Merge branch 'x86/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (821 commits)
  x86: make 64bit hpet_set_mapping to use ioremap too, v2
  x86: get x86_phys_bits early
  x86: max_low_pfn_mapped fix #4
  x86: change _node_to_cpumask_ptr to return const ptr
  x86: I/O APIC: remove an IRQ2-mask hack
  x86: fix numaq_tsc_disable calling
  x86, e820: remove end_user_pfn
  x86: max_low_pfn_mapped fix, #3
  x86: max_low_pfn_mapped fix, #2
  x86: max_low_pfn_mapped fix, #1
  x86_64: fix delayed signals
  x86: remove conflicting nx6325 and nx6125 quirks
  x86: Recover timer_ack lost in the merge of the NMI watchdog
  x86: I/O APIC: Never configure IRQ2
  x86: L-APIC: Always fully configure IRQ0
  x86: L-APIC: Set IRQ0 as edge-triggered
  x86: merge dwarf2 headers
  x86: use AS_CFI instead of UNWIND_INFO
  x86: use ignore macro instead of hash comment
  x86: use matching CFI_ENDPROC
  ...

Documentation/ABI/testing/sysfs-firmware-memmap

@@ -0,0 +1,71 @@
+What:		/sys/firmware/memmap/
+Date:		June 2008
+Contact:	Bernhard Walle <bwalle@suse.de>
+Description:
+		On all platforms, the firmware provides a memory map which the
+		kernel reads. The resources from that memory map are registered
+		in the kernel resource tree and exposed to userspace via
+		/proc/iomem (together with other resources).
+
+		However, on most architectures that firmware-provided memory
+		map is modified afterwards by the kernel itself, either because
+		the kernel merges that memory map with other information or
+		just because the user overwrites that memory map via command
+		line.
+
+		kexec needs the raw firmware-provided memory map to setup the
+		parameter segment of the kernel that should be booted with
+		kexec. Also, the raw memory map is useful for debugging. For
+		that reason, /sys/firmware/memmap is an interface that provides
+		the raw memory map to userspace.
+
+		The structure is as follows: Under /sys/firmware/memmap there
+		are subdirectories with the number of the entry as their name:
+
+			/sys/firmware/memmap/0
+			/sys/firmware/memmap/1
+			/sys/firmware/memmap/2
+			/sys/firmware/memmap/3
+			...
+
+		The maximum depends on the number of memory map entries provided
+		by the firmware. The order is just the order that the firmware
+		provides.
+
+		Each directory contains three files:
+
+		start	: The start address (as hexadecimal number with the
+			  '0x' prefix).
+		end	: The end address, inclusive (regardless whether the
+			  firmware provides inclusive or exclusive ranges).
+		type	: Type of the entry as string. See below for a list of
+			  valid types.
+
+		So, for example:
+
+			/sys/firmware/memmap/0/start
+			/sys/firmware/memmap/0/end
+			/sys/firmware/memmap/0/type
+			/sys/firmware/memmap/1/start
+			...
+
+		Currently following types exist:
+
+		  - System RAM
+		  - ACPI Tables
+		  - ACPI Non-volatile Storage
+		  - reserved
+
+		Following shell snippet can be used to display that memory
+		map in a human-readable format:
+
+		-------------------- 8< ----------------------------------------
+		  #!/bin/bash
+		  cd /sys/firmware/memmap
+		  for dir in * ; do
+		      start=$(cat $dir/start)
+		      end=$(cat $dir/end)
+		      type=$(cat $dir/type)
+		      printf "%016x-%016x (%s)\n" $start $[ $end +1] "$type"
+		  done
+		-------------------- >8 ----------------------------------------

Documentation/kdump/kdump.txt

@@ -109,7 +109,7 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
    no need to build a separate dump-capture kernel. This is possible
    only with the architecutres which support a relocatable kernel. As
-   of today i386 and ia64 architectures support relocatable kernel.
+   of today, i386, x86_64 and ia64 architectures support relocatable kernel.
 
 Building a relocatable kernel is advantageous from the point of view that
 one does not have to build a second kernel for capturing the dump. But

Documentation/kernel-parameters.txt

@@ -271,6 +271,17 @@ and is between 256 and 4096 characters. It is defined in the file
 	aic79xx=	[HW,SCSI]
 			See Documentation/scsi/aic79xx.txt.
 
+	amd_iommu=	[HW,X86-84]
+			Pass parameters to the AMD IOMMU driver in the system.
+			Possible values are:
+			isolate - enable device isolation (each device, as far
+			          as possible, will get its own protection
+			          domain)
+	amd_iommu_size= [HW,X86-64]
+			Define the size of the aperture for the AMD IOMMU
+			driver. Possible values are:
+			'32M', '64M' (default), '128M', '256M', '512M', '1G'
+
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
@@ -599,6 +610,29 @@ and is between 256 and 4096 characters. It is defined in the file
 			See drivers/char/README.epca and
 			Documentation/digiepca.txt.
 
+	disable_mtrr_cleanup [X86]
+	enable_mtrr_cleanup [X86]
+			The kernel tries to adjust MTRR layout from continuous
+			to discrete, to make X server driver able to add WB
+			entry later. This parameter enables/disables that.
+
+	mtrr_chunk_size=nn[KMG] [X86]
+			used for mtrr cleanup. It is largest continous chunk
+			that could hold holes aka. UC entries.
+
+	mtrr_gran_size=nn[KMG] [X86]
+			Used for mtrr cleanup. It is granularity of mtrr block.
+			Default is 1.
+			Large value could prevent small alignment from
+			using up MTRRs.
+
+	mtrr_spare_reg_nr=n [X86]
+			Format: <integer>
+			Range: 0,7 : spare reg number
+			Default : 1
+			Used for mtrr cleanup. It is spare mtrr entries number.
+			Set to 2 or more if your graphical card needs more.
+
 	disable_mtrr_trim [X86, Intel and AMD only]
 			By default the kernel will trim any uncacheable
 			memory out of your available memory pool based on
@@ -2116,6 +2150,9 @@ and is between 256 and 4096 characters. It is defined in the file
 	usbhid.mousepoll=
 			[USBHID] The interval which mice are to be polled at.
 
+	add_efi_memmap	[EFI; x86-32,X86-64] Include EFI memory map in
+			kernel's map of available physical RAM.
+
 	vdso=		[X86-32,SH,x86-64]
 			vdso=2: enable compat VDSO (default with COMPAT_VDSO)
 			vdso=1: enable VDSO (default)

Documentation/nmi_watchdog.txt

@@ -10,7 +10,7 @@ us to generate 'watchdog NMI interrupts'.  (NMI: Non Maskable Interrupt
 which get executed even if the system is otherwise locked up hard).
 This can be used to debug hard kernel lockups.  By executing periodic
 NMI interrupts, the kernel can monitor whether any CPU has locked up,
-and print out debugging messages if so.  
+and print out debugging messages if so.
 
 In order to use the NMI watchdog, you need to have APIC support in your
 kernel. For SMP kernels, APIC support gets compiled in automatically. For
@@ -22,8 +22,7 @@ CONFIG_X86_UP_IOAPIC is for uniprocessor with an IO-APIC. [Note: certain
 kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
 may implicitly disable the NMI watchdog.]
 
-For x86-64, the needed APIC is always compiled in, and the NMI watchdog is
-always enabled with I/O-APIC mode (nmi_watchdog=1).
+For x86-64, the needed APIC is always compiled in.
 
 Using local APIC (nmi_watchdog=2) needs the first performance register, so
 you can't use it for other purposes (such as high precision performance
@@ -63,16 +62,15 @@ when the system is idle), but if your system locks up on anything but the
 "hlt", then you are out of luck -- the event will not happen at all and the
 watchdog won't trigger. This is a shortcoming of the local APIC watchdog
 -- unfortunately there is no "clock ticks" event that would work all the
-time. The I/O APIC watchdog is driven externally and has no such shortcoming.  
+time. The I/O APIC watchdog is driven externally and has no such shortcoming.
 But its NMI frequency is much higher, resulting in a more significant hit
 to the overall system performance.
 
-NOTE: starting with 2.4.2-ac18 the NMI-oopser is disabled by default,
-you have to enable it with a boot time parameter.  Prior to 2.4.2-ac18
-the NMI-oopser is enabled unconditionally on x86 SMP boxes.
+On x86 nmi_watchdog is disabled by default so you have to enable it with
+a boot time parameter.
 
-On x86-64 the NMI oopser is on by default. On 64bit Intel CPUs
-it uses IO-APIC by default and on AMD it uses local APIC.
+NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
+on x86 SMP boxes.
 
 [ feel free to send bug reports, suggestions and patches to
   Ingo Molnar <mingo@redhat.com> or the Linux SMP mailing

Documentation/i386/boot.txt → Documentation/x86/i386/boot.txt

@@ -1,17 +1,14 @@
-		     THE LINUX/I386 BOOT PROTOCOL
-		     ----------------------------
+		     THE LINUX/x86 BOOT PROTOCOL
+		     ---------------------------
 
-		    H. Peter Anvin <hpa@zytor.com>
-			Last update 2007-05-23
-
-On the i386 platform, the Linux kernel uses a rather complicated boot
+On the x86 platform, the Linux kernel uses a rather complicated boot
 convention.  This has evolved partially due to historical aspects, as
 well as the desire in the early days to have the kernel itself be a
 bootable image, the complicated PC memory model and due to changed
 expectations in the PC industry caused by the effective demise of
 real-mode DOS as a mainstream operating system.
 
-Currently, the following versions of the Linux/i386 boot protocol exist.
+Currently, the following versions of the Linux/x86 boot protocol exist.
 
 Old kernels:	zImage/Image support only.  Some very early kernels
 		may not even support a command line.
@@ -372,10 +369,17 @@ Protocol:	2.00+
 	- If 0, the protected-mode code is loaded at 0x10000.
 	- If 1, the protected-mode code is loaded at 0x100000.
 
+  Bit 5 (write): QUIET_FLAG
+	- If 0, print early messages.
+	- If 1, suppress early messages.
+		This requests to the kernel (decompressor and early
+		kernel) to not write early messages that require
+		accessing the display hardware directly.
+
   Bit 6 (write): KEEP_SEGMENTS
 	Protocol: 2.07+
-	- if 0, reload the segment registers in the 32bit entry point.
-	- if 1, do not reload the segment registers in the 32bit entry point.
+	- If 0, reload the segment registers in the 32bit entry point.
+	- If 1, do not reload the segment registers in the 32bit entry point.
 		Assume that %cs %ds %ss %es are all set to flat segments with
 		a base of 0 (or the equivalent for their environment).
 
@@ -504,7 +508,7 @@ Protocol:	2.06+
   maximum size was 255.
 
 Field name:	hardware_subarch
-Type:		write
+Type:		write (optional, defaults to x86/PC)
 Offset/size:	0x23c/4
 Protocol:	2.07+
 
@@ -520,11 +524,13 @@ Protocol:	2.07+
   0x00000002	Xen
 
 Field name:	hardware_subarch_data
-Type:		write
+Type:		write (subarch-dependent)
 Offset/size:	0x240/8
 Protocol:	2.07+
 
   A pointer to data that is specific to hardware subarch
+  This field is currently unused for the default x86/PC environment,
+  do not modify.
 
 Field name:	payload_offset
 Type:		read
@@ -545,6 +551,34 @@ Protocol:	2.08+
 
   The length of the payload.
 
+Field name:	setup_data
+Type:		write (special)
+Offset/size:	0x250/8
+Protocol:	2.09+
+
+  The 64-bit physical pointer to NULL terminated single linked list of
+  struct setup_data. This is used to define a more extensible boot
+  parameters passing mechanism. The definition of struct setup_data is
+  as follow:
+
+  struct setup_data {
+	  u64 next;
+	  u32 type;
+	  u32 len;
+	  u8  data[0];
+  };
+
+  Where, the next is a 64-bit physical pointer to the next node of
+  linked list, the next field of the last node is 0; the type is used
+  to identify the contents of data; the len is the length of data
+  field; the data holds the real payload.
+
+  This list may be modified at a number of points during the bootup
+  process.  Therefore, when modifying this list one should always make
+  sure to consider the case where the linked list already contains
+  entries.
+
+
 **** THE IMAGE CHECKSUM
 
 From boot protocol version 2.08 onwards the CRC-32 is calculated over
@@ -553,6 +587,7 @@ initial remainder of 0xffffffff.  The checksum is appended to the
 file; therefore the CRC of the file up to the limit specified in the
 syssize field of the header is always 0.
 
+
 **** THE KERNEL COMMAND LINE
 
 The kernel command line has become an important way for the boot
@@ -584,28 +619,6 @@ command line is entered using the following protocol:
 	covered by setup_move_size, so you may need to adjust this
 	field.
 
-Field name:	setup_data
-Type:		write (obligatory)
-Offset/size:	0x250/8
-Protocol:	2.09+
-
-  The 64-bit physical pointer to NULL terminated single linked list of
-  struct setup_data. This is used to define a more extensible boot
-  parameters passing mechanism. The definition of struct setup_data is
-  as follow:
-
-  struct setup_data {
-	  u64 next;
-	  u32 type;
-	  u32 len;
-	  u8  data[0];
-  };
-
-  Where, the next is a 64-bit physical pointer to the next node of
-  linked list, the next field of the last node is 0; the type is used
-  to identify the contents of data; the len is the length of data
-  field; the data holds the real payload.
-
 
 **** MEMORY LAYOUT OF THE REAL-MODE CODE
 

Documentation/x86_64/mm.txt → Documentation/x86/x86_64/mm.txt

@@ -11,9 +11,8 @@ ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
 ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
-ffffffff80000000 - ffffffff82800000 (=40 MB)   kernel text mapping, from phys 0
-... unused hole ...
-ffffffff88000000 - fffffffffff00000 (=1919 MB) module mapping space
+ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
+ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space
 
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory

Documentation/x86_64/uefi.txt → Documentation/x86/x86_64/uefi.txt

@@ -36,3 +36,7 @@ Mechanics:
   services.
 	noefi		turn off all EFI runtime services
 	reboot_type=k	turn off EFI reboot runtime service
+- If the EFI memory map has additional entries not in the E820 map,
+  you can include those entries in the kernels memory map of available
+  physical RAM by using the following kernel command line parameter.
+	add_efi_memmap	include EFI memory map of available physical RAM

MAINTAINERS

@@ -376,6 +376,12 @@ L:	linux-geode@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.amd.com/us-en/ConnectivitySolutions/TechnicalResources/0,,50_2334_2452_11363,00.html
 S:	Supported
 
+AMD IOMMU (AMD-VI)
+P:	Joerg Roedel
+M:	joerg.roedel@amd.com
+L:	iommu@lists.linux-foundation.org
+S:	Supported
+
 AMS (Apple Motion Sensor) DRIVER
 P:	Stelian Pop
 M:	stelian@popies.net

arch/x86/Kconfig

@@ -121,7 +121,7 @@ config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
 config HAVE_SETUP_PER_CPU_AREA
-	def_bool X86_64 || (X86_SMP && !X86_VOYAGER)
+	def_bool X86_64_SMP || (X86_SMP && !X86_VOYAGER)
 
 config HAVE_CPUMASK_OF_CPU_MAP
 	def_bool X86_64_SMP
@@ -181,12 +181,12 @@ config X86_64_SMP
 config X86_HT
 	bool
 	depends on SMP
-	depends on (X86_32 && !(X86_VISWS || X86_VOYAGER)) || X86_64
+	depends on (X86_32 && !X86_VOYAGER) || X86_64
 	default y
 
 config X86_BIOS_REBOOT
 	bool
-	depends on !X86_VISWS && !X86_VOYAGER
+	depends on !X86_VOYAGER
 	default y
 
 config X86_TRAMPOLINE
@@ -230,6 +230,26 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config X86_FIND_SMP_CONFIG
+	def_bool y
+	depends on X86_MPPARSE || X86_VOYAGER
+
+if ACPI
+config X86_MPPARSE
+	def_bool y
+	bool "Enable MPS table"
+	depends on X86_LOCAL_APIC
+	help
+	  For old smp systems that do not have proper acpi support. Newer systems
+	  (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
+endif
+
+if !ACPI
+config X86_MPPARSE
+	def_bool y
+	depends on X86_LOCAL_APIC
+endif
+
 choice
 	prompt "Subarchitecture Type"
 	default X86_PC
@@ -251,7 +271,7 @@ config X86_ELAN
 
 config X86_VOYAGER
 	bool "Voyager (NCR)"
-	depends on X86_32 && (SMP || BROKEN)
+	depends on X86_32 && (SMP || BROKEN) && !PCI
 	help
 	  Voyager is an MCA-based 32-way capable SMP architecture proprietary
 	  to NCR Corp.  Machine classes 345x/35xx/4100/51xx are Voyager-based.
@@ -261,16 +281,27 @@ config X86_VOYAGER
 	  If you do not specifically know you have a Voyager based machine,
 	  say N here, otherwise the kernel you build will not be bootable.
 
+config X86_GENERICARCH
+       bool "Generic architecture"
+	depends on X86_32
+       help
+          This option compiles in the NUMAQ, Summit, bigsmp, ES7000, default
+	  subarchitectures.  It is intended for a generic binary kernel.
+	  if you select them all, kernel will probe it one by one. and will
+	  fallback to default.
+
+if X86_GENERICARCH
+
 config X86_NUMAQ
 	bool "NUMAQ (IBM/Sequent)"
-	depends on SMP && X86_32
+	depends on SMP && X86_32 && PCI && X86_MPPARSE
 	select NUMA
 	help
-	  This option is used for getting Linux to run on a (IBM/Sequent) NUMA
-	  multiquad box. This changes the way that processors are bootstrapped,
-	  and uses Clustered Logical APIC addressing mode instead of Flat Logical.
-	  You will need a new lynxer.elf file to flash your firmware with - send
-	  email to <Martin.Bligh@us.ibm.com>.
+	  This option is used for getting Linux to run on a NUMAQ (IBM/Sequent)
+	  NUMA multiquad box. This changes the way that processors are
+	  bootstrapped, and uses Clustered Logical APIC addressing mode instead
+	  of Flat Logical.  You will need a new lynxer.elf file to flash your
+	  firmware with - send email to <Martin.Bligh@us.ibm.com>.
 
 config X86_SUMMIT
 	bool "Summit/EXA (IBM x440)"
@@ -279,46 +310,21 @@ config X86_SUMMIT
 	  This option is needed for IBM systems that use the Summit/EXA chipset.
 	  In particular, it is needed for the x440.
 
-	  If you don't have one of these computers, you should say N here.
-	  If you want to build a NUMA kernel, you must select ACPI.
+config X86_ES7000
+	bool "Support for Unisys ES7000 IA32 series"
+	depends on X86_32 && SMP
+	help
+	  Support for Unisys ES7000 systems.  Say 'Y' here if this kernel is
+	  supposed to run on an IA32-based Unisys ES7000 system.
 
 config X86_BIGSMP
-	bool "Support for other sub-arch SMP systems with more than 8 CPUs"
+	bool "Support for big SMP systems with more than 8 CPUs"
 	depends on X86_32 && SMP
 	help
 	  This option is needed for the systems that have more than 8 CPUs
 	  and if the system is not of any sub-arch type above.
 
-	  If you don't have such a system, you should say N here.
-
-config X86_VISWS
-	bool "SGI 320/540 (Visual Workstation)"
-	depends on X86_32
-	help
-	  The SGI Visual Workstation series is an IA32-based workstation
-	  based on SGI systems chips with some legacy PC hardware attached.
-
-	  Say Y here to create a kernel to run on the SGI 320 or 540.
-
-	  A kernel compiled for the Visual Workstation will not run on PCs
-	  and vice versa. See <file:Documentation/sgi-visws.txt> for details.
-
-config X86_GENERICARCH
-       bool "Generic architecture (Summit, bigsmp, ES7000, default)"
-	depends on X86_32
-       help
-          This option compiles in the Summit, bigsmp, ES7000, default subarchitectures.
-	  It is intended for a generic binary kernel.
-	  If you want a NUMA kernel, select ACPI.   We need SRAT for NUMA.
-
-config X86_ES7000
-	bool "Support for Unisys ES7000 IA32 series"
-	depends on X86_32 && SMP
-	help
-	  Support for Unisys ES7000 systems.  Say 'Y' here if this kernel is
-	  supposed to run on an IA32-based Unisys ES7000 system.
-	  Only choose this option if you have such a system, otherwise you
-	  should say N here.
+endif
 
 config X86_RDC321X
 	bool "RDC R-321x SoC"
@@ -337,7 +343,7 @@ config X86_RDC321X
 config X86_VSMP
 	bool "Support for ScaleMP vSMP"
 	select PARAVIRT
-	depends on X86_64
+	depends on X86_64 && PCI
 	help
 	  Support for ScaleMP vSMP systems.  Say 'Y' here if this kernel is
 	  supposed to run on these EM64T-based machines.  Only choose this option
@@ -345,6 +351,18 @@ config X86_VSMP
 
 endchoice
 
+config X86_VISWS
+	bool "SGI 320/540 (Visual Workstation)"
+	depends on X86_32 && PCI && !X86_VOYAGER && X86_MPPARSE && PCI_GODIRECT
+	help
+	  The SGI Visual Workstation series is an IA32-based workstation
+	  based on SGI systems chips with some legacy PC hardware attached.
+
+	  Say Y here to create a kernel to run on the SGI 320 or 540.
+
+	  A kernel compiled for the Visual Workstation will run on general
+	  PCs as well. See <file:Documentation/sgi-visws.txt> for details.
+
 config SCHED_NO_NO_OMIT_FRAME_POINTER
 	def_bool y
 	prompt "Single-depth WCHAN output"
@@ -373,7 +391,7 @@ config VMI
 	bool "VMI Guest support"
 	select PARAVIRT
 	depends on X86_32
-	depends on !(X86_VISWS || X86_VOYAGER)
+	depends on !X86_VOYAGER
 	help
 	  VMI provides a paravirtualized interface to the VMware ESX server
 	  (it could be used by other hypervisors in theory too, but is not
@@ -384,7 +402,7 @@ config KVM_CLOCK
 	bool "KVM paravirtualized clock"
 	select PARAVIRT
 	select PARAVIRT_CLOCK
-	depends on !(X86_VISWS || X86_VOYAGER)
+	depends on !X86_VOYAGER
 	help
 	  Turning on this option will allow you to run a paravirtualized clock
 	  when running over the KVM hypervisor. Instead of relying on a PIT
@@ -395,7 +413,7 @@ config KVM_CLOCK
 config KVM_GUEST
 	bool "KVM Guest support"
 	select PARAVIRT
-	depends on !(X86_VISWS || X86_VOYAGER)
+	depends on !X86_VOYAGER
 	help
 	 This option enables various optimizations for running under the KVM
 	 hypervisor.
@@ -404,7 +422,7 @@ source "arch/x86/lguest/Kconfig"
 
 config PARAVIRT
 	bool "Enable paravirtualization code"
-	depends on !(X86_VISWS || X86_VOYAGER)
+	depends on !X86_VOYAGER
 	help
 	  This changes the kernel so it can modify itself when it is run
 	  under a hypervisor, potentially improving performance significantly
@@ -417,51 +435,33 @@ config PARAVIRT_CLOCK
 
 endif
 
-config MEMTEST_BOOTPARAM
-	bool "Memtest boot parameter"
+config PARAVIRT_DEBUG
+       bool "paravirt-ops debugging"
+       depends on PARAVIRT && DEBUG_KERNEL
+       help
+         Enable to debug paravirt_ops internals.  Specifically, BUG if
+	 a paravirt_op is missing when it is called.
+
+config MEMTEST
+	bool "Memtest"
 	depends on X86_64
 	default y
 	help
 	  This option adds a kernel parameter 'memtest', which allows memtest
-	  to be disabled at boot.  If this option is selected, memtest
-	  functionality can be disabled with memtest=0 on the kernel
-	  command line.  The purpose of this option is to allow a single
-	  kernel image to be distributed with memtest built in, but not
-	  necessarily enabled.
-
+	  to be set.
+		memtest=0, mean disabled; -- default
+		memtest=1, mean do 1 test pattern;
+		...
+		memtest=4, mean do 4 test patterns.
 	  If you are unsure how to answer this question, answer Y.
 
-config MEMTEST_BOOTPARAM_VALUE
-	int "Memtest boot parameter default value (0-4)"
-	depends on MEMTEST_BOOTPARAM
-	range 0 4
-	default 0
-	help
-	  This option sets the default value for the kernel parameter
-	  'memtest', which allows memtest to be disabled at boot.  If this
-	  option is set to 0 (zero), the memtest kernel parameter will
-	  default to 0, disabling memtest at bootup.  If this option is
-	  set to 4, the memtest kernel parameter will default to 4,
-	  enabling memtest at bootup, and use that as pattern number.
-
-	  If you are unsure how to answer this question, answer 0.
-
-config ACPI_SRAT
-	def_bool y
-	depends on X86_32 && ACPI && NUMA && (X86_SUMMIT || X86_GENERICARCH)
-	select ACPI_NUMA
-
-config HAVE_ARCH_PARSE_SRAT
-	def_bool y
-	depends on ACPI_SRAT
-
 config X86_SUMMIT_NUMA
 	def_bool y
-	depends on X86_32 && NUMA && (X86_SUMMIT || X86_GENERICARCH)
+	depends on X86_32 && NUMA && X86_GENERICARCH
 
 config X86_CYCLONE_TIMER
 	def_bool y
-	depends on X86_32 && X86_SUMMIT || X86_GENERICARCH
+	depends on X86_GENERICARCH
 
 config ES7000_CLUSTERED_APIC
 	def_bool y
@@ -549,6 +549,21 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT
 	  Calgary anyway, pass 'iommu=calgary' on the kernel command line.
 	  If unsure, say Y.
 
+config AMD_IOMMU
+	bool "AMD IOMMU support"
+	select SWIOTLB
+	depends on X86_64 && PCI && ACPI
+	help
+	  With this option you can enable support for AMD IOMMU hardware in
+	  your system. An IOMMU is a hardware component which provides
+	  remapping of DMA memory accesses from devices. With an AMD IOMMU you
+	  can isolate the the DMA memory of different devices and protect the
+	  system from misbehaving device drivers or hardware.
+
+	  You can find out if your system has an AMD IOMMU if you look into
+	  your BIOS for an option to enable it or if you have an IVRS ACPI
+	  table.
+
 # need this always selected by IOMMU for the VIA workaround
 config SWIOTLB
 	bool
@@ -560,21 +575,36 @@ config SWIOTLB
 	  3 GB of memory. If unsure, say Y.
 
 config IOMMU_HELPER
-	def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB)
+	def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU)
+config MAXSMP
+	bool "Configure Maximum number of SMP Processors and NUMA Nodes"
+	depends on X86_64 && SMP
+	default n
+	help
+	  Configure maximum number of CPUS and NUMA Nodes for this architecture.
+	  If unsure, say N.
 
+if MAXSMP
 config NR_CPUS
-	int "Maximum number of CPUs (2-255)"
-	range 2 255
+	int
+	default "4096"
+endif
+
+if !MAXSMP
+config NR_CPUS
+	int "Maximum number of CPUs (2-4096)"
+	range 2 4096
 	depends on SMP
 	default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000
 	default "8"
 	help
 	  This allows you to specify the maximum number of CPUs which this
-	  kernel will support.  The maximum supported value is 255 and the
+	  kernel will support.  The maximum supported value is 4096 and the
 	  minimum value which makes sense is 2.
 
 	  This is purely to save memory - each supported CPU adds
 	  approximately eight kilobytes to the kernel image.
+endif
 
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
@@ -598,7 +628,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on X86_32 && !SMP && !(X86_VISWS || X86_VOYAGER || X86_GENERICARCH)
+	depends on X86_32 && !SMP && !(X86_VOYAGER || X86_GENERICARCH)
 	help
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -623,11 +653,11 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	def_bool y
-	depends on X86_64 || (X86_32 && (X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER) || X86_GENERICARCH))
+	depends on X86_64 || (X86_32 && (X86_UP_APIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH))
 
 config X86_IO_APIC
 	def_bool y
-	depends on X86_64 || (X86_32 && (X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER)) || X86_GENERICARCH))
+	depends on X86_64 || (X86_32 && (X86_UP_IOAPIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH))
 
 config X86_VISWS_APIC
 	def_bool y
@@ -681,7 +711,7 @@ config X86_MCE_NONFATAL
 
 config X86_MCE_P4THERMAL
 	bool "check for P4 thermal throttling interrupt."
-	depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP) && !X86_VISWS
+	depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP)
 	help
 	  Enabling this feature will cause a message to be printed when the P4
 	  enters thermal throttling.
@@ -911,9 +941,9 @@ config X86_PAE
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
 	depends on SMP
-	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) && EXPERIMENTAL)
+	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
 	default n if X86_PC
-	default y if (X86_NUMAQ || X86_SUMMIT)
+	default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
 	help
 	  Enable NUMA (Non Uniform Memory Access) support.
 	  The kernel will try to allocate memory used by a CPU on the
@@ -965,13 +995,25 @@ config NUMA_EMU
 	  into virtual nodes when booted with "numa=fake=N", where N is the
 	  number of nodes. This is only useful for debugging.
 
+if MAXSMP
+
+config NODES_SHIFT
+	int
+	default "9"
+endif
+
+if !MAXSMP
 config NODES_SHIFT
-	int "Max num nodes shift(1-9)"
-	range 1 9  if X86_64
+	int "Maximum NUMA Nodes (as a power of 2)"
+	range 1 9   if X86_64
 	default "6" if X86_64
 	default "4" if X86_NUMAQ
 	default "3"
 	depends on NEED_MULTIPLE_NODES
+	help
+	  Specify the maximum number of NUMA Nodes available on the target
+	  system.  Increases memory reserved to accomodate various tables.
+endif
 
 config HAVE_ARCH_BOOTMEM_NODE
 	def_bool y
@@ -1090,6 +1132,40 @@ config MTRR
 
 	  See <file:Documentation/mtrr.txt> for more information.
 
+config MTRR_SANITIZER
+	def_bool y
+	prompt "MTRR cleanup support"
+	depends on MTRR
+	help
+	  Convert MTRR layout from continuous to discrete, so some X driver
+	  could add WB entries.
+
+	  Say N here if you see bootup problems (boot crash, boot hang,
+	  spontaneous reboots).
+
+	  Could be disabled with disable_mtrr_cleanup. Also mtrr_chunk_size
+	  could be used to send largest mtrr entry size for continuous block
+	  to hold holes (aka. UC entries)
+
+	  If unsure, say Y.
+
+config MTRR_SANITIZER_ENABLE_DEFAULT
+	int "MTRR cleanup enable value (0-1)"
+	range 0 1
+	default "0"
+	depends on MTRR_SANITIZER
+	help
+	  Enable mtrr cleanup default value
+
+config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT
+	int "MTRR cleanup spare reg num (0-7)"
+	range 0 7
+	default "1"
+	depends on MTRR_SANITIZER
+	help
+	  mtrr cleanup spare entries default, it can be changed via
+	  mtrr_spare_reg_nr=
+
 config X86_PAT
 	bool
 	prompt "x86 PAT support"
@@ -1190,7 +1266,6 @@ config KEXEC
 
 config CRASH_DUMP
 	bool "kernel crash dumps (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
 	depends on X86_64 || (X86_32 && HIGHMEM)
 	help
 	  Generate crash dump after being started by kexec.
@@ -1339,7 +1414,7 @@ config X86_APM_BOOT
 
 menuconfig APM
 	tristate "APM (Advanced Power Management) BIOS support"
-	depends on X86_32 && PM_SLEEP && !X86_VISWS
+	depends on X86_32 && PM_SLEEP
 	---help---
 	  APM is a BIOS specification for saving power using several different
 	  techniques. This is mostly useful for battery powered laptops with
@@ -1475,8 +1550,7 @@ endmenu
 menu "Bus options (PCI etc.)"
 
 config PCI
-	bool "PCI support" if !X86_VISWS && !X86_VSMP
-	depends on !X86_VOYAGER
+	bool "PCI support"
 	default y
 	select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC)
 	help
@@ -1487,7 +1561,7 @@ config PCI
 
 choice
 	prompt "PCI access mode"
-	depends on X86_32 && PCI && !X86_VISWS
+	depends on X86_32 && PCI
 	default PCI_GOANY
 	---help---
 	  On PCI systems, the BIOS can be used to detect the PCI devices and
@@ -1524,12 +1598,12 @@ endchoice
 
 config PCI_BIOS
 	def_bool y
-	depends on X86_32 && !X86_VISWS && PCI && (PCI_GOBIOS || PCI_GOANY)
+	depends on X86_32 && PCI && (PCI_GOBIOS || PCI_GOANY)
 
 # x86-64 doesn't support PCI BIOS access from long mode so always go direct.
 config PCI_DIRECT
 	def_bool y
-	depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC) || X86_VISWS)
+	depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC))
 
 config PCI_MMCONFIG
 	def_bool y
@@ -1589,7 +1663,7 @@ if X86_32
 
 config ISA
 	bool "ISA support"
-	depends on !(X86_VOYAGER || X86_VISWS)
+	depends on !X86_VOYAGER
 	help
 	  Find out whether you have ISA slots on your motherboard.  ISA is the
 	  name of a bus system, i.e. the way the CPU talks to the other stuff
@@ -1616,7 +1690,7 @@ config EISA
 source "drivers/eisa/Kconfig"
 
 config MCA
-	bool "MCA support" if !(X86_VISWS || X86_VOYAGER)
+	bool "MCA support" if !X86_VOYAGER
 	default y if X86_VOYAGER
 	help
 	  MicroChannel Architecture is found in some IBM PS/2 machines and

arch/x86/Kconfig.cpu

@@ -344,7 +344,7 @@ config X86_F00F_BUG
 
 config X86_WP_WORKS_OK
 	def_bool y
-	depends on X86_32 && !M386
+	depends on !M386
 
 config X86_INVLPG
 	def_bool y
@@ -399,6 +399,10 @@ config X86_TSC
 	def_bool y
 	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) || X86_64
 
+config X86_CMPXCHG64
+	def_bool y
+	depends on X86_PAE || X86_64
+
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
 config X86_CMOV

arch/x86/Kconfig.debug

@@ -20,6 +20,14 @@ config NONPROMISC_DEVMEM
 
 	  If in doubt, say Y.
 
+config X86_VERBOSE_BOOTUP
+	bool "Enable verbose x86 bootup info messages"
+	default y
+	help
+	  Enables the informational output from the decompression stage
+	  (e.g. bzImage) of the boot. If you disable this you will still
+	  see errors. Disable this if you want silent bootup.
+
 config EARLY_PRINTK
 	bool "Early printk" if EMBEDDED
 	default y
@@ -60,7 +68,7 @@ config DEBUG_PAGEALLOC
 config DEBUG_PER_CPU_MAPS
 	bool "Debug access to per_cpu maps"
 	depends on DEBUG_KERNEL
-	depends on X86_64_SMP
+	depends on X86_SMP
 	default n
 	help
 	  Say Y to verify that the per_cpu map being accessed has
@@ -129,15 +137,6 @@ config 4KSTACKS
 	  on the VM subsystem for higher order allocations. This option
 	  will also use IRQ stacks to compensate for the reduced stackspace.
 
-config X86_FIND_SMP_CONFIG
-	def_bool y
-	depends on X86_LOCAL_APIC || X86_VOYAGER
-	depends on X86_32
-
-config X86_MPPARSE
-	def_bool y
-	depends on (X86_32 && (X86_LOCAL_APIC && !X86_VISWS)) || X86_64
-
 config DOUBLEFAULT
 	default y
 	bool "Enable doublefault exception handler" if EMBEDDED

arch/x86/Makefile

@@ -113,33 +113,11 @@ mcore-y  := arch/x86/mach-default/
 mflags-$(CONFIG_X86_VOYAGER)	:= -Iinclude/asm-x86/mach-voyager
 mcore-$(CONFIG_X86_VOYAGER)	:= arch/x86/mach-voyager/
 
-# VISWS subarch support
-mflags-$(CONFIG_X86_VISWS)	:= -Iinclude/asm-x86/mach-visws
-mcore-$(CONFIG_X86_VISWS)	:= arch/x86/mach-visws/
-
-# NUMAQ subarch support
-mflags-$(CONFIG_X86_NUMAQ)	:= -Iinclude/asm-x86/mach-numaq
-mcore-$(CONFIG_X86_NUMAQ)	:= arch/x86/mach-default/
-
-# BIGSMP subarch support
-mflags-$(CONFIG_X86_BIGSMP)	:= -Iinclude/asm-x86/mach-bigsmp
-mcore-$(CONFIG_X86_BIGSMP)	:= arch/x86/mach-default/
-
-#Summit subarch support
-mflags-$(CONFIG_X86_SUMMIT)	:= -Iinclude/asm-x86/mach-summit
-mcore-$(CONFIG_X86_SUMMIT)	:= arch/x86/mach-default/
-
 # generic subarchitecture
 mflags-$(CONFIG_X86_GENERICARCH):= -Iinclude/asm-x86/mach-generic
 fcore-$(CONFIG_X86_GENERICARCH)	+= arch/x86/mach-generic/
 mcore-$(CONFIG_X86_GENERICARCH)	:= arch/x86/mach-default/
 
-
-# ES7000 subarch support
-mflags-$(CONFIG_X86_ES7000)	:= -Iinclude/asm-x86/mach-es7000
-fcore-$(CONFIG_X86_ES7000)	:= arch/x86/mach-es7000/
-mcore-$(CONFIG_X86_ES7000)	:= arch/x86/mach-default/
-
 # RDC R-321x subarch support
 mflags-$(CONFIG_X86_RDC321X)	:= -Iinclude/asm-x86/mach-rdc321x
 mcore-$(CONFIG_X86_RDC321X)	:= arch/x86/mach-default/
@@ -160,6 +138,7 @@ KBUILD_AFLAGS += $(mflags-y)
 
 head-y := arch/x86/kernel/head_$(BITS).o
 head-y += arch/x86/kernel/head$(BITS).o
+head-y += arch/x86/kernel/head.o
 head-y += arch/x86/kernel/init_task.o
 
 libs-y  += arch/x86/lib/
@@ -210,12 +189,12 @@ all: bzImage
 
 # KBUILD_IMAGE specify target image being built
                     KBUILD_IMAGE := $(boot)/bzImage
-zImage zlilo zdisk: KBUILD_IMAGE := arch/x86/boot/zImage
+zImage zlilo zdisk: KBUILD_IMAGE := $(boot)/zImage
 
 zImage bzImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE)
 	$(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot
-	$(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/bzImage
+	$(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@
 
 compressed: zImage
 

arch/x86/boot/a20.c

@@ -1,7 +1,7 @@
 /* -*- linux-c -*- ------------------------------------------------------- *
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
- *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -95,6 +95,9 @@ static void enable_a20_kbc(void)
 
 	outb(0xdf, 0x60);	/* A20 on */
 	empty_8042();
+
+	outb(0xff, 0x64);	/* Null command, but UHCI wants it */
+	empty_8042();
 }
 
 static void enable_a20_fast(void)

arch/x86/boot/compressed/head_64.S

@@ -30,6 +30,7 @@
 #include <asm/page.h>
 #include <asm/boot.h>
 #include <asm/msr.h>
+#include <asm/processor-flags.h>
 #include <asm/asm-offsets.h>
 
 .section ".text.head"
@@ -109,7 +110,7 @@ startup_32:
 
 	/* Enable PAE mode */
 	xorl	%eax, %eax
-	orl	$(1 << 5), %eax
+	orl	$(X86_CR4_PAE), %eax
 	movl	%eax, %cr4
 
  /*
@@ -170,7 +171,7 @@ startup_32:
 	pushl	%eax
 
 	/* Enter paged protected Mode, activating Long Mode */
-	movl	$0x80000001, %eax /* Enable Paging and Protected mode */
+	movl	$(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */
 	movl	%eax, %cr0
 
 	/* Jump from 32bit compatibility mode into 64bit mode. */

arch/x86/boot/compressed/misc.c

@@ -30,6 +30,7 @@
 #include <asm/io.h>
 #include <asm/page.h>
 #include <asm/boot.h>
+#include <asm/bootparam.h>
 
 /* WARNING!!
  * This code is compiled with -fPIC and it is relocated dynamically
@@ -187,13 +188,8 @@ static void gzip_release(void **);
 /*
  * This is set up by the setup-routine at boot-time
  */
-static unsigned char *real_mode; /* Pointer to real-mode data */
-
-#define RM_EXT_MEM_K   (*(unsigned short *)(real_mode + 0x2))
-#ifndef STANDARD_MEMORY_BIOS_CALL
-#define RM_ALT_MEM_K   (*(unsigned long *)(real_mode + 0x1e0))
-#endif
-#define RM_SCREEN_INFO (*(struct screen_info *)(real_mode+0))
+static struct boot_params *real_mode;		/* Pointer to real-mode data */
+static int quiet;
 
 extern unsigned char input_data[];
 extern int input_len;
@@ -206,7 +202,8 @@ static void free(void *where);
 static void *memset(void *s, int c, unsigned n);
 static void *memcpy(void *dest, const void *src, unsigned n);
 
-static void putstr(const char *);
+static void __putstr(int, const char *);
+#define putstr(__x)  __putstr(0, __x)
 
 #ifdef CONFIG_X86_64
 #define memptr long
@@ -221,10 +218,6 @@ static char *vidmem;
 static int vidport;
 static int lines, cols;
 
-#ifdef CONFIG_X86_NUMAQ
-void *xquad_portio;
-#endif
-
 #include "../../../../lib/inflate.c"
 
 static void *malloc(int size)
@@ -270,18 +263,24 @@ static void scroll(void)
 		vidmem[i] = ' ';
 }
 
-static void putstr(const char *s)
+static void __putstr(int error, const char *s)
 {
 	int x, y, pos;
 	char c;
 
+#ifndef CONFIG_X86_VERBOSE_BOOTUP
+	if (!error)
+		return;
+#endif
+
 #ifdef CONFIG_X86_32
-	if (RM_SCREEN_INFO.orig_video_mode == 0 && lines == 0 && cols == 0)
+	if (real_mode->screen_info.orig_video_mode == 0 &&
+	    lines == 0 && cols == 0)
 		return;
 #endif
 
-	x = RM_SCREEN_INFO.orig_x;
-	y = RM_SCREEN_INFO.orig_y;
+	x = real_mode->screen_info.orig_x;
+	y = real_mode->screen_info.orig_y;
 
 	while ((c = *s++) != '\0') {
 		if (c == '\n') {
@@ -302,8 +301,8 @@ static void putstr(const char *s)
 		}
 	}
 
-	RM_SCREEN_INFO.orig_x = x;
-	RM_SCREEN_INFO.orig_y = y;
+	real_mode->screen_info.orig_x = x;
+	real_mode->screen_info.orig_y = y;
 
 	pos = (x + cols * y) * 2;	/* Update cursor position */
 	outb(14, vidport);
@@ -366,9 +365,9 @@ static void flush_window(void)
 
 static void error(char *x)
 {
-	putstr("\n\n");
-	putstr(x);
-	putstr("\n\n -- System halted");
+	__putstr(1, "\n\n");
+	__putstr(1, x);
+	__putstr(1, "\n\n -- System halted");
 
 	while (1)
 		asm("hlt");
@@ -395,7 +394,8 @@ static void parse_elf(void *output)
 		return;
 	}
 
-	putstr("Parsing ELF... ");
+	if (!quiet)
+		putstr("Parsing ELF... ");
 
 	phdrs = malloc(sizeof(*phdrs) * ehdr.e_phnum);
 	if (!phdrs)
@@ -430,7 +430,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 {
 	real_mode = rmode;
 
-	if (RM_SCREEN_INFO.orig_video_mode == 7) {
+	if (real_mode->hdr.loadflags & QUIET_FLAG)
+		quiet = 1;
+
+	if (real_mode->screen_info.orig_video_mode == 7) {
 		vidmem = (char *) 0xb0000;
 		vidport = 0x3b4;
 	} else {
@@ -438,8 +441,8 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 		vidport = 0x3d4;
 	}
 
-	lines = RM_SCREEN_INFO.orig_video_lines;
-	cols = RM_SCREEN_INFO.orig_video_cols;
+	lines = real_mode->screen_info.orig_video_lines;
+	cols = real_mode->screen_info.orig_video_cols;
 
 	window = output;		/* Output buffer (Normally at 1M) */
 	free_mem_ptr     = heap;	/* Heap */
@@ -465,9 +468,11 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 #endif
 
 	makecrc();
-	putstr("\nDecompressing Linux... ");
+	if (!quiet)
+		putstr("\nDecompressing Linux... ");
 	gunzip();
 	parse_elf(output);
-	putstr("done.\nBooting the kernel.\n");
+	if (!quiet)
+		putstr("done.\nBooting the kernel.\n");
 	return;
 }

arch/x86/boot/compressed/relocs.c

@@ -10,16 +10,20 @@
 #define USE_BSD
 #include <endian.h>
 
-#define MAX_SHDRS 100
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 static Elf32_Ehdr ehdr;
-static Elf32_Shdr shdr[MAX_SHDRS];
-static Elf32_Sym  *symtab[MAX_SHDRS];
-static Elf32_Rel  *reltab[MAX_SHDRS];
-static char *strtab[MAX_SHDRS];
 static unsigned long reloc_count, reloc_idx;
 static unsigned long *relocs;
 
+struct section {
+	Elf32_Shdr     shdr;
+	struct section *link;
+	Elf32_Sym      *symtab;
+	Elf32_Rel      *reltab;
+	char           *strtab;
+};
+static struct section *secs;
+
 /*
  * Following symbols have been audited. There values are constant and do
  * not change if bzImage is loaded at a different physical address than
@@ -35,7 +39,7 @@ static int is_safe_abs_reloc(const char* sym_name)
 {
 	int i;
 
-	for(i = 0; i < ARRAY_SIZE(safe_abs_relocs); i++) {
+	for (i = 0; i < ARRAY_SIZE(safe_abs_relocs); i++) {
 		if (!strcmp(sym_name, safe_abs_relocs[i]))
 			/* Match found */
 			return 1;
@@ -137,10 +141,10 @@ static const char *sec_name(unsigned shndx)
 {
 	const char *sec_strtab;
 	const char *name;
-	sec_strtab = strtab[ehdr.e_shstrndx];
+	sec_strtab = secs[ehdr.e_shstrndx].strtab;
 	name = "<noname>";
 	if (shndx < ehdr.e_shnum) {
-		name = sec_strtab + shdr[shndx].sh_name;
+		name = sec_strtab + secs[shndx].shdr.sh_name;
 	}
 	else if (shndx == SHN_ABS) {
 		name = "ABSOLUTE";
@@ -159,7 +163,7 @@ static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym)
 		name = sym_strtab + sym->st_name;
 	}
 	else {
-		name = sec_name(shdr[sym->st_shndx].sh_name);
+		name = sec_name(secs[sym->st_shndx].shdr.sh_name);
 	}
 	return name;
 }
@@ -244,29 +248,34 @@ static void read_ehdr(FILE *fp)
 static void read_shdrs(FILE *fp)
 {
 	int i;
-	if (ehdr.e_shnum > MAX_SHDRS) {
-		die("%d section headers supported: %d\n",
-			ehdr.e_shnum, MAX_SHDRS);
+	Elf32_Shdr shdr;
+
+	secs = calloc(ehdr.e_shnum, sizeof(struct section));
+	if (!secs) {
+		die("Unable to allocate %d section headers\n",
+		    ehdr.e_shnum);
 	}
 	if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) {
 		die("Seek to %d failed: %s\n",
 			ehdr.e_shoff, strerror(errno));
 	}
-	if (fread(&shdr, sizeof(shdr[0]), ehdr.e_shnum, fp) != ehdr.e_shnum) {
-		die("Cannot read ELF section headers: %s\n",
-			strerror(errno));
-	}
-	for(i = 0; i < ehdr.e_shnum; i++) {
-		shdr[i].sh_name      = elf32_to_cpu(shdr[i].sh_name);
-		shdr[i].sh_type      = elf32_to_cpu(shdr[i].sh_type);
-		shdr[i].sh_flags     = elf32_to_cpu(shdr[i].sh_flags);
-		shdr[i].sh_addr      = elf32_to_cpu(shdr[i].sh_addr);
-		shdr[i].sh_offset    = elf32_to_cpu(shdr[i].sh_offset);
-		shdr[i].sh_size      = elf32_to_cpu(shdr[i].sh_size);
-		shdr[i].sh_link      = elf32_to_cpu(shdr[i].sh_link);
-		shdr[i].sh_info      = elf32_to_cpu(shdr[i].sh_info);
-		shdr[i].sh_addralign = elf32_to_cpu(shdr[i].sh_addralign);
-		shdr[i].sh_entsize   = elf32_to_cpu(shdr[i].sh_entsize);
+	for (i = 0; i < ehdr.e_shnum; i++) {
+		struct section *sec = &secs[i];
+		if (fread(&shdr, sizeof shdr, 1, fp) != 1)
+			die("Cannot read ELF section headers %d/%d: %s\n",
+			    i, ehdr.e_shnum, strerror(errno));
+		sec->shdr.sh_name      = elf32_to_cpu(shdr.sh_name);
+		sec->shdr.sh_type      = elf32_to_cpu(shdr.sh_type);
+		sec->shdr.sh_flags     = elf32_to_cpu(shdr.sh_flags);
+		sec->shdr.sh_addr      = elf32_to_cpu(shdr.sh_addr);
+		sec->shdr.sh_offset    = elf32_to_cpu(shdr.sh_offset);
+		sec->shdr.sh_size      = elf32_to_cpu(shdr.sh_size);
+		sec->shdr.sh_link      = elf32_to_cpu(shdr.sh_link);
+		sec->shdr.sh_info      = elf32_to_cpu(shdr.sh_info);
+		sec->shdr.sh_addralign = elf32_to_cpu(shdr.sh_addralign);
+		sec->shdr.sh_entsize   = elf32_to_cpu(shdr.sh_entsize);
+		if (sec->shdr.sh_link < ehdr.e_shnum)
+			sec->link = &secs[sec->shdr.sh_link];
 	}
 
 }
@@ -274,20 +283,22 @@ static void read_shdrs(FILE *fp)
 static void read_strtabs(FILE *fp)
 {
 	int i;
-	for(i = 0; i < ehdr.e_shnum; i++) {
-		if (shdr[i].sh_type != SHT_STRTAB) {
+	for (i = 0; i < ehdr.e_shnum; i++) {
+		struct section *sec = &secs[i];
+		if (sec->shdr.sh_type != SHT_STRTAB) {
 			continue;
 		}
-		strtab[i] = malloc(shdr[i].sh_size);
-		if (!strtab[i]) {
+		sec->strtab = malloc(sec->shdr.sh_size);
+		if (!sec->strtab) {
 			die("malloc of %d bytes for strtab failed\n",
-				shdr[i].sh_size);
+				sec->shdr.sh_size);
 		}
-		if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) {
+		if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
 			die("Seek to %d failed: %s\n",
-				shdr[i].sh_offset, strerror(errno));
+				sec->shdr.sh_offset, strerror(errno));
 		}
-		if (fread(strtab[i], 1, shdr[i].sh_size, fp) != shdr[i].sh_size) {
+		if (fread(sec->strtab, 1, sec->shdr.sh_size, fp)
+		    != sec->shdr.sh_size) {
 			die("Cannot read symbol table: %s\n",
 				strerror(errno));
 		}
@@ -297,28 +308,31 @@ static void read_strtabs(FILE *fp)
 static void read_symtabs(FILE *fp)
 {
 	int i,j;
-	for(i = 0; i < ehdr.e_shnum; i++) {
-		if (shdr[i].sh_type != SHT_SYMTAB) {
+	for (i = 0; i < ehdr.e_shnum; i++) {
+		struct section *sec = &secs[i];
+		if (sec->shdr.sh_type != SHT_SYMTAB) {
 			continue;
 		}
-		symtab[i] = malloc(shdr[i].sh_size);
-		if (!symtab[i]) {
+		sec->symtab = malloc(sec->shdr.sh_size);
+		if (!sec->symtab) {
 			die("malloc of %d bytes for symtab failed\n",
-				shdr[i].sh_size);
+				sec->shdr.sh_size);
 		}
-		if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) {
+		if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
 			die("Seek to %d failed: %s\n",
-				shdr[i].sh_offset, strerror(errno));
+				sec->shdr.sh_offset, strerror(errno));
 		}
-		if (fread(symtab[i], 1, shdr[i].sh_size, fp) != shdr[i].sh_size) {
+		if (fread(sec->symtab, 1, sec->shdr.sh_size, fp)
+		    != sec->shdr.sh_size) {
 			die("Cannot read symbol table: %s\n",
 				strerror(errno));
 		}
-		for(j = 0; j < shdr[i].sh_size/sizeof(symtab[i][0]); j++) {
-			symtab[i][j].st_name  = elf32_to_cpu(symtab[i][j].st_name);
-			symtab[i][j].st_value = elf32_to_cpu(symtab[i][j].st_value);
-			symtab[i][j].st_size  = elf32_to_cpu(symtab[i][j].st_size);
-			symtab[i][j].st_shndx = elf16_to_cpu(symtab[i][j].st_shndx);
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) {
+			Elf32_Sym *sym = &sec->symtab[j];
+			sym->st_name  = elf32_to_cpu(sym->st_name);
+			sym->st_value = elf32_to_cpu(sym->st_value);
+			sym->st_size  = elf32_to_cpu(sym->st_size);
+			sym->st_shndx = elf16_to_cpu(sym->st_shndx);
 		}
 	}
 }
@@ -327,26 +341,29 @@ static void read_symtabs(FILE *fp)
 static void read_relocs(FILE *fp)
 {
 	int i,j;
-	for(i = 0; i < ehdr.e_shnum; i++) {
-		if (shdr[i].sh_type != SHT_REL) {
+	for (i = 0; i < ehdr.e_shnum; i++) {
+		struct section *sec = &secs[i];
+		if (sec->shdr.sh_type != SHT_REL) {
 			continue;
 		}
-		reltab[i] = malloc(shdr[i].sh_size);
-		if (!reltab[i]) {
+		sec->reltab = malloc(sec->shdr.sh_size);
+		if (!sec->reltab) {
 			die("malloc of %d bytes for relocs failed\n",
-				shdr[i].sh_size);
+				sec->shdr.sh_size);
 		}
-		if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) {
+		if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
 			die("Seek to %d failed: %s\n",
-				shdr[i].sh_offset, strerror(errno));
+				sec->shdr.sh_offset, strerror(errno));
 		}
-		if (fread(reltab[i], 1, shdr[i].sh_size, fp) != shdr[i].sh_size) {
+		if (fread(sec->reltab, 1, sec->shdr.sh_size, fp)
+		    != sec->shdr.sh_size) {
 			die("Cannot read symbol table: %s\n",
 				strerror(errno));
 		}
-		for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) {
-			reltab[i][j].r_offset = elf32_to_cpu(reltab[i][j].r_offset);
-			reltab[i][j].r_info   = elf32_to_cpu(reltab[i][j].r_info);
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) {
+			Elf32_Rel *rel = &sec->reltab[j];
+			rel->r_offset = elf32_to_cpu(rel->r_offset);
+			rel->r_info   = elf32_to_cpu(rel->r_info);
 		}
 	}
 }
@@ -357,19 +374,21 @@ static void print_absolute_symbols(void)
 	int i;
 	printf("Absolute symbols\n");
 	printf(" Num:    Value Size  Type       Bind        Visibility  Name\n");
-	for(i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < ehdr.e_shnum; i++) {
+		struct section *sec = &secs[i];
 		char *sym_strtab;
 		Elf32_Sym *sh_symtab;
 		int j;
-		if (shdr[i].sh_type != SHT_SYMTAB) {
+
+		if (sec->shdr.sh_type != SHT_SYMTAB) {
 			continue;
 		}
-		sh_symtab = symtab[i];
-		sym_strtab = strtab[shdr[i].sh_link];
-		for(j = 0; j < shdr[i].sh_size/sizeof(symtab[0][0]); j++) {
+		sh_symtab = sec->symtab;
+		sym_strtab = sec->link->strtab;
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) {
 			Elf32_Sym *sym;
 			const char *name;
-			sym = &symtab[i][j];
+			sym = &sec->symtab[j];
 			name = sym_name(sym_strtab, sym);
 			if (sym->st_shndx != SHN_ABS) {
 				continue;
@@ -389,26 +408,27 @@ static void print_absolute_relocs(void)
 {
 	int i, printed = 0;
 
-	for(i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < ehdr.e_shnum; i++) {
+		struct section *sec = &secs[i];
+		struct section *sec_applies, *sec_symtab;
 		char *sym_strtab;
 		Elf32_Sym *sh_symtab;
-		unsigned sec_applies, sec_symtab;
 		int j;
-		if (shdr[i].sh_type != SHT_REL) {
+		if (sec->shdr.sh_type != SHT_REL) {
 			continue;
 		}
-		sec_symtab  = shdr[i].sh_link;
-		sec_applies = shdr[i].sh_info;
-		if (!(shdr[sec_applies].sh_flags & SHF_ALLOC)) {
+		sec_symtab  = sec->link;
+		sec_applies = &secs[sec->shdr.sh_info];
+		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) {
 			continue;
 		}
-		sh_symtab = symtab[sec_symtab];
-		sym_strtab = strtab[shdr[sec_symtab].sh_link];
-		for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) {
+		sh_symtab  = sec_symtab->symtab;
+		sym_strtab = sec_symtab->link->strtab;
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) {
 			Elf32_Rel *rel;
 			Elf32_Sym *sym;
 			const char *name;
-			rel = &reltab[i][j];
+			rel = &sec->reltab[j];
 			sym = &sh_symtab[ELF32_R_SYM(rel->r_info)];
 			name = sym_name(sym_strtab, sym);
 			if (sym->st_shndx != SHN_ABS) {
@@ -456,26 +476,28 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
 {
 	int i;
 	/* Walk through the relocations */
-	for(i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < ehdr.e_shnum; i++) {
 		char *sym_strtab;
 		Elf32_Sym *sh_symtab;
-		unsigned sec_applies, sec_symtab;
+		struct section *sec_applies, *sec_symtab;
 		int j;
-		if (shdr[i].sh_type != SHT_REL) {
+		struct section *sec = &secs[i];
+
+		if (sec->shdr.sh_type != SHT_REL) {
 			continue;
 		}
-		sec_symtab  = shdr[i].sh_link;
-		sec_applies = shdr[i].sh_info;
-		if (!(shdr[sec_applies].sh_flags & SHF_ALLOC)) {
+		sec_symtab  = sec->link;
+		sec_applies = &secs[sec->shdr.sh_info];
+		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) {
 			continue;
 		}
-		sh_symtab = symtab[sec_symtab];
-		sym_strtab = strtab[shdr[sec_symtab].sh_link];
-		for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) {
+		sh_symtab = sec_symtab->symtab;
+		sym_strtab = sec->link->strtab;
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) {
 			Elf32_Rel *rel;
 			Elf32_Sym *sym;
 			unsigned r_type;
-			rel = &reltab[i][j];
+			rel = &sec->reltab[j];
 			sym = &sh_symtab[ELF32_R_SYM(rel->r_info)];
 			r_type = ELF32_R_TYPE(rel->r_info);
 			/* Don't visit relocations to absolute symbols */
@@ -539,7 +561,7 @@ static void emit_relocs(int as_text)
 		 */
 		printf(".section \".data.reloc\",\"a\"\n");
 		printf(".balign 4\n");
-		for(i = 0; i < reloc_count; i++) {
+		for (i = 0; i < reloc_count; i++) {
 			printf("\t .long 0x%08lx\n", relocs[i]);
 		}
 		printf("\n");
@@ -550,7 +572,7 @@ static void emit_relocs(int as_text)
 		/* Print a stop */
 		printf("%c%c%c%c", buf[0], buf[1], buf[2], buf[3]);
 		/* Now print each relocation */
-		for(i = 0; i < reloc_count; i++) {
+		for (i = 0; i < reloc_count; i++) {
 			buf[0] = (relocs[i] >>  0) & 0xff;
 			buf[1] = (relocs[i] >>  8) & 0xff;
 			buf[2] = (relocs[i] >> 16) & 0xff;
@@ -577,7 +599,7 @@ int main(int argc, char **argv)
 	show_absolute_relocs = 0;
 	as_text = 0;
 	fname = NULL;
-	for(i = 1; i < argc; i++) {
+	for (i = 1; i < argc; i++) {
 		char *arg = argv[i];
 		if (*arg == '-') {
 			if (strcmp(argv[1], "--abs-syms") == 0) {

arch/x86/boot/cpu.c

@@ -28,6 +28,8 @@ static char *cpu_name(int level)
 	if (level == 64) {
 		return "x86-64";
 	} else {
+		if (level == 15)
+			level = 6;
 		sprintf(buf, "i%d86", level);
 		return buf;
 	}

arch/x86/boot/main.c

@@ -165,6 +165,10 @@ void main(void)
 	/* Set the video mode */
 	set_video();
 
+	/* Parse command line for 'quiet' and pass it to decompressor. */
+	if (cmdline_find_option_bool("quiet"))
+		boot_params.hdr.loadflags |= QUIET_FLAG;
+
 	/* Do the last things and invoke protected mode */
 	go_to_protected_mode();
 }

arch/x86/boot/memory.c

@@ -13,6 +13,7 @@
  */
 
 #include "boot.h"
+#include <linux/kernel.h>
 
 #define SMAP	0x534d4150	/* ASCII "SMAP" */
 
@@ -53,7 +54,7 @@ static int detect_memory_e820(void)
 
 		count++;
 		desc++;
-	} while (next && count < E820MAX);
+	} while (next && count < ARRAY_SIZE(boot_params.e820_map));
 
 	return boot_params.e820_entries = count;
 }

arch/x86/boot/pmjump.S

@@ -33,6 +33,8 @@ protected_mode_jump:
 	movw	%cs, %bx
 	shll	$4, %ebx
 	addl	%ebx, 2f
+	jmp	1f			# Short jump to serialize on 386/486
+1:
 
 	movw	$__BOOT_DS, %cx
 	movw	$__BOOT_TSS, %di
@@ -40,8 +42,6 @@ protected_mode_jump:
 	movl	%cr0, %edx
 	orb	$X86_CR0_PE, %dl	# Protected mode
 	movl	%edx, %cr0
-	jmp	1f			# Short jump to serialize on 386/486
-1:
 
 	# Transition to 32-bit mode
 	.byte	0x66, 0xea		# ljmpl opcode

arch/x86/boot/video-vga.c

@@ -259,8 +259,7 @@ static int vga_probe(void)
 	return mode_count[adapter];
 }
 
-__videocard video_vga =
-{
+__videocard video_vga = {
 	.card_name	= "VGA",
 	.probe		= vga_probe,
 	.set_mode	= vga_set_mode,

arch/x86/ia32/ia32entry.S

@@ -61,6 +61,19 @@
 	CFI_UNDEFINED	r15
 	.endm
 
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret32)
+	swapgs
+	sysretl
+ENDPROC(native_usergs_sysret32)
+
+ENTRY(native_irq_enable_sysexit)
+	swapgs
+	sti
+	sysexit
+ENDPROC(native_irq_enable_sysexit)
+#endif
+
 /*
  * 32bit SYSENTER instruction entry.
  *
@@ -85,14 +98,14 @@ ENTRY(ia32_sysenter_target)
 	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA	rsp,0
 	CFI_REGISTER	rsp,rbp
-	swapgs
+	SWAPGS_UNSAFE_STACK
 	movq	%gs:pda_kernelstack, %rsp
 	addq	$(PDA_STACKOFFSET),%rsp	
 	/*
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs, here we enable it straight after entry:
 	 */
-	sti	
+	ENABLE_INTERRUPTS(CLBR_NONE)
  	movl	%ebp,%ebp		/* zero extension */
 	pushq	$__USER32_DS
 	CFI_ADJUST_CFA_OFFSET 8
@@ -103,7 +116,7 @@ ENTRY(ia32_sysenter_target)
 	pushfq
 	CFI_ADJUST_CFA_OFFSET 8
 	/*CFI_REL_OFFSET rflags,0*/
-	movl	8*3-THREAD_SIZE+threadinfo_sysenter_return(%rsp), %r10d
+	movl	8*3-THREAD_SIZE+TI_sysenter_return(%rsp), %r10d
 	CFI_REGISTER rip,r10
 	pushq	$__USER32_CS
 	CFI_ADJUST_CFA_OFFSET 8
@@ -123,8 +136,9 @@ ENTRY(ia32_sysenter_target)
  	.quad 1b,ia32_badarg
  	.previous	
 	GET_THREAD_INFO(%r10)
-	orl    $TS_COMPAT,threadinfo_status(%r10)
-	testl  $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10)
+	orl    $TS_COMPAT,TI_status(%r10)
+	testl  $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+		 TI_flags(%r10)
 	CFI_REMEMBER_STATE
 	jnz  sysenter_tracesys
 sysenter_do_call:	
@@ -134,11 +148,11 @@ sysenter_do_call:
 	call	*ia32_sys_call_table(,%rax,8)
 	movq	%rax,RAX-ARGOFFSET(%rsp)
 	GET_THREAD_INFO(%r10)
-	cli
+	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	testl	$_TIF_ALLWORK_MASK,threadinfo_flags(%r10)
+	testl	$_TIF_ALLWORK_MASK,TI_flags(%r10)
 	jnz	int_ret_from_sys_call
-	andl    $~TS_COMPAT,threadinfo_status(%r10)
+	andl    $~TS_COMPAT,TI_status(%r10)
 	/* clear IF, that popfq doesn't enable interrupts early */
 	andl  $~0x200,EFLAGS-R11(%rsp) 
 	movl	RIP-R11(%rsp),%edx		/* User %eip */
@@ -151,10 +165,7 @@ sysenter_do_call:
 	CFI_ADJUST_CFA_OFFSET -8
 	CFI_REGISTER rsp,rcx
 	TRACE_IRQS_ON
-	swapgs
-	sti		/* sti only takes effect after the next instruction */
-	/* sysexit */
-	.byte	0xf, 0x35
+	ENABLE_INTERRUPTS_SYSEXIT32
 
 sysenter_tracesys:
 	CFI_RESTORE_STATE
@@ -200,7 +211,7 @@ ENTRY(ia32_cstar_target)
 	CFI_DEF_CFA	rsp,PDA_STACKOFFSET
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
-	swapgs
+	SWAPGS_UNSAFE_STACK
 	movl	%esp,%r8d
 	CFI_REGISTER	rsp,r8
 	movq	%gs:pda_kernelstack,%rsp
@@ -208,7 +219,7 @@ ENTRY(ia32_cstar_target)
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs and here we enable it straight after entry:
 	 */
-	sti
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_ARGS 8,1,1
 	movl 	%eax,%eax	/* zero extension */
 	movq	%rax,ORIG_RAX-ARGOFFSET(%rsp)
@@ -230,8 +241,9 @@ ENTRY(ia32_cstar_target)
 	.quad 1b,ia32_badarg
 	.previous	
 	GET_THREAD_INFO(%r10)
-	orl   $TS_COMPAT,threadinfo_status(%r10)
-	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10)
+	orl   $TS_COMPAT,TI_status(%r10)
+	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+		TI_flags(%r10)
 	CFI_REMEMBER_STATE
 	jnz   cstar_tracesys
 cstar_do_call:	
@@ -241,11 +253,11 @@ cstar_do_call:
 	call *ia32_sys_call_table(,%rax,8)
 	movq %rax,RAX-ARGOFFSET(%rsp)
 	GET_THREAD_INFO(%r10)
-	cli
+	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10)
+	testl $_TIF_ALLWORK_MASK,TI_flags(%r10)
 	jnz  int_ret_from_sys_call
-	andl $~TS_COMPAT,threadinfo_status(%r10)
+	andl $~TS_COMPAT,TI_status(%r10)
 	RESTORE_ARGS 1,-ARG_SKIP,1,1,1
 	movl RIP-ARGOFFSET(%rsp),%ecx
 	CFI_REGISTER rip,rcx
@@ -254,8 +266,7 @@ cstar_do_call:
 	TRACE_IRQS_ON
 	movl RSP-ARGOFFSET(%rsp),%esp
 	CFI_RESTORE rsp
-	swapgs
-	sysretl
+	USERGS_SYSRET32
 	
 cstar_tracesys:	
 	CFI_RESTORE_STATE
@@ -310,12 +321,12 @@ ENTRY(ia32_syscall)
 	/*CFI_REL_OFFSET	rflags,EFLAGS-RIP*/
 	/*CFI_REL_OFFSET	cs,CS-RIP*/
 	CFI_REL_OFFSET	rip,RIP-RIP
-	swapgs
+	SWAPGS
 	/*
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs and here we enable it straight after entry:
 	 */
-	sti
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	movl %eax,%eax
 	pushq %rax
 	CFI_ADJUST_CFA_OFFSET 8
@@ -324,8 +335,9 @@ ENTRY(ia32_syscall)
 	   this could be a problem. */
 	SAVE_ARGS 0,0,1
 	GET_THREAD_INFO(%r10)
-	orl   $TS_COMPAT,threadinfo_status(%r10)
-	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10)
+	orl   $TS_COMPAT,TI_status(%r10)
+	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+		TI_flags(%r10)
 	jnz ia32_tracesys
 ia32_do_syscall:	
 	cmpl $(IA32_NR_syscalls-1),%eax
@@ -370,13 +382,11 @@ quiet_ni_syscall:
 	PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi
 	PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi
 	PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx
-	PTREGSCALL stub32_sigsuspend, sys32_sigsuspend, %rcx
 	PTREGSCALL stub32_execve, sys32_execve, %rcx
 	PTREGSCALL stub32_fork, sys_fork, %rdi
 	PTREGSCALL stub32_clone, sys32_clone, %rdx
 	PTREGSCALL stub32_vfork, sys_vfork, %rdi
 	PTREGSCALL stub32_iopl, sys_iopl, %rsi
-	PTREGSCALL stub32_rt_sigsuspend, sys_rt_sigsuspend, %rdx
 
 ENTRY(ia32_ptregs_common)
 	popq %r11
@@ -476,7 +486,7 @@ ia32_sys_call_table:
 	.quad sys_ssetmask
 	.quad sys_setreuid16	/* 70 */
 	.quad sys_setregid16
-	.quad stub32_sigsuspend
+	.quad sys32_sigsuspend
 	.quad compat_sys_sigpending
 	.quad sys_sethostname
 	.quad compat_sys_setrlimit	/* 75 */
@@ -583,7 +593,7 @@ ia32_sys_call_table:
 	.quad sys32_rt_sigpending
 	.quad compat_sys_rt_sigtimedwait
 	.quad sys32_rt_sigqueueinfo
-	.quad stub32_rt_sigsuspend
+	.quad sys_rt_sigsuspend
 	.quad sys32_pread		/* 180 */
 	.quad sys32_pwrite
 	.quad sys_chown16

arch/x86/kernel/Makefile

@@ -2,7 +2,7 @@
 # Makefile for the linux kernel.
 #
 
-extra-y                := head_$(BITS).o head$(BITS).o init_task.o vmlinux.lds
+extra-y                := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinux.lds
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
@@ -13,20 +13,21 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
 CFLAGS_hpet.o		:= $(nostackp)
-CFLAGS_tsc_64.o		:= $(nostackp)
+CFLAGS_tsc.o		:= $(nostackp)
 
 obj-y			:= process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
 obj-y			+= traps_$(BITS).o irq_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o
-obj-y			+= setup_$(BITS).o i8259_$(BITS).o setup.o
+obj-y			+= setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
+obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
+obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
-obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o setup64.o
-obj-y			+= bootflag.o e820_$(BITS).o
+obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
+obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o
-obj-$(CONFIG_X86_64)	+= bugs_64.o
-obj-y			+= tsc_$(BITS).o io_delay.o rtc.o
+obj-y			+= tsc.o io_delay.o rtc.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
@@ -53,7 +54,7 @@ obj-$(CONFIG_X86_32_SMP)	+= smpcommon.o
 obj-$(CONFIG_X86_64_SMP)	+= tsc_sync.o smpcommon.o
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline_$(BITS).o
 obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
-obj-$(CONFIG_X86_LOCAL_APIC)	+= apic_$(BITS).o nmi_$(BITS).o
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic_$(BITS).o nmi.o
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic_$(BITS).o
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
@@ -64,7 +65,6 @@ obj-$(CONFIG_X86_SUMMIT_NUMA)	+= summit_32.o
 obj-y				+= vsmp_64.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_MODULES)		+= module_$(BITS).o
-obj-$(CONFIG_ACPI_SRAT) 	+= srat_32.o
 obj-$(CONFIG_EFI) 		+= efi.o efi_$(BITS).o efi_stub_$(BITS).o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
@@ -94,12 +94,13 @@ obj-$(CONFIG_OLPC)		+= olpc.o
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
-        obj-y				+= genapic_64.o genapic_flat_64.o genx2apic_uv_x.o
+        obj-y				+= genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
         obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
         obj-$(CONFIG_AUDIT)		+= audit_64.o
 
         obj-$(CONFIG_GART_IOMMU)	+= pci-gart_64.o aperture_64.o
         obj-$(CONFIG_CALGARY_IOMMU)	+= pci-calgary_64.o tce_64.o
+        obj-$(CONFIG_AMD_IOMMU)		+= amd_iommu_init.o amd_iommu.o
         obj-$(CONFIG_SWIOTLB)		+= pci-swiotlb_64.o
 
         obj-$(CONFIG_PCI_MMCONFIG)	+= mmconf-fam10h_64.o

arch/x86/kernel/acpi/boot.c

@@ -37,6 +37,7 @@
 #include <asm/pgtable.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
+#include <asm/genapic.h>
 #include <asm/io.h>
 #include <asm/mpspec.h>
 #include <asm/smp.h>
@@ -106,21 +107,6 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
  */
 enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC;
 
-#ifdef	CONFIG_X86_64
-
-/* rely on all ACPI tables being in the direct mapping */
-char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size)
-{
-	if (!phys_addr || !size)
-		return NULL;
-
-	if (phys_addr+size <= (max_pfn_mapped << PAGE_SHIFT) + PAGE_SIZE)
-		return __va(phys_addr);
-
-	return NULL;
-}
-
-#else
 
 /*
  * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END,
@@ -139,11 +125,15 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 	unsigned long base, offset, mapped_size;
 	int idx;
 
-	if (phys + size < 8 * 1024 * 1024)
+	if (!phys || !size)
+		return NULL;
+
+	if (phys+size <= (max_low_pfn_mapped << PAGE_SHIFT))
 		return __va(phys);
 
 	offset = phys & (PAGE_SIZE - 1);
 	mapped_size = PAGE_SIZE - offset;
+	clear_fixmap(FIX_ACPI_END);
 	set_fixmap(FIX_ACPI_END, phys);
 	base = fix_to_virt(FIX_ACPI_END);
 
@@ -155,13 +145,13 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 		if (--idx < FIX_ACPI_BEGIN)
 			return NULL;	/* cannot handle this */
 		phys += PAGE_SIZE;
+		clear_fixmap(idx);
 		set_fixmap(idx, phys);
 		mapped_size += PAGE_SIZE;
 	}
 
 	return ((unsigned char *)base + offset);
 }
-#endif
 
 #ifdef CONFIG_PCI_MMCONFIG
 /* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
@@ -338,8 +328,6 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e
 
 #ifdef CONFIG_X86_IO_APIC
 
-struct mp_ioapic_routing mp_ioapic_routing[MAX_IO_APICS];
-
 static int __init
 acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
 {
@@ -514,8 +502,6 @@ int acpi_register_gsi(u32 gsi, int triggering, int polarity)
 	 * Make sure all (legacy) PCI IRQs are set as level-triggered.
 	 */
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
-		extern void eisa_set_level_irq(unsigned int irq);
-
 		if (triggering == ACPI_LEVEL_SENSITIVE)
 			eisa_set_level_irq(gsi);
 	}
@@ -860,6 +846,364 @@ static int __init acpi_parse_madt_lapic_entries(void)
 #endif				/* CONFIG_X86_LOCAL_APIC */
 
 #ifdef	CONFIG_X86_IO_APIC
+#define MP_ISA_BUS		0
+
+#ifdef CONFIG_X86_ES7000
+extern int es7000_plat;
+#endif
+
+static struct {
+	int apic_id;
+	int gsi_base;
+	int gsi_end;
+	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+} mp_ioapic_routing[MAX_IO_APICS];
+
+static int mp_find_ioapic(int gsi)
+{
+	int i = 0;
+
+	/* Find the IOAPIC that manages this GSI. */
+	for (i = 0; i < nr_ioapics; i++) {
+		if ((gsi >= mp_ioapic_routing[i].gsi_base)
+		    && (gsi <= mp_ioapic_routing[i].gsi_end))
+			return i;
+	}
+
+	printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi);
+	return -1;
+}
+
+static u8 __init uniq_ioapic_id(u8 id)
+{
+#ifdef CONFIG_X86_32
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+	    !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+		return io_apic_get_unique_id(nr_ioapics, id);
+	else
+		return id;
+#else
+	int i;
+	DECLARE_BITMAP(used, 256);
+	bitmap_zero(used, 256);
+	for (i = 0; i < nr_ioapics; i++) {
+		struct mp_config_ioapic *ia = &mp_ioapics[i];
+		__set_bit(ia->mp_apicid, used);
+	}
+	if (!test_bit(id, used))
+		return id;
+	return find_first_zero_bit(used, 256);
+#endif
+}
+
+static int bad_ioapic(unsigned long address)
+{
+	if (nr_ioapics >= MAX_IO_APICS) {
+		printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded "
+		       "(found %d)\n", MAX_IO_APICS, nr_ioapics);
+		panic("Recompile kernel with bigger MAX_IO_APICS!\n");
+	}
+	if (!address) {
+		printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address"
+		       " found in table, skipping!\n");
+		return 1;
+	}
+	return 0;
+}
+
+void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
+{
+	int idx = 0;
+
+	if (bad_ioapic(address))
+		return;
+
+	idx = nr_ioapics;
+
+	mp_ioapics[idx].mp_type = MP_IOAPIC;
+	mp_ioapics[idx].mp_flags = MPC_APIC_USABLE;
+	mp_ioapics[idx].mp_apicaddr = address;
+
+	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
+	mp_ioapics[idx].mp_apicid = uniq_ioapic_id(id);
+#ifdef CONFIG_X86_32
+	mp_ioapics[idx].mp_apicver = io_apic_get_version(idx);
+#else
+	mp_ioapics[idx].mp_apicver = 0;
+#endif
+	/*
+	 * Build basic GSI lookup table to facilitate gsi->io_apic lookups
+	 * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
+	 */
+	mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mp_apicid;
+	mp_ioapic_routing[idx].gsi_base = gsi_base;
+	mp_ioapic_routing[idx].gsi_end = gsi_base +
+	    io_apic_get_redir_entries(idx);
+
+	printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, "
+	       "GSI %d-%d\n", idx, mp_ioapics[idx].mp_apicid,
+	       mp_ioapics[idx].mp_apicver, mp_ioapics[idx].mp_apicaddr,
+	       mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end);
+
+	nr_ioapics++;
+}
+
+static void assign_to_mp_irq(struct mp_config_intsrc *m,
+				    struct mp_config_intsrc *mp_irq)
+{
+	memcpy(mp_irq, m, sizeof(struct mp_config_intsrc));
+}
+
+static int mp_irq_cmp(struct mp_config_intsrc *mp_irq,
+				struct mp_config_intsrc *m)
+{
+	return memcmp(mp_irq, m, sizeof(struct mp_config_intsrc));
+}
+
+static void save_mp_irq(struct mp_config_intsrc *m)
+{
+	int i;
+
+	for (i = 0; i < mp_irq_entries; i++) {
+		if (!mp_irq_cmp(&mp_irqs[i], m))
+			return;
+	}
+
+	assign_to_mp_irq(m, &mp_irqs[mp_irq_entries]);
+	if (++mp_irq_entries == MAX_IRQ_SOURCES)
+		panic("Max # of irq sources exceeded!!\n");
+}
+
+void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
+{
+	int ioapic;
+	int pin;
+	struct mp_config_intsrc mp_irq;
+
+	/*
+	 * Convert 'gsi' to 'ioapic.pin'.
+	 */
+	ioapic = mp_find_ioapic(gsi);
+	if (ioapic < 0)
+		return;
+	pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+
+	/*
+	 * TBD: This check is for faulty timer entries, where the override
+	 *      erroneously sets the trigger to level, resulting in a HUGE
+	 *      increase of timer interrupts!
+	 */
+	if ((bus_irq == 0) && (trigger == 3))
+		trigger = 1;
+
+	mp_irq.mp_type = MP_INTSRC;
+	mp_irq.mp_irqtype = mp_INT;
+	mp_irq.mp_irqflag = (trigger << 2) | polarity;
+	mp_irq.mp_srcbus = MP_ISA_BUS;
+	mp_irq.mp_srcbusirq = bus_irq;	/* IRQ */
+	mp_irq.mp_dstapic = mp_ioapics[ioapic].mp_apicid; /* APIC ID */
+	mp_irq.mp_dstirq = pin;	/* INTIN# */
+
+	save_mp_irq(&mp_irq);
+}
+
+void __init mp_config_acpi_legacy_irqs(void)
+{
+	int i;
+	int ioapic;
+	unsigned int dstapic;
+	struct mp_config_intsrc mp_irq;
+
+#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
+	/*
+	 * Fabricate the legacy ISA bus (bus #31).
+	 */
+	mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA;
+#endif
+	set_bit(MP_ISA_BUS, mp_bus_not_pci);
+	Dprintk("Bus #%d is ISA\n", MP_ISA_BUS);
+
+#ifdef CONFIG_X86_ES7000
+	/*
+	 * Older generations of ES7000 have no legacy identity mappings
+	 */
+	if (es7000_plat == 1)
+		return;
+#endif
+
+	/*
+	 * Locate the IOAPIC that manages the ISA IRQs (0-15).
+	 */
+	ioapic = mp_find_ioapic(0);
+	if (ioapic < 0)
+		return;
+	dstapic = mp_ioapics[ioapic].mp_apicid;
+
+	/*
+	 * Use the default configuration for the IRQs 0-15.  Unless
+	 * overridden by (MADT) interrupt source override entries.
+	 */
+	for (i = 0; i < 16; i++) {
+		int idx;
+
+		for (idx = 0; idx < mp_irq_entries; idx++) {
+			struct mp_config_intsrc *irq = mp_irqs + idx;
+
+			/* Do we already have a mapping for this ISA IRQ? */
+			if (irq->mp_srcbus == MP_ISA_BUS
+			    && irq->mp_srcbusirq == i)
+				break;
+
+			/* Do we already have a mapping for this IOAPIC pin */
+			if (irq->mp_dstapic == dstapic &&
+			    irq->mp_dstirq == i)
+				break;
+		}
+
+		if (idx != mp_irq_entries) {
+			printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i);
+			continue;	/* IRQ already used */
+		}
+
+		mp_irq.mp_type = MP_INTSRC;
+		mp_irq.mp_irqflag = 0;	/* Conforming */
+		mp_irq.mp_srcbus = MP_ISA_BUS;
+		mp_irq.mp_dstapic = dstapic;
+		mp_irq.mp_irqtype = mp_INT;
+		mp_irq.mp_srcbusirq = i; /* Identity mapped */
+		mp_irq.mp_dstirq = i;
+
+		save_mp_irq(&mp_irq);
+	}
+}
+
+int mp_register_gsi(u32 gsi, int triggering, int polarity)
+{
+	int ioapic;
+	int ioapic_pin;
+#ifdef CONFIG_X86_32
+#define MAX_GSI_NUM	4096
+#define IRQ_COMPRESSION_START	64
+
+	static int pci_irq = IRQ_COMPRESSION_START;
+	/*
+	 * Mapping between Global System Interrupts, which
+	 * represent all possible interrupts, and IRQs
+	 * assigned to actual devices.
+	 */
+	static int gsi_to_irq[MAX_GSI_NUM];
+#else
+
+	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
+		return gsi;
+#endif
+
+	/* Don't set up the ACPI SCI because it's already set up */
+	if (acpi_gbl_FADT.sci_interrupt == gsi)
+		return gsi;
+
+	ioapic = mp_find_ioapic(gsi);
+	if (ioapic < 0) {
+		printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi);
+		return gsi;
+	}
+
+	ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+
+#ifdef CONFIG_X86_32
+	if (ioapic_renumber_irq)
+		gsi = ioapic_renumber_irq(ioapic, gsi);
+#endif
+
+	/*
+	 * Avoid pin reprogramming.  PRTs typically include entries
+	 * with redundant pin->gsi mappings (but unique PCI devices);
+	 * we only program the IOAPIC on the first.
+	 */
+	if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
+		printk(KERN_ERR "Invalid reference to IOAPIC pin "
+		       "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+		       ioapic_pin);
+		return gsi;
+	}
+	if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
+		Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
+			mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
+#ifdef CONFIG_X86_32
+		return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]);
+#else
+		return gsi;
+#endif
+	}
+
+	set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
+#ifdef CONFIG_X86_32
+	/*
+	 * For GSI >= 64, use IRQ compression
+	 */
+	if ((gsi >= IRQ_COMPRESSION_START)
+	    && (triggering == ACPI_LEVEL_SENSITIVE)) {
+		/*
+		 * For PCI devices assign IRQs in order, avoiding gaps
+		 * due to unused I/O APIC pins.
+		 */
+		int irq = gsi;
+		if (gsi < MAX_GSI_NUM) {
+			/*
+			 * Retain the VIA chipset work-around (gsi > 15), but
+			 * avoid a problem where the 8254 timer (IRQ0) is setup
+			 * via an override (so it's not on pin 0 of the ioapic),
+			 * and at the same time, the pin 0 interrupt is a PCI
+			 * type.  The gsi > 15 test could cause these two pins
+			 * to be shared as IRQ0, and they are not shareable.
+			 * So test for this condition, and if necessary, avoid
+			 * the pin collision.
+			 */
+			gsi = pci_irq++;
+			/*
+			 * Don't assign IRQ used by ACPI SCI
+			 */
+			if (gsi == acpi_gbl_FADT.sci_interrupt)
+				gsi = pci_irq++;
+			gsi_to_irq[irq] = gsi;
+		} else {
+			printk(KERN_ERR "GSI %u is too high\n", gsi);
+			return gsi;
+		}
+	}
+#endif
+	io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
+				triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
+				polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+	return gsi;
+}
+
+int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
+			u32 gsi, int triggering, int polarity)
+{
+#ifdef CONFIG_X86_MPPARSE
+	struct mp_config_intsrc mp_irq;
+	int ioapic;
+
+	if (!acpi_ioapic)
+		return 0;
+
+	/* print the entry should happen on mptable identically */
+	mp_irq.mp_type = MP_INTSRC;
+	mp_irq.mp_irqtype = mp_INT;
+	mp_irq.mp_irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
+	mp_irq.mp_srcbus = number;
+	mp_irq.mp_srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+	ioapic = mp_find_ioapic(gsi);
+	mp_irq.mp_dstapic = mp_ioapic_routing[ioapic].apic_id;
+	mp_irq.mp_dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
+
+	save_mp_irq(&mp_irq);
+#endif
+	return 0;
+}
+
 /*
  * Parse IOAPIC related entries in MADT
  * returns 0 on success, < 0 on error
@@ -1009,8 +1353,6 @@ static void __init acpi_process_madt(void)
 	return;
 }
 
-#ifdef __i386__
-
 static int __init disable_acpi_irq(const struct dmi_system_id *d)
 {
 	if (!acpi_force) {
@@ -1060,6 +1402,16 @@ static int __init force_acpi_ht(const struct dmi_system_id *d)
 	return 0;
 }
 
+/*
+ * Force ignoring BIOS IRQ0 pin2 override
+ */
+static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
+{
+	pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n", d->ident);
+	acpi_skip_timer_override = 1;
+	return 0;
+}
+
 /*
  * If your system is blacklisted here, but you find that acpi=force
  * works for you, please contact acpi-devel@sourceforge.net
@@ -1227,11 +1579,35 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = {
 		     DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"),
 		     },
 	 },
+	/*
+	 * HP laptops which use a DSDT reporting as HP/SB400/10000,
+	 * which includes some code which overrides all temperature
+	 * trip points to 16C if the INTIN2 input of the I/O APIC
+	 * is enabled.  This input is incorrectly designated the
+	 * ISA IRQ 0 via an interrupt source override even though
+	 * it is wired to the output of the master 8259A and INTIN0
+	 * is not connected at all.  Force ignoring BIOS IRQ0 pin2
+	 * override in that cases.
+	 */
+	{
+	 .callback = dmi_ignore_irq0_timer_override,
+	 .ident = "HP NX6125 laptop",
+	 .matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nx6125"),
+		     },
+	 },
+	{
+	 .callback = dmi_ignore_irq0_timer_override,
+	 .ident = "HP NX6325 laptop",
+	 .matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nx6325"),
+		     },
+	 },
 	{}
 };
 
-#endif				/* __i386__ */
-
 /*
  * acpi_boot_table_init() and acpi_boot_init()
  *  called from setup_arch(), always.
@@ -1259,9 +1635,7 @@ int __init acpi_boot_table_init(void)
 {
 	int error;
 
-#ifdef __i386__
 	dmi_check_system(acpi_dmi_table);
-#endif
 
 	/*
 	 * If acpi_disabled, bail out
@@ -1386,6 +1760,20 @@ static int __init parse_pci(char *arg)
 }
 early_param("pci", parse_pci);
 
+int __init acpi_mps_check(void)
+{
+#if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE)
+/* mptable code is not built-in*/
+	if (acpi_disabled || acpi_noirq) {
+		printk(KERN_WARNING "MPS support code is not built-in.\n"
+		       "Using acpi=off or acpi=noirq or pci=noacpi "
+		       "may have problem\n");
+		return 1;
+	}
+#endif
+	return 0;
+}
+
 #ifdef CONFIG_X86_IO_APIC
 static int __init parse_acpi_skip_timer_override(char *arg)
 {

arch/x86/kernel/acpi/sleep.c

@@ -86,7 +86,9 @@ int acpi_save_state_mem(void)
 	saved_magic = 0x12345678;
 #else /* CONFIG_64BIT */
 	header->trampoline_segment = setup_trampoline() >> 4;
-	init_rsp = (unsigned long)temp_stack + 4096;
+#ifdef CONFIG_SMP
+	stack_start.sp = temp_stack + 4096;
+#endif
 	initial_code = (unsigned long)wakeup_long64;
 	saved_magic = 0x123456789abcdef0;
 #endif /* CONFIG_64BIT */

arch/x86/kernel/amd_iommu.c

@@ -0,0 +1,962 @@
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *         Leo Duran <leo.duran@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/pci.h>
+#include <linux/gfp.h>
+#include <linux/bitops.h>
+#include <linux/scatterlist.h>
+#include <linux/iommu-helper.h>
+#include <asm/proto.h>
+#include <asm/gart.h>
+#include <asm/amd_iommu_types.h>
+#include <asm/amd_iommu.h>
+
+#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
+
+#define to_pages(addr, size) \
+	 (round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT)
+
+static DEFINE_RWLOCK(amd_iommu_devtable_lock);
+
+struct command {
+	u32 data[4];
+};
+
+static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
+			     struct unity_map_entry *e);
+
+static int iommu_has_npcache(struct amd_iommu *iommu)
+{
+	return iommu->cap & IOMMU_CAP_NPCACHE;
+}
+
+static int __iommu_queue_command(struct amd_iommu *iommu, struct command *cmd)
+{
+	u32 tail, head;
+	u8 *target;
+
+	tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+	target = (iommu->cmd_buf + tail);
+	memcpy_toio(target, cmd, sizeof(*cmd));
+	tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
+	head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+	if (tail == head)
+		return -ENOMEM;
+	writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+
+	return 0;
+}
+
+static int iommu_queue_command(struct amd_iommu *iommu, struct command *cmd)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	ret = __iommu_queue_command(iommu, cmd);
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return ret;
+}
+
+static int iommu_completion_wait(struct amd_iommu *iommu)
+{
+	int ret;
+	struct command cmd;
+	volatile u64 ready = 0;
+	unsigned long ready_phys = virt_to_phys(&ready);
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.data[0] = LOW_U32(ready_phys) | CMD_COMPL_WAIT_STORE_MASK;
+	cmd.data[1] = HIGH_U32(ready_phys);
+	cmd.data[2] = 1; /* value written to 'ready' */
+	CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
+
+	iommu->need_sync = 0;
+
+	ret = iommu_queue_command(iommu, &cmd);
+
+	if (ret)
+		return ret;
+
+	while (!ready)
+		cpu_relax();
+
+	return 0;
+}
+
+static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid)
+{
+	struct command cmd;
+
+	BUG_ON(iommu == NULL);
+
+	memset(&cmd, 0, sizeof(cmd));
+	CMD_SET_TYPE(&cmd, CMD_INV_DEV_ENTRY);
+	cmd.data[0] = devid;
+
+	iommu->need_sync = 1;
+
+	return iommu_queue_command(iommu, &cmd);
+}
+
+static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
+		u64 address, u16 domid, int pde, int s)
+{
+	struct command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	address &= PAGE_MASK;
+	CMD_SET_TYPE(&cmd, CMD_INV_IOMMU_PAGES);
+	cmd.data[1] |= domid;
+	cmd.data[2] = LOW_U32(address);
+	cmd.data[3] = HIGH_U32(address);
+	if (s)
+		cmd.data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+	if (pde)
+		cmd.data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+
+	iommu->need_sync = 1;
+
+	return iommu_queue_command(iommu, &cmd);
+}
+
+static int iommu_flush_pages(struct amd_iommu *iommu, u16 domid,
+		u64 address, size_t size)
+{
+	int s = 0;
+	unsigned pages = to_pages(address, size);
+
+	address &= PAGE_MASK;
+
+	if (pages > 1) {
+		/*
+		 * If we have to flush more than one page, flush all
+		 * TLB entries for this domain
+		 */
+		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
+		s = 1;
+	}
+
+	iommu_queue_inv_iommu_pages(iommu, address, domid, 0, s);
+
+	return 0;
+}
+
+static int iommu_map(struct protection_domain *dom,
+		     unsigned long bus_addr,
+		     unsigned long phys_addr,
+		     int prot)
+{
+	u64 __pte, *pte, *page;
+
+	bus_addr  = PAGE_ALIGN(bus_addr);
+	phys_addr = PAGE_ALIGN(bus_addr);
+
+	/* only support 512GB address spaces for now */
+	if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
+		return -EINVAL;
+
+	pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(bus_addr)];
+
+	if (!IOMMU_PTE_PRESENT(*pte)) {
+		page = (u64 *)get_zeroed_page(GFP_KERNEL);
+		if (!page)
+			return -ENOMEM;
+		*pte = IOMMU_L2_PDE(virt_to_phys(page));
+	}
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L1_INDEX(bus_addr)];
+
+	if (!IOMMU_PTE_PRESENT(*pte)) {
+		page = (u64 *)get_zeroed_page(GFP_KERNEL);
+		if (!page)
+			return -ENOMEM;
+		*pte = IOMMU_L1_PDE(virt_to_phys(page));
+	}
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L0_INDEX(bus_addr)];
+
+	if (IOMMU_PTE_PRESENT(*pte))
+		return -EBUSY;
+
+	__pte = phys_addr | IOMMU_PTE_P;
+	if (prot & IOMMU_PROT_IR)
+		__pte |= IOMMU_PTE_IR;
+	if (prot & IOMMU_PROT_IW)
+		__pte |= IOMMU_PTE_IW;
+
+	*pte = __pte;
+
+	return 0;
+}
+
+static int iommu_for_unity_map(struct amd_iommu *iommu,
+			       struct unity_map_entry *entry)
+{
+	u16 bdf, i;
+
+	for (i = entry->devid_start; i <= entry->devid_end; ++i) {
+		bdf = amd_iommu_alias_table[i];
+		if (amd_iommu_rlookup_table[bdf] == iommu)
+			return 1;
+	}
+
+	return 0;
+}
+
+static int iommu_init_unity_mappings(struct amd_iommu *iommu)
+{
+	struct unity_map_entry *entry;
+	int ret;
+
+	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
+		if (!iommu_for_unity_map(iommu, entry))
+			continue;
+		ret = dma_ops_unity_map(iommu->default_dom, entry);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
+			     struct unity_map_entry *e)
+{
+	u64 addr;
+	int ret;
+
+	for (addr = e->address_start; addr < e->address_end;
+	     addr += PAGE_SIZE) {
+		ret = iommu_map(&dma_dom->domain, addr, addr, e->prot);
+		if (ret)
+			return ret;
+		/*
+		 * if unity mapping is in aperture range mark the page
+		 * as allocated in the aperture
+		 */
+		if (addr < dma_dom->aperture_size)
+			__set_bit(addr >> PAGE_SHIFT, dma_dom->bitmap);
+	}
+
+	return 0;
+}
+
+static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom,
+					  u16 devid)
+{
+	struct unity_map_entry *e;
+	int ret;
+
+	list_for_each_entry(e, &amd_iommu_unity_map, list) {
+		if (!(devid >= e->devid_start && devid <= e->devid_end))
+			continue;
+		ret = dma_ops_unity_map(dma_dom, e);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static unsigned long dma_mask_to_pages(unsigned long mask)
+{
+	return (mask >> PAGE_SHIFT) +
+		(PAGE_ALIGN(mask & ~PAGE_MASK) >> PAGE_SHIFT);
+}
+
+static unsigned long dma_ops_alloc_addresses(struct device *dev,
+					     struct dma_ops_domain *dom,
+					     unsigned int pages)
+{
+	unsigned long limit = dma_mask_to_pages(*dev->dma_mask);
+	unsigned long address;
+	unsigned long size = dom->aperture_size >> PAGE_SHIFT;
+	unsigned long boundary_size;
+
+	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+			PAGE_SIZE) >> PAGE_SHIFT;
+	limit = limit < size ? limit : size;
+
+	if (dom->next_bit >= limit)
+		dom->next_bit = 0;
+
+	address = iommu_area_alloc(dom->bitmap, limit, dom->next_bit, pages,
+			0 , boundary_size, 0);
+	if (address == -1)
+		address = iommu_area_alloc(dom->bitmap, limit, 0, pages,
+				0, boundary_size, 0);
+
+	if (likely(address != -1)) {
+		dom->next_bit = address + pages;
+		address <<= PAGE_SHIFT;
+	} else
+		address = bad_dma_address;
+
+	WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size);
+
+	return address;
+}
+
+static void dma_ops_free_addresses(struct dma_ops_domain *dom,
+				   unsigned long address,
+				   unsigned int pages)
+{
+	address >>= PAGE_SHIFT;
+	iommu_area_free(dom->bitmap, address, pages);
+}
+
+static u16 domain_id_alloc(void)
+{
+	unsigned long flags;
+	int id;
+
+	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID);
+	BUG_ON(id == 0);
+	if (id > 0 && id < MAX_DOMAIN_ID)
+		__set_bit(id, amd_iommu_pd_alloc_bitmap);
+	else
+		id = 0;
+	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+	return id;
+}
+
+static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
+				      unsigned long start_page,
+				      unsigned int pages)
+{
+	unsigned int last_page = dom->aperture_size >> PAGE_SHIFT;
+
+	if (start_page + pages > last_page)
+		pages = last_page - start_page;
+
+	set_bit_string(dom->bitmap, start_page, pages);
+}
+
+static void dma_ops_free_pagetable(struct dma_ops_domain *dma_dom)
+{
+	int i, j;
+	u64 *p1, *p2, *p3;
+
+	p1 = dma_dom->domain.pt_root;
+
+	if (!p1)
+		return;
+
+	for (i = 0; i < 512; ++i) {
+		if (!IOMMU_PTE_PRESENT(p1[i]))
+			continue;
+
+		p2 = IOMMU_PTE_PAGE(p1[i]);
+		for (j = 0; j < 512; ++i) {
+			if (!IOMMU_PTE_PRESENT(p2[j]))
+				continue;
+			p3 = IOMMU_PTE_PAGE(p2[j]);
+			free_page((unsigned long)p3);
+		}
+
+		free_page((unsigned long)p2);
+	}
+
+	free_page((unsigned long)p1);
+}
+
+static void dma_ops_domain_free(struct dma_ops_domain *dom)
+{
+	if (!dom)
+		return;
+
+	dma_ops_free_pagetable(dom);
+
+	kfree(dom->pte_pages);
+
+	kfree(dom->bitmap);
+
+	kfree(dom);
+}
+
+static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu,
+						   unsigned order)
+{
+	struct dma_ops_domain *dma_dom;
+	unsigned i, num_pte_pages;
+	u64 *l2_pde;
+	u64 address;
+
+	/*
+	 * Currently the DMA aperture must be between 32 MB and 1GB in size
+	 */
+	if ((order < 25) || (order > 30))
+		return NULL;
+
+	dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL);
+	if (!dma_dom)
+		return NULL;
+
+	spin_lock_init(&dma_dom->domain.lock);
+
+	dma_dom->domain.id = domain_id_alloc();
+	if (dma_dom->domain.id == 0)
+		goto free_dma_dom;
+	dma_dom->domain.mode = PAGE_MODE_3_LEVEL;
+	dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+	dma_dom->domain.priv = dma_dom;
+	if (!dma_dom->domain.pt_root)
+		goto free_dma_dom;
+	dma_dom->aperture_size = (1ULL << order);
+	dma_dom->bitmap = kzalloc(dma_dom->aperture_size / (PAGE_SIZE * 8),
+				  GFP_KERNEL);
+	if (!dma_dom->bitmap)
+		goto free_dma_dom;
+	/*
+	 * mark the first page as allocated so we never return 0 as
+	 * a valid dma-address. So we can use 0 as error value
+	 */
+	dma_dom->bitmap[0] = 1;
+	dma_dom->next_bit = 0;
+
+	if (iommu->exclusion_start &&
+	    iommu->exclusion_start < dma_dom->aperture_size) {
+		unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
+		int pages = to_pages(iommu->exclusion_start,
+				iommu->exclusion_length);
+		dma_ops_reserve_addresses(dma_dom, startpage, pages);
+	}
+
+	num_pte_pages = dma_dom->aperture_size / (PAGE_SIZE * 512);
+	dma_dom->pte_pages = kzalloc(num_pte_pages * sizeof(void *),
+			GFP_KERNEL);
+	if (!dma_dom->pte_pages)
+		goto free_dma_dom;
+
+	l2_pde = (u64 *)get_zeroed_page(GFP_KERNEL);
+	if (l2_pde == NULL)
+		goto free_dma_dom;
+
+	dma_dom->domain.pt_root[0] = IOMMU_L2_PDE(virt_to_phys(l2_pde));
+
+	for (i = 0; i < num_pte_pages; ++i) {
+		dma_dom->pte_pages[i] = (u64 *)get_zeroed_page(GFP_KERNEL);
+		if (!dma_dom->pte_pages[i])
+			goto free_dma_dom;
+		address = virt_to_phys(dma_dom->pte_pages[i]);
+		l2_pde[i] = IOMMU_L1_PDE(address);
+	}
+
+	return dma_dom;
+
+free_dma_dom:
+	dma_ops_domain_free(dma_dom);
+
+	return NULL;
+}
+
+static struct protection_domain *domain_for_device(u16 devid)
+{
+	struct protection_domain *dom;
+	unsigned long flags;
+
+	read_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	dom = amd_iommu_pd_table[devid];
+	read_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+	return dom;
+}
+
+static void set_device_domain(struct amd_iommu *iommu,
+			      struct protection_domain *domain,
+			      u16 devid)
+{
+	unsigned long flags;
+
+	u64 pte_root = virt_to_phys(domain->pt_root);
+
+	pte_root |= (domain->mode & 0x07) << 9;
+	pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | 2;
+
+	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	amd_iommu_dev_table[devid].data[0] = pte_root;
+	amd_iommu_dev_table[devid].data[1] = pte_root >> 32;
+	amd_iommu_dev_table[devid].data[2] = domain->id;
+
+	amd_iommu_pd_table[devid] = domain;
+	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+	iommu_queue_inv_dev_entry(iommu, devid);
+
+	iommu->need_sync = 1;
+}
+
+static int get_device_resources(struct device *dev,
+				struct amd_iommu **iommu,
+				struct protection_domain **domain,
+				u16 *bdf)
+{
+	struct dma_ops_domain *dma_dom;
+	struct pci_dev *pcidev;
+	u16 _bdf;
+
+	BUG_ON(!dev || dev->bus != &pci_bus_type || !dev->dma_mask);
+
+	pcidev = to_pci_dev(dev);
+	_bdf = (pcidev->bus->number << 8) | pcidev->devfn;
+
+	if (_bdf >= amd_iommu_last_bdf) {
+		*iommu = NULL;
+		*domain = NULL;
+		*bdf = 0xffff;
+		return 0;
+	}
+
+	*bdf = amd_iommu_alias_table[_bdf];
+
+	*iommu = amd_iommu_rlookup_table[*bdf];
+	if (*iommu == NULL)
+		return 0;
+	dma_dom = (*iommu)->default_dom;
+	*domain = domain_for_device(*bdf);
+	if (*domain == NULL) {
+		*domain = &dma_dom->domain;
+		set_device_domain(*iommu, *domain, *bdf);
+		printk(KERN_INFO "AMD IOMMU: Using protection domain %d for "
+				"device ", (*domain)->id);
+		print_devid(_bdf, 1);
+	}
+
+	return 1;
+}
+
+static dma_addr_t dma_ops_domain_map(struct amd_iommu *iommu,
+				     struct dma_ops_domain *dom,
+				     unsigned long address,
+				     phys_addr_t paddr,
+				     int direction)
+{
+	u64 *pte, __pte;
+
+	WARN_ON(address > dom->aperture_size);
+
+	paddr &= PAGE_MASK;
+
+	pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
+	pte += IOMMU_PTE_L0_INDEX(address);
+
+	__pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC;
+
+	if (direction == DMA_TO_DEVICE)
+		__pte |= IOMMU_PTE_IR;
+	else if (direction == DMA_FROM_DEVICE)
+		__pte |= IOMMU_PTE_IW;
+	else if (direction == DMA_BIDIRECTIONAL)
+		__pte |= IOMMU_PTE_IR | IOMMU_PTE_IW;
+
+	WARN_ON(*pte);
+
+	*pte = __pte;
+
+	return (dma_addr_t)address;
+}
+
+static void dma_ops_domain_unmap(struct amd_iommu *iommu,
+				 struct dma_ops_domain *dom,
+				 unsigned long address)
+{
+	u64 *pte;
+
+	if (address >= dom->aperture_size)
+		return;
+
+	WARN_ON(address & 0xfffULL || address > dom->aperture_size);
+
+	pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
+	pte += IOMMU_PTE_L0_INDEX(address);
+
+	WARN_ON(!*pte);
+
+	*pte = 0ULL;
+}
+
+static dma_addr_t __map_single(struct device *dev,
+			       struct amd_iommu *iommu,
+			       struct dma_ops_domain *dma_dom,
+			       phys_addr_t paddr,
+			       size_t size,
+			       int dir)
+{
+	dma_addr_t offset = paddr & ~PAGE_MASK;
+	dma_addr_t address, start;
+	unsigned int pages;
+	int i;
+
+	pages = to_pages(paddr, size);
+	paddr &= PAGE_MASK;
+
+	address = dma_ops_alloc_addresses(dev, dma_dom, pages);
+	if (unlikely(address == bad_dma_address))
+		goto out;
+
+	start = address;
+	for (i = 0; i < pages; ++i) {
+		dma_ops_domain_map(iommu, dma_dom, start, paddr, dir);
+		paddr += PAGE_SIZE;
+		start += PAGE_SIZE;
+	}
+	address += offset;
+
+out:
+	return address;
+}
+
+static void __unmap_single(struct amd_iommu *iommu,
+			   struct dma_ops_domain *dma_dom,
+			   dma_addr_t dma_addr,
+			   size_t size,
+			   int dir)
+{
+	dma_addr_t i, start;
+	unsigned int pages;
+
+	if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size))
+		return;
+
+	pages = to_pages(dma_addr, size);
+	dma_addr &= PAGE_MASK;
+	start = dma_addr;
+
+	for (i = 0; i < pages; ++i) {
+		dma_ops_domain_unmap(iommu, dma_dom, start);
+		start += PAGE_SIZE;
+	}
+
+	dma_ops_free_addresses(dma_dom, dma_addr, pages);
+}
+
+static dma_addr_t map_single(struct device *dev, phys_addr_t paddr,
+			     size_t size, int dir)
+{
+	unsigned long flags;
+	struct amd_iommu *iommu;
+	struct protection_domain *domain;
+	u16 devid;
+	dma_addr_t addr;
+
+	get_device_resources(dev, &iommu, &domain, &devid);
+
+	if (iommu == NULL || domain == NULL)
+		return (dma_addr_t)paddr;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	addr = __map_single(dev, iommu, domain->priv, paddr, size, dir);
+	if (addr == bad_dma_address)
+		goto out;
+
+	if (iommu_has_npcache(iommu))
+		iommu_flush_pages(iommu, domain->id, addr, size);
+
+	if (iommu->need_sync)
+		iommu_completion_wait(iommu);
+
+out:
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return addr;
+}
+
+static void unmap_single(struct device *dev, dma_addr_t dma_addr,
+			 size_t size, int dir)
+{
+	unsigned long flags;
+	struct amd_iommu *iommu;
+	struct protection_domain *domain;
+	u16 devid;
+
+	if (!get_device_resources(dev, &iommu, &domain, &devid))
+		return;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	__unmap_single(iommu, domain->priv, dma_addr, size, dir);
+
+	iommu_flush_pages(iommu, domain->id, dma_addr, size);
+
+	if (iommu->need_sync)
+		iommu_completion_wait(iommu);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static int map_sg_no_iommu(struct device *dev, struct scatterlist *sglist,
+			   int nelems, int dir)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sglist, s, nelems, i) {
+		s->dma_address = (dma_addr_t)sg_phys(s);
+		s->dma_length  = s->length;
+	}
+
+	return nelems;
+}
+
+static int map_sg(struct device *dev, struct scatterlist *sglist,
+		  int nelems, int dir)
+{
+	unsigned long flags;
+	struct amd_iommu *iommu;
+	struct protection_domain *domain;
+	u16 devid;
+	int i;
+	struct scatterlist *s;
+	phys_addr_t paddr;
+	int mapped_elems = 0;
+
+	get_device_resources(dev, &iommu, &domain, &devid);
+
+	if (!iommu || !domain)
+		return map_sg_no_iommu(dev, sglist, nelems, dir);
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	for_each_sg(sglist, s, nelems, i) {
+		paddr = sg_phys(s);
+
+		s->dma_address = __map_single(dev, iommu, domain->priv,
+					      paddr, s->length, dir);
+
+		if (s->dma_address) {
+			s->dma_length = s->length;
+			mapped_elems++;
+		} else
+			goto unmap;
+		if (iommu_has_npcache(iommu))
+			iommu_flush_pages(iommu, domain->id, s->dma_address,
+					  s->dma_length);
+	}
+
+	if (iommu->need_sync)
+		iommu_completion_wait(iommu);
+
+out:
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return mapped_elems;
+unmap:
+	for_each_sg(sglist, s, mapped_elems, i) {
+		if (s->dma_address)
+			__unmap_single(iommu, domain->priv, s->dma_address,
+				       s->dma_length, dir);
+		s->dma_address = s->dma_length = 0;
+	}
+
+	mapped_elems = 0;
+
+	goto out;
+}
+
+static void unmap_sg(struct device *dev, struct scatterlist *sglist,
+		     int nelems, int dir)
+{
+	unsigned long flags;
+	struct amd_iommu *iommu;
+	struct protection_domain *domain;
+	struct scatterlist *s;
+	u16 devid;
+	int i;
+
+	if (!get_device_resources(dev, &iommu, &domain, &devid))
+		return;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	for_each_sg(sglist, s, nelems, i) {
+		__unmap_single(iommu, domain->priv, s->dma_address,
+			       s->dma_length, dir);
+		iommu_flush_pages(iommu, domain->id, s->dma_address,
+				  s->dma_length);
+		s->dma_address = s->dma_length = 0;
+	}
+
+	if (iommu->need_sync)
+		iommu_completion_wait(iommu);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void *alloc_coherent(struct device *dev, size_t size,
+			    dma_addr_t *dma_addr, gfp_t flag)
+{
+	unsigned long flags;
+	void *virt_addr;
+	struct amd_iommu *iommu;
+	struct protection_domain *domain;
+	u16 devid;
+	phys_addr_t paddr;
+
+	virt_addr = (void *)__get_free_pages(flag, get_order(size));
+	if (!virt_addr)
+		return 0;
+
+	memset(virt_addr, 0, size);
+	paddr = virt_to_phys(virt_addr);
+
+	get_device_resources(dev, &iommu, &domain, &devid);
+
+	if (!iommu || !domain) {
+		*dma_addr = (dma_addr_t)paddr;
+		return virt_addr;
+	}
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	*dma_addr = __map_single(dev, iommu, domain->priv, paddr,
+				 size, DMA_BIDIRECTIONAL);
+
+	if (*dma_addr == bad_dma_address) {
+		free_pages((unsigned long)virt_addr, get_order(size));
+		virt_addr = NULL;
+		goto out;
+	}
+
+	if (iommu_has_npcache(iommu))
+		iommu_flush_pages(iommu, domain->id, *dma_addr, size);
+
+	if (iommu->need_sync)
+		iommu_completion_wait(iommu);
+
+out:
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return virt_addr;
+}
+
+static void free_coherent(struct device *dev, size_t size,
+			  void *virt_addr, dma_addr_t dma_addr)
+{
+	unsigned long flags;
+	struct amd_iommu *iommu;
+	struct protection_domain *domain;
+	u16 devid;
+
+	get_device_resources(dev, &iommu, &domain, &devid);
+
+	if (!iommu || !domain)
+		goto free_mem;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	__unmap_single(iommu, domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
+	iommu_flush_pages(iommu, domain->id, dma_addr, size);
+
+	if (iommu->need_sync)
+		iommu_completion_wait(iommu);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+free_mem:
+	free_pages((unsigned long)virt_addr, get_order(size));
+}
+
+/*
+ * If the driver core informs the DMA layer if a driver grabs a device
+ * we don't need to preallocate the protection domains anymore.
+ * For now we have to.
+ */
+void prealloc_protection_domains(void)
+{
+	struct pci_dev *dev = NULL;
+	struct dma_ops_domain *dma_dom;
+	struct amd_iommu *iommu;
+	int order = amd_iommu_aperture_order;
+	u16 devid;
+
+	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+		devid = (dev->bus->number << 8) | dev->devfn;
+		if (devid >= amd_iommu_last_bdf)
+			continue;
+		devid = amd_iommu_alias_table[devid];
+		if (domain_for_device(devid))
+			continue;
+		iommu = amd_iommu_rlookup_table[devid];
+		if (!iommu)
+			continue;
+		dma_dom = dma_ops_domain_alloc(iommu, order);
+		if (!dma_dom)
+			continue;
+		init_unity_mappings_for_device(dma_dom, devid);
+		set_device_domain(iommu, &dma_dom->domain, devid);
+		printk(KERN_INFO "AMD IOMMU: Allocated domain %d for device ",
+		       dma_dom->domain.id);
+		print_devid(devid, 1);
+	}
+}
+
+static struct dma_mapping_ops amd_iommu_dma_ops = {
+	.alloc_coherent = alloc_coherent,
+	.free_coherent = free_coherent,
+	.map_single = map_single,
+	.unmap_single = unmap_single,
+	.map_sg = map_sg,
+	.unmap_sg = unmap_sg,
+};
+
+int __init amd_iommu_init_dma_ops(void)
+{
+	struct amd_iommu *iommu;
+	int order = amd_iommu_aperture_order;
+	int ret;
+
+	list_for_each_entry(iommu, &amd_iommu_list, list) {
+		iommu->default_dom = dma_ops_domain_alloc(iommu, order);
+		if (iommu->default_dom == NULL)
+			return -ENOMEM;
+		ret = iommu_init_unity_mappings(iommu);
+		if (ret)
+			goto free_domains;
+	}
+
+	if (amd_iommu_isolate)
+		prealloc_protection_domains();
+
+	iommu_detected = 1;
+	force_iommu = 1;
+	bad_dma_address = 0;
+#ifdef CONFIG_GART_IOMMU
+	gart_iommu_aperture_disabled = 1;
+	gart_iommu_aperture = 0;
+#endif
+
+	dma_ops = &amd_iommu_dma_ops;
+
+	return 0;
+
+free_domains:
+
+	list_for_each_entry(iommu, &amd_iommu_list, list) {
+		if (iommu->default_dom)
+			dma_ops_domain_free(iommu->default_dom);
+	}
+
+	return ret;
+}

arch/x86/kernel/amd_iommu_init.c

@@ -0,0 +1,875 @@
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *         Leo Duran <leo.duran@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/gfp.h>
+#include <linux/list.h>
+#include <linux/sysdev.h>
+#include <asm/pci-direct.h>
+#include <asm/amd_iommu_types.h>
+#include <asm/amd_iommu.h>
+#include <asm/gart.h>
+
+/*
+ * definitions for the ACPI scanning code
+ */
+#define UPDATE_LAST_BDF(x) do {\
+	if ((x) > amd_iommu_last_bdf) \
+		amd_iommu_last_bdf = (x); \
+	} while (0);
+
+#define DEVID(bus, devfn) (((bus) << 8) | (devfn))
+#define PCI_BUS(x) (((x) >> 8) & 0xff)
+#define IVRS_HEADER_LENGTH 48
+#define TBL_SIZE(x) (1 << (PAGE_SHIFT + get_order(amd_iommu_last_bdf * (x))))
+
+#define ACPI_IVHD_TYPE                  0x10
+#define ACPI_IVMD_TYPE_ALL              0x20
+#define ACPI_IVMD_TYPE                  0x21
+#define ACPI_IVMD_TYPE_RANGE            0x22
+
+#define IVHD_DEV_ALL                    0x01
+#define IVHD_DEV_SELECT                 0x02
+#define IVHD_DEV_SELECT_RANGE_START     0x03
+#define IVHD_DEV_RANGE_END              0x04
+#define IVHD_DEV_ALIAS                  0x42
+#define IVHD_DEV_ALIAS_RANGE            0x43
+#define IVHD_DEV_EXT_SELECT             0x46
+#define IVHD_DEV_EXT_SELECT_RANGE       0x47
+
+#define IVHD_FLAG_HT_TUN_EN             0x00
+#define IVHD_FLAG_PASSPW_EN             0x01
+#define IVHD_FLAG_RESPASSPW_EN          0x02
+#define IVHD_FLAG_ISOC_EN               0x03
+
+#define IVMD_FLAG_EXCL_RANGE            0x08
+#define IVMD_FLAG_UNITY_MAP             0x01
+
+#define ACPI_DEVFLAG_INITPASS           0x01
+#define ACPI_DEVFLAG_EXTINT             0x02
+#define ACPI_DEVFLAG_NMI                0x04
+#define ACPI_DEVFLAG_SYSMGT1            0x10
+#define ACPI_DEVFLAG_SYSMGT2            0x20
+#define ACPI_DEVFLAG_LINT0              0x40
+#define ACPI_DEVFLAG_LINT1              0x80
+#define ACPI_DEVFLAG_ATSDIS             0x10000000
+
+struct ivhd_header {
+	u8 type;
+	u8 flags;
+	u16 length;
+	u16 devid;
+	u16 cap_ptr;
+	u64 mmio_phys;
+	u16 pci_seg;
+	u16 info;
+	u32 reserved;
+} __attribute__((packed));
+
+struct ivhd_entry {
+	u8 type;
+	u16 devid;
+	u8 flags;
+	u32 ext;
+} __attribute__((packed));
+
+struct ivmd_header {
+	u8 type;
+	u8 flags;
+	u16 length;
+	u16 devid;
+	u16 aux;
+	u64 resv;
+	u64 range_start;
+	u64 range_length;
+} __attribute__((packed));
+
+static int __initdata amd_iommu_detected;
+
+u16 amd_iommu_last_bdf;
+struct list_head amd_iommu_unity_map;
+unsigned amd_iommu_aperture_order = 26;
+int amd_iommu_isolate;
+
+struct list_head amd_iommu_list;
+struct dev_table_entry *amd_iommu_dev_table;
+u16 *amd_iommu_alias_table;
+struct amd_iommu **amd_iommu_rlookup_table;
+struct protection_domain **amd_iommu_pd_table;
+unsigned long *amd_iommu_pd_alloc_bitmap;
+
+static u32 dev_table_size;
+static u32 alias_table_size;
+static u32 rlookup_table_size;
+
+static void __init iommu_set_exclusion_range(struct amd_iommu *iommu)
+{
+	u64 start = iommu->exclusion_start & PAGE_MASK;
+	u64 limit = (start + iommu->exclusion_length) & PAGE_MASK;
+	u64 entry;
+
+	if (!iommu->exclusion_start)
+		return;
+
+	entry = start | MMIO_EXCL_ENABLE_MASK;
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
+			&entry, sizeof(entry));
+
+	entry = limit;
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET,
+			&entry, sizeof(entry));
+}
+
+static void __init iommu_set_device_table(struct amd_iommu *iommu)
+{
+	u32 entry;
+
+	BUG_ON(iommu->mmio_base == NULL);
+
+	entry = virt_to_phys(amd_iommu_dev_table);
+	entry |= (dev_table_size >> 12) - 1;
+	memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET,
+			&entry, sizeof(entry));
+}
+
+static void __init iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
+{
+	u32 ctrl;
+
+	ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET);
+	ctrl |= (1 << bit);
+	writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
+}
+
+static void __init iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
+{
+	u32 ctrl;
+
+	ctrl = (u64)readl(iommu->mmio_base + MMIO_CONTROL_OFFSET);
+	ctrl &= ~(1 << bit);
+	writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
+}
+
+void __init iommu_enable(struct amd_iommu *iommu)
+{
+	printk(KERN_INFO "AMD IOMMU: Enabling IOMMU at ");
+	print_devid(iommu->devid, 0);
+	printk(" cap 0x%hx\n", iommu->cap_ptr);
+
+	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
+}
+
+static u8 * __init iommu_map_mmio_space(u64 address)
+{
+	u8 *ret;
+
+	if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu"))
+		return NULL;
+
+	ret = ioremap_nocache(address, MMIO_REGION_LENGTH);
+	if (ret != NULL)
+		return ret;
+
+	release_mem_region(address, MMIO_REGION_LENGTH);
+
+	return NULL;
+}
+
+static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu)
+{
+	if (iommu->mmio_base)
+		iounmap(iommu->mmio_base);
+	release_mem_region(iommu->mmio_phys, MMIO_REGION_LENGTH);
+}
+
+static int __init find_last_devid_on_pci(int bus, int dev, int fn, int cap_ptr)
+{
+	u32 cap;
+
+	cap = read_pci_config(bus, dev, fn, cap_ptr+MMIO_RANGE_OFFSET);
+	UPDATE_LAST_BDF(DEVID(MMIO_GET_BUS(cap), MMIO_GET_LD(cap)));
+
+	return 0;
+}
+
+static int __init find_last_devid_from_ivhd(struct ivhd_header *h)
+{
+	u8 *p = (void *)h, *end = (void *)h;
+	struct ivhd_entry *dev;
+
+	p += sizeof(*h);
+	end += h->length;
+
+	find_last_devid_on_pci(PCI_BUS(h->devid),
+			PCI_SLOT(h->devid),
+			PCI_FUNC(h->devid),
+			h->cap_ptr);
+
+	while (p < end) {
+		dev = (struct ivhd_entry *)p;
+		switch (dev->type) {
+		case IVHD_DEV_SELECT:
+		case IVHD_DEV_RANGE_END:
+		case IVHD_DEV_ALIAS:
+		case IVHD_DEV_EXT_SELECT:
+			UPDATE_LAST_BDF(dev->devid);
+			break;
+		default:
+			break;
+		}
+		p += 0x04 << (*p >> 6);
+	}
+
+	WARN_ON(p != end);
+
+	return 0;
+}
+
+static int __init find_last_devid_acpi(struct acpi_table_header *table)
+{
+	int i;
+	u8 checksum = 0, *p = (u8 *)table, *end = (u8 *)table;
+	struct ivhd_header *h;
+
+	/*
+	 * Validate checksum here so we don't need to do it when
+	 * we actually parse the table
+	 */
+	for (i = 0; i < table->length; ++i)
+		checksum += p[i];
+	if (checksum != 0)
+		/* ACPI table corrupt */
+		return -ENODEV;
+
+	p += IVRS_HEADER_LENGTH;
+
+	end += table->length;
+	while (p < end) {
+		h = (struct ivhd_header *)p;
+		switch (h->type) {
+		case ACPI_IVHD_TYPE:
+			find_last_devid_from_ivhd(h);
+			break;
+		default:
+			break;
+		}
+		p += h->length;
+	}
+	WARN_ON(p != end);
+
+	return 0;
+}
+
+static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
+{
+	u8 *cmd_buf = (u8 *)__get_free_pages(GFP_KERNEL,
+			get_order(CMD_BUFFER_SIZE));
+	u64 entry = 0;
+
+	if (cmd_buf == NULL)
+		return NULL;
+
+	iommu->cmd_buf_size = CMD_BUFFER_SIZE;
+
+	memset(cmd_buf, 0, CMD_BUFFER_SIZE);
+
+	entry = (u64)virt_to_phys(cmd_buf);
+	entry |= MMIO_CMD_SIZE_512;
+	memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
+			&entry, sizeof(entry));
+
+	iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
+
+	return cmd_buf;
+}
+
+static void __init free_command_buffer(struct amd_iommu *iommu)
+{
+	if (iommu->cmd_buf)
+		free_pages((unsigned long)iommu->cmd_buf,
+				get_order(CMD_BUFFER_SIZE));
+}
+
+static void set_dev_entry_bit(u16 devid, u8 bit)
+{
+	int i = (bit >> 5) & 0x07;
+	int _bit = bit & 0x1f;
+
+	amd_iommu_dev_table[devid].data[i] |= (1 << _bit);
+}
+
+static void __init set_dev_entry_from_acpi(u16 devid, u32 flags, u32 ext_flags)
+{
+	if (flags & ACPI_DEVFLAG_INITPASS)
+		set_dev_entry_bit(devid, DEV_ENTRY_INIT_PASS);
+	if (flags & ACPI_DEVFLAG_EXTINT)
+		set_dev_entry_bit(devid, DEV_ENTRY_EINT_PASS);
+	if (flags & ACPI_DEVFLAG_NMI)
+		set_dev_entry_bit(devid, DEV_ENTRY_NMI_PASS);
+	if (flags & ACPI_DEVFLAG_SYSMGT1)
+		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1);
+	if (flags & ACPI_DEVFLAG_SYSMGT2)
+		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2);
+	if (flags & ACPI_DEVFLAG_LINT0)
+		set_dev_entry_bit(devid, DEV_ENTRY_LINT0_PASS);
+	if (flags & ACPI_DEVFLAG_LINT1)
+		set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS);
+}
+
+static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid)
+{
+	amd_iommu_rlookup_table[devid] = iommu;
+}
+
+static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
+{
+	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+	if (!(m->flags & IVMD_FLAG_EXCL_RANGE))
+		return;
+
+	if (iommu) {
+		set_dev_entry_bit(m->devid, DEV_ENTRY_EX);
+		iommu->exclusion_start = m->range_start;
+		iommu->exclusion_length = m->range_length;
+	}
+}
+
+static void __init init_iommu_from_pci(struct amd_iommu *iommu)
+{
+	int bus = PCI_BUS(iommu->devid);
+	int dev = PCI_SLOT(iommu->devid);
+	int fn  = PCI_FUNC(iommu->devid);
+	int cap_ptr = iommu->cap_ptr;
+	u32 range;
+
+	iommu->cap = read_pci_config(bus, dev, fn, cap_ptr+MMIO_CAP_HDR_OFFSET);
+
+	range = read_pci_config(bus, dev, fn, cap_ptr+MMIO_RANGE_OFFSET);
+	iommu->first_device = DEVID(MMIO_GET_BUS(range), MMIO_GET_FD(range));
+	iommu->last_device = DEVID(MMIO_GET_BUS(range), MMIO_GET_LD(range));
+}
+
+static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
+					struct ivhd_header *h)
+{
+	u8 *p = (u8 *)h;
+	u8 *end = p, flags = 0;
+	u16 dev_i, devid = 0, devid_start = 0, devid_to = 0;
+	u32 ext_flags = 0;
+	bool alias = 0;
+	struct ivhd_entry *e;
+
+	/*
+	 * First set the recommended feature enable bits from ACPI
+	 * into the IOMMU control registers
+	 */
+	h->flags & IVHD_FLAG_HT_TUN_EN ?
+		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
+		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
+
+	h->flags & IVHD_FLAG_PASSPW_EN ?
+		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
+		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
+
+	h->flags & IVHD_FLAG_RESPASSPW_EN ?
+		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
+		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
+
+	h->flags & IVHD_FLAG_ISOC_EN ?
+		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
+		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
+
+	/*
+	 * make IOMMU memory accesses cache coherent
+	 */
+	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
+
+	/*
+	 * Done. Now parse the device entries
+	 */
+	p += sizeof(struct ivhd_header);
+	end += h->length;
+
+	while (p < end) {
+		e = (struct ivhd_entry *)p;
+		switch (e->type) {
+		case IVHD_DEV_ALL:
+			for (dev_i = iommu->first_device;
+					dev_i <= iommu->last_device; ++dev_i)
+				set_dev_entry_from_acpi(dev_i, e->flags, 0);
+			break;
+		case IVHD_DEV_SELECT:
+			devid = e->devid;
+			set_dev_entry_from_acpi(devid, e->flags, 0);
+			break;
+		case IVHD_DEV_SELECT_RANGE_START:
+			devid_start = e->devid;
+			flags = e->flags;
+			ext_flags = 0;
+			alias = 0;
+			break;
+		case IVHD_DEV_ALIAS:
+			devid = e->devid;
+			devid_to = e->ext >> 8;
+			set_dev_entry_from_acpi(devid, e->flags, 0);
+			amd_iommu_alias_table[devid] = devid_to;
+			break;
+		case IVHD_DEV_ALIAS_RANGE:
+			devid_start = e->devid;
+			flags = e->flags;
+			devid_to = e->ext >> 8;
+			ext_flags = 0;
+			alias = 1;
+			break;
+		case IVHD_DEV_EXT_SELECT:
+			devid = e->devid;
+			set_dev_entry_from_acpi(devid, e->flags, e->ext);
+			break;
+		case IVHD_DEV_EXT_SELECT_RANGE:
+			devid_start = e->devid;
+			flags = e->flags;
+			ext_flags = e->ext;
+			alias = 0;
+			break;
+		case IVHD_DEV_RANGE_END:
+			devid = e->devid;
+			for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
+				if (alias)
+					amd_iommu_alias_table[dev_i] = devid_to;
+				set_dev_entry_from_acpi(
+						amd_iommu_alias_table[dev_i],
+						flags, ext_flags);
+			}
+			break;
+		default:
+			break;
+		}
+
+		p += 0x04 << (e->type >> 6);
+	}
+}
+
+static int __init init_iommu_devices(struct amd_iommu *iommu)
+{
+	u16 i;
+
+	for (i = iommu->first_device; i <= iommu->last_device; ++i)
+		set_iommu_for_device(iommu, i);
+
+	return 0;
+}
+
+static void __init free_iommu_one(struct amd_iommu *iommu)
+{
+	free_command_buffer(iommu);
+	iommu_unmap_mmio_space(iommu);
+}
+
+static void __init free_iommu_all(void)
+{
+	struct amd_iommu *iommu, *next;
+
+	list_for_each_entry_safe(iommu, next, &amd_iommu_list, list) {
+		list_del(&iommu->list);
+		free_iommu_one(iommu);
+		kfree(iommu);
+	}
+}
+
+static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
+{
+	spin_lock_init(&iommu->lock);
+	list_add_tail(&iommu->list, &amd_iommu_list);
+
+	/*
+	 * Copy data from ACPI table entry to the iommu struct
+	 */
+	iommu->devid = h->devid;
+	iommu->cap_ptr = h->cap_ptr;
+	iommu->mmio_phys = h->mmio_phys;
+	iommu->mmio_base = iommu_map_mmio_space(h->mmio_phys);
+	if (!iommu->mmio_base)
+		return -ENOMEM;
+
+	iommu_set_device_table(iommu);
+	iommu->cmd_buf = alloc_command_buffer(iommu);
+	if (!iommu->cmd_buf)
+		return -ENOMEM;
+
+	init_iommu_from_pci(iommu);
+	init_iommu_from_acpi(iommu, h);
+	init_iommu_devices(iommu);
+
+	return 0;
+}
+
+static int __init init_iommu_all(struct acpi_table_header *table)
+{
+	u8 *p = (u8 *)table, *end = (u8 *)table;
+	struct ivhd_header *h;
+	struct amd_iommu *iommu;
+	int ret;
+
+	INIT_LIST_HEAD(&amd_iommu_list);
+
+	end += table->length;
+	p += IVRS_HEADER_LENGTH;
+
+	while (p < end) {
+		h = (struct ivhd_header *)p;
+		switch (*p) {
+		case ACPI_IVHD_TYPE:
+			iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
+			if (iommu == NULL)
+				return -ENOMEM;
+			ret = init_iommu_one(iommu, h);
+			if (ret)
+				return ret;
+			break;
+		default:
+			break;
+		}
+		p += h->length;
+
+	}
+	WARN_ON(p != end);
+
+	return 0;
+}
+
+static void __init free_unity_maps(void)
+{
+	struct unity_map_entry *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &amd_iommu_unity_map, list) {
+		list_del(&entry->list);
+		kfree(entry);
+	}
+}
+
+static int __init init_exclusion_range(struct ivmd_header *m)
+{
+	int i;
+
+	switch (m->type) {
+	case ACPI_IVMD_TYPE:
+		set_device_exclusion_range(m->devid, m);
+		break;
+	case ACPI_IVMD_TYPE_ALL:
+		for (i = 0; i < amd_iommu_last_bdf; ++i)
+			set_device_exclusion_range(i, m);
+		break;
+	case ACPI_IVMD_TYPE_RANGE:
+		for (i = m->devid; i <= m->aux; ++i)
+			set_device_exclusion_range(i, m);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int __init init_unity_map_range(struct ivmd_header *m)
+{
+	struct unity_map_entry *e = 0;
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (e == NULL)
+		return -ENOMEM;
+
+	switch (m->type) {
+	default:
+	case ACPI_IVMD_TYPE:
+		e->devid_start = e->devid_end = m->devid;
+		break;
+	case ACPI_IVMD_TYPE_ALL:
+		e->devid_start = 0;
+		e->devid_end = amd_iommu_last_bdf;
+		break;
+	case ACPI_IVMD_TYPE_RANGE:
+		e->devid_start = m->devid;
+		e->devid_end = m->aux;
+		break;
+	}
+	e->address_start = PAGE_ALIGN(m->range_start);
+	e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
+	e->prot = m->flags >> 1;
+
+	list_add_tail(&e->list, &amd_iommu_unity_map);
+
+	return 0;
+}
+
+static int __init init_memory_definitions(struct acpi_table_header *table)
+{
+	u8 *p = (u8 *)table, *end = (u8 *)table;
+	struct ivmd_header *m;
+
+	INIT_LIST_HEAD(&amd_iommu_unity_map);
+
+	end += table->length;
+	p += IVRS_HEADER_LENGTH;
+
+	while (p < end) {
+		m = (struct ivmd_header *)p;
+		if (m->flags & IVMD_FLAG_EXCL_RANGE)
+			init_exclusion_range(m);
+		else if (m->flags & IVMD_FLAG_UNITY_MAP)
+			init_unity_map_range(m);
+
+		p += m->length;
+	}
+
+	return 0;
+}
+
+static void __init enable_iommus(void)
+{
+	struct amd_iommu *iommu;
+
+	list_for_each_entry(iommu, &amd_iommu_list, list) {
+		iommu_set_exclusion_range(iommu);
+		iommu_enable(iommu);
+	}
+}
+
+/*
+ * Suspend/Resume support
+ * disable suspend until real resume implemented
+ */
+
+static int amd_iommu_resume(struct sys_device *dev)
+{
+	return 0;
+}
+
+static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
+{
+	return -EINVAL;
+}
+
+static struct sysdev_class amd_iommu_sysdev_class = {
+	.name = "amd_iommu",
+	.suspend = amd_iommu_suspend,
+	.resume = amd_iommu_resume,
+};
+
+static struct sys_device device_amd_iommu = {
+	.id = 0,
+	.cls = &amd_iommu_sysdev_class,
+};
+
+int __init amd_iommu_init(void)
+{
+	int i, ret = 0;
+
+
+	if (no_iommu) {
+		printk(KERN_INFO "AMD IOMMU disabled by kernel command line\n");
+		return 0;
+	}
+
+	if (!amd_iommu_detected)
+		return -ENODEV;
+
+	/*
+	 * First parse ACPI tables to find the largest Bus/Dev/Func
+	 * we need to handle. Upon this information the shared data
+	 * structures for the IOMMUs in the system will be allocated
+	 */
+	if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0)
+		return -ENODEV;
+
+	dev_table_size     = TBL_SIZE(DEV_TABLE_ENTRY_SIZE);
+	alias_table_size   = TBL_SIZE(ALIAS_TABLE_ENTRY_SIZE);
+	rlookup_table_size = TBL_SIZE(RLOOKUP_TABLE_ENTRY_SIZE);
+
+	ret = -ENOMEM;
+
+	/* Device table - directly used by all IOMMUs */
+	amd_iommu_dev_table = (void *)__get_free_pages(GFP_KERNEL,
+				      get_order(dev_table_size));
+	if (amd_iommu_dev_table == NULL)
+		goto out;
+
+	/*
+	 * Alias table - map PCI Bus/Dev/Func to Bus/Dev/Func the
+	 * IOMMU see for that device
+	 */
+	amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL,
+			get_order(alias_table_size));
+	if (amd_iommu_alias_table == NULL)
+		goto free;
+
+	/* IOMMU rlookup table - find the IOMMU for a specific device */
+	amd_iommu_rlookup_table = (void *)__get_free_pages(GFP_KERNEL,
+			get_order(rlookup_table_size));
+	if (amd_iommu_rlookup_table == NULL)
+		goto free;
+
+	/*
+	 * Protection Domain table - maps devices to protection domains
+	 * This table has the same size as the rlookup_table
+	 */
+	amd_iommu_pd_table = (void *)__get_free_pages(GFP_KERNEL,
+				     get_order(rlookup_table_size));
+	if (amd_iommu_pd_table == NULL)
+		goto free;
+
+	amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages(GFP_KERNEL,
+					    get_order(MAX_DOMAIN_ID/8));
+	if (amd_iommu_pd_alloc_bitmap == NULL)
+		goto free;
+
+	/*
+	 * memory is allocated now; initialize the device table with all zeroes
+	 * and let all alias entries point to itself
+	 */
+	memset(amd_iommu_dev_table, 0, dev_table_size);
+	for (i = 0; i < amd_iommu_last_bdf; ++i)
+		amd_iommu_alias_table[i] = i;
+
+	memset(amd_iommu_pd_table, 0, rlookup_table_size);
+	memset(amd_iommu_pd_alloc_bitmap, 0, MAX_DOMAIN_ID / 8);
+
+	/*
+	 * never allocate domain 0 because its used as the non-allocated and
+	 * error value placeholder
+	 */
+	amd_iommu_pd_alloc_bitmap[0] = 1;
+
+	/*
+	 * now the data structures are allocated and basically initialized
+	 * start the real acpi table scan
+	 */
+	ret = -ENODEV;
+	if (acpi_table_parse("IVRS", init_iommu_all) != 0)
+		goto free;
+
+	if (acpi_table_parse("IVRS", init_memory_definitions) != 0)
+		goto free;
+
+	ret = amd_iommu_init_dma_ops();
+	if (ret)
+		goto free;
+
+	ret = sysdev_class_register(&amd_iommu_sysdev_class);
+	if (ret)
+		goto free;
+
+	ret = sysdev_register(&device_amd_iommu);
+	if (ret)
+		goto free;
+
+	enable_iommus();
+
+	printk(KERN_INFO "AMD IOMMU: aperture size is %d MB\n",
+			(1 << (amd_iommu_aperture_order-20)));
+
+	printk(KERN_INFO "AMD IOMMU: device isolation ");
+	if (amd_iommu_isolate)
+		printk("enabled\n");
+	else
+		printk("disabled\n");
+
+out:
+	return ret;
+
+free:
+	if (amd_iommu_pd_alloc_bitmap)
+		free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, 1);
+
+	if (amd_iommu_pd_table)
+		free_pages((unsigned long)amd_iommu_pd_table,
+				get_order(rlookup_table_size));
+
+	if (amd_iommu_rlookup_table)
+		free_pages((unsigned long)amd_iommu_rlookup_table,
+				get_order(rlookup_table_size));
+
+	if (amd_iommu_alias_table)
+		free_pages((unsigned long)amd_iommu_alias_table,
+				get_order(alias_table_size));
+
+	if (amd_iommu_dev_table)
+		free_pages((unsigned long)amd_iommu_dev_table,
+				get_order(dev_table_size));
+
+	free_iommu_all();
+
+	free_unity_maps();
+
+	goto out;
+}
+
+static int __init early_amd_iommu_detect(struct acpi_table_header *table)
+{
+	return 0;
+}
+
+void __init amd_iommu_detect(void)
+{
+	if (swiotlb || no_iommu || iommu_detected)
+		return;
+
+	if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) {
+		iommu_detected = 1;
+		amd_iommu_detected = 1;
+#ifdef CONFIG_GART_IOMMU
+		gart_iommu_aperture_disabled = 1;
+		gart_iommu_aperture = 0;
+#endif
+	}
+}
+
+static int __init parse_amd_iommu_options(char *str)
+{
+	for (; *str; ++str) {
+		if (strcmp(str, "isolate") == 0)
+			amd_iommu_isolate = 1;
+	}
+
+	return 1;
+}
+
+static int __init parse_amd_iommu_size_options(char *str)
+{
+	for (; *str; ++str) {
+		if (strcmp(str, "32M") == 0)
+			amd_iommu_aperture_order = 25;
+		if (strcmp(str, "64M") == 0)
+			amd_iommu_aperture_order = 26;
+		if (strcmp(str, "128M") == 0)
+			amd_iommu_aperture_order = 27;
+		if (strcmp(str, "256M") == 0)
+			amd_iommu_aperture_order = 28;
+		if (strcmp(str, "512M") == 0)
+			amd_iommu_aperture_order = 29;
+		if (strcmp(str, "1G") == 0)
+			amd_iommu_aperture_order = 30;
+	}
+
+	return 1;
+}
+
+__setup("amd_iommu=", parse_amd_iommu_options);
+__setup("amd_iommu_size=", parse_amd_iommu_size_options);

arch/x86/kernel/aperture_64.c

@@ -35,6 +35,18 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
+struct bus_dev_range {
+	int bus;
+	int dev_base;
+	int dev_limit;
+};
+
+static struct bus_dev_range bus_dev_ranges[] __initdata = {
+	{ 0x00, 0x18, 0x20},
+	{ 0xff, 0x00, 0x20},
+	{ 0xfe, 0x00, 0x20}
+};
+
 static struct resource gart_resource = {
 	.name	= "GART",
 	.flags	= IORESOURCE_MEM,
@@ -55,8 +67,9 @@ static u32 __init allocate_aperture(void)
 	u32 aper_size;
 	void *p;
 
