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
  ...

arch/x86/Kconfig

@@ -1921,54 +1921,38 @@ config RELOCATABLE
 	  (CONFIG_PHYSICAL_START) is used as the minimum location.
 
 config RANDOMIZE_BASE
-	bool "Randomize the address of the kernel image"
+	bool "Randomize the address of the kernel image (KASLR)"
 	depends on RELOCATABLE
 	default n
 	---help---
-	   Randomizes the physical and virtual address at which the
+	  In support of Kernel Address Space Layout Randomization (KASLR),
-	   kernel image is decompressed, as a security feature that
+	  this randomizes the physical address at which the kernel image
-	   deters exploit attempts relying on knowledge of the location
+	  is decompressed and the virtual address where the kernel
-	   of kernel internals.
+	  image is mapped, as a security feature that deters exploit
+	  attempts relying on knowledge of the location of kernel
+	  code internals.
 
-	   Entropy is generated using the RDRAND instruction if it is
+	  The kernel physical and virtual address can be randomized
-	   supported. If RDTSC is supported, it is used as well. If
+	  from 16MB up to 1GB on 64-bit and 512MB on 32-bit. (Note that
-	   neither RDRAND nor RDTSC are supported, then randomness is
+	  using RANDOMIZE_BASE reduces the memory space available to
-	   read from the i8254 timer.
+	  kernel modules from 1.5GB to 1GB.)
 
-	   The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET,
+	  Entropy is generated using the RDRAND instruction if it is
-	   and aligned according to PHYSICAL_ALIGN. Since the kernel is
+	  supported. If RDTSC is supported, its value is mixed into
-	   built using 2GiB addressing, and PHYSICAL_ALGIN must be at a
+	  the entropy pool as well. If neither RDRAND nor RDTSC are
-	   minimum of 2MiB, only 10 bits of entropy is theoretically
+	  supported, then entropy is read from the i8254 timer.
-	   possible. At best, due to page table layouts, 64-bit can use
-	   9 bits of entropy and 32-bit uses 8 bits.
 
-	   If unsure, say N.
+	  Since the kernel is built using 2GB addressing, and
+	  PHYSICAL_ALIGN must be at a minimum of 2MB, only 10 bits of
+	  entropy is theoretically possible. Currently, with the
+	  default value for PHYSICAL_ALIGN and due to page table
+	  layouts, 64-bit uses 9 bits of entropy and 32-bit uses 8 bits.
 
-config RANDOMIZE_BASE_MAX_OFFSET
+	  If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot
-	hex "Maximum kASLR offset allowed" if EXPERT
+	  time. To enable it, boot with "kaslr" on the kernel command
-	depends on RANDOMIZE_BASE
+	  line (which will also disable hibernation).
-	range 0x0 0x20000000 if X86_32
-	default "0x20000000" if X86_32
-	range 0x0 0x40000000 if X86_64
-	default "0x40000000" if X86_64
-	---help---
-	  The lesser of RANDOMIZE_BASE_MAX_OFFSET and available physical
-	  memory is used to determine the maximal offset in bytes that will
-	  be applied to the kernel when kernel Address Space Layout
-	  Randomization (kASLR) is active. This must be a multiple of
-	  PHYSICAL_ALIGN.
 
-	  On 32-bit this is limited to 512MiB by page table layouts. The
+	  If unsure, say N.
-	  default is 512MiB.
-
-	  On 64-bit this is limited by how the kernel fixmap page table is
-	  positioned, so this cannot be larger than 1GiB currently. Without
-	  RANDOMIZE_BASE, there is a 512MiB to 1.5GiB split between kernel
-	  and modules. When RANDOMIZE_BASE_MAX_OFFSET is above 512MiB, the
-	  modules area will shrink to compensate, up to the current maximum
-	  1GiB to 1GiB split. The default is 1GiB.
-
-	  If unsure, leave at the default value.
 
 # Relocation on x86 needs some additional build support
 config X86_NEED_RELOCS

arch/x86/Makefile

@@ -208,7 +208,8 @@ endif
 
 head-y := arch/x86/kernel/head_$(BITS).o
 head-y += arch/x86/kernel/head$(BITS).o
-head-y += arch/x86/kernel/head.o
+head-y += arch/x86/kernel/ebda.o
+head-y += arch/x86/kernel/platform-quirks.o
 
 libs-y  += arch/x86/lib/
 

arch/x86/boot/Makefile

@@ -86,16 +86,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
-
-quiet_cmd_voffset = VOFFSET $@
-      cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
-
-targets += voffset.h
-$(obj)/voffset.h: vmlinux FORCE
-	$(call if_changed,voffset)
-
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
@@ -106,7 +97,7 @@ $(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
 
 
 AFLAGS_header.o += -I$(obj)
-$(obj)/header.o: $(obj)/voffset.h $(obj)/zoffset.h
+$(obj)/header.o: $(obj)/zoffset.h
 
 LDFLAGS_setup.elf	:= -T
 $(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE

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

arch/x86/boot/compressed/aslr.c

@@ -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;
-}

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;
 }

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");
+}

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 */

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: */
+				/* push arguments for extract_kernel: */
-	pushl	$z_run_size	/* size of kernel with .bss and .brk */
 	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 */
+	call	extract_kernel	/* returns kernel location in %eax */
-	addl	$28, %esp
+	addl	$24, %esp
 
 /*
- * Jump to the decompressed kernel.
+ * Jump to the extracted kernel.
  */
 	xorl	%ebx, %ebx
 	jmp	*%eax

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 */
+	call	extract_kernel		/* returns kernel location in %rax */
-	popq	%r9
 	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

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)
+		region.size = KERNEL_IMAGE_SIZE - 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, &overlap))
+			continue;
+		slots_append(img.start);
+	}
+}
+
+static unsigned long find_random_phys_addr(unsigned long minimum,
+					   unsigned long image_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 < boot_params->e820_entries; i++) {
+		process_e820_entry(&boot_params->e820_map[i], minimum,
+				   image_size);
+	}
+
+	return slots_fetch_random();
+}
+
+static unsigned long find_random_virt_addr(unsigned long minimum,
+					   unsigned long image_size)
+{
+	unsigned long slots, random_addr;
+
+	/* Make sure minimum is aligned. */
+	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+	/* Align image_size for easy slot calculations. */
+	image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN);
+
+	/*
+	 * There are how many CONFIG_PHYSICAL_ALIGN-sized slots
+	 * that can hold image_size within the range of minimum to
+	 * KERNEL_IMAGE_SIZE?
+	 */
+	slots = (KERNEL_IMAGE_SIZE - minimum - image_size) /
+		 CONFIG_PHYSICAL_ALIGN + 1;
+
+	random_addr = get_random_long("Virtual") % slots;
+
+	return random_addr * CONFIG_PHYSICAL_ALIGN + minimum;
+}
+
+/*
+ * Since this function examines addresses much more numerically,
+ * it takes the input and output pointers as 'unsigned long'.
+ */
+unsigned char *choose_random_location(unsigned long input,
+				      unsigned long input_size,
+				      unsigned long output,
+				      unsigned long output_size)
+{
+	unsigned long choice = output;
+	unsigned long random_addr;
+
+#ifdef CONFIG_HIBERNATION
+	if (!cmdline_find_option_bool("kaslr")) {
+		warn("KASLR disabled: 'kaslr' not on cmdline (hibernation selected).");
+		goto out;
+	}
+#else
+	if (cmdline_find_option_bool("nokaslr")) {
+		warn("KASLR disabled: 'nokaslr' on cmdline.");
+		goto out;
+	}
+#endif
+
+	boot_params->hdr.loadflags |= KASLR_FLAG;
+
+	/* Record the various known unsafe memory ranges. */
+	mem_avoid_init(input, input_size, output);
+
+	/* Walk e820 and find a random address. */
+	random_addr = find_random_phys_addr(output, output_size);
+	if (!random_addr) {
+		warn("KASLR disabled: could not find suitable E820 region!");
+		goto out;
+	}
+
+	/* Always enforce the minimum. */
+	if (random_addr < choice)
+		goto out;
+
+	choice = random_addr;
+
+	add_identity_map(choice, output_size);
+
+	/* This actually loads the identity pagetable on x86_64. */
+	finalize_identity_maps();
+out:
+	return (unsigned char *)choice;
+}

arch/x86/boot/compressed/misc.c

@@ -1,8 +1,10 @@
 /*
  * misc.c
  *
- * This is a collection of several routines from gzip-1.0.3
+ * This is a collection of several routines used to extract the kernel
- * adapted for Linux.
+ * which includes KASLR relocation, decompression, ELF parsing, and
+ * relocation processing. Additionally included are the screen and serial
+ * output functions and related debugging support functions.
  *
  * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
  * puts by Nick Holloway 1993, better puts by Martin Mares 1995
@@ -10,111 +12,37 @@
  */
 
