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

Pull x86 boot updates from Ingo Molnar:
 "The biggest changes in this cycle were:

   - prepare for more KASLR related changes, by restructuring, cleaning
     up and fixing the existing boot code.  (Kees Cook, Baoquan He,
     Yinghai Lu)

   - simplifly/concentrate subarch handling code, eliminate
     paravirt_enabled() usage.  (Luis R Rodriguez)"

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  x86/KASLR: Clarify purpose of each get_random_long()
  x86/KASLR: Add virtual address choosing function
  x86/KASLR: Return earliest overlap when avoiding regions
  x86/KASLR: Add 'struct slot_area' to manage random_addr slots
  x86/boot: Add missing file header comments
  x86/KASLR: Initialize mapping_info every time
  x86/boot: Comment what finalize_identity_maps() does
  x86/KASLR: Build identity mappings on demand
  x86/boot: Split out kernel_ident_mapping_init()
  x86/boot: Clean up indenting for asm/boot.h
  x86/KASLR: Improve comments around the mem_avoid[] logic
  x86/boot: Simplify pointer casting in choose_random_location()
  x86/KASLR: Consolidate mem_avoid[] entries
  x86/boot: Clean up pointer casting
  x86/boot: Warn on future overlapping memcpy() use
  x86/boot: Extract error reporting functions
  x86/boot: Correctly bounds-check relocations
  x86/KASLR: Clean up unused code from old 'run_size' and rename it to 'kernel_total_size'
  x86/boot: Fix "run_size" calculation
  x86/boot: Calculate decompression size during boot not build
  ...

14 files changed, 835 insertions, 527 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 8774cb23064f..cfdd8c3f8af2 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -57,12 +57,27 @@ LDFLAGS_vmlinux := -T
 hostprogs-y	:= mkpiggy
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
+
+quiet_cmd_voffset = VOFFSET $@
+      cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
+
+targets += ../voffset.h
+
+$(obj)/../voffset.h: vmlinux FORCE
+	$(call if_changed,voffset)
+
+$(obj)/misc.o: $(obj)/../voffset.h
+
 vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
-	$(obj)/string.o $(obj)/cmdline.o \
+	$(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \
 	$(obj)/piggy.o $(obj)/cpuflags.o
 
 vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o
-vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/aslr.o
+vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o
+ifdef CONFIG_X86_64
+	vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o
+endif
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
@@ -109,10 +124,8 @@ suffix-$(CONFIG_KERNEL_XZ)	:= xz
 suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
 
-RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
-	     $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh)
 quiet_cmd_mkpiggy = MKPIGGY $@
-      cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
+      cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
 
 targets += piggy.S
 $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
deleted file mode 100644
index 6a9b96b4624d..000000000000
--- a/arch/x86/boot/compressed/aslr.c
+++ /dev/null
@@ -1,339 +0,0 @@
-#include "misc.h"
-
-#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");
-		raw = rdtsc();
-
-		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
-static 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? */
-static bool mem_avoid_overlap(struct mem_vector *img)
-{
-	int i;
-	struct setup_data *ptr;
-
-	for (i = 0; i < MEM_AVOID_MAX; i++) {
-		if (mem_overlaps(img, &mem_avoid[i]))
-			return true;
-	}
-
-	/* Avoid all entries in the setup_data linked list. */
-	ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data;
-	while (ptr) {
-		struct mem_vector avoid;
-
-		avoid.start = (unsigned long)ptr;
-		avoid.size = sizeof(*ptr) + ptr->len;
-
-		if (mem_overlaps(img, &avoid))
-			return true;
-
-		ptr = (struct setup_data *)(unsigned long)ptr->next;
-	}
-
-	return false;
-}
-
-static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
-			   CONFIG_PHYSICAL_ALIGN];
-static unsigned long slot_max;
-
-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(struct boot_params *boot_params,
-				      unsigned char *input,
-				      unsigned long input_size,
-				      unsigned char *output,
-				      unsigned long output_size)
-{
-	unsigned long choice = (unsigned long)output;
-	unsigned long random;
-
-#ifdef CONFIG_HIBERNATION
-	if (!cmdline_find_option_bool("kaslr")) {
-		debug_putstr("KASLR disabled by default...\n");
-		goto out;
-	}
-#else
-	if (cmdline_find_option_bool("nokaslr")) {
-		debug_putstr("KASLR disabled by cmdline...\n");
-		goto out;
-	}
-#endif
-
-	boot_params->hdr.loadflags |= KASLR_FLAG;
-
-	/* 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;
-}
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index b68e3033e6b9..73ccf63b0f48 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -15,9 +15,9 @@ static inline char rdfs8(addr_t addr)
 #include "../cmdline.c"
 static unsigned long get_cmd_line_ptr(void)
 {
-	unsigned long cmd_line_ptr = real_mode->hdr.cmd_line_ptr;
+	unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr;
 