-	if (fallback_aper_order > 7)
-		fallback_aper_order = 7;
+	/* aper_size should <= 1G */
+	if (fallback_aper_order > 5)
+		fallback_aper_order = 5;
 	aper_size = (32 * 1024 * 1024) << fallback_aper_order;
 
 	/*
@@ -65,7 +78,20 @@ static u32 __init allocate_aperture(void)
 	 * memory. Unfortunately we cannot move it up because that would
 	 * make the IOMMU useless.
 	 */
-	p = __alloc_bootmem_nopanic(aper_size, aper_size, 0);
+	/*
+	 * using 512M as goal, in case kexec will load kernel_big
+	 * that will do the on position decompress, and  could overlap with
+	 * that positon with gart that is used.
+	 * sequende:
+	 * kernel_small
+	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
+	 * ==> kernel_small(gart area become e820_reserved)
+	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
+	 * ==> kerne_big (uncompressed size will be big than 64M or 128M)
+	 * so don't use 512M below as gart iommu, leave the space for kernel
+	 * code for safe
+	 */
+	p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20);
 	if (!p || __pa(p)+aper_size > 0xffffffff) {
 		printk(KERN_ERR
 			"Cannot allocate aperture memory hole (%p,%uK)\n",
@@ -83,69 +109,53 @@ static u32 __init allocate_aperture(void)
 	return (u32)__pa(p);
 }
 
-static int __init aperture_valid(u64 aper_base, u32 aper_size)
-{
-	if (!aper_base)
-		return 0;
-
-	if (aper_base + aper_size > 0x100000000UL) {
-		printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n");
-		return 0;
-	}
-	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
-		printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
-		return 0;
-	}
-	if (aper_size < 64*1024*1024) {
-		printk(KERN_ERR "Aperture too small (%d MB)\n", aper_size>>20);
-		return 0;
-	}
-
-	return 1;
-}
 
 /* Find a PCI capability */
-static __u32 __init find_cap(int num, int slot, int func, int cap)
+static u32 __init find_cap(int bus, int slot, int func, int cap)
 {
 	int bytes;
 	u8 pos;
 
-	if (!(read_pci_config_16(num, slot, func, PCI_STATUS) &
+	if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) &
 						PCI_STATUS_CAP_LIST))
 		return 0;
 
-	pos = read_pci_config_byte(num, slot, func, PCI_CAPABILITY_LIST);
+	pos = read_pci_config_byte(bus, slot, func, PCI_CAPABILITY_LIST);
 	for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) {
 		u8 id;
 
 		pos &= ~3;
-		id = read_pci_config_byte(num, slot, func, pos+PCI_CAP_LIST_ID);
+		id = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_ID);
 		if (id == 0xff)
 			break;
 		if (id == cap)
 			return pos;
-		pos = read_pci_config_byte(num, slot, func,
+		pos = read_pci_config_byte(bus, slot, func,
 						pos+PCI_CAP_LIST_NEXT);
 	}
 	return 0;
 }
 
 /* Read a standard AGPv3 bridge header */
-static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
+static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
 {
 	u32 apsize;
 	u32 apsizereg;
 	int nbits;
 	u32 aper_low, aper_hi;
 	u64 aper;
+	u32 old_order;
 
-	printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", num, slot, func);
-	apsizereg = read_pci_config_16(num, slot, func, cap + 0x14);
+	printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", bus, slot, func);
+	apsizereg = read_pci_config_16(bus, slot, func, cap + 0x14);
 	if (apsizereg == 0xffffffff) {
 		printk(KERN_ERR "APSIZE in AGP bridge unreadable\n");
 		return 0;
 	}
 
+	/* old_order could be the value from NB gart setting */
+	old_order = *order;
+
 	apsize = apsizereg & 0xfff;
 	/* Some BIOS use weird encodings not in the AGPv3 table. */
 	if (apsize & 0xff)
@@ -155,14 +165,26 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 	if ((int)*order < 0) /* < 32MB */
 		*order = 0;
 
-	aper_low = read_pci_config(num, slot, func, 0x10);
-	aper_hi = read_pci_config(num, slot, func, 0x14);
+	aper_low = read_pci_config(bus, slot, func, 0x10);
+	aper_hi = read_pci_config(bus, slot, func, 0x14);
 	aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32);
 
+	/*
+	 * On some sick chips, APSIZE is 0. It means it wants 4G
+	 * so let double check that order, and lets trust AMD NB settings:
+	 */
+	printk(KERN_INFO "Aperture from AGP @ %Lx old size %u MB\n",
+			aper, 32 << old_order);
+	if (aper + (32ULL<<(20 + *order)) > 0x100000000ULL) {
+		printk(KERN_INFO "Aperture size %u MB (APSIZE %x) is not right, using settings from NB\n",
+				32 << *order, apsizereg);
+		*order = old_order;
+	}
+
 	printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n",
 			aper, 32 << *order, apsizereg);
 
-	if (!aperture_valid(aper, (32*1024*1024) << *order))
+	if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20))
 		return 0;
 	return (u32)aper;
 }
@@ -180,17 +202,17 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
  * the AGP bridges should be always an own bus on the HT hierarchy,
  * but do it here for future safety.
  */
-static __u32 __init search_agp_bridge(u32 *order, int *valid_agp)
+static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 {
-	int num, slot, func;
+	int bus, slot, func;
 
 	/* Poor man's PCI discovery */
-	for (num = 0; num < 256; num++) {
+	for (bus = 0; bus < 256; bus++) {
 		for (slot = 0; slot < 32; slot++) {
 			for (func = 0; func < 8; func++) {
 				u32 class, cap;
 				u8 type;
-				class = read_pci_config(num, slot, func,
+				class = read_pci_config(bus, slot, func,
 							PCI_CLASS_REVISION);
 				if (class == 0xffffffff)
 					break;
@@ -199,17 +221,17 @@ static __u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 				case PCI_CLASS_BRIDGE_HOST:
 				case PCI_CLASS_BRIDGE_OTHER: /* needed? */
 					/* AGP bridge? */
-					cap = find_cap(num, slot, func,
+					cap = find_cap(bus, slot, func,
 							PCI_CAP_ID_AGP);
 					if (!cap)
 						break;
 					*valid_agp = 1;
-					return read_agp(num, slot, func, cap,
+					return read_agp(bus, slot, func, cap,
 							order);
 				}
 
 				/* No multi-function device? */
-				type = read_pci_config_byte(num, slot, func,
+				type = read_pci_config_byte(bus, slot, func,
 							       PCI_HEADER_TYPE);
 				if (!(type & 0x80))
 					break;
@@ -249,36 +271,50 @@ void __init early_gart_iommu_check(void)
 	 * or BIOS forget to put that in reserved.
 	 * try to update e820 to make that region as reserved.
 	 */
-	int fix, num;
+	int i, fix, slot;
 	u32 ctl;
 	u32 aper_size = 0, aper_order = 0, last_aper_order = 0;
 	u64 aper_base = 0, last_aper_base = 0;
-	int aper_enabled = 0, last_aper_enabled = 0;
+	int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0;
 
 	if (!early_pci_allowed())
 		return;
 
+	/* This is mostly duplicate of iommu_hole_init */
 	fix = 0;
-	for (num = 24; num < 32; num++) {
-		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
-			continue;
-
-		ctl = read_pci_config(0, num, 3, 0x90);
-		aper_enabled = ctl & 1;
-		aper_order = (ctl >> 1) & 7;
-		aper_size = (32 * 1024 * 1024) << aper_order;
-		aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff;
-		aper_base <<= 25;
-
-		if ((last_aper_order && aper_order != last_aper_order) ||
-		    (last_aper_base && aper_base != last_aper_base) ||
-		    (last_aper_enabled && aper_enabled != last_aper_enabled)) {
-			fix = 1;
-			break;
+	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+		int bus;
+		int dev_base, dev_limit;
+
+		bus = bus_dev_ranges[i].bus;
+		dev_base = bus_dev_ranges[i].dev_base;
+		dev_limit = bus_dev_ranges[i].dev_limit;
+
+		for (slot = dev_base; slot < dev_limit; slot++) {
+			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+				continue;
+
+			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
+			aper_enabled = ctl & AMD64_GARTEN;
+			aper_order = (ctl >> 1) & 7;
+			aper_size = (32 * 1024 * 1024) << aper_order;
+			aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
+			aper_base <<= 25;
+
+			if (last_valid) {
+				if ((aper_order != last_aper_order) ||
+				    (aper_base != last_aper_base) ||
+				    (aper_enabled != last_aper_enabled)) {
+					fix = 1;
+					break;
+				}
+			}
+
+			last_aper_order = aper_order;
+			last_aper_base = aper_base;
+			last_aper_enabled = aper_enabled;
+			last_valid = 1;
 		}
-		last_aper_order = aper_order;
-		last_aper_base = aper_base;
-		last_aper_enabled = aper_enabled;
 	}
 
 	if (!fix && !aper_enabled)
@@ -290,32 +326,46 @@ void __init early_gart_iommu_check(void)
 	if (gart_fix_e820 && !fix && aper_enabled) {
 		if (e820_any_mapped(aper_base, aper_base + aper_size,
 				    E820_RAM)) {
-			/* reserved it, so we can resuse it in second kernel */
+			/* reserve it, so we can reuse it in second kernel */
 			printk(KERN_INFO "update e820 for GART\n");
-			add_memory_region(aper_base, aper_size, E820_RESERVED);
+			e820_add_region(aper_base, aper_size, E820_RESERVED);
 			update_e820();
 		}
-		return;
 	}
 
+	if (!fix)
+		return;
+
 	/* different nodes have different setting, disable them all at first*/
-	for (num = 24; num < 32; num++) {
-		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
-			continue;
+	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+		int bus;
+		int dev_base, dev_limit;
+
+		bus = bus_dev_ranges[i].bus;
+		dev_base = bus_dev_ranges[i].dev_base;
+		dev_limit = bus_dev_ranges[i].dev_limit;
+
+		for (slot = dev_base; slot < dev_limit; slot++) {
+			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+				continue;
 
-		ctl = read_pci_config(0, num, 3, 0x90);
-		ctl &= ~1;
-		write_pci_config(0, num, 3, 0x90, ctl);
+			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
+			ctl &= ~AMD64_GARTEN;
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
+		}
 	}
 
 }
 
+static int __initdata printed_gart_size_msg;
+
 void __init gart_iommu_hole_init(void)
 {
+	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
 	u64 aper_base, last_aper_base = 0;
-	int fix, num, valid_agp = 0;
-	int node;
+	int fix, slot, valid_agp = 0;
+	int i, node;
 
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
@@ -323,38 +373,65 @@ void __init gart_iommu_hole_init(void)
 
 	printk(KERN_INFO  "Checking aperture...\n");
 
+	if (!fallback_aper_force)
+		agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp);
+
 	fix = 0;
 	node = 0;
-	for (num = 24; num < 32; num++) {
-		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
-			continue;
-
-		iommu_detected = 1;
-		gart_iommu_aperture = 1;
-
-		aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7;
-		aper_size = (32 * 1024 * 1024) << aper_order;
-		aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff;
-		aper_base <<= 25;
-
-		printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n",
-				node, aper_base, aper_size >> 20);
-		node++;
-
-		if (!aperture_valid(aper_base, aper_size)) {
-			fix = 1;
-			break;
-		}
+	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+		int bus;
+		int dev_base, dev_limit;
+
+		bus = bus_dev_ranges[i].bus;
+		dev_base = bus_dev_ranges[i].dev_base;
+		dev_limit = bus_dev_ranges[i].dev_limit;
+
+		for (slot = dev_base; slot < dev_limit; slot++) {
+			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+				continue;
+
+			iommu_detected = 1;
+			gart_iommu_aperture = 1;
+
+			aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7;
+			aper_size = (32 * 1024 * 1024) << aper_order;
+			aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
+			aper_base <<= 25;
+
+			printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n",
+					node, aper_base, aper_size >> 20);
+			node++;
+
+			if (!aperture_valid(aper_base, aper_size, 64<<20)) {
+				if (valid_agp && agp_aper_base &&
+				    agp_aper_base == aper_base &&
+				    agp_aper_order == aper_order) {
+					/* the same between two setting from NB and agp */
+					if (!no_iommu &&
+					    max_pfn > MAX_DMA32_PFN &&
+					    !printed_gart_size_msg) {
+						printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n");
+						printk(KERN_ERR "please increase GART size in your BIOS setup\n");
+						printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n");
+						printed_gart_size_msg = 1;
+					}
+				} else {
+					fix = 1;
+					goto out;
+				}
+			}
 
-		if ((last_aper_order && aper_order != last_aper_order) ||
-		    (last_aper_base && aper_base != last_aper_base)) {
-			fix = 1;
-			break;
+			if ((last_aper_order && aper_order != last_aper_order) ||
+			    (last_aper_base && aper_base != last_aper_base)) {
+				fix = 1;
+				goto out;
+			}
+			last_aper_order = aper_order;
+			last_aper_base = aper_base;
 		}
-		last_aper_order = aper_order;
-		last_aper_base = aper_base;
 	}
 
+out:
 	if (!fix && !fallback_aper_force) {
 		if (last_aper_base) {
 			unsigned long n = (32 * 1024 * 1024) << last_aper_order;
@@ -364,14 +441,16 @@ void __init gart_iommu_hole_init(void)
 		return;
 	}
 
-	if (!fallback_aper_force)
-		aper_alloc = search_agp_bridge(&aper_order, &valid_agp);
+	if (!fallback_aper_force) {
+		aper_alloc = agp_aper_base;
+		aper_order = agp_aper_order;
+	}
 
 	if (aper_alloc) {
 		/* Got the aperture from the AGP bridge */
 	} else if (swiotlb && !valid_agp) {
 		/* Do nothing */
-	} else if ((!no_iommu && end_pfn > MAX_DMA32_PFN) ||
+	} else if ((!no_iommu && max_pfn > MAX_DMA32_PFN) ||
 		   force_iommu ||
 		   valid_agp ||
 		   fallback_aper_force) {
@@ -401,16 +480,24 @@ void __init gart_iommu_hole_init(void)
 	}
 
 	/* Fix up the north bridges */
-	for (num = 24; num < 32; num++) {
-		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
-			continue;
-
-		/*
-		 * Don't enable translation yet. That is done later.
-		 * Assume this BIOS didn't initialise the GART so
-		 * just overwrite all previous bits
-		 */
-		write_pci_config(0, num, 3, 0x90, aper_order<<1);
-		write_pci_config(0, num, 3, 0x94, aper_alloc>>25);
+	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+		int bus;
+		int dev_base, dev_limit;
+
+		bus = bus_dev_ranges[i].bus;
+		dev_base = bus_dev_ranges[i].dev_base;
+		dev_limit = bus_dev_ranges[i].dev_limit;
+		for (slot = dev_base; slot < dev_limit; slot++) {
+			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+				continue;
+
+			/* Don't enable translation yet. That is done later.
+			   Assume this BIOS didn't initialise the GART so
+			   just overwrite all previous bits */
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1);
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25);
+		}
 	}
+
+	set_up_gart_resume(aper_order, aper_alloc);
 }

arch/x86/kernel/apic_32.c

@@ -52,30 +52,41 @@
 
 unsigned long mp_lapic_addr;
 
-DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID;
-EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
 /*
  * Knob to control our willingness to enable the local APIC.
  *
- * -1=force-disable, +1=force-enable
+ * +1=force-enable
  */
-static int enable_local_apic __initdata;
+static int force_enable_local_apic;
+int disable_apic;
 
 /* Local APIC timer verification ok */
 static int local_apic_timer_verify_ok;
-/* Disable local APIC timer from the kernel commandline or via dmi quirk
-   or using CPU MSR check */
-int local_apic_timer_disabled;
+/* Disable local APIC timer from the kernel commandline or via dmi quirk */
+static int local_apic_timer_disabled;
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
 
+int first_system_vector = 0xfe;
+
+char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+
 /*
  * Debug level, exported for io_apic.c
  */
 int apic_verbosity;
 
+int pic_mode;
+
+/* Have we found an MP table */
+int smp_found_config;
+
+static struct resource lapic_resource = {
+	.name = "Local APIC",
+	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
+};
+
 static unsigned int calibration_result;
 
 static int lapic_next_event(unsigned long delta,
@@ -545,7 +556,7 @@ void __init setup_boot_APIC_clock(void)
 			lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 		else
 			printk(KERN_WARNING "APIC timer registered as dummy,"
-			       " due to nmi_watchdog=1!\n");
+				" due to nmi_watchdog=%d!\n", nmi_watchdog);
 	}
 
 	/* Setup the lapic or request the broadcast */
@@ -963,7 +974,7 @@ void __cpuinit setup_local_APIC(void)
 	 * Double-check whether this APIC is really registered.
 	 */
 	if (!apic_id_registered())
-		BUG();
+		WARN_ON_ONCE(1);
 
 	/*
 	 * Intel recommends to set DFR, LDR and TPR before enabling
@@ -1094,7 +1105,7 @@ static int __init detect_init_APIC(void)
 	u32 h, l, features;
 
 	/* Disabled by kernel option? */
-	if (enable_local_apic < 0)
+	if (disable_apic)
 		return -1;
 
 	switch (boot_cpu_data.x86_vendor) {
@@ -1117,7 +1128,7 @@ static int __init detect_init_APIC(void)
 		 * Over-ride BIOS and try to enable the local APIC only if
 		 * "lapic" specified.
 		 */
-		if (enable_local_apic <= 0) {
+		if (!force_enable_local_apic) {
 			printk(KERN_INFO "Local APIC disabled by BIOS -- "
 			       "you can enable it with \"lapic\"\n");
 			return -1;
@@ -1154,9 +1165,6 @@ static int __init detect_init_APIC(void)
 	if (l & MSR_IA32_APICBASE_ENABLE)
 		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
 
-	if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED)
-		nmi_watchdog = NMI_LOCAL_APIC;
-
 	printk(KERN_INFO "Found and enabled local APIC!\n");
 
 	apic_pm_activate();
@@ -1195,36 +1203,6 @@ void __init init_apic_mappings(void)
 	if (boot_cpu_physical_apicid == -1U)
 		boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
 
-#ifdef CONFIG_X86_IO_APIC
-	{
-		unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
-		int i;
-
-		for (i = 0; i < nr_ioapics; i++) {
-			if (smp_found_config) {
-				ioapic_phys = mp_ioapics[i].mpc_apicaddr;
-				if (!ioapic_phys) {
-					printk(KERN_ERR
-					       "WARNING: bogus zero IO-APIC "
-					       "address found in MPTABLE, "
-					       "disabling IO/APIC support!\n");
-					smp_found_config = 0;
-					skip_ioapic_setup = 1;
-					goto fake_ioapic_page;
-				}
-			} else {
-fake_ioapic_page:
-				ioapic_phys = (unsigned long)
-					      alloc_bootmem_pages(PAGE_SIZE);
-				ioapic_phys = __pa(ioapic_phys);
-			}
-			set_fixmap_nocache(idx, ioapic_phys);
-			printk(KERN_DEBUG "mapped IOAPIC to %08lx (%08lx)\n",
-			       __fix_to_virt(idx), ioapic_phys);
-			idx++;
-		}
-	}
-#endif
 }
 
 /*
@@ -1236,7 +1214,7 @@ int apic_version[MAX_APICS];
 
 int __init APIC_init_uniprocessor(void)
 {
-	if (enable_local_apic < 0)
+	if (disable_apic)
 		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 
 	if (!smp_found_config && !cpu_has_apic)
@@ -1265,10 +1243,14 @@ int __init APIC_init_uniprocessor(void)
 #ifdef CONFIG_CRASH_DUMP
 	boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
 #endif
-	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+	physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
 
 	setup_local_APIC();
 
+#ifdef CONFIG_X86_IO_APIC
+	if (!smp_found_config || skip_ioapic_setup || !nr_ioapics)
+#endif
+		localise_nmi_watchdog();
 	end_local_APIC_setup();
 #ifdef CONFIG_X86_IO_APIC
 	if (smp_found_config)
@@ -1351,13 +1333,13 @@ void __init smp_intr_init(void)
 	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
 	 * IPI, driven by wakeup.
 	 */
-	set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
 
 	/* IPI for invalidation */
-	set_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
 
 	/* IPI for generic function call */
-	set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 }
 #endif
 
@@ -1370,15 +1352,15 @@ void __init apic_intr_init(void)
 	smp_intr_init();
 #endif
 	/* self generated IPI for local APIC timer */
-	set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
 
 	/* IPI vectors for APIC spurious and error interrupts */
-	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
 
 	/* thermal monitor LVT interrupt */
 #ifdef CONFIG_X86_MCE_P4THERMAL
-	set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
 #endif
 }
 
@@ -1513,6 +1495,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
 		 */
 		cpu = 0;
 
+	if (apicid > max_physical_apicid)
+		max_physical_apicid = apicid;
+
 	/*
 	 * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y
 	 * but we need to work other dependencies like SMP_SUSPEND etc
@@ -1520,7 +1505,7 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	 * if (CPU_HOTPLUG_ENABLED || num_processors > 8)
 	 *       - Ashok Raj <ashok.raj@intel.com>
 	 */
-	if (num_processors > 8) {
+	if (max_physical_apicid >= 8) {
 		switch (boot_cpu_data.x86_vendor) {
 		case X86_VENDOR_INTEL:
 			if (!APIC_XAPIC(version)) {
@@ -1534,9 +1519,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	}
 #ifdef CONFIG_SMP
 	/* are we being called early in kernel startup? */
-	if (x86_cpu_to_apicid_early_ptr) {
-		u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;
-		u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+	if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
+		u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+		u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 
 		cpu_to_apicid[cpu] = apicid;
 		bios_cpu_apicid[cpu] = apicid;
@@ -1703,14 +1688,14 @@ static void apic_pm_activate(void) { }
  */
 static int __init parse_lapic(char *arg)
 {
-	enable_local_apic = 1;
+	force_enable_local_apic = 1;
 	return 0;
 }
 early_param("lapic", parse_lapic);
 
 static int __init parse_nolapic(char *arg)
 {
-	enable_local_apic = -1;
+	disable_apic = 1;
 	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 	return 0;
 }
@@ -1740,3 +1725,21 @@ static int __init apic_set_verbosity(char *str)
 }
 __setup("apic=", apic_set_verbosity);
 
+static int __init lapic_insert_resource(void)
+{
+	if (!apic_phys)
+		return -1;
+
+	/* Put local APIC into the resource map. */
+	lapic_resource.start = apic_phys;
+	lapic_resource.end = lapic_resource.start + PAGE_SIZE - 1;
+	insert_resource(&iomem_resource, &lapic_resource);
+
+	return 0;
+}
+
+/*
+ * need call insert after e820_reserve_resources()
+ * that is using request_resource
+ */
+late_initcall(lapic_insert_resource);

arch/x86/kernel/apic_64.c

@@ -43,7 +43,7 @@
 #include <mach_ipi.h>
 #include <mach_apic.h>
 
-int disable_apic_timer __cpuinitdata;
+static int disable_apic_timer __cpuinitdata;
 static int apic_calibrate_pmtmr __initdata;
 int disable_apic;
 
@@ -56,6 +56,9 @@ EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
  */
 int apic_verbosity;
 
+/* Have we found an MP table */
+int smp_found_config;
+
 static struct resource lapic_resource = {
 	.name = "Local APIC",
 	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
@@ -87,9 +90,6 @@ static unsigned long apic_phys;
 
 unsigned long mp_lapic_addr;
 
-DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID;
-EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
 unsigned int __cpuinitdata maxcpus = NR_CPUS;
 /*
  * Get the LAPIC version
@@ -417,37 +417,13 @@ void __init setup_boot_APIC_clock(void)
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 	else
 		printk(KERN_WARNING "APIC timer registered as dummy,"
-		       " due to nmi_watchdog=1!\n");
+			" due to nmi_watchdog=%d!\n", nmi_watchdog);
 
 	setup_APIC_timer();
 }
 
-/*
- * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
- * C1E flag only in the secondary CPU, so when we detect the wreckage
- * we already have enabled the boot CPU local apic timer. Check, if
- * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
- * set the DUMMY flag again and force the broadcast mode in the
- * clockevents layer.
- */
-static void __cpuinit check_boot_apic_timer_broadcast(void)
-{
-	if (!disable_apic_timer ||
-	    (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
-		return;
-
-	printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
-	lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
-
-	local_irq_enable();
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
-			   &boot_cpu_physical_apicid);
-	local_irq_disable();
-}
-
 void __cpuinit setup_secondary_APIC_clock(void)
 {
-	check_boot_apic_timer_broadcast();
 	setup_APIC_timer();
 }
 
@@ -850,7 +826,6 @@ static void __cpuinit lapic_setup_esr(void)
 void __cpuinit end_local_APIC_setup(void)
 {
 	lapic_setup_esr();
-	nmi_watchdog_default();
 	setup_apic_nmi_watchdog(NULL);
 	apic_pm_activate();
 }
@@ -875,7 +850,7 @@ static int __init detect_init_APIC(void)
 
 void __init early_init_lapic_mapping(void)
 {
-	unsigned long apic_phys;
+	unsigned long phys_addr;
 
 	/*
 	 * If no local APIC can be found then go out
@@ -884,11 +859,11 @@ void __init early_init_lapic_mapping(void)
 	if (!smp_found_config)
 		return;
 
-	apic_phys = mp_lapic_addr;
+	phys_addr = mp_lapic_addr;
 
-	set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+	set_fixmap_nocache(FIX_APIC_BASE, phys_addr);
 	apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
-				 APIC_BASE, apic_phys);
+		    APIC_BASE, phys_addr);
 
 	/*
 	 * Fetch the APIC ID of the BSP in case we have a
@@ -942,7 +917,9 @@ int __init APIC_init_uniprocessor(void)
 
 	verify_local_APIC();
 
-	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+	connect_bsp_APIC();
+
+	physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
 	apic_write(APIC_ID, SET_APIC_ID(boot_cpu_physical_apicid));
 
 	setup_local_APIC();
@@ -954,6 +931,8 @@ int __init APIC_init_uniprocessor(void)
 	if (!skip_ioapic_setup && nr_ioapics)
 		enable_IO_APIC();
 
+	if (!smp_found_config || skip_ioapic_setup || !nr_ioapics)
+		localise_nmi_watchdog();
 	end_local_APIC_setup();
 
 	if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
@@ -1021,6 +1000,14 @@ asmlinkage void smp_error_interrupt(void)
 	irq_exit();
 }
 
+/**
+ *  * connect_bsp_APIC - attach the APIC to the interrupt system
+ *   */
+void __init connect_bsp_APIC(void)
+{
+	enable_apic_mode();
+}
+
 void disconnect_bsp_APIC(int virt_wire_setup)
 {
 	/* Go back to Virtual Wire compatibility mode */
@@ -1090,10 +1077,13 @@ void __cpuinit generic_processor_info(int apicid, int version)
 		 */
 		cpu = 0;
 	}
+	if (apicid > max_physical_apicid)
+		max_physical_apicid = apicid;
+
 	/* are we being called early in kernel startup? */
-	if (x86_cpu_to_apicid_early_ptr) {
-		u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;
-		u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+	if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
+		u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+		u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 
 		cpu_to_apicid[cpu] = apicid;
 		bios_cpu_apicid[cpu] = apicid;
@@ -1269,7 +1259,7 @@ __cpuinit int apic_is_clustered_box(void)
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
 		return 0;
 
-	bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+	bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
 
 	for (i = 0; i < NR_CPUS; i++) {

arch/x86/kernel/apm_32.c

@@ -228,6 +228,7 @@
 #include <linux/suspend.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
+#include <linux/smp_lock.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -1149,7 +1150,7 @@ static void queue_event(apm_event_t event, struct apm_user *sender)
 				as->event_tail = 0;
 		}
 		as->events[as->event_head] = event;
-		if ((!as->suser) || (!as->writer))
+		if (!as->suser || !as->writer)
 			continue;
 		switch (event) {
 		case APM_SYS_SUSPEND:
@@ -1396,7 +1397,7 @@ static void apm_mainloop(void)
 
 static int check_apm_user(struct apm_user *as, const char *func)
 {
-	if ((as == NULL) || (as->magic != APM_BIOS_MAGIC)) {
+	if (as == NULL || as->magic != APM_BIOS_MAGIC) {
 		printk(KERN_ERR "apm: %s passed bad filp\n", func);
 		return 1;
 	}
@@ -1459,18 +1460,19 @@ static unsigned int do_poll(struct file *fp, poll_table *wait)
 	return 0;
 }
 
-static int do_ioctl(struct inode *inode, struct file *filp,
-		    u_int cmd, u_long arg)
+static long do_ioctl(struct file *filp, u_int cmd, u_long arg)
 {
 	struct apm_user *as;
+	int ret;
 
 	as = filp->private_data;
 	if (check_apm_user(as, "ioctl"))
 		return -EIO;
-	if ((!as->suser) || (!as->writer))
+	if (!as->suser || !as->writer)
 		return -EPERM;
 	switch (cmd) {
 	case APM_IOC_STANDBY:
+		lock_kernel();
 		if (as->standbys_read > 0) {
 			as->standbys_read--;
 			as->standbys_pending--;
@@ -1479,8 +1481,10 @@ static int do_ioctl(struct inode *inode, struct file *filp,
 			queue_event(APM_USER_STANDBY, as);
 		if (standbys_pending <= 0)
 			standby();
+		unlock_kernel();
 		break;
 	case APM_IOC_SUSPEND:
+		lock_kernel();
 		if (as->suspends_read > 0) {
 			as->suspends_read--;
 			as->suspends_pending--;
@@ -1488,16 +1492,17 @@ static int do_ioctl(struct inode *inode, struct file *filp,
 		} else
 			queue_event(APM_USER_SUSPEND, as);
 		if (suspends_pending <= 0) {
-			return suspend(1);
+			ret = suspend(1);
 		} else {
 			as->suspend_wait = 1;
 			wait_event_interruptible(apm_suspend_waitqueue,
 					as->suspend_wait == 0);
-			return as->suspend_result;
+			ret = as->suspend_result;
 		}
-		break;
+		unlock_kernel();
+		return ret;
 	default:
-		return -EINVAL;
+		return -ENOTTY;
 	}
 	return 0;
 }
@@ -1860,7 +1865,7 @@ static const struct file_operations apm_bios_fops = {
 	.owner		= THIS_MODULE,
 	.read		= do_read,
 	.poll		= do_poll,
-	.ioctl		= do_ioctl,
+	.unlocked_ioctl	= do_ioctl,
 	.open		= do_open,
 	.release	= do_release,
 };

arch/x86/kernel/asm-offsets_32.c

@@ -111,7 +111,7 @@ void foo(void)
 	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
 	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
 	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
-	OFFSET(PV_CPU_irq_enable_syscall_ret, pv_cpu_ops, irq_enable_syscall_ret);
+	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
 	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
 #endif
 

arch/x86/kernel/asm-offsets_64.c

@@ -34,7 +34,7 @@ int main(void)
 	ENTRY(pid);
 	BLANK();
 #undef ENTRY
-#define ENTRY(entry) DEFINE(threadinfo_ ## entry, offsetof(struct thread_info, entry))
+#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry))
 	ENTRY(flags);
 	ENTRY(addr_limit);
 	ENTRY(preempt_count);
@@ -61,8 +61,11 @@ int main(void)
 	OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
 	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
 	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
+	OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame);
 	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
-	OFFSET(PV_CPU_irq_enable_syscall_ret, pv_cpu_ops, irq_enable_syscall_ret);
+	OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32);
+	OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
+	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
 	OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
 	OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
 #endif

arch/x86/kernel/cpu/Makefile

@@ -6,11 +6,15 @@ obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
 obj-y			+= proc.o feature_names.o
 
 obj-$(CONFIG_X86_32)	+= common.o bugs.o
+obj-$(CONFIG_X86_64)	+= common_64.o bugs_64.o
 obj-$(CONFIG_X86_32)	+= amd.o
+obj-$(CONFIG_X86_64)	+= amd_64.o
 obj-$(CONFIG_X86_32)	+= cyrix.o
 obj-$(CONFIG_X86_32)	+= centaur.o
+obj-$(CONFIG_X86_64)	+= centaur_64.o
 obj-$(CONFIG_X86_32)	+= transmeta.o
 obj-$(CONFIG_X86_32)	+= intel.o
+obj-$(CONFIG_X86_64)	+= intel_64.o
 obj-$(CONFIG_X86_32)	+= umc.o
 
 obj-$(CONFIG_X86_MCE)	+= mcheck/

arch/x86/kernel/cpu/addon_cpuid_features.c

@@ -1,9 +1,7 @@
-
 /*
  *	Routines to indentify additional cpu features that are scattered in
  *	cpuid space.
  */
-
 #include <linux/cpu.h>
 
 #include <asm/pat.h>
@@ -53,19 +51,20 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_PAT
 void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
 {
+	if (!cpu_has_pat)
+		pat_disable("PAT not supported by CPU.");
+
 	switch (c->x86_vendor) {
-	case X86_VENDOR_AMD:
-		if (c->x86 >= 0xf && c->x86 <= 0x11)
-			return;
-		break;
 	case X86_VENDOR_INTEL:
 		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
 			return;
 		break;
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_CENTAUR:
+	case X86_VENDOR_TRANSMETA:
+		return;
 	}
 
-	pat_disable(cpu_has_pat ?
-		    "PAT disabled. Not yet verified on this CPU type." :
-		    "PAT not supported by CPU.");
+	pat_disable("PAT disabled. Not yet verified on this CPU type.");
 }
 #endif

arch/x86/kernel/cpu/amd.c

@@ -24,43 +24,6 @@
 extern void vide(void);
 __asm__(".align 4\nvide: ret");
 
-#ifdef CONFIG_X86_LOCAL_APIC
-#define ENABLE_C1E_MASK         0x18000000
-#define CPUID_PROCESSOR_SIGNATURE       1
-#define CPUID_XFAM              0x0ff00000
-#define CPUID_XFAM_K8           0x00000000
-#define CPUID_XFAM_10H          0x00100000
-#define CPUID_XFAM_11H          0x00200000
-#define CPUID_XMOD              0x000f0000
-#define CPUID_XMOD_REV_F        0x00040000
-
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(void)
-{
-	u32 lo, hi;
-	u32 eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
-	switch (eax & CPUID_XFAM) {
-	case CPUID_XFAM_K8:
-		if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
-			break;
-	case CPUID_XFAM_10H:
-	case CPUID_XFAM_11H:
-		rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
-		if (lo & ENABLE_C1E_MASK) {
-			if (smp_processor_id() != boot_cpu_physical_apicid)
-				printk(KERN_INFO "AMD C1E detected late. "
-				       "	Force timer broadcast.\n");
-			return 1;
-		}
-		break;
-	default:
-		/* err on the side of caution */
-		return 1;
-	}
-	return 0;
-}
-#endif
-
 int force_mwait __cpuinitdata;
 
 static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
@@ -297,11 +260,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 			num_cache_leaves = 3;
 	}
 
-#ifdef CONFIG_X86_LOCAL_APIC
-	if (amd_apic_timer_broken())
-		local_apic_timer_disabled = 1;
-#endif
-
 	/* K6s reports MCEs but don't actually have all the MSRs */
 	if (c->x86 < 6)
 		clear_cpu_cap(c, X86_FEATURE_MCE);

arch/x86/kernel/cpu/amd_64.c

@@ -0,0 +1,222 @@
+#include <linux/init.h>
+#include <linux/mm.h>
+
+#include <asm/numa_64.h>
+#include <asm/mmconfig.h>
+#include <asm/cacheflush.h>
+
+#include <mach_apic.h>
+
+#include "cpu.h"
+
+int force_mwait __cpuinitdata;
+
+#ifdef CONFIG_NUMA
+static int __cpuinit nearby_node(int apicid)
+{
+	int i, node;
+
+	for (i = apicid - 1; i >= 0; i--) {
+		node = apicid_to_node[i];
+		if (node != NUMA_NO_NODE && node_online(node))
+			return node;
+	}
+	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
+		node = apicid_to_node[i];
+		if (node != NUMA_NO_NODE && node_online(node))
+			return node;
+	}
+	return first_node(node_online_map); /* Shouldn't happen */
+}
+#endif
+
+/*
+ * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
+ * Assumes number of cores is a power of two.
+ */
+static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned bits;
+#ifdef CONFIG_NUMA
+	int cpu = smp_processor_id();
+	int node = 0;
+	unsigned apicid = hard_smp_processor_id();
+#endif
+	bits = c->x86_coreid_bits;
+
+	/* Low order bits define the core id (index of core in socket) */
+	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+	/* Convert the initial APIC ID into the socket ID */
+	c->phys_proc_id = c->initial_apicid >> bits;
+
+#ifdef CONFIG_NUMA
+	node = c->phys_proc_id;
+	if (apicid_to_node[apicid] != NUMA_NO_NODE)
+		node = apicid_to_node[apicid];
+	if (!node_online(node)) {
+		/* Two possibilities here:
+		   - The CPU is missing memory and no node was created.
+		   In that case try picking one from a nearby CPU
+		   - The APIC IDs differ from the HyperTransport node IDs
+		   which the K8 northbridge parsing fills in.
+		   Assume they are all increased by a constant offset,
+		   but in the same order as the HT nodeids.
+		   If that doesn't result in a usable node fall back to the
+		   path for the previous case.  */
+
+		int ht_nodeid = c->initial_apicid;
+
+		if (ht_nodeid >= 0 &&
+		    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+			node = apicid_to_node[ht_nodeid];
+		/* Pick a nearby node */
+		if (!node_online(node))
+			node = nearby_node(apicid);
+	}
+	numa_set_node(cpu, node);
+
+	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+#endif
+}
+
+static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned bits, ecx;
+
+	/* Multi core CPU? */
+	if (c->extended_cpuid_level < 0x80000008)
+		return;
+
+	ecx = cpuid_ecx(0x80000008);
+
+	c->x86_max_cores = (ecx & 0xff) + 1;
+
+	/* CPU telling us the core id bits shift? */
+	bits = (ecx >> 12) & 0xF;
+
+	/* Otherwise recompute */
+	if (bits == 0) {
+		while ((1 << bits) < c->x86_max_cores)
+			bits++;
+	}
+
+	c->x86_coreid_bits = bits;
+
+#endif
+}
+
+static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+{
+	early_init_amd_mc(c);
+
+	/* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
+	if (c->x86_power & (1<<8))
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+}
+
+static void __cpuinit init_amd(struct cpuinfo_x86 *c)
+{
+	unsigned level;
+
+#ifdef CONFIG_SMP
+	unsigned long value;
+
+	/*
+	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
+	 * bit 6 of msr C001_0015
+	 *
+	 * Errata 63 for SH-B3 steppings
+	 * Errata 122 for all steppings (F+ have it disabled by default)
+	 */
+	if (c->x86 == 0xf) {
+		rdmsrl(MSR_K8_HWCR, value);
+		value |= 1 << 6;
+		wrmsrl(MSR_K8_HWCR, value);
+	}
+#endif
+
+	/* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+	   3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
+	clear_cpu_cap(c, 0*32+31);
+
+	/* On C+ stepping K8 rep microcode works well for copy/memset */
+	if (c->x86 == 0xf) {
+		level = cpuid_eax(1);
+		if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
+			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+	}
+	if (c->x86 == 0x10 || c->x86 == 0x11)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	/* Enable workaround for FXSAVE leak */
+	if (c->x86 >= 6)
+		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
+
+	level = get_model_name(c);
+	if (!level) {
+		switch (c->x86) {
+		case 0xf:
+			/* Should distinguish Models here, but this is only
+			   a fallback anyways. */
+			strcpy(c->x86_model_id, "Hammer");
+			break;
+		}
+	}
+	display_cacheinfo(c);
+
+	/* Multi core CPU? */
+	if (c->extended_cpuid_level >= 0x80000008)
+		amd_detect_cmp(c);
+
+	if (c->extended_cpuid_level >= 0x80000006 &&
+		(cpuid_edx(0x80000006) & 0xf000))
+		num_cache_leaves = 4;
+	else
+		num_cache_leaves = 3;
+
+	if (c->x86 >= 0xf && c->x86 <= 0x11)
+		set_cpu_cap(c, X86_FEATURE_K8);
+
+	/* MFENCE stops RDTSC speculation */
+	set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+
+	if (c->x86 == 0x10) {
+		/* do this for boot cpu */
+		if (c == &boot_cpu_data)
+			check_enable_amd_mmconf_dmi();
+
+		fam10h_check_enable_mmcfg();
+	}
+
+	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
+		unsigned long long tseg;
+
+		/*
+		 * Split up direct mapping around the TSEG SMM area.
+		 * Don't do it for gbpages because there seems very little
+		 * benefit in doing so.
+		 */
+		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+		    printk(KERN_DEBUG "tseg: %010llx\n", tseg);
+		    if ((tseg>>PMD_SHIFT) <
+				(max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
+			((tseg>>PMD_SHIFT) <
+				(max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
+			 (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
+			set_memory_4k((unsigned long)__va(tseg), 1);
+		}
+	}
+}
+
+static struct cpu_dev amd_cpu_dev __cpuinitdata = {
+	.c_vendor	= "AMD",
+	.c_ident	= { "AuthenticAMD" },
+	.c_early_init   = early_init_amd,
+	.c_init		= init_amd,
+};
+
+cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev);
+

arch/x86/kernel/cpu/bugs.c

@@ -59,8 +59,12 @@ static void __init check_fpu(void)
 		return;
 	}
 
-/* trap_init() enabled FXSR and company _before_ testing for FP problems here. */
-	/* Test for the divl bug.. */
+	/*
+	 * 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"
@@ -108,10 +112,15 @@ static void __init check_popad(void)
 	  "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" );
+	  : "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
 }
 
@@ -137,7 +146,8 @@ static void __init check_config(void)
  * 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 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
@@ -170,6 +180,7 @@ void __init check_bugs(void)
 	check_fpu();
 	check_hlt();
 	check_popad();
-	init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+	init_utsname()->machine[1] =
+		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions();
 }

arch/x86/kernel/cpu/centaur_64.c

@@ -0,0 +1,35 @@
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+
+#include "cpu.h"
+
+static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
+{
+	if (c->x86 == 0x6 && c->x86_model >= 0xf)
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+
+	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+}
+
+static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
+{
+	if (c->x86 == 0x6 && c->x86_model >= 0xf) {
+		c->x86_cache_alignment = c->x86_clflush_size * 2;
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+	}
+	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+}
+
+static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
+	.c_vendor	= "Centaur",
+	.c_ident	= { "CentaurHauls" },
+	.c_early_init	= early_init_centaur,
+	.c_init		= init_centaur,
+};
+
+cpu_vendor_dev_register(X86_VENDOR_CENTAUR, &centaur_cpu_dev);
+

arch/x86/kernel/cpu/common.c

@@ -427,7 +427,7 @@ __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;
 

arch/x86/kernel/cpu/common_64.c

@@ -0,0 +1,681 @@
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/bootmem.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/kgdb.h>
+#include <linux/topology.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/msr.h>
+#include <asm/io.h>
+#include <asm/mmu_context.h>
+#include <asm/mtrr.h>
+#include <asm/mce.h>
+#include <asm/pat.h>
+#include <asm/numa.h>
+#ifdef CONFIG_X86_LOCAL_APIC
+#include <asm/mpspec.h>
+#include <asm/apic.h>
+#include <mach_apic.h>
+#endif
+#include <asm/pda.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/proto.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/genapic.h>
+
+#include "cpu.h"
+
+/* We need valid kernel segments for data and code in long mode too
+ * IRET will check the segment types  kkeil 2000/10/28
+ * Also sysret mandates a special GDT layout
+ */
+/* The TLS descriptors are currently at a different place compared to i386.
+   Hopefully nobody expects them at a fixed place (Wine?) */
+DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+	[GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
+	[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
+	[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
+	[GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
+	[GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
+	[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
+} };
+EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
+
+__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+
+/* 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 desc_ptr gdt_descr;
+
+	gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+}
+
+struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
+
+static void __cpuinit default_init(struct cpuinfo_x86 *c)
+{
+	display_cacheinfo(c);
+}
+
+static struct cpu_dev __cpuinitdata default_cpu = {
+	.c_init	= default_init,
+	.c_vendor = "Unknown",
+};
+static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
+
+int __cpuinit get_model_name(struct cpuinfo_x86 *c)
+{
+	unsigned int *v;
+
+	if (c->extended_cpuid_level < 0x80000004)
+		return 0;
+
+	v = (unsigned int *) c->x86_model_id;
+	cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
+	cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
+	cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
+	c->x86_model_id[48] = 0;
+	return 1;
+}
+
+
+void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
+{
+	unsigned int n, dummy, ebx, ecx, edx;
+
+	n = c->extended_cpuid_level;
+
+	if (n >= 0x80000005) {
+		cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
+		printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), "
+		       "D cache %dK (%d bytes/line)\n",
+		       edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+		c->x86_cache_size = (ecx>>24) + (edx>>24);
+		/* On K8 L1 TLB is inclusive, so don't count it */
+		c->x86_tlbsize = 0;
+	}
+
+	if (n >= 0x80000006) {
+		cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
+		ecx = cpuid_ecx(0x80000006);
+		c->x86_cache_size = ecx >> 16;
+		c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
+
+		printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
+		c->x86_cache_size, ecx & 0xFF);
+	}
+}
+
+void __cpuinit detect_ht(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	u32 eax, ebx, ecx, edx;
+	int index_msb, core_bits;
+
+	cpuid(1, &eax, &ebx, &ecx, &edx);
+
+
+	if (!cpu_has(c, X86_FEATURE_HT))
+		return;
+	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
+		goto out;
+
+	smp_num_siblings = (ebx & 0xff0000) >> 16;
+
+	if (smp_num_siblings == 1) {
+		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
+	} else if (smp_num_siblings > 1) {
+
+		if (smp_num_siblings > NR_CPUS) {
+			printk(KERN_WARNING "CPU: Unsupported number of "
+			       "siblings %d", smp_num_siblings);
+			smp_num_siblings = 1;
+			return;
+		}
+
+		index_msb = get_count_order(smp_num_siblings);
+		c->phys_proc_id = phys_pkg_id(index_msb);
+
+		smp_num_siblings = smp_num_siblings / c->x86_max_cores;
+
+		index_msb = get_count_order(smp_num_siblings);
+
+		core_bits = get_count_order(c->x86_max_cores);
+
+		c->cpu_core_id = phys_pkg_id(index_msb) &
+					       ((1 << core_bits) - 1);
+	}
+out:
+	if ((c->x86_max_cores * smp_num_siblings) > 1) {
+		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
+		       c->phys_proc_id);
+		printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
+		       c->cpu_core_id);
+	}
+
+#endif
+}
+
+static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
+{
+	char *v = c->x86_vendor_id;
+	int i;
+	static int printed;
+
+	for (i = 0; i < X86_VENDOR_NUM; i++) {
+		if (cpu_devs[i]) {
+			if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
+			    (cpu_devs[i]->c_ident[1] &&
+			    !strcmp(v, cpu_devs[i]->c_ident[1]))) {
+				c->x86_vendor = i;
+				this_cpu = cpu_devs[i];
+				return;
+			}
+		}
+	}
+	if (!printed) {
+		printed++;
+		printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n");
+		printk(KERN_ERR "CPU: Your system may be unstable.\n");
+	}
+	c->x86_vendor = X86_VENDOR_UNKNOWN;
+}
+
+static void __init early_cpu_support_print(void)
+{
+	int i,j;
+	struct cpu_dev *cpu_devx;
+
+	printk("KERNEL supported cpus:\n");
+	for (i = 0; i < X86_VENDOR_NUM; i++) {
+		cpu_devx = cpu_devs[i];
+		if (!cpu_devx)
+			continue;
+		for (j = 0; j < 2; j++) {
+			if (!cpu_devx->c_ident[j])
+				continue;
+			printk("  %s %s\n", cpu_devx->c_vendor,
+				cpu_devx->c_ident[j]);
+		}
+	}
+}
+
+static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c);
+
+void __init early_cpu_init(void)
+{
+        struct cpu_vendor_dev *cvdev;
+
+        for (cvdev = __x86cpuvendor_start ;
+             cvdev < __x86cpuvendor_end   ;
+             cvdev++)
+                cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
+	early_cpu_support_print();
+	early_identify_cpu(&boot_cpu_data);
+}
+
+/* Do some early cpuid on the boot CPU to get some parameter that are
+   needed before check_bugs. Everything advanced is in identify_cpu
+   below. */
+static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
+{
+	u32 tfms, xlvl;
+
+	c->loops_per_jiffy = loops_per_jiffy;
+	c->x86_cache_size = -1;
+	c->x86_vendor = X86_VENDOR_UNKNOWN;
+	c->x86_model = c->x86_mask = 0;	/* So far unknown... */
+	c->x86_vendor_id[0] = '\0'; /* Unset */
+	c->x86_model_id[0] = '\0';  /* Unset */
+	c->x86_clflush_size = 64;
+	c->x86_cache_alignment = c->x86_clflush_size;
+	c->x86_max_cores = 1;
+	c->x86_coreid_bits = 0;
+	c->extended_cpuid_level = 0;
+	memset(&c->x86_capability, 0, sizeof c->x86_capability);
+
+	/* Get vendor name */
+	cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
+	      (unsigned int *)&c->x86_vendor_id[0],
+	      (unsigned int *)&c->x86_vendor_id[8],
+	      (unsigned int *)&c->x86_vendor_id[4]);
+
+	get_cpu_vendor(c);
+
+	/* Initialize the standard set of capabilities */
+	/* Note that the vendor-specific code below might override */
+
+	/* Intel-defined flags: level 0x00000001 */
+	if (c->cpuid_level >= 0x00000001) {
+		__u32 misc;
+		cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4],
+		      &c->x86_capability[0]);
+		c->x86 = (tfms >> 8) & 0xf;
+		c->x86_model = (tfms >> 4) & 0xf;
+		c->x86_mask = tfms & 0xf;
+		if (c->x86 == 0xf)
+			c->x86 += (tfms >> 20) & 0xff;
+		if (c->x86 >= 0x6)
+			c->x86_model += ((tfms >> 16) & 0xF) << 4;
+		if (test_cpu_cap(c, X86_FEATURE_CLFLSH))
+			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
+	} else {
+		/* Have CPUID level 0 only - unheard of */
+		c->x86 = 4;
+	}
+
+	c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xff;
+#ifdef CONFIG_SMP
+	c->phys_proc_id = c->initial_apicid;
+#endif
+	/* AMD-defined flags: level 0x80000001 */
+	xlvl = cpuid_eax(0x80000000);
+	c->extended_cpuid_level = xlvl;
+	if ((xlvl & 0xffff0000) == 0x80000000) {
+		if (xlvl >= 0x80000001) {
+			c->x86_capability[1] = cpuid_edx(0x80000001);
+			c->x86_capability[6] = cpuid_ecx(0x80000001);
+		}
+		if (xlvl >= 0x80000004)
+			get_model_name(c); /* Default name */
+	}
+
+	/* Transmeta-defined flags: level 0x80860001 */
+	xlvl = cpuid_eax(0x80860000);
+	if ((xlvl & 0xffff0000) == 0x80860000) {
+		/* Don't set x86_cpuid_level here for now to not confuse. */
+		if (xlvl >= 0x80860001)
+			c->x86_capability[2] = cpuid_edx(0x80860001);
+	}
+
+	c->extended_cpuid_level = cpuid_eax(0x80000000);
+	if (c->extended_cpuid_level >= 0x80000007)
+		c->x86_power = cpuid_edx(0x80000007);
+
+	if (c->extended_cpuid_level >= 0x80000008) {
+		u32 eax = cpuid_eax(0x80000008);
+
+		c->x86_virt_bits = (eax >> 8) & 0xff;
+		c->x86_phys_bits = eax & 0xff;
+	}
+
+	/* Assume all 64-bit CPUs support 32-bit syscall */
+	set_cpu_cap(c, X86_FEATURE_SYSCALL32);
+
+	if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
+	    cpu_devs[c->x86_vendor]->c_early_init)
+		cpu_devs[c->x86_vendor]->c_early_init(c);
+
+	validate_pat_support(c);
+
+	/* early_param could clear that, but recall get it set again */
+	if (disable_apic)
+		clear_cpu_cap(c, X86_FEATURE_APIC);
+}
+
+/*
+ * This does the hard work of actually picking apart the CPU stuff...
+ */
+static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
+{
+	int i;
+
+	early_identify_cpu(c);
+
+	init_scattered_cpuid_features(c);
+
+	c->apicid = phys_pkg_id(0);
+
+	/*
+	 * Vendor-specific initialization.  In this section we
+	 * canonicalize the feature flags, meaning if there are
+	 * features a certain CPU supports which CPUID doesn't
+	 * tell us, CPUID claiming incorrect flags, or other bugs,
+	 * we handle them here.
+	 *
+	 * At the end of this section, c->x86_capability better
+	 * indicate the features this CPU genuinely supports!
+	 */
+	if (this_cpu->c_init)
+		this_cpu->c_init(c);
+
+	detect_ht(c);
+
+	/*
+	 * On SMP, boot_cpu_data holds the common feature set between
+	 * all CPUs; so make sure that we indicate which features are
+	 * common between the CPUs.  The first time this routine gets
+	 * executed, c == &boot_cpu_data.
+	 */
+	if (c != &boot_cpu_data) {
+		/* AND the already accumulated flags with these */
+		for (i = 0; i < NCAPINTS; i++)
+			boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
+	}
+
+	/* Clear all flags overriden by options */
+	for (i = 0; i < NCAPINTS; i++)
+		c->x86_capability[i] &= ~cleared_cpu_caps[i];
+
+#ifdef CONFIG_X86_MCE
+	mcheck_init(c);
+#endif
+	select_idle_routine(c);
+
+#ifdef CONFIG_NUMA
+	numa_add_cpu(smp_processor_id());
+#endif
+
+}
+
+void __cpuinit identify_boot_cpu(void)
+{
+	identify_cpu(&boot_cpu_data);
+}
+
+void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
+{
+	BUG_ON(c == &boot_cpu_data);
+	identify_cpu(c);
+	mtrr_ap_init();
+}
+
+static __init int setup_noclflush(char *arg)
+{
+	setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
+	return 1;
+}
+__setup("noclflush", setup_noclflush);
+
+void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
+{
+	if (c->x86_model_id[0])
+		printk(KERN_CONT "%s", c->x86_model_id);
+
+	if (c->x86_mask || c->cpuid_level >= 0)
+		printk(KERN_CONT " stepping %02x\n", c->x86_mask);
+	else
+		printk(KERN_CONT "\n");
+}
+
+static __init int setup_disablecpuid(char *arg)
+{
+	int bit;
+	if (get_option(&arg, &bit) && bit < NCAPINTS*32)
+		setup_clear_cpu_cap(bit);
+	else
+		return 0;
+	return 1;
+}
+__setup("clearcpuid=", setup_disablecpuid);
+
+cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
+
+struct x8664_pda **_cpu_pda __read_mostly;
+EXPORT_SYMBOL(_cpu_pda);
+
+struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
+
+char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+
+unsigned long __supported_pte_mask __read_mostly = ~0UL;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
+
+static int do_not_nx __cpuinitdata;
+
+/* noexec=on|off
+Control non executable mappings for 64bit processes.
+
+on	Enable(default)
+off	Disable
+*/
+static int __init nonx_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	if (!strncmp(str, "on", 2)) {
+		__supported_pte_mask |= _PAGE_NX;
+		do_not_nx = 0;
+	} else if (!strncmp(str, "off", 3)) {
+		do_not_nx = 1;
+		__supported_pte_mask &= ~_PAGE_NX;
+	}
+	return 0;
+}
+early_param("noexec", nonx_setup);
+
+int force_personality32;
+
+/* noexec32=on|off
+Control non executable heap for 32bit processes.
+To control the stack too use noexec=off
+
+on	PROT_READ does not imply PROT_EXEC for 32bit processes (default)
+off	PROT_READ implies PROT_EXEC
+*/
+static int __init nonx32_setup(char *str)
+{
+	if (!strcmp(str, "on"))
+		force_personality32 &= ~READ_IMPLIES_EXEC;
+	else if (!strcmp(str, "off"))
+		force_personality32 |= READ_IMPLIES_EXEC;
+	return 1;
+}
+__setup("noexec32=", nonx32_setup);
+
+void pda_init(int cpu)
+{
+	struct x8664_pda *pda = cpu_pda(cpu);
+
+	/* Setup up data that may be needed in __get_free_pages early */
+	loadsegment(fs, 0);
+	loadsegment(gs, 0);
+	/* Memory clobbers used to order PDA accessed */
+	mb();
+	wrmsrl(MSR_GS_BASE, pda);
+	mb();
+
+	pda->cpunumber = cpu;
+	pda->irqcount = -1;
+	pda->kernelstack = (unsigned long)stack_thread_info() -
+				 PDA_STACKOFFSET + THREAD_SIZE;
+	pda->active_mm = &init_mm;
+	pda->mmu_state = 0;
+
+	if (cpu == 0) {
+		/* others are initialized in smpboot.c */
+		pda->pcurrent = &init_task;
+		pda->irqstackptr = boot_cpu_stack;
+	} else {
+		pda->irqstackptr = (char *)
+			__get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
+		if (!pda->irqstackptr)
+			panic("cannot allocate irqstack for cpu %d", cpu);
+
+		if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
+			pda->nodenumber = cpu_to_node(cpu);
+	}
+
+	pda->irqstackptr += IRQSTACKSIZE-64;
+}
+
+char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
+			   DEBUG_STKSZ]
+__attribute__((section(".bss.page_aligned")));
+
+extern asmlinkage void ignore_sysret(void);
+
+/* May not be marked __init: used by software suspend */
+void syscall_init(void)
+{
+	/*
+	 * LSTAR and STAR live in a bit strange symbiosis.
+	 * They both write to the same internal register. STAR allows to
+	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
+	 */
+	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
+	wrmsrl(MSR_LSTAR, system_call);
+	wrmsrl(MSR_CSTAR, ignore_sysret);
+
+#ifdef CONFIG_IA32_EMULATION
+	syscall32_cpu_init();
+#endif
+
+	/* Flags to clear on syscall */
+	wrmsrl(MSR_SYSCALL_MASK,
+	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL);
+}
+
+void __cpuinit check_efer(void)
+{
+	unsigned long efer;
+
+	rdmsrl(MSR_EFER, efer);
+	if (!(efer & EFER_NX) || do_not_nx)
+		__supported_pte_mask &= ~_PAGE_NX;
+}
+
+unsigned long kernel_eflags;
+
+/*
+ * Copies of the original ist values from the tss are only accessed during
+ * debugging, no special alignment required.
+ */
+DEFINE_PER_CPU(struct orig_ist, orig_ist);
+
+/*
+ * 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.
+ * A lot of state is already set up in PDA init.
+ */
+void __cpuinit cpu_init(void)
+{
+	int cpu = stack_smp_processor_id();
+	struct tss_struct *t = &per_cpu(init_tss, cpu);
+	struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
+	unsigned long v;
+	char *estacks = NULL;
+	struct task_struct *me;
+	int i;
+
+	/* CPU 0 is initialised in head64.c */
+	if (cpu != 0)
+		pda_init(cpu);
+	else
+		estacks = boot_exception_stacks;
+
+	me = current;
+
+	if (cpu_test_and_set(cpu, cpu_initialized))
+		panic("CPU#%d already initialized!\n", cpu);
+
+	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
+
+	clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+
+	/*
+	 * Initialize the per-CPU GDT with the boot GDT,
+	 * and set up the GDT descriptor:
+	 */
+
+	switch_to_new_gdt();
+	load_idt((const struct desc_ptr *)&idt_descr);
+
+	memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
+	syscall_init();
+
+	wrmsrl(MSR_FS_BASE, 0);
+	wrmsrl(MSR_KERNEL_GS_BASE, 0);
+	barrier();
+
+	check_efer();
+
+	/*
+	 * set up and load the per-CPU TSS
+	 */
+	for (v = 0; v < N_EXCEPTION_STACKS; v++) {
+		static const unsigned int order[N_EXCEPTION_STACKS] = {
+			[0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
+			[DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+		};
+		if (cpu) {
+			estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
+			if (!estacks)
+				panic("Cannot allocate exception stack %ld %d\n",
+				      v, cpu);
+		}
+		estacks += PAGE_SIZE << order[v];
+		orig_ist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks;
+	}
+
+	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+	/*
+	 * <= is required because the CPU will access up to
+	 * 8 bits beyond the end of the IO permission bitmap.
+	 */
+	for (i = 0; i <= IO_BITMAP_LONGS; i++)
+		t->io_bitmap[i] = ~0UL;
+
+	atomic_inc(&init_mm.mm_count);
+	me->active_mm = &init_mm;
+	if (me->mm)
+		BUG();
+	enter_lazy_tlb(&init_mm, me);
+
+	load_sp0(t, &current->thread);
+	set_tss_desc(cpu, t);
+	load_TR_desc();
+	load_LDT(&init_mm.context);
+
+#ifdef CONFIG_KGDB
+	/*
+	 * If the kgdb is connected no debug regs should be altered.  This
+	 * is only applicable when KGDB and a KGDB I/O module are built
+	 * into the kernel and you are using early debugging with
+	 * kgdbwait. KGDB will control the kernel HW breakpoint registers.
+	 */
+	if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
+		arch_kgdb_ops.correct_hw_break();
+	else {
+#endif
+	/*
+	 * Clear all 6 debug registers:
+	 */
+
+	set_debugreg(0UL, 0);
+	set_debugreg(0UL, 1);
+	set_debugreg(0UL, 2);
+	set_debugreg(0UL, 3);
+	set_debugreg(0UL, 6);
+	set_debugreg(0UL, 7);
+#ifdef CONFIG_KGDB
+	/* If the kgdb is connected no debug regs should be altered. */
+	}
+#endif
+
+	fpu_init();
+
+	raw_local_save_flags(kernel_eflags);
+
+	if (is_uv_system())
+		uv_cpu_init();
+}

arch/x86/kernel/cpu/cpu.h

@@ -1,3 +1,6 @@
+#ifndef ARCH_X86_CPU_H
+
+#define ARCH_X86_CPU_H
 
 struct cpu_model_info {
 	int vendor;
@@ -36,3 +39,5 @@ extern struct cpu_vendor_dev __x86cpuvendor_start[], __x86cpuvendor_end[];
 
 extern int get_model_name(struct cpuinfo_x86 *c);
 extern void display_cacheinfo(struct cpuinfo_x86 *c);
+
+#endif

arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c

@@ -26,9 +26,10 @@
 #define NFORCE2_SAFE_DISTANCE 50
 
 /* Delay in ms between FSB changes */
-//#define NFORCE2_DELAY 10
+/* #define NFORCE2_DELAY 10 */
 
