commit 860d7d2f64bf5ce79d387b3dcee915797afc4e31 Author: vanten-s Date: Thu Jul 11 08:56:52 2024 +0200 Init diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..796b96d --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +/build diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..0783759 --- /dev/null +++ b/Makefile @@ -0,0 +1,50 @@ +ARCHDIR=../arch/i686 + + +CFLAGS=-O2 \ +-std=gnu99 \ +-ffreestanding \ +-Wall -Wextra \ +-I $(INCLUDEDIR) + + +KERNEL_OBJS=kernel.o +LIB_OBJS=bootstrap.o \ +tty.o\ +strlib.o\ +interrupt.o +OBJS=$(KERNEL_OBJS) $(LIB_OBJS) +LDFLAGS=$(OBJS) \ +-ffreestanding \ +-O2 \ +-nostdlib \ +-lgcc + + +INCLUDEDIR=../include + + +all: + mkdir build || true + cp Makefile build + $(MAKE) -C build test-kernel-qemu + +architecture: + i686-elf-as $(ARCHDIR)/bootstrap.s -o bootstrap.o + + i686-elf-gcc -c $(ARCHDIR)/tty.c -o tty.o $(CFLAGS) + i686-elf-gcc -c $(ARCHDIR)/interrupt.c -o interrupt.o $(CFLAGS) + i686-elf-gcc -c $(ARCHDIR)/strlib.c -o strlib.o $(CFLAGS) + +kernel: + i686-elf-gcc -c ../kernel/kernel.c -o kernel.o $(CFLAGS) + + +myos-bin: architecture kernel + i686-elf-gcc -T $(ARCHDIR)/linker.ld -o myos.bin $(LDFLAGS) + + grub-file --is-x86-multiboot myos.bin + +test-kernel-qemu: myos-bin + qemu-system-i386 -kernel myos.bin + diff --git a/arch/i686/bootstrap.s b/arch/i686/bootstrap.s new file mode 100644 index 0000000..66c98bc --- /dev/null +++ b/arch/i686/bootstrap.s @@ -0,0 +1,109 @@ +/* Declare constants for the multiboot header. */ +.set ALIGN, 1<<0 /* align loaded modules on page boundaries */ +.set MEMINFO, 1<<1 /* provide memory map */ +.set FLAGS, ALIGN | MEMINFO /* this is the Multiboot 'flag' field */ +.set MAGIC, 0x1BADB002 /* 'magic number' lets bootloader find the header */ +.set CHECKSUM, -(MAGIC + FLAGS) /* checksum of above, to prove we are multiboot */ + +/* +Declare a multiboot header that marks the program as a kernel. These are magic +values that are documented in the multiboot standard. The bootloader will +search for this signature in the first 8 KiB of the kernel file, aligned at a +32-bit boundary. The signature is in its own section so the header can be +forced to be within the first 8 KiB of the kernel file. +*/ +.section .multiboot +.align 4 +.long MAGIC +.long FLAGS +.long CHECKSUM + +/* +The multiboot standard does not define the value of the stack pointer register +(esp) and it is up to the kernel to provide a stack. This allocates room for a +small stack by creating a symbol at the bottom of it, then allocating 16384 +bytes for it, and finally creating a symbol at the top. The stack grows +downwards on x86. The stack is in its own section so it can be marked nobits, +which means the kernel file is smaller because it does not contain an +uninitialized stack. The stack on x86 must be 16-byte aligned according to the +System V ABI standard and de-facto extensions. The compiler will assume the +stack is properly aligned and failure to align the stack will result in +undefined behavior. +*/ +.section .bss +.align 16 +stack_bottom: +.skip 16384 # 16 KiB +stack_top: + +/* +The linker script specifies _start as the entry point to the kernel and the +bootloader will jump to this position once the kernel has been loaded. It +doesn't make sense to return from this function as the bootloader is gone. +*/ +.section .text +.global _start +.type _start, @function +_start: + /* + The bootloader has loaded us into 32-bit protected mode on a x86 + machine. Interrupts are disabled. Paging is disabled. The processor + state is as defined in the multiboot standard. The kernel has full + control of the CPU. The kernel can only make use of hardware features + and any code it provides as part of itself. There's no printf + function, unless the kernel provides its own header and a + printf implementation. There are no security restrictions, no + safeguards, no debugging mechanisms, only what the kernel provides + itself. It has absolute and complete power over the + machine. + */ + + /* + To set up a stack, we set the esp register to point to the top of the + stack (as it grows downwards on x86 systems). This is necessarily done + in assembly as languages