331 files changed, 8352 insertions, 4926 deletions

diff --git a/include/asm-x86/Kbuild b/include/asm-x86/Kbuild
index 1e3554596f72..4a8e80cdcfa5 100644
--- a/include/asm-x86/Kbuild
+++ b/include/asm-x86/Kbuild
@@ -3,7 +3,6 @@ include include/asm-generic/Kbuild.asm
 header-y += boot.h
 header-y += bootparam.h
 header-y += debugreg.h
-header-y += kvm.h
 header-y += ldt.h
 header-y += msr-index.h
 header-y += prctl.h
@@ -19,7 +18,6 @@ unifdef-y += msr.h
 unifdef-y += mtrr.h
 unifdef-y += posix_types_32.h
 unifdef-y += posix_types_64.h
-unifdef-y += ptrace.h
 unifdef-y += unistd_32.h
 unifdef-y += unistd_64.h
 unifdef-y += vm86.h
diff --git a/include/asm-x86/a.out-core.h b/include/asm-x86/a.out-core.h
index 714207a1c387..f5705761a37b 100644
--- a/include/asm-x86/a.out-core.h
+++ b/include/asm-x86/a.out-core.h
@@ -9,8 +9,8 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
-#ifndef _ASM_A_OUT_CORE_H
-#define _ASM_A_OUT_CORE_H
+#ifndef ASM_X86__A_OUT_CORE_H
+#define ASM_X86__A_OUT_CORE_H
 
 #ifdef __KERNEL__
 #ifdef CONFIG_X86_32
@@ -70,4 +70,4 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 
 #endif /* CONFIG_X86_32 */
 #endif /* __KERNEL__ */
-#endif /* _ASM_A_OUT_CORE_H */
+#endif /* ASM_X86__A_OUT_CORE_H */
diff --git a/include/asm-x86/a.out.h b/include/asm-x86/a.out.h
index 4684f97a5bbd..0948748bc69c 100644
--- a/include/asm-x86/a.out.h
+++ b/include/asm-x86/a.out.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_A_OUT_H
-#define _ASM_X86_A_OUT_H
+#ifndef ASM_X86__A_OUT_H
+#define ASM_X86__A_OUT_H
 
 struct exec
 {
@@ -17,4 +17,4 @@ struct exec
 #define N_DRSIZE(a)     ((a).a_drsize)
 #define N_SYMSIZE(a)    ((a).a_syms)
 
-#endif /* _ASM_X86_A_OUT_H */
+#endif /* ASM_X86__A_OUT_H */
diff --git a/include/asm-x86/acpi.h b/include/asm-x86/acpi.h
index 14411c9de46f..392e17336be1 100644
--- a/include/asm-x86/acpi.h
+++ b/include/asm-x86/acpi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_ACPI_H
-#define _ASM_X86_ACPI_H
+#ifndef ASM_X86__ACPI_H
+#define ASM_X86__ACPI_H
 
 /*
  *  Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
@@ -28,6 +28,7 @@
 #include <asm/numa.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
+#include <asm/mpspec.h>
 
 #define COMPILER_DEPENDENT_INT64   long long
 #define COMPILER_DEPENDENT_UINT64  unsigned long long
@@ -139,6 +140,8 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
             boot_cpu_data.x86_model <= 0x05 &&
             boot_cpu_data.x86_mask < 0x0A)
                 return 1;
+        else if (boot_cpu_has(X86_FEATURE_AMDC1E))
+                return 1;
         else
                 return max_cstate;
 }
@@ -160,9 +163,7 @@ struct bootnode;
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
 extern int acpi_scan_nodes(unsigned long start, unsigned long end);
-#ifdef CONFIG_X86_64
-# define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-#endif
+#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
 extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
                                    int num_nodes);
 #else
@@ -174,4 +175,4 @@ static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
 
 #define acpi_unlazy_tlb(x)      leave_mm(x)
 
-#endif /*__X86_ASM_ACPI_H*/
+#endif /* ASM_X86__ACPI_H */
diff --git a/include/asm-x86/agp.h b/include/asm-x86/agp.h
index e4004a9f6a9a..3617fd4fcdf9 100644
--- a/include/asm-x86/agp.h
+++ b/include/asm-x86/agp.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_AGP_H
-#define _ASM_X86_AGP_H
+#ifndef ASM_X86__AGP_H
+#define ASM_X86__AGP_H
 
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
@@ -32,4 +32,4 @@
 #define free_gatt_pages(table, order)   \
         free_pages((unsigned long)(table), (order))
 
-#endif
+#endif /* ASM_X86__AGP_H */
diff --git a/include/asm-x86/alternative.h b/include/asm-x86/alternative.h
index 1f6a9ca10126..22d3c9862bf3 100644
--- a/include/asm-x86/alternative.h
+++ b/include/asm-x86/alternative.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_ALTERNATIVE_H
-#define _ASM_X86_ALTERNATIVE_H
+#ifndef ASM_X86__ALTERNATIVE_H
+#define ASM_X86__ALTERNATIVE_H
 
 #include <linux/types.h>
 #include <linux/stddef.h>
@@ -72,6 +72,8 @@ static inline void alternatives_smp_module_del(struct module *mod) {}
 static inline void alternatives_smp_switch(int smp) {}
 #endif  /* CONFIG_SMP */
 
+const unsigned char *const *find_nop_table(void);
+
 /*
  * Alternative instructions for different CPU types or capabilities.
  *
@@ -178,4 +180,4 @@ extern void add_nops(void *insns, unsigned int len);
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_early(void *addr, const void *opcode, size_t len);
 
-#endif /* _ASM_X86_ALTERNATIVE_H */
+#endif /* ASM_X86__ALTERNATIVE_H */
diff --git a/include/asm-x86/amd_iommu.h b/include/asm-x86/amd_iommu.h
new file mode 100644
index 000000000000..041d0db7da27
--- /dev/null
+++ b/include/asm-x86/amd_iommu.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *         Leo Duran <leo.duran@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_H
+#define ASM_X86__AMD_IOMMU_H
+
+#include <linux/irqreturn.h>
+
+#ifdef CONFIG_AMD_IOMMU
+extern int amd_iommu_init(void);
+extern int amd_iommu_init_dma_ops(void);
+extern void amd_iommu_detect(void);
+extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
+#else
+static inline int amd_iommu_init(void) { return -ENODEV; }
+static inline void amd_iommu_detect(void) { }
+#endif
+
+#endif /* ASM_X86__AMD_IOMMU_H */
diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h
new file mode 100644
index 000000000000..b3085869a17b
--- /dev/null
+++ b/include/asm-x86/amd_iommu_types.h
@@ -0,0 +1,404 @@
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *         Leo Duran <leo.duran@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_TYPES_H
+#define ASM_X86__AMD_IOMMU_TYPES_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+/*
+ * some size calculation constants
+ */
+#define DEV_TABLE_ENTRY_SIZE            32
+#define ALIAS_TABLE_ENTRY_SIZE          2
+#define RLOOKUP_TABLE_ENTRY_SIZE        (sizeof(void *))
+
+/* Length of the MMIO region for the AMD IOMMU */
+#define MMIO_REGION_LENGTH       0x4000
+
+/* Capability offsets used by the driver */
+#define MMIO_CAP_HDR_OFFSET     0x00
+#define MMIO_RANGE_OFFSET       0x0c
+#define MMIO_MISC_OFFSET        0x10
+
+/* Masks, shifts and macros to parse the device range capability */
+#define MMIO_RANGE_LD_MASK      0xff000000
+#define MMIO_RANGE_FD_MASK      0x00ff0000
+#define MMIO_RANGE_BUS_MASK     0x0000ff00
+#define MMIO_RANGE_LD_SHIFT     24
+#define MMIO_RANGE_FD_SHIFT     16
+#define MMIO_RANGE_BUS_SHIFT    8
+#define MMIO_GET_LD(x)  (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT)
+#define MMIO_GET_FD(x)  (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT)
+#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT)
+#define MMIO_MSI_NUM(x) ((x) & 0x1f)
+
+/* Flag masks for the AMD IOMMU exclusion range */
+#define MMIO_EXCL_ENABLE_MASK 0x01ULL
+#define MMIO_EXCL_ALLOW_MASK  0x02ULL
+
+/* Used offsets into the MMIO space */
+#define MMIO_DEV_TABLE_OFFSET   0x0000
+#define MMIO_CMD_BUF_OFFSET     0x0008
+#define MMIO_EVT_BUF_OFFSET     0x0010
+#define MMIO_CONTROL_OFFSET     0x0018
+#define MMIO_EXCL_BASE_OFFSET   0x0020
+#define MMIO_EXCL_LIMIT_OFFSET  0x0028
+#define MMIO_CMD_HEAD_OFFSET    0x2000
+#define MMIO_CMD_TAIL_OFFSET    0x2008
+#define MMIO_EVT_HEAD_OFFSET    0x2010
+#define MMIO_EVT_TAIL_OFFSET    0x2018
+#define MMIO_STATUS_OFFSET      0x2020
+
+/* MMIO status bits */
+#define MMIO_STATUS_COM_WAIT_INT_MASK   0x04
+
+/* event logging constants */
+#define EVENT_ENTRY_SIZE        0x10
+#define EVENT_TYPE_SHIFT        28
+#define EVENT_TYPE_MASK         0xf
+#define EVENT_TYPE_ILL_DEV      0x1
+#define EVENT_TYPE_IO_FAULT     0x2
+#define EVENT_TYPE_DEV_TAB_ERR  0x3
+#define EVENT_TYPE_PAGE_TAB_ERR 0x4
+#define EVENT_TYPE_ILL_CMD      0x5
+#define EVENT_TYPE_CMD_HARD_ERR 0x6
+#define EVENT_TYPE_IOTLB_INV_TO 0x7
+#define EVENT_TYPE_INV_DEV_REQ  0x8
+#define EVENT_DEVID_MASK        0xffff
+#define EVENT_DEVID_SHIFT       0
+#define EVENT_DOMID_MASK        0xffff
+#define EVENT_DOMID_SHIFT       0
+#define EVENT_FLAGS_MASK        0xfff
+#define EVENT_FLAGS_SHIFT       0x10
+
+/* feature control bits */
+#define CONTROL_IOMMU_EN        0x00ULL
+#define CONTROL_HT_TUN_EN       0x01ULL
+#define CONTROL_EVT_LOG_EN      0x02ULL
+#define CONTROL_EVT_INT_EN      0x03ULL
+#define CONTROL_COMWAIT_EN      0x04ULL
+#define CONTROL_PASSPW_EN       0x08ULL
+#define CONTROL_RESPASSPW_EN    0x09ULL
+#define CONTROL_COHERENT_EN     0x0aULL
+#define CONTROL_ISOC_EN         0x0bULL
+#define CONTROL_CMDBUF_EN       0x0cULL
+#define CONTROL_PPFLOG_EN       0x0dULL
+#define CONTROL_PPFINT_EN       0x0eULL
+
+/* command specific defines */
+#define CMD_COMPL_WAIT          0x01
+#define CMD_INV_DEV_ENTRY       0x02
+#define CMD_INV_IOMMU_PAGES     0x03
+
+#define CMD_COMPL_WAIT_STORE_MASK       0x01
+#define CMD_COMPL_WAIT_INT_MASK         0x02
+#define CMD_INV_IOMMU_PAGES_SIZE_MASK   0x01
+#define CMD_INV_IOMMU_PAGES_PDE_MASK    0x02
+
+#define CMD_INV_IOMMU_ALL_PAGES_ADDRESS 0x7fffffffffffffffULL
+
+/* macros and definitions for device table entries */
+#define DEV_ENTRY_VALID         0x00
+#define DEV_ENTRY_TRANSLATION   0x01
+#define DEV_ENTRY_IR            0x3d
+#define DEV_ENTRY_IW            0x3e
+#define DEV_ENTRY_NO_PAGE_FAULT 0x62
+#define DEV_ENTRY_EX            0x67
+#define DEV_ENTRY_SYSMGT1       0x68
+#define DEV_ENTRY_SYSMGT2       0x69
+#define DEV_ENTRY_INIT_PASS     0xb8
+#define DEV_ENTRY_EINT_PASS     0xb9
+#define DEV_ENTRY_NMI_PASS      0xba
+#define DEV_ENTRY_LINT0_PASS    0xbe
+#define DEV_ENTRY_LINT1_PASS    0xbf
+#define DEV_ENTRY_MODE_MASK     0x07
+#define DEV_ENTRY_MODE_SHIFT    0x09
+
+/* constants to configure the command buffer */
+#define CMD_BUFFER_SIZE    8192
+#define CMD_BUFFER_ENTRIES 512
+#define MMIO_CMD_SIZE_SHIFT 56
+#define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
+
+/* constants for event buffer handling */
+#define EVT_BUFFER_SIZE         8192 /* 512 entries */
+#define EVT_LEN_MASK            (0x9ULL << 56)
+
+#define PAGE_MODE_1_LEVEL 0x01
+#define PAGE_MODE_2_LEVEL 0x02
+#define PAGE_MODE_3_LEVEL 0x03
+
+#define IOMMU_PDE_NL_0   0x000ULL
+#define IOMMU_PDE_NL_1   0x200ULL
+#define IOMMU_PDE_NL_2   0x400ULL
+#define IOMMU_PDE_NL_3   0x600ULL
+
+#define IOMMU_PTE_L2_INDEX(address) (((address) >> 30) & 0x1ffULL)
+#define IOMMU_PTE_L1_INDEX(address) (((address) >> 21) & 0x1ffULL)
+#define IOMMU_PTE_L0_INDEX(address) (((address) >> 12) & 0x1ffULL)
+
+#define IOMMU_MAP_SIZE_L1 (1ULL << 21)
+#define IOMMU_MAP_SIZE_L2 (1ULL << 30)
+#define IOMMU_MAP_SIZE_L3 (1ULL << 39)
+
+#define IOMMU_PTE_P  (1ULL << 0)
+#define IOMMU_PTE_TV (1ULL << 1)
+#define IOMMU_PTE_U  (1ULL << 59)
+#define IOMMU_PTE_FC (1ULL << 60)
+#define IOMMU_PTE_IR (1ULL << 61)
+#define IOMMU_PTE_IW (1ULL << 62)
+
+#define IOMMU_L1_PDE(address) \
+        ((address) | IOMMU_PDE_NL_1 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
+#define IOMMU_L2_PDE(address) \
+        ((address) | IOMMU_PDE_NL_2 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
+
+#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
+#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
+#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
+#define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07)
+
+#define IOMMU_PROT_MASK 0x03
+#define IOMMU_PROT_IR 0x01
+#define IOMMU_PROT_IW 0x02
+
+/* IOMMU capabilities */
+#define IOMMU_CAP_IOTLB   24
+#define IOMMU_CAP_NPCACHE 26
+
+#define MAX_DOMAIN_ID 65536
+
+/* FIXME: move this macro to <linux/pci.h> */
+#define PCI_BUS(x) (((x) >> 8) & 0xff)
+
+/*
+ * This structure contains generic data for  IOMMU protection domains
+ * independent of their use.
+ */
+struct protection_domain {
+        spinlock_t lock; /* mostly used to lock the page table*/
+        u16 id;          /* the domain id written to the device table */
+        int mode;        /* paging mode (0-6 levels) */
+        u64 *pt_root;    /* page table root pointer */
+        void *priv;      /* private data */
+};
+
+/*
+ * Data container for a dma_ops specific protection domain
+ */
+struct dma_ops_domain {
+        struct list_head list;
+
+        /* generic protection domain information */
+        struct protection_domain domain;
+
+        /* size of the aperture for the mappings */
+        unsigned long aperture_size;
+
+        /* address we start to search for free addresses */
+        unsigned long next_bit;
+
+        /* address allocation bitmap */
+        unsigned long *bitmap;
+
+        /*
+         * Array of PTE pages for the aperture. In this array we save all the
+         * leaf pages of the domain page table used for the aperture. This way
+         * we don't need to walk the page table to find a specific PTE. We can
+         * just calculate its address in constant time.
+         */
+        u64 **pte_pages;
+
+        /* This will be set to true when TLB needs to be flushed */
+        bool need_flush;
+
+        /*
+         * if this is a preallocated domain, keep the device for which it was
+         * preallocated in this variable
+         */
+        u16 target_dev;
+};
+
+/*
+ * Structure where we save information about one hardware AMD IOMMU in the
+ * system.
+ */
+struct amd_iommu {
+        struct list_head list;
+
+        /* locks the accesses to the hardware */
+        spinlock_t lock;
+
+        /* Pointer to PCI device of this IOMMU */
+        struct pci_dev *dev;
+
+        /*
+         * Capability pointer. There could be more than one IOMMU per PCI
+         * device function if there are more than one AMD IOMMU capability
+         * pointers.
+         */
+        u16 cap_ptr;
+
+        /* physical address of MMIO space */
+        u64 mmio_phys;
+        /* virtual address of MMIO space */
+        u8 *mmio_base;
+
+        /* capabilities of that IOMMU read from ACPI */
+        u32 cap;
+
+        /* pci domain of this IOMMU */
+        u16 pci_seg;
+
+        /* first device this IOMMU handles. read from PCI */
+        u16 first_device;
+        /* last device this IOMMU handles. read from PCI */
+        u16 last_device;
+
+        /* start of exclusion range of that IOMMU */
+        u64 exclusion_start;
+        /* length of exclusion range of that IOMMU */
+        u64 exclusion_length;
+
+        /* command buffer virtual address */
+        u8 *cmd_buf;
+        /* size of command buffer */
+        u32 cmd_buf_size;
+
+        /* event buffer virtual address */
+        u8 *evt_buf;
+        /* size of event buffer */
+        u32 evt_buf_size;
+        /* MSI number for event interrupt */
+        u16 evt_msi_num;
+
+        /* if one, we need to send a completion wait command */
+        int need_sync;
+
+        /* true if interrupts for this IOMMU are already enabled */
+        bool int_enabled;
+
+        /* default dma_ops domain for that IOMMU */
+        struct dma_ops_domain *default_dom;
+};
+
+/*
+ * List with all IOMMUs in the system. This list is not locked because it is
+ * only written and read at driver initialization or suspend time
+ */
+extern struct list_head amd_iommu_list;
+
+/*
+ * Structure defining one entry in the device table
+ */
+struct dev_table_entry {
+        u32 data[8];
+};
+
+/*
+ * One entry for unity mappings parsed out of the ACPI table.
+ */
+struct unity_map_entry {
+        struct list_head list;
+
+        /* starting device id this entry is used for (including) */
+        u16 devid_start;
+        /* end device id this entry is used for (including) */
+        u16 devid_end;
+
+        /* start address to unity map (including) */
+        u64 address_start;
+        /* end address to unity map (including) */
+        u64 address_end;
+
+        /* required protection */
+        int prot;
+};
+
+/*
+ * List of all unity mappings. It is not locked because as runtime it is only
+ * read. It is created at ACPI table parsing time.
+ */
+extern struct list_head amd_iommu_unity_map;
+
+/*
+ * Data structures for device handling
+ */
+
+/*
+ * Device table used by hardware. Read and write accesses by software are
+ * locked with the amd_iommu_pd_table lock.
+ */
+extern struct dev_table_entry *amd_iommu_dev_table;
+
+/*
+ * Alias table to find requestor ids to device ids. Not locked because only
+ * read on runtime.
+ */
+extern u16 *amd_iommu_alias_table;
+
+/*
+ * Reverse lookup table to find the IOMMU which translates a specific device.
+ */
+extern struct amd_iommu **amd_iommu_rlookup_table;
+
+/* size of the dma_ops aperture as power of 2 */
+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 int amd_iommu_isolate;
+
+/*
+ * If true, the addresses will be flushed on unmap time, not when
+ * they are reused
+ */
+extern bool amd_iommu_unmap_flush;
+
+/* takes a PCI device id and prints it out in a readable form */
+static inline void print_devid(u16 devid, int nl)
+{
+        int bus = devid >> 8;
+        int dev = devid >> 3 & 0x1f;
+        int fn  = devid & 0x07;
+
+        printk("%02x:%02x.%x", bus, dev, fn);
+        if (nl)
+                printk("\n");
+}
+
+/* takes bus and device/function and returns the device id
+ * FIXME: should that be in generic PCI code? */
+static inline u16 calc_devid(u8 bus, u8 devfn)
+{
+        return (((u16)bus) << 8) | devfn;
+}
+
+#endif /* ASM_X86__AMD_IOMMU_TYPES_H */
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index be9639a9a186..d76a0839abe9 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -1,17 +1,19 @@
-#ifndef _ASM_X86_APIC_H
-#define _ASM_X86_APIC_H
+#ifndef ASM_X86__APIC_H
+#define ASM_X86__APIC_H
 
 #include <linux/pm.h>
 #include <linux/delay.h>
+
+#include <asm/alternative.h>
 #include <asm/fixmap.h>
 #include <asm/apicdef.h>
 #include <asm/processor.h>
 #include <asm/system.h>
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3      1
 
-#define Dprintk(x...)
-
 /*
  * Debugging macros
  */
@@ -35,71 +37,109 @@ extern void generic_apic_probe(void);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
-extern int apic_verbosity;
-extern int timer_over_8254;
+extern unsigned int apic_verbosity;
 extern int local_apic_timer_c2_ok;
-extern int local_apic_timer_disabled;
 
-extern int apic_runs_main_timer;
 extern int ioapic_force;
-extern int disable_apic;
-extern int disable_apic_timer;
 
+extern int disable_apic;
 /*
  * Basic functions accessing APICs.
  */
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
-#define apic_write native_apic_write
-#define apic_write_atomic native_apic_write_atomic
-#define apic_read native_apic_read
 #define setup_boot_clock setup_boot_APIC_clock
 #define setup_secondary_clock setup_secondary_APIC_clock
 #endif
 
 extern int is_vsmp_box(void);
+extern void xapic_wait_icr_idle(void);
+extern u32 safe_xapic_wait_icr_idle(void);
+extern u64 xapic_icr_read(void);
+extern void xapic_icr_write(u32, u32);
+extern int setup_profiling_timer(unsigned int);
 
-static inline void native_apic_write(unsigned long reg, u32 v)
+static inline void native_apic_mem_write(u32 reg, u32 v)
 {
-        *((volatile u32 *)(APIC_BASE + reg)) = v;
+        volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
+
+        alternative_io("movl %0, %1", "xchgl %0, %1", X86_FEATURE_11AP,
+                       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
+                       ASM_OUTPUT2("0" (v), "m" (*addr)));
 }
 
-static inline void native_apic_write_atomic(unsigned long reg, u32 v)
+static inline u32 native_apic_mem_read(u32 reg)
 {
-        (void)xchg((u32 *)(APIC_BASE + reg), v);
+        return *((volatile u32 *)(APIC_BASE + reg));
 }
 
-static inline u32 native_apic_read(unsigned long reg)
+static inline void native_apic_msr_write(u32 reg, u32 v)
 {
-        return *((volatile u32 *)(APIC_BASE + reg));
+        if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||
+            reg == APIC_LVR)
+                return;
+
+        wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
 }
 
-extern void apic_wait_icr_idle(void);
-extern u32 safe_apic_wait_icr_idle(void);
+static inline u32 native_apic_msr_read(u32 reg)
+{
+        u32 low, high;
+
+        if (reg == APIC_DFR)
+                return -1;
+
+        rdmsr(APIC_BASE_MSR + (reg >> 4), low, high);
+        return low;
+}
+
+#ifndef CONFIG_X86_32
+extern int x2apic, x2apic_preenabled;
+extern void check_x2apic(void);
+extern void enable_x2apic(void);
+extern void enable_IR_x2apic(void);
+extern void x2apic_icr_write(u32 low, u32 id);
+#endif
+
+struct apic_ops {
+        u32 (*read)(u32 reg);
+        void (*write)(u32 reg, u32 v);
+        u64 (*icr_read)(void);
+        void (*icr_write)(u32 low, u32 high);
+        void (*wait_icr_idle)(void);
+        u32 (*safe_wait_icr_idle)(void);
+};
+
+extern struct apic_ops *apic_ops;
+
+#define apic_read (apic_ops->read)
+#define apic_write (apic_ops->write)
+#define apic_icr_read (apic_ops->icr_read)
+#define apic_icr_write (apic_ops->icr_write)
+#define apic_wait_icr_idle (apic_ops->wait_icr_idle)
+#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle)
+
 extern int get_physical_broadcast(void);
 
-#ifdef CONFIG_X86_GOOD_APIC
-# define FORCE_READ_AROUND_WRITE 0
-# define apic_read_around(x)
-# define apic_write_around(x, y) apic_write((x), (y))
-#else
-# define FORCE_READ_AROUND_WRITE 1
-# define apic_read_around(x) apic_read(x)
-# define apic_write_around(x, y) apic_write_atomic((x), (y))
+#ifdef CONFIG_X86_64
+static inline void ack_x2APIC_irq(void)
+{
+        /* Docs say use 0 for future compatibility */
+        native_apic_msr_write(APIC_EOI, 0);
+}
 #endif
 
+
 static inline void ack_APIC_irq(void)
 {
         /*
-         * ack_APIC_irq() actually gets compiled as a single instruction:
-         * - a single rmw on Pentium/82489DX
-         * - a single write on P6+ cores (CONFIG_X86_GOOD_APIC)
+         * ack_APIC_irq() actually gets compiled as a single instruction
          * ... yummie.
          */
 
         /* Docs say use 0 for future compatibility */
-        apic_write_around(APIC_EOI, 0);
+        apic_write(APIC_EOI, 0);
 }
 
 extern int lapic_get_maxlvt(void);
@@ -125,17 +165,23 @@ extern void enable_NMI_through_LVT0(void);
  */
 #ifdef CONFIG_X86_64
 extern void early_init_lapic_mapping(void);
+extern int apic_is_clustered_box(void);
+#else
+static inline int apic_is_clustered_box(void)
+{
+        return 0;
+}
 #endif
 
 extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
 extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
 
-extern int apic_is_clustered_box(void);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok          1
+static inline void init_apic_mappings(void) { }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
-#endif /* __ASM_APIC_H */
+#endif /* ASM_X86__APIC_H */
diff --git a/include/asm-x86/apicdef.h b/include/asm-x86/apicdef.h
index 6b9008c78731..b922c85ac91d 100644
--- a/include/asm-x86/apicdef.h
+++ b/include/asm-x86/apicdef.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_APICDEF_H
-#define _ASM_X86_APICDEF_H
+#ifndef ASM_X86__APICDEF_H
+#define ASM_X86__APICDEF_H
 
 /*
  * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
@@ -105,6 +105,7 @@
 #define APIC_TMICT      0x380
 #define APIC_TMCCT      0x390
 #define APIC_TDCR       0x3E0
+#define APIC_SELF_IPI   0x3F0
 #define         APIC_TDR_DIV_TMBASE     (1 << 2)
 #define         APIC_TDR_DIV_1          0xB
 #define         APIC_TDR_DIV_2          0x0
@@ -128,6 +129,8 @@
 #define APIC_EILVT3     0x530
 
 #define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
+#define APIC_BASE_MSR   0x800
+#define X2APIC_ENABLE   (1UL << 10)
 
 #ifdef CONFIG_X86_32
 # define MAX_IO_APICS 64
@@ -411,4 +414,4 @@ struct local_apic {
 #else
  #define BAD_APICID 0xFFFFu
 #endif
-#endif
+#endif /* ASM_X86__APICDEF_H */
diff --git a/include/asm-x86/arch_hooks.h b/include/asm-x86/arch_hooks.h
index 768aee8a04ef..de4596b24c23 100644
--- a/include/asm-x86/arch_hooks.h
+++ b/include/asm-x86/arch_hooks.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_ARCH_HOOKS_H
-#define _ASM_ARCH_HOOKS_H
+#ifndef ASM_X86__ARCH_HOOKS_H
+#define ASM_X86__ARCH_HOOKS_H
 
 #include <linux/interrupt.h>
 
@@ -12,8 +12,6 @@
 /* these aren't arch hooks, they are generic routines
  * that can be used by the hooks */
 extern void init_ISA_irqs(void);
-extern void apic_intr_init(void);
-extern void smp_intr_init(void);
 extern irqreturn_t timer_interrupt(int irq, void *dev_id);
 
 /* these are the defined hooks */
@@ -21,7 +19,8 @@ extern void intr_init_hook(void);
 extern void pre_intr_init_hook(void);
 extern void pre_setup_arch_hook(void);
 extern void trap_init_hook(void);
+extern void pre_time_init_hook(void);
 extern void time_init_hook(void);
 extern void mca_nmi_hook(void);
 
-#endif
+#endif /* ASM_X86__ARCH_HOOKS_H */
diff --git a/include/asm-x86/asm.h b/include/asm-x86/asm.h
index 90dec0c23646..e1355f44d7c3 100644
--- a/include/asm-x86/asm.h
+++ b/include/asm-x86/asm.h
@@ -1,39 +1,47 @@
-#ifndef _ASM_X86_ASM_H
-#define _ASM_X86_ASM_H
-
-#ifdef CONFIG_X86_32
-/* 32 bits */
-
-# define _ASM_PTR       " .long "
-# define _ASM_ALIGN     " .balign 4 "
-# define _ASM_MOV_UL    " movl "
-
-# define _ASM_INC       " incl "
-# define _ASM_DEC       " decl "
-# define _ASM_ADD       " addl "
-# define _ASM_SUB       " subl "
-# define _ASM_XADD      " xaddl "
+#ifndef ASM_X86__ASM_H
+#define ASM_X86__ASM_H
 
+#ifdef __ASSEMBLY__
+# define __ASM_FORM(x)  x
+# define __ASM_EX_SEC   .section __ex_table
 #else
-/* 64 bits */
+# define __ASM_FORM(x)  " " #x " "
+# define __ASM_EX_SEC   " .section __ex_table,\"a\"\n"
+#endif
 
-# define _ASM_PTR       " .quad "
-# define _ASM_ALIGN     " .balign 8 "
-# define _ASM_MOV_UL    " movq "
-
-# define _ASM_INC       " incq "
-# define _ASM_DEC       " decq "
-# define _ASM_ADD       " addq "
-# define _ASM_SUB       " subq "
-# define _ASM_XADD      " xaddq "
-
-#endif /* CONFIG_X86_32 */
+#ifdef CONFIG_X86_32
+# define __ASM_SEL(a,b) __ASM_FORM(a)
+#else
+# define __ASM_SEL(a,b) __ASM_FORM(b)
+#endif
+
+#define __ASM_SIZE(inst)        __ASM_SEL(inst##l, inst##q)
+#define __ASM_REG(reg)          __ASM_SEL(e##reg, r##reg)
+
+#define _ASM_PTR        __ASM_SEL(.long, .quad)
+#define _ASM_ALIGN      __ASM_SEL(.balign 4, .balign 8)
+
+#define _ASM_MOV        __ASM_SIZE(mov)
+#define _ASM_INC        __ASM_SIZE(inc)
+#define _ASM_DEC        __ASM_SIZE(dec)
+#define _ASM_ADD        __ASM_SIZE(add)
+#define _ASM_SUB        __ASM_SIZE(sub)
+#define _ASM_XADD       __ASM_SIZE(xadd)
+
+#define _ASM_AX         __ASM_REG(ax)
+#define _ASM_BX         __ASM_REG(bx)
+#define _ASM_CX         __ASM_REG(cx)
+#define _ASM_DX         __ASM_REG(dx)
+#define _ASM_SP         __ASM_REG(sp)
+#define _ASM_BP         __ASM_REG(bp)
+#define _ASM_SI         __ASM_REG(si)
+#define _ASM_DI         __ASM_REG(di)
 
 /* Exception table entry */
 # define _ASM_EXTABLE(from,to) \
-        " .section __ex_table,\"a\"\n" \
+        __ASM_EX_SEC    \
         _ASM_ALIGN "\n" \
         _ASM_PTR #from "," #to "\n" \
         " .previous\n"
 
-#endif /* _ASM_X86_ASM_H */
+#endif /* ASM_X86__ASM_H */
diff --git a/include/asm-x86/atomic_32.h b/include/asm-x86/atomic_32.h
index 21a4825148c0..14d3f0beb889 100644
--- a/include/asm-x86/atomic_32.h
+++ b/include/asm-x86/atomic_32.h
@@ -1,5 +1,5 @@
-#ifndef __ARCH_I386_ATOMIC__
-#define __ARCH_I386_ATOMIC__
+#ifndef ASM_X86__ATOMIC_32_H
+#define ASM_X86__ATOMIC_32_H
 
 #include <linux/compiler.h>
 #include <asm/processor.h>
@@ -256,4 +256,4 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 #define smp_mb__after_atomic_inc()      barrier()
 
 #include <asm-generic/atomic.h>
-#endif
+#endif /* ASM_X86__ATOMIC_32_H */
diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h
index 3e0cd7d38335..2cb218c4a356 100644
--- a/include/asm-x86/atomic_64.h
+++ b/include/asm-x86/atomic_64.h
@@ -1,5 +1,5 @@
-#ifndef __ARCH_X86_64_ATOMIC__
-#define __ARCH_X86_64_ATOMIC__
+#ifndef ASM_X86__ATOMIC_64_H
+#define ASM_X86__ATOMIC_64_H
 
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
@@ -11,12 +11,6 @@
  * resource counting etc..
  */
 
-#ifdef CONFIG_SMP
-#define LOCK "lock ; "
-#else
-#define LOCK ""
-#endif
-
 /*
  * Make sure gcc doesn't try to be clever and move things around
  * on us. We need to use _exactly_ the address the user gave us,
@@ -234,7 +228,7 @@ static inline void atomic64_add(long i, atomic64_t *v)
 {
         asm volatile(LOCK_PREFIX "addq %1,%0"
                      : "=m" (v->counter)
-                     : "ir" (i), "m" (v->counter));
+                     : "er" (i), "m" (v->counter));
 }
 
 /**
@@ -248,7 +242,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 {
         asm volatile(LOCK_PREFIX "subq %1,%0"
                      : "=m" (v->counter)
-                     : "ir" (i), "m" (v->counter));
+                     : "er" (i), "m" (v->counter));
 }
 
 /**
@@ -266,7 +260,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v)
 
         asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
                      : "=m" (v->counter), "=qm" (c)
-                     : "ir" (i), "m" (v->counter) : "memory");
+                     : "er" (i), "m" (v->counter) : "memory");
         return c;
 }
 
@@ -347,7 +341,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v)
 
         asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
                      : "=m" (v->counter), "=qm" (c)
-                     : "ir" (i), "m" (v->counter) : "memory");
+                     : "er" (i), "m" (v->counter) : "memory");
         return c;
 }
 
@@ -431,6 +425,32 @@ static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
         return c != (u);
 }
 
+/**
+ * atomic_inc_short - increment of a short integer
+ * @v: pointer to type int
+ *
+ * Atomically adds 1 to @v
+ * Returns the new value of @u
+ */
+static inline short int atomic_inc_short(short int *v)
+{
+        asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
+        return *v;
+}
+
+/**
+ * atomic_or_long - OR of two long integers
+ * @v1: pointer to type unsigned long
+ * @v2: pointer to type unsigned long
+ *
+ * Atomically ORs @v1 and @v2
+ * Returns the result of the OR
+ */
+static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
+{
+        asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
+}
+
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
 
 /* These are x86-specific, used by some header files */
@@ -450,4 +470,4 @@ static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
 #define smp_mb__after_atomic_inc()      barrier()
 
 #include <asm-generic/atomic.h>
-#endif
+#endif /* ASM_X86__ATOMIC_64_H */
diff --git a/include/asm-x86/auxvec.h b/include/asm-x86/auxvec.h
index 87f5e6d5a020..12c7cac74202 100644
--- a/include/asm-x86/auxvec.h
+++ b/include/asm-x86/auxvec.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_AUXVEC_H
-#define _ASM_X86_AUXVEC_H
+#ifndef ASM_X86__AUXVEC_H
+#define ASM_X86__AUXVEC_H
 /*
  * Architecture-neutral AT_ values in 0-17, leave some room
  * for more of them, start the x86-specific ones at 32.
@@ -9,4 +9,4 @@
 #endif
 #define AT_SYSINFO_EHDR         33
 
-#endif
+#endif /* ASM_X86__AUXVEC_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_apic.h b/include/asm-x86/bigsmp/apic.h
index 8327907c79bf..0a9cd7c5ca0c 100644
--- a/include/asm-x86/mach-bigsmp/mach_apic.h
+++ b/include/asm-x86/bigsmp/apic.h
@@ -11,7 +11,7 @@ static inline int apic_id_registered(void)
 
 /* Round robin the irqs amoung the online cpus */
 static inline cpumask_t target_cpus(void)
-{ 
+{
         static unsigned long cpu = NR_CPUS;
         do {
                 if (cpu >= NR_CPUS)
@@ -23,7 +23,7 @@ static inline cpumask_t target_cpus(void)
 }
 
 #undef APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL       0
+#define APIC_DEST_LOGICAL       0
 #define TARGET_CPUS             (target_cpus())
 #define APIC_DFR_VALUE          (APIC_DFR_FLAT)
 #define INT_DELIVERY_MODE       (dest_Fixed)
@@ -63,9 +63,9 @@ static inline void init_apic_ldr(void)
         unsigned long val;
         int cpu = smp_processor_id();
 
-        apic_write_around(APIC_DFR, APIC_DFR_VALUE);
+        apic_write(APIC_DFR, APIC_DFR_VALUE);
         val = calculate_ldr(cpu);
-        apic_write_around(APIC_LDR, val);
+        apic_write(APIC_LDR, val);
 }
 
 static inline void setup_apic_routing(void)
@@ -81,7 +81,7 @@ static inline int multi_timer_check(int apic, int irq)
 
 static inline int apicid_to_node(int logical_apicid)
 {
-        return (0);
+        return apicid_2_node[hard_smp_processor_id()];
 }
 
 static inline int cpu_present_to_apicid(int mps_cpu)
diff --git a/include/asm-x86/mach-es7000/mach_apicdef.h b/include/asm-x86/bigsmp/apicdef.h
index a58ab5a75c8c..392c3f5ef2fe 100644
--- a/include/asm-x86/mach-es7000/mach_apicdef.h
+++ b/include/asm-x86/bigsmp/apicdef.h
@@ -3,10 +3,10 @@
 
 #define         APIC_ID_MASK            (0xFF<<24)
 
-static inline unsigned get_apic_id(unsigned long x) 
-{ 
+static inline unsigned get_apic_id(unsigned long x)
+{
         return (((x)>>24)&0xFF);
-} 
+}
 
 #define         GET_APIC_ID(x)  get_apic_id(x)
 
diff --git a/include/asm-x86/mach-bigsmp/mach_ipi.h b/include/asm-x86/bigsmp/ipi.h
index 9404c535b7ec..9404c535b7ec 100644
--- a/include/asm-x86/mach-bigsmp/mach_ipi.h
+++ b/include/asm-x86/bigsmp/ipi.h
diff --git a/include/asm-x86/bios_ebda.h b/include/asm-x86/bios_ebda.h
index b4a46b7be794..79b4b88505d7 100644
--- a/include/asm-x86/bios_ebda.h
+++ b/include/asm-x86/bios_ebda.h
@@ -1,5 +1,5 @@
-#ifndef _MACH_BIOS_EBDA_H
-#define _MACH_BIOS_EBDA_H
+#ifndef ASM_X86__BIOS_EBDA_H
+#define ASM_X86__BIOS_EBDA_H
 
 #include <asm/io.h>
 
@@ -14,4 +14,23 @@ static inline unsigned int get_bios_ebda(void)
         return address; /* 0 means none */
 }
 
-#endif /* _MACH_BIOS_EBDA_H */
+void reserve_ebda_region(void);
+
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+/*
+ * This is obviously not a great place for this, but we want to be
+ * able to scatter it around anywhere in the kernel.
+ */
+void check_for_bios_corruption(void);
+void start_periodic_check_for_corruption(void);
+#else
+static inline void check_for_bios_corruption(void)
+{
+}
+
+static inline void start_periodic_check_for_corruption(void)
+{
+}
+#endif
+
+#endif /* ASM_X86__BIOS_EBDA_H */
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index ee4b3ead6a43..451a74762bd4 100644
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_BITOPS_H
-#define _ASM_X86_BITOPS_H
+#ifndef ASM_X86__BITOPS_H
+#define ASM_X86__BITOPS_H
 
 /*
  * Copyright 1992, Linus Torvalds.
@@ -23,11 +23,21 @@
 #if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1)
 /* Technically wrong, but this avoids compilation errors on some gcc
    versions. */
-#define ADDR "=m" (*(volatile long *) addr)
+#define BITOP_ADDR(x) "=m" (*(volatile long *) (x))
 #else
-#define ADDR "+m" (*(volatile long *) addr)
+#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
 #endif
 
+#define ADDR                            BITOP_ADDR(addr)
+
+/*
+ * We do the locked ops that don't return the old value as
+ * a mask operation on a byte.
+ */
+#define IS_IMMEDIATE(nr)                (__builtin_constant_p(nr))
+#define CONST_MASK_ADDR(nr, addr)       BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK(nr)                  (1 << ((nr) & 7))
+
 /**
  * set_bit - Atomically set a bit in memory
  * @nr: the bit to set
@@ -43,9 +53,17 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(int nr, volatile void *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *addr)
 {
-        asm volatile(LOCK_PREFIX "bts %1,%0" : ADDR : "Ir" (nr) : "memory");
+        if (IS_IMMEDIATE(nr)) {
+                asm volatile(LOCK_PREFIX "orb %1,%0"
+                        : CONST_MASK_ADDR(nr, addr)
+                        : "iq" ((u8)CONST_MASK(nr))
+                        : "memory");
+        } else {
+                asm volatile(LOCK_PREFIX "bts %1,%0"
+                        : BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+        }
 }
 
 /**
@@ -57,7 +75,7 @@ static inline void set_bit(int nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile void *addr)
+static inline void __set_bit(int nr, volatile unsigned long *addr)
 {
         asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
@@ -72,9 +90,17 @@ static inline void __set_bit(int nr, volatile void *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void clear_bit(int nr, volatile void *addr)
+static inline void clear_bit(int nr, volatile unsigned long *addr)
 {
-        asm volatile(LOCK_PREFIX "btr %1,%0" : ADDR : "Ir" (nr));
+        if (IS_IMMEDIATE(nr)) {
+                asm volatile(LOCK_PREFIX "andb %1,%0"
+                        : CONST_MASK_ADDR(nr, addr)
+                        : "iq" ((u8)~CONST_MASK(nr)));
+        } else {
+                asm volatile(LOCK_PREFIX "btr %1,%0"
+                        : BITOP_ADDR(addr)
+                        : "Ir" (nr));
+        }
 }
 
 /*
@@ -85,13 +111,13 @@ static inline void clear_bit(int nr, volatile void *addr)
  * clear_bit() is atomic and implies release semantics before the memory
  * operation. It can be used for an unlock.
  */
-static inline void clear_bit_unlock(unsigned nr, volatile void *addr)
+static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
 {
         barrier();
         clear_bit(nr, addr);
 }
 
-static inline void __clear_bit(int nr, volatile void *addr)
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
 {
         asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
@@ -108,7 +134,7 @@ static inline void __clear_bit(int nr, volatile void *addr)
  * No memory barrier is required here, because x86 cannot reorder stores past
  * older loads. Same principle as spin_unlock.
  */
-static inline void __clear_bit_unlock(unsigned nr, volatile void *addr)
+static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
 {
         barrier();
         __clear_bit(nr, addr);
@@ -126,7 +152,7 @@ static inline void __clear_bit_unlock(unsigned nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile void *addr)
+static inline void __change_bit(int nr, volatile unsigned long *addr)
 {
         asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -140,7 +166,7 @@ static inline void __change_bit(int nr, volatile void *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(int nr, volatile void *addr)
+static inline void change_bit(int nr, volatile unsigned long *addr)
 {
         asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -153,7 +179,7 @@ static inline void change_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_set_bit(int nr, volatile void *addr)
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -170,7 +196,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
  *
  * This is the same as test_and_set_bit on x86.
  */
-static inline int test_and_set_bit_lock(int nr, volatile void *addr)
+static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
 {
         return test_and_set_bit(nr, addr);
 }
@@ -184,7 +210,7 @@ static inline int test_and_set_bit_lock(int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile void *addr)
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -203,7 +229,7 @@ static inline int __test_and_set_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_clear_bit(int nr, volatile void *addr)
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -223,7 +249,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile void *addr)
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -235,7 +261,7 @@ static inline int __test_and_clear_bit(int nr, volatile void *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile void *addr)
+static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -255,7 +281,7 @@ static inline int __test_and_change_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_change_bit(int nr, volatile void *addr)
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -266,13 +292,13 @@ static inline int test_and_change_bit(int nr, volatile void *addr)
         return oldbit;
 }
 
-static inline int constant_test_bit(int nr, const volatile void *addr)
+static inline int constant_test_bit(int nr, const volatile unsigned long *addr)
 {
         return ((1UL << (nr % BITS_PER_LONG)) &
                 (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
 }
 
-static inline int variable_test_bit(int nr, volatile const void *addr)
+static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
 {
         int oldbit;
 
@@ -330,7 +356,7 @@ static inline unsigned long ffz(unsigned long word)
  * __fls: find last set bit in word
  * @word: The word to search
  *
- * Undefined if no zero exists, so code should check against ~0UL first.
+ * Undefined if no set bit exists, so code should check against 0 first.
  */
 static inline unsigned long __fls(unsigned long word)
 {
@@ -398,16 +424,6 @@ static inline int fls(int x)
 
 #undef ADDR
 
-static inline void set_bit_string(unsigned long *bitmap,
-                unsigned long i, int len)
-{
-        unsigned long end = i + len;
-        while (i < end) {
-                __set_bit(i, bitmap);
-                i++;
-        }
-}
-
 #ifdef __KERNEL__
 
 #include <asm-generic/bitops/sched.h>
@@ -432,4 +448,4 @@ static inline void set_bit_string(unsigned long *bitmap,
 #include <asm-generic/bitops/minix.h>
 
 #endif /* __KERNEL__ */
-#endif  /* _ASM_X86_BITOPS_H */
+#endif /* ASM_X86__BITOPS_H */
diff --git a/include/asm-x86/boot.h b/include/asm-x86/boot.h
index 2faed7ecb092..1d63bd5d5946 100644
--- a/include/asm-x86/boot.h
+++ b/include/asm-x86/boot.h
@@ -1,10 +1,8 @@
-#ifndef _ASM_BOOT_H
-#define _ASM_BOOT_H
+#ifndef ASM_X86__BOOT_H
+#define ASM_X86__BOOT_H
 
 /* Don't touch these, unless you really know what you're doing. */
-#define DEF_INITSEG     0x9000
 #define DEF_SYSSEG      0x1000
-#define DEF_SETUPSEG    0x9020
 #define DEF_SYSSIZE     0x7F00
 
 /* Internal svga startup constants */
@@ -25,4 +23,4 @@
 #define BOOT_STACK_SIZE 0x1000
 #endif
 
-#endif /* _ASM_BOOT_H */
+#endif /* ASM_X86__BOOT_H */
diff --git a/include/asm-x86/bootparam.h b/include/asm-x86/bootparam.h
index f62f4733606b..ccf027e2d97d 100644
--- a/include/asm-x86/bootparam.h
+++ b/include/asm-x86/bootparam.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_BOOTPARAM_H
-#define _ASM_BOOTPARAM_H
+#ifndef ASM_X86__BOOTPARAM_H
+#define ASM_X86__BOOTPARAM_H
 
 #include <linux/types.h>
 #include <linux/screen_info.h>
@@ -11,6 +11,7 @@
 
 /* setup data types */
 #define SETUP_NONE                      0
+#define SETUP_E820_EXT                  1
 
 /* extensible setup data list node */
 struct setup_data {
@@ -40,6 +41,7 @@ struct setup_header {
         __u8    type_of_loader;
         __u8    loadflags;
 #define LOADED_HIGH     (1<<0)
+#define QUIET_FLAG      (1<<5)
 #define KEEP_SEGMENTS   (1<<6)
 #define CAN_USE_HEAP    (1<<7)
         __u16   setup_move_size;
@@ -106,4 +108,4 @@ struct boot_params {
         __u8  _pad9[276];                               /* 0xeec */
 } __attribute__((packed));
 
-#endif /* _ASM_BOOTPARAM_H */
+#endif /* ASM_X86__BOOTPARAM_H */
diff --git a/include/asm-x86/bug.h b/include/asm-x86/bug.h
index b69aa64b82a4..91ad43a54c47 100644
--- a/include/asm-x86/bug.h
+++ b/include/asm-x86/bug.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_BUG_H
-#define _ASM_X86_BUG_H
+#ifndef ASM_X86__BUG_H
+#define ASM_X86__BUG_H
 
 #ifdef CONFIG_BUG
 #define HAVE_ARCH_BUG
@@ -36,4 +36,4 @@ do {								\
 #endif /* !CONFIG_BUG */
 
 #include <asm-generic/bug.h>
-#endif
+#endif /* ASM_X86__BUG_H */
diff --git a/include/asm-x86/bugs.h b/include/asm-x86/bugs.h
index 021cbdd5f258..dc604985f2ad 100644
--- a/include/asm-x86/bugs.h
+++ b/include/asm-x86/bugs.h
@@ -1,7 +1,12 @@
-#ifndef _ASM_X86_BUGS_H
-#define _ASM_X86_BUGS_H
+#ifndef ASM_X86__BUGS_H
+#define ASM_X86__BUGS_H
 
 extern void check_bugs(void);
+
+#if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
 int ppro_with_ram_bug(void);
+#else
+static inline int ppro_with_ram_bug(void) { return 0; }
+#endif
 
-#endif /* _ASM_X86_BUGS_H */
+#endif /* ASM_X86__BUGS_H */
diff --git a/include/asm-x86/byteorder.h b/include/asm-x86/byteorder.h
index e02ae2d89acf..722f27d68105 100644
--- a/include/asm-x86/byteorder.h
+++ b/include/asm-x86/byteorder.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_BYTEORDER_H
-#define _ASM_X86_BYTEORDER_H
+#ifndef ASM_X86__BYTEORDER_H
+#define ASM_X86__BYTEORDER_H
 
 #include <asm/types.h>
 #include <linux/compiler.h>
@@ -78,4 +78,4 @@ static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
 
 #include <linux/byteorder/little_endian.h>
 
-#endif /* _ASM_X86_BYTEORDER_H */
+#endif /* ASM_X86__BYTEORDER_H */
diff --git a/include/asm-x86/cache.h b/include/asm-x86/cache.h
index 1e0bac86f38f..ea3f1cc06a97 100644
--- a/include/asm-x86/cache.h
+++ b/include/asm-x86/cache.h
@@ -1,5 +1,5 @@
-#ifndef _ARCH_X86_CACHE_H
-#define _ARCH_X86_CACHE_H
+#ifndef ASM_X86__CACHE_H
+#define ASM_X86__CACHE_H
 
 /* L1 cache line size */
 #define L1_CACHE_SHIFT  (CONFIG_X86_L1_CACHE_SHIFT)
@@ -17,4 +17,4 @@
 #endif
 #endif
 
-#endif
+#endif /* ASM_X86__CACHE_H */
diff --git a/include/asm-x86/cacheflush.h b/include/asm-x86/cacheflush.h
index f4c0ab50d2c2..68840ef1b35a 100644
--- a/include/asm-x86/cacheflush.h
+++ b/include/asm-x86/cacheflush.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_CACHEFLUSH_H
-#define _ASM_X86_CACHEFLUSH_H
+#ifndef ASM_X86__CACHEFLUSH_H
+#define ASM_X86__CACHEFLUSH_H
 
 /* Keep includes the same across arches.  */
 #include <linux/mm.h>
@@ -24,6 +24,8 @@
 #define copy_from_user_page(vma, page, vaddr, dst, src, len)    \
         memcpy((dst), (src), (len))
 
+#define PG_non_WB                               PG_arch_1
+PAGEFLAG(NonWB, non_WB)
 
 /*
  * The set_memory_* API can be used to change various attributes of a virtual
@@ -66,6 +68,9 @@ int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_np(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
 
+int set_memory_array_uc(unsigned long *addr, int addrinarray);
+int set_memory_array_wb(unsigned long *addr, int addrinarray);
+
 /*
  * For legacy compatibility with the old APIs, a few functions
  * are provided that work on a "struct page".
@@ -96,8 +101,6 @@ int set_pages_rw(struct page *page, int numpages);
 
 void clflush_cache_range(void *addr, unsigned int size);
 
-void cpa_init(void);
-
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
@@ -112,4 +115,4 @@ static inline int rodata_test(void)
 }
 #endif
 
-#endif
+#endif /* ASM_X86__CACHEFLUSH_H */
diff --git a/include/asm-x86/calgary.h b/include/asm-x86/calgary.h
index 67f60406e2d8..933fd272f826 100644
--- a/include/asm-x86/calgary.h
+++ b/include/asm-x86/calgary.h
@@ -21,8 +21,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _ASM_X86_64_CALGARY_H
-#define _ASM_X86_64_CALGARY_H
+#ifndef ASM_X86__CALGARY_H
+#define ASM_X86__CALGARY_H
 
 #include <linux/spinlock.h>
 #include <linux/device.h>
@@ -69,4 +69,4 @@ static inline int calgary_iommu_init(void) { return 1; }
 static inline void detect_calgary(void) { return; }
 #endif
 
-#endif /* _ASM_X86_64_CALGARY_H */
+#endif /* ASM_X86__CALGARY_H */
diff --git a/include/asm-x86/calling.h b/include/asm-x86/calling.h
index f13e62e2cb3e..2bc162e0ec6e 100644
--- a/include/asm-x86/calling.h
+++ b/include/asm-x86/calling.h
@@ -104,7 +104,7 @@
         .endif
         .endm
 
-        .macro LOAD_ARGS offset
+        .macro LOAD_ARGS offset, skiprax=0
         movq \offset(%rsp),    %r11
         movq \offset+8(%rsp),  %r10
         movq \offset+16(%rsp), %r9
@@ -113,7 +113,10 @@
         movq \offset+48(%rsp), %rdx
         movq \offset+56(%rsp), %rsi
         movq \offset+64(%rsp), %rdi
+        .if \skiprax
+        .else
         movq \offset+72(%rsp), %rax
+        .endif
         .endm
 
 #define REST_SKIP       6*8
@@ -165,4 +168,3 @@
         .macro icebp
         .byte 0xf1
         .endm
-
diff --git a/include/asm-x86/checksum_32.h b/include/asm-x86/checksum_32.h
index 52bbb0d8c4c1..d041e8cda227 100644
--- a/include/asm-x86/checksum_32.h
+++ b/include/asm-x86/checksum_32.h
@@ -1,5 +1,5 @@
-#ifndef _I386_CHECKSUM_H
-#define _I386_CHECKSUM_H
+#ifndef ASM_X86__CHECKSUM_32_H
+#define ASM_X86__CHECKSUM_32_H
 
 #include <linux/in6.h>
 
@@ -186,4 +186,4 @@ static inline __wsum csum_and_copy_to_user(const void *src,
         return (__force __wsum)-1; /* invalid checksum */
 }
 
-#endif
+#endif /* ASM_X86__CHECKSUM_32_H */
diff --git a/include/asm-x86/checksum_64.h b/include/asm-x86/checksum_64.h
index 8bd861cc5267..110f403beb89 100644
--- a/include/asm-x86/checksum_64.h
+++ b/include/asm-x86/checksum_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_CHECKSUM_H
-#define _X86_64_CHECKSUM_H
+#ifndef ASM_X86__CHECKSUM_64_H
+#define ASM_X86__CHECKSUM_64_H
 
 /*
  * Checksums for x86-64
@@ -188,4 +188,4 @@ static inline unsigned add32_with_carry(unsigned a, unsigned b)
         return a;
 }
 
-#endif
+#endif /* ASM_X86__CHECKSUM_64_H */
diff --git a/include/asm-x86/cmpxchg_32.h b/include/asm-x86/cmpxchg_32.h
index bf5a69d1329e..0622e45cdf7c 100644
--- a/include/asm-x86/cmpxchg_32.h
+++ b/include/asm-x86/cmpxchg_32.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_CMPXCHG_H
-#define __ASM_CMPXCHG_H
+#ifndef ASM_X86__CMPXCHG_32_H
+#define ASM_X86__CMPXCHG_32_H
 
 #include <linux/bitops.h> /* for LOCK_PREFIX */
 
@@ -341,4 +341,4 @@ extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
 
 #endif
 
-#endif
+#endif /* ASM_X86__CMPXCHG_32_H */
diff --git a/include/asm-x86/cmpxchg_64.h b/include/asm-x86/cmpxchg_64.h
index d9b26b9a28cf..63c1a5e61b99 100644
--- a/include/asm-x86/cmpxchg_64.h
+++ b/include/asm-x86/cmpxchg_64.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_CMPXCHG_H
-#define __ASM_CMPXCHG_H
+#ifndef ASM_X86__CMPXCHG_64_H
+#define ASM_X86__CMPXCHG_64_H
 
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
@@ -93,6 +93,39 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
         return old;
 }
 
+/*
+ * Always use locked operations when touching memory shared with a
+ * hypervisor, since the system may be SMP even if the guest kernel
+ * isn't.
+ */
+static inline unsigned long __sync_cmpxchg(volatile void *ptr,
+                                           unsigned long old,
+                                           unsigned long new, int size)
+{
+        unsigned long prev;
+        switch (size) {
+        case 1:
+                asm volatile("lock; cmpxchgb %b1,%2"
+                             : "=a"(prev)
+                             : "q"(new), "m"(*__xg(ptr)), "0"(old)
+                             : "memory");
+                return prev;
+        case 2:
+                asm volatile("lock; cmpxchgw %w1,%2"
+                             : "=a"(prev)
+                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                             : "memory");
+                return prev;
+        case 4:
+                asm volatile("lock; cmpxchgl %1,%2"
+                             : "=a"(prev)
+                             : "r"(new), "m"(*__xg(ptr)), "0"(old)
+                             : "memory");
+                return prev;
+        }
+        return old;
+}
+
 static inline unsigned long __cmpxchg_local(volatile void *ptr,
                                             unsigned long old,
                                             unsigned long new, int size)
@@ -139,10 +172,14 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
         ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \
                                              (unsigned long)(n),        \
                                              sizeof(*(ptr))))
+#define sync_cmpxchg(ptr, o, n)                                         \
+        ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),  \
+                                            (unsigned long)(n),         \
+                                            sizeof(*(ptr))))
 #define cmpxchg64_local(ptr, o, n)                                      \
 ({                                                                      \
         BUILD_BUG_ON(sizeof(*(ptr)) != 8);                              \
         cmpxchg_local((ptr), (o), (n));                                 \
 })
 
-#endif
+#endif /* ASM_X86__CMPXCHG_64_H */
diff --git a/include/asm-x86/compat.h b/include/asm-x86/compat.h
index 1793ac317a30..6732b150949e 100644
--- a/include/asm-x86/compat.h
+++ b/include/asm-x86/compat.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_COMPAT_H
-#define _ASM_X86_64_COMPAT_H
+#ifndef ASM_X86__COMPAT_H
+#define ASM_X86__COMPAT_H
 
 /*
  * Architecture specific compatibility types
@@ -215,4 +215,4 @@ static inline int is_compat_task(void)
         return current_thread_info()->status & TS_COMPAT;
 }
 
-#endif /* _ASM_X86_64_COMPAT_H */
+#endif /* ASM_X86__COMPAT_H */
diff --git a/include/asm-x86/cpu.h b/include/asm-x86/cpu.h
index 73f2ea84fd74..83a115083f0d 100644
--- a/include/asm-x86/cpu.h
+++ b/include/asm-x86/cpu.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_I386_CPU_H_
-#define _ASM_I386_CPU_H_
+#ifndef ASM_X86__CPU_H
+#define ASM_X86__CPU_H
 
 #include <linux/device.h>
 #include <linux/cpu.h>
@@ -17,4 +17,4 @@ extern void arch_unregister_cpu(int);
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
-#endif /* _ASM_I386_CPU_H_ */
+#endif /* ASM_X86__CPU_H */
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index 0d609c837a41..adfeae6586e1 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -1,12 +1,18 @@
 /*
  * Defines x86 CPU feature bits
  */
-#ifndef _ASM_X86_CPUFEATURE_H
-#define _ASM_X86_CPUFEATURE_H
+#ifndef ASM_X86__CPUFEATURE_H
+#define ASM_X86__CPUFEATURE_H
 
 #include <asm/required-features.h>
 
-#define NCAPINTS        8       /* N 32-bit words worth of info */
+#define NCAPINTS        9       /* N 32-bit words worth of info */
+
+/*
+ * Note: If the comment begins with a quoted string, that string is used
+ * in /proc/cpuinfo instead of the macro name.  If the string is "",
+ * this feature bit is not displayed in /proc/cpuinfo at all.
+ */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
 #define X86_FEATURE_FPU         (0*32+ 0) /* Onboard FPU */
@@ -14,7 +20,7 @@
 #define X86_FEATURE_DE          (0*32+ 2) /* Debugging Extensions */
 #define X86_FEATURE_PSE         (0*32+ 3) /* Page Size Extensions */
 #define X86_FEATURE_TSC         (0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR         (0*32+ 5) /* Model-Specific Registers, RDMSR, WRMSR */
+#define X86_FEATURE_MSR         (0*32+ 5) /* Model-Specific Registers */
 #define X86_FEATURE_PAE         (0*32+ 6) /* Physical Address Extensions */
 #define X86_FEATURE_MCE         (0*32+ 7) /* Machine Check Architecture */
 #define X86_FEATURE_CX8         (0*32+ 8) /* CMPXCHG8 instruction */
@@ -23,22 +29,23 @@
 #define X86_FEATURE_MTRR        (0*32+12) /* Memory Type Range Registers */
 #define X86_FEATURE_PGE         (0*32+13) /* Page Global Enable */
 #define X86_FEATURE_MCA         (0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV        (0*32+15) /* CMOV instruction (FCMOVCC and FCOMI too if FPU present) */
+#define X86_FEATURE_CMOV        (0*32+15) /* CMOV instructions */
+                                          /* (plus FCMOVcc, FCOMI with FPU) */
 #define X86_FEATURE_PAT         (0*32+16) /* Page Attribute Table */
 #define X86_FEATURE_PSE36       (0*32+17) /* 36-bit PSEs */
 #define X86_FEATURE_PN          (0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH      (0*32+19) /* Supports the CLFLUSH instruction */
-#define X86_FEATURE_DS          (0*32+21) /* Debug Store */
+#define X86_FEATURE_CLFLSH      (0*32+19) /* "clflush" CLFLUSH instruction */
+#define X86_FEATURE_DS          (0*32+21) /* "dts" Debug Store */
 #define X86_FEATURE_ACPI        (0*32+22) /* ACPI via MSR */
 #define X86_FEATURE_MMX         (0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR        (0*32+24) /* FXSAVE and FXRSTOR instructions (fast save and restore */
-                                          /* of FPU context), and CR4.OSFXSR available */
-#define X86_FEATURE_XMM         (0*32+25) /* Streaming SIMD Extensions */
-#define X86_FEATURE_XMM2        (0*32+26) /* Streaming SIMD Extensions-2 */
-#define X86_FEATURE_SELFSNOOP   (0*32+27) /* CPU self snoop */
+#define X86_FEATURE_FXSR        (0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM         (0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2        (0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP   (0*32+27) /* "ss" CPU self snoop */
 #define X86_FEATURE_HT          (0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC         (0*32+29) /* Automatic clock control */
+#define X86_FEATURE_ACC         (0*32+29) /* "tm" Automatic clock control */
 #define X86_FEATURE_IA64        (0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE         (0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
@@ -46,7 +53,8 @@
 #define X86_FEATURE_MP          (1*32+19) /* MP Capable. */
 #define X86_FEATURE_NX          (1*32+20) /* Execute Disable */
 #define X86_FEATURE_MMXEXT      (1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_GBPAGES     (1*32+26) /* GB pages */
+#define X86_FEATURE_FXSR_OPT    (1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES     (1*32+26) /* "pdpe1gb" GB pages */
 #define X86_FEATURE_RDTSCP      (1*32+27) /* RDTSCP */
 #define X86_FEATURE_LM          (1*32+29) /* Long Mode (x86-64) */
 #define X86_FEATURE_3DNOWEXT    (1*32+30) /* AMD 3DNow! extensions */
@@ -64,48 +72,79 @@
 #define X86_FEATURE_CYRIX_ARR   (3*32+ 2) /* Cyrix ARRs (= MTRRs) */
 #define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */
 /* cpu types for specific tunings: */
-#define X86_FEATURE_K8          (3*32+ 4) /* Opteron, Athlon64 */
-#define X86_FEATURE_K7          (3*32+ 5) /* Athlon */
-#define X86_FEATURE_P3          (3*32+ 6) /* P3 */
-#define X86_FEATURE_P4          (3*32+ 7) /* P4 */
+#define X86_FEATURE_K8          (3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7          (3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3          (3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4          (3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
 #define X86_FEATURE_UP          (3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS        (3*32+12)  /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS         (3*32+13)  /* Branch Trace Store */
-/* 14 free */
-/* 15 free */
-#define X86_FEATURE_REP_GOOD    (3*32+16) /* rep microcode works well on this CPU */
-#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* Lfence synchronizes RDTSC */
+#define X86_FEATURE_NOPL        (3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_PEBS        (3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS         (3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32   (3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32  (3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD    (3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
+#define X86_FEATURE_11AP        (3*32+19) /* "" Bad local APIC aka 11AP */
+#define X86_FEATURE_NOPL        (3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_AMDC1E      (3*32+21) /* AMD C1E detected */
+#define X86_FEATURE_XTOPOLOGY   (3*32+21) /* cpu topology enum extensions */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3        (4*32+ 0) /* Streaming SIMD Extensions-3 */
-#define X86_FEATURE_MWAIT       (4*32+ 3) /* Monitor/Mwait support */
-#define X86_FEATURE_DSCPL       (4*32+ 4) /* CPL Qualified Debug Store */
+#define X86_FEATURE_XMM3        (4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ   (4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64      (4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT       (4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL       (4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX         (4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX         (4*32+ 6) /* Safer mode */
 #define X86_FEATURE_EST         (4*32+ 7) /* Enhanced SpeedStep */
 #define X86_FEATURE_TM2         (4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3       (4*32+ 9) /* Supplemental SSE-3 */
 #define X86_FEATURE_CID         (4*32+10) /* Context ID */
+#define X86_FEATURE_FMA         (4*32+12) /* Fused multiply-add */
 #define X86_FEATURE_CX16        (4*32+13) /* CMPXCHG16B */
 #define X86_FEATURE_XTPR        (4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM        (4*32+15) /* Performance Capabilities */
 #define X86_FEATURE_DCA         (4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1      (4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2      (4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC      (4*32+21) /* x2APIC */
+#define X86_FEATURE_AES         (4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE       (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE     (4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX         (4*32+28) /* Advanced Vector Extensions */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE      (5*32+ 2) /* on-CPU RNG present (xstore insn) */
-#define X86_FEATURE_XSTORE_EN   (5*32+ 3) /* on-CPU RNG enabled */
-#define X86_FEATURE_XCRYPT      (5*32+ 6) /* on-CPU crypto (xcrypt insn) */
-#define X86_FEATURE_XCRYPT_EN   (5*32+ 7) /* on-CPU crypto enabled */
+#define X86_FEATURE_XSTORE      (5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN   (5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT      (5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN   (5*32+ 7) /* "ace_en" on-CPU crypto enabled */
 #define X86_FEATURE_ACE2        (5*32+ 8) /* Advanced Cryptography Engine v2 */
 #define X86_FEATURE_ACE2_EN     (5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE         (5*32+ 10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN      (5*32+ 11) /* PHE enabled */
-#define X86_FEATURE_PMM         (5*32+ 12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN      (5*32+ 13) /* PMM enabled */
+#define X86_FEATURE_PHE         (5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN      (5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM         (5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN      (5*32+13) /* PMM enabled */
 
 /* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
 #define X86_FEATURE_LAHF_LM     (6*32+ 0) /* LAHF/SAHF in long mode */
 #define X86_FEATURE_CMP_LEGACY  (6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM         (6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC     (6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY  (6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM         (6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A       (6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW        (6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS         (6*32+10) /* Instruction Based Sampling */
+#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 */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -113,6 +152,13 @@
  */
 #define X86_FEATURE_IDA         (7*32+ 0) /* Intel Dynamic Acceleration */
 
+/* Virtualization flags: Linux defined */
+#define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        (8*32+ 1) /* Intel Virtual NMI */
+#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 */
+
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
 #include <linux/bitops.h>
@@ -142,11 +188,11 @@ extern const char * const x86_power_flags[32];
 #define clear_cpu_cap(c, bit)   clear_bit(bit, (unsigned long *)((c)->x86_capability))
 #define setup_clear_cpu_cap(bit) do { \
         clear_cpu_cap(&boot_cpu_data, bit);     \
-        set_bit(bit, cleared_cpu_caps);         \
+        set_bit(bit, (unsigned long *)cleared_cpu_caps); \
 } while (0)
 #define setup_force_cpu_cap(bit) do { \
         set_cpu_cap(&boot_cpu_data, bit);       \
-        clear_bit(bit, cleared_cpu_caps);       \
+        clear_bit(bit, (unsigned long *)cleared_cpu_caps);      \
 } while (0)
 
 #define cpu_has_fpu             boot_cpu_has(X86_FEATURE_FPU)
@@ -187,6 +233,10 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_gbpages         boot_cpu_has(X86_FEATURE_GBPAGES)
 #define cpu_has_arch_perfmon    boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
 #define cpu_has_pat             boot_cpu_has(X86_FEATURE_PAT)
+#define cpu_has_xmm4_1          boot_cpu_has(X86_FEATURE_XMM4_1)
+#define cpu_has_xmm4_2          boot_cpu_has(X86_FEATURE_XMM4_2)
+#define cpu_has_x2apic          boot_cpu_has(X86_FEATURE_X2APIC)
+#define cpu_has_xsave           boot_cpu_has(X86_FEATURE_XSAVE)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg         1
@@ -218,4 +268,4 @@ extern const char * const x86_power_flags[32];
 
 #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
 
-#endif /* _ASM_X86_CPUFEATURE_H */
+#endif /* ASM_X86__CPUFEATURE_H */
diff --git a/include/asm-x86/current.h b/include/asm-x86/current.h
index d2526d3f7346..a863ead856f3 100644
--- a/include/asm-x86/current.h
+++ b/include/asm-x86/current.h
@@ -1,5 +1,39 @@
+#ifndef ASM_X86__CURRENT_H
+#define ASM_X86__CURRENT_H
+
 #ifdef CONFIG_X86_32
-# include "current_32.h"
-#else
-# include "current_64.h"
-#endif
+#include <linux/compiler.h>
+#include <asm/percpu.h>
+
+struct task_struct;
+
+DECLARE_PER_CPU(struct task_struct *, current_task);
+static __always_inline struct task_struct *get_current(void)
+{
+        return x86_read_percpu(current_task);
+}
+
+#else /* X86_32 */
+
+#ifndef __ASSEMBLY__
+#include <asm/pda.h>
+
+struct task_struct;
+
+static __always_inline struct task_struct *get_current(void)
+{
+        return read_pda(pcurrent);
+}
+
+#else /* __ASSEMBLY__ */
+
+#include <asm/asm-offsets.h>
+#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* X86_32 */
+
+#define current get_current()
+
+#endif /* ASM_X86__CURRENT_H */
diff --git a/include/asm-x86/current_32.h b/include/asm-x86/current_32.h
deleted file mode 100644
index 5af9bdb97a16..000000000000
--- a/include/asm-x86/current_32.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _I386_CURRENT_H
-#define _I386_CURRENT_H
-
-#include <linux/compiler.h>
-#include <asm/percpu.h>
-
-struct task_struct;
-
-DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
-        return x86_read_percpu(current_task);
-}
-
-#define current get_current()
-
-#endif /* !(_I386_CURRENT_H) */
diff --git a/include/asm-x86/current_64.h b/include/asm-x86/current_64.h
deleted file mode 100644
index 2d368ede2fc1..000000000000
--- a/include/asm-x86/current_64.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef _X86_64_CURRENT_H
-#define _X86_64_CURRENT_H
-
-#if !defined(__ASSEMBLY__)
-struct task_struct;
-
-#include <asm/pda.h>
-
-static inline struct task_struct *get_current(void)
-{
-        struct task_struct *t = read_pda(pcurrent);
-        return t;
-}
-
-#define current get_current()
-
-#else
-
-#ifndef ASM_OFFSET_H
-#include <asm/asm-offsets.h>
-#endif
-
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
-
-#endif
-
-#endif /* !(_X86_64_CURRENT_H) */
diff --git a/include/asm-x86/debugreg.h b/include/asm-x86/debugreg.h
index c6344d572b03..ecb6907c3ea4 100644
--- a/include/asm-x86/debugreg.h
+++ b/include/asm-x86/debugreg.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DEBUGREG_H
-#define _ASM_X86_DEBUGREG_H
+#ifndef ASM_X86__DEBUGREG_H
+#define ASM_X86__DEBUGREG_H
 
 
 /* Indicate the register numbers for a number of the specific
@@ -67,4 +67,4 @@
 #define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
 #define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
 
-#endif
+#endif /* ASM_X86__DEBUGREG_H */
diff --git a/include/asm-x86/delay.h b/include/asm-x86/delay.h
index 409a649204aa..8a0da95b4fc5 100644
--- a/include/asm-x86/delay.h
+++ b/include/asm-x86/delay.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DELAY_H
-#define _ASM_X86_DELAY_H
+#ifndef ASM_X86__DELAY_H
+#define ASM_X86__DELAY_H
 
 /*
  * Copyright (C) 1993 Linus Torvalds
@@ -28,4 +28,4 @@ extern void __delay(unsigned long loops);
 
 void use_tsc_delay(void);
 
-#endif /* _ASM_X86_DELAY_H */
+#endif /* ASM_X86__DELAY_H */
diff --git a/include/asm-x86/desc.h b/include/asm-x86/desc.h
index 268a012bcd79..ebc307817e98 100644
--- a/include/asm-x86/desc.h
+++ b/include/asm-x86/desc.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_DESC_H_
-#define _ASM_DESC_H_
+#ifndef ASM_X86__DESC_H
+#define ASM_X86__DESC_H
 
 #ifndef __ASSEMBLY__
 #include <asm/desc_defs.h>
@@ -24,16 +24,27 @@ static inline void fill_ldt(struct desc_struct *desc,
         desc->d = info->seg_32bit;
         desc->g = info->limit_in_pages;
         desc->base2 = (info->base_addr & 0xff000000) >> 24;
+        /*
+         * Don't allow setting of the lm bit. It is useless anyway
+         * because 64bit system calls require __USER_CS:
+         */
+        desc->l = 0;
 }
 
 extern struct desc_ptr idt_descr;
 extern gate_desc idt_table[];
 
+struct gdt_page {
+        struct desc_struct gdt[GDT_ENTRIES];
+} __attribute__((aligned(PAGE_SIZE)));
+DECLARE_PER_CPU(struct gdt_page, gdt_page);
+
+static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
+{
+        return per_cpu(gdt_page, cpu).gdt;
+}
+
 #ifdef CONFIG_X86_64
-extern struct desc_struct cpu_gdt_table[GDT_ENTRIES];
-extern struct desc_ptr cpu_gdt_descr[];
-/* the cpu gdt accessor */
-#define get_cpu_gdt_table(x) ((struct desc_struct *)cpu_gdt_descr[x].address)
 
 static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
                              unsigned dpl, unsigned ist, unsigned seg)
@@ -51,16 +62,6 @@ static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
 }
 
 #else
-struct gdt_page {
-        struct desc_struct gdt[GDT_ENTRIES];
-} __attribute__((aligned(PAGE_SIZE)));
-DECLARE_PER_CPU(struct gdt_page, gdt_page);
-
-static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
-{
-        return per_cpu(gdt_page, cpu).gdt;
-}
-
 static inline void pack_gate(gate_desc *gate, unsigned char type,
                              unsigned long base, unsigned dpl, unsigned flags,
                              unsigned short seg)
@@ -101,7 +102,15 @@ static inline int desc_empty(const void *ptr)
         native_write_gdt_entry(dt, entry, desc, type)
 #define write_idt_entry(dt, entry, g)           \
         native_write_idt_entry(dt, entry, g)
-#endif
+
+static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
+{
+}
+
+static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
+{
+}
+#endif  /* CONFIG_PARAVIRT */
 
 static inline void native_write_idt_entry(gate_desc *idt, int entry,
                                           const gate_desc *gate)
@@ -192,8 +201,8 @@ static inline void native_set_ldt(const void *addr, unsigned int entries)
                 unsigned cpu = smp_processor_id();
                 ldt_desc ldt;
 
-                set_tssldt_descriptor(&ldt, (unsigned long)addr,
-                                      DESC_LDT, entries * sizeof(ldt) - 1);
+                set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT,
+                                      entries * LDT_ENTRY_SIZE - 1);
                 write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT,
                                 &ldt, DESC_LDT);
                 asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8));
@@ -311,6 +320,28 @@ static inline void set_intr_gate(unsigned int n, void *addr)
         _set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS);
 }
 
+#define SYS_VECTOR_FREE         0
+#define SYS_VECTOR_ALLOCED      1
+
+extern int first_system_vector;
+extern char system_vectors[];
+
+static inline void alloc_system_vector(int vector)
+{
+        if (system_vectors[vector] == SYS_VECTOR_FREE) {
+                system_vectors[vector] = SYS_VECTOR_ALLOCED;
+                if (first_system_vector > vector)
+                        first_system_vector = vector;
+        } else
+                BUG();
+}
+
+static inline void alloc_intr_gate(unsigned int n, void *addr)
+{
+        alloc_system_vector(n);
+        set_intr_gate(n, addr);
+}
+
 /*
  * This routine sets up an interrupt gate at directory privilege level 3.
  */
@@ -379,4 +410,4 @@ static inline void set_system_gate_ist(int n, void *addr, unsigned ist)
 
 #endif /* __ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__DESC_H */
diff --git a/include/asm-x86/desc_defs.h b/include/asm-x86/desc_defs.h
index eccb4ea1f918..b881db664b46 100644
--- a/include/asm-x86/desc_defs.h
+++ b/include/asm-x86/desc_defs.h
@@ -1,6 +1,6 @@
 /* Written 2000 by Andi Kleen */
-#ifndef __ARCH_DESC_DEFS_H
-#define __ARCH_DESC_DEFS_H
+#ifndef ASM_X86__DESC_DEFS_H
+#define ASM_X86__DESC_DEFS_H
 
 /*
  * Segment descriptor structure definitions, usable from both x86_64 and i386
@@ -75,10 +75,14 @@ struct ldttss_desc64 {
 typedef struct gate_struct64 gate_desc;
 typedef struct ldttss_desc64 ldt_desc;
 typedef struct ldttss_desc64 tss_desc;
+#define gate_offset(g) ((g).offset_low | ((unsigned long)(g).offset_middle << 16) | ((unsigned long)(g).offset_high << 32))
+#define gate_segment(g) ((g).segment)
 #else
 typedef struct desc_struct gate_desc;
 typedef struct desc_struct ldt_desc;
 typedef struct desc_struct tss_desc;
+#define gate_offset(g)          (((g).b & 0xffff0000) | ((g).a & 0x0000ffff))
+#define gate_segment(g)         ((g).a >> 16)
 #endif
 
 struct desc_ptr {
@@ -88,4 +92,4 @@ struct desc_ptr {
 
 #endif /* !__ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__DESC_DEFS_H */
diff --git a/include/asm-x86/device.h b/include/asm-x86/device.h
index 87a715367a1b..1bece04c7d9d 100644
--- a/include/asm-x86/device.h
+++ b/include/asm-x86/device.h
@@ -1,13 +1,16 @@
-#ifndef _ASM_X86_DEVICE_H
-#define _ASM_X86_DEVICE_H
+#ifndef ASM_X86__DEVICE_H
+#define ASM_X86__DEVICE_H
 
 struct dev_archdata {
 #ifdef CONFIG_ACPI
         void    *acpi_handle;
 #endif
+#ifdef CONFIG_X86_64
+struct dma_mapping_ops *dma_ops;
+#endif
 #ifdef CONFIG_DMAR
         void *iommu; /* hook for IOMMU specific extension */
 #endif
 };
 
-#endif /* _ASM_X86_DEVICE_H */
+#endif /* ASM_X86__DEVICE_H */
diff --git a/include/asm-x86/div64.h b/include/asm-x86/div64.h
index 9a2d644c08ef..f9530f23f1d6 100644
--- a/include/asm-x86/div64.h
+++ b/include/asm-x86/div64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DIV64_H
-#define _ASM_X86_DIV64_H
+#ifndef ASM_X86__DIV64_H
+#define ASM_X86__DIV64_H
 
 #ifdef CONFIG_X86_32
 
@@ -57,4 +57,4 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 # include <asm-generic/div64.h>
 #endif /* CONFIG_X86_32 */
 
-#endif /* _ASM_X86_DIV64_H */
+#endif /* ASM_X86__DIV64_H */
diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
index a1a4dc7fe6ec..219c33d6361c 100644
--- a/include/asm-x86/dma-mapping.h
+++ b/include/asm-x86/dma-mapping.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_DMA_MAPPING_H_
-#define _ASM_DMA_MAPPING_H_
+#ifndef ASM_X86__DMA_MAPPING_H
+#define ASM_X86__DMA_MAPPING_H
 
 /*
  * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for
@@ -9,25 +9,22 @@
 #include <linux/scatterlist.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
+#include <asm-generic/dma-coherent.h>
 
 extern dma_addr_t bad_dma_address;
 extern int iommu_merge;
-extern struct device fallback_dev;
+extern struct device x86_dma_fallback_dev;
 extern int panic_on_overflow;
-extern int forbid_dac;
-extern int force_iommu;
 
 struct dma_mapping_ops {
-        int             (*mapping_error)(dma_addr_t dma_addr);
+        int             (*mapping_error)(struct device *dev,
+                                         dma_addr_t dma_addr);
         void*           (*alloc_coherent)(struct device *dev, size_t size,
                                 dma_addr_t *dma_handle, gfp_t gfp);
         void            (*free_coherent)(struct device *dev, size_t size,
                                 void *vaddr, dma_addr_t dma_handle);
         dma_addr_t      (*map_single)(struct device *hwdev, phys_addr_t ptr,
                                 size_t size, int direction);
-        /* like map_single, but doesn't check the device mask */
-        dma_addr_t      (*map_simple)(struct device *hwdev, phys_addr_t ptr,
-                                size_t size, int direction);
         void            (*unmap_single)(struct device *dev, dma_addr_t addr,
                                 size_t size, int direction);
         void            (*sync_single_for_cpu)(struct device *hwdev,
@@ -57,71 +54,95 @@ struct dma_mapping_ops {
         int             is_phys;
 };
 
-extern const struct dma_mapping_ops *dma_ops;
+extern struct dma_mapping_ops *dma_ops;
 
-static inline int dma_mapping_error(dma_addr_t dma_addr)
+static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 {
-        if (dma_ops->mapping_error)
-                return dma_ops->mapping_error(dma_addr);
+#ifdef CONFIG_X86_32
+        return dma_ops;
+#else
+        if (unlikely(!dev) || !dev->archdata.dma_ops)
+                return dma_ops;
+        else
+                return dev->archdata.dma_ops;
+#endif /* ASM_X86__DMA_MAPPING_H */
+}
+
+/* Make sure we keep the same behaviour */
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+#ifdef CONFIG_X86_32
+        return 0;
+#else
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+        if (ops->mapping_error)
+                return ops->mapping_error(dev, dma_addr);
 
         return (dma_addr == bad_dma_address);
+#endif
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-                           dma_addr_t *dma_handle, gfp_t flag);
-
-void dma_free_coherent(struct device *dev, size_t size,
-                         void *vaddr, dma_addr_t dma_handle);
-
+#define dma_is_consistent(d, h) (1)
 
 extern int dma_supported(struct device *hwdev, u64 mask);
 extern int dma_set_mask(struct device *dev, u64 mask);
 
+extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
+                                        dma_addr_t *dma_addr, gfp_t flag);
+
 static inline dma_addr_t
 dma_map_single(struct device *hwdev, void *ptr, size_t size,
                int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        return dma_ops->map_single(hwdev, virt_to_phys(ptr), size, direction);
+        return ops->map_single(hwdev, virt_to_phys(ptr), size, direction);
 }
 
 static inline void
 dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size,
                  int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->unmap_single)
-                dma_ops->unmap_single(dev, addr, size, direction);
+        if (ops->unmap_single)
+                ops->unmap_single(dev, addr, size, direction);
 }
 
 static inline int
 dma_map_sg(struct device *hwdev, struct scatterlist *sg,
            int nents, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        return dma_ops->map_sg(hwdev, sg, nents, direction);
+        return ops->map_sg(hwdev, sg, nents, direction);
 }
 
 static inline void
 dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
              int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->unmap_sg)
-                dma_ops->unmap_sg(hwdev, sg, nents, direction);
+        if (ops->unmap_sg)
+                ops->unmap_sg(hwdev, sg, nents, direction);
 }
 
 static inline void
 dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
                         size_t size, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_single_for_cpu)
-                dma_ops->sync_single_for_cpu(hwdev, dma_handle, size,
-                                             direction);
+        if (ops->sync_single_for_cpu)
+                ops->sync_single_for_cpu(hwdev, dma_handle, size, direction);
         flush_write_buffers();
 }
 