 #include "misc.h"
+#include "error.h"
 #include "../string.h"
-
+#include "../voffset.h"
-/* WARNING!!
- * This code is compiled with -fPIC and it is relocated dynamically
- * at run time, but no relocation processing is performed.
- * This means that it is not safe to place pointers in static structures.
- */
 
 /*
- * Getting to provable safe in place decompression is hard.
+ * WARNING!!
- * Worst case behaviours need to be analyzed.
+ * This code is compiled with -fPIC and it is relocated dynamically at
- * Background information:
+ * run time, but no relocation processing is performed. This means that
- *
+ * it is not safe to place pointers in static structures.
- * The file layout is:
- *    magic[2]
- *    method[1]
- *    flags[1]
- *    timestamp[4]
- *    extraflags[1]
- *    os[1]
- *    compressed data blocks[N]
- *    crc[4] orig_len[4]
- *
- * resulting in 18 bytes of non compressed data overhead.
- *
- * Files divided into blocks
- * 1 bit (last block flag)
- * 2 bits (block type)
- *
- * 1 block occurs every 32K -1 bytes or when there 50% compression
- * has been achieved. The smallest block type encoding is always used.
- *
- * stored:
- *    32 bits length in bytes.
- *
- * fixed:
- *    magic fixed tree.
- *    symbols.
- *
- * dynamic:
- *    dynamic tree encoding.
- *    symbols.
- *
- *
- * The buffer for decompression in place is the length of the
- * uncompressed data, plus a small amount extra to keep the algorithm safe.
- * The compressed data is placed at the end of the buffer.  The output
- * pointer is placed at the start of the buffer and the input pointer
- * is placed where the compressed data starts.  Problems will occur
- * when the output pointer overruns the input pointer.
- *
- * The output pointer can only overrun the input pointer if the input
- * pointer is moving faster than the output pointer.  A condition only
- * triggered by data whose compressed form is larger than the uncompressed
- * form.
- *
- * The worst case at the block level is a growth of the compressed data
- * of 5 bytes per 32767 bytes.
- *
- * The worst case internal to a compressed block is very hard to figure.
- * The worst case can at least be boundined by having one bit that represents
- * 32764 bytes and then all of the rest of the bytes representing the very
- * very last byte.
- *
- * All of which is enough to compute an amount of extra data that is required
- * to be safe.  To avoid problems at the block level allocating 5 extra bytes
- * per 32767 bytes of data is sufficient.  To avoind problems internal to a
- * block adding an extra 32767 bytes (the worst case uncompressed block size)
- * is sufficient, to ensure that in the worst case the decompressed data for
- * block will stop the byte before the compressed data for a block begins.
- * To avoid problems with the compressed data's meta information an extra 18
- * bytes are needed.  Leading to the formula:
- *
- * extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size.
- *
- * Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
- * Adding 32768 instead of 32767 just makes for round numbers.
- * Adding the decompressor_size is necessary as it musht live after all
- * of the data as well.  Last I measured the decompressor is about 14K.
- * 10K of actual data and 4K of bss.
- *
  */
 
-/*
+/* Macros used by the included decompressor code below. */
- * gzip declarations
- */
 #define STATIC		static
 
-#undef memcpy
-
 /*
- * Use a normal definition of memset() from string.c. There are already
+ * Use normal definitions of mem*() from string.c. There are already
  * included header files which expect a definition of memset() and by
  * the time we define memset macro, it is too late.
  */
+#undef memcpy
 #undef memset
 #define memzero(s, n)	memset((s), 0, (n))
+#define memmove		memmove
 
-
+/* Functions used by the included decompressor code below. */
-static void error(char *m);
+void *memmove(void *dest, const void *src, size_t n);
 
 /*
  * This is set up by the setup-routine at boot-time
  */
-struct boot_params *real_mode;		/* Pointer to real-mode data */
+struct boot_params *boot_params;
 
 memptr free_mem_ptr;
 memptr free_mem_end_ptr;
@@ -146,12 +74,16 @@ static int lines, cols;
 #ifdef CONFIG_KERNEL_LZ4
 #include "../../../../lib/decompress_unlz4.c"
 #endif
+/*
+ * NOTE: When adding a new decompressor, please update the analysis in
+ * ../header.S.
+ */
 
 static void scroll(void)
 {
 	int i;
 
-	memcpy(vidmem, vidmem + cols * 2, (lines - 1) * cols * 2);
+	memmove(vidmem, vidmem + cols * 2, (lines - 1) * cols * 2);
 	for (i = (lines - 1) * cols * 2; i < lines * cols * 2; i += 2)
 		vidmem[i] = ' ';
 }
@@ -184,12 +116,12 @@ void __putstr(const char *s)
 		}
 	}
 
-	if (real_mode->screen_info.orig_video_mode == 0 &&
+	if (boot_params->screen_info.orig_video_mode == 0 &&
 	    lines == 0 && cols == 0)
 		return;
 
-	x = real_mode->screen_info.orig_x;
+	x = boot_params->screen_info.orig_x;
-	y = real_mode->screen_info.orig_y;
+	y = boot_params->screen_info.orig_y;
 
 	while ((c = *s++) != '\0') {
 		if (c == '\n') {
@@ -210,8 +142,8 @@ void __putstr(const char *s)
 		}
 	}
 
-	real_mode->screen_info.orig_x = x;
+	boot_params->screen_info.orig_x = x;
-	real_mode->screen_info.orig_y = y;
+	boot_params->screen_info.orig_y = y;
 
 	pos = (x + cols * y) * 2;	/* Update cursor position */
 	outb(14, vidport);
@@ -237,23 +169,13 @@ void __puthex(unsigned long value)
 	}
 }
 
-static void error(char *x)
-{
-	error_putstr("\n\n");
-	error_putstr(x);
-	error_putstr("\n\n -- System halted");
-
-	while (1)
-		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;
+	unsigned long max_addr = min_addr + (VO___bss_start - VO__text);
 
 	/*
 	 * Calculate the delta between where vmlinux was linked to load
@@ -295,7 +217,7 @@ static void handle_relocations(void *output, unsigned long output_len)
 	 * So we work backwards from the end of the decompressed image.
 	 */
 	for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) {
-		int extended = *reloc;
+		long extended = *reloc;
 		extended += map;
 
 		ptr = (unsigned long)extended;
@@ -372,9 +294,7 @@ static void parse_elf(void *output)
 #else
 			dest = (void *)(phdr->p_paddr);
 #endif
-			memcpy(dest,
+			memmove(dest, output + phdr->p_offset, phdr->p_filesz);
-			       output + phdr->p_offset,
-			       phdr->p_filesz);
 			break;
 		default: /* Ignore other PT_* */ break;
 		}
@@ -383,23 +303,41 @@ static void parse_elf(void *output)
 	free(phdrs);
 }
 
-asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
+/*
+ * The compressed kernel image (ZO), has been moved so that its position
+ * is against the end of the buffer used to hold the uncompressed kernel
+ * image (VO) and the execution environment (.bss, .brk), which makes sure
+ * there is room to do the in-place decompression. (See header.S for the
+ * calculations.)
+ *
+ *                             |-----compressed kernel image------|
+ *                             V                                  V
+ * 0                       extract_offset                      +INIT_SIZE
+ * |-----------|---------------|-------------------------|--------|
+ *             |               |                         |        |
+ *           VO__text      startup_32 of ZO          VO__end    ZO__end
+ *             ^                                         ^
+ *             |-------uncompressed kernel image---------|
+ *
+ */
+asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
-				  unsigned long output_len,
+				  unsigned long output_len)
-				  unsigned long run_size)
 {
+	const unsigned long kernel_total_size = VO__end - VO__text;
 	unsigned char *output_orig = output;
 
-	real_mode = rmode;
+	/* Retain x86 boot parameters pointer passed from startup_32/64. */
+	boot_params = rmode;
 
-	/* Clear it for solely in-kernel use */
+	/* Clear flags intended for solely in-kernel use. */
-	real_mode->hdr.loadflags &= ~KASLR_FLAG;
+	boot_params->hdr.loadflags &= ~KASLR_FLAG;
 
-	sanitize_boot_params(real_mode);
+	sanitize_boot_params(boot_params);
 
-	if (real_mode->screen_info.orig_video_mode == 7) {
+	if (boot_params->screen_info.orig_video_mode == 7) {
 		vidmem = (char *) 0xb0000;
 		vidport = 0x3b4;
 	} else {
@@ -407,11 +345,11 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 		vidport = 0x3d4;
 	}
 
-	lines = real_mode->screen_info.orig_video_lines;
+	lines = boot_params->screen_info.orig_video_lines;
-	cols = real_mode->screen_info.orig_video_cols;
+	cols = boot_params->screen_info.orig_video_cols;
 
 	console_init();
-	debug_putstr("early console in decompress_kernel\n");
+	debug_putstr("early console in extract_kernel\n");
 
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
@@ -421,16 +359,16 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	debug_putaddr(input_len);
 	debug_putaddr(output);
 	debug_putaddr(output_len);
-	debug_putaddr(run_size);
+	debug_putaddr(kernel_total_size);
 
 	/*
 	 * The memory hole needed for the kernel is the larger of either
 	 * the entire decompressed kernel plus relocation table, or the
 	 * entire decompressed kernel plus .bss and .brk sections.
 	 */
-	output = choose_kernel_location(real_mode, input_data, input_len, output,
+	output = choose_random_location((unsigned long)input_data, input_len,
-					output_len > run_size ? output_len
+					(unsigned long)output,
-							      : run_size);
+					max(output_len, kernel_total_size));
 
 	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))

arch/x86/boot/compressed/misc.h

@@ -32,7 +32,7 @@
 /* misc.c */
 extern memptr free_mem_ptr;
 extern memptr free_mem_end_ptr;
-extern struct boot_params *real_mode;		/* Pointer to real-mode data */
+extern struct boot_params *boot_params;
 void __putstr(const char *s);
 void __puthex(unsigned long value);
 #define error_putstr(__x)  __putstr(__x)
@@ -66,26 +66,35 @@ int cmdline_find_option_bool(const char *option);
 
 
 #if CONFIG_RANDOMIZE_BASE
-/* aslr.c */
+/* kaslr.c */
-unsigned char *choose_kernel_location(struct boot_params *boot_params,
+unsigned char *choose_random_location(unsigned long input_ptr,
-				      unsigned char *input,
 				      unsigned long input_size,
-				      unsigned char *output,
+				      unsigned long output_ptr,
 				      unsigned long output_size);
 /* cpuflags.c */
 bool has_cpuflag(int flag);
 #else
 static inline
-unsigned char *choose_kernel_location(struct boot_params *boot_params,
+unsigned char *choose_random_location(unsigned long input_ptr,
-				      unsigned char *input,
 				      unsigned long input_size,
-				      unsigned char *output,
+				      unsigned long output_ptr,
 				      unsigned long output_size)
 {
-	return output;
+	return (unsigned char *)output_ptr;
 }
 #endif
 
+#ifdef CONFIG_X86_64
+void add_identity_map(unsigned long start, unsigned long size);
+void finalize_identity_maps(void);
+extern unsigned char _pgtable[];
+#else
+static inline void add_identity_map(unsigned long start, unsigned long size)
+{ }
+static inline void finalize_identity_maps(void)
+{ }
+#endif
+
 #ifdef CONFIG_EARLY_PRINTK
 /* early_serial_console.c */
 extern int early_serial_base;

arch/x86/boot/compressed/mkpiggy.c

@@ -18,11 +18,10 @@
  *
  *  H. Peter Anvin <hpa@linux.intel.com>
  *
- * ----------------------------------------------------------------------- */
+ * -----------------------------------------------------------------------
-
+ *
-/*
+ * Outputs a small assembly wrapper with the appropriate symbols defined.
- * Compute the desired load offset from a compressed program; outputs
+ *
- * a small assembly wrapper with the appropriate symbols defined.
  */
 
 #include <stdlib.h>
@@ -35,14 +34,11 @@ int main(int argc, char *argv[])
 {
 	uint32_t olen;
 	long ilen;
-	unsigned long offs;
-	unsigned long run_size;
 	FILE *f = NULL;
 	int retval = 1;
 
-	if (argc < 3) {
+	if (argc < 2) {
-		fprintf(stderr, "Usage: %s compressed_file run_size\n",
+		fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
-				argv[0]);
 		goto bail;
 	}
 
@@ -67,29 +63,11 @@ int main(int argc, char *argv[])
 	ilen = ftell(f);
 	olen = get_unaligned_le32(&olen);
 
-	/*
-	 * Now we have the input (compressed) and output (uncompressed)
-	 * sizes, compute the necessary decompression offset...
-	 */
-
-	offs = (olen > ilen) ? olen - ilen : 0;
-	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
-	offs += 64*1024 + 128;	/* Add 64K + 128 bytes slack */
-	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
-	run_size = atoi(argv[2]);
-
 	printf(".section \".rodata..compressed\",\"a\",@progbits\n");
 	printf(".globl z_input_len\n");
 	printf("z_input_len = %lu\n", ilen);
 	printf(".globl z_output_len\n");
 	printf("z_output_len = %lu\n", (unsigned long)olen);
-	printf(".globl z_extract_offset\n");
-	printf("z_extract_offset = 0x%lx\n", offs);
-	/* z_extract_offset_negative allows simplification of head_32.S */
-	printf(".globl z_extract_offset_negative\n");
-	printf("z_extract_offset_negative = -0x%lx\n", offs);
-	printf(".globl z_run_size\n");
-	printf("z_run_size = %lu\n", run_size);
 
 	printf(".globl input_data, input_data_end\n");
 	printf("input_data:\n");

arch/x86/boot/compressed/pagetable.c

@@ -0,0 +1,129 @@
+/*
+ * This code is used on x86_64 to create page table identity mappings on
+ * demand by building up a new set of page tables (or appending to the
+ * existing ones), and then switching over to them when ready.
+ */
+
+/*
+ * Since we're dealing with identity mappings, physical and virtual
+ * addresses are the same, so override these defines which are ultimately
+ * used by the headers in misc.h.
+ */
+#define __pa(x)  ((unsigned long)(x))
+#define __va(x)  ((void *)((unsigned long)(x)))
+
+#include "misc.h"
+
+/* These actually do the work of building the kernel identity maps. */
+#include <asm/init.h>
+#include <asm/pgtable.h>
+#include "../../mm/ident_map.c"
+
+/* Used by pgtable.h asm code to force instruction serialization. */
+unsigned long __force_order;
+
+/* Used to track our page table allocation area. */
+struct alloc_pgt_data {
+	unsigned char *pgt_buf;
+	unsigned long pgt_buf_size;
+	unsigned long pgt_buf_offset;
+};
+
+/*
+ * Allocates space for a page table entry, using struct alloc_pgt_data
+ * above. Besides the local callers, this is used as the allocation
+ * callback in mapping_info below.
+ */
+static void *alloc_pgt_page(void *context)
+{
+	struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context;
+	unsigned char *entry;
+
+	/* Validate there is space available for a new page. */
+	if (pages->pgt_buf_offset >= pages->pgt_buf_size) {
+		debug_putstr("out of pgt_buf in " __FILE__ "!?\n");
+		debug_putaddr(pages->pgt_buf_offset);
+		debug_putaddr(pages->pgt_buf_size);
+		return NULL;
+	}
+
+	entry = pages->pgt_buf + pages->pgt_buf_offset;
+	pages->pgt_buf_offset += PAGE_SIZE;
+
+	return entry;
+}
+
+/* Used to track our allocated page tables. */
+static struct alloc_pgt_data pgt_data;
+
+/* The top level page table entry pointer. */
+static unsigned long level4p;
+
+/* Locates and clears a region for a new top level page table. */
+static void prepare_level4(void)
+{
+	/*
+	 * It should be impossible for this not to already be true,
+	 * but since calling this a second time would rewind the other
+	 * counters, let's just make sure this is reset too.
+	 */
+	pgt_data.pgt_buf_offset = 0;
+
+	/*
+	 * If we came here via startup_32(), cr3 will be _pgtable already
+	 * and we must append to the existing area instead of entirely
+	 * overwriting it.
+	 */
+	level4p = read_cr3();
+	if (level4p == (unsigned long)_pgtable) {
+		debug_putstr("booted via startup_32()\n");
+		pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE;
+		pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE;
+		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
+	} else {
+		debug_putstr("booted via startup_64()\n");
+		pgt_data.pgt_buf = _pgtable;
+		pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
+		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
+		level4p = (unsigned long)alloc_pgt_page(&pgt_data);
+	}
+}
+
+/*
+ * Adds the specified range to what will become the new identity mappings.
+ * Once all ranges have been added, the new mapping is activated by calling
+ * finalize_identity_maps() below.
+ */
+void add_identity_map(unsigned long start, unsigned long size)
+{
+	struct x86_mapping_info mapping_info = {
+		.alloc_pgt_page	= alloc_pgt_page,
+		.context	= &pgt_data,
+		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
+	};
+	unsigned long end = start + size;
+
+	/* Make sure we have a top level page table ready to use. */
+	if (!level4p)
+		prepare_level4();
+
+	/* Align boundary to 2M. */
+	start = round_down(start, PMD_SIZE);
+	end = round_up(end, PMD_SIZE);
+	if (start >= end)
+		return;
+
+	/* Build the mapping. */
+	kernel_ident_mapping_init(&mapping_info, (pgd_t *)level4p,
+				  start, end);
+}
+
+/*
+ * This switches the page tables to the new level4 that has been built
+ * via calls to add_identity_map() above. If booted via startup_32(),
+ * this is effectively a no-op.
+ */
+void finalize_identity_maps(void)
+{
+	write_cr3(level4p);
+}

arch/x86/boot/compressed/string.c

@@ -1,7 +1,16 @@
+/*
+ * This provides an optimized implementation of memcpy, and a simplified
+ * implementation of memset and memmove. These are used here because the
+ * standard kernel runtime versions are not yet available and we don't
+ * trust the gcc built-in implementations as they may do unexpected things
+ * (e.g. FPU ops) in the minimal decompression stub execution environment.
+ */
+#include "error.h"
+
 #include "../string.c"
 
 #ifdef CONFIG_X86_32
-void *memcpy(void *dest, const void *src, size_t n)
+static void *__memcpy(void *dest, const void *src, size_t n)
 {
 	int d0, d1, d2;
 	asm volatile(
@@ -15,7 +24,7 @@ void *memcpy(void *dest, const void *src, size_t n)
 	return dest;
 }
 #else
-void *memcpy(void *dest, const void *src, size_t n)
+static void *__memcpy(void *dest, const void *src, size_t n)
 {
 	long d0, d1, d2;
 	asm volatile(
@@ -39,3 +48,27 @@ void *memset(void *s, int c, size_t n)
 		ss[i] = c;
 	return s;
 }
+
+void *memmove(void *dest, const void *src, size_t n)
+{
+	unsigned char *d = dest;
+	const unsigned char *s = src;
+
+	if (d <= s || d - s >= n)
+		return __memcpy(dest, src, n);
+
+	while (n-- > 0)
+		d[n] = s[n];
+
+	return dest;
+}
+
+/* Detect and warn about potential overlaps, but handle them with memmove. */
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	if (dest > src && dest - src < n) {
+		warn("Avoiding potentially unsafe overlapping memcpy()!");
+		return memmove(dest, src, n);
+	}
+	return __memcpy(dest, src, n);
+}

arch/x86/boot/compressed/vmlinux.lds.S

@@ -70,5 +70,6 @@ SECTIONS
 		_epgtable = . ;
 	}
 #endif
+	. = ALIGN(PAGE_SIZE);	/* keep ZO size page aligned */
 	_end = .;
 }

arch/x86/boot/early_serial_console.c

@@ -1,3 +1,7 @@
+/*
+ * Serial port routines for use during early boot reporting. This code is
+ * included from both the compressed kernel and the regular kernel.
+ */
 #include "boot.h"
 
