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

@@ -0,0 +1,66 @@
+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

@@ -1,7 +1,7 @@
 #
 # 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

@@ -0,0 +1,191 @@
+/*
+ *  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/perfctr-watchdog.c

@@ -0,0 +1,658 @@
+/* local apic based NMI watchdog for various CPUs.
+   This file also handles reservation of performance counters for coordination
+   with other users (like oprofile).
+
+   Note that these events normally don't tick when the CPU idles. This means
+   the frequency varies with CPU load.
+
+   Original code for K7/P6 written by Keith Owens */
+
+#include <linux/percpu.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/smp.h>
+#include <linux/nmi.h>
+#include <asm/apic.h>
+#include <asm/intel_arch_perfmon.h>
+
+struct nmi_watchdog_ctlblk {
+	unsigned int cccr_msr;
+	unsigned int perfctr_msr;  /* the MSR to reset in NMI handler */
+	unsigned int evntsel_msr;  /* the MSR to select the events to handle */
+};
+
+/* Interface defining a CPU specific perfctr watchdog */
+struct wd_ops {
+	int (*reserve)(void);
+	void (*unreserve)(void);
+	int (*setup)(unsigned nmi_hz);
+	void (*rearm)(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz);
+	void (*stop)(void *);
+	unsigned perfctr;
+	unsigned evntsel;
+	u64 checkbit;
+};
+
+static struct wd_ops *wd_ops;
+
+/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
+ * offset from MSR_P4_BSU_ESCR0.  It will be the max for all platforms (for now)
+ */
+#define NMI_MAX_COUNTER_BITS 66
+
+/* perfctr_nmi_owner tracks the ownership of the perfctr registers:
+ * evtsel_nmi_owner tracks the ownership of the event selection
+ * - different performance counters/ event selection may be reserved for
+ *   different subsystems this reservation system just tries to coordinate
+ *   things a little
+ */
+static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS);
+static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS);
+
+static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
+
+/* converts an msr to an appropriate reservation bit */
+static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
+{
+	return wd_ops ? msr - wd_ops->perfctr : 0;
+}
+
+/* converts an msr to an appropriate reservation bit */
+/* returns the bit offset of the event selection register */
+static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
+{
+	return wd_ops ? msr - wd_ops->evntsel : 0;
+}
+
+/* checks for a bit availability (hack for oprofile) */
+int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
+{
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	return (!test_bit(counter, perfctr_nmi_owner));
+}
+
+/* checks the an msr for availability */
+int avail_to_resrv_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	return (!test_bit(counter, perfctr_nmi_owner));
+}
+
+int reserve_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	if (!test_and_set_bit(counter, perfctr_nmi_owner))
+		return 1;
+	return 0;
+}
+
+void release_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	clear_bit(counter, perfctr_nmi_owner);
+}
+
+int reserve_evntsel_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_evntsel_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	if (!test_and_set_bit(counter, evntsel_nmi_owner))
+		return 1;
+	return 0;
+}
+
+void release_evntsel_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_evntsel_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	clear_bit(counter, evntsel_nmi_owner);
+}
+
+EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi);
+EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
+EXPORT_SYMBOL(reserve_perfctr_nmi);
+EXPORT_SYMBOL(release_perfctr_nmi);
+EXPORT_SYMBOL(reserve_evntsel_nmi);
+EXPORT_SYMBOL(release_evntsel_nmi);
+
+void disable_lapic_nmi_watchdog(void)
+{
+	BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
+
+	if (atomic_read(&nmi_active) <= 0)
+		return;
+
+	on_each_cpu(wd_ops->stop, NULL, 0, 1);
+	wd_ops->unreserve();
+
+	BUG_ON(atomic_read(&nmi_active) != 0);
+}
+
+void enable_lapic_nmi_watchdog(void)
+{
+	BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
+
+	/* are we already enabled */
+	if (atomic_read(&nmi_active) != 0)
+		return;
+
+	/* are we lapic aware */
+	if (!wd_ops)
+		return;
+	if (!wd_ops->reserve()) {
+		printk(KERN_ERR "NMI watchdog: cannot reserve perfctrs\n");
+		return;
+	}
+
+	on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
+	touch_nmi_watchdog();
+}
+
+/*
+ * Activate the NMI watchdog via the local APIC.
+ */
+
+static unsigned int adjust_for_32bit_ctr(unsigned int hz)
+{
+	u64 counter_val;
+	unsigned int retval = hz;
+
+	/*
+	 * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter
+	 * are writable, with higher bits sign extending from bit 31.
+	 * So, we can only program the counter with 31 bit values and
+	 * 32nd bit should be 1, for 33.. to be 1.
+	 * Find the appropriate nmi_hz
+	 */
+	counter_val = (u64)cpu_khz * 1000;
+	do_div(counter_val, retval);
+ 	if (counter_val > 0x7fffffffULL) {
+		u64 count = (u64)cpu_khz * 1000;
+		do_div(count, 0x7fffffffUL);
+		retval = count + 1;
+	}
+	return retval;
+}
+
+static void
+write_watchdog_counter(unsigned int perfctr_msr, const char *descr, unsigned nmi_hz)
+{
+	u64 count = (u64)cpu_khz * 1000;
+
+	do_div(count, nmi_hz);
+	if(descr)
+		Dprintk("setting %s to -0x%08Lx\n", descr, count);
+	wrmsrl(perfctr_msr, 0 - count);
+}
+
+static void write_watchdog_counter32(unsigned int perfctr_msr,
+		const char *descr, unsigned nmi_hz)
+{
+	u64 count = (u64)cpu_khz * 1000;
+
+	do_div(count, nmi_hz);
+	if(descr)
+		Dprintk("setting %s to -0x%08Lx\n", descr, count);
+	wrmsr(perfctr_msr, (u32)(-count), 0);
+}
+
+/* AMD K7/K8/Family10h/Family11h support. AMD keeps this interface
+   nicely stable so there is not much variety */
+
+#define K7_EVNTSEL_ENABLE	(1 << 22)
+#define K7_EVNTSEL_INT		(1 << 20)
+#define K7_EVNTSEL_OS		(1 << 17)
+#define K7_EVNTSEL_USR		(1 << 16)
+#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING	0x76
+#define K7_NMI_EVENT		K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING
+
+static int setup_k7_watchdog(unsigned nmi_hz)
+{
+	unsigned int perfctr_msr, evntsel_msr;
+	unsigned int evntsel;
+	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
+	perfctr_msr = MSR_K7_PERFCTR0;
+	evntsel_msr = MSR_K7_EVNTSEL0;
+
+	wrmsrl(perfctr_msr, 0UL);
+
+	evntsel = K7_EVNTSEL_INT
+		| K7_EVNTSEL_OS
+		| K7_EVNTSEL_USR
+		| K7_NMI_EVENT;
+
+	/* 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);
+
+	wd->perfctr_msr = perfctr_msr;
+	wd->evntsel_msr = evntsel_msr;
+	wd->cccr_msr = 0;  //unused
+	return 1;
+}
+
+static void single_msr_stop_watchdog(void *arg)
+{
+	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
+	wrmsr(wd->evntsel_msr, 0, 0);
+}
+
+static int single_msr_reserve(void)
+{
+	if (!reserve_perfctr_nmi(wd_ops->perfctr))
+		return 0;
+
+	if (!reserve_evntsel_nmi(wd_ops->evntsel)) {
+		release_perfctr_nmi(wd_ops->perfctr);
+		return 0;
+	}
+	return 1;
+}
+
+static void single_msr_unreserve(void)
+{
+	release_evntsel_nmi(wd_ops->perfctr);
+	release_perfctr_nmi(wd_ops->evntsel);
+}
+
+static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+{
+	/* start the cycle over again */
+	write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
+}
+
+static struct wd_ops k7_wd_ops = {
+	.reserve = single_msr_reserve,
+	.unreserve = single_msr_unreserve,
+	.setup = setup_k7_watchdog,
+	.rearm = single_msr_rearm,
+	.stop = single_msr_stop_watchdog,
+	.perfctr = MSR_K7_PERFCTR0,
+	.evntsel = MSR_K7_EVNTSEL0,
+	.checkbit = 1ULL<<63,
+};
+
+/* Intel Model 6 (PPro+,P2,P3,P-M,Core1) */
+
+#define P6_EVNTSEL0_ENABLE	(1 << 22)
+#define P6_EVNTSEL_INT		(1 << 20)
+#define P6_EVNTSEL_OS		(1 << 17)
+#define P6_EVNTSEL_USR		(1 << 16)
+#define P6_EVENT_CPU_CLOCKS_NOT_HALTED	0x79
+#define P6_NMI_EVENT		P6_EVENT_CPU_CLOCKS_NOT_HALTED
+
+static int setup_p6_watchdog(unsigned nmi_hz)
+{
+	unsigned int perfctr_msr, evntsel_msr;
+	unsigned int evntsel;
+	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
+	perfctr_msr = MSR_P6_PERFCTR0;
+	evntsel_msr = MSR_P6_EVNTSEL0;
+
+	wrmsrl(perfctr_msr, 0UL);
+
+	evntsel = P6_EVNTSEL_INT
+		| P6_EVNTSEL_OS
+		| P6_EVNTSEL_USR
+		| P6_NMI_EVENT;
+
+	/* setup the timer */
+	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);
+
+	wd->perfctr_msr = perfctr_msr;
+	wd->evntsel_msr = evntsel_msr;
+	wd->cccr_msr = 0;  //unused
+	return 1;
+}
+
+static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+{
+	/* P6 based Pentium M need to re-unmask
+	 * the apic vector but it doesn't hurt
+	 * other P6 variant.
+	 * ArchPerfom/Core Duo also needs this */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	/* P6/ARCH_PERFMON has 32 bit counter write */
+	write_watchdog_counter32(wd->perfctr_msr, NULL,nmi_hz);
+}
+
+static struct wd_ops p6_wd_ops = {
+	.reserve = single_msr_reserve,
+	.unreserve = single_msr_unreserve,
+	.setup = setup_p6_watchdog,
+	.rearm = p6_rearm,
+	.stop = single_msr_stop_watchdog,
+	.perfctr = MSR_P6_PERFCTR0,
+	.evntsel = MSR_P6_EVNTSEL0,
+	.checkbit = 1ULL<<39,
+};
+
+/* Intel P4 performance counters. By far the most complicated of all. */
+
+#define MSR_P4_MISC_ENABLE_PERF_AVAIL	(1<<7)
+#define P4_ESCR_EVENT_SELECT(N)	((N)<<25)
+#define P4_ESCR_OS		(1<<3)
+#define P4_ESCR_USR		(1<<2)
+#define P4_CCCR_OVF_PMI0	(1<<26)
+#define P4_CCCR_OVF_PMI1	(1<<27)
+#define P4_CCCR_THRESHOLD(N)	((N)<<20)
+#define P4_CCCR_COMPLEMENT	(1<<19)
+#define P4_CCCR_COMPARE		(1<<18)
+#define P4_CCCR_REQUIRED	(3<<16)
+#define P4_CCCR_ESCR_SELECT(N)	((N)<<13)
+#define P4_CCCR_ENABLE		(1<<12)
+#define P4_CCCR_OVF 		(1<<31)
+
+/* 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
+   max threshold. [IA32-Vol3, Section 14.9.9] */
+
+static int setup_p4_watchdog(unsigned nmi_hz)
+{
+	unsigned int perfctr_msr, evntsel_msr, cccr_msr;
+	unsigned int evntsel, cccr_val;
+	unsigned int misc_enable, dummy;
+	unsigned int ht_num;
+	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
+	rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy);
+	if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL))
+		return 0;
+
+#ifdef CONFIG_SMP
+	/* detect which hyperthread we are on */
+	if (smp_num_siblings == 2) {
+		unsigned int ebx, apicid;
+
+        	ebx = cpuid_ebx(1);
+	        apicid = (ebx >> 24) & 0xff;
+        	ht_num = apicid & 1;
+	} else
+#endif
+		ht_num = 0;
+
+	/* performance counters are shared resources
+	 * assign each hyperthread its own set
+	 * (re-use the ESCR0 register, seems safe
+	 * and keeps the cccr_val the same)
+	 */
+	if (!ht_num) {
+		/* logical cpu 0 */
+		perfctr_msr = MSR_P4_IQ_PERFCTR0;
+		evntsel_msr = MSR_P4_CRU_ESCR0;
+		cccr_msr = MSR_P4_IQ_CCCR0;
+		cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
+	} else {
+		/* logical cpu 1 */
+		perfctr_msr = MSR_P4_IQ_PERFCTR1;
+		evntsel_msr = MSR_P4_CRU_ESCR0;
+		cccr_msr = MSR_P4_IQ_CCCR1;
+		cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4);
+	}
+
+	evntsel = P4_ESCR_EVENT_SELECT(0x3F)
+	 	| P4_ESCR_OS
+		| P4_ESCR_USR;
+
+	cccr_val |= P4_CCCR_THRESHOLD(15)
+		 | P4_CCCR_COMPLEMENT
+		 | P4_CCCR_COMPARE
+		 | P4_CCCR_REQUIRED;
+
+	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;
+	return 1;
+}
+
+static void stop_p4_watchdog(void *arg)
+{
+	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+	wrmsr(wd->cccr_msr, 0, 0);
+	wrmsr(wd->evntsel_msr, 0, 0);
+}
+
+static int p4_reserve(void)
+{
+	if (!reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR0))
+		return 0;
+#ifdef CONFIG_SMP
+	if (smp_num_siblings > 1 && !reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR1))
+		goto fail1;
+#endif
+	if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0))
+		goto fail2;
+	/* RED-PEN why is ESCR1 not reserved here? */
+	return 1;
+ fail2:
+#ifdef CONFIG_SMP
+	if (smp_num_siblings > 1)
+		release_perfctr_nmi(MSR_P4_IQ_PERFCTR1);
+ fail1:
+#endif
+	release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
+	return 0;
+}
+
+static void p4_unreserve(void)
+{
+#ifdef CONFIG_SMP
+	if (smp_num_siblings > 1)
+		release_evntsel_nmi(MSR_P4_IQ_PERFCTR1);
+#endif
+	release_evntsel_nmi(MSR_P4_IQ_PERFCTR0);
+	release_perfctr_nmi(MSR_P4_CRU_ESCR0);
+}
+
+static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+{
+	unsigned dummy;
+	/*
+ 	 * P4 quirks:
+	 * - An overflown perfctr will assert its interrupt
+	 *   until the OVF flag in its CCCR is cleared.
+	 * - LVTPC is masked on interrupt and must be
+	 *   unmasked by the LVTPC handler.
+	 */
+	rdmsrl(wd->cccr_msr, dummy);
+	dummy &= ~P4_CCCR_OVF;
+	wrmsrl(wd->cccr_msr, dummy);
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	/* start the cycle over again */
+	write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
+}
+
+static struct wd_ops p4_wd_ops = {
+	.reserve = p4_reserve,
+	.unreserve = p4_unreserve,
+	.setup = setup_p4_watchdog,
+	.rearm = p4_rearm,
+	.stop = stop_p4_watchdog,
+	/* RED-PEN this is wrong for the other sibling */
+	.perfctr = MSR_P4_BPU_PERFCTR0,
+	.evntsel = MSR_P4_BSU_ESCR0,
+	.checkbit = 1ULL<<39,
+};
+
+/* Watchdog using the Intel architected PerfMon. Used for Core2 and hopefully
+   all future Intel CPUs. */
+
+#define ARCH_PERFMON_NMI_EVENT_SEL	ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
+#define ARCH_PERFMON_NMI_EVENT_UMASK	ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
+
+static int setup_intel_arch_watchdog(unsigned nmi_hz)
+{
+	unsigned int ebx;
+	union cpuid10_eax eax;
+	unsigned int unused;
+	unsigned int perfctr_msr, evntsel_msr;
+	unsigned int evntsel;
+	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * Unhalted Core Cycles Event or not.
+	 * NOTE: Corresponding bit = 0 in ebx indicates event present.
+	 */
+	cpuid(10, &(eax.full), &ebx, &unused, &unused);
+	if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
+	    (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
+		return 0;
+
+	perfctr_msr = MSR_ARCH_PERFMON_PERFCTR1;
+	evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL1;
+
+	wrmsrl(perfctr_msr, 0UL);
+
+	evntsel = ARCH_PERFMON_EVENTSEL_INT
+		| ARCH_PERFMON_EVENTSEL_OS
+		| ARCH_PERFMON_EVENTSEL_USR
+		| ARCH_PERFMON_NMI_EVENT_SEL
+		| ARCH_PERFMON_NMI_EVENT_UMASK;
+
+	/* setup the timer */
+	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
+	wd_ops->checkbit = 1ULL << (eax.split.bit_width - 1);
+	return 1;
+}
+
+static struct wd_ops intel_arch_wd_ops = {
+	.reserve = single_msr_reserve,
+	.unreserve = single_msr_unreserve,
+	.setup = setup_intel_arch_watchdog,
+	.rearm = p6_rearm,
+	.stop = single_msr_stop_watchdog,
+	.perfctr = MSR_ARCH_PERFMON_PERFCTR0,
+	.evntsel = MSR_ARCH_PERFMON_EVENTSEL0,
+};
+
+static void probe_nmi_watchdog(void)
+{
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 &&
+		    boot_cpu_data.x86 != 16)
+			return;
+		wd_ops = &k7_wd_ops;
+		break;
+	case X86_VENDOR_INTEL:
+		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+			wd_ops = &intel_arch_wd_ops;
+			break;
+		}
+		switch (boot_cpu_data.x86) {
+		case 6:
+			if (boot_cpu_data.x86_model > 0xd)
+				return;
+
+			wd_ops = &p6_wd_ops;
+			break;
+		case 15:
+			if (boot_cpu_data.x86_model > 0x4)
+				return;
+
+			wd_ops = &p4_wd_ops;
+			break;
+		default:
+			return;
+		}
+		break;
+	}
+}
+
+/* Interface to nmi.c */
+
+int lapic_watchdog_init(unsigned nmi_hz)
+{
+	if (!wd_ops) {
+		probe_nmi_watchdog();
+		if (!wd_ops)
+			return -1;
+	}
+
+	if (!(wd_ops->setup(nmi_hz))) {
+		printk(KERN_ERR "Cannot setup NMI watchdog on CPU %d\n",
+		       raw_smp_processor_id());
+		return -1;
+	}
+
+	return 0;
+}
+
+void lapic_watchdog_stop(void)
+{
+	if (wd_ops)
+		wd_ops->stop(NULL);
+}
+
+unsigned lapic_adjust_nmi_hz(unsigned hz)
+{
+	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+	if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
+	    wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1)
+		hz = adjust_for_32bit_ctr(hz);
+	return hz;
+}
+
+int lapic_wd_event(unsigned nmi_hz)
+{
+	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+	u64 ctr;
+	rdmsrl(wd->perfctr_msr, ctr);
+	if (ctr & wd_ops->checkbit) { /* perfctr still running? */
+		return 0;
+	}
+	wd_ops->rearm(wd, nmi_hz);
+	return 1;
+}
+
+int lapic_watchdog_ok(void)
+{
+	return wd_ops != NULL;
+}

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/nmi.c

@@ -20,7 +20,6 @@
 #include <linux/sysdev.h>
 #include <linux/sysctl.h>
 #include <linux/percpu.h>
-#include <linux/dmi.h>
 #include <linux/kprobes.h>
 #include <linux/cpumask.h>
 #include <linux/kernel_stat.h>
@@ -28,30 +27,14 @@
 #include <asm/smp.h>
 #include <asm/nmi.h>
 #include <asm/kdebug.h>
-#include <asm/intel_arch_perfmon.h>
 
 #include "mach_traps.h"
 
 int unknown_nmi_panic;
 int nmi_watchdog_enabled;
 
-/* perfctr_nmi_owner tracks the ownership of the perfctr registers:
- * evtsel_nmi_owner tracks the ownership of the event selection
- * - different performance counters/ event selection may be reserved for
- *   different subsystems this reservation system just tries to coordinate
- *   things a little
- */
-
-/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
- * offset from MSR_P4_BSU_ESCR0.  It will be the max for all platforms (for now)
- */
-#define NMI_MAX_COUNTER_BITS 66
-#define NMI_MAX_COUNTER_LONGS BITS_TO_LONGS(NMI_MAX_COUNTER_BITS)
-
-static DEFINE_PER_CPU(unsigned long, perfctr_nmi_owner[NMI_MAX_COUNTER_LONGS]);
-static DEFINE_PER_CPU(unsigned long, evntsel_nmi_owner[NMI_MAX_COUNTER_LONGS]);
-
 static cpumask_t backtrace_mask = CPU_MASK_NONE;
+
 /* nmi_active:
  * >0: the lapic NMI watchdog is active, but can be disabled
  * <0: the lapic NMI watchdog has not been set up, and cannot
@@ -63,206 +46,11 @@ atomic_t nmi_active = ATOMIC_INIT(0);		/* oprofile uses this */
 unsigned int nmi_watchdog = NMI_DEFAULT;
 static unsigned int nmi_hz = HZ;
 
-struct nmi_watchdog_ctlblk {
-	int enabled;
-	u64 check_bit;
-	unsigned int cccr_msr;
-	unsigned int perfctr_msr;  /* the MSR to reset in NMI handler */
-	unsigned int evntsel_msr;  /* the MSR to select the events to handle */
-};
-static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
+static DEFINE_PER_CPU(short, wd_enabled);
 
 /* local prototypes */
 static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
 
-extern void show_registers(struct pt_regs *regs);
-extern int unknown_nmi_panic;
-
-/* converts an msr to an appropriate reservation bit */
-static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
-{
-	/* returns the bit offset of the performance counter register */
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		return (msr - MSR_K7_PERFCTR0);
-	case X86_VENDOR_INTEL:
-		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
-			return (msr - MSR_ARCH_PERFMON_PERFCTR0);
-
-		switch (boot_cpu_data.x86) {
-		case 6:
-			return (msr - MSR_P6_PERFCTR0);
-		case 15:
-			return (msr - MSR_P4_BPU_PERFCTR0);
-		}
-	}
-	return 0;
-}
-
-/* converts an msr to an appropriate reservation bit */
-static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
-{
-	/* returns the bit offset of the event selection register */
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		return (msr - MSR_K7_EVNTSEL0);
-	case X86_VENDOR_INTEL:
-		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
-			return (msr - MSR_ARCH_PERFMON_EVENTSEL0);
-
-		switch (boot_cpu_data.x86) {
-		case 6:
-			return (msr - MSR_P6_EVNTSEL0);
-		case 15:
-			return (msr - MSR_P4_BSU_ESCR0);
-		}
-	}
-	return 0;
-}
-
-/* checks for a bit availability (hack for oprofile) */
-int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
-{
-	int cpu;
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-	for_each_possible_cpu (cpu) {
-		if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)[0]))
-			return 0;
-	}
-	return 1;
-}
-
-/* checks the an msr for availability */
-int avail_to_resrv_perfctr_nmi(unsigned int msr)
-{
-	unsigned int counter;
-	int cpu;
-
-	counter = nmi_perfctr_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
-	for_each_possible_cpu (cpu) {
-		if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)[0]))
-			return 0;
-	}
-	return 1;
-}
-
-static int __reserve_perfctr_nmi(int cpu, unsigned int msr)
-{
-	unsigned int counter;
-	if (cpu < 0)
-		cpu = smp_processor_id();
-
-	counter = nmi_perfctr_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
-	if (!test_and_set_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)[0]))
-		return 1;
-	return 0;
-}
-
-static void __release_perfctr_nmi(int cpu, unsigned int msr)
-{
-	unsigned int counter;
-	if (cpu < 0)
-		cpu = smp_processor_id();
-
-	counter = nmi_perfctr_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
-	clear_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)[0]);
-}
-
-int reserve_perfctr_nmi(unsigned int msr)
-{
-	int cpu, i;
-	for_each_possible_cpu (cpu) {
-		if (!__reserve_perfctr_nmi(cpu, msr)) {
-			for_each_possible_cpu (i) {
-				if (i >= cpu)
-					break;
-				__release_perfctr_nmi(i, msr);
-			}
-			return 0;
-		}
-	}
-	return 1;
-}
-
-void release_perfctr_nmi(unsigned int msr)
-{
-	int cpu;
-	for_each_possible_cpu (cpu) {
-		__release_perfctr_nmi(cpu, msr);
-	}
-}
-
-int __reserve_evntsel_nmi(int cpu, unsigned int msr)
-{
-	unsigned int counter;
-	if (cpu < 0)
-		cpu = smp_processor_id();
-
-	counter = nmi_evntsel_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
-	if (!test_and_set_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0]))
-		return 1;
-	return 0;
-}
-
-static void __release_evntsel_nmi(int cpu, unsigned int msr)
-{
-	unsigned int counter;
-	if (cpu < 0)
-		cpu = smp_processor_id();
-
-	counter = nmi_evntsel_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
-	clear_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0]);
-}
-
-int reserve_evntsel_nmi(unsigned int msr)
-{
-	int cpu, i;
-	for_each_possible_cpu (cpu) {
-		if (!__reserve_evntsel_nmi(cpu, msr)) {
-			for_each_possible_cpu (i) {
-				if (i >= cpu)
-					break;
-				__release_evntsel_nmi(i, msr);
-			}
-			return 0;
-		}
-	}
-	return 1;
-}
-
-void release_evntsel_nmi(unsigned int msr)
-{
-	int cpu;
-	for_each_possible_cpu (cpu) {
-		__release_evntsel_nmi(cpu, msr);
-	}
-}
-
-static __cpuinit inline int nmi_known_cpu(void)
-{
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6)
-			|| (boot_cpu_data.x86 == 16));
-	case X86_VENDOR_INTEL:
-		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
-			return 1;
-		else
-			return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6));
-	}
-	return 0;
-}
-
 static int endflag __initdata = 0;
 
 #ifdef CONFIG_SMP
@@ -284,28 +72,6 @@ static __init void nmi_cpu_busy(void *data)
 }
 #endif
 
