[PATCH] x86-64: Relocatable Kernel Support

This patch modifies the x86_64 kernel so that it can be loaded and run
at any 2M aligned address, below 512G.  The technique used is to
compile the decompressor with -fPIC and modify it so the decompressor
is fully relocatable.  For the main kernel the page tables are
modified so the kernel remains at the same virtual address.  In
addition a variable phys_base is kept that holds the physical address
the kernel is loaded at.  __pa_symbol is modified to add that when
we take the address of a kernel symbol.

When loaded with a normal bootloader the decompressor will decompress
the kernel to 2M and it will run there.  This both ensures the
relocation code is always working, and makes it easier to use 2M
pages for the kernel and the cpu.

AK: changed to not make RELOCATABLE default in Kconfig

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>
diff --git a/arch/x86_64/boot/compressed/head.S b/arch/x86_64/boot/compressed/head.S
index 6f55565..c353a92 100644
--- a/arch/x86_64/boot/compressed/head.S
+++ b/arch/x86_64/boot/compressed/head.S
@@ -26,116 +26,262 @@
 
 #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,%fs
-	movl %eax,%gs
+	movl	$(__KERNEL_DS), %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	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.
+ */
+/* %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
 
 /*
- * 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.
+ * Prepare for entering 64 bit mode
  */
-	pushl $0
-	popfl
+
+	/* 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
+
+	/* 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 0x100
+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
+
+	/* 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
  */
-	xorl %eax,%eax
-	movl $_edata,%edi
-	movl $_end,%ecx
-	subl %edi,%ecx
+	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..
  */
-	subl $16,%esp	# place for structure on the stack
-	movl %esp,%eax
-	pushl %esi	# real mode pointer as second arg
-	pushl %eax	# address of structure as first arg
-	call decompress_kernel
-	orl  %eax,%eax 
-	jnz  3f
-	addl $8,%esp
-	xorl %ebx,%ebx
-	ljmp $(__KERNEL_CS), $__PHYSICAL_START
+	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
+
 
 /*
- * 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.
+ * Jump to the decompressed kernel.
  */
-3:
-	movl %esi,%ebx	
-	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
+	jmp	*%rbp
 
-	popl %esi	# discard the address
-	addl $4,%esp	# 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 $(__KERNEL_CS), $0x1000 # and jump to the move routine
-
-/*
- * Routine (template) for moving the decompressed kernel in place,
- * if we were high loaded. This _must_ PIC-code !
- */
-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 $(__KERNEL_CS), $__PHYSICAL_START
-move_routine_end:
-
-
-/* Stack for uncompression */ 	
-	.align 32
-user_stack:	 	
+	.data
+gdt:
+	.word	gdt_end - gdt
+	.long	gdt
+	.word	0
+	.quad	0x0000000000000000	/* NULL descriptor */
+	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
+	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
+gdt_end:
+	.bss
+/* Stack for uncompression */
+	.balign 4
+user_stack:
 	.fill 4096,4,0
-stack_start:	
-	.long user_stack+4096
-	.word __KERNEL_DS
-
+user_stack_end: