[CRIU] Dealing with VDSO remap

[Laurent Dufour]

On 20/03/2015 11:46, Cyrill Gorcunov wrote:
> On Fri, Mar 20, 2015 at 11:25:40AM +0100, Laurent Dufour wrote:
>> On 20/03/2015 11:21, Cyrill Gorcunov wrote:
>>> On Fri, Mar 20, 2015 at 11:18:42AM +0100, Laurent Dufour wrote:
>>>>
>>>> You're right Cyrill, if the vDSO is mapped back to the address it has at
>>>> checkpoint time, then the checkpointed stack frame is good. If there is
>>>> a need for a new vDSO then the proxy would have to handle that.
>>>>
>>>> I had to work on this vDSO proxy for ppc64, I put it on the back burner,
>>>> but it's now time to make it.
>>>
>>> Just curious. the vdso for ppc64 is rip relative as well?
>>
>> What do you mean by 'rip relative' ?
> 
> position independent code, ie you can move it to another place
> and still it will work (for x86-64 it means we're use rIP-relative
> addressing)

Yes that's a PIE piece of code. That's necessary since it is mapped at
different place (randomized) per process and the vDSO's pages are shared
between processes (that's needed to have the data part updated in the
back of each process by the kernel).

By the way, is there an IRC channel somewhere to discuss about CRIU ?