Merge branch 'x86-kaslr-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 kernel address space randomization support from Peter Anvin:
 "This enables kernel address space randomization for x86"

* 'x86-kaslr-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, kaslr: Clarify RANDOMIZE_BASE_MAX_OFFSET
  x86, kaslr: Remove unused including <linux/version.h>
  x86, kaslr: Use char array to gain sizeof sanity
  x86, kaslr: Add a circular multiply for better bit diffusion
  x86, kaslr: Mix entropy sources together as needed
  x86/relocs: Add percpu fixup for GNU ld 2.23
  x86, boot: Rename get_flags() and check_flags() to *_cpuflags()
  x86, kaslr: Raise the maximum virtual address to -1 GiB on x86_64
  x86, kaslr: Report kernel offset on panic
  x86, kaslr: Select random position from e820 maps
  x86, kaslr: Provide randomness functions
  x86, kaslr: Return location from decompress_kernel
  x86, boot: Move CPU flags out of cpucheck
  x86, relocs: Add more per-cpu gold special cases

8 files changed, 385 insertions, 28 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index c8a6792e7842..0fcd9133790c 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -28,7 +28,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
 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)/piggy.o $(obj)/cpuflags.o $(obj)/aslr.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
new file mode 100644
index 000000000000..90a21f430117
--- /dev/null
+++ b/arch/x86/boot/compressed/aslr.c
@@ -0,0 +1,316 @@
+#include "misc.h"
+
+#ifdef CONFIG_RANDOMIZE_BASE
+#include <asm/msr.h>
+#include <asm/archrandom.h>
+#include <asm/e820.h>
+
+#include <generated/compile.h>
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <generated/utsrelease.h>
+
+/* Simplified build-specific string for starting entropy. */
+static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+
+#define I8254_PORT_CONTROL	0x43
+#define I8254_PORT_COUNTER0	0x40
+#define I8254_CMD_READBACK	0xC0
+#define I8254_SELECT_COUNTER0	0x02
+#define I8254_STATUS_NOTREADY	0x40
+static inline u16 i8254(void)
+{
+	u16 status, timer;
+
+	do {
+		outb(I8254_PORT_CONTROL,
+		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		status = inb(I8254_PORT_COUNTER0);
+		timer  = inb(I8254_PORT_COUNTER0);
+		timer |= inb(I8254_PORT_COUNTER0) << 8;
+	} while (status & I8254_STATUS_NOTREADY);
+
+	return timer;
+}
+
+static unsigned long rotate_xor(unsigned long hash, const void *area,
+				size_t size)
+{
+	size_t i;
+	unsigned long *ptr = (unsigned long *)area;
+
+	for (i = 0; i < size / sizeof(hash); i++) {
+		/* Rotate by odd number of bits and XOR. */
+		hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
+		hash ^= ptr[i];
+	}
+
+	return hash;
+}
+
+/* Attempt to create a simple but unpredictable starting entropy. */
+static unsigned long get_random_boot(void)
+{
+	unsigned long hash = 0;
+
+	hash = rotate_xor(hash, build_str, sizeof(build_str));
+	hash = rotate_xor(hash, real_mode, sizeof(*real_mode));
+
+	return hash;
+}
+
+static unsigned long get_random_long(void)
+{
+#ifdef CONFIG_X86_64
+	const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
+#else
+	const unsigned long mix_const = 0x3f39e593UL;
+#endif
+	unsigned long raw, random = get_random_boot();
+	bool use_i8254 = true;
+
+	debug_putstr("KASLR using");
+
+	if (has_cpuflag(X86_FEATURE_RDRAND)) {
+		debug_putstr(" RDRAND");
+		if (rdrand_long(&raw)) {
+			random ^= raw;
+			use_i8254 = false;
+		}
+	}
+
+	if (has_cpuflag(X86_FEATURE_TSC)) {
+		debug_putstr(" RDTSC");
+		rdtscll(raw);
+
+		random ^= raw;
+		use_i8254 = false;
+	}
+
+	if (use_i8254) {
+		debug_putstr(" i8254");
+		random ^= i8254();
+	}
+
+	/* Circular multiply for better bit diffusion */
+	asm("mul %3"
+	    : "=a" (random), "=d" (raw)
+	    : "a" (random), "rm" (mix_const));
+	random += raw;
+
+	debug_putstr("...\n");
+
+	return random;
+}
+
+struct mem_vector {
+	unsigned long start;
+	unsigned long size;
+};
+
+#define MEM_AVOID_MAX 5
+struct mem_vector mem_avoid[MEM_AVOID_MAX];
+
+static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
+{
+	/* Item at least partially before region. */
+	if (item->start < region->start)
+		return false;
+	/* Item at least partially after region. */
+	if (item->start + item->size > region->start + region->size)
+		return false;
+	return true;
+}
+
+static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
+{
+	/* Item one is entirely before item two. */
+	if (one->start + one->size <= two->start)
+		return false;
+	/* Item one is entirely after item two. */
+	if (one->start >= two->start + two->size)
+		return false;
+	return true;
+}
+
+static void mem_avoid_init(unsigned long input, unsigned long input_size,
+			   unsigned long output, unsigned long output_size)
+{
+	u64 initrd_start, initrd_size;
+	u64 cmd_line, cmd_line_size;
+	unsigned long unsafe, unsafe_len;
+	char *ptr;
+
+	/*
+	 * Avoid the region that is unsafe to overlap during
+	 * decompression (see calculations at top of misc.c).
+	 */
+	unsafe_len = (output_size >> 12) + 32768 + 18;
+	unsafe = (unsigned long)input + input_size - unsafe_len;
+	mem_avoid[0].start = unsafe;
+	mem_avoid[0].size = unsafe_len;
+
+	/* Avoid initrd. */
+	initrd_start  = (u64)real_mode->ext_ramdisk_image << 32;
+	initrd_start |= real_mode->hdr.ramdisk_image;
+	initrd_size  = (u64)real_mode->ext_ramdisk_size << 32;
+	initrd_size |= real_mode->hdr.ramdisk_size;
+	mem_avoid[1].start = initrd_start;
+	mem_avoid[1].size = initrd_size;
+
+	/* Avoid kernel command line. */
+	cmd_line  = (u64)real_mode->ext_cmd_line_ptr << 32;
