Re: mm, something wring in page_lock_anon_vma_read()?

[zhong jiang]

On 2017/5/23 17:33, Vlastimil Babka wrote:
> On 05/23/2017 11:21 AM, zhong jiang wrote:
>> On 2017/5/23 0:51, Vlastimil Babka wrote:
>>> On 05/20/2017 05:01 AM, zhong jiang wrote:
>>>> On 2017/5/20 10:40, Hugh Dickins wrote:
>>>>> On Sat, 20 May 2017, Xishi Qiu wrote:
>>>>>> Here is a bug report form redhat: https://bugzilla.redhat.com/show_bug.cgi?id=1305620
>>>>>> And I meet the bug too. However it is hard to reproduce, and 
>>>>>> 624483f3ea82598("mm: rmap: fix use-after-free in __put_anon_vma") is not help.
>>>>>>
>>>>>> From the vmcore, it seems that the page is still mapped(_mapcount=0 and _count=2),
>>>>>> and the value of mapping is a valid address(mapping = 0xffff8801b3e2a101),
>>>>>> but anon_vma has been corrupted.
>>>>>>
>>>>>> Any ideas?
>>>>> Sorry, no.  I assume that _mapcount has been misaccounted, for example
>>>>> a pte mapped in on top of another pte; but cannot begin tell you where
>>>>> in Red Hat's kernel-3.10.0-229.4.2.el7 that might happen.
>>>>>
>>>>> Hugh
>>>>>
>>>>> .
>>>>>
>>>> Hi, Hugh
>>>>
>>>> I find the following message from the dmesg.
>>>>
>>>> [26068.316592] BUG: Bad rss-counter state mm:ffff8800a7de2d80 idx:1 val:1
>>>>
>>>> I can prove that the __mapcount is misaccount.  when task is exited. the rmap
>>>> still exist.
>>> Check if the kernel in question contains this commit: ad33bb04b2a6 ("mm:
>>> thp: fix SMP race condition between THP page fault and MADV_DONTNEED")
>>   HI, Vlastimil
>>  
>>   I miss the patch.
> Try applying it then, there's good chance the error and crash will go
> away. Even if your workload doesn't actually run any madvise(MADV_DONTNEED).
 ok , I will try.   Thanks
>> when I read the patch. I find the following issue. but I am sure it is right.
>>
>>       if (unlikely(pmd_trans_unstable(pmd)))
>>         return 0;
>>     /*
>>      * A regular pmd is established and it can't morph into a huge pmd
>>      * from under us anymore at this point because we hold the mmap_sem
>>      * read mode and khugepaged takes it in write mode. So now it's
>>      * safe to run pte_offset_map().
>>      */
>>     pte = pte_offset_map(pmd, address);
>>
>>   after pmd_trans_unstable call,  without any protect method.  by the comments,
>>   it think the pte_offset_map is safe.    before pte_offset_map call, it still may be
>>   unstable. it is possible?
> IIRC it's "unstable" wrt possible none->huge->none transition. But once
> we've seen it's a regular pmd via pmd_trans_unstable(), we're safe as a
> transition from regular pmd can't happen.
  Thank you for clarify. 
 
  Regards
 zhongjiang
>>   Thanks
>> zhongjiang
>>>> Thanks
>>>> zhongjiang
>>>>
>>>> --
>>>> To unsubscribe, send a message with 'unsubscribe linux-mm' in
>>>> the body to majordomo@xxxxxxxxxx  For more info on Linux MM,
>>>> see: http://www.linux-mm.org/ .
>>>> Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
>>>>
>>> .
>>>
>>
>> --
>> To unsubscribe, send a message with 'unsubscribe linux-mm' in
>> the body to majordomo@xxxxxxxxxx  For more info on Linux MM,
>> see: http://www.linux-mm.org/ .
>> Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
>>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@xxxxxxxxxx  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
>
> .
>