such as C cannot function without a stack. + */ + mov $stack_top, %esp + + /* + This is a good place to initialize crucial processor state before the + high-level kernel is entered. It's best to minimize the early + environment where crucial features are offline. Note that the + processor is not fully initialized yet: Features such as floating + point instructions and instruction set extensions are not initialized + yet. The GDT should be loaded here. Paging should be enabled here. + C++ features such as global constructors and exceptions will require + runtime support to work as well. + */ + + /* + Enter the high-level kernel. The ABI requires the stack is 16-byte + aligned at the time of the call instruction (which afterwards pushes + the return pointer of size 4 bytes). The stack was originally 16-byte + aligned above and we've pushed a multiple of 16 bytes to the + stack since (pushed 0 bytes so far), so the alignment has thus been + preserved and the call is well defined. + */ + call kernel_main + + /* + If the system has nothing more to do, put the computer into an + infinite loop. To do that: + 1) Disable interrupts with cli (clear interrupt enable in eflags). + They are already disabled by the bootloader, so this is not needed. + Mind that you might later enable interrupts and return from + kernel_main (which is sort of nonsensical to do). + 2) Wait for the next interrupt to arrive with hlt (halt instruction). + Since they are disabled, this will lock up the computer. + 3) Jump to the hlt instruction if it ever wakes up due to a + non-maskable interrupt occurring or due to system management mode. + */ + cli +1: hlt + jmp 1b + +/* +Set the size of the _start symbol to the current location '.' minus its start. +This is useful when debugging or when you implement call tracing. +*/ +.size _start, . - _start diff --git a/arch/i686/interrupt.c b/arch/i686/interrupt.c new file mode 100644 index 0000000..0ec6ef9 --- /dev/null +++ b/arch/i686/interrupt.c @@ -0,0 +1,16 @@ +#include +#include +#include + +const uint16_t NUM_ID = 0; + +void load_idt(struct InterruptDescriptorTable *idt) +{ + asm("lidt %0" : : "m"(idt)); +} + +void interrupt_initialize(struct InterruptDescriptorTable IDT) +{ + terminal_writestring("Loading IDT\n"); + load_idt(&IDT); +} diff --git a/arch/i686/linker.ld b/arch/i686/linker.ld new file mode 100644 index 0000000..f00fa2d --- /dev/null +++ b/arch/i686/linker.ld @@ -0,0 +1,52 @@ +/* The bootloader will look at this image and start execution at the symbol + designated as the entry point. */ +ENTRY(_start) + +/* Tell where the various sections of the object files will be put in the final + kernel image. */ +SECTIONS +{ + /* It used to be universally recommended to use 1M as a start offset, + as it was effectively guaranteed to be available under BIOS systems. + However, UEFI has made things more complicated, and experimental data + strongly suggests that 2M is a safer place to load. In 2016, a new + feature was introduced to the multiboot2 spec to inform bootloaders + that a kernel can be loaded anywhere within a range of addresses and + will be able to relocate itself to run from such a loader-selected + address, in order to give the loader freedom in selecting a span of + memory which is verified to be available by the firmware, in order to + work around this issue. This does not use that feature, so 2M was + chosen as a safer option than the traditional 1M. */ + . = 2M; + + /* First put the multiboot header, as it is required to be put very early + in the image or the bootloader won't recognize the file format. + Next we'll put the .text section. */ + .text BLOCK(4K) : ALIGN(4K) + { + *(.multiboot) + *(.text) + } + + /* Read-only data. */ + .rodata BLOCK(4K) : ALIGN(4K) + { + *(.rodata) + } + + /* Read-write data (initialized) */ + .data BLOCK(4K) : ALIGN(4K) + { + *(.data) + } + + /* Read-write data (uninitialized) and stack */ + .bss BLOCK(4K) : ALIGN(4K) + { + *(COMMON) + *(.bss) + } + + /* The compiler may produce other sections, by default it will put them in + a segment with the same name. Simply add stuff here as needed. */ +} diff --git a/arch/i686/strlib.c