@@ -129,10 +150,11 @@ static inline void
 dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
                            size_t size, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_single_for_device)
-                dma_ops->sync_single_for_device(hwdev, dma_handle, size,
-                                                direction);
+        if (ops->sync_single_for_device)
+                ops->sync_single_for_device(hwdev, dma_handle, size, direction);
         flush_write_buffers();
 }
 
@@ -140,11 +162,12 @@ static inline void
 dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
                               unsigned long offset, size_t size, int direction)
 {
-        BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_single_range_for_cpu)
-                dma_ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
-                                                   size, direction);
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
 
+        BUG_ON(!valid_dma_direction(direction));
+        if (ops->sync_single_range_for_cpu)
+                ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
+                                               size, direction);
         flush_write_buffers();
 }
 
@@ -153,11 +176,12 @@ dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
                                  unsigned long offset, size_t size,
                                  int direction)
 {
-        BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_single_range_for_device)
-                dma_ops->sync_single_range_for_device(hwdev, dma_handle,
-                                                      offset, size, direction);
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
 
+        BUG_ON(!valid_dma_direction(direction));
+        if (ops->sync_single_range_for_device)
+                ops->sync_single_range_for_device(hwdev, dma_handle,
+                                                  offset, size, direction);
         flush_write_buffers();
 }
 
@@ -165,9 +189,11 @@ static inline void
 dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
                     int nelems, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_sg_for_cpu)
-                dma_ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
+        if (ops->sync_sg_for_cpu)
+                ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
         flush_write_buffers();
 }
 
@@ -175,9 +201,11 @@ static inline void
 dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
                        int nelems, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_sg_for_device)
-                dma_ops->sync_sg_for_device(hwdev, sg, nelems, direction);
+        if (ops->sync_sg_for_device)
+                ops->sync_sg_for_device(hwdev, sg, nelems, direction);
 
         flush_write_buffers();
 }
@@ -186,9 +214,11 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
                                       size_t offset, size_t size,
                                       int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+
         BUG_ON(!valid_dma_direction(direction));
-        return dma_ops->map_single(dev, page_to_phys(page)+offset,
-                                   size, direction);
+        return ops->map_single(dev, page_to_phys(page) + offset,
+                               size, direction);
 }
 
 static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
@@ -211,27 +241,68 @@ static inline int dma_get_cache_alignment(void)
         return boot_cpu_data.x86_clflush_size;
 }
 
-#define dma_is_consistent(d, h) (1)
+static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
+                                                    gfp_t gfp)
+{
+        unsigned long dma_mask = 0;
 
-#ifdef CONFIG_X86_32
-#  define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
-struct dma_coherent_mem {
-        void            *virt_base;
-        u32             device_base;
-        int             size;
-        int             flags;
-        unsigned long   *bitmap;
-};
+        dma_mask = dev->coherent_dma_mask;
+        if (!dma_mask)
+                dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
+
+        return dma_mask;
+}
+
+static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
+{
+#ifdef CONFIG_X86_64
+        unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
+
+        if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+                gfp |= GFP_DMA32;
+#endif
+       return gfp;
+}
+
+static inline void *
+dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+                gfp_t gfp)
+{
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+        void *memory;
+
+        gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+
+        if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+                return memory;
+
+        if (!dev) {
+                dev = &x86_dma_fallback_dev;
+                gfp |= GFP_DMA;
+        }
+
+        if (!is_device_dma_capable(dev))
+                return NULL;
+
+        if (!ops->alloc_coherent)
+                return NULL;
 
-extern int
-dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
-                            dma_addr_t device_addr, size_t size, int flags);
+        return ops->alloc_coherent(dev, size, dma_handle,
+                                   dma_alloc_coherent_gfp_flags(dev, gfp));
+}
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+                                     void *vaddr, dma_addr_t bus)
+{
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
 
-extern void
-dma_release_declared_memory(struct device *dev);
+        WARN_ON(irqs_disabled());       /* for portability */
+
+        if (dma_release_from_coherent(dev, get_order(size), vaddr))
+                return;
+
+        if (ops->free_coherent)
+                ops->free_coherent(dev, size, vaddr, bus);
+}
 
-extern void *
-dma_mark_declared_memory_occupied(struct device *dev,
-                                  dma_addr_t device_addr, size_t size);
-#endif /* CONFIG_X86_32 */
 #endif
diff --git a/include/asm-x86/dma.h b/include/asm-x86/dma.h
index ca1098a7e580..c9f7a4eec555 100644
--- a/include/asm-x86/dma.h
+++ b/include/asm-x86/dma.h
@@ -5,8 +5,8 @@
  * and John Boyd, Nov. 1992.
  */
 
-#ifndef _ASM_X86_DMA_H
-#define _ASM_X86_DMA_H
+#ifndef ASM_X86__DMA_H
+#define ASM_X86__DMA_H
 
 #include <linux/spinlock.h>     /* And spinlocks */
 #include <asm/io.h>             /* need byte IO */
@@ -315,4 +315,4 @@ extern int isa_dma_bridge_buggy;
 #define isa_dma_bridge_buggy    (0)
 #endif
 
-#endif /* _ASM_X86_DMA_H */
+#endif /* ASM_X86__DMA_H */
diff --git a/include/asm-x86/dmi.h b/include/asm-x86/dmi.h
index 4edf7514a750..1cff6fe81fa5 100644
--- a/include/asm-x86/dmi.h
+++ b/include/asm-x86/dmi.h
@@ -1,14 +1,8 @@
-#ifndef _ASM_X86_DMI_H
-#define _ASM_X86_DMI_H
+#ifndef ASM_X86__DMI_H
+#define ASM_X86__DMI_H
 
 #include <asm/io.h>
 
-#ifdef CONFIG_X86_32
-
-#define dmi_alloc alloc_bootmem
-
-#else /* CONFIG_X86_32 */
-
 #define DMI_MAX_DATA 2048
 
 extern int dmi_alloc_index;
@@ -25,10 +19,8 @@ static inline void *dmi_alloc(unsigned len)
         return dmi_alloc_data + idx;
 }
 
-#endif
-
 /* Use early IO mappings for DMI because it's initialized early */
 #define dmi_ioremap early_ioremap
 #define dmi_iounmap early_iounmap
 
-#endif
+#endif /* ASM_X86__DMI_H */
diff --git a/include/asm-x86/ds.h b/include/asm-x86/ds.h
index 7881368142fa..c3c953a45b21 100644
--- a/include/asm-x86/ds.h
+++ b/include/asm-x86/ds.h
@@ -2,71 +2,237 @@
  * Debug Store (DS) support
  *
  * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for last branch recording (LBR) and
+ * feature that is used for branch trace store (BTS) and
  * precise-event based sampling (PEBS).
  *
- * Different architectures use a different DS layout/pointer size.
- * The below functions therefore work on a void*.
+ * It manages:
+ * - per-thread and per-cpu allocation of BTS and PEBS
+ * - buffer memory allocation (optional)
+ * - buffer overflow handling
+ * - buffer access
  *
+ * It assumes:
+ * - get_task_struct on all parameter tasks
+ * - current is allowed to trace parameter tasks
  *
- * Since there is no user for PEBS, yet, only LBR (or branch
- * trace store, BTS) is supported.
  *
- *
- * Copyright (C) 2007 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, Dec 2007
+ * Copyright (C) 2007-2008 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
  */
 
-#ifndef _ASM_X86_DS_H
-#define _ASM_X86_DS_H
+#ifndef ASM_X86__DS_H
+#define ASM_X86__DS_H
+
+#ifdef CONFIG_X86_DS
 
 #include <linux/types.h>
 #include <linux/init.h>
 
-struct cpuinfo_x86;
 
+struct task_struct;
 
-/* a branch trace record entry
+/*
+ * Request BTS or PEBS
+ *
+ * Due to alignement constraints, the actual buffer may be slightly
+ * smaller than the requested or provided buffer.
  *
- * In order to unify the interface between various processor versions,
- * we use the below data structure for all processors.
+ * Returns 0 on success; -Eerrno otherwise
+ *
+ * task: the task to request recording for;
+ *       NULL for per-cpu recording on the current cpu
+ * base: the base pointer for the (non-pageable) buffer;
+ *       NULL if buffer allocation requested
+ * size: the size of the requested or provided buffer
+ * ovfl: pointer to a function to be called on buffer overflow;
+ *       NULL if cyclic buffer requested
  */
-enum bts_qualifier {
-        BTS_INVALID = 0,
-        BTS_BRANCH,
-        BTS_TASK_ARRIVES,
-        BTS_TASK_DEPARTS
-};
+typedef void (*ds_ovfl_callback_t)(struct task_struct *);
+extern int ds_request_bts(struct task_struct *task, void *base, size_t size,
+                          ds_ovfl_callback_t ovfl);
+extern int ds_request_pebs(struct task_struct *task, void *base, size_t size,
+                           ds_ovfl_callback_t ovfl);
 
-struct bts_struct {
-        u64 qualifier;
-        union {
-                /* BTS_BRANCH */
-                struct {
-                        u64 from_ip;
-                        u64 to_ip;
-                } lbr;
-                /* BTS_TASK_ARRIVES or
-                   BTS_TASK_DEPARTS */
-                u64 jiffies;
-        } variant;
+/*
+ * Release BTS or PEBS resources
+ *
+ * Frees buffers allocated on ds_request.
+ *
+ * Returns 0 on success; -Eerrno otherwise
+ *
+ * task: the task to release resources for;
+ *       NULL to release resources for the current cpu
+ */
+extern int ds_release_bts(struct task_struct *task);
+extern int ds_release_pebs(struct task_struct *task);
+
+/*
+ * Return the (array) index of the write pointer.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * Returns -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * pos (out): if not NULL, will hold the result
+ */
+extern int ds_get_bts_index(struct task_struct *task, size_t *pos);
+extern int ds_get_pebs_index(struct task_struct *task, size_t *pos);
+
+/*
+ * Return the (array) index one record beyond the end of the array.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * Returns -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * pos (out): if not NULL, will hold the result
+ */
+extern int ds_get_bts_end(struct task_struct *task, size_t *pos);
+extern int ds_get_pebs_end(struct task_struct *task, size_t *pos);
+
+/*
+ * Provide a pointer to the BTS/PEBS record at parameter index.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * The pointer points directly into the buffer. The user is
+ * responsible for copying the record.
+ *
+ * Returns the size of a single record on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * index: the index of the requested record
+ * record (out): pointer to the requested record
+ */
+extern int ds_access_bts(struct task_struct *task,
+                         size_t index, const void **record);
+extern int ds_access_pebs(struct task_struct *task,
+                          size_t index, const void **record);
+
+/*
+ * Write one or more BTS/PEBS records at the write pointer index and
+ * advance the write pointer.
+ *
+ * If size is not a multiple of the record size, trailing bytes are
+ * zeroed out.
+ *
+ * May result in one or more overflow notifications.
+ *
+ * If called during overflow handling, that is, with index >=
+ * interrupt threshold, the write will wrap around.
+ *
+ * An overflow notification is given if and when the interrupt
+ * threshold is reached during or after the write.
+ *
+ * Returns the number of bytes written or -Eerrno.
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * buffer: the buffer to write
+ * size: the size of the buffer
+ */
+extern int ds_write_bts(struct task_struct *task,
+                        const void *buffer, size_t size);
+extern int ds_write_pebs(struct task_struct *task,
+                         const void *buffer, size_t size);
+
+/*
+ * Same as ds_write_bts/pebs, but omit ownership checks.
+ *
+ * This is needed to have some other task than the owner of the
+ * BTS/PEBS buffer or the parameter task itself write into the
+ * respective buffer.
+ */
+extern int ds_unchecked_write_bts(struct task_struct *task,
+                                  const void *buffer, size_t size);
+extern int ds_unchecked_write_pebs(struct task_struct *task,
+                                   const void *buffer, size_t size);
+
+/*
+ * Reset the write pointer of the BTS/PEBS buffer.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ */
+extern int ds_reset_bts(struct task_struct *task);
+extern int ds_reset_pebs(struct task_struct *task);
+
+/*
+ * Clear the BTS/PEBS buffer and reset the write pointer.
+ * The entire buffer will be zeroed out.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ */
+extern int ds_clear_bts(struct task_struct *task);
+extern int ds_clear_pebs(struct task_struct *task);
+
+/*
+ * Provide the PEBS counter reset value.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * value (out): the counter reset value
+ */
+extern int ds_get_pebs_reset(struct task_struct *task, u64 *value);
+
+/*
+ * Set the PEBS counter reset value.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * value: the new counter reset value
+ */
+extern int ds_set_pebs_reset(struct task_struct *task, u64 value);
+
+/*
+ * Initialization
+ */
+struct cpuinfo_x86;
+extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
+
+
+
+/*
+ * The DS context - part of struct thread_struct.
+ */
+struct ds_context {
+        /* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
+        unsigned char *ds;
+        /* the owner of the BTS and PEBS configuration, respectively */
+        struct task_struct *owner[2];
+        /* buffer overflow notification function for BTS and PEBS */
+        ds_ovfl_callback_t callback[2];
+        /* the original buffer address */
+        void *buffer[2];
+        /* the number of allocated pages for on-request allocated buffers */
+        unsigned int pages[2];
+        /* use count */
+        unsigned long count;
+        /* a pointer to the context location inside the thread_struct
+         * or the per_cpu context array */
+        struct ds_context **this;
+        /* a pointer to the task owning this context, or NULL, if the
+         * context is owned by a cpu */
+        struct task_struct *task;
 };
 
-/* Overflow handling mechanisms */
-#define DS_O_SIGNAL     1 /* send overflow signal */
-#define DS_O_WRAP       2 /* wrap around */
-
-extern int ds_allocate(void **, size_t);
-extern int ds_free(void **);
-extern int ds_get_bts_size(void *);
-extern int ds_get_bts_end(void *);
-extern int ds_get_bts_index(void *);
-extern int ds_set_overflow(void *, int);
-extern int ds_get_overflow(void *);
-extern int ds_clear(void *);
-extern int ds_read_bts(void *, int, struct bts_struct *);
-extern int ds_write_bts(void *, const struct bts_struct *);
-extern unsigned long ds_debugctl_mask(void);
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *c);
-
-#endif /* _ASM_X86_DS_H */
+/* called by exit_thread() to free leftover contexts */
+extern void ds_free(struct ds_context *context);
+
+#else /* CONFIG_X86_DS */
+
+#define ds_init_intel(config) do {} while (0)
+
+#endif /* CONFIG_X86_DS */
+#endif /* ASM_X86__DS_H */
diff --git a/include/asm-x86/dwarf2.h b/include/asm-x86/dwarf2.h
index b3cbb0ccae18..21d1bc32ad7c 100644
--- a/include/asm-x86/dwarf2.h
+++ b/include/asm-x86/dwarf2.h
@@ -1,5 +1,61 @@
-#ifdef CONFIG_X86_32
-# include "dwarf2_32.h"
+#ifndef ASM_X86__DWARF2_H
+#define ASM_X86__DWARF2_H
+
+#ifndef __ASSEMBLY__
+#warning "asm/dwarf2.h should be only included in pure assembly files"
+#endif
+
+/*
+   Macros for dwarf2 CFI unwind table entries.
+   See "as.info" for details on these pseudo ops. Unfortunately
+   they are only supported in very new binutils, so define them
+   away for older version.
+ */
+
+#ifdef CONFIG_AS_CFI
+
+#define CFI_STARTPROC .cfi_startproc
+#define CFI_ENDPROC .cfi_endproc
+#define CFI_DEF_CFA .cfi_def_cfa
+#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
+#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
+#define CFI_OFFSET .cfi_offset
+#define CFI_REL_OFFSET .cfi_rel_offset
+#define CFI_REGISTER .cfi_register
+#define CFI_RESTORE .cfi_restore
+#define CFI_REMEMBER_STATE .cfi_remember_state
+#define CFI_RESTORE_STATE .cfi_restore_state
+#define CFI_UNDEFINED .cfi_undefined
+
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
+
 #else
-# include "dwarf2_64.h"
+
+/* Due to the structure of pre-exisiting code, don't use assembler line
+   comment character # to ignore the arguments. Instead, use a dummy macro. */
+.macro cfi_ignore a=0, b=0, c=0, d=0
+.endm
+
+#define CFI_STARTPROC   cfi_ignore
+#define CFI_ENDPROC     cfi_ignore
+#define CFI_DEF_CFA     cfi_ignore
+#define CFI_DEF_CFA_REGISTER    cfi_ignore
+#define CFI_DEF_CFA_OFFSET      cfi_ignore
+#define CFI_ADJUST_CFA_OFFSET   cfi_ignore
+#define CFI_OFFSET      cfi_ignore
+#define CFI_REL_OFFSET  cfi_ignore
+#define CFI_REGISTER    cfi_ignore
+#define CFI_RESTORE     cfi_ignore
+#define CFI_REMEMBER_STATE cfi_ignore
+#define CFI_RESTORE_STATE cfi_ignore
+#define CFI_UNDEFINED cfi_ignore
+#define CFI_SIGNAL_FRAME cfi_ignore
+
 #endif
+
+#endif /* ASM_X86__DWARF2_H */
diff --git a/include/asm-x86/dwarf2_32.h b/include/asm-x86/dwarf2_32.h
deleted file mode 100644
index 6d66398a307d..000000000000
--- a/include/asm-x86/dwarf2_32.h
+++ /dev/null
@@ -1,61 +0,0 @@
-#ifndef _DWARF2_H
-#define _DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
- */
-
-#ifdef CONFIG_UNWIND_INFO
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#else
-
-/* Due to the structure of pre-exisiting code, don't use assembler line
-   comment character # to ignore the arguments. Instead, use a dummy macro. */
-.macro ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC   ignore
-#define CFI_ENDPROC     ignore
-#define CFI_DEF_CFA     ignore
-#define CFI_DEF_CFA_REGISTER    ignore
-#define CFI_DEF_CFA_OFFSET      ignore
-#define CFI_ADJUST_CFA_OFFSET   ignore
-#define CFI_OFFSET      ignore
-#define CFI_REL_OFFSET  ignore
-#define CFI_REGISTER    ignore
-#define CFI_RESTORE     ignore
-#define CFI_REMEMBER_STATE ignore
-#define CFI_RESTORE_STATE ignore
-#define CFI_UNDEFINED ignore
-#define CFI_SIGNAL_FRAME ignore
-
-#endif
-
-#endif
diff --git a/include/asm-x86/dwarf2_64.h b/include/asm-x86/dwarf2_64.h
deleted file mode 100644
index c950519a264d..000000000000
--- a/include/asm-x86/dwarf2_64.h
+++ /dev/null
@@ -1,56 +0,0 @@
-#ifndef _DWARF2_H
-#define _DWARF2_H 1
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#else
-
-/* use assembler line comment character # to ignore the arguments. */
-#define CFI_STARTPROC   #
-#define CFI_ENDPROC     #
-#define CFI_DEF_CFA     #
-#define CFI_DEF_CFA_REGISTER    #
-#define CFI_DEF_CFA_OFFSET      #
-#define CFI_ADJUST_CFA_OFFSET   #
-#define CFI_OFFSET      #
-#define CFI_REL_OFFSET  #
-#define CFI_REGISTER    #
-#define CFI_RESTORE     #
-#define CFI_REMEMBER_STATE      #
-#define CFI_RESTORE_STATE       #
-#define CFI_UNDEFINED   #
-#define CFI_SIGNAL_FRAME        #
-
-#endif
-
-#endif
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
index 7004251fc66b..5abbdec06bd2 100644
--- a/include/asm-x86/e820.h
+++ b/include/asm-x86/e820.h
@@ -1,13 +1,52 @@
-#ifndef __ASM_E820_H
-#define __ASM_E820_H
+#ifndef ASM_X86__E820_H
+#define ASM_X86__E820_H
 #define E820MAP 0x2d0           /* our map */
 #define E820MAX 128             /* number of entries in E820MAP */
+
+/*
+ * Legacy E820 BIOS limits us to 128 (E820MAX) nodes due to the
+ * constrained space in the zeropage.  If we have more nodes than
+ * that, and if we've booted off EFI firmware, then the EFI tables
+ * passed us from the EFI firmware can list more nodes.  Size our
+ * internal memory map tables to have room for these additional
+ * nodes, based on up to three entries per node for which the
+ * kernel was built: MAX_NUMNODES == (1 << CONFIG_NODES_SHIFT),
+ * plus E820MAX, allowing space for the possible duplicate E820
+ * entries that might need room in the same arrays, prior to the
+ * call to sanitize_e820_map() to remove duplicates.  The allowance
+ * of three memory map entries per node is "enough" entries for
+ * the initial hardware platform motivating this mechanism to make
+ * use of additional EFI map entries.  Future platforms may want
+ * to allow more than three entries per node or otherwise refine
+ * this size.
+ */
+
+/*
+ * Odd: 'make headers_check' complains about numa.h if I try
+ * to collapse the next two #ifdef lines to a single line:
+ *      #if defined(__KERNEL__) && defined(CONFIG_EFI)
+ */
+#ifdef __KERNEL__
+#ifdef CONFIG_EFI
+#include <linux/numa.h>
+#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
+#else   /* ! CONFIG_EFI */
+#define E820_X_MAX E820MAX
+#endif
+#else   /* ! __KERNEL__ */
+#define E820_X_MAX E820MAX
+#endif
+
 #define E820NR  0x1e8           /* # entries in E820MAP */
 
 #define E820_RAM        1
 #define E820_RESERVED   2
 #define E820_ACPI       3
 #define E820_NVS        4
+#define E820_UNUSABLE   5
+
+/* reserved RAM used by kernel itself */
+#define E820_RESERVED_KERN        128
 
 #ifndef __ASSEMBLY__
 struct e820entry {
@@ -18,22 +57,90 @@ struct e820entry {
 
 struct e820map {
         __u32 nr_map;
-        struct e820entry map[E820MAX];
+        struct e820entry map[E820_X_MAX];
 };
+
+#ifdef __KERNEL__
+/* see comment in arch/x86/kernel/e820.c */
+extern struct e820map e820;
+extern struct e820map e820_saved;
+
+extern unsigned long pci_mem_start;
+extern int e820_any_mapped(u64 start, u64 end, unsigned type);
+extern int e820_all_mapped(u64 start, u64 end, unsigned type);
+extern void e820_add_region(u64 start, u64 size, int type);
+extern void e820_print_map(char *who);
+extern int
+sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map);
+extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
+                               unsigned new_type);
+extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
+                             int checktype);
+extern void update_e820(void);
+extern void e820_setup_gap(void);
+extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
+                        unsigned long start_addr, unsigned long long end_addr);
+struct setup_data;
+extern void parse_e820_ext(struct setup_data *data, unsigned long pa_data);
+
+#if defined(CONFIG_X86_64) || \
+        (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
+extern void e820_mark_nosave_regions(unsigned long limit_pfn);
+#else
+static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
+{
+}
+#endif
+
+#ifdef CONFIG_MEMTEST
+extern void early_memtest(unsigned long start, unsigned long end);
+#else
+static inline void early_memtest(unsigned long start, unsigned long end)
+{
+}
+#endif
+
+extern unsigned long end_user_pfn;
+
+extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
+extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
+extern void reserve_early(u64 start, u64 end, char *name);
+extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
+extern void free_early(u64 start, u64 end);
+extern void early_res_to_bootmem(u64 start, u64 end);
+extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+
+extern unsigned long e820_end_of_ram_pfn(void);
+extern unsigned long e820_end_of_low_ram_pfn(void);
+extern int e820_find_active_region(const struct e820entry *ei,
+                                  unsigned long start_pfn,
+                                  unsigned long last_pfn,
+                                  unsigned long *ei_startpfn,
+                                  unsigned long *ei_endpfn);
+extern void e820_register_active_regions(int nid, unsigned long start_pfn,
+                                         unsigned long end_pfn);
+extern u64 e820_hole_size(u64 start, u64 end);
+extern void finish_e820_parsing(void);
+extern void e820_reserve_resources(void);
+extern void e820_reserve_resources_late(void);
+extern void setup_memory_map(void);
+extern char *default_machine_specific_memory_setup(void);
+extern char *machine_specific_memory_setup(void);
+extern char *memory_setup(void);
+#endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 
 #define ISA_START_ADDRESS       0xa0000
 #define ISA_END_ADDRESS         0x100000
+#define is_ISA_range(s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS)
 
 #define BIOS_BEGIN              0x000a0000
 #define BIOS_END                0x00100000
 
 #ifdef __KERNEL__
-#ifdef CONFIG_X86_32
-# include "e820_32.h"
-#else
-# include "e820_64.h"
-#endif
+#include <linux/ioport.h>
+
+#define HIGH_MEMORY     (1024*1024)
 #endif /* __KERNEL__ */
 
-#endif  /* __ASM_E820_H */
+#endif /* ASM_X86__E820_H */
diff --git a/include/asm-x86/e820_32.h b/include/asm-x86/e820_32.h
deleted file mode 100644
index a9f7c6ec32bf..000000000000
--- a/include/asm-x86/e820_32.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * structures and definitions for the int 15, ax=e820 memory map
- * scheme.
- *
- * In a nutshell, arch/i386/boot/setup.S populates a scratch table
- * in the empty_zero_block that contains a list of usable address/size
- * duples.   In arch/i386/kernel/setup.c, this information is
- * transferred into the e820map, and in arch/i386/mm/init.c, that
- * new information is used to mark pages reserved or not.
- *
- */
-#ifndef __E820_HEADER
-#define __E820_HEADER
-
-#include <linux/ioport.h>
-
-#define HIGH_MEMORY     (1024*1024)
-
-#ifndef __ASSEMBLY__
-
-extern struct e820map e820;
-extern void update_e820(void);
-
-extern int e820_all_mapped(unsigned long start, unsigned long end,
-                           unsigned type);
-extern int e820_any_mapped(u64 start, u64 end, unsigned type);
-extern void propagate_e820_map(void);
-extern void register_bootmem_low_pages(unsigned long max_low_pfn);
-extern void add_memory_region(unsigned long long start,
-                              unsigned long long size, int type);
-extern void update_memory_range(u64 start, u64 size, unsigned old_type,
-                                unsigned new_type);
-extern void e820_register_memory(void);
-extern void limit_regions(unsigned long long size);
-extern void print_memory_map(char *who);
-extern void init_iomem_resources(struct resource *code_resource,
-                                 struct resource *data_resource,
-                                 struct resource *bss_resource);
-
-#if defined(CONFIG_PM) && defined(CONFIG_HIBERNATION)
-extern void e820_mark_nosave_regions(void);
-#else
-static inline void e820_mark_nosave_regions(void)
-{
-}
-#endif
-
-
-#endif/*!__ASSEMBLY__*/
-#endif/*__E820_HEADER*/
diff --git a/include/asm-x86/e820_64.h b/include/asm-x86/e820_64.h
deleted file mode 100644
index 71c4d685d30d..000000000000
--- a/include/asm-x86/e820_64.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * structures and definitions for the int 15, ax=e820 memory map
- * scheme.
- *
- * In a nutshell, setup.S populates a scratch table in the
- * empty_zero_block that contains a list of usable address/size
- * duples.  setup.c, this information is transferred into the e820map,
- * and in init.c/numa.c, that new information is used to mark pages
- * reserved or not.
- */
-#ifndef __E820_HEADER
-#define __E820_HEADER
-
-#include <linux/ioport.h>
-
-#ifndef __ASSEMBLY__
-extern unsigned long find_e820_area(unsigned long start, unsigned long end,
-                                    unsigned long size, unsigned long align);
-extern unsigned long find_e820_area_size(unsigned long start,
-                                         unsigned long *sizep,
-                                         unsigned long align);
-extern void add_memory_region(unsigned long start, unsigned long size,
-                              int type);
-extern void update_memory_range(u64 start, u64 size, unsigned old_type,
-                                unsigned new_type);
-extern void setup_memory_region(void);
-extern void contig_e820_setup(void);
-extern unsigned long e820_end_of_ram(void);
-extern void e820_reserve_resources(void);
-extern void e820_mark_nosave_regions(void);
-extern int e820_any_mapped(unsigned long start, unsigned long end,
-                           unsigned type);
-extern int e820_all_mapped(unsigned long start, unsigned long end,
-                           unsigned type);
-extern int e820_any_non_reserved(unsigned long start, unsigned long end);
-extern int is_memory_any_valid(unsigned long start, unsigned long end);
-extern int e820_all_non_reserved(unsigned long start, unsigned long end);
-extern int is_memory_all_valid(unsigned long start, unsigned long end);
-extern unsigned long e820_hole_size(unsigned long start, unsigned long end);
-
-extern void e820_setup_gap(void);
-extern void e820_register_active_regions(int nid, unsigned long start_pfn,
-                                         unsigned long end_pfn);
-
-extern void finish_e820_parsing(void);
-
-extern struct e820map e820;
-extern void update_e820(void);
-
-extern void reserve_early(unsigned long start, unsigned long end, char *name);
-extern void free_early(unsigned long start, unsigned long end);
-extern void early_res_to_bootmem(unsigned long start, unsigned long end);
-
-#endif/*!__ASSEMBLY__*/
-
-#endif/*__E820_HEADER*/
diff --git a/include/asm-x86/edac.h b/include/asm-x86/edac.h
index a8088f63a30e..9493c5b27bbd 100644
--- a/include/asm-x86/edac.h
+++ b/include/asm-x86/edac.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_EDAC_H
-#define _ASM_X86_EDAC_H
+#ifndef ASM_X86__EDAC_H
+#define ASM_X86__EDAC_H
 
 /* ECC atomic, DMA, SMP and interrupt safe scrub function */
 
@@ -15,4 +15,4 @@ static inline void atomic_scrub(void *va, u32 size)
                 asm volatile("lock; addl $0, %0"::"m" (*virt_addr));
 }
 
-#endif
+#endif /* ASM_X86__EDAC_H */
diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h
index d53004b855cc..ed2de22e8705 100644
--- a/include/asm-x86/efi.h
+++ b/include/asm-x86/efi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_EFI_H
-#define _ASM_X86_EFI_H
+#ifndef ASM_X86__EFI_H
+#define ASM_X86__EFI_H
 
 #ifdef CONFIG_X86_32
 
@@ -86,12 +86,12 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
         efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
                   (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
-extern void *efi_ioremap(unsigned long addr, unsigned long size);
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
 
 #endif /* CONFIG_X86_32 */
 
-extern void efi_reserve_bootmem(void);
+extern void efi_reserve_early(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
-#endif
+#endif /* ASM_X86__EFI_H */
diff --git a/include/asm-x86/elf.h b/include/asm-x86/elf.h
index 8f232dc5b5fe..5c4745bec906 100644
--- a/include/asm-x86/elf.h
+++ b/include/asm-x86/elf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_ELF_H
-#define _ASM_X86_ELF_H
+#ifndef ASM_X86__ELF_H
+#define ASM_X86__ELF_H
 
 /*
  * ELF register definitions..
@@ -83,9 +83,9 @@ extern unsigned int vdso_enabled;
         (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
 
 #include <asm/processor.h>
+#include <asm/system.h>
 
 #ifdef CONFIG_X86_32
-#include <asm/system.h>         /* for savesegment */
 #include <asm/desc.h>
 
 #define elf_check_arch(x)       elf_check_arch_ia32(x)
@@ -148,8 +148,9 @@ do {						\
 
 static inline void start_ia32_thread(struct pt_regs *regs, u32 ip, u32 sp)
 {
-        asm volatile("movl %0,%%fs" :: "r" (0));
-        asm volatile("movl %0,%%es; movl %0,%%ds" : : "r" (__USER32_DS));
+        loadsegment(fs, 0);
+        loadsegment(ds, __USER32_DS);
+        loadsegment(es, __USER32_DS);
         load_gs_index(0);
         regs->ip = ip;
         regs->sp = sp;
@@ -332,4 +333,4 @@ extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
-#endif
+#endif /* ASM_X86__ELF_H */
diff --git a/include/asm-x86/emergency-restart.h b/include/asm-x86/emergency-restart.h
index 8e6aef19f8f0..190d0d8b71e3 100644
--- a/include/asm-x86/emergency-restart.h
+++ b/include/asm-x86/emergency-restart.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
+#ifndef ASM_X86__EMERGENCY_RESTART_H
+#define ASM_X86__EMERGENCY_RESTART_H
 
 enum reboot_type {
         BOOT_TRIPLE = 't',
@@ -15,4 +15,4 @@ extern enum reboot_type reboot_type;
 
 extern void machine_emergency_restart(void);
 
-#endif /* _ASM_EMERGENCY_RESTART_H */
+#endif /* ASM_X86__EMERGENCY_RESTART_H */
diff --git a/include/asm-x86/mach-es7000/mach_apic.h b/include/asm-x86/es7000/apic.h
index fbc8ad256f5a..bd2c44d1f7ac 100644
--- a/include/asm-x86/mach-es7000/mach_apic.h
+++ b/include/asm-x86/es7000/apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef __ASM_ES7000_APIC_H
+#define __ASM_ES7000_APIC_H
 
 #define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
 #define esr_disable (1)
@@ -10,7 +10,7 @@ static inline int apic_id_registered(void)
 }
 
 static inline cpumask_t target_cpus(void)
-{ 
+{
 #if defined CONFIG_ES7000_CLUSTERED_APIC
         return CPU_MASK_ALL;
 #else
@@ -23,24 +23,24 @@ static inline cpumask_t target_cpus(void)
 #define APIC_DFR_VALUE          (APIC_DFR_CLUSTER)
 #define INT_DELIVERY_MODE       (dest_LowestPrio)
 #define INT_DEST_MODE           (1)    /* logical delivery broadcast to all procs */
-#define NO_BALANCE_IRQ          (1)
+#define NO_BALANCE_IRQ          (1)
 #undef  WAKE_SECONDARY_VIA_INIT
 #define WAKE_SECONDARY_VIA_MIP
 #else
 #define APIC_DFR_VALUE          (APIC_DFR_FLAT)
 #define INT_DELIVERY_MODE       (dest_Fixed)
 #define INT_DEST_MODE           (0)    /* phys delivery to target procs */
-#define NO_BALANCE_IRQ          (0)
+#define NO_BALANCE_IRQ          (0)
 #undef  APIC_DEST_LOGICAL
 #define APIC_DEST_LOGICAL       0x0
 #define WAKE_SECONDARY_VIA_INIT
 #endif
 
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{ 
+{
         return 0;
-} 
-static inline unsigned long check_apicid_present(int bit) 
+}
+static inline unsigned long check_apicid_present(int bit)
 {
         return physid_isset(bit, phys_cpu_present_map);
 }
@@ -66,9 +66,9 @@ static inline void init_apic_ldr(void)
         unsigned long val;
         int cpu = smp_processor_id();
 
-        apic_write_around(APIC_DFR, APIC_DFR_VALUE);
+        apic_write(APIC_DFR, APIC_DFR_VALUE);
         val = calculate_ldr(cpu);
-        apic_write_around(APIC_LDR, val);
+        apic_write(APIC_LDR, val);
 }
 
 #ifndef CONFIG_X86_GENERICARCH
@@ -80,7 +80,7 @@ static inline void setup_apic_routing(void)
 {
         int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
         printk("Enabling APIC mode:  %s.  Using %d I/O APICs, target cpus %lx\n",
-                (apic_version[apic] == 0x14) ? 
+                (apic_version[apic] == 0x14) ?
                 "Physical Cluster" : "Logical Cluster", nr_ioapics, cpus_addr(TARGET_CPUS)[0]);
 }
 
@@ -141,7 +141,7 @@ static inline void setup_portio_remap(void)
 extern unsigned int boot_cpu_physical_apicid;
 static inline int check_phys_apicid_present(int cpu_physical_apicid)
 {
-        boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+        boot_cpu_physical_apicid = read_apic_id();
         return (1);
 }
 
@@ -150,7 +150,7 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
         int num_bits_set;
         int cpus_found = 0;
         int cpu;
-        int apicid;     
+        int apicid;
 
         num_bits_set = cpus_weight(cpumask);
         /* Return id to all */
@@ -160,16 +160,16 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
 #else
                 return cpu_to_logical_apicid(0);
 #endif
-        /* 
-         * The cpus in the mask must all be on the apic cluster.  If are not 
-         * on the same apicid cluster return default value of TARGET_CPUS. 
+        /*
+         * The cpus in the mask must all be on the apic cluster.  If are not
+         * on the same apicid cluster return default value of TARGET_CPUS.
          */
         cpu = first_cpu(cpumask);
         apicid = cpu_to_logical_apicid(cpu);
         while (cpus_found < num_bits_set) {
                 if (cpu_isset(cpu, cpumask)) {
                         int new_apicid = cpu_to_logical_apicid(cpu);
-                        if (apicid_cluster(apicid) != 
+                        if (apicid_cluster(apicid) !=
                                         apicid_cluster(new_apicid)){
                                 printk ("%s: Not a valid mask!\n",__FUNCTION__);
 #if defined CONFIG_ES7000_CLUSTERED_APIC
@@ -191,4 +191,4 @@ static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
         return cpuid_apic >> index_msb;
 }
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* __ASM_ES7000_APIC_H */
diff --git a/include/asm-x86/es7000/apicdef.h b/include/asm-x86/es7000/apicdef.h
new file mode 100644
index 000000000000..8b234a3cb851
--- /dev/null
+++ b/include/asm-x86/es7000/apicdef.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_ES7000_APICDEF_H
+#define __ASM_ES7000_APICDEF_H
+
+#define         APIC_ID_MASK            (0xFF<<24)
+
+static inline unsigned get_apic_id(unsigned long x)
+{
+        return (((x)>>24)&0xFF);
+}
+
+#define         GET_APIC_ID(x)  get_apic_id(x)
+
+#endif
diff --git a/include/asm-x86/mach-es7000/mach_ipi.h b/include/asm-x86/es7000/ipi.h
index 5e61bd220b06..632a955fcc0a 100644
--- a/include/asm-x86/mach-es7000/mach_ipi.h
+++ b/include/asm-x86/es7000/ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef __ASM_ES7000_IPI_H
+#define __ASM_ES7000_IPI_H
 
 void send_IPI_mask_sequence(cpumask_t mask, int vector);
 
@@ -21,4 +21,4 @@ static inline void send_IPI_all(int vector)
         send_IPI_mask(cpu_online_map, vector);
 }
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* __ASM_ES7000_IPI_H */
diff --git a/include/asm-x86/mach-es7000/mach_mpparse.h b/include/asm-x86/es7000/mpparse.h
index ef26d3523625..7b5c889d8e7d 100644
--- a/include/asm-x86/mach-es7000/mach_mpparse.h
+++ b/include/asm-x86/es7000/mpparse.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef __ASM_ES7000_MPPARSE_H
+#define __ASM_ES7000_MPPARSE_H
 
 #include <linux/acpi.h>
 
diff --git a/include/asm-x86/mach-es7000/mach_wakecpu.h b/include/asm-x86/es7000/wakecpu.h
index 84ff58314501..3ffc5a7bf667 100644
--- a/include/asm-x86/mach-es7000/mach_wakecpu.h
+++ b/include/asm-x86/es7000/wakecpu.h
@@ -1,7 +1,7 @@
-#ifndef __ASM_MACH_WAKECPU_H
-#define __ASM_MACH_WAKECPU_H
+#ifndef __ASM_ES7000_WAKECPU_H
+#define __ASM_ES7000_WAKECPU_H
 
-/* 
+/*
  * This file copes with machines that wakeup secondary CPUs by the
  * INIT, INIT, STARTUP sequence.
  */
diff --git a/include/asm-x86/fb.h b/include/asm-x86/fb.h
index 53018464aea6..aca38dbd9a64 100644
--- a/include/asm-x86/fb.h
+++ b/include/asm-x86/fb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_FB_H
-#define _ASM_X86_FB_H
+#ifndef ASM_X86__FB_H
+#define ASM_X86__FB_H
 
 #include <linux/fb.h>
 #include <linux/fs.h>
@@ -18,4 +18,4 @@ extern int fb_is_primary_device(struct fb_info *info);
 static inline int fb_is_primary_device(struct fb_info *info) { return 0; }
 #endif
 
-#endif /* _ASM_X86_FB_H */
+#endif /* ASM_X86__FB_H */
diff --git a/include/asm-x86/fixmap.h b/include/asm-x86/fixmap.h
index 5bd206973dca..78e33a1bc591 100644
--- a/include/asm-x86/fixmap.h
+++ b/include/asm-x86/fixmap.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_FIXMAP_H
-#define _ASM_FIXMAP_H
+#ifndef ASM_X86__FIXMAP_H
+#define ASM_X86__FIXMAP_H
 
 #ifdef CONFIG_X86_32
 # include "fixmap_32.h"
@@ -7,7 +7,62 @@
 # include "fixmap_64.h"
 #endif
 
+extern int fixmaps_set;
+
+void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
+void native_set_fixmap(enum fixed_addresses idx,
+                       unsigned long phys, pgprot_t flags);
+
+#ifndef CONFIG_PARAVIRT
+static inline void __set_fixmap(enum fixed_addresses idx,
+                                unsigned long phys, pgprot_t flags)
+{
+        native_set_fixmap(idx, phys, flags);
+}
+#endif
+
+#define set_fixmap(idx, phys)                           \
+        __set_fixmap(idx, phys, PAGE_KERNEL)
+
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys)                   \
+        __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+
 #define clear_fixmap(idx)                       \
         __set_fixmap(idx, 0, __pgprot(0))
 
-#endif
+#define __fix_to_virt(x)        (FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)        ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without translation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
+{
+        /*
+         * this branch gets completely eliminated after inlining,
+         * except when someone tries to use fixaddr indices in an
+         * illegal way. (such as mixing up address types or using
+         * out-of-range indices).
+         *
+         * If it doesn't get removed, the linker will complain
+         * loudly with a reasonably clear error message..
+         */
+        if (idx >= __end_of_fixed_addresses)
+                __this_fixmap_does_not_exist();
+
+        return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+        BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+        return __virt_to_fix(vaddr);
+}
+#endif /* ASM_X86__FIXMAP_H */
diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h
index 4b96148e90c1..784e3e759866 100644
--- a/include/asm-x86/fixmap_32.h
+++ b/include/asm-x86/fixmap_32.h
@@ -10,8 +10,8 @@
  * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
  */
 
-#ifndef _ASM_FIXMAP_32_H
-#define _ASM_FIXMAP_32_H
+#ifndef ASM_X86__FIXMAP_32_H
+#define ASM_X86__FIXMAP_32_H
 
 
 /* used by vmalloc.c, vsyscall.lds.S.
@@ -79,10 +79,6 @@ enum fixed_addresses {
         FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
         FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
 #endif
-#ifdef CONFIG_ACPI
-        FIX_ACPI_BEGIN,
-        FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
 #ifdef CONFIG_PCI_MMCONFIG
         FIX_PCIE_MCFG,
 #endif
@@ -94,32 +90,27 @@ enum fixed_addresses {
          * 256 temporary boot-time mappings, used by early_ioremap(),
          * before ioremap() is functional.
          *
-         * We round it up to the next 512 pages boundary so that we
+         * 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_NESTING      4
-        FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 512 -
-                        (__end_of_permanent_fixed_addresses & 511),
+        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_NESTING - 1,
         FIX_WP_TEST,
+#ifdef CONFIG_ACPI
+        FIX_ACPI_BEGIN,
+        FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
         FIX_OHCI1394_BASE,
 #endif
         __end_of_fixed_addresses
 };
 
-extern void __set_fixmap(enum fixed_addresses idx,
-                         unsigned long phys, pgprot_t flags);
 extern void reserve_top_address(unsigned long reserve);
 
-#define set_fixmap(idx, phys)                           \
-        __set_fixmap(idx, phys, PAGE_KERNEL)
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys)                   \
-        __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
 
 #define FIXADDR_TOP     ((unsigned long)__FIXADDR_TOP)
 
@@ -128,38 +119,5 @@ extern void reserve_top_address(unsigned long reserve);
 #define FIXADDR_START           (FIXADDR_TOP - __FIXADDR_SIZE)
 #define FIXADDR_BOOT_START      (FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
 
-#define __fix_to_virt(x)        (FIXADDR_TOP - ((x) << PAGE_SHIFT))
-#define __virt_to_fix(x)        ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without tranlation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static __always_inline unsigned long fix_to_virt(const unsigned int idx)
-{
-        /*
-         * this branch gets completely eliminated after inlining,
-         * except when someone tries to use fixaddr indices in an
-         * illegal way. (such as mixing up address types or using
-         * out-of-range indices).
-         *
-         * If it doesn't get removed, the linker will complain
-         * loudly with a reasonably clear error message..
-         */
-        if (idx >= __end_of_fixed_addresses)
-                __this_fixmap_does_not_exist();
-
-        return __fix_to_virt(idx);
-}
-
-static inline unsigned long virt_to_fix(const unsigned long vaddr)
-{
-        BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
-        return __virt_to_fix(vaddr);
-}
-
 #endif /* !__ASSEMBLY__ */
-#endif
+#endif /* ASM_X86__FIXMAP_32_H */
diff --git a/include/asm-x86/fixmap_64.h b/include/asm-x86/fixmap_64.h
index 355d26a75a82..dafb24bc0424 100644
--- a/include/asm-x86/fixmap_64.h
+++ b/include/asm-x86/fixmap_64.h
@@ -8,10 +8,11 @@
  * Copyright (C) 1998 Ingo Molnar
  */
 
-#ifndef _ASM_FIXMAP_64_H
-#define _ASM_FIXMAP_64_H
+#ifndef ASM_X86__FIXMAP_64_H
+#define ASM_X86__FIXMAP_64_H
 
 #include <linux/kernel.h>
+#include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
 #include <asm/vsyscall.h>
@@ -39,30 +40,38 @@ enum fixed_addresses {
         VSYSCALL_HPET,
         FIX_DBGP_BASE,
         FIX_EARLYCON_MEM_BASE,
-        FIX_HPET_BASE,
         FIX_APIC_BASE,  /* local (CPU) APIC) -- required for SMP or not */
         FIX_IO_APIC_BASE_0,
         FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
         FIX_EFI_IO_MAP_LAST_PAGE,
         FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE
                                   + MAX_EFI_IO_PAGES - 1,
+#ifdef CONFIG_PARAVIRT
+        FIX_PARAVIRT_BOOTMAP,
+#endif
+#ifdef CONFIG_ACPI
+        FIX_ACPI_BEGIN,
+        FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
         FIX_OHCI1394_BASE,
 #endif
+        __end_of_permanent_fixed_addresses,
+        /*
+         * 256 temporary boot-time mappings, used by early_ioremap(),
+         * before ioremap() is functional.
+         *
+         * We round it up to the next 512 pages boundary so that we
+         * can have a single pgd entry and a single pte table:
+         */
+#define NR_FIX_BTMAPS           64
+#define FIX_BTMAPS_NESTING      4
+        FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 512 -
+                        (__end_of_permanent_fixed_addresses & 511),
+        FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_NESTING - 1,
         __end_of_fixed_addresses
 };
 
-extern void __set_fixmap(enum fixed_addresses idx,
-                         unsigned long phys, pgprot_t flags);
-
-#define set_fixmap(idx, phys)                   \
-        __set_fixmap(idx, phys, PAGE_KERNEL)
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys)                   \
-        __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
-
 #define FIXADDR_TOP     (VSYSCALL_END-PAGE_SIZE)
 #define FIXADDR_SIZE    (__end_of_fixed_addresses << PAGE_SHIFT)
 #define FIXADDR_START   (FIXADDR_TOP - FIXADDR_SIZE)
@@ -71,30 +80,4 @@ extern void __set_fixmap(enum fixed_addresses idx,
 #define FIXADDR_USER_START      ((unsigned long)VSYSCALL32_VSYSCALL)
 #define FIXADDR_USER_END        (FIXADDR_USER_START + PAGE_SIZE)
 
-#define __fix_to_virt(x)        (FIXADDR_TOP - ((x) << PAGE_SHIFT))
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without translation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static __always_inline unsigned long fix_to_virt(const unsigned int idx)
-{
-        /*
-         * this branch gets completely eliminated after inlining,
-         * except when someone tries to use fixaddr indices in an
-         * illegal way. (such as mixing up address types or using
-         * out-of-range indices).
-         *
-         * If it doesn't get removed, the linker will complain
-         * loudly with a reasonably clear error message..
-         */
-        if (idx >= __end_of_fixed_addresses)
-                __this_fixmap_does_not_exist();
-
-        return __fix_to_virt(idx);
-}
-
-#endif
+#endif /* ASM_X86__FIXMAP_64_H */
diff --git a/include/asm-x86/floppy.h b/include/asm-x86/floppy.h
index dbe82a5c5eac..7d83a3a83e37 100644
--- a/include/asm-x86/floppy.h
+++ b/include/asm-x86/floppy.h
@@ -7,8 +7,8 @@
  *
  * Copyright (C) 1995
  */
-#ifndef _ASM_X86_FLOPPY_H
-#define _ASM_X86_FLOPPY_H
+#ifndef ASM_X86__FLOPPY_H
+#define ASM_X86__FLOPPY_H
 
 #include <linux/vmalloc.h>
 
@@ -278,4 +278,4 @@ static int FDC2 = -1;
 
 #define EXTRA_FLOPPY_PARAMS
 
-#endif /* _ASM_X86_FLOPPY_H */
+#endif /* ASM_X86__FLOPPY_H */
diff --git a/include/asm-x86/ftrace.h b/include/asm-x86/ftrace.h
new file mode 100644
index 000000000000..be0e004ad148
--- /dev/null
+++ b/include/asm-x86/ftrace.h
@@ -0,0 +1,14 @@
+#ifndef ASM_X86__FTRACE_H
+#define ASM_X86__FTRACE_H
+
+#ifdef CONFIG_FTRACE
+#define MCOUNT_ADDR             ((long)(mcount))
+#define MCOUNT_INSN_SIZE        5 /* sizeof mcount call */
+
+#ifndef __ASSEMBLY__
+extern void mcount(void);
+#endif
+
+#endif /* CONFIG_FTRACE */
+
+#endif /* ASM_X86__FTRACE_H */
diff --git a/include/asm-x86/futex.h b/include/asm-x86/futex.h
index e7a76b37b333..06b924ef6fa5 100644
--- a/include/asm-x86/futex.h
+++ b/include/asm-x86/futex.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_FUTEX_H
-#define _ASM_X86_FUTEX_H
+#ifndef ASM_X86__FUTEX_H
+#define ASM_X86__FUTEX_H
 
 #ifdef __KERNEL__
 
@@ -25,7 +25,7 @@
         asm volatile("1:\tmovl  %2, %0\n"                       \
                      "\tmovl\t%0, %3\n"                         \
                      "\t" insn "\n"                             \
-                     "2:\tlock; cmpxchgl %3, %2\n"              \
+                     "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"     \
                      "\tjnz\t1b\n"                              \
                      "3:\t.section .fixup,\"ax\"\n"             \
                      "4:\tmov\t%5, %1\n"                        \
@@ -64,7 +64,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
                 __futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg);
                 break;
         case FUTEX_OP_ADD:
-                __futex_atomic_op1("lock; xaddl %0, %2", ret, oldval,
+                __futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval,
                                    uaddr, oparg);
                 break;
         case FUTEX_OP_OR:
@@ -122,7 +122,7 @@ static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
         if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
                 return -EFAULT;
 
-        asm volatile("1:\tlock; cmpxchgl %3, %1\n"
+        asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
                      "2:\t.section .fixup, \"ax\"\n"
                      "3:\tmov     %2, %0\n"
                      "\tjmp     2b\n"
@@ -137,4 +137,4 @@ static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
 }
 
 #endif
-#endif
+#endif /* ASM_X86__FUTEX_H */
diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h
index 90958ed993fa..605edb39ef9e 100644
--- a/include/asm-x86/gart.h
+++ b/include/asm-x86/gart.h
@@ -1,34 +1,73 @@
-#ifndef _ASM_X8664_IOMMU_H
-#define _ASM_X8664_IOMMU_H 1
-
-extern void pci_iommu_shutdown(void);
-extern void no_iommu_init(void);
-extern int force_iommu, no_iommu;
-extern int iommu_detected;
-#ifdef CONFIG_GART_IOMMU
-extern void gart_iommu_init(void);
-extern void gart_iommu_shutdown(void);
-extern void __init gart_parse_options(char *);
-extern void early_gart_iommu_check(void);
-extern void gart_iommu_hole_init(void);
+#ifndef ASM_X86__GART_H
+#define ASM_X86__GART_H
+
+#include <asm/e820.h>
+
+extern void set_up_gart_resume(u32, u32);
+
 extern int fallback_aper_order;
 extern int fallback_aper_force;
-extern int gart_iommu_aperture;
-extern int gart_iommu_aperture_allowed;
-extern int gart_iommu_aperture_disabled;
 extern int fix_aperture;
-#else
-#define gart_iommu_aperture 0
-#define gart_iommu_aperture_allowed 0
 
-static inline void early_gart_iommu_check(void)
+/* PTE bits. */
+#define GPTE_VALID      1
+#define GPTE_COHERENT   2
+
+/* Aperture control register bits. */
+#define GARTEN          (1<<0)
+#define DISGARTCPU      (1<<4)
+#define DISGARTIO       (1<<5)
+
+/* GART cache control register bits. */
+#define INVGART         (1<<0)
+#define GARTPTEERR      (1<<1)
+
+/* K8 On-cpu GART registers */
+#define AMD64_GARTAPERTURECTL   0x90
+#define AMD64_GARTAPERTUREBASE  0x94
+#define AMD64_GARTTABLEBASE     0x98
+#define AMD64_GARTCACHECTL      0x9c
+#define AMD64_GARTEN            (1<<0)
+
+extern int agp_amd64_init(void);
+
+static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
 {
+        u32 tmp, ctl;
+
+        /* address of the mappings table */
+        addr >>= 12;
+        tmp = (u32) addr<<4;
+        tmp &= ~0xf;
+        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+
+        /* Enable GART translation for this hammer. */
+        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+        ctl |= GARTEN;
+        ctl &= ~(DISGARTCPU | DISGARTIO);
+        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
 
-static inline void gart_iommu_shutdown(void)
+static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
 {
-}
+        if (!aper_base)
+                return 0;
+
+        if (aper_base + aper_size > 0x100000000ULL) {
+                printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
+                return 0;
+        }
+        if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+                printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
+                return 0;
+        }
+        if (aper_size < min_size) {
+                printk(KERN_INFO "Aperture too small (%d MB) than (%d MB)\n",
+                                 aper_size>>20, min_size>>20);
+                return 0;
+        }
 
-#endif
+        return 1;
+}
 
-#endif
+#endif /* ASM_X86__GART_H */
diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h
index b02ea6e17de8..34280f027664 100644
--- a/include/asm-x86/genapic_32.h
+++ b/include/asm-x86/genapic_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_GENAPIC_H
-#define _ASM_GENAPIC_H 1
+#ifndef ASM_X86__GENAPIC_32_H
+#define ASM_X86__GENAPIC_32_H
 
 #include <asm/mpspec.h>
 
@@ -118,6 +118,7 @@ enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
 #define get_uv_system_type()            UV_NONE
 #define is_uv_system()                  0
 #define uv_wakeup_secondary(a, b)       1
+#define uv_system_init()                do {} while (0)
 
 
-#endif
+#endif /* ASM_X86__GENAPIC_32_H */
diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h
index 1de931b263ce..ed6a4886c082 100644
--- a/include/asm-x86/genapic_64.h
+++ b/include/asm-x86/genapic_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_GENAPIC_H
-#define _ASM_GENAPIC_H 1
+#ifndef ASM_X86__GENAPIC_64_H
+#define ASM_X86__GENAPIC_64_H
 
 /*
  * Copyright 2004 James Cleverdon, IBM.
@@ -14,6 +14,7 @@
 
 struct genapic {
         char *name;
+        int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
         u32 int_delivery_mode;
         u32 int_dest_mode;
         int (*apic_id_registered)(void);
@@ -24,17 +25,24 @@ struct genapic {
         void (*send_IPI_mask)(cpumask_t mask, int vector);
         void (*send_IPI_allbutself)(int vector);
         void (*send_IPI_all)(int vector);
+        void (*send_IPI_self)(int vector);
         /* */
         unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
         unsigned int (*phys_pkg_id)(int index_msb);
+        unsigned int (*get_apic_id)(unsigned long x);
+        unsigned long (*set_apic_id)(unsigned int id);
+        unsigned long apic_id_mask;
 };
 
 extern struct genapic *genapic;
 
 extern struct genapic apic_flat;
 extern struct genapic apic_physflat;
+extern struct genapic apic_x2apic_cluster;
+extern struct genapic apic_x2apic_phys;
 extern int acpi_madt_oem_check(char *, char *);
 
+extern void apic_send_IPI_self(int vector);
 enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
 extern enum uv_system_type get_uv_system_type(void);
 extern int is_uv_system(void);
@@ -42,6 +50,9 @@ extern int is_uv_system(void);
 extern struct genapic apic_x2apic_uv_x;
 DECLARE_PER_CPU(int, x2apic_extra_bits);
 extern void uv_cpu_init(void);
+extern void uv_system_init(void);
 extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
 
-#endif
+extern void setup_apic_routing(void);
+
+#endif /* ASM_X86__GENAPIC_64_H */
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
index 6e6458853a36..3f3444be2638 100644
--- a/include/asm-x86/geode.h
+++ b/include/asm-x86/geode.h
@@ -7,8 +7,8 @@
  * as published by the Free Software Foundation.
  */
 
-#ifndef _ASM_GEODE_H_
-#define _ASM_GEODE_H_
+#ifndef ASM_X86__GEODE_H
+#define ASM_X86__GEODE_H
 
 #include <asm/processor.h>
 #include <linux/io.h>
@@ -50,6 +50,7 @@ extern int geode_get_dev_base(unsigned int dev);
 #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
@@ -112,8 +113,8 @@ extern int geode_get_dev_base(unsigned int dev);
 #define VSA_VR_UNLOCK           0xFC53  /* unlock virtual register */
 #define VSA_VR_SIGNATURE        0x0003
 #define VSA_VR_MEM_SIZE         0x0200
-#define VSA_SIG                 0x4132  /* signature is ascii 'VSA2' */
-
+#define AMD_VSA_SIG             0x4132  /* signature is ascii 'VSA2' */
+#define GSW_VSA_SIG             0x534d  /* General Software signature */
 /* GPIO */
 
 #define GPIO_OUTPUT_VAL         0x00
@@ -237,7 +238,7 @@ static inline u16 geode_mfgpt_read(int timer, u16 reg)
 }
 
 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_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)
@@ -249,4 +250,4 @@ extern int __init mfgpt_timer_setup(void);
 static inline int mfgpt_timer_setup(void) { return 0; }
 #endif
 
-#endif
+#endif /* ASM_X86__GEODE_H */
diff --git a/include/asm-x86/gpio.h b/include/asm-x86/gpio.h
index ff87fca0caf9..497fb980d962 100644
--- a/include/asm-x86/gpio.h
+++ b/include/asm-x86/gpio.h
@@ -1,6 +1,56 @@
+/*
+ * Generic GPIO API implementation for x86.
+ *
+ * Derived from the generic GPIO API for powerpc:
+ *
+ * Copyright (c) 2007-2008  MontaVista Software, Inc.
+ *
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.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.
+ */
+
 #ifndef _ASM_I386_GPIO_H
 #define _ASM_I386_GPIO_H
 
-#include <gpio.h>
+#include <asm-generic/gpio.h>
+
+#ifdef CONFIG_GPIOLIB
+
+/*
+ * Just call gpiolib.
+ */
+static inline int gpio_get_value(unsigned int gpio)
+{
+        return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned int gpio, int value)
+{
+        __gpio_set_value(gpio, value);
+}
+
+static inline int gpio_cansleep(unsigned int gpio)
+{
+        return __gpio_cansleep(gpio);
+}
+
+/*
+ * Not implemented, yet.
+ */
+static inline int gpio_to_irq(unsigned int gpio)
+{
+        return -ENOSYS;
+}
+
+static inline int irq_to_gpio(unsigned int irq)
+{
+        return -EINVAL;
+}
+
+#endif /* CONFIG_GPIOLIB */
 
-#endif /* _ASM_I386_GPIO_H */
+#endif /* ASM_X86__GPIO_H */
diff --git a/include/asm-x86/hardirq.h b/include/asm-x86/hardirq.h
index 314434d664e7..000787df66e6 100644
--- a/include/asm-x86/hardirq.h
+++ b/include/asm-x86/hardirq.h
@@ -3,3 +3,9 @@
 #else
 # include "hardirq_64.h"
 #endif
+
+extern u64 arch_irq_stat_cpu(unsigned int cpu);
+#define arch_irq_stat_cpu       arch_irq_stat_cpu
+
+extern u64 arch_irq_stat(void);
+#define arch_irq_stat           arch_irq_stat
diff --git a/include/asm-x86/hardirq_32.h b/include/asm-x86/hardirq_32.h
index 4f85f0f4b563..700fe230d919 100644
--- a/include/asm-x86/hardirq_32.h
+++ b/include/asm-x86/hardirq_32.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_HARDIRQ_H
-#define __ASM_HARDIRQ_H
+#ifndef ASM_X86__HARDIRQ_32_H
+#define ASM_X86__HARDIRQ_32_H
 
 #include <linux/threads.h>
 #include <linux/irq.h>
@@ -25,4 +25,4 @@ DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
 void ack_bad_irq(unsigned int irq);
 #include <linux/irq_cpustat.h>
 
-#endif /* __ASM_HARDIRQ_H */
+#endif /* ASM_X86__HARDIRQ_32_H */
diff --git a/include/asm-x86/hardirq_64.h b/include/asm-x86/hardirq_64.h
index 95d5e090ed89..f8bd2919a8ce 100644
--- a/include/asm-x86/hardirq_64.h
+++ b/include/asm-x86/hardirq_64.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_HARDIRQ_H
-#define __ASM_HARDIRQ_H
+#ifndef ASM_X86__HARDIRQ_64_H
+#define ASM_X86__HARDIRQ_64_H
 
 #include <linux/threads.h>
 #include <linux/irq.h>
@@ -20,4 +20,4 @@
 
 extern void ack_bad_irq(unsigned int irq);
 
-#endif /* __ASM_HARDIRQ_H */
+#endif /* ASM_X86__HARDIRQ_64_H */
diff --git a/include/asm-x86/highmem.h b/include/asm-x86/highmem.h
index e153f3b44774..bc3f6a280316 100644
--- a/include/asm-x86/highmem.h
+++ b/include/asm-x86/highmem.h
@@ -15,8 +15,8 @@
  * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
  */
 
-#ifndef _ASM_HIGHMEM_H
-#define _ASM_HIGHMEM_H
+#ifndef ASM_X86__HIGHMEM_H
+#define ASM_X86__HIGHMEM_H
 
 #ifdef __KERNEL__
 
@@ -74,6 +74,9 @@ struct page *kmap_atomic_to_page(void *ptr);
 
 #define flush_cache_kmaps()     do { } while (0)
 
+extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn,
+                                        unsigned long end_pfn);
+
 #endif /* __KERNEL__ */
 
-#endif /* _ASM_HIGHMEM_H */
+#endif /* ASM_X86__HIGHMEM_H */
diff --git a/include/asm-x86/hpet.h b/include/asm-x86/hpet.h
index 6a9b4ac59bf7..cbbbb6d4dd32 100644
--- a/include/asm-x86/hpet.h
+++ b/include/asm-x86/hpet.h
@@ -1,5 +1,5 @@
-#ifndef ASM_X86_HPET_H
-#define ASM_X86_HPET_H
+#ifndef ASM_X86__HPET_H
+#define ASM_X86__HPET_H
 
 #ifdef CONFIG_HPET_TIMER
 
@@ -86,8 +86,8 @@ extern void hpet_unregister_irq_handler(rtc_irq_handler handler);
 #else /* CONFIG_HPET_TIMER */
 
 static inline int hpet_enable(void) { return 0; }
-static inline unsigned long hpet_readl(unsigned long a) { return 0; }
 static inline int is_hpet_enabled(void) { return 0; }
+#define hpet_readl(a) 0
 
 #endif
-#endif /* ASM_X86_HPET_H */
+#endif /* ASM_X86__HPET_H */
diff --git a/include/asm-x86/hugetlb.h b/include/asm-x86/hugetlb.h
index 14171a4924f6..0b7ec5dc0884 100644
--- a/include/asm-x86/hugetlb.h
+++ b/include/asm-x86/hugetlb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_HUGETLB_H
-#define _ASM_X86_HUGETLB_H
+#ifndef ASM_X86__HUGETLB_H
+#define ASM_X86__HUGETLB_H
 
 #include <asm/page.h>
 
@@ -14,11 +14,13 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+                        unsigned long addr, unsigned long len)
 {
-        if (len & ~HPAGE_MASK)
+        struct hstate *h = hstate_file(file);
+        if (len & ~huge_page_mask(h))
                 return -EINVAL;
-        if (addr & ~HPAGE_MASK)
+        if (addr & ~huge_page_mask(h))
                 return -EINVAL;
         return 0;
 }
@@ -26,7 +28,7 @@ static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
 static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather **tlb,
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
                                           unsigned long addr, unsigned long end,
                                           unsigned long floor,
                                           unsigned long ceiling)
@@ -88,4 +90,4 @@ static inline void arch_release_hugepage(struct page *page)
 {
 }
 
-#endif /* _ASM_X86_HUGETLB_H */
+#endif /* ASM_X86__HUGETLB_H */
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
index bf025399d939..50f6e0316b50 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -1,5 +1,136 @@
+#ifndef ASM_X86__HW_IRQ_H
+#define ASM_X86__HW_IRQ_H
+
+/*
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * moved some of the old arch/i386/kernel/irq.h to here. VY
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@informatik.tu-chemnitz.de>
+ *
+ * hacked by Andi Kleen for x86-64.
+ * unified by tglx
+ */
+
+#include <asm/irq_vectors.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/smp.h>
+
+#include <asm/atomic.h>
+#include <asm/irq.h>
+#include <asm/sections.h>
+
+#define platform_legacy_irq(irq)        ((irq) < 16)
+
+/* Interrupt handlers registered during init_IRQ */
+extern void apic_timer_interrupt(void);
+extern void error_interrupt(void);
+extern void spurious_interrupt(void);
+extern void thermal_interrupt(void);
+extern void reschedule_interrupt(void);
+
+extern void invalidate_interrupt(void);
+extern void invalidate_interrupt0(void);
+extern void invalidate_interrupt1(void);
+extern void invalidate_interrupt2(void);
+extern void invalidate_interrupt3(void);
+extern void invalidate_interrupt4(void);
+extern void invalidate_interrupt5(void);
+extern void invalidate_interrupt6(void);
+extern void invalidate_interrupt7(void);
+
+extern void irq_move_cleanup_interrupt(void);
+extern void threshold_interrupt(void);
+
+extern void call_function_interrupt(void);
+extern void call_function_single_interrupt(void);
+
+/* PIC specific functions */
+extern void disable_8259A_irq(unsigned int irq);
+extern void enable_8259A_irq(unsigned int irq);
+extern int i8259A_irq_pending(unsigned int irq);
+extern void make_8259A_irq(unsigned int irq);
+extern void init_8259A(int aeoi);
+
+/* IOAPIC */
+#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
+extern unsigned long io_apic_irqs;
+
+extern void init_VISWS_APIC_irqs(void);
+extern void setup_IO_APIC(void);
+extern void disable_IO_APIC(void);
+extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
+extern void setup_ioapic_dest(void);
+
+#ifdef CONFIG_X86_64
+extern void enable_IO_APIC(void);
+#endif
+
+/* IPI functions */
+#ifdef CONFIG_X86_32
+extern void send_IPI_self(int vector);
+#endif
+extern void send_IPI(int dest, int vector);
+
+/* Statistics */
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
+
+/* EISA */
+extern void eisa_set_level_irq(unsigned int irq);
+
+/* Voyager functions */
+extern asmlinkage void vic_cpi_interrupt(void);
+extern asmlinkage void vic_sys_interrupt(void);
+extern asmlinkage void vic_cmn_interrupt(void);
+extern asmlinkage void qic_timer_interrupt(void);
+extern asmlinkage void qic_invalidate_interrupt(void);
+extern asmlinkage void qic_reschedule_interrupt(void);
+extern asmlinkage void qic_enable_irq_interrupt(void);
+extern asmlinkage void qic_call_function_interrupt(void);
+
+/* SMP */
+extern void smp_apic_timer_interrupt(struct pt_regs *);
+#ifdef CONFIG_X86_32
+extern void smp_spurious_interrupt(struct pt_regs *);
+extern void smp_error_interrupt(struct pt_regs *);
+#else
+extern asmlinkage void smp_spurious_interrupt(void);
+extern asmlinkage void smp_error_interrupt(void);
+#endif
+#ifdef CONFIG_X86_SMP
+extern void smp_reschedule_interrupt(struct pt_regs *);
+extern void smp_call_function_interrupt(struct pt_regs *);
+extern void smp_call_function_single_interrupt(struct pt_regs *);
 #ifdef CONFIG_X86_32
-# include "hw_irq_32.h"
+extern void smp_invalidate_interrupt(struct pt_regs *);
+#else
+extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
+#endif
+#endif
+
+#ifdef CONFIG_X86_32
+extern void (*const interrupt[NR_IRQS])(void);
+#else
+typedef int vector_irq_t[NR_VECTORS];
+DECLARE_PER_CPU(vector_irq_t, vector_irq);
+#endif
+
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_X86_64)
+extern void lock_vector_lock(void);
+extern void unlock_vector_lock(void);
+extern void __setup_vector_irq(int cpu);
 #else
-# include "hw_irq_64.h"
+static inline void lock_vector_lock(void) {}
+static inline void unlock_vector_lock(void) {}
+static inline void __setup_vector_irq(int cpu) {}
 #endif
+
+#endif /* !ASSEMBLY_ */
+
+#endif /* ASM_X86__HW_IRQ_H */
diff --git a/include/asm-x86/hw_irq_32.h b/include/asm-x86/hw_irq_32.h
deleted file mode 100644
index ea88054e03f3..000000000000
--- a/include/asm-x86/hw_irq_32.h
+++ /dev/null
@@ -1,66 +0,0 @@
-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
-
-/*
- *      linux/include/asm/hw_irq.h
- *
- *      (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *      moved some of the old arch/i386/kernel/irq.h to here. VY
- *
- *      IRQ/IPI changes taken from work by Thomas Radke
- *      <tomsoft@informatik.tu-chemnitz.de>
- */
-
-#include <linux/profile.h>
-#include <asm/atomic.h>
-#include <asm/irq.h>
-#include <asm/sections.h>
-
-#define NMI_VECTOR              0x02
-
-/*
- * Various low-level irq details needed by irq.c, process.c,
- * time.c, io_apic.c and smp.c
- *
- * Interrupt entry/exit code at both C and assembly level
- */
-
-extern void (*const interrupt[NR_IRQS])(void);
-
-#ifdef CONFIG_SMP
-void reschedule_interrupt(void);
-void invalidate_interrupt(void);
-void call_function_interrupt(void);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-void apic_timer_interrupt(void);
-void error_interrupt(void);
-void spurious_interrupt(void);
-void thermal_interrupt(void);
-#define platform_legacy_irq(irq)        ((irq) < 16)
-#endif
-
-void disable_8259A_irq(unsigned int irq);
-void enable_8259A_irq(unsigned int irq);
-int i8259A_irq_pending(unsigned int irq);
-void make_8259A_irq(unsigned int irq);
-void init_8259A(int aeoi);
-void send_IPI_self(int vector);
-void init_VISWS_APIC_irqs(void);
-void setup_IO_APIC(void);
-void disable_IO_APIC(void);
-void print_IO_APIC(void);
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
-void send_IPI(int dest, int vector);
-void setup_ioapic_dest(void);
-
-extern unsigned long io_apic_irqs;
-
-extern atomic_t irq_err_count;
-extern atomic_t irq_mis_count;
-
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
-
-#endif /* _ASM_HW_IRQ_H */
diff --git a/include/asm-x86/hw_irq_64.h b/include/asm-x86/hw_irq_64.h
deleted file mode 100644
index 0062ef390f67..000000000000
--- a/include/asm-x86/hw_irq_64.h
+++ /dev/null
@@ -1,173 +0,0 @@
-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
-
-/*
- *      linux/include/asm/hw_irq.h
- *
- *      (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *      moved some of the old arch/i386/kernel/irq.h to here. VY
- *
- *      IRQ/IPI changes taken from work by Thomas Radke
- *      <tomsoft@informatik.tu-chemnitz.de>
- *
- *      hacked by Andi Kleen for x86-64.
- */
-
-#ifndef __ASSEMBLY__
-#include <asm/atomic.h>
-#include <asm/irq.h>
-#include <linux/profile.h>
-#include <linux/smp.h>
-#include <linux/percpu.h>
-#endif
-
-#define NMI_VECTOR              0x02
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR   0x20
-
-#define IA32_SYSCALL_VECTOR     0x80
-
-
-/* Reserve the lowest usable priority level 0x20 - 0x2f for triggering
- * cleanup after irq migration.
- */
-#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR
-
-/*
- * Vectors 0x30-0x3f are used for ISA interrupts.
- */
-#define IRQ0_VECTOR             (FIRST_EXTERNAL_VECTOR + 0x10)
-#define IRQ1_VECTOR             (IRQ0_VECTOR + 1)
-#define IRQ2_VECTOR             (IRQ0_VECTOR + 2)
-#define IRQ3_VECTOR             (IRQ0_VECTOR + 3)
-#define IRQ4_VECTOR             (IRQ0_VECTOR + 4)
-#define IRQ5_VECTOR             (IRQ0_VECTOR + 5)
-#define IRQ6_VECTOR             (IRQ0_VECTOR + 6)
-#define IRQ7_VECTOR             (IRQ0_VECTOR + 7)
-#define IRQ8_VECTOR             (IRQ0_VECTOR + 8)
-#define IRQ9_VECTOR             (IRQ0_VECTOR + 9)
-#define IRQ10_VECTOR            (IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR            (IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR            (IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR            (IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR            (IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR            (IRQ0_VECTOR + 15)
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- */
-#define SPURIOUS_APIC_VECTOR    0xff
-#define ERROR_APIC_VECTOR       0xfe
-#define RESCHEDULE_VECTOR       0xfd
-#define CALL_FUNCTION_VECTOR    0xfc
-/* fb free - please don't readd KDB here because it's useless
-   (hint - think what a NMI bit does to a vector) */
-#define THERMAL_APIC_VECTOR     0xfa
-#define THRESHOLD_APIC_VECTOR   0xf9
-/* f8 free */
-#define INVALIDATE_TLB_VECTOR_END       0xf7
-#define INVALIDATE_TLB_VECTOR_START     0xf0    /* f0-f7 used for TLB flush */
-
-#define NUM_INVALIDATE_TLB_VECTORS      8
-
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR      0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x41 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR     (IRQ15_VECTOR + 2)
-#define FIRST_SYSTEM_VECTOR     0xef   /* duplicated in irq.h */
-
-
-#ifndef __ASSEMBLY__
-
-/* Interrupt handlers registered during init_IRQ */
-void apic_timer_interrupt(void);
-void spurious_interrupt(void);
-void error_interrupt(void);
-void reschedule_interrupt(void);
-void call_function_interrupt(void);
-void irq_move_cleanup_interrupt(void);
-void invalidate_interrupt0(void);
-void invalidate_interrupt1(void);
-void invalidate_interrupt2(void);
-void invalidate_interrupt3(void);
-void invalidate_interrupt4(void);
-void invalidate_interrupt5(void);
-void invalidate_interrupt6(void);
-void invalidate_interrupt7(void);
-void thermal_interrupt(void);
-void threshold_interrupt(void);
-void i8254_timer_resume(void);
-
-typedef int vector_irq_t[NR_VECTORS];
-DECLARE_PER_CPU(vector_irq_t, vector_irq);
-extern void __setup_vector_irq(int cpu);
-extern spinlock_t vector_lock;
-
-/*
- * Various low-level irq details needed by irq.c, process.c,
- * time.c, io_apic.c and smp.c
- *
- * Interrupt entry/exit code at both C and assembly level
- */
-
-extern void disable_8259A_irq(unsigned int irq);
-extern void enable_8259A_irq(unsigned int irq);
-extern int i8259A_irq_pending(unsigned int irq);
-extern void make_8259A_irq(unsigned int irq);
-extern void init_8259A(int aeoi);
-extern void send_IPI_self(int vector);
-extern void init_VISWS_APIC_irqs(void);
-extern void setup_IO_APIC(void);
-extern void enable_IO_APIC(void);
-extern void disable_IO_APIC(void);
-extern void print_IO_APIC(void);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
-extern void send_IPI(int dest, int vector);
-extern void setup_ioapic_dest(void);
-extern void native_init_IRQ(void);
-
-extern unsigned long io_apic_irqs;
-
-extern atomic_t irq_err_count;
-extern atomic_t irq_mis_count;
-
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
-
-#include <asm/ptrace.h>
-
-#define IRQ_NAME2(nr) nr##_interrupt(void)
-#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
-
-/*
- *      SMP has a few special interrupts for IPI messages
- */
-
-#define BUILD_IRQ(nr)                           \
-        asmlinkage void IRQ_NAME(nr);           \
-        asm("\n.p2align\n"                      \
-            "IRQ" #nr "_interrupt:\n\t"         \
-            "push $~(" #nr ") ; "               \
-            "jmp common_interrupt");
-
-#define platform_legacy_irq(irq)        ((irq) < 16)
-
-#endif
-
-#endif /* _ASM_HW_IRQ_H */
diff --git a/include/asm-x86/hypertransport.h b/include/asm-x86/hypertransport.h
index d2bbd238b3e1..cc011a3bc1c2 100644
--- a/include/asm-x86/hypertransport.h
+++ b/include/asm-x86/hypertransport.h
@@ -1,5 +1,5 @@
-#ifndef ASM_HYPERTRANSPORT_H
-#define ASM_HYPERTRANSPORT_H
+#ifndef ASM_X86__HYPERTRANSPORT_H
+#define ASM_X86__HYPERTRANSPORT_H
 
 /*
  * Constants for x86 Hypertransport Interrupts.
@@ -42,4 +42,4 @@
 #define HT_IRQ_HIGH_DEST_ID(v)                                          \
         ((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK)
 
-#endif /* ASM_HYPERTRANSPORT_H */
+#endif /* ASM_X86__HYPERTRANSPORT_H */
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index 37672f79dcc8..9ba862a4eac0 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -7,34 +7,44 @@
  * x86-64 work by Andi Kleen 2002
  */
 
-#ifndef _ASM_X86_I387_H
-#define _ASM_X86_I387_H
+#ifndef ASM_X86__I387_H
+#define ASM_X86__I387_H
 
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
 #include <linux/regset.h>
+#include <linux/hardirq.h>
 #include <asm/asm.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
 #include <asm/user.h>
 #include <asm/uaccess.h>
+#include <asm/xsave.h>
 
+extern unsigned int sig_xstate_size;
 extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
 extern asmlinkage void math_state_restore(void);
 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 struct _fpx_sw_bytes fx_sw_reserved;
 #ifdef CONFIG_IA32_EMULATION
+extern unsigned int sig_xstate_ia32_size;
+extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
 struct _fpstate_ia32;
-extern int save_i387_ia32(struct _fpstate_ia32 __user *buf);
-extern int restore_i387_ia32(struct _fpstate_ia32 __user *buf);
+struct _xstate_ia32;
+extern int save_i387_xstate_ia32(void __user *buf);
+extern int restore_i387_xstate_ia32(void __user *buf);
 #endif
 
+#define X87_FSW_ES (1 << 7)     /* Exception Summary */
+
 #ifdef CONFIG_X86_64
 
 /* Ignore delayed exceptions from user space */
@@ -45,7 +55,7 @@ static inline void tolerant_fwait(void)
                      _ASM_EXTABLE(1b, 2b));
 }
 
-static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
         int err;
 
@@ -62,20 +72,34 @@ static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
 #else
                      : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
 #endif
-        if (unlikely(err))
-                init_fpu(current);
         return err;
 }
 
-#define X87_FSW_ES (1 << 7)     /* Exception Summary */
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+        if (task_thread_info(tsk)->status & TS_XSAVE)
+                return xrstor_checking(&tsk->thread.xstate->xsave);
+        else
+                return fxrstor_checking(&tsk->thread.xstate->fxsave);
+}
 
 /* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
    is pending. Clear the x87 state here by setting it to fixed
    values. The kernel data segment can be sometimes 0 and sometimes
    new user value. Both should be ok.
    Use the PDA as safe address because it should be already in L1. */
-static inline void clear_fpu_state(struct i387_fxsave_struct *fx)
+static inline void clear_fpu_state(struct task_struct *tsk)
 {
+        struct xsave_struct *xstate = &tsk->thread.xstate->xsave;
+        struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
+
+        /*
+         * xsave header may indicate the init state of the FP.
+         */
+        if ((task_thread_info(tsk)->status & TS_XSAVE) &&
+            !(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
+                return;
+
         if (unlikely(fx->swd & X87_FSW_ES))
                 asm volatile("fnclex");
         alternative_input(ASM_NOP8 ASM_NOP2,
@@ -84,7 +108,7 @@ static inline void clear_fpu_state(struct i387_fxsave_struct *fx)
                           X86_FEATURE_FXSAVE_LEAK);
 }
 
-static inline int save_i387_checking(struct i387_fxsave_struct __user *fx)
+static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
         int err;
 
@@ -108,7 +132,7 @@ static inline int save_i387_checking(struct i387_fxsave_struct __user *fx)
         return err;
 }
 
-static inline void __save_init_fpu(struct task_struct *tsk)
+static inline void fxsave(struct task_struct *tsk)
 {
         /* Using "rex64; fxsave %0" is broken because, if the memory operand
            uses any extended registers for addressing, a second REX prefix
@@ -133,62 +157,17 @@ static inline void __save_init_fpu(struct task_struct *tsk)
                              : "=m" (tsk->thread.xstate->fxsave)
                              : "cdaSDb" (&tsk->thread.xstate->fxsave));
 #endif
-        clear_fpu_state(&tsk->thread.xstate->fxsave);
-        task_thread_info(tsk)->status &= ~TS_USEDFPU;
-}
-
-/*
- * Signal frame handlers.
- */
-
-static inline int save_i387(struct _fpstate __user *buf)
-{
-        struct task_struct *tsk = current;
-        int err = 0;
-
-        BUILD_BUG_ON(sizeof(struct user_i387_struct) !=
-                        sizeof(tsk->thread.xstate->fxsave));
-
-        if ((unsigned long)buf % 16)
-                printk("save_i387: bad fpstate %p\n", buf);
-
-        if (!used_math())
-                return 0;
-        clear_used_math(); /* trigger finit */
-        if (task_thread_info(tsk)->status & TS_USEDFPU) {
-                err = save_i387_checking((struct i387_fxsave_struct __user *)
-                                         buf);
-                if (err)
-                        return err;
-                task_thread_info(tsk)->status &= ~TS_USEDFPU;
-                stts();
-        } else {
-                if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
-                                   sizeof(struct i387_fxsave_struct)))
-                        return -1;
-        }
-        return 1;
 }
 
-/*
- * This restores directly out of user space. Exceptions are handled.
- */
-static inline int restore_i387(struct _fpstate __user *buf)
+static inline void __save_init_fpu(struct task_struct *tsk)
 {
-        struct task_struct *tsk = current;
-        int err;
-
-        if (!used_math()) {
-                err = init_fpu(tsk);
-                if (err)
-                        return err;
-        }
+        if (task_thread_info(tsk)->status & TS_XSAVE)
+                xsave(tsk);
+        else
+                fxsave(tsk);
 
-        if (!(task_thread_info(current)->status & TS_USEDFPU)) {
-                clts();
-                task_thread_info(current)->status |= TS_USEDFPU;
-        }
-        return restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+        clear_fpu_state(tsk);
+        task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
 #else  /* CONFIG_X86_32 */
@@ -202,6 +181,10 @@ static inline void tolerant_fwait(void)
 
 static inline void restore_fpu(struct task_struct *tsk)
 {
+        if (task_thread_info(tsk)->status & TS_XSAVE) {
+                xrstor_checking(&tsk->thread.xstate->xsave);
+                return;
+        }
         /*
          * The "nop" is needed to make the instructions the same
          * length.
@@ -227,6 +210,27 @@ static inline void restore_fpu(struct task_struct *tsk)
  */
 static inline void __save_init_fpu(struct task_struct *tsk)
 {
+        if (task_thread_info(tsk)->status & TS_XSAVE) {
+                struct xsave_struct *xstate = &tsk->thread.xstate->xsave;
+                struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
+
+                xsave(tsk);
+
+                /*
+                 * xsave header may indicate the init state of the FP.
+                 */
+                if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
+                        goto end;
+
+                if (unlikely(fx->swd & X87_FSW_ES))
+                        asm volatile("fnclex");
+
+                /*
+                 * we can do a simple return here or be paranoid :)
+                 */
+                goto clear_state;
+        }
+
         /* Use more nops than strictly needed in case the compiler
            varies code */
         alternative_input(
@@ -236,6 +240,7 @@ static inline void __save_init_fpu(struct task_struct *tsk)
                 X86_FEATURE_FXSR,
                 [fx] "m" (tsk->thread.xstate->fxsave),
                 [fsw] "m" (tsk->thread.xstate->fxsave.swd) : "memory");
+clear_state:
         /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
            is pending.  Clear the x87 state here by setting it to fixed
            values. safe_address is a random variable that should be in L1 */
@@ -245,16 +250,17 @@ static inline void __save_init_fpu(struct task_struct *tsk)
                 "fildl %[addr]",        /* set F?P to defined value */
                 X86_FEATURE_FXSAVE_LEAK,
                 [addr] "m" (safe_address));
+end:
         task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
+#endif  /* CONFIG_X86_64 */
+
 /*
  * Signal frame handlers...
  */
-extern int save_i387(struct _fpstate __user *buf);
-extern int restore_i387(struct _fpstate __user *buf);
-
-#endif  /* CONFIG_X86_64 */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
 
 static inline void __unlazy_fpu(struct task_struct *tsk)
 {
@@ -290,6 +296,37 @@ static inline void kernel_fpu_end(void)
         preempt_enable();
 }
 
