diff mbox series

[PATCHv2,net-next,5/5] net: move the nat function to nf_nat_ovs for ovs and tc

Message ID bf19487f4dfc8cd91a4395672d9905b10917128d.1669138256.git.lucien.xin@gmail.com (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series net: eliminate the duplicate code in the ct nat functions of ovs and tc | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 20 this patch: 20
netdev/cc_maintainers warning 3 maintainers not CCed: coreteam@netfilter.org netfilter-devel@vger.kernel.org kadlec@netfilter.org
netdev/build_clang success Errors and warnings before: 5 this patch: 5
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 20 this patch: 20
netdev/checkpatch warning WARNING: Prefer 'fallthrough;' over fallthrough comment WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? WARNING: line length of 83 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Xin Long Nov. 22, 2022, 5:32 p.m. UTC
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.

Reviewed-by: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
 include/net/netfilter/nf_nat.h |   4 +
 net/netfilter/Makefile         |   2 +-
 net/netfilter/nf_nat_ovs.c     | 135 ++++++++++++++++++++++++++++++++
 net/openvswitch/conntrack.c    | 137 +++------------------------------
 net/sched/act_ct.c             | 136 +++-----------------------------
 5 files changed, 161 insertions(+), 253 deletions(-)
 create mode 100644 net/netfilter/nf_nat_ovs.c

Comments

Marcelo Ricardo Leitner Nov. 23, 2022, 3:09 p.m. UTC | #1
On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> +		maniptype = NF_NAT_MANIP_SRC;
> +	} else if (ct_action & (1 << 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);
> diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> index cc643a556ea1..d03c75165663 100644
> --- a/net/openvswitch/conntrack.c
> +++ b/net/openvswitch/conntrack.c
> @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
>  	}
>  }
>  
> -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> -			      enum ip_conntrack_info ctinfo,
> -			      const struct nf_nat_range2 *range,
> -			      enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> -{
> -	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 (IS_ENABLED(CONFIG_NF_NAT) &&
> -		    skb->protocol == 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) &&
> -			   skb->protocol == 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);
> -out:
> -	/* Update the flow key if NAT successful. */
> -	if (err == NF_ACCEPT)
> -		ovs_nat_update_key(key, skb, maniptype);
> -
> -	return err;
> -}
> -
>  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
>  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
>  		      const struct ovs_conntrack_info *info,
>  		      struct sk_buff *skb, struct nf_conn *ct,
>  		      enum ip_conntrack_info ctinfo)
>  {
> -	enum nf_nat_manip_type maniptype;
> -	int err;
> +	int err, action = 0;
>  
>  	if (!(info->nat & OVS_CT_NAT))
>  		return NF_ACCEPT;
> +	if (info->nat & OVS_CT_SRC_NAT)
> +		action |= (1 << NF_NAT_MANIP_SRC);
> +	if (info->nat & OVS_CT_DST_NAT)
> +		action |= (1 << NF_NAT_MANIP_DST);

I'm wondering why this dance at this level with supporting multiple
MANIPs while actually only one can be used at a time.

act_ct will reject an action using both:
        if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
            (p->ct_action & TCA_CT_ACT_NAT_DST)) {
                NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
                return -EOPNOTSUPP;

I couldn't find this kind of check in ovs code right now (didn't look much, I
confess :)), but even the code here was already doing:

-	} else if (info->nat & OVS_CT_SRC_NAT) {
-		maniptype = NF_NAT_MANIP_SRC;
-	} else if (info->nat & OVS_CT_DST_NAT) {
-		maniptype = NF_NAT_MANIP_DST;

And in case of tuple conflict, maniptype will be forcibly updated in
[*] below.

Anyhow, if really needed, it would be nice to use BIT(NF_NAT_MANIP_..)
instead.

