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
54 lines
1.8 KiB
C
54 lines
1.8 KiB
C
#ifndef _KERNEL_EXEC_H
|
|
#define _KERNEL_EXEC_H
|
|
|
|
#include <stdint.h>
|
|
#include <stddef.h>
|
|
#include <stdbool.h>
|
|
#include <kernel/types.h>
|
|
#include <mm/vmspace.h>
|
|
|
|
/* A process running in ring 3. */
|
|
typedef struct uproc {
|
|
pid_t pid;
|
|
char name[32];
|
|
vmspace_t* vm;
|
|
uint64_t entry;
|
|
uint64_t brk; /* program break, grown by SYS_brk */
|
|
uint64_t brk_start; /* end of the loaded image */
|
|
uint64_t kstack; /* kernel stack used for traps out of ring 3 */
|
|
size_t kstack_size;
|
|
int exit_code;
|
|
bool exited;
|
|
} uproc_t;
|
|
|
|
/* The process currently executing in ring 3, or NULL in plain kernel context. */
|
|
uproc_t* uproc_current(void);
|
|
|
|
/*
|
|
* Load a static ELF64 image and run it in ring 3. Blocks until the process
|
|
* exits and returns its exit status, or a negative value if it could not be
|
|
* started. `image` must stay valid for the lifetime of the call.
|
|
*/
|
|
int exec_user_image(const char* name, const void* image, size_t len);
|
|
|
|
/* Terminate the running process and unwind back into exec_user_image(). */
|
|
void uproc_exit(int status) __attribute__((noreturn));
|
|
|
|
/*
|
|
* Abort the running process because it faulted. Safe to call from an
|
|
* exception handler; does not return.
|
|
*/
|
|
void uproc_fault(const char* reason, uint64_t addr) __attribute__((noreturn));
|
|
|
|
/* Bounds-checked transfers between the kernel and the running process. */
|
|
bool uaccess_ok(uint64_t uaddr, size_t len);
|
|
int uaccess_copy_from_user(void* dst, uint64_t usrc, size_t len);
|
|
int uaccess_copy_to_user(uint64_t udst, const void* src, size_t len);
|
|
/* Copy a NUL-terminated user string; returns its length or -1. */
|
|
long uaccess_copy_string(char* dst, uint64_t usrc, size_t max);
|
|
|
|
/* Run the built-in /sbin/init image. Returns its exit status. */
|
|
int exec_run_builtin_init(void);
|
|
|
|
#endif /* _KERNEL_EXEC_H */
|