-	cmd_line_ptr |= (u64)real_mode->ext_cmd_line_ptr << 32;
+	cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32;
 
 	return cmd_line_ptr;
 }
diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c
new file mode 100644
index 000000000000..6248740b68b5
--- /dev/null
+++ b/arch/x86/boot/compressed/error.c
@@ -0,0 +1,22 @@
+/*
+ * Callers outside of misc.c need access to the error reporting routines,
+ * but the *_putstr() functions need to stay in misc.c because of how
+ * memcpy() and memmove() are defined for the compressed boot environment.
+ */
+#include "misc.h"
+
+void warn(char *m)
+{
+	error_putstr("\n\n");
+	error_putstr(m);
+	error_putstr("\n\n");
+}
+
+void error(char *m)
+{
+	warn(m);
+	error_putstr(" -- System halted");
+
+	while (1)
+		asm("hlt");
+}
diff --git a/arch/x86/boot/compressed/error.h b/arch/x86/boot/compressed/error.h
new file mode 100644
index 000000000000..2e59dac07f9e
--- /dev/null
+++ b/arch/x86/boot/compressed/error.h
@@ -0,0 +1,7 @@
+#ifndef BOOT_COMPRESSED_ERROR_H
+#define BOOT_COMPRESSED_ERROR_H
+
+void warn(char *m);
+void error(char *m);
+
+#endif /* BOOT_COMPRESSED_ERROR_H */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 0256064da8da..1038524270e7 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -176,7 +176,9 @@ preferred_addr:
 1:
 
 	/* Target address to relocate to for decompression */
-	addl	$z_extract_offset, %ebx
+	movl    BP_init_size(%esi), %eax
+	subl    $_end, %eax
+	addl    %eax, %ebx
 
 	/* Set up the stack */
 	leal	boot_stack_end(%ebx), %esp
@@ -233,24 +235,28 @@ relocated:
 2:
 
 /*
- * Do the decompression, and jump to the new kernel..
+ * Do the extraction, and jump to the new kernel..
  */
-				/* push arguments for decompress_kernel: */
-	pushl	$z_run_size	/* size of kernel with .bss and .brk */
+				/* push arguments for extract_kernel: */
 	pushl	$z_output_len	/* decompressed length, end of relocs */
-	leal	z_extract_offset_negative(%ebx), %ebp
+
+	movl    BP_init_size(%esi), %eax
+	subl    $_end, %eax
+	movl    %ebx, %ebp
+	subl    %eax, %ebp
 	pushl	%ebp		/* output address */
+
 	pushl	$z_input_len	/* input_len */
 	leal	input_data(%ebx), %eax
 	pushl	%eax		/* input_data */
 	leal	boot_heap(%ebx), %eax
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
-	call	decompress_kernel /* returns kernel location in %eax */
-	addl	$28, %esp
+	call	extract_kernel	/* returns kernel location in %eax */
+	addl	$24, %esp
 
