Merge branch 'wip-2.6.34' into old-private-masterarchived-private-master

125 files changed, 3387 insertions, 2655 deletions

diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 4a8e80cdcfa5..493092efaa3b 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -10,6 +10,8 @@ header-y += ptrace-abi.h
 header-y += sigcontext32.h
 header-y += ucontext.h
 header-y += processor-flags.h
+header-y += hw_breakpoint.h
+header-y += hyperv.h
 
 unifdef-y += e820.h
 unifdef-y += ist.h
diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h
index bb70e397aa84..7a15588e45d4 100644
--- a/arch/x86/include/asm/a.out-core.h
+++ b/arch/x86/include/asm/a.out-core.h
@@ -17,6 +17,7 @@
 
 #include <linux/user.h>
 #include <linux/elfcore.h>
+#include <asm/debugreg.h>
 
 /*
  * fill in the user structure for an a.out core dump
@@ -32,14 +33,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
                         >> PAGE_SHIFT;
         dump->u_dsize -= dump->u_tsize;
         dump->u_ssize = 0;
-        dump->u_debugreg[0] = current->thread.debugreg0;
-        dump->u_debugreg[1] = current->thread.debugreg1;
-        dump->u_debugreg[2] = current->thread.debugreg2;
-        dump->u_debugreg[3] = current->thread.debugreg3;
-        dump->u_debugreg[4] = 0;
-        dump->u_debugreg[5] = 0;
-        dump->u_debugreg[6] = current->thread.debugreg6;
-        dump->u_debugreg[7] = current->thread.debugreg7;
+        aout_dump_debugregs(dump);
 
         if (dump->start_stack < TASK_SIZE)
                 dump->u_ssize = ((unsigned long)(TASK_SIZE - dump->start_stack))
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 4518dc500903..56f462cf22d2 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -118,7 +118,7 @@ extern void acpi_restore_state_mem(void);
 extern unsigned long acpi_wakeup_address;
 
 /* early initialization routine */
-extern void acpi_reserve_bootmem(void);
+extern void acpi_reserve_wakeup_memory(void);
 
 /*
  * Check if the CPU can handle C2 and deeper
@@ -142,6 +142,32 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
                 return max_cstate;
 }
 
+static inline bool arch_has_acpi_pdc(void)
+{
+        struct cpuinfo_x86 *c = &cpu_data(0);
+        return (c->x86_vendor == X86_VENDOR_INTEL ||
+                c->x86_vendor == X86_VENDOR_CENTAUR);
+}
+
+static inline void arch_acpi_set_pdc_bits(u32 *buf)
+{
+        struct cpuinfo_x86 *c = &cpu_data(0);
+
+        buf[2] |= ACPI_PDC_C_CAPABILITY_SMP;
+
+        if (cpu_has(c, X86_FEATURE_EST))
+                buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP;
+
+        if (cpu_has(c, X86_FEATURE_ACPI))
+                buf[2] |= ACPI_PDC_T_FFH;
+
+        /*
+         * If mwait/monitor is unsupported, C2/C3_FFH will be disabled
+         */
+        if (!cpu_has(c, X86_FEATURE_MWAIT))
+                buf[2] &= ~(ACPI_PDC_C_C2C3_FFH);
+}
+
 #else /* !CONFIG_ACPI */
 
 #define acpi_lapic 0
@@ -158,6 +184,7 @@ struct bootnode;
 
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
+extern int acpi_get_nodes(struct bootnode *physnodes);
 extern int acpi_scan_nodes(unsigned long start, unsigned long end);
 #define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
 extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index e2077d343c33..b97f786a48d5 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -1,17 +1,13 @@
 #ifdef __ASSEMBLY__
 
-#ifdef CONFIG_X86_32
-# define X86_ALIGN .long
-#else
-# define X86_ALIGN .quad
-#endif
+#include <asm/asm.h>
 
 #ifdef CONFIG_SMP
         .macro LOCK_PREFIX
 1:      lock
         .section .smp_locks,"a"
-        .align 4
-        X86_ALIGN 1b
+        _ASM_ALIGN
+        _ASM_PTR 1b
         .previous
         .endm
 #else
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index c240efc74e00..b09ec55650b3 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -65,12 +65,17 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
                                         void *text, void *text_end);
 extern void alternatives_smp_module_del(struct module *mod);
 extern void alternatives_smp_switch(int smp);
+extern int alternatives_text_reserved(void *start, void *end);
 #else
 static inline void alternatives_smp_module_add(struct module *mod, char *name,
                                                void *locks, void *locks_end,
                                                void *text, void *text_end) {}
 static inline void alternatives_smp_module_del(struct module *mod) {}
 static inline void alternatives_smp_switch(int smp) {}
+static inline int alternatives_text_reserved(void *start, void *end)
+{
+        return 0;
+}
 #endif  /* CONFIG_SMP */
 
 /* alternative assembly primitive: */
@@ -84,6 +89,7 @@ static inline void alternatives_smp_switch(int smp) {}
       "  .byte " __stringify(feature) "\n"      /* feature bit     */   \
       "  .byte 662b-661b\n"                     /* sourcelen       */   \
       "  .byte 664f-663f\n"                     /* replacementlen  */   \
+      "  .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */   \
       ".previous\n"                                                     \
       ".section .altinstr_replacement, \"ax\"\n"                        \
       "663:\n\t" newinstr "\n664:\n"            /* replacement     */   \
@@ -124,11 +130,16 @@ static inline void alternatives_smp_switch(int smp) {}
         asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)          \
                 : output : "i" (0), ## input)
 
+/* Like alternative_io, but for replacing a direct call with another one. */
+#define alternative_call(oldfunc, newfunc, feature, output, input...)   \
+        asm volatile (ALTERNATIVE("call %P[old]", "call %P[new]", feature) \
+                : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
+
 /*
  * use this macro(s) if you need more than one output parameter
  * in alternative_io
  */
-#define ASM_OUTPUT2(a, b) a, b
+#define ASM_OUTPUT2(a...) a
 
 struct paravirt_patch_site;
 #ifdef CONFIG_PARAVIRT
@@ -154,10 +165,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
  * invalid instruction possible) or if the instructions are changed from a
  * consistent state to another consistent state atomically.
  * More care must be taken when modifying code in the SMP case because of
- * Intel's errata.
+ * Intel's errata. text_poke_smp() takes care that errata, but still
+ * doesn't support NMI/MCE handler code modifying.
  * On the local CPU you need to be protected again NMI or MCE handlers seeing an
  * inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index 4b180897e6b5..5af2982133b5 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -23,19 +23,13 @@
 #include <linux/irqreturn.h>
 
 #ifdef CONFIG_AMD_IOMMU
-extern int amd_iommu_init(void);
-extern int amd_iommu_init_dma_ops(void);
-extern int amd_iommu_init_passthrough(void);
+
 extern void amd_iommu_detect(void);
-extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-extern void amd_iommu_flush_all_domains(void);
-extern void amd_iommu_flush_all_devices(void);
-extern void amd_iommu_shutdown(void);
-extern void amd_iommu_apply_erratum_63(u16 devid);
+
 #else
-static inline int amd_iommu_init(void) { return -ENODEV; }
+
 static inline void amd_iommu_detect(void) { }
-static inline void amd_iommu_shutdown(void) { }
+
 #endif
 
 #endif /* _ASM_X86_AMD_IOMMU_H */
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
new file mode 100644
index 000000000000..d2544f1d705d
--- /dev/null
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright (C) 2009 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef _ASM_X86_AMD_IOMMU_PROTO_H
+#define _ASM_X86_AMD_IOMMU_PROTO_H
+
+struct amd_iommu;
+
+extern int amd_iommu_init_dma_ops(void);
+extern int amd_iommu_init_passthrough(void);
+extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
+extern void amd_iommu_flush_all_domains(void);
+extern void amd_iommu_flush_all_devices(void);
+extern void amd_iommu_apply_erratum_63(u16 devid);
+extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
+extern int amd_iommu_init_devices(void);
+extern void amd_iommu_uninit_devices(void);
+extern void amd_iommu_init_notifier(void);
+extern void amd_iommu_init_api(void);
+#ifndef CONFIG_AMD_IOMMU_STATS
+
+static inline void amd_iommu_stats_init(void) { }
+
+#endif /* !CONFIG_AMD_IOMMU_STATS */
+
+#endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 2a2cc7a78a81..86a0ff0aeac7 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -21,10 +21,16 @@
 #define _ASM_X86_AMD_IOMMU_TYPES_H
 
 #include <linux/types.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 
 /*
+ * Maximum number of IOMMUs supported
+ */
+#define MAX_IOMMUS      32
+
+/*
  * some size calculation constants
  */
 #define DEV_TABLE_ENTRY_SIZE            32
@@ -135,6 +141,7 @@
 
 /* constants to configure the command buffer */
 #define CMD_BUFFER_SIZE    8192
+#define CMD_BUFFER_UNINITIALIZED 1
 #define CMD_BUFFER_ENTRIES 512
 #define MMIO_CMD_SIZE_SHIFT 56
 #define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
@@ -206,6 +213,9 @@ extern bool amd_iommu_dump;
                         printk(KERN_INFO "AMD-Vi: " format, ## arg);    \
         } while(0);
 
+/* global flag if IOMMUs cache non-present entries */
+extern bool amd_iommu_np_cache;
+
 /*
  * Make iterating over all IOMMUs easier
  */
@@ -226,14 +236,30 @@ extern bool amd_iommu_dump;
  * independent of their use.
  */
 struct protection_domain {
+        struct list_head list;  /* for list of all protection domains */
+        struct list_head dev_list; /* List of all devices in this domain */
         spinlock_t lock;        /* mostly used to lock the page table*/
+        struct mutex api_lock;  /* protect page tables in the iommu-api path */
         u16 id;                 /* the domain id written to the device table */
         int mode;               /* paging mode (0-6 levels) */
         u64 *pt_root;           /* page table root pointer */
         unsigned long flags;    /* flags to find out type of domain */
         bool updated;           /* complete domain flush required */
         unsigned dev_cnt;       /* devices assigned to this domain */
+        unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
         void *priv;             /* private data */
+
+};
+
+/*
+ * This struct contains device specific data for the IOMMU
+ */
+struct iommu_dev_data {
+        struct list_head list;            /* For domain->dev_list */
+        struct device *dev;               /* Device this data belong to */
+        struct device *alias;             /* The Alias Device */
+        struct protection_domain *domain; /* Domain the device is bound to */
+        atomic_t bind;                    /* Domain attach reverent count */
 };
 
 /*
@@ -291,6 +317,9 @@ struct dma_ops_domain {
 struct amd_iommu {
         struct list_head list;
 
+        /* Index within the IOMMU array */
+        int index;
+
         /* locks the accesses to the hardware */
         spinlock_t lock;
 
@@ -357,6 +386,21 @@ struct amd_iommu {
 extern struct list_head amd_iommu_list;
 
 /*
+ * Array with pointers to each IOMMU struct
+ * The indices are referenced in the protection domains
+ */
+extern struct amd_iommu *amd_iommus[MAX_IOMMUS];
+
+/* Number of IOMMUs present in the system */
+extern int amd_iommus_present;
+
+/*
+ * Declarations for the global list of all protection domains
+ */
+extern spinlock_t amd_iommu_pd_lock;
+extern struct list_head amd_iommu_pd_list;
+
+/*
  * Structure defining one entry in the device table
  */
 struct dev_table_entry {
@@ -416,15 +460,9 @@ extern unsigned amd_iommu_aperture_order;
 /* largest PCI device id we expect translation requests for */
 extern u16 amd_iommu_last_bdf;
 
-/* data structures for protection domain handling */
-extern struct protection_domain **amd_iommu_pd_table;
-
 /* allocation bitmap for domain ids */
 extern unsigned long *amd_iommu_pd_alloc_bitmap;
 
-/* will be 1 if device isolation is enabled */
-extern bool amd_iommu_isolate;
-
 /*
  * If true, the addresses will be flushed on unmap time, not when
  * they are reused
@@ -462,11 +500,6 @@ struct __iommu_counter {
 #define ADD_STATS_COUNTER(name, x)
 #define SUB_STATS_COUNTER(name, x)
 
-static inline void amd_iommu_stats_init(void) { }
-
 #endif /* CONFIG_AMD_IOMMU_STATS */
 
-/* some function prototypes */
-extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
-
 #endif /* _ASM_X86_AMD_IOMMU_TYPES_H */
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
new file mode 100644
index 000000000000..c74a2eebe570
--- /dev/null
+++ b/arch/x86/include/asm/apb_timer.h
@@ -0,0 +1,70 @@
+/*
+ * apb_timer.h: Driver for Langwell APB timer based on Synopsis DesignWare
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Jacob Pan (jacob.jun.pan@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Note:
+ */
+
+#ifndef ASM_X86_APBT_H
+#define ASM_X86_APBT_H
+#include <linux/sfi.h>
+
+#ifdef CONFIG_APB_TIMER
+
+/* Langwell DW APB timer registers */
+#define APBTMR_N_LOAD_COUNT    0x00
+#define APBTMR_N_CURRENT_VALUE 0x04
+#define APBTMR_N_CONTROL       0x08
+#define APBTMR_N_EOI           0x0c
+#define APBTMR_N_INT_STATUS    0x10
+
+#define APBTMRS_INT_STATUS     0xa0
+#define APBTMRS_EOI            0xa4
+#define APBTMRS_RAW_INT_STATUS 0xa8
+#define APBTMRS_COMP_VERSION   0xac
+#define APBTMRS_REG_SIZE       0x14
+
+/* register bits */
+#define APBTMR_CONTROL_ENABLE  (1<<0)
+#define APBTMR_CONTROL_MODE_PERIODIC   (1<<1) /*1: periodic 0:free running */
+#define APBTMR_CONTROL_INT     (1<<2)
+
+/* default memory mapped register base */
+#define LNW_SCU_ADDR           0xFF100000
+#define LNW_EXT_TIMER_OFFSET   0x1B800
+#define APBT_DEFAULT_BASE      (LNW_SCU_ADDR+LNW_EXT_TIMER_OFFSET)
+#define LNW_EXT_TIMER_PGOFFSET         0x800
+
+/* APBT clock speed range from PCLK to fabric base, 25-100MHz */
+#define APBT_MAX_FREQ          50
+#define APBT_MIN_FREQ          1
+#define APBT_MMAP_SIZE         1024
+
+#define APBT_DEV_USED  1
+
+extern void apbt_time_init(void);
+extern struct clock_event_device *global_clock_event;
+extern unsigned long apbt_quick_calibrate(void);
+extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
+extern void apbt_setup_secondary_clock(void);
+extern unsigned int boot_cpu_id;
+extern int disable_apbt_percpu;
+
+extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
+extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr);
+extern int sfi_mtimer_num;
+
+#else /* CONFIG_APB_TIMER */
+
+static inline unsigned long apbt_quick_calibrate(void) {return 0; }
+static inline void apbt_time_init(void) {return 0; }
+
+#endif
+#endif /* ASM_X86_APBT_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 474d80d3e6cc..b4ac2cdcb64f 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -297,20 +297,20 @@ struct apic {
         int disable_esr;
 
         int dest_logical;
-        unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
+        unsigned long (*check_apicid_used)(physid_mask_t *map, 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 (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
 
         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 (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap);
         void (*setup_portio_remap)(void);
         int (*check_phys_apicid_present)(int phys_apicid);
         void (*enable_apic_mode)(void);
@@ -488,6 +488,8 @@ static inline unsigned int read_apic_id(void)
 
 extern void default_setup_apic_routing(void);
 
+extern struct apic apic_noop;
+
 #ifdef CONFIG_X86_32
 
 extern struct apic apic_default;
@@ -532,9 +534,9 @@ default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
         return (unsigned int)(mask1 & mask2 & mask3);
 }
 
-static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid)
+static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid)
 {
-        return physid_isset(apicid, bitmap);
+        return physid_isset(apicid, *map);
 }
 
 static inline unsigned long default_check_apicid_present(int bit)
@@ -542,9 +544,9 @@ 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)
+static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
 {
-        return phys_map;
+        *retmap = *phys_map;
 }
 
 /* Mapping from cpu number to logical apicid */
@@ -583,11 +585,6 @@ extern int default_cpu_present_to_apicid(int mps_cpu);
 extern int default_check_phys_apicid_present(int phys_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
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 3b62da926de9..7fe3b3060f08 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -11,6 +11,12 @@
 #define IO_APIC_DEFAULT_PHYS_BASE       0xfec00000
 #define APIC_DEFAULT_PHYS_BASE          0xfee00000
 
+/*
+ * This is the IO-APIC register space as specified
+ * by Intel docs:
+ */
+#define IO_APIC_SLOT_SIZE               1024
+
 #define APIC_ID         0x20
 
 #define APIC_LVR        0x30
diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h
deleted file mode 100644
index 82f613c607ce..000000000000
--- a/arch/x86/include/asm/apicnum.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#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/asm-offsets.h b/arch/x86/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/x86/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 4e1b8873c474..8f8217b9bdac 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -1,5 +1,300 @@
+#ifndef _ASM_X86_ATOMIC_H
+#define _ASM_X86_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <asm/alternative.h>
+#include <asm/cmpxchg.h>
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+#define ATOMIC_INIT(i)  { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+        return v->counter;
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+        v->counter = i;
+}
+
+/**
+ * atomic_add - add integer to atomic variable
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+        asm volatile(LOCK_PREFIX "addl %1,%0"
+                     : "+m" (v->counter)
+                     : "ir" (i));
+}
+
+/**
+ * atomic_sub - subtract integer from atomic variable
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static inline void atomic_sub(int i, atomic_t *v)
+{
+        asm volatile(LOCK_PREFIX "subl %1,%0"
+                     : "+m" (v->counter)
+                     : "ir" (i));
+}
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic_sub_and_test(int i, atomic_t *v)
+{
+        unsigned char c;
+
+        asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
+                     : "+m" (v->counter), "=qm" (c)
+                     : "ir" (i) : "memory");
+        return c;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+        asm volatile(LOCK_PREFIX "incl %0"
+                     : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic_dec(atomic_t *v)
+{
+        asm volatile(LOCK_PREFIX "decl %0"
+                     : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+        unsigned char c;
+
+        asm volatile(LOCK_PREFIX "decl %0; sete %1"
+                     : "+m" (v->counter), "=qm" (c)
+                     : : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic_inc_and_test(atomic_t *v)
+{
+        unsigned char c;
+
+        asm volatile(LOCK_PREFIX "incl %0; sete %1"
+                     : "+m" (v->counter), "=qm" (c)
+                     : : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int atomic_add_negative(int i, atomic_t *v)
+{
+        unsigned char c;
+
+        asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
+                     : "+m" (v->counter), "=qm" (c)
+                     : "ir" (i) : "memory");
+        return c;
+}
+
+/**
+ * atomic_add_return - add integer and return
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+        int __i;
+#ifdef CONFIG_M386
+        unsigned long flags;
+        if (unlikely(boot_cpu_data.x86 <= 3))
+                goto no_xadd;
+#endif
+        /* Modern 486+ processor */
+        __i = i;
+        asm volatile(LOCK_PREFIX "xaddl %0, %1"
+                     : "+r" (i), "+m" (v->counter)
+                     : : "memory");
+        return i + __i;
+
+#ifdef CONFIG_M386
+no_xadd: /* Legacy 386 processor */
+        raw_local_irq_save(flags);
+        __i = atomic_read(v);
+        atomic_set(v, i + __i);
+        raw_local_irq_restore(flags);
+        return i + __i;
+#endif
+}
+
+/**
+ * atomic_sub_return - subtract integer and return
+ * @v: pointer of type atomic_t
+ * @i: integer value to subtract
+ *
+ * Atomically subtracts @i from @v and returns @v - @i
+ */
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+        return atomic_add_return(-i, v);
+}
+
+#define atomic_inc_return(v)  (atomic_add_return(1, v))
+#define atomic_dec_return(v)  (atomic_sub_return(1, v))
+
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+        return cmpxchg(&v->counter, old, new);
+}
+
+static inline int atomic_xchg(atomic_t *v, int new)
+{
+        return xchg(&v->counter, new);
+}
+
+/**
+ * atomic_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as @v was not already @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static inline int atomic_add_unless(atomic_t *v, int a, int u)
+{
+        int c, old;
+        c = atomic_read(v);
+        for (;;) {
+                if (unlikely(c == (u)))
+                        break;
+                old = atomic_cmpxchg((v), c, c + (a));
+                if (likely(old == c))
+                        break;
+                c = old;
+        }
+        return c != (u);
+}
+
+#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
+/**
+ * atomic_inc_short - increment of a short integer
+ * @v: pointer to type int
+ *
+ * Atomically adds 1 to @v
+ * Returns the new value of @u
+ */
+static inline short int atomic_inc_short(short int *v)
+{
+        asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
+        return *v;
+}
+
+#ifdef CONFIG_X86_64
+/**
+ * atomic_or_long - OR of two long integers
+ * @v1: pointer to type unsigned long
+ * @v2: pointer to type unsigned long
+ *
+ * Atomically ORs @v1 and @v2
+ * Returns the result of the OR
+ */
+static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
+{
+        asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
+}
+#endif
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr)                           \
+        asm volatile(LOCK_PREFIX "andl %0,%1"                   \
+                     : : "r" (~(mask)), "m" (*(addr)) : "memory")
+
+#define atomic_set_mask(mask, addr)                             \
+        asm volatile(LOCK_PREFIX "orl %0,%1"                    \
+                     : : "r" ((unsigned)(mask)), "m" (*(addr))  \
+                     : "memory")
+
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic_dec()     barrier()
+#define smp_mb__after_atomic_dec()      barrier()
+#define smp_mb__before_atomic_inc()     barrier()
+#define smp_mb__after_atomic_inc()      barrier()
+
 #ifdef CONFIG_X86_32
-# include "atomic_32.h"
+# include "atomic64_32.h"
 #else
-# include "atomic_64.h"
+# include "atomic64_64.h"
 #endif
+
+#include <asm-generic/atomic-long.h>
+#endif /* _ASM_X86_ATOMIC_H */
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
new file mode 100644
index 000000000000..03027bf28de5
--- /dev/null
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -0,0 +1,160 @@
+#ifndef _ASM_X86_ATOMIC64_32_H
+#define _ASM_X86_ATOMIC64_32_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/processor.h>
+//#include <asm/cmpxchg.h>
+
+/* An 64bit atomic type */
+
+typedef struct {
+        u64 __aligned(8) counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(val)      { (val) }
+
+extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val);
+
+/**
+ * atomic64_xchg - xchg atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ * @new_val:  value to assign
+ *
+ * Atomically xchgs the value of @ptr to @new_val and returns
+ * the old value.
+ */
+extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val);
+
+/**
+ * atomic64_set - set atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ * @new_val:  value to assign
+ *
+ * Atomically sets the value of @ptr to @new_val.
+ */
+extern void atomic64_set(atomic64_t *ptr, u64 new_val);
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ *
+ * Atomically reads the value of @ptr and returns it.
+ */
+static inline u64 atomic64_read(atomic64_t *ptr)
+{
+        u64 res;
+
+        /*
+         * Note, we inline this atomic64_t primitive because
+         * it only clobbers EAX/EDX and leaves the others
+         * untouched. We also (somewhat subtly) rely on the
+         * fact that cmpxchg8b returns the current 64-bit value
+         * of the memory location we are touching:
+         */
+        asm volatile(
+                "mov %%ebx, %%eax\n\t"
+                "mov %%ecx, %%edx\n\t"
+                LOCK_PREFIX "cmpxchg8b %1\n"
+                        : "=&A" (res)
+                        : "m" (*ptr)
+                );
+
+        return res;
+}
+
+extern u64 atomic64_read(atomic64_t *ptr);
+
+/**
+ * atomic64_add_return - add and return
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr and returns @delta + *@ptr
+ */
+extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr);
+
+/*
+ * Other variants with different arithmetic operators:
+ */
+extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr);
+extern u64 atomic64_inc_return(atomic64_t *ptr);
+extern u64 atomic64_dec_return(atomic64_t *ptr);
+
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr.
+ */
+extern void atomic64_add(u64 delta, atomic64_t *ptr);
+
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @delta: integer value to subtract
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically subtracts @delta from @ptr.
+ */
+extern void atomic64_sub(u64 delta, atomic64_t *ptr);
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @delta: integer value to subtract
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically subtracts @delta from @ptr and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr);
+
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically increments @ptr by 1.
+ */
+extern void atomic64_inc(atomic64_t *ptr);
+
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically decrements @ptr by 1.
+ */
+extern void atomic64_dec(atomic64_t *ptr);
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically decrements @ptr by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+extern int atomic64_dec_and_test(atomic64_t *ptr);
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically increments @ptr by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+extern int atomic64_inc_and_test(atomic64_t *ptr);
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+extern int atomic64_add_negative(u64 delta, atomic64_t *ptr);
+
+#endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
new file mode 100644
index 000000000000..51c5b4056929
--- /dev/null
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -0,0 +1,224 @@
+#ifndef _ASM_X86_ATOMIC64_64_H
+#define _ASM_X86_ATOMIC64_64_H
+
+#include <linux/types.h>
+#include <asm/alternative.h>
+#include <asm/cmpxchg.h>
+
+/* The 64-bit atomic type */
+
+#define ATOMIC64_INIT(i)        { (i) }
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically reads the value of @v.
+ * Doesn't imply a read memory barrier.
+ */
+static inline long atomic64_read(const atomic64_t *v)
+{
+        return v->counter;
+}
+
+/**
+ * atomic64_set - set atomic64 variable
+ * @v: pointer to type atomic64_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic64_set(atomic64_t *v, long i)
+{
+        v->counter = i;
+}
+
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v.
+ */
+static inline void atomic64_add(long i, atomic64_t *v)
+{
+        asm volatile(LOCK_PREFIX "addq %1,%0"
+                     : "=m" (v->counter)
+                     : "er" (i), "m" (v->counter));
+}
+
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static inline void atomic64_sub(long i, atomic64_t *v)
+{
+        asm volatile(LOCK_PREFIX "subq %1,%0"
+                     : "=m" (v->counter)
+                     : "er" (i), "m" (v->counter));
+}
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_sub_and_test(long i, atomic64_t *v)
+{
+        unsigned char c;
+
+        asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
+                     : "=m" (v->counter), "=qm" (c)
+                     : "er" (i), "m" (v->counter) : "memory");
+        return c;
+}
+
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic64_inc(atomic64_t *v)
+{
+        asm volatile(LOCK_PREFIX "incq %0"
+                     : "=m" (v->counter)
+                     : "m" (v->counter));
+}
+
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic64_dec(atomic64_t *v)
+{
+        asm volatile(LOCK_PREFIX "decq %0"
+                     : "=m" (v->counter)
+                     : "m" (v->counter));
+}
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic64_dec_and_test(atomic64_t *v)
+{
+        unsigned char c;
+
+        asm volatile(LOCK_PREFIX "decq %0; sete %1"
+                     : "=m" (v->counter), "=qm" (c)
+                     : "m" (v->counter) : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_inc_and_test(atomic64_t *v)
+{
+        unsigned char c;
+
+        asm volatile(LOCK_PREFIX "incq %0; sete %1"
+                     : "=m" (v->counter), "=qm" (c)
+                     : "m" (v->counter) : "memory");
+        return c != 0;
+}
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int atomic64_add_negative(long i, atomic64_t *v)
+{
+        unsigned char c;
+
+        asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
+                     : "=m" (v->counter), "=qm" (c)
+                     : "er" (i), "m" (v->counter) : "memory");
+        return c;
+}
+
+/**
+ * atomic64_add_return - add and return
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static inline long atomic64_add_return(long i, atomic64_t *v)
+{
+        long __i = i;
+        asm volatile(LOCK_PREFIX "xaddq %0, %1;"
+                     : "+r" (i), "+m" (v->counter)
+                     : : "memory");
+        return i + __i;
+}
+
+static inline long atomic64_sub_return(long i, atomic64_t *v)
+{
+        return atomic64_add_return(-i, v);
+}
+
+#define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
+#define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
+
+static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+{
+        return cmpxchg(&v->counter, old, new);
+}
+
+static inline long atomic64_xchg(atomic64_t *v, long new)
+{
+        return xchg(&v->counter, new);
+}
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+        long c, old;
+        c = atomic64_read(v);
+        for (;;) {
+                if (unlikely(c == (u)))
+                        break;
+                old = atomic64_cmpxchg((v), c, c + (a));
+                if (likely(old == c))
+                        break;
+                c = old;
+        }
+        return c != (u);
+}
+
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+
+#endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
deleted file mode 100644
index dc5a667ff791..000000000000
--- a/arch/x86/include/asm/atomic_32.h
+++ /dev/null
@@ -1,415 +0,0 @@
-#ifndef _ASM_X86_ATOMIC_32_H
-#define _ASM_X86_ATOMIC_32_H
-
-#include <linux/compiler.h>
-#include <linux/types.h>
-#include <asm/processor.h>
-#include <asm/cmpxchg.h>
-
-/*
- * Atomic operations that C can't guarantee us.  Useful for
- * resource counting etc..
- */
-
-#define ATOMIC_INIT(i)  { (i) }
-
-/**
- * atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v.
- */
-static inline int atomic_read(const atomic_t *v)
-{
-        return v->counter;
-}
-
-/**
- * atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-static inline void atomic_set(atomic_t *v, int i)
-{
-        v->counter = i;
-}
-
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
-        asm volatile(LOCK_PREFIX "addl %1,%0"
-                     : "+m" (v->counter)
-                     : "ir" (i));
-}
-
-/**
- * atomic_sub - subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic_sub(int i, atomic_t *v)
-{
-        asm volatile(LOCK_PREFIX "subl %1,%0"
-                     : "+m" (v->counter)
-                     : "ir" (i));
-}
-
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
-                     : "+m" (v->counter), "=qm" (c)
-                     : "ir" (i) : "memory");
-        return c;
-}
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic_inc(atomic_t *v)
-{
-        asm volatile(LOCK_PREFIX "incl %0"
-                     : "+m" (v->counter));
-}
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic_dec(atomic_t *v)
-{
-        asm volatile(LOCK_PREFIX "decl %0"
-                     : "+m" (v->counter));
-}
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic_dec_and_test(atomic_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "decl %0; sete %1"
-                     : "+m" (v->counter), "=qm" (c)
-                     : : "memory");
-        return c != 0;
-}
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_inc_and_test(atomic_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "incl %0; sete %1"
-                     : "+m" (v->counter), "=qm" (c)
-                     : : "memory");
-        return c != 0;
-}
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
-                     : "+m" (v->counter), "=qm" (c)
-                     : "ir" (i) : "memory");
-        return c;
-}
-
-/**
- * atomic_add_return - add integer and return
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-        int __i;
-#ifdef CONFIG_M386
-        unsigned long flags;
-        if (unlikely(boot_cpu_data.x86 <= 3))
-                goto no_xadd;
-#endif
-        /* Modern 486+ processor */
-        __i = i;
-        asm volatile(LOCK_PREFIX "xaddl %0, %1"
-                     : "+r" (i), "+m" (v->counter)
-                     : : "memory");
-        return i + __i;
-
-#ifdef CONFIG_M386
-no_xadd: /* Legacy 386 processor */
-        local_irq_save(flags);
-        __i = atomic_read(v);
-        atomic_set(v, i + __i);
-        local_irq_restore(flags);
-        return i + __i;
-#endif
-}
-
-/**
- * atomic_sub_return - subtract integer and return
- * @v: pointer of type atomic_t
- * @i: integer value to subtract
- *
- * Atomically subtracts @i from @v and returns @v - @i
- */
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-        return atomic_add_return(-i, v);
-}
-
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
-{
-        return cmpxchg(&v->counter, old, new);
-}
-
-static inline int atomic_xchg(atomic_t *v, int new)
-{
-        return xchg(&v->counter, new);
-}
-
-/**
- * atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
-{
-        int c, old;
-        c = atomic_read(v);
-        for (;;) {
-                if (unlikely(c == (u)))
-                        break;
-                old = atomic_cmpxchg((v), c, c + (a));
-                if (likely(old == c))
-                        break;
-                c = old;
-        }
-        return c != (u);
-}
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_inc_return(v)  (atomic_add_return(1, v))
-#define atomic_dec_return(v)  (atomic_sub_return(1, v))
-
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr)                           \
-        asm volatile(LOCK_PREFIX "andl %0,%1"                   \
-                     : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr)                             \
-        asm volatile(LOCK_PREFIX "orl %0,%1"                            \
-                     : : "r" (mask), "m" (*(addr)) : "memory")
-
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec()     barrier()
-#define smp_mb__after_atomic_dec()      barrier()
-#define smp_mb__before_atomic_inc()     barrier()
-#define smp_mb__after_atomic_inc()      barrier()
-
-/* An 64bit atomic type */
-
-typedef struct {
-        u64 __aligned(8) counter;
-} atomic64_t;
-
-#define ATOMIC64_INIT(val)      { (val) }
-
-extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val);
-
-/**
- * atomic64_xchg - xchg atomic64 variable
- * @ptr:      pointer to type atomic64_t
- * @new_val:  value to assign
- *
- * Atomically xchgs the value of @ptr to @new_val and returns
- * the old value.
- */
-extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val);
-
-/**
- * atomic64_set - set atomic64 variable
- * @ptr:      pointer to type atomic64_t
- * @new_val:  value to assign
- *
- * Atomically sets the value of @ptr to @new_val.
- */
-extern void atomic64_set(atomic64_t *ptr, u64 new_val);
-
-/**
- * atomic64_read - read atomic64 variable
- * @ptr:      pointer to type atomic64_t
- *
- * Atomically reads the value of @ptr and returns it.
- */
-static inline u64 atomic64_read(atomic64_t *ptr)
-{
-        u64 res;
-
-        /*
-         * Note, we inline this atomic64_t primitive because
-         * it only clobbers EAX/EDX and leaves the others
-         * untouched. We also (somewhat subtly) rely on the
-         * fact that cmpxchg8b returns the current 64-bit value
-         * of the memory location we are touching:
-         */
-        asm volatile(
-                "mov %%ebx, %%eax\n\t"
-                "mov %%ecx, %%edx\n\t"
-                LOCK_PREFIX "cmpxchg8b %1\n"
-                        : "=&A" (res)
-                        : "m" (*ptr)
-                );
-
-        return res;
-}
-
-extern u64 atomic64_read(atomic64_t *ptr);
-
-/**
- * atomic64_add_return - add and return
- * @delta: integer value to add
- * @ptr:   pointer to type atomic64_t
- *
- * Atomically adds @delta to @ptr and returns @delta + *@ptr
- */
-extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr);
-
-/*
- * Other variants with different arithmetic operators:
- */
-extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr);
-extern u64 atomic64_inc_return(atomic64_t *ptr);
-extern u64 atomic64_dec_return(atomic64_t *ptr);
-
-/**
- * atomic64_add - add integer to atomic64 variable
- * @delta: integer value to add
- * @ptr:   pointer to type atomic64_t
- *
- * Atomically adds @delta to @ptr.
- */
-extern void atomic64_add(u64 delta, atomic64_t *ptr);
-
-/**
- * atomic64_sub - subtract the atomic64 variable
- * @delta: integer value to subtract
- * @ptr:   pointer to type atomic64_t
- *
- * Atomically subtracts @delta from @ptr.
- */
-extern void atomic64_sub(u64 delta, atomic64_t *ptr);
-
-/**
- * atomic64_sub_and_test - subtract value from variable and test result
- * @delta: integer value to subtract
- * @ptr:   pointer to type atomic64_t
- *
- * Atomically subtracts @delta from @ptr and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr);
-
-/**
- * atomic64_inc - increment atomic64 variable
- * @ptr: pointer to type atomic64_t
- *
- * Atomically increments @ptr by 1.
- */
-extern void atomic64_inc(atomic64_t *ptr);
-
-/**
- * atomic64_dec - decrement atomic64 variable
- * @ptr: pointer to type atomic64_t
- *
- * Atomically decrements @ptr by 1.
- */
-extern void atomic64_dec(atomic64_t *ptr);
-
-/**
- * atomic64_dec_and_test - decrement and test
- * @ptr: pointer to type atomic64_t
- *
- * Atomically decrements @ptr by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-extern int atomic64_dec_and_test(atomic64_t *ptr);
-
-/**
- * atomic64_inc_and_test - increment and test
- * @ptr: pointer to type atomic64_t
- *
- * Atomically increments @ptr by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-extern int atomic64_inc_and_test(atomic64_t *ptr);
-
-/**
- * atomic64_add_negative - add and test if negative
- * @delta: integer value to add
- * @ptr:   pointer to type atomic64_t
- *
- * Atomically adds @delta to @ptr and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-extern int atomic64_add_negative(u64 delta, atomic64_t *ptr);
-
-#include <asm-generic/atomic-long.h>
-#endif /* _ASM_X86_ATOMIC_32_H */
diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h
deleted file mode 100644
index d605dc268e79..000000000000
--- a/arch/x86/include/asm/atomic_64.h
+++ /dev/null
@@ -1,485 +0,0 @@
-#ifndef _ASM_X86_ATOMIC_64_H
-#define _ASM_X86_ATOMIC_64_H
-
-#include <linux/types.h>
-#include <asm/alternative.h>
-#include <asm/cmpxchg.h>
-
-/*
- * Atomic operations that C can't guarantee us.  Useful for
- * resource counting etc..
- */
-
-#define ATOMIC_INIT(i)  { (i) }
-
-/**
- * atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v.
- */
-static inline int atomic_read(const atomic_t *v)
-{
-        return v->counter;
-}
-
-/**
- * atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-static inline void atomic_set(atomic_t *v, int i)
-{
-        v->counter = i;
-}
-
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
-        asm volatile(LOCK_PREFIX "addl %1,%0"
-                     : "=m" (v->counter)
-                     : "ir" (i), "m" (v->counter));
-}
-
-/**
- * atomic_sub - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic_sub(int i, atomic_t *v)
-{
-        asm volatile(LOCK_PREFIX "subl %1,%0"
-                     : "=m" (v->counter)
-                     : "ir" (i), "m" (v->counter));
-}
-
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
-                     : "=m" (v->counter), "=qm" (c)
-                     : "ir" (i), "m" (v->counter) : "memory");
-        return c;
-}
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic_inc(atomic_t *v)
-{
-        asm volatile(LOCK_PREFIX "incl %0"
-                     : "=m" (v->counter)
-                     : "m" (v->counter));
-}
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic_dec(atomic_t *v)
-{
-        asm volatile(LOCK_PREFIX "decl %0"
-                     : "=m" (v->counter)
-                     : "m" (v->counter));
-}
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic_dec_and_test(atomic_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "decl %0; sete %1"
-                     : "=m" (v->counter), "=qm" (c)
-                     : "m" (v->counter) : "memory");
-        return c != 0;
-}
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_inc_and_test(atomic_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "incl %0; sete %1"
-                     : "=m" (v->counter), "=qm" (c)
-                     : "m" (v->counter) : "memory");
-        return c != 0;
-}
-
-/**
- * atomic_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
-                     : "=m" (v->counter), "=qm" (c)
-                     : "ir" (i), "m" (v->counter) : "memory");
-        return c;
-}
-
-/**
- * atomic_add_return - add and return
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-        int __i = i;
-        asm volatile(LOCK_PREFIX "xaddl %0, %1"
-                     : "+r" (i), "+m" (v->counter)
-                     : : "memory");
-        return i + __i;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-        return atomic_add_return(-i, v);
-}
-
-#define atomic_inc_return(v)  (atomic_add_return(1, v))
-#define atomic_dec_return(v)  (atomic_sub_return(1, v))
-
-/* The 64-bit atomic type */
-
-#define ATOMIC64_INIT(i)        { (i) }
-
-/**
- * atomic64_read - read atomic64 variable
- * @v: pointer of type atomic64_t
- *
- * Atomically reads the value of @v.
- * Doesn't imply a read memory barrier.
- */
-static inline long atomic64_read(const atomic64_t *v)
-{
-        return v->counter;
-}
-
-/**
- * atomic64_set - set atomic64 variable
- * @v: pointer to type atomic64_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-static inline void atomic64_set(atomic64_t *v, long i)
-{
-        v->counter = i;
-}
-
-/**
- * atomic64_add - add integer to atomic64 variable
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic64_add(long i, atomic64_t *v)
-{
-        asm volatile(LOCK_PREFIX "addq %1,%0"
-                     : "=m" (v->counter)
-                     : "er" (i), "m" (v->counter));
-}
-
-/**
- * atomic64_sub - subtract the atomic64 variable
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic64_sub(long i, atomic64_t *v)
-{
-        asm volatile(LOCK_PREFIX "subq %1,%0"
-                     : "=m" (v->counter)
-                     : "er" (i), "m" (v->counter));
-}
-
-/**
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic64_sub_and_test(long i, atomic64_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
-                     : "=m" (v->counter), "=qm" (c)
-                     : "er" (i), "m" (v->counter) : "memory");
-        return c;
-}
-
-/**
- * atomic64_inc - increment atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic64_inc(atomic64_t *v)
-{
-        asm volatile(LOCK_PREFIX "incq %0"
-                     : "=m" (v->counter)
-                     : "m" (v->counter));
-}
-
-/**
- * atomic64_dec - decrement atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic64_dec(atomic64_t *v)
-{
-        asm volatile(LOCK_PREFIX "decq %0"
-                     : "=m" (v->counter)
-                     : "m" (v->counter));
-}
-
-/**
- * atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic64_dec_and_test(atomic64_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "decq %0; sete %1"
-                     : "=m" (v->counter), "=qm" (c)
-                     : "m" (v->counter) : "memory");
-        return c != 0;
-}
-
-/**
- * atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic64_inc_and_test(atomic64_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "incq %0; sete %1"
-                     : "=m" (v->counter), "=qm" (c)
-                     : "m" (v->counter) : "memory");
-        return c != 0;
-}
-
-/**
- * atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic64_add_negative(long i, atomic64_t *v)
-{
-        unsigned char c;
-
-        asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
-                     : "=m" (v->counter), "=qm" (c)
-                     : "er" (i), "m" (v->counter) : "memory");
-        return c;
-}
-
-/**
- * atomic64_add_return - add and return
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline long atomic64_add_return(long i, atomic64_t *v)
-{
-        long __i = i;
-        asm volatile(LOCK_PREFIX "xaddq %0, %1;"
-                     : "+r" (i), "+m" (v->counter)
-                     : : "memory");
-        return i + __i;
-}
-
-static inline long atomic64_sub_return(long i, atomic64_t *v)
-{
-        return atomic64_add_return(-i, v);
-}
-
-#define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
-#define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
-
-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
-{
-        return cmpxchg(&v->counter, old, new);
-}
-
-static inline long atomic64_xchg(atomic64_t *v, long new)
-{
-        return xchg(&v->counter, new);
-}
-
-static inline long atomic_cmpxchg(atomic_t *v, int old, int new)
-{
-        return cmpxchg(&v->counter, old, new);
-}
-
-static inline long atomic_xchg(atomic_t *v, int new)
-{
-        return xchg(&v->counter, new);
-}
-
-/**
- * atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
-{
-        int c, old;
-        c = atomic_read(v);
-        for (;;) {
-                if (unlikely(c == (u)))
-                        break;
-                old = atomic_cmpxchg((v), c, c + (a));
-                if (likely(old == c))
-                        break;
-                c = old;
-        }
-        return c != (u);
-}
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-        long c, old;
-        c = atomic64_read(v);
-        for (;;) {
-                if (unlikely(c == (u)))
-                        break;
-                old = atomic64_cmpxchg((v), c, c + (a));
-                if (likely(old == c))
-                        break;
-                c = old;
-        }
-        return c != (u);
-}
-
-/**
- * atomic_inc_short - increment of a short integer
- * @v: pointer to type int
- *
- * Atomically adds 1 to @v
- * Returns the new value of @u
- */
-static inline short int atomic_inc_short(short int *v)
-{
-        asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
-        return *v;
-}
-
-/**
- * atomic_or_long - OR of two long integers
- * @v1: pointer to type unsigned long
- * @v2: pointer to type unsigned long
- *
- * Atomically ORs @v1 and @v2
- * Returns the result of the OR
- */
-static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
-{
-        asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr)                                   \
-        asm volatile(LOCK_PREFIX "andl %0,%1"                           \
-                     : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr)                                     \
-        asm volatile(LOCK_PREFIX "orl %0,%1"                            \
-                     : : "r" ((unsigned)(mask)), "m" (*(addr))          \
-                     : "memory")
-
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec()     barrier()
-#define smp_mb__after_atomic_dec()      barrier()
-#define smp_mb__before_atomic_inc()     barrier()
-#define smp_mb__after_atomic_inc()      barrier()
-
-#include <asm-generic/atomic-long.h>
-#endif /* _ASM_X86_ATOMIC_64_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index d9cf1cd156d2..f654d1bb17fb 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -22,14 +22,14 @@ do {								\
                      ".popsection"                              \
                      : : "i" (__FILE__), "i" (__LINE__),        \
                      "i" (sizeof(struct bug_entry)));           \
-        for (;;) ;                                              \
+        unreachable();                                          \
 } while (0)
 