>  
> -	/* Add NAT extension if not confirmed yet. */
> -	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
> -		return NF_ACCEPT;   /* Can't NAT. */
> +	err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit);
>  
> -	/* Determine NAT type.
> -	 * Check if the NAT type can be deduced from the tracked connection.
> -	 * Make sure new expected connections (IP_CT_RELATED) are NATted only
> -	 * when committing.
> -	 */
> -	if (ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK &&
> -	    (ctinfo != IP_CT_RELATED || info->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 (info->nat & OVS_CT_SRC_NAT) {
> -		maniptype = NF_NAT_MANIP_SRC;
> -	} else if (info->nat & OVS_CT_DST_NAT) {
> -		maniptype = NF_NAT_MANIP_DST;
> -	} else {
> -		return NF_ACCEPT; /* Connection is not NATed. */
> -	}
> -	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key);
> -
> -	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 = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
> -						 maniptype, key);
> -		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
> -			err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
> -						 NF_NAT_MANIP_SRC, key);
> -		}
> -	}
> +	if (action & (1 << NF_NAT_MANIP_SRC))
> +		ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC);
> +	if (action & (1 << NF_NAT_MANIP_DST))
> +		ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST);
>  
>  	return err;
>  }
> diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
> index c7782c9a6ab6..0c410220239f 100644
> --- a/net/sched/act_ct.c
> +++ b/net/sched/act_ct.c
> @@ -863,90 +863,6 @@ static void tcf_ct_params_free_rcu(struct rcu_head *head)
>  	tcf_ct_params_free(params);
>  }
>  
> -#if IS_ENABLED(CONFIG_NF_NAT)
> -/* 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 ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> -			  enum ip_conntrack_info ctinfo,
> -			  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);
> -out:
> -	if (err == NF_ACCEPT) {
> -		if (maniptype == NF_NAT_MANIP_SRC)
> -			tc_skb_cb(skb)->post_ct_snat = 1;
> -		if (maniptype == NF_NAT_MANIP_DST)
> -			tc_skb_cb(skb)->post_ct_dnat = 1;
> -	}
> -	return err;
> -}
> -#endif /* CONFIG_NF_NAT */
> -
>  static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
>  {
>  #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
> @@ -986,52 +902,22 @@ static int tcf_ct_act_nat(struct sk_buff *skb,
>  			  bool commit)
>  {
>  #if IS_ENABLED(CONFIG_NF_NAT)
> -	int err;
> -	enum nf_nat_manip_type maniptype;
> +	int err, action = 0;
>  
>  	if (!(ct_action & TCA_CT_ACT_NAT))
>  		return NF_ACCEPT;
> +	if (ct_action & TCA_CT_ACT_NAT_SRC)
> +		action |= (1 << NF_NAT_MANIP_SRC);
> +	if (ct_action & TCA_CT_ACT_NAT_DST)
> +		action |= (1 << NF_NAT_MANIP_DST);
>  
> -	/* Add NAT extension if not confirmed yet. */
> -	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
> -		return NF_ACCEPT;   /* 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 & TCA_CT_ACT_NAT_SRC) {
> -		maniptype = NF_NAT_MANIP_SRC;
> -	} else if (ct_action & TCA_CT_ACT_NAT_DST) {
> -		maniptype = NF_NAT_MANIP_DST;
> -	} else {
> -		return NF_ACCEPT;
> -	}
> +	err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
> +
> +	if (action & (1 << NF_NAT_MANIP_SRC))
> +		tc_skb_cb(skb)->post_ct_snat = 1;
> +	if (action & (1 << NF_NAT_MANIP_DST))
> +		tc_skb_cb(skb)->post_ct_dnat = 1;
>  
> -	err = ct_nat_execute(skb, ct, ctinfo, 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 = ct_nat_execute(skb, ct, ctinfo, range,
> -					     maniptype);
> -		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
> -			err = ct_nat_execute(skb, ct, ctinfo, NULL,
> -					     NF_NAT_MANIP_SRC);
> -		}
> -	}
>  	return err;
>  #else
>  	return NF_ACCEPT;
> -- 
> 2.31.1
>
Marcelo Ricardo Leitner Nov. 23, 2022, 3:13 p.m. UTC | #2
On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > +		maniptype = NF_NAT_MANIP_SRC;
> > +	} else if (ct_action & (1 << 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);
> > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > index cc643a556ea1..d03c75165663 100644
> > --- a/net/openvswitch/conntrack.c
> > +++ b/net/openvswitch/conntrack.c
> > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> >  	}
> >  }
> >  
> > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > -			      enum ip_conntrack_info ctinfo,
> > -			      const struct nf_nat_range2 *range,
> > -			      enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > -{
> > -	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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > -		    skb->protocol == 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) &&
> > -			   skb->protocol == 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);
> > -out:
> > -	/* Update the flow key if NAT successful. */
> > -	if (err == NF_ACCEPT)
> > -		ovs_nat_update_key(key, skb, maniptype);
> > -
> > -	return err;
> > -}
> > -
> >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> >  		      const struct ovs_conntrack_info *info,
> >  		      struct sk_buff *skb, struct nf_conn *ct,
> >  		      enum ip_conntrack_info ctinfo)
> >  {
> > -	enum nf_nat_manip_type maniptype;
> > -	int err;
> > +	int err, action = 0;
> >  
> >  	if (!(info->nat & OVS_CT_NAT))
> >  		return NF_ACCEPT;
> > +	if (info->nat & OVS_CT_SRC_NAT)
> > +		action |= (1 << NF_NAT_MANIP_SRC);
> > +	if (info->nat & OVS_CT_DST_NAT)
> > +		action |= (1 << NF_NAT_MANIP_DST);
> 
> I'm wondering why this dance at this level with supporting multiple
> MANIPs while actually only one can be used at a time.
> 
> act_ct will reject an action using both:
>         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
>             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
>                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
>                 return -EOPNOTSUPP;
> 
> I couldn't find this kind of check in ovs code right now (didn't look much, I
> confess :)), but even the code here was already doing:
> 
> -	} else if (info->nat & OVS_CT_SRC_NAT) {
> -		maniptype = NF_NAT_MANIP_SRC;
> -	} else if (info->nat & OVS_CT_DST_NAT) {
> -		maniptype = NF_NAT_MANIP_DST;
> 
> And in case of tuple conflict, maniptype will be forcibly updated in
> [*] below.

Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
set both.

> 
> Anyhow, if really needed, it would be nice to use BIT(NF_NAT_MANIP_..)
> instead.

But still this.

