Re: switching network namespace midway

[James Chapman <jchapman@katalix.com>]

On 30/10/12 00:21, Eric W. Biederman wrote:
> Stephen Hemminger <shemminger@vyatta.com> writes:
> 
>> On Sat, 27 Oct 2012 22:43:13 -0700
>> ebiederm@xmission.com (Eric W. Biederman) wrote:
>>
>>> Stephen Hemminger <shemminger@vyatta.com> writes:
>>>
>>>> I noticed that the L2TP sockets are not being moved to the correct name
>>>> space.
>>>>
>>>> Something like this is probably needed.
>>>
>>> This is almost right.
>>>
>>> There needs to be a line in l2tp_tunnel_create that verifies
>>> the network namespace of the socket derived from a file descriptor
>>> and the passed in network namespace match.
>>>
>>> For the l2tp_tunnel_sock_create case where we have a socket that is not
>>> exported to userspace using sk_change_net seems appropriate to avoid
>>> reference counting problems.  And it may be worth moving that work into
>>> sk_create_kern.  But we need a network namespace hook that will lookup
>>> all l2tp tunnel sockets when a network namespace is being destroyed and
>>> remove them.  I think we can hit this bug with rmmod as well.
>>
>> Since I don't use netns or L2TP for real, someone else needs to take
>> up the crusade here.
> 
> Let's see if James Chapman is interested.  I don't use L2TP for real either.
> 
> James are you at all interested in the network namespace bugs that have
> been found in the l2tp code?

Very much so, Eric. Thanks for keeping me in the loop. Unfortunately, I
am busy on other things at the moment. It's in my queue. I'll get to it
as soon as I can.

> 
> Eric


-- 
James Chapman
Katalix Systems Ltd
http://www.katalix.com
Catalysts for your Embedded Linux software development