-/* nforce2_chipset:
+/*
+ * nforce2_chipset:
  * FSB is changed using the chipset
  */
 static struct pci_dev *nforce2_chipset_dev;
@@ -36,13 +37,13 @@ static struct pci_dev *nforce2_chipset_dev;
 /* fid:
  * multiplier * 10
  */
-static int fid = 0;
+static int fid;
 
 /* min_fsb, max_fsb:
  * minimum and maximum FSB (= FSB at boot time)
  */
-static int min_fsb = 0;
-static int max_fsb = 0;
+static int min_fsb;
+static int max_fsb;
 
 MODULE_AUTHOR("Sebastian Witt <se.witt@gmx.net>");
 MODULE_DESCRIPTION("nForce2 FSB changing cpufreq driver");
@@ -53,7 +54,7 @@ module_param(min_fsb, int, 0444);
 
 MODULE_PARM_DESC(fid, "CPU multiplier to use (11.5 = 115)");
 MODULE_PARM_DESC(min_fsb,
-                 "Minimum FSB to use, if not defined: current FSB - 50");
+		"Minimum FSB to use, if not defined: current FSB - 50");
 
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "cpufreq-nforce2", msg)
 
@@ -139,7 +140,7 @@ static unsigned int nforce2_fsb_read(int bootfsb)
 
 	/* Get chipset boot FSB from subdevice 5 (FSB at boot-time) */
 	nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA,
-						0x01EF,PCI_ANY_ID,PCI_ANY_ID,NULL);
+						0x01EF, PCI_ANY_ID, PCI_ANY_ID, NULL);
 	if (!nforce2_sub5)
 		return 0;
 
@@ -147,13 +148,13 @@ static unsigned int nforce2_fsb_read(int bootfsb)
 	fsb /= 1000000;
 
 	/* Check if PLL register is already set */
-	pci_read_config_byte(nforce2_chipset_dev,NFORCE2_PLLENABLE, (u8 *)&temp);
+	pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp);
 
-	if(bootfsb || !temp)
+	if (bootfsb || !temp)
 		return fsb;
-		
+
 	/* Use PLL register FSB value */
-	pci_read_config_dword(nforce2_chipset_dev,NFORCE2_PLLREG, &temp);
+	pci_read_config_dword(nforce2_chipset_dev, NFORCE2_PLLREG, &temp);
 	fsb = nforce2_calc_fsb(temp);
 
 	return fsb;
@@ -184,7 +185,7 @@ static int nforce2_set_fsb(unsigned int fsb)
 	}
 
 	/* First write? Then set actual value */
-	pci_read_config_byte(nforce2_chipset_dev,NFORCE2_PLLENABLE, (u8 *)&temp);
+	pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp);
 	if (!temp) {
 		pll = nforce2_calc_pll(tfsb);
 
@@ -210,7 +211,8 @@ static int nforce2_set_fsb(unsigned int fsb)
 			tfsb--;
 
 		/* Calculate the PLL reg. value */
-		if ((pll = nforce2_calc_pll(tfsb)) == -1)
+		pll = nforce2_calc_pll(tfsb);
+		if (pll == -1)
 			return -EINVAL;
 
 		nforce2_write_pll(pll);
@@ -249,7 +251,7 @@ static unsigned int nforce2_get(unsigned int cpu)
 static int nforce2_target(struct cpufreq_policy *policy,
 			  unsigned int target_freq, unsigned int relation)
 {
-//        unsigned long         flags;
+/*        unsigned long         flags; */
 	struct cpufreq_freqs freqs;
 	unsigned int target_fsb;
 
@@ -271,17 +273,17 @@ static int nforce2_target(struct cpufreq_policy *policy,
 	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 
 	/* Disable IRQs */
-	//local_irq_save(flags);
+	/* local_irq_save(flags); */
 
 	if (nforce2_set_fsb(target_fsb) < 0)
 		printk(KERN_ERR "cpufreq: Changing FSB to %d failed\n",
-                       target_fsb);
+			target_fsb);
 	else
 		dprintk("Changed FSB successfully to %d\n",
-                       target_fsb);
+			target_fsb);
 
 	/* Enable IRQs */
-	//local_irq_restore(flags);
+	/* local_irq_restore(flags); */
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
@@ -302,8 +304,8 @@ static int nforce2_verify(struct cpufreq_policy *policy)
 		policy->max = (fsb_pol_max + 1) * fid * 100;
 
 	cpufreq_verify_within_limits(policy,
-                                     policy->cpuinfo.min_freq,
-                                     policy->cpuinfo.max_freq);
+				     policy->cpuinfo.min_freq,
+				     policy->cpuinfo.max_freq);
 	return 0;
 }
 
@@ -347,7 +349,7 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy)
 	/* Set maximum FSB to FSB at boot time */
 	max_fsb = nforce2_fsb_read(1);
 
-	if(!max_fsb)
+	if (!max_fsb)
 		return -EIO;
 
 	if (!min_fsb)

arch/x86/kernel/cpu/intel.c

@@ -226,6 +226,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 
 	if (cpu_has_bts)
 		ds_init_intel(c);
+
+#ifdef CONFIG_X86_NUMAQ
+	numaq_tsc_disable();
+#endif
 }
 
 static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)

arch/x86/kernel/cpu/intel_64.c

@@ -0,0 +1,95 @@
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/topology.h>
+#include <asm/numa_64.h>
+
+#include "cpu.h"
+
+static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
+{
+	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
+	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+
+	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+}
+
+/*
+ * find out the number of processor cores on the die
+ */
+static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
+{
+	unsigned int eax, t;
+
+	if (c->cpuid_level < 4)
+		return 1;
+
+	cpuid_count(4, 0, &eax, &t, &t, &t);
+
+	if (eax & 0x1f)
+		return ((eax >> 26) + 1);
+	else
+		return 1;
+}
+
+static void __cpuinit srat_detect_node(void)
+{
+#ifdef CONFIG_NUMA
+	unsigned node;
+	int cpu = smp_processor_id();
+	int apicid = hard_smp_processor_id();
+
+	/* Don't do the funky fallback heuristics the AMD version employs
+	   for now. */
+	node = apicid_to_node[apicid];
+	if (node == NUMA_NO_NODE || !node_online(node))
+		node = first_node(node_online_map);
+	numa_set_node(cpu, node);
+
+	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+}
+
+static void __cpuinit init_intel(struct cpuinfo_x86 *c)
+{
+	init_intel_cacheinfo(c);
+	if (c->cpuid_level > 9) {
+		unsigned eax = cpuid_eax(10);
+		/* Check for version and the number of counters */
+		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
+			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+	}
+
+	if (cpu_has_ds) {
+		unsigned int l1, l2;
+		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
+		if (!(l1 & (1<<11)))
+			set_cpu_cap(c, X86_FEATURE_BTS);
+		if (!(l1 & (1<<12)))
+			set_cpu_cap(c, X86_FEATURE_PEBS);
+	}
+
+
+	if (cpu_has_bts)
+		ds_init_intel(c);
+
+	if (c->x86 == 15)
+		c->x86_cache_alignment = c->x86_clflush_size * 2;
+	if (c->x86 == 6)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+	c->x86_max_cores = intel_num_cpu_cores(c);
+
+	srat_detect_node();
+}
+
+static struct cpu_dev intel_cpu_dev __cpuinitdata = {
+	.c_vendor	= "Intel",
+	.c_ident	= { "GenuineIntel" },
+	.c_early_init   = early_init_intel,
+	.c_init		= init_intel,
+};
+cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev);
+

arch/x86/kernel/cpu/intel_cacheinfo.c

@@ -62,6 +62,7 @@ static struct _cache_table cache_table[] __cpuinitdata =
 	{ 0x4b, LVL_3,      8192 },	/* 16-way set assoc, 64 byte line size */
 	{ 0x4c, LVL_3,     12288 },	/* 12-way set assoc, 64 byte line size */
 	{ 0x4d, LVL_3,     16384 },	/* 16-way set assoc, 64 byte line size */
+	{ 0x4e, LVL_2,      6144 },	/* 24-way set assoc, 64 byte line size */
 	{ 0x60, LVL_1_DATA, 16 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x66, LVL_1_DATA, 8 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x67, LVL_1_DATA, 16 },	/* 4-way set assoc, sectored cache, 64 byte line size */

arch/x86/kernel/cpu/mcheck/k7.c

@@ -9,23 +9,23 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 
-#include <asm/processor.h> 
+#include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/msr.h>
 
 #include "mce.h"
 
 /* Machine Check Handler For AMD Athlon/Duron */
-static void k7_machine_check(struct pt_regs * regs, long error_code)
+static void k7_machine_check(struct pt_regs *regs, long error_code)
 {
-	int recover=1;
+	int recover = 1;
 	u32 alow, ahigh, high, low;
 	u32 mcgstl, mcgsth;
 	int i;
 
-	rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
+	rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 	if (mcgstl & (1<<0))	/* Recoverable ? */
-		recover=0;
+		recover = 0;
 
 	printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
 		smp_processor_id(), mcgsth, mcgstl);
@@ -60,12 +60,12 @@ static void k7_machine_check(struct pt_regs * regs, long error_code)
 	}
 
 	if (recover&2)
-		panic ("CPU context corrupt");
+		panic("CPU context corrupt");
 	if (recover&1)
-		panic ("Unable to continue");
-	printk (KERN_EMERG "Attempting to continue.\n");
+		panic("Unable to continue");
+	printk(KERN_EMERG "Attempting to continue.\n");
 	mcgstl &= ~(1<<2);
-	wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
+	wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 }
 
 
@@ -81,25 +81,25 @@ void amd_mcheck_init(struct cpuinfo_x86 *c)
 	machine_check_vector = k7_machine_check;
 	wmb();
 
-	printk (KERN_INFO "Intel machine check architecture supported.\n");
-	rdmsr (MSR_IA32_MCG_CAP, l, h);
+	printk(KERN_INFO "Intel machine check architecture supported.\n");
+	rdmsr(MSR_IA32_MCG_CAP, l, h);
 	if (l & (1<<8))	/* Control register present ? */
-		wrmsr (MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 	nr_mce_banks = l & 0xff;
 
 	/* Clear status for MC index 0 separately, we don't touch CTL,
 	 * as some K7 Athlons cause spurious MCEs when its enabled. */
 	if (boot_cpu_data.x86 == 6) {
-		wrmsr (MSR_IA32_MC0_STATUS, 0x0, 0x0);
+		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);
+	for (; i < nr_mce_banks; i++) {
+		wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
+		wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
 	}
 
-	set_in_cr4 (X86_CR4_MCE);
-	printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
+	set_in_cr4(X86_CR4_MCE);
+	printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
 		smp_processor_id());
 }

arch/x86/kernel/cpu/mcheck/mce_64.c

@@ -31,7 +31,7 @@
 #include <asm/idle.h>
 
 #define MISC_MCELOG_MINOR 227
-#define NR_BANKS 6
+#define NR_SYSFS_BANKS 6
 
 atomic_t mce_entry;
 
@@ -46,7 +46,7 @@ static int mce_dont_init;
  */
 static int tolerant = 1;
 static int banks;
-static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
+static unsigned long bank[NR_SYSFS_BANKS] = { [0 ... NR_SYSFS_BANKS-1] = ~0UL };
 static unsigned long notify_user;
 static int rip_msr;
 static int mce_bootlog = -1;
@@ -209,7 +209,7 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 	barrier();
 
 	for (i = 0; i < banks; i++) {
-		if (!bank[i])
+		if (i < NR_SYSFS_BANKS && !bank[i])
 			continue;
 
 		m.misc = 0;
@@ -444,9 +444,10 @@ static void mce_init(void *dummy)
 
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	banks = cap & 0xff;
-	if (banks > NR_BANKS) {
-		printk(KERN_INFO "MCE: warning: using only %d banks\n", banks);
-		banks = NR_BANKS;
+	if (banks > MCE_EXTENDED_BANK) {
+		banks = MCE_EXTENDED_BANK;
+		printk(KERN_INFO "MCE: warning: using only %d banks\n",
+		       MCE_EXTENDED_BANK);
 	}
 	/* Use accurate RIP reporting if available. */
 	if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9)
@@ -462,7 +463,11 @@ static void mce_init(void *dummy)
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 
 	for (i = 0; i < banks; i++) {
-		wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
+		if (i < NR_SYSFS_BANKS)
+			wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
+		else
+			wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL);
+
 		wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
 	}
 }
@@ -766,7 +771,10 @@ DEFINE_PER_CPU(struct sys_device, device_mce);
 	}								\
 	static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name);
 
-/* TBD should generate these dynamically based on number of available banks */
+/*
+ * TBD should generate these dynamically based on number of available banks.
+ * Have only 6 contol banks in /sysfs until then.
+ */
 ACCESSOR(bank0ctl,bank[0],mce_restart())
 ACCESSOR(bank1ctl,bank[1],mce_restart())
 ACCESSOR(bank2ctl,bank[2],mce_restart())

arch/x86/kernel/cpu/mcheck/p4.c

@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 
-#include <asm/processor.h> 
+#include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
@@ -32,12 +32,12 @@ struct intel_mce_extended_msrs {
 	/* u32 *reserved[]; */
 };
 
-static int mce_num_extended_msrs = 0;
+static int mce_num_extended_msrs;
 
 
 #ifdef CONFIG_X86_MCE_P4THERMAL
 static void unexpected_thermal_interrupt(struct pt_regs *regs)
-{	
+{
 	printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
 			smp_processor_id());
 	add_taint(TAINT_MACHINE_CHECK);
@@ -83,7 +83,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
 	 * be some SMM goo which handles it, so we can't even put a handler
 	 * since it might be delivered via SMI already -zwanem.
 	 */
-	rdmsr (MSR_IA32_MISC_ENABLE, l, h);
+	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
 	h = apic_read(APIC_LVTTHMR);
 	if ((l & (1<<3)) && (h & APIC_DM_SMI)) {
 		printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n",
@@ -91,7 +91,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
 		return; /* -EBUSY */
 	}
 
-	/* check whether a vector already exists, temporarily masked? */	
+	/* check whether a vector already exists, temporarily masked? */
 	if (h & APIC_VECTOR_MASK) {
 		printk(KERN_DEBUG "CPU%d: Thermal LVT vector (%#x) already "
 				"installed\n",
@@ -104,18 +104,18 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
 	h |= (APIC_DM_FIXED | APIC_LVT_MASKED);	/* we'll mask till we're ready */
 	apic_write_around(APIC_LVTTHMR, h);
 
-	rdmsr (MSR_IA32_THERM_INTERRUPT, l, h);
-	wrmsr (MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
+	rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
+	wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
 
 	/* ok we're good to go... */
 	vendor_thermal_interrupt = intel_thermal_interrupt;
-	
-	rdmsr (MSR_IA32_MISC_ENABLE, l, h);
-	wrmsr (MSR_IA32_MISC_ENABLE, l | (1<<3), h);
 
-	l = apic_read (APIC_LVTTHMR);
-	apic_write_around (APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
-	printk (KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu);
+	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+	wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
+
+	l = apic_read(APIC_LVTTHMR);
+	apic_write_around(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+	printk(KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu);
 
 	/* enable thermal throttle processing */
 	atomic_set(&therm_throt_en, 1);
@@ -129,28 +129,28 @@ static inline void intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
 {
 	u32 h;
 
-	rdmsr (MSR_IA32_MCG_EAX, r->eax, h);
-	rdmsr (MSR_IA32_MCG_EBX, r->ebx, h);
-	rdmsr (MSR_IA32_MCG_ECX, r->ecx, h);
-	rdmsr (MSR_IA32_MCG_EDX, r->edx, h);
-	rdmsr (MSR_IA32_MCG_ESI, r->esi, h);
-	rdmsr (MSR_IA32_MCG_EDI, r->edi, h);
-	rdmsr (MSR_IA32_MCG_EBP, r->ebp, h);
-	rdmsr (MSR_IA32_MCG_ESP, r->esp, h);
-	rdmsr (MSR_IA32_MCG_EFLAGS, r->eflags, h);
-	rdmsr (MSR_IA32_MCG_EIP, r->eip, h);
+	rdmsr(MSR_IA32_MCG_EAX, r->eax, h);
+	rdmsr(MSR_IA32_MCG_EBX, r->ebx, h);
+	rdmsr(MSR_IA32_MCG_ECX, r->ecx, h);
+	rdmsr(MSR_IA32_MCG_EDX, r->edx, h);
+	rdmsr(MSR_IA32_MCG_ESI, r->esi, h);
+	rdmsr(MSR_IA32_MCG_EDI, r->edi, h);
+	rdmsr(MSR_IA32_MCG_EBP, r->ebp, h);
+	rdmsr(MSR_IA32_MCG_ESP, r->esp, h);
+	rdmsr(MSR_IA32_MCG_EFLAGS, r->eflags, h);
+	rdmsr(MSR_IA32_MCG_EIP, r->eip, h);
 }
 
-static void intel_machine_check(struct pt_regs * regs, long error_code)
+static void intel_machine_check(struct pt_regs *regs, long error_code)
 {
-	int recover=1;
+	int recover = 1;
 	u32 alow, ahigh, high, low;
 	u32 mcgstl, mcgsth;
 	int i;
 
-	rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
+	rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 	if (mcgstl & (1<<0))	/* Recoverable ? */
-		recover=0;
+		recover = 0;
 
 	printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
 		smp_processor_id(), mcgsth, mcgstl);
@@ -191,20 +191,20 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
 	}
 
 	if (recover & 2)
-		panic ("CPU context corrupt");
+		panic("CPU context corrupt");
 	if (recover & 1)
-		panic ("Unable to continue");
+		panic("Unable to continue");
 
 	printk(KERN_EMERG "Attempting to continue.\n");
-	/* 
-	 * Do not clear the MSR_IA32_MCi_STATUS if the error is not 
+	/*
+	 * Do not clear the MSR_IA32_MCi_STATUS if the error is not
 	 * recoverable/continuable.This will allow BIOS to look at the MSRs
 	 * for errors if the OS could not log the error.
 	 */
-	for (i=0; i<nr_mce_banks; i++) {
+	for (i = 0; i < nr_mce_banks; i++) {
 		u32 msr;
 		msr = MSR_IA32_MC0_STATUS+i*4;
-		rdmsr (msr, low, high);
+		rdmsr(msr, low, high);
 		if (high&(1<<31)) {
 			/* Clear it */
 			wrmsr(msr, 0UL, 0UL);
@@ -214,7 +214,7 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
 		}
 	}
 	mcgstl &= ~(1<<2);
-	wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
+	wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 }
 
 
@@ -222,30 +222,30 @@ void intel_p4_mcheck_init(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
 	int i;
-	
+
 	machine_check_vector = intel_machine_check;
 	wmb();
 
-	printk (KERN_INFO "Intel machine check architecture supported.\n");
-	rdmsr (MSR_IA32_MCG_CAP, l, h);
+	printk(KERN_INFO "Intel machine check architecture supported.\n");
+	rdmsr(MSR_IA32_MCG_CAP, l, h);
 	if (l & (1<<8))	/* Control register present ? */
-		wrmsr (MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 	nr_mce_banks = l & 0xff;
 
-	for (i=0; i<nr_mce_banks; i++) {
-		wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
-		wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
+	for (i = 0; i < nr_mce_banks; i++) {
+		wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
+		wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
 	}
 
-	set_in_cr4 (X86_CR4_MCE);
-	printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
+	set_in_cr4(X86_CR4_MCE);
+	printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
 		smp_processor_id());
 
 	/* Check for P4/Xeon extended MCE MSRs */
-	rdmsr (MSR_IA32_MCG_CAP, l, h);
+	rdmsr(MSR_IA32_MCG_CAP, l, h);
 	if (l & (1<<9))	{/* MCG_EXT_P */
 		mce_num_extended_msrs = (l >> 16) & 0xff;
-		printk (KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)"
+		printk(KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)"
 				" available\n",
 			smp_processor_id(), mce_num_extended_msrs);
 

arch/x86/kernel/cpu/mtrr/generic.c

@@ -37,7 +37,7 @@ static struct fixed_range_block fixed_range_blocks[] = {
 static unsigned long smp_changes_mask;
 static struct mtrr_state mtrr_state = {};
 static int mtrr_state_set;
-static u64 tom2;
+u64 mtrr_tom2;
 
 #undef MODULE_PARAM_PREFIX
 #define MODULE_PARAM_PREFIX "mtrr."
@@ -139,8 +139,8 @@ u8 mtrr_type_lookup(u64 start, u64 end)
 		}
 	}
 
-	if (tom2) {
-		if (start >= (1ULL<<32) && (end < tom2))
+	if (mtrr_tom2) {
+		if (start >= (1ULL<<32) && (end < mtrr_tom2))
 			return MTRR_TYPE_WRBACK;
 	}
 
@@ -158,6 +158,20 @@ get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
 	rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi);
 }
 
+/*  fill the MSR pair relating to a var range  */
+void fill_mtrr_var_range(unsigned int index,
+		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi)
+{
+	struct mtrr_var_range *vr;
+
+	vr = mtrr_state.var_ranges;
+
+	vr[index].base_lo = base_lo;
+	vr[index].base_hi = base_hi;
+	vr[index].mask_lo = mask_lo;
+	vr[index].mask_hi = mask_hi;
+}
+
 static void
 get_fixed_ranges(mtrr_type * frs)
 {
@@ -213,13 +227,13 @@ void __init get_mtrr_state(void)
 	mtrr_state.enabled = (lo & 0xc00) >> 10;
 
 	if (amd_special_default_mtrr()) {
-		unsigned lo, hi;
+		unsigned low, high;
 		/* TOP_MEM2 */
-		rdmsr(MSR_K8_TOP_MEM2, lo, hi);
-		tom2 = hi;
-		tom2 <<= 32;
-		tom2 |= lo;
-		tom2 &= 0xffffff8000000ULL;
+		rdmsr(MSR_K8_TOP_MEM2, low, high);
+		mtrr_tom2 = high;
+		mtrr_tom2 <<= 32;
+		mtrr_tom2 |= low;
+		mtrr_tom2 &= 0xffffff800000ULL;
 	}
 	if (mtrr_show) {
 		int high_width;
@@ -251,9 +265,9 @@ void __init get_mtrr_state(void)
 			else
 				printk(KERN_INFO "MTRR %u disabled\n", i);
 		}
-		if (tom2) {
+		if (mtrr_tom2) {
 			printk(KERN_INFO "TOM2: %016llx aka %lldM\n",
-					  tom2, tom2>>20);
+					  mtrr_tom2, mtrr_tom2>>20);
 		}
 	}
 	mtrr_state_set = 1;
@@ -328,7 +342,7 @@ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords)
 
 	if (lo != msrwords[0] || hi != msrwords[1]) {
 		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
-		    boot_cpu_data.x86 == 15 &&
+		    (boot_cpu_data.x86 >= 0x0f && boot_cpu_data.x86 <= 0x11) &&
 		    ((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK))
 			k8_enable_fixed_iorrs();
 		mtrr_wrmsr(msr, msrwords[0], msrwords[1]);

arch/x86/kernel/cpu/mtrr/main.c

@@ -37,6 +37,7 @@
 #include <linux/smp.h>
 #include <linux/cpu.h>
 #include <linux/mutex.h>
+#include <linux/sort.h>
 
 #include <asm/e820.h>
 #include <asm/mtrr.h>
@@ -609,6 +610,787 @@ static struct sysdev_driver mtrr_sysdev_driver = {
 	.resume		= mtrr_restore,
 };
 
+/* should be related to MTRR_VAR_RANGES nums */
+#define RANGE_NUM 256
+
+struct res_range {
+	unsigned long start;
+	unsigned long end;
+};
+
+static int __init
+add_range(struct res_range *range, int nr_range, unsigned long start,
+			      unsigned long end)
+{
+	/* out of slots */
+	if (nr_range >= RANGE_NUM)
+		return nr_range;
+
+	range[nr_range].start = start;
+	range[nr_range].end = end;
+
+	nr_range++;
+
+	return nr_range;
+}
+
+static int __init
+add_range_with_merge(struct res_range *range, int nr_range, unsigned long start,
+			      unsigned long end)
+{
+	int i;
+
+	/* try to merge it with old one */
+	for (i = 0; i < nr_range; i++) {
+		unsigned long final_start, final_end;
+		unsigned long common_start, common_end;
+
+		if (!range[i].end)
+			continue;
+
+		common_start = max(range[i].start, start);
+		common_end = min(range[i].end, end);
+		if (common_start > common_end + 1)
+			continue;
+
+		final_start = min(range[i].start, start);
+		final_end = max(range[i].end, end);
+
+		range[i].start = final_start;
+		range[i].end =  final_end;
+		return nr_range;
+	}
+
+	/* need to add that */
+	return add_range(range, nr_range, start, end);
+}
+
+static void __init
+subtract_range(struct res_range *range, unsigned long start, unsigned long end)
+{
+	int i, j;
+
+	for (j = 0; j < RANGE_NUM; j++) {
+		if (!range[j].end)
+			continue;
+
+		if (start <= range[j].start && end >= range[j].end) {
+			range[j].start = 0;
+			range[j].end = 0;
+			continue;
+		}
+
+		if (start <= range[j].start && end < range[j].end &&
+		    range[j].start < end + 1) {
+			range[j].start = end + 1;
+			continue;
+		}
+
+
+		if (start > range[j].start && end >= range[j].end &&
+		    range[j].end > start - 1) {
+			range[j].end = start - 1;
+			continue;
+		}
+
+		if (start > range[j].start && end < range[j].end) {
+			/* find the new spare */
+			for (i = 0; i < RANGE_NUM; i++) {
+				if (range[i].end == 0)
+					break;
+			}
+			if (i < RANGE_NUM) {
+				range[i].end = range[j].end;
+				range[i].start = end + 1;
+			} else {
+				printk(KERN_ERR "run of slot in ranges\n");
+			}
+			range[j].end = start - 1;
+			continue;
+		}
+	}
+}
+
+static int __init cmp_range(const void *x1, const void *x2)
+{
+	const struct res_range *r1 = x1;
+	const struct res_range *r2 = x2;
+	long start1, start2;
+
+	start1 = r1->start;
+	start2 = r2->start;
+
+	return start1 - start2;
+}
+
+struct var_mtrr_range_state {
+	unsigned long base_pfn;
+	unsigned long size_pfn;
+	mtrr_type type;
+};
+
+struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
+static int __initdata debug_print;
+
+static int __init
+x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
+		       unsigned long extra_remove_base,
+		       unsigned long extra_remove_size)
+{
+	unsigned long i, base, size;
+	mtrr_type type;
+
+	for (i = 0; i < num_var_ranges; i++) {
+		type = range_state[i].type;
+		if (type != MTRR_TYPE_WRBACK)
+			continue;
+		base = range_state[i].base_pfn;
+		size = range_state[i].size_pfn;
+		nr_range = add_range_with_merge(range, nr_range, base,
+						base + size - 1);
+	}
+	if (debug_print) {
+		printk(KERN_DEBUG "After WB checking\n");
+		for (i = 0; i < nr_range; i++)
+			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+				 range[i].start, range[i].end + 1);
+	}
+
+	/* take out UC ranges */
+	for (i = 0; i < num_var_ranges; i++) {
+		type = range_state[i].type;
+		if (type != MTRR_TYPE_UNCACHABLE)
+			continue;
+		size = range_state[i].size_pfn;
+		if (!size)
+			continue;
+		base = range_state[i].base_pfn;
+		subtract_range(range, base, base + size - 1);
+	}
+	if (extra_remove_size)
+		subtract_range(range, extra_remove_base,
+				 extra_remove_base + extra_remove_size  - 1);
+
+	/* get new range num */
+	nr_range = 0;
+	for (i = 0; i < RANGE_NUM; i++) {
+		if (!range[i].end)
+			continue;
+		nr_range++;
+	}
+	if  (debug_print) {
+		printk(KERN_DEBUG "After UC checking\n");
+		for (i = 0; i < nr_range; i++)
+			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+				 range[i].start, range[i].end + 1);
+	}
+
+	/* sort the ranges */
+	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+	if  (debug_print) {
+		printk(KERN_DEBUG "After sorting\n");
+		for (i = 0; i < nr_range; i++)
+			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+				 range[i].start, range[i].end + 1);
+	}
+
+	/* clear those is not used */
+	for (i = nr_range; i < RANGE_NUM; i++)
+		memset(&range[i], 0, sizeof(range[i]));
+
+	return nr_range;
+}
+
+static struct res_range __initdata range[RANGE_NUM];
+
+#ifdef CONFIG_MTRR_SANITIZER
+
+static unsigned long __init sum_ranges(struct res_range *range, int nr_range)
+{
+	unsigned long sum;
+	int i;
+
+	sum = 0;
+	for (i = 0; i < nr_range; i++)
+		sum += range[i].end + 1 - range[i].start;
+
+	return sum;
+}
+
+static int enable_mtrr_cleanup __initdata =
+	CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT;
+
+static int __init disable_mtrr_cleanup_setup(char *str)
+{
+	if (enable_mtrr_cleanup != -1)
+		enable_mtrr_cleanup = 0;
+	return 0;
+}
+early_param("disable_mtrr_cleanup", disable_mtrr_cleanup_setup);
+
+static int __init enable_mtrr_cleanup_setup(char *str)
+{
+	if (enable_mtrr_cleanup != -1)
+		enable_mtrr_cleanup = 1;
+	return 0;
+}
+early_param("enble_mtrr_cleanup", enable_mtrr_cleanup_setup);
+
+struct var_mtrr_state {
+	unsigned long	range_startk;
+	unsigned long	range_sizek;
+	unsigned long	chunk_sizek;
+	unsigned long	gran_sizek;
+	unsigned int	reg;
+};
+
+static void __init
+set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
+		unsigned char type, unsigned int address_bits)
+{
+	u32 base_lo, base_hi, mask_lo, mask_hi;
+	u64 base, mask;
+
+	if (!sizek) {
+		fill_mtrr_var_range(reg, 0, 0, 0, 0);
+		return;
+	}
+
+	mask = (1ULL << address_bits) - 1;
+	mask &= ~((((u64)sizek) << 10) - 1);
+
+	base  = ((u64)basek) << 10;
+
+	base |= type;
+	mask |= 0x800;
+
+	base_lo = base & ((1ULL<<32) - 1);
+	base_hi = base >> 32;
+
+	mask_lo = mask & ((1ULL<<32) - 1);
+	mask_hi = mask >> 32;
+
+	fill_mtrr_var_range(reg, base_lo, base_hi, mask_lo, mask_hi);
+}
+
+static void __init
+save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
+		unsigned char type)
+{
+	range_state[reg].base_pfn = basek >> (PAGE_SHIFT - 10);
+	range_state[reg].size_pfn = sizek >> (PAGE_SHIFT - 10);
+	range_state[reg].type = type;
+}
+
+static void __init
+set_var_mtrr_all(unsigned int address_bits)
+{
+	unsigned long basek, sizek;
+	unsigned char type;
+	unsigned int reg;
+
+	for (reg = 0; reg < num_var_ranges; reg++) {
+		basek = range_state[reg].base_pfn << (PAGE_SHIFT - 10);
+		sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10);
+		type = range_state[reg].type;
+
+		set_var_mtrr(reg, basek, sizek, type, address_bits);
+	}
+}
+
+static unsigned int __init
+range_to_mtrr(unsigned int reg, unsigned long range_startk,
+	      unsigned long range_sizek, unsigned char type)
+{
+	if (!range_sizek || (reg >= num_var_ranges))
+		return reg;
+
+	while (range_sizek) {
+		unsigned long max_align, align;
+		unsigned long sizek;
+
+		/* Compute the maximum size I can make a range */
+		if (range_startk)
+			max_align = ffs(range_startk) - 1;
+		else
+			max_align = 32;
+		align = fls(range_sizek) - 1;
+		if (align > max_align)
+			align = max_align;
+
+		sizek = 1 << align;
+		if (debug_print)
+			printk(KERN_DEBUG "Setting variable MTRR %d, "
+				"base: %ldMB, range: %ldMB, type %s\n",
+				reg, range_startk >> 10, sizek >> 10,
+				(type == MTRR_TYPE_UNCACHABLE)?"UC":
+				    ((type == MTRR_TYPE_WRBACK)?"WB":"Other")
+				);
+		save_var_mtrr(reg++, range_startk, sizek, type);
+		range_startk += sizek;
+		range_sizek -= sizek;
+		if (reg >= num_var_ranges)
+			break;
+	}
+	return reg;
+}
+
+static unsigned __init
+range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
+			unsigned long sizek)
+{
+	unsigned long hole_basek, hole_sizek;
+	unsigned long second_basek, second_sizek;
+	unsigned long range0_basek, range0_sizek;
+	unsigned long range_basek, range_sizek;
+	unsigned long chunk_sizek;
+	unsigned long gran_sizek;
+
+	hole_basek = 0;
+	hole_sizek = 0;
+	second_basek = 0;
+	second_sizek = 0;
+	chunk_sizek = state->chunk_sizek;
+	gran_sizek = state->gran_sizek;
+
+	/* align with gran size, prevent small block used up MTRRs */
+	range_basek = ALIGN(state->range_startk, gran_sizek);
+	if ((range_basek > basek) && basek)
+		return second_sizek;
+	state->range_sizek -= (range_basek - state->range_startk);
+	range_sizek = ALIGN(state->range_sizek, gran_sizek);
+
+	while (range_sizek > state->range_sizek) {
+		range_sizek -= gran_sizek;
+		if (!range_sizek)
+			return 0;
+	}
+	state->range_sizek = range_sizek;
+
+	/* try to append some small hole */
+	range0_basek = state->range_startk;
+	range0_sizek = ALIGN(state->range_sizek, chunk_sizek);
+	if (range0_sizek == state->range_sizek) {
+		if (debug_print)
+			printk(KERN_DEBUG "rangeX: %016lx - %016lx\n",
+				range0_basek<<10,
+				(range0_basek + state->range_sizek)<<10);
+		state->reg = range_to_mtrr(state->reg, range0_basek,
+				state->range_sizek, MTRR_TYPE_WRBACK);
+		return 0;
+	}
+
+	range0_sizek -= chunk_sizek;
+	if (range0_sizek && sizek) {
+	    while (range0_basek + range0_sizek > (basek + sizek)) {
+		range0_sizek -= chunk_sizek;
+		if (!range0_sizek)
+			break;
+	    }
+	}
+
+	if (range0_sizek) {
+		if (debug_print)
+			printk(KERN_DEBUG "range0: %016lx - %016lx\n",
+				range0_basek<<10,
+				(range0_basek + range0_sizek)<<10);
+		state->reg = range_to_mtrr(state->reg, range0_basek,
+				range0_sizek, MTRR_TYPE_WRBACK);
+
+	}
+
+	range_basek = range0_basek + range0_sizek;
+	range_sizek = chunk_sizek;
+
+	if (range_basek + range_sizek > basek &&
+	    range_basek + range_sizek <= (basek + sizek)) {
+		/* one hole */
+		second_basek = basek;
+		second_sizek = range_basek + range_sizek - basek;
+	}
+
+	/* if last piece, only could one hole near end */
+	if ((second_basek || !basek) &&
+	    range_sizek - (state->range_sizek - range0_sizek) - second_sizek <
+	    (chunk_sizek >> 1)) {
+		/*
+		 * one hole in middle (second_sizek is 0) or at end
+		 * (second_sizek is 0 )
+		 */
+		hole_sizek = range_sizek - (state->range_sizek - range0_sizek)
+				 - second_sizek;
+		hole_basek = range_basek + range_sizek - hole_sizek
+				 - second_sizek;
+	} else {
+		/* fallback for big hole, or several holes */
+		range_sizek = state->range_sizek - range0_sizek;
+		second_basek = 0;
+		second_sizek = 0;
+	}
+
+	if (debug_print)
+		printk(KERN_DEBUG "range: %016lx - %016lx\n", range_basek<<10,
+			 (range_basek + range_sizek)<<10);
+	state->reg = range_to_mtrr(state->reg, range_basek, range_sizek,
+					 MTRR_TYPE_WRBACK);
+	if (hole_sizek) {
+		if (debug_print)
+			printk(KERN_DEBUG "hole: %016lx - %016lx\n",
+				 hole_basek<<10, (hole_basek + hole_sizek)<<10);
+		state->reg = range_to_mtrr(state->reg, hole_basek, hole_sizek,
+						 MTRR_TYPE_UNCACHABLE);
+
+	}
+
+	return second_sizek;
+}
+
+static void __init
+set_var_mtrr_range(struct var_mtrr_state *state, unsigned long base_pfn,
+		   unsigned long size_pfn)
+{
+	unsigned long basek, sizek;
+	unsigned long second_sizek = 0;
+
+	if (state->reg >= num_var_ranges)
+		return;
+
+	basek = base_pfn << (PAGE_SHIFT - 10);
+	sizek = size_pfn << (PAGE_SHIFT - 10);
+
+	/* See if I can merge with the last range */
+	if ((basek <= 1024) ||
+	    (state->range_startk + state->range_sizek == basek)) {
+		unsigned long endk = basek + sizek;
+		state->range_sizek = endk - state->range_startk;
+		return;
+	}
+	/* Write the range mtrrs */
+	if (state->range_sizek != 0)
+		second_sizek = range_to_mtrr_with_hole(state, basek, sizek);
+
+	/* Allocate an msr */
+	state->range_startk = basek + second_sizek;
+	state->range_sizek  = sizek - second_sizek;
+}
+
+/* mininum size of mtrr block that can take hole */
+static u64 mtrr_chunk_size __initdata = (256ULL<<20);
+
+static int __init parse_mtrr_chunk_size_opt(char *p)
+{
+	if (!p)
+		return -EINVAL;
+	mtrr_chunk_size = memparse(p, &p);
+	return 0;
+}
+early_param("mtrr_chunk_size", parse_mtrr_chunk_size_opt);
+
+/* granity of mtrr of block */
+static u64 mtrr_gran_size __initdata;
+
+static int __init parse_mtrr_gran_size_opt(char *p)
+{
+	if (!p)
+		return -EINVAL;
+	mtrr_gran_size = memparse(p, &p);
+	return 0;
+}
+early_param("mtrr_gran_size", parse_mtrr_gran_size_opt);
+
+static int nr_mtrr_spare_reg __initdata =
+				 CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT;
+
+static int __init parse_mtrr_spare_reg(char *arg)
+{
+	if (arg)
+		nr_mtrr_spare_reg = simple_strtoul(arg, NULL, 0);
+	return 0;
+}
+
+early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg);
+
+static int __init
+x86_setup_var_mtrrs(struct res_range *range, int nr_range,
+		    u64 chunk_size, u64 gran_size)
+{
+	struct var_mtrr_state var_state;
+	int i;
+	int num_reg;
+
+	var_state.range_startk	= 0;
+	var_state.range_sizek	= 0;
+	var_state.reg		= 0;
+	var_state.chunk_sizek	= chunk_size >> 10;
+	var_state.gran_sizek	= gran_size >> 10;
+
+	memset(range_state, 0, sizeof(range_state));
+
+	/* Write the range etc */
+	for (i = 0; i < nr_range; i++)
+		set_var_mtrr_range(&var_state, range[i].start,
+				   range[i].end - range[i].start + 1);
+
+	/* Write the last range */
+	if (var_state.range_sizek != 0)
+		range_to_mtrr_with_hole(&var_state, 0, 0);
+
+	num_reg = var_state.reg;
+	/* Clear out the extra MTRR's */
+	while (var_state.reg < num_var_ranges) {
+		save_var_mtrr(var_state.reg, 0, 0, 0);
+		var_state.reg++;
+	}
+
+	return num_reg;
+}
+
+struct mtrr_cleanup_result {
+	unsigned long gran_sizek;
+	unsigned long chunk_sizek;
+	unsigned long lose_cover_sizek;
+	unsigned int num_reg;
+	int bad;
+};
+
+/*
+ * gran_size: 1M, 2M, ..., 2G
+ * chunk size: gran_size, ..., 4G
+ * so we need (2+13)*6
+ */
+#define NUM_RESULT	90
+#define PSHIFT		(PAGE_SHIFT - 10)
+
+static struct mtrr_cleanup_result __initdata result[NUM_RESULT];
+static struct res_range __initdata range_new[RANGE_NUM];
+static unsigned long __initdata min_loss_pfn[RANGE_NUM];
+
+static int __init mtrr_cleanup(unsigned address_bits)
+{
+	unsigned long extra_remove_base, extra_remove_size;
+	unsigned long i, base, size, def, dummy;
+	mtrr_type type;
+	int nr_range, nr_range_new;
+	u64 chunk_size, gran_size;
+	unsigned long range_sums, range_sums_new;
+	int index_good;
+	int num_reg_good;
+
+	/* extra one for all 0 */
+	int num[MTRR_NUM_TYPES + 1];
+
+	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
+		return 0;
+	rdmsr(MTRRdefType_MSR, def, dummy);
+	def &= 0xff;
+	if (def != MTRR_TYPE_UNCACHABLE)
+		return 0;
+
+	/* get it and store it aside */
+	memset(range_state, 0, sizeof(range_state));
+	for (i = 0; i < num_var_ranges; i++) {
+		mtrr_if->get(i, &base, &size, &type);
+		range_state[i].base_pfn = base;
+		range_state[i].size_pfn = size;
+		range_state[i].type = type;
+	}
+
+	/* check entries number */
+	memset(num, 0, sizeof(num));
+	for (i = 0; i < num_var_ranges; i++) {
+		type = range_state[i].type;
+		size = range_state[i].size_pfn;
+		if (type >= MTRR_NUM_TYPES)
+			continue;
+		if (!size)
+			type = MTRR_NUM_TYPES;
+		num[type]++;
+	}
+
+	/* check if we got UC entries */
+	if (!num[MTRR_TYPE_UNCACHABLE])
+		return 0;
+
+	/* check if we only had WB and UC */
+	if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] !=
+		num_var_ranges - num[MTRR_NUM_TYPES])
+		return 0;
+
+	memset(range, 0, sizeof(range));
+	extra_remove_size = 0;
+	if (mtrr_tom2) {
+		extra_remove_base = 1 << (32 - PAGE_SHIFT);
+		extra_remove_size =
+			(mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base;
+	}
+	nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base,
+					  extra_remove_size);
+	range_sums = sum_ranges(range, nr_range);
+	printk(KERN_INFO "total RAM coverred: %ldM\n",
+	       range_sums >> (20 - PAGE_SHIFT));
+
+	if (mtrr_chunk_size && mtrr_gran_size) {
+		int num_reg;
+
+		debug_print = 1;
+		/* convert ranges to var ranges state */
+		num_reg = x86_setup_var_mtrrs(range, nr_range, mtrr_chunk_size,
+					      mtrr_gran_size);
+
+		/* we got new setting in range_state, check it */
+		memset(range_new, 0, sizeof(range_new));
+		nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
+						      extra_remove_base,
+						      extra_remove_size);
+		range_sums_new = sum_ranges(range_new, nr_range_new);
+
+		i = 0;
+		result[i].chunk_sizek = mtrr_chunk_size >> 10;
+		result[i].gran_sizek = mtrr_gran_size >> 10;
+		result[i].num_reg = num_reg;
+		if (range_sums < range_sums_new) {
+			result[i].lose_cover_sizek =
+				(range_sums_new - range_sums) << PSHIFT;
+			result[i].bad = 1;
+		} else
+			result[i].lose_cover_sizek =
+				(range_sums - range_sums_new) << PSHIFT;
+
+		printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t",
+			 result[i].bad?"*BAD*":" ", result[i].gran_sizek >> 10,
+			 result[i].chunk_sizek >> 10);
+		printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ldM \n",
+			 result[i].num_reg, result[i].bad?"-":"",
+			 result[i].lose_cover_sizek >> 10);
+		if (!result[i].bad) {
+			set_var_mtrr_all(address_bits);
+			return 1;
+		}
+		printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
+		       "will find optimal one\n");
+		debug_print = 0;
+		memset(result, 0, sizeof(result[0]));
+	}
+
+	i = 0;
+	memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn));
+	memset(result, 0, sizeof(result));
+	for (gran_size = (1ULL<<20); gran_size < (1ULL<<32); gran_size <<= 1) {
+		for (chunk_size = gran_size; chunk_size < (1ULL<<33);
+		     chunk_size <<= 1) {
+			int num_reg;
+
+			if (debug_print)
+				printk(KERN_INFO
+			       "\ngran_size: %lldM   chunk_size_size: %lldM\n",
+				       gran_size >> 20, chunk_size >> 20);
+			if (i >= NUM_RESULT)
+				continue;
+
+			/* convert ranges to var ranges state */
+			num_reg = x86_setup_var_mtrrs(range, nr_range,
+							 chunk_size, gran_size);
+
+			/* we got new setting in range_state, check it */
+			memset(range_new, 0, sizeof(range_new));
+			nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
+					 extra_remove_base, extra_remove_size);
+			range_sums_new = sum_ranges(range_new, nr_range_new);
+
+			result[i].chunk_sizek = chunk_size >> 10;
+			result[i].gran_sizek = gran_size >> 10;
+			result[i].num_reg = num_reg;
+			if (range_sums < range_sums_new) {
+				result[i].lose_cover_sizek =
+					(range_sums_new - range_sums) << PSHIFT;
+				result[i].bad = 1;
+			} else
+				result[i].lose_cover_sizek =
+					(range_sums - range_sums_new) << PSHIFT;
+
+			/* double check it */
+			if (!result[i].bad && !result[i].lose_cover_sizek) {
+				if (nr_range_new != nr_range ||
+					memcmp(range, range_new, sizeof(range)))
+						result[i].bad = 1;
+			}
+
+			if (!result[i].bad && (range_sums - range_sums_new <
+					       min_loss_pfn[num_reg])) {
+				min_loss_pfn[num_reg] =
+					range_sums - range_sums_new;
+			}
+			i++;
+		}
+	}
+
+	/* print out all */
+	for (i = 0; i < NUM_RESULT; i++) {
+		printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t",
+		       result[i].bad?"*BAD* ":" ", result[i].gran_sizek >> 10,
+		       result[i].chunk_sizek >> 10);
+		printk(KERN_CONT "num_reg: %d \tlose RAM: %s%ldM\n",
+		       result[i].num_reg, result[i].bad?"-":"",
+		       result[i].lose_cover_sizek >> 10);
+	}
+
+	/* try to find the optimal index */
+	if (nr_mtrr_spare_reg >= num_var_ranges)
+		nr_mtrr_spare_reg = num_var_ranges - 1;
+	num_reg_good = -1;
+	for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
+		if (!min_loss_pfn[i]) {
+			num_reg_good = i;
+			break;
+		}
+	}
+
+	index_good = -1;
+	if (num_reg_good != -1) {
+		for (i = 0; i < NUM_RESULT; i++) {
+			if (!result[i].bad &&
+			    result[i].num_reg == num_reg_good &&
+			    !result[i].lose_cover_sizek) {
+				index_good = i;
+				break;
+			}
+		}
+	}
+
+	if (index_good != -1) {
+		printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
+		i = index_good;
+		printk(KERN_INFO "gran_size: %ldM \tchunk_size: %ldM \t",
+				result[i].gran_sizek >> 10,
+				result[i].chunk_sizek >> 10);
+		printk(KERN_CONT "num_reg: %d \tlose RAM: %ldM\n",
+				result[i].num_reg,
+				result[i].lose_cover_sizek >> 10);
+		/* convert ranges to var ranges state */
+		chunk_size = result[i].chunk_sizek;
+		chunk_size <<= 10;
+		gran_size = result[i].gran_sizek;
+		gran_size <<= 10;
+		debug_print = 1;
+		x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
+		set_var_mtrr_all(address_bits);
+		return 1;
+	}
+
+	printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n");
+	printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n");
+
+	return 0;
+}
+#else
+static int __init mtrr_cleanup(unsigned address_bits)
+{
+	return 0;
+}
+#endif
+
+static int __initdata changed_by_mtrr_cleanup;
+
 static int disable_mtrr_trim;
 
 static int __init disable_mtrr_trim_setup(char *str)
@@ -648,6 +1430,19 @@ int __init amd_special_default_mtrr(void)
 	return 0;
 }
 
+static u64 __init real_trim_memory(unsigned long start_pfn,
+				   unsigned long limit_pfn)
+{
+	u64 trim_start, trim_size;
+	trim_start = start_pfn;
+	trim_start <<= PAGE_SHIFT;
+	trim_size = limit_pfn;
+	trim_size <<= PAGE_SHIFT;
+	trim_size -= trim_start;
+
+	return e820_update_range(trim_start, trim_size, E820_RAM,
+				E820_RESERVED);
+}
 /**
  * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs
  * @end_pfn: ending page frame number
@@ -663,8 +1458,11 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 {
 	unsigned long i, base, size, highest_pfn = 0, def, dummy;
 	mtrr_type type;
-	u64 trim_start, trim_size;
+	int nr_range;
+	u64 total_trim_size;
 
+	/* extra one for all 0 */
+	int num[MTRR_NUM_TYPES + 1];
 	/*
 	 * Make sure we only trim uncachable memory on machines that
 	 * support the Intel MTRR architecture:
@@ -676,14 +1474,22 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 	if (def != MTRR_TYPE_UNCACHABLE)
 		return 0;
 
-	if (amd_special_default_mtrr())
-		return 0;
+	/* get it and store it aside */
+	memset(range_state, 0, sizeof(range_state));
+	for (i = 0; i < num_var_ranges; i++) {
+		mtrr_if->get(i, &base, &size, &type);
+		range_state[i].base_pfn = base;
+		range_state[i].size_pfn = size;
+		range_state[i].type = type;
+	}
 
 	/* Find highest cached pfn */
 	for (i = 0; i < num_var_ranges; i++) {
-		mtrr_if->get(i, &base, &size, &type);
+		type = range_state[i].type;
 		if (type != MTRR_TYPE_WRBACK)
 			continue;
+		base = range_state[i].base_pfn;
+		size = range_state[i].size_pfn;
 		if (highest_pfn < base + size)
 			highest_pfn = base + size;
 	}
@@ -698,22 +1504,65 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 		return 0;
 	}
 
-	if (highest_pfn < end_pfn) {
+	/* check entries number */
+	memset(num, 0, sizeof(num));
+	for (i = 0; i < num_var_ranges; i++) {
+		type = range_state[i].type;
+		if (type >= MTRR_NUM_TYPES)
+			continue;
+		size = range_state[i].size_pfn;
+		if (!size)
+			type = MTRR_NUM_TYPES;
+		num[type]++;
+	}
+
+	/* no entry for WB? */
+	if (!num[MTRR_TYPE_WRBACK])
+		return 0;
+
+	/* check if we only had WB and UC */
+	if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] !=
+		num_var_ranges - num[MTRR_NUM_TYPES])
+		return 0;
+
+	memset(range, 0, sizeof(range));
+	nr_range = 0;
+	if (mtrr_tom2) {
+		range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT));
+		range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1;
+		if (highest_pfn < range[nr_range].end + 1)
+			highest_pfn = range[nr_range].end + 1;
+		nr_range++;
+	}
+	nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0);
+
+	total_trim_size = 0;
+	/* check the head */
+	if (range[0].start)
+		total_trim_size += real_trim_memory(0, range[0].start);
+	/* check the holes */
+	for (i = 0; i < nr_range - 1; i++) {
+		if (range[i].end + 1 < range[i+1].start)
+			total_trim_size += real_trim_memory(range[i].end + 1,
+							    range[i+1].start);
+	}
+	/* check the top */
+	i = nr_range - 1;
+	if (range[i].end + 1 < end_pfn)
+		total_trim_size += real_trim_memory(range[i].end + 1,
+							 end_pfn);
+
+	if (total_trim_size) {
 		printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover"
-			" all of memory, losing %luMB of RAM.\n",
-			(end_pfn - highest_pfn) >> (20 - PAGE_SHIFT));
+			" all of memory, losing %lluMB of RAM.\n",
+			total_trim_size >> 20);
 
-		WARN_ON(1);
+		if (!changed_by_mtrr_cleanup)
+			WARN_ON(1);
 
 		printk(KERN_INFO "update e820 for mtrr\n");
-		trim_start = highest_pfn;
-		trim_start <<= PAGE_SHIFT;
-		trim_size = end_pfn;
-		trim_size <<= PAGE_SHIFT;
-		trim_size -= trim_start;
-		update_memory_range(trim_start, trim_size, E820_RAM,
-					E820_RESERVED);
 		update_e820();
+
 		return 1;
 	}
 
@@ -729,18 +1578,21 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
  */
 void __init mtrr_bp_init(void)
 {
+	u32 phys_addr;
 	init_ifs();
 
+	phys_addr = 32;
+
 	if (cpu_has_mtrr) {
 		mtrr_if = &generic_mtrr_ops;
 		size_or_mask = 0xff000000;	/* 36 bits */
 		size_and_mask = 0x00f00000;
+		phys_addr = 36;
 
 		/* This is an AMD specific MSR, but we assume(hope?) that
 		   Intel will implement it to when they extend the address
 		   bus of the Xeon. */
 		if (cpuid_eax(0x80000000) >= 0x80000008) {
-			u32 phys_addr;
 			phys_addr = cpuid_eax(0x80000008) & 0xff;
 			/* CPUID workaround for Intel 0F33/0F34 CPU */
 			if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
@@ -758,6 +1610,7 @@ void __init mtrr_bp_init(void)
 			   don't support PAE */
 			size_or_mask = 0xfff00000;	/* 32 bits */
 			size_and_mask = 0;
+			phys_addr = 32;
 		}
 	} else {
 		switch (boot_cpu_data.x86_vendor) {
@@ -791,8 +1644,15 @@ void __init mtrr_bp_init(void)
 	if (mtrr_if) {
 		set_num_var_ranges();
 		init_table();
-		if (use_intel())
+		if (use_intel()) {
 			get_mtrr_state();
+
+			if (mtrr_cleanup(phys_addr)) {
+				changed_by_mtrr_cleanup = 1;
+				mtrr_if->set_all();
+			}
+
+		}
 	}
 }
 
@@ -829,9 +1689,10 @@ static int __init mtrr_init_finialize(void)
 {
 	if (!mtrr_if)
 		return 0;
-	if (use_intel())
-		mtrr_state_warn();
-	else {
+	if (use_intel()) {
+		if (!changed_by_mtrr_cleanup)
+			mtrr_state_warn();
+	} else {
 		/* The CPUs haven't MTRR and seem to not support SMP. They have
 		 * specific drivers, we use a tricky method to support
 		 * suspend/resume for them.

arch/x86/kernel/cpu/mtrr/mtrr.h

@@ -81,6 +81,8 @@ void set_mtrr_done(struct set_mtrr_context *ctxt);
 void set_mtrr_cache_disable(struct set_mtrr_context *ctxt);
 void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
 
+void fill_mtrr_var_range(unsigned int index,
+		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
 void get_mtrr_state(void);
 
 extern void set_mtrr_ops(struct mtrr_ops * ops);
@@ -92,6 +94,7 @@ extern struct mtrr_ops * mtrr_if;
 #define use_intel()	(mtrr_if && mtrr_if->use_intel_if == 1)
 
 extern unsigned int num_var_ranges;
+extern u64 mtrr_tom2;
 
 void mtrr_state_warn(void);
 const char *mtrr_attrib_to_str(int x);

arch/x86/kernel/cpu/perfctr-watchdog.c

@@ -1,11 +1,15 @@
-/* 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 */
+/*
+ * 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>
@@ -36,12 +40,16 @@ struct wd_ops {
 
 static const 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)
+/*
+ * 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:
+/*
+ * 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
@@ -73,8 +81,10 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 	return 0;
 }
 
-/* converts an msr to an appropriate reservation bit */
-/* returns the bit offset of the event selection register */
+/*
+ * 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)
 {
 	/* returns the bit offset of the event selection register */
@@ -114,6 +124,7 @@ int avail_to_resrv_perfctr_nmi(unsigned int msr)
 
 	return (!test_bit(counter, perfctr_nmi_owner));
 }
+EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
 
 int reserve_perfctr_nmi(unsigned int msr)
 {
@@ -128,6 +139,7 @@ int reserve_perfctr_nmi(unsigned int msr)
 		return 1;
 	return 0;
 }
+EXPORT_SYMBOL(reserve_perfctr_nmi);
 
 void release_perfctr_nmi(unsigned int msr)
 {
@@ -140,6 +152,7 @@ void release_perfctr_nmi(unsigned int msr)
 
 	clear_bit(counter, perfctr_nmi_owner);
 }
+EXPORT_SYMBOL(release_perfctr_nmi);
 
 int reserve_evntsel_nmi(unsigned int msr)
 {
@@ -154,6 +167,7 @@ int reserve_evntsel_nmi(unsigned int msr)
 		return 1;
 	return 0;
 }
+EXPORT_SYMBOL(reserve_evntsel_nmi);
 
 void release_evntsel_nmi(unsigned int msr)
 {
@@ -166,11 +180,6 @@ void release_evntsel_nmi(unsigned int msr)
 
 	clear_bit(counter, evntsel_nmi_owner);
 }
-
-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)
@@ -181,7 +190,9 @@ void disable_lapic_nmi_watchdog(void)
 		return;
 
 	on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);
-	wd_ops->unreserve();
+
+	if (wd_ops)
+		wd_ops->unreserve();
 
 	BUG_ON(atomic_read(&nmi_active) != 0);
 }
@@ -232,8 +243,8 @@ static unsigned int adjust_for_32bit_ctr(unsigned int hz)
 	return retval;
 }
 
-static void
-write_watchdog_counter(unsigned int perfctr_msr, const char *descr, unsigned nmi_hz)
+static void write_watchdog_counter(unsigned int perfctr_msr,
+				const char *descr, unsigned nmi_hz)
 {
 	u64 count = (u64)cpu_khz * 1000;
 
@@ -244,7 +255,7 @@ write_watchdog_counter(unsigned int perfctr_msr, const char *descr, unsigned nmi
 }
 
 static void write_watchdog_counter32(unsigned int perfctr_msr,
-		const char *descr, unsigned nmi_hz)
+				const char *descr, unsigned nmi_hz)
 {
 	u64 count = (u64)cpu_khz * 1000;
 
@@ -254,9 +265,10 @@ static void write_watchdog_counter32(unsigned int perfctr_msr,
 	wrmsr(perfctr_msr, (u32)(-count), 0);
 }
 
-/* AMD K7/K8/Family10h/Family11h support. AMD keeps this interface
-   nicely stable so there is not much variety */
-
+/*
+ * 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)
@@ -289,7 +301,7 @@ static int setup_k7_watchdog(unsigned nmi_hz)
 
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  //unused
+	wd->cccr_msr = 0;  /* unused */
 	return 1;
 }
 
@@ -325,18 +337,19 @@ static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 }
 
 static const 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<<47,
+	.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 << 47,
 };
 
-/* Intel Model 6 (PPro+,P2,P3,P-M,Core1) */
-
+/*
+ * 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)
@@ -372,52 +385,58 @@ static int setup_p6_watchdog(unsigned nmi_hz)
 
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  //unused
+	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
+	/*
+	 * 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 */
+	 * 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 const 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,
+	.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] */
+/*
+ * 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;
@@ -442,7 +461,8 @@ static int setup_p4_watchdog(unsigned nmi_hz)
 #endif
 		ht_num = 0;
 
-	/* performance counters are shared resources
+	/*
+	 * 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)
@@ -540,20 +560,21 @@ static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 }
 
 static const struct wd_ops p4_wd_ops = {
-	.reserve = p4_reserve,
-	.unreserve = p4_unreserve,
-	.setup = setup_p4_watchdog,
-	.rearm = p4_rearm,
-	.stop = stop_p4_watchdog,
+	.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,
+	.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. */
-
+/*
+ * 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
 
@@ -599,19 +620,19 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz)
 