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context aswell. To prevent these kernel instructions
+ * in interrupt context interact wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+static inline int irq_ts_save(void)
+{
+        /*
+         * If we are in process context, we are ok to take a spurious DNA fault.
+         * Otherwise, doing clts() in process context require pre-emption to
+         * be disabled or some heavy lifting like kernel_fpu_begin()
+         */
+        if (!in_interrupt())
+                return 0;
+
+        if (read_cr0() & X86_CR0_TS) {
+                clts();
+                return 1;
+        }
+
+        return 0;
+}
+
+static inline void irq_ts_restore(int TS_state)
+{
+        if (TS_state)
+                stts();
+}
+
 #ifdef CONFIG_X86_64
 
 static inline void save_init_fpu(struct task_struct *tsk)
@@ -360,4 +397,4 @@ static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
         }
 }
 
-#endif  /* _ASM_X86_I387_H */
+#endif /* ASM_X86__I387_H */
diff --git a/include/asm-x86/i8253.h b/include/asm-x86/i8253.h
index b51c0487fc41..15a5b530044e 100644
--- a/include/asm-x86/i8253.h
+++ b/include/asm-x86/i8253.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_I8253_H__
-#define __ASM_I8253_H__
+#ifndef ASM_X86__I8253_H
+#define ASM_X86__I8253_H
 
 /* i8253A PIT registers */
 #define PIT_MODE                0x43
@@ -15,4 +15,4 @@ extern void setup_pit_timer(void);
 #define inb_pit         inb_p
 #define outb_pit        outb_p
 
-#endif  /* __ASM_I8253_H__ */
+#endif /* ASM_X86__I8253_H */
diff --git a/include/asm-x86/i8259.h b/include/asm-x86/i8259.h
index 45d4df3e51e6..23c1b3baaecd 100644
--- a/include/asm-x86/i8259.h
+++ b/include/asm-x86/i8259.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_I8259_H__
-#define __ASM_I8259_H__
+#ifndef ASM_X86__I8259_H
+#define ASM_X86__I8259_H
 
 #include <linux/delay.h>
 
@@ -55,4 +55,9 @@ static inline void outb_pic(unsigned char value, unsigned int port)
         udelay(2);
 }
 
-#endif  /* __ASM_I8259_H__ */
+extern struct irq_chip i8259A_chip;
+
+extern void mask_8259A(void);
+extern void unmask_8259A(void);
+
+#endif /* ASM_X86__I8259_H */
diff --git a/include/asm-x86/ia32.h b/include/asm-x86/ia32.h
index 55d3abe5276f..f932f7ad51dd 100644
--- a/include/asm-x86/ia32.h
+++ b/include/asm-x86/ia32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_IA32_H
-#define _ASM_X86_64_IA32_H
+#ifndef ASM_X86__IA32_H
+#define ASM_X86__IA32_H
 
 
 #ifdef CONFIG_IA32_EMULATION
@@ -167,4 +167,4 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm);
 
 #endif /* !CONFIG_IA32_SUPPORT */
 
-#endif
+#endif /* ASM_X86__IA32_H */
diff --git a/include/asm-x86/ia32_unistd.h b/include/asm-x86/ia32_unistd.h
index 61cea9e7c5c1..dbd887d8a5a5 100644
--- a/include/asm-x86/ia32_unistd.h
+++ b/include/asm-x86/ia32_unistd.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_IA32_UNISTD_H_
-#define _ASM_X86_64_IA32_UNISTD_H_
+#ifndef ASM_X86__IA32_UNISTD_H
+#define ASM_X86__IA32_UNISTD_H
 
 /*
  * This file contains the system call numbers of the ia32 port,
@@ -15,4 +15,4 @@
 #define __NR_ia32_sigreturn     119
 #define __NR_ia32_rt_sigreturn  173
 
-#endif /* _ASM_X86_64_IA32_UNISTD_H_ */
+#endif /* ASM_X86__IA32_UNISTD_H */
diff --git a/include/asm-x86/ide.h b/include/asm-x86/ide.h
deleted file mode 100644
index cf9c98e5bdb5..000000000000
--- a/include/asm-x86/ide.h
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- *  Copyright (C) 1994-1996  Linus Torvalds & authors
- */
-
-/*
- *  This file contains the i386 architecture specific IDE code.
- */
-
-#ifndef __ASMi386_IDE_H
-#define __ASMi386_IDE_H
-
-#ifdef __KERNEL__
-
-
-#ifndef MAX_HWIFS
-# ifdef CONFIG_BLK_DEV_IDEPCI
-#define MAX_HWIFS       10
-# else
-#define MAX_HWIFS       6
-# endif
-#endif
-
-static __inline__ int ide_default_irq(unsigned long base)
-{
-        switch (base) {
-                case 0x1f0: return 14;
-                case 0x170: return 15;
-                case 0x1e8: return 11;
-                case 0x168: return 10;
-                case 0x1e0: return 8;
-                case 0x160: return 12;
-                default:
-                        return 0;
-        }
-}
-
-static __inline__ unsigned long ide_default_io_base(int index)
-{
-        /*
-         *      If PCI is present then it is not safe to poke around
-         *      the other legacy IDE ports. Only 0x1f0 and 0x170 are
-         *      defined compatibility mode ports for PCI. A user can 
-         *      override this using ide= but we must default safe.
-         */
-        if (no_pci_devices()) {
-                switch(index) {
-                        case 2: return 0x1e8;
-                        case 3: return 0x168;
-                        case 4: return 0x1e0;
-                        case 5: return 0x160;
-                }
-        }
-        switch (index) {
-                case 0: return 0x1f0;
-                case 1: return 0x170;
-                default:
-                        return 0;
-        }
-}
-
-#include <asm-generic/ide_iops.h>
-
-#endif /* __KERNEL__ */
-
-#endif /* __ASMi386_IDE_H */
diff --git a/include/asm-x86/idle.h b/include/asm-x86/idle.h
index d240e5b30a45..baa3f783d27d 100644
--- a/include/asm-x86/idle.h
+++ b/include/asm-x86/idle.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_IDLE_H
-#define _ASM_X86_64_IDLE_H 1
+#ifndef ASM_X86__IDLE_H
+#define ASM_X86__IDLE_H
 
 #define IDLE_START 1
 #define IDLE_END 2
@@ -10,4 +10,6 @@ void idle_notifier_register(struct notifier_block *n);
 void enter_idle(void);
 void exit_idle(void);
 
-#endif
+void c1e_remove_cpu(int cpu);
+
+#endif /* ASM_X86__IDLE_H */
diff --git a/include/asm-x86/intel_arch_perfmon.h b/include/asm-x86/intel_arch_perfmon.h
index fa0fd068bc2e..07c03c6c9a16 100644
--- a/include/asm-x86/intel_arch_perfmon.h
+++ b/include/asm-x86/intel_arch_perfmon.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_INTEL_ARCH_PERFMON_H
-#define _ASM_X86_INTEL_ARCH_PERFMON_H
+#ifndef ASM_X86__INTEL_ARCH_PERFMON_H
+#define ASM_X86__INTEL_ARCH_PERFMON_H
 
 #define MSR_ARCH_PERFMON_PERFCTR0               0xc1
 #define MSR_ARCH_PERFMON_PERFCTR1               0xc2
@@ -28,4 +28,4 @@ union cpuid10_eax {
         unsigned int full;
 };
 
-#endif /* _ASM_X86_INTEL_ARCH_PERFMON_H */
+#endif /* ASM_X86__INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h
index d5b11f60dbd0..72b7719523bf 100644
--- a/include/asm-x86/io.h
+++ b/include/asm-x86/io.h
@@ -1,8 +1,80 @@
-#ifndef _ASM_X86_IO_H
-#define _ASM_X86_IO_H
+#ifndef ASM_X86__IO_H
+#define ASM_X86__IO_H
 
 #define ARCH_HAS_IOREMAP_WC
 
+#include <linux/compiler.h>
+
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ * A boot-time mapping is currently limited to at most 16 pages.
+ */
+#ifndef __ASSEMBLY__
+extern void early_ioremap_init(void);
+extern void early_ioremap_clear(void);
+extern void early_ioremap_reset(void);
+extern void *early_ioremap(unsigned long offset, unsigned long size);
+extern void early_iounmap(void *addr, unsigned long size);
+extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
+#endif
+
+#define build_mmio_read(name, size, type, reg, barrier) \
+static inline type name(const volatile void __iomem *addr) \
+{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \
+:"m" (*(volatile type __force *)addr) barrier); return ret; }
+
+#define build_mmio_write(name, size, type, reg, barrier) \
+static inline void name(type val, volatile void __iomem *addr) \
+{ asm volatile("mov" size " %0,%1": :reg (val), \
+"m" (*(volatile type __force *)addr) barrier); }
+
+build_mmio_read(readb, "b", unsigned char, "=q", :"memory")
+build_mmio_read(readw, "w", unsigned short, "=r", :"memory")
+build_mmio_read(readl, "l", unsigned int, "=r", :"memory")
+
+build_mmio_read(__readb, "b", unsigned char, "=q", )
+build_mmio_read(__readw, "w", unsigned short, "=r", )
+build_mmio_read(__readl, "l", unsigned int, "=r", )
+
+build_mmio_write(writeb, "b", unsigned char, "q", :"memory")
+build_mmio_write(writew, "w", unsigned short, "r", :"memory")
+build_mmio_write(writel, "l", unsigned int, "r", :"memory")
+
+build_mmio_write(__writeb, "b", unsigned char, "q", )
+build_mmio_write(__writew, "w", unsigned short, "r", )
+build_mmio_write(__writel, "l", unsigned int, "r", )
+
+#define readb_relaxed(a) __readb(a)
+#define readw_relaxed(a) __readw(a)
+#define readl_relaxed(a) __readl(a)
+#define __raw_readb __readb
+#define __raw_readw __readw
+#define __raw_readl __readl
+
+#define __raw_writeb __writeb
+#define __raw_writew __writew
+#define __raw_writel __writel
+
+#define mmiowb() barrier()
+
+#ifdef CONFIG_X86_64
+build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
+build_mmio_read(__readq, "q", unsigned long, "=r", )
+build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
+build_mmio_write(__writeq, "q", unsigned long, "r", )
+
+#define readq_relaxed(a) __readq(a)
+#define __raw_readq __readq
+#define __raw_writeq writeq
+
+/* Let people know we have them */
+#define readq readq
+#define writeq writeq
+#endif
+
+extern int iommu_bio_merge;
+
 #ifdef CONFIG_X86_32
 # include "io_32.h"
 #else
@@ -16,4 +88,17 @@ extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
                                 unsigned long prot_val);
 extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
 
-#endif /* _ASM_X86_IO_H */
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ * A boot-time mapping is currently limited to at most 16 pages.
+ */
+extern void early_ioremap_init(void);
+extern void early_ioremap_clear(void);
+extern void early_ioremap_reset(void);
+extern void *early_ioremap(unsigned long offset, unsigned long size);
+extern void early_iounmap(void *addr, unsigned long size);
+extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
+
+
+#endif /* ASM_X86__IO_H */
diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h
index 049e81e797a0..4f7d878bda18 100644
--- a/include/asm-x86/io_32.h
+++ b/include/asm-x86/io_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IO_H
-#define _ASM_IO_H
+#ifndef ASM_X86__IO_32_H
+#define ASM_X86__IO_32_H
 
 #include <linux/string.h>
 #include <linux/compiler.h>
@@ -110,6 +110,8 @@ static inline void *phys_to_virt(unsigned long address)
  */
 extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+                                unsigned long prot_val);
 
 /*
  * The default ioremap() behavior is non-cached:
@@ -122,18 +124,6 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
 extern void iounmap(volatile void __iomem *addr);
 
 /*
- * early_ioremap() and early_iounmap() are for temporary early boot-time
- * mappings, before the real ioremap() is functional.
- * A boot-time mapping is currently limited to at most 16 pages.
- */
-extern void early_ioremap_init(void);
-extern void early_ioremap_clear(void);
-extern void early_ioremap_reset(void);
-extern void *early_ioremap(unsigned long offset, unsigned long size);
-extern void early_iounmap(void *addr, unsigned long size);
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
-
-/*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
 #define isa_virt_to_bus virt_to_phys
@@ -149,55 +139,6 @@ extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 #define virt_to_bus virt_to_phys
 #define bus_to_virt phys_to_virt
 
-/*
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the x86 architecture, we just read/write the
- * memory location directly.
- */
-
-static inline unsigned char readb(const volatile void __iomem *addr)
-{
-        return *(volatile unsigned char __force *)addr;
-}
-
-static inline unsigned short readw(const volatile void __iomem *addr)
-{
-        return *(volatile unsigned short __force *)addr;
-}
-
-static inline unsigned int readl(const volatile void __iomem *addr)
-{
-        return *(volatile unsigned int __force *) addr;
-}
-
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
-#define __raw_readb readb
-#define __raw_readw readw
-#define __raw_readl readl
-
-static inline void writeb(unsigned char b, volatile void __iomem *addr)
-{
-        *(volatile unsigned char __force *)addr = b;
-}
-
-static inline void writew(unsigned short b, volatile void __iomem *addr)
-{
-        *(volatile unsigned short __force *)addr = b;
-}
-
-static inline void writel(unsigned int b, volatile void __iomem *addr)
-{
-        *(volatile unsigned int __force *)addr = b;
-}
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
-
-#define mmiowb()
-
 static inline void
 memset_io(volatile void __iomem *addr, unsigned char val, int count)
 {
@@ -340,4 +281,4 @@ BUILDIO(b, b, char)
 BUILDIO(w, w, short)
 BUILDIO(l, , int)
 
-#endif
+#endif /* ASM_X86__IO_32_H */
diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h
index 0930bedf9e4d..64429e9431a8 100644
--- a/include/asm-x86/io_64.h
+++ b/include/asm-x86/io_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IO_H
-#define _ASM_IO_H
+#ifndef ASM_X86__IO_64_H
+#define ASM_X86__IO_64_H
 
 
 /*
@@ -175,6 +175,8 @@ extern void early_iounmap(void *addr, unsigned long size);
  */
 extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+                                unsigned long prot_val);
 
 /*
  * The default ioremap() behavior is non-cached:
@@ -204,77 +206,6 @@ extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 #define virt_to_bus virt_to_phys
 #define bus_to_virt phys_to_virt
 
-/*
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the x86 architecture, we just read/write the
- * memory location directly.
- */
-
-static inline __u8 __readb(const volatile void __iomem *addr)
-{
-        return *(__force volatile __u8 *)addr;
-}
-
-static inline __u16 __readw(const volatile void __iomem *addr)
-{
-        return *(__force volatile __u16 *)addr;
-}
-
-static __always_inline __u32 __readl(const volatile void __iomem *addr)
-{
-        return *(__force volatile __u32 *)addr;
-}
-
-static inline __u64 __readq(const volatile void __iomem *addr)
-{
-        return *(__force volatile __u64 *)addr;
-}
-
-#define readb(x) __readb(x)
-#define readw(x) __readw(x)
-#define readl(x) __readl(x)
-#define readq(x) __readq(x)
-#define readb_relaxed(a) readb(a)
-#define readw_relaxed(a) readw(a)
-#define readl_relaxed(a) readl(a)
-#define readq_relaxed(a) readq(a)
-#define __raw_readb readb
-#define __raw_readw readw
-#define __raw_readl readl
-#define __raw_readq readq
-
-#define mmiowb()
-
-static inline void __writel(__u32 b, volatile void __iomem *addr)
-{
-        *(__force volatile __u32 *)addr = b;
-}
-
-static inline void __writeq(__u64 b, volatile void __iomem *addr)
-{
-        *(__force volatile __u64 *)addr = b;
-}
-
-static inline void __writeb(__u8 b, volatile void __iomem *addr)
-{
-        *(__force volatile __u8 *)addr = b;
-}
-
-static inline void __writew(__u16 b, volatile void __iomem *addr)
-{
-        *(__force volatile __u16 *)addr = b;
-}
-
-#define writeq(val, addr) __writeq((val), (addr))
-#define writel(val, addr) __writel((val), (addr))
-#define writew(val, addr) __writew((val), (addr))
-#define writeb(val, addr) __writeb((val), (addr))
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
-#define __raw_writeq writeq
-
 void __memcpy_fromio(void *, unsigned long, unsigned);
 void __memcpy_toio(unsigned long, const void *, unsigned);
 
@@ -304,7 +235,6 @@ void memset_io(volatile void __iomem *a, int b, size_t c);
 
 #define flush_write_buffers()
 
-extern int iommu_bio_merge;
 #define BIO_VMERGE_BOUNDARY iommu_bio_merge
 
 /*
@@ -314,4 +244,4 @@ extern int iommu_bio_merge;
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__IO_64_H */
diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h
index d593e14f0341..8ec68a50cf10 100644
--- a/include/asm-x86/io_apic.h
+++ b/include/asm-x86/io_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_IO_APIC_H
-#define __ASM_IO_APIC_H
+#ifndef ASM_X86__IO_APIC_H
+#define ASM_X86__IO_APIC_H
 
 #include <linux/types.h>
 #include <asm/mpspec.h>
@@ -11,6 +11,15 @@
  * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
  */
 
+/* I/O Unit Redirection Table */
+#define IO_APIC_REDIR_VECTOR_MASK       0x000FF
+#define IO_APIC_REDIR_DEST_LOGICAL      0x00800
+#define IO_APIC_REDIR_DEST_PHYSICAL     0x00000
+#define IO_APIC_REDIR_SEND_PENDING      (1 << 12)
+#define IO_APIC_REDIR_REMOTE_IRR        (1 << 14)
+#define IO_APIC_REDIR_LEVEL_TRIGGER     (1 << 15)
+#define IO_APIC_REDIR_MASKED            (1 << 16)
+
 /*
  * The structure of the IO-APIC:
  */
@@ -98,6 +107,20 @@ struct IO_APIC_route_entry {
 
 } __attribute__ ((packed));
 
+struct IR_IO_APIC_route_entry {
+        __u64   vector          : 8,
+                zero            : 3,
+                index2          : 1,
+                delivery_status : 1,
+                polarity        : 1,
+                irr             : 1,
+                trigger         : 1,
+                mask            : 1,
+                reserved        : 31,
+                format          : 1,
+                index           : 15;
+} __attribute__ ((packed));
+
 #ifdef CONFIG_X86_IO_APIC
 
 /*
@@ -112,21 +135,32 @@ extern int nr_ioapic_registers[MAX_IO_APICS];
 
 #define MP_MAX_IOAPIC_PIN 127
 
-struct mp_ioapic_routing {
-        int apic_id;
-        int gsi_base;
-        int gsi_end;
-        DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+struct mp_config_ioapic {
+        unsigned long mp_apicaddr;
+        unsigned int mp_apicid;
+        unsigned char mp_type;
+        unsigned char mp_apicver;
+        unsigned char mp_flags;
+};
+
+struct mp_config_intsrc {
+        unsigned int mp_dstapic;
+        unsigned char mp_type;
+        unsigned char mp_irqtype;
+        unsigned short mp_irqflag;
+        unsigned char mp_srcbus;
+        unsigned char mp_srcbusirq;
+        unsigned char mp_dstirq;
 };
 
 /* I/O APIC entries */
-extern struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
 
 /* MP IRQ source entries */
-extern struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
 /* non-0 if default (table-less) MP configuration */
 extern int mpc_default_type;
@@ -137,6 +171,9 @@ extern int sis_apic_bug;
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
+/* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
+extern int timer_through_8259;
+
 static inline void disable_ioapic_setup(void)
 {
         skip_ioapic_setup = 1;
@@ -160,8 +197,16 @@ extern int io_apic_set_pci_routing(int ioapic, int pin, int irq,
 extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
 
+#ifdef CONFIG_X86_64
+extern int save_mask_IO_APIC_setup(void);
+extern void restore_IO_APIC_setup(void);
+extern void reinit_intr_remapped_IO_APIC(int);
+#endif
+
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
+static const int timer_through_8259 = 0;
+static inline void ioapic_init_mappings(void) { }
 #endif
 
-#endif
+#endif /* ASM_X86__IO_APIC_H */
diff --git a/include/asm-x86/ioctls.h b/include/asm-x86/ioctls.h
index c0c338bd4068..336603512399 100644
--- a/include/asm-x86/ioctls.h
+++ b/include/asm-x86/ioctls.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_IOCTLS_H
-#define _ASM_X86_IOCTLS_H
+#ifndef ASM_X86__IOCTLS_H
+#define ASM_X86__IOCTLS_H
 
 #include <asm/ioctl.h>
 
@@ -85,4 +85,4 @@
 
 #define TIOCSER_TEMT    0x01    /* Transmitter physically empty */
 
-#endif
+#endif /* ASM_X86__IOCTLS_H */
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
index 07862fdd23c0..546ad3110fea 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -1,29 +1,46 @@
-#ifndef _ASM_X8664_GART_H
-#define _ASM_X8664_GART_H 1
+#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_mapping_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
-#ifdef CONFIG_IOMMU
+extern int dmar_disabled;
+
+extern unsigned long iommu_num_pages(unsigned long addr, unsigned long len);
+
+#ifdef CONFIG_GART_IOMMU
+extern int gart_iommu_aperture;
+extern int gart_iommu_aperture_allowed;
+extern int gart_iommu_aperture_disabled;
+
+extern void early_gart_iommu_check(void);
 extern void gart_iommu_init(void);
 extern void gart_iommu_shutdown(void);
 extern void __init gart_parse_options(char *);
-extern void iommu_hole_init(void);
-extern int fallback_aper_order;
-extern int fallback_aper_force;
-extern int iommu_aperture;
-extern int iommu_aperture_allowed;
-extern int iommu_aperture_disabled;
-extern int fix_aperture;
+extern void gart_iommu_hole_init(void);
+
 #else
-#define iommu_aperture 0
-#define iommu_aperture_allowed 0
+#define gart_iommu_aperture            0
+#define gart_iommu_aperture_allowed    0
+#define gart_iommu_aperture_disabled   1
 
+static inline void 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)
+{
+}
+static inline void gart_iommu_hole_init(void)
+{
+}
 #endif
 
-#endif
+#endif /* ASM_X86__IOMMU_H */
diff --git a/include/asm-x86/ipcbuf.h b/include/asm-x86/ipcbuf.h
index ee678fd51594..910304fbdc8f 100644
--- a/include/asm-x86/ipcbuf.h
+++ b/include/asm-x86/ipcbuf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_IPCBUF_H
-#define _ASM_X86_IPCBUF_H
+#ifndef ASM_X86__IPCBUF_H
+#define ASM_X86__IPCBUF_H
 
 /*
  * The ipc64_perm structure for x86 architecture.
@@ -25,4 +25,4 @@ struct ipc64_perm {
         unsigned long           __unused2;
 };
 
-#endif /* _ASM_X86_IPCBUF_H */
+#endif /* ASM_X86__IPCBUF_H */
diff --git a/include/asm-x86/ipi.h b/include/asm-x86/ipi.h
index ecc80f341f37..30a692cfaff8 100644
--- a/include/asm-x86/ipi.h
+++ b/include/asm-x86/ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_IPI_H
-#define __ASM_IPI_H
+#ifndef ASM_X86__IPI_H
+#define ASM_X86__IPI_H
 
 /*
  * Copyright 2004 James Cleverdon, IBM.
@@ -20,6 +20,7 @@
 
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
+#include <asm/smp.h>
 
 /*
  * the following functions deal with sending IPIs between CPUs.
@@ -48,6 +49,12 @@ static inline int __prepare_ICR2(unsigned int mask)
         return SET_APIC_DEST_FIELD(mask);
 }
 
+static inline void __xapic_wait_icr_idle(void)
+{
+        while (native_apic_mem_read(APIC_ICR) & APIC_ICR_BUSY)
+                cpu_relax();
+}
+
 static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
                                        unsigned int dest)
 {
@@ -63,7 +70,7 @@ static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
         /*
          * Wait for idle.
          */
-        apic_wait_icr_idle();
+        __xapic_wait_icr_idle();
 
         /*
          * No need to touch the target chip field
@@ -73,7 +80,7 @@ static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
         /*
          * Send the IPI. The write to APIC_ICR fires this off.
          */
-        apic_write(APIC_ICR, cfg);
+        native_apic_mem_write(APIC_ICR, cfg);
 }
 
 /*
@@ -91,13 +98,13 @@ static inline void __send_IPI_dest_field(unsigned int mask, int vector,
         if (unlikely(vector == NMI_VECTOR))
                 safe_apic_wait_icr_idle();
         else
-                apic_wait_icr_idle();
+                __xapic_wait_icr_idle();
 
         /*
          * prepare target chip field
          */
         cfg = __prepare_ICR2(mask);
-        apic_write(APIC_ICR2, cfg);
+        native_apic_mem_write(APIC_ICR2, cfg);
 
         /*
          * program the ICR
@@ -107,7 +114,7 @@ static inline void __send_IPI_dest_field(unsigned int mask, int vector,
         /*
          * Send the IPI. The write to APIC_ICR fires this off.
          */
-        apic_write(APIC_ICR, cfg);
+        native_apic_mem_write(APIC_ICR, cfg);
 }
 
 static inline void send_IPI_mask_sequence(cpumask_t mask, int vector)
@@ -121,11 +128,11 @@ static inline void send_IPI_mask_sequence(cpumask_t mask, int vector)
          * - mbligh
          */
         local_irq_save(flags);
-        for_each_cpu_mask(query_cpu, mask) {
+        for_each_cpu_mask_nr(query_cpu, mask) {
                 __send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu),
                                       vector, APIC_DEST_PHYSICAL);
         }
         local_irq_restore(flags);
 }
 
-#endif /* __ASM_IPI_H */
+#endif /* ASM_X86__IPI_H */
diff --git a/include/asm-x86/irq.h b/include/asm-x86/irq.h
index 7ba905465a53..1e5f2909c1db 100644
--- a/include/asm-x86/irq.h
+++ b/include/asm-x86/irq.h
@@ -1,5 +1,50 @@
-#ifdef CONFIG_X86_32
-# include "irq_32.h"
+#ifndef ASM_X86__IRQ_H
+#define ASM_X86__IRQ_H
+/*
+ *      (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ *      IRQ/IPI changes taken from work by Thomas Radke
+ *      <tomsoft@informatik.tu-chemnitz.de>
+ */
+
+#include <asm/apicdef.h>
+#include <asm/irq_vectors.h>
+
+static inline int irq_canonicalize(int irq)
+{
+        return ((irq == 2) ? 9 : irq);
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+# define ARCH_HAS_NMI_WATCHDOG
+#endif
+
+#ifdef CONFIG_4KSTACKS
+  extern void irq_ctx_init(int cpu);
+  extern void irq_ctx_exit(int cpu);
+# define __ARCH_HAS_DO_SOFTIRQ
 #else
-# include "irq_64.h"
+# define irq_ctx_init(cpu) do { } while (0)
+# define irq_ctx_exit(cpu) do { } while (0)
+# ifdef CONFIG_X86_64
+#  define __ARCH_HAS_DO_SOFTIRQ
+# endif
+#endif
+
+#ifdef CONFIG_IRQBALANCE
+extern int irqbalance_disable(char *str);
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+#include <linux/cpumask.h>
+extern void fixup_irqs(cpumask_t map);
 #endif
+
+extern unsigned int do_IRQ(struct pt_regs *regs);
+extern void init_IRQ(void);
+extern void native_init_IRQ(void);
+
+/* Interrupt vector management */
+extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
+
+#endif /* ASM_X86__IRQ_H */
diff --git a/include/asm-x86/irq_32.h b/include/asm-x86/irq_32.h
deleted file mode 100644
index 0b79f3185243..000000000000
--- a/include/asm-x86/irq_32.h
+++ /dev/null
@@ -1,51 +0,0 @@
-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
-
-/*
- *      linux/include/asm/irq.h
- *
- *      (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *      IRQ/IPI changes taken from work by Thomas Radke
- *      <tomsoft@informatik.tu-chemnitz.de>
- */
-
-#include <linux/sched.h>
-/* include comes from machine specific directory */
-#include "irq_vectors.h"
-#include <asm/thread_info.h>
-
-static inline int irq_canonicalize(int irq)
-{
-        return ((irq == 2) ? 9 : irq);
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-# define ARCH_HAS_NMI_WATCHDOG          /* See include/linux/nmi.h */
-#endif
-
-#ifdef CONFIG_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
-#else
-# define irq_ctx_init(cpu) do { } while (0)
-# define irq_ctx_exit(cpu) do { } while (0)
-#endif
-
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
-
-#ifdef CONFIG_HOTPLUG_CPU
-extern void fixup_irqs(cpumask_t map);
-#endif
-
-unsigned int do_IRQ(struct pt_regs *regs);
-void init_IRQ(void);
-void __init native_init_IRQ(void);
-
-/* Interrupt vector management */
-extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
-
-#endif /* _ASM_IRQ_H */
diff --git a/include/asm-x86/irq_64.h b/include/asm-x86/irq_64.h
deleted file mode 100644
index 083d35a62c94..000000000000
--- a/include/asm-x86/irq_64.h
+++ /dev/null
@@ -1,51 +0,0 @@
-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
-
-/*
- *      linux/include/asm/irq.h
- *
- *      (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *      IRQ/IPI changes taken from work by Thomas Radke
- *      <tomsoft@informatik.tu-chemnitz.de>
- */
-
-#define TIMER_IRQ 0
-
-/*
- * 16 8259A IRQ's, 208 potential APIC interrupt sources.
- * Right now the APIC is mostly only used for SMP.
- * 256 vectors is an architectural limit. (we can have
- * more than 256 devices theoretically, but they will
- * have to use shared interrupts)
- * Since vectors 0x00-0x1f are used/reserved for the CPU,
- * the usable vector space is 0x20-0xff (224 vectors)
- */
-
-/*
- * The maximum number of vectors supported by x86_64 processors
- * is limited to 256. For processors other than x86_64, NR_VECTORS
- * should be changed accordingly.
- */
-#define NR_VECTORS 256
-
-#define FIRST_SYSTEM_VECTOR     0xef   /* duplicated in hw_irq.h */
-
-#define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
-#define NR_IRQ_VECTORS NR_IRQS
-
-static inline int irq_canonicalize(int irq)
-{
-        return ((irq == 2) ? 9 : irq);
-}
-
-#define ARCH_HAS_NMI_WATCHDOG           /* See include/linux/nmi.h */
-
-#ifdef CONFIG_HOTPLUG_CPU
-#include <linux/cpumask.h>
-extern void fixup_irqs(cpumask_t map);
-#endif
-
-#define __ARCH_HAS_DO_SOFTIRQ 1
-
-#endif /* _ASM_IRQ_H */
diff --git a/include/asm-x86/irq_regs_32.h b/include/asm-x86/irq_regs_32.h
index 3368b20c0b48..316a3b258871 100644
--- a/include/asm-x86/irq_regs_32.h
+++ b/include/asm-x86/irq_regs_32.h
@@ -4,8 +4,8 @@
  *
  * Jeremy Fitzhardinge <jeremy@goop.org>
  */
-#ifndef _ASM_I386_IRQ_REGS_H
-#define _ASM_I386_IRQ_REGS_H
+#ifndef ASM_X86__IRQ_REGS_32_H
+#define ASM_X86__IRQ_REGS_32_H
 
 #include <asm/percpu.h>
 
@@ -26,4 +26,4 @@ static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
         return old_regs;
 }
 
-#endif /* _ASM_I386_IRQ_REGS_H */
+#endif /* ASM_X86__IRQ_REGS_32_H */
diff --git a/include/asm-x86/irq_remapping.h b/include/asm-x86/irq_remapping.h
new file mode 100644
index 000000000000..78242c6ffa58
--- /dev/null
+++ b/include/asm-x86/irq_remapping.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_IRQ_REMAPPING_H
+#define _ASM_IRQ_REMAPPING_H
+
+extern int x2apic;
+
+#define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8)
+
+#endif
diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h
new file mode 100644
index 000000000000..c5d2d767a1f3
--- /dev/null
+++ b/include/asm-x86/irq_vectors.h
@@ -0,0 +1,182 @@
+#ifndef ASM_X86__IRQ_VECTORS_H
+#define ASM_X86__IRQ_VECTORS_H
+
+#include <linux/threads.h>
+
+#define NMI_VECTOR              0x02
+
+/*
+ * IDT vectors usable for external interrupt sources start
+ * at 0x20:
+ */
+#define FIRST_EXTERNAL_VECTOR   0x20
+
+#ifdef CONFIG_X86_32
+# define SYSCALL_VECTOR         0x80
+#else
+# define IA32_SYSCALL_VECTOR    0x80
+#endif
+
+/*
+ * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
+ * cleanup after irq migration on 64 bit.
+ */
+#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR
+
+/*
+ * Vectors 0x20-0x2f are used for ISA interrupts on 32 bit.
+ * Vectors 0x30-0x3f are used for ISA interrupts on 64 bit.
+ */
+#ifdef CONFIG_X86_32
+#define IRQ0_VECTOR             (FIRST_EXTERNAL_VECTOR)
+#else
+#define IRQ0_VECTOR             (FIRST_EXTERNAL_VECTOR + 0x10)
+#endif
+#define IRQ1_VECTOR             (IRQ0_VECTOR + 1)
+#define IRQ2_VECTOR             (IRQ0_VECTOR + 2)
+#define IRQ3_VECTOR             (IRQ0_VECTOR + 3)
+#define IRQ4_VECTOR             (IRQ0_VECTOR + 4)
+#define IRQ5_VECTOR             (IRQ0_VECTOR + 5)
+#define IRQ6_VECTOR             (IRQ0_VECTOR + 6)
+#define IRQ7_VECTOR             (IRQ0_VECTOR + 7)
+#define IRQ8_VECTOR             (IRQ0_VECTOR + 8)
+#define IRQ9_VECTOR             (IRQ0_VECTOR + 9)
+#define IRQ10_VECTOR            (IRQ0_VECTOR + 10)
+#define IRQ11_VECTOR            (IRQ0_VECTOR + 11)
+#define IRQ12_VECTOR            (IRQ0_VECTOR + 12)
+#define IRQ13_VECTOR            (IRQ0_VECTOR + 13)
+#define IRQ14_VECTOR            (IRQ0_VECTOR + 14)
+#define IRQ15_VECTOR            (IRQ0_VECTOR + 15)
+
+/*
+ * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
+ *
+ *  some of the following vectors are 'rare', they are merged
+ *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
+ *  TLB, reschedule and local APIC vectors are performance-critical.
+ *
+ *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
+ */
+#ifdef CONFIG_X86_32
+
+# define SPURIOUS_APIC_VECTOR           0xff
+# define ERROR_APIC_VECTOR              0xfe
+# define INVALIDATE_TLB_VECTOR          0xfd
+# define RESCHEDULE_VECTOR              0xfc
+# define CALL_FUNCTION_VECTOR           0xfb
+# define CALL_FUNCTION_SINGLE_VECTOR    0xfa
+# define THERMAL_APIC_VECTOR            0xf0
+
+#else
+
+#define SPURIOUS_APIC_VECTOR            0xff
+#define ERROR_APIC_VECTOR               0xfe
+#define RESCHEDULE_VECTOR               0xfd
+#define CALL_FUNCTION_VECTOR            0xfc
+#define CALL_FUNCTION_SINGLE_VECTOR     0xfb
+#define THERMAL_APIC_VECTOR             0xfa
+#define THRESHOLD_APIC_VECTOR           0xf9
+#define UV_BAU_MESSAGE                  0xf8
+#define INVALIDATE_TLB_VECTOR_END       0xf7
+#define INVALIDATE_TLB_VECTOR_START     0xf0    /* f0-f7 used for TLB flush */
+
+#define NUM_INVALIDATE_TLB_VECTORS      8
+
+#endif
+
+/*
+ * Local APIC timer IRQ vector is on a different priority level,
+ * to work around the 'lost local interrupt if more than 2 IRQ
+ * sources per level' errata.
+ */
+#define LOCAL_TIMER_VECTOR      0xef
+
+/*
+ * First APIC vector available to drivers: (vectors 0x30-0xee) we
+ * start at 0x31(0x41) to spread out vectors evenly between priority
+ * levels. (0x80 is the syscall vector)
+ */
+#ifdef CONFIG_X86_32
+# define FIRST_DEVICE_VECTOR    0x31
+#else
+# define FIRST_DEVICE_VECTOR    (IRQ15_VECTOR + 2)
+#endif
+
+#define NR_VECTORS              256
+
+#define FPU_IRQ                 13
+
+#define FIRST_VM86_IRQ          3
+#define LAST_VM86_IRQ           15
+#define invalid_vm86_irq(irq)   ((irq) < 3 || (irq) > 15)
+
+#ifdef CONFIG_X86_64
+# if NR_CPUS < MAX_IO_APICS
+#  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
+# else
+#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
+# endif
+# define NR_IRQ_VECTORS NR_IRQS
+
+#elif !defined(CONFIG_X86_VOYAGER)
+
+# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
+
+#  define NR_IRQS               224
+
+#  if (224 >= 32 * NR_CPUS)
+#   define NR_IRQ_VECTORS       NR_IRQS
+#  else
+#   define NR_IRQ_VECTORS       (32 * NR_CPUS)
+#  endif
+
+# else /* IO_APIC || PARAVIRT */
+
+#  define NR_IRQS               16
+#  define NR_IRQ_VECTORS        NR_IRQS
+
+# endif
+
+#else /* !VISWS && !VOYAGER */
+
+# define NR_IRQS                224
+# define NR_IRQ_VECTORS         NR_IRQS
+
+#endif /* VISWS */
+
+/* Voyager specific defines */
+/* These define the CPIs we use in linux */
+#define VIC_CPI_LEVEL0                  0
+#define VIC_CPI_LEVEL1                  1
+/* now the fake CPIs */
+#define VIC_TIMER_CPI                   2
+#define VIC_INVALIDATE_CPI              3
+#define VIC_RESCHEDULE_CPI              4
+#define VIC_ENABLE_IRQ_CPI              5
+#define VIC_CALL_FUNCTION_CPI           6
+#define VIC_CALL_FUNCTION_SINGLE_CPI    7
+
+/* Now the QIC CPIs:  Since we don't need the two initial levels,
+ * these are 2 less than the VIC CPIs */
+#define QIC_CPI_OFFSET                  1
+#define QIC_TIMER_CPI                   (VIC_TIMER_CPI - QIC_CPI_OFFSET)
+#define QIC_INVALIDATE_CPI              (VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
+#define QIC_RESCHEDULE_CPI              (VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
+#define QIC_ENABLE_IRQ_CPI              (VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_CPI           (VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_SINGLE_CPI    (VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
+
+#define VIC_START_FAKE_CPI              VIC_TIMER_CPI
+#define VIC_END_FAKE_CPI                VIC_CALL_FUNCTION_SINGLE_CPI
+
+/* this is the SYS_INT CPI. */
+#define VIC_SYS_INT                     8
+#define VIC_CMN_INT                     15
+
+/* This is the boot CPI for alternate processors.  It gets overwritten
+ * by the above once the system has activated all available processors */
+#define VIC_CPU_BOOT_CPI                VIC_CPI_LEVEL0
+#define VIC_CPU_BOOT_ERRATA_CPI         (VIC_CPI_LEVEL0 + 8)
+
+
+#endif /* ASM_X86__IRQ_VECTORS_H */
diff --git a/include/asm-x86/irqflags.h b/include/asm-x86/irqflags.h
index c242527f970e..424acb48cd61 100644
--- a/include/asm-x86/irqflags.h
+++ b/include/asm-x86/irqflags.h
@@ -111,14 +111,35 @@ static inline unsigned long __raw_local_irq_save(void)
 #define DISABLE_INTERRUPTS(x)   cli
 
 #ifdef CONFIG_X86_64
+#define SWAPGS  swapgs
+/*
+ * Currently paravirt can't handle swapgs nicely when we
+ * don't have a stack we can rely on (such as a user space
+ * stack).  So we either find a way around these or just fault
+ * and emulate if a guest tries to call swapgs directly.
+ *
+ * Either way, this is a good way to document that we don't
+ * have a reliable stack. x86_64 only.
+ */
+#define SWAPGS_UNSAFE_STACK     swapgs
+
+#define PARAVIRT_ADJUST_EXCEPTION_FRAME /*  */
+
 #define INTERRUPT_RETURN        iretq
-#define ENABLE_INTERRUPTS_SYSCALL_RET                   \
-                        movq    %gs:pda_oldrsp, %rsp;   \
-                        swapgs;                         \
-                        sysretq;
+#define USERGS_SYSRET64                         \
+        swapgs;                                 \
+        sysretq;
+#define USERGS_SYSRET32                         \
+        swapgs;                                 \
+        sysretl
+#define ENABLE_INTERRUPTS_SYSEXIT32             \
+        swapgs;                                 \
+        sti;                                    \
+        sysexit
+
 #else
 #define INTERRUPT_RETURN                iret
-#define ENABLE_INTERRUPTS_SYSCALL_RET   sti; sysexit
+#define ENABLE_INTERRUPTS_SYSEXIT       sti; sysexit
 #define GET_CR0_INTO_EAX                movl %cr0, %eax
 #endif
 
@@ -169,18 +190,6 @@ static inline void trace_hardirqs_fixup(void)
 #else
 
 #ifdef CONFIG_X86_64
-/*
- * Currently paravirt can't handle swapgs nicely when we
- * don't have a stack we can rely on (such as a user space
- * stack).  So we either find a way around these or just fault
- * and emulate if a guest tries to call swapgs directly.
- *
- * Either way, this is a good way to document that we don't
- * have a reliable stack. x86_64 only.
- */
-#define SWAPGS_UNSAFE_STACK     swapgs
-#define ARCH_TRACE_IRQS_ON              call trace_hardirqs_on_thunk
-#define ARCH_TRACE_IRQS_OFF             call trace_hardirqs_off_thunk
 #define ARCH_LOCKDEP_SYS_EXIT           call lockdep_sys_exit_thunk
 #define ARCH_LOCKDEP_SYS_EXIT_IRQ       \
         TRACE_IRQS_ON; \
@@ -192,24 +201,6 @@ static inline void trace_hardirqs_fixup(void)
         TRACE_IRQS_OFF;
 
 #else
-#define ARCH_TRACE_IRQS_ON                      \
-        pushl %eax;                             \
-        pushl %ecx;                             \
-        pushl %edx;                             \
-        call trace_hardirqs_on;                 \
-        popl %edx;                              \
-        popl %ecx;                              \
-        popl %eax;
-
-#define ARCH_TRACE_IRQS_OFF                     \
-        pushl %eax;                             \
-        pushl %ecx;                             \
-        pushl %edx;                             \
-        call trace_hardirqs_off;                \
-        popl %edx;                              \
-        popl %ecx;                              \
-        popl %eax;
-
 #define ARCH_LOCKDEP_SYS_EXIT                   \
         pushl %eax;                             \
         pushl %ecx;                             \
@@ -223,8 +214,8 @@ static inline void trace_hardirqs_fixup(void)
 #endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
-#  define TRACE_IRQS_ON         ARCH_TRACE_IRQS_ON
-#  define TRACE_IRQS_OFF        ARCH_TRACE_IRQS_OFF
+#  define TRACE_IRQS_ON         call trace_hardirqs_on_thunk;
+#  define TRACE_IRQS_OFF        call trace_hardirqs_off_thunk;
 #else
 #  define TRACE_IRQS_ON
 #  define TRACE_IRQS_OFF
diff --git a/include/asm-x86/ist.h b/include/asm-x86/ist.h
index 6ec6ceed95a7..35a2fe9bc921 100644
--- a/include/asm-x86/ist.h
+++ b/include/asm-x86/ist.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IST_H
-#define _ASM_IST_H
+#ifndef ASM_X86__IST_H
+#define ASM_X86__IST_H
 
 /*
  * Include file for the interface to IST BIOS
@@ -31,4 +31,4 @@ struct ist_info {
 extern struct ist_info ist_info;
 
 #endif  /* __KERNEL__ */
-#endif  /* _ASM_IST_H */
+#endif /* ASM_X86__IST_H */
diff --git a/include/asm-x86/k8.h b/include/asm-x86/k8.h
index 452e2b696ff4..2bbaf4370a55 100644
--- a/include/asm-x86/k8.h
+++ b/include/asm-x86/k8.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_K8_H
-#define _ASM_K8_H 1
+#ifndef ASM_X86__K8_H
+#define ASM_X86__K8_H
 
 #include <linux/pci.h>
 
@@ -12,4 +12,4 @@ extern int cache_k8_northbridges(void);
 extern void k8_flush_garts(void);
 extern int k8_scan_nodes(unsigned long start, unsigned long end);
 
-#endif
+#endif /* ASM_X86__K8_H */
diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h
index 96651bb59ba1..5ec3ad3e825c 100644
--- a/include/asm-x86/kdebug.h
+++ b/include/asm-x86/kdebug.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_KDEBUG_H
-#define _ASM_X86_KDEBUG_H
+#ifndef ASM_X86__KDEBUG_H
+#define ASM_X86__KDEBUG_H
 
 #include <linux/notifier.h>
 
@@ -35,4 +35,4 @@ extern void show_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
 
-#endif
+#endif /* ASM_X86__KDEBUG_H */
diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h
index 8f855a15f64d..ea09600d6129 100644
--- a/include/asm-x86/kexec.h
+++ b/include/asm-x86/kexec.h
@@ -1,5 +1,5 @@
-#ifndef _KEXEC_H
-#define _KEXEC_H
+#ifndef ASM_X86__KEXEC_H
+#define ASM_X86__KEXEC_H
 
 #ifdef CONFIG_X86_32
 # define PA_CONTROL_PAGE        0
@@ -10,14 +10,15 @@
 # define VA_PTE_0               5
 # define PA_PTE_1               6
 # define VA_PTE_1               7
+# define PA_SWAP_PAGE           8
 # ifdef CONFIG_X86_PAE
-#  define PA_PMD_0              8
-#  define VA_PMD_0              9
-#  define PA_PMD_1              10
-#  define VA_PMD_1              11
-#  define PAGES_NR              12
+#  define PA_PMD_0              9
+#  define VA_PMD_0              10
+#  define PA_PMD_1              11
+#  define VA_PMD_1              12
+#  define PAGES_NR              13
 # else
-#  define PAGES_NR              8
+#  define PAGES_NR              9
 # endif
 #else
 # define PA_CONTROL_PAGE        0
@@ -40,6 +41,10 @@
 # define PAGES_NR               17
 #endif
 
+#ifdef CONFIG_X86_32
+# define KEXEC_CONTROL_CODE_MAX_SIZE    2048
+#endif
+
 #ifndef __ASSEMBLY__
 
 #include <linux/string.h>
@@ -62,7 +67,7 @@
 /* Maximum address we can use for the control code buffer */
 # define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
 
-# define KEXEC_CONTROL_CODE_SIZE        4096
+# define KEXEC_CONTROL_PAGE_SIZE        4096
 
 /* The native architecture */
 # define KEXEC_ARCH KEXEC_ARCH_386
@@ -78,7 +83,7 @@
 # define KEXEC_CONTROL_MEMORY_LIMIT     (0xFFFFFFFFFFUL)
 
 /* Allocate one page for the pdp and the second for the code */
-# define KEXEC_CONTROL_CODE_SIZE  (4096UL + 4096UL)
+# define KEXEC_CONTROL_PAGE_SIZE  (4096UL + 4096UL)
 
 /* The native architecture */
 # define KEXEC_ARCH KEXEC_ARCH_X86_64
@@ -152,11 +157,12 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 }
 
 #ifdef CONFIG_X86_32
-asmlinkage NORET_TYPE void
+asmlinkage unsigned long
 relocate_kernel(unsigned long indirection_page,
                 unsigned long control_page,
                 unsigned long start_address,
-                unsigned int has_pae) ATTRIB_NORET;
+                unsigned int has_pae,
+                unsigned int preserve_context);
 #else
 NORET_TYPE void
 relocate_kernel(unsigned long indirection_page,
@@ -166,4 +172,4 @@ relocate_kernel(unsigned long indirection_page,
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* _KEXEC_H */
+#endif /* ASM_X86__KEXEC_H */
diff --git a/include/asm-x86/kgdb.h b/include/asm-x86/kgdb.h
index 484c47554f3b..d283863354de 100644
--- a/include/asm-x86/kgdb.h
+++ b/include/asm-x86/kgdb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_KGDB_H_
-#define _ASM_KGDB_H_
+#ifndef ASM_X86__KGDB_H
+#define ASM_X86__KGDB_H
 
 /*
  * Copyright (C) 2001-2004 Amit S. Kale
@@ -39,12 +39,13 @@ enum regnames {
         GDB_FS,                 /* 14 */
         GDB_GS,                 /* 15 */
 };
+#define NUMREGBYTES             ((GDB_GS+1)*4)
 #else /* ! CONFIG_X86_32 */
-enum regnames {
+enum regnames64 {
         GDB_AX,                 /* 0 */
-        GDB_DX,                 /* 1 */
+        GDB_BX,                 /* 1 */
         GDB_CX,                 /* 2 */
-        GDB_BX,                 /* 3 */
+        GDB_DX,                 /* 3 */
         GDB_SI,                 /* 4 */
         GDB_DI,                 /* 5 */
         GDB_BP,                 /* 6 */
@@ -58,18 +59,15 @@ enum regnames {
         GDB_R14,                /* 14 */
         GDB_R15,                /* 15 */
         GDB_PC,                 /* 16 */
-        GDB_PS,                 /* 17 */
 };
-#endif /* CONFIG_X86_32 */
 
-/*
- * Number of bytes of registers:
- */
-#ifdef CONFIG_X86_32
-# define NUMREGBYTES            64
-#else
-# define NUMREGBYTES            ((GDB_PS+1)*8)
-#endif
+enum regnames32 {
+        GDB_PS = 34,
+        GDB_CS,
+        GDB_SS,
+};
+#define NUMREGBYTES             ((GDB_SS+1)*4)
+#endif /* CONFIG_X86_32 */
 
 static inline void arch_kgdb_breakpoint(void)
 {
@@ -78,4 +76,4 @@ static inline void arch_kgdb_breakpoint(void)
 #define BREAK_INSTR_SIZE        1
 #define CACHE_FLUSH_IS_SAFE     1
 
-#endif                          /* _ASM_KGDB_H_ */
+#endif /* ASM_X86__KGDB_H */
diff --git a/include/asm-x86/kmap_types.h b/include/asm-x86/kmap_types.h
index 5f4174132a22..89f44493e643 100644
--- a/include/asm-x86/kmap_types.h
+++ b/include/asm-x86/kmap_types.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_KMAP_TYPES_H
-#define _ASM_X86_KMAP_TYPES_H
+#ifndef ASM_X86__KMAP_TYPES_H
+#define ASM_X86__KMAP_TYPES_H
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_DEBUG_HIGHMEM)
 # define D(n) __KM_FENCE_##n ,
@@ -26,4 +26,4 @@ D(13)	KM_TYPE_NR
 
 #undef D
 
-#endif
+#endif /* ASM_X86__KMAP_TYPES_H */
diff --git a/include/asm-x86/kprobes.h b/include/asm-x86/kprobes.h
index 54980b0b3892..bd8407863c13 100644
--- a/include/asm-x86/kprobes.h
+++ b/include/asm-x86/kprobes.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_KPROBES_H
-#define _ASM_KPROBES_H
+#ifndef ASM_X86__KPROBES_H
+#define ASM_X86__KPROBES_H
 /*
  *  Kernel Probes (KProbes)
  *
@@ -94,4 +94,4 @@ static inline void restore_interrupts(struct pt_regs *regs)
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_exceptions_notify(struct notifier_block *self,
                                     unsigned long val, void *data);
-#endif                          /* _ASM_KPROBES_H */
+#endif /* ASM_X86__KPROBES_H */
diff --git a/include/asm-x86/kvm.h b/include/asm-x86/kvm.h
index 80eefef2cc76..78e954db1e7f 100644
--- a/include/asm-x86/kvm.h
+++ b/include/asm-x86/kvm.h
@@ -1,5 +1,5 @@
-#ifndef __LINUX_KVM_X86_H
-#define __LINUX_KVM_X86_H
+#ifndef ASM_X86__KVM_H
+#define ASM_X86__KVM_H
 
 /*
  * KVM x86 specific structures and definitions
@@ -228,5 +228,6 @@ struct kvm_pit_state {
 #define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
 #define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
 #define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
+#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
 
-#endif
+#endif /* ASM_X86__KVM_H */
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index 1d8cd01fa514..69794547f514 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -1,4 +1,4 @@
-#/*
+/*
  * Kernel-based Virtual Machine driver for Linux
  *
  * This header defines architecture specific interfaces, x86 version
@@ -8,16 +8,18 @@
  *
  */
 
-#ifndef ASM_KVM_HOST_H
-#define ASM_KVM_HOST_H
+#ifndef ASM_X86__KVM_HOST_H
+#define ASM_X86__KVM_HOST_H
 
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/mmu_notifier.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
 #include <linux/kvm_types.h>
 
+#include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 
 #define KVM_MAX_VCPUS 16
@@ -26,6 +28,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 4
 
 #define KVM_PIO_PAGE_OFFSET 1
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
 
 #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
 #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
@@ -78,6 +81,7 @@
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_NR_VAR_MTRR 8
 
 extern spinlock_t kvm_lock;
 extern struct list_head vm_list;
@@ -108,12 +112,12 @@ enum {
 };
 
 enum {
+        VCPU_SREG_ES,
         VCPU_SREG_CS,
+        VCPU_SREG_SS,
         VCPU_SREG_DS,
-        VCPU_SREG_ES,
         VCPU_SREG_FS,
         VCPU_SREG_GS,
-        VCPU_SREG_SS,
         VCPU_SREG_TR,
         VCPU_SREG_LDTR,
 };
@@ -242,11 +246,13 @@ struct kvm_vcpu_arch {
         gfn_t last_pt_write_gfn;
         int   last_pt_write_count;
         u64  *last_pte_updated;
+        gfn_t last_pte_gfn;
 
         struct {
                 gfn_t gfn;      /* presumed gfn during guest pte update */
                 pfn_t pfn;      /* pfn corresponding to that gfn */
                 int largepage;
+                unsigned long mmu_seq;
         } update_pte;
 
         struct i387_fxsave_struct host_fx_image;
@@ -282,9 +288,14 @@ struct kvm_vcpu_arch {
         struct x86_emulate_ctxt emulate_ctxt;
 
         gpa_t time;
-        struct kvm_vcpu_time_info hv_clock;
+        struct pvclock_vcpu_time_info hv_clock;
+        unsigned int hv_clock_tsc_khz;
         unsigned int time_offset;
         struct page *time_page;
+
+        bool nmi_pending;
+
+        u64 mtrr[0x100];
 };
 
 struct kvm_mem_alias {
@@ -342,6 +353,7 @@ struct kvm_vcpu_stat {
         u32 mmio_exits;
         u32 signal_exits;
         u32 irq_window_exits;
+        u32 nmi_window_exits;
         u32 halt_exits;
         u32 halt_wakeup;
         u32 request_irq_exits;
@@ -377,7 +389,6 @@ struct kvm_x86_ops {
         void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
         void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
         void (*vcpu_put)(struct kvm_vcpu *vcpu);
-        void (*vcpu_decache)(struct kvm_vcpu *vcpu);
 
         int (*set_guest_debug)(struct kvm_vcpu *vcpu,
                                struct kvm_debug_guest *dbg);
@@ -495,6 +506,10 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
 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_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
 
 void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
@@ -513,6 +528,8 @@ void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
                            u32 error_code);
 
+void kvm_inject_nmi(struct kvm_vcpu *vcpu);
+
 void fx_init(struct kvm_vcpu *vcpu);
 
 int emulator_read_std(unsigned long addr,
@@ -541,6 +558,7 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
 
 void kvm_enable_tdp(void);
+void kvm_disable_tdp(void);
 
 int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
 int complete_pio(struct kvm_vcpu *vcpu);
@@ -552,55 +570,53 @@ static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
         return (struct kvm_mmu_page *)page_private(page);
 }
 
-static inline u16 read_fs(void)
+static inline u16 kvm_read_fs(void)
 {
         u16 seg;
         asm("mov %%fs, %0" : "=g"(seg));
         return seg;
 }
 
-static inline u16 read_gs(void)
+static inline u16 kvm_read_gs(void)
 {
         u16 seg;
         asm("mov %%gs, %0" : "=g"(seg));
         return seg;
 }
 
-static inline u16 read_ldt(void)
+static inline u16 kvm_read_ldt(void)
 {
         u16 ldt;
         asm("sldt %0" : "=g"(ldt));
         return ldt;
 }
 
-static inline void load_fs(u16 sel)
+static inline void kvm_load_fs(u16 sel)
 {
         asm("mov %0, %%fs" : : "rm"(sel));
 }
 
-static inline void load_gs(u16 sel)
+static inline void kvm_load_gs(u16 sel)
 {
         asm("mov %0, %%gs" : : "rm"(sel));
 }
 
-#ifndef load_ldt
-static inline void load_ldt(u16 sel)
+static inline void kvm_load_ldt(u16 sel)
 {
         asm("lldt %0" : : "rm"(sel));
 }
-#endif
 
-static inline void get_idt(struct descriptor_table *table)
+static inline void kvm_get_idt(struct descriptor_table *table)
 {
         asm("sidt %0" : "=m"(*table));
 }
 
-static inline void get_gdt(struct descriptor_table *table)
+static inline void kvm_get_gdt(struct descriptor_table *table)
 {
         asm("sgdt %0" : "=m"(*table));
 }
 
-static inline unsigned long read_tr_base(void)
+static inline unsigned long kvm_read_tr_base(void)
 {
         u16 tr;
         asm("str %0" : "=g"(tr));
@@ -617,17 +633,17 @@ static inline unsigned long read_msr(unsigned long msr)
 }
 #endif
 
-static inline void fx_save(struct i387_fxsave_struct *image)
+static inline void kvm_fx_save(struct i387_fxsave_struct *image)
 {
         asm("fxsave (%0)":: "r" (image));
 }
 
-static inline void fx_restore(struct i387_fxsave_struct *image)
+static inline void kvm_fx_restore(struct i387_fxsave_struct *image)
 {
         asm("fxrstor (%0)":: "r" (image));
 }
 
-static inline void fx_finit(void)
+static inline void kvm_fx_finit(void)
 {
         asm("finit");
 }
@@ -689,4 +705,34 @@ enum {
         trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
                                                 vcpu, 0, 0, 0, 0, 0, 0)
 
+#ifdef CONFIG_64BIT
+# define KVM_EX_ENTRY ".quad"
+# define KVM_EX_PUSH "pushq"
+#else
+# define KVM_EX_ENTRY ".long"
+# define KVM_EX_PUSH "pushl"
 #endif
+
+/*
+ * Hardware virtualization extension instructions may fault if a
+ * reboot turns off virtualization while processes are running.
+ * Trap the fault and ignore the instruction if that happens.
+ */
+asmlinkage void kvm_handle_fault_on_reboot(void);
+
+#define __kvm_handle_fault_on_reboot(insn) \
+        "666: " insn "\n\t" \
+        ".pushsection .fixup, \"ax\" \n" \
+        "667: \n\t" \
+        KVM_EX_PUSH " $666b \n\t" \
+        "jmp kvm_handle_fault_on_reboot \n\t" \
+        ".popsection \n\t" \
+        ".pushsection __ex_table, \"a\" \n\t" \
+        KVM_EX_ENTRY " 666b, 667b \n\t" \
+        ".popsection"
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+
+#endif /* ASM_X86__KVM_HOST_H */
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
index 509845942070..30054fded4fb 100644
--- a/include/asm-x86/kvm_para.h
+++ b/include/asm-x86/kvm_para.h
@@ -1,5 +1,5 @@
-#ifndef __X86_KVM_PARA_H
-#define __X86_KVM_PARA_H
+#ifndef ASM_X86__KVM_PARA_H
+#define ASM_X86__KVM_PARA_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.
@@ -48,24 +48,6 @@ struct kvm_mmu_op_release_pt {
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
-/* xen binary-compatible interface. See xen headers for details */
-struct kvm_vcpu_time_info {
-        uint32_t version;
-        uint32_t pad0;
-        uint64_t tsc_timestamp;
-        uint64_t system_time;
-        uint32_t tsc_to_system_mul;
-        int8_t   tsc_shift;
-        int8_t   pad[3];
-} __attribute__((__packed__)); /* 32 bytes */
-
-struct kvm_wall_clock {
-        uint32_t wc_version;
-        uint32_t wc_sec;
-        uint32_t wc_nsec;
-} __attribute__((__packed__));
-
-
 extern void kvmclock_init(void);
 
 
@@ -89,7 +71,8 @@ static inline long kvm_hypercall0(unsigned int nr)
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr));
+                     : "a"(nr)
+                     : "memory");
         return ret;
 }
 
@@ -98,7 +81,8 @@ static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr), "b"(p1));
+                     : "a"(nr), "b"(p1)
+                     : "memory");
         return ret;
 }
 
@@ -108,7 +92,8 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr), "b"(p1), "c"(p2));
+                     : "a"(nr), "b"(p1), "c"(p2)
+                     : "memory");
         return ret;
 }
 
@@ -118,7 +103,8 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr), "b"(p1), "c"(p2), "d"(p3));
+                     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
+                     : "memory");
         return ret;
 }
 
@@ -129,7 +115,8 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4));
+                     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)
+                     : "memory");
         return ret;
 }
 
@@ -157,4 +144,4 @@ static inline unsigned int kvm_arch_para_features(void)
 
 #endif
 
-#endif
+#endif /* ASM_X86__KVM_PARA_H */
diff --git a/include/asm-x86/kvm_x86_emulate.h b/include/asm-x86/kvm_x86_emulate.h
index b877bbd2d3a7..e2d9b030c1ac 100644
--- a/include/asm-x86/kvm_x86_emulate.h
+++ b/include/asm-x86/kvm_x86_emulate.h
@@ -8,8 +8,8 @@
  * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4
  */
 
-#ifndef __X86_EMULATE_H__
-#define __X86_EMULATE_H__
+#ifndef ASM_X86__KVM_X86_EMULATE_H
+#define ASM_X86__KVM_X86_EMULATE_H
 
 struct x86_emulate_ctxt;
 
@@ -124,7 +124,8 @@ struct decode_cache {
         u8 rex_prefix;
         struct operand src;
         struct operand dst;
-        unsigned long *override_base;
+        bool has_seg_override;
+        u8 seg_override;
         unsigned int d;
         unsigned long regs[NR_VCPU_REGS];
         unsigned long eip;
@@ -134,6 +135,7 @@ struct decode_cache {
         u8 modrm_reg;
         u8 modrm_rm;
         u8 use_modrm_ea;
+        bool rip_relative;
         unsigned long modrm_ea;
         void *modrm_ptr;
         unsigned long modrm_val;
@@ -150,12 +152,7 @@ struct x86_emulate_ctxt {
         /* Emulated execution mode, represented by an X86EMUL_MODE value. */
         int mode;
 
-        unsigned long cs_base;
-        unsigned long ds_base;
-        unsigned long es_base;
-        unsigned long ss_base;
-        unsigned long gs_base;
-        unsigned long fs_base;
+        u32 cs_base;
 
         /* decode cache */
 
@@ -184,4 +181,4 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
                      struct x86_emulate_ops *ops);
 
-#endif                          /* __X86_EMULATE_H__ */
+#endif /* ASM_X86__KVM_X86_EMULATE_H */
diff --git a/include/asm-x86/ldt.h b/include/asm-x86/ldt.h
index 20c597242b53..a5228504d867 100644
--- a/include/asm-x86/ldt.h
+++ b/include/asm-x86/ldt.h
@@ -3,8 +3,8 @@
  *
  * Definitions of structures used with the modify_ldt system call.
  */
-#ifndef _ASM_X86_LDT_H
-#define _ASM_X86_LDT_H
+#ifndef ASM_X86__LDT_H
+#define ASM_X86__LDT_H
 
 /* Maximum number of LDT entries supported. */
 #define LDT_ENTRIES     8192
@@ -37,4 +37,4 @@ struct user_desc {
 #define MODIFY_LDT_CONTENTS_CODE        2
 
 #endif /* !__ASSEMBLY__ */
-#endif
+#endif /* ASM_X86__LDT_H */
diff --git a/include/asm-x86/lguest.h b/include/asm-x86/lguest.h
index be4a7247fa2b..7505e947ed27 100644
--- a/include/asm-x86/lguest.h
+++ b/include/asm-x86/lguest.h
@@ -1,5 +1,5 @@
-#ifndef _X86_LGUEST_H
-#define _X86_LGUEST_H
+#ifndef ASM_X86__LGUEST_H
+#define ASM_X86__LGUEST_H
 
 #define GDT_ENTRY_LGUEST_CS     10
 #define GDT_ENTRY_LGUEST_DS     11
@@ -91,4 +91,4 @@ static inline void lguest_set_ts(void)
 
 #endif /* __ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__LGUEST_H */
diff --git a/include/asm-x86/lguest_hcall.h b/include/asm-x86/lguest_hcall.h
index a3241f28e34a..8f034ba4b53e 100644
--- a/include/asm-x86/lguest_hcall.h
+++ b/include/asm-x86/lguest_hcall.h
@@ -1,6 +1,6 @@
 /* Architecture specific portion of the lguest hypercalls */
-#ifndef _X86_LGUEST_HCALL_H
-#define _X86_LGUEST_HCALL_H
+#ifndef ASM_X86__LGUEST_HCALL_H
+#define ASM_X86__LGUEST_HCALL_H
 
 #define LHCALL_FLUSH_ASYNC      0
 #define LHCALL_LGUEST_INIT      1
@@ -68,4 +68,4 @@ struct hcall_args {
 };
 
 #endif /* !__ASSEMBLY__ */
-#endif  /* _I386_LGUEST_HCALL_H */
+#endif /* ASM_X86__LGUEST_HCALL_H */
diff --git a/include/asm-x86/linkage.h b/include/asm-x86/linkage.h
index 64e444f8e85b..42d8b62ee8ab 100644
--- a/include/asm-x86/linkage.h
+++ b/include/asm-x86/linkage.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_LINKAGE_H
-#define __ASM_LINKAGE_H
+#ifndef ASM_X86__LINKAGE_H
+#define ASM_X86__LINKAGE_H
 
 #undef notrace
 #define notrace __attribute__((no_instrument_function))
@@ -57,5 +57,5 @@
 #define __ALIGN_STR ".align 16,0x90"
 #endif
 
-#endif
+#endif /* ASM_X86__LINKAGE_H */
 
diff --git a/include/asm-x86/local.h b/include/asm-x86/local.h
index 330a72496abd..ae91994fd6c9 100644
--- a/include/asm-x86/local.h
+++ b/include/asm-x86/local.h
@@ -1,5 +1,5 @@
-#ifndef _ARCH_LOCAL_H
-#define _ARCH_LOCAL_H
+#ifndef ASM_X86__LOCAL_H
+#define ASM_X86__LOCAL_H
 
 #include <linux/percpu.h>
 
@@ -232,4 +232,4 @@ static inline long local_sub_return(long i, local_t *l)
 #define __cpu_local_add(i, l)   cpu_local_add((i), (l))
 #define __cpu_local_sub(i, l)   cpu_local_sub((i), (l))
 
-#endif /* _ARCH_LOCAL_H */
+#endif /* ASM_X86__LOCAL_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_apicdef.h b/include/asm-x86/mach-bigsmp/mach_apicdef.h
deleted file mode 100644
index a58ab5a75c8c..000000000000
--- a/include/asm-x86/mach-bigsmp/mach_apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
-
-#define         APIC_ID_MASK            (0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x) 
-{ 
-        return (((x)>>24)&0xFF);
-} 
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/include/asm-x86/mach-bigsmp/mach_mpspec.h b/include/asm-x86/mach-bigsmp/mach_mpspec.h
deleted file mode 100644
index 6b5dadcf1d0e..000000000000
--- a/include/asm-x86/mach-bigsmp/mach_mpspec.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-#define MAX_MP_BUSSES 32
-
-#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-default/apm.h b/include/asm-x86/mach-default/apm.h
index 989f34c37d32..2aa61b54fbd5 100644
--- a/include/asm-x86/mach-default/apm.h
+++ b/include/asm-x86/mach-default/apm.h
@@ -3,8 +3,8 @@
  *  Split out from apm.c by Osamu Tomita <tomita@cinet.co.jp>
  */
 
-#ifndef _ASM_APM_H
-#define _ASM_APM_H
+#ifndef ASM_X86__MACH_DEFAULT__APM_H
+#define ASM_X86__MACH_DEFAULT__APM_H
 
 #ifdef APM_ZERO_SEGS
 #       define APM_DO_ZERO_SEGS \
@@ -70,4 +70,4 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
         return error;
 }
 
-#endif /* _ASM_APM_H */
+#endif /* ASM_X86__MACH_DEFAULT__APM_H */
diff --git a/include/asm-x86/mach-default/entry_arch.h b/include/asm-x86/mach-default/entry_arch.h
index bc861469bdba..9283b60a1dd2 100644
--- a/include/asm-x86/mach-default/entry_arch.h
+++ b/include/asm-x86/mach-default/entry_arch.h
@@ -13,6 +13,7 @@
 BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
 BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
+BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 #endif
 
 /*
diff --git a/include/asm-x86/mach-default/irq_vectors.h b/include/asm-x86/mach-default/irq_vectors.h
deleted file mode 100644
index 881c63ca61ad..000000000000
--- a/include/asm-x86/mach-default/irq_vectors.h
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * This file should contain #defines for all of the interrupt vector
- * numbers used by this architecture.
- *
- * In addition, there are some standard defines:
- *
- *      FIRST_EXTERNAL_VECTOR:
- *              The first free place for external interrupts
- *
- *      SYSCALL_VECTOR:
- *              The IRQ vector a syscall makes the user to kernel transition
- *              under.
- *
- *      TIMER_IRQ:
- *              The IRQ number the timer interrupt comes in at.
- *
- *      NR_IRQS:
- *              The total number of interrupt vectors (including all the
- *              architecture specific interrupts) needed.
- *
- */                     
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR   0x20
-
-#define SYSCALL_VECTOR          0x80
-
-/*
- * Vectors 0x20-0x2f are used for ISA interrupts.
- */
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
- */
-#define SPURIOUS_APIC_VECTOR    0xff
-#define ERROR_APIC_VECTOR       0xfe
-#define INVALIDATE_TLB_VECTOR   0xfd
-#define RESCHEDULE_VECTOR       0xfc
-#define CALL_FUNCTION_VECTOR    0xfb
-
-#define THERMAL_APIC_VECTOR     0xf0
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR      0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x31 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR     0x31
-#define FIRST_SYSTEM_VECTOR     0xef
-
-#define TIMER_IRQ 0
-
-/*
- * 16 8259A IRQ's, 208 potential APIC interrupt sources.
- * Right now the APIC is mostly only used for SMP.
- * 256 vectors is an architectural limit. (we can have
- * more than 256 devices theoretically, but they will
- * have to use shared interrupts)
- * Since vectors 0x00-0x1f are used/reserved for the CPU,
- * the usable vector space is 0x20-0xff (224 vectors)
- */
-
-/*
- * The maximum number of vectors supported by i386 processors
- * is limited to 256. For processors other than i386, NR_VECTORS
- * should be changed accordingly.
- */
-#define NR_VECTORS 256
-
-#include "irq_vectors_limits.h"
-
-#define FPU_IRQ                 13
-
-#define FIRST_VM86_IRQ          3
-#define LAST_VM86_IRQ           15
-#define invalid_vm86_irq(irq)   ((irq) < 3 || (irq) > 15)
-
-
-#endif /* _ASM_IRQ_VECTORS_H */
diff --git a/include/asm-x86/mach-default/irq_vectors_limits.h b/include/asm-x86/mach-default/irq_vectors_limits.h
deleted file mode 100644
index a90c7a60109f..000000000000
--- a/include/asm-x86/mach-default/irq_vectors_limits.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
-
-#if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT)
-#define NR_IRQS 224
-# if (224 >= 32 * NR_CPUS)
-# define NR_IRQ_VECTORS NR_IRQS
-# else
-# define NR_IRQ_VECTORS (32 * NR_CPUS)
-# endif
-#else
-#define NR_IRQS 16
-#define NR_IRQ_VECTORS NR_IRQS
-#endif
-
-#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/mach-default/mach_apic.h b/include/asm-x86/mach-default/mach_apic.h
index 21003b56ae95..2a330a41b3dd 100644
--- a/include/asm-x86/mach-default/mach_apic.h
+++ b/include/asm-x86/mach-default/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_APIC_H
+#define ASM_X86__MACH_DEFAULT__MACH_APIC_H
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
@@ -30,6 +30,8 @@ static inline cpumask_t target_cpus(void)
 #define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
 #define phys_pkg_id     (genapic->phys_pkg_id)
 #define vector_allocation_domain    (genapic->vector_allocation_domain)
+#define read_apic_id()  (GET_APIC_ID(apic_read(APIC_ID)))
+#define send_IPI_self (genapic->send_IPI_self)
 extern void setup_apic_routing(void);
 #else
 #define INT_DELIVERY_MODE dest_LowestPrio
@@ -46,15 +48,15 @@ static inline void init_apic_ldr(void)
 {
         unsigned long val;
 
-        apic_write_around(APIC_DFR, APIC_DFR_VALUE);
+        apic_write(APIC_DFR, APIC_DFR_VALUE);
         val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
         val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
-        apic_write_around(APIC_LDR, val);
+        apic_write(APIC_LDR, val);
 }
 
 static inline int apic_id_registered(void)
 {
-        return physid_isset(GET_APIC_ID(read_apic_id()), phys_cpu_present_map);
+        return physid_isset(read_apic_id(), phys_cpu_present_map);
 }
 
 static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
@@ -77,7 +79,11 @@ static inline void setup_apic_routing(void)
 
 static inline int apicid_to_node(int logical_apicid)
 {
+#ifdef CONFIG_SMP
+        return apicid_2_node[hard_smp_processor_id()];
+#else
         return 0;
+#endif
 }
 #endif
 
@@ -134,4 +140,4 @@ static inline void enable_apic_mode(void)
 }
 
 #endif /* CONFIG_X86_LOCAL_APIC */
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_APIC_H */
diff --git a/include/asm-x86/mach-default/mach_apicdef.h b/include/asm-x86/mach-default/mach_apicdef.h
index e4b29ba37de6..0c2d41c41b20 100644
--- a/include/asm-x86/mach-default/mach_apicdef.h
+++ b/include/asm-x86/mach-default/mach_apicdef.h
@@ -1,12 +1,12 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_APICDEF_H
+#define ASM_X86__MACH_DEFAULT__MACH_APICDEF_H
 
 #include <asm/apic.h>
 
 #ifdef CONFIG_X86_64
-#define APIC_ID_MASK            (0xFFu<<24)
-#define GET_APIC_ID(x)          (((x)>>24)&0xFFu)
-#define SET_APIC_ID(x)          (((x)<<24))
+#define APIC_ID_MASK            (genapic->apic_id_mask)
+#define GET_APIC_ID(x)          (genapic->get_apic_id(x))
+#define SET_APIC_ID(x)          (genapic->set_apic_id(x))
 #else
 #define         APIC_ID_MASK            (0xF<<24)
 static inline unsigned get_apic_id(unsigned long x) 
@@ -21,4 +21,4 @@ static inline unsigned get_apic_id(unsigned long x)
 #define         GET_APIC_ID(x)  get_apic_id(x)
 #endif
 
-#endif
+#endif /* ASM_X86__MACH_DEFAULT__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-default/mach_ipi.h b/include/asm-x86/mach-default/mach_ipi.h
index be323364e68f..674bc7e50c35 100644
--- a/include/asm-x86/mach-default/mach_ipi.h
+++ b/include/asm-x86/mach-default/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_IPI_H
+#define ASM_X86__MACH_DEFAULT__MACH_IPI_H
 
 /* Avoid include hell */
 #define NMI_VECTOR 0x02
@@ -61,4 +61,4 @@ static inline void send_IPI_all(int vector)
 }
 #endif
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_IPI_H */
diff --git a/include/asm-x86/mach-default/mach_mpparse.h b/include/asm-x86/mach-default/mach_mpparse.h
index d14108505bb8..9c381f2815ac 100644
--- a/include/asm-x86/mach-default/mach_mpparse.h
+++ b/include/asm-x86/mach-default/mach_mpparse.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H
+#define ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H
 
 static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, 
                 char *productid)
@@ -14,4 +14,4 @@ static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 }
 
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-default/mach_mpspec.h b/include/asm-x86/mach-default/mach_mpspec.h
index 51c9a9775932..d77646f011f1 100644
--- a/include/asm-x86/mach-default/mach_mpspec.h
+++ b/include/asm-x86/mach-default/mach_mpspec.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H
+#define ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H
 
 #define MAX_IRQ_SOURCES 256
 
@@ -9,4 +9,4 @@
 #define MAX_MP_BUSSES 32
 #endif
 
-#endif /* __ASM_MACH_MPSPEC_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-default/mach_timer.h b/include/asm-x86/mach-default/mach_timer.h
index 4b76e536cd98..990b15833834 100644
--- a/include/asm-x86/mach-default/mach_timer.h
+++ b/include/asm-x86/mach-default/mach_timer.h
@@ -10,8 +10,8 @@
  * directly because of the awkward 8-bit access mechanism of the 82C54
  * device.
  */
-#ifndef _MACH_TIMER_H
-#define _MACH_TIMER_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_TIMER_H
+#define ASM_X86__MACH_DEFAULT__MACH_TIMER_H
 
 #define CALIBRATE_TIME_MSEC 30 /* 30 msecs */
 #define CALIBRATE_LATCH \
@@ -45,4 +45,4 @@ static inline void mach_countup(unsigned long *count_p)
         *count_p = count;
 }
 
-#endif /* !_MACH_TIMER_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_TIMER_H */
diff --git a/include/asm-x86/mach-default/mach_traps.h b/include/asm-x86/mach-default/mach_traps.h
index 2fe7705c0484..de9ac3f5c4ce 100644
--- a/include/asm-x86/mach-default/mach_traps.h
+++ b/include/asm-x86/mach-default/mach_traps.h
@@ -2,8 +2,8 @@
  *  Machine specific NMI handling for generic.
  *  Split out from traps.c by Osamu Tomita <tomita@cinet.co.jp>
  */
-#ifndef _MACH_TRAPS_H
-#define _MACH_TRAPS_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_TRAPS_H
+#define ASM_X86__MACH_DEFAULT__MACH_TRAPS_H
 
 #include <asm/mc146818rtc.h>
 
@@ -36,4 +36,4 @@ static inline void reassert_nmi(void)
                 unlock_cmos();
 }
 
-#endif /* !_MACH_TRAPS_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_TRAPS_H */
diff --git a/include/asm-x86/mach-default/mach_wakecpu.h b/include/asm-x86/mach-default/mach_wakecpu.h
index 3ebb17893aa5..361b810f5160 100644
--- a/include/asm-x86/mach-default/mach_wakecpu.h
+++ b/include/asm-x86/mach-default/mach_wakecpu.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_WAKECPU_H
-#define __ASM_MACH_WAKECPU_H
+#ifndef ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H
+#define ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H
 
 /* 
  * This file copes with machines that wakeup secondary CPUs by the
@@ -39,4 +39,4 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
  #define inquire_remote_apic(apicid) {}
 #endif
 
-#endif /* __ASM_MACH_WAKECPU_H */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H */
diff --git a/include/asm-x86/mach-default/setup_arch.h b/include/asm-x86/mach-default/setup_arch.h
index 605e3ccb991b..38846208b548 100644
--- a/include/asm-x86/mach-default/setup_arch.h
+++ b/include/asm-x86/mach-default/setup_arch.h
@@ -1,7 +1,3 @@
 /* Hook to call BIOS initialisation function */
 
 /* no action for generic */
-
-#ifndef ARCH_SETUP
-#define ARCH_SETUP
-#endif
diff --git a/include/asm-x86/mach-default/smpboot_hooks.h b/include/asm-x86/mach-default/smpboot_hooks.h
index 56d0e1fa0258..dbab36d64d48 100644
--- a/include/asm-x86/mach-default/smpboot_hooks.h
+++ b/include/asm-x86/mach-default/smpboot_hooks.h
@@ -3,18 +3,20 @@
 
 static inline void smpboot_clear_io_apic_irqs(void)
 {
+#ifdef CONFIG_X86_IO_APIC
         io_apic_irqs = 0;
+#endif
 }
 
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
         CMOS_WRITE(0xa, 0xf);
         local_flush_tlb();
-        Dprintk("1.\n");
+        pr_debug("1.\n");
         *((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
-        Dprintk("2.\n");
+        pr_debug("2.\n");
         *((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
-        Dprintk("3.\n");
+        pr_debug("3.\n");
 }
 
 static inline void smpboot_restore_warm_reset_vector(void)
@@ -35,17 +37,23 @@ static inline void smpboot_restore_warm_reset_vector(void)
 
 static inline void __init smpboot_setup_io_apic(void)
 {
+#ifdef CONFIG_X86_IO_APIC
         /*
          * Here we can be sure that there is an IO-APIC in the system. Let's
          * go and set it up:
          */
         if (!skip_ioapic_setup && nr_ioapics)
                 setup_IO_APIC();
-        else
+        else {
                 nr_ioapics = 0;
+                localise_nmi_watchdog();
+        }
+#endif
 }
 
 static inline void smpboot_clear_io_apic(void)
 {
+#ifdef CONFIG_X86_IO_APIC
         nr_ioapics = 0;
+#endif
 }
diff --git a/include/asm-x86/mach-es7000/mach_mpspec.h b/include/asm-x86/mach-es7000/mach_mpspec.h
deleted file mode 100644
index b1f5039d4506..000000000000
--- a/include/asm-x86/mach-es7000/mach_mpspec.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-#define MAX_MP_BUSSES 256
-
-#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-generic/gpio.h b/include/asm-x86/mach-generic/gpio.h
index 5305dcb96df2..6ce0f7786ef8 100644
--- a/include/asm-x86/mach-generic/gpio.h
+++ b/include/asm-x86/mach-generic/gpio.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_GENERIC_GPIO_H
-#define __ASM_MACH_GENERIC_GPIO_H
+#ifndef ASM_X86__MACH_GENERIC__GPIO_H
+#define ASM_X86__MACH_GENERIC__GPIO_H
 
 int gpio_request(unsigned gpio, const char *label);
 void gpio_free(unsigned gpio);
@@ -12,4 +12,4 @@ int irq_to_gpio(unsigned irq);
 
 #include <asm-generic/gpio.h>           /* cansleep wrappers */
 
-#endif /* __ASM_MACH_GENERIC_GPIO_H */
+#endif /* ASM_X86__MACH_GENERIC__GPIO_H */
diff --git a/include/asm-x86/mach-generic/irq_vectors_limits.h b/include/asm-x86/mach-generic/irq_vectors_limits.h
index 890ce3f5e09a..f7870e1a220d 100644
--- a/include/asm-x86/mach-generic/irq_vectors_limits.h
+++ b/include/asm-x86/mach-generic/irq_vectors_limits.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
+#ifndef ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H
+#define ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H
 
 /*
  * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
@@ -11,4 +11,4 @@
 #define NR_IRQS 224
 #define NR_IRQ_VECTORS  1024
 
-#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
+#endif /* ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/mach-generic/mach_apic.h b/include/asm-x86/mach-generic/mach_apic.h
index 6eff343e1233..5d010c6881dd 100644
--- a/include/asm-x86/mach-generic/mach_apic.h
+++ b/include/asm-x86/mach-generic/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_GENERIC__MACH_APIC_H
+#define ASM_X86__MACH_GENERIC__MACH_APIC_H
 
 #include <asm/genapic.h>
 
@@ -29,4 +29,4 @@
 
 extern void generic_bigsmp_probe(void);
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_GENERIC__MACH_APIC_H */
diff --git a/include/asm-x86/mach-generic/mach_apicdef.h b/include/asm-x86/mach-generic/mach_apicdef.h
index 28ed98972ca8..1657f38b8f27 100644
--- a/include/asm-x86/mach-generic/mach_apicdef.h
+++ b/include/asm-x86/mach-generic/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef _GENAPIC_MACH_APICDEF_H
-#define _GENAPIC_MACH_APICDEF_H 1
+#ifndef ASM_X86__MACH_GENERIC__MACH_APICDEF_H
+#define ASM_X86__MACH_GENERIC__MACH_APICDEF_H
 
 #ifndef APIC_DEFINITION
 #include <asm/genapic.h>
@@ -8,4 +8,4 @@
 #define APIC_ID_MASK (genapic->apic_id_mask)
 #endif
 
-#endif
+#endif /* ASM_X86__MACH_GENERIC__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-generic/mach_ipi.h b/include/asm-x86/mach-generic/mach_ipi.h
index 441b0fe3ed1d..f67433dbd65f 100644
--- a/include/asm-x86/mach-generic/mach_ipi.h
+++ b/include/asm-x86/mach-generic/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef _MACH_IPI_H
-#define _MACH_IPI_H 1
+#ifndef ASM_X86__MACH_GENERIC__MACH_IPI_H
+#define ASM_X86__MACH_GENERIC__MACH_IPI_H
 
