x86_64: move boot

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

6 files changed, 767 insertions, 1 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 76ab5caddf9..52c1db85452 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -1,5 +1,5 @@
 ifeq ($(CONFIG_X86_32),y)
 include ${srctree}/arch/x86/boot/compressed/Makefile_32
 else
-include ${srctree}/arch/x86_64/boot/compressed/Makefile_64
+include ${srctree}/arch/x86/boot/compressed/Makefile_64
 endif
diff --git a/arch/x86/boot/compressed/Makefile_64 b/arch/x86/boot/compressed/Makefile_64
new file mode 100644
index 00000000000..dc6b3380cc4
--- /dev/null
+++ b/arch/x86/boot/compressed/Makefile_64
@@ -0,0 +1,30 @@
+#
+# linux/arch/x86/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+targets		:= vmlinux vmlinux.bin vmlinux.bin.gz head_64.o misc_64.o piggy.o
+
+CFLAGS := -m64 -D__KERNEL__ $(LINUXINCLUDE) -O2  \
+	  -fno-strict-aliasing -fPIC -mcmodel=small \
+	   $(call cc-option, -ffreestanding) \
+	   $(call cc-option, -fno-stack-protector)
+AFLAGS  := $(CFLAGS) -D__ASSEMBLY__
+LDFLAGS := -m elf_x86_64
+
+LDFLAGS_vmlinux := -T
+$(obj)/vmlinux: $(src)/vmlinux_64.lds $(obj)/head_64.o $(obj)/misc_64.o $(obj)/piggy.o FORCE
+	$(call if_changed,ld)
+	@:
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,gzip)
+
+LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
+
+$(obj)/piggy.o: $(obj)/vmlinux_64.scr $(obj)/vmlinux.bin.gz FORCE
+	$(call if_changed,ld)
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
new file mode 100644
index 00000000000..cff3d1dc5dd
--- /dev/null
+++ b/arch/x86/boot/compressed/head_64.S
@@ -0,0 +1,311 @@
+/*
+ *  linux/boot/head.S
+ *
+ *  Copyright (C) 1991, 1992, 1993  Linus Torvalds
+ */
+
+/*
+ *  head.S contains the 32-bit startup code.
+ *
+ * NOTE!!! Startup happens at absolute address 0x00001000, which is also where
+ * the page directory will exist. The startup code will be overwritten by
+ * the page directory. [According to comments etc elsewhere on a compressed
+ * kernel it will end up at 0x1000 + 1Mb I hope so as I assume this. - AC]
+ *
+ * Page 0 is deliberately kept safe, since System Management Mode code in 
+ * laptops may need to access the BIOS data stored there.  This is also
+ * useful for future device drivers that either access the BIOS via VM86 
+ * mode.
+ */
+
+/*
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+.code32
+.text
+
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/pgtable.h>
+#include <asm/page.h>
+#include <asm/msr.h>
+
+.section ".text.head"
+	.code32
+	.globl startup_32
+
+startup_32:
+	cld
+	cli
+	movl	$(__KERNEL_DS), %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+
+/* 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 0x1e4 (defined as a scratch field) are used as the stack
+ * for this calculation. Only 4 bytes are needed.
+ */
+	leal	(0x1e4+4)(%esi), %esp
+	call	1f
+1:	popl	%ebp
+	subl	$1b, %ebp
+
+/* setup a stack and make sure cpu supports long mode. */
+	movl	$user_stack_end, %eax
+	addl	%ebp, %eax
+	movl	%eax, %esp
+
+	call	verify_cpu
+	testl	%eax, %eax
+	jnz	no_longmode
+
+/* Compute the delta between where we were compiled to run at
+ * and where the code will actually run at.