> 
> >  
> > -	/* Add NAT extension if not confirmed yet. */
> > -	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
> > -		return NF_ACCEPT;   /* Can't NAT. */
> > +	err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit);
> >  
> > -	/* Determine NAT type.
> > -	 * Check if the NAT type can be deduced from the tracked connection.
> > -	 * Make sure new expected connections (IP_CT_RELATED) are NATted only
> > -	 * when committing.
> > -	 */
> > -	if (ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK &&
> > -	    (ctinfo != IP_CT_RELATED || info->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 (info->nat & OVS_CT_SRC_NAT) {
> > -		maniptype = NF_NAT_MANIP_SRC;
> > -	} else if (info->nat & OVS_CT_DST_NAT) {
> > -		maniptype = NF_NAT_MANIP_DST;
> > -	} else {
> > -		return NF_ACCEPT; /* Connection is not NATed. */
> > -	}
> > -	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key);
> > -
> > -	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 = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
> > -						 maniptype, key);
> > -		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
> > -			err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
> > -						 NF_NAT_MANIP_SRC, key);
> > -		}
> > -	}
> > +	if (action & (1 << NF_NAT_MANIP_SRC))
> > +		ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC);
> > +	if (action & (1 << NF_NAT_MANIP_DST))
> > +		ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST);
> >  
> >  	return err;
> >  }
> > diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
> > index c7782c9a6ab6..0c410220239f 100644
> > --- a/net/sched/act_ct.c
> > +++ b/net/sched/act_ct.c
> > @@ -863,90 +863,6 @@ static void tcf_ct_params_free_rcu(struct rcu_head *head)
> >  	tcf_ct_params_free(params);
> >  }
> >  
> > -#if IS_ENABLED(CONFIG_NF_NAT)
> > -/* 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 ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > -			  enum ip_conntrack_info ctinfo,
> > -			  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);
> > -out:
> > -	if (err == NF_ACCEPT) {
> > -		if (maniptype == NF_NAT_MANIP_SRC)
> > -			tc_skb_cb(skb)->post_ct_snat = 1;
> > -		if (maniptype == NF_NAT_MANIP_DST)
> > -			tc_skb_cb(skb)->post_ct_dnat = 1;
> > -	}
> > -	return err;
> > -}
> > -#endif /* CONFIG_NF_NAT */
> > -
> >  static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
> >  {
> >  #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
> > @@ -986,52 +902,22 @@ static int tcf_ct_act_nat(struct sk_buff *skb,
> >  			  bool commit)
> >  {
> >  #if IS_ENABLED(CONFIG_NF_NAT)
> > -	int err;
> > -	enum nf_nat_manip_type maniptype;
> > +	int err, action = 0;
> >  
> >  	if (!(ct_action & TCA_CT_ACT_NAT))
> >  		return NF_ACCEPT;
> > +	if (ct_action & TCA_CT_ACT_NAT_SRC)
> > +		action |= (1 << NF_NAT_MANIP_SRC);
> > +	if (ct_action & TCA_CT_ACT_NAT_DST)
> > +		action |= (1 << NF_NAT_MANIP_DST);
> >  
> > -	/* Add NAT extension if not confirmed yet. */
> > -	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
> > -		return NF_ACCEPT;   /* 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 & TCA_CT_ACT_NAT_SRC) {
> > -		maniptype = NF_NAT_MANIP_SRC;
> > -	} else if (ct_action & TCA_CT_ACT_NAT_DST) {
> > -		maniptype = NF_NAT_MANIP_DST;
> > -	} else {
> > -		return NF_ACCEPT;
> > -	}
> > +	err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
> > +
> > +	if (action & (1 << NF_NAT_MANIP_SRC))
> > +		tc_skb_cb(skb)->post_ct_snat = 1;
> > +	if (action & (1 << NF_NAT_MANIP_DST))
> > +		tc_skb_cb(skb)->post_ct_dnat = 1;
> >  
> > -	err = ct_nat_execute(skb, ct, ctinfo, 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 = ct_nat_execute(skb, ct, ctinfo, range,
> > -					     maniptype);
> > -		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
> > -			err = ct_nat_execute(skb, ct, ctinfo, NULL,
> > -					     NF_NAT_MANIP_SRC);
> > -		}
> > -	}
> >  	return err;
> >  #else
> >  	return NF_ACCEPT;
> > -- 
> > 2.31.1
> > 
> _______________________________________________
> dev mailing list
> dev@openvswitch.org
> https://mail.openvswitch.org/mailman/listinfo/ovs-dev
>
Xin Long Nov. 23, 2022, 5:31 p.m. UTC | #3
On Wed, Nov 23, 2022 at 10:13 AM Marcelo Ricardo Leitner
<marcelo.leitner@gmail.com> wrote:
>
> On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> > On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > > +           maniptype = NF_NAT_MANIP_SRC;
> > > +   } else if (ct_action & (1 << 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);
> > > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > > index cc643a556ea1..d03c75165663 100644
> > > --- a/net/openvswitch/conntrack.c
> > > +++ b/net/openvswitch/conntrack.c
> > > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> > >     }
> > >  }
> > >
> > > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > -                         enum ip_conntrack_info ctinfo,
> > > -                         const struct nf_nat_range2 *range,
> > > -                         enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > > -{
> > > -   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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > > -               skb->protocol == 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) &&
> > > -                      skb->protocol == 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);
> > > -out:
> > > -   /* Update the flow key if NAT successful. */
> > > -   if (err == NF_ACCEPT)
> > > -           ovs_nat_update_key(key, skb, maniptype);
> > > -
> > > -   return err;
> > > -}
> > > -
> > >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> > >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> > >                   const struct ovs_conntrack_info *info,
> > >                   struct sk_buff *skb, struct nf_conn *ct,
> > >                   enum ip_conntrack_info ctinfo)
> > >  {
> > > -   enum nf_nat_manip_type maniptype;
> > > -   int err;
> > > +   int err, action = 0;
> > >
> > >     if (!(info->nat & OVS_CT_NAT))
> > >             return NF_ACCEPT;
> > > +   if (info->nat & OVS_CT_SRC_NAT)
> > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > +   if (info->nat & OVS_CT_DST_NAT)
> > > +           action |= (1 << NF_NAT_MANIP_DST);
> >
> > I'm wondering why this dance at this level with supporting multiple
> > MANIPs while actually only one can be used at a time.
> >
> > act_ct will reject an action using both:
> >         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
> >             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
> >                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
> >                 return -EOPNOTSUPP;
> >
> > I couldn't find this kind of check in ovs code right now (didn't look much, I
> > confess :)), but even the code here was already doing:
> >
> > -     } else if (info->nat & OVS_CT_SRC_NAT) {
> > -             maniptype = NF_NAT_MANIP_SRC;
> > -     } else if (info->nat & OVS_CT_DST_NAT) {
> > -             maniptype = NF_NAT_MANIP_DST;
> >
> > And in case of tuple conflict, maniptype will be forcibly updated in
> > [*] below.
>
> Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
> set both.
Right.
BTW. The tuple conflict processing actually has provided the
code to do full nat (snat and dnat at the same time), which I
think is more efficient than doing full nat in two zones. All
we have to do is adjust a few lines of code for that.

