linux/arch/x86/boot/header.S
Nick Terrell 0fe4f4ef8c x86: Bump ZO_z_extra_bytes margin for zstd
Bump the ZO_z_extra_bytes margin for zstd.

Zstd needs 3 bytes per 128 KB, and has a 22 byte fixed overhead.
Zstd needs to maintain 128 KB of space at all times, since that is
the maximum block size. See the comments regarding in-place
decompression added in lib/decompress_unzstd.c for details.

The existing code is written so that all the compression algorithms use
the same ZO_z_extra_bytes. It is taken to be the maximum of the growth
rate plus the maximum fixed overhead. The comments just above this diff
state that:

Signed-off-by: Nick Terrell <terrelln@fb.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200730190841.2071656-6-nickrterrell@gmail.com
2020-07-31 11:49:08 +02:00

657 lines
18 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/*
* header.S
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Based on bootsect.S and setup.S
* modified by more people than can be counted
*
* Rewritten as a common file by H. Peter Anvin (Apr 2007)
*
* BIG FAT NOTE: We're in real mode using 64k segments. Therefore segment
* addresses must be multiplied by 16 to obtain their respective linear
* addresses. To avoid confusion, linear addresses are written using leading
* hex while segment addresses are written as segment:offset.
*
*/
#include <linux/pe.h>
#include <asm/segment.h>
#include <asm/boot.h>
#include <asm/page_types.h>
#include <asm/setup.h>
#include <asm/bootparam.h>
#include "boot.h"
#include "voffset.h"
#include "zoffset.h"
BOOTSEG = 0x07C0 /* original address of boot-sector */
SYSSEG = 0x1000 /* historical load address >> 4 */
#ifndef SVGA_MODE
#define SVGA_MODE ASK_VGA
#endif
#ifndef ROOT_RDONLY
#define ROOT_RDONLY 1
#endif
.code16
.section ".bstext", "ax"
.global bootsect_start
bootsect_start:
#ifdef CONFIG_EFI_STUB
# "MZ", MS-DOS header
.word MZ_MAGIC
#endif
# Normalize the start address
ljmp $BOOTSEG, $start2
start2:
movw %cs, %ax
movw %ax, %ds
movw %ax, %es
movw %ax, %ss
xorw %sp, %sp
sti
cld
movw $bugger_off_msg, %si
msg_loop:
lodsb
andb %al, %al
jz bs_die
movb $0xe, %ah
movw $7, %bx
int $0x10
jmp msg_loop
bs_die:
# Allow the user to press a key, then reboot
xorw %ax, %ax
int $0x16
int $0x19
# int 0x19 should never return. In case it does anyway,
# invoke the BIOS reset code...
ljmp $0xf000,$0xfff0
#ifdef CONFIG_EFI_STUB
.org 0x3c
#
# Offset to the PE header.
#
.long pe_header
#endif /* CONFIG_EFI_STUB */
.section ".bsdata", "a"
bugger_off_msg:
.ascii "Use a boot loader.\r\n"
.ascii "\n"
.ascii "Remove disk and press any key to reboot...\r\n"
.byte 0
#ifdef CONFIG_EFI_STUB
pe_header:
.long PE_MAGIC
coff_header:
#ifdef CONFIG_X86_32
.set image_file_add_flags, IMAGE_FILE_32BIT_MACHINE
.set pe_opt_magic, PE_OPT_MAGIC_PE32
.word IMAGE_FILE_MACHINE_I386
#else
.set image_file_add_flags, 0
.set pe_opt_magic, PE_OPT_MAGIC_PE32PLUS
.word IMAGE_FILE_MACHINE_AMD64
#endif
.word section_count # nr_sections
.long 0 # TimeDateStamp
.long 0 # PointerToSymbolTable
.long 1 # NumberOfSymbols
.word section_table - optional_header # SizeOfOptionalHeader
.word IMAGE_FILE_EXECUTABLE_IMAGE | \
image_file_add_flags | \