-static unsigned int adjust_for_32bit_ctr(unsigned int hz)
-{
-	u64 counter_val;
-	unsigned int retval = hz;
-
-	/*
-	 * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter
-	 * are writable, with higher bits sign extending from bit 31.
-	 * So, we can only program the counter with 31 bit values and
-	 * 32nd bit should be 1, for 33.. to be 1.
-	 * Find the appropriate nmi_hz
-	 */
-	counter_val = (u64)cpu_khz * 1000;
-	do_div(counter_val, retval);
- 	if (counter_val > 0x7fffffffULL) {
-		u64 count = (u64)cpu_khz * 1000;
-		do_div(count, 0x7fffffffUL);
-		retval = count + 1;
-	}
-	return retval;
-}
-
 static int __init check_nmi_watchdog(void)
 {
 	unsigned int *prev_nmi_count;
@@ -338,14 +104,14 @@ static int __init check_nmi_watchdog(void)
 		if (!cpu_isset(cpu, cpu_callin_map))
 			continue;
 #endif
-		if (!per_cpu(nmi_watchdog_ctlblk, cpu).enabled)
+		if (!per_cpu(wd_enabled, cpu))
 			continue;
 		if (nmi_count(cpu) - prev_nmi_count[cpu] <= 5) {
 			printk("CPU#%d: NMI appears to be stuck (%d->%d)!\n",
 				cpu,
 				prev_nmi_count[cpu],
 				nmi_count(cpu));
-			per_cpu(nmi_watchdog_ctlblk, cpu).enabled = 0;
+			per_cpu(wd_enabled, cpu) = 0;
 			atomic_dec(&nmi_active);
 		}
 	}
@@ -359,16 +125,8 @@ static int __init check_nmi_watchdog(void)
 
 	/* now that we know it works we can reduce NMI frequency to
 	   something more reasonable; makes a difference in some configs */
-	if (nmi_watchdog == NMI_LOCAL_APIC) {
-		struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-		nmi_hz = 1;
-
-		if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
-		    wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
-			nmi_hz = adjust_for_32bit_ctr(nmi_hz);
-		}
-	}
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+		nmi_hz = lapic_adjust_nmi_hz(1);
 
 	kfree(prev_nmi_count);
 	return 0;
@@ -391,85 +149,8 @@ static int __init setup_nmi_watchdog(char *str)
 
 __setup("nmi_watchdog=", setup_nmi_watchdog);
 
-static void disable_lapic_nmi_watchdog(void)
-{
-	BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
-	if (atomic_read(&nmi_active) <= 0)
-		return;
-
-	on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);
-
-	BUG_ON(atomic_read(&nmi_active) != 0);
-}
-
-static void enable_lapic_nmi_watchdog(void)
-{
-	BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
-	/* are we already enabled */
-	if (atomic_read(&nmi_active) != 0)
-		return;
-
-	/* are we lapic aware */
-	if (nmi_known_cpu() <= 0)
-		return;
 
-	on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
-	touch_nmi_watchdog();
-}
-
-void disable_timer_nmi_watchdog(void)
-{
-	BUG_ON(nmi_watchdog != NMI_IO_APIC);
-
-	if (atomic_read(&nmi_active) <= 0)
-		return;
-
-	disable_irq(0);
-	on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);
-
-	BUG_ON(atomic_read(&nmi_active) != 0);
-}
-
-void enable_timer_nmi_watchdog(void)
-{
-	BUG_ON(nmi_watchdog != NMI_IO_APIC);
-
-	if (atomic_read(&nmi_active) == 0) {
-		touch_nmi_watchdog();
-		on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
-		enable_irq(0);
-	}
-}
-
-static void __acpi_nmi_disable(void *__unused)
-{
-	apic_write_around(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
-}
-
-/*
- * Disable timer based NMIs on all CPUs:
- */
-void acpi_nmi_disable(void)
-{
-	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
-		on_each_cpu(__acpi_nmi_disable, NULL, 0, 1);
-}
-
-static void __acpi_nmi_enable(void *__unused)
-{
-	apic_write_around(APIC_LVT0, APIC_DM_NMI);
-}
-
-/*
- * Enable timer based NMIs on all CPUs:
- */
-void acpi_nmi_enable(void)
-{
-	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
-		on_each_cpu(__acpi_nmi_enable, NULL, 0, 1);
-}
+/* Suspend/resume support */
 
 #ifdef CONFIG_PM
 
@@ -516,7 +197,7 @@ static int __init init_lapic_nmi_sysfs(void)
 	if (nmi_watchdog != NMI_LOCAL_APIC)
 		return 0;
 
-	if ( atomic_read(&nmi_active) < 0 )
+	if (atomic_read(&nmi_active) < 0)
 		return 0;
 
 	error = sysdev_class_register(&nmi_sysclass);
@@ -529,433 +210,69 @@ late_initcall(init_lapic_nmi_sysfs);
 
 #endif	/* CONFIG_PM */
 
-/*
- * Activate the NMI watchdog via the local APIC.
- * Original code written by Keith Owens.
- */
-
-static void write_watchdog_counter(unsigned int perfctr_msr, const char *descr)
-{
-	u64 count = (u64)cpu_khz * 1000;
-
-	do_div(count, nmi_hz);
-	if(descr)
-		Dprintk("setting %s to -0x%08Lx\n", descr, count);
-	wrmsrl(perfctr_msr, 0 - count);
-}
-
-static void write_watchdog_counter32(unsigned int perfctr_msr,
-		const char *descr)
-{
-	u64 count = (u64)cpu_khz * 1000;
-
-	do_div(count, nmi_hz);
-	if(descr)
-		Dprintk("setting %s to -0x%08Lx\n", descr, count);
-	wrmsr(perfctr_msr, (u32)(-count), 0);
-}
-
-/* Note that these events don't tick when the CPU idles. This means
-   the frequency varies with CPU load. */
-
-#define K7_EVNTSEL_ENABLE	(1 << 22)
-#define K7_EVNTSEL_INT		(1 << 20)
-#define K7_EVNTSEL_OS		(1 << 17)
-#define K7_EVNTSEL_USR		(1 << 16)
-#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING	0x76
-#define K7_NMI_EVENT		K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING
-
-static int setup_k7_watchdog(void)
-{
-	unsigned int perfctr_msr, evntsel_msr;
-	unsigned int evntsel;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	perfctr_msr = MSR_K7_PERFCTR0;
-	evntsel_msr = MSR_K7_EVNTSEL0;
-	if (!__reserve_perfctr_nmi(-1, perfctr_msr))
-		goto fail;
-
-	if (!__reserve_evntsel_nmi(-1, evntsel_msr))
-		goto fail1;
-
-	wrmsrl(perfctr_msr, 0UL);
-
-	evntsel = K7_EVNTSEL_INT
-		| K7_EVNTSEL_OS
-		| K7_EVNTSEL_USR
-		| K7_NMI_EVENT;
-
-	/* setup the timer */
-	wrmsr(evntsel_msr, evntsel, 0);
-	write_watchdog_counter(perfctr_msr, "K7_PERFCTR0");
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= K7_EVNTSEL_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
-
-	wd->perfctr_msr = perfctr_msr;
-	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  //unused
-	wd->check_bit = 1ULL<<63;
-	return 1;
-fail1:
-	__release_perfctr_nmi(-1, perfctr_msr);
-fail:
-	return 0;
-}
-
-static void stop_k7_watchdog(void)
-{
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	wrmsr(wd->evntsel_msr, 0, 0);
-
-	__release_evntsel_nmi(-1, wd->evntsel_msr);
-	__release_perfctr_nmi(-1, wd->perfctr_msr);
-}
-
-#define P6_EVNTSEL0_ENABLE	(1 << 22)
-#define P6_EVNTSEL_INT		(1 << 20)
-#define P6_EVNTSEL_OS		(1 << 17)
-#define P6_EVNTSEL_USR		(1 << 16)
-#define P6_EVENT_CPU_CLOCKS_NOT_HALTED	0x79
-#define P6_NMI_EVENT		P6_EVENT_CPU_CLOCKS_NOT_HALTED
-
-static int setup_p6_watchdog(void)
-{
-	unsigned int perfctr_msr, evntsel_msr;
-	unsigned int evntsel;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	perfctr_msr = MSR_P6_PERFCTR0;
-	evntsel_msr = MSR_P6_EVNTSEL0;
-	if (!__reserve_perfctr_nmi(-1, perfctr_msr))
-		goto fail;
-
-	if (!__reserve_evntsel_nmi(-1, evntsel_msr))
-		goto fail1;
-
-	wrmsrl(perfctr_msr, 0UL);
-
-	evntsel = P6_EVNTSEL_INT
-		| P6_EVNTSEL_OS
-		| P6_EVNTSEL_USR
-		| P6_NMI_EVENT;
-
-	/* setup the timer */
-	wrmsr(evntsel_msr, evntsel, 0);
-	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
-	write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0");
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= P6_EVNTSEL0_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
-
-	wd->perfctr_msr = perfctr_msr;
-	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  //unused
-	wd->check_bit = 1ULL<<39;
-	return 1;
-fail1:
-	__release_perfctr_nmi(-1, perfctr_msr);
-fail:
-	return 0;
-}
-
-static void stop_p6_watchdog(void)
-{
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	wrmsr(wd->evntsel_msr, 0, 0);
-
-	__release_evntsel_nmi(-1, wd->evntsel_msr);
-	__release_perfctr_nmi(-1, wd->perfctr_msr);
-}
-
-/* Note that these events don't tick when the CPU idles. This means
-   the frequency varies with CPU load. */
-
-#define MSR_P4_MISC_ENABLE_PERF_AVAIL	(1<<7)
-#define P4_ESCR_EVENT_SELECT(N)	((N)<<25)
-#define P4_ESCR_OS		(1<<3)
-#define P4_ESCR_USR		(1<<2)
-#define P4_CCCR_OVF_PMI0	(1<<26)
-#define P4_CCCR_OVF_PMI1	(1<<27)
-#define P4_CCCR_THRESHOLD(N)	((N)<<20)
-#define P4_CCCR_COMPLEMENT	(1<<19)
-#define P4_CCCR_COMPARE		(1<<18)
-#define P4_CCCR_REQUIRED	(3<<16)
-#define P4_CCCR_ESCR_SELECT(N)	((N)<<13)
-#define P4_CCCR_ENABLE		(1<<12)
-#define P4_CCCR_OVF 		(1<<31)
-/* 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
-   max threshold. [IA32-Vol3, Section 14.9.9] */
-
-static int setup_p4_watchdog(void)
+static void __acpi_nmi_enable(void *__unused)
 {
-	unsigned int perfctr_msr, evntsel_msr, cccr_msr;
-	unsigned int evntsel, cccr_val;
-	unsigned int misc_enable, dummy;
-	unsigned int ht_num;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy);
-	if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL))
-		return 0;
-
-#ifdef CONFIG_SMP
-	/* detect which hyperthread we are on */
-	if (smp_num_siblings == 2) {
-		unsigned int ebx, apicid;
-
-        	ebx = cpuid_ebx(1);
-	        apicid = (ebx >> 24) & 0xff;
-        	ht_num = apicid & 1;
-	} else
-#endif
-		ht_num = 0;
-
-	/* performance counters are shared resources
-	 * assign each hyperthread its own set
-	 * (re-use the ESCR0 register, seems safe
-	 * and keeps the cccr_val the same)
-	 */
-	if (!ht_num) {
-		/* logical cpu 0 */
-		perfctr_msr = MSR_P4_IQ_PERFCTR0;
-		evntsel_msr = MSR_P4_CRU_ESCR0;
-		cccr_msr = MSR_P4_IQ_CCCR0;
-		cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
-	} else {
-		/* logical cpu 1 */
-		perfctr_msr = MSR_P4_IQ_PERFCTR1;
-		evntsel_msr = MSR_P4_CRU_ESCR0;
-		cccr_msr = MSR_P4_IQ_CCCR1;
-		cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4);
-	}
-
-	if (!__reserve_perfctr_nmi(-1, perfctr_msr))
-		goto fail;
-
-	if (!__reserve_evntsel_nmi(-1, evntsel_msr))
-		goto fail1;
-
-	evntsel = P4_ESCR_EVENT_SELECT(0x3F)
-	 	| P4_ESCR_OS
-		| P4_ESCR_USR;
-
-	cccr_val |= P4_CCCR_THRESHOLD(15)
-		 | P4_CCCR_COMPLEMENT
-		 | P4_CCCR_COMPARE
-		 | P4_CCCR_REQUIRED;
-
-	wrmsr(evntsel_msr, evntsel, 0);
-	wrmsr(cccr_msr, cccr_val, 0);
-	write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0");
-	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;
-	wd->check_bit = 1ULL<<39;
-	return 1;
-fail1:
-	__release_perfctr_nmi(-1, perfctr_msr);
-fail:
-	return 0;
+	apic_write_around(APIC_LVT0, APIC_DM_NMI);
 }
 
-static void stop_p4_watchdog(void)
+/*
+ * Enable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_enable(void)
 {
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	wrmsr(wd->cccr_msr, 0, 0);
-	wrmsr(wd->evntsel_msr, 0, 0);
-
-	__release_evntsel_nmi(-1, wd->evntsel_msr);
-	__release_perfctr_nmi(-1, wd->perfctr_msr);
+	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
+		on_each_cpu(__acpi_nmi_enable, NULL, 0, 1);
 }
 
-#define ARCH_PERFMON_NMI_EVENT_SEL	ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
-#define ARCH_PERFMON_NMI_EVENT_UMASK	ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
-
-static int setup_intel_arch_watchdog(void)
+static void __acpi_nmi_disable(void *__unused)
 {
-	unsigned int ebx;
-	union cpuid10_eax eax;
-	unsigned int unused;
-	unsigned int perfctr_msr, evntsel_msr;
-	unsigned int evntsel;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	/*
-	 * Check whether the Architectural PerfMon supports
-	 * Unhalted Core Cycles Event or not.
-	 * NOTE: Corresponding bit = 0 in ebx indicates event present.
-	 */
-	cpuid(10, &(eax.full), &ebx, &unused, &unused);
-	if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
-	    (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
-		goto fail;
-
-	perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
-	evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0;
-
-	if (!__reserve_perfctr_nmi(-1, perfctr_msr))
-		goto fail;
-
-	if (!__reserve_evntsel_nmi(-1, evntsel_msr))
-		goto fail1;
-
-	wrmsrl(perfctr_msr, 0UL);
-
-	evntsel = ARCH_PERFMON_EVENTSEL_INT
-		| ARCH_PERFMON_EVENTSEL_OS
-		| ARCH_PERFMON_EVENTSEL_USR
-		| ARCH_PERFMON_NMI_EVENT_SEL
-		| ARCH_PERFMON_NMI_EVENT_UMASK;
-
-	/* setup the timer */
-	wrmsr(evntsel_msr, evntsel, 0);
-	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
-	write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0");
-	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
-	wd->check_bit = 1ULL << (eax.split.bit_width - 1);
-	return 1;
-fail1:
-	__release_perfctr_nmi(-1, perfctr_msr);
-fail:
-	return 0;
+	apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
 }
 
-static void stop_intel_arch_watchdog(void)
+/*
+ * Disable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_disable(void)
 {
-	unsigned int ebx;
-	union cpuid10_eax eax;
-	unsigned int unused;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	/*
-	 * Check whether the Architectural PerfMon supports
-	 * Unhalted Core Cycles Event or not.
-	 * NOTE: Corresponding bit = 0 in ebx indicates event present.
-	 */
-	cpuid(10, &(eax.full), &ebx, &unused, &unused);
-	if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
-	    (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
-		return;
-
-	wrmsr(wd->evntsel_msr, 0, 0);
-	__release_evntsel_nmi(-1, wd->evntsel_msr);
-	__release_perfctr_nmi(-1, wd->perfctr_msr);
+	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
+		on_each_cpu(__acpi_nmi_disable, NULL, 0, 1);
 }
 
 void setup_apic_nmi_watchdog (void *unused)
 {
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	/* only support LOCAL and IO APICs for now */
-	if ((nmi_watchdog != NMI_LOCAL_APIC) &&
-	    (nmi_watchdog != NMI_IO_APIC))
-	    	return;
-
-	if (wd->enabled == 1)
-		return;
+	if (__get_cpu_var(wd_enabled))
+ 		return;
 
 	/* cheap hack to support suspend/resume */
 	/* if cpu0 is not active neither should the other cpus */
 	if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0))
 		return;
 
-	if (nmi_watchdog == NMI_LOCAL_APIC) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_AMD:
-			if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 &&
-				boot_cpu_data.x86 != 16)
-				return;
-			if (!setup_k7_watchdog())
-				return;
-			break;
-		case X86_VENDOR_INTEL:
-			if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-				if (!setup_intel_arch_watchdog())
-					return;
-				break;
-			}
-			switch (boot_cpu_data.x86) {
-			case 6:
-				if (boot_cpu_data.x86_model > 0xd)
-					return;
-
-				if (!setup_p6_watchdog())
-					return;
-				break;
-			case 15:
-				if (boot_cpu_data.x86_model > 0x4)
-					return;
-
-				if (!setup_p4_watchdog())
-					return;
-				break;
-			default:
-				return;
-			}
-			break;
-		default:
+	switch (nmi_watchdog) {
+	case NMI_LOCAL_APIC:
+		__get_cpu_var(wd_enabled) = 1; /* enable it before to avoid race with handler */
+		if (lapic_watchdog_init(nmi_hz) < 0) {
+			__get_cpu_var(wd_enabled) = 0;
 			return;
 		}
+		/* FALL THROUGH */
+	case NMI_IO_APIC:
+		__get_cpu_var(wd_enabled) = 1;
+		atomic_inc(&nmi_active);
 	}
-	wd->enabled = 1;
-	atomic_inc(&nmi_active);
 }
 
 void stop_apic_nmi_watchdog(void *unused)
 {
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
 	/* only support LOCAL and IO APICs for now */
 	if ((nmi_watchdog != NMI_LOCAL_APIC) &&
 	    (nmi_watchdog != NMI_IO_APIC))
 	    	return;
-
-	if (wd->enabled == 0)
+	if (__get_cpu_var(wd_enabled) == 0)
 		return;
-
-	if (nmi_watchdog == NMI_LOCAL_APIC) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_AMD:
-			stop_k7_watchdog();
-			break;
-		case X86_VENDOR_INTEL:
-			if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-				stop_intel_arch_watchdog();
-				break;
-			}
-			switch (boot_cpu_data.x86) {
-			case 6:
-				if (boot_cpu_data.x86_model > 0xd)
-					break;
-				stop_p6_watchdog();
-				break;
-			case 15:
-				if (boot_cpu_data.x86_model > 0x4)
-					break;
-				stop_p4_watchdog();
-				break;
-			}
-			break;
-		default:
-			return;
-		}
-	}
-	wd->enabled = 0;
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+		lapic_watchdog_stop();
+	__get_cpu_var(wd_enabled) = 0;
 	atomic_dec(&nmi_active);
 }
 
@@ -1011,8 +328,6 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 	unsigned int sum;
 	int touched = 0;
 	int cpu = smp_processor_id();
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-	u64 dummy;
 	int rc=0;
 
 	/* check for other users first */
@@ -1055,53 +370,20 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 		alert_counter[cpu] = 0;
 	}
 	/* see if the nmi watchdog went off */
-	if (wd->enabled) {
-		if (nmi_watchdog == NMI_LOCAL_APIC) {
-			rdmsrl(wd->perfctr_msr, dummy);
-			if (dummy & wd->check_bit){
-				/* this wasn't a watchdog timer interrupt */
-				goto done;
-			}
-
-			/* only Intel P4 uses the cccr msr */
-	 		if (wd->cccr_msr != 0) {
-	 			/*
-	 			 * P4 quirks:
-	 			 * - An overflown perfctr will assert its interrupt
-	 			 *   until the OVF flag in its CCCR is cleared.
-	 			 * - LVTPC is masked on interrupt and must be
-	 			 *   unmasked by the LVTPC handler.
-	 			 */
-				rdmsrl(wd->cccr_msr, dummy);
-				dummy &= ~P4_CCCR_OVF;
-	 			wrmsrl(wd->cccr_msr, dummy);
-	 			apic_write(APIC_LVTPC, APIC_DM_NMI);
-				/* start the cycle over again */
-				write_watchdog_counter(wd->perfctr_msr, NULL);
-	 		}
-			else if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
-				 wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
-				/* P6 based Pentium M need to re-unmask
-				 * the apic vector but it doesn't hurt
-				 * other P6 variant.
-				 * ArchPerfom/Core Duo also needs this */
-				apic_write(APIC_LVTPC, APIC_DM_NMI);
-				/* P6/ARCH_PERFMON has 32 bit counter write */
-				write_watchdog_counter32(wd->perfctr_msr, NULL);
-			} else {
-				/* start the cycle over again */
-				write_watchdog_counter(wd->perfctr_msr, NULL);
-			}
-			rc = 1;
-		} else if (nmi_watchdog == NMI_IO_APIC) {
-			/* don't know how to accurately check for this.
-			 * just assume it was a watchdog timer interrupt
-			 * This matches the old behaviour.
-			 */
-			rc = 1;
-		}
+	if (!__get_cpu_var(wd_enabled))
+		return rc;
+	switch (nmi_watchdog) {
+	case NMI_LOCAL_APIC:
+		rc |= lapic_wd_event(nmi_hz);
+		break;
+	case NMI_IO_APIC:
+		/* don't know how to accurately check for this.
+		 * just assume it was a watchdog timer interrupt
+		 * This matches the old behaviour.
+		 */
+		rc = 1;
+		break;
 	}
-done:
 	return rc;
 }
 
@@ -1146,7 +428,7 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
 	}
 
 	if (nmi_watchdog == NMI_DEFAULT) {
-		if (nmi_known_cpu() > 0)
+		if (lapic_watchdog_ok())
 			nmi_watchdog = NMI_LOCAL_APIC;
 		else
 			nmi_watchdog = NMI_IO_APIC;
@@ -1182,11 +464,3 @@ void __trigger_all_cpu_backtrace(void)
 
 EXPORT_SYMBOL(nmi_active);
 EXPORT_SYMBOL(nmi_watchdog);
-EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi);
-EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
-EXPORT_SYMBOL(reserve_perfctr_nmi);
-EXPORT_SYMBOL(release_perfctr_nmi);
-EXPORT_SYMBOL(reserve_evntsel_nmi);
-EXPORT_SYMBOL(release_evntsel_nmi);
-EXPORT_SYMBOL(disable_timer_nmi_watchdog);
-EXPORT_SYMBOL(enable_timer_nmi_watchdog);

arch/i386/kernel/paravirt.c

@@ -20,6 +20,7 @@
 #include <linux/efi.h>
 #include <linux/bcd.h>
 #include <linux/start_kernel.h>
+#include <linux/highmem.h>
 
 #include <asm/bug.h>
 #include <asm/paravirt.h>
@@ -35,7 +36,7 @@
 #include <asm/timer.h>
 
 /* nop stub */
-static void native_nop(void)
+void _paravirt_nop(void)
 {
 }
 
@@ -54,331 +55,148 @@ char *memory_setup(void)
 #define DEF_NATIVE(name, code)					\
 	extern const char start_##name[], end_##name[];		\
 	asm("start_" #name ": " code "; end_" #name ":")
-DEF_NATIVE(cli, "cli");
-DEF_NATIVE(sti, "sti");
-DEF_NATIVE(popf, "push %eax; popf");
-DEF_NATIVE(pushf, "pushf; pop %eax");
-DEF_NATIVE(pushf_cli, "pushf; pop %eax; cli");
+
+DEF_NATIVE(irq_disable, "cli");
+DEF_NATIVE(irq_enable, "sti");
+DEF_NATIVE(restore_fl, "push %eax; popf");
+DEF_NATIVE(save_fl, "pushf; pop %eax");
 DEF_NATIVE(iret, "iret");
-DEF_NATIVE(sti_sysexit, "sti; sysexit");
+DEF_NATIVE(irq_enable_sysexit, "sti; sysexit");
+DEF_NATIVE(read_cr2, "mov %cr2, %eax");
+DEF_NATIVE(write_cr3, "mov %eax, %cr3");
+DEF_NATIVE(read_cr3, "mov %cr3, %eax");
+DEF_NATIVE(clts, "clts");
+DEF_NATIVE(read_tsc, "rdtsc");
 
-static const struct native_insns
-{
-	const char *start, *end;
-} native_insns[] = {
-	[PARAVIRT_IRQ_DISABLE] = { start_cli, end_cli },
-	[PARAVIRT_IRQ_ENABLE] = { start_sti, end_sti },
-	[PARAVIRT_RESTORE_FLAGS] = { start_popf, end_popf },
-	[PARAVIRT_SAVE_FLAGS] = { start_pushf, end_pushf },
-	[PARAVIRT_SAVE_FLAGS_IRQ_DISABLE] = { start_pushf_cli, end_pushf_cli },
-	[PARAVIRT_INTERRUPT_RETURN] = { start_iret, end_iret },
-	[PARAVIRT_STI_SYSEXIT] = { start_sti_sysexit, end_sti_sysexit },
-};
+DEF_NATIVE(ud2a, "ud2a");
 
 static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len)
 {
-	unsigned int insn_len;
-
-	/* Don't touch it if we don't have a replacement */
-	if (type >= ARRAY_SIZE(native_insns) || !native_insns[type].start)
-		return len;
-
-	insn_len = native_insns[type].end - native_insns[type].start;
-
-	/* Similarly if we can't fit replacement. */
-	if (len < insn_len)
-		return len;
+	const unsigned char *start, *end;
+	unsigned ret;
+
+	switch(type) {
+#define SITE(x)	case PARAVIRT_PATCH(x):	start = start_##x; end = end_##x; goto patch_site
+		SITE(irq_disable);
+		SITE(irq_enable);
+		SITE(restore_fl);
+		SITE(save_fl);
+		SITE(iret);
+		SITE(irq_enable_sysexit);
+		SITE(read_cr2);
+		SITE(read_cr3);
+		SITE(write_cr3);
+		SITE(clts);
+		SITE(read_tsc);
+#undef SITE
+
+	patch_site:
+		ret = paravirt_patch_insns(insns, len, start, end);
+		break;
 
-	memcpy(insns, native_insns[type].start, insn_len);
-	return insn_len;
-}
+	case PARAVIRT_PATCH(make_pgd):
+	case PARAVIRT_PATCH(make_pte):
+	case PARAVIRT_PATCH(pgd_val):
+	case PARAVIRT_PATCH(pte_val):
+#ifdef CONFIG_X86_PAE
+	case PARAVIRT_PATCH(make_pmd):
+	case PARAVIRT_PATCH(pmd_val):
+#endif
+		/* These functions end up returning exactly what
+		   they're passed, in the same registers. */
+		ret = paravirt_patch_nop();
+		break;
 
