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

* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (156 commits)
  [PATCH] x86-64: Export smp_call_function_single
  [PATCH] i386: Clean up smp_tune_scheduling()
  [PATCH] unwinder: move .eh_frame to RODATA
  [PATCH] unwinder: fully support linker generated .eh_frame_hdr section
  [PATCH] x86-64: don't use set_irq_regs()
  [PATCH] x86-64: check vector in setup_ioapic_dest to verify if need setup_IO_APIC_irq
  [PATCH] x86-64: Make ix86 default to HIGHMEM4G instead of NOHIGHMEM
  [PATCH] i386: replace kmalloc+memset with kzalloc
  [PATCH] x86-64: remove remaining pc98 code
  [PATCH] x86-64: remove unused variable
  [PATCH] x86-64: Fix constraints in atomic_add_return()
  [PATCH] x86-64: fix asm constraints in i386 atomic_add_return
  [PATCH] x86-64: Correct documentation for bzImage protocol v2.05
  [PATCH] x86-64: replace kmalloc+memset with kzalloc in MTRR code
  [PATCH] x86-64: Fix numaq build error
  [PATCH] x86-64: include/asm-x86_64/cpufeature.h isn't a userspace header
  [PATCH] unwinder: Add debugging output to the Dwarf2 unwinder
  [PATCH] x86-64: Clarify error message in GART code
  [PATCH] x86-64: Fix interrupt race in idle callback (3rd try)
  [PATCH] x86-64: Remove unwind stack pointer alignment forcing again
  ...

Fixed conflict in include/linux/uaccess.h manually
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Documentation/i386/boot.txt

@@ -2,7 +2,7 @@
 		     ----------------------------
 
 		    H. Peter Anvin <hpa@zytor.com>
-			Last update 2005-09-02
+			Last update 2006-11-17
 
 On the i386 platform, the Linux kernel uses a rather complicated boot
 convention.  This has evolved partially due to historical aspects, as
@@ -35,6 +35,8 @@ Protocol 2.03:	(Kernel 2.4.18-pre1) Explicitly makes the highest possible
 		initrd address available to the bootloader.
 
 Protocol 2.04:	(Kernel 2.6.14) Extend the syssize field to four bytes.
+Protocol 2.05:	(Kernel 2.6.20) Make protected mode kernel relocatable.
+		Introduce relocatable_kernel and kernel_alignment fields.
 
 
 **** MEMORY LAYOUT
@@ -129,6 +131,8 @@ Offset	Proto	Name		Meaning
 0226/2	N/A	pad1		Unused
 0228/4	2.02+	cmd_line_ptr	32-bit pointer to the kernel command line
 022C/4	2.03+	initrd_addr_max	Highest legal initrd address
+0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
+0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
 
 (1) For backwards compatibility, if the setup_sects field contains 0, the
     real value is 4.

Documentation/kernel-parameters.txt

@@ -599,8 +599,6 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	hugepages=	[HW,IA-32,IA-64] Maximal number of HugeTLB pages.
 
-	noirqbalance	[IA-32,SMP,KNL] Disable kernel irq balancing
-
 	i8042.direct	[HW] Put keyboard port into non-translated mode
 	i8042.dumbkbd	[HW] Pretend that controller can only read data from
 			     keyboard and cannot control its state
@@ -1065,9 +1063,14 @@ and is between 256 and 4096 characters. It is defined in the file
 			in certain environments such as networked servers or
 			real-time systems.
 
+	noirqbalance	[IA-32,SMP,KNL] Disable kernel irq balancing
+
 	noirqdebug	[IA-32] Disables the code which attempts to detect and
 			disable unhandled interrupt sources.
 
+	no_timer_check	[IA-32,X86_64,APIC] Disables the code which tests for
+			broken timer IRQ sources.
+
 	noisapnp	[ISAPNP] Disables ISA PnP code.
 
 	noinitrd	[RAM] Tells the kernel not to load any configured
@@ -1752,6 +1755,9 @@ and is between 256 and 4096 characters. It is defined in the file
 	norandmaps	Don't use address space randomization
 			Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space
 
+ 	unwind_debug=N 	N > 0 will enable dwarf2 unwinder debugging
+			This is useful to get more information why
+			you got a "dwarf2 unwinder stuck"
 
 ______________________________________________________________________
 

Documentation/stable_api_nonsense.txt

@@ -62,9 +62,6 @@ consider the following facts about the Linux kernel:
       - different structures can contain different fields
       - Some functions may not be implemented at all, (i.e. some locks
 	compile away to nothing for non-SMP builds.)
-      - Parameter passing of variables from function to function can be
-	done in different ways (the CONFIG_REGPARM option controls
-	this.)
       - Memory within the kernel can be aligned in different ways,
 	depending on the build options.
   - Linux runs on a wide range of different processor architectures.

Documentation/sysctl/kernel.txt

@@ -27,6 +27,7 @@ show up in /proc/sys/kernel:
 - hotplug
 - java-appletviewer           [ binfmt_java, obsolete ]
 - java-interpreter            [ binfmt_java, obsolete ]
+- kstack_depth_to_print       [ X86 only ]
 - l2cr                        [ PPC only ]
 - modprobe                    ==> Documentation/kmod.txt
 - msgmax
@@ -170,6 +171,13 @@ This flag controls the L2 cache of G3 processor boards. If
 
 ==============================================================
 
+kstack_depth_to_print: (X86 only)
+
+Controls the number of words to print when dumping the raw
+kernel stack.
+
+==============================================================
+
 osrelease, ostype & version:
 
 # cat osrelease

Documentation/x86_64/boot-options.txt

@@ -52,10 +52,6 @@ APICs
 		 apicmaintimer. Useful when your PIT timer is totally
 		 broken.
 
-   disable_8254_timer / enable_8254_timer
-		 Enable interrupt 0 timer routing over the 8254 in addition to over
-	         the IO-APIC. The kernel tries to set a sensible default.
-
 Early Console
 
    syntax: earlyprintk=vga
@@ -183,7 +179,7 @@ PCI
 IOMMU
 
  iommu=[size][,noagp][,off][,force][,noforce][,leak][,memaper[=order]][,merge]
-         [,forcesac][,fullflush][,nomerge][,noaperture]
+         [,forcesac][,fullflush][,nomerge][,noaperture][,calgary]
    size  set size of iommu (in bytes)
    noagp don't initialize the AGP driver and use full aperture.
    off   don't use the IOMMU
@@ -204,6 +200,7 @@ IOMMU
 	    buffering.
    nodac    Forbid DMA >4GB
    panic    Always panic when IOMMU overflows
+   calgary  Use the Calgary IOMMU if it is available
 
   swiotlb=pages[,force]
 

arch/h8300/kernel/vmlinux.lds.S

@@ -70,6 +70,7 @@ SECTIONS
 #endif
         .text :
 	{
+	_text = .;
 #if defined(CONFIG_ROMKERNEL)
 	*(.int_redirect)
 #endif

arch/i386/Kconfig

@@ -182,6 +182,17 @@ config X86_ES7000
 
 endchoice
 
+config PARAVIRT
+	bool "Paravirtualization support (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	help
+	  Paravirtualization is a way of running multiple instances of
+	  Linux on the same machine, under a hypervisor.  This option
+	  changes the kernel so it can modify itself when it is run
+	  under a hypervisor, improving performance significantly.
+	  However, when run without a hypervisor the kernel is
+	  theoretically slower.  If in doubt, say N.
+
 config ACPI_SRAT
 	bool
 	default y
@@ -443,7 +454,8 @@ source "drivers/firmware/Kconfig"
 
 choice
 	prompt "High Memory Support"
-	default NOHIGHMEM
+	default HIGHMEM4G if !X86_NUMAQ
+	default HIGHMEM64G if X86_NUMAQ
 
 config NOHIGHMEM
 	bool "off"
@@ -710,20 +722,6 @@ config BOOT_IOREMAP
 	depends on (((X86_SUMMIT || X86_GENERICARCH) && NUMA) || (X86 && EFI))
 	default y
 
-config REGPARM
-	bool "Use register arguments"
-	default y
-	help
-	Compile the kernel with -mregparm=3. This instructs gcc to use
-	a more efficient function call ABI which passes the first three
-	arguments of a function call via registers, which results in denser
-	and faster code.
-
-	If this option is disabled, then the default ABI of passing
-	arguments via the stack is used.
-
-	If unsure, say Y.
-
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	depends on PROC_FS
@@ -773,23 +771,39 @@ config CRASH_DUMP
           PHYSICAL_START.
 	  For more details see Documentation/kdump/kdump.txt
 
-config PHYSICAL_START
-	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
+config RELOCATABLE
+	bool "Build a relocatable kernel(EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	help
+	  This build a kernel image that retains relocation information
+          so it can be loaded someplace besides the default 1MB.
+	  The relocations tend to the kernel binary about 10% larger,
+          but are discarded at runtime.
+
+	  One use is for the kexec on panic case where the recovery kernel
+          must live at a different physical address than the primary
+          kernel.
 
-	default "0x1000000" if CRASH_DUMP
+config PHYSICAL_ALIGN
+	hex "Alignment value to which kernel should be aligned"
 	default "0x100000"
+	range 0x2000 0x400000
 	help
-	  This gives the physical address where the kernel is loaded. Normally
-	  for regular kernels this value is 0x100000 (1MB). But in the case
-	  of kexec on panic the fail safe kernel needs to run at a different
-	  address than the panic-ed kernel. This option is used to set the load
-	  address for kernels used to capture crash dump on being kexec'ed
-	  after panic. The default value for crash dump kernels is
-	  0x1000000 (16MB). This can also be set based on the "X" value as
-	  specified in the "crashkernel=YM@XM" command line boot parameter
-	  passed to the panic-ed kernel. Typically this parameter is set as
-	  crashkernel=64M@16M. Please take a look at
-	  Documentation/kdump/kdump.txt for more details about crash dumps.
+	  This value puts the alignment restrictions on physical address
+ 	  where kernel is loaded and run from. Kernel is compiled for an
+ 	  address which meets above alignment restriction.
+
+ 	  If bootloader loads the kernel at a non-aligned address and
+ 	  CONFIG_RELOCATABLE is set, kernel will move itself to nearest
+ 	  address aligned to above value and run from there.
+
+ 	  If bootloader loads the kernel at a non-aligned address and
+ 	  CONFIG_RELOCATABLE is not set, kernel will ignore the run time
+ 	  load address and decompress itself to the address it has been
+ 	  compiled for and run from there. The address for which kernel is
+ 	  compiled already meets above alignment restrictions. Hence the
+ 	  end result is that kernel runs from a physical address meeting
+	  above alignment restrictions.
 
 	  Don't change this unless you know what you are doing.
 

arch/i386/Kconfig.cpu

@@ -103,8 +103,15 @@ config MPENTIUMM
 	  Select this for Intel Pentium M (not Pentium-4 M)
 	  notebook chips.
 