 #define DEFAULT_SERIAL_PORT 0x3f8 /* ttyS0 */

arch/x86/boot/header.S

@@ -440,13 +440,116 @@ setup_data:		.quad 0			# 64-bit physical pointer to
 
 pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 
-#define ZO_INIT_SIZE	(ZO__end - ZO_startup_32 + ZO_z_extract_offset)
+#
+# Getting to provably safe in-place decompression is hard. Worst case
+# behaviours need to be analyzed. Here let's take the decompression of
+# a gzip-compressed kernel as example, to illustrate it:
+#
+# The file layout of gzip compressed kernel is:
+#
+#    magic[2]
+#    method[1]
+#    flags[1]
+#    timestamp[4]
+#    extraflags[1]
+#    os[1]
+#    compressed data blocks[N]
+#    crc[4] orig_len[4]
+#
+# ... resulting in +18 bytes overhead of uncompressed data.
+#
+# (For more information, please refer to RFC 1951 and RFC 1952.)
+#
+# Files divided into blocks
+# 1 bit (last block flag)
+# 2 bits (block type)
+#
+# 1 block occurs every 32K -1 bytes or when there 50% compression
+# has been achieved. The smallest block type encoding is always used.
+#
+# stored:
+#    32 bits length in bytes.
+#
+# fixed:
+#    magic fixed tree.
+#    symbols.
+#
+# dynamic:
+#    dynamic tree encoding.
+#    symbols.
+#
+#
+# The buffer for decompression in place is the length of the uncompressed
+# data, plus a small amount extra to keep the algorithm safe. The
+# compressed data is placed at the end of the buffer.  The output pointer
+# is placed at the start of the buffer and the input pointer is placed
+# where the compressed data starts. Problems will occur when the output
+# pointer overruns the input pointer.
+#
+# The output pointer can only overrun the input pointer if the input
+# pointer is moving faster than the output pointer.  A condition only
+# triggered by data whose compressed form is larger than the uncompressed
+# form.
+#
+# The worst case at the block level is a growth of the compressed data
+# of 5 bytes per 32767 bytes.
+#
+# The worst case internal to a compressed block is very hard to figure.
+# The worst case can at least be bounded by having one bit that represents
+# 32764 bytes and then all of the rest of the bytes representing the very
+# very last byte.
+#
+# All of which is enough to compute an amount of extra data that is required
+# to be safe.  To avoid problems at the block level allocating 5 extra bytes
+# per 32767 bytes of data is sufficient.  To avoid problems internal to a
+# block adding an extra 32767 bytes (the worst case uncompressed block size)
+# is sufficient, to ensure that in the worst case the decompressed data for
+# block will stop the byte before the compressed data for a block begins.
+# To avoid problems with the compressed data's meta information an extra 18
+# bytes are needed.  Leading to the formula:
+#
+# extra_bytes = (uncompressed_size >> 12) + 32768 + 18
+#
+# Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
+# Adding 32768 instead of 32767 just makes for round numbers.
+#
+# Above analysis is for decompressing gzip compressed kernel only. Up to
+# now 6 different decompressor are supported all together. And among them
+# xz stores data in chunks and has maximum chunk of 64K. Hence safety
+# margin should be updated to cover all decompressors so that we don't
+# need to deal with each of them separately. Please check
+# the description in lib/decompressor_xxx.c for specific information.
+#
+# extra_bytes = (uncompressed_size >> 12) + 65536 + 128
+
+#define ZO_z_extra_bytes	((ZO_z_output_len >> 12) + 65536 + 128)
+#if ZO_z_output_len > ZO_z_input_len
+# define ZO_z_extract_offset	(ZO_z_output_len + ZO_z_extra_bytes - \
+				 ZO_z_input_len)
+#else
+# define ZO_z_extract_offset	ZO_z_extra_bytes
+#endif
+
+/*
+ * The extract_offset has to be bigger than ZO head section. Otherwise when
+ * the head code is running to move ZO to the end of the buffer, it will
+ * overwrite the head code itself.
+ */
+#if (ZO__ehead - ZO_startup_32) > ZO_z_extract_offset
+# define ZO_z_min_extract_offset ((ZO__ehead - ZO_startup_32 + 4095) & ~4095)
+#else
+# define ZO_z_min_extract_offset ((ZO_z_extract_offset + 4095) & ~4095)
+#endif
+
+#define ZO_INIT_SIZE	(ZO__end - ZO_startup_32 + ZO_z_min_extract_offset)
+
 #define VO_INIT_SIZE	(VO__end - VO__text)
 #if ZO_INIT_SIZE > VO_INIT_SIZE
-#define INIT_SIZE ZO_INIT_SIZE
+# define INIT_SIZE ZO_INIT_SIZE
 #else
-#define INIT_SIZE VO_INIT_SIZE
+# define INIT_SIZE VO_INIT_SIZE
 #endif
+
 init_size:		.long INIT_SIZE		# kernel initialization size
 handover_offset:	.long 0			# Filled in by build.c
 

arch/x86/include/asm/boot.h

@@ -12,29 +12,46 @@
 
 /* Minimum kernel alignment, as a power of two */
 #ifdef CONFIG_X86_64
-#define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
+# define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
 #else
-#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT + THREAD_SIZE_ORDER)
+# define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT + THREAD_SIZE_ORDER)
 #endif
 #define MIN_KERNEL_ALIGN	(_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
 
 #if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \
 	(CONFIG_PHYSICAL_ALIGN < MIN_KERNEL_ALIGN)
-#error "Invalid value for CONFIG_PHYSICAL_ALIGN"
+# error "Invalid value for CONFIG_PHYSICAL_ALIGN"
 #endif
 
 #ifdef CONFIG_KERNEL_BZIP2
-#define BOOT_HEAP_SIZE             0x400000
+# define BOOT_HEAP_SIZE		0x400000
 #else /* !CONFIG_KERNEL_BZIP2 */
-
+# define BOOT_HEAP_SIZE		 0x10000
-#define BOOT_HEAP_SIZE	0x10000
+#endif
-
-#endif /* !CONFIG_KERNEL_BZIP2 */
 
 #ifdef CONFIG_X86_64
-#define BOOT_STACK_SIZE	0x4000
+# define BOOT_STACK_SIZE	0x4000
-#else
+
-#define BOOT_STACK_SIZE	0x1000
+# define BOOT_INIT_PGT_SIZE	(6*4096)
+# ifdef CONFIG_RANDOMIZE_BASE
+/*
+ * Assuming all cross the 512GB boundary:
+ * 1 page for level4
+ * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel
+ * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP).
+ * Total is 19 pages.
+ */
+#  ifdef CONFIG_X86_VERBOSE_BOOTUP
+#   define BOOT_PGT_SIZE	(19*4096)
+#  else /* !CONFIG_X86_VERBOSE_BOOTUP */
+#   define BOOT_PGT_SIZE	(17*4096)
+#  endif
+# else /* !CONFIG_RANDOMIZE_BASE */
+#  define BOOT_PGT_SIZE		BOOT_INIT_PGT_SIZE
+# endif
+
+#else /* !CONFIG_X86_64 */
+# define BOOT_STACK_SIZE	0x1000
 #endif
 
 #endif /* _ASM_X86_BOOT_H */

arch/x86/include/asm/page.h

@@ -37,7 +37,10 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
+#ifndef __pa
 #define __pa(x)		__phys_addr((unsigned long)(x))
+#endif
+
 #define __pa_nodebug(x)	__phys_addr_nodebug((unsigned long)(x))
 /* __pa_symbol should be used for C visible symbols.
    This seems to be the official gcc blessed way to do such arithmetic. */
@@ -51,7 +54,9 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 #define __pa_symbol(x) \
 	__phys_addr_symbol(__phys_reloc_hide((unsigned long)(x)))
 
+#ifndef __va
 #define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
+#endif
 
 #define __boot_va(x)		__va(x)
 #define __boot_pa(x)		__pa(x)

arch/x86/include/asm/page_64_types.h

@@ -47,12 +47,10 @@
  * are fully set up. If kernel ASLR is configured, it can extend the
  * kernel page table mapping, reducing the size of the modules area.
  */
-#define KERNEL_IMAGE_SIZE_DEFAULT      (512 * 1024 * 1024)
+#if defined(CONFIG_RANDOMIZE_BASE)
-#if defined(CONFIG_RANDOMIZE_BASE) && \
+#define KERNEL_IMAGE_SIZE	(1024 * 1024 * 1024)
-	CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE_DEFAULT
-#define KERNEL_IMAGE_SIZE   CONFIG_RANDOMIZE_BASE_MAX_OFFSET
 #else
-#define KERNEL_IMAGE_SIZE      KERNEL_IMAGE_SIZE_DEFAULT
+#define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
 #endif
 
 #endif /* _ASM_X86_PAGE_64_DEFS_H */

arch/x86/include/asm/paravirt.h

@@ -15,17 +15,6 @@
 #include <linux/cpumask.h>
 #include <asm/frame.h>
 
-static inline int paravirt_enabled(void)
-{
-	return pv_info.paravirt_enabled;
-}
-
-static inline int paravirt_has_feature(unsigned int feature)
-{
-	WARN_ON_ONCE(!pv_info.paravirt_enabled);
-	return (pv_info.features & feature);
-}
-
 static inline void load_sp0(struct tss_struct *tss,
 			     struct thread_struct *thread)
 {

arch/x86/include/asm/paravirt_types.h

@@ -69,15 +69,9 @@ struct pv_info {
 	u16 extra_user_64bit_cs;  /* __USER_CS if none */
 #endif
 
-	int paravirt_enabled;
-	unsigned int features;	  /* valid only if paravirt_enabled is set */
 	const char *name;
 };
 
