374 files changed, 3870 insertions, 2221 deletions

diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 5b5aba404aac..73060819ed99 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -251,8 +251,6 @@ mono.txt
         - how to execute Mono-based .NET binaries with the help of BINFMT_MISC.
 moxa-smartio
         - file with info on installing/using Moxa multiport serial driver.
-mtrr.txt
-        - how to use PPro Memory Type Range Registers to increase performance.
 mutex-design.txt
         - info on the generic mutex subsystem.
 namespaces/
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1150444a21ab..329dcabe4c5e 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -463,12 +463,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         Range: 0 - 8192
                         Default: 64
 
-        disable_8254_timer
-        enable_8254_timer
-                        [IA32/X86_64] Disable/Enable interrupt 0 timer routing
-                        over the 8254 in addition to over the IO-APIC. The
-                        kernel tries to set a sensible default.
-
         hpet=           [X86-32,HPET] option to control HPET usage
                         Format: { enable (default) | disable | force }
                         disable: disable HPET and use PIT instead
@@ -1882,6 +1876,12 @@ and is between 256 and 4096 characters. It is defined in the file
         shapers=        [NET]
                         Maximal number of shapers.
 
+        show_msr=       [x86] show boot-time MSR settings
+                        Format: { <integer> }
+                        Show boot-time (BIOS-initialized) MSR settings.
+                        The parameter means the number of CPUs to show,
+                        for example 1 means boot CPU only.
+
         sim710=         [SCSI,HW]
                         See header of drivers/scsi/sim710.c.
 
diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX
new file mode 100644
index 000000000000..dbe3377754af
--- /dev/null
+++ b/Documentation/x86/00-INDEX
@@ -0,0 +1,4 @@
+00-INDEX
+        - this file
+mtrr.txt
+        - how to use x86 Memory Type Range Registers to increase performance
diff --git a/Documentation/x86/i386/boot.txt b/Documentation/x86/boot.txt
index 147bfe511cdd..83c0033ee9e0 100644
--- a/Documentation/x86/i386/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -308,7 +308,7 @@ Protocol:	2.00+
 
 Field name:     start_sys
 Type:           read
-Offset/size:    0x20c/4
+Offset/size:    0x20c/2
 Protocol:       2.00+
 
   The load low segment (0x1000).  Obsolete.
diff --git a/Documentation/mtrr.txt b/Documentation/x86/mtrr.txt
index c39ac395970e..cc071dc333c2 100644
--- a/Documentation/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -18,7 +18,7 @@ Richard Gooch
   The AMD K6-2 (stepping 8 and above) and K6-3 processors have two
   MTRRs. These are supported.  The AMD Athlon family provide 8 Intel
   style MTRRs.
-  
+
   The Centaur C6 (WinChip) has 8 MCRs, allowing write-combining. These
   are supported.
 
@@ -87,7 +87,7 @@ reg00: base=0x00000000 (   0MB), size=  64MB: write-back, count=1
 reg01: base=0xfb000000 (4016MB), size=  16MB: write-combining, count=1
 reg02: base=0xfb000000 (4016MB), size=   4kB: uncachable, count=1
 
-Some cards (especially Voodoo Graphics boards) need this 4 kB area 
+Some cards (especially Voodoo Graphics boards) need this 4 kB area
 excluded from the beginning of the region because it is used for
 registers.
 
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index 17965f927c15..c93ff5f4c0dd 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -14,6 +14,10 @@ PAT allows for different types of memory attributes. The most commonly used
 ones that will be supported at this time are Write-back, Uncached,
 Write-combined and Uncached Minus.
 
+
+PAT APIs
+--------
+
 There are many different APIs in the kernel that allows setting of memory
 attributes at the page level. In order to avoid aliasing, these interfaces
 should be used thoughtfully. Below is a table of interfaces available,
@@ -26,38 +30,38 @@ address range to avoid any aliasing.
 API                    |    RAM   |  ACPI,...  |  Reserved/Holes  |
 -----------------------|----------|------------|------------------|
                        |          |            |                  |
-ioremap                |    --    |    UC      |       UC         |
+ioremap                |    --    |    UC-     |       UC-        |
                        |          |            |                  |
 ioremap_cache          |    --    |    WB      |       WB         |
                        |          |            |                  |
-ioremap_nocache        |    --    |    UC      |       UC         |
+ioremap_nocache        |    --    |    UC-     |       UC-        |
                        |          |            |                  |
 ioremap_wc             |    --    |    --      |       WC         |
                        |          |            |                  |
-set_memory_uc          |    UC    |    --      |       --         |
+set_memory_uc          |    UC-   |    --      |       --         |
  set_memory_wb         |          |            |                  |
                        |          |            |                  |
 set_memory_wc          |    WC    |    --      |       --         |
  set_memory_wb         |          |            |                  |
                        |          |            |                  |
-pci sysfs resource     |    --    |    --      |       UC         |
+pci sysfs resource     |    --    |    --      |       UC-        |
                        |          |            |                  |
 pci sysfs resource_wc  |    --    |    --      |       WC         |
  is IORESOURCE_PREFETCH|          |            |                  |
                        |          |            |                  |
-pci proc               |    --    |    --      |       UC         |
+pci proc               |    --    |    --      |       UC-        |
  !PCIIOC_WRITE_COMBINE |          |            |                  |
                        |          |            |                  |
 pci proc               |    --    |    --      |       WC         |
  PCIIOC_WRITE_COMBINE  |          |            |                  |
                        |          |            |                  |
-/dev/mem               |    --    |    UC      |       UC         |
+/dev/mem               |    --    |  WB/WC/UC- |    WB/WC/UC-     |
  read-write            |          |            |                  |
                        |          |            |                  |
-/dev/mem               |    --    |    UC      |       UC         |
+/dev/mem               |    --    |    UC-     |       UC-        |
  mmap SYNC flag        |          |            |                  |
                        |          |            |                  |
-/dev/mem               |    --    |  WB/WC/UC  |    WB/WC/UC      |
+/dev/mem               |    --    |  WB/WC/UC- |    WB/WC/UC-     |
  mmap !SYNC flag       |          |(from exist-|  (from exist-    |
  and                   |          |  ing alias)|    ing alias)    |
  any alias to this area|          |            |                  |
@@ -68,7 +72,7 @@ pci proc               |    --    |    --      |       WC         |
  and                   |          |            |                  |
  MTRR says WB          |          |            |                  |
                        |          |            |                  |
-/dev/mem               |    --    |    --      |    UC_MINUS      |
+/dev/mem               |    --    |    --      |       UC-        |
  mmap !SYNC flag       |          |            |                  |
  no alias to this area |          |            |                  |
  and                   |          |            |                  |
@@ -98,3 +102,35 @@ types.
 
 Drivers should use set_memory_[uc|wc] to set access type for RAM ranges.
 
+
+PAT debugging
+-------------
+
+With CONFIG_DEBUG_FS enabled, PAT memtype list can be examined by
+
+# mount -t debugfs debugfs /sys/kernel/debug
+# cat /sys/kernel/debug/x86/pat_memtype_list
+PAT memtype list:
+uncached-minus @ 0x7fadf000-0x7fae0000
+uncached-minus @ 0x7fb19000-0x7fb1a000
+uncached-minus @ 0x7fb1a000-0x7fb1b000
+uncached-minus @ 0x7fb1b000-0x7fb1c000
+uncached-minus @ 0x7fb1c000-0x7fb1d000
+uncached-minus @ 0x7fb1d000-0x7fb1e000
+uncached-minus @ 0x7fb1e000-0x7fb25000
+uncached-minus @ 0x7fb25000-0x7fb26000
+uncached-minus @ 0x7fb26000-0x7fb27000
+uncached-minus @ 0x7fb27000-0x7fb28000
+uncached-minus @ 0x7fb28000-0x7fb2e000
+uncached-minus @ 0x7fb2e000-0x7fb2f000
+uncached-minus @ 0x7fb2f000-0x7fb30000
+uncached-minus @ 0x7fb31000-0x7fb32000
+uncached-minus @ 0x80000000-0x90000000
+
+This list shows physical address ranges and various PAT settings used to
+access those physical address ranges.
+
+Another, more verbose way of getting PAT related debug messages is with
+"debugpat" boot parameter. With this parameter, various debug messages are
+printed to dmesg log.
+
diff --git a/Documentation/x86/i386/usb-legacy-support.txt b/Documentation/x86/usb-legacy-support.txt
index 1894cdfc69d9..1894cdfc69d9 100644
--- a/Documentation/x86/i386/usb-legacy-support.txt
+++ b/Documentation/x86/usb-legacy-support.txt
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index b0c7b6c4abda..72ffb5373ec7 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -54,10 +54,6 @@ APICs
                  apicmaintimer. Useful when your PIT timer is totally
                  broken.
 
-   disable_8254_timer / enable_8254_timer
-                 Enable interrupt 0 timer routing over the 8254 in addition to over
-                 the IO-APIC. The kernel tries to set a sensible default.
-
 Early Console
 
    syntax: earlyprintk=vga
diff --git a/Documentation/x86/i386/zero-page.txt b/Documentation/x86/zero-page.txt
index 169ad423a3d1..169ad423a3d1 100644
--- a/Documentation/x86/i386/zero-page.txt
+++ b/Documentation/x86/zero-page.txt
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ed92864d1325..97f0d2b6dc0c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -29,6 +29,7 @@ config X86
         select HAVE_FTRACE
         select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
         select HAVE_ARCH_KGDB if !X86_VOYAGER
+        select HAVE_ARCH_TRACEHOOK
         select HAVE_GENERIC_DMA_COHERENT if X86_32
         select HAVE_EFFICIENT_UNALIGNED_ACCESS
 
@@ -1020,7 +1021,7 @@ config HAVE_ARCH_ALLOC_REMAP
 
 config ARCH_FLATMEM_ENABLE
         def_bool y
-        depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && X86_PC && !NUMA
+        depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
         def_bool y
@@ -1036,7 +1037,7 @@ config ARCH_SPARSEMEM_DEFAULT
 
 config ARCH_SPARSEMEM_ENABLE
         def_bool y
-        depends on X86_64 || NUMA || (EXPERIMENTAL && X86_PC)
+        depends on X86_64 || NUMA || (EXPERIMENTAL && X86_PC) || X86_GENERICARCH
         select SPARSEMEM_STATIC if X86_32
         select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
@@ -1117,10 +1118,10 @@ config MTRR
           You can safely say Y even if your machine doesn't have MTRRs, you'll
           just add about 9 KB to your kernel.
 
-          See <file:Documentation/mtrr.txt> for more information.
+          See <file:Documentation/x86/mtrr.txt> for more information.
 
 config MTRR_SANITIZER
-        bool
+        def_bool y
         prompt "MTRR cleanup support"
         depends on MTRR
         help
@@ -1131,7 +1132,7 @@ config MTRR_SANITIZER
           The largest mtrr entry size for a continous block can be set with
           mtrr_chunk_size.
 
-          If unsure, say N.
+          If unsure, say Y.
 
 config MTRR_SANITIZER_ENABLE_DEFAULT
         int "MTRR cleanup enable value (0-1)"
@@ -1191,7 +1192,6 @@ config IRQBALANCE
 config SECCOMP
         def_bool y
         prompt "Enable seccomp to safely compute untrusted bytecode"
-        depends on PROC_FS
         help
           This kernel feature is useful for number crunching applications
           that may need to compute untrusted bytecode during their
@@ -1199,7 +1199,7 @@ config SECCOMP
           the process as file descriptors supporting the read/write
           syscalls, it's possible to isolate those applications in
           their own address space using seccomp. Once seccomp is
-          enabled via /proc/<pid>/seccomp, it cannot be disabled
+          enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
           and the task is only allowed to execute a few safe syscalls
           defined by each seccomp mode.
 
@@ -1356,14 +1356,14 @@ config PHYSICAL_ALIGN
           Don't change this unless you know what you are doing.
 
 config HOTPLUG_CPU
-        bool "Support for suspend on SMP and hot-pluggable CPUs (EXPERIMENTAL)"
-        depends on SMP && HOTPLUG && EXPERIMENTAL && !X86_VOYAGER
+        bool "Support for hot-pluggable CPUs"
+        depends on SMP && HOTPLUG && !X86_VOYAGER
         ---help---
-          Say Y here to experiment with turning CPUs off and on, and to
-          enable suspend on SMP systems. CPUs can be controlled through
-          /sys/devices/system/cpu.
-          Say N if you want to disable CPU hotplug and don't need to
-          suspend.
+          Say Y here to allow turning CPUs off and on. CPUs can be
+          controlled through /sys/devices/system/cpu.
+          ( Note: power management support will enable this option
+            automatically on SMP systems. )
+          Say N if you want to disable CPU hotplug.
 
 config COMPAT_VDSO
         def_bool y
@@ -1378,6 +1378,51 @@ config COMPAT_VDSO
 
           If unsure, say Y.
 
+config CMDLINE_BOOL
+        bool "Built-in kernel command line"
+        default n
+        help
+          Allow for specifying boot arguments to the kernel at
+          build time.  On some systems (e.g. embedded ones), it is
+          necessary or convenient to provide some or all of the
+          kernel boot arguments with the kernel itself (that is,
+          to not rely on the boot loader to provide them.)
+
+          To compile command line arguments into the kernel,
+          set this option to 'Y', then fill in the
+          the boot arguments in CONFIG_CMDLINE.
+
+          Systems with fully functional boot loaders (i.e. non-embedded)
+          should leave this option set to 'N'.
+
+config CMDLINE
+        string "Built-in kernel command string"
+        depends on CMDLINE_BOOL
+        default ""
+        help
+          Enter arguments here that should be compiled into the kernel
+          image and used at boot time.  If the boot loader provides a
+          command line at boot time, it is appended to this string to
+          form the full kernel command line, when the system boots.
+
+          However, you can use the CONFIG_CMDLINE_OVERRIDE option to
+          change this behavior.
+
+          In most cases, the command line (whether built-in or provided
+          by the boot loader) should specify the device for the root
+          file system.
+
+config CMDLINE_OVERRIDE
+        bool "Built-in command line overrides boot loader arguments"
+        default n
+        depends on CMDLINE_BOOL
+        help
+          Set this option to 'Y' to have the kernel ignore the boot loader
+          command line, and use ONLY the built-in command line.
+
+          This is used to work around broken boot loaders.  This should
+          be set to 'N' under normal conditions.
+
 endmenu
 
 config ARCH_ENABLE_MEMORY_HOTPLUG
@@ -1773,7 +1818,7 @@ config COMPAT_FOR_U64_ALIGNMENT
 
 config SYSVIPC_COMPAT
         def_bool y
-        depends on X86_64 && COMPAT && SYSVIPC
+        depends on COMPAT && SYSVIPC
 
 endmenu
 
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b225219c448c..60a85768cfcb 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -418,3 +418,21 @@ config X86_MINIMUM_CPU_FAMILY
 config X86_DEBUGCTLMSR
         def_bool y
         depends on !(MK6 || MWINCHIPC6 || MWINCHIP2 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386)
+
+config X86_DS
+        bool "Debug Store support"
+        default y
+        help
+          Add support for Debug Store.
+          This allows the kernel to provide a memory buffer to the hardware
+          to store various profiling and tracing events.
+
+config X86_PTRACE_BTS
+        bool "ptrace interface to Branch Trace Store"
+        default y
+        depends on (X86_DS && X86_DEBUGCTLMSR)
+        help
+          Add a ptrace interface to allow collecting an execution trace
+          of the traced task.
+          This collects control flow changes in a (cyclic) buffer and allows
+          debuggers to fill in the gaps and show an execution trace of the debuggee.
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index ba7736cf2ec7..29c5fbf08392 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -137,14 +137,15 @@ relocated:
  */
         movl output_len(%ebx), %eax
         pushl %eax
+                        # push arguments for decompress_kernel:
         pushl %ebp      # output address
         movl input_len(%ebx), %eax
         pushl %eax      # input_len
         leal input_data(%ebx), %eax
         pushl %eax      # input_data
         leal boot_heap(%ebx), %eax
-        pushl %eax      # heap area as third argument
-        pushl %esi      # real mode pointer as second arg
+        pushl %eax      # heap area
+        pushl %esi      # real mode pointer
         call decompress_kernel
         addl $20, %esp
         popl %ecx
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 9fea73706479..5780d361105b 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -16,7 +16,7 @@
  */
 #undef CONFIG_PARAVIRT
 #ifdef CONFIG_X86_32
-#define _ASM_DESC_H_ 1
+#define ASM_X86__DESC_H 1
 #endif
 
 #ifdef CONFIG_X86_64
@@ -27,7 +27,7 @@
 #include <linux/linkage.h>
 #include <linux/screen_info.h>
 #include <linux/elf.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/page.h>
 #include <asm/boot.h>
 #include <asm/bootparam.h>
@@ -251,7 +251,7 @@ static void __putstr(int error, const char *s)
                                 y--;
                         }
                 } else {
-                        vidmem [(x + cols * y) * 2] = c;
+                        vidmem[(x + cols * y) * 2] = c;
                         if (++x >= cols) {
                                 x = 0;
                                 if (++y >= lines) {
@@ -277,7 +277,8 @@ static void *memset(void *s, int c, unsigned n)
         int i;
         char *ss = s;
 
-        for (i = 0; i < n; i++) ss[i] = c;
+        for (i = 0; i < n; i++)
+                ss[i] = c;
         return s;
 }
 
@@ -287,7 +288,8 @@ static void *memcpy(void *dest, const void *src, unsigned n)
         const char *s = src;
         char *d = dest;
 
-        for (i = 0; i < n; i++) d[i] = s[i];
+        for (i = 0; i < n; i++)
+                d[i] = s[i];
         return dest;
 }
 
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index af86e431acfa..b993062e9a5f 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -30,7 +30,6 @@ SYSSEG		= DEF_SYSSEG		/* system loaded at 0x10000 (65536) */
 SYSSIZE         = DEF_SYSSIZE           /* system size: # of 16-byte clicks */
                                         /* to be loaded */
 ROOT_DEV        = 0                     /* ROOT_DEV is now written by "build" */
-SWAP_DEV        = 0                     /* SWAP_DEV is now written by "build" */
 
 #ifndef SVGA_MODE
 #define SVGA_MODE ASK_VGA
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 104275e191a8..ef9a52005ec9 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.27-rc4
-# Mon Aug 25 15:04:00 2008
+# Linux kernel version: 2.6.27-rc5
+# Wed Sep  3 17:23:09 2008
 #
 # CONFIG_64BIT is not set
 CONFIG_X86_32=y
@@ -202,7 +202,7 @@ CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
 # CONFIG_M586 is not set
 # CONFIG_M586TSC is not set
 # CONFIG_M586MMX is not set
-# CONFIG_M686 is not set
+CONFIG_M686=y
 # CONFIG_MPENTIUMII is not set
 # CONFIG_MPENTIUMIII is not set
 # CONFIG_MPENTIUMM is not set
@@ -221,13 +221,14 @@ CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
 # CONFIG_MVIAC3_2 is not set
 # CONFIG_MVIAC7 is not set
 # CONFIG_MPSC is not set
-CONFIG_MCORE2=y
+# CONFIG_MCORE2 is not set
 # CONFIG_GENERIC_CPU is not set
 CONFIG_X86_GENERIC=y
 CONFIG_X86_CPU=y
 CONFIG_X86_CMPXCHG=y
 CONFIG_X86_L1_CACHE_SHIFT=7
 CONFIG_X86_XADD=y
+# CONFIG_X86_PPRO_FENCE is not set
 CONFIG_X86_WP_WORKS_OK=y
 CONFIG_X86_INVLPG=y
 CONFIG_X86_BSWAP=y
@@ -235,14 +236,15 @@ CONFIG_X86_POPAD_OK=y
 CONFIG_X86_INTEL_USERCOPY=y
 CONFIG_X86_USE_PPRO_CHECKSUM=y
 CONFIG_X86_TSC=y
+CONFIG_X86_CMOV=y
 CONFIG_X86_MINIMUM_CPU_FAMILY=4
 CONFIG_X86_DEBUGCTLMSR=y
 CONFIG_HPET_TIMER=y
 CONFIG_HPET_EMULATE_RTC=y
 CONFIG_DMI=y
 # CONFIG_IOMMU_HELPER is not set
-CONFIG_NR_CPUS=4
-# CONFIG_SCHED_SMT is not set
+CONFIG_NR_CPUS=64
+CONFIG_SCHED_SMT=y
 CONFIG_SCHED_MC=y
 # CONFIG_PREEMPT_NONE is not set
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -254,7 +256,8 @@ CONFIG_VM86=y
 # CONFIG_TOSHIBA is not set
 # CONFIG_I8K is not set
 CONFIG_X86_REBOOTFIXUPS=y
-# CONFIG_MICROCODE is not set
+CONFIG_MICROCODE=y
+CONFIG_MICROCODE_OLD_INTERFACE=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
 # CONFIG_NOHIGHMEM is not set
@@ -2115,7 +2118,7 @@ CONFIG_IO_DELAY_0X80=y
 CONFIG_DEFAULT_IO_DELAY_TYPE=0
 CONFIG_DEBUG_BOOT_PARAMS=y
 # CONFIG_CPA_DEBUG is not set
-# CONFIG_OPTIMIZE_INLINING is not set
+CONFIG_OPTIMIZE_INLINING=y
 
 #
 # Security options
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 678c8acefe04..e620ea6e2a7a 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.27-rc4
-# Mon Aug 25 14:40:46 2008
+# Linux kernel version: 2.6.27-rc5
+# Wed Sep  3 17:13:39 2008
 #
 CONFIG_64BIT=y
 # CONFIG_X86_32 is not set
@@ -218,17 +218,14 @@ CONFIG_X86_PC=y
 # CONFIG_MVIAC3_2 is not set
 # CONFIG_MVIAC7 is not set
 # CONFIG_MPSC is not set
-CONFIG_MCORE2=y
-# CONFIG_GENERIC_CPU is not set
+# CONFIG_MCORE2 is not set
+CONFIG_GENERIC_CPU=y
 CONFIG_X86_CPU=y
-CONFIG_X86_L1_CACHE_BYTES=64
-CONFIG_X86_INTERNODE_CACHE_BYTES=64
+CONFIG_X86_L1_CACHE_BYTES=128
+CONFIG_X86_INTERNODE_CACHE_BYTES=128
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_L1_CACHE_SHIFT=6
+CONFIG_X86_L1_CACHE_SHIFT=7
 CONFIG_X86_WP_WORKS_OK=y
-CONFIG_X86_INTEL_USERCOPY=y
-CONFIG_X86_USE_PPRO_CHECKSUM=y
-CONFIG_X86_P6_NOP=y
 CONFIG_X86_TSC=y
 CONFIG_X86_CMPXCHG64=y
 CONFIG_X86_CMOV=y
@@ -243,9 +240,8 @@ CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT=y
 CONFIG_AMD_IOMMU=y
 CONFIG_SWIOTLB=y
 CONFIG_IOMMU_HELPER=y
-# CONFIG_MAXSMP is not set
-CONFIG_NR_CPUS=4
-# CONFIG_SCHED_SMT is not set
+CONFIG_NR_CPUS=64
+CONFIG_SCHED_SMT=y
 CONFIG_SCHED_MC=y
 # CONFIG_PREEMPT_NONE is not set
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -254,7 +250,8 @@ CONFIG_X86_LOCAL_APIC=y
 CONFIG_X86_IO_APIC=y
 # CONFIG_X86_MCE is not set
 # CONFIG_I8K is not set
-# CONFIG_MICROCODE is not set
+CONFIG_MICROCODE=y
+CONFIG_MICROCODE_OLD_INTERFACE=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
 CONFIG_NUMA=y
@@ -290,7 +287,7 @@ CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
 CONFIG_MTRR=y
 # CONFIG_MTRR_SANITIZER is not set
-# CONFIG_X86_PAT is not set
+CONFIG_X86_PAT=y
 CONFIG_EFI=y
 CONFIG_SECCOMP=y
 # CONFIG_HZ_100 is not set
@@ -2089,7 +2086,7 @@ CONFIG_IO_DELAY_0X80=y
 CONFIG_DEFAULT_IO_DELAY_TYPE=0
 CONFIG_DEBUG_BOOT_PARAMS=y
 # CONFIG_CPA_DEBUG is not set
-# CONFIG_OPTIMIZE_INLINING is not set
+CONFIG_OPTIMIZE_INLINING=y
 
 #
 # Security options
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index a0e1dbe67dc1..127ec3f07214 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -85,8 +85,10 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
         dump->regs.ax = regs->ax;
         dump->regs.ds = current->thread.ds;
         dump->regs.es = current->thread.es;
-        asm("movl %%fs,%0" : "=r" (fs)); dump->regs.fs = fs;
-        asm("movl %%gs,%0" : "=r" (gs)); dump->regs.gs = gs;
+        savesegment(fs, fs);
+        dump->regs.fs = fs;
+        savesegment(gs, gs);
+        dump->regs.gs = gs;
         dump->regs.orig_ax = regs->orig_ax;
         dump->regs.ip = regs->ip;
         dump->regs.cs = regs->cs;
@@ -430,8 +432,9 @@ beyond_if:
         current->mm->start_stack =
                 (unsigned long)create_aout_tables((char __user *)bprm->p, bprm);
         /* start thread */
-        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 = ex.a_entry;
         (regs)->sp = current->mm->start_stack;
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 20af4c79579a..f1a2ac777faf 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -206,7 +206,7 @@ struct rt_sigframe
         { unsigned int cur;                                             \
           unsigned short pre;                                           \
           err |= __get_user(pre, &sc->seg);                             \
-          asm volatile("movl %%" #seg ",%0" : "=r" (cur));              \
+          savesegment(seg, cur);                                        \
           pre |= mask;                                                  \
           if (pre != cur) loadsegment(seg, pre); }
 
@@ -235,7 +235,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
          */
         err |= __get_user(gs, &sc->gs);
         gs |= 3;
-        asm("movl %%gs,%0" : "=r" (oldgs));
+        savesegment(gs, oldgs);
         if (gs != oldgs)
                 load_gs_index(gs);
 
@@ -355,14 +355,13 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
 {
         int tmp, err = 0;
 
-        tmp = 0;
-        __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
+        savesegment(gs, tmp);
         err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
-        __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
+        savesegment(fs, tmp);
         err |= __put_user(tmp, (unsigned int __user *)&sc->fs);
-        __asm__("movl %%ds,%0" : "=r"(tmp): "0"(tmp));
+        savesegment(ds, tmp);
         err |= __put_user(tmp, (unsigned int __user *)&sc->ds);
-        __asm__("movl %%es,%0" : "=r"(tmp): "0"(tmp));
+        savesegment(es, tmp);
         err |= __put_user(tmp, (unsigned int __user *)&sc->es);
 
         err |= __put_user((u32)regs->di, &sc->di);
@@ -498,8 +497,8 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
         regs->dx = 0;
         regs->cx = 0;
 
-        asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
-        asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+        loadsegment(ds, __USER32_DS);
+        loadsegment(es, __USER32_DS);
 
         regs->cs = __USER32_CS;
         regs->ss = __USER32_DS;
@@ -591,8 +590,8 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
         regs->dx = (unsigned long) &frame->info;
         regs->cx = (unsigned long) &frame->uc;
 
-        asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
-        asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+        loadsegment(ds, __USER32_DS);
+        loadsegment(es, __USER32_DS);
 
         regs->cs = __USER32_CS;
         regs->ss = __USER32_DS;
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index d3c64088b981..beda4232ce69 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -556,15 +556,6 @@ asmlinkage long sys32_rt_sigqueueinfo(int pid, int sig,
         return ret;
 }
 
-/* These are here just in case some old ia32 binary calls it. */
-asmlinkage long sys32_pause(void)
-{
-        current->state = TASK_INTERRUPTIBLE;
-        schedule();
-        return -ERESTARTNOHAND;
-}
-
-
 #ifdef CONFIG_SYSCTL_SYSCALL
 struct sysctl_ia32 {
         unsigned int    name;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index bfd10fd211cd..e5032d7b391d 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -58,7 +58,6 @@ EXPORT_SYMBOL(acpi_disabled);
 #ifdef  CONFIG_X86_64
 
 #include <asm/proto.h>
-#include <asm/genapic.h>
 
 #else                           /* X86 */
 
@@ -97,8 +96,6 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 #warning ACPI uses CMPXCHG, i486 and later hardware
 #endif
 
-static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
-
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */
@@ -160,6 +157,8 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 struct acpi_mcfg_allocation *pci_mmcfg_config;
 int pci_mmcfg_config_num;
 
+static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
+
 static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg)
 {
         if (!strcmp(mcfg->header.oem_id, "SGI"))
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 65a0c1b48696..fb04e49776ba 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -231,25 +231,25 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
                         continue;
                 if (*ptr > text_end)
                         continue;
-                text_poke(*ptr, ((unsigned char []){0xf0}), 1); /* add lock prefix */
+                /* turn DS segment override prefix into lock prefix */
+                text_poke(*ptr, ((unsigned char []){0xf0}), 1);
         };
 }
 
 static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 {
         u8 **ptr;
-        char insn[1];
 
         if (noreplace_smp)
                 return;
 
-        add_nops(insn, 1);
         for (ptr = start; ptr < end; ptr++) {
                 if (*ptr < text)
                         continue;
                 if (*ptr > text_end)
                         continue;
-                text_poke(*ptr, insn, 1);
+                /* turn lock prefix into DS segment override prefix */
+                text_poke(*ptr, ((unsigned char []){0x3E}), 1);
         };
 }
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 44e21826db11..9a32b37ee2ee 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -455,11 +455,11 @@ out:
                    force_iommu ||
                    valid_agp ||
                    fallback_aper_force) {
-                printk(KERN_ERR
+                printk(KERN_INFO
                         "Your BIOS doesn't leave a aperture memory hole\n");
-                printk(KERN_ERR
+                printk(KERN_INFO
                         "Please enable the IOMMU option in the BIOS setup\n");
-                printk(KERN_ERR
+                printk(KERN_INFO
                         "This costs you %d MB of RAM\n",
                                 32 << fallback_aper_order);
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 732d1f4e10ee..5145a6e72bbb 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,7 +228,6 @@
 #include <linux/suspend.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
-#include <linux/smp_lock.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index aa89387006fe..505543a75a56 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -22,7 +22,7 @@
 
 #define __NO_STUBS 1
 #undef __SYSCALL
-#undef _ASM_X86_64_UNISTD_H_
+#undef ASM_X86__UNISTD_64_H
 #define __SYSCALL(nr, sym) [nr] = 1,
 static char syscalls[] = {
 #include <asm/unistd.h>
diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index c639bd55391c..fdd585f9c53d 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -25,11 +25,11 @@ x86_bios_strerror(long status)
 {
         const char *str;
         switch (status) {
-        case  0: str = "Call completed without error"; break;
-        case -1: str = "Not implemented"; break;
-        case -2: str = "Invalid argument"; break;
-        case -3: str = "Call completed with error"; break;
-        default: str = "Unknown BIOS status code"; break;
+        case  0: str = "Call completed without error";  break;
+        case -1: str = "Not implemented";               break;
+        case -2: str = "Invalid argument";              break;
+        case -3: str = "Call completed with error";     break;
+        default: str = "Unknown BIOS status code";      break;
         }
         return str;
 }
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index a11f5d4477cd..305b465889b0 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -430,6 +430,49 @@ static __init int setup_noclflush(char *arg)
 }
 __setup("noclflush", setup_noclflush);
 
+struct msr_range {
+        unsigned min;
+        unsigned max;
+};
+
+static struct msr_range msr_range_array[] __cpuinitdata = {
+        { 0x00000000, 0x00000418},
+        { 0xc0000000, 0xc000040b},
+        { 0xc0010000, 0xc0010142},
+        { 0xc0011000, 0xc001103b},
+};
+
+static void __cpuinit print_cpu_msr(void)
+{
+        unsigned index;
+        u64 val;
+        int i;
+        unsigned index_min, index_max;
+
+        for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) {
+                index_min = msr_range_array[i].min;
+                index_max = msr_range_array[i].max;
+                for (index = index_min; index < index_max; index++) {
+                        if (rdmsrl_amd_safe(index, &val))
+                                continue;
+                        printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
+                }
+        }
+}
+
+static int show_msr __cpuinitdata;
+static __init int setup_show_msr(char *arg)
+{
+        int num;
+
+        get_option(&arg, &num);
+
+        if (num > 0)
+                show_msr = num;
+        return 1;
+}
+__setup("show_msr=", setup_show_msr);
+
 void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
 {
         if (c->x86_model_id[0])
@@ -439,6 +482,14 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
                 printk(KERN_CONT " stepping %02x\n", c->x86_mask);
         else
                 printk(KERN_CONT "\n");
+
+#ifdef CONFIG_SMP
+        if (c->cpu_index < show_msr)
+                print_cpu_msr();
+#else
+        if (show_msr)
+                print_cpu_msr();
+#endif
 }
 
 static __init int setup_disablecpuid(char *arg)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b75f2569b8f8..f113ef4595f6 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -222,10 +222,11 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
                         set_cpu_cap(c, X86_FEATURE_BTS);
                 if (!(l1 & (1<<12)))
                         set_cpu_cap(c, X86_FEATURE_PEBS);
+                ds_init_intel(c);
         }
 
         if (cpu_has_bts)
-                ds_init_intel(c);
+                ptrace_bts_init_intel(c);
 
         /*
          * See if we have a good local APIC by checking for buggy Pentia,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index cb7d3b6a80eb..4e8d77f01eeb 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -401,12 +401,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
                 tmp |= ~((1<<(hi - 1)) - 1);
 
                 if (tmp != mask_lo) {
-                        static int once = 1;
-
-                        if (once) {
-                                printk(KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n");
-                                once = 0;
-                        }
+                        WARN_ONCE(1, KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n");
                         mask_lo = tmp;
                 }
         }
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 84c480bb3715..4c4214690dd1 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -405,9 +405,9 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset)
                         }
                         /* RED-PEN: base can be > 32bit */ 
                         len += seq_printf(seq, 
-                                   "reg%02i: base=0x%05lx000 (%4luMB), size=%4lu%cB: %s, count=%d\n",
+                                   "reg%02i: base=0x%06lx000 (%5luMB), size=%5lu%cB, count=%d: %s\n",
                              i, base, base >> (20 - PAGE_SHIFT), size, factor,
-                             mtrr_attrib_to_str(type), mtrr_usage_table[i]);
+                             mtrr_usage_table[i], mtrr_attrib_to_str(type));
                 }
         }
         return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 885c8265e6b5..c78c04821ea1 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -729,7 +729,7 @@ struct var_mtrr_range_state {
         mtrr_type type;
 };
 
-struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
+static struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
 static int __initdata debug_print;
 
 static int __init
@@ -759,7 +759,8 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
         /* take out UC ranges */
         for (i = 0; i < num_var_ranges; i++) {
                 type = range_state[i].type;
-                if (type != MTRR_TYPE_UNCACHABLE)
+                if (type != MTRR_TYPE_UNCACHABLE &&
+                    type != MTRR_TYPE_WRPROT)
                         continue;
                 size = range_state[i].size_pfn;
                 if (!size)
@@ -836,6 +837,13 @@ static int __init enable_mtrr_cleanup_setup(char *str)
 }
 early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup);
 
+static int __init mtrr_cleanup_debug_setup(char *str)
+{
+        debug_print = 1;
+        return 0;
+}
+early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup);
+
 struct var_mtrr_state {
         unsigned long   range_startk;
         unsigned long   range_sizek;
@@ -898,6 +906,27 @@ set_var_mtrr_all(unsigned int address_bits)
         }
 }
 
+static unsigned long to_size_factor(unsigned long sizek, char *factorp)
+{
+        char factor;
+        unsigned long base = sizek;
+
+        if (base & ((1<<10) - 1)) {
+                /* not MB alignment */
+                factor = 'K';
+        } else if (base & ((1<<20) - 1)){
+                factor = 'M';
+                base >>= 10;
+        } else {
+                factor = 'G';
+                base >>= 20;
+        }
+
+        *factorp = factor;
+
+        return base;
+}
+
 static unsigned int __init
 range_to_mtrr(unsigned int reg, unsigned long range_startk,
               unsigned long range_sizek, unsigned char type)
@@ -919,13 +948,21 @@ range_to_mtrr(unsigned int reg, unsigned long range_startk,
                         align = max_align;
 
                 sizek = 1 << align;
-                if (debug_print)
+                if (debug_print) {
+                        char start_factor = 'K', size_factor = 'K';
+                        unsigned long start_base, size_base;
+
+                        start_base = to_size_factor(range_startk, &start_factor),
+                        size_base = to_size_factor(sizek, &size_factor),
+
                         printk(KERN_DEBUG "Setting variable MTRR %d, "
-                                "base: %ldMB, range: %ldMB, type %s\n",
-                                reg, range_startk >> 10, sizek >> 10,
+                                "base: %ld%cB, range: %ld%cB, type %s\n",
+                                reg, start_base, start_factor,
+                                size_base, size_factor,
                                 (type == MTRR_TYPE_UNCACHABLE)?"UC":
                                     ((type == MTRR_TYPE_WRBACK)?"WB":"Other")
                                 );
+                }
                 save_var_mtrr(reg++, range_startk, sizek, type);
                 range_startk += sizek;
                 range_sizek -= sizek;
@@ -970,6 +1007,8 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
         /* try to append some small hole */
         range0_basek = state->range_startk;
         range0_sizek = ALIGN(state->range_sizek, chunk_sizek);
+
+        /* no increase */
         if (range0_sizek == state->range_sizek) {
                 if (debug_print)
                         printk(KERN_DEBUG "rangeX: %016lx - %016lx\n",
@@ -980,13 +1019,40 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
                 return 0;
         }
 
-        range0_sizek -= chunk_sizek;
-        if (range0_sizek && sizek) {
-            while (range0_basek + range0_sizek > (basek + sizek)) {
-                range0_sizek -= chunk_sizek;
-                if (!range0_sizek)
-                        break;
-            }
+        /* only cut back, when it is not the last */
+        if (sizek) {
+                while (range0_basek + range0_sizek > (basek + sizek)) {
+                        if (range0_sizek >= chunk_sizek)
+                                range0_sizek -= chunk_sizek;
+                        else
+                                range0_sizek = 0;
+
+                        if (!range0_sizek)
+                                break;
+                }
+        }
+
+second_try:
+        range_basek = range0_basek + range0_sizek;
+
+        /* one hole in the middle */
+        if (range_basek > basek && range_basek <= (basek + sizek))
+                second_sizek = range_basek - basek;
+
+        if (range0_sizek > state->range_sizek) {
+
+                /* one hole in middle or at end */
+                hole_sizek = range0_sizek - state->range_sizek - second_sizek;
+
+                /* hole size should be less than half of range0 size */
+                if (hole_sizek >= (range0_sizek >> 1) &&
+                    range0_sizek >= chunk_sizek) {
+                        range0_sizek -= chunk_sizek;
+                        second_sizek = 0;
+                        hole_sizek = 0;
+
+                        goto second_try;
+                }
         }
 
         if (range0_sizek) {
@@ -996,50 +1062,28 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
                                 (range0_basek + range0_sizek)<<10);
                 state->reg = range_to_mtrr(state->reg, range0_basek,
                                 range0_sizek, MTRR_TYPE_WRBACK);
-
-        }
-
-        range_basek = range0_basek + range0_sizek;
-        range_sizek = chunk_sizek;
-
-        if (range_basek + range_sizek > basek &&
-            range_basek + range_sizek <= (basek + sizek)) {
-                /* one hole */
-                second_basek = basek;
-                second_sizek = range_basek + range_sizek - basek;
         }
 
-        /* if last piece, only could one hole near end */
-        if ((second_basek || !basek) &&
-            range_sizek - (state->range_sizek - range0_sizek) - second_sizek <
-            (chunk_sizek >> 1)) {
-                /*
-                 * one hole in middle (second_sizek is 0) or at end
-                 * (second_sizek is 0 )
-                 */
-                hole_sizek = range_sizek - (state->range_sizek - range0_sizek)
-                                 - second_sizek;
-                hole_basek = range_basek + range_sizek - hole_sizek
-                                 - second_sizek;
-        } else {
-                /* fallback for big hole, or several holes */
+        if (range0_sizek < state->range_sizek) {
+                /* need to handle left over */
                 range_sizek = state->range_sizek - range0_sizek;
-                second_basek = 0;
-                second_sizek = 0;
+
+                if (debug_print)
+                        printk(KERN_DEBUG "range: %016lx - %016lx\n",
+                                 range_basek<<10,
+                                 (range_basek + range_sizek)<<10);
+                state->reg = range_to_mtrr(state->reg, range_basek,
+                                 range_sizek, MTRR_TYPE_WRBACK);
         }
 
-        if (debug_print)
-                printk(KERN_DEBUG "range: %016lx - %016lx\n", range_basek<<10,
-                         (range_basek + range_sizek)<<10);
-        state->reg = range_to_mtrr(state->reg, range_basek, range_sizek,
-                                         MTRR_TYPE_WRBACK);
         if (hole_sizek) {
+                hole_basek = range_basek - hole_sizek - second_sizek;
                 if (debug_print)
                         printk(KERN_DEBUG "hole: %016lx - %016lx\n",
-                                 hole_basek<<10, (hole_basek + hole_sizek)<<10);
-                state->reg = range_to_mtrr(state->reg, hole_basek, hole_sizek,
-                                                 MTRR_TYPE_UNCACHABLE);
-
+                                 hole_basek<<10,
+                                 (hole_basek + hole_sizek)<<10);
+                state->reg = range_to_mtrr(state->reg, hole_basek,
+                                 hole_sizek, MTRR_TYPE_UNCACHABLE);
         }
 
         return second_sizek;
@@ -1154,11 +1198,11 @@ struct mtrr_cleanup_result {
 };
 
 /*
- * gran_size: 1M, 2M, ..., 2G
- * chunk size: gran_size, ..., 4G
- * so we need (2+13)*6
+ * gran_size: 64K, 128K, 256K, 512K, 1M, 2M, ..., 2G
+ * chunk size: gran_size, ..., 2G
+ * so we need (1+16)*8
  */
-#define NUM_RESULT      90
+#define NUM_RESULT      136
 #define PSHIFT          (PAGE_SHIFT - 10)
 
 static struct mtrr_cleanup_result __initdata result[NUM_RESULT];
@@ -1168,13 +1212,14 @@ static unsigned long __initdata min_loss_pfn[RANGE_NUM];
 static int __init mtrr_cleanup(unsigned address_bits)
 {
         unsigned long extra_remove_base, extra_remove_size;
-        unsigned long i, base, size, def, dummy;
+        unsigned long base, size, def, dummy;
         mtrr_type type;
         int nr_range, nr_range_new;
         u64 chunk_size, gran_size;
         unsigned long range_sums, range_sums_new;
         int index_good;
         int num_reg_good;
+        int i;
 
         /* extra one for all 0 */
         int num[MTRR_NUM_TYPES + 1];
@@ -1204,6 +1249,8 @@ static int __init mtrr_cleanup(unsigned address_bits)
                         continue;
                 if (!size)
                         type = MTRR_NUM_TYPES;
+                if (type == MTRR_TYPE_WRPROT)
+                        type = MTRR_TYPE_UNCACHABLE;
                 num[type]++;
         }
 
@@ -1216,23 +1263,57 @@ static int __init mtrr_cleanup(unsigned address_bits)
                 num_var_ranges - num[MTRR_NUM_TYPES])
                 return 0;
 
+        /* print original var MTRRs at first, for debugging: */
+        printk(KERN_DEBUG "original variable MTRRs\n");
+        for (i = 0; i < num_var_ranges; i++) {
+                char start_factor = 'K', size_factor = 'K';
+                unsigned long start_base, size_base;
+
+                size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
+                if (!size_base)
+                        continue;
+
+                size_base = to_size_factor(size_base, &size_factor),
+                start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
+                start_base = to_size_factor(start_base, &start_factor),
+                type = range_state[i].type;
+
+                printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
+                        i, start_base, start_factor,
+                        size_base, size_factor,
+                        (type == MTRR_TYPE_UNCACHABLE) ? "UC" :
+                            ((type == MTRR_TYPE_WRPROT) ? "WP" :
+                             ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
+                        );
+        }
+
         memset(range, 0, sizeof(range));
         extra_remove_size = 0;
-        if (mtrr_tom2) {
-                extra_remove_base = 1 << (32 - PAGE_SHIFT);
+        extra_remove_base = 1 << (32 - PAGE_SHIFT);
+        if (mtrr_tom2)
                 extra_remove_size =
                         (mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base;
-        }
         nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base,
                                           extra_remove_size);
+        /*
+         * [0, 1M) should always be coverred by var mtrr with WB
+         * and fixed mtrrs should take effective before var mtrr for it
+         */
+        nr_range = add_range_with_merge(range, nr_range, 0,
+                                        (1ULL<<(20 - PAGE_SHIFT)) - 1);
+        /* sort the ranges */
+        sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+
         range_sums = sum_ranges(range, nr_range);
         printk(KERN_INFO "total RAM coverred: %ldM\n",
                range_sums >> (20 - PAGE_SHIFT));
 
         if (mtrr_chunk_size && mtrr_gran_size) {
                 int num_reg;
+                char gran_factor, chunk_factor, lose_factor;
+                unsigned long gran_base, chunk_base, lose_base;
 
-                debug_print = 1;
+                debug_print++;
                 /* convert ranges to var ranges state */
                 num_reg = x86_setup_var_mtrrs(range, nr_range, mtrr_chunk_size,
                                               mtrr_gran_size);
@@ -1256,34 +1337,48 @@ static int __init mtrr_cleanup(unsigned address_bits)
                         result[i].lose_cover_sizek =
                                 (range_sums - range_sums_new) << PSHIFT;
 
-                printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t",
-                         result[i].bad?"*BAD*":" ", result[i].gran_sizek >> 10,
-                         result[i].chunk_sizek >> 10);
-                printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ldM \n",
+                gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+                chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+                lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+                printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
+                         result[i].bad?"*BAD*":" ",
+                         gran_base, gran_factor, chunk_base, chunk_factor);
+                printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
                          result[i].num_reg, result[i].bad?"-":"",
-                         result[i].lose_cover_sizek >> 10);
+                         lose_base, lose_factor);
                 if (!result[i].bad) {
                         set_var_mtrr_all(address_bits);
                         return 1;
                 }
                 printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
                        "will find optimal one\n");
-                debug_print = 0;
+                debug_print--;
                 memset(result, 0, sizeof(result[0]));
         }
 
         i = 0;
         memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn));
         memset(result, 0, sizeof(result));
-        for (gran_size = (1ULL<<20); gran_size < (1ULL<<32); gran_size <<= 1) {
-                for (chunk_size = gran_size; chunk_size < (1ULL<<33);
+        for (gran_size = (1ULL<<16); gran_size < (1ULL<<32); gran_size <<= 1) {
+                char gran_factor;
+                unsigned long gran_base;
+
+                if (debug_print)
+                        gran_base = to_size_factor(gran_size >> 10, &gran_factor);
+
+                for (chunk_size = gran_size; chunk_size < (1ULL<<32);
                      chunk_size <<= 1) {
                         int num_reg;
 
-                        if (debug_print)
-                                printk(KERN_INFO
-                               "\ngran_size: %lldM   chunk_size_size: %lldM\n",
-                                       gran_size >> 20, chunk_size >> 20);
+                        if (debug_print) {
+                                char chunk_factor;
+                                unsigned long chunk_base;
+
+                                chunk_base = to_size_factor(chunk_size>>10, &chunk_factor),
+                                printk(KERN_INFO "\n");
+                                printk(KERN_INFO "gran_size: %ld%c   chunk_size: %ld%c \n",
+                                       gran_base, gran_factor, chunk_base, chunk_factor);
+                        }
                         if (i >= NUM_RESULT)
                                 continue;
 
@@ -1326,12 +1421,18 @@ static int __init mtrr_cleanup(unsigned address_bits)
 
         /* print out all */
         for (i = 0; i < NUM_RESULT; i++) {
-                printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t",
-                       result[i].bad?"*BAD* ":" ", result[i].gran_sizek >> 10,
-                       result[i].chunk_sizek >> 10);
-                printk(KERN_CONT "num_reg: %d \tlose RAM: %s%ldM\n",
-                       result[i].num_reg, result[i].bad?"-":"",
-                       result[i].lose_cover_sizek >> 10);
+                char gran_factor, chunk_factor, lose_factor;
+                unsigned long gran_base, chunk_base, lose_base;
+
+                gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+                chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+                lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+                printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
+                         result[i].bad?"*BAD*":" ",
+                         gran_base, gran_factor, chunk_base, chunk_factor);
+                printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
+                         result[i].num_reg, result[i].bad?"-":"",
+                         lose_base, lose_factor);
         }
 
         /* try to find the optimal index */
@@ -1339,10 +1440,8 @@ static int __init mtrr_cleanup(unsigned address_bits)
                 nr_mtrr_spare_reg = num_var_ranges - 1;
         num_reg_good = -1;
         for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
-                if (!min_loss_pfn[i]) {
+                if (!min_loss_pfn[i])
                         num_reg_good = i;
-                        break;
-                }
         }
 
         index_good = -1;
@@ -1358,21 +1457,26 @@ static int __init mtrr_cleanup(unsigned address_bits)
         }
 
         if (index_good != -1) {
+                char gran_factor, chunk_factor, lose_factor;
+                unsigned long gran_base, chunk_base, lose_base;
+
                 printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
                 i = index_good;
-                printk(KERN_INFO "gran_size: %ldM \tchunk_size: %ldM \t",
-                                result[i].gran_sizek >> 10,
-                                result[i].chunk_sizek >> 10);
-                printk(KERN_CONT "num_reg: %d \tlose RAM: %ldM\n",
-                                result[i].num_reg,
-                                result[i].lose_cover_sizek >> 10);
+                gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+                chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+                lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+                printk(KERN_INFO "gran_size: %ld%c \tchunk_size: %ld%c \t",
+                         gran_base, gran_factor, chunk_base, chunk_factor);
+                printk(KERN_CONT "num_reg: %d  \tlose RAM: %ld%c\n",
+                         result[i].num_reg, lose_base, lose_factor);
                 /* convert ranges to var ranges state */
                 chunk_size = result[i].chunk_sizek;
                 chunk_size <<= 10;
                 gran_size = result[i].gran_sizek;
                 gran_size <<= 10;
-                debug_print = 1;
+                debug_print++;
                 x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
+                debug_print--;
                 set_var_mtrr_all(address_bits);
                 return 1;
         }
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 05cc22dbd4ff..6bff382094f5 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -295,13 +295,19 @@ static int setup_k7_watchdog(unsigned nmi_hz)
         /* setup the timer */
         wrmsr(evntsel_msr, evntsel, 0);
         write_watchdog_counter(perfctr_msr, "K7_PERFCTR0",nmi_hz);
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        evntsel |= K7_EVNTSEL_ENABLE;
-        wrmsr(evntsel_msr, evntsel, 0);
 
+        /* initialize the wd struct before enabling */
         wd->perfctr_msr = perfctr_msr;
         wd->evntsel_msr = evntsel_msr;
         wd->cccr_msr = 0;  /* unused */
+
+        /* ok, everything is initialized, announce that we're set */
+        cpu_nmi_set_wd_enabled();
+
+        apic_write(APIC_LVTPC, APIC_DM_NMI);
+        evntsel |= K7_EVNTSEL_ENABLE;
+        wrmsr(evntsel_msr, evntsel, 0);
+
         return 1;
 }
 
@@ -379,13 +385,19 @@ static int setup_p6_watchdog(unsigned nmi_hz)
         wrmsr(evntsel_msr, evntsel, 0);
         nmi_hz = adjust_for_32bit_ctr(nmi_hz);
         write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0",nmi_hz);
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        evntsel |= P6_EVNTSEL0_ENABLE;
-        wrmsr(evntsel_msr, evntsel, 0);
 
+        /* initialize the wd struct before enabling */
         wd->perfctr_msr = perfctr_msr;
         wd->evntsel_msr = evntsel_msr;
         wd->cccr_msr = 0;  /* unused */
+
+        /* ok, everything is initialized, announce that we're set */
+        cpu_nmi_set_wd_enabled();
+
+        apic_write(APIC_LVTPC, APIC_DM_NMI);
+        evntsel |= P6_EVNTSEL0_ENABLE;
+        wrmsr(evntsel_msr, evntsel, 0);
+
         return 1;
 }
 
@@ -432,6 +444,27 @@ static const struct wd_ops p6_wd_ops = {
 #define P4_CCCR_ENABLE          (1 << 12)
 #define P4_CCCR_OVF             (1 << 31)
 
+#define P4_CONTROLS 18
+static unsigned int p4_controls[18] = {
+        MSR_P4_BPU_CCCR0,
+        MSR_P4_BPU_CCCR1,
+        MSR_P4_BPU_CCCR2,
+        MSR_P4_BPU_CCCR3,
+        MSR_P4_MS_CCCR0,
+        MSR_P4_MS_CCCR1,
+        MSR_P4_MS_CCCR2,
+        MSR_P4_MS_CCCR3,
+        MSR_P4_FLAME_CCCR0,
+        MSR_P4_FLAME_CCCR1,
+        MSR_P4_FLAME_CCCR2,
+        MSR_P4_FLAME_CCCR3,
+        MSR_P4_IQ_CCCR0,
+        MSR_P4_IQ_CCCR1,
+        MSR_P4_IQ_CCCR2,
+        MSR_P4_IQ_CCCR3,
+        MSR_P4_IQ_CCCR4,
+        MSR_P4_IQ_CCCR5,
+};
 /*
  * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
  * CRU_ESCR0 (with any non-null event selector) through a complemented
@@ -473,6 +506,26 @@ static int setup_p4_watchdog(unsigned nmi_hz)
                 evntsel_msr = MSR_P4_CRU_ESCR0;
                 cccr_msr = MSR_P4_IQ_CCCR0;
                 cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
+
+                /*
+                 * If we're on the kdump kernel or other situation, we may
+                 * still have other performance counter registers set to
+                 * interrupt and they'll keep interrupting forever because
+                 * of the P4_CCCR_OVF quirk. So we need to ACK all the
+                 * pending interrupts and disable all the registers here,
+                 * before reenabling the NMI delivery. Refer to p4_rearm()
+                 * about the P4_CCCR_OVF quirk.
+                 */
+                if (reset_devices) {
+                        unsigned int low, high;
+                        int i;
+
+                        for (i = 0; i < P4_CONTROLS; i++) {
+                                rdmsr(p4_controls[i], low, high);
+                                low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF);
+                                wrmsr(p4_controls[i], low, high);
+                        }
+                }
         } else {
                 /* logical cpu 1 */
                 perfctr_msr = MSR_P4_IQ_PERFCTR1;
@@ -499,12 +552,17 @@ static int setup_p4_watchdog(unsigned nmi_hz)
         wrmsr(evntsel_msr, evntsel, 0);
         wrmsr(cccr_msr, cccr_val, 0);
         write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz);
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        cccr_val |= P4_CCCR_ENABLE;
-        wrmsr(cccr_msr, cccr_val, 0);
+
         wd->perfctr_msr = perfctr_msr;
         wd->evntsel_msr = evntsel_msr;
         wd->cccr_msr = cccr_msr;
+
+        /* ok, everything is initialized, announce that we're set */
+        cpu_nmi_set_wd_enabled();
+
+        apic_write(APIC_LVTPC, APIC_DM_NMI);
+        cccr_val |= P4_CCCR_ENABLE;
+        wrmsr(cccr_msr, cccr_val, 0);
         return 1;
 }
 
@@ -620,13 +678,17 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz)
         wrmsr(evntsel_msr, evntsel, 0);
         nmi_hz = adjust_for_32bit_ctr(nmi_hz);
         write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz);
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
-        wrmsr(evntsel_msr, evntsel, 0);
 
         wd->perfctr_msr = perfctr_msr;
         wd->evntsel_msr = evntsel_msr;
         wd->cccr_msr = 0;  /* unused */
+
+        /* ok, everything is initialized, announce that we're set */
+        cpu_nmi_set_wd_enabled();
+
+        apic_write(APIC_LVTPC, APIC_DM_NMI);
+        evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+        wrmsr(evntsel_msr, evntsel, 0);
         intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
         return 1;
 }
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 8e9cd6a8ec12..6a44d6465991 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -36,7 +36,6 @@
 #include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
-#include <linux/smp_lock.h>
 #include <linux/device.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 15e6c6bc4a46..e90a60ef10c2 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -7,9 +7,8 @@
 
 #include <linux/errno.h>
 #include <linux/crash_dump.h>
-
-#include <asm/uaccess.h>
-#include <asm/io.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
 
 /**
  * copy_oldmem_page - copy one page from "oldmem"
@@ -25,7 +24,7 @@
  * in the current kernel. We stitch up a pte, similar to kmap_atomic.
  */
 ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-                               size_t csize, unsigned long offset, int userbuf)
+                size_t csize, unsigned long offset, int userbuf)
 {
         void  *vaddr;
 
@@ -33,14 +32,16 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
                 return 0;
 
         vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+        if (!vaddr)
+                return -ENOMEM;
 
         if (userbuf) {
-                if (copy_to_user(buf, (vaddr + offset), csize)) {
+                if (copy_to_user(buf, vaddr + offset, csize)) {
                         iounmap(vaddr);
                         return -EFAULT;
                 }
         } else
-        memcpy(buf, (vaddr + offset), csize);
+                memcpy(buf, vaddr + offset, csize);
 
         iounmap(vaddr);
         return csize;
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 11c11b8ec48d..2b69994fd3a8 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -2,26 +2,49 @@
  * Debug Store 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
  */
 
+
+#ifdef CONFIG_X86_DS
+
 #include <asm/ds.h>
 
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+
+
+/*
+ * The configuration for a particular DS hardware implementation.
+ */
+struct ds_configuration {
+        /* the size of the DS structure in bytes */
+        unsigned char  sizeof_ds;
+        /* the size of one pointer-typed field in the DS structure in bytes;
+           this covers the first 8 fields related to buffer management. */
+        unsigned char  sizeof_field;
+        /* the size of a BTS/PEBS record in bytes */
+        unsigned char  sizeof_rec[2];
+};
+static struct ds_configuration ds_cfg;
 
 
 /*
@@ -44,378 +67,747 @@
  *   (interrupt occurs when write pointer passes interrupt pointer)
  * - value to which counter is reset following counter overflow
  *
- * On later architectures, the last branch recording hardware uses
- * 64bit pointers even in 32bit mode.
- *
- *
- * Branch Trace Store (BTS) records store information about control
- * flow changes. They at least provide the following information:
- * - source linear address
- * - destination linear address
+ * Later architectures use 64bit pointers throughout, whereas earlier
+ * architectures use 32bit pointers in 32bit mode.
  *
- * Netburst supported a predicated bit that had been dropped in later
- * architectures. We do not suppor it.
  *
+ * We compute the base address for the first 8 fields based on:
+ * - the field size stored in the DS configuration
+ * - the relative field position
+ * - an offset giving the start of the respective region
  *
- * In order to abstract from the actual DS and BTS layout, we describe
- * the access to the relevant fields.
- * Thanks to Andi Kleen for proposing this design.
+ * This offset is further used to index various arrays holding
+ * information for BTS and PEBS at the respective index.
  *
- * The implementation, however, is not as general as it might seem. In
- * order to stay somewhat simple and efficient, we assume an
- * underlying unsigned type (mostly a pointer type) and we expect the
- * field to be at least as big as that type.
+ * On later 32bit processors, we only access the lower 32bit of the
+ * 64bit pointer fields. The upper halves will be zeroed out.
  */
 
-/*
- * A special from_ip address to indicate that the BTS record is an
- * info record that needs to be interpreted or skipped.
- */
-#define BTS_ESCAPE_ADDRESS (-1)
+enum ds_field {
+        ds_buffer_base = 0,
+        ds_index,
+        ds_absolute_maximum,
+        ds_interrupt_threshold,
+};
 
-/*
- * A field access descriptor
- */
-struct access_desc {
-        unsigned char offset;
-        unsigned char size;
+enum ds_qualifier {
+        ds_bts  = 0,
+        ds_pebs
 };
 
+static inline unsigned long ds_get(const unsigned char *base,
+                                   enum ds_qualifier qual, enum ds_field field)
+{
+        base += (ds_cfg.sizeof_field * (field + (4 * qual)));
+        return *(unsigned long *)base;
+}
+
+static inline void ds_set(unsigned char *base, enum ds_qualifier qual,
+                          enum ds_field field, unsigned long value)
+{
+        base += (ds_cfg.sizeof_field * (field + (4 * qual)));
+        (*(unsigned long *)base) = value;
+}
+
+
 /*
- * The configuration for a particular DS/BTS hardware implementation.
+ * Locking is done only for allocating BTS or PEBS resources and for
+ * guarding context and buffer memory allocation.
+ *
+ * Most functions require the current task to own the ds context part
+ * they are going to access. All the locking is done when validating
+ * access to the context.
  */
-struct ds_configuration {
-        /* the DS configuration */
-        unsigned char  sizeof_ds;
-        struct access_desc bts_buffer_base;
-        struct access_desc bts_index;
-        struct access_desc bts_absolute_maximum;
-        struct access_desc bts_interrupt_threshold;
-        /* the BTS configuration */
-        unsigned char  sizeof_bts;
-        struct access_desc from_ip;
-        struct access_desc to_ip;
-        /* BTS variants used to store additional information like
-           timestamps */
-        struct access_desc info_type;
-        struct access_desc info_data;
-        unsigned long debugctl_mask;
-};
+static spinlock_t ds_lock = __SPIN_LOCK_UNLOCKED(ds_lock);
 
 /*
- * The global configuration used by the below accessor functions
+ * Validate that the current task is allowed to access the BTS/PEBS
+ * buffer of the parameter task.
+ *
+ * Returns 0, if access is granted; -Eerrno, otherwise.
  */
-static struct ds_configuration ds_cfg;
+static inline int ds_validate_access(struct ds_context *context,
+                                     enum ds_qualifier qual)
+{
+        if (!context)
+                return -EPERM;
+
+        if (context->owner[qual] == current)
+                return 0;
+
+        return -EPERM;
+}
+
 