+config MCORE2
+	bool "Core 2/newer Xeon"
+	help
+	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and 53xx)
+	  CPUs. You can distingush newer from older Xeons by the CPU family
+	  in /proc/cpuinfo. Newer ones have 6.
+
 config MPENTIUM4
-	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/Xeon"
+	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
 	help
 	  Select this for Intel Pentium 4 chips.  This includes the
 	  Pentium 4, P4-based Celeron and Xeon, and Pentium-4 M
@@ -229,7 +236,7 @@ config X86_L1_CACHE_SHIFT
 	default "7" if MPENTIUM4 || X86_GENERIC
 	default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
-	default "6" if MK7 || MK8 || MPENTIUMM
+	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2
 
 config RWSEM_GENERIC_SPINLOCK
 	bool
@@ -287,17 +294,17 @@ config X86_ALIGNMENT_16
 
 config X86_GOOD_APIC
 	bool
-	depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || MK8 || MEFFICEON
+	depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || MK8 || MEFFICEON || MCORE2
 	default y
 
 config X86_INTEL_USERCOPY
 	bool
-	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON
+	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
 	default y
 
 config X86_USE_PPRO_CHECKSUM
 	bool
-	depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX
+	depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2
 	default y
 
 config X86_USE_3DNOW
@@ -312,5 +319,5 @@ config X86_OOSTORE
 
 config X86_TSC
 	bool
-	depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MGEODEGX1 || MGEODE_LX) && !X86_NUMAQ
+	depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ
 	default y

arch/i386/Kconfig.debug

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

arch/i386/Makefile

@@ -26,10 +26,12 @@ endif
 
 LDFLAGS		:= -m elf_i386
 OBJCOPYFLAGS	:= -O binary -R .note -R .comment -S
-LDFLAGS_vmlinux :=
+ifdef CONFIG_RELOCATABLE
+LDFLAGS_vmlinux := --emit-relocs
+endif
 CHECKFLAGS	+= -D__i386__
 
-CFLAGS += -pipe -msoft-float
+CFLAGS += -pipe -msoft-float -mregparm=3
 
 # prevent gcc from keeping the stack 16 byte aligned
 CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
@@ -37,8 +39,6 @@ CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
 # CPU-specific tuning. Anything which can be shared with UML should go here.
 include $(srctree)/arch/i386/Makefile.cpu
 
-cflags-$(CONFIG_REGPARM) += -mregparm=3
-
 # temporary until string.h is fixed
 cflags-y += -ffreestanding
 

arch/i386/Makefile.cpu

@@ -32,6 +32,7 @@ cflags-$(CONFIG_MWINCHIP2)	+= $(call cc-option,-march=winchip2,-march=i586)
 cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
 cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
+cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call cc-option,-mtune=core2,$(call cc-option,-mtune=generic,-mtune=i686))
 
 # AMD Elan support
 cflags-$(CONFIG_X86_ELAN)	+= -march=i486

arch/i386/boot/compressed/Makefile

@@ -4,22 +4,42 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
-targets		:= vmlinux vmlinux.bin vmlinux.bin.gz head.o misc.o piggy.o
+targets		:= vmlinux vmlinux.bin vmlinux.bin.gz head.o misc.o piggy.o \
+			vmlinux.bin.all vmlinux.relocs
 EXTRA_AFLAGS	:= -traditional
 
-LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -e startup_32
+LDFLAGS_vmlinux := -T
+CFLAGS_misc.o += -fPIC
+hostprogs-y	:= relocs
 
-$(obj)/vmlinux: $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o FORCE
+$(obj)/vmlinux: $(src)/vmlinux.lds $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o FORCE
 	$(call if_changed,ld)
 	@:
 
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
+quiet_cmd_relocs = RELOCS  $@
+      cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
+$(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
+	$(call if_changed,relocs)
+
+vmlinux.bin.all-y := $(obj)/vmlinux.bin
+vmlinux.bin.all-$(CONFIG_RELOCATABLE) += $(obj)/vmlinux.relocs
+quiet_cmd_relocbin = BUILD   $@
+      cmd_relocbin = cat $(filter-out FORCE,$^) > $@
+$(obj)/vmlinux.bin.all: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,relocbin)
+
+ifdef CONFIG_RELOCATABLE
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
+	$(call if_changed,gzip)
+else
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
+endif
 
 LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
 
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE
+$(obj)/piggy.o: $(src)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE
 	$(call if_changed,ld)

arch/i386/boot/compressed/head.S

@@ -26,7 +26,9 @@
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/page.h>
+#include <asm/boot.h>
 
+.section ".text.head"
 	.globl startup_32
 
 startup_32:
@@ -37,93 +39,142 @@ startup_32:
 	movl %eax,%es
 	movl %eax,%fs
 	movl %eax,%gs
+	movl %eax,%ss
 
-	lss stack_start,%esp
-	xorl %eax,%eax
-1:	incl %eax		# check that A20 really IS enabled
-	movl %eax,0x000000	# loop forever if it isn't
-	cmpl %eax,0x100000
-	je 1b
+/* Calculate the delta between where we were compiled to run
+ * at and where we were actually loaded at.  This can only be done
+ * with a short local call on x86.  Nothing  else will tell us what
+ * address we are running at.  The reserved chunk of the real-mode
+ * data at 0x34-0x3f are used as the stack for this calculation.
+ * Only 4 bytes are needed.
+ */
+	leal 0x40(%esi), %esp
+	call 1f
+1:	popl %ebp
+	subl $1b, %ebp
+
+/* %ebp contains the address we are loaded at by the boot loader and %ebx
+ * contains the address where we should move the kernel image temporarily
+ * for safe in-place decompression.
+ */
+
+#ifdef CONFIG_RELOCATABLE
+	movl 	%ebp, %ebx
+	addl    $(CONFIG_PHYSICAL_ALIGN - 1), %ebx
+	andl    $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebx
+#else
+	movl $LOAD_PHYSICAL_ADDR, %ebx
+#endif
+
+	/* Replace the compressed data size with the uncompressed size */
+	subl input_len(%ebp), %ebx
+	movl output_len(%ebp), %eax
+	addl %eax, %ebx
+	/* Add 8 bytes for every 32K input block */
+	shrl $12, %eax
+	addl %eax, %ebx
+	/* Add 32K + 18 bytes of extra slack */
+	addl $(32768 + 18), %ebx
+	/* Align on a 4K boundary */
+	addl $4095, %ebx
+	andl $~4095, %ebx
+
+/* Copy the compressed kernel to the end of our buffer
+ * where decompression in place becomes safe.
+ */
+	pushl %esi
+	leal _end(%ebp), %esi
+	leal _end(%ebx), %edi
+	movl $(_end - startup_32), %ecx
+	std
+	rep
+	movsb
+	cld
+	popl %esi
+
+/* Compute the kernel start address.
+ */
+#ifdef CONFIG_RELOCATABLE
+	addl    $(CONFIG_PHYSICAL_ALIGN - 1), %ebp
+	andl    $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebp
+#else
+	movl	$LOAD_PHYSICAL_ADDR, %ebp
+#endif
 
 /*
- * Initialize eflags.  Some BIOS's leave bits like NT set.  This would
- * confuse the debugger if this code is traced.
- * XXX - best to initialize before switching to protected mode.
+ * Jump to the relocated address.
  */
-	pushl $0
-	popfl
+	leal relocated(%ebx), %eax
+	jmp *%eax
+.section ".text"
+relocated:
+
 /*
  * Clear BSS
  */
 	xorl %eax,%eax
-	movl $_edata,%edi
-	movl $_end,%ecx
+	leal _edata(%ebx),%edi
+	leal _end(%ebx), %ecx
 	subl %edi,%ecx
 	cld
 	rep
 	stosb
+
+/*
+ * Setup the stack for the decompressor
+ */
+	leal stack_end(%ebx), %esp
+
 /*
  * Do the decompression, and jump to the new kernel..
  */
-	subl $16,%esp	# place for structure on the stack
-	movl %esp,%eax
+	movl output_len(%ebx), %eax
+	pushl %eax
+	pushl %ebp	# output address
+	movl input_len(%ebx), %eax
+	pushl %eax	# input_len
+	leal input_data(%ebx), %eax
+	pushl %eax	# input_data
+	leal _end(%ebx), %eax
+	pushl %eax	# end of the image as third argument
 	pushl %esi	# real mode pointer as second arg
-	pushl %eax	# address of structure as first arg
 	call decompress_kernel
-	orl  %eax,%eax 
-	jnz  3f
-	popl %esi	# discard address
-	popl %esi	# real mode pointer
-	xorl %ebx,%ebx
-	ljmp $(__BOOT_CS), $__PHYSICAL_START
+	addl $20, %esp
+	popl %ecx
 
+#if CONFIG_RELOCATABLE
+/* Find the address of the relocations.
+ */
+	movl %ebp, %edi
+	addl %ecx, %edi
+
+/* Calculate the delta between where vmlinux was compiled to run
+ * and where it was actually loaded.
+ */
+	movl %ebp, %ebx
+	subl $LOAD_PHYSICAL_ADDR, %ebx
+	jz   2f		/* Nothing to be done if loaded at compiled addr. */
 /*
- * We come here, if we were loaded high.
- * We need to move the move-in-place routine down to 0x1000
- * and then start it with the buffer addresses in registers,
- * which we got from the stack.
+ * Process relocations.
  */
-3:
-	movl $move_routine_start,%esi
-	movl $0x1000,%edi
-	movl $move_routine_end,%ecx
-	subl %esi,%ecx
-	addl $3,%ecx
-	shrl $2,%ecx
-	cld
-	rep
-	movsl
-
-	popl %esi	# discard the address
-	popl %ebx	# real mode pointer
-	popl %esi	# low_buffer_start
-	popl %ecx	# lcount
-	popl %edx	# high_buffer_start
-	popl %eax	# hcount
-	movl $__PHYSICAL_START,%edi
-	cli		# make sure we don't get interrupted
-	ljmp $(__BOOT_CS), $0x1000 # and jump to the move routine
+
+1:	subl $4, %edi
+	movl 0(%edi), %ecx
+	testl %ecx, %ecx
+	jz 2f
+	addl %ebx, -__PAGE_OFFSET(%ebx, %ecx)
+	jmp 1b
+2:
+#endif
 
 /*
- * Routine (template) for moving the decompressed kernel in place,
- * if we were high loaded. This _must_ PIC-code !
+ * Jump to the decompressed kernel.
  */
-move_routine_start:
-	movl %ecx,%ebp
-	shrl $2,%ecx
-	rep
-	movsl
-	movl %ebp,%ecx
-	andl $3,%ecx
-	rep
-	movsb
-	movl %edx,%esi
-	movl %eax,%ecx	# NOTE: rep movsb won't move if %ecx == 0
-	addl $3,%ecx
-	shrl $2,%ecx
-	rep
-	movsl
-	movl %ebx,%esi	# Restore setup pointer
 	xorl %ebx,%ebx
-	ljmp $(__BOOT_CS), $__PHYSICAL_START
-move_routine_end:
+	jmp *%ebp
+
+.bss
+.balign 4
+stack:
+	.fill 4096, 1, 0
+stack_end:

arch/i386/boot/compressed/vmlinux.lds

+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+ENTRY(startup_32)
+SECTIONS
+{
+        /* Be careful parts of head.S assume startup_32 is at
+         * address 0.
+	 */
+	. =  0 	;
+	.text.head : {
+		_head = . ;
+		*(.text.head)
+		_ehead = . ;
+	}
+	.data.compressed : {
+		*(.data.compressed)
+	}
+	.text :	{
+		_text = .; 	/* Text */
+		*(.text)
+		*(.text.*)
+		_etext = . ;
+	}
+	.rodata : {
+		_rodata = . ;
+		*(.rodata)	 /* read-only data */
+		*(.rodata.*)
+		_erodata = . ;
+	}
+	.data :	{
+		_data = . ;
+		*(.data)
+		*(.data.*)
+		_edata = . ;
+	}
+	.bss : {
+		_bss = . ;
+		*(.bss)
+		*(.bss.*)
+		*(COMMON)
+		_end = . ;
+	}
+}

arch/i386/boot/compressed/vmlinux.scr

 SECTIONS
 {
-  .data : { 
+  .data.compressed : {
 	input_len = .;
 	LONG(input_data_end - input_data) input_data = .; 
 	*(.data) 
+	output_len = . - 4;
 	input_data_end = .; 
 	}
 }

arch/i386/boot/setup.S

@@ -81,7 +81,7 @@ start:
 # This is the setup header, and it must start at %cs:2 (old 0x9020:2)
 
 		.ascii	"HdrS"		# header signature
-		.word	0x0204		# header version number (>= 0x0105)
+		.word	0x0205		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
 start_sys_seg:	.word	SYSSEG
@@ -160,6 +160,17 @@ ramdisk_max:	.long (-__PAGE_OFFSET-(512 << 20)-1) & 0x7fffffff
 					# The highest safe address for
 					# the contents of an initrd
 
+kernel_alignment:  .long CONFIG_PHYSICAL_ALIGN 	#physical addr alignment
+						#required for protected mode
+						#kernel
+#ifdef CONFIG_RELOCATABLE
+relocatable_kernel:    .byte 1
+#else
+relocatable_kernel:    .byte 0
+#endif
+pad2:			.byte 0
+pad3:			.word 0
+
 trampoline:	call	start_of_setup
 		.align 16
 					# The offset at this point is 0x240
@@ -588,11 +599,6 @@ rmodeswtch_normal:
 	call	default_switch
 
 rmodeswtch_end:
-# we get the code32 start address and modify the below 'jmpi'
-# (loader may have changed it)
-	movl	%cs:code32_start, %eax
-	movl	%eax, %cs:code32
-
 # Now we move the system to its rightful place ... but we check if we have a
 # big-kernel. In that case we *must* not move it ...
 	testb	$LOADED_HIGH, %cs:loadflags
@@ -788,11 +794,12 @@ a20_err_msg:
 a20_done:
 
 #endif /* CONFIG_X86_VOYAGER */
-# set up gdt and idt
+# set up gdt and idt and 32bit start address
 	lidt	idt_48				# load idt with 0,0
 	xorl	%eax, %eax			# Compute gdt_base
 	movw	%ds, %ax			# (Convert %ds:gdt to a linear ptr)
 	shll	$4, %eax
+	addl	%eax, code32
 	addl	$gdt, %eax
 	movl	%eax, (gdt_48+2)
 	lgdt	gdt_48				# load gdt with whatever is
@@ -851,9 +858,26 @@ flush_instr:
 #	Manual, Mixing 16-bit and 32-bit code, page 16-6)
 
 	.byte 0x66, 0xea			# prefix + jmpi-opcode
-code32:	.long	0x1000				# will be set to 0x100000
-						# for big kernels
+code32:	.long	startup_32			# will be set to %cs+startup_32
 	.word	__BOOT_CS
+.code32
+startup_32:
+	movl $(__BOOT_DS), %eax
+	movl %eax, %ds
+	movl %eax, %es
+	movl %eax, %fs
+	movl %eax, %gs
+	movl %eax, %ss
+
+	xorl %eax, %eax
+1:	incl %eax				# check that A20 really IS enabled
+	movl %eax, 0x00000000			# loop forever if it isn't
+	cmpl %eax, 0x00100000
+	je 1b
+
+	# Jump to the 32bit entry point
+	jmpl *(code32_start - start + (DELTA_INITSEG << 4))(%esi)
+.code16
 
 # Here's a bunch of information about your current kernel..
 kernel_version:	.ascii	UTS_RELEASE

arch/i386/defconfig

 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.19-rc2-git4
-# Sat Oct 21 03:38:56 2006
+# Linux kernel version: 2.6.19-git7
+# Wed Dec  6 23:50:49 2006
 #
 CONFIG_X86_32=y
 CONFIG_GENERIC_TIME=y
@@ -40,13 +40,14 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 # CONFIG_CPUSETS is not set
+CONFIG_SYSFS_DEPRECATED=y
 # CONFIG_RELAY is not set
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 # CONFIG_EMBEDDED is not set
 CONFIG_UID16=y
-# CONFIG_SYSCTL_SYSCALL is not set
+CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
@@ -110,6 +111,7 @@ CONFIG_SMP=y
 # CONFIG_X86_VISWS is not set
 CONFIG_X86_GENERICARCH=y
 # CONFIG_X86_ES7000 is not set
+# CONFIG_PARAVIRT is not set
 CONFIG_X86_CYCLONE_TIMER=y
 # CONFIG_M386 is not set
 # CONFIG_M486 is not set
@@ -120,6 +122,7 @@ CONFIG_X86_CYCLONE_TIMER=y
 # CONFIG_MPENTIUMII is not set
 CONFIG_MPENTIUMIII=y
 # CONFIG_MPENTIUMM is not set
+# CONFIG_MCORE2 is not set
 # CONFIG_MPENTIUM4 is not set
 # CONFIG_MK6 is not set
 # CONFIG_MK7 is not set
@@ -197,7 +200,6 @@ CONFIG_RESOURCES_64BIT=y
 CONFIG_MTRR=y
 # CONFIG_EFI is not set
 # CONFIG_IRQBALANCE is not set
-CONFIG_REGPARM=y
 CONFIG_SECCOMP=y
 # CONFIG_HZ_100 is not set
 CONFIG_HZ_250=y
@@ -205,7 +207,8 @@ CONFIG_HZ_250=y
 CONFIG_HZ=250
 # CONFIG_KEXEC is not set
 # CONFIG_CRASH_DUMP is not set
-CONFIG_PHYSICAL_START=0x100000
+# CONFIG_RELOCATABLE is not set
+CONFIG_PHYSICAL_ALIGN=0x100000
 # CONFIG_HOTPLUG_CPU is not set
 CONFIG_COMPAT_VDSO=y
 CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
@@ -367,6 +370,7 @@ CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
 CONFIG_TCP_CONG_CUBIC=y
 CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
 CONFIG_IPV6=y
 # CONFIG_IPV6_PRIVACY is not set
 # CONFIG_IPV6_ROUTER_PREF is not set
@@ -677,6 +681,7 @@ CONFIG_SATA_INTEL_COMBINED=y
 # CONFIG_PATA_IT821X is not set
 # CONFIG_PATA_JMICRON is not set
 # CONFIG_PATA_TRIFLEX is not set
+# CONFIG_PATA_MARVELL is not set
 # CONFIG_PATA_MPIIX is not set
 # CONFIG_PATA_OLDPIIX is not set
 # CONFIG_PATA_NETCELL is not set
@@ -850,6 +855,7 @@ CONFIG_BNX2=y
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
+# CONFIG_NETXEN_NIC is not set
 
 #
 # Token Ring devices
@@ -984,10 +990,6 @@ CONFIG_RTC=y
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
 # CONFIG_SONYPI is not set
-
-#
-# Ftape, the floppy tape device driver
-#
 CONFIG_AGP=y
 # CONFIG_AGP_ALI is not set
 # CONFIG_AGP_ATI is not set
@@ -1108,6 +1110,7 @@ CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_BANDWIDTH is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
+# CONFIG_USB_MULTITHREAD_PROBE is not set
 # CONFIG_USB_OTG is not set
 
 #
@@ -1185,6 +1188,7 @@ CONFIG_USB_HIDINPUT=y
 # CONFIG_USB_KAWETH is not set
 # CONFIG_USB_PEGASUS is not set
 # CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET_MII is not set
 # CONFIG_USB_USBNET is not set
 CONFIG_USB_MON=y
 

arch/i386/kernel/Makefile

@@ -6,7 +6,7 @@ extra-y := head.o init_task.o vmlinux.lds
 
 obj-y	:= process.o signal.o entry.o traps.o irq.o \
 		ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \
-		pci-dma.o i386_ksyms.o i387.o bootflag.o \
+		pci-dma.o i386_ksyms.o i387.o bootflag.o e820.o\
 		quirks.o i8237.o topology.o alternative.o i8253.o tsc.o
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
@@ -40,6 +40,9 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_K8_NB)		+= k8.o
 
+# Make sure this is linked after any other paravirt_ops structs: see head.S
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
+
 EXTRA_AFLAGS   := -traditional
 
 obj-$(CONFIG_SCx200)		+= scx200.o

arch/i386/kernel/acpi/earlyquirk.c

@@ -10,6 +10,7 @@
 #include <asm/pci-direct.h>
 #include <asm/acpi.h>
 #include <asm/apic.h>
+#include <asm/irq.h>
 
 #ifdef CONFIG_ACPI
 
@@ -49,6 +50,24 @@ static int __init check_bridge(int vendor, int device)
 	return 0;
 }
 
+static void check_intel(void)
+{
+	u16 vendor, device;
+
+	vendor = read_pci_config_16(0, 0, 0, PCI_VENDOR_ID);
+
+	if (vendor != PCI_VENDOR_ID_INTEL)
+		return;
+
+	device = read_pci_config_16(0, 0, 0, PCI_DEVICE_ID);
+#ifdef CONFIG_SMP
+	if (device == PCI_DEVICE_ID_INTEL_E7320_MCH ||
+	    device == PCI_DEVICE_ID_INTEL_E7520_MCH ||
+	    device == PCI_DEVICE_ID_INTEL_E7525_MCH)
+		quirk_intel_irqbalance();
+#endif
+}
+
 void __init check_acpi_pci(void)
 {
 	int num, slot, func;
@@ -60,6 +79,8 @@ void __init check_acpi_pci(void)
 	if (!early_pci_allowed())
 		return;
 
+	check_intel();
+
 	/* Poor man's PCI discovery */
 	for (num = 0; num < 32; num++) {
 		for (slot = 0; slot < 32; slot++) {

arch/i386/kernel/alternative.c

@@ -124,6 +124,20 @@ static unsigned char** find_nop_table(void)
 
 #endif /* CONFIG_X86_64 */
 
+static void nop_out(void *insns, unsigned int len)
+{
+	unsigned char **noptable = find_nop_table();
+
+	while (len > 0) {
+		unsigned int noplen = len;
+		if (noplen > ASM_NOP_MAX)
+			noplen = ASM_NOP_MAX;
+		memcpy(insns, noptable[noplen], noplen);
+		insns += noplen;
+		len -= noplen;
+	}
+}
+
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern struct alt_instr __smp_alt_instructions[], __smp_alt_instructions_end[];
 extern u8 *__smp_locks[], *__smp_locks_end[];
@@ -138,10 +152,9 @@ extern u8 __smp_alt_begin[], __smp_alt_end[];
 
 void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
-	unsigned char **noptable = find_nop_table();
 	struct alt_instr *a;
 	u8 *instr;
-	int diff, i, k;
+	int diff;
 
 	DPRINTK("%s: alt table %p -> %p\n", __FUNCTION__, start, end);
 	for (a = start; a < end; a++) {
@@ -159,13 +172,7 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 #endif
 		memcpy(instr, a->replacement, a->replacementlen);
 		diff = a->instrlen - a->replacementlen;
-		/* Pad the rest with nops */
-		for (i = a->replacementlen; diff > 0; diff -= k, i += k) {
-			k = diff;
-			if (k > ASM_NOP_MAX)
-				k = ASM_NOP_MAX;
-			memcpy(a->instr + i, noptable[k], k);
-		}
+		nop_out(instr + a->replacementlen, diff);
 	}
 }
 
@@ -209,7 +216,6 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 
 static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 {
-	unsigned char **noptable = find_nop_table();
 	u8 **ptr;
 
 	for (ptr = start; ptr < end; ptr++) {
@@ -217,7 +223,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end
 			continue;
 		if (*ptr > text_end)
 			continue;
-		**ptr = noptable[1][0];
+		nop_out(*ptr, 1);
 	};
 }
 
@@ -343,6 +349,40 @@ void alternatives_smp_switch(int smp)
 
 #endif
 
+#ifdef CONFIG_PARAVIRT
+void apply_paravirt(struct paravirt_patch *start, struct paravirt_patch *end)
+{
+	struct paravirt_patch *p;
+
+	for (p = start; p < end; p++) {
+		unsigned int used;
+
+		used = paravirt_ops.patch(p->instrtype, p->clobbers, p->instr,
+					  p->len);
+#ifdef CONFIG_DEBUG_PARAVIRT
+		{
+		int i;
+		/* Deliberately clobber regs using "not %reg" to find bugs. */
+		for (i = 0; i < 3; i++) {
+			if (p->len - used >= 2 && (p->clobbers & (1 << i))) {
+				memcpy(p->instr + used, "\xf7\xd0", 2);
+				p->instr[used+1] |= i;
+				used += 2;
+			}
+		}
+		}
+#endif
+		/* Pad the rest with nops */
+		nop_out(p->instr + used, p->len - used);
+	}
+
+	/* Sync to be conservative, in case we patched following instructions */
+	sync_core();
+}
+extern struct paravirt_patch __start_parainstructions[],
+	__stop_parainstructions[];
+#endif	/* CONFIG_PARAVIRT */
+
 void __init alternative_instructions(void)
 {
 	unsigned long flags;
@@ -390,5 +430,6 @@ void __init alternative_instructions(void)
 		alternatives_smp_switch(0);
 	}
 #endif
+ 	apply_paravirt(__start_parainstructions, __stop_parainstructions);
 	local_irq_restore(flags);
 }

arch/i386/kernel/apic.c

@@ -647,23 +647,30 @@ static struct {
 static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 {
 	unsigned long flags;
+	int maxlvt;
 
 	if (!apic_pm_state.active)
 		return 0;
 
+	maxlvt = get_maxlvt();
+
 	apic_pm_state.apic_id = apic_read(APIC_ID);
 	apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
 	apic_pm_state.apic_ldr = apic_read(APIC_LDR);
 	apic_pm_state.apic_dfr = apic_read(APIC_DFR);
 	apic_pm_state.apic_spiv = apic_read(APIC_SPIV);
 	apic_pm_state.apic_lvtt = apic_read(APIC_LVTT);
+	if (maxlvt >= 4)
 		apic_pm_state.apic_lvtpc = apic_read(APIC_LVTPC);
 	apic_pm_state.apic_lvt0 = apic_read(APIC_LVT0);
 	apic_pm_state.apic_lvt1 = apic_read(APIC_LVT1);
 	apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
 	apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
 	apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
+#ifdef CONFIG_X86_MCE_P4THERMAL
+	if (maxlvt >= 5)
 		apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
+#endif
 	
 	local_irq_save(flags);
 	disable_local_APIC();
@@ -675,10 +682,13 @@ static int lapic_resume(struct sys_device *dev)
 {
 	unsigned int l, h;
 	unsigned long flags;
+	int maxlvt;
 
 	if (!apic_pm_state.active)
 		return 0;
 
+	maxlvt = get_maxlvt();
+
 	local_irq_save(flags);
 
 	/*
@@ -700,7 +710,11 @@ static int lapic_resume(struct sys_device *dev)
 	apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
 	apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
 	apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
+#ifdef CONFIG_X86_MCE_P4THERMAL
+	if (maxlvt >= 5)
 		apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
+#endif
+	if (maxlvt >= 4)
 		apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
 	apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
 	apic_write(APIC_TDCR, apic_pm_state.apic_tdcr);

arch/i386/kernel/apm.c

@@ -231,6 +231,7 @@
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/i8253.h>
+#include <asm/paravirt.h>
 
 #include "io_ports.h"
 
@@ -2235,7 +2236,7 @@ static int __init apm_init(void)
 
 	dmi_check_system(apm_dmi_table);
 
-	if (apm_info.bios.version == 0) {
+	if (apm_info.bios.version == 0 || paravirt_enabled()) {
 		printk(KERN_INFO "apm: BIOS not found.\n");
 		return -ENODEV;
 	}

arch/i386/kernel/asm-offsets.c

@@ -15,6 +15,7 @@
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 #include <asm/elf.h>
+#include <asm/pda.h>
 
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))
@@ -51,13 +52,35 @@ void foo(void)
 	OFFSET(TI_exec_domain, thread_info, exec_domain);
 	OFFSET(TI_flags, thread_info, flags);
 	OFFSET(TI_status, thread_info, status);
-	OFFSET(TI_cpu, thread_info, cpu);
 	OFFSET(TI_preempt_count, thread_info, preempt_count);
 	OFFSET(TI_addr_limit, thread_info, addr_limit);
 	OFFSET(TI_restart_block, thread_info, restart_block);
 	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
 	BLANK();
 
+	OFFSET(GDS_size, Xgt_desc_struct, size);
+	OFFSET(GDS_address, Xgt_desc_struct, address);
+	OFFSET(GDS_pad, Xgt_desc_struct, pad);
+	BLANK();
+
+	OFFSET(PT_EBX, pt_regs, ebx);
+	OFFSET(PT_ECX, pt_regs, ecx);
+	OFFSET(PT_EDX, pt_regs, edx);
+	OFFSET(PT_ESI, pt_regs, esi);
+	OFFSET(PT_EDI, pt_regs, edi);
+	OFFSET(PT_EBP, pt_regs, ebp);
+	OFFSET(PT_EAX, pt_regs, eax);
+	OFFSET(PT_DS,  pt_regs, xds);
+	OFFSET(PT_ES,  pt_regs, xes);
+	OFFSET(PT_GS,  pt_regs, xgs);
+	OFFSET(PT_ORIG_EAX, pt_regs, orig_eax);
+	OFFSET(PT_EIP, pt_regs, eip);
+	OFFSET(PT_CS,  pt_regs, xcs);
+	OFFSET(PT_EFLAGS, pt_regs, eflags);
+	OFFSET(PT_OLDESP, pt_regs, esp);
+	OFFSET(PT_OLDSS,  pt_regs, xss);
+	BLANK();
+
 	OFFSET(EXEC_DOMAIN_handler, exec_domain, handler);
 	OFFSET(RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
 	BLANK();
@@ -74,4 +97,18 @@ void foo(void)
 	DEFINE(VDSO_PRELINK, VDSO_PRELINK);
 
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
+
+	BLANK();
+ 	OFFSET(PDA_cpu, i386_pda, cpu_number);
+	OFFSET(PDA_pcurrent, i386_pda, pcurrent);
+
+#ifdef CONFIG_PARAVIRT
+	BLANK();
+	OFFSET(PARAVIRT_enabled, paravirt_ops, paravirt_enabled);
+	OFFSET(PARAVIRT_irq_disable, paravirt_ops, irq_disable);
+	OFFSET(PARAVIRT_irq_enable, paravirt_ops, irq_enable);
+	OFFSET(PARAVIRT_irq_enable_sysexit, paravirt_ops, irq_enable_sysexit);
+	OFFSET(PARAVIRT_iret, paravirt_ops, iret);
+	OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0);
+#endif
 }

arch/i386/kernel/cpu/amd.c

@@ -105,9 +105,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 				rdtscl(d2);
 				d = d2-d;
 
-				/* Knock these two lines out if it debugs out ok */
-				printk(KERN_INFO "AMD K6 stepping B detected - ");
-				/* -- cut here -- */
 				if (d > 20*K6_BUG_LOOP) 
 					printk("system stability may be impaired when more than 32 MB are used.\n");
 				else 

arch/i386/kernel/cpu/intel.c

@@ -107,7 +107,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 	 * Note that the workaround only should be initialized once...
 	 */
 	c->f00f_bug = 0;
-	if ( c->x86 == 5 ) {
+	if (!paravirt_enabled() && c->x86 == 5) {
 		static int f00f_workaround_enabled = 0;
 
 		c->f00f_bug = 1;
@@ -195,8 +195,16 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
-}
 
+	if (cpu_has_ds) {
+		unsigned int l1;
+		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
+		if (!(l1 & (1<<11)))
+			set_bit(X86_FEATURE_BTS, c->x86_capability);
+		if (!(l1 & (1<<12)))
+			set_bit(X86_FEATURE_PEBS, c->x86_capability);
+	}
+}
 
 static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 * c, unsigned int size)
 {

arch/i386/kernel/cpu/intel_cacheinfo.c

@@ -480,12 +480,10 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 	if (num_cache_leaves == 0)
 		return -ENOENT;
 
