On 07/31/2014 02:23 PM, Herbert Xu wrote:
> On Thu, Jul 31, 2014 at 11:07:26AM +0800, Ming Liu wrote:
>> And we've figure out a patch as the attached, the basic idea is just
>> queue the packets if "irq_fpu_usable()" is not usable or if there
>> are already few packets queued for decryption. Else decrypt the
>> packets.
> Yes your description makes sense and I will review your patch
> for inclusion.
Hi, Herbert:

Please review this attached patch instead, the original one has a 
problem causing the kernel crash.

the best,
thank you
>
> Thanks,