>
> >
> > Anyhow, if really needed, it would be nice to use BIT(NF_NAT_MANIP_..)
> > instead.
BIT() looks a good one, will use it.
Thanks.

>
> But still this.
>
> >
> > >
> > > -   /* Add NAT extension if not confirmed yet. */
> > > -   if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
> > > -           return NF_ACCEPT;   /* Can't NAT. */
> > > +   err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit);
> > >
> > > -   /* Determine NAT type.
> > > -    * Check if the NAT type can be deduced from the tracked connection.
> > > -    * Make sure new expected connections (IP_CT_RELATED) are NATted only
> > > -    * when committing.
> > > -    */
> > > -   if (ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK &&
> > > -       (ctinfo != IP_CT_RELATED || info->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 (info->nat & OVS_CT_SRC_NAT) {
> > > -           maniptype = NF_NAT_MANIP_SRC;
> > > -   } else if (info->nat & OVS_CT_DST_NAT) {
> > > -           maniptype = NF_NAT_MANIP_DST;
> > > -   } else {
> > > -           return NF_ACCEPT; /* Connection is not NATed. */
> > > -   }
> > > -   err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key);
> > > -
> > > -   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 = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
> > > -                                            maniptype, key);
> > > -           } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
> > > -                   err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
> > > -                                            NF_NAT_MANIP_SRC, key);
> > > -           }
> > > -   }
> > > +   if (action & (1 << NF_NAT_MANIP_SRC))
> > > +           ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC);
> > > +   if (action & (1 << NF_NAT_MANIP_DST))
> > > +           ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST);
> > >
> > >     return err;
> > >  }
> > > diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
> > > index c7782c9a6ab6..0c410220239f 100644
> > > --- a/net/sched/act_ct.c
> > > +++ b/net/sched/act_ct.c
> > > @@ -863,90 +863,6 @@ static void tcf_ct_params_free_rcu(struct rcu_head *head)
> > >     tcf_ct_params_free(params);
> > >  }
> > >
> > > -#if IS_ENABLED(CONFIG_NF_NAT)
> > > -/* 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 ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > -                     enum ip_conntrack_info ctinfo,
> > > -                     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);
> > > -out:
> > > -   if (err == NF_ACCEPT) {
> > > -           if (maniptype == NF_NAT_MANIP_SRC)
> > > -                   tc_skb_cb(skb)->post_ct_snat = 1;
> > > -           if (maniptype == NF_NAT_MANIP_DST)
> > > -                   tc_skb_cb(skb)->post_ct_dnat = 1;
> > > -   }
> > > -   return err;
> > > -}
> > > -#endif /* CONFIG_NF_NAT */
> > > -
> > >  static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
> > >  {
> > >  #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
> > > @@ -986,52 +902,22 @@ static int tcf_ct_act_nat(struct sk_buff *skb,
> > >                       bool commit)
> > >  {
> > >  #if IS_ENABLED(CONFIG_NF_NAT)
> > > -   int err;
> > > -   enum nf_nat_manip_type maniptype;
> > > +   int err, action = 0;
> > >
> > >     if (!(ct_action & TCA_CT_ACT_NAT))
> > >             return NF_ACCEPT;
> > > +   if (ct_action & TCA_CT_ACT_NAT_SRC)
> > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > +   if (ct_action & TCA_CT_ACT_NAT_DST)
> > > +           action |= (1 << NF_NAT_MANIP_DST);
> > >
> > > -   /* Add NAT extension if not confirmed yet. */
> > > -   if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
> > > -           return NF_ACCEPT;   /* 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 & TCA_CT_ACT_NAT_SRC) {
> > > -           maniptype = NF_NAT_MANIP_SRC;
> > > -   } else if (ct_action & TCA_CT_ACT_NAT_DST) {
> > > -           maniptype = NF_NAT_MANIP_DST;
> > > -   } else {
> > > -           return NF_ACCEPT;
> > > -   }
> > > +   err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
> > > +
> > > +   if (action & (1 << NF_NAT_MANIP_SRC))
> > > +           tc_skb_cb(skb)->post_ct_snat = 1;
> > > +   if (action & (1 << NF_NAT_MANIP_DST))
> > > +           tc_skb_cb(skb)->post_ct_dnat = 1;
> > >
> > > -   err = ct_nat_execute(skb, ct, ctinfo, 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 = ct_nat_execute(skb, ct, ctinfo, range,
> > > -                                        maniptype);
> > > -           } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
> > > -                   err = ct_nat_execute(skb, ct, ctinfo, NULL,
> > > -                                        NF_NAT_MANIP_SRC);
> > > -           }
> > > -   }
> > >     return err;
> > >  #else
> > >     return NF_ACCEPT;
> > > --
> > > 2.31.1
> > >
> > _______________________________________________
> > dev mailing list
> > dev@openvswitch.org
> > https://mail.openvswitch.org/mailman/listinfo/ovs-dev
> >
Marcelo Ricardo Leitner Nov. 23, 2022, 6:48 p.m. UTC | #4
On Wed, Nov 23, 2022 at 12:31:38PM -0500, Xin Long wrote:
> On Wed, Nov 23, 2022 at 10:13 AM Marcelo Ricardo Leitner
> <marcelo.leitner@gmail.com> wrote:
> >
> > On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> > > On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > > > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > > > +           maniptype = NF_NAT_MANIP_SRC;
> > > > +   } else if (ct_action & (1 << 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);
> > > > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > > > index cc643a556ea1..d03c75165663 100644
> > > > --- a/net/openvswitch/conntrack.c
> > > > +++ b/net/openvswitch/conntrack.c
> > > > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> > > >     }
> > > >  }
> > > >
> > > > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > > -                         enum ip_conntrack_info ctinfo,
> > > > -                         const struct nf_nat_range2 *range,
> > > > -                         enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > > > -{
> > > > -   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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > > > -               skb->protocol == 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) &&
> > > > -                      skb->protocol == 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);
> > > > -out:
> > > > -   /* Update the flow key if NAT successful. */
> > > > -   if (err == NF_ACCEPT)
> > > > -           ovs_nat_update_key(key, skb, maniptype);
> > > > -
> > > > -   return err;
> > > > -}
> > > > -
> > > >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> > > >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> > > >                   const struct ovs_conntrack_info *info,
> > > >                   struct sk_buff *skb, struct nf_conn *ct,
> > > >                   enum ip_conntrack_info ctinfo)
> > > >  {
> > > > -   enum nf_nat_manip_type maniptype;
> > > > -   int err;
> > > > +   int err, action = 0;
> > > >
> > > >     if (!(info->nat & OVS_CT_NAT))
> > > >             return NF_ACCEPT;
> > > > +   if (info->nat & OVS_CT_SRC_NAT)
> > > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > > +   if (info->nat & OVS_CT_DST_NAT)
> > > > +           action |= (1 << NF_NAT_MANIP_DST);
> > >
> > > I'm wondering why this dance at this level with supporting multiple
> > > MANIPs while actually only one can be used at a time.
> > >
> > > act_ct will reject an action using both:
> > >         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
> > >             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
> > >                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
> > >                 return -EOPNOTSUPP;
> > >
> > > I couldn't find this kind of check in ovs code right now (didn't look much, I
> > > confess :)), but even the code here was already doing:
> > >
> > > -     } else if (info->nat & OVS_CT_SRC_NAT) {
> > > -             maniptype = NF_NAT_MANIP_SRC;
> > > -     } else if (info->nat & OVS_CT_DST_NAT) {
> > > -             maniptype = NF_NAT_MANIP_DST;
> > >
> > > And in case of tuple conflict, maniptype will be forcibly updated in
> > > [*] below.
> >
> > Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
> > set both.
> Right.
> BTW. The tuple conflict processing actually has provided the
> code to do full nat (snat and dnat at the same time), which I
> think is more efficient than doing full nat in two zones. All
> we have to do is adjust a few lines of code for that.

