Re: [PATCH 3/4] Check whether pages are poisoned before copying

[Hidetoshi Seto]

(2011/03/17 15:26), Andi Kleen wrote:
> On Thu, Mar 17, 2011 at 02:20:42PM +0900, Hidetoshi Seto wrote:
>> (2011/03/17 13:14), Andi Kleen wrote:
>>> On Thu, Mar 17, 2011 at 11:32:55AM +0900, Hidetoshi Seto wrote:
>>>> So to avoid the above problem, add poison checks for both of 4K pages
>>>> and the THP before copying in __collapse_huge_page_copy().
>>>
>>> I don't think you need the check for the huge page -- it should not be allocated
>>> in this case.
>>
>> Is there no case that the THP is once allocated but poison flag
>> is set before copy?  Though I know it is one of corner cases,
>> having this check for THP is worse than nothing.
> 
> There's a theoretical window, but it's only a few instructions.
> Probably not worth caring about, especially since you have a similar
> window after your check again.

At least copy to the last page of the huge page is performed after
all preceding copies are finished.  So I'm not sure it is really
"a few" or not.
Still I think making the window smaller than now is worthwhile,
no matter it is change from 0.1% to 0.01%, or from 0.01% to 0.001%.

Or did you find the downside of the check here?


Thanks,
H.Seto

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/