Merge branch 'x86/core' into x86/unify-pci

Documentation/ABI/testing/sysfs-firmware-memmap

+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

-		     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.cpu

@@ -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

@@ -117,29 +117,11 @@ mcore-$(CONFIG_X86_VOYAGER)	:= arch/x86/mach-voyager/
 mflags-$(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 +142,7 @@ 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 +193,12 @@ 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

 /* -*- 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/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
@@ -134,7 +147,7 @@ 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)
 	jnz	int_ret_from_sys_call
@@ -151,10 +164,7 @@ 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 +210,7 @@ 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 +218,7 @@ 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)
@@ -241,7 +251,7 @@ 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)
 	jnz  int_ret_from_sys_call
@@ -254,8 +264,7 @@ 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 +319,12 @@ 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
@@ -370,13 +379,11 @@ 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 +483,7 @@ 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 +590,7 @@ 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)
 
@@ -18,15 +18,15 @@ CFLAGS_tsc_64.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-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(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-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
@@ -53,7 +53,7 @@ obj-$(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 +64,6 @@ 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 +93,13 @@ 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/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/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 */
@@ -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/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

@@ -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/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/cpu.h

+#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