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  //unused
+	wd->cccr_msr = 0;  /* unused */
 	intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
 	return 1;
 }
 
 static struct wd_ops intel_arch_wd_ops __read_mostly = {
-	.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_PERFCTR1,
-	.evntsel = MSR_ARCH_PERFMON_EVENTSEL1,
+	.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_PERFCTR1,
+	.evntsel	= MSR_ARCH_PERFMON_EVENTSEL1,
 };
 
 static void probe_nmi_watchdog(void)
@@ -624,8 +645,10 @@ static void probe_nmi_watchdog(void)
 		wd_ops = &k7_wd_ops;
 		break;
 	case X86_VENDOR_INTEL:
-		/* Work around Core Duo (Yonah) errata AE49 where perfctr1
-		   doesn't have a working enable bit. */
+		/*
+		 * Work around Core Duo (Yonah) errata AE49 where perfctr1
+		 * doesn't have a working enable bit.
+		 */
 		if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) {
 			intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0;
 			intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0;
@@ -636,7 +659,7 @@ static void probe_nmi_watchdog(void)
 		}
 		switch (boot_cpu_data.x86) {
 		case 6:
-			if (boot_cpu_data.x86_model > 0xd)
+			if (boot_cpu_data.x86_model > 13)
 				return;
 
 			wd_ops = &p6_wd_ops;
@@ -697,10 +720,11 @@ 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? */
+	if (ctr & wd_ops->checkbit) /* perfctr still running? */
 		return 0;
-	}
+
 	wd_ops->rearm(wd, nmi_hz);
 	return 1;
 }

arch/x86/kernel/e820.c

@@ -0,0 +1,1390 @@
+/*
+ * Handle the memory map.
+ * The functions here do the job until bootmem takes over.
+ *
+ *  Getting sanitize_e820_map() in sync with i386 version by applying change:
+ *  -  Provisions for empty E820 memory regions (reported by certain BIOSes).
+ *     Alex Achenbach <xela@slit.de>, December 2002.
+ *  Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/ioport.h>
+#include <linux/string.h>
+#include <linux/kexec.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/pfn.h>
+#include <linux/suspend.h>
+#include <linux/firmware-map.h>
+
+#include <asm/pgtable.h>
+#include <asm/page.h>
+#include <asm/e820.h>
+#include <asm/proto.h>
+#include <asm/setup.h>
+#include <asm/trampoline.h>
+
+/*
+ * The e820 map is the map that gets modified e.g. with command line parameters
+ * and that is also registered with modifications in the kernel resource tree
+ * with the iomem_resource as parent.
+ *
+ * The e820_saved is directly saved after the BIOS-provided memory map is
+ * copied. It doesn't get modified afterwards. It's registered for the
+ * /sys/firmware/memmap interface.
+ *
+ * That memory map is not modified and is used as base for kexec. The kexec'd
+ * kernel should get the same memory map as the firmware provides. Then the
+ * user can e.g. boot the original kernel with mem=1G while still booting the
+ * next kernel with full memory.
+ */
+struct e820map e820;
+struct e820map e820_saved;
+
+/* For PCI or other memory-mapped resources */
+unsigned long pci_mem_start = 0xaeedbabe;
+#ifdef CONFIG_PCI
+EXPORT_SYMBOL(pci_mem_start);
+#endif
+
+/*
+ * 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++) {
+		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.
+ *
+ * Note: this function only works correct if the e820 table is sorted and
+ * not-overlapping, which is the case
+ */
+int __init e820_all_mapped(u64 start, u64 end, unsigned type)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		if (type && ei->type != type)
+			continue;
+		/* is the region (part) in overlap with the current region ?*/
+		if (ei->addr >= end || ei->addr + ei->size <= start)
+			continue;
+
+		/* if the region is at the beginning of <start,end> we move
+		 * start to the end of the region since it's ok until there
+		 */
+		if (ei->addr <= start)
+			start = ei->addr + ei->size;
+		/*
+		 * if start is now at or beyond end, we're done, full
+		 * coverage
+		 */
+		if (start >= end)
+			return 1;
+	}
+	return 0;
+}
+
+/*
+ * Add a memory region to the kernel e820 map.
+ */
+void __init e820_add_region(u64 start, u64 size, int type)
+{
+	int x = e820.nr_map;
+
+	if (x == ARRAY_SIZE(e820.map)) {
+		printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
+		return;
+	}
+
+	e820.map[x].addr = start;
+	e820.map[x].size = size;
+	e820.map[x].type = type;
+	e820.nr_map++;
+}
+
+void __init e820_print_map(char *who)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		printk(KERN_INFO " %s: %016Lx - %016Lx ", who,
+		       (unsigned long long) e820.map[i].addr,
+		       (unsigned long long)
+		       (e820.map[i].addr + e820.map[i].size));
+		switch (e820.map[i].type) {
+		case E820_RAM:
+		case E820_RESERVED_KERN:
+			printk(KERN_CONT "(usable)\n");
+			break;
+		case E820_RESERVED:
+			printk(KERN_CONT "(reserved)\n");
+			break;
+		case E820_ACPI:
+			printk(KERN_CONT "(ACPI data)\n");
+			break;
+		case E820_NVS:
+			printk(KERN_CONT "(ACPI NVS)\n");
+			break;
+		default:
+			printk(KERN_CONT "type %u\n", e820.map[i].type);
+			break;
+		}
+	}
+}
+
+/*
+ * Sanitize the BIOS e820 map.
+ *
+ * Some e820 responses include overlapping entries. The following
+ * replaces the original e820 map with a new one, removing overlaps,
+ * and resolving conflicting memory types in favor of highest
+ * numbered type.
+ *
+ * The input parameter biosmap points to an array of 'struct
+ * e820entry' which on entry has elements in the range [0, *pnr_map)
+ * valid, and which has space for up to max_nr_map entries.
+ * On return, the resulting sanitized e820 map entries will be in
+ * overwritten in the same location, starting at biosmap.
+ *
+ * The integer pointed to by pnr_map must be valid on entry (the
+ * current number of valid entries located at biosmap) and will
+ * be updated on return, with the new number of valid entries
+ * (something no more than max_nr_map.)
+ *
+ * The return value from sanitize_e820_map() is zero if it
+ * successfully 'sanitized' the map entries passed in, and is -1
+ * if it did nothing, which can happen if either of (1) it was
+ * only passed one map entry, or (2) any of the input map entries
+ * were invalid (start + size < start, meaning that the size was
+ * so big the described memory range wrapped around through zero.)
+ *
+ *	Visually we're performing the following
+ *	(1,2,3,4 = memory types)...
+ *
+ *	Sample memory map (w/overlaps):
+ *	   ____22__________________
+ *	   ______________________4_
+ *	   ____1111________________
+ *	   _44_____________________
+ *	   11111111________________
+ *	   ____________________33__
+ *	   ___________44___________
+ *	   __________33333_________
+ *	   ______________22________
+ *	   ___________________2222_
+ *	   _________111111111______
+ *	   _____________________11_
+ *	   _________________4______
+ *
+ *	Sanitized equivalent (no overlap):
+ *	   1_______________________
+ *	   _44_____________________
+ *	   ___1____________________
+ *	   ____22__________________
+ *	   ______11________________
+ *	   _________1______________
+ *	   __________3_____________
+ *	   ___________44___________
+ *	   _____________33_________
+ *	   _______________2________
+ *	   ________________1_______
+ *	   _________________4______
+ *	   ___________________2____
+ *	   ____________________33__
+ *	   ______________________4_
+ */
+
+int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
+				int *pnr_map)
+{
+	struct change_member {
+		struct e820entry *pbios; /* pointer to original bios entry */
+		unsigned long long addr; /* address for this change point */
+	};
+	static struct change_member change_point_list[2*E820_X_MAX] __initdata;
+	static struct change_member *change_point[2*E820_X_MAX] __initdata;
+	static struct e820entry *overlap_list[E820_X_MAX] __initdata;
+	static struct e820entry new_bios[E820_X_MAX] __initdata;
+	struct change_member *change_tmp;
+	unsigned long current_type, last_type;
+	unsigned long long last_addr;
+	int chgidx, still_changing;
+	int overlap_entries;
+	int new_bios_entry;
+	int old_nr, new_nr, chg_nr;
+	int i;
+
+	/* if there's only one memory region, don't bother */
+	if (*pnr_map < 2)
+		return -1;
+
+	old_nr = *pnr_map;
+	BUG_ON(old_nr > max_nr_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)
+			return -1;
+
+	/* create pointers for initial change-point information (for sorting) */
+	for (i = 0; i < 2 * old_nr; i++)
+		change_point[i] = &change_point_list[i];
+
+	/* record all known change-points (starting and ending addresses),
+	   omitting those that are for empty memory regions */
+	chgidx = 0;
+	for (i = 0; i < old_nr; i++)	{
+		if (biosmap[i].size != 0) {
+			change_point[chgidx]->addr = biosmap[i].addr;
+			change_point[chgidx++]->pbios = &biosmap[i];
+			change_point[chgidx]->addr = biosmap[i].addr +
+				biosmap[i].size;
+			change_point[chgidx++]->pbios = &biosmap[i];
+		}
+	}
+	chg_nr = chgidx;
+
+	/* sort change-point list by memory addresses (low -> high) */
+	still_changing = 1;
+	while (still_changing)	{
+		still_changing = 0;
+		for (i = 1; i < chg_nr; i++)  {
+			unsigned long long curaddr, lastaddr;
+			unsigned long long curpbaddr, lastpbaddr;
+
+			curaddr = change_point[i]->addr;
+			lastaddr = change_point[i - 1]->addr;
+			curpbaddr = change_point[i]->pbios->addr;
+			lastpbaddr = change_point[i - 1]->pbios->addr;
+
+			/*
+			 * swap entries, when:
+			 *
+			 * curaddr > lastaddr or
+			 * curaddr == lastaddr and curaddr == curpbaddr and
+			 * lastaddr != lastpbaddr
+			 */
+			if (curaddr < lastaddr ||
+			    (curaddr == lastaddr && curaddr == curpbaddr &&
+			     lastaddr != lastpbaddr)) {
+				change_tmp = change_point[i];
+				change_point[i] = change_point[i-1];
+				change_point[i-1] = change_tmp;
+				still_changing = 1;
+			}
+		}
+	}
+
+	/* create a new bios memory map, removing overlaps */
+	overlap_entries = 0;	 /* number of entries in the overlap table */
+	new_bios_entry = 0;	 /* index for creating new bios map entries */
+	last_type = 0;		 /* start with undefined memory type */
+	last_addr = 0;		 /* start with 0 as last starting address */
+
+	/* loop through change-points, determining affect on the new bios map */
+	for (chgidx = 0; chgidx < chg_nr; chgidx++) {
+		/* keep track of all overlapping bios entries */
+		if (change_point[chgidx]->addr ==
+		    change_point[chgidx]->pbios->addr) {
+			/*
+			 * add map entry to overlap list (> 1 entry
+			 * implies an overlap)
+			 */
+			overlap_list[overlap_entries++] =
+				change_point[chgidx]->pbios;
+		} else {
+			/*
+			 * remove entry from list (order independent,
+			 * so swap with last)
+			 */
+			for (i = 0; i < overlap_entries; i++) {
+				if (overlap_list[i] ==
+				    change_point[chgidx]->pbios)
+					overlap_list[i] =
+						overlap_list[overlap_entries-1];
+			}
+			overlap_entries--;
+		}
+		/*
+		 * if there are overlapping entries, decide which
+		 * "type" to use (larger value takes precedence --
+		 * 1=usable, 2,3,4,4+=unusable)
+		 */
+		current_type = 0;
+		for (i = 0; i < overlap_entries; i++)
+			if (overlap_list[i]->type > current_type)
+				current_type = overlap_list[i]->type;
+		/*
+		 * continue building up new bios map based on this
+		 * information
+		 */
+		if (current_type != last_type)	{
+			if (last_type != 0)	 {
+				new_bios[new_bios_entry].size =
+					change_point[chgidx]->addr - last_addr;
+				/*
+				 * move forward only if the new size
+				 * was non-zero
+				 */
+				if (new_bios[new_bios_entry].size != 0)
+					/*
+					 * no more space left for new
+					 * bios entries ?
+					 */
+					if (++new_bios_entry >= max_nr_map)
+						break;
+			}
+			if (current_type != 0)	{
+				new_bios[new_bios_entry].addr =
+					change_point[chgidx]->addr;
+				new_bios[new_bios_entry].type = current_type;
+				last_addr = change_point[chgidx]->addr;
+			}
+			last_type = current_type;
+		}
+	}
+	/* retain count for new bios entries */
+	new_nr = new_bios_entry;
+
+	/* copy new bios mapping into original location */
+	memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry));
+	*pnr_map = new_nr;
+
+	return 0;
+}
+
+static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
+{
+	while (nr_map) {
+		u64 start = biosmap->addr;
+		u64 size = biosmap->size;
+		u64 end = start + size;
+		u32 type = biosmap->type;
+
+		/* Overflow in 64 bits? Ignore the memory map. */
+		if (start > end)
+			return -1;
+
+		e820_add_region(start, size, type);
+
+		biosmap++;
+		nr_map--;
+	}
+	return 0;
+}
+
+/*
+ * Copy the BIOS e820 map into a safe place.
+ *
+ * Sanity-check it while we're at it..
+ *
+ * If we're lucky and live on a modern system, the setup code
+ * will have given us a memory map that we can use to properly
+ * set up memory.  If we aren't, we'll fake a memory map.
+ */
+static int __init append_e820_map(struct e820entry *biosmap, int nr_map)
+{
+	/* Only one memory region (or negative)? Ignore it */
+	if (nr_map < 2)
+		return -1;
+
+	return __append_e820_map(biosmap, nr_map);
+}
+
+static u64 __init e820_update_range_map(struct e820map *e820x, u64 start,
+					u64 size, unsigned old_type,
+					unsigned new_type)
+{
+	int i;
+	u64 real_updated_size = 0;
+
+	BUG_ON(old_type == new_type);
+
+	if (size > (ULLONG_MAX - start))
+		size = ULLONG_MAX - start;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820x->map[i];
+		u64 final_start, final_end;
+		if (ei->type != old_type)
+			continue;
+		/* totally covered? */
+		if (ei->addr >= start &&
+		    (ei->addr + ei->size) <= (start + size)) {
+			ei->type = new_type;
+			real_updated_size += ei->size;
+			continue;
+		}
+		/* partially covered */
+		final_start = max(start, ei->addr);
+		final_end = min(start + size, ei->addr + ei->size);
+		if (final_start >= final_end)
+			continue;
+		e820_add_region(final_start, final_end - final_start,
+					 new_type);
+		real_updated_size += final_end - final_start;
+
+		ei->size -= final_end - final_start;
+		if (ei->addr < final_start)
+			continue;
+		ei->addr = final_end;
+	}
+	return real_updated_size;
+}
+
+u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
+			     unsigned new_type)
+{
+	return e820_update_range_map(&e820, start, size, old_type, new_type);
+}
+
+static u64 __init e820_update_range_saved(u64 start, u64 size,
+					  unsigned old_type, unsigned new_type)
+{
+	return e820_update_range_map(&e820_saved, start, size, old_type,
+				     new_type);
+}
+
+/* make e820 not cover the range */
+u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
+			     int checktype)
+{
+	int i;
+	u64 real_removed_size = 0;
+
+	if (size > (ULLONG_MAX - start))
+		size = ULLONG_MAX - start;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		u64 final_start, final_end;
+
+		if (checktype && ei->type != old_type)
+			continue;
+		/* totally covered? */
+		if (ei->addr >= start &&
+		    (ei->addr + ei->size) <= (start + size)) {
+			real_removed_size += ei->size;
+			memset(ei, 0, sizeof(struct e820entry));
+			continue;
+		}
+		/* partially covered */
+		final_start = max(start, ei->addr);
+		final_end = min(start + size, ei->addr + ei->size);
+		if (final_start >= final_end)
+			continue;
+		real_removed_size += final_end - final_start;
+
+		ei->size -= final_end - final_start;
+		if (ei->addr < final_start)
+			continue;
+		ei->addr = final_end;
+	}
+	return real_removed_size;
+}
+
+void __init update_e820(void)
+{
+	int nr_map;
+
+	nr_map = e820.nr_map;
+	if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
+		return;
+	e820.nr_map = nr_map;
+	printk(KERN_INFO "modified physical RAM map:\n");
+	e820_print_map("modified");
+}
+static void __init update_e820_saved(void)
+{
+	int nr_map;
+
+	nr_map = e820_saved.nr_map;
+	if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map))
+		return;
+	e820_saved.nr_map = nr_map;
+}
+#define MAX_GAP_END 0x100000000ull
+/*
+ * Search for a gap in the e820 memory space from start_addr to end_addr.
+ */
+__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
+		unsigned long start_addr, unsigned long long end_addr)
+{
+	unsigned long long last;
+	int i = e820.nr_map;
+	int found = 0;
+
+	last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END;
+
+	while (--i >= 0) {
+		unsigned long long start = e820.map[i].addr;
+		unsigned long long end = start + e820.map[i].size;
+
+		if (end < start_addr)
+			continue;
+
+		/*
+		 * Since "last" is at most 4GB, we know we'll
+		 * fit in 32 bits if this condition is true
+		 */
+		if (last > end) {
+			unsigned long gap = last - end;
+
+			if (gap >= *gapsize) {
+				*gapsize = gap;
+				*gapstart = end;
+				found = 1;
+			}
+		}
+		if (start < last)
+			last = start;
+	}
+	return found;
+}
+
+/*
+ * Search for the biggest gap in the low 32 bits of the e820
+ * memory space.  We pass this space to PCI to assign MMIO resources
+ * for hotplug or unconfigured devices in.
+ * Hopefully the BIOS let enough space left.
+ */
+__init void e820_setup_gap(void)
+{
+	unsigned long gapstart, gapsize, round;
+	int found;
+
+	gapstart = 0x10000000;
+	gapsize = 0x400000;
+	found  = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END);
+
+#ifdef CONFIG_X86_64
+	if (!found) {
+		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
+		printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit "
+		       "address range\n"
+		       KERN_ERR "PCI: Unassigned devices with 32bit resource "
+		       "registers may break!\n");
+	}
+#endif
+
+	/*
+	 * See how much we want to round up: start off with
+	 * rounding to the next 1MB area.
+	 */
+	round = 0x100000;
+	while ((gapsize >> 4) > round)
+		round += round;
+	/* Fun with two's complement */
+	pci_mem_start = (gapstart + round) & -round;
+
+	printk(KERN_INFO
+	       "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
+	       pci_mem_start, gapstart, gapsize);
+}
+
+/**
+ * Because of the size limitation of struct boot_params, only first
+ * 128 E820 memory entries are passed to kernel via
+ * boot_params.e820_map, others are passed via SETUP_E820_EXT node of
+ * linked list of struct setup_data, which is parsed here.
+ */
+void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data)
+{
+	u32 map_len;
+	int entries;
+	struct e820entry *extmap;
+
+	entries = sdata->len / sizeof(struct e820entry);
+	map_len = sdata->len + sizeof(struct setup_data);
+	if (map_len > PAGE_SIZE)
+		sdata = early_ioremap(pa_data, map_len);
+	extmap = (struct e820entry *)(sdata->data);
+	__append_e820_map(extmap, entries);
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	if (map_len > PAGE_SIZE)
+		early_iounmap(sdata, map_len);
+	printk(KERN_INFO "extended physical RAM map:\n");
+	e820_print_map("extended");
+}
+
+#if defined(CONFIG_X86_64) || \
+	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
+/**
+ * Find the ranges of physical addresses that do not correspond to
+ * e820 RAM areas and mark the corresponding pages as nosave for
+ * hibernation (32 bit) or software suspend and suspend to RAM (64 bit).
+ *
+ * This function requires the e820 map to be sorted and without any
+ * overlapping entries and assumes the first e820 area to be RAM.
+ */
+void __init e820_mark_nosave_regions(unsigned long limit_pfn)
+{
+	int i;
+	unsigned long pfn;
+
+	pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size);
+	for (i = 1; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		if (pfn < PFN_UP(ei->addr))
+			register_nosave_region(pfn, PFN_UP(ei->addr));
+
+		pfn = PFN_DOWN(ei->addr + ei->size);
+		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+			register_nosave_region(PFN_UP(ei->addr), pfn);
+
+		if (pfn >= limit_pfn)
+			break;
+	}
+}
+#endif
+
+/*
+ * Early reserved memory areas.
+ */
+#define MAX_EARLY_RES 20
+
+struct early_res {
+	u64 start, end;
+	char name[16];
+	char overlap_ok;
+};
+static struct early_res early_res[MAX_EARLY_RES] __initdata = {
+	{ 0, PAGE_SIZE, "BIOS data page" },	/* BIOS data page */
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_TRAMPOLINE)
+	{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
+#endif
+#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
+	/*
+	 * But first pinch a few for the stack/trampoline stuff
+	 * FIXME: Don't need the extra page at 4K, but need to fix
+	 * trampoline before removing it. (see the GDT stuff)
+	 */
+	{ PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE" },
+	/*
+	 * Has to be in very low memory so we can execute
+	 * real-mode AP code.
+	 */
+	{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + PAGE_SIZE, "TRAMPOLINE" },
+#endif
+	{}
+};
+
+static int __init find_overlapped_early(u64 start, u64 end)
+{
+	int i;
+	struct early_res *r;
+
+	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+		r = &early_res[i];
+		if (end > r->start && start < r->end)
+			break;
+	}
+
+	return i;
+}
+
+/*
+ * Drop the i-th range from the early reservation map,
+ * by copying any higher ranges down one over it, and
+ * clearing what had been the last slot.
+ */
+static void __init drop_range(int i)
+{
+	int j;
+
+	for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
+		;
+
+	memmove(&early_res[i], &early_res[i + 1],
+	       (j - 1 - i) * sizeof(struct early_res));
+
+	early_res[j - 1].end = 0;
+}
+
+/*
+ * Split any existing ranges that:
+ *  1) are marked 'overlap_ok', and
+ *  2) overlap with the stated range [start, end)
+ * into whatever portion (if any) of the existing range is entirely
+ * below or entirely above the stated range.  Drop the portion
+ * of the existing range that overlaps with the stated range,
+ * which will allow the caller of this routine to then add that
+ * stated range without conflicting with any existing range.
+ */
+static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
+{
+	int i;
+	struct early_res *r;
+	u64 lower_start, lower_end;
+	u64 upper_start, upper_end;
+	char name[16];
+
+	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+		r = &early_res[i];
+
+		/* Continue past non-overlapping ranges */
+		if (end <= r->start || start >= r->end)
+			continue;
+
+		/*
+		 * Leave non-ok overlaps as is; let caller
+		 * panic "Overlapping early reservations"
+		 * when it hits this overlap.
+		 */
+		if (!r->overlap_ok)
+			return;
+
+		/*
+		 * We have an ok overlap.  We will drop it from the early
+		 * reservation map, and add back in any non-overlapping
+		 * portions (lower or upper) as separate, overlap_ok,
+		 * non-overlapping ranges.
+		 */
+
+		/* 1. Note any non-overlapping (lower or upper) ranges. */
+		strncpy(name, r->name, sizeof(name) - 1);
+
+		lower_start = lower_end = 0;
+		upper_start = upper_end = 0;
+		if (r->start < start) {
+		 	lower_start = r->start;
+			lower_end = start;
+		}
+		if (r->end > end) {
+			upper_start = end;
+			upper_end = r->end;
+		}
+
+		/* 2. Drop the original ok overlapping range */
+		drop_range(i);
+
+		i--;		/* resume for-loop on copied down entry */
+
+		/* 3. Add back in any non-overlapping ranges. */
+		if (lower_end)
+			reserve_early_overlap_ok(lower_start, lower_end, name);
+		if (upper_end)
+			reserve_early_overlap_ok(upper_start, upper_end, name);
+	}
+}
+
+static void __init __reserve_early(u64 start, u64 end, char *name,
+						int overlap_ok)
+{
+	int i;
+	struct early_res *r;
+
+	i = find_overlapped_early(start, end);
+	if (i >= MAX_EARLY_RES)
+		panic("Too many early reservations");
+	r = &early_res[i];
+	if (r->end)
+		panic("Overlapping early reservations "
+		      "%llx-%llx %s to %llx-%llx %s\n",
+		      start, end - 1, name?name:"", r->start,
+		      r->end - 1, r->name);
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = overlap_ok;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+}
+
+/*
+ * A few early reservtations come here.
+ *
+ * The 'overlap_ok' in the name of this routine does -not- mean it
+ * is ok for these reservations to overlap an earlier reservation.
+ * Rather it means that it is ok for subsequent reservations to
+ * overlap this one.
+ *
+ * Use this entry point to reserve early ranges when you are doing
+ * so out of "Paranoia", reserving perhaps more memory than you need,
+ * just in case, and don't mind a subsequent overlapping reservation
+ * that is known to be needed.
+ *
+ * The drop_overlaps_that_are_ok() call here isn't really needed.
+ * It would be needed if we had two colliding 'overlap_ok'
+ * reservations, so that the second such would not panic on the
+ * overlap with the first.  We don't have any such as of this
+ * writing, but might as well tolerate such if it happens in
+ * the future.
+ */
+void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
+{
+	drop_overlaps_that_are_ok(start, end);
+	__reserve_early(start, end, name, 1);
+}
+
+/*
+ * Most early reservations come here.
+ *
+ * We first have drop_overlaps_that_are_ok() drop any pre-existing
+ * 'overlap_ok' ranges, so that we can then reserve this memory
+ * range without risk of panic'ing on an overlapping overlap_ok
+ * early reservation.
+ */
+void __init reserve_early(u64 start, u64 end, char *name)
+{
+	drop_overlaps_that_are_ok(start, end);
+	__reserve_early(start, end, name, 0);
+}
+
+void __init free_early(u64 start, u64 end)
+{
+	struct early_res *r;
+	int i;
+
+	i = find_overlapped_early(start, end);
+	r = &early_res[i];
+	if (i >= MAX_EARLY_RES || r->end != end || r->start != start)
+		panic("free_early on not reserved area: %llx-%llx!",
+			 start, end - 1);
+
+	drop_range(i);
+}
+
+void __init early_res_to_bootmem(u64 start, u64 end)
+{
+	int i, count;
+	u64 final_start, final_end;
+
+	count  = 0;
+	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++)
+		count++;
+
+	printk(KERN_INFO "(%d early reservations) ==> bootmem\n", count);
+	for (i = 0; i < count; i++) {
+		struct early_res *r = &early_res[i];
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
+			r->start, r->end, r->name);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end) {
+			printk(KERN_CONT "\n");
+			continue;
+		}
+		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
+			final_start, final_end);
+		reserve_bootmem_generic(final_start, final_end - final_start,
+				BOOTMEM_DEFAULT);
+	}
+}
+
+/* Check for already reserved areas */
+static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
+{
+	int i;
+	u64 addr = *addrp;
+	int changed = 0;
+	struct early_res *r;
+again:
+	i = find_overlapped_early(addr, addr + size);
+	r = &early_res[i];
+	if (i < MAX_EARLY_RES && r->end) {
+		*addrp = addr = round_up(r->end, align);
+		changed = 1;
+		goto again;
+	}
+	return changed;
+}
+
+/* Check for already reserved areas */
+static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+{
+	int i;
+	u64 addr = *addrp, last;
+	u64 size = *sizep;
+	int changed = 0;
+again:
+	last = addr + size;
+	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+		struct early_res *r = &early_res[i];
+		if (last > r->start && addr < r->start) {
+			size = r->start - addr;
+			changed = 1;
+			goto again;
+		}
+		if (last > r->end && addr < r->end) {
+			addr = round_up(r->end, align);
+			size = last - addr;
+			changed = 1;
+			goto again;
+		}
+		if (last <= r->end && addr >= r->start) {
+			(*sizep)++;
+			return 0;
+		}
+	}
+	if (changed) {
+		*addrp = addr;
+		*sizep = size;
+	}
+	return changed;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		u64 addr, last;
+		u64 ei_last;
+
+		if (ei->type != E820_RAM)
+			continue;
+		addr = round_up(ei->addr, align);
+		ei_last = ei->addr + ei->size;
+		if (addr < start)
+			addr = round_up(start, align);
+		if (addr >= ei_last)
+			continue;
+		while (bad_addr(&addr, size, align) && addr+size <= ei_last)
+			;
+		last = addr + size;
+		if (last > ei_last)
+			continue;
+		if (last > end)
+			continue;
+		return addr;
+	}
+	return -1ULL;
+}
+
+/*
+ * Find next free range after *start
+ */
+u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		u64 addr, last;
+		u64 ei_last;
+
+		if (ei->type != E820_RAM)
+			continue;
+		addr = round_up(ei->addr, align);
+		ei_last = ei->addr + ei->size;
+		if (addr < start)
+			addr = round_up(start, align);
+		if (addr >= ei_last)
+			continue;
+		*sizep = ei_last - addr;
+		while (bad_addr_size(&addr, sizep, align) &&
+			addr + *sizep <= ei_last)
+			;
+		last = addr + *sizep;
+		if (last > ei_last)
+			continue;
+		return addr;
+	}
+	return -1UL;
+
+}
+
+/*
+ * pre allocated 4k and reserved it in e820
+ */
+u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
+{
+	u64 size = 0;
+	u64 addr;
+	u64 start;
+
+	start = startt;
+	while (size < sizet)
+		start = find_e820_area_size(start, &size, align);
+
+	if (size < sizet)
+		return 0;
+
+	addr = round_down(start + size - sizet, align);
+	e820_update_range(addr, sizet, E820_RAM, E820_RESERVED);
+	e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED);
+	printk(KERN_INFO "update e820 for early_reserve_e820\n");
+	update_e820();
+	update_e820_saved();
+
+	return addr;
+}
+
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_X86_PAE
+#  define MAX_ARCH_PFN		(1ULL<<(36-PAGE_SHIFT))
+# else
+#  define MAX_ARCH_PFN		(1ULL<<(32-PAGE_SHIFT))
+# endif
+#else /* CONFIG_X86_32 */
+# define MAX_ARCH_PFN MAXMEM>>PAGE_SHIFT
+#endif
+
+/*
+ * Find the highest page frame number we have available
+ */
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
+{
+	int i;
+	unsigned long last_pfn = 0;
+	unsigned long max_arch_pfn = MAX_ARCH_PFN;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		unsigned long start_pfn;
+		unsigned long end_pfn;
+
+		if (ei->type != type)
+			continue;
+
+		start_pfn = ei->addr >> PAGE_SHIFT;
+		end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;
+
+		if (start_pfn >= limit_pfn)
+			continue;
+		if (end_pfn > limit_pfn) {
+			last_pfn = limit_pfn;
+			break;
+		}
+		if (end_pfn > last_pfn)
+			last_pfn = end_pfn;
+	}
+
+	if (last_pfn > max_arch_pfn)
+		last_pfn = max_arch_pfn;
+
+	printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n",
+			 last_pfn, max_arch_pfn);
+	return last_pfn;
+}
+unsigned long __init e820_end_of_ram_pfn(void)
+{
+	return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
+}
+
+unsigned long __init e820_end_of_low_ram_pfn(void)
+{
+	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
+}
+/*
+ * Finds an active region in the address range from start_pfn to last_pfn and
+ * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
+ */
+int __init e820_find_active_region(const struct e820entry *ei,
+				  unsigned long start_pfn,
+				  unsigned long last_pfn,
+				  unsigned long *ei_startpfn,
+				  unsigned long *ei_endpfn)
+{
+	u64 align = PAGE_SIZE;
+
+	*ei_startpfn = round_up(ei->addr, align) >> PAGE_SHIFT;
+	*ei_endpfn = round_down(ei->addr + ei->size, align) >> PAGE_SHIFT;
+
+	/* Skip map entries smaller than a page */
+	if (*ei_startpfn >= *ei_endpfn)
+		return 0;
+
+	/* Skip if map is outside the node */
+	if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
+				    *ei_startpfn >= last_pfn)
+		return 0;
+
+	/* Check for overlaps */
+	if (*ei_startpfn < start_pfn)
+		*ei_startpfn = start_pfn;
+	if (*ei_endpfn > last_pfn)
+		*ei_endpfn = last_pfn;
+
+	return 1;
+}
+
+/* Walk the e820 map and register active regions within a node */
+void __init e820_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn)
+{
+	unsigned long ei_startpfn;
+	unsigned long ei_endpfn;
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++)
+		if (e820_find_active_region(&e820.map[i],
+					    start_pfn, last_pfn,
+					    &ei_startpfn, &ei_endpfn))
+			add_active_range(nid, ei_startpfn, ei_endpfn);
+}
+
+/*
+ * Find the hole size (in bytes) in the memory range.
+ * @start: starting address of the memory range to scan
+ * @end: ending address of the memory range to scan
+ */
+u64 __init e820_hole_size(u64 start, u64 end)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long last_pfn = end >> PAGE_SHIFT;
+	unsigned long ei_startpfn, ei_endpfn, ram = 0;
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		if (e820_find_active_region(&e820.map[i],
+					    start_pfn, last_pfn,
+					    &ei_startpfn, &ei_endpfn))
+			ram += ei_endpfn - ei_startpfn;
+	}
+	return end - start - ((u64)ram << PAGE_SHIFT);
+}
+
+static void early_panic(char *msg)
+{
+	early_printk(msg);
+	panic(msg);
+}
+
+static int userdef __initdata;
+
+/* "mem=nopentium" disables the 4MB page tables. */
+static int __init parse_memopt(char *p)
+{
+	u64 mem_size;
+
+	if (!p)
+		return -EINVAL;
+
+#ifdef CONFIG_X86_32
+	if (!strcmp(p, "nopentium")) {
+		setup_clear_cpu_cap(X86_FEATURE_PSE);
+		return 0;
+	}
+#endif
+
+	userdef = 1;
+	mem_size = memparse(p, &p);
+	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
+
+	return 0;
+}
+early_param("mem", parse_memopt);
+
+static int __init parse_memmap_opt(char *p)
+{
+	char *oldp;
+	u64 start_at, mem_size;
+
+	if (!p)
+		return -EINVAL;
+
+	if (!strcmp(p, "exactmap")) {
+#ifdef CONFIG_CRASH_DUMP
+		/*
+		 * If we are doing a crash dump, we still need to know
+		 * the real mem size before original memory map is
+		 * reset.
+		 */
+		saved_max_pfn = e820_end_of_ram_pfn();
+#endif
+		e820.nr_map = 0;
+		userdef = 1;
+		return 0;
+	}
+
+	oldp = p;
+	mem_size = memparse(p, &p);
+	if (p == oldp)
+		return -EINVAL;
+
+	userdef = 1;
+	if (*p == '@') {
+		start_at = memparse(p+1, &p);
+		e820_add_region(start_at, mem_size, E820_RAM);
+	} else if (*p == '#') {
+		start_at = memparse(p+1, &p);
+		e820_add_region(start_at, mem_size, E820_ACPI);
+	} else if (*p == '$') {
+		start_at = memparse(p+1, &p);
+		e820_add_region(start_at, mem_size, E820_RESERVED);
+	} else
+		e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
+
+	return *p == '\0' ? 0 : -EINVAL;
+}
+early_param("memmap", parse_memmap_opt);
+
+void __init finish_e820_parsing(void)
+{
+	if (userdef) {
+		int nr = e820.nr_map;
+
+		if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0)
+			early_panic("Invalid user supplied memory map");
+		e820.nr_map = nr;
+
+		printk(KERN_INFO "user-defined physical RAM map:\n");
+		e820_print_map("user");
+	}
+}
+
+static inline const char *e820_type_to_string(int e820_type)
+{
+	switch (e820_type) {
+	case E820_RESERVED_KERN:
+	case E820_RAM:	return "System RAM";
+	case E820_ACPI:	return "ACPI Tables";
+	case E820_NVS:	return "ACPI Non-volatile Storage";
+	default:	return "reserved";
+	}
+}
+
+/*
+ * Mark e820 reserved areas as busy for the resource manager.
+ */
+void __init e820_reserve_resources(void)
+{
+	int i;
+	struct resource *res;
+	u64 end;
+
+	res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map);
+	for (i = 0; i < e820.nr_map; i++) {
+		end = e820.map[i].addr + e820.map[i].size - 1;
+#ifndef CONFIG_RESOURCES_64BIT
+		if (end > 0x100000000ULL) {
+			res++;
+			continue;
+		}
+#endif
+		res->name = e820_type_to_string(e820.map[i].type);
+		res->start = e820.map[i].addr;
+		res->end = end;
+
+		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+		insert_resource(&iomem_resource, res);
+		res++;
+	}
+
+	for (i = 0; i < e820_saved.nr_map; i++) {
+		struct e820entry *entry = &e820_saved.map[i];
+		firmware_map_add_early(entry->addr,
+			entry->addr + entry->size - 1,
+			e820_type_to_string(entry->type));
+	}
+}
+
+/*
+ * Non-standard memory setup can be specified via this quirk:
+ */
+char * (*arch_memory_setup_quirk)(void);
+
+char *__init default_machine_specific_memory_setup(void)
+{
+	char *who = "BIOS-e820";
+	int new_nr;
+	/*
+	 * Try to copy the BIOS-supplied E820-map.
+	 *
+	 * Otherwise fake a memory map; one section from 0k->640k,
+	 * the next section from 1mb->appropriate_mem_k
+	 */
+	new_nr = boot_params.e820_entries;
+	sanitize_e820_map(boot_params.e820_map,
+			ARRAY_SIZE(boot_params.e820_map),
+			&new_nr);
+	boot_params.e820_entries = new_nr;
+	if (append_e820_map(boot_params.e820_map, boot_params.e820_entries)
+	  < 0) {
+		u64 mem_size;
+
+		/* compare results from other methods and take the greater */
+		if (boot_params.alt_mem_k
+		    < boot_params.screen_info.ext_mem_k) {
+			mem_size = boot_params.screen_info.ext_mem_k;
+			who = "BIOS-88";
+		} else {
+			mem_size = boot_params.alt_mem_k;
+			who = "BIOS-e801";
+		}
+
+		e820.nr_map = 0;
+		e820_add_region(0, LOWMEMSIZE(), E820_RAM);
+		e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
+	}
+
+	/* In case someone cares... */
+	return who;
+}
+
+char *__init __attribute__((weak)) machine_specific_memory_setup(void)
+{
+	if (arch_memory_setup_quirk) {
+		char *who = arch_memory_setup_quirk();
+
+		if (who)
+			return who;
+	}
+	return default_machine_specific_memory_setup();
+}
+
+/* Overridden in paravirt.c if CONFIG_PARAVIRT */
+char * __init __attribute__((weak)) memory_setup(void)
+{
+	return machine_specific_memory_setup();
+}
+
+void __init setup_memory_map(void)
+{
+	char *who;
+
+	who = memory_setup();
+	memcpy(&e820_saved, &e820, sizeof(struct e820map));
+	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
+	e820_print_map(who);
+}
+
+#ifdef CONFIG_X86_64
+int __init arch_get_ram_range(int slot, u64 *addr, u64 *size)
+{
+	int i;
+
+	if (slot < 0 || slot >= e820.nr_map)
+		return -1;
+	for (i = slot; i < e820.nr_map; i++) {
+		if (e820.map[i].type != E820_RAM)
+			continue;
+		break;
+	}
+	if (i == e820.nr_map || e820.map[i].addr > (max_pfn << PAGE_SHIFT))
+		return -1;
+	*addr = e820.map[i].addr;
+	*size = min_t(u64, e820.map[i].size + e820.map[i].addr,
+		max_pfn << PAGE_SHIFT) - *addr;
+	return i + 1;
+}
+#endif

arch/x86/kernel/e820_32.c

@@ -1,775 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/ioport.h>
-#include <linux/string.h>
-#include <linux/kexec.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/pfn.h>
-#include <linux/uaccess.h>
-#include <linux/suspend.h>
-
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/e820.h>
-#include <asm/setup.h>
-
-struct e820map e820;
-struct change_member {
-	struct e820entry *pbios; /* pointer to original bios entry */
-	unsigned long long addr; /* address for this change point */
-};
-static struct change_member change_point_list[2*E820MAX] __initdata;
-static struct change_member *change_point[2*E820MAX] __initdata;
-static struct e820entry *overlap_list[E820MAX] __initdata;
-static struct e820entry new_bios[E820MAX] __initdata;
-/* For PCI or other memory-mapped resources */
-unsigned long pci_mem_start = 0x10000000;
-#ifdef CONFIG_PCI
-EXPORT_SYMBOL(pci_mem_start);
-#endif
-extern int user_defined_memmap;
-
-static struct resource system_rom_resource = {
-	.name	= "System ROM",
-	.start	= 0xf0000,
-	.end	= 0xfffff,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-};
-
-static struct resource extension_rom_resource = {
-	.name	= "Extension ROM",
-	.start	= 0xe0000,
-	.end	= 0xeffff,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-};
-
-static struct resource adapter_rom_resources[] = { {
-	.name 	= "Adapter ROM",
-	.start	= 0xc8000,
-	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-}, {
-	.name 	= "Adapter ROM",
-	.start	= 0,
-	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-}, {
-	.name 	= "Adapter ROM",
-	.start	= 0,
-	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-}, {
-	.name 	= "Adapter ROM",
-	.start	= 0,
-	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-}, {
-	.name 	= "Adapter ROM",
-	.start	= 0,
-	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-}, {
-	.name 	= "Adapter ROM",
-	.start	= 0,
-	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-} };
-
-static struct resource video_rom_resource = {
-	.name 	= "Video ROM",
-	.start	= 0xc0000,
-	.end	= 0xc7fff,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
-};
-
-#define ROMSIGNATURE 0xaa55
-
-static int __init romsignature(const unsigned char *rom)
-{
-	const unsigned short * const ptr = (const unsigned short *)rom;
-	unsigned short sig;
-
-	return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE;
-}
-
-static int __init romchecksum(const unsigned char *rom, unsigned long length)
-{
-	unsigned char sum, c;
-
-	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 c;
-	int i;
-
-	/* video rom */
-	upper = adapter_rom_resources[0].start;
-	for (start = video_rom_resource.start; start < upper; start += 2048) {
-		rom = isa_bus_to_virt(start);
-		if (!romsignature(rom))
-			continue;
-
-		video_rom_resource.start = start;
-
-		if (probe_kernel_address(rom + 2, c) != 0)
-			continue;
-
-		/* 0 < length <= 0x7f * 512, historically */
-		length = c * 512;
-
-		/* if checksum okay, trust length byte */
-		if (length && romchecksum(rom, length))
-			video_rom_resource.end = start + length - 1;
-
-		request_resource(&iomem_resource, &video_rom_resource);
-		break;
-	}
-
-	start = (video_rom_resource.end + 1 + 2047) & ~2047UL;
-	if (start < upper)
-		start = upper;
-
-	/* system rom */
-	request_resource(&iomem_resource, &system_rom_resource);
-	upper = system_rom_resource.start;
-
-	/* check for extension rom (ignore length byte!) */
-	rom = isa_bus_to_virt(extension_rom_resource.start);
-	if (romsignature(rom)) {
-		length = extension_rom_resource.end - extension_rom_resource.start + 1;
-		if (romchecksum(rom, length)) {
-			request_resource(&iomem_resource, &extension_rom_resource);
-			upper = extension_rom_resource.start;
-		}
-	}
-
-	/* check for adapter roms on 2k boundaries */
-	for (i = 0; i < ARRAY_SIZE(adapter_rom_resources) && start < upper; start += 2048) {
-		rom = isa_bus_to_virt(start);
-		if (!romsignature(rom))
-			continue;
-
-		if (probe_kernel_address(rom + 2, c) != 0)
-			continue;
-
-		/* 0 < length <= 0x7f * 512, historically */
-		length = c * 512;
-
-		/* but accept any length that fits if checksum okay */
-		if (!length || start + length > upper || !romchecksum(rom, length))
-			continue;
-
-		adapter_rom_resources[i].start = start;
-		adapter_rom_resources[i].end = start + length - 1;
-		request_resource(&iomem_resource, &adapter_rom_resources[i]);
-
-		start = adapter_rom_resources[i++].end & ~2047UL;
-	}
-}
-
-/*
- * Request address space for all standard RAM and ROM resources
- * and also for regions reported as reserved by the e820.
- */
-void __init init_iomem_resources(struct resource *code_resource,
-		struct resource *data_resource,
-		struct resource *bss_resource)
-{
-	int i;
-
-	probe_roms();
-	for (i = 0; i < e820.nr_map; i++) {
-		struct resource *res;
-#ifndef CONFIG_RESOURCES_64BIT
-		if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL)
-			continue;
-#endif
-		res = kzalloc(sizeof(struct resource), GFP_ATOMIC);
-		switch (e820.map[i].type) {
-		case E820_RAM:	res->name = "System RAM"; break;
-		case E820_ACPI:	res->name = "ACPI Tables"; break;
-		case E820_NVS:	res->name = "ACPI Non-volatile Storage"; break;
-		default:	res->name = "reserved";
-		}
-		res->start = e820.map[i].addr;
-		res->end = res->start + e820.map[i].size - 1;
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
-		if (request_resource(&iomem_resource, res)) {
-			kfree(res);
-			continue;
-		}
-		if (e820.map[i].type == E820_RAM) {
-			/*
-			 *  We don't know which RAM region contains kernel data,
-			 *  so we try it repeatedly and let the resource manager
-			 *  test it.
-			 */
-			request_resource(res, code_resource);
-			request_resource(res, data_resource);
-			request_resource(res, bss_resource);
-#ifdef CONFIG_KEXEC
-			if (crashk_res.start != crashk_res.end)
-				request_resource(res, &crashk_res);
-#endif
-		}
-	}
-}
-
-#if defined(CONFIG_PM) && defined(CONFIG_HIBERNATION)
-/**
- * e820_mark_nosave_regions - Find the ranges of physical addresses that do not
- * correspond to e820 RAM areas and mark the corresponding pages as nosave for
- * hibernation.
- *
- * This function requires the e820 map to be sorted and without any
- * overlapping entries and assumes the first e820 area to be RAM.
- */
-void __init e820_mark_nosave_regions(void)
-{
-	int i;
-	unsigned long pfn;
-
-	pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size);
-	for (i = 1; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-
-		if (pfn < PFN_UP(ei->addr))
-			register_nosave_region(pfn, PFN_UP(ei->addr));
-
-		pfn = PFN_DOWN(ei->addr + ei->size);
-		if (ei->type != E820_RAM)
-			register_nosave_region(PFN_UP(ei->addr), pfn);
-
-		if (pfn >= max_low_pfn)
-			break;
-	}
-}
-#endif
-
-void __init add_memory_region(unsigned long long start,
-			      unsigned long long size, int type)
-{
-	int x;
-
-	x = e820.nr_map;
-
-	if (x == E820MAX) {
-		printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
-		return;
-	}
-
-	e820.map[x].addr = start;
-	e820.map[x].size = size;
-	e820.map[x].type = type;
-	e820.nr_map++;
-} /* add_memory_region */
-
-/*
- * Sanitize the BIOS e820 map.
- *
- * Some e820 responses include overlapping entries.  The following
- * replaces the original e820 map with a new one, removing overlaps.
- *
- */
-int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
-{
-	struct change_member *change_tmp;
-	unsigned long current_type, last_type;
-	unsigned long long last_addr;
-	int chgidx, still_changing;
-	int overlap_entries;
-	int new_bios_entry;
-	int old_nr, new_nr, chg_nr;
-	int i;
-
-	/*
-		Visually we're performing the following (1,2,3,4 = memory types)...
-
-		Sample memory map (w/overlaps):
-		   ____22__________________
-		   ______________________4_
-		   ____1111________________
-		   _44_____________________
-		   11111111________________
-		   ____________________33__
-		   ___________44___________
-		   __________33333_________
-		   ______________22________
-		   ___________________2222_
-		   _________111111111______
-		   _____________________11_
-		   _________________4______
-
-		Sanitized equivalent (no overlap):
-		   1_______________________
-		   _44_____________________
-		   ___1____________________
-		   ____22__________________
-		   ______11________________
-		   _________1______________
-		   __________3_____________
-		   ___________44___________
-		   _____________33_________
-		   _______________2________
-		   ________________1_______
-		   _________________4______
-		   ___________________2____
-		   ____________________33__
-		   ______________________4_
-	*/
-	/* if there's only one memory region, don't bother */
-	if (*pnr_map < 2) {
-		return -1;
-	}
-
-	old_nr = *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) {
-			return -1;
-		}
-
-	/* create pointers for initial change-point information (for sorting) */
-	for (i=0; i < 2*old_nr; i++)
-		change_point[i] = &change_point_list[i];
-
-	/* record all known change-points (starting and ending addresses),
-	   omitting those that are for empty memory regions */
-	chgidx = 0;
-	for (i=0; i < old_nr; i++)	{
-		if (biosmap[i].size != 0) {
-			change_point[chgidx]->addr = biosmap[i].addr;
-			change_point[chgidx++]->pbios = &biosmap[i];
-			change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size;
-			change_point[chgidx++]->pbios = &biosmap[i];
-		}
-	}
-	chg_nr = chgidx;    	/* true number of change-points */
-
-	/* sort change-point list by memory addresses (low -> high) */
-	still_changing = 1;
-	while (still_changing)	{
-		still_changing = 0;
-		for (i=1; i < chg_nr; i++)  {
-			/* if <current_addr> > <last_addr>, swap */
-			/* or, if current=<start_addr> & last=<end_addr>, swap */
-			if ((change_point[i]->addr < change_point[i-1]->addr) ||
-				((change_point[i]->addr == change_point[i-1]->addr) &&
-				 (change_point[i]->addr == change_point[i]->pbios->addr) &&
-				 (change_point[i-1]->addr != change_point[i-1]->pbios->addr))
-			   )
-			{
-				change_tmp = change_point[i];
-				change_point[i] = change_point[i-1];
-				change_point[i-1] = change_tmp;
-				still_changing=1;
-			}
-		}
-	}
-
-	/* create a new bios memory map, removing overlaps */
-	overlap_entries=0;	 /* number of entries in the overlap table */
-	new_bios_entry=0;	 /* index for creating new bios map entries */
-	last_type = 0;		 /* start with undefined memory type */
-	last_addr = 0;		 /* start with 0 as last starting address */
-	/* loop through change-points, determining affect on the new bios map */
-	for (chgidx=0; chgidx < chg_nr; chgidx++)
-	{
-		/* keep track of all overlapping bios entries */
-		if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr)
-		{
-			/* add map entry to overlap list (> 1 entry implies an overlap) */
-			overlap_list[overlap_entries++]=change_point[chgidx]->pbios;
-		}
-		else
-		{
-			/* remove entry from list (order independent, so swap with last) */
-			for (i=0; i<overlap_entries; i++)
-			{
-				if (overlap_list[i] == change_point[chgidx]->pbios)
-					overlap_list[i] = overlap_list[overlap_entries-1];
-			}
-			overlap_entries--;
-		}
-		/* if there are overlapping entries, decide which "type" to use */
-		/* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */
-		current_type = 0;
-		for (i=0; i<overlap_entries; i++)
-			if (overlap_list[i]->type > current_type)
-				current_type = overlap_list[i]->type;
-		/* continue building up new bios map based on this information */
-		if (current_type != last_type)	{
-			if (last_type != 0)	 {
-				new_bios[new_bios_entry].size =
-					change_point[chgidx]->addr - last_addr;
-				/* move forward only if the new size was non-zero */
-				if (new_bios[new_bios_entry].size != 0)
-					if (++new_bios_entry >= E820MAX)
-						break; 	/* no more space left for new bios entries */
-			}
-			if (current_type != 0)	{
-				new_bios[new_bios_entry].addr = change_point[chgidx]->addr;
-				new_bios[new_bios_entry].type = current_type;
-				last_addr=change_point[chgidx]->addr;
-			}
-			last_type = current_type;
-		}
-	}
-	new_nr = new_bios_entry;   /* retain count for new bios entries */
-
-	/* copy new bios mapping into original location */
-	memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry));
-	*pnr_map = new_nr;
-
-	return 0;
-}
-
-/*
- * Copy the BIOS e820 map into a safe place.
- *
- * Sanity-check it while we're at it..
- *
- * If we're lucky and live on a modern system, the setup code
- * will have given us a memory map that we can use to properly
- * set up memory.  If we aren't, we'll fake a memory map.
- *
- * We check to see that the memory map contains at least 2 elements
- * before we'll use it, because the detection code in setup.S may
- * not be perfect and most every PC known to man has two memory
- * regions: one from 0 to 640k, and one from 1mb up.  (The IBM
- * thinkpad 560x, for example, does not cooperate with the memory
- * detection code.)
- */
-int __init copy_e820_map(struct e820entry *biosmap, int nr_map)
-{
-	/* Only one memory region (or negative)? Ignore it */
-	if (nr_map < 2)
-		return -1;
-
-	do {
-		u64 start = biosmap->addr;
-		u64 size = biosmap->size;
-		u64 end = start + size;
-		u32 type = biosmap->type;
-
-		/* Overflow in 64 bits? Ignore the memory map. */
-		if (start > end)
-			return -1;
-
-		add_memory_region(start, size, type);
-	} while (biosmap++, --nr_map);
-
-	return 0;
-}
-
-/*
- * Find the highest page frame number we have available
- */
-void __init propagate_e820_map(void)
-{
-	int i;
-
-	max_pfn = 0;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		unsigned long start, end;
-		/* RAM? */
-		if (e820.map[i].type != E820_RAM)
-			continue;
-		start = PFN_UP(e820.map[i].addr);
-		end = PFN_DOWN(e820.map[i].addr + e820.map[i].size);
-		if (start >= end)
-			continue;
-		if (end > max_pfn)
-			max_pfn = end;
-		memory_present(0, start, end);
-	}
-}
-
-/*
- * Register fully available low RAM pages with the bootmem allocator.
- */
-void __init register_bootmem_low_pages(unsigned long max_low_pfn)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		unsigned long curr_pfn, last_pfn, size;
-		/*
-		 * Reserve usable low memory
-		 */
-		if (e820.map[i].type != E820_RAM)
-			continue;
-		/*
-		 * We are rounding up the start address of usable memory:
-		 */
-		curr_pfn = PFN_UP(e820.map[i].addr);
-		if (curr_pfn >= max_low_pfn)
-			continue;
-		/*
-		 * ... and at the end of the usable range downwards:
-		 */
-		last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size);
-
-		if (last_pfn > max_low_pfn)
-			last_pfn = max_low_pfn;
-
-		/*
-		 * .. finally, did all the rounding and playing
-		 * around just make the area go away?
-		 */
-		if (last_pfn <= curr_pfn)
-			continue;
-
-		size = last_pfn - curr_pfn;
-		free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size));
-	}
-}
-
-void __init e820_register_memory(void)
-{
-	unsigned long gapstart, gapsize, round;
-	unsigned long long last;
-	int i;
-
-	/*
-	 * Search for the biggest gap in the low 32 bits of the e820
-	 * memory space.
-	 */
-	last = 0x100000000ull;
-	gapstart = 0x10000000;
-	gapsize = 0x400000;
-	i = e820.nr_map;
-	while (--i >= 0) {
-		unsigned long long start = e820.map[i].addr;
-		unsigned long long end = start + e820.map[i].size;
-
-		/*
-		 * Since "last" is at most 4GB, we know we'll
-		 * fit in 32 bits if this condition is true
-		 */
-		if (last > end) {
-			unsigned long gap = last - end;
-
-			if (gap > gapsize) {
-				gapsize = gap;
-				gapstart = end;
-			}
-		}
-		if (start < last)
-			last = start;
-	}
-
-	/*
-	 * See how much we want to round up: start off with
-	 * rounding to the next 1MB area.
-	 */
-	round = 0x100000;
-	while ((gapsize >> 4) > round)
-		round += round;
-	/* Fun with two's complement */
-	pci_mem_start = (gapstart + round) & -round;
-
-	printk("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n",
-		pci_mem_start, gapstart, gapsize);
-}
-
-void __init print_memory_map(char *who)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		printk(" %s: %016Lx - %016Lx ", who,
-			e820.map[i].addr,
-			e820.map[i].addr + e820.map[i].size);
-		switch (e820.map[i].type) {
-		case E820_RAM:	printk("(usable)\n");
-				break;
-		case E820_RESERVED:
-				printk("(reserved)\n");
-				break;
-		case E820_ACPI:
-				printk("(ACPI data)\n");
-				break;
-		case E820_NVS:
-				printk("(ACPI NVS)\n");
-				break;
-		default:	printk("type %u\n", e820.map[i].type);
-				break;
-		}
-	}
-}
-
-void __init limit_regions(unsigned long long size)
-{
-	unsigned long long current_addr;
-	int i;
-
-	print_memory_map("limit_regions start");
-	for (i = 0; i < e820.nr_map; i++) {
-		current_addr = e820.map[i].addr + e820.map[i].size;
-		if (current_addr < size)
-			continue;
-
-		if (e820.map[i].type != E820_RAM)
-			continue;
-
-		if (e820.map[i].addr >= size) {
-			/*
-			 * This region starts past the end of the
-			 * requested size, skip it completely.
-			 */
-			e820.nr_map = i;
-		} else {
-			e820.nr_map = i + 1;
-			e820.map[i].size -= current_addr - size;
-		}
-		print_memory_map("limit_regions endfor");
-		return;
-	}
-	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.
-  *
-  * Note: this function only works correct if the e820 table is sorted and
-  * not-overlapping, which is the case
-  */
-int __init
-e820_all_mapped(unsigned long s, unsigned long e, unsigned type)
-{
-	u64 start = s;
-	u64 end = e;
-	int i;
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		if (type && ei->type != type)
-			continue;
-		/* is the region (part) in overlap with the current region ?*/
-		if (ei->addr >= end || ei->addr + ei->size <= start)
-			continue;
-		/* if the region is at the beginning of <start,end> we move
-		 * start to the end of the region since it's ok until there
-		 */
-		if (ei->addr <= start)
-			start = ei->addr + ei->size;
-		/* if start is now at or beyond end, we're done, full
-		 * coverage */
-		if (start >= end)
-			return 1; /* we're done */
-	}
-	return 0;
-}
-
-static int __init parse_memmap(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	if (strcmp(arg, "exactmap") == 0) {
-#ifdef CONFIG_CRASH_DUMP
-		/* If we are doing a crash dump, we
-		 * still need to know the real mem
-		 * size before original memory map is
-		 * reset.
-		 */
-		propagate_e820_map();
-		saved_max_pfn = max_pfn;
-#endif
-		e820.nr_map = 0;
-		user_defined_memmap = 1;
-	} else {
-		/* If the user specifies memory size, we
-		 * limit the BIOS-provided memory map to
-		 * that size. exactmap can be used to specify
-		 * the exact map. mem=number can be used to
-		 * trim the existing memory map.
-		 */
-		unsigned long long start_at, mem_size;
-
-		mem_size = memparse(arg, &arg);
-		if (*arg == '@') {
-			start_at = memparse(arg+1, &arg);
-			add_memory_region(start_at, mem_size, E820_RAM);
-		} else if (*arg == '#') {
-			start_at = memparse(arg+1, &arg);
-			add_memory_region(start_at, mem_size, E820_ACPI);
-		} else if (*arg == '$') {
-			start_at = memparse(arg+1, &arg);
-			add_memory_region(start_at, mem_size, E820_RESERVED);
-		} else {
-			limit_regions(mem_size);
-			user_defined_memmap = 1;
-		}
-	}
-	return 0;
-}
-early_param("memmap", parse_memmap);
-void __init update_memory_range(u64 start, u64 size, unsigned old_type,
-				unsigned new_type)
-{
-	int i;
-
-	BUG_ON(old_type == new_type);
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 final_start, final_end;
-		if (ei->type != old_type)
-			continue;
-		/* totally covered? */
-		if (ei->addr >= start && ei->size <= size) {
-			ei->type = new_type;
-			continue;
-		}
-		/* partially covered */
-		final_start = max(start, ei->addr);
-		final_end = min(start + size, ei->addr + ei->size);
-		if (final_start >= final_end)
-			continue;
-		add_memory_region(final_start, final_end - final_start,
-					 new_type);
-	}
-}
-void __init update_e820(void)
-{
-	u8 nr_map;
-
-	nr_map = e820.nr_map;
-	if (sanitize_e820_map(e820.map, &nr_map))
-		return;
-	e820.nr_map = nr_map;
-	printk(KERN_INFO "modified physical RAM map:\n");
-	print_memory_map("modified");
-}

