kernel 3.10代码分析--缺页异常(page fault)处理流程

kernel 3.10内核源码分析--缺页异常(page fault)处理流程

基本原理
1、page fault由硬件产生，是一种“异常”。产生条件为：当CPU访问某线性地址，而该线性地址还没有对应的页表项，即还没有分配相应的物理内存并进行映射时，自动产生异常。
2、page fault基本流程：
从cr2中获取发生异常的地址
  缺页地址位于内核态
    位于vmalloc区？->从主内核页表同步数据到进程页表
    非vmalloc区 ->不应该产生page fault->oops
  缺页地址位于用户态
     缺页上下文发生在内核态
        exception table中有相应的处理项？ ->进行修正
        没有 ->oops
     查找vma
        找到？-> 是否expand stack？->堆栈扩展
                       不是->正常的缺页处理：handle_mm_fault                    
        没找到->bad_area    

/*
  *缺页异常主处理函数。
  *regs:异常时的寄存器信息；
  *error_code-当异常发生时，硬件压入栈中的错误代码。
  *              当第0位被清0时，则异常是由一个不存在的页所引起的。否则是由无效的访问权限引起的。
  *              如果第1位被清0，则异常由读访问或者执行访问所引起，如果被设置，则异常由写访问引起。
  *              如果第2位被清0，则异常发生在内核态，否则异常发生在用户态。
  */
static void __kprobes
__do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
    struct vm_area_struct *vma;
    struct task_struct *tsk;
    unsigned long address;
    struct mm_struct *mm;
    int fault;
    int write = error_code & PF_WRITE;
    unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
                    (write ? FAULT_FLAG_WRITE : 0);

    tsk = current;
    mm = tsk->mm;

    /* Get the faulting address: */
    //缺页异常的地址默认存放于CR2寄存器中，x86硬件决定
    address = read_cr2();

    /*
     * Detect and handle instructions that would cause a page fault for
     * both a tracked kernel page and a userspace page.
     */
    if (kmemcheck_active(regs))
        kmemcheck_hide(regs);
    prefetchw(&mm->mmap_sem);

    // mmio不应该发生缺页，通常都会ioremap到vmalloc区，然后进行访问
    if (unlikely(kmmio_fault(regs, address)))
        return;

    /*
     * We fault-in kernel-space virtual memory on-demand. The
     * 'reference' page table is init_mm.pgd.
     *
     * 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.
     */
     /*
     * 缺页地址位于内核空间。并不代表异常发生于内核空间，有可能是用户
     * 态访问了内核空间的地址。
     */
    if (unlikely(fault_in_kernel_space(address))) {
        if (!(error_code & (PF_RSVD | PF_USER | PF_PROT))) {
            /*
             * 检查发生缺页的地址是否在vmalloc区，是则进行相应的处理
             * 主要是从内核主页表向进程页表同步数据
             */
            if (vmalloc_fault(address) >= 0)
                return;

            if (kmemcheck_fault(regs, address, error_code))
                return;
        }

        /* Can handle a stale RO->RW TLB: */
        /*
         * 检查是否是由于陈旧的TLB导致的假的pagefault(由于TLB的延迟flush导致,
         * 因为提前flush会有比较大的性能代价)。
         */
        if (spurious_fault(error_code, address))
            return;

        /* kprobes don't want to hook the spurious faults: */
        if (notify_page_fault(regs))
            return;
        /*
         * Don't take the mm semaphore here. If we fixup a prefetch
         * fault we could otherwise deadlock:
         */
        /*
         * 有问题了: 由于异常地址位于内核态，触发内核异常，因为vmalloc
         * 区的缺页异常前面已经处理过了，内核态的缺页异常只能发生在
         * vmalloc区，如果不是，那就是内核异常了。
         */
        bad_area_nosemaphore(regs, error_code, address);

        return;
    }

    // 进入到这里，说明异常地址位于用户态
    /* kprobes don't want to hook the spurious faults: */
    if (unlikely(notify_page_fault(regs)))
        return;
    /*
     * It's safe to allow irq's after cr2 has been saved and the
     * vmalloc fault has been handled.
     *
     * User-mode registers count as a user access even for any
     * potential system fault or CPU buglet:
     */
    /*
     * 开中断，这种情况下，是安全的，可以缩短因缺页异常导致的关中断时长。
     * 老内核版本中(2.6.11)没有这样的操作
     */
    if (user_mode_vm(regs)) {
        local_irq_enable();
        error_code |= PF_USER;
    } else {
        if (regs->flags & X86_EFLAGS_IF)
            local_irq_enable();
    }

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

    if (static_cpu_has(X86_FEATURE_SMAP)) {
        if (unlikely(smap_violation(error_code, regs))) {
            bad_area_nosemaphore(regs, error_code, address);
            return;
        }
    }

    perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

    /*
     * If we're in an interrupt, have no user context or are running
     * in an atomic region then we must not take the fault:
     */
    /*
     * 当缺页异常发生于中断或其它atomic上下文中时，则产生异常。
     * 这种情况下，不应该再产生page fault
     */
    if (unlikely(in_atomic() || !mm)) {
        bad_area_nosemaphore(regs, error_code, address);
        return;
    }

    /*
     * 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 (unlikely(!down_read_trylock(&mm->mmap_sem))) {
        /*
         * 缺页发生在内核上下文，这种情况发生缺页的地址只能位于用户态地址空间
         * 这种情况下，也只能为exceptions table中预先定义好的异常，如果exceptions
         * table中没有预先定义的处理，或者缺页的地址位于内核态地址空间，则表示
         * 错误，进入oops流程。
         */
        if ((error_code & PF_USER) == 0 &&
         !search_exception_tables(regs->ip)) {
            bad_area_nosemaphore(regs, error_code, address);
            return;
        }
retry:
        // 如果发生在用户态或者有exception table，说明不是内核异常
        down_read(&mm->mmap_sem);
    } else {
        /*
         * The above down_read_trylock() might have succeeded in
         * which case we'll have missed the might_sleep() from
         * down_read():
         */
        might_sleep();
    }

    // 在当前进程的地址空间中寻找发生异常的地址对应的VMA。
    vma = find_vma(mm, address);
    // 如果没找到VMA，则释放mem_sem信号量后，进入__bad_area_nosemaphore处理。
    if (unlikely(!vma)) {
        bad_area(regs, error_code, address);
        return;
    }
    /* 找到VMA，且发生异常的虚拟地址位于vma的有效范围内，则为正常的缺页
     * 异常，请求调页，分配物理内存 */
    if (likely(vma->vm_start <= address))
        goto good_area;
    /* 如果异常地址不是位于紧挨着堆栈区的那个区域，同时又没有相应VMA，则
     * 进程访问了非法地址，进入bad_area处理
     */
    if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
        bad_area(regs, error_code, address);
        return;
    }
    if (error_code & PF_USER) {
        /*
         * Accessing the stack below %sp is always a bug.
         * The large cushion allows instructions like enter
         * and pusha to work. ("enter $65535, $31" pushes
         * 32 pointers and then decrements %sp by 65535.)
         */
        /*
         * 压栈操作时，操作的地址最大的偏移为65536+32*sizeof(unsigned long),
         * 该操作由pusha命令触发(老版本中，pusha命令最大只能操作32字节，即
         * 同时压栈8个寄存器)。如果访问的地址距栈顶的距离超过了，则肯定是非法
         * 地址访问了。
         */
        if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
            bad_area(regs, error_code, address);
            return;
        }
    }

    /*
    * 运行到这里，说明设置了VM_GROWSDOWN标记，表示缺页异常地址位于堆栈区
    * 需要扩展堆栈。说明: 堆栈区的虚拟地址空间也是动态分配和扩展的，不是
    * 一开始就分配好的。
    */
    if (unlikely(expand_stack(vma, address))) {
        bad_area(regs, error_code, address);
        return;
    }

    /*
     * Ok, we have a good vm_area for this memory access, so
     * we can handle it..
     */
    /*
     * 运行到这里，说明是正常的缺页异常，则进行请求调页，分配物理内存
     */
good_area:
    if (unlikely(access_error(error_code, vma))) {
        bad_area_access_error(regs, error_code, address);
        return;
    }

    /*
     * If for any reason at all we couldn't handle the fault,
     * make sure we exit gracefully rather than endlessly redo
     * the fault:
     */
    /*
     * 分配物理内存，缺页异常的正常处理主函数
     * 可能的情况有:1、请求调页/按需分配；2、COW；3、缺的页位于交换分区，
     * 需要换入。
     */
    fault = handle_mm_fault(mm, vma, address, flags);

    if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
        if (mm_fault_error(regs, error_code, address, fault))
            return;
    }

    /*
     * Major/minor page fault accounting is only done on the
     * initial attempt. If we go through a retry, it is extremely
     * likely that the page will be found in page cache at that point.
     */
    if (flags & FAULT_FLAG_ALLOW_RETRY) {
        if (fault & VM_FAULT_MAJOR) {
            tsk->maj_flt++;
            perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
                      regs, address);
        } else {
            tsk->min_flt++;
            perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
                      regs, address);
        }
        if (fault & VM_FAULT_RETRY) {
            /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
             * of starvation. */
            flags &= ~FAULT_FLAG_ALLOW_RETRY;
            flags |= FAULT_FLAG_TRIED;
            goto retry;
        }
    }

    // VM86模式(兼容老环境)相关检查
    check_v8086_mode(regs, address, tsk);

    up_read(&mm->mmap_sem);
}