-	cpuid4_info[cpu] = kmalloc(
+	cpuid4_info[cpu] = kzalloc(
 	    sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL);
 	if (unlikely(cpuid4_info[cpu] == NULL))
 		return -ENOMEM;
-	memset(cpuid4_info[cpu], 0,
-	    sizeof(struct _cpuid4_info) * num_cache_leaves);
 
 	oldmask = current->cpus_allowed;
 	retval = set_cpus_allowed(current, cpumask_of_cpu(cpu));
@@ -658,17 +656,14 @@ static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu)
 		return -ENOENT;
 
 	/* Allocate all required memory */
-	cache_kobject[cpu] = kmalloc(sizeof(struct kobject), GFP_KERNEL);
+	cache_kobject[cpu] = kzalloc(sizeof(struct kobject), GFP_KERNEL);
 	if (unlikely(cache_kobject[cpu] == NULL))
 		goto err_out;
-	memset(cache_kobject[cpu], 0, sizeof(struct kobject));
 
-	index_kobject[cpu] = kmalloc(
+	index_kobject[cpu] = kzalloc(
 	    sizeof(struct _index_kobject ) * num_cache_leaves, GFP_KERNEL);
 	if (unlikely(index_kobject[cpu] == NULL))
 		goto err_out;
-	memset(index_kobject[cpu], 0,
-	    sizeof(struct _index_kobject) * num_cache_leaves);
 
 	return 0;
 

arch/i386/kernel/cpu/mtrr/Makefile

 obj-y		:= main.o if.o generic.o state.o
-obj-y		+= amd.o
-obj-y		+= cyrix.o
-obj-y		+= centaur.o
+obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o
 

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

@@ -7,7 +7,7 @@
 
 static void
 amd_get_mtrr(unsigned int reg, unsigned long *base,
-	     unsigned int *size, mtrr_type * type)
+	     unsigned long *size, mtrr_type * type)
 {
 	unsigned long low, high;
 

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

@@ -17,7 +17,7 @@ static u8 centaur_mcr_type;	/* 0 for winchip, 1 for winchip2 */
  */
 
 static int
-centaur_get_free_region(unsigned long base, unsigned long size)
+centaur_get_free_region(unsigned long base, unsigned long size, int replace_reg)
 /*  [SUMMARY] Get a free MTRR.
     <base> The starting (base) address of the region.
     <size> The size (in bytes) of the region.
@@ -26,10 +26,11 @@ centaur_get_free_region(unsigned long base, unsigned long size)
 {
 	int i, max;
 	mtrr_type ltype;
-	unsigned long lbase;
-	unsigned int lsize;
+	unsigned long lbase, lsize;
 
 	max = num_var_ranges;
+	if (replace_reg >= 0 && replace_reg < max)
+		return replace_reg;
 	for (i = 0; i < max; ++i) {
 		if (centaur_mcr_reserved & (1 << i))
 			continue;
@@ -49,7 +50,7 @@ mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
 
 static void
 centaur_get_mcr(unsigned int reg, unsigned long *base,
-		unsigned int *size, mtrr_type * type)
+		unsigned long *size, mtrr_type * type)
 {
 	*base = centaur_mcr[reg].high >> PAGE_SHIFT;
 	*size = -(centaur_mcr[reg].low & 0xfffff000) >> PAGE_SHIFT;

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

@@ -9,7 +9,7 @@ int arr3_protected;
 
 static void
 cyrix_get_arr(unsigned int reg, unsigned long *base,
-	      unsigned int *size, mtrr_type * type)
+	      unsigned long *size, mtrr_type * type)
 {
 	unsigned long flags;
 	unsigned char arr, ccr3, rcr, shift;
@@ -77,7 +77,7 @@ cyrix_get_arr(unsigned int reg, unsigned long *base,
 }
 
 static int
-cyrix_get_free_region(unsigned long base, unsigned long size)
+cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg)
 /*  [SUMMARY] Get a free ARR.
     <base> The starting (base) address of the region.
     <size> The size (in bytes) of the region.
@@ -86,9 +86,24 @@ cyrix_get_free_region(unsigned long base, unsigned long size)
 {
 	int i;
 	mtrr_type ltype;
-	unsigned long lbase;
-	unsigned int  lsize;
+	unsigned long lbase, lsize;
 
+	switch (replace_reg) {
+	case 7:
+		if (size < 0x40)
+			break;
+	case 6:
+	case 5:
+	case 4:
+		return replace_reg;
+	case 3:
+		if (arr3_protected)
+			break;
+	case 2:
+	case 1:
+	case 0:
+		return replace_reg;
+	}
 	/* If we are to set up a region >32M then look at ARR7 immediately */
 	if (size > 0x2000) {
 		cyrix_get_arr(7, &lbase, &lsize, &ltype);
@@ -214,7 +229,7 @@ static void cyrix_set_arr(unsigned int reg, unsigned long base,
 
 typedef struct {
 	unsigned long base;
-	unsigned int size;
+	unsigned long size;
 	mtrr_type type;
 } arr_state_t;
 

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

@@ -3,6 +3,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/module.h>
 #include <asm/io.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
@@ -15,12 +16,19 @@ struct mtrr_state {
 	struct mtrr_var_range *var_ranges;
 	mtrr_type fixed_ranges[NUM_FIXED_RANGES];
 	unsigned char enabled;
+	unsigned char have_fixed;
 	mtrr_type def_type;
 };
 
 static unsigned long smp_changes_mask;
 static struct mtrr_state mtrr_state = {};
 
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "mtrr."
+
+static __initdata int mtrr_show;
+module_param_named(show, mtrr_show, bool, 0);
+
 /*  Get the MSR pair relating to a var range  */
 static void __init
 get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
@@ -43,6 +51,14 @@ get_fixed_ranges(mtrr_type * frs)
 		rdmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], p[7 + i * 2]);
 }
 
+static void __init print_fixed(unsigned base, unsigned step, const mtrr_type*types)
+{
+	unsigned i;
+
+	for (i = 0; i < 8; ++i, ++types, base += step)
+		printk(KERN_INFO "MTRR %05X-%05X %s\n", base, base + step - 1, mtrr_attrib_to_str(*types));
+}
+
 /*  Grab all of the MTRR state for this CPU into *state  */
 void __init get_mtrr_state(void)
 {
@@ -58,13 +74,49 @@ void __init get_mtrr_state(void)
 	} 
 	vrs = mtrr_state.var_ranges;
 
+	rdmsr(MTRRcap_MSR, lo, dummy);
+	mtrr_state.have_fixed = (lo >> 8) & 1;
+
 	for (i = 0; i < num_var_ranges; i++)
 		get_mtrr_var_range(i, &vrs[i]);
+	if (mtrr_state.have_fixed)
 		get_fixed_ranges(mtrr_state.fixed_ranges);
 
 	rdmsr(MTRRdefType_MSR, lo, dummy);
 	mtrr_state.def_type = (lo & 0xff);
 	mtrr_state.enabled = (lo & 0xc00) >> 10;
+
+	if (mtrr_show) {
+		int high_width;
+
+		printk(KERN_INFO "MTRR default type: %s\n", mtrr_attrib_to_str(mtrr_state.def_type));
+		if (mtrr_state.have_fixed) {
+			printk(KERN_INFO "MTRR fixed ranges %sabled:\n",
+			       mtrr_state.enabled & 1 ? "en" : "dis");
+			print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
+			for (i = 0; i < 2; ++i)
+				print_fixed(0x80000 + i * 0x20000, 0x04000, mtrr_state.fixed_ranges + (i + 1) * 8);
+			for (i = 0; i < 8; ++i)
+				print_fixed(0xC0000 + i * 0x08000, 0x01000, mtrr_state.fixed_ranges + (i + 3) * 8);
+		}
+		printk(KERN_INFO "MTRR variable ranges %sabled:\n",
+		       mtrr_state.enabled & 2 ? "en" : "dis");
+		high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4;
+		for (i = 0; i < num_var_ranges; ++i) {
+			if (mtrr_state.var_ranges[i].mask_lo & (1 << 11))
+				printk(KERN_INFO "MTRR %u base %0*X%05X000 mask %0*X%05X000 %s\n",
+				       i,
+				       high_width,
+				       mtrr_state.var_ranges[i].base_hi,
+				       mtrr_state.var_ranges[i].base_lo >> 12,
+				       high_width,
+				       mtrr_state.var_ranges[i].mask_hi,
+				       mtrr_state.var_ranges[i].mask_lo >> 12,
+				       mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & 0xff));
+			else
+				printk(KERN_INFO "MTRR %u disabled\n", i);
+		}
+	}
 }
 
 /*  Some BIOS's are fucked and don't set all MTRRs the same!  */
@@ -95,7 +147,7 @@ void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b)
 			smp_processor_id(), msr, a, b);
 }
 
-int generic_get_free_region(unsigned long base, unsigned long size)
+int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg)
 /*  [SUMMARY] Get a free MTRR.
     <base> The starting (base) address of the region.
     <size> The size (in bytes) of the region.
@@ -104,10 +156,11 @@ int generic_get_free_region(unsigned long base, unsigned long size)
 {
 	int i, max;
 	mtrr_type ltype;
-	unsigned long lbase;
-	unsigned lsize;
+	unsigned long lbase, lsize;
 
 	max = num_var_ranges;
+	if (replace_reg >= 0 && replace_reg < max)
+		return replace_reg;
 	for (i = 0; i < max; ++i) {
 		mtrr_if->get(i, &lbase, &lsize, &ltype);
 		if (lsize == 0)
@@ -117,7 +170,7 @@ int generic_get_free_region(unsigned long base, unsigned long size)
 }
 
 static void generic_get_mtrr(unsigned int reg, unsigned long *base,
-			     unsigned int *size, mtrr_type * type)
+			     unsigned long *size, mtrr_type *type)
 {
 	unsigned int mask_lo, mask_hi, base_lo, base_hi;
 
@@ -202,7 +255,9 @@ static int set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
 	return changed;
 }
 
-static unsigned long set_mtrr_state(u32 deftype_lo, u32 deftype_hi)
+static u32 deftype_lo, deftype_hi;
+
+static unsigned long set_mtrr_state(void)
 /*  [SUMMARY] Set the MTRR state for this CPU.
     <state> The MTRR state information to read.
     <ctxt> Some relevant CPU context.
@@ -217,14 +272,14 @@ static unsigned long set_mtrr_state(u32 deftype_lo, u32 deftype_hi)
 		if (set_mtrr_var_ranges(i, &mtrr_state.var_ranges[i]))
 			change_mask |= MTRR_CHANGE_MASK_VARIABLE;
 
-	if (set_fixed_ranges(mtrr_state.fixed_ranges))
+	if (mtrr_state.have_fixed && set_fixed_ranges(mtrr_state.fixed_ranges))
 		change_mask |= MTRR_CHANGE_MASK_FIXED;
 