+	cmd_line |= real_mode->hdr.cmd_line_ptr;
+	/* Calculate size of cmd_line. */
+	ptr = (char *)(unsigned long)cmd_line;
+	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
+		;
+	mem_avoid[2].start = cmd_line;
+	mem_avoid[2].size = cmd_line_size;
+
+	/* Avoid heap memory. */
+	mem_avoid[3].start = (unsigned long)free_mem_ptr;
+	mem_avoid[3].size = BOOT_HEAP_SIZE;
+
+	/* Avoid stack memory. */
+	mem_avoid[4].start = (unsigned long)free_mem_end_ptr;
+	mem_avoid[4].size = BOOT_STACK_SIZE;
+}
+
+/* Does this memory vector overlap a known avoided area? */
+bool mem_avoid_overlap(struct mem_vector *img)
+{
+	int i;
+
+	for (i = 0; i < MEM_AVOID_MAX; i++) {
+		if (mem_overlaps(img, &mem_avoid[i]))
+			return true;
+	}
+
+	return false;
+}
+
+unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
+unsigned long slot_max = 0;
+
+static void slots_append(unsigned long addr)
+{
+	/* Overflowing the slots list should be impossible. */
+	if (slot_max >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			CONFIG_PHYSICAL_ALIGN)
+		return;
+
+	slots[slot_max++] = addr;
+}
+
+static unsigned long slots_fetch_random(void)
+{
+	/* Handle case of no slots stored. */
+	if (slot_max == 0)
+		return 0;
+
+	return slots[get_random_long() % slot_max];
+}
+
+static void process_e820_entry(struct e820entry *entry,
+			       unsigned long minimum,
+			       unsigned long image_size)
+{
+	struct mem_vector region, img;
+
+	/* Skip non-RAM entries. */
+	if (entry->type != E820_RAM)
+		return;
+
+	/* Ignore entries entirely above our maximum. */
+	if (entry->addr >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+		return;
+
+	/* Ignore entries entirely below our minimum. */
+	if (entry->addr + entry->size < minimum)
+		return;
+
+	region.start = entry->addr;
+	region.size = entry->size;
+
+	/* Potentially raise address to minimum location. */
+	if (region.start < minimum)
+		region.start = minimum;
+
+	/* Potentially raise address to meet alignment requirements. */
+	region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
+
+	/* Did we raise the address above the bounds of this e820 region? */
+	if (region.start > entry->addr + entry->size)
+		return;
+
+	/* Reduce size by any delta from the original address. */
+	region.size -= region.start - entry->addr;
+
+	/* Reduce maximum size to fit end of image within maximum limit. */
+	if (region.start + region.size > CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+		region.size = CONFIG_RANDOMIZE_BASE_MAX_OFFSET - region.start;
+
+	/* Walk each aligned slot and check for avoided areas. */
+	for (img.start = region.start, img.size = image_size ;
+	     mem_contains(&region, &img) ;
+	     img.start += CONFIG_PHYSICAL_ALIGN) {
+		if (mem_avoid_overlap(&img))
+			continue;
+		slots_append(img.start);
+	}
+}
+
+static unsigned long find_random_addr(unsigned long minimum,
+				      unsigned long size)
+{
+	int i;
+	unsigned long addr;
+
+	/* Make sure minimum is aligned. */
+	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+
+	/* Verify potential e820 positions, appending to slots list. */
+	for (i = 0; i < real_mode->e820_entries; i++) {
+		process_e820_entry(&real_mode->e820_map[i], minimum, size);
+	}
+
+	return slots_fetch_random();
+}
+
+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;
+	unsigned long random;
+
+	if (cmdline_find_option_bool("nokaslr")) {
+		debug_putstr("KASLR disabled...\n");
+		goto out;
+	}
+
+	/* Record the various known unsafe memory ranges. */
+	mem_avoid_init((unsigned long)input, input_size,
+		       (unsigned long)output, output_size);
+
+	/* Walk e820 and find a random address. */
+	random = find_random_addr(choice, output_size);
+	if (!random) {
+		debug_putstr("KASLR could not find suitable E820 region...\n");
+		goto out;
+	}
+
+	/* Always enforce the minimum. */
+	if (random < choice)
+		goto out;
+
+	choice = random;
+out:
+	return (unsigned char *)choice;
+}
+
+#endif /* CONFIG_RANDOMIZE_BASE */
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index bffd73b45b1f..b68e3033e6b9 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,6 +1,6 @@
 #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)
diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c
new file mode 100644
index 000000000000..aa313466118b
--- /dev/null
+++ b/arch/x86/boot/compressed/cpuflags.c
@@ -0,0 +1,12 @@
+#ifdef CONFIG_RANDOMIZE_BASE
+
+#include "../cpuflags.c"
+
+bool has_cpuflag(int flag)
+{
+	get_cpuflags();
+
+	return test_bit(flag, cpu.flags);
+}
+
+#endif
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 5d6f6891b188..9116aac232c7 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -117,9 +117,11 @@ preferred_addr:
 	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
@@ -191,14 +193,14 @@ relocated:
 	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
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index c337422b575d..c5c1ae0997e7 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -94,9 +94,11 @@ ENTRY(startup_32)
 	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
@@ -269,9 +271,11 @@ preferred_addr:
 	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
@@ -339,13 +343,13 @@ relocated:
 	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:
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 434f077d2c4d..196eaf373a06 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -112,14 +112,8 @@ struct boot_params *real_mode;		/* Pointer to real-mode data */
 void *memset(void *s, int c, size_t n);
 void *memcpy(void *dest, const void *src, size_t n);
 