IMAGE_FILE_DEBUG_STRIPPED | \
IMAGE_FILE_LINE_NUMS_STRIPPED # Characteristics
optional_header:
.word pe_opt_magic
.byte 0x02 # MajorLinkerVersion
.byte 0x14 # MinorLinkerVersion
# Filled in by build.c
.long 0 # SizeOfCode
.long 0 # SizeOfInitializedData
.long 0 # SizeOfUninitializedData
# Filled in by build.c
.long 0x0000 # AddressOfEntryPoint
.long 0x0200 # BaseOfCode
#ifdef CONFIG_X86_32
.long 0 # data
#endif
extra_header_fields:
# PE specification requires ImageBase to be 64k aligned
.set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff
#ifdef CONFIG_X86_32
.long image_base # ImageBase
#else
.quad image_base # ImageBase
#endif
.long 0x20 # SectionAlignment
.long 0x20 # FileAlignment
.word 0 # MajorOperatingSystemVersion
.word 0 # MinorOperatingSystemVersion
.word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion
.word LINUX_EFISTUB_MINOR_VERSION # MinorImageVersion
.word 0 # MajorSubsystemVersion
.word 0 # MinorSubsystemVersion
.long 0 # Win32VersionValue
#
# The size of the bzImage is written in tools/build.c
#
.long 0 # SizeOfImage
.long 0x200 # SizeOfHeaders
.long 0 # CheckSum
.word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application)
.word 0 # DllCharacteristics
#ifdef CONFIG_X86_32
.long 0 # SizeOfStackReserve
.long 0 # SizeOfStackCommit
.long 0 # SizeOfHeapReserve
.long 0 # SizeOfHeapCommit
#else
.quad 0 # SizeOfStackReserve
.quad 0 # SizeOfStackCommit
.quad 0 # SizeOfHeapReserve
.quad 0 # SizeOfHeapCommit
#endif
.long 0 # LoaderFlags
.long (section_table - .) / 8 # NumberOfRvaAndSizes
.quad 0 # ExportTable
.quad 0 # ImportTable
.quad 0 # ResourceTable
.quad 0 # ExceptionTable
.quad 0 # CertificationTable
.quad 0 # BaseRelocationTable
# Section table
section_table:
#
# The offset & size fields are filled in by build.c.
#
.ascii ".setup"
.byte 0
.byte 0
.long 0
.long 0x0 # startup_{32,64}
.long 0 # Size of initialized data
# on disk
.long 0x0 # startup_{32,64}
.long 0 # PointerToRelocations
.long 0 # PointerToLineNumbers
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long IMAGE_SCN_CNT_CODE | \
IMAGE_SCN_MEM_READ | \
IMAGE_SCN_MEM_EXECUTE | \
IMAGE_SCN_ALIGN_16BYTES # Characteristics
#
# The EFI application loader requires a relocation section
# because EFI applications must be relocatable. The .reloc
# offset & size fields are filled in by build.c.
#
.ascii ".reloc"
.byte 0
.byte 0
.long 0
.long 0
.long 0 # SizeOfRawData
.long 0 # PointerToRawData
.long 0 # PointerToRelocations
.long 0 # PointerToLineNumbers
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long IMAGE_SCN_CNT_INITIALIZED_DATA | \
IMAGE_SCN_MEM_READ | \
IMAGE_SCN_MEM_DISCARDABLE | \
IMAGE_SCN_ALIGN_1BYTES # Characteristics
#ifdef CONFIG_EFI_MIXED
#
# The offset & size fields are filled in by build.c.
#
.asciz ".compat"
.long 0
.long 0x0
.long 0 # Size of initialized data
# on disk
.long 0x0
.long 0 # PointerToRelocations
.long 0 # PointerToLineNumbers
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long IMAGE_SCN_CNT_INITIALIZED_DATA | \
IMAGE_SCN_MEM_READ | \
IMAGE_SCN_MEM_DISCARDABLE | \
IMAGE_SCN_ALIGN_1BYTES # Characteristics
#endif
#
# The offset & size fields are filled in by build.c.
#
.ascii ".text"