arch/x86/kernel/e820_64.c

@@ -1,952 +0,0 @@
-/*
- * Handle the memory map.
- * The functions here do the job until bootmem takes over.
- *
- *  Getting sanitize_e820_map() in sync with i386 version by applying change:
- *  -  Provisions for empty E820 memory regions (reported by certain BIOSes).
- *     Alex Achenbach <xela@slit.de>, December 2002.
- *  Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
- *
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/ioport.h>
-#include <linux/string.h>
-#include <linux/kexec.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/suspend.h>
-#include <linux/pfn.h>
-
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/e820.h>
-#include <asm/proto.h>
-#include <asm/setup.h>
-#include <asm/sections.h>
-#include <asm/kdebug.h>
-#include <asm/trampoline.h>
-
-struct e820map e820;
-
-/*
- * PFN of last memory page.
- */
-unsigned long end_pfn;
-
-/*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
- */
-unsigned long max_pfn_mapped;
-
-/*
- * Last pfn which the user wants to use.
- */
-static unsigned long __initdata end_user_pfn = MAXMEM>>PAGE_SHIFT;
-
-/*
- * Early reserved memory areas.
- */
-#define MAX_EARLY_RES 20
-
-struct early_res {
-	unsigned long start, end;
-	char name[16];
-};
-static struct early_res early_res[MAX_EARLY_RES] __initdata = {
-	{ 0, PAGE_SIZE, "BIOS data page" },			/* BIOS data page */
-#ifdef CONFIG_X86_TRAMPOLINE
-	{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
-#endif
-	{}
-};
-
-void __init reserve_early(unsigned long start, unsigned long end, char *name)
-{
-	int i;
-	struct early_res *r;
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
-		r = &early_res[i];
-		if (end > r->start && start < r->end)
-			panic("Overlapping early reservations %lx-%lx %s to %lx-%lx %s\n",
-			      start, end - 1, name?name:"", r->start, r->end - 1, r->name);
-	}
-	if (i >= MAX_EARLY_RES)
-		panic("Too many early reservations");
-	r = &early_res[i];
-	r->start = start;
-	r->end = end;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-}
-
-void __init free_early(unsigned long start, unsigned long end)
-{
-	struct early_res *r;
-	int i, j;
-
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
-		r = &early_res[i];
-		if (start == r->start && end == r->end)
-			break;
-	}
-	if (i >= MAX_EARLY_RES || !early_res[i].end)
-		panic("free_early on not reserved area: %lx-%lx!", start, end);
-
-	for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
-		;
-
-	memmove(&early_res[i], &early_res[i + 1],
-	       (j - 1 - i) * sizeof(struct early_res));
-
-	early_res[j - 1].end = 0;
-}
-
-void __init early_res_to_bootmem(unsigned long start, unsigned long end)
-{
-	int i;
-	unsigned long final_start, final_end;
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		final_start = max(start, r->start);
-		final_end = min(end, r->end);
-		if (final_start >= final_end)
-			continue;
-		printk(KERN_INFO "  early res: %d [%lx-%lx] %s\n", i,
-			final_start, final_end - 1, r->name);
-		reserve_bootmem_generic(final_start, final_end - final_start);
-	}
-}
-
-/* Check for already reserved areas */
-static inline int __init
-bad_addr(unsigned long *addrp, unsigned long size, unsigned long align)
-{
-	int i;
-	unsigned long addr = *addrp, last;
-	int changed = 0;
-again:
-	last = addr + size;
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		if (last >= r->start && addr < r->end) {
-			*addrp = addr = round_up(r->end, align);
-			changed = 1;
-			goto again;
-		}
-	}
-	return changed;
-}
-
-/* Check for already reserved areas */
-static inline int __init
-bad_addr_size(unsigned long *addrp, unsigned long *sizep, unsigned long align)
-{
-	int i;
-	unsigned long addr = *addrp, last;
-	unsigned long size = *sizep;
-	int changed = 0;
-again:
-	last = addr + size;
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		if (last > r->start && addr < r->start) {
-			size = r->start - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last > r->end && addr < r->end) {
-			addr = round_up(r->end, align);
-			size = last - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last <= r->end && addr >= r->start) {
-			(*sizep)++;
-			return 0;
-		}
-	}
-	if (changed) {
-		*addrp = addr;
-		*sizep = size;
-	}
-	return changed;
-}
-/*
- * This function checks if any part of the range <start,end> is mapped
- * with type.
- */
-int
-e820_any_mapped(unsigned long start, unsigned long end, unsigned type)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		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.
- *
- * Note: this function only works correct if the e820 table is sorted and
- * not-overlapping, which is the case
- */
-int __init e820_all_mapped(unsigned long start, unsigned long end,
-			   unsigned type)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-
-		if (type && ei->type != type)
-			continue;
-		/* is the region (part) in overlap with the current region ?*/
-		if (ei->addr >= end || ei->addr + ei->size <= start)
-			continue;
-
-		/* if the region is at the beginning of <start,end> we move
-		 * start to the end of the region since it's ok until there
-		 */
-		if (ei->addr <= start)
-			start = ei->addr + ei->size;
-		/*
-		 * if start is now at or beyond end, we're done, full
-		 * coverage
-		 */
-		if (start >= end)
-			return 1;
-	}
-	return 0;
-}
-
-/*
- * Find a free area with specified alignment in a specific range.
- */
-unsigned long __init find_e820_area(unsigned long start, unsigned long end,
-				    unsigned long size, unsigned long align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		unsigned long addr, last;
-		unsigned long ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-		addr = round_up(ei->addr, align);
-		ei_last = ei->addr + ei->size;
-		if (addr < start)
-			addr = round_up(start, align);
-		if (addr >= ei_last)
-			continue;
-		while (bad_addr(&addr, size, align) && addr+size <= ei_last)
-			;
-		last = addr + size;
-		if (last > ei_last)
-			continue;
-		if (last > end)
-			continue;
-		return addr;
-	}
-	return -1UL;
-}
-
-/*
- * Find next free range after *start
- */
-unsigned long __init find_e820_area_size(unsigned long start,
-					 unsigned long *sizep,
-					 unsigned long align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		unsigned long addr, last;
-		unsigned long ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-		addr = round_up(ei->addr, align);
-		ei_last = ei->addr + ei->size;
-		if (addr < start)
-			addr = round_up(start, align);
-		if (addr >= ei_last)
-			continue;
-		*sizep = ei_last - addr;
-		while (bad_addr_size(&addr, sizep, align) &&
-			addr + *sizep <= ei_last)
-			;
-		last = addr + *sizep;
-		if (last > ei_last)
-			continue;
-		return addr;
-	}
-	return -1UL;
-
-}
-/*
- * Find the highest page frame number we have available
- */
-unsigned long __init e820_end_of_ram(void)
-{
-	unsigned long end_pfn;
-
-	end_pfn = find_max_pfn_with_active_regions();
-
-	if (end_pfn > max_pfn_mapped)
-		max_pfn_mapped = end_pfn;
-	if (max_pfn_mapped > MAXMEM>>PAGE_SHIFT)
-		max_pfn_mapped = MAXMEM>>PAGE_SHIFT;
-	if (end_pfn > end_user_pfn)
-		end_pfn = end_user_pfn;
-	if (end_pfn > max_pfn_mapped)
-		end_pfn = max_pfn_mapped;
-
-	printk(KERN_INFO "max_pfn_mapped = %lu\n", max_pfn_mapped);
-	return end_pfn;
-}
-
-/*
- * Mark e820 reserved areas as busy for the resource manager.
- */
-void __init e820_reserve_resources(void)
-{
-	int i;
-	struct resource *res;
-
-	res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map);
-	for (i = 0; i < e820.nr_map; i++) {
-		switch (e820.map[i].type) {
-		case E820_RAM:	res->name = "System RAM"; break;
-		case E820_ACPI:	res->name = "ACPI Tables"; break;
-		case E820_NVS:	res->name = "ACPI Non-volatile Storage"; break;
-		default:	res->name = "reserved";
-		}
-		res->start = e820.map[i].addr;
-		res->end = res->start + e820.map[i].size - 1;
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
-		insert_resource(&iomem_resource, res);
-		res++;
-	}
-}
-
-/*
- * Find the ranges of physical addresses that do not correspond to
- * e820 RAM areas and mark the corresponding pages as nosave for software
- * suspend and suspend to RAM.
- *
- * This function requires the e820 map to be sorted and without any
- * overlapping entries and assumes the first e820 area to be RAM.
- */
-void __init e820_mark_nosave_regions(void)
-{
-	int i;
-	unsigned long paddr;
-
-	paddr = round_down(e820.map[0].addr + e820.map[0].size, PAGE_SIZE);
-	for (i = 1; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-
-		if (paddr < ei->addr)
-			register_nosave_region(PFN_DOWN(paddr),
-						PFN_UP(ei->addr));
-
-		paddr = round_down(ei->addr + ei->size, PAGE_SIZE);
-		if (ei->type != E820_RAM)
-			register_nosave_region(PFN_UP(ei->addr),
-						PFN_DOWN(paddr));
-
-		if (paddr >= (end_pfn << PAGE_SHIFT))
-			break;
-	}
-}
-
-/*
- * Finds an active region in the address range from start_pfn to end_pfn and
- * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
- */
-static int __init e820_find_active_region(const struct e820entry *ei,
-					  unsigned long start_pfn,
-					  unsigned long end_pfn,
-					  unsigned long *ei_startpfn,
-					  unsigned long *ei_endpfn)
-{
-	*ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT;
-	*ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE) >> PAGE_SHIFT;
-
-	/* Skip map entries smaller than a page */
-	if (*ei_startpfn >= *ei_endpfn)
-		return 0;
-
-	/* Check if max_pfn_mapped should be updated */
-	if (ei->type != E820_RAM && *ei_endpfn > max_pfn_mapped)
-		max_pfn_mapped = *ei_endpfn;
-
-	/* Skip if map is outside the node */
-	if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
-				    *ei_startpfn >= end_pfn)
-		return 0;
-
-	/* Check for overlaps */
-	if (*ei_startpfn < start_pfn)
-		*ei_startpfn = start_pfn;
-	if (*ei_endpfn > end_pfn)
-		*ei_endpfn = end_pfn;
-
-	/* Obey end_user_pfn to save on memmap */
-	if (*ei_startpfn >= end_user_pfn)
-		return 0;
-	if (*ei_endpfn > end_user_pfn)
-		*ei_endpfn = end_user_pfn;
-
-	return 1;
-}
-
-/* Walk the e820 map and register active regions within a node */
-void __init
-e820_register_active_regions(int nid, unsigned long start_pfn,
-							unsigned long end_pfn)
-{
-	unsigned long ei_startpfn;
-	unsigned long ei_endpfn;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++)
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, end_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			add_active_range(nid, ei_startpfn, ei_endpfn);
-}
-
-/*
- * Add a memory region to the kernel e820 map.
- */
-void __init add_memory_region(unsigned long start, unsigned long size, int type)
-{
-	int x = e820.nr_map;
-
-	if (x == E820MAX) {
-		printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
-		return;
-	}
-
-	e820.map[x].addr = start;
-	e820.map[x].size = size;
-	e820.map[x].type = type;
-	e820.nr_map++;
-}
-
-/*
- * Find the hole size (in bytes) in the memory range.
- * @start: starting address of the memory range to scan
- * @end: ending address of the memory range to scan
- */
-unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long end_pfn = end >> PAGE_SHIFT;
-	unsigned long ei_startpfn, ei_endpfn, ram = 0;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, end_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			ram += ei_endpfn - ei_startpfn;
-	}
-	return end - start - (ram << PAGE_SHIFT);
-}
-
-static void __init e820_print_map(char *who)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		printk(KERN_INFO " %s: %016Lx - %016Lx ", who,
-		       (unsigned long long) e820.map[i].addr,
-		       (unsigned long long)
-		       (e820.map[i].addr + e820.map[i].size));
-		switch (e820.map[i].type) {
-		case E820_RAM:
-			printk(KERN_CONT "(usable)\n");
-			break;
-		case E820_RESERVED:
-			printk(KERN_CONT "(reserved)\n");
-			break;
-		case E820_ACPI:
-			printk(KERN_CONT "(ACPI data)\n");
-			break;
-		case E820_NVS:
-			printk(KERN_CONT "(ACPI NVS)\n");
-			break;
-		default:
-			printk(KERN_CONT "type %u\n", e820.map[i].type);
-			break;
-		}
-	}
-}
-
-/*
- * Sanitize the BIOS e820 map.
- *
- * Some e820 responses include overlapping entries. The following
- * replaces the original e820 map with a new one, removing overlaps.
- *
- */
-static int __init sanitize_e820_map(struct e820entry *biosmap, char *pnr_map)
-{
-	struct change_member {
-		struct e820entry *pbios; /* pointer to original bios entry */
-		unsigned long long addr; /* address for this change point */
-	};
-	static struct change_member change_point_list[2*E820MAX] __initdata;
-	static struct change_member *change_point[2*E820MAX] __initdata;
-	static struct e820entry *overlap_list[E820MAX] __initdata;
-	static struct e820entry new_bios[E820MAX] __initdata;
-	struct change_member *change_tmp;
-	unsigned long current_type, last_type;
-	unsigned long long last_addr;
-	int chgidx, still_changing;
-	int overlap_entries;
-	int new_bios_entry;
-	int old_nr, new_nr, chg_nr;
-	int i;
-
-	/*
-		Visually we're performing the following
-		(1,2,3,4 = memory types)...
-
-		Sample memory map (w/overlaps):
-		   ____22__________________
-		   ______________________4_
-		   ____1111________________
-		   _44_____________________
-		   11111111________________
-		   ____________________33__
-		   ___________44___________
-		   __________33333_________
-		   ______________22________
-		   ___________________2222_
-		   _________111111111______
-		   _____________________11_
-		   _________________4______
-
-		Sanitized equivalent (no overlap):
-		   1_______________________
-		   _44_____________________
-		   ___1____________________
-		   ____22__________________
-		   ______11________________
-		   _________1______________
-		   __________3_____________
-		   ___________44___________
-		   _____________33_________
-		   _______________2________
-		   ________________1_______
-		   _________________4______
-		   ___________________2____
-		   ____________________33__
-		   ______________________4_
-	*/
-
-	/* if there's only one memory region, don't bother */
-	if (*pnr_map < 2)
-		return -1;
-
-	old_nr = *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)
-			return -1;
-
-	/* create pointers for initial change-point information (for sorting) */
-	for (i = 0; i < 2 * old_nr; i++)
-		change_point[i] = &change_point_list[i];
-
-	/* record all known change-points (starting and ending addresses),
-	   omitting those that are for empty memory regions */
-	chgidx = 0;
-	for (i = 0; i < old_nr; i++)	{
-		if (biosmap[i].size != 0) {
-			change_point[chgidx]->addr = biosmap[i].addr;
-			change_point[chgidx++]->pbios = &biosmap[i];
-			change_point[chgidx]->addr = biosmap[i].addr +
-				biosmap[i].size;
-			change_point[chgidx++]->pbios = &biosmap[i];
-		}
-	}
-	chg_nr = chgidx;
-
-	/* sort change-point list by memory addresses (low -> high) */
-	still_changing = 1;
-	while (still_changing)	{
-		still_changing = 0;
-		for (i = 1; i < chg_nr; i++)  {
-			unsigned long long curaddr, lastaddr;
-			unsigned long long curpbaddr, lastpbaddr;
-
-			curaddr = change_point[i]->addr;
-			lastaddr = change_point[i - 1]->addr;
-			curpbaddr = change_point[i]->pbios->addr;
-			lastpbaddr = change_point[i - 1]->pbios->addr;
-
-			/*
-			 * swap entries, when:
-			 *
-			 * curaddr > lastaddr or
-			 * curaddr == lastaddr and curaddr == curpbaddr and
-			 * lastaddr != lastpbaddr
-			 */
-			if (curaddr < lastaddr ||
-			    (curaddr == lastaddr && curaddr == curpbaddr &&
-			     lastaddr != lastpbaddr)) {
-				change_tmp = change_point[i];
-				change_point[i] = change_point[i-1];
-				change_point[i-1] = change_tmp;
-				still_changing = 1;
-			}
-		}
-	}
-
-	/* create a new bios memory map, removing overlaps */
-	overlap_entries = 0;	 /* number of entries in the overlap table */
-	new_bios_entry = 0;	 /* index for creating new bios map entries */
-	last_type = 0;		 /* start with undefined memory type */
-	last_addr = 0;		 /* start with 0 as last starting address */
-
-	/* loop through change-points, determining affect on the new bios map */
-	for (chgidx = 0; chgidx < chg_nr; chgidx++) {
-		/* keep track of all overlapping bios entries */
-		if (change_point[chgidx]->addr ==
-		    change_point[chgidx]->pbios->addr) {
-			/*
-			 * add map entry to overlap list (> 1 entry
-			 * implies an overlap)
-			 */
-			overlap_list[overlap_entries++] =
-				change_point[chgidx]->pbios;
-		} else {
-			/*
-			 * remove entry from list (order independent,
-			 * so swap with last)
-			 */
-			for (i = 0; i < overlap_entries; i++) {
-				if (overlap_list[i] ==
-				    change_point[chgidx]->pbios)
-					overlap_list[i] =
-						overlap_list[overlap_entries-1];
-			}
-			overlap_entries--;
-		}
-		/*
-		 * if there are overlapping entries, decide which
-		 * "type" to use (larger value takes precedence --
-		 * 1=usable, 2,3,4,4+=unusable)
-		 */
-		current_type = 0;
-		for (i = 0; i < overlap_entries; i++)
-			if (overlap_list[i]->type > current_type)
-				current_type = overlap_list[i]->type;
-		/*
-		 * continue building up new bios map based on this
-		 * information
-		 */
-		if (current_type != last_type)	{
-			if (last_type != 0)	 {
-				new_bios[new_bios_entry].size =
-					change_point[chgidx]->addr - last_addr;
-				/*
-				 * move forward only if the new size
-				 * was non-zero
-				 */
-				if (new_bios[new_bios_entry].size != 0)
-					/*
-					 * no more space left for new
-					 * bios entries ?
-					 */
-					if (++new_bios_entry >= E820MAX)
-						break;
-			}
-			if (current_type != 0)	{
-				new_bios[new_bios_entry].addr =
-					change_point[chgidx]->addr;
-				new_bios[new_bios_entry].type = current_type;
-				last_addr = change_point[chgidx]->addr;
-			}
-			last_type = current_type;
-		}
-	}
-	/* retain count for new bios entries */
-	new_nr = new_bios_entry;
-
-	/* copy new bios mapping into original location */
-	memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry));
-	*pnr_map = new_nr;
-
-	return 0;
-}
-
-/*
- * Copy the BIOS e820 map into a safe place.
- *
- * Sanity-check it while we're at it..
- *
- * If we're lucky and live on a modern system, the setup code
- * will have given us a memory map that we can use to properly
- * set up memory.  If we aren't, we'll fake a memory map.
- */
-static int __init copy_e820_map(struct e820entry *biosmap, int nr_map)
-{
-	/* Only one memory region (or negative)? Ignore it */
-	if (nr_map < 2)
-		return -1;
-
-	do {
-		u64 start = biosmap->addr;
-		u64 size = biosmap->size;
-		u64 end = start + size;
-		u32 type = biosmap->type;
-
-		/* Overflow in 64 bits? Ignore the memory map. */
-		if (start > end)
-			return -1;
-
-		add_memory_region(start, size, type);
-	} while (biosmap++, --nr_map);
-	return 0;
-}
-
-static void early_panic(char *msg)
-{
-	early_printk(msg);
-	panic(msg);
-}
-
-/* We're not void only for x86 32-bit compat */
-char * __init machine_specific_memory_setup(void)
-{
-	char *who = "BIOS-e820";
-	/*
-	 * Try to copy the BIOS-supplied E820-map.
-	 *
-	 * Otherwise fake a memory map; one section from 0k->640k,
-	 * the next section from 1mb->appropriate_mem_k
-	 */
-	sanitize_e820_map(boot_params.e820_map, &boot_params.e820_entries);
-	if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) < 0)
-		early_panic("Cannot find a valid memory map");
-	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
-	e820_print_map(who);
-
-	/* In case someone cares... */
-	return who;
-}
-
-static int __init parse_memopt(char *p)
-{
-	if (!p)
-		return -EINVAL;
-	end_user_pfn = memparse(p, &p);
-	end_user_pfn >>= PAGE_SHIFT;
-	return 0;
-}
-early_param("mem", parse_memopt);
-
-static int userdef __initdata;
-
-static int __init parse_memmap_opt(char *p)
-{
-	char *oldp;
-	unsigned long long start_at, mem_size;
-
-	if (!strcmp(p, "exactmap")) {
-#ifdef CONFIG_CRASH_DUMP
-		/*
-		 * If we are doing a crash dump, we still need to know
-		 * the real mem size before original memory map is
-		 * reset.
-		 */
-		e820_register_active_regions(0, 0, -1UL);
-		saved_max_pfn = e820_end_of_ram();
-		remove_all_active_ranges();
-#endif
-		max_pfn_mapped = 0;
-		e820.nr_map = 0;
-		userdef = 1;
-		return 0;
-	}
-
-	oldp = p;
-	mem_size = memparse(p, &p);
-	if (p == oldp)
-		return -EINVAL;
-
-	userdef = 1;
-	if (*p == '@') {
-		start_at = memparse(p+1, &p);
-		add_memory_region(start_at, mem_size, E820_RAM);
-	} else if (*p == '#') {
-		start_at = memparse(p+1, &p);
-		add_memory_region(start_at, mem_size, E820_ACPI);
-	} else if (*p == '$') {
-		start_at = memparse(p+1, &p);
-		add_memory_region(start_at, mem_size, E820_RESERVED);
-	} else {
-		end_user_pfn = (mem_size >> PAGE_SHIFT);
-	}
-	return *p == '\0' ? 0 : -EINVAL;
-}
-early_param("memmap", parse_memmap_opt);
-
-void __init finish_e820_parsing(void)
-{
-	if (userdef) {
-		char nr = e820.nr_map;
-
-		if (sanitize_e820_map(e820.map, &nr) < 0)
-			early_panic("Invalid user supplied memory map");
-		e820.nr_map = nr;
-
-		printk(KERN_INFO "user-defined physical RAM map:\n");
-		e820_print_map("user");
-	}
-}
-
-void __init update_memory_range(u64 start, u64 size, unsigned old_type,
-				unsigned new_type)
-{
-	int i;
-
-	BUG_ON(old_type == new_type);
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 final_start, final_end;
-		if (ei->type != old_type)
-			continue;
-		/* totally covered? */
-		if (ei->addr >= start && ei->size <= size) {
-			ei->type = new_type;
-			continue;
-		}
-		/* partially covered */
-		final_start = max(start, ei->addr);
-		final_end = min(start + size, ei->addr + ei->size);
-		if (final_start >= final_end)
-			continue;
-		add_memory_region(final_start, final_end - final_start,
-					 new_type);
-	}
-}
-
-void __init update_e820(void)
-{
-	u8 nr_map;
-
-	nr_map = e820.nr_map;
-	if (sanitize_e820_map(e820.map, &nr_map))
-		return;
-	e820.nr_map = nr_map;
-	printk(KERN_INFO "modified physical RAM map:\n");
-	e820_print_map("modified");
-}
-
-unsigned long pci_mem_start = 0xaeedbabe;
-EXPORT_SYMBOL(pci_mem_start);
-
-/*
- * Search for the biggest gap in the low 32 bits of the e820
- * memory space.  We pass this space to PCI to assign MMIO resources
- * for hotplug or unconfigured devices in.
- * Hopefully the BIOS let enough space left.
- */
-__init void e820_setup_gap(void)
-{
-	unsigned long gapstart, gapsize, round;
-	unsigned long last;
-	int i;
-	int found = 0;
-
-	last = 0x100000000ull;
-	gapstart = 0x10000000;
-	gapsize = 0x400000;
-	i = e820.nr_map;
-	while (--i >= 0) {
-		unsigned long long start = e820.map[i].addr;
-		unsigned long long end = start + e820.map[i].size;
-
-		/*
-		 * Since "last" is at most 4GB, we know we'll
-		 * fit in 32 bits if this condition is true
-		 */
-		if (last > end) {
-			unsigned long gap = last - end;
-
-			if (gap > gapsize) {
-				gapsize = gap;
-				gapstart = end;
-				found = 1;
-			}
-		}
-		if (start < last)
-			last = start;
-	}
-
-	if (!found) {
-		gapstart = (end_pfn << PAGE_SHIFT) + 1024*1024;
-		printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit "
-		       "address range\n"
-		       KERN_ERR "PCI: Unassigned devices with 32bit resource "
-		       "registers may break!\n");
-	}
-
-	/*
-	 * See how much we want to round up: start off with
-	 * rounding to the next 1MB area.
-	 */
-	round = 0x100000;
-	while ((gapsize >> 4) > round)
-		round += round;
-	/* Fun with two's complement */
-	pci_mem_start = (gapstart + round) & -round;
-
-	printk(KERN_INFO
-	       "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
-	       pci_mem_start, gapstart, gapsize);
-}
-
-int __init arch_get_ram_range(int slot, u64 *addr, u64 *size)
-{
-	int i;
-
-	if (slot < 0 || slot >= e820.nr_map)
-		return -1;
-	for (i = slot; i < e820.nr_map; i++) {
-		if (e820.map[i].type != E820_RAM)
-			continue;
-		break;
-	}
-	if (i == e820.nr_map || e820.map[i].addr > (max_pfn << PAGE_SHIFT))
-		return -1;
-	*addr = e820.map[i].addr;
-	*size = min_t(u64, e820.map[i].size + e820.map[i].addr,
-		max_pfn << PAGE_SHIFT) - *addr;
-	return i + 1;
-}

arch/x86/kernel/early-quirks.c

@@ -50,7 +50,7 @@ static void __init fix_hypertransport_config(int num, int slot, int func)
 static void __init via_bugs(int  num, int slot, int func)
 {
 #ifdef CONFIG_GART_IOMMU
-	if ((end_pfn > MAX_DMA32_PFN ||  force_iommu) &&
+	if ((max_pfn > MAX_DMA32_PFN ||  force_iommu) &&
 	    !gart_iommu_aperture_allowed) {
 		printk(KERN_INFO
 		       "Looks like a VIA chipset. Disabling IOMMU."
@@ -98,17 +98,6 @@ static void __init nvidia_bugs(int num, int slot, int func)
 
 }
 
-static void __init ati_bugs(int num, int slot, int func)
-{
-#ifdef CONFIG_X86_IO_APIC
-	if (timer_over_8254 == 1) {
-		timer_over_8254 = 0;
-		printk(KERN_INFO
-		"ATI board detected. Disabling timer routing over 8254.\n");
-	}
-#endif
-}
-
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -126,8 +115,6 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
 	{ PCI_VENDOR_ID_VIA, PCI_ANY_ID,
 	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, via_bugs },
-	{ PCI_VENDOR_ID_ATI, PCI_ANY_ID,
-	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, ati_bugs },
 	{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
 	  PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, fix_hypertransport_config },
 	{}

arch/x86/kernel/efi.c

@@ -64,6 +64,17 @@ static int __init setup_noefi(char *arg)
 }
 early_param("noefi", setup_noefi);
 
+int add_efi_memmap;
+EXPORT_SYMBOL(add_efi_memmap);
+
+static int __init setup_add_efi_memmap(char *arg)
+{
+	add_efi_memmap = 1;
+	return 0;
+}
+early_param("add_efi_memmap", setup_add_efi_memmap);
+
+
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	return efi_call_virt2(get_time, tm, tc);
@@ -213,6 +224,50 @@ unsigned long efi_get_time(void)
 		      eft.minute, eft.second);
 }
 
+/*
+ * Tell the kernel about the EFI memory map.  This might include
+ * more than the max 128 entries that can fit in the e820 legacy
+ * (zeropage) memory map.
+ */
+
+static void __init do_add_efi_memmap(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		int e820_type;
+
+		if (md->attribute & EFI_MEMORY_WB)
+			e820_type = E820_RAM;
+		else
+			e820_type = E820_RESERVED;
+		e820_add_region(start, size, e820_type);
+	}
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+}
+
+void __init efi_reserve_early(void)
+{
+	unsigned long pmap;
+
+#ifdef CONFIG_X86_32
+	pmap = boot_params.efi_info.efi_memmap;
+#else
+	pmap = (boot_params.efi_info.efi_memmap |
+		((__u64)boot_params.efi_info.efi_memmap_hi<<32));
+#endif
+	memmap.phys_map = (void *)pmap;
+	memmap.nr_map = boot_params.efi_info.efi_memmap_size /
+		boot_params.efi_info.efi_memdesc_size;
+	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
+	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
+	reserve_early(pmap, pmap + memmap.nr_map * memmap.desc_size,
+		      "EFI memmap");
+}
+
 #if EFI_DEBUG
 static void __init print_efi_memmap(void)
 {
@@ -244,19 +299,11 @@ void __init efi_init(void)
 
 #ifdef CONFIG_X86_32
 	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
-	memmap.phys_map = (void *)boot_params.efi_info.efi_memmap;
 #else
 	efi_phys.systab = (efi_system_table_t *)
 		(boot_params.efi_info.efi_systab |
 		 ((__u64)boot_params.efi_info.efi_systab_hi<<32));
-	memmap.phys_map = (void *)
-		(boot_params.efi_info.efi_memmap |
-		 ((__u64)boot_params.efi_info.efi_memmap_hi<<32));
 #endif
-	memmap.nr_map = boot_params.efi_info.efi_memmap_size /
-		boot_params.efi_info.efi_memdesc_size;
-	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
-	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
 
 	efi.systab = early_ioremap((unsigned long)efi_phys.systab,
 				   sizeof(efi_system_table_t));
@@ -370,6 +417,8 @@ void __init efi_init(void)
 	if (memmap.desc_size != sizeof(efi_memory_desc_t))
 		printk(KERN_WARNING "Kernel-defined memdesc"
 		       "doesn't match the one from EFI!\n");
+	if (add_efi_memmap)
+		do_add_efi_memmap();
 
 	/* Setup for EFI runtime service */
 	reboot_type = BOOT_EFI;
@@ -424,7 +473,7 @@ void __init efi_enter_virtual_mode(void)
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
 
-		if (PFN_UP(end) <= max_pfn_mapped)
+		if (PFN_UP(end) <= max_low_pfn_mapped)
 			va = __va(md->phys_addr);
 		else
 			va = efi_ioremap(md->phys_addr, size);

arch/x86/kernel/efi_64.c

@@ -97,13 +97,7 @@ void __init efi_call_phys_epilog(void)
 	early_runtime_code_mapping_set_exec(0);
 }
 
-void __init efi_reserve_bootmem(void)
-{
-	reserve_bootmem_generic((unsigned long)memmap.phys_map,
-				memmap.nr_map * memmap.desc_size);
-}
-
-void __iomem * __init efi_ioremap(unsigned long phys_addr, unsigned long size)
+void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size)
 {
 	static unsigned pages_mapped __initdata;
 	unsigned i, pages;

arch/x86/kernel/entry_32.S

@@ -51,14 +51,14 @@
 #include <asm/percpu.h>
 #include <asm/dwarf2.h>
 #include <asm/processor-flags.h>
-#include "irq_vectors.h"
+#include <asm/irq_vectors.h>
 
 /*
  * We use macros for low-level operations which need to be overridden
  * for paravirtualization.  The following will never clobber any registers:
  *   INTERRUPT_RETURN (aka. "iret")
  *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
- *   ENABLE_INTERRUPTS_SYSCALL_RET (aka "sti; sysexit").
+ *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
  *
  * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
  * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
@@ -349,7 +349,7 @@ sysenter_past_esp:
 	xorl %ebp,%ebp
 	TRACE_IRQS_ON
 1:	mov  PT_FS(%esp), %fs
-	ENABLE_INTERRUPTS_SYSCALL_RET
+	ENABLE_INTERRUPTS_SYSEXIT
 	CFI_ENDPROC
 .pushsection .fixup,"ax"
 2:	movl $0,PT_FS(%esp)
@@ -874,10 +874,10 @@ ENTRY(native_iret)
 .previous
 END(native_iret)
 
-ENTRY(native_irq_enable_syscall_ret)
+ENTRY(native_irq_enable_sysexit)
 	sti
 	sysexit
-END(native_irq_enable_syscall_ret)
+END(native_irq_enable_sysexit)
 #endif
 
 KPROBE_ENTRY(int3)
@@ -1024,6 +1024,7 @@ ENTRY(xen_sysenter_target)
 	RING0_INT_FRAME
 	addl $5*4, %esp		/* remove xen-provided frame */
 	jmp sysenter_past_esp
+	CFI_ENDPROC
 
 ENTRY(xen_hypervisor_callback)
 	CFI_STARTPROC

arch/x86/kernel/entry_64.S

@@ -59,8 +59,7 @@
 #endif	
 
 #ifdef CONFIG_PARAVIRT
-ENTRY(native_irq_enable_syscall_ret)
-	movq	%gs:pda_oldrsp,%rsp
+ENTRY(native_usergs_sysret64)
 	swapgs
 	sysretq
 #endif /* CONFIG_PARAVIRT */
@@ -104,7 +103,7 @@ ENTRY(native_irq_enable_syscall_ret)
 	.macro FAKE_STACK_FRAME child_rip
 	/* push in order ss, rsp, eflags, cs, rip */
 	xorl %eax, %eax
-	pushq %rax /* ss */
+	pushq $__KERNEL_DS /* ss */
 	CFI_ADJUST_CFA_OFFSET	8
 	/*CFI_REL_OFFSET	ss,0*/
 	pushq %rax /* rsp */
@@ -169,13 +168,13 @@ ENTRY(ret_from_fork)
 	CFI_ADJUST_CFA_OFFSET -4
 	call schedule_tail
 	GET_THREAD_INFO(%rcx)
-	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx)
+	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
 	jnz rff_trace
 rff_action:	
 	RESTORE_REST
 	testl $3,CS-ARGOFFSET(%rsp)	# from kernel_thread?
 	je   int_ret_from_sys_call
-	testl $_TIF_IA32,threadinfo_flags(%rcx)
+	testl $_TIF_IA32,TI_flags(%rcx)
 	jnz  int_ret_from_sys_call
 	RESTORE_TOP_OF_STACK %rdi,ARGOFFSET
 	jmp ret_from_sys_call
@@ -244,7 +243,8 @@ ENTRY(system_call_after_swapgs)
 	movq  %rcx,RIP-ARGOFFSET(%rsp)
 	CFI_REL_OFFSET rip,RIP-ARGOFFSET
 	GET_THREAD_INFO(%rcx)
-	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx)
+	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+		TI_flags(%rcx)
 	jnz tracesys
 	cmpq $__NR_syscall_max,%rax
 	ja badsys
@@ -263,7 +263,7 @@ sysret_check:
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	movl threadinfo_flags(%rcx),%edx
+	movl TI_flags(%rcx),%edx
 	andl %edi,%edx
 	jnz  sysret_careful 
 	CFI_REMEMBER_STATE
@@ -275,7 +275,8 @@ sysret_check:
 	CFI_REGISTER	rip,rcx
 	RESTORE_ARGS 0,-ARG_SKIP,1
 	/*CFI_REGISTER	rflags,r11*/
-	ENABLE_INTERRUPTS_SYSCALL_RET
+	movq	%gs:pda_oldrsp, %rsp
+	USERGS_SYSRET64
 
 	CFI_RESTORE_STATE
 	/* Handle reschedules */
@@ -305,7 +306,7 @@ sysret_signal:
 	leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1
 	xorl %esi,%esi # oldset -> arg2
 	call ptregscall_common
-1:	movl $_TIF_NEED_RESCHED,%edi
+1:	movl $_TIF_WORK_MASK,%edi
 	/* Use IRET because user could have changed frame. This
 	   works because ptregscall_common has called FIXUP_TOP_OF_STACK. */
 	DISABLE_INTERRUPTS(CLBR_NONE)
@@ -347,10 +348,10 @@ int_ret_from_sys_call:
 int_with_check:
 	LOCKDEP_SYS_EXIT_IRQ
 	GET_THREAD_INFO(%rcx)
-	movl threadinfo_flags(%rcx),%edx
+	movl TI_flags(%rcx),%edx
 	andl %edi,%edx
 	jnz   int_careful
-	andl    $~TS_COMPAT,threadinfo_status(%rcx)
+	andl    $~TS_COMPAT,TI_status(%rcx)
 	jmp   retint_swapgs
 
 	/* Either reschedule or signal or syscall exit tracking needed. */
@@ -393,7 +394,7 @@ int_signal:
 	movq %rsp,%rdi		# &ptregs -> arg1
 	xorl %esi,%esi		# oldset -> arg2
 	call do_notify_resume
-1:	movl $_TIF_NEED_RESCHED,%edi	
+1:	movl $_TIF_WORK_MASK,%edi
 int_restore_rest:
 	RESTORE_REST
 	DISABLE_INTERRUPTS(CLBR_NONE)
@@ -420,7 +421,6 @@ END(\label)
 	PTREGSCALL stub_clone, sys_clone, %r8
 	PTREGSCALL stub_fork, sys_fork, %rdi
 	PTREGSCALL stub_vfork, sys_vfork, %rdi
-	PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx
 	PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
 	PTREGSCALL stub_iopl, sys_iopl, %rsi
 
@@ -559,7 +559,7 @@ retint_with_reschedule:
 	movl $_TIF_WORK_MASK,%edi
 retint_check:
 	LOCKDEP_SYS_EXIT_IRQ
-	movl threadinfo_flags(%rcx),%edx
+	movl TI_flags(%rcx),%edx
 	andl %edi,%edx
 	CFI_REMEMBER_STATE
 	jnz  retint_careful
@@ -647,17 +647,16 @@ retint_signal:
 	RESTORE_REST
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	movl $_TIF_NEED_RESCHED,%edi
 	GET_THREAD_INFO(%rcx)
-	jmp retint_check
+	jmp retint_with_reschedule
 
 #ifdef CONFIG_PREEMPT
 	/* Returning to kernel space. Check if we need preemption */
 	/* rcx:	 threadinfo. interrupts off. */
 ENTRY(retint_kernel)
-	cmpl $0,threadinfo_preempt_count(%rcx)
+	cmpl $0,TI_preempt_count(%rcx)
 	jnz  retint_restore_args
-	bt  $TIF_NEED_RESCHED,threadinfo_flags(%rcx)
+	bt  $TIF_NEED_RESCHED,TI_flags(%rcx)
 	jnc  retint_restore_args
 	bt   $9,EFLAGS-ARGOFFSET(%rsp)	/* interrupts off? */
 	jnc  retint_restore_args
@@ -720,6 +719,10 @@ ENTRY(apic_timer_interrupt)
 	apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt
 END(apic_timer_interrupt)
 
+ENTRY(uv_bau_message_intr1)
+	apicinterrupt 220,uv_bau_message_interrupt
+END(uv_bau_message_intr1)
+
 ENTRY(error_interrupt)
 	apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt
 END(error_interrupt)
@@ -733,6 +736,7 @@ END(spurious_interrupt)
  */ 		
 	.macro zeroentry sym
 	INTR_FRAME
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq $0	/* push error code/oldrax */ 
 	CFI_ADJUST_CFA_OFFSET 8
 	pushq %rax	/* push real oldrax to the rdi slot */ 
@@ -745,6 +749,7 @@ END(spurious_interrupt)
 
 	.macro errorentry sym
 	XCPT_FRAME
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq %rax
 	CFI_ADJUST_CFA_OFFSET 8
 	CFI_REL_OFFSET rax,0
@@ -814,7 +819,7 @@ paranoid_restore\trace:
 	jmp irq_return
 paranoid_userspace\trace:
 	GET_THREAD_INFO(%rcx)
-	movl threadinfo_flags(%rcx),%ebx
+	movl TI_flags(%rcx),%ebx
 	andl $_TIF_WORK_MASK,%ebx
 	jz paranoid_swapgs\trace
 	movq %rsp,%rdi			/* &pt_regs */
@@ -912,7 +917,7 @@ error_exit:
 	testl %eax,%eax
 	jne  retint_kernel
 	LOCKDEP_SYS_EXIT_IRQ
-	movl  threadinfo_flags(%rcx),%edx
+	movl  TI_flags(%rcx),%edx
 	movl  $_TIF_WORK_MASK,%edi
 	andl  %edi,%edx
 	jnz  retint_careful
@@ -926,11 +931,11 @@ error_kernelspace:
 	   iret run with kernel gs again, so don't set the user space flag.
 	   B stepping K8s sometimes report an truncated RIP for IRET 
 	   exceptions returning to compat mode. Check for these here too. */
-	leaq irq_return(%rip),%rbp
-	cmpq %rbp,RIP(%rsp) 
+	leaq irq_return(%rip),%rcx
+	cmpq %rcx,RIP(%rsp)
 	je   error_swapgs
-	movl %ebp,%ebp	/* zero extend */
-	cmpq %rbp,RIP(%rsp) 
+	movl %ecx,%ecx	/* zero extend */
+	cmpq %rcx,RIP(%rsp)
 	je   error_swapgs
 	cmpq $gs_change,RIP(%rsp)
         je   error_swapgs
@@ -939,7 +944,7 @@ KPROBE_END(error_entry)
 	
        /* Reload gs selector with exception handling */
        /* edi:  new selector */ 
-ENTRY(load_gs_index)
+ENTRY(native_load_gs_index)
 	CFI_STARTPROC
 	pushf
 	CFI_ADJUST_CFA_OFFSET 8
@@ -953,7 +958,7 @@ gs_change:
 	CFI_ADJUST_CFA_OFFSET -8
         ret
 	CFI_ENDPROC
-ENDPROC(load_gs_index)
+ENDPROC(native_load_gs_index)
        
         .section __ex_table,"a"
         .align 8
@@ -1120,10 +1125,6 @@ ENTRY(coprocessor_segment_overrun)
 	zeroentry do_coprocessor_segment_overrun
 END(coprocessor_segment_overrun)
 
-ENTRY(reserved)
-	zeroentry do_reserved
-END(reserved)
-
 	/* runs on exception stack */
 ENTRY(double_fault)
 	XCPT_FRAME

arch/x86/kernel/genapic_64.c

@@ -51,7 +51,7 @@ void __init setup_apic_routing(void)
 	else
 #endif
 
-	if (num_possible_cpus() <= 8)
+	if (max_physical_apicid < 8)
 		genapic = &apic_flat;
 	else
 		genapic = &apic_physflat;

arch/x86/kernel/genx2apic_uv_x.c

@@ -5,9 +5,10 @@
  *
  * SGI UV APIC functions (note: not an Intel compatible APIC)
  *
- * Copyright (C) 2007 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
+#include <linux/kernel.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/string.h>
@@ -20,6 +21,7 @@
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
+#include <asm/pgtable.h>
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
 
@@ -55,37 +57,37 @@ static cpumask_t uv_vector_allocation_domain(int cpu)
 int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip)
 {
 	unsigned long val;
-	int nasid;
+	int pnode;
 
-	nasid = uv_apicid_to_nasid(phys_apicid);
+	pnode = uv_apicid_to_pnode(phys_apicid);
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
 	    (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_INIT;
-	uv_write_global_mmr64(nasid, UVH_IPI_INT, val);
+	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 	mdelay(10);
 
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
 	    (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_STARTUP;
-	uv_write_global_mmr64(nasid, UVH_IPI_INT, val);
+	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 	return 0;
 }
 
 static void uv_send_IPI_one(int cpu, int vector)
 {
 	unsigned long val, apicid, lapicid;
-	int nasid;
+	int pnode;
 
 	apicid = per_cpu(x86_cpu_to_apicid, cpu); /* ZZZ - cache node-local ? */
 	lapicid = apicid & 0x3f;		/* ZZZ macro needed */
-	nasid = uv_apicid_to_nasid(apicid);
+	pnode = uv_apicid_to_pnode(apicid);
 	val =
 	    (1UL << UVH_IPI_INT_SEND_SHFT) | (lapicid <<
 					      UVH_IPI_INT_APIC_ID_SHFT) |
 	    (vector << UVH_IPI_INT_VECTOR_SHFT);
-	uv_write_global_mmr64(nasid, UVH_IPI_INT, val);
+	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 }
 
 static void uv_send_IPI_mask(cpumask_t mask, int vector)
@@ -159,39 +161,146 @@ struct genapic apic_x2apic_uv_x = {
 	.phys_pkg_id = phys_pkg_id,	/* Fixme ZZZ */
 };
 
-static __cpuinit void set_x2apic_extra_bits(int nasid)
+static __cpuinit void set_x2apic_extra_bits(int pnode)
 {
-	__get_cpu_var(x2apic_extra_bits) = ((nasid >> 1) << 6);
+	__get_cpu_var(x2apic_extra_bits) = (pnode << 6);
 }
 
 /*
  * Called on boot cpu.
  */
+static __init int boot_pnode_to_blade(int pnode)
+{
+	int blade;
+
+	for (blade = 0; blade < uv_num_possible_blades(); blade++)
+		if (pnode == uv_blade_info[blade].pnode)
+			return blade;
+	BUG();
+}
+
+struct redir_addr {
+	unsigned long redirect;
+	unsigned long alias;
+};
+
+#define DEST_SHIFT UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT
+
+static __initdata struct redir_addr redir_addrs[] = {
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_SI_ALIAS0_OVERLAY_CONFIG},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_SI_ALIAS1_OVERLAY_CONFIG},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_SI_ALIAS2_OVERLAY_CONFIG},
+};
+
+static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
+{
+	union uvh_si_alias0_overlay_config_u alias;
+	union uvh_rh_gam_alias210_redirect_config_2_mmr_u redirect;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) {
+		alias.v = uv_read_local_mmr(redir_addrs[i].alias);
+		if (alias.s.base == 0) {
+			*size = (1UL << alias.s.m_alias);
+			redirect.v = uv_read_local_mmr(redir_addrs[i].redirect);
+			*base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
+			return;
+		}
+	}
+	BUG();
+}
+
+static __init void map_low_mmrs(void)
+{
+	init_extra_mapping_uc(UV_GLOBAL_MMR32_BASE, UV_GLOBAL_MMR32_SIZE);
+	init_extra_mapping_uc(UV_LOCAL_MMR_BASE, UV_LOCAL_MMR_SIZE);
+}
+
+enum map_type {map_wb, map_uc};
+
+static void map_high(char *id, unsigned long base, int shift, enum map_type map_type)
+{
+	unsigned long bytes, paddr;
+
+	paddr = base << shift;
+	bytes = (1UL << shift);
+	printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr,
+	       					paddr + bytes);
+	if (map_type == map_uc)
+		init_extra_mapping_uc(paddr, bytes);
+	else
+		init_extra_mapping_wb(paddr, bytes);
+
+}
+static __init void map_gru_high(int max_pnode)
+{
+	union uvh_rh_gam_gru_overlay_config_mmr_u gru;
+	int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
+
+	gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR);
+	if (gru.s.enable)
+		map_high("GRU", gru.s.base, shift, map_wb);
+}
+
+static __init void map_config_high(int max_pnode)
+{
+	union uvh_rh_gam_cfg_overlay_config_mmr_u cfg;
+	int shift = UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT;
+
+	cfg.v = uv_read_local_mmr(UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR);
+	if (cfg.s.enable)
+		map_high("CONFIG", cfg.s.base, shift, map_uc);
+}
+
+static __init void map_mmr_high(int max_pnode)
+{
+	union uvh_rh_gam_mmr_overlay_config_mmr_u mmr;
+	int shift = UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT;
+
+	mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR);
+	if (mmr.s.enable)
+		map_high("MMR", mmr.s.base, shift, map_uc);
+}
+
+static __init void map_mmioh_high(int max_pnode)
+{
+	union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
+	int shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+
+	mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
+	if (mmioh.s.enable)
+		map_high("MMIOH", mmioh.s.base, shift, map_uc);
+}
+
 static __init void uv_system_init(void)
 {
 	union uvh_si_addr_map_config_u m_n_config;
-	int bytes, nid, cpu, lcpu, nasid, last_nasid, blade;
-	unsigned long mmr_base;
+	union uvh_node_id_u node_id;
+	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
+	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
+	int max_pnode = 0;
+	unsigned long mmr_base, present;
+
+	map_low_mmrs();
 
 	m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG);
+	m_val = m_n_config.s.m_skt;
+	n_val = m_n_config.s.n_skt;
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
 	printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
 
-	last_nasid = -1;
-	for_each_possible_cpu(cpu) {
-		nid = cpu_to_node(cpu);
-		nasid = uv_apicid_to_nasid(per_cpu(x86_cpu_to_apicid, cpu));
-		if (nasid != last_nasid)
-			uv_possible_blades++;
-		last_nasid = nasid;
-	}
+	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
+		uv_possible_blades +=
+		  hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8));
 	printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
 	uv_blade_info = alloc_bootmem_pages(bytes);
 
+	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
+
 	bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
 	uv_node_to_blade = alloc_bootmem_pages(bytes);
 	memset(uv_node_to_blade, 255, bytes);
@@ -200,43 +309,62 @@ static __init void uv_system_init(void)
 	uv_cpu_to_blade = alloc_bootmem_pages(bytes);
 	memset(uv_cpu_to_blade, 255, bytes);
 
-	last_nasid = -1;
-	blade = -1;
-	lcpu = -1;
-	for_each_possible_cpu(cpu) {
-		nid = cpu_to_node(cpu);
-		nasid = uv_apicid_to_nasid(per_cpu(x86_cpu_to_apicid, cpu));
-		if (nasid != last_nasid) {
-			blade++;
-			lcpu = -1;
-			uv_blade_info[blade].nr_posible_cpus = 0;
+	blade = 0;
+	for (i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) {
+		present = uv_read_local_mmr(UVH_NODE_PRESENT_TABLE + i * 8);
+		for (j = 0; j < 64; j++) {
+			if (!test_bit(j, &present))
+				continue;
+			uv_blade_info[blade].pnode = (i * 64 + j);
+			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
+			blade++;
 		}
-		last_nasid = nasid;
-		lcpu++;
+	}
 
-		uv_cpu_hub_info(cpu)->m_val = m_n_config.s.m_skt;
-		uv_cpu_hub_info(cpu)->n_val = m_n_config.s.n_skt;
+	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+	gnode_upper = (((unsigned long)node_id.s.node_id) &
+		       ~((1 << n_val) - 1)) << m_val;
+
+	for_each_present_cpu(cpu) {
+		nid = cpu_to_node(cpu);
+		pnode = uv_apicid_to_pnode(per_cpu(x86_cpu_to_apicid, cpu));
+		blade = boot_pnode_to_blade(pnode);
+		lcpu = uv_blade_info[blade].nr_possible_cpus;
+		uv_blade_info[blade].nr_possible_cpus++;
+
+		uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
+		uv_cpu_hub_info(cpu)->lowmem_remap_top =
+					lowmem_redir_base + lowmem_redir_size;
+		uv_cpu_hub_info(cpu)->m_val = m_val;
+		uv_cpu_hub_info(cpu)->n_val = m_val;
 		uv_cpu_hub_info(cpu)->numa_blade_id = blade;
 		uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
-		uv_cpu_hub_info(cpu)->local_nasid = nasid;
-		uv_cpu_hub_info(cpu)->gnode_upper =
-		    nasid & ~((1 << uv_hub_info->n_val) - 1);
+		uv_cpu_hub_info(cpu)->pnode = pnode;
+		uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1;
+		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
+		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
 		uv_cpu_hub_info(cpu)->coherency_domain_number = 0;/* ZZZ */
-		uv_blade_info[blade].nasid = nasid;
-		uv_blade_info[blade].nr_posible_cpus++;
 		uv_node_to_blade[nid] = blade;
 		uv_cpu_to_blade[cpu] = blade;
+		max_pnode = max(pnode, max_pnode);
 
-		printk(KERN_DEBUG "UV cpu %d, apicid 0x%x, nasid %d, nid %d\n",
-		       cpu, per_cpu(x86_cpu_to_apicid, cpu), nasid, nid);
-		printk(KERN_DEBUG "UV   lcpu %d, blade %d\n", lcpu, blade);
+		printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, "
+			"lcpu %d, blade %d\n",
+			cpu, per_cpu(x86_cpu_to_apicid, cpu), pnode, nid,
+			lcpu, blade);
 	}
+
+	map_gru_high(max_pnode);
+	map_mmr_high(max_pnode);
+	map_config_high(max_pnode);
+	map_mmioh_high(max_pnode);
 }
 
 /*
  * Called on each cpu to initialize the per_cpu UV data area.
+ * 	ZZZ hotplug not supported yet
  */
 void __cpuinit uv_cpu_init(void)
 {
@@ -246,5 +374,5 @@ void __cpuinit uv_cpu_init(void)
 	uv_blade_info[uv_numa_blade_id()].nr_online_cpus++;
 
 	if (get_uv_system_type() == UV_NON_UNIQUE_APIC)
-		set_x2apic_extra_bits(uv_hub_info->local_nasid);
+		set_x2apic_extra_bits(uv_hub_info->pnode);
 }

arch/x86/kernel/head.c

@@ -0,0 +1,55 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+
+#include <asm/setup.h>
+#include <asm/bios_ebda.h>
+
+#define BIOS_LOWMEM_KILOBYTES 0x413
+
+/*
+ * The BIOS places the EBDA/XBDA at the top of conventional
+ * memory, and usually decreases the reported amount of
+ * conventional memory (int 0x12) too. This also contains a
+ * workaround for Dell systems that neglect to reserve EBDA.
+ * The same workaround also avoids a problem with the AMD768MPX
+ * chipset: reserve a page before VGA to prevent PCI prefetch
+ * into it (errata #56). Usually the page is reserved anyways,
+ * unless you have no PS/2 mouse plugged in.
+ */
+void __init reserve_ebda_region(void)
+{
+	unsigned int lowmem, ebda_addr;
+
+	/* To determine the position of the EBDA and the */
+	/* end of conventional memory, we need to look at */
+	/* the BIOS data area. In a paravirtual environment */
+	/* that area is absent. We'll just have to assume */
+	/* that the paravirt case can handle memory setup */
+	/* correctly, without our help. */
+	if (paravirt_enabled())
+		return;
+
+	/* end of low (conventional) memory */
+	lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
+	lowmem <<= 10;
+
+	/* start of EBDA area */
+	ebda_addr = get_bios_ebda();
+
+	/* Fixup: bios puts an EBDA in the top 64K segment */
+	/* of conventional memory, but does not adjust lowmem. */
+	if ((lowmem - ebda_addr) <= 0x10000)
+		lowmem = ebda_addr;
+
+	/* Fixup: bios does not report an EBDA at all. */
+	/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
+	if ((ebda_addr == 0) && (lowmem >= 0x9f000))
+		lowmem = 0x9f000;
+
+	/* Paranoia: should never happen, but... */
+	if ((lowmem == 0) || (lowmem >= 0x100000))
+		lowmem = 0x9f000;
+
+	/* reserve all memory between lowmem and the 1MB mark */
+	reserve_early_overlap_ok(lowmem, 0x100000, "BIOS reserved");
+}

arch/x86/kernel/head32.c

@@ -8,7 +8,34 @@
 #include <linux/init.h>
 #include <linux/start_kernel.h>
 
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/e820.h>
+#include <asm/bios_ebda.h>
+
 void __init i386_start_kernel(void)
 {
+	reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	/* Reserve INITRD */
+	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+	}
+#endif
+	reserve_early(init_pg_tables_start, init_pg_tables_end,
+			"INIT_PG_TABLE");
+
+	reserve_ebda_region();
+
+	/*
+	 * At this point everything still needed from the boot loader
+	 * or BIOS or kernel text should be early reserved or marked not
+	 * RAM in e820. All other memory is free game.
+	 */
+
 	start_kernel();
 }

arch/x86/kernel/head64.c

@@ -25,6 +25,20 @@
 #include <asm/e820.h>
 #include <asm/bios_ebda.h>
 
+/* boot cpu pda */
+static struct x8664_pda _boot_cpu_pda __read_mostly;
+
+#ifdef CONFIG_SMP
+/*
+ * We install an empty cpu_pda pointer table to indicate to early users
+ * (numa_set_node) that the cpu_pda pointer table for cpus other than
+ * the boot cpu is not yet setup.
+ */
+static struct x8664_pda *__cpu_pda[NR_CPUS] __initdata;
+#else
+static struct x8664_pda *__cpu_pda[NR_CPUS] __read_mostly;
+#endif
+
 static void __init zap_identity_mappings(void)
 {
 	pgd_t *pgd = pgd_offset_k(0UL);
@@ -51,74 +65,6 @@ static void __init copy_bootdata(char *real_mode_data)
 	}
 }
 
-#define BIOS_LOWMEM_KILOBYTES 0x413
-
-/*
- * The BIOS places the EBDA/XBDA at the top of conventional
- * memory, and usually decreases the reported amount of
- * conventional memory (int 0x12) too. This also contains a
- * workaround for Dell systems that neglect to reserve EBDA.
- * The same workaround also avoids a problem with the AMD768MPX
- * chipset: reserve a page before VGA to prevent PCI prefetch
- * into it (errata #56). Usually the page is reserved anyways,
- * unless you have no PS/2 mouse plugged in.
- */
-static void __init reserve_ebda_region(void)
-{
-	unsigned int lowmem, ebda_addr;
-
-	/* To determine the position of the EBDA and the */
-	/* end of conventional memory, we need to look at */
-	/* the BIOS data area. In a paravirtual environment */
-	/* that area is absent. We'll just have to assume */
-	/* that the paravirt case can handle memory setup */
-	/* correctly, without our help. */
-	if (paravirt_enabled())
-		return;
-
-	/* end of low (conventional) memory */
-	lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
-	lowmem <<= 10;
-
-	/* start of EBDA area */
-	ebda_addr = get_bios_ebda();
-
-	/* Fixup: bios puts an EBDA in the top 64K segment */
-	/* of conventional memory, but does not adjust lowmem. */
-	if ((lowmem - ebda_addr) <= 0x10000)
-		lowmem = ebda_addr;
-
-	/* Fixup: bios does not report an EBDA at all. */
-	/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
-	if ((ebda_addr == 0) && (lowmem >= 0x9f000))
-		lowmem = 0x9f000;
-
-	/* Paranoia: should never happen, but... */
-	if ((lowmem == 0) || (lowmem >= 0x100000))
-		lowmem = 0x9f000;
-
-	/* reserve all memory between lowmem and the 1MB mark */
-	reserve_early(lowmem, 0x100000, "BIOS reserved");
-}
-
-static void __init reserve_setup_data(void)
-{
-	struct setup_data *data;
-	unsigned long pa_data;
-	char buf[32];
-
-	if (boot_params.hdr.version < 0x0209)
-		return;
-	pa_data = boot_params.hdr.setup_data;
-	while (pa_data) {
-		data = early_ioremap(pa_data, sizeof(*data));
-		sprintf(buf, "setup data %x", data->type);
-		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
-		pa_data = data->next;
-		early_iounmap(data, sizeof(*data));
-	}
-}
-
 void __init x86_64_start_kernel(char * real_mode_data)
 {
 	int i;
@@ -156,10 +102,17 @@ void __init x86_64_start_kernel(char * real_mode_data)
 
 	early_printk("Kernel alive\n");
 
- 	for (i = 0; i < NR_CPUS; i++)
- 		cpu_pda(i) = &boot_cpu_pda[i];
-
+	_cpu_pda = __cpu_pda;
+	cpu_pda(0) = &_boot_cpu_pda;
 	pda_init(0);
+
+	early_printk("Kernel really alive\n");
+
+	x86_64_start_reservations(real_mode_data);
+}
+
+void __init x86_64_start_reservations(char *real_mode_data)
+{
 	copy_bootdata(__va(real_mode_data));
 
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
@@ -175,7 +128,6 @@ void __init x86_64_start_kernel(char * real_mode_data)
 #endif
 
 	reserve_ebda_region();
-	reserve_setup_data();
 
 	/*
 	 * At this point everything still needed from the boot loader

arch/x86/kernel/head_32.S

@@ -194,6 +194,7 @@ default_entry:
 	xorl %ebx,%ebx				/* %ebx is kept at zero */
 
 	movl $pa(pg0), %edi
+	movl %edi, pa(init_pg_tables_start)
 	movl $pa(swapper_pg_pmd), %edx
 	movl $PTE_ATTR, %eax
 10:
@@ -219,6 +220,8 @@ default_entry:
 	jb 10b
 1:
 	movl %edi,pa(init_pg_tables_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
 
 	/* Do early initialization of the fixmap area */
 	movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax
@@ -228,6 +231,7 @@ default_entry:
 page_pde_offset = (__PAGE_OFFSET >> 20);
 
 	movl $pa(pg0), %edi
+	movl %edi, pa(init_pg_tables_start)
 	movl $pa(swapper_pg_dir), %edx
 	movl $PTE_ATTR, %eax
 10:
@@ -249,6 +253,8 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
 	cmpl %ebp,%eax
 	jb 10b
 	movl %edi,pa(init_pg_tables_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
 
 	/* Do early initialization of the fixmap area */
 	movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax
@@ -446,10 +452,13 @@ is386:	movl $2,%ecx		# set MP
 	je   1f
 	movl $(__KERNEL_PERCPU), %eax
 	movl %eax,%fs		# set this cpu's percpu
-	jmp initialize_secondary # all other CPUs call initialize_secondary
+	movl (stack_start), %esp
 1:
 #endif /* CONFIG_SMP */
-	jmp i386_start_kernel
+	jmp *(initial_code)
+.align 4
+ENTRY(initial_code)
+	.long i386_start_kernel
 
 /*
  * We depend on ET to be correct. This checks for 287/387.

arch/x86/kernel/head_64.S

@@ -18,6 +18,7 @@
 #include <asm/page.h>
 #include <asm/msr.h>
 #include <asm/cache.h>
+#include <asm/processor-flags.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -31,6 +32,13 @@
  *
  */
 
+#define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
+
+L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET)
+L3_PAGE_OFFSET = pud_index(__PAGE_OFFSET)
+L4_START_KERNEL = pgd_index(__START_KERNEL_map)
+L3_START_KERNEL = pud_index(__START_KERNEL_map)
+
 	.text
 	.section .text.head
 	.code64
@@ -76,8 +84,8 @@ startup_64:
 	/* Fixup the physical addresses in the page table
 	 */
 	addq	%rbp, init_level4_pgt + 0(%rip)
-	addq	%rbp, init_level4_pgt + (258*8)(%rip)
-	addq	%rbp, init_level4_pgt + (511*8)(%rip)
+	addq	%rbp, init_level4_pgt + (L4_PAGE_OFFSET*8)(%rip)
+	addq	%rbp, init_level4_pgt + (L4_START_KERNEL*8)(%rip)
 
 	addq	%rbp, level3_ident_pgt + 0(%rip)
 
@@ -154,9 +162,7 @@ ENTRY(secondary_startup_64)
 	 */
 
 	/* Enable PAE mode and PGE */
-	xorq	%rax, %rax
-	btsq	$5, %rax
-	btsq	$7, %rax
+	movl	$(X86_CR4_PAE | X86_CR4_PGE), %eax
 	movq	%rax, %cr4
 
 	/* Setup early boot stage 4 level pagetables. */
@@ -184,19 +190,15 @@ ENTRY(secondary_startup_64)
 1:	wrmsr				/* Make changes effective */
 
 	/* Setup cr0 */
-#define CR0_PM				1		/* protected mode */
-#define CR0_MP				(1<<1)
-#define CR0_ET				(1<<4)
-#define CR0_NE				(1<<5)
-#define CR0_WP				(1<<16)
-#define CR0_AM				(1<<18)
-#define CR0_PAGING 			(1<<31)
-	movl $CR0_PM|CR0_MP|CR0_ET|CR0_NE|CR0_WP|CR0_AM|CR0_PAGING,%eax
+#define CR0_STATE	(X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
+			 X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
+			 X86_CR0_PG)
+	movl	$CR0_STATE, %eax
 	/* Make changes effective */
 	movq	%rax, %cr0
 
 	/* Setup a boot time stack */
-	movq init_rsp(%rip),%rsp
+	movq stack_start(%rip),%rsp
 
 	/* zero EFLAGS after setting rsp */
 	pushq $0
@@ -208,7 +210,7 @@ ENTRY(secondary_startup_64)
 	 * addresses where we're currently running on. We have to do that here
 	 * because in 32bit we couldn't load a 64bit linear address.
 	 */
-	lgdt	cpu_gdt_descr(%rip)
+	lgdt	early_gdt_descr(%rip)
 
 	/* set up data segments. actually 0 would do too */
 	movl $__KERNEL_DS,%eax
@@ -257,8 +259,9 @@ ENTRY(secondary_startup_64)
 	.quad	x86_64_start_kernel
 	__FINITDATA
 
-	ENTRY(init_rsp)
+	ENTRY(stack_start)
 	.quad  init_thread_union+THREAD_SIZE-8
+	.word  0
 
 bad_address:
 	jmp bad_address
@@ -327,11 +330,11 @@ early_idt_ripmsg:
 ENTRY(name)
 
 /* Automate the creation of 1 to 1 mapping pmd entries */
-#define PMDS(START, PERM, COUNT)		\
-	i = 0 ;					\
-	.rept (COUNT) ;				\
-	.quad	(START) + (i << 21) + (PERM) ;	\
-	i = i + 1 ;				\
+#define PMDS(START, PERM, COUNT)			\
+	i = 0 ;						\
+	.rept (COUNT) ;					\
+	.quad	(START) + (i << PMD_SHIFT) + (PERM) ;	\
+	i = i + 1 ;					\
 	.endr
 
 	/*
@@ -342,9 +345,9 @@ ENTRY(name)
 	 */
 NEXT_PAGE(init_level4_pgt)
 	.quad	level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
-	.fill	257,8,0
+	.org	init_level4_pgt + L4_PAGE_OFFSET*8, 0
 	.quad	level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
-	.fill	252,8,0
+	.org	init_level4_pgt + L4_START_KERNEL*8, 0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
 
@@ -353,7 +356,7 @@ NEXT_PAGE(level3_ident_pgt)
 	.fill	511,8,0
 
 NEXT_PAGE(level3_kernel_pgt)
-	.fill	510,8,0
+	.fill	L3_START_KERNEL,8,0
 	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
 	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
 	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
@@ -384,7 +387,7 @@ NEXT_PAGE(level2_kernel_pgt)
 	 *  If you want to increase this then increase MODULES_VADDR
 	 *  too.)
 	 */
-	PMDS(0, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL,
+	PMDS(0, __PAGE_KERNEL_LARGE_EXEC,
 		KERNEL_IMAGE_SIZE/PMD_SIZE)
 
 NEXT_PAGE(level2_spare_pgt)
@@ -395,54 +398,16 @@ NEXT_PAGE(level2_spare_pgt)
 
 	.data
 	.align 16
-	.globl cpu_gdt_descr
-cpu_gdt_descr:
-	.word	gdt_end-cpu_gdt_table-1
-gdt:
-	.quad	cpu_gdt_table
-#ifdef CONFIG_SMP
-	.rept	NR_CPUS-1
-	.word	0
-	.quad	0
-	.endr
-#endif
+	.globl early_gdt_descr
+early_gdt_descr:
+	.word	GDT_ENTRIES*8-1
+	.quad   per_cpu__gdt_page
 
 ENTRY(phys_base)
 	/* This must match the first entry in level2_kernel_pgt */
 	.quad   0x0000000000000000
 
-/* We need valid kernel segments for data and code in long mode too
- * IRET will check the segment types  kkeil 2000/10/28
- * Also sysret mandates a special GDT layout 
- */
-		 		
-	.section .data.page_aligned, "aw"
-	.align PAGE_SIZE
-
-/* The TLS descriptors are currently at a different place compared to i386.
-   Hopefully nobody expects them at a fixed place (Wine?) */
 	
-ENTRY(cpu_gdt_table)
-	.quad	0x0000000000000000	/* NULL descriptor */
-	.quad	0x00cf9b000000ffff	/* __KERNEL32_CS */
-	.quad	0x00af9b000000ffff	/* __KERNEL_CS */
-	.quad	0x00cf93000000ffff	/* __KERNEL_DS */
-	.quad	0x00cffb000000ffff	/* __USER32_CS */
-	.quad	0x00cff3000000ffff	/* __USER_DS, __USER32_DS  */
-	.quad	0x00affb000000ffff	/* __USER_CS */
-	.quad	0x0			/* unused */
-	.quad	0,0			/* TSS */
-	.quad	0,0			/* LDT */
-	.quad   0,0,0			/* three TLS descriptors */ 
-	.quad	0x0000f40000000000	/* node/CPU stored in limit */
-gdt_end:	
-	/* asm/segment.h:GDT_ENTRIES must match this */	
-	/* This should be a multiple of the cache line size */
-	/* GDTs of other CPUs are now dynamically allocated */
-
-	/* zero the remaining page */
-	.fill PAGE_SIZE / 8 - GDT_ENTRIES,8,0
-
 	.section .bss, "aw", @nobits
 	.align L1_CACHE_BYTES
 ENTRY(idt_table)

arch/x86/kernel/hpet.c

@@ -17,7 +17,7 @@
 
 /* FSEC = 10^-15
    NSEC = 10^-9 */
-#define FSEC_PER_NSEC	1000000
+#define FSEC_PER_NSEC	1000000L
 
 /*
  * HPET address is set in acpi/boot.c, when an ACPI entry exists
@@ -36,26 +36,15 @@ static inline void hpet_writel(unsigned long d, unsigned long a)
 }
 
 #ifdef CONFIG_X86_64
-
 #include <asm/pgtable.h>
-
-static inline void hpet_set_mapping(void)
-{
-	set_fixmap_nocache(FIX_HPET_BASE, hpet_address);
-	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
-	hpet_virt_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE);
-}
-
-static inline void hpet_clear_mapping(void)
-{
-	hpet_virt_address = NULL;
-}
-
-#else
+#endif
 
 static inline void hpet_set_mapping(void)
 {
 	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+#ifdef CONFIG_X86_64
+	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
+#endif
 }
 
 static inline void hpet_clear_mapping(void)
@@ -63,7 +52,6 @@ static inline void hpet_clear_mapping(void)
 	iounmap(hpet_virt_address);
 	hpet_virt_address = NULL;
 }
-#endif
 
 /*
  * HPET command line enable / disable
@@ -206,20 +194,19 @@ static void hpet_enable_legacy_int(void)
 
 static void hpet_legacy_clockevent_register(void)
 {
-	uint64_t hpet_freq;
-
 	/* Start HPET legacy interrupts */
 	hpet_enable_legacy_int();
 
 	/*
-	 * The period is a femto seconds value. We need to calculate the
-	 * scaled math multiplication factor for nanosecond to hpet tick
-	 * conversion.
+	 * The mult factor is defined as (include/linux/clockchips.h)
+	 *  mult/2^shift = cyc/ns (in contrast to ns/cyc in clocksource.h)
+	 * hpet_period is in units of femtoseconds (per cycle), so
+	 *  mult/2^shift = cyc/ns = 10^6/hpet_period
+	 *  mult = (10^6 * 2^shift)/hpet_period
+	 *  mult = (FSEC_PER_NSEC << hpet_clockevent.shift)/hpet_period
 	 */
-	hpet_freq = 1000000000000000ULL;
-	do_div(hpet_freq, hpet_period);
-	hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
-				      NSEC_PER_SEC, hpet_clockevent.shift);
+	hpet_clockevent.mult = div_sc((unsigned long) FSEC_PER_NSEC,
+				      hpet_period, hpet_clockevent.shift);
 	/* Calculate the min / max delta */
 	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
 							   &hpet_clockevent);
@@ -324,7 +311,7 @@ static struct clocksource clocksource_hpet = {
 
 static int hpet_clocksource_register(void)
 {
-	u64 tmp, start, now;
+	u64 start, now;
 	cycle_t t1;
 
 	/* Start the counter */
@@ -351,21 +338,15 @@ static int hpet_clocksource_register(void)
 		return -ENODEV;
 	}
 
-	/* Initialize and register HPET clocksource
-	 *
-	 * hpet period is in femto seconds per cycle
-	 * so we need to convert this to ns/cyc units
-	 * approximated by mult/2^shift
-	 *
-	 *  fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift
-	 *  fsec/cyc * 1ns/1000000fsec * 2^shift = mult
-	 *  fsec/cyc * 2^shift * 1nsec/1000000fsec = mult
-	 *  (fsec/cyc << shift)/1000000 = mult
-	 *  (hpet_period << shift)/FSEC_PER_NSEC = mult
+	/*
+	 * The definition of mult is (include/linux/clocksource.h)
+	 * mult/2^shift = ns/cyc and hpet_period is in units of fsec/cyc
+	 * so we first need to convert hpet_period to ns/cyc units:
+	 *  mult/2^shift = ns/cyc = hpet_period/10^6
+	 *  mult = (hpet_period * 2^shift)/10^6
+	 *  mult = (hpet_period << shift)/FSEC_PER_NSEC
 	 */
-	tmp = (u64)hpet_period << HPET_SHIFT;
-	do_div(tmp, FSEC_PER_NSEC);
-	clocksource_hpet.mult = (u32)tmp;
+	clocksource_hpet.mult = div_sc(hpet_period, FSEC_PER_NSEC, HPET_SHIFT);
 
 	clocksource_register(&clocksource_hpet);
 

arch/x86/kernel/i387.c

@@ -162,7 +162,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 	int ret;
 
 	if (!cpu_has_fxsr)
-		return -EIO;
+		return -ENODEV;
 
 	ret = init_fpu(target);
 	if (ret)
@@ -179,7 +179,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	int ret;
 
 	if (!cpu_has_fxsr)
-		return -EIO;
+		return -ENODEV;
 
 	ret = init_fpu(target);
 	if (ret)

arch/x86/kernel/i8259_32.c → arch/x86/kernel/i8259.c

@@ -1,8 +1,10 @@
+#include <linux/linkage.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/timex.h>
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/init.h>
@@ -10,10 +12,12 @@
 #include <linux/sysdev.h>
 #include <linux/bitops.h>
 
+#include <asm/acpi.h>
 #include <asm/atomic.h>
 #include <asm/system.h>
 #include <asm/io.h>
 #include <asm/timer.h>
+#include <asm/hw_irq.h>
 #include <asm/pgtable.h>
 #include <asm/delay.h>
 #include <asm/desc.h>
@@ -32,7 +36,7 @@ static int i8259A_auto_eoi;
 DEFINE_SPINLOCK(i8259A_lock);
 static void mask_and_ack_8259A(unsigned int);
 
-static struct irq_chip i8259A_chip = {
+struct irq_chip i8259A_chip = {
 	.name		= "XT-PIC",
 	.mask		= disable_8259A_irq,
 	.disable	= disable_8259A_irq,
@@ -125,14 +129,14 @@ static inline int i8259A_irq_real(unsigned int irq)
 	int irqmask = 1<<irq;
 
 	if (irq < 8) {
-		outb(0x0B,PIC_MASTER_CMD);	/* ISR register */
+		outb(0x0B, PIC_MASTER_CMD);	/* ISR register */
 		value = inb(PIC_MASTER_CMD) & irqmask;
-		outb(0x0A,PIC_MASTER_CMD);	/* back to the IRR register */
+		outb(0x0A, PIC_MASTER_CMD);	/* back to the IRR register */
 		return value;
 	}
-	outb(0x0B,PIC_SLAVE_CMD);	/* ISR register */
+	outb(0x0B, PIC_SLAVE_CMD);	/* ISR register */
 	value = inb(PIC_SLAVE_CMD) & (irqmask >> 8);
-	outb(0x0A,PIC_SLAVE_CMD);	/* back to the IRR register */
+	outb(0x0A, PIC_SLAVE_CMD);	/* back to the IRR register */
 	return value;
 }
 