 #include <asm/genapic.h>
 
@@ -7,4 +7,4 @@
 #define send_IPI_allbutself (genapic->send_IPI_allbutself)
 #define send_IPI_all (genapic->send_IPI_all)
 
-#endif
+#endif /* ASM_X86__MACH_GENERIC__MACH_IPI_H */
diff --git a/include/asm-x86/mach-generic/mach_mpparse.h b/include/asm-x86/mach-generic/mach_mpparse.h
index 0d0b5ba2e9d1..3115564e557c 100644
--- a/include/asm-x86/mach-generic/mach_mpparse.h
+++ b/include/asm-x86/mach-generic/mach_mpparse.h
@@ -1,7 +1,10 @@
-#ifndef _MACH_MPPARSE_H
-#define _MACH_MPPARSE_H 1
+#ifndef ASM_X86__MACH_GENERIC__MACH_MPPARSE_H
+#define ASM_X86__MACH_GENERIC__MACH_MPPARSE_H
 
-int mps_oem_check(struct mp_config_table *mpc, char *oem, char *productid); 
-int acpi_madt_oem_check(char *oem_id, char *oem_table_id); 
 
-#endif
+extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
+                         char *productid);
+
+extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
+
+#endif /* ASM_X86__MACH_GENERIC__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-generic/mach_mpspec.h b/include/asm-x86/mach-generic/mach_mpspec.h
index 9ef0b941bb22..6061b153613e 100644
--- a/include/asm-x86/mach-generic/mach_mpspec.h
+++ b/include/asm-x86/mach-generic/mach_mpspec.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
+#ifndef ASM_X86__MACH_GENERIC__MACH_MPSPEC_H
+#define ASM_X86__MACH_GENERIC__MACH_MPSPEC_H
 
 #define MAX_IRQ_SOURCES 256
 
@@ -7,4 +7,6 @@
 /* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */
 #define MAX_MP_BUSSES 260
 
-#endif /* __ASM_MACH_MPSPEC_H */
+extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
+                                char *productid);
+#endif /* ASM_X86__MACH_GENERIC__MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-numaq/mach_mpparse.h b/include/asm-x86/mach-numaq/mach_mpparse.h
deleted file mode 100644
index 459b12401187..000000000000
--- a/include/asm-x86/mach-numaq/mach_mpparse.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
-
-extern void mpc_oem_bus_info(struct mpc_config_bus *m, char *name,
-                             struct mpc_config_translation *translation);
-extern void mpc_oem_pci_bus(struct mpc_config_bus *m,
-        struct mpc_config_translation *translation);
-
-/* Hook from generic ACPI tables.c */
-static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-}
-
-#endif /* __ASM_MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-numaq/mach_mpspec.h b/include/asm-x86/mach-numaq/mach_mpspec.h
deleted file mode 100644
index dffb09856f8f..000000000000
--- a/include/asm-x86/mach-numaq/mach_mpspec.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 512
-
-#define MAX_MP_BUSSES 32
-
-#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-rdc321x/gpio.h b/include/asm-x86/mach-rdc321x/gpio.h
index acce0b7d397b..94b6cdf532e2 100644
--- a/include/asm-x86/mach-rdc321x/gpio.h
+++ b/include/asm-x86/mach-rdc321x/gpio.h
@@ -1,5 +1,7 @@
-#ifndef _RDC321X_GPIO_H
-#define _RDC321X_GPIO_H
+#ifndef ASM_X86__MACH_RDC321X__GPIO_H
+#define ASM_X86__MACH_RDC321X__GPIO_H
+
+#include <linux/kernel.h>
 
 extern int rdc_gpio_get_value(unsigned gpio);
 extern void rdc_gpio_set_value(unsigned gpio, int value);
@@ -18,6 +20,7 @@ static inline int gpio_request(unsigned gpio, const char *label)
 
 static inline void gpio_free(unsigned gpio)
 {
+        might_sleep();
         rdc_gpio_free(gpio);
 }
 
@@ -54,4 +57,4 @@ static inline int irq_to_gpio(unsigned irq)
 /* For cansleep */
 #include <asm-generic/gpio.h>
 
-#endif /* _RDC321X_GPIO_H_ */
+#endif /* ASM_X86__MACH_RDC321X__GPIO_H */
diff --git a/include/asm-x86/mach-summit/mach_apicdef.h b/include/asm-x86/mach-summit/mach_apicdef.h
deleted file mode 100644
index a58ab5a75c8c..000000000000
--- a/include/asm-x86/mach-summit/mach_apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
-
-#define         APIC_ID_MASK            (0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x) 
-{ 
-        return (((x)>>24)&0xFF);
-} 
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/include/asm-x86/mach-summit/mach_mpspec.h b/include/asm-x86/mach-summit/mach_mpspec.h
deleted file mode 100644
index bd765523511a..000000000000
--- a/include/asm-x86/mach-summit/mach_mpspec.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_MACH_MPSPEC_H
-#define __ASM_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-/* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */
-#define MAX_MP_BUSSES 260
-
-#endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-visws/entry_arch.h b/include/asm-x86/mach-visws/entry_arch.h
deleted file mode 100644
index b183fa6d83d9..000000000000
--- a/include/asm-x86/mach-visws/entry_arch.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * The following vectors are part of the Linux architecture, there
- * is no hardware IRQ pin equivalent for them, they are triggered
- * through the ICC by us (IPIs)
- */
-#ifdef CONFIG_X86_SMP
-BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
-BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
-#endif
-
-/*
- * every pentium local APIC has two 'local interrupts', with a
- * soft-definable vector attached to both interrupts, one of
- * which is a timer interrupt, the other one is error counter
- * overflow. Linux uses the local APIC timer interrupt to get
- * a much simpler SMP time architecture:
- */
-#ifdef CONFIG_X86_LOCAL_APIC
-BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
-BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
-BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
-#endif
diff --git a/include/asm-x86/mach-visws/irq_vectors.h b/include/asm-x86/mach-visws/irq_vectors.h
deleted file mode 100644
index cb572d8db505..000000000000
--- a/include/asm-x86/mach-visws/irq_vectors.h
+++ /dev/null
@@ -1,62 +0,0 @@
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR   0x20
-
-#define SYSCALL_VECTOR          0x80
-
-/*
- * Vectors 0x20-0x2f are used for ISA interrupts.
- */
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
- */
-#define SPURIOUS_APIC_VECTOR    0xff
-#define ERROR_APIC_VECTOR       0xfe
-#define INVALIDATE_TLB_VECTOR   0xfd
-#define RESCHEDULE_VECTOR       0xfc
-#define CALL_FUNCTION_VECTOR    0xfb
-
-#define THERMAL_APIC_VECTOR     0xf0
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR      0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x31 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR     0x31
-#define FIRST_SYSTEM_VECTOR     0xef
-
-#define TIMER_IRQ 0
-
-/*
- * IRQ definitions
- */
-#define NR_VECTORS 256
-#define NR_IRQS 224
-#define NR_IRQ_VECTORS NR_IRQS
-
-#define FPU_IRQ                 13
-
-#define FIRST_VM86_IRQ          3
-#define LAST_VM86_IRQ           15
-#define invalid_vm86_irq(irq)   ((irq) < 3 || (irq) > 15)
-
-#endif /* _ASM_IRQ_VECTORS_H */
diff --git a/include/asm-x86/mach-visws/mach_apic.h b/include/asm-x86/mach-visws/mach_apic.h
deleted file mode 100644
index a9ef33a8a995..000000000000
--- a/include/asm-x86/mach-visws/mach_apic.h
+++ /dev/null
@@ -1,103 +0,0 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
-
-#include <mach_apicdef.h>
-#include <asm/smp.h>
-
-#define APIC_DFR_VALUE  (APIC_DFR_FLAT)
-
-#define no_balance_irq (0)
-#define esr_disable (0)
-
-#define INT_DELIVERY_MODE dest_LowestPrio
-#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-
-#ifdef CONFIG_SMP
- #define TARGET_CPUS cpu_online_map
-#else
- #define TARGET_CPUS cpumask_of_cpu(0)
-#endif
-
-#define check_apicid_used(bitmap, apicid)       physid_isset(apicid, bitmap)
-#define check_apicid_present(bit)               physid_isset(bit, phys_cpu_present_map)
-
-static inline int apic_id_registered(void)
-{
-        return physid_isset(GET_APIC_ID(read_apic_id()), phys_cpu_present_map);
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-        unsigned long val;
-
-        apic_write_around(APIC_DFR, APIC_DFR_VALUE);
-        val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-        val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
-        apic_write_around(APIC_LDR, val);
-}
-
-static inline void summit_check(char *oem, char *productid) 
-{
-}
-
-static inline void setup_apic_routing(void)
-{
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-        return 0;
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-        return 1 << cpu;
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-        if (mps_cpu < get_physical_broadcast())
-                return mps_cpu;
-        else
-                return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int apicid)
-{
-        return physid_mask_of_physid(apicid);
-}
-
-#define WAKE_SECONDARY_VIA_INIT
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-        return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
-}
-
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
-{
-        return cpus_addr(cpumask)[0];
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-        return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/mach-visws/mach_apicdef.h b/include/asm-x86/mach-visws/mach_apicdef.h
deleted file mode 100644
index 826cfa97d778..000000000000
--- a/include/asm-x86/mach-visws/mach_apicdef.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
-
-#define         APIC_ID_MASK            (0xF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-                return (((x)>>24)&0xF);
-}
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/include/asm-x86/mach-visws/setup_arch.h b/include/asm-x86/mach-visws/setup_arch.h
deleted file mode 100644
index 33f700ef6831..000000000000
--- a/include/asm-x86/mach-visws/setup_arch.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/* Hook to call BIOS initialisation function */
-
-extern unsigned long sgivwfb_mem_phys;
-extern unsigned long sgivwfb_mem_size;
-
-/* no action for visws */
-
-#define ARCH_SETUP
diff --git a/include/asm-x86/mach-visws/smpboot_hooks.h b/include/asm-x86/mach-visws/smpboot_hooks.h
deleted file mode 100644
index c9b83e395a2e..000000000000
--- a/include/asm-x86/mach-visws/smpboot_hooks.h
+++ /dev/null
@@ -1,28 +0,0 @@
-static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
-{
-        CMOS_WRITE(0xa, 0xf);
-        local_flush_tlb();
-        Dprintk("1.\n");
-        *((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
-        Dprintk("2.\n");
-        *((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
-        Dprintk("3.\n");
-}
-
-/* for visws do nothing for any of these */
-
-static inline void smpboot_clear_io_apic_irqs(void)
-{
-}
-
-static inline void smpboot_restore_warm_reset_vector(void)
-{
-}
-
-static inline void smpboot_setup_io_apic(void)
-{
-}
-
-static inline void smpboot_clear_io_apic(void)
-{
-}
diff --git a/include/asm-x86/mach-voyager/entry_arch.h b/include/asm-x86/mach-voyager/entry_arch.h
index 4a1e1e8c10b6..ae52624b5937 100644
--- a/include/asm-x86/mach-voyager/entry_arch.h
+++ b/include/asm-x86/mach-voyager/entry_arch.h
@@ -23,4 +23,4 @@ BUILD_INTERRUPT(qic_invalidate_interrupt, QIC_INVALIDATE_CPI);
 BUILD_INTERRUPT(qic_reschedule_interrupt, QIC_RESCHEDULE_CPI);
 BUILD_INTERRUPT(qic_enable_irq_interrupt, QIC_ENABLE_IRQ_CPI);
 BUILD_INTERRUPT(qic_call_function_interrupt, QIC_CALL_FUNCTION_CPI);
-
+BUILD_INTERRUPT(qic_call_function_single_interrupt, QIC_CALL_FUNCTION_SINGLE_CPI);
diff --git a/include/asm-x86/mach-voyager/irq_vectors.h b/include/asm-x86/mach-voyager/irq_vectors.h
deleted file mode 100644
index 165421f5821c..000000000000
--- a/include/asm-x86/mach-voyager/irq_vectors.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 2002
- *
- * Author: James.Bottomley@HansenPartnership.com
- *
- * linux/arch/i386/voyager/irq_vectors.h
- *
- * This file provides definitions for the VIC and QIC CPIs
- */
-
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR   0x20
-
-#define SYSCALL_VECTOR          0x80
-
-/*
- * Vectors 0x20-0x2f are used for ISA interrupts.
- */
-
-/* These define the CPIs we use in linux */
-#define VIC_CPI_LEVEL0                  0
-#define VIC_CPI_LEVEL1                  1
-/* now the fake CPIs */
-#define VIC_TIMER_CPI                   2
-#define VIC_INVALIDATE_CPI              3
-#define VIC_RESCHEDULE_CPI              4
-#define VIC_ENABLE_IRQ_CPI              5
-#define VIC_CALL_FUNCTION_CPI           6
-
-/* Now the QIC CPIs:  Since we don't need the two initial levels,
- * these are 2 less than the VIC CPIs */
-#define QIC_CPI_OFFSET                  1
-#define QIC_TIMER_CPI                   (VIC_TIMER_CPI - QIC_CPI_OFFSET)
-#define QIC_INVALIDATE_CPI              (VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
-#define QIC_RESCHEDULE_CPI              (VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
-#define QIC_ENABLE_IRQ_CPI              (VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_CPI           (VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
-
-#define VIC_START_FAKE_CPI              VIC_TIMER_CPI
-#define VIC_END_FAKE_CPI                VIC_CALL_FUNCTION_CPI
-
-/* this is the SYS_INT CPI. */
-#define VIC_SYS_INT                     8
-#define VIC_CMN_INT                     15
-
-/* This is the boot CPI for alternate processors.  It gets overwritten
- * by the above once the system has activated all available processors */
-#define VIC_CPU_BOOT_CPI                VIC_CPI_LEVEL0
-#define VIC_CPU_BOOT_ERRATA_CPI         (VIC_CPI_LEVEL0 + 8)
-
-#define NR_VECTORS 256
-#define NR_IRQS 224
-#define NR_IRQ_VECTORS NR_IRQS
-
-#define FPU_IRQ                         13
-
-#define FIRST_VM86_IRQ          3
-#define LAST_VM86_IRQ           15
-#define invalid_vm86_irq(irq)   ((irq) < 3 || (irq) > 15)
-
-#ifndef __ASSEMBLY__
-extern asmlinkage void vic_cpi_interrupt(void);
-extern asmlinkage void vic_sys_interrupt(void);
-extern asmlinkage void vic_cmn_interrupt(void);
-extern asmlinkage void qic_timer_interrupt(void);
-extern asmlinkage void qic_invalidate_interrupt(void);
-extern asmlinkage void qic_reschedule_interrupt(void);
-extern asmlinkage void qic_enable_irq_interrupt(void);
-extern asmlinkage void qic_call_function_interrupt(void);
-#endif /* !__ASSEMBLY__ */
-
-#endif /* _ASM_IRQ_VECTORS_H */
diff --git a/include/asm-x86/math_emu.h b/include/asm-x86/math_emu.h
index 9bf4ae93ab10..5768d8e95c8c 100644
--- a/include/asm-x86/math_emu.h
+++ b/include/asm-x86/math_emu.h
@@ -1,5 +1,5 @@
-#ifndef _I386_MATH_EMU_H
-#define _I386_MATH_EMU_H
+#ifndef ASM_X86__MATH_EMU_H
+#define ASM_X86__MATH_EMU_H
 
 /* This structure matches the layout of the data saved to the stack
    following a device-not-present interrupt, part of it saved
@@ -28,4 +28,4 @@ struct info {
         long ___vm86_fs;
         long ___vm86_gs;
 };
-#endif
+#endif /* ASM_X86__MATH_EMU_H */
diff --git a/include/asm-x86/mc146818rtc.h b/include/asm-x86/mc146818rtc.h
index daf1ccde77af..a995f33176cd 100644
--- a/include/asm-x86/mc146818rtc.h
+++ b/include/asm-x86/mc146818rtc.h
@@ -1,8 +1,8 @@
 /*
  * Machine dependent access functions for RTC registers.
  */
-#ifndef _ASM_MC146818RTC_H
-#define _ASM_MC146818RTC_H
+#ifndef ASM_X86__MC146818RTC_H
+#define ASM_X86__MC146818RTC_H
 
 #include <asm/io.h>
 #include <asm/system.h>
@@ -101,4 +101,4 @@ extern unsigned long mach_get_cmos_time(void);
 
 #define RTC_IRQ 8
 
-#endif /* _ASM_MC146818RTC_H */
+#endif /* ASM_X86__MC146818RTC_H */
diff --git a/include/asm-x86/mca.h b/include/asm-x86/mca.h
index 09adf2eac4dc..60d1ed287b13 100644
--- a/include/asm-x86/mca.h
+++ b/include/asm-x86/mca.h
@@ -1,8 +1,8 @@
 /* -*- mode: c; c-basic-offset: 8 -*- */
 
 /* Platform specific MCA defines */
-#ifndef _ASM_MCA_H
-#define _ASM_MCA_H
+#ifndef ASM_X86__MCA_H
+#define ASM_X86__MCA_H
 
 /* Maximal number of MCA slots - actually, some machines have less, but
  * they all have sufficient number of POS registers to cover 8.
@@ -40,4 +40,4 @@
  */
 #define MCA_NUMADAPTERS (MCA_MAX_SLOT_NR+3)
 
-#endif
+#endif /* ASM_X86__MCA_H */
diff --git a/include/asm-x86/mca_dma.h b/include/asm-x86/mca_dma.h
index c3dca6edc6b1..49f22be237d2 100644
--- a/include/asm-x86/mca_dma.h
+++ b/include/asm-x86/mca_dma.h
@@ -1,5 +1,5 @@
-#ifndef MCA_DMA_H
-#define MCA_DMA_H
+#ifndef ASM_X86__MCA_DMA_H
+#define ASM_X86__MCA_DMA_H
 
 #include <asm/io.h>
 #include <linux/ioport.h>
@@ -198,4 +198,4 @@ static inline void mca_set_dma_mode(unsigned int dmanr, unsigned int mode)
         outb(mode, MCA_DMA_REG_EXE);
 }
 
-#endif /* MCA_DMA_H */
+#endif /* ASM_X86__MCA_DMA_H */
diff --git a/include/asm-x86/mce.h b/include/asm-x86/mce.h
index 94f1fd79e22a..036133eaf744 100644
--- a/include/asm-x86/mce.h
+++ b/include/asm-x86/mce.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_MCE_H
-#define _ASM_X86_MCE_H
+#ifndef ASM_X86__MCE_H
+#define ASM_X86__MCE_H
 
 #ifdef __x86_64__
 
@@ -92,6 +92,7 @@ extern int mce_disabled;
 
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, device_mce);
+extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
 #ifdef CONFIG_X86_MCE_INTEL
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
@@ -126,4 +127,4 @@ extern void restart_mce(void);
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__MCE_H */
diff --git a/include/asm-x86/microcode.h b/include/asm-x86/microcode.h
new file mode 100644
index 000000000000..62c793bb70ca
--- /dev/null
+++ b/include/asm-x86/microcode.h
@@ -0,0 +1,47 @@
+#ifndef ASM_X86__MICROCODE_H
+#define ASM_X86__MICROCODE_H
+
+struct cpu_signature {
+        unsigned int sig;
+        unsigned int pf;
+        unsigned int rev;
+};
+
+struct device;
+
+struct microcode_ops {
+        int  (*request_microcode_user) (int cpu, const void __user *buf, size_t size);
+        int  (*request_microcode_fw) (int cpu, struct device *device);
+
+        void (*apply_microcode) (int cpu);
+
+        int  (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
+        void (*microcode_fini_cpu) (int cpu);
+};
+
+struct ucode_cpu_info {
+        struct cpu_signature cpu_sig;
+        int valid;
+        void *mc;
+};
+extern struct ucode_cpu_info ucode_cpu_info[];
+
+#ifdef CONFIG_MICROCODE_INTEL
+extern struct microcode_ops * __init init_intel_microcode(void);
+#else
+static inline struct microcode_ops * __init init_intel_microcode(void)
+{
+        return NULL;
+}
+#endif /* CONFIG_MICROCODE_INTEL */
+
+#ifdef CONFIG_MICROCODE_AMD
+extern struct microcode_ops * __init init_amd_microcode(void);
+#else
+static inline struct microcode_ops * __init init_amd_microcode(void)
+{
+        return NULL;
+}
+#endif
+
+#endif /* ASM_X86__MICROCODE_H */
diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h
index c1682b542daf..4ef28e6de383 100644
--- a/include/asm-x86/mman.h
+++ b/include/asm-x86/mman.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_MMAN_H
-#define _ASM_X86_MMAN_H
+#ifndef ASM_X86__MMAN_H
+#define ASM_X86__MMAN_H
 
 #include <asm-generic/mman.h>
 
@@ -12,8 +12,9 @@
 #define MAP_NORESERVE   0x4000          /* don't check for reservations */
 #define MAP_POPULATE    0x8000          /* populate (prefault) pagetables */
 #define MAP_NONBLOCK    0x10000         /* do not block on IO */
+#define MAP_STACK       0x20000         /* give out an address that is best suited for process/thread stacks */
 
 #define MCL_CURRENT     1               /* lock all current mappings */
 #define MCL_FUTURE      2               /* lock all future mappings */
 
-#endif /* _ASM_X86_MMAN_H */
+#endif /* ASM_X86__MMAN_H */
diff --git a/include/asm-x86/mmconfig.h b/include/asm-x86/mmconfig.h
new file mode 100644
index 000000000000..fb79b1cf5d07
--- /dev/null
+++ b/include/asm-x86/mmconfig.h
@@ -0,0 +1,12 @@
+#ifndef ASM_X86__MMCONFIG_H
+#define ASM_X86__MMCONFIG_H
+
+#ifdef CONFIG_PCI_MMCONFIG
+extern void __cpuinit fam10h_check_enable_mmcfg(void);
+extern void __cpuinit check_enable_amd_mmconf_dmi(void);
+#else
+static inline void fam10h_check_enable_mmcfg(void) { }
+static inline void check_enable_amd_mmconf_dmi(void) { }
+#endif
+
+#endif /* ASM_X86__MMCONFIG_H */
diff --git a/include/asm-x86/mmu.h b/include/asm-x86/mmu.h
index 00e88679e11f..9d5aff14334a 100644
--- a/include/asm-x86/mmu.h
+++ b/include/asm-x86/mmu.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_MMU_H
-#define _ASM_X86_MMU_H
+#ifndef ASM_X86__MMU_H
+#define ASM_X86__MMU_H
 
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
@@ -7,14 +7,9 @@
 /*
  * The x86 doesn't have a mmu context, but
  * we put the segment information here.
- *
- * cpu_vm_mask is used to optimize ldt flushing.
  */
 typedef struct {
         void *ldt;
-#ifdef CONFIG_X86_64
-        rwlock_t ldtlock;
-#endif
         int size;
         struct mutex lock;
         void *vdso;
@@ -28,4 +23,4 @@ static inline void leave_mm(int cpu)
 }
 #endif
 
-#endif /* _ASM_X86_MMU_H */
+#endif /* ASM_X86__MMU_H */
diff --git a/include/asm-x86/mmu_context.h b/include/asm-x86/mmu_context.h
index 6598450da6c6..8ec940bfd079 100644
--- a/include/asm-x86/mmu_context.h
+++ b/include/asm-x86/mmu_context.h
@@ -1,5 +1,37 @@
+#ifndef ASM_X86__MMU_CONTEXT_H
+#define ASM_X86__MMU_CONTEXT_H
+
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/paravirt.h>
+#ifndef CONFIG_PARAVIRT
+#include <asm-generic/mm_hooks.h>
+
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+                                        struct mm_struct *next)
+{
+}
+#endif  /* !CONFIG_PARAVIRT */
+
+/*
+ * Used for LDT copy/destruction.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
+
 #ifdef CONFIG_X86_32
 # include "mmu_context_32.h"
 #else
 # include "mmu_context_64.h"
 #endif
+
+#define activate_mm(prev, next)                 \
+do {                                            \
+        paravirt_activate_mm((prev), (next));   \
+        switch_mm((prev), (next), NULL);        \
+} while (0);
+
+
+#endif /* ASM_X86__MMU_CONTEXT_H */
diff --git a/include/asm-x86/mmu_context_32.h b/include/asm-x86/mmu_context_32.h
index 9756ae0f1dd3..cce6f6e4afd6 100644
--- a/include/asm-x86/mmu_context_32.h
+++ b/include/asm-x86/mmu_context_32.h
@@ -1,27 +1,5 @@
-#ifndef __I386_SCHED_H
-#define __I386_SCHED_H
-
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/paravirt.h>
-#ifndef CONFIG_PARAVIRT
-#include <asm-generic/mm_hooks.h>
-
-static inline void paravirt_activate_mm(struct mm_struct *prev,
-                                        struct mm_struct *next)
-{
-}
-#endif  /* !CONFIG_PARAVIRT */
-
-
-/*
- * Used for LDT copy/destruction.
- */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
-
+#ifndef ASM_X86__MMU_CONTEXT_32_H
+#define ASM_X86__MMU_CONTEXT_32_H
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
@@ -75,10 +53,4 @@ static inline void switch_mm(struct mm_struct *prev,
 #define deactivate_mm(tsk, mm)                  \
         asm("movl %0,%%gs": :"r" (0));
 
-#define activate_mm(prev, next)                 \
-do {                                            \
-        paravirt_activate_mm((prev), (next));   \
-        switch_mm((prev), (next), NULL);        \
-} while (0);
-
-#endif
+#endif /* ASM_X86__MMU_CONTEXT_32_H */
diff --git a/include/asm-x86/mmu_context_64.h b/include/asm-x86/mmu_context_64.h
index ca44c71e7fb3..26758673c828 100644
--- a/include/asm-x86/mmu_context_64.h
+++ b/include/asm-x86/mmu_context_64.h
@@ -1,21 +1,7 @@
-#ifndef __X86_64_MMU_CONTEXT_H
-#define __X86_64_MMU_CONTEXT_H
+#ifndef ASM_X86__MMU_CONTEXT_64_H
+#define ASM_X86__MMU_CONTEXT_64_H
 
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/pgalloc.h>
 #include <asm/pda.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#ifndef CONFIG_PARAVIRT
-#include <asm-generic/mm_hooks.h>
-#endif
-
-/*
- * possibly do the LDT unload here?
- */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
@@ -65,8 +51,4 @@ do {						\
         asm volatile("movl %0,%%fs"::"r"(0));   \
 } while (0)
 
-#define activate_mm(prev, next)                 \
-        switch_mm((prev), (next), NULL)
-
-
-#endif
+#endif /* ASM_X86__MMU_CONTEXT_64_H */
diff --git a/include/asm-x86/mmx.h b/include/asm-x86/mmx.h
index 940881218ff8..2e7299bb3653 100644
--- a/include/asm-x86/mmx.h
+++ b/include/asm-x86/mmx.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_MMX_H
-#define _ASM_MMX_H
+#ifndef ASM_X86__MMX_H
+#define ASM_X86__MMX_H
 
 /*
  *      MMX 3Dnow! helper operations
@@ -11,4 +11,4 @@ extern void *_mmx_memcpy(void *to, const void *from, size_t size);
 extern void mmx_clear_page(void *page);
 extern void mmx_copy_page(void *to, void *from);
 
-#endif
+#endif /* ASM_X86__MMX_H */
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
index cb2cad0b65a7..121b65d61d86 100644
--- a/include/asm-x86/mmzone_32.h
+++ b/include/asm-x86/mmzone_32.h
@@ -3,8 +3,8 @@
  *
  */
 
-#ifndef _ASM_MMZONE_H_
-#define _ASM_MMZONE_H_
+#ifndef ASM_X86__MMZONE_32_H
+#define ASM_X86__MMZONE_32_H
 
 #include <asm/smp.h>
 
@@ -12,11 +12,9 @@
 extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)  (node_data[nid])
 
-#ifdef CONFIG_X86_NUMAQ
-        #include <asm/numaq.h>
-#elif defined(CONFIG_ACPI_SRAT)/* summit or generic arch */
-        #include <asm/srat.h>
-#endif
+#include <asm/numaq.h>
+/* summit or generic arch */
+#include <asm/srat.h>
 
 extern int get_memcfg_numa_flat(void);
 /*
@@ -26,28 +24,20 @@ extern int get_memcfg_numa_flat(void);
  */
 static inline void get_memcfg_numa(void)
 {
-#ifdef CONFIG_X86_NUMAQ
+
         if (get_memcfg_numaq())
                 return;
-#elif defined(CONFIG_ACPI_SRAT)
         if (get_memcfg_from_srat())
                 return;
-#endif
-
         get_memcfg_numa_flat();
 }
 
 extern int early_pfn_to_nid(unsigned long pfn);
-extern void numa_kva_reserve(void);
 
 #else /* !CONFIG_NUMA */
 
 #define get_memcfg_numa get_memcfg_numa_flat
-#define get_zholes_size(n) (0)
 
-static inline void numa_kva_reserve(void)
-{
-}
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DISCONTIGMEM
@@ -55,14 +45,14 @@ static inline void numa_kva_reserve(void)
 /*
  * generic node memory support, the following assumptions apply:
  *
- * 1) memory comes in 256Mb contigious chunks which are either present or not
+ * 1) memory comes in 64Mb contigious chunks which are either present or not
  * 2) we will not have more than 64Gb in total
  *
  * for now assume that 64Gb is max amount of RAM for whole system
  *    64Gb / 4096bytes/page = 16777216 pages
  */
 #define MAX_NR_PAGES 16777216
-#define MAX_ELEMENTS 256
+#define MAX_ELEMENTS 1024
 #define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
 
 extern s8 physnode_map[];
@@ -87,9 +77,6 @@ static inline int pfn_to_nid(unsigned long pfn)
         __pgdat->node_start_pfn + __pgdat->node_spanned_pages;          \
 })
 
-#ifdef CONFIG_X86_NUMAQ            /* we have contiguous memory on NUMA-Q */
-#define pfn_valid(pfn)          ((pfn) < num_physpages)
-#else
 static inline int pfn_valid(int pfn)
 {
         int nid = pfn_to_nid(pfn);
@@ -98,7 +85,6 @@ static inline int pfn_valid(int pfn)
                 return (pfn < node_end_pfn(nid));
         return 0;
 }
-#endif /* CONFIG_X86_NUMAQ */
 
 #endif /* CONFIG_DISCONTIGMEM */
 
@@ -111,10 +97,16 @@ static inline int pfn_valid(int pfn)
         reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags))
 #define alloc_bootmem(x) \
         __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_nopanic(x) \
+        __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \
+                                __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low(x) \
         __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
 #define alloc_bootmem_pages(x) \
         __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_pages_nopanic(x) \
+        __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \
+                                __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low_pages(x) \
         __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
 #define alloc_bootmem_node(pgdat, x)                                    \
@@ -139,4 +131,4 @@ static inline int pfn_valid(int pfn)
 })
 #endif /* CONFIG_NEED_MULTIPLE_NODES */
 
-#endif /* _ASM_MMZONE_H_ */
+#endif /* ASM_X86__MMZONE_32_H */
diff --git a/include/asm-x86/mmzone_64.h b/include/asm-x86/mmzone_64.h
index 5e3a6cbddb49..6480f3333b2a 100644
--- a/include/asm-x86/mmzone_64.h
+++ b/include/asm-x86/mmzone_64.h
@@ -1,8 +1,8 @@
 /* K8 NUMA support */
 /* Copyright 2002,2003 by Andi Kleen, SuSE Labs */
 /* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */
-#ifndef _ASM_X86_64_MMZONE_H
-#define _ASM_X86_64_MMZONE_H 1
+#ifndef ASM_X86__MMZONE_64_H
+#define ASM_X86__MMZONE_64_H
 
 
 #ifdef CONFIG_NUMA
@@ -48,4 +48,4 @@ extern int early_pfn_to_nid(unsigned long pfn);
 #endif
 
 #endif
-#endif
+#endif /* ASM_X86__MMZONE_64_H */
diff --git a/include/asm-x86/module.h b/include/asm-x86/module.h
index bfedb247871c..48dc3e0c07d9 100644
--- a/include/asm-x86/module.h
+++ b/include/asm-x86/module.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_MODULE_H
-#define _ASM_MODULE_H
+#ifndef ASM_X86__MODULE_H
+#define ASM_X86__MODULE_H
 
 /* x86_32/64 are simple */
 struct mod_arch_specific {};
@@ -79,4 +79,4 @@ struct mod_arch_specific {};
 # define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
 #endif
 
-#endif /* _ASM_MODULE_H */
+#endif /* ASM_X86__MODULE_H */
diff --git a/include/asm-x86/mpspec.h b/include/asm-x86/mpspec.h
index 57a991b9c053..be2241a818f1 100644
--- a/include/asm-x86/mpspec.h
+++ b/include/asm-x86/mpspec.h
@@ -1,18 +1,25 @@
-#ifndef _AM_X86_MPSPEC_H
-#define _AM_X86_MPSPEC_H
+#ifndef ASM_X86__MPSPEC_H
+#define ASM_X86__MPSPEC_H
 
 #include <linux/init.h>
 
 #include <asm/mpspec_def.h>
 
+extern int apic_version[MAX_APICS];
+
 #ifdef CONFIG_X86_32
 #include <mach_mpspec.h>
 
 extern unsigned int def_to_bigsmp;
-extern int apic_version[MAX_APICS];
 extern u8 apicid_2_node[];
 extern int pic_mode;
 
+#ifdef CONFIG_X86_NUMAQ
+extern int mp_bus_id_to_node[MAX_MP_BUSSES];
+extern int mp_bus_id_to_local[MAX_MP_BUSSES];
+extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
+#endif
+
 #define MAX_APICID 256
 
 #else
@@ -21,26 +28,30 @@ extern int pic_mode;
 /* Each PCI slot may be a combo card with its own bus.  4 IRQ pins per slot. */
 #define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4)
 
+#endif
+
 extern void early_find_smp_config(void);
 extern void early_get_smp_config(void);
 
-#endif
-
 #if defined(CONFIG_MCA) || defined(CONFIG_EISA)
 extern int mp_bus_id_to_type[MAX_MP_BUSSES];
 #endif
 
 extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
-extern int mp_bus_id_to_pci_bus[MAX_MP_BUSSES];
-
 extern unsigned int boot_cpu_physical_apicid;
+extern unsigned int max_physical_apicid;
 extern int smp_found_config;
 extern int mpc_default_type;
 extern unsigned long mp_lapic_addr;
 
 extern void find_smp_config(void);
 extern void get_smp_config(void);
+#ifdef CONFIG_X86_MPPARSE
+extern void early_reserve_e820_mpc_new(void);
+#else
+static inline void early_reserve_e820_mpc_new(void) { }
+#endif
 
 void __cpuinit generic_processor_info(int apicid, int version);
 #ifdef CONFIG_ACPI
@@ -49,6 +60,17 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
                                    u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
 extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+#ifdef CONFIG_X86_IO_APIC
+extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
+                                u32 gsi, int triggering, int polarity);
+#else
+static inline int
+mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
+                   u32 gsi, int triggering, int polarity)
+{
+        return 0;
+}
+#endif
 #endif /* CONFIG_ACPI */
 
 #define PHYSID_ARRAY_SIZE       BITS_TO_LONGS(MAX_APICS)
@@ -101,6 +123,7 @@ typedef struct physid_mask physid_mask_t;
                 __physid_mask;                                          \
         })
 
+/* Note: will create very large stack frames if physid_mask_t is big */
 #define physid_mask_of_physid(physid)                                   \
         ({                                                              \
                 physid_mask_t __physid_mask = PHYSID_MASK_NONE;         \
@@ -108,9 +131,15 @@ typedef struct physid_mask physid_mask_t;
                 __physid_mask;                                          \
         })
 
+static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
+{
+        physids_clear(*map);
+        physid_set(physid, *map);
+}
+
 #define PHYSID_MASK_ALL         { {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} }
 #define PHYSID_MASK_NONE        { {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} }
 
 extern physid_mask_t phys_cpu_present_map;
 
-#endif
+#endif /* ASM_X86__MPSPEC_H */
diff --git a/include/asm-x86/mpspec_def.h b/include/asm-x86/mpspec_def.h
index dc6ef85e3624..79166b048012 100644
--- a/include/asm-x86/mpspec_def.h
+++ b/include/asm-x86/mpspec_def.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MPSPEC_DEF_H
-#define __ASM_MPSPEC_DEF_H
+#ifndef ASM_X86__MPSPEC_DEF_H
+#define ASM_X86__MPSPEC_DEF_H
 
 /*
  * Structure definitions for SMP machines following the
@@ -17,10 +17,11 @@
 # define MAX_MPC_ENTRY 1024
 # define MAX_APICS      256
 #else
-/*
- * A maximum of 255 APICs with the current APIC ID architecture.
- */
-# define MAX_APICS 255
+# if NR_CPUS <= 255
+#  define MAX_APICS     255
+# else
+#  define MAX_APICS   32768
+# endif
 #endif
 
 struct intel_mp_floating {
@@ -176,4 +177,4 @@ enum mp_bustype {
         MP_BUS_PCI,
         MP_BUS_MCA,
 };
-#endif
+#endif /* ASM_X86__MPSPEC_DEF_H */
diff --git a/include/asm-x86/msgbuf.h b/include/asm-x86/msgbuf.h
index 7e4e9481f51c..1b538c907a3d 100644
--- a/include/asm-x86/msgbuf.h
+++ b/include/asm-x86/msgbuf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_MSGBUF_H
-#define _ASM_X86_MSGBUF_H
+#ifndef ASM_X86__MSGBUF_H
+#define ASM_X86__MSGBUF_H
 
 /*
  * The msqid64_ds structure for i386 architecture.
@@ -36,4 +36,4 @@ struct msqid64_ds {
         unsigned long  __unused5;
 };
 
-#endif /* _ASM_X86_MSGBUF_H */
+#endif /* ASM_X86__MSGBUF_H */
diff --git a/include/asm-x86/msidef.h b/include/asm-x86/msidef.h
index 296f29ce426d..ed9190246876 100644
--- a/include/asm-x86/msidef.h
+++ b/include/asm-x86/msidef.h
@@ -1,5 +1,5 @@
-#ifndef ASM_MSIDEF_H
-#define ASM_MSIDEF_H
+#ifndef ASM_X86__MSIDEF_H
+#define ASM_X86__MSIDEF_H
 
 /*
  * Constants for Intel APIC based MSI messages.
@@ -48,4 +48,8 @@
 #define  MSI_ADDR_DEST_ID(dest)         (((dest) << MSI_ADDR_DEST_ID_SHIFT) & \
                                          MSI_ADDR_DEST_ID_MASK)
 
-#endif /* ASM_MSIDEF_H */
+#define MSI_ADDR_IR_EXT_INT             (1 << 4)
+#define MSI_ADDR_IR_SHV                 (1 << 3)
+#define MSI_ADDR_IR_INDEX1(index)       ((index & 0x8000) >> 13)
+#define MSI_ADDR_IR_INDEX2(index)       ((index & 0x7fff) << 5)
+#endif /* ASM_X86__MSIDEF_H */
diff --git a/include/asm-x86/msr-index.h b/include/asm-x86/msr-index.h
index 09413ad39d3c..0bb43301a202 100644
--- a/include/asm-x86/msr-index.h
+++ b/include/asm-x86/msr-index.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MSR_INDEX_H
-#define __ASM_MSR_INDEX_H
+#ifndef ASM_X86__MSR_INDEX_H
+#define ASM_X86__MSR_INDEX_H
 
 /* CPU model specific register (MSR) numbers */
 
@@ -111,7 +111,9 @@
 #define MSR_K8_TOP_MEM2                 0xc001001d
 #define MSR_K8_SYSCFG                   0xc0010010
 #define MSR_K8_HWCR                     0xc0010015
-#define MSR_K8_ENABLE_C1E               0xc0010055
+#define MSR_K8_INT_PENDING_MSG          0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK         0x18000000
 #define MSR_K8_TSEG_ADDR                0xc0010112
 #define K8_MTRRFIXRANGE_DRAM_ENABLE     0x00040000 /* MtrrFixDramEn bit    */
 #define K8_MTRRFIXRANGE_DRAM_MODIFY     0x00080000 /* MtrrFixDramModEn bit */
@@ -174,6 +176,7 @@
 #define MSR_IA32_TSC                    0x00000010
 #define MSR_IA32_PLATFORM_ID            0x00000017
 #define MSR_IA32_EBL_CR_POWERON         0x0000002a
+#define MSR_IA32_FEATURE_CONTROL        0x0000003a
 
 #define MSR_IA32_APICBASE               0x0000001b
 #define MSR_IA32_APICBASE_BSP           (1<<8)
@@ -308,4 +311,19 @@
 /* Geode defined MSRs */
 #define MSR_GEODE_BUSCONT_CONF0         0x00001900
 
-#endif /* __ASM_MSR_INDEX_H */
+/* Intel VT MSRs */
+#define MSR_IA32_VMX_BASIC              0x00000480
+#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
+#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
+#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
+#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
+#define MSR_IA32_VMX_MISC               0x00000485
+#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
+#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
+#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
+#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
+#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
+#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
+#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
+
+#endif /* ASM_X86__MSR_INDEX_H */
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
index 3707650a169b..530af1f6389e 100644
--- a/include/asm-x86/msr.h
+++ b/include/asm-x86/msr.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_X86_MSR_H_
-#define __ASM_X86_MSR_H_
+#ifndef ASM_X86__MSR_H
+#define ASM_X86__MSR_H
 
 #include <asm/msr-index.h>
 
@@ -18,7 +18,7 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
         unsigned long low, high;
         asm volatile(".byte 0x0f,0x01,0xf9"
                      : "=a" (low), "=d" (high), "=c" (*aux));
-        return low | ((u64)high >> 32);
+        return low | ((u64)high << 32);
 }
 
 /*
@@ -52,6 +52,22 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 {
         DECLARE_ARGS(val, low, high);
 
+        asm volatile("2: rdmsr ; xor %[err],%[err]\n"
+                     "1:\n\t"
+                     ".section .fixup,\"ax\"\n\t"
+                     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
+                     ".previous\n\t"
+                     _ASM_EXTABLE(2b, 3b)
+                     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
+                     : "c" (msr), [fault] "i" (-EFAULT));
+        return EAX_EDX_VAL(val, low, high);
+}
+
+static inline unsigned long long native_read_msr_amd_safe(unsigned int msr,
+                                                      int *err)
+{
+        DECLARE_ARGS(val, low, high);
+
         asm volatile("2: rdmsr ; xor %0,%0\n"
                      "1:\n\t"
                      ".section .fixup,\"ax\"\n\t"
@@ -59,29 +75,30 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
                      ".previous\n\t"
                      _ASM_EXTABLE(2b, 3b)
                      : "=r" (*err), EAX_EDX_RET(val, low, high)
-                     : "c" (msr), "i" (-EFAULT));
+                     : "c" (msr), "D" (0x9c5a203a), "i" (-EFAULT));
         return EAX_EDX_VAL(val, low, high);
 }
 
 static inline void native_write_msr(unsigned int msr,
                                     unsigned low, unsigned high)
 {
-        asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high));
+        asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
 }
 
 static inline int native_write_msr_safe(unsigned int msr,
                                         unsigned low, unsigned high)
 {
         int err;
-        asm volatile("2: wrmsr ; xor %0,%0\n"
+        asm volatile("2: wrmsr ; xor %[err],%[err]\n"
                      "1:\n\t"
                      ".section .fixup,\"ax\"\n\t"
-                     "3:  mov %4,%0 ; jmp 1b\n\t"
+                     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
                      ".previous\n\t"
                      _ASM_EXTABLE(2b, 3b)
-                     : "=a" (err)
+                     : [err] "=a" (err)
                      : "c" (msr), "0" (low), "d" (high),
-                     "i" (-EFAULT));
+                       [fault] "i" (-EFAULT)
+                     : "memory");
         return err;
 }
 
@@ -157,6 +174,13 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
         *p = native_read_msr_safe(msr, &err);
         return err;
 }
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+        int err;
+
+        *p = native_read_msr_amd_safe(msr, &err);
+        return err;
+}
 
 #define rdtscl(low)                                             \
         ((low) = (u32)native_read_tsc())
@@ -191,19 +215,20 @@ do {                                                            \
 #define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
 
 #ifdef CONFIG_SMP
-void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
-void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsr_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);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
-
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 #else  /*  CONFIG_SMP  */
-static inline void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
         rdmsr(msr_no, *l, *h);
+        return 0;
 }
-static inline void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+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 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
                                     u32 *l, u32 *h)
@@ -219,4 +244,4 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 #endif /* __KERNEL__ */
 
 
-#endif
+#endif /* ASM_X86__MSR_H */
diff --git a/include/asm-x86/mtrr.h b/include/asm-x86/mtrr.h
index a69a01a51729..23a7f83da953 100644
--- a/include/asm-x86/mtrr.h
+++ b/include/asm-x86/mtrr.h
@@ -20,8 +20,8 @@
     The postal address is:
       Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
 */
-#ifndef _ASM_X86_MTRR_H
-#define _ASM_X86_MTRR_H
+#ifndef ASM_X86__MTRR_H
+#define ASM_X86__MTRR_H
 
 #include <linux/ioctl.h>
 #include <linux/errno.h>
@@ -170,4 +170,4 @@ struct mtrr_gentry32 {
 
 #endif /* __KERNEL__ */
 
-#endif  /*  _ASM_X86_MTRR_H  */
+#endif /* ASM_X86__MTRR_H */
diff --git a/include/asm-x86/mutex_32.h b/include/asm-x86/mutex_32.h
index 73e928ef5f03..25c16d8ba3c7 100644
--- a/include/asm-x86/mutex_32.h
+++ b/include/asm-x86/mutex_32.h
@@ -6,8 +6,8 @@
  *
  *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
-#ifndef _ASM_MUTEX_H
-#define _ASM_MUTEX_H
+#ifndef ASM_X86__MUTEX_32_H
+#define ASM_X86__MUTEX_32_H
 
 #include <asm/alternative.h>
 
@@ -122,4 +122,4 @@ static inline int __mutex_fastpath_trylock(atomic_t *count,
 #endif
 }
 
-#endif
+#endif /* ASM_X86__MUTEX_32_H */
diff --git a/include/asm-x86/mutex_64.h b/include/asm-x86/mutex_64.h
index f3fae9becb38..918ba21ab9d9 100644
--- a/include/asm-x86/mutex_64.h
+++ b/include/asm-x86/mutex_64.h
@@ -6,8 +6,8 @@
  *
  *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
-#ifndef _ASM_MUTEX_H
-#define _ASM_MUTEX_H
+#ifndef ASM_X86__MUTEX_64_H
+#define ASM_X86__MUTEX_64_H
 
 /**
  * __mutex_fastpath_lock - decrement and call function if negative
@@ -97,4 +97,4 @@ static inline int __mutex_fastpath_trylock(atomic_t *count,
                 return 0;
 }
 
-#endif
+#endif /* ASM_X86__MUTEX_64_H */
diff --git a/include/asm-x86/namei.h b/include/asm-x86/namei.h
deleted file mode 100644
index 415ef5d9550e..000000000000
--- a/include/asm-x86/namei.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _ASM_X86_NAMEI_H
-#define _ASM_X86_NAMEI_H
-
-/* This dummy routine maybe changed to something useful
- * for /usr/gnemul/ emulation stuff.
- * Look at asm-sparc/namei.h for details.
- */
-
-#define __emul_prefix() NULL
-
-#endif /* _ASM_X86_NAMEI_H */
diff --git a/include/asm-x86/nmi.h b/include/asm-x86/nmi.h
index 1e363021e72f..d5e715f024dc 100644
--- a/include/asm-x86/nmi.h
+++ b/include/asm-x86/nmi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_NMI_H_
-#define _ASM_X86_NMI_H_
+#ifndef ASM_X86__NMI_H
+#define ASM_X86__NMI_H
 
 #include <linux/pm.h>
 #include <asm/irq.h>
@@ -15,38 +15,13 @@
  */
 int do_nmi_callback(struct pt_regs *regs, int cpu);
 
-#ifdef CONFIG_PM
-
-/** Replace the PM callback routine for NMI. */
-struct pm_dev *set_nmi_pm_callback(pm_callback callback);
-
-/** Unset the PM callback routine back to the default. */
-void unset_nmi_pm_callback(struct pm_dev *dev);
-
-#else
-
-static inline struct pm_dev *set_nmi_pm_callback(pm_callback callback)
-{
-        return 0;
-}
-
-static inline void unset_nmi_pm_callback(struct pm_dev *dev)
-{
-}
-
-#endif /* CONFIG_PM */
-
 #ifdef CONFIG_X86_64
 extern void default_do_nmi(struct pt_regs *);
-extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
-extern void nmi_watchdog_default(void);
-#else
-#define nmi_watchdog_default() do {} while (0)
 #endif
 
+extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int check_nmi_watchdog(void);
 extern int nmi_watchdog_enabled;
-extern int unknown_nmi_panic;
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int avail_to_resrv_perfctr_nmi(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
@@ -59,15 +34,14 @@ extern void stop_apic_nmi_watchdog(void *);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
 extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
+extern void cpu_nmi_set_wd_enabled(void);
 
 extern atomic_t nmi_active;
 extern unsigned int nmi_watchdog;
-#define NMI_DISABLED    -1
 #define NMI_NONE        0
 #define NMI_IO_APIC     1
 #define NMI_LOCAL_APIC  2
 #define NMI_INVALID     3
-#define NMI_DEFAULT     NMI_DISABLED
 
 struct ctl_table;
 struct file;
@@ -78,6 +52,24 @@ extern int unknown_nmi_panic;
 void __trigger_all_cpu_backtrace(void);
 #define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
 
+static inline void localise_nmi_watchdog(void)
+{
+        if (nmi_watchdog == NMI_IO_APIC)
+                nmi_watchdog = NMI_LOCAL_APIC;
+}
+
+/* check if nmi_watchdog is active (ie was specified at boot) */
+static inline int nmi_watchdog_active(void)
+{
+        /*
+         * actually it should be:
+         *      return (nmi_watchdog == NMI_LOCAL_APIC ||
+         *              nmi_watchdog == NMI_IO_APIC)
+         * but since they are power of two we could use a
+         * cheaper way --cvg
+         */
+        return nmi_watchdog & 0x3;
+}
 #endif
 
 void lapic_watchdog_stop(void);
@@ -90,4 +82,4 @@ void enable_lapic_nmi_watchdog(void);
 void stop_nmi(void);
 void restart_nmi(void);
 
-#endif
+#endif /* ASM_X86__NMI_H */
diff --git a/include/asm-x86/nops.h b/include/asm-x86/nops.h
index ad0bedd10b89..ae742721ae73 100644
--- a/include/asm-x86/nops.h
+++ b/include/asm-x86/nops.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_NOPS_H
-#define _ASM_NOPS_H 1
+#ifndef ASM_X86__NOPS_H
+#define ASM_X86__NOPS_H
 
 /* Define nops for use with alternative() */
 
@@ -115,4 +115,4 @@
 
 #define ASM_NOP_MAX 8
 
-#endif
+#endif /* ASM_X86__NOPS_H */
diff --git a/include/asm-x86/numa_32.h b/include/asm-x86/numa_32.h
index 03d0f7a9bf02..44cb07855c5b 100644
--- a/include/asm-x86/numa_32.h
+++ b/include/asm-x86/numa_32.h
@@ -1,15 +1,11 @@
-#ifndef _ASM_X86_32_NUMA_H
-#define _ASM_X86_32_NUMA_H 1
+#ifndef ASM_X86__NUMA_32_H
+#define ASM_X86__NUMA_32_H
 
 extern int pxm_to_nid(int pxm);
+extern void numa_remove_cpu(int cpu);
 
 #ifdef CONFIG_NUMA
-extern void __init remap_numa_kva(void);
-extern void set_highmem_pages_init(int);
-#else
-static inline void remap_numa_kva(void)
-{
-}
+extern void set_highmem_pages_init(void);
 #endif
 
-#endif /* _ASM_X86_32_NUMA_H */
+#endif /* ASM_X86__NUMA_32_H */
diff --git a/include/asm-x86/numa_64.h b/include/asm-x86/numa_64.h
index 22e87c9f6a80..15c990395b02 100644
--- a/include/asm-x86/numa_64.h
+++ b/include/asm-x86/numa_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X8664_NUMA_H
-#define _ASM_X8664_NUMA_H 1
+#ifndef ASM_X86__NUMA_64_H
+#define ASM_X86__NUMA_64_H
 
 #include <linux/nodemask.h>
 #include <asm/apicdef.h>
@@ -14,32 +14,30 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,
 
 #define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
-extern void numa_add_cpu(int cpu);
 extern void numa_init_array(void);
 extern int numa_off;
 
-extern void numa_set_node(int cpu, int node);
 extern void srat_reserve_add_area(int nodeid);
 extern int hotadd_percent;
 
 extern s16 apicid_to_node[MAX_LOCAL_APIC];
 
-extern void numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn);
 extern unsigned long numa_free_all_bootmem(void);
 extern void setup_node_bootmem(int nodeid, unsigned long start,
                                unsigned long end);
 
 #ifdef CONFIG_NUMA
 extern void __init init_cpu_to_node(void);
-
-static inline void clear_node_cpumask(int cpu)
-{
-        clear_bit(cpu, (unsigned long *)&node_to_cpumask_map[cpu_to_node(cpu)]);
-}
-
+extern void __cpuinit numa_set_node(int cpu, int node);
+extern void __cpuinit numa_clear_node(int cpu);
+extern void __cpuinit numa_add_cpu(int cpu);
+extern void __cpuinit numa_remove_cpu(int cpu);
 #else
-#define init_cpu_to_node() do {} while (0)
-#define clear_node_cpumask(cpu) do {} while (0)
+static inline void init_cpu_to_node(void)               { }
+static inline void numa_set_node(int cpu, int node)     { }
+static inline void numa_clear_node(int cpu)             { }
+static inline void numa_add_cpu(int cpu, int node)      { }
+static inline void numa_remove_cpu(int cpu)             { }
 #endif
 
-#endif
+#endif /* ASM_X86__NUMA_64_H */
diff --git a/include/asm-x86/numaq.h b/include/asm-x86/numaq.h
index 94b86c31239a..124bf7d4b70a 100644
--- a/include/asm-x86/numaq.h
+++ b/include/asm-x86/numaq.h
@@ -23,11 +23,12 @@
  * Send feedback to <gone@us.ibm.com>
  */
 
-#ifndef NUMAQ_H
-#define NUMAQ_H
+#ifndef ASM_X86__NUMAQ_H
+#define ASM_X86__NUMAQ_H
 
 #ifdef CONFIG_X86_NUMAQ
 
+extern int found_numaq;
 extern int get_memcfg_numaq(void);
 
 /*
@@ -156,10 +157,13 @@ struct sys_cfg_data {
         struct          eachquadmem eq[MAX_NUMNODES];   /* indexed by quad id */
 };
 
-static inline unsigned long *get_zholes_size(int nid)
+void numaq_tsc_disable(void);
+
+#else
+static inline int get_memcfg_numaq(void)
 {
-        return NULL;
+        return 0;
 }
 #endif /* CONFIG_X86_NUMAQ */
-#endif /* NUMAQ_H */
+#endif /* ASM_X86__NUMAQ_H */
 
diff --git a/include/asm-x86/mach-numaq/mach_apic.h b/include/asm-x86/numaq/apic.h
index 75a56e5afbe7..a8344ba6ea15 100644
--- a/include/asm-x86/mach-numaq/mach_apic.h
+++ b/include/asm-x86/numaq/apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef __ASM_NUMAQ_APIC_H
+#define __ASM_NUMAQ_APIC_H
 
 #include <asm/io.h>
 #include <linux/mmzone.h>
@@ -20,8 +20,14 @@ static inline cpumask_t target_cpus(void)
 #define INT_DELIVERY_MODE dest_LowestPrio
 #define INT_DEST_MODE 0     /* physical delivery on LOCAL quad */
  
-#define check_apicid_used(bitmap, apicid) physid_isset(apicid, bitmap)
-#define check_apicid_present(bit) physid_isset(bit, phys_cpu_present_map)
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+        return physid_isset(apicid, bitmap);
+}
+static inline unsigned long check_apicid_present(int bit)
+{
+        return physid_isset(bit, phys_cpu_present_map);
+}
 #define apicid_cluster(apicid) (apicid & 0xF0)
 
 static inline int apic_id_registered(void)
@@ -77,11 +83,6 @@ static inline int cpu_present_to_apicid(int mps_cpu)
                 return BAD_APICID;
 }
 
-static inline int generate_logical_apicid(int quad, int phys_apicid)
-{
-        return (quad << 4) + (phys_apicid ? phys_apicid << 1 : 1);
-}
-
 static inline int apicid_to_node(int logical_apicid) 
 {
         return logical_apicid >> 4;
@@ -95,30 +96,6 @@ static inline physid_mask_t apicid_to_cpu_present(int logical_apicid)
         return physid_mask_of_physid(cpu + 4*node);
 }
 
-struct mpc_config_translation {
-        unsigned char mpc_type;
-        unsigned char trans_len;
-        unsigned char trans_type;
-        unsigned char trans_quad;
-        unsigned char trans_global;
-        unsigned char trans_local;
-        unsigned short trans_reserved;
-};
-
-static inline int mpc_apic_id(struct mpc_config_processor *m, 
-                        struct mpc_config_translation *translation_record)
-{
-        int quad = translation_record->trans_quad;
-        int logical_apicid = generate_logical_apicid(quad, m->mpc_apicid);
-
-        printk("Processor #%d %u:%u APIC version %d (quad %d, apic %d)\n",
-               m->mpc_apicid,
-               (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
-               (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
-               m->mpc_apicver, quad, logical_apicid);
-        return logical_apicid;
-}
-
 extern void *xquad_portio;
 
 static inline void setup_portio_remap(void)
@@ -158,4 +135,4 @@ static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
         return cpuid_apic >> index_msb;
 }
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* __ASM_NUMAQ_APIC_H */
diff --git a/include/asm-x86/mach-numaq/mach_apicdef.h b/include/asm-x86/numaq/apicdef.h
index bf439d0690f5..e012a46cc22a 100644
--- a/include/asm-x86/mach-numaq/mach_apicdef.h
+++ b/include/asm-x86/numaq/apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef __ASM_NUMAQ_APICDEF_H
+#define __ASM_NUMAQ_APICDEF_H
 
 
 #define APIC_ID_MASK (0xF<<24)
diff --git a/include/asm-x86/mach-numaq/mach_ipi.h b/include/asm-x86/numaq/ipi.h
index c6044488e9e6..935588d286cf 100644
--- a/include/asm-x86/mach-numaq/mach_ipi.h
+++ b/include/asm-x86/numaq/ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef __ASM_NUMAQ_IPI_H
+#define __ASM_NUMAQ_IPI_H
 
 void send_IPI_mask_sequence(cpumask_t, int vector);
 
@@ -22,4 +22,4 @@ static inline void send_IPI_all(int vector)
         send_IPI_mask(cpu_online_map, vector);
 }
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* __ASM_NUMAQ_IPI_H */
diff --git a/include/asm-x86/numaq/mpparse.h b/include/asm-x86/numaq/mpparse.h
new file mode 100644
index 000000000000..252292e077b6
--- /dev/null
+++ b/include/asm-x86/numaq/mpparse.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_NUMAQ_MPPARSE_H
+#define __ASM_NUMAQ_MPPARSE_H
+
+extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
+                                char *productid);
+
+#endif /* __ASM_NUMAQ_MPPARSE_H */
diff --git a/include/asm-x86/mach-numaq/mach_wakecpu.h b/include/asm-x86/numaq/wakecpu.h
index 00530041a991..c577bda5b1c5 100644
--- a/include/asm-x86/mach-numaq/mach_wakecpu.h
+++ b/include/asm-x86/numaq/wakecpu.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_WAKECPU_H
-#define __ASM_MACH_WAKECPU_H
+#ifndef __ASM_NUMAQ_WAKECPU_H
+#define __ASM_NUMAQ_WAKECPU_H
 
 /* This file copes with machines that wakeup secondary CPUs by NMIs */
 
@@ -40,4 +40,4 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 
 #define inquire_remote_apic(apicid) {}
 
-#endif /* __ASM_MACH_WAKECPU_H */
+#endif /* __ASM_NUMAQ_WAKECPU_H */
diff --git a/include/asm-x86/olpc.h b/include/asm-x86/olpc.h
index 97d47133486f..d7328b1a05c1 100644
--- a/include/asm-x86/olpc.h
+++ b/include/asm-x86/olpc.h
@@ -1,7 +1,7 @@
 /* OLPC machine specific definitions */
 
-#ifndef ASM_OLPC_H_
-#define ASM_OLPC_H_
+#ifndef ASM_X86__OLPC_H
+#define ASM_X86__OLPC_H
 
 #include <asm/geode.h>
 
@@ -129,4 +129,4 @@ extern int olpc_ec_mask_unset(uint8_t bits);
 #define OLPC_GPIO_LID           geode_gpio(26)
 #define OLPC_GPIO_ECSCI         geode_gpio(27)
 
-#endif
+#endif /* ASM_X86__OLPC_H */
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
index dc936dddf161..c91574776751 100644
--- a/include/asm-x86/page.h
+++ b/include/asm-x86/page.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PAGE_H
-#define _ASM_X86_PAGE_H
+#ifndef ASM_X86__PAGE_H
+#define ASM_X86__PAGE_H
 
 #include <linux/const.h>
 
@@ -18,8 +18,11 @@
    (ie, 32-bit PAE). */
 #define PHYSICAL_PAGE_MASK      (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
 
-/* PTE_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
-#define PTE_MASK                ((pteval_t)PHYSICAL_PAGE_MASK)
+/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
+#define PTE_PFN_MASK            ((pteval_t)PHYSICAL_PAGE_MASK)
+
+/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
+#define PTE_FLAGS_MASK          (~PTE_PFN_MASK)
 
 #define PMD_PAGE_SIZE           (_AC(1, UL) << PMD_SHIFT)
 #define PMD_PAGE_MASK           (~(PMD_PAGE_SIZE-1))
@@ -29,8 +32,7 @@
 #define HPAGE_MASK              (~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
 
-/* to align the pointer to the (next) page boundary */
-#define PAGE_ALIGN(addr)        (((addr)+PAGE_SIZE-1)&PAGE_MASK)
+#define HUGE_MAX_HSTATE 2
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
@@ -51,9 +53,18 @@
 
 #ifndef __ASSEMBLY__
 
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pgprotval_t pgprot; } pgprot_t;
+
 extern int page_is_ram(unsigned long pagenr);
+extern int pagerange_is_ram(unsigned long start, unsigned long end);
 extern int devmem_is_allowed(unsigned long pagenr);
+extern void map_devmem(unsigned long pfn, unsigned long size,
+                       pgprot_t vma_prot);
+extern void unmap_devmem(unsigned long pfn, unsigned long size,
+                         pgprot_t vma_prot);
 
+extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
 struct page;
@@ -74,9 +85,6 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
         alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
-typedef struct { pgdval_t pgd; } pgd_t;
-typedef struct { pgprotval_t pgprot; } pgprot_t;
-
 static inline pgd_t native_make_pgd(pgdval_t val)
 {
         return (pgd_t) { val };
@@ -139,6 +147,11 @@ static inline pteval_t native_pte_val(pte_t pte)
         return pte.pte;
 }
 
+static inline pteval_t native_pte_flags(pte_t pte)
+{
+        return native_pte_val(pte) & PTE_FLAGS_MASK;
+}
+
 #define pgprot_val(x)   ((x).pgprot)
 #define __pgprot(x)     ((pgprot_t) { (x) } )
 
@@ -160,6 +173,7 @@ static inline pteval_t native_pte_val(pte_t pte)
 #endif
 
 #define pte_val(x)      native_pte_val(x)
+#define pte_flags(x)    native_pte_flags(x)
 #define __pte(x)        native_make_pte(x)
 
 #endif  /* CONFIG_PARAVIRT */
@@ -186,4 +200,4 @@ static inline pteval_t native_pte_val(pte_t pte)
 #define __HAVE_ARCH_GATE_AREA 1
 
 #endif  /* __KERNEL__ */
-#endif  /* _ASM_X86_PAGE_H */
+#endif /* ASM_X86__PAGE_H */
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
index 71a2e424e584..9c5a737a9af9 100644
--- a/include/asm-x86/page_32.h
+++ b/include/asm-x86/page_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PAGE_32_H
-#define _ASM_X86_PAGE_32_H
+#ifndef ASM_X86__PAGE_32_H
+#define ASM_X86__PAGE_32_H
 
 /*
  * This handles the memory map.
@@ -13,8 +13,17 @@
  */
 #define __PAGE_OFFSET           _AC(CONFIG_PAGE_OFFSET, UL)
 
+#ifdef CONFIG_4KSTACKS
+#define THREAD_ORDER    0
+#else
+#define THREAD_ORDER    1
+#endif
+#define THREAD_SIZE     (PAGE_SIZE << THREAD_ORDER)
+
+
 #ifdef CONFIG_X86_PAE
-#define __PHYSICAL_MASK_SHIFT   36
+/* 44=32+12, the limit we can fit into an unsigned long pfn */
+#define __PHYSICAL_MASK_SHIFT   44
 #define __VIRTUAL_MASK_SHIFT    32
 #define PAGETABLE_LEVELS        3
 
@@ -85,8 +94,13 @@ extern int nx_enabled;
 extern unsigned int __VMALLOC_RESERVE;
 extern int sysctl_legacy_va_layout;
 
-#define VMALLOC_RESERVE         ((unsigned long)__VMALLOC_RESERVE)
-#define MAXMEM                  (-__PAGE_OFFSET - __VMALLOC_RESERVE)
+extern void find_low_pfn_range(void);
+extern unsigned long init_memory_mapping(unsigned long start,
+                                         unsigned long end);
+extern void initmem_init(unsigned long, unsigned long);
+extern void free_initmem(void);
+extern void setup_bootmem_allocator(void);
+
 
 #ifdef CONFIG_X86_USE_3DNOW
 #include <asm/mmx.h>
@@ -115,4 +129,4 @@ static inline void copy_page(void *to, void *from)
 #endif  /* CONFIG_X86_3DNOW */
 #endif  /* !__ASSEMBLY__ */
 
-#endif /* _ASM_X86_PAGE_32_H */
+#endif /* ASM_X86__PAGE_32_H */
diff --git a/include/asm-x86/page_64.h b/include/asm-x86/page_64.h
index 6ea72859c491..5e64acfed0a4 100644
--- a/include/asm-x86/page_64.h
+++ b/include/asm-x86/page_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_PAGE_H
-#define _X86_64_PAGE_H
+#ifndef ASM_X86__PAGE_64_H
+#define ASM_X86__PAGE_64_H
 
 #define PAGETABLE_LEVELS        4
 
@@ -26,7 +26,13 @@
 #define PUD_PAGE_SIZE           (_AC(1, UL) << PUD_SHIFT)
 #define PUD_PAGE_MASK           (~(PUD_PAGE_SIZE-1))
 
-#define __PAGE_OFFSET           _AC(0xffff810000000000, UL)
+/*
+ * Set __PAGE_OFFSET to the most negative possible address +
+ * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
+ * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
+ * what Xen requires.
+ */
+#define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
 
 #define __PHYSICAL_START        CONFIG_PHYSICAL_START
 #define __KERNEL_ALIGN          0x200000
@@ -58,7 +64,8 @@
 void clear_page(void *page);
 void copy_page(void *to, void *from);
 
-extern unsigned long end_pfn;
+/* duplicated to the one in bootmem.h */
+extern unsigned long max_pfn;
 extern unsigned long phys_base;
 
 extern unsigned long __phys_addr(unsigned long);
@@ -83,11 +90,17 @@ typedef struct { pteval_t pte; } pte_t;
 extern unsigned long init_memory_mapping(unsigned long start,
                                          unsigned long end);
 
+extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern void free_initmem(void);
+
+extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
+extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
+
 #endif  /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_FLATMEM
-#define pfn_valid(pfn)          ((pfn) < end_pfn)
+#define pfn_valid(pfn)          ((pfn) < max_pfn)
 #endif
 
 
-#endif /* _X86_64_PAGE_H */
+#endif /* ASM_X86__PAGE_64_H */
diff --git a/include/asm-x86/param.h b/include/asm-x86/param.h
index 6f0d0422f4ca..0009cfb11a5f 100644
--- a/include/asm-x86/param.h
+++ b/include/asm-x86/param.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PARAM_H
-#define _ASM_X86_PARAM_H
+#ifndef ASM_X86__PARAM_H
+#define ASM_X86__PARAM_H
 
 #ifdef __KERNEL__
 # define HZ             CONFIG_HZ       /* Internal kernel timer frequency */
@@ -19,4 +19,4 @@
 
 #define MAXHOSTNAMELEN  64      /* max length of hostname */
 
-#endif /* _ASM_X86_PARAM_H */
+#endif /* ASM_X86__PARAM_H */
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index 0f13b945e240..8d6ae2f760d0 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_PARAVIRT_H
-#define __ASM_PARAVIRT_H
+#ifndef ASM_X86__PARAVIRT_H
+#define ASM_X86__PARAVIRT_H
 /* Various instructions on x86 need to be replaced for
  * para-virtualization: those hooks are defined here. */
 
@@ -84,7 +84,7 @@ struct pv_time_ops {
         int (*set_wallclock)(unsigned long);
 
         unsigned long long (*sched_clock)(void);
-        unsigned long (*get_cpu_khz)(void);
+        unsigned long (*get_tsc_khz)(void);
 };
 
 struct pv_cpu_ops {
@@ -115,12 +115,18 @@ struct pv_cpu_ops {
         void (*set_ldt)(const void *desc, unsigned entries);
         unsigned long (*store_tr)(void);
         void (*load_tls)(struct thread_struct *t, unsigned int cpu);
+#ifdef CONFIG_X86_64
+        void (*load_gs_index)(unsigned int idx);
+#endif
         void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum,
                                 const void *desc);
         void (*write_gdt_entry)(struct desc_struct *,
                                 int entrynum, const void *desc, int size);
         void (*write_idt_entry)(gate_desc *,
                                 int entrynum, const gate_desc *gate);
+        void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
+        void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
+
         void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
 
         void (*set_iopl_mask)(unsigned mask);
@@ -134,6 +140,7 @@ struct pv_cpu_ops {
 
         /* MSR, PMC and TSR operations.
            err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
+        u64 (*read_msr_amd)(unsigned int msr, int *err);
         u64 (*read_msr)(unsigned int msr, int *err);
         int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
 
@@ -141,8 +148,32 @@ struct pv_cpu_ops {
         u64 (*read_pmc)(int counter);
         unsigned long long (*read_tscp)(unsigned int *aux);
 
-        /* These two are jmp to, not actually called. */
-        void (*irq_enable_syscall_ret)(void);
+        /*
+         * Atomically enable interrupts and return to userspace.  This
+         * is only ever used to return to 32-bit processes; in a
+         * 64-bit kernel, it's used for 32-on-64 compat processes, but
+         * never native 64-bit processes.  (Jump, not call.)
+         */
+        void (*irq_enable_sysexit)(void);
+
+        /*
+         * Switch to usermode gs and return to 64-bit usermode using
+         * sysret.  Only used in 64-bit kernels to return to 64-bit
+         * processes.  Usermode register state, including %rsp, must
+         * already be restored.
+         */
+        void (*usergs_sysret64)(void);
+
+        /*
+         * Switch to usermode gs and return to 32-bit usermode using
+         * sysret.  Used to return to 32-on-64 compat processes.
+         * Other usermode register state, including %esp, must already
+         * be restored.
+         */
+        void (*usergs_sysret32)(void);
+
+        /* Normal iret.  Jump to this with the standard iret stack
+           frame set up. */
         void (*iret)(void);
 
         void (*swapgs)(void);
@@ -165,17 +196,14 @@ struct pv_irq_ops {
         void (*irq_enable)(void);
         void (*safe_halt)(void);
         void (*halt)(void);
+
+#ifdef CONFIG_X86_64
+        void (*adjust_exception_frame)(void);
+#endif
 };
 
 struct pv_apic_ops {
 #ifdef CONFIG_X86_LOCAL_APIC
-        /*
-         * Direct APIC operations, principally for VMI.  Ideally
-         * these shouldn't be in this interface.
-         */
-        void (*apic_write)(unsigned long reg, u32 v);
-        void (*apic_write_atomic)(unsigned long reg, u32 v);
-        u32 (*apic_read)(unsigned long reg);
         void (*setup_boot_clock)(void);
         void (*setup_secondary_clock)(void);
 
@@ -219,14 +247,21 @@ struct pv_mmu_ops {
         void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
                                  unsigned long va);
 
-        /* Hooks for allocating/releasing pagetable pages */
-        void (*alloc_pte)(struct mm_struct *mm, u32 pfn);
-        void (*alloc_pmd)(struct mm_struct *mm, u32 pfn);
-        void (*alloc_pmd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count);
-        void (*alloc_pud)(struct mm_struct *mm, u32 pfn);
-        void (*release_pte)(u32 pfn);
-        void (*release_pmd)(u32 pfn);
-        void (*release_pud)(u32 pfn);
+        /* Hooks for allocating and freeing a pagetable top-level */
+        int  (*pgd_alloc)(struct mm_struct *mm);
+        void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd);
+
+        /*
+         * Hooks for allocating/releasing pagetable pages when they're
+         * attached to a pagetable
+         */
+        void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
+        void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
+        void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
+        void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
+        void (*release_pte)(unsigned long pfn);
+        void (*release_pmd)(unsigned long pfn);
+        void (*release_pud)(unsigned long pfn);
 
         /* Pagetable manipulation functions */
         void (*set_pte)(pte_t *ptep, pte_t pteval);
@@ -238,7 +273,13 @@ struct pv_mmu_ops {
         void (*pte_update_defer)(struct mm_struct *mm,
                                  unsigned long addr, pte_t *ptep);
 
+        pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
+                                        pte_t *ptep);
+        void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
+                                        pte_t *ptep, pte_t pte);
+
         pteval_t (*pte_val)(pte_t);
+        pteval_t (*pte_flags)(pte_t);
         pte_t (*make_pte)(pteval_t pte);
 
         pgdval_t (*pgd_val)(pgd_t);
@@ -273,6 +314,23 @@ struct pv_mmu_ops {
 #endif
 
         struct pv_lazy_ops lazy_mode;
+
+        /* dom0 ops */
+
+        /* Sometimes the physical address is a pfn, and sometimes its
+           an mfn.  We can tell which is which from the index. */
+        void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
+                           unsigned long phys, pgprot_t flags);
+};
+
+struct raw_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);
 };
 
 /* This contains all the paravirt structures: we get a convenient
@@ -285,6 +343,7 @@ struct paravirt_patch_template {
         struct pv_irq_ops pv_irq_ops;
         struct pv_apic_ops pv_apic_ops;
         struct pv_mmu_ops pv_mmu_ops;
+        struct pv_lock_ops pv_lock_ops;
 };
 
 extern struct pv_info pv_info;
@@ -294,6 +353,7 @@ extern struct pv_cpu_ops pv_cpu_ops;
 extern struct pv_irq_ops pv_irq_ops;
 extern struct pv_apic_ops pv_apic_ops;
 extern struct pv_mmu_ops pv_mmu_ops;
+extern struct pv_lock_ops pv_lock_ops;
 
 #define PARAVIRT_PATCH(x)                                       \
         (offsetof(struct paravirt_patch_template, x) / sizeof(void *))
@@ -439,10 +499,17 @@ int paravirt_disable_iospace(void);
 #define VEXTRA_CLOBBERS  , "rax", "r8", "r9", "r10", "r11"
 #endif
 
+#ifdef CONFIG_PARAVIRT_DEBUG
+#define PVOP_TEST_NULL(op)      BUG_ON(op == NULL)
+#else
+#define PVOP_TEST_NULL(op)      ((void)op)
+#endif
+
 #define __PVOP_CALL(rettype, op, pre, post, ...)                        \
         ({                                                              \
                 rettype __ret;                                          \
                 PVOP_CALL_ARGS;                                 \
+                PVOP_TEST_NULL(op);                                     \
                 /* This is 32-bit specific, but is okay in 64-bit */    \
                 /* since this condition will never hold */              \
                 if (sizeof(rettype) > sizeof(unsigned long)) {          \
@@ -471,6 +538,7 @@ int paravirt_disable_iospace(void);
 #define __PVOP_VCALL(op, pre, post, ...)                                \
         ({                                                              \
                 PVOP_VCALL_ARGS;                                        \
+                PVOP_TEST_NULL(op);                                     \
                 asm volatile(pre                                        \
                              paravirt_alt(PARAVIRT_CALL)                \
                              post                                       \
@@ -657,6 +725,10 @@ static inline u64 paravirt_read_msr(unsigned msr, int *err)
 {
         return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
 }
+static inline u64 paravirt_read_msr_amd(unsigned msr, int *err)
+{
+        return PVOP_CALL2(u64, pv_cpu_ops.read_msr_amd, msr, err);
+}
 static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
 {
         return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
@@ -702,6 +774,13 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
         *p = paravirt_read_msr(msr, &err);
         return err;
 }
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+        int err;
+
+        *p = paravirt_read_msr_amd(msr, &err);
+        return err;
+}
 
 static inline u64 paravirt_read_tsc(void)
 {
@@ -720,7 +799,7 @@ static inline unsigned long long paravirt_sched_clock(void)
 {
         return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
-#define calculate_cpu_khz() (pv_time_ops.get_cpu_khz())
+#define calibrate_tsc() (pv_time_ops.get_tsc_khz())
 
 static inline unsigned long long paravirt_read_pmc(int counter)
 {
@@ -755,6 +834,16 @@ do {							\
         (aux) = __aux;                                  \
 } while (0)
 
+static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
+{
+        PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
+}
+
+static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
+{
+        PVOP_VCALL2(pv_cpu_ops.free_ldt, ldt, entries);
+}
+
 static inline void load_TR_desc(void)
 {
         PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
@@ -789,6 +878,13 @@ static inline void load_TLS(struct thread_struct *t, unsigned cpu)
         PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
 }
 
+#ifdef CONFIG_X86_64
+static inline void load_gs_index(unsigned int gs)
+{
+        PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs);
+}
+#endif
+
 static inline void write_ldt_entry(struct desc_struct *dt, int entry,
                                    const void *desc)
 {
@@ -822,24 +918,6 @@ static inline void slow_down_io(void)
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
-/*
- * Basic functions accessing APICs.
- */
-static inline void apic_write(unsigned long reg, u32 v)
-{
-        PVOP_VCALL2(pv_apic_ops.apic_write, reg, v);
-}
-
-static inline void apic_write_atomic(unsigned long reg, u32 v)
-{
-        PVOP_VCALL2(pv_apic_ops.apic_write_atomic, reg, v);
-}
-
-static inline u32 apic_read(unsigned long reg)
-{
-        return PVOP_CALL1(unsigned long, pv_apic_ops.apic_read, reg);
-}
-
 static inline void setup_boot_clock(void)
 {
         PVOP_VCALL0(pv_apic_ops.setup_boot_clock);
@@ -912,35 +990,45 @@ static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
         PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
 }
 
-static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned pfn)
+static inline int paravirt_pgd_alloc(struct mm_struct *mm)
+{
+        return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
+}
+
+static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+        PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
+}
+
+static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)
 {
         PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
 }
-static inline void paravirt_release_pte(unsigned pfn)
+static inline void paravirt_release_pte(unsigned long pfn)
 {
         PVOP_VCALL1(pv_mmu_ops.release_pte, pfn);
 }
 
-static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned pfn)
+static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
 {
         PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
 }
 
-static inline void paravirt_alloc_pmd_clone(unsigned pfn, unsigned clonepfn,
-                                            unsigned start, unsigned count)
+static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
+                                            unsigned long start, unsigned long count)
 {
         PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
 }
-static inline void paravirt_release_pmd(unsigned pfn)
+static inline void paravirt_release_pmd(unsigned long pfn)
 {
         PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
 }
 
-static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned pfn)
+static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
         PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn);
 }
-static inline void paravirt_release_pud(unsigned pfn)
+static inline void paravirt_release_pud(unsigned long pfn)
 {
         PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
 }
@@ -996,6 +1084,23 @@ static inline pteval_t pte_val(pte_t pte)
         return ret;
 }
 
+static inline pteval_t pte_flags(pte_t pte)
+{
+        pteval_t ret;
+
+        if (sizeof(pteval_t) > sizeof(long))
+                ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
+                                 pte.pte, (u64)pte.pte >> 32);
+        else
+                ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
+                                 pte.pte);
+
+#ifdef CONFIG_PARAVIRT_DEBUG
+        BUG_ON(ret & PTE_PFN_MASK);
+#endif
+        return ret;
+}
+
 static inline pgd_t __pgd(pgdval_t val)
 {
         pgdval_t ret;
@@ -1024,6 +1129,29 @@ static inline pgdval_t pgd_val(pgd_t pgd)
         return ret;
 }
 
+#define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+                                           pte_t *ptep)
+{
+        pteval_t ret;
+
+        ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start,
+                         mm, addr, ptep);
+
+        return (pte_t) { .pte = ret };
+}
+
+static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+                                           pte_t *ptep, pte_t pte)
+{
+        if (sizeof(pteval_t) > sizeof(long))
+                /* 5 arg words */
+                pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
+        else
+                PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit,
+                            mm, addr, ptep, pte.pte);
+}
+
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
         if (sizeof(pteval_t) > sizeof(long))
@@ -1252,9 +1380,52 @@ static inline void arch_flush_lazy_mmu_mode(void)
         }
 }
 
+static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
+                                unsigned long phys, pgprot_t flags)
+{
+        pv_mmu_ops.set_fixmap(idx, phys, flags);
+}
+
 void _paravirt_nop(void);
 #define paravirt_nop    ((void *)_paravirt_nop)
 
+void paravirt_use_bytelocks(void);
+
+#ifdef CONFIG_SMP
+
+static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
+{
+        return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
+}
+
+static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
+{
+        return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
+}
+
+static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
+{
+        PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
+}
+
+static __always_inline void __raw_spin_lock_flags(struct raw_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)
+{
+        return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
+}
+
+static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
+{
+        PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
+}
+
+#endif
+
 /* These all sit in the .parainstructions section to tell us what to patch. */
 struct paravirt_patch_site {
         u8 *instr;              /* original instructions */
@@ -1277,8 +1448,8 @@ extern struct paravirt_patch_site __parainstructions[],
  * caller saved registers but the argument parameter */
 #define PV_SAVE_REGS "pushq %%rdi;"
 #define PV_RESTORE_REGS "popq %%rdi;"
-#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx"
-#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx"
+#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi"
+#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi"
 #define PV_FLAGS_ARG "D"
 #endif
 
@@ -1339,6 +1510,7 @@ static inline unsigned long __raw_local_irq_save(void)
         return f;
 }
 
+
 /* Make sure as little as possible of this mess escapes. */
 #undef PARAVIRT_CALL
 #undef __PVOP_CALL
@@ -1370,59 +1542,109 @@ static inline unsigned long __raw_local_irq_save(void)
 
 
 #ifdef CONFIG_X86_64
-#define PV_SAVE_REGS   pushq %rax; pushq %rdi; pushq %rcx; pushq %rdx
-#define PV_RESTORE_REGS popq %rdx; popq %rcx; popq %rdi; popq %rax
+#define PV_SAVE_REGS                            \
+        push %rax;                              \
+        push %rcx;                              \
+        push %rdx;                              \
+        push %rsi;                              \
+        push %rdi;                              \
+        push %r8;                               \
+        push %r9;                               \
+        push %r10;                              \
+        push %r11
+#define PV_RESTORE_REGS                         \
+        pop %r11;                               \
+        pop %r10;                               \
+        pop %r9;                                \
+        pop %r8;                                \
+        pop %rdi;                               \
+        pop %rsi;                               \
+        pop %rdx;                               \
+        pop %rcx;                               \
+        pop %rax
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 8)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
+#define PARA_INDIRECT(addr)     *addr(%rip)
 #else
 #define PV_SAVE_REGS   pushl %eax; pushl %edi; pushl %ecx; pushl %edx
 #define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 4)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
+#define PARA_INDIRECT(addr)     *%cs:addr
 #endif
 
 #define INTERRUPT_RETURN                                                \
         PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,       \
-                  jmp *%cs:pv_cpu_ops+PV_CPU_iret)
+                  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))
 
 #define DISABLE_INTERRUPTS(clobbers)                                    \
         PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
-                  PV_SAVE_REGS;                 \
-                  call *%cs:pv_irq_ops+PV_IRQ_irq_disable;              \
+                  PV_SAVE_REGS;                                         \
+                  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);    \
                   PV_RESTORE_REGS;)                     \
 
 #define ENABLE_INTERRUPTS(clobbers)                                     \
         PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,  \
-                  PV_SAVE_REGS;                 \
-                  call *%cs:pv_irq_ops+PV_IRQ_irq_enable;               \
+                  PV_SAVE_REGS;                                         \
+                  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);     \
                   PV_RESTORE_REGS;)
 
-#define ENABLE_INTERRUPTS_SYSCALL_RET                                   \
-        PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_syscall_ret),\
+#define USERGS_SYSRET32                                                 \
+        PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),       \
                   CLBR_NONE,                                            \
-                  jmp *%cs:pv_cpu_ops+PV_CPU_irq_enable_syscall_ret)
-
+                  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32))
 