 /*
- * Jump to the decompressed kernel.
+ * Jump to the extracted kernel.
  */
 	xorl	%ebx, %ebx
 	jmp	*%eax
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 86558a199139..0d80a7ad65cd 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -110,7 +110,9 @@ ENTRY(startup_32)
 1:
 
 	/* Target address to relocate to for decompression */
-	addl	$z_extract_offset, %ebx
+	movl	BP_init_size(%esi), %eax
+	subl	$_end, %eax
+	addl	%eax, %ebx
 
 /*
  * Prepare for entering 64 bit mode
@@ -132,7 +134,7 @@ ENTRY(startup_32)
 	/* Initialize Page tables to 0 */
 	leal	pgtable(%ebx), %edi
 	xorl	%eax, %eax
-	movl	$((4096*6)/4), %ecx
+	movl	$(BOOT_INIT_PGT_SIZE/4), %ecx
 	rep	stosl
 
 	/* Build Level 4 */
@@ -338,7 +340,9 @@ preferred_addr:
 1:
 
 	/* Target address to relocate to for decompression */
-	leaq	z_extract_offset(%rbp), %rbx
+	movl	BP_init_size(%rsi), %ebx
+	subl	$_end, %ebx
+	addq	%rbp, %rbx
 
 	/* Set up the stack */
 	leaq	boot_stack_end(%rbx), %rsp
@@ -408,19 +412,16 @@ relocated:
 2:
 	
 /*
- * Do the decompression, and jump to the new kernel..
+ * Do the extraction, and jump to the new kernel..
  */
 	pushq	%rsi			/* Save the real mode argument */
-	movq	$z_run_size, %r9	/* size of kernel with .bss and .brk */
-	pushq	%r9
 	movq	%rsi, %rdi		/* real mode address */
 	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
 	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, end of relocs */
-	call	decompress_kernel	/* returns kernel location in %rax */
-	popq	%r9
+	call	extract_kernel		/* returns kernel location in %rax */
 	popq	%rsi
 
