asmlinkage void do_page_fault()

in mm/fault.c [210:352]

• 85 lines of code
• 23 McCabe index (conditional complexity)

asmlinkage void do_page_fault(struct pt_regs *regs)
{
	struct task_struct *tsk;
	struct vm_area_struct *vma;
	struct mm_struct *mm;
	unsigned long addr, cause;
	unsigned int flags = FAULT_FLAG_DEFAULT;
	int code = SEGV_MAPERR;
	vm_fault_t fault;

	cause = regs->cause;
	addr = regs->badaddr;

	tsk = current;
	mm = tsk->mm;

	if (kprobe_page_fault(regs, cause))
		return;

	/*
	 * Fault-in kernel-space virtual memory on-demand.
	 * The 'reference' page table is init_mm.pgd.
	 *
	 * NOTE! We MUST NOT take any locks for this case. We may
	 * be in an interrupt or a critical region, and should
	 * only copy the information from the master page table,
	 * nothing more.
	 */
	if (unlikely((addr >= VMALLOC_START) && (addr < VMALLOC_END))) {
		vmalloc_fault(regs, code, addr);
		return;
	}

#ifdef CONFIG_64BIT
	/*
	 * Modules in 64bit kernels lie in their own virtual region which is not
	 * in the vmalloc region, but dealing with page faults in this region
	 * or the vmalloc region amounts to doing the same thing: checking that
	 * the mapping exists in init_mm.pgd and updating user page table, so
	 * just use vmalloc_fault.
	 */
	if (unlikely(addr >= MODULES_VADDR && addr < MODULES_END)) {
		vmalloc_fault(regs, code, addr);
		return;
	}
#endif
	/* Enable interrupts if they were enabled in the parent context. */
	if (likely(regs->status & SR_PIE))
		local_irq_enable();

	/*
	 * If we're in an interrupt, have no user context, or are running
	 * in an atomic region, then we must not take the fault.
	 */
	if (unlikely(faulthandler_disabled() || !mm)) {
		tsk->thread.bad_cause = cause;
		no_context(regs, addr);
		return;
	}

	if (user_mode(regs))
		flags |= FAULT_FLAG_USER;

	if (!user_mode(regs) && addr < TASK_SIZE &&
			unlikely(!(regs->status & SR_SUM)))
		die_kernel_fault("access to user memory without uaccess routines",
				addr, regs);

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);

	if (cause == EXC_STORE_PAGE_FAULT)
		flags |= FAULT_FLAG_WRITE;
	else if (cause == EXC_INST_PAGE_FAULT)
		flags |= FAULT_FLAG_INSTRUCTION;
retry:
	mmap_read_lock(mm);
	vma = find_vma(mm, addr);
	if (unlikely(!vma)) {
		tsk->thread.bad_cause = cause;
		bad_area(regs, mm, code, addr);
		return;
	}
	if (likely(vma->vm_start <= addr))
		goto good_area;
	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
		tsk->thread.bad_cause = cause;
		bad_area(regs, mm, code, addr);
		return;
	}
	if (unlikely(expand_stack(vma, addr))) {
		tsk->thread.bad_cause = cause;
		bad_area(regs, mm, code, addr);
		return;
	}

	/*
	 * Ok, we have a good vm_area for this memory access, so
	 * we can handle it.
	 */
good_area:
	code = SEGV_ACCERR;

	if (unlikely(access_error(cause, vma))) {
		tsk->thread.bad_cause = cause;
		bad_area(regs, mm, code, addr);
		return;
	}

	/*
	 * If for any reason at all we could not handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
	fault = handle_mm_fault(vma, addr, flags, regs);

	/*
	 * If we need to retry but a fatal signal is pending, handle the
	 * signal first. We do not need to release the mmap_lock because it
	 * would already be released in __lock_page_or_retry in mm/filemap.c.
	 */
	if (fault_signal_pending(fault, regs))
		return;

	if (unlikely(fault & VM_FAULT_RETRY)) {
		flags |= FAULT_FLAG_TRIED;

		/*
		 * No need to mmap_read_unlock(mm) as we would
		 * have already released it in __lock_page_or_retry
		 * in mm/filemap.c.
		 */
		goto retry;
	}

	mmap_read_unlock(mm);

	if (unlikely(fault & VM_FAULT_ERROR)) {
		tsk->thread.bad_cause = cause;
		mm_fault_error(regs, addr, fault);
		return;
	}
	return;
}