Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6

* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (231 commits)
  [PATCH] i386: Don't delete cpu_devs data to identify different x86 types in late_initcall
  [PATCH] i386: type may be unused
  [PATCH] i386: Some additional chipset register values validation.
  [PATCH] i386: Add missing !X86_PAE dependincy to the 2G/2G split.
  [PATCH] x86-64: Don't exclude asm-offsets.c in Documentation/dontdiff
  [PATCH] i386: avoid redundant preempt_disable in __unlazy_fpu
  [PATCH] i386: white space fixes in i387.h
  [PATCH] i386: Drop noisy e820 debugging printks
  [PATCH] x86-64: Fix allnoconfig error in genapic_flat.c
  [PATCH] x86-64: Shut up warnings for vfat compat ioctls on other file systems
  [PATCH] x86-64: Share identical video.S between i386 and x86-64
  [PATCH] x86-64: Remove CONFIG_REORDER
  [PATCH] x86-64: Print type and size correctly for unknown compat ioctls
  [PATCH] i386: Remove copy_*_user BUG_ONs for (size < 0)
  [PATCH] i386: Little cleanups in smpboot.c
  [PATCH] x86-64: Don't enable NUMA for a single node in K8 NUMA scanning
  [PATCH] x86: Use RDTSCP for synchronous get_cycles if possible
  [PATCH] i386: Add X86_FEATURE_RDTSCP
  [PATCH] i386: Implement X86_FEATURE_SYNC_RDTSC on i386
  [PATCH] i386: Implement alternative_io for i386
  ...

Fix up trivial conflict in include/linux/highmem.h manually.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

CREDITS

@@ -1745,8 +1745,9 @@ S: D-64295
 S: Germany
 
 N: Andi Kleen
-E: ak@muc.de
-D: network hacker, syncookies
+E: andi@firstfloor.org
+U: http://www.halobates.de
+D: network, x86, NUMA, various hacks
 S: Schwalbenstr. 96
 S: 85551 Ottobrunn
 S: Germany

Documentation/dontdiff

@@ -55,8 +55,8 @@ aic7*seq.h*
 aicasm
 aicdb.h*
 asm
-asm-offsets.*
-asm_offsets.*
+asm-offsets.h
+asm_offsets.h
 autoconf.h*
 bbootsect
 bin2c

Documentation/i386/boot.txt

@@ -2,7 +2,7 @@
 		     ----------------------------
 
 		    H. Peter Anvin <hpa@zytor.com>
-			Last update 2007-01-26
+			Last update 2007-03-06
 
 On the i386 platform, the Linux kernel uses a rather complicated boot
 convention.  This has evolved partially due to historical aspects, as
@@ -35,9 +35,13 @@ Protocol 2.03:	(Kernel 2.4.18-pre1) Explicitly makes the highest possible
 		initrd address available to the bootloader.
 
 Protocol 2.04:	(Kernel 2.6.14) Extend the syssize field to four bytes.
+
 Protocol 2.05:	(Kernel 2.6.20) Make protected mode kernel relocatable.
 		Introduce relocatable_kernel and kernel_alignment fields.
 
+Protocol 2.06:	(Kernel 2.6.22) Added a field that contains the size of
+		the boot command line
+
 
 **** MEMORY LAYOUT
 
@@ -133,6 +137,8 @@ Offset	Proto	Name		Meaning
 022C/4	2.03+	initrd_addr_max	Highest legal initrd address
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
+0235/3	N/A	pad2		Unused
+0238/4	2.06+	cmdline_size	Maximum size of the kernel command line
 
 (1) For backwards compatibility, if the setup_sects field contains 0, the
     real value is 4.
@@ -233,6 +239,12 @@ filled out, however:
 	if your ramdisk is exactly 131072 bytes long and this field is
 	0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
 
+  cmdline_size:
+	The maximum size of the command line without the terminating
+	zero. This means that the command line can contain at most
+	cmdline_size characters. With protocol version 2.05 and
+	earlier, the maximum size was 255.
+
 
 **** THE KERNEL COMMAND LINE
 
@@ -241,11 +253,10 @@ loader to communicate with the kernel.  Some of its options are also
 relevant to the boot loader itself, see "special command line options"
 below.
 
-The kernel command line is a null-terminated string currently up to
-255 characters long, plus the final null.  A string that is too long
-will be automatically truncated by the kernel, a boot loader may allow
-a longer command line to be passed to permit future kernels to extend
-this limit.
+The kernel command line is a null-terminated string. The maximum
+length can be retrieved from the field cmdline_size.  Before protocol
+version 2.06, the maximum was 255 characters.  A string that is too
+long will be automatically truncated by the kernel.
 
 If the boot protocol version is 2.02 or later, the address of the
 kernel command line is given by the header field cmd_line_ptr (see

Documentation/kernel-parameters.txt

@@ -64,6 +64,7 @@ parameter is applicable:
 	GENERIC_TIME The generic timeofday code is enabled.
 	NFS	Appropriate NFS support is enabled.
 	OSS	OSS sound support is enabled.
+	PV_OPS	A paravirtualized kernel
 	PARIDE	The ParIDE subsystem is enabled.
 	PARISC	The PA-RISC architecture is enabled.
 	PCI	PCI bus support is enabled.
@@ -695,8 +696,15 @@ and is between 256 and 4096 characters. It is defined in the file
 	idebus=		[HW] (E)IDE subsystem - VLB/PCI bus speed
 			See Documentation/ide.txt.
 
-	idle=		[HW]
-			Format: idle=poll or idle=halt
+	idle=		[X86]
+			Format: idle=poll or idle=mwait
+			Poll forces a polling idle loop that can slightly improves the performance
+			of waking up a idle CPU, but will use a lot of power and make the system
+			run hot. Not recommended.
+			idle=mwait. On systems which support MONITOR/MWAIT but the kernel chose
+			to not use it because it doesn't save as much power as a normal idle
+			loop use the MONITOR/MWAIT idle loop anyways. Performance should be the same
+			as idle=poll.
 
 	ignore_loglevel	[KNL]
 			Ignore loglevel setting - this will print /all/
@@ -1157,6 +1165,11 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nomce		[IA-32] Machine Check Exception
 
+	noreplace-paravirt	[IA-32,PV_OPS] Don't patch paravirt_ops
+
+	noreplace-smp	[IA-32,SMP] Don't replace SMP instructions
+			with UP alternatives
+
 	noresidual	[PPC] Don't use residual data on PReP machines.
 
 	noresume	[SWSUSP] Disables resume and restores original swap
@@ -1562,6 +1575,9 @@ and is between 256 and 4096 characters. It is defined in the file
 	smart2=		[HW]
 			Format: <io1>[,<io2>[,...,<io8>]]
 
+	smp-alt-once	[IA-32,SMP] On a hotplug CPU system, only
+			attempt to substitute SMP alternatives once at boot.
+
 	snd-ad1816a=	[HW,ALSA]
 
 	snd-ad1848=	[HW,ALSA]
@@ -1820,6 +1836,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			[USBHID] The interval which mice are to be polled at.
 
 	vdso=		[IA-32,SH]
+			vdso=2: enable compat VDSO (default with COMPAT_VDSO)
 			vdso=1: enable VDSO (default)
 			vdso=0: disable VDSO mapping
 

Documentation/x86_64/boot-options.txt

@@ -149,7 +149,19 @@ NUMA
 
   numa=noacpi   Don't parse the SRAT table for NUMA setup
 
-  numa=fake=X   Fake X nodes and ignore NUMA setup of the actual machine.
+  numa=fake=CMDLINE
+		If a number, fakes CMDLINE nodes and ignores NUMA setup of the
+		actual machine.  Otherwise, system memory is configured
+		depending on the sizes and coefficients listed.  For example:
+			numa=fake=2*512,1024,4*256,*128
+		gives two 512M nodes, a 1024M node, four 256M nodes, and the
+		rest split into 128M chunks.  If the last character of CMDLINE
+		is a *, the remaining memory is divided up equally among its
+		coefficient:
+			numa=fake=2*512,2*
+		gives two 512M nodes and the rest split into two nodes.
+		Otherwise, the remaining system RAM is allocated to an
+		additional node.
 
   numa=hotadd=percent
 		Only allow hotadd memory to preallocate page structures upto

Documentation/x86_64/fake-numa-for-cpusets

+Using numa=fake and CPUSets for Resource Management
+Written by David Rientjes <rientjes@cs.washington.edu>
+
+This document describes how the numa=fake x86_64 command-line option can be used
+in conjunction with cpusets for coarse memory management.  Using this feature,
+you can create fake NUMA nodes that represent contiguous chunks of memory and
+assign them to cpusets and their attached tasks.  This is a way of limiting the
+amount of system memory that are available to a certain class of tasks.
+
+For more information on the features of cpusets, see Documentation/cpusets.txt.
+There are a number of different configurations you can use for your needs.  For
+more information on the numa=fake command line option and its various ways of
+configuring fake nodes, see Documentation/x86_64/boot-options.txt.
+
+For the purposes of this introduction, we'll assume a very primitive NUMA
+emulation setup of "numa=fake=4*512,".  This will split our system memory into
+four equal chunks of 512M each that we can now use to assign to cpusets.  As
+you become more familiar with using this combination for resource control,
+you'll determine a better setup to minimize the number of nodes you have to deal
+with.
+
+A machine may be split as follows with "numa=fake=4*512," as reported by dmesg:
+
+	Faking node 0 at 0000000000000000-0000000020000000 (512MB)
+	Faking node 1 at 0000000020000000-0000000040000000 (512MB)
+	Faking node 2 at 0000000040000000-0000000060000000 (512MB)
+	Faking node 3 at 0000000060000000-0000000080000000 (512MB)
+	...
+	On node 0 totalpages: 130975
+	On node 1 totalpages: 131072
+	On node 2 totalpages: 131072
+	On node 3 totalpages: 131072
+
+Now following the instructions for mounting the cpusets filesystem from
+Documentation/cpusets.txt, you can assign fake nodes (i.e. contiguous memory
+address spaces) to individual cpusets:
+
+	[root@xroads /]# mkdir exampleset
+	[root@xroads /]# mount -t cpuset none exampleset
+	[root@xroads /]# mkdir exampleset/ddset
+	[root@xroads /]# cd exampleset/ddset
+	[root@xroads /exampleset/ddset]# echo 0-1 > cpus
+	[root@xroads /exampleset/ddset]# echo 0-1 > mems
+
+Now this cpuset, 'ddset', will only allowed access to fake nodes 0 and 1 for
+memory allocations (1G).
+
+You can now assign tasks to these cpusets to limit the memory resources
+available to them according to the fake nodes assigned as mems:
+
+	[root@xroads /exampleset/ddset]# echo $$ > tasks
+	[root@xroads /exampleset/ddset]# dd if=/dev/zero of=tmp bs=1024 count=1G
+	[1] 13425
+
+Notice the difference between the system memory usage as reported by
+/proc/meminfo between the restricted cpuset case above and the unrestricted
+case (i.e. running the same 'dd' command without assigning it to a fake NUMA
+cpuset):
+				Unrestricted	Restricted
+	MemTotal:		3091900 kB	3091900 kB
+	MemFree:		  42113 kB	1513236 kB
+
+This allows for coarse memory management for the tasks you assign to particular
+cpusets.  Since cpusets can form a hierarchy, you can create some pretty
+interesting combinations of use-cases for various classes of tasks for your
+memory management needs.

Documentation/x86_64/machinecheck

@@ -36,7 +36,12 @@ between all CPUs.
 
 check_interval
 	How often to poll for corrected machine check errors, in seconds
-	(Note output is hexademical). Default 5 minutes.
+	(Note output is hexademical). Default 5 minutes.  When the poller
+	finds MCEs it triggers an exponential speedup (poll more often) on
+	the polling interval.  When the poller stops finding MCEs, it
+	triggers an exponential backoff (poll less often) on the polling
+	interval. The check_interval variable is both the initial and
+	maximum polling interval.
 
 tolerant
 	Tolerance level. When a machine check exception occurs for a non

MAINTAINERS

@@ -1617,7 +1617,7 @@ S:	Maintained
 
 HPET:	x86_64
 P:	Andi Kleen and Vojtech Pavlik
-M:	ak@muc.de and vojtech@suse.cz
+M:	andi@firstfloor.org and vojtech@suse.cz
 S:	Maintained
 
 HPET:	ACPI hpet.c
@@ -2652,6 +2652,19 @@ T:	git kernel.org:/pub/scm/linux/kernel/git/kyle/parisc-2.6.git
 T:	cvs cvs.parisc-linux.org:/var/cvs/linux-2.6
 S:	Maintained
 
+PARAVIRT_OPS INTERFACE
+P:	Jeremy Fitzhardinge
+M:	jeremy@xensource.com
+P:	Chris Wright
+M:	chrisw@sous-sol.org
+P:	Zachary Amsden
+M:	zach@vmware.com
+P:	Rusty Russell
+M:	rusty@rustcorp.com.au
+L:	virtualization@lists.osdl.org
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+
 PC87360 HARDWARE MONITORING DRIVER
 P:	Jim Cromie
 M:	jim.cromie@gmail.com
@@ -3876,6 +3889,15 @@ M:	eis@baty.hanse.de
 L:	linux-x25@vger.kernel.org
 S:	Maintained
 
+XEN HYPERVISOR INTERFACE
+P:	Jeremy Fitzhardinge
+M:	jeremy@xensource.com
+P:	Chris Wright
+M:	chrisw@sous-sol.org
+L:	virtualization@lists.osdl.org
+L:	xen-devel@lists.xensource.com
+S:	Supported
+
 XFS FILESYSTEM
 P:	Silicon Graphics Inc
 P:	Tim Shimmin, David Chatterton

Makefile

@@ -491,7 +491,7 @@ endif
 include $(srctree)/arch/$(ARCH)/Makefile
 
 ifdef CONFIG_FRAME_POINTER
-CFLAGS		+= -fno-omit-frame-pointer $(call cc-option,-fno-optimize-sibling-calls,)
+CFLAGS		+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 else
 CFLAGS		+= -fomit-frame-pointer
 endif

arch/alpha/boot/misc.c

@@ -98,7 +98,7 @@ extern int end;
 static ulg free_mem_ptr;
 static ulg free_mem_ptr_end;
 
