fault_64.c

linux 内核源代码

	mm = tsk->mm;
	prefetchw(&mm->mmap_sem);

	/* get the address */
	address = read_cr2();

	info.si_code = SEGV_MAPERR;


	/*
	 * We 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.
	 *
	 * This verifies that the fault happens in kernel space
	 * (error_code & 4) == 0, and that the fault was not a
	 * protection error (error_code & 9) == 0.
	 */
	if (unlikely(address >= TASK_SIZE64)) {
		/*
		 * Don't check for the module range here: its PML4
		 * is always initialized because it's shared with the main
		 * kernel text. Only vmalloc may need PML4 syncups.
		 */
		if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) &&
		      ((address >= VMALLOC_START && address < VMALLOC_END))) {
			if (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;

	if (likely(regs->eflags & X86_EFLAGS_IF))
		local_irq_enable();

	if (unlikely(error_code & PF_RSVD))
		pgtable_bad(address, regs, error_code);

	/*
	 * If we're in an interrupt or have no user
	 * context, we must not take the fault..
	 */
	if (unlikely(in_atomic() || !mm))
		goto bad_area_nosemaphore;

	/*
	 * User-mode registers count as a user access even for any
	 * potential system fault or CPU buglet.
	 */
	if (user_mode_vm(regs))
		error_code |= PF_USER;

 again:
	/* 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 & PF_USER) == 0 &&
		    !search_exception_tables(regs->rip))
			goto bad_area_nosemaphore;
		down_read(&mm->mmap_sem);
	}

	vma = find_vma(mm, address);
	if (!vma)
		goto bad_area;
	if (likely(vma->vm_start <= address))
		goto good_area;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		goto bad_area;
	if (error_code & 4) {
		/* Allow userspace just enough access below the stack pointer
		 * to let the 'enter' instruction work.
		 */
		if (address + 65536 + 32 * sizeof(unsigned long) < regs->rsp)
			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:
	info.si_code = SEGV_ACCERR;
	write = 0;
	switch (error_code & (PF_PROT|PF_WRITE)) {
		default:	/* 3: write, present */
			/* fall through */
		case PF_WRITE:		/* write, not present */
			if (!(vma->vm_flags & VM_WRITE))
				goto bad_area;
			write++;
			break;
		case PF_PROT:		/* read, present */
			goto bad_area;
		case 0:			/* read, not present */
			if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
				goto bad_area;
	}

	/*
	 * 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++;
	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 & PF_USER) {

		/*
		 * It's possible to have interrupts off here.
		 */
		local_irq_enable();

		if (is_prefetch(regs, address, error_code))
			return;

		/* Work around K8 erratum #100 K8 in compat mode
		   occasionally jumps to illegal addresses >4GB.  We
		   catch this here in the page fault handler because
		   these addresses are not reachable. Just detect this
		   case and return.  Any code segment in LDT is
		   compatibility mode. */
		if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) &&
		    (address >> 32))
			return;

		if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
		    printk_ratelimit()) {
			printk(
		       "%s%s[%d]: segfault at %lx rip %lx rsp %lx error %lx\n",
					tsk->pid > 1 ? KERN_INFO : KERN_EMERG,
					tsk->comm, tsk->pid, address, regs->rip,
					regs->rsp, 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;
		info.si_signo = SIGSEGV;
		info.si_errno = 0;
		/* info.si_code has been set above */
		info.si_addr = (void __user *)address;
		force_sig_info(SIGSEGV, &info, tsk);
		return;
	}

no_context:
	
	/* Are we prepared to handle this kernel fault?  */
	fixup = search_exception_tables(regs->rip);
	if (fixup) {
		regs->rip = fixup->fixup;
		return;
	}

	/* 
	 * Hall of shame of CPU/BIOS bugs.
	 */

 	if (is_prefetch(regs, address, error_code))
 		return;

	if (is_errata93(regs, address))
		return; 

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

	flags = oops_begin();

	if (address < PAGE_SIZE)
		printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
	else
		printk(KERN_ALERT "Unable to handle kernel paging request");
	printk(" at %016lx RIP: \n" KERN_ALERT,address);
	printk_address(regs->rip);
	dump_pagetable(address);
	tsk->thread.cr2 = address;
	tsk->thread.trap_no = 14;
	tsk->thread.error_code = error_code;
	__die("Oops", regs, error_code);
	/* Executive summary in case the body of the oops scrolled away */
	printk(KERN_EMERG "CR2: %016lx\n", address);
	oops_end(flags);
	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(current)) {
		yield();
		goto again;
	}
	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 & PF_USER))
		goto no_context;

	tsk->thread.cr2 = address;
	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = 14;
	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code = BUS_ADRERR;
	info.si_addr = (void __user *)address;
	force_sig_info(SIGBUS, &info, tsk);
	return;
}

DEFINE_SPINLOCK(pgd_lock);
LIST_HEAD(pgd_list);

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 = VMALLOC_START & PGDIR_MASK;
	unsigned long address;

	for (address = start; address <= VMALLOC_END; address += PGDIR_SIZE) {
		if (!test_bit(pgd_index(address), insync)) {
			const pgd_t *pgd_ref = pgd_offset_k(address);
			struct page *page;

			if (pgd_none(*pgd_ref))
				continue;
			spin_lock(&pgd_lock);
			list_for_each_entry(page, &pgd_list, lru) {
				pgd_t *pgd;
				pgd = (pgd_t *)page_address(page) + pgd_index(address);
				if (pgd_none(*pgd))
					set_pgd(pgd, *pgd_ref);
				else
					BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
			}
			spin_unlock(&pgd_lock);
			set_bit(pgd_index(address), insync);
		}
		if (address == start)
			start = address + PGDIR_SIZE;
	}
	/* Check that there is no need to do the same for the modules area. */
	BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
	BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == 
				(__START_KERNEL & PGDIR_MASK)));
}