-static unsigned long native_get_debugreg(int regno)
-{
-	unsigned long val = 0; 	/* Damn you, gcc! */
-
-	switch (regno) {
-	case 0:
-		asm("movl %%db0, %0" :"=r" (val)); break;
-	case 1:
-		asm("movl %%db1, %0" :"=r" (val)); break;
-	case 2:
-		asm("movl %%db2, %0" :"=r" (val)); break;
-	case 3:
-		asm("movl %%db3, %0" :"=r" (val)); break;
-	case 6:
-		asm("movl %%db6, %0" :"=r" (val)); break;
-	case 7:
-		asm("movl %%db7, %0" :"=r" (val)); break;
 	default:
-		BUG();
-	}
-	return val;
-}
-
-static void native_set_debugreg(int regno, unsigned long value)
-{
-	switch (regno) {
-	case 0:
-		asm("movl %0,%%db0"	: /* no output */ :"r" (value));
-		break;
-	case 1:
-		asm("movl %0,%%db1"	: /* no output */ :"r" (value));
-		break;
-	case 2:
-		asm("movl %0,%%db2"	: /* no output */ :"r" (value));
+		ret = paravirt_patch_default(type, clobbers, insns, len);
 		break;
-	case 3:
-		asm("movl %0,%%db3"	: /* no output */ :"r" (value));
-		break;
-	case 6:
-		asm("movl %0,%%db6"	: /* no output */ :"r" (value));
-		break;
-	case 7:
-		asm("movl %0,%%db7"	: /* no output */ :"r" (value));
-		break;
-	default:
-		BUG();
 	}
-}
-
-void init_IRQ(void)
-{
-	paravirt_ops.init_IRQ();
-}
-
-static void native_clts(void)
-{
-	asm volatile ("clts");
-}
-
-static unsigned long native_read_cr0(void)
-{
-	unsigned long val;
-	asm volatile("movl %%cr0,%0\n\t" :"=r" (val));
-	return val;
-}
-
-static void native_write_cr0(unsigned long val)
-{
-	asm volatile("movl %0,%%cr0": :"r" (val));
-}
-
-static unsigned long native_read_cr2(void)
-{
-	unsigned long val;
-	asm volatile("movl %%cr2,%0\n\t" :"=r" (val));
-	return val;
-}
-
-static void native_write_cr2(unsigned long val)
-{
-	asm volatile("movl %0,%%cr2": :"r" (val));
-}
-
-static unsigned long native_read_cr3(void)
-{
-	unsigned long val;
-	asm volatile("movl %%cr3,%0\n\t" :"=r" (val));
-	return val;
-}
-
-static void native_write_cr3(unsigned long val)
-{
-	asm volatile("movl %0,%%cr3": :"r" (val));
-}
-
-static unsigned long native_read_cr4(void)
-{
-	unsigned long val;
-	asm volatile("movl %%cr4,%0\n\t" :"=r" (val));
-	return val;
-}
-
-static unsigned long native_read_cr4_safe(void)
-{
-	unsigned long val;
-	/* This could fault if %cr4 does not exist */
-	asm("1: movl %%cr4, %0		\n"
-		"2:				\n"
-		".section __ex_table,\"a\"	\n"
-		".long 1b,2b			\n"
-		".previous			\n"
-		: "=r" (val): "0" (0));
-	return val;
-}
-
-static void native_write_cr4(unsigned long val)
-{
-	asm volatile("movl %0,%%cr4": :"r" (val));
-}
-
-static unsigned long native_save_fl(void)
-{
-	unsigned long f;
-	asm volatile("pushfl ; popl %0":"=g" (f): /* no input */);
-	return f;
-}
-
-static void native_restore_fl(unsigned long f)
-{
-	asm volatile("pushl %0 ; popfl": /* no output */
-			     :"g" (f)
-			     :"memory", "cc");
-}
-
-static void native_irq_disable(void)
-{
-	asm volatile("cli": : :"memory");
-}
-
-static void native_irq_enable(void)
-{
-	asm volatile("sti": : :"memory");
-}
-
-static void native_safe_halt(void)
-{
-	asm volatile("sti; hlt": : :"memory");
-}
 
-static void native_halt(void)
-{
-	asm volatile("hlt": : :"memory");
+	return ret;
 }
 
-static void native_wbinvd(void)
+unsigned paravirt_patch_nop(void)
 {
-	asm volatile("wbinvd": : :"memory");
+	return 0;
 }
 
-static unsigned long long native_read_msr(unsigned int msr, int *err)
+unsigned paravirt_patch_ignore(unsigned len)
 {
-	unsigned long long val;
-
-	asm volatile("2: rdmsr ; xorl %0,%0\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  movl %3,%0 ; jmp 1b\n\t"
-		     ".previous\n\t"
- 		     ".section __ex_table,\"a\"\n"
-		     "   .align 4\n\t"
-		     "   .long 	2b,3b\n\t"
-		     ".previous"
-		     : "=r" (*err), "=A" (val)
-		     : "c" (msr), "i" (-EFAULT));
-
-	return val;
+	return len;
 }
 
-static int native_write_msr(unsigned int msr, unsigned long long val)
+unsigned paravirt_patch_call(void *target, u16 tgt_clobbers,
+			     void *site, u16 site_clobbers,
+			     unsigned len)
 {
-	int err;
-	asm volatile("2: wrmsr ; xorl %0,%0\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  movl %4,%0 ; jmp 1b\n\t"
-		     ".previous\n\t"
- 		     ".section __ex_table,\"a\"\n"
-		     "   .align 4\n\t"
-		     "   .long 	2b,3b\n\t"
-		     ".previous"
-		     : "=a" (err)
-		     : "c" (msr), "0" ((u32)val), "d" ((u32)(val>>32)),
-		       "i" (-EFAULT));
-	return err;
-}
+	unsigned char *call = site;
+	unsigned long delta = (unsigned long)target - (unsigned long)(call+5);
 
-static unsigned long long native_read_tsc(void)
-{
-	unsigned long long val;
-	asm volatile("rdtsc" : "=A" (val));
-	return val;
-}
+	if (tgt_clobbers & ~site_clobbers)
+		return len;	/* target would clobber too much for this site */
+	if (len < 5)
+		return len;	/* call too long for patch site */
 
-static unsigned long long native_read_pmc(void)
-{
-	unsigned long long val;
-	asm volatile("rdpmc" : "=A" (val));
-	return val;
-}
+	*call++ = 0xe8;		/* call */
+	*(unsigned long *)call = delta;
 
-static void native_load_tr_desc(void)
-{
-	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
+	return 5;
 }
 
-static void native_load_gdt(const struct Xgt_desc_struct *dtr)
+unsigned paravirt_patch_jmp(void *target, void *site, unsigned len)
 {
-	asm volatile("lgdt %0"::"m" (*dtr));
-}
+	unsigned char *jmp = site;
+	unsigned long delta = (unsigned long)target - (unsigned long)(jmp+5);
 
-static void native_load_idt(const struct Xgt_desc_struct *dtr)
-{
-	asm volatile("lidt %0"::"m" (*dtr));
-}
+	if (len < 5)
+		return len;	/* call too long for patch site */
 
-static void native_store_gdt(struct Xgt_desc_struct *dtr)
-{
-	asm ("sgdt %0":"=m" (*dtr));
-}
+	*jmp++ = 0xe9;		/* jmp */
+	*(unsigned long *)jmp = delta;
 
-static void native_store_idt(struct Xgt_desc_struct *dtr)
-{
-	asm ("sidt %0":"=m" (*dtr));
+	return 5;
 }
 
-static unsigned long native_store_tr(void)
+unsigned paravirt_patch_default(u8 type, u16 clobbers, void *site, unsigned len)
 {
-	unsigned long tr;
-	asm ("str %0":"=r" (tr));
-	return tr;
-}
+	void *opfunc = *((void **)&paravirt_ops + type);
+	unsigned ret;
 
-static void native_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-#define C(i) get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]
-	C(0); C(1); C(2);
-#undef C
-}
+	if (opfunc == NULL)
+		/* If there's no function, patch it with a ud2a (BUG) */
+		ret = paravirt_patch_insns(site, len, start_ud2a, end_ud2a);
+	else if (opfunc == paravirt_nop)
+		/* If the operation is a nop, then nop the callsite */
+		ret = paravirt_patch_nop();
+	else if (type == PARAVIRT_PATCH(iret) ||
+		 type == PARAVIRT_PATCH(irq_enable_sysexit))
+		/* If operation requires a jmp, then jmp */
+		ret = paravirt_patch_jmp(opfunc, site, len);
+	else
+		/* Otherwise call the function; assume target could
+		   clobber any caller-save reg */
+		ret = paravirt_patch_call(opfunc, CLBR_ANY,
+					  site, clobbers, len);
 
-static inline void native_write_dt_entry(void *dt, int entry, u32 entry_low, u32 entry_high)
-{
-	u32 *lp = (u32 *)((char *)dt + entry*8);
-	lp[0] = entry_low;
-	lp[1] = entry_high;
+	return ret;
 }
 
-static void native_write_ldt_entry(void *dt, int entrynum, u32 low, u32 high)
+unsigned paravirt_patch_insns(void *site, unsigned len,
+			      const char *start, const char *end)
 {
-	native_write_dt_entry(dt, entrynum, low, high);
-}
+	unsigned insn_len = end - start;
 
-static void native_write_gdt_entry(void *dt, int entrynum, u32 low, u32 high)
-{
-	native_write_dt_entry(dt, entrynum, low, high);
-}
-
-static void native_write_idt_entry(void *dt, int entrynum, u32 low, u32 high)
-{
-	native_write_dt_entry(dt, entrynum, low, high);
-}
+	if (insn_len > len || start == NULL)
+		insn_len = len;
+	else
+		memcpy(site, start, insn_len);
 
-static void native_load_esp0(struct tss_struct *tss,
-				      struct thread_struct *thread)
-{
-	tss->esp0 = thread->esp0;
-
-	/* This can only happen when SEP is enabled, no need to test "SEP"arately */
-	if (unlikely(tss->ss1 != thread->sysenter_cs)) {
-		tss->ss1 = thread->sysenter_cs;
-		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
-	}
+	return insn_len;
 }
 
-static void native_io_delay(void)
+void init_IRQ(void)
 {
-	asm volatile("outb %al,$0x80");
+	paravirt_ops.init_IRQ();
 }
 
 static void native_flush_tlb(void)
@@ -395,83 +213,11 @@ static void native_flush_tlb_global(void)
 	__native_flush_tlb_global();
 }
 
-static void native_flush_tlb_single(u32 addr)
+static void native_flush_tlb_single(unsigned long addr)
 {
 	__native_flush_tlb_single(addr);
 }
 
-#ifndef CONFIG_X86_PAE
-static void native_set_pte(pte_t *ptep, pte_t pteval)
-{
-	*ptep = pteval;
-}
-
-static void native_set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pteval)
-{
-	*ptep = pteval;
-}
-
-static void native_set_pmd(pmd_t *pmdp, pmd_t pmdval)
-{
-	*pmdp = pmdval;
-}
-
-#else /* CONFIG_X86_PAE */
-
-static void native_set_pte(pte_t *ptep, pte_t pte)
-{
-	ptep->pte_high = pte.pte_high;
-	smp_wmb();
-	ptep->pte_low = pte.pte_low;
-}
-
-static void native_set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pte)
-{
-	ptep->pte_high = pte.pte_high;
-	smp_wmb();
-	ptep->pte_low = pte.pte_low;
-}
-
-static void native_set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
-{
-	ptep->pte_low = 0;
-	smp_wmb();
-	ptep->pte_high = pte.pte_high;
-	smp_wmb();
-	ptep->pte_low = pte.pte_low;
-}
-
-static void native_set_pte_atomic(pte_t *ptep, pte_t pteval)
-{
-	set_64bit((unsigned long long *)ptep,pte_val(pteval));
-}
-
-static void native_set_pmd(pmd_t *pmdp, pmd_t pmdval)
-{
-	set_64bit((unsigned long long *)pmdp,pmd_val(pmdval));
-}
-
-static void native_set_pud(pud_t *pudp, pud_t pudval)
-{
-	*pudp = pudval;
-}
-
-static void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	ptep->pte_low = 0;
-	smp_wmb();
-	ptep->pte_high = 0;
-}
-
-static void native_pmd_clear(pmd_t *pmd)
-{
-	u32 *tmp = (u32 *)pmd;
-	*tmp = 0;
-	smp_wmb();
-	*(tmp + 1) = 0;
-}
-#endif /* CONFIG_X86_PAE */
-
 /* These are in entry.S */
 extern void native_iret(void);
 extern void native_irq_enable_sysexit(void);
@@ -487,10 +233,11 @@ struct paravirt_ops paravirt_ops = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
 	.kernel_rpl = 0,
+	.shared_kernel_pmd = 1,	/* Only used when CONFIG_X86_PAE is set */
 
  	.patch = native_patch,
 	.banner = default_banner,
-	.arch_setup = native_nop,
+	.arch_setup = paravirt_nop,
 	.memory_setup = machine_specific_memory_setup,
 	.get_wallclock = native_get_wallclock,
 	.set_wallclock = native_set_wallclock,
@@ -517,8 +264,8 @@ struct paravirt_ops paravirt_ops = {
 	.safe_halt = native_safe_halt,
 	.halt = native_halt,
 	.wbinvd = native_wbinvd,
-	.read_msr = native_read_msr,
-	.write_msr = native_write_msr,
+	.read_msr = native_read_msr_safe,
+	.write_msr = native_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
 	.get_scheduled_cycles = native_read_tsc,
@@ -531,9 +278,9 @@ struct paravirt_ops paravirt_ops = {
 	.store_idt = native_store_idt,
 	.store_tr = native_store_tr,
 	.load_tls = native_load_tls,
-	.write_ldt_entry = native_write_ldt_entry,
-	.write_gdt_entry = native_write_gdt_entry,
-	.write_idt_entry = native_write_idt_entry,
+	.write_ldt_entry = write_dt_entry,
+	.write_gdt_entry = write_dt_entry,
+	.write_idt_entry = write_dt_entry,
 	.load_esp0 = native_load_esp0,
 
 	.set_iopl_mask = native_set_iopl_mask,
@@ -545,44 +292,57 @@ struct paravirt_ops paravirt_ops = {
 	.apic_read = native_apic_read,
 	.setup_boot_clock = setup_boot_APIC_clock,
 	.setup_secondary_clock = setup_secondary_APIC_clock,
+	.startup_ipi_hook = paravirt_nop,
 #endif
-	.set_lazy_mode = (void *)native_nop,
+	.set_lazy_mode = paravirt_nop,
+
+	.pagetable_setup_start = native_pagetable_setup_start,
+	.pagetable_setup_done = native_pagetable_setup_done,
 
 	.flush_tlb_user = native_flush_tlb,
 	.flush_tlb_kernel = native_flush_tlb_global,
 	.flush_tlb_single = native_flush_tlb_single,
+	.flush_tlb_others = native_flush_tlb_others,
 
-	.map_pt_hook = (void *)native_nop,
-
-	.alloc_pt = (void *)native_nop,
-	.alloc_pd = (void *)native_nop,
-	.alloc_pd_clone = (void *)native_nop,
-	.release_pt = (void *)native_nop,
-	.release_pd = (void *)native_nop,
+	.alloc_pt = paravirt_nop,
+	.alloc_pd = paravirt_nop,
+	.alloc_pd_clone = paravirt_nop,
+	.release_pt = paravirt_nop,
+	.release_pd = paravirt_nop,
 
 	.set_pte = native_set_pte,
 	.set_pte_at = native_set_pte_at,
 	.set_pmd = native_set_pmd,
-	.pte_update = (void *)native_nop,
-	.pte_update_defer = (void *)native_nop,
+	.pte_update = paravirt_nop,
+	.pte_update_defer = paravirt_nop,
+
+#ifdef CONFIG_HIGHPTE
+	.kmap_atomic_pte = kmap_atomic,
+#endif
+
 #ifdef CONFIG_X86_PAE
 	.set_pte_atomic = native_set_pte_atomic,
 	.set_pte_present = native_set_pte_present,
 	.set_pud = native_set_pud,
 	.pte_clear = native_pte_clear,
 	.pmd_clear = native_pmd_clear,
+
+	.pmd_val = native_pmd_val,
+	.make_pmd = native_make_pmd,
 #endif
 
+	.pte_val = native_pte_val,
+	.pgd_val = native_pgd_val,
+
+	.make_pte = native_make_pte,
+	.make_pgd = native_make_pgd,
+
 	.irq_enable_sysexit = native_irq_enable_sysexit,
 	.iret = native_iret,
 
-	.startup_ipi_hook = (void *)native_nop,
+	.dup_mmap = paravirt_nop,
+	.exit_mmap = paravirt_nop,
+	.activate_mm = paravirt_nop,
 };
 
-/*
- * NOTE: CONFIG_PARAVIRT is experimental and the paravirt_ops
- * semantics are subject to change. Hence we only do this
- * internal-only export of this, until it gets sorted out and
- * all lowlevel CPU ops used by modules are separately exported.
- */
-EXPORT_SYMBOL_GPL(paravirt_ops);
+EXPORT_SYMBOL(paravirt_ops);

arch/i386/kernel/process.c

@@ -39,6 +39,7 @@
 #include <linux/random.h>
 #include <linux/personality.h>
 #include <linux/tick.h>
+#include <linux/percpu.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -57,7 +58,6 @@
 
 #include <asm/tlbflush.h>
 #include <asm/cpu.h>
-#include <asm/pda.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
@@ -66,6 +66,12 @@ static int hlt_counter;
 unsigned long boot_option_idle_override = 0;
 EXPORT_SYMBOL(boot_option_idle_override);
 
+DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+
+DEFINE_PER_CPU(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
+
 /*
  * Return saved PC of a blocked thread.
  */
@@ -272,25 +278,24 @@ void __devinit select_idle_routine(const struct cpuinfo_x86 *c)
 	}
 }
 
-static int __init idle_setup (char *str)
+static int __init idle_setup(char *str)
 {
-	if (!strncmp(str, "poll", 4)) {
+	if (!strcmp(str, "poll")) {
 		printk("using polling idle threads.\n");
 		pm_idle = poll_idle;
 #ifdef CONFIG_X86_SMP
 		if (smp_num_siblings > 1)
 			printk("WARNING: polling idle and HT enabled, performance may degrade.\n");
 #endif
-	} else if (!strncmp(str, "halt", 4)) {
-		printk("using halt in idle threads.\n");
-		pm_idle = default_idle;
-	}
+	} else if (!strcmp(str, "mwait"))
+		force_mwait = 1;
+	else
+		return -1;
 
 	boot_option_idle_override = 1;
-	return 1;
+	return 0;
 }
-
-__setup("idle=", idle_setup);
+early_param("idle", idle_setup);
 
 void show_regs(struct pt_regs * regs)
 {
@@ -343,7 +348,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 
 	regs.xds = __USER_DS;
 	regs.xes = __USER_DS;
-	regs.xfs = __KERNEL_PDA;
+	regs.xfs = __KERNEL_PERCPU;
 	regs.orig_eax = -1;
 	regs.eip = (unsigned long) kernel_thread_helper;
 	regs.xcs = __KERNEL_CS | get_kernel_rpl();
@@ -376,7 +381,7 @@ void exit_thread(void)
 		t->io_bitmap_max = 0;
 		tss->io_bitmap_owner = NULL;
 		tss->io_bitmap_max = 0;
-		tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
+		tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
 		put_cpu();
 	}
 }
@@ -555,7 +560,7 @@ static noinline void __switch_to_xtra(struct task_struct *next_p,
 		 * Disable the bitmap via an invalid offset. We still cache
 		 * the previous bitmap owner and the IO bitmap contents:
 		 */
-		tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
+		tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
 		return;
 	}
 
@@ -565,7 +570,7 @@ static noinline void __switch_to_xtra(struct task_struct *next_p,
 		 * matches the next task, we dont have to do anything but
 		 * to set a valid offset in the TSS:
 		 */
-		tss->io_bitmap_base = IO_BITMAP_OFFSET;
+		tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
 		return;
 	}
 	/*
@@ -577,7 +582,7 @@ static noinline void __switch_to_xtra(struct task_struct *next_p,
 	 * redundant copies when the currently switched task does not
 	 * perform any I/O during its timeslice.
 	 */
-	tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
+	tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
 }
 
 /*
@@ -712,7 +717,7 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	if (prev->gs | next->gs)
 		loadsegment(gs, next->gs);
 
-	write_pda(pcurrent, next_p);
+	x86_write_percpu(current_task, next_p);
 
 	return prev_p;
 }

arch/i386/kernel/quirks.c

@@ -3,12 +3,10 @@
  */
 #include <linux/pci.h>
 #include <linux/irq.h>
-#include <asm/pci-direct.h>
-#include <asm/genapic.h>
-#include <asm/cpu.h>
 
 #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
-static void __devinit verify_quirk_intel_irqbalance(struct pci_dev *dev)
+
+static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
 {
 	u8 config, rev;
 	u32 word;
@@ -16,12 +14,14 @@ static void __devinit verify_quirk_intel_irqbalance(struct pci_dev *dev)
 	/* BIOS may enable hardware IRQ balancing for
 	 * E7520/E7320/E7525(revision ID 0x9 and below)
 	 * based platforms.
-	 * For those platforms, make sure that the genapic is set to 'flat'
+	 * Disable SW irqbalance/affinity on those platforms.
 	 */
 	pci_read_config_byte(dev, PCI_CLASS_REVISION, &rev);
 	if (rev > 0x9)
 		return;
 
+	printk(KERN_INFO "Intel E7520/7320/7525 detected.");
+
 	/* enable access to config space*/
 	pci_read_config_byte(dev, 0xf4, &config);
 	pci_write_config_byte(dev, 0xf4, config|0x2);
@@ -29,44 +29,6 @@ static void __devinit verify_quirk_intel_irqbalance(struct pci_dev *dev)
 	/* read xTPR register */
 	raw_pci_ops->read(0, 0, 0x40, 0x4c, 2, &word);
 
-	if (!(word & (1 << 13))) {
-#ifdef CONFIG_X86_64
-		if (genapic !=  &apic_flat)
-			panic("APIC mode must be flat on this system\n");
-#elif defined(CONFIG_X86_GENERICARCH)
-		if (genapic != &apic_default)
-			panic("APIC mode must be default(flat) on this system. Use apic=default\n");
-#endif
-	}
-
-	/* put back the original value for config space*/
-	if (!(config & 0x2))
-		pci_write_config_byte(dev, 0xf4, config);
-}
-
-void __init quirk_intel_irqbalance(void)
-{
-	u8 config, rev;
-	u32 word;
-
-	/* BIOS may enable hardware IRQ balancing for
-	 * E7520/E7320/E7525(revision ID 0x9 and below)
-	 * based platforms.
-	 * Disable SW irqbalance/affinity on those platforms.
-	 */
-	rev = read_pci_config_byte(0, 0, 0, PCI_CLASS_REVISION);
-	if (rev > 0x9)
-		return;
-
-	printk(KERN_INFO "Intel E7520/7320/7525 detected.");
-
-	/* enable access to config space */
-	config = read_pci_config_byte(0, 0, 0, 0xf4);
-	write_pci_config_byte(0, 0, 0, 0xf4, config|0x2);
-
-	/* read xTPR register */
-	word = read_pci_config_16(0, 0, 0x40, 0x4c);
-
 	if (!(word & (1 << 13))) {
 		printk(KERN_INFO "Disabling irq balancing and affinity\n");
 #ifdef CONFIG_IRQBALANCE
@@ -75,25 +37,14 @@ void __init quirk_intel_irqbalance(void)
 		noirqdebug_setup("");
 #ifdef CONFIG_PROC_FS
 		no_irq_affinity = 1;
-#endif
-#ifdef CONFIG_HOTPLUG_CPU
-		printk(KERN_INFO "Disabling cpu hotplug control\n");
-		enable_cpu_hotplug = 0;
-#endif
-#ifdef CONFIG_X86_64
-		/* force the genapic selection to flat mode so that
-		 * interrupts can be redirected to more than one CPU.
-		 */
-		genapic_force = &apic_flat;
 #endif
 	}
 
-	/* put back the original value for config space */
+	/* put back the original value for config space*/
 	if (!(config & 0x2))
-		write_pci_config_byte(0, 0, 0, 0xf4, config);
+		pci_write_config_byte(dev, 0xf4, config);
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_E7320_MCH,  verify_quirk_intel_irqbalance);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_E7525_MCH,  verify_quirk_intel_irqbalance);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_E7520_MCH,  verify_quirk_intel_irqbalance);
-
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7320_MCH,	quirk_intel_irqbalance);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7525_MCH,	quirk_intel_irqbalance);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7520_MCH,	quirk_intel_irqbalance);
 #endif

arch/i386/kernel/reboot.c

@@ -17,7 +17,8 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 #include "mach_reboot.h"
-#include <linux/reboot_fixups.h>
+#include <asm/reboot_fixups.h>
+#include <asm/reboot.h>
 
 /*
  * Power off function, if any
@@ -197,8 +198,6 @@ static unsigned char jump_to_bios [] =
  */
 void machine_real_restart(unsigned char *code, int length)
 {
-	unsigned long flags;
-
 	local_irq_disable();
 
 	/* Write zero to CMOS register number 0x0f, which the BIOS POST
@@ -211,9 +210,9 @@ void machine_real_restart(unsigned char *code, int length)
 	   safe side.  (Yes, CMOS_WRITE does outb_p's. -  Paul G.)
 	 */
 
-	spin_lock_irqsave(&rtc_lock, flags);
+	spin_lock(&rtc_lock);
 	CMOS_WRITE(0x00, 0x8f);
-	spin_unlock_irqrestore(&rtc_lock, flags);
+	spin_unlock(&rtc_lock);
 
 	/* Remap the kernel at virtual address zero, as well as offset zero
 	   from the kernel segment.  This assumes the kernel segment starts at
@@ -280,7 +279,7 @@ void machine_real_restart(unsigned char *code, int length)
 EXPORT_SYMBOL(machine_real_restart);
 #endif
 