+ */
+/* %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	$(LARGE_PAGE_SIZE -1), %ebx
+	andl	$LARGE_PAGE_MASK, %ebx
+#else
+	movl	$CONFIG_PHYSICAL_START, %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 and align on a 4K boundary */
+	addl	$(32768 + 18 + 4095), %ebx
+	andl	$~4095, %ebx
+
+/*
+ * Prepare for entering 64 bit mode
+ */
+
+	/* Load new GDT with the 64bit segments using 32bit descriptor */
+	leal	gdt(%ebp), %eax
+	movl	%eax, gdt+2(%ebp)
+	lgdt	gdt(%ebp)
+
+	/* Enable PAE mode */
+	xorl	%eax, %eax
+	orl	$(1 << 5), %eax
+	movl	%eax, %cr4
+
+ /*
+  * Build early 4G boot pagetable
+  */
+	/* Initialize Page tables to 0*/
+	leal	pgtable(%ebx), %edi
+	xorl	%eax, %eax
+	movl	$((4096*6)/4), %ecx
+	rep	stosl
+
+	/* Build Level 4 */
+	leal	pgtable + 0(%ebx), %edi
+	leal	0x1007 (%edi), %eax
+	movl	%eax, 0(%edi)
+
+	/* Build Level 3 */
+	leal	pgtable + 0x1000(%ebx), %edi
+	leal	0x1007(%edi), %eax
+	movl	$4, %ecx
+1:	movl	%eax, 0x00(%edi)
+	addl	$0x00001000, %eax
+	addl	$8, %edi
+	decl	%ecx
+	jnz	1b
+
+	/* Build Level 2 */
+	leal	pgtable + 0x2000(%ebx), %edi
+	movl	$0x00000183, %eax
+	movl	$2048, %ecx
+1:	movl	%eax, 0(%edi)
+	addl	$0x00200000, %eax
+	addl	$8, %edi
+	decl	%ecx
+	jnz	1b
+
+	/* Enable the boot page tables */
+	leal	pgtable(%ebx), %eax
+	movl	%eax, %cr3
+
+	/* Enable Long mode in EFER (Extended Feature Enable Register) */
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+
+	/* Setup for the jump to 64bit mode
+	 *
+	 * When the jump is performend we will be in long mode but
+	 * in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1
+	 * (and in turn EFER.LMA = 1).	To jump into 64bit mode we use
+	 * the new gdt/idt that has __KERNEL_CS with CS.L = 1.
+	 * We place all of the values on our mini stack so lret can
+	 * used to perform that far jump.
+	 */
+	pushl	$__KERNEL_CS
+	leal	startup_64(%ebp), %eax
+	pushl	%eax
+
+	/* Enter paged protected Mode, activating Long Mode */
+	movl	$0x80000001, %eax /* Enable Paging and Protected mode */
+	movl	%eax, %cr0
+
+	/* Jump from 32bit compatibility mode into 64bit mode. */
+	lret
+
+no_longmode:
+	/* This isn't an x86-64 CPU so hang */
+1:
+	hlt
+	jmp     1b
+
+#include "../../../x86_64/kernel/verify_cpu_64.S"
+
+	/* Be careful here startup_64 needs to be at a predictable
+	 * address so I can export it in an ELF header.  Bootloaders
+	 * should look at the ELF header to find this address, as
+	 * it may change in the future.
+	 */
+	.code64
+	.org 0x200
+ENTRY(startup_64)
+	/* We come here either from startup_32 or directly from a
+	 * 64bit bootloader.  If we come here from a bootloader we depend on
+	 * an identity mapped page table being provied that maps our
+	 * entire text+data+bss and hopefully all of memory.
+	 */
+
+	/* Setup data segments. */
+	xorl	%eax, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+	movl	%eax, %fs
+	movl	%eax, %gs
+	lldt	%ax
+	movl    $0x20, %eax
+	ltr	%ax
+
+	/* Compute the decompressed kernel start address.  It is where
+	 * we were loaded at aligned to a 2M boundary. %rbp contains the
+	 * decompressed kernel start address.
+	 *
+	 * If it is a relocatable kernel then decompress and run the kernel
+	 * from load address aligned to 2MB addr, otherwise decompress and
+	 * run the kernel from CONFIG_PHYSICAL_START
+	 */
+
+	/* Start with the delta to where the kernel will run at. */
+#ifdef CONFIG_RELOCATABLE
+	leaq	startup_32(%rip) /* - $startup_32 */, %rbp
+	addq	$(LARGE_PAGE_SIZE - 1), %rbp
+	andq	$LARGE_PAGE_MASK, %rbp
+	movq	%rbp, %rbx
+#else
+	movq	$CONFIG_PHYSICAL_START, %rbp
+	movq	%rbp, %rbx
+#endif
+
+	/* Replace the compressed data size with the uncompressed size */
+	movl	input_len(%rip), %eax
+	subq	%rax, %rbx
+	movl	output_len(%rip), %eax
+	addq	%rax, %rbx
+	/* Add 8 bytes for every 32K input block */
+	shrq	$12, %rax
+	addq	%rax, %rbx
+	/* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
+	addq	$(32768 + 18 + 4095), %rbx
+	andq	$~4095, %rbx
+
+/* Copy the compressed kernel to the end of our buffer
+ * where decompression in place becomes safe.
+ */
+	leaq	_end(%rip), %r8
+	leaq	_end(%rbx), %r9
+	movq	$_end /* - $startup_32 */, %rcx
+1:	subq	$8, %r8
+	subq	$8, %r9
+	movq	0(%r8), %rax
+	movq	%rax, 0(%r9)
+	subq	$8, %rcx
+	jnz	1b
+
+/*
+ * Jump to the relocated address.
+ */
+	leaq	relocated(%rbx), %rax
+	jmp	*%rax
+
+.section ".text"
+relocated:
+
+/*
+ * Clear BSS
+ */
+	xorq	%rax, %rax
+	leaq    _edata(%rbx), %rdi
+	leaq    _end(%rbx), %rcx
+	subq	%rdi, %rcx
+	cld
+	rep
+	stosb
+
+	/* Setup the stack */
+	leaq	user_stack_end(%rip), %rsp
+
+	/* zero EFLAGS after setting rsp */
+	pushq	$0
+	popfq
+
+/*
+ * Do the decompression, and jump to the new kernel..
+ */
+	pushq	%rsi			# Save the real mode argument
+	movq	%rsi, %rdi		# real mode address
+	leaq	_heap(%rip), %rsi	# _heap
+	leaq	input_data(%rip), %rdx  # input_data
+	movl	input_len(%rip), %eax
+	movq	%rax, %rcx		# input_len
+	movq	%rbp, %r8		# output
+	call	decompress_kernel
+	popq	%rsi
+
+
+/*
+ * Jump to the decompressed kernel.
+ */
+	jmp	*%rbp
+
+	.data
+gdt:
+	.word	gdt_end - gdt
+	.long	gdt
+	.word	0
+	.quad	0x0000000000000000	/* NULL descriptor */
+	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
+	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
+	.quad	0x0080890000000000	/* TS descriptor */
+	.quad   0x0000000000000000	/* TS continued */
+gdt_end:
+	.bss
+/* Stack for uncompression */
+	.balign 4
+user_stack:
+	.fill 4096,4,0
+user_stack_end:
diff --git a/arch/x86/boot/compressed/misc_64.c b/arch/x86/boot/compressed/misc_64.c
new file mode 100644
index 00000000000..f932b0e8909
--- /dev/null
+++ b/arch/x86/boot/compressed/misc_64.c
@@ -0,0 +1,371 @@
+/*
+ * misc.c
+ * 
+ * This is a collection of several routines from gzip-1.0.3 
+ * adapted for Linux.
+ *
+ * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ * puts by Nick Holloway 1993, better puts by Martin Mares 1995
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+
+#define _LINUX_STRING_H_ 1
+#define __LINUX_BITMAP_H 1
+
+#include <linux/linkage.h>
+#include <linux/screen_info.h>
+#include <asm/io.h>
+#include <asm/page.h>
+
+/* WARNING!!
+ * This code is compiled with -fPIC and it is relocated dynamically
+ * at run time, but no relocation processing is performed.
+ * This means that it is not safe to place pointers in static structures.
+ */
+
+/*
+ * Getting to provable safe in place decompression is hard.
+ * Worst case behaviours need to be analized.
