fault_32.c

linux 内核源代码

	if (unlikely(address >= TASK_SIZE)) {
		if (!(error_code & 0x0000000d) && vmalloc_fault(address) >= 0)
			return;
		if (notify_page_fault(regs))
			return;
		/*
		 * Don't take the mm semaphore here. If we fixup a prefetch
		 * fault we could otherwise deadlock.
		 */
		goto bad_area_nosemaphore;
	}

	if (notify_page_fault(regs))
		return;

	/* It's safe to allow irq's after cr2 has been saved and the vmalloc
	   fault has been handled. */
	if (regs->eflags & (X86_EFLAGS_IF|VM_MASK))
		local_irq_enable();

	mm = tsk->mm;

	/*
	 * 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 (in_atomic() || !mm)
		goto bad_area_nosemaphore;

	/* When running in the kernel we expect faults to occur only to
	 * addresses in user space.  All other faults represent errors in the
	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
	 * erroneous fault occurring in a code path which already holds mmap_sem
	 * we will deadlock attempting to validate the fault against the
	 * address space.  Luckily the kernel only validly references user
	 * space from well defined areas of code, which are listed in the
	 * exceptions table.
	 *
	 * As the vast majority of faults will be valid we will only perform
	 * the source reference check when there is a possibility of a deadlock.
	 * Attempt to lock the address space, if we cannot we then validate the
	 * source.  If this is invalid we can skip the address space check,
	 * thus avoiding the deadlock.
	 */
	if (!down_read_trylock(&mm->mmap_sem)) {
		if ((error_code & 4) == 0 &&
		    !search_exception_tables(regs->eip))
			goto bad_area_nosemaphore;
		down_read(&mm->mmap_sem);
	}

	vma = find_vma(mm, address);
	if (!vma)
		goto bad_area;
	if (vma->vm_start <= address)
		goto good_area;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		goto bad_area;
	if (error_code & 4) {
		/*
		 * Accessing the stack below %esp is always a bug.
		 * The large cushion allows instructions like enter
		 * and pusha to work.  ("enter $65535,$31" pushes
		 * 32 pointers and then decrements %esp by 65535.)
		 */
		if (address + 65536 + 32 * sizeof(unsigned long) < regs->esp)
			goto bad_area;
	}
	if (expand_stack(vma, address))
		goto bad_area;
/*
 * Ok, we have a good vm_area for this memory access, so
 * we can handle it..
 */
good_area:
	si_code = SEGV_ACCERR;
	write = 0;
	switch (error_code & 3) {
		default:	/* 3: write, present */
				/* fall through */
		case 2:		/* write, not present */
			if (!(vma->vm_flags & VM_WRITE))
				goto bad_area;
			write++;
			break;
		case 1:		/* read, present */
			goto bad_area;
		case 0:		/* read, not present */
			if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
				goto bad_area;
	}

 survive:
	/*
	 * If for any reason at all we couldn't handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
	fault = handle_mm_fault(mm, vma, address, write);
	if (unlikely(fault & VM_FAULT_ERROR)) {
		if (fault & VM_FAULT_OOM)
			goto out_of_memory;
		else if (fault & VM_FAULT_SIGBUS)
			goto do_sigbus;
		BUG();
	}
	if (fault & VM_FAULT_MAJOR)
		tsk->maj_flt++;
	else
		tsk->min_flt++;

	/*
	 * Did it hit the DOS screen memory VA from vm86 mode?
	 */
	if (regs->eflags & VM_MASK) {
		unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT;
		if (bit < 32)
			tsk->thread.screen_bitmap |= 1 << bit;
	}
	up_read(&mm->mmap_sem);
	return;

/*
 * Something tried to access memory that isn't in our memory map..
 * Fix it, but check if it's kernel or user first..
 */
bad_area:
	up_read(&mm->mmap_sem);

bad_area_nosemaphore:
	/* User mode accesses just cause a SIGSEGV */
	if (error_code & 4) {
		/*
		 * It's possible to have interrupts off here.
		 */
		local_irq_enable();

		/* 
		 * Valid to do another page fault here because this one came 
		 * from user space.
		 */
		if (is_prefetch(regs, address, error_code))
			return;

		if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
		    printk_ratelimit()) {
			printk("%s%s[%d]: segfault at %08lx eip %08lx "
			    "esp %08lx error %lx\n",
			    task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
			    tsk->comm, task_pid_nr(tsk), address, regs->eip,
			    regs->esp, error_code);
		}
		tsk->thread.cr2 = address;
		/* Kernel addresses are always protection faults */
		tsk->thread.error_code = error_code | (address >= TASK_SIZE);
		tsk->thread.trap_no = 14;
		force_sig_info_fault(SIGSEGV, si_code, address, tsk);
		return;
	}