 /*
- * Accessor functions for some DS and BTS fields using the above
- * global ptrace_bts_cfg.
+ * We either support (system-wide) per-cpu or per-thread allocation.
+ * We distinguish the two based on the task_struct pointer, where a
+ * NULL pointer indicates per-cpu allocation for the current cpu.
+ *
+ * Allocations are use-counted. As soon as resources are allocated,
+ * further allocations must be of the same type (per-cpu or
+ * per-thread). We model this by counting allocations (i.e. the number
+ * of tracers of a certain type) for one type negatively:
+ *   =0  no tracers
+ *   >0  number of per-thread tracers
+ *   <0  number of per-cpu tracers
+ *
+ * The below functions to get and put tracers and to check the
+ * allocation type require the ds_lock to be held by the caller.
+ *
+ * Tracers essentially gives the number of ds contexts for a certain
+ * type of allocation.
  */
-static inline unsigned long get_bts_buffer_base(char *base)
+static long tracers;
+
+static inline void get_tracer(struct task_struct *task)
 {
-        return *(unsigned long *)(base + ds_cfg.bts_buffer_base.offset);
+        tracers += (task ? 1 : -1);
 }
-static inline void set_bts_buffer_base(char *base, unsigned long value)
+
+static inline void put_tracer(struct task_struct *task)
 {
-        (*(unsigned long *)(base + ds_cfg.bts_buffer_base.offset)) = value;
+        tracers -= (task ? 1 : -1);
 }
-static inline unsigned long get_bts_index(char *base)
+
+static inline int check_tracer(struct task_struct *task)
 {
-        return *(unsigned long *)(base + ds_cfg.bts_index.offset);
+        return (task ? (tracers >= 0) : (tracers <= 0));
 }
-static inline void set_bts_index(char *base, unsigned long value)
+
+
+/*
+ * The DS context is either attached to a thread or to a cpu:
+ * - in the former case, the thread_struct contains a pointer to the
+ *   attached context.
+ * - in the latter case, we use a static array of per-cpu context
+ *   pointers.
+ *
+ * Contexts are use-counted. They are allocated on first access and
+ * deallocated when the last user puts the context.
+ *
+ * We distinguish between an allocating and a non-allocating get of a
+ * context:
+ * - the allocating get is used for requesting BTS/PEBS resources. It
+ *   requires the caller to hold the global ds_lock.
+ * - the non-allocating get is used for all other cases. A
+ *   non-existing context indicates an error. It acquires and releases
+ *   the ds_lock itself for obtaining the context.
+ *
+ * A context and its DS configuration are allocated and deallocated
+ * together. A context always has a DS configuration of the
+ * appropriate size.
+ */
+static DEFINE_PER_CPU(struct ds_context *, system_context);
+
+#define this_system_context per_cpu(system_context, smp_processor_id())
+
+/*
+ * Returns the pointer to the parameter task's context or to the
+ * system-wide context, if task is NULL.
+ *
+ * Increases the use count of the returned context, if not NULL.
+ */
+static inline struct ds_context *ds_get_context(struct task_struct *task)
 {
-        (*(unsigned long *)(base + ds_cfg.bts_index.offset)) = value;
+        struct ds_context *context;
+
+        spin_lock(&ds_lock);
+
+        context = (task ? task->thread.ds_ctx : this_system_context);
+        if (context)
+                context->count++;
+
+        spin_unlock(&ds_lock);
+
+        return context;
 }
-static inline unsigned long get_bts_absolute_maximum(char *base)
+
+/*
+ * Same as ds_get_context, but allocates the context and it's DS
+ * structure, if necessary; returns NULL; if out of memory.
+ *
+ * pre: requires ds_lock to be held
+ */
+static inline struct ds_context *ds_alloc_context(struct task_struct *task)
 {
-        return *(unsigned long *)(base + ds_cfg.bts_absolute_maximum.offset);
+        struct ds_context **p_context =
+                (task ? &task->thread.ds_ctx : &this_system_context);
+        struct ds_context *context = *p_context;
+
+        if (!context) {
+                context = kzalloc(sizeof(*context), GFP_KERNEL);
+
+                if (!context)
+                        return NULL;
+
+                context->ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
+                if (!context->ds) {
+                        kfree(context);
+                        return NULL;
+                }
+
+                *p_context = context;
+
+                context->this = p_context;
+                context->task = task;
+
+                if (task)
+                        set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
+
+                if (!task || (task == current))
+                        wrmsr(MSR_IA32_DS_AREA, (unsigned long)context->ds, 0);
+
+                get_tracer(task);
+        }
+
+        context->count++;
+
+        return context;
 }
-static inline void set_bts_absolute_maximum(char *base, unsigned long value)
+
+/*
+ * Decreases the use count of the parameter context, if not NULL.
+ * Deallocates the context, if the use count reaches zero.
+ */
+static inline void ds_put_context(struct ds_context *context)
 {
-        (*(unsigned long *)(base + ds_cfg.bts_absolute_maximum.offset)) = value;
+        if (!context)
+                return;
+
+        spin_lock(&ds_lock);
+
+        if (--context->count)
+                goto out;
+
+        *(context->this) = NULL;
+
+        if (context->task)
+                clear_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+
+        if (!context->task || (context->task == current))
+                wrmsrl(MSR_IA32_DS_AREA, 0);
+
+        put_tracer(context->task);
+
+        /* free any leftover buffers from tracers that did not
+         * deallocate them properly. */
+        kfree(context->buffer[ds_bts]);
+        kfree(context->buffer[ds_pebs]);
+        kfree(context->ds);
+        kfree(context);
+ out:
+        spin_unlock(&ds_lock);
 }
-static inline unsigned long get_bts_interrupt_threshold(char *base)
+
+
+/*
+ * Handle a buffer overflow
+ *
+ * task: the task whose buffers are overflowing;
+ *       NULL for a buffer overflow on the current cpu
+ * context: the ds context
+ * qual: the buffer type
+ */
+static void ds_overflow(struct task_struct *task, struct ds_context *context,
+                        enum ds_qualifier qual)
 {
-        return *(unsigned long *)(base + ds_cfg.bts_interrupt_threshold.offset);
+        if (!context)
+                return;
+
+        if (context->callback[qual])
+                (*context->callback[qual])(task);
+
+        /* todo: do some more overflow handling */
 }
-static inline void set_bts_interrupt_threshold(char *base, unsigned long value)
+
+
+/*
+ * Allocate a non-pageable buffer of the parameter size.
+ * Checks the memory and the locked memory rlimit.
+ *
+ * Returns the buffer, if successful;
+ *         NULL, if out of memory or rlimit exceeded.
+ *
+ * size: the requested buffer size in bytes
+ * pages (out): if not NULL, contains the number of pages reserved
+ */
+static inline void *ds_allocate_buffer(size_t size, unsigned int *pages)
 {
-        (*(unsigned long *)(base + ds_cfg.bts_interrupt_threshold.offset)) = value;
+        unsigned long rlim, vm, pgsz;
+        void *buffer;
+
+        pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+        rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+        vm   = current->mm->total_vm  + pgsz;
+        if (rlim < vm)
+                return NULL;
+
+        rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+        vm   = current->mm->locked_vm  + pgsz;
+        if (rlim < vm)
+                return NULL;
+
+        buffer = kzalloc(size, GFP_KERNEL);
+        if (!buffer)
+                return NULL;
+
+        current->mm->total_vm  += pgsz;
+        current->mm->locked_vm += pgsz;
+
+        if (pages)
+                *pages = pgsz;
+
+        return buffer;
 }
-static inline unsigned long get_from_ip(char *base)
+
+static int ds_request(struct task_struct *task, void *base, size_t size,
+                      ds_ovfl_callback_t ovfl, enum ds_qualifier qual)
 {
-        return *(unsigned long *)(base + ds_cfg.from_ip.offset);
+        struct ds_context *context;
+        unsigned long buffer, adj;
+        const unsigned long alignment = (1 << 3);
+        int error = 0;
+
+        if (!ds_cfg.sizeof_ds)
+                return -EOPNOTSUPP;
+
+        /* we require some space to do alignment adjustments below */
+        if (size < (alignment + ds_cfg.sizeof_rec[qual]))
+                return -EINVAL;
+
+        /* buffer overflow notification is not yet implemented */
+        if (ovfl)
+                return -EOPNOTSUPP;
+
+
+        spin_lock(&ds_lock);
+
+        if (!check_tracer(task))
+                return -EPERM;
+
+        error = -ENOMEM;
+        context = ds_alloc_context(task);
+        if (!context)
+                goto out_unlock;
+
+        error = -EALREADY;
+        if (context->owner[qual] == current)
+                goto out_unlock;
+        error = -EPERM;
+        if (context->owner[qual] != NULL)
+                goto out_unlock;
+        context->owner[qual] = current;
+
+        spin_unlock(&ds_lock);
+
+
+        error = -ENOMEM;
+        if (!base) {
+                base = ds_allocate_buffer(size, &context->pages[qual]);
+                if (!base)
+                        goto out_release;
+
+                context->buffer[qual]   = base;
+        }
+        error = 0;
+
+        context->callback[qual] = ovfl;
+
+        /* adjust the buffer address and size to meet alignment
+         * constraints:
+         * - buffer is double-word aligned
+         * - size is multiple of record size
+         *
+         * We checked the size at the very beginning; we have enough
+         * space to do the adjustment.
+         */
+        buffer = (unsigned long)base;
+
+        adj = ALIGN(buffer, alignment) - buffer;
+        buffer += adj;
+        size   -= adj;
+
+        size /= ds_cfg.sizeof_rec[qual];
+        size *= ds_cfg.sizeof_rec[qual];
+
+        ds_set(context->ds, qual, ds_buffer_base, buffer);
+        ds_set(context->ds, qual, ds_index, buffer);
+        ds_set(context->ds, qual, ds_absolute_maximum, buffer + size);
+
+        if (ovfl) {
+                /* todo: select a suitable interrupt threshold */
+        } else
+                ds_set(context->ds, qual,
+                       ds_interrupt_threshold, buffer + size + 1);
+
+        /* we keep the context until ds_release */
+        return error;
+
+ out_release:
+        context->owner[qual] = NULL;
+        ds_put_context(context);
+        return error;
+
+ out_unlock:
+        spin_unlock(&ds_lock);
+        ds_put_context(context);
+        return error;
 }
-static inline void set_from_ip(char *base, unsigned long value)
+
+int ds_request_bts(struct task_struct *task, void *base, size_t size,
+                   ds_ovfl_callback_t ovfl)
 {
-        (*(unsigned long *)(base + ds_cfg.from_ip.offset)) = value;
+        return ds_request(task, base, size, ovfl, ds_bts);
 }
-static inline unsigned long get_to_ip(char *base)
+
+int ds_request_pebs(struct task_struct *task, void *base, size_t size,
+                    ds_ovfl_callback_t ovfl)
 {
-        return *(unsigned long *)(base + ds_cfg.to_ip.offset);
+        return ds_request(task, base, size, ovfl, ds_pebs);
 }
-static inline void set_to_ip(char *base, unsigned long value)
+
+static int ds_release(struct task_struct *task, enum ds_qualifier qual)
 {
-        (*(unsigned long *)(base + ds_cfg.to_ip.offset)) = value;
+        struct ds_context *context;
+        int error;
+
+        context = ds_get_context(task);
+        error = ds_validate_access(context, qual);
+        if (error < 0)
+                goto out;
+
+        kfree(context->buffer[qual]);
+        context->buffer[qual] = NULL;
+
+        current->mm->total_vm  -= context->pages[qual];
+        current->mm->locked_vm -= context->pages[qual];
+        context->pages[qual] = 0;
+        context->owner[qual] = NULL;
+
+        /*
+         * we put the context twice:
+         *   once for the ds_get_context
+         *   once for the corresponding ds_request
+         */
+        ds_put_context(context);
+ out:
+        ds_put_context(context);
+        return error;
 }
-static inline unsigned char get_info_type(char *base)
+
+int ds_release_bts(struct task_struct *task)
 {
-        return *(unsigned char *)(base + ds_cfg.info_type.offset);
+        return ds_release(task, ds_bts);
 }
-static inline void set_info_type(char *base, unsigned char value)
+
+int ds_release_pebs(struct task_struct *task)
 {
-        (*(unsigned char *)(base + ds_cfg.info_type.offset)) = value;
+        return ds_release(task, ds_pebs);
 }
-static inline unsigned long get_info_data(char *base)
+
+static int ds_get_index(struct task_struct *task, size_t *pos,
+                        enum ds_qualifier qual)
 {
-        return *(unsigned long *)(base + ds_cfg.info_data.offset);
+        struct ds_context *context;
+        unsigned long base, index;
+        int error;
+
+        context = ds_get_context(task);
+        error = ds_validate_access(context, qual);
+        if (error < 0)
+                goto out;
+
+        base  = ds_get(context->ds, qual, ds_buffer_base);
+        index = ds_get(context->ds, qual, ds_index);
+
+        error = ((index - base) / ds_cfg.sizeof_rec[qual]);
+        if (pos)
+                *pos = error;
+ out:
+        ds_put_context(context);
+        return error;
 }
-static inline void set_info_data(char *base, unsigned long value)
+
+int ds_get_bts_index(struct task_struct *task, size_t *pos)
 {
-        (*(unsigned long *)(base + ds_cfg.info_data.offset)) = value;
+        return ds_get_index(task, pos, ds_bts);
 }
 
+int ds_get_pebs_index(struct task_struct *task, size_t *pos)
+{
+        return ds_get_index(task, pos, ds_pebs);
+}
 
-int ds_allocate(void **dsp, size_t bts_size_in_bytes)
+static int ds_get_end(struct task_struct *task, size_t *pos,
+                      enum ds_qualifier qual)
 {
-        size_t bts_size_in_records;
-        unsigned long bts;
-        void *ds;
+        struct ds_context *context;
+        unsigned long base, end;
+        int error;
+
+        context = ds_get_context(task);
+        error = ds_validate_access(context, qual);
+        if (error < 0)
+                goto out;
+
+        base = ds_get(context->ds, qual, ds_buffer_base);
+        end  = ds_get(context->ds, qual, ds_absolute_maximum);
+
+        error = ((end - base) / ds_cfg.sizeof_rec[qual]);
+        if (pos)
+                *pos = error;
+ out:
+        ds_put_context(context);
+        return error;
+}
 
-        if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-                return -EOPNOTSUPP;
+int ds_get_bts_end(struct task_struct *task, size_t *pos)
+{
+        return ds_get_end(task, pos, ds_bts);
+}
 
-        if (bts_size_in_bytes < 0)
-                return -EINVAL;
+int ds_get_pebs_end(struct task_struct *task, size_t *pos)
+{
+        return ds_get_end(task, pos, ds_pebs);
+}
 
-        bts_size_in_records =
-                bts_size_in_bytes / ds_cfg.sizeof_bts;
-        bts_size_in_bytes =
-                bts_size_in_records * ds_cfg.sizeof_bts;
+static int ds_access(struct task_struct *task, size_t index,
+                     const void **record, enum ds_qualifier qual)
+{
+        struct ds_context *context;
+        unsigned long base, idx;
+        int error;
 
-        if (bts_size_in_bytes <= 0)
+        if (!record)
                 return -EINVAL;
 
-        bts = (unsigned long)kzalloc(bts_size_in_bytes, GFP_KERNEL);
-
-        if (!bts)
-                return -ENOMEM;
+        context = ds_get_context(task);
+        error = ds_validate_access(context, qual);
+        if (error < 0)
+                goto out;
 
-        ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
+        base = ds_get(context->ds, qual, ds_buffer_base);
+        idx = base + (index * ds_cfg.sizeof_rec[qual]);
 
-        if (!ds) {
-                kfree((void *)bts);
-                return -ENOMEM;
-        }
-
-        set_bts_buffer_base(ds, bts);
-        set_bts_index(ds, bts);
-        set_bts_absolute_maximum(ds, bts + bts_size_in_bytes);
-        set_bts_interrupt_threshold(ds, bts + bts_size_in_bytes + 1);
+        error = -EINVAL;
+        if (idx > ds_get(context->ds, qual, ds_absolute_maximum))
+                goto out;
 
-        *dsp = ds;
-        return 0;
+        *record = (const void *)idx;
+        error = ds_cfg.sizeof_rec[qual];
+ out:
+        ds_put_context(context);
+        return error;
 }
 
-int ds_free(void **dsp)
+int ds_access_bts(struct task_struct *task, size_t index, const void **record)
 {
-        if (*dsp) {
-                kfree((void *)get_bts_buffer_base(*dsp));
-                kfree(*dsp);
-                *dsp = NULL;
-        }
-        return 0;
+        return ds_access(task, index, record, ds_bts);
 }
 
-int ds_get_bts_size(void *ds)
+int ds_access_pebs(struct task_struct *task, size_t index, const void **record)
 {
-        int size_in_bytes;
-
-        if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-                return -EOPNOTSUPP;
-
-        if (!ds)
-                return 0;
-
-        size_in_bytes =
-                get_bts_absolute_maximum(ds) -
-                get_bts_buffer_base(ds);
-        return size_in_bytes;
+        return ds_access(task, index, record, ds_pebs);
 }
 
-int ds_get_bts_end(void *ds)
+static int ds_write(struct task_struct *task, const void *record, size_t size,
+                    enum ds_qualifier qual, int force)
 {
-        int size_in_bytes = ds_get_bts_size(ds);
-
-        if (size_in_bytes <= 0)
-                return size_in_bytes;
+        struct ds_context *context;
+        int error;
 
-        return size_in_bytes / ds_cfg.sizeof_bts;
-}
+        if (!record)
+                return -EINVAL;
 
-int ds_get_bts_index(void *ds)
-{
-        int index_offset_in_bytes;
+        error = -EPERM;
+        context = ds_get_context(task);
+        if (!context)
+                goto out;
 
-        if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-                return -EOPNOTSUPP;
+        if (!force) {
+                error = ds_validate_access(context, qual);
+                if (error < 0)
+                        goto out;
+        }
 
-        index_offset_in_bytes =
-                get_bts_index(ds) -
-                get_bts_buffer_base(ds);
+        error = 0;
+        while (size) {
+                unsigned long base, index, end, write_end, int_th;
+                unsigned long write_size, adj_write_size;
+
+                /*
+                 * write as much as possible without producing an
+                 * overflow interrupt.
+                 *
+                 * interrupt_threshold must either be
+                 * - bigger than absolute_maximum or
+                 * - point to a record between buffer_base and absolute_maximum
+                 *
+                 * index points to a valid record.
+                 */
+                base   = ds_get(context->ds, qual, ds_buffer_base);
+                index  = ds_get(context->ds, qual, ds_index);
+                end    = ds_get(context->ds, qual, ds_absolute_maximum);
+                int_th = ds_get(context->ds, qual, ds_interrupt_threshold);
+
+                write_end = min(end, int_th);
+
+                /* if we are already beyond the interrupt threshold,
+                 * we fill the entire buffer */
+                if (write_end <= index)
+                        write_end = end;
+
+                if (write_end <= index)
+                        goto out;
+
+                write_size = min((unsigned long) size, write_end - index);
+                memcpy((void *)index, record, write_size);
+
+                record = (const char *)record + write_size;
+                size  -= write_size;
+                error += write_size;
+
+                adj_write_size = write_size / ds_cfg.sizeof_rec[qual];
+                adj_write_size *= ds_cfg.sizeof_rec[qual];
+
+                /* zero out trailing bytes */
+                memset((char *)index + write_size, 0,
+                       adj_write_size - write_size);
+                index += adj_write_size;
+
+                if (index >= end)
+                        index = base;
+                ds_set(context->ds, qual, ds_index, index);
+
+                if (index >= int_th)
+                        ds_overflow(task, context, qual);
+        }
 
-        return index_offset_in_bytes / ds_cfg.sizeof_bts;
+ out:
+        ds_put_context(context);
+        return error;
 }
 
-int ds_set_overflow(void *ds, int method)
+int ds_write_bts(struct task_struct *task, const void *record, size_t size)
 {
-        switch (method) {
-        case DS_O_SIGNAL:
-                return -EOPNOTSUPP;
-        case DS_O_WRAP:
-                return 0;
-        default:
-                return -EINVAL;
-        }
+        return ds_write(task, record, size, ds_bts, /* force = */ 0);
 }
 
-int ds_get_overflow(void *ds)
+int ds_write_pebs(struct task_struct *task, const void *record, size_t size)
 {
-        return DS_O_WRAP;
+        return ds_write(task, record, size, ds_pebs, /* force = */ 0);
 }
 
-int ds_clear(void *ds)
+int ds_unchecked_write_bts(struct task_struct *task,
+                           const void *record, size_t size)
 {
-        int bts_size = ds_get_bts_size(ds);
-        unsigned long bts_base;
-
-        if (bts_size <= 0)
-                return bts_size;
-
-        bts_base = get_bts_buffer_base(ds);
-        memset((void *)bts_base, 0, bts_size);
-
-        set_bts_index(ds, bts_base);
-        return 0;
+        return ds_write(task, record, size, ds_bts, /* force = */ 1);
 }
 
-int ds_read_bts(void *ds, int index, struct bts_struct *out)
+int ds_unchecked_write_pebs(struct task_struct *task,
+                            const void *record, size_t size)
 {
-        void *bts;
+        return ds_write(task, record, size, ds_pebs, /* force = */ 1);
+}
 
-        if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-                return -EOPNOTSUPP;
+static int ds_reset_or_clear(struct task_struct *task,
+                             enum ds_qualifier qual, int clear)
+{
+        struct ds_context *context;
+        unsigned long base, end;
+        int error;
 
-        if (index < 0)
-                return -EINVAL;
+        context = ds_get_context(task);
+        error = ds_validate_access(context, qual);
+        if (error < 0)
+                goto out;
 
-        if (index >= ds_get_bts_size(ds))
-                return -EINVAL;
+        base = ds_get(context->ds, qual, ds_buffer_base);
+        end  = ds_get(context->ds, qual, ds_absolute_maximum);
 
-        bts = (void *)(get_bts_buffer_base(ds) + (index * ds_cfg.sizeof_bts));
+        if (clear)
+                memset((void *)base, 0, end - base);
 
-        memset(out, 0, sizeof(*out));
-        if (get_from_ip(bts) == BTS_ESCAPE_ADDRESS) {
-                out->qualifier       = get_info_type(bts);
-                out->variant.jiffies = get_info_data(bts);
-        } else {
-                out->qualifier = BTS_BRANCH;
-                out->variant.lbr.from_ip = get_from_ip(bts);
-                out->variant.lbr.to_ip   = get_to_ip(bts);
-        }
+        ds_set(context->ds, qual, ds_index, base);
 
-        return sizeof(*out);;
+        error = 0;
+ out:
+        ds_put_context(context);
+        return error;
 }
 
-int ds_write_bts(void *ds, const struct bts_struct *in)
+int ds_reset_bts(struct task_struct *task)
 {
-        unsigned long bts;
-
-        if (!ds_cfg.sizeof_ds || !ds_cfg.sizeof_bts)
-                return -EOPNOTSUPP;
-
-        if (ds_get_bts_size(ds) <= 0)
-                return -ENXIO;
+        return ds_reset_or_clear(task, ds_bts, /* clear = */ 0);
+}
 
-        bts = get_bts_index(ds);
+int ds_reset_pebs(struct task_struct *task)
+{
+        return ds_reset_or_clear(task, ds_pebs, /* clear = */ 0);
+}
 
-        memset((void *)bts, 0, ds_cfg.sizeof_bts);
-        switch (in->qualifier) {
-        case BTS_INVALID:
-                break;
+int ds_clear_bts(struct task_struct *task)
+{
+        return ds_reset_or_clear(task, ds_bts, /* clear = */ 1);
+}
 
-        case BTS_BRANCH:
-                set_from_ip((void *)bts, in->variant.lbr.from_ip);
-                set_to_ip((void *)bts, in->variant.lbr.to_ip);
-                break;
+int ds_clear_pebs(struct task_struct *task)
+{
+        return ds_reset_or_clear(task, ds_pebs, /* clear = */ 1);
+}
 
-        case BTS_TASK_ARRIVES:
-        case BTS_TASK_DEPARTS:
-                set_from_ip((void *)bts, BTS_ESCAPE_ADDRESS);
-                set_info_type((void *)bts, in->qualifier);
-                set_info_data((void *)bts, in->variant.jiffies);
-                break;
+int ds_get_pebs_reset(struct task_struct *task, u64 *value)
+{
+        struct ds_context *context;
+        int error;
 
-        default:
+        if (!value)
                 return -EINVAL;
-        }
 
-        bts = bts + ds_cfg.sizeof_bts;
-        if (bts >= get_bts_absolute_maximum(ds))
-                bts = get_bts_buffer_base(ds);
-        set_bts_index(ds, bts);
+        context = ds_get_context(task);
+        error = ds_validate_access(context, ds_pebs);
+        if (error < 0)
+                goto out;
 
-        return ds_cfg.sizeof_bts;
+        *value = *(u64 *)(context->ds + (ds_cfg.sizeof_field * 8));
+
+        error = 0;
+ out:
+        ds_put_context(context);
+        return error;
 }
 
-unsigned long ds_debugctl_mask(void)
+int ds_set_pebs_reset(struct task_struct *task, u64 value)
 {
-        return ds_cfg.debugctl_mask;
-}
+        struct ds_context *context;
+        int error;
 
-#ifdef __i386__
-static const struct ds_configuration ds_cfg_netburst = {
-        .sizeof_ds = 9 * 4,
-        .bts_buffer_base = { 0, 4 },
-        .bts_index = { 4, 4 },
-        .bts_absolute_maximum = { 8, 4 },
-        .bts_interrupt_threshold = { 12, 4 },
-        .sizeof_bts = 3 * 4,
-        .from_ip = { 0, 4 },
-        .to_ip = { 4, 4 },
-        .info_type = { 4, 1 },
-        .info_data = { 8, 4 },
-        .debugctl_mask = (1<<2)|(1<<3)
-};
+        context = ds_get_context(task);
+        error = ds_validate_access(context, ds_pebs);
+        if (error < 0)
+                goto out;
 
-static const struct ds_configuration ds_cfg_pentium_m = {
-        .sizeof_ds = 9 * 4,
-        .bts_buffer_base = { 0, 4 },
-        .bts_index = { 4, 4 },
-        .bts_absolute_maximum = { 8, 4 },
-        .bts_interrupt_threshold = { 12, 4 },
-        .sizeof_bts = 3 * 4,
-        .from_ip = { 0, 4 },
-        .to_ip = { 4, 4 },
-        .info_type = { 4, 1 },
-        .info_data = { 8, 4 },
-        .debugctl_mask = (1<<6)|(1<<7)
+        *(u64 *)(context->ds + (ds_cfg.sizeof_field * 8)) = value;
+
+        error = 0;
+ out:
+        ds_put_context(context);
+        return error;
+}
+
+static const struct ds_configuration ds_cfg_var = {
+        .sizeof_ds    = sizeof(long) * 12,
+        .sizeof_field = sizeof(long),
+        .sizeof_rec[ds_bts]   = sizeof(long) * 3,
+        .sizeof_rec[ds_pebs]  = sizeof(long) * 10
 };
-#endif /* _i386_ */
-
-static const struct ds_configuration ds_cfg_core2 = {
-        .sizeof_ds = 9 * 8,
-        .bts_buffer_base = { 0, 8 },
-        .bts_index = { 8, 8 },
-        .bts_absolute_maximum = { 16, 8 },
-        .bts_interrupt_threshold = { 24, 8 },
-        .sizeof_bts = 3 * 8,
-        .from_ip = { 0, 8 },
-        .to_ip = { 8, 8 },
-        .info_type = { 8, 1 },
-        .info_data = { 16, 8 },
-        .debugctl_mask = (1<<6)|(1<<7)|(1<<9)
+static const struct ds_configuration ds_cfg_64 = {
+        .sizeof_ds    = 8 * 12,
+        .sizeof_field = 8,
+        .sizeof_rec[ds_bts]   = 8 * 3,
+        .sizeof_rec[ds_pebs]  = 8 * 10
 };
 
 static inline void
@@ -429,14 +821,13 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
         switch (c->x86) {
         case 0x6:
                 switch (c->x86_model) {
-#ifdef __i386__
                 case 0xD:
                 case 0xE: /* Pentium M */
-                        ds_configure(&ds_cfg_pentium_m);
+                        ds_configure(&ds_cfg_var);
                         break;
-#endif /* _i386_ */
                 case 0xF: /* Core2 */
-                        ds_configure(&ds_cfg_core2);
+                case 0x1C: /* Atom */
+                        ds_configure(&ds_cfg_64);
                         break;
                 default:
                         /* sorry, don't know about them */
@@ -445,13 +836,11 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
                 break;
         case 0xF:
                 switch (c->x86_model) {
-#ifdef __i386__
                 case 0x0:
                 case 0x1:
                 case 0x2: /* Netburst */
-                        ds_configure(&ds_cfg_netburst);
+                        ds_configure(&ds_cfg_var);
                         break;
-#endif /* _i386_ */
                 default:
                         /* sorry, don't know about them */
                         break;
@@ -462,3 +851,14 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
                 break;
         }
 }
+
+void ds_free(struct ds_context *context)
+{
+        /* This is called when the task owning the parameter context
+         * is dying. There should not be any user of that context left
+         * to disturb us, anymore. */
+        unsigned long leftovers = context->count;
+        while (leftovers--)
+                ds_put_context(context);
+}
+#endif /* CONFIG_X86_DS */
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 06cc8d4254b1..945a31cdd81f 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -414,9 +414,11 @@ void __init efi_init(void)
         if (memmap.map == NULL)
                 printk(KERN_ERR "Could not map the EFI memory map!\n");
         memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size);
+
         if (memmap.desc_size != sizeof(efi_memory_desc_t))
-                printk(KERN_WARNING "Kernel-defined memdesc"
-                       "doesn't match the one from EFI!\n");
+                printk(KERN_WARNING
+                  "Kernel-defined memdesc doesn't match the one from EFI!\n");
+
         if (add_efi_memmap)
                 do_add_efi_memmap();
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 89434d439605..cf3a0b2d0059 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -275,9 +275,9 @@ ENTRY(native_usergs_sysret64)
 ENTRY(ret_from_fork)
         CFI_DEFAULT_STACK
         push kernel_eflags(%rip)
-        CFI_ADJUST_CFA_OFFSET 4
+        CFI_ADJUST_CFA_OFFSET 8
         popf                            # reset kernel eflags
-        CFI_ADJUST_CFA_OFFSET -4
+        CFI_ADJUST_CFA_OFFSET -8
         call schedule_tail
         GET_THREAD_INFO(%rcx)
         testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 9bfc4d72fb2e..d16084f90649 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -108,12 +108,11 @@ void __init x86_64_start_kernel(char * real_mode_data)
         }
         load_idt((const struct desc_ptr *)&idt_descr);
 
-        early_printk("Kernel alive\n");
+        if (console_loglevel == 10)
+                early_printk("Kernel alive\n");
 
         x86_64_init_pda();
 
-        early_printk("Kernel really alive\n");
-
         x86_64_start_reservations(real_mode_data);
 }
 
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 50e5e4a31c85..191914302744 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/thread_info.h>
 #include <linux/syscalls.h>
+#include <asm/syscalls.h>
 
 /* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
 static void set_bitmap(unsigned long *bitmap, unsigned int base,
diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c
index 3f7537b669d3..f1c688e46f35 100644
--- a/arch/x86/kernel/ipi.c
+++ b/arch/x86/kernel/ipi.c
@@ -20,6 +20,8 @@
 
 #ifdef CONFIG_X86_32
 #include <mach_apic.h>
+#include <mach_ipi.h>
+
 /*
  * the following functions deal with sending IPIs between CPUs.
  *
@@ -147,7 +149,6 @@ void send_IPI_mask_sequence(cpumask_t mask, int vector)
 }
 
 /* must come after the send_IPI functions above for inlining */
-#include <mach_ipi.h>
 static int convert_apicid_to_cpu(int apic_id)
 {
         int i;
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 1cf8c1fcc088..b71e02d42f4f 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -325,7 +325,7 @@ skip:
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ",
                                 per_cpu(irq_stat,j).irq_call_count);
-                seq_printf(p, "  function call interrupts\n");
+                seq_printf(p, "  Function call interrupts\n");
                 seq_printf(p, "TLB: ");
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ",
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 1f78b238d8d2..f065fe9071b9 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -129,7 +129,7 @@ skip:
                 seq_printf(p, "CAL: ");
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", cpu_pda(j)->irq_call_count);
-                seq_printf(p, "  function call interrupts\n");
+                seq_printf(p, "  Function call interrupts\n");
                 seq_printf(p, "TLB: ");
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 8b7a3cf37d2b..478bca986eca 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -178,7 +178,7 @@ static void kvm_flush_tlb(void)
         kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
 }
 
-static void kvm_release_pt(u32 pfn)
+static void kvm_release_pt(unsigned long pfn)
 {
         struct kvm_mmu_op_release_pt rpt = {
                 .header.op = KVM_MMU_OP_RELEASE_PT,
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index b68e21f06f4f..0ed5f939b905 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -18,6 +18,7 @@
 #include <asm/ldt.h>
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
+#include <asm/syscalls.h>
 
 #ifdef CONFIG_SMP
 static void flush_ldt(void *current_mm)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index abb78a2cc4ad..2c97f07f1c2c 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -299,6 +299,15 @@ void acpi_nmi_disable(void)
                 on_each_cpu(__acpi_nmi_disable, NULL, 1);
 }
 
+/*
+ * This function is called as soon the LAPIC NMI watchdog driver has everything
+ * in place and it's ready to check if the NMIs belong to the NMI watchdog
+ */
+void cpu_nmi_set_wd_enabled(void)
+{
+        __get_cpu_var(wd_enabled) = 1;
+}
+
 void setup_apic_nmi_watchdog(void *unused)
 {
         if (__get_cpu_var(wd_enabled))
@@ -311,8 +320,6 @@ void setup_apic_nmi_watchdog(void *unused)
 
         switch (nmi_watchdog) {
         case NMI_LOCAL_APIC:
-                 /* enable it before to avoid race with handler */
-                __get_cpu_var(wd_enabled) = 1;
                 if (lapic_watchdog_init(nmi_hz) < 0) {
                         __get_cpu_var(wd_enabled) = 0;
                         return;
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 3e6672274807..7a13fac63a1f 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -190,12 +190,12 @@ EXPORT_SYMBOL_GPL(olpc_ec_cmd);
 static void __init platform_detect(void)
 {
         size_t propsize;
-        u32 rev;
+        __be32 rev;
 
         if (ofw("getprop", 4, 1, NULL, "board-revision-int", &rev, 4,
                         &propsize) || propsize != 4) {
                 printk(KERN_ERR "ofw: getprop call failed!\n");
-                rev = 0;
+                rev = cpu_to_be32(0);
         }
         olpc_platform_info.boardrev = be32_to_cpu(rev);
 }
@@ -203,7 +203,7 @@ static void __init platform_detect(void)
 static void __init platform_detect(void)
 {
         /* stopgap until OFW support is added to the kernel */
-        olpc_platform_info.boardrev = be32_to_cpu(0xc2);
+        olpc_platform_info.boardrev = 0xc2;
 }
 #endif
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 300da17e61cb..e2f43768723a 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -330,6 +330,7 @@ struct pv_cpu_ops pv_cpu_ops = {
 #endif
         .wbinvd = native_wbinvd,
         .read_msr = native_read_msr_safe,
+        .read_msr_amd = native_read_msr_amd_safe,
         .write_msr = native_write_msr_safe,
         .read_tsc = native_read_tsc,
         .read_pmc = native_read_pmc,
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 58262218781b..9fe644f4861d 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -23,7 +23,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
                         start = start_##ops##_##x;              \
                         end = end_##ops##_##x;                  \
                         goto patch_site
-        switch(type) {
+        switch (type) {
                 PATCH_SITE(pv_irq_ops, irq_disable);
                 PATCH_SITE(pv_irq_ops, irq_enable);
                 PATCH_SITE(pv_irq_ops, restore_fl);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 87d4d6964ec2..f704cb51ff82 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -82,7 +82,7 @@ void __init dma32_reserve_bootmem(void)
          * using 512M as goal
          */
         align = 64ULL<<20;
-        size = round_up(dma32_bootmem_size, align);
+        size = roundup(dma32_bootmem_size, align);
         dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align,
                                  512ULL<<20);
         if (dma32_bootmem_ptr)
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index be33a5442d82..1a895a582534 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -82,7 +82,8 @@ AGPEXTERN __u32 *agp_gatt_table;
 static unsigned long next_bit;  /* protected by iommu_bitmap_lock */
 static int need_flush;          /* global flush state. set for each gart wrap */
 
-static unsigned long alloc_iommu(struct device *dev, int size)
+static unsigned long alloc_iommu(struct device *dev, int size,
+                                 unsigned long align_mask)
 {
         unsigned long offset, flags;
         unsigned long boundary_size;
@@ -90,16 +91,17 @@ static unsigned long alloc_iommu(struct device *dev, int size)
 
         base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
                            PAGE_SIZE) >> PAGE_SHIFT;
-        boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+        boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
                               PAGE_SIZE) >> PAGE_SHIFT;
 
         spin_lock_irqsave(&iommu_bitmap_lock, flags);
         offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit,
-                                  size, base_index, boundary_size, 0);
+                                  size, base_index, boundary_size, align_mask);
         if (offset == -1) {
                 need_flush = 1;
                 offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, 0,
-                                          size, base_index, boundary_size, 0);
+                                          size, base_index, boundary_size,
+                                          align_mask);
         }
         if (offset != -1) {
                 next_bit = offset+size;
@@ -236,10 +238,10 @@ nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
  * Caller needs to check if the iommu is needed and flush.
  */
 static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
-                                size_t size, int dir)
+                                size_t size, int dir, unsigned long align_mask)
 {
         unsigned long npages = iommu_num_pages(phys_mem, size);
-        unsigned long iommu_page = alloc_iommu(dev, npages);
+        unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
         int i;
 
         if (iommu_page == -1) {
@@ -262,7 +264,11 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 static dma_addr_t
 gart_map_simple(struct device *dev, phys_addr_t paddr, size_t size, int dir)
 {
-        dma_addr_t map = dma_map_area(dev, paddr, size, dir);
+        dma_addr_t map;
+        unsigned long align_mask;
+
+        align_mask = (1UL << get_order(size)) - 1;
+        map = dma_map_area(dev, paddr, size, dir, align_mask);
 
         flush_gart();
 
@@ -281,7 +287,8 @@ gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir)
         if (!need_iommu(dev, paddr, size))
                 return paddr;
 
-        bus = gart_map_simple(dev, paddr, size, dir);
+        bus = dma_map_area(dev, paddr, size, dir, 0);
+        flush_gart();
 
         return bus;
 }
@@ -340,7 +347,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
                 unsigned long addr = sg_phys(s);
 
                 if (nonforced_iommu(dev, addr, s->length)) {
-                        addr = dma_map_area(dev, addr, s->length, dir);
+                        addr = dma_map_area(dev, addr, s->length, dir, 0);
                         if (addr == bad_dma_address) {
                                 if (i > 0)
                                         gart_unmap_sg(dev, sg, i, dir);
@@ -362,7 +369,7 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start,
                           int nelems, struct scatterlist *sout,
                           unsigned long pages)
 {
-        unsigned long iommu_start = alloc_iommu(dev, pages);
+        unsigned long iommu_start = alloc_iommu(dev, pages, 0);
         unsigned long iommu_page = iommu_start;
         struct scatterlist *s;
         int i;
diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c
index bc1f2d3ea277..a311ffcaad16 100644
--- a/arch/x86/kernel/pcspeaker.c
+++ b/arch/x86/kernel/pcspeaker.c
@@ -1,20 +1,13 @@
 #include <linux/platform_device.h>
-#include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/init.h>
 
 static __init int add_pcspkr(void)
 {
         struct platform_device *pd;
-        int ret;
 
-        pd = platform_device_alloc("pcspkr", -1);
-        if (!pd)
-                return -ENOMEM;
+        pd = platform_device_register_simple("pcspkr", -1, NULL, 0);
 