 #else
 #define BUG()                                                   \
 do {                                                            \
         asm volatile("ud2");                                    \
-        for (;;) ;                                              \
+        unreachable();                                          \
 } while (0)
 #endif
 
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index 549860d3be8f..2f9047cfaaca 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -9,12 +9,13 @@
 
 #define __read_mostly __attribute__((__section__(".data.read_mostly")))
 
+#define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT
+#define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT)
+
 #ifdef CONFIG_X86_VSMP
-/* vSMP Internode cacheline shift */
-#define INTERNODE_CACHE_SHIFT (12)
 #ifdef CONFIG_SMP
 #define __cacheline_aligned_in_smp                                      \
-        __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))      \
+        __attribute__((__aligned__(INTERNODE_CACHE_BYTES)))             \
         __page_aligned_data
 #endif
 #endif
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index b54f6afe7ec4..634c40a739a6 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -12,6 +12,7 @@ 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) { }
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
 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) { }
@@ -176,6 +177,7 @@ void clflush_cache_range(void *addr, unsigned int size);
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
+extern int kernel_set_to_readonly;
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);
 #else
diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h
index b03bedb62aa7..0918654305af 100644
--- a/arch/x86/include/asm/calgary.h
+++ b/arch/x86/include/asm/calgary.h
@@ -62,10 +62,8 @@ struct cal_chipset_ops {
 extern int use_calgary;
 
 #ifdef CONFIG_CALGARY_IOMMU
-extern int calgary_iommu_init(void);
 extern void detect_calgary(void);
 #else
-static inline int calgary_iommu_init(void) { return 1; }
 static inline void detect_calgary(void) { return; }
 #endif
 
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index ee1931be6593..ffb9bb6b6c37 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -8,14 +8,50 @@
  *       you need to test for the feature in boot_cpu_data.
  */
 
-#define xchg(ptr, v)                                                    \
-        ((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), sizeof(*(ptr))))
+extern void __xchg_wrong_size(void);
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ *        but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
 
 struct __xchg_dummy {
         unsigned long a[100];
 };
 #define __xg(x) ((struct __xchg_dummy *)(x))
 
+#define __xchg(x, ptr, size)                                            \
+({                                                                      \
+        __typeof(*(ptr)) __x = (x);                                     \
+        switch (size) {                                                 \
+        case 1:                                                         \
+                asm volatile("xchgb %b0,%1"                             \
+                             : "=q" (__x)                               \
+                             : "m" (*__xg(ptr)), "0" (__x)              \
+                             : "memory");                               \
+                break;                                                  \
+        case 2:                                                         \
+                asm volatile("xchgw %w0,%1"                             \
+                             : "=r" (__x)                               \
+                             : "m" (*__xg(ptr)), "0" (__x)              \
+                             : "memory");                               \
+                break;                                                  \
+        case 4:                                                         \
+                asm volatile("xchgl %0,%1"                              \
+                             : "=r" (__x)                               \
+                             : "m" (*__xg(ptr)), "0" (__x)              \
+                             : "memory");                               \
+                break;                                                  \
+        default:                                                        \
+                __xchg_wrong_size();                                    \
+        }                                                               \
+        __x;                                                            \
+})
+
+#define xchg(ptr, v)                                                    \
+        __xchg((v), (ptr), sizeof(*ptr))
+
 /*
  * The semantics of XCHGCMP8B are a bit strange, this is why
  * there is a loop and the loading of %%eax and %%edx has to
@@ -71,57 +107,63 @@ static inline void __set_64bit_var(unsigned long long *ptr,
                        (unsigned int)((value) >> 32))                   \
          : __set_64bit(ptr, ll_low((value)), ll_high((value))))
 
-/*
- * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
- * Note 2: xchg has side effect, so that attribute volatile is necessary,
- *        but generally the primitive is invalid, *ptr is output argument. --ANK
- */
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
-                                   int size)
-{
-        switch (size) {
-        case 1:
-                asm volatile("xchgb %b0,%1"
-                             : "=q" (x)
-                             : "m" (*__xg(ptr)), "0" (x)
-                             : "memory");
-                break;
-        case 2:
-                asm volatile("xchgw %w0,%1"
-                             : "=r" (x)
-                             : "m" (*__xg(ptr)), "0" (x)
-                             : "memory");
-                break;
-        case 4:
-                asm volatile("xchgl %0,%1"
-                             : "=r" (x)
-                             : "m" (*__xg(ptr)), "0" (x)
-                             : "memory");
-                break;
-        }
-        return x;
-}
+extern void __cmpxchg_wrong_size(void);
 
 /*
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
+#define __raw_cmpxchg(ptr, old, new, size, lock)                        \
+({                                                                      \
+        __typeof__(*(ptr)) __ret;                                       \
+        __typeof__(*(ptr)) __old = (old);                               \
+        __typeof__(*(ptr)) __new = (new);                               \
+        switch (size) {                                                 \
+        case 1:                                                         \
+                asm volatile(lock "cmpxchgb %b1,%2"                     \
+                             : "=a"(__ret)                              \
+                             : "q"(__new), "m"(*__xg(ptr)), "0"(__old)  \
+                             : "memory");                               \
+                break;                                                  \
+        case 2:                                                         \
+                asm volatile(lock "cmpxchgw %w1,%2"                     \
+                             : "=a"(__ret)                              \
+                             : "r"(__new), "m"(*__xg(ptr)), "0"(__old)  \
+                             : "memory");                               \
+                break;                                                  \
+        case 4:                                                         \
+                asm volatile(lock "cmpxchgl %1,%2"                      \
+                             : "=a"(__ret)                              \
+                             : "r"(__new), "m"(*__xg(ptr)), "0"(__old)  \
+                             : "memory");                               \
+                break;                                                  \
+        default:                                                        \
+                __cmpxchg_wrong_size();                                 \
+        }                                                               \
+        __ret;                                                          \
+})
+
+#define __cmpxchg(ptr, old, new, size)                                  \
+        __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
+
+#define __sync_cmpxchg(ptr, old, new, size)                             \
+        __raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
+
+#define __cmpxchg_local(ptr, old, new, size)                            \
+        __raw_cmpxchg((ptr), (old), (new), (size), "")
 
 #ifdef CONFIG_X86_CMPXCHG
 #define __HAVE_ARCH_CMPXCHG 1
-#define cmpxchg(ptr, o, n)                                              \
-        ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),       \
-                                       (unsigned long)(n),              \
-                                       sizeof(*(ptr))))
-#define sync_cmpxchg(ptr, o, n)                                         \
-        ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),  \
-                                            (unsigned long)(n),         \
-                                            sizeof(*(ptr))))
-#define cmpxchg_local(ptr, o, n)                                        \
-        ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \
-                                             (unsigned long)(n),        \
-                                             sizeof(*(ptr))))
+
+#define cmpxchg(ptr, old, new)                                          \
+        __cmpxchg((ptr), (old), (new), sizeof(*ptr))
+
+#define sync_cmpxchg(ptr, old, new)                                     \
+        __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+
+#define cmpxchg_local(ptr, old, new)                                    \
+        __cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
 #endif
 
 #ifdef CONFIG_X86_CMPXCHG64
@@ -133,94 +175,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
                                                (unsigned long long)(n)))
 #endif
 
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-                                      unsigned long new, int size)
-{
-        unsigned long prev;
-        switch (size) {
-        case 1:
-                asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2"
-                             : "=a"(prev)
-                             : "q"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 2:
-                asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 4:
-                asm volatile(LOCK_PREFIX "cmpxchgl %1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        }
-        return old;
-}
-
-/*
- * Always use locked operations when touching memory shared with a
- * hypervisor, since the system may be SMP even if the guest kernel
- * isn't.
- */
-static inline unsigned long __sync_cmpxchg(volatile void *ptr,
-                                           unsigned long old,
-                                           unsigned long new, int size)
-{
-        unsigned long prev;
-        switch (size) {
-        case 1:
-                asm volatile("lock; cmpxchgb %b1,%2"
-                             : "=a"(prev)
-                             : "q"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 2:
-                asm volatile("lock; cmpxchgw %w1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 4:
-                asm volatile("lock; cmpxchgl %1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        }
-        return old;
-}
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-                                            unsigned long old,
-                                            unsigned long new, int size)
-{
-        unsigned long prev;
-        switch (size) {
-        case 1:
-                asm volatile("cmpxchgb %b1,%2"
-                             : "=a"(prev)
-                             : "q"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 2:
-                asm volatile("cmpxchgw %w1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 4:
-                asm volatile("cmpxchgl %1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        }
-        return old;
-}
-
 static inline unsigned long long __cmpxchg64(volatile void *ptr,
                                              unsigned long long old,
                                              unsigned long long new)
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 52de72e0de8c..485ae415faec 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -3,9 +3,6 @@
 
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
-#define xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), \
-                                                 (ptr), sizeof(*(ptr))))
-
 #define __xg(x) ((volatile long *)(x))
 
 static inline void set_64bit(volatile unsigned long *ptr, unsigned long val)
@@ -15,167 +12,118 @@ static inline void set_64bit(volatile unsigned long *ptr, unsigned long val)
 
 #define _set_64bit set_64bit
 
+extern void __xchg_wrong_size(void);
+extern void __cmpxchg_wrong_size(void);
+
 /*
  * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
  * Note 2: xchg has side effect, so that attribute volatile is necessary,
  *        but generally the primitive is invalid, *ptr is output argument. --ANK
  */
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
-                                   int size)
-{
-        switch (size) {
-        case 1:
-                asm volatile("xchgb %b0,%1"
-                             : "=q" (x)
-                             : "m" (*__xg(ptr)), "0" (x)
-                             : "memory");
-                break;
-        case 2:
-                asm volatile("xchgw %w0,%1"
-                             : "=r" (x)
-                             : "m" (*__xg(ptr)), "0" (x)
-                             : "memory");
-                break;
-        case 4:
-                asm volatile("xchgl %k0,%1"
-                             : "=r" (x)
-                             : "m" (*__xg(ptr)), "0" (x)
-                             : "memory");
-                break;
-        case 8:
-                asm volatile("xchgq %0,%1"
-                             : "=r" (x)
-                             : "m" (*__xg(ptr)), "0" (x)
-                             : "memory");
-                break;
-        }
-        return x;
-}
+#define __xchg(x, ptr, size)                                            \
+({                                                                      \
+        __typeof(*(ptr)) __x = (x);                                     \
+        switch (size) {                                                 \
+        case 1:                                                         \
+                asm volatile("xchgb %b0,%1"                             \
+                             : "=q" (__x)                               \
+                             : "m" (*__xg(ptr)), "0" (__x)              \
+                             : "memory");                               \
+                break;                                                  \
+        case 2:                                                         \
+                asm volatile("xchgw %w0,%1"                             \
+                             : "=r" (__x)                               \
+                             : "m" (*__xg(ptr)), "0" (__x)              \
+                             : "memory");                               \
+                break;                                                  \
+        case 4:                                                         \
+                asm volatile("xchgl %k0,%1"                             \
+                             : "=r" (__x)                               \
+                             : "m" (*__xg(ptr)), "0" (__x)              \
+                             : "memory");                               \
+                break;                                                  \
+        case 8:                                                         \
+                asm volatile("xchgq %0,%1"                              \
+                             : "=r" (__x)                               \
+                             : "m" (*__xg(ptr)), "0" (__x)              \
+                             : "memory");                               \
+                break;                                                  \
+        default:                                                        \
+                __xchg_wrong_size();                                    \
+        }                                                               \
+        __x;                                                            \
+})
+
+#define xchg(ptr, v)                                                    \
+        __xchg((v), (ptr), sizeof(*ptr))
+
+#define __HAVE_ARCH_CMPXCHG 1
 
 /*
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
+#define __raw_cmpxchg(ptr, old, new, size, lock)                        \
+({                                                                      \
+        __typeof__(*(ptr)) __ret;                                       \
+        __typeof__(*(ptr)) __old = (old);                               \
+        __typeof__(*(ptr)) __new = (new);                               \
+        switch (size) {                                                 \
+        case 1:                                                         \
+                asm volatile(lock "cmpxchgb %b1,%2"                     \
+                             : "=a"(__ret)                              \
+                             : "q"(__new), "m"(*__xg(ptr)), "0"(__old)  \
+                             : "memory");                               \
+                break;                                                  \
+        case 2:                                                         \
+                asm volatile(lock "cmpxchgw %w1,%2"                     \
+                             : "=a"(__ret)                              \
+                             : "r"(__new), "m"(*__xg(ptr)), "0"(__old)  \
+                             : "memory");                               \
+                break;                                                  \
+        case 4:                                                         \
+                asm volatile(lock "cmpxchgl %k1,%2"                     \
+                             : "=a"(__ret)                              \
+                             : "r"(__new), "m"(*__xg(ptr)), "0"(__old)  \
+                             : "memory");                               \
+                break;                                                  \
+        case 8:                                                         \
+                asm volatile(lock "cmpxchgq %1,%2"                      \
+                             : "=a"(__ret)                              \
+                             : "r"(__new), "m"(*__xg(ptr)), "0"(__old)  \
+                             : "memory");                               \
+                break;                                                  \
+        default:                                                        \
+                __cmpxchg_wrong_size();                                 \
+        }                                                               \
+        __ret;                                                          \
+})
 
-#define __HAVE_ARCH_CMPXCHG 1
+#define __cmpxchg(ptr, old, new, size)                                  \
+        __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
 
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-                                      unsigned long new, int size)
-{
-        unsigned long prev;
-        switch (size) {
-        case 1:
-                asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2"
-                             : "=a"(prev)
-                             : "q"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 2:
-                asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 4:
-                asm volatile(LOCK_PREFIX "cmpxchgl %k1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 8:
-                asm volatile(LOCK_PREFIX "cmpxchgq %1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        }
-        return old;
-}
+#define __sync_cmpxchg(ptr, old, new, size)                             \
+        __raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
 
-/*
- * Always use locked operations when touching memory shared with a
- * hypervisor, since the system may be SMP even if the guest kernel
- * isn't.
- */
-static inline unsigned long __sync_cmpxchg(volatile void *ptr,
-                                           unsigned long old,
-                                           unsigned long new, int size)
-{
-        unsigned long prev;
-        switch (size) {
-        case 1:
-                asm volatile("lock; cmpxchgb %b1,%2"
-                             : "=a"(prev)
-                             : "q"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 2:
-                asm volatile("lock; cmpxchgw %w1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 4:
-                asm volatile("lock; cmpxchgl %1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        }
-        return old;
-}
+#define __cmpxchg_local(ptr, old, new, size)                            \
+        __raw_cmpxchg((ptr), (old), (new), (size), "")
 
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-                                            unsigned long old,
-                                            unsigned long new, int size)
-{
-        unsigned long prev;
-        switch (size) {
-        case 1:
-                asm volatile("cmpxchgb %b1,%2"
-                             : "=a"(prev)
-                             : "q"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 2:
-                asm volatile("cmpxchgw %w1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 4:
-                asm volatile("cmpxchgl %k1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        case 8:
-                asm volatile("cmpxchgq %1,%2"
-                             : "=a"(prev)
-                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
-                             : "memory");
-                return prev;
-        }
-        return old;
-}
+#define cmpxchg(ptr, old, new)                                          \
+        __cmpxchg((ptr), (old), (new), sizeof(*ptr))
+
+#define sync_cmpxchg(ptr, old, new)                                     \
+        __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+
+#define cmpxchg_local(ptr, old, new)                                    \
+        __cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
 
-#define cmpxchg(ptr, o, n)                                              \
-        ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),       \
-                                       (unsigned long)(n), sizeof(*(ptr))))
 #define cmpxchg64(ptr, o, n)                                            \
 ({                                                                      \
         BUILD_BUG_ON(sizeof(*(ptr)) != 8);                              \
         cmpxchg((ptr), (o), (n));                                       \
 })
-#define cmpxchg_local(ptr, o, n)                                        \
-        ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \
-                                             (unsigned long)(n),        \
-                                             sizeof(*(ptr))))
-#define sync_cmpxchg(ptr, o, n)                                         \
-        ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),  \
-                                            (unsigned long)(n),         \
-                                            sizeof(*(ptr))))
+
 #define cmpxchg64_local(ptr, o, n)                                      \
 ({                                                                      \
         BUILD_BUG_ON(sizeof(*(ptr)) != 8);                              \
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 9a9c7bdc923d..306160e58b48 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -8,7 +8,8 @@
 #include <linux/sched.h>
 #include <asm/user32.h>
 
-#define COMPAT_USER_HZ  100
+#define COMPAT_USER_HZ          100
+#define COMPAT_UTS_MACHINE      "i686\0\0"
 
 typedef u32             compat_size_t;
 typedef s32             compat_ssize_t;
diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
deleted file mode 100644
index d96c1ee3a95c..000000000000
--- a/arch/x86/include/asm/cpu_debug.h
+++ /dev/null
@@ -1,127 +0,0 @@
-#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)
-
-#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      */
-};
-
-#endif /* _ASM_X86_CPU_DEBUG_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 9cfc88b97742..0cd82d068613 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -153,6 +153,7 @@
 #define X86_FEATURE_SSE5        (6*32+11) /* SSE-5 */
 #define X86_FEATURE_SKINIT      (6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT         (6*32+13) /* Watchdog timer */
+#define X86_FEATURE_NODEID_MSR  (6*32+19) /* NodeId MSR */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -167,6 +168,10 @@
 #define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
 #define X86_FEATURE_EPT         (8*32+ 3) /* Intel Extended Page Table */
 #define X86_FEATURE_VPID        (8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_NPT         (8*32+5)  /* AMD Nested Page Table support */
+#define X86_FEATURE_LBRV        (8*32+6)  /* AMD LBR Virtualization support */
+#define X86_FEATURE_SVML        (8*32+7)  /* "svm_lock" AMD SVM locking MSR */
+#define X86_FEATURE_NRIPS       (8*32+8)  /* "nrip_save" AMD SVM next_rip save */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
@@ -248,6 +253,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_x2apic          boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave           boot_cpu_has(X86_FEATURE_XSAVE)
 #define cpu_has_hypervisor      boot_cpu_has(X86_FEATURE_HYPERVISOR)
+#define cpu_has_pclmulqdq       boot_cpu_has(X86_FEATURE_PCLMULQDQ)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg         1
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 3ea6f37be9e2..b81002f23614 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -14,10 +14,14 @@
    which debugging register was responsible for the trap.  The other bits
    are either reserved or not of interest to us. */
 
