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
109 lines
3.2 KiB
C
109 lines
3.2 KiB
C
#include <arch/x86_64/isr.h>
|
|
#include <arch/x86_64/idt.h>
|
|
#include <arch/x86_64/pic.h>
|
|
#include <kernel/printk.h>
|
|
#include <kernel/panic.h>
|
|
#include <kernel/exec.h>
|
|
#include <lib/string.h>
|
|
|
|
extern void* isr_stub_table[48];
|
|
|
|
static isr_handler_t interrupt_handlers[256];
|
|
|
|
static const char* exception_messages[32] = {
|
|
"Division By Zero",
|
|
"Debug",
|
|
"Non-Maskable Interrupt",
|
|
"Breakpoint",
|
|
"Into Detected Overflow",
|
|
"Out of Bounds",
|
|
"Invalid Opcode",
|
|
"No Coprocessor",
|
|
"Double Fault",
|
|
"Coprocessor Segment Overrun",
|
|
"Bad TSS",
|
|
"Segment Not Present",
|
|
"Stack Fault",
|
|
"General Protection Fault",
|
|
"Page Fault",
|
|
"Unknown Interrupt",
|
|
"Coprocessor Fault",
|
|
"Alignment Check",
|
|
"Machine Check",
|
|
"SIMD Floating-Point Exception",
|
|
"Virtualization Exception",
|
|
"Control Protection Exception",
|
|
"Reserved",
|
|
"Reserved",
|
|
"Reserved",
|
|
"Reserved",
|
|
"Reserved",
|
|
"Reserved",
|
|
"Hypervisor Injection Exception",
|
|
"VMM Communication Exception",
|
|
"Security Exception",
|
|
"Reserved"
|
|
};
|
|
|
|
void isr_register_handler(uint8_t int_no, isr_handler_t handler) {
|
|
interrupt_handlers[int_no] = handler;
|
|
}
|
|
|
|
void isr_unregister_handler(uint8_t int_no) {
|
|
interrupt_handlers[int_no] = NULL;
|
|
}
|
|
|
|
void isr_handler_common(registers_t* regs) {
|
|
if (regs->int_no < 32) {
|
|
/* A page fault reports the offending address in CR2; everything else
|
|
* is best described by where it was executing. */
|
|
uint64_t fault_addr = regs->rip;
|
|
if (regs->int_no == 14) {
|
|
__asm__ volatile("mov %%cr2, %0" : "=r"(fault_addr));
|
|
}
|
|
|
|
/*
|
|
* CS still carries the privilege level the fault was taken from. A
|
|
* ring 3 fault is the process's problem, not the kernel's: report it
|
|
* and tear that process down instead of bringing the machine down
|
|
* with it.
|
|
*/
|
|
if ((regs->cs & 3) == 3 && uproc_current()) {
|
|
printk(KERN_ERR "\n[USER FAULT] Vector %llu: %s (error 0x%llx) at rip=0x%llx\n",
|
|
regs->int_no, exception_messages[regs->int_no],
|
|
regs->error_code, regs->rip);
|
|
uproc_fault(exception_messages[regs->int_no], fault_addr);
|
|
}
|
|
|
|
// CPU Exception Fault
|
|
printk(KERN_EMERG "\n[EXCEPTION] Vector %llu: %s (Error code: 0x%llx)\n",
|
|
regs->int_no, exception_messages[regs->int_no], regs->error_code);
|
|
panic_with_regs(exception_messages[regs->int_no], regs);
|
|
}
|
|
|
|
if (interrupt_handlers[regs->int_no] != NULL) {
|
|
interrupt_handlers[regs->int_no](regs);
|
|
}
|
|
|
|
// Acknowledge Hardware PIC Interrupts (IRQs 32-47)
|
|
if (regs->int_no >= 32 && regs->int_no < 48) {
|
|
pic_send_eoi((uint8_t)(regs->int_no - 32));
|
|
}
|
|
}
|
|
|
|
extern void isr_stub_default(void);
|
|
|
|
void isr_init(void) {
|
|
memset(interrupt_handlers, 0, sizeof(interrupt_handlers));
|
|
|
|
// 1. Initialize all 256 gates to isr_stub_default
|
|
for (int i = 0; i < 256; i++) {
|
|
idt_set_gate(i, (void*)isr_stub_default, 0x8E);
|
|
}
|
|
|
|
// 2. Install dedicated CPU exception gates (0-31) and hardware IRQ gates (32-47)
|
|
for (uint8_t i = 0; i < 48; i++) {
|
|
idt_set_gate(i, isr_stub_table[i], 0x8E);
|
|
}
|
|
}
|