-        ret = platform_device_add(pd);
-        if (ret)
-                platform_device_put(pd);
-
-        return ret;
+        return IS_ERR(pd) ? PTR_ERR(pd) : 0;
 }
 device_initcall(add_pcspkr);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 876e91890777..ec7a2ba9bce8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -185,7 +185,8 @@ static void mwait_idle(void)
 static void poll_idle(void)
 {
         local_irq_enable();
-        cpu_relax();
+        while (!need_resched())
+                cpu_relax();
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 31f40b24bf5d..205188db9626 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -37,6 +37,7 @@
 #include <linux/tick.h>
 #include <linux/percpu.h>
 #include <linux/prctl.h>
+#include <linux/dmi.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -56,6 +57,8 @@
 #include <asm/cpu.h>
 #include <asm/kdebug.h>
 #include <asm/idle.h>
+#include <asm/syscalls.h>
+#include <asm/smp.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
@@ -161,6 +164,7 @@ void __show_registers(struct pt_regs *regs, int all)
         unsigned long d0, d1, d2, d3, d6, d7;
         unsigned long sp;
         unsigned short ss, gs;
+        const char *board;
 
         if (user_mode_vm(regs)) {
                 sp = regs->sp;
@@ -173,11 +177,15 @@ void __show_registers(struct pt_regs *regs, int all)
         }
 
         printk("\n");
-        printk("Pid: %d, comm: %s %s (%s %.*s)\n",
+
+        board = dmi_get_system_info(DMI_PRODUCT_NAME);
+        if (!board)
+                board = "";
+        printk("Pid: %d, comm: %s %s (%s %.*s) %s\n",
                         task_pid_nr(current), current->comm,
                         print_tainted(), init_utsname()->release,
                         (int)strcspn(init_utsname()->version, " "),
-                        init_utsname()->version);
+                        init_utsname()->version, board);
 
         printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
                         (u16)regs->cs, regs->ip, regs->flags,
@@ -277,6 +285,14 @@ void exit_thread(void)
                 tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
                 put_cpu();
         }
+#ifdef CONFIG_X86_DS
+        /* Free any DS contexts that have not been properly released. */
+        if (unlikely(current->thread.ds_ctx)) {
+                /* we clear debugctl to make sure DS is not used. */
+                update_debugctlmsr(0);
+                ds_free(current->thread.ds_ctx);
+        }
+#endif /* CONFIG_X86_DS */
 }
 
 void flush_thread(void)
@@ -438,6 +454,35 @@ int set_tsc_mode(unsigned int val)
         return 0;
 }
 
+#ifdef CONFIG_X86_DS
+static int update_debugctl(struct thread_struct *prev,
+                        struct thread_struct *next, unsigned long debugctl)
+{
+        unsigned long ds_prev = 0;
+        unsigned long ds_next = 0;
+
+        if (prev->ds_ctx)
+                ds_prev = (unsigned long)prev->ds_ctx->ds;
+        if (next->ds_ctx)
+                ds_next = (unsigned long)next->ds_ctx->ds;
+
+        if (ds_next != ds_prev) {
+                /* we clear debugctl to make sure DS
+                 * is not in use when we change it */
+                debugctl = 0;
+                update_debugctlmsr(0);
+                wrmsr(MSR_IA32_DS_AREA, ds_next, 0);
+        }
+        return debugctl;
+}
+#else
+static int update_debugctl(struct thread_struct *prev,
+                        struct thread_struct *next, unsigned long debugctl)
+{
+        return debugctl;
+}
+#endif /* CONFIG_X86_DS */
+
 static noinline void
 __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
                  struct tss_struct *tss)
@@ -448,14 +493,7 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
         prev = &prev_p->thread;
         next = &next_p->thread;
 
-        debugctl = prev->debugctlmsr;
-        if (next->ds_area_msr != prev->ds_area_msr) {
-                /* we clear debugctl to make sure DS
-                 * is not in use when we change it */
-                debugctl = 0;
-                update_debugctlmsr(0);
-                wrmsr(MSR_IA32_DS_AREA, next->ds_area_msr, 0);
-        }
+        debugctl = update_debugctl(prev, next, prev->debugctlmsr);
 
         if (next->debugctlmsr != debugctl)
                 update_debugctlmsr(next->debugctlmsr);
@@ -479,13 +517,13 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
                         hard_enable_TSC();
         }
 
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
         if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
                 ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
         if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
                 ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 
         if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e12e0e4dd256..2a8ccb9238b4 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -37,11 +37,11 @@
 #include <linux/kdebug.h>
 #include <linux/tick.h>
 #include <linux/prctl.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
-#include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/mmu_context.h>
@@ -51,6 +51,7 @@
 #include <asm/proto.h>
 #include <asm/ia32.h>
 #include <asm/idle.h>
+#include <asm/syscalls.h>
 
 asmlinkage extern void ret_from_fork(void);
 
@@ -88,7 +89,7 @@ void exit_idle(void)
 #ifdef CONFIG_HOTPLUG_CPU
 DECLARE_PER_CPU(int, cpu_state);
 
-#include <asm/nmi.h>
+#include <linux/nmi.h>
 /* We halt the CPU with physical CPU hotplug */
 static inline void play_dead(void)
 {
@@ -153,7 +154,7 @@ void cpu_idle(void)
 }
 
 /* Prints also some state that isn't saved in the pt_regs */
-void __show_regs(struct pt_regs * regs)
+void __show_regs(struct pt_regs *regs)
 {
         unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
         unsigned long d0, d1, d2, d3, d6, d7;
@@ -162,59 +163,61 @@ void __show_regs(struct pt_regs * regs)
 
         printk("\n");
         print_modules();
-        printk("Pid: %d, comm: %.20s %s %s %.*s\n",
+        printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s\n",
                 current->pid, current->comm, print_tainted(),
                 init_utsname()->release,
                 (int)strcspn(init_utsname()->version, " "),
                 init_utsname()->version);
-        printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
+        printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
         printk_address(regs->ip, 1);
-        printk("RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss, regs->sp,
-                regs->flags);
-        printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
+        printk(KERN_INFO "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
+                        regs->sp, regs->flags);
+        printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
                regs->ax, regs->bx, regs->cx);
-        printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
+        printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n",
                regs->dx, regs->si, regs->di);
-        printk("RBP: %016lx R08: %016lx R09: %016lx\n",
+        printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n",
                regs->bp, regs->r8, regs->r9);
-        printk("R10: %016lx R11: %016lx R12: %016lx\n",
-               regs->r10, regs->r11, regs->r12); 
-        printk("R13: %016lx R14: %016lx R15: %016lx\n",
-               regs->r13, regs->r14, regs->r15); 
-
-        asm("movl %%ds,%0" : "=r" (ds)); 
-        asm("movl %%cs,%0" : "=r" (cs)); 
-        asm("movl %%es,%0" : "=r" (es)); 
+        printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n",
+               regs->r10, regs->r11, regs->r12);
+        printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n",
+               regs->r13, regs->r14, regs->r15);
+
+        asm("movl %%ds,%0" : "=r" (ds));
+        asm("movl %%cs,%0" : "=r" (cs));
+        asm("movl %%es,%0" : "=r" (es));
         asm("movl %%fs,%0" : "=r" (fsindex));
         asm("movl %%gs,%0" : "=r" (gsindex));
 
         rdmsrl(MSR_FS_BASE, fs);
-        rdmsrl(MSR_GS_BASE, gs); 
-        rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); 
+        rdmsrl(MSR_GS_BASE, gs);
+        rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
 
         cr0 = read_cr0();
         cr2 = read_cr2();
         cr3 = read_cr3();
         cr4 = read_cr4();
 
-        printk("FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", 
-               fs,fsindex,gs,gsindex,shadowgs); 
-        printk("CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); 
-        printk("CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4);
+        printk(KERN_INFO "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
+               fs, fsindex, gs, gsindex, shadowgs);
+        printk(KERN_INFO "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
+                        es, cr0);
+        printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
+                        cr4);
 
         get_debugreg(d0, 0);
         get_debugreg(d1, 1);
         get_debugreg(d2, 2);
-        printk("DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
+        printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
         get_debugreg(d3, 3);
         get_debugreg(d6, 6);
         get_debugreg(d7, 7);
-        printk("DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
+        printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
 }
 
 void show_regs(struct pt_regs *regs)
 {
-        printk("CPU %d:", smp_processor_id());
+        printk(KERN_INFO "CPU %d:", smp_processor_id());
         __show_regs(regs);
         show_trace(NULL, regs, (void *)(regs + 1), regs->bp);
 }
@@ -240,6 +243,14 @@ void exit_thread(void)
                 t->io_bitmap_max = 0;
                 put_cpu();
         }
+#ifdef CONFIG_X86_DS
+        /* Free any DS contexts that have not been properly released. */
+        if (unlikely(t->ds_ctx)) {
+                /* we clear debugctl to make sure DS is not used. */
+                update_debugctlmsr(0);
+                ds_free(t->ds_ctx);
+        }
+#endif /* CONFIG_X86_DS */
 }
 
 void flush_thread(void)
@@ -315,10 +326,10 @@ void prepare_to_copy(struct task_struct *tsk)
 
 int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
                 unsigned long unused,
-        struct task_struct * p, struct pt_regs * regs)
+        struct task_struct *p, struct pt_regs *regs)
 {
         int err;
-        struct pt_regs * childregs;
+        struct pt_regs *childregs;
         struct task_struct *me = current;
 
         childregs = ((struct pt_regs *)
@@ -363,10 +374,10 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
                 if (test_thread_flag(TIF_IA32))
                         err = do_set_thread_area(p, -1,
                                 (struct user_desc __user *)childregs->si, 0);
-                else                    
-#endif   
-                        err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); 
-                if (err) 
+                else
+#endif
+                        err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8);
+                if (err)
                         goto out;
         }
         err = 0;
@@ -473,13 +484,27 @@ static inline void __switch_to_xtra(struct task_struct *prev_p,
         next = &next_p->thread;
 
         debugctl = prev->debugctlmsr;
-        if (next->ds_area_msr != prev->ds_area_msr) {
-                /* we clear debugctl to make sure DS
-                 * is not in use when we change it */
-                debugctl = 0;
-                update_debugctlmsr(0);
-                wrmsrl(MSR_IA32_DS_AREA, next->ds_area_msr);
+
+#ifdef CONFIG_X86_DS
+        {
+                unsigned long ds_prev = 0, ds_next = 0;
+
+                if (prev->ds_ctx)
+                        ds_prev = (unsigned long)prev->ds_ctx->ds;
+                if (next->ds_ctx)
+                        ds_next = (unsigned long)next->ds_ctx->ds;
+
+                if (ds_next != ds_prev) {
+                        /*
+                         * We clear debugctl to make sure DS
+                         * is not in use when we change it:
+                         */
+                        debugctl = 0;
+                        update_debugctlmsr(0);
+                        wrmsrl(MSR_IA32_DS_AREA, ds_next);
+                }
         }
+#endif /* CONFIG_X86_DS */
 
         if (next->debugctlmsr != debugctl)
                 update_debugctlmsr(next->debugctlmsr);
@@ -517,13 +542,13 @@ static inline void __switch_to_xtra(struct task_struct *prev_p,
                 memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
         }
 
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
         if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
                 ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
         if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
                 ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
 }
 
 /*
@@ -545,7 +570,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         unsigned fsindex, gsindex;
 
         /* we're going to use this soon, after a few expensive things */
-        if (next_p->fpu_counter>5)
+        if (next_p->fpu_counter > 5)
                 prefetch(next->xstate);
 
         /*
@@ -553,13 +578,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
          */
         load_sp0(tss, next);
 
-        /* 
+        /*
          * Switch DS and ES.
          * This won't pick up thread selector changes, but I guess that is ok.
          */
         savesegment(es, prev->es);
         if (unlikely(next->es | prev->es))
-                loadsegment(es, next->es); 
+                loadsegment(es, next->es);
 
         savesegment(ds, prev->ds);
         if (unlikely(next->ds | prev->ds))
@@ -585,7 +610,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
          */
         arch_leave_lazy_cpu_mode();
 
-        /* 
+        /*
          * Switch FS and GS.
          *
          * Segment register != 0 always requires a reload.  Also
@@ -594,13 +619,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
          */
         if (unlikely(fsindex | next->fsindex | prev->fs)) {
                 loadsegment(fs, next->fsindex);
-                /* 
+                /*
                  * Check if the user used a selector != 0; if yes
                  *  clear 64bit base, since overloaded base is always
                  *  mapped to the Null selector
                  */
                 if (fsindex)
-                        prev->fs = 0;                           
+                        prev->fs = 0;
         }
         /* when next process has a 64bit base use it */
         if (next->fs)
@@ -610,7 +635,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         if (unlikely(gsindex | next->gsindex | prev->gs)) {
                 load_gs_index(next->gsindex);
                 if (gsindex)
-                        prev->gs = 0;                           
+                        prev->gs = 0;
         }
         if (next->gs)
                 wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
@@ -619,12 +644,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         /* Must be after DS reload */
         unlazy_fpu(prev_p);
 
-        /* 
+        /*
          * Switch the PDA and FPU contexts.
          */
         prev->usersp = read_pda(oldrsp);
         write_pda(oldrsp, next->usersp);
-        write_pda(pcurrent, next_p); 
+        write_pda(pcurrent, next_p);
 
         write_pda(kernelstack,
                   (unsigned long)task_stack_page(next_p) +
@@ -665,7 +690,7 @@ long sys_execve(char __user *name, char __user * __user *argv,
                 char __user * __user *envp, struct pt_regs *regs)
 {
         long error;
-        char * filename;
+        char *filename;
 
         filename = getname(name);
         error = PTR_ERR(filename);
@@ -723,55 +748,55 @@ asmlinkage long sys_vfork(struct pt_regs *regs)
 unsigned long get_wchan(struct task_struct *p)
 {
         unsigned long stack;
-        u64 fp,ip;
+        u64 fp, ip;
         int count = 0;
 
-        if (!p || p == current || p->state==TASK_RUNNING)
-                return 0; 
+        if (!p || p == current || p->state == TASK_RUNNING)
+                return 0;
         stack = (unsigned long)task_stack_page(p);
         if (p->thread.sp < stack || p->thread.sp > stack+THREAD_SIZE)
                 return 0;
         fp = *(u64 *)(p->thread.sp);
-        do { 
+        do {
                 if (fp < (unsigned long)stack ||
                     fp > (unsigned long)stack+THREAD_SIZE)
-                        return 0; 
+                        return 0;
                 ip = *(u64 *)(fp+8);
                 if (!in_sched_functions(ip))
                         return ip;
-                fp = *(u64 *)fp; 
-        } while (count++ < 16); 
+                fp = *(u64 *)fp;
+        } while (count++ < 16);
         return 0;
 }
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
-{ 
-        int ret = 0; 
+{
+        int ret = 0;
         int doit = task == current;
         int cpu;
 
-        switch (code) { 
+        switch (code) {
         case ARCH_SET_GS:
                 if (addr >= TASK_SIZE_OF(task))
-                        return -EPERM; 
+                        return -EPERM;
                 cpu = get_cpu();
-                /* handle small bases via the GDT because that's faster to 
+                /* handle small bases via the GDT because that's faster to
                    switch. */
-                if (addr <= 0xffffffff) {  
-                        set_32bit_tls(task, GS_TLS, addr); 
-                        if (doit) { 
+                if (addr <= 0xffffffff) {
+                        set_32bit_tls(task, GS_TLS, addr);
+                        if (doit) {
                                 load_TLS(&task->thread, cpu);
-                                load_gs_index(GS_TLS_SEL); 
+                                load_gs_index(GS_TLS_SEL);
                         }
-                        task->thread.gsindex = GS_TLS_SEL; 
+                        task->thread.gsindex = GS_TLS_SEL;
                         task->thread.gs = 0;
-                } else { 
+                } else {
                         task->thread.gsindex = 0;
                         task->thread.gs = addr;
                         if (doit) {
                                 load_gs_index(0);
                                 ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr);
-                        } 
+                        }
                 }
                 put_cpu();
                 break;
@@ -825,8 +850,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
                                 rdmsrl(MSR_KERNEL_GS_BASE, base);
                         else
                                 base = task->thread.gs;
-                }
-                else
+                } else
                         base = task->thread.gs;
                 ret = put_user(base, (unsigned long __user *)addr);
                 break;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index e37dccce85db..e375b658efc3 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
+#include <linux/tracehook.h>
 #include <linux/user.h>
 #include <linux/elf.h>
 #include <linux/security.h>
@@ -69,7 +70,7 @@ static inline bool invalid_selector(u16 value)
 
 #define FLAG_MASK               FLAG_MASK_32
 
-static long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
+static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
 {
         BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
         regno >>= 2;
@@ -554,45 +555,115 @@ static int ptrace_set_debugreg(struct task_struct *child,
         return 0;
 }
 
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
+/*
+ * The configuration for a particular BTS hardware implementation.
+ */
+struct bts_configuration {
+        /* the size of a BTS record in bytes; at most BTS_MAX_RECORD_SIZE */
+        unsigned char  sizeof_bts;
+        /* the size of a field in the BTS record in bytes */
+        unsigned char  sizeof_field;
+        /* a bitmask to enable/disable BTS in DEBUGCTL MSR */
+        unsigned long debugctl_mask;
+};
+static struct bts_configuration bts_cfg;
+
+#define BTS_MAX_RECORD_SIZE (8 * 3)
+
+
+/*
+ * Branch Trace Store (BTS) uses the following format. Different
+ * architectures vary in the size of those fields.
+ * - source linear address
+ * - destination linear address
+ * - flags
+ *
+ * Later architectures use 64bit pointers throughout, whereas earlier
+ * architectures use 32bit pointers in 32bit mode.
+ *
+ * We compute the base address for the first 8 fields based on:
+ * - the field size stored in the DS configuration
+ * - the relative field position
+ *
+ * In order to store additional information in the BTS buffer, we use
+ * a special source address to indicate that the record requires
+ * special interpretation.
+ *
+ * Netburst indicated via a bit in the flags field whether the branch
+ * was predicted; this is ignored.
+ */
+
+enum bts_field {
+        bts_from = 0,
+        bts_to,
+        bts_flags,
+
+        bts_escape = (unsigned long)-1,
+        bts_qual = bts_to,
+        bts_jiffies = bts_flags
+};
+
+static inline unsigned long bts_get(const char *base, enum bts_field field)
+{
+        base += (bts_cfg.sizeof_field * field);
+        return *(unsigned long *)base;
+}
 
-static int ptrace_bts_get_size(struct task_struct *child)
+static inline void bts_set(char *base, enum bts_field field, unsigned long val)
 {
-        if (!child->thread.ds_area_msr)
-                return -ENXIO;
+        base += (bts_cfg.sizeof_field * field);;
+        (*(unsigned long *)base) = val;
+}
 
-        return ds_get_bts_index((void *)child->thread.ds_area_msr);
+/*
+ * Translate a BTS record from the raw format into the bts_struct format
+ *
+ * out (out): bts_struct interpretation
+ * raw: raw BTS record
+ */
+static void ptrace_bts_translate_record(struct bts_struct *out, const void *raw)
+{
+        memset(out, 0, sizeof(*out));
+        if (bts_get(raw, bts_from) == bts_escape) {
+                out->qualifier       = bts_get(raw, bts_qual);
+                out->variant.jiffies = bts_get(raw, bts_jiffies);
+        } else {
+                out->qualifier = BTS_BRANCH;
+                out->variant.lbr.from_ip = bts_get(raw, bts_from);
+                out->variant.lbr.to_ip   = bts_get(raw, bts_to);
+        }
 }
 
-static int ptrace_bts_read_record(struct task_struct *child,
-                                  long index,
+static int ptrace_bts_read_record(struct task_struct *child, size_t index,
                                   struct bts_struct __user *out)
 {
         struct bts_struct ret;
-        int retval;
-        int bts_end;
-        int bts_index;
-
-        if (!child->thread.ds_area_msr)
-                return -ENXIO;
+        const void *bts_record;
+        size_t bts_index, bts_end;
+        int error;
 
-        if (index < 0)
-                return -EINVAL;
+        error = ds_get_bts_end(child, &bts_end);
+        if (error < 0)
+                return error;
 
-        bts_end = ds_get_bts_end((void *)child->thread.ds_area_msr);
         if (bts_end <= index)
                 return -EINVAL;
 
+        error = ds_get_bts_index(child, &bts_index);
+        if (error < 0)
+                return error;
+
         /* translate the ptrace bts index into the ds bts index */
-        bts_index = ds_get_bts_index((void *)child->thread.ds_area_msr);
-        bts_index -= (index + 1);
-        if (bts_index < 0)
-                bts_index += bts_end;
+        bts_index += bts_end - (index + 1);
+        if (bts_end <= bts_index)
+                bts_index -= bts_end;
 
-        retval = ds_read_bts((void *)child->thread.ds_area_msr,
-                             bts_index, &ret);
-        if (retval < 0)
-                return retval;
+        error = ds_access_bts(child, bts_index, &bts_record);
+        if (error < 0)
+                return error;
+
+        ptrace_bts_translate_record(&ret, bts_record);
 
         if (copy_to_user(out, &ret, sizeof(ret)))
                 return -EFAULT;
@@ -600,101 +671,106 @@ static int ptrace_bts_read_record(struct task_struct *child,
         return sizeof(ret);
 }
 
-static int ptrace_bts_clear(struct task_struct *child)
-{
-        if (!child->thread.ds_area_msr)
-                return -ENXIO;
-
-        return ds_clear((void *)child->thread.ds_area_msr);
-}
-
 static int ptrace_bts_drain(struct task_struct *child,
                             long size,
                             struct bts_struct __user *out)
 {
-        int end, i;
-        void *ds = (void *)child->thread.ds_area_msr;
-
-        if (!ds)
-                return -ENXIO;
+        struct bts_struct ret;
+        const unsigned char *raw;
+        size_t end, i;
+        int error;
 
-        end = ds_get_bts_index(ds);
-        if (end <= 0)
-                return end;
+        error = ds_get_bts_index(child, &end);
+        if (error < 0)
+                return error;
 
         if (size < (end * sizeof(struct bts_struct)))
                 return -EIO;
 
-        for (i = 0; i < end; i++, out++) {
-                struct bts_struct ret;
-                int retval;
+        error = ds_access_bts(child, 0, (const void **)&raw);
+        if (error < 0)
+                return error;
 
-                retval = ds_read_bts(ds, i, &ret);
-                if (retval < 0)
-                        return retval;
+        for (i = 0; i < end; i++, out++, raw += bts_cfg.sizeof_bts) {
+                ptrace_bts_translate_record(&ret, raw);
 
                 if (copy_to_user(out, &ret, sizeof(ret)))
                         return -EFAULT;
         }
 
-        ds_clear(ds);
+        error = ds_clear_bts(child);
+        if (error < 0)
+                return error;
 
         return end;
 }
 
+static void ptrace_bts_ovfl(struct task_struct *child)
+{
+        send_sig(child->thread.bts_ovfl_signal, child, 0);
+}
+
 static int ptrace_bts_config(struct task_struct *child,
                              long cfg_size,
                              const struct ptrace_bts_config __user *ucfg)
 {
         struct ptrace_bts_config cfg;
-        int bts_size, ret = 0;
-        void *ds;
+        int error = 0;
+
+        error = -EOPNOTSUPP;
+        if (!bts_cfg.sizeof_bts)
+                goto errout;
 
+        error = -EIO;
         if (cfg_size < sizeof(cfg))
-                return -EIO;
+                goto errout;
 
+        error = -EFAULT;
         if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
-                return -EFAULT;
+                goto errout;
 
-        if ((int)cfg.size < 0)
-                return -EINVAL;
+        error = -EINVAL;
+        if ((cfg.flags & PTRACE_BTS_O_SIGNAL) &&
+            !(cfg.flags & PTRACE_BTS_O_ALLOC))
+                goto errout;
 
-        bts_size = 0;
-        ds = (void *)child->thread.ds_area_msr;
-        if (ds) {
-                bts_size = ds_get_bts_size(ds);
-                if (bts_size < 0)
-                        return bts_size;
-        }
-        cfg.size = PAGE_ALIGN(cfg.size);
+        if (cfg.flags & PTRACE_BTS_O_ALLOC) {
+                ds_ovfl_callback_t ovfl = NULL;
+                unsigned int sig = 0;
+
+                /* we ignore the error in case we were not tracing child */
+                (void)ds_release_bts(child);
 
-        if (bts_size != cfg.size) {
-                ret = ptrace_bts_realloc(child, cfg.size,
-                                         cfg.flags & PTRACE_BTS_O_CUT_SIZE);
-                if (ret < 0)
+                if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
+                        if (!cfg.signal)
+                                goto errout;
+
+                        sig  = cfg.signal;
+                        ovfl = ptrace_bts_ovfl;
+                }
+
+                error = ds_request_bts(child, /* base = */ NULL, cfg.size, ovfl);
+                if (error < 0)
                         goto errout;
 
-                ds = (void *)child->thread.ds_area_msr;
+                child->thread.bts_ovfl_signal = sig;
         }
 
-        if (cfg.flags & PTRACE_BTS_O_SIGNAL)
-                ret = ds_set_overflow(ds, DS_O_SIGNAL);
-        else
-                ret = ds_set_overflow(ds, DS_O_WRAP);
-        if (ret < 0)
+        error = -EINVAL;
+        if (!child->thread.ds_ctx && cfg.flags)
                 goto errout;
 
         if (cfg.flags & PTRACE_BTS_O_TRACE)
-                child->thread.debugctlmsr |= ds_debugctl_mask();
+                child->thread.debugctlmsr |= bts_cfg.debugctl_mask;
         else
-                child->thread.debugctlmsr &= ~ds_debugctl_mask();
+                child->thread.debugctlmsr &= ~bts_cfg.debugctl_mask;
 
         if (cfg.flags & PTRACE_BTS_O_SCHED)
                 set_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
         else
                 clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
 
-        ret = sizeof(cfg);
+        error = sizeof(cfg);
 
 out:
         if (child->thread.debugctlmsr)
@@ -702,10 +778,10 @@ out:
         else
                 clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
 
-        return ret;
+        return error;
 
 errout:
-        child->thread.debugctlmsr &= ~ds_debugctl_mask();
+        child->thread.debugctlmsr &= ~bts_cfg.debugctl_mask;
         clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
         goto out;
 }
@@ -714,29 +790,40 @@ static int ptrace_bts_status(struct task_struct *child,
                              long cfg_size,
                              struct ptrace_bts_config __user *ucfg)
 {
-        void *ds = (void *)child->thread.ds_area_msr;
         struct ptrace_bts_config cfg;
+        size_t end;
+        const void *base, *max;
+        int error;
 
         if (cfg_size < sizeof(cfg))
                 return -EIO;
 
-        memset(&cfg, 0, sizeof(cfg));
+        error = ds_get_bts_end(child, &end);
+        if (error < 0)
+                return error;
 
-        if (ds) {
-                cfg.size = ds_get_bts_size(ds);
+        error = ds_access_bts(child, /* index = */ 0, &base);
+        if (error < 0)
+                return error;
 
-                if (ds_get_overflow(ds) == DS_O_SIGNAL)
-                        cfg.flags |= PTRACE_BTS_O_SIGNAL;
+        error = ds_access_bts(child, /* index = */ end, &max);
+        if (error < 0)
+                return error;
 
-                if (test_tsk_thread_flag(child, TIF_DEBUGCTLMSR) &&
-                    child->thread.debugctlmsr & ds_debugctl_mask())
-                        cfg.flags |= PTRACE_BTS_O_TRACE;
+        memset(&cfg, 0, sizeof(cfg));
+        cfg.size = (max - base);
+        cfg.signal = child->thread.bts_ovfl_signal;
+        cfg.bts_size = sizeof(struct bts_struct);
 
-                if (test_tsk_thread_flag(child, TIF_BTS_TRACE_TS))
-                        cfg.flags |= PTRACE_BTS_O_SCHED;
-        }
+        if (cfg.signal)
+                cfg.flags |= PTRACE_BTS_O_SIGNAL;
 
-        cfg.bts_size = sizeof(struct bts_struct);
+        if (test_tsk_thread_flag(child, TIF_DEBUGCTLMSR) &&
+            child->thread.debugctlmsr & bts_cfg.debugctl_mask)
+                cfg.flags |= PTRACE_BTS_O_TRACE;
+
+        if (test_tsk_thread_flag(child, TIF_BTS_TRACE_TS))
+                cfg.flags |= PTRACE_BTS_O_SCHED;
 
         if (copy_to_user(ucfg, &cfg, sizeof(cfg)))
                 return -EFAULT;
@@ -744,89 +831,38 @@ static int ptrace_bts_status(struct task_struct *child,
         return sizeof(cfg);
 }
 
-
 static int ptrace_bts_write_record(struct task_struct *child,
                                    const struct bts_struct *in)
 {
-        int retval;
+        unsigned char bts_record[BTS_MAX_RECORD_SIZE];
 
-        if (!child->thread.ds_area_msr)
-                return -ENXIO;
+        BUG_ON(BTS_MAX_RECORD_SIZE < bts_cfg.sizeof_bts);
 
-        retval = ds_write_bts((void *)child->thread.ds_area_msr, in);
-        if (retval)
-                return retval;
+        memset(bts_record, 0, bts_cfg.sizeof_bts);
+        switch (in->qualifier) {
+        case BTS_INVALID:
+                break;
 
-        return sizeof(*in);
-}
+        case BTS_BRANCH:
+                bts_set(bts_record, bts_from, in->variant.lbr.from_ip);
+                bts_set(bts_record, bts_to,   in->variant.lbr.to_ip);
+                break;
 
-static int ptrace_bts_realloc(struct task_struct *child,
-                              int size, int reduce_size)
-{
-        unsigned long rlim, vm;
-        int ret, old_size;
+        case BTS_TASK_ARRIVES:
+        case BTS_TASK_DEPARTS:
+                bts_set(bts_record, bts_from,    bts_escape);
+                bts_set(bts_record, bts_qual,    in->qualifier);
+                bts_set(bts_record, bts_jiffies, in->variant.jiffies);
+                break;
 
-        if (size < 0)
+        default:
                 return -EINVAL;
-
-        old_size = ds_get_bts_size((void *)child->thread.ds_area_msr);
-        if (old_size < 0)
-                return old_size;
-
-        ret = ds_free((void **)&child->thread.ds_area_msr);
-        if (ret < 0)
-                goto out;
-
-        size >>= PAGE_SHIFT;
-        old_size >>= PAGE_SHIFT;
-
-        current->mm->total_vm  -= old_size;
-        current->mm->locked_vm -= old_size;
-
-        if (size == 0)
-                goto out;
-
-        rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
-        vm = current->mm->total_vm  + size;
-        if (rlim < vm) {
-                ret = -ENOMEM;
-
-                if (!reduce_size)
-                        goto out;
-
-                size = rlim - current->mm->total_vm;
-                if (size <= 0)
-                        goto out;
-        }
-
-        rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
-        vm = current->mm->locked_vm  + size;
-        if (rlim < vm) {
-                ret = -ENOMEM;
-
-                if (!reduce_size)
-                        goto out;
-
-                size = rlim - current->mm->locked_vm;
-                if (size <= 0)
-                        goto out;
         }
 
-        ret = ds_allocate((void **)&child->thread.ds_area_msr,
-                          size << PAGE_SHIFT);
-        if (ret < 0)
-                goto out;
-
-        current->mm->total_vm  += size;
-        current->mm->locked_vm += size;
-
-out:
-        if (child->thread.ds_area_msr)
-                set_tsk_thread_flag(child, TIF_DS_AREA_MSR);
-        else
-                clear_tsk_thread_flag(child, TIF_DS_AREA_MSR);
-
-        return ret;
+        /* The writing task will be the switched-to task on a context
+         * switch. It needs to write into the switched-from task's BTS
+         * buffer. */
+        return ds_unchecked_write_bts(child, bts_record, bts_cfg.sizeof_bts);
 }
 
 void ptrace_bts_take_timestamp(struct task_struct *tsk,
@@ -839,7 +875,66 @@ void ptrace_bts_take_timestamp(struct task_struct *tsk,
 
         ptrace_bts_write_record(tsk, &rec);
 }
-#endif /* X86_BTS */
+
+static const struct bts_configuration bts_cfg_netburst = {
+        .sizeof_bts    = sizeof(long) * 3,
+        .sizeof_field  = sizeof(long),
+        .debugctl_mask = (1<<2)|(1<<3)|(1<<5)
+};
+
+static const struct bts_configuration bts_cfg_pentium_m = {
+        .sizeof_bts    = sizeof(long) * 3,
+        .sizeof_field  = sizeof(long),
+        .debugctl_mask = (1<<6)|(1<<7)
+};
+
+static const struct bts_configuration bts_cfg_core2 = {
+        .sizeof_bts    = 8 * 3,
+        .sizeof_field  = 8,
+        .debugctl_mask = (1<<6)|(1<<7)|(1<<9)
+};
+
+static inline void bts_configure(const struct bts_configuration *cfg)
+{
+        bts_cfg = *cfg;
+}
+
+void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *c)
+{
+        switch (c->x86) {
+        case 0x6:
+                switch (c->x86_model) {
+                case 0xD:
+                case 0xE: /* Pentium M */
+                        bts_configure(&bts_cfg_pentium_m);
+                        break;
+                case 0xF: /* Core2 */
+        case 0x1C: /* Atom */
+                        bts_configure(&bts_cfg_core2);
+                        break;
+                default:
+                        /* sorry, don't know about them */
+                        break;
+                }
+                break;
+        case 0xF:
+                switch (c->x86_model) {
+                case 0x0:
+                case 0x1:
+                case 0x2: /* Netburst */
+                        bts_configure(&bts_cfg_netburst);
+                        break;
+                default:
+                        /* sorry, don't know about them */
+                        break;
+                }
+                break;
+        default:
+                /* sorry, don't know about them */
+                break;
+        }
+}
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 /*
  * Called by kernel/ptrace.c when detaching..
@@ -852,15 +947,15 @@ void ptrace_disable(struct task_struct *child)
 #ifdef TIF_SYSCALL_EMU
         clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
 #endif
-        if (child->thread.ds_area_msr) {
-#ifdef X86_BTS
-                ptrace_bts_realloc(child, 0, 0);
-#endif
-                child->thread.debugctlmsr &= ~ds_debugctl_mask();
-                if (!child->thread.debugctlmsr)
-                        clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
-                clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
-        }
+#ifdef CONFIG_X86_PTRACE_BTS
+        (void)ds_release_bts(child);
+
+        child->thread.debugctlmsr &= ~bts_cfg.debugctl_mask;
+        if (!child->thread.debugctlmsr)
+                clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
+
+        clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
+#endif /* CONFIG_X86_PTRACE_BTS */
 }
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
@@ -980,7 +1075,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
         /*
          * These bits need more cooking - not enabled yet:
          */
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
         case PTRACE_BTS_CONFIG:
                 ret = ptrace_bts_config
                         (child, data, (struct ptrace_bts_config __user *)addr);
@@ -992,7 +1087,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
                 break;
 
         case PTRACE_BTS_SIZE:
-                ret = ptrace_bts_get_size(child);
+                ret = ds_get_bts_index(child, /* pos = */ NULL);
                 break;
 
         case PTRACE_BTS_GET:
@@ -1001,14 +1096,14 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
                 break;
 
         case PTRACE_BTS_CLEAR:
-                ret = ptrace_bts_clear(child);
+                ret = ds_clear_bts(child);
                 break;
 
         case PTRACE_BTS_DRAIN:
                 ret = ptrace_bts_drain
                         (child, data, (struct bts_struct __user *) addr);
                 break;
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
 
         default:
                 ret = ptrace_request(child, request, addr, data);
@@ -1375,30 +1470,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
         force_sig_info(SIGTRAP, &info, tsk);
 }
 