In this part, yes. But it needs some surgery all around for full
support. The code in ovs kernel for using only one type starts here:

static int parse_nat(const struct nlattr *attr,
                     struct ovs_conntrack_info *info, bool log)
{
...
                switch (type) {
                case OVS_NAT_ATTR_SRC:
                case OVS_NAT_ATTR_DST:
                        if (info->nat) {
                                OVS_NLERR(log, "Only one type of NAT may be specified");
                                return -ERANGE;
                        }
...
}

So vswitchd also doesn't support it. And then tc, iproute and drivers
that offload it as well. Not sure if it has impacts on openflow too.
Marcelo Ricardo Leitner Nov. 23, 2022, 6:52 p.m. UTC | #5
On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> --- a/net/netfilter/Makefile
> +++ b/net/netfilter/Makefile
> @@ -52,7 +52,7 @@ obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
>  obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
>  obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o
>  
> -nf_nat-y	:= nf_nat_core.o nf_nat_proto.o nf_nat_helper.o
> +nf_nat-y	:= nf_nat_core.o nf_nat_proto.o nf_nat_helper.o nf_nat_ovs.o

Considering that the code in nf_nat_ovs is only used if ovs or act_ct
are enabled, shouldn't it be using an invisible knob here that gets
automatically selected by them? Pablo?

I think this is my last comment on this series. The rest LGTM.