-#define HEAP_SIZE 0x2000
+#define HEAP_SIZE 0x3000
 
 #include "../../../lib/inflate.c"
 

arch/alpha/kernel/vmlinux.lds.S

@@ -69,7 +69,7 @@ SECTIONS
   . = ALIGN(8);
   SECURITY_INIT
 
-  . = ALIGN(64);
+  . = ALIGN(8192);
   __per_cpu_start = .;
   .data.percpu : { *(.data.percpu) }
   __per_cpu_end = .;

arch/arm/boot/compressed/misc.c

@@ -239,7 +239,7 @@ extern int end;
 static ulg free_mem_ptr;
 static ulg free_mem_ptr_end;
 
-#define HEAP_SIZE 0x2000
+#define HEAP_SIZE 0x3000
 
 #include "../../../../lib/inflate.c"
 

arch/arm/kernel/vmlinux.lds.S

@@ -59,7 +59,7 @@ SECTIONS
 			usr/built-in.o(.init.ramfs)
 		__initramfs_end = .;
 #endif
-		. = ALIGN(64);
+		. = ALIGN(4096);
 		__per_cpu_start = .;
 			*(.data.percpu)
 		__per_cpu_end = .;

arch/arm26/boot/compressed/misc.c

@@ -182,7 +182,7 @@ extern int end;
 static ulg free_mem_ptr;
 static ulg free_mem_ptr_end;
 
-#define HEAP_SIZE 0x2000
+#define HEAP_SIZE 0x3000
 
 #include "../../../../lib/inflate.c"
 

arch/cris/arch-v32/vmlinux.lds.S

@@ -91,6 +91,7 @@ SECTIONS
 	}
 	SECURITY_INIT
 
+	. =  ALIGN (8192);
 	__per_cpu_start = .;
 	.data.percpu  : { *(.data.percpu) }
 	__per_cpu_end = .;

arch/frv/kernel/vmlinux.lds.S

@@ -57,6 +57,7 @@ SECTIONS
   __alt_instructions_end = .;
  .altinstr_replacement : { *(.altinstr_replacement) }
 
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;

arch/i386/Kconfig

@@ -220,7 +220,7 @@ config PARAVIRT
 
 config VMI
 	bool "VMI Paravirt-ops support"
-	depends on PARAVIRT && !COMPAT_VDSO
+	depends on PARAVIRT
 	help
 	  VMI provides a paravirtualized interface to the VMware ESX server
 	  (it could be used by other hypervisors in theory too, but is not
@@ -571,6 +571,9 @@ choice
 		bool "3G/1G user/kernel split (for full 1G low memory)"
 	config VMSPLIT_2G
 		bool "2G/2G user/kernel split"
+	config VMSPLIT_2G_OPT
+		depends on !HIGHMEM
+		bool "2G/2G user/kernel split (for full 2G low memory)"
 	config VMSPLIT_1G
 		bool "1G/3G user/kernel split"
 endchoice
@@ -578,7 +581,8 @@ endchoice
 config PAGE_OFFSET
 	hex
 	default 0xB0000000 if VMSPLIT_3G_OPT
-	default 0x78000000 if VMSPLIT_2G
+	default 0x80000000 if VMSPLIT_2G
+	default 0x78000000 if VMSPLIT_2G_OPT
 	default 0x40000000 if VMSPLIT_1G
 	default 0xC0000000
 
@@ -915,12 +919,9 @@ source kernel/power/Kconfig
 
 source "drivers/acpi/Kconfig"
 
-menu "APM (Advanced Power Management) BIOS Support"
-depends on PM && !X86_VISWS
-
-config APM
+menuconfig APM
 	tristate "APM (Advanced Power Management) BIOS support"
-	depends on PM
+	depends on PM && !X86_VISWS
 	---help---
 	  APM is a BIOS specification for saving power using several different
 	  techniques. This is mostly useful for battery powered laptops with
@@ -977,9 +978,10 @@ config APM
 	  To compile this driver as a module, choose M here: the
 	  module will be called apm.
 
+if APM
+
 config APM_IGNORE_USER_SUSPEND
 	bool "Ignore USER SUSPEND"
-	depends on APM
 	help
 	  This option will ignore USER SUSPEND requests. On machines with a
 	  compliant APM BIOS, you want to say N. However, on the NEC Versa M
@@ -987,7 +989,6 @@ config APM_IGNORE_USER_SUSPEND
 
 config APM_DO_ENABLE
 	bool "Enable PM at boot time"
-	depends on APM
 	---help---
 	  Enable APM features at boot time. From page 36 of the APM BIOS
 	  specification: "When disabled, the APM BIOS does not automatically
@@ -1005,7 +1006,6 @@ config APM_DO_ENABLE
 
 config APM_CPU_IDLE
 	bool "Make CPU Idle calls when idle"
-	depends on APM
 	help
 	  Enable calls to APM CPU Idle/CPU Busy inside the kernel's idle loop.
 	  On some machines, this can activate improved power savings, such as
@@ -1017,7 +1017,6 @@ config APM_CPU_IDLE
 
 config APM_DISPLAY_BLANK
 	bool "Enable console blanking using APM"
-	depends on APM
 	help
 	  Enable console blanking using the APM. Some laptops can use this to
 	  turn off the LCD backlight when the screen blanker of the Linux
@@ -1029,22 +1028,8 @@ config APM_DISPLAY_BLANK
 	  backlight at all, or it might print a lot of errors to the console,
 	  especially if you are using gpm.
 
-config APM_RTC_IS_GMT
-	bool "RTC stores time in GMT"
-	depends on APM
-	help
-	  Say Y here if your RTC (Real Time Clock a.k.a. hardware clock)
-	  stores the time in GMT (Greenwich Mean Time). Say N if your RTC
-	  stores localtime.
-
-	  It is in fact recommended to store GMT in your RTC, because then you
-	  don't have to worry about daylight savings time changes. The only
-	  reason not to use GMT in your RTC is if you also run a broken OS
-	  that doesn't understand GMT.
-
 config APM_ALLOW_INTS
 	bool "Allow interrupts during APM BIOS calls"
-	depends on APM
 	help
 	  Normally we disable external interrupts while we are making calls to
 	  the APM BIOS as a measure to lessen the effects of a badly behaving
@@ -1055,13 +1040,12 @@ config APM_ALLOW_INTS
 
 config APM_REAL_MODE_POWER_OFF
 	bool "Use real mode APM BIOS call to power off"
-	depends on APM
 	help
 	  Use real mode APM BIOS calls to switch off the computer. This is
 	  a work-around for a number of buggy BIOSes. Switch this option on if
 	  your computer crashes instead of powering off properly.
 
-endmenu
+endif # APM
 
 source "arch/i386/kernel/cpu/cpufreq/Kconfig"
 

arch/i386/Kconfig.cpu

@@ -43,6 +43,7 @@ config M386
 	  - "Geode GX/LX" For AMD Geode GX and LX processors.
 	  - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3.
 	  - "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above).
+	  - "VIA C7" for VIA C7.
 
 	  If you don't know what to do, choose "386".
 
@@ -203,6 +204,12 @@ config MVIAC3_2
 	  of SSE and tells gcc to treat the CPU as a 686.
 	  Note, this kernel will not boot on older (pre model 9) C3s.
 
+config MVIAC7
+	bool "VIA C7"
+	help
+	  Select this for a VIA C7.  Selecting this uses the correct cache
+	  shift and tells gcc to treat the CPU as a 686.
+
 endchoice
 
 config X86_GENERIC
@@ -231,16 +238,21 @@ config X86_L1_CACHE_SHIFT
 	default "7" if MPENTIUM4 || X86_GENERIC
 	default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2
+	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7
+
+config X86_XADD
+	bool
+	depends on !M386
+	default y
 
 config RWSEM_GENERIC_SPINLOCK
 	bool
-	depends on M386
+	depends on !X86_XADD
 	default y
 
 config RWSEM_XCHGADD_ALGORITHM
 	bool
-	depends on !M386
+	depends on X86_XADD
 	default y
 
 config ARCH_HAS_ILOG2_U32
@@ -297,7 +309,7 @@ config X86_ALIGNMENT_16
 
 config X86_GOOD_APIC
 	bool
-	depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || MK8 || MEFFICEON || MCORE2
+	depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || MK8 || MEFFICEON || MCORE2 || MVIAC7
 	default y
 
 config X86_INTEL_USERCOPY
@@ -322,5 +334,18 @@ config X86_OOSTORE
 
 config X86_TSC
 	bool
-	depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ
+	depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ
 	default y
+
+# this should be set for all -march=.. options where the compiler
+# generates cmov.
+config X86_CMOV
+	bool
+	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7)
+	default y
+
+config X86_MINIMUM_CPU_MODEL
+	int
+	default "4" if X86_XADD || X86_CMPXCHG || X86_BSWAP
+	default "0"
+

arch/i386/Kconfig.debug

@@ -85,14 +85,4 @@ config DOUBLEFAULT
           option saves about 4k and might cause you much additional grey
           hair.
 
-config DEBUG_PARAVIRT
-	bool "Enable some paravirtualization debugging"
-	default n
-	depends on PARAVIRT && DEBUG_KERNEL
-	help
-	  Currently deliberately clobbers regs which are allowed to be
-	  clobbered in inlined paravirt hooks, even in native mode.
-	  If turning this off solves a problem, then DISABLE_INTERRUPTS() or
-	  ENABLE_INTERRUPTS() is lying about what registers can be clobbered.
-
 endmenu

arch/i386/Makefile

@@ -34,7 +34,7 @@ CHECKFLAGS	+= -D__i386__
 CFLAGS += -pipe -msoft-float -mregparm=3 -freg-struct-return
 
 # prevent gcc from keeping the stack 16 byte aligned
-CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
+CFLAGS += -mpreferred-stack-boundary=4
 
 # CPU-specific tuning. Anything which can be shared with UML should go here.
 include $(srctree)/arch/i386/Makefile.cpu

arch/i386/Makefile.cpu

@@ -4,9 +4,9 @@
 #-mtune exists since gcc 3.4
 HAS_MTUNE	:= $(call cc-option-yn, -mtune=i386)
 ifeq ($(HAS_MTUNE),y)
-tune		= $(call cc-option,-mtune=$(1),)
+tune		= $(call cc-option,-mtune=$(1),$(2))
 else
-tune		= $(call cc-option,-mcpu=$(1),)
+tune		= $(call cc-option,-mcpu=$(1),$(2))
 endif
 
 align := $(cc-option-align)
@@ -32,7 +32,8 @@ cflags-$(CONFIG_MWINCHIP2)	+= $(call cc-option,-march=winchip2,-march=i586)
 cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
 cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
-cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call cc-option,-mtune=core2,$(call cc-option,-mtune=generic,-mtune=i686))
+cflags-$(CONFIG_MVIAC7)		+= -march=i686
+cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)
 
 # AMD Elan support
 cflags-$(CONFIG_X86_ELAN)	+= -march=i486
@@ -42,5 +43,5 @@ cflags-$(CONFIG_MGEODEGX1)	+= -march=pentium-mmx
 
 # add at the end to overwrite eventual tuning options from earlier
 # cpu entries
-cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic)
+cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic,$(call tune,i686))
 

arch/i386/boot/Makefile

@@ -36,9 +36,9 @@ HOSTCFLAGS_build.o := $(LINUXINCLUDE)
 # ---------------------------------------------------------------------------
 
 $(obj)/zImage:  IMAGE_OFFSET := 0x1000
-$(obj)/zImage:  EXTRA_AFLAGS := -traditional $(SVGA_MODE) $(RAMDISK)
+$(obj)/zImage:  EXTRA_AFLAGS := $(SVGA_MODE) $(RAMDISK)
 $(obj)/bzImage: IMAGE_OFFSET := 0x100000
-$(obj)/bzImage: EXTRA_AFLAGS := -traditional $(SVGA_MODE) $(RAMDISK) -D__BIG_KERNEL__
+$(obj)/bzImage: EXTRA_AFLAGS := $(SVGA_MODE) $(RAMDISK) -D__BIG_KERNEL__
 $(obj)/bzImage: BUILDFLAGS   := -b
 
 quiet_cmd_image = BUILD   $@

arch/i386/boot/compressed/misc.c

@@ -189,7 +189,7 @@ static void putstr(const char *);
 static unsigned long free_mem_ptr;
 static unsigned long free_mem_end_ptr;
 
-#define HEAP_SIZE             0x3000
+#define HEAP_SIZE             0x4000
 
 static char *vidmem = (char *)0xb8000;
 static int vidport;

arch/i386/boot/setup.S

@@ -52,6 +52,7 @@
 #include <asm/boot.h>
 #include <asm/e820.h>
 #include <asm/page.h>
+#include <asm/setup.h>
 	
 /* Signature words to ensure LILO loaded us right */
 #define SIG1	0xAA55
@@ -81,7 +82,7 @@ start:
 # This is the setup header, and it must start at %cs:2 (old 0x9020:2)
 
 		.ascii	"HdrS"		# header signature
-		.word	0x0205		# header version number (>= 0x0105)
+		.word	0x0206		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
 start_sys_seg:	.word	SYSSEG
@@ -171,6 +172,10 @@ relocatable_kernel:    .byte 0
 pad2:			.byte 0
 pad3:			.word 0
 
+cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
+                                                #added with boot protocol
+                                                #version 2.06
+
 trampoline:	call	start_of_setup
 		.align 16
 					# The offset at this point is 0x240
@@ -297,7 +302,24 @@ good_sig:
 
 loader_panic_mess: .string "Wrong loader, giving up..."
 