-static void syscall_trace(struct pt_regs *regs)
-{
-        if (!(current->ptrace & PT_PTRACED))
-                return;
-
-#if 0
-        printk("trace %s ip %lx sp %lx ax %d origrax %d caller %lx tiflags %x ptrace %x\n",
-               current->comm,
-               regs->ip, regs->sp, regs->ax, regs->orig_ax, __builtin_return_address(0),
-               current_thread_info()->flags, current->ptrace);
-#endif
-
-        ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
-                                ? 0x80 : 0));
-        /*
-         * this isn't the same as continuing with a signal, but it will do
-         * for normal use.  strace only continues with a signal if the
-         * stopping signal is not SIGTRAP.  -brl
-         */
-        if (current->exit_code) {
-                send_sig(current->exit_code, current, 1);
-                current->exit_code = 0;
-        }
-}
 
 #ifdef CONFIG_X86_32
 # define IS_IA32        1
@@ -1432,8 +1503,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs)
         if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
                 ret = -1L;
 
-        if (ret || test_thread_flag(TIF_SYSCALL_TRACE))
-                syscall_trace(regs);
+        if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
+            tracehook_report_syscall_entry(regs))
+                ret = -1L;
 
         if (unlikely(current->audit_context)) {
                 if (IS_IA32)
@@ -1459,7 +1531,7 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
                 audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
 
         if (test_thread_flag(TIF_SYSCALL_TRACE))
-                syscall_trace(regs);
+                tracehook_report_syscall_exit(regs, 0);
 
         /*
          * If TIF_SYSCALL_EMU is set, we only get here because of
@@ -1475,6 +1547,6 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
          * system call instruction.
          */
         if (test_thread_flag(TIF_SINGLESTEP) &&
-            (current->ptrace & PT_PTRACED))
+            tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL))
                 send_sigtrap(current, regs, 0);
 }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 724adfc63cb9..f4c93f1cfc19 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -29,7 +29,11 @@ EXPORT_SYMBOL(pm_power_off);
 
 static const struct desc_ptr no_idt = {};
 static int reboot_mode;
-enum reboot_type reboot_type = BOOT_KBD;
+/*
+ * Keyboard reset and triple fault may result in INIT, not RESET, which
+ * doesn't work when we're in vmx root mode.  Try ACPI first.
+ */
+enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9838f2539dfc..141efab52400 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -223,6 +223,9 @@ unsigned long saved_video_mode;
 #define RAMDISK_LOAD_FLAG               0x4000
 
 static char __initdata command_line[COMMAND_LINE_SIZE];
+#ifdef CONFIG_CMDLINE_BOOL
+static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+#endif
 
 #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
 struct edd edd;
@@ -665,6 +668,19 @@ void __init setup_arch(char **cmdline_p)
         bss_resource.start = virt_to_phys(&__bss_start);
         bss_resource.end = virt_to_phys(&__bss_stop)-1;
 
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+        strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+        if (builtin_cmdline[0]) {
+                /* append boot loader cmdline to builtin */
+                strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+                strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+                strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+        }
+#endif
+#endif
+
         strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
         *cmdline_p = command_line;
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 76e305e064f9..0e67f72d9316 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -162,9 +162,16 @@ void __init setup_per_cpu_areas(void)
                         printk(KERN_INFO
                                "cpu %d has no node %d or node-local memory\n",
                                 cpu, node);
+                        if (ptr)
+                                printk(KERN_DEBUG "per cpu data for cpu%d at %016lx\n",
+                                         cpu, __pa(ptr));
                 }
-                else
+                else {
                         ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
+                        if (ptr)
+                                printk(KERN_DEBUG "per cpu data for cpu%d on node%d at %016lx\n",
+                                         cpu, node, __pa(ptr));
+                }
 #endif
                 per_cpu_offset(cpu) = ptr - __per_cpu_start;
                 memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
diff --git a/arch/x86/kernel/sigframe.h b/arch/x86/kernel/sigframe.h
index 72bbb519d2dc..8b4956e800ac 100644
--- a/arch/x86/kernel/sigframe.h
+++ b/arch/x86/kernel/sigframe.h
@@ -24,4 +24,9 @@ struct rt_sigframe {
         struct ucontext uc;
         struct siginfo info;
 };
+
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+                sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+                sigset_t *set, struct pt_regs *regs);
 #endif
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 6fb5bcdd8933..2a2435d3037d 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/tracehook.h>
 #include <linux/elf.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
@@ -26,6 +27,7 @@
 #include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/vdso.h>
+#include <asm/syscalls.h>
 
 #include "sigframe.h"
 
@@ -558,8 +560,6 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
          * handler too.
          */
         regs->flags &= ~X86_EFLAGS_TF;
-        if (test_thread_flag(TIF_SINGLESTEP))
-                ptrace_notify(SIGTRAP);
 
         spin_lock_irq(&current->sighand->siglock);
         sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
@@ -568,6 +568,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
         recalc_sigpending();
         spin_unlock_irq(&current->sighand->siglock);
 
+        tracehook_signal_handler(sig, info, ka, regs,
+                                 test_thread_flag(TIF_SINGLESTEP));
+
         return 0;
 }
 
@@ -661,5 +664,10 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
         if (thread_info_flags & _TIF_SIGPENDING)
                 do_signal(regs);
 
+        if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+                clear_thread_flag(TIF_NOTIFY_RESUME);
+                tracehook_notify_resume(regs);
+        }
+
         clear_thread_flag(TIF_IRET);
 }
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index ca316b5b742c..694aa888bb19 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -15,17 +15,21 @@
 #include <linux/errno.h>
 #include <linux/wait.h>
 #include <linux/ptrace.h>
+#include <linux/tracehook.h>
 #include <linux/unistd.h>
 #include <linux/stddef.h>
 #include <linux/personality.h>
 #include <linux/compiler.h>
+#include <linux/uaccess.h>
+
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/proto.h>
 #include <asm/ia32_unistd.h>
 #include <asm/mce.h>
+#include <asm/syscall.h>
+#include <asm/syscalls.h>
 #include "sigframe.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
@@ -41,11 +45,6 @@
 # define FIX_EFLAGS     __FIX_EFLAGS
 #endif
 
-int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-               sigset_t *set, struct pt_regs * regs); 
-int ia32_setup_frame(int sig, struct k_sigaction *ka,
-            sigset_t *set, struct pt_regs * regs); 
-
 asmlinkage long
 sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
                 struct pt_regs *regs)
@@ -128,7 +127,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
         /* Always make any pending restarted system calls return -EINTR */
         current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
-#define COPY(x)         err |= __get_user(regs->x, &sc->x)
+#define COPY(x)         (err |= __get_user(regs->x, &sc->x))
 
         COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
         COPY(dx); COPY(cx); COPY(ip);
@@ -158,7 +157,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
         }
 
         {
-                struct _fpstate __user * buf;
+                struct _fpstate __user *buf;
                 err |= __get_user(buf, &sc->fpstate);
 
                 if (buf) {
@@ -198,7 +197,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
         current->blocked = set;
         recalc_sigpending();
         spin_unlock_irq(&current->sighand->siglock);
-        
+
         if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
                 goto badframe;
 
@@ -208,16 +207,17 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
         return ax;
 
 badframe:
-        signal_fault(regs,frame,"sigreturn");
+        signal_fault(regs, frame, "sigreturn");
         return 0;
-}       
+}
 
 /*
  * Set up a signal frame.
  */
 
 static inline int
-setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, unsigned long mask, struct task_struct *me)
+setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
+                unsigned long mask, struct task_struct *me)
 {
         int err = 0;
 
@@ -273,35 +273,35 @@ get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size)
 }
 
 static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-                           sigset_t *set, struct pt_regs * regs)
+                           sigset_t *set, struct pt_regs *regs)
 {
         struct rt_sigframe __user *frame;
-        struct _fpstate __user *fp = NULL; 
+        struct _fpstate __user *fp = NULL;
         int err = 0;
         struct task_struct *me = current;
 
         if (used_math()) {
-                fp = get_stack(ka, regs, sizeof(struct _fpstate)); 
+                fp = get_stack(ka, regs, sizeof(struct _fpstate));
                 frame = (void __user *)round_down(
                         (unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
 
                 if (!access_ok(VERIFY_WRITE, fp, sizeof(struct _fpstate)))
                         goto give_sigsegv;
 
-                if (save_i387(fp) < 0) 
-                        err |= -1; 
+                if (save_i387(fp) < 0)
+                        err |= -1;
         } else
                 frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
 
         if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
                 goto give_sigsegv;
 
-        if (ka->sa.sa_flags & SA_SIGINFO) { 
+        if (ka->sa.sa_flags & SA_SIGINFO) {
                 err |= copy_siginfo_to_user(&frame->info, info);
                 if (err)
                         goto give_sigsegv;
         }
-                
+
         /* Create the ucontext.  */
         err |= __put_user(0, &frame->uc.uc_flags);
         err |= __put_user(0, &frame->uc.uc_link);
@@ -311,9 +311,9 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
         err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
         err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me);
         err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate);
-        if (sizeof(*set) == 16) { 
+        if (sizeof(*set) == 16) {
                 __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
-                __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); 
+                __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
         } else
                 err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
 
@@ -324,7 +324,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                 err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
         } else {
                 /* could use a vstub here */
-                goto give_sigsegv; 
+                goto give_sigsegv;
         }
 
         if (err)
@@ -332,7 +332,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 
         /* Set up registers for signal handler */
         regs->di = sig;
-        /* In case the signal handler was declared without prototypes */ 
+        /* In case the signal handler was declared without prototypes */
         regs->ax = 0;
 
         /* This also works for non SA_SIGINFO handlers because they expect the
@@ -355,37 +355,8 @@ give_sigsegv:
 }
 
 /*
- * Return -1L or the syscall number that @regs is executing.
- */
-static long current_syscall(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;
-}
-
-/*
- * Return a value that is -EFOO if the system call in @regs->orig_ax
- * returned an error.  This only works for @regs from @current.
- */
-static long current_syscall_ret(struct pt_regs *regs)
-{
-#ifdef CONFIG_IA32_EMULATION
-        if (test_thread_flag(TIF_IA32))
-                /*
-                 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
-                 * and will match correctly in comparisons.
-                 */
-                return (int) regs->ax;
-#endif
-        return regs->ax;
-}
-
-/*
  * OK, we're invoking a handler
- */     
+ */
 
 static int
 handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
@@ -394,9 +365,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
         int ret;
 
         /* Are we from a system call? */
-        if (current_syscall(regs) >= 0) {
+        if (syscall_get_nr(current, regs) >= 0) {
                 /* If so, check system call restarting.. */
-                switch (current_syscall_ret(regs)) {
+                switch (syscall_get_error(current, regs)) {
                 case -ERESTART_RESTARTBLOCK:
                 case -ERESTARTNOHAND:
                         regs->ax = -EINTR;
@@ -429,7 +400,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
                         ret = ia32_setup_rt_frame(sig, ka, info, oldset, regs);
                 else
                         ret = ia32_setup_frame(sig, ka, oldset, regs);
-        } else 
+        } else
 #endif
         ret = setup_rt_frame(sig, ka, info, oldset, regs);
 
@@ -453,15 +424,16 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
                  * handler too.
                  */
                 regs->flags &= ~X86_EFLAGS_TF;
-                if (test_thread_flag(TIF_SINGLESTEP))
-                        ptrace_notify(SIGTRAP);
 
                 spin_lock_irq(&current->sighand->siglock);
-                sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
+                sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
                 if (!(ka->sa.sa_flags & SA_NODEFER))
-                        sigaddset(&current->blocked,sig);
+                        sigaddset(&current->blocked, sig);
                 recalc_sigpending();
                 spin_unlock_irq(&current->sighand->siglock);
+
+                tracehook_signal_handler(sig, info, ka, regs,
+                                         test_thread_flag(TIF_SINGLESTEP));
         }
 
         return ret;
@@ -518,9 +490,9 @@ static void do_signal(struct pt_regs *regs)
         }
 
         /* Did we come from a system call? */
-        if (current_syscall(regs) >= 0) {
+        if (syscall_get_nr(current, regs) >= 0) {
                 /* Restart the system call - no handlers present */
-                switch (current_syscall_ret(regs)) {
+                switch (syscall_get_error(current, regs)) {
                 case -ERESTARTNOHAND:
                 case -ERESTARTSYS:
                 case -ERESTARTNOINTR:
@@ -558,17 +530,23 @@ void do_notify_resume(struct pt_regs *regs, void *unused,
         /* deal with pending signal delivery */
         if (thread_info_flags & _TIF_SIGPENDING)
                 do_signal(regs);
+
+        if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+                clear_thread_flag(TIF_NOTIFY_RESUME);
+                tracehook_notify_resume(regs);
+        }
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
-{ 
-        struct task_struct *me = current; 
+{
+        struct task_struct *me = current;
         if (show_unhandled_signals && printk_ratelimit()) {
                 printk("%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
-               me->comm,me->pid,where,frame,regs->ip,regs->sp,regs->orig_ax);
+               me->comm, me->pid, where, frame, regs->ip,
+                   regs->sp, regs->orig_ax);
                 print_vma_addr(" in ", regs->ip);
                 printk("\n");
         }
 
-        force_sig(SIGSEGV, me); 
-} 
+        force_sig(SIGSEGV, me);
+}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7985c5b3f916..45531e3ba194 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -88,7 +88,7 @@ static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
 #define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
 #define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
 #else
-struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
+static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
 #define get_idle_for_cpu(x)      (idle_thread_array[(x)])
 #define set_idle_for_cpu(x, p)   (idle_thread_array[(x)] = (p))
 #endif
@@ -129,7 +129,7 @@ static int boot_cpu_logical_apicid;
 static cpumask_t cpu_sibling_setup_map;
 
 /* Set if we find a B stepping CPU */
-int __cpuinitdata smp_b_stepping;
+static int __cpuinitdata smp_b_stepping;
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
 
@@ -1313,16 +1313,13 @@ __init void prefill_possible_map(void)
         if (!num_processors)
                 num_processors = 1;
 
-#ifdef CONFIG_HOTPLUG_CPU
         if (additional_cpus == -1) {
                 if (disabled_cpus > 0)
                         additional_cpus = disabled_cpus;
                 else
                         additional_cpus = 0;
         }
-#else
-        additional_cpus = 0;
-#endif
+
         possible = num_processors + additional_cpus;
         if (possible > NR_CPUS)
                 possible = NR_CPUS;
diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
index 7066cb855a60..1884a8d12bfa 100644
--- a/arch/x86/kernel/sys_i386_32.c
+++ b/arch/x86/kernel/sys_i386_32.c
@@ -22,6 +22,8 @@
 #include <linux/uaccess.h>
 #include <linux/unistd.h>
 
+#include <asm/syscalls.h>
+
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
                           unsigned long prot, unsigned long flags,
                           unsigned long fd, unsigned long pgoff)
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 3b360ef33817..6bc211accf08 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -13,15 +13,17 @@
 #include <linux/utsname.h>
 #include <linux/personality.h>
 #include <linux/random.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/ia32.h>
+#include <asm/syscalls.h>
 
-asmlinkage long sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags,
-        unsigned long fd, unsigned long off)
+asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
+                unsigned long prot, unsigned long flags,
+                unsigned long fd, unsigned long off)
 {
         long error;
-        struct file * file;
+        struct file *file;
 
         error = -EINVAL;
         if (off & ~PAGE_MASK)
@@ -56,9 +58,9 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
                    unmapped base down for this case. This can give
                    conflicts with the heap, but we assume that glibc
                    malloc knows how to fall back to mmap. Give it 1GB
-                   of playground for now. -AK */ 
-                *begin = 0x40000000; 
-                *end = 0x80000000;              
+                   of playground for now. -AK */
+                *begin = 0x40000000;
+                *end = 0x80000000;
                 if (current->flags & PF_RANDOMIZE) {
                         new_begin = randomize_range(*begin, *begin + 0x02000000, 0);
                         if (new_begin)
@@ -66,9 +68,9 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
                 }
         } else {
                 *begin = TASK_UNMAPPED_BASE;
-                *end = TASK_SIZE; 
+                *end = TASK_SIZE;
         }
-} 
+}
 
 unsigned long
 arch_get_unmapped_area(struct file *filp, unsigned long addr,
@@ -78,11 +80,11 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
         struct vm_area_struct *vma;
         unsigned long start_addr;
         unsigned long begin, end;
-        
+
         if (flags & MAP_FIXED)
                 return addr;
 
-        find_start_end(flags, &begin, &end); 
+        find_start_end(flags, &begin, &end);
 
         if (len > end)
                 return -ENOMEM;
@@ -96,12 +98,12 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
         }
         if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32))
             && len <= mm->cached_hole_size) {
-                mm->cached_hole_size = 0;
+                mm->cached_hole_size = 0;
                 mm->free_area_cache = begin;
         }
         addr = mm->free_area_cache;
-        if (addr < begin) 
-                addr = begin; 
+        if (addr < begin)
+                addr = begin;
         start_addr = addr;
 
 full_search:
@@ -127,7 +129,7 @@ full_search:
                         return addr;
                 }
                 if (addr + mm->cached_hole_size < vma->vm_start)
-                        mm->cached_hole_size = vma->vm_start - addr;
+                        mm->cached_hole_size = vma->vm_start - addr;
 
                 addr = vma->vm_end;
         }
@@ -177,7 +179,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
                 vma = find_vma(mm, addr-len);
                 if (!vma || addr <= vma->vm_start)
                         /* remember the address as a hint for next time */
-                        return (mm->free_area_cache = addr-len);
+                        return mm->free_area_cache = addr-len;
         }
 
         if (mm->mmap_base < len)
@@ -194,7 +196,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
                 vma = find_vma(mm, addr);
                 if (!vma || addr+len <= vma->vm_start)
                         /* remember the address as a hint for next time */
-                        return (mm->free_area_cache = addr);
+                        return mm->free_area_cache = addr;
 
                 /* remember the largest hole we saw so far */
                 if (addr + mm->cached_hole_size < vma->vm_start)
@@ -224,13 +226,13 @@ bottomup:
 }
 
 
-asmlinkage long sys_uname(struct new_utsname __user * name)
+asmlinkage long sys_uname(struct new_utsname __user *name)
 {
         int err;
         down_read(&uts_sem);
-        err = copy_to_user(name, utsname(), sizeof (*name));
+        err = copy_to_user(name, utsname(), sizeof(*name));
         up_read(&uts_sem);
-        if (personality(current->personality) == PER_LINUX32) 
-                err |= copy_to_user(&name->machine, "i686", 5);                 
+        if (personality(current->personality) == PER_LINUX32)
+                err |= copy_to_user(&name->machine, "i686", 5);
         return err ? -EFAULT : 0;
 }
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index 170d43c17487..3d1be4f0fac5 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -8,12 +8,12 @@
 #define __NO_STUBS
 
 #define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ;
-#undef _ASM_X86_64_UNISTD_H_
+#undef ASM_X86__UNISTD_64_H
 #include <asm/unistd_64.h>
 
 #undef __SYSCALL
 #define __SYSCALL(nr, sym) [nr] = sym,
-#undef _ASM_X86_64_UNISTD_H_
+#undef ASM_X86__UNISTD_64_H
 
 typedef void (*sys_call_ptr_t)(void);
 
diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
index ffe3c664afc0..bbecf8b6bf96 100644
--- a/arch/x86/kernel/time_32.c
+++ b/arch/x86/kernel/time_32.c
@@ -36,6 +36,7 @@
 #include <asm/arch_hooks.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
+#include <asm/timer.h>
 
 #include "do_timer.h"
 
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index ab6bf375a307..6bb7b8579e70 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -10,6 +10,7 @@
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/proto.h>
+#include <asm/syscalls.h>
 
 #include "tls.h"
 
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index 513caaca7115..7a31f104bef9 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -32,6 +32,8 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 #include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/io.h>
 
 #if defined(CONFIG_EDAC)
 #include <linux/edac.h>
@@ -45,9 +47,6 @@
 #include <asm/unwind.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
-#include <asm/nmi.h>
-#include <asm/smp.h>
-#include <asm/io.h>
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #include <asm/pda.h>
@@ -85,7 +84,8 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 
 void printk_address(unsigned long address, int reliable)
 {
-        printk(" [<%016lx>] %s%pS\n", address, reliable ? "": "? ", (void *) address);
+        printk(" [<%016lx>] %s%pS\n",
+                        address, reliable ?     "" : "? ", (void *) address);
 }
 
 static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
@@ -98,7 +98,8 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
                 [STACKFAULT_STACK - 1] = "#SS",
                 [MCE_STACK - 1] = "#MC",
 #if DEBUG_STKSZ > EXCEPTION_STKSZ
-                [N_EXCEPTION_STACKS ... N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
+                [N_EXCEPTION_STACKS ...
+                        N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
 #endif
         };
         unsigned k;
@@ -163,7 +164,7 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 }
 
 /*
- * x86-64 can have up to three kernel stacks: 
+ * x86-64 can have up to three kernel stacks:
  * process stack
  * interrupt stack
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
@@ -219,7 +220,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                 const struct stacktrace_ops *ops, void *data)
 {
         const unsigned cpu = get_cpu();
-        unsigned long *irqstack_end = (unsigned long*)cpu_pda(cpu)->irqstackptr;
+        unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
         unsigned used = 0;
         struct thread_info *tinfo;
 
@@ -237,7 +238,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
         if (!bp) {
                 if (task == current) {
                         /* Grab bp right from our regs */
-                        asm("movq %%rbp, %0" : "=r" (bp) :);
+                        asm("movq %%rbp, %0" : "=r" (bp) : );
                 } else {
                         /* bp is the last reg pushed by switch_to */
                         bp = *(unsigned long *) task->thread.sp;
@@ -339,9 +340,8 @@ static void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp, char *log_lvl)
 {
-        printk("\nCall Trace:\n");
+        printk("Call Trace:\n");
         dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-        printk("\n");
 }
 
 void show_trace(struct task_struct *task, struct pt_regs *regs,
@@ -357,11 +357,15 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
         unsigned long *stack;
         int i;
         const int cpu = smp_processor_id();
-        unsigned long *irqstack_end = (unsigned long *) (cpu_pda(cpu)->irqstackptr);
-        unsigned long *irqstack = (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
+        unsigned long *irqstack_end =
+                (unsigned long *) (cpu_pda(cpu)->irqstackptr);
+        unsigned long *irqstack =
+                (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
 
-        // debugging aid: "show_stack(NULL, NULL);" prints the
-        // back trace for this cpu.
+        /*
+         * debugging aid: "show_stack(NULL, NULL);" prints the
+         * back trace for this cpu.
+         */
 
         if (sp == NULL) {
                 if (task)
@@ -386,6 +390,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
                 printk(" %016lx", *stack++);
                 touch_nmi_watchdog();
         }
+        printk("\n");
         show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
@@ -404,7 +409,7 @@ void dump_stack(void)
 
 #ifdef CONFIG_FRAME_POINTER
         if (!bp)
-                asm("movq %%rbp, %0" : "=r" (bp):);
+                asm("movq %%rbp, %0" : "=r" (bp) : );
 #endif
 
         printk("Pid: %d, comm: %.20s %s %s %.*s\n",
@@ -414,7 +419,6 @@ void dump_stack(void)
                 init_utsname()->version);
         show_trace(NULL, NULL, &stack, bp);
 }
-
 EXPORT_SYMBOL(dump_stack);
 
 void show_registers(struct pt_regs *regs)
@@ -443,7 +447,6 @@ void show_registers(struct pt_regs *regs)
                 printk("Stack: ");
                 show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
                                 regs->bp, "");
-                printk("\n");
 
                 printk(KERN_EMERG "Code: ");
 
@@ -493,7 +496,7 @@ unsigned __kprobes long oops_begin(void)
         raw_local_irq_save(flags);
         cpu = smp_processor_id();
         if (!__raw_spin_trylock(&die_lock)) {
-                if (cpu == die_owner) 
+                if (cpu == die_owner)
                         /* nested oops. should stop eventually */;
                 else
                         __raw_spin_lock(&die_lock);
@@ -638,7 +641,7 @@ kernel_trap:
 }
 
 #define DO_ERROR(trapnr, signr, str, name) \
-asmlinkage void do_##name(struct pt_regs * regs, long error_code)       \
+asmlinkage void do_##name(struct pt_regs *regs, long error_code)        \
 {                                                                       \
         if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)  \
                                                         == NOTIFY_STOP) \
@@ -648,7 +651,7 @@ asmlinkage void do_##name(struct pt_regs * regs, long error_code)	\
 }
 
 #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)         \
-asmlinkage void do_##name(struct pt_regs * regs, long error_code)       \
+asmlinkage void do_##name(struct pt_regs *regs, long error_code)        \
 {                                                                       \
         siginfo_t info;                                                 \
         info.si_signo = signr;                                          \
@@ -683,7 +686,7 @@ asmlinkage void do_stack_segment(struct pt_regs *regs, long error_code)
         preempt_conditional_cli(regs);
 }
 
-asmlinkage void do_double_fault(struct pt_regs * regs, long error_code)
+asmlinkage void do_double_fault(struct pt_regs *regs, long error_code)
 {
         static const char str[] = "double fault";
         struct task_struct *tsk = current;
@@ -778,9 +781,10 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 }
 
 static notrace __kprobes void
-unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
+unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 {
-        if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
+        if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) ==
+                        NOTIFY_STOP)
                 return;
         printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n",
                 reason);
@@ -882,7 +886,7 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
         else if (user_mode(eregs))
                 regs = task_pt_regs(current);
         /* Exception from kernel and interrupts are enabled. Move to
-           kernel process stack. */
+           kernel process stack. */
         else if (eregs->flags & X86_EFLAGS_IF)
                 regs = (struct pt_regs *)(eregs->sp -= sizeof(struct pt_regs));
         if (eregs != regs)
@@ -891,7 +895,7 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 }
 
 /* runs on IST stack. */
-asmlinkage void __kprobes do_debug(struct pt_regs * regs,
+asmlinkage void __kprobes do_debug(struct pt_regs *regs,
                                    unsigned long error_code)
 {
         struct task_struct *tsk = current;
@@ -1035,7 +1039,7 @@ asmlinkage void do_coprocessor_error(struct pt_regs *regs)
 
 asmlinkage void bad_intr(void)
 {
-        printk("bad interrupt"); 
+        printk("bad interrupt");
 }
 
 asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs)
@@ -1047,7 +1051,7 @@ asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs)
 
         conditional_sti(regs);
         if (!user_mode(regs) &&
-                kernel_math_error(regs, "kernel simd math error", 19))
+                        kernel_math_error(regs, "kernel simd math error", 19))
                 return;
 
         /*
@@ -1092,7 +1096,7 @@ asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs)
         force_sig_info(SIGFPE, &info, task);
 }
 
-asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs)
+asmlinkage void do_spurious_interrupt_bug(struct pt_regs *regs)
 {
 }
 
@@ -1149,8 +1153,10 @@ void __init trap_init(void)
         set_intr_gate(0, &divide_error);
         set_intr_gate_ist(1, &debug, DEBUG_STACK);
         set_intr_gate_ist(2, &nmi, NMI_STACK);
-        set_system_gate_ist(3, &int3, DEBUG_STACK); /* int3 can be called from all */
-        set_system_gate(4, &overflow); /* int4 can be called from all */
+        /* int3 can be called from all */
+        set_system_gate_ist(3, &int3, DEBUG_STACK);
+        /* int4 can be called from all */
+        set_system_gate(4, &overflow);
         set_intr_gate(5, &bounds);
         set_intr_gate(6, &invalid_op);
         set_intr_gate(7, &device_not_available);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8f98e9de1b82..161bb850fc47 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -104,7 +104,7 @@ __setup("notsc", notsc_setup);
 /*
  * Read TSC and the reference counters. Take care of SMI disturbance
  */
-static u64 tsc_read_refs(u64 *pm, u64 *hpet)
+static u64 tsc_read_refs(u64 *p, int hpet)
 {
         u64 t1, t2;
         int i;
@@ -112,9 +112,9 @@ static u64 tsc_read_refs(u64 *pm, u64 *hpet)
         for (i = 0; i < MAX_RETRIES; i++) {
                 t1 = get_cycles();
                 if (hpet)
-                        *hpet = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
+                        *p = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
                 else
-                        *pm = acpi_pm_read_early();
+                        *p = acpi_pm_read_early();
                 t2 = get_cycles();
                 if ((t2 - t1) < SMI_TRESHOLD)
                         return t2;
@@ -123,13 +123,59 @@ static u64 tsc_read_refs(u64 *pm, u64 *hpet)
 }
 
 /*
+ * Calculate the TSC frequency from HPET reference
+ */
+static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2)
+{
+        u64 tmp;
+
+        if (hpet2 < hpet1)
+                hpet2 += 0x100000000ULL;
+        hpet2 -= hpet1;
+        tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
+        do_div(tmp, 1000000);
+        do_div(deltatsc, tmp);
+
+        return (unsigned long) deltatsc;
+}
+
+/*
+ * Calculate the TSC frequency from PMTimer reference
+ */
+static unsigned long calc_pmtimer_ref(u64 deltatsc, u64 pm1, u64 pm2)
+{
+        u64 tmp;
+
+        if (!pm1 && !pm2)
+                return ULONG_MAX;
+
+        if (pm2 < pm1)
+                pm2 += (u64)ACPI_PM_OVRRUN;
+        pm2 -= pm1;
+        tmp = pm2 * 1000000000LL;
+        do_div(tmp, PMTMR_TICKS_PER_SEC);
+        do_div(deltatsc, tmp);
+
+        return (unsigned long) deltatsc;
+}
+
+#define CAL_MS          10
+#define CAL_LATCH       (CLOCK_TICK_RATE / (1000 / CAL_MS))
+#define CAL_PIT_LOOPS   1000
+
+#define CAL2_MS         50
+#define CAL2_LATCH      (CLOCK_TICK_RATE / (1000 / CAL2_MS))
+#define CAL2_PIT_LOOPS  5000
+
+
+/*
  * Try to calibrate the TSC against the Programmable
  * Interrupt Timer and return the frequency of the TSC
  * in kHz.
  *
  * Return ULONG_MAX on failure to calibrate.
  */
-static unsigned long pit_calibrate_tsc(void)
+static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin)
 {
         u64 tsc, t1, t2, delta;
         unsigned long tscmin, tscmax;
@@ -144,8 +190,8 @@ static unsigned long pit_calibrate_tsc(void)
          * (LSB then MSB) to begin countdown.
          */
         outb(0xb0, 0x43);
-        outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
-        outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42);
+        outb(latch & 0xff, 0x42);
+        outb(latch >> 8, 0x42);
 
         tsc = t1 = t2 = get_cycles();
 
@@ -166,31 +212,154 @@ static unsigned long pit_calibrate_tsc(void)
         /*
          * Sanity checks:
          *
-         * If we were not able to read the PIT more than 5000
+         * If we were not able to read the PIT more than loopmin
          * times, then we have been hit by a massive SMI
          *
          * If the maximum is 10 times larger than the minimum,
          * then we got hit by an SMI as well.
          */
-        if (pitcnt < 5000 || tscmax > 10 * tscmin)
+        if (pitcnt < loopmin || tscmax > 10 * tscmin)
                 return ULONG_MAX;
 
         /* Calculate the PIT value */
         delta = t2 - t1;
-        do_div(delta, 50);
+        do_div(delta, ms);
         return delta;
 }
 
+/*
+ * This reads the current MSB of the PIT counter, and
+ * checks if we are running on sufficiently fast and
+ * non-virtualized hardware.
+ *
+ * Our expectations are:
+ *
+ *  - the PIT is running at roughly 1.19MHz
+ *
+ *  - each IO is going to take about 1us on real hardware,
+ *    but we allow it to be much faster (by a factor of 10) or
+ *    _slightly_ slower (ie we allow up to a 2us read+counter
+ *    update - anything else implies a unacceptably slow CPU
+ *    or PIT for the fast calibration to work.
+ *
+ *  - with 256 PIT ticks to read the value, we have 214us to
+ *    see the same MSB (and overhead like doing a single TSC
+ *    read per MSB value etc).
+ *
+ *  - We're doing 2 reads per loop (LSB, MSB), and we expect
+ *    them each to take about a microsecond on real hardware.
+ *    So we expect a count value of around 100. But we'll be
+ *    generous, and accept anything over 50.
+ *
+ *  - if the PIT is stuck, and we see *many* more reads, we
+ *    return early (and the next caller of pit_expect_msb()
+ *    then consider it a failure when they don't see the
+ *    next expected value).
+ *
+ * These expectations mean that we know that we have seen the
+ * transition from one expected value to another with a fairly
+ * high accuracy, and we didn't miss any events. We can thus
+ * use the TSC value at the transitions to calculate a pretty
+ * good value for the TSC frequencty.
+ */
+static inline int pit_expect_msb(unsigned char val)
+{
+        int count = 0;
+
+        for (count = 0; count < 50000; count++) {
+                /* Ignore LSB */
+                inb(0x42);
+                if (inb(0x42) != val)
+                        break;
+        }
+        return count > 50;
+}
+
+/*
+ * How many MSB values do we want to see? We aim for a
+ * 15ms calibration, which assuming a 2us counter read
+ * error should give us roughly 150 ppm precision for
+ * the calibration.
+ */
+#define QUICK_PIT_MS 15
+#define QUICK_PIT_ITERATIONS (QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
+
+static unsigned long quick_pit_calibrate(void)
+{
+        /* Set the Gate high, disable speaker */
+        outb((inb(0x61) & ~0x02) | 0x01, 0x61);
+
+        /*
+         * Counter 2, mode 0 (one-shot), binary count
+         *
+         * NOTE! Mode 2 decrements by two (and then the
+         * output is flipped each time, giving the same
+         * final output frequency as a decrement-by-one),
+         * so mode 0 is much better when looking at the
+         * individual counts.
+         */
+        outb(0xb0, 0x43);
+
+        /* Start at 0xffff */
+        outb(0xff, 0x42);
+        outb(0xff, 0x42);
+
+        if (pit_expect_msb(0xff)) {
+                int i;
+                u64 t1, t2, delta;
+                unsigned char expect = 0xfe;
+
+                t1 = get_cycles();
+                for (i = 0; i < QUICK_PIT_ITERATIONS; i++, expect--) {
+                        if (!pit_expect_msb(expect))
+                                goto failed;
+                }
+                t2 = get_cycles();
+
+                /*
+                 * Make sure we can rely on the second TSC timestamp:
+                 */
+                if (!pit_expect_msb(expect))
+                        goto failed;
+
+                /*
+                 * Ok, if we get here, then we've seen the
+                 * MSB of the PIT decrement QUICK_PIT_ITERATIONS
+                 * times, and each MSB had many hits, so we never
+                 * had any sudden jumps.
+                 *
+                 * As a result, we can depend on there not being
+                 * any odd delays anywhere, and the TSC reads are
+                 * reliable.
+                 *
+                 * kHz = ticks / time-in-seconds / 1000;
+                 * kHz = (t2 - t1) / (QPI * 256 / PIT_TICK_RATE) / 1000
+                 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (QPI * 256 * 1000)
+                 */
+                delta = (t2 - t1)*PIT_TICK_RATE;
+                do_div(delta, QUICK_PIT_ITERATIONS*256*1000);
+                printk("Fast TSC calibration using PIT\n");
+                return delta;
+        }
+failed:
+        return 0;
+}
 