-#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x)
-/* Supported features */
-#define PV_SUPPORTED_RTC        (1<<0)
-
 struct pv_init_ops {
 	/*
 	 * Patch may replace one of the defined code sequences with

arch/x86/include/asm/processor.h

@@ -480,8 +480,6 @@ static inline unsigned long current_top_of_stack(void)
 #include <asm/paravirt.h>
 #else
 #define __cpuid			native_cpuid
-#define paravirt_enabled()	0
-#define paravirt_has(x) 	0
 
 static inline void load_sp0(struct tss_struct *tss,
 			    struct thread_struct *thread)

arch/x86/include/asm/x86_init.h

@@ -141,6 +141,44 @@ struct x86_cpuinit_ops {
 
 struct timespec;
 
+/**
+ * struct x86_legacy_devices - legacy x86 devices
+ *
+ * @pnpbios: this platform can have a PNPBIOS. If this is disabled the platform
+ * 	is known to never have a PNPBIOS.
+ *
+ * These are devices known to require LPC or ISA bus. The definition of legacy
+ * devices adheres to the ACPI 5.2.9.3 IA-PC Boot Architecture flag
+ * ACPI_FADT_LEGACY_DEVICES. These devices consist of user visible devices on
+ * the LPC or ISA bus. User visible devices are devices that have end-user
+ * accessible connectors (for example, LPT parallel port). Legacy devices on
+ * the LPC bus consist for example of serial and parallel ports, PS/2 keyboard
+ * / mouse, and the floppy disk controller. A system that lacks all known
+ * legacy devices can assume all devices can be detected exclusively via
+ * standard device enumeration mechanisms including the ACPI namespace.
+ *
+ * A system which has does not have ACPI_FADT_LEGACY_DEVICES enabled must not
+ * have any of the legacy devices enumerated below present.
+ */
+struct x86_legacy_devices {
+	int pnpbios;
+};
+
+/**
+ * struct x86_legacy_features - legacy x86 features
+ *
+ * @rtc: this device has a CMOS real-time clock present
+ * @ebda_search: it's safe to search for the EBDA signature in the hardware's
+ * 	low RAM
+ * @devices: legacy x86 devices, refer to struct x86_legacy_devices
+ * 	documentation for further details.
+ */
+struct x86_legacy_features {
+	int rtc;
+	int ebda_search;
+	struct x86_legacy_devices devices;
+};
+
 /**
  * struct x86_platform_ops - platform specific runtime functions
  * @calibrate_tsc:		calibrate TSC
@@ -152,6 +190,14 @@ struct timespec;
  * @save_sched_clock_state:	save state for sched_clock() on suspend
  * @restore_sched_clock_state:	restore state for sched_clock() on resume
  * @apic_post_init:		adjust apic if neeeded
+ * @legacy:			legacy features
+ * @set_legacy_features:	override legacy features. Use of this callback
+ * 				is highly discouraged. You should only need
+ * 				this if your hardware platform requires further
+ * 				custom fine tuning far beyong what may be
+ * 				possible in x86_early_init_platform_quirks() by
+ * 				only using the current x86_hardware_subarch
+ * 				semantics.
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
@@ -165,6 +211,8 @@ struct x86_platform_ops {
 	void (*save_sched_clock_state)(void);
 	void (*restore_sched_clock_state)(void);
 	void (*apic_post_init)(void);
+	struct x86_legacy_features legacy;
+	void (*set_legacy_features)(void);
 };
 
 struct pci_dev;
@@ -186,6 +234,8 @@ extern struct x86_cpuinit_ops x86_cpuinit;
 extern struct x86_platform_ops x86_platform;
 extern struct x86_msi_ops x86_msi;
 extern struct x86_io_apic_ops x86_io_apic_ops;
+
+extern void x86_early_init_platform_quirks(void);
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
 

arch/x86/include/uapi/asm/bootparam.h

@@ -157,7 +157,46 @@ struct boot_params {
 	__u8  _pad9[276];				/* 0xeec */
 } __attribute__((packed));
 
-enum {
+/**
+ * enum x86_hardware_subarch - x86 hardware subarchitecture
+ *
+ * The x86 hardware_subarch and hardware_subarch_data were added as of the x86
+ * boot protocol 2.07 to help distinguish and support custom x86 boot
+ * sequences. This enum represents accepted values for the x86
+ * hardware_subarch.  Custom x86 boot sequences (not X86_SUBARCH_PC) do not
+ * have or simply *cannot* make use of natural stubs like BIOS or EFI, the
+ * hardware_subarch can be used on the Linux entry path to revector to a
+ * subarchitecture stub when needed. This subarchitecture stub can be used to
+ * set up Linux boot parameters or for special care to account for nonstandard
+ * handling of page tables.
+ *
+ * These enums should only ever be used by x86 code, and the code that uses
+ * it should be well contained and compartamentalized.
+ *
+ * KVM and Xen HVM do not have a subarch as these are expected to follow
+ * standard x86 boot entries. If there is a genuine need for "hypervisor" type
+ * that should be considered separately in the future. Future guest types
+ * should seriously consider working with standard x86 boot stubs such as
+ * the BIOS or EFI boot stubs.
+ *
+ * WARNING: this enum is only used for legacy hacks, for platform features that
+ *	    are not easily enumerated or discoverable. You should not ever use
+ *	    this for new features.
+ *
+ * @X86_SUBARCH_PC: Should be used if the hardware is enumerable using standard
+ *	PC mechanisms (PCI, ACPI) and doesn't need a special boot flow.
+ * @X86_SUBARCH_LGUEST: Used for x86 hypervisor demo, lguest
+ * @X86_SUBARCH_XEN: Used for Xen guest types which follow the PV boot path,
+ * 	which start at asm startup_xen() entry point and later jump to the C
+ * 	xen_start_kernel() entry point. Both domU and dom0 type of guests are
+ * 	currently supportd through this PV boot path.
+ * @X86_SUBARCH_INTEL_MID: Used for Intel MID (Mobile Internet Device) platform
+ *	systems which do not have the PCI legacy interfaces.
+ * @X86_SUBARCH_CE4100: Used for Intel CE media processor (CE4100) SoC for
+ * 	for settop boxes and media devices, the use of a subarch for CE4100
+ * 	is more of a hack...
+ */
+enum x86_hardware_subarch {
 	X86_SUBARCH_PC = 0,
 	X86_SUBARCH_LGUEST,
 	X86_SUBARCH_XEN,

arch/x86/kernel/Makefile

@@ -2,7 +2,11 @@
 # Makefile for the linux kernel.
 #
 
-extra-y                := head_$(BITS).o head$(BITS).o head.o vmlinux.lds
+extra-y	:= head_$(BITS).o
+extra-y	+= head$(BITS).o
+extra-y	+= ebda.o
+extra-y	+= platform-quirks.o
+extra-y	+= vmlinux.lds
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 

arch/x86/kernel/acpi/boot.c

@@ -913,6 +913,15 @@ late_initcall(hpet_insert_resource);
 
 static int __init acpi_parse_fadt(struct acpi_table_header *table)
 {
+	if (!(acpi_gbl_FADT.boot_flags & ACPI_FADT_LEGACY_DEVICES)) {
+		pr_debug("ACPI: no legacy devices present\n");
+		x86_platform.legacy.devices.pnpbios = 0;
+	}
+
+	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) {
+		pr_debug("ACPI: not registering RTC platform device\n");
+		x86_platform.legacy.rtc = 0;
+	}
 
 #ifdef CONFIG_X86_PM_TIMER
 	/* detect the location of the ACPI PM Timer */

arch/x86/kernel/apm_32.c

@@ -2267,7 +2267,7 @@ static int __init apm_init(void)
 
 	dmi_check_system(apm_dmi_table);
 