@@ -171,12 +175,14 @@ handle_real_irq:
 	if (irq & 8) {
 		inb(PIC_SLAVE_IMR);	/* DUMMY - (do we need this?) */
 		outb(cached_slave_mask, PIC_SLAVE_IMR);
-		outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */
-		outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to master-IRQ2 */
+		/* 'Specific EOI' to slave */
+		outb(0x60+(irq&7), PIC_SLAVE_CMD);
+		 /* 'Specific EOI' to master-IRQ2 */
+		outb(0x60+PIC_CASCADE_IR, PIC_MASTER_CMD);
 	} else {
 		inb(PIC_MASTER_IMR);	/* DUMMY - (do we need this?) */
 		outb(cached_master_mask, PIC_MASTER_IMR);
-		outb(0x60+irq,PIC_MASTER_CMD);	/* 'Specific EOI to master */
+		outb(0x60+irq, PIC_MASTER_CMD);	/* 'Specific EOI to master */
 	}
 	spin_unlock_irqrestore(&i8259A_lock, flags);
 	return;
@@ -199,7 +205,8 @@ spurious_8259A_irq:
 		 * lets ACK and report it. [once per IRQ]
 		 */
 		if (!(spurious_irq_mask & irqmask)) {
-			printk(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq);
+			printk(KERN_DEBUG
+			       "spurious 8259A interrupt: IRQ%d.\n", irq);
 			spurious_irq_mask |= irqmask;
 		}
 		atomic_inc(&irq_err_count);
@@ -290,17 +297,28 @@ void init_8259A(int auto_eoi)
 	 * outb_pic - this has to work on a wide range of PC hardware.
 	 */
 	outb_pic(0x11, PIC_MASTER_CMD);	/* ICW1: select 8259A-1 init */
-	outb_pic(0x20 + 0, PIC_MASTER_IMR);	/* ICW2: 8259A-1 IR0-7 mapped to 0x20-0x27 */
-	outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);	/* 8259A-1 (the master) has a slave on IR2 */
+
+	/* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 on x86-64,
+	                       to 0x20-0x27 on i386 */
+	outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+
+	/* 8259A-1 (the master) has a slave on IR2 */
+	outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);
+
 	if (auto_eoi)	/* master does Auto EOI */
 		outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR);
 	else		/* master expects normal EOI */
 		outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR);
 
 	outb_pic(0x11, PIC_SLAVE_CMD);	/* ICW1: select 8259A-2 init */
-	outb_pic(0x20 + 8, PIC_SLAVE_IMR);	/* ICW2: 8259A-2 IR0-7 mapped to 0x28-0x2f */
-	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);	/* 8259A-2 is a slave on master's IR2 */
-	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */
+
+	/* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */
+	outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
+	/* 8259A-2 is a slave on master's IR2 */
+	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
+	/* (slave's support for AEOI in flat mode is to be investigated) */
+	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR);
+
 	if (auto_eoi)
 		/*
 		 * In AEOI mode we just have to mask the interrupt
@@ -317,93 +335,3 @@ void init_8259A(int auto_eoi)
 
 	spin_unlock_irqrestore(&i8259A_lock, flags);
 }
-
-/*
- * Note that on a 486, we don't want to do a SIGFPE on an irq13
- * as the irq is unreliable, and exception 16 works correctly
- * (ie as explained in the intel literature). On a 386, you
- * can't use exception 16 due to bad IBM design, so we have to
- * rely on the less exact irq13.
- *
- * Careful.. Not only is IRQ13 unreliable, but it is also
- * leads to races. IBM designers who came up with it should
- * be shot.
- */
- 
-
-static irqreturn_t math_error_irq(int cpl, void *dev_id)
-{
-	extern void math_error(void __user *);
-	outb(0,0xF0);
-	if (ignore_fpu_irq || !boot_cpu_data.hard_math)
-		return IRQ_NONE;
-	math_error((void __user *)get_irq_regs()->ip);
-	return IRQ_HANDLED;
-}
-
-/*
- * New motherboards sometimes make IRQ 13 be a PCI interrupt,
- * so allow interrupt sharing.
- */
-static struct irqaction fpu_irq = {
-	.handler = math_error_irq,
-	.mask = CPU_MASK_NONE,
-	.name = "fpu",
-};
-
-void __init init_ISA_irqs (void)
-{
-	int i;
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	init_bsp_APIC();
-#endif
-	init_8259A(0);
-
-	/*
-	 * 16 old-style INTA-cycle interrupts:
-	 */
-	for (i = 0; i < 16; i++) {
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-					      handle_level_irq, "XT");
-	}
-}
-
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
-{
-	int i;
-
-	/* all the set up before the call gates are initialised */
-	pre_intr_init_hook();
-
-	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
-	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (i >= NR_IRQS)
-			break;
-		/* SYSCALL_VECTOR was reserved in trap_init. */
-		if (!test_bit(vector, used_vectors))
-			set_intr_gate(vector, interrupt[i]);
-	}
-
-	/* setup after call gates are initialised (usually add in
-	 * the architecture specific gates)
-	 */
-	intr_init_hook();
-
-	/*
-	 * External FPU? Set up irq13 if so, for
-	 * original braindamaged IBM FERR coupling.
-	 */
-	if (boot_cpu_data.hard_math && !cpu_has_fpu)
-		setup_irq(FPU_IRQ, &fpu_irq);
-
-	irq_ctx_init(smp_processor_id());
-}

arch/x86/kernel/i8259_64.c

@@ -1,512 +0,0 @@
-#include <linux/linkage.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-
-#include <asm/acpi.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/hw_irq.h>
-#include <asm/pgtable.h>
-#include <asm/delay.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/i8259.h>
-
-/*
- * Common place to define all x86 IRQ vectors
- *
- * This builds up the IRQ handler stubs using some ugly macros in irq.h
- *
- * These macros create the low-level assembly IRQ routines that save
- * register context and call do_IRQ(). do_IRQ() then does all the
- * operations that are needed to keep the AT (or SMP IOAPIC)
- * interrupt-controller happy.
- */
-
-#define BI(x,y) \
-	BUILD_IRQ(x##y)
-
-#define BUILD_16_IRQS(x) \
-	BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
-	BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
-	BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
-	BI(x,c) BI(x,d) BI(x,e) BI(x,f)
-
-/*
- * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
- * (these are usually mapped to vectors 0x30-0x3f)
- */
-
-/*
- * The IO-APIC gives us many more interrupt sources. Most of these
- * are unused but an SMP system is supposed to have enough memory ...
- * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
- * across the spectrum, so we really want to be prepared to get all
- * of these. Plus, more powerful systems might have more than 64
- * IO-APIC registers.
- *
- * (these are usually mapped into the 0x30-0xff vector range)
- */
-				      BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
-BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
-BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
-BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
-
-#undef BUILD_16_IRQS
-#undef BI
-
-
-#define IRQ(x,y) \
-	IRQ##x##y##_interrupt
-
-#define IRQLIST_16(x) \
-	IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
-	IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
-	IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
-	IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
-
-/* for the irq vectors */
-static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
-					  IRQLIST_16(0x2), IRQLIST_16(0x3),
-	IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
-	IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
-	IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
-};
-
-#undef IRQ
-#undef IRQLIST_16
-
-/*
- * This is the 'legacy' 8259A Programmable Interrupt Controller,
- * present in the majority of PC/AT boxes.
- * plus some generic x86 specific things if generic specifics makes
- * any sense at all.
- * this file should become arch/i386/kernel/irq.c when the old irq.c
- * moves to arch independent land
- */
-
-static int i8259A_auto_eoi;
-DEFINE_SPINLOCK(i8259A_lock);
-static void mask_and_ack_8259A(unsigned int);
-
-static struct irq_chip i8259A_chip = {
-	.name		= "XT-PIC",
-	.mask		= disable_8259A_irq,
-	.disable	= disable_8259A_irq,
-	.unmask		= enable_8259A_irq,
-	.mask_ack	= mask_and_ack_8259A,
-};
-
-/*
- * 8259A PIC functions to handle ISA devices:
- */
-
-/*
- * This contains the irq mask for both 8259A irq controllers,
- */
-unsigned int cached_irq_mask = 0xffff;
-
-/*
- * Not all IRQs can be routed through the IO-APIC, eg. on certain (older)
- * boards the timer interrupt is not really connected to any IO-APIC pin,
- * it's fed to the master 8259A's IR0 line only.
- *
- * Any '1' bit in this mask means the IRQ is routed through the IO-APIC.
- * this 'mixed mode' IRQ handling costs nothing because it's only used
- * at IRQ setup time.
- */
-unsigned long io_apic_irqs;
-
-void disable_8259A_irq(unsigned int irq)
-{
-	unsigned int mask = 1 << irq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	cached_irq_mask |= mask;
-	if (irq & 8)
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-	else
-		outb(cached_master_mask, PIC_MASTER_IMR);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-void enable_8259A_irq(unsigned int irq)
-{
-	unsigned int mask = ~(1 << irq);
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	cached_irq_mask &= mask;
-	if (irq & 8)
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-	else
-		outb(cached_master_mask, PIC_MASTER_IMR);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-int i8259A_irq_pending(unsigned int irq)
-{
-	unsigned int mask = 1<<irq;
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	if (irq < 8)
-		ret = inb(PIC_MASTER_CMD) & mask;
-	else
-		ret = inb(PIC_SLAVE_CMD) & (mask >> 8);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-
-	return ret;
-}
-
-void make_8259A_irq(unsigned int irq)
-{
-	disable_irq_nosync(irq);
-	io_apic_irqs &= ~(1<<irq);
-	set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
-				      "XT");
-	enable_irq(irq);
-}
-
-/*
- * This function assumes to be called rarely. Switching between
- * 8259A registers is slow.
- * This has to be protected by the irq controller spinlock
- * before being called.
- */
-static inline int i8259A_irq_real(unsigned int irq)
-{
-	int value;
-	int irqmask = 1<<irq;
-
-	if (irq < 8) {
-		outb(0x0B,PIC_MASTER_CMD);	/* ISR register */
-		value = inb(PIC_MASTER_CMD) & irqmask;
-		outb(0x0A,PIC_MASTER_CMD);	/* back to the IRR register */
-		return value;
-	}
-	outb(0x0B,PIC_SLAVE_CMD);	/* ISR register */
-	value = inb(PIC_SLAVE_CMD) & (irqmask >> 8);
-	outb(0x0A,PIC_SLAVE_CMD);	/* back to the IRR register */
-	return value;
-}
-
-/*
- * Careful! The 8259A is a fragile beast, it pretty
- * much _has_ to be done exactly like this (mask it
- * first, _then_ send the EOI, and the order of EOI
- * to the two 8259s is important!
- */
-static void mask_and_ack_8259A(unsigned int irq)
-{
-	unsigned int irqmask = 1 << irq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	/*
-	 * Lightweight spurious IRQ detection. We do not want
-	 * to overdo spurious IRQ handling - it's usually a sign
-	 * of hardware problems, so we only do the checks we can
-	 * do without slowing down good hardware unnecessarily.
-	 *
-	 * Note that IRQ7 and IRQ15 (the two spurious IRQs
-	 * usually resulting from the 8259A-1|2 PICs) occur
-	 * even if the IRQ is masked in the 8259A. Thus we
-	 * can check spurious 8259A IRQs without doing the
-	 * quite slow i8259A_irq_real() call for every IRQ.
-	 * This does not cover 100% of spurious interrupts,
-	 * but should be enough to warn the user that there
-	 * is something bad going on ...
-	 */
-	if (cached_irq_mask & irqmask)
-		goto spurious_8259A_irq;
-	cached_irq_mask |= irqmask;
-
-handle_real_irq:
-	if (irq & 8) {
-		inb(PIC_SLAVE_IMR);	/* DUMMY - (do we need this?) */
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-		/* 'Specific EOI' to slave */
-		outb(0x60+(irq&7),PIC_SLAVE_CMD);
-		 /* 'Specific EOI' to master-IRQ2 */
-		outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD);
-	} else {
-		inb(PIC_MASTER_IMR);	/* DUMMY - (do we need this?) */
-		outb(cached_master_mask, PIC_MASTER_IMR);
-		/* 'Specific EOI' to master */
-		outb(0x60+irq,PIC_MASTER_CMD);
-	}
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-	return;
-
-spurious_8259A_irq:
-	/*
-	 * this is the slow path - should happen rarely.
-	 */
-	if (i8259A_irq_real(irq))
-		/*
-		 * oops, the IRQ _is_ in service according to the
-		 * 8259A - not spurious, go handle it.
-		 */
-		goto handle_real_irq;
-
-	{
-		static int spurious_irq_mask;
-		/*
-		 * At this point we can be sure the IRQ is spurious,
-		 * lets ACK and report it. [once per IRQ]
-		 */
-		if (!(spurious_irq_mask & irqmask)) {
-			printk(KERN_DEBUG
-			       "spurious 8259A interrupt: IRQ%d.\n", irq);
-			spurious_irq_mask |= irqmask;
-		}
-		atomic_inc(&irq_err_count);
-		/*
-		 * Theoretically we do not have to handle this IRQ,
-		 * but in Linux this does not cause problems and is
-		 * simpler for us.
-		 */
-		goto handle_real_irq;
-	}
-}
-
-static char irq_trigger[2];
-/**
- * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
- */
-static void restore_ELCR(char *trigger)
-{
-	outb(trigger[0], 0x4d0);
-	outb(trigger[1], 0x4d1);
-}
-
-static void save_ELCR(char *trigger)
-{
-	/* IRQ 0,1,2,8,13 are marked as reserved */
-	trigger[0] = inb(0x4d0) & 0xF8;
-	trigger[1] = inb(0x4d1) & 0xDE;
-}
-
-static int i8259A_resume(struct sys_device *dev)
-{
-	init_8259A(i8259A_auto_eoi);
-	restore_ELCR(irq_trigger);
-	return 0;
-}
-
-static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
-{
-	save_ELCR(irq_trigger);
-	return 0;
-}
-
-static int i8259A_shutdown(struct sys_device *dev)
-{
-	/* Put the i8259A into a quiescent state that
-	 * the kernel initialization code can get it
-	 * out of.
-	 */
-	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
-	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-1 */
-	return 0;
-}
-
-static struct sysdev_class i8259_sysdev_class = {
-	.name = "i8259",
-	.suspend = i8259A_suspend,
-	.resume = i8259A_resume,
-	.shutdown = i8259A_shutdown,
-};
-
-static struct sys_device device_i8259A = {
-	.id	= 0,
-	.cls	= &i8259_sysdev_class,
-};
-
-static int __init i8259A_init_sysfs(void)
-{
-	int error = sysdev_class_register(&i8259_sysdev_class);
-	if (!error)
-		error = sysdev_register(&device_i8259A);
-	return error;
-}
-
-device_initcall(i8259A_init_sysfs);
-
-void init_8259A(int auto_eoi)
-{
-	unsigned long flags;
-
-	i8259A_auto_eoi = auto_eoi;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-
-	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
-	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
-
-	/*
-	 * outb_pic - this has to work on a wide range of PC hardware.
-	 */
-	outb_pic(0x11, PIC_MASTER_CMD);	/* ICW1: select 8259A-1 init */
-	/* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
-	outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
-	/* 8259A-1 (the master) has a slave on IR2 */
-	outb_pic(0x04, PIC_MASTER_IMR);
-	if (auto_eoi)	/* master does Auto EOI */
-		outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR);
-	else		/* master expects normal EOI */
-		outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR);
-
-	outb_pic(0x11, PIC_SLAVE_CMD);	/* ICW1: select 8259A-2 init */
-	/* ICW2: 8259A-2 IR0-7 mapped to 0x38-0x3f */
-	outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
-	/* 8259A-2 is a slave on master's IR2 */
-	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
-	/* (slave's support for AEOI in flat mode is to be investigated) */
-	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR);
-
-	if (auto_eoi)
-		/*
-		 * In AEOI mode we just have to mask the interrupt
-		 * when acking.
-		 */
-		i8259A_chip.mask_ack = disable_8259A_irq;
-	else
-		i8259A_chip.mask_ack = mask_and_ack_8259A;
-
-	udelay(100);		/* wait for 8259A to initialize */
-
-	outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
-	outb(cached_slave_mask, PIC_SLAVE_IMR);	  /* restore slave IRQ mask */
-
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-
-
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.mask = CPU_MASK_NONE,
-	.name = "cascade",
-};
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... IRQ0_VECTOR - 1] = -1,
-	[IRQ0_VECTOR] = 0,
-	[IRQ1_VECTOR] = 1,
-	[IRQ2_VECTOR] = 2,
-	[IRQ3_VECTOR] = 3,
-	[IRQ4_VECTOR] = 4,
-	[IRQ5_VECTOR] = 5,
-	[IRQ6_VECTOR] = 6,
-	[IRQ7_VECTOR] = 7,
-	[IRQ8_VECTOR] = 8,
-	[IRQ9_VECTOR] = 9,
-	[IRQ10_VECTOR] = 10,
-	[IRQ11_VECTOR] = 11,
-	[IRQ12_VECTOR] = 12,
-	[IRQ13_VECTOR] = 13,
-	[IRQ14_VECTOR] = 14,
-	[IRQ15_VECTOR] = 15,
-	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-void __init init_ISA_irqs (void)
-{
-	int i;
-
-	init_bsp_APIC();
-	init_8259A(0);
-
-	for (i = 0; i < NR_IRQS; i++) {
-		irq_desc[i].status = IRQ_DISABLED;
-		irq_desc[i].action = NULL;
-		irq_desc[i].depth = 1;
-
-		if (i < 16) {
-			/*
-			 * 16 old-style INTA-cycle interrupts:
-			 */
-			set_irq_chip_and_handler_name(i, &i8259A_chip,
-						      handle_level_irq, "XT");
-		} else {
-			/*
-			 * 'high' PCI IRQs filled in on demand
-			 */
-			irq_desc[i].chip = &no_irq_chip;
-		}
-	}
-}
-
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
-{
-	int i;
-
-	init_ISA_irqs();
-	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
-	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (vector != IA32_SYSCALL_VECTOR)
-			set_intr_gate(vector, interrupt[i]);
-	}
-
-#ifdef CONFIG_SMP
-	/*
-	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
-	 * IPI, driven by wakeup.
-	 */
-	set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
-	/* IPIs for invalidation */
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
-
-	/* IPI for generic function call */
-	set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
-	/* Low priority IPI to cleanup after moving an irq */
-	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
-#endif
-	set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-	set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
-
-	/* self generated IPI for local APIC timer */
-	set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
-	/* IPI vectors for APIC spurious and error interrupts */
-	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-
-	if (!acpi_ioapic)
-		setup_irq(2, &irq2);
-}

arch/x86/kernel/io_apic_64.c

@@ -61,7 +61,7 @@ struct irq_cfg {
 };
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
 	[0]  = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR,  },
 	[1]  = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR,  },
 	[2]  = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR,  },
@@ -82,6 +82,10 @@ struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
 
 static int assign_irq_vector(int irq, cpumask_t mask);
 
+int first_system_vector = 0xfe;
+
+char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+
 #define __apicdebuginit  __init
 
 int sis_apic_bug; /* not actually supported, dummy for compile */
@@ -90,7 +94,7 @@ static int no_timer_check;
 
 static int disable_timer_pin_1 __initdata;
 
-int timer_over_8254 __initdata = 1;
+int timer_through_8259 __initdata;
 
 /* Where if anywhere is the i8259 connect in external int mode */
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
@@ -104,15 +108,17 @@ DEFINE_SPINLOCK(vector_lock);
 int nr_ioapic_registers[MAX_IO_APICS];
 
 /* I/O APIC entries */
-struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
 int nr_ioapics;
 
 /* MP IRQ source entries */
-struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
 /* # of MP IRQ source entries */
 int mp_irq_entries;
 
+DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+
 /*
  * Rough estimation of how many shared IRQs there are, can
  * be changed anytime.
@@ -140,7 +146,7 @@ struct io_apic {
 static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
 {
 	return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
-		+ (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK);
+		+ (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
 }
 
 static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
@@ -183,7 +189,7 @@ static bool io_apic_level_ack_pending(unsigned int irq)
 			break;
 		reg = io_apic_read(entry->apic, 0x10 + pin*2);
 		/* Is the remote IRR bit set? */
-		if ((reg >> 14) & 1) {
+		if (reg & IO_APIC_REDIR_REMOTE_IRR) {
 			spin_unlock_irqrestore(&ioapic_lock, flags);
 			return true;
 		}
@@ -298,7 +304,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 			break;
 		io_apic_write(apic, 0x11 + pin*2, dest);
 		reg = io_apic_read(apic, 0x10 + pin*2);
-		reg &= ~0x000000ff;
+		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
 		reg |= vector;
 		io_apic_modify(apic, reg);
 		if (!entry->next)
@@ -360,16 +366,37 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 	entry->pin = pin;
 }
 
+/*
+ * Reroute an IRQ to a different pin.
+ */
+static void __init replace_pin_at_irq(unsigned int irq,
+				      int oldapic, int oldpin,
+				      int newapic, int newpin)
+{
+	struct irq_pin_list *entry = irq_2_pin + irq;
+
+	while (1) {
+		if (entry->apic == oldapic && entry->pin == oldpin) {
+			entry->apic = newapic;
+			entry->pin = newpin;
+		}
+		if (!entry->next)
+			break;
+		entry = irq_2_pin + entry->next;
+	}
+}
+
 
 #define DO_ACTION(name,R,ACTION, FINAL)					\
 									\
 	static void name##_IO_APIC_irq (unsigned int irq)		\
 	__DO_ACTION(R, ACTION, FINAL)
 
-DO_ACTION( __mask,             0, |= 0x00010000, io_apic_sync(entry->apic) )
-						/* mask = 1 */
-DO_ACTION( __unmask,           0, &= 0xfffeffff, )
-						/* mask = 0 */
+/* mask = 1 */
+DO_ACTION(__mask,	0, |= IO_APIC_REDIR_MASKED, io_apic_sync(entry->apic))
+
+/* mask = 0 */
+DO_ACTION(__unmask,	0, &= ~IO_APIC_REDIR_MASKED, )
 
 static void mask_IO_APIC_irq (unsigned int irq)
 {
@@ -430,20 +457,6 @@ static int __init disable_timer_pin_setup(char *arg)
 }
 __setup("disable_timer_pin_1", disable_timer_pin_setup);
 
-static int __init setup_disable_8254_timer(char *s)
-{
-	timer_over_8254 = -1;
-	return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
-	timer_over_8254 = 2;
-	return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
 
 /*
  * Find the IRQ entry number of a certain pin.
@@ -453,10 +466,10 @@ static int find_irq_entry(int apic, int pin, int type)
 	int i;
 
 	for (i = 0; i < mp_irq_entries; i++)
-		if (mp_irqs[i].mpc_irqtype == type &&
-		    (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid ||
-		     mp_irqs[i].mpc_dstapic == MP_APIC_ALL) &&
-		    mp_irqs[i].mpc_dstirq == pin)
+		if (mp_irqs[i].mp_irqtype == type &&
+		    (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
+		     mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
+		    mp_irqs[i].mp_dstirq == pin)
 			return i;
 
 	return -1;
@@ -470,13 +483,13 @@ static int __init find_isa_irq_pin(int irq, int type)
 	int i;
 
 	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].mpc_srcbus;
+		int lbus = mp_irqs[i].mp_srcbus;
 
 		if (test_bit(lbus, mp_bus_not_pci) &&
-		    (mp_irqs[i].mpc_irqtype == type) &&
-		    (mp_irqs[i].mpc_srcbusirq == irq))
+		    (mp_irqs[i].mp_irqtype == type) &&
+		    (mp_irqs[i].mp_srcbusirq == irq))
 
-			return mp_irqs[i].mpc_dstirq;
+			return mp_irqs[i].mp_dstirq;
 	}
 	return -1;
 }
@@ -486,17 +499,17 @@ static int __init find_isa_irq_apic(int irq, int type)
 	int i;
 
 	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].mpc_srcbus;
+		int lbus = mp_irqs[i].mp_srcbus;
 
 		if (test_bit(lbus, mp_bus_not_pci) &&
-		    (mp_irqs[i].mpc_irqtype == type) &&
-		    (mp_irqs[i].mpc_srcbusirq == irq))
+		    (mp_irqs[i].mp_irqtype == type) &&
+		    (mp_irqs[i].mp_srcbusirq == irq))
 			break;
 	}
 	if (i < mp_irq_entries) {
 		int apic;
 		for(apic = 0; apic < nr_ioapics; apic++) {
-			if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
+			if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
 				return apic;
 		}
 	}
@@ -516,28 +529,28 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 
 	apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
 		bus, slot, pin);
-	if (mp_bus_id_to_pci_bus[bus] == -1) {
+	if (test_bit(bus, mp_bus_not_pci)) {
 		apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
 		return -1;
 	}
 	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].mpc_srcbus;
+		int lbus = mp_irqs[i].mp_srcbus;
 
 		for (apic = 0; apic < nr_ioapics; apic++)
-			if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic ||
-			    mp_irqs[i].mpc_dstapic == MP_APIC_ALL)
+			if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
+			    mp_irqs[i].mp_dstapic == MP_APIC_ALL)
 				break;
 
 		if (!test_bit(lbus, mp_bus_not_pci) &&
-		    !mp_irqs[i].mpc_irqtype &&
+		    !mp_irqs[i].mp_irqtype &&
 		    (bus == lbus) &&
-		    (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
-			int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+		    (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
+			int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
 
 			if (!(apic || IO_APIC_IRQ(irq)))
 				continue;
 
-			if (pin == (mp_irqs[i].mpc_srcbusirq & 3))
+			if (pin == (mp_irqs[i].mp_srcbusirq & 3))
 				return irq;
 			/*
 			 * Use the first all-but-pin matching entry as a
@@ -565,13 +578,13 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 
 static int MPBIOS_polarity(int idx)
 {
-	int bus = mp_irqs[idx].mpc_srcbus;
+	int bus = mp_irqs[idx].mp_srcbus;
 	int polarity;
 
 	/*
 	 * Determine IRQ line polarity (high active or low active):
 	 */
-	switch (mp_irqs[idx].mpc_irqflag & 3)
+	switch (mp_irqs[idx].mp_irqflag & 3)
 	{
 		case 0: /* conforms, ie. bus-type dependent polarity */
 			if (test_bit(bus, mp_bus_not_pci))
@@ -607,13 +620,13 @@ static int MPBIOS_polarity(int idx)
 
 static int MPBIOS_trigger(int idx)
 {
-	int bus = mp_irqs[idx].mpc_srcbus;
+	int bus = mp_irqs[idx].mp_srcbus;
 	int trigger;
 
 	/*
 	 * Determine IRQ trigger mode (edge or level sensitive):
 	 */
-	switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+	switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
 	{
 		case 0: /* conforms, ie. bus-type dependent */
 			if (test_bit(bus, mp_bus_not_pci))
@@ -660,16 +673,16 @@ static inline int irq_trigger(int idx)
 static int pin_2_irq(int idx, int apic, int pin)
 {
 	int irq, i;
-	int bus = mp_irqs[idx].mpc_srcbus;
+	int bus = mp_irqs[idx].mp_srcbus;
 
 	/*
 	 * Debugging check, we are in big trouble if this message pops up!
 	 */
-	if (mp_irqs[idx].mpc_dstirq != pin)
+	if (mp_irqs[idx].mp_dstirq != pin)
 		printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
 
 	if (test_bit(bus, mp_bus_not_pci)) {
-		irq = mp_irqs[idx].mpc_srcbusirq;
+		irq = mp_irqs[idx].mp_srcbusirq;
 	} else {
 		/*
 		 * PCI IRQs are mapped in order
@@ -730,7 +743,7 @@ static int __assign_irq_vector(int irq, cpumask_t mask)
 		offset = current_offset;
 next:
 		vector += 8;
-		if (vector >= FIRST_SYSTEM_VECTOR) {
+		if (vector >= first_system_vector) {
 			/* If we run out of vectors on large boxen, must share them. */
 			offset = (offset + 1) % 8;
 			vector = FIRST_DEVICE_VECTOR + offset;
@@ -788,7 +801,7 @@ static void __clear_irq_vector(int irq)
 	cpus_clear(cfg->domain);
 }
 
-void __setup_vector_irq(int cpu)
+static void __setup_vector_irq(int cpu)
 {
 	/* Initialize vector_irq on a new cpu */
 	/* This function must be called with vector_lock held */
@@ -811,6 +824,13 @@ void __setup_vector_irq(int cpu)
 	}
 }
 
+void setup_vector_irq(int cpu)
+{
+	spin_lock(&vector_lock);
+	__setup_vector_irq(smp_processor_id());
+	spin_unlock(&vector_lock);
+}
+
 
 static struct irq_chip ioapic_chip;
 
@@ -846,7 +866,7 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
 	apic_printk(APIC_VERBOSE,KERN_DEBUG
 		    "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
 		    "IRQ %d Mode:%i Active:%i)\n",
-		    apic, mp_ioapics[apic].mpc_apicid, pin, cfg->vector,
+		    apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
 		    irq, trigger, polarity);
 
 	/*
@@ -887,10 +907,10 @@ static void __init setup_IO_APIC_irqs(void)
 		idx = find_irq_entry(apic,pin,mp_INT);
 		if (idx == -1) {
 			if (first_notcon) {
-				apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mpc_apicid, pin);
+				apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mp_apicid, pin);
 				first_notcon = 0;
 			} else
-				apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin);
+				apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mp_apicid, pin);
 			continue;
 		}
 		if (!first_notcon) {
@@ -911,26 +931,21 @@ static void __init setup_IO_APIC_irqs(void)
 }
 
 /*
- * Set up the 8259A-master output pin as broadcast to all
- * CPUs.
+ * Set up the timer pin, possibly with the 8259A-master behind.
  */
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+					int vector)
 {
 	struct IO_APIC_route_entry entry;
 
 	memset(&entry, 0, sizeof(entry));
 
-	disable_8259A_irq(0);
-
-	/* mask LVT0 */
-	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-
 	/*
 	 * We use logical delivery to get the timer IRQ
 	 * to the first CPU.
 	 */
 	entry.dest_mode = INT_DEST_MODE;
-	entry.mask = 0;					/* unmask IRQ now */
+	entry.mask = 1;					/* mask IRQ now */
 	entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
 	entry.delivery_mode = INT_DELIVERY_MODE;
 	entry.polarity = 0;
@@ -939,7 +954,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 
 	/*
 	 * The timer IRQ doesn't have to know that behind the
-	 * scene we have a 8259A-master in AEOI mode ...
+	 * scene we may have a 8259A-master in AEOI mode ...
 	 */
 	set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
 
@@ -947,8 +962,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 	 * Add it to the IO-APIC irq-routing table:
 	 */
 	ioapic_write_entry(apic, pin, entry);
-
-	enable_8259A_irq(0);
 }
 
 void __apicdebuginit print_IO_APIC(void)
@@ -965,7 +978,7 @@ void __apicdebuginit print_IO_APIC(void)
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
 	for (i = 0; i < nr_ioapics; i++)
 		printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
-		       mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
+		       mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
 
 	/*
 	 * We are a bit conservative about what we expect.  We have to
@@ -983,7 +996,7 @@ void __apicdebuginit print_IO_APIC(void)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	printk("\n");
-	printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
+	printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
 	printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
 	printk(KERN_DEBUG ".......    : physical APIC id: %02X\n", reg_00.bits.ID);
 
@@ -1077,6 +1090,7 @@ void __apicdebuginit print_local_APIC(void * dummy)
 
 	printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
 		smp_processor_id(), hard_smp_processor_id());
+	v = apic_read(APIC_ID);
 	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
 	v = apic_read(APIC_LVR);
 	printk(KERN_INFO "... APIC VERSION: %08x\n", v);
@@ -1540,7 +1554,7 @@ static inline void init_IO_APIC_traps(void)
 	}
 }
 
-static void enable_lapic_irq (unsigned int irq)
+static void unmask_lapic_irq(unsigned int irq)
 {
 	unsigned long v;
 
@@ -1548,7 +1562,7 @@ static void enable_lapic_irq (unsigned int irq)
 	apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
 }
 
-static void disable_lapic_irq (unsigned int irq)
+static void mask_lapic_irq(unsigned int irq)
 {
 	unsigned long v;
 
@@ -1561,19 +1575,20 @@ static void ack_lapic_irq (unsigned int irq)
 	ack_APIC_irq();
 }
 
-static void end_lapic_irq (unsigned int i) { /* nothing */ }
-
-static struct hw_interrupt_type lapic_irq_type __read_mostly = {
-	.name = "local-APIC",
-	.typename = "local-APIC-edge",
-	.startup = NULL, /* startup_irq() not used for IRQ0 */
-	.shutdown = NULL, /* shutdown_irq() not used for IRQ0 */
-	.enable = enable_lapic_irq,
-	.disable = disable_lapic_irq,
-	.ack = ack_lapic_irq,
-	.end = end_lapic_irq,
+static struct irq_chip lapic_chip __read_mostly = {
+	.name		= "local-APIC",
+	.mask		= mask_lapic_irq,
+	.unmask		= unmask_lapic_irq,
+	.ack		= ack_lapic_irq,
 };
 
+static void lapic_register_intr(int irq)
+{
+	irq_desc[irq].status &= ~IRQ_LEVEL;
+	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+				      "edge");
+}
+
 static void __init setup_nmi(void)
 {
 	/*
@@ -1659,6 +1674,7 @@ static inline void __init check_timer(void)
 	struct irq_cfg *cfg = irq_cfg + 0;
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
+	int no_pin1 = 0;
 
 	local_irq_save(flags);
 
@@ -1669,16 +1685,11 @@ static inline void __init check_timer(void)
 	assign_irq_vector(0, TARGET_CPUS);
 
 	/*
-	 * Subtle, code in do_timer_interrupt() expects an AEOI
-	 * mode for the 8259A whenever interrupts are routed
-	 * through I/O APICs.  Also IRQ0 has to be enabled in
-	 * the 8259A which implies the virtual wire has to be
-	 * disabled in the local APIC.
+	 * As IRQ0 is to be enabled in the 8259A, the virtual
+	 * wire has to be disabled in the local APIC.
 	 */
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
-	if (timer_over_8254 > 0)
-		enable_8259A_irq(0);
 
 	pin1  = find_isa_irq_pin(0, mp_INT);
 	apic1 = find_isa_irq_apic(0, mp_INT);
@@ -1688,15 +1699,33 @@ static inline void __init check_timer(void)
 	apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
 		cfg->vector, apic1, pin1, apic2, pin2);
 
+	/*
+	 * Some BIOS writers are clueless and report the ExtINTA
+	 * I/O APIC input from the cascaded 8259A as the timer
+	 * interrupt input.  So just in case, if only one pin
+	 * was found above, try it both directly and through the
+	 * 8259A.
+	 */
+	if (pin1 == -1) {
+		pin1 = pin2;
+		apic1 = apic2;
+		no_pin1 = 1;
+	} else if (pin2 == -1) {
+		pin2 = pin1;
+		apic2 = apic1;
+	}
+
 	if (pin1 != -1) {
 		/*
 		 * Ok, does IRQ0 through the IOAPIC work?
 		 */
+		if (no_pin1) {
+			add_pin_to_irq(0, apic1, pin1);
+			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+		}
 		unmask_IO_APIC_irq(0);
 		if (!no_timer_check && timer_irq_works()) {
-			nmi_watchdog_default();
 			if (nmi_watchdog == NMI_IO_APIC) {
-				disable_8259A_irq(0);
 				setup_nmi();
 				enable_8259A_irq(0);
 			}
@@ -1705,43 +1734,48 @@ static inline void __init check_timer(void)
 			goto out;
 		}
 		clear_IO_APIC_pin(apic1, pin1);
-		apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not "
-				"connected to IO-APIC\n");
-	}
+		if (!no_pin1)
+			apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: "
+				    "8254 timer not connected to IO-APIC\n");
 
-	apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) "
-				"through the 8259A ... ");
-	if (pin2 != -1) {
+		apic_printk(APIC_VERBOSE,KERN_INFO
+			"...trying to set up timer (IRQ0) "
+			"through the 8259A ... ");
 		apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...",
 			apic2, pin2);
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector);
+		replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+		unmask_IO_APIC_irq(0);
+		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_VERBOSE," works.\n");
-			nmi_watchdog_default();
+			timer_through_8259 = 1;
 			if (nmi_watchdog == NMI_IO_APIC) {
+				disable_8259A_irq(0);
 				setup_nmi();
+				enable_8259A_irq(0);
 			}
 			goto out;
 		}
 		/*
 		 * Cleanup, just in case ...
 		 */
+		disable_8259A_irq(0);
 		clear_IO_APIC_pin(apic2, pin2);
+		apic_printk(APIC_VERBOSE," failed.\n");
 	}
-	apic_printk(APIC_VERBOSE," failed.\n");
 
 	if (nmi_watchdog == NMI_IO_APIC) {
 		printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
-		nmi_watchdog = 0;
+		nmi_watchdog = NMI_NONE;
 	}
 
 	apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
 
-	disable_8259A_irq(0);
-	irq_desc[0].chip = &lapic_irq_type;
+	lapic_register_intr(0);
 	apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);	/* Fixed mode */
 	enable_8259A_irq(0);
 
@@ -1749,6 +1783,7 @@ static inline void __init check_timer(void)
 		apic_printk(APIC_VERBOSE," works.\n");
 		goto out;
 	}
+	disable_8259A_irq(0);
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
 	apic_printk(APIC_VERBOSE," failed.\n");
 
@@ -1778,11 +1813,21 @@ static int __init notimercheck(char *s)
 __setup("no_timer_check", notimercheck);
 
 /*
- *
- * IRQs that are handled by the PIC in the MPS IOAPIC case.
- * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
- *   Linux doesn't really care, as it's not actually used
- *   for any interrupt handling anyway.
+ * Traditionally ISA IRQ2 is the cascade IRQ, and is not available
+ * to devices.  However there may be an I/O APIC pin available for
+ * this interrupt regardless.  The pin may be left unconnected, but
+ * typically it will be reused as an ExtINT cascade interrupt for
+ * the master 8259A.  In the MPS case such a pin will normally be
+ * reported as an ExtINT interrupt in the MP table.  With ACPI
+ * there is no provision for ExtINT interrupts, and in the absence
+ * of an override it would be treated as an ordinary ISA I/O APIC
+ * interrupt, that is edge-triggered and unmasked by default.  We
+ * used to do this, but it caused problems on some systems because
+ * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using
+ * the same ExtINT cascade interrupt to drive the local APIC of the
+ * bootstrap processor.  Therefore we refrain from routing IRQ2 to
+ * the I/O APIC in all cases now.  No actual device should request
+ * it anyway.  --macro
  */
 #define PIC_IRQS	(1<<2)
 
@@ -1793,10 +1838,7 @@ void __init setup_IO_APIC(void)
 	 * calling enable_IO_APIC() is moved to setup_local_APIC for BP
 	 */
 
-	if (acpi_ioapic)
-		io_apic_irqs = ~0;	/* all IRQs go through IOAPIC */
-	else
-		io_apic_irqs = ~PIC_IRQS;
+	io_apic_irqs = ~PIC_IRQS;
 
 	apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
 
@@ -1841,8 +1883,8 @@ static int ioapic_resume(struct sys_device *dev)
 
 	spin_lock_irqsave(&ioapic_lock, flags);
 	reg_00.raw = io_apic_read(dev->id, 0);
-	if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) {
-		reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid;
+	if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
+		reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
 		io_apic_write(dev->id, 0, reg_00.raw);
 	}
 	spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -2242,8 +2284,8 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 		return -1;
 
 	for (i = 0; i < mp_irq_entries; i++)
-		if (mp_irqs[i].mpc_irqtype == mp_INT &&
-		    mp_irqs[i].mpc_srcbusirq == bus_irq)
+		if (mp_irqs[i].mp_irqtype == mp_INT &&
+		    mp_irqs[i].mp_srcbusirq == bus_irq)
 			break;
 	if (i >= mp_irq_entries)
 		return -1;
@@ -2336,7 +2378,7 @@ void __init ioapic_init_mappings(void)
 	ioapic_res = ioapic_setup_resources();
 	for (i = 0; i < nr_ioapics; i++) {
 		if (smp_found_config) {
-			ioapic_phys = mp_ioapics[i].mpc_apicaddr;
+			ioapic_phys = mp_ioapics[i].mp_apicaddr;
 		} else {
 			ioapic_phys = (unsigned long)
 				alloc_bootmem_pages(PAGE_SIZE);

arch/x86/kernel/ipi.c

@@ -8,7 +8,6 @@
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/cache.h>
-#include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
 

arch/x86/kernel/irq_32.c

@@ -48,6 +48,29 @@ void ack_bad_irq(unsigned int irq)
 #endif
 }
 
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+/* Debugging check for stack overflow: is there less than 1KB free? */
+static int check_stack_overflow(void)
+{
+	long sp;
+
+	__asm__ __volatile__("andl %%esp,%0" :
+			     "=r" (sp) : "0" (THREAD_SIZE - 1));
+
+	return sp < (sizeof(struct thread_info) + STACK_WARN);
+}
+
+static void print_stack_overflow(void)
+{
+	printk(KERN_WARNING "low stack detected by irq handler\n");
+	dump_stack();
+}
+
+#else
+static inline int check_stack_overflow(void) { return 0; }
+static inline void print_stack_overflow(void) { }
+#endif
+
 #ifdef CONFIG_4KSTACKS
 /*
  * per-CPU IRQ handling contexts (thread information and stack)
@@ -59,48 +82,29 @@ union irq_ctx {
 
 static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly;
 static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly;
-#endif
 
-/*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- */
-unsigned int do_IRQ(struct pt_regs *regs)
-{	
-	struct pt_regs *old_regs;
-	/* high bit used in ret_from_ code */
-	int irq = ~regs->orig_ax;
-	struct irq_desc *desc = irq_desc + irq;
-#ifdef CONFIG_4KSTACKS
-	union irq_ctx *curctx, *irqctx;
-	u32 *isp;
-#endif
+static char softirq_stack[NR_CPUS * THREAD_SIZE]
+		__attribute__((__section__(".bss.page_aligned")));
 
-	if (unlikely((unsigned)irq >= NR_IRQS)) {
-		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
-					__func__, irq);
-		BUG();
-	}
+static char hardirq_stack[NR_CPUS * THREAD_SIZE]
+		__attribute__((__section__(".bss.page_aligned")));
 
-	old_regs = set_irq_regs(regs);
-	irq_enter();
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
-	/* Debugging check for stack overflow: is there less than 1KB free? */
-	{
-		long sp;
-
-		__asm__ __volatile__("andl %%esp,%0" :
-					"=r" (sp) : "0" (THREAD_SIZE - 1));
-		if (unlikely(sp < (sizeof(struct thread_info) + STACK_WARN))) {
-			printk("do_IRQ: stack overflow: %ld\n",
-				sp - sizeof(struct thread_info));
-			dump_stack();
-		}
-	}
-#endif
+static void call_on_stack(void *func, void *stack)
+{
+	asm volatile("xchgl	%%ebx,%%esp	\n"
+		     "call	*%%edi		\n"
+		     "movl	%%ebx,%%esp	\n"
+		     : "=b" (stack)
+		     : "0" (stack),
+		       "D"(func)
+		     : "memory", "cc", "edx", "ecx", "eax");
+}
 
-#ifdef CONFIG_4KSTACKS
+static inline int
+execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
+{
+	union irq_ctx *curctx, *irqctx;
+	u32 *isp, arg1, arg2;
 
 	curctx = (union irq_ctx *) current_thread_info();
 	irqctx = hardirq_ctx[smp_processor_id()];
@@ -111,52 +115,39 @@ unsigned int do_IRQ(struct pt_regs *regs)
 	 * handler) we can't do that and just have to keep using the
 	 * current stack (which is the irq stack already after all)
 	 */
-	if (curctx != irqctx) {
-		int arg1, arg2, bx;
-
-		/* build the stack frame on the IRQ stack */
-		isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
-		irqctx->tinfo.task = curctx->tinfo.task;
-		irqctx->tinfo.previous_esp = current_stack_pointer;
+	if (unlikely(curctx == irqctx))
+		return 0;
 
-		/*
-		 * Copy the softirq bits in preempt_count so that the
-		 * softirq checks work in the hardirq context.
-		 */
-		irqctx->tinfo.preempt_count =
-			(irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) |
-			(curctx->tinfo.preempt_count & SOFTIRQ_MASK);
-
-		asm volatile(
-			"       xchgl  %%ebx,%%esp    \n"
-			"       call   *%%edi         \n"
-			"       movl   %%ebx,%%esp    \n"
-			: "=a" (arg1), "=d" (arg2), "=b" (bx)
-			:  "0" (irq),   "1" (desc),  "2" (isp),
-			   "D" (desc->handle_irq)
-			: "memory", "cc", "ecx"
-		);
-	} else
-#endif
-		desc->handle_irq(irq, desc);
+	/* build the stack frame on the IRQ stack */
+	isp = (u32 *) ((char*)irqctx + sizeof(*irqctx));
+	irqctx->tinfo.task = curctx->tinfo.task;
+	irqctx->tinfo.previous_esp = current_stack_pointer;
 
-	irq_exit();
-	set_irq_regs(old_regs);
+	/*
+	 * Copy the softirq bits in preempt_count so that the
+	 * softirq checks work in the hardirq context.
+	 */
+	irqctx->tinfo.preempt_count =
+		(irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) |
+		(curctx->tinfo.preempt_count & SOFTIRQ_MASK);
+
+	if (unlikely(overflow))
+		call_on_stack(print_stack_overflow, isp);
+
+	asm volatile("xchgl	%%ebx,%%esp	\n"
+		     "call	*%%edi		\n"
+		     "movl	%%ebx,%%esp	\n"
+		     : "=a" (arg1), "=d" (arg2), "=b" (isp)
+		     :  "0" (irq),   "1" (desc),  "2" (isp),
+			"D" (desc->handle_irq)
+		     : "memory", "cc", "ecx");
 	return 1;
 }
 
-#ifdef CONFIG_4KSTACKS
-
-static char softirq_stack[NR_CPUS * THREAD_SIZE]
-		__attribute__((__section__(".bss.page_aligned")));
-
-static char hardirq_stack[NR_CPUS * THREAD_SIZE]
-		__attribute__((__section__(".bss.page_aligned")));
-
 /*
  * allocate per-cpu stacks for hardirq and for softirq processing
  */
-void irq_ctx_init(int cpu)
+void __cpuinit irq_ctx_init(int cpu)
 {
 	union irq_ctx *irqctx;
 
@@ -164,25 +155,25 @@ void irq_ctx_init(int cpu)
 		return;
 
 	irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE];
-	irqctx->tinfo.task              = NULL;
-	irqctx->tinfo.exec_domain       = NULL;
-	irqctx->tinfo.cpu               = cpu;
-	irqctx->tinfo.preempt_count     = HARDIRQ_OFFSET;
-	irqctx->tinfo.addr_limit        = MAKE_MM_SEG(0);
+	irqctx->tinfo.task		= NULL;
+	irqctx->tinfo.exec_domain	= NULL;
+	irqctx->tinfo.cpu		= cpu;
+	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
+	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
 
 	hardirq_ctx[cpu] = irqctx;
 
 	irqctx = (union irq_ctx*) &softirq_stack[cpu*THREAD_SIZE];
-	irqctx->tinfo.task              = NULL;
-	irqctx->tinfo.exec_domain       = NULL;
-	irqctx->tinfo.cpu               = cpu;
-	irqctx->tinfo.preempt_count     = 0;
-	irqctx->tinfo.addr_limit        = MAKE_MM_SEG(0);
+	irqctx->tinfo.task		= NULL;
+	irqctx->tinfo.exec_domain	= NULL;
+	irqctx->tinfo.cpu		= cpu;
+	irqctx->tinfo.preempt_count	= 0;
+	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
 
 	softirq_ctx[cpu] = irqctx;
 
-	printk("CPU %u irqstacks, hard=%p soft=%p\n",
-		cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
+	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
+	       cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
 }
 
 void irq_ctx_exit(int cpu)
@@ -211,24 +202,55 @@ asmlinkage void do_softirq(void)
 		/* build the stack frame on the softirq stack */
 		isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
 
-		asm volatile(
-			"       xchgl   %%ebx,%%esp     \n"
-			"       call    __do_softirq    \n"
-			"       movl    %%ebx,%%esp     \n"
-			: "=b"(isp)
-			: "0"(isp)
-			: "memory", "cc", "edx", "ecx", "eax"
-		);
+		call_on_stack(__do_softirq, isp);
 		/*
 		 * Shouldnt happen, we returned above if in_interrupt():
-	 	 */
+		 */
 		WARN_ON_ONCE(softirq_count());
 	}
 
 	local_irq_restore(flags);
 }
+
+#else
+static inline int
+execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
 #endif
 
+/*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+unsigned int do_IRQ(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs;
+	/* high bit used in ret_from_ code */
+	int overflow, irq = ~regs->orig_ax;
+	struct irq_desc *desc = irq_desc + irq;
+
+	if (unlikely((unsigned)irq >= NR_IRQS)) {
+		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
+					__func__, irq);
+		BUG();
+	}
+
+	old_regs = set_irq_regs(regs);
+	irq_enter();
+
+	overflow = check_stack_overflow();
+
+	if (!execute_on_irq_stack(overflow, desc, irq)) {
+		if (unlikely(overflow))
+			print_stack_overflow();
+		desc->handle_irq(irq, desc);
+	}
+
+	irq_exit();
+	set_irq_regs(old_regs);
+	return 1;
+}
+
 /*
  * Interrupt statistics:
  */
@@ -313,16 +335,20 @@ skip:
 				per_cpu(irq_stat,j).irq_tlb_count);
 		seq_printf(p, "  TLB shootdowns\n");
 #endif
+#ifdef CONFIG_X86_MCE
 		seq_printf(p, "TRM: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ",
 				per_cpu(irq_stat,j).irq_thermal_count);
 		seq_printf(p, "  Thermal event interrupts\n");
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
 		seq_printf(p, "SPU: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ",
 				per_cpu(irq_stat,j).irq_spurious_count);
 		seq_printf(p, "  Spurious interrupts\n");
+#endif
 		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
 		seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
@@ -331,6 +357,40 @@ skip:
 	return 0;
 }
 
+/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+	u64 sum = nmi_count(cpu);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	sum += per_cpu(irq_stat, cpu).apic_timer_irqs;
+#endif
+#ifdef CONFIG_SMP
+	sum += per_cpu(irq_stat, cpu).irq_resched_count;
+	sum += per_cpu(irq_stat, cpu).irq_call_count;
+	sum += per_cpu(irq_stat, cpu).irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+	sum += per_cpu(irq_stat, cpu).irq_thermal_count;
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+	sum += per_cpu(irq_stat, cpu).irq_spurious_count;
+#endif
+	return sum;
+}
+
+u64 arch_irq_stat(void)
+{
+	u64 sum = atomic_read(&irq_err_count);
+
+#ifdef CONFIG_X86_IO_APIC
+	sum += atomic_read(&irq_mis_count);
+#endif
+	return sum;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <mach_apic.h>
 

arch/x86/kernel/irq_64.c

@@ -135,6 +135,7 @@ skip:
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
 		seq_printf(p, "  TLB shootdowns\n");
 #endif
+#ifdef CONFIG_X86_MCE
 		seq_printf(p, "TRM: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count);
@@ -143,6 +144,7 @@ skip:
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count);
 		seq_printf(p, "  Threshold APIC interrupts\n");
+#endif
 		seq_printf(p, "SPU: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count);
@@ -152,6 +154,32 @@ skip:
 	return 0;
 }
 
+/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+	u64 sum = cpu_pda(cpu)->__nmi_count;
+
+	sum += cpu_pda(cpu)->apic_timer_irqs;
+#ifdef CONFIG_SMP
+	sum += cpu_pda(cpu)->irq_resched_count;
+	sum += cpu_pda(cpu)->irq_call_count;
+	sum += cpu_pda(cpu)->irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+	sum += cpu_pda(cpu)->irq_thermal_count;
+	sum += cpu_pda(cpu)->irq_threshold_count;
+#endif
+	sum += cpu_pda(cpu)->irq_spurious_count;
+	return sum;
+}
+
+u64 arch_irq_stat(void)
+{
+	return atomic_read(&irq_err_count);
+}
+
 /*
  * do_IRQ handles all normal device IRQ's (the special
  * SMP cross-CPU interrupts have their own specific

arch/x86/kernel/irqinit_32.c

@@ -0,0 +1,114 @@
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/timer.h>
+#include <asm/pgtable.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#include <asm/arch_hooks.h>
+#include <asm/i8259.h>
+
+
+
+/*
+ * Note that on a 486, we don't want to do a SIGFPE on an irq13
+ * as the irq is unreliable, and exception 16 works correctly
+ * (ie as explained in the intel literature). On a 386, you
+ * can't use exception 16 due to bad IBM design, so we have to
+ * rely on the less exact irq13.
+ *
+ * Careful.. Not only is IRQ13 unreliable, but it is also
+ * leads to races. IBM designers who came up with it should
+ * be shot.
+ */
+ 
+
+static irqreturn_t math_error_irq(int cpl, void *dev_id)
+{
+	extern void math_error(void __user *);
+	outb(0,0xF0);
+	if (ignore_fpu_irq || !boot_cpu_data.hard_math)
+		return IRQ_NONE;
+	math_error((void __user *)get_irq_regs()->ip);
+	return IRQ_HANDLED;
+}
+
+/*
+ * New motherboards sometimes make IRQ 13 be a PCI interrupt,
+ * so allow interrupt sharing.
+ */
+static struct irqaction fpu_irq = {
+	.handler = math_error_irq,
+	.mask = CPU_MASK_NONE,
+	.name = "fpu",
+};
+
+void __init init_ISA_irqs (void)
+{
+	int i;
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	init_bsp_APIC();
+#endif
+	init_8259A(0);
+
+	/*
+	 * 16 old-style INTA-cycle interrupts:
+	 */
+	for (i = 0; i < 16; i++) {
+		set_irq_chip_and_handler_name(i, &i8259A_chip,
+					      handle_level_irq, "XT");
+	}
+}
+
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(void)
+{
+	int i;
+
+	/* all the set up before the call gates are initialised */
+	pre_intr_init_hook();
+
+	/*
+	 * Cover the whole vector space, no vector can escape
+	 * us. (some of these will be overridden and become
+	 * 'special' SMP interrupts)
+	 */
+	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
+		int vector = FIRST_EXTERNAL_VECTOR + i;
+		if (i >= NR_IRQS)
+			break;
+		/* SYSCALL_VECTOR was reserved in trap_init. */
+		if (!test_bit(vector, used_vectors))
+			set_intr_gate(vector, interrupt[i]);
+	}
+
+	/* setup after call gates are initialised (usually add in
+	 * the architecture specific gates)
+	 */
+	intr_init_hook();
+
+	/*
+	 * External FPU? Set up irq13 if so, for
+	 * original braindamaged IBM FERR coupling.
+	 */
+	if (boot_cpu_data.hard_math && !cpu_has_fpu)
+		setup_irq(FPU_IRQ, &fpu_irq);
+
+	irq_ctx_init(smp_processor_id());
+}

arch/x86/kernel/irqinit_64.c

@@ -0,0 +1,217 @@
+#include <linux/linkage.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+
+#include <asm/acpi.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/hw_irq.h>
+#include <asm/pgtable.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#include <asm/i8259.h>
+
+/*
+ * Common place to define all x86 IRQ vectors
+ *
+ * This builds up the IRQ handler stubs using some ugly macros in irq.h
+ *
+ * These macros create the low-level assembly IRQ routines that save
+ * register context and call do_IRQ(). do_IRQ() then does all the
+ * operations that are needed to keep the AT (or SMP IOAPIC)
+ * interrupt-controller happy.
+ */
+
+#define IRQ_NAME2(nr) nr##_interrupt(void)
+#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
+
+/*
+ *	SMP has a few special interrupts for IPI messages
+ */
+
+#define BUILD_IRQ(nr)				\
+	asmlinkage void IRQ_NAME(nr);		\
+	asm("\n.p2align\n"			\
+	    "IRQ" #nr "_interrupt:\n\t"		\
+	    "push $~(" #nr ") ; "		\
+	    "jmp common_interrupt");
+
+#define BI(x,y) \
+	BUILD_IRQ(x##y)
+
+#define BUILD_16_IRQS(x) \
+	BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
+	BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
+	BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
+	BI(x,c) BI(x,d) BI(x,e) BI(x,f)
+
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
+
+/*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
+				      BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
+BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
+BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
+BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
+
+#undef BUILD_16_IRQS
+#undef BI
+
+
+#define IRQ(x,y) \
+	IRQ##x##y##_interrupt
+
+#define IRQLIST_16(x) \
+	IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
+	IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
+	IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
+	IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
+
+/* for the irq vectors */
+static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
+					  IRQLIST_16(0x2), IRQLIST_16(0x3),
+	IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
+	IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
+	IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
+};
+
+#undef IRQ
+#undef IRQLIST_16
+
+
+
+
+/*
+ * IRQ2 is cascade interrupt to second interrupt controller
+ */
+
+static struct irqaction irq2 = {
+	.handler = no_action,
+	.mask = CPU_MASK_NONE,
+	.name = "cascade",
+};
+DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
+	[0 ... IRQ0_VECTOR - 1] = -1,
+	[IRQ0_VECTOR] = 0,
+	[IRQ1_VECTOR] = 1,
+	[IRQ2_VECTOR] = 2,
+	[IRQ3_VECTOR] = 3,
+	[IRQ4_VECTOR] = 4,
+	[IRQ5_VECTOR] = 5,
+	[IRQ6_VECTOR] = 6,
+	[IRQ7_VECTOR] = 7,
+	[IRQ8_VECTOR] = 8,
+	[IRQ9_VECTOR] = 9,
+	[IRQ10_VECTOR] = 10,
+	[IRQ11_VECTOR] = 11,
+	[IRQ12_VECTOR] = 12,
+	[IRQ13_VECTOR] = 13,
+	[IRQ14_VECTOR] = 14,
+	[IRQ15_VECTOR] = 15,
+	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
+};
+
+static void __init init_ISA_irqs (void)
+{
+	int i;
+
+	init_bsp_APIC();
+	init_8259A(0);
+
+	for (i = 0; i < NR_IRQS; i++) {
+		irq_desc[i].status = IRQ_DISABLED;
+		irq_desc[i].action = NULL;
+		irq_desc[i].depth = 1;
+
+		if (i < 16) {
+			/*
+			 * 16 old-style INTA-cycle interrupts:
+			 */
+			set_irq_chip_and_handler_name(i, &i8259A_chip,
+						      handle_level_irq, "XT");
+		} else {
+			/*
+			 * 'high' PCI IRQs filled in on demand
+			 */
+			irq_desc[i].chip = &no_irq_chip;
+		}
+	}
+}
+
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(void)
+{
+	int i;
+
+	init_ISA_irqs();
+	/*
+	 * Cover the whole vector space, no vector can escape
+	 * us. (some of these will be overridden and become
+	 * 'special' SMP interrupts)
+	 */
+	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
+		int vector = FIRST_EXTERNAL_VECTOR + i;
+		if (vector != IA32_SYSCALL_VECTOR)
+			set_intr_gate(vector, interrupt[i]);
+	}
+
+#ifdef CONFIG_SMP
+	/*
+	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
+	 * IPI, driven by wakeup.
+	 */
+	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+
+	/* IPIs for invalidation */
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
+
+	/* IPI for generic function call */
+	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+
+	/* Low priority IPI to cleanup after moving an irq */
+	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
+#endif
+	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+
+	/* self generated IPI for local APIC timer */
+	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+
+	/* IPI vectors for APIC spurious and error interrupts */
+	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+	if (!acpi_ioapic)
+		setup_irq(2, &irq2);
+}

arch/x86/kernel/ldt.c

@@ -20,9 +20,9 @@
 #include <asm/mmu_context.h>
 
 #ifdef CONFIG_SMP
-static void flush_ldt(void *null)
+static void flush_ldt(void *current_mm)
 {
-	if (current->active_mm)
+	if (current->active_mm == current_mm)
 		load_LDT(&current->active_mm->context);
 }
 #endif
@@ -68,7 +68,7 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 		load_LDT(pc);
 		mask = cpumask_of_cpu(smp_processor_id());
 		if (!cpus_equal(current->mm->cpu_vm_mask, mask))
-			smp_call_function(flush_ldt, NULL, 1, 1);
+			smp_call_function(flush_ldt, current->mm, 1, 1);
 		preempt_enable();
 #else
 		load_LDT(pc);

arch/x86/kernel/machine_kexec_32.c

@@ -39,7 +39,7 @@ static void set_idt(void *newidt, __u16 limit)
 	curidt.address = (unsigned long)newidt;
 
 	load_idt(&curidt);
-};
+}
 
 
 static void set_gdt(void *newgdt, __u16 limit)
@@ -51,7 +51,7 @@ static void set_gdt(void *newgdt, __u16 limit)
 	curgdt.address = (unsigned long)newgdt;
 
 	load_gdt(&curgdt);
-};
+}
 
 static void load_segments(void)
 {

arch/x86/kernel/machine_kexec_64.c

@@ -110,7 +110,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 {
 	pgd_t *level4p;
 	level4p = (pgd_t *)__va(start_pgtable);
- 	return init_level4_page(image, level4p, 0, end_pfn << PAGE_SHIFT);
+	return init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT);
 }
 
 static void set_idt(void *newidt, u16 limit)

arch/x86/kernel/microcode.c

@@ -5,13 +5,14 @@
  *		      2006	Shaohua Li <shaohua.li@intel.com>
  *
  *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II, 
+ *	belonging to IA-32 family - PentiumPro, Pentium II,
  *	Pentium III, Xeon, Pentium 4, etc.
  *
- *	Reference: Section 8.10 of Volume III, Intel Pentium 4 Manual, 
- *	Order Number 245472 or free download from:
- *		
- *	http://developer.intel.com/design/pentium4/manuals/245472.htm
+ *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
+ *	Software Developer's Manual
+ *	Order Number 253668 or free download from:
+ *
+ *	http://developer.intel.com/design/pentium4/manuals/253668.htm
  *
  *	For more information, go to http://www.urbanmyth.org/microcode
  *
@@ -58,12 +59,12 @@
  *		nature of implementation.
  *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
  *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, 
+ *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
  *		Jun Nakajima <jun.nakajima@intel.com>
  *		Support for the microcode updates in the new format.
  *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
  *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode 
+ *		because we no longer hold a copy of applied microcode
  *		in kernel memory.
  *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
@@ -320,11 +321,11 @@ static void apply_microcode(int cpu)
 		return;
 
 	/* serialize access to the physical write to MSR 0x79 */
-	spin_lock_irqsave(&microcode_update_lock, flags);          
+	spin_lock_irqsave(&microcode_update_lock, flags);
 
 	/* write microcode via MSR 0x79 */
 	wrmsr(MSR_IA32_UCODE_WRITE,
-		(unsigned long) uci->mc->bits, 
+		(unsigned long) uci->mc->bits,
 		(unsigned long) uci->mc->bits >> 16 >> 16);
 	wrmsr(MSR_IA32_UCODE_REV, 0, 0);
 
@@ -341,7 +342,7 @@ static void apply_microcode(int cpu)
 		return;
 	}
 	printk(KERN_INFO "microcode: CPU%d updated from revision "
-	       "0x%x to 0x%x, date = %08x \n", 
+	       "0x%x to 0x%x, date = %08x \n",
 	       cpu_num, uci->rev, val[1], uci->mc->hdr.date);
 	uci->rev = val[1];
 }
@@ -534,7 +535,7 @@ static int cpu_request_microcode(int cpu)
 		c->x86, c->x86_model, c->x86_mask);
 	error = request_firmware(&firmware, name, &microcode_pdev->dev);
 	if (error) {
-		pr_debug("microcode: ucode data file %s load failed\n", name);
+		pr_debug("microcode: data file %s load failed\n", name);
 		return error;
 	}
 	buf = firmware->data;
@@ -805,6 +806,9 @@ static int __init microcode_init (void)
 {
 	int error;
 
+	printk(KERN_INFO
+		"IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>\n");
+
 	error = microcode_dev_init();
 	if (error)
 		return error;
@@ -825,9 +829,6 @@ static int __init microcode_init (void)
 	}
 
 	register_hotcpu_notifier(&mc_cpu_notifier);
-
-	printk(KERN_INFO 
-		"IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>\n");
 	return 0;
 }
 

arch/x86/kernel/mmconf-fam10h_64.c

@@ -12,6 +12,7 @@
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/acpi.h>
+#include <asm/mmconfig.h>
 
 #include "../pci/pci.h"
 

arch/x86/kernel/mpparse.c

@@ -25,6 +25,8 @@
 #include <asm/proto.h>
 #include <asm/acpi.h>
 #include <asm/bios_ebda.h>
+#include <asm/e820.h>
+#include <asm/trampoline.h>
 
 #include <mach_apic.h>
 #ifdef CONFIG_X86_32
@@ -32,28 +34,6 @@
 #include <mach_mpparse.h>
 #endif
 
-/* Have we found an MP table */
-int smp_found_config;
-
-/*
- * Various Linux-internal data structures created from the
- * MP-table.
- */
-#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
-int mp_bus_id_to_type[MAX_MP_BUSSES];
-#endif
-
-DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
-int mp_bus_id_to_pci_bus[MAX_MP_BUSSES] = {[0 ... MAX_MP_BUSSES - 1] = -1 };
-
-static int mp_current_pci_id;
-
-int pic_mode;
-
-/*
- * Intel MP BIOS table parsing routines:
- */
-
 /*
  * Checksum an MP configuration block.
  */
@@ -69,15 +49,73 @@ static int __init mpf_checksum(unsigned char *mp, int len)
 }
 
