) { }
 
 /*
  * Replace default node_to_cpumask_ptr with optimized version
@@ -222,14 +233,6 @@ static inline int node_to_first_cpu(int node)
 
 #include <asm-generic/topology.h>
 
-#ifdef CONFIG_NUMA
-/* Returns the number of the first CPU on Node 'node'. */
-static inline int node_to_first_cpu(int node)
-{
-        return cpumask_first(cpumask_of_node(node));
-}
-#endif
-
 extern cpumask_t cpu_coregroup_map(int cpu);
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 780ba0ab94f9..90f06c25221d 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -13,6 +13,7 @@ extern unsigned char *trampoline_base;
 
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
+extern unsigned long initial_gs;
 
 #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 #define TRAMPOLINE_BASE 0x6000
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index cf3bb053da0b..0d5342515b86 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -41,7 +41,7 @@ dotraplinkage void do_int3(struct pt_regs *, long);
 dotraplinkage void do_overflow(struct pt_regs *, long);
 dotraplinkage void do_bounds(struct pt_regs *, long);
 dotraplinkage void do_invalid_op(struct pt_regs *, long);
-dotraplinkage void do_device_not_available(struct pt_regs);
+dotraplinkage void do_device_not_available(struct pt_regs *, long);
 dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long);
 dotraplinkage void do_invalid_TSS(struct pt_regs *, long);
 dotraplinkage void do_segment_not_present(struct pt_regs *, long);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 4340055b7559..b685ece89d5c 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -121,7 +121,7 @@ extern int __get_user_bad(void);
 
 #define __get_user_x(size, ret, x, ptr)               \
         asm volatile("call __get_user_" #size         \
-                     : "=a" (ret),"=d" (x)            \
+                     : "=a" (ret), "=d" (x)           \
                      : "0" (ptr))                     \
 
 /* Careful: we have to cast the result to the type of the pointer
@@ -181,12 +181,12 @@ extern int __get_user_bad(void);
 
 #define __put_user_x(size, x, ptr, __ret_pu)                    \
         asm volatile("call __put_user_" #size : "=a" (__ret_pu) \
-                     :"0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+                     : "0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
 
 
 
 #ifdef CONFIG_X86_32
-#define __put_user_u64(x, addr, err)                                    \
+#define __put_user_asm_u64(x, addr, err, errret)                        \
         asm volatile("1:        movl %%eax,0(%2)\n"                     \
                      "2:        movl %%edx,4(%2)\n"                     \
                      "3:\n"                                             \
@@ -197,14 +197,24 @@ extern int __get_user_bad(void);
                      _ASM_EXTABLE(1b, 4b)                               \
                      _ASM_EXTABLE(2b, 4b)                               \
                      : "=r" (err)                                       \
-                     : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
+                     : "A" (x), "r" (addr), "i" (errret), "0" (err))
+
+#define __put_user_asm_ex_u64(x, addr)                                  \
+        asm volatile("1:        movl %%eax,0(%1)\n"                     \
+                     "2:        movl %%edx,4(%1)\n"                     \
+                     "3:\n"                                             \
+                     _ASM_EXTABLE(1b, 2b - 1b)                          \
+                     _ASM_EXTABLE(2b, 3b - 2b)                          \
+                     : : "A" (x), "r" (addr))
 
 #define __put_user_x8(x, ptr, __ret_pu)                         \
         asm volatile("call __put_user_8" : "=a" (__ret_pu)      \
                      : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
 #else
-#define __put_user_u64(x, ptr, retval) \
-        __put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT)
+#define __put_user_asm_u64(x, ptr, retval, errret) \
+        __put_user_asm(x, ptr, retval, "q", "", "Zr", errret)
+#define __put_user_asm_ex_u64(x, addr)  \
+        __put_user_asm_ex(x, addr, "q", "", "Zr")
 #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
 #endif
 
@@ -276,10 +286,32 @@ do {									\
                 __put_user_asm(x, ptr, retval, "w", "w", "ir", errret); \
                 break;                                                  \
         case 4:                                                         \
-                __put_user_asm(x, ptr, retval, "l", "k",  "ir", errret);\
+                __put_user_asm(x, ptr, retval, "l", "k", "ir", errret); \
                 break;                                                  \
         case 8:                                                         \
-                __put_user_u64((__typeof__(*ptr))(x), ptr, retval);     \
+                __put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval,  \
+                                   errret);                             \
+                break;                                                  \
+        default:                                                        \
+                __put_user_bad();                                       \
+        }                                                               \
+} while (0)
+
+#define __put_user_size_ex(x, ptr, size)                                \
+do {                                                                    \
+        __chk_user_ptr(ptr);                                            \
+        switch (size) {                                                 \
+        case 1:                                                         \
+                __put_user_asm_ex(x, ptr, "b", "b", "iq");              \
+                break;                                                  \
+        case 2:                                                         \
+                __put_user_asm_ex(x, ptr, "w", "w", "ir");              \
+                break;                                                  \
+        case 4:                                                         \
+                __put_user_asm_ex(x, ptr, "l", "k", "ir");              \
+                break;                                                  \
+        case 8:                                                         \
+                __put_user_asm_ex_u64((__typeof__(*ptr))(x), ptr);      \
                 break;                                                  \
         default:                                                        \
                 __put_user_bad();                                       \
@@ -311,9 +343,12 @@ do {									\
 
 #ifdef CONFIG_X86_32
 #define __get_user_asm_u64(x, ptr, retval, errret)      (x) = __get_user_bad()
+#define __get_user_asm_ex_u64(x, ptr)                   (x) = __get_user_bad()
 #else
 #define __get_user_asm_u64(x, ptr, retval, errret) \
          __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
+#define __get_user_asm_ex_u64(x, ptr) \
+         __get_user_asm_ex(x, ptr, "q", "", "=r")
 #endif
 
 #define __get_user_size(x, ptr, size, retval, errret)                   \
@@ -350,6 +385,33 @@ do {									\
                      : "=r" (err), ltype(x)                             \
                      : "m" (__m(addr)), "i" (errret), "0" (err))
 