+# check minimum cpuid
+# we do this here because it is the last place we can actually
+# show a user visible error message. Later the video modus
+# might be already messed up.
 loader_ok:
+	call verify_cpu
+	testl  %eax,%eax
+	jz	cpu_ok
+	lea	cpu_panic_mess,%si
+	call	prtstr
+1:	jmp	1b
+
+cpu_panic_mess:
+	.asciz  "PANIC: CPU too old for this kernel."
+
+#include "../kernel/verify_cpu.S"
+
+cpu_ok:
 # Get memory size (extended mem, kB)
 
 	xorl	%eax, %eax

arch/i386/defconfig

 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.21-rc3
-# Wed Mar  7 15:29:47 2007
+# Linux kernel version: 2.6.21-git3
+# Tue May  1 07:30:51 2007
 #
 CONFIG_X86_32=y
 CONFIG_GENERIC_TIME=y
@@ -108,9 +108,9 @@ CONFIG_DEFAULT_IOSCHED="anticipatory"
 #
 # Processor type and features
 #
-# CONFIG_TICK_ONESHOT is not set
-# CONFIG_NO_HZ is not set
-# CONFIG_HIGH_RES_TIMERS is not set
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
 # CONFIG_X86_PC is not set
 # CONFIG_X86_ELAN is not set
@@ -146,9 +146,11 @@ CONFIG_MPENTIUMIII=y
 # CONFIG_MGEODE_LX is not set
 # CONFIG_MCYRIXIII is not set
 # CONFIG_MVIAC3_2 is not set
+# CONFIG_MVIAC7 is not set
 CONFIG_X86_GENERIC=y
 CONFIG_X86_CMPXCHG=y
 CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_X86_XADD=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
@@ -162,6 +164,8 @@ CONFIG_X86_GOOD_APIC=y
 CONFIG_X86_INTEL_USERCOPY=y
 CONFIG_X86_USE_PPRO_CHECKSUM=y
 CONFIG_X86_TSC=y
+CONFIG_X86_CMOV=y
+CONFIG_X86_MINIMUM_CPU_MODEL=4
 CONFIG_HPET_TIMER=y
 CONFIG_HPET_EMULATE_RTC=y
 CONFIG_NR_CPUS=32
@@ -248,7 +252,6 @@ CONFIG_ACPI_FAN=y
 CONFIG_ACPI_PROCESSOR=y
 CONFIG_ACPI_THERMAL=y
 # CONFIG_ACPI_ASUS is not set
-# CONFIG_ACPI_IBM is not set
 # CONFIG_ACPI_TOSHIBA is not set
 CONFIG_ACPI_BLACKLIST_YEAR=2001
 CONFIG_ACPI_DEBUG=y
@@ -257,10 +260,7 @@ CONFIG_ACPI_POWER=y
 CONFIG_ACPI_SYSTEM=y
 CONFIG_X86_PM_TIMER=y
 # CONFIG_ACPI_CONTAINER is not set
-
-#
-# APM (Advanced Power Management) BIOS Support
-#
+# CONFIG_ACPI_SBS is not set
 # CONFIG_APM is not set
 
 #
@@ -277,7 +277,7 @@ CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
-# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 
 #
 # CPUFreq processor drivers
@@ -349,7 +349,6 @@ CONFIG_NET=y
 #
 # Networking options
 #
-# CONFIG_NETDEBUG is not set
 CONFIG_PACKET=y
 # CONFIG_PACKET_MMAP is not set
 CONFIG_UNIX=y
@@ -388,6 +387,7 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 CONFIG_IPV6=y
 # CONFIG_IPV6_PRIVACY is not set
 # CONFIG_IPV6_ROUTER_PREF is not set
+# CONFIG_IPV6_OPTIMISTIC_DAD is not set
 # CONFIG_INET6_AH is not set
 # CONFIG_INET6_ESP is not set
 # CONFIG_INET6_IPCOMP is not set
@@ -443,6 +443,13 @@ CONFIG_IPV6_SIT=y
 # CONFIG_HAMRADIO is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+
+#
+# Wireless
+#
+# CONFIG_CFG80211 is not set
+# CONFIG_WIRELESS_EXT is not set
 # CONFIG_IEEE80211 is not set
 
 #
@@ -463,10 +470,6 @@ CONFIG_FW_LOADER=y
 # Connector - unified userspace <-> kernelspace linker
 #
 # CONFIG_CONNECTOR is not set
-
-#
-# Memory Technology Devices (MTD)
-#
 # CONFIG_MTD is not set
 
 #
@@ -513,6 +516,7 @@ CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
 # CONFIG_SGI_IOC4 is not set
 # CONFIG_TIFM_CORE is not set
 # CONFIG_SONY_LAPTOP is not set
+# CONFIG_THINKPAD_ACPI is not set
 
 #
 # ATA/ATAPI/MFM/RLL support
@@ -548,7 +552,6 @@ CONFIG_BLK_DEV_IDEPCI=y
 # CONFIG_BLK_DEV_RZ1000 is not set
 CONFIG_BLK_DEV_IDEDMA_PCI=y
 # CONFIG_BLK_DEV_IDEDMA_FORCED is not set
-CONFIG_IDEDMA_PCI_AUTO=y
 # CONFIG_IDEDMA_ONLYDISK is not set
 # CONFIG_BLK_DEV_AEC62XX is not set
 # CONFIG_BLK_DEV_ALI15X3 is not set
@@ -580,7 +583,6 @@ CONFIG_BLK_DEV_PIIX=y
 # CONFIG_IDE_ARM is not set
 CONFIG_BLK_DEV_IDEDMA=y
 # CONFIG_IDEDMA_IVB is not set
-CONFIG_IDEDMA_AUTO=y
 # CONFIG_BLK_DEV_HD is not set
 
 #
@@ -669,6 +671,7 @@ CONFIG_AIC79XX_DEBUG_MASK=0
 # CONFIG_SCSI_DC390T is not set
 # CONFIG_SCSI_NSP32 is not set
 # CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_ESP_CORE is not set
 # CONFIG_SCSI_SRP is not set
 
 #
@@ -697,6 +700,7 @@ CONFIG_SATA_ACPI=y
 # CONFIG_PATA_AMD is not set
 # CONFIG_PATA_ARTOP is not set
 # CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_CMD640_PCI is not set
 # CONFIG_PATA_CMD64X is not set
 # CONFIG_PATA_CS5520 is not set
 # CONFIG_PATA_CS5530 is not set
@@ -762,10 +766,9 @@ CONFIG_IEEE1394=y
 # Subsystem Options
 #
 # CONFIG_IEEE1394_VERBOSEDEBUG is not set
-# CONFIG_IEEE1394_EXTRA_CONFIG_ROMS is not set
 
 #
-# Device Drivers
+# Controllers
 #
 
 #
@@ -774,10 +777,11 @@ CONFIG_IEEE1394=y
 CONFIG_IEEE1394_OHCI1394=y
 
 #
-# Protocol Drivers
+# Protocols
 #
 # CONFIG_IEEE1394_VIDEO1394 is not set
 # CONFIG_IEEE1394_SBP2 is not set
+# CONFIG_IEEE1394_ETH1394_ROM_ENTRY is not set
 # CONFIG_IEEE1394_ETH1394 is not set
 # CONFIG_IEEE1394_DV1394 is not set
 CONFIG_IEEE1394_RAWIO=y
@@ -820,7 +824,9 @@ CONFIG_MII=y
 # CONFIG_HAPPYMEAL is not set
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
-# CONFIG_NET_VENDOR_3COM is not set
+CONFIG_NET_VENDOR_3COM=y
+CONFIG_VORTEX=y
+# CONFIG_TYPHOON is not set
 
 #
 # Tulip family network device support
@@ -901,9 +907,10 @@ CONFIG_BNX2=y
 # CONFIG_TR is not set
 
 #
-# Wireless LAN (non-hamradio)
+# Wireless LAN
 #
-# CONFIG_NET_RADIO is not set
+# CONFIG_WLAN_PRE80211 is not set
+# CONFIG_WLAN_80211 is not set
 
 #
 # Wan interfaces
@@ -917,7 +924,6 @@ CONFIG_BNX2=y
 # CONFIG_SHAPER is not set
 CONFIG_NETCONSOLE=y
 CONFIG_NETPOLL=y
-# CONFIG_NETPOLL_RX is not set
 # CONFIG_NETPOLL_TRAP is not set
 CONFIG_NET_POLL_CONTROLLER=y
 
@@ -1050,7 +1056,7 @@ CONFIG_MAX_RAW_DEVS=256
 CONFIG_HPET=y
 # CONFIG_HPET_RTC_IRQ is not set
 CONFIG_HPET_MMAP=y
-CONFIG_HANGCHECK_TIMER=y
+# CONFIG_HANGCHECK_TIMER is not set
 
 #
 # TPM devices
@@ -1141,6 +1147,14 @@ CONFIG_SOUND_ICH=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
 
+#
+# USB Input Devices
+#
+CONFIG_USB_HID=y
+# CONFIG_USB_HIDINPUT_POWERBOOK is not set
+# CONFIG_HID_FF is not set
+# CONFIG_USB_HIDDEV is not set
+
 #
 # USB support
 #
@@ -1154,6 +1168,7 @@ CONFIG_USB=y
 # Miscellaneous USB options
 #
 CONFIG_USB_DEVICEFS=y
+# CONFIG_USB_DEVICE_CLASS is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
 # CONFIG_USB_OTG is not set
@@ -1204,10 +1219,6 @@ CONFIG_USB_STORAGE=y
 #
 # USB Input Devices
 #
-CONFIG_USB_HID=y
-# CONFIG_USB_HIDINPUT_POWERBOOK is not set
-# CONFIG_HID_FF is not set
-# CONFIG_USB_HIDDEV is not set
 # CONFIG_USB_AIPTEK is not set
 # CONFIG_USB_WACOM is not set
 # CONFIG_USB_ACECAD is not set
@@ -1528,7 +1539,7 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_LOG_BUF_SHIFT=18
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_SCHEDSTATS is not set
-# CONFIG_TIMER_STATS is not set
+CONFIG_TIMER_STATS=y
 # CONFIG_DEBUG_SLAB is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set

arch/i386/kernel/Makefile

@@ -39,12 +39,10 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_K8_NB)		+= k8.o
 
-obj-$(CONFIG_VMI)		+= vmi.o vmitime.o
+obj-$(CONFIG_VMI)		+= vmi.o vmiclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 obj-y				+= pcspeaker.o
 
-EXTRA_AFLAGS   := -traditional
-
 obj-$(CONFIG_SCx200)		+= scx200.o
 
 # vsyscall.o contains the vsyscall DSO images as __initdata.

arch/i386/kernel/acpi/boot.c

@@ -874,7 +874,7 @@ static void __init acpi_process_madt(void)
 				acpi_ioapic = 1;
 
 				smp_found_config = 1;
-				clustered_apic_check();
+				setup_apic_routing();
 			}
 		}
 		if (error == -EINVAL) {

arch/i386/kernel/acpi/earlyquirk.c

@@ -10,7 +10,6 @@
 #include <asm/pci-direct.h>
 #include <asm/acpi.h>
 #include <asm/apic.h>
-#include <asm/irq.h>
 
 #ifdef CONFIG_ACPI
 
@@ -48,24 +47,6 @@ static int __init check_bridge(int vendor, int device)
 	return 0;
 }
 
-static void check_intel(void)
-{
-	u16 vendor, device;
-
-	vendor = read_pci_config_16(0, 0, 0, PCI_VENDOR_ID);
-
-	if (vendor != PCI_VENDOR_ID_INTEL)
-		return;
-
-	device = read_pci_config_16(0, 0, 0, PCI_DEVICE_ID);
-#ifdef CONFIG_SMP
-	if (device == PCI_DEVICE_ID_INTEL_E7320_MCH ||
-	    device == PCI_DEVICE_ID_INTEL_E7520_MCH ||
-	    device == PCI_DEVICE_ID_INTEL_E7525_MCH)
-		quirk_intel_irqbalance();
-#endif
-}
-
 void __init check_acpi_pci(void)
 {
 	int num, slot, func;
@@ -77,8 +58,6 @@ void __init check_acpi_pci(void)
 	if (!early_pci_allowed())
 		return;
 
-	check_intel();
-
 	/* Poor man's PCI discovery */
 	for (num = 0; num < 32; num++) {
 		for (slot = 0; slot < 32; slot++) {

arch/i386/kernel/alternative.c

@@ -5,6 +5,7 @@
 #include <asm/alternative.h>
 #include <asm/sections.h>
 
+static int noreplace_smp     = 0;
 static int smp_alt_once      = 0;
 static int debug_alternative = 0;
 
@@ -13,15 +14,33 @@ static int __init bootonly(char *str)
 	smp_alt_once = 1;
 	return 1;
 }
+__setup("smp-alt-boot", bootonly);
+
 static int __init debug_alt(char *str)
 {
 	debug_alternative = 1;
 	return 1;
 }
-
-__setup("smp-alt-boot", bootonly);
 __setup("debug-alternative", debug_alt);
 
+static int __init setup_noreplace_smp(char *str)
+{
+	noreplace_smp = 1;
+	return 1;
+}
+__setup("noreplace-smp", setup_noreplace_smp);
+
+#ifdef CONFIG_PARAVIRT
+static int noreplace_paravirt = 0;
+
+static int __init setup_noreplace_paravirt(char *str)
+{
+	noreplace_paravirt = 1;
+	return 1;
+}
+__setup("noreplace-paravirt", setup_noreplace_paravirt);
+#endif
+
 #define DPRINTK(fmt, args...) if (debug_alternative) \
 	printk(KERN_DEBUG fmt, args)
 
@@ -132,11 +151,8 @@ static void nop_out(void *insns, unsigned int len)
 }
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
-extern struct alt_instr __smp_alt_instructions[], __smp_alt_instructions_end[];
 extern u8 *__smp_locks[], *__smp_locks_end[];
 
-extern u8 __smp_alt_begin[], __smp_alt_end[];
-
 /* Replace instructions with better alternatives for this CPU type.
    This runs before SMP is initialized to avoid SMP problems with
    self modifying code. This implies that assymetric systems where
@@ -171,29 +187,6 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 
 #ifdef CONFIG_SMP
 