 #ifdef CONFIG_X86_32
-#define GET_CR0_INTO_EAX                        \
-        push %ecx; push %edx;                   \
-        call *pv_cpu_ops+PV_CPU_read_cr0;       \
+#define GET_CR0_INTO_EAX                                \
+        push %ecx; push %edx;                           \
+        call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \
         pop %edx; pop %ecx
-#else
+
+#define ENABLE_INTERRUPTS_SYSEXIT                                       \
+        PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),    \
+                  CLBR_NONE,                                            \
+                  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
+
+
+#else   /* !CONFIG_X86_32 */
+
+/*
+ * If swapgs is used while the userspace stack is still current,
+ * there's no way to call a pvop.  The PV replacement *must* be
+ * inlined, or the swapgs instruction must be trapped and emulated.
+ */
+#define SWAPGS_UNSAFE_STACK                                             \
+        PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,     \
+                  swapgs)
+
 #define SWAPGS                                                          \
         PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,     \
                   PV_SAVE_REGS;                                         \
-                  call *pv_cpu_ops+PV_CPU_swapgs;                       \
+                  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);         \
                   PV_RESTORE_REGS                                       \
                  )
 
-#define GET_CR2_INTO_RCX                        \
-        call *pv_mmu_ops+PV_MMU_read_cr2;       \
-        movq %rax, %rcx;                        \
+#define GET_CR2_INTO_RCX                                \
+        call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2); \
+        movq %rax, %rcx;                                \
         xorq %rax, %rax;
 
-#endif
+#define PARAVIRT_ADJUST_EXCEPTION_FRAME                                 \
+        PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \
+                  CLBR_NONE,                                            \
+                  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame))
+
+#define USERGS_SYSRET64                                                 \
+        PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),       \
+                  CLBR_NONE,                                            \
+                  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#define ENABLE_INTERRUPTS_SYSEXIT32                                     \
+        PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),    \
+                  CLBR_NONE,                                            \
+                  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
+#endif  /* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_PARAVIRT */
-#endif  /* __ASM_PARAVIRT_H */
+#endif /* ASM_X86__PARAVIRT_H */
diff --git a/include/asm-x86/parport.h b/include/asm-x86/parport.h
index 3c4ffeb467e9..2e3dda4dc3d9 100644
--- a/include/asm-x86/parport.h
+++ b/include/asm-x86/parport.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PARPORT_H
-#define _ASM_X86_PARPORT_H
+#ifndef ASM_X86__PARPORT_H
+#define ASM_X86__PARPORT_H
 
 static int __devinit parport_pc_find_isa_ports(int autoirq, int autodma);
 static int __devinit parport_pc_find_nonpci_ports(int autoirq, int autodma)
@@ -7,4 +7,4 @@ static int __devinit parport_pc_find_nonpci_ports(int autoirq, int autodma)
         return parport_pc_find_isa_ports(autoirq, autodma);
 }
 
-#endif /* _ASM_X86_PARPORT_H */
+#endif /* ASM_X86__PARPORT_H */
diff --git a/include/asm-x86/pat.h b/include/asm-x86/pat.h
index 88f60cc6a227..482c3e3f9879 100644
--- a/include/asm-x86/pat.h
+++ b/include/asm-x86/pat.h
@@ -1,14 +1,13 @@
-
-#ifndef _ASM_PAT_H
-#define _ASM_PAT_H 1
+#ifndef ASM_X86__PAT_H
+#define ASM_X86__PAT_H
 
 #include <linux/types.h>
 
 #ifdef CONFIG_X86_PAT
-extern int pat_wc_enabled;
+extern int pat_enabled;
 extern void validate_pat_support(struct cpuinfo_x86 *c);
 #else
-static const int pat_wc_enabled = 0;
+static const int pat_enabled;
 static inline void validate_pat_support(struct cpuinfo_x86 *c) { }
 #endif
 
@@ -20,5 +19,4 @@ extern int free_memtype(u64 start, u64 end);
 
 extern void pat_disable(char *reason);
 
-#endif
-
+#endif /* ASM_X86__PAT_H */
diff --git a/include/asm-x86/pci-direct.h b/include/asm-x86/pci-direct.h
index 5b21485be573..da42be07b690 100644
--- a/include/asm-x86/pci-direct.h
+++ b/include/asm-x86/pci-direct.h
@@ -1,5 +1,5 @@
-#ifndef ASM_PCI_DIRECT_H
-#define ASM_PCI_DIRECT_H 1
+#ifndef ASM_X86__PCI_DIRECT_H
+#define ASM_X86__PCI_DIRECT_H
 
 #include <linux/types.h>
 
@@ -11,7 +11,11 @@ extern u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset);
 extern u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset);
 extern void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset, u32 val);
 extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val);
+extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val);
 
 extern int early_pci_allowed(void);
 
-#endif
+extern unsigned int pci_early_dump_regs;
+extern void early_dump_pci_device(u8 bus, u8 slot, u8 func);
+extern void early_dump_pci_devices(void);
+#endif /* ASM_X86__PCI_DIRECT_H */
diff --git a/include/asm-x86/pci.h b/include/asm-x86/pci.h
index 30bbde0cb34b..602583192991 100644
--- a/include/asm-x86/pci.h
+++ b/include/asm-x86/pci.h
@@ -1,5 +1,5 @@
-#ifndef __x86_PCI_H
-#define __x86_PCI_H
+#ifndef ASM_X86__PCI_H
+#define ASM_X86__PCI_H
 
 #include <linux/mm.h> /* for struct page */
 #include <linux/types.h>
@@ -18,6 +18,8 @@ struct pci_sysdata {
 #endif
 };
 
+extern int pci_routeirq;
+
 /* scan a bus after allocating a pci_sysdata for it */
 extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
                                             int node);
@@ -109,4 +111,4 @@ static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus)
 }
 #endif
 
-#endif
+#endif /* ASM_X86__PCI_H */
diff --git a/include/asm-x86/pci_32.h b/include/asm-x86/pci_32.h
index 8c4c3a0368e2..3f2288207c0c 100644
--- a/include/asm-x86/pci_32.h
+++ b/include/asm-x86/pci_32.h
@@ -1,5 +1,5 @@
-#ifndef __i386_PCI_H
-#define __i386_PCI_H
+#ifndef ASM_X86__PCI_32_H
+#define ASM_X86__PCI_32_H
 
 
 #ifdef __KERNEL__
@@ -18,15 +18,17 @@ struct pci_dev;
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
 /* pci_unmap_{page,single} is a nop so... */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
-#define pci_unmap_addr(PTR, ADDR_NAME)          (0)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
-#define pci_unmap_len(PTR, LEN_NAME)            (0)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)   do { } while (0)
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       dma_addr_t ADDR_NAME[0];
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0];
+#define pci_unmap_addr(PTR, ADDR_NAME)  sizeof((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+        do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
+#define pci_unmap_len(PTR, LEN_NAME)            sizeof((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
+        do { break; } while (pci_unmap_len(PTR, LEN_NAME))
 
 
 #endif /* __KERNEL__ */
 
 
-#endif /* __i386_PCI_H */
+#endif /* ASM_X86__PCI_32_H */
diff --git a/include/asm-x86/pci_64.h b/include/asm-x86/pci_64.h
index f330234ffa5c..f72e12d5770e 100644
--- a/include/asm-x86/pci_64.h
+++ b/include/asm-x86/pci_64.h
@@ -1,5 +1,5 @@
-#ifndef __x8664_PCI_H
-#define __x8664_PCI_H
+#ifndef ASM_X86__PCI_64_H
+#define ASM_X86__PCI_64_H
 
 #ifdef __KERNEL__
 
@@ -63,4 +63,4 @@ extern void pci_iommu_alloc(void);
 
 #endif /* __KERNEL__ */
 
-#endif /* __x8664_PCI_H */
+#endif /* ASM_X86__PCI_64_H */
diff --git a/include/asm-x86/pda.h b/include/asm-x86/pda.h
index 101fb9e11954..80860afffbdb 100644
--- a/include/asm-x86/pda.h
+++ b/include/asm-x86/pda.h
@@ -1,5 +1,5 @@
-#ifndef X86_64_PDA_H
-#define X86_64_PDA_H
+#ifndef ASM_X86__PDA_H
+#define ASM_X86__PDA_H
 
 #ifndef __ASSEMBLY__
 #include <linux/stddef.h>
@@ -22,6 +22,8 @@ struct x8664_pda {
                                            offset 40!!! */
 #endif
         char *irqstackptr;
+        short nodenumber;               /* number of current node (32k max) */
+        short in_bootmem;               /* pda lives in bootmem */
         unsigned int __softirq_pending;
         unsigned int __nmi_count;       /* number of NMI on this CPUs */
         short mmu_state;
@@ -37,8 +39,7 @@ struct x8664_pda {
         unsigned irq_spurious_count;
 } ____cacheline_aligned_in_smp;
 
-extern struct x8664_pda *_cpu_pda[];
-extern struct x8664_pda boot_cpu_pda[];
+extern struct x8664_pda **_cpu_pda;
 extern void pda_init(int);
 
 #define cpu_pda(i) (_cpu_pda[i])
@@ -133,4 +134,4 @@ do {									\
 
 #define PDA_STACKOFFSET (5*8)
 
-#endif
+#endif /* ASM_X86__PDA_H */
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
index 736fc3bb8e1e..e10a1d0678cf 100644
--- a/include/asm-x86/percpu.h
+++ b/include/asm-x86/percpu.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PERCPU_H_
-#define _ASM_X86_PERCPU_H_
+#ifndef ASM_X86__PERCPU_H
+#define ASM_X86__PERCPU_H
 
 #ifdef CONFIG_X86_64
 #include <linux/compiler.h>
@@ -22,6 +22,32 @@
 
 DECLARE_PER_CPU(struct x8664_pda, pda);
 
+/*
+ * These are supposed to be implemented as a single instruction which
+ * operates on the per-cpu data base segment.  x86-64 doesn't have
+ * that yet, so this is a fairly inefficient workaround for the
+ * meantime.  The single instruction is atomic with respect to
+ * preemption and interrupts, so we need to explicitly disable
+ * interrupts here to achieve the same effect.  However, because it
+ * can be used from within interrupt-disable/enable, we can't actually
+ * disable interrupts; disabling preemption is enough.
+ */
+#define x86_read_percpu(var)                                            \
+        ({                                                              \
+                typeof(per_cpu_var(var)) __tmp;                         \
+                preempt_disable();                                      \
+                __tmp = __get_cpu_var(var);                             \
+                preempt_enable();                                       \
+                __tmp;                                                  \
+        })
+
+#define x86_write_percpu(var, val)                                      \
+        do {                                                            \
+                preempt_disable();                                      \
+                __get_cpu_var(var) = (val);                             \
+                preempt_enable();                                       \
+        } while(0)
+
 #else /* CONFIG_X86_64 */
 
 #ifdef __ASSEMBLY__
@@ -143,4 +169,50 @@ do {							\
 #define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
 #endif /* !__ASSEMBLY__ */
 #endif /* !CONFIG_X86_64 */
-#endif /* _ASM_X86_PERCPU_H_ */
+
+#ifdef CONFIG_SMP
+
+/*
+ * Define the "EARLY_PER_CPU" macros.  These are used for some per_cpu
+ * variables that are initialized and accessed before there are per_cpu
+ * areas allocated.
+ */
+
+#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)                  \
+        DEFINE_PER_CPU(_type, _name) = _initvalue;                      \
+        __typeof__(_type) _name##_early_map[NR_CPUS] __initdata =       \
+                                { [0 ... NR_CPUS-1] = _initvalue };     \
+        __typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)                      \
+        EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name)                     \
+        DECLARE_PER_CPU(_type, _name);                          \
+        extern __typeof__(_type) *_name##_early_ptr;            \
+        extern __typeof__(_type)  _name##_early_map[]
+
+#define early_per_cpu_ptr(_name) (_name##_early_ptr)
+#define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
+#define early_per_cpu(_name, _cpu)                              \
+        (early_per_cpu_ptr(_name) ?                             \
+                early_per_cpu_ptr(_name)[_cpu] :                \
+                per_cpu(_name, _cpu))
+
+#else   /* !CONFIG_SMP */
+#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)          \
+        DEFINE_PER_CPU(_type, _name) = _initvalue
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)                      \
+        EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name)                     \
+        DECLARE_PER_CPU(_type, _name)
+
+#define early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
+#define early_per_cpu_ptr(_name) NULL
+/* no early_per_cpu_map() */
+
+#endif  /* !CONFIG_SMP */
+
+#endif /* ASM_X86__PERCPU_H */
diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h
index 91e4641f3f31..3cd23adedae8 100644
--- a/include/asm-x86/pgalloc.h
+++ b/include/asm-x86/pgalloc.h
@@ -1,13 +1,17 @@
-#ifndef _ASM_X86_PGALLOC_H
-#define _ASM_X86_PGALLOC_H
+#ifndef ASM_X86__PGALLOC_H
+#define ASM_X86__PGALLOC_H
 
 #include <linux/threads.h>
 #include <linux/mm.h>           /* for struct page */
 #include <linux/pagemap.h>
 
+static inline int  __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
+#define paravirt_pgd_alloc(mm)  __paravirt_pgd_alloc(mm)
+static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {}
 static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)  {}
 static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)  {}
 static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
@@ -107,4 +111,4 @@ extern void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
 #endif  /* PAGETABLE_LEVELS > 3 */
 #endif  /* PAGETABLE_LEVELS > 2 */
 
-#endif  /* _ASM_X86_PGALLOC_H */
+#endif /* ASM_X86__PGALLOC_H */
diff --git a/include/asm-x86/pgtable-2level-defs.h b/include/asm-x86/pgtable-2level-defs.h
index 0f71c9f13da4..7ec48f4e5347 100644
--- a/include/asm-x86/pgtable-2level-defs.h
+++ b/include/asm-x86/pgtable-2level-defs.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_2LEVEL_DEFS_H
-#define _I386_PGTABLE_2LEVEL_DEFS_H
+#ifndef ASM_X86__PGTABLE_2LEVEL_DEFS_H
+#define ASM_X86__PGTABLE_2LEVEL_DEFS_H
 
 #define SHARED_KERNEL_PMD       0
 
@@ -17,4 +17,4 @@
 
 #define PTRS_PER_PTE    1024
 
-#endif /* _I386_PGTABLE_2LEVEL_DEFS_H */
+#endif /* ASM_X86__PGTABLE_2LEVEL_DEFS_H */
diff --git a/include/asm-x86/pgtable-2level.h b/include/asm-x86/pgtable-2level.h
index 46bc52c0eae1..81762081dcd8 100644
--- a/include/asm-x86/pgtable-2level.h
+++ b/include/asm-x86/pgtable-2level.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_2LEVEL_H
-#define _I386_PGTABLE_2LEVEL_H
+#ifndef ASM_X86__PGTABLE_2LEVEL_H
+#define ASM_X86__PGTABLE_2LEVEL_H
 
 #define pte_ERROR(e) \
         printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
@@ -53,9 +53,7 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#define pte_page(x)             pfn_to_page(pte_pfn(x))
 #define pte_none(x)             (!(x).pte_low)
-#define pte_pfn(x)              (pte_val(x) >> PAGE_SHIFT)
 
 /*
  * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
@@ -78,4 +76,4 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #define __pte_to_swp_entry(pte)         ((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)           ((pte_t) { .pte = (x).val })
 
-#endif /* _I386_PGTABLE_2LEVEL_H */
+#endif /* ASM_X86__PGTABLE_2LEVEL_H */
diff --git a/include/asm-x86/pgtable-3level-defs.h b/include/asm-x86/pgtable-3level-defs.h
index 448ac9516314..c05fe6ff3720 100644
--- a/include/asm-x86/pgtable-3level-defs.h
+++ b/include/asm-x86/pgtable-3level-defs.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_3LEVEL_DEFS_H
-#define _I386_PGTABLE_3LEVEL_DEFS_H
+#ifndef ASM_X86__PGTABLE_3LEVEL_DEFS_H
+#define ASM_X86__PGTABLE_3LEVEL_DEFS_H
 
 #ifdef CONFIG_PARAVIRT
 #define SHARED_KERNEL_PMD       (pv_info.shared_kernel_pmd)
@@ -25,4 +25,4 @@
  */
 #define PTRS_PER_PTE    512
 
-#endif /* _I386_PGTABLE_3LEVEL_DEFS_H */
+#endif /* ASM_X86__PGTABLE_3LEVEL_DEFS_H */
diff --git a/include/asm-x86/pgtable-3level.h b/include/asm-x86/pgtable-3level.h
index c93dbb6c2624..75f4276b5ddb 100644
--- a/include/asm-x86/pgtable-3level.h
+++ b/include/asm-x86/pgtable-3level.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_3LEVEL_H
-#define _I386_PGTABLE_3LEVEL_H
+#ifndef ASM_X86__PGTABLE_3LEVEL_H
+#define ASM_X86__PGTABLE_3LEVEL_H
 
 /*
  * Intel Physical Address Extension (PAE) Mode - three-level page
@@ -25,7 +25,7 @@ static inline int pud_none(pud_t pud)
 
 static inline int pud_bad(pud_t pud)
 {
-        return (pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
+        return (pud_val(pud) & ~(PTE_PFN_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
 }
 
 static inline int pud_present(pud_t pud)
@@ -120,9 +120,9 @@ static inline void pud_clear(pud_t *pudp)
                 write_cr3(pgd);
 }
 
-#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_MASK))
+#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_PFN_MASK))
 
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_MASK))
+#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_PFN_MASK))
 
 
 /* Find an entry in the second-level page table.. */
@@ -151,18 +151,11 @@ static inline int pte_same(pte_t a, pte_t b)
         return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
 }
 
-#define pte_page(x)     pfn_to_page(pte_pfn(x))
-
 static inline int pte_none(pte_t pte)
 {
         return !pte.pte_low && !pte.pte_high;
 }
 
-static inline unsigned long pte_pfn(pte_t pte)
-{
-        return (pte_val(pte) & PTE_MASK) >> PAGE_SHIFT;
-}
-
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.
@@ -179,4 +172,4 @@ static inline unsigned long pte_pfn(pte_t pte)
 #define __pte_to_swp_entry(pte)         ((swp_entry_t){ (pte).pte_high })
 #define __swp_entry_to_pte(x)           ((pte_t){ { .pte_high = (x).val } })
 
-#endif /* _I386_PGTABLE_3LEVEL_H */
+#endif /* ASM_X86__PGTABLE_3LEVEL_H */
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index 97c271b2910b..ed932453ef26 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PGTABLE_H
-#define _ASM_X86_PGTABLE_H
+#ifndef ASM_X86__PGTABLE_H
+#define ASM_X86__PGTABLE_H
 
 #define FIRST_USER_ADDRESS      0
 
@@ -18,32 +18,32 @@
 #define _PAGE_BIT_UNUSED2       10
 #define _PAGE_BIT_UNUSED3       11
 #define _PAGE_BIT_PAT_LARGE     12      /* On 2MB or 1GB pages */
+#define _PAGE_BIT_SPECIAL       _PAGE_BIT_UNUSED1
+#define _PAGE_BIT_CPA_TEST      _PAGE_BIT_UNUSED1
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
-/*
- * Note: we use _AC(1, L) instead of _AC(1, UL) so that we get a
- * sign-extended value on 32-bit with all 1's in the upper word,
- * which preserves the upper pte values on 64-bit ptes:
- */
-#define _PAGE_PRESENT   (_AC(1, L)<<_PAGE_BIT_PRESENT)
-#define _PAGE_RW        (_AC(1, L)<<_PAGE_BIT_RW)
-#define _PAGE_USER      (_AC(1, L)<<_PAGE_BIT_USER)
-#define _PAGE_PWT       (_AC(1, L)<<_PAGE_BIT_PWT)
-#define _PAGE_PCD       (_AC(1, L)<<_PAGE_BIT_PCD)
-#define _PAGE_ACCESSED  (_AC(1, L)<<_PAGE_BIT_ACCESSED)
-#define _PAGE_DIRTY     (_AC(1, L)<<_PAGE_BIT_DIRTY)
-#define _PAGE_PSE       (_AC(1, L)<<_PAGE_BIT_PSE)      /* 2MB page */
-#define _PAGE_GLOBAL    (_AC(1, L)<<_PAGE_BIT_GLOBAL)   /* Global TLB entry */
-#define _PAGE_UNUSED1   (_AC(1, L)<<_PAGE_BIT_UNUSED1)
-#define _PAGE_UNUSED2   (_AC(1, L)<<_PAGE_BIT_UNUSED2)
-#define _PAGE_UNUSED3   (_AC(1, L)<<_PAGE_BIT_UNUSED3)
-#define _PAGE_PAT       (_AC(1, L)<<_PAGE_BIT_PAT)
-#define _PAGE_PAT_LARGE (_AC(1, L)<<_PAGE_BIT_PAT_LARGE)
+#define _PAGE_PRESENT   (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
+#define _PAGE_RW        (_AT(pteval_t, 1) << _PAGE_BIT_RW)
+#define _PAGE_USER      (_AT(pteval_t, 1) << _PAGE_BIT_USER)
+#define _PAGE_PWT       (_AT(pteval_t, 1) << _PAGE_BIT_PWT)
+#define _PAGE_PCD       (_AT(pteval_t, 1) << _PAGE_BIT_PCD)
+#define _PAGE_ACCESSED  (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
+#define _PAGE_DIRTY     (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
+#define _PAGE_PSE       (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
+#define _PAGE_GLOBAL    (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
+#define _PAGE_UNUSED1   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
+#define _PAGE_UNUSED2   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED2)
+#define _PAGE_UNUSED3   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
+#define _PAGE_PAT       (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
+#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
+#define _PAGE_SPECIAL   (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
+#define _PAGE_CPA_TEST  (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define __HAVE_ARCH_PTE_SPECIAL
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-#define _PAGE_NX        (_AC(1, ULL) << _PAGE_BIT_NX)
+#define _PAGE_NX        (_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else
-#define _PAGE_NX        0
+#define _PAGE_NX        (_AT(pteval_t, 0))
 #endif
 
 /* If _PAGE_PRESENT is clear, we use these: */
@@ -58,8 +58,8 @@
                          _PAGE_DIRTY)
 
 /* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK  (PTE_MASK | _PAGE_PCD | _PAGE_PWT |             \
-                         _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK  (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |         \
+                         _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
 
 #define _PAGE_CACHE_MASK        (_PAGE_PCD | _PAGE_PWT)
 #define _PAGE_CACHE_WB          (0)
@@ -83,19 +83,9 @@
 #define PAGE_READONLY_EXEC      __pgprot(_PAGE_PRESENT | _PAGE_USER |   \
                                          _PAGE_ACCESSED)
 
-#ifdef CONFIG_X86_32
-#define _PAGE_KERNEL_EXEC \
-        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
-#define _PAGE_KERNEL (_PAGE_KERNEL_EXEC | _PAGE_NX)
-
-#ifndef __ASSEMBLY__
-extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
-#endif  /* __ASSEMBLY__ */
-#else
 #define __PAGE_KERNEL_EXEC                                              \
-        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+        (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
 #define __PAGE_KERNEL           (__PAGE_KERNEL_EXEC | _PAGE_NX)
-#endif
 
 #define __PAGE_KERNEL_RO                (__PAGE_KERNEL & ~_PAGE_RW)
 #define __PAGE_KERNEL_RX                (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
@@ -106,26 +96,22 @@ extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
 #define __PAGE_KERNEL_VSYSCALL          (__PAGE_KERNEL_RX | _PAGE_USER)
 #define __PAGE_KERNEL_VSYSCALL_NOCACHE  (__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
 #define __PAGE_KERNEL_LARGE             (__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_NOCACHE     (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_EXEC        (__PAGE_KERNEL_EXEC | _PAGE_PSE)
 
-#ifdef CONFIG_X86_32
-# define MAKE_GLOBAL(x)                 __pgprot((x))
-#else
-# define MAKE_GLOBAL(x)                 __pgprot((x) | _PAGE_GLOBAL)
-#endif
-
-#define PAGE_KERNEL                     MAKE_GLOBAL(__PAGE_KERNEL)
-#define PAGE_KERNEL_RO                  MAKE_GLOBAL(__PAGE_KERNEL_RO)
-#define PAGE_KERNEL_EXEC                MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
-#define PAGE_KERNEL_RX                  MAKE_GLOBAL(__PAGE_KERNEL_RX)
-#define PAGE_KERNEL_WC                  MAKE_GLOBAL(__PAGE_KERNEL_WC)
-#define PAGE_KERNEL_NOCACHE             MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
-#define PAGE_KERNEL_UC_MINUS            MAKE_GLOBAL(__PAGE_KERNEL_UC_MINUS)
-#define PAGE_KERNEL_EXEC_NOCACHE        MAKE_GLOBAL(__PAGE_KERNEL_EXEC_NOCACHE)
-#define PAGE_KERNEL_LARGE               MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
-#define PAGE_KERNEL_LARGE_EXEC          MAKE_GLOBAL(__PAGE_KERNEL_LARGE_EXEC)
-#define PAGE_KERNEL_VSYSCALL            MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_VSYSCALL_NOCACHE    MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+#define PAGE_KERNEL                     __pgprot(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO                  __pgprot(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_EXEC                __pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RX                  __pgprot(__PAGE_KERNEL_RX)
+#define PAGE_KERNEL_WC                  __pgprot(__PAGE_KERNEL_WC)
+#define PAGE_KERNEL_NOCACHE             __pgprot(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_UC_MINUS            __pgprot(__PAGE_KERNEL_UC_MINUS)
+#define PAGE_KERNEL_EXEC_NOCACHE        __pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
+#define PAGE_KERNEL_LARGE               __pgprot(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_LARGE_NOCACHE       __pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
+#define PAGE_KERNEL_LARGE_EXEC          __pgprot(__PAGE_KERNEL_LARGE_EXEC)
+#define PAGE_KERNEL_VSYSCALL            __pgprot(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_VSYSCALL_NOCACHE    __pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
 
 /*         xwr */
 #define __P000  PAGE_NONE
@@ -146,6 +132,17 @@ extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
 #define __S110  PAGE_SHARED_EXEC
 #define __S111  PAGE_SHARED_EXEC
 
+/*
+ * early identity mapping  pte attrib macros.
+ */
+#ifdef CONFIG_X86_64
+#define __PAGE_KERNEL_IDENT_LARGE_EXEC  __PAGE_KERNEL_LARGE_EXEC
+#else
+#define PTE_IDENT_ATTR   0x003          /* PRESENT+RW */
+#define PDE_IDENT_ATTR   0x063          /* PRESENT+RW+DIRTY+ACCESSED */
+#define PGD_IDENT_ATTR   0x001          /* PRESENT (no other attributes) */
+#endif
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -164,44 +161,51 @@ extern struct list_head pgd_list;
  */
 static inline int pte_dirty(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_DIRTY;
+        return pte_flags(pte) & _PAGE_DIRTY;
 }
 
 static inline int pte_young(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_ACCESSED;
+        return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
 static inline int pte_write(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_RW;
+        return pte_flags(pte) & _PAGE_RW;
 }
 
 static inline int pte_file(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_FILE;
+        return pte_flags(pte) & _PAGE_FILE;
 }
 
 static inline int pte_huge(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_PSE;
+        return pte_flags(pte) & _PAGE_PSE;
 }
 
 static inline int pte_global(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_GLOBAL;
+        return pte_flags(pte) & _PAGE_GLOBAL;
 }
 
 static inline int pte_exec(pte_t pte)
 {
-        return !(pte_val(pte) & _PAGE_NX);
+        return !(pte_flags(pte) & _PAGE_NX);
 }
 
 static inline int pte_special(pte_t pte)
 {
-        return 0;
+        return pte_val(pte) & _PAGE_SPECIAL;
+}
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+        return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
+#define pte_page(pte)   pfn_to_page(pte_pfn(pte))
+
 static inline int pmd_large(pmd_t pte)
 {
         return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
@@ -210,22 +214,22 @@ static inline int pmd_large(pmd_t pte)
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_DIRTY);
+        return __pte(pte_val(pte) & ~_PAGE_DIRTY);
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_ACCESSED);
+        return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
 }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_RW);
+        return __pte(pte_val(pte) & ~_PAGE_RW);
 }
 
 static inline pte_t pte_mkexec(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_NX);
+        return __pte(pte_val(pte) & ~_PAGE_NX);
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
@@ -250,7 +254,7 @@ static inline pte_t pte_mkhuge(pte_t pte)
 
 static inline pte_t pte_clrhuge(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_PSE);
+        return __pte(pte_val(pte) & ~_PAGE_PSE);
 }
 
 static inline pte_t pte_mkglobal(pte_t pte)
@@ -260,12 +264,12 @@ static inline pte_t pte_mkglobal(pte_t pte)
 
 static inline pte_t pte_clrglobal(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_GLOBAL);
+        return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
 {
-        return pte;
+        return __pte(pte_val(pte) | _PAGE_SPECIAL);
 }
 
 extern pteval_t __supported_pte_mask;
@@ -305,7 +309,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
         return __pgprot(preservebits | addbits);
 }
 
-#define pte_pgprot(x) __pgprot(pte_val(x) & ~PTE_MASK)
+#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
 
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 
@@ -318,6 +322,19 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
                               unsigned long size, pgprot_t *vma_prot);
 #endif
 
+/* Install a pte for a particular vaddr in kernel space. */
+void set_pte_vaddr(unsigned long vaddr, pte_t pte);
+
+#ifdef CONFIG_X86_32
+extern void native_pagetable_setup_start(pgd_t *base);
+extern void native_pagetable_setup_done(pgd_t *base);
+#else
+static inline void native_pagetable_setup_start(pgd_t *base) {}
+static inline void native_pagetable_setup_done(pgd_t *base) {}
+#endif
+
+extern int arch_report_meminfo(char *page);
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT */
@@ -349,6 +366,16 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 
 #define pte_update(mm, addr, ptep)              do { } while (0)
 #define pte_update_defer(mm, addr, ptep)        do { } while (0)
+
+static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
+{
+        native_pagetable_setup_start(base);
+}
+
+static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
+{
+        native_pagetable_setup_done(base);
+}
 #endif  /* CONFIG_PARAVIRT */
 
 #endif  /* __ASSEMBLY__ */
@@ -359,6 +386,26 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 # include "pgtable_64.h"
 #endif
 
+/*
+ * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
+ *
+ * this macro returns the index of the entry in the pgd page which would
+ * control the given virtual address
+ */
+#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
+
+/*
+ * pgd_offset() returns a (pgd_t *)
+ * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
+ */
+#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+/*
+ * a shortcut which implies the use of the kernel's pgd, instead
+ * of a process's
+ */
+#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
+
+
 #define KERNEL_PGD_BOUNDARY     pgd_index(PAGE_OFFSET)
 #define KERNEL_PGD_PTRS         (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
 
@@ -369,8 +416,15 @@ enum {
         PG_LEVEL_4K,
         PG_LEVEL_2M,
         PG_LEVEL_1G,
+        PG_LEVEL_NUM
 };
 
+#ifdef CONFIG_PROC_FS
+extern void update_page_count(int level, unsigned long pages);
+#else
+static inline void update_page_count(int level, unsigned long pages) { }
+#endif
+
 /*
  * Helper function that returns the kernel pagetable entry controlling
  * the virtual address 'address'. NULL means no pagetable entry present.
@@ -420,6 +474,8 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
  * race with other CPU's that might be updating the dirty
  * bit at the same time.
  */
+struct vm_area_struct;
+
 #define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
                                  unsigned long address, pte_t *ptep,
@@ -487,4 +543,4 @@ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 #include <asm-generic/pgtable.h>
 #endif  /* __ASSEMBLY__ */
 
-#endif  /* _ASM_X86_PGTABLE_H */
+#endif /* ASM_X86__PGTABLE_H */
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
index 32ca03109a4c..8de702dc7d62 100644
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -1,5 +1,5 @@
-#ifndef _I386_PGTABLE_H
-#define _I386_PGTABLE_H
+#ifndef ASM_X86__PGTABLE_32_H
+#define ASM_X86__PGTABLE_32_H
 
 
 /*
@@ -31,6 +31,7 @@ static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
 void paging_init(void);
 
+extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
 
 /*
  * The Linux x86 paging architecture is 'compile-time dual-mode', it
@@ -56,8 +57,7 @@ void paging_init(void);
  * area for the same reason. ;)
  */
 #define VMALLOC_OFFSET  (8 * 1024 * 1024)
-#define VMALLOC_START   (((unsigned long)high_memory + 2 * VMALLOC_OFFSET - 1) \
-                         & ~(VMALLOC_OFFSET - 1))
+#define VMALLOC_START   ((unsigned long)high_memory + VMALLOC_OFFSET)
 #ifdef CONFIG_X86_PAE
 #define LAST_PKMAP 512
 #else
@@ -73,6 +73,8 @@ void paging_init(void);
 # define VMALLOC_END    (FIXADDR_START - 2 * PAGE_SIZE)
 #endif
 
+#define MAXMEM  (VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
+
 /*
  * Define this if things work differently on an i386 and an i486:
  * it will (on an i486) warn about kernel memory accesses that are
@@ -88,7 +90,7 @@ extern unsigned long pg0[];
 /* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
 #define pmd_none(x)     (!(unsigned long)pmd_val((x)))
 #define pmd_present(x)  (pmd_val((x)) & _PAGE_PRESENT)
-#define pmd_bad(x) ((pmd_val(x) & (~PTE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+#define pmd_bad(x) ((pmd_val(x) & (PTE_FLAGS_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
 
 #define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
 
@@ -113,26 +115,6 @@ extern unsigned long pg0[];
  */
 #define mk_pte(page, pgprot)    pfn_pte(page_to_pfn(page), (pgprot))
 
-/*
- * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
- *
- * this macro returns the index of the entry in the pgd page which would
- * control the given virtual address
- */
-#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
-#define pgd_index_k(addr) pgd_index((addr))
-
-/*
- * pgd_offset() returns a (pgd_t *)
- * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
- */
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
-
-/*
- * a shortcut which implies the use of the kernel's pgd, instead
- * of a process's
- */
-#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
 
 static inline int pud_large(pud_t pud) { return 0; }
 
@@ -159,7 +141,7 @@ static inline int pud_large(pud_t pud) { return 0; }
 #define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
 
 #define pmd_page_vaddr(pmd)                                     \
-        ((unsigned long)__va(pmd_val((pmd)) & PTE_MASK))
+        ((unsigned long)__va(pmd_val((pmd)) & PTE_PFN_MASK))
 
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address)                                    \
@@ -191,21 +173,6 @@ do {						\
  */
 #define update_mmu_cache(vma, address, pte) do { } while (0)
 
-extern void native_pagetable_setup_start(pgd_t *base);
-extern void native_pagetable_setup_done(pgd_t *base);
-
-#ifndef CONFIG_PARAVIRT
-static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
-{
-        native_pagetable_setup_start(base);
-}
-
-static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
-{
-        native_pagetable_setup_done(base);
-}
-#endif  /* !CONFIG_PARAVIRT */
-
 #endif /* !__ASSEMBLY__ */
 
 /*
@@ -221,4 +188,4 @@ static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
 #define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
         remap_pfn_range(vma, vaddr, pfn, size, prot)
 
-#endif /* _I386_PGTABLE_H */
+#endif /* ASM_X86__PGTABLE_32_H */
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index 1cc50d22d735..fde9770e53d1 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_PGTABLE_H
-#define _X86_64_PGTABLE_H
+#ifndef ASM_X86__PGTABLE_64_H
+#define ASM_X86__PGTABLE_64_H
 
 #include <linux/const.h>
 #ifndef __ASSEMBLY__
@@ -16,6 +16,8 @@
 extern pud_t level3_kernel_pgt[512];
 extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
+extern pmd_t level2_fixmap_pgt[512];
+extern pmd_t level2_ident_pgt[512];
 extern pgd_t init_level4_pgt[];
 
 #define swapper_pg_dir init_level4_pgt
@@ -70,6 +72,9 @@ extern void paging_init(void);
 
 struct mm_struct;
 
+void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
+
+
 static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
                                     pte_t *ptep)
 {
@@ -146,32 +151,30 @@ static inline void native_pgd_clear(pgd_t *pgd)
 #define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
 #define VMEMMAP_START    _AC(0xffffe20000000000, UL)
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
-#define MODULES_END      _AC(0xfffffffffff00000, UL)
+#define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 
 #ifndef __ASSEMBLY__
 
 static inline int pgd_bad(pgd_t pgd)
 {
-        return (pgd_val(pgd) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE;
+        return (pgd_val(pgd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
 }
 
 static inline int pud_bad(pud_t pud)
 {
-        return (pud_val(pud) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE;
+        return (pud_val(pud) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
 }
 
 static inline int pmd_bad(pmd_t pmd)
 {
-        return (pmd_val(pmd) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE;
+        return (pmd_val(pmd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
 }
 
 #define pte_none(x)     (!pte_val((x)))
 #define pte_present(x)  (pte_val((x)) & (_PAGE_PRESENT | _PAGE_PROTNONE))
 
 #define pages_to_mb(x)  ((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
-#define pte_page(x)     pfn_to_page(pte_pfn((x)))
-#define pte_pfn(x)      ((pte_val((x)) & __PHYSICAL_MASK) >> PAGE_SHIFT)
 
 /*
  * Macro to mark a page protection value as "uncacheable".
@@ -188,14 +191,11 @@ static inline int pmd_bad(pmd_t pmd)
  * Level 4 access.
  */
 #define pgd_page_vaddr(pgd)                                             \
-        ((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_MASK))
+        ((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_PFN_MASK))
 #define pgd_page(pgd)           (pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT))
-#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
-#define pgd_offset_k(address) (init_level4_pgt + pgd_index((address)))
 #define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
 static inline int pgd_large(pgd_t pgd) { return 0; }
-#define mk_kernel_pgd(address) ((pgd_t){ (address) | _KERNPG_TABLE })
+#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
 
 /* PUD - Level3 access */
 /* to find an entry in a page-table-directory. */
@@ -214,7 +214,7 @@ static inline int pud_large(pud_t pte)
 }
 
 /* PMD  - Level 2 access */
-#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_MASK))
+#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_PFN_MASK))
 #define pmd_page(pmd)           (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
 
 #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
@@ -282,4 +282,4 @@ extern void cleanup_highmap(void);
 #define __HAVE_ARCH_PTE_SAME
 #endif /* !__ASSEMBLY__ */
 
-#endif /* _X86_64_PGTABLE_H */
+#endif /* ASM_X86__PGTABLE_64_H */
diff --git a/include/asm-x86/posix_types_32.h b/include/asm-x86/posix_types_32.h
index b031efda37ec..70cf2bb05939 100644
--- a/include/asm-x86/posix_types_32.h
+++ b/include/asm-x86/posix_types_32.h
@@ -1,5 +1,5 @@
-#ifndef __ARCH_I386_POSIX_TYPES_H
-#define __ARCH_I386_POSIX_TYPES_H
+#ifndef ASM_X86__POSIX_TYPES_32_H
+#define ASM_X86__POSIX_TYPES_32_H
 
 /*
  * This file is generally used by user-level software, so you need to
@@ -82,4 +82,4 @@ do {								\
 
 #endif /* defined(__KERNEL__) */
 
-#endif
+#endif /* ASM_X86__POSIX_TYPES_32_H */
diff --git a/include/asm-x86/posix_types_64.h b/include/asm-x86/posix_types_64.h
index d6624c95854a..388b4e7f4a44 100644
--- a/include/asm-x86/posix_types_64.h
+++ b/include/asm-x86/posix_types_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_POSIX_TYPES_H
-#define _ASM_X86_64_POSIX_TYPES_H
+#ifndef ASM_X86__POSIX_TYPES_64_H
+#define ASM_X86__POSIX_TYPES_64_H
 
 /*
  * This file is generally used by user-level software, so you need to
@@ -116,4 +116,4 @@ static inline void __FD_ZERO(__kernel_fd_set *p)
 
 #endif /* defined(__KERNEL__) */
 
-#endif
+#endif /* ASM_X86__POSIX_TYPES_64_H */
diff --git a/include/asm-x86/prctl.h b/include/asm-x86/prctl.h
index 52952adef1ca..e7ae34eb4103 100644
--- a/include/asm-x86/prctl.h
+++ b/include/asm-x86/prctl.h
@@ -1,5 +1,5 @@
-#ifndef X86_64_PRCTL_H
-#define X86_64_PRCTL_H 1
+#ifndef ASM_X86__PRCTL_H
+#define ASM_X86__PRCTL_H
 
 #define ARCH_SET_GS 0x1001
 #define ARCH_SET_FS 0x1002
@@ -7,4 +7,4 @@
 #define ARCH_GET_GS 0x1004
 
 
-#endif
+#endif /* ASM_X86__PRCTL_H */
diff --git a/include/asm-x86/processor-cyrix.h b/include/asm-x86/processor-cyrix.h
index 97568ada1f97..1198f2a0e42c 100644
--- a/include/asm-x86/processor-cyrix.h
+++ b/include/asm-x86/processor-cyrix.h
@@ -28,3 +28,11 @@ static inline void setCx86(u8 reg, u8 data)
         outb(reg, 0x22);
         outb(data, 0x23);
 }
+
+#define getCx86_old(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86_old(reg, data) do { \
+        outb((reg), 0x22); \
+        outb((data), 0x23); \
+} while (0)
+
diff --git a/include/asm-x86/processor-flags.h b/include/asm-x86/processor-flags.h
index 199cab107d85..dc5f0712f9fa 100644
--- a/include/asm-x86/processor-flags.h
+++ b/include/asm-x86/processor-flags.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_I386_PROCESSOR_FLAGS_H
-#define __ASM_I386_PROCESSOR_FLAGS_H
+#ifndef ASM_X86__PROCESSOR_FLAGS_H
+#define ASM_X86__PROCESSOR_FLAGS_H
 /* Various flags defined: can be included from assembler. */
 
 /*
@@ -59,6 +59,7 @@
 #define X86_CR4_OSFXSR  0x00000200 /* enable fast FPU save and restore */
 #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
 #define X86_CR4_VMXE    0x00002000 /* enable VMX virtualization */
+#define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
 
 /*
  * x86-64 Task Priority Register, CR8
@@ -88,4 +89,12 @@
 #define CX86_ARR_BASE   0xc4
 #define CX86_RCR_BASE   0xdc
 
-#endif  /* __ASM_I386_PROCESSOR_FLAGS_H */
+#ifdef __KERNEL__
+#ifdef CONFIG_VM86
+#define X86_VM_MASK     X86_EFLAGS_VM
+#else
+#define X86_VM_MASK     0 /* No VM86 support */
+#endif
+#endif
+
+#endif /* ASM_X86__PROCESSOR_FLAGS_H */
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 559105220a47..ee7cbb30773a 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_X86_PROCESSOR_H
-#define __ASM_X86_PROCESSOR_H
+#ifndef ASM_X86__PROCESSOR_H
+#define ASM_X86__PROCESSOR_H
 
 #include <asm/processor-flags.h>
 
@@ -20,6 +20,7 @@ struct mm_struct;
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
+#include <asm/ds.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -75,11 +76,11 @@ struct cpuinfo_x86 {
         int                      x86_tlbsize;
         __u8                    x86_virt_bits;
         __u8                    x86_phys_bits;
+#endif
         /* CPUID returned core id bits: */
         __u8                    x86_coreid_bits;
         /* Max extended CPUID function supported: */
         __u32                   extended_cpuid_level;
-#endif
         /* Maximum supported CPUID level, -1=no CPUID: */
         int                     cpuid_level;
         __u32                   x86_capability[NCAPINTS];
@@ -134,12 +135,14 @@ extern __u32			cleared_cpu_caps[NCAPINTS];
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info);
 #define cpu_data(cpu)           per_cpu(cpu_info, cpu)
-#define current_cpu_data        cpu_data(smp_processor_id())
+#define current_cpu_data        __get_cpu_var(cpu_info)
 #else
 #define cpu_data(cpu)           boot_cpu_data
 #define current_cpu_data        boot_cpu_data
 #endif
 
+extern const struct seq_operations cpuinfo_op;
+
 static inline int hlt_works(int cpu)
 {
 #ifdef CONFIG_X86_32
@@ -153,7 +156,9 @@ static inline int hlt_works(int cpu)
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
 
-extern void identify_cpu(struct cpuinfo_x86 *);
+extern struct pt_regs *idle_regs(struct pt_regs *);
+
+extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
@@ -161,11 +166,8 @@ extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern unsigned short num_cache_leaves;
 
-#if defined(CONFIG_X86_HT) || defined(CONFIG_X86_64)
+extern void detect_extended_topology(struct cpuinfo_x86 *c);
 extern void detect_ht(struct cpuinfo_x86 *c);
-#else
-static inline void detect_ht(struct cpuinfo_x86 *c) {}
-#endif
 
 static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
                                 unsigned int *ecx, unsigned int *edx)
@@ -263,15 +265,11 @@ struct tss_struct {
         struct thread_struct    *io_bitmap_owner;
 
         /*
-         * Pad the TSS to be cacheline-aligned (size is 0x100):
-         */
-        unsigned long           __cacheline_filler[35];
-        /*
          * .. and then another 0x100 bytes for the emergency kernel stack:
          */
         unsigned long           stack[64];
 
-} __attribute__((packed));
+} ____cacheline_aligned;
 
 DECLARE_PER_CPU(struct tss_struct, init_tss);
 
@@ -326,7 +324,12 @@ struct i387_fxsave_struct {
         /* 16*16 bytes for each XMM-reg = 256 bytes:                    */
         u32                     xmm_space[64];
 
-        u32                     padding[24];
+        u32                     padding[12];
+
+        union {
+                u32             padding1[12];
+                u32             sw_reserved[12];
+        };
 
 } __attribute__((aligned(16)));
 
@@ -350,10 +353,23 @@ struct i387_soft_struct {
         u32                     entry_eip;
 };
 
+struct xsave_hdr_struct {
+        u64 xstate_bv;
+        u64 reserved1[2];
+        u64 reserved2[5];
+} __attribute__((packed));
+
+struct xsave_struct {
+        struct i387_fxsave_struct i387;
+        struct xsave_hdr_struct xsave_hdr;
+        /* new processor state extensions will go here */
+} __attribute__ ((packed, aligned (64)));
+
 union thread_xstate {
         struct i387_fsave_struct        fsave;
         struct i387_fxsave_struct       fxsave;
         struct i387_soft_struct         soft;
+        struct xsave_struct             xsave;
 };
 
 #ifdef CONFIG_X86_64
@@ -415,9 +431,14 @@ struct thread_struct {
         unsigned                io_bitmap_max;
 /* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
         unsigned long   debugctlmsr;
-/* Debug Store - if not 0 points to a DS Save Area configuration;
- *               goes into MSR_IA32_DS_AREA */
-        unsigned long   ds_area_msr;
+#ifdef CONFIG_X86_DS
+/* Debug Store context; see include/asm-x86/ds.h; goes into MSR_IA32_DS_AREA */
+        struct ds_context       *ds_ctx;
+#endif /* CONFIG_X86_DS */
+#ifdef CONFIG_X86_PTRACE_BTS
+/* the signal to send on a bts buffer overflow */
+        unsigned int    bts_ovfl_signal;
+#endif /* CONFIG_X86_PTRACE_BTS */
 };
 
 static inline unsigned long native_get_debugreg(int regno)
@@ -535,7 +556,6 @@ static inline void load_sp0(struct tss_struct *tss,
 }
 
 #define set_iopl_mask native_set_iopl_mask
-#define SWAPGS  swapgs
 #endif /* CONFIG_PARAVIRT */
 
 /*
@@ -566,41 +586,6 @@ static inline void clear_in_cr4(unsigned long mask)
         write_cr4(cr4);
 }
 
-struct microcode_header {
-        unsigned int            hdrver;
-        unsigned int            rev;
-        unsigned int            date;
-        unsigned int            sig;
-        unsigned int            cksum;
-        unsigned int            ldrver;
-        unsigned int            pf;
-        unsigned int            datasize;
-        unsigned int            totalsize;
-        unsigned int            reserved[3];
-};
-
-struct microcode {
-        struct microcode_header hdr;
-        unsigned int            bits[0];
-};
-
-typedef struct microcode        microcode_t;
-typedef struct microcode_header microcode_header_t;
-
-/* microcode format is extended from prescott processors */
-struct extended_signature {
-        unsigned int            sig;
-        unsigned int            pf;
-        unsigned int            cksum;
-};
-
-struct extended_sigtable {
-        unsigned int            count;
-        unsigned int            cksum;
-        unsigned int            reserved[3];
-        struct extended_signature sigs[0];
-};
-
 typedef struct {
         unsigned long           seg;
 } mm_segment_t;
@@ -727,11 +712,34 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
-extern int                      force_mwait;
-
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
 
 extern unsigned long            boot_option_idle_override;
+extern unsigned long            idle_halt;
+extern unsigned long            idle_nomwait;
+
+/*
+ * on systems with caches, caches must be flashed as the absolute
+ * last instruction before going into a suspended halt.  Otherwise,
+ * dirty data can linger in the cache and become stale on resume,
+ * leading to strange errors.
+ *
+ * perform a variety of operations to guarantee that the compiler
+ * will not reorder instructions.  wbinvd itself is serializing
+ * so the processor will not reorder.
+ *
+ * Systems without cache can just go into halt.
+ */
+static inline void wbinvd_halt(void)
+{
+        mb();
+        /* check for clflush to determine if wbinvd is legal */
+        if (cpu_has_clflush)
+                asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
+        else
+                while (1)
+                        halt();
+}
 
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
@@ -925,4 +933,4 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
-#endif
+#endif /* ASM_X86__PROCESSOR_H */
diff --git a/include/asm-x86/proto.h b/include/asm-x86/proto.h
index 6c8b41b03f6d..6e89e8b4de0e 100644
--- a/include/asm-x86/proto.h
+++ b/include/asm-x86/proto.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X8664_PROTO_H
-#define _ASM_X8664_PROTO_H 1
+#ifndef ASM_X86__PROTO_H
+#define ASM_X86__PROTO_H
 
 #include <asm/ldt.h>
 
@@ -14,8 +14,6 @@ extern void ia32_syscall(void);
 extern void ia32_cstar_target(void);
 extern void ia32_sysenter_target(void);
 
-extern void reserve_bootmem_generic(unsigned long phys, unsigned len);
-
 extern void syscall32_cpu_init(void);
 
 extern void check_efer(void);
@@ -31,4 +29,4 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 #define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
 #define round_down(x, y) ((x) & ~((y) - 1))
 
-#endif
+#endif /* ASM_X86__PROTO_H */
diff --git a/include/asm-x86/ptrace-abi.h b/include/asm-x86/ptrace-abi.h
index f224eb3c3157..4298b8882a78 100644
--- a/include/asm-x86/ptrace-abi.h
+++ b/include/asm-x86/ptrace-abi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PTRACE_ABI_H
-#define _ASM_X86_PTRACE_ABI_H
+#ifndef ASM_X86__PTRACE_ABI_H
+#define ASM_X86__PTRACE_ABI_H
 
 #ifdef __i386__
 
@@ -73,15 +73,16 @@
 
 #ifdef __x86_64__
 # define PTRACE_ARCH_PRCTL        30
-#else
-# define PTRACE_SYSEMU            31
-# define PTRACE_SYSEMU_SINGLESTEP 32
 #endif
 
+#define PTRACE_SYSEMU             31
+#define PTRACE_SYSEMU_SINGLESTEP  32
+
 #define PTRACE_SINGLEBLOCK      33      /* resume execution until next branch */
 
-#ifndef __ASSEMBLY__
+#ifdef CONFIG_X86_PTRACE_BTS
 
+#ifndef __ASSEMBLY__
 #include <asm/types.h>
 
 /* configuration/status structure used in PTRACE_BTS_CONFIG and
@@ -97,20 +98,20 @@ struct ptrace_bts_config {
         /* actual size of bts_struct in bytes */
         __u32 bts_size;
 };
-#endif
+#endif /* __ASSEMBLY__ */
 
 #define PTRACE_BTS_O_TRACE      0x1 /* branch trace */
 #define PTRACE_BTS_O_SCHED      0x2 /* scheduling events w/ jiffies */
 #define PTRACE_BTS_O_SIGNAL     0x4 /* send SIG<signal> on buffer overflow
                                        instead of wrapping around */
-#define PTRACE_BTS_O_CUT_SIZE   0x8 /* cut requested size to max available
-                                       instead of failing */
+#define PTRACE_BTS_O_ALLOC      0x8 /* (re)allocate buffer */
 
 #define PTRACE_BTS_CONFIG       40
 /* Configure branch trace recording.
    ADDR points to a struct ptrace_bts_config.
    DATA gives the size of that buffer.
-   A new buffer is allocated, iff the size changes.
+   A new buffer is allocated, if requested in the flags.
+   An overflow signal may only be requested for new buffers.
    Returns the number of bytes read.
 */
 #define PTRACE_BTS_STATUS       41
@@ -119,7 +120,7 @@ struct ptrace_bts_config {
    Returns the number of bytes written.
 */
 #define PTRACE_BTS_SIZE         42
-/* Return the number of available BTS records.
+/* Return the number of available BTS records for draining.
    DATA and ADDR are ignored.
 */
 #define PTRACE_BTS_GET          43
@@ -139,5 +140,6 @@ struct ptrace_bts_config {
    BTS records are read from oldest to newest.
    Returns number of BTS records drained.
 */
+#endif /* CONFIG_X86_PTRACE_BTS */
 
-#endif
+#endif /* ASM_X86__PTRACE_ABI_H */
diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h
index 9f922b0b95d6..ac578f11c1c5 100644
--- a/include/asm-x86/ptrace.h
+++ b/include/asm-x86/ptrace.h
@@ -1,9 +1,14 @@
-#ifndef _ASM_X86_PTRACE_H
-#define _ASM_X86_PTRACE_H
+#ifndef ASM_X86__PTRACE_H
+#define ASM_X86__PTRACE_H
 
 #include <linux/compiler.h>     /* For __user */
 #include <asm/ptrace-abi.h>
+#include <asm/processor-flags.h>
 
+#ifdef __KERNEL__
+#include <asm/ds.h>             /* the DS BTS struct is used for ptrace too */
+#include <asm/segment.h>
+#endif
 
 #ifndef __ASSEMBLY__
 
@@ -55,9 +60,6 @@ struct pt_regs {
         unsigned long ss;
 };
 
-#include <asm/vm86.h>
-#include <asm/segment.h>
-
 #endif /* __KERNEL__ */
 
 #else /* __i386__ */
@@ -125,14 +127,48 @@ struct pt_regs {
 #endif /* __KERNEL__ */
 #endif /* !__i386__ */
 
+
+#ifdef CONFIG_X86_PTRACE_BTS
+/* a branch trace record entry
+ *
+ * In order to unify the interface between various processor versions,
+ * we use the below data structure for all processors.
+ */
+enum bts_qualifier {
+        BTS_INVALID = 0,
+        BTS_BRANCH,
+        BTS_TASK_ARRIVES,
+        BTS_TASK_DEPARTS
+};
+
+struct bts_struct {
+        __u64 qualifier;
+        union {
+                /* BTS_BRANCH */
+                struct {
+                        __u64 from_ip;
+                        __u64 to_ip;
+                } lbr;
+                /* BTS_TASK_ARRIVES or
+                   BTS_TASK_DEPARTS */
+                __u64 jiffies;
+        } variant;
+};
+#endif /* CONFIG_X86_PTRACE_BTS */
+
 #ifdef __KERNEL__
 
-/* the DS BTS struct is used for ptrace as well */
-#include <asm/ds.h>
+#include <linux/init.h>
 
+struct cpuinfo_x86;
 struct task_struct;
 
+#ifdef CONFIG_X86_PTRACE_BTS
+extern void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *);
 extern void ptrace_bts_take_timestamp(struct task_struct *, enum bts_qualifier);
+#else
+#define ptrace_bts_init_intel(config) do {} while (0)
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 extern unsigned long profile_pc(struct pt_regs *regs);
 
@@ -141,11 +177,14 @@ convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
 
 #ifdef CONFIG_X86_32
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
-                         int error_code);
-#else
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+                         int error_code, int si_code);
 #endif
 
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+extern long syscall_trace_enter(struct pt_regs *);
+extern void syscall_trace_leave(struct pt_regs *);
+
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
         return regs->ax;
@@ -211,6 +250,11 @@ static inline unsigned long frame_pointer(struct pt_regs *regs)
         return regs->bp;
 }
 
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+        return regs->sp;
+}
+
 /*
  * These are defined as per linux/ptrace.h, which see.
  */
@@ -237,4 +281,4 @@ extern int do_set_thread_area(struct task_struct *p, int idx,
 
 #endif /* !__ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__PTRACE_H */
diff --git a/include/asm-x86/pvclock-abi.h b/include/asm-x86/pvclock-abi.h
new file mode 100644
index 000000000000..edb3b4ecfc81
--- /dev/null
+++ b/include/asm-x86/pvclock-abi.h
@@ -0,0 +1,42 @@
+#ifndef ASM_X86__PVCLOCK_ABI_H
+#define ASM_X86__PVCLOCK_ABI_H
+#ifndef __ASSEMBLY__
+
+/*
+ * These structs MUST NOT be changed.
+ * They are the ABI between hypervisor and guest OS.
+ * Both Xen and KVM are using this.
+ *
+ * pvclock_vcpu_time_info holds the system time and the tsc timestamp
+ * of the last update. So the guest can use the tsc delta to get a
+ * more precise system time.  There is one per virtual cpu.
+ *
+ * pvclock_wall_clock references the point in time when the system
+ * time was zero (usually boot time), thus the guest calculates the
+ * current wall clock by adding the system time.
+ *
+ * Protocol for the "version" fields is: hypervisor raises it (making
+ * it uneven) before it starts updating the fields and raises it again
+ * (making it even) when it is done.  Thus the guest can make sure the
+ * time values it got are consistent by checking the version before
+ * and after reading them.
+ */
+
+struct pvclock_vcpu_time_info {
+        u32   version;
+        u32   pad0;
+        u64   tsc_timestamp;
+        u64   system_time;
+        u32   tsc_to_system_mul;
+        s8    tsc_shift;
+        u8    pad[3];
+} __attribute__((__packed__)); /* 32 bytes */
+
+struct pvclock_wall_clock {
+        u32   version;
+        u32   sec;
+        u32   nsec;
+} __attribute__((__packed__));
+
+#endif /* __ASSEMBLY__ */
+#endif /* ASM_X86__PVCLOCK_ABI_H */
diff --git a/include/asm-x86/pvclock.h b/include/asm-x86/pvclock.h
new file mode 100644
index 000000000000..1a38f6834800
--- /dev/null
+++ b/include/asm-x86/pvclock.h
@@ -0,0 +1,13 @@
+#ifndef ASM_X86__PVCLOCK_H
+#define ASM_X86__PVCLOCK_H
+
+#include <linux/clocksource.h>
+#include <asm/pvclock-abi.h>
+
+/* some helper functions for xen and kvm pv clock sources */
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
+                            struct pvclock_vcpu_time_info *vcpu,
+                            struct timespec *ts);
+
+#endif /* ASM_X86__PVCLOCK_H */
diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h
index e63741f19392..1c2f0ce9e31e 100644
--- a/include/asm-x86/reboot.h
+++ b/include/asm-x86/reboot.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_REBOOT_H
-#define _ASM_REBOOT_H
+#ifndef ASM_X86__REBOOT_H
+#define ASM_X86__REBOOT_H
 
 struct pt_regs;
 
@@ -14,8 +14,8 @@ struct machine_ops {
 
 extern struct machine_ops machine_ops;
 
-void machine_real_restart(unsigned char *code, int length);
 void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
+void machine_real_restart(const unsigned char *code, int length);
 
-#endif  /* _ASM_REBOOT_H */
+#endif /* ASM_X86__REBOOT_H */
diff --git a/include/asm-x86/reboot_fixups.h b/include/asm-x86/reboot_fixups.h
index 0cb7d87c2b68..2c2987d97570 100644
--- a/include/asm-x86/reboot_fixups.h
+++ b/include/asm-x86/reboot_fixups.h
@@ -1,6 +1,6 @@
-#ifndef _LINUX_REBOOT_FIXUPS_H
-#define _LINUX_REBOOT_FIXUPS_H
+#ifndef ASM_X86__REBOOT_FIXUPS_H
+#define ASM_X86__REBOOT_FIXUPS_H
 
 extern void mach_reboot_fixups(void);
 
-#endif /* _LINUX_REBOOT_FIXUPS_H */
+#endif /* ASM_X86__REBOOT_FIXUPS_H */
diff --git a/include/asm-x86/required-features.h b/include/asm-x86/required-features.h
index 7400d3ad75c6..a01c4e376331 100644
--- a/include/asm-x86/required-features.h
+++ b/include/asm-x86/required-features.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_REQUIRED_FEATURES_H
-#define _ASM_REQUIRED_FEATURES_H 1
+#ifndef ASM_X86__REQUIRED_FEATURES_H
+#define ASM_X86__REQUIRED_FEATURES_H
 
 /* Define minimum CPUID feature set for kernel These bits are checked
    really early to actually display a visible error message before the
@@ -19,9 +19,13 @@
 
 #if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
 # define NEED_PAE       (1<<(X86_FEATURE_PAE & 31))
-# define NEED_CX8       (1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_PAE       0
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+# define NEED_CX8       (1<<(X86_FEATURE_CX8 & 31))
+#else
 # define NEED_CX8       0
 #endif
 
@@ -37,8 +41,14 @@
 # define NEED_3DNOW     0
 #endif
 
+#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
+# define NEED_NOPL      (1<<(X86_FEATURE_NOPL & 31))
+#else
+# define NEED_NOPL      0
+#endif
+
 #ifdef CONFIG_X86_64
-#define NEED_PSE        (1<<(X86_FEATURE_PSE & 31))
+#define NEED_PSE        0
 #define NEED_MSR        (1<<(X86_FEATURE_MSR & 31))
 #define NEED_PGE        (1<<(X86_FEATURE_PGE & 31))
 #define NEED_FXSR       (1<<(X86_FEATURE_FXSR & 31))
@@ -63,10 +73,10 @@
 #define REQUIRED_MASK1  (NEED_LM|NEED_3DNOW)
 
 #define REQUIRED_MASK2  0
-#define REQUIRED_MASK3  0
+#define REQUIRED_MASK3  (NEED_NOPL)
 #define REQUIRED_MASK4  0
 #define REQUIRED_MASK5  0
 #define REQUIRED_MASK6  0
 #define REQUIRED_MASK7  0
 
-#endif
+#endif /* ASM_X86__REQUIRED_FEATURES_H */
diff --git a/include/asm-x86/resume-trace.h b/include/asm-x86/resume-trace.h
index 2557514d7ef6..e39376d7de50 100644
--- a/include/asm-x86/resume-trace.h
+++ b/include/asm-x86/resume-trace.h
@@ -1,13 +1,13 @@
-#ifndef _ASM_X86_RESUME_TRACE_H
-#define _ASM_X86_RESUME_TRACE_H
+#ifndef ASM_X86__RESUME_TRACE_H
+#define ASM_X86__RESUME_TRACE_H
 
 #include <asm/asm.h>
 
 #define TRACE_RESUME(user)                                      \
 do {                                                            \
         if (pm_trace_enabled) {                                 \
-                void *tracedata;                                \
-                asm volatile(_ASM_MOV_UL " $1f,%0\n"            \
+                const void *tracedata;                          \
+                asm volatile(_ASM_MOV " $1f,%0\n"               \
                              ".section .tracedata,\"a\"\n"      \
                              "1:\t.word %c1\n\t"                \
                              _ASM_PTR " %c2\n"                  \
@@ -18,4 +18,4 @@ do {								\
         }                                                       \
 } while (0)
 
-#endif
+#endif /* ASM_X86__RESUME_TRACE_H */
diff --git a/include/asm-x86/rio.h b/include/asm-x86/rio.h
index c9448bd8968f..5e1256bdee83 100644
--- a/include/asm-x86/rio.h
+++ b/include/asm-x86/rio.h
@@ -5,8 +5,8 @@
  * Author: Laurent Vivier <Laurent.Vivier@bull.net>
  */
 
-#ifndef __ASM_RIO_H
-#define __ASM_RIO_H
+#ifndef ASM_X86__RIO_H
+#define ASM_X86__RIO_H
 
 #define RIO_TABLE_VERSION       3
 
@@ -60,4 +60,4 @@ enum {
         ALT_CALGARY     = 5,    /* Second Planar Calgary      */
 };
 
-#endif /* __ASM_RIO_H */
+#endif /* ASM_X86__RIO_H */
diff --git a/include/asm-x86/rwlock.h b/include/asm-x86/rwlock.h
index 6a8c0d645108..48a3109e1a7d 100644
--- a/include/asm-x86/rwlock.h
+++ b/include/asm-x86/rwlock.h
@@ -1,8 +1,8 @@
-#ifndef _ASM_X86_RWLOCK_H
-#define _ASM_X86_RWLOCK_H
+#ifndef ASM_X86__RWLOCK_H
+#define ASM_X86__RWLOCK_H
 
 #define RW_LOCK_BIAS             0x01000000
 
 /* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */
 
-#endif /* _ASM_X86_RWLOCK_H */
+#endif /* ASM_X86__RWLOCK_H */
diff --git a/include/asm-x86/rwsem.h b/include/asm-x86/rwsem.h
index 750f2a3542b3..3ff3015b71a8 100644
--- a/include/asm-x86/rwsem.h
+++ b/include/asm-x86/rwsem.h
@@ -29,8 +29,8 @@
  * front, then they'll all be woken up, but no other readers will be.
  */
 
-#ifndef _I386_RWSEM_H
-#define _I386_RWSEM_H
+#ifndef ASM_X86__RWSEM_H
+#define ASM_X86__RWSEM_H
 
 #ifndef _LINUX_RWSEM_H
 #error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
@@ -262,4 +262,4 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 }
 
 #endif /* __KERNEL__ */
-#endif /* _I386_RWSEM_H */
+#endif /* ASM_X86__RWSEM_H */
diff --git a/include/asm-x86/scatterlist.h b/include/asm-x86/scatterlist.h
index c0432061f81a..ee48f880005d 100644
--- a/include/asm-x86/scatterlist.h
+++ b/include/asm-x86/scatterlist.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SCATTERLIST_H
-#define _ASM_X86_SCATTERLIST_H
+#ifndef ASM_X86__SCATTERLIST_H
+#define ASM_X86__SCATTERLIST_H
 
 #include <asm/types.h>
 
@@ -30,4 +30,4 @@ struct scatterlist {
 # define sg_dma_len(sg)         ((sg)->dma_length)
 #endif
 
-#endif
+#endif /* ASM_X86__SCATTERLIST_H */
diff --git a/include/asm-x86/seccomp_32.h b/include/asm-x86/seccomp_32.h
index 18da19e89bff..cf9ab2dbcef1 100644
--- a/include/asm-x86/seccomp_32.h
+++ b/include/asm-x86/seccomp_32.h
@@ -1,4 +1,5 @@
-#ifndef _ASM_SECCOMP_H
+#ifndef ASM_X86__SECCOMP_32_H
+#define ASM_X86__SECCOMP_32_H
 
 #include <linux/thread_info.h>
 
@@ -13,4 +14,4 @@
 #define __NR_seccomp_exit __NR_exit
 #define __NR_seccomp_sigreturn __NR_sigreturn
 
-#endif /* _ASM_SECCOMP_H */
+#endif /* ASM_X86__SECCOMP_32_H */
diff --git a/include/asm-x86/seccomp_64.h b/include/asm-x86/seccomp_64.h
index 553af65a2287..03274cea751f 100644
--- a/include/asm-x86/seccomp_64.h
+++ b/include/asm-x86/seccomp_64.h
@@ -1,4 +1,5 @@
-#ifndef _ASM_SECCOMP_H
+#ifndef ASM_X86__SECCOMP_64_H
+#define ASM_X86__SECCOMP_64_H
 
 #include <linux/thread_info.h>
 
@@ -21,4 +22,4 @@
 #define __NR_seccomp_exit_32 __NR_ia32_exit
 #define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn
 
-#endif /* _ASM_SECCOMP_H */
+#endif /* ASM_X86__SECCOMP_64_H */
diff --git a/include/asm-x86/segment.h b/include/asm-x86/segment.h
index ed5131dd7d92..ea5f0a8686f7 100644
--- a/include/asm-x86/segment.h
+++ b/include/asm-x86/segment.h
@@ -1,5 +1,14 @@
-#ifndef _ASM_X86_SEGMENT_H_
-#define _ASM_X86_SEGMENT_H_
+#ifndef ASM_X86__SEGMENT_H
+#define ASM_X86__SEGMENT_H
+
+/* Constructor for a conventional segment GDT (or LDT) entry */
+/* This is a macro so it can be used in initializers */
+#define GDT_ENTRY(flags, base, limit)                   \
+        ((((base)  & 0xff000000ULL) << (56-24)) |       \
+         (((flags) & 0x0000f0ffULL) << 40) |            \
+         (((limit) & 0x000f0000ULL) << (48-16)) |       \
+         (((base)  & 0x00ffffffULL) << 16) |            \
+         (((limit) & 0x0000ffffULL)))
 
 /* Simple and small GDT entries for booting only */
 
@@ -61,18 +70,14 @@
 #define GDT_ENTRY_TLS_MAX       (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)
 
 #define GDT_ENTRY_DEFAULT_USER_CS       14
-#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS * 8 + 3)
 
 #define GDT_ENTRY_DEFAULT_USER_DS       15
-#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS * 8 + 3)
 
 #define GDT_ENTRY_KERNEL_BASE   12
 
 #define GDT_ENTRY_KERNEL_CS             (GDT_ENTRY_KERNEL_BASE + 0)
-#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS * 8)
 
 #define GDT_ENTRY_KERNEL_DS             (GDT_ENTRY_KERNEL_BASE + 1)
-#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS * 8)
 
 #define GDT_ENTRY_TSS                   (GDT_ENTRY_KERNEL_BASE + 4)
 #define GDT_ENTRY_LDT                   (GDT_ENTRY_KERNEL_BASE + 5)
@@ -139,10 +144,11 @@
 #else
 #include <asm/cache.h>
 
-#define __KERNEL_CS     0x10
-#define __KERNEL_DS     0x18
+#define GDT_ENTRY_KERNEL32_CS 1
+#define GDT_ENTRY_KERNEL_CS 2
+#define GDT_ENTRY_KERNEL_DS 3
 
-#define __KERNEL32_CS   0x08
+#define __KERNEL32_CS   (GDT_ENTRY_KERNEL32_CS * 8)
 
 /*
  * we cannot use the same code segment descriptor for user and kernel
@@ -150,10 +156,10 @@
  * The segment offset needs to contain a RPL. Grr. -AK
  * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets)
  */
-
-#define __USER32_CS   0x23   /* 4*8+3 */
-#define __USER_DS     0x2b   /* 5*8+3 */
-#define __USER_CS     0x33   /* 6*8+3 */
+#define GDT_ENTRY_DEFAULT_USER32_CS 4
+#define GDT_ENTRY_DEFAULT_USER_DS 5
+#define GDT_ENTRY_DEFAULT_USER_CS 6
+#define __USER32_CS   (GDT_ENTRY_DEFAULT_USER32_CS * 8 + 3)
 #define __USER32_DS     __USER_DS
 
 #define GDT_ENTRY_TSS 8 /* needs two entries */
@@ -175,6 +181,10 @@
 
 #endif
 
+#define __KERNEL_CS     (GDT_ENTRY_KERNEL_CS * 8)
+#define __KERNEL_DS     (GDT_ENTRY_KERNEL_DS * 8)
+#define __USER_DS     (GDT_ENTRY_DEFAULT_USER_DS* 8 + 3)
+#define __USER_CS     (GDT_ENTRY_DEFAULT_USER_CS* 8 + 3)
 #ifndef CONFIG_PARAVIRT
 #define get_kernel_rpl()  0
 #endif
@@ -202,4 +212,4 @@ extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
 #endif
 #endif
 
-#endif
+#endif /* ASM_X86__SEGMENT_H */
diff --git a/include/asm-x86/semaphore.h b/include/asm-x86/semaphore.h
deleted file mode 100644
index d9b2034ed1d2..000000000000
--- a/include/asm-x86/semaphore.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <linux/semaphore.h>
diff --git a/include/asm-x86/sembuf.h b/include/asm-x86/sembuf.h
index ee50c801f7b7..81f06b7e5a3f 100644
--- a/include/asm-x86/sembuf.h
+++ b/include/asm-x86/sembuf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SEMBUF_H
-#define _ASM_X86_SEMBUF_H
+#ifndef ASM_X86__SEMBUF_H
+#define ASM_X86__SEMBUF_H
 
 /*
  * The semid64_ds structure for x86 architecture.
@@ -21,4 +21,4 @@ struct semid64_ds {
         unsigned long   __unused4;
 };
 
-#endif /* _ASM_X86_SEMBUF_H */
+#endif /* ASM_X86__SEMBUF_H */
diff --git a/include/asm-x86/serial.h b/include/asm-x86/serial.h
index 628c801535ea..303660b671e5 100644
--- a/include/asm-x86/serial.h
+++ b/include/asm-x86/serial.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SERIAL_H
-#define _ASM_X86_SERIAL_H
+#ifndef ASM_X86__SERIAL_H
+#define ASM_X86__SERIAL_H
 
 /*
  * This assumes you have a 1.8432 MHz clock for your UART.
@@ -26,4 +26,4 @@
         { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },      /* ttyS2 */     \
         { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },     /* ttyS3 */
 
-#endif /* _ASM_X86_SERIAL_H */
+#endif /* ASM_X86__SERIAL_H */
diff --git a/include/asm-x86/setup.h b/include/asm-x86/setup.h
index fa6763af8d26..11b6cc14b289 100644
--- a/include/asm-x86/setup.h
+++ b/include/asm-x86/setup.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SETUP_H
-#define _ASM_X86_SETUP_H
+#ifndef ASM_X86__SETUP_H
+#define ASM_X86__SETUP_H
 
 #define COMMAND_LINE_SIZE 2048
 
@@ -8,7 +8,42 @@
 /* Interrupt control for vSMPowered x86_64 systems */
 void vsmp_init(void);
 
-char *machine_specific_memory_setup(void);
+#ifdef CONFIG_X86_VISWS
+extern void visws_early_detect(void);
+extern int is_visws_box(void);
+#else
+static inline void visws_early_detect(void) { }
+static inline int is_visws_box(void) { return 0; }
+#endif
+
+/*
+ * Any setup quirks to be performed?
+ */
+struct mpc_config_processor;
+struct mpc_config_bus;
+struct mp_config_oemtable;
+struct x86_quirks {
+        int (*arch_pre_time_init)(void);
+        int (*arch_time_init)(void);
+        int (*arch_pre_intr_init)(void);
+        int (*arch_intr_init)(void);
+        int (*arch_trap_init)(void);
+        char * (*arch_memory_setup)(void);
+        int (*mach_get_smp_config)(unsigned int early);
+        int (*mach_find_smp_config)(unsigned int reserve);
+
+        int *mpc_record;
+        int (*mpc_apic_id)(struct mpc_config_processor *m);
+        void (*mpc_oem_bus_info)(struct mpc_config_bus *m, char *name);
+        void (*mpc_oem_pci_bus)(struct mpc_config_bus *m);
+        void (*smp_read_mpc_oem)(struct mp_config_oemtable *oemtable,
+                                    unsigned short oemsize);
+        int (*setup_ioapic_ids)(void);
+};
+
+extern struct x86_quirks *x86_quirks;
+extern unsigned long saved_video_mode;
+
 #ifndef CONFIG_PARAVIRT
 #define paravirt_post_allocator_init()  do {} while (0)
 #endif
@@ -43,30 +78,28 @@ char *machine_specific_memory_setup(void);
  */
 extern struct boot_params boot_params;
 
-#ifdef __i386__
 /*
  * Do NOT EVER look at the BIOS memory size location.
  * It does not work on many machines.
  */
 #define LOWMEMSIZE()    (0x9f000)
 
-struct e820entry;
-
-char * __init machine_specific_memory_setup(void);
-char *memory_setup(void);
+#ifdef __i386__
 
-int __init copy_e820_map(struct e820entry *biosmap, int nr_map);
-int __init sanitize_e820_map(struct e820entry *biosmap, char *pnr_map);
-void __init add_memory_region(unsigned long long start,
-                              unsigned long long size, int type);
+void __init i386_start_kernel(void);
+extern void probe_roms(void);
 
+extern unsigned long init_pg_tables_start;
 extern unsigned long init_pg_tables_end;
 
-
+#else
+void __init x86_64_init_pda(void);
+void __init x86_64_start_kernel(char *real_mode);
+void __init x86_64_start_reservations(char *real_mode_data);
 
 #endif /* __i386__ */
 #endif /* _SETUP */
 #endif /* __ASSEMBLY__ */
 #endif  /*  __KERNEL__  */
 
-#endif /* _ASM_X86_SETUP_H */
+#endif /* ASM_X86__SETUP_H */
diff --git a/include/asm-x86/shmbuf.h b/include/asm-x86/shmbuf.h
index b51413b74971..f51aec2298e9 100644
--- a/include/asm-x86/shmbuf.h
+++ b/include/asm-x86/shmbuf.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SHMBUF_H
-#define _ASM_X86_SHMBUF_H
+#ifndef ASM_X86__SHMBUF_H
+#define ASM_X86__SHMBUF_H
 
 /*
  * The shmid64_ds structure for x86 architecture.
@@ -48,4 +48,4 @@ struct shminfo64 {
         unsigned long   __unused4;
 };
 
-#endif /* _ASM_X86_SHMBUF_H */
+#endif /* ASM_X86__SHMBUF_H */
diff --git a/include/asm-x86/shmparam.h b/include/asm-x86/shmparam.h
index 0880cf0917b9..a83a1fd96a0e 100644
--- a/include/asm-x86/shmparam.h
+++ b/include/asm-x86/shmparam.h
@@ -1,6 +1,6 @@
-#ifndef _ASM_X86_SHMPARAM_H
-#define _ASM_X86_SHMPARAM_H
+#ifndef ASM_X86__SHMPARAM_H
+#define ASM_X86__SHMPARAM_H
 
 #define SHMLBA PAGE_SIZE         /* attach addr a multiple of this */
 
-#endif /* _ASM_X86_SHMPARAM_H */
+#endif /* ASM_X86__SHMPARAM_H */
diff --git a/include/asm-x86/sigcontext.h b/include/asm-x86/sigcontext.h
index 2f9c884d2c0f..ee813f4fe5d5 100644
--- a/include/asm-x86/sigcontext.h
+++ b/include/asm-x86/sigcontext.h
@@ -1,9 +1,43 @@
-#ifndef _ASM_X86_SIGCONTEXT_H
-#define _ASM_X86_SIGCONTEXT_H
+#ifndef ASM_X86__SIGCONTEXT_H
+#define ASM_X86__SIGCONTEXT_H
 
 #include <linux/compiler.h>
 #include <asm/types.h>
 
+#define FP_XSTATE_MAGIC1        0x46505853U
+#define FP_XSTATE_MAGIC2        0x46505845U
+#define FP_XSTATE_MAGIC2_SIZE   sizeof(FP_XSTATE_MAGIC2)
+
+/*
+ * bytes 464..511 in the current 512byte layout of fxsave/fxrstor frame
+ * are reserved for SW usage. On cpu's supporting xsave/xrstor, these bytes
+ * are used to extended the fpstate pointer in the sigcontext, which now
+ * includes the extended state information along with fpstate information.
+ *
+ * Presence of FP_XSTATE_MAGIC1 at the beginning of this SW reserved
+ * area and FP_XSTATE_MAGIC2 at the end of memory layout
+ * (extended_size - FP_XSTATE_MAGIC2_SIZE) indicates the presence of the
+ * extended state information in the memory layout pointed by the fpstate
+ * pointer in sigcontext.
+ */
+struct _fpx_sw_bytes {
+        __u32 magic1;           /* FP_XSTATE_MAGIC1 */
+        __u32 extended_size;    /* total size of the layout referred by
+                                 * fpstate pointer in the sigcontext.
+                                 */
+        __u64 xstate_bv;
+                                /* feature bit mask (including fp/sse/extended
+                                 * state) that is present in the memory
+                                 * layout.
+                                 */
+        __u32 xstate_size;      /* actual xsave state size, based on the
+                                 * features saved in the layout.
+                                 * 'extended_size' will be greater than
+                                 * 'xstate_size'.
+                                 */
+        __u32 padding[7];       /*  for future use. */
+};
+
 #ifdef __i386__
 /*
  * As documented in the iBCS2 standard..
@@ -53,7 +87,13 @@ struct _fpstate {
         unsigned long   reserved;
         struct _fpxreg  _fxsr_st[8];    /* FXSR FPU reg data is ignored */
         struct _xmmreg  _xmm[8];
-        unsigned long   padding[56];
+        unsigned long   padding1[44];
+
+        union {
+                unsigned long   padding2[12];
+                struct _fpx_sw_bytes sw_reserved; /* represents the extended
+                                                   * state info */
+        };
 };
 
 #define X86_FXSR_MAGIC          0x0000
@@ -79,7 +119,15 @@ struct sigcontext {
         unsigned long flags;
         unsigned long sp_at_signal;
         unsigned short ss, __ssh;
-        struct _fpstate __user *fpstate;
+
+        /*
+         * 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
+         * (struct _fpx_sw_bytes)
+         */
+        void __user *fpstate;           /* zero when no FPU/extended context */
         unsigned long oldmask;
         unsigned long cr2;
 };
@@ -130,7 +178,12 @@ struct _fpstate {
         __u32   mxcsr_mask;
         __u32   st_space[32];   /* 8*16 bytes for each FP-reg */
         __u32   xmm_space[64];  /* 16*16 bytes for each XMM-reg  */
-        __u32   reserved2[24];
+        __u32   reserved2[12];
+        union {
+                __u32   reserved3[12];
+                struct _fpx_sw_bytes sw_reserved; /* represents the extended
+                                                   * state information */
+        };
 };
 
 #ifdef __KERNEL__
@@ -161,7 +214,15 @@ struct sigcontext {
         unsigned long trapno;
         unsigned long oldmask;
         unsigned long cr2;
-        struct _fpstate __user *fpstate;        /* zero when no FPU context */
+
+        /*
+         * 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
+         * (struct _fpx_sw_bytes)
+         */
+        void __user *fpstate;           /* zero when no FPU/extended context */
         unsigned long reserved1[8];
 };
 #else /* __KERNEL__ */
@@ -202,4 +263,22 @@ struct sigcontext {
 
 #endif /* !__i386__ */
 
-#endif
+struct _xsave_hdr {
+        __u64 xstate_bv;
+        __u64 reserved1[2];
+        __u64 reserved2[5];
+};
+
+/*
+ * Extended state pointed by the fpstate pointer in the sigcontext.
+ * In addition to the fpstate, information encoded in the xstate_hdr
+ * indicates the presence of other extended state information
+ * supported by the processor and OS.
+ */
+struct _xstate {
+        struct _fpstate fpstate;
+        struct _xsave_hdr xstate_hdr;
+        /* new processor state extensions go here */
+};
+
+#endif /* ASM_X86__SIGCONTEXT_H */
diff --git a/include/asm-x86/sigcontext32.h b/include/asm-x86/sigcontext32.h
index 57a9686fb491..8c347032c2f2 100644
--- a/include/asm-x86/sigcontext32.h
+++ b/include/asm-x86/sigcontext32.h
@@ -1,5 +1,5 @@
-#ifndef _SIGCONTEXT32_H
-#define _SIGCONTEXT32_H 1
+#ifndef ASM_X86__SIGCONTEXT32_H
+#define ASM_X86__SIGCONTEXT32_H
 
 /* signal context for 32bit programs. */
 
@@ -40,7 +40,11 @@ struct _fpstate_ia32 {
         __u32   reserved;
         struct _fpxreg  _fxsr_st[8];
         struct _xmmreg  _xmm[8];        /* It's actually 16 */
-        __u32   padding[56];
+        __u32   padding[44];
+        union {
+                __u32 padding2[12];
+                struct _fpx_sw_bytes sw_reserved;
+        };
 };
 
 struct sigcontext_ia32 {
@@ -68,4 +72,4 @@ struct sigcontext_ia32 {
        unsigned int cr2;
 };
 
-#endif
+#endif /* ASM_X86__SIGCONTEXT32_H */
diff --git a/include/asm-x86/siginfo.h b/include/asm-x86/siginfo.h
index a477bea0c2a1..808bdfb2958c 100644
--- a/include/asm-x86/siginfo.h
+++ b/include/asm-x86/siginfo.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SIGINFO_H
-#define _ASM_X86_SIGINFO_H
+#ifndef ASM_X86__SIGINFO_H
+#define ASM_X86__SIGINFO_H
 
 #ifdef __x86_64__
 # define __ARCH_SI_PREAMBLE_SIZE        (4 * sizeof(int))
@@ -7,4 +7,4 @@
 
 #include <asm-generic/siginfo.h>
 
-#endif
+#endif /* ASM_X86__SIGINFO_H */
diff --git a/include/asm-x86/signal.h b/include/asm-x86/signal.h
index f15186d39c69..65acc82d267a 100644
--- a/include/asm-x86/signal.h
+++ b/include/asm-x86/signal.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SIGNAL_H
-#define _ASM_X86_SIGNAL_H
+#ifndef ASM_X86__SIGNAL_H
+#define ASM_X86__SIGNAL_H
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
@@ -140,6 +140,9 @@ struct sigaction {
 struct k_sigaction {
         struct sigaction sa;
 };
+
+extern void do_notify_resume(struct pt_regs *, void *, __u32);
+
 # else /* __KERNEL__ */
 /* Here we must cater to libcs that poke about in kernel headers.  */
 