+#define __get_user_size_ex(x, ptr, size)                                \
+do {                                                                    \
+        __chk_user_ptr(ptr);                                            \
+        switch (size) {                                                 \
+        case 1:                                                         \
+                __get_user_asm_ex(x, ptr, "b", "b", "=q");              \
+                break;                                                  \
+        case 2:                                                         \
+                __get_user_asm_ex(x, ptr, "w", "w", "=r");              \
+                break;                                                  \
+        case 4:                                                         \
+                __get_user_asm_ex(x, ptr, "l", "k", "=r");              \
+                break;                                                  \
+        case 8:                                                         \
+                __get_user_asm_ex_u64(x, ptr);                          \
+                break;                                                  \
+        default:                                                        \
+                (x) = __get_user_bad();                                 \
+        }                                                               \
+} while (0)
+
+#define __get_user_asm_ex(x, addr, itype, rtype, ltype)                 \
+        asm volatile("1:        mov"itype" %1,%"rtype"0\n"              \
+                     "2:\n"                                             \
+                     _ASM_EXTABLE(1b, 2b - 1b)                          \
+                     : ltype(x) : "m" (__m(addr)))
+
 #define __put_user_nocheck(x, ptr, size)                        \
 ({                                                              \
         int __pu_err;                                           \
@@ -385,6 +447,26 @@ struct __large_struct { unsigned long buf[100]; };
                      _ASM_EXTABLE(1b, 3b)                               \
                      : "=r"(err)                                        \
                      : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
+
+#define __put_user_asm_ex(x, addr, itype, rtype, ltype)                 \
+        asm volatile("1:        mov"itype" %"rtype"0,%1\n"              \
+                     "2:\n"                                             \
+                     _ASM_EXTABLE(1b, 2b - 1b)                          \
+                     : : ltype(x), "m" (__m(addr)))
+
+/*
+ * uaccess_try and catch
+ */
+#define uaccess_try     do {                                            \
+        int prev_err = current_thread_info()->uaccess_err;              \
+        current_thread_info()->uaccess_err = 0;                         \
+        barrier();
+
+#define uaccess_catch(err)                                              \
+        (err) |= current_thread_info()->uaccess_err;                    \
+        current_thread_info()->uaccess_err = prev_err;                  \
+} while (0)
+
 /**
  * __get_user: - Get a simple variable from user space, with less checking.
  * @x:   Variable to store result.
@@ -408,6 +490,7 @@ struct __large_struct { unsigned long buf[100]; };
 
 #define __get_user(x, ptr)                                              \
         __get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+
 /**
  * __put_user: - Write a simple value into user space, with less checking.
  * @x:   Value to copy to user space.
@@ -435,6 +518,45 @@ struct __large_struct { unsigned long buf[100]; };
 #define __put_user_unaligned __put_user
 
 /*
+ * {get|put}_user_try and catch
+ *
+ * get_user_try {
+ *      get_user_ex(...);
+ * } get_user_catch(err)
+ */
+#define get_user_try            uaccess_try
+#define get_user_catch(err)     uaccess_catch(err)
+
+#define get_user_ex(x, ptr)     do {                                    \
+        unsigned long __gue_val;                                        \
+        __get_user_size_ex((__gue_val), (ptr), (sizeof(*(ptr))));       \
+        (x) = (__force __typeof__(*(ptr)))__gue_val;                    \
+} while (0)
+
+#ifdef CONFIG_X86_WP_WORKS_OK
+
+#define put_user_try            uaccess_try
+#define put_user_catch(err)     uaccess_catch(err)
+
+#define put_user_ex(x, ptr)                                             \
+        __put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+
+#else /* !CONFIG_X86_WP_WORKS_OK */
+
+#define put_user_try            do {            \
+        int __uaccess_err = 0;
+
+#define put_user_catch(err)                     \
+        (err) |= __uaccess_err;                 \
+} while (0)
+
+#define put_user_ex(x, ptr)     do {            \
+        __uaccess_err |= __put_user(x, ptr);    \
+} while (0)
+
+#endif /* CONFIG_X86_WP_WORKS_OK */
+
+/*
  * movsl can be slow when source and dest are not both 8-byte aligned
  */
 #ifdef CONFIG_X86_INTEL_USERCOPY
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 84210c479fca..8cc687326eb8 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -188,16 +188,16 @@ __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
 extern long __copy_user_nocache(void *dst, const void __user *src,
                                 unsigned size, int zerorest);
 
-static inline int __copy_from_user_nocache(void *dst, const void __user *src,
-                                           unsigned size)
+static inline int
+__copy_from_user_nocache(void *dst, const void __user *src, unsigned size)
 {
         might_sleep();
         return __copy_user_nocache(dst, src, size, 1);
 }
 
-static inline int __copy_from_user_inatomic_nocache(void *dst,
-                                                    const void __user *src,
-                                                    unsigned size)
+static inline int
+__copy_from_user_inatomic_nocache(void *dst, const void __user *src,
+                                  unsigned size)
 {
         return __copy_user_nocache(dst, src, size, 0);
 }
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index f2bba78430a4..6e72d74cf8dc 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -338,6 +338,8 @@
 #define __NR_dup3               330
 #define __NR_pipe2              331
 #define __NR_inotify_init1      332
+#define __NR_preadv             333
+#define __NR_pwritev            334
 
 #ifdef __KERNEL__
 
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index d2e415e6666f..f81829462325 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3)
 __SYSCALL(__NR_pipe2, sys_pipe2)
 #define __NR_inotify_init1                      294
 __SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_preadv                             295
+__SYSCALL(__NR_preadv, sys_preadv)
+#define __NR_pwritev                            296
+__SYSCALL(__NR_pwritev, sys_pwritev)
 
