[PATCH] i386: Relocatable kernel support

This patch modifies the i386 kernel so that if CONFIG_RELOCATABLE is
selected it will be able to be loaded at any 4K aligned address below
1G.  The technique used is to compile the decompressor with -fPIC and
modify it so the decompressor is fully relocatable.  For the main
kernel relocations are generated.  Resulting in a kernel that is relocatable
with no runtime overhead and no need to modify the source code.

A reserved 32bit word in the parameters has been assigned
to serve as a stack so we figure out where are running.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andi Kleen <ak@suse.de>

1 files changed, 117 insertions, 67 deletions

diff --git a/arch/i386/boot/compressed/head.S b/arch/i386/boot/compressed/head.S
index 40a8de8270a9..e4dd7a6b9b0f 100644
--- a/arch/i386/boot/compressed/head.S
+++ b/arch/i386/boot/compressed/head.S
@@ -25,9 +25,11 @@
 
 #include <linux/linkage.h>
 #include <asm/segment.h>
+#include <asm/page.h>
 
+.section ".text.head"
 	.globl startup_32
-	
+
 startup_32:
 	cld
 	cli
@@ -36,93 +38,141 @@ 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
+
+/* Compute the delta between where we were compiled to run at
+ * and where the code will actually run at.
+ */
+	/* Start with the delta to where the kernel will run at.  If we are
+	 * a relocatable kernel this is the delta to our load address otherwise
+	 * this is the delta to CONFIG_PHYSICAL start.
+	 */
+#ifdef CONFIG_RELOCATABLE
+	movl %ebp, %ebx
+#else
+	movl $(CONFIG_PHYSICAL_START - startup_32), %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
+	leal	startup_32(%ebp), %ebp
+#else
+	movl	$CONFIG_PHYSICAL_START, %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), $CONFIG_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 $CONFIG_PHYSICAL_START, %ebx
 
 /*
- * 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 $CONFIG_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), $CONFIG_PHYSICAL_START
-move_routine_end:
+	jmp *%ebp
+
+.bss
+.balign 4
+stack:
+	.fill 4096, 1, 0
+stack_end: