net: create nf_conntrack_ovs for ovs and tc use

Similar to nf_nat_ovs created by Commit ebddb1404900 ("net: move the
nat function to nf_nat_ovs for ovs and tc"), this patch is to create
nf_conntrack_ovs to get these functions shared by OVS and TC only.

There are nf_ct_helper() and nf_ct_add_helper() from nf_conntrak_helper
in this patch, and will be more in the following patches.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index f71b41c..4d67371 100644 (file)
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -189,6 +189,9 @@ config NF_CONNTRACK_LABELS
          to connection tracking entries.  It can be used with xtables connlabel
          match and the nftables ct expression.
 
+config NF_CONNTRACK_OVS
+       bool
+
 config NF_CT_PROTO_DCCP
        bool 'DCCP protocol connection tracking support'
        depends on NETFILTER_ADVANCED

diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index ba2a6b5..5ffef1c 100644 (file)
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -11,6 +11,7 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o
+nf_conntrack-$(CONFIG_NF_CONNTRACK_OVS) += nf_conntrack_ovs.o
 nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o
 nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o
 nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o

diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 48ea6d0..0c4db2f 100644 (file)
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -242,104 +242,6 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
 }
 EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper);
 
-/* 'skb' should already be pulled to nh_ofs. */
-int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct,
-                enum ip_conntrack_info ctinfo, u16 proto)
-{
-       const struct nf_conntrack_helper *helper;
-       const struct nf_conn_help *help;
-       unsigned int protoff;
-       int err;
-
-       if (ctinfo == IP_CT_RELATED_REPLY)
-               return NF_ACCEPT;
-
-       help = nfct_help(ct);
-       if (!help)
-               return NF_ACCEPT;
-
-       helper = rcu_dereference(help->helper);
-       if (!helper)
-               return NF_ACCEPT;
-
-       if (helper->tuple.src.l3num != NFPROTO_UNSPEC &&
-           helper->tuple.src.l3num != proto)
-               return NF_ACCEPT;
-
-       switch (proto) {
-       case NFPROTO_IPV4:
-               protoff = ip_hdrlen(skb);
-               proto = ip_hdr(skb)->protocol;
-               break;
-       case NFPROTO_IPV6: {
-               u8 nexthdr = ipv6_hdr(skb)->nexthdr;
-               __be16 frag_off;
-               int ofs;
-
-               ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
-                                      &frag_off);
-               if (ofs < 0 || (frag_off & htons(~0x7)) != 0) {
-                       pr_debug("proto header not found\n");
-                       return NF_ACCEPT;
-               }
-               protoff = ofs;
-               proto = nexthdr;
-               break;
-       }
-       default:
-               WARN_ONCE(1, "helper invoked on non-IP family!");
-               return NF_DROP;
-       }
-
-       if (helper->tuple.dst.protonum != proto)
-               return NF_ACCEPT;
-
-       err = helper->help(skb, protoff, ct, ctinfo);
-       if (err != NF_ACCEPT)
-               return err;
-
-       /* Adjust seqs after helper.  This is needed due to some helpers (e.g.,
-        * FTP with NAT) adusting the TCP payload size when mangling IP
-        * addresses and/or port numbers in the text-based control connection.
-        */
-       if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
-           !nf_ct_seq_adjust(skb, ct, ctinfo, protoff))
-               return NF_DROP;
-       return NF_ACCEPT;
-}
-EXPORT_SYMBOL_GPL(nf_ct_helper);
-
-int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family,
-                    u8 proto, bool nat, struct nf_conntrack_helper **hp)
-{
-       struct nf_conntrack_helper *helper;
-       struct nf_conn_help *help;
-       int ret = 0;
-
-       helper = nf_conntrack_helper_try_module_get(name, family, proto);
-       if (!helper)
-               return -EINVAL;
-
-       help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
-       if (!help) {
-               nf_conntrack_helper_put(helper);
-               return -ENOMEM;
-       }
-#if IS_ENABLED(CONFIG_NF_NAT)
-       if (nat) {
-               ret = nf_nat_helper_try_module_get(name, family, proto);
-               if (ret) {
-                       nf_conntrack_helper_put(helper);
-                       return ret;
-               }
-       }
-#endif
-       rcu_assign_pointer(help->helper, helper);
-       *hp = helper;
-       return ret;
-}
-EXPORT_SYMBOL_GPL(nf_ct_add_helper);
-
 /* appropriate ct lock protecting must be taken by caller */
 static int unhelp(struct nf_conn *ct, void *me)
 {