-static void alternatives_smp_save(struct alt_instr *start, struct alt_instr *end)
-{
-	struct alt_instr *a;
-
-	DPRINTK("%s: alt table %p-%p\n", __FUNCTION__, start, end);
-	for (a = start; a < end; a++) {
-		memcpy(a->replacement + a->replacementlen,
-		       a->instr,
-		       a->instrlen);
-	}
-}
-
-static void alternatives_smp_apply(struct alt_instr *start, struct alt_instr *end)
-{
-	struct alt_instr *a;
-
-	for (a = start; a < end; a++) {
-		memcpy(a->instr,
-		       a->replacement + a->replacementlen,
-		       a->instrlen);
-	}
-}
-
 static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 {
 	u8 **ptr;
@@ -211,6 +204,9 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end
 {
 	u8 **ptr;
 
+	if (noreplace_smp)
+		return;
+
 	for (ptr = start; ptr < end; ptr++) {
 		if (*ptr < text)
 			continue;
@@ -245,6 +241,9 @@ void alternatives_smp_module_add(struct module *mod, char *name,
 	struct smp_alt_module *smp;
 	unsigned long flags;
 
+	if (noreplace_smp)
+		return;
+
 	if (smp_alt_once) {
 		if (boot_cpu_has(X86_FEATURE_UP))
 			alternatives_smp_unlock(locks, locks_end,
@@ -279,7 +278,7 @@ void alternatives_smp_module_del(struct module *mod)
 	struct smp_alt_module *item;
 	unsigned long flags;
 
-	if (smp_alt_once)
+	if (smp_alt_once || noreplace_smp)
 		return;
 
 	spin_lock_irqsave(&smp_alt, flags);
@@ -310,7 +309,7 @@ void alternatives_smp_switch(int smp)
 	return;
 #endif
 
-	if (smp_alt_once)
+	if (noreplace_smp || smp_alt_once)
 		return;
 	BUG_ON(!smp && (num_online_cpus() > 1));
 
@@ -319,8 +318,6 @@ void alternatives_smp_switch(int smp)
 		printk(KERN_INFO "SMP alternatives: switching to SMP code\n");
 		clear_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
 		clear_bit(X86_FEATURE_UP, cpu_data[0].x86_capability);
-		alternatives_smp_apply(__smp_alt_instructions,
-				       __smp_alt_instructions_end);
 		list_for_each_entry(mod, &smp_alt_modules, next)
 			alternatives_smp_lock(mod->locks, mod->locks_end,
 					      mod->text, mod->text_end);
@@ -328,8 +325,6 @@ void alternatives_smp_switch(int smp)
 		printk(KERN_INFO "SMP alternatives: switching to UP code\n");
 		set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
 		set_bit(X86_FEATURE_UP, cpu_data[0].x86_capability);
-		apply_alternatives(__smp_alt_instructions,
-				   __smp_alt_instructions_end);
 		list_for_each_entry(mod, &smp_alt_modules, next)
 			alternatives_smp_unlock(mod->locks, mod->locks_end,
 						mod->text, mod->text_end);
@@ -340,36 +335,31 @@ void alternatives_smp_switch(int smp)
 #endif
 
 #ifdef CONFIG_PARAVIRT
-void apply_paravirt(struct paravirt_patch *start, struct paravirt_patch *end)
+void apply_paravirt(struct paravirt_patch_site *start,
+		    struct paravirt_patch_site *end)
 {
-	struct paravirt_patch *p;
+	struct paravirt_patch_site *p;
+
+	if (noreplace_paravirt)
+		return;
 
 	for (p = start; p < end; p++) {
 		unsigned int used;
 
 		used = paravirt_ops.patch(p->instrtype, p->clobbers, p->instr,
 					  p->len);
-#ifdef CONFIG_DEBUG_PARAVIRT
-		{
-		int i;
-		/* Deliberately clobber regs using "not %reg" to find bugs. */
-		for (i = 0; i < 3; i++) {
-			if (p->len - used >= 2 && (p->clobbers & (1 << i))) {
-				memcpy(p->instr + used, "\xf7\xd0", 2);
-				p->instr[used+1] |= i;
-				used += 2;
-			}
-		}
-		}
-#endif
+
+		BUG_ON(used > p->len);
+
 		/* Pad the rest with nops */
 		nop_out(p->instr + used, p->len - used);
 	}
 
-	/* Sync to be conservative, in case we patched following instructions */
+	/* Sync to be conservative, in case we patched following
+	 * instructions */
 	sync_core();
 }
-extern struct paravirt_patch __start_parainstructions[],
+extern struct paravirt_patch_site __start_parainstructions[],
 	__stop_parainstructions[];
 #endif	/* CONFIG_PARAVIRT */
 
@@ -396,23 +386,19 @@ void __init alternative_instructions(void)
 			printk(KERN_INFO "SMP alternatives: switching to UP code\n");
 			set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
 			set_bit(X86_FEATURE_UP, cpu_data[0].x86_capability);
-			apply_alternatives(__smp_alt_instructions,
-					   __smp_alt_instructions_end);
 			alternatives_smp_unlock(__smp_locks, __smp_locks_end,
 						_text, _etext);
 		}
 		free_init_pages("SMP alternatives",
-				(unsigned long)__smp_alt_begin,
-				(unsigned long)__smp_alt_end);
+				__pa_symbol(&__smp_locks),
+				__pa_symbol(&__smp_locks_end));
 	} else {
-		alternatives_smp_save(__smp_alt_instructions,
-				      __smp_alt_instructions_end);
 		alternatives_smp_module_add(NULL, "core kernel",
 					    __smp_locks, __smp_locks_end,
 					    _text, _etext);
 		alternatives_smp_switch(0);
 	}
 #endif
- 	apply_paravirt(__start_parainstructions, __stop_parainstructions);
+ 	apply_paravirt(__parainstructions, __parainstructions_end);
 	local_irq_restore(flags);
 }

arch/i386/kernel/apic.c

@@ -129,6 +129,28 @@ static int modern_apic(void)
 	return lapic_get_version() >= 0x14;
 }
 
+void apic_wait_icr_idle(void)
+{
+	while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
+		cpu_relax();
+}
+
+unsigned long safe_apic_wait_icr_idle(void)
+{
+	unsigned long send_status;
+	int timeout;
+
+	timeout = 0;
+	do {
+		send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
+		if (!send_status)
+			break;
+		udelay(100);
+	} while (timeout++ < 1000);
+
+	return send_status;
+}
+
 /**
  * enable_NMI_through_LVT0 - enable NMI through local vector table 0
  */

arch/i386/kernel/apm.c

@@ -233,11 +233,10 @@
 #include <asm/desc.h>
 #include <asm/i8253.h>
 #include <asm/paravirt.h>
+#include <asm/reboot.h>
 
 #include "io_ports.h"
 
-extern void machine_real_restart(unsigned char *, int);
-
 #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
 extern int (*console_blank_hook)(int);
 #endif
@@ -384,13 +383,6 @@ static int			ignore_sys_suspend;
 static int			ignore_normal_resume;
 static int			bounce_interval __read_mostly = DEFAULT_BOUNCE_INTERVAL;
 
-#ifdef CONFIG_APM_RTC_IS_GMT
-#	define	clock_cmos_diff	0
-#	define	got_clock_diff	1
-#else
-static long			clock_cmos_diff;
-static int			got_clock_diff;
-#endif
 static int			debug __read_mostly;
 static int			smp __read_mostly;
 static int			apm_disabled = -1;

arch/i386/kernel/asm-offsets.c

@@ -11,11 +11,11 @@
 #include <linux/suspend.h>
 #include <asm/ucontext.h>
 #include "sigframe.h"
+#include <asm/pgtable.h>
 #include <asm/fixmap.h>
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 #include <asm/elf.h>
-#include <asm/pda.h>
 
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))
@@ -25,6 +25,9 @@
 #define OFFSET(sym, str, mem) \
 	DEFINE(sym, offsetof(struct str, mem));
 
+/* workaround for a warning with -Wmissing-prototypes */
+void foo(void);
+
 void foo(void)
 {
 	OFFSET(SIGCONTEXT_eax, sigcontext, eax);
@@ -90,17 +93,18 @@ void foo(void)
 	OFFSET(pbe_next, pbe, next);
 
 	/* Offset from the sysenter stack to tss.esp0 */
-	DEFINE(TSS_sysenter_esp0, offsetof(struct tss_struct, esp0) -
+	DEFINE(TSS_sysenter_esp0, offsetof(struct tss_struct, x86_tss.esp0) -
 		 sizeof(struct tss_struct));
 
 	DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
-	DEFINE(VDSO_PRELINK, VDSO_PRELINK);
+	DEFINE(PAGE_SHIFT_asm, PAGE_SHIFT);
+	DEFINE(PTRS_PER_PTE, PTRS_PER_PTE);
+	DEFINE(PTRS_PER_PMD, PTRS_PER_PMD);
+	DEFINE(PTRS_PER_PGD, PTRS_PER_PGD);
 
-	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
+	DEFINE(VDSO_PRELINK_asm, VDSO_PRELINK);
 
-	BLANK();
- 	OFFSET(PDA_cpu, i386_pda, cpu_number);
-	OFFSET(PDA_pcurrent, i386_pda, pcurrent);
+	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
 
 #ifdef CONFIG_PARAVIRT
 	BLANK();

arch/i386/kernel/cpu/Makefile

@@ -2,7 +2,7 @@
 # Makefile for x86-compatible CPU details and quirks
 #
 
-obj-y	:=	common.o proc.o
+obj-y	:=	common.o proc.o bugs.o
 
 obj-y	+=	amd.o
 obj-y	+=	cyrix.o
@@ -17,3 +17,5 @@ obj-$(CONFIG_X86_MCE)	+=	mcheck/
 
 obj-$(CONFIG_MTRR)	+= 	mtrr/
 obj-$(CONFIG_CPU_FREQ)	+=	cpufreq/
+
+obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o

arch/i386/kernel/cpu/amd.c

@@ -53,6 +53,8 @@ static __cpuinit int amd_apic_timer_broken(void)
 	return 0;
 }
 
+int force_mwait __cpuinitdata;
+
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
@@ -275,6 +277,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 
 	if (amd_apic_timer_broken())
 		set_bit(X86_FEATURE_LAPIC_TIMER_BROKEN, c->x86_capability);
+
+	if (c->x86 == 0x10 && !force_mwait)
+		clear_bit(X86_FEATURE_MWAIT, c->x86_capability);
 }
 
 static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 * c, unsigned int size)
@@ -314,13 +319,3 @@ int __init amd_init_cpu(void)
 	cpu_devs[X86_VENDOR_AMD] = &amd_cpu_dev;
 	return 0;
 }
-
-//early_arch_initcall(amd_init_cpu);
-
-static int __init amd_exit_cpu(void)
-{
-	cpu_devs[X86_VENDOR_AMD] = NULL;
-	return 0;
-}
-
-late_initcall(amd_exit_cpu);

arch/i386/kernel/cpu/bugs.c

+/*
+ *  arch/i386/cpu/bugs.c
+ *
+ *  Copyright (C) 1994  Linus Torvalds
+ *
+ *  Cyrix stuff, June 1998 by:
+ *	- Rafael R. Reilova (moved everything from head.S),
+ *        <rreilova@ececs.uc.edu>
+ *	- Channing Corn (tests & fixes),
+ *	- Andrew D. Balsa (code cleanup).
+ */
+#include <linux/init.h>
+#include <linux/utsname.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/msr.h>
+#include <asm/paravirt.h>
+#include <asm/alternative.h>
+
+static int __init no_halt(char *s)
+{
+	boot_cpu_data.hlt_works_ok = 0;
+	return 1;
+}
+
+__setup("no-hlt", no_halt);
+
+static int __init mca_pentium(char *s)
+{
+	mca_pentium_flag = 1;
+	return 1;
+}
+
+__setup("mca-pentium", mca_pentium);
+
+static int __init no_387(char *s)
+{
+	boot_cpu_data.hard_math = 0;
+	write_cr0(0xE | read_cr0());
+	return 1;
+}
+
+__setup("no387", no_387);
+
+static double __initdata x = 4195835.0;
+static double __initdata y = 3145727.0;
+
+/*
+ * This used to check for exceptions..
+ * However, it turns out that to support that,
+ * the XMM trap handlers basically had to
+ * be buggy. So let's have a correct XMM trap
+ * handler, and forget about printing out
+ * some status at boot.
+ *
+ * We should really only care about bugs here
+ * anyway. Not features.
+ */
+static void __init check_fpu(void)
+{
+	if (!boot_cpu_data.hard_math) {
+#ifndef CONFIG_MATH_EMULATION
+		printk(KERN_EMERG "No coprocessor found and no math emulation present.\n");
+		printk(KERN_EMERG "Giving up.\n");
+		for (;;) ;
+#endif
+		return;
+	}
+
+/* trap_init() enabled FXSR and company _before_ testing for FP problems here. */
+	/* Test for the divl bug.. */
+	__asm__("fninit\n\t"
+		"fldl %1\n\t"
+		"fdivl %2\n\t"
+		"fmull %2\n\t"
+		"fldl %1\n\t"
+		"fsubp %%st,%%st(1)\n\t"
+		"fistpl %0\n\t"
+		"fwait\n\t"
+		"fninit"
+		: "=m" (*&boot_cpu_data.fdiv_bug)
+		: "m" (*&x), "m" (*&y));
+	if (boot_cpu_data.fdiv_bug)
+		printk("Hmm, FPU with FDIV bug.\n");
+}
+
+static void __init check_hlt(void)
+{
+	if (paravirt_enabled())
+		return;
+
+	printk(KERN_INFO "Checking 'hlt' instruction... ");
+	if (!boot_cpu_data.hlt_works_ok) {
+		printk("disabled\n");
+		return;
+	}
+	halt();
+	halt();
+	halt();
+	halt();
+	printk("OK.\n");
+}
+
+/*
+ *	Most 386 processors have a bug where a POPAD can lock the
+ *	machine even from user space.
+ */
+
+static void __init check_popad(void)
+{
+#ifndef CONFIG_X86_POPAD_OK
+	int res, inp = (int) &res;
+
+	printk(KERN_INFO "Checking for popad bug... ");
+	__asm__ __volatile__(
+	  "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx "
+	  : "=&a" (res)
+	  : "d" (inp)
+	  : "ecx", "edi" );
+	/* If this fails, it means that any user program may lock the CPU hard. Too bad. */
+	if (res != 12345678) printk( "Buggy.\n" );
+		        else printk( "OK.\n" );
+#endif
+}
+
+/*
+ * Check whether we are able to run this kernel safely on SMP.
+ *
+ * - In order to run on a i386, we need to be compiled for i386
+ *   (for due to lack of "invlpg" and working WP on a i386)
+ * - In order to run on anything without a TSC, we need to be
+ *   compiled for a i486.
+ * - In order to support the local APIC on a buggy Pentium machine,
+ *   we need to be compiled with CONFIG_X86_GOOD_APIC disabled,
+ *   which happens implicitly if compiled for a Pentium or lower
+ *   (unless an advanced selection of CPU features is used) as an
+ *   otherwise config implies a properly working local APIC without
+ *   the need to do extra reads from the APIC.
+*/
+
+static void __init check_config(void)
+{
+/*
+ * We'd better not be a i386 if we're configured to use some
+ * i486+ only features! (WP works in supervisor mode and the
+ * new "invlpg" and "bswap" instructions)
+ */
+#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_BSWAP)
+	if (boot_cpu_data.x86 == 3)
+		panic("Kernel requires i486+ for 'invlpg' and other features");
+#endif
+
+/*
+ * If we configured ourselves for a TSC, we'd better have one!
+ */
+#ifdef CONFIG_X86_TSC
+	if (!cpu_has_tsc && !tsc_disable)
+		panic("Kernel compiled for Pentium+, requires TSC feature!");
+#endif
+
+/*
+ * If we were told we had a good local APIC, check for buggy Pentia,
+ * i.e. all B steppings and the C2 stepping of P54C when using their
+ * integrated APIC (see 11AP erratum in "Pentium Processor
+ * Specification Update").
+ */
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_GOOD_APIC)
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL
+	    && cpu_has_apic
+	    && boot_cpu_data.x86 == 5
+	    && boot_cpu_data.x86_model == 2
+	    && (boot_cpu_data.x86_mask < 6 || boot_cpu_data.x86_mask == 11))
+		panic("Kernel compiled for PMMX+, assumes a local APIC without the read-before-write bug!");
+#endif
+}
+
+
+void __init check_bugs(void)
+{
+	identify_boot_cpu();
+#ifndef CONFIG_SMP
+	printk("CPU: ");
+	print_cpu_info(&boot_cpu_data);
+#endif
+	check_config();
+	check_fpu();
+	check_hlt();
+	check_popad();
+	init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+	alternative_instructions();
+}

