Re: [Cake] [PATCH net-next v15 4/7] sch_cake: Add NAT awareness to packet classifier

[Pablo Neira Ayuso <pablo@netfilter.org>]

Hi Toke,

On Tue, May 22, 2018 at 03:57:38PM +0200, Toke Høiland-Jørgensen wrote:
> When CAKE is deployed on a gateway that also performs NAT (which is a
> common deployment mode), the host fairness mechanism cannot distinguish
> internal hosts from each other, and so fails to work correctly.
> 
> To fix this, we add an optional NAT awareness mode, which will query the
> kernel conntrack mechanism to obtain the pre-NAT addresses for each packet
> and use that in the flow and host hashing.
> 
> When the shaper is enabled and the host is already performing NAT, the cost
> of this lookup is negligible. However, in unlimited mode with no NAT being
> performed, there is a significant CPU cost at higher bandwidths. For this
> reason, the feature is turned off by default.
> 
> Cc: netfilter-devel@vger.kernel.org
> Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
> ---
>  net/sched/sch_cake.c |   79 ++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 79 insertions(+)
> 
> diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
> index 68ac908470f1..6f7cae705c84 100644
> --- a/net/sched/sch_cake.c
> +++ b/net/sched/sch_cake.c
> @@ -71,6 +71,12 @@
>  #include <net/tcp.h>
>  #include <net/flow_dissector.h>
>  
> +#if IS_REACHABLE(CONFIG_NF_CONNTRACK)
> +#include <net/netfilter/nf_conntrack_core.h>
> +#include <net/netfilter/nf_conntrack_zones.h>
> +#include <net/netfilter/nf_conntrack.h>
> +#endif
> +
>  #define CAKE_SET_WAYS (8)
>  #define CAKE_MAX_TINS (8)
>  #define CAKE_QUEUES (1024)
> @@ -516,6 +522,60 @@ static bool cobalt_should_drop(struct cobalt_vars *vars,
>  	return drop;
>  }
>  
> +#if IS_REACHABLE(CONFIG_NF_CONNTRACK)
> +
> +static void cake_update_flowkeys(struct flow_keys *keys,
> +				 const struct sk_buff *skb)
> +{
> +	const struct nf_conntrack_tuple *tuple;
> +	enum ip_conntrack_info ctinfo;
> +	struct nf_conn *ct;
> +	bool rev = false;
> +
> +	if (tc_skb_protocol(skb) != htons(ETH_P_IP))
> +		return;
> +
> +	ct = nf_ct_get(skb, &ctinfo);
> +	if (ct) {
> +		tuple = nf_ct_tuple(ct, CTINFO2DIR(ctinfo));
> +	} else {
> +		const struct nf_conntrack_tuple_hash *hash;
> +		struct nf_conntrack_tuple srctuple;
> +
> +		if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
> +				       NFPROTO_IPV4, dev_net(skb->dev),
> +				       &srctuple))
> +			return;
> +
> +		hash = nf_conntrack_find_get(dev_net(skb->dev),
> +					     &nf_ct_zone_dflt,
> +					     &srctuple);
> +		if (!hash)
> +			return;
> +
> +		rev = true;
> +		ct = nf_ct_tuplehash_to_ctrack(hash);
> +		tuple = nf_ct_tuple(ct, !hash->tuple.dst.dir);
> +	}
> +
> +	keys->addrs.v4addrs.src = rev ? tuple->dst.u3.ip : tuple->src.u3.ip;
> +	keys->addrs.v4addrs.dst = rev ? tuple->src.u3.ip : tuple->dst.u3.ip;
> +
> +	if (keys->ports.ports) {
> +		keys->ports.src = rev ? tuple->dst.u.all : tuple->src.u.all;
> +		keys->ports.dst = rev ? tuple->src.u.all : tuple->dst.u.all;
> +	}
> +	if (rev)
> +		nf_ct_put(ct);
> +}

This is going to pull in the nf_conntrack module, even if you may not
want it, as soon as cake is in place.