-#ifdef CONFIG_X86_64
-#define memptr long
-#else
-#define memptr unsigned
-#endif
-
-static memptr free_mem_ptr;
-static memptr free_mem_end_ptr;
+memptr free_mem_ptr;
+memptr free_mem_end_ptr;
 
 static char *vidmem;
 static int vidport;
@@ -395,7 +389,7 @@ static void parse_elf(void *output)
 	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,
@@ -422,6 +416,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	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
@@ -441,5 +439,5 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	parse_elf(output);
 	handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
-	return;
+	return output;
 }
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 674019d8e235..24e3e569a13c 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -23,7 +23,15 @@
 #define BOOT_BOOT_H
 #include "../ctype.h"
 
+#ifdef CONFIG_X86_64
+#define memptr long
+#else
+#define memptr unsigned
+#endif
+
 /* misc.c */
+extern memptr free_mem_ptr;
+extern memptr free_mem_end_ptr;
 extern struct boot_params *real_mode;		/* Pointer to real-mode data */
 void __putstr(const char *s);
 #define error_putstr(__x)  __putstr(__x)
@@ -39,23 +47,40 @@ static inline void debug_putstr(const char *s)
 
 #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
 
-/* early_serial_console.c */
-extern int early_serial_base;
-void console_init(void);
 
+#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);
+/* cpuflags.c */
+bool has_cpuflag(int flag);
 #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
 static const int early_serial_base;
 static inline void console_init(void)
 { }
-
 #endif
 
 #endif