+/* Define reserved bits in DR6 which are always set to 1 */
+#define DR6_RESERVED    (0xFFFF0FF0)
+
 #define DR_TRAP0        (0x1)           /* db0 */
 #define DR_TRAP1        (0x2)           /* db1 */
 #define DR_TRAP2        (0x4)           /* db2 */
 #define DR_TRAP3        (0x8)           /* db3 */
+#define DR_TRAP_BITS    (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)
 
 #define DR_STEP         (0x4000)        /* single-step */
 #define DR_SWITCH       (0x8000)        /* task switch */
@@ -49,6 +53,8 @@
 
 #define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
 #define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
+#define DR_LOCAL_ENABLE (0x1)      /* Local enable for reg 0 */
+#define DR_GLOBAL_ENABLE (0x2)     /* Global enable for reg 0 */
 #define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
 
 #define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
@@ -67,4 +73,34 @@
 #define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
 #define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
 
+/*
+ * HW breakpoint additions
+ */
+#ifdef __KERNEL__
+
+DECLARE_PER_CPU(unsigned long, cpu_dr7);
+
+static inline void hw_breakpoint_disable(void)
+{
+        /* Zero the control register for HW Breakpoint */
+        set_debugreg(0UL, 7);
+
+        /* Zero-out the individual HW breakpoint address registers */
+        set_debugreg(0UL, 0);
+        set_debugreg(0UL, 1);
+        set_debugreg(0UL, 2);
+        set_debugreg(0UL, 3);
+}
+
+static inline int hw_breakpoint_active(void)
+{
+        return __get_cpu_var(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
+}
+
+extern void aout_dump_debugregs(struct user *dump);
+
+extern void hw_breakpoint_restore(void);
+
+#endif  /* __KERNEL__ */
+
 #endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index 9d6684849fd9..278441f39856 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -12,9 +12,9 @@
 #include <linux/types.h>
 
 /*
- * FIXME: Acessing the desc_struct through its fields is more elegant,
+ * FIXME: Accessing the desc_struct through its fields is more elegant,
  * and should be the one valid thing to do. However, a lot of open code
- * still touches the a and b acessors, and doing this allow us to do it
+ * still touches the a and b accessors, and doing this allow us to do it
  * incrementally. We keep the signature as a struct, rather than an union,
  * so we can get rid of it transparently in the future -- glommer
  */
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index cee34e9ca45b..029f230ab637 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,7 +8,7 @@ struct dev_archdata {
 #ifdef CONFIG_X86_64
 struct dma_map_ops *dma_ops;
 #endif
-#ifdef CONFIG_DMAR
+#if defined(CONFIG_DMAR) || defined(CONFIG_AMD_IOMMU)
         void *iommu; /* hook for IOMMU specific extension */
 #endif
 };
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 6a25d5d42836..ac91eed21061 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -20,7 +20,8 @@
 # define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
 #endif
 
-extern dma_addr_t bad_dma_address;
+#define DMA_ERROR_CODE  0
+
 extern int iommu_merge;
 extern struct device x86_dma_fallback_dev;
 extern int panic_on_overflow;
@@ -48,7 +49,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
         if (ops->mapping_error)
                 return ops->mapping_error(dev, dma_addr);
 
-        return (dma_addr == bad_dma_address);
+        return (dma_addr == DMA_ERROR_CODE);
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
@@ -66,7 +67,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
         if (!dev->dma_mask)
                 return 0;
 
-        return addr + size <= *dev->dma_mask;
+        return addr + size - 1 <= *dev->dma_mask;
 }
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 40b4e614fe71..0e22296790d3 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -61,6 +61,12 @@ struct e820map {
         struct e820entry map[E820_X_MAX];
 };
 
+#define ISA_START_ADDRESS       0xa0000
+#define ISA_END_ADDRESS         0x100000
+
+#define BIOS_BEGIN              0x000a0000
+#define BIOS_END                0x00100000
+
 #ifdef __KERNEL__
 /* see comment in arch/x86/kernel/e820.c */
 extern struct e820map e820;
@@ -105,11 +111,8 @@ extern unsigned long end_user_pfn;
 
 extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
 extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+#include <linux/early_res.h>
 
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
@@ -126,15 +129,18 @@ extern void e820_reserve_resources(void);
 extern void e820_reserve_resources_late(void);
 extern void setup_memory_map(void);
 extern char *default_machine_specific_memory_setup(void);
-#endif /* __KERNEL__ */
-#endif /* __ASSEMBLY__ */
 
-#define ISA_START_ADDRESS       0xa0000
-#define ISA_END_ADDRESS         0x100000
-#define is_ISA_range(s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS)
+/*
+ * Returns true iff the specified range [s,e) is completely contained inside
+ * the ISA region.
+ */
+static inline bool is_ISA_range(u64 s, u64 e)
+{
+        return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS;
+}
 
-#define BIOS_BEGIN              0x000a0000
-#define BIOS_END                0x00100000
+#endif /* __KERNEL__ */
+#endif /* __ASSEMBLY__ */
 
 #ifdef __KERNEL__
 #include <linux/ioport.h>
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 456a304b8172..f2ad2163109d 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -157,19 +157,6 @@ do {						\
 
 #define compat_elf_check_arch(x)        elf_check_arch_ia32(x)
 
-static inline void start_ia32_thread(struct pt_regs *regs, u32 ip, u32 sp)
-{
-        loadsegment(fs, 0);
-        loadsegment(ds, __USER32_DS);
-        loadsegment(es, __USER32_DS);
-        load_gs_index(0);
-        regs->ip = ip;
-        regs->sp = sp;
-        regs->flags = X86_EFLAGS_IF;
-        regs->cs = __USER32_CS;
-        regs->ss = __USER32_DS;
-}
-
 static inline void elf_common_init(struct thread_struct *t,
                                    struct pt_regs *regs, const u16 ds)
 {
@@ -183,28 +170,16 @@ static inline void elf_common_init(struct thread_struct *t,
 }
 
 #define ELF_PLAT_INIT(_r, load_addr)                    \
-do {                                                    \
-        elf_common_init(&current->thread, _r, 0);       \
-        clear_thread_flag(TIF_IA32);                    \
-} while (0)
+        elf_common_init(&current->thread, _r, 0)
 
 #define COMPAT_ELF_PLAT_INIT(regs, load_addr)           \
         elf_common_init(&current->thread, regs, __USER_DS)
 
-#define compat_start_thread(regs, ip, sp)               \
-do {                                                    \
-        start_ia32_thread(regs, ip, sp);                \
-        set_fs(USER_DS);                                \
-} while (0)
+void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
+#define compat_start_thread start_thread_ia32
 
-#define COMPAT_SET_PERSONALITY(ex)                      \
-do {                                                    \
-        if (test_thread_flag(TIF_IA32))                 \
-                clear_thread_flag(TIF_ABI_PENDING);     \
-        else                                            \
-                set_thread_flag(TIF_ABI_PENDING);       \
-        current->personality |= force_personality32;    \
-} while (0)
+void set_personality_ia32(void);
+#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32()
 
 #define COMPAT_ELF_PLATFORM                     ("i686")
 
@@ -255,7 +230,6 @@ extern int force_personality32;
 #endif /* !CONFIG_X86_32 */
 
 #define CORE_DUMP_USE_REGSET
-#define USE_ELF_CORE_DUMP
 #define ELF_EXEC_PAGESIZE       4096
 
 /* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 19e22e3784d0..5d07dea2ebb8 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -35,7 +35,7 @@ BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
                  smp_invalidate_interrupt)
 #endif
 
-BUILD_INTERRUPT(generic_interrupt, GENERIC_INTERRUPT_VECTOR)
+BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
 
 /*
  * every pentium local APIC has two 'local interrupts', with a
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
index 53018464aea6..2519d0679d99 100644
--- a/arch/x86/include/asm/fb.h
+++ b/arch/x86/include/asm/fb.h
@@ -12,10 +12,6 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
                 pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
 }
 
-#ifdef CONFIG_X86_32
 extern int fb_is_primary_device(struct fb_info *info);
-#else
-static inline int fb_is_primary_device(struct fb_info *info) { return 0; }
-#endif
 
 #endif /* _ASM_X86_FB_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 14f9890eb495..d07b44f7d1dc 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -82,6 +82,9 @@ enum fixed_addresses {
 #endif
         FIX_DBGP_BASE,
         FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+        FIX_OHCI1394_BASE,
+#endif
 #ifdef CONFIG_X86_LOCAL_APIC
         FIX_APIC_BASE,  /* local (CPU) APIC) -- required for SMP or not */
 #endif
@@ -118,17 +121,20 @@ enum 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:
+         * If necessary 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_PROVIDE_OHCI1394_DMA_INIT
-        FIX_OHCI1394_BASE,
-#endif
+#define TOTAL_FIX_BTMAPS        (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+        FIX_BTMAP_END =
+         (__end_of_permanent_fixed_addresses ^
+          (__end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS - 1)) &
+         -PTRS_PER_PTE
+         ? __end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS -
+           (__end_of_permanent_fixed_addresses & (TOTAL_FIX_BTMAPS - 1))
+         : __end_of_permanent_fixed_addresses,
+        FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
 #ifdef CONFIG_X86_32
         FIX_WP_TEST,
 #endif
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 6cfdafa409d8..4ac5b0f33fc1 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -35,8 +35,7 @@ extern int gart_iommu_aperture_allowed;
 extern int gart_iommu_aperture_disabled;
 
 extern void early_gart_iommu_check(void);
-extern void gart_iommu_init(void);
-extern void gart_iommu_shutdown(void);
+extern int gart_iommu_init(void);
 extern void __init gart_parse_options(char *);
 extern void gart_iommu_hole_init(void);
 
@@ -48,12 +47,6 @@ extern void gart_iommu_hole_init(void);
 static inline void early_gart_iommu_check(void)
 {
 }
-static inline void gart_iommu_init(void)
-{
-}
-static inline void gart_iommu_shutdown(void)
-{
-}
 static inline void gart_parse_options(char *options)
 {
 }
diff --git a/arch/x86/include/asm/geode.h b/arch/x86/include/asm/geode.h
index ad3c2ed75481..7cd73552a4e8 100644
--- a/arch/x86/include/asm/geode.h
+++ b/arch/x86/include/asm/geode.h
@@ -12,160 +12,7 @@
 
 #include <asm/processor.h>
 #include <linux/io.h>
-
-/* Generic southbridge functions */
-
-#define GEODE_DEV_PMS 0
-#define GEODE_DEV_ACPI 1
-#define GEODE_DEV_GPIO 2
-#define GEODE_DEV_MFGPT 3
-
-extern int geode_get_dev_base(unsigned int dev);
-
-/* Useful macros */
-#define geode_pms_base()        geode_get_dev_base(GEODE_DEV_PMS)
-#define geode_acpi_base()       geode_get_dev_base(GEODE_DEV_ACPI)
-#define geode_gpio_base()       geode_get_dev_base(GEODE_DEV_GPIO)
-#define geode_mfgpt_base()      geode_get_dev_base(GEODE_DEV_MFGPT)
-
-/* MSRS */
-
-#define MSR_GLIU_P2D_RO0        0x10000029
-
-#define MSR_LX_GLD_MSR_CONFIG   0x48002001
-#define MSR_LX_MSR_PADSEL       0x48002011      /* NOT 0x48000011; the data
-                                                 * sheet has the wrong value */
-#define MSR_GLCP_SYS_RSTPLL     0x4C000014
-#define MSR_GLCP_DOTPLL         0x4C000015
-
-#define MSR_LBAR_SMB            0x5140000B
-#define MSR_LBAR_GPIO           0x5140000C
-#define MSR_LBAR_MFGPT          0x5140000D
-#define MSR_LBAR_ACPI           0x5140000E
-#define MSR_LBAR_PMS            0x5140000F
-
-#define MSR_DIVIL_SOFT_RESET    0x51400017
-
-#define MSR_PIC_YSEL_LOW        0x51400020
-#define MSR_PIC_YSEL_HIGH       0x51400021
-#define MSR_PIC_ZSEL_LOW        0x51400022
-#define MSR_PIC_ZSEL_HIGH       0x51400023
-#define MSR_PIC_IRQM_LPC        0x51400025
-
-#define MSR_MFGPT_IRQ           0x51400028
-#define MSR_MFGPT_NR            0x51400029
-#define MSR_MFGPT_SETUP         0x5140002B
-
-#define MSR_LX_SPARE_MSR        0x80000011      /* DC-specific */
-
-#define MSR_GX_GLD_MSR_CONFIG   0xC0002001
-#define MSR_GX_MSR_PADSEL       0xC0002011
-
-/* Resource Sizes */
-
-#define LBAR_GPIO_SIZE          0xFF
-#define LBAR_MFGPT_SIZE         0x40
-#define LBAR_ACPI_SIZE          0x40
-#define LBAR_PMS_SIZE           0x80
-
-/* ACPI registers (PMS block) */
-
-/*
- * PM1_EN is only valid when VSA is enabled for 16 bit reads.
- * When VSA is not enabled, *always* read both PM1_STS and PM1_EN
- * with a 32 bit read at offset 0x0
- */
-
-#define PM1_STS                 0x00
-#define PM1_EN                  0x02
-#define PM1_CNT                 0x08
-#define PM2_CNT                 0x0C
-#define PM_TMR                  0x10
-#define PM_GPE0_STS             0x18
-#define PM_GPE0_EN              0x1C
-
-/* PMC registers (PMS block) */
-
-#define PM_SSD                  0x00
-#define PM_SCXA                 0x04
-#define PM_SCYA                 0x08
-#define PM_OUT_SLPCTL           0x0C
-#define PM_SCLK                 0x10
-#define PM_SED                  0x1
-#define PM_SCXD                 0x18
-#define PM_SCYD                 0x1C
-#define PM_IN_SLPCTL            0x20
-#define PM_WKD                  0x30
-#define PM_WKXD                 0x34
-#define PM_RD                   0x38
-#define PM_WKXA                 0x3C
-#define PM_FSD                  0x40
-#define PM_TSD                  0x44
-#define PM_PSD                  0x48
-#define PM_NWKD                 0x4C
-#define PM_AWKD                 0x50
-#define PM_SSC                  0x54
-
-/* VSA2 magic values */
-
-#define VSA_VRC_INDEX           0xAC1C
-#define VSA_VRC_DATA            0xAC1E
-#define VSA_VR_UNLOCK           0xFC53  /* unlock virtual register */
-#define VSA_VR_SIGNATURE        0x0003
-#define VSA_VR_MEM_SIZE         0x0200
-#define AMD_VSA_SIG             0x4132  /* signature is ascii 'VSA2' */
-#define GSW_VSA_SIG             0x534d  /* General Software signature */
-/* GPIO */
-
-#define GPIO_OUTPUT_VAL         0x00
-#define GPIO_OUTPUT_ENABLE      0x04
-#define GPIO_OUTPUT_OPEN_DRAIN  0x08
-#define GPIO_OUTPUT_INVERT      0x0C
-#define GPIO_OUTPUT_AUX1        0x10
-#define GPIO_OUTPUT_AUX2        0x14
-#define GPIO_PULL_UP            0x18
-#define GPIO_PULL_DOWN          0x1C
-#define GPIO_INPUT_ENABLE       0x20
-#define GPIO_INPUT_INVERT       0x24
-#define GPIO_INPUT_FILTER       0x28
-#define GPIO_INPUT_EVENT_COUNT  0x2C
-#define GPIO_READ_BACK          0x30
-#define GPIO_INPUT_AUX1         0x34
-#define GPIO_EVENTS_ENABLE      0x38
-#define GPIO_LOCK_ENABLE        0x3C
-#define GPIO_POSITIVE_EDGE_EN   0x40
-#define GPIO_NEGATIVE_EDGE_EN   0x44
-#define GPIO_POSITIVE_EDGE_STS  0x48
-#define GPIO_NEGATIVE_EDGE_STS  0x4C
-
-#define GPIO_MAP_X              0xE0
-#define GPIO_MAP_Y              0xE4
-#define GPIO_MAP_Z              0xE8
-#define GPIO_MAP_W              0xEC
-
-static inline u32 geode_gpio(unsigned int nr)
-{
-        BUG_ON(nr > 28);
-        return 1 << nr;
-}
-
-extern void geode_gpio_set(u32, unsigned int);
-extern void geode_gpio_clear(u32, unsigned int);
-extern int geode_gpio_isset(u32, unsigned int);
-extern void geode_gpio_setup_event(unsigned int, int, int);
-extern void geode_gpio_set_irq(unsigned int, unsigned int);
-
-static inline void geode_gpio_event_irq(unsigned int gpio, int pair)
-{
-        geode_gpio_setup_event(gpio, pair, 0);
-}
-
-static inline void geode_gpio_event_pme(unsigned int gpio, int pair)
-{
-        geode_gpio_setup_event(gpio, pair, 1);
-}
-
-/* Specific geode tests */
+#include <linux/cs5535.h>
 
 static inline int is_geode_gx(void)
 {
@@ -186,68 +33,4 @@ static inline int is_geode(void)
         return (is_geode_gx() || is_geode_lx());
 }
 
-#ifdef CONFIG_MGEODE_LX
-extern int geode_has_vsa2(void);
-#else
-static inline int geode_has_vsa2(void)
-{
-        return 0;
-}
-#endif
-
-/* MFGPTs */
-
-#define MFGPT_MAX_TIMERS        8
-#define MFGPT_TIMER_ANY         (-1)
-
-#define MFGPT_DOMAIN_WORKING    1
-#define MFGPT_DOMAIN_STANDBY    2
-#define MFGPT_DOMAIN_ANY        (MFGPT_DOMAIN_WORKING | MFGPT_DOMAIN_STANDBY)
-
-#define MFGPT_CMP1              0
-#define MFGPT_CMP2              1
-
-#define MFGPT_EVENT_IRQ         0
-#define MFGPT_EVENT_NMI         1
-#define MFGPT_EVENT_RESET       3
-
-#define MFGPT_REG_CMP1          0
-#define MFGPT_REG_CMP2          2
-#define MFGPT_REG_COUNTER       4
-#define MFGPT_REG_SETUP         6
-
-#define MFGPT_SETUP_CNTEN       (1 << 15)
-#define MFGPT_SETUP_CMP2        (1 << 14)
-#define MFGPT_SETUP_CMP1        (1 << 13)
-#define MFGPT_SETUP_SETUP       (1 << 12)
-#define MFGPT_SETUP_STOPEN      (1 << 11)
-#define MFGPT_SETUP_EXTEN       (1 << 10)
-#define MFGPT_SETUP_REVEN       (1 << 5)
-#define MFGPT_SETUP_CLKSEL      (1 << 4)
-
-static inline void geode_mfgpt_write(int timer, u16 reg, u16 value)
-{
-        u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
-        outw(value, base + reg + (timer * 8));
-}
-
-static inline u16 geode_mfgpt_read(int timer, u16 reg)
-{
-        u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
-        return inw(base + reg + (timer * 8));
-}
-
-extern int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable);
-extern int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable);
-extern int geode_mfgpt_alloc_timer(int timer, int domain);
-
-#define geode_mfgpt_setup_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 1)
-#define geode_mfgpt_release_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 0)
-
-#ifdef CONFIG_GEODE_MFGPT_TIMER
-extern int __init mfgpt_timer_setup(void);
-#else
-static inline int mfgpt_timer_setup(void) { return 0; }
-#endif
-
 #endif /* _ASM_X86_GEODE_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 82e3e8f01043..0f8576427cfe 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -12,7 +12,7 @@ typedef struct {
         unsigned int apic_timer_irqs;   /* arch dependent */
         unsigned int irq_spurious_count;
 #endif
-        unsigned int generic_irqs;      /* arch dependent */
+        unsigned int x86_platform_ipis; /* arch dependent */
         unsigned int apic_perf_irqs;
         unsigned int apic_pending_irqs;
 #ifdef CONFIG_SMP
@@ -20,11 +20,11 @@ typedef struct {
         unsigned int irq_call_count;
         unsigned int irq_tlb_count;
 #endif
-#ifdef CONFIG_X86_MCE
+#ifdef CONFIG_X86_THERMAL_VECTOR
         unsigned int irq_thermal_count;
-# ifdef CONFIG_X86_MCE_THRESHOLD
+#endif
+#ifdef CONFIG_X86_MCE_THRESHOLD
         unsigned int irq_threshold_count;
-# endif
 #endif
 } ____cacheline_aligned irq_cpustat_t;
 
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 014c2b85ae45..a726650fc80f 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -66,10 +66,6 @@ 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
-#define kmap_atomic_pte(page, type)     kmap_atomic(page, type)
-#endif
-
 #define flush_cache_kmaps()     do { } while (0)
 
 extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn,
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 1c22cb05ad6a..1d5c08a1bdfd 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -65,11 +65,13 @@
 /* hpet memory map physical address */
 extern unsigned long hpet_address;
 extern unsigned long force_hpet_address;
+extern u8 hpet_blockid;
 extern int hpet_force_user;
+extern u8 hpet_msi_disable;
 extern int is_hpet_enabled(void);
 extern int hpet_enable(void);
 extern void hpet_disable(void);
-extern unsigned long hpet_readl(unsigned long a);
+extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
 extern void hpet_msi_unmask(unsigned int irq);
@@ -78,9 +80,9 @@ extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
 extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
 
 #ifdef CONFIG_PCI_MSI
-extern int arch_setup_hpet_msi(unsigned int irq);
+extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id);
 #else
-static inline int arch_setup_hpet_msi(unsigned int irq)
+static inline int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
         return -EINVAL;
 }
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
new file mode 100644
index 000000000000..2a1bd8f4f23a
--- /dev/null
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -0,0 +1,72 @@
+#ifndef _I386_HW_BREAKPOINT_H
+#define _I386_HW_BREAKPOINT_H
+
+#ifdef  __KERNEL__
+#define __ARCH_HW_BREAKPOINT_H
+
+/*
+ * The name should probably be something dealt in
+ * a higher level. While dealing with the user
+ * (display/resolving)
+ */
+struct arch_hw_breakpoint {
+        unsigned long   address;
+        u8              len;
+        u8              type;
+};
+
+#include <linux/kdebug.h>
+#include <linux/percpu.h>
+#include <linux/list.h>
+
+/* Available HW breakpoint length encodings */
+#define X86_BREAKPOINT_LEN_1            0x40
+#define X86_BREAKPOINT_LEN_2            0x44
+#define X86_BREAKPOINT_LEN_4            0x4c
+#define X86_BREAKPOINT_LEN_EXECUTE      0x40
+
+#ifdef CONFIG_X86_64
+#define X86_BREAKPOINT_LEN_8            0x48
+#endif
+
+/* Available HW breakpoint type encodings */
+
+/* trigger on instruction execute */
+#define X86_BREAKPOINT_EXECUTE  0x80
+/* trigger on memory write */
+#define X86_BREAKPOINT_WRITE    0x81
+/* trigger on memory read or write */
+#define X86_BREAKPOINT_RW       0x83
+
+/* Total number of available HW breakpoint registers */
+#define HBP_NUM 4
+
+struct perf_event;
+struct pmu;
+
+extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
+                                         struct task_struct *tsk);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+                                           unsigned long val, void *data);
+
+
+int arch_install_hw_breakpoint(struct perf_event *bp);
+void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+void hw_breakpoint_pmu_read(struct perf_event *bp);
+void hw_breakpoint_pmu_unthrottle(struct perf_event *bp);
+
+extern void
+arch_fill_perf_breakpoint(struct perf_event *bp);
+
+unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type);
+int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, unsigned *type);
+
+extern int arch_bp_generic_fields(int x86_len, int x86_type,
+                                  int *gen_len, int *gen_type);
+
+extern struct pmu perf_ops_bp;
+
+#endif  /* __KERNEL__ */
+#endif  /* _I386_HW_BREAKPOINT_H */
+
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 68900e7dada8..c17411503f28 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -27,7 +27,7 @@
 
 /* Interrupt handlers registered during init_IRQ */
 extern void apic_timer_interrupt(void);
-extern void generic_interrupt(void);
+extern void x86_platform_ipi(void);
 extern void error_interrupt(void);
 extern void perf_pending_interrupt(void);
 
@@ -55,13 +55,6 @@ extern void call_function_single_interrupt(void);
 
 extern void pull_timers_interrupt(void);
 
-/* PIC specific functions */
-extern void disable_8259A_irq(unsigned int irq);
-extern void enable_8259A_irq(unsigned int irq);
-extern int i8259A_irq_pending(unsigned int irq);
-extern void make_8259A_irq(unsigned int irq);
-extern void init_8259A(int aeoi);
-
 /* IOAPIC */
 #define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs))
 extern unsigned long io_apic_irqs;
@@ -81,14 +74,33 @@ static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
                                         int ioapic, int ioapic_pin,
                                         int trigger, int polarity)
 {
-        irq_attr->ioapic     = ioapic;
-        irq_attr->ioapic_pin = ioapic_pin;
-        irq_attr->trigger    = trigger;
-        irq_attr->polarity   = polarity;
+        irq_attr->ioapic        = ioapic;
+        irq_attr->ioapic_pin    = ioapic_pin;
+        irq_attr->trigger       = trigger;
+        irq_attr->polarity      = polarity;
 }
 
-extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin,
-                                        struct io_apic_irq_attr *irq_attr);
+/*
+ * This is performance-critical, we want to do it O(1)
+ *
+ * Most irqs are mapped 1:1 with pins.
+ */
+struct irq_cfg {
+        struct irq_pin_list     *irq_2_pin;
+        cpumask_var_t           domain;
+        cpumask_var_t           old_domain;
+        u8                      vector;
+        u8                      move_in_progress : 1;
+};
+
+extern struct irq_cfg *irq_cfg(unsigned int);
+extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
+extern void send_cleanup_vector(struct irq_cfg *);
+
+struct irq_desc;
+extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
+                                      unsigned int *dest_id);
+extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
 extern void enable_IO_APIC(void);
@@ -103,7 +115,7 @@ extern void eisa_set_level_irq(unsigned int irq);
 /* SMP */
 extern void smp_apic_timer_interrupt(struct pt_regs *);
 extern void smp_spurious_interrupt(struct pt_regs *);
-extern void smp_generic_interrupt(struct pt_regs *);
+extern void smp_x86_platform_ipi(struct pt_regs *);
 extern void smp_error_interrupt(struct pt_regs *);
 #ifdef CONFIG_X86_IO_APIC
 extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
@@ -124,6 +136,7 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
+extern void setup_vector_irq(int cpu);
 
 #ifdef CONFIG_X86_IO_APIC
 extern void lock_vector_lock(void);
diff --git a/arch/x86/include/asm/hyperv.h b/arch/x86/include/asm/hyperv.h
new file mode 100644
index 000000000000..e153a2b3889a
--- /dev/null
+++ b/arch/x86/include/asm/hyperv.h
@@ -0,0 +1,186 @@
+#ifndef _ASM_X86_KVM_HYPERV_H
+#define _ASM_X86_KVM_HYPERV_H
+
+#include <linux/types.h>
+
+/*
+ * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
+ * is set by CPUID(HvCpuIdFunctionVersionAndFeatures).
+ */
+#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS   0x40000000
+#define HYPERV_CPUID_INTERFACE                  0x40000001
+#define HYPERV_CPUID_VERSION                    0x40000002
+#define HYPERV_CPUID_FEATURES                   0x40000003
+#define HYPERV_CPUID_ENLIGHTMENT_INFO           0x40000004
+#define HYPERV_CPUID_IMPLEMENT_LIMITS           0x40000005
+
+/*
+ * Feature identification. EAX indicates which features are available
+ * to the partition based upon the current partition privileges.
+ */
+
+/* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */
+#define HV_X64_MSR_VP_RUNTIME_AVAILABLE         (1 << 0)
+/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
+#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE     (1 << 1)
+/*
+ * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
+ * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
+ */
+#define HV_X64_MSR_SYNIC_AVAILABLE              (1 << 2)
+/*
+ * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through
+ * HV_X64_MSR_STIMER3_COUNT) available
+ */
+#define HV_X64_MSR_SYNTIMER_AVAILABLE           (1 << 3)
+/*
+ * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR)
+ * are available
+ */
+#define HV_X64_MSR_APIC_ACCESS_AVAILABLE        (1 << 4)
+/* Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL) available*/
+#define HV_X64_MSR_HYPERCALL_AVAILABLE          (1 << 5)
+/* Access virtual processor index MSR (HV_X64_MSR_VP_INDEX) available*/
+#define HV_X64_MSR_VP_INDEX_AVAILABLE           (1 << 6)
+/* Virtual system reset MSR (HV_X64_MSR_RESET) is available*/
+#define HV_X64_MSR_RESET_AVAILABLE              (1 << 7)
+ /*
+  * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE,
+  * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE,
+  * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available
+  */
+#define HV_X64_MSR_STAT_PAGES_AVAILABLE         (1 << 8)
+
+/*
+ * Feature identification: EBX indicates which flags were specified at
+ * partition creation. The format is the same as the partition creation
+ * flag structure defined in section Partition Creation Flags.
+ */
+#define HV_X64_CREATE_PARTITIONS                (1 << 0)
+#define HV_X64_ACCESS_PARTITION_ID              (1 << 1)
+#define HV_X64_ACCESS_MEMORY_POOL               (1 << 2)
+#define HV_X64_ADJUST_MESSAGE_BUFFERS           (1 << 3)
+#define HV_X64_POST_MESSAGES                    (1 << 4)
+#define HV_X64_SIGNAL_EVENTS                    (1 << 5)
+#define HV_X64_CREATE_PORT                      (1 << 6)
+#define HV_X64_CONNECT_PORT                     (1 << 7)
+#define HV_X64_ACCESS_STATS                     (1 << 8)
+#define HV_X64_DEBUGGING                        (1 << 11)
+#define HV_X64_CPU_POWER_MANAGEMENT             (1 << 12)
+#define HV_X64_CONFIGURE_PROFILER               (1 << 13)
+
+/*
+ * Feature identification. EDX indicates which miscellaneous features
+ * are available to the partition.
+ */
+/* The MWAIT instruction is available (per section MONITOR / MWAIT) */
+#define HV_X64_MWAIT_AVAILABLE                          (1 << 0)
+/* Guest debugging support is available */
+#define HV_X64_GUEST_DEBUGGING_AVAILABLE                (1 << 1)
+/* Performance Monitor support is available*/
+#define HV_X64_PERF_MONITOR_AVAILABLE                   (1 << 2)
+/* Support for physical CPU dynamic partitioning events is available*/
+#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE       (1 << 3)
+/*
+ * Support for passing hypercall input parameter block via XMM
+ * registers is available
+ */
+#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE           (1 << 4)
+/* Support for a virtual guest idle state is available */
+#define HV_X64_GUEST_IDLE_STATE_AVAILABLE               (1 << 5)
+
+/*
+ * Implementation recommendations. Indicates which behaviors the hypervisor
+ * recommends the OS implement for optimal performance.
+ */
+ /*
+  * Recommend using hypercall for address space switches rather
+  * than MOV to CR3 instruction
+  */
+#define HV_X64_MWAIT_RECOMMENDED                (1 << 0)
+/* Recommend using hypercall for local TLB flushes rather
+ * than INVLPG or MOV to CR3 instructions */
+#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED      (1 << 1)
+/*
+ * Recommend using hypercall for remote TLB flushes rather
+ * than inter-processor interrupts
+ */
+#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED     (1 << 2)
+/*
+ * Recommend using MSRs for accessing APIC registers
+ * EOI, ICR and TPR rather than their memory-mapped counterparts
+ */
+#define HV_X64_APIC_ACCESS_RECOMMENDED          (1 << 3)
+/* Recommend using the hypervisor-provided MSR to initiate a system RESET */
+#define HV_X64_SYSTEM_RESET_RECOMMENDED         (1 << 4)
+/*
+ * Recommend using relaxed timing for this partition. If used,
+ * the VM should disable any watchdog timeouts that rely on the
+ * timely delivery of external interrupts
+ */
+#define HV_X64_RELAXED_TIMING_RECOMMENDED       (1 << 5)
+
+/* MSR used to identify the guest OS. */
+#define HV_X64_MSR_GUEST_OS_ID                  0x40000000
+
+/* MSR used to setup pages used to communicate with the hypervisor. */
+#define HV_X64_MSR_HYPERCALL                    0x40000001
+
+/* MSR used to provide vcpu index */
+#define HV_X64_MSR_VP_INDEX                     0x40000002
+
+/* Define the virtual APIC registers */
+#define HV_X64_MSR_EOI                          0x40000070
+#define HV_X64_MSR_ICR                          0x40000071
+#define HV_X64_MSR_TPR                          0x40000072
+#define HV_X64_MSR_APIC_ASSIST_PAGE             0x40000073
+
+/* Define synthetic interrupt controller model specific registers. */
+#define HV_X64_MSR_SCONTROL                     0x40000080
+#define HV_X64_MSR_SVERSION                     0x40000081
+#define HV_X64_MSR_SIEFP                        0x40000082
+#define HV_X64_MSR_SIMP                         0x40000083
+#define HV_X64_MSR_EOM                          0x40000084
+#define HV_X64_MSR_SINT0                        0x40000090
+#define HV_X64_MSR_SINT1                        0x40000091
+#define HV_X64_MSR_SINT2                        0x40000092
+#define HV_X64_MSR_SINT3                        0x40000093
+#define HV_X64_MSR_SINT4                        0x40000094
+#define HV_X64_MSR_SINT5                        0x40000095
+#define HV_X64_MSR_SINT6                        0x40000096
+#define HV_X64_MSR_SINT7                        0x40000097
+#define HV_X64_MSR_SINT8                        0x40000098
+#define HV_X64_MSR_SINT9                        0x40000099
+#define HV_X64_MSR_SINT10                       0x4000009A
+#define HV_X64_MSR_SINT11                       0x4000009B
+#define HV_X64_MSR_SINT12                       0x4000009C
+#define HV_X64_MSR_SINT13                       0x4000009D
+#define HV_X64_MSR_SINT14                       0x4000009E
+#define HV_X64_MSR_SINT15                       0x4000009F
+
+
+#define HV_X64_MSR_HYPERCALL_ENABLE             0x00000001
+#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12
+#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK  \
+                (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
+
+/* Declare the various hypercall operations. */
+#define HV_X64_HV_NOTIFY_LONG_SPIN_WAIT         0x0008
+
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE              0x00000001
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT       12
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_MASK        \
+                (~((1ull << HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+#define HV_PROCESSOR_POWER_STATE_C0             0
+#define HV_PROCESSOR_POWER_STATE_C1             1
+#define HV_PROCESSOR_POWER_STATE_C2             2
+#define HV_PROCESSOR_POWER_STATE_C3             3
+
+/* hypercall status code */
+#define HV_STATUS_SUCCESS                       0
+#define HV_STATUS_INVALID_HYPERCALL_CODE        2
+#define HV_STATUS_INVALID_HYPERCALL_INPUT       3
+#define HV_STATUS_INVALID_ALIGNMENT             4
+
+#endif
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 0b20bbb758f2..da2930924501 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -10,6 +10,8 @@
 #ifndef _ASM_X86_I387_H
 #define _ASM_X86_I387_H
 