@@ -181,12 +184,12 @@ typedef struct sigaltstack {
 #ifdef __KERNEL__
 #include <asm/sigcontext.h>
 
-#ifdef __386__
+#ifdef __i386__
 
 #define __HAVE_ARCH_SIG_BITOPS
 
 #define sigaddset(set,sig)                  \
-        (__builtin_constantp(sig)           \
+        (__builtin_constant_p(sig)          \
          ? __const_sigaddset((set), (sig))  \
          : __gen_sigaddset((set), (sig)))
 
@@ -256,4 +259,4 @@ struct pt_regs;
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 
-#endif
+#endif /* ASM_X86__SIGNAL_H */
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
index 1ebaa5cd3112..6df2615f9138 100644
--- a/include/asm-x86/smp.h
+++ b/include/asm-x86/smp.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SMP_H_
-#define _ASM_X86_SMP_H_
+#ifndef ASM_X86__SMP_H
+#define ASM_X86__SMP_H
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
 #include <linux/init.h>
@@ -25,25 +25,21 @@ extern cpumask_t cpu_callin_map;
 extern void (*mtrr_hook)(void);
 extern void zap_low_mappings(void);
 
+extern int __cpuinit get_local_pda(int cpu);
+
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 extern cpumask_t cpu_initialized;
 
-#ifdef CONFIG_SMP
-extern u16 x86_cpu_to_apicid_init[];
-extern u16 x86_bios_cpu_apicid_init[];
-extern void *x86_cpu_to_apicid_early_ptr;
-extern void *x86_bios_cpu_apicid_early_ptr;
-#else
-#define x86_cpu_to_apicid_early_ptr NULL
-#define x86_bios_cpu_apicid_early_ptr NULL
-#endif
-
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
-DECLARE_PER_CPU(u16, x86_cpu_to_apicid);
-DECLARE_PER_CPU(u16, x86_bios_cpu_apicid);
+#ifdef CONFIG_X86_32
+DECLARE_PER_CPU(int, cpu_number);
+#endif
+
+DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
 
 /* Static state in head.S used to set up a CPU */
 extern struct {
@@ -54,14 +50,18 @@ extern struct {
 struct smp_ops {
         void (*smp_prepare_boot_cpu)(void);
         void (*smp_prepare_cpus)(unsigned max_cpus);
-        int (*cpu_up)(unsigned cpu);
         void (*smp_cpus_done)(unsigned max_cpus);
 
         void (*smp_send_stop)(void);
         void (*smp_send_reschedule)(int cpu);
-        int (*smp_call_function_mask)(cpumask_t mask,
-                                      void (*func)(void *info), void *info,
-                                      int wait);
+
+        int (*cpu_up)(unsigned cpu);
+        int (*cpu_disable)(void);
+        void (*cpu_die)(unsigned int cpu);
+        void (*play_dead)(void);
+
+        void (*send_call_func_ipi)(cpumask_t mask);
+        void (*send_call_func_single_ipi)(int cpu);
 };
 
 /* Globals due to paravirt */
@@ -98,27 +98,48 @@ static inline int __cpu_up(unsigned int cpu)
         return smp_ops.cpu_up(cpu);
 }
 
+static inline int __cpu_disable(void)
+{
+        return smp_ops.cpu_disable();
+}
+
+static inline void __cpu_die(unsigned int cpu)
+{
+        smp_ops.cpu_die(cpu);
+}
+
+static inline void play_dead(void)
+{
+        smp_ops.play_dead();
+}
+
 static inline void smp_send_reschedule(int cpu)
 {
         smp_ops.smp_send_reschedule(cpu);
 }
 
-static inline int smp_call_function_mask(cpumask_t mask,
-                                         void (*func) (void *info), void *info,
-                                         int wait)
+static inline void arch_send_call_function_single_ipi(int cpu)
 {
-        return smp_ops.smp_call_function_mask(mask, func, info, wait);
+        smp_ops.send_call_func_single_ipi(cpu);
 }
 
+static inline void arch_send_call_function_ipi(cpumask_t mask)
+{
+        smp_ops.send_call_func_ipi(mask);
+}
+
+void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void native_smp_cpus_done(unsigned int max_cpus);
 int native_cpu_up(unsigned int cpunum);
+int native_cpu_disable(void);
+void native_cpu_die(unsigned int cpu);
+void native_play_dead(void);
+void play_dead_common(void);
 
-extern int __cpu_disable(void);
-extern void __cpu_die(unsigned int cpu);
-
-extern void prefill_possible_map(void);
+void native_send_call_func_ipi(cpumask_t mask);
+void native_send_call_func_single_ipi(int cpu);
 
 void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)    per_cpu(x86_cpu_to_apicid, cpu)
@@ -130,6 +151,14 @@ static inline int num_booting_cpus(void)
 }
 #endif /* CONFIG_SMP */
 
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_CPU)
+extern void prefill_possible_map(void);
+#else
+static inline void prefill_possible_map(void)
+{
+}
+#endif
+
 extern unsigned disabled_cpus __cpuinitdata;
 
 #ifdef CONFIG_X86_32_SMP
@@ -138,7 +167,6 @@ extern unsigned disabled_cpus __cpuinitdata;
  * from the initial startup. We map APIC_BASE very early in page_setup(),
  * so this is correct in the x86 case.
  */
-DECLARE_PER_CPU(int, cpu_number);
 #define raw_smp_processor_id() (x86_read_percpu(cpu_number))
 extern int safe_smp_processor_id(void);
 
@@ -161,30 +189,33 @@ extern int safe_smp_processor_id(void);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
+#ifndef CONFIG_X86_64
 static inline int logical_smp_processor_id(void)
 {
         /* we don't want to mark this access volatile - bad code generation */
         return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
 }
 
-#ifndef CONFIG_X86_64
+#include <mach_apicdef.h>
 static inline unsigned int read_apic_id(void)
 {
-        return *(u32 *)(APIC_BASE + APIC_ID);
+        unsigned int reg;
+
+        reg = *(u32 *)(APIC_BASE + APIC_ID);
+
+        return GET_APIC_ID(reg);
 }
-#else
-extern unsigned int read_apic_id(void);
 #endif
 
 
-# ifdef APIC_DEFINITION
+# if defined(APIC_DEFINITION) || defined(CONFIG_X86_64)
 extern int hard_smp_processor_id(void);
 # else
-#  include <mach_apicdef.h>
+#include <mach_apicdef.h>
 static inline int hard_smp_processor_id(void)
 {
         /* we don't want to mark this access volatile - bad code generation */
-        return GET_APIC_ID(read_apic_id());
+        return read_apic_id();
 }
 # endif /* APIC_DEFINITION */
 
@@ -196,13 +227,5 @@ static inline int hard_smp_processor_id(void)
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern void cpu_exit_clear(void);
-extern void cpu_uninit(void);
-#endif
-
-extern void smp_alloc_memory(void);
-extern void lock_ipi_call_lock(void);
-extern void unlock_ipi_call_lock(void);
 #endif /* __ASSEMBLY__ */
-#endif
+#endif /* ASM_X86__SMP_H */
diff --git a/include/asm-x86/socket.h b/include/asm-x86/socket.h
index 80af9c4ccad7..db73274c83c3 100644
--- a/include/asm-x86/socket.h
+++ b/include/asm-x86/socket.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SOCKET_H
-#define _ASM_SOCKET_H
+#ifndef ASM_X86__SOCKET_H
+#define ASM_X86__SOCKET_H
 
 #include <asm/sockios.h>
 
@@ -54,4 +54,4 @@
 
 #define SO_MARK                 36
 
-#endif /* _ASM_SOCKET_H */
+#endif /* ASM_X86__SOCKET_H */
diff --git a/include/asm-x86/sockios.h b/include/asm-x86/sockios.h
index 49cc72b5d3c9..a006704fdc84 100644
--- a/include/asm-x86/sockios.h
+++ b/include/asm-x86/sockios.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SOCKIOS_H
-#define _ASM_X86_SOCKIOS_H
+#ifndef ASM_X86__SOCKIOS_H
+#define ASM_X86__SOCKIOS_H
 
 /* Socket-level I/O control calls. */
 #define FIOSETOWN       0x8901
@@ -10,4 +10,4 @@
 #define SIOCGSTAMP      0x8906          /* Get stamp (timeval) */
 #define SIOCGSTAMPNS    0x8907          /* Get stamp (timespec) */
 
-#endif /* _ASM_X86_SOCKIOS_H */
+#endif /* ASM_X86__SOCKIOS_H */
diff --git a/include/asm-x86/sparsemem.h b/include/asm-x86/sparsemem.h
index 9bd48b0a534b..38f8e6bc3186 100644
--- a/include/asm-x86/sparsemem.h
+++ b/include/asm-x86/sparsemem.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SPARSEMEM_H
-#define _ASM_X86_SPARSEMEM_H
+#ifndef ASM_X86__SPARSEMEM_H
+#define ASM_X86__SPARSEMEM_H
 
 #ifdef CONFIG_SPARSEMEM
 /*
@@ -31,4 +31,4 @@
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
-#endif
+#endif /* ASM_X86__SPARSEMEM_H */
diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h
index 21e89bf92f1c..157ff7fab97a 100644
--- a/include/asm-x86/spinlock.h
+++ b/include/asm-x86/spinlock.h
@@ -1,12 +1,12 @@
-#ifndef _X86_SPINLOCK_H_
-#define _X86_SPINLOCK_H_
+#ifndef ASM_X86__SPINLOCK_H
+#define ASM_X86__SPINLOCK_H
 
 #include <asm/atomic.h>
 #include <asm/rwlock.h>
 #include <asm/page.h>
 #include <asm/processor.h>
 #include <linux/compiler.h>
-
+#include <asm/paravirt.h>
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  *
@@ -21,8 +21,10 @@
 
 #ifdef CONFIG_X86_32
 # define LOCK_PTR_REG "a"
+# define REG_PTR_MODE "k"
 #else
 # define LOCK_PTR_REG "D"
+# define REG_PTR_MODE "q"
 #endif
 
 #if defined(CONFIG_X86_32) && \
@@ -54,21 +56,9 @@
  * much between them in performance though, especially as locks are out of line.
  */
 #if (NR_CPUS < 256)
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
-{
-        int tmp = ACCESS_ONCE(lock->slock);
-
-        return (((tmp >> 8) & 0xff) != (tmp & 0xff));
-}
-
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
-{
-        int tmp = ACCESS_ONCE(lock->slock);
-
-        return (((tmp >> 8) & 0xff) - (tmp & 0xff)) > 1;
-}
+#define TICKET_SHIFT 8
 
-static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 {
         short inc = 0x0100;
 
@@ -87,30 +77,26 @@ static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
                 : "memory", "cc");
 }
 
-#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
-
-static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 {
-        int tmp;
-        short new;
+        int tmp, new;
 
-        asm volatile("movw %2,%w0\n\t"
+        asm volatile("movzwl %2, %0\n\t"
                      "cmpb %h0,%b0\n\t"
+                     "leal 0x100(%" REG_PTR_MODE "0), %1\n\t"
                      "jne 1f\n\t"
-                     "movw %w0,%w1\n\t"
-                     "incb %h1\n\t"
-                     "lock ; cmpxchgw %w1,%2\n\t"
+                     LOCK_PREFIX "cmpxchgw %w1,%2\n\t"
                      "1:"
                      "sete %b1\n\t"
                      "movzbl %b1,%0\n\t"
-                     : "=&a" (tmp), "=Q" (new), "+m" (lock->slock)
+                     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
                      :
                      : "memory", "cc");
 
         return tmp;
 }
 
-static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 {
         asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
                      : "+m" (lock->slock)
@@ -118,26 +104,14 @@ static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
                      : "memory", "cc");
 }
 #else
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
-{
-        int tmp = ACCESS_ONCE(lock->slock);
-
-        return (((tmp >> 16) & 0xffff) != (tmp & 0xffff));
-}
+#define TICKET_SHIFT 16
 
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
-{
-        int tmp = ACCESS_ONCE(lock->slock);
-
-        return (((tmp >> 16) & 0xffff) - (tmp & 0xffff)) > 1;
-}
-
-static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 {
         int inc = 0x00010000;
         int tmp;
 
-        asm volatile("lock ; xaddl %0, %1\n"
+        asm volatile(LOCK_PREFIX "xaddl %0, %1\n"
                      "movzwl %w0, %2\n\t"
                      "shrl $16, %0\n\t"
                      "1:\t"
@@ -148,14 +122,12 @@ static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
                      /* don't need lfence here, because loads are in-order */
                      "jmp 1b\n"
                      "2:"
-                     : "+Q" (inc), "+m" (lock->slock), "=r" (tmp)
+                     : "+r" (inc), "+m" (lock->slock), "=&r" (tmp)
                      :
                      : "memory", "cc");
 }
 
-#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
-
-static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 {
         int tmp;
         int new;
@@ -164,20 +136,20 @@ static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
                      "movl %0,%1\n\t"
                      "roll $16, %0\n\t"
                      "cmpl %0,%1\n\t"
+                     "leal 0x00010000(%" REG_PTR_MODE "0), %1\n\t"
                      "jne 1f\n\t"
-                     "addl $0x00010000, %1\n\t"
-                     "lock ; cmpxchgl %1,%2\n\t"
+                     LOCK_PREFIX "cmpxchgl %1,%2\n\t"
                      "1:"
                      "sete %b1\n\t"
                      "movzbl %b1,%0\n\t"
-                     : "=&a" (tmp), "=r" (new), "+m" (lock->slock)
+                     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
                      :
                      : "memory", "cc");
 
         return tmp;
 }
 
-static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 {
         asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
                      : "+m" (lock->slock)
@@ -186,6 +158,117 @@ static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
 }
 #endif
 
+static inline int __ticket_spin_is_locked(raw_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)
+{
+        int tmp = ACCESS_ONCE(lock->slock);
+
+        return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
+}
+
+#ifdef CONFIG_PARAVIRT
+/*
+ * Define virtualization-friendly old-style lock byte lock, for use in
+ * pv_lock_ops if desired.
+ *
+ * This differs from the pre-2.6.24 spinlock by always using xchgb
+ * rather than decb to take the lock; this allows it to use a
+ * zero-initialized lock structure.  It also maintains a 1-byte
+ * contention counter, so that we can implement
+ * __byte_spin_is_contended.
+ */
+struct __byte_spinlock {
+        s8 lock;
+        s8 spinners;
+};
+
+static inline int __byte_spin_is_locked(raw_spinlock_t *lock)
+{
+        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+        return bl->lock != 0;
+}
+
+static inline int __byte_spin_is_contended(raw_spinlock_t *lock)
+{
+        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+        return bl->spinners != 0;
+}
+
+static inline void __byte_spin_lock(raw_spinlock_t *lock)
+{
+        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+        s8 val = 1;
+
+        asm("1: xchgb %1, %0\n"
+            "   test %1,%1\n"
+            "   jz 3f\n"
+            "   " LOCK_PREFIX "incb %2\n"
+            "2: rep;nop\n"
+            "   cmpb $1, %0\n"
+            "   je 2b\n"
+            "   " LOCK_PREFIX "decb %2\n"
+            "   jmp 1b\n"
+            "3:"
+            : "+m" (bl->lock), "+q" (val), "+m" (bl->spinners): : "memory");
+}
+
+static inline int __byte_spin_trylock(raw_spinlock_t *lock)
+{
+        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+        u8 old = 1;
+
+        asm("xchgb %1,%0"
+            : "+m" (bl->lock), "+q" (old) : : "memory");
+
+        return old == 0;
+}
+
+static inline void __byte_spin_unlock(raw_spinlock_t *lock)
+{
+        struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+        smp_wmb();
+        bl->lock = 0;
+}
+#else  /* !CONFIG_PARAVIRT */
+static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+{
+        return __ticket_spin_is_locked(lock);
+}
+
+static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+{
+        return __ticket_spin_is_contended(lock);
+}
+
+static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+{
+        __ticket_spin_lock(lock);
+}
+
+static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+{
+        return __ticket_spin_trylock(lock);
+}
+
+static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+{
+        __ticket_spin_unlock(lock);
+}
+
+static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
+                                                  unsigned long flags)
+{
+        __raw_spin_lock(lock);
+}
+
+#endif  /* CONFIG_PARAVIRT */
+
 static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
 {
         while (__raw_spin_is_locked(lock))
@@ -278,4 +361,4 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 #define _raw_read_relax(lock)   cpu_relax()
 #define _raw_write_relax(lock)  cpu_relax()
 
-#endif
+#endif /* ASM_X86__SPINLOCK_H */
diff --git a/include/asm-x86/spinlock_types.h b/include/asm-x86/spinlock_types.h
index 9029cf78cf5d..6aa9b562c508 100644
--- a/include/asm-x86/spinlock_types.h
+++ b/include/asm-x86/spinlock_types.h
@@ -1,11 +1,11 @@
-#ifndef __ASM_SPINLOCK_TYPES_H
-#define __ASM_SPINLOCK_TYPES_H
+#ifndef ASM_X86__SPINLOCK_TYPES_H
+#define ASM_X86__SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_H
 # error "please don't include this file directly"
 #endif
 
-typedef struct {
+typedef struct raw_spinlock {
         unsigned int slock;
 } raw_spinlock_t;
 
@@ -17,4 +17,4 @@ typedef struct {
 
 #define __RAW_RW_LOCK_UNLOCKED          { RW_LOCK_BIAS }
 
-#endif
+#endif /* ASM_X86__SPINLOCK_TYPES_H */
diff --git a/include/asm-x86/srat.h b/include/asm-x86/srat.h
index f4bba131d068..5363e4f7e1cd 100644
--- a/include/asm-x86/srat.h
+++ b/include/asm-x86/srat.h
@@ -24,14 +24,16 @@
  * Send feedback to Pat Gaughen <gone@us.ibm.com>
  */
 
-#ifndef _ASM_SRAT_H_
-#define _ASM_SRAT_H_
-
-#ifndef CONFIG_ACPI_SRAT
-#error CONFIG_ACPI_SRAT not defined, and srat.h header has been included
-#endif
+#ifndef ASM_X86__SRAT_H
+#define ASM_X86__SRAT_H
 
+#ifdef CONFIG_ACPI_NUMA
 extern int get_memcfg_from_srat(void);
-extern unsigned long *get_zholes_size(int);
+#else
+static inline int get_memcfg_from_srat(void)
+{
+        return 0;
+}
+#endif
 
-#endif /* _ASM_SRAT_H_ */
+#endif /* ASM_X86__SRAT_H */
diff --git a/include/asm-x86/stacktrace.h b/include/asm-x86/stacktrace.h
index 30f82526a8e2..f43517e28532 100644
--- a/include/asm-x86/stacktrace.h
+++ b/include/asm-x86/stacktrace.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_STACKTRACE_H
-#define _ASM_STACKTRACE_H 1
+#ifndef ASM_X86__STACKTRACE_H
+#define ASM_X86__STACKTRACE_H
 
 extern int kstack_depth_to_print;
 
@@ -18,4 +18,4 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data);
 
-#endif
+#endif /* ASM_X86__STACKTRACE_H */
diff --git a/include/asm-x86/stat.h b/include/asm-x86/stat.h
index 5c22dcb5d17e..1e120f628905 100644
--- a/include/asm-x86/stat.h
+++ b/include/asm-x86/stat.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_STAT_H
-#define _ASM_X86_STAT_H
+#ifndef ASM_X86__STAT_H
+#define ASM_X86__STAT_H
 
 #define STAT_HAVE_NSEC 1
 
@@ -111,4 +111,4 @@ struct __old_kernel_stat {
 #endif
 };
 
-#endif
+#endif /* ASM_X86__STAT_H */
diff --git a/include/asm-x86/statfs.h b/include/asm-x86/statfs.h
index 7c651aa97252..3f005bc3aa5b 100644
--- a/include/asm-x86/statfs.h
+++ b/include/asm-x86/statfs.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_STATFS_H
-#define _ASM_X86_STATFS_H
+#ifndef ASM_X86__STATFS_H
+#define ASM_X86__STATFS_H
 
 #ifdef __i386__
 #include <asm-generic/statfs.h>
@@ -60,4 +60,4 @@ struct compat_statfs64 {
 } __attribute__((packed));
 
 #endif /* !__i386__ */
-#endif
+#endif /* ASM_X86__STATFS_H */
diff --git a/include/asm-x86/string_32.h b/include/asm-x86/string_32.h
index b49369ad9a61..487843ed245a 100644
--- a/include/asm-x86/string_32.h
+++ b/include/asm-x86/string_32.h
@@ -1,5 +1,5 @@
-#ifndef _I386_STRING_H_
-#define _I386_STRING_H_
+#ifndef ASM_X86__STRING_32_H
+#define ASM_X86__STRING_32_H
 
 #ifdef __KERNEL__
 
@@ -29,81 +29,116 @@ extern char *strchr(const char *s, int c);
 #define __HAVE_ARCH_STRLEN
 extern size_t strlen(const char *s);
 
-static __always_inline void * __memcpy(void * to, const void * from, size_t n)
+static __always_inline void *__memcpy(void *to, const void *from, size_t n)
 {
-int d0, d1, d2;
-__asm__ __volatile__(
-        "rep ; movsl\n\t"
-        "movl %4,%%ecx\n\t"
-        "andl $3,%%ecx\n\t"
-        "jz 1f\n\t"
-        "rep ; movsb\n\t"
-        "1:"
-        : "=&c" (d0), "=&D" (d1), "=&S" (d2)
-        : "0" (n/4), "g" (n), "1" ((long) to), "2" ((long) from)
-        : "memory");
-return (to);
+        int d0, d1, d2;
+        asm volatile("rep ; movsl\n\t"
+                     "movl %4,%%ecx\n\t"
+                     "andl $3,%%ecx\n\t"
+                     "jz 1f\n\t"
+                     "rep ; movsb\n\t"
+                     "1:"
+                     : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+                     : "0" (n / 4), "g" (n), "1" ((long)to), "2" ((long)from)
+                     : "memory");
+        return to;
 }
 
 /*
  * This looks ugly, but the compiler can optimize it totally,
  * as the count is constant.
  */
-static __always_inline void * __constant_memcpy(void * to, const void * from, size_t n)
+static __always_inline void *__constant_memcpy(void *to, const void *from,
+                                               size_t n)
 {
         long esi, edi;
-        if (!n) return to;
-#if 1   /* want to do small copies with non-string ops? */
+        if (!n)
+                return to;
+
         switch (n) {
-                case 1: *(char*)to = *(char*)from; return to;
-                case 2: *(short*)to = *(short*)from; return to;
-                case 4: *(int*)to = *(int*)from; return to;
-#if 1   /* including those doable with two moves? */
-                case 3: *(short*)to = *(short*)from;
-                        *((char*)to+2) = *((char*)from+2); return to;
-                case 5: *(int*)to = *(int*)from;
-                        *((char*)to+4) = *((char*)from+4); return to;
-                case 6: *(int*)to = *(int*)from;
-                        *((short*)to+2) = *((short*)from+2); return to;
-                case 8: *(int*)to = *(int*)from;
-                        *((int*)to+1) = *((int*)from+1); return to;
-#endif
+        case 1:
+                *(char *)to = *(char *)from;
+                return to;
+        case 2:
+                *(short *)to = *(short *)from;
+                return to;
+        case 4:
+                *(int *)to = *(int *)from;
+                return to;
+
+        case 3:
+                *(short *)to = *(short *)from;
+                *((char *)to + 2) = *((char *)from + 2);
+                return to;
+        case 5:
+                *(int *)to = *(int *)from;
+                *((char *)to + 4) = *((char *)from + 4);
+                return to;
+        case 6:
+                *(int *)to = *(int *)from;
+                *((short *)to + 2) = *((short *)from + 2);
+                return to;
+        case 8:
+                *(int *)to = *(int *)from;
+                *((int *)to + 1) = *((int *)from + 1);
+                return to;
         }
-#endif
-        esi = (long) from;
-        edi = (long) to;
-        if (n >= 5*4) {
+
+        esi = (long)from;
+        edi = (long)to;
+        if (n >= 5 * 4) {
                 /* large block: use rep prefix */
                 int ecx;
-                __asm__ __volatile__(
-                        "rep ; movsl"
-                        : "=&c" (ecx), "=&D" (edi), "=&S" (esi)
-                        : "0" (n/4), "1" (edi),"2" (esi)
-                        : "memory"
+                asm volatile("rep ; movsl"
+                             : "=&c" (ecx), "=&D" (edi), "=&S" (esi)
+                             : "0" (n / 4), "1" (edi), "2" (esi)
+                             : "memory"
                 );
         } else {
                 /* small block: don't clobber ecx + smaller code */
-                if (n >= 4*4) __asm__ __volatile__("movsl"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                if (n >= 3*4) __asm__ __volatile__("movsl"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                if (n >= 2*4) __asm__ __volatile__("movsl"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                if (n >= 1*4) __asm__ __volatile__("movsl"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
+                if (n >= 4 * 4)
+                        asm volatile("movsl"
+                                     : "=&D"(edi), "=&S"(esi)
+                                     : "0"(edi), "1"(esi)
+                                     : "memory");
+                if (n >= 3 * 4)
+                        asm volatile("movsl"
+                                     : "=&D"(edi), "=&S"(esi)
+                                     : "0"(edi), "1"(esi)
+                                     : "memory");
+                if (n >= 2 * 4)
+                        asm volatile("movsl"
+                                     : "=&D"(edi), "=&S"(esi)
+                                     : "0"(edi), "1"(esi)
+                                     : "memory");
+                if (n >= 1 * 4)
+                        asm volatile("movsl"
+                                     : "=&D"(edi), "=&S"(esi)
+                                     : "0"(edi), "1"(esi)
+                                     : "memory");
         }
         switch (n % 4) {
                 /* tail */
-                case 0: return to;
-                case 1: __asm__ __volatile__("movsb"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                        return to;
-                case 2: __asm__ __volatile__("movsw"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                        return to;
-                default: __asm__ __volatile__("movsw\n\tmovsb"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                        return to;
+        case 0:
+                return to;
+        case 1:
+                asm volatile("movsb"
+                             : "=&D"(edi), "=&S"(esi)
+                             : "0"(edi), "1"(esi)
+                             : "memory");
+                return to;
+        case 2:
+                asm volatile("movsw"
+                             : "=&D"(edi), "=&S"(esi)
+                             : "0"(edi), "1"(esi)
+                             : "memory");
+                return to;
+        default:
+                asm volatile("movsw\n\tmovsb"
+                             : "=&D"(edi), "=&S"(esi)
+                             : "0"(edi), "1"(esi)
+                             : "memory");
+                return to;
         }
 }
 
@@ -117,87 +152,86 @@ static __always_inline void * __constant_memcpy(void * to, const void * from, si
  *      This CPU favours 3DNow strongly (eg AMD Athlon)
  */
 
-static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
+static inline void *__constant_memcpy3d(void *to, const void *from, size_t len)
 {
         if (len < 512)
                 return __constant_memcpy(to, from, len);
         return _mmx_memcpy(to, from, len);
 }
 
-static __inline__ void *__memcpy3d(void *to, const void *from, size_t len)
+static inline void *__memcpy3d(void *to, const void *from, size_t len)
 {
         if (len < 512)
                 return __memcpy(to, from, len);
         return _mmx_memcpy(to, from, len);
 }
 
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy3d((t),(f),(n)) : \
- __memcpy3d((t),(f),(n)))
+#define memcpy(t, f, n)                         \
+        (__builtin_constant_p((n))              \
+         ? __constant_memcpy3d((t), (f), (n))   \
+         : __memcpy3d((t), (f), (n)))
 
 #else
 
 /*
  *      No 3D Now!
  */
- 
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy((t),(f),(n)) : \
- __memcpy((t),(f),(n)))
+
+#define memcpy(t, f, n)                         \
+        (__builtin_constant_p((n))              \
+         ? __constant_memcpy((t), (f), (n))     \
+         : __memcpy((t), (f), (n)))
 
 #endif
 
 #define __HAVE_ARCH_MEMMOVE
-void *memmove(void * dest,const void * src, size_t n);
+void *memmove(void *dest, const void *src, size_t n);
 
 #define memcmp __builtin_memcmp
 
 #define __HAVE_ARCH_MEMCHR
-extern void *memchr(const void * cs,int c,size_t count);
+extern void *memchr(const void *cs, int c, size_t count);
 
-static inline void * __memset_generic(void * s, char c,size_t count)
+static inline void *__memset_generic(void *s, char c, size_t count)
 {
-int d0, d1;
-__asm__ __volatile__(
-        "rep\n\t"
-        "stosb"
-        : "=&c" (d0), "=&D" (d1)
-        :"a" (c),"1" (s),"0" (count)
-        :"memory");
-return s;
+        int d0, d1;
+        asm volatile("rep\n\t"
+                     "stosb"
+                     : "=&c" (d0), "=&D" (d1)
+                     : "a" (c), "1" (s), "0" (count)
+                     : "memory");
+        return s;
 }
 
 /* we might want to write optimized versions of these later */
-#define __constant_count_memset(s,c,count) __memset_generic((s),(c),(count))
+#define __constant_count_memset(s, c, count) __memset_generic((s), (c), (count))
 
 /*
- * memset(x,0,y) is a reasonably common thing to do, so we want to fill
+ * memset(x, 0, y) is a reasonably common thing to do, so we want to fill
  * things 32 bits at a time even when we don't know the size of the
  * area at compile-time..
  */
-static __always_inline void * __constant_c_memset(void * s, unsigned long c, size_t count)
+static __always_inline
+void *__constant_c_memset(void *s, unsigned long c, size_t count)
 {
-int d0, d1;
-__asm__ __volatile__(
-        "rep ; stosl\n\t"
-        "testb $2,%b3\n\t"
-        "je 1f\n\t"
-        "stosw\n"
-        "1:\ttestb $1,%b3\n\t"
-        "je 2f\n\t"
-        "stosb\n"
-        "2:"
-        :"=&c" (d0), "=&D" (d1)
-        :"a" (c), "q" (count), "0" (count/4), "1" ((long) s)
-        :"memory");
-return (s);     
+        int d0, d1;
+        asm volatile("rep ; stosl\n\t"
+                     "testb $2,%b3\n\t"
+                     "je 1f\n\t"
+                     "stosw\n"
+                     "1:\ttestb $1,%b3\n\t"
+                     "je 2f\n\t"
+                     "stosb\n"
+                     "2:"
+                     : "=&c" (d0), "=&D" (d1)
+                     : "a" (c), "q" (count), "0" (count/4), "1" ((long)s)
+                     : "memory");
+        return s;
 }
 
 /* Added by Gertjan van Wingerde to make minix and sysv module work */
 #define __HAVE_ARCH_STRNLEN
-extern size_t strnlen(const char * s, size_t count);
+extern size_t strnlen(const char *s, size_t count);
 /* end of additional stuff */
 
 #define __HAVE_ARCH_STRSTR
@@ -207,67 +241,86 @@ extern char *strstr(const char *cs, const char *ct);
  * This looks horribly ugly, but the compiler can optimize it totally,
  * as we by now know that both pattern and count is constant..
  */
-static __always_inline void * __constant_c_and_count_memset(void * s, unsigned long pattern, size_t count)
+static __always_inline
+void *__constant_c_and_count_memset(void *s, unsigned long pattern,
+                                    size_t count)
 {
         switch (count) {
+        case 0:
+                return s;
+        case 1:
+                *(unsigned char *)s = pattern & 0xff;
+                return s;
+        case 2:
+                *(unsigned short *)s = pattern & 0xffff;
+                return s;
+        case 3:
+                *(unsigned short *)s = pattern & 0xffff;
+                *((unsigned char *)s + 2) = pattern & 0xff;
+                return s;
+        case 4:
+                *(unsigned long *)s = pattern;
+                return s;
+        }
+
+#define COMMON(x)                                                       \
+        asm volatile("rep ; stosl"                                      \
+                     x                                                  \
+                     : "=&c" (d0), "=&D" (d1)                           \
+                     : "a" (eax), "0" (count/4), "1" ((long)s)  \
+                     : "memory")
+
+        {
+                int d0, d1;
+#if __GNUC__ == 4 && __GNUC_MINOR__ == 0
+                /* Workaround for broken gcc 4.0 */
+                register unsigned long eax asm("%eax") = pattern;
+#else
+                unsigned long eax = pattern;
+#endif
+
+                switch (count % 4) {
                 case 0:
+                        COMMON("");
                         return s;
                 case 1:
-                        *(unsigned char *)s = pattern & 0xff;
+                        COMMON("\n\tstosb");
                         return s;
                 case 2:
-                        *(unsigned short *)s = pattern & 0xffff;
-                        return s;
-                case 3:
-                        *(unsigned short *)s = pattern & 0xffff;
-                        *(2+(unsigned char *)s) = pattern & 0xff;
+                        COMMON("\n\tstosw");
                         return s;
-                case 4:
-                        *(unsigned long *)s = pattern;
+                default:
+                        COMMON("\n\tstosw\n\tstosb");
                         return s;
+                }
         }
-#define COMMON(x) \
-__asm__  __volatile__( \
-        "rep ; stosl" \
-        x \
-        : "=&c" (d0), "=&D" (d1) \
-        : "a" (pattern),"0" (count/4),"1" ((long) s) \
-        : "memory")
-{
-        int d0, d1;
-        switch (count % 4) {
-                case 0: COMMON(""); return s;
-                case 1: COMMON("\n\tstosb"); return s;
-                case 2: COMMON("\n\tstosw"); return s;
-                default: COMMON("\n\tstosw\n\tstosb"); return s;
-        }
-}
-  
+
 #undef COMMON
 }
 
-#define __constant_c_x_memset(s, c, count) \
-(__builtin_constant_p(count) ? \
- __constant_c_and_count_memset((s),(c),(count)) : \
- __constant_c_memset((s),(c),(count)))
+#define __constant_c_x_memset(s, c, count)                      \
+        (__builtin_constant_p(count)                            \
+         ? __constant_c_and_count_memset((s), (c), (count))     \
+         : __constant_c_memset((s), (c), (count)))
 
-#define __memset(s, c, count) \
-(__builtin_constant_p(count) ? \
- __constant_count_memset((s),(c),(count)) : \
- __memset_generic((s),(c),(count)))
+#define __memset(s, c, count)                           \
+        (__builtin_constant_p(count)                    \
+         ? __constant_count_memset((s), (c), (count))   \
+         : __memset_generic((s), (c), (count)))
 
 #define __HAVE_ARCH_MEMSET
-#define memset(s, c, count) \
-(__builtin_constant_p(c) ? \
- __constant_c_x_memset((s),(0x01010101UL*(unsigned char)(c)),(count)) : \
- __memset((s),(c),(count)))
+#define memset(s, c, count)                                             \
+        (__builtin_constant_p(c)                                        \
+         ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \
+                                 (count))                               \
+         : __memset((s), (c), (count)))
 
 /*
  * find the first occurrence of byte 'c', or 1 past the area if none
  */
 #define __HAVE_ARCH_MEMSCAN
-extern void *memscan(void * addr, int c, size_t size);
+extern void *memscan(void *addr, int c, size_t size);
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__STRING_32_H */
diff --git a/include/asm-x86/string_64.h b/include/asm-x86/string_64.h
index 52b5ab383395..a2add11d3b66 100644
--- a/include/asm-x86/string_64.h
+++ b/include/asm-x86/string_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_STRING_H_
-#define _X86_64_STRING_H_
+#ifndef ASM_X86__STRING_64_H
+#define ASM_X86__STRING_64_H
 
 #ifdef __KERNEL__
 
@@ -57,4 +57,4 @@ int strcmp(const char *cs, const char *ct);
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__STRING_64_H */
diff --git a/include/asm-x86/mach-summit/mach_apic.h b/include/asm-x86/summit/apic.h
index 1f76c2e70232..c5b2e4b10358 100644
--- a/include/asm-x86/mach-summit/mach_apic.h
+++ b/include/asm-x86/summit/apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef __ASM_SUMMIT_APIC_H
+#define __ASM_SUMMIT_APIC_H
 
 #include <asm/smp.h>
 
@@ -21,7 +21,7 @@ static inline cpumask_t target_cpus(void)
          * Just start on cpu 0.  IRQ balancing will spread load
          */
         return cpumask_of_cpu(0);
-} 
+}
 #define TARGET_CPUS     (target_cpus())
 
 #define INT_DELIVERY_MODE (dest_LowestPrio)
@@ -30,10 +30,10 @@ static inline cpumask_t target_cpus(void)
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
 {
         return 0;
-} 
+}
 
 /* we don't use the phys_cpu_present_map to indicate apicid presence */
-static inline unsigned long check_apicid_present(int bit) 
+static inline unsigned long check_apicid_present(int bit)
 {
         return 1;
 }
@@ -63,10 +63,10 @@ static inline void init_apic_ldr(void)
          * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
         BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
         id = my_cluster | (1UL << count);
-        apic_write_around(APIC_DFR, APIC_DFR_VALUE);
+        apic_write(APIC_DFR, APIC_DFR_VALUE);
         val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
         val |= SET_APIC_LOGICAL_ID(id);
-        apic_write_around(APIC_LDR, val);
+        apic_write(APIC_LDR, val);
 }
 
 static inline int multi_timer_check(int apic, int irq)
@@ -143,22 +143,22 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
         int num_bits_set;
         int cpus_found = 0;
         int cpu;
-        int apicid;     
+        int apicid;
 
         num_bits_set = cpus_weight(cpumask);
         /* Return id to all */
         if (num_bits_set == NR_CPUS)
                 return (int) 0xFF;
-        /* 
-         * The cpus in the mask must all be on the apic cluster.  If are not 
-         * on the same apicid cluster return default value of TARGET_CPUS. 
+        /*
+         * The cpus in the mask must all be on the apic cluster.  If are not
+         * on the same apicid cluster return default value of TARGET_CPUS.
          */
         cpu = first_cpu(cpumask);
         apicid = cpu_to_logical_apicid(cpu);
         while (cpus_found < num_bits_set) {
                 if (cpu_isset(cpu, cpumask)) {
                         int new_apicid = cpu_to_logical_apicid(cpu);
-                        if (apicid_cluster(apicid) != 
+                        if (apicid_cluster(apicid) !=
                                         apicid_cluster(new_apicid)){
                                 printk ("%s: Not a valid mask!\n",__FUNCTION__);
                                 return 0xFF;
@@ -182,4 +182,4 @@ static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
         return hard_smp_processor_id() >> index_msb;
 }
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* __ASM_SUMMIT_APIC_H */
diff --git a/include/asm-x86/summit/apicdef.h b/include/asm-x86/summit/apicdef.h
new file mode 100644
index 000000000000..f3fbca1f61c1
--- /dev/null
+++ b/include/asm-x86/summit/apicdef.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_SUMMIT_APICDEF_H
+#define __ASM_SUMMIT_APICDEF_H
+
+#define         APIC_ID_MASK            (0xFF<<24)
+
+static inline unsigned get_apic_id(unsigned long x)
+{
+        return (x>>24)&0xFF;
+}
+
+#define         GET_APIC_ID(x)  get_apic_id(x)
+
+#endif
diff --git a/include/asm-x86/mach-summit/mach_ipi.h b/include/asm-x86/summit/ipi.h
index 9404c535b7ec..53bd1e7bd7b4 100644
--- a/include/asm-x86/mach-summit/mach_ipi.h
+++ b/include/asm-x86/summit/ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef __ASM_SUMMIT_IPI_H
+#define __ASM_SUMMIT_IPI_H
 
 void send_IPI_mask_sequence(cpumask_t mask, int vector);
 
@@ -22,4 +22,4 @@ static inline void send_IPI_all(int vector)
         send_IPI_mask(cpu_online_map, vector);
 }
 
-#endif /* __ASM_MACH_IPI_H */
+#endif /* __ASM_SUMMIT_IPI_H */
diff --git a/include/asm-x86/mach-summit/irq_vectors_limits.h b/include/asm-x86/summit/irq_vectors_limits.h
index 890ce3f5e09a..890ce3f5e09a 100644
--- a/include/asm-x86/mach-summit/irq_vectors_limits.h
+++ b/include/asm-x86/summit/irq_vectors_limits.h
diff --git a/include/asm-x86/mach-summit/mach_mpparse.h b/include/asm-x86/summit/mpparse.h
index fdf591701339..013ce6fab2d5 100644
--- a/include/asm-x86/mach-summit/mach_mpparse.h
+++ b/include/asm-x86/summit/mpparse.h
@@ -1,7 +1,6 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef __ASM_SUMMIT_MPPARSE_H
+#define __ASM_SUMMIT_MPPARSE_H
 
-#include <mach_apic.h>
 #include <asm/tsc.h>
 
 extern int use_cyclone;
@@ -12,11 +11,11 @@ extern void setup_summit(void);
 #define setup_summit()  {}
 #endif
 
-static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, 
+static inline int mps_oem_check(struct mp_config_table *mpc, char *oem,
                 char *productid)
 {
-        if (!strncmp(oem, "IBM ENSW", 8) && 
-                        (!strncmp(productid, "VIGIL SMP", 9) 
+        if (!strncmp(oem, "IBM ENSW", 8) &&
+                        (!strncmp(productid, "VIGIL SMP", 9)
                          || !strncmp(productid, "EXA", 3)
                          || !strncmp(productid, "RUTHLESS SMP", 12))){
                 mark_tsc_unstable("Summit based system");
@@ -107,4 +106,4 @@ static inline int is_WPEG(struct rio_detail *rio){
                 rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
 }
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* __ASM_SUMMIT_MPPARSE_H */
diff --git a/include/asm-x86/suspend_32.h b/include/asm-x86/suspend_32.h
index 24e1c080aa8a..acb6d4d491f4 100644
--- a/include/asm-x86/suspend_32.h
+++ b/include/asm-x86/suspend_32.h
@@ -3,6 +3,9 @@
  * Based on code
  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
  */
+#ifndef ASM_X86__SUSPEND_32_H
+#define ASM_X86__SUSPEND_32_H
+
 #include <asm/desc.h>
 #include <asm/i387.h>
 
@@ -44,3 +47,5 @@ static inline void acpi_save_register_state(unsigned long return_point)
 /* routines for saving/restoring kernel state */
 extern int acpi_save_state_mem(void);
 #endif
+
+#endif /* ASM_X86__SUSPEND_32_H */
diff --git a/include/asm-x86/suspend_64.h b/include/asm-x86/suspend_64.h
index dc3262b43072..cf821dd310e8 100644
--- a/include/asm-x86/suspend_64.h
+++ b/include/asm-x86/suspend_64.h
@@ -3,8 +3,8 @@
  * Based on code
  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
  */
-#ifndef __ASM_X86_64_SUSPEND_H
-#define __ASM_X86_64_SUSPEND_H
+#ifndef ASM_X86__SUSPEND_64_H
+#define ASM_X86__SUSPEND_64_H
 
 #include <asm/desc.h>
 #include <asm/i387.h>
@@ -49,4 +49,4 @@ extern int acpi_save_state_mem(void);
 extern char core_restore_code;
 extern char restore_registers;
 
-#endif /* __ASM_X86_64_SUSPEND_H */
+#endif /* ASM_X86__SUSPEND_64_H */
diff --git a/include/asm-x86/swiotlb.h b/include/asm-x86/swiotlb.h
index f5d9e74b1e4a..1e20adbcad4b 100644
--- a/include/asm-x86/swiotlb.h
+++ b/include/asm-x86/swiotlb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SWIOTLB_H
-#define _ASM_SWIOTLB_H 1
+#ifndef ASM_X86__SWIOTLB_H
+#define ASM_X86__SWIOTLB_H
 
 #include <asm/dma-mapping.h>
 
@@ -35,7 +35,7 @@ extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg,
                           int nents, int direction);
 extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
                              int nents, int direction);
-extern int swiotlb_dma_mapping_error(dma_addr_t dma_addr);
+extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
 extern void swiotlb_free_coherent(struct device *hwdev, size_t size,
                                   void *vaddr, dma_addr_t dma_handle);
 extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
@@ -45,12 +45,14 @@ extern int swiotlb_force;
 
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
+extern void pci_swiotlb_init(void);
 #else
 #define swiotlb 0
+static inline void pci_swiotlb_init(void)
+{
+}
 #endif
 
-extern void pci_swiotlb_init(void);
-
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
-#endif /* _ASM_SWIOTLB_H */
+#endif /* ASM_X86__SWIOTLB_H */
diff --git a/include/asm-x86/sync_bitops.h b/include/asm-x86/sync_bitops.h
index b47a1d0b8a83..b689bee71104 100644
--- a/include/asm-x86/sync_bitops.h
+++ b/include/asm-x86/sync_bitops.h
@@ -1,5 +1,5 @@
-#ifndef _I386_SYNC_BITOPS_H
-#define _I386_SYNC_BITOPS_H
+#ifndef ASM_X86__SYNC_BITOPS_H
+#define ASM_X86__SYNC_BITOPS_H
 
 /*
  * Copyright 1992, Linus Torvalds.
@@ -127,4 +127,4 @@ static inline int sync_test_and_change_bit(int nr, volatile unsigned long *addr)
 
 #undef ADDR
 
-#endif /* _I386_SYNC_BITOPS_H */
+#endif /* ASM_X86__SYNC_BITOPS_H */
diff --git a/include/asm-x86/syscall.h b/include/asm-x86/syscall.h
new file mode 100644
index 000000000000..04c47dc5597c
--- /dev/null
+++ b/include/asm-x86/syscall.h
@@ -0,0 +1,211 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * Copyright (C) 2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_SYSCALL_H
+#define _ASM_SYSCALL_H  1
+
+#include <linux/sched.h>
+#include <linux/err.h>
+
+static inline long syscall_get_nr(struct task_struct *task,
+                                  struct pt_regs *regs)
+{
+        /*
+         * We always sign-extend a -1 value being set here,
+         * so this is always either -1L or a syscall number.
+         */
+        return regs->orig_ax;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+                                    struct pt_regs *regs)
+{
+        regs->ax = regs->orig_ax;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+                                     struct pt_regs *regs)
+{
+        unsigned long error = regs->ax;
+#ifdef CONFIG_IA32_EMULATION
+        /*
+         * TS_COMPAT is set for 32-bit syscall entries and then
+         * remains set until we return to user mode.
+         */
+        if (task_thread_info(task)->status & TS_COMPAT)
+                /*
+                 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+                 * and will match correctly in comparisons.
+                 */
+                error = (long) (int) error;
+#endif
+        return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+                                            struct pt_regs *regs)
+{
+        return regs->ax;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+                                            struct pt_regs *regs,
+                                            int error, long val)
+{
+        regs->ax = (long) error ?: val;
+}
+
+#ifdef CONFIG_X86_32
+
+static inline void syscall_get_arguments(struct task_struct *task,
+                                         struct pt_regs *regs,
+                                         unsigned int i, unsigned int n,
+                                         unsigned long *args)
+{
+        BUG_ON(i + n > 6);
+        memcpy(args, &regs->bx + i, n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+                                         struct pt_regs *regs,
+                                         unsigned int i, unsigned int n,
+                                         const unsigned long *args)
+{
+        BUG_ON(i + n > 6);
+        memcpy(&regs->bx + i, args, n * sizeof(args[0]));
+}
+
+#else    /* CONFIG_X86_64 */
+
+static inline void syscall_get_arguments(struct task_struct *task,
+                                         struct pt_regs *regs,
+                                         unsigned int i, unsigned int n,
+                                         unsigned long *args)
+{
+# ifdef CONFIG_IA32_EMULATION
+        if (task_thread_info(task)->status & TS_COMPAT)
+                switch (i + n) {
+                case 6:
+                        if (!n--) break;
+                        *args++ = regs->bp;
+                case 5:
+                        if (!n--) break;
+                        *args++ = regs->di;
+                case 4:
+                        if (!n--) break;
+                        *args++ = regs->si;
+                case 3:
+                        if (!n--) break;
+                        *args++ = regs->dx;
+                case 2:
+                        if (!n--) break;
+                        *args++ = regs->cx;
+                case 1:
+                        if (!n--) break;
+                        *args++ = regs->bx;
+                case 0:
+                        if (!n--) break;
+                default:
+                        BUG();
+                        break;
+                }
+        else
+# endif
+                switch (i + n) {
+                case 6:
+                        if (!n--) break;
+                        *args++ = regs->r9;
+                case 5:
+                        if (!n--) break;
+                        *args++ = regs->r8;
+                case 4:
+                        if (!n--) break;
+                        *args++ = regs->r10;
+                case 3:
+                        if (!n--) break;
+                        *args++ = regs->dx;
+                case 2:
+                        if (!n--) break;
+                        *args++ = regs->si;
+                case 1:
+                        if (!n--) break;
+                        *args++ = regs->di;
+                case 0:
+                        if (!n--) break;
+                default:
+                        BUG();
+                        break;
+                }
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+                                         struct pt_regs *regs,
+                                         unsigned int i, unsigned int n,
+                                         const unsigned long *args)
+{
+# ifdef CONFIG_IA32_EMULATION
+        if (task_thread_info(task)->status & TS_COMPAT)
+                switch (i + n) {
+                case 6:
+                        if (!n--) break;
+                        regs->bp = *args++;
+                case 5:
+                        if (!n--) break;
+                        regs->di = *args++;
+                case 4:
+                        if (!n--) break;
+                        regs->si = *args++;
+                case 3:
+                        if (!n--) break;
+                        regs->dx = *args++;
+                case 2:
+                        if (!n--) break;
+                        regs->cx = *args++;
+                case 1:
+                        if (!n--) break;
+                        regs->bx = *args++;
+                case 0:
+                        if (!n--) break;
+                default:
+                        BUG();
+                }
+        else
+# endif
+                switch (i + n) {
+                case 6:
+                        if (!n--) break;
+                        regs->r9 = *args++;
+                case 5:
+                        if (!n--) break;
+                        regs->r8 = *args++;
+                case 4:
+                        if (!n--) break;
+                        regs->r10 = *args++;
+                case 3:
+                        if (!n--) break;
+                        regs->dx = *args++;
+                case 2:
+                        if (!n--) break;
+                        regs->si = *args++;
+                case 1:
+                        if (!n--) break;
+                        regs->di = *args++;
+                case 0:
+                        if (!n--) break;
+                default:
+                        BUG();
+                }
+}
+
+#endif  /* CONFIG_X86_32 */
+
+#endif  /* _ASM_SYSCALL_H */
diff --git a/include/asm-x86/syscalls.h b/include/asm-x86/syscalls.h
new file mode 100644
index 000000000000..87803da44010
--- /dev/null
+++ b/include/asm-x86/syscalls.h
@@ -0,0 +1,93 @@
+/*
+ * syscalls.h - Linux syscall interfaces (arch-specific)
+ *
+ * Copyright (c) 2008 Jaswinder Singh
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#ifndef _ASM_X86_SYSCALLS_H
+#define _ASM_X86_SYSCALLS_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/signal.h>
+
+/* Common in X86_32 and X86_64 */
+/* kernel/ioport.c */
+asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
+
+/* X86_32 only */
+#ifdef CONFIG_X86_32
+/* kernel/process_32.c */
+asmlinkage int sys_fork(struct pt_regs);
+asmlinkage int sys_clone(struct pt_regs);
+asmlinkage int sys_vfork(struct pt_regs);
+asmlinkage int sys_execve(struct pt_regs);
+
+/* kernel/signal_32.c */
+asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
+asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
+                             struct old_sigaction __user *);
+asmlinkage int sys_sigaltstack(unsigned long);
+asmlinkage unsigned long sys_sigreturn(unsigned long);
+asmlinkage int sys_rt_sigreturn(unsigned long);
+
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned long);
+
+/* kernel/ldt.c */
+asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+
+/* kernel/sys_i386_32.c */
+asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
+                          unsigned long, unsigned long, unsigned long);
+struct mmap_arg_struct;
+asmlinkage int old_mmap(struct mmap_arg_struct __user *);
+struct sel_arg_struct;
+asmlinkage int old_select(struct sel_arg_struct __user *);
+asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
+struct old_utsname;
+asmlinkage int sys_uname(struct old_utsname __user *);
+struct oldold_utsname;
+asmlinkage int sys_olduname(struct oldold_utsname __user *);
+
+/* kernel/tls.c */
+asmlinkage int sys_set_thread_area(struct user_desc __user *);
+asmlinkage int sys_get_thread_area(struct user_desc __user *);
+
+/* kernel/vm86_32.c */
+asmlinkage int sys_vm86old(struct pt_regs);
+asmlinkage int sys_vm86(struct pt_regs);
+
+#else /* CONFIG_X86_32 */
+
+/* X86_64 only */
+/* kernel/process_64.c */
+asmlinkage long sys_fork(struct pt_regs *);
+asmlinkage long sys_clone(unsigned long, unsigned long,
+                          void __user *, void __user *,
+                          struct pt_regs *);
+asmlinkage long sys_vfork(struct pt_regs *);
+asmlinkage long sys_execve(char __user *, char __user * __user *,
+                           char __user * __user *,
+                           struct pt_regs *);
+
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
+
+/* kernel/signal_64.c */
+asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
+                                struct pt_regs *);
+asmlinkage long sys_rt_sigreturn(struct pt_regs *);
+
+/* kernel/sys_x86_64.c */
+asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
+                         unsigned long, unsigned long, unsigned long);
+struct new_utsname;
+asmlinkage long sys_uname(struct new_utsname __user *);
+
+#endif /* CONFIG_X86_32 */
+#endif /* _ASM_X86_SYSCALLS_H */
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
index a2f04cd79b29..34505dd7b24d 100644
--- a/include/asm-x86/system.h
+++ b/include/asm-x86/system.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_SYSTEM_H_
-#define _ASM_X86_SYSTEM_H_
+#ifndef ASM_X86__SYSTEM_H
+#define ASM_X86__SYSTEM_H
 
 #include <asm/asm.h>
 #include <asm/segment.h>
@@ -136,7 +136,7 @@ __asm__ __volatile__ ("movw %%dx,%1\n\t" \
 #define set_base(ldt, base) _set_base(((char *)&(ldt)) , (base))
 #define set_limit(ldt, limit) _set_limit(((char *)&(ldt)) , ((limit)-1))
 
-extern void load_gs_index(unsigned);
+extern void native_load_gs_index(unsigned);
 
 /*
  * Load a segment. Fall back on loading the zero
@@ -153,14 +153,14 @@ extern void load_gs_index(unsigned);
                      "jmp 2b\n"                 \
                      ".previous\n"              \
                      _ASM_EXTABLE(1b,3b)        \
-                     : :"r" (value), "r" (0))
+                     : :"r" (value), "r" (0) : "memory")
 
 
 /*
  * Save a segment register away
  */
 #define savesegment(seg, value)                         \
-        asm volatile("mov %%" #seg ",%0":"=rm" (value))
+        asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
 static inline unsigned long get_limit(unsigned long segment)
 {
@@ -282,6 +282,7 @@ static inline void native_wbinvd(void)
 #ifdef CONFIG_X86_64
 #define read_cr8()      (native_read_cr8())
 #define write_cr8(x)    (native_write_cr8(x))
+#define load_gs_index   native_load_gs_index
 #endif
 
 /* Clear the 'TS' bit */
@@ -289,7 +290,7 @@ static inline void native_wbinvd(void)
 
 #endif/* CONFIG_PARAVIRT */
 
-#define stts() write_cr0(8 | read_cr0())
+#define stts() write_cr0(read_cr0() | X86_CR0_TS)
 
 #endif /* __KERNEL__ */
 
@@ -303,7 +304,6 @@ static inline void clflush(volatile void *__p)
 void disable_hlt(void);
 void enable_hlt(void);
 
-extern int es7000_plat;
 void cpu_idle_wait(void);
 
 extern unsigned long arch_align_stack(unsigned long sp);
@@ -419,4 +419,4 @@ static inline void rdtsc_barrier(void)
         alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
 }
 
-#endif
+#endif /* ASM_X86__SYSTEM_H */
diff --git a/include/asm-x86/system_64.h b/include/asm-x86/system_64.h
index 97fa251ccb2b..5aedb8bffc5a 100644
--- a/include/asm-x86/system_64.h
+++ b/include/asm-x86/system_64.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_SYSTEM_H
-#define __ASM_SYSTEM_H
+#ifndef ASM_X86__SYSTEM_64_H
+#define ASM_X86__SYSTEM_64_H
 
 #include <asm/segment.h>
 #include <asm/cmpxchg.h>
@@ -19,4 +19,4 @@ static inline void write_cr8(unsigned long val)
 
 #include <linux/irqflags.h>
 
-#endif
+#endif /* ASM_X86__SYSTEM_64_H */
diff --git a/include/asm-x86/tce.h b/include/asm-x86/tce.h
index b1a4ea00df78..e7932d7fbbab 100644
--- a/include/asm-x86/tce.h
+++ b/include/asm-x86/tce.h
@@ -21,8 +21,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _ASM_X86_64_TCE_H
-#define _ASM_X86_64_TCE_H
+#ifndef ASM_X86__TCE_H
+#define ASM_X86__TCE_H
 
 extern unsigned int specified_table_size;
 struct iommu_table;
@@ -45,4 +45,4 @@ extern void * __init alloc_tce_table(void);
 extern void __init free_tce_table(void *tbl);
 extern int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar);
 
-#endif /* _ASM_X86_64_TCE_H */
+#endif /* ASM_X86__TCE_H */
diff --git a/include/asm-x86/termbits.h b/include/asm-x86/termbits.h
index af1b70ea440f..3d00dc5e0c71 100644
--- a/include/asm-x86/termbits.h
+++ b/include/asm-x86/termbits.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TERMBITS_H
-#define _ASM_X86_TERMBITS_H
+#ifndef ASM_X86__TERMBITS_H
+#define ASM_X86__TERMBITS_H
 
 #include <linux/posix_types.h>
 
@@ -195,4 +195,4 @@ struct ktermios {
 #define TCSADRAIN       1
 #define TCSAFLUSH       2
 
-#endif /* _ASM_X86_TERMBITS_H */
+#endif /* ASM_X86__TERMBITS_H */
diff --git a/include/asm-x86/termios.h b/include/asm-x86/termios.h
index f72956331c49..e235db248071 100644
--- a/include/asm-x86/termios.h
+++ b/include/asm-x86/termios.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TERMIOS_H
-#define _ASM_X86_TERMIOS_H
+#ifndef ASM_X86__TERMIOS_H
+#define ASM_X86__TERMIOS_H
 
 #include <asm/termbits.h>
 #include <asm/ioctls.h>
@@ -110,4 +110,4 @@ static inline int kernel_termios_to_user_termios_1(struct termios __user *u,
 
 #endif  /* __KERNEL__ */
 
-#endif /* _ASM_X86_TERMIOS_H */
+#endif /* ASM_X86__TERMIOS_H */
diff --git a/include/asm-x86/therm_throt.h b/include/asm-x86/therm_throt.h
index 399bf6026b16..1c7f57b6b66e 100644
--- a/include/asm-x86/therm_throt.h
+++ b/include/asm-x86/therm_throt.h
@@ -1,9 +1,9 @@
-#ifndef __ASM_I386_THERM_THROT_H__
-#define __ASM_I386_THERM_THROT_H__ 1
+#ifndef ASM_X86__THERM_THROT_H
+#define ASM_X86__THERM_THROT_H
 
 #include <asm/atomic.h>
 
 extern atomic_t therm_throt_en;
 int therm_throt_process(int curr);
 
-#endif /* __ASM_I386_THERM_THROT_H__ */
+#endif /* ASM_X86__THERM_THROT_H */
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
index 77244f17993f..3f4e52bb77f5 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -1,14 +1,264 @@
-#ifndef _ASM_X86_THREAD_INFO_H
+/* thread_info.h: low-level thread information
+ *
+ * Copyright (C) 2002  David Howells (dhowells@redhat.com)
+ * - Incorporating suggestions made by Linus Torvalds and Dave Miller
+ */
+
+#ifndef ASM_X86__THREAD_INFO_H
+#define ASM_X86__THREAD_INFO_H
+
+#include <linux/compiler.h>
+#include <asm/page.h>
+#include <asm/types.h>
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - this struct shares the supervisor stack pages
+ */
+#ifndef __ASSEMBLY__
+struct task_struct;
+struct exec_domain;
+#include <asm/processor.h>
+
+struct thread_info {
+        struct task_struct      *task;          /* main task structure */
+        struct exec_domain      *exec_domain;   /* execution domain */
+        unsigned long           flags;          /* low level flags */
+        __u32                   status;         /* thread synchronous flags */
+        __u32                   cpu;            /* current CPU */
+        int                     preempt_count;  /* 0 => preemptable,
+                                                   <0 => BUG */
+        mm_segment_t            addr_limit;
+        struct restart_block    restart_block;
+        void __user             *sysenter_return;
 #ifdef CONFIG_X86_32
-# include "thread_info_32.h"
+        unsigned long           previous_esp;   /* ESP of the previous stack in
+                                                   case of nested (IRQ) stacks
+                                                */
+        __u8                    supervisor_stack[0];
+#endif
+};
+
+#define INIT_THREAD_INFO(tsk)                   \
+{                                               \
+        .task           = &tsk,                 \
+        .exec_domain    = &default_exec_domain, \
+        .flags          = 0,                    \
+        .cpu            = 0,                    \
+        .preempt_count  = 1,                    \
+        .addr_limit     = KERNEL_DS,            \
+        .restart_block = {                      \
+                .fn = do_no_restart_syscall,    \
+        },                                      \
+}
+
+#define init_thread_info        (init_thread_union.thread_info)
+#define init_stack              (init_thread_union.stack)
+
+#else /* !__ASSEMBLY__ */
+
+#include <asm/asm-offsets.h>
+
+#endif
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files
+ *   may need to access
+ * - pending work-to-be-done flags are in LSW
+ * - other flags in MSW
+ * Warning: layout of LSW is hardcoded in entry.S
+ */
+#define TIF_SYSCALL_TRACE       0       /* syscall trace active */
+#define TIF_NOTIFY_RESUME       1       /* callback before returning to user */
+#define TIF_SIGPENDING          2       /* signal pending */
+#define TIF_NEED_RESCHED        3       /* rescheduling necessary */
+#define TIF_SINGLESTEP          4       /* reenable singlestep on user return*/
+#define TIF_IRET                5       /* force IRET */
+#define TIF_SYSCALL_EMU         6       /* syscall emulation active */
+#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_NOTSC               16      /* TSC is not accessible in userland */
+#define TIF_IA32                17      /* 32bit process */
+#define TIF_FORK                18      /* ret_from_fork */
+#define TIF_ABI_PENDING         19
+#define TIF_MEMDIE              20
+#define TIF_DEBUG               21      /* uses debug registers */
+#define TIF_IO_BITMAP           22      /* uses I/O bitmap */
+#define TIF_FREEZE              23      /* is freezing for suspend */
+#define TIF_FORCED_TF           24      /* true if TF in eflags artificially */
+#define TIF_DEBUGCTLMSR         25      /* uses thread_struct.debugctlmsr */
+#define TIF_DS_AREA_MSR         26      /* uses thread_struct.ds_area_msr */
+#define TIF_BTS_TRACE_TS        27      /* record scheduling event timestamps */
+
+#define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME      (1 << TIF_NOTIFY_RESUME)
+#define _TIF_SIGPENDING         (1 << TIF_SIGPENDING)
+#define _TIF_SINGLESTEP         (1 << TIF_SINGLESTEP)
+#define _TIF_NEED_RESCHED       (1 << TIF_NEED_RESCHED)
+#define _TIF_IRET               (1 << TIF_IRET)
+#define _TIF_SYSCALL_EMU        (1 << TIF_SYSCALL_EMU)
+#define _TIF_SYSCALL_AUDIT      (1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP            (1 << TIF_SECCOMP)
+#define _TIF_MCE_NOTIFY         (1 << TIF_MCE_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)
+#define _TIF_FORCED_TF          (1 << TIF_FORCED_TF)
+#define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
+#define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
+#define _TIF_BTS_TRACE_TS       (1 << TIF_BTS_TRACE_TS)
+
+/* work to do in syscall_trace_enter() */
+#define _TIF_WORK_SYSCALL_ENTRY \
+        (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \
+         _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
+
+/* work to do in syscall_trace_leave() */
+#define _TIF_WORK_SYSCALL_EXIT  \
+        (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK                                                  \
+        (0x0000FFFF &                                                   \
+         ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|                       \
+           _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
+
+/* work to do on any return to user space */
+#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
+
+/* Only used for 64 bit */
+#define _TIF_DO_NOTIFY_MASK                                             \
+        (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
+
+/* flags to check in __switch_to() */
+#define _TIF_WORK_CTXSW                                                 \
+        (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS| \
+                                                                _TIF_NOTSC)
+
+#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
+#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
+
+#define PREEMPT_ACTIVE          0x10000000
+
+/* thread information allocation */
+#ifdef CONFIG_DEBUG_STACK_USAGE
+#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
 #else
-# include "thread_info_64.h"
+#define THREAD_FLAGS GFP_KERNEL
 #endif
 
+#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
+
+#define alloc_thread_info(tsk)                                          \
+        ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
+
+#ifdef CONFIG_X86_32
+
+#define STACK_WARN      (THREAD_SIZE/8)
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#ifndef __ASSEMBLY__
+
+
+/* how to get the current stack pointer from C */
+register unsigned long current_stack_pointer asm("esp") __used;
+
+/* how to get the thread information struct from C */
+static inline struct thread_info *current_thread_info(void)
+{
+        return (struct thread_info *)
+                (current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
+#else /* !__ASSEMBLY__ */
+
+/* how to get the thread information struct from ASM */
+#define GET_THREAD_INFO(reg)     \
+        movl $-THREAD_SIZE, reg; \
+        andl %esp, reg
+
+/* use this one if reg already contains %esp */
+#define GET_THREAD_INFO_WITH_ESP(reg) \
+        andl $-THREAD_SIZE, reg
+
+#endif
+
+#else /* X86_32 */
+
+#include <asm/pda.h>
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#ifndef __ASSEMBLY__
+static inline struct thread_info *current_thread_info(void)
+{
+        struct thread_info *ti;
+        ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
+        return ti;
+}
+
+/* do not use in interrupt context */
+static inline struct thread_info *stack_thread_info(void)
+{
+        struct thread_info *ti;
+        asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
+        return ti;
+}
+
+#else /* !__ASSEMBLY__ */
+
+/* how to get the thread information struct from ASM */
+#define GET_THREAD_INFO(reg) \
+        movq %gs:pda_kernelstack,reg ; \
+        subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
+
+#endif
+
+#endif /* !X86_32 */
+
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_USEDFPU              0x0001  /* FPU was used by this task
+                                           this quantum (SMP) */
+#define TS_COMPAT               0x0002  /* 32bit syscall active (64BIT)*/
+#define TS_POLLING              0x0004  /* true if in idle loop
+                                           and not sleeping */
+#define TS_RESTORE_SIGMASK      0x0008  /* restore signal mask in do_signal() */
+#define TS_XSAVE                0x0010  /* Use xsave/xrstor */
+
+#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
+
+#ifndef __ASSEMBLY__
+#define HAVE_SET_RESTORE_SIGMASK        1
+static inline void set_restore_sigmask(void)
+{
+        struct thread_info *ti = current_thread_info();
+        ti->status |= TS_RESTORE_SIGMASK;
+        set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
+}
+#endif  /* !__ASSEMBLY__ */
+
 #ifndef __ASSEMBLY__
 extern void arch_task_cache_init(void);
 extern void free_thread_info(struct thread_info *ti);
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define arch_task_cache_init arch_task_cache_init
 #endif
-#endif /* _ASM_X86_THREAD_INFO_H */
+#endif /* ASM_X86__THREAD_INFO_H */
diff --git a/include/asm-x86/thread_info_32.h b/include/asm-x86/thread_info_32.h
deleted file mode 100644
index b6338829d1a8..000000000000
--- a/include/asm-x86/thread_info_32.h
+++ /dev/null
@@ -1,205 +0,0 @@
-/* thread_info.h: i386 low-level thread information
- *
- * Copyright (C) 2002  David Howells (dhowells@redhat.com)
- * - Incorporating suggestions made by Linus Torvalds and Dave Miller
- */
-
-#ifndef _ASM_THREAD_INFO_H
-#define _ASM_THREAD_INFO_H
-
-#ifdef __KERNEL__
-
-#include <linux/compiler.h>
-#include <asm/page.h>
-
-#ifndef __ASSEMBLY__
-#include <asm/processor.h>
-#endif
-
-/*
- * low level task data that entry.S needs immediate access to
- * - this struct should fit entirely inside of one cache line
- * - this struct shares the supervisor stack pages
- * - if the contents of this structure are changed,
- *   the assembly constants must also be changed
- */
-#ifndef __ASSEMBLY__
-
-struct thread_info {
-        struct task_struct      *task;          /* main task structure */
-        struct exec_domain      *exec_domain;   /* execution domain */
-        unsigned long           flags;          /* low level flags */
-        unsigned long           status;         /* thread-synchronous flags */
-        __u32                   cpu;            /* current CPU */
-        int                     preempt_count;  /* 0 => preemptable,
-                                                   <0 => BUG */
-        mm_segment_t            addr_limit;     /* thread address space:
-                                                   0-0xBFFFFFFF user-thread
-                                                   0-0xFFFFFFFF kernel-thread
-                                                */
-        void                    *sysenter_return;
-        struct restart_block    restart_block;
-        unsigned long           previous_esp;   /* ESP of the previous stack in
-                                                   case of nested (IRQ) stacks
-                                                */
-        __u8                    supervisor_stack[0];
-};
-
-#else /* !__ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-
-#endif
-
-#define PREEMPT_ACTIVE          0x10000000
-#ifdef CONFIG_4KSTACKS
-#define THREAD_SIZE            (4096)
-#else
-#define THREAD_SIZE             (8192)
-#endif
-
-#define STACK_WARN             (THREAD_SIZE/8)
-/*
- * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
-
-#define INIT_THREAD_INFO(tsk)                   \
-{                                               \
-        .task           = &tsk,                 \
-        .exec_domain    = &default_exec_domain, \
-        .flags          = 0,                    \
-        .cpu            = 0,                    \
-        .preempt_count  = 1,                    \
-        .addr_limit     = KERNEL_DS,            \
-        .restart_block = {                      \
-                .fn = do_no_restart_syscall,    \
-        },                                      \
-}
-
-#define init_thread_info        (init_thread_union.thread_info)
-#define init_stack              (init_thread_union.stack)
-
-
-/* how to get the current stack pointer from C */
-register unsigned long current_stack_pointer asm("esp") __used;
-
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-        return (struct thread_info *)
-                (current_stack_pointer & ~(THREAD_SIZE - 1));
-}
-
-/* thread information allocation */
-#ifdef CONFIG_DEBUG_STACK_USAGE
-#define alloc_thread_info(tsk) ((struct thread_info *)                  \
-        __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(THREAD_SIZE)))
-#else
-#define alloc_thread_info(tsk) ((struct thread_info *)                  \
-        __get_free_pages(GFP_KERNEL, get_order(THREAD_SIZE)))
-#endif
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg)     \
-        movl $-THREAD_SIZE, reg; \
-        andl %esp, reg
-
-/* use this one if reg already contains %esp */
-#define GET_THREAD_INFO_WITH_ESP(reg) \
-        andl $-THREAD_SIZE, reg
-
-#endif
-
-/*
- * thread information flags
- * - these are process state flags that various
- *   assembly files may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- */
-#define TIF_SYSCALL_TRACE       0       /* syscall trace active */
-#define TIF_SIGPENDING          1       /* signal pending */
-#define TIF_NEED_RESCHED        2       /* rescheduling necessary */
-#define TIF_SINGLESTEP          3       /* restore singlestep on return to
-                                           user mode */
-#define TIF_IRET                4       /* return with iret */
-#define TIF_SYSCALL_EMU         5       /* syscall emulation active */
-#define TIF_SYSCALL_AUDIT       6       /* syscall auditing active */
-#define TIF_SECCOMP             7       /* secure computing */
-#define TIF_HRTICK_RESCHED      9       /* reprogram hrtick timer */
-#define TIF_MEMDIE              16
-#define TIF_DEBUG               17      /* uses debug registers */
-#define TIF_IO_BITMAP           18      /* uses I/O bitmap */
-#define TIF_FREEZE              19      /* is freezing for suspend */
-#define TIF_NOTSC               20      /* TSC is not accessible in userland */
-#define TIF_FORCED_TF           21      /* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR         22      /* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR         23      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS        24      /* record scheduling event timestamps */
-
-#define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING         (1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED       (1 << TIF_NEED_RESCHED)
-#define _TIF_SINGLESTEP         (1 << TIF_SINGLESTEP)
-#define _TIF_IRET               (1 << TIF_IRET)
-#define _TIF_SYSCALL_EMU        (1 << TIF_SYSCALL_EMU)
-#define _TIF_SYSCALL_AUDIT      (1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP            (1 << TIF_SECCOMP)
-#define _TIF_HRTICK_RESCHED     (1 << TIF_HRTICK_RESCHED)
-#define _TIF_DEBUG              (1 << TIF_DEBUG)
-#define _TIF_IO_BITMAP          (1 << TIF_IO_BITMAP)
-#define _TIF_FREEZE             (1 << TIF_FREEZE)
-#define _TIF_NOTSC              (1 << TIF_NOTSC)
-#define _TIF_FORCED_TF          (1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
-#define _TIF_BTS_TRACE_TS       (1 << TIF_BTS_TRACE_TS)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK                                                  \
-        (0x0000FFFF & ~(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |       \
-                        _TIF_SECCOMP | _TIF_SYSCALL_EMU))
-/* work to do on any return to u-space */
-#define _TIF_ALLWORK_MASK       (0x0000FFFF & ~_TIF_SECCOMP)
-
-/* flags to check in __switch_to() */
-#define _TIF_WORK_CTXSW                                         \
-        (_TIF_IO_BITMAP | _TIF_NOTSC | _TIF_DEBUGCTLMSR |       \
-         _TIF_DS_AREA_MSR | _TIF_BTS_TRACE_TS)
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
-#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW | _TIF_DEBUG)
-
-
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_USEDFPU              0x0001  /* FPU was used by this task
-                                           this quantum (SMP) */
-#define TS_POLLING              0x0002  /* True if in idle loop
-                                           and not sleeping */
-#define TS_RESTORE_SIGMASK      0x0004  /* restore signal mask in do_signal() */
-
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK        1
-static inline void set_restore_sigmask(void)
-{
-        struct thread_info *ti = current_thread_info();
-        ti->status |= TS_RESTORE_SIGMASK;
-        set_bit(TIF_SIGPENDING, &ti->flags);
-}
-#endif  /* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_THREAD_INFO_H */
diff --git a/include/asm-x86/thread_info_64.h b/include/asm-x86/thread_info_64.h
deleted file mode 100644
index cb69f70abba1..000000000000
--- a/include/asm-x86/thread_info_64.h
+++ /dev/null
@@ -1,195 +0,0 @@
-/* thread_info.h: x86_64 low-level thread information
- *
- * Copyright (C) 2002  David Howells (dhowells@redhat.com)
- * - Incorporating suggestions made by Linus Torvalds and Dave Miller
- */
-
-#ifndef _ASM_THREAD_INFO_H
-#define _ASM_THREAD_INFO_H
-
-#ifdef __KERNEL__
-
-#include <asm/page.h>
-#include <asm/types.h>
-#include <asm/pda.h>
-
-/*
- * low level task data that entry.S needs immediate access to
- * - this struct should fit entirely inside of one cache line
- * - this struct shares the supervisor stack pages
- */
-#ifndef __ASSEMBLY__
-struct task_struct;
-struct exec_domain;
-#include <asm/processor.h>
-
-struct thread_info {
-        struct task_struct      *task;          /* main task structure */
-        struct exec_domain      *exec_domain;   /* execution domain */
-        __u32                   flags;          /* low level flags */
-        __u32                   status;         /* thread synchronous flags */
-        __u32                   cpu;            /* current CPU */
-        int                     preempt_count;  /* 0 => preemptable,
-                                                   <0 => BUG */
-        mm_segment_t            addr_limit;
-        struct restart_block    restart_block;
-#ifdef CONFIG_IA32_EMULATION
-        void __user             *sysenter_return;
-#endif
-};
-#endif
-
-/*
- * macros/functions for gaining access to the thread information structure
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
-#define INIT_THREAD_INFO(tsk)                   \
-{                                               \
-        .task          = &tsk,                  \
-        .exec_domain   = &default_exec_domain,  \
-        .flags         = 0,                     \
-        .cpu           = 0,                     \
-        .preempt_count = 1,                     \
-        .addr_limit     = KERNEL_DS,            \
-        .restart_block = {                      \
-                .fn = do_no_restart_syscall,    \
-        },                                      \
-}
-
-#define init_thread_info        (init_thread_union.thread_info)
-#define init_stack              (init_thread_union.stack)
-
-static inline struct thread_info *current_thread_info(void)
-{
-        struct thread_info *ti;
-        ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
-        return ti;
-}
-
-/* do not use in interrupt context */
-static inline struct thread_info *stack_thread_info(void)
-{
-        struct thread_info *ti;
-        asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
-        return ti;
-}
-
-/* thread information allocation */
-#ifdef CONFIG_DEBUG_STACK_USAGE
-#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
-#else
-#define THREAD_FLAGS GFP_KERNEL
-#endif
-
-#define alloc_thread_info(tsk)                                          \
-        ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg) \
-        movq %gs:pda_kernelstack,reg ; \
-        subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
-
-#endif
-
-/*
- * thread information flags
- * - these are process state flags that various assembly files
- *   may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- * Warning: layout of LSW is hardcoded in entry.S
- */
-#define TIF_SYSCALL_TRACE       0       /* syscall trace active */
-#define TIF_SIGPENDING          2       /* signal pending */
-#define TIF_NEED_RESCHED        3       /* rescheduling necessary */
-#define TIF_SINGLESTEP          4       /* reenable singlestep on user return*/
-#define TIF_IRET                5       /* force IRET */
-#define TIF_SYSCALL_AUDIT       7       /* syscall auditing active */
-#define TIF_SECCOMP             8       /* secure computing */
-#define TIF_MCE_NOTIFY          10      /* notify userspace of an MCE */
-#define TIF_HRTICK_RESCHED      11      /* reprogram hrtick timer */
-/* 16 free */
-#define TIF_IA32                17      /* 32bit process */
-#define TIF_FORK                18      /* ret_from_fork */
-#define TIF_ABI_PENDING         19
-#define TIF_MEMDIE              20
-#define TIF_DEBUG               21      /* uses debug registers */
-#define TIF_IO_BITMAP           22      /* uses I/O bitmap */
-#define TIF_FREEZE              23      /* is freezing for suspend */
-#define TIF_FORCED_TF           24      /* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR         25      /* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR         26      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS        27      /* record scheduling event timestamps */
-#define TIF_NOTSC               28      /* TSC is not accessible in userland */
-
-#define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING         (1 << TIF_SIGPENDING)
-#define _TIF_SINGLESTEP         (1 << TIF_SINGLESTEP)
-#define _TIF_NEED_RESCHED       (1 << TIF_NEED_RESCHED)
-#define _TIF_IRET               (1 << TIF_IRET)
-#define _TIF_SYSCALL_AUDIT      (1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP            (1 << TIF_SECCOMP)
-#define _TIF_MCE_NOTIFY         (1 << TIF_MCE_NOTIFY)
-#define _TIF_HRTICK_RESCHED     (1 << TIF_HRTICK_RESCHED)
-#define _TIF_IA32               (1 << TIF_IA32)
-#define _TIF_FORK               (1 << TIF_FORK)
-#define _TIF_ABI_PENDING        (1 << TIF_ABI_PENDING)
-#define _TIF_DEBUG              (1 << TIF_DEBUG)
-#define _TIF_IO_BITMAP          (1 << TIF_IO_BITMAP)
-#define _TIF_FREEZE             (1 << TIF_FREEZE)
-#define _TIF_FORCED_TF          (1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
-#define _TIF_BTS_TRACE_TS       (1 << TIF_BTS_TRACE_TS)
-#define _TIF_NOTSC              (1 << TIF_NOTSC)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK                                                  \
-        (0x0000FFFF &                                                   \
-         ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|_TIF_SECCOMP))
-/* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
-
-#define _TIF_DO_NOTIFY_MASK                                             \
-        (_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
-
-/* flags to check in __switch_to() */
-#define _TIF_WORK_CTXSW                                                 \
-        (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS|_TIF_NOTSC)
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
-#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
-
-#define PREEMPT_ACTIVE     0x10000000
-
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_USEDFPU              0x0001  /* FPU was used by this task
-                                           this quantum (SMP) */
-#define TS_COMPAT               0x0002  /* 32bit syscall active */
-#define TS_POLLING              0x0004  /* true if in idle loop
-                                           and not sleeping */
-#define TS_RESTORE_SIGMASK      0x0008  /* restore signal mask in do_signal() */
-
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK        1
-static inline void set_restore_sigmask(void)
-{
-        struct thread_info *ti = current_thread_info();
-        ti->status |= TS_RESTORE_SIGMASK;
-        set_bit(TIF_SIGPENDING, &ti->flags);
-}
-#endif  /* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_THREAD_INFO_H */
diff --git a/include/asm-x86/time.h b/include/asm-x86/time.h
index bce72d7a958c..3e724eef7ac4 100644
--- a/include/asm-x86/time.h
+++ b/include/asm-x86/time.h
@@ -1,5 +1,5 @@
-#ifndef _ASMX86_TIME_H
-#define _ASMX86_TIME_H
+#ifndef ASM_X86__TIME_H
+#define ASM_X86__TIME_H
 
 extern void hpet_time_init(void);
 
@@ -46,6 +46,8 @@ static inline int native_set_wallclock(unsigned long nowtime)
 
 #endif
 
+extern void time_init(void);
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else /* !CONFIG_PARAVIRT */
@@ -56,4 +58,6 @@ static inline int native_set_wallclock(unsigned long nowtime)
 
 #endif /* CONFIG_PARAVIRT */
 
-#endif
+extern unsigned long __init calibrate_cpu(void);
+
+#endif /* ASM_X86__TIME_H */
diff --git a/include/asm-x86/timer.h b/include/asm-x86/timer.h
index 4f6fcb050c11..d0babce4b47a 100644
--- a/include/asm-x86/timer.h
+++ b/include/asm-x86/timer.h
@@ -1,5 +1,5 @@
-#ifndef _ASMi386_TIMER_H
-#define _ASMi386_TIMER_H
+#ifndef ASM_X86__TIMER_H
+#define ASM_X86__TIMER_H
 #include <linux/init.h>
 #include <linux/pm.h>
 #include <linux/percpu.h>
@@ -7,14 +7,17 @@
 #define TICK_SIZE (tick_nsec / 1000)
 
 unsigned long long native_sched_clock(void);
-unsigned long native_calculate_cpu_khz(void);
+unsigned long native_calibrate_tsc(void);
 
+#ifdef CONFIG_X86_32
 extern int timer_ack;
-extern int no_timer_check;
 extern int recalibrate_cpu_khz(void);
+#endif /* CONFIG_X86_32 */
+
+extern int no_timer_check;
 
 #ifndef CONFIG_PARAVIRT
-#define calculate_cpu_khz() native_calculate_cpu_khz()
+#define calibrate_tsc() native_calibrate_tsc()
 #endif
 
 /* Accelerators for sched_clock()
@@ -60,4 +63,4 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
         return ns;
 }
 
-#endif
+#endif /* ASM_X86__TIMER_H */
diff --git a/include/asm-x86/timex.h b/include/asm-x86/timex.h
index 43e5a78500c5..d1ce2416a5da 100644
--- a/include/asm-x86/timex.h
+++ b/include/asm-x86/timex.h
@@ -1,6 +1,6 @@
 /* x86 architecture timex specifications */
-#ifndef _ASM_X86_TIMEX_H
-#define _ASM_X86_TIMEX_H
+#ifndef ASM_X86__TIMEX_H
+#define ASM_X86__TIMEX_H
 
 #include <asm/processor.h>
 #include <asm/tsc.h>
@@ -16,4 +16,4 @@
 
 #define ARCH_HAS_READ_CURRENT_TIMER
 
-#endif
+#endif /* ASM_X86__TIMEX_H */
diff --git a/include/asm-x86/tlb.h b/include/asm-x86/tlb.h
index e4e9e2d07a93..db36e9e89e87 100644
--- a/include/asm-x86/tlb.h
+++ b/include/asm-x86/tlb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TLB_H
-#define _ASM_X86_TLB_H
+#ifndef ASM_X86__TLB_H
+#define ASM_X86__TLB_H
 
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma) do { } while (0)
@@ -8,4 +8,4 @@
 
 #include <asm-generic/tlb.h>
 
-#endif
+#endif /* ASM_X86__TLB_H */
diff --git a/include/asm-x86/tlbflush.h b/include/asm-x86/tlbflush.h
index 35c76ceb9f40..3cdd08b5bdb7 100644
--- a/include/asm-x86/tlbflush.h
+++ b/include/asm-x86/tlbflush.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TLBFLUSH_H
-#define _ASM_X86_TLBFLUSH_H
+#ifndef ASM_X86__TLBFLUSH_H
+#define ASM_X86__TLBFLUSH_H
 
 #include <linux/mm.h>
 #include <linux/sched.h>
@@ -119,6 +119,10 @@ static inline void native_flush_tlb_others(const cpumask_t *cpumask,
 {
 }
 
