Skip to contentSkip to conversation

Question about xfrm by MARK feature

DISCUSSION Gerd v. Egidy 4 participants 7 messages Jun 23, 2010 – Jun 25, 2010

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

Hi Jamal,

while looking through the 2.6.34 changelog I found the xfrm by MARK feature you developed in february. I'm currently working on NAT for ipsec connections and thought your feature might help me.

For example I have 2 different remote networks with the same ip network each and both of them have a tunnel to the same local network. I map their IPs to something different so I can distinguish them in the local network. But after the nat the xfrm code sees two tunnels with exactly the same values. So this can't work.

But if I understood your feature correctly, I can now mark the packets (e.g. in iptables with ... -j MARK --set-mark 1) and have xfrm select the correct ipsec tunnel via the mark. Correct?

But does your feature also set the mark on packets decrypted by xfrm? I need some way to find out from which tunnel the packet came to correctly treat it.

Do you know if any of the ipsec solutions for linux (e.g. strongswan, openswan, racoon) already have support for this feature or are developing on it?

Kind regards,

Gerd

Signature · 2 lines
Address (better: trap) for people I really don't want to get mail from:
[email protected]
#1 lore raw
Quoted 10 lines · Gerd v. Egidy

Hi Jamal,

while looking through the 2.6.34 changelog I found the xfrm by MARK feature you developed in february. I'm currently working on NAT for ipsec connections and thought your feature might help me.

For example I have 2 different remote networks with the same ip network each and both of them have a tunnel to the same local network. I map their IPs to something different so I can distinguish them in the local network. But after the nat the xfrm code sees two tunnels with exactly the same values. So this can't work.

But if I understood your feature correctly, I can now mark the packets (e.g. in iptables with ... -j MARK --set-mark 1) and have xfrm select the correct ipsec tunnel via the mark. Correct?

But does your feature also set the mark on packets decrypted by xfrm? I need some way to find out from which tunnel the packet came to correctly treat it.

You should be able to use the policy match to distinguish the tunnels, f.i. by matching on the tunnel endpoints.

#2 lore raw
Quoted 6 lines
Quoted 3 lines

But does your feature also set the mark on packets decrypted by xfrm? I need some way to find out from which tunnel the packet came to correctly treat it.

You should be able to use the policy match to distinguish the tunnels, f.i. by matching on the tunnel endpoints.

That would work for endpoints with fixed ips. But as soon as the endpoint has a dynamic ip, I'd have to change the iptables depending on the vpns currently connected. This is something I want to avoid in any case.

Reason is that I'd have to introduce some kind of locking around the calls to iptables. Otherwise two connections established or disconnected nearly simultaneously could result in loss of the rules for one of them.

Kind regards,

Gerd

#3 lore raw
Quoted 4 lines · Gerd v. Egidy

That would work for endpoints with fixed ips. But as soon as the endpoint has a dynamic ip, I'd have to change the iptables depending on the vpns currently connected. This is something I want to avoid in any case.

That's what reqids are for.

Cheers,

Signature · 4 lines
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <[email protected]>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
#4 lore raw
In reply to Gerd v. Egidy

Hi Gerd,

Quoted 8 lines · Gerd v. Egidy

Hi Jamal,

while looking through the 2.6.34 changelog I found the xfrm by MARK feature you developed in february. I'm currently working on NAT for ipsec connections and thought your feature might help me.

For example I have 2 different remote networks with the same ip network each and both of them have a tunnel to the same local network.

It seems "Same IP network" means that two remote locations will have exactly same IP address? This is hard of course - but nat may do it.. There's also the nat zones feature that Patrick introduced a while back that may help you

Quoted 5 lines

I map their IPs to
something different so I can distinguish them in the local network. But after the nat the xfrm code sees two tunnels with exactly the same values. So this can't work.

Can you look at the incoming encrypted packet headers and tell if they are from different remotes? If not, are different remotes coming in via a different network device? If yes, you can install a tc rule to mark them as they come in before decryption and that mark should stay with them even after they get decrypted.

Quoted 7 lines

But if I understood your feature correctly, I can now mark the packets (e.g. in iptables with ... -j MARK --set-mark 1) and have xfrm select the correct ipsec tunnel via the mark. Correct?

But does your feature also set the mark on packets decrypted by xfrm? I need some way to find out from which tunnel the packet came to correctly treat it.

Refer to above and also to policy routing.

Quoted 3 lines

Do you know if any of the ipsec solutions for linux (e.g. strongswan, openswan, racoon) already have support for this feature or are developing on it?

AFAIK, only iproute2 can use marks. I believe the ike daemons can be made to use reqid (as Herbert mentioned) but i am not sure that is sufficient for what you want.

cheers,
jamal

#5 lore raw

Hi Jamal,

thanks for your detailed answer.

Quoted 5 lines
Quoted 2 lines

For example I have 2 different remote networks with the same ip network each and both of them have a tunnel to the same local network.

It seems "Same IP network" means that two remote locations will have exactly same IP address?

yes

Quoted 3 lines

This is hard of course - but nat may do it..
There's also the nat zones feature that Patrick introduced a while back that may help you

I'm using Patricks conntrack zones. And Patrick helped me with a input chain in the nat table. The other cases with e.g. a ip clash between local and remote net already work.

So only the case with two remotes and same ips is missing.

Quoted 9 lines
Quoted 4 lines

I map their IPs to
something different so I can distinguish them in the local network. But after the nat the xfrm code sees two tunnels with exactly the same values. So this can't work.

Can you look at the incoming encrypted packet headers and tell if they are from different remotes? If not, are different remotes coming in via a different network device? If yes, you can install a tc rule to mark them as they come in before decryption

I planned to avoid looking at the remote gateway ip (to even allow two different remote gateways hiding natted behind the same ip) but that would be a good fallback solution if my other ideas don't work out.

Quoted 2 lines

and that mark should stay with
them even after they get decrypted.

Didn't know that, very good.

I just contacted the strongswan maintainers about reqids and marks. Let's see if this works out...

Kind regards,

Gerd

Signature · 2 lines
Address (better: trap) for people I really don't want to get mail from:
[email protected]
#6 lore raw

Hi Gerd,

Quoted 4 lines · Gerd v. Egidy

I planned to avoid looking at the remote gateway ip (to even allow two different remote gateways hiding natted behind the same ip) but that would be a good fallback solution if my other ideas don't work out.

Doesnt have to be a remote IP...
If you can somehow even map a remote to some MAC address or incoming virtual interface (such as a VLAN) that would do it as well. Alternatively, you should probably look at namespaces - i just find it more usable when you have overlapping/conflicting ip addresses. You of course will have to run strongswan per namespace if you dont want to hack strongswan.

cheers,
jamal