-	if (apm_info.bios.version == 0 || paravirt_enabled() || machine_is_olpc()) {
+	if (apm_info.bios.version == 0 || machine_is_olpc()) {
 		printk(KERN_INFO "apm: BIOS not found.\n");
 		return -ENODEV;
 	}

arch/x86/kernel/asm-offsets.c

@@ -80,6 +80,7 @@ void common(void) {
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
 	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
+	OFFSET(BP_init_size, boot_params, hdr.init_size);
 	OFFSET(BP_pref_address, boot_params, hdr.pref_address);
 	OFFSET(BP_code32_start, boot_params, hdr.code32_start);
 

arch/x86/kernel/cpu/intel.c

@@ -233,7 +233,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * The Quark is also family 5, but does not have the same bug.
 	 */
 	clear_cpu_bug(c, X86_BUG_F00F);
-	if (!paravirt_enabled() && c->x86 == 5 && c->x86_model < 9) {
+	if (c->x86 == 5 && c->x86_model < 9) {
 		static int f00f_workaround_enabled;
 
 		set_cpu_bug(c, X86_BUG_F00F);

arch/x86/kernel/ebda.c

@@ -38,7 +38,7 @@ void __init reserve_ebda_region(void)
 	 * that the paravirt case can handle memory setup
 	 * correctly, without our help.
 	 */
-	if (paravirt_enabled())
+	if (!x86_platform.legacy.ebda_search)
 		return;
 
 	/* end of low (conventional) memory */

arch/x86/kernel/head32.c

@@ -34,6 +34,8 @@ asmlinkage __visible void __init i386_start_kernel(void)
 	cr4_init_shadow();
 	sanitize_boot_params(&boot_params);
 
+	x86_early_init_platform_quirks();
+
 	/* Call the subarch specific early setup function */
 	switch (boot_params.hdr.hardware_subarch) {
 	case X86_SUBARCH_INTEL_MID:

arch/x86/kernel/head64.c

@@ -182,6 +182,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
 	if (!boot_params.hdr.version)
 		copy_bootdata(__va(real_mode_data));
 
+	x86_early_init_platform_quirks();
 	reserve_ebda_region();
 
 	switch (boot_params.hdr.hardware_subarch) {

arch/x86/kernel/kvm.c

@@ -285,14 +285,6 @@ static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
 
-	/*
-	 * KVM isn't paravirt in the sense of paravirt_enabled.  A KVM
-	 * guest kernel works like a bare metal kernel with additional
-	 * features, and paravirt_enabled is about features that are
-	 * missing.
-	 */
-	pv_info.paravirt_enabled = 0;
-
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
 

arch/x86/kernel/paravirt.c

@@ -294,7 +294,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 
 struct pv_info pv_info = {
 	.name = "bare hardware",
-	.paravirt_enabled = 0,
 	.kernel_rpl = 0,
 	.shared_kernel_pmd = 1,	/* Only used when CONFIG_X86_PAE is set */
 

arch/x86/kernel/platform-quirks.c

@@ -0,0 +1,35 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+
+#include <asm/setup.h>
+#include <asm/bios_ebda.h>
+
+void __init x86_early_init_platform_quirks(void)
+{
+	x86_platform.legacy.rtc = 1;
+	x86_platform.legacy.ebda_search = 0;
+	x86_platform.legacy.devices.pnpbios = 1;
+
+	switch (boot_params.hdr.hardware_subarch) {
+	case X86_SUBARCH_PC:
+		x86_platform.legacy.ebda_search = 1;
+		break;
+	case X86_SUBARCH_XEN:
+	case X86_SUBARCH_LGUEST:
+	case X86_SUBARCH_INTEL_MID:
+	case X86_SUBARCH_CE4100:
+		x86_platform.legacy.devices.pnpbios = 0;
+		x86_platform.legacy.rtc = 0;
+		break;
+	}
+
+	if (x86_platform.set_legacy_features)
+		x86_platform.set_legacy_features();
+}
+
+#if defined(CONFIG_PNPBIOS)
+bool __init arch_pnpbios_disabled(void)
+{
+	return x86_platform.legacy.devices.pnpbios == 0;
+}
+#endif

arch/x86/kernel/rtc.c

@@ -14,6 +14,7 @@
 #include <asm/time.h>
 #include <asm/intel-mid.h>
 #include <asm/rtc.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_X86_32
 /*
@@ -185,22 +186,7 @@ static __init int add_rtc_cmos(void)
 		}
 	}
 #endif
-	if (of_have_populated_dt())
+	if (!x86_platform.legacy.rtc)
-		return 0;
-
-	/* Intel MID platforms don't have ioport rtc */
-	if (intel_mid_identify_cpu())
-		return -ENODEV;
-
-#ifdef CONFIG_ACPI
-	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) {
-		/* This warning can likely go away again in a year or two. */
-		pr_info("ACPI: not registering RTC platform device\n");
-		return -ENODEV;
-	}
-#endif
-
-	if (paravirt_enabled() && !paravirt_has(RTC))
 		return -ENODEV;
 
 	platform_device_register(&rtc_device);

arch/x86/kernel/tboot.c

@@ -74,12 +74,6 @@ void __init tboot_probe(void)
 		return;
 	}
 
-	/* only a natively booted kernel should be using TXT */
-	if (paravirt_enabled()) {
-		pr_warning("non-0 tboot_addr but pv_ops is enabled\n");
-		return;
-	}
-
 	/* Map and check for tboot UUID. */
 	set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr);
 	tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE);

arch/x86/kernel/vmlinux.lds.S

@@ -334,7 +334,7 @@ SECTIONS
 		__brk_limit = .;
 	}
 
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(PAGE_SIZE);		/* keep VO_INIT_SIZE page aligned */
 	_end = .;
 
         STABS_DEBUG

arch/x86/lguest/boot.c

@@ -1408,13 +1408,10 @@ __init void lguest_init(void)
 {
 	/* We're under lguest. */
 	pv_info.name = "lguest";
-	/* Paravirt is enabled. */
-	pv_info.paravirt_enabled = 1;
 	/* We're running at privilege level 1, not 0 as normal. */
 	pv_info.kernel_rpl = 1;
 	/* Everyone except Xen runs with this set. */
 	pv_info.shared_kernel_pmd = 1;
-	pv_info.features = 0;
 
 	/*
 	 * We set up all the lguest overrides for sensitive operations.  These

arch/x86/mm/ident_map.c

@@ -0,0 +1,79 @@
+/*
+ * Helper routines for building identity mapping page tables. This is
+ * included by both the compressed kernel and the regular kernel.
+ */
+
+static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
+			   unsigned long addr, unsigned long end)
+{
+	addr &= PMD_MASK;
+	for (; addr < end; addr += PMD_SIZE) {
+		pmd_t *pmd = pmd_page + pmd_index(addr);
+
+		if (!pmd_present(*pmd))
+			set_pmd(pmd, __pmd(addr | pmd_flag));
+	}
+}
+
+static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
+			  unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+
+	for (; addr < end; addr = next) {
+		pud_t *pud = pud_page + pud_index(addr);
+		pmd_t *pmd;
+
+		next = (addr & PUD_MASK) + PUD_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pud_present(*pud)) {
+			pmd = pmd_offset(pud, 0);
+			ident_pmd_init(info->pmd_flag, pmd, addr, next);
+			continue;
+		}
+		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
+		if (!pmd)
+			return -ENOMEM;
+		ident_pmd_init(info->pmd_flag, pmd, addr, next);
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}
+
+int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
+			      unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	int result;
+	int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
+
+	for (; addr < end; addr = next) {
+		pgd_t *pgd = pgd_page + pgd_index(addr) + off;
+		pud_t *pud;
+
+		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pgd_present(*pgd)) {
+			pud = pud_offset(pgd, 0);
+			result = ident_pud_init(info, pud, addr, next);
+			if (result)
+				return result;
+			continue;
+		}
+
+		pud = (pud_t *)info->alloc_pgt_page(info->context);
+		if (!pud)
+			return -ENOMEM;
+		result = ident_pud_init(info, pud, addr, next);
+		if (result)
+			return result;
+		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}

arch/x86/mm/init_32.c

@@ -804,9 +804,6 @@ void __init mem_init(void)
 	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
 #undef high_memory
 #undef __FIXADDR_TOP
-#ifdef CONFIG_RANDOMIZE_BASE
-	BUILD_BUG_ON(CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE);
-#endif
 
