x86, relocs: Move ELF relocation handling to C

Moves the relocation handling into C, after decompression. This requires
that the decompressed size is passed to the decompression routine as
well so that relocations can be found. Only kernels that need relocation
support will use the code (currently just x86_32), but this is laying
the ground work for 64-bit using it in support of KASLR.

Based on work by Neill Clift and Michael Davidson.
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20130708161517.GA4832@www.outflux.netAcked-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

arch/x86/Kconfig

@@ -1716,9 +1716,10 @@ config X86_NEED_RELOCS
 	depends on X86_32 && RELOCATABLE
 
 config PHYSICAL_ALIGN
-	hex "Alignment value to which kernel should be aligned" if X86_32
+	hex "Alignment value to which kernel should be aligned"
 	default "0x1000000"
-	range 0x2000 0x1000000
+	range 0x2000 0x1000000 if X86_32
+	range 0x200000 0x1000000 if X86_64
 	---help---
 	  This value puts the alignment restrictions on physical address
 	  where kernel is loaded and run from. Kernel is compiled for an
@@ -1736,6 +1737,9 @@ config PHYSICAL_ALIGN
 	  end result is that kernel runs from a physical address meeting
 	  above alignment restrictions.
 
+	  On 32-bit this value must be a multiple of 0x2000. On 64-bit
+	  this value must be a multiple of 0x200000.
+
 	  Don't change this unless you know what you are doing.
 
 config HOTPLUG_CPU

arch/x86/Makefile

@@ -16,6 +16,10 @@ endif
 # e.g.: obj-y += foo_$(BITS).o
 export BITS
 
+ifdef CONFIG_X86_NEED_RELOCS
+        LDFLAGS_vmlinux := --emit-relocs
+endif
+
 ifeq ($(CONFIG_X86_32),y)
         BITS := 32
         UTS_MACHINE := i386
@@ -25,10 +29,6 @@ ifeq ($(CONFIG_X86_32),y)
         KBUILD_AFLAGS += $(biarch)
         KBUILD_CFLAGS += $(biarch)
 
-        ifdef CONFIG_RELOCATABLE
-                LDFLAGS_vmlinux := --emit-relocs
-        endif
-
         KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
 
         # Never want PIC in a 32-bit kernel, prevent breakage with GCC built

arch/x86/boot/compressed/head_32.S

@@ -181,8 +181,9 @@ relocated:
 /*
  * Do the decompression, and jump to the new kernel..
  */
-	leal	z_extract_offset_negative(%ebx), %ebp
 				/* push arguments for decompress_kernel: */
+	pushl	$z_output_len	/* decompressed length */
+	leal	z_extract_offset_negative(%ebx), %ebp
 	pushl	%ebp		/* output address */
 	pushl	$z_input_len	/* input_len */
 	leal	input_data(%ebx), %eax
@@ -191,33 +192,7 @@ relocated:
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
 	call	decompress_kernel
-	addl	$20, %esp
-
-#if CONFIG_RELOCATABLE
-/*
- * Find the address of the relocations.
- */
-	leal	z_output_len(%ebp), %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. */
-/*
- * Process relocations.
- */
-
-1:	subl	$4, %edi
-	movl	(%edi), %ecx
-	testl	%ecx, %ecx
-	jz	2f
-	addl	%ebx, -__PAGE_OFFSET(%ebx, %ecx)
-	jmp	1b
-2:
-#endif
+	addl	$24, %esp
 
 /*
  * Jump to the decompressed kernel.

