xv6OSを真面目に読みこんでカーネルを完全に理解する -ブートストラップ編-

# Makefile
xv6.img: bootblock kernel
	dd if=/dev/zero of=xv6.img count=10000
	dd if=bootblock of=xv6.img conv=notrunc
	dd if=kernel of=xv6.img seek=1 conv=notrunc

# Makefile
UPROGS=\
	_cat\
	_echo\
	_forktest\
	_grep\
	_init\
	_kill\
	_ln\
	_ls\
	_mkdir\
	_rm\
	_sh\
	_stressfs\
	_usertests\
	_wc\
	_zombie\

mkfs: mkfs.c fs.h
	gcc -Werror -Wall -o mkfs mkfs.c

fs.img: mkfs README $(UPROGS)
	./mkfs fs.img README $(UPROGS)

bootblock: bootasm.S bootmain.c
	$(CC) $(CFLAGS) -fno-pic -O -nostdinc -I. -c bootmain.c
	$(CC) $(CFLAGS) -fno-pic -nostdinc -I. -c bootasm.S
	$(LD) $(LDFLAGS) -N -e start -Ttext 0x7C00 -o bootblock.o bootasm.o bootmain.o
	$(OBJDUMP) -S bootblock.o > bootblock.asm
	$(OBJCOPY) -S -O binary -j .text bootblock.o bootblock
	./sign.pl bootblock

# Cross-compiling (e.g., on Mac OS X)
# TOOLPREFIX = i386-jos-elf

# Using native tools (e.g., on X86 Linux)
#TOOLPREFIX = 

# Try to infer the correct TOOLPREFIX if not set
ifndef TOOLPREFIX
TOOLPREFIX := $(shell if i386-jos-elf-objdump -i 2>&1 | grep '^elf32-i386$$' >/dev/null 2>&1; \
	then echo 'i386-jos-elf-'; \
	elif objdump -i 2>&1 | grep 'elf32-i386' >/dev/null 2>&1; \
	then echo ''; \
	else echo "***" 1>&2; \
	echo "*** Error: Couldn't find an i386-*-elf version of GCC/binutils." 1>&2; \
	echo "*** Is the directory with i386-jos-elf-gcc in your PATH?" 1>&2; \
	echo "*** If your i386-*-elf toolchain is installed with a command" 1>&2; \
	echo "*** prefix other than 'i386-jos-elf-', set your TOOLPREFIX" 1>&2; \
	echo "*** environment variable to that prefix and run 'make' again." 1>&2; \
	echo "*** To turn off this error, run 'gmake TOOLPREFIX= ...'." 1>&2; \
	echo "***" 1>&2; exit 1; fi)
endif

CC = $(TOOLPREFIX)gcc

CFLAGS = -fno-pic -static -fno-builtin -fno-strict-aliasing -O2 -Wall -MD -ggdb -m32 -Werror -fno-omit-frame-pointer
CFLAGS += $(shell $(CC) -fno-stack-protector -E -x c /dev/null >/dev/null 2>&1 && echo -fno-stack-protector)

// Boot loader.
//
// Part of the boot block, along with bootasm.S, which calls bootmain().
// bootasm.S has put the processor into protected 32-bit mode.
// bootmain() loads an ELF kernel image from the disk starting at
// sector 1 and then jumps to the kernel entry routine.

#include "types.h"
#include "elf.h"
#include "x86.h"
#include "memlayout.h"

#define SECTSIZE  512

void readseg(uchar*, uint, uint);

void
bootmain(void)
{
  struct elfhdr *elf;
  struct proghdr *ph, *eph;
  void (*entry)(void);
  uchar* pa;

  elf = (struct elfhdr*)0x10000;  // scratch space

  // Read 1st page off disk
  readseg((uchar*)elf, 4096, 0);

  // Is this an ELF executable?
  if(elf->magic != ELF_MAGIC)
    return;  // let bootasm.S handle error

  // Load each program segment (ignores ph flags).
  ph = (struct proghdr*)((uchar*)elf + elf->phoff);
  eph = ph + elf->phnum;
  for(; ph < eph; ph++){
    pa = (uchar*)ph->paddr;
    readseg(pa, ph->filesz, ph->off);
    if(ph->memsz > ph->filesz)
      stosb(pa + ph->filesz, 0, ph->memsz - ph->filesz);
  }

  // Call the entry point from the ELF header.
  // Does not return!
  entry = (void(*)(void))(elf->entry);
  entry();
}

void
waitdisk(void)
{
  // Wait for disk ready.
  while((inb(0x1F7) & 0xC0) != 0x40)
    ;
}

// Read a single sector at offset into dst.
void
readsect(void *dst, uint offset)
{
  // Issue command.
  waitdisk();
  outb(0x1F2, 1);   // count = 1
  outb(0x1F3, offset);
  outb(0x1F4, offset >> 8);
  outb(0x1F5, offset >> 16);
  outb(0x1F6, (offset >> 24) | 0xE0);
  outb(0x1F7, 0x20);  // cmd 0x20 - read sectors

  // Read data.
  waitdisk();
  insl(0x1F0, dst, SECTSIZE/4);
}

// Read 'count' bytes at 'offset' from kernel into physical address 'pa'.
// Might copy more than asked.
void
readseg(uchar* pa, uint count, uint offset)
{
  uchar* epa;

  epa = pa + count;

  // Round down to sector boundary.
  pa -= offset % SECTSIZE;

  // Translate from bytes to sectors; kernel starts at sector 1.
  offset = (offset / SECTSIZE) + 1;

  // If this is too slow, we could read lots of sectors at a time.
  // We'd write more to memory than asked, but it doesn't matter --
  // we load in increasing order.
  for(; pa < epa; pa += SECTSIZE, offset++)
    readsect(pa, offset);
}

#include "asm.h"
#include "memlayout.h"
#include "mmu.h"

# Start the first CPU: switch to 32-bit protected mode, jump into C.
# The BIOS loads this code from the first sector of the hard disk into
# memory at physical address 0x7c00 and starts executing in real mode
# with %cs=0 %ip=7c00.

.code16                       # Assemble for 16-bit mode
.globl start
start:
  cli                         # BIOS enabled interrupts; disable

  # Zero data segment registers DS, ES, and SS.
  xorw    %ax,%ax             # Set %ax to zero
  movw    %ax,%ds             # -> Data Segment
  movw    %ax,%es             # -> Extra Segment
  movw    %ax,%ss             # -> Stack Segment

  # Physical address line A20 is tied to zero so that the first PCs 
  # with 2 MB would run software that assumed 1 MB.  Undo that.
seta20.1:
  inb     $0x64,%al               # Wait for not busy
  testb   $0x2,%al
  jnz     seta20.1

  movb    $0xd1,%al               # 0xd1 -> port 0x64
  outb    %al,$0x64

seta20.2:
  inb     $0x64,%al               # Wait for not busy
  testb   $0x2,%al
  jnz     seta20.2

  movb    $0xdf,%al               # 0xdf -> port 0x60
  outb    %al,$0x60

  # Switch from real to protected mode.  Use a bootstrap GDT that makes
  # virtual addresses map directly to physical addresses so that the
  # effective memory map doesn't change during the transition.
  lgdt    gdtdesc
  movl    %cr0, %eax
  orl     $CR0_PE, %eax
  movl    %eax, %cr0

//PAGEBREAK!
  # Complete the transition to 32-bit protected mode by using a long jmp
  # to reload %cs and %eip.  The segment descriptors are set up with no
  # translation, so that the mapping is still the identity mapping.
  ljmp    $(SEG_KCODE<<3), $start32

.code32  # Tell assembler to generate 32-bit code now.
start32:
  # Set up the protected-mode data segment registers
  movw    $(SEG_KDATA<<3), %ax    # Our data segment selector
  movw    %ax, %ds                # -> DS: Data Segment
  movw    %ax, %es                # -> ES: Extra Segment
  movw    %ax, %ss                # -> SS: Stack Segment
  movw    $0, %ax                 # Zero segments not ready for use
  movw    %ax, %fs                # -> FS
  movw    %ax, %gs                # -> GS

  # Set up the stack pointer and call into C.
  movl    $start, %esp
  call    bootmain

  # If bootmain returns (it shouldn't), trigger a Bochs
  # breakpoint if running under Bochs, then loop.
  movw    $0x8a00, %ax            # 0x8a00 -> port 0x8a00
  movw    %ax, %dx
  outw    %ax, %dx
  movw    $0x8ae0, %ax            # 0x8ae0 -> port 0x8a00
  outw    %ax, %dx
spin:
  jmp     spin

# Bootstrap GDT
.p2align 2                                # force 4 byte alignment
gdt:
  SEG_NULLASM                             # null seg
  SEG_ASM(STA_X|STA_R, 0x0, 0xffffffff)   # code seg
  SEG_ASM(STA_W, 0x0, 0xffffffff)         # data seg

gdtdesc:
  .word   (gdtdesc - gdt - 1)             # sizeof(gdt) - 1
  .long   gdt                             # address gdt

ld -m elf_i386 -N -e start -Ttext 0x7C00 -o bootblock.o bootasm.o bootmain.o

#include "asm.h"
#include "memlayout.h"
#include "mmu.h"

# Start the first CPU: switch to 32-bit protected mode, jump into C.
# The BIOS loads this code from the first sector of the hard disk into
# memory at physical address 0x7c00 and starts executing in real mode
# with %cs=0 %ip=7c00.

.code16                       # Assemble for 16-bit mode
.globl start
start:
  cli                         # BIOS enabled interrupts; disable

  # Zero data segment registers DS, ES, and SS.
  xorw    %ax,%ax             # Set %ax to zero
  movw    %ax,%ds             # -> Data Segment
  movw    %ax,%es             # -> Extra Segment
  movw    %ax,%ss             # -> Stack Segment

  # Physical address line A20 is tied to zero so that the first PCs 
  # with 2 MB would run software that assumed 1 MB.  Undo that.
seta20.1:
  inb     $0x64,%al               # Wait for not busy
  testb   $0x2,%al
  jnz     seta20.1

  movb    $0xd1,%al               # 0xd1 -> port 0x64
  outb    %al,$0x64

seta20.2:
  inb     $0x64,%al               # Wait for not busy
  testb   $0x2,%al
  jnz     seta20.2

  movb    $0xdf,%al               # 0xdf -> port 0x60
  outb    %al,$0x60

  # Switch from real to protected mode.  Use a bootstrap GDT that makes
  # virtual addresses map directly to physical addresses so that the
  # effective memory map doesn't change during the transition.
  lgdt    gdtdesc
  movl    %cr0, %eax
  orl     $CR0_PE, %eax
  movl    %eax, %cr0

//PAGEBREAK!
  # Complete the transition to 32-bit protected mode by using a long jmp
  # to reload %cs and %eip.  The segment descriptors are set up with no
  # translation, so that the mapping is still the identity mapping.
  ljmp    $(SEG_KCODE<<3), $start32

.code32  # Tell assembler to generate 32-bit code now.
start32:
{{ 省略 }}

.code16                       # Assemble for 16-bit mode
.globl start
start:
  cli                         # BIOS enabled interrupts; disable

  # Zero data segment registers DS, ES, and SS.
  xorw    %ax,%ax             # Set %ax to zero
  movw    %ax,%ds             # -> Data Segment
  movw    %ax,%es             # -> Extra Segment
  movw    %ax,%ss             # -> Stack Segment

  # Physical address line A20 is tied to zero so that the first PCs 
  # with 2 MB would run software that assumed 1 MB.  Undo that.
seta20.1:
  inb     $0x64,%al               # Wait for not busy
  testb   $0x2,%al
  jnz     seta20.1

  movb    $0xd1,%al               # 0xd1 -> port 0x64
  outb    %al,$0x64

seta20.2:
  inb     $0x64,%al               # Wait for not busy
  testb   $0x2,%al
  jnz     seta20.2

  movb    $0xdf,%al               # 0xdf -> port 0x60
  outb    %al,$0x60

  # Switch from real to protected mode.  Use a bootstrap GDT that makes
  # virtual addresses map directly to physical addresses so that the
  # effective memory map doesn't change during the transition.
  lgdt    gdtdesc
  movl    %cr0, %eax
  orl     $CR0_PE, %eax
  movl    %eax, %cr0

//PAGEBREAK!
  # Complete the transition to 32-bit protected mode by using a long jmp
  # to reload %cs and %eip.  The segment descriptors are set up with no
  # translation, so that the mapping is still the identity mapping.
  ljmp    $(SEG_KCODE<<3), $start32

.code32  # Tell assembler to generate 32-bit code now.
start32:

movl    %cr0, %eax
orl     $CR0_PE, %eax
movl    %eax, %cr0

# Bootstrap GDT
.p2align 2                                # force 4 byte alignment
gdt:
  SEG_NULLASM                             # null seg
  SEG_ASM(STA_X|STA_R, 0x0, 0xffffffff)   # code seg
  SEG_ASM(STA_W, 0x0, 0xffffffff)         # data seg

gdtdesc:
  .word   (gdtdesc - gdt - 1)             # sizeof(gdt) - 1
  .long   gdt                             # address gdt

//
// assembler macros to create x86 segments
//

#define SEG_NULLASM                                             \
        .word 0, 0;                                             \
        .byte 0, 0, 0, 0

// The 0xC0 means the limit is in 4096-byte units
// and (for executable segments) 32-bit mode.
#define SEG_ASM(type,base,lim)                                  \
        .word (((lim) >> 12) & 0xffff), ((base) & 0xffff);      \
        .byte (((base) >> 16) & 0xff), (0x90 | (type)),         \
                (0xC0 | (((lim) >> 28) & 0xf)), (((base) >> 24) & 0xff)

#define STA_X     0x8       // Executable segment
#define STA_W     0x2       // Writeable (non-executable segments)
#define STA_R     0x2       // Readable (executable segments)

struct SEGMENT_DESCRIPTOR{
    short limit_low, base_low;
    char base_mid, access_right;
    char limit_high, base_high;
};

//PAGEBREAK!
  # Complete the transition to 32-bit protected mode by using a long jmp
  # to reload %cs and %eip.  The segment descriptors are set up with no
  # translation, so that the mapping is still the identity mapping.
  ljmp    $(SEG_KCODE<<3), $start32

.code32  # Tell assembler to generate 32-bit code now.
start32:

// various segment selectors.
#define SEG_KCODE 1  // kernel code
#define SEG_KDATA 2  // kernel data+stack
#define SEG_UCODE 3  // user code
#define SEG_UDATA 4  // user data+stack
#define SEG_TSS   5  // this process's task state

  lgdt    gdtdesc
  movl    %cr0, %eax
  orl     $CR0_PE, %eax
  movl    %eax, %cr0
  ljmp    $(SEG_KCODE<<3), $start32

.code32  # Tell assembler to generate 32-bit code now.
start32:
{{ 省略 }}

.code32  # Tell assembler to generate 32-bit code now.
start32:
  # Set up the protected-mode data segment registers
  movw    $(SEG_KDATA<<3), %ax    # Our data segment selector
  movw    %ax, %ds                # -> DS: Data Segment
  movw    %ax, %es                # -> ES: Extra Segment
  movw    %ax, %ss                # -> SS: Stack Segment
  movw    $0, %ax                 # Zero segments not ready for use
  movw    %ax, %fs                # -> FS
  movw    %ax, %gs                # -> GS

  # Set up the stack pointer and call into C.
  movl    $start, %esp
  call    bootmain

  # If bootmain returns (it shouldn't), trigger a Bochs
  # breakpoint if running under Bochs, then loop.
  movw    $0x8a00, %ax            # 0x8a00 -> port 0x8a00
  movw    %ax, %dx
  outw    %ax, %dx
  movw    $0x8ae0, %ax            # 0x8ae0 -> port 0x8a00
  outw    %ax, %dx
spin:
  jmp     spin

start32:
  # Set up the protected-mode data segment registers
  movw    $(SEG_KDATA<<3), %ax    # Our data segment selector
  movw    %ax, %ds                # -> DS: Data Segment
  movw    %ax, %es                # -> ES: Extra Segment
  movw    %ax, %ss                # -> SS: Stack Segment
  
  movw    $0, %ax                 # Zero segments not ready for use
  movw    %ax, %fs                # -> FS
  movw    %ax, %gs                # -> GS

# Set up the stack pointer and call into C.
movl    $start, %esp
call    bootmain

  # If bootmain returns (it shouldn't), trigger a Bochs
  # breakpoint if running under Bochs, then loop.
  movw    $0x8a00, %ax            # 0x8a00 -> port 0x8a00
  movw    %ax, %dx
  outw    %ax, %dx
  movw    $0x8ae0, %ax            # 0x8ae0 -> port 0x8a00
  outw    %ax, %dx
spin:
  jmp     spin

void bootmain(void)
{
  struct elfhdr *elf;
  struct proghdr *ph, *eph;
  void (*entry)(void);
  uchar* pa;

  elf = (struct elfhdr*)0x10000;  // scratch space

  // Read 1st page off disk
  readseg((uchar*)elf, 4096, 0);

  // Is this an ELF executable?
  if(elf->magic != ELF_MAGIC)
    return;  // let bootasm.S handle error

  // Load each program segment (ignores ph flags).
  ph = (struct proghdr*)((uchar*)elf + elf->phoff);
  eph = ph + elf->phnum;
  for(; ph < eph; ph++){
    pa = (uchar*)ph->paddr;
    readseg(pa, ph->filesz, ph->off);
    if(ph->memsz > ph->filesz)
      stosb(pa + ph->filesz, 0, ph->memsz - ph->filesz);
  }

  // Call the entry point from the ELF header.
  // Does not return!
  entry = (void(*)(void))(elf->entry);
  entry();
}

// Format of an ELF executable file

#define ELF_MAGIC 0x464C457FU  // "\x7FELF" in little endian

// File header
struct elfhdr {
  uint magic;  // must equal ELF_MAGIC
  uchar elf[12];
  ushort type;
  ushort machine;
  uint version;
  uint entry;
  uint phoff;
  uint shoff;
  uint flags;
  ushort ehsize;
  ushort phentsize;
  ushort phnum;
  ushort shentsize;
  ushort shnum;
  ushort shstrndx;
};

// Program section header
struct proghdr {
  uint type;
  uint off;
  uint vaddr;
  uint paddr;
  uint filesz;
  uint memsz;
  uint flags;
  uint align;
};

// Values for Proghdr type
#define ELF_PROG_LOAD           1

// Flag bits for Proghdr flags
#define ELF_PROG_FLAG_EXEC      1
#define ELF_PROG_FLAG_WRITE     2
#define ELF_PROG_FLAG_READ      4

elf = (struct elfhdr*)0x10000;  // scratch space

// Read 1st page off disk
readseg((uchar*)elf, 4096, 0);

// Read 'count' bytes at 'offset' from kernel into physical address 'pa'.
// Might copy more than asked.
void readseg(uchar* pa, uint count, uint offset)
{
  uchar* epa;
  epa = pa + count;

  // Round down to sector boundary.
  pa -= offset % SECTSIZE;
  
  // Translate from bytes to sectors; kernel starts at sector 1.
  offset = (offset / SECTSIZE) + 1;

  // If this is too slow, we could read lots of sectors at a time.
  // We'd write more to memory than asked, but it doesn't matter --
  // we load in increasing order.
  for(; pa < epa; pa += SECTSIZE, offset++)
    readsect(pa, offset);
}

// Read a single sector at offset into dst.
void readsect(void *dst, uint offset)
{
  // Issue command.
  waitdisk();
  outb(0x1F2, 1);   // count = 1
  outb(0x1F3, offset);
  outb(0x1F4, offset >> 8);
  outb(0x1F5, offset >> 16);
  outb(0x1F6, (offset >> 24) | 0xE0);
  outb(0x1F7, 0x20);  // cmd 0x20 - read sectors

  // Read data.
  waitdisk();
  insl(0x1F0, dst, SECTSIZE/4);
}

// Is this an ELF executable?
if(elf->magic != ELF_MAGIC)
	return;  // let bootasm.S handle error

// Load each program segment (ignores ph flags).
ph = (struct proghdr*)((uchar*)elf + elf->phoff);
eph = ph + elf->phnum;
for(; ph < eph; ph++){
  pa = (uchar*)ph->paddr;
  readseg(pa, ph->filesz, ph->off);
  if(ph->memsz > ph->filesz)
    stosb(pa + ph->filesz, 0, ph->memsz - ph->filesz);
}

static inline void
stosb(void *addr, int data, int cnt)
{
  asm volatile("cld; rep stosb" :
               "=D" (addr), "=c" (cnt) :
               "0" (addr), "1" (cnt), "a" (data) :
               "memory", "cc");
}

// Call the entry point from the ELF header.
// Does not return!
entry = (void(*)(void))(elf->entry);
entry();