-void machine_shutdown(void)
+static void native_machine_shutdown(void)
 {
 #ifdef CONFIG_SMP
 	int reboot_cpu_id;
@@ -316,7 +315,11 @@ void machine_shutdown(void)
 #endif
 }
 
-void machine_emergency_restart(void)
+void __attribute__((weak)) mach_reboot_fixups(void)
+{
+}
+
+static void native_machine_emergency_restart(void)
 {
 	if (!reboot_thru_bios) {
 		if (efi_enabled) {
@@ -340,17 +343,17 @@ void machine_emergency_restart(void)
 	machine_real_restart(jump_to_bios, sizeof(jump_to_bios));
 }
 
-void machine_restart(char * __unused)
+static void native_machine_restart(char * __unused)
 {
 	machine_shutdown();
 	machine_emergency_restart();
 }
 
-void machine_halt(void)
+static void native_machine_halt(void)
 {
 }
 
-void machine_power_off(void)
+static void native_machine_power_off(void)
 {
 	if (pm_power_off) {
 		machine_shutdown();
@@ -359,3 +362,35 @@ void machine_power_off(void)
 }
 
 
+struct machine_ops machine_ops = {
+	.power_off = native_machine_power_off,
+	.shutdown = native_machine_shutdown,
+	.emergency_restart = native_machine_emergency_restart,
+	.restart = native_machine_restart,
+	.halt = native_machine_halt,
+};
+
+void machine_power_off(void)
+{
+	machine_ops.power_off();
+}
+
+void machine_shutdown(void)
+{
+	machine_ops.shutdown();
+}
+
+void machine_emergency_restart(void)
+{
+	machine_ops.emergency_restart();
+}
+
+void machine_restart(char *cmd)
+{
+	machine_ops.restart(cmd);
+}
+
+void machine_halt(void)
+{
+	machine_ops.halt();
+}

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/smp.c

@@ -165,20 +165,20 @@ void fastcall send_IPI_self(int vector)
 }
 
 /*
- * This is only used on smaller machines.
+ * This is used to send an IPI with no shorthand notation (the destination is
+ * specified in bits 56 to 63 of the ICR).
  */
-void send_IPI_mask_bitmask(cpumask_t cpumask, int vector)
+static inline void __send_IPI_dest_field(unsigned long mask, int vector)
 {
-	unsigned long mask = cpus_addr(cpumask)[0];
 	unsigned long cfg;
-	unsigned long flags;
 
-	local_irq_save(flags);
-	WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]);
 	/*
 	 * Wait for idle.
 	 */
-	apic_wait_icr_idle();
+	if (unlikely(vector == NMI_VECTOR))
+		safe_apic_wait_icr_idle();
+	else
+		apic_wait_icr_idle();
 		
 	/*
 	 * prepare target chip field
@@ -195,13 +195,25 @@ void send_IPI_mask_bitmask(cpumask_t cpumask, int vector)
 	 * Send the IPI. The write to APIC_ICR fires this off.
 	 */
 	apic_write_around(APIC_ICR, cfg);
+}
+
+/*
+ * This is only used on smaller machines.
+ */
+void send_IPI_mask_bitmask(cpumask_t cpumask, int vector)
+{
+	unsigned long mask = cpus_addr(cpumask)[0];
+	unsigned long flags;
 
+	local_irq_save(flags);
+	WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]);
+	__send_IPI_dest_field(mask, vector);
 	local_irq_restore(flags);
 }
 
 void send_IPI_mask_sequence(cpumask_t mask, int vector)
 {
-	unsigned long cfg, flags;
+	unsigned long flags;
 	unsigned int query_cpu;
 
 	/*
@@ -211,30 +223,10 @@ void send_IPI_mask_sequence(cpumask_t mask, int vector)
 	 */ 
 
 	local_irq_save(flags);
-
 	for (query_cpu = 0; query_cpu < NR_CPUS; ++query_cpu) {
 		if (cpu_isset(query_cpu, mask)) {
-		
-			/*
-			 * Wait for idle.
-			 */
-			apic_wait_icr_idle();
-		
-			/*
-			 * prepare target chip field
-			 */
-			cfg = __prepare_ICR2(cpu_to_logical_apicid(query_cpu));
-			apic_write_around(APIC_ICR2, cfg);
-		
-			/*
-			 * program the ICR 
-			 */
-			cfg = __prepare_ICR(0, vector);
-			
-			/*
-			 * Send the IPI. The write to APIC_ICR fires this off.
-			 */
-			apic_write_around(APIC_ICR, cfg);
+			__send_IPI_dest_field(cpu_to_logical_apicid(query_cpu),
+					      vector);
 		}
 	}
 	local_irq_restore(flags);
@@ -256,7 +248,6 @@ static cpumask_t flush_cpumask;
 static struct mm_struct * flush_mm;
 static unsigned long flush_va;
 static DEFINE_SPINLOCK(tlbstate_lock);
-#define FLUSH_ALL	0xffffffff
 
 /*
  * We cannot call mmdrop() because we are in interrupt context, 
@@ -338,7 +329,7 @@ fastcall void smp_invalidate_interrupt(struct pt_regs *regs)
 		 
 	if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) {
 		if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) {
-			if (flush_va == FLUSH_ALL)
+			if (flush_va == TLB_FLUSH_ALL)
 				local_flush_tlb();
 			else
 				__flush_tlb_one(flush_va);
@@ -353,9 +344,11 @@ out:
 	put_cpu_no_resched();
 }
 
-static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
-						unsigned long va)
+void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
+			     unsigned long va)
 {
+	cpumask_t cpumask = *cpumaskp;
+
 	/*
 	 * A couple of (to be removed) sanity checks:
 	 *
@@ -366,10 +359,12 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	BUG_ON(cpu_isset(smp_processor_id(), cpumask));
 	BUG_ON(!mm);
 
+#ifdef CONFIG_HOTPLUG_CPU
 	/* If a CPU which we ran on has gone down, OK. */
 	cpus_and(cpumask, cpumask, cpu_online_map);
-	if (cpus_empty(cpumask))
+	if (unlikely(cpus_empty(cpumask)))
 		return;
+#endif
 
 	/*
 	 * i'm not happy about this global shared spinlock in the
@@ -380,17 +375,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	
 	flush_mm = mm;
 	flush_va = va;
-#if NR_CPUS <= BITS_PER_LONG
-	atomic_set_mask(cpumask, &flush_cpumask);
-#else
-	{
-		int k;
-		unsigned long *flush_mask = (unsigned long *)&flush_cpumask;
-		unsigned long *cpu_mask = (unsigned long *)&cpumask;
-		for (k = 0; k < BITS_TO_LONGS(NR_CPUS); ++k)
-			atomic_set_mask(cpu_mask[k], &flush_mask[k]);
-	}
-#endif
+	cpus_or(flush_cpumask, cpumask, flush_cpumask);
 	/*
 	 * We have to send the IPI only to
 	 * CPUs affected.
@@ -417,7 +402,7 @@ void flush_tlb_current_task(void)
 
 	local_flush_tlb();
 	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+		flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
@@ -436,7 +421,7 @@ void flush_tlb_mm (struct mm_struct * mm)
 			leave_mm(smp_processor_id());
 	}
 	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+		flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
 
 	preempt_enable();
 }
@@ -483,7 +468,7 @@ void flush_tlb_all(void)
  * it goes straight through and wastes no time serializing
  * anything. Worst case is that we lose a reschedule ...
  */
-void smp_send_reschedule(int cpu)
+void native_smp_send_reschedule(int cpu)
 {
 	WARN_ON(cpu_is_offline(cpu));
 	send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
@@ -515,36 +500,78 @@ void unlock_ipi_call_lock(void)
 
 static struct call_data_struct *call_data;
 
+static void __smp_call_function(void (*func) (void *info), void *info,
+				int nonatomic, int wait)
+{
+	struct call_data_struct data;
+	int cpus = num_online_cpus() - 1;
+
+	if (!cpus)
+		return;
+
+	data.func = func;
+	data.info = info;
+	atomic_set(&data.started, 0);
+	data.wait = wait;
+	if (wait)
+		atomic_set(&data.finished, 0);
+
+	call_data = &data;
+	mb();
+	
+	/* Send a message to all other CPUs and wait for them to respond */
+	send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+
+	/* Wait for response */
+	while (atomic_read(&data.started) != cpus)
+		cpu_relax();
+
+	if (wait)
+		while (atomic_read(&data.finished) != cpus)
+			cpu_relax();
+}
+
+
 /**
- * smp_call_function(): Run a function on all other CPUs.
+ * smp_call_function_mask(): Run a function on a set of other CPUs.
+ * @mask: The set of cpus to run on.  Must not include the current cpu.
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @nonatomic: currently unused.
  * @wait: If true, wait (atomically) until function has completed on other CPUs.
  *
- * Returns 0 on success, else a negative status code. Does not return until
- * remote CPUs are nearly ready to execute <<func>> or are or have executed.
+  * Returns 0 on success, else a negative status code.
+ *
+ * If @wait is true, then returns once @func has returned; otherwise
+ * it returns just before the target cpu calls @func.
  *
  * You must not call this function with disabled interrupts or from a
  * hardware interrupt handler or from a bottom half handler.
  */
-int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
-			int wait)
+int native_smp_call_function_mask(cpumask_t mask,
+				  void (*func)(void *), void *info,
+				  int wait)
 {
 	struct call_data_struct data;
+	cpumask_t allbutself;
 	int cpus;
 
+	/* Can deadlock when called with interrupts disabled */
+	WARN_ON(irqs_disabled());
+
 	/* Holding any lock stops cpus from going down. */
 	spin_lock(&call_lock);
-	cpus = num_online_cpus() - 1;
+
+	allbutself = cpu_online_map;
+	cpu_clear(smp_processor_id(), allbutself);
+
+	cpus_and(mask, mask, allbutself);
+	cpus = cpus_weight(mask);
+
 	if (!cpus) {
 		spin_unlock(&call_lock);
 		return 0;
 	}
 
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
 	data.func = func;
 	data.info = info;
 	atomic_set(&data.started, 0);
@@ -554,9 +581,12 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
 
 	call_data = &data;
 	mb();
-	
-	/* Send a message to all other CPUs and wait for them to respond */
-	send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+
+	/* Send a message to other CPUs */
+	if (cpus_equal(mask, allbutself))
+		send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+	else
+		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
 
 	/* Wait for response */
 	while (atomic_read(&data.started) != cpus)
@@ -569,15 +599,68 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
 
 	return 0;
 }
+
+/**
+ * smp_call_function(): Run a function on all other CPUs.
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @nonatomic: Unused.
+ * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ *
+ * Returns 0 on success, else a negative status code.
+ *
+ * If @wait is true, then returns once @func has returned; otherwise
+ * it returns just before the target cpu calls @func.
+ *
+ * You must not call this function with disabled interrupts or from a
+ * hardware interrupt handler or from a bottom half handler.
+ */
+int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
+		      int wait)
+{
+	return smp_call_function_mask(cpu_online_map, func, info, wait);
+}
 EXPORT_SYMBOL(smp_call_function);
 
+/**
+ * smp_call_function_single - Run a function on another CPU
+ * @cpu: The target CPU.  Cannot be the calling CPU.
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @nonatomic: Unused.
+ * @wait: If true, wait until function has completed on other CPUs.
+ *
+ * Returns 0 on success, else a negative status code.
+ *
+ * If @wait is true, then returns once @func has returned; otherwise
+ * it returns just before the target cpu calls @func.
+ */
+int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+			     int nonatomic, int wait)
+{
+	/* prevent preemption and reschedule on another processor */
+	int ret;
+	int me = get_cpu();
+	if (cpu == me) {
+		WARN_ON(1);
+		put_cpu();
+		return -EBUSY;
+	}
+
+	ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait);
+
+	put_cpu();
+	return ret;
+}
+EXPORT_SYMBOL(smp_call_function_single);
+
 static void stop_this_cpu (void * dummy)
 {
+	local_irq_disable();
 	/*
 	 * Remove this CPU:
 	 */
 	cpu_clear(smp_processor_id(), cpu_online_map);
-	local_irq_disable();
 	disable_local_APIC();
 	if (cpu_data[smp_processor_id()].hlt_works_ok)
 		for(;;) halt();
@@ -588,13 +671,18 @@ static void stop_this_cpu (void * dummy)
  * this function calls the 'stop' function on all other CPUs in the system.
  */
 
-void smp_send_stop(void)
+void native_smp_send_stop(void)
 {
-	smp_call_function(stop_this_cpu, NULL, 1, 0);
+	/* Don't deadlock on the call lock in panic */
+	int nolock = !spin_trylock(&call_lock);
+	unsigned long flags;
 
-	local_irq_disable();
+	local_irq_save(flags);
+	__smp_call_function(stop_this_cpu, NULL, 0, 0);
+	if (!nolock)
+		spin_unlock(&call_lock);
 	disable_local_APIC();
-	local_irq_enable();
+	local_irq_restore(flags);
 }
 
 /*
@@ -633,77 +721,6 @@ fastcall void smp_call_function_interrupt(struct pt_regs *regs)
 	}
 }
 
-/*
- * this function sends a 'generic call function' IPI to one other CPU
- * in the system.
- *
- * cpu is a standard Linux logical CPU number.
- */
-static void
-__smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-				int nonatomic, int wait)
-{
-	struct call_data_struct data;
-	int cpus = 1;
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	wmb();
-	/* Send a message to all other CPUs and wait for them to respond */
-	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_VECTOR);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (!wait)
-		return;
-
-	while (atomic_read(&data.finished) != cpus)
-		cpu_relax();
-}
-
-/*
- * smp_call_function_single - Run a function on another CPU
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @nonatomic: Currently unused.
- * @wait: If true, wait until function has completed on other CPUs.
- *
- * Retrurns 0 on success, else a negative status code.
- *
- * Does not return until the remote CPU is nearly ready to execute <func>
- * or is or has executed.
- */
-
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			int nonatomic, int wait)
-{
-	/* prevent preemption and reschedule on another processor */
-	int me = get_cpu();
-	if (cpu == me) {
-		WARN_ON(1);
-		put_cpu();
-		return -EBUSY;
-	}
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	spin_lock_bh(&call_lock);
-	__smp_call_function_single(cpu, func, info, nonatomic, wait);
-	spin_unlock_bh(&call_lock);
-	put_cpu();
-	return 0;
-}
-EXPORT_SYMBOL(smp_call_function_single);
-
 static int convert_apicid_to_cpu(int apic_id)
 {
 	int i;
@@ -730,3 +747,14 @@ int safe_smp_processor_id(void)
 
 	return cpuid >= 0 ? cpuid : 0;
 }
+
+struct smp_ops smp_ops = {
+	.smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
+	.smp_prepare_cpus = native_smp_prepare_cpus,
+	.cpu_up = native_cpu_up,
+	.smp_cpus_done = native_smp_cpus_done,
+
+	.smp_send_stop = native_smp_send_stop,
+	.smp_send_reschedule = native_smp_send_reschedule,
+	.smp_call_function_mask = native_smp_call_function_mask,
+};

arch/i386/kernel/smpboot.c

@@ -53,13 +53,12 @@
 #include <asm/desc.h>
 #include <asm/arch_hooks.h>
 #include <asm/nmi.h>
-#include <asm/pda.h>
-#include <asm/genapic.h>
 
 #include <mach_apic.h>
 #include <mach_wakecpu.h>
 #include <smpboot_hooks.h>
 #include <asm/vmi.h>
+#include <asm/mtrr.h>
 
 /* Set if we find a B stepping CPU */
 static int __devinitdata smp_b_stepping;
@@ -100,6 +99,9 @@ EXPORT_SYMBOL(x86_cpu_to_apicid);
 
 u8 apicid_2_node[MAX_APICID];
 
+DEFINE_PER_CPU(unsigned long, this_cpu_off);
+EXPORT_PER_CPU_SYMBOL(this_cpu_off);
+
 /*
  * Trampoline 80x86 program as an array.
  */
@@ -156,7 +158,7 @@ static void __cpuinit smp_store_cpu_info(int id)
 
 	*c = boot_cpu_data;
 	if (id!=0)
-		identify_cpu(c);
+		identify_secondary_cpu(c);
 	/*
 	 * Mask B, Pentium, but not Pentium MMX
 	 */
@@ -379,14 +381,14 @@ set_cpu_sibling_map(int cpu)
 static void __cpuinit start_secondary(void *unused)
 {
 	/*
-	 * Don't put *anything* before secondary_cpu_init(), SMP
-	 * booting is too fragile that we want to limit the
-	 * things done here to the most necessary things.
+	 * Don't put *anything* before cpu_init(), SMP booting is too
+	 * fragile that we want to limit the things done here to the
+	 * most necessary things.
 	 */
 #ifdef CONFIG_VMI
 	vmi_bringup();
 #endif
-	secondary_cpu_init();
+	cpu_init();
 	preempt_disable();
 	smp_callin();
 	while (!cpu_isset(smp_processor_id(), smp_commenced_mask))
@@ -440,12 +442,6 @@ static void __cpuinit start_secondary(void *unused)
  */
 void __devinit initialize_secondary(void)
 {
-	/*
-	 * switch to the per CPU GDT we already set up
-	 * in do_boot_cpu()
-	 */
-	cpu_set_gdt(current_thread_info()->cpu);
-
 	/*
 	 * We don't actually need to load the full TSS,
 	 * basically just the stack pointer and the eip.
@@ -463,7 +459,6 @@ extern struct {
 	void * esp;
 	unsigned short ss;
 } stack_start;
-extern struct i386_pda *start_pda;
 
 #ifdef CONFIG_NUMA
 
@@ -521,12 +516,12 @@ static void unmap_cpu_to_logical_apicid(int cpu)
 	unmap_cpu_to_node(cpu);
 }
 
-#if APIC_DEBUG
 static inline void __inquire_remote_apic(int apicid)
 {
 	int i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
 	char *names[] = { "ID", "VERSION", "SPIV" };
-	int timeout, status;
+	int timeout;
+	unsigned long status;
 
 	printk("Inquiring remote APIC #%d...\n", apicid);
 
@@ -536,7 +531,9 @@ static inline void __inquire_remote_apic(int apicid)
 		/*
 		 * Wait for idle.
 		 */
-		apic_wait_icr_idle();
+		status = safe_apic_wait_icr_idle();
+		if (status)
+			printk("a previous APIC delivery may have failed\n");
 
 		apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
 		apic_write_around(APIC_ICR, APIC_DM_REMRD | regs[i]);
@@ -550,14 +547,13 @@ static inline void __inquire_remote_apic(int apicid)
 		switch (status) {
 		case APIC_ICR_RR_VALID:
 			status = apic_read(APIC_RRR);
-			printk("%08x\n", status);
+			printk("%lx\n", status);
 			break;
 		default:
 			printk("failed\n");
 		}
 	}
 }
-#endif
 
 #ifdef WAKE_SECONDARY_VIA_NMI
 /* 
@@ -568,8 +564,8 @@ static inline void __inquire_remote_apic(int apicid)
 static int __devinit
 wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
 {
-	unsigned long send_status = 0, accept_status = 0;
-	int timeout, maxlvt;
+	unsigned long send_status, accept_status = 0;
+	int maxlvt;
 
 	/* Target chip */
 	apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid));
@@ -579,12 +575,7 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
 	apic_write_around(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL);
 
 	Dprintk("Waiting for send to finish...\n");
-	timeout = 0;
-	do {
-		Dprintk("+");
-		udelay(100);
-		send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
-	} while (send_status && (timeout++ < 1000));
+	send_status = safe_apic_wait_icr_idle();
 
 	/*
 	 * Give the other CPU some time to accept the IPI.
@@ -614,8 +605,8 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
 static int __devinit
 wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 {
-	unsigned long send_status = 0, accept_status = 0;
-	int maxlvt, timeout, num_starts, j;
+	unsigned long send_status, accept_status = 0;
+	int maxlvt, num_starts, j;
 
 	/*
 	 * Be paranoid about clearing APIC errors.
@@ -640,12 +631,7 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 				| APIC_DM_INIT);
 
 	Dprintk("Waiting for send to finish...\n");
-	timeout = 0;
-	do {
-		Dprintk("+");
-		udelay(100);
-		send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
-	} while (send_status && (timeout++ < 1000));
+	send_status = safe_apic_wait_icr_idle();
 
 	mdelay(10);
 
@@ -658,12 +644,7 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 	apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
 
 	Dprintk("Waiting for send to finish...\n");
-	timeout = 0;
-	do {
-		Dprintk("+");
-		udelay(100);
-		send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
-	} while (send_status && (timeout++ < 1000));
+	send_status = safe_apic_wait_icr_idle();
 
 	atomic_set(&init_deasserted, 1);
 
@@ -719,12 +700,7 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 		Dprintk("Startup point 1.\n");
 
 		Dprintk("Waiting for send to finish...\n");
-		timeout = 0;
-		do {
-			Dprintk("+");
-			udelay(100);
-			send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
-		} while (send_status && (timeout++ < 1000));
+		send_status = safe_apic_wait_icr_idle();
 
 		/*
 		 * Give the other CPU some time to accept the IPI.
@@ -788,6 +764,25 @@ static inline struct task_struct * alloc_idle_task(int cpu)
 #define alloc_idle_task(cpu) fork_idle(cpu)
 #endif
 
+/* Initialize the CPU's GDT.  This is either the boot CPU doing itself
+   (still using the master per-cpu area), or a CPU doing it for a
+   secondary which will soon come up. */
+static __cpuinit void init_gdt(int cpu)
+{
+	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+
+	pack_descriptor((u32 *)&gdt[GDT_ENTRY_PERCPU].a,
+			(u32 *)&gdt[GDT_ENTRY_PERCPU].b,
+			__per_cpu_offset[cpu], 0xFFFFF,
+			0x80 | DESCTYPE_S | 0x2, 0x8);
+
+	per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
+	per_cpu(cpu_number, cpu) = cpu;
+}
+
+/* Defined in head.S */
+extern struct Xgt_desc_struct early_gdt_descr;
+
 static int __cpuinit do_boot_cpu(int apicid, int cpu)
 /*
  * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
@@ -801,6 +796,12 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
 	unsigned long start_eip;
 	unsigned short nmi_high = 0, nmi_low = 0;
 
+	/*
+	 * Save current MTRR state in case it was changed since early boot
+	 * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync:
+	 */
+	mtrr_save_state();
+
 	/*
 	 * We can't use kernel_thread since we must avoid to
 	 * reschedule the child.
@@ -809,13 +810,9 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
 	if (IS_ERR(idle))
 		panic("failed fork for CPU %d", cpu);
 
-	/* Pre-allocate and initialize the CPU's GDT and PDA so it
-	   doesn't have to do any memory allocation during the
-	   delicate CPU-bringup phase. */
-	if (!init_gdt(cpu, idle)) {
-		printk(KERN_INFO "Couldn't allocate GDT/PDA for CPU %d\n", cpu);
-		return -1;	/* ? */
-	}
+	init_gdt(cpu);
+ 	per_cpu(current_task, cpu) = idle;
+	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 
 	idle->thread.eip = (unsigned long) start_secondary;
 	/* start_eip had better be page-aligned! */
@@ -941,7 +938,6 @@ static int __cpuinit __smp_prepare_cpu(int cpu)
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct warm_boot_cpu_info info;
 	int	apicid, ret;
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
 
 	apicid = x86_cpu_to_apicid[cpu];
 	if (apicid == BAD_APICID) {
@@ -949,18 +945,6 @@ static int __cpuinit __smp_prepare_cpu(int cpu)
 		goto exit;
 	}
 
-	/*
-	 * the CPU isn't initialized at boot time, allocate gdt table here.
-	 * cpu_init will initialize it
-	 */
-	if (!cpu_gdt_descr->address) {
-		cpu_gdt_descr->address = get_zeroed_page(GFP_KERNEL);
-		if (!cpu_gdt_descr->address)
-			printk(KERN_CRIT "CPU%d failed to allocate GDT\n", cpu);
-			ret = -ENOMEM;
-			goto exit;
-	}
-
 	info.complete = &done;
 	info.apicid = apicid;
 	info.cpu = cpu;
@@ -1173,7 +1157,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 
 /* These are wrappers to interface to the new boot process.  Someone
    who understands all this stuff should rewrite it properly. --RR 15/Jul/02 */
-void __init smp_prepare_cpus(unsigned int max_cpus)
+void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
 	smp_commenced_mask = cpumask_of_cpu(0);
 	cpu_callin_map = cpumask_of_cpu(0);
@@ -1181,13 +1165,18 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	smp_boot_cpus(max_cpus);
 }
 
-void __devinit smp_prepare_boot_cpu(void)
+void __init native_smp_prepare_boot_cpu(void)
 {
-	cpu_set(smp_processor_id(), cpu_online_map);
-	cpu_set(smp_processor_id(), cpu_callout_map);
-	cpu_set(smp_processor_id(), cpu_present_map);
-	cpu_set(smp_processor_id(), cpu_possible_map);
-	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
+	unsigned int cpu = smp_processor_id();
+
+	init_gdt(cpu);
+	switch_to_new_gdt();
+
+	cpu_set(cpu, cpu_online_map);
+	cpu_set(cpu, cpu_callout_map);
+	cpu_set(cpu, cpu_present_map);
+	cpu_set(cpu, cpu_possible_map);
+	__get_cpu_var(cpu_state) = CPU_ONLINE;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -1277,7 +1266,7 @@ void __cpu_die(unsigned int cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-int __cpuinit __cpu_up(unsigned int cpu)
+int __cpuinit native_cpu_up(unsigned int cpu)
 {
 	unsigned long flags;
 #ifdef CONFIG_HOTPLUG_CPU
@@ -1319,15 +1308,10 @@ int __cpuinit __cpu_up(unsigned int cpu)
 		touch_nmi_watchdog();
 	}
 
-#ifdef CONFIG_X86_GENERICARCH
-	if (num_online_cpus() > 8 && genapic == &apic_default)
-		panic("Default flat APIC routing can't be used with > 8 cpus\n");
-#endif
-
 	return 0;
 }
 