 #ifdef CONFIG_X86_NUMAQ
+int found_numaq;
 /*
  * Have to match translation table entries to main table entries by counter
  * hence the mpc_record variable .... can't see a less disgusting way of
  * doing this ....
  */
+struct mpc_config_translation {
+	unsigned char mpc_type;
+	unsigned char trans_len;
+	unsigned char trans_type;
+	unsigned char trans_quad;
+	unsigned char trans_global;
+	unsigned char trans_local;
+	unsigned short trans_reserved;
+};
+
 
 static int mpc_record;
 static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY]
     __cpuinitdata;
+
+static inline int generate_logical_apicid(int quad, int phys_apicid)
+{
+	return (quad << 4) + (phys_apicid ? phys_apicid << 1 : 1);
+}
+
+
+static inline int mpc_apic_id(struct mpc_config_processor *m,
+			struct mpc_config_translation *translation_record)
+{
+	int quad = translation_record->trans_quad;
+	int logical_apicid = generate_logical_apicid(quad, m->mpc_apicid);
+
+	printk(KERN_DEBUG "Processor #%d %u:%u APIC version %d (quad %d, apic %d)\n",
+	       m->mpc_apicid,
+	       (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
+	       (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
+	       m->mpc_apicver, quad, logical_apicid);
+	return logical_apicid;
+}
+
+int mp_bus_id_to_node[MAX_MP_BUSSES];
+
+int mp_bus_id_to_local[MAX_MP_BUSSES];
+
+static void mpc_oem_bus_info(struct mpc_config_bus *m, char *name,
+	struct mpc_config_translation *translation)
+{
+	int quad = translation->trans_quad;
+	int local = translation->trans_local;
+
+	mp_bus_id_to_node[m->mpc_busid] = quad;
+	mp_bus_id_to_local[m->mpc_busid] = local;
+	printk(KERN_INFO "Bus #%d is %s (node %d)\n",
+	       m->mpc_busid, name, quad);
+}
+
+int quad_local_to_mp_bus_id [NR_CPUS/4][4];
+static void mpc_oem_pci_bus(struct mpc_config_bus *m,
+	struct mpc_config_translation *translation)
+{
+	int quad = translation->trans_quad;
+	int local = translation->trans_local;
+
+	quad_local_to_mp_bus_id[quad][local] = m->mpc_busid;
+}
+
 #endif
 
 static void __cpuinit MP_processor_info(struct mpc_config_processor *m)
@@ -90,7 +128,10 @@ static void __cpuinit MP_processor_info(struct mpc_config_processor *m)
 		return;
 	}
 #ifdef CONFIG_X86_NUMAQ
-	apicid = mpc_apic_id(m, translation_table[mpc_record]);
+	if (found_numaq)
+		apicid = mpc_apic_id(m, translation_table[mpc_record]);
+	else
+		apicid = m->mpc_apicid;
 #else
 	apicid = m->mpc_apicid;
 #endif
@@ -103,17 +144,18 @@ static void __cpuinit MP_processor_info(struct mpc_config_processor *m)
 	generic_processor_info(apicid, m->mpc_apicver);
 }
 
+#ifdef CONFIG_X86_IO_APIC
 static void __init MP_bus_info(struct mpc_config_bus *m)
 {
 	char str[7];
-
 	memcpy(str, m->mpc_bustype, 6);
 	str[6] = 0;
 
 #ifdef CONFIG_X86_NUMAQ
-	mpc_oem_bus_info(m, str, translation_table[mpc_record]);
+	if (found_numaq)
+		mpc_oem_bus_info(m, str, translation_table[mpc_record]);
 #else
-	Dprintk("Bus #%d is %s\n", m->mpc_busid, str);
+	printk(KERN_INFO "Bus #%d is %s\n", m->mpc_busid, str);
 #endif
 
 #if MAX_MP_BUSSES < 256
@@ -132,11 +174,10 @@ static void __init MP_bus_info(struct mpc_config_bus *m)
 #endif
 	} else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) {
 #ifdef CONFIG_X86_NUMAQ
-		mpc_oem_pci_bus(m, translation_table[mpc_record]);
+		if (found_numaq)
+			mpc_oem_pci_bus(m, translation_table[mpc_record]);
 #endif
 		clear_bit(m->mpc_busid, mp_bus_not_pci);
-		mp_bus_id_to_pci_bus[m->mpc_busid] = mp_current_pci_id;
-		mp_current_pci_id++;
 #if defined(CONFIG_EISA) || defined (CONFIG_MCA)
 		mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI;
 	} else if (strncmp(str, BUSTYPE_EISA, sizeof(BUSTYPE_EISA) - 1) == 0) {
@@ -147,6 +188,7 @@ static void __init MP_bus_info(struct mpc_config_bus *m)
 	} else
 		printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str);
 }
+#endif
 
 #ifdef CONFIG_X86_IO_APIC
 
@@ -176,18 +218,89 @@ static void __init MP_ioapic_info(struct mpc_config_ioapic *m)
 	if (bad_ioapic(m->mpc_apicaddr))
 		return;
 
-	mp_ioapics[nr_ioapics] = *m;
+	mp_ioapics[nr_ioapics].mp_apicaddr = m->mpc_apicaddr;
+	mp_ioapics[nr_ioapics].mp_apicid = m->mpc_apicid;
+	mp_ioapics[nr_ioapics].mp_type = m->mpc_type;
+	mp_ioapics[nr_ioapics].mp_apicver = m->mpc_apicver;
+	mp_ioapics[nr_ioapics].mp_flags = m->mpc_flags;
 	nr_ioapics++;
 }
 
-static void __init MP_intsrc_info(struct mpc_config_intsrc *m)
+static void print_MP_intsrc_info(struct mpc_config_intsrc *m)
 {
-	mp_irqs[mp_irq_entries] = *m;
-	Dprintk("Int: type %d, pol %d, trig %d, bus %d,"
+	printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x,"
 		" IRQ %02x, APIC ID %x, APIC INT %02x\n",
 		m->mpc_irqtype, m->mpc_irqflag & 3,
 		(m->mpc_irqflag >> 2) & 3, m->mpc_srcbus,
 		m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq);
+}
+
+static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq)
+{
+	printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x,"
+		" IRQ %02x, APIC ID %x, APIC INT %02x\n",
+		mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3,
+		(mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus,
+		mp_irq->mp_srcbusirq, mp_irq->mp_dstapic, mp_irq->mp_dstirq);
+}
+
+static void __init assign_to_mp_irq(struct mpc_config_intsrc *m,
+				    struct mp_config_intsrc *mp_irq)
+{
+	mp_irq->mp_dstapic = m->mpc_dstapic;
+	mp_irq->mp_type = m->mpc_type;
+	mp_irq->mp_irqtype = m->mpc_irqtype;
+	mp_irq->mp_irqflag = m->mpc_irqflag;
+	mp_irq->mp_srcbus = m->mpc_srcbus;
+	mp_irq->mp_srcbusirq = m->mpc_srcbusirq;
+	mp_irq->mp_dstirq = m->mpc_dstirq;
+}
+
+static void __init assign_to_mpc_intsrc(struct mp_config_intsrc *mp_irq,
+					struct mpc_config_intsrc *m)
+{
+	m->mpc_dstapic = mp_irq->mp_dstapic;
+	m->mpc_type = mp_irq->mp_type;
+	m->mpc_irqtype = mp_irq->mp_irqtype;
+	m->mpc_irqflag = mp_irq->mp_irqflag;
+	m->mpc_srcbus = mp_irq->mp_srcbus;
+	m->mpc_srcbusirq = mp_irq->mp_srcbusirq;
+	m->mpc_dstirq = mp_irq->mp_dstirq;
+}
+
+static int __init mp_irq_mpc_intsrc_cmp(struct mp_config_intsrc *mp_irq,
+					struct mpc_config_intsrc *m)
+{
+	if (mp_irq->mp_dstapic != m->mpc_dstapic)
+		return 1;
+	if (mp_irq->mp_type != m->mpc_type)
+		return 2;
+	if (mp_irq->mp_irqtype != m->mpc_irqtype)
+		return 3;
+	if (mp_irq->mp_irqflag != m->mpc_irqflag)
+		return 4;
+	if (mp_irq->mp_srcbus != m->mpc_srcbus)
+		return 5;
+	if (mp_irq->mp_srcbusirq != m->mpc_srcbusirq)
+		return 6;
+	if (mp_irq->mp_dstirq != m->mpc_dstirq)
+		return 7;
+
+	return 0;
+}
+
+static void __init MP_intsrc_info(struct mpc_config_intsrc *m)
+{
+	int i;
+
+	print_MP_intsrc_info(m);
+
+	for (i = 0; i < mp_irq_entries; i++) {
+		if (!mp_irq_mpc_intsrc_cmp(&mp_irqs[i], m))
+			return;
+	}
+
+	assign_to_mp_irq(m, &mp_irqs[mp_irq_entries]);
 	if (++mp_irq_entries == MAX_IRQ_SOURCES)
 		panic("Max # of irq sources exceeded!!\n");
 }
@@ -196,7 +309,7 @@ static void __init MP_intsrc_info(struct mpc_config_intsrc *m)
 
 static void __init MP_lintsrc_info(struct mpc_config_lintsrc *m)
 {
-	Dprintk("Lint: type %d, pol %d, trig %d, bus %d,"
+	printk(KERN_INFO "Lint: type %d, pol %d, trig %d, bus %02x,"
 		" IRQ %02x, APIC ID %x, APIC LINT %02x\n",
 		m->mpc_irqtype, m->mpc_irqflag & 3,
 		(m->mpc_irqflag >> 2) & 3, m->mpc_srcbusid,
@@ -266,11 +379,14 @@ static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable,
 	}
 }
 
-static inline void mps_oem_check(struct mp_config_table *mpc, char *oem,
+void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
 				 char *productid)
 {
 	if (strncmp(oem, "IBM NUMA", 8))
-		printk("Warning!  May not be a NUMA-Q system!\n");
+		printk("Warning!  Not a NUMA-Q system!\n");
+	else
+		found_numaq = 1;
+
 	if (mpc->mpc_oemptr)
 		smp_read_mpc_oem((struct mp_config_oemtable *)mpc->mpc_oemptr,
 				 mpc->mpc_oemsize);
@@ -281,12 +397,9 @@ static inline void mps_oem_check(struct mp_config_table *mpc, char *oem,
  * Read/parse the MPC
  */
 
-static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
+static int __init smp_check_mpc(struct mp_config_table *mpc, char *oem,
+				char *str)
 {
-	char str[16];
-	char oem[10];
-	int count = sizeof(*mpc);
-	unsigned char *mpt = ((unsigned char *)mpc) + count;
 
 	if (memcmp(mpc->mpc_signature, MPC_SIGNATURE, 4)) {
 		printk(KERN_ERR "MPTABLE: bad signature [%c%c%c%c]!\n",
@@ -309,19 +422,42 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
 	}
 	memcpy(oem, mpc->mpc_oem, 8);
 	oem[8] = 0;
-	printk(KERN_INFO "MPTABLE: OEM ID: %s ", oem);
+	printk(KERN_INFO "MPTABLE: OEM ID: %s\n", oem);
 
 	memcpy(str, mpc->mpc_productid, 12);
 	str[12] = 0;
-	printk("Product ID: %s ", str);
 
-#ifdef CONFIG_X86_32
-	mps_oem_check(mpc, oem, str);
-#endif
-	printk(KERN_INFO "MPTABLE: Product ID: %s ", str);
+	printk(KERN_INFO "MPTABLE: Product ID: %s\n", str);
 
 	printk(KERN_INFO "MPTABLE: APIC at: 0x%X\n", mpc->mpc_lapic);
 
+	return 1;
+}
+
+static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
+{
+	char str[16];
+	char oem[10];
+
+	int count = sizeof(*mpc);
+	unsigned char *mpt = ((unsigned char *)mpc) + count;
+
+	if (!smp_check_mpc(mpc, oem, str))
+		return 0;
+
+#ifdef CONFIG_X86_32
+	/*
+	 * need to make sure summit and es7000's mps_oem_check is safe to be
+	 * called early via genericarch 's mps_oem_check
+	 */
+	if (early) {
+#ifdef CONFIG_X86_NUMAQ
+		numaq_mps_oem_check(mpc, oem, str);
+#endif
+	} else
+		mps_oem_check(mpc, oem, str);
+#endif
+
 	/* save the local APIC address, it might be non-default */
 	if (!acpi_lapic)
 		mp_lapic_addr = mpc->mpc_lapic;
@@ -352,7 +488,9 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
 			{
 				struct mpc_config_bus *m =
 				    (struct mpc_config_bus *)mpt;
+#ifdef CONFIG_X86_IO_APIC
 				MP_bus_info(m);
+#endif
 				mpt += sizeof(*m);
 				count += sizeof(*m);
 				break;
@@ -402,6 +540,11 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
 		++mpc_record;
 #endif
 	}
+
+#ifdef CONFIG_X86_GENERICARCH
+       generic_bigsmp_probe();
+#endif
+
 	setup_apic_routing();
 	if (!num_processors)
 		printk(KERN_ERR "MPTABLE: no processors registered!\n");
@@ -427,7 +570,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 	intsrc.mpc_type = MP_INTSRC;
 	intsrc.mpc_irqflag = 0;	/* conforming */
 	intsrc.mpc_srcbus = 0;
-	intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid;
+	intsrc.mpc_dstapic = mp_ioapics[0].mp_apicid;
 
 	intsrc.mpc_irqtype = mp_INT;
 
@@ -488,40 +631,11 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 	MP_intsrc_info(&intsrc);
 }
 
-#endif
 
-static inline void __init construct_default_ISA_mptable(int mpc_default_type)
+static void construct_ioapic_table(int mpc_default_type)
 {
-	struct mpc_config_processor processor;
-	struct mpc_config_bus bus;
-#ifdef CONFIG_X86_IO_APIC
 	struct mpc_config_ioapic ioapic;
-#endif
-	struct mpc_config_lintsrc lintsrc;
-	int linttypes[2] = { mp_ExtINT, mp_NMI };
-	int i;
-
-	/*
-	 * local APIC has default address
-	 */
-	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-
-	/*
-	 * 2 CPUs, numbered 0 & 1.
-	 */
-	processor.mpc_type = MP_PROCESSOR;
-	/* Either an integrated APIC or a discrete 82489DX. */
-	processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01;
-	processor.mpc_cpuflag = CPU_ENABLED;
-	processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) |
-	    (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask;
-	processor.mpc_featureflag = boot_cpu_data.x86_capability[0];
-	processor.mpc_reserved[0] = 0;
-	processor.mpc_reserved[1] = 0;
-	for (i = 0; i < 2; i++) {
-		processor.mpc_apicid = i;
-		MP_processor_info(&processor);
-	}
+	struct mpc_config_bus bus;
 
 	bus.mpc_type = MP_BUS;
 	bus.mpc_busid = 0;
@@ -550,7 +664,6 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 		MP_bus_info(&bus);
 	}
 
-#ifdef CONFIG_X86_IO_APIC
 	ioapic.mpc_type = MP_IOAPIC;
 	ioapic.mpc_apicid = 2;
 	ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01;
@@ -562,7 +675,42 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 	 * We set up most of the low 16 IO-APIC pins according to MPS rules.
 	 */
 	construct_default_ioirq_mptable(mpc_default_type);
+}
+#else
+static inline void construct_ioapic_table(int mpc_default_type) { }
 #endif
+
+static inline void __init construct_default_ISA_mptable(int mpc_default_type)
+{
+	struct mpc_config_processor processor;
+	struct mpc_config_lintsrc lintsrc;
+	int linttypes[2] = { mp_ExtINT, mp_NMI };
+	int i;
+
+	/*
+	 * local APIC has default address
+	 */
+	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
+
+	/*
+	 * 2 CPUs, numbered 0 & 1.
+	 */
+	processor.mpc_type = MP_PROCESSOR;
+	/* Either an integrated APIC or a discrete 82489DX. */
+	processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01;
+	processor.mpc_cpuflag = CPU_ENABLED;
+	processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) |
+	    (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask;
+	processor.mpc_featureflag = boot_cpu_data.x86_capability[0];
+	processor.mpc_reserved[0] = 0;
+	processor.mpc_reserved[1] = 0;
+	for (i = 0; i < 2; i++) {
+		processor.mpc_apicid = i;
+		MP_processor_info(&processor);
+	}
+
+	construct_ioapic_table(mpc_default_type);
+
 	lintsrc.mpc_type = MP_LINTSRC;
 	lintsrc.mpc_irqflag = 0;	/* conforming */
 	lintsrc.mpc_srcbusid = 0;
@@ -577,13 +725,23 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 
 static struct intel_mp_floating *mpf_found;
 
+/*
+ * Machine specific quirk for finding the SMP config before other setup
+ * activities destroy the table:
+ */
+int (*mach_get_smp_config_quirk)(unsigned int early);
+
 /*
  * Scan the memory blocks for an SMP configuration block.
  */
-static void __init __get_smp_config(unsigned early)
+static void __init __get_smp_config(unsigned int early)
 {
 	struct intel_mp_floating *mpf = mpf_found;
 
+	if (mach_get_smp_config_quirk) {
+		if (mach_get_smp_config_quirk(early))
+			return;
+	}
 	if (acpi_lapic && early)
 		return;
 	/*
@@ -600,7 +758,7 @@ static void __init __get_smp_config(unsigned early)
 
 	printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
 	       mpf->mpf_specification);
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
 	if (mpf->mpf_feature2 & (1 << 7)) {
 		printk(KERN_INFO "    IMCR and PIC compatibility mode.\n");
 		pic_mode = 1;
@@ -632,7 +790,9 @@ static void __init __get_smp_config(unsigned early)
 		 * override the defaults.
 		 */
 		if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr), early)) {
+#ifdef CONFIG_X86_LOCAL_APIC
 			smp_found_config = 0;
+#endif
 			printk(KERN_ERR
 			       "BIOS bug, MP table errors detected!...\n");
 			printk(KERN_ERR "... disabling SMP support. "
@@ -689,7 +849,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 	unsigned int *bp = phys_to_virt(base);
 	struct intel_mp_floating *mpf;
 
-	Dprintk("Scan SMP from %p for %ld bytes.\n", bp, length);
+	printk(KERN_DEBUG "Scan SMP from %p for %ld bytes.\n", bp, length);
 	BUILD_BUG_ON(sizeof(*mpf) != 16);
 
 	while (length > 0) {
@@ -699,15 +859,21 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 		    !mpf_checksum((unsigned char *)bp, 16) &&
 		    ((mpf->mpf_specification == 1)
 		     || (mpf->mpf_specification == 4))) {
-
+#ifdef CONFIG_X86_LOCAL_APIC
 			smp_found_config = 1;
+#endif
 			mpf_found = mpf;
-#ifdef CONFIG_X86_32
+
 			printk(KERN_INFO "found SMP MP-table at [%p] %08lx\n",
 			       mpf, virt_to_phys(mpf));
-			reserve_bootmem(virt_to_phys(mpf), PAGE_SIZE,
+
+			if (!reserve)
+				return 1;
+			reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE,
 					BOOTMEM_DEFAULT);
 			if (mpf->mpf_physptr) {
+				unsigned long size = PAGE_SIZE;
+#ifdef CONFIG_X86_32
 				/*
 				 * We cannot access to MPC table to compute
 				 * table size yet, as only few megabytes from
@@ -717,24 +883,15 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 				 * PAGE_SIZE from mpg->mpf_physptr yields BUG()
 				 * in reserve_bootmem.
 				 */
-				unsigned long size = PAGE_SIZE;
 				unsigned long end = max_low_pfn * PAGE_SIZE;
 				if (mpf->mpf_physptr + size > end)
 					size = end - mpf->mpf_physptr;
-				reserve_bootmem(mpf->mpf_physptr, size,
+#endif
+				reserve_bootmem_generic(mpf->mpf_physptr, size,
 						BOOTMEM_DEFAULT);
 			}
 
-#else
-			if (!reserve)
-				return 1;
-
-			reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE);
-			if (mpf->mpf_physptr)
-				reserve_bootmem_generic(mpf->mpf_physptr,
-							PAGE_SIZE);
-#endif
-		return 1;
+			return 1;
 		}
 		bp += 4;
 		length -= 16;
@@ -742,10 +899,16 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 	return 0;
 }
 
-static void __init __find_smp_config(unsigned reserve)
+int (*mach_find_smp_config_quirk)(unsigned int reserve);
+
+static void __init __find_smp_config(unsigned int reserve)
 {
 	unsigned int address;
 
+	if (mach_find_smp_config_quirk) {
+		if (mach_find_smp_config_quirk(reserve))
+			return;
+	}
 	/*
 	 * FIXME: Linux assumes you have 640K of base ram..
 	 * this continues the error...
@@ -790,298 +953,294 @@ void __init find_smp_config(void)
 	__find_smp_config(1);
 }
 
-/* --------------------------------------------------------------------------
-                            ACPI-based MP Configuration
-   -------------------------------------------------------------------------- */
+#ifdef CONFIG_X86_IO_APIC
+static u8 __initdata irq_used[MAX_IRQ_SOURCES];
 
-/*
- * Keep this outside and initialized to 0, for !CONFIG_ACPI builds:
- */
-int es7000_plat;
+static int  __init get_MP_intsrc_index(struct mpc_config_intsrc *m)
+{
+	int i;
 
-#ifdef CONFIG_ACPI
+	if (m->mpc_irqtype != mp_INT)
+		return 0;
 
-#ifdef	CONFIG_X86_IO_APIC
+	if (m->mpc_irqflag != 0x0f)
+		return 0;
 
-#define MP_ISA_BUS		0
+	/* not legacy */
 
-extern struct mp_ioapic_routing mp_ioapic_routing[MAX_IO_APICS];
+	for (i = 0; i < mp_irq_entries; i++) {
+		if (mp_irqs[i].mp_irqtype != mp_INT)
+			continue;
 
-static int mp_find_ioapic(int gsi)
-{
-	int i = 0;
+		if (mp_irqs[i].mp_irqflag != 0x0f)
+			continue;
 
-	/* Find the IOAPIC that manages this GSI. */
-	for (i = 0; i < nr_ioapics; i++) {
-		if ((gsi >= mp_ioapic_routing[i].gsi_base)
-		    && (gsi <= mp_ioapic_routing[i].gsi_end))
-			return i;
+		if (mp_irqs[i].mp_srcbus != m->mpc_srcbus)
+			continue;
+		if (mp_irqs[i].mp_srcbusirq != m->mpc_srcbusirq)
+			continue;
+		if (irq_used[i]) {
+			/* already claimed */
+			return -2;
+		}
+		irq_used[i] = 1;
+		return i;
 	}
 
-	printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi);
+	/* not found */
 	return -1;
 }
 
-static u8 __init uniq_ioapic_id(u8 id)
-{
-#ifdef CONFIG_X86_32
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
-	    !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
-		return io_apic_get_unique_id(nr_ioapics, id);
-	else
-		return id;
-#else
-	int i;
-	DECLARE_BITMAP(used, 256);
-	bitmap_zero(used, 256);
-	for (i = 0; i < nr_ioapics; i++) {
-		struct mpc_config_ioapic *ia = &mp_ioapics[i];
-		__set_bit(ia->mpc_apicid, used);
-	}
-	if (!test_bit(id, used))
-		return id;
-	return find_first_zero_bit(used, 256);
+#define SPARE_SLOT_NUM 20
+
+static struct mpc_config_intsrc __initdata *m_spare[SPARE_SLOT_NUM];
 #endif
-}
 
-void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
+static int  __init replace_intsrc_all(struct mp_config_table *mpc,
+					unsigned long mpc_new_phys,
+					unsigned long mpc_new_length)
 {
-	int idx = 0;
-
-	if (bad_ioapic(address))
-		return;
+#ifdef CONFIG_X86_IO_APIC
+	int i;
+	int nr_m_spare = 0;
+#endif
 
-	idx = nr_ioapics;
+	int count = sizeof(*mpc);
+	unsigned char *mpt = ((unsigned char *)mpc) + count;
 
-	mp_ioapics[idx].mpc_type = MP_IOAPIC;
-	mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE;
-	mp_ioapics[idx].mpc_apicaddr = address;
+	printk(KERN_INFO "mpc_length %x\n", mpc->mpc_length);
+	while (count < mpc->mpc_length) {
+		switch (*mpt) {
+		case MP_PROCESSOR:
+			{
+				struct mpc_config_processor *m =
+				    (struct mpc_config_processor *)mpt;
+				mpt += sizeof(*m);
+				count += sizeof(*m);
+				break;
+			}
+		case MP_BUS:
+			{
+				struct mpc_config_bus *m =
+				    (struct mpc_config_bus *)mpt;
+				mpt += sizeof(*m);
+				count += sizeof(*m);
+				break;
+			}
+		case MP_IOAPIC:
+			{
+				mpt += sizeof(struct mpc_config_ioapic);
+				count += sizeof(struct mpc_config_ioapic);
+				break;
+			}
+		case MP_INTSRC:
+			{
+#ifdef CONFIG_X86_IO_APIC
+				struct mpc_config_intsrc *m =
+				    (struct mpc_config_intsrc *)mpt;
 
-	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
-	mp_ioapics[idx].mpc_apicid = uniq_ioapic_id(id);
-#ifdef CONFIG_X86_32
-	mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx);
-#else
-	mp_ioapics[idx].mpc_apicver = 0;
+				printk(KERN_INFO "OLD ");
+				print_MP_intsrc_info(m);
+				i = get_MP_intsrc_index(m);
+				if (i > 0) {
+					assign_to_mpc_intsrc(&mp_irqs[i], m);
+					printk(KERN_INFO "NEW ");
+					print_mp_irq_info(&mp_irqs[i]);
+				} else if (!i) {
+					/* legacy, do nothing */
+				} else if (nr_m_spare < SPARE_SLOT_NUM) {
+					/*
+					 * not found (-1), or duplicated (-2)
+					 * are invalid entries,
+					 * we need to use the slot  later
+					 */
+					m_spare[nr_m_spare] = m;
+					nr_m_spare++;
+				}
 #endif
-	/*
-	 * Build basic GSI lookup table to facilitate gsi->io_apic lookups
-	 * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
-	 */
-	mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid;
-	mp_ioapic_routing[idx].gsi_base = gsi_base;
-	mp_ioapic_routing[idx].gsi_end = gsi_base +
-	    io_apic_get_redir_entries(idx);
-
-	printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
-	       "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid,
-	       mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr,
-	       mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end);
-
-	nr_ioapics++;
-}
+				mpt += sizeof(struct mpc_config_intsrc);
+				count += sizeof(struct mpc_config_intsrc);
+				break;
+			}
+		case MP_LINTSRC:
+			{
+				struct mpc_config_lintsrc *m =
+				    (struct mpc_config_lintsrc *)mpt;
+				mpt += sizeof(*m);
+				count += sizeof(*m);
+				break;
+			}
+		default:
+			/* wrong mptable */
+			printk(KERN_ERR "Your mptable is wrong, contact your HW vendor!\n");
+			printk(KERN_ERR "type %x\n", *mpt);
+			print_hex_dump(KERN_ERR, "  ", DUMP_PREFIX_ADDRESS, 16,
+					1, mpc, mpc->mpc_length, 1);
+			goto out;
+		}
+	}
 
-void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
-{
-	struct mpc_config_intsrc intsrc;
-	int ioapic = -1;
-	int pin = -1;
+#ifdef CONFIG_X86_IO_APIC
+	for (i = 0; i < mp_irq_entries; i++) {
+		if (irq_used[i])
+			continue;
 
-	/*
-	 * Convert 'gsi' to 'ioapic.pin'.
-	 */
-	ioapic = mp_find_ioapic(gsi);
-	if (ioapic < 0)
-		return;
-	pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+		if (mp_irqs[i].mp_irqtype != mp_INT)
+			continue;
 
-	/*
-	 * TBD: This check is for faulty timer entries, where the override
-	 *      erroneously sets the trigger to level, resulting in a HUGE
-	 *      increase of timer interrupts!
-	 */
-	if ((bus_irq == 0) && (trigger == 3))
-		trigger = 1;
+		if (mp_irqs[i].mp_irqflag != 0x0f)
+			continue;
 
-	intsrc.mpc_type = MP_INTSRC;
-	intsrc.mpc_irqtype = mp_INT;
-	intsrc.mpc_irqflag = (trigger << 2) | polarity;
-	intsrc.mpc_srcbus = MP_ISA_BUS;
-	intsrc.mpc_srcbusirq = bus_irq;	/* IRQ */
-	intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid;	/* APIC ID */
-	intsrc.mpc_dstirq = pin;	/* INTIN# */
+		if (nr_m_spare > 0) {
+			printk(KERN_INFO "*NEW* found ");
+			nr_m_spare--;
+			assign_to_mpc_intsrc(&mp_irqs[i], m_spare[nr_m_spare]);
+			m_spare[nr_m_spare] = NULL;
+		} else {
+			struct mpc_config_intsrc *m =
+			    (struct mpc_config_intsrc *)mpt;
+			count += sizeof(struct mpc_config_intsrc);
+			if (!mpc_new_phys) {
+				printk(KERN_INFO "No spare slots, try to append...take your risk, new mpc_length %x\n", count);
+			} else {
+				if (count <= mpc_new_length)
+					printk(KERN_INFO "No spare slots, try to append..., new mpc_length %x\n", count);
+				else {
+					printk(KERN_ERR "mpc_new_length %lx is too small\n", mpc_new_length);
+					goto out;
+				}
+			}
+			assign_to_mpc_intsrc(&mp_irqs[i], m);
+			mpc->mpc_length = count;
+			mpt += sizeof(struct mpc_config_intsrc);
+		}
+		print_mp_irq_info(&mp_irqs[i]);
+	}
+#endif
+out:
+	/* update checksum */
+	mpc->mpc_checksum = 0;
+	mpc->mpc_checksum -= mpf_checksum((unsigned char *)mpc,
+					   mpc->mpc_length);
 
-	MP_intsrc_info(&intsrc);
+	return 0;
 }
 
-void __init mp_config_acpi_legacy_irqs(void)
-{
-	struct mpc_config_intsrc intsrc;
-	int i = 0;
-	int ioapic = -1;
+static int __initdata enable_update_mptable;
 
-#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
-	/*
-	 * Fabricate the legacy ISA bus (bus #31).
-	 */
-	mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA;
-#endif
-	set_bit(MP_ISA_BUS, mp_bus_not_pci);
-	Dprintk("Bus #%d is ISA\n", MP_ISA_BUS);
+static int __init update_mptable_setup(char *str)
+{
+	enable_update_mptable = 1;
+	return 0;
+}
+early_param("update_mptable", update_mptable_setup);
 
-	/*
-	 * Older generations of ES7000 have no legacy identity mappings
-	 */
-	if (es7000_plat == 1)
-		return;
+static unsigned long __initdata mpc_new_phys;
+static unsigned long mpc_new_length __initdata = 4096;
 
-	/*
-	 * Locate the IOAPIC that manages the ISA IRQs (0-15).
-	 */
-	ioapic = mp_find_ioapic(0);
-	if (ioapic < 0)
-		return;
+/* alloc_mptable or alloc_mptable=4k */
+static int __initdata alloc_mptable;
+static int __init parse_alloc_mptable_opt(char *p)
+{
+	enable_update_mptable = 1;
+	alloc_mptable = 1;
+	if (!p)
+		return 0;
+	mpc_new_length = memparse(p, &p);
+	return 0;
+}
+early_param("alloc_mptable", parse_alloc_mptable_opt);
 
-	intsrc.mpc_type = MP_INTSRC;
-	intsrc.mpc_irqflag = 0;	/* Conforming */
-	intsrc.mpc_srcbus = MP_ISA_BUS;
-#ifdef CONFIG_X86_IO_APIC
-	intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid;
+void __init early_reserve_e820_mpc_new(void)
+{
+	if (enable_update_mptable && alloc_mptable) {
+		u64 startt = 0;
+#ifdef CONFIG_X86_TRAMPOLINE
+		startt = TRAMPOLINE_BASE;
 #endif
-	/*
-	 * Use the default configuration for the IRQs 0-15.  Unless
-	 * overridden by (MADT) interrupt source override entries.
-	 */
-	for (i = 0; i < 16; i++) {
-		int idx;
-
-		for (idx = 0; idx < mp_irq_entries; idx++) {
-			struct mpc_config_intsrc *irq = mp_irqs + idx;
-
-			/* Do we already have a mapping for this ISA IRQ? */
-			if (irq->mpc_srcbus == MP_ISA_BUS
-			    && irq->mpc_srcbusirq == i)
-				break;
-
-			/* Do we already have a mapping for this IOAPIC pin */
-			if ((irq->mpc_dstapic == intsrc.mpc_dstapic) &&
-			    (irq->mpc_dstirq == i))
-				break;
-		}
-
-		if (idx != mp_irq_entries) {
-			printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i);
-			continue;	/* IRQ already used */
-		}
-
-		intsrc.mpc_irqtype = mp_INT;
-		intsrc.mpc_srcbusirq = i;	/* Identity mapped */
-		intsrc.mpc_dstirq = i;
-
-		MP_intsrc_info(&intsrc);
+		mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4);
 	}
 }
 
-int mp_register_gsi(u32 gsi, int triggering, int polarity)
+static int __init update_mp_table(void)
 {
-	int ioapic;
-	int ioapic_pin;
-#ifdef CONFIG_X86_32
-#define MAX_GSI_NUM	4096
-#define IRQ_COMPRESSION_START	64
+	char str[16];
+	char oem[10];
+	struct intel_mp_floating *mpf;
+	struct mp_config_table *mpc;
+	struct mp_config_table *mpc_new;
+
+	if (!enable_update_mptable)
+		return 0;
+
+	mpf = mpf_found;
+	if (!mpf)
+		return 0;
 
-	static int pci_irq = IRQ_COMPRESSION_START;
 	/*
-	 * Mapping between Global System Interrupts, which
-	 * represent all possible interrupts, and IRQs
-	 * assigned to actual devices.
+	 * Now see if we need to go further.
 	 */
-	static int gsi_to_irq[MAX_GSI_NUM];
-#else
-
-	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
-		return gsi;
-#endif
+	if (mpf->mpf_feature1 != 0)
+		return 0;
 
-	/* Don't set up the ACPI SCI because it's already set up */
-	if (acpi_gbl_FADT.sci_interrupt == gsi)
-		return gsi;
+	if (!mpf->mpf_physptr)
+		return 0;
 
-	ioapic = mp_find_ioapic(gsi);
-	if (ioapic < 0) {
-		printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi);
-		return gsi;
-	}
+	mpc = phys_to_virt(mpf->mpf_physptr);
 
-	ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+	if (!smp_check_mpc(mpc, oem, str))
+		return 0;
 
-#ifdef CONFIG_X86_32
-	if (ioapic_renumber_irq)
-		gsi = ioapic_renumber_irq(ioapic, gsi);
-#endif
+	printk(KERN_INFO "mpf: %lx\n", virt_to_phys(mpf));
+	printk(KERN_INFO "mpf_physptr: %x\n", mpf->mpf_physptr);
 
-	/*
-	 * Avoid pin reprogramming.  PRTs typically include entries
-	 * with redundant pin->gsi mappings (but unique PCI devices);
-	 * we only program the IOAPIC on the first.
-	 */
-	if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
-		printk(KERN_ERR "Invalid reference to IOAPIC pin "
-		       "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
-		       ioapic_pin);
-		return gsi;
+	if (mpc_new_phys && mpc->mpc_length > mpc_new_length) {
+		mpc_new_phys = 0;
+		printk(KERN_INFO "mpc_new_length is %ld, please use alloc_mptable=8k\n",
+			 mpc_new_length);
 	}
-	if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
-		Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
-			mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
-#ifdef CONFIG_X86_32
-		return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]);
-#else
-		return gsi;
-#endif
+
+	if (!mpc_new_phys) {
+		unsigned char old, new;
+		/* check if we can change the postion */
+		mpc->mpc_checksum = 0;
+		old = mpf_checksum((unsigned char *)mpc, mpc->mpc_length);
+		mpc->mpc_checksum = 0xff;
+		new = mpf_checksum((unsigned char *)mpc, mpc->mpc_length);
+		if (old == new) {
+			printk(KERN_INFO "mpc is readonly, please try alloc_mptable instead\n");
+			return 0;
+		}
+		printk(KERN_INFO "use in-positon replacing\n");
+	} else {
+		mpf->mpf_physptr = mpc_new_phys;
+		mpc_new = phys_to_virt(mpc_new_phys);
+		memcpy(mpc_new, mpc, mpc->mpc_length);
+		mpc = mpc_new;
+		/* check if we can modify that */
+		if (mpc_new_phys - mpf->mpf_physptr) {
+			struct intel_mp_floating *mpf_new;
+			/* steal 16 bytes from [0, 1k) */
+			printk(KERN_INFO "mpf new: %x\n", 0x400 - 16);
+			mpf_new = phys_to_virt(0x400 - 16);
+			memcpy(mpf_new, mpf, 16);
+			mpf = mpf_new;
+			mpf->mpf_physptr = mpc_new_phys;
+		}
+		mpf->mpf_checksum = 0;
+		mpf->mpf_checksum -= mpf_checksum((unsigned char *)mpf, 16);
+		printk(KERN_INFO "mpf_physptr new: %x\n", mpf->mpf_physptr);
 	}
 
-	set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
-#ifdef CONFIG_X86_32
 	/*
-	 * For GSI >= 64, use IRQ compression
+	 * only replace the one with mp_INT and
+	 *	 MP_IRQ_TRIGGER_LEVEL|MP_IRQ_POLARITY_LOW,
+	 * already in mp_irqs , stored by ... and mp_config_acpi_gsi,
+	 * may need pci=routeirq for all coverage
 	 */
-	if ((gsi >= IRQ_COMPRESSION_START)
-	    && (triggering == ACPI_LEVEL_SENSITIVE)) {
-		/*
-		 * For PCI devices assign IRQs in order, avoiding gaps
-		 * due to unused I/O APIC pins.
-		 */
-		int irq = gsi;
-		if (gsi < MAX_GSI_NUM) {
-			/*
-			 * Retain the VIA chipset work-around (gsi > 15), but
-			 * avoid a problem where the 8254 timer (IRQ0) is setup
-			 * via an override (so it's not on pin 0 of the ioapic),
-			 * and at the same time, the pin 0 interrupt is a PCI
-			 * type.  The gsi > 15 test could cause these two pins
-			 * to be shared as IRQ0, and they are not shareable.
-			 * So test for this condition, and if necessary, avoid
-			 * the pin collision.
-			 */
-			gsi = pci_irq++;
-			/*
-			 * Don't assign IRQ used by ACPI SCI
-			 */
-			if (gsi == acpi_gbl_FADT.sci_interrupt)
-				gsi = pci_irq++;
-			gsi_to_irq[irq] = gsi;
-		} else {
-			printk(KERN_ERR "GSI %u is too high\n", gsi);
-			return gsi;
-		}
-	}
-#endif
-	io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
-				triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
-				polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
-	return gsi;
+	replace_intsrc_all(mpc, mpc_new_phys, mpc_new_length);
+
+	return 0;
 }
 
-#endif /* CONFIG_X86_IO_APIC */
-#endif /* CONFIG_ACPI */
+late_initcall(update_mp_table);

arch/x86/kernel/nmi_32.c → arch/x86/kernel/nmi.c

@@ -11,10 +11,13 @@
  *  Mikael Pettersson	: PM converted to driver model. Disable/enable API.
  */
 
+#include <asm/apic.h>
+
+#include <linux/nmi.h>
+#include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-#include <linux/nmi.h>
 #include <linux/sysdev.h>
 #include <linux/sysctl.h>
 #include <linux/percpu.h>
@@ -22,12 +25,18 @@
 #include <linux/cpumask.h>
 #include <linux/kernel_stat.h>
 #include <linux/kdebug.h>
-#include <linux/slab.h>
+#include <linux/smp.h>
 
+#include <asm/i8259.h>
+#include <asm/io_apic.h>
 #include <asm/smp.h>
 #include <asm/nmi.h>
+#include <asm/proto.h>
+#include <asm/timer.h>
 
-#include "mach_traps.h"
+#include <asm/mce.h>
+
+#include <mach_traps.h>
 
 int unknown_nmi_panic;
 int nmi_watchdog_enabled;
@@ -41,28 +50,65 @@ static cpumask_t backtrace_mask = CPU_MASK_NONE;
  *  0: the lapic NMI watchdog is disabled, but can be enabled
  */
 atomic_t nmi_active = ATOMIC_INIT(0);		/* oprofile uses this */
+EXPORT_SYMBOL(nmi_active);
 
-unsigned int nmi_watchdog = NMI_DEFAULT;
-static unsigned int nmi_hz = HZ;
+unsigned int nmi_watchdog = NMI_NONE;
+EXPORT_SYMBOL(nmi_watchdog);
 
+static int panic_on_timeout;
+
+static unsigned int nmi_hz = HZ;
 static DEFINE_PER_CPU(short, wd_enabled);
+static int endflag __initdata;
 
-static int endflag __initdata = 0;
+static inline unsigned int get_nmi_count(int cpu)
+{
+#ifdef CONFIG_X86_64
+	return cpu_pda(cpu)->__nmi_count;
+#else
+	return nmi_count(cpu);
+#endif
+}
+
+static inline int mce_in_progress(void)
+{
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
+	return atomic_read(&mce_entry) > 0;
+#endif
+	return 0;
+}
+
+/*
+ * Take the local apic timer and PIT/HPET into account. We don't
+ * know which one is active, when we have highres/dyntick on
+ */
+static inline unsigned int get_timer_irqs(int cpu)
+{
+#ifdef CONFIG_X86_64
+	return read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
+#else
+	return per_cpu(irq_stat, cpu).apic_timer_irqs +
+		per_cpu(irq_stat, cpu).irq0_irqs;
+#endif
+}
 
 #ifdef CONFIG_SMP
-/* The performance counters used by NMI_LOCAL_APIC don't trigger when
+/*
+ * The performance counters used by NMI_LOCAL_APIC don't trigger when
  * the CPU is idle. To make sure the NMI watchdog really ticks on all
  * CPUs during the test make them busy.
  */
 static __init void nmi_cpu_busy(void *data)
 {
 	local_irq_enable_in_hardirq();
-	/* Intentionally don't use cpu_relax here. This is
-	   to make sure that the performance counter really ticks,
-	   even if there is a simulator or similar that catches the
-	   pause instruction. On a real HT machine this is fine because
-	   all other CPUs are busy with "useless" delay loops and don't
-	   care if they get somewhat less cycles. */
+	/*
+	 * Intentionally don't use cpu_relax here. This is
+	 * to make sure that the performance counter really ticks,
+	 * even if there is a simulator or similar that catches the
+	 * pause instruction. On a real HT machine this is fine because
+	 * all other CPUs are busy with "useless" delay loops and don't
+	 * care if they get somewhat less cycles.
+	 */
 	while (endflag == 0)
 		mb();
 }
@@ -73,15 +119,12 @@ int __init check_nmi_watchdog(void)
 	unsigned int *prev_nmi_count;
 	int cpu;
 
-	if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DISABLED))
-		return 0;
-
-	if (!atomic_read(&nmi_active))
+	if (!nmi_watchdog_active() || !atomic_read(&nmi_active))
 		return 0;
 
-	prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
+	prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
 	if (!prev_nmi_count)
-		return -1;
+		goto error;
 
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
@@ -91,25 +134,19 @@ int __init check_nmi_watchdog(void)
 #endif
 
 	for_each_possible_cpu(cpu)
-		prev_nmi_count[cpu] = nmi_count(cpu);
+		prev_nmi_count[cpu] = get_nmi_count(cpu);
 	local_irq_enable();
-	mdelay((20*1000)/nmi_hz); // wait 20 ticks
+	mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
 
-	for_each_possible_cpu(cpu) {
-#ifdef CONFIG_SMP
-		/* Check cpu_callin_map here because that is set
-		   after the timer is started. */
-		if (!cpu_isset(cpu, cpu_callin_map))
-			continue;
-#endif
+	for_each_online_cpu(cpu) {
 		if (!per_cpu(wd_enabled, cpu))
 			continue;
-		if (nmi_count(cpu) - prev_nmi_count[cpu] <= 5) {
+		if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) {
 			printk(KERN_WARNING "WARNING: CPU#%d: NMI "
 				"appears to be stuck (%d->%d)!\n",
 				cpu,
 				prev_nmi_count[cpu],
-				nmi_count(cpu));
+				get_nmi_count(cpu));
 			per_cpu(wd_enabled, cpu) = 0;
 			atomic_dec(&nmi_active);
 		}
@@ -118,37 +155,53 @@ int __init check_nmi_watchdog(void)
 	if (!atomic_read(&nmi_active)) {
 		kfree(prev_nmi_count);
 		atomic_set(&nmi_active, -1);
-		return -1;
+		goto error;
 	}
 	printk("OK.\n");
 
-	/* now that we know it works we can reduce NMI frequency to
-	   something more reasonable; makes a difference in some configs */
+	/*
+	 * 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)
 		nmi_hz = lapic_adjust_nmi_hz(1);
 
 	kfree(prev_nmi_count);
 	return 0;
+error:
+	if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
+		disable_8259A_irq(0);
+#ifdef CONFIG_X86_32
+	timer_ack = 0;
+#endif
+	return -1;
 }
 
 static int __init setup_nmi_watchdog(char *str)
 {
-	int nmi;
+	unsigned int nmi;
+
+	if (!strncmp(str, "panic", 5)) {
+		panic_on_timeout = 1;
+		str = strchr(str, ',');
+		if (!str)
+			return 1;
+		++str;
+	}
 
 	get_option(&str, &nmi);
 
-	if ((nmi >= NMI_INVALID) || (nmi < NMI_NONE))
+	if (nmi >= NMI_INVALID)
 		return 0;
 
 	nmi_watchdog = nmi;
 	return 1;
 }
-
 __setup("nmi_watchdog=", setup_nmi_watchdog);
 
-
-/* Suspend/resume support */
-
+/*
+ * Suspend/resume support
+ */
 #ifdef CONFIG_PM
 
 static int nmi_pm_active; /* nmi_active before suspend */
@@ -172,7 +225,6 @@ static int lapic_nmi_resume(struct sys_device *dev)
 	return 0;
 }
 
-
 static struct sysdev_class nmi_sysclass = {
 	.name		= "lapic_nmi",
 	.resume		= lapic_nmi_resume,
@@ -188,7 +240,8 @@ static int __init init_lapic_nmi_sysfs(void)
 {
 	int error;
 
-	/* should really be a BUG_ON but b/c this is an
+	/*
+	 * should really be a BUG_ON but b/c this is an
 	 * init call, it just doesn't work.  -dcz
 	 */
 	if (nmi_watchdog != NMI_LOCAL_APIC)
@@ -202,6 +255,7 @@ static int __init init_lapic_nmi_sysfs(void)
 		error = sysdev_register(&device_lapic_nmi);
 	return error;
 }
+
 /* must come after the local APIC's device_initcall() */
 late_initcall(init_lapic_nmi_sysfs);
 
@@ -223,7 +277,7 @@ void acpi_nmi_enable(void)
 
 static void __acpi_nmi_disable(void *__unused)
 {
-	apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
+	apic_write_around(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
 }
 
 /*
@@ -242,12 +296,13 @@ void setup_apic_nmi_watchdog(void *unused)
 
 	/* 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))
+	if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0)
 		return;
 
 	switch (nmi_watchdog) {
 	case NMI_LOCAL_APIC:
-		__get_cpu_var(wd_enabled) = 1; /* enable it before to avoid race with handler */
+		 /* enable it before to avoid race with handler */
+		__get_cpu_var(wd_enabled) = 1;
 		if (lapic_watchdog_init(nmi_hz) < 0) {
 			__get_cpu_var(wd_enabled) = 0;
 			return;
@@ -262,9 +317,8 @@ void setup_apic_nmi_watchdog(void *unused)
 void stop_apic_nmi_watchdog(void *unused)
 {
 	/* only support LOCAL and IO APICs for now */
-	if ((nmi_watchdog != NMI_LOCAL_APIC) &&
-	    (nmi_watchdog != NMI_IO_APIC))
-	    	return;
+	if (!nmi_watchdog_active())
+		return;
 	if (__get_cpu_var(wd_enabled) == 0)
 		return;
 	if (nmi_watchdog == NMI_LOCAL_APIC)
@@ -284,26 +338,26 @@ void stop_apic_nmi_watchdog(void *unused)
  * since NMIs don't listen to _any_ locks, we have to be extremely
  * careful not to rely on unsafe variables. The printk might lock
  * up though, so we have to break up any console locks first ...
- * [when there will be more tty-related locks, break them up
- *  here too!]
+ * [when there will be more tty-related locks, break them up here too!]
  */
 
-static unsigned int
-	last_irq_sums [NR_CPUS],
-	alert_counter [NR_CPUS];
+static DEFINE_PER_CPU(unsigned, last_irq_sum);
+static DEFINE_PER_CPU(local_t, alert_counter);
+static DEFINE_PER_CPU(int, nmi_touch);
 
 void touch_nmi_watchdog(void)
 {
-	if (nmi_watchdog > 0) {
+	if (nmi_watchdog_active()) {
 		unsigned cpu;
 
 		/*
-		 * Just reset the alert counters, (other CPUs might be
-		 * spinning on locks we hold):
+		 * Tell other CPUs to reset their alert counters. We cannot
+		 * do it ourselves because the alert count increase is not
+		 * atomic.
 		 */
 		for_each_present_cpu(cpu) {
-			if (alert_counter[cpu])
-				alert_counter[cpu] = 0;
+			if (per_cpu(nmi_touch, cpu) != 1)
+				per_cpu(nmi_touch, cpu) = 1;
 		}
 	}
 
@@ -314,12 +368,9 @@ void touch_nmi_watchdog(void)
 }
 EXPORT_SYMBOL(touch_nmi_watchdog);
 
-extern void die_nmi(struct pt_regs *, const char *msg);
-
 notrace __kprobes int
 nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 {
-
 	/*
 	 * Since current_thread_info()-> is always on the stack, and we
 	 * always switch the stack NMI-atomically, it's safe to use
@@ -337,39 +388,45 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		touched = 1;
 	}
 
+	sum = get_timer_irqs(cpu);
+
+	if (__get_cpu_var(nmi_touch)) {
+		__get_cpu_var(nmi_touch) = 0;
+		touched = 1;
+	}
+
 	if (cpu_isset(cpu, backtrace_mask)) {
 		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
 
 		spin_lock(&lock);
-		printk("NMI backtrace for cpu %d\n", cpu);
+		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
 		dump_stack();
 		spin_unlock(&lock);
 		cpu_clear(cpu, backtrace_mask);
 	}
 
-	/*
-	 * Take the local apic timer and PIT/HPET into account. We don't
-	 * know which one is active, when we have highres/dyntick on
-	 */
-	sum = per_cpu(irq_stat, cpu).apic_timer_irqs +
-		per_cpu(irq_stat, cpu).irq0_irqs;
+	/* Could check oops_in_progress here too, but it's safer not to */
+	if (mce_in_progress())
+		touched = 1;
 
 	/* if the none of the timers isn't firing, this cpu isn't doing much */
-	if (!touched && last_irq_sums[cpu] == sum) {
+	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
 		/*
 		 * Ayiee, looks like this CPU is stuck ...
 		 * wait a few IRQs (5 seconds) before doing the oops ...
 		 */
-		alert_counter[cpu]++;
-		if (alert_counter[cpu] == 5*nmi_hz)
+		local_inc(&__get_cpu_var(alert_counter));
+		if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz)
 			/*
 			 * die_nmi will return ONLY if NOTIFY_STOP happens..
 			 */
-			die_nmi(regs, "BUG: NMI Watchdog detected LOCKUP");
+			die_nmi("BUG: NMI Watchdog detected LOCKUP",
+				regs, panic_on_timeout);
 	} else {
-		last_irq_sums[cpu] = sum;
-		alert_counter[cpu] = 0;
+		__get_cpu_var(last_irq_sum) = sum;
+		local_set(&__get_cpu_var(alert_counter), 0);
 	}
+
 	/* see if the nmi watchdog went off */
 	if (!__get_cpu_var(wd_enabled))
 		return rc;
@@ -378,7 +435,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		rc |= lapic_wd_event(nmi_hz);
 		break;
 	case NMI_IO_APIC:
-		/* don't know how to accurately check for this.
+		/*
+		 * don't know how to accurately check for this.
 		 * just assume it was a watchdog timer interrupt
 		 * This matches the old behaviour.
 		 */
@@ -396,7 +454,7 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
 	char buf[64];
 
 	sprintf(buf, "NMI received for unknown reason %02x\n", reason);
-	die_nmi(regs, buf);
+	die_nmi(buf, regs, 1); /* Always panic here */
 	return 0;
 }
 
@@ -414,32 +472,26 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
 	if (!!old_state == !!nmi_watchdog_enabled)
 		return 0;
 
-	if (atomic_read(&nmi_active) < 0 || nmi_watchdog == NMI_DISABLED) {
-		printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
+	if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) {
+		printk(KERN_WARNING
+			"NMI watchdog is permanently disabled\n");
 		return -EIO;
 	}
 
-	if (nmi_watchdog == NMI_DEFAULT) {
-		if (lapic_watchdog_ok())
-			nmi_watchdog = NMI_LOCAL_APIC;
-		else
-			nmi_watchdog = NMI_IO_APIC;
-	}
-
 	if (nmi_watchdog == NMI_LOCAL_APIC) {
 		if (nmi_watchdog_enabled)
 			enable_lapic_nmi_watchdog();
 		else
 			disable_lapic_nmi_watchdog();
 	} else {
-		printk( KERN_WARNING
+		printk(KERN_WARNING
 			"NMI watchdog doesn't know what hardware to touch\n");
 		return -EIO;
 	}
 	return 0;
 }
 
-#endif
+#endif /* CONFIG_SYSCTL */
 
 int do_nmi_callback(struct pt_regs *regs, int cpu)
 {
@@ -462,6 +514,3 @@ void __trigger_all_cpu_backtrace(void)
 		mdelay(1);
 	}
 }
-
-EXPORT_SYMBOL(nmi_active);
-EXPORT_SYMBOL(nmi_watchdog);

arch/x86/kernel/nmi_64.c

@@ -1,482 +0,0 @@
-/*
- *  NMI watchdog support on APIC systems
- *
- *  Started by Ingo Molnar <mingo@redhat.com>
- *
- *  Fixes:
- *  Mikael Pettersson	: AMD K7 support for local APIC NMI watchdog.
- *  Mikael Pettersson	: Power Management for local APIC NMI watchdog.
- *  Pavel Machek and
- *  Mikael Pettersson	: PM converted to driver model. Disable/enable API.
- */
-
-#include <linux/nmi.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/sysdev.h>
-#include <linux/sysctl.h>
-#include <linux/kprobes.h>
-#include <linux/cpumask.h>
-#include <linux/kdebug.h>
-
-#include <asm/smp.h>
-#include <asm/nmi.h>
-#include <asm/proto.h>
-#include <asm/mce.h>
-
-#include <mach_traps.h>
-
-int unknown_nmi_panic;
-int nmi_watchdog_enabled;
-int panic_on_unrecovered_nmi;
-
-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
- *     be enabled
- *  0: the lapic NMI watchdog is disabled, but can be enabled
- */
-atomic_t nmi_active = ATOMIC_INIT(0);		/* oprofile uses this */
-static int panic_on_timeout;
-
-unsigned int nmi_watchdog = NMI_DEFAULT;
-static unsigned int nmi_hz = HZ;
-
-static DEFINE_PER_CPU(short, wd_enabled);
-
-/* Run after command line and cpu_init init, but before all other checks */
-void nmi_watchdog_default(void)
-{
-	if (nmi_watchdog != NMI_DEFAULT)
-		return;
-	nmi_watchdog = NMI_NONE;
-}
-
-static int endflag __initdata = 0;
-
-#ifdef CONFIG_SMP
-/* The performance counters used by NMI_LOCAL_APIC don't trigger when
- * the CPU is idle. To make sure the NMI watchdog really ticks on all
- * CPUs during the test make them busy.
- */
-static __init void nmi_cpu_busy(void *data)
-{
-	local_irq_enable_in_hardirq();
-	/* Intentionally don't use cpu_relax here. This is
-	   to make sure that the performance counter really ticks,
-	   even if there is a simulator or similar that catches the
-	   pause instruction. On a real HT machine this is fine because
-	   all other CPUs are busy with "useless" delay loops and don't
-	   care if they get somewhat less cycles. */
-	while (endflag == 0)
-		mb();
-}
-#endif
-
-int __init check_nmi_watchdog(void)
-{
-	int *prev_nmi_count;
-	int cpu;
-
-	if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DISABLED))
-		return 0;
-
-	if (!atomic_read(&nmi_active))
-		return 0;
-
-	prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
-	if (!prev_nmi_count)
-		return -1;
-
-	printk(KERN_INFO "Testing NMI watchdog ... ");
-
-#ifdef CONFIG_SMP
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0);
-#endif
-
-	for (cpu = 0; cpu < NR_CPUS; cpu++)
-		prev_nmi_count[cpu] = cpu_pda(cpu)->__nmi_count;
-	local_irq_enable();
-	mdelay((20*1000)/nmi_hz); // wait 20 ticks
-
-	for_each_online_cpu(cpu) {
-		if (!per_cpu(wd_enabled, cpu))
-			continue;
-		if (cpu_pda(cpu)->__nmi_count - prev_nmi_count[cpu] <= 5) {
-			printk(KERN_WARNING "WARNING: CPU#%d: NMI "
-			       "appears to be stuck (%d->%d)!\n",
-				cpu,
-				prev_nmi_count[cpu],
-				cpu_pda(cpu)->__nmi_count);
-			per_cpu(wd_enabled, cpu) = 0;
-			atomic_dec(&nmi_active);
-		}
-	}
-	endflag = 1;
-	if (!atomic_read(&nmi_active)) {
-		kfree(prev_nmi_count);
-		atomic_set(&nmi_active, -1);
-		return -1;
-	}
-	printk("OK.\n");
-
-	/* 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)
-		nmi_hz = lapic_adjust_nmi_hz(1);
-
-	kfree(prev_nmi_count);
-	return 0;
-}
-
-static int __init setup_nmi_watchdog(char *str)
-{
-	int nmi;
-
-	if (!strncmp(str,"panic",5)) {
-		panic_on_timeout = 1;
-		str = strchr(str, ',');
-		if (!str)
-			return 1;
-		++str;
-	}
-
-	get_option(&str, &nmi);
-
-	if ((nmi >= NMI_INVALID) || (nmi < NMI_NONE))
-		return 0;
-
-	nmi_watchdog = nmi;
-	return 1;
-}
-
-__setup("nmi_watchdog=", setup_nmi_watchdog);
-
-#ifdef CONFIG_PM
-
-static int nmi_pm_active; /* nmi_active before suspend */
-
-static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
-{
-	/* only CPU0 goes here, other CPUs should be offline */
-	nmi_pm_active = atomic_read(&nmi_active);
-	stop_apic_nmi_watchdog(NULL);
-	BUG_ON(atomic_read(&nmi_active) != 0);
-	return 0;
-}
-
-static int lapic_nmi_resume(struct sys_device *dev)
-{
-	/* only CPU0 goes here, other CPUs should be offline */
-	if (nmi_pm_active > 0) {
-		setup_apic_nmi_watchdog(NULL);
-		touch_nmi_watchdog();
-	}
-	return 0;
-}
-
-static struct sysdev_class nmi_sysclass = {
-	.name		= "lapic_nmi",
-	.resume		= lapic_nmi_resume,
-	.suspend	= lapic_nmi_suspend,
-};
-
-static struct sys_device device_lapic_nmi = {
-	.id	= 0,
-	.cls	= &nmi_sysclass,
-};
-
-static int __init init_lapic_nmi_sysfs(void)
-{
-	int error;
-
-	/* should really be a BUG_ON but b/c this is an
-	 * init call, it just doesn't work.  -dcz
-	 */
-	if (nmi_watchdog != NMI_LOCAL_APIC)
-		return 0;
-
-	if (atomic_read(&nmi_active) < 0)
-		return 0;
-
-	error = sysdev_class_register(&nmi_sysclass);
-	if (!error)
-		error = sysdev_register(&device_lapic_nmi);
-	return error;
-}
-/* must come after the local APIC's device_initcall() */
-late_initcall(init_lapic_nmi_sysfs);
-
-#endif	/* CONFIG_PM */
-
-static void __acpi_nmi_enable(void *__unused)
-{
-	apic_write(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);
-}
-
-static void __acpi_nmi_disable(void *__unused)
-{
-	apic_write(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);
-}
-
-void setup_apic_nmi_watchdog(void *unused)
-{
-	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;
-
-	switch (nmi_watchdog) {
-	case NMI_LOCAL_APIC:
-		__get_cpu_var(wd_enabled) = 1;
-		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);
-	}
-}
-
-void stop_apic_nmi_watchdog(void *unused)
-{
-	/* only support LOCAL and IO APICs for now */
-	if ((nmi_watchdog != NMI_LOCAL_APIC) &&
-	    (nmi_watchdog != NMI_IO_APIC))
-	    	return;
-	if (__get_cpu_var(wd_enabled) == 0)
-		return;
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		lapic_watchdog_stop();
-	__get_cpu_var(wd_enabled) = 0;
-	atomic_dec(&nmi_active);
-}
-
-/*
- * the best way to detect whether a CPU has a 'hard lockup' problem
- * is to check it's local APIC timer IRQ counts. If they are not
- * changing then that CPU has some problem.
- *
- * as these watchdog NMI IRQs are generated on every CPU, we only
- * have to check the current processor.
- */
-
-static DEFINE_PER_CPU(unsigned, last_irq_sum);
-static DEFINE_PER_CPU(local_t, alert_counter);
-static DEFINE_PER_CPU(int, nmi_touch);
-
-void touch_nmi_watchdog(void)
-{
-	if (nmi_watchdog > 0) {
-		unsigned cpu;
-
-		/*
- 		 * Tell other CPUs to reset their alert counters. We cannot
-		 * do it ourselves because the alert count increase is not
-		 * atomic.
-		 */
-		for_each_present_cpu(cpu) {
-			if (per_cpu(nmi_touch, cpu) != 1)
-				per_cpu(nmi_touch, cpu) = 1;
-		}
-	}
-
-	touch_softlockup_watchdog();
-}
-EXPORT_SYMBOL(touch_nmi_watchdog);
-
-notrace __kprobes int
-nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
-{
-	int sum;
-	int touched = 0;
-	int cpu = smp_processor_id();
-	int rc = 0;
-
-	/* check for other users first */
-	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
-			== NOTIFY_STOP) {
-		rc = 1;
-		touched = 1;
-	}
-
-	sum = read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
-	if (__get_cpu_var(nmi_touch)) {
-		__get_cpu_var(nmi_touch) = 0;
-		touched = 1;
-	}
-
-	if (cpu_isset(cpu, backtrace_mask)) {
-		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
-
-		spin_lock(&lock);
-		printk("NMI backtrace for cpu %d\n", cpu);
-		dump_stack();
-		spin_unlock(&lock);
-		cpu_clear(cpu, backtrace_mask);
-	}
-
-#ifdef CONFIG_X86_MCE
-	/* Could check oops_in_progress here too, but it's safer
-	   not too */
-	if (atomic_read(&mce_entry) > 0)
-		touched = 1;
-#endif
-	/* if the apic timer isn't firing, this cpu isn't doing much */
-	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
-		/*
-		 * Ayiee, looks like this CPU is stuck ...
-		 * wait a few IRQs (5 seconds) before doing the oops ...
-		 */
-		local_inc(&__get_cpu_var(alert_counter));
-		if (local_read(&__get_cpu_var(alert_counter)) == 5*nmi_hz)
-			die_nmi("NMI Watchdog detected LOCKUP on CPU %d\n", regs,
-				panic_on_timeout);
-	} else {
-		__get_cpu_var(last_irq_sum) = sum;
-		local_set(&__get_cpu_var(alert_counter), 0);
-	}
-
-	/* see if the nmi watchdog went off */
-	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;
-	}
-	return rc;
-}
-
-static unsigned ignore_nmis;
-
-asmlinkage notrace __kprobes void
-do_nmi(struct pt_regs *regs, long error_code)
-{
-	nmi_enter();
-	add_pda(__nmi_count,1);
-	if (!ignore_nmis)
-		default_do_nmi(regs);
-	nmi_exit();
-}
-
-void stop_nmi(void)
-{
-	acpi_nmi_disable();
-	ignore_nmis++;
-}
-
-void restart_nmi(void)
-{
-	ignore_nmis--;
-	acpi_nmi_enable();
-}
-
-#ifdef CONFIG_SYSCTL
-
-static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
-{
-	unsigned char reason = get_nmi_reason();
-	char buf[64];
-
-	sprintf(buf, "NMI received for unknown reason %02x\n", reason);
-	die_nmi(buf, regs, 1);	/* Always panic here */
-	return 0;
-}
-
-/*
- * proc handler for /proc/sys/kernel/nmi
- */
-int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
-			void __user *buffer, size_t *length, loff_t *ppos)
-{
-	int old_state;
-
-	nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
-	old_state = nmi_watchdog_enabled;
-	proc_dointvec(table, write, file, buffer, length, ppos);
-	if (!!old_state == !!nmi_watchdog_enabled)
-		return 0;
-
-	if (atomic_read(&nmi_active) < 0 || nmi_watchdog == NMI_DISABLED) {
-		printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
-		return -EIO;
-	}
-
-	/* if nmi_watchdog is not set yet, then set it */
-	nmi_watchdog_default();
-
-	if (nmi_watchdog == NMI_LOCAL_APIC) {
-		if (nmi_watchdog_enabled)
-			enable_lapic_nmi_watchdog();
-		else
-			disable_lapic_nmi_watchdog();
-	} else {
-		printk( KERN_WARNING
-			"NMI watchdog doesn't know what hardware to touch\n");
-		return -EIO;
-	}
-	return 0;
-}
-
-#endif
-
-int do_nmi_callback(struct pt_regs *regs, int cpu)
-{
-#ifdef CONFIG_SYSCTL
-	if (unknown_nmi_panic)
-		return unknown_nmi_panic_callback(regs, cpu);
-#endif
-	return 0;
-}
-
-void __trigger_all_cpu_backtrace(void)
-{
-	int i;
-
-	backtrace_mask = cpu_online_map;
-	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
-	for (i = 0; i < 10 * 1000; i++) {
-		if (cpus_empty(backtrace_mask))
-			break;
-		mdelay(1);
-	}
-}
-
-EXPORT_SYMBOL(nmi_active);
-EXPORT_SYMBOL(nmi_watchdog);

arch/x86/kernel/numaq_32.c

@@ -31,6 +31,8 @@
 #include <asm/numaq.h>
 #include <asm/topology.h>
 #include <asm/processor.h>
+#include <asm/mpspec.h>
+#include <asm/e820.h>
 
 #define	MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT))
 
@@ -58,6 +60,8 @@ static void __init smp_dump_qct(void)
 			node_end_pfn[node] = MB_TO_PAGES(
 				eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
 
+			e820_register_active_regions(node, node_start_pfn[node],
+							node_end_pfn[node]);
 			memory_present(node,
 				node_start_pfn[node], node_end_pfn[node]);
 			node_remap_size[node] = node_memmap_size_bytes(node,
@@ -67,23 +71,35 @@ static void __init smp_dump_qct(void)
 	}
 }
 
-/*
- * Unlike Summit, we don't really care to let the NUMA-Q
- * fall back to flat mode.  Don't compile for NUMA-Q
- * unless you really need it!
- */
+static __init void early_check_numaq(void)
+{
+	/*
+	 * Find possible boot-time SMP configuration:
+	 */
+	early_find_smp_config();
+	/*
+	 * get boot-time SMP configuration:
+	 */
+	if (smp_found_config)
+		early_get_smp_config();
+}
+
 int __init get_memcfg_numaq(void)
 {
+	early_check_numaq();
+	if (!found_numaq)
+		return 0;
 	smp_dump_qct();
 	return 1;
 }
 
-static int __init numaq_tsc_disable(void)
+void __init numaq_tsc_disable(void)
 {
+	if (!found_numaq)
+		return -1;
+
 	if (num_online_nodes() > 1) {
 		printk(KERN_DEBUG "NUMAQ: disabling TSC\n");
 		setup_clear_cpu_cap(X86_FEATURE_TSC);
 	}
-	return 0;
 }
-arch_initcall(numaq_tsc_disable);