mirror of
https://github.com/subhobhai943/SUB-OS.git
synced 2026-10-25 16:52:29 +00:00
subhobhai943andClaude Opus 5
ecdc5be435
SUB-OS had a syscall table and user GDT descriptors but nothing that could actually leave ring 0: lazybox and the shell run as kernel code, and syscall_handler() was never reachable from a user program. This adds the missing path end to end on x86_64. Address spaces (arch/x86_64/mm/vmspace.c) - The boot page tables identity-map the low 4 GB off PML4[0] and leave the rest empty, so userland is given its own PML4 slot (512 GiB) rather than holes punched in the kernel's 2 MB huge-page map. A process PML4 shares entry 0 with the kernel and privately owns entry 1. - Frames outside the identity map are refused rather than written through an unmapped pointer; lifting that needs a recursive map or a higher-half direct map, which is noted in the file. ELF loader (kernel/elf.c) - Validates ELF64/little-endian/ET_EXEC/machine, bounds-checks every program header against both the image and the user address range, and lays PT_LOAD segments into an address space. Frames arrive zeroed, so .bss is covered. Ring transition (arch/x86_64/cpu/usermode.asm) - user_enter() drops to ring 3 via iretq after scrubbing every GPR, and user_return() unwinds back to it when the process exits, so exec looks like a call that blocks until the program finishes. Syscalls - INT 0x80 installed at DPL 3 with the Linux x86_64 register convention. The process gets its own kernel stack for the trap, because TSS.rsp0 must not point at the stack user_enter() is standing on. - Every user pointer is range-checked before use. The process page tables are still live during a syscall, so without that check a program could pass a kernel address and have write(2) dump kernel text to the console. The new /sbin/init asserts both a wild pointer and a kernel pointer are rejected. - write(2) to stdout/stderr routes through the new console_write(), which reuses printk's routing so output reaches serial and the framebuffer console rather than only the VGA text buffer. Faults - A ring 3 exception now kills that process and reports CR2 instead of panicking the machine. Userland (userland/init/) - /sbin/init is a real freestanding static executable, linked at the user base and embedded in the kernel image by scripts/mkblob.py. It reports its pid, verifies .bss was zeroed and .data is writable, checks the two pointer rejections, and exits. aarch64 and armv8i keep building: the loader and exec path are portable, and those ports get honest vmspace stubs that fail cleanly rather than pretending to run a program with kernel privileges. Verified under QEMU: init loads at 0x80004000a0, reports pid 1, .bss zeroed, .data writable, both bad pointers rejected, and exits 0 back into the shell. Co-Authored-By: Claude Opus 5 <[email protected]> Claude-Session: https://claude.ai/code/session_0161Jh7uCEMLYEMNPsjC1LKf
75 lines
2.7 KiB
C
75 lines
2.7 KiB
C
#ifndef _KERNEL_PRINTK_H
|
|
#define _KERNEL_PRINTK_H
|
|
|
|
#include <stddef.h>
|
|
#include <stdint.h>
|
|
#include <stdarg.h>
|
|
#include <stdbool.h>
|
|
#include <lib/printf.h>
|
|
|
|
// Linux-compatible log level prefixes
|
|
#define KERN_EMERG "\0010" /* system is unusable */
|
|
#define KERN_ALERT "\0011" /* action must be taken immediately */
|
|
#define KERN_CRIT "\0012" /* critical conditions */
|
|
#define KERN_ERR "\0013" /* error conditions */
|
|
#define KERN_WARNING "\0014" /* warning conditions */
|
|
#define KERN_NOTICE "\0015" /* normal but significant condition */
|
|
#define KERN_INFO "\0016" /* informational */
|
|
#define KERN_DEBUG "\0017" /* debug-level messages */
|
|
|
|
// ANSI Color Escape Sequences
|
|
#define ANSI_RESET "\033[0m"
|
|
#define ANSI_BOLD "\033[1m"
|
|
#define ANSI_BLACK "\033[30m"
|
|
#define ANSI_RED "\033[31m"
|
|
#define ANSI_GREEN "\033[32m"
|
|
#define ANSI_YELLOW "\033[33m"
|
|
#define ANSI_BLUE "\033[34m"
|
|
#define ANSI_MAGENTA "\033[35m"
|
|
#define ANSI_CYAN "\033[36m"
|
|
#define ANSI_WHITE "\033[37m"
|
|
#define ANSI_BRIGHT_BLACK "\033[90m"
|
|
#define ANSI_BRIGHT_RED "\033[91m"
|
|
#define ANSI_BRIGHT_GREEN "\033[92m"
|
|
#define ANSI_BRIGHT_YELLOW "\033[93m"
|
|
#define ANSI_BRIGHT_BLUE "\033[94m"
|
|
#define ANSI_BRIGHT_MAGENTA "\033[95m"
|
|
#define ANSI_BRIGHT_CYAN "\033[96m"
|
|
#define ANSI_BRIGHT_WHITE "\033[97m"
|
|
#define ANSI_INVERT "\033[7m"
|
|
#define ANSI_BG_BLACK "\033[40m"
|
|
#define ANSI_BG_BLUE "\033[44m"
|
|
#define ANSI_BG_WHITE "\033[47m"
|
|
|
|
// Printk API
|
|
void printk_init(void);
|
|
|
|
// Write raw bytes to every console printk drives (TTY or framebuffer, plus
|
|
// serial). Used by the write(2) path so userland output is routed identically.
|
|
void console_write(const char* data, size_t len);
|
|
int printk(const char* fmt, ...);
|
|
int vprintk(const char* fmt, va_list args);
|
|
int kprintf(const char* fmt, ...); // Alias for compatibility
|
|
|
|
// Kernel Dmesg Ring Buffer API
|
|
void dmesg_dump(void);
|
|
const char* dmesg_get_buffer(size_t* size_out);
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Console redirection
|
|
//
|
|
// While a sink is installed, printk output is handed to the callback instead
|
|
// of the text console, so a caller can run a subsystem that reports via printk
|
|
// and capture what it printed. The serial console and the dmesg ring still
|
|
// receive everything, which keeps a captured run debuggable.
|
|
//
|
|
// The sink must not itself call printk; re-entrant output is dropped.
|
|
// ---------------------------------------------------------------------------
|
|
typedef void (*printk_sink_fn_t)(const char* text, size_t len, void* ctx);
|
|
|
|
void printk_set_sink(printk_sink_fn_t fn, void* ctx);
|
|
void printk_clear_sink(void);
|
|
bool printk_has_sink(void);
|
|
|
|
#endif // _KERNEL_PRINTK_H
|