+static inline void reset_lazy_tlbstate(void)
+{
+}
+
 #else  /* SMP */
 
 #include <asm/smp.h>
@@ -151,6 +155,12 @@ struct tlb_state {
         char __cacheline_padding[L1_CACHE_BYTES-8];
 };
 DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
+
+void reset_lazy_tlbstate(void);
+#else
+static inline void reset_lazy_tlbstate(void)
+{
+}
 #endif
 
 #endif  /* SMP */
@@ -165,4 +175,4 @@ static inline void flush_tlb_kernel_range(unsigned long start,
         flush_tlb_all();
 }
 
-#endif /* _ASM_X86_TLBFLUSH_H */
+#endif /* ASM_X86__TLBFLUSH_H */
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index dcf3f8131d6b..7eca9bc022b2 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -22,8 +22,8 @@
  *
  * Send feedback to <colpatch@us.ibm.com>
  */
-#ifndef _ASM_X86_TOPOLOGY_H
-#define _ASM_X86_TOPOLOGY_H
+#ifndef ASM_X86__TOPOLOGY_H
+#define ASM_X86__TOPOLOGY_H
 
 #ifdef CONFIG_X86_32
 # ifdef CONFIG_X86_HT
@@ -35,79 +35,93 @@
 # endif
 #endif
 
+/* Node not present */
+#define NUMA_NO_NODE    (-1)
+
 #ifdef CONFIG_NUMA
 #include <linux/cpumask.h>
 #include <asm/mpspec.h>
 
-/* Mappings between logical cpu number and node number */
 #ifdef CONFIG_X86_32
-extern int cpu_to_node_map[];
-#else
-/* Returns the number of the current Node. */
-#define numa_node_id()          (early_cpu_to_node(raw_smp_processor_id()))
-#endif
-
-DECLARE_PER_CPU(int, x86_cpu_to_node_map);
-
-#ifdef CONFIG_SMP
-extern int x86_cpu_to_node_map_init[];
-extern void *x86_cpu_to_node_map_early_ptr;
-#else
-#define x86_cpu_to_node_map_early_ptr NULL
-#endif
 
+/* Mappings between node number and cpus on that node. */
 extern cpumask_t node_to_cpumask_map[];
 
-#define NUMA_NO_NODE    (-1)
+/* Mappings between logical cpu number and node number */
+extern int cpu_to_node_map[];
 
 /* Returns the number of the node containing CPU 'cpu' */
-#ifdef CONFIG_X86_32
-#define early_cpu_to_node(cpu)  cpu_to_node(cpu)
 static inline int cpu_to_node(int cpu)
 {
         return cpu_to_node_map[cpu];
 }
+#define early_cpu_to_node(cpu)  cpu_to_node(cpu)
 
-#else /* CONFIG_X86_64 */
-
-#ifdef CONFIG_SMP
-static inline int early_cpu_to_node(int cpu)
+/* Returns a bitmask of CPUs on Node 'node'.
+ *
+ * Side note: this function creates the returned cpumask on the stack
+ * so with a high NR_CPUS count, excessive stack space is used.  The
+ * node_to_cpumask_ptr function should be used whenever possible.
+ */
+static inline cpumask_t node_to_cpumask(int node)
 {
-        int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
-
-        if (cpu_to_node_map)
-                return cpu_to_node_map[cpu];
-        else if (per_cpu_offset(cpu))
-                return per_cpu(x86_cpu_to_node_map, cpu);
-        else
-                return NUMA_NO_NODE;
+        return node_to_cpumask_map[node];
 }
-#else
-#define early_cpu_to_node(cpu)  cpu_to_node(cpu)
-#endif
 
+#else /* CONFIG_X86_64 */
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_t *node_to_cpumask_map;
+
+/* Mappings between logical cpu number and node number */
+DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
+
+/* Returns the number of the current Node. */
+#define numa_node_id()          read_pda(nodenumber)
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern int cpu_to_node(int cpu);
+extern int early_cpu_to_node(int cpu);
+extern const cpumask_t *_node_to_cpumask_ptr(int node);
+extern cpumask_t node_to_cpumask(int node);
+
+#else   /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Returns the number of the node containing CPU 'cpu' */
 static inline int cpu_to_node(int cpu)
 {
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-        if (x86_cpu_to_node_map_early_ptr) {
-                printk("KERN_NOTICE cpu_to_node(%d): usage too early!\n",
-                       (int)cpu);
-                dump_stack();
-                return ((int *)x86_cpu_to_node_map_early_ptr)[cpu];
-        }
-#endif
         return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-#ifdef  CONFIG_NUMA
+/* Same function but used if called before per_cpu areas are setup */
+static inline int early_cpu_to_node(int cpu)
+{
+        if (early_per_cpu_ptr(x86_cpu_to_node_map))
+                return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+        return per_cpu(x86_cpu_to_node_map, cpu);
+}
 
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+{
+        return &node_to_cpumask_map[node];
+}
+
+/* Returns a bitmask of CPUs on Node 'node'. */
+static inline cpumask_t node_to_cpumask(int node)
+{
+        return node_to_cpumask_map[node];
+}
+
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Replace default node_to_cpumask_ptr with optimized version */
 #define node_to_cpumask_ptr(v, node)            \
-                cpumask_t *v = &(node_to_cpumask_map[node])
+                const cpumask_t *v = _node_to_cpumask_ptr(node)
 
 #define node_to_cpumask_ptr_next(v, node)       \
-                           v = &(node_to_cpumask_map[node])
-#endif
+                           v = _node_to_cpumask_ptr(node)
 
 #endif /* CONFIG_X86_64 */
 
@@ -117,20 +131,6 @@ static inline int cpu_to_node(int cpu)
  */
 #define parent_node(node) (node)
 
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline cpumask_t node_to_cpumask(int node)
-{
-        return node_to_cpumask_map[node];
-}
-
-/* Returns the number of the first CPU on Node 'node'. */
-static inline int node_to_first_cpu(int node)
-{
-        cpumask_t mask = node_to_cpumask(node);
-
-        return first_cpu(mask);
-}
-
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 #define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
 
@@ -180,12 +180,44 @@ extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 #endif
 
-#else /* CONFIG_NUMA */
+#else /* !CONFIG_NUMA */
 
+#define numa_node_id()          0
+#define cpu_to_node(cpu)        0
+#define early_cpu_to_node(cpu)  0
+
+static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+{
+        return &cpu_online_map;
+}
+static inline cpumask_t node_to_cpumask(int node)
+{
+        return cpu_online_map;
+}
+static inline int node_to_first_cpu(int node)
+{
+        return first_cpu(cpu_online_map);
+}
+
+/* Replace default node_to_cpumask_ptr with optimized version */
+#define node_to_cpumask_ptr(v, node)            \
+                const cpumask_t *v = _node_to_cpumask_ptr(node)
+
+#define node_to_cpumask_ptr_next(v, node)       \
+                           v = _node_to_cpumask_ptr(node)
 #endif
 
 #include <asm-generic/topology.h>
 
+#ifdef CONFIG_NUMA
+/* Returns the number of the first CPU on Node 'node'. */
+static inline int node_to_first_cpu(int node)
+{
+        node_to_cpumask_ptr(mask, node);
+        return first_cpu(*mask);
+}
+#endif
+
 extern cpumask_t cpu_coregroup_map(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
@@ -193,6 +225,9 @@ extern cpumask_t cpu_coregroup_map(int cpu);
 #define topology_core_id(cpu)                   (cpu_data(cpu).cpu_core_id)
 #define topology_core_siblings(cpu)             (per_cpu(cpu_core_map, cpu))
 #define topology_thread_siblings(cpu)           (per_cpu(cpu_sibling_map, cpu))
+
+/* indicates that pointers to the topology cpumask_t maps are valid */
+#define arch_provides_topology_pointers         yes
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
@@ -220,4 +255,4 @@ static inline void set_mp_bus_to_node(int busnum, int node)
 }
 #endif
 
-#endif
+#endif /* ASM_X86__TOPOLOGY_H */
diff --git a/include/asm-x86/trampoline.h b/include/asm-x86/trampoline.h
index b156b08d0131..0406bbd898a9 100644
--- a/include/asm-x86/trampoline.h
+++ b/include/asm-x86/trampoline.h
@@ -1,5 +1,5 @@
-#ifndef __TRAMPOLINE_HEADER
-#define __TRAMPOLINE_HEADER
+#ifndef ASM_X86__TRAMPOLINE_H
+#define ASM_X86__TRAMPOLINE_H
 
 #ifndef __ASSEMBLY__
 
@@ -18,4 +18,4 @@ extern unsigned long setup_trampoline(void);
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* __TRAMPOLINE_HEADER */
+#endif /* ASM_X86__TRAMPOLINE_H */
diff --git a/include/asm-x86/traps.h b/include/asm-x86/traps.h
new file mode 100644
index 000000000000..7a692baa51ae
--- /dev/null
+++ b/include/asm-x86/traps.h
@@ -0,0 +1,82 @@
+#ifndef ASM_X86__TRAPS_H
+#define ASM_X86__TRAPS_H
+
+#include <asm/debugreg.h>
+
+/* Common in X86_32 and X86_64 */
+asmlinkage void divide_error(void);
+asmlinkage void debug(void);
+asmlinkage void nmi(void);
+asmlinkage void int3(void);
+asmlinkage void overflow(void);
+asmlinkage void bounds(void);
+asmlinkage void invalid_op(void);
+asmlinkage void device_not_available(void);
+asmlinkage void coprocessor_segment_overrun(void);
+asmlinkage void invalid_TSS(void);
+asmlinkage void segment_not_present(void);
+asmlinkage void stack_segment(void);
+asmlinkage void general_protection(void);
+asmlinkage void page_fault(void);
+asmlinkage void coprocessor_error(void);
+asmlinkage void simd_coprocessor_error(void);
+asmlinkage void alignment_check(void);
+asmlinkage void spurious_interrupt_bug(void);
+#ifdef CONFIG_X86_MCE
+asmlinkage void machine_check(void);
+#endif /* CONFIG_X86_MCE */
+
+void do_divide_error(struct pt_regs *, long);
+void do_overflow(struct pt_regs *, long);
+void do_bounds(struct pt_regs *, long);
+void do_coprocessor_segment_overrun(struct pt_regs *, long);
+void do_invalid_TSS(struct pt_regs *, long);
+void do_segment_not_present(struct pt_regs *, long);
+void do_stack_segment(struct pt_regs *, long);
+void do_alignment_check(struct pt_regs *, long);
+void do_invalid_op(struct pt_regs *, long);
+void do_general_protection(struct pt_regs *, long);
+void do_nmi(struct pt_regs *, long);
+
+static inline int get_si_code(unsigned long condition)
+{
+        if (condition & DR_STEP)
+                return TRAP_TRACE;
+        else if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3))
+                return TRAP_HWBKPT;
+        else
+                return TRAP_BRKPT;
+}
+
+extern int panic_on_unrecovered_nmi;
+extern int kstack_depth_to_print;
+
+#ifdef CONFIG_X86_32
+
+void do_iret_error(struct pt_regs *, long);
+void do_int3(struct pt_regs *, long);
+void do_debug(struct pt_regs *, long);
+void math_error(void __user *);
+void do_coprocessor_error(struct pt_regs *, long);
+void do_simd_coprocessor_error(struct pt_regs *, long);
+void do_spurious_interrupt_bug(struct pt_regs *, long);
+unsigned long patch_espfix_desc(unsigned long, unsigned long);
+asmlinkage void math_emulate(long);
+
+void do_page_fault(struct pt_regs *regs, unsigned long error_code);
+
+#else /* CONFIG_X86_32 */
+
+asmlinkage void double_fault(void);
+
+asmlinkage void do_int3(struct pt_regs *, long);
+asmlinkage void do_stack_segment(struct pt_regs *, long);
+asmlinkage void do_debug(struct pt_regs *, unsigned long);
+asmlinkage void do_coprocessor_error(struct pt_regs *);
+asmlinkage void do_simd_coprocessor_error(struct pt_regs *);
+asmlinkage void do_spurious_interrupt_bug(struct pt_regs *);
+
+asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code);
+
+#endif /* CONFIG_X86_32 */
+#endif /* ASM_X86__TRAPS_H */
diff --git a/include/asm-x86/tsc.h b/include/asm-x86/tsc.h
index 548873ab5fc1..ad0f5c41e78c 100644
--- a/include/asm-x86/tsc.h
+++ b/include/asm-x86/tsc.h
@@ -1,8 +1,8 @@
 /*
  * x86 TSC related functions
  */
-#ifndef _ASM_X86_TSC_H
-#define _ASM_X86_TSC_H
+#ifndef ASM_X86__TSC_H
+#define ASM_X86__TSC_H
 
 #include <asm/processor.h>
 
@@ -48,7 +48,6 @@ static __always_inline cycles_t vget_cycles(void)
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
-extern void init_tsc_clocksource(void);
 int check_tsc_unstable(void);
 
 /*
@@ -58,7 +57,6 @@ int check_tsc_unstable(void);
 extern void check_tsc_sync_source(int cpu);
 extern void check_tsc_sync_target(void);
 
-extern void tsc_calibrate(void);
 extern int notsc_setup(char *);
 
-#endif
+#endif /* ASM_X86__TSC_H */
diff --git a/include/asm-x86/types.h b/include/asm-x86/types.h
index 1ac80cd9acf8..e78b52e17444 100644
--- a/include/asm-x86/types.h
+++ b/include/asm-x86/types.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TYPES_H
-#define _ASM_X86_TYPES_H
+#ifndef ASM_X86__TYPES_H
+#define ASM_X86__TYPES_H
 
 #include <asm-generic/int-ll64.h>
 
@@ -33,4 +33,4 @@ typedef u32 dma_addr_t;
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__TYPES_H */
diff --git a/include/asm-x86/uaccess.h b/include/asm-x86/uaccess.h
index 9fefd2947e78..48ebc0ad40ec 100644
--- a/include/asm-x86/uaccess.h
+++ b/include/asm-x86/uaccess.h
@@ -1,5 +1,454 @@
+#ifndef ASM_X86__UACCESS_H
+#define ASM_X86__UACCESS_H
+/*
+ * User space memory access functions
+ */
+#include <linux/errno.h>
+#include <linux/compiler.h>
+#include <linux/thread_info.h>
+#include <linux/prefetch.h>
+#include <linux/string.h>
+#include <asm/asm.h>
+#include <asm/page.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not.  If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define MAKE_MM_SEG(s)  ((mm_segment_t) { (s) })
+
+#define KERNEL_DS       MAKE_MM_SEG(-1UL)
+#define USER_DS         MAKE_MM_SEG(PAGE_OFFSET)
+
+#define get_ds()        (KERNEL_DS)
+#define get_fs()        (current_thread_info()->addr_limit)
+#define set_fs(x)       (current_thread_info()->addr_limit = (x))
+
+#define segment_eq(a, b)        ((a).seg == (b).seg)
+
+#define __addr_ok(addr)                                 \
+        ((unsigned long __force)(addr) <                \
+         (current_thread_info()->addr_limit.seg))
+
+/*
+ * Test whether a block of memory is a valid user space address.
+ * Returns 0 if the range is valid, nonzero otherwise.
+ *
+ * This is equivalent to the following test:
+ * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
+ *
+ * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
+ */
+
+#define __range_not_ok(addr, size)                                      \
+({                                                                      \
+        unsigned long flag, roksum;                                     \
+        __chk_user_ptr(addr);                                           \
+        asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"             \
+            : "=&r" (flag), "=r" (roksum)                               \
+            : "1" (addr), "g" ((long)(size)),                           \
+              "rm" (current_thread_info()->addr_limit.seg));            \
+        flag;                                                           \
+})
+
+/**
+ * access_ok: - Checks if a user space pointer is valid
+ * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
+ *        %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe
+ *        to write to a block, it is always safe to read from it.
+ * @addr: User space pointer to start of block to check
+ * @size: Size of block to check
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Checks if a pointer to a block of memory in user space is valid.
+ *
+ * Returns true (nonzero) if the memory block may be valid, false (zero)
+ * if it is definitely invalid.
+ *
+ * Note that, depending on architecture, this function probably just
+ * checks that the pointer is in the user space range - after calling
+ * this function, memory access functions may still return -EFAULT.
+ */
+#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry {
+        unsigned long insn, fixup;
+};
+
+extern int fixup_exception(struct pt_regs *regs);
+
+/*
+ * These are the main single-value transfer routines.  They automatically
+ * use the right size if we just have the right pointer type.
+ *
+ * This gets kind of ugly. We want to return _two_ values in "get_user()"
+ * and yet we don't want to do any pointers, because that is too much
+ * of a performance impact. Thus we have a few rather ugly macros here,
+ * and hide all the ugliness from the user.
+ *
+ * The "__xxx" versions of the user access functions are versions that
+ * do not verify the address space, that must have been done previously
+ * with a separate "access_ok()" call (this is used when we do multiple
+ * accesses to the same area of user memory).
+ */
+
+extern int __get_user_1(void);
+extern int __get_user_2(void);
+extern int __get_user_4(void);
+extern int __get_user_8(void);
+extern int __get_user_bad(void);
+
+#define __get_user_x(size, ret, x, ptr)               \
+        asm volatile("call __get_user_" #size         \
+                     : "=a" (ret),"=d" (x)            \
+                     : "0" (ptr))                     \
+
+/* Careful: we have to cast the result to the type of the pointer
+ * for sign reasons */
+
+/**
+ * get_user: - Get a simple variable from user space.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#ifdef CONFIG_X86_32
+#define __get_user_8(__ret_gu, __val_gu, ptr)                           \
+                __get_user_x(X, __ret_gu, __val_gu, ptr)
+#else
+#define __get_user_8(__ret_gu, __val_gu, ptr)                           \
+                __get_user_x(8, __ret_gu, __val_gu, ptr)
+#endif
+
+#define get_user(x, ptr)                                                \
+({                                                                      \
+        int __ret_gu;                                                   \
+        unsigned long __val_gu;                                         \
+        __chk_user_ptr(ptr);                                            \
+        switch (sizeof(*(ptr))) {                                       \
+        case 1:                                                         \
+                __get_user_x(1, __ret_gu, __val_gu, ptr);               \
+                break;                                                  \
+        case 2:                                                         \
+                __get_user_x(2, __ret_gu, __val_gu, ptr);               \
+                break;                                                  \
+        case 4:                                                         \
+                __get_user_x(4, __ret_gu, __val_gu, ptr);               \
+                break;                                                  \
+        case 8:                                                         \
+                __get_user_8(__ret_gu, __val_gu, ptr);                  \
+                break;                                                  \
+        default:                                                        \
+                __get_user_x(X, __ret_gu, __val_gu, ptr);               \
+                break;                                                  \
+        }                                                               \
+        (x) = (__typeof__(*(ptr)))__val_gu;                             \
+        __ret_gu;                                                       \
+})
+
+#define __put_user_x(size, x, ptr, __ret_pu)                    \
+        asm volatile("call __put_user_" #size : "=a" (__ret_pu) \
+                     :"0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+
+
+
+#ifdef CONFIG_X86_32
+#define __put_user_u64(x, addr, err)                                    \
+        asm volatile("1:        movl %%eax,0(%2)\n"                     \
+                     "2:        movl %%edx,4(%2)\n"                     \
+                     "3:\n"                                             \
+                     ".section .fixup,\"ax\"\n"                         \
+                     "4:        movl %3,%0\n"                           \
+                     "  jmp 3b\n"                                       \
+                     ".previous\n"                                      \
+                     _ASM_EXTABLE(1b, 4b)                               \
+                     _ASM_EXTABLE(2b, 4b)                               \
+                     : "=r" (err)                                       \
+                     : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
+
+#define __put_user_x8(x, ptr, __ret_pu)                         \
+        asm volatile("call __put_user_8" : "=a" (__ret_pu)      \
+                     : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+#else
+#define __put_user_u64(x, ptr, retval) \
+        __put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT)
+#define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
+#endif
+
+extern void __put_user_bad(void);
+
+/*
+ * Strange magic calling convention: pointer in %ecx,
+ * value in %eax(:%edx), return value in %eax. clobbers %rbx
+ */
+extern void __put_user_1(void);
+extern void __put_user_2(void);
+extern void __put_user_4(void);
+extern void __put_user_8(void);
+
+#ifdef CONFIG_X86_WP_WORKS_OK
+
+/**
+ * put_user: - Write a simple value into user space.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define put_user(x, ptr)                                        \
+({                                                              \
+        int __ret_pu;                                           \
+        __typeof__(*(ptr)) __pu_val;                            \
+        __chk_user_ptr(ptr);                                    \
+        __pu_val = x;                                           \
+        switch (sizeof(*(ptr))) {                               \
+        case 1:                                                 \
+                __put_user_x(1, __pu_val, ptr, __ret_pu);       \
+                break;                                          \
+        case 2:                                                 \
+                __put_user_x(2, __pu_val, ptr, __ret_pu);       \
+                break;                                          \
+        case 4:                                                 \
+                __put_user_x(4, __pu_val, ptr, __ret_pu);       \
+                break;                                          \
+        case 8:                                                 \
+                __put_user_x8(__pu_val, ptr, __ret_pu);         \
+                break;                                          \
+        default:                                                \
+                __put_user_x(X, __pu_val, ptr, __ret_pu);       \
+                break;                                          \
+        }                                                       \
+        __ret_pu;                                               \
+})
+
+#define __put_user_size(x, ptr, size, retval, errret)                   \
+do {                                                                    \
+        retval = 0;                                                     \
+        __chk_user_ptr(ptr);                                            \
+        switch (size) {                                                 \
+        case 1:                                                         \
+                __put_user_asm(x, ptr, retval, "b", "b", "iq", errret); \
+                break;                                                  \
+        case 2:                                                         \
+                __put_user_asm(x, ptr, retval, "w", "w", "ir", errret); \
+                break;                                                  \
+        case 4:                                                         \
+                __put_user_asm(x, ptr, retval, "l", "k",  "ir", errret);\
+                break;                                                  \
+        case 8:                                                         \
+                __put_user_u64((__typeof__(*ptr))(x), ptr, retval);     \
+                break;                                                  \
+        default:                                                        \
+                __put_user_bad();                                       \
+        }                                                               \
+} while (0)
+
+#else
+
+#define __put_user_size(x, ptr, size, retval, errret)                   \
+do {                                                                    \
+        __typeof__(*(ptr))__pus_tmp = x;                                \
+        retval = 0;                                                     \
+                                                                        \
+        if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0))    \
+                retval = errret;                                        \
+} while (0)
+
+#define put_user(x, ptr)                                        \
+({                                                              \
+        int __ret_pu;                                           \
+        __typeof__(*(ptr))__pus_tmp = x;                        \
+        __ret_pu = 0;                                           \
+        if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp,         \
+                                       sizeof(*(ptr))) != 0))   \
+                __ret_pu = -EFAULT;                             \
+        __ret_pu;                                               \
+})
+#endif
+
+#ifdef CONFIG_X86_32
+#define __get_user_asm_u64(x, ptr, retval, errret)      (x) = __get_user_bad()
+#else
+#define __get_user_asm_u64(x, ptr, retval, errret) \
+         __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
+#endif
+
+#define __get_user_size(x, ptr, size, retval, errret)                   \
+do {                                                                    \
+        retval = 0;                                                     \
+        __chk_user_ptr(ptr);                                            \
+        switch (size) {                                                 \
+        case 1:                                                         \
+                __get_user_asm(x, ptr, retval, "b", "b", "=q", errret); \
+                break;                                                  \
+        case 2:                                                         \
+                __get_user_asm(x, ptr, retval, "w", "w", "=r", errret); \
+                break;                                                  \
+        case 4:                                                         \
+                __get_user_asm(x, ptr, retval, "l", "k", "=r", errret); \
+                break;                                                  \
+        case 8:                                                         \
+                __get_user_asm_u64(x, ptr, retval, errret);             \
+                break;                                                  \
+        default:                                                        \
+                (x) = __get_user_bad();                                 \
+        }                                                               \
+} while (0)
+
+#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret)       \
+        asm volatile("1:        mov"itype" %2,%"rtype"1\n"              \
+                     "2:\n"                                             \
+                     ".section .fixup,\"ax\"\n"                         \
+                     "3:        mov %3,%0\n"                            \
+                     "  xor"itype" %"rtype"1,%"rtype"1\n"               \
+                     "  jmp 2b\n"                                       \
+                     ".previous\n"                                      \
+                     _ASM_EXTABLE(1b, 3b)                               \
+                     : "=r" (err), ltype(x)                             \
+                     : "m" (__m(addr)), "i" (errret), "0" (err))
+
+#define __put_user_nocheck(x, ptr, size)                        \
+({                                                              \
+        long __pu_err;                                          \
+        __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \
+        __pu_err;                                               \
+})
+
+#define __get_user_nocheck(x, ptr, size)                                \
+({                                                                      \
+        long __gu_err;                                                  \
+        unsigned long __gu_val;                                         \
+        __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);    \
+        (x) = (__force __typeof__(*(ptr)))__gu_val;                     \
+        __gu_err;                                                       \
+})
+
+/* FIXME: this hack is definitely wrong -AK */
+struct __large_struct { unsigned long buf[100]; };
+#define __m(x) (*(struct __large_struct __user *)(x))
+
+/*
+ * Tell gcc we read from memory instead of writing: this is because
+ * we do not write to any memory gcc knows about, so there are no
+ * aliasing issues.
+ */
+#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret)       \
+        asm volatile("1:        mov"itype" %"rtype"1,%2\n"              \
+                     "2:\n"                                             \
+                     ".section .fixup,\"ax\"\n"                         \
+                     "3:        mov %3,%0\n"                            \
+                     "  jmp 2b\n"                                       \
+                     ".previous\n"                                      \
+                     _ASM_EXTABLE(1b, 3b)                               \
+                     : "=r"(err)                                        \
+                     : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
+/**
+ * __get_user: - Get a simple variable from user space, with less checking.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+
+#define __get_user(x, ptr)                                              \
+        __get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+/**
+ * __put_user: - Write a simple value into user space, with less checking.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+
+#define __put_user(x, ptr)                                              \
+        __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+
+#define __get_user_unaligned __get_user
+#define __put_user_unaligned __put_user
+
+/*
+ * movsl can be slow when source and dest are not both 8-byte aligned
+ */
+#ifdef CONFIG_X86_INTEL_USERCOPY
+extern struct movsl_mask {
+        int mask;
+} ____cacheline_aligned_in_smp movsl_mask;
+#endif
+
+#define ARCH_HAS_NOCACHE_UACCESS 1
+
 #ifdef CONFIG_X86_32
 # include "uaccess_32.h"
 #else
+# define ARCH_HAS_SEARCH_EXTABLE
 # include "uaccess_64.h"
 #endif
+
+#endif /* ASM_X86__UACCESS_H */
+
diff --git a/include/asm-x86/uaccess_32.h b/include/asm-x86/uaccess_32.h
index 8e7595c1f34e..6b5b57d9c6d1 100644
--- a/include/asm-x86/uaccess_32.h
+++ b/include/asm-x86/uaccess_32.h
@@ -1,5 +1,5 @@
-#ifndef __i386_UACCESS_H
-#define __i386_UACCESS_H
+#ifndef ASM_X86__UACCESS_32_H
+#define ASM_X86__UACCESS_32_H
 
 /*
  * User space memory access functions
@@ -11,426 +11,6 @@
 #include <asm/asm.h>
 #include <asm/page.h>
 
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define MAKE_MM_SEG(s)  ((mm_segment_t) { (s) })
-
-
-#define KERNEL_DS       MAKE_MM_SEG(0xFFFFFFFFUL)
-#define USER_DS         MAKE_MM_SEG(PAGE_OFFSET)
-
-#define get_ds()        (KERNEL_DS)
-#define get_fs()        (current_thread_info()->addr_limit)
-#define set_fs(x)       (current_thread_info()->addr_limit = (x))
-
-#define segment_eq(a, b)        ((a).seg == (b).seg)
-
-/*
- * movsl can be slow when source and dest are not both 8-byte aligned
- */
-#ifdef CONFIG_X86_INTEL_USERCOPY
-extern struct movsl_mask {
-        int mask;
-} ____cacheline_aligned_in_smp movsl_mask;
-#endif
-
-#define __addr_ok(addr)                                 \
-        ((unsigned long __force)(addr) <                \
-         (current_thread_info()->addr_limit.seg))
-
-/*
- * Test whether a block of memory is a valid user space address.
- * Returns 0 if the range is valid, nonzero otherwise.
- *
- * This is equivalent to the following test:
- * (u33)addr + (u33)size >= (u33)current->addr_limit.seg
- *
- * This needs 33-bit arithmetic. We have a carry...
- */
-#define __range_ok(addr, size)                                          \
-({                                                                      \
-        unsigned long flag, roksum;                                     \
-        __chk_user_ptr(addr);                                           \
-        asm("addl %3,%1 ; sbbl %0,%0; cmpl %1,%4; sbbl $0,%0"           \
-            :"=&r" (flag), "=r" (roksum)                                \
-            :"1" (addr), "g" ((int)(size)),                             \
-            "rm" (current_thread_info()->addr_limit.seg));              \
-        flag;                                                           \
-})
-
-/**
- * access_ok: - Checks if a user space pointer is valid
- * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
- *        %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe
- *        to write to a block, it is always safe to read from it.
- * @addr: User space pointer to start of block to check
- * @size: Size of block to check
- *
- * Context: User context only.  This function may sleep.
- *
- * Checks if a pointer to a block of memory in user space is valid.
- *
- * Returns true (nonzero) if the memory block may be valid, false (zero)
- * if it is definitely invalid.
- *
- * Note that, depending on architecture, this function probably just
- * checks that the pointer is in the user space range - after calling
- * this function, memory access functions may still return -EFAULT.
- */
-#define access_ok(type, addr, size) (likely(__range_ok(addr, size) == 0))
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-        unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
-
-/*
- * These are the main single-value transfer routines.  They automatically
- * use the right size if we just have the right pointer type.
- *
- * This gets kind of ugly. We want to return _two_ values in "get_user()"
- * and yet we don't want to do any pointers, because that is too much
- * of a performance impact. Thus we have a few rather ugly macros here,
- * and hide all the ugliness from the user.
- *
- * The "__xxx" versions of the user access functions are versions that
- * do not verify the address space, that must have been done previously
- * with a separate "access_ok()" call (this is used when we do multiple
- * accesses to the same area of user memory).
- */
-
-extern void __get_user_1(void);
-extern void __get_user_2(void);
-extern void __get_user_4(void);
-
-#define __get_user_x(size, ret, x, ptr)       \
-        asm volatile("call __get_user_" #size \
-                     :"=a" (ret),"=d" (x)     \
-                     :"0" (ptr))
-
-
-/* Careful: we have to cast the result to the type of the pointer
- * for sign reasons */
-
-/**
- * get_user: - Get a simple variable from user space.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define get_user(x, ptr)                                                \
-({                                                                      \
-        int __ret_gu;                                                   \
-        unsigned long __val_gu;                                         \
-        __chk_user_ptr(ptr);                                            \
-        switch (sizeof(*(ptr))) {                                       \
-        case 1:                                                         \
-                __get_user_x(1, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        case 2:                                                         \
-                __get_user_x(2, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        case 4:                                                         \
-                __get_user_x(4, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        default:                                                        \
-                __get_user_x(X, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        }                                                               \
-        (x) = (__typeof__(*(ptr)))__val_gu;                             \
-        __ret_gu;                                                       \
-})
-
-extern void __put_user_bad(void);
-
-/*
- * Strange magic calling convention: pointer in %ecx,
- * value in %eax(:%edx), return value in %eax, no clobbers.
- */
-extern void __put_user_1(void);
-extern void __put_user_2(void);
-extern void __put_user_4(void);
-extern void __put_user_8(void);
-
-#define __put_user_1(x, ptr)                                    \
-        asm volatile("call __put_user_1" : "=a" (__ret_pu)      \
-                     : "0" ((typeof(*(ptr)))(x)), "c" (ptr))
-
-#define __put_user_2(x, ptr)                                    \
-        asm volatile("call __put_user_2" : "=a" (__ret_pu)      \
-                     : "0" ((typeof(*(ptr)))(x)), "c" (ptr))
-
-#define __put_user_4(x, ptr)                                    \
-        asm volatile("call __put_user_4" : "=a" (__ret_pu)      \
-                     : "0" ((typeof(*(ptr)))(x)), "c" (ptr))
-
-#define __put_user_8(x, ptr)                                    \
-        asm volatile("call __put_user_8" : "=a" (__ret_pu)      \
-                     : "A" ((typeof(*(ptr)))(x)), "c" (ptr))
-
-#define __put_user_X(x, ptr)                                    \
-        asm volatile("call __put_user_X" : "=a" (__ret_pu)      \
-                     : "c" (ptr))
-
-/**
- * put_user: - Write a simple value into user space.
- * @x:   Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#ifdef CONFIG_X86_WP_WORKS_OK
-
-#define put_user(x, ptr)                                        \
-({                                                              \
-        int __ret_pu;                                           \
-        __typeof__(*(ptr)) __pu_val;                            \
-        __chk_user_ptr(ptr);                                    \
-        __pu_val = x;                                           \
-        switch (sizeof(*(ptr))) {                               \
-        case 1:                                                 \
-                __put_user_1(__pu_val, ptr);                    \
-                break;                                          \
-        case 2:                                                 \
-                __put_user_2(__pu_val, ptr);                    \
-                break;                                          \
-        case 4:                                                 \
-                __put_user_4(__pu_val, ptr);                    \
-                break;                                          \
-        case 8:                                                 \
-                __put_user_8(__pu_val, ptr);                    \
-                break;                                          \
-        default:                                                \
-                __put_user_X(__pu_val, ptr);                    \
-                break;                                          \
-        }                                                       \
-        __ret_pu;                                               \
-})
-
-#else
-#define put_user(x, ptr)                                        \
-({                                                              \
-        int __ret_pu;                                           \
-        __typeof__(*(ptr))__pus_tmp = x;                        \
-        __ret_pu = 0;                                           \
-        if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp,         \
-                                       sizeof(*(ptr))) != 0))   \
-                __ret_pu = -EFAULT;                             \
-        __ret_pu;                                               \
-})
-
-
-#endif
-
-/**
- * __get_user: - Get a simple variable from user space, with less checking.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define __get_user(x, ptr)                              \
-        __get_user_nocheck((x), (ptr), sizeof(*(ptr)))
-
-
-/**
- * __put_user: - Write a simple value into user space, with less checking.
- * @x:   Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define __put_user(x, ptr)                                              \
-        __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-
-#define __put_user_nocheck(x, ptr, size)                        \
-({                                                              \
-        long __pu_err;                                          \
-        __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \
-        __pu_err;                                               \
-})
-
-
-#define __put_user_u64(x, addr, err)                                    \
-        asm volatile("1:        movl %%eax,0(%2)\n"                     \
-                     "2:        movl %%edx,4(%2)\n"                     \
-                     "3:\n"                                             \
-                     ".section .fixup,\"ax\"\n"                         \
-                     "4:        movl %3,%0\n"                           \
-                     "  jmp 3b\n"                                       \
-                     ".previous\n"                                      \
-                     _ASM_EXTABLE(1b, 4b)                               \
-                     _ASM_EXTABLE(2b, 4b)                               \
-                     : "=r" (err)                                       \
-                     : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
-
-#ifdef CONFIG_X86_WP_WORKS_OK
-
-#define __put_user_size(x, ptr, size, retval, errret)                   \
-do {                                                                    \
-        retval = 0;                                                     \
-        __chk_user_ptr(ptr);                                            \
-        switch (size) {                                                 \
-        case 1:                                                         \
-                __put_user_asm(x, ptr, retval, "b", "b", "iq", errret); \
-                break;                                                  \
-        case 2:                                                         \
-                __put_user_asm(x, ptr, retval, "w", "w", "ir", errret); \
-                break;                                                  \
-        case 4:                                                         \
-                __put_user_asm(x, ptr, retval, "l", "",  "ir", errret); \
-                break;                                                  \
-        case 8:                                                         \
-                __put_user_u64((__typeof__(*ptr))(x), ptr, retval);     \
-                break;                                                  \
-        default:                                                        \
-                __put_user_bad();                                       \
-        }                                                               \
-} while (0)
-
-#else
-
-#define __put_user_size(x, ptr, size, retval, errret)                   \
-do {                                                                    \
-        __typeof__(*(ptr))__pus_tmp = x;                                \
-        retval = 0;                                                     \
-                                                                        \
-        if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0))    \
-                retval = errret;                                        \
-} while (0)
-
-#endif
-struct __large_struct { unsigned long buf[100]; };
-#define __m(x) (*(struct __large_struct __user *)(x))
-
-/*
- * Tell gcc we read from memory instead of writing: this is because
- * we do not write to any memory gcc knows about, so there are no
- * aliasing issues.
- */
-#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret)       \
-        asm volatile("1:        mov"itype" %"rtype"1,%2\n"              \
-                     "2:\n"                                             \
-                     ".section .fixup,\"ax\"\n"                         \
-                     "3:        movl %3,%0\n"                           \
-                     "  jmp 2b\n"                                       \
-                     ".previous\n"                                      \
-                     _ASM_EXTABLE(1b, 3b)                               \
-                     : "=r"(err)                                        \
-                     : ltype (x), "m" (__m(addr)), "i" (errret), "0" (err))
-
-
-#define __get_user_nocheck(x, ptr, size)                                \
-({                                                                      \
-        long __gu_err;                                                  \
-        unsigned long __gu_val;                                         \
-        __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);    \
-        (x) = (__typeof__(*(ptr)))__gu_val;                             \
-        __gu_err;                                                       \
-})
-
-extern long __get_user_bad(void);
-
-#define __get_user_size(x, ptr, size, retval, errret)                   \
-do {                                                                    \
-        retval = 0;                                                     \
-        __chk_user_ptr(ptr);                                            \
-        switch (size) {                                                 \
-        case 1:                                                         \
-                __get_user_asm(x, ptr, retval, "b", "b", "=q", errret); \
-                break;                                                  \
-        case 2:                                                         \
-                __get_user_asm(x, ptr, retval, "w", "w", "=r", errret); \
-                break;                                                  \
-        case 4:                                                         \
-                __get_user_asm(x, ptr, retval, "l", "", "=r", errret);  \
-                break;                                                  \
-        default:                                                        \
-                (x) = __get_user_bad();                                 \
-        }                                                               \
-} while (0)
-
-#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret)       \
-        asm volatile("1:        mov"itype" %2,%"rtype"1\n"              \
-                     "2:\n"                                             \
-                     ".section .fixup,\"ax\"\n"                         \
-                     "3:        movl %3,%0\n"                           \
-                     "  xor"itype" %"rtype"1,%"rtype"1\n"               \
-                     "  jmp 2b\n"                                       \
-                     ".previous\n"                                      \
-                     _ASM_EXTABLE(1b, 3b)                               \
-                     : "=r" (err), ltype (x)                            \
-                     : "m" (__m(addr)), "i" (errret), "0" (err))
-
-
 unsigned long __must_check __copy_to_user_ll
                 (void __user *to, const void *from, unsigned long n);
 unsigned long __must_check __copy_from_user_ll
@@ -576,8 +156,6 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
         return __copy_from_user_ll(to, from, n);
 }
 
-#define ARCH_HAS_NOCACHE_UACCESS
-
 static __always_inline unsigned long __copy_from_user_nocache(void *to,
                                 const void __user *from, unsigned long n)
 {
@@ -637,4 +215,4 @@ long strnlen_user(const char __user *str, long n);
 unsigned long __must_check clear_user(void __user *mem, unsigned long len);
 unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
 
-#endif /* __i386_UACCESS_H */
+#endif /* ASM_X86__UACCESS_32_H */
diff --git a/include/asm-x86/uaccess_64.h b/include/asm-x86/uaccess_64.h
index b8a2f4339903..c96c1f5d07a2 100644
--- a/include/asm-x86/uaccess_64.h
+++ b/include/asm-x86/uaccess_64.h
@@ -1,5 +1,5 @@
-#ifndef __X86_64_UACCESS_H
-#define __X86_64_UACCESS_H
+#ifndef ASM_X86__UACCESS_64_H
+#define ASM_X86__UACCESS_64_H
 
 /*
  * User space memory access functions
@@ -7,267 +7,9 @@
 #include <linux/compiler.h>
 #include <linux/errno.h>
 #include <linux/prefetch.h>
+#include <linux/lockdep.h>
 #include <asm/page.h>
 
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define MAKE_MM_SEG(s)  ((mm_segment_t) { (s) })
-
-#define KERNEL_DS       MAKE_MM_SEG(0xFFFFFFFFFFFFFFFFUL)
-#define USER_DS         MAKE_MM_SEG(PAGE_OFFSET)
-
-#define get_ds()        (KERNEL_DS)
-#define get_fs()        (current_thread_info()->addr_limit)
-#define set_fs(x)       (current_thread_info()->addr_limit = (x))
-
-#define segment_eq(a, b)        ((a).seg == (b).seg)
-
-#define __addr_ok(addr) (!((unsigned long)(addr) &                      \
-                           (current_thread_info()->addr_limit.seg)))
-
-/*
- * Uhhuh, this needs 65-bit arithmetic. We have a carry..
- */
-#define __range_not_ok(addr, size)                                      \
-({                                                                      \
-        unsigned long flag, roksum;                                     \
-        __chk_user_ptr(addr);                                           \
-        asm("# range_ok\n\r"                                            \
-            "addq %3,%1 ; sbbq %0,%0 ; cmpq %1,%4 ; sbbq $0,%0"         \
-            : "=&r" (flag), "=r" (roksum)                               \
-            : "1" (addr), "g" ((long)(size)),                           \
-              "g" (current_thread_info()->addr_limit.seg));             \
-        flag;                                                           \
-})
-
-#define access_ok(type, addr, size) (__range_not_ok(addr, size) == 0)
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-        unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
-
-#define ARCH_HAS_SEARCH_EXTABLE
-
-/*
- * These are the main single-value transfer routines.  They automatically
- * use the right size if we just have the right pointer type.
- *
- * This gets kind of ugly. We want to return _two_ values in "get_user()"
- * and yet we don't want to do any pointers, because that is too much
- * of a performance impact. Thus we have a few rather ugly macros here,
- * and hide all the ugliness from the user.
- *
- * The "__xxx" versions of the user access functions are versions that
- * do not verify the address space, that must have been done previously
- * with a separate "access_ok()" call (this is used when we do multiple
- * accesses to the same area of user memory).
- */
-
-#define __get_user_x(size, ret, x, ptr)               \
-        asm volatile("call __get_user_" #size         \
-                     : "=a" (ret),"=d" (x)            \
-                     : "c" (ptr)                      \
-                     : "r8")
-
-/* Careful: we have to cast the result to the type of the pointer
- * for sign reasons */
-
-#define get_user(x, ptr)                                                \
-({                                                                      \
-        unsigned long __val_gu;                                         \
-        int __ret_gu;                                                   \
-        __chk_user_ptr(ptr);                                            \
-        switch (sizeof(*(ptr))) {                                       \
-        case 1:                                                         \
-                __get_user_x(1, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        case 2:                                                         \
-                __get_user_x(2, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        case 4:                                                         \
-                __get_user_x(4, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        case 8:                                                         \
-                __get_user_x(8, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        default:                                                        \
-                __get_user_bad();                                       \
-                break;                                                  \
-        }                                                               \
-        (x) = (__force typeof(*(ptr)))__val_gu;                         \
-        __ret_gu;                                                       \
-})
-
-extern void __put_user_1(void);
-extern void __put_user_2(void);
-extern void __put_user_4(void);
-extern void __put_user_8(void);
-extern void __put_user_bad(void);
-
-#define __put_user_x(size, ret, x, ptr)                                 \
-        asm volatile("call __put_user_" #size                           \
-                     :"=a" (ret)                                        \
-                     :"c" (ptr),"d" (x)                                 \
-                     :"r8")
-
-#define put_user(x, ptr)                                                \
-        __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-
-#define __get_user(x, ptr)                                              \
-        __get_user_nocheck((x), (ptr), sizeof(*(ptr)))
-#define __put_user(x, ptr)                                              \
-        __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-
-#define __get_user_unaligned __get_user
-#define __put_user_unaligned __put_user
-
-#define __put_user_nocheck(x, ptr, size)                \
-({                                                      \
-        int __pu_err;                                   \
-        __put_user_size((x), (ptr), (size), __pu_err);  \
-        __pu_err;                                       \
-})
-
-
-#define __put_user_check(x, ptr, size)                          \
-({                                                              \
-        int __pu_err;                                           \
-        typeof(*(ptr)) __user *__pu_addr = (ptr);               \
-        switch (size) {                                         \
-        case 1:                                                 \
-                __put_user_x(1, __pu_err, x, __pu_addr);        \
-                break;                                          \
-        case 2:                                                 \
-                __put_user_x(2, __pu_err, x, __pu_addr);        \
-                break;                                          \
-        case 4:                                                 \
-                __put_user_x(4, __pu_err, x, __pu_addr);        \
-                break;                                          \
-        case 8:                                                 \
-                __put_user_x(8, __pu_err, x, __pu_addr);        \
-                break;                                          \
-        default:                                                \
-                __put_user_bad();                               \
-        }                                                       \
-        __pu_err;                                               \
-})
-
-#define __put_user_size(x, ptr, size, retval)                           \
-do {                                                                    \
-        retval = 0;                                                     \
-        __chk_user_ptr(ptr);                                            \
-        switch (size) {                                                 \
-        case 1:                                                         \
-                __put_user_asm(x, ptr, retval, "b", "b", "iq", -EFAULT);\
-                break;                                                  \
-        case 2:                                                         \
-                __put_user_asm(x, ptr, retval, "w", "w", "ir", -EFAULT);\
-                break;                                                  \
-        case 4:                                                         \
-                __put_user_asm(x, ptr, retval, "l", "k", "ir", -EFAULT);\
-                break;                                                  \
-        case 8:                                                         \
-                __put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT); \
-                break;                                                  \
-        default:                                                        \
-                __put_user_bad();                                       \
-        }                                                               \
-} while (0)
-
-/* FIXME: this hack is definitely wrong -AK */
-struct __large_struct { unsigned long buf[100]; };
-#define __m(x) (*(struct __large_struct __user *)(x))
-
-/*
- * Tell gcc we read from memory instead of writing: this is because
- * we do not write to any memory gcc knows about, so there are no
- * aliasing issues.
- */
-#define __put_user_asm(x, addr, err, itype, rtype, ltype, errno)        \
-        asm volatile("1:        mov"itype" %"rtype"1,%2\n"              \
-                     "2:\n"                                             \
-                     ".section .fixup, \"ax\"\n"                        \
-                     "3:        mov %3,%0\n"                            \
-                     "  jmp 2b\n"                                       \
-                     ".previous\n"                                      \
-                     _ASM_EXTABLE(1b, 3b)                               \
-                     : "=r"(err)                                        \
-                     : ltype (x), "m" (__m(addr)), "i" (errno), "0" (err))
-
-
-#define __get_user_nocheck(x, ptr, size)                        \
-({                                                              \
-        int __gu_err;                                           \
-        unsigned long __gu_val;                                 \
-        __get_user_size(__gu_val, (ptr), (size), __gu_err);     \
-        (x) = (__force typeof(*(ptr)))__gu_val;                 \
-        __gu_err;                                               \
-})
-
-extern int __get_user_1(void);
-extern int __get_user_2(void);
-extern int __get_user_4(void);
-extern int __get_user_8(void);
-extern int __get_user_bad(void);
-
-#define __get_user_size(x, ptr, size, retval)                           \
-do {                                                                    \
-        retval = 0;                                                     \
-        __chk_user_ptr(ptr);                                            \
-        switch (size) {                                                 \
-        case 1:                                                         \
-                __get_user_asm(x, ptr, retval, "b", "b", "=q", -EFAULT);\
-                break;                                                  \
-        case 2:                                                         \
-                __get_user_asm(x, ptr, retval, "w", "w", "=r", -EFAULT);\
-                break;                                                  \
-        case 4:                                                         \
-                __get_user_asm(x, ptr, retval, "l", "k", "=r", -EFAULT);\
-                break;                                                  \
-        case 8:                                                         \
-                __get_user_asm(x, ptr, retval, "q", "", "=r", -EFAULT); \
-                break;                                                  \
-        default:                                                        \
-                (x) = __get_user_bad();                                 \
-        }                                                               \
-} while (0)
-
-#define __get_user_asm(x, addr, err, itype, rtype, ltype, errno)        \
-        asm volatile("1:        mov"itype" %2,%"rtype"1\n"              \
-                     "2:\n"                                             \
-                     ".section .fixup, \"ax\"\n"                        \
-                     "3:        mov %3,%0\n"                            \
-                     "  xor"itype" %"rtype"1,%"rtype"1\n"               \
-                     "  jmp 2b\n"                                       \
-                     ".previous\n"                                      \
-                     _ASM_EXTABLE(1b, 3b)                               \
-                     : "=r" (err), ltype (x)                            \
-                     : "m" (__m(addr)), "i"(errno), "0"(err))
-
 /*
  * Copy To/From Userspace
  */
@@ -437,7 +179,6 @@ __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
         return copy_user_generic((__force void *)dst, src, size);
 }
 
-#define ARCH_HAS_NOCACHE_UACCESS 1
 extern long __copy_user_nocache(void *dst, const void __user *src,
                                 unsigned size, int zerorest);
 
@@ -455,4 +196,7 @@ static inline int __copy_from_user_inatomic_nocache(void *dst,
         return __copy_user_nocache(dst, src, size, 0);
 }
 
-#endif /* __X86_64_UACCESS_H */
+unsigned long
+copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest);
+
+#endif /* ASM_X86__UACCESS_64_H */
diff --git a/include/asm-x86/ucontext.h b/include/asm-x86/ucontext.h
index 50a79f7fcde9..89eaa5456a7e 100644
--- a/include/asm-x86/ucontext.h
+++ b/include/asm-x86/ucontext.h
@@ -1,5 +1,11 @@
-#ifndef _ASM_X86_UCONTEXT_H
-#define _ASM_X86_UCONTEXT_H
+#ifndef ASM_X86__UCONTEXT_H
+#define ASM_X86__UCONTEXT_H
+
+#define UC_FP_XSTATE    0x1     /* indicates the presence of extended state
+                                 * information in the memory layout pointed
+                                 * by the fpstate pointer in the ucontext's
+                                 * sigcontext struct (uc_mcontext).
+                                 */
 
 struct ucontext {
         unsigned long     uc_flags;
@@ -9,4 +15,4 @@ struct ucontext {
         sigset_t          uc_sigmask;   /* mask last for extensibility */
 };
 
-#endif /* _ASM_X86_UCONTEXT_H */
+#endif /* ASM_X86__UCONTEXT_H */
diff --git a/include/asm-x86/unaligned.h b/include/asm-x86/unaligned.h
index a7bd416b4763..59dcdec37160 100644
--- a/include/asm-x86/unaligned.h
+++ b/include/asm-x86/unaligned.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_UNALIGNED_H
-#define _ASM_X86_UNALIGNED_H
+#ifndef ASM_X86__UNALIGNED_H
+#define ASM_X86__UNALIGNED_H
 
 /*
  * The x86 can do unaligned accesses itself.
@@ -11,4 +11,4 @@
 #define get_unaligned __get_unaligned_le
 #define put_unaligned __put_unaligned_le
 
-#endif /* _ASM_X86_UNALIGNED_H */
+#endif /* ASM_X86__UNALIGNED_H */
diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h
index 8317d94771d3..017f4a87c913 100644
--- a/include/asm-x86/unistd_32.h
+++ b/include/asm-x86/unistd_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_I386_UNISTD_H_
-#define _ASM_I386_UNISTD_H_
+#ifndef ASM_X86__UNISTD_32_H
+#define ASM_X86__UNISTD_32_H
 
 /*
  * This file contains the system call numbers.
@@ -332,6 +332,12 @@
 #define __NR_fallocate          324
 #define __NR_timerfd_settime    325
 #define __NR_timerfd_gettime    326
+#define __NR_signalfd4          327
+#define __NR_eventfd2           328
+#define __NR_epoll_create1      329
+#define __NR_dup3               330
+#define __NR_pipe2              331
+#define __NR_inotify_init1      332
 
 #ifdef __KERNEL__
 
@@ -370,4 +376,4 @@
 #endif
 
 #endif /* __KERNEL__ */
-#endif /* _ASM_I386_UNISTD_H_ */
+#endif /* ASM_X86__UNISTD_32_H */
diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h
index fe26e36d0f51..ace83f1f6787 100644
--- a/include/asm-x86/unistd_64.h
+++ b/include/asm-x86/unistd_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_UNISTD_H_
-#define _ASM_X86_64_UNISTD_H_
+#ifndef ASM_X86__UNISTD_64_H
+#define ASM_X86__UNISTD_64_H
 
 #ifndef __SYSCALL
 #define __SYSCALL(a, b)
@@ -290,7 +290,7 @@ __SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait)
 #define __NR_rt_sigqueueinfo                    129
 __SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo)
 #define __NR_rt_sigsuspend                      130
-__SYSCALL(__NR_rt_sigsuspend, stub_rt_sigsuspend)
+__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend)
 #define __NR_sigaltstack                        131
 __SYSCALL(__NR_sigaltstack, stub_sigaltstack)
 #define __NR_utime                              132
@@ -639,6 +639,20 @@ __SYSCALL(__NR_fallocate, sys_fallocate)
 __SYSCALL(__NR_timerfd_settime, sys_timerfd_settime)
 #define __NR_timerfd_gettime                    287
 __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
+#define __NR_paccept                            288
+__SYSCALL(__NR_paccept, sys_paccept)
+#define __NR_signalfd4                          289
+__SYSCALL(__NR_signalfd4, sys_signalfd4)
+#define __NR_eventfd2                           290
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+#define __NR_epoll_create1                      291
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_dup3                               292
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR_pipe2                              293
+__SYSCALL(__NR_pipe2, sys_pipe2)
+#define __NR_inotify_init1                      294
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
 
 
 #ifndef __NO_STUBS
@@ -676,4 +690,4 @@ __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
 #define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
 #endif  /* __KERNEL__ */
 
-#endif /* _ASM_X86_64_UNISTD_H_ */
+#endif /* ASM_X86__UNISTD_64_H */
diff --git a/include/asm-x86/unwind.h b/include/asm-x86/unwind.h
index 8b064bd9c553..a2151567db44 100644
--- a/include/asm-x86/unwind.h
+++ b/include/asm-x86/unwind.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_UNWIND_H
-#define _ASM_X86_UNWIND_H
+#ifndef ASM_X86__UNWIND_H
+#define ASM_X86__UNWIND_H
 
 #define UNW_PC(frame) ((void)(frame), 0UL)
 #define UNW_SP(frame) ((void)(frame), 0UL)
@@ -10,4 +10,4 @@ static inline int arch_unw_user_mode(const void *info)
         return 0;
 }
 
-#endif /* _ASM_X86_UNWIND_H */
+#endif /* ASM_X86__UNWIND_H */
diff --git a/include/asm-x86/user32.h b/include/asm-x86/user32.h
index a3d910047879..aa66c1857f06 100644
--- a/include/asm-x86/user32.h
+++ b/include/asm-x86/user32.h
@@ -1,5 +1,5 @@
-#ifndef USER32_H
-#define USER32_H 1
+#ifndef ASM_X86__USER32_H
+#define ASM_X86__USER32_H
 
 /* IA32 compatible user structures for ptrace.
  * These should be used for 32bit coredumps too. */
@@ -67,4 +67,4 @@ struct user32 {
 };
 
 
-#endif
+#endif /* ASM_X86__USER32_H */
diff --git a/include/asm-x86/user_32.h b/include/asm-x86/user_32.h
index d6e51edc259d..e0fe2f55f1a6 100644
--- a/include/asm-x86/user_32.h
+++ b/include/asm-x86/user_32.h
@@ -1,5 +1,5 @@
-#ifndef _I386_USER_H
-#define _I386_USER_H
+#ifndef ASM_X86__USER_32_H
+#define ASM_X86__USER_32_H
 
 #include <asm/page.h>
 /* Core file format: The core file is written in such a way that gdb
@@ -128,4 +128,4 @@ struct user{
 #define HOST_TEXT_START_ADDR (u.start_code)
 #define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
 
-#endif /* _I386_USER_H */
+#endif /* ASM_X86__USER_32_H */
diff --git a/include/asm-x86/user_64.h b/include/asm-x86/user_64.h
index 6037b634c77f..38b5799863b4 100644
--- a/include/asm-x86/user_64.h
+++ b/include/asm-x86/user_64.h
@@ -1,5 +1,5 @@
-#ifndef _X86_64_USER_H
-#define _X86_64_USER_H
+#ifndef ASM_X86__USER_64_H
+#define ASM_X86__USER_64_H
 
 #include <asm/types.h>
 #include <asm/page.h>
@@ -134,4 +134,4 @@ struct user {
 #define HOST_TEXT_START_ADDR (u.start_code)
 #define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
 
-#endif /* _X86_64_USER_H */
+#endif /* ASM_X86__USER_64_H */
diff --git a/include/asm-x86/uv/bios.h b/include/asm-x86/uv/bios.h
new file mode 100644
index 000000000000..7cd6d7ec1308
--- /dev/null
+++ b/include/asm-x86/uv/bios.h
@@ -0,0 +1,68 @@
+#ifndef ASM_X86__UV__BIOS_H
+#define ASM_X86__UV__BIOS_H
+
+/*
+ * BIOS layer definitions.
+ *
+ *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  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 <linux/rtc.h>
+
+#define BIOS_FREQ_BASE                  0x01000001
+
+enum {
+        BIOS_FREQ_BASE_PLATFORM = 0,
+        BIOS_FREQ_BASE_INTERVAL_TIMER = 1,
+        BIOS_FREQ_BASE_REALTIME_CLOCK = 2
+};
+
+# define BIOS_CALL(result, a0, a1, a2, a3, a4, a5, a6, a7)              \
+        do {                                                            \
+                /* XXX - the real call goes here */                     \
+                result.status = BIOS_STATUS_UNIMPLEMENTED;              \
+                isrv.v0 = 0;                                            \
+                isrv.v1 = 0;                                            \
+        } while (0)
+
+enum {
+        BIOS_STATUS_SUCCESS             =  0,
+        BIOS_STATUS_UNIMPLEMENTED       = -1,
+        BIOS_STATUS_EINVAL              = -2,
+        BIOS_STATUS_ERROR               = -3
+};
+
+struct uv_bios_retval {
+        /*
+         * A zero status value indicates call completed without error.
+         * A negative status value indicates reason of call failure.
+         * A positive status value indicates success but an
+         * informational value should be printed (e.g., "reboot for
+         * change to take effect").
+         */
+        s64 status;
+        u64 v0;
+        u64 v1;
+        u64 v2;
+};
+
+extern long
+x86_bios_freq_base(unsigned long which, unsigned long *ticks_per_second,
+                   unsigned long *drift_info);
+extern const char *x86_bios_strerror(long status);
+
+#endif /* ASM_X86__UV__BIOS_H */
diff --git a/include/asm-x86/uv/uv_bau.h b/include/asm-x86/uv/uv_bau.h
new file mode 100644
index 000000000000..77153fb18f5e
--- /dev/null
+++ b/include/asm-x86/uv/uv_bau.h
@@ -0,0 +1,332 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV Broadcast Assist Unit definitions
+ *
+ * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#ifndef ASM_X86__UV__UV_BAU_H
+#define ASM_X86__UV__UV_BAU_H
+
+#include <linux/bitmap.h>
+#define BITSPERBYTE 8
+
+/*
+ * Broadcast Assist Unit messaging structures
+ *
+ * Selective Broadcast activations are induced by software action
+ * specifying a particular 8-descriptor "set" via a 6-bit index written
+ * to an MMR.
+ * Thus there are 64 unique 512-byte sets of SB descriptors - one set for
+ * each 6-bit index value. These descriptor sets are mapped in sequence
+ * starting with set 0 located at the address specified in the
+ * BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512,
+ * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on.
+ *
+ * We will use 31 sets, one for sending BAU messages from each of the 32
+ * cpu's on the node.
+ *
+ * TLB shootdown will use the first of the 8 descriptors of each set.
+ * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
+ */
+
+#define UV_ITEMS_PER_DESCRIPTOR         8
+#define UV_CPUS_PER_ACT_STATUS          32
+#define UV_ACT_STATUS_MASK              0x3
+#define UV_ACT_STATUS_SIZE              2
+#define UV_ACTIVATION_DESCRIPTOR_SIZE   32
+#define UV_DISTRIBUTION_SIZE            256
+#define UV_SW_ACK_NPENDING              8
+#define UV_NET_ENDPOINT_INTD            0x38
+#define UV_DESC_BASE_PNODE_SHIFT        49
+#define UV_PAYLOADQ_PNODE_SHIFT         49
+#define UV_PTC_BASENAME                 "sgi_uv/ptc_statistics"
+#define uv_physnodeaddr(x)              ((__pa((unsigned long)(x)) & uv_mmask))
+
+/*
+ * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1
+ */
+#define DESC_STATUS_IDLE                0
+#define DESC_STATUS_ACTIVE              1
+#define DESC_STATUS_DESTINATION_TIMEOUT 2
+#define DESC_STATUS_SOURCE_TIMEOUT      3
+
+/*
+ * source side threshholds at which message retries print a warning
+ */
+#define SOURCE_TIMEOUT_LIMIT            20
+#define DESTINATION_TIMEOUT_LIMIT       20
+
+/*
+ * number of entries in the destination side payload queue
+ */
+#define DEST_Q_SIZE                     17
+/*
+ * number of destination side software ack resources
+ */
+#define DEST_NUM_RESOURCES              8
+#define MAX_CPUS_PER_NODE               32
+/*
+ * completion statuses for sending a TLB flush message
+ */
+#define FLUSH_RETRY                     1
+#define FLUSH_GIVEUP                    2
+#define FLUSH_COMPLETE                  3
+
+/*
+ * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
+ * If the 'multilevel' flag in the header portion of the descriptor
+ * has been set to 0, then endpoint multi-unicast mode is selected.
+ * The distribution specification (32 bytes) is interpreted as a 256-bit
+ * distribution vector. Adjacent bits correspond to consecutive even numbered
+ * nodeIDs. The result of adding the index of a given bit to the 15-bit
+ * 'base_dest_nodeid' field of the header corresponds to the
+ * destination nodeID associated with that specified bit.
+ */
+struct bau_target_nodemask {
+        unsigned long bits[BITS_TO_LONGS(256)];
+};
+
+/*
+ * mask of cpu's on a node
+ * (during initialization we need to check that unsigned long has
+ *  enough bits for max. cpu's per node)
+ */
+struct bau_local_cpumask {
+        unsigned long bits;
+};
+
+/*
+ * Payload: 16 bytes (128 bits) (bytes 0x20-0x2f of descriptor)
+ * only 12 bytes (96 bits) of the payload area are usable.
+ * An additional 3 bytes (bits 27:4) of the header address are carried
+ * to the next bytes of the destination payload queue.
+ * And an additional 2 bytes of the header Suppl_A field are also
+ * carried to the destination payload queue.
+ * But the first byte of the Suppl_A becomes bits 127:120 (the 16th byte)
+ * of the destination payload queue, which is written by the hardware
+ * with the s/w ack resource bit vector.
+ * [ effective message contents (16 bytes (128 bits) maximum), not counting
+ *   the s/w ack bit vector  ]
+ */
+
+/*
+ * The payload is software-defined for INTD transactions
+ */
+struct bau_msg_payload {
+        unsigned long address;          /* signifies a page or all TLB's
+                                                of the cpu */
+        /* 64 bits */
+        unsigned short sending_cpu;     /* filled in by sender */
+        /* 16 bits */
+        unsigned short acknowledge_count;/* filled in by destination */
+        /* 16 bits */
+        unsigned int reserved1:32;      /* not usable */
+};
+
+
+/*
+ * Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * see table 4.2.3.0.1 in broacast_assist spec.
+ */
+struct bau_msg_header {
+        int dest_subnodeid:6;   /* must be zero */
+        /* bits 5:0 */
+        int base_dest_nodeid:15; /* nasid>>1 (pnode) of first bit in node_map */
+        /* bits 20:6 */
+        int command:8;          /* message type */
+        /* bits 28:21 */
+                                /* 0x38: SN3net EndPoint Message */
+        int rsvd_1:3;           /* must be zero */
+        /* bits 31:29 */
+                                /* int will align on 32 bits */
+        int rsvd_2:9;           /* must be zero */
+        /* bits 40:32 */
+                                /* Suppl_A is 56-41 */
+        int payload_2a:8;       /* becomes byte 16 of msg */
+        /* bits 48:41 */        /* not currently using */
+        int payload_2b:8;       /* becomes byte 17 of msg */
+        /* bits 56:49 */        /* not currently using */
+                                /* Address field (96:57) is never used as an
+                                   address (these are address bits 42:3) */
+        int rsvd_3:1;           /* must be zero */
+        /* bit 57 */
+                                /* address bits 27:4 are payload */
+                                /* these 24 bits become bytes 12-14 of msg */
+        int replied_to:1;       /* sent as 0 by the source to byte 12 */
+        /* bit 58 */
+
+        int payload_1a:5;       /* not currently used */
+        /* bits 63:59 */
+        int payload_1b:8;       /* not currently used */
+        /* bits 71:64 */
+        int payload_1c:8;       /* not currently used */
+        /* bits 79:72 */
+        int payload_1d:2;       /* not currently used */
+        /* bits 81:80 */
+
+        int rsvd_4:7;           /* must be zero */
+        /* bits 88:82 */
+        int sw_ack_flag:1;      /* software acknowledge flag */
+        /* bit 89 */
+                                /* INTD trasactions at destination are to
+                                   wait for software acknowledge */
+        int rsvd_5:6;           /* must be zero */
+        /* bits 95:90 */
+        int rsvd_6:5;           /* must be zero */
+        /* bits 100:96 */
+        int int_both:1;         /* if 1, interrupt both sockets on the blade */
+        /* bit 101*/
+        int fairness:3;         /* usually zero */
+        /* bits 104:102 */
+        int multilevel:1;       /* multi-level multicast format */
+        /* bit 105 */
+                                /* 0 for TLB: endpoint multi-unicast messages */
+        int chaining:1;         /* next descriptor is part of this activation*/
+        /* bit 106 */
+        int rsvd_7:21;          /* must be zero */
+        /* bits 127:107 */
+};
+
+/*
+ * The activation descriptor:
+ * The format of the message to send, plus all accompanying control
+ * Should be 64 bytes
+ */
+struct bau_desc {
+        struct bau_target_nodemask distribution;
+        /*
+         * message template, consisting of header and payload:
+         */
+        struct bau_msg_header header;
+        struct bau_msg_payload payload;
+};
+/*
+ *   -payload--    ---------header------
+ *   bytes 0-11    bits 41-56  bits 58-81
+ *       A           B  (2)      C (3)
+ *
+ *            A/B/C are moved to:
+ *       A            C          B
+ *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
+ *   ------------payload queue-----------
+ */
+
+/*
+ * The payload queue on the destination side is an array of these.
+ * With BAU_MISC_CONTROL set for software acknowledge mode, the messages
+ * are 32 bytes (2 micropackets) (256 bits) in length, but contain only 17
+ * bytes of usable data, including the sw ack vector in byte 15 (bits 127:120)
+ * (12 bytes come from bau_msg_payload, 3 from payload_1, 2 from
+ *  sw_ack_vector and payload_2)
+ * "Enabling Software Acknowledgment mode (see Section 4.3.3 Software
+ *  Acknowledge Processing) also selects 32 byte (17 bytes usable) payload
+ *  operation."
+ */
+struct bau_payload_queue_entry {
+        unsigned long address;          /* signifies a page or all TLB's
+                                                of the cpu */
+        /* 64 bits, bytes 0-7 */
+
+        unsigned short sending_cpu;     /* cpu that sent the message */
+        /* 16 bits, bytes 8-9 */
+
+        unsigned short acknowledge_count; /* filled in by destination */
+        /* 16 bits, bytes 10-11 */
+
+        unsigned short replied_to:1;    /* sent as 0 by the source */
+        /* 1 bit */
+        unsigned short unused1:7;       /* not currently using */
+        /* 7 bits: byte 12) */
+
+        unsigned char unused2[2];       /* not currently using */
+        /* bytes 13-14 */
+
+        unsigned char sw_ack_vector;    /* filled in by the hardware */
+        /* byte 15 (bits 127:120) */
+
+        unsigned char unused4[3];       /* not currently using bytes 17-19 */
+        /* bytes 17-19 */
+
+        int number_of_cpus;             /* filled in at destination */
+        /* 32 bits, bytes 20-23 (aligned) */
+
+        unsigned char unused5[8];       /* not using */
+        /* bytes 24-31 */
+};
+
+/*
+ * one for every slot in the destination payload queue
+ */
+struct bau_msg_status {
+        struct bau_local_cpumask seen_by;       /* map of cpu's */
+};
+
+/*
+ * one for every slot in the destination software ack resources
+ */
+struct bau_sw_ack_status {
+        struct bau_payload_queue_entry *msg;    /* associated message */
+        int watcher;                            /* cpu monitoring, or -1 */
+};
+
+/*
+ * one on every node and per-cpu; to locate the software tables
+ */
+struct bau_control {
+        struct bau_desc *descriptor_base;
+        struct bau_payload_queue_entry *bau_msg_head;
+        struct bau_payload_queue_entry *va_queue_first;
+        struct bau_payload_queue_entry *va_queue_last;
+        struct bau_msg_status *msg_statuses;
+        int *watching; /* pointer to array */
+};
+
+/*
+ * This structure is allocated per_cpu for UV TLB shootdown statistics.
+ */
+struct ptc_stats {
+        unsigned long ptc_i;    /* number of IPI-style flushes */
+        unsigned long requestor;        /* number of nodes this cpu sent to */
+        unsigned long requestee;        /* times cpu was remotely requested */
+        unsigned long alltlb;   /* times all tlb's on this cpu were flushed */
+        unsigned long onetlb;   /* times just one tlb on this cpu was flushed */
+        unsigned long s_retry;  /* retries on source side timeouts */
+        unsigned long d_retry;  /* retries on destination side timeouts */
+        unsigned long sflush;   /* cycles spent in uv_flush_tlb_others */
+        unsigned long dflush;   /* cycles spent on destination side */
+        unsigned long retriesok; /* successes on retries */
+        unsigned long nomsg;    /* interrupts with no message */
+        unsigned long multmsg;  /* interrupts with multiple messages */
+        unsigned long ntargeted;/* nodes targeted */
+};
+
+static inline int bau_node_isset(int node, struct bau_target_nodemask *dstp)
+{
+        return constant_test_bit(node, &dstp->bits[0]);
+}
+static inline void bau_node_set(int node, struct bau_target_nodemask *dstp)
+{
+        __set_bit(node, &dstp->bits[0]);
+}
+static inline void bau_nodes_clear(struct bau_target_nodemask *dstp, int nbits)
+{
+        bitmap_zero(&dstp->bits[0], nbits);
+}
+
+static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
+{
+        bitmap_zero(&dstp->bits, nbits);
+}
+
+#define cpubit_isset(cpu, bau_local_cpumask) \
+        test_bit((cpu), (bau_local_cpumask).bits)
+
+extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long);
+extern void uv_bau_message_intr1(void);
+extern void uv_bau_timeout_intr1(void);
+
+#endif /* ASM_X86__UV__UV_BAU_H */
diff --git a/include/asm-x86/uv/uv_hub.h b/include/asm-x86/uv/uv_hub.h
index 26b9240d1e23..bdb5b01afbf5 100644
--- a/include/asm-x86/uv/uv_hub.h
+++ b/include/asm-x86/uv/uv_hub.h
@@ -5,11 +5,11 @@
  *
  * SGI UV architectural definitions
  *
- * Copyright (C) 2007 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
-#ifndef __ASM_X86_UV_HUB_H__
-#define __ASM_X86_UV_HUB_H__
+#ifndef ASM_X86__UV__UV_HUB_H
+#define ASM_X86__UV__UV_HUB_H
 
 #include <linux/numa.h>
 #include <linux/percpu.h>
@@ -20,26 +20,49 @@
 /*
  * Addressing Terminology
  *
- *      NASID - network ID of a router, Mbrick or Cbrick. Nasid values of
- *              routers always have low bit of 1, C/MBricks have low bit
- *              equal to 0. Most addressing macros that target UV hub chips
- *              right shift the NASID by 1 to exclude the always-zero bit.
+ *      M       - The low M bits of a physical address represent the offset
+ *                into the blade local memory. RAM memory on a blade is physically
+ *                contiguous (although various IO spaces may punch holes in
+ *                it)..
  *
- *      SNASID - NASID right shifted by 1 bit.
+ *      N       - Number of bits in the node portion of a socket physical
+ *                address.
+ *
+ *      NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
+ *                routers always have low bit of 1, C/MBricks have low bit
+ *                equal to 0. Most addressing macros that target UV hub chips
+ *                right shift the NASID by 1 to exclude the always-zero bit.
+ *                NASIDs contain up to 15 bits.
+ *
+ *      GNODE   - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
+ *                of nasids.
+ *
+ *      PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
+ *                of the nasid for socket usage.
+ *
+ *
+ *  NumaLink Global Physical Address Format:
+ *  +--------------------------------+---------------------+
+ *  |00..000|      GNODE             |      NodeOffset     |
+ *  +--------------------------------+---------------------+
+ *          |<-------53 - M bits --->|<--------M bits ----->
+ *
+ *      M - number of node offset bits (35 .. 40)
  *
  *
  *  Memory/UV-HUB Processor Socket Address Format:
- *  +--------+---------------+---------------------+
- *  |00..0000|    SNASID     |      NodeOffset     |
- *  +--------+---------------+---------------------+
- *           <--- N bits --->|<--------M bits ----->
+ *  +----------------+---------------+---------------------+
+ *  |00..000000000000|   PNODE       |      NodeOffset     |
+ *  +----------------+---------------+---------------------+
+ *                   <--- N bits --->|<--------M bits ----->
  *
- *      M number of node offset bits (35 .. 40)
- *      N number of SNASID bits (0 .. 10)
+ *      M - number of node offset bits (35 .. 40)
+ *      N - number of PNODE bits (0 .. 10)
  *
  *              Note: M + N cannot currently exceed 44 (x86_64) or 46 (IA64).
  *              The actual values are configuration dependent and are set at
- *              boot time
+ *              boot time. M & N values are set by the hardware/BIOS at boot.
+ *
  *
  * APICID format
  *      NOTE!!!!!! This is the current format of the APICID. However, code
@@ -48,14 +71,14 @@
  *
  *              1111110000000000
  *              5432109876543210
- *              nnnnnnnnnnlc0cch
+ *              pppppppppplc0cch
  *              sssssssssss
  *
- *                      n  = snasid bits
+ *                      p  = pnode bits
  *                      l =  socket number on board
  *                      c  = core
  *                      h  = hyperthread
- *                      s  = bits that are in the socket CSR
+ *                      s  = bits that are in the SOCKET_ID CSR
  *
  *      Note: Processor only supports 12 bits in the APICID register. The ACPI
  *            tables hold all 16 bits. Software needs to be aware of this.
@@ -74,7 +97,7 @@
  * This value is also the value of the maximum number of non-router NASIDs
  * in the numalink fabric.
  *
- * NOTE: a brick may be 1 or 2 OS nodes. Don't get these confused.
+ * NOTE: a brick may contain 1 or 2 OS nodes. Don't get these confused.
  */
 #define UV_MAX_NUMALINK_BLADES  16384
 
@@ -96,8 +119,12 @@
  */
 struct uv_hub_info_s {
         unsigned long   global_mmr_base;
-        unsigned short  local_nasid;
-        unsigned short  gnode_upper;
+        unsigned long   gpa_mask;
+        unsigned long   gnode_upper;
+        unsigned long   lowmem_remap_top;
+        unsigned long   lowmem_remap_base;
+        unsigned short  pnode;
+        unsigned short  pnode_mask;
         unsigned short  coherency_domain_number;
         unsigned short  numa_blade_id;
         unsigned char   blade_processor_id;
@@ -112,83 +139,126 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
  * Local & Global MMR space macros.
  *      Note: macros are intended to be used ONLY by inline functions
  *      in this file - not by other kernel code.
+ *              n -  NASID (full 15-bit global nasid)
+ *              g -  GNODE (full 15-bit global nasid, right shifted 1)
+ *              p -  PNODE (local part of nsids, right shifted 1)
  */
-#define UV_SNASID(n)                    ((n) >> 1)
-#define UV_NASID(n)                     ((n) << 1)
+#define UV_NASID_TO_PNODE(n)            (((n) >> 1) & uv_hub_info->pnode_mask)
+#define UV_PNODE_TO_NASID(p)            (((p) << 1) | uv_hub_info->gnode_upper)
 
 #define UV_LOCAL_MMR_BASE               0xf4000000UL
 #define UV_GLOBAL_MMR32_BASE            0xf8000000UL
 #define UV_GLOBAL_MMR64_BASE            (uv_hub_info->global_mmr_base)
+#define UV_LOCAL_MMR_SIZE               (64UL * 1024 * 1024)
+#define UV_GLOBAL_MMR32_SIZE            (64UL * 1024 * 1024)
 
-#define UV_GLOBAL_MMR32_SNASID_MASK     0x3ff
-#define UV_GLOBAL_MMR32_SNASID_SHIFT    15
-#define UV_GLOBAL_MMR64_SNASID_SHIFT    26
+#define UV_GLOBAL_MMR32_PNODE_SHIFT     15
+#define UV_GLOBAL_MMR64_PNODE_SHIFT     26
 
-#define UV_GLOBAL_MMR32_NASID_BITS(n)                                   \
-                (((UV_SNASID(n) & UV_GLOBAL_MMR32_SNASID_MASK)) <<      \
-                (UV_GLOBAL_MMR32_SNASID_SHIFT))
+#define UV_GLOBAL_MMR32_PNODE_BITS(p)   ((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
-#define UV_GLOBAL_MMR64_NASID_BITS(n)                                   \
-        ((unsigned long)UV_SNASID(n) << UV_GLOBAL_MMR64_SNASID_SHIFT)
+#define UV_GLOBAL_MMR64_PNODE_BITS(p)                                   \
+        ((unsigned long)(p) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+
+#define UV_APIC_PNODE_SHIFT     6
+
+/*
+ * Macros for converting between kernel virtual addresses, socket local physical
+ * addresses, and UV global physical addresses.
+ *      Note: use the standard __pa() & __va() macros for converting
+ *            between socket virtual and socket physical addresses.
+ */
+
+/* socket phys RAM --> UV global physical address */
+static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
+{
+        if (paddr < uv_hub_info->lowmem_remap_top)
+                paddr += uv_hub_info->lowmem_remap_base;
+        return paddr | uv_hub_info->gnode_upper;
+}
+
+
+/* socket virtual --> UV global physical address */
+static inline unsigned long uv_gpa(void *v)
+{
+        return __pa(v) | uv_hub_info->gnode_upper;
+}
+
+/* socket virtual --> UV global physical address */
+static inline void *uv_vgpa(void *v)
+{
+        return (void *)uv_gpa(v);
+}
+
+/* UV global physical address --> socket virtual */
+static inline void *uv_va(unsigned long gpa)
+{
+        return __va(gpa & uv_hub_info->gpa_mask);
+}
+
+/* pnode, offset --> socket virtual */
+static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
+{
+        return __va(((unsigned long)pnode << uv_hub_info->m_val) | offset);
+}
 
-#define UV_APIC_NASID_SHIFT     6
 
 /*
- * Extract a NASID from an APICID (full apicid, not processor subset)
+ * Extract a PNODE from an APICID (full apicid, not processor subset)
  */
-static inline int uv_apicid_to_nasid(int apicid)
+static inline int uv_apicid_to_pnode(int apicid)
 {
-        return (UV_NASID(apicid >> UV_APIC_NASID_SHIFT));
+        return (apicid >> UV_APIC_PNODE_SHIFT);
 }
 
 /*
  * Access global MMRs using the low memory MMR32 space. This region supports
  * faster MMR access but not all MMRs are accessible in this space.
  */
-static inline unsigned long *uv_global_mmr32_address(int nasid,
+static inline unsigned long *uv_global_mmr32_address(int pnode,
                                 unsigned long offset)
 {
         return __va(UV_GLOBAL_MMR32_BASE |
-                       UV_GLOBAL_MMR32_NASID_BITS(nasid) | offset);
+                       UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr32(int nasid, unsigned long offset,
+static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
                                  unsigned long val)
 {
-        *uv_global_mmr32_address(nasid, offset) = val;
+        *uv_global_mmr32_address(pnode, offset) = val;
 }
 
-static inline unsigned long uv_read_global_mmr32(int nasid,
+static inline unsigned long uv_read_global_mmr32(int pnode,
                                                  unsigned long offset)
 {
-        return *uv_global_mmr32_address(nasid, offset);
+        return *uv_global_mmr32_address(pnode, offset);
 }
 
 /*
  * Access Global MMR space using the MMR space located at the top of physical
  * memory.
  */
-static inline unsigned long *uv_global_mmr64_address(int nasid,
+static inline unsigned long *uv_global_mmr64_address(int pnode,
                                 unsigned long offset)
 {
         return __va(UV_GLOBAL_MMR64_BASE |
-                       UV_GLOBAL_MMR64_NASID_BITS(nasid) | offset);
+                    UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr64(int nasid, unsigned long offset,
+static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
                                 unsigned long val)
 {
-        *uv_global_mmr64_address(nasid, offset) = val;
+        *uv_global_mmr64_address(pnode, offset) = val;
 }
 
-static inline unsigned long uv_read_global_mmr64(int nasid,
+static inline unsigned long uv_read_global_mmr64(int pnode,
                                                  unsigned long offset)
 {
-        return *uv_global_mmr64_address(nasid, offset);
+        return *uv_global_mmr64_address(pnode, offset);
 }
 
 /*
- * Access node local MMRs. Faster than using global space but only local MMRs
+ * Access hub local MMRs. Faster than using global space but only local MMRs
  * are accessible.
  */
 static inline unsigned long *uv_local_mmr_address(unsigned long offset)
@@ -207,15 +277,15 @@ static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
 }
 
 /*
- * Structures and definitions for converting between cpu, node, and blade
+ * Structures and definitions for converting between cpu, node, pnode, and blade
  * numbers.
  */
 struct uv_blade_info {
-        unsigned short  nr_posible_cpus;
+        unsigned short  nr_possible_cpus;
         unsigned short  nr_online_cpus;
-        unsigned short  nasid;
+        unsigned short  pnode;
 };
-struct uv_blade_info *uv_blade_info;
+extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
 extern short *uv_cpu_to_blade;
 extern short uv_possible_blades;
@@ -244,16 +314,16 @@ static inline int uv_node_to_blade_id(int nid)
         return uv_node_to_blade[nid];
 }
 
-/* Convert a blade id to the NASID of the blade */
-static inline int uv_blade_to_nasid(int bid)
+/* Convert a blade id to the PNODE of the blade */
+static inline int uv_blade_to_pnode(int bid)
 {
-        return uv_blade_info[bid].nasid;
+        return uv_blade_info[bid].pnode;
 }
 
 /* Determine the number of possible cpus on a blade */
 static inline int uv_blade_nr_possible_cpus(int bid)
 {
-        return uv_blade_info[bid].nr_posible_cpus;
+        return uv_blade_info[bid].nr_possible_cpus;
 }
 
 /* Determine the number of online cpus on a blade */
@@ -262,16 +332,16 @@ static inline int uv_blade_nr_online_cpus(int bid)
         return uv_blade_info[bid].nr_online_cpus;
 }
 
-/* Convert a cpu id to the NASID of the blade containing the cpu */
-static inline int uv_cpu_to_nasid(int cpu)
+/* Convert a cpu id to the PNODE of the blade containing the cpu */
+static inline int uv_cpu_to_pnode(int cpu)
 {
-        return uv_blade_info[uv_cpu_to_blade_id(cpu)].nasid;
+        return uv_blade_info[uv_cpu_to_blade_id(cpu)].pnode;
 }
 
-/* Convert a node number to the NASID of the blade */
-static inline int uv_node_to_nasid(int nid)
+/* Convert a linux node number to the PNODE of the blade */
+static inline int uv_node_to_pnode(int nid)
 {
-        return uv_blade_info[uv_node_to_blade_id(nid)].nasid;
+        return uv_blade_info[uv_node_to_blade_id(nid)].pnode;
 }
 
 /* Maximum possible number of blades */
@@ -280,5 +350,5 @@ static inline int uv_num_possible_blades(void)
         return uv_possible_blades;
 }
 
-#endif /* __ASM_X86_UV_HUB__ */
+#endif /* ASM_X86__UV__UV_HUB_H */
 
diff --git a/include/asm-x86/uv/uv_mmrs.h b/include/asm-x86/uv/uv_mmrs.h
index 3b69fe6b6376..8b03d89d2459 100644
--- a/include/asm-x86/uv/uv_mmrs.h
+++ b/include/asm-x86/uv/uv_mmrs.h
@@ -8,20 +8,293 @@
  * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
-#ifndef __ASM_X86_UV_MMRS__
-#define __ASM_X86_UV_MMRS__
+#ifndef ASM_X86__UV__UV_MMRS_H
+#define ASM_X86__UV__UV_MMRS_H
 
