Initial commit:

Barebones kernel that can print to a "tty". Has some basic functions
like memcpy, strlen, etc.
A GDT is also present, however it has not yet been properly tested.
The folder structure is currently not optimal or well organized.

.gitignore

@@ -0,0 +1,5 @@
+*.o
+*.bin
+isodir/
+*.iso
+

Makefile

@@ -0,0 +1,25 @@
+CC=i686-elf-gcc
+
+.PHONY: iso run clean
+
+%.o: %.c
+	$(CC) -c $< -o $@ -std=gnu99 -ffreestanding -O2 -Wall -Wextra -pedantic -I.
+
+bootstrap.o: bootstrap.s
+	i686-elf-as bootstrap.s -o bootstrap.o
+
+kernel.bin: bootstrap.o kernel.o vga.o std/std.o
+	$(CC) -T linker.ld -o kernel.bin -ffreestanding -O2 -nostdlib bootstrap.o kernel.o vga.o std/std.o -lgcc
+
+iso: kernel.bin
+	mkdir -p isodir/boot/grub
+	cp kernel.bin isodir/boot/kernel.bin
+	cp extra/grub.cfg isodir/boot/grub/grub.cfg
+	grub-mkrescue -o generated-iso.iso isodir
+
+run: iso
+	qemu-system-i386 -cdrom generated-iso.iso
+
+clean:
+	rm -rf kernel.o bootstrap.o kernel.bin isodir generated-iso.iso
+

bootstrap.s

@@ -0,0 +1,126 @@
+/* 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:
+
+.section .data
+gdt_ptr:
+.word gdt_end - gdt - 1
+.long gdt
+gdt:
+// generated using https://wiki.osdev.org/GDT_Tutorial#Some_stuff_to_make_your_life_easy
+// signature for create_descriptor function: void create_descriptor(uint32_t base, uint32_t limit, uint16_t flag)
+.quad 0x0000000000000000 // create_descriptor(0, 0, 0);
+.quad 0x00CF9A000000FFFF // create_descriptor(0, 0x000FFFFF, (GDT_CODE_PL0));
+.quad 0x00CF92000000FFFF // create_descriptor(0, 0x000FFFFF, (GDT_DATA_PL0));
+.quad 0x00CFFA000000FFFF // create_descriptor(0, 0x000FFFFF, (GDT_CODE_PL3));
+.quad 0x00CFF2000000FFFF // create_descriptor(0, 0x000FFFFF, (GDT_DATA_PL3));
+gdt_end:
+
+/*
+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 <stdio.h> 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.
+    */
+
+    lgdt gdt_ptr
+ 
+    /*
+    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
+

extra/grub.cfg

@@ -0,0 +1,4 @@
+menuentry "just some OS" {
+    multiboot /boot/kernel.bin
+}
+

kernel.c

@@ -0,0 +1,24 @@
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include "vga.h"
+ 
+/* 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 OS needs to be compiled with a ix86-elf compiler"
+#endif
+ 
+void kernel_main(void) 
+{
+    /* Initialize terminal interface */
+    terminal_initialize();
+ 
+    /* Newline support is left as an exercise. */
+    terminal_writestring("Hello, kernel World!\n");
+}
+

linker.ld

@@ -0,0 +1,44 @@
+/* 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
+{
+	/* Begin putting sections at 1 MiB, a conventional place for kernels to be
+	   loaded at by the bootloader. */
+	. = 1M;
+ 
+	/* First put the multiboot header, as it is required to be put very early
+	   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. */
+}
+

std/std.c

@@ -0,0 +1,43 @@
+#include "std/std.h"
+
+size_t strlen(const char* str) {
+    size_t len = 0;
+    while (str[len])
+        len++;
+    return len;
+}
+
+int memcmp(const void *av, const void *bv, size_t size) {
+    const unsigned char *a = (const unsigned char*) av;
+    const unsigned char *b = (const unsigned char*) bv;
+
+    for (size_t i = 0; i < size; i++) {
+        if (a[i] < b[i]) {
+            return -1;
+        } else if (b[i] < a[i]) {
+            return 1;
+        }
+    }
+
+    return 0;
+}
+
+void* memset(void *bufv, int value, size_t size) {
+    unsigned char* buf = (unsigned char*) buf;
+    for (size_t i = 0; i < size; i++) {
+        buf[i] = (unsigned char) value;
+    }
+    return bufv;
+}
+
+void* memcpy(void *destv, void *srcv, size_t size) {
+    unsigned char *dest = (unsigned char*) destv;
+    const unsigned char *src = (unsigned char*) srcv;
+
+    for (size_t i = 0; i < size; i++) {
+        dest[i] = src[i];
+    }
+
+    return destv;
+}
+

std/std.h

@@ -0,0 +1,13 @@
+#ifndef _STD_H
+#define _STD_H
+
+#include <stddef.h>
+#include <stdint.h>
+
+size_t strlen(const char* str);
+int memcmp(const void *av, const void *bv, size_t size);
+void* memset(void *bufv, int value, size_t size);
+void *memcpy(void *destv, void *srcv, size_t size);
+
+#endif
+

vga.c

@@ -0,0 +1,48 @@
+#include "vga.h"
+#include "std/std.h"
+
+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;
+}
+ 
+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);
+}
+ 
+void terminal_putchar(char c) {
+    terminal_putentryat(c, terminal_color, terminal_column, terminal_row);
+    if (++terminal_column == VGA_WIDTH) {
+        terminal_column = 0;
+        if (++terminal_row == VGA_HEIGHT)
+            terminal_row = 0;
+    }
+}
+ 
+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));
+}
+

vga.h

@@ -0,0 +1,47 @@
+#ifndef _VGA_H
+#define _VGA_H
+
+#include <stddef.h>
+#include <stdint.h>
+
+static const size_t VGA_WIDTH = 80;
+static const size_t VGA_HEIGHT = 25;
+
+/* 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;
+}
+
+void terminal_initialize(void); 
+void terminal_setcolor(uint8_t color);
+void terminal_putentryat(char c, uint8_t color, size_t x, size_t y);
+void terminal_putchar(char c);
+void terminal_write(const char* data, size_t size);
+void terminal_writestring(const char* data);
+
+#endif