.byte 0
.byte 0
.byte 0
.long 0
.long 0x0 # startup_{32,64}
.long 0 # Size of initialized data
# on disk
.long 0x0 # startup_{32,64}
.long 0 # PointerToRelocations
.long 0 # PointerToLineNumbers
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long IMAGE_SCN_CNT_CODE | \
IMAGE_SCN_MEM_READ | \
IMAGE_SCN_MEM_EXECUTE | \
IMAGE_SCN_ALIGN_16BYTES # Characteristics
.set section_count, (. - section_table) / 40
#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
# header, from the old boot sector.
.section ".header", "a"
.globl sentinel
sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */
.globl hdr
hdr:
setup_sects: .byte 0 /* Filled in by build.c */
root_flags: .word ROOT_RDONLY
syssize: .long 0 /* Filled in by build.c */
ram_size: .word 0 /* Obsolete */
vid_mode: .word SVGA_MODE
root_dev: .word 0 /* Filled in by build.c */
boot_flag: .word 0xAA55
# offset 512, entry point
.globl _start
_start:
# Explicitly enter this as bytes, or the assembler
# tries to generate a 3-byte jump here, which causes
# everything else to push off to the wrong offset.
.byte 0xeb # short (2-byte) jump
.byte start_of_setup-1f
1:
# Part 2 of the header, from the old setup.S
.ascii "HdrS" # header signature
.word 0x020f # header version number (>= 0x0105)
# or else old loadlin-1.5 will fail)
.globl realmode_swtch
realmode_swtch: .word 0, 0 # default_switch, SETUPSEG
start_sys_seg: .word SYSSEG # obsolete and meaningless, but just
# in case something decided to "use" it
.word kernel_version-512 # pointing to kernel version string
# above section of header is compatible
# with loadlin-1.5 (header v1.5). Don't
# change it.
type_of_loader: .byte 0 # 0 means ancient bootloader, newer
# bootloaders know to change this.
# See Documentation/x86/boot.rst for
# assigned ids
# flags, unused bits must be zero (RFU) bit within loadflags
loadflags:
.byte LOADED_HIGH # The kernel is to be loaded high
setup_move_size: .word 0x8000 # size to move, when setup is not
# loaded at 0x90000. We will move setup
# to 0x90000 then just before jumping
# into the kernel. However, only the
# loader knows how much data behind
# us also needs to be loaded.
code32_start: # here loaders can put a different
# start address for 32-bit code.
.long 0x100000 # 0x100000 = default for big kernel
ramdisk_image: .long 0 # address of loaded ramdisk image
# Here the loader puts the 32-bit
# address where it loaded the image.
# This only will be read by the kernel.
ramdisk_size: .long 0 # its size in bytes
bootsect_kludge:
.long 0 # obsolete
heap_end_ptr: .word _end+STACK_SIZE-512
# (Header version 0x0201 or later)
# space from here (exclusive) down to
# end of setup code can be used by setup
# for local heap purposes.
ext_loader_ver:
.byte 0 # Extended boot loader version
ext_loader_type:
.byte 0 # Extended boot loader type
cmd_line_ptr: .long 0 # (Header version 0x0202 or later)