 	/*  Set_mtrr_restore restores the old value of MTRRdefType,
 	   so to set it we fiddle with the saved value  */
 	if ((deftype_lo & 0xff) != mtrr_state.def_type
 	    || ((deftype_lo & 0xc00) >> 10) != mtrr_state.enabled) {
-		deftype_lo |= (mtrr_state.def_type | mtrr_state.enabled << 10);
+		deftype_lo = (deftype_lo & ~0xcff) | mtrr_state.def_type | (mtrr_state.enabled << 10);
 		change_mask |= MTRR_CHANGE_MASK_DEFTYPE;
 	}
 
@@ -233,7 +288,6 @@ static unsigned long set_mtrr_state(u32 deftype_lo, u32 deftype_hi)
 
 
 static unsigned long cr4 = 0;
-static u32 deftype_lo, deftype_hi;
 static DEFINE_SPINLOCK(set_atomicity_lock);
 
 /*
@@ -271,7 +325,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	rdmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
 
 	/*  Disable MTRRs, and set the default type to uncached  */
-	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & 0xf300UL, deftype_hi);
+	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & ~0xcff, deftype_hi);
 }
 
 static void post_set(void) __releases(set_atomicity_lock)
@@ -300,7 +354,7 @@ static void generic_set_all(void)
 	prepare_set();
 
 	/* Actually set the state */
-	mask = set_mtrr_state(deftype_lo,deftype_hi);
+	mask = set_mtrr_state();
 
 	post_set();
 	local_irq_restore(flags);
@@ -366,7 +420,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, unsigned i
 			printk(KERN_WARNING "mtrr: base(0x%lx000) is not 4 MiB aligned\n", base);
 			return -EINVAL;
 		}
-		if (!(base + size < 0x70000000 || base > 0x7003FFFF) &&
+		if (!(base + size < 0x70000 || base > 0x7003F) &&
 		    (type == MTRR_TYPE_WRCOMB
 		     || type == MTRR_TYPE_WRBACK)) {
 			printk(KERN_WARNING "mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n");

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

@@ -17,7 +17,7 @@ extern unsigned int *usage_table;
 
 #define FILE_FCOUNT(f) (((struct seq_file *)((f)->private_data))->private)
 
-static char *mtrr_strings[MTRR_NUM_TYPES] =
+static const char *const mtrr_strings[MTRR_NUM_TYPES] =
 {
     "uncachable",               /* 0 */
     "write-combining",          /* 1 */
@@ -28,7 +28,7 @@ static char *mtrr_strings[MTRR_NUM_TYPES] =
     "write-back",               /* 6 */
 };
 
-char *mtrr_attrib_to_str(int x)
+const char *mtrr_attrib_to_str(int x)
 {
 	return (x <= 6) ? mtrr_strings[x] : "?";
 }
@@ -44,10 +44,9 @@ mtrr_file_add(unsigned long base, unsigned long size,
 
 	max = num_var_ranges;
 	if (fcount == NULL) {
-		fcount = kmalloc(max * sizeof *fcount, GFP_KERNEL);
+		fcount = kzalloc(max * sizeof *fcount, GFP_KERNEL);
 		if (!fcount)
 			return -ENOMEM;
-		memset(fcount, 0, max * sizeof *fcount);
 		FILE_FCOUNT(file) = fcount;
 	}
 	if (!page) {
@@ -155,6 +154,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 {
 	int err = 0;
 	mtrr_type type;
+	unsigned long size;
 	struct mtrr_sentry sentry;
 	struct mtrr_gentry gentry;
 	void __user *arg = (void __user *) __arg;
@@ -235,15 +235,15 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 	case MTRRIOC_GET_ENTRY:
 		if (gentry.regnum >= num_var_ranges)
 			return -EINVAL;
-		mtrr_if->get(gentry.regnum, &gentry.base, &gentry.size, &type);
+		mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
 
 		/* Hide entries that go above 4GB */
-		if (gentry.base + gentry.size > 0x100000
-		    || gentry.size == 0x100000)
+		if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
+		    || size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)))
 			gentry.base = gentry.size = gentry.type = 0;
 		else {
 			gentry.base <<= PAGE_SHIFT;
-			gentry.size <<= PAGE_SHIFT;
+			gentry.size = size << PAGE_SHIFT;
 			gentry.type = type;
 		}
 
@@ -273,8 +273,14 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 	case MTRRIOC_GET_PAGE_ENTRY:
 		if (gentry.regnum >= num_var_ranges)
 			return -EINVAL;
-		mtrr_if->get(gentry.regnum, &gentry.base, &gentry.size, &type);
+		mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+		/* Hide entries that would overflow */
+		if (size != (__typeof__(gentry.size))size)
+			gentry.base = gentry.size = gentry.type = 0;
+		else {
+			gentry.size = size;
 			gentry.type = type;
+		}
 		break;
 	}
 
@@ -353,8 +359,7 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset)
 	char factor;
 	int i, max, len;
 	mtrr_type type;
-	unsigned long base;
-	unsigned int size;
+	unsigned long base, size;
 
 	len = 0;
 	max = num_var_ranges;
@@ -373,7 +378,7 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset)
 			}
 			/* RED-PEN: base can be > 32bit */ 
 			len += seq_printf(seq, 
-				   "reg%02i: base=0x%05lx000 (%4liMB), size=%4i%cB: %s, count=%d\n",
+				   "reg%02i: base=0x%05lx000 (%4luMB), size=%4lu%cB: %s, count=%d\n",
 			     i, base, base >> (20 - PAGE_SHIFT), size, factor,
 			     mtrr_attrib_to_str(type), usage_table[i]);
 		}

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

@@ -59,7 +59,11 @@ struct mtrr_ops * mtrr_if = NULL;
 static void set_mtrr(unsigned int reg, unsigned long base,
 		     unsigned long size, mtrr_type type);
 
+#ifndef CONFIG_X86_64
 extern int arr3_protected;
+#else
+#define arr3_protected 0
+#endif
 
 void set_mtrr_ops(struct mtrr_ops * ops)
 {
@@ -168,6 +172,13 @@ static void ipi_handler(void *info)
 
 #endif
 
+static inline int types_compatible(mtrr_type type1, mtrr_type type2) {
+	return type1 == MTRR_TYPE_UNCACHABLE ||
+	       type2 == MTRR_TYPE_UNCACHABLE ||
+	       (type1 == MTRR_TYPE_WRTHROUGH && type2 == MTRR_TYPE_WRBACK) ||
+	       (type1 == MTRR_TYPE_WRBACK && type2 == MTRR_TYPE_WRTHROUGH);
+}
+
 /**
  * set_mtrr - update mtrrs on all processors
  * @reg:	mtrr in question
@@ -263,8 +274,8 @@ static void set_mtrr(unsigned int reg, unsigned long base,
 
 /**
  *	mtrr_add_page - Add a memory type region
- *	@base: Physical base address of region in pages (4 KB)
- *	@size: Physical size of region in pages (4 KB)
+ *	@base: Physical base address of region in pages (in units of 4 kB!)
+ *	@size: Physical size of region in pages (4 kB)
  *	@type: Type of MTRR desired
  *	@increment: If this is true do usage counting on the region
  *
@@ -300,11 +311,9 @@ static void set_mtrr(unsigned int reg, unsigned long base,
 int mtrr_add_page(unsigned long base, unsigned long size, 
 		  unsigned int type, char increment)
 {
-	int i;
+	int i, replace, error;
 	mtrr_type ltype;
-	unsigned long lbase;
-	unsigned int lsize;
-	int error;
+	unsigned long lbase, lsize;
 
 	if (!mtrr_if)
 		return -ENXIO;
@@ -324,12 +333,18 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 		return -ENOSYS;
 	}
 
+	if (!size) {
+		printk(KERN_WARNING "mtrr: zero sized request\n");
+		return -EINVAL;
+	}
+
 	if (base & size_or_mask || size & size_or_mask) {
 		printk(KERN_WARNING "mtrr: base or size exceeds the MTRR width\n");
 		return -EINVAL;
 	}
 
 	error = -EINVAL;
+	replace = -1;
 
 	/* No CPU hotplug when we change MTRR entries */
 	lock_cpu_hotplug();
@@ -337,21 +352,28 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 	mutex_lock(&mtrr_mutex);
 	for (i = 0; i < num_var_ranges; ++i) {
 		mtrr_if->get(i, &lbase, &lsize, &ltype);
-		if (base >= lbase + lsize)
-			continue;
-		if ((base < lbase) && (base + size <= lbase))
+		if (!lsize || base > lbase + lsize - 1 || base + size - 1 < lbase)
 			continue;
 		/*  At this point we know there is some kind of overlap/enclosure  */
-		if ((base < lbase) || (base + size > lbase + lsize)) {
+		if (base < lbase || base + size - 1 > lbase + lsize - 1) {
+			if (base <= lbase && base + size - 1 >= lbase + lsize - 1) {
+				/*  New region encloses an existing region  */
+				if (type == ltype) {
+					replace = replace == -1 ? i : -2;
+					continue;
+				}
+				else if (types_compatible(type, ltype))
+					continue;
+			}
 			printk(KERN_WARNING
 			       "mtrr: 0x%lx000,0x%lx000 overlaps existing"
-			       " 0x%lx000,0x%x000\n", base, size, lbase,
+			       " 0x%lx000,0x%lx000\n", base, size, lbase,
 			       lsize);
 			goto out;
 		}
 		/*  New region is enclosed by an existing region  */
 		if (ltype != type) {
-			if (type == MTRR_TYPE_UNCACHABLE)
+			if (types_compatible(type, ltype))
 				continue;
 			printk (KERN_WARNING "mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n",
 			     base, size, mtrr_attrib_to_str(ltype),
@@ -364,10 +386,18 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 		goto out;
 	}
 	/*  Search for an empty MTRR  */
-	i = mtrr_if->get_free_region(base, size);
+	i = mtrr_if->get_free_region(base, size, replace);
 	if (i >= 0) {
 		set_mtrr(i, base, size, type);
+		if (likely(replace < 0))
 			usage_table[i] = 1;
+		else {
+			usage_table[i] = usage_table[replace] + !!increment;
+			if (unlikely(replace != i)) {
+				set_mtrr(replace, 0, 0, 0);
+				usage_table[replace] = 0;
+			}
+		}
 	} else
 		printk(KERN_INFO "mtrr: no more MTRRs available\n");
 	error = i;
@@ -455,8 +485,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 {
 	int i, max;
 	mtrr_type ltype;
-	unsigned long lbase;
-	unsigned int lsize;
+	unsigned long lbase, lsize;
 	int error = -EINVAL;
 
 	if (!mtrr_if)
@@ -544,9 +573,11 @@ extern void centaur_init_mtrr(void);
 
 static void __init init_ifs(void)
 {
+#ifndef CONFIG_X86_64
 	amd_init_mtrr();
 	cyrix_init_mtrr();
 	centaur_init_mtrr();
+#endif
 }
 