-void __init smp_cpus_done(unsigned int max_cpus)
+void __init native_smp_cpus_done(unsigned int max_cpus)
 {
 #ifdef CONFIG_X86_IO_APIC
 	setup_ioapic_dest();

arch/i386/kernel/sysenter.c

@@ -22,16 +22,26 @@
 #include <asm/msr.h>
 #include <asm/pgtable.h>
 #include <asm/unistd.h>
+#include <asm/elf.h>
+#include <asm/tlbflush.h>
+
+enum {
+	VDSO_DISABLED = 0,
+	VDSO_ENABLED = 1,
+	VDSO_COMPAT = 2,
+};
+
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_DEFAULT	VDSO_COMPAT
+#else
+#define VDSO_DEFAULT	VDSO_ENABLED
+#endif
 
 /*
  * Should the kernel map a VDSO page into processes and pass its
  * address down to glibc upon exec()?
  */
-#ifdef CONFIG_PARAVIRT
-unsigned int __read_mostly vdso_enabled = 0;
-#else
-unsigned int __read_mostly vdso_enabled = 1;
-#endif
+unsigned int __read_mostly vdso_enabled = VDSO_DEFAULT;
 
 EXPORT_SYMBOL_GPL(vdso_enabled);
 
@@ -46,6 +56,123 @@ __setup("vdso=", vdso_setup);
 
 extern asmlinkage void sysenter_entry(void);
 
+static __init void reloc_symtab(Elf32_Ehdr *ehdr,
+				unsigned offset, unsigned size)
+{
+	Elf32_Sym *sym = (void *)ehdr + offset;
+	unsigned nsym = size / sizeof(*sym);
+	unsigned i;
+
+	for(i = 0; i < nsym; i++, sym++) {
+		if (sym->st_shndx == SHN_UNDEF ||
+		    sym->st_shndx == SHN_ABS)
+			continue;  /* skip */
+
+		if (sym->st_shndx > SHN_LORESERVE) {
+			printk(KERN_INFO "VDSO: unexpected st_shndx %x\n",
+			       sym->st_shndx);
+			continue;
+		}
+
+		switch(ELF_ST_TYPE(sym->st_info)) {
+		case STT_OBJECT:
+		case STT_FUNC:
+		case STT_SECTION:
+		case STT_FILE:
+			sym->st_value += VDSO_HIGH_BASE;
+		}
+	}
+}
+
+static __init void reloc_dyn(Elf32_Ehdr *ehdr, unsigned offset)
+{
+	Elf32_Dyn *dyn = (void *)ehdr + offset;
+
+	for(; dyn->d_tag != DT_NULL; dyn++)
+		switch(dyn->d_tag) {
+		case DT_PLTGOT:
+		case DT_HASH:
+		case DT_STRTAB:
+		case DT_SYMTAB:
+		case DT_RELA:
+		case DT_INIT:
+		case DT_FINI:
+		case DT_REL:
+		case DT_DEBUG:
+		case DT_JMPREL:
+		case DT_VERSYM:
+		case DT_VERDEF:
+		case DT_VERNEED:
+		case DT_ADDRRNGLO ... DT_ADDRRNGHI:
+			/* definitely pointers needing relocation */
+			dyn->d_un.d_ptr += VDSO_HIGH_BASE;
+			break;
+
+		case DT_ENCODING ... OLD_DT_LOOS-1:
+		case DT_LOOS ... DT_HIOS-1:
+			/* Tags above DT_ENCODING are pointers if
+			   they're even */
+			if (dyn->d_tag >= DT_ENCODING &&
+			    (dyn->d_tag & 1) == 0)
+				dyn->d_un.d_ptr += VDSO_HIGH_BASE;
+			break;
+
+		case DT_VERDEFNUM:
+		case DT_VERNEEDNUM:
+		case DT_FLAGS_1:
+		case DT_RELACOUNT:
+		case DT_RELCOUNT:
+		case DT_VALRNGLO ... DT_VALRNGHI:
+			/* definitely not pointers */
+			break;
+
+		case OLD_DT_LOOS ... DT_LOOS-1:
+		case DT_HIOS ... DT_VALRNGLO-1:
+		default:
+			if (dyn->d_tag > DT_ENCODING)
+				printk(KERN_INFO "VDSO: unexpected DT_tag %x\n",
+				       dyn->d_tag);
+			break;
+		}
+}
+
+static __init void relocate_vdso(Elf32_Ehdr *ehdr)
+{
+	Elf32_Phdr *phdr;
+	Elf32_Shdr *shdr;
+	int i;
+
+	BUG_ON(memcmp(ehdr->e_ident, ELFMAG, 4) != 0 ||
+	       !elf_check_arch(ehdr) ||
+	       ehdr->e_type != ET_DYN);
+
+	ehdr->e_entry += VDSO_HIGH_BASE;
+
+	/* rebase phdrs */
+	phdr = (void *)ehdr + ehdr->e_phoff;
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		phdr[i].p_vaddr += VDSO_HIGH_BASE;
+
+		/* relocate dynamic stuff */
+		if (phdr[i].p_type == PT_DYNAMIC)
+			reloc_dyn(ehdr, phdr[i].p_offset);
+	}
+
+	/* rebase sections */
+	shdr = (void *)ehdr + ehdr->e_shoff;
+	for(i = 0; i < ehdr->e_shnum; i++) {
+		if (!(shdr[i].sh_flags & SHF_ALLOC))
+			continue;
+
+		shdr[i].sh_addr += VDSO_HIGH_BASE;
+
+		if (shdr[i].sh_type == SHT_SYMTAB ||
+		    shdr[i].sh_type == SHT_DYNSYM)
+			reloc_symtab(ehdr, shdr[i].sh_offset,
+				     shdr[i].sh_size);
+	}
+}
+
 void enable_sep_cpu(void)
 {
 	int cpu = get_cpu();
@@ -56,14 +183,33 @@ void enable_sep_cpu(void)
 		return;
 	}
 
-	tss->ss1 = __KERNEL_CS;
-	tss->esp1 = sizeof(struct tss_struct) + (unsigned long) tss;
+	tss->x86_tss.ss1 = __KERNEL_CS;
+	tss->x86_tss.esp1 = sizeof(struct tss_struct) + (unsigned long) tss;
 	wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
-	wrmsr(MSR_IA32_SYSENTER_ESP, tss->esp1, 0);
+	wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.esp1, 0);
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) sysenter_entry, 0);
 	put_cpu();	
 }
 
+static struct vm_area_struct gate_vma;
+
+static int __init gate_vma_init(void)
+{
+	gate_vma.vm_mm = NULL;
+	gate_vma.vm_start = FIXADDR_USER_START;
+	gate_vma.vm_end = FIXADDR_USER_END;
+	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
+	gate_vma.vm_page_prot = __P101;
+	/*
+	 * Make sure the vDSO gets into every core dump.
+	 * Dumping its contents makes post-mortem fully interpretable later
+	 * without matching up the same kernel and hardware config to see
+	 * what PC values meant.
+	 */
+	gate_vma.vm_flags |= VM_ALWAYSDUMP;
+	return 0;
+}
+
 /*
  * These symbols are defined by vsyscall.o to mark the bounds
  * of the ELF DSO images included therein.
@@ -72,31 +218,48 @@ extern const char vsyscall_int80_start, vsyscall_int80_end;
 extern const char vsyscall_sysenter_start, vsyscall_sysenter_end;
 static struct page *syscall_pages[1];
 
+static void map_compat_vdso(int map)
+{
+	static int vdso_mapped;
+
+	if (map == vdso_mapped)
+		return;
+
+	vdso_mapped = map;
+
+	__set_fixmap(FIX_VDSO, page_to_pfn(syscall_pages[0]) << PAGE_SHIFT,
+		     map ? PAGE_READONLY_EXEC : PAGE_NONE);
+
+	/* flush stray tlbs */
+	flush_tlb_all();
+}
+
 int __init sysenter_setup(void)
 {
 	void *syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
+	const void *vsyscall;
+	size_t vsyscall_len;
+
 	syscall_pages[0] = virt_to_page(syscall_page);
 
-#ifdef CONFIG_COMPAT_VDSO
-	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY_EXEC);
+	gate_vma_init();
+
 	printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO));
-#endif
 
 	if (!boot_cpu_has(X86_FEATURE_SEP)) {
-		memcpy(syscall_page,
-		       &vsyscall_int80_start,
-		       &vsyscall_int80_end - &vsyscall_int80_start);
-		return 0;
+		vsyscall = &vsyscall_int80_start;
+		vsyscall_len = &vsyscall_int80_end - &vsyscall_int80_start;
+	} else {
+		vsyscall = &vsyscall_sysenter_start;
+		vsyscall_len = &vsyscall_sysenter_end - &vsyscall_sysenter_start;
 	}
 
-	memcpy(syscall_page,
-	       &vsyscall_sysenter_start,
-	       &vsyscall_sysenter_end - &vsyscall_sysenter_start);
+	memcpy(syscall_page, vsyscall, vsyscall_len);
+	relocate_vdso(syscall_page);
 
 	return 0;
 }
 
-#ifndef CONFIG_COMPAT_VDSO
 /* Defined in vsyscall-sysenter.S */
 extern void SYSENTER_RETURN;
 
@@ -105,36 +268,52 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
-	int ret;
+	int ret = 0;
+	bool compat;
 
 	down_write(&mm->mmap_sem);
-	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
-	if (IS_ERR_VALUE(addr)) {
-		ret = addr;
-		goto up_fail;
-	}
 
-	/*
-	 * MAYWRITE to allow gdb to COW and set breakpoints
-	 *
-	 * Make sure the vDSO gets into every core dump.
-	 * Dumping its contents makes post-mortem fully interpretable later
-	 * without matching up the same kernel and hardware config to see
-	 * what PC values meant.
-	 */
-	ret = install_special_mapping(mm, addr, PAGE_SIZE,
-				      VM_READ|VM_EXEC|
-				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
-				      VM_ALWAYSDUMP,
-				      syscall_pages);
-	if (ret)
-		goto up_fail;
+	/* Test compat mode once here, in case someone
+	   changes it via sysctl */
+	compat = (vdso_enabled == VDSO_COMPAT);
+
+	map_compat_vdso(compat);
+
+	if (compat)
+		addr = VDSO_HIGH_BASE;
+	else {
+		addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+		if (IS_ERR_VALUE(addr)) {
+			ret = addr;
+			goto up_fail;
+		}
+
+		/*
+		 * MAYWRITE to allow gdb to COW and set breakpoints
+		 *
+		 * Make sure the vDSO gets into every core dump.
+		 * Dumping its contents makes post-mortem fully
+		 * interpretable later without matching up the same
+		 * kernel and hardware config to see what PC values
+		 * meant.
+		 */
+		ret = install_special_mapping(mm, addr, PAGE_SIZE,
+					      VM_READ|VM_EXEC|
+					      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+					      VM_ALWAYSDUMP,
+					      syscall_pages);
+
+		if (ret)
+			goto up_fail;
+	}
 
 	current->mm->context.vdso = (void *)addr;
 	current_thread_info()->sysenter_return =
-				    (void *)VDSO_SYM(&SYSENTER_RETURN);
-up_fail:
+		(void *)VDSO_SYM(&SYSENTER_RETURN);
+
+  up_fail:
 	up_write(&mm->mmap_sem);
+
 	return ret;
 }
 
@@ -147,6 +326,11 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 
 struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
 {
+	struct mm_struct *mm = tsk->mm;
+
+	/* Check to see if this task was created in compat vdso mode */
+	if (mm && mm->context.vdso == (void *)VDSO_HIGH_BASE)
+		return &gate_vma;
 	return NULL;
 }
 
@@ -159,4 +343,3 @@ int in_gate_area_no_task(unsigned long addr)
 {
 	return 0;
 }
-#endif

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/trampoline.S

@@ -29,7 +29,7 @@
  *
  *	TYPE              VALUE
  *	R_386_32          startup_32_smp
- *	R_386_32          boot_gdt_table
+ *	R_386_32          boot_gdt
  */
 
 #include <linux/linkage.h>
@@ -62,8 +62,8 @@ r_base = .
 	 * to 32 bit.
 	 */
 
-	lidtl	boot_idt - r_base	# load idt with 0, 0
-	lgdtl	boot_gdt - r_base	# load gdt with whatever is appropriate
+	lidtl	boot_idt_descr - r_base	# load idt with 0, 0
+	lgdtl	boot_gdt_descr - r_base	# load gdt with whatever is appropriate
 
 	xor	%ax, %ax
 	inc	%ax		# protected mode (PE) bit
@@ -73,11 +73,11 @@ r_base = .
 
 	# These need to be in the same 64K segment as the above;
 	# hence we don't use the boot_gdt_descr defined in head.S
-boot_gdt:
+boot_gdt_descr:
 	.word	__BOOT_DS + 7			# gdt limit
-	.long	boot_gdt_table-__PAGE_OFFSET	# gdt base
+	.long	boot_gdt - __PAGE_OFFSET	# gdt base
 
-boot_idt:
+boot_idt_descr:
 	.word	0				# idt limit = 0
 	.long	0				# idt base = 0L
 

arch/i386/kernel/traps.c

@@ -476,8 +476,6 @@ static void __kprobes do_trap(int trapnr, int signr, char *str, int vm86,
 			      siginfo_t *info)
 {
 	struct task_struct *tsk = current;
-	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = trapnr;
 
 	if (regs->eflags & VM_MASK) {
 		if (vm86)
@@ -489,6 +487,18 @@ static void __kprobes do_trap(int trapnr, int signr, char *str, int vm86,
 		goto kernel_trap;
 
 	trap_signal: {
+		/*
+		 * We want error_code and trap_no set for userspace faults and
+		 * kernelspace faults which result in die(), but not
+		 * kernelspace faults which are fixed up.  die() gives the
+		 * process no chance to handle the signal and notice the
+		 * kernel fault information, so that won't result in polluting
+		 * the information about previously queued, but not yet
+		 * delivered, faults.  See also do_general_protection below.
+		 */
+		tsk->thread.error_code = error_code;
+		tsk->thread.trap_no = trapnr;
+
 		if (info)
 			force_sig_info(signr, info, tsk);
 		else
@@ -497,8 +507,11 @@ static void __kprobes do_trap(int trapnr, int signr, char *str, int vm86,
 	}
 
 	kernel_trap: {
-		if (!fixup_exception(regs))
+		if (!fixup_exception(regs)) {
+			tsk->thread.error_code = error_code;
+			tsk->thread.trap_no = trapnr;
 			die(str, regs, error_code);
+		}
 		return;
 	}
 
@@ -583,7 +596,7 @@ fastcall void __kprobes do_general_protection(struct pt_regs * regs,
 	 * and we set the offset field correctly. Then we let the CPU to
 	 * restart the faulting instruction.
 	 */
-	if (tss->io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY &&
+	if (tss->x86_tss.io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY &&
 	    thread->io_bitmap_ptr) {
 		memcpy(tss->io_bitmap, thread->io_bitmap_ptr,
 		       thread->io_bitmap_max);
@@ -596,16 +609,13 @@ fastcall void __kprobes do_general_protection(struct pt_regs * regs,
 				thread->io_bitmap_max, 0xff,
 				tss->io_bitmap_max - thread->io_bitmap_max);
 		tss->io_bitmap_max = thread->io_bitmap_max;
-		tss->io_bitmap_base = IO_BITMAP_OFFSET;
+		tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
 		tss->io_bitmap_owner = thread;
 		put_cpu();
 		return;
 	}
 	put_cpu();
 
-	current->thread.error_code = error_code;
-	current->thread.trap_no = 13;
-
 	if (regs->eflags & VM_MASK)
 		goto gp_in_vm86;
 
@@ -624,6 +634,8 @@ gp_in_vm86:
 
 gp_in_kernel:
 	if (!fixup_exception(regs)) {
+		current->thread.error_code = error_code;
+		current->thread.trap_no = 13;
 		if (notify_die(DIE_GPF, "general protection fault", regs,
 				error_code, 13, SIGSEGV) == NOTIFY_STOP)
 			return;
@@ -1018,9 +1030,7 @@ fastcall void do_spurious_interrupt_bug(struct pt_regs * regs,
 fastcall unsigned long patch_espfix_desc(unsigned long uesp,
 					  unsigned long kesp)
 {
-	int cpu = smp_processor_id();
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
-	struct desc_struct *gdt = (struct desc_struct *)cpu_gdt_descr->address;
+	struct desc_struct *gdt = __get_cpu_var(gdt_page).gdt;
 	unsigned long base = (kesp - uesp) & -THREAD_SIZE;
 	unsigned long new_kesp = kesp - base;
 	unsigned long lim_pages = (new_kesp | (THREAD_SIZE - 1)) >> PAGE_SHIFT;

arch/i386/kernel/tsc.c

@@ -200,13 +200,10 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data)
 {
 	struct cpufreq_freqs *freq = data;
 
-	if (val != CPUFREQ_RESUMECHANGE && val != CPUFREQ_SUSPENDCHANGE)
-		write_seqlock_irq(&xtime_lock);
-
 	if (!ref_freq) {
 		if (!freq->old){
 			ref_freq = freq->new;
-			goto end;
+			return 0;
 		}
 		ref_freq = freq->old;
 		loops_per_jiffy_ref = cpu_data[freq->cpu].loops_per_jiffy;
@@ -233,13 +230,10 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data)
 				 * TSC based sched_clock turns
 				 * to junk w/ cpufreq
 				 */
-				mark_tsc_unstable();
+				mark_tsc_unstable("cpufreq changes");
 			}
 		}
 	}
-end:
-	if (val != CPUFREQ_RESUMECHANGE && val != CPUFREQ_SUSPENDCHANGE)
-		write_sequnlock_irq(&xtime_lock);
 
 	return 0;
 }
@@ -281,11 +275,12 @@ static struct clocksource clocksource_tsc = {
 				  CLOCK_SOURCE_MUST_VERIFY,
 };
 
-void mark_tsc_unstable(void)
+void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
 		tsc_enabled = 0;
+		printk("Marking TSC unstable due to: %s.\n", reason);
 		/* Can be called before registration */
 		if (clocksource_tsc.mult)
 			clocksource_change_rating(&clocksource_tsc, 0);

arch/i386/kernel/verify_cpu.S

@@ -0,0 +1,65 @@
+/* Check if CPU has some minimum CPUID bits
+   This runs in 16bit mode so that the caller can still use the BIOS
+   to output errors on the screen */
+#include <asm/cpufeature.h>
+
+verify_cpu:
+	pushfl				# Save caller passed flags
+	pushl	$0			# Kill any dangerous flags
+	popfl
+
+#if CONFIG_X86_MINIMUM_CPU_MODEL >= 4
+	pushfl
+	orl	$(1<<18),(%esp)		# try setting AC
+	popfl
+	pushfl
+	popl    %eax
+	testl	$(1<<18),%eax
+	jz	bad
+#endif
+#if REQUIRED_MASK1 != 0
+	pushfl				# standard way to check for cpuid
+	popl	%eax
+	movl	%eax,%ebx
+	xorl	$0x200000,%eax
+	pushl	%eax
+	popfl
+	pushfl
+	popl	%eax
+	cmpl	%eax,%ebx
+	pushfl				# standard way to check for cpuid
+	popl	%eax
+	movl	%eax,%ebx
+	xorl	$0x200000,%eax
+	pushl	%eax
+	popfl
+	pushfl
+	popl	%eax
+	cmpl	%eax,%ebx
+	jz	bad			# REQUIRED_MASK1 != 0 requires CPUID
+
+	movl	$0x0,%eax		# See if cpuid 1 is implemented
+	cpuid
+	cmpl	$0x1,%eax
+	jb	bad			# no cpuid 1
+
+	movl    $0x1,%eax		# Does the cpu have what it takes
+	cpuid
+
+#if CONFIG_X86_MINIMUM_CPU_MODEL > 4
+#error	add proper model checking here
+#endif
+
+	andl	$REQUIRED_MASK1,%edx
+	xorl	$REQUIRED_MASK1,%edx
+	jnz	bad
+#endif /* REQUIRED_MASK1 */
+
+	popfl
+	xor	%eax,%eax
+	ret
+
+bad:
+	popfl
+	movl	$1,%eax
+	ret

arch/i386/kernel/vmi.c

@@ -26,6 +26,7 @@
 #include <linux/cpu.h>
 #include <linux/bootmem.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 #include <asm/vmi.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
@@ -56,7 +57,7 @@ static int disable_noidle;
 static int disable_vmi_timer;
 
 /* Cached VMI operations */
-struct {
+static struct {
 	void (*cpuid)(void /* non-c */);
 	void (*_set_ldt)(u32 selector);
 	void (*set_tr)(u32 selector);
@@ -65,16 +66,15 @@ struct {
 	void (*release_page)(u32, u32);
 	void (*set_pte)(pte_t, pte_t *, unsigned);
 	void (*update_pte)(pte_t *, unsigned);
-	void (*set_linear_mapping)(int, u32, u32, u32);
-	void (*flush_tlb)(int);
+	void (*set_linear_mapping)(int, void *, u32, u32);
+	void (*_flush_tlb)(int);
 	void (*set_initial_ap_state)(int, int);
 	void (*halt)(void);
   	void (*set_lazy_mode)(int mode);
 } vmi_ops;
 
-/* XXX move this to alternative.h */
-extern struct paravirt_patch __start_parainstructions[],
-	__stop_parainstructions[];
+/* Cached VMI operations */
+struct vmi_timer_ops vmi_timer_ops;
 
 /*
  * VMI patching routines.
@@ -83,11 +83,6 @@ extern struct paravirt_patch __start_parainstructions[],
 #define MNEM_JMP  0xe9
 #define MNEM_RET  0xc3
 
-static char irq_save_disable_callout[] = {
-	MNEM_CALL, 0, 0, 0, 0,
-	MNEM_CALL, 0, 0, 0, 0,
-	MNEM_RET
-};
 #define IRQ_PATCH_INT_MASK 0
 #define IRQ_PATCH_DISABLE  5
 
@@ -135,33 +130,17 @@ static unsigned patch_internal(int call, unsigned len, void *insns)
 static unsigned vmi_patch(u8 type, u16 clobbers, void *insns, unsigned len)
 {
 	switch (type) {
-		case PARAVIRT_IRQ_DISABLE:
+		case PARAVIRT_PATCH(irq_disable):
 			return patch_internal(VMI_CALL_DisableInterrupts, len, insns);
-		case PARAVIRT_IRQ_ENABLE:
+		case PARAVIRT_PATCH(irq_enable):
 			return patch_internal(VMI_CALL_EnableInterrupts, len, insns);
-		case PARAVIRT_RESTORE_FLAGS:
+		case PARAVIRT_PATCH(restore_fl):
 			return patch_internal(VMI_CALL_SetInterruptMask, len, insns);
-		case PARAVIRT_SAVE_FLAGS:
+		case PARAVIRT_PATCH(save_fl):
 			return patch_internal(VMI_CALL_GetInterruptMask, len, insns);
-        	case PARAVIRT_SAVE_FLAGS_IRQ_DISABLE:
-			if (len >= 10) {
-				patch_internal(VMI_CALL_GetInterruptMask, len, insns);
-				patch_internal(VMI_CALL_DisableInterrupts, len-5, insns+5);
-				return 10;
-			} else {
-				/*
-				 * You bastards didn't leave enough room to
-				 * patch save_flags_irq_disable inline.  Patch
-				 * to a helper
-				 */
-				BUG_ON(len < 5);
-				*(char *)insns = MNEM_CALL;
-				patch_offset(insns, irq_save_disable_callout);
-				return 5;
-			}
-		case PARAVIRT_INTERRUPT_RETURN:
+		case PARAVIRT_PATCH(iret):
 			return patch_internal(VMI_CALL_IRET, len, insns);
-		case PARAVIRT_STI_SYSEXIT:
+		case PARAVIRT_PATCH(irq_enable_sysexit):
 			return patch_internal(VMI_CALL_SYSEXIT, len, insns);
 		default:
 			break;
@@ -230,24 +209,24 @@ static void vmi_set_tr(void)
 static void vmi_load_esp0(struct tss_struct *tss,
 				   struct thread_struct *thread)
 {
-	tss->esp0 = thread->esp0;
+	tss->x86_tss.esp0 = thread->esp0;
 
 	/* This can only happen when SEP is enabled, no need to test "SEP"arately */
-	if (unlikely(tss->ss1 != thread->sysenter_cs)) {
-		tss->ss1 = thread->sysenter_cs;
+	if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
+		tss->x86_tss.ss1 = thread->sysenter_cs;
 		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
 	}
-	vmi_ops.set_kernel_stack(__KERNEL_DS, tss->esp0);
+	vmi_ops.set_kernel_stack(__KERNEL_DS, tss->x86_tss.esp0);
 }
 
 static void vmi_flush_tlb_user(void)
 {
-	vmi_ops.flush_tlb(VMI_FLUSH_TLB);
+	vmi_ops._flush_tlb(VMI_FLUSH_TLB);
 }
 
 static void vmi_flush_tlb_kernel(void)
 {
-	vmi_ops.flush_tlb(VMI_FLUSH_TLB | VMI_FLUSH_GLOBAL);
+	vmi_ops._flush_tlb(VMI_FLUSH_TLB | VMI_FLUSH_GLOBAL);
 }
 
 /* Stub to do nothing at all; used for delays and unimplemented calls */
@@ -255,18 +234,6 @@ static void vmi_nop(void)
 {
 }
 
-/* For NO_IDLE_HZ, we stop the clock when halting the kernel */
-static fastcall void vmi_safe_halt(void)
-{
-	int idle = vmi_stop_hz_timer();
-	vmi_ops.halt();
-	if (idle) {
-		local_irq_disable();
-		vmi_account_time_restart_hz_timer();
-		local_irq_enable();
-	}
-}
-
 #ifdef CONFIG_DEBUG_PAGE_TYPE
 
 #ifdef CONFIG_X86_PAE
@@ -370,8 +337,11 @@ static void vmi_check_page_type(u32 pfn, int type)
 #define vmi_check_page_type(p,t) do { } while (0)
 #endif
 