 #ifdef CONFIG_HIGHMEM
 	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);

arch/x86/mm/init_64.c

@@ -58,79 +58,7 @@
 
 #include "mm_internal.h"
 
-static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
+#include "ident_map.c"
-			   unsigned long addr, unsigned long end)
-{
-	addr &= PMD_MASK;
-	for (; addr < end; addr += PMD_SIZE) {
-		pmd_t *pmd = pmd_page + pmd_index(addr);
-
-		if (!pmd_present(*pmd))
-			set_pmd(pmd, __pmd(addr | pmd_flag));
-	}
-}
-static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
-			  unsigned long addr, unsigned long end)
-{
-	unsigned long next;
-
-	for (; addr < end; addr = next) {
-		pud_t *pud = pud_page + pud_index(addr);
-		pmd_t *pmd;
-
-		next = (addr & PUD_MASK) + PUD_SIZE;
-		if (next > end)
-			next = end;
-
-		if (pud_present(*pud)) {
-			pmd = pmd_offset(pud, 0);
-			ident_pmd_init(info->pmd_flag, pmd, addr, next);
-			continue;
-		}
-		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
-		if (!pmd)
-			return -ENOMEM;
-		ident_pmd_init(info->pmd_flag, pmd, addr, next);
-		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
-	}
-
-	return 0;
-}
-
-int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
-			      unsigned long addr, unsigned long end)
-{
-	unsigned long next;
-	int result;
-	int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
-
-	for (; addr < end; addr = next) {
-		pgd_t *pgd = pgd_page + pgd_index(addr) + off;
-		pud_t *pud;
-
-		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
-		if (next > end)
-			next = end;
-
-		if (pgd_present(*pgd)) {
-			pud = pud_offset(pgd, 0);
-			result = ident_pud_init(info, pud, addr, next);
-			if (result)
-				return result;
-			continue;
-		}
-
-		pud = (pud_t *)info->alloc_pgt_page(info->context);
-		if (!pud)
-			return -ENOMEM;
-		result = ident_pud_init(info, pud, addr, next);
-		if (result)
-			return result;
-		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
-	}
-
-	return 0;
-}
 
 /*
  * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the

arch/x86/tools/calc_run_size.sh

@@ -1,42 +0,0 @@
-#!/bin/sh
-#
-# Calculate the amount of space needed to run the kernel, including room for
-# the .bss and .brk sections.
-#
-# Usage:
-# objdump -h a.out | sh calc_run_size.sh
-
-NUM='\([0-9a-fA-F]*[ \t]*\)'
-OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p')
-if [ -z "$OUT" ] ; then
-	echo "Never found .bss or .brk file offset" >&2
-	exit 1
-fi
-
-OUT=$(echo ${OUT# })
-sizeA=$(printf "%d" 0x${OUT%% *})
-OUT=${OUT#* }
-offsetA=$(printf "%d" 0x${OUT%% *})
-OUT=${OUT#* }
-sizeB=$(printf "%d" 0x${OUT%% *})
-OUT=${OUT#* }
-offsetB=$(printf "%d" 0x${OUT%% *})
-
-run_size=$(( $offsetA + $sizeA + $sizeB ))
-
-# BFD linker shows the same file offset in ELF.
-if [ "$offsetA" -ne "$offsetB" ] ; then
-	# Gold linker shows them as consecutive.
-	endB=$(( $offsetB + $sizeB ))
-	if [ "$endB" != "$run_size" ] ; then
-		printf "sizeA: 0x%x\n" $sizeA >&2
-		printf "offsetA: 0x%x\n" $offsetA >&2
-		printf "sizeB: 0x%x\n" $sizeB >&2
-		printf "offsetB: 0x%x\n" $offsetB >&2
-		echo ".bss and .brk are non-contiguous" >&2
-		exit 1
-	fi
-fi
-
-printf "%d\n" $run_size
-exit 0

arch/x86/xen/enlighten.c

@@ -1206,13 +1206,11 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 }
 
 static const struct pv_info xen_info __initconst = {
-	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 
 #ifdef CONFIG_X86_64
 	.extra_user_64bit_cs = FLAT_USER_CS64,
 #endif
-	.features = 0,
 	.name = "Xen",
 };
 
@@ -1528,6 +1526,11 @@ static void __init xen_pvh_early_guest_init(void)
 }
 #endif    /* CONFIG_XEN_PVH */
 
+static void __init xen_dom0_set_legacy_features(void)
+{
+	x86_platform.legacy.rtc = 1;
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
@@ -1548,8 +1551,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
-	if (xen_initial_domain())
-		pv_info.features |= PV_SUPPORTED_RTC;
 	pv_init_ops = xen_init_ops;
 	if (!xen_pvh_domain()) {
 		pv_cpu_ops = xen_cpu_ops;
@@ -1684,6 +1685,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	boot_params.hdr.ramdisk_image = initrd_start;
 	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
 	boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
+	boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN;
 
 	if (!xen_initial_domain()) {
 		add_preferred_console("xenboot", 0, NULL);
@@ -1701,6 +1703,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 			.u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
 		};
 
+		x86_platform.set_legacy_features =
+				xen_dom0_set_legacy_features;
 		xen_init_vga(info, xen_start_info->console.dom0.info_size);
 		xen_start_info->console.domU.mfn = 0;
 		xen_start_info->console.domU.evtchn = 0;

drivers/pnp/pnpbios/core.c

@@ -521,10 +521,11 @@ static int __init pnpbios_init(void)
 	int ret;
 
 	if (pnpbios_disabled || dmi_check_system(pnpbios_dmi_table) ||
-	    paravirt_enabled()) {
+	    arch_pnpbios_disabled()) {
 		printk(KERN_INFO "PnPBIOS: Disabled\n");
 		return -ENODEV;
 	}
+
 #ifdef CONFIG_PNPACPI
 	if (!acpi_disabled && !pnpacpi_disabled) {
 		pnpbios_disabled = 1;

include/linux/pnp.h

@@ -337,9 +337,11 @@ extern struct mutex pnp_res_mutex;
 
 #ifdef CONFIG_PNPBIOS
 extern struct pnp_protocol pnpbios_protocol;
+extern bool arch_pnpbios_disabled(void);
 #define pnp_device_is_pnpbios(dev) ((dev)->protocol == (&pnpbios_protocol))
 #else
 #define pnp_device_is_pnpbios(dev) 0
+#define arch_pnpbios_disabled()	false
 #endif
 
 #ifdef CONFIG_PNPACPI

tools/lguest/lguest.c

@@ -3351,12 +3351,18 @@ int main(int argc, char *argv[])
 	/* Boot protocol version: 2.07 supports the fields for lguest. */
 	boot->hdr.version = 0x207;
 
-	/* The hardware_subarch value of "1" tells the Guest it's an lguest. */
+	/* X86_SUBARCH_LGUEST tells the Guest it's an lguest. */
-	boot->hdr.hardware_subarch = 1;
+	boot->hdr.hardware_subarch = X86_SUBARCH_LGUEST;
 
 	/* Tell the entry path not to try to reload segment registers. */
 	boot->hdr.loadflags |= KEEP_SEGMENTS;
 
+	/* We don't support tboot: */
+	boot->tboot_addr = 0;
+
+	/* Ensure this is 0 to prevent APM from loading: */
+	boot->apm_bios_info.version = 0;
+
 	/* We tell the kernel to initialize the Guest. */
 	tell_kernel(start);