arch/i386/kernel/cpu/centaur.c

@@ -469,13 +469,3 @@ int __init centaur_init_cpu(void)
 	cpu_devs[X86_VENDOR_CENTAUR] = &centaur_cpu_dev;
 	return 0;
 }
-
-//early_arch_initcall(centaur_init_cpu);
-
-static int __init centaur_exit_cpu(void)
-{
-	cpu_devs[X86_VENDOR_CENTAUR] = NULL;
-	return 0;
-}
-
-late_initcall(centaur_exit_cpu);

arch/i386/kernel/cpu/common.c

@@ -18,15 +18,37 @@
 #include <asm/apic.h>
 #include <mach_apic.h>
 #endif
-#include <asm/pda.h>
 
 #include "cpu.h"
 
-DEFINE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
-EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr);
+DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+	[GDT_ENTRY_KERNEL_CS] = { 0x0000ffff, 0x00cf9a00 },
+	[GDT_ENTRY_KERNEL_DS] = { 0x0000ffff, 0x00cf9200 },
+	[GDT_ENTRY_DEFAULT_USER_CS] = { 0x0000ffff, 0x00cffa00 },
+	[GDT_ENTRY_DEFAULT_USER_DS] = { 0x0000ffff, 0x00cff200 },
+	/*
+	 * Segments used for calling PnP BIOS have byte granularity.
+	 * They code segments and data segments have fixed 64k limits,
+	 * the transfer segment sizes are set at run time.
+	 */
+	[GDT_ENTRY_PNPBIOS_CS32] = { 0x0000ffff, 0x00409a00 },/* 32-bit code */
+	[GDT_ENTRY_PNPBIOS_CS16] = { 0x0000ffff, 0x00009a00 },/* 16-bit code */
+	[GDT_ENTRY_PNPBIOS_DS] = { 0x0000ffff, 0x00009200 }, /* 16-bit data */
+	[GDT_ENTRY_PNPBIOS_TS1] = { 0x00000000, 0x00009200 },/* 16-bit data */
+	[GDT_ENTRY_PNPBIOS_TS2] = { 0x00000000, 0x00009200 },/* 16-bit data */
+	/*
+	 * The APM segments have byte granularity and their bases
+	 * are set at run time.  All have 64k limits.
+	 */
+	[GDT_ENTRY_APMBIOS_BASE] = { 0x0000ffff, 0x00409a00 },/* 32-bit code */
+	/* 16-bit code */
+	[GDT_ENTRY_APMBIOS_BASE+1] = { 0x0000ffff, 0x00009a00 },
+	[GDT_ENTRY_APMBIOS_BASE+2] = { 0x0000ffff, 0x00409200 }, /* data */
 
-struct i386_pda *_cpu_pda[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
+	[GDT_ENTRY_ESPFIX_SS] = { 0x00000000, 0x00c09200 },
+	[GDT_ENTRY_PERCPU] = { 0x00000000, 0x00000000 },
+} };
+EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
 static int cachesize_override __cpuinitdata = -1;
 static int disable_x86_fxsr __cpuinitdata;
@@ -368,7 +390,7 @@ __setup("serialnumber", x86_serial_nr_setup);
 /*
  * This does the hard work of actually picking apart the CPU stuff...
  */
-void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
+static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 {
 	int i;
 
@@ -479,15 +501,22 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 
 	/* Init Machine Check Exception if available. */
 	mcheck_init(c);
+}
 
-	if (c == &boot_cpu_data)
-		sysenter_setup();
+void __init identify_boot_cpu(void)
+{
+	identify_cpu(&boot_cpu_data);
+	sysenter_setup();
 	enable_sep_cpu();
+	mtrr_bp_init();
+}
 
-	if (c == &boot_cpu_data)
-		mtrr_bp_init();
-	else
-		mtrr_ap_init();
+void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
+{
+	BUG_ON(c == &boot_cpu_data);
+	identify_cpu(c);
+	enable_sep_cpu();
+	mtrr_ap_init();
 }
 
 #ifdef CONFIG_X86_HT
@@ -601,129 +630,36 @@ void __init early_cpu_init(void)
 #endif
 }
 
-/* Make sure %gs is initialized properly in idle threads */
+/* Make sure %fs is initialized properly in idle threads */
 struct pt_regs * __devinit idle_regs(struct pt_regs *regs)
 {
 	memset(regs, 0, sizeof(struct pt_regs));
-	regs->xfs = __KERNEL_PDA;
+	regs->xfs = __KERNEL_PERCPU;
 	return regs;
 }
 
-static __cpuinit int alloc_gdt(int cpu)
+/* Current gdt points %fs at the "master" per-cpu area: after this,
+ * it's on the real one. */
+void switch_to_new_gdt(void)
 {
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
-	struct desc_struct *gdt;
-	struct i386_pda *pda;
-
-	gdt = (struct desc_struct *)cpu_gdt_descr->address;
-	pda = cpu_pda(cpu);
-
-	/*
-	 * This is a horrible hack to allocate the GDT.  The problem
-	 * is that cpu_init() is called really early for the boot CPU
-	 * (and hence needs bootmem) but much later for the secondary
-	 * CPUs, when bootmem will have gone away
-	 */
-	if (NODE_DATA(0)->bdata->node_bootmem_map) {
-		BUG_ON(gdt != NULL || pda != NULL);
-
-		gdt = alloc_bootmem_pages(PAGE_SIZE);
-		pda = alloc_bootmem(sizeof(*pda));
-		/* alloc_bootmem(_pages) panics on failure, so no check */
-
-		memset(gdt, 0, PAGE_SIZE);
-		memset(pda, 0, sizeof(*pda));
-	} else {
-		/* GDT and PDA might already have been allocated if
-		   this is a CPU hotplug re-insertion. */
-		if (gdt == NULL)
-			gdt = (struct desc_struct *)get_zeroed_page(GFP_KERNEL);
-
-		if (pda == NULL)
-			pda = kmalloc_node(sizeof(*pda), GFP_KERNEL, cpu_to_node(cpu));
-
-		if (unlikely(!gdt || !pda)) {
-			free_pages((unsigned long)gdt, 0);
-			kfree(pda);
-			return 0;
-		}
-	}
-
- 	cpu_gdt_descr->address = (unsigned long)gdt;
-	cpu_pda(cpu) = pda;
-
-	return 1;
-}
+	struct Xgt_desc_struct gdt_descr;
 
-/* Initial PDA used by boot CPU */
-struct i386_pda boot_pda = {
-	._pda = &boot_pda,
-	.cpu_number = 0,
-	.pcurrent = &init_task,
-};
-
-static inline void set_kernel_fs(void)
-{
-	/* Set %fs for this CPU's PDA.  Memory clobber is to create a
-	   barrier with respect to any PDA operations, so the compiler
-	   doesn't move any before here. */
-	asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_PDA) : "memory");
+	gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+	asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
 }
 
-/* Initialize the CPU's GDT and PDA.  The boot CPU does this for
-   itself, but secondaries find this done for them. */
-__cpuinit int init_gdt(int cpu, struct task_struct *idle)
-{
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
-	struct desc_struct *gdt;
-	struct i386_pda *pda;
-
-	/* For non-boot CPUs, the GDT and PDA should already have been
-	   allocated. */
-	if (!alloc_gdt(cpu)) {
-		printk(KERN_CRIT "CPU%d failed to allocate GDT or PDA\n", cpu);
-		return 0;
-	}
-
-	gdt = (struct desc_struct *)cpu_gdt_descr->address;
-	pda = cpu_pda(cpu);
-
-	BUG_ON(gdt == NULL || pda == NULL);
-
-	/*
-	 * Initialize the per-CPU GDT with the boot GDT,
-	 * and set up the GDT descriptor:
-	 */
- 	memcpy(gdt, cpu_gdt_table, GDT_SIZE);
-	cpu_gdt_descr->size = GDT_SIZE - 1;
-
-	pack_descriptor((u32 *)&gdt[GDT_ENTRY_PDA].a,
-			(u32 *)&gdt[GDT_ENTRY_PDA].b,
-			(unsigned long)pda, sizeof(*pda) - 1,
-			0x80 | DESCTYPE_S | 0x2, 0); /* present read-write data segment */
-
-	memset(pda, 0, sizeof(*pda));
-	pda->_pda = pda;
-	pda->cpu_number = cpu;
-	pda->pcurrent = idle;
-
-	return 1;
-}
-
-void __cpuinit cpu_set_gdt(int cpu)
-{
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
-
-	/* Reinit these anyway, even if they've already been done (on
-	   the boot CPU, this will transition from the boot gdt+pda to
-	   the real ones). */
-	load_gdt(cpu_gdt_descr);
-	set_kernel_fs();
-}
-
-/* Common CPU init for both boot and secondary CPUs */
-static void __cpuinit _cpu_init(int cpu, struct task_struct *curr)
+/*
+ * cpu_init() initializes state that is per-CPU. Some data is already
+ * initialized (naturally) in the bootstrap process, such as the GDT
+ * and IDT. We reload them nevertheless, this function acts as a
+ * 'CPU state barrier', nothing should get across.
+ */
+void __cpuinit cpu_init(void)
 {
+	int cpu = smp_processor_id();
+	struct task_struct *curr = current;
 	struct tss_struct * t = &per_cpu(init_tss, cpu);
 	struct thread_struct *thread = &curr->thread;
 
@@ -744,6 +680,7 @@ static void __cpuinit _cpu_init(int cpu, struct task_struct *curr)
 	}
 
 	load_idt(&idt_descr);
+	switch_to_new_gdt();
 
 	/*
 	 * Set up and load the per-CPU TSS and LDT
@@ -783,38 +720,6 @@ static void __cpuinit _cpu_init(int cpu, struct task_struct *curr)
 	mxcsr_feature_mask_init();
 }
 
-/* Entrypoint to initialize secondary CPU */
-void __cpuinit secondary_cpu_init(void)
-{
-	int cpu = smp_processor_id();
-	struct task_struct *curr = current;
-
-	_cpu_init(cpu, curr);
-}
-
-/*
- * cpu_init() initializes state that is per-CPU. Some data is already
- * initialized (naturally) in the bootstrap process, such as the GDT
- * and IDT. We reload them nevertheless, this function acts as a
- * 'CPU state barrier', nothing should get across.
- */
-void __cpuinit cpu_init(void)
-{
-	int cpu = smp_processor_id();
-	struct task_struct *curr = current;
-
-	/* Set up the real GDT and PDA, so we can transition from the
-	   boot versions. */
-	if (!init_gdt(cpu, curr)) {
-		/* failed to allocate something; not much we can do... */
-		for (;;)
-			local_irq_enable();
-	}
-
-	cpu_set_gdt(cpu);
-	_cpu_init(cpu, curr);
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 void __cpuinit cpu_uninit(void)
 {

arch/i386/kernel/cpu/cyrix.c

@@ -279,7 +279,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
 		 */  
 		if (vendor == PCI_VENDOR_ID_CYRIX &&
 	 (device == PCI_DEVICE_ID_CYRIX_5510 || device == PCI_DEVICE_ID_CYRIX_5520))
-			pit_latch_buggy = 1;
+			mark_tsc_unstable("cyrix 5510/5520 detected");
 	}
 #endif
 		c->x86_cache_size=16;	/* Yep 16K integrated cache thats it */
@@ -448,16 +448,6 @@ int __init cyrix_init_cpu(void)
 	return 0;
 }
 