 
 #ifndef __NO_STUBS
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
new file mode 100644
index 000000000000..c0a01b5d985b
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv.h
@@ -0,0 +1,33 @@
+#ifndef _ASM_X86_UV_UV_H
+#define _ASM_X86_UV_UV_H
+
+enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
+
+struct cpumask;
+struct mm_struct;
+
+#ifdef CONFIG_X86_UV
+
+extern enum uv_system_type get_uv_system_type(void);
+extern int is_uv_system(void);
+extern void uv_cpu_init(void);
+extern void uv_system_init(void);
+extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+                                                 struct mm_struct *mm,
+                                                 unsigned long va,
+                                                 unsigned int cpu);
+
+#else   /* X86_UV */
+
+static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
+static inline int is_uv_system(void)    { return 0; }
+static inline void uv_cpu_init(void)    { }
+static inline void uv_system_init(void) { }
+static inline const struct cpumask *
+uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm,
+                    unsigned long va, unsigned int cpu)
+{ return cpumask; }
+
+#endif  /* X86_UV */
+
+#endif  /* _ASM_X86_UV_UV_H */
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 50423c7b56b2..9b0e61bf7a88 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -325,7 +325,6 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
 #define cpubit_isset(cpu, bau_local_cpumask) \
         test_bit((cpu), (bau_local_cpumask).bits)
 
-extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long);
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);
 
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 777327ef05c1..d3a98ea1062e 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -11,11 +11,13 @@
 #ifndef _ASM_X86_UV_UV_HUB_H
 #define _ASM_X86_UV_UV_HUB_H
 
+#ifdef CONFIG_X86_64
 #include <linux/numa.h>
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <asm/types.h>
 #include <asm/percpu.h>
+#include <asm/uv/uv_mmrs.h>
 
 
 /*
@@ -199,6 +201,10 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define SCIR_CPU_ACTIVITY       0x02    /* not idle */
 #define SCIR_CPU_HB_INTERVAL    (HZ)    /* once per second */
 
+/* Loop through all installed blades */
+#define for_each_possible_blade(bid)            \
+        for ((bid) = 0; (bid) < uv_num_possible_blades(); (bid)++)
+
 /*
  * Macros for converting between kernel virtual addresses, socket local physical
  * addresses, and UV global physical addresses.
@@ -393,6 +399,7 @@ static inline void uv_set_scir_bits(unsigned char value)
                 uv_write_local_mmr8(uv_hub_info->scir.offset, value);
         }
 }
+
 static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 {
         if (uv_cpu_hub_info(cpu)->scir.state != value) {
@@ -401,4 +408,15 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
         }
 }
 
+static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
+{
+        unsigned long val;
+
+        val = (1UL << UVH_IPI_INT_SEND_SHFT) |
+                        ((apicid & 0x3f) << UVH_IPI_INT_APIC_ID_SHFT) |
+                        (vector << UVH_IPI_INT_VECTOR_SHFT);
+        uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
+}
+
+#endif /* CONFIG_X86_64 */
 #endif /* _ASM_X86_UV_UV_HUB_H */
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index dd627793a234..db68ac8a5ac2 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -1,3 +1,4 @@
+
 /*
  * 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
@@ -243,6 +244,158 @@ union uvh_event_occurred0_u {
 #define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
 
 /* ========================================================================= */
+/*                         UVH_GR0_TLB_INT0_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL
+
+#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR0_TLB_INT0_CONFIG_DM_SHFT 8
+#define UVH_GR0_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR0_TLB_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_GR0_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR0_TLB_INT0_CONFIG_P_SHFT 13
+#define UVH_GR0_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR0_TLB_INT0_CONFIG_T_SHFT 15
+#define UVH_GR0_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR0_TLB_INT0_CONFIG_M_SHFT 16
+#define UVH_GR0_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr0_tlb_int0_config_u {
+    unsigned long       v;
+    struct uvh_gr0_tlb_int0_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR0_TLB_INT1_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR0_TLB_INT1_CONFIG 0x61b40UL
+
+#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_SHFT 0
+#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR0_TLB_INT1_CONFIG_DM_SHFT 8
+#define UVH_GR0_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR0_TLB_INT1_CONFIG_STATUS_SHFT 12
+#define UVH_GR0_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR0_TLB_INT1_CONFIG_P_SHFT 13
+#define UVH_GR0_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR0_TLB_INT1_CONFIG_T_SHFT 15
+#define UVH_GR0_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR0_TLB_INT1_CONFIG_M_SHFT 16
+#define UVH_GR0_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr0_tlb_int1_config_u {
+    unsigned long       v;
+    struct uvh_gr0_tlb_int1_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR1_TLB_INT0_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL
+
+#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR1_TLB_INT0_CONFIG_DM_SHFT 8
+#define UVH_GR1_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR1_TLB_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_GR1_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR1_TLB_INT0_CONFIG_P_SHFT 13
+#define UVH_GR1_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR1_TLB_INT0_CONFIG_T_SHFT 15
+#define UVH_GR1_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR1_TLB_INT0_CONFIG_M_SHFT 16
+#define UVH_GR1_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr1_tlb_int0_config_u {
+    unsigned long       v;
+    struct uvh_gr1_tlb_int0_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR1_TLB_INT1_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL
+
+#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT 0
+#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR1_TLB_INT1_CONFIG_DM_SHFT 8
+#define UVH_GR1_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR1_TLB_INT1_CONFIG_STATUS_SHFT 12
+#define UVH_GR1_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR1_TLB_INT1_CONFIG_P_SHFT 13
+#define UVH_GR1_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR1_TLB_INT1_CONFIG_T_SHFT 15
+#define UVH_GR1_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR1_TLB_INT1_CONFIG_M_SHFT 16
+#define UVH_GR1_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr1_tlb_int1_config_u {
+    unsigned long       v;
+    struct uvh_gr1_tlb_int1_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                               UVH_INT_CMPB                                */
 /* ========================================================================= */
 #define UVH_INT_CMPB 0x22080UL
diff --git a/arch/x86/include/asm/vic.h b/arch/x86/include/asm/vic.h
deleted file mode 100644
index 53100f353612..000000000000
--- a/arch/x86/include/asm/vic.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * Standard include definitions for the NCR Voyager Interrupt Controller */
-
-/* The eight CPI vectors.  To activate a CPI, you write a bit mask
- * corresponding to the processor set to be interrupted into the
- * relevant register.  That set of CPUs will then be interrupted with
- * the CPI */
-static const int VIC_CPI_Registers[] =
-        {0xFC00, 0xFC01, 0xFC08, 0xFC09,
-         0xFC10, 0xFC11, 0xFC18, 0xFC19 };
-
-#define VIC_PROC_WHO_AM_I               0xfc29
-#       define  QUAD_IDENTIFIER         0xC0
-#       define  EIGHT_SLOT_IDENTIFIER   0xE0
-#define QIC_EXTENDED_PROCESSOR_SELECT   0xFC72
-#define VIC_CPI_BASE_REGISTER           0xFC41
-#define VIC_PROCESSOR_ID                0xFC21
-#       define VIC_CPU_MASQUERADE_ENABLE 0x8
-
-#define VIC_CLAIM_REGISTER_0            0xFC38
-#define VIC_CLAIM_REGISTER_1            0xFC39
-#define VIC_REDIRECT_REGISTER_0         0xFC60
-#define VIC_REDIRECT_REGISTER_1         0xFC61
-#define VIC_PRIORITY_REGISTER           0xFC20
-
-#define VIC_PRIMARY_MC_BASE             0xFC48
-#define VIC_SECONDARY_MC_BASE           0xFC49
-
-#define QIC_PROCESSOR_ID                0xFC71
-#       define  QIC_CPUID_ENABLE        0x08
-
-#define QIC_VIC_CPI_BASE_REGISTER       0xFC79
-#define QIC_CPI_BASE_REGISTER           0xFC7A
-
-#define QIC_MASK_REGISTER0              0xFC80
-/* NOTE: these are masked high, enabled low */
-#       define QIC_PERF_TIMER           0x01
-#       define QIC_LPE                  0x02
-#       define QIC_SYS_INT              0x04
-#       define QIC_CMN_INT              0x08
-/* at the moment, just enable CMN_INT, disable SYS_INT */
-#       define QIC_DEFAULT_MASK0        (~(QIC_CMN_INT /* | VIC_SYS_INT */))
-#define QIC_MASK_REGISTER1              0xFC81
-#       define QIC_BOOT_CPI_MASK        0xFE
-/* Enable CPI's 1-6 inclusive */
-#       define QIC_CPI_ENABLE           0x81
-
-#define QIC_INTERRUPT_CLEAR0            0xFC8A
-#define QIC_INTERRUPT_CLEAR1            0xFC8B
-
-/* this is where we place the CPI vectors */
-#define VIC_DEFAULT_CPI_BASE            0xC0
-/* this is where we place the QIC CPI vectors */
-#define QIC_DEFAULT_CPI_BASE            0xD0
-
-#define VIC_BOOT_INTERRUPT_MASK         0xfe
-
-extern void smp_vic_timer_interrupt(void);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 593636275238..e0f9aa16358b 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -118,7 +118,7 @@ static inline void cpu_svm_disable(void)
 
