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

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

Fix up trivial conflict in include/linux/highmem.h manually.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 109 insertions, 14 deletions

diff --git a/arch/x86_64/kernel/trampoline.S b/arch/x86_64/kernel/trampoline.S
index c79b99a9e2f..e7e2764c461 100644
--- a/arch/x86_64/kernel/trampoline.S
+++ b/arch/x86_64/kernel/trampoline.S
@@ -3,6 +3,7 @@
  *	Trampoline.S	Derived from Setup.S by Linus Torvalds
  *
  *	4 Jan 1997 Michael Chastain: changed to gnu as.
+ *	15 Sept 2005 Eric Biederman: 64bit PIC support
  *
  *	Entry: CS:IP point to the start of our code, we are 
  *	in real mode with no stack, but the rest of the 
@@ -17,15 +18,20 @@
  *	and IP is zero.  Thus, data addresses need to be absolute
  *	(no relocation) and are taken with regard to r_base.
  *
+ *	With the addition of trampoline_level4_pgt this code can
+ *	now enter a 64bit kernel that lives at arbitrary 64bit
+ *	physical addresses.
+ *
  *	If you work on this file, check the object module with objdump
  *	--full-contents --reloc to make sure there are no relocation
- *	entries. For the GDT entry we do hand relocation in smpboot.c
- *	because of 64bit linker limitations.
+ *	entries.
  */
 
 #include <linux/linkage.h>
-#include <asm/segment.h>
+#include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/msr.h>
+#include <asm/segment.h>
 
 .data
 
@@ -33,15 +39,33 @@
 
 ENTRY(trampoline_data)
 r_base = .
+	cli			# We should be safe anyway
 	wbinvd	
 	mov	%cs, %ax	# Code and data in the same place
 	mov	%ax, %ds
+	mov	%ax, %es
+	mov	%ax, %ss
 
-	cli			# We should be safe anyway
 
 	movl	$0xA5A5A5A5, trampoline_data - r_base
 				# write marker for master knows we're running
 
+					# Setup stack
+	movw	$(trampoline_stack_end - r_base), %sp
+
+	call	verify_cpu		# Verify the cpu supports long mode
+	testl   %eax, %eax		# Check for return code
+	jnz	no_longmode
+
+	mov	%cs, %ax
+	movzx	%ax, %esi		# Find the 32bit trampoline location
+	shll	$4, %esi
+
+					# Fixup the vectors
+	addl	%esi, startup_32_vector - r_base
+	addl	%esi, startup_64_vector - r_base
+	addl	%esi, tgdt + 2 - r_base	# Fixup the gdt pointer
+
 	/*
 	 * GDT tables in non default location kernel can be beyond 16MB and
 	 * lgdt will not be able to load the address as in real mode default
@@ -49,23 +73,94 @@ r_base = .
 	 * to 32 bit.
 	 */
 
-	lidtl	idt_48 - r_base	# load idt with 0, 0
-	lgdtl	gdt_48 - r_base	# load gdt with whatever is appropriate
+	lidtl	tidt - r_base	# load idt with 0, 0
+	lgdtl	tgdt - r_base	# load gdt with whatever is appropriate
 
 	xor	%ax, %ax
 	inc	%ax		# protected mode (PE) bit
 	lmsw	%ax		# into protected mode
-	# flaush prefetch and jump to startup_32 in arch/x86_64/kernel/head.S
-	ljmpl	$__KERNEL32_CS, $(startup_32-__START_KERNEL_map)
+
+	# flush prefetch and jump to startup_32
+	ljmpl	*(startup_32_vector - r_base)
+
+	.code32
+	.balign 4
+startup_32:
+	movl	$__KERNEL_DS, %eax	# Initialize the %ds segment register
+	movl	%eax, %ds
+
+	xorl	%eax, %eax
+	btsl	$5, %eax		# Enable PAE mode
+	movl	%eax, %cr4
+
+					# Setup trampoline 4 level pagetables
+	leal	(trampoline_level4_pgt - r_base)(%esi), %eax
+	movl	%eax, %cr3
+
+	movl	$MSR_EFER, %ecx
+	movl	$(1 << _EFER_LME), %eax	# Enable Long Mode
+	xorl	%edx, %edx
+	wrmsr
+
+	xorl	%eax, %eax
+	btsl	$31, %eax		# Enable paging and in turn activate Long Mode
+	btsl	$0, %eax		# Enable protected mode
+	movl	%eax, %cr0
+
+	/*
+	 * At this point we're in long mode but in 32bit compatibility mode
+	 * with EFER.LME = 1, CS.L = 0, CS.D = 1 (and in turn
+	 * EFER.LMA = 1). Now we want to jump in 64bit mode, to do that we use
+	 * the new gdt/idt that has __KERNEL_CS with CS.L = 1.
+	 */
+	ljmp	*(startup_64_vector - r_base)(%esi)
+
+	.code64
+	.balign 4
+startup_64:
+	# Now jump into the kernel using virtual addresses
+	movq	$secondary_startup_64, %rax
+	jmp	*%rax
+
+	.code16
+no_longmode:
+	hlt
+	jmp no_longmode
+#include "verify_cpu.S"
 
 	# Careful these need to be in the same 64K segment as the above;
-idt_48:
+tidt:
 	.word	0			# idt limit = 0
 	.word	0, 0			# idt base = 0L
 
-gdt_48:
-	.short	GDT_ENTRIES*8 - 1	# gdt limit
-	.long	cpu_gdt_table-__START_KERNEL_map
+	# Duplicate the global descriptor table
+	# so the kernel can live anywhere
+	.balign 4
+tgdt:
+	.short	tgdt_end - tgdt		# gdt limit
+	.long	tgdt - r_base
+	.short 0
+	.quad	0x00cf9b000000ffff	# __KERNEL32_CS
+	.quad	0x00af9b000000ffff	# __KERNEL_CS
+	.quad	0x00cf93000000ffff	# __KERNEL_DS
+tgdt_end:
+
+	.balign 4
+startup_32_vector:
+	.long	startup_32 - r_base
+	.word	__KERNEL32_CS, 0
+
+	.balign 4
+startup_64_vector:
+	.long	startup_64 - r_base
+	.word	__KERNEL_CS, 0
+
+trampoline_stack:
+	.org 0x1000
+trampoline_stack_end:
+ENTRY(trampoline_level4_pgt)
+	.quad	level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+	.fill	510,8,0
+	.quad	level3_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
 
-.globl trampoline_end
-trampoline_end:	
+ENTRY(trampoline_end)