-//early_arch_initcall(cyrix_init_cpu);
-
-static int __init cyrix_exit_cpu(void)
-{
-	cpu_devs[X86_VENDOR_CYRIX] = NULL;
-	return 0;
-}
-
-late_initcall(cyrix_exit_cpu);
-
 static struct cpu_dev nsc_cpu_dev __cpuinitdata = {
 	.c_vendor	= "NSC",
 	.c_ident 	= { "Geode by NSC" },
@@ -470,12 +460,3 @@ int __init nsc_init_cpu(void)
 	return 0;
 }
 
-//early_arch_initcall(nsc_init_cpu);
-
-static int __init nsc_exit_cpu(void)
-{
-	cpu_devs[X86_VENDOR_NSC] = NULL;
-	return 0;
-}
-
-late_initcall(nsc_exit_cpu);

arch/i386/kernel/cpu/intel.c

@@ -188,8 +188,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 	}
 #endif
 
-	if (c->x86 == 15)
+	if (c->x86 == 15) {
 		set_bit(X86_FEATURE_P4, c->x86_capability);
+		set_bit(X86_FEATURE_SYNC_RDTSC, c->x86_capability);
+	}
 	if (c->x86 == 6) 
 		set_bit(X86_FEATURE_P3, c->x86_capability);
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||

arch/i386/kernel/cpu/mcheck/k7.c

@@ -75,6 +75,9 @@ void amd_mcheck_init(struct cpuinfo_x86 *c)
 	machine_check_vector = k7_machine_check;
 	wmb();
 
+	if (!cpu_has(c, X86_FEATURE_MCE))
+		return;
+
 	printk (KERN_INFO "Intel machine check architecture supported.\n");
 	rdmsr (MSR_IA32_MCG_CAP, l, h);
 	if (l & (1<<8))	/* Control register present ? */
@@ -82,9 +85,13 @@ void amd_mcheck_init(struct cpuinfo_x86 *c)
 	nr_mce_banks = l & 0xff;
 
 	/* Clear status for MC index 0 separately, we don't touch CTL,
-	 * as some Athlons cause spurious MCEs when its enabled. */
-	wrmsr (MSR_IA32_MC0_STATUS, 0x0, 0x0);
-	for (i=1; i<nr_mce_banks; i++) {
+	 * as some K7 Athlons cause spurious MCEs when its enabled. */
+	if (boot_cpu_data.x86 == 6) {
+		wrmsr (MSR_IA32_MC0_STATUS, 0x0, 0x0);
+		i = 1;
+	} else
+		i = 0;
+	for (; i<nr_mce_banks; i++) {
 		wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
 		wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
 	}

arch/i386/kernel/cpu/mcheck/mce.c

@@ -38,8 +38,7 @@ void mcheck_init(struct cpuinfo_x86 *c)
 
 	switch (c->x86_vendor) {
 		case X86_VENDOR_AMD:
-			if (c->x86==6 || c->x86==15)
-				amd_mcheck_init(c);
+			amd_mcheck_init(c);
 			break;
 
 		case X86_VENDOR_INTEL:

arch/i386/kernel/cpu/mcheck/p4.c

@@ -124,13 +124,10 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
 
 
 /* P4/Xeon Extended MCE MSR retrieval, return 0 if unsupported */
-static inline int intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
+static inline void intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
 {
 	u32 h;
 
-	if (mce_num_extended_msrs == 0)
-		goto done;
-
 	rdmsr (MSR_IA32_MCG_EAX, r->eax, h);
 	rdmsr (MSR_IA32_MCG_EBX, r->ebx, h);
 	rdmsr (MSR_IA32_MCG_ECX, r->ecx, h);
@@ -141,12 +138,6 @@ static inline int intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
 	rdmsr (MSR_IA32_MCG_ESP, r->esp, h);
 	rdmsr (MSR_IA32_MCG_EFLAGS, r->eflags, h);
 	rdmsr (MSR_IA32_MCG_EIP, r->eip, h);
-
-	/* can we rely on kmalloc to do a dynamic
-	 * allocation for the reserved registers?
-	 */
-done:
-	return mce_num_extended_msrs;
 }
 
 static fastcall void intel_machine_check(struct pt_regs * regs, long error_code)
@@ -155,7 +146,6 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code)
 	u32 alow, ahigh, high, low;
 	u32 mcgstl, mcgsth;
 	int i;
-	struct intel_mce_extended_msrs dbg;
 
 	rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 	if (mcgstl & (1<<0))	/* Recoverable ? */
@@ -164,7 +154,9 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code)
 	printk (KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
 		smp_processor_id(), mcgsth, mcgstl);
 
-	if (intel_get_extended_msrs(&dbg)) {
+	if (mce_num_extended_msrs > 0) {
+		struct intel_mce_extended_msrs dbg;
+		intel_get_extended_msrs(&dbg);
 		printk (KERN_DEBUG "CPU %d: EIP: %08x EFLAGS: %08x\n",
 			smp_processor_id(), dbg.eip, dbg.eflags);
 		printk (KERN_DEBUG "\teax: %08x ebx: %08x ecx: %08x edx: %08x\n",

arch/i386/kernel/cpu/mtrr/generic.c

@@ -20,13 +20,25 @@ struct mtrr_state {
 	mtrr_type def_type;
 };
 
+struct fixed_range_block {
+	int base_msr; /* start address of an MTRR block */
+	int ranges;   /* number of MTRRs in this block  */
+};
+
+static struct fixed_range_block fixed_range_blocks[] = {
+	{ MTRRfix64K_00000_MSR, 1 }, /* one  64k MTRR  */
+	{ MTRRfix16K_80000_MSR, 2 }, /* two  16k MTRRs */
+	{ MTRRfix4K_C0000_MSR,  8 }, /* eight 4k MTRRs */
+	{}
+};
+
 static unsigned long smp_changes_mask;
 static struct mtrr_state mtrr_state = {};
 
 #undef MODULE_PARAM_PREFIX
 #define MODULE_PARAM_PREFIX "mtrr."
 
-static __initdata int mtrr_show;
+static int mtrr_show;
 module_param_named(show, mtrr_show, bool, 0);
 
 /*  Get the MSR pair relating to a var range  */
@@ -37,7 +49,7 @@ get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
 	rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi);
 }
 
-static void __init
+static void
 get_fixed_ranges(mtrr_type * frs)
 {
 	unsigned int *p = (unsigned int *) frs;
@@ -51,12 +63,18 @@ get_fixed_ranges(mtrr_type * frs)
 		rdmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], p[7 + i * 2]);
 }
 
-static void __init print_fixed(unsigned base, unsigned step, const mtrr_type*types)
+void mtrr_save_fixed_ranges(void *info)
+{
+	get_fixed_ranges(mtrr_state.fixed_ranges);
+}
+
+static void __cpuinit print_fixed(unsigned base, unsigned step, const mtrr_type*types)
 {
 	unsigned i;
 
 	for (i = 0; i < 8; ++i, ++types, base += step)
-		printk(KERN_INFO "MTRR %05X-%05X %s\n", base, base + step - 1, mtrr_attrib_to_str(*types));
+		printk(KERN_INFO "MTRR %05X-%05X %s\n",
+			base, base + step - 1, mtrr_attrib_to_str(*types));
 }
 
 /*  Grab all of the MTRR state for this CPU into *state  */
@@ -147,6 +165,44 @@ void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b)
 			smp_processor_id(), msr, a, b);
 }
 
+/**
+ * Enable and allow read/write of extended fixed-range MTRR bits on K8 CPUs
+ * see AMD publication no. 24593, chapter 3.2.1 for more information
+ */
+static inline void k8_enable_fixed_iorrs(void)
+{
+	unsigned lo, hi;
+
+	rdmsr(MSR_K8_SYSCFG, lo, hi);
+	mtrr_wrmsr(MSR_K8_SYSCFG, lo
+				| K8_MTRRFIXRANGE_DRAM_ENABLE
+				| K8_MTRRFIXRANGE_DRAM_MODIFY, hi);
+}
+
+/**
+ * Checks and updates an fixed-range MTRR if it differs from the value it
+ * should have. If K8 extenstions are wanted, update the K8 SYSCFG MSR also.
+ * see AMD publication no. 24593, chapter 7.8.1, page 233 for more information
+ * \param msr MSR address of the MTTR which should be checked and updated
+ * \param changed pointer which indicates whether the MTRR needed to be changed
+ * \param msrwords pointer to the MSR values which the MSR should have
+ */
+static void set_fixed_range(int msr, int * changed, unsigned int * msrwords)
+{
+	unsigned lo, hi;
+
+	rdmsr(msr, lo, hi);
+
+	if (lo != msrwords[0] || hi != msrwords[1]) {
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
+		    boot_cpu_data.x86 == 15 &&
+		    ((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK))
+			k8_enable_fixed_iorrs();
+		mtrr_wrmsr(msr, msrwords[0], msrwords[1]);
+		*changed = TRUE;
+	}
+}
+
 int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg)
 /*  [SUMMARY] Get a free MTRR.
     <base> The starting (base) address of the region.
@@ -196,36 +252,21 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 	*type = base_lo & 0xff;
 }
 
+/**
+ * Checks and updates the fixed-range MTRRs if they differ from the saved set
+ * \param frs pointer to fixed-range MTRR values, saved by get_fixed_ranges()
+ */
 static int set_fixed_ranges(mtrr_type * frs)
 {
-	unsigned int *p = (unsigned int *) frs;
+	unsigned long long *saved = (unsigned long long *) frs;
 	int changed = FALSE;
-	int i;
-	unsigned int lo, hi;
+	int block=-1, range;
 
-	rdmsr(MTRRfix64K_00000_MSR, lo, hi);
-	if (p[0] != lo || p[1] != hi) {
-		mtrr_wrmsr(MTRRfix64K_00000_MSR, p[0], p[1]);
-		changed = TRUE;
-	}
+	while (fixed_range_blocks[++block].ranges)
+	    for (range=0; range < fixed_range_blocks[block].ranges; range++)
+		set_fixed_range(fixed_range_blocks[block].base_msr + range,
+		    &changed, (unsigned int *) saved++);
 
-	for (i = 0; i < 2; i++) {
-		rdmsr(MTRRfix16K_80000_MSR + i, lo, hi);
-		if (p[2 + i * 2] != lo || p[3 + i * 2] != hi) {
-			mtrr_wrmsr(MTRRfix16K_80000_MSR + i, p[2 + i * 2],
-			      p[3 + i * 2]);
-			changed = TRUE;
-		}
-	}
-
-	for (i = 0; i < 8; i++) {
-		rdmsr(MTRRfix4K_C0000_MSR + i, lo, hi);
-		if (p[6 + i * 2] != lo || p[7 + i * 2] != hi) {
-			mtrr_wrmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2],
-			      p[7 + i * 2]);
-			changed = TRUE;
-		}
-	}
 	return changed;
 }
 
@@ -428,7 +469,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, unsigned i
 		}
 	}
 
-	if (base + size < 0x100) {
+	if (base < 0x100) {
 		printk(KERN_WARNING "mtrr: cannot set region below 1 MiB (0x%lx000,0x%lx000)\n",
 		       base, size);
 		return -EINVAL;

arch/i386/kernel/cpu/mtrr/main.c

@@ -729,6 +729,17 @@ void mtrr_ap_init(void)
 	local_irq_restore(flags);
 }
 
+/**
+ * Save current fixed-range MTRR state of the BSP
+ */
+void mtrr_save_state(void)
+{
+	if (smp_processor_id() == 0)
+		mtrr_save_fixed_ranges(NULL);
+	else
+		smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
+}
+
 static int __init mtrr_init_finialize(void)
 {
 	if (!mtrr_if)

arch/i386/kernel/cpu/nexgen.c

@@ -58,13 +58,3 @@ int __init nexgen_init_cpu(void)
 	cpu_devs[X86_VENDOR_NEXGEN] = &nexgen_cpu_dev;
 	return 0;
 }
-
-//early_arch_initcall(nexgen_init_cpu);
-
-static int __init nexgen_exit_cpu(void)
-{
-	cpu_devs[X86_VENDOR_NEXGEN] = NULL;
-	return 0;
-}
-
-late_initcall(nexgen_exit_cpu);

arch/i386/kernel/cpu/proc.c

@@ -72,8 +72,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		"stc",
 		"100mhzsteps",
 		"hwpstate",
-		NULL,
-		NULL,	/* constant_tsc - moved to flags */
+		"",	/* constant_tsc - moved to flags */
 		/* nothing */
 	};
 	struct cpuinfo_x86 *c = v;

arch/i386/kernel/cpu/rise.c

@@ -50,12 +50,3 @@ int __init rise_init_cpu(void)
 	return 0;
 }
 
-//early_arch_initcall(rise_init_cpu);
-
-static int __init rise_exit_cpu(void)
-{
-	cpu_devs[X86_VENDOR_RISE] = NULL;
-	return 0;
-}
-
-late_initcall(rise_exit_cpu);

arch/i386/kernel/cpu/transmeta.c

@@ -112,13 +112,3 @@ int __init transmeta_init_cpu(void)
 	cpu_devs[X86_VENDOR_TRANSMETA] = &transmeta_cpu_dev;
 	return 0;
 }
-
-//early_arch_initcall(transmeta_init_cpu);
-
-static int __init transmeta_exit_cpu(void)
-{
-	cpu_devs[X86_VENDOR_TRANSMETA] = NULL;
-	return 0;
-}
-
-late_initcall(transmeta_exit_cpu);

arch/i386/kernel/cpu/umc.c

@@ -24,13 +24,3 @@ int __init umc_init_cpu(void)
 	cpu_devs[X86_VENDOR_UMC] = &umc_cpu_dev;
 	return 0;
 }
-
-//early_arch_initcall(umc_init_cpu);
-
-static int __init umc_exit_cpu(void)
-{
-	cpu_devs[X86_VENDOR_UMC] = NULL;
-	return 0;
-}
-
-late_initcall(umc_exit_cpu);

arch/i386/kernel/doublefault.c

@@ -33,7 +33,7 @@ static void doublefault_fn(void)
 		printk("double fault, tss at %08lx\n", tss);
 
 		if (ptr_ok(tss)) {
-			struct tss_struct *t = (struct tss_struct *)tss;
+			struct i386_hw_tss *t = (struct i386_hw_tss *)tss;
 
 			printk("eip = %08lx, esp = %08lx\n", t->eip, t->esp);
 