b/arch/i686/strlib.c new file mode 100644 index 0000000..73c42c6 --- /dev/null +++ b/arch/i686/strlib.c @@ -0,0 +1,44 @@ +#include + +size_t strlen(const char* str) +{ + size_t len = 0; + while (str[len]) + len++; + return len; +} + +char to_upper_char(char c) +{ + if ('a' <= c && c <= 'z') { + return c - 0x20; + } else { + return c; + } +} + +char to_lower_char(char c) +{ + if ('A' <= c && c <= 'Z') { + return c + 0x20; + } else { + return c; + } +} + +char* to_lower_str(char* str) +{ + for (size_t i = 0; i < strlen(str); i++) { + str[i] = to_lower_char(str[i]); + } + return str; +} + +char* to_upper_str(char* str) +{ + for (size_t i = 0; i < strlen(str); i++) { + str[i] = to_upper_char(str[i]); + } + return str; +} + diff --git a/arch/i686/tty.c b/arch/i686/tty.c new file mode 100644 index 0000000..346e3d6 --- /dev/null +++ b/arch/i686/tty.c @@ -0,0 +1,142 @@ +#include +#include +#include +#include + +/* Check if the compiler thinks you are targeting the wrong operating system. */ +#if defined(__linux__) +#error "You are not using a cross-compiler, you will most certainly run into trouble" +#endif + +/* This tutorial will only work for the 32-bit ix86 targets. */ +#if !defined(__i386__) +#error "This tutorial needs to be compiled with a ix86-elf compiler" +#endif + +/* Hardware text mode color constants. */ +enum vga_color { + VGA_COLOR_BLACK = 0, + VGA_COLOR_BLUE = 1, + VGA_COLOR_GREEN = 2, + VGA_COLOR_CYAN = 3, + VGA_COLOR_RED = 4, + VGA_COLOR_MAGENTA = 5, + VGA_COLOR_BROWN = 6, + VGA_COLOR_LIGHT_GREY = 7, + VGA_COLOR_DARK_GREY = 8, + VGA_COLOR_LIGHT_BLUE = 9, + VGA_COLOR_LIGHT_GREEN = 10, + VGA_COLOR_LIGHT_CYAN = 11, + VGA_COLOR_LIGHT_RED = 12, + VGA_COLOR_LIGHT_MAGENTA = 13, + VGA_COLOR_LIGHT_BROWN = 14, + VGA_COLOR_WHITE = 15, +}; + +static inline uint8_t vga_entry_color(enum vga_color fg, enum vga_color bg) +{ + return fg | bg << 4; +} + +static inline uint16_t vga_entry(unsigned char uc, uint8_t color) +{ + return (uint16_t) uc | (uint16_t) color << 8; +} + +static inline unsigned char vga_char(uint16_t entry) +{ + return entry & 0xFF; +} + +static inline uint8_t vga_color(uint16_t entry) +{ + return (entry >> 8) & 0xFF; +} + +static const size_t VGA_WIDTH = 80; +static const size_t VGA_HEIGHT = 25; + +size_t terminal_row; +size_t terminal_column; +uint8_t terminal_color; +uint16_t* terminal_buffer; + +void terminal_initialize(void) +{ + terminal_row = 0; + terminal_column = 0; + terminal_color = vga_entry_color(VGA_COLOR_LIGHT_GREY, VGA_COLOR_BLACK); + terminal_buffer = (uint16_t*) 0xB8000; + for (size_t y = 0; y < VGA_HEIGHT; y++) { + for (size_t x = 0; x < VGA_WIDTH; x++) { + const size_t index = y * VGA_WIDTH + x; + terminal_buffer[index] = vga_entry(' ', terminal_color); + } + } +} + +void terminal_setcolor(uint8_t color) +{ + terminal_color = color; +} + +static void terminal_putentryat(char c, uint8_t color, size_t x, size_t y) +{ + const size_t index = y * VGA_WIDTH + x; + terminal_buffer[index] = vga_entry(c, color); +} + +static uint16_t terminal_getentryat(size_t x, size_t y) +{ + const size_t index = y * VGA_WIDTH + x; + return terminal_buffer[index]; +} + +static void terminal_scroll() +{ + for (size_t y = 0; y < VGA_HEIGHT; y++) { + for (size_t x = 0; x < VGA_WIDTH; x++) { + if (y == VGA_HEIGHT - 1) { + terminal_putentryat(' ', terminal_color, x, y); + } + uint16_t entry = terminal_getentryat(x, y + 1); + char scrolled = vga_char(entry); + uint8_t color = vga_color(entry); + terminal_putentryat(scrolled, color, x, y); + } + } + terminal_row = VGA_HEIGHT - 1; + terminal_column = 0; +} + +static void terminal_newline() { + if (++terminal_row == VGA_HEIGHT) { + terminal_scroll(); + } + terminal_column = 0; +} + +void terminal_putchar(char c) +{ + if (c == '\n') { + terminal_newline(); + return; + } + terminal_putentryat(c, terminal_color, terminal_column, terminal_row); + if (++terminal_column == VGA_WIDTH) { + terminal_column = 0; + if (++terminal_row == VGA_HEIGHT) + terminal_scroll(); + } +} + +static void terminal_write(const char* data, size_t size) +{ + for (size_t i = 0; i < size; i++) + terminal_putchar(data[i]); +} + +void terminal_writestring(const char* data) +{ + terminal_write(data, strlen(data)); +} diff --git a/include/debugging.c b/include/debugging.c new file mode 100644 index 0000000..6fdc74f --- /dev/null +++ b/include/debugging.c @@ -0,0 +1,146 @@ +#include +#include +#include +#include + +static inline uint8_t inb(uint16_t port) +{ + uint8_t ret; + __asm__ volatile ( "inb %w1, %b0" + : "=a"(ret) + : "Nd"(port) + : "memory"); + return ret; +} + +bool is_in_shift; + +static unsigned char keyboard_char(unsigned char scancode) { + if (0x01 < scancode && scancode < 0x0B) { + return scancode - 2 + '1'; + } + + if (scancode == 0x0B) { + return '0'; + } + + switch (scancode) { + case 0x10: + return 'Q'; + case 0x11: + return 'W'; + case 0x12: + return 'E'; + case 0x13: + return 'R'; + case 0x14: + return 'T'; + case 0x15: + return 'Y'; + case 0x16: + return 'U'; + case 0x17: + return 'I'; + case 0x18: + return 'O'; + case 0x19: + return 'P'; + case 0x1a: + return '['; + case 0x1b: + return ']'; + case 0x1c: + return '\n'; + case 0x1d: + return '\b'; + case 0x1e: + return 'A'; + case 0x1f: + return 'S'; + case 0x20: + return 'D'; + case 0x21: + return 'F'; + case 0x22: + return 'G'; + case 0x23: + return 'H'; + case 0x24: + return 'J'; + case 0x25: + return 'K'; + case 0x26: + return 'L'; + case 0x27: + return ';'; + case 0x28: + return '\''; + case 0x29: + return '`'; + case 0x2a: + is_in_shift = true; + break; + case 0x2b: + return '\\'; + case 0x2c: + return 'Z'; + case 0x2d: + return 'X'; + case 0x2e: + return 'C'; + case 0x2f: + return 'V'; + case 0x30: + return 'B'; + case 0x31: + return 'N'; + case 0x32: + return 'M'; + case 0x33: + return ','; + case 0x34: + return '.'; + case 0x35: + return '/'; + case 0x36: + is_in_shift = true; + break; + case 0x39: + return ' '; + case 0xaa: + is_in_shift = false; + break; + case 0xb6: + is_in_shift = false; + break; + } + + return -1; +} + +char get_last_key_pressed() { + char scancode = inb(0x60); + + if (is_in_shift) { + return keyboard_char(scancode); + } + + return to_lower_char(keyboard_char(scancode)); +} + +void print_hex_digit(uint8_t digit) { + digit = digit & 0xf; + if (digit < 0xA) { + terminal_putchar(digit + 0x30); + } else { + terminal_putchar(digit + 0x41 - 0xA); + } +} + +void print_hex_byte(uint8_t byte) { + int upper = byte >> 4; + int lower = byte & 0x0F; + + print_hex_digit(upper); + print_hex_digit(lower); +} diff --git a/include/kernel/interrupt.h b/include/kernel/interrupt.h new file mode 100644 index 0000000..1d94c45 --- /dev/null +++ b/include/kernel/interrupt.h @@ -0,0 +1,14 @@ +#include + +struct InterruptDescriptor +{ + +}; + +struct InterruptDescriptorTable +{ + uint16_t limit; /* Size of IDT array - 1 */ + struct InterruptDescriptor* base; /* Pointer to IDT array */ +} __attribute__((packed)); + +void interrupt_initialize(struct InterruptDescriptorTable IDT); diff --git a/include/kernel/tty.h b/include/kernel/tty.h new file mode 100644 index 0000000..7d5095c --- /dev/null +++ b/include/kernel/tty.h @@ -0,0 +1,6 @@ +#include + +void terminal_writestring(const char* data); +void terminal_initialize(void); +void terminal_putchar(char c); +void terminal_setcolor(uint8_t color); diff --git a/include/strlib.h b/include/strlib.h new file mode 100644 index 0000000..51b078a --- /dev/null +++ b/include/strlib.h @@ -0,0 +1,8 @@ +#include + +size_t strlen(const char* str); + +char to_upper_char(char c); +char to_lower_char(char c); +char* to_lower_str(char* str); +char* to_upper_str(char* str); diff --git a/kernel/kernel.c b/kernel/kernel.c new file mode 100644 index 0000000..d934a07 --- /dev/null +++ b/kernel/kernel.c @@ -0,0 +1,27 @@ +#include +#include +#include + +void kernel_main(void) +{ + /* Initialize terminal interface */ + terminal_initialize(); + + terminal_putchar(get_last_key_pressed()); + + char current_character = get_last_key_pressed(); + while (current_character != ',') { + char tmp = get_last_key_pressed(); + if (current_character != -1 && tmp != current_character) { + terminal_putchar(current_character); + } + current_character = tmp; + } + + struct InterruptDescriptorTable IDTR = { + + }; + interrupt_initialize(IDTR); + + terminal_writestring("Hello World!"); +}