+ * Background information:
+ *
+ * The file layout is:
+ *    magic[2]
+ *    method[1]
+ *    flags[1]
+ *    timestamp[4]
+ *    extraflags[1]
+ *    os[1]
+ *    compressed data blocks[N]
+ *    crc[4] orig_len[4]
+ *
+ * resulting in 18 bytes of non compressed data overhead.
+ *
+ * Files divided into blocks
+ * 1 bit (last block flag)
+ * 2 bits (block type)
+ *
+ * 1 block occurs every 32K -1 bytes or when there 50% compression has been achieved.
+ * The smallest block type encoding is always used.
+ *
+ * stored:
+ *    32 bits length in bytes.
+ *
+ * fixed:
+ *    magic fixed tree.
+ *    symbols.
+ *
+ * dynamic:
+ *    dynamic tree encoding.
+ *    symbols.
+ *
+ *
+ * The buffer for decompression in place is the length of the
+ * uncompressed data, plus a small amount extra to keep the algorithm safe.
+ * The compressed data is placed at the end of the buffer.  The output
+ * pointer is placed at the start of the buffer and the input pointer
+ * is placed where the compressed data starts.  Problems will occur
+ * when the output pointer overruns the input pointer.
+ *
+ * The output pointer can only overrun the input pointer if the input
+ * pointer is moving faster than the output pointer.  A condition only
+ * triggered by data whose compressed form is larger than the uncompressed
+ * form.
+ *
+ * The worst case at the block level is a growth of the compressed data
+ * of 5 bytes per 32767 bytes.
+ *
+ * The worst case internal to a compressed block is very hard to figure.
+ * The worst case can at least be boundined by having one bit that represents
+ * 32764 bytes and then all of the rest of the bytes representing the very
+ * very last byte.
+ *
+ * All of which is enough to compute an amount of extra data that is required
+ * to be safe.  To avoid problems at the block level allocating 5 extra bytes
+ * per 32767 bytes of data is sufficient.  To avoind problems internal to a block
+ * adding an extra 32767 bytes (the worst case uncompressed block size) is
+ * sufficient, to ensure that in the worst case the decompressed data for
+ * block will stop the byte before the compressed data for a block begins.
+ * To avoid problems with the compressed data's meta information an extra 18
+ * bytes are needed.  Leading to the formula:
+ *
+ * extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size.
+ *
+ * Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
+ * Adding 32768 instead of 32767 just makes for round numbers.
+ * Adding the decompressor_size is necessary as it musht live after all
+ * of the data as well.  Last I measured the decompressor is about 14K.
+ * 10K of actuall data and 4K of bss.
+ *
+ */
+
+/*
+ * gzip declarations
+ */
+
+#define OF(args)  args
+#define STATIC static
+
+#undef memset
+#undef memcpy
+#define memzero(s, n)     memset ((s), 0, (n))
+
+typedef unsigned char  uch;
+typedef unsigned short ush;
+typedef unsigned long  ulg;
+
+#define WSIZE 0x80000000	/* Window size must be at least 32k,
+				 * and a power of two
+				 * We don't actually have a window just
+				 * a huge output buffer so I report
+				 * a 2G windows size, as that should
+				 * always be larger than our output buffer.