@@ -49,18 +49,21 @@ static void doublefault_fn(void)
 }
 
 struct tss_struct doublefault_tss __cacheline_aligned = {
-	.esp0		= STACK_START,
-	.ss0		= __KERNEL_DS,
-	.ldt		= 0,
-	.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
+	.x86_tss = {
+		.esp0		= STACK_START,
+		.ss0		= __KERNEL_DS,
+		.ldt		= 0,
+		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
 
-	.eip		= (unsigned long) doublefault_fn,
-	.eflags		= X86_EFLAGS_SF | 0x2,	/* 0x2 bit is always set */
-	.esp		= STACK_START,
-	.es		= __USER_DS,
-	.cs		= __KERNEL_CS,
-	.ss		= __KERNEL_DS,
-	.ds		= __USER_DS,
+		.eip		= (unsigned long) doublefault_fn,
+		/* 0x2 bit is always set */
+		.eflags		= X86_EFLAGS_SF | 0x2,
+		.esp		= STACK_START,
+		.es		= __USER_DS,
+		.cs		= __KERNEL_CS,
+		.ss		= __KERNEL_DS,
+		.ds		= __USER_DS,
 
-	.__cr3		= __pa(swapper_pg_dir)
+		.__cr3		= __pa(swapper_pg_dir)
+	}
 };

arch/i386/kernel/e820.c

@@ -161,26 +161,27 @@ static struct resource standard_io_resources[] = { {
 
 static int __init romsignature(const unsigned char *rom)
 {
+	const unsigned short * const ptr = (const unsigned short *)rom;
 	unsigned short sig;
 
-	return probe_kernel_address((const unsigned short *)rom, sig) == 0 &&
-	       sig == ROMSIGNATURE;
+	return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE;
 }
 
-static int __init romchecksum(unsigned char *rom, unsigned long length)
+static int __init romchecksum(const unsigned char *rom, unsigned long length)
 {
-	unsigned char sum;
+	unsigned char sum, c;
 
-	for (sum = 0; length; length--)
-		sum += *rom++;
-	return sum == 0;
+	for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--)
+		sum += c;
+	return !length && !sum;
 }
 
 static void __init probe_roms(void)
 {
+	const unsigned char *rom;
 	unsigned long start, length, upper;
-	unsigned char *rom;
-	int	      i;
+	unsigned char c;
+	int i;
 
 	/* video rom */
 	upper = adapter_rom_resources[0].start;
@@ -191,8 +192,11 @@ static void __init probe_roms(void)
 
 		video_rom_resource.start = start;
 
+		if (probe_kernel_address(rom + 2, c) != 0)
+			continue;
+
 		/* 0 < length <= 0x7f * 512, historically */
-		length = rom[2] * 512;
+		length = c * 512;
 
 		/* if checksum okay, trust length byte */
 		if (length && romchecksum(rom, length))
@@ -226,8 +230,11 @@ static void __init probe_roms(void)
 		if (!romsignature(rom))
 			continue;
 
+		if (probe_kernel_address(rom + 2, c) != 0)
+			continue;
+
 		/* 0 < length <= 0x7f * 512, historically */
-		length = rom[2] * 512;
+		length = c * 512;
 
 		/* but accept any length that fits if checksum okay */
 		if (!length || start + length > upper || !romchecksum(rom, length))
@@ -386,10 +393,8 @@ int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
 		   ____________________33__
 		   ______________________4_
 	*/
-	printk("sanitize start\n");
 	/* if there's only one memory region, don't bother */
 	if (*pnr_map < 2) {
-		printk("sanitize bail 0\n");
 		return -1;
 	}
 
@@ -398,7 +403,6 @@ int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
 	/* bail out if we find any unreasonable addresses in bios map */
 	for (i=0; i<old_nr; i++)
 		if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) {
-			printk("sanitize bail 1\n");
 			return -1;
 		}
 
@@ -494,7 +498,6 @@ int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
 	memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry));
 	*pnr_map = new_nr;
 
-	printk("sanitize end\n");
 	return 0;
 }
 
@@ -525,7 +528,6 @@ int __init copy_e820_map(struct e820entry * biosmap, int nr_map)
 		unsigned long long size = biosmap->size;
 		unsigned long long end = start + size;
 		unsigned long type = biosmap->type;
-		printk("copy_e820_map() start: %016Lx size: %016Lx end: %016Lx type: %ld\n", start, size, end, type);
 
 		/* Overflow in 64 bits? Ignore the memory map. */
 		if (start > end)
@@ -536,17 +538,11 @@ int __init copy_e820_map(struct e820entry * biosmap, int nr_map)
 		 * Not right. Fix it up.
 		 */
 		if (type == E820_RAM) {
-			printk("copy_e820_map() type is E820_RAM\n");
 			if (start < 0x100000ULL && end > 0xA0000ULL) {
-				printk("copy_e820_map() lies in range...\n");
-				if (start < 0xA0000ULL) {
-					printk("copy_e820_map() start < 0xA0000ULL\n");
+				if (start < 0xA0000ULL)
 					add_memory_region(start, 0xA0000ULL-start, type);
-				}
-				if (end <= 0x100000ULL) {
-					printk("copy_e820_map() end <= 0x100000ULL\n");
+				if (end <= 0x100000ULL)
 					continue;
-				}
 				start = 0x100000ULL;
 				size = end - start;
 			}
@@ -818,6 +814,26 @@ void __init limit_regions(unsigned long long size)
 	print_memory_map("limit_regions endfunc");
 }
 
+/*
+ * This function checks if any part of the range <start,end> is mapped
+ * with type.
+ */
+int
+e820_any_mapped(u64 start, u64 end, unsigned type)
+{
+	int i;
+	for (i = 0; i < e820.nr_map; i++) {
+		const struct e820entry *ei = &e820.map[i];
+		if (type && ei->type != type)
+			continue;
+		if (ei->addr >= end || ei->addr + ei->size <= start)
+			continue;
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(e820_any_mapped);
+
  /*
   * This function checks if the entire range <start,end> is mapped with type.
   *

arch/i386/kernel/efi.c

@@ -69,13 +69,11 @@ static void efi_call_phys_prelog(void) __acquires(efi_rt_lock)
 {
 	unsigned long cr4;
 	unsigned long temp;
-	struct Xgt_desc_struct *cpu_gdt_descr;
+	struct Xgt_desc_struct gdt_descr;
 
 	spin_lock(&efi_rt_lock);
 	local_irq_save(efi_rt_eflags);
 
-	cpu_gdt_descr = &per_cpu(cpu_gdt_descr, 0);
-
 	/*
 	 * If I don't have PSE, I should just duplicate two entries in page
 	 * directory. If I have PSE, I just need to duplicate one entry in
@@ -105,17 +103,19 @@ static void efi_call_phys_prelog(void) __acquires(efi_rt_lock)
 	 */
 	local_flush_tlb();
 
-	cpu_gdt_descr->address = __pa(cpu_gdt_descr->address);
-	load_gdt(cpu_gdt_descr);
+	gdt_descr.address = __pa(get_cpu_gdt_table(0));
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
 }
 
 static void efi_call_phys_epilog(void) __releases(efi_rt_lock)
 {
 	unsigned long cr4;
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, 0);
+	struct Xgt_desc_struct gdt_descr;
 
-	cpu_gdt_descr->address = (unsigned long)__va(cpu_gdt_descr->address);
-	load_gdt(cpu_gdt_descr);
+	gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
 
 	cr4 = read_cr4();
 

arch/i386/kernel/entry.S

@@ -15,7 +15,7 @@
  * I changed all the .align's to 4 (16 byte alignment), as that's faster
  * on a 486.
  *
- * Stack layout in 'ret_from_system_call':
+ * Stack layout in 'syscall_exit':
  * 	ptrace needs to have all regs on the stack.
  *	if the order here is changed, it needs to be
  *	updated in fork.c:copy_process, signal.c:do_signal,
@@ -132,7 +132,7 @@ VM_MASK		= 0x00020000
 	movl $(__USER_DS), %edx; \
 	movl %edx, %ds; \
 	movl %edx, %es; \
-	movl $(__KERNEL_PDA), %edx; \
+	movl $(__KERNEL_PERCPU), %edx; \
 	movl %edx, %fs
 
 #define RESTORE_INT_REGS \
@@ -305,16 +305,12 @@ sysenter_past_esp:
 	pushl $(__USER_CS)
 	CFI_ADJUST_CFA_OFFSET 4
 	/*CFI_REL_OFFSET cs, 0*/
-#ifndef CONFIG_COMPAT_VDSO
 	/*
 	 * Push current_thread_info()->sysenter_return to the stack.
 	 * A tiny bit of offset fixup is necessary - 4*4 means the 4 words
 	 * pushed above; +8 corresponds to copy_thread's esp0 setting.
 	 */
 	pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
-#else
-	pushl $SYSENTER_RETURN
-#endif
 	CFI_ADJUST_CFA_OFFSET 4
 	CFI_REL_OFFSET eip, 0
 
@@ -342,7 +338,7 @@ sysenter_past_esp:
 	jae syscall_badsys
 	call *sys_call_table(,%eax,4)
 	movl %eax,PT_EAX(%esp)
-	DISABLE_INTERRUPTS(CLBR_ECX|CLBR_EDX)
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
 	testw $_TIF_ALLWORK_MASK, %cx
@@ -560,9 +556,7 @@ END(syscall_badsys)
 
 #define FIXUP_ESPFIX_STACK \
 	/* since we are on a wrong stack, we cant make it a C code :( */ \
-	movl %fs:PDA_cpu, %ebx; \
-	PER_CPU(cpu_gdt_descr, %ebx); \
-	movl GDS_address(%ebx), %ebx; \
+	PER_CPU(gdt_page, %ebx); \
 	GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah); \
 	addl %esp, %eax; \
 	pushl $__KERNEL_DS; \
@@ -635,7 +629,7 @@ ENTRY(name)				\
 	SAVE_ALL;			\
 	TRACE_IRQS_OFF			\
 	movl %esp,%eax;			\
-	call smp_/**/name;		\
+	call smp_##name;		\
 	jmp ret_from_intr;		\
 	CFI_ENDPROC;			\
 ENDPROC(name)
@@ -643,11 +637,6 @@ ENDPROC(name)
 /* The include is where all of the SMP etc. interrupts come from */
 #include "entry_arch.h"
 
-/* This alternate entry is needed because we hijack the apic LVTT */
-#if defined(CONFIG_VMI) && defined(CONFIG_X86_LOCAL_APIC)
-BUILD_INTERRUPT(apic_vmi_timer_interrupt,LOCAL_TIMER_VECTOR)
-#endif
-
 KPROBE_ENTRY(page_fault)
 	RING0_EC_FRAME
 	pushl $do_page_fault
@@ -686,7 +675,7 @@ error_code:
 	pushl %fs
 	CFI_ADJUST_CFA_OFFSET 4
 	/*CFI_REL_OFFSET fs, 0*/
-	movl $(__KERNEL_PDA), %ecx
+	movl $(__KERNEL_PERCPU), %ecx
 	movl %ecx, %fs
 	UNWIND_ESPFIX_STACK
 	popl %ecx

arch/i386/kernel/head.S

@@ -34,17 +34,32 @@
 
 /*
  * This is how much memory *in addition to the memory covered up to
- * and including _end* we need mapped initially.  We need one bit for
- * each possible page, but only in low memory, which means
- * 2^32/4096/8 = 128K worst case (4G/4G split.)
+ * and including _end* we need mapped initially.
+ * We need:
+ *  - one bit for each possible page, but only in low memory, which means
+ *     2^32/4096/8 = 128K worst case (4G/4G split.)
+ *  - enough space to map all low memory, which means
+ *     (2^32/4096) / 1024 pages (worst case, non PAE)
+ *     (2^32/4096) / 512 + 4 pages (worst case for PAE)
+ *  - a few pages for allocator use before the kernel pagetable has
+ *     been set up
  *
  * Modulo rounding, each megabyte assigned here requires a kilobyte of
  * memory, which is currently unreclaimed.
  *
  * This should be a multiple of a page.
  */
-#define INIT_MAP_BEYOND_END	(128*1024)
+LOW_PAGES = 1<<(32-PAGE_SHIFT_asm)
 
+#if PTRS_PER_PMD > 1
+PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PMD) + PTRS_PER_PGD
+#else
+PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PGD)
+#endif
+BOOTBITMAP_SIZE = LOW_PAGES / 8
+ALLOCATOR_SLOP = 4
+
+INIT_MAP_BEYOND_END = BOOTBITMAP_SIZE + (PAGE_TABLE_SIZE + ALLOCATOR_SLOP)*PAGE_SIZE_asm
 
 /*
  * 32-bit kernel entrypoint; only used by the boot CPU.  On entry,
@@ -147,8 +162,7 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
 /*
  * Non-boot CPU entry point; entered from trampoline.S
  * We can't lgdt here, because lgdt itself uses a data segment, but
- * we know the trampoline has already loaded the boot_gdt_table GDT
- * for us.
+ * we know the trampoline has already loaded the boot_gdt for us.
  *
  * If cpu hotplug is not supported then this code can go in init section
  * which will be freed later
@@ -318,12 +332,12 @@ is386:	movl $2,%ecx		# set MP
 	movl %eax,%cr0
 
 	call check_x87
-	call setup_pda
 	lgdt early_gdt_descr
 	lidt idt_descr
 	ljmp $(__KERNEL_CS),$1f
 1:	movl $(__KERNEL_DS),%eax	# reload all the segment registers
 	movl %eax,%ss			# after changing gdt.
+	movl %eax,%fs			# gets reset once there's real percpu
 
 	movl $(__USER_DS),%eax		# DS/ES contains default USER segment
 	movl %eax,%ds
@@ -333,16 +347,17 @@ is386:	movl $2,%ecx		# set MP
 	movl %eax,%gs
 	lldt %ax
 
