Cong Wang <xiyou.wangc...@gmail.com> writes:
> On Wed, May 16, 2018 at 1:29 PM, Toke Høiland-Jørgensen <t...@toke.dk> 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.
>>
>> Signed-off-by: Toke Høiland-Jørgensen <t...@toke.dk>
>> ---
>> net/sched/sch_cake.c | 73
>> ++++++++++++++++++++++++++++++++++++++++++++++++++
>> 1 file changed, 73 insertions(+)
>>
>> diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
>> index 65439b643c92..e1038a7b6686 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)
>> @@ -514,6 +520,60 @@ 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);
>> +}
>> +#else
>> +static void cake_update_flowkeys(struct flow_keys *keys,
>> + const struct sk_buff *skb)
>> +{
>> + /* There is nothing we can do here without CONNTRACK */
>> +}
>> +#endif
>> +
>> /* Cake has several subtle multiple bit settings. In these cases you
>> * would be matching triple isolate mode as well.
>> */
>> @@ -541,6 +601,9 @@ static u32 cake_hash(struct cake_tin_data *q, const
>> struct sk_buff *skb,
>> skb_flow_dissect_flow_keys(skb, &keys,
>> FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
>>
>> + if (flow_mode & CAKE_FLOW_NAT_FLAG)
>> + cake_update_flowkeys(&keys, skb);
>> +
>> /* flow_hash_from_keys() sorts the addresses by value, so we have
>> * to preserve their order in a separate data structure to treat
>> * src and dst host addresses as independently selectable.
>> @@ -1727,6 +1790,12 @@ static int cake_change(struct Qdisc *sch, struct
>> nlattr *opt,
>> q->flow_mode = (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) &
>> CAKE_FLOW_MASK);
>>
>> + if (tb[TCA_CAKE_NAT]) {
>> + q->flow_mode &= ~CAKE_FLOW_NAT_FLAG;
>> + q->flow_mode |= CAKE_FLOW_NAT_FLAG *
>> + !!nla_get_u32(tb[TCA_CAKE_NAT]);
>> + }
>
>
> I think it's better to return -EOPNOTSUPP when CONFIG_NF_CONNTRACK
> is not enabled.
Good point, will fix :)
-Toke