 /* The suspend/resume methods are only for CPU without MTRR. CPU using generic
@@ -555,7 +586,7 @@ static void __init init_ifs(void)
 struct mtrr_value {
 	mtrr_type	ltype;
 	unsigned long	lbase;
-	unsigned int	lsize;
+	unsigned long	lsize;
 };
 
 static struct mtrr_value * mtrr_state;
@@ -565,10 +596,8 @@ static int mtrr_save(struct sys_device * sysdev, pm_message_t state)
 	int i;
 	int size = num_var_ranges * sizeof(struct mtrr_value);
 
-	mtrr_state = kmalloc(size,GFP_ATOMIC);
-	if (mtrr_state)
-		memset(mtrr_state,0,size);
-	else
+	mtrr_state = kzalloc(size,GFP_ATOMIC);
+	if (!mtrr_state)
 		return -ENOMEM;
 
 	for (i = 0; i < num_var_ranges; i++) {

arch/i386/kernel/cpu/mtrr/mtrr.h

@@ -43,15 +43,16 @@ struct mtrr_ops {
 	void	(*set_all)(void);
 
 	void	(*get)(unsigned int reg, unsigned long *base,
-		       unsigned int *size, mtrr_type * type);
-	int	(*get_free_region) (unsigned long base, unsigned long size);
-
+		       unsigned long *size, mtrr_type * type);
+	int	(*get_free_region)(unsigned long base, unsigned long size,
+				   int replace_reg);
 	int	(*validate_add_page)(unsigned long base, unsigned long size,
 				     unsigned int type);
 	int	(*have_wrcomb)(void);
 };
 
-extern int generic_get_free_region(unsigned long base, unsigned long size);
+extern int generic_get_free_region(unsigned long base, unsigned long size,
+				   int replace_reg);
 extern int generic_validate_add_page(unsigned long base, unsigned long size,
 				     unsigned int type);
 
@@ -62,17 +63,17 @@ extern int positive_have_wrcomb(void);
 /* library functions for processor-specific routines */
 struct set_mtrr_context {
 	unsigned long flags;
-	unsigned long deftype_lo;
-	unsigned long deftype_hi;
 	unsigned long cr4val;
-	unsigned long ccr3;
+	u32 deftype_lo;
+	u32 deftype_hi;
+	u32 ccr3;
 };
 
 struct mtrr_var_range {
-	unsigned long base_lo;
-	unsigned long base_hi;
-	unsigned long mask_lo;
-	unsigned long mask_hi;
+	u32 base_lo;
+	u32 base_hi;
+	u32 mask_lo;
+	u32 mask_hi;
 };
 
 void set_mtrr_done(struct set_mtrr_context *ctxt);
@@ -92,6 +93,6 @@ extern struct mtrr_ops * mtrr_if;
 extern unsigned int num_var_ranges;
 
 void mtrr_state_warn(void);
-char *mtrr_attrib_to_str(int x);
+const char *mtrr_attrib_to_str(int x);
 void mtrr_wrmsr(unsigned, unsigned, unsigned);
 

arch/i386/kernel/cpu/proc.c

@@ -152,9 +152,10 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 				seq_printf(m, " [%d]", i);
 		}
 
-	seq_printf(m, "\nbogomips\t: %lu.%02lu\n\n",
+	seq_printf(m, "\nbogomips\t: %lu.%02lu\n",
 		     c->loops_per_jiffy/(500000/HZ),
 		     (c->loops_per_jiffy/(5000/HZ)) % 100);
+	seq_printf(m, "clflush size\t: %u\n\n", c->x86_clflush_size);
 
 	return 0;
 }

arch/i386/kernel/cpuid.c

@@ -34,7 +34,6 @@
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/smp_lock.h>
-#include <linux/fs.h>
 #include <linux/device.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>

arch/i386/kernel/efi.c

@@ -194,17 +194,24 @@ inline int efi_set_rtc_mmss(unsigned long nowtime)
 	return 0;
 }
 /*
- * This should only be used during kernel init and before runtime
- * services have been remapped, therefore, we'll need to call in physical
- * mode.  Note, this call isn't used later, so mark it __init.
+ * This is used during kernel init before runtime
+ * services have been remapped and also during suspend, therefore,
+ * we'll need to call both in physical and virtual modes.
  */
-inline unsigned long __init efi_get_time(void)
+inline unsigned long efi_get_time(void)
 {
 	efi_status_t status;
 	efi_time_t eft;
 	efi_time_cap_t cap;
 
+	if (efi.get_time) {
+		/* if we are in virtual mode use remapped function */
+ 		status = efi.get_time(&eft, &cap);
+	} else {
+		/* we are in physical mode */
 		status = phys_efi_get_time(&eft, &cap);
+	}
+
 	if (status != EFI_SUCCESS)
 		printk("Oops: efitime: can't read time status: 0x%lx\n",status);
 

arch/i386/kernel/head.S

@@ -55,6 +55,12 @@
  */
 ENTRY(startup_32)
 
+#ifdef CONFIG_PARAVIRT
+        movl %cs, %eax
+        testl $0x3, %eax
+        jnz startup_paravirt
+#endif
+
 /*
  * Set segments to known values.
  */
@@ -302,6 +308,7 @@ is386:	movl $2,%ecx		# set MP
 	movl %eax,%cr0
 
 	call check_x87
+	call setup_pda
 	lgdt cpu_gdt_descr
 	lidt idt_descr
 	ljmp $(__KERNEL_CS),$1f
@@ -312,10 +319,13 @@ is386:	movl $2,%ecx		# set MP
 	movl %eax,%ds
 	movl %eax,%es
 
-	xorl %eax,%eax			# Clear FS/GS and LDT
+	xorl %eax,%eax			# Clear FS and LDT
 	movl %eax,%fs
-	movl %eax,%gs
 	lldt %ax
+
+	movl $(__KERNEL_PDA),%eax
+	mov  %eax,%gs
+
 	cld			# gcc2 wants the direction flag cleared at all times
 	pushl $0		# fake return address for unwinder
 #ifdef CONFIG_SMP
@@ -345,6 +355,23 @@ check_x87:
 	.byte 0xDB,0xE4		/* fsetpm for 287, ignored by 387 */
 	ret
 
+/*
+ * Point the GDT at this CPU's PDA.  On boot this will be
+ * cpu_gdt_table and boot_pda; for secondary CPUs, these will be
+ * that CPU's GDT and PDA.
+ */
+setup_pda:
+	/* get the PDA pointer */
+	movl start_pda, %eax
+
+	/* slot the PDA address into the GDT */
+	mov cpu_gdt_descr+2, %ecx
+	mov %ax, (__KERNEL_PDA+0+2)(%ecx)		/* base & 0x0000ffff */
+	shr $16, %eax
+	mov %al, (__KERNEL_PDA+4+0)(%ecx)		/* base & 0x00ff0000 */
+	mov %ah, (__KERNEL_PDA+4+3)(%ecx)		/* base & 0xff000000 */
+	ret
+
 /*
  *  setup_idt
  *
@@ -465,6 +492,33 @@ ignore_int:
 #endif
 	iret
 
+#ifdef CONFIG_PARAVIRT
+startup_paravirt:
+	cld
+ 	movl $(init_thread_union+THREAD_SIZE),%esp
+
+	/* We take pains to preserve all the regs. */
+	pushl	%edx
+	pushl	%ecx
+	pushl	%eax
+
+	/* paravirt.o is last in link, and that probe fn never returns */
+	pushl	$__start_paravirtprobe
+1:
+	movl	0(%esp), %eax
+	pushl	(%eax)
+	movl	8(%esp), %eax
+	call	*(%esp)
+	popl	%eax
+
+	movl	4(%esp), %eax
+	movl	8(%esp), %ecx
+	movl	12(%esp), %edx
+
+	addl	$4, (%esp)
+	jmp	1b
+#endif
+
 /*
  * Real beginning of normal "text" segment
  */
@@ -484,6 +538,8 @@ ENTRY(empty_zero_page)
  * This starts the data section.
  */
 .data
+ENTRY(start_pda)
+	.long boot_pda
 
 ENTRY(stack_start)
 	.long init_thread_union+THREAD_SIZE
@@ -525,7 +581,7 @@ idt_descr:
 
 # boot GDT descriptor (later on used by CPU#0):
 	.word 0				# 32 bit align gdt_desc.address
-cpu_gdt_descr:
+ENTRY(cpu_gdt_descr)
 	.word GDT_ENTRIES*8-1
 	.long cpu_gdt_table
 
@@ -584,8 +640,8 @@ ENTRY(cpu_gdt_table)
 	.quad 0x00009a000000ffff	/* 0xc0 APM CS 16 code (16 bit) */
 	.quad 0x004092000000ffff	/* 0xc8 APM DS    data */
 
-	.quad 0x0000920000000000	/* 0xd0 - ESPFIX 16-bit SS */
-	.quad 0x0000000000000000	/* 0xd8 - unused */
+	.quad 0x00c0920000000000	/* 0xd0 - ESPFIX SS */
+	.quad 0x00cf92000000ffff	/* 0xd8 - PDA */
 	.quad 0x0000000000000000	/* 0xe0 - unused */
 	.quad 0x0000000000000000	/* 0xe8 - unused */
 	.quad 0x0000000000000000	/* 0xf0 - unused */

arch/i386/kernel/hpet.c

@@ -34,6 +34,7 @@ static int __init init_hpet_clocksource(void)
 	unsigned long hpet_period;
 	void __iomem* hpet_base;
 	u64 tmp;
+	int err;
 
 	if (!is_hpet_enabled())
 		return -ENODEV;
@@ -61,7 +62,11 @@ static int __init init_hpet_clocksource(void)
 	do_div(tmp, FSEC_PER_NSEC);
 	clocksource_hpet.mult = (u32)tmp;
 