>  
>  obj-$(CONFIG_NF_LOG_SYSLOG) += nf_log_syslog.o
>
Xin Long Nov. 23, 2022, 6:54 p.m. UTC | #6
On Wed, Nov 23, 2022 at 1:48 PM Marcelo Ricardo Leitner
<marcelo.leitner@gmail.com> wrote:
>
> On Wed, Nov 23, 2022 at 12:31:38PM -0500, Xin Long wrote:
> > On Wed, Nov 23, 2022 at 10:13 AM Marcelo Ricardo Leitner
> > <marcelo.leitner@gmail.com> wrote:
> > >
> > > On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> > > > On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > > > > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > > > > +           maniptype = NF_NAT_MANIP_SRC;
> > > > > +   } else if (ct_action & (1 << 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);
> > > > > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > > > > index cc643a556ea1..d03c75165663 100644
> > > > > --- a/net/openvswitch/conntrack.c
> > > > > +++ b/net/openvswitch/conntrack.c
> > > > > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> > > > >     }
> > > > >  }
> > > > >
> > > > > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > > > -                         enum ip_conntrack_info ctinfo,
> > > > > -                         const struct nf_nat_range2 *range,
> > > > > -                         enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > > > > -{
> > > > > -   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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > > > > -               skb->protocol == 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) &&
> > > > > -                      skb->protocol == 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);
> > > > > -out:
> > > > > -   /* Update the flow key if NAT successful. */
> > > > > -   if (err == NF_ACCEPT)
> > > > > -           ovs_nat_update_key(key, skb, maniptype);
> > > > > -
> > > > > -   return err;
> > > > > -}
> > > > > -
> > > > >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> > > > >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> > > > >                   const struct ovs_conntrack_info *info,
> > > > >                   struct sk_buff *skb, struct nf_conn *ct,
> > > > >                   enum ip_conntrack_info ctinfo)
> > > > >  {
> > > > > -   enum nf_nat_manip_type maniptype;
> > > > > -   int err;
> > > > > +   int err, action = 0;
> > > > >
> > > > >     if (!(info->nat & OVS_CT_NAT))
> > > > >             return NF_ACCEPT;
> > > > > +   if (info->nat & OVS_CT_SRC_NAT)
> > > > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > > > +   if (info->nat & OVS_CT_DST_NAT)
> > > > > +           action |= (1 << NF_NAT_MANIP_DST);
> > > >
> > > > I'm wondering why this dance at this level with supporting multiple
> > > > MANIPs while actually only one can be used at a time.
> > > >
> > > > act_ct will reject an action using both:
> > > >         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
> > > >             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
> > > >                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
> > > >                 return -EOPNOTSUPP;
> > > >
> > > > I couldn't find this kind of check in ovs code right now (didn't look much, I
> > > > confess :)), but even the code here was already doing:
> > > >
> > > > -     } else if (info->nat & OVS_CT_SRC_NAT) {
> > > > -             maniptype = NF_NAT_MANIP_SRC;
> > > > -     } else if (info->nat & OVS_CT_DST_NAT) {
> > > > -             maniptype = NF_NAT_MANIP_DST;
> > > >
> > > > And in case of tuple conflict, maniptype will be forcibly updated in
> > > > [*] below.
> > >
> > > Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
> > > set both.
> > Right.
> > BTW. The tuple conflict processing actually has provided the
> > code to do full nat (snat and dnat at the same time), which I
> > think is more efficient than doing full nat in two zones. All
> > we have to do is adjust a few lines of code for that.
>
> In this part, yes. But it needs some surgery all around for full
> support. The code in ovs kernel for using only one type starts here:
>
> static int parse_nat(const struct nlattr *attr,
>                      struct ovs_conntrack_info *info, bool log)
> {
> ...
>                 switch (type) {
>                 case OVS_NAT_ATTR_SRC:
>                 case OVS_NAT_ATTR_DST:
>                         if (info->nat) {
>                                 OVS_NLERR(log, "Only one type of NAT may be specified");
>                                 return -ERANGE;
>                         }
> ...
> }
>
> So vswitchd also doesn't support it. And then tc, iproute and drivers
> that offload it as well. Not sure if it has impacts on openflow too.
>
not in one single action, but two actions:

"table=1, in_port=veth1,tcp,tcp_dst=2121,ct_state=+trk+new
actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1),
alg=ftp),veth2"