-static void vmi_map_pt_hook(int type, pte_t *va, u32 pfn)
+#ifdef CONFIG_HIGHPTE
+static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
 {
+	void *va = kmap_atomic(page, type);
+
 	/*
 	 * Internally, the VMI ROM must map virtual addresses to physical
 	 * addresses for processing MMU updates.  By the time MMU updates
@@ -385,8 +355,11 @@ static void vmi_map_pt_hook(int type, pte_t *va, u32 pfn)
 	 *  args:                 SLOT                 VA    COUNT PFN
 	 */
 	BUG_ON(type != KM_PTE0 && type != KM_PTE1);
-	vmi_ops.set_linear_mapping((type - KM_PTE0)+1, (u32)va, 1, pfn);
+	vmi_ops.set_linear_mapping((type - KM_PTE0)+1, va, 1, page_to_pfn(page));
+
+	return va;
 }
+#endif
 
 static void vmi_allocate_pt(u32 pfn)
 {
@@ -443,13 +416,13 @@ static void vmi_release_pd(u32 pfn)
         ((level) | (is_current_as(mm, user) ?                           \
                 (VMI_PAGE_DEFER | VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
 
-static void vmi_update_pte(struct mm_struct *mm, u32 addr, pte_t *ptep)
+static void vmi_update_pte(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
 	vmi_ops.update_pte(ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
 }
 
-static void vmi_update_pte_defer(struct mm_struct *mm, u32 addr, pte_t *ptep)
+static void vmi_update_pte_defer(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
 	vmi_ops.update_pte(ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 0));
@@ -462,7 +435,7 @@ static void vmi_set_pte(pte_t *ptep, pte_t pte)
 	vmi_ops.set_pte(pte, ptep, VMI_PAGE_PT);
 }
 
-static void vmi_set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pte)
+static void vmi_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
 {
 	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
 	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
@@ -516,7 +489,7 @@ static void vmi_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
 }
 
-void vmi_pmd_clear(pmd_t *pmd)
+static void vmi_pmd_clear(pmd_t *pmd)
 {
 	const pte_t pte = { 0 };
 	vmi_check_page_type(__pa(pmd) >> PAGE_SHIFT, VMI_PAGE_PMD);
@@ -525,8 +498,6 @@ void vmi_pmd_clear(pmd_t *pmd)
 #endif
 
 #ifdef CONFIG_SMP
-extern void setup_pda(void);
-
 static void __devinit
 vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 		     unsigned long start_esp)
@@ -551,13 +522,11 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 
 	ap.ds = __USER_DS;
 	ap.es = __USER_DS;
-	ap.fs = __KERNEL_PDA;
+	ap.fs = __KERNEL_PERCPU;
 	ap.gs = 0;
 
 	ap.eflags = 0;
 
-	setup_pda();
-
 #ifdef CONFIG_X86_PAE
 	/* efer should match BSP efer. */
 	if (cpu_has_nx) {
@@ -575,9 +544,9 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 }
 #endif
 
-static void vmi_set_lazy_mode(int mode)
+static void vmi_set_lazy_mode(enum paravirt_lazy_mode mode)
 {
-	static DEFINE_PER_CPU(int, lazy_mode);
+	static DEFINE_PER_CPU(enum paravirt_lazy_mode, lazy_mode);
 
 	if (!vmi_ops.set_lazy_mode)
 		return;
@@ -685,7 +654,7 @@ void vmi_bringup(void)
 {
  	/* We must establish the lowmem mapping for MMU ops to work */
 	if (vmi_ops.set_linear_mapping)
-		vmi_ops.set_linear_mapping(0, __PAGE_OFFSET, max_low_pfn, 0);
+		vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, max_low_pfn, 0);
 }
 
 /*
@@ -740,7 +709,6 @@ do {								\
 	}							\
 } while (0)
 
-
 /*
  * Activate the VMI interface and switch into paravirtualized mode
  */
@@ -796,12 +764,6 @@ static inline int __init activate_vmi(void)
 	para_fill(irq_disable, DisableInterrupts);
 	para_fill(irq_enable, EnableInterrupts);
 
-	/* irq_save_disable !!! sheer pain */
-	patch_offset(&irq_save_disable_callout[IRQ_PATCH_INT_MASK],
-		     (char *)paravirt_ops.save_fl);
-	patch_offset(&irq_save_disable_callout[IRQ_PATCH_DISABLE],
-		     (char *)paravirt_ops.irq_disable);
-
 	para_fill(wbinvd, WBINVD);
 	para_fill(read_tsc, RDTSC);
 
@@ -831,8 +793,8 @@ static inline int __init activate_vmi(void)
 	para_wrap(set_lazy_mode, vmi_set_lazy_mode, set_lazy_mode, SetLazyMode);
 
 	/* user and kernel flush are just handled with different flags to FlushTLB */
-	para_wrap(flush_tlb_user, vmi_flush_tlb_user, flush_tlb, FlushTLB);
-	para_wrap(flush_tlb_kernel, vmi_flush_tlb_kernel, flush_tlb, FlushTLB);
+	para_wrap(flush_tlb_user, vmi_flush_tlb_user, _flush_tlb, FlushTLB);
+	para_wrap(flush_tlb_kernel, vmi_flush_tlb_kernel, _flush_tlb, FlushTLB);
 	para_fill(flush_tlb_single, InvalPage);
 
 	/*
@@ -878,8 +840,13 @@ static inline int __init activate_vmi(void)
 		paravirt_ops.release_pt = vmi_release_pt;
 		paravirt_ops.release_pd = vmi_release_pd;
 	}
-	para_wrap(map_pt_hook, vmi_map_pt_hook, set_linear_mapping,
-		  SetLinearMapping);
+
+	/* Set linear is needed in all cases */
+	vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping);
+#ifdef CONFIG_HIGHPTE
+	if (vmi_ops.set_linear_mapping)
+		paravirt_ops.kmap_atomic_pte = vmi_kmap_atomic_pte;
+#endif
 
 	/*
 	 * These MUST always be patched.  Don't support indirect jumps
@@ -920,8 +887,8 @@ static inline int __init activate_vmi(void)
 		paravirt_ops.get_wallclock = vmi_get_wallclock;
 		paravirt_ops.set_wallclock = vmi_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-		paravirt_ops.setup_boot_clock = vmi_timer_setup_boot_alarm;
-		paravirt_ops.setup_secondary_clock = vmi_timer_setup_secondary_alarm;
+		paravirt_ops.setup_boot_clock = vmi_time_bsp_init;
+		paravirt_ops.setup_secondary_clock = vmi_time_ap_init;
 #endif
 		paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles;
  		paravirt_ops.get_cpu_khz = vmi_cpu_khz;
@@ -933,11 +900,7 @@ static inline int __init activate_vmi(void)
 		disable_vmi_timer = 1;
 	}
 
-	/* No idle HZ mode only works if VMI timer and no idle is enabled */
-	if (disable_noidle || disable_vmi_timer)
-		para_fill(safe_halt, Halt);
-	else
-		para_wrap(safe_halt, vmi_safe_halt, halt, Halt);
+	para_fill(safe_halt, Halt);
 
 	/*
 	 * Alternative instruction rewriting doesn't happen soon enough
@@ -945,7 +908,7 @@ static inline int __init activate_vmi(void)
 	 * to do this before IRQs get reenabled.  Fortunately, it is
 	 * idempotent.
 	 */
-	apply_paravirt(__start_parainstructions, __stop_parainstructions);
+	apply_paravirt(__parainstructions, __parainstructions_end);
 
 	vmi_bringup();
 

arch/i386/kernel/vmiclock.c

@@ -0,0 +1,318 @@
+/*
+ * VMI paravirtual timer support routines.
+ *
+ * Copyright (C) 2007, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ */
+
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/cpumask.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+
+#include <asm/vmi.h>
+#include <asm/vmi_time.h>
+#include <asm/arch_hooks.h>
+#include <asm/apicdef.h>
+#include <asm/apic.h>
+#include <asm/timer.h>
+
+#include <irq_vectors.h>
+#include "io_ports.h"
+
+#define VMI_ONESHOT  (VMI_ALARM_IS_ONESHOT  | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
+#define VMI_PERIODIC (VMI_ALARM_IS_PERIODIC | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
+
+static DEFINE_PER_CPU(struct clock_event_device, local_events);
+
+static inline u32 vmi_counter(u32 flags)
+{
+	/* Given VMI_ONESHOT or VMI_PERIODIC, return the corresponding
+	 * cycle counter. */
+	return flags & VMI_ALARM_COUNTER_MASK;
+}
+
+/* paravirt_ops.get_wallclock = vmi_get_wallclock */
+unsigned long vmi_get_wallclock(void)
+{
+	unsigned long long wallclock;
+	wallclock = vmi_timer_ops.get_wallclock(); // nsec
+	(void)do_div(wallclock, 1000000000);       // sec
+
+	return wallclock;
+}
+
+/* paravirt_ops.set_wallclock = vmi_set_wallclock */
+int vmi_set_wallclock(unsigned long now)
+{
+	return 0;
+}
+
+/* paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles */
+unsigned long long vmi_get_sched_cycles(void)
+{
+	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE);
+}
+
+/* paravirt_ops.get_cpu_khz = vmi_cpu_khz */
+unsigned long vmi_cpu_khz(void)
+{
+	unsigned long long khz;
+	khz = vmi_timer_ops.get_cycle_frequency();
+	(void)do_div(khz, 1000);
+	return khz;
+}
+
+static inline unsigned int vmi_get_timer_vector(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+	return FIRST_DEVICE_VECTOR;
+#else
+	return FIRST_EXTERNAL_VECTOR;
+#endif
+}
+
+/** vmi clockchip */
+#ifdef CONFIG_X86_LOCAL_APIC
+static unsigned int startup_timer_irq(unsigned int irq)
+{
+	unsigned long val = apic_read(APIC_LVTT);
+	apic_write(APIC_LVTT, vmi_get_timer_vector());
+
+	return (val & APIC_SEND_PENDING);
+}
+
+static void mask_timer_irq(unsigned int irq)
+{
+	unsigned long val = apic_read(APIC_LVTT);
+	apic_write(APIC_LVTT, val | APIC_LVT_MASKED);
+}
+
+static void unmask_timer_irq(unsigned int irq)
+{
+	unsigned long val = apic_read(APIC_LVTT);
+	apic_write(APIC_LVTT, val & ~APIC_LVT_MASKED);
+}
+
+static void ack_timer_irq(unsigned int irq)
+{
+	ack_APIC_irq();
+}
+
+static struct irq_chip vmi_chip __read_mostly = {
+	.name 		= "VMI-LOCAL",
+	.startup 	= startup_timer_irq,
+	.mask	 	= mask_timer_irq,
+	.unmask	 	= unmask_timer_irq,
+	.ack 		= ack_timer_irq
+};
+#endif
+
+/** vmi clockevent */
+#define VMI_ALARM_WIRED_IRQ0    0x00000000
+#define VMI_ALARM_WIRED_LVTT    0x00010000
+static int vmi_wiring = VMI_ALARM_WIRED_IRQ0;
+
+static inline int vmi_get_alarm_wiring(void)
+{
+	return vmi_wiring;
+}
+
+static void vmi_timer_set_mode(enum clock_event_mode mode,
+			       struct clock_event_device *evt)
+{
+	cycle_t now, cycles_per_hz;
+	BUG_ON(!irqs_disabled());
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_ONESHOT:
+		break;
+	case CLOCK_EVT_MODE_PERIODIC:
+		cycles_per_hz = vmi_timer_ops.get_cycle_frequency();
+		(void)do_div(cycles_per_hz, HZ);
+		now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_PERIODIC));
+		vmi_timer_ops.set_alarm(VMI_PERIODIC, now, cycles_per_hz);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		switch (evt->mode) {
+		case CLOCK_EVT_MODE_ONESHOT:
+			vmi_timer_ops.cancel_alarm(VMI_ONESHOT);
+			break;
+		case CLOCK_EVT_MODE_PERIODIC:
+			vmi_timer_ops.cancel_alarm(VMI_PERIODIC);
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static int vmi_timer_next_event(unsigned long delta,
+				struct clock_event_device *evt)
+{
+	/* Unfortunately, set_next_event interface only passes relative
+	 * expiry, but we want absolute expiry.  It'd be better if were
+	 * were passed an aboslute expiry, since a bunch of time may
+	 * have been stolen between the time the delta is computed and
+	 * when we set the alarm below. */
+	cycle_t now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_ONESHOT));
+
+	BUG_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
+	vmi_timer_ops.set_alarm(VMI_ONESHOT, now + delta, 0);
+	return 0;
+}
+
+static struct clock_event_device vmi_clockevent = {
+	.name		= "vmi-timer",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.shift		= 22,
+	.set_mode	= vmi_timer_set_mode,
+	.set_next_event = vmi_timer_next_event,
+	.rating         = 1000,
+	.irq		= 0,
+};
+
+static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = &__get_cpu_var(local_events);
+	evt->event_handler(evt);
+	return IRQ_HANDLED;
+}
+
+static struct irqaction vmi_clock_action  = {
+	.name 		= "vmi-timer",
+	.handler 	= vmi_timer_interrupt,
+	.flags 		= IRQF_DISABLED | IRQF_NOBALANCING,
+	.mask 		= CPU_MASK_ALL,
+};
+
+static void __devinit vmi_time_init_clockevent(void)
+{
+	cycle_t cycles_per_msec;
+	struct clock_event_device *evt;
+
+	int cpu = smp_processor_id();
+	evt = &__get_cpu_var(local_events);
+
+	/* Use cycles_per_msec since div_sc params are 32-bits. */
+	cycles_per_msec = vmi_timer_ops.get_cycle_frequency();
+	(void)do_div(cycles_per_msec, 1000);
+
+	memcpy(evt, &vmi_clockevent, sizeof(*evt));
+	/* Must pick .shift such that .mult fits in 32-bits.  Choosing
+	 * .shift to be 22 allows 2^(32-22) cycles per nano-seconds
+	 * before overflow. */
+	evt->mult = div_sc(cycles_per_msec, NSEC_PER_MSEC, evt->shift);
+	/* Upper bound is clockevent's use of ulong for cycle deltas. */
+	evt->max_delta_ns = clockevent_delta2ns(ULONG_MAX, evt);
+	evt->min_delta_ns = clockevent_delta2ns(1, evt);
+	evt->cpumask = cpumask_of_cpu(cpu);
+
+	printk(KERN_WARNING "vmi: registering clock event %s. mult=%lu shift=%u\n",
+	       evt->name, evt->mult, evt->shift);
+	clockevents_register_device(evt);
+}
+
+void __init vmi_time_init(void)
+{
+	/* Disable PIT: BIOSes start PIT CH0 with 18.2hz peridic. */
+	outb_p(0x3a, PIT_MODE); /* binary, mode 5, LSB/MSB, ch 0 */
+
+	vmi_time_init_clockevent();
+	setup_irq(0, &vmi_clock_action);
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+void __devinit vmi_time_bsp_init(void)
+{
+	/*
+	 * On APIC systems, we want local timers to fire on each cpu.  We do
+	 * this by programming LVTT to deliver timer events to the IRQ handler
+	 * for IRQ-0, since we can't re-use the APIC local timer handler
+	 * without interfering with that code.
+	 */
+	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
+	local_irq_disable();
+#ifdef CONFIG_X86_SMP
+	/*
+	 * XXX handle_percpu_irq only defined for SMP; we need to switch over
+	 * to using it, since this is a local interrupt, which each CPU must
+	 * handle individually without locking out or dropping simultaneous
+	 * local timers on other CPUs.  We also don't want to trigger the
+	 * quirk workaround code for interrupts which gets invoked from
+	 * handle_percpu_irq via eoi, so we use our own IRQ chip.
+	 */
+	set_irq_chip_and_handler_name(0, &vmi_chip, handle_percpu_irq, "lvtt");
+#else
+	set_irq_chip_and_handler_name(0, &vmi_chip, handle_edge_irq, "lvtt");
+#endif
+	vmi_wiring = VMI_ALARM_WIRED_LVTT;
+	apic_write(APIC_LVTT, vmi_get_timer_vector());
+	local_irq_enable();
+	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
+}
+
+void __devinit vmi_time_ap_init(void)
+{
+	vmi_time_init_clockevent();
+	apic_write(APIC_LVTT, vmi_get_timer_vector());
+}
+#endif
+
+/** vmi clocksource */
+
+static cycle_t read_real_cycles(void)
+{
+	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+}
+
+static struct clocksource clocksource_vmi = {
+	.name			= "vmi-timer",
+	.rating			= 450,
+	.read			= read_real_cycles,
+	.mask			= CLOCKSOURCE_MASK(64),
+	.mult			= 0, /* to be set */
+	.shift			= 22,
+	.flags			= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static int __init init_vmi_clocksource(void)
+{
+	cycle_t cycles_per_msec;
+
+	if (!vmi_timer_ops.get_cycle_frequency)
+		return 0;
+	/* Use khz2mult rather than hz2mult since hz arg is only 32-bits. */
+	cycles_per_msec = vmi_timer_ops.get_cycle_frequency();
+	(void)do_div(cycles_per_msec, 1000);
+
+	/* Note that clocksource.{mult, shift} converts in the opposite direction
+	 * as clockevents.  */
+	clocksource_vmi.mult = clocksource_khz2mult(cycles_per_msec,
+						    clocksource_vmi.shift);
+
+	printk(KERN_WARNING "vmi: registering clock source khz=%lld\n", cycles_per_msec);
+	return clocksource_register(&clocksource_vmi);
+
+}
+module_init(init_vmi_clocksource);