 /*
@@ -485,4 +486,4 @@ boot_stack_end:
 	.section ".pgtable","a",@nobits
 	.balign 4096
 pgtable:
-	.fill 6*4096, 1, 0
+	.fill BOOT_PGT_SIZE, 1, 0
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
new file mode 100644
index 000000000000..cfeb0259ed81
--- /dev/null
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -0,0 +1,510 @@
+/*
+ * kaslr.c
+ *
+ * This contains the routines needed to generate a reasonable level of
+ * entropy to choose a randomized kernel base address offset in support
+ * of Kernel Address Space Layout Randomization (KASLR). Additionally
+ * handles walking the physical memory maps (and tracking memory regions
+ * to avoid) in order to select a physical memory location that can
+ * contain the entire properly aligned running kernel image.
+ *
+ */
+#include "misc.h"
+#include "error.h"
+
+#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, boot_params, sizeof(*boot_params));
+
+	return hash;
+}
+
+static unsigned long get_random_long(const char *purpose)
+{
+#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(purpose);
+	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");
+		raw = rdtsc();
+
+		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;
+};
+
+enum mem_avoid_index {
+	MEM_AVOID_ZO_RANGE = 0,
+	MEM_AVOID_INITRD,
+	MEM_AVOID_CMDLINE,
+	MEM_AVOID_BOOTPARAMS,
+	MEM_AVOID_MAX,
+};
+
+static 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;
+}
+
+/*
+ * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
+ * The mem_avoid array is used to store the ranges that need to be avoided
+ * when KASLR searches for an appropriate random address. We must avoid any
+ * regions that are unsafe to overlap with during decompression, and other
+ * things like the initrd, cmdline and boot_params. This comment seeks to
+ * explain mem_avoid as clearly as possible since incorrect mem_avoid
+ * memory ranges lead to really hard to debug boot failures.
+ *
+ * The initrd, cmdline, and boot_params are trivial to identify for
+ * avoiding. They are MEM_AVOID_INITRD, MEM_AVOID_CMDLINE, and
+ * MEM_AVOID_BOOTPARAMS respectively below.
+ *
+ * What is not obvious how to avoid is the range of memory that is used
+ * during decompression (MEM_AVOID_ZO_RANGE below). This range must cover
+ * the compressed kernel (ZO) and its run space, which is used to extract
+ * the uncompressed kernel (VO) and relocs.
+ *
+ * ZO's full run size sits against the end of the decompression buffer, so
+ * we can calculate where text, data, bss, etc of ZO are positioned more
+ * easily.
+ *
+ * For additional background, the decompression calculations can be found
+ * in header.S, and the memory diagram is based on the one found in misc.c.
+ *
+ * The following conditions are already enforced by the image layouts and
+ * associated code:
+ *  - input + input_size >= output + output_size
+ *  - kernel_total_size <= init_size
+ *  - kernel_total_size <= output_size (see Note below)
+ *  - output + init_size >= output + output_size
+ *
+ * (Note that kernel_total_size and output_size have no fundamental
+ * relationship, but output_size is passed to choose_random_location
+ * as a maximum of the two. The diagram is showing a case where
+ * kernel_total_size is larger than output_size, but this case is
+ * handled by bumping output_size.)
+ *
+ * The above conditions can be illustrated by a diagram:
+ *
+ * 0   output            input            input+input_size    output+init_size
+ * |     |                 |                             |             |
+ * |     |                 |                             |             |
+ * |-----|--------|--------|--------------|-----------|--|-------------|
+ *                |                       |           |
+ *                |                       |           |
+ * output+init_size-ZO_INIT_SIZE  output+output_size  output+kernel_total_size
+ *
+ * [output, output+init_size) is the entire memory range used for
+ * extracting the compressed image.
+ *
+ * [output, output+kernel_total_size) is the range needed for the
+ * uncompressed kernel (VO) and its run size (bss, brk, etc).
+ *
+ * [output, output+output_size) is VO plus relocs (i.e. the entire
+ * uncompressed payload contained by ZO). This is the area of the buffer
+ * written to during decompression.
+ *
+ * [output+init_size-ZO_INIT_SIZE, output+init_size) is the worst-case
+ * range of the copied ZO and decompression code. (i.e. the range
+ * covered backwards of size ZO_INIT_SIZE, starting from output+init_size.)
+ *
+ * [input, input+input_size) is the original copied compressed image (ZO)
