x86, kaslr: Return location from decompress_kernel

This allows decompress_kernel to return a new location for the kernel to
be relocated to. Additionally, enforces CONFIG_PHYSICAL_START as the
minimum relocation position when building with CONFIG_RELOCATABLE.

With CONFIG_RANDOMIZE_BASE set, the choose_kernel_location routine
will select a new location to decompress the kernel, though here it is
presently a no-op. The kernel command line option "nokaslr" is introduced
to bypass these routines.

Signed-off-by: Kees Cook <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: H. Peter Anvin <[e-mail]>

Documentation/kernel-parameters.txt

···
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
+	nokaslr		[X86]
+			Disable kernel base offset ASLR (Address Space
+			Layout Randomization) if built into the kernel.
+
 	noautogroup	Disable scheduler automatic task group creation.
 
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem

arch/x86/Kconfig

···
 
 	  Note: If CONFIG_RELOCATABLE=y, then the kernel runs from the address
 	  it has been loaded at and the compile time physical address
-	  (CONFIG_PHYSICAL_START) is ignored.
+	  (CONFIG_PHYSICAL_START) is used as the minimum location.
 
-# Relocation on x86-32 needs some additional build support
+config RANDOMIZE_BASE
+	bool "Randomize the address of the kernel image"
+	depends on RELOCATABLE
+	depends on !HIBERNATION
+	default n
+	---help---
+	   Randomizes the physical and virtual address at which the
+	   kernel image is decompressed, as a security feature that
+	   deters exploit attempts relying on knowledge of the location
+	   of kernel internals.
+
+	   Entropy is generated using the RDRAND instruction if it
+	   is supported.  If not, then RDTSC is used, if supported. If
+	   neither RDRAND nor RDTSC are supported, then no randomness
+	   is introduced.
+
+	   The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET,
+	   and aligned according to PHYSICAL_ALIGN.
+
+config RANDOMIZE_BASE_MAX_OFFSET
+	hex "Maximum ASLR offset allowed"
+	depends on RANDOMIZE_BASE
+	default "0x10000000"
+	range 0x0 0x10000000
+	---help---
+	 Determines the maximal offset in bytes that will be applied to the
+	 kernel when Address Space Layout Randomization (ASLR) is active.
+	 Must be less than or equal to the actual physical memory on the
+	 system. This must be a power of two.
+
+# Relocation on x86 needs some additional build support
 config X86_NEED_RELOCS
 	def_bool y
-	depends on X86_32 && RELOCATABLE
+	depends on RANDOMIZE_BASE || (X86_32 && RELOCATABLE)
 
 config PHYSICAL_ALIGN
 	hex "Alignment value to which kernel should be aligned"
-	default "0x1000000"
+	default "0x200000"
 	range 0x2000 0x1000000 if X86_32
 	range 0x200000 0x1000000 if X86_64
 	---help---

arch/x86/boot/compressed/Makefile

···
 
 VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
 	$(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
-	$(obj)/piggy.o $(obj)/cpuflags.o
+	$(obj)/piggy.o $(obj)/cpuflags.o $(obj)/aslr.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 

arch/x86/boot/compressed/aslr.c

···
+#include "misc.h"
+
+#ifdef CONFIG_RANDOMIZE_BASE
+
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size)
+{
+	unsigned long choice = (unsigned long)output;
+
+	if (cmdline_find_option_bool("nokaslr")) {
+		debug_putstr("KASLR disabled...\n");
+		goto out;
+	}
+
+	/* XXX: choose random location. */
+
+out:
+	return (unsigned char *)choice;
+}
+
+#endif /* CONFIG_RANDOMIZE_BASE */

arch/x86/boot/compressed/cmdline.c

···
 #include "misc.h"
 
-#ifdef CONFIG_EARLY_PRINTK
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
 
 static unsigned long fs;
 static inline void set_fs(unsigned long seg)

arch/x86/boot/compressed/head_32.S

···
 	addl    %eax, %ebx
 	notl	%eax
 	andl    %eax, %ebx
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebx
+	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
+	jge	1f
 #endif
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
+1:
 
 	/* Target address to relocate to for decompression */
 	addl	$z_extract_offset, %ebx
···
 	leal	boot_heap(%ebx), %eax
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
-	call	decompress_kernel
+	call	decompress_kernel /* returns kernel location in %eax */
 	addl	$24, %esp
 
 /*
  * Jump to the decompressed kernel.
  */
 	xorl	%ebx, %ebx
-	jmp	*%ebp
+	jmp	*%eax
 
 /*
  * Stack and heap for uncompression

arch/x86/boot/compressed/head_64.S

···
 	addl	%eax, %ebx
 	notl	%eax
 	andl	%eax, %ebx
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebx
+	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
+	jge	1f
 #endif
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
+1:
 
 	/* Target address to relocate to for decompression */
 	addl	$z_extract_offset, %ebx
···
 	addq	%rax, %rbp
 	notq	%rax
 	andq	%rax, %rbp
-#else
-	movq	$LOAD_PHYSICAL_ADDR, %rbp
+	cmpq	$LOAD_PHYSICAL_ADDR, %rbp
+	jge	1f
 #endif
+	movq	$LOAD_PHYSICAL_ADDR, %rbp
+1:
 
 	/* Target address to relocate to for decompression */
 	leaq	z_extract_offset(%rbp), %rbx
···
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
 	movq	$z_output_len, %r9	/* decompressed length */
-	call	decompress_kernel
+	call	decompress_kernel	/* returns kernel location in %rax */
 	popq	%rsi
 
 /*
  * Jump to the decompressed kernel.
  */
-	jmp	*%rbp
+	jmp	*%rax
 
 	.code32
 no_longmode:

arch/x86/boot/compressed/misc.c

···
 	free(phdrs);
 }
 
-asmlinkage void decompress_kernel(void *rmode, memptr heap,
+asmlinkage void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
···
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	output = choose_kernel_location(input_data, input_len,
+					output, output_len);
+
+	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
 		error("Destination address inappropriately aligned");
 #ifdef CONFIG_X86_64
···
 	parse_elf(output);
 	handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
-	return;
+	return output;
 }

arch/x86/boot/compressed/misc.h

···
 
 #endif
 
-#ifdef CONFIG_EARLY_PRINTK
-
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
 /* cmdline.c */
 int cmdline_find_option(const char *option, char *buffer, int bufsize);
 int cmdline_find_option_bool(const char *option);
+#endif
 
+
+#if CONFIG_RANDOMIZE_BASE
+/* aslr.c */
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size);
+#else
+static inline
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size)
+{
+	return output;
+}
+#endif
+
+#ifdef CONFIG_EARLY_PRINTK
 /* early_serial_console.c */
 extern int early_serial_base;
 void console_init(void);
-
 #else
-
-/* early_serial_console.c */
 static const int early_serial_base;
 static inline void console_init(void)
 { }
-
 #endif
 
 #endif