+#ifndef __ASSEMBLY__
+
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
 #include <linux/regset.h>
@@ -31,8 +33,16 @@ extern void init_thread_xstate(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+                                xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+                                 xstateregs_set;
+
+/*
+ * xstateregs_active == fpregs_active. Please refer to the comment
+ * at the definition of fpregs_active.
+ */
+#define xstateregs_active       fpregs_active
 
 extern struct _fpx_sw_bytes fx_sw_reserved;
 #ifdef CONFIG_IA32_EMULATION
@@ -411,4 +421,9 @@ static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
         }
 }
 
+#endif /* __ASSEMBLY__ */
+
+#define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5
+#define PSHUFB_XMM5_XMM6 .byte 0x66, 0x0f, 0x38, 0x00, 0xf5
+
 #endif /* _ASM_X86_I387_H */
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 58d7091eeb1f..1655147646aa 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -24,12 +24,7 @@ extern unsigned int cached_irq_mask;
 #define SLAVE_ICW4_DEFAULT      0x01
 #define PIC_ICW4_AEOI           2
 
-extern spinlock_t i8259A_lock;
-
-extern void init_8259A(int auto_eoi);
-extern void enable_8259A_irq(unsigned int irq);
-extern void disable_8259A_irq(unsigned int irq);
-extern unsigned int startup_8259A_irq(unsigned int irq);
+extern raw_spinlock_t i8259A_lock;
 
 /* the PIC may need a careful delay on some platforms, hence specific calls */
 static inline unsigned char inb_pic(unsigned int port)
@@ -57,7 +52,17 @@ static inline void outb_pic(unsigned char value, unsigned int port)
 
 extern struct irq_chip i8259A_chip;
 
-extern void mask_8259A(void);
-extern void unmask_8259A(void);
+struct legacy_pic {
+        int nr_legacy_irqs;
+        struct irq_chip *chip;
+        void (*mask_all)(void);
+        void (*restore_mask)(void);
+        void (*init)(int auto_eoi);
+        int (*irq_pending)(unsigned int irq);
+        void (*make_irq)(unsigned int irq);
+};
+
+extern struct legacy_pic *legacy_pic;
+extern struct legacy_pic null_legacy_pic;
 
 #endif /* _ASM_X86_I8259_H */
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
new file mode 100644
index 000000000000..205b063e3e32
--- /dev/null
+++ b/arch/x86/include/asm/inat.h
@@ -0,0 +1,220 @@
+#ifndef _ASM_X86_INAT_H
+#define _ASM_X86_INAT_H
+/*
+ * x86 instruction attributes
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include <asm/inat_types.h>
+
+/*
+ * Internal bits. Don't use bitmasks directly, because these bits are
+ * unstable. You should use checking functions.
+ */
+
+#define INAT_OPCODE_TABLE_SIZE 256
+#define INAT_GROUP_TABLE_SIZE 8
+
+/* Legacy last prefixes */
+#define INAT_PFX_OPNDSZ 1       /* 0x66 */ /* LPFX1 */
+#define INAT_PFX_REPE   2       /* 0xF3 */ /* LPFX2 */
+#define INAT_PFX_REPNE  3       /* 0xF2 */ /* LPFX3 */
+/* Other Legacy prefixes */
+#define INAT_PFX_LOCK   4       /* 0xF0 */
+#define INAT_PFX_CS     5       /* 0x2E */
+#define INAT_PFX_DS     6       /* 0x3E */
+#define INAT_PFX_ES     7       /* 0x26 */
+#define INAT_PFX_FS     8       /* 0x64 */
+#define INAT_PFX_GS     9       /* 0x65 */
+#define INAT_PFX_SS     10      /* 0x36 */
+#define INAT_PFX_ADDRSZ 11      /* 0x67 */
+/* x86-64 REX prefix */
+#define INAT_PFX_REX    12      /* 0x4X */
+/* AVX VEX prefixes */
+#define INAT_PFX_VEX2   13      /* 2-bytes VEX prefix */
+#define INAT_PFX_VEX3   14      /* 3-bytes VEX prefix */
+
+#define INAT_LSTPFX_MAX 3
+#define INAT_LGCPFX_MAX 11
+
+/* Immediate size */
+#define INAT_IMM_BYTE           1
+#define INAT_IMM_WORD           2
+#define INAT_IMM_DWORD          3
+#define INAT_IMM_QWORD          4
+#define INAT_IMM_PTR            5
+#define INAT_IMM_VWORD32        6
+#define INAT_IMM_VWORD          7
+
+/* Legacy prefix */
+#define INAT_PFX_OFFS   0
+#define INAT_PFX_BITS   4
+#define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
+#define INAT_PFX_MASK   (INAT_PFX_MAX << INAT_PFX_OFFS)
+/* Escape opcodes */
+#define INAT_ESC_OFFS   (INAT_PFX_OFFS + INAT_PFX_BITS)
+#define INAT_ESC_BITS   2
+#define INAT_ESC_MAX    ((1 << INAT_ESC_BITS) - 1)
+#define INAT_ESC_MASK   (INAT_ESC_MAX << INAT_ESC_OFFS)
+/* Group opcodes (1-16) */
+#define INAT_GRP_OFFS   (INAT_ESC_OFFS + INAT_ESC_BITS)
+#define INAT_GRP_BITS   5
+#define INAT_GRP_MAX    ((1 << INAT_GRP_BITS) - 1)
+#define INAT_GRP_MASK   (INAT_GRP_MAX << INAT_GRP_OFFS)
+/* Immediates */
+#define INAT_IMM_OFFS   (INAT_GRP_OFFS + INAT_GRP_BITS)
+#define INAT_IMM_BITS   3
+#define INAT_IMM_MASK   (((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS)
+/* Flags */
+#define INAT_FLAG_OFFS  (INAT_IMM_OFFS + INAT_IMM_BITS)
+#define INAT_MODRM      (1 << (INAT_FLAG_OFFS))
+#define INAT_FORCE64    (1 << (INAT_FLAG_OFFS + 1))
+#define INAT_SCNDIMM    (1 << (INAT_FLAG_OFFS + 2))
+#define INAT_MOFFSET    (1 << (INAT_FLAG_OFFS + 3))
+#define INAT_VARIANT    (1 << (INAT_FLAG_OFFS + 4))
+#define INAT_VEXOK      (1 << (INAT_FLAG_OFFS + 5))
+#define INAT_VEXONLY    (1 << (INAT_FLAG_OFFS + 6))
+/* Attribute making macros for attribute tables */
+#define INAT_MAKE_PREFIX(pfx)   (pfx << INAT_PFX_OFFS)
+#define INAT_MAKE_ESCAPE(esc)   (esc << INAT_ESC_OFFS)
+#define INAT_MAKE_GROUP(grp)    ((grp << INAT_GRP_OFFS) | INAT_MODRM)
+#define INAT_MAKE_IMM(imm)      (imm << INAT_IMM_OFFS)
+
+/* Attribute search APIs */
+extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
+extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
+                                             insn_byte_t last_pfx,
+                                             insn_attr_t esc_attr);
+extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
+                                            insn_byte_t last_pfx,
+                                            insn_attr_t esc_attr);
+extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
+                                          insn_byte_t vex_m,
+                                          insn_byte_t vex_pp);
+
+/* Attribute checking functions */
+static inline int inat_is_legacy_prefix(insn_attr_t attr)
+{
+        attr &= INAT_PFX_MASK;
+        return attr && attr <= INAT_LGCPFX_MAX;
+}
+
+static inline int inat_is_address_size_prefix(insn_attr_t attr)
+{
+        return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ;
+}
+
+static inline int inat_is_operand_size_prefix(insn_attr_t attr)
+{
+        return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ;
+}
+
+static inline int inat_is_rex_prefix(insn_attr_t attr)
+{
+        return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
+}
+
+static inline int inat_last_prefix_id(insn_attr_t attr)
+{
+        if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
+                return 0;
+        else
+                return attr & INAT_PFX_MASK;
+}
+
+static inline int inat_is_vex_prefix(insn_attr_t attr)
+{
+        attr &= INAT_PFX_MASK;
+        return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+}
+
+static inline int inat_is_vex3_prefix(insn_attr_t attr)
+{
+        return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
+}
+
+static inline int inat_is_escape(insn_attr_t attr)
+{
+        return attr & INAT_ESC_MASK;
+}
+
+static inline int inat_escape_id(insn_attr_t attr)
+{
+        return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS;
+}
+
+static inline int inat_is_group(insn_attr_t attr)
+{
+        return attr & INAT_GRP_MASK;
+}
+
+static inline int inat_group_id(insn_attr_t attr)
+{
+        return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS;
+}
+
+static inline int inat_group_common_attribute(insn_attr_t attr)
+{
+        return attr & ~INAT_GRP_MASK;
+}
+
+static inline int inat_has_immediate(insn_attr_t attr)
+{
+        return attr & INAT_IMM_MASK;
+}
+
+static inline int inat_immediate_size(insn_attr_t attr)
+{
+        return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS;
+}
+
+static inline int inat_has_modrm(insn_attr_t attr)
+{
+        return attr & INAT_MODRM;
+}
+
+static inline int inat_is_force64(insn_attr_t attr)
+{
+        return attr & INAT_FORCE64;
+}
+
+static inline int inat_has_second_immediate(insn_attr_t attr)
+{
+        return attr & INAT_SCNDIMM;
+}
+
+static inline int inat_has_moffset(insn_attr_t attr)
+{
+        return attr & INAT_MOFFSET;
+}
+
+static inline int inat_has_variant(insn_attr_t attr)
+{
+        return attr & INAT_VARIANT;
+}
+
+static inline int inat_accept_vex(insn_attr_t attr)
+{
+        return attr & INAT_VEXOK;
+}
+
+static inline int inat_must_vex(insn_attr_t attr)
+{
+        return attr & INAT_VEXONLY;
+}
+#endif
diff --git a/arch/x86/include/asm/inat_types.h b/arch/x86/include/asm/inat_types.h
new file mode 100644
index 000000000000..cb3c20ce39cf
--- /dev/null
+++ b/arch/x86/include/asm/inat_types.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_X86_INAT_TYPES_H
+#define _ASM_X86_INAT_TYPES_H
+/*
+ * x86 instruction attributes
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+/* Instruction attributes */
+typedef unsigned int insn_attr_t;
+typedef unsigned char insn_byte_t;
+typedef signed int insn_value_t;
+
+#endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
new file mode 100644
index 000000000000..96c2e0ad04ca
--- /dev/null
+++ b/arch/x86/include/asm/insn.h
@@ -0,0 +1,184 @@
+#ifndef _ASM_X86_INSN_H
+#define _ASM_X86_INSN_H
+/*
+ * x86 instruction analysis
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+/* insn_attr_t is defined in inat.h */
+#include <asm/inat.h>
+
+struct insn_field {
+        union {
+                insn_value_t value;
+                insn_byte_t bytes[4];
+        };
+        /* !0 if we've run insn_get_xxx() for this field */
+        unsigned char got;
+        unsigned char nbytes;
+};
+
+struct insn {
+        struct insn_field prefixes;     /*
+                                         * Prefixes
+                                         * prefixes.bytes[3]: last prefix
+                                         */
+        struct insn_field rex_prefix;   /* REX prefix */
+        struct insn_field vex_prefix;   /* VEX prefix */
+        struct insn_field opcode;       /*
+                                         * opcode.bytes[0]: opcode1
+                                         * opcode.bytes[1]: opcode2
+                                         * opcode.bytes[2]: opcode3
+                                         */
+        struct insn_field modrm;
+        struct insn_field sib;
+        struct insn_field displacement;
+        union {
+                struct insn_field immediate;
+                struct insn_field moffset1;     /* for 64bit MOV */
+                struct insn_field immediate1;   /* for 64bit imm or off16/32 */
+        };
+        union {
+                struct insn_field moffset2;     /* for 64bit MOV */
+                struct insn_field immediate2;   /* for 64bit imm or seg16 */
+        };
+
+        insn_attr_t attr;
+        unsigned char opnd_bytes;
+        unsigned char addr_bytes;
+        unsigned char length;
+        unsigned char x86_64;
+
+        const insn_byte_t *kaddr;       /* kernel address of insn to analyze */
+        const insn_byte_t *next_byte;
+};
+
+#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
+#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
+#define X86_MODRM_RM(modrm) ((modrm) & 0x07)
+
+#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6)
+#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
+#define X86_SIB_BASE(sib) ((sib) & 0x07)
+
+#define X86_REX_W(rex) ((rex) & 8)
+#define X86_REX_R(rex) ((rex) & 4)
+#define X86_REX_X(rex) ((rex) & 2)
+#define X86_REX_B(rex) ((rex) & 1)
+
+/* VEX bit flags  */
+#define X86_VEX_W(vex)  ((vex) & 0x80)  /* VEX3 Byte2 */
+#define X86_VEX_R(vex)  ((vex) & 0x80)  /* VEX2/3 Byte1 */
+#define X86_VEX_X(vex)  ((vex) & 0x40)  /* VEX3 Byte1 */
+#define X86_VEX_B(vex)  ((vex) & 0x20)  /* VEX3 Byte1 */
+#define X86_VEX_L(vex)  ((vex) & 0x04)  /* VEX3 Byte2, VEX2 Byte1 */
+/* VEX bit fields */
+#define X86_VEX3_M(vex) ((vex) & 0x1f)          /* VEX3 Byte1 */
+#define X86_VEX2_M      1                       /* VEX2.M always 1 */
+#define X86_VEX_V(vex)  (((vex) & 0x78) >> 3)   /* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_P(vex)  ((vex) & 0x03)          /* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_M_MAX   0x1f                    /* VEX3.M Maximum value */
+
+/* The last prefix is needed for two-byte and three-byte opcodes */
+static inline insn_byte_t insn_last_prefix(struct insn *insn)
+{
+        return insn->prefixes.bytes[3];
+}
+
+extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
+extern void insn_get_prefixes(struct insn *insn);
+extern void insn_get_opcode(struct insn *insn);
+extern void insn_get_modrm(struct insn *insn);
+extern void insn_get_sib(struct insn *insn);
+extern void insn_get_displacement(struct insn *insn);
+extern void insn_get_immediate(struct insn *insn);
+extern void insn_get_length(struct insn *insn);
+
+/* Attribute will be determined after getting ModRM (for opcode groups) */
+static inline void insn_get_attribute(struct insn *insn)
+{
+        insn_get_modrm(insn);
+}
+
+/* Instruction uses RIP-relative addressing */
+extern int insn_rip_relative(struct insn *insn);
+
+/* Init insn for kernel text */
+static inline void kernel_insn_init(struct insn *insn, const void *kaddr)
+{
+#ifdef CONFIG_X86_64
+        insn_init(insn, kaddr, 1);
+#else /* CONFIG_X86_32 */
+        insn_init(insn, kaddr, 0);
+#endif
+}
+
+static inline int insn_is_avx(struct insn *insn)
+{
+        if (!insn->prefixes.got)
+                insn_get_prefixes(insn);
+        return (insn->vex_prefix.value != 0);
+}
+
+static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
+{
+        if (insn->vex_prefix.nbytes == 2)       /* 2 bytes VEX */
+                return X86_VEX2_M;
+        else
+                return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+}
+
+static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
+{
+        if (insn->vex_prefix.nbytes == 2)       /* 2 bytes VEX */
+                return X86_VEX_P(insn->vex_prefix.bytes[1]);
+        else
+                return X86_VEX_P(insn->vex_prefix.bytes[2]);
+}
+
+/* Offset of each field from kaddr */
+static inline int insn_offset_rex_prefix(struct insn *insn)
+{
+        return insn->prefixes.nbytes;
+}
+static inline int insn_offset_vex_prefix(struct insn *insn)
+{
+        return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes;
+}
+static inline int insn_offset_opcode(struct insn *insn)
+{
+        return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes;
+}
+static inline int insn_offset_modrm(struct insn *insn)
+{
+        return insn_offset_opcode(insn) + insn->opcode.nbytes;
+}
+static inline int insn_offset_sib(struct insn *insn)
+{
+        return insn_offset_modrm(insn) + insn->modrm.nbytes;
+}
+static inline int insn_offset_displacement(struct insn *insn)
+{
+        return insn_offset_sib(insn) + insn->sib.nbytes;
+}
+static inline int insn_offset_immediate(struct insn *insn)
+{
+        return insn_offset_displacement(insn) + insn->displacement.nbytes;
+}
+
+#endif /* _ASM_X86_INSN_H */
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
new file mode 100644
index 000000000000..14cf526091f9
--- /dev/null
+++ b/arch/x86/include/asm/inst.h
@@ -0,0 +1,150 @@
+/*
+ * Generate .byte code for some instructions not supported by old
+ * binutils.
+ */
+#ifndef X86_ASM_INST_H
+#define X86_ASM_INST_H
+
+#ifdef __ASSEMBLY__
+
+        .macro XMM_NUM opd xmm
+        .ifc \xmm,%xmm0
+        \opd = 0
+        .endif
+        .ifc \xmm,%xmm1
+        \opd = 1
+        .endif
+        .ifc \xmm,%xmm2
+        \opd = 2
+        .endif
+        .ifc \xmm,%xmm3
+        \opd = 3
+        .endif
+        .ifc \xmm,%xmm4
+        \opd = 4
+        .endif
+        .ifc \xmm,%xmm5
+        \opd = 5
+        .endif
+        .ifc \xmm,%xmm6
+        \opd = 6
+        .endif
+        .ifc \xmm,%xmm7
+        \opd = 7
+        .endif
+        .ifc \xmm,%xmm8
+        \opd = 8
+        .endif
+        .ifc \xmm,%xmm9
+        \opd = 9
+        .endif
+        .ifc \xmm,%xmm10
+        \opd = 10
+        .endif
+        .ifc \xmm,%xmm11
+        \opd = 11
+        .endif
+        .ifc \xmm,%xmm12
+        \opd = 12
+        .endif
+        .ifc \xmm,%xmm13
+        \opd = 13
+        .endif
+        .ifc \xmm,%xmm14
+        \opd = 14
+        .endif
+        .ifc \xmm,%xmm15
+        \opd = 15
+        .endif
+        .endm
+
+        .macro PFX_OPD_SIZE
+        .byte 0x66
+        .endm
+
+        .macro PFX_REX opd1 opd2
+        .if (\opd1 | \opd2) & 8
+        .byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1)
+        .endif
+        .endm
+
+        .macro MODRM mod opd1 opd2
+        .byte \mod | (\opd1 & 7) | ((\opd2 & 7) << 3)
+        .endm
+
+        .macro PSHUFB_XMM xmm1 xmm2
+        XMM_NUM pshufb_opd1 \xmm1
+        XMM_NUM pshufb_opd2 \xmm2
+        PFX_OPD_SIZE
+        PFX_REX pshufb_opd1 pshufb_opd2
+        .byte 0x0f, 0x38, 0x00
+        MODRM 0xc0 pshufb_opd1 pshufb_opd2
+        .endm
+
+        .macro PCLMULQDQ imm8 xmm1 xmm2
+        XMM_NUM clmul_opd1 \xmm1
+        XMM_NUM clmul_opd2 \xmm2
+        PFX_OPD_SIZE
+        PFX_REX clmul_opd1 clmul_opd2
+        .byte 0x0f, 0x3a, 0x44
+        MODRM 0xc0 clmul_opd1 clmul_opd2
+        .byte \imm8
+        .endm
+
+        .macro AESKEYGENASSIST rcon xmm1 xmm2
+        XMM_NUM aeskeygen_opd1 \xmm1
+        XMM_NUM aeskeygen_opd2 \xmm2
+        PFX_OPD_SIZE
+        PFX_REX aeskeygen_opd1 aeskeygen_opd2
+        .byte 0x0f, 0x3a, 0xdf
+        MODRM 0xc0 aeskeygen_opd1 aeskeygen_opd2
+        .byte \rcon
+        .endm
+
+        .macro AESIMC xmm1 xmm2
+        XMM_NUM aesimc_opd1 \xmm1
+        XMM_NUM aesimc_opd2 \xmm2
+        PFX_OPD_SIZE
+        PFX_REX aesimc_opd1 aesimc_opd2
+        .byte 0x0f, 0x38, 0xdb
+        MODRM 0xc0 aesimc_opd1 aesimc_opd2
+        .endm
+
+        .macro AESENC xmm1 xmm2
+        XMM_NUM aesenc_opd1 \xmm1
+        XMM_NUM aesenc_opd2 \xmm2
+        PFX_OPD_SIZE
+        PFX_REX aesenc_opd1 aesenc_opd2
+        .byte 0x0f, 0x38, 0xdc
+        MODRM 0xc0 aesenc_opd1 aesenc_opd2
+        .endm
+
+        .macro AESENCLAST xmm1 xmm2
+        XMM_NUM aesenclast_opd1 \xmm1
+        XMM_NUM aesenclast_opd2 \xmm2
+        PFX_OPD_SIZE
+        PFX_REX aesenclast_opd1 aesenclast_opd2
+        .byte 0x0f, 0x38, 0xdd
+        MODRM 0xc0 aesenclast_opd1 aesenclast_opd2
+        .endm
+
+        .macro AESDEC xmm1 xmm2
+        XMM_NUM aesdec_opd1 \xmm1
+        XMM_NUM aesdec_opd2 \xmm2
+        PFX_OPD_SIZE
+        PFX_REX aesdec_opd1 aesdec_opd2
+        .byte 0x0f, 0x38, 0xde
+        MODRM 0xc0 aesdec_opd1 aesdec_opd2
+        .endm
+
+        .macro AESDECLAST xmm1 xmm2
+        XMM_NUM aesdeclast_opd1 \xmm1
+        XMM_NUM aesdeclast_opd2 \xmm2
+        PFX_OPD_SIZE
+        PFX_REX aesdeclast_opd1 aesdeclast_opd2
+        .byte 0x0f, 0x38, 0xdf
+        MODRM 0xc0 aesdeclast_opd1 aesdeclast_opd2
+        .endm
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 73739322b6d0..30a3e9776123 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -1,8 +1,42 @@
 #ifndef _ASM_X86_IO_H
 #define _ASM_X86_IO_H
 
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ *              Linus
+ */
+
+ /*
+  *  Bit simplified and optimized by Jan Hubicka
+  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+  *
+  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+  *  isa_read[wl] and isa_write[wl] fixed
+  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+  */
+
 #define ARCH_HAS_IOREMAP_WC
 
+#include <linux/string.h>
 #include <linux/compiler.h>
 #include <asm-generic/int-ll64.h>
 #include <asm/page.h>
@@ -173,11 +207,126 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
 extern void iounmap(volatile void __iomem *addr);
 
 
-#ifdef CONFIG_X86_32
-# include "io_32.h"
+#ifdef __KERNEL__
+
+#include <asm-generic/iomap.h>
+
+#include <linux/vmalloc.h>
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)   p
+
+static inline void
+memset_io(volatile void __iomem *addr, unsigned char val, size_t count)
+{
+        memset((void __force *)addr, val, count);
+}
+
+static inline void
+memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count)
+{
+        memcpy(dst, (const void __force *)src, count);
+}
+
+static inline void
+memcpy_toio(volatile void __iomem *dst, const void *src, size_t count)
+{
+        memcpy((void __force *)dst, src, count);
+}
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
+
+/*
+ *      Cache management
+ *
+ *      This needed for two cases
+ *      1. Out of order aware processors
+ *      2. Accidentally out of order processors (PPro errata #51)
+ */
+
+static inline void flush_write_buffers(void)
+{
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+        asm volatile("lock; addl $0,0(%%esp)": : :"memory");
+#endif
+}
+
+#endif /* __KERNEL__ */
+
+extern void native_io_delay(void);
+
+extern int io_delay_type;
+extern void io_delay_init(void);
+
+#if defined(CONFIG_PARAVIRT)
+#include <asm/paravirt.h>
 #else
-# include "io_64.h"
+
+static inline void slow_down_io(void)
+{
+        native_io_delay();
+#ifdef REALLY_SLOW_IO
+        native_io_delay();
+        native_io_delay();
+        native_io_delay();
 #endif
+}
+
+#endif
+
+#define BUILDIO(bwl, bw, type)                                          \
+static inline void out##bwl(unsigned type value, int port)              \
+{                                                                       \
+        asm volatile("out" #bwl " %" #bw "0, %w1"                       \
+                     : : "a"(value), "Nd"(port));                       \
+}                                                                       \
+                                                                        \
+static inline unsigned type in##bwl(int port)                           \
+{                                                                       \
+        unsigned type value;                                            \
+        asm volatile("in" #bwl " %w1, %" #bw "0"                        \
+                     : "=a"(value) : "Nd"(port));                       \
+        return value;                                                   \
+}                                                                       \
+                                                                        \
+static inline void out##bwl##_p(unsigned type value, int port)          \
+{                                                                       \
+        out##bwl(value, port);                                          \
+        slow_down_io();                                                 \
+}                                                                       \
+                                                                        \
+static inline unsigned type in##bwl##_p(int port)                       \
+{                                                                       \
+        unsigned type value = in##bwl(port);                            \
+        slow_down_io();                                                 \
+        return value;                                                   \
+}                                                                       \
+                                                                        \
+static inline void outs##bwl(int port, const void *addr, unsigned long count) \
+{                                                                       \
+        asm volatile("rep; outs" #bwl                                   \
+                     : "+S"(addr), "+c"(count) : "d"(port));            \
+}                                                                       \
+                                                                        \
+static inline void ins##bwl(int port, void *addr, unsigned long count)  \
+{                                                                       \
+        asm volatile("rep; ins" #bwl                                    \
+                     : "+D"(addr), "+c"(count) : "d"(port));            \
+}
+
+BUILDIO(b, b, char)
+BUILDIO(w, w, short)
+BUILDIO(l, , int)
 
 extern void *xlate_dev_mem_ptr(unsigned long phys);
 extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
@@ -198,6 +347,7 @@ extern void __iomem *early_ioremap(resource_size_t phys_addr,
 extern void __iomem *early_memremap(resource_size_t phys_addr,
                                     unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void fixup_early_ioremap(void);
 