         wrmsrl(MSR_VM_HSAVE_PA, 0);
         rdmsrl(MSR_EFER, efer);
-        wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
+        wrmsrl(MSR_EFER, efer & ~EFER_SVME);
 }
 
 /** Makes sure SVM is disabled, if it is supported on the CPU
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index d0238e6151d8..498f944010b9 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -270,8 +270,9 @@ enum vmcs_field {
 
 #define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
 #define INTR_TYPE_NMI_INTR              (2 << 8) /* NMI */
-#define INTR_TYPE_EXCEPTION             (3 << 8) /* processor exception */
+#define INTR_TYPE_HARD_EXCEPTION        (3 << 8) /* processor exception */
 #define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
+#define INTR_TYPE_SOFT_EXCEPTION        (6 << 8) /* software exception */
 
 /* GUEST_INTERRUPTIBILITY_INFO flags. */
 #define GUEST_INTR_STATE_STI            0x00000001
@@ -311,7 +312,7 @@ enum vmcs_field {
 #define DEBUG_REG_ACCESS_TYPE           0x10    /* 4, direction of access */
 #define TYPE_MOV_TO_DR                  (0 << 4)
 #define TYPE_MOV_FROM_DR                (1 << 4)
-#define DEBUG_REG_ACCESS_REG            0xf00   /* 11:8, general purpose reg. */
+#define DEBUG_REG_ACCESS_REG(eq)        (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */
 
 
 /* segment AR */
diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h
deleted file mode 100644
index b3e647307625..000000000000
--- a/arch/x86/include/asm/voyager.h
+++ /dev/null
@@ -1,529 +0,0 @@
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * Standard include definitions for the NCR Voyager system */
-
-#undef  VOYAGER_DEBUG
-#undef  VOYAGER_CAT_DEBUG
-
-#ifdef VOYAGER_DEBUG
-#define VDEBUG(x)       printk x
-#else
-#define VDEBUG(x)
-#endif
-
-/* There are three levels of voyager machine: 3,4 and 5. The rule is
- * if it's less than 3435 it's a Level 3 except for a 3360 which is
- * a level 4.  A 3435 or above is a Level 5 */
-#define VOYAGER_LEVEL5_AND_ABOVE        0x3435
-#define VOYAGER_LEVEL4                  0x3360
-
-/* The L4 DINO ASIC */
-#define VOYAGER_DINO                    0x43
-
-/* voyager ports in standard I/O space */
-#define VOYAGER_MC_SETUP        0x96
-
-
-#define VOYAGER_CAT_CONFIG_PORT                 0x97
-#       define VOYAGER_CAT_DESELECT             0xff
-#define VOYAGER_SSPB_RELOCATION_PORT            0x98
-
-/* Valid CAT controller commands */
-/* start instruction register cycle */
-#define VOYAGER_CAT_IRCYC                       0x01
-/* start data register cycle */
-#define VOYAGER_CAT_DRCYC                       0x02
-/* move to execute state */
-#define VOYAGER_CAT_RUN                         0x0F
-/* end operation */
-#define VOYAGER_CAT_END                         0x80
-/* hold in idle state */
-#define VOYAGER_CAT_HOLD                        0x90
-/* single step an "intest" vector */
-#define VOYAGER_CAT_STEP                        0xE0
-/* return cat controller to CLEMSON mode */
-#define VOYAGER_CAT_CLEMSON                     0xFF
-
-/* the default cat command header */
-#define VOYAGER_CAT_HEADER                      0x7F
-
-/* the range of possible CAT module ids in the system */
-#define VOYAGER_MIN_MODULE                      0x10
-#define VOYAGER_MAX_MODULE                      0x1f
-
-/* The voyager registers per asic */
-#define VOYAGER_ASIC_ID_REG                     0x00
-#define VOYAGER_ASIC_TYPE_REG                   0x01
-/* the sub address registers can be made auto incrementing on reads */
-#define VOYAGER_AUTO_INC_REG                    0x02
-#       define VOYAGER_AUTO_INC                 0x04
-#       define VOYAGER_NO_AUTO_INC              0xfb
-#define VOYAGER_SUBADDRDATA                     0x03
-#define VOYAGER_SCANPATH                        0x05
-#       define VOYAGER_CONNECT_ASIC             0x01
-#       define VOYAGER_DISCONNECT_ASIC          0xfe
-#define VOYAGER_SUBADDRLO                       0x06
-#define VOYAGER_SUBADDRHI                       0x07
-#define VOYAGER_SUBMODSELECT                    0x08
-#define VOYAGER_SUBMODPRESENT                   0x09
-
-#define VOYAGER_SUBADDR_LO                      0xff
-#define VOYAGER_SUBADDR_HI                      0xffff
-
-/* the maximum size of a scan path -- used to form instructions */
-#define VOYAGER_MAX_SCAN_PATH                   0x100
-/* the biggest possible register size (in bytes) */
-#define VOYAGER_MAX_REG_SIZE                    4
-
-/* Total number of possible modules (including submodules) */
-#define VOYAGER_MAX_MODULES                     16
-/* Largest number of asics per module */
-#define VOYAGER_MAX_ASICS_PER_MODULE            7
-
-/* the CAT asic of each module is always the first one */
-#define VOYAGER_CAT_ID                          0
-#define VOYAGER_PSI                             0x1a
-
-/* voyager instruction operations and registers */
-#define VOYAGER_READ_CONFIG                     0x1
-#define VOYAGER_WRITE_CONFIG                    0x2
-#define VOYAGER_BYPASS                          0xff
-
-typedef struct voyager_asic {
-        __u8    asic_addr;      /* ASIC address; Level 4 */
-        __u8    asic_type;      /* ASIC type */
-        __u8    asic_id;        /* ASIC id */
-        __u8    jtag_id[4];     /* JTAG id */
-        __u8    asic_location;  /* Location within scan path; start w/ 0 */
-        __u8    bit_location;   /* Location within bit stream; start w/ 0 */
-        __u8    ireg_length;    /* Instruction register length */
-        __u16   subaddr;        /* Amount of sub address space */
-        struct voyager_asic *next;      /* Next asic in linked list */
-} voyager_asic_t;
-
-typedef struct voyager_module {
-        __u8    module_addr;            /* Module address */
-        __u8    scan_path_connected;    /* Scan path connected */
-        __u16   ee_size;                /* Size of the EEPROM */
-        __u16   num_asics;              /* Number of Asics */
-        __u16   inst_bits;              /* Instruction bits in the scan path */
-        __u16   largest_reg;            /* Largest register in the scan path */
-        __u16   smallest_reg;           /* Smallest register in the scan path */
-        voyager_asic_t   *asic;         /* First ASIC in scan path (CAT_I) */
-        struct   voyager_module *submodule;     /* Submodule pointer */
-        struct   voyager_module *next;          /* Next module in linked list */
-} voyager_module_t;
-
-typedef struct voyager_eeprom_hdr {
-         __u8  module_id[4];
-         __u8  version_id;
-         __u8  config_id;
-         __u16 boundry_id;      /* boundary scan id */
-         __u16 ee_size;         /* size of EEPROM */
-         __u8  assembly[11];    /* assembly # */
-         __u8  assembly_rev;    /* assembly rev */
-         __u8  tracer[4];       /* tracer number */
-         __u16 assembly_cksum;  /* asm checksum */
-         __u16 power_consump;   /* pwr requirements */
-         __u16 num_asics;       /* number of asics */
-         __u16 bist_time;       /* min. bist time */
-         __u16 err_log_offset;  /* error log offset */
-         __u16 scan_path_offset;/* scan path offset */
-         __u16 cct_offset;
-         __u16 log_length;      /* length of err log */
-         __u16 xsum_end;        /* offset to end of
-                                   checksum */
-         __u8  reserved[4];
-         __u8  sflag;           /* starting sentinal */
-         __u8  part_number[13]; /* prom part number */
-         __u8  version[10];     /* version number */
-         __u8  signature[8];
-         __u16 eeprom_chksum;
-         __u32  data_stamp_offset;
-         __u8  eflag ;           /* ending sentinal */
-} __attribute__((packed)) voyager_eprom_hdr_t;
-
-
-
-#define VOYAGER_EPROM_SIZE_OFFSET                               \
-        ((__u16)(&(((voyager_eprom_hdr_t *)0)->ee_size)))
-#define VOYAGER_XSUM_END_OFFSET         0x2a
-
-/* the following three definitions are for internal table layouts
- * in the module EPROMs.  We really only care about the IDs and
- * offsets */
-typedef struct voyager_sp_table {
-        __u8 asic_id;
-        __u8 bypass_flag;
-        __u16 asic_data_offset;
-        __u16 config_data_offset;
-} __attribute__((packed)) voyager_sp_table_t;
-
-typedef struct voyager_jtag_table {
-        __u8 icode[4];
-        __u8 runbist[4];
-        __u8 intest[4];
-        __u8 samp_preld[4];
-        __u8 ireg_len;
-} __attribute__((packed)) voyager_jtt_t;
-
-typedef struct voyager_asic_data_table {
-        __u8 jtag_id[4];
-        __u16 length_bsr;
-        __u16 length_bist_reg;
-        __u32 bist_clk;
-        __u16 subaddr_bits;
-        __u16 seed_bits;
-        __u16 sig_bits;
-        __u16 jtag_offset;
-} __attribute__((packed)) voyager_at_t;
-
-/* Voyager Interrupt Controller (VIC) registers */
-
-/* Base to add to Cross Processor Interrupts (CPIs) when triggering
- * the CPU IRQ line */
-/* register defines for the WCBICs (one per processor) */
-#define VOYAGER_WCBIC0  0x41            /* bus A node P1 processor 0 */
-#define VOYAGER_WCBIC1  0x49            /* bus A node P1 processor 1 */
-#define VOYAGER_WCBIC2  0x51            /* bus A node P2 processor 0 */
-#define VOYAGER_WCBIC3  0x59            /* bus A node P2 processor 1 */
-#define VOYAGER_WCBIC4  0x61            /* bus B node P1 processor 0 */
-#define VOYAGER_WCBIC5  0x69            /* bus B node P1 processor 1 */
-#define VOYAGER_WCBIC6  0x71            /* bus B node P2 processor 0 */
-#define VOYAGER_WCBIC7  0x79            /* bus B node P2 processor 1 */
-
-
-/* top of memory registers */
-#define VOYAGER_WCBIC_TOM_L     0x4
-#define VOYAGER_WCBIC_TOM_H     0x5
-
-/* register defines for Voyager Memory Contol (VMC)
- * these are present on L4 machines only */
-#define VOYAGER_VMC1            0x81
-#define VOYAGER_VMC2            0x91
-#define VOYAGER_VMC3            0xa1
-#define VOYAGER_VMC4            0xb1
-
-/* VMC Ports */
-#define VOYAGER_VMC_MEMORY_SETUP        0x9
-#       define VMC_Interleaving         0x01
-#       define VMC_4Way                 0x02
-#       define VMC_EvenCacheLines       0x04
-#       define VMC_HighLine             0x08
-#       define VMC_Start0_Enable        0x20
-#       define VMC_Start1_Enable        0x40
-#       define VMC_Vremap               0x80
-#define VOYAGER_VMC_BANK_DENSITY        0xa
-#       define  VMC_BANK_EMPTY          0
-#       define  VMC_BANK_4MB            1
-#       define  VMC_BANK_16MB           2
-#       define  VMC_BANK_64MB           3
-#       define  VMC_BANK0_MASK          0x03
-#       define  VMC_BANK1_MASK          0x0C
-#       define  VMC_BANK2_MASK          0x30
-#       define  VMC_BANK3_MASK          0xC0
-
-/* Magellan Memory Controller (MMC) defines - present on L5 */
-#define VOYAGER_MMC_ASIC_ID             1
-/* the two memory modules corresponding to memory cards in the system */
-#define VOYAGER_MMC_MEMORY0_MODULE      0x14
-#define VOYAGER_MMC_MEMORY1_MODULE      0x15
-/* the Magellan Memory Address (MMA) defines */
-#define VOYAGER_MMA_ASIC_ID             2
-
-/* Submodule number for the Quad Baseboard */
-#define VOYAGER_QUAD_BASEBOARD          1
-
-/* ASIC defines for the Quad Baseboard */
-#define VOYAGER_QUAD_QDATA0             1
-#define VOYAGER_QUAD_QDATA1             2
-#define VOYAGER_QUAD_QABC               3
-
-/* Useful areas in extended CMOS */
-#define VOYAGER_PROCESSOR_PRESENT_MASK  0x88a
-#define VOYAGER_MEMORY_CLICKMAP         0xa23
-#define VOYAGER_DUMP_LOCATION           0xb1a
-
-/* SUS In Control bit - used to tell SUS that we don't need to be
- * babysat anymore */
-#define VOYAGER_SUS_IN_CONTROL_PORT     0x3ff
-#       define VOYAGER_IN_CONTROL_FLAG  0x80
-
-/* Voyager PSI defines */
-#define VOYAGER_PSI_STATUS_REG          0x08
-#       define PSI_DC_FAIL              0x01
-#       define PSI_MON                  0x02
-#       define PSI_FAULT                0x04
-#       define PSI_ALARM                0x08
-#       define PSI_CURRENT              0x10
-#       define PSI_DVM                  0x20
-#       define PSI_PSCFAULT             0x40
-#       define PSI_STAT_CHG             0x80
-
-#define VOYAGER_PSI_SUPPLY_REG          0x8000
-        /* read */
-#       define PSI_FAIL_DC              0x01
-#       define PSI_FAIL_AC              0x02
-#       define PSI_MON_INT              0x04
-#       define PSI_SWITCH_OFF           0x08
-#       define PSI_HX_OFF               0x10
-#       define PSI_SECURITY             0x20
-#       define PSI_CMOS_BATT_LOW        0x40
-#       define PSI_CMOS_BATT_FAIL       0x80
-        /* write */
-#       define PSI_CLR_SWITCH_OFF       0x13
-#       define PSI_CLR_HX_OFF           0x14
-#       define PSI_CLR_CMOS_BATT_FAIL   0x17
-
-#define VOYAGER_PSI_MASK                0x8001
-#       define PSI_MASK_MASK            0x10
-
-#define VOYAGER_PSI_AC_FAIL_REG         0x8004
-#define AC_FAIL_STAT_CHANGE             0x80
-
-#define VOYAGER_PSI_GENERAL_REG         0x8007
-        /* read */
-#       define PSI_SWITCH_ON            0x01
-#       define PSI_SWITCH_ENABLED       0x02
-#       define PSI_ALARM_ENABLED        0x08
-#       define PSI_SECURE_ENABLED       0x10
-#       define PSI_COLD_RESET           0x20
-#       define PSI_COLD_START           0x80
-        /* write */
-#       define PSI_POWER_DOWN           0x10
-#       define PSI_SWITCH_DISABLE       0x01
-#       define PSI_SWITCH_ENABLE        0x11
-#       define PSI_CLEAR                0x12
-#       define PSI_ALARM_DISABLE        0x03
-#       define PSI_ALARM_ENABLE         0x13
-#       define PSI_CLEAR_COLD_RESET     0x05
-#       define PSI_SET_COLD_RESET       0x15
-#       define PSI_CLEAR_COLD_START     0x07
-#       define PSI_SET_COLD_START       0x17
-
-
-
-struct voyager_bios_info {
-        __u8    len;
-        __u8    major;
-        __u8    minor;
-        __u8    debug;
-        __u8    num_classes;
-        __u8    class_1;
-        __u8    class_2;
-};
-
-/* The following structures and definitions are for the Kernel/SUS
- * interface these are needed to find out how SUS initialised any Quad
- * boards in the system */
-
-#define NUMBER_OF_MC_BUSSES     2
-#define SLOTS_PER_MC_BUS        8
-#define MAX_CPUS                16      /* 16 way CPU system */
-#define MAX_PROCESSOR_BOARDS    4       /* 4 processor slot system */
-#define MAX_CACHE_LEVELS        4       /* # of cache levels supported */
-#define MAX_SHARED_CPUS         4       /* # of CPUs that can share a LARC */
-#define NUMBER_OF_POS_REGS      8
-
-typedef struct {
-        __u8    MC_Slot;
-        __u8    POS_Values[NUMBER_OF_POS_REGS];
-} __attribute__((packed)) MC_SlotInformation_t;
-
-struct QuadDescription {
-        __u8  Type;     /* for type 0 (DYADIC or MONADIC) all fields
-                         * will be zero except for slot */
-        __u8 StructureVersion;
-        __u32 CPI_BaseAddress;
-        __u32  LARC_BankSize;
-        __u32 LocalMemoryStateBits;
-        __u8  Slot; /* Processor slots 1 - 4 */
-} __attribute__((packed));
-
-struct ProcBoardInfo {
-        __u8 Type;
-        __u8 StructureVersion;
-        __u8 NumberOfBoards;
-        struct QuadDescription QuadData[MAX_PROCESSOR_BOARDS];
-} __attribute__((packed));
-
-struct CacheDescription {
-        __u8 Level;
-        __u32 TotalSize;
-        __u16 LineSize;
-        __u8  Associativity;
-        __u8  CacheType;
-        __u8  WriteType;
-        __u8  Number_CPUs_SharedBy;
-        __u8  Shared_CPUs_Hardware_IDs[MAX_SHARED_CPUS];
-
-} __attribute__((packed));
-
-struct CPU_Description {
-        __u8 CPU_HardwareId;
-        char *FRU_String;
-        __u8 NumberOfCacheLevels;
-        struct CacheDescription CacheLevelData[MAX_CACHE_LEVELS];
-} __attribute__((packed));
-
-struct CPU_Info {
-        __u8 Type;
-        __u8 StructureVersion;
-        __u8 NumberOf_CPUs;
-        struct CPU_Description CPU_Data[MAX_CPUS];
-} __attribute__((packed));
-
-
-/*
- * This structure will be used by SUS and the OS.
- * The assumption about this structure is that no blank space is
- * packed in it by our friend the compiler.
- */
-typedef struct {
-        __u8    Mailbox_SUS;            /* Written to by SUS to give
-                                           commands/response to the OS */
-        __u8    Mailbox_OS;             /* Written to by the OS to give
-                                           commands/response to SUS */
-        __u8    SUS_MailboxVersion;     /* Tells the OS which iteration of the
-                                           interface SUS supports */
-        __u8    OS_MailboxVersion;      /* Tells SUS which iteration of the
-                                           interface the OS supports */
-        __u32   OS_Flags;               /* Flags set by the OS as info for
-                                           SUS */
-        __u32   SUS_Flags;              /* Flags set by SUS as info
-                                           for the OS */
-        __u32   WatchDogPeriod;         /* Watchdog period (in seconds) which
-                                           the DP uses to see if the OS
-                                           is dead */
-        __u32   WatchDogCount;          /* Updated by the OS on every tic. */
-        __u32   MemoryFor_SUS_ErrorLog; /* Flat 32 bit address which tells SUS
-                                           where to stuff the SUS error log
-                                           on a dump */
-        MC_SlotInformation_t MC_SlotInfo[NUMBER_OF_MC_BUSSES*SLOTS_PER_MC_BUS];
-                                        /* Storage for MCA POS data */
-        /* All new SECOND_PASS_INTERFACE fields added from this point */
-        struct ProcBoardInfo    *BoardData;
-        struct CPU_Info         *CPU_Data;
-        /* All new fields must be added from this point */
-} Voyager_KernelSUS_Mbox_t;
-
-/* structure for finding the right memory address to send a QIC CPI to */
-struct voyager_qic_cpi {
-        /* Each cache line (32 bytes) can trigger a cpi.  The cpi
-         * read/write may occur anywhere in the cache line---pick the
-         * middle to be safe */
-        struct  {
-                __u32 pad1[3];
-                __u32 cpi;
-                __u32 pad2[4];
-        } qic_cpi[8];
-};
-
-struct voyager_status {
-        __u32   power_fail:1;
-        __u32   switch_off:1;
-        __u32   request_from_kernel:1;
-};
-
-struct voyager_psi_regs {
-        __u8 cat_id;
-        __u8 cat_dev;
-        __u8 cat_control;
-        __u8 subaddr;
-        __u8 dummy4;
-        __u8 checkbit;
-        __u8 subaddr_low;
-        __u8 subaddr_high;
-        __u8 intstatus;
-        __u8 stat1;
-        __u8 stat3;
-        __u8 fault;
-        __u8 tms;
-        __u8 gen;
-        __u8 sysconf;
-        __u8 dummy15;
-};
-
-struct voyager_psi_subregs {
-        __u8 supply;
-        __u8 mask;
-        __u8 present;
-        __u8 DCfail;
-        __u8 ACfail;
-        __u8 fail;
-        __u8 UPSfail;
-        __u8 genstatus;
-};
-
-struct voyager_psi {
-        struct voyager_psi_regs regs;
-        struct voyager_psi_subregs subregs;
-};
-
-struct voyager_SUS {
-#define VOYAGER_DUMP_BUTTON_NMI         0x1
-#define VOYAGER_SUS_VALID               0x2
-#define VOYAGER_SYSINT_COMPLETE         0x3
-        __u8    SUS_mbox;
-#define VOYAGER_NO_COMMAND              0x0
-#define VOYAGER_IGNORE_DUMP             0x1
-#define VOYAGER_DO_DUMP                 0x2
-#define VOYAGER_SYSINT_HANDSHAKE        0x3
-#define VOYAGER_DO_MEM_DUMP             0x4
-#define VOYAGER_SYSINT_WAS_RECOVERED    0x5
-        __u8    kernel_mbox;
-#define VOYAGER_MAILBOX_VERSION         0x10
-        __u8    SUS_version;
-        __u8    kernel_version;
-#define VOYAGER_OS_HAS_SYSINT           0x1
-#define VOYAGER_OS_IN_PROGRESS          0x2
-#define VOYAGER_UPDATING_WDPERIOD       0x4
-        __u32   kernel_flags;
-#define VOYAGER_SUS_BOOTING             0x1
-#define VOYAGER_SUS_IN_PROGRESS         0x2
-        __u32   SUS_flags;
-        __u32   watchdog_period;
-        __u32   watchdog_count;
-        __u32   SUS_errorlog;
-        /* lots of system configuration stuff under here */
-};
-
-/* Variables exported by voyager_smp */
-extern __u32 voyager_extended_vic_processors;
-extern __u32 voyager_allowed_boot_processors;
-extern __u32 voyager_quad_processors;
-extern struct voyager_qic_cpi *voyager_quad_cpi_addr[NR_CPUS];
-extern struct voyager_SUS *voyager_SUS;
-
-/* variables exported always */
-extern struct task_struct *voyager_thread;
-extern int voyager_level;
-extern struct voyager_status voyager_status;
-
-/* functions exported by the voyager and voyager_smp modules */
-extern int voyager_cat_readb(__u8 module, __u8 asic, int reg);
-extern void voyager_cat_init(void);
-extern void voyager_detect(struct voyager_bios_info *);
-extern void voyager_trap_init(void);
-extern void voyager_setup_irqs(void);
-extern int voyager_memory_detect(int region, __u32 *addr, __u32 *length);
-extern void voyager_smp_intr_init(void);
-extern __u8 voyager_extended_cmos_read(__u16 cmos_address);
-extern void voyager_smp_dump(void);
-extern void voyager_timer_interrupt(void);
-extern void smp_local_timer_interrupt(void);
-extern void voyager_power_off(void);
-extern void smp_voyager_power_off(void *dummy);
-extern void voyager_restart(void);
-extern void voyager_cat_power_off(void);
-extern void voyager_cat_do_common_interrupt(void);
-extern void voyager_handle_nmi(void);
-extern void voyager_smp_intr_init(void);
-/* Commands for the following are */
-#define VOYAGER_PSI_READ        0
-#define VOYAGER_PSI_WRITE       1
-#define VOYAGER_PSI_SUBREAD     2
-#define VOYAGER_PSI_SUBWRITE    3
-extern void voyager_cat_psi(__u8, __u16, __u8 *);
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index 19144184983a..1df35417c412 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -15,10 +15,4 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
         return raw_irqs_disabled_flags(regs->flags);
 }
 
