Re: Hang on large copy_from_user with PREEMPT_NONE

[Sasha Levin]

On 04/07/2015 10:37 AM, Ingo Molnar wrote:
> 
> * Michal Hocko <mhocko@xxxxxxx> wrote:
> 
>> On Tue 07-04-15 13:05:31, Ingo Molnar wrote:
>>>
>>> * Borislav Petkov <bp@xxxxxxxxx> wrote:
>>>
>>>> On Tue, Apr 07, 2015 at 11:31:45AM +0200, Ingo Molnar wrote:
>>>>> Would be nice to see the actual kernel .config, as there's a few
>>>>> debug features that can slow things down significantly, such as
>>>>> CONFIG_KMEMCHECK=y or in some cases CONFIG_DEBUG_PAGEALLOC=y.
>>>>
>>>> He sent it here: https://lkml.kernel.org/r/55229D7E.6080309@xxxxxxxxxx
>>>>
>>>> I'm attaching it again.
>>>
>>> Thanks. Nothing particularly expensive stands out to me at a quick 
>>> glance:-/
>>
>> Sasha uses KASAN very often and it is enabled here as well. I guess 
>> this might slow things really down.
> 
> Indeed, that kind of instrumentation might explain the overhead ...

It locks up quickly without KASan as well.


Thanks,
Sasha

--
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/