as long as it allows the 1st one doesn't commit, which is a simple
check in parse_nat().
I tested it, TC already supports it. I'm not sure about drivers, but I
think it should be, as with two actions.
Marcelo Ricardo Leitner Nov. 23, 2022, 7:17 p.m. UTC | #7
On Wed, Nov 23, 2022 at 01:54:41PM -0500, Xin Long wrote:
> On Wed, Nov 23, 2022 at 1:48 PM Marcelo Ricardo Leitner
> <marcelo.leitner@gmail.com> wrote:
> >
> > On Wed, Nov 23, 2022 at 12:31:38PM -0500, Xin Long wrote:
> > > On Wed, Nov 23, 2022 at 10:13 AM Marcelo Ricardo Leitner
> > > <marcelo.leitner@gmail.com> wrote:
> > > >
> > > > On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> > > > > On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > > > > > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > > > > > +           maniptype = NF_NAT_MANIP_SRC;
> > > > > > +   } else if (ct_action & (1 << 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);
> > > > > > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > > > > > index cc643a556ea1..d03c75165663 100644
> > > > > > --- a/net/openvswitch/conntrack.c
> > > > > > +++ b/net/openvswitch/conntrack.c
> > > > > > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> > > > > >     }
> > > > > >  }
> > > > > >
> > > > > > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > > > > -                         enum ip_conntrack_info ctinfo,
> > > > > > -                         const struct nf_nat_range2 *range,
> > > > > > -                         enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > > > > > -{
> > > > > > -   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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > > > > > -               skb->protocol == 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) &&
> > > > > > -                      skb->protocol == 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);
> > > > > > -out:
> > > > > > -   /* Update the flow key if NAT successful. */
> > > > > > -   if (err == NF_ACCEPT)
> > > > > > -           ovs_nat_update_key(key, skb, maniptype);
> > > > > > -
> > > > > > -   return err;
> > > > > > -}
> > > > > > -
> > > > > >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> > > > > >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> > > > > >                   const struct ovs_conntrack_info *info,
> > > > > >                   struct sk_buff *skb, struct nf_conn *ct,
> > > > > >                   enum ip_conntrack_info ctinfo)
> > > > > >  {
> > > > > > -   enum nf_nat_manip_type maniptype;
> > > > > > -   int err;
> > > > > > +   int err, action = 0;
> > > > > >
> > > > > >     if (!(info->nat & OVS_CT_NAT))
> > > > > >             return NF_ACCEPT;
> > > > > > +   if (info->nat & OVS_CT_SRC_NAT)
> > > > > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > > > > +   if (info->nat & OVS_CT_DST_NAT)
> > > > > > +           action |= (1 << NF_NAT_MANIP_DST);
> > > > >
> > > > > I'm wondering why this dance at this level with supporting multiple
> > > > > MANIPs while actually only one can be used at a time.
> > > > >
> > > > > act_ct will reject an action using both:
> > > > >         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
> > > > >             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
> > > > >                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
> > > > >                 return -EOPNOTSUPP;
> > > > >
> > > > > I couldn't find this kind of check in ovs code right now (didn't look much, I
> > > > > confess :)), but even the code here was already doing:
> > > > >
> > > > > -     } else if (info->nat & OVS_CT_SRC_NAT) {
> > > > > -             maniptype = NF_NAT_MANIP_SRC;
> > > > > -     } else if (info->nat & OVS_CT_DST_NAT) {
> > > > > -             maniptype = NF_NAT_MANIP_DST;
> > > > >
> > > > > And in case of tuple conflict, maniptype will be forcibly updated in
> > > > > [*] below.
> > > >
> > > > Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
> > > > set both.
> > > Right.
> > > BTW. The tuple conflict processing actually has provided the
> > > code to do full nat (snat and dnat at the same time), which I
> > > think is more efficient than doing full nat in two zones. All
> > > we have to do is adjust a few lines of code for that.
> >
> > In this part, yes. But it needs some surgery all around for full
> > support. The code in ovs kernel for using only one type starts here:
> >
> > static int parse_nat(const struct nlattr *attr,
> >                      struct ovs_conntrack_info *info, bool log)
> > {
> > ...
> >                 switch (type) {
> >                 case OVS_NAT_ATTR_SRC:
> >                 case OVS_NAT_ATTR_DST:
> >                         if (info->nat) {
> >                                 OVS_NLERR(log, "Only one type of NAT may be specified");
> >                                 return -ERANGE;
> >                         }
> > ...
> > }
> >
> > So vswitchd also doesn't support it. And then tc, iproute and drivers
> > that offload it as well. Not sure if it has impacts on openflow too.
> >
> not in one single action, but two actions:

Oh.

> 
> "table=1, in_port=veth1,tcp,tcp_dst=2121,ct_state=+trk+new
> actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1),
> alg=ftp),veth2"
> 
> as long as it allows the 1st one doesn't commit, which is a simple
> check in parse_nat().
> I tested it, TC already supports it. I'm not sure about drivers, but I

There's an outstanding issue with act_ct that it may reuse an old
CT cache. Fixing it could (I'm not sure) impact this use case:

https://bugzilla.redhat.com/show_bug.cgi?id=2099220
same issue in ovs was fixed in
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2061ecfdf2350994e5b61c43e50e98a7a70e95ee

(please don't ask me who would NAT and then overwrite IP addresses and
then NAT it again :D)

> think it should be, as with two actions.