+ * (i.e. it does not include its run size). This range must be avoided
+ * because it contains the data used for decompression.
+ *
+ * [input+input_size, output+init_size) is [_text, _end) for ZO. This
+ * range includes ZO's heap and stack, and must be avoided since it
+ * performs the decompression.
+ *
+ * Since the above two ranges need to be avoided and they are adjacent,
+ * they can be merged, resulting in: [input, output+init_size) which
+ * becomes the MEM_AVOID_ZO_RANGE below.
+ */
+static void mem_avoid_init(unsigned long input, unsigned long input_size,
+			   unsigned long output)
+{
+	unsigned long init_size = boot_params->hdr.init_size;
+	u64 initrd_start, initrd_size;
+	u64 cmd_line, cmd_line_size;
+	char *ptr;
+
+	/*
+	 * Avoid the region that is unsafe to overlap during
+	 * decompression.
+	 */
+	mem_avoid[MEM_AVOID_ZO_RANGE].start = input;
+	mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input;
+	add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start,
+			 mem_avoid[MEM_AVOID_ZO_RANGE].size);
+
+	/* Avoid initrd. */
+	initrd_start  = (u64)boot_params->ext_ramdisk_image << 32;
+	initrd_start |= boot_params->hdr.ramdisk_image;
+	initrd_size  = (u64)boot_params->ext_ramdisk_size << 32;
+	initrd_size |= boot_params->hdr.ramdisk_size;
+	mem_avoid[MEM_AVOID_INITRD].start = initrd_start;
+	mem_avoid[MEM_AVOID_INITRD].size = initrd_size;
+	/* No need to set mapping for initrd, it will be handled in VO. */
+
+	/* Avoid kernel command line. */
+	cmd_line  = (u64)boot_params->ext_cmd_line_ptr << 32;
+	cmd_line |= boot_params->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[MEM_AVOID_CMDLINE].start = cmd_line;
+	mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
+	add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start,
+			 mem_avoid[MEM_AVOID_CMDLINE].size);
+
+	/* Avoid boot parameters. */
+	mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params;
+	mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params);
+	add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start,
+			 mem_avoid[MEM_AVOID_BOOTPARAMS].size);
+
+	/* We don't need to set a mapping for setup_data. */
+
+#ifdef CONFIG_X86_VERBOSE_BOOTUP
+	/* Make sure video RAM can be used. */
+	add_identity_map(0, PMD_SIZE);
+#endif
+}
+
+/*
+ * Does this memory vector overlap a known avoided area? If so, record the
+ * overlap region with the lowest address.
+ */
+static bool mem_avoid_overlap(struct mem_vector *img,
+			      struct mem_vector *overlap)
+{
+	int i;
+	struct setup_data *ptr;
+	unsigned long earliest = img->start + img->size;
+	bool is_overlapping = false;
+
+	for (i = 0; i < MEM_AVOID_MAX; i++) {
+		if (mem_overlaps(img, &mem_avoid[i]) &&
+		    mem_avoid[i].start < earliest) {
+			*overlap = mem_avoid[i];
+			is_overlapping = true;
+		}
+	}
+
+	/* Avoid all entries in the setup_data linked list. */
+	ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
+	while (ptr) {
+		struct mem_vector avoid;
+
+		avoid.start = (unsigned long)ptr;
+		avoid.size = sizeof(*ptr) + ptr->len;
+
+		if (mem_overlaps(img, &avoid) && (avoid.start < earliest)) {
+			*overlap = avoid;
+			is_overlapping = true;
+		}
+
+		ptr = (struct setup_data *)(unsigned long)ptr->next;
+	}
+
+	return is_overlapping;
+}
+
+static unsigned long slots[KERNEL_IMAGE_SIZE / CONFIG_PHYSICAL_ALIGN];
+
+struct slot_area {
+	unsigned long addr;
+	int num;
+};
+
+#define MAX_SLOT_AREA 100
+
+static struct slot_area slot_areas[MAX_SLOT_AREA];
+
+static unsigned long slot_max;
+
+static unsigned long slot_area_index;
+
+static void store_slot_info(struct mem_vector *region, unsigned long image_size)
+{
+	struct slot_area slot_area;
+
+	if (slot_area_index == MAX_SLOT_AREA)
+		return;
+
+	slot_area.addr = region->start;
+	slot_area.num = (region->size - image_size) /
+			CONFIG_PHYSICAL_ALIGN + 1;
+
+	if (slot_area.num > 0) {
+		slot_areas[slot_area_index++] = slot_area;
+		slot_max += slot_area.num;
+	}
+}
+
+static void slots_append(unsigned long addr)
+{
+	/* Overflowing the slots list should be impossible. */
+	if (slot_max >= KERNEL_IMAGE_SIZE / 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("Physical") % slot_max];
+}
+
+static void process_e820_entry(struct e820entry *entry,
+			       unsigned long minimum,
+			       unsigned long image_size)
+{
+	struct mem_vector region, img, overlap;
+
+	/* Skip non-RAM entries. */
+	if (entry->type != E820_RAM)
+		return;
+
+	/* Ignore entries entirely above our maximum. */
+	if (entry->addr >= KERNEL_IMAGE_SIZE)
+		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 > KERNEL_IMAGE_SIZE)