arch/x86/boot/compressed/head_64.S

@@ -338,6 +338,7 @@ relocated:
 	leaq	input_data(%rip), %rdx  /* input_data */
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
+	movq	$z_output_len, %r9	/* decompressed length */
 	call	decompress_kernel
 	popq	%rsi
 

arch/x86/boot/compressed/misc.c

@@ -271,6 +271,79 @@ static void error(char *x)
 		asm("hlt");
 }
 
+#if CONFIG_X86_NEED_RELOCS
+static void handle_relocations(void *output, unsigned long output_len)
+{
+	int *reloc;
+	unsigned long delta, map, ptr;
+	unsigned long min_addr = (unsigned long)output;
+	unsigned long max_addr = min_addr + output_len;
+
+	/*
+	 * Calculate the delta between where vmlinux was linked to load
+	 * and where it was actually loaded.
+	 */
+	delta = min_addr - LOAD_PHYSICAL_ADDR;
+	if (!delta) {
+		debug_putstr("No relocation needed... ");
+		return;
+	}
+	debug_putstr("Performing relocations... ");
+
+	/*
+	 * The kernel contains a table of relocation addresses. Those
+	 * addresses have the final load address of the kernel in virtual
+	 * memory. We are currently working in the self map. So we need to
+	 * create an adjustment for kernel memory addresses to the self map.
+	 * This will involve subtracting out the base address of the kernel.
+	 */
+	map = delta - __START_KERNEL_map;
+
+	/*
+	 * Process relocations: 32 bit relocations first then 64 bit after.
+	 * Two sets of binary relocations are added to the end of the kernel
+	 * before compression. Each relocation table entry is the kernel
+	 * address of the location which needs to be updated stored as a
+	 * 32-bit value which is sign extended to 64 bits.
+	 *
+	 * Format is:
+	 *
+	 * kernel bits...
+	 * 0 - zero terminator for 64 bit relocations
+	 * 64 bit relocation repeated
+	 * 0 - zero terminator for 32 bit relocations
+	 * 32 bit relocation repeated
+	 *
+	 * So we work backwards from the end of the decompressed image.
+	 */
+	for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) {
+		int extended = *reloc;
+		extended += map;
+
+		ptr = (unsigned long)extended;
+		if (ptr < min_addr || ptr > max_addr)
+			error("32-bit relocation outside of kernel!\n");
+
+		*(uint32_t *)ptr += delta;
+	}
+#ifdef CONFIG_X86_64
+	for (reloc--; *reloc; reloc--) {
+		long extended = *reloc;
+		extended += map;
+
+		ptr = (unsigned long)extended;
+		if (ptr < min_addr || ptr > max_addr)
+			error("64-bit relocation outside of kernel!\n");
+
+		*(uint64_t *)ptr += delta;
+	}
+#endif
+}
+#else
+static inline void handle_relocations(void *output, unsigned long output_len)
+{ }
+#endif
+
 static void parse_elf(void *output)
 {
 #ifdef CONFIG_X86_64
@@ -325,7 +398,8 @@ static void parse_elf(void *output)
 asmlinkage void decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
-				  unsigned char *output)
+				  unsigned char *output,
+				  unsigned long output_len)
 {
 	real_mode = rmode;
 
@@ -365,6 +439,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	debug_putstr("\nDecompressing Linux... ");
 	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
 	parse_elf(output);
+	handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
 	return;
 }

arch/x86/include/asm/page_32_types.h

@@ -15,6 +15,8 @@
  */
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
+#define __START_KERNEL_map	__PAGE_OFFSET
+
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 

arch/x86/include/asm/page_64_types.h

@@ -32,11 +32,6 @@
  */
 #define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
 
-#define __PHYSICAL_START	((CONFIG_PHYSICAL_START +	 	\
-				  (CONFIG_PHYSICAL_ALIGN - 1)) &	\
-				 ~(CONFIG_PHYSICAL_ALIGN - 1))
-
-#define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */

arch/x86/include/asm/page_types.h

@@ -33,6 +33,11 @@
 	(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
 	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
+#define __PHYSICAL_START	ALIGN(CONFIG_PHYSICAL_START, \
+				      CONFIG_PHYSICAL_ALIGN)
+
+#define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
+
 #ifdef CONFIG_X86_64
 #include <asm/page_64_types.h>
 #else