 #define IO_SPACE_LIMIT 0xffff
 
diff --git a/arch/x86/include/asm/io_32.h b/arch/x86/include/asm/io_32.h
deleted file mode 100644
index a299900f5920..000000000000
--- a/arch/x86/include/asm/io_32.h
+++ /dev/null
@@ -1,196 +0,0 @@
-#ifndef _ASM_X86_IO_32_H
-#define _ASM_X86_IO_32_H
-
-#include <linux/string.h>
-#include <linux/compiler.h>
-
-/*
- * This file contains the definitions for the x86 IO instructions
- * inb/inw/inl/outb/outw/outl and the "string versions" of the same
- * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
- * versions of the single-IO instructions (inb_p/inw_p/..).
- *
- * This file is not meant to be obfuscating: it's just complicated
- * to (a) handle it all in a way that makes gcc able to optimize it
- * as well as possible and (b) trying to avoid writing the same thing
- * over and over again with slight variations and possibly making a
- * mistake somewhere.
- */
-
-/*
- * Thanks to James van Artsdalen for a better timing-fix than
- * the two short jumps: using outb's to a nonexistent port seems
- * to guarantee better timings even on fast machines.
- *
- * On the other hand, I'd like to be sure of a non-existent port:
- * I feel a bit unsafe about using 0x80 (should be safe, though)
- *
- *              Linus
- */
-
- /*
-  *  Bit simplified and optimized by Jan Hubicka
-  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
-  *
-  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
-  *  isa_read[wl] and isa_write[wl] fixed
-  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-  */
-
-#define XQUAD_PORTIO_BASE 0xfe400000
-#define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
-
-#ifdef __KERNEL__
-
-#include <asm-generic/iomap.h>
-
-#include <linux/vmalloc.h>
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)   p
-
-static inline void
-memset_io(volatile void __iomem *addr, unsigned char val, int count)
-{
-        memset((void __force *)addr, val, count);
-}
-
-static inline void
-memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
-{
-        __memcpy(dst, (const void __force *)src, count);
-}
-
-static inline void
-memcpy_toio(volatile void __iomem *dst, const void *src, int count)
-{
-        __memcpy((void __force *)dst, src, count);
-}
-
-/*
- * ISA space is 'always mapped' on a typical x86 system, no need to
- * explicitly ioremap() it. The fact that the ISA IO space is mapped
- * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
- * are physical addresses. The following constant pointer can be
- * used as the IO-area pointer (it can be iounmapped as well, so the
- * analogy with PCI is quite large):
- */
-#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
-
-/*
- *      Cache management
- *
- *      This needed for two cases
- *      1. Out of order aware processors
- *      2. Accidentally out of order processors (PPro errata #51)
- */
-
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
-
-static inline void flush_write_buffers(void)
-{
-        asm volatile("lock; addl $0,0(%%esp)": : :"memory");
-}
-
-#else
-
-#define flush_write_buffers() do { } while (0)
-
-#endif
-
-#endif /* __KERNEL__ */
-
-extern void native_io_delay(void);
-
-extern int io_delay_type;
-extern void io_delay_init(void);
-
-#if defined(CONFIG_PARAVIRT)
-#include <asm/paravirt.h>
-#else
-
-static inline void slow_down_io(void)
-{
-        native_io_delay();
-#ifdef REALLY_SLOW_IO
-        native_io_delay();
-        native_io_delay();
-        native_io_delay();
-#endif
-}
-
-#endif
-
-#define __BUILDIO(bwl, bw, type)                                \
-static inline void out##bwl(unsigned type value, int port)      \
-{                                                               \
-        out##bwl##_local(value, port);                          \
-}                                                               \
-                                                                \
-static inline unsigned type in##bwl(int port)                   \
-{                                                               \
-        return in##bwl##_local(port);                           \
-}
-
-#define BUILDIO(bwl, bw, type)                                          \
-static inline void out##bwl##_local(unsigned type value, int port)      \
-{                                                                       \
-        asm volatile("out" #bwl " %" #bw "0, %w1"               \
-                     : : "a"(value), "Nd"(port));                       \
-}                                                                       \
-                                                                        \
-static inline unsigned type in##bwl##_local(int port)                   \
-{                                                                       \
-        unsigned type value;                                            \
-        asm volatile("in" #bwl " %w1, %" #bw "0"                \
-                     : "=a"(value) : "Nd"(port));                       \
-        return value;                                                   \
-}                                                                       \
-                                                                        \
-static inline void out##bwl##_local_p(unsigned type value, int port)    \
-{                                                                       \
-        out##bwl##_local(value, port);                                  \
-        slow_down_io();                                                 \
-}                                                                       \
-                                                                        \
-static inline unsigned type in##bwl##_local_p(int port)                 \
-{                                                                       \
-        unsigned type value = in##bwl##_local(port);                    \
-        slow_down_io();                                                 \
-        return value;                                                   \
-}                                                                       \
-                                                                        \
-__BUILDIO(bwl, bw, type)                                                \
-                                                                        \
-static inline void out##bwl##_p(unsigned type value, int port)          \
-{                                                                       \
-        out##bwl(value, port);                                          \
-        slow_down_io();                                                 \
-}                                                                       \
-                                                                        \
-static inline unsigned type in##bwl##_p(int port)                       \
-{                                                                       \
-        unsigned type value = in##bwl(port);                            \
-        slow_down_io();                                                 \
-        return value;                                                   \
-}                                                                       \
-                                                                        \
-static inline void outs##bwl(int port, const void *addr, unsigned long count) \
-{                                                                       \
-        asm volatile("rep; outs" #bwl                                   \
-                     : "+S"(addr), "+c"(count) : "d"(port));            \
-}                                                                       \
-                                                                        \
-static inline void ins##bwl(int port, void *addr, unsigned long count)  \
-{                                                                       \
-        asm volatile("rep; ins" #bwl                                    \
-                     : "+D"(addr), "+c"(count) : "d"(port));            \
-}
-
-BUILDIO(b, b, char)
-BUILDIO(w, w, short)
-BUILDIO(l, , int)
-
-#endif /* _ASM_X86_IO_32_H */
diff --git a/arch/x86/include/asm/io_64.h b/arch/x86/include/asm/io_64.h
deleted file mode 100644
index 244067893af4..000000000000
--- a/arch/x86/include/asm/io_64.h
+++ /dev/null
@@ -1,181 +0,0 @@
-#ifndef _ASM_X86_IO_64_H
-#define _ASM_X86_IO_64_H
-
-
-/*
- * This file contains the definitions for the x86 IO instructions
- * inb/inw/inl/outb/outw/outl and the "string versions" of the same
- * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
- * versions of the single-IO instructions (inb_p/inw_p/..).
- *
- * This file is not meant to be obfuscating: it's just complicated
- * to (a) handle it all in a way that makes gcc able to optimize it
- * as well as possible and (b) trying to avoid writing the same thing
- * over and over again with slight variations and possibly making a
- * mistake somewhere.
- */
-
-/*
- * Thanks to James van Artsdalen for a better timing-fix than
- * the two short jumps: using outb's to a nonexistent port seems
- * to guarantee better timings even on fast machines.
- *
- * On the other hand, I'd like to be sure of a non-existent port:
- * I feel a bit unsafe about using 0x80 (should be safe, though)
- *
- *              Linus
- */
-
- /*
-  *  Bit simplified and optimized by Jan Hubicka
-  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
-  *
-  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
-  *  isa_read[wl] and isa_write[wl] fixed
-  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-  */
-
-extern void native_io_delay(void);
-
-extern int io_delay_type;
-extern void io_delay_init(void);
-
-#if defined(CONFIG_PARAVIRT)
-#include <asm/paravirt.h>
-#else
-
-static inline void slow_down_io(void)
-{
-        native_io_delay();
-#ifdef REALLY_SLOW_IO
-        native_io_delay();
-        native_io_delay();
-        native_io_delay();
-#endif
-}
-#endif
-
-/*
- * Talk about misusing macros..
- */
-#define __OUT1(s, x)                                                    \
-static inline void out##s(unsigned x value, unsigned short port) {
-
-#define __OUT2(s, s1, s2)                               \
-asm volatile ("out" #s " %" s1 "0,%" s2 "1"
-
-#ifndef REALLY_SLOW_IO
-#define REALLY_SLOW_IO
-#define UNSET_REALLY_SLOW_IO
-#endif
-
-#define __OUT(s, s1, x)                                                 \
-        __OUT1(s, x) __OUT2(s, s1, "w") : : "a" (value), "Nd" (port));  \
-        }                                                               \
-        __OUT1(s##_p, x) __OUT2(s, s1, "w") : : "a" (value), "Nd" (port)); \
-        slow_down_io();                                                 \
-}
-
-#define __IN1(s)                                                        \
-static inline RETURN_TYPE in##s(unsigned short port)                    \
-{                                                                       \
-        RETURN_TYPE _v;
-
-#define __IN2(s, s1, s2)                                                \
-        asm volatile ("in" #s " %" s2 "1,%" s1 "0"
-
-#define __IN(s, s1, i...)                                               \
-        __IN1(s) __IN2(s, s1, "w") : "=a" (_v) : "Nd" (port), ##i);     \
-        return _v;                                                      \
-        }                                                               \
-        __IN1(s##_p) __IN2(s, s1, "w") : "=a" (_v) : "Nd" (port), ##i); \
-        slow_down_io(); \
-        return _v; }
-
-#ifdef UNSET_REALLY_SLOW_IO
-#undef REALLY_SLOW_IO
-#endif
-
-#define __INS(s)                                                        \
-static inline void ins##s(unsigned short port, void *addr,              \
-                          unsigned long count)                          \
-{                                                                       \
-        asm volatile ("rep ; ins" #s                                    \
-                      : "=D" (addr), "=c" (count)                       \
-                      : "d" (port), "0" (addr), "1" (count));           \
-}
-
-#define __OUTS(s)                                                       \
-static inline void outs##s(unsigned short port, const void *addr,       \
-                           unsigned long count)                         \
-{                                                                       \
-        asm volatile ("rep ; outs" #s                                   \
-                      : "=S" (addr), "=c" (count)                       \
-                      : "d" (port), "0" (addr), "1" (count));           \
-}
-
-#define RETURN_TYPE unsigned char
-__IN(b, "")
-#undef RETURN_TYPE
-#define RETURN_TYPE unsigned short
-__IN(w, "")
-#undef RETURN_TYPE
-#define RETURN_TYPE unsigned int
-__IN(l, "")
-#undef RETURN_TYPE
-
-__OUT(b, "b", char)
-__OUT(w, "w", short)
-__OUT(l, , int)
-
-__INS(b)
-__INS(w)
-__INS(l)
-
-__OUTS(b)
-__OUTS(w)
-__OUTS(l)
-
-#if defined(__KERNEL__) && defined(__x86_64__)
-
-#include <linux/vmalloc.h>
-
-#include <asm-generic/iomap.h>
-
-void __memcpy_fromio(void *, unsigned long, unsigned);
-void __memcpy_toio(unsigned long, const void *, unsigned);
-
-static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
-                                 unsigned len)
-{
-        __memcpy_fromio(to, (unsigned long)from, len);
-}
-
-static inline void memcpy_toio(volatile void __iomem *to, const void *from,
-                               unsigned len)
-{
-        __memcpy_toio((unsigned long)to, from, len);
-}
-
-void memset_io(volatile void __iomem *a, int b, size_t c);
-
-/*
- * ISA space is 'always mapped' on a typical x86 system, no need to
- * explicitly ioremap() it. The fact that the ISA IO space is mapped
- * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
- * are physical addresses. The following constant pointer can be
- * used as the IO-area pointer (it can be iounmapped as well, so the
- * analogy with PCI is quite large):
- */
-#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
-
-#define flush_write_buffers()
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)   p
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_IO_64_H */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 7c7c16cde1f8..35832a03a515 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -143,8 +143,6 @@ extern int noioapicreroute;
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 
-extern void io_apic_disable_legacy(void);
-
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.
@@ -160,6 +158,7 @@ extern int io_apic_get_redir_entries(int ioapic);
 struct io_apic_irq_attr;
 extern int io_apic_set_pci_routing(struct device *dev, int irq,
                  struct io_apic_irq_attr *irq_attr);
+void setup_IO_APIC_irq_extra(u32 gsi);
 extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
 extern void ioapic_insert_resources(void);
@@ -188,6 +187,7 @@ extern struct mp_ioapic_gsi  mp_gsi_routing[];
 int mp_find_ioapic(int gsi);
 int mp_find_ioapic_pin(int ioapic, int gsi);
 void __init mp_register_ioapic(int id, u32 address, u32 gsi_base);
+extern void __init pre_init_apic_IRQ0(void);
 
 #else  /* !CONFIG_X86_IO_APIC */
 
@@ -197,7 +197,11 @@ static const int timer_through_8259 = 0;
 static inline void ioapic_init_mappings(void)   { }
 static inline void ioapic_insert_resources(void) { }
 static inline void probe_nr_irqs_gsi(void)      { }
+static inline int mp_find_ioapic(int gsi) { return 0; }
 
+struct io_apic_irq_attr;
+static inline int io_apic_set_pci_routing(struct device *dev, int irq,
+                 struct io_apic_irq_attr *irq_attr) { return 0; }
 #endif
 
 #endif /* _ASM_X86_IO_APIC_H */
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index fd6d21bbee6c..345c99cef152 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -1,8 +1,6 @@
 #ifndef _ASM_X86_IOMMU_H
 #define _ASM_X86_IOMMU_H
 
-extern void pci_iommu_shutdown(void);
-extern void no_iommu_init(void);
 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/irq.h b/arch/x86/include/asm/irq.h
index ddda6cbed6f4..5458380b6ef8 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -34,9 +34,10 @@ static inline int irq_canonicalize(int irq)
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(void);
+extern void irq_force_complete_move(int);
 #endif
 
-extern void (*generic_interrupt_extension)(void);
+extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
 extern bool handle_irq(unsigned irq, struct pt_regs *regs);
 
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 28c3bf3f4c84..bb5318bbe0e4 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -28,28 +28,33 @@
 #define MCE_VECTOR                      0x12
 
 /*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
+ * IDT vectors usable for external interrupt sources start at 0x20.
+ * (0x80 is the syscall vector, 0x30-0x3f are for ISA)
  */
 #define FIRST_EXTERNAL_VECTOR           0x20
-
-#ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR                 0x80
-# define IA32_SYSCALL_VECTOR            0x80
-#else
-# define IA32_SYSCALL_VECTOR            0x80
-#endif
+/*
+ * We start allocating at 0x21 to spread out vectors evenly between
+ * priority levels. (0x80 is the syscall vector)
+ */
+#define VECTOR_OFFSET_START             1
 
 /*
- * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
- * cleanup after irq migration.
+ * Reserve the lowest usable vector (and hence lowest priority)  0x20 for
+ * triggering cleanup after irq migration. 0x21-0x2f will still be used
+ * for device interrupts.
  */
 #define IRQ_MOVE_CLEANUP_VECTOR         FIRST_EXTERNAL_VECTOR
 
+#define IA32_SYSCALL_VECTOR             0x80
+#ifdef CONFIG_X86_32
+# define SYSCALL_VECTOR                 0x80
+#endif
+
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.
+ *   round up to the next 16-vector boundary
  */
-#define IRQ0_VECTOR                     (FIRST_EXTERNAL_VECTOR + 0x10)
+#define IRQ0_VECTOR                     ((FIRST_EXTERNAL_VECTOR + 16) & ~15)
 
 #define IRQ1_VECTOR                     (IRQ0_VECTOR +  1)
 #define IRQ2_VECTOR                     (IRQ0_VECTOR +  2)
@@ -111,27 +116,20 @@
 /*
  * Generic system vector for platform specific use
  */
-#define GENERIC_INTERRUPT_VECTOR        0xed
+#define X86_PLATFORM_IPI_VECTOR         0xed
 
 /*
  * Performance monitoring pending work vector:
  */
 #define LOCAL_PENDING_VECTOR            0xec
 
-#define UV_BAU_MESSAGE                  0xec
+#define UV_BAU_MESSAGE                  0xea
 
 /*
  * Self IPI vector for machine checks
  */
 #define MCE_SELF_VECTOR                 0xeb
 
-/*
- * 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 NR_VECTORS                       256
 
 #define FPU_IRQ                           13
@@ -159,21 +157,21 @@ static inline int invalid_vm86_irq(int irq)
 
 #define NR_IRQS_LEGACY                    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 CPU_VECTOR_LIMIT              (64 * NR_CPUS)
 #  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
+#  define CPU_VECTOR_LIMIT              (32 * NR_CPUS)
+#  define NR_IRQS                                       \
+        (CPU_VECTOR_LIMIT < IO_APIC_VECTOR_LIMIT ?      \
+                (NR_VECTORS + CPU_VECTOR_LIMIT)  :      \
+                (NR_VECTORS + IO_APIC_VECTOR_LIMIT))
 # endif
 #else /* !CONFIG_X86_IO_APIC: */
 # define NR_IRQS                        NR_IRQS_LEGACY
diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/k8.h
index c2d1f3b58e5f..af00bd1d2089 100644
--- a/arch/x86/include/asm/k8.h
+++ b/arch/x86/include/asm/k8.h
@@ -4,20 +4,28 @@
 #include <linux/pci.h>
 
 extern struct pci_device_id k8_nb_ids[];
+struct bootnode;
 
 extern int early_is_k8_nb(u32 value);
 extern struct pci_dev **k8_northbridges;
 extern int num_k8_northbridges;
 extern int cache_k8_northbridges(void);
 extern void k8_flush_garts(void);
-extern int k8_scan_nodes(unsigned long start, unsigned long end);
+extern int k8_get_nodes(struct bootnode *nodes);
+extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn);
+extern int k8_scan_nodes(void);
 
 #ifdef CONFIG_K8_NB
+extern int num_k8_northbridges;
+
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
         return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
 }
+
 #else
+#define num_k8_northbridges 0
+
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
         return NULL;
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4fe681de1e76..4ffa345a8ccb 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -32,7 +32,10 @@ struct kprobe;
 
 typedef u8 kprobe_opcode_t;
 #define BREAKPOINT_INSTRUCTION  0xcc
-#define RELATIVEJUMP_INSTRUCTION 0xe9
+#define RELATIVEJUMP_OPCODE 0xe9
+#define RELATIVEJUMP_SIZE 5
+#define RELATIVECALL_OPCODE 0xe8
+#define RELATIVE_ADDR_SIZE 4
 #define MAX_INSN_SIZE 16
 #define MAX_STACK_SIZE 64
 #define MIN_STACK_SIZE(ADDR)                                           \
@@ -44,6 +47,17 @@ typedef u8 kprobe_opcode_t;
 
 #define flush_insn_slot(p)      do { } while (0)
 
+/* optinsn template addresses */
+extern kprobe_opcode_t optprobe_template_entry;
+extern kprobe_opcode_t optprobe_template_val;
+extern kprobe_opcode_t optprobe_template_call;
+extern kprobe_opcode_t optprobe_template_end;
+#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE)
+#define MAX_OPTINSN_SIZE                                \
+        (((unsigned long)&optprobe_template_end -       \
+          (unsigned long)&optprobe_template_entry) +    \
+         MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE)
+
 extern const int kretprobe_blacklist_size;
 
 void arch_remove_kprobe(struct kprobe *p);
@@ -64,6 +78,21 @@ struct arch_specific_insn {
         int boostable;
 };
 
+struct arch_optimized_insn {
+        /* copy of the original instructions */
+        kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE];
+        /* detour code buffer */
+        kprobe_opcode_t *insn;
+        /* the size of instructions copied to detour code buffer */
+        size_t size;
+};
+
+/* Return true (!0) if optinsn is prepared for optimization. */
+static inline int arch_prepared_optinsn(struct arch_optimized_insn *optinsn)
+{
+        return optinsn->size;
+}
+
 struct prev_kprobe {
         struct kprobe *kp;
         unsigned long status;
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 4a5fe914dc59..f46b79f6c16c 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -19,6 +19,8 @@
 #define __KVM_HAVE_MSIX
 #define __KVM_HAVE_MCE
 #define __KVM_HAVE_PIT_STATE2
+#define __KVM_HAVE_XEN_HVM
+#define __KVM_HAVE_VCPU_EVENTS
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -79,6 +81,7 @@ struct kvm_ioapic_state {
 #define KVM_IRQCHIP_PIC_MASTER   0
 #define KVM_IRQCHIP_PIC_SLAVE    1
 #define KVM_IRQCHIP_IOAPIC       2
+#define KVM_NR_IRQCHIPS          3
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
@@ -250,4 +253,35 @@ struct kvm_reinject_control {
         __u8 pit_reinject;
         __u8 reserved[31];
 };
+
+/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
+#define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001
+#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
+
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+        struct {
+                __u8 injected;
+                __u8 nr;
+                __u8 has_error_code;
+                __u8 pad;
+                __u32 error_code;
+        } exception;
+        struct {
+                __u8 injected;
+                __u8 nr;
+                __u8 soft;
+                __u8 pad;
+        } interrupt;
+        struct {
+                __u8 injected;
+                __u8 pending;
+                __u8 masked;
+                __u8 pad;
+        } nmi;
+        __u32 sipi_vector;
+        __u32 flags;
+        __u32 reserved[10];
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index b7ed2c423116..7a6f54fa13ba 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -54,13 +54,23 @@ struct x86_emulate_ctxt;
 struct x86_emulate_ops {
         /*
          * read_std: Read bytes of standard (non-emulated/special) memory.
-         *           Used for instruction fetch, stack operations, and others.
+         *           Used for descriptor reading.
          *  @addr:  [IN ] Linear address from which to read.
          *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
          *  @bytes: [IN ] Number of bytes to read from memory.
          */
         int (*read_std)(unsigned long addr, void *val,
-                        unsigned int bytes, struct kvm_vcpu *vcpu);
+                        unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+
+        /*
+         * fetch: Read bytes of standard (non-emulated/special) memory.
+         *        Used for instruction fetch.
+         *  @addr:  [IN ] Linear address from which to read.
+         *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
+         *  @bytes: [IN ] Number of bytes to read from memory.
+         */
+        int (*fetch)(unsigned long addr, void *val,
+                        unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
 
         /*
          * read_emulated: Read bytes from emulated/special memory area.
@@ -74,7 +84,7 @@ struct x86_emulate_ops {
                              struct kvm_vcpu *vcpu);
 
         /*
-         * write_emulated: Read bytes from emulated/special memory area.
+         * write_emulated: Write bytes to emulated/special memory area.
          *  @addr:  [IN ] Linear address to which to write.
          *  @val:   [IN ] Value to write to memory (low-order bytes used as
          *                required).
@@ -129,7 +139,7 @@ struct decode_cache {
         u8 seg_override;
         unsigned int d;
         unsigned long regs[NR_VCPU_REGS];
-        unsigned long eip;
+        unsigned long eip, eip_orig;
         /* modrm */
         u8 modrm;
         u8 modrm_mod;
@@ -168,6 +178,7 @@ struct x86_emulate_ctxt {
 
 /* Execution mode, passed to the emulator. */
 #define X86EMUL_MODE_REAL     0 /* Real mode.             */
+#define X86EMUL_MODE_VM86     1 /* Virtual 8086 mode.     */
 #define X86EMUL_MODE_PROT16   2 /* 16-bit protected mode. */
 #define X86EMUL_MODE_PROT32   4 /* 32-bit protected mode. */
 #define X86EMUL_MODE_PROT64   8 /* 64-bit (long) mode.    */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d83892226f73..06d9e79ca37d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -25,7 +25,7 @@
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
 
-#define KVM_MAX_VCPUS 16
+#define KVM_MAX_VCPUS 64
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
@@ -38,19 +38,6 @@
 #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |    \
                                   0xFFFFFF0000000000ULL)
 
-#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST                           \
-        (X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
-#define KVM_GUEST_CR0_MASK                                              \
-        (KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
-#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST                         \
-        (X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
-#define KVM_VM_CR0_ALWAYS_ON                                            \
-        (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
-#define KVM_GUEST_CR4_MASK                                              \
-        (X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
-#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
-#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
-
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
@@ -256,7 +243,8 @@ struct kvm_mmu {
         void (*new_cr3)(struct kvm_vcpu *vcpu);
         int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
         void (*free)(struct kvm_vcpu *vcpu);
-        gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
+        gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
+                            u32 *error);
         void (*prefetch_page)(struct kvm_vcpu *vcpu,
                               struct kvm_mmu_page *page);
         int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -282,13 +270,15 @@ struct kvm_vcpu_arch {
         u32 regs_dirty;
 
         unsigned long cr0;
+        unsigned long cr0_guest_owned_bits;
         unsigned long cr2;
         unsigned long cr3;
         unsigned long cr4;
+        unsigned long cr4_guest_owned_bits;
         unsigned long cr8;
         u32 hflags;
         u64 pdptrs[4]; /* pae */
-        u64 shadow_efer;
+        u64 efer;
         u64 apic_base;
         struct kvm_lapic *apic;    /* kernel irqchip context */
         int32_t apic_arb_prio;
@@ -354,7 +344,6 @@ struct kvm_vcpu_arch {
         unsigned int time_offset;
         struct page *time_page;
 
-        bool singlestep; /* guest is single stepped by KVM */
         bool nmi_pending;
         bool nmi_injected;
 
@@ -371,17 +360,31 @@ struct kvm_vcpu_arch {
         u64 mcg_status;
         u64 mcg_ctl;
         u64 *mce_banks;
+
+        /* used for guest single stepping over the given code position */
+        u16 singlestep_cs;
+        unsigned long singlestep_rip;
+        /* fields used by HYPER-V emulation */
+        u64 hv_vapic;
 };
 
 struct kvm_mem_alias {
         gfn_t base_gfn;
         unsigned long npages;
         gfn_t target_gfn;
+#define KVM_ALIAS_INVALID     1UL
+        unsigned long flags;
 };
 
-struct kvm_arch{
-        int naliases;
+#define KVM_ARCH_HAS_UNALIAS_INSTANTIATION
+
+struct kvm_mem_aliases {
         struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
+        int naliases;
+};
+
+struct kvm_arch {
+        struct kvm_mem_aliases *aliases;
 
         unsigned int n_free_mmu_pages;
         unsigned int n_requested_mmu_pages;
@@ -397,7 +400,6 @@ struct kvm_arch{
         struct kvm_pic *vpic;
         struct kvm_ioapic *vioapic;
         struct kvm_pit *vpit;
-        struct hlist_head irq_ack_notifier_list;
         int vapics_in_nmi_mode;
 
         unsigned int tss_addr;
@@ -410,8 +412,14 @@ struct kvm_arch{
         gpa_t ept_identity_map_addr;
 
         unsigned long irq_sources_bitmap;
-        unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
         u64 vm_init_tsc;
+        s64 kvmclock_offset;
+
+        struct kvm_xen_hvm_config xen_hvm_config;
+
+        /* fields used by HYPER-V emulation */
+        u64 hv_guest_os_id;
+        u64 hv_hypercall;
 };
 
 struct kvm_vm_stat {
@@ -461,12 +469,13 @@ struct descriptor_table {
 struct kvm_x86_ops {
         int (*cpu_has_kvm_support)(void);          /* __init */
         int (*disabled_by_bios)(void);             /* __init */
-        void (*hardware_enable)(void *dummy);      /* __init */
+        int (*hardware_enable)(void *dummy);
         void (*hardware_disable)(void *dummy);
         void (*check_processor_compatibility)(void *rtn);
         int (*hardware_setup)(void);               /* __init */
         void (*hardware_unsetup)(void);            /* __exit */
         bool (*cpu_has_accelerated_tpr)(void);
+        void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
         /* Create, but do not attach this VCPU */
         struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
@@ -477,8 +486,8 @@ struct kvm_x86_ops {
         void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
         void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
-        int (*set_guest_debug)(struct kvm_vcpu *vcpu,
-                               struct kvm_guest_debug *dbg);
+        void (*set_guest_debug)(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);
@@ -488,6 +497,7 @@ struct kvm_x86_ops {
         void (*set_segment)(struct kvm_vcpu *vcpu,
                             struct kvm_segment *var, int seg);
         void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
+        void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
         void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
         void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
         void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -497,17 +507,18 @@ struct kvm_x86_ops {
         void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
         void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
         void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-        unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr);
-        void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value,
-                       int *exception);
+        int (*get_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long *dest);
+        int (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value);
         void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
         unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
         void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+        void (*fpu_activate)(struct kvm_vcpu *vcpu);
+        void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
 
         void (*tlb_flush)(struct kvm_vcpu *vcpu);
 
-        void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
-        int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+        void (*run)(struct kvm_vcpu *vcpu);
+        int (*handle_exit)(struct kvm_vcpu *vcpu);
         void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
         void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
         u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
@@ -519,13 +530,16 @@ struct kvm_x86_ops {
                                 bool has_error_code, u32 error_code);
         int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
         int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+        bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
+        void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
         void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
         void (*enable_irq_window)(struct kvm_vcpu *vcpu);
         void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
         int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
         int (*get_tdp_level)(void);
         u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
-        bool (*gb_page_enable)(void);
+        int (*get_lpage_level)(void);
+        bool (*rdtscp_supported)(void);
 
         const struct trace_print_flags *exit_reasons_str;
 };
@@ -568,7 +582,7 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE          (1 << 0)
 #define EMULTYPE_TRAP_UD            (1 << 1)
 #define EMULTYPE_SKIP               (1 << 2)
-int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
+int emulate_instruction(struct kvm_vcpu *vcpu,
                         unsigned long cr2, u16 error_code, int emulation_type);
 void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
@@ -585,9 +599,9 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 
 struct x86_emulate_ctxt;
 
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in,
                      int size, unsigned port);
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
                            int size, unsigned long count, int down,
                             gva_t address, int rep, unsigned port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
@@ -600,8 +614,7 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
                     unsigned long value);
 
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
-int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-                                int type_bits, int seg);
+int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
 
 int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
 
@@ -616,6 +629,9 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
 
+unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
+void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
+
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 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,
@@ -644,6 +660,10 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
+gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
@@ -657,6 +677,7 @@ void kvm_disable_tdp(void);
 
 int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
 int complete_pio(struct kvm_vcpu *vcpu);
+bool kvm_check_iopl(struct kvm_vcpu *vcpu);
 
 struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn);
 
@@ -802,4 +823,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 
+void kvm_define_shared_msr(unsigned index, u32 msr);
+void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c584076a47f4..ffae1420e7d7 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_KVM_PARA_H
 
 #include <linux/types.h>
+#include <asm/hyperv.h>
 
 /* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
  * should be used to determine that a VM is running under KVM.
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index ba0eed8aa1a6..b60f2924c413 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -28,22 +28,39 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/hw_irq.h>
-#include <asm/kvm_para.h>
 
 /*G:030
  * 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.
  *
- * We use the KVM hypercall mechanism, though completely different hypercall
- * numbers. Seventeen hypercalls are available: the hypercall number is put in
- * the %eax register, and the arguments (when required) are placed in %ebx,
- * %ecx, %edx and %esi.  If a return value makes sense, it's returned in %eax.
+ * Our hypercall mechanism uses the highest unused trap code (traps 32 and
+ * above are used by real hardware interrupts).  Seventeen hypercalls are
+ * available: the hypercall number is put in the %eax register, and the
+ * arguments (when required) are placed in %ebx, %ecx, %edx and %esi.
+ * If a return value makes sense, it's returned in %eax.
  *
  * Grossly invalid calls result in Sudden Death at the hands of the vengeful
  * Host, rather than returning failure.  This reflects Winston Churchill's
  * 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,
+      unsigned long arg4)
+{
+        /* "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, %ebx, %ecx, %edx & %esi */
+                     : "a"(call), "b"(arg1), "c"(arg2), "d"(arg3), "S"(arg4)
+                       /* "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 */
 #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 47b9b6f19057..2e9972468a5d 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -195,41 +195,4 @@ static inline long local_sub_return(long i, local_t *l)
 #define __local_add(i, l)       local_add((i), (l))
 #define __local_sub(i, l)       local_sub((i), (l))
 
-/* Use these for per-cpu local_t variables: on some archs they are
- * much more efficient than these naive implementations.  Note they take
- * a variable, not an address.
- *
- * X86_64: This could be done better if we moved the per cpu data directly
- * after GS.
- */
-
-/* Need to disable preemption for the cpu local counters otherwise we could
-   still access a variable of a previous CPU in a non atomic way. */
-#define cpu_local_wrap_v(l)             \
-({                                      \
-        local_t res__;                  \
-        preempt_disable();              \
-        res__ = (l);                    \
-        preempt_enable();               \
-        res__;                          \
-})
-#define cpu_local_wrap(l)               \
-({                                      \
-        preempt_disable();              \
-        (l);                            \
-        preempt_enable();               \
-})                                      \
-
-#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var((l))))
-#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var((l)), (i)))
-#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var((l))))
-#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var((l))))
-#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var((l))))
-#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var((l))))
-
-#define __cpu_local_inc(l)      cpu_local_inc((l))
-#define __cpu_local_dec(l)      cpu_local_dec((l))
-#define __cpu_local_add(i, l)   cpu_local_add((i), (l))
-#define __cpu_local_sub(i, l)   cpu_local_sub((i), (l))
-
 #endif /* _ASM_X86_LOCAL_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index f1363b72364f..6c3fdd631ed3 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -108,8 +108,11 @@ struct mce_log {
 #define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
 #define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
 
+
 #ifdef __KERNEL__
 
+extern struct atomic_notifier_head x86_mce_decoder_chain;
+
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <asm/atomic.h>
@@ -118,9 +121,11 @@ extern int mce_disabled;
 extern int mce_p5_enabled;
 
 #ifdef CONFIG_X86_MCE
-void mcheck_init(struct cpuinfo_x86 *c);
+int mcheck_init(void);
+void mcheck_cpu_init(struct cpuinfo_x86 *c);
 #else
-static inline void mcheck_init(struct cpuinfo_x86 *c) {}
+static inline int mcheck_init(void) { return 0; }
+static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
 #endif
 
 #ifdef CONFIG_X86_ANCIENT_MCE
@@ -214,5 +219,11 @@ void intel_init_thermal(struct cpuinfo_x86 *c);
 
 void mce_log_therm_throt_event(__u64 status);
 
+#ifdef CONFIG_X86_THERMAL_VECTOR
+extern void mcheck_intel_therm_init(void);
+#else
+static inline void mcheck_intel_therm_init(void) { }
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index ede6998bd92c..91df7c51806c 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -47,7 +47,7 @@ static inline void resume_map_numa_kva(pgd_t *pgd) {}
 /*
  * generic node memory support, the following assumptions apply:
  *
- * 1) memory comes in 64Mb contigious chunks which are either present or not
+ * 1) memory comes in 64Mb contiguous chunks which are either present or not
  * 2) we will not have more than 64Gb in total
  *
  * for now assume that 64Gb is max amount of RAM for whole system
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index a29f48c2a322..288b96f815a6 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -39,11 +39,5 @@ static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
 #define node_start_pfn(nid)     (NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +       \
                                  NODE_DATA(nid)->node_spanned_pages)
-
-#ifdef CONFIG_NUMA_EMU
-#define FAKE_NODE_MIN_SIZE      (64 * 1024 * 1024)
-#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
-#endif
-
 #endif
 #endif /* _ASM_X86_MMZONE_64_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 79c94500c0bb..d8bf23a88d05 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -71,12 +71,7 @@ static inline void early_get_smp_config(void)
 
 static inline void find_smp_config(void)
 {
-        x86_init.mpparse.find_smp_config(1);
-}
-
-static inline void early_find_smp_config(void)
-{
-        x86_init.mpparse.find_smp_config(0);
+        x86_init.mpparse.find_smp_config();
 }
 
 #ifdef CONFIG_X86_MPPARSE
@@ -89,7 +84,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str);
 # else
 #  define default_mpc_oem_bus_info NULL
 # endif
-extern void default_find_smp_config(unsigned int reserve);
+extern void default_find_smp_config(void);
 extern void default_get_smp_config(unsigned int early);
 #else
 static inline void early_reserve_e820_mpc_new(void) { }
@@ -97,7 +92,7 @@ static inline void early_reserve_e820_mpc_new(void) { }
 #define default_mpc_apic_id NULL
 #define default_smp_read_mpc_oem NULL
 #define default_mpc_oem_bus_info NULL
-#define default_find_smp_config x86_init_uint_noop
+#define default_find_smp_config x86_init_noop
 #define default_get_smp_config x86_init_uint_noop
 #endif
 
@@ -163,14 +158,16 @@ typedef struct physid_mask physid_mask_t;
 #define physids_shift_left(d, s, n)                             \
         bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS)
 
-#define physids_coerce(map)                     ((map).mask[0])
+static inline unsigned long physids_coerce(physid_mask_t *map)
+{
+        return map->mask[0];
+}
 
-#define physids_promote(physids)                                        \
-        ({                                                              \
-                physid_mask_t __physid_mask = PHYSID_MASK_NONE;         \
-                __physid_mask.mask[0] = physids;                        \
-                __physid_mask;                                          \
-        })
+static inline void physids_promote(unsigned long physids, physid_mask_t *map)
+{
+        physids_clear(*map);
+        map->mask[0] = physids;
+}
 
 /* Note: will create very large stack frames if physid_mask_t is big */
 #define physid_mask_of_physid(physid)                                   \
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
new file mode 100644
index 000000000000..451d30e7f62d
--- /dev/null
+++ b/arch/x86/include/asm/mrst.h
@@ -0,0 +1,19 @@
+/*
+ * mrst.h: Intel Moorestown platform specific setup code
+ *
+ * (C) Copyright 2009 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#ifndef _ASM_X86_MRST_H
+#define _ASM_X86_MRST_H
+extern int pci_mrst_init(void);
+int __init sfi_parse_mrtc(struct sfi_table_header *table);
+
+#define SFI_MTMR_MAX_NUM 8
+#define SFI_MRTC_MAX    8
+
+#endif /* _ASM_X86_MRST_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4ffe09b2ad75..4604e6a54d36 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -12,6 +12,7 @@
 #define MSR_FS_BASE             0xc0000100 /* 64bit FS base */
 #define MSR_GS_BASE             0xc0000101 /* 64bit GS base */
 #define MSR_KERNEL_GS_BASE      0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX             0xc0000103 /* Auxiliary TSC */
 
 /* EFER bits: */
 #define _EFER_SCE               0  /* SYSCALL/SYSRET */
@@ -104,6 +105,8 @@
 #define MSR_AMD64_PATCH_LEVEL           0x0000008b
 #define MSR_AMD64_NB_CFG                0xc001001f
 #define MSR_AMD64_PATCH_LOADER          0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH        0xc0010140
+#define MSR_AMD64_OSVW_STATUS           0xc0010141
 #define MSR_AMD64_IBSFETCHCTL           0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD         0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD        0xc0011032
@@ -123,6 +126,7 @@
 #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
 #define FAM10H_MMIO_CONF_BASE_MASK      0xfffffff
 #define FAM10H_MMIO_CONF_BASE_SHIFT     20
+#define MSR_FAM10H_NODE_ID              0xc001100c
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1                 0xc001001a
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 7e2b6ba962ff..c5bc4c2d33f5 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -27,6 +27,18 @@ struct msr {
         };
 };
 
+struct msr_info {
+        u32 msr_no;
+        struct msr reg;
+        struct msr *msrs;
+        int err;
+};
+
+struct msr_regs_info {
+        u32 *regs;
+        int err;
+};
+
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
         unsigned long low, high;
@@ -240,15 +252,18 @@ do {                                                            \
 #define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val),         \
                                              (u32)((val) >> 32))
 
-#define write_tsc(val1, val2) wrmsr(0x10, (val1), (val2))
+#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))
+
+#define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0)
 
-#define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
+struct msr *msrs_alloc(void);
+void msrs_free(struct msr *msrs);
 
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
-void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
+void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs);
+void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
@@ -264,12 +279,12 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
         wrmsr(msr_no, l, h);
         return 0;
 }
-static inline void rdmsr_on_cpus(const cpumask_t *m, u32 msr_no,
+static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no,
                                 struct msr *msrs)
 {
        rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h));
 }
-static inline void wrmsr_on_cpus(const cpumask_t *m, u32 msr_no,
+static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no,
                                 struct msr *msrs)
 {
        wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h);
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 139d4c1a33a7..93da9c3f3341 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -19,7 +19,6 @@ extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int check_nmi_watchdog(void);
 extern int nmi_watchdog_enabled;
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
-extern int avail_to_resrv_perfctr_nmi(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);
 extern int reserve_evntsel_nmi(unsigned int);
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index c4ae822e415f..823e070e7c26 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -36,6 +36,11 @@ extern void __cpuinit numa_set_node(int cpu, int node);
 extern void __cpuinit numa_clear_node(int cpu);
 extern void __cpuinit numa_add_cpu(int cpu);
 extern void __cpuinit numa_remove_cpu(int cpu);
+
+#ifdef CONFIG_NUMA_EMU
+#define FAKE_NODE_MIN_SIZE      ((u64)64 << 20)
+#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
+#endif /* CONFIG_NUMA_EMU */
 #else
 static inline void init_cpu_to_node(void)               { }
 static inline void numa_set_node(int cpu, int node)     { }
diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h
index 9f0a5f5d29ec..37c516545ec8 100644
--- a/arch/x86/include/asm/numaq.h
+++ b/arch/x86/include/asm/numaq.h
@@ -30,9 +30,14 @@
 
 extern int found_numaq;
 extern int get_memcfg_numaq(void);
+extern int pci_numaq_init(void);
 
 extern void *xquad_portio;
 
+#define XQUAD_PORTIO_BASE 0xfe400000
+#define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
+#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port)
+
 /*
  * SYS_CFG_DATA_PRIV_ADDR, struct eachquadmem, and struct sys_cfg_data are the
  */
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
index 834a30295fab..101229b0d8ed 100644
--- a/arch/x86/include/asm/olpc.h
+++ b/arch/x86/include/asm/olpc.h
@@ -13,7 +13,6 @@ struct olpc_platform_t {
 
 #define OLPC_F_PRESENT          0x01
 #define OLPC_F_DCON             0x02
-#define OLPC_F_VSA              0x04
 
 #ifdef CONFIG_OLPC
 
@@ -51,18 +50,6 @@ static inline int olpc_has_dcon(void)
 }
 
 /*
- * The VSA is software from AMD that typical Geode bioses will include.
- * It is used to emulate the PCI bus, VGA, etc.  OLPC's Open Firmware does
- * not include the VSA; instead, PCI is emulated by the kernel.
- *
- * The VSA is described further in arch/x86/pci/olpc.c.
- */
-static inline int olpc_has_vsa(void)
-{
-        return (olpc_platform_info.flags & OLPC_F_VSA) ? 1 : 0;
-}
-
-/*
  * The "Mass Production" version of OLPC's XO is identified as being model
  * C2.  During the prototype phase, the following models (in chronological
  * order) were created: A1, B1, B2, B3, B4, C1.  The A1 through B2 models
@@ -87,13 +74,10 @@ static inline int olpc_has_dcon(void)
         return 0;
 }
 
-static inline int olpc_has_vsa(void)
-{
-        return 0;
-}
-
 #endif
 
+extern int pci_olpc_init(void);
+
 /* EC related functions */
 
 extern int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen,
@@ -120,7 +104,7 @@ extern int olpc_ec_mask_unset(uint8_t bits);
 
 /* GPIO assignments */
 
-#define OLPC_GPIO_MIC_AC        geode_gpio(1)
+#define OLPC_GPIO_MIC_AC        1
 #define OLPC_GPIO_DCON_IRQ      geode_gpio(7)
 #define OLPC_GPIO_THRM_ALRM     geode_gpio(10)
 #define OLPC_GPIO_SMB_CLK       geode_gpio(14)
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 6473f5ccff85..a667f24c7254 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -40,7 +40,6 @@
 
 #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;
@@ -49,7 +48,8 @@ extern unsigned long max_pfn_mapped;
 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 initmem_init(unsigned long start_pfn, unsigned long end_pfn,
+                                int acpi, int k8);
 extern void free_initmem(void);
 
 #endif  /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index efb38994859c..5653f43d90e5 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -435,15 +435,6 @@ static inline void paravirt_release_pud(unsigned long pfn)
         PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
 }
 
-#ifdef CONFIG_HIGHPTE
-static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
-{
-        unsigned long ret;
-        ret = PVOP_CALL2(unsigned long, pv_mmu_ops.kmap_atomic_pte, page, type);
-        return (void *)ret;
-}
-#endif
-
 static inline void pte_update(struct mm_struct *mm, unsigned long addr,
                               pte_t *ptep)
 {
@@ -731,34 +722,34 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
-static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
+static inline int arch_spin_is_locked(struct arch_spinlock *lock)
 {
         return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
 }
 
-static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
+static inline int arch_spin_is_contended(struct arch_spinlock *lock)
 {
         return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
 }
-#define __raw_spin_is_contended __raw_spin_is_contended
+#define arch_spin_is_contended  arch_spin_is_contended
 
-static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
+static __always_inline void arch_spin_lock(struct arch_spinlock *lock)
 {
         PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
 }
 
-static __always_inline void __raw_spin_lock_flags(struct raw_spinlock *lock,
+static __always_inline void arch_spin_lock_flags(struct arch_spinlock *lock,
                                                   unsigned long flags)
 {
         PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
 }
 
-static __always_inline int __raw_spin_trylock(struct raw_spinlock *lock)
+static __always_inline int arch_spin_trylock(struct arch_spinlock *lock)
 {
         return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
 }
 
-static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
+static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
 {
         PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
 }
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 9357473c8da0..db9ef5532341 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -304,10 +304,6 @@ struct pv_mmu_ops {
 #endif  /* PAGETABLE_LEVELS == 4 */
 #endif  /* PAGETABLE_LEVELS >= 3 */
 
-#ifdef CONFIG_HIGHPTE
-        void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
-#endif
-
         struct pv_lazy_ops lazy_mode;
 
         /* dom0 ops */
@@ -318,14 +314,14 @@ struct pv_mmu_ops {
                            phys_addr_t phys, pgprot_t flags);
 };
 
-struct raw_spinlock;
+struct arch_spinlock;
 struct pv_lock_ops {
-        int (*spin_is_locked)(struct raw_spinlock *lock);
-        int (*spin_is_contended)(struct raw_spinlock *lock);
-        void (*spin_lock)(struct raw_spinlock *lock);
-        void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags);
-        int (*spin_trylock)(struct raw_spinlock *lock);
-        void (*spin_unlock)(struct raw_spinlock *lock);
+        int (*spin_is_locked)(struct arch_spinlock *lock);
+        int (*spin_is_contended)(struct arch_spinlock *lock);
+        void (*spin_lock)(struct arch_spinlock *lock);
+        void (*spin_lock_flags)(struct arch_spinlock *lock, unsigned long flags);
+        int (*spin_trylock)(struct arch_spinlock *lock);
+        void (*spin_unlock)(struct arch_spinlock *lock);
 };
 
 /* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index ada8c201d513..404a880ea325 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -45,8 +45,15 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 
 #ifdef CONFIG_PCI
 extern unsigned int pcibios_assign_all_busses(void);
+extern int pci_legacy_init(void);
+# ifdef CONFIG_ACPI
+#  define x86_default_pci_init pci_acpi_init
+# else
+#  define x86_default_pci_init pci_legacy_init
+# endif
 #else
-#define pcibios_assign_all_busses()     0
+# define pcibios_assign_all_busses()    0
+# define x86_default_pci_init           NULL
 #endif
 
 extern unsigned long pci_mem_start;
@@ -90,40 +97,14 @@ extern void pci_iommu_alloc(void);
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || 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))
-
-#else
-
-#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
 
+void dma32_reserve_bootmem(void);
+
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index ae5e40f67daf..fe15cfb21b9b 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -22,8 +22,6 @@ extern int (*pci_config_read)(int seg, int bus, int dev, int fn,
 extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
                                int reg, int len, u32 value);
 
-extern void dma32_reserve_bootmem(void);
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_PCI_64_H */
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index b399988eee3a..1a0422348d6d 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -29,6 +29,7 @@
 #define PCI_CHECK_ENABLE_AMD_MMCONF     0x20000
 #define PCI_HAS_IO_ECS          0x40000
 #define PCI_NOASSIGN_ROMS       0x80000
+#define PCI_ROOT_NO_CRS         0x100000
 
 extern unsigned int pci_probe;
 extern unsigned long pirq_table_addr;
@@ -82,7 +83,6 @@ struct irq_routing_table {
 
 extern unsigned int pcibios_irq_mask;
 
-extern int pcibios_scanned;
 extern spinlock_t pci_config_lock;
 
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
@@ -105,24 +105,39 @@ extern bool port_cf9_safe;
 extern int pci_direct_probe(void);
 extern void pci_direct_init(int type);
 extern void pci_pcbios_init(void);
-extern int pci_olpc_init(void);
 extern void __init dmi_check_pciprobe(void);
 extern void __init dmi_check_skip_isa_align(void);
 
 /* some common used subsys_initcalls */
 extern int __init pci_acpi_init(void);
-extern int __init pcibios_irq_init(void);
-extern int __init pci_visws_init(void);
-extern int __init pci_numaq_init(void);
+extern void __init pcibios_irq_init(void);
 extern int __init pcibios_init(void);
+extern int pci_legacy_init(void);
+extern void pcibios_fixup_irqs(void);
 
 /* pci-mmconfig.c */
 
+/* "PCI MMCONFIG %04x [bus %02x-%02x]" */
+#define PCI_MMCFG_RESOURCE_NAME_LEN (22 + 4 + 2 + 2)
+
+struct pci_mmcfg_region {
+        struct list_head list;
+        struct resource res;
+        u64 address;
+        char __iomem *virt;
+        u16 segment;
+        u8 start_bus;
+        u8 end_bus;
+        char name[PCI_MMCFG_RESOURCE_NAME_LEN];
+};
+
 extern int __init pci_mmcfg_arch_init(void);
 extern void __init pci_mmcfg_arch_free(void);
+extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus);
+
+extern struct list_head pci_mmcfg_list;
 
-extern struct acpi_mcfg_allocation *pci_mmcfg_config;
-extern int pci_mmcfg_config_num;
+#define PCI_MMCFG_BUS_OFFSET(bus)      ((bus) << 20)
 
 /*
  * AMD Fam10h CPUs are buggy, and cannot access MMIO config space
@@ -166,3 +181,17 @@ static inline void mmio_config_writel(void __iomem *pos, u32 val)
 {
         asm volatile("movl %%eax,(%1)" : : "a" (val), "r" (pos) : "memory");
 }
+
+#ifdef CONFIG_PCI
+# ifdef CONFIG_ACPI
+#  define x86_default_pci_init          pci_acpi_init
+# else
+#  define x86_default_pci_init          pci_legacy_init
+# endif
+# define x86_default_pci_init_irq       pcibios_irq_init
+# define x86_default_pci_fixup_irqs     pcibios_fixup_irqs
+#else
+# define x86_default_pci_init           NULL
+# define x86_default_pci_init_irq       NULL
+# define x86_default_pci_fixup_irqs     NULL
+#endif
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index b65a36defeb7..66a272dfd8b8 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -25,19 +25,18 @@
  */
 #ifdef CONFIG_SMP
 #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)        %__percpu_seg:per_cpu__##var
+        __percpu_mov_op %__percpu_seg:this_cpu_off, reg;                \
+        lea var(reg), reg
+#define PER_CPU_VAR(var)        %__percpu_seg:var
 #else /* ! SMP */
-#define PER_CPU(var, reg)                                               \
-        __percpu_mov_op $per_cpu__##var, reg
-#define PER_CPU_VAR(var)        per_cpu__##var
+#define PER_CPU(var, reg)       __percpu_mov_op $var, reg
+#define PER_CPU_VAR(var)        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
+#define INIT_PER_CPU_VAR(var)  var
 #endif
 
 #else /* ...!ASSEMBLY */
@@ -60,12 +59,12 @@
  * There also must be an entry in vmlinux_64.lds.S
  */
 #define DECLARE_INIT_PER_CPU(var) \
-       extern typeof(per_cpu_var(var)) init_per_cpu_var(var)
+       extern typeof(var) init_per_cpu_var(var)
 
 #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)
+#define init_per_cpu_var(var)  var
 #endif
 
 /* For arch-specific code, we can use direct single-insn ops (they
@@ -74,63 +73,121 @@ extern void __bad_percpu_size(void);
 
 #define percpu_to_op(op, var, val)                      \
 do {                                                    \
-        typedef typeof(var) T__;                        \
+        typedef typeof(var) pto_T__;                    \
         if (0) {                                        \
-                T__ tmp__;                              \
-                tmp__ = (val);                          \
+                pto_T__ pto_tmp__;                      \
+                pto_tmp__ = (val);                      \
         }                                               \
         switch (sizeof(var)) {                          \
         case 1:                                         \
                 asm(op "b %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "qi" ((T__)(val)));               \
+                    : "qi" ((pto_T__)(val)));           \
                 break;                                  \
         case 2:                                         \
                 asm(op "w %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "ri" ((T__)(val)));               \
+                    : "ri" ((pto_T__)(val)));           \
                 break;                                  \
         case 4:                                         \
                 asm(op "l %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "ri" ((T__)(val)));               \
+                    : "ri" ((pto_T__)(val)));           \
                 break;                                  \
         case 8:                                         \
                 asm(op "q %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "re" ((T__)(val)));               \
+                    : "re" ((pto_T__)(val)));           \
                 break;                                  \
         default: __bad_percpu_size();                   \
         }                                               \
 } while (0)
 
+/*
+ * Generate a percpu add to memory instruction and optimize code
+ * if a one is added or subtracted.
+ */
+#define percpu_add_op(var, val)                                         \
+do {                                                                    \
+        typedef typeof(var) pao_T__;                                    \
+        const int pao_ID__ = (__builtin_constant_p(val) &&              \
+                              ((val) == 1 || (val) == -1)) ? (val) : 0; \
+        if (0) {                                                        \
+                pao_T__ pao_tmp__;                                      \
+                pao_tmp__ = (val);                                      \
+        }                                                               \
+        switch (sizeof(var)) {                                          \
+        case 1:                                                         \
+                if (pao_ID__ == 1)                                      \
+                        asm("incb "__percpu_arg(0) : "+m" (var));       \
+                else if (pao_ID__ == -1)                                \
+                        asm("decb "__percpu_arg(0) : "+m" (var));       \
+                else                                                    \
+                        asm("addb %1, "__percpu_arg(0)                  \
+                            : "+m" (var)                                \
+                            : "qi" ((pao_T__)(val)));                   \
+                break;                                                  \
+        case 2:                                                         \
+                if (pao_ID__ == 1)                                      \
+                        asm("incw "__percpu_arg(0) : "+m" (var));       \
+                else if (pao_ID__ == -1)                                \
+                        asm("decw "__percpu_arg(0) : "+m" (var));       \
+                else                                                    \
+                        asm("addw %1, "__percpu_arg(0)                  \
+                            : "+m" (var)                                \
+                            : "ri" ((pao_T__)(val)));                   \
+                break;                                                  \
+        case 4:                                                         \
+                if (pao_ID__ == 1)                                      \
+                        asm("incl "__percpu_arg(0) : "+m" (var));       \
+                else if (pao_ID__ == -1)                                \
+                        asm("decl "__percpu_arg(0) : "+m" (var));       \
+                else                                                    \
+                        asm("addl %1, "__percpu_arg(0)                  \
+                            : "+m" (var)                                \
+                            : "ri" ((pao_T__)(val)));                   \
+                break;                                                  \
+        case 8:                                                         \
+                if (pao_ID__ == 1)                                      \
+                        asm("incq "__percpu_arg(0) : "+m" (var));       \
+                else if (pao_ID__ == -1)                                \
+                        asm("decq "__percpu_arg(0) : "+m" (var));       \
+                else                                                    \
+                        asm("addq %1, "__percpu_arg(0)                  \
+                            : "+m" (var)                                \
+                            : "re" ((pao_T__)(val)));                   \
+                break;                                                  \
+        default: __bad_percpu_size();                                   \
+        }                                                               \
+} while (0)
+
 #define percpu_from_op(op, var, constraint)             \
 ({                                                      \
-        typeof(var) ret__;                              \
+        typeof(var) pfo_ret__;                          \
         switch (sizeof(var)) {                          \
         case 1:                                         \
                 asm(op "b "__percpu_arg(1)",%0"         \
-                    : "=q" (ret__)                      \
+                    : "=q" (pfo_ret__)                  \
                     : constraint);                      \
                 break;                                  \
         case 2:                                         \
                 asm(op "w "__percpu_arg(1)",%0"         \
-                    : "=r" (ret__)                      \
+                    : "=r" (pfo_ret__)                  \
                     : constraint);                      \
                 break;                                  \
         case 4:                                         \
                 asm(op "l "__percpu_arg(1)",%0"         \
-                    : "=r" (ret__)                      \
+                    : "=r" (pfo_ret__)                  \
                     : constraint);                      \
                 break;                                  \
         case 8:                                         \
                 asm(op "q "__percpu_arg(1)",%0"         \
-                    : "=r" (ret__)                      \
+                    : "=r" (pfo_ret__)                  \
                     : constraint);                      \
                 break;                                  \
         default: __bad_percpu_size();                   \
         }                                               \
-        ret__;                                          \
+        pfo_ret__;                                      \
 })
 
 /*
@@ -142,23 +199,99 @@ do {							\
  * per-thread variables implemented as per-cpu variables and thus
  * stable for the duration of the respective task.
  */
-#define percpu_read(var)        percpu_from_op("mov", per_cpu__##var,   \
-                                               "m" (per_cpu__##var))
-#define percpu_read_stable(var) percpu_from_op("mov", per_cpu__##var,   \
-                                               "p" (&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)
+#define percpu_read(var)                percpu_from_op("mov", var, "m" (var))
+#define percpu_read_stable(var)         percpu_from_op("mov", var, "p" (&(var)))
+#define percpu_write(var, val)          percpu_to_op("mov", var, val)
+#define percpu_add(var, val)            percpu_add_op(var, val)
+#define percpu_sub(var, val)            percpu_add_op(var, -(val))
+#define percpu_and(var, val)            percpu_to_op("and", var, val)
+#define percpu_or(var, val)             percpu_to_op("or", var, val)
+#define percpu_xor(var, val)            percpu_to_op("xor", var, val)
+
+#define __this_cpu_read_1(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_read_2(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_read_4(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
+
+#define __this_cpu_write_1(pcp, val)    percpu_to_op("mov", (pcp), val)
+#define __this_cpu_write_2(pcp, val)    percpu_to_op("mov", (pcp), val)
+#define __this_cpu_write_4(pcp, val)    percpu_to_op("mov", (pcp), val)
+#define __this_cpu_add_1(pcp, val)      percpu_add_op((pcp), val)
+#define __this_cpu_add_2(pcp, val)      percpu_add_op((pcp), val)
+#define __this_cpu_add_4(pcp, val)      percpu_add_op((pcp), val)
+#define __this_cpu_and_1(pcp, val)      percpu_to_op("and", (pcp), val)
+#define __this_cpu_and_2(pcp, val)      percpu_to_op("and", (pcp), val)
+#define __this_cpu_and_4(pcp, val)      percpu_to_op("and", (pcp), val)
+#define __this_cpu_or_1(pcp, val)       percpu_to_op("or", (pcp), val)
+#define __this_cpu_or_2(pcp, val)       percpu_to_op("or", (pcp), val)
+#define __this_cpu_or_4(pcp, val)       percpu_to_op("or", (pcp), val)
+#define __this_cpu_xor_1(pcp, val)      percpu_to_op("xor", (pcp), val)
+#define __this_cpu_xor_2(pcp, val)      percpu_to_op("xor", (pcp), val)
+#define __this_cpu_xor_4(pcp, val)      percpu_to_op("xor", (pcp), val)
+
+#define this_cpu_read_1(pcp)            percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_2(pcp)            percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_4(pcp)            percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_1(pcp, val)      percpu_to_op("mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)      percpu_to_op("mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)      percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_1(pcp, val)        percpu_add_op((pcp), val)
+#define this_cpu_add_2(pcp, val)        percpu_add_op((pcp), val)
+#define this_cpu_add_4(pcp, val)        percpu_add_op((pcp), val)
+#define this_cpu_and_1(pcp, val)        percpu_to_op("and", (pcp), val)
+#define this_cpu_and_2(pcp, val)        percpu_to_op("and", (pcp), val)
+#define this_cpu_and_4(pcp, val)        percpu_to_op("and", (pcp), val)
+#define this_cpu_or_1(pcp, val)         percpu_to_op("or", (pcp), val)
+#define this_cpu_or_2(pcp, val)         percpu_to_op("or", (pcp), val)
+#define this_cpu_or_4(pcp, val)         percpu_to_op("or", (pcp), val)
+#define this_cpu_xor_1(pcp, val)        percpu_to_op("xor", (pcp), val)
+#define this_cpu_xor_2(pcp, val)        percpu_to_op("xor", (pcp), val)
+#define this_cpu_xor_4(pcp, val)        percpu_to_op("xor", (pcp), val)
+
+#define irqsafe_cpu_add_1(pcp, val)     percpu_add_op((pcp), val)
+#define irqsafe_cpu_add_2(pcp, val)     percpu_add_op((pcp), val)
+#define irqsafe_cpu_add_4(pcp, val)     percpu_add_op((pcp), val)
+#define irqsafe_cpu_and_1(pcp, val)     percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_and_2(pcp, val)     percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_and_4(pcp, val)     percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_or_1(pcp, val)      percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_or_2(pcp, val)      percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_or_4(pcp, val)      percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_xor_1(pcp, val)     percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xor_2(pcp, val)     percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xor_4(pcp, val)     percpu_to_op("xor", (pcp), val)
+
+/*
+ * Per cpu atomic 64 bit operations are only available under 64 bit.
+ * 32 bit must fall back to generic operations.
+ */
+#ifdef CONFIG_X86_64
+#define __this_cpu_read_8(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_write_8(pcp, val)    percpu_to_op("mov", (pcp), val)
+#define __this_cpu_add_8(pcp, val)      percpu_add_op((pcp), val)
+#define __this_cpu_and_8(pcp, val)      percpu_to_op("and", (pcp), val)
+#define __this_cpu_or_8(pcp, val)       percpu_to_op("or", (pcp), val)
+#define __this_cpu_xor_8(pcp, val)      percpu_to_op("xor", (pcp), val)
+
+#define this_cpu_read_8(pcp)            percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_8(pcp, val)      percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_8(pcp, val)        percpu_add_op((pcp), val)
+#define this_cpu_and_8(pcp, val)        percpu_to_op("and", (pcp), val)
+#define this_cpu_or_8(pcp, val)         percpu_to_op("or", (pcp), val)
+#define this_cpu_xor_8(pcp, val)        percpu_to_op("xor", (pcp), val)
+
+#define irqsafe_cpu_add_8(pcp, val)     percpu_add_op((pcp), val)
+#define irqsafe_cpu_and_8(pcp, val)     percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_or_8(pcp, val)      percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_xor_8(pcp, val)     percpu_to_op("xor", (pcp), val)
+
+#endif
 
 /* 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)              \
+                     : "=r" (old__), "+m" (var)                         \
                      : "dIr" (bit));                                    \
         old__;                                                          \
 })
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index ad7ce3fd5065..db6109a885a7 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -18,7 +18,8 @@
 #define MSR_ARCH_PERFMON_EVENTSEL0                           0x186
 #define MSR_ARCH_PERFMON_EVENTSEL1                           0x187
 
-#define ARCH_PERFMON_EVENTSEL0_ENABLE                     (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_ENABLE                      (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_ANY                         (1 << 21)
 #define ARCH_PERFMON_EVENTSEL_INT                         (1 << 20)
 #define ARCH_PERFMON_EVENTSEL_OS                          (1 << 17)
 #define ARCH_PERFMON_EVENTSEL_USR                         (1 << 16)
@@ -26,11 +27,34 @@
 /*
  * Includes eventsel and unit mask as well:
  */
-#define ARCH_PERFMON_EVENT_MASK                             0xffff
+
+
+#define INTEL_ARCH_EVTSEL_MASK          0x000000FFULL
+#define INTEL_ARCH_UNIT_MASK            0x0000FF00ULL
+#define INTEL_ARCH_EDGE_MASK            0x00040000ULL
+#define INTEL_ARCH_INV_MASK             0x00800000ULL
+#define INTEL_ARCH_CNT_MASK             0xFF000000ULL
+#define INTEL_ARCH_EVENT_MASK   (INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK)
+
+/*
+ * filter mask to validate fixed counter events.
+ * the following filters disqualify for fixed counters:
+ *  - inv
+ *  - edge
+ *  - cnt-mask
+ *  The other filters are supported by fixed counters.
+ *  The any-thread option is supported starting with v3.
+ */
+#define INTEL_ARCH_FIXED_MASK \
+        (INTEL_ARCH_CNT_MASK| \
+         INTEL_ARCH_INV_MASK| \
+         INTEL_ARCH_EDGE_MASK|\
+         INTEL_ARCH_UNIT_MASK|\
+         INTEL_ARCH_EVENT_MASK)
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL                 0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK         (0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX                  0
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX                  0
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
                 (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
 
@@ -93,6 +117,18 @@ union cpuid10_edx {
  */
 #define X86_PMC_IDX_FIXED_BTS                           (X86_PMC_IDX_FIXED + 16)
 
+/* IbsFetchCtl bits/masks */
+#define IBS_FETCH_RAND_EN               (1ULL<<57)
+#define IBS_FETCH_VAL                   (1ULL<<49)
+#define IBS_FETCH_ENABLE                (1ULL<<48)
+#define IBS_FETCH_CNT                   0xFFFF0000ULL
+#define IBS_FETCH_MAX_CNT               0x0000FFFFULL
+
+/* IbsOpCtl bits */
+#define IBS_OP_CNT_CTL                  (1ULL<<19)
+#define IBS_OP_VAL                      (1ULL<<18)
+#define IBS_OP_ENABLE                   (1ULL<<17)
+#define IBS_OP_MAX_CNT                  0x0000FFFFULL
 
