Re: [RFC] net: add new socket option SO_SETNETNS

[Alok Tiagi <aloktiagi@gmail.com>]

On Thu, Feb 02, 2023 at 09:48:10AM +0800, Hillf Danton wrote:
> On Wed, 1 Feb 2023 19:22:57 +0000 aloktiagi <aloktiagi@gmail.com>
> > @@ -1535,6 +1535,52 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
> >  		WRITE_ONCE(sk->sk_txrehash, (u8)val);
> >  		break;
> >  
> > +	case SO_SETNETNS:
> > +	{
> > +		struct net *other_ns, *my_ns;
> > +
> > +		if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) {
> > +			ret = -EOPNOTSUPP;
> > +			break;
> > +		}
> > +
> > +		if (sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_DGRAM) {
> > +			ret = -EOPNOTSUPP;
> > +			break;
> > +		}
> > +
> > +		other_ns = get_net_ns_by_fd(val);
> > +		if (IS_ERR(other_ns)) {
> > +			ret = PTR_ERR(other_ns);
> > +			break;
> > +		}
> > +
> > +		if (!ns_capable(other_ns->user_ns, CAP_NET_ADMIN)) {
> > +			ret = -EPERM;
> > +			goto out_err;
> > +		}
> > +
> > +		/* check that the socket has never been connected or recently disconnected */
> > +		if (sk->sk_state != TCP_CLOSE || sk->sk_shutdown & SHUTDOWN_MASK) {
> > +			ret = -EOPNOTSUPP;
> > +			goto out_err;
> > +		}
> > +
> > +		/* check that the socket is not bound to an interface*/
> > +		if (sk->sk_bound_dev_if != 0) {
> > +			ret = -EOPNOTSUPP;
> > +			goto out_err;
> > +		}
> > +
> > +		my_ns = sock_net(sk);
> > +		sock_net_set(sk, other_ns);
> > +		put_net(my_ns);
> > +		break;
> 
> 		cpu 0				cpu 2
> 		---				---
> 						ns = sock_net(sk);
> 		my_ns = sock_net(sk);
> 		sock_net_set(sk, other_ns);
> 		put_net(my_ns);
> 						ns is invalid ?

That is the reason we want the socket to be in an un-connected state. That
should help us avoid this situation.

> 
> > +out_err:
> > +		put_net(other_ns);
> > +		break;
> > +	}
> > +
> >  	default:
> >  		ret = -ENOPROTOOPT;
> >  		break;