arch/i386/kernel/vmitime.c

@@ -1,482 +0,0 @@
-/*
- * VMI paravirtual timer support routines.
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to dhecht@vmware.com
- *
- */
-
-/*
- * Portions of this code from arch/i386/kernel/timers/timer_tsc.c.
- * Portions of the CONFIG_NO_IDLE_HZ code from arch/s390/kernel/time.c.
- * See comments there for proper credits.
- */
-
-#include <linux/spinlock.h>
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/jiffies.h>
-#include <linux/interrupt.h>
-#include <linux/kernel_stat.h>
-#include <linux/rcupdate.h>
-#include <linux/clocksource.h>
-
-#include <asm/timer.h>
-#include <asm/io.h>
-#include <asm/apic.h>
-#include <asm/div64.h>
-#include <asm/timer.h>
-#include <asm/desc.h>
-
-#include <asm/vmi.h>
-#include <asm/vmi_time.h>
-
-#include <mach_timer.h>
-#include <io_ports.h>
-
-#ifdef CONFIG_X86_LOCAL_APIC
-#define VMI_ALARM_WIRING VMI_ALARM_WIRED_LVTT
-#else
-#define VMI_ALARM_WIRING VMI_ALARM_WIRED_IRQ0
-#endif
-
-/* Cached VMI operations */
-struct vmi_timer_ops vmi_timer_ops;
-
-#ifdef CONFIG_NO_IDLE_HZ
-
-/* /proc/sys/kernel/hz_timer state. */
-int sysctl_hz_timer;
-
-/* Some stats */
-static DEFINE_PER_CPU(unsigned long, vmi_idle_no_hz_irqs);
-static DEFINE_PER_CPU(unsigned long, vmi_idle_no_hz_jiffies);
-static DEFINE_PER_CPU(unsigned long, idle_start_jiffies);
-
-#endif /* CONFIG_NO_IDLE_HZ */
-
-/* Number of alarms per second. By default this is CONFIG_VMI_ALARM_HZ. */
-static int alarm_hz = CONFIG_VMI_ALARM_HZ;
-
-/* Cache of the value get_cycle_frequency / HZ. */
-static signed long long cycles_per_jiffy;
-
-/* Cache of the value get_cycle_frequency / alarm_hz. */
-static signed long long cycles_per_alarm;
-
-/* The number of cycles accounted for by the 'jiffies'/'xtime' count.
- * Protected by xtime_lock. */
-static unsigned long long real_cycles_accounted_system;
-
-/* The number of cycles accounted for by update_process_times(), per cpu. */
-static DEFINE_PER_CPU(unsigned long long, process_times_cycles_accounted_cpu);
-
-/* The number of stolen cycles accounted, per cpu. */
-static DEFINE_PER_CPU(unsigned long long, stolen_cycles_accounted_cpu);
-
-/* Clock source. */
-static cycle_t read_real_cycles(void)
-{
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
-}
-
-static cycle_t read_available_cycles(void)
-{
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE);
-}
-
-#if 0
-static cycle_t read_stolen_cycles(void)
-{
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_STOLEN);
-}
-#endif  /*  0  */
-
-static struct clocksource clocksource_vmi = {
-	.name			= "vmi-timer",
-	.rating			= 450,
-	.read			= read_real_cycles,
-	.mask			= CLOCKSOURCE_MASK(64),
-	.mult			= 0, /* to be set */
-	.shift			= 22,
-	.flags			= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-
-/* Timer interrupt handler. */
-static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id);
-
-static struct irqaction vmi_timer_irq  = {
-	.handler = vmi_timer_interrupt,
-	.flags = IRQF_DISABLED,
-	.mask = CPU_MASK_NONE,
-	.name = "VMI-alarm",
-};
-
-/* Alarm rate */
-static int __init vmi_timer_alarm_rate_setup(char* str)
-{
-	int alarm_rate;
-	if (get_option(&str, &alarm_rate) == 1 && alarm_rate > 0) {
-		alarm_hz = alarm_rate;
-		printk(KERN_WARNING "VMI timer alarm HZ set to %d\n", alarm_hz);
-	}
-	return 1;
-}
-__setup("vmi_timer_alarm_hz=", vmi_timer_alarm_rate_setup);
-
-
-/* Initialization */
-static void vmi_get_wallclock_ts(struct timespec *ts)
-{
-	unsigned long long wallclock;
-	wallclock = vmi_timer_ops.get_wallclock(); // nsec units
-	ts->tv_nsec = do_div(wallclock, 1000000000);
-	ts->tv_sec = wallclock;
-}
-
-unsigned long vmi_get_wallclock(void)
-{
-	struct timespec ts;
-	vmi_get_wallclock_ts(&ts);
-	return ts.tv_sec;
-}
-
-int vmi_set_wallclock(unsigned long now)
-{
-	return -1;
-}
-
-unsigned long long vmi_get_sched_cycles(void)
-{
-	return read_available_cycles();
-}
-
-unsigned long vmi_cpu_khz(void)
-{
-	unsigned long long khz;
-
-	khz = vmi_timer_ops.get_cycle_frequency();
-	(void)do_div(khz, 1000);
-	return khz;
-}
-
-void __init vmi_time_init(void)
-{
-	unsigned long long cycles_per_sec, cycles_per_msec;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	setup_irq(0, &vmi_timer_irq);
-#ifdef CONFIG_X86_LOCAL_APIC
-	set_intr_gate(LOCAL_TIMER_VECTOR, apic_vmi_timer_interrupt);
-#endif
-
-	real_cycles_accounted_system = read_real_cycles();
-	per_cpu(process_times_cycles_accounted_cpu, 0) = read_available_cycles();
-
-	cycles_per_sec = vmi_timer_ops.get_cycle_frequency();
-	cycles_per_jiffy = cycles_per_sec;
-	(void)do_div(cycles_per_jiffy, HZ);
-	cycles_per_alarm = cycles_per_sec;
-	(void)do_div(cycles_per_alarm, alarm_hz);
-	cycles_per_msec = cycles_per_sec;
-	(void)do_div(cycles_per_msec, 1000);
-
-	printk(KERN_WARNING "VMI timer cycles/sec = %llu ; cycles/jiffy = %llu ;"
-	       "cycles/alarm = %llu\n", cycles_per_sec, cycles_per_jiffy,
-	       cycles_per_alarm);
-
-	clocksource_vmi.mult = clocksource_khz2mult(cycles_per_msec,
-						    clocksource_vmi.shift);
-	if (clocksource_register(&clocksource_vmi))
-		printk(KERN_WARNING "Error registering VMITIME clocksource.");
-
-	/* Disable PIT. */
-	outb_p(0x3a, PIT_MODE); /* binary, mode 5, LSB/MSB, ch 0 */
-
-	/* schedule the alarm. do this in phase with process_times_cycles_accounted_cpu
-	 * reduce the latency calling update_process_times. */
-	vmi_timer_ops.set_alarm(
-		      VMI_ALARM_WIRED_IRQ0 | VMI_ALARM_IS_PERIODIC | VMI_CYCLES_AVAILABLE,
-		      per_cpu(process_times_cycles_accounted_cpu, 0) + cycles_per_alarm,
-		      cycles_per_alarm);
-
-	local_irq_restore(flags);
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-
-void __init vmi_timer_setup_boot_alarm(void)
-{
-	local_irq_disable();
-
-	/* Route the interrupt to the correct vector. */
-	apic_write_around(APIC_LVTT, LOCAL_TIMER_VECTOR);
-
-	/* Cancel the IRQ0 wired alarm, and setup the LVTT alarm. */
-	vmi_timer_ops.cancel_alarm(VMI_CYCLES_AVAILABLE);
-	vmi_timer_ops.set_alarm(
-		      VMI_ALARM_WIRED_LVTT | VMI_ALARM_IS_PERIODIC | VMI_CYCLES_AVAILABLE,
-		      per_cpu(process_times_cycles_accounted_cpu, 0) + cycles_per_alarm,
-		      cycles_per_alarm);
-	local_irq_enable();
-}
-
-/* Initialize the time accounting variables for an AP on an SMP system.
- * Also, set the local alarm for the AP. */
-void __devinit vmi_timer_setup_secondary_alarm(void)
-{
-	int cpu = smp_processor_id();
-
-	/* Route the interrupt to the correct vector. */
-	apic_write_around(APIC_LVTT, LOCAL_TIMER_VECTOR);
-
-	per_cpu(process_times_cycles_accounted_cpu, cpu) = read_available_cycles();
-
-	vmi_timer_ops.set_alarm(
-		      VMI_ALARM_WIRED_LVTT | VMI_ALARM_IS_PERIODIC | VMI_CYCLES_AVAILABLE,
-		      per_cpu(process_times_cycles_accounted_cpu, cpu) + cycles_per_alarm,
-		      cycles_per_alarm);
-}
-
-#endif
-
-/* Update system wide (real) time accounting (e.g. jiffies, xtime). */
-static void vmi_account_real_cycles(unsigned long long cur_real_cycles)
-{
-	long long cycles_not_accounted;
-
-	write_seqlock(&xtime_lock);
-
-	cycles_not_accounted = cur_real_cycles - real_cycles_accounted_system;
-	while (cycles_not_accounted >= cycles_per_jiffy) {
-		/* systems wide jiffies. */
-		do_timer(1);
-
-		cycles_not_accounted -= cycles_per_jiffy;
-		real_cycles_accounted_system += cycles_per_jiffy;
-	}
-
-	write_sequnlock(&xtime_lock);
-}
-
-/* Update per-cpu process times. */
-static void vmi_account_process_times_cycles(struct pt_regs *regs, int cpu,
-					     unsigned long long cur_process_times_cycles)
-{
-	long long cycles_not_accounted;
-	cycles_not_accounted = cur_process_times_cycles -
-		per_cpu(process_times_cycles_accounted_cpu, cpu);
-
-	while (cycles_not_accounted >= cycles_per_jiffy) {
-		/* Account time to the current process.  This includes
-		 * calling into the scheduler to decrement the timeslice
-		 * and possibly reschedule.*/
-		update_process_times(user_mode(regs));
-		/* XXX handle /proc/profile multiplier.  */
-		profile_tick(CPU_PROFILING);
-
-		cycles_not_accounted -= cycles_per_jiffy;
-		per_cpu(process_times_cycles_accounted_cpu, cpu) += cycles_per_jiffy;
-	}
-}
-
-#ifdef CONFIG_NO_IDLE_HZ
-/* Update per-cpu idle times.  Used when a no-hz halt is ended. */
-static void vmi_account_no_hz_idle_cycles(int cpu,
-					  unsigned long long cur_process_times_cycles)
-{
-	long long cycles_not_accounted;
-	unsigned long no_idle_hz_jiffies = 0;
-
-	cycles_not_accounted = cur_process_times_cycles -
-		per_cpu(process_times_cycles_accounted_cpu, cpu);
-
-	while (cycles_not_accounted >= cycles_per_jiffy) {
-		no_idle_hz_jiffies++;
-		cycles_not_accounted -= cycles_per_jiffy;
-		per_cpu(process_times_cycles_accounted_cpu, cpu) += cycles_per_jiffy;
-	}
-	/* Account time to the idle process. */
-	account_steal_time(idle_task(cpu), jiffies_to_cputime(no_idle_hz_jiffies));
-}
-#endif
-
-/* Update per-cpu stolen time. */
-static void vmi_account_stolen_cycles(int cpu,
-				      unsigned long long cur_real_cycles,
-				      unsigned long long cur_avail_cycles)
-{
-	long long stolen_cycles_not_accounted;
-	unsigned long stolen_jiffies = 0;
-
-	if (cur_real_cycles < cur_avail_cycles)
-		return;
-
-	stolen_cycles_not_accounted = cur_real_cycles - cur_avail_cycles -
-		per_cpu(stolen_cycles_accounted_cpu, cpu);
-
-	while (stolen_cycles_not_accounted >= cycles_per_jiffy) {
-		stolen_jiffies++;
-		stolen_cycles_not_accounted -= cycles_per_jiffy;
-		per_cpu(stolen_cycles_accounted_cpu, cpu) += cycles_per_jiffy;
-	}
-	/* HACK: pass NULL to force time onto cpustat->steal. */
-	account_steal_time(NULL, jiffies_to_cputime(stolen_jiffies));
-}
-
-/* Body of either IRQ0 interrupt handler (UP no local-APIC) or
- * local-APIC LVTT interrupt handler (UP & local-APIC or SMP). */
-static void vmi_local_timer_interrupt(int cpu)
-{
-	unsigned long long cur_real_cycles, cur_process_times_cycles;
-
-	cur_real_cycles = read_real_cycles();
-	cur_process_times_cycles = read_available_cycles();
-	/* Update system wide (real) time state (xtime, jiffies). */
-	vmi_account_real_cycles(cur_real_cycles);
-	/* Update per-cpu process times. */
-	vmi_account_process_times_cycles(get_irq_regs(), cpu, cur_process_times_cycles);
-        /* Update time stolen from this cpu by the hypervisor. */
-	vmi_account_stolen_cycles(cpu, cur_real_cycles, cur_process_times_cycles);
-}
-
-#ifdef CONFIG_NO_IDLE_HZ
-
-/* Must be called only from idle loop, with interrupts disabled. */
-int vmi_stop_hz_timer(void)
-{
-	/* Note that cpu_set, cpu_clear are (SMP safe) atomic on x86. */
-
-	unsigned long seq, next;
-	unsigned long long real_cycles_expiry;
-	int cpu = smp_processor_id();
-
-	BUG_ON(!irqs_disabled());
-	if (sysctl_hz_timer != 0)
-		return 0;
-
-	cpu_set(cpu, nohz_cpu_mask);
-	smp_mb();
-
-	if (rcu_needs_cpu(cpu) || local_softirq_pending() ||
-	    (next = next_timer_interrupt(),
-	     time_before_eq(next, jiffies + HZ/CONFIG_VMI_ALARM_HZ))) {
-		cpu_clear(cpu, nohz_cpu_mask);
-		return 0;
-	}
-
-	/* Convert jiffies to the real cycle counter. */
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		real_cycles_expiry = real_cycles_accounted_system +
-			(long)(next - jiffies) * cycles_per_jiffy;
-	} while (read_seqretry(&xtime_lock, seq));
-
-	/* This cpu is going idle. Disable the periodic alarm. */
-	vmi_timer_ops.cancel_alarm(VMI_CYCLES_AVAILABLE);
-	per_cpu(idle_start_jiffies, cpu) = jiffies;
-	/* Set the real time alarm to expire at the next event. */
-	vmi_timer_ops.set_alarm(
-		VMI_ALARM_WIRING | VMI_ALARM_IS_ONESHOT | VMI_CYCLES_REAL,
-		real_cycles_expiry, 0);
-	return 1;
-}
-
-static void vmi_reenable_hz_timer(int cpu)
-{
-	/* For /proc/vmi/info idle_hz stat. */
-	per_cpu(vmi_idle_no_hz_jiffies, cpu) += jiffies - per_cpu(idle_start_jiffies, cpu);
-	per_cpu(vmi_idle_no_hz_irqs, cpu)++;
-
-	/* Don't bother explicitly cancelling the one-shot alarm -- at
-	 * worse we will receive a spurious timer interrupt. */
-	vmi_timer_ops.set_alarm(
-		      VMI_ALARM_WIRING | VMI_ALARM_IS_PERIODIC | VMI_CYCLES_AVAILABLE,
-		      per_cpu(process_times_cycles_accounted_cpu, cpu) + cycles_per_alarm,
-		      cycles_per_alarm);
-	/* Indicate this cpu is no longer nohz idle. */
-	cpu_clear(cpu, nohz_cpu_mask);
-}
-
-/* Called from interrupt handlers when (local) HZ timer is disabled. */
-void vmi_account_time_restart_hz_timer(void)
-{
-	unsigned long long cur_real_cycles, cur_process_times_cycles;
-	int cpu = smp_processor_id();
-
-	BUG_ON(!irqs_disabled());
-	/* Account the time during which the HZ timer was disabled. */
-	cur_real_cycles = read_real_cycles();
-	cur_process_times_cycles = read_available_cycles();
-	/* Update system wide (real) time state (xtime, jiffies). */
-	vmi_account_real_cycles(cur_real_cycles);
-	/* Update per-cpu idle times. */
-	vmi_account_no_hz_idle_cycles(cpu, cur_process_times_cycles);
-        /* Update time stolen from this cpu by the hypervisor. */
-	vmi_account_stolen_cycles(cpu, cur_real_cycles, cur_process_times_cycles);
-	/* Reenable the hz timer. */
-	vmi_reenable_hz_timer(cpu);
-}
-
-#endif /* CONFIG_NO_IDLE_HZ */
-
-/* UP (and no local-APIC) VMI-timer alarm interrupt handler.
- * Handler for IRQ0. Not used when SMP or X86_LOCAL_APIC after
- * APIC setup and setup_boot_vmi_alarm() is called.  */
-static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
-{
-	vmi_local_timer_interrupt(smp_processor_id());
-	return IRQ_HANDLED;
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-
-/* SMP VMI-timer alarm interrupt handler. Handler for LVTT vector.
- * Also used in UP when CONFIG_X86_LOCAL_APIC.
- * The wrapper code is from arch/i386/kernel/apic.c#smp_apic_timer_interrupt. */
-void smp_apic_vmi_timer_interrupt(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-	int cpu = smp_processor_id();
-
-	/*
-	 * the NMI deadlock-detector uses this.
-	 */
-        per_cpu(irq_stat,cpu).apic_timer_irqs++;
-
-	/*
-	 * NOTE! We'd better ACK the irq immediately,
-	 * because timer handling can be slow.
-	 */
-	ack_APIC_irq();
-
-	/*
-	 * update_process_times() expects us to have done irq_enter().
-	 * Besides, if we don't timer interrupts ignore the global
-	 * interrupt lock, which is the WrongThing (tm) to do.
-	 */
-	irq_enter();
-	vmi_local_timer_interrupt(cpu);
-	irq_exit();
-	set_irq_regs(old_regs);
-}
-
-#endif  /* CONFIG_X86_LOCAL_APIC */

arch/i386/kernel/vmlinux.lds.S

@@ -26,12 +26,11 @@ OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
 OUTPUT_ARCH(i386)
 ENTRY(phys_startup_32)
 jiffies = jiffies_64;
-_proxy_pda = 1;
 
 PHDRS {
 	text PT_LOAD FLAGS(5);	/* R_E */
 	data PT_LOAD FLAGS(7);	/* RWE */
-	note PT_NOTE FLAGS(4);	/* R__ */
+	note PT_NOTE FLAGS(0);	/* ___ */
 }
 SECTIONS
 {
@@ -61,8 +60,6 @@ SECTIONS
   	__stop___ex_table = .;
   }
 
-  RODATA
-
   BUG_TABLE
 
   . = ALIGN(4);
@@ -72,6 +69,8 @@ SECTIONS
   	__tracedata_end = .;
   }
 
+  RODATA
+
   /* writeable */
   . = ALIGN(4096);
   .data : AT(ADDR(.data) - LOAD_OFFSET) {	/* Data */
@@ -117,22 +116,11 @@ SECTIONS
 
   /* might get freed after init */
   . = ALIGN(4096);
-  .smp_altinstructions : AT(ADDR(.smp_altinstructions) - LOAD_OFFSET) {
-	__smp_alt_begin = .;
-	__smp_alt_instructions = .;
-	*(.smp_altinstructions)
-	__smp_alt_instructions_end = .;
-  }
-  . = ALIGN(4);
   .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
   	__smp_locks = .;
 	*(.smp_locks)
 	__smp_locks_end = .;
   }
-  .smp_altinstr_replacement : AT(ADDR(.smp_altinstr_replacement) - LOAD_OFFSET) {
-	*(.smp_altinstr_replacement)
-  	__smp_alt_end = .;
-  }
   /* will be freed after init
    * Following ALIGN() is required to make sure no other data falls on the
    * same page where __smp_alt_end is pointing as that page might be freed
@@ -178,9 +166,9 @@ SECTIONS
   }
   . = ALIGN(4);
   .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
-  	__start_parainstructions = .;
+  	__parainstructions = .;
 	*(.parainstructions)
-  	__stop_parainstructions = .;
+  	__parainstructions_end = .;
   }
   /* .exit.text is discard at runtime, not link time, to deal with references
      from .altinstructions and .eh_frame */
@@ -194,7 +182,7 @@ SECTIONS
 	__initramfs_end = .;
   }
 #endif
-  . = ALIGN(L1_CACHE_BYTES);
+  . = ALIGN(4096);
   .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
 	__per_cpu_start = .;
 	*(.data.percpu)

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/lib/bitops.c

@@ -43,7 +43,7 @@ EXPORT_SYMBOL(find_next_bit);
  */
 int find_next_zero_bit(const unsigned long *addr, int size, int offset)
 {
-	unsigned long * p = ((unsigned long *) addr) + (offset >> 5);
+	const unsigned long *p = addr + (offset >> 5);
 	int set = 0, bit = offset & 31, res;
 
 	if (bit) {
@@ -64,7 +64,7 @@ int find_next_zero_bit(const unsigned long *addr, int size, int offset)
 	/*
 	 * No zero yet, search remaining full bytes for a zero
 	 */
-	res = find_first_zero_bit (p, size - 32 * (p - (unsigned long *) addr));
+	res = find_first_zero_bit(p, size - 32 * (p - addr));
 	return (offset + set + res);
 }
 EXPORT_SYMBOL(find_next_zero_bit);

arch/i386/lib/checksum.S

@@ -25,6 +25,8 @@
  *		2 of the License, or (at your option) any later version.
  */
 
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
 #include <asm/errno.h>
 				
 /*
@@ -36,8 +38,6 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
  */
 		
 .text
-.align 4
-.globl csum_partial								
 		
 #ifndef CONFIG_X86_USE_PPRO_CHECKSUM
 
@@ -48,9 +48,14 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
 	   * Fortunately, it is easy to convert 2-byte alignment to 4-byte
 	   * alignment for the unrolled loop.
 	   */		
-csum_partial:	
+ENTRY(csum_partial)
+	CFI_STARTPROC
 	pushl %esi
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET esi, 0
 	pushl %ebx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ebx, 0
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
 	movl 12(%esp),%esi	# Function arg: unsigned char *buff
@@ -128,16 +133,27 @@ csum_partial:
 	roll $8, %eax
 8:
 	popl %ebx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ebx
 	popl %esi
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE esi
 	ret
+	CFI_ENDPROC
+ENDPROC(csum_partial)
 
 #else
 
 /* Version for PentiumII/PPro */
 
-csum_partial:
+ENTRY(csum_partial)
+	CFI_STARTPROC
 	pushl %esi
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET esi, 0
 	pushl %ebx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ebx, 0
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
 	movl 12(%esp),%esi	# Function arg:	const unsigned char *buf
@@ -245,8 +261,14 @@ csum_partial:
 	roll $8, %eax
 90: 
 	popl %ebx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ebx
 	popl %esi
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE esi
 	ret
+	CFI_ENDPROC
+ENDPROC(csum_partial)
 				
 #endif
 
@@ -278,19 +300,24 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
 	.long 9999b, 6002f	;	\
 	.previous
 
-.align 4
-.globl csum_partial_copy_generic
-				
 #ifndef CONFIG_X86_USE_PPRO_CHECKSUM
 
 #define ARGBASE 16		
 #define FP		12
 		
-csum_partial_copy_generic:
+ENTRY(csum_partial_copy_generic)
+	CFI_STARTPROC
 	subl  $4,%esp	
+	CFI_ADJUST_CFA_OFFSET 4
 	pushl %edi
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET edi, 0
 	pushl %esi
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET esi, 0
 	pushl %ebx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ebx, 0
 	movl ARGBASE+16(%esp),%eax	# sum
 	movl ARGBASE+12(%esp),%ecx	# len
 	movl ARGBASE+4(%esp),%esi	# src
@@ -400,10 +427,19 @@ DST(	movb %cl, (%edi)	)
 .previous
 
 	popl %ebx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ebx
 	popl %esi
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE esi
 	popl %edi
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE edi
 	popl %ecx			# equivalent to addl $4,%esp
+	CFI_ADJUST_CFA_OFFSET -4
 	ret	
+	CFI_ENDPROC
+ENDPROC(csum_partial_copy_generic)
 
 #else
 
@@ -421,10 +457,17 @@ DST(	movb %cl, (%edi)	)
 
 #define ARGBASE 12
 		
-csum_partial_copy_generic:
+ENTRY(csum_partial_copy_generic)
+	CFI_STARTPROC
 	pushl %ebx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ebx, 0
 	pushl %edi
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET edi, 0
 	pushl %esi
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET esi, 0
 	movl ARGBASE+4(%esp),%esi	#src
 	movl ARGBASE+8(%esp),%edi	#dst	
 	movl ARGBASE+12(%esp),%ecx	#len
@@ -485,9 +528,17 @@ DST(	movb %dl, (%edi)         )
 .previous				
 
 	popl %esi
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE esi
 	popl %edi
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE edi
 	popl %ebx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ebx
 	ret
+	CFI_ENDPROC
+ENDPROC(csum_partial_copy_generic)
 				
 #undef ROUND
 #undef ROUND1		

arch/i386/lib/getuser.S

@@ -8,6 +8,8 @@
  * return an error value in addition to the "real"
  * return value.
  */
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
 #include <asm/thread_info.h>
 
 
@@ -24,19 +26,19 @@
  */
 
 .text
-.align 4
-.globl __get_user_1
-__get_user_1:
+ENTRY(__get_user_1)
+	CFI_STARTPROC
 	GET_THREAD_INFO(%edx)
 	cmpl TI_addr_limit(%edx),%eax
 	jae bad_get_user
 1:	movzbl (%eax),%edx
 	xorl %eax,%eax
 	ret
+	CFI_ENDPROC
+ENDPROC(__get_user_1)
 
-.align 4
-.globl __get_user_2
-__get_user_2:
+ENTRY(__get_user_2)
+	CFI_STARTPROC
 	addl $1,%eax
 	jc bad_get_user
 	GET_THREAD_INFO(%edx)
@@ -45,10 +47,11 @@ __get_user_2:
 2:	movzwl -1(%eax),%edx
 	xorl %eax,%eax
 	ret
+	CFI_ENDPROC
+ENDPROC(__get_user_2)
 
-.align 4
-.globl __get_user_4
-__get_user_4:
+ENTRY(__get_user_4)
+	CFI_STARTPROC
 	addl $3,%eax
 	jc bad_get_user
 	GET_THREAD_INFO(%edx)
@@ -57,11 +60,16 @@ __get_user_4:
 3:	movl -3(%eax),%edx
 	xorl %eax,%eax
 	ret
+	CFI_ENDPROC
+ENDPROC(__get_user_4)
 
 bad_get_user:
+	CFI_STARTPROC
 	xorl %edx,%edx
 	movl $-14,%eax
 	ret
+	CFI_ENDPROC
+END(bad_get_user)
 
 .section __ex_table,"a"
 	.long 1b,bad_get_user

arch/i386/lib/putuser.S

@@ -8,6 +8,8 @@
  * return an error value in addition to the "real"
  * return value.
  */
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
 #include <asm/thread_info.h>
 
 
@@ -23,23 +25,28 @@
  * as they get called from within inline assembly.
  */
 
-#define ENTER	pushl %ebx ; GET_THREAD_INFO(%ebx)
-#define EXIT	popl %ebx ; ret
+#define ENTER	CFI_STARTPROC ; \
+		pushl %ebx ; \
+		CFI_ADJUST_CFA_OFFSET 4 ; \
+		CFI_REL_OFFSET ebx, 0 ; \
+		GET_THREAD_INFO(%ebx)
+#define EXIT	popl %ebx ; \
+		CFI_ADJUST_CFA_OFFSET -4 ; \
+		CFI_RESTORE ebx ; \
+		ret ; \
+		CFI_ENDPROC
 
 .text
-.align 4
-.globl __put_user_1
-__put_user_1:
+ENTRY(__put_user_1)
 	ENTER
 	cmpl TI_addr_limit(%ebx),%ecx
 	jae bad_put_user
 1:	movb %al,(%ecx)
 	xorl %eax,%eax
 	EXIT
+ENDPROC(__put_user_1)
 
-.align 4
-.globl __put_user_2
-__put_user_2:
+ENTRY(__put_user_2)
 	ENTER
 	movl TI_addr_limit(%ebx),%ebx
 	subl $1,%ebx
@@ -48,10 +55,9 @@ __put_user_2:
 2:	movw %ax,(%ecx)
 	xorl %eax,%eax
 	EXIT
+ENDPROC(__put_user_2)
 
-.align 4
-.globl __put_user_4
-__put_user_4:
+ENTRY(__put_user_4)
 	ENTER
 	movl TI_addr_limit(%ebx),%ebx
 	subl $3,%ebx
@@ -60,10 +66,9 @@ __put_user_4:
 3:	movl %eax,(%ecx)
 	xorl %eax,%eax
 	EXIT
+ENDPROC(__put_user_4)
 
-.align 4
-.globl __put_user_8
-__put_user_8:
+ENTRY(__put_user_8)
 	ENTER
 	movl TI_addr_limit(%ebx),%ebx
 	subl $7,%ebx
@@ -73,10 +78,16 @@ __put_user_8:
 5:	movl %edx,4(%ecx)
 	xorl %eax,%eax
 	EXIT
+ENDPROC(__put_user_8)
 
 bad_put_user:
+	CFI_STARTPROC simple
+	CFI_DEF_CFA esp, 2*4
+	CFI_OFFSET eip, -1*4
+	CFI_OFFSET ebx, -2*4
 	movl $-14,%eax
 	EXIT
+END(bad_put_user)
 
 .section __ex_table,"a"
 	.long 1b,bad_put_user

arch/i386/lib/usercopy.c

@@ -716,7 +716,6 @@ do {									\
 unsigned long __copy_to_user_ll(void __user *to, const void *from,
 				unsigned long n)
 {
-	BUG_ON((long) n < 0);
 #ifndef CONFIG_X86_WP_WORKS_OK
 	if (unlikely(boot_cpu_data.wp_works_ok == 0) &&
 			((unsigned long )to) < TASK_SIZE) {
@@ -785,7 +784,6 @@ EXPORT_SYMBOL(__copy_to_user_ll);
 unsigned long __copy_from_user_ll(void *to, const void __user *from,
 					unsigned long n)
 {
-	BUG_ON((long)n < 0);
 	if (movsl_is_ok(to, from, n))
 		__copy_user_zeroing(to, from, n);
 	else
@@ -797,7 +795,6 @@ EXPORT_SYMBOL(__copy_from_user_ll);
 unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
 					 unsigned long n)
 {
-	BUG_ON((long)n < 0);
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
@@ -810,7 +807,6 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero);
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 					unsigned long n)
 {
-	BUG_ON((long)n < 0);
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if ( n > 64 && cpu_has_xmm2)
                 n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -825,7 +821,6 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
 					unsigned long n)
 {
-	BUG_ON((long)n < 0);
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if ( n > 64 && cpu_has_xmm2)
                 n = __copy_user_intel_nocache(to, from, n);
@@ -853,7 +848,6 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr
 unsigned long
 copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	BUG_ON((long) n < 0);
 	if (access_ok(VERIFY_WRITE, to, n))
 		n = __copy_to_user(to, from, n);
 	return n;
@@ -879,7 +873,6 @@ EXPORT_SYMBOL(copy_to_user);
 unsigned long
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	BUG_ON((long) n < 0);
 	if (access_ok(VERIFY_READ, from, n))
 		n = __copy_from_user(to, from, n);
 	else

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;

arch/i386/mach-generic/es7000.c

@@ -25,4 +25,45 @@ static int probe_es7000(void)
 	return 0;
 }
 
+extern void es7000_sw_apic(void);
+static void __init enable_apic_mode(void)
+{
+	es7000_sw_apic();
+	return;
+}
+
+static __init int mps_oem_check(struct mp_config_table *mpc, char *oem,
+		char *productid)
+{
+	if (mpc->mpc_oemptr) {
+		struct mp_config_oemtable *oem_table =
+			(struct mp_config_oemtable *)mpc->mpc_oemptr;
+		if (!strncmp(oem, "UNISYS", 6))
+			return parse_unisys_oem((char *)oem_table);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_ACPI
+/* Hook from generic ACPI tables.c */
+static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	unsigned long oem_addr;
+	if (!find_unisys_acpi_oem_table(&oem_addr)) {
+		if (es7000_check_dsdt())
+			return parse_unisys_oem((char *)oem_addr);
+		else {
+			setup_unisys();
+			return 1;
+		}
+	}
+	return 0;
+}
+#else
+static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return 0;
+}
+#endif
+
 struct genapic apic_es7000 = APIC_INIT("es7000", probe_es7000);

arch/i386/mach-voyager/voyager_smp.c

@@ -573,15 +573,7 @@ do_boot_cpu(__u8 cpu)
 	/* init_tasks (in sched.c) is indexed logically */
 	stack_start.esp = (void *) idle->thread.esp;
 
-	/* Pre-allocate and initialize the CPU's GDT and PDA so it
-	   doesn't have to do any memory allocation during the
-	   delicate CPU-bringup phase. */
-	if (!init_gdt(cpu, idle)) {
-		printk(KERN_INFO "Couldn't allocate GDT/PDA for CPU %d\n", cpu);
-		cpucount--;
-		return;
-	}
-
+	init_gdt(cpu, idle);
 	irq_ctx_init(cpu);
 
 	/* Note: Don't modify initial ss override */
@@ -748,12 +740,6 @@ initialize_secondary(void)
 	set_current(hard_get_current());
 #endif
 
-	/*
-	 * switch to the per CPU GDT we already set up
-	 * in do_boot_cpu()
-	 */
-	cpu_set_gdt(current_thread_info()->cpu);
-
 	/*
 	 * We don't actually need to load the full TSS,
 	 * basically just the stack pointer and the eip.

arch/i386/mm/fault.c

@@ -20,6 +20,7 @@
 #include <linux/tty.h>
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 #include <linux/highmem.h>
+#include <linux/bootmem.h>		/* for max_low_pfn */
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
@@ -301,7 +302,6 @@ fastcall void __kprobes do_page_fault(struct pt_regs *regs,
 	struct mm_struct *mm;
 	struct vm_area_struct * vma;
 	unsigned long address;
-	unsigned long page;
 	int write, si_code;
 
 	/* get the address */
@@ -510,7 +510,9 @@ no_context:
 	bust_spinlocks(1);
 
 	if (oops_may_print()) {
-	#ifdef CONFIG_X86_PAE
+		__typeof__(pte_val(__pte(0))) page;
+
+#ifdef CONFIG_X86_PAE
 		if (error_code & 16) {
 			pte_t *pte = lookup_address(address);
 
