| Message ID | 6b9347d5c1a0b364e88d900b29a616c3f8e5b1ca.1723483073.git.lucien.xin@gmail.com (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | fcb1aa5163b1ae4cf2864b688b08927aac51f51e |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [PATCHv2,net-next] openvswitch: switch to per-action label counting in conntrack | expand |
Xin Long <lucien.xin@gmail.com> writes: > Similar to commit 70f06c115bcc ("sched: act_ct: switch to per-action > label counting"), we should also switch to per-action label counting > in openvswitch conntrack, as Florian suggested. > > The difference is that nf_connlabels_get() is called unconditionally > when creating an ct action in ovs_ct_copy_action(). As with these > flows: > > table=0,ip,actions=ct(commit,table=1) > table=1,ip,actions=ct(commit,exec(set_field:0xac->ct_label),table=2) > > it needs to make sure the label ext is created in the 1st flow before > the ct is committed in ovs_ct_commit(). Otherwise, the warning in > nf_ct_ext_add() when creating the label ext in the 2nd flow will > be triggered: > > WARN_ON(nf_ct_is_confirmed(ct)); > > Signed-off-by: Xin Long <lucien.xin@gmail.com> > --- Reviewed-by: Aaron Conole <aconole@redhat.com>
Xin Long <lucien.xin@gmail.com> wrote: > Similar to commit 70f06c115bcc ("sched: act_ct: switch to per-action > label counting"), we should also switch to per-action label counting > in openvswitch conntrack, as Florian suggested. > > The difference is that nf_connlabels_get() is called unconditionally > when creating an ct action in ovs_ct_copy_action(). As with these > flows: > > table=0,ip,actions=ct(commit,table=1) > table=1,ip,actions=ct(commit,exec(set_field:0xac->ct_label),table=2) > > it needs to make sure the label ext is created in the 1st flow before > the ct is committed in ovs_ct_commit(). Otherwise, the warning in > nf_ct_ext_add() when creating the label ext in the 2nd flow will > be triggered: With this and https://patchwork.ozlabs.org/project/netfilter-devel/patch/7380c37e2d58a93164b7f2212c90cd23f9d910f8.1721268584.git.lucien.xin@gmail.com/ applied new netns doesn't have conntrack enabled anymore, so Acked-by: Florian Westphal <fw@strlen.de> Thanks Xinlong!
Hello: This patch was applied to netdev/net-next.git (main) by Jakub Kicinski <kuba@kernel.org>: On Mon, 12 Aug 2024 13:17:53 -0400 you wrote: > Similar to commit 70f06c115bcc ("sched: act_ct: switch to per-action > label counting"), we should also switch to per-action label counting > in openvswitch conntrack, as Florian suggested. > > The difference is that nf_connlabels_get() is called unconditionally > when creating an ct action in ovs_ct_copy_action(). As with these > flows: > > [...] Here is the summary with links: - [PATCHv2,net-next] openvswitch: switch to per-action label counting in conntrack https://git.kernel.org/netdev/net-next/c/fcb1aa5163b1 You are awesome, thank you!
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 8eb1d644b741..a3da5ee34f92 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1368,11 +1368,8 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - attr == OVS_KEY_ATTR_CT_LABELS) { - struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - - return ovs_net->xt_label; - } + attr == OVS_KEY_ATTR_CT_LABELS) + return true; return false; } @@ -1381,6 +1378,7 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log) { + unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_conntrack_info ct_info; const char *helper = NULL; u16 family; @@ -1409,6 +1407,12 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, return -ENOMEM; } + if (nf_connlabels_get(net, n_bits - 1)) { + nf_ct_tmpl_free(ct_info.ct); + OVS_NLERR(log, "Failed to set connlabel length"); + return -EOPNOTSUPP; + } + if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) @@ -1577,6 +1581,7 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) if (ct_info->ct) { if (ct_info->timeout[0]) nf_ct_destroy_timeout(ct_info->ct); + nf_connlabels_put(nf_ct_net(ct_info->ct)); nf_ct_tmpl_free(ct_info->ct); } } @@ -2002,17 +2007,9 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = { int ovs_ct_init(struct net *net) { - unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - if (nf_connlabels_get(net, n_bits - 1)) { - ovs_net->xt_label = false; - OVS_NLERR(true, "Failed to set connlabel length"); - } else { - ovs_net->xt_label = true; - } - -#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) return ovs_ct_limit_init(net, ovs_net); #else return 0; @@ -2021,12 +2018,9 @@ int ovs_ct_init(struct net *net) void ovs_ct_exit(struct net *net) { +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_net *ovs_net = net_generic(net, ovs_net_id); -#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) ovs_ct_limit_exit(net, ovs_net); #endif - - if (ovs_net->xt_label) - nf_connlabels_put(net); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 9ca6231ea647..365b9bb7f546 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -160,9 +160,6 @@ struct ovs_net { #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_ct_limit_info *ct_limit_info; #endif - - /* Module reference for configuring conntrack. */ - bool xt_label; }; /**
Similar to commit 70f06c115bcc ("sched: act_ct: switch to per-action label counting"), we should also switch to per-action label counting in openvswitch conntrack, as Florian suggested. The difference is that nf_connlabels_get() is called unconditionally when creating an ct action in ovs_ct_copy_action(). As with these flows: table=0,ip,actions=ct(commit,table=1) table=1,ip,actions=ct(commit,exec(set_field:0xac->ct_label),table=2) it needs to make sure the label ext is created in the 1st flow before the ct is committed in ovs_ct_commit(). Otherwise, the warning in nf_ct_ext_add() when creating the label ext in the 2nd flow will be triggered: WARN_ON(nf_ct_is_confirmed(ct)); Signed-off-by: Xin Long <lucien.xin@gmail.com> --- v2: move ovs_net into #if in ovs_ct_exit() as Jakub noticed. --- net/openvswitch/conntrack.c | 30 ++++++++++++------------------ net/openvswitch/datapath.h | 3 --- 2 files changed, 12 insertions(+), 21 deletions(-)