-	return clocksource_register(&clocksource_hpet);
+	err = clocksource_register(&clocksource_hpet);
+	if (err)
+		iounmap(hpet_base);
+
+	return err;
 }
 
 module_init(init_hpet_clocksource);

arch/i386/kernel/i8259.c

@@ -381,7 +381,10 @@ void __init init_ISA_irqs (void)
 	}
 }
 
-void __init init_IRQ(void)
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(void)
 {
 	int i;
 

arch/i386/kernel/io_apic.c

@@ -154,14 +154,20 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
  * the interrupt, and we need to make sure the entry is fully populated
  * before that happens.
  */
-static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void
+__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
-	unsigned long flags;
 	union entry_union eu;
 	eu.entry = e;
-	spin_lock_irqsave(&ioapic_lock, flags);
 	io_apic_write(apic, 0x11 + 2*pin, eu.w2);
 	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
+}
+
+static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&ioapic_lock, flags);
+	__ioapic_write_entry(apic, pin, e);
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
@@ -837,8 +843,7 @@ static int __init find_isa_irq_pin(int irq, int type)
 
 		if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA ||
 		     mp_bus_id_to_type[lbus] == MP_BUS_EISA ||
-		     mp_bus_id_to_type[lbus] == MP_BUS_MCA ||
-		     mp_bus_id_to_type[lbus] == MP_BUS_NEC98
+		     mp_bus_id_to_type[lbus] == MP_BUS_MCA
 		    ) &&
 		    (mp_irqs[i].mpc_irqtype == type) &&
 		    (mp_irqs[i].mpc_srcbusirq == irq))
@@ -857,8 +862,7 @@ static int __init find_isa_irq_apic(int irq, int type)
 
 		if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA ||
 		     mp_bus_id_to_type[lbus] == MP_BUS_EISA ||
-		     mp_bus_id_to_type[lbus] == MP_BUS_MCA ||
-		     mp_bus_id_to_type[lbus] == MP_BUS_NEC98
+		     mp_bus_id_to_type[lbus] == MP_BUS_MCA
 		    ) &&
 		    (mp_irqs[i].mpc_irqtype == type) &&
 		    (mp_irqs[i].mpc_srcbusirq == irq))
@@ -988,12 +992,6 @@ static int EISA_ELCR(unsigned int irq)
 #define default_MCA_trigger(idx)	(1)
 #define default_MCA_polarity(idx)	(0)
 
-/* NEC98 interrupts are always polarity zero edge triggered,
- * when listed as conforming in the MP table. */
-
-#define default_NEC98_trigger(idx)     (0)
-#define default_NEC98_polarity(idx)    (0)
-
 static int __init MPBIOS_polarity(int idx)
 {
 	int bus = mp_irqs[idx].mpc_srcbus;
@@ -1028,11 +1026,6 @@ static int __init MPBIOS_polarity(int idx)
 					polarity = default_MCA_polarity(idx);
 					break;
 				}
-				case MP_BUS_NEC98: /* NEC 98 pin */
-				{
-					polarity = default_NEC98_polarity(idx);
-					break;
-				}
 				default:
 				{
 					printk(KERN_WARNING "broken BIOS!!\n");
@@ -1102,11 +1095,6 @@ static int MPBIOS_trigger(int idx)
 					trigger = default_MCA_trigger(idx);
 					break;
 				}
-				case MP_BUS_NEC98: /* NEC 98 pin */
-				{
-					trigger = default_NEC98_trigger(idx);
-					break;
-				}
 				default:
 				{
 					printk(KERN_WARNING "broken BIOS!!\n");
@@ -1168,7 +1156,6 @@ static int pin_2_irq(int idx, int apic, int pin)
 		case MP_BUS_ISA: /* ISA pin */
 		case MP_BUS_EISA:
 		case MP_BUS_MCA:
-		case MP_BUS_NEC98:
 		{
 			irq = mp_irqs[idx].mpc_srcbusirq;
 			break;
@@ -1236,7 +1223,7 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 
 /* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */
-u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 };
+static u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 };
 
 static int __assign_irq_vector(int irq)
 {
@@ -1361,8 +1348,8 @@ static void __init setup_IO_APIC_irqs(void)
 			if (!apic && (irq < 16))
 				disable_8259A_irq(irq);
 		}
-		ioapic_write_entry(apic, pin, entry);
 		spin_lock_irqsave(&ioapic_lock, flags);
+		__ioapic_write_entry(apic, pin, entry);
 		set_native_irq_info(irq, TARGET_CPUS);
 		spin_unlock_irqrestore(&ioapic_lock, flags);
 	}
@@ -1927,6 +1914,15 @@ static void __init setup_ioapic_ids_from_mpc(void)
 static void __init setup_ioapic_ids_from_mpc(void) { }
 #endif
 
+static int no_timer_check __initdata;
+
+static int __init notimercheck(char *s)
+{
+	no_timer_check = 1;
+	return 1;
+}
+__setup("no_timer_check", notimercheck);
+
 /*
  * There is a nasty bug in some older SMP boards, their mptable lies
  * about the timer IRQ. We do the following to work around the situation:
@@ -1935,10 +1931,13 @@ static void __init setup_ioapic_ids_from_mpc(void) { }
  *	- if this function detects that timer IRQs are defunct, then we fall
  *	  back to ISA timer IRQs
  */
-static int __init timer_irq_works(void)
+int __init timer_irq_works(void)
 {
 	unsigned long t1 = jiffies;
 
+	if (no_timer_check)
+		return 1;
+
 	local_irq_enable();
 	/* Let ten ticks pass... */
 	mdelay((10 * 1000) / HZ);
@@ -2162,9 +2161,15 @@ static inline void unlock_ExtINT_logic(void)
 	unsigned char save_control, save_freq_select;
 
 	pin  = find_isa_irq_pin(8, mp_INT);
+	if (pin == -1) {
+		WARN_ON_ONCE(1);
+		return;
+	}
 	apic = find_isa_irq_apic(8, mp_INT);
-	if (pin == -1)
+	if (apic == -1) {
+		WARN_ON_ONCE(1);
 		return;
+	}
 
 	entry0 = ioapic_read_entry(apic, pin);
 	clear_IO_APIC_pin(apic, pin);
@@ -2209,7 +2214,7 @@ int timer_uses_ioapic_pin_0;
  * is so screwy.  Thanks to Brian Perkins for testing/hacking this beast
  * fanatically on his truly buggy board.
  */
-static inline void check_timer(void)
+static inline void __init check_timer(void)
 {
 	int apic1, pin1, apic2, pin2;
 	int vector;
@@ -2857,8 +2862,8 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a
 	if (!ioapic && (irq < 16))
 		disable_8259A_irq(irq);
 
-	ioapic_write_entry(ioapic, pin, entry);
 	spin_lock_irqsave(&ioapic_lock, flags);
+	__ioapic_write_entry(ioapic, pin, entry);
 	set_native_irq_info(irq, TARGET_CPUS);
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 

arch/i386/kernel/ldt.c

@@ -160,16 +160,14 @@ static int read_default_ldt(void __user * ptr, unsigned long bytecount)
 {
 	int err;
 	unsigned long size;
-	void *address;
 
 	err = 0;
-	address = &default_ldt[0];
 	size = 5*sizeof(struct desc_struct);
 	if (size > bytecount)
 		size = bytecount;
 
 	err = size;
-	if (copy_to_user(ptr, address, size))
+	if (clear_user(ptr, size))
 		err = -EFAULT;
 
 	return err;

arch/i386/kernel/mca.c

@@ -283,10 +283,9 @@ static int __init mca_init(void)
 	bus->f.mca_transform_memory = mca_dummy_transform_memory;
 
 	/* get the motherboard device */
-	mca_dev = kmalloc(sizeof(struct mca_device), GFP_KERNEL);
+	mca_dev = kzalloc(sizeof(struct mca_device), GFP_KERNEL);
 	if(unlikely(!mca_dev))
 		goto out_nomem;
-	memset(mca_dev, 0, sizeof(struct mca_device));
 
 	/*
 	 * We do not expect many MCA interrupts during initialization,
@@ -310,11 +309,9 @@ static int __init mca_init(void)
 	mca_dev->slot = MCA_MOTHERBOARD;
 	mca_register_device(MCA_PRIMARY_BUS, mca_dev);
 
-	mca_dev = kmalloc(sizeof(struct mca_device), GFP_ATOMIC);
+	mca_dev = kzalloc(sizeof(struct mca_device), GFP_ATOMIC);
 	if(unlikely(!mca_dev))
 		goto out_unlock_nomem;
-	memset(mca_dev, 0, sizeof(struct mca_device));
-
 
 	/* Put motherboard into video setup mode, read integrated video
 	 * POS registers, and turn motherboard setup off.
@@ -349,10 +346,9 @@ static int __init mca_init(void)
 	}
 	if(which_scsi) {
 		/* found a scsi card */
-		mca_dev = kmalloc(sizeof(struct mca_device), GFP_ATOMIC);
+		mca_dev = kzalloc(sizeof(struct mca_device), GFP_ATOMIC);
 		if(unlikely(!mca_dev))
 			goto out_unlock_nomem;
-		memset(mca_dev, 0, sizeof(struct mca_device));
 
 		for(j = 0; j < 8; j++)
 			mca_dev->pos[j] = pos[j];
@@ -378,10 +374,9 @@ static int __init mca_init(void)
 		if(!mca_read_and_store_pos(pos))
 			continue;
 
-		mca_dev = kmalloc(sizeof(struct mca_device), GFP_ATOMIC);
+		mca_dev = kzalloc(sizeof(struct mca_device), GFP_ATOMIC);
 		if(unlikely(!mca_dev))
 			goto out_unlock_nomem;
-		memset(mca_dev, 0, sizeof(struct mca_device));
 
 		for(j=0; j<8; j++)
 			mca_dev->pos[j]=pos[j];

arch/i386/kernel/module.c

@@ -108,7 +108,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
-	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL;
+	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
+		*para = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { 
@@ -118,6 +119,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 			alt = s;
 		if (!strcmp(".smp_locks", secstrings + s->sh_name))
 			locks= s;
+		if (!strcmp(".parainstructions", secstrings + s->sh_name))
+			para = s;
 	}
 
 	if (alt) {
@@ -132,6 +135,12 @@ int module_finalize(const Elf_Ehdr *hdr,
 					    lseg, lseg + locks->sh_size,
 					    tseg, tseg + text->sh_size);
 	}
+
+	if (para) {
+		void *pseg = (void *)para->sh_addr;
+		apply_paravirt(pseg, pseg + para->sh_size);
+	}
+
 	return 0;
 }
 

arch/i386/kernel/mpparse.c

@@ -249,8 +249,6 @@ static void __init MP_bus_info (struct mpc_config_bus *m)
 		mp_current_pci_id++;
 	} else if (strncmp(str, BUSTYPE_MCA, sizeof(BUSTYPE_MCA)-1) == 0) {
 		mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA;
-	} else if (strncmp(str, BUSTYPE_NEC98, sizeof(BUSTYPE_NEC98)-1) == 0) {
-		mp_bus_id_to_type[m->mpc_busid] = MP_BUS_NEC98;
 	} else {
 		printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str);
 	}

arch/i386/kernel/msr.c

@@ -195,7 +195,6 @@ static ssize_t msr_write(struct file *file, const char __user *buf,
 {
 	const u32 __user *tmp = (const u32 __user *)buf;
 	u32 data[2];
-	size_t rv;
 	u32 reg = *ppos;
 	int cpu = iminor(file->f_dentry->d_inode);
 	int err;
@@ -203,7 +202,7 @@ static ssize_t msr_write(struct file *file, const char __user *buf,
 	if (count % 8)
 		return -EINVAL;	/* Invalid chunk size */
 
-	for (rv = 0; count; count -= 8) {
+	for (; count; count -= 8) {
 		if (copy_from_user(&data, tmp, 8))
 			return -EFAULT;
 		err = do_wrmsr(cpu, reg, data[0], data[1]);