# If nonzero, a 32-bit pointer
# to the kernel command line.
# The command line should be
# located between the start of
# setup and the end of low
# memory (0xa0000), or it may
# get overwritten before it
# gets read. If this field is
# used, there is no longer
# anything magical about the
# 0x90000 segment; the setup
# can be located anywhere in
# low memory 0x10000 or higher.
initrd_addr_max: .long 0x7fffffff
# (Header version 0x0203 or later)
# The highest safe address for
# the contents of an initrd
# The current kernel allows up to 4 GB,
# but leave it at 2 GB to avoid
# possible bootloader bugs.
kernel_alignment: .long CONFIG_PHYSICAL_ALIGN #physical addr alignment
#required for protected mode
#kernel
#ifdef CONFIG_RELOCATABLE
relocatable_kernel: .byte 1
#else
relocatable_kernel: .byte 0
#endif
min_alignment: .byte MIN_KERNEL_ALIGN_LG2 # minimum alignment
xloadflags:
#ifdef CONFIG_X86_64
# define XLF0 XLF_KERNEL_64 /* 64-bit kernel */
#else
# define XLF0 0
#endif
#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64)
/* kernel/boot_param/ramdisk could be loaded above 4g */
# define XLF1 XLF_CAN_BE_LOADED_ABOVE_4G
#else
# define XLF1 0
#endif
#ifdef CONFIG_EFI_STUB
# ifdef CONFIG_EFI_MIXED
# define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64)
# else
# ifdef CONFIG_X86_64
# define XLF23 XLF_EFI_HANDOVER_64 /* 64-bit EFI handover ok */
# else
# define XLF23 XLF_EFI_HANDOVER_32 /* 32-bit EFI handover ok */
# endif
# endif
#else
# define XLF23 0
#endif
#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC_CORE)
# define XLF4 XLF_EFI_KEXEC
#else
# define XLF4 0
#endif
#ifdef CONFIG_X86_64
#ifdef CONFIG_X86_5LEVEL
#define XLF56 (XLF_5LEVEL|XLF_5LEVEL_ENABLED)
#else
#define XLF56 XLF_5LEVEL
#endif
#else
#define XLF56 0
#endif
.word XLF0 | XLF1 | XLF23 | XLF4 | XLF56
cmdline_size: .long COMMAND_LINE_SIZE-1 #length of the command line,
#added with boot protocol
#version 2.06
hardware_subarch: .long 0 # subarchitecture, added with 2.07
# default to 0 for normal x86 PC
hardware_subarch_data: .quad 0
payload_offset: .long ZO_input_data
payload_length: .long ZO_z_input_len
setup_data: .quad 0 # 64-bit physical pointer to
# single linked list of
# struct setup_data
pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr
#
# 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
#
# LZ4 is even worse: data that cannot be further compressed grows by 0.4%,
# or one byte per 256 bytes. OTOH, we can safely get rid of the +128 as
# the size-dependent part now grows so fast.
#
# extra_bytes = (uncompressed_size >> 8) + 65536
#
# ZSTD compressed data grows by at most 3 bytes per 128K, and only has a 22
# byte fixed overhead but has a maximum block size of 128K, so it needs a
# larger margin.
#
# extra_bytes = (uncompressed_size >> 8) + 131072
#define ZO_z_extra_bytes ((ZO_z_output_len >> 8) + 131072)
#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
#else
# define INIT_SIZE VO_INIT_SIZE
#endif
init_size: .long INIT_SIZE # kernel initialization size
handover_offset: .long 0 # Filled in by build.c
kernel_info_offset: .long 0 # Filled in by build.c
# End of setup header #####################################################
.section ".entrytext", "ax"
start_of_setup:
# Force %es = %ds
movw %ds, %ax
movw %ax, %es
cld
# Apparently some ancient versions of LILO invoked the kernel with %ss != %ds,
# which happened to work by accident for the old code. Recalculate the stack
# pointer if %ss is invalid. Otherwise leave it alone, LOADLIN sets up the
# stack behind its own code, so we can't blindly put it directly past the heap.
movw %ss, %dx
cmpw %ax, %dx # %ds == %ss?
movw %sp, %dx
je 2f # -> assume %sp is reasonably set
# Invalid %ss, make up a new stack
movw $_end, %dx
testb $CAN_USE_HEAP, loadflags
jz 1f
movw heap_end_ptr, %dx
1: addw $STACK_SIZE, %dx
jnc 2f
xorw %dx, %dx # Prevent wraparound
2: # Now %dx should point to the end of our stack space
andw $~3, %dx # dword align (might as well...)
jnz 3f
movw $0xfffc, %dx # Make sure we're not zero
3: movw %ax, %ss
movzwl %dx, %esp # Clear upper half of %esp
sti # Now we should have a working stack
# We will have entered with %cs = %ds+0x20, normalize %cs so
# it is on par with the other segments.
pushw %ds
pushw $6f
lretw
6:
# Check signature at end of setup
cmpl $0x5a5aaa55, setup_sig
jne setup_bad
# Zero the bss
movw $__bss_start, %di
movw $_end+3, %cx
xorl %eax, %eax
subw %di, %cx
shrw $2, %cx
rep; stosl
# Jump to C code (should not return)
calll main
# Setup corrupt somehow...
setup_bad:
movl $setup_corrupt, %eax
calll puts
# Fall through...
.globl die
.type die, @function
die:
hlt
jmp die
.size die, .-die
.section ".initdata", "a"
setup_corrupt:
.byte 7
.string "No setup signature found...\n"