 #ifdef CONFIG_PERF_EVENTS
 extern void init_hw_perf_events(void);
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 0e8c2a0fd922..271de94c3810 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -23,6 +23,11 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
 #endif
 
 /*
+ * Flags to use when allocating a user page table page.
+ */
+extern gfp_t __userpte_alloc_gfp;
+
+/*
  * Allocate and free page tables.
  */
 extern pgd_t *pgd_alloc(struct mm_struct *);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index af6fd360ab35..a34c785c5a63 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -16,6 +16,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/x86_init.h>
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -270,9 +272,9 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
                                          unsigned long new_flags)
 {
         /*
-         * PAT type is always WB for ISA. So no need to check.
+         * PAT type is always WB for untracked ranges, so no need to check.
          */
-        if (is_ISA_range(paddr, paddr + size - 1))
+        if (x86_platform.is_untracked_pat_range(paddr, paddr + size))
                 return 1;
 
         /*
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 01fd9461d323..2984a25ff383 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -19,7 +19,6 @@
 #include <asm/paravirt.h>
 
 #include <linux/bitops.h>
-#include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 
@@ -54,10 +53,10 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
          in_irq() ? KM_IRQ_PTE :        \
          KM_PTE0)
 #define pte_offset_map(dir, address)                                    \
-        ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), __KM_PTE) +         \
+        ((pte_t *)kmap_atomic(pmd_page(*(dir)), __KM_PTE) +             \
          pte_index((address)))
 #define pte_offset_map_nested(dir, address)                             \
-        ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE1) +          \
+        ((pte_t *)kmap_atomic(pmd_page(*(dir)), KM_PTE1) +              \
          pte_index((address)))
 #define pte_unmap(pte) kunmap_atomic((pte), __KM_PTE)
 #define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1)
@@ -80,7 +79,7 @@ do {						\
  * The i386 doesn't have any external MMU info: the kernel page
  * tables contain all the necessary information.
  */
-#define update_mmu_cache(vma, address, pte) do { } while (0)
+#define update_mmu_cache(vma, address, ptep) do { } while (0)
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index c57a30117149..181be528c612 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -129,7 +129,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 #define pte_unmap(pte) /* NOP */
 #define pte_unmap_nested(pte) /* NOP */
 
-#define update_mmu_cache(vma, address, pte) do { } while (0)
+#define update_mmu_cache(vma, address, ptep) do { } while (0)
 
 /* Encode and de-code a swap entry */
 #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index e75daac64962..91d323f47364 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -30,6 +30,7 @@ struct mm_struct;
 #include <linux/math64.h>
 #include <linux/init.h>
 
+#define HBP_NUM 4
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
@@ -182,7 +183,7 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
                                 unsigned int *ecx, unsigned int *edx)
 {
         /* ecx is often an input as well as an output. */
-        asm("cpuid"
+        asm volatile("cpuid"
             : "=a" (*eax),
               "=b" (*ebx),
               "=c" (*ecx),
@@ -424,6 +425,8 @@ extern unsigned int xstate_size;
 extern void free_thread_xstate(struct task_struct *);
 extern struct kmem_cache *task_xstate_cachep;
 
+struct perf_event;
+
 struct thread_struct {
         /* Cached TLS descriptors: */
         struct desc_struct      tls_array[GDT_ENTRY_TLS_ENTRIES];
@@ -445,13 +448,12 @@ struct thread_struct {
         unsigned long           fs;
 #endif
         unsigned long           gs;
-        /* Hardware debugging registers: */
-        unsigned long           debugreg0;
-        unsigned long           debugreg1;
-        unsigned long           debugreg2;
-        unsigned long           debugreg3;
-        unsigned long           debugreg6;
-        unsigned long           debugreg7;
+        /* Save middle states of ptrace breakpoints */
+        struct perf_event       *ptrace_bps[HBP_NUM];
+        /* Debug status used for traps, single steps, etc... */
+        unsigned long           debugreg6;
+        /* Keep track of the exact dr7 value set by the user */
+        unsigned long           ptrace_dr7;
         /* Fault info: */
         unsigned long           cr2;
         unsigned long           trap_no;
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 621f56d73121..6f414ed88620 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -5,31 +5,22 @@
 
 /* misc architecture specific prototypes */
 
-extern void early_idt_handler(void);
+void early_idt_handler(void);
 
-extern void system_call(void);
-extern void syscall_init(void);
+void system_call(void);
+void syscall_init(void);
 
-extern void ia32_syscall(void);
-extern void ia32_cstar_target(void);
-extern void ia32_sysenter_target(void);
+void ia32_syscall(void);
+void ia32_cstar_target(void);
+void ia32_sysenter_target(void);
 
-extern void syscall32_cpu_init(void);
+void syscall32_cpu_init(void);
 
-extern void check_efer(void);
+void x86_configure_nx(void);
+void x86_report_nx(void);
 
 extern int reboot_force;
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x,y) ((__typeof__(x))((y)-1))
-#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
-#define round_down(x,y) ((x) & ~__round_mask(x,y))
-
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 0f0d908349aa..69a686a7dff0 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -7,6 +7,7 @@
 
 #ifdef __KERNEL__
 #include <asm/segment.h>
+#include <asm/page_types.h>
 #endif
 
 #ifndef __ASSEMBLY__
@@ -216,20 +217,72 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs)
         return regs->sp;
 }
 
-/*
- * These are defined as per linux/ptrace.h, which see.
+/* Query offset/name of register from its name/offset */
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, ss))
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:       pt_regs from which register value is gotten.
+ * @offset:     offset number of the register.
+ *
+ * regs_get_register returns the value of a register. The @offset is the
+ * offset of the register in struct pt_regs address which specified by @regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
  */
-#define arch_has_single_step()  (1)
-extern void user_enable_single_step(struct task_struct *);
-extern void user_disable_single_step(struct task_struct *);
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+                                              unsigned int offset)
+{
+        if (unlikely(offset > MAX_REG_OFFSET))
+                return 0;
+        return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:       pt_regs which contains kernel stack pointer.
+ * @addr:       address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static inline int regs_within_kernel_stack(struct pt_regs *regs,
+                                           unsigned long addr)
+{
+        return ((addr & ~(THREAD_SIZE - 1))  ==
+                (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)));
+}
 
-extern void user_enable_block_step(struct task_struct *);
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:       pt_regs which contains kernel stack pointer.
+ * @n:          stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+                                                      unsigned int n)
+{
+        unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+        addr += n;
+        if (regs_within_kernel_stack(regs, (unsigned long)addr))
+                return *addr;
+        else
+                return 0;
+}
+
+#define arch_has_single_step()  (1)
 #ifdef CONFIG_X86_DEBUGCTLMSR
 #define arch_has_block_step()   (1)
 #else
 #define arch_has_block_step()   (boot_cpu_data.x86 >= 6)
 #endif
 
+#define ARCH_HAS_USER_SINGLE_STEP_INFO
+
 struct user_desc;
 extern int do_get_thread_area(struct task_struct *p, int idx,
                               struct user_desc __user *info);
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index ca7517d33776..606ede126972 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -41,6 +41,7 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/lockdep.h>
+#include <asm/asm.h>
 
 struct rwsem_waiter;
 
@@ -55,17 +56,28 @@ extern asmregparm struct rw_semaphore *
 
 /*
  * the semaphore definition
+ *
+ * The bias values and the counter type limits the number of
+ * potential readers/writers to 32767 for 32 bits and 2147483647
+ * for 64 bits.
  */
 
-#define RWSEM_UNLOCKED_VALUE            0x00000000
-#define RWSEM_ACTIVE_BIAS               0x00000001
-#define RWSEM_ACTIVE_MASK               0x0000ffff
-#define RWSEM_WAITING_BIAS              (-0x00010000)
+#ifdef CONFIG_X86_64
+# define RWSEM_ACTIVE_MASK              0xffffffffL
+#else
+# define RWSEM_ACTIVE_MASK              0x0000ffffL
+#endif
+
+#define RWSEM_UNLOCKED_VALUE            0x00000000L
+#define RWSEM_ACTIVE_BIAS               0x00000001L
+#define RWSEM_WAITING_BIAS              (-RWSEM_ACTIVE_MASK-1)
 #define RWSEM_ACTIVE_READ_BIAS          RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS         (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
+typedef signed long rwsem_count_t;
+
 struct rw_semaphore {
-        signed long             count;
+        rwsem_count_t           count;
         spinlock_t              wait_lock;
         struct list_head        wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -105,7 +117,7 @@ do {								\
 static inline void __down_read(struct rw_semaphore *sem)
 {
         asm volatile("# beginning down_read\n\t"
-                     LOCK_PREFIX "  incl      (%%eax)\n\t"
+                     LOCK_PREFIX _ASM_INC "(%1)\n\t"
                      /* adds 0x00000001, returns the old value */
                      "  jns        1f\n"
                      "  call call_rwsem_down_read_failed\n"
@@ -121,14 +133,14 @@ static inline void __down_read(struct rw_semaphore *sem)
  */
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
-        __s32 result, tmp;
+        rwsem_count_t result, tmp;
         asm volatile("# beginning __down_read_trylock\n\t"
-                     "  movl      %0,%1\n\t"
+                     "  mov          %0,%1\n\t"
                      "1:\n\t"
-                     "  movl         %1,%2\n\t"
-                     "  addl      %3,%2\n\t"
+                     "  mov          %1,%2\n\t"
+                     "  add          %3,%2\n\t"
                      "  jle          2f\n\t"
-                     LOCK_PREFIX "  cmpxchgl  %2,%0\n\t"
+                     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
                      "  jnz          1b\n\t"
                      "2:\n\t"
                      "# ending __down_read_trylock\n\t"
@@ -143,13 +155,13 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
  */
 static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 {
-        int tmp;
+        rwsem_count_t tmp;
 
         tmp = RWSEM_ACTIVE_WRITE_BIAS;
         asm volatile("# beginning down_write\n\t"
-                     LOCK_PREFIX "  xadd      %%edx,(%%eax)\n\t"
+                     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                      /* subtract 0x0000ffff, returns the old value */
-                     "  testl     %%edx,%%edx\n\t"
+                     "  test      %1,%1\n\t"
                      /* was the count 0 before? */
                      "  jz        1f\n"
                      "  call call_rwsem_down_write_failed\n"
@@ -170,9 +182,9 @@ static inline void __down_write(struct rw_semaphore *sem)
  */
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-        signed long ret = cmpxchg(&sem->count,
-                                  RWSEM_UNLOCKED_VALUE,
-                                  RWSEM_ACTIVE_WRITE_BIAS);
+        rwsem_count_t ret = cmpxchg(&sem->count,
+                                    RWSEM_UNLOCKED_VALUE,
+                                    RWSEM_ACTIVE_WRITE_BIAS);
         if (ret == RWSEM_UNLOCKED_VALUE)
                 return 1;
         return 0;
@@ -183,9 +195,9 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
  */
 static inline void __up_read(struct rw_semaphore *sem)
 {
-        __s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
+        rwsem_count_t tmp = -RWSEM_ACTIVE_READ_BIAS;
         asm volatile("# beginning __up_read\n\t"
-                     LOCK_PREFIX "  xadd      %%edx,(%%eax)\n\t"
+                     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                      /* subtracts 1, returns the old value */
                      "  jns        1f\n\t"
                      "  call call_rwsem_wake\n"
@@ -201,18 +213,18 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
+        rwsem_count_t tmp;
         asm volatile("# beginning __up_write\n\t"
-                     "  movl      %2,%%edx\n\t"
-                     LOCK_PREFIX "  xaddl     %%edx,(%%eax)\n\t"
+                     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                      /* tries to transition
                         0xffff0001 -> 0x00000000 */
                      "  jz       1f\n"
                      "  call call_rwsem_wake\n"
                      "1:\n\t"
                      "# ending __up_write\n"
-                     : "+m" (sem->count)
-                     : "a" (sem), "i" (-RWSEM_ACTIVE_WRITE_BIAS)
-                     : "memory", "cc", "edx");
+                     : "+m" (sem->count), "=d" (tmp)
+                     : "a" (sem), "1" (-RWSEM_ACTIVE_WRITE_BIAS)
+                     : "memory", "cc");
 }
 
 /*
@@ -221,33 +233,38 @@ static inline void __up_write(struct rw_semaphore *sem)
 static inline void __downgrade_write(struct rw_semaphore *sem)
 {
         asm volatile("# beginning __downgrade_write\n\t"
-                     LOCK_PREFIX "  addl      %2,(%%eax)\n\t"
-                     /* transitions 0xZZZZ0001 -> 0xYYYY0001 */
+                     LOCK_PREFIX _ASM_ADD "%2,(%1)\n\t"
+                     /*
+                      * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386)
+                      *     0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64)
+                      */
                      "  jns       1f\n\t"
                      "  call call_rwsem_downgrade_wake\n"
                      "1:\n\t"
                      "# ending __downgrade_write\n"
                      : "+m" (sem->count)
-                     : "a" (sem), "i" (-RWSEM_WAITING_BIAS)
+                     : "a" (sem), "er" (-RWSEM_WAITING_BIAS)
                      : "memory", "cc");
 }
 
 /*
  * implement atomic add functionality
  */
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+static inline void rwsem_atomic_add(rwsem_count_t delta,
+                                    struct rw_semaphore *sem)
 {
-        asm volatile(LOCK_PREFIX "addl %1,%0"
+        asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
                      : "+m" (sem->count)
-                     : "ir" (delta));
+                     : "er" (delta));
 }
 
 /*
  * implement exchange and add functionality
  */
-static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta,
+                                                struct rw_semaphore *sem)
 {
-        int tmp = delta;
+        rwsem_count_t tmp = delta;
 
         asm volatile(LOCK_PREFIX "xadd %0,%1"
                      : "+r" (tmp), "+m" (sem->count)
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 1b7ee5d673c2..0a5242428659 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -2,7 +2,13 @@
 #define _ASM_X86_SECTIONS_H
 
 #include <asm-generic/sections.h>
+#include <asm/uaccess.h>
 
 extern char __brk_base[], __brk_limit[];
+extern struct exception_table_entry __stop___ex_table[];
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+extern char __end_rodata_hpage_align[];
+#endif
 
 #endif  /* _ASM_X86_SECTIONS_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 18e496c98ff0..86b1506f4179 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -37,10 +37,8 @@ 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 unsigned long saved_video_mode;
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 72e5a4491661..04459d25e66e 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -124,7 +124,7 @@ struct sigcontext {
          * fpstate is really (struct _fpstate *) or (struct _xstate *)
          * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
          * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
-         * of extended memory layout. See comments at the defintion of
+         * of extended memory layout. See comments at the definition of
          * (struct _fpx_sw_bytes)
          */
         void __user *fpstate;           /* zero when no FPU/extended context */
@@ -219,7 +219,7 @@ struct sigcontext {
          * fpstate is really (struct _fpstate *) or (struct _xstate *)
          * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
          * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
-         * of extended memory layout. See comments at the defintion of
+         * of extended memory layout. See comments at the definition of
          * (struct _fpx_sw_bytes)
          */
         void __user *fpstate;           /* zero when no FPU/extended context */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 1e796782cd7b..4cfc90824068 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -135,6 +135,8 @@ int native_cpu_disable(void);
 void native_cpu_die(unsigned int cpu);
 void native_play_dead(void);
 void play_dead_common(void);
+void wbinvd_on_cpu(int cpu);
+int wbinvd_on_all_cpus(void);
 
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
@@ -147,6 +149,13 @@ static inline int num_booting_cpus(void)
 {
         return cpumask_weight(cpu_callout_mask);
 }
+#else /* !CONFIG_SMP */
+#define wbinvd_on_cpu(cpu)     wbinvd()
+static inline int wbinvd_on_all_cpus(void)
+{
+        wbinvd();
+        return 0;
+}
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus __cpuinitdata;
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 4e77853321db..3089f70c0c52 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -58,7 +58,7 @@
 #if (NR_CPUS < 256)
 #define TICKET_SHIFT 8
 
-static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 {
         short inc = 0x0100;
 
@@ -77,7 +77,7 @@ static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
                 : "memory", "cc");
 }
 
-static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
         int tmp, new;
 
@@ -96,7 +96,7 @@ static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
         return tmp;
 }
 
-static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 {
         asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
                      : "+m" (lock->slock)
@@ -106,7 +106,7 @@ static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 #else
 #define TICKET_SHIFT 16
 
-static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 {
         int inc = 0x00010000;
         int tmp;
@@ -127,7 +127,7 @@ static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
                      : "memory", "cc");
 }
 
-static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
         int tmp;
         int new;
@@ -149,7 +149,7 @@ static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
         return tmp;
 }
 
-static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 {
         asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
                      : "+m" (lock->slock)
@@ -158,14 +158,14 @@ static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 }
 #endif
 
-static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
         int tmp = ACCESS_ONCE(lock->slock);
 
         return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1));
 }
 
-static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
 {
         int tmp = ACCESS_ONCE(lock->slock);
 
@@ -174,43 +174,43 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 
 #ifndef CONFIG_PARAVIRT_SPINLOCKS
 
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
         return __ticket_spin_is_locked(lock);
 }
 
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
         return __ticket_spin_is_contended(lock);
 }
-#define __raw_spin_is_contended __raw_spin_is_contended
+#define arch_spin_is_contended  arch_spin_is_contended
 
-static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
 {
         __ticket_spin_lock(lock);
 }
 
-static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
         return __ticket_spin_trylock(lock);
 }
 
-static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
         __ticket_spin_unlock(lock);
 }
 
-static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
+static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
                                                   unsigned long flags)
 {
-        __raw_spin_lock(lock);
+        arch_spin_lock(lock);
 }
 
 #endif  /* CONFIG_PARAVIRT_SPINLOCKS */
 
-static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
-        while (__raw_spin_is_locked(lock))
+        while (arch_spin_is_locked(lock))
                 cpu_relax();
 }
 
@@ -232,7 +232,7 @@ static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
  * read_can_lock - would read_trylock() succeed?
  * @lock: the rwlock in question.
  */
-static inline int __raw_read_can_lock(raw_rwlock_t *lock)
+static inline int arch_read_can_lock(arch_rwlock_t *lock)
 {
         return (int)(lock)->lock > 0;
 }
@@ -241,12 +241,12 @@ static inline int __raw_read_can_lock(raw_rwlock_t *lock)
  * write_can_lock - would write_trylock() succeed?
  * @lock: the rwlock in question.
  */
-static inline int __raw_write_can_lock(raw_rwlock_t *lock)
+static inline int arch_write_can_lock(arch_rwlock_t *lock)
 {
         return (lock)->lock == RW_LOCK_BIAS;
 }
 
-static inline void __raw_read_lock(raw_rwlock_t *rw)
+static inline void arch_read_lock(arch_rwlock_t *rw)
 {
         asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t"
                      "jns 1f\n"
@@ -255,7 +255,7 @@ static inline void __raw_read_lock(raw_rwlock_t *rw)
                      ::LOCK_PTR_REG (rw) : "memory");
 }
 
-static inline void __raw_write_lock(raw_rwlock_t *rw)
+static inline void arch_write_lock(arch_rwlock_t *rw)
 {
         asm volatile(LOCK_PREFIX " subl %1,(%0)\n\t"
                      "jz 1f\n"
@@ -264,7 +264,7 @@ static inline void __raw_write_lock(raw_rwlock_t *rw)
                      ::LOCK_PTR_REG (rw), "i" (RW_LOCK_BIAS) : "memory");
 }
 
-static inline int __raw_read_trylock(raw_rwlock_t *lock)
+static inline int arch_read_trylock(arch_rwlock_t *lock)
 {
         atomic_t *count = (atomic_t *)lock;
 
@@ -274,7 +274,7 @@ static inline int __raw_read_trylock(raw_rwlock_t *lock)
         return 0;
 }
 
-static inline int __raw_write_trylock(raw_rwlock_t *lock)
+static inline int arch_write_trylock(arch_rwlock_t *lock)
 {
         atomic_t *count = (atomic_t *)lock;
 
@@ -284,23 +284,23 @@ static inline int __raw_write_trylock(raw_rwlock_t *lock)
         return 0;
 }
 
-static inline void __raw_read_unlock(raw_rwlock_t *rw)
+static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
         asm volatile(LOCK_PREFIX "incl %0" :"+m" (rw->lock) : : "memory");
 }
 
-static inline void __raw_write_unlock(raw_rwlock_t *rw)
+static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
         asm volatile(LOCK_PREFIX "addl %1, %0"
                      : "+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 arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 
-#define _raw_spin_relax(lock)   cpu_relax()
-#define _raw_read_relax(lock)   cpu_relax()
-#define _raw_write_relax(lock)  cpu_relax()
+#define arch_spin_relax(lock)   cpu_relax()
+#define arch_read_relax(lock)   cpu_relax()
+#define arch_write_relax(lock)  cpu_relax()
 
 /* The {read|write|spin}_lock() on x86 are full memory barriers. */
 static inline void smp_mb__after_lock(void) { }
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 845f81c87091..dcb48b2edc11 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -5,16 +5,16 @@
 # error "please don't include this file directly"
 #endif
 
-typedef struct raw_spinlock {
+typedef struct arch_spinlock {
         unsigned int slock;
-} raw_spinlock_t;
+} arch_spinlock_t;
 
-#define __RAW_SPIN_LOCK_UNLOCKED        { 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED       { 0 }
 
 typedef struct {
         unsigned int lock;
-} raw_rwlock_t;
+} arch_rwlock_t;
 
-#define __RAW_RW_LOCK_UNLOCKED          { RW_LOCK_BIAS }
+#define __ARCH_RW_LOCK_UNLOCKED         { RW_LOCK_BIAS }
 
 #endif /* _ASM_X86_SPINLOCK_TYPES_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index cf86a5e73815..4dab78edbad9 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -3,7 +3,28 @@
 
 extern int kstack_depth_to_print;
 
-int x86_is_stack_id(int id, char *name);
+struct thread_info;
+struct stacktrace_ops;
+
+typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
+                                      unsigned long *stack,
+                                      unsigned long bp,
+                                      const struct stacktrace_ops *ops,
+                                      void *data,
+                                      unsigned long *end,
+                                      int *graph);
+
+extern unsigned long
+print_context_stack(struct thread_info *tinfo,
+                    unsigned long *stack, unsigned long bp,
+                    const struct stacktrace_ops *ops, void *data,
+                    unsigned long *end, int *graph);
+
+extern unsigned long
+print_context_stack_bp(struct thread_info *tinfo,
+                       unsigned long *stack, unsigned long bp,
+                       const struct stacktrace_ops *ops, void *data,
+                       unsigned long *end, int *graph);
 
 /* Generic stack tracer with callbacks */
 
@@ -14,6 +35,7 @@ struct stacktrace_ops {
         void (*address)(void *data, unsigned long address, int reliable);
         /* On negative return stop dumping */
         int (*stack)(void *data, char *name);
+        walk_stack_t    walk_stack;
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index ae907e617181..3d3e8353ee5c 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -177,10 +177,15 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
  */
 
 #ifndef CONFIG_KMEMCHECK
+
+#if (__GNUC__ >= 4)
+#define memcpy(t, f, n) __builtin_memcpy(t, f, n)
+#else
 #define memcpy(t, f, n)                         \
         (__builtin_constant_p((n))              \
          ? __constant_memcpy((t), (f), (n))     \
          : __memcpy((t), (f), (n)))
+#endif
 #else
 /*
  * kmemcheck becomes very happy if we use the REP instructions unconditionally,
@@ -316,11 +321,15 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern,
          : __memset_generic((s), (c), (count)))
 
 #define __HAVE_ARCH_MEMSET
+#if (__GNUC__ >= 4)
+#define memset(s, c, count) __builtin_memset(s, c, count)
+#else
 #define memset(s, c, count)                                             \
         (__builtin_constant_p(c)                                        \
          ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \
                                  (count))                               \
          : __memset((s), (c), (count)))
+#endif
 
 /*
  * find the first occurrence of byte 'c', or 1 past the area if none
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 85574b7c1bc1..38638cd2fa4c 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -57,7 +57,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
         u16 intercept_dr_write;
         u32 intercept_exceptions;
         u64 intercept;
-        u8 reserved_1[44];
+        u8 reserved_1[42];
+        u16 pause_filter_count;
         u64 iopm_base_pa;
         u64 msrpm_base_pa;
         u64 tsc_offset;
@@ -312,7 +313,7 @@ struct __attribute__ ((__packed__)) vmcb {
 
 #define SVM_EXIT_ERR            -1
 
-#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) /* TS and MP */
+#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
 
 #define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda"
 #define SVM_VMRUN  ".byte 0x0f, 0x01, 0xd8"
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index b9e4e20174fb..8085277e1b8b 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -3,15 +3,16 @@
 
 #include <linux/swiotlb.h>
 
-/* SWIOTLB interface */
-
-extern int swiotlb_force;
-
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
-extern void pci_swiotlb_init(void);
+extern int __init pci_swiotlb_detect(void);
+extern void __init pci_swiotlb_init(void);
 #else
 #define swiotlb 0
+static inline int pci_swiotlb_detect(void)
+{
+        return 0;
+}
 static inline void pci_swiotlb_init(void)
 {
 }
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 72a6dcd1299b..3ad421784ae7 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -26,11 +26,10 @@ asmlinkage long sys32_lstat64(char __user *, struct stat64 __user *);
 asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *);
 asmlinkage long sys32_fstatat(unsigned int, char __user *,
                               struct stat64 __user *, int);
-struct mmap_arg_struct;
-asmlinkage long sys32_mmap(struct mmap_arg_struct __user *);
+struct mmap_arg_struct32;
+asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *);
 asmlinkage long sys32_mprotect(unsigned long, size_t, unsigned long);
 
-asmlinkage long sys32_pipe(int __user *);
 struct sigaction32;
 struct old_sigaction32;
 asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *,
@@ -41,8 +40,6 @@ asmlinkage long sys32_rt_sigprocmask(int, compat_sigset_t __user *,
                                      compat_sigset_t __user *, unsigned int);
 asmlinkage long sys32_alarm(unsigned int);
 
-struct sel_arg_struct;
-asmlinkage long sys32_old_select(struct sel_arg_struct __user *);
 asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int);
 asmlinkage long sys32_sysfs(int, u32, u32);
 
@@ -51,25 +48,12 @@ asmlinkage long sys32_sched_rr_get_interval(compat_pid_t,
 asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *, compat_size_t);
 asmlinkage long sys32_rt_sigqueueinfo(int, int, compat_siginfo_t __user *);
 
-#ifdef CONFIG_SYSCTL_SYSCALL
-struct sysctl_ia32;
-asmlinkage long sys32_sysctl(struct sysctl_ia32 __user *);
-#endif
-
 asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32);
 asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32);
 
 asmlinkage long sys32_personality(unsigned long);
 asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32);
 
-asmlinkage long sys32_mmap2(unsigned long, unsigned long, unsigned long,
-                            unsigned long, unsigned long, unsigned long);
-
-struct oldold_utsname;
-struct old_utsname;
-asmlinkage long sys32_olduname(struct oldold_utsname __user *);
-long sys32_uname(struct old_utsname __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/syscall.h b/arch/x86/include/asm/syscall.h
index 8d33bc5462d1..c4a348f7bd43 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,6 +16,8 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 
+extern const unsigned long sys_call_table[];
+
 /*
  * Only the low 32 bits of orig_ax are meaningful, so we return int.
  * This importantly ignores the high bits on 64-bit, so comparisons
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 372b76edd63f..5c044b43e9a7 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -18,16 +18,24 @@
 /* Common in X86_32 and X86_64 */
 /* kernel/ioport.c */
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
+long sys_iopl(unsigned int, struct pt_regs *);
 
 /* kernel/process.c */
 int sys_fork(struct pt_regs *);
 int sys_vfork(struct pt_regs *);
+long sys_execve(char __user *, char __user * __user *,
+                char __user * __user *, struct pt_regs *);
+long sys_clone(unsigned long, unsigned long, void __user *,
+               void __user *, struct pt_regs *);
 
 /* kernel/ldt.c */
 asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
 
 /* kernel/signal.c */
 long sys_rt_sigreturn(struct pt_regs *);
+long sys_sigaltstack(const stack_t __user *, stack_t __user *,
+                     struct pt_regs *);
+
 
 /* kernel/tls.c */
 asmlinkage int sys_set_thread_area(struct user_desc __user *);
@@ -35,63 +43,26 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *);
 
 /* X86_32 only */
 #ifdef CONFIG_X86_32
-/* kernel/ioport.c */
-long sys_iopl(struct pt_regs *);
-
-/* kernel/process_32.c */
-int sys_clone(struct pt_regs *);
-int sys_execve(struct pt_regs *);
 
 /* kernel/signal.c */
 asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
 asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
                              struct old_sigaction __user *);
-int sys_sigaltstack(struct pt_regs *);
 unsigned long sys_sigreturn(struct pt_regs *);
 
-/* kernel/sys_i386_32.c */
-struct mmap_arg_struct;
-struct sel_arg_struct;
-struct oldold_utsname;
-struct old_utsname;
-
-asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
-                          unsigned long, unsigned long, unsigned long);
-asmlinkage int old_mmap(struct mmap_arg_struct __user *);
-asmlinkage int old_select(struct sel_arg_struct __user *);
-asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
-asmlinkage int sys_uname(struct old_utsname __user *);
-asmlinkage int sys_olduname(struct oldold_utsname __user *);
-
 /* kernel/vm86_32.c */
-int sys_vm86old(struct pt_regs *);
-int sys_vm86(struct pt_regs *);
+int sys_vm86old(struct vm86_struct __user *, struct pt_regs *);
+int sys_vm86(unsigned long, unsigned long, struct pt_regs *);
 
 #else /* CONFIG_X86_32 */
 
 /* X86_64 only */
-/* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
-
 /* kernel/process_64.c */
-asmlinkage long sys_clone(unsigned long, unsigned long,
-                          void __user *, void __user *,
-                          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/signal.c */
-asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
-                                struct pt_regs *);
-
 /* kernel/sys_x86_64.c */
-struct new_utsname;
-
 asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
                          unsigned long, unsigned long, unsigned long);
-asmlinkage long sys_uname(struct new_utsname __user *);
 
 #endif /* CONFIG_X86_32 */
 #endif /* _ASM_X86_SYSCALLS_H */
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index f08f97374892..b8fe48ee2ed9 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -11,9 +11,9 @@
 #include <linux/irqflags.h>
 
 /* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
+#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
 # define AT_VECTOR_SIZE_ARCH 2
-#else
+#else /* else it's non-compat x86-64 */
 # define AT_VECTOR_SIZE_ARCH 1
 #endif
 
@@ -23,6 +23,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 struct tss_struct;
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
                       struct tss_struct *tss);
+extern void show_regs_common(void);
 