-static inline void xen_do_IRQ(int irq, struct pt_regs *regs)
-{
-        regs->orig_ax = ~irq;
-        do_IRQ(regs);
-}
-
 #endif /* _ASM_X86_XEN_EVENTS_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 5e79ca694326..9c371e4a9fa6 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -296,6 +296,8 @@ HYPERVISOR_get_debugreg(int reg)
 static inline int
 HYPERVISOR_update_descriptor(u64 ma, u64 desc)
 {
+        if (sizeof(u64) == sizeof(long))
+                return _hypercall2(int, update_descriptor, ma, desc);
         return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
 }
 
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 81fbd735aec4..d5b7e90c0edf 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -38,22 +38,30 @@ extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
 enum xen_domain_type {
-        XEN_NATIVE,
-        XEN_PV_DOMAIN,
-        XEN_HVM_DOMAIN,
+        XEN_NATIVE,             /* running on bare hardware    */
+        XEN_PV_DOMAIN,          /* running in a PV domain      */
+        XEN_HVM_DOMAIN,         /* running in a Xen hvm domain */
 };
 
-extern enum xen_domain_type xen_domain_type;
-
 #ifdef CONFIG_XEN
-#define xen_domain()            (xen_domain_type != XEN_NATIVE)
+extern enum xen_domain_type xen_domain_type;
 #else
-#define xen_domain()            (0)
+#define xen_domain_type         XEN_NATIVE
 #endif
 
-#define xen_pv_domain()         (xen_domain() && xen_domain_type == XEN_PV_DOMAIN)
-#define xen_hvm_domain()        (xen_domain() && xen_domain_type == XEN_HVM_DOMAIN)
+#define xen_domain()            (xen_domain_type != XEN_NATIVE)
+#define xen_pv_domain()         (xen_domain() &&                        \
+                                 xen_domain_type == XEN_PV_DOMAIN)
+#define xen_hvm_domain()        (xen_domain() &&                        \
+                                 xen_domain_type == XEN_HVM_DOMAIN)
+
+#ifdef CONFIG_XEN_DOM0
+#include <xen/interface/xen.h>
 
-#define xen_initial_domain()    (xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
+#define xen_initial_domain()    (xen_pv_domain() && \
+                                 xen_start_info->flags & SIF_INITDOMAIN)
+#else  /* !CONFIG_XEN_DOM0 */
+#define xen_initial_domain()    (0)
+#endif  /* CONFIG_XEN_DOM0 */
 
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 4bd990ee43df..1a918dde46b5 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -164,6 +164,7 @@ static inline pte_t __pte_ma(pteval_t x)
 
 
 xmaddr_t arbitrary_virt_to_machine(void *address);
+unsigned long arbitrary_virt_to_mfn(void *vaddr);
 void make_lowmem_page_readonly(void *vaddr);
 void make_lowmem_page_readwrite(void *vaddr);