Commit ebddb140 authored by Xin Long's avatar Xin Long Committed by David S. Miller
Browse files

net: move the nat function to nf_nat_ovs for ovs and tc 



There are two nat functions are nearly the same in both OVS and
TC code, (ovs_)ct_nat_execute() and ovs_ct_nat/tcf_ct_act_nat().

This patch creates nf_nat_ovs.c under netfilter and moves them
there then exports nf_ct_nat() so that it can be shared by both
OVS and TC, and keeps the nat (type) check and nat flag update
in OVS and TC's own place, as these parts are different between
OVS and TC.

Note that in OVS nat function it was using skb->protocol to get
the proto as it already skips vlans in key_extract(), while it
doesn't in TC, and TC has to call skb_protocol() to get proto.
So in nf_ct_nat_execute(), we keep using skb_protocol() which
works for both OVS and TC contrack.

Signed-off-by: default avatarXin Long <lucien.xin@gmail.com>
Acked-by: default avatarAaron Conole <aconole@redhat.com>
Acked-by: default avatarPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 0564c3e5

include/net/netfilter/nf_nat.h

+4 −0
Original line number Diff line number Diff line
@@ -104,6 +104,10 @@ unsigned int 
nf_nat_inet_fn(void *priv, struct sk_buff *skb,

	       const struct nf_hook_state *state);



int nf_ct_nat(struct sk_buff *skb, struct nf_conn *ct,

	      enum ip_conntrack_info ctinfo, int *action,

	      const struct nf_nat_range2 *range, bool commit);



static inline int nf_nat_initialized(const struct nf_conn *ct,

				     enum nf_nat_manip_type manip)

{

net/netfilter/Kconfig

+3 −0
Original line number Diff line number Diff line
@@ -459,6 +459,9 @@ config NF_NAT_REDIRECT 
config NF_NAT_MASQUERADE

	bool



config NF_NAT_OVS

	bool



config NETFILTER_SYNPROXY

	tristate

net/netfilter/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -59,6 +59,7 @@ obj-$(CONFIG_NF_LOG_SYSLOG) += nf_log_syslog.o 
obj-$(CONFIG_NF_NAT) += nf_nat.o

nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o

nf_nat-$(CONFIG_NF_NAT_MASQUERADE) += nf_nat_masquerade.o

nf_nat-$(CONFIG_NF_NAT_OVS) += nf_nat_ovs.o



ifeq ($(CONFIG_NF_NAT),m)

nf_nat-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_nat_bpf.o

net/netfilter/nf_nat_ovs.c

0 → 100644
+135 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0-only

/* Support nat functions for openvswitch and used by OVS and TC conntrack. */



#include <net/netfilter/nf_nat.h>



/* Modelled after nf_nat_ipv[46]_fn().

 * range is only used for new, uninitialized NAT state.

 * Returns either NF_ACCEPT or NF_DROP.

 */

static int nf_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,

			     enum ip_conntrack_info ctinfo, int *action,

			     const struct nf_nat_range2 *range,

			     enum nf_nat_manip_type maniptype)

{

	__be16 proto = skb_protocol(skb, true);

	int hooknum, err = NF_ACCEPT;



	/* See HOOK2MANIP(). */

	if (maniptype == NF_NAT_MANIP_SRC)

		hooknum = NF_INET_LOCAL_IN; /* Source NAT */

	else

		hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */



	switch (ctinfo) {

	case IP_CT_RELATED:

	case IP_CT_RELATED_REPLY:

		if (proto == htons(ETH_P_IP) &&

		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {

			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,

							   hooknum))

				err = NF_DROP;

			goto out;

		} else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) {

			__be16 frag_off;

			u8 nexthdr = ipv6_hdr(skb)->nexthdr;

			int hdrlen = ipv6_skip_exthdr(skb,

						      sizeof(struct ipv6hdr),

						      &nexthdr, &frag_off);



			if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {

				if (!nf_nat_icmpv6_reply_translation(skb, ct,

								     ctinfo,

								     hooknum,

								     hdrlen))

					err = NF_DROP;

				goto out;

			}

		}

		/* Non-ICMP, fall thru to initialize if needed. */

		fallthrough;

	case IP_CT_NEW:

		/* Seen it before?  This can happen for loopback, retrans,

		 * or local packets.

		 */

		if (!nf_nat_initialized(ct, maniptype)) {

			/* Initialize according to the NAT action. */

			err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)

				/* Action is set up to establish a new

				 * mapping.

				 */

				? nf_nat_setup_info(ct, range, maniptype)

				: nf_nat_alloc_null_binding(ct, hooknum);

			if (err != NF_ACCEPT)

				goto out;

		}

		break;



	case IP_CT_ESTABLISHED:

	case IP_CT_ESTABLISHED_REPLY:

		break;



	default:

		err = NF_DROP;

		goto out;

	}



	err = nf_nat_packet(ct, ctinfo, hooknum, skb);

	if (err == NF_ACCEPT)

		*action |= BIT(maniptype);

out:

	return err;

}



int nf_ct_nat(struct sk_buff *skb, struct nf_conn *ct,

	      enum ip_conntrack_info ctinfo, int *action,

	      const struct nf_nat_range2 *range, bool commit)

{

	enum nf_nat_manip_type maniptype;

	int err, ct_action = *action;



	*action = 0;



	/* Add NAT extension if not confirmed yet. */

	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))

		return NF_DROP;   /* Can't NAT. */



	if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) &&

	    (ctinfo != IP_CT_RELATED || commit)) {

		/* NAT an established or related connection like before. */

		if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)

			/* This is the REPLY direction for a connection

			 * for which NAT was applied in the forward

			 * direction.  Do the reverse NAT.

			 */

			maniptype = ct->status & IPS_SRC_NAT

				? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;

		else

			maniptype = ct->status & IPS_SRC_NAT

				? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;

	} else if (ct_action & BIT(NF_NAT_MANIP_SRC)) {

		maniptype = NF_NAT_MANIP_SRC;

	} else if (ct_action & BIT(NF_NAT_MANIP_DST)) {

		maniptype = NF_NAT_MANIP_DST;

	} else {

		return NF_ACCEPT;

	}



	err = nf_ct_nat_execute(skb, ct, ctinfo, action, range, maniptype);

	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {

		if (ct->status & IPS_SRC_NAT) {

			if (maniptype == NF_NAT_MANIP_SRC)

				maniptype = NF_NAT_MANIP_DST;

			else

				maniptype = NF_NAT_MANIP_SRC;



			err = nf_ct_nat_execute(skb, ct, ctinfo, action, range,

						maniptype);

		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {

			err = nf_ct_nat_execute(skb, ct, ctinfo, action, NULL,

						NF_NAT_MANIP_SRC);

		}

	}

	return err;

}

EXPORT_SYMBOL_GPL(nf_ct_nat);

net/openvswitch/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -15,6 +15,7 @@ config OPENVSWITCH 
	select NET_MPLS_GSO

	select DST_CACHE

	select NET_NSH

	select NF_NAT_OVS if NF_NAT

	help

	  Open vSwitch is a multilayer Ethernet switch targeted at virtualized

	  environments.  In addition to supporting a variety of features