 /**
  * native_calibrate_tsc - calibrate the tsc on boot
  */
 unsigned long native_calibrate_tsc(void)
 {
-        u64 tsc1, tsc2, delta, pm1, pm2, hpet1, hpet2;
+        u64 tsc1, tsc2, delta, ref1, ref2;
         unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-        unsigned long flags;
-        int hpet = is_hpet_enabled(), i;
+        unsigned long flags, latch, ms, fast_calibrate;
+        int hpet = is_hpet_enabled(), i, loopmin;
+
+        local_irq_save(flags);
+        fast_calibrate = quick_pit_calibrate();
+        local_irq_restore(flags);
+        if (fast_calibrate)
+                return fast_calibrate;
 
         /*
          * Run 5 calibration loops to get the lowest frequency value
@@ -216,7 +385,13 @@ unsigned long native_calibrate_tsc(void)
          * calibration delay loop as we have to wait for a certain
          * amount of time anyway.
          */
-        for (i = 0; i < 5; i++) {
+
+        /* Preset PIT loop values */
+        latch = CAL_LATCH;
+        ms = CAL_MS;
+        loopmin = CAL_PIT_LOOPS;
+
+        for (i = 0; i < 3; i++) {
                 unsigned long tsc_pit_khz;
 
                 /*
@@ -226,16 +401,16 @@ unsigned long native_calibrate_tsc(void)
                  * read the end value.
                  */
                 local_irq_save(flags);
-                tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
-                tsc_pit_khz = pit_calibrate_tsc();
-                tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
+                tsc1 = tsc_read_refs(&ref1, hpet);
+                tsc_pit_khz = pit_calibrate_tsc(latch, ms, loopmin);
+                tsc2 = tsc_read_refs(&ref2, hpet);
                 local_irq_restore(flags);
 
                 /* Pick the lowest PIT TSC calibration so far */
                 tsc_pit_min = min(tsc_pit_min, tsc_pit_khz);
 
                 /* hpet or pmtimer available ? */
-                if (!hpet && !pm1 && !pm2)
+                if (!hpet && !ref1 && !ref2)
                         continue;
 
                 /* Check, whether the sampling was disturbed by an SMI */
@@ -243,23 +418,41 @@ unsigned long native_calibrate_tsc(void)
                         continue;
 
                 tsc2 = (tsc2 - tsc1) * 1000000LL;
+                if (hpet)
+                        tsc2 = calc_hpet_ref(tsc2, ref1, ref2);
+                else
+                        tsc2 = calc_pmtimer_ref(tsc2, ref1, ref2);
 
-                if (hpet) {
-                        if (hpet2 < hpet1)
-                                hpet2 += 0x100000000ULL;
-                        hpet2 -= hpet1;
-                        tsc1 = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
-                        do_div(tsc1, 1000000);
-                } else {
-                        if (pm2 < pm1)
-                                pm2 += (u64)ACPI_PM_OVRRUN;
-                        pm2 -= pm1;
-                        tsc1 = pm2 * 1000000000LL;
-                        do_div(tsc1, PMTMR_TICKS_PER_SEC);
+                tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2);
+
+                /* Check the reference deviation */
+                delta = ((u64) tsc_pit_min) * 100;
+                do_div(delta, tsc_ref_min);
+
+                /*
+                 * If both calibration results are inside a 10% window
+                 * then we can be sure, that the calibration
+                 * succeeded. We break out of the loop right away. We
+                 * use the reference value, as it is more precise.
+                 */
+                if (delta >= 90 && delta <= 110) {
+                        printk(KERN_INFO
+                               "TSC: PIT calibration matches %s. %d loops\n",
+                               hpet ? "HPET" : "PMTIMER", i + 1);
+                        return tsc_ref_min;
                 }
 
-                do_div(tsc2, tsc1);
-                tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2);
+                /*
+                 * Check whether PIT failed more than once. This
+                 * happens in virtualized environments. We need to
+                 * give the virtual PC a slightly longer timeframe for
+                 * the HPET/PMTIMER to make the result precise.
+                 */
+                if (i == 1 && tsc_pit_min == ULONG_MAX) {
+                        latch = CAL2_LATCH;
+                        ms = CAL2_MS;
+                        loopmin = CAL2_PIT_LOOPS;
+                }
         }
 
         /*
@@ -270,7 +463,7 @@ unsigned long native_calibrate_tsc(void)
                 printk(KERN_WARNING "TSC: Unable to calibrate against PIT\n");
 
                 /* We don't have an alternative source, disable TSC */
-                if (!hpet && !pm1 && !pm2) {
+                if (!hpet && !ref1 && !ref2) {
                         printk("TSC: No reference (HPET/PMTIMER) available\n");
                         return 0;
                 }
@@ -278,7 +471,7 @@ unsigned long native_calibrate_tsc(void)
                 /* The alternative source failed as well, disable TSC */
                 if (tsc_ref_min == ULONG_MAX) {
                         printk(KERN_WARNING "TSC: HPET/PMTIMER calibration "
-                               "failed due to SMI disturbance.\n");
+                               "failed.\n");
                         return 0;
                 }
 
@@ -290,44 +483,25 @@ unsigned long native_calibrate_tsc(void)
         }
 
         /* We don't have an alternative source, use the PIT calibration value */
-        if (!hpet && !pm1 && !pm2) {
+        if (!hpet && !ref1 && !ref2) {
                 printk(KERN_INFO "TSC: Using PIT calibration value\n");
                 return tsc_pit_min;
         }
 
         /* The alternative source failed, use the PIT calibration value */
         if (tsc_ref_min == ULONG_MAX) {
-                printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed due "
-                       "to SMI disturbance. Using PIT calibration\n");
+                printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed. "
+                       "Using PIT calibration\n");
                 return tsc_pit_min;
         }
 
-        /* Check the reference deviation */
-        delta = ((u64) tsc_pit_min) * 100;
-        do_div(delta, tsc_ref_min);
-
-        /*
-         * If both calibration results are inside a 5% window, the we
-         * use the lower frequency of those as it is probably the
-         * closest estimate.
-         */
-        if (delta >= 95 && delta <= 105) {
-                printk(KERN_INFO "TSC: PIT calibration confirmed by %s.\n",
-                       hpet ? "HPET" : "PMTIMER");
-                printk(KERN_INFO "TSC: using %s calibration value\n",
-                       tsc_pit_min <= tsc_ref_min ? "PIT" :
-                       hpet ? "HPET" : "PMTIMER");
-                return tsc_pit_min <= tsc_ref_min ? tsc_pit_min : tsc_ref_min;
-        }
-
-        printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n",
-               hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min);
-
         /*
          * The calibration values differ too much. In doubt, we use
          * the PIT value as we know that there are PMTIMERs around
-         * running at double speed.
+         * running at double speed. At least we let the user know:
          */
+        printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n",
+               hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min);
         printk(KERN_INFO "TSC: Using PIT calibration value\n");
         return tsc_pit_min;
 }
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 594ef47f0a63..61a97e616f70 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -25,45 +25,31 @@
 #include <asm/visws/cobalt.h>
 #include <asm/visws/piix4.h>
 #include <asm/arch_hooks.h>
+#include <asm/io_apic.h>
 #include <asm/fixmap.h>
 #include <asm/reboot.h>
 #include <asm/setup.h>
 #include <asm/e820.h>
-#include <asm/smp.h>
 #include <asm/io.h>
 
 #include <mach_ipi.h>
 
 #include "mach_apic.h"
 
-#include <linux/init.h>
-#include <linux/smp.h>
-
 #include <linux/kernel_stat.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
 
-#include <asm/io.h>
-#include <asm/apic.h>
 #include <asm/i8259.h>
 #include <asm/irq_vectors.h>
-#include <asm/visws/cobalt.h>
 #include <asm/visws/lithium.h>
-#include <asm/visws/piix4.h>
 
 #include <linux/sched.h>
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
 
 extern int no_broadcast;
 
-#include <asm/io.h>
 #include <asm/apic.h>
-#include <asm/arch_hooks.h>
-#include <asm/visws/cobalt.h>
-#include <asm/visws/lithium.h>
 
 char visws_board_type   = -1;
 char visws_board_rev    = -1;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 38f566fa27d2..4eeb5cf9720d 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -46,6 +46,7 @@
 #include <asm/io.h>
 #include <asm/tlbflush.h>
 #include <asm/irq.h>
+#include <asm/syscalls.h>
 
 /*
  * Known problems:
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index edfb09f30479..8c9ad02af5a2 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -393,13 +393,13 @@ static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
 }
 #endif
 
-static void vmi_allocate_pte(struct mm_struct *mm, u32 pfn)
+static void vmi_allocate_pte(struct mm_struct *mm, unsigned long pfn)
 {
         vmi_set_page_type(pfn, VMI_PAGE_L1);
         vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
 }
 
-static void vmi_allocate_pmd(struct mm_struct *mm, u32 pfn)
+static void vmi_allocate_pmd(struct mm_struct *mm, unsigned long pfn)
 {
         /*
          * This call comes in very early, before mem_map is setup.
@@ -410,20 +410,20 @@ static void vmi_allocate_pmd(struct mm_struct *mm, u32 pfn)
         vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0);
 }
 
-static void vmi_allocate_pmd_clone(u32 pfn, u32 clonepfn, u32 start, u32 count)
+static void vmi_allocate_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count)
 {
         vmi_set_page_type(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE);
         vmi_check_page_type(clonepfn, VMI_PAGE_L2);
         vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count);
 }
 
-static void vmi_release_pte(u32 pfn)
+static void vmi_release_pte(unsigned long pfn)
 {
         vmi_ops.release_page(pfn, VMI_PAGE_L1);
         vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
 }
 
-static void vmi_release_pmd(u32 pfn)
+static void vmi_release_pmd(unsigned long pfn)
 {
         vmi_ops.release_page(pfn, VMI_PAGE_L2);
         vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
diff --git a/arch/x86/lib/msr-on-cpu.c b/arch/x86/lib/msr-on-cpu.c
index 01b868ba82f8..321cf720dbb6 100644
--- a/arch/x86/lib/msr-on-cpu.c
+++ b/arch/x86/lib/msr-on-cpu.c
@@ -16,37 +16,46 @@ static void __rdmsr_on_cpu(void *info)
         rdmsr(rv->msr_no, rv->l, rv->h);
 }
 
-static void __rdmsr_safe_on_cpu(void *info)
+static void __wrmsr_on_cpu(void *info)
 {
         struct msr_info *rv = info;
 
-        rv->err = rdmsr_safe(rv->msr_no, &rv->l, &rv->h);
+        wrmsr(rv->msr_no, rv->l, rv->h);
 }
 
-static int _rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h, int safe)
+int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
-        int err = 0;
+        int err;
         struct msr_info rv;
 
         rv.msr_no = msr_no;
-        if (safe) {
-                err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu,
-                                               &rv, 1);
-                err = err ? err : rv.err;
-        } else {
-                err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
-        }
+        err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
         *l = rv.l;
         *h = rv.h;
 
         return err;
 }
 
-static void __wrmsr_on_cpu(void *info)
+int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+        int err;
+        struct msr_info rv;
+
+        rv.msr_no = msr_no;
+        rv.l = l;
+        rv.h = h;
+        err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
+
+        return err;
+}
+
+/* These "safe" variants are slower and should be used when the target MSR
+   may not actually exist. */
+static void __rdmsr_safe_on_cpu(void *info)
 {
         struct msr_info *rv = info;
 
-        wrmsr(rv->msr_no, rv->l, rv->h);
+        rv->err = rdmsr_safe(rv->msr_no, &rv->l, &rv->h);
 }
 
 static void __wrmsr_safe_on_cpu(void *info)
@@ -56,45 +65,30 @@ static void __wrmsr_safe_on_cpu(void *info)
         rv->err = wrmsr_safe(rv->msr_no, rv->l, rv->h);
 }
 
-static int _wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h, int safe)
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
-        int err = 0;
+        int err;
         struct msr_info rv;
 
         rv.msr_no = msr_no;
-        rv.l = l;
-        rv.h = h;
-        if (safe) {
-                err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu,
-                                               &rv, 1);
-                err = err ? err : rv.err;
-        } else {
-                err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
-        }
-
-        return err;
-}
+        err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
+        *l = rv.l;
+        *h = rv.h;
 
-int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-        return _wrmsr_on_cpu(cpu, msr_no, l, h, 0);
+        return err ? err : rv.err;
 }
 
-int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-        return _rdmsr_on_cpu(cpu, msr_no, l, h, 0);
-}
-
-/* These "safe" variants are slower and should be used when the target MSR
-   may not actually exist. */
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 {
-        return _wrmsr_on_cpu(cpu, msr_no, l, h, 1);
-}
+        int err;
+        struct msr_info rv;
 
-int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-        return _rdmsr_on_cpu(cpu, msr_no, l, h, 1);
+        rv.msr_no = msr_no;
+        rv.l = l;
+        rv.h = h;
+        err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
+
+        return err ? err : rv.err;
 }
 
 EXPORT_SYMBOL(rdmsr_on_cpu);
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 94972e7c094d..82004d2bf05e 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -22,7 +22,7 @@ char *strcpy(char *dest, const char *src)
                 "testb %%al,%%al\n\t"
                 "jne 1b"
                 : "=&S" (d0), "=&D" (d1), "=&a" (d2)
-                :"0" (src), "1" (dest) : "memory");
+                : "0" (src), "1" (dest) : "memory");
         return dest;
 }
 EXPORT_SYMBOL(strcpy);
@@ -42,7 +42,7 @@ char *strncpy(char *dest, const char *src, size_t count)
                 "stosb\n"
                 "2:"
                 : "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
-                :"0" (src), "1" (dest), "2" (count) : "memory");
+                : "0" (src), "1" (dest), "2" (count) : "memory");
         return dest;
 }
 EXPORT_SYMBOL(strncpy);
@@ -60,7 +60,7 @@ char *strcat(char *dest, const char *src)
                 "testb %%al,%%al\n\t"
                 "jne 1b"
                 : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
-                : "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu): "memory");
+                : "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu) : "memory");
         return dest;
 }
 EXPORT_SYMBOL(strcat);
@@ -105,9 +105,9 @@ int strcmp(const char *cs, const char *ct)
                 "2:\tsbbl %%eax,%%eax\n\t"
                 "orb $1,%%al\n"
                 "3:"
-                :"=a" (res), "=&S" (d0), "=&D" (d1)
-                :"1" (cs), "2" (ct)
-                :"memory");
+                : "=a" (res), "=&S" (d0), "=&D" (d1)
+                : "1" (cs), "2" (ct)
+                : "memory");
         return res;
 }
 EXPORT_SYMBOL(strcmp);
@@ -130,9 +130,9 @@ int strncmp(const char *cs, const char *ct, size_t count)
                 "3:\tsbbl %%eax,%%eax\n\t"
                 "orb $1,%%al\n"
                 "4:"
-                :"=a" (res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
-                :"1" (cs), "2" (ct), "3" (count)
-                :"memory");
+                : "=a" (res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
+                : "1" (cs), "2" (ct), "3" (count)
+                : "memory");
         return res;
 }
 EXPORT_SYMBOL(strncmp);
@@ -152,9 +152,9 @@ char *strchr(const char *s, int c)
                 "movl $1,%1\n"
                 "2:\tmovl %1,%0\n\t"
                 "decl %0"
-                :"=a" (res), "=&S" (d0)
-                :"1" (s), "0" (c)
-                :"memory");
+                : "=a" (res), "=&S" (d0)
+                : "1" (s), "0" (c)
+                : "memory");
         return res;
 }
 EXPORT_SYMBOL(strchr);
@@ -169,9 +169,9 @@ size_t strlen(const char *s)
                 "scasb\n\t"
                 "notl %0\n\t"
                 "decl %0"
-                :"=c" (res), "=&D" (d0)
-                :"1" (s), "a" (0), "0" (0xffffffffu)
-                :"memory");
+                : "=c" (res), "=&D" (d0)
+                : "1" (s), "a" (0), "0" (0xffffffffu)
+                : "memory");
         return res;
 }
 EXPORT_SYMBOL(strlen);
@@ -189,9 +189,9 @@ void *memchr(const void *cs, int c, size_t count)
                 "je 1f\n\t"
                 "movl $1,%0\n"
                 "1:\tdecl %0"
-                :"=D" (res), "=&c" (d0)
-                :"a" (c), "0" (cs), "1" (count)
-                :"memory");
+                : "=D" (res), "=&c" (d0)
+                : "a" (c), "0" (cs), "1" (count)
+                : "memory");
         return res;
 }
 EXPORT_SYMBOL(memchr);
@@ -228,9 +228,9 @@ size_t strnlen(const char *s, size_t count)
                 "cmpl $-1,%1\n\t"
                 "jne 1b\n"
                 "3:\tsubl %2,%0"
-                :"=a" (res), "=&d" (d0)
-                :"c" (s), "1" (count)
-                :"memory");
+                : "=a" (res), "=&d" (d0)
+                : "c" (s), "1" (count)
+                : "memory");
         return res;
 }
 EXPORT_SYMBOL(strnlen);
diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c
index 42e8a50303f3..8e2d55f754bf 100644
--- a/arch/x86/lib/strstr_32.c
+++ b/arch/x86/lib/strstr_32.c
@@ -23,9 +23,9 @@ __asm__ __volatile__(
         "jne 1b\n\t"
         "xorl %%eax,%%eax\n\t"
         "2:"
-        :"=a" (__res), "=&c" (d0), "=&S" (d1)
-        :"0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
-        :"dx", "di");
+        : "=a" (__res), "=&c" (d0), "=&S" (d1)
+        : "0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
+        : "dx", "di");
 return __res;
 }
 
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index 3d317836be9e..3f2cf11f201a 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -10,13 +10,15 @@
 #include <asm/e820.h>
 #include <asm/setup.h>
 
+#include <mach_ipi.h>
+
 #ifdef CONFIG_HOTPLUG_CPU
 #define DEFAULT_SEND_IPI        (1)
 #else
 #define DEFAULT_SEND_IPI        (0)
 #endif
 
-int no_broadcast=DEFAULT_SEND_IPI;
+int no_broadcast = DEFAULT_SEND_IPI;
 
 /**
  * pre_intr_init_hook - initialisation prior to setting up interrupt vectors
diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c
index 62fa440678d8..847c164725f4 100644
--- a/arch/x86/mm/discontig_32.c
+++ b/arch/x86/mm/discontig_32.c
@@ -328,7 +328,7 @@ void __init initmem_init(unsigned long start_pfn,
 
         get_memcfg_numa();
 
-        kva_pages = round_up(calculate_numa_remap_pages(), PTRS_PER_PTE);
+        kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE);
 
         kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
         do {
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index a20d1fa64b4e..e7277cbcfb40 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -148,8 +148,8 @@ static void note_page(struct seq_file *m, struct pg_state *st,
          * we have now. "break" is either changing perms, levels or
          * address space marker.
          */
-        prot = pgprot_val(new_prot) & ~(PTE_PFN_MASK);
-        cur = pgprot_val(st->current_prot) & ~(PTE_PFN_MASK);
+        prot = pgprot_val(new_prot) & PTE_FLAGS_MASK;
+        cur = pgprot_val(st->current_prot) & PTE_FLAGS_MASK;
 
         if (!st->level) {
                 /* First entry */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 455f3fe67b42..8f92cac4e6db 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -35,6 +35,7 @@
 #include <asm/tlbflush.h>
 #include <asm/proto.h>
 #include <asm-generic/sections.h>
+#include <asm/traps.h>
 
 /*
  * Page fault error code bits
@@ -357,8 +358,6 @@ static int is_errata100(struct pt_regs *regs, unsigned long address)
         return 0;
 }
 
-void do_invalid_op(struct pt_regs *, unsigned long);
-
 static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_F00F_BUG
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 60ec1d08ff24..6b9a9358b330 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -47,6 +47,7 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/smp.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index d3746efb060d..770536ebf7e9 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -225,7 +225,7 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
 void __init cleanup_highmap(void)
 {
         unsigned long vaddr = __START_KERNEL_map;
-        unsigned long end = round_up((unsigned long)_end, PMD_SIZE) - 1;
+        unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
         pmd_t *pmd = level2_kernel_pgt;
         pmd_t *last_pmd = pmd + PTRS_PER_PMD;
 
@@ -451,14 +451,14 @@ static void __init find_early_table_space(unsigned long end)
         unsigned long puds, pmds, ptes, tables, start;
 
         puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-        tables = round_up(puds * sizeof(pud_t), PAGE_SIZE);
+        tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
         if (direct_gbpages) {
                 unsigned long extra;
                 extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
                 pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
         } else
                 pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-        tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
+        tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
 
         if (cpu_has_pse) {
                 unsigned long extra;
@@ -466,7 +466,7 @@ static void __init find_early_table_space(unsigned long end)
                 ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
         } else
                 ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
-        tables += round_up(ptes * sizeof(pte_t), PAGE_SIZE);
+        tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
 
         /*
          * RED-PEN putting page tables only on node 0 could
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index d4b6e6a29ae3..cac6da54203b 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -421,7 +421,7 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr)
         return;
 }
 
-int __initdata early_ioremap_debug;
+static int __initdata early_ioremap_debug;
 
 static int __init early_ioremap_debug_setup(char *str)
 {
@@ -547,7 +547,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
 }
 
 
-int __initdata early_ioremap_nested;
+static int __initdata early_ioremap_nested;
 
 static int __init check_early_ioremap_leak(void)
 {
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index a4dd793d6003..cebcbf152d46 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -79,7 +79,7 @@ static int __init allocate_cachealigned_memnodemap(void)
                 return 0;
 
         addr = 0x8000;
-        nodemap_size = round_up(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
+        nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
         nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT,
                                       nodemap_size, L1_CACHE_BYTES);
         if (nodemap_addr == -1UL) {
@@ -176,10 +176,10 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
         unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
         unsigned long bootmap_start, nodedata_phys;
         void *bootmap;
-        const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
+        const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
         int nid;
 
-        start = round_up(start, ZONE_ALIGN);
+        start = roundup(start, ZONE_ALIGN);
 
         printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
                start, end);
@@ -210,9 +210,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
         bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
         nid = phys_to_nid(nodedata_phys);
         if (nid == nodeid)
-                bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+                bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
         else
-                bootmap_start = round_up(start, PAGE_SIZE);
+                bootmap_start = roundup(start, PAGE_SIZE);
         /*
          * SMP_CACHE_BYTES could be enough, but init_bootmem_node like
          * to use that to align to PAGE_SIZE
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 43e2f8483e4f..898fad617abe 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -84,7 +84,7 @@ static inline unsigned long highmap_start_pfn(void)
 
 static inline unsigned long highmap_end_pfn(void)
 {
-        return __pa(round_up((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT;
+        return __pa(roundup((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT;
 }
 
 #endif
@@ -906,11 +906,13 @@ int set_memory_ro(unsigned long addr, int numpages)
 {
         return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_RW));
 }
+EXPORT_SYMBOL_GPL(set_memory_ro);
 
 int set_memory_rw(unsigned long addr, int numpages)
 {
         return change_page_attr_set(addr, numpages, __pgprot(_PAGE_RW));
 }
+EXPORT_SYMBOL_GPL(set_memory_rw);
 
 int set_memory_np(unsigned long addr, int numpages)
 {
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index d50302774fe2..86f2ffc43c3d 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -63,10 +63,8 @@ static inline void pgd_list_del(pgd_t *pgd)
 #define UNSHARED_PTRS_PER_PGD                           \
         (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
 
-static void pgd_ctor(void *p)
+static void pgd_ctor(pgd_t *pgd)
 {
-        pgd_t *pgd = p;
-
         /* If the pgd points to a shared pagetable level (either the
            ptes in non-PAE, or shared PMD in PAE), then just copy the
            references from swapper_pg_dir. */
@@ -87,7 +85,7 @@ static void pgd_ctor(void *p)
                 pgd_list_add(pgd);
 }
 
-static void pgd_dtor(void *pgd)
+static void pgd_dtor(pgd_t *pgd)
 {
         unsigned long flags; /* can be called from interrupt context */
 
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index cab0abbd1ebe..0951db9ee519 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -123,7 +123,8 @@ static int __init parse_vmalloc(char *arg)
         if (!arg)
                 return -EINVAL;
 
-        __VMALLOC_RESERVE = memparse(arg, &arg);
+        /* Add VMALLOC_OFFSET to the parsed value due to vm area guard hole*/
+        __VMALLOC_RESERVE = memparse(arg, &arg) + VMALLOC_OFFSET;
         return 0;
 }
 early_param("vmalloc", parse_vmalloc);
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 56b4757a1f47..43ac5af338d8 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -10,11 +10,12 @@
 
 #include <linux/oprofile.h>
 #include <linux/smp.h>
+#include <linux/ptrace.h>
+#include <linux/nmi.h>
 #include <asm/msr.h>
-#include <asm/ptrace.h>
 #include <asm/fixmap.h>
 #include <asm/apic.h>
-#include <asm/nmi.h>
+
 
 #include "op_x86_model.h"
 #include "op_counter.h"
@@ -40,7 +41,7 @@ static unsigned int num_controls = NUM_CONTROLS_NON_HT;
 static inline void setup_num_counters(void)
 {
 #ifdef CONFIG_SMP
-        if (smp_num_siblings == 2){
+        if (smp_num_siblings == 2) {
                 num_counters = NUM_COUNTERS_HT2;
                 num_controls = NUM_CONTROLS_HT2;
         }
@@ -86,7 +87,7 @@ struct p4_event_binding {
 #define CTR_FLAME_2    (1 << 6)
 #define CTR_IQ_5       (1 << 7)
 
-static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = {
+static struct p4_counter_binding p4_counters[NUM_COUNTERS_NON_HT] = {
         { CTR_BPU_0,   MSR_P4_BPU_PERFCTR0,   MSR_P4_BPU_CCCR0 },
         { CTR_MS_0,    MSR_P4_MS_PERFCTR0,    MSR_P4_MS_CCCR0 },
         { CTR_FLAME_0, MSR_P4_FLAME_PERFCTR0, MSR_P4_FLAME_CCCR0 },
@@ -97,32 +98,32 @@ static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = {
         { CTR_IQ_5,    MSR_P4_IQ_PERFCTR5,    MSR_P4_IQ_CCCR5 }
 };
 
-#define NUM_UNUSED_CCCRS        NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT
+#define NUM_UNUSED_CCCRS (NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT)
 
 /* p4 event codes in libop/op_event.h are indices into this table. */
 
 static struct p4_event_binding p4_events[NUM_EVENTS] = {
-        
+
         { /* BRANCH_RETIRED */
-                0x05, 0x06, 
+                0x05, 0x06,
                 { {CTR_IQ_4, MSR_P4_CRU_ESCR2},
                   {CTR_IQ_5, MSR_P4_CRU_ESCR3} }
         },
-        
+
         { /* MISPRED_BRANCH_RETIRED */
-                0x04, 0x03, 
+                0x04, 0x03,
                 { { CTR_IQ_4, MSR_P4_CRU_ESCR0},
                   { CTR_IQ_5, MSR_P4_CRU_ESCR1} }
         },
-        
+
         { /* TC_DELIVER_MODE */
                 0x01, 0x01,
-                { { CTR_MS_0, MSR_P4_TC_ESCR0},  
+                { { CTR_MS_0, MSR_P4_TC_ESCR0},
                   { CTR_MS_2, MSR_P4_TC_ESCR1} }
         },
-        
+
         { /* BPU_FETCH_REQUEST */
-                0x00, 0x03, 
+                0x00, 0x03,
                 { { CTR_BPU_0, MSR_P4_BPU_ESCR0},
                   { CTR_BPU_2, MSR_P4_BPU_ESCR1} }
         },
@@ -146,7 +147,7 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
         },
 
         { /* LOAD_PORT_REPLAY */
-                0x02, 0x04, 
+                0x02, 0x04,
                 { { CTR_FLAME_0, MSR_P4_SAAT_ESCR0},
                   { CTR_FLAME_2, MSR_P4_SAAT_ESCR1} }
         },
@@ -170,43 +171,43 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
         },
 
         { /* BSQ_CACHE_REFERENCE */
-                0x07, 0x0c, 
+                0x07, 0x0c,
                 { { CTR_BPU_0, MSR_P4_BSU_ESCR0},
                   { CTR_BPU_2, MSR_P4_BSU_ESCR1} }
         },
 
         { /* IOQ_ALLOCATION */
-                0x06, 0x03, 
+                0x06, 0x03,
                 { { CTR_BPU_0, MSR_P4_FSB_ESCR0},
                   { 0, 0 } }
         },
 
         { /* IOQ_ACTIVE_ENTRIES */
-                0x06, 0x1a, 
+                0x06, 0x1a,
                 { { CTR_BPU_2, MSR_P4_FSB_ESCR1},
                   { 0, 0 } }
         },
 
         { /* FSB_DATA_ACTIVITY */
-                0x06, 0x17, 
+                0x06, 0x17,
                 { { CTR_BPU_0, MSR_P4_FSB_ESCR0},
                   { CTR_BPU_2, MSR_P4_FSB_ESCR1} }
         },
 
         { /* BSQ_ALLOCATION */
-                0x07, 0x05, 
+                0x07, 0x05,
                 { { CTR_BPU_0, MSR_P4_BSU_ESCR0},
                   { 0, 0 } }
         },
 
         { /* BSQ_ACTIVE_ENTRIES */
                 0x07, 0x06,
-                { { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */},  
+                { { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */},
                   { 0, 0 } }
         },
 
         { /* X87_ASSIST */
-                0x05, 0x03, 
+                0x05, 0x03,
                 { { CTR_IQ_4, MSR_P4_CRU_ESCR2},
                   { CTR_IQ_5, MSR_P4_CRU_ESCR3} }
         },
@@ -216,21 +217,21 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
                 { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
                   { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
         },
-  
+
         { /* PACKED_SP_UOP */
-                0x01, 0x08, 
+                0x01, 0x08,
                 { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
                   { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
         },
-  
+
         { /* PACKED_DP_UOP */
-                0x01, 0x0c, 
+                0x01, 0x0c,
                 { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
                   { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
         },
 
         { /* SCALAR_SP_UOP */
-                0x01, 0x0a, 
+                0x01, 0x0a,
                 { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
                   { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
         },
@@ -242,31 +243,31 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
         },
 
         { /* 64BIT_MMX_UOP */
-                0x01, 0x02, 
+                0x01, 0x02,
                 { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
                   { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
         },
-  
+
         { /* 128BIT_MMX_UOP */
-                0x01, 0x1a, 
+                0x01, 0x1a,
                 { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
                   { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
         },
 
         { /* X87_FP_UOP */
-                0x01, 0x04, 
+                0x01, 0x04,
                 { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
                   { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
         },
-  
+
         { /* X87_SIMD_MOVES_UOP */
-                0x01, 0x2e, 
+                0x01, 0x2e,
                 { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
                   { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
         },
-  
+
         { /* MACHINE_CLEAR */
-                0x05, 0x02, 
+                0x05, 0x02,
                 { { CTR_IQ_4, MSR_P4_CRU_ESCR2},
                   { CTR_IQ_5, MSR_P4_CRU_ESCR3} }
         },
@@ -276,9 +277,9 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
                 { { CTR_BPU_0, MSR_P4_FSB_ESCR0},
                   { CTR_BPU_2, MSR_P4_FSB_ESCR1} }
         },
-  
+
         { /* TC_MS_XFER */
-                0x00, 0x05, 
+                0x00, 0x05,
                 { { CTR_MS_0, MSR_P4_MS_ESCR0},
                   { CTR_MS_2, MSR_P4_MS_ESCR1} }
         },
@@ -308,7 +309,7 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
         },
 
         { /* INSTR_RETIRED */
-                0x04, 0x02, 
+                0x04, 0x02,
                 { { CTR_IQ_4, MSR_P4_CRU_ESCR0},
                   { CTR_IQ_5, MSR_P4_CRU_ESCR1} }
         },
@@ -319,14 +320,14 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
                   { CTR_IQ_5, MSR_P4_CRU_ESCR1} }
         },
 
-        { /* UOP_TYPE */    
-                0x02, 0x02, 
+        { /* UOP_TYPE */
+                0x02, 0x02,
                 { { CTR_IQ_4, MSR_P4_RAT_ESCR0},
                   { CTR_IQ_5, MSR_P4_RAT_ESCR1} }
         },
 
         { /* RETIRED_MISPRED_BRANCH_TYPE */
-                0x02, 0x05, 
+                0x02, 0x05,
                 { { CTR_MS_0, MSR_P4_TBPU_ESCR0},
                   { CTR_MS_2, MSR_P4_TBPU_ESCR1} }
         },
@@ -349,8 +350,8 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
 #define ESCR_SET_OS_1(escr, os) ((escr) |= (((os) & 1) << 1))
 #define ESCR_SET_EVENT_SELECT(escr, sel) ((escr) |= (((sel) & 0x3f) << 25))
 #define ESCR_SET_EVENT_MASK(escr, mask) ((escr) |= (((mask) & 0xffff) << 9))
-#define ESCR_READ(escr,high,ev,i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high));} while (0)
-#define ESCR_WRITE(escr,high,ev,i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high));} while (0)
+#define ESCR_READ(escr, high, ev, i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0)
+#define ESCR_WRITE(escr, high, ev, i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0)
 