-/*
- *       AUTO GENERATED - Do not edit
- */
+#define UV_MMR_ENABLE           (1UL << 63)
+
+/* ========================================================================= */
+/*                           UVH_BAU_DATA_CONFIG                             */
+/* ========================================================================= */
+#define UVH_BAU_DATA_CONFIG 0x61680UL
+#define UVH_BAU_DATA_CONFIG_32 0x0438
+
+#define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0
+#define UVH_BAU_DATA_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_BAU_DATA_CONFIG_DM_SHFT 8
+#define UVH_BAU_DATA_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_BAU_DATA_CONFIG_DESTMODE_SHFT 11
+#define UVH_BAU_DATA_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_BAU_DATA_CONFIG_STATUS_SHFT 12
+#define UVH_BAU_DATA_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_BAU_DATA_CONFIG_P_SHFT 13
+#define UVH_BAU_DATA_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_BAU_DATA_CONFIG_T_SHFT 15
+#define UVH_BAU_DATA_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_BAU_DATA_CONFIG_M_SHFT 16
+#define UVH_BAU_DATA_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_BAU_DATA_CONFIG_APIC_ID_SHFT 32
+#define UVH_BAU_DATA_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_bau_data_config_u {
+    unsigned long       v;
+    struct uvh_bau_data_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_EVENT_OCCURRED0                             */
+/* ========================================================================= */
+#define UVH_EVENT_OCCURRED0 0x70000UL
+#define UVH_EVENT_OCCURRED0_32 0x005e8
+
+#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UVH_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
+#define UVH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
+#define UVH_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
+#define UVH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
+#define UVH_EVENT_OCCURRED0_LH_HCERR_SHFT 3
+#define UVH_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
+#define UVH_EVENT_OCCURRED0_RH_HCERR_SHFT 4
+#define UVH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
+#define UVH_EVENT_OCCURRED0_XN_HCERR_SHFT 5
+#define UVH_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
+#define UVH_EVENT_OCCURRED0_SI_HCERR_SHFT 6
+#define UVH_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
+#define UVH_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
+#define UVH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
+#define UVH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
+#define UVH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UVH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
+#define UVH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UVH_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
+#define UVH_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
+#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UVH_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
+#define UVH_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
+#define UVH_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
+#define UVH_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
+#define UVH_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
+#define UVH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
+#define UVH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
+#define UVH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UVH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
+#define UVH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UVH_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
+#define UVH_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
+#define UVH_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
+#define UVH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
+#define UVH_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
+#define UVH_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
+#define UVH_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
+#define UVH_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
+#define UVH_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
+#define UVH_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UVH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
+#define UVH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UVH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
+#define UVH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
+#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
+#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UVH_EVENT_OCCURRED0_LTC_INT_SHFT 43
+#define UVH_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
+#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
+#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+#define UVH_EVENT_OCCURRED0_IPI_INT_SHFT 45
+#define UVH_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
+#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
+#define UVH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
+#define UVH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
+#define UVH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
+#define UVH_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
+#define UVH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC0_SHFT 51
+#define UVH_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC1_SHFT 52
+#define UVH_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC2_SHFT 53
+#define UVH_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC3_SHFT 54
+#define UVH_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
+#define UVH_EVENT_OCCURRED0_BAU_DATA_SHFT 55
+#define UVH_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
+#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
+#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+union uvh_event_occurred0_u {
+    unsigned long       v;
+    struct uvh_event_occurred0_s {
+        unsigned long   lb_hcerr             :  1;  /* RW, W1C */
+        unsigned long   gr0_hcerr            :  1;  /* RW, W1C */
+        unsigned long   gr1_hcerr            :  1;  /* RW, W1C */
+        unsigned long   lh_hcerr             :  1;  /* RW, W1C */
+        unsigned long   rh_hcerr             :  1;  /* RW, W1C */
+        unsigned long   xn_hcerr             :  1;  /* RW, W1C */
+        unsigned long   si_hcerr             :  1;  /* RW, W1C */
+        unsigned long   lb_aoerr0            :  1;  /* RW, W1C */
+        unsigned long   gr0_aoerr0           :  1;  /* RW, W1C */
+        unsigned long   gr1_aoerr0           :  1;  /* RW, W1C */
+        unsigned long   lh_aoerr0            :  1;  /* RW, W1C */
+        unsigned long   rh_aoerr0            :  1;  /* RW, W1C */
+        unsigned long   xn_aoerr0            :  1;  /* RW, W1C */
+        unsigned long   si_aoerr0            :  1;  /* RW, W1C */
+        unsigned long   lb_aoerr1            :  1;  /* RW, W1C */
+        unsigned long   gr0_aoerr1           :  1;  /* RW, W1C */
+        unsigned long   gr1_aoerr1           :  1;  /* RW, W1C */
+        unsigned long   lh_aoerr1            :  1;  /* RW, W1C */
+        unsigned long   rh_aoerr1            :  1;  /* RW, W1C */
+        unsigned long   xn_aoerr1            :  1;  /* RW, W1C */
+        unsigned long   si_aoerr1            :  1;  /* RW, W1C */
+        unsigned long   rh_vpi_int           :  1;  /* RW, W1C */
+        unsigned long   system_shutdown_int  :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_0         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_1         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_2         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_3         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_4         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_5         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_6         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_7         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_8         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_9         :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_10        :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_11        :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_12        :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_13        :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_14        :  1;  /* RW, W1C */
+        unsigned long   lb_irq_int_15        :  1;  /* RW, W1C */
+        unsigned long   l1_nmi_int           :  1;  /* RW, W1C */
+        unsigned long   stop_clock           :  1;  /* RW, W1C */
+        unsigned long   asic_to_l1           :  1;  /* RW, W1C */
+        unsigned long   l1_to_asic           :  1;  /* RW, W1C */
+        unsigned long   ltc_int              :  1;  /* RW, W1C */
+        unsigned long   la_seq_trigger       :  1;  /* RW, W1C */
+        unsigned long   ipi_int              :  1;  /* RW, W1C */
+        unsigned long   extio_int0           :  1;  /* RW, W1C */
+        unsigned long   extio_int1           :  1;  /* RW, W1C */
+        unsigned long   extio_int2           :  1;  /* RW, W1C */
+        unsigned long   extio_int3           :  1;  /* RW, W1C */
+        unsigned long   profile_int          :  1;  /* RW, W1C */
+        unsigned long   rtc0                 :  1;  /* RW, W1C */
+        unsigned long   rtc1                 :  1;  /* RW, W1C */
+        unsigned long   rtc2                 :  1;  /* RW, W1C */
+        unsigned long   rtc3                 :  1;  /* RW, W1C */
+        unsigned long   bau_data             :  1;  /* RW, W1C */
+        unsigned long   power_management_req :  1;  /* RW, W1C */
+        unsigned long   rsvd_57_63           :  7;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                        UVH_EVENT_OCCURRED0_ALIAS                          */
+/* ========================================================================= */
+#define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL
+#define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPB                                */
+/* ========================================================================= */
+#define UVH_INT_CMPB 0x22080UL
+
+#define UVH_INT_CMPB_REAL_TIME_CMPB_SHFT 0
+#define UVH_INT_CMPB_REAL_TIME_CMPB_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpb_u {
+    unsigned long       v;
+    struct uvh_int_cmpb_s {
+        unsigned long   real_time_cmpb : 56;  /* RW */
+        unsigned long   rsvd_56_63     :  8;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPC                                */
+/* ========================================================================= */
+#define UVH_INT_CMPC 0x22100UL
+
+#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0
+#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpc_u {
+    unsigned long       v;
+    struct uvh_int_cmpc_s {
+        unsigned long   real_time_cmpc : 56;  /* RW */
+        unsigned long   rsvd_56_63     :  8;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPD                                */
+/* ========================================================================= */
+#define UVH_INT_CMPD 0x22180UL
 
- #define UV_MMR_ENABLE          (1UL << 63)
+#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0
+#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpd_u {
+    unsigned long       v;
+    struct uvh_int_cmpd_s {
+        unsigned long   real_time_cmpd : 56;  /* RW */
+        unsigned long   rsvd_56_63     :  8;  /*    */
+    } s;
+};
 
 /* ========================================================================= */
 /*                               UVH_IPI_INT                                 */
 /* ========================================================================= */
 #define UVH_IPI_INT 0x60500UL
-#define UVH_IPI_INT_32 0x0360
+#define UVH_IPI_INT_32 0x0348
 
 #define UVH_IPI_INT_VECTOR_SHFT 0
 #define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL
@@ -51,7 +324,7 @@ union uvh_ipi_int_u {
 /*                   UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009f0
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009c0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -73,7 +346,7 @@ union uvh_lb_bau_intd_payload_queue_first_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009f8
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009c8
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -91,7 +364,7 @@ union uvh_lb_bau_intd_payload_queue_last_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x00a00
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x009d0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
@@ -109,6 +382,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u {
 /*                   UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE                    */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0x0a68
 
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
@@ -169,12 +443,13 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 /*                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS                 */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70
 
 /* ========================================================================= */
 /*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009d8
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009a8
 
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_MASK 0x000000000000003fUL
@@ -197,7 +472,7 @@ union uvh_lb_bau_sb_activation_control_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_0                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009e0
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009b0
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL
@@ -213,7 +488,7 @@ union uvh_lb_bau_sb_activation_status_0_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_1                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009e8
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009b8
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL
@@ -229,7 +504,7 @@ union uvh_lb_bau_sb_activation_status_1_u {
 /*                      UVH_LB_BAU_SB_DESCRIPTOR_BASE                        */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009d0
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009a0
 
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
@@ -248,6 +523,334 @@ union uvh_lb_bau_sb_descriptor_base_u {
 };
 
 /* ========================================================================= */
+/*                      UVH_LB_MCAST_AOERR0_RPT_ENABLE                       */
+/* ========================================================================= */
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE 0x50b20UL
+
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_SHFT 0
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_MASK 0x0000000000000001UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_SHFT 1
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_MASK 0x0000000000000002UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_SHFT 2
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_MASK 0x0000000000000004UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_SHFT 3
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_MASK 0x0000000000000008UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_SHFT 4
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_MASK 0x0000000000000010UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_SHFT 5
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_MASK 0x0000000000000020UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_SHFT 6
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_MASK 0x0000000000000040UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_SHFT 7
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_MASK 0x0000000000000080UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_SHFT 8
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_MASK 0x0000000000000100UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_SHFT 9
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_MASK 0x0000000000000200UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_SHFT 10
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_MASK 0x0000000000000400UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_SHFT 11
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_MASK 0x0000000000000800UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_SHFT 12
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_MASK 0x0000000000001000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_SHFT 13
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_MASK 0x0000000000002000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_SHFT 14
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_MASK 0x0000000000004000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_SHFT 15
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_MASK 0x0000000000008000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_SHFT 16
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_MASK 0x0000000000010000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_SHFT 17
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_MASK 0x0000000000020000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_SHFT 18
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_MASK 0x0000000000040000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_SHFT 19
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_MASK 0x0000000000080000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_SHFT 20
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_MASK 0x0000000000100000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_SHFT 21
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_MASK 0x0000000000200000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_SHFT 22
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_MASK 0x0000000000400000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_SHFT 23
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_MASK 0x0000000000800000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_SHFT 24
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_MASK 0x0000000001000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_SHFT 25
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_MASK 0x0000000002000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_SHFT 26
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_MASK 0x0000000004000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_SHFT 27
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_MASK 0x0000000008000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_SHFT 28
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_MASK 0x0000000010000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_SHFT 29
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_MASK 0x0000000020000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_SHFT 30
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_MASK 0x0000000040000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_SHFT 31
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_MASK 0x0000000080000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_SHFT 32
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_MASK 0x0000000100000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_SHFT 33
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_MASK 0x0000000200000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_SHFT 34
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_MASK 0x0000000400000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_SHFT 35
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_MASK 0x0000000800000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_SHFT 36
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_MASK 0x0000001000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_SHFT 37
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_MASK 0x0000002000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_SHFT 38
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_MASK 0x0000004000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_SHFT 39
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_MASK 0x0000008000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_SHFT 40
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_MASK 0x0000010000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_SHFT 41
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_MASK 0x0000020000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_SHFT 42
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_MASK 0x0000040000000000UL
+
+union uvh_lb_mcast_aoerr0_rpt_enable_u {
+    unsigned long       v;
+    struct uvh_lb_mcast_aoerr0_rpt_enable_s {
+        unsigned long   mcast_obese_msg                         :  1;  /* RW */
+        unsigned long   mcast_data_sb_err                       :  1;  /* RW */
+        unsigned long   mcast_nack_buff_parity                  :  1;  /* RW */
+        unsigned long   mcast_timeout                           :  1;  /* RW */
+        unsigned long   mcast_inactive_reply                    :  1;  /* RW */
+        unsigned long   mcast_upgrade_error                     :  1;  /* RW */
+        unsigned long   mcast_reg_count_underflow               :  1;  /* RW */
+        unsigned long   mcast_rep_obese_msg                     :  1;  /* RW */
+        unsigned long   ucache_req_runt_msg                     :  1;  /* RW */
+        unsigned long   ucache_req_obese_msg                    :  1;  /* RW */
+        unsigned long   ucache_req_data_sb_err                  :  1;  /* RW */
+        unsigned long   ucache_rep_runt_msg                     :  1;  /* RW */
+        unsigned long   ucache_rep_obese_msg                    :  1;  /* RW */
+        unsigned long   ucache_rep_data_sb_err                  :  1;  /* RW */
+        unsigned long   ucache_rep_command_err                  :  1;  /* RW */
+        unsigned long   ucache_pend_timeout                     :  1;  /* RW */
+        unsigned long   macc_req_runt_msg                       :  1;  /* RW */
+        unsigned long   macc_req_obese_msg                      :  1;  /* RW */
+        unsigned long   macc_req_data_sb_err                    :  1;  /* RW */
+        unsigned long   macc_rep_runt_msg                       :  1;  /* RW */
+        unsigned long   macc_rep_obese_msg                      :  1;  /* RW */
+        unsigned long   macc_rep_data_sb_err                    :  1;  /* RW */
+        unsigned long   macc_amo_timeout                        :  1;  /* RW */
+        unsigned long   macc_put_timeout                        :  1;  /* RW */
+        unsigned long   macc_spurious_event                     :  1;  /* RW */
+        unsigned long   ioh_destination_table_parity            :  1;  /* RW */
+        unsigned long   get_had_error_reply                     :  1;  /* RW */
+        unsigned long   get_timeout                             :  1;  /* RW */
+        unsigned long   lock_manager_had_error_reply            :  1;  /* RW */
+        unsigned long   put_had_error_reply                     :  1;  /* RW */
+        unsigned long   put_timeout                             :  1;  /* RW */
+        unsigned long   sb_activation_overrun                   :  1;  /* RW */
+        unsigned long   completed_gb_activation_had_error_reply :  1;  /* RW */
+        unsigned long   completed_gb_activation_timeout         :  1;  /* RW */
+        unsigned long   descriptor_buffer_0_parity              :  1;  /* RW */
+        unsigned long   descriptor_buffer_1_parity              :  1;  /* RW */
+        unsigned long   socket_destination_table_parity         :  1;  /* RW */
+        unsigned long   bau_reply_payload_corruption            :  1;  /* RW */
+        unsigned long   io_port_destination_table_parity        :  1;  /* RW */
+        unsigned long   intd_soft_ack_timeout                   :  1;  /* RW */
+        unsigned long   int_rep_obese_msg                       :  1;  /* RW */
+        unsigned long   int_rep_command_err                     :  1;  /* RW */
+        unsigned long   int_timeout                             :  1;  /* RW */
+        unsigned long   rsvd_43_63                              : 21;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                          UVH_LOCAL_INT0_CONFIG                            */
+/* ========================================================================= */
+#define UVH_LOCAL_INT0_CONFIG 0x61000UL
+
+#define UVH_LOCAL_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_LOCAL_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_LOCAL_INT0_CONFIG_DM_SHFT 8
+#define UVH_LOCAL_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_LOCAL_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_LOCAL_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_LOCAL_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_LOCAL_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_LOCAL_INT0_CONFIG_P_SHFT 13
+#define UVH_LOCAL_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_LOCAL_INT0_CONFIG_T_SHFT 15
+#define UVH_LOCAL_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_LOCAL_INT0_CONFIG_M_SHFT 16
+#define UVH_LOCAL_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_LOCAL_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_LOCAL_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_local_int0_config_u {
+    unsigned long       v;
+    struct uvh_local_int0_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                          UVH_LOCAL_INT0_ENABLE                            */
+/* ========================================================================= */
+#define UVH_LOCAL_INT0_ENABLE 0x65000UL
+
+#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_SHFT 0
+#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_MASK 0x0000000000000001UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_SHFT 1
+#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_MASK 0x0000000000000002UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_SHFT 2
+#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_MASK 0x0000000000000004UL
+#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_SHFT 3
+#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_MASK 0x0000000000000008UL
+#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_SHFT 4
+#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_MASK 0x0000000000000010UL
+#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_SHFT 5
+#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_MASK 0x0000000000000020UL
+#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_SHFT 6
+#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_MASK 0x0000000000000040UL
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_SHFT 7
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_MASK 0x0000000000000080UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_SHFT 8
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_SHFT 9
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_SHFT 10
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_MASK 0x0000000000000400UL
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_SHFT 11
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_MASK 0x0000000000000800UL
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_SHFT 12
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_MASK 0x0000000000001000UL
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_SHFT 13
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_MASK 0x0000000000002000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_SHFT 14
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_MASK 0x0000000000004000UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_SHFT 15
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_SHFT 16
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_SHFT 17
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_MASK 0x0000000000020000UL
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_SHFT 18
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_MASK 0x0000000000040000UL
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_SHFT 19
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_MASK 0x0000000000080000UL
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_SHFT 20
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_MASK 0x0000000000100000UL
+#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_SHFT 21
+#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_SHFT 23
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_SHFT 24
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_SHFT 25
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_SHFT 26
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_SHFT 27
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_SHFT 28
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_SHFT 29
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_SHFT 30
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_SHFT 31
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_SHFT 32
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_SHFT 33
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_SHFT 34
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_SHFT 35
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_SHFT 36
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_SHFT 37
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_SHFT 38
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_SHFT 39
+#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_SHFT 40
+#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_SHFT 41
+#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_SHFT 42
+#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LTC_INT_SHFT 43
+#define UVH_LOCAL_INT0_ENABLE_LTC_INT_MASK 0x0000080000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_SHFT 44
+#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+
+union uvh_local_int0_enable_u {
+    unsigned long       v;
+    struct uvh_local_int0_enable_s {
+        unsigned long   lb_hcerr            :  1;  /* RW */
+        unsigned long   gr0_hcerr           :  1;  /* RW */
+        unsigned long   gr1_hcerr           :  1;  /* RW */
+        unsigned long   lh_hcerr            :  1;  /* RW */
+        unsigned long   rh_hcerr            :  1;  /* RW */
+        unsigned long   xn_hcerr            :  1;  /* RW */
+        unsigned long   si_hcerr            :  1;  /* RW */
+        unsigned long   lb_aoerr0           :  1;  /* RW */
+        unsigned long   gr0_aoerr0          :  1;  /* RW */
+        unsigned long   gr1_aoerr0          :  1;  /* RW */
+        unsigned long   lh_aoerr0           :  1;  /* RW */
+        unsigned long   rh_aoerr0           :  1;  /* RW */
+        unsigned long   xn_aoerr0           :  1;  /* RW */
+        unsigned long   si_aoerr0           :  1;  /* RW */
+        unsigned long   lb_aoerr1           :  1;  /* RW */
+        unsigned long   gr0_aoerr1          :  1;  /* RW */
+        unsigned long   gr1_aoerr1          :  1;  /* RW */
+        unsigned long   lh_aoerr1           :  1;  /* RW */
+        unsigned long   rh_aoerr1           :  1;  /* RW */
+        unsigned long   xn_aoerr1           :  1;  /* RW */
+        unsigned long   si_aoerr1           :  1;  /* RW */
+        unsigned long   rh_vpi_int          :  1;  /* RW */
+        unsigned long   system_shutdown_int :  1;  /* RW */
+        unsigned long   lb_irq_int_0        :  1;  /* RW */
+        unsigned long   lb_irq_int_1        :  1;  /* RW */
+        unsigned long   lb_irq_int_2        :  1;  /* RW */
+        unsigned long   lb_irq_int_3        :  1;  /* RW */
+        unsigned long   lb_irq_int_4        :  1;  /* RW */
+        unsigned long   lb_irq_int_5        :  1;  /* RW */
+        unsigned long   lb_irq_int_6        :  1;  /* RW */
+        unsigned long   lb_irq_int_7        :  1;  /* RW */
+        unsigned long   lb_irq_int_8        :  1;  /* RW */
+        unsigned long   lb_irq_int_9        :  1;  /* RW */
+        unsigned long   lb_irq_int_10       :  1;  /* RW */
+        unsigned long   lb_irq_int_11       :  1;  /* RW */
+        unsigned long   lb_irq_int_12       :  1;  /* RW */
+        unsigned long   lb_irq_int_13       :  1;  /* RW */
+        unsigned long   lb_irq_int_14       :  1;  /* RW */
+        unsigned long   lb_irq_int_15       :  1;  /* RW */
+        unsigned long   l1_nmi_int          :  1;  /* RW */
+        unsigned long   stop_clock          :  1;  /* RW */
+        unsigned long   asic_to_l1          :  1;  /* RW */
+        unsigned long   l1_to_asic          :  1;  /* RW */
+        unsigned long   ltc_int             :  1;  /* RW */
+        unsigned long   la_seq_trigger      :  1;  /* RW */
+        unsigned long   rsvd_45_63          : 19;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
 /*                               UVH_NODE_ID                                 */
 /* ========================================================================= */
 #define UVH_NODE_ID 0x0UL
@@ -284,14 +887,101 @@ union uvh_node_id_u {
 };
 
 /* ========================================================================= */
+/*                          UVH_NODE_PRESENT_TABLE                           */
+/* ========================================================================= */
+#define UVH_NODE_PRESENT_TABLE 0x1400UL
+#define UVH_NODE_PRESENT_TABLE_DEPTH 16
+
+#define UVH_NODE_PRESENT_TABLE_NODES_SHFT 0
+#define UVH_NODE_PRESENT_TABLE_NODES_MASK 0xffffffffffffffffUL
+
+union uvh_node_present_table_u {
+    unsigned long       v;
+    struct uvh_node_present_table_s {
+        unsigned long   nodes : 64;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_alias210_redirect_config_0_mmr_s {
+        unsigned long   rsvd_0_23 : 24;  /*    */
+        unsigned long   dest_base : 22;  /* RW */
+        unsigned long   rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_alias210_redirect_config_1_mmr_s {
+        unsigned long   rsvd_0_23 : 24;  /*    */
+        unsigned long   dest_base : 22;  /* RW */
+        unsigned long   rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_alias210_redirect_config_2_mmr_s {
+        unsigned long   rsvd_0_23 : 24;  /*    */
+        unsigned long   dest_base : 22;  /* RW */
+        unsigned long   rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR                      */
+/* ========================================================================= */
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR 0x1600020UL
+
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_cfg_overlay_config_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_cfg_overlay_config_mmr_s {
+        unsigned long   rsvd_0_25: 26;  /*    */
+        unsigned long   base   : 20;  /* RW */
+        unsigned long   rsvd_46_62: 17;  /*    */
+        unsigned long   enable :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                    UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
 
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 46
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0000400000000000UL
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
@@ -302,8 +992,9 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
     struct uvh_rh_gam_gru_overlay_config_mmr_s {
         unsigned long   rsvd_0_27: 28;  /*    */
         unsigned long   base   : 18;  /* RW */
+        unsigned long   rsvd_46_47:  2;  /*    */
         unsigned long   gr4    :  1;  /* RW */
-        unsigned long   rsvd_47_51:  5;  /*    */
+        unsigned long   rsvd_49_51:  3;  /*    */
         unsigned long   n_gru  :  4;  /* RW */
         unsigned long   rsvd_56_62:  7;  /*    */
         unsigned long   enable :  1;  /* RW */
@@ -311,6 +1002,32 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 };
 
 /* ========================================================================= */
+/*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR                     */
+/* ========================================================================= */
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_mmioh_overlay_config_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_mmioh_overlay_config_mmr_s {
+        unsigned long   rsvd_0_29: 30;  /*    */
+        unsigned long   base   : 16;  /* RW */
+        unsigned long   m_io   :  6;  /* RW */
+        unsigned long   n_io   :  4;  /* RW */
+        unsigned long   rsvd_56_62:  7;  /*    */
+        unsigned long   enable :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                    UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
@@ -336,7 +1053,7 @@ union uvh_rh_gam_mmr_overlay_config_mmr_u {
 /* ========================================================================= */
 /*                                 UVH_RTC                                   */
 /* ========================================================================= */
-#define UVH_RTC 0x28000UL
+#define UVH_RTC 0x340000UL
 
 #define UVH_RTC_REAL_TIME_CLOCK_SHFT 0
 #define UVH_RTC_REAL_TIME_CLOCK_MASK 0x00ffffffffffffffUL
@@ -350,6 +1067,139 @@ union uvh_rtc_u {
 };
 
 /* ========================================================================= */
+/*                           UVH_RTC1_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC1_INT_CONFIG 0x615c0UL
+
+#define UVH_RTC1_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC1_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC1_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC1_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC1_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC1_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC1_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC1_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC1_INT_CONFIG_P_SHFT 13
+#define UVH_RTC1_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC1_INT_CONFIG_T_SHFT 15
+#define UVH_RTC1_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC1_INT_CONFIG_M_SHFT 16
+#define UVH_RTC1_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC1_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC1_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc1_int_config_u {
+    unsigned long       v;
+    struct uvh_rtc1_int_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_RTC2_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC2_INT_CONFIG 0x61600UL
+
+#define UVH_RTC2_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC2_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC2_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC2_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC2_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC2_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC2_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC2_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC2_INT_CONFIG_P_SHFT 13
+#define UVH_RTC2_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC2_INT_CONFIG_T_SHFT 15
+#define UVH_RTC2_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC2_INT_CONFIG_M_SHFT 16
+#define UVH_RTC2_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC2_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC2_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc2_int_config_u {
+    unsigned long       v;
+    struct uvh_rtc2_int_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_RTC3_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC3_INT_CONFIG 0x61640UL
+
+#define UVH_RTC3_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC3_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC3_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC3_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC3_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC3_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC3_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC3_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC3_INT_CONFIG_P_SHFT 13
+#define UVH_RTC3_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC3_INT_CONFIG_T_SHFT 15
+#define UVH_RTC3_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC3_INT_CONFIG_M_SHFT 16
+#define UVH_RTC3_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC3_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC3_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc3_int_config_u {
+    unsigned long       v;
+    struct uvh_rtc3_int_config_s {
+        unsigned long   vector_  :  8;  /* RW */
+        unsigned long   dm       :  3;  /* RW */
+        unsigned long   destmode :  1;  /* RW */
+        unsigned long   status   :  1;  /* RO */
+        unsigned long   p        :  1;  /* RO */
+        unsigned long   rsvd_14  :  1;  /*    */
+        unsigned long   t        :  1;  /* RO */
+        unsigned long   m        :  1;  /* RW */
+        unsigned long   rsvd_17_31: 15;  /*    */
+        unsigned long   apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                            UVH_RTC_INC_RATIO                              */
+/* ========================================================================= */
+#define UVH_RTC_INC_RATIO 0x350000UL
+
+#define UVH_RTC_INC_RATIO_FRACTION_SHFT 0
+#define UVH_RTC_INC_RATIO_FRACTION_MASK 0x00000000000fffffUL
+#define UVH_RTC_INC_RATIO_RATIO_SHFT 20
+#define UVH_RTC_INC_RATIO_RATIO_MASK 0x0000000000700000UL
+
+union uvh_rtc_inc_ratio_u {
+    unsigned long       v;
+    struct uvh_rtc_inc_ratio_s {
+        unsigned long   fraction : 20;  /* RW */
+        unsigned long   ratio    :  3;  /* RW */
+        unsigned long   rsvd_23_63: 41;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
 /*                          UVH_SI_ADDR_MAP_CONFIG                           */
 /* ========================================================================= */
 #define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL
@@ -369,5 +1219,77 @@ union uvh_si_addr_map_config_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS0_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG 0xc80008UL
+
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias0_overlay_config_u {
+    unsigned long       v;
+    struct uvh_si_alias0_overlay_config_s {
+        unsigned long   rsvd_0_23: 24;  /*    */
+        unsigned long   base    :  8;  /* RW */
+        unsigned long   rsvd_32_47: 16;  /*    */
+        unsigned long   m_alias :  5;  /* RW */
+        unsigned long   rsvd_53_62: 10;  /*    */
+        unsigned long   enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS1_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG 0xc80010UL
+
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias1_overlay_config_u {
+    unsigned long       v;
+    struct uvh_si_alias1_overlay_config_s {
+        unsigned long   rsvd_0_23: 24;  /*    */
+        unsigned long   base    :  8;  /* RW */
+        unsigned long   rsvd_32_47: 16;  /*    */
+        unsigned long   m_alias :  5;  /* RW */
+        unsigned long   rsvd_53_62: 10;  /*    */
+        unsigned long   enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS2_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG 0xc80018UL
+
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias2_overlay_config_u {
+    unsigned long       v;
+    struct uvh_si_alias2_overlay_config_s {
+        unsigned long   rsvd_0_23: 24;  /*    */
+        unsigned long   base    :  8;  /* RW */
+        unsigned long   rsvd_32_47: 16;  /*    */
+        unsigned long   m_alias :  5;  /* RW */
+        unsigned long   rsvd_53_62: 10;  /*    */
+        unsigned long   enable  :  1;  /* RW */
+    } s;
+};
+
 
-#endif /* __ASM_X86_UV_MMRS__ */
+#endif /* ASM_X86__UV__UV_MMRS_H */
diff --git a/include/asm-x86/vdso.h b/include/asm-x86/vdso.h
index 86e085e003d2..4ab320913ea3 100644
--- a/include/asm-x86/vdso.h
+++ b/include/asm-x86/vdso.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_VDSO_H
-#define _ASM_X86_VDSO_H 1
+#ifndef ASM_X86__VDSO_H
+#define ASM_X86__VDSO_H
 
 #ifdef CONFIG_X86_64
 extern const char VDSO64_PRELINK[];
@@ -36,4 +36,12 @@ extern const char VDSO32_PRELINK[];
 extern void __user __kernel_sigreturn;
 extern void __user __kernel_rt_sigreturn;
 
-#endif  /* asm-x86/vdso.h */
+/*
+ * These symbols are defined by vdso32.S to mark the bounds
+ * of the ELF DSO images included therein.
+ */
+extern const char vdso32_int80_start, vdso32_int80_end;
+extern const char vdso32_syscall_start, vdso32_syscall_end;
+extern const char vdso32_sysenter_start, vdso32_sysenter_end;
+
+#endif /* ASM_X86__VDSO_H */
diff --git a/include/asm-x86/vga.h b/include/asm-x86/vga.h
index 0ccf804377e6..b9e493d07d07 100644
--- a/include/asm-x86/vga.h
+++ b/include/asm-x86/vga.h
@@ -4,8 +4,8 @@
  *      (c) 1998 Martin Mares <mj@ucw.cz>
  */
 
-#ifndef _LINUX_ASM_VGA_H_
-#define _LINUX_ASM_VGA_H_
+#ifndef ASM_X86__VGA_H
+#define ASM_X86__VGA_H
 
 /*
  *      On the PC, we can just recalculate addresses and then
@@ -17,4 +17,4 @@
 #define vga_readb(x) (*(x))
 #define vga_writeb(x, y) (*(y) = (x))
 
-#endif
+#endif /* ASM_X86__VGA_H */
diff --git a/include/asm-x86/vgtod.h b/include/asm-x86/vgtod.h
index 3301f0929342..38fd13364021 100644
--- a/include/asm-x86/vgtod.h
+++ b/include/asm-x86/vgtod.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_VGTOD_H
-#define _ASM_VGTOD_H 1
+#ifndef ASM_X86__VGTOD_H
+#define ASM_X86__VGTOD_H
 
 #include <asm/vsyscall.h>
 #include <linux/clocksource.h>
@@ -26,4 +26,4 @@ extern struct vsyscall_gtod_data __vsyscall_gtod_data
 __section_vsyscall_gtod_data;
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
-#endif
+#endif /* ASM_X86__VGTOD_H */
diff --git a/include/asm-x86/mach-visws/cobalt.h b/include/asm-x86/visws/cobalt.h
index 995258831b7f..9627a8fe84e9 100644
--- a/include/asm-x86/mach-visws/cobalt.h
+++ b/include/asm-x86/visws/cobalt.h
@@ -1,5 +1,5 @@
-#ifndef __I386_SGI_COBALT_H
-#define __I386_SGI_COBALT_H
+#ifndef ASM_X86__VISWS__COBALT_H
+#define ASM_X86__VISWS__COBALT_H
 
 #include <asm/fixmap.h>
 
@@ -122,4 +122,4 @@ extern char visws_board_type;
 
 extern char visws_board_rev;
 
-#endif /* __I386_SGI_COBALT_H */
+#endif /* ASM_X86__VISWS__COBALT_H */
diff --git a/include/asm-x86/mach-visws/lithium.h b/include/asm-x86/visws/lithium.h
index dfcd4f07ab85..b36d3b378c63 100644
--- a/include/asm-x86/mach-visws/lithium.h
+++ b/include/asm-x86/visws/lithium.h
@@ -1,5 +1,5 @@
-#ifndef __I386_SGI_LITHIUM_H
-#define __I386_SGI_LITHIUM_H
+#ifndef ASM_X86__VISWS__LITHIUM_H
+#define ASM_X86__VISWS__LITHIUM_H
 
 #include <asm/fixmap.h>
 
@@ -49,5 +49,5 @@ static inline unsigned short li_pcib_read16(unsigned long reg)
         return *((volatile unsigned short *)(LI_PCIB_VADDR+reg));
 }
 
-#endif
+#endif /* ASM_X86__VISWS__LITHIUM_H */
 
diff --git a/include/asm-x86/mach-visws/piix4.h b/include/asm-x86/visws/piix4.h
index 83ea4f46e419..61c938045ec9 100644
--- a/include/asm-x86/mach-visws/piix4.h
+++ b/include/asm-x86/visws/piix4.h
@@ -1,5 +1,5 @@
-#ifndef __I386_SGI_PIIX_H
-#define __I386_SGI_PIIX_H
+#ifndef ASM_X86__VISWS__PIIX4_H
+#define ASM_X86__VISWS__PIIX4_H
 
 /*
  * PIIX4 as used on SGI Visual Workstations
@@ -104,4 +104,4 @@
  */
 #define PIIX_GPI_STPCLK         0x4     // STPCLK signal routed back in
 
-#endif
+#endif /* ASM_X86__VISWS__PIIX4_H */
diff --git a/include/asm-x86/visws/sgivw.h b/include/asm-x86/visws/sgivw.h
new file mode 100644
index 000000000000..5fbf63e1003c
--- /dev/null
+++ b/include/asm-x86/visws/sgivw.h
@@ -0,0 +1,5 @@
+/*
+ * Frame buffer position and size:
+ */
+extern unsigned long sgivwfb_mem_phys;
+extern unsigned long sgivwfb_mem_size;
diff --git a/include/asm-x86/vm86.h b/include/asm-x86/vm86.h
index 074b357146df..998bd18eb737 100644
--- a/include/asm-x86/vm86.h
+++ b/include/asm-x86/vm86.h
@@ -1,5 +1,5 @@
-#ifndef _LINUX_VM86_H
-#define _LINUX_VM86_H
+#ifndef ASM_X86__VM86_H
+#define ASM_X86__VM86_H
 
 /*
  * I'm guessing at the VIF/VIP flag usage, but hope that this is how
@@ -14,12 +14,6 @@
 
 #include <asm/processor-flags.h>
 
-#ifdef CONFIG_VM86
-#define X86_VM_MASK     X86_EFLAGS_VM
-#else
-#define X86_VM_MASK     0 /* No VM86 support */
-#endif
-
 #define BIOSSEG         0x0f000
 
 #define CPU_086         0
@@ -121,7 +115,6 @@ struct vm86plus_info_struct {
         unsigned long is_vm86pus:1;           /* for vm86 internal use */
         unsigned char vm86dbg_intxxtab[32];   /* for debugger */
 };
-
 struct vm86plus_struct {
         struct vm86_regs regs;
         unsigned long flags;
@@ -133,6 +126,9 @@ struct vm86plus_struct {
 };
 
 #ifdef __KERNEL__
+
+#include <asm/ptrace.h>
+
 /*
  * This is the (kernel) stack-layout when we have done a "SAVE_ALL" from vm86
  * mode - the main change is that the old segment descriptors aren't
@@ -141,7 +137,6 @@ struct vm86plus_struct {
  * at the end of the structure. Look at ptrace.h to see the "normal"
  * setup. For user space layout see 'struct vm86_regs' above.
  */
-#include <asm/ptrace.h>
 
 struct kernel_vm86_regs {
 /*
@@ -210,4 +205,4 @@ static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c)
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__VM86_H */
diff --git a/include/asm-x86/vmi_time.h b/include/asm-x86/vmi_time.h
index 478188130328..b2d39e6a08b7 100644
--- a/include/asm-x86/vmi_time.h
+++ b/include/asm-x86/vmi_time.h
@@ -22,8 +22,8 @@
  *
  */
 
-#ifndef __VMI_TIME_H
-#define __VMI_TIME_H
+#ifndef ASM_X86__VMI_TIME_H
+#define ASM_X86__VMI_TIME_H
 
 /*
  * Raw VMI call indices for timer functions
@@ -50,7 +50,7 @@ extern void __init vmi_time_init(void);
 extern unsigned long vmi_get_wallclock(void);
 extern int vmi_set_wallclock(unsigned long now);
 extern unsigned long long vmi_sched_clock(void);
-extern unsigned long vmi_cpu_khz(void);
+extern unsigned long vmi_tsc_khz(void);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 extern void __devinit vmi_time_bsp_init(void);
@@ -95,4 +95,4 @@ extern void __devinit vmi_time_ap_init(void);
 
 #define CONFIG_VMI_ALARM_HZ     100
 
-#endif
+#endif /* ASM_X86__VMI_TIME_H */
diff --git a/include/asm-x86/vsyscall.h b/include/asm-x86/vsyscall.h
index 17b3700949bf..dcd4682413de 100644
--- a/include/asm-x86/vsyscall.h
+++ b/include/asm-x86/vsyscall.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_64_VSYSCALL_H_
-#define _ASM_X86_64_VSYSCALL_H_
+#ifndef ASM_X86__VSYSCALL_H
+#define ASM_X86__VSYSCALL_H
 
 enum vsyscall_num {
         __NR_vgettimeofday,
@@ -24,7 +24,8 @@ enum vsyscall_num {
         ((unused, __section__ (".vsyscall_gtod_data"),aligned(16)))
 #define __section_vsyscall_clock __attribute__ \
         ((unused, __section__ (".vsyscall_clock"),aligned(16)))
-#define __vsyscall_fn __attribute__ ((unused,__section__(".vsyscall_fn")))
+#define __vsyscall_fn \
+        __attribute__ ((unused, __section__(".vsyscall_fn"))) notrace
 
 #define VGETCPU_RDTSCP  1
 #define VGETCPU_LSL     2
@@ -40,4 +41,4 @@ extern void map_vsyscall(void);
 
 #endif /* __KERNEL__ */
 
-#endif /* _ASM_X86_64_VSYSCALL_H_ */
+#endif /* ASM_X86__VSYSCALL_H */
diff --git a/include/asm-x86/xcr.h b/include/asm-x86/xcr.h
new file mode 100644
index 000000000000..f2cba4e79a23
--- /dev/null
+++ b/include/asm-x86/xcr.h
@@ -0,0 +1,49 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright 2008 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * asm-x86/xcr.h
+ *
+ * Definitions for the eXtended Control Register instructions
+ */
+
+#ifndef _ASM_X86_XCR_H
+#define _ASM_X86_XCR_H
+
+#define XCR_XFEATURE_ENABLED_MASK       0x00000000
+
+#ifdef __KERNEL__
+# ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+static inline u64 xgetbv(u32 index)
+{
+        u32 eax, edx;
+
+        asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
+                     : "=a" (eax), "=d" (edx)
+                     : "c" (index));
+        return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+        u32 eax = value;
+        u32 edx = value >> 32;
+
+        asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
+                     : : "a" (eax), "d" (edx), "c" (index));
+}
+
+# endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_XCR_H */
diff --git a/include/asm-x86/xen/events.h b/include/asm-x86/xen/events.h
index 596312a7bfc9..8151f5b8b6cb 100644
--- a/include/asm-x86/xen/events.h
+++ b/include/asm-x86/xen/events.h
@@ -1,9 +1,11 @@
-#ifndef __XEN_EVENTS_H
-#define __XEN_EVENTS_H
+#ifndef ASM_X86__XEN__EVENTS_H
+#define ASM_X86__XEN__EVENTS_H
 
 enum ipi_vector {
         XEN_RESCHEDULE_VECTOR,
         XEN_CALL_FUNCTION_VECTOR,
+        XEN_CALL_FUNCTION_SINGLE_VECTOR,
+        XEN_SPIN_UNLOCK_VECTOR,
 
         XEN_NR_IPIS,
 };
@@ -19,4 +21,4 @@ static inline void xen_do_IRQ(int irq, struct pt_regs *regs)
         do_IRQ(regs);
 }
 
-#endif /* __XEN_EVENTS_H */
+#endif /* ASM_X86__XEN__EVENTS_H */
diff --git a/include/asm-x86/xen/grant_table.h b/include/asm-x86/xen/grant_table.h
index 2444d4593a3b..c4baab4d2b68 100644
--- a/include/asm-x86/xen/grant_table.h
+++ b/include/asm-x86/xen/grant_table.h
@@ -1,7 +1,7 @@
-#ifndef __XEN_GRANT_TABLE_H
-#define __XEN_GRANT_TABLE_H
+#ifndef ASM_X86__XEN__GRANT_TABLE_H
+#define ASM_X86__XEN__GRANT_TABLE_H
 
 #define xen_alloc_vm_area(size) alloc_vm_area(size)
 #define xen_free_vm_area(area)  free_vm_area(area)
 
-#endif /* __XEN_GRANT_TABLE_H */
+#endif /* ASM_X86__XEN__GRANT_TABLE_H */
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
index c2ccd997ed35..44f4259bee3f 100644
--- a/include/asm-x86/xen/hypercall.h
+++ b/include/asm-x86/xen/hypercall.h
@@ -30,8 +30,8 @@
  * IN THE SOFTWARE.
  */
 
-#ifndef __HYPERCALL_H__
-#define __HYPERCALL_H__
+#ifndef ASM_X86__XEN__HYPERCALL_H
+#define ASM_X86__XEN__HYPERCALL_H
 
 #include <linux/errno.h>
 #include <linux/string.h>
@@ -40,83 +40,157 @@
 #include <xen/interface/sched.h>
 #include <xen/interface/physdev.h>
 
+/*
+ * The hypercall asms have to meet several constraints:
+ * - Work on 32- and 64-bit.
+ *    The two architectures put their arguments in different sets of
+ *    registers.
+ *
+ * - Work around asm syntax quirks
+ *    It isn't possible to specify one of the rNN registers in a
+ *    constraint, so we use explicit register variables to get the
+ *    args into the right place.
+ *
+ * - Mark all registers as potentially clobbered
+ *    Even unused parameters can be clobbered by the hypervisor, so we
+ *    need to make sure gcc knows it.
+ *
+ * - Avoid compiler bugs.
+ *    This is the tricky part.  Because x86_32 has such a constrained
+ *    register set, gcc versions below 4.3 have trouble generating
+ *    code when all the arg registers and memory are trashed by the
+ *    asm.  There are syntactically simpler ways of achieving the
+ *    semantics below, but they cause the compiler to crash.
+ *
+ *    The only combination I found which works is:
+ *     - assign the __argX variables first
+ *     - list all actually used parameters as "+r" (__argX)
+ *     - clobber the rest
+ *
+ * The result certainly isn't pretty, and it really shows up cpp's
+ * weakness as as macro language.  Sorry.  (But let's just give thanks
+ * there aren't more than 5 arguments...)
+ */
+
 extern struct { char _entry[32]; } hypercall_page[];
 
+#define __HYPERCALL             "call hypercall_page+%c[offset]"
+#define __HYPERCALL_ENTRY(x)                                            \
+        [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
+
+#ifdef CONFIG_X86_32
+#define __HYPERCALL_RETREG      "eax"
+#define __HYPERCALL_ARG1REG     "ebx"
+#define __HYPERCALL_ARG2REG     "ecx"
+#define __HYPERCALL_ARG3REG     "edx"
+#define __HYPERCALL_ARG4REG     "esi"
+#define __HYPERCALL_ARG5REG     "edi"
+#else
+#define __HYPERCALL_RETREG      "rax"
+#define __HYPERCALL_ARG1REG     "rdi"
+#define __HYPERCALL_ARG2REG     "rsi"
+#define __HYPERCALL_ARG3REG     "rdx"
+#define __HYPERCALL_ARG4REG     "r10"
+#define __HYPERCALL_ARG5REG     "r8"
+#endif
+
+#define __HYPERCALL_DECLS                                               \
+        register unsigned long __res  asm(__HYPERCALL_RETREG);          \
+        register unsigned long __arg1 asm(__HYPERCALL_ARG1REG) = __arg1; \
+        register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
+        register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
+        register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
+        register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
+
+#define __HYPERCALL_0PARAM      "=r" (__res)
+#define __HYPERCALL_1PARAM      __HYPERCALL_0PARAM, "+r" (__arg1)
+#define __HYPERCALL_2PARAM      __HYPERCALL_1PARAM, "+r" (__arg2)
+#define __HYPERCALL_3PARAM      __HYPERCALL_2PARAM, "+r" (__arg3)
+#define __HYPERCALL_4PARAM      __HYPERCALL_3PARAM, "+r" (__arg4)
+#define __HYPERCALL_5PARAM      __HYPERCALL_4PARAM, "+r" (__arg5)
+
+#define __HYPERCALL_0ARG()
+#define __HYPERCALL_1ARG(a1)                                            \
+        __HYPERCALL_0ARG()              __arg1 = (unsigned long)(a1);
+#define __HYPERCALL_2ARG(a1,a2)                                         \
+        __HYPERCALL_1ARG(a1)            __arg2 = (unsigned long)(a2);
+#define __HYPERCALL_3ARG(a1,a2,a3)                                      \
+        __HYPERCALL_2ARG(a1,a2)         __arg3 = (unsigned long)(a3);
+#define __HYPERCALL_4ARG(a1,a2,a3,a4)                                   \
+        __HYPERCALL_3ARG(a1,a2,a3)      __arg4 = (unsigned long)(a4);
+#define __HYPERCALL_5ARG(a1,a2,a3,a4,a5)                                \
+        __HYPERCALL_4ARG(a1,a2,a3,a4)   __arg5 = (unsigned long)(a5);
+
+#define __HYPERCALL_CLOBBER5    "memory"
+#define __HYPERCALL_CLOBBER4    __HYPERCALL_CLOBBER5, __HYPERCALL_ARG5REG
+#define __HYPERCALL_CLOBBER3    __HYPERCALL_CLOBBER4, __HYPERCALL_ARG4REG
+#define __HYPERCALL_CLOBBER2    __HYPERCALL_CLOBBER3, __HYPERCALL_ARG3REG
+#define __HYPERCALL_CLOBBER1    __HYPERCALL_CLOBBER2, __HYPERCALL_ARG2REG
+#define __HYPERCALL_CLOBBER0    __HYPERCALL_CLOBBER1, __HYPERCALL_ARG1REG
+
 #define _hypercall0(type, name)                                         \
 ({                                                                      \
-        long __res;                                                     \
-        asm volatile (                                                  \
-                "call %[call]"                                          \
-                : "=a" (__res)                                          \
-                : [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
-                : "memory" );                                           \
+        __HYPERCALL_DECLS;                                              \
+        __HYPERCALL_0ARG();                                             \
+        asm volatile (__HYPERCALL                                       \
+                      : __HYPERCALL_0PARAM                              \
+                      : __HYPERCALL_ENTRY(name)                         \
+                      : __HYPERCALL_CLOBBER0);                          \
         (type)__res;                                                    \
 })
 
 #define _hypercall1(type, name, a1)                                     \
 ({                                                                      \
-        long __res, __ign1;                                             \
-        asm volatile (                                                  \
-                "call %[call]"                                          \
-                : "=a" (__res), "=b" (__ign1)                           \
-                : "1" ((long)(a1)),                                     \
-                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
-                : "memory" );                                           \
+        __HYPERCALL_DECLS;                                              \
+        __HYPERCALL_1ARG(a1);                                           \
+        asm volatile (__HYPERCALL                                       \
+                      : __HYPERCALL_1PARAM                              \
+                      : __HYPERCALL_ENTRY(name)                         \
+                      : __HYPERCALL_CLOBBER1);                          \
         (type)__res;                                                    \
 })
 
 #define _hypercall2(type, name, a1, a2)                                 \
 ({                                                                      \
-        long __res, __ign1, __ign2;                                     \
-        asm volatile (                                                  \
-                "call %[call]"                                          \
-                : "=a" (__res), "=b" (__ign1), "=c" (__ign2)            \
-                : "1" ((long)(a1)), "2" ((long)(a2)),                   \
-                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
-                : "memory" );                                           \
+        __HYPERCALL_DECLS;                                              \
+        __HYPERCALL_2ARG(a1, a2);                                       \
+        asm volatile (__HYPERCALL                                       \
+                      : __HYPERCALL_2PARAM                              \
+                      : __HYPERCALL_ENTRY(name)                         \
+                      : __HYPERCALL_CLOBBER2);                          \
         (type)__res;                                                    \
 })
 
 #define _hypercall3(type, name, a1, a2, a3)                             \
 ({                                                                      \
-        long __res, __ign1, __ign2, __ign3;                             \
-        asm volatile (                                                  \
-                "call %[call]"                                          \
-                : "=a" (__res), "=b" (__ign1), "=c" (__ign2),           \
-                "=d" (__ign3)                                           \
-                : "1" ((long)(a1)), "2" ((long)(a2)),                   \
-                  "3" ((long)(a3)),                                     \
-                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
-                : "memory" );                                           \
+        __HYPERCALL_DECLS;                                              \
+        __HYPERCALL_3ARG(a1, a2, a3);                                   \
+        asm volatile (__HYPERCALL                                       \
+                      : __HYPERCALL_3PARAM                              \
+                      : __HYPERCALL_ENTRY(name)                         \
+                      : __HYPERCALL_CLOBBER3);                          \
         (type)__res;                                                    \
 })
 
 #define _hypercall4(type, name, a1, a2, a3, a4)                         \
 ({                                                                      \
-        long __res, __ign1, __ign2, __ign3, __ign4;                     \
-        asm volatile (                                                  \
-                "call %[call]"                                          \
-                : "=a" (__res), "=b" (__ign1), "=c" (__ign2),           \
-                "=d" (__ign3), "=S" (__ign4)                            \
-                : "1" ((long)(a1)), "2" ((long)(a2)),                   \
-                  "3" ((long)(a3)), "4" ((long)(a4)),                   \
-                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
-                : "memory" );                                           \
+        __HYPERCALL_DECLS;                                              \
+        __HYPERCALL_4ARG(a1, a2, a3, a4);                               \
+        asm volatile (__HYPERCALL                                       \
+                      : __HYPERCALL_4PARAM                              \
+                      : __HYPERCALL_ENTRY(name)                         \
+                      : __HYPERCALL_CLOBBER4);                          \
         (type)__res;                                                    \
 })
 
 #define _hypercall5(type, name, a1, a2, a3, a4, a5)                     \
 ({                                                                      \
-        long __res, __ign1, __ign2, __ign3, __ign4, __ign5;             \
-        asm volatile (                                                  \
-                "call %[call]"                                          \
-                : "=a" (__res), "=b" (__ign1), "=c" (__ign2),           \
-                "=d" (__ign3), "=S" (__ign4), "=D" (__ign5)             \
-                : "1" ((long)(a1)), "2" ((long)(a2)),                   \
-                  "3" ((long)(a3)), "4" ((long)(a4)),                   \
-                  "5" ((long)(a5)),                                     \
-                  [call] "m" (hypercall_page[__HYPERVISOR_##name])      \
-                : "memory" );                                           \
+        __HYPERCALL_DECLS;                                              \
+        __HYPERCALL_5ARG(a1, a2, a3, a4, a5);                           \
+        asm volatile (__HYPERCALL                                       \
+                      : __HYPERCALL_5PARAM                              \
+                      : __HYPERCALL_ENTRY(name)                         \
+                      : __HYPERCALL_CLOBBER5);                          \
         (type)__res;                                                    \
 })
 
@@ -152,6 +226,7 @@ HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp)
         return _hypercall2(int, stack_switch, ss, esp);
 }
 
+#ifdef CONFIG_X86_32
 static inline int
 HYPERVISOR_set_callbacks(unsigned long event_selector,
                          unsigned long event_address,
@@ -162,6 +237,17 @@ HYPERVISOR_set_callbacks(unsigned long event_selector,
                            event_selector, event_address,
                            failsafe_selector, failsafe_address);
 }
+#else  /* CONFIG_X86_64 */
+static inline int
+HYPERVISOR_set_callbacks(unsigned long event_address,
+                        unsigned long failsafe_address,
+                        unsigned long syscall_address)
+{
+        return _hypercall3(int, set_callbacks,
+                           event_address, failsafe_address,
+                           syscall_address);
+}
+#endif  /* CONFIG_X86_{32,64} */
 
 static inline int
 HYPERVISOR_callback_op(int cmd, void *arg)
@@ -176,9 +262,9 @@ HYPERVISOR_fpu_taskswitch(int set)
 }
 
 static inline int
-HYPERVISOR_sched_op(int cmd, unsigned long arg)
+HYPERVISOR_sched_op(int cmd, void *arg)
 {
-        return _hypercall2(int, sched_op, cmd, arg);
+        return _hypercall2(int, sched_op_new, cmd, arg);
 }
 
 static inline long
@@ -223,12 +309,12 @@ static inline int
 HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
                              unsigned long flags)
 {
-        unsigned long pte_hi = 0;
-#ifdef CONFIG_X86_PAE
-        pte_hi = new_val.pte_high;
-#endif
-        return _hypercall4(int, update_va_mapping, va,
-                           new_val.pte_low, pte_hi, flags);
+        if (sizeof(new_val) == sizeof(long))
+                return _hypercall3(int, update_va_mapping, va,
+                                   new_val.pte, flags);
+        else
+                return _hypercall4(int, update_va_mapping, va,
+                                   new_val.pte, new_val.pte >> 32, flags);
 }
 
 static inline int
@@ -281,12 +367,13 @@ static inline int
 HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val,
                                          unsigned long flags, domid_t domid)
 {
-        unsigned long pte_hi = 0;
-#ifdef CONFIG_X86_PAE
-        pte_hi = new_val.pte_high;
-#endif
-        return _hypercall5(int, update_va_mapping_otherdomain, va,
-                           new_val.pte_low, pte_hi, flags, domid);
+        if (sizeof(new_val) == sizeof(long))
+                return _hypercall4(int, update_va_mapping_otherdomain, va,
+                                   new_val.pte, flags, domid);
+        else
+                return _hypercall5(int, update_va_mapping_otherdomain, va,
+                                   new_val.pte, new_val.pte >> 32,
+                                   flags, domid);
 }
 
 static inline int
@@ -301,6 +388,14 @@ HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args)
         return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args);
 }
 
+#ifdef CONFIG_X86_64
+static inline int
+HYPERVISOR_set_segment_base(int reg, unsigned long value)
+{
+        return _hypercall2(int, set_segment_base, reg, value);
+}
+#endif
+
 static inline int
 HYPERVISOR_suspend(unsigned long srec)
 {
@@ -315,19 +410,26 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg)
 }
 
 static inline void
+MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
+{
+        mcl->op = __HYPERVISOR_fpu_taskswitch;
+        mcl->args[0] = set;
+}
+
+static inline void
 MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
                         pte_t new_val, unsigned long flags)
 {
         mcl->op = __HYPERVISOR_update_va_mapping;
         mcl->args[0] = va;
-#ifdef CONFIG_X86_PAE
-        mcl->args[1] = new_val.pte_low;
-        mcl->args[2] = new_val.pte_high;
-#else
-        mcl->args[1] = new_val.pte_low;
-        mcl->args[2] = 0;
-#endif
-        mcl->args[3] = flags;
+        if (sizeof(new_val) == sizeof(long)) {
+                mcl->args[1] = new_val.pte;
+                mcl->args[2] = flags;
+        } else {
+                mcl->args[1] = new_val.pte;
+                mcl->args[2] = new_val.pte >> 32;
+                mcl->args[3] = flags;
+        }
 }
 
 static inline void
@@ -347,15 +449,16 @@ MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long v
 {
         mcl->op = __HYPERVISOR_update_va_mapping_otherdomain;
         mcl->args[0] = va;
-#ifdef CONFIG_X86_PAE
-        mcl->args[1] = new_val.pte_low;
-        mcl->args[2] = new_val.pte_high;
-#else
-        mcl->args[1] = new_val.pte_low;
-        mcl->args[2] = 0;
-#endif
-        mcl->args[3] = flags;
-        mcl->args[4] = domid;
+        if (sizeof(new_val) == sizeof(long)) {
+                mcl->args[1] = new_val.pte;
+                mcl->args[2] = flags;
+                mcl->args[3] = domid;
+        } else {
+                mcl->args[1] = new_val.pte;
+                mcl->args[2] = new_val.pte >> 32;
+                mcl->args[3] = flags;
+                mcl->args[4] = domid;
+        }
 }
 
 static inline void
@@ -363,10 +466,15 @@ MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
                         struct desc_struct desc)
 {
         mcl->op = __HYPERVISOR_update_descriptor;
-        mcl->args[0] = maddr;
-        mcl->args[1] = maddr >> 32;
-        mcl->args[2] = desc.a;
-        mcl->args[3] = desc.b;
+        if (sizeof(maddr) == sizeof(long)) {
+                mcl->args[0] = maddr;
+                mcl->args[1] = *(unsigned long *)&desc;
+        } else {
+                mcl->args[0] = maddr;
+                mcl->args[1] = maddr >> 32;
+                mcl->args[2] = desc.a;
+                mcl->args[3] = desc.b;
+        }
 }
 
 static inline void
@@ -416,4 +524,4 @@ MULTI_stack_switch(struct multicall_entry *mcl,
         mcl->args[1] = esp;
 }
 
-#endif /* __HYPERCALL_H__ */
+#endif /* ASM_X86__XEN__HYPERCALL_H */
diff --git a/include/asm-x86/xen/hypervisor.h b/include/asm-x86/xen/hypervisor.h
index 8e15dd28c91f..445a24759560 100644
--- a/include/asm-x86/xen/hypervisor.h
+++ b/include/asm-x86/xen/hypervisor.h
@@ -30,12 +30,11 @@
  * IN THE SOFTWARE.
  */
 
-#ifndef __HYPERVISOR_H__
-#define __HYPERVISOR_H__
+#ifndef ASM_X86__XEN__HYPERVISOR_H
+#define ASM_X86__XEN__HYPERVISOR_H
 
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/version.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/version.h>
@@ -55,7 +54,6 @@
 /* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
-#define is_initial_xendomain() (xen_start_info->flags & SIF_INITDOMAIN)
 
 /* arch/i386/mach-xen/evtchn.c */
 /* Force a proper event-channel callback from Xen. */
@@ -68,6 +66,17 @@ u64 jiffies_to_st(unsigned long jiffies);
 #define MULTI_UVMFLAGS_INDEX 3
 #define MULTI_UVMDOMID_INDEX 4
 
-#define is_running_on_xen()     (xen_start_info ? 1 : 0)
+enum xen_domain_type {
+        XEN_NATIVE,
+        XEN_PV_DOMAIN,
+        XEN_HVM_DOMAIN,
+};
 
-#endif /* __HYPERVISOR_H__ */
+extern enum xen_domain_type xen_domain_type;
+
+#define xen_domain()            (xen_domain_type != XEN_NATIVE)
+#define xen_pv_domain()         (xen_domain_type == XEN_PV_DOMAIN)
+#define xen_initial_domain()    (xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
+#define xen_hvm_domain()        (xen_domain_type == XEN_HVM_DOMAIN)
+
+#endif /* ASM_X86__XEN__HYPERVISOR_H */
diff --git a/include/asm-x86/xen/interface.h b/include/asm-x86/xen/interface.h
index 6227000a1e84..d077bba96da9 100644
--- a/include/asm-x86/xen/interface.h
+++ b/include/asm-x86/xen/interface.h
@@ -1,13 +1,13 @@
 /******************************************************************************
  * arch-x86_32.h
  *
- * Guest OS interface to x86 32-bit Xen.
+ * Guest OS interface to x86 Xen.
  *
  * Copyright (c) 2004, K A Fraser
  */
 
-#ifndef __XEN_PUBLIC_ARCH_X86_32_H__
-#define __XEN_PUBLIC_ARCH_X86_32_H__
+#ifndef ASM_X86__XEN__INTERFACE_H
+#define ASM_X86__XEN__INTERFACE_H
 
 #ifdef __XEN__
 #define __DEFINE_GUEST_HANDLE(name, type) \
@@ -57,6 +57,17 @@ DEFINE_GUEST_HANDLE(long);
 DEFINE_GUEST_HANDLE(void);
 #endif
 
+#ifndef HYPERVISOR_VIRT_START
+#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#endif
+
+#ifndef machine_to_phys_mapping
+#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
+#endif
+
+/* Maximum number of virtual CPUs in multi-processor guests. */
+#define MAX_VIRT_CPUS 32
+
 /*
  * SEGMENT DESCRIPTOR TABLES
  */
@@ -71,58 +82,21 @@ DEFINE_GUEST_HANDLE(void);
 #define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
 
 /*
- * These flat segments are in the Xen-private section of every GDT. Since these
- * are also present in the initial GDT, many OSes will be able to avoid
- * installing their own GDT.
- */
-#define FLAT_RING1_CS 0xe019    /* GDT index 259 */
-#define FLAT_RING1_DS 0xe021    /* GDT index 260 */
-#define FLAT_RING1_SS 0xe021    /* GDT index 260 */
-#define FLAT_RING3_CS 0xe02b    /* GDT index 261 */
-#define FLAT_RING3_DS 0xe033    /* GDT index 262 */
-#define FLAT_RING3_SS 0xe033    /* GDT index 262 */
-
-#define FLAT_KERNEL_CS FLAT_RING1_CS
-#define FLAT_KERNEL_DS FLAT_RING1_DS
-#define FLAT_KERNEL_SS FLAT_RING1_SS
-#define FLAT_USER_CS    FLAT_RING3_CS
-#define FLAT_USER_DS    FLAT_RING3_DS
-#define FLAT_USER_SS    FLAT_RING3_SS
-
-/* And the trap vector is... */
-#define TRAP_INSTR "int $0x82"
-
-/*
- * Virtual addresses beyond this are not modifiable by guest OSes. The
- * machine->physical mapping table starts at this address, read-only.
- */
-#ifdef CONFIG_X86_PAE
-#define __HYPERVISOR_VIRT_START 0xF5800000
-#else
-#define __HYPERVISOR_VIRT_START 0xFC000000
-#endif
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#endif
-
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
-
-/* Maximum number of virtual CPUs in multi-processor guests. */
-#define MAX_VIRT_CPUS 32
-
-#ifndef __ASSEMBLY__
-
-/*
  * Send an array of these to HYPERVISOR_set_trap_table()
+ * The privilege level specifies which modes may enter a trap via a software
+ * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
+ * privilege levels as follows:
+ *  Level == 0: Noone may enter
+ *  Level == 1: Kernel may enter
+ *  Level == 2: Kernel may enter
+ *  Level == 3: Everyone may enter
  */
 #define TI_GET_DPL(_ti)         ((_ti)->flags & 3)
 #define TI_GET_IF(_ti)          ((_ti)->flags & 4)
 #define TI_SET_DPL(_ti, _dpl)   ((_ti)->flags |= (_dpl))
 #define TI_SET_IF(_ti, _if)     ((_ti)->flags |= ((!!(_if))<<2))
 
+#ifndef __ASSEMBLY__
 struct trap_info {
     uint8_t       vector;  /* exception vector                              */
     uint8_t       flags;   /* 0-3: privilege level; 4: clear event enable?  */
@@ -131,32 +105,21 @@ struct trap_info {
 };
 DEFINE_GUEST_HANDLE_STRUCT(trap_info);
 
-struct cpu_user_regs {
-    uint32_t ebx;
-    uint32_t ecx;
-    uint32_t edx;
-    uint32_t esi;
-    uint32_t edi;
-    uint32_t ebp;
-    uint32_t eax;
-    uint16_t error_code;    /* private */
-    uint16_t entry_vector;  /* private */
-    uint32_t eip;
-    uint16_t cs;
-    uint8_t  saved_upcall_mask;
-    uint8_t  _pad0;
-    uint32_t eflags;        /* eflags.IF == !saved_upcall_mask */
-    uint32_t esp;
-    uint16_t ss, _pad1;
-    uint16_t es, _pad2;
-    uint16_t ds, _pad3;
-    uint16_t fs, _pad4;
-    uint16_t gs, _pad5;
+struct arch_shared_info {
+    unsigned long max_pfn;                  /* max pfn that appears in table */
+    /* Frame containing list of mfns containing list of mfns containing p2m. */
+    unsigned long pfn_to_mfn_frame_list_list;
+    unsigned long nmi_reason;
 };
-DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+#endif  /* !__ASSEMBLY__ */
 
-typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
+#ifdef CONFIG_X86_32
+#include "interface_32.h"
+#else
+#include "interface_64.h"
+#endif
 
+#ifndef __ASSEMBLY__
 /*
  * The following is all CPU context. Note that the fpu_ctxt block is filled
  * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
@@ -173,33 +136,29 @@ struct vcpu_guest_context {
     unsigned long ldt_base, ldt_ents;       /* LDT (linear address, # ents) */
     unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */
     unsigned long kernel_ss, kernel_sp;     /* Virtual TSS (only SS1/SP1)   */
+    /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */
     unsigned long ctrlreg[8];               /* CR0-CR7 (control registers)  */
     unsigned long debugreg[8];              /* DB0-DB7 (debug registers)    */
+#ifdef __i386__
     unsigned long event_callback_cs;        /* CS:EIP of event callback     */
     unsigned long event_callback_eip;
     unsigned long failsafe_callback_cs;     /* CS:EIP of failsafe callback  */
     unsigned long failsafe_callback_eip;
+#else
+    unsigned long event_callback_eip;
+    unsigned long failsafe_callback_eip;
+    unsigned long syscall_callback_eip;
+#endif
     unsigned long vm_assist;                /* VMASST_TYPE_* bitmap */
+#ifdef __x86_64__
+    /* Segment base addresses. */
+    uint64_t      fs_base;
+    uint64_t      gs_base_kernel;
+    uint64_t      gs_base_user;
+#endif
 };
 DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
-
-struct arch_shared_info {
-    unsigned long max_pfn;                  /* max pfn that appears in table */
-    /* Frame containing list of mfns containing list of mfns containing p2m. */
-    unsigned long pfn_to_mfn_frame_list_list;
-    unsigned long nmi_reason;
-};
-
-struct arch_vcpu_info {
-    unsigned long cr2;
-    unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
-};
-
-struct xen_callback {
-        unsigned long cs;
-        unsigned long eip;
-};
-#endif /* !__ASSEMBLY__ */
+#endif  /* !__ASSEMBLY__ */
 
 /*
  * Prefix forces emulation of some non-trapping instructions.
@@ -213,4 +172,4 @@ struct xen_callback {
 #define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
 #endif
 
-#endif
+#endif /* ASM_X86__XEN__INTERFACE_H */
diff --git a/include/asm-x86/xen/interface_32.h b/include/asm-x86/xen/interface_32.h
new file mode 100644
index 000000000000..08167e19fc66
--- /dev/null
+++ b/include/asm-x86/xen/interface_32.h
@@ -0,0 +1,97 @@
+/******************************************************************************
+ * arch-x86_32.h
+ *
+ * Guest OS interface to x86 32-bit Xen.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef ASM_X86__XEN__INTERFACE_32_H
+#define ASM_X86__XEN__INTERFACE_32_H
+
+
+/*
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+#define FLAT_RING1_CS 0xe019    /* GDT index 259 */
+#define FLAT_RING1_DS 0xe021    /* GDT index 260 */
+#define FLAT_RING1_SS 0xe021    /* GDT index 260 */
+#define FLAT_RING3_CS 0xe02b    /* GDT index 261 */
+#define FLAT_RING3_DS 0xe033    /* GDT index 262 */
+#define FLAT_RING3_SS 0xe033    /* GDT index 262 */
+
+#define FLAT_KERNEL_CS FLAT_RING1_CS
+#define FLAT_KERNEL_DS FLAT_RING1_DS
+#define FLAT_KERNEL_SS FLAT_RING1_SS
+#define FLAT_USER_CS    FLAT_RING3_CS
+#define FLAT_USER_DS    FLAT_RING3_DS
+#define FLAT_USER_SS    FLAT_RING3_SS
+
+/* And the trap vector is... */
+#define TRAP_INSTR "int $0x82"
+
+/*
+ * Virtual addresses beyond this are not modifiable by guest OSes. The
+ * machine->physical mapping table starts at this address, read-only.
+ */
+#define __HYPERVISOR_VIRT_START 0xF5800000
+
+#ifndef __ASSEMBLY__
+
+struct cpu_user_regs {
+    uint32_t ebx;
+    uint32_t ecx;
+    uint32_t edx;
+    uint32_t esi;
+    uint32_t edi;
+    uint32_t ebp;
+    uint32_t eax;
+    uint16_t error_code;    /* private */
+    uint16_t entry_vector;  /* private */
+    uint32_t eip;
+    uint16_t cs;
+    uint8_t  saved_upcall_mask;
+    uint8_t  _pad0;
+    uint32_t eflags;        /* eflags.IF == !saved_upcall_mask */
+    uint32_t esp;
+    uint16_t ss, _pad1;
+    uint16_t es, _pad2;
+    uint16_t ds, _pad3;
+    uint16_t fs, _pad4;
+    uint16_t gs, _pad5;
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
+
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
+};
+
+struct xen_callback {
+        unsigned long cs;
+        unsigned long eip;
+};
+typedef struct xen_callback xen_callback_t;
+
+#define XEN_CALLBACK(__cs, __eip)                               \
+        ((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) })
+#endif /* !__ASSEMBLY__ */
+
+
+/*
+ * Page-directory addresses above 4GB do not fit into architectural %cr3.
+ * When accessing %cr3, or equivalent field in vcpu_guest_context, guests
+ * must use the following accessor macros to pack/unpack valid MFNs.
+ *
+ * Note that Xen is using the fact that the pagetable base is always
+ * page-aligned, and putting the 12 MSB of the address into the 12 LSB
+ * of cr3.
+ */
+#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20))
+#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20))
+
+#endif /* ASM_X86__XEN__INTERFACE_32_H */
diff --git a/include/asm-x86/xen/interface_64.h b/include/asm-x86/xen/interface_64.h
new file mode 100644
index 000000000000..046c0f1e01d4
--- /dev/null
+++ b/include/asm-x86/xen/interface_64.h
@@ -0,0 +1,159 @@
+#ifndef ASM_X86__XEN__INTERFACE_64_H
+#define ASM_X86__XEN__INTERFACE_64_H
+
+/*
+ * 64-bit segment selectors
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+
+#define FLAT_RING3_CS32 0xe023  /* GDT index 260 */
+#define FLAT_RING3_CS64 0xe033  /* GDT index 261 */
+#define FLAT_RING3_DS32 0xe02b  /* GDT index 262 */
+#define FLAT_RING3_DS64 0x0000  /* NULL selector */
+#define FLAT_RING3_SS32 0xe02b  /* GDT index 262 */
+#define FLAT_RING3_SS64 0xe02b  /* GDT index 262 */
+
+#define FLAT_KERNEL_DS64 FLAT_RING3_DS64
+#define FLAT_KERNEL_DS32 FLAT_RING3_DS32
+#define FLAT_KERNEL_DS   FLAT_KERNEL_DS64
+#define FLAT_KERNEL_CS64 FLAT_RING3_CS64
+#define FLAT_KERNEL_CS32 FLAT_RING3_CS32
+#define FLAT_KERNEL_CS   FLAT_KERNEL_CS64
+#define FLAT_KERNEL_SS64 FLAT_RING3_SS64
+#define FLAT_KERNEL_SS32 FLAT_RING3_SS32
+#define FLAT_KERNEL_SS   FLAT_KERNEL_SS64
+
+#define FLAT_USER_DS64 FLAT_RING3_DS64
+#define FLAT_USER_DS32 FLAT_RING3_DS32
+#define FLAT_USER_DS   FLAT_USER_DS64
+#define FLAT_USER_CS64 FLAT_RING3_CS64
+#define FLAT_USER_CS32 FLAT_RING3_CS32
+#define FLAT_USER_CS   FLAT_USER_CS64
+#define FLAT_USER_SS64 FLAT_RING3_SS64
+#define FLAT_USER_SS32 FLAT_RING3_SS32
+#define FLAT_USER_SS   FLAT_USER_SS64
+
+#define __HYPERVISOR_VIRT_START 0xFFFF800000000000
+#define __HYPERVISOR_VIRT_END   0xFFFF880000000000
+#define __MACH2PHYS_VIRT_START  0xFFFF800000000000
+#define __MACH2PHYS_VIRT_END    0xFFFF804000000000
+
+#ifndef HYPERVISOR_VIRT_START
+#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#define HYPERVISOR_VIRT_END   mk_unsigned_long(__HYPERVISOR_VIRT_END)
+#endif
+
+#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
+#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
+#ifndef machine_to_phys_mapping
+#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
+#endif
+
+/*
+ * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
+ *  @which == SEGBASE_*  ;  @base == 64-bit base address
+ * Returns 0 on success.
+ */
+#define SEGBASE_FS          0
+#define SEGBASE_GS_USER     1
+#define SEGBASE_GS_KERNEL   2
+#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */
+
+/*
+ * int HYPERVISOR_iret(void)
+ * All arguments are on the kernel stack, in the following format.
+ * Never returns if successful. Current kernel context is lost.
+ * The saved CS is mapped as follows:
+ *   RING0 -> RING3 kernel mode.
+ *   RING1 -> RING3 kernel mode.
+ *   RING2 -> RING3 kernel mode.
+ *   RING3 -> RING3 user mode.
+ * However RING0 indicates that the guest kernel should return to iteself
+ * directly with
+ *      orb   $3,1*8(%rsp)
+ *      iretq
+ * If flags contains VGCF_in_syscall:
+ *   Restore RAX, RIP, RFLAGS, RSP.
+ *   Discard R11, RCX, CS, SS.
+ * Otherwise:
+ *   Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP.
+ * All other registers are saved on hypercall entry and restored to user.
+ */
+/* Guest exited in SYSCALL context? Return to guest with SYSRET? */
+#define _VGCF_in_syscall 8
+#define VGCF_in_syscall  (1<<_VGCF_in_syscall)
+#define VGCF_IN_SYSCALL  VGCF_in_syscall
+
+#ifndef __ASSEMBLY__
+
+struct iret_context {
+    /* Top of stack (%rsp at point of hypercall). */
+    uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss;
+    /* Bottom of iret stack frame. */
+};
+
+#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
+/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */
+#define __DECL_REG(name) union { \
+    uint64_t r ## name, e ## name; \
+    uint32_t _e ## name; \
+}
+#else
+/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */
+#define __DECL_REG(name) uint64_t r ## name
+#endif
+
+struct cpu_user_regs {
+    uint64_t r15;
+    uint64_t r14;
+    uint64_t r13;
+    uint64_t r12;
+    __DECL_REG(bp);
+    __DECL_REG(bx);
+    uint64_t r11;
+    uint64_t r10;
+    uint64_t r9;
+    uint64_t r8;
+    __DECL_REG(ax);
+    __DECL_REG(cx);
+    __DECL_REG(dx);
+    __DECL_REG(si);
+    __DECL_REG(di);
+    uint32_t error_code;    /* private */
+    uint32_t entry_vector;  /* private */
+    __DECL_REG(ip);
+    uint16_t cs, _pad0[1];
+    uint8_t  saved_upcall_mask;
+    uint8_t  _pad1[3];
+    __DECL_REG(flags);      /* rflags.IF == !saved_upcall_mask */
+    __DECL_REG(sp);
+    uint16_t ss, _pad2[3];
+    uint16_t es, _pad3[3];
+    uint16_t ds, _pad4[3];
+    uint16_t fs, _pad5[3]; /* Non-zero => takes precedence over fs_base.     */
+    uint16_t gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+#undef __DECL_REG
+
+#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12)
+#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12)
+
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+typedef unsigned long xen_callback_t;
+
+#define XEN_CALLBACK(__cs, __rip)                               \
+        ((unsigned long)(__rip))
+
+#endif /* !__ASSEMBLY__ */
+
+
+#endif /* ASM_X86__XEN__INTERFACE_64_H */
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
index baf3a4dce28c..c50185dccec1 100644
--- a/include/asm-x86/xen/page.h
+++ b/include/asm-x86/xen/page.h
@@ -1,5 +1,5 @@
-#ifndef __XEN_PAGE_H
-#define __XEN_PAGE_H
+#ifndef ASM_X86__XEN__PAGE_H
+#define ASM_X86__XEN__PAGE_H
 
 #include <linux/pfn.h>
 
@@ -26,15 +26,20 @@ typedef struct xpaddr {
 #define FOREIGN_FRAME_BIT       (1UL<<31)
 #define FOREIGN_FRAME(m)        ((m) | FOREIGN_FRAME_BIT)
 
-extern unsigned long *phys_to_machine_mapping;
+/* Maximum amount of memory we can handle in a domain in pages */
+#define MAX_DOMAIN_PAGES                                                \
+    ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
+
+
+extern unsigned long get_phys_to_machine(unsigned long pfn);
+extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return pfn;
 
-        return phys_to_machine_mapping[(unsigned int)(pfn)] &
-                ~FOREIGN_FRAME_BIT;
+        return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
 }
 
 static inline int phys_to_machine_mapping_valid(unsigned long pfn)
@@ -42,7 +47,7 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return 1;
 
-        return (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY);
+        return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
 static inline unsigned long mfn_to_pfn(unsigned long mfn)
@@ -106,20 +111,12 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
         unsigned long pfn = mfn_to_pfn(mfn);
         if ((pfn < max_mapnr)
             && !xen_feature(XENFEAT_auto_translated_physmap)
-            && (phys_to_machine_mapping[pfn] != mfn))
+            && (get_phys_to_machine(pfn) != mfn))
                 return max_mapnr; /* force !pfn_valid() */
+        /* XXX fixme; not true with sparsemem */
         return pfn;
 }
 
-static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
-        if (xen_feature(XENFEAT_auto_translated_physmap)) {
-                BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
-                return;
-        }
-        phys_to_machine_mapping[pfn] = mfn;
-}
-
 /* VIRT <-> MACHINE conversion */
 #define virt_to_machine(v)      (phys_to_machine(XPADDR(__pa(v))))
 #define virt_to_mfn(v)          (pfn_to_mfn(PFN_DOWN(__pa(v))))
@@ -127,7 +124,7 @@ static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 
 static inline unsigned long pte_mfn(pte_t pte)
 {
-        return (pte.pte & PTE_MASK) >> PAGE_SHIFT;
+        return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
@@ -150,19 +147,19 @@ static inline pte_t __pte_ma(pteval_t x)
         return (pte_t) { .pte = x };
 }
 
-#ifdef CONFIG_X86_PAE
 #define pmd_val_ma(v) ((v).pmd)
+#ifdef __PAGETABLE_PUD_FOLDED
 #define pud_val_ma(v) ((v).pgd.pgd)
+#else
+#define pud_val_ma(v) ((v).pud)
+#endif
 #define __pmd_ma(x)     ((pmd_t) { (x) } )
-#else  /* !X86_PAE */
-#define pmd_val_ma(v)   ((v).pud.pgd.pgd)
-#endif  /* CONFIG_X86_PAE */
 
 #define pgd_val_ma(x)   ((x).pgd)
 
 
-xmaddr_t arbitrary_virt_to_machine(unsigned long address);
+xmaddr_t arbitrary_virt_to_machine(void *address);
 void make_lowmem_page_readonly(void *vaddr);
 void make_lowmem_page_readwrite(void *vaddr);
 
-#endif /* __XEN_PAGE_H */
+#endif /* ASM_X86__XEN__PAGE_H */
diff --git a/include/asm-x86/xor_32.h b/include/asm-x86/xor_32.h
index 067b5c1835a3..921b45840449 100644
--- a/include/asm-x86/xor_32.h
+++ b/include/asm-x86/xor_32.h
@@ -1,3 +1,6 @@
+#ifndef ASM_X86__XOR_32_H
+#define ASM_X86__XOR_32_H
+
 /*
  * Optimized RAID-5 checksumming functions for MMX and SSE.
  *
@@ -881,3 +884,5 @@ do {							\
    deals with a load to a line that is being prefetched.  */
 #define XOR_SELECT_TEMPLATE(FASTEST)                    \
         (cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
+
+#endif /* ASM_X86__XOR_32_H */
diff --git a/include/asm-x86/xor_64.h b/include/asm-x86/xor_64.h
index 24957e39ac8a..2d3a18de295b 100644
--- a/include/asm-x86/xor_64.h
+++ b/include/asm-x86/xor_64.h
@@ -1,3 +1,6 @@
+#ifndef ASM_X86__XOR_64_H
+#define ASM_X86__XOR_64_H
+
 /*
  * Optimized RAID-5 checksumming functions for MMX and SSE.
  *
@@ -354,3 +357,5 @@ do {						\
    We may also be able to load into the L1 only depending on how the cpu
    deals with a load to a line that is being prefetched.  */
 #define XOR_SELECT_TEMPLATE(FASTEST) (&xor_block_sse)
+
+#endif /* ASM_X86__XOR_64_H */
diff --git a/include/asm-x86/xsave.h b/include/asm-x86/xsave.h
new file mode 100644
index 000000000000..08e9a1ac07a9
--- /dev/null
+++ b/include/asm-x86/xsave.h
@@ -0,0 +1,118 @@
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+
+#define XSTATE_FP       0x1
+#define XSTATE_SSE      0x2
+
+#define XSTATE_FPSSE    (XSTATE_FP | XSTATE_SSE)
+
+#define FXSAVE_SIZE     512
+
+/*
+ * These are the features that the OS can handle currently.
+ */
+#define XCNTXT_MASK     (XSTATE_FP | XSTATE_SSE)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX      "0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern unsigned int xstate_size;
+extern u64 pcntxt_mask;
+extern struct xsave_struct *init_xstate_buf;
+
+extern void xsave_cntxt_init(void);
+extern void xsave_init(void);
+extern int init_fpu(struct task_struct *child);
+extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
+                            void __user *fpstate,
+                            struct _fpx_sw_bytes *sw);
+
+static inline int xrstor_checking(struct xsave_struct *fx)
+{
+        int err;
+
+        asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
+                     "2:\n"
+                     ".section .fixup,\"ax\"\n"
+                     "3:  movl $-1,%[err]\n"
+                     "    jmp  2b\n"
+                     ".previous\n"
+                     _ASM_EXTABLE(1b, 3b)
+                     : [err] "=r" (err)
+                     : "D" (fx), "m" (*fx), "a" (-1), "d" (-1), "0" (0)
+                     : "memory");
+
+        return err;
+}
+
+static inline int xsave_user(struct xsave_struct __user *buf)
+{
+        int err;
+        __asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
+                             "2:\n"
+                             ".section .fixup,\"ax\"\n"
+                             "3:  movl $-1,%[err]\n"
+                             "    jmp  2b\n"
+                             ".previous\n"
+                             ".section __ex_table,\"a\"\n"
+                             _ASM_ALIGN "\n"
+                             _ASM_PTR "1b,3b\n"
+                             ".previous"
+                             : [err] "=r" (err)
+                             : "D" (buf), "a" (-1), "d" (-1), "0" (0)
+                             : "memory");
+        if (unlikely(err) && __clear_user(buf, xstate_size))
+                err = -EFAULT;
+        /* No need to clear here because the caller clears USED_MATH */
+        return err;
+}
+
+static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
+{
+        int err;
+        struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
+        u32 lmask = mask;
+        u32 hmask = mask >> 32;
+
+        __asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
+                             "2:\n"
+                             ".section .fixup,\"ax\"\n"
+                             "3:  movl $-1,%[err]\n"
+                             "    jmp  2b\n"
+                             ".previous\n"
+                             ".section __ex_table,\"a\"\n"
+                             _ASM_ALIGN "\n"
+                             _ASM_PTR "1b,3b\n"
+                             ".previous"
+                             : [err] "=r" (err)
+                             : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
+                             : "memory");       /* memory required? */
+        return err;
+}
+
+static inline void xrstor_state(struct xsave_struct *fx, u64 mask)
+{
+        u32 lmask = mask;
+        u32 hmask = mask >> 32;
+
+        asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
+                     : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+                     :   "memory");
+}
+
+static inline void xsave(struct task_struct *tsk)
+{
+        /* This, however, we can work around by forcing the compiler to select
+           an addressing mode that doesn't require extended registers. */
+        __asm__ __volatile__(".byte " REX_PREFIX "0x0f,0xae,0x27"
+                             : : "D" (&(tsk->thread.xstate->xsave)),
+                                 "a" (-1), "d"(-1) : "memory");
+}
+#endif