#ifdef CONFIG_X86_F00F_BUG
	/*
	 * Pentium F0 0F C7 C8 bug workaround.
	 */
	if (boot_cpu_data.f00f_bug) {
		unsigned long nr;
		
		nr = (address - idt_descr.address) >> 3;

		if (nr == 6) {
			do_invalid_op(regs, 0);
			return;
		}
	}
#endif

no_context:
	/* Are we prepared to handle this kernel fault?  */
	if (fixup_exception(regs))
		return;

	/* 
	 * Valid to do another page fault here, because if this fault
	 * had been triggered by is_prefetch fixup_exception would have 
	 * handled it.
	 */
 	if (is_prefetch(regs, address, error_code))
 		return;

/*
 * Oops. The kernel tried to access some bad page. We'll have to
 * terminate things with extreme prejudice.
 */

	bust_spinlocks(1);

	if (oops_may_print()) {
		__typeof__(pte_val(__pte(0))) page;

#ifdef CONFIG_X86_PAE
		if (error_code & 16) {
			pte_t *pte = lookup_address(address);

			if (pte && pte_present(*pte) && !pte_exec_kernel(*pte))
				printk(KERN_CRIT "kernel tried to execute "
					"NX-protected page - exploit attempt? "
					"(uid: %d)\n", current->uid);
		}
#endif
		if (address < PAGE_SIZE)
			printk(KERN_ALERT "BUG: unable to handle kernel NULL "
					"pointer dereference");
		else
			printk(KERN_ALERT "BUG: unable to handle kernel paging"
					" request");
		printk(" at virtual address %08lx\n",address);
		printk(KERN_ALERT "printing eip: %08lx ", regs->eip);

		page = read_cr3();
		page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
#ifdef CONFIG_X86_PAE
		printk("*pdpt = %016Lx ", page);
		if ((page >> PAGE_SHIFT) < max_low_pfn
		    && page & _PAGE_PRESENT) {
			page &= PAGE_MASK;
			page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
			                                         & (PTRS_PER_PMD - 1)];
			printk(KERN_CONT "*pde = %016Lx ", page);
			page &= ~_PAGE_NX;
		}
#else
		printk("*pde = %08lx ", page);
#endif

		/*
		 * We must not directly access the pte in the highpte
		 * case if the page table is located in highmem.
		 * And let's rather not kmap-atomic the pte, just in case
		 * it's allocated already.
		 */
		if ((page >> PAGE_SHIFT) < max_low_pfn
		    && (page & _PAGE_PRESENT)
		    && !(page & _PAGE_PSE)) {
			page &= PAGE_MASK;
			page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
			                                         & (PTRS_PER_PTE - 1)];
			printk("*pte = %0*Lx ", sizeof(page)*2, (u64)page);
		}

		printk("\n");
	}

	tsk->thread.cr2 = address;
	tsk->thread.trap_no = 14;
	tsk->thread.error_code = error_code;
	die("Oops", regs, error_code);
	bust_spinlocks(0);
	do_exit(SIGKILL);

/*
 * We ran out of memory, or some other thing happened to us that made
 * us unable to handle the page fault gracefully.
 */
out_of_memory:
	up_read(&mm->mmap_sem);
	if (is_global_init(tsk)) {
		yield();
		down_read(&mm->mmap_sem);
		goto survive;
	}
	printk("VM: killing process %s\n", tsk->comm);
	if (error_code & 4)
		do_group_exit(SIGKILL);
	goto no_context;

do_sigbus:
	up_read(&mm->mmap_sem);

	/* Kernel mode? Handle exceptions or die */
	if (!(error_code & 4))
		goto no_context;

	/* User space => ok to do another page fault */
	if (is_prefetch(regs, address, error_code))
		return;

	tsk->thread.cr2 = address;
	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = 14;
	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
}

void vmalloc_sync_all(void)
{
	/*
	 * Note that races in the updates of insync and start aren't
	 * problematic: insync can only get set bits added, and updates to
	 * start are only improving performance (without affecting correctness
	 * if undone).
	 */
	static DECLARE_BITMAP(insync, PTRS_PER_PGD);
	static unsigned long start = TASK_SIZE;
	unsigned long address;

	if (SHARED_KERNEL_PMD)
		return;

	BUILD_BUG_ON(TASK_SIZE & ~PGDIR_MASK);
	for (address = start; address >= TASK_SIZE; address += PGDIR_SIZE) {
		if (!test_bit(pgd_index(address), insync)) {
			unsigned long flags;
			struct page *page;

			spin_lock_irqsave(&pgd_lock, flags);
			for (page = pgd_list; page; page =
					(struct page *)page->index)
				if (!vmalloc_sync_one(page_address(page),
								address)) {
					BUG_ON(page != pgd_list);
					break;
				}
			spin_unlock_irqrestore(&pgd_lock, flags);
			if (!page)
				set_bit(pgd_index(address), insync);
		}
		if (address == start && test_bit(pgd_index(address), insync))
			start = address + PGDIR_SIZE;
	}
}