 #define CCCR_RESERVED_BITS 0x38030FFF
 #define CCCR_CLEAR(cccr) ((cccr) &= CCCR_RESERVED_BITS)
@@ -360,15 +361,15 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
 #define CCCR_SET_PMI_OVF_1(cccr) ((cccr) |= (1<<27))
 #define CCCR_SET_ENABLE(cccr) ((cccr) |= (1<<12))
 #define CCCR_SET_DISABLE(cccr) ((cccr) &= ~(1<<12))
-#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high));} while (0)
-#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high));} while (0)
+#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0)
+#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0)
 #define CCCR_OVF_P(cccr) ((cccr) & (1U<<31))
 #define CCCR_CLEAR_OVF(cccr) ((cccr) &= (~(1U<<31)))
 
-#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0)
-#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l,h,i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h));} while (0)
-#define CTR_WRITE(l,i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1);} while (0)
+#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
+#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
+#define CTR_READ(l, h, i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h)); } while (0)
+#define CTR_WRITE(l, i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1); } while (0)
 #define CTR_OVERFLOW_P(ctr) (!((ctr) & 0x80000000))
 
 
@@ -380,7 +381,7 @@ static unsigned int get_stagger(void)
 #ifdef CONFIG_SMP
         int cpu = smp_processor_id();
         return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu)));
-#endif  
+#endif
         return 0;
 }
 
@@ -395,25 +396,23 @@ static unsigned long reset_value[NUM_COUNTERS_NON_HT];
 
 static void p4_fill_in_addresses(struct op_msrs * const msrs)
 {
-        unsigned int i; 
+        unsigned int i;
         unsigned int addr, cccraddr, stag;
 
         setup_num_counters();
         stag = get_stagger();
 
         /* initialize some registers */
-        for (i = 0; i < num_counters; ++i) {
+        for (i = 0; i < num_counters; ++i)
                 msrs->counters[i].addr = 0;
-        }
-        for (i = 0; i < num_controls; ++i) {
+        for (i = 0; i < num_controls; ++i)
                 msrs->controls[i].addr = 0;
-        }
-        
+
         /* the counter & cccr registers we pay attention to */
         for (i = 0; i < num_counters; ++i) {
                 addr = p4_counters[VIRT_CTR(stag, i)].counter_address;
                 cccraddr = p4_counters[VIRT_CTR(stag, i)].cccr_address;
-                if (reserve_perfctr_nmi(addr)){
+                if (reserve_perfctr_nmi(addr)) {
                         msrs->counters[i].addr = addr;
                         msrs->controls[i].addr = cccraddr;
                 }
@@ -447,22 +446,22 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs)
                 if (reserve_evntsel_nmi(addr))
                         msrs->controls[i].addr = addr;
         }
-        
+
         for (addr = MSR_P4_MS_ESCR0 + stag;
-             addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) { 
+             addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) {
                 if (reserve_evntsel_nmi(addr))
                         msrs->controls[i].addr = addr;
         }
-        
+
         for (addr = MSR_P4_IX_ESCR0 + stag;
-             addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) { 
+             addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) {
                 if (reserve_evntsel_nmi(addr))
                         msrs->controls[i].addr = addr;
         }
 
         /* there are 2 remaining non-contiguously located ESCRs */
 
-        if (num_counters == NUM_COUNTERS_NON_HT) {              
+        if (num_counters == NUM_COUNTERS_NON_HT) {
                 /* standard non-HT CPUs handle both remaining ESCRs*/
                 if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5))
                         msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
@@ -498,20 +497,20 @@ static void pmc_setup_one_p4_counter(unsigned int ctr)
         unsigned int stag;
 
         stag = get_stagger();
-        
+
         /* convert from counter *number* to counter *bit* */
         counter_bit = 1 << VIRT_CTR(stag, ctr);
-        
+
         /* find our event binding structure. */
         if (counter_config[ctr].event <= 0 || counter_config[ctr].event > NUM_EVENTS) {
-                printk(KERN_ERR 
-                       "oprofile: P4 event code 0x%lx out of range\n", 
+                printk(KERN_ERR
+                       "oprofile: P4 event code 0x%lx out of range\n",
                        counter_config[ctr].event);
                 return;
         }
-        
+
         ev = &(p4_events[counter_config[ctr].event - 1]);
-        
+
         for (i = 0; i < maxbind; i++) {
                 if (ev->bindings[i].virt_counter & counter_bit) {
 
@@ -526,25 +525,24 @@ static void pmc_setup_one_p4_counter(unsigned int ctr)
                                 ESCR_SET_OS_1(escr, counter_config[ctr].kernel);
                         }
                         ESCR_SET_EVENT_SELECT(escr, ev->event_select);
-                        ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask);                       
+                        ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask);
                         ESCR_WRITE(escr, high, ev, i);
-                       
+
                         /* modify CCCR */
                         CCCR_READ(cccr, high, VIRT_CTR(stag, ctr));
                         CCCR_CLEAR(cccr);
                         CCCR_SET_REQUIRED_BITS(cccr);
                         CCCR_SET_ESCR_SELECT(cccr, ev->escr_select);
-                        if (stag == 0) {
+                        if (stag == 0)
                                 CCCR_SET_PMI_OVF_0(cccr);
-                        } else {
+                        else
                                 CCCR_SET_PMI_OVF_1(cccr);
-                        }
                         CCCR_WRITE(cccr, high, VIRT_CTR(stag, ctr));
                         return;
                 }
         }
 
-        printk(KERN_ERR 
+        printk(KERN_ERR
                "oprofile: P4 event code 0x%lx no binding, stag %d ctr %d\n",
                counter_config[ctr].event, stag, ctr);
 }
@@ -559,14 +557,14 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs)
         stag = get_stagger();
 
         rdmsr(MSR_IA32_MISC_ENABLE, low, high);
-        if (! MISC_PMC_ENABLED_P(low)) {
+        if (!MISC_PMC_ENABLED_P(low)) {
                 printk(KERN_ERR "oprofile: P4 PMC not available\n");
                 return;
         }
 
         /* clear the cccrs we will use */
         for (i = 0 ; i < num_counters ; i++) {
-                if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+                if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
                         continue;
                 rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
                 CCCR_CLEAR(low);
@@ -576,14 +574,14 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs)
 
         /* clear all escrs (including those outside our concern) */
         for (i = num_counters; i < num_controls; i++) {
-                if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+                if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
                         continue;
                 wrmsr(msrs->controls[i].addr, 0, 0);
         }
 
         /* setup all counters */
         for (i = 0 ; i < num_counters ; ++i) {
-                if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs,i))) {
+                if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs, i))) {
                         reset_value[i] = counter_config[i].count;
                         pmc_setup_one_p4_counter(i);
                         CTR_WRITE(counter_config[i].count, VIRT_CTR(stag, i));
@@ -603,11 +601,11 @@ static int p4_check_ctrs(struct pt_regs * const regs,
         stag = get_stagger();
 
         for (i = 0; i < num_counters; ++i) {
-                
-                if (!reset_value[i]) 
+
+                if (!reset_value[i])
                         continue;
 
-                /* 
+                /*
                  * there is some eccentricity in the hardware which
                  * requires that we perform 2 extra corrections:
                  *
@@ -616,24 +614,24 @@ static int p4_check_ctrs(struct pt_regs * const regs,
                  *
                  * - write the counter back twice to ensure it gets
                  *   updated properly.
-                 * 
+                 *
                  * the former seems to be related to extra NMIs happening
                  * during the current NMI; the latter is reported as errata
                  * N15 in intel doc 249199-029, pentium 4 specification
                  * update, though their suggested work-around does not
                  * appear to solve the problem.
                  */
-                
+
                 real = VIRT_CTR(stag, i);
 
                 CCCR_READ(low, high, real);
-                CTR_READ(ctr, high, real);
+                CTR_READ(ctr, high, real);
                 if (CCCR_OVF_P(low) || CTR_OVERFLOW_P(ctr)) {
                         oprofile_add_sample(regs, i);
-                        CTR_WRITE(reset_value[i], real);
+                        CTR_WRITE(reset_value[i], real);
                         CCCR_CLEAR_OVF(low);
                         CCCR_WRITE(low, high, real);
-                        CTR_WRITE(reset_value[i], real);
+                        CTR_WRITE(reset_value[i], real);
                 }
         }
 
@@ -683,15 +681,16 @@ static void p4_shutdown(struct op_msrs const * const msrs)
         int i;
 
         for (i = 0 ; i < num_counters ; ++i) {
-                if (CTR_IS_RESERVED(msrs,i))
+                if (CTR_IS_RESERVED(msrs, i))
                         release_perfctr_nmi(msrs->counters[i].addr);
         }
-        /* some of the control registers are specially reserved in
+        /*
+         * some of the control registers are specially reserved in
          * conjunction with the counter registers (hence the starting offset).
          * This saves a few bits.
          */
         for (i = num_counters ; i < num_controls ; ++i) {
-                if (CTRL_IS_RESERVED(msrs,i))
+                if (CTRL_IS_RESERVED(msrs, i))
                         release_evntsel_nmi(msrs->controls[i].addr);
         }
 }
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 6a0fca78c362..22e057665e55 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -580,7 +580,7 @@ static int __cpuinit amd_cpu_notify(struct notifier_block *self,
                                     unsigned long action, void *hcpu)
 {
         int cpu = (long)hcpu;
-        switch(action) {
+        switch (action) {
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
                 smp_call_function_single(cpu, enable_pci_io_ecs, NULL, 0);
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 8e077185e185..006599db0dc7 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1043,35 +1043,44 @@ static void __init pcibios_fixup_irqs(void)
                 if (io_apic_assign_pci_irqs) {
                         int irq;
 
-                        if (pin) {
-                                /*
-                                 * interrupt pins are numbered starting
-                                 * from 1
-                                 */
-                                pin--;
-                                irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
-                                        PCI_SLOT(dev->devfn), pin);
-        /*
-         * Busses behind bridges are typically not listed in the MP-table.
-         * In this case we have to look up the IRQ based on the parent bus,
-         * parent slot, and pin number. The SMP code detects such bridged
-         * busses itself so we should get into this branch reliably.
-         */
-                                if (irq < 0 && dev->bus->parent) { /* go back to the bridge */
-                                        struct pci_dev *bridge = dev->bus->self;
-
-                                        pin = (pin + PCI_SLOT(dev->devfn)) % 4;
-                                        irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
-                                                        PCI_SLOT(bridge->devfn), pin);
-                                        if (irq >= 0)
-                                                dev_warn(&dev->dev, "using bridge %s INT %c to get IRQ %d\n",
-                                                         pci_name(bridge),
-                                                         'A' + pin, irq);
-                                }
-                                if (irq >= 0) {
-                                        dev_info(&dev->dev, "PCI->APIC IRQ transform: INT %c -> IRQ %d\n", 'A' + pin, irq);
-                                        dev->irq = irq;
-                                }
+                        if (!pin)
+                                continue;
+
+                        /*
+                         * interrupt pins are numbered starting from 1
+                         */
+                        pin--;
+                        irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
+                                PCI_SLOT(dev->devfn), pin);
+                        /*
+                         * Busses behind bridges are typically not listed in the
+                         * MP-table.  In this case we have to look up the IRQ
+                         * based on the parent bus, parent slot, and pin number.
+                         * The SMP code detects such bridged busses itself so we
+                         * should get into this branch reliably.
+                         */
+                        if (irq < 0 && dev->bus->parent) {
+                                /* go back to the bridge */
+                                struct pci_dev *bridge = dev->bus->self;
+                                int bus;
+
+                                pin = (pin + PCI_SLOT(dev->devfn)) % 4;
+                                bus = bridge->bus->number;
+                                irq = IO_APIC_get_PCI_irq_vector(bus,
+                                                PCI_SLOT(bridge->devfn), pin);
+                                if (irq >= 0)
+                                        dev_warn(&dev->dev,
+                                                "using bridge %s INT %c to "
+                                                        "get IRQ %d\n",
+                                                 pci_name(bridge),
+                                                 'A' + pin, irq);
+                        }
+                        if (irq >= 0) {
+                                dev_info(&dev->dev,
+                                        "PCI->APIC IRQ transform: INT %c "
+                                                "-> IRQ %d\n",
+                                        'A' + pin, irq);
+                                dev->irq = irq;
                         }
                 }
 #endif
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 4fc7e872c85e..d1e9b53f9d33 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -1,5 +1,3 @@
-.text
-
 /*
  * This may not use any stack, nor any variable that is not "NoSave":
  *
@@ -12,17 +10,18 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
 
-        .text
+.text
 
 ENTRY(swsusp_arch_suspend)
-
         movl %esp, saved_context_esp
         movl %ebx, saved_context_ebx
         movl %ebp, saved_context_ebp
         movl %esi, saved_context_esi
         movl %edi, saved_context_edi
-        pushfl ; popl saved_context_eflags
+        pushfl
+        popl saved_context_eflags
 
         call swsusp_save
         ret
@@ -59,7 +58,7 @@ done:
         movl    mmu_cr4_features, %ecx
         jecxz   1f      # cr4 Pentium and higher, skip if zero
         movl    %ecx, %edx
-        andl    $~(1<<7), %edx;  # PGE
+        andl    $~(X86_CR4_PGE), %edx
         movl    %edx, %cr4;  # turn off PGE
 1:
         movl    %cr3, %eax;  # flush TLB
@@ -74,7 +73,8 @@ done:
         movl saved_context_esi, %esi
         movl saved_context_edi, %edi
 
-        pushl saved_context_eflags ; popfl
+        pushl saved_context_eflags
+        popfl
 
         xorl    %eax, %eax
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a4e201b47f64..7dcd321a0508 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -812,7 +812,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
-static __init void xen_alloc_pte_init(struct mm_struct *mm, u32 pfn)
+static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
 {
 #ifdef CONFIG_FLATMEM
         BUG_ON(mem_map);        /* should only be used early */
@@ -822,7 +822,7 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, u32 pfn)
 
 /* Early release_pte assumes that all pts are pinned, since there's
    only init_mm and anything attached to that is pinned. */
-static void xen_release_pte_init(u32 pfn)
+static void xen_release_pte_init(unsigned long pfn)
 {
         make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
@@ -838,7 +838,7 @@ static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
 
 /* This needs to make sure the new pte page is pinned iff its being
    attached to a pinned pagetable. */
-static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level)
+static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
 {
         struct page *page = pfn_to_page(pfn);
 
@@ -856,12 +856,12 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level)
         }
 }
 
-static void xen_alloc_pte(struct mm_struct *mm, u32 pfn)
+static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn)
 {
         xen_alloc_ptpage(mm, pfn, PT_PTE);
 }
 
-static void xen_alloc_pmd(struct mm_struct *mm, u32 pfn)
+static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
 {
         xen_alloc_ptpage(mm, pfn, PT_PMD);
 }
@@ -909,7 +909,7 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 }
 
 /* This should never happen until we're OK to use struct page */
-static void xen_release_ptpage(u32 pfn, unsigned level)
+static void xen_release_ptpage(unsigned long pfn, unsigned level)
 {
         struct page *page = pfn_to_page(pfn);
 
@@ -923,23 +923,23 @@ static void xen_release_ptpage(u32 pfn, unsigned level)
         }
 }
 
-static void xen_release_pte(u32 pfn)
+static void xen_release_pte(unsigned long pfn)
 {
         xen_release_ptpage(pfn, PT_PTE);
 }
 
-static void xen_release_pmd(u32 pfn)
+static void xen_release_pmd(unsigned long pfn)
 {
         xen_release_ptpage(pfn, PT_PMD);
 }
 
 #if PAGETABLE_LEVELS == 4
-static void xen_alloc_pud(struct mm_struct *mm, u32 pfn)
+static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
         xen_alloc_ptpage(mm, pfn, PT_PUD);
 }
 
-static void xen_release_pud(u32 pfn)
+static void xen_release_pud(unsigned long pfn)
 {
         xen_release_ptpage(pfn, PT_PUD);
 }
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 35d1743b57ac..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>
@@ -175,4 +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 f6aa18eadf71..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>
@@ -180,4 +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
index 30a12049353b..783f43e58052 100644
--- a/include/asm-x86/amd_iommu.h
+++ b/include/asm-x86/amd_iommu.h
@@ -17,8 +17,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _ASM_X86_AMD_IOMMU_H
-#define _ASM_X86_AMD_IOMMU_H
+#ifndef ASM_X86__AMD_IOMMU_H
+#define ASM_X86__AMD_IOMMU_H
 
 #ifdef CONFIG_AMD_IOMMU
 extern int amd_iommu_init(void);
@@ -29,4 +29,4 @@ static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
 #endif
 
-#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
index dcc812067394..1ffa4e53c989 100644
--- a/include/asm-x86/amd_iommu_types.h
+++ b/include/asm-x86/amd_iommu_types.h
@@ -17,8 +17,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef __AMD_IOMMU_TYPES_H__
-#define __AMD_IOMMU_TYPES_H__
+#ifndef ASM_X86__AMD_IOMMU_TYPES_H
+#define ASM_X86__AMD_IOMMU_TYPES_H
 
 #include <linux/types.h>
 #include <linux/list.h>
@@ -341,4 +341,4 @@ static inline u16 calc_devid(u8 bus, u8 devfn)
         return (((u16)bus) << 8) | devfn;
 }
 
-#endif
+#endif /* ASM_X86__AMD_IOMMU_TYPES_H */
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index 133c998161ca..65590c9aecd4 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -1,5 +1,5 @@
-#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>
@@ -54,6 +54,11 @@ extern int disable_apic;
 #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)
 {
@@ -76,9 +81,7 @@ extern int get_physical_broadcast(void);
 static inline void ack_APIC_irq(void)
 {
         /*
-         * ack_APIC_irq() actually gets compiled as a single instruction:
-         * - a single rmw on Pentium/82489DX
-         * - a single write on P6+ cores (CONFIG_X86_GOOD_APIC)
+         * ack_APIC_irq() actually gets compiled as a single instruction
          * ... yummie.
          */
 
@@ -128,4 +131,4 @@ 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..c40687da20fc 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.)
@@ -411,4 +411,4 @@ 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 8411750ceb63..72adc3a109cc 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>
 
@@ -25,4 +25,4 @@ 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 97220321f39d..e1355f44d7c3 100644
--- a/include/asm-x86/asm.h
+++ b/include/asm-x86/asm.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_ASM_H
-#define _ASM_X86_ASM_H
+#ifndef ASM_X86__ASM_H
+#define ASM_X86__ASM_H
 
 #ifdef __ASSEMBLY__
 # define __ASM_FORM(x)  x
@@ -20,17 +20,22 @@
 
 #define _ASM_PTR        __ASM_SEL(.long, .quad)
 #define _ASM_ALIGN      __ASM_SEL(.balign 4, .balign 8)
-#define _ASM_MOV_UL     __ASM_SIZE(mov)
 
+#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) \
@@ -39,4 +44,4 @@
         _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 91c7d03e65bc..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>
@@ -470,4 +470,4 @@ static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
 #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/bios_ebda.h b/include/asm-x86/bios_ebda.h
index 0033e50c13b2..ec42ed874591 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>
 
@@ -16,4 +16,4 @@ static inline unsigned int get_bios_ebda(void)
 
 void reserve_ebda_region(void);
 
-#endif /* _MACH_BIOS_EBDA_H */
+#endif /* ASM_X86__BIOS_EBDA_H */
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index cfb2b64f76e7..61989b93b475 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.
@@ -458,4 +458,4 @@ 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..825de5dc867c 100644
--- a/include/asm-x86/boot.h
+++ b/include/asm-x86/boot.h
@@ -1,5 +1,5 @@
-#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
@@ -25,4 +25,4 @@
 #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 ae22bdf0ab14..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>
@@ -108,4 +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..4761c461d23a 100644
--- a/include/asm-x86/bugs.h
+++ b/include/asm-x86/bugs.h
@@ -1,7 +1,7 @@
-#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);
 int ppro_with_ram_bug(void);
 
-#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..59859cb28a36 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>
@@ -112,4 +112,4 @@ 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/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 17463ccf8166..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 */
 
@@ -182,4 +182,4 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
         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 cfcfb0a806ba..250fa0cb144b 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -1,8 +1,8 @@
 /*
  * 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>
 
@@ -224,4 +224,4 @@ 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 7515c19d4988..a863ead856f3 100644
--- a/include/asm-x86/current.h
+++ b/include/asm-x86/current.h
@@ -1,5 +1,5 @@
-#ifndef _X86_CURRENT_H
-#define _X86_CURRENT_H
+#ifndef ASM_X86__CURRENT_H
+#define ASM_X86__CURRENT_H
 
 #ifdef CONFIG_X86_32
 #include <linux/compiler.h>
@@ -36,4 +36,4 @@ static __always_inline struct task_struct *get_current(void)
 
 #define current get_current()
 
-#endif /* X86_CURRENT_H */
+#endif /* ASM_X86__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 a44c4dc70590..b73fea54def2 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>
@@ -397,4 +397,4 @@ 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 f7bacf357dac..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
@@ -92,4 +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 3c034f48fdb0..1bece04c7d9d 100644
--- a/include/asm-x86/device.h
+++ b/include/asm-x86/device.h
@@ -1,5 +1,5 @@
-#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
@@ -13,4 +13,4 @@ struct dma_mapping_ops *dma_ops;
 #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 ad9cd6d49bfc..5d200e78bd81 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
@@ -250,4 +250,4 @@ static inline int dma_get_cache_alignment(void)
 #define dma_is_consistent(d, h) (1)
 
 #include <asm-generic/dma-coherent.h>
-#endif
+#endif /* ASM_X86__DMA_MAPPING_H */
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 58a86571fe0f..1cff6fe81fa5 100644
--- a/include/asm-x86/dmi.h
+++ b/include/asm-x86/dmi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_DMI_H
-#define _ASM_X86_DMI_H
+#ifndef ASM_X86__DMI_H
+#define ASM_X86__DMI_H
 
 #include <asm/io.h>
 
@@ -23,4 +23,4 @@ static inline void *dmi_alloc(unsigned len)
 #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 738bb9fb3e53..21d1bc32ad7c 100644
--- a/include/asm-x86/dwarf2.h
+++ b/include/asm-x86/dwarf2.h
@@ -1,5 +1,5 @@
-#ifndef _DWARF2_H
-#define _DWARF2_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"
@@ -58,4 +58,4 @@
 
 #endif
 
-#endif
+#endif /* ASM_X86__DWARF2_H */
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
index 16a31e2c7c57..f52daf176bcb 100644
--- a/include/asm-x86/e820.h
+++ b/include/asm-x86/e820.h
@@ -1,5 +1,5 @@
-#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 */
 
@@ -64,6 +64,7 @@ struct e820map {
 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);
@@ -140,4 +141,4 @@ extern char *memory_setup(void);
 #define HIGH_MEMORY     (1024*1024)
 #endif /* __KERNEL__ */
 
-#endif  /* __ASM_E820_H */
+#endif /* ASM_X86__E820_H */
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 d4f2b0abe929..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
 
@@ -94,4 +94,4 @@ 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 7be4733c793e..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..
@@ -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/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 44d4f8217349..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"
@@ -65,4 +65,4 @@ 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
+#endif /* ASM_X86__FIXMAP_H */
diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h
index f1ac2b2167d7..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.
@@ -120,4 +120,4 @@ extern void reserve_top_address(unsigned long reserve);
 #define FIXADDR_BOOT_START      (FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
 
 #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 00f3d74a0524..dafb24bc0424 100644
--- a/include/asm-x86/fixmap_64.h
+++ b/include/asm-x86/fixmap_64.h
@@ -8,8 +8,8 @@
  * 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>
@@ -80,4 +80,4 @@ enum fixed_addresses {
 #define FIXADDR_USER_START      ((unsigned long)VSYSCALL32_VSYSCALL)
 #define FIXADDR_USER_END        (FIXADDR_USER_START + PAGE_SIZE)
 
-#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
index 5c68b32ee1c8..be0e004ad148 100644
--- a/include/asm-x86/ftrace.h
+++ b/include/asm-x86/ftrace.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_FTRACE
-#define _ASM_X86_FTRACE
+#ifndef ASM_X86__FTRACE_H
+#define ASM_X86__FTRACE_H
 
 #ifdef CONFIG_FTRACE
 #define MCOUNT_ADDR             ((long)(mcount))
@@ -11,4 +11,4 @@ extern void mcount(void);
 
 #endif /* CONFIG_FTRACE */
 
-#endif /* _ASM_X86_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 3f62a83887f3..baa54faba892 100644
--- a/include/asm-x86/gart.h
+++ b/include/asm-x86/gart.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X8664_GART_H
-#define _ASM_X8664_GART_H 1
+#ifndef ASM_X86__GART_H
+#define ASM_X86__GART_H
 
 #include <asm/e820.h>
 
@@ -52,15 +52,15 @@ static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
                 return 0;
 
         if (aper_base + aper_size > 0x100000000ULL) {
-                printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n");
+                printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
                 return 0;
         }
         if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
-                printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
+                printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
                 return 0;
         }
         if (aper_size < min_size) {
-                printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n",
+                printk(KERN_INFO "Aperture too small (%d MB) than (%d MB)\n",
                                  aper_size>>20, min_size>>20);
                 return 0;
         }
@@ -68,4 +68,4 @@ static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
         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 754d635f90ff..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>
 
@@ -121,4 +121,4 @@ enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
 #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 a47d63129135..25097a8cc5ef 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.
@@ -47,4 +47,4 @@ extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
 
 extern void setup_apic_routing(void);
 
-#endif
+#endif /* ASM_X86__GENAPIC_64_H */
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
index 2c1cda0b8a86..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>
@@ -250,4 +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 c4c91b37c104..497fb980d962 100644
--- a/include/asm-x86/gpio.h
+++ b/include/asm-x86/gpio.h
@@ -53,4 +53,4 @@ static inline int irq_to_gpio(unsigned int irq)
 
 #endif /* CONFIG_GPIOLIB */
 
-#endif /* _ASM_I386_GPIO_H */
+#endif /* ASM_X86__GPIO_H */
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 4514b16cc723..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__
 
@@ -79,4 +79,4 @@ extern void add_highpages_with_active_regions(int nid, unsigned long start_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 82f1ac641bd7..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
 
@@ -90,4 +90,4 @@ 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 439a9acc132d..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>
 
@@ -90,4 +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 edd0b95f14d0..65997b15d56a 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
+#ifndef ASM_X86__HW_IRQ_H
+#define ASM_X86__HW_IRQ_H
 
 /*
  * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
@@ -93,6 +93,26 @@ 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
+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
@@ -112,4 +132,4 @@ static inline void __setup_vector_irq(int cpu) {}
 
 #endif /* !ASSEMBLY_ */
 
-#endif
+#endif /* ASM_X86__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 56d00e31aec0..1ecdc3ed96e4 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -7,8 +7,8 @@
  * 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>
@@ -25,6 +25,7 @@ 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;
@@ -336,4 +337,4 @@ 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 2f98df91f1f2..c586559a6957 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>
 
@@ -57,4 +57,4 @@ static inline void outb_pic(unsigned char value, unsigned int port)
 
 extern struct irq_chip i8259A_chip;
 
-#endif  /* __ASM_I8259_H__ */
+#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/idle.h b/include/asm-x86/idle.h
index cbb649123612..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
@@ -12,4 +12,4 @@ void exit_idle(void);
 
 void c1e_remove_cpu(int cpu);
 
-#endif
+#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 0f954dc89cb3..72b7719523bf 100644
--- a/include/asm-x86/io.h
+++ b/include/asm-x86/io.h
@@ -1,5 +1,5 @@
-#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
 
@@ -73,6 +73,8 @@ build_mmio_write(__writeq, "q", unsigned long, "r", )
 #define writeq writeq
 #endif
 
+extern int iommu_bio_merge;
+
 #ifdef CONFIG_X86_32
 # include "io_32.h"
 #else
@@ -99,4 +101,4 @@ extern void early_iounmap(void *addr, unsigned long size);
 extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 
 
-#endif /* _ASM_X86_IO_H */
+#endif /* ASM_X86__IO_H */
diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h
index e876d89ac156..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>
@@ -281,4 +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 22995c5c5adc..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
 
 
 /*
@@ -235,7 +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
 
 /*
@@ -245,4 +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 14f82bbcb5fd..be62847ab07e 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>
@@ -189,4 +189,4 @@ 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 5f888cc5be49..e86f44148c66 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X8664_IOMMU_H
-#define _ASM_X8664_IOMMU_H 1
+#ifndef ASM_X86__IOMMU_H
+#define ASM_X86__IOMMU_H
 
 extern void pci_iommu_shutdown(void);
 extern void no_iommu_init(void);
@@ -42,4 +42,4 @@ 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 bb1c09f7a76c..c1b226797518 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.
@@ -129,4 +129,4 @@ static inline void send_IPI_mask_sequence(cpumask_t mask, int vector)
         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 1a2925757317..1e5f2909c1db 100644
--- a/include/asm-x86/irq.h
+++ b/include/asm-x86/irq.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
+#ifndef ASM_X86__IRQ_H
+#define ASM_X86__IRQ_H
 /*
  *      (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
  *
@@ -47,4 +47,4 @@ extern void native_init_IRQ(void);
 /* Interrupt vector management */
 extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
 
-#endif /* _ASM_IRQ_H */
+#endif /* ASM_X86__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_vectors.h b/include/asm-x86/irq_vectors.h
index a48c7f2dbdc0..c5d2d767a1f3 100644
--- a/include/asm-x86/irq_vectors.h
+++ b/include/asm-x86/irq_vectors.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
+#ifndef ASM_X86__IRQ_VECTORS_H
+#define ASM_X86__IRQ_VECTORS_H
 
 #include <linux/threads.h>
 
@@ -179,4 +179,4 @@
 #define VIC_CPU_BOOT_ERRATA_CPI         (VIC_CPI_LEVEL0 + 8)
 
 
-#endif /* _ASM_IRQ_VECTORS_H */
+#endif /* ASM_X86__IRQ_VECTORS_H */
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 4246ab7dc988..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
@@ -172,4 +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 94d63db10365..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
@@ -76,4 +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 6f1840812e59..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
@@ -230,4 +230,4 @@ struct kvm_pit_state {
 #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 c2e34c275900..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
@@ -8,8 +8,8 @@
  *
  */
 
-#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>
@@ -735,4 +735,4 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 
-#endif
+#endif /* ASM_X86__KVM_HOST_H */
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
index 76f392146daa..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.
@@ -144,4 +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 4e8c1e48d91d..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;
 
@@ -181,4 +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_apic.h b/include/asm-x86/mach-bigsmp/mach_apic.h
index c3b9dc6970c9..05362d44a3ee 100644
--- a/include/asm-x86/mach-bigsmp/mach_apic.h
+++ b/include/asm-x86/mach-bigsmp/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_BIGSMP__MACH_APIC_H
+#define ASM_X86__MACH_BIGSMP__MACH_APIC_H
 
 #define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu))
 #define esr_disable (1)
@@ -141,4 +141,4 @@ static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
         return cpuid_apic >> index_msb;
 }
 
-#endif /* __ASM_MACH_APIC_H */
+#endif /* ASM_X86__MACH_BIGSMP__MACH_APIC_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_apicdef.h b/include/asm-x86/mach-bigsmp/mach_apicdef.h
index a58ab5a75c8c..811935d9d49b 100644
--- a/include/asm-x86/mach-bigsmp/mach_apicdef.h
+++ b/include/asm-x86/mach-bigsmp/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_BIGSMP__MACH_APICDEF_H
+#define ASM_X86__MACH_BIGSMP__MACH_APICDEF_H
 
 #define         APIC_ID_MASK            (0xFF<<24)
 
@@ -10,4 +10,4 @@ static inline unsigned get_apic_id(unsigned long x)
 
 #define         GET_APIC_ID(x)  get_apic_id(x)
 
-#endif
+#endif /* ASM_X86__MACH_BIGSMP__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-bigsmp/mach_ipi.h b/include/asm-x86/mach-bigsmp/mach_ipi.h
index 9404c535b7ec..b1b0f966a009 100644
--- a/include/asm-x86/mach-bigsmp/mach_ipi.h
+++ b/include/asm-x86/mach-bigsmp/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_BIGSMP__MACH_IPI_H
+#define ASM_X86__MACH_BIGSMP__MACH_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_X86__MACH_BIGSMP__MACH_IPI_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/mach_apic.h b/include/asm-x86/mach-default/mach_apic.h
index f3226b9a6b82..b615f40736be 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
 
@@ -138,4 +138,4 @@ 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..936704f816d6 100644
--- a/include/asm-x86/mach-default/mach_apicdef.h
+++ b/include/asm-x86/mach-default/mach_apicdef.h
@@ -1,5 +1,5 @@
-#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>
 
@@ -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-es7000/mach_apic.h b/include/asm-x86/mach-es7000/mach_apic.h
index 0a3fdf930672..c1f6f682d619 100644
--- a/include/asm-x86/mach-es7000/mach_apic.h
+++ b/include/asm-x86/mach-es7000/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_ES7000__MACH_APIC_H
+#define ASM_X86__MACH_ES7000__MACH_APIC_H
 
 #define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
 #define esr_disable (1)
@@ -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_X86__MACH_ES7000__MACH_APIC_H */
diff --git a/include/asm-x86/mach-es7000/mach_apicdef.h b/include/asm-x86/mach-es7000/mach_apicdef.h
index a58ab5a75c8c..a07e56744028 100644
--- a/include/asm-x86/mach-es7000/mach_apicdef.h
+++ b/include/asm-x86/mach-es7000/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_ES7000__MACH_APICDEF_H
+#define ASM_X86__MACH_ES7000__MACH_APICDEF_H
 
 #define         APIC_ID_MASK            (0xFF<<24)
 
@@ -10,4 +10,4 @@ static inline unsigned get_apic_id(unsigned long x)
 
 #define         GET_APIC_ID(x)  get_apic_id(x)
 