diff --git a/net/netfilter/nf_conntrack_ovs.c b/net/netfilter/nf_conntrack_ovs.c
new file mode 100644 (file)
index 0000000..eff4d53
--- /dev/null
+++ b/net/netfilter/nf_conntrack_ovs.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Support ct functions for openvswitch and used by OVS and TC conntrack. */
+
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/ip.h>
+
+/* 'skb' should already be pulled to nh_ofs. */
+int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct,
+                enum ip_conntrack_info ctinfo, u16 proto)
+{
+       const struct nf_conntrack_helper *helper;
+       const struct nf_conn_help *help;
+       unsigned int protoff;
+       int err;
+
+       if (ctinfo == IP_CT_RELATED_REPLY)
+               return NF_ACCEPT;
+
+       help = nfct_help(ct);
+       if (!help)
+               return NF_ACCEPT;
+
+       helper = rcu_dereference(help->helper);
+       if (!helper)
+               return NF_ACCEPT;
+
+       if (helper->tuple.src.l3num != NFPROTO_UNSPEC &&
+           helper->tuple.src.l3num != proto)
+               return NF_ACCEPT;
+
+       switch (proto) {
+       case NFPROTO_IPV4:
+               protoff = ip_hdrlen(skb);
+               proto = ip_hdr(skb)->protocol;
+               break;
+       case NFPROTO_IPV6: {
+               u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+               __be16 frag_off;
+               int ofs;
+
+               ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+                                      &frag_off);
+               if (ofs < 0 || (frag_off & htons(~0x7)) != 0) {
+                       pr_debug("proto header not found\n");
+                       return NF_ACCEPT;
+               }
+               protoff = ofs;
+               proto = nexthdr;
+               break;
+       }
+       default:
+               WARN_ONCE(1, "helper invoked on non-IP family!");
+               return NF_DROP;
+       }
+
+       if (helper->tuple.dst.protonum != proto)
+               return NF_ACCEPT;
+
+       err = helper->help(skb, protoff, ct, ctinfo);
+       if (err != NF_ACCEPT)
+               return err;
+
+       /* Adjust seqs after helper.  This is needed due to some helpers (e.g.,
+        * FTP with NAT) adusting the TCP payload size when mangling IP
+        * addresses and/or port numbers in the text-based control connection.
+        */
+       if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+           !nf_ct_seq_adjust(skb, ct, ctinfo, protoff))
+               return NF_DROP;
+       return NF_ACCEPT;
+}
+EXPORT_SYMBOL_GPL(nf_ct_helper);
+
+int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family,
+                    u8 proto, bool nat, struct nf_conntrack_helper **hp)
+{
+       struct nf_conntrack_helper *helper;
+       struct nf_conn_help *help;
+       int ret = 0;
+
+       helper = nf_conntrack_helper_try_module_get(name, family, proto);
+       if (!helper)
+               return -EINVAL;
+
+       help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
+       if (!help) {
+               nf_conntrack_helper_put(helper);
+               return -ENOMEM;
+       }
+#if IS_ENABLED(CONFIG_NF_NAT)
+       if (nat) {
+               ret = nf_nat_helper_try_module_get(name, family, proto);
+               if (ret) {
+                       nf_conntrack_helper_put(helper);
+                       return ret;
+               }
+       }
+#endif
+       rcu_assign_pointer(help->helper, helper);
+       *hp = helper;
+       return ret;
+}
+EXPORT_SYMBOL_GPL(nf_ct_add_helper);

diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 747d537..29a7081 100644 (file)
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -15,6 +15,7 @@ config OPENVSWITCH
        select NET_MPLS_GSO
        select DST_CACHE
        select NET_NSH
+       select NF_CONNTRACK_OVS if NF_CONNTRACK
        select NF_NAT_OVS if NF_NAT
        help
          Open vSwitch is a multilayer Ethernet switch targeted at virtualized

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index f5acb53..4f7b52f 100644 (file)
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -984,6 +984,7 @@ config NET_ACT_TUNNEL_KEY
 config NET_ACT_CT
        tristate "connection tracking tc action"
        depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE
+       select NF_CONNTRACK_OVS
        select NF_NAT_OVS if NF_NAT
        help
          Say Y here to allow sending the packets to conntrack module.