 #ifdef CONFIG_X86_32
 
@@ -31,7 +32,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
         "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.canary))
+        , [stack_canary] "=m" (stack_canary.canary)
 #define __switch_canary_iparam                                          \
         , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
 #else   /* CC_STACKPROTECTOR */
@@ -113,7 +114,7 @@ do {									\
         "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))
+        , [gs_canary] "=m" (irq_stack_union.stack_canary)
 #define __switch_canary_iparam                                            \
         , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
 #else   /* CC_STACKPROTECTOR */
@@ -128,13 +129,11 @@ do {									\
              "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 "__percpu_arg([current_task])",%%rsi\n\t"              \
              __switch_canary                                              \
              "movq %P[thread_info](%%rsi),%%r8\n\t"                       \
              "movq %%rax,%%rdi\n\t"                                       \
-             "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"         \
+             "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"                 \
              "jnz   ret_from_fork\n\t"                                    \
              RESTORE_CONTEXT                                              \
              : "=a" (last)                                                \
@@ -144,7 +143,7 @@ do {									\
                [ti_flags] "i" (offsetof(struct thread_info, flags)),      \
                [_tif_fork] "i" (_TIF_FORK),                               \
                [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-               [current_task] "m" (per_cpu_var(current_task))             \
+               [current_task] "m" (current_task)                          \
                __switch_canary_iparam                                     \
              : "memory", "cc" __EXTRA_CLOBBER)
 #endif
@@ -157,19 +156,22 @@ extern void native_load_gs_index(unsigned);
  * Load a segment. Fall back on loading the zero
  * segment if something goes wrong..
  */
-#define loadsegment(seg, value)                 \
-        asm volatile("\n"                       \
-                     "1:\t"                     \
-                     "movl %k0,%%" #seg "\n"    \
-                     "2:\n"                     \
-                     ".section .fixup,\"ax\"\n" \
-                     "3:\t"                     \
-                     "movl %k1, %%" #seg "\n\t" \
-                     "jmp 2b\n"                 \
-                     ".previous\n"              \
-                     _ASM_EXTABLE(1b,3b)        \
-                     : :"r" (value), "r" (0) : "memory")
-
+#define loadsegment(seg, value)                                         \
+do {                                                                    \
+        unsigned short __val = (value);                                 \
+                                                                        \
+        asm volatile("                                          \n"     \
+                     "1:        movl %k0,%%" #seg "             \n"     \
+                                                                        \
+                     ".section .fixup,\"ax\"                    \n"     \
+                     "2:        xorl %k0,%k0                    \n"     \
+                     "          jmp 1b                          \n"     \
+                     ".previous                                 \n"     \
+                                                                        \
+                     _ASM_EXTABLE(1b, 2b)                               \
+                                                                        \
+                     : "+r" (__val) : : "memory");                      \
+} while (0)
 
 /*
  * Save a segment register away
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index d27d0a2fec4c..e0d28901e969 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -83,10 +83,10 @@ struct thread_info {
 #define TIF_SYSCALL_AUDIT       7       /* syscall auditing active */
 #define TIF_SECCOMP             8       /* secure computing */
 #define TIF_MCE_NOTIFY          10      /* notify userspace of an MCE */
+#define TIF_USER_RETURN_NOTIFY  11      /* notify kernel of userspace return */
 #define TIF_NOTSC               16      /* TSC is not accessible in userland */
 #define TIF_IA32                17      /* 32bit process */
 #define TIF_FORK                18      /* ret_from_fork */
-#define TIF_ABI_PENDING         19
 #define TIF_MEMDIE              20
 #define TIF_DEBUG               21      /* uses debug registers */
 #define TIF_IO_BITMAP           22      /* uses I/O bitmap */
@@ -107,10 +107,10 @@ struct thread_info {
 #define _TIF_SYSCALL_AUDIT      (1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP            (1 << TIF_SECCOMP)
 #define _TIF_MCE_NOTIFY         (1 << TIF_MCE_NOTIFY)
+#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_NOTSC              (1 << TIF_NOTSC)
 #define _TIF_IA32               (1 << TIF_IA32)
 #define _TIF_FORK               (1 << TIF_FORK)
-#define _TIF_ABI_PENDING        (1 << TIF_ABI_PENDING)
 #define _TIF_DEBUG              (1 << TIF_DEBUG)
 #define _TIF_IO_BITMAP          (1 << TIF_IO_BITMAP)
 #define _TIF_FREEZE             (1 << TIF_FREEZE)
@@ -142,13 +142,14 @@ struct thread_info {
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK                                             \
-        (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
+        (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME |       \
+         _TIF_USER_RETURN_NOTIFY)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW                                                 \
         (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC)
 
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
+#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
 
 #define PREEMPT_ACTIVE          0x10000000
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 40e37b10c6c0..c5087d796587 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -35,11 +35,16 @@
 # endif
 #endif
 
-/* Node not present */
-#define NUMA_NO_NODE    (-1)
+/*
+ * to preserve the visibility of NUMA_NO_NODE definition,
+ * moved to there from here.  May be used independent of
+ * CONFIG_NUMA.
+ */
+#include <linux/numa.h>
 
 #ifdef CONFIG_NUMA
 #include <linux/cpumask.h>
+
 #include <asm/mpspec.h>
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 90f06c25221d..cb507bb05d79 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -16,7 +16,6 @@ extern unsigned long initial_code;
 extern unsigned long initial_gs;
 
 #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
-#define TRAMPOLINE_BASE 0x6000
 
 extern unsigned long setup_trampoline(void);
 extern void __init reserve_trampoline_memory(void);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index d2c6c930b491..abd3e0ea762a 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -570,7 +570,6 @@ extern struct movsl_mask {
 #ifdef CONFIG_X86_32
 # include "uaccess_32.h"
 #else
-# define ARCH_HAS_SEARCH_EXTABLE
 # include "uaccess_64.h"
 #endif
 
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 632fb44b4cb5..088d09fb1615 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -187,9 +187,33 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from,
 
 unsigned long __must_check copy_to_user(void __user *to,
                                         const void *from, unsigned long n);
-unsigned long __must_check copy_from_user(void *to,
+unsigned long __must_check _copy_from_user(void *to,
                                           const void __user *from,
                                           unsigned long n);
+
+
+extern void copy_from_user_overflow(void)
+#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
+        __compiletime_error("copy_from_user() buffer size is not provably correct")
+#else
+        __compiletime_warning("copy_from_user() buffer size is not provably correct")
+#endif
+;
+
+static inline unsigned long __must_check copy_from_user(void *to,
+                                          const void __user *from,
+                                          unsigned long n)
+{
+        int sz = __compiletime_object_size(to);
+
+        if (likely(sz == -1 || sz >= n))
+                n = _copy_from_user(to, from, n);
+        else
+                copy_from_user_overflow();
+
+        return n;
+}
+
 long __must_check strncpy_from_user(char *dst, const char __user *src,
                                     long count);
 long __must_check __strncpy_from_user(char *dst,
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index db24b215fc50..316708d5af92 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -8,6 +8,8 @@
 #include <linux/errno.h>
 #include <linux/prefetch.h>
 #include <linux/lockdep.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 #include <asm/page.h>
 
 /*
@@ -16,15 +18,56 @@
 
 /* Handles exceptions in both to and from, but doesn't do access_ok */
 __must_check unsigned long
-copy_user_generic(void *to, const void *from, unsigned len);
+copy_user_generic_string(void *to, const void *from, unsigned len);
+__must_check unsigned long
+copy_user_generic_unrolled(void *to, const void *from, unsigned len);
+
+static __always_inline __must_check unsigned long
+copy_user_generic(void *to, const void *from, unsigned len)
+{
+        unsigned ret;
+
+        alternative_call(copy_user_generic_unrolled,
+                         copy_user_generic_string,
+                         X86_FEATURE_REP_GOOD,
+                         ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from),
+                                     "=d" (len)),
+                         "1" (to), "2" (from), "3" (len)
+                         : "memory", "rcx", "r8", "r9", "r10", "r11");
+        return ret;
+}
 
 __must_check unsigned long
-copy_to_user(void __user *to, const void *from, unsigned len);
+_copy_to_user(void __user *to, const void *from, unsigned len);
 __must_check unsigned long
-copy_from_user(void *to, const void __user *from, unsigned len);
+_copy_from_user(void *to, const void __user *from, unsigned len);
 __must_check unsigned long
 copy_in_user(void __user *to, const void __user *from, unsigned len);
 
+static inline unsigned long __must_check copy_from_user(void *to,
+                                          const void __user *from,
+                                          unsigned long n)
+{
+        int sz = __compiletime_object_size(to);
+
+        might_fault();
+        if (likely(sz == -1 || sz >= n))
+                n = _copy_from_user(to, from, n);
+#ifdef CONFIG_DEBUG_VM
+        else
+                WARN(1, "Buffer overflow detected!\n");
+#endif
+        return n;
+}
+
+static __always_inline __must_check
+int copy_to_user(void __user *dst, const void *src, unsigned size)
+{
+        might_fault();
+
+        return _copy_to_user(dst, src, size);
+}
+
 static __always_inline __must_check
 int __copy_from_user(void *dst, const void __user *src, unsigned size)
 {
@@ -176,8 +219,11 @@ __must_check long strlen_user(const char __user *str);
 __must_check unsigned long clear_user(void __user *mem, unsigned long len);
 __must_check unsigned long __clear_user(void __user *mem, unsigned long len);
 
-__must_check long __copy_from_user_inatomic(void *dst, const void __user *src,
-                                            unsigned size);
+static __must_check __always_inline int
+__copy_from_user_inatomic(void *dst, const void __user *src, unsigned size)
+{
+        return copy_user_generic(dst, (__force const void *)src, size);
+}
 
 static __must_check __always_inline int
 __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index f9b507f30d65..4f61e8b0715a 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -342,14 +342,15 @@
 #define __NR_pwritev            334
 #define __NR_rt_tgsigqueueinfo  335
 #define __NR_perf_event_open    336
+#define __NR_recvmmsg           337
 
-#define __NR_LITMUS             337
+#define __NR_LITMUS             338
 
 #include "litmus/unistd_32.h"
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 336 + NR_litmus_syscalls
+#define NR_syscalls 339 + NR_litmus_syscalls
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
@@ -357,6 +358,7 @@
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_IPC
 #define __ARCH_WANT_SYS_PAUSE
 #define __ARCH_WANT_SYS_SGETMASK
 #define __ARCH_WANT_SYS_SIGNAL
@@ -369,6 +371,9 @@
 #define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLD_UNAME
+#define __ARCH_WANT_SYS_OLD_MMAP
+#define __ARCH_WANT_SYS_OLD_SELECT
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_SIGPROCMASK
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 33b2003c0450..b21c3b269aac 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -146,7 +146,7 @@ __SYSCALL(__NR_wait4, sys_wait4)
 #define __NR_kill                               62
 __SYSCALL(__NR_kill, sys_kill)
 #define __NR_uname                              63
-__SYSCALL(__NR_uname, sys_uname)
+__SYSCALL(__NR_uname, sys_newuname)
 
 #define __NR_semget                             64
 __SYSCALL(__NR_semget, sys_semget)
@@ -661,6 +661,8 @@ __SYSCALL(__NR_pwritev, sys_pwritev)
 __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
 #define __NR_perf_event_open                    298
 __SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_recvmmsg                           299
+__SYSCALL(__NR_recvmmsg, sys_recvmmsg)
 
 #define __NR_LITMUS                             299
 
@@ -682,6 +684,7 @@ __SYSCALL(__NR_perf_event_open, sys_perf_event_open)
 #define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLD_UNAME
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_SIGPROCMASK
diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h
index 999873b22e7f..24532c7da3d6 100644
--- a/arch/x86/include/asm/user.h
+++ b/arch/x86/include/asm/user.h
@@ -1,5 +1,63 @@
+#ifndef _ASM_X86_USER_H
+#define _ASM_X86_USER_H
+
 #ifdef CONFIG_X86_32
 # include "user_32.h"
 #else
 # include "user_64.h"
 #endif
+
+#include <asm/types.h>
+
+struct user_ymmh_regs {
+        /* 16 * 16 bytes for each YMMH-reg */
+        __u32 ymmh_space[64];
+};
+
+struct user_xsave_hdr {
+        __u64 xstate_bv;
+        __u64 reserved1[2];
+        __u64 reserved2[5];
+};
+
+/*
+ * The structure layout of user_xstateregs, used for exporting the
+ * extended register state through ptrace and core-dump (NT_X86_XSTATE note)
+ * interfaces will be same as the memory layout of xsave used by the processor
+ * (except for the bytes 464..511, which can be used by the software) and hence
+ * the size of this structure varies depending on the features supported by the
+ * processor and OS. The size of the structure that users need to use can be
+ * obtained by doing:
+ *     cpuid_count(0xd, 0, &eax, &ptrace_xstateregs_struct_size, &ecx, &edx);
+ * i.e., cpuid.(eax=0xd,ecx=0).ebx will be the size that user (debuggers, etc.)
+ * need to use.
+ *
+ * For now, only the first 8 bytes of the software usable bytes[464..471] will
+ * be used and will be set to OS enabled xstate mask (which is same as the
+ * 64bit mask returned by the xgetbv's xCR0).  Users (analyzing core dump
+ * remotely, etc.) can use this mask as well as the mask saved in the
+ * xstate_hdr bytes and interpret what states the processor/OS supports
+ * and what states are in modified/initialized conditions for the
+ * particular process/thread.
+ *
+ * Also when the user modifies certain state FP/SSE/etc through the
+ * ptrace interface, they must ensure that the xsave_hdr.xstate_bv
+ * bytes[512..519] of the memory layout are updated correspondingly.
+ * i.e., for example when FP state is modified to a non-init state,
+ * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to
+ * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc.
+ */
+#define USER_XSTATE_FX_SW_WORDS 6
+#define USER_XSTATE_XCR0_WORD   0
+
+struct user_xstateregs {
+        struct {
+                __u64 fpx_space[58];
+                __u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS];
+        } i387;
+        struct user_xsave_hdr xsave_hdr;
+        struct user_ymmh_regs ymmh;
+        /* further processor state extensions go here */
+};
+
+#endif /* _ASM_X86_USER_H */
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index 7ed17ff502b9..71605c7d5c5c 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -18,8 +18,8 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  *
- *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
- *  Copyright (c) Russ Anderson
+ *  Copyright (c) 2008-2009 Silicon Graphics, Inc.  All Rights Reserved.
+ *  Copyright (c) Russ Anderson <rja@sgi.com>
  */
 
 #include <linux/rtc.h>
@@ -36,7 +36,8 @@ enum uv_bios_cmd {
         UV_BIOS_WATCHLIST_ALLOC,
         UV_BIOS_WATCHLIST_FREE,
         UV_BIOS_MEMPROTECT,
-        UV_BIOS_GET_PARTITION_ADDR
+        UV_BIOS_GET_PARTITION_ADDR,
+        UV_BIOS_SET_LEGACY_VGA_TARGET
 };
 
 /*
@@ -76,15 +77,6 @@ union partition_info_u {
         };
 };
 
-union uv_watchlist_u {
-        u64     val;
-        struct {
-                u64     blade   : 16,
-                        size    : 32,
-                        filler  : 16;
-        };
-};
-
 enum uv_memprotect {
         UV_MEMPROT_RESTRICT_ACCESS,
         UV_MEMPROT_ALLOW_AMO,
@@ -98,13 +90,14 @@ extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 
-extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
+extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *, long *);
 extern s64 uv_bios_freq_base(u64, u64 *);
-extern int uv_bios_mq_watchlist_alloc(int, unsigned long, unsigned int,
+extern int uv_bios_mq_watchlist_alloc(unsigned long, unsigned int,
                                         unsigned long *);
 extern int uv_bios_mq_watchlist_free(int, int);
 extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
 extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *);
+extern int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus);
 
 extern void uv_bios_init(void);
 
@@ -113,6 +106,7 @@ extern int uv_type;
 extern long sn_partition_id;
 extern long sn_coherency_id;
 extern long sn_region_size;
+extern long system_serial_number;
 #define partition_coherence_id()        (sn_coherency_id)
 
 extern struct kobject *sgi_uv_kobj;     /* /sys/firmware/sgi_uv */
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index c0a01b5d985b..3bb9491b7659 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -11,6 +11,7 @@ struct mm_struct;
 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_nmi_init(void);
 extern void uv_system_init(void);
 extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
                                                  struct mm_struct *mm,
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 80e2984f521c..b414d2b401f6 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -55,7 +55,7 @@
 #define DESC_STATUS_SOURCE_TIMEOUT      3
 
 /*
- * source side threshholds at which message retries print a warning
+ * source side thresholds at which message retries print a warning
  */
 #define SOURCE_TIMEOUT_LIMIT            20
 #define DESTINATION_TIMEOUT_LIMIT       20
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index d1414af98559..14cc74ba5d23 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -31,20 +31,20 @@
  *                contiguous (although various IO spaces may punch holes in
  *                it)..
  *
- *      N       - Number of bits in the node portion of a socket physical
- *                address.
+ *      N       - Number of bits in the node portion of a socket physical
+ *                address.
  *
- *      NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
- *                routers always have low bit of 1, C/MBricks have low bit
- *                equal to 0. Most addressing macros that target UV hub chips
- *                right shift the NASID by 1 to exclude the always-zero bit.
- *                NASIDs contain up to 15 bits.
+ *      NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
+ *                routers always have low bit of 1, C/MBricks have low bit
+ *                equal to 0. Most addressing macros that target UV hub chips
+ *                right shift the NASID by 1 to exclude the always-zero bit.
+ *                NASIDs contain up to 15 bits.
  *
  *      GNODE   - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
  *                of nasids.
  *
- *      PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
- *                of the nasid for socket usage.
+ *      PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
+ *                of the nasid for socket usage.
  *
  *
  *  NumaLink Global Physical Address Format:
@@ -71,12 +71,12 @@
  *
  *
  * APICID format
- *      NOTE!!!!!! This is the current format of the APICID. However, code
- *      should assume that this will change in the future. Use functions
- *      in this file for all APICID bit manipulations and conversion.
+ *      NOTE!!!!!! This is the current format of the APICID. However, code
+ *      should assume that this will change in the future. Use functions
+ *      in this file for all APICID bit manipulations and conversion.
  *
- *              1111110000000000
- *              5432109876543210
+ *              1111110000000000
+ *              5432109876543210
  *              pppppppppplc0cch
  *              sssssssssss
  *
@@ -89,9 +89,9 @@
  *      Note: Processor only supports 12 bits in the APICID register. The ACPI
  *            tables hold all 16 bits. Software needs to be aware of this.
  *
- *            Unless otherwise specified, all references to APICID refer to
- *            the FULL value contained in ACPI tables, not the subset in the
- *            processor APICID register.
+ *            Unless otherwise specified, all references to APICID refer to
+ *            the FULL value contained in ACPI tables, not the subset in the
+ *            processor APICID register.
  */
 
 
@@ -151,16 +151,16 @@ struct uv_hub_info_s {
 };
 
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info             (&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info             (&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)    (&per_cpu(__uv_hub_info, cpu))
 
 /*
  * Local & Global MMR space macros.
- *      Note: macros are intended to be used ONLY by inline functions
- *      in this file - not by other kernel code.
- *              n -  NASID (full 15-bit global nasid)
- *              g -  GNODE (full 15-bit global nasid, right shifted 1)
- *              p -  PNODE (local part of nsids, right shifted 1)
+ *      Note: macros are intended to be used ONLY by inline functions
+ *      in this file - not by other kernel code.
+ *              n -  NASID (full 15-bit global nasid)
+ *              g -  GNODE (full 15-bit global nasid, right shifted 1)
+ *              p -  PNODE (local part of nsids, right shifted 1)
  */
 #define UV_NASID_TO_PNODE(n)            (((n) >> 1) & uv_hub_info->pnode_mask)
 #define UV_PNODE_TO_GNODE(p)            ((p) |uv_hub_info->gnode_extra)
@@ -172,6 +172,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_LOCAL_MMR_SIZE               (64UL * 1024 * 1024)
 #define UV_GLOBAL_MMR32_SIZE            (64UL * 1024 * 1024)
 
+#define UV_GLOBAL_GRU_MMR_BASE          0x4000000
+
 #define UV_GLOBAL_MMR32_PNODE_SHIFT     15
 #define UV_GLOBAL_MMR64_PNODE_SHIFT     26
 
@@ -213,8 +215,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 /*
  * Macros for converting between kernel virtual addresses, socket local physical
  * addresses, and UV global physical addresses.
- *      Note: use the standard __pa() & __va() macros for converting
- *            between socket virtual and socket physical addresses.
+ *      Note: use the standard __pa() & __va() macros for converting
+ *            between socket virtual and socket physical addresses.
  */
 
 /* socket phys RAM --> UV global physical address */
@@ -232,6 +234,26 @@ static inline unsigned long uv_gpa(void *v)
         return uv_soc_phys_ram_to_gpa(__pa(v));
 }
 
+/* Top two bits indicate the requested address is in MMR space.  */
+static inline int
+uv_gpa_in_mmr_space(unsigned long gpa)
+{
+        return (gpa >> 62) == 0x3UL;
+}
+
+/* UV global physical address --> socket phys RAM */
+static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
+{
+        unsigned long paddr = gpa & uv_hub_info->gpa_mask;
+        unsigned long remap_base = uv_hub_info->lowmem_remap_base;
+        unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
+
+        if (paddr >= remap_base && paddr < remap_base + remap_top)
+                paddr -= remap_base;
+        return paddr;
+}
+
+
 /* gnode -> pnode */
 static inline unsigned long uv_gpa_to_gnode(unsigned long gpa)
 {
@@ -265,21 +287,18 @@ static inline int uv_apicid_to_pnode(int apicid)
  * Access global MMRs using the low memory MMR32 space. This region supports
  * faster MMR access but not all MMRs are accessible in this space.
  */
-static inline unsigned long *uv_global_mmr32_address(int pnode,
-                                unsigned long offset)
+static inline unsigned long *uv_global_mmr32_address(int pnode, unsigned long offset)
 {
         return __va(UV_GLOBAL_MMR32_BASE |
                        UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
-                                 unsigned long val)
+static inline void uv_write_global_mmr32(int pnode, unsigned long offset, unsigned long val)
 {
         writeq(val, uv_global_mmr32_address(pnode, offset));
 }
 
-static inline unsigned long uv_read_global_mmr32(int pnode,
-                                                 unsigned long offset)
+static inline unsigned long uv_read_global_mmr32(int pnode, unsigned long offset)
 {
         return readq(uv_global_mmr32_address(pnode, offset));
 }
@@ -288,26 +307,43 @@ static inline unsigned long uv_read_global_mmr32(int pnode,
  * Access Global MMR space using the MMR space located at the top of physical
  * memory.
  */
-static inline unsigned long *uv_global_mmr64_address(int pnode,
-                                unsigned long offset)
+static inline unsigned long *uv_global_mmr64_address(int pnode, unsigned long offset)
 {
         return __va(UV_GLOBAL_MMR64_BASE |
                     UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
-                                unsigned long val)
+static inline void uv_write_global_mmr64(int pnode, unsigned long offset, unsigned long val)
 {
         writeq(val, uv_global_mmr64_address(pnode, offset));
 }
 
-static inline unsigned long uv_read_global_mmr64(int pnode,
-                                                 unsigned long offset)
+static inline unsigned long uv_read_global_mmr64(int pnode, unsigned long offset)
 {
         return readq(uv_global_mmr64_address(pnode, offset));
 }
 
 /*
+ * Global MMR space addresses when referenced by the GRU. (GRU does
+ * NOT use socket addressing).
+ */
+static inline unsigned long uv_global_gru_mmr_address(int pnode, unsigned long offset)
+{
+        return UV_GLOBAL_GRU_MMR_BASE | offset |
+                ((unsigned long)pnode << uv_hub_info->m_val);
+}
+
+static inline void uv_write_global_mmr8(int pnode, unsigned long offset, unsigned char val)
+{
+        writeb(val, uv_global_mmr64_address(pnode, offset));
+}
+
+static inline unsigned char uv_read_global_mmr8(int pnode, unsigned long offset)
+{
+        return readb(uv_global_mmr64_address(pnode, offset));
+}
+
+/*
  * Access hub local MMRs. Faster than using global space but only local MMRs
  * are accessible.
  */
@@ -426,14 +462,28 @@ static inline void uv_set_scir_bits(unsigned char value)
         }
 }
 
+static inline unsigned long uv_scir_offset(int apicid)
+{
+        return SCIR_LOCAL_MMR_BASE | (apicid & 0x3f);
+}
+
 static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 {
         if (uv_cpu_hub_info(cpu)->scir.state != value) {
+                uv_write_global_mmr8(uv_cpu_to_pnode(cpu),
+                                uv_cpu_hub_info(cpu)->scir.offset, value);
                 uv_cpu_hub_info(cpu)->scir.state = value;
-                uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
         }
 }
 
+static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode)
+{
+        return (1UL << UVH_IPI_INT_SEND_SHFT) |
+                        ((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
+                        (mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
+                        (vector << UVH_IPI_INT_VECTOR_SHFT);
+}
+
 static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 {
         unsigned long val;
@@ -442,12 +492,21 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
         if (vector == NMI_VECTOR)
                 dmode = dest_NMI;
 
-        val = (1UL << UVH_IPI_INT_SEND_SHFT) |
-                        ((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
-                        (dmode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
-                        (vector << UVH_IPI_INT_VECTOR_SHFT);
+        val = uv_hub_ipi_value(apicid, vector, dmode);
         uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 }
 
+/*
+ * Get the minimum revision number of the hub chips within the partition.
+ *     1 - initial rev 1.0 silicon
+ *     2 - rev 2.0 production silicon
+ */
+static inline int uv_get_min_hub_revision_id(void)
+{
+        extern int uv_min_hub_revision_id;
+
+        return uv_min_hub_revision_id;
+}
+
 #endif /* CONFIG_X86_64 */
 #endif /* _ASM_X86_UV_UV_HUB_H */
diff --git a/arch/x86/include/asm/uv/uv_irq.h b/arch/x86/include/asm/uv/uv_irq.h
index 9613c8c0b647..d6b17c760622 100644
--- a/arch/x86/include/asm/uv/uv_irq.h
+++ b/arch/x86/include/asm/uv/uv_irq.h
@@ -25,12 +25,14 @@ struct uv_IO_APIC_route_entry {
                 dest            : 32;
 };
 
-extern struct irq_chip uv_irq_chip;
-
-extern int arch_enable_uv_irq(char *, unsigned int, int, int, unsigned long);
-extern void arch_disable_uv_irq(int, unsigned long);
+enum {
+        UV_AFFINITY_ALL,
+        UV_AFFINITY_NODE,
+        UV_AFFINITY_CPU
+};
 
-extern int uv_setup_irq(char *, int, int, unsigned long);
-extern void uv_teardown_irq(unsigned int, int, unsigned long);
+extern int uv_irq_2_mmr_info(int, unsigned long *, int *);
+extern int uv_setup_irq(char *, int, int, unsigned long, int);
+extern void uv_teardown_irq(unsigned int);
 
 #endif /* _ASM_X86_UV_UV_IRQ_H */
diff --git a/arch/x86/include/asm/visws/cobalt.h b/arch/x86/include/asm/visws/cobalt.h
index 166adf61e770..2edb37637ead 100644
--- a/arch/x86/include/asm/visws/cobalt.h
+++ b/arch/x86/include/asm/visws/cobalt.h
@@ -122,4 +122,6 @@ extern char visws_board_type;
 
 extern char visws_board_rev;
 
+extern int pci_visws_init(void);
+
 #endif /* _ASM_X86_VISWS_COBALT_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 272514c2d456..fb9a080740ec 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -53,9 +53,11 @@
  */
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
+#define SECONDARY_EXEC_RDTSCP                   0x00000008
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING           0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST       0x00000080
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING       0x00000400
 
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
@@ -144,6 +146,8 @@ enum vmcs_field {
         VM_ENTRY_INSTRUCTION_LEN        = 0x0000401a,
         TPR_THRESHOLD                   = 0x0000401c,
         SECONDARY_VM_EXEC_CONTROL       = 0x0000401e,
+        PLE_GAP                         = 0x00004020,
+        PLE_WINDOW                      = 0x00004022,
         VM_INSTRUCTION_ERROR            = 0x00004400,
         VM_EXIT_REASON                  = 0x00004402,
         VM_EXIT_INTR_INFO               = 0x00004404,
@@ -248,6 +252,8 @@ enum vmcs_field {
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION   40
 #define EXIT_REASON_MCE_DURING_VMENTRY   41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
@@ -358,6 +364,7 @@ enum vmcs_field {
 #define VMX_EPTP_UC_BIT                         (1ull << 8)
 #define VMX_EPTP_WB_BIT                         (1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT                    (1ull << 16)
+#define VMX_EPT_1GB_PAGE_BIT                    (1ull << 17)
 #define VMX_EPT_EXTENT_INDIVIDUAL_BIT           (1ull << 24)
 #define VMX_EPT_EXTENT_CONTEXT_BIT              (1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT               (1ull << 26)
@@ -370,7 +377,7 @@ enum vmcs_field {
 #define VMX_EPT_READABLE_MASK                   0x1ull
 #define VMX_EPT_WRITABLE_MASK                   0x2ull
 #define VMX_EPT_EXECUTABLE_MASK                 0x4ull
-#define VMX_EPT_IGMT_BIT                        (1ull << 6)
+#define VMX_EPT_IPAT_BIT                        (1ull << 6)
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR         0xfffbc000ul
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 2c756fd4ab0e..519b54327d75 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -26,7 +26,7 @@ struct x86_init_mpparse {
         void (*smp_read_mpc_oem)(struct mpc_table *mpc);
         void (*mpc_oem_pci_bus)(struct mpc_bus *m);
         void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name);
-        void (*find_smp_config)(unsigned int reserve);
+        void (*find_smp_config)(void);
         void (*get_smp_config)(unsigned int early);
 };
 
@@ -91,6 +91,28 @@ struct x86_init_timers {
 };
 
 /**
+ * struct x86_init_iommu - platform specific iommu setup
+ * @iommu_init:                 platform specific iommu setup
+ */
+struct x86_init_iommu {
+        int (*iommu_init)(void);
+};
+
+/**
+ * struct x86_init_pci - platform specific pci init functions
+ * @arch_init:                  platform specific pci arch init call
+ * @init:                       platform specific pci subsystem init
+ * @init_irq:                   platform specific pci irq init
+ * @fixup_irqs:                 platform specific pci irq fixup
+ */
+struct x86_init_pci {
+        int (*arch_init)(void);
+        int (*init)(void);
+        void (*init_irq)(void);
+        void (*fixup_irqs)(void);
+};
+
+/**
  * struct x86_init_ops - functions for platform specific setup
  *
  */
@@ -101,6 +123,8 @@ struct x86_init_ops {
         struct x86_init_oem             oem;
         struct x86_init_paging          paging;
         struct x86_init_timers          timers;
+        struct x86_init_iommu           iommu;
+        struct x86_init_pci             pci;
 };
 
 /**
@@ -116,11 +140,16 @@ struct x86_cpuinit_ops {
  * @calibrate_tsc:              calibrate TSC
  * @get_wallclock:              get time from HW clock like RTC etc.
  * @set_wallclock:              set time back to HW clock
+ * @is_untracked_pat_range      exclude from PAT logic
+ * @nmi_init                    enable NMI on cpus
  */
 struct x86_platform_ops {
         unsigned long (*calibrate_tsc)(void);
         unsigned long (*get_wallclock)(void);
         int (*set_wallclock)(unsigned long nowtime);
+        void (*iommu_shutdown)(void);
+        bool (*is_untracked_pat_range)(u64 start, u64 end);
+        void (*nmi_init)(void);
 };
 
 extern struct x86_init_ops x86_init;
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index d5b7e90c0edf..396ff4cc8ed4 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -37,31 +37,4 @@
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
-enum xen_domain_type {
-        XEN_NATIVE,             /* running on bare hardware    */
-        XEN_PV_DOMAIN,          /* running in a PV domain      */
-        XEN_HVM_DOMAIN,         /* running in a Xen hvm domain */
-};
-
-#ifdef CONFIG_XEN
-extern enum xen_domain_type xen_domain_type;
-#else
-#define xen_domain_type         XEN_NATIVE
-#endif
-
-#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)
-#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/xsave.h b/arch/x86/include/asm/xsave.h
index 727acc152344..ddc04ccad03b 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -27,9 +27,11 @@
 extern unsigned int xstate_size;
 extern u64 pcntxt_mask;
 extern struct xsave_struct *init_xstate_buf;
+extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
 extern void xsave_cntxt_init(void);
 extern void xsave_init(void);
+extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 extern int init_fpu(struct task_struct *child);
 extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
                             void __user *fpstate,