-#endif
+#endif /* ASM_X86__MACH_ES7000__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-es7000/mach_ipi.h b/include/asm-x86/mach-es7000/mach_ipi.h
index 5e61bd220b06..3a21240e03dc 100644
--- a/include/asm-x86/mach-es7000/mach_ipi.h
+++ b/include/asm-x86/mach-es7000/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_ES7000__MACH_IPI_H
+#define ASM_X86__MACH_ES7000__MACH_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_X86__MACH_ES7000__MACH_IPI_H */
diff --git a/include/asm-x86/mach-es7000/mach_mpparse.h b/include/asm-x86/mach-es7000/mach_mpparse.h
index ef26d3523625..befde24705b7 100644
--- a/include/asm-x86/mach-es7000/mach_mpparse.h
+++ b/include/asm-x86/mach-es7000/mach_mpparse.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef ASM_X86__MACH_ES7000__MACH_MPPARSE_H
+#define ASM_X86__MACH_ES7000__MACH_MPPARSE_H
 
 #include <linux/acpi.h>
 
@@ -26,4 +26,4 @@ static inline int es7000_check_dsdt(void)
 }
 #endif
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* ASM_X86__MACH_ES7000__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-es7000/mach_wakecpu.h b/include/asm-x86/mach-es7000/mach_wakecpu.h
index 84ff58314501..97c776ce13f2 100644
--- a/include/asm-x86/mach-es7000/mach_wakecpu.h
+++ b/include/asm-x86/mach-es7000/mach_wakecpu.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_WAKECPU_H
-#define __ASM_MACH_WAKECPU_H
+#ifndef ASM_X86__MACH_ES7000__MACH_WAKECPU_H
+#define ASM_X86__MACH_ES7000__MACH_WAKECPU_H
 
 /* 
  * This file copes with machines that wakeup secondary CPUs by the
@@ -56,4 +56,4 @@ 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_ES7000__MACH_WAKECPU_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 586cadbf3787..3115564e557c 100644
--- a/include/asm-x86/mach-generic/mach_mpparse.h
+++ b/include/asm-x86/mach-generic/mach_mpparse.h
@@ -1,5 +1,5 @@
-#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
 
 
 extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
@@ -7,4 +7,4 @@ extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
 
 extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
 
-#endif
+#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 c83c120be538..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
 
@@ -9,4 +9,4 @@
 
 extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
                                 char *productid);
-#endif /* __ASM_MACH_MPSPEC_H */
+#endif /* ASM_X86__MACH_GENERIC__MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-numaq/mach_apic.h b/include/asm-x86/mach-numaq/mach_apic.h
index d802465e026a..7a0d39edfcfa 100644
--- a/include/asm-x86/mach-numaq/mach_apic.h
+++ b/include/asm-x86/mach-numaq/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_APIC_H
+#define ASM_X86__MACH_NUMAQ__MACH_APIC_H
 
 #include <asm/io.h>
 #include <linux/mmzone.h>
@@ -135,4 +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_X86__MACH_NUMAQ__MACH_APIC_H */
diff --git a/include/asm-x86/mach-numaq/mach_apicdef.h b/include/asm-x86/mach-numaq/mach_apicdef.h
index bf439d0690f5..f870ec5f7782 100644
--- a/include/asm-x86/mach-numaq/mach_apicdef.h
+++ b/include/asm-x86/mach-numaq/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_APICDEF_H
+#define ASM_X86__MACH_NUMAQ__MACH_APICDEF_H
 
 
 #define APIC_ID_MASK (0xF<<24)
@@ -11,4 +11,4 @@ static inline unsigned get_apic_id(unsigned long x)
 
 #define         GET_APIC_ID(x)  get_apic_id(x)
 
-#endif
+#endif /* ASM_X86__MACH_NUMAQ__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-numaq/mach_ipi.h b/include/asm-x86/mach-numaq/mach_ipi.h
index c6044488e9e6..1e835823f4bc 100644
--- a/include/asm-x86/mach-numaq/mach_ipi.h
+++ b/include/asm-x86/mach-numaq/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_IPI_H
+#define ASM_X86__MACH_NUMAQ__MACH_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_X86__MACH_NUMAQ__MACH_IPI_H */
diff --git a/include/asm-x86/mach-numaq/mach_mpparse.h b/include/asm-x86/mach-numaq/mach_mpparse.h
index 626aef6b155f..74ade184920b 100644
--- a/include/asm-x86/mach-numaq/mach_mpparse.h
+++ b/include/asm-x86/mach-numaq/mach_mpparse.h
@@ -1,7 +1,7 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_MPPARSE_H
+#define ASM_X86__MACH_NUMAQ__MACH_MPPARSE_H
 
 extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
                                 char *productid);
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* ASM_X86__MACH_NUMAQ__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-numaq/mach_wakecpu.h b/include/asm-x86/mach-numaq/mach_wakecpu.h
index 00530041a991..0db8cea643c0 100644
--- a/include/asm-x86/mach-numaq/mach_wakecpu.h
+++ b/include/asm-x86/mach-numaq/mach_wakecpu.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_WAKECPU_H
-#define __ASM_MACH_WAKECPU_H
+#ifndef ASM_X86__MACH_NUMAQ__MACH_WAKECPU_H
+#define ASM_X86__MACH_NUMAQ__MACH_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_X86__MACH_NUMAQ__MACH_WAKECPU_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/irq_vectors_limits.h b/include/asm-x86/mach-summit/irq_vectors_limits.h
index 890ce3f5e09a..22f376ad68e1 100644
--- a/include/asm-x86/mach-summit/irq_vectors_limits.h
+++ b/include/asm-x86/mach-summit/irq_vectors_limits.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
+#ifndef ASM_X86__MACH_SUMMIT__IRQ_VECTORS_LIMITS_H
+#define ASM_X86__MACH_SUMMIT__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_SUMMIT__IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/mach-summit/mach_apic.h b/include/asm-x86/mach-summit/mach_apic.h
index c47e2ab5c5ca..7a66758d701d 100644
--- a/include/asm-x86/mach-summit/mach_apic.h
+++ b/include/asm-x86/mach-summit/mach_apic.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
+#ifndef ASM_X86__MACH_SUMMIT__MACH_APIC_H
+#define ASM_X86__MACH_SUMMIT__MACH_APIC_H
 
 #include <asm/smp.h>
 
@@ -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_X86__MACH_SUMMIT__MACH_APIC_H */
diff --git a/include/asm-x86/mach-summit/mach_apicdef.h b/include/asm-x86/mach-summit/mach_apicdef.h
index a58ab5a75c8c..d4bc8590c4f6 100644
--- a/include/asm-x86/mach-summit/mach_apicdef.h
+++ b/include/asm-x86/mach-summit/mach_apicdef.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
+#ifndef ASM_X86__MACH_SUMMIT__MACH_APICDEF_H
+#define ASM_X86__MACH_SUMMIT__MACH_APICDEF_H
 
 #define         APIC_ID_MASK            (0xFF<<24)
 
@@ -10,4 +10,4 @@ static inline unsigned get_apic_id(unsigned long x)
 
 #define         GET_APIC_ID(x)  get_apic_id(x)
 
-#endif
+#endif /* ASM_X86__MACH_SUMMIT__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-summit/mach_ipi.h b/include/asm-x86/mach-summit/mach_ipi.h
index 9404c535b7ec..a3b31c528d90 100644
--- a/include/asm-x86/mach-summit/mach_ipi.h
+++ b/include/asm-x86/mach-summit/mach_ipi.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
+#ifndef ASM_X86__MACH_SUMMIT__MACH_IPI_H
+#define ASM_X86__MACH_SUMMIT__MACH_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_X86__MACH_SUMMIT__MACH_IPI_H */
diff --git a/include/asm-x86/mach-summit/mach_mpparse.h b/include/asm-x86/mach-summit/mach_mpparse.h
index fdf591701339..92396f28772b 100644
--- a/include/asm-x86/mach-summit/mach_mpparse.h
+++ b/include/asm-x86/mach-summit/mach_mpparse.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MACH_MPPARSE_H
-#define __ASM_MACH_MPPARSE_H
+#ifndef ASM_X86__MACH_SUMMIT__MACH_MPPARSE_H
+#define ASM_X86__MACH_SUMMIT__MACH_MPPARSE_H
 
 #include <mach_apic.h>
 #include <asm/tsc.h>
@@ -107,4 +107,4 @@ static inline int is_WPEG(struct rio_detail *rio){
                 rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
 }
 
-#endif /* __ASM_MACH_MPPARSE_H */
+#endif /* ASM_X86__MACH_SUMMIT__MACH_MPPARSE_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 531eaa587455..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__
 
@@ -127,4 +127,4 @@ extern void restart_mce(void);
 
 #endif /* __KERNEL__ */
 
-#endif
+#endif /* ASM_X86__MCE_H */
diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h
index 90bc4108a4fd..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>
 
@@ -17,4 +17,4 @@
 #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
index e293ab81e850..fb79b1cf5d07 100644
--- a/include/asm-x86/mmconfig.h
+++ b/include/asm-x86/mmconfig.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_MMCONFIG_H
-#define _ASM_MMCONFIG_H
+#ifndef ASM_X86__MMCONFIG_H
+#define ASM_X86__MMCONFIG_H
 
 #ifdef CONFIG_PCI_MMCONFIG
 extern void __cpuinit fam10h_check_enable_mmcfg(void);
@@ -9,4 +9,4 @@ static inline void fam10h_check_enable_mmcfg(void) { }
 static inline void check_enable_amd_mmconf_dmi(void) { }
 #endif
 
-#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 fac57014e7c6..8ec940bfd079 100644
--- a/include/asm-x86/mmu_context.h
+++ b/include/asm-x86/mmu_context.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_X86_MMU_CONTEXT_H
-#define __ASM_X86_MMU_CONTEXT_H
+#ifndef ASM_X86__MMU_CONTEXT_H
+#define ASM_X86__MMU_CONTEXT_H
 
 #include <asm/desc.h>
 #include <asm/atomic.h>
@@ -34,4 +34,4 @@ do {						\
 } while (0);
 
 
-#endif /* __ASM_X86_MMU_CONTEXT_H */
+#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 824fc575c6d8..cce6f6e4afd6 100644
--- a/include/asm-x86/mmu_context_32.h
+++ b/include/asm-x86/mmu_context_32.h
@@ -1,5 +1,5 @@
-#ifndef __I386_SCHED_H
-#define __I386_SCHED_H
+#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)
 {
@@ -53,4 +53,4 @@ static inline void switch_mm(struct mm_struct *prev,
 #define deactivate_mm(tsk, mm)                  \
         asm("movl %0,%%gs": :"r" (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 c7000634ccae..26758673c828 100644
--- a/include/asm-x86/mmu_context_64.h
+++ b/include/asm-x86/mmu_context_64.h
@@ -1,5 +1,5 @@
-#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/pda.h>
 
@@ -51,4 +51,4 @@ do {						\
         asm volatile("movl %0,%%fs"::"r"(0));   \
 } while (0)
 
-#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 5862e6460658..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>
 
@@ -131,4 +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 594bd0dc1d08..626b03a14875 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
@@ -49,4 +49,4 @@ 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 b6995e567fcc..118da365e371 100644
--- a/include/asm-x86/mpspec.h
+++ b/include/asm-x86/mpspec.h
@@ -1,5 +1,5 @@
-#ifndef _AM_X86_MPSPEC_H
-#define _AM_X86_MPSPEC_H
+#ifndef ASM_X86__MPSPEC_H
+#define ASM_X86__MPSPEC_H
 
 #include <linux/init.h>
 
@@ -141,4 +141,4 @@ static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
 
 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 38d1e73b49e4..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
@@ -177,4 +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..3139666a94fa 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 +48,4 @@
 #define  MSI_ADDR_DEST_ID(dest)         (((dest) << MSI_ADDR_DEST_ID_SHIFT) & \
                                          MSI_ADDR_DEST_ID_MASK)
 
-#endif /* ASM_MSIDEF_H */
+#endif /* ASM_X86__MSIDEF_H */
diff --git a/include/asm-x86/msr-index.h b/include/asm-x86/msr-index.h
index 44bce773012e..3052f058ab06 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 */
 
@@ -310,4 +310,4 @@
 /* Geode defined MSRs */
 #define MSR_GEODE_BUSCONT_CONF0         0x00001900
 
-#endif /* __ASM_MSR_INDEX_H */
+#endif /* ASM_X86__MSR_INDEX_H */
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
index 2362cfda1fbc..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>
 
@@ -63,6 +63,22 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
         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"
+                     "3:  mov %3,%0 ; jmp 1b\n\t"
+                     ".previous\n\t"
+                     _ASM_EXTABLE(2b, 3b)
+                     : "=r" (*err), EAX_EDX_RET(val, low, high)
+                     : "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)
 {
@@ -158,6 +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())
@@ -221,4 +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/nmi.h b/include/asm-x86/nmi.h
index 21f8d0202a82..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>
@@ -34,6 +34,7 @@ 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;
@@ -81,4 +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 220d7b7707a0..44cb07855c5b 100644
--- a/include/asm-x86/numa_32.h
+++ b/include/asm-x86/numa_32.h
@@ -1,5 +1,5 @@
-#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);
@@ -8,4 +8,4 @@ extern void numa_remove_cpu(int cpu);
 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 3830094434a9..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>
@@ -40,4 +40,4 @@ 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 34b92d581fa3..124bf7d4b70a 100644
--- a/include/asm-x86/numaq.h
+++ b/include/asm-x86/numaq.h
@@ -23,8 +23,8 @@
  * 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
 
@@ -165,5 +165,5 @@ static inline int get_memcfg_numaq(void)
         return 0;
 }
 #endif /* CONFIG_X86_NUMAQ */
-#endif /* NUMAQ_H */
+#endif /* ASM_X86__NUMAQ_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 49982110e4d9..79544e6ffb8b 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>
 
@@ -199,4 +199,4 @@ static inline pteval_t native_pte_flags(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 ab8528793f08..72f7305682c6 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.
@@ -89,13 +89,11 @@ 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);
 
 
@@ -126,4 +124,4 @@ 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 c6916c83e6b1..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
 
@@ -91,6 +91,7 @@ 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);
@@ -102,4 +103,4 @@ extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
 #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 fbbde93f12d6..891971f57d35 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. */
 
@@ -137,6 +137,7 @@ 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);
 
@@ -257,13 +258,13 @@ struct pv_mmu_ops {
          * Hooks for allocating/releasing pagetable pages when they're
          * attached to a pagetable
          */
-        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);
+        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);
@@ -726,6 +727,10 @@ 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);
@@ -771,6 +776,13 @@ 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)
 {
@@ -993,35 +1005,35 @@ 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 pfn)
+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);
 }
@@ -1634,4 +1646,4 @@ static inline unsigned long __raw_local_irq_save(void)
 
 #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 7edc47307217..482c3e3f9879 100644
--- a/include/asm-x86/pat.h
+++ b/include/asm-x86/pat.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_PAT_H
-#define _ASM_PAT_H
+#ifndef ASM_X86__PAT_H
+#define ASM_X86__PAT_H
 
 #include <linux/types.h>
 
@@ -19,4 +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 80c775d9fe20..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>
 
@@ -18,4 +18,4 @@ extern int early_pci_allowed(void);
 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
+#endif /* ASM_X86__PCI_DIRECT_H */
diff --git a/include/asm-x86/pci.h b/include/asm-x86/pci.h
index 2db14cf17db8..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>
@@ -111,4 +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 a50d46851285..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__
@@ -31,4 +31,4 @@ struct pci_dev;
 #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 b34e9a7cc80b..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>
@@ -134,4 +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 f643a3a92da0..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>
@@ -215,4 +215,4 @@ do {							\
 
 #endif  /* !CONFIG_SMP */
 
-#endif /* _ASM_X86_PERCPU_H_ */
+#endif /* ASM_X86__PERCPU_H */
diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h
index d63ea431cb3b..3cd23adedae8 100644
--- a/include/asm-x86/pgalloc.h
+++ b/include/asm-x86/pgalloc.h
@@ -1,5 +1,5 @@
-#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 */
@@ -111,4 +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 105057f34032..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
@@ -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_PFN_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 04caa2f544df..888add7b0882 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
 
@@ -186,6 +186,13 @@ static inline int pte_special(pte_t pte)
         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)) ==
@@ -313,6 +320,8 @@ 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 */
@@ -521,4 +530,4 @@ 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 5c3b26567a95..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
@@ -186,4 +188,4 @@ do {						\
 #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 549144d03d99..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__
@@ -175,8 +175,6 @@ static inline int pmd_bad(pmd_t pmd)
 #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".
@@ -284,4 +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-flags.h b/include/asm-x86/processor-flags.h
index eff2ecd7fff0..5dd79774f693 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. */
 
 /*
@@ -96,4 +96,4 @@
 #endif
 #endif
 
-#endif  /* __ASM_I386_PROCESSOR_FLAGS_H */
+#endif /* ASM_X86__PROCESSOR_FLAGS_H */
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 4df3e2f6fb56..5eaf9bf0a623 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>
@@ -140,6 +141,8 @@ DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info);
 #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
@@ -153,6 +156,8 @@ static inline int hlt_works(int cpu)
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
 
+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 *);
@@ -411,9 +416,14 @@ 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)
@@ -943,4 +953,4 @@ 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 3dd458c385c0..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>
 
@@ -29,4 +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 72e7b9db29bb..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__
 
@@ -80,8 +80,9 @@
 
 #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 8a71db803da6..d64a61097165 100644
--- a/include/asm-x86/ptrace.h
+++ b/include/asm-x86/ptrace.h
@@ -1,5 +1,5 @@
-#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>
@@ -127,14 +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);
 
@@ -148,6 +182,9 @@ extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 #endif
 
+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;
@@ -213,6 +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.
  */
@@ -239,4 +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
index 6857f840b243..edb3b4ecfc81 100644
--- a/include/asm-x86/pvclock-abi.h
+++ b/include/asm-x86/pvclock-abi.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PVCLOCK_ABI_H_
-#define _ASM_X86_PVCLOCK_ABI_H_
+#ifndef ASM_X86__PVCLOCK_ABI_H
+#define ASM_X86__PVCLOCK_ABI_H
 #ifndef __ASSEMBLY__
 
 /*
@@ -39,4 +39,4 @@ struct pvclock_wall_clock {
 } __attribute__((__packed__));
 
 #endif /* __ASSEMBLY__ */
-#endif /* _ASM_X86_PVCLOCK_ABI_H_ */
+#endif /* ASM_X86__PVCLOCK_ABI_H */
diff --git a/include/asm-x86/pvclock.h b/include/asm-x86/pvclock.h
index 85b1bba8e0a3..1a38f6834800 100644
--- a/include/asm-x86/pvclock.h
+++ b/include/asm-x86/pvclock.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_PVCLOCK_H_
-#define _ASM_X86_PVCLOCK_H_
+#ifndef ASM_X86__PVCLOCK_H
+#define ASM_X86__PVCLOCK_H
 
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
@@ -10,4 +10,4 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
                             struct pvclock_vcpu_time_info *vcpu,
                             struct timespec *ts);
 
-#endif /* _ASM_X86_PVCLOCK_H_ */
+#endif /* ASM_X86__PVCLOCK_H */
diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h
index 206f355786dc..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;
 
@@ -18,4 +18,4 @@ 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 5c2ff4bc2980..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
@@ -79,4 +79,4 @@
 #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 8d9f0b41ee86..e39376d7de50 100644
--- a/include/asm-x86/resume-trace.h
+++ b/include/asm-x86/resume-trace.h
@@ -1,5 +1,5 @@
-#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>
 
@@ -7,7 +7,7 @@
 do {                                                            \
         if (pm_trace_enabled) {                                 \
                 const void *tracedata;                          \
-                asm volatile(_ASM_MOV_UL " $1f,%0\n"            \
+                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 36e71c5f306f..cf9ab2dbcef1 100644
--- a/include/asm-x86/seccomp_32.h
+++ b/include/asm-x86/seccomp_32.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SECCOMP_H
-#define _ASM_SECCOMP_H
+#ifndef ASM_X86__SECCOMP_32_H
+#define ASM_X86__SECCOMP_32_H
 
 #include <linux/thread_info.h>
 
@@ -14,4 +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 76cfe69aa63c..03274cea751f 100644
--- a/include/asm-x86/seccomp_64.h
+++ b/include/asm-x86/seccomp_64.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SECCOMP_H
-#define _ASM_SECCOMP_H
+#ifndef ASM_X86__SECCOMP_64_H
+#define ASM_X86__SECCOMP_64_H
 
 #include <linux/thread_info.h>
 
@@ -22,4 +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 646452ea9ea3..ea5f0a8686f7 100644
--- a/include/asm-x86/segment.h
+++ b/include/asm-x86/segment.h
@@ -1,5 +1,5 @@
-#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 */
@@ -212,4 +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/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 a07c6f1c01e1..9030cb73c4d7 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
 
@@ -41,6 +41,7 @@ struct x86_quirks {
 };
 
 extern struct x86_quirks *x86_quirks;
+extern unsigned long saved_video_mode;
 
 #ifndef CONFIG_PARAVIRT
 #define paravirt_post_allocator_init()  do {} while (0)
@@ -100,4 +101,4 @@ void __init x86_64_start_reservations(char *real_mode_data);
 #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..24879c85b291 100644
--- a/include/asm-x86/sigcontext.h
+++ b/include/asm-x86/sigcontext.h
@@ -1,5 +1,5 @@
-#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>
@@ -202,4 +202,4 @@ struct sigcontext {
 
 #endif /* !__i386__ */
 
-#endif
+#endif /* ASM_X86__SIGCONTEXT_H */
diff --git a/include/asm-x86/sigcontext32.h b/include/asm-x86/sigcontext32.h
index 57a9686fb491..4e2ec732dd01 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. */
 
@@ -68,4 +68,4 @@ 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 6dac49364e95..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.  */
 
@@ -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 3c877f74f279..04f84f4e2c8b 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>
@@ -34,6 +34,9 @@ extern cpumask_t cpu_initialized;
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
+#ifdef CONFIG_X86_32
+DECLARE_PER_CPU(int, cpu_number);
+#endif
 
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
@@ -142,7 +145,6 @@ 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);
 
@@ -205,4 +207,4 @@ extern void cpu_uninit(void);
 #endif
 
 #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 e39c790dbfd2..93adae338ac6 100644
--- a/include/asm-x86/spinlock.h
+++ b/include/asm-x86/spinlock.h
@@ -1,5 +1,5 @@
-#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>
@@ -97,7 +97,7 @@ static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
                      "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"
@@ -135,7 +135,7 @@ 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"
@@ -162,7 +162,7 @@ static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
                      "cmpl %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"
@@ -366,4 +366,4 @@ 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 06c071c9eee9..6aa9b562c508 100644
--- a/include/asm-x86/spinlock_types.h
+++ b/include/asm-x86/spinlock_types.h
@@ -1,5 +1,5 @@
-#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"
@@ -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 774c919dc232..5363e4f7e1cd 100644
--- a/include/asm-x86/srat.h
+++ b/include/asm-x86/srat.h
@@ -24,8 +24,8 @@
  * Send feedback to Pat Gaughen <gone@us.ibm.com>
  */
 
-#ifndef _ASM_SRAT_H_
-#define _ASM_SRAT_H_
+#ifndef ASM_X86__SRAT_H
+#define ASM_X86__SRAT_H
 
 #ifdef CONFIG_ACPI_NUMA
 extern int get_memcfg_from_srat(void);
@@ -36,4 +36,4 @@ static inline int get_memcfg_from_srat(void)
 }
 #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 193578cd1fd9..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__
 
@@ -323,4 +323,4 @@ 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/suspend_32.h b/include/asm-x86/suspend_32.h
index 8675c6782a7d..acb6d4d491f4 100644
--- a/include/asm-x86/suspend_32.h
+++ b/include/asm-x86/suspend_32.h
@@ -3,8 +3,8 @@
  * Based on code
  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
  */
-#ifndef __ASM_X86_32_SUSPEND_H
-#define __ASM_X86_32_SUSPEND_H
+#ifndef ASM_X86__SUSPEND_32_H
+#define ASM_X86__SUSPEND_32_H
 
 #include <asm/desc.h>
 #include <asm/i387.h>
@@ -48,4 +48,4 @@ static inline void acpi_save_register_state(unsigned long return_point)
 extern int acpi_save_state_mem(void);
 #endif
 
-#endif /* __ASM_X86_32_SUSPEND_H */
+#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 2730b351afcf..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>
 
@@ -55,4 +55,4 @@ static inline 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 983ce37c491f..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>
@@ -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 da0a675adf94..4db0066a3a35 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -4,8 +4,8 @@
  * - Incorporating suggestions made by Linus Torvalds and Dave Miller
  */
 
-#ifndef _ASM_X86_THREAD_INFO_H
-#define _ASM_X86_THREAD_INFO_H
+#ifndef ASM_X86__THREAD_INFO_H
+#define ASM_X86__THREAD_INFO_H
 
 #include <linux/compiler.h>
 #include <asm/page.h>
@@ -71,6 +71,7 @@ struct thread_info {
  * 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*/
@@ -93,6 +94,7 @@ struct thread_info {
 #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)
@@ -133,7 +135,7 @@ struct thread_info {
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK                                             \
-        (_TIF_SIGPENDING|_TIF_MCE_NOTIFY)
+        (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW                                                 \
@@ -258,4 +260,4 @@ 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/time.h b/include/asm-x86/time.h
index a17fa473e91d..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 */
@@ -58,4 +60,4 @@ static inline int native_set_wallclock(unsigned long nowtime)
 
 extern unsigned long __init calibrate_cpu(void);
 
-#endif
+#endif /* ASM_X86__TIME_H */
diff --git a/include/asm-x86/timer.h b/include/asm-x86/timer.h
index fb2a4ddddf3d..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>
@@ -9,9 +9,12 @@
 unsigned long long native_sched_clock(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 calibrate_tsc() native_calibrate_tsc()
@@ -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..ef68b76dc3c5 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>
@@ -165,4 +165,4 @@ 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 90ac7718469a..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
@@ -255,4 +255,4 @@ static inline void set_mp_bus_to_node(int busnum, int node)
 }
 #endif
 
-#endif /* _ASM_X86_TOPOLOGY_H */
+#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
index a4b65a71bd66..2ccebc6fb0b0 100644
--- a/include/asm-x86/traps.h
+++ b/include/asm-x86/traps.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_TRAPS_H
-#define _ASM_X86_TRAPS_H
+#ifndef ASM_X86__TRAPS_H
+#define ASM_X86__TRAPS_H
 
 /* Common in X86_32 and X86_64 */
 asmlinkage void divide_error(void);
@@ -51,6 +51,8 @@ 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);
@@ -62,5 +64,7 @@ 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 */
+#endif /* ASM_X86__TRAPS_H */
diff --git a/include/asm-x86/tsc.h b/include/asm-x86/tsc.h
index cb6f6ee45b8f..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>
 
@@ -59,4 +59,4 @@ extern void check_tsc_sync_target(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 5f702d1d5218..48ebc0ad40ec 100644
--- a/include/asm-x86/uaccess.h
+++ b/include/asm-x86/uaccess.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_UACCES_H_
-#define _ASM_UACCES_H_
+#ifndef ASM_X86__UACCESS_H
+#define ASM_X86__UACCESS_H
 /*
  * User space memory access functions
  */
@@ -450,5 +450,5 @@ extern struct movsl_mask {
 # include "uaccess_64.h"
 #endif
 
-#endif
+#endif /* ASM_X86__UACCESS_H */
 
diff --git a/include/asm-x86/uaccess_32.h b/include/asm-x86/uaccess_32.h
index 6fdef39a0bcb..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
@@ -215,4 +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 45806d60bcbe..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
@@ -199,4 +199,4 @@ static inline int __copy_from_user_inatomic_nocache(void *dst,
 unsigned long
 copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest);
 
-#endif /* __X86_64_UACCESS_H */
+#endif /* ASM_X86__UACCESS_64_H */
diff --git a/include/asm-x86/ucontext.h b/include/asm-x86/ucontext.h
index 50a79f7fcde9..9948dd328084 100644
--- a/include/asm-x86/ucontext.h
+++ b/include/asm-x86/ucontext.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_UCONTEXT_H
-#define _ASM_X86_UCONTEXT_H
+#ifndef ASM_X86__UCONTEXT_H
+#define ASM_X86__UCONTEXT_H
 
 struct ucontext {
         unsigned long     uc_flags;
@@ -9,4 +9,4 @@ 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 d7394673b772..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.
@@ -376,4 +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 3a341d791792..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)
@@ -690,4 +690,4 @@ __SYSCALL(__NR_inotify_init1, sys_inotify_init1)
 #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
index aa73362ff5df..7cd6d7ec1308 100644
--- a/include/asm-x86/uv/bios.h
+++ b/include/asm-x86/uv/bios.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_BIOS_H
-#define _ASM_X86_BIOS_H
+#ifndef ASM_X86__UV__BIOS_H
+#define ASM_X86__UV__BIOS_H
 
 /*
  * BIOS layer definitions.
@@ -65,4 +65,4 @@ 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_BIOS_H */
+#endif /* ASM_X86__UV__BIOS_H */
diff --git a/include/asm-x86/uv/uv_bau.h b/include/asm-x86/uv/uv_bau.h
index 610b6b308e93..77153fb18f5e 100644
--- a/include/asm-x86/uv/uv_bau.h
+++ b/include/asm-x86/uv/uv_bau.h
@@ -8,8 +8,8 @@
  * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
  */
 
-#ifndef __ASM_X86_UV_BAU__
-#define __ASM_X86_UV_BAU__
+#ifndef ASM_X86__UV__UV_BAU_H
+#define ASM_X86__UV__UV_BAU_H
 
 #include <linux/bitmap.h>
 #define BITSPERBYTE 8
@@ -329,4 +329,4 @@ 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_BAU__ */
+#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 a4ef26e5850b..bdb5b01afbf5 100644
--- a/include/asm-x86/uv/uv_hub.h
+++ b/include/asm-x86/uv/uv_hub.h
@@ -8,8 +8,8 @@
  * 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>
@@ -350,5 +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 151fd7fcb809..8b03d89d2459 100644
--- a/include/asm-x86/uv/uv_mmrs.h
+++ b/include/asm-x86/uv/uv_mmrs.h
@@ -8,8 +8,8 @@
  * 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
 
 #define UV_MMR_ENABLE           (1UL << 63)
 
@@ -1292,4 +1292,4 @@ union uvh_si_alias2_overlay_config_u {
 };
 
 
-#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 8e18fb80f5e6..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[];
@@ -44,4 +44,4 @@ 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 */
+#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/visws/cobalt.h b/include/asm-x86/visws/cobalt.h
index 995258831b7f..9627a8fe84e9 100644
--- a/include/asm-x86/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/visws/lithium.h b/include/asm-x86/visws/lithium.h
index dfcd4f07ab85..b36d3b378c63 100644
--- a/include/asm-x86/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/visws/piix4.h b/include/asm-x86/visws/piix4.h
index 83ea4f46e419..61c938045ec9 100644
--- a/include/asm-x86/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/vm86.h b/include/asm-x86/vm86.h
index 5ce351325e01..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
@@ -205,4 +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 c3118c385156..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
@@ -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 6b66ff905af0..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,
@@ -41,4 +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/xen/events.h b/include/asm-x86/xen/events.h
index 8ded74720024..8151f5b8b6cb 100644
--- a/include/asm-x86/xen/events.h
+++ b/include/asm-x86/xen/events.h
@@ -1,5 +1,5 @@
-#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,
@@ -21,4 +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 91cb7fd5c123..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>
@@ -524,4 +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 04ee0610014a..0ef3a88b869d 100644
--- a/include/asm-x86/xen/hypervisor.h
+++ b/include/asm-x86/xen/hypervisor.h
@@ -30,8 +30,8 @@
  * 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>
@@ -69,4 +69,4 @@ u64 jiffies_to_st(unsigned long jiffies);
 
 #define is_running_on_xen()     (xen_start_info ? 1 : 0)
 
-#endif /* __HYPERVISOR_H__ */
+#endif /* ASM_X86__XEN__HYPERVISOR_H */
diff --git a/include/asm-x86/xen/interface.h b/include/asm-x86/xen/interface.h
index 9d810f2538a2..d077bba96da9 100644
--- a/include/asm-x86/xen/interface.h
+++ b/include/asm-x86/xen/interface.h
@@ -6,8 +6,8 @@
  * Copyright (c) 2004, K A Fraser
  */
 
-#ifndef __ASM_X86_XEN_INTERFACE_H
-#define __ASM_X86_XEN_INTERFACE_H
+#ifndef ASM_X86__XEN__INTERFACE_H
+#define ASM_X86__XEN__INTERFACE_H
 
 #ifdef __XEN__
 #define __DEFINE_GUEST_HANDLE(name, type) \
@@ -172,4 +172,4 @@ DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
 #define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
 #endif
 
-#endif  /* __ASM_X86_XEN_INTERFACE_H */
+#endif /* ASM_X86__XEN__INTERFACE_H */
diff --git a/include/asm-x86/xen/interface_32.h b/include/asm-x86/xen/interface_32.h
index d8ac41d5db86..08167e19fc66 100644
--- a/include/asm-x86/xen/interface_32.h
+++ b/include/asm-x86/xen/interface_32.h
@@ -6,8 +6,8 @@
  * Copyright (c) 2004, K A Fraser
  */
 
-#ifndef __ASM_X86_XEN_INTERFACE_32_H
-#define __ASM_X86_XEN_INTERFACE_32_H
+#ifndef ASM_X86__XEN__INTERFACE_32_H
+#define ASM_X86__XEN__INTERFACE_32_H
 
 
 /*
@@ -94,4 +94,4 @@ typedef struct xen_callback xen_callback_t;
 #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 */
+#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
index 842266ce96e6..046c0f1e01d4 100644
--- a/include/asm-x86/xen/interface_64.h
+++ b/include/asm-x86/xen/interface_64.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_X86_XEN_INTERFACE_64_H
-#define __ASM_X86_XEN_INTERFACE_64_H
+#ifndef ASM_X86__XEN__INTERFACE_64_H
+#define ASM_X86__XEN__INTERFACE_64_H
 
 /*
  * 64-bit segment selectors
@@ -156,4 +156,4 @@ typedef unsigned long xen_callback_t;
 #endif /* !__ASSEMBLY__ */
 
 
-#endif  /* __ASM_X86_XEN_INTERFACE_64_H */
+#endif /* ASM_X86__XEN__INTERFACE_64_H */
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
index 7b3835d3b77d..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>
 
@@ -162,4 +162,4 @@ 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 */