-	movl $(__KERNEL_PDA),%eax
-	mov  %eax,%fs
-
 	cld			# gcc2 wants the direction flag cleared at all times
 	pushl $0		# fake return address for unwinder
 #ifdef CONFIG_SMP
 	movb ready, %cl
 	movb $1, ready
 	cmpb $0,%cl		# the first CPU calls start_kernel
-	jne initialize_secondary # all other CPUs call initialize_secondary
+	je   1f
+	movl $(__KERNEL_PERCPU), %eax
+	movl %eax,%fs		# set this cpu's percpu
+	jmp initialize_secondary # all other CPUs call initialize_secondary
+1:
 #endif /* CONFIG_SMP */
 	jmp start_kernel
 
@@ -365,23 +380,6 @@ check_x87:
 	.byte 0xDB,0xE4		/* fsetpm for 287, ignored by 387 */
 	ret
 
-/*
- * Point the GDT at this CPU's PDA.  On boot this will be
- * cpu_gdt_table and boot_pda; for secondary CPUs, these will be
- * that CPU's GDT and PDA.
- */
-ENTRY(setup_pda)
-	/* get the PDA pointer */
-	movl start_pda, %eax
-
-	/* slot the PDA address into the GDT */
-	mov early_gdt_descr+2, %ecx
-	mov %ax, (__KERNEL_PDA+0+2)(%ecx)		/* base & 0x0000ffff */
-	shr $16, %eax
-	mov %al, (__KERNEL_PDA+4+0)(%ecx)		/* base & 0x00ff0000 */
-	mov %ah, (__KERNEL_PDA+4+3)(%ecx)		/* base & 0xff000000 */
-	ret
-
 /*
  *  setup_idt
  *
@@ -554,9 +552,6 @@ ENTRY(empty_zero_page)
  * This starts the data section.
  */
 .data
-ENTRY(start_pda)
-	.long boot_pda
-
 ENTRY(stack_start)
 	.long init_thread_union+THREAD_SIZE
 	.long __BOOT_DS
@@ -588,7 +583,7 @@ fault_msg:
 	.word 0				# 32 bit align gdt_desc.address
 boot_gdt_descr:
 	.word __BOOT_DS+7
-	.long boot_gdt_table - __PAGE_OFFSET
+	.long boot_gdt - __PAGE_OFFSET
 
 	.word 0				# 32-bit align idt_desc.address
 idt_descr:
@@ -599,67 +594,14 @@ idt_descr:
 	.word 0				# 32 bit align gdt_desc.address
 ENTRY(early_gdt_descr)
 	.word GDT_ENTRIES*8-1
-	.long cpu_gdt_table
+	.long per_cpu__gdt_page		/* Overwritten for secondary CPUs */
 
 /*
- * The boot_gdt_table must mirror the equivalent in setup.S and is
+ * The boot_gdt must mirror the equivalent in setup.S and is
  * used only for booting.
  */
 	.align L1_CACHE_BYTES
-ENTRY(boot_gdt_table)
+ENTRY(boot_gdt)
 	.fill GDT_ENTRY_BOOT_CS,8,0
 	.quad 0x00cf9a000000ffff	/* kernel 4GB code at 0x00000000 */
 	.quad 0x00cf92000000ffff	/* kernel 4GB data at 0x00000000 */
-
-/*
- * The Global Descriptor Table contains 28 quadwords, per-CPU.
- */
-	.align L1_CACHE_BYTES
-ENTRY(cpu_gdt_table)
-	.quad 0x0000000000000000	/* NULL descriptor */
-	.quad 0x0000000000000000	/* 0x0b reserved */
-	.quad 0x0000000000000000	/* 0x13 reserved */
-	.quad 0x0000000000000000	/* 0x1b reserved */
-	.quad 0x0000000000000000	/* 0x20 unused */
-	.quad 0x0000000000000000	/* 0x28 unused */
-	.quad 0x0000000000000000	/* 0x33 TLS entry 1 */
-	.quad 0x0000000000000000	/* 0x3b TLS entry 2 */
-	.quad 0x0000000000000000	/* 0x43 TLS entry 3 */
-	.quad 0x0000000000000000	/* 0x4b reserved */
-	.quad 0x0000000000000000	/* 0x53 reserved */
-	.quad 0x0000000000000000	/* 0x5b reserved */
-
-	.quad 0x00cf9a000000ffff	/* 0x60 kernel 4GB code at 0x00000000 */
-	.quad 0x00cf92000000ffff	/* 0x68 kernel 4GB data at 0x00000000 */
-	.quad 0x00cffa000000ffff	/* 0x73 user 4GB code at 0x00000000 */
-	.quad 0x00cff2000000ffff	/* 0x7b user 4GB data at 0x00000000 */
-
-	.quad 0x0000000000000000	/* 0x80 TSS descriptor */
-	.quad 0x0000000000000000	/* 0x88 LDT descriptor */
-
-	/*
-	 * Segments used for calling PnP BIOS have byte granularity.
-	 * They code segments and data segments have fixed 64k limits,
-	 * the transfer segment sizes are set at run time.
-	 */
-	.quad 0x00409a000000ffff	/* 0x90 32-bit code */
-	.quad 0x00009a000000ffff	/* 0x98 16-bit code */
-	.quad 0x000092000000ffff	/* 0xa0 16-bit data */
-	.quad 0x0000920000000000	/* 0xa8 16-bit data */
-	.quad 0x0000920000000000	/* 0xb0 16-bit data */
-
-	/*
-	 * The APM segments have byte granularity and their bases
-	 * are set at run time.  All have 64k limits.
-	 */
-	.quad 0x00409a000000ffff	/* 0xb8 APM CS    code */
-	.quad 0x00009a000000ffff	/* 0xc0 APM CS 16 code (16 bit) */
-	.quad 0x004092000000ffff	/* 0xc8 APM DS    data */
-
-	.quad 0x00c0920000000000	/* 0xd0 - ESPFIX SS */
-	.quad 0x00cf92000000ffff	/* 0xd8 - PDA */
-	.quad 0x0000000000000000	/* 0xe0 - unused */
-	.quad 0x0000000000000000	/* 0xe8 - unused */
-	.quad 0x0000000000000000	/* 0xf0 - unused */
-	.quad 0x0000000000000000	/* 0xf8 - GDT entry 31: double-fault TSS */
-

arch/i386/kernel/i386_ksyms.c

@@ -28,5 +28,3 @@ EXPORT_SYMBOL(__read_lock_failed);
 #endif
 
 EXPORT_SYMBOL(csum_partial);
-
-EXPORT_SYMBOL(_proxy_pda);

arch/i386/kernel/io_apic.c

@@ -35,6 +35,7 @@
 #include <linux/msi.h>
 #include <linux/htirq.h>
 #include <linux/freezer.h>
+#include <linux/kthread.h>
 
 #include <asm/io.h>
 #include <asm/smp.h>
@@ -661,8 +662,6 @@ static int balanced_irq(void *unused)
 	unsigned long prev_balance_time = jiffies;
 	long time_remaining = balanced_irq_interval;
 
-	daemonize("kirqd");
-	
 	/* push everything to CPU 0 to give us a starting point.  */
 	for (i = 0 ; i < NR_IRQS ; i++) {
 		irq_desc[i].pending_mask = cpumask_of_cpu(0);
@@ -722,10 +721,9 @@ static int __init balanced_irq_init(void)
 	}
 	
 	printk(KERN_INFO "Starting balanced_irq\n");
-	if (kernel_thread(balanced_irq, NULL, CLONE_KERNEL) >= 0) 
+	if (!IS_ERR(kthread_run(balanced_irq, NULL, "kirqd")))
 		return 0;
-	else 
-		printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq");
+	printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq");
 failed:
 	for_each_possible_cpu(i) {
 		kfree(irq_cpu_data[i].irq_delta);
@@ -1403,10 +1401,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 	enable_8259A_irq(0);
 }
 
-static inline void UNEXPECTED_IO_APIC(void)
-{
-}
-
 void __init print_IO_APIC(void)
 {
 	int apic, i;
@@ -1446,34 +1440,12 @@ void __init print_IO_APIC(void)
 	printk(KERN_DEBUG ".......    : physical APIC id: %02X\n", reg_00.bits.ID);
 	printk(KERN_DEBUG ".......    : Delivery Type: %X\n", reg_00.bits.delivery_type);
 	printk(KERN_DEBUG ".......    : LTS          : %X\n", reg_00.bits.LTS);
-	if (reg_00.bits.ID >= get_physical_broadcast())
-		UNEXPECTED_IO_APIC();
-	if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2)
-		UNEXPECTED_IO_APIC();
 
 	printk(KERN_DEBUG ".... register #01: %08X\n", reg_01.raw);
 	printk(KERN_DEBUG ".......     : max redirection entries: %04X\n", reg_01.bits.entries);
-	if (	(reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */
-		(reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */
-		(reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */
-		(reg_01.bits.entries != 0x1f) && /* dual Xeon boards */
-		(reg_01.bits.entries != 0x22) && /* bigger Xeon boards */
-		(reg_01.bits.entries != 0x2E) &&
-		(reg_01.bits.entries != 0x3F)
-	)
-		UNEXPECTED_IO_APIC();
 
 	printk(KERN_DEBUG ".......     : PRQ implemented: %X\n", reg_01.bits.PRQ);
 	printk(KERN_DEBUG ".......     : IO APIC version: %04X\n", reg_01.bits.version);
-	if (	(reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */
-		(reg_01.bits.version != 0x10) && /* oldest IO-APICs */
-		(reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */
-		(reg_01.bits.version != 0x13) && /* Xeon IO-APICs */
-		(reg_01.bits.version != 0x20)    /* Intel P64H (82806 AA) */
-	)
-		UNEXPECTED_IO_APIC();
-	if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2)
-		UNEXPECTED_IO_APIC();
 
 	/*
 	 * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02,
@@ -1483,8 +1455,6 @@ void __init print_IO_APIC(void)
 	if (reg_01.bits.version >= 0x10 && reg_02.raw != reg_01.raw) {
 		printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw);
 		printk(KERN_DEBUG ".......     : arbitration: %02X\n", reg_02.bits.arbitration);
-		if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2)
-			UNEXPECTED_IO_APIC();
 	}
 
 	/*
@@ -1496,8 +1466,6 @@ void __init print_IO_APIC(void)
 	    reg_03.raw != reg_01.raw) {
 		printk(KERN_DEBUG ".... register #03: %08X\n", reg_03.raw);
 		printk(KERN_DEBUG ".......     : Boot DT    : %X\n", reg_03.bits.boot_DT);
-		if (reg_03.bits.__reserved_1)
-			UNEXPECTED_IO_APIC();
 	}
 
 	printk(KERN_DEBUG ".... IRQ redirection table:\n");

arch/i386/kernel/ioport.c

@@ -16,6 +16,7 @@
 #include <linux/stddef.h>
 #include <linux/slab.h>
 #include <linux/thread_info.h>
+#include <linux/syscalls.h>
 
 /* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
 static void set_bitmap(unsigned long *bitmap, unsigned int base, unsigned int extent, int new_value)
@@ -113,7 +114,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 * Reset the owner so that a process switch will not set
 	 * tss->io_bitmap_base to IO_BITMAP_OFFSET.
 	 */
-	tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
+	tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
 	tss->io_bitmap_owner = NULL;
 
 	put_cpu();

arch/i386/kernel/irq.c

@@ -24,6 +24,9 @@
 DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_internodealigned_in_smp;
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
+
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
  * each architecture has to answer this themselves.

arch/i386/kernel/mpparse.c

@@ -477,7 +477,7 @@ static int __init smp_read_mpc(struct mp_config_table *mpc)
 		}
 		++mpc_record;
 	}
-	clustered_apic_check();
+	setup_apic_routing();
 	if (!num_processors)
 		printk(KERN_ERR "SMP mptable: no processors registered!\n");
 	return num_processors;

arch/i386/kernel/reboot_fixups.c

@@ -10,7 +10,7 @@
 
 #include <asm/delay.h>
 #include <linux/pci.h>
-#include <linux/reboot_fixups.h>
+#include <asm/reboot_fixups.h>
 
 static void cs5530a_warm_reset(struct pci_dev *dev)
 {

arch/i386/kernel/time.c

@@ -70,8 +70,6 @@
 
 #include <asm/i8259.h>
 
-int pit_latch_buggy;              /* extern */
-
 #include "do_timer.h"
 
 unsigned int cpu_khz;	/* Detected as we calibrate the TSC */

arch/i386/kernel/vsyscall.lds.S

@@ -7,7 +7,7 @@
 
 SECTIONS
 {
-  . = VDSO_PRELINK + SIZEOF_HEADERS;
+  . = VDSO_PRELINK_asm + SIZEOF_HEADERS;
 
   .hash           : { *(.hash) }		:text
   .gnu.hash       : { *(.gnu.hash) }
@@ -21,7 +21,7 @@ SECTIONS
      For the layouts to match, we need to skip more than enough
      space for the dynamic symbol table et al.  If this amount
      is insufficient, ld -shared will barf.  Just increase it here.  */
-  . = VDSO_PRELINK + 0x400;
+  . = VDSO_PRELINK_asm + 0x400;
 
   .text           : { *(.text) }		:text =0x90909090
   .note		  : { *(.note.*) }		:text :note

arch/i386/mach-generic/bigsmp.c

@@ -45,7 +45,7 @@ static struct dmi_system_id __initdata bigsmp_dmi_table[] = {
 };
 
 
-static int probe_bigsmp(void)
+static int __init probe_bigsmp(void)
 { 
 	if (def_to_bigsmp)
         	dmi_bigsmp = 1;