@@ -519,7 +521,7 @@ no_context:
 					"NX-protected page - exploit attempt? "
 					"(uid: %d)\n", current->uid);
 		}
-	#endif
+#endif
 		if (address < PAGE_SIZE)
 			printk(KERN_ALERT "BUG: unable to handle kernel NULL "
 					"pointer dereference");
@@ -529,25 +531,38 @@ no_context:
 		printk(" at virtual address %08lx\n",address);
 		printk(KERN_ALERT " printing eip:\n");
 		printk("%08lx\n", regs->eip);
-	}
-	page = read_cr3();
-	page = ((unsigned long *) __va(page))[address >> 22];
-	if (oops_may_print())
+
+		page = read_cr3();
+		page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
+#ifdef CONFIG_X86_PAE
+		printk(KERN_ALERT "*pdpt = %016Lx\n", page);
+		if ((page >> PAGE_SHIFT) < max_low_pfn
+		    && page & _PAGE_PRESENT) {
+			page &= PAGE_MASK;
+			page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
+			                                         & (PTRS_PER_PMD - 1)];
+			printk(KERN_ALERT "*pde = %016Lx\n", page);
+			page &= ~_PAGE_NX;
+		}
+#else
 		printk(KERN_ALERT "*pde = %08lx\n", page);
-	/*
-	 * We must not directly access the pte in the highpte
-	 * case, the page table might be allocated in highmem.
-	 * And lets rather not kmap-atomic the pte, just in case
-	 * it's allocated already.
-	 */
-#ifndef CONFIG_HIGHPTE
-	if ((page & 1) && oops_may_print()) {
-		page &= PAGE_MASK;
-		address &= 0x003ff000;
-		page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
-		printk(KERN_ALERT "*pte = %08lx\n", page);
-	}
 #endif
+
+		/*
+		 * We must not directly access the pte in the highpte
+		 * case if the page table is located in highmem.
+		 * And let's rather not kmap-atomic the pte, just in case
+		 * it's allocated already.
+		 */
+		if ((page >> PAGE_SHIFT) < max_low_pfn
+		    && (page & _PAGE_PRESENT)) {
+			page &= PAGE_MASK;
+			page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
+			                                         & (PTRS_PER_PTE - 1)];
+			printk(KERN_ALERT "*pte = %0*Lx\n", sizeof(page)*2, (u64)page);
+		}
+	}
+
 	tsk->thread.cr2 = address;
 	tsk->thread.trap_no = 14;
 	tsk->thread.error_code = error_code;
@@ -588,7 +603,6 @@ do_sigbus:
 	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
 }
 
-#ifndef CONFIG_X86_PAE
 void vmalloc_sync_all(void)
 {
 	/*
@@ -601,6 +615,9 @@ void vmalloc_sync_all(void)
 	static unsigned long start = TASK_SIZE;
 	unsigned long address;
 
+	if (SHARED_KERNEL_PMD)
+		return;
+
 	BUILD_BUG_ON(TASK_SIZE & ~PGDIR_MASK);
 	for (address = start; address >= TASK_SIZE; address += PGDIR_SIZE) {
 		if (!test_bit(pgd_index(address), insync)) {
@@ -623,4 +640,3 @@ void vmalloc_sync_all(void)
 			start = address + PGDIR_SIZE;
 	}
 }
-#endif

arch/i386/mm/highmem.c

@@ -26,7 +26,7 @@ void kunmap(struct page *page)
  * However when holding an atomic kmap is is not legal to sleep, so atomic
  * kmaps are appropriate for short, tight code paths only.
  */
-void *kmap_atomic(struct page *page, enum km_type type)
+void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
 {
 	enum fixed_addresses idx;
 	unsigned long vaddr;
@@ -41,12 +41,17 @@ void *kmap_atomic(struct page *page, enum km_type type)
 		return page_address(page);
 
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	set_pte(kmap_pte-idx, mk_pte(page, kmap_prot));
+	set_pte(kmap_pte-idx, mk_pte(page, prot));
 	arch_flush_lazy_mmu_mode();
 
 	return (void*) vaddr;
 }
 
+void *kmap_atomic(struct page *page, enum km_type type)
+{
+	return kmap_atomic_prot(page, type, kmap_prot);
+}
+
 void kunmap_atomic(void *kvaddr, enum km_type type)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
@@ -67,6 +72,7 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 #endif
 	}
 
+	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 

arch/i386/mm/init.c

@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
 #include <linux/slab.h>
@@ -42,6 +43,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
+#include <asm/paravirt.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
@@ -61,17 +63,18 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 	pmd_t *pmd_table;
 		
 #ifdef CONFIG_X86_PAE
-	pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
-	paravirt_alloc_pd(__pa(pmd_table) >> PAGE_SHIFT);
-	set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
-	pud = pud_offset(pgd, 0);
-	if (pmd_table != pmd_offset(pud, 0)) 
-		BUG();
-#else
+	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
+		pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+
+		paravirt_alloc_pd(__pa(pmd_table) >> PAGE_SHIFT);
+		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
+		pud = pud_offset(pgd, 0);
+		if (pmd_table != pmd_offset(pud, 0))
+			BUG();
+	}
+#endif
 	pud = pud_offset(pgd, 0);
 	pmd_table = pmd_offset(pud, 0);
-#endif
-
 	return pmd_table;
 }
 
@@ -81,14 +84,12 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
  */
 static pte_t * __init one_page_table_init(pmd_t *pmd)
 {
-	if (pmd_none(*pmd)) {
+	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
 		pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+
 		paravirt_alloc_pt(__pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
-		if (page_table != pte_offset_kernel(pmd, 0))
-			BUG();	
-
-		return page_table;
+		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
 	}
 	
 	return pte_offset_kernel(pmd, 0);
@@ -108,7 +109,6 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 static void __init page_table_range_init (unsigned long start, unsigned long end, pgd_t *pgd_base)
 {
 	pgd_t *pgd;
-	pud_t *pud;
 	pmd_t *pmd;
 	int pgd_idx, pmd_idx;
 	unsigned long vaddr;
@@ -119,13 +119,10 @@ static void __init page_table_range_init (unsigned long start, unsigned long end
 	pgd = pgd_base + pgd_idx;
 
 	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) {
-		if (pgd_none(*pgd)) 
-			one_md_table_init(pgd);
-		pud = pud_offset(pgd, vaddr);
-		pmd = pmd_offset(pud, vaddr);
+		pmd = one_md_table_init(pgd);
+		pmd = pmd + pmd_index(vaddr);
 		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++, pmd_idx++) {
-			if (pmd_none(*pmd)) 
-				one_page_table_init(pmd);
+			one_page_table_init(pmd);
 
 			vaddr += PMD_SIZE;
 		}
@@ -167,20 +164,22 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 			/* Map with big pages if possible, otherwise create normal page tables. */
 			if (cpu_has_pse) {
 				unsigned int address2 = (pfn + PTRS_PER_PTE - 1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1;
-
 				if (is_kernel_text(address) || is_kernel_text(address2))
 					set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC));
 				else
 					set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE));
+
 				pfn += PTRS_PER_PTE;
 			} else {
 				pte = one_page_table_init(pmd);
 
-				for (pte_ofs = 0; pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn; pte++, pfn++, pte_ofs++) {
-						if (is_kernel_text(address))
-							set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
-						else
-							set_pte(pte, pfn_pte(pfn, PAGE_KERNEL));
+				for (pte_ofs = 0;
+				     pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn;
+				     pte++, pfn++, pte_ofs++, address += PAGE_SIZE) {
+					if (is_kernel_text(address))
+						set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
+					else
+						set_pte(pte, pfn_pte(pfn, PAGE_KERNEL));
 				}
 			}
 		}
@@ -337,24 +336,78 @@ extern void __init remap_numa_kva(void);
 #define remap_numa_kva() do {} while (0)
 #endif
 
-static void __init pagetable_init (void)
+void __init native_pagetable_setup_start(pgd_t *base)
 {
-	unsigned long vaddr;
-	pgd_t *pgd_base = swapper_pg_dir;
-
 #ifdef CONFIG_X86_PAE
 	int i;
-	/* Init entries of the first-level page table to the zero page */
-	for (i = 0; i < PTRS_PER_PGD; i++)
-		set_pgd(pgd_base + i, __pgd(__pa(empty_zero_page) | _PAGE_PRESENT));
+
+	/*
+	 * Init entries of the first-level page table to the
+	 * zero page, if they haven't already been set up.
+	 *
+	 * In a normal native boot, we'll be running on a
+	 * pagetable rooted in swapper_pg_dir, but not in PAE
+	 * mode, so this will end up clobbering the mappings
+	 * for the lower 24Mbytes of the address space,
+	 * without affecting the kernel address space.
+	 */
+	for (i = 0; i < USER_PTRS_PER_PGD; i++)
+		set_pgd(&base[i],
+			__pgd(__pa(empty_zero_page) | _PAGE_PRESENT));
+
+	/* Make sure kernel address space is empty so that a pagetable
+	   will be allocated for it. */
+	memset(&base[USER_PTRS_PER_PGD], 0,
+	       KERNEL_PGD_PTRS * sizeof(pgd_t));
 #else
 	paravirt_alloc_pd(__pa(swapper_pg_dir) >> PAGE_SHIFT);
 #endif
+}
+
+void __init native_pagetable_setup_done(pgd_t *base)
+{
+#ifdef CONFIG_X86_PAE
+	/*
+	 * Add low memory identity-mappings - SMP needs it when
+	 * starting up on an AP from real-mode. In the non-PAE
+	 * case we already have these mappings through head.S.
+	 * All user-space mappings are explicitly cleared after
+	 * SMP startup.
+	 */
+	set_pgd(&base[0], base[USER_PTRS_PER_PGD]);
+#endif
+}
+
+/*
+ * Build a proper pagetable for the kernel mappings.  Up until this
+ * point, we've been running on some set of pagetables constructed by
+ * the boot process.
+ *
+ * If we're booting on native hardware, this will be a pagetable
+ * constructed in arch/i386/kernel/head.S, and not running in PAE mode
+ * (even if we'll end up running in PAE).  The root of the pagetable
+ * will be swapper_pg_dir.
+ *
+ * If we're booting paravirtualized under a hypervisor, then there are
+ * more options: we may already be running PAE, and the pagetable may
+ * or may not be based in swapper_pg_dir.  In any case,
+ * paravirt_pagetable_setup_start() will set up swapper_pg_dir
+ * appropriately for the rest of the initialization to work.
+ *
+ * In general, pagetable_init() assumes that the pagetable may already
+ * be partially populated, and so it avoids stomping on any existing
+ * mappings.
+ */
+static void __init pagetable_init (void)
+{
+	unsigned long vaddr, end;
+	pgd_t *pgd_base = swapper_pg_dir;
+
+	paravirt_pagetable_setup_start(pgd_base);
 
 	/* Enable PSE if available */
-	if (cpu_has_pse) {
+	if (cpu_has_pse)
 		set_in_cr4(X86_CR4_PSE);
-	}
 
 	/* Enable PGE if available */
 	if (cpu_has_pge) {
@@ -371,20 +424,12 @@ static void __init pagetable_init (void)
 	 * created - mappings will be set by set_fixmap():
 	 */
 	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
-	page_table_range_init(vaddr, 0, pgd_base);
+	end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
+	page_table_range_init(vaddr, end, pgd_base);
 
 	permanent_kmaps_init(pgd_base);
 
-#ifdef CONFIG_X86_PAE
-	/*
-	 * Add low memory identity-mappings - SMP needs it when
-	 * starting up on an AP from real-mode. In the non-PAE
-	 * case we already have these mappings through head.S.
-	 * All user-space mappings are explicitly cleared after
-	 * SMP startup.
-	 */
-	set_pgd(&pgd_base[0], pgd_base[USER_PTRS_PER_PGD]);
-#endif
+	paravirt_pagetable_setup_done(pgd_base);
 }
 
 #if defined(CONFIG_SOFTWARE_SUSPEND) || defined(CONFIG_ACPI_SLEEP)
@@ -700,6 +745,8 @@ struct kmem_cache *pmd_cache;
 
 void __init pgtable_cache_init(void)
 {
+	size_t pgd_size = PTRS_PER_PGD*sizeof(pgd_t);
+
 	if (PTRS_PER_PMD > 1) {
 		pmd_cache = kmem_cache_create("pmd",
 					PTRS_PER_PMD*sizeof(pmd_t),
@@ -709,13 +756,23 @@ void __init pgtable_cache_init(void)
 					NULL);
 		if (!pmd_cache)
 			panic("pgtable_cache_init(): cannot create pmd cache");
+
+		if (!SHARED_KERNEL_PMD) {
+			/* If we're in PAE mode and have a non-shared
+			   kernel pmd, then the pgd size must be a
+			   page size.  This is because the pgd_list
+			   links through the page structure, so there
+			   can only be one pgd per page for this to
+			   work. */
+			pgd_size = PAGE_SIZE;
+		}
 	}
 	pgd_cache = kmem_cache_create("pgd",
-				PTRS_PER_PGD*sizeof(pgd_t),
-				PTRS_PER_PGD*sizeof(pgd_t),
+				pgd_size,
+				pgd_size,
 				0,
 				pgd_ctor,
-				PTRS_PER_PMD == 1 ? pgd_dtor : NULL);
+				(!SHARED_KERNEL_PMD) ? pgd_dtor : NULL);
 	if (!pgd_cache)
 		panic("pgtable_cache_init(): Cannot create pgd cache");
 }
@@ -751,13 +808,25 @@ static int noinline do_test_wp_bit(void)
 
 void mark_rodata_ro(void)
 {
-	unsigned long addr = (unsigned long)__start_rodata;
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
 
-	for (; addr < (unsigned long)__end_rodata; addr += PAGE_SIZE)
-		change_page_attr(virt_to_page(addr), 1, PAGE_KERNEL_RO);
+#ifdef CONFIG_HOTPLUG_CPU
+	/* It must still be possible to apply SMP alternatives. */
+	if (num_possible_cpus() <= 1)
+#endif
+	{
+		change_page_attr(virt_to_page(start),
+		                 size >> PAGE_SHIFT, PAGE_KERNEL_RX);
+		printk("Write protecting the kernel text: %luk\n", size >> 10);
+	}
 
-	printk("Write protecting the kernel read-only data: %uk\n",
-			(__end_rodata - __start_rodata) >> 10);
+	start += size;
+	size = (unsigned long)__end_rodata - start;
+	change_page_attr(virt_to_page(start),
+	                 size >> PAGE_SHIFT, PAGE_KERNEL_RO);
+	printk("Write protecting the kernel read-only data: %luk\n",
+	       size >> 10);
 
 	/*
 	 * change_page_attr() requires a global_flush_tlb() call after it.
@@ -774,26 +843,27 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	unsigned long addr;
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		free_page(addr);
+		struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
+		ClearPageReserved(page);
+		init_page_count(page);
+		memset(page_address(page), POISON_FREE_INITMEM, PAGE_SIZE);
+		__free_page(page);
 		totalram_pages++;
 	}
-	printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
+	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 }
 
 void free_initmem(void)
 {
 	free_init_pages("unused kernel memory",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
+			__pa_symbol(&__init_begin),
+			__pa_symbol(&__init_end));
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	free_init_pages("initrd memory", __pa(start), __pa(end));
 }
 #endif
 

arch/i386/mm/pageattr.c

@@ -91,7 +91,7 @@ static void set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
 	unsigned long flags;
 
 	set_pte_atomic(kpte, pte); 	/* change init_mm */
-	if (PTRS_PER_PMD > 1)
+	if (SHARED_KERNEL_PMD)
 		return;
 
 	spin_lock_irqsave(&pgd_lock, flags);
@@ -142,7 +142,7 @@ __change_page_attr(struct page *page, pgprot_t prot)
 		return -EINVAL;
 	kpte_page = virt_to_page(kpte);
 	if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) { 
-		if ((pte_val(*kpte) & _PAGE_PSE) == 0) { 
+		if (!pte_huge(*kpte)) {
 			set_pte_atomic(kpte, mk_pte(page, prot)); 
 		} else {
 			pgprot_t ref_prot;
@@ -158,7 +158,7 @@ __change_page_attr(struct page *page, pgprot_t prot)
 			kpte_page = split;
 		}
 		page_private(kpte_page)++;
-	} else if ((pte_val(*kpte) & _PAGE_PSE) == 0) { 
+	} else if (!pte_huge(*kpte)) {
 		set_pte_atomic(kpte, mk_pte(page, PAGE_KERNEL));
 		BUG_ON(page_private(kpte_page) == 0);
 		page_private(kpte_page)--;

arch/i386/mm/pgtable.c

@@ -144,10 +144,8 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
 }
 
 static int fixmaps;
-#ifndef CONFIG_COMPAT_VDSO
 unsigned long __FIXADDR_TOP = 0xfffff000;
 EXPORT_SYMBOL(__FIXADDR_TOP);
-#endif
 
 void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
 {
@@ -173,12 +171,8 @@ void reserve_top_address(unsigned long reserve)
 	BUG_ON(fixmaps > 0);
 	printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
 	       (int)-reserve);
-#ifdef CONFIG_COMPAT_VDSO
-	BUG_ON(reserve != 0);
-#else
 	__FIXADDR_TOP = -reserve - PAGE_SIZE;
 	__VMALLOC_RESERVE += reserve;
-#endif
 }
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
@@ -238,42 +232,92 @@ static inline void pgd_list_del(pgd_t *pgd)
 		set_page_private(next, (unsigned long)pprev);
 }
 
+#if (PTRS_PER_PMD == 1)
+/* Non-PAE pgd constructor */
 void pgd_ctor(void *pgd, struct kmem_cache *cache, unsigned long unused)
 {
 	unsigned long flags;
 
-	if (PTRS_PER_PMD == 1) {
-		memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
-		spin_lock_irqsave(&pgd_lock, flags);
-	}
+	/* !PAE, no pagetable sharing */
+	memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
+
+	spin_lock_irqsave(&pgd_lock, flags);
 
+	/* must happen under lock */
 	clone_pgd_range((pgd_t *)pgd + USER_PTRS_PER_PGD,
 			swapper_pg_dir + USER_PTRS_PER_PGD,
 			KERNEL_PGD_PTRS);
-
-	if (PTRS_PER_PMD > 1)
-		return;
-
-	/* must happen under lock */
 	paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT,
-			__pa(swapper_pg_dir) >> PAGE_SHIFT,
-			USER_PTRS_PER_PGD, PTRS_PER_PGD - USER_PTRS_PER_PGD);
-
+				__pa(swapper_pg_dir) >> PAGE_SHIFT,
+				USER_PTRS_PER_PGD,
+				KERNEL_PGD_PTRS);
 	pgd_list_add(pgd);
 	spin_unlock_irqrestore(&pgd_lock, flags);
 }
+#else  /* PTRS_PER_PMD > 1 */
+/* PAE pgd constructor */
+void pgd_ctor(void *pgd, struct kmem_cache *cache, unsigned long unused)
+{
+	/* PAE, kernel PMD may be shared */
+
+	if (SHARED_KERNEL_PMD) {
+		clone_pgd_range((pgd_t *)pgd + USER_PTRS_PER_PGD,
+				swapper_pg_dir + USER_PTRS_PER_PGD,
+				KERNEL_PGD_PTRS);
+	} else {
+		unsigned long flags;
+
+		memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
+		spin_lock_irqsave(&pgd_lock, flags);
+		pgd_list_add(pgd);
+		spin_unlock_irqrestore(&pgd_lock, flags);
+	}
+}
+#endif	/* PTRS_PER_PMD */
 
-/* never called when PTRS_PER_PMD > 1 */
 void pgd_dtor(void *pgd, struct kmem_cache *cache, unsigned long unused)
 {
 	unsigned long flags; /* can be called from interrupt context */
 
+	BUG_ON(SHARED_KERNEL_PMD);
+
 	paravirt_release_pd(__pa(pgd) >> PAGE_SHIFT);
 	spin_lock_irqsave(&pgd_lock, flags);
 	pgd_list_del(pgd);
 	spin_unlock_irqrestore(&pgd_lock, flags);
 }
 
+#define UNSHARED_PTRS_PER_PGD				\
+	(SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD)
+
+/* If we allocate a pmd for part of the kernel address space, then
+   make sure its initialized with the appropriate kernel mappings.
+   Otherwise use a cached zeroed pmd.  */
+static pmd_t *pmd_cache_alloc(int idx)
+{
+	pmd_t *pmd;
+
+	if (idx >= USER_PTRS_PER_PGD) {
+		pmd = (pmd_t *)__get_free_page(GFP_KERNEL);
+
+		if (pmd)
+			memcpy(pmd,
+			       (void *)pgd_page_vaddr(swapper_pg_dir[idx]),
+			       sizeof(pmd_t) * PTRS_PER_PMD);
+	} else
+		pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL);
+
+	return pmd;
+}
+
+static void pmd_cache_free(pmd_t *pmd, int idx)
+{
+	if (idx >= USER_PTRS_PER_PGD)
+		free_page((unsigned long)pmd);
+	else
+		kmem_cache_free(pmd_cache, pmd);
+}
+
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	int i;
@@ -282,10 +326,12 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	if (PTRS_PER_PMD == 1 || !pgd)
 		return pgd;
 
-	for (i = 0; i < USER_PTRS_PER_PGD; ++i) {
-		pmd_t *pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL);
+ 	for (i = 0; i < UNSHARED_PTRS_PER_PGD; ++i) {
+		pmd_t *pmd = pmd_cache_alloc(i);
+
 		if (!pmd)
 			goto out_oom;
+
 		paravirt_alloc_pd(__pa(pmd) >> PAGE_SHIFT);
 		set_pgd(&pgd[i], __pgd(1 + __pa(pmd)));
 	}
@@ -296,7 +342,7 @@ out_oom:
 		pgd_t pgdent = pgd[i];
 		void* pmd = (void *)__va(pgd_val(pgdent)-1);
 		paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT);
-		kmem_cache_free(pmd_cache, pmd);
+		pmd_cache_free(pmd, i);
 	}
 	kmem_cache_free(pgd_cache, pgd);
 	return NULL;
@@ -308,11 +354,11 @@ void pgd_free(pgd_t *pgd)
 
 	/* in the PAE case user pgd entries are overwritten before usage */
 	if (PTRS_PER_PMD > 1)
-		for (i = 0; i < USER_PTRS_PER_PGD; ++i) {
+		for (i = 0; i < UNSHARED_PTRS_PER_PGD; ++i) {
 			pgd_t pgdent = pgd[i];
 			void* pmd = (void *)__va(pgd_val(pgdent)-1);
 			paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT);
-			kmem_cache_free(pmd_cache, pmd);
+			pmd_cache_free(pmd, i);
 		}
 	/* in the non-PAE case, free_pgtables() clears user pgd entries */
 	kmem_cache_free(pgd_cache, pgd);

arch/i386/oprofile/nmi_int.c

@@ -414,6 +414,10 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 				   user space an consistent name. */
 				cpu_type = "x86-64/hammer";
 				break;
+			case 0x10:
+				model = &op_athlon_spec;
+				cpu_type = "x86-64/family10";
+				break;
 			}
 			break;
  

arch/i386/pci/init.c

@@ -6,7 +6,7 @@
    in the right sequence from here. */
 static __init int pci_access_init(void)
 {
-	int type = 0;
+	int type __attribute__((unused)) = 0;
 
 #ifdef CONFIG_PCI_DIRECT
 	type = pci_direct_probe();

arch/i386/pci/mmconfig-shared.c

@@ -60,14 +60,19 @@ static const char __init *pci_mmcfg_e7520(void)
 	u32 win;
 	pci_conf1_read(0, 0, PCI_DEVFN(0,0), 0xce, 2, &win);
 
-	pci_mmcfg_config_num = 1;
-	pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL);
-	if (!pci_mmcfg_config)
-		return NULL;
-	pci_mmcfg_config[0].address = (win & 0xf000) << 16;
-	pci_mmcfg_config[0].pci_segment = 0;
-	pci_mmcfg_config[0].start_bus_number = 0;
-	pci_mmcfg_config[0].end_bus_number = 255;
+	win = win & 0xf000;
+	if(win == 0x0000 || win == 0xf000)
+		pci_mmcfg_config_num = 0;
+	else {
+		pci_mmcfg_config_num = 1;
+		pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL);
+		if (!pci_mmcfg_config)
+			return NULL;
+		pci_mmcfg_config[0].address = win << 16;
+		pci_mmcfg_config[0].pci_segment = 0;
+		pci_mmcfg_config[0].start_bus_number = 0;
+		pci_mmcfg_config[0].end_bus_number = 255;
+	}
 
 	return "Intel Corporation E7520 Memory Controller Hub";
 }
@@ -108,6 +113,10 @@ static const char __init *pci_mmcfg_intel_945(void)
 	if ((pciexbar & mask) & 0x0fffffffU)
 		pci_mmcfg_config_num = 0;
 
+	/* Don't hit the APIC registers and their friends */
+	if ((pciexbar & mask) >= 0xf0000000U)
+		pci_mmcfg_config_num = 0;
+
 	if (pci_mmcfg_config_num) {
 		pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL);
 		if (!pci_mmcfg_config)

arch/i386/power/cpu.c

@@ -21,6 +21,7 @@ unsigned long saved_context_eflags;
 
 void __save_processor_state(struct saved_context *ctxt)
 {
+	mtrr_save_fixed_ranges(NULL);
 	kernel_fpu_begin();
 
 	/*

arch/i386/power/suspend.c

@@ -16,6 +16,9 @@
 /* Defined in arch/i386/power/swsusp.S */
 extern int restore_image(void);
 
+/* References to section boundaries */
+extern const void __nosave_begin, __nosave_end;
+
 /* Pointer to the temporary resume page tables */
 pgd_t *resume_pg_dir;
 
@@ -156,3 +159,14 @@ int swsusp_arch_resume(void)
 	restore_image();
 	return 0;
 }
+
+/*
+ *	pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}

arch/m32r/kernel/vmlinux.lds.S

@@ -110,7 +110,7 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-  . = ALIGN(32);
+  . = ALIGN(4096);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;

arch/mips/kernel/vmlinux.lds.S

@@ -119,7 +119,7 @@ SECTIONS
   .init.ramfs : { *(.init.ramfs) }
   __initramfs_end = .;
 #endif
-  . = ALIGN(32);
+  . = ALIGN(_PAGE_SIZE);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;

arch/parisc/kernel/vmlinux.lds.S

@@ -181,7 +181,7 @@ SECTIONS
   .init.ramfs : { *(.init.ramfs) }
   __initramfs_end = .;
 #endif
-  . = ALIGN(32);
+  . = ALIGN(ASM_PAGE_SIZE);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }
   __per_cpu_end = .;