+				 */
+
+static uch *inbuf;	/* input buffer */
+static uch *window;	/* Sliding window buffer, (and final output buffer) */
+
+static unsigned insize;  /* valid bytes in inbuf */
+static unsigned inptr;   /* index of next byte to be processed in inbuf */
+static unsigned outcnt;  /* bytes in output buffer */
+
+/* gzip flag byte */
+#define ASCII_FLAG   0x01 /* bit 0 set: file probably ASCII text */
+#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */
+#define EXTRA_FIELD  0x04 /* bit 2 set: extra field present */
+#define ORIG_NAME    0x08 /* bit 3 set: original file name present */
+#define COMMENT      0x10 /* bit 4 set: file comment present */
+#define ENCRYPTED    0x20 /* bit 5 set: file is encrypted */
+#define RESERVED     0xC0 /* bit 6,7:   reserved */
+
+#define get_byte()  (inptr < insize ? inbuf[inptr++] : fill_inbuf())
+		
+/* Diagnostic functions */
+#ifdef DEBUG
+#  define Assert(cond,msg) {if(!(cond)) error(msg);}
+#  define Trace(x) fprintf x
+#  define Tracev(x) {if (verbose) fprintf x ;}
+#  define Tracevv(x) {if (verbose>1) fprintf x ;}
+#  define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
+#  define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
+#else
+#  define Assert(cond,msg)
+#  define Trace(x)
+#  define Tracev(x)
+#  define Tracevv(x)
+#  define Tracec(c,x)
+#  define Tracecv(c,x)
+#endif
+
+static int  fill_inbuf(void);
+static void flush_window(void);
+static void error(char *m);
+static void gzip_mark(void **);
+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))
+
+extern unsigned char input_data[];
+extern int input_len;
+
+static long bytes_out = 0;
+
+static void *malloc(int size);
+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 long free_mem_ptr;
+static long free_mem_end_ptr;
+
+#define HEAP_SIZE             0x7000
+
+static char *vidmem = (char *)0xb8000;
+static int vidport;
+static int lines, cols;
+
+#include "../../../../lib/inflate.c"
+
+static void *malloc(int size)
+{
+	void *p;
+
+	if (size <0) error("Malloc error");
+	if (free_mem_ptr <= 0) error("Memory error");
+
+	free_mem_ptr = (free_mem_ptr + 3) & ~3;	/* Align */
+
+	p = (void *)free_mem_ptr;
+	free_mem_ptr += size;
+
+	if (free_mem_ptr >= free_mem_end_ptr)
+		error("Out of memory");
+
+	return p;
+}
+
+static void free(void *where)
+{	/* Don't care */
+}
+
+static void gzip_mark(void **ptr)
+{
+	*ptr = (void *) free_mem_ptr;
+}
+
+static void gzip_release(void **ptr)
+{
+	free_mem_ptr = (long) *ptr;
+}
+ 
+static void scroll(void)
+{
+	int i;
+
+	memcpy ( vidmem, vidmem + cols * 2, ( lines - 1 ) * cols * 2 );
+	for ( i = ( lines - 1 ) * cols * 2; i < lines * cols * 2; i += 2 )
+		vidmem[i] = ' ';
+}
+
+static void putstr(const char *s)
+{
+	int x,y,pos;
+	char c;
+
+	x = RM_SCREEN_INFO.orig_x;
+	y = RM_SCREEN_INFO.orig_y;
+
+	while ( ( c = *s++ ) != '\0' ) {
+		if ( c == '\n' ) {
+			x = 0;
+			if ( ++y >= lines ) {
+				scroll();
+				y--;
+			}
+		} else {
+			vidmem [ ( x + cols * y ) * 2 ] = c; 
+			if ( ++x >= cols ) {
+				x = 0;
+				if ( ++y >= lines ) {
+					scroll();
+					y--;
+				}
+			}
+		}
+	}
+
+	RM_SCREEN_INFO.orig_x = x;
+	RM_SCREEN_INFO.orig_y = y;
+
+	pos = (x + cols * y) * 2;	/* Update cursor position */
+	outb_p(14, vidport);
+	outb_p(0xff & (pos >> 9), vidport+1);
+	outb_p(15, vidport);
+	outb_p(0xff & (pos >> 1), vidport+1);
+}
+
+static void* memset(void* s, int c, unsigned n)
+{
+	int i;
+	char *ss = (char*)s;
+
+	for (i=0;i<n;i++) ss[i] = c;
+	return s;
+}
+
+static void* memcpy(void* dest, const void* src, unsigned n)
+{
+	int i;
+	char *d = (char *)dest, *s = (char *)src;
+
+	for (i=0;i<n;i++) d[i] = s[i];
+	return dest;
+}
+
+/* ===========================================================================
+ * Fill the input buffer. This is called only when the buffer is empty
+ * and at least one byte is really needed.
+ */
+static int fill_inbuf(void)
+{
+	error("ran out of input data");
+	return 0;
+}
+
+/* ===========================================================================
+ * Write the output window window[0..outcnt-1] and update crc and bytes_out.
+ * (Used for the decompressed data only.)
+ */
+static void flush_window(void)
+{
+	/* With my window equal to my output buffer
+	 * I only need to compute the crc here.
+	 */
+	ulg c = crc;         /* temporary variable */
+	unsigned n;
+	uch *in, ch;
+
+	in = window;
+	for (n = 0; n < outcnt; n++) {
+		ch = *in++;
+		c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
+	}
+	crc = c;
+	bytes_out += (ulg)outcnt;
+	outcnt = 0;
+}
+
+static void error(char *x)
+{
+	putstr("\n\n");
+	putstr(x);
+	putstr("\n\n -- System halted");
+
+	while(1);	/* Halt */
+}
+
+asmlinkage void decompress_kernel(void *rmode, unsigned long heap,
+	uch *input_data, unsigned long input_len, uch *output)
+{
+	real_mode = rmode;
+
+	if (RM_SCREEN_INFO.orig_video_mode == 7) {
+		vidmem = (char *) 0xb0000;
+		vidport = 0x3b4;
+	} else {
+		vidmem = (char *) 0xb8000;
+		vidport = 0x3d4;
+	}
+
+	lines = RM_SCREEN_INFO.orig_video_lines;
+	cols = RM_SCREEN_INFO.orig_video_cols;
+
+	window = output;  		/* Output buffer (Normally at 1M) */
+	free_mem_ptr     = heap;	/* Heap  */
+	free_mem_end_ptr = heap + HEAP_SIZE;
+	inbuf  = input_data;		/* Input buffer */
+	insize = input_len;
+	inptr  = 0;
+
+	if ((ulg)output & (__KERNEL_ALIGN - 1))
+		error("Destination address not 2M aligned");
+	if ((ulg)output >= 0xffffffffffUL)
+		error("Destination address too large");
+
+	makecrc();
+	putstr(".\nDecompressing Linux...");
+	gunzip();
+	putstr("done.\nBooting the kernel.\n");
+	return;
+}
diff --git a/arch/x86/boot/compressed/vmlinux_64.lds b/arch/x86/boot/compressed/vmlinux_64.lds
new file mode 100644
index 00000000000..94c13e557fb
--- /dev/null
+++ b/arch/x86/boot/compressed/vmlinux_64.lds
@@ -0,0 +1,44 @@
+OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
+OUTPUT_ARCH(i386:x86-64)
+ENTRY(startup_64)
+SECTIONS
+{
+	/* Be careful parts of head.S assume startup_32 is at
+ 	 * address 0.
+	 */
+	. = 0;
+	.text :	{
+		_head = . ;
+		*(.text.head)
+		_ehead = . ;
+		*(.text.compressed)
+		_text = .; 	/* Text */
+		*(.text)
+		*(.text.*)
+		_etext = . ;
+	}
+	.rodata : {
+		_rodata = . ;
+		*(.rodata)	 /* read-only data */
+		*(.rodata.*)
+		_erodata = . ;
+	}
+	.data :	{
+		_data = . ;
+		*(.data)
+		*(.data.*)
+		_edata = . ;
+	}
+	.bss : {
+		_bss = . ;
+		*(.bss)
+		*(.bss.*)
+		*(COMMON)
+		. = ALIGN(8);
+		_end = . ;
+		. = ALIGN(4096);
+		pgtable = . ;
+		. = . + 4096 * 6;
+		_heap = .;
+	}
+}
diff --git a/arch/x86/boot/compressed/vmlinux_64.scr b/arch/x86/boot/compressed/vmlinux_64.scr
new file mode 100644
index 00000000000..bd1429ce193
--- /dev/null
+++ b/arch/x86/boot/compressed/vmlinux_64.scr
@@ -0,0 +1,10 @@
+SECTIONS
+{
+  .text.compressed : {
+	input_len = .;
+	LONG(input_data_end - input_data) input_data = .;
+	*(.data)
+	output_len = . - 4;
+	input_data_end = .;
+	}
+}