mlx5 at least currently doesn't support it. Good that tc already
supports it, then. Maybe drivers can get up to speed later on.
Xin Long Nov. 23, 2022, 7:55 p.m. UTC | #8
On Wed, Nov 23, 2022 at 2:17 PM Marcelo Ricardo Leitner
<marcelo.leitner@gmail.com> wrote:
>
> On Wed, Nov 23, 2022 at 01:54:41PM -0500, Xin Long wrote:
> > On Wed, Nov 23, 2022 at 1:48 PM Marcelo Ricardo Leitner
> > <marcelo.leitner@gmail.com> wrote:
> > >
> > > On Wed, Nov 23, 2022 at 12:31:38PM -0500, Xin Long wrote:
> > > > On Wed, Nov 23, 2022 at 10:13 AM Marcelo Ricardo Leitner
> > > > <marcelo.leitner@gmail.com> wrote:
> > > > >
> > > > > On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> > > > > > On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > > > > > > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > > > > > > +           maniptype = NF_NAT_MANIP_SRC;
> > > > > > > +   } else if (ct_action & (1 << 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);
> > > > > > > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > > > > > > index cc643a556ea1..d03c75165663 100644
> > > > > > > --- a/net/openvswitch/conntrack.c
> > > > > > > +++ b/net/openvswitch/conntrack.c
> > > > > > > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> > > > > > >     }
> > > > > > >  }
> > > > > > >
> > > > > > > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > > > > > -                         enum ip_conntrack_info ctinfo,
> > > > > > > -                         const struct nf_nat_range2 *range,
> > > > > > > -                         enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > > > > > > -{
> > > > > > > -   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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > > > > > > -               skb->protocol == 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) &&
> > > > > > > -                      skb->protocol == 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);
> > > > > > > -out:
> > > > > > > -   /* Update the flow key if NAT successful. */
> > > > > > > -   if (err == NF_ACCEPT)
> > > > > > > -           ovs_nat_update_key(key, skb, maniptype);
> > > > > > > -
> > > > > > > -   return err;
> > > > > > > -}
> > > > > > > -
> > > > > > >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> > > > > > >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> > > > > > >                   const struct ovs_conntrack_info *info,
> > > > > > >                   struct sk_buff *skb, struct nf_conn *ct,
> > > > > > >                   enum ip_conntrack_info ctinfo)
> > > > > > >  {
> > > > > > > -   enum nf_nat_manip_type maniptype;
> > > > > > > -   int err;
> > > > > > > +   int err, action = 0;
> > > > > > >
> > > > > > >     if (!(info->nat & OVS_CT_NAT))
> > > > > > >             return NF_ACCEPT;
> > > > > > > +   if (info->nat & OVS_CT_SRC_NAT)
> > > > > > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > > > > > +   if (info->nat & OVS_CT_DST_NAT)
> > > > > > > +           action |= (1 << NF_NAT_MANIP_DST);
> > > > > >
> > > > > > I'm wondering why this dance at this level with supporting multiple
> > > > > > MANIPs while actually only one can be used at a time.
> > > > > >
> > > > > > act_ct will reject an action using both:
> > > > > >         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
> > > > > >             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
> > > > > >                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
> > > > > >                 return -EOPNOTSUPP;
> > > > > >
> > > > > > I couldn't find this kind of check in ovs code right now (didn't look much, I
> > > > > > confess :)), but even the code here was already doing:
> > > > > >
> > > > > > -     } else if (info->nat & OVS_CT_SRC_NAT) {
> > > > > > -             maniptype = NF_NAT_MANIP_SRC;
> > > > > > -     } else if (info->nat & OVS_CT_DST_NAT) {
> > > > > > -             maniptype = NF_NAT_MANIP_DST;
> > > > > >
> > > > > > And in case of tuple conflict, maniptype will be forcibly updated in
> > > > > > [*] below.
> > > > >
> > > > > Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
> > > > > set both.
> > > > Right.
> > > > BTW. The tuple conflict processing actually has provided the
> > > > code to do full nat (snat and dnat at the same time), which I
> > > > think is more efficient than doing full nat in two zones. All
> > > > we have to do is adjust a few lines of code for that.
> > >
> > > In this part, yes. But it needs some surgery all around for full
> > > support. The code in ovs kernel for using only one type starts here:
> > >
> > > static int parse_nat(const struct nlattr *attr,
> > >                      struct ovs_conntrack_info *info, bool log)
> > > {
> > > ...
> > >                 switch (type) {
> > >                 case OVS_NAT_ATTR_SRC:
> > >                 case OVS_NAT_ATTR_DST:
> > >                         if (info->nat) {
> > >                                 OVS_NLERR(log, "Only one type of NAT may be specified");
> > >                                 return -ERANGE;
> > >                         }
> > > ...
> > > }
> > >
> > > So vswitchd also doesn't support it. And then tc, iproute and drivers
> > > that offload it as well. Not sure if it has impacts on openflow too.
> > >
> > not in one single action, but two actions:
>
> Oh.
>
> >
> > "table=1, in_port=veth1,tcp,tcp_dst=2121,ct_state=+trk+new
> > actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1),
> > alg=ftp),veth2"
> >
> > as long as it allows the 1st one doesn't commit, which is a simple
> > check in parse_nat().
> > I tested it, TC already supports it. I'm not sure about drivers, but I
>
> There's an outstanding issue with act_ct that it may reuse an old
> CT cache. Fixing it could (I'm not sure) impact this use case:
>
> https://bugzilla.redhat.com/show_bug.cgi?id=2099220
> same issue in ovs was fixed in
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2061ecfdf2350994e5b61c43e50e98a7a70e95ee
>
> (please don't ask me who would NAT and then overwrite IP addresses and
> then NAT it again :D)
I thought only traditional NAT would change IP, I'm too naive.

nftables names this as "stateless NAT."
With two CTs in the same zone for full nat is more close to the
netfilter's NAT processing (the same CT goes from prerouting to
postrouting).
Now I'm wondering how nftables handles the stateful NAT and stateless
NAT at the same time.

>
> > think it should be, as with two actions.
>
> mlx5 at least currently doesn't support it. Good that tc already
> supports it, then. Maybe drivers can get up to speed later on.
So because mlx5 currently only supports one ct action in one tc rule
or something?
Marcelo Ricardo Leitner Nov. 23, 2022, 9:21 p.m. UTC | #9
On Wed, Nov 23, 2022 at 02:55:05PM -0500, Xin Long wrote:
> On Wed, Nov 23, 2022 at 2:17 PM Marcelo Ricardo Leitner
> <marcelo.leitner@gmail.com> wrote:
> >
> > On Wed, Nov 23, 2022 at 01:54:41PM -0500, Xin Long wrote:
> > > On Wed, Nov 23, 2022 at 1:48 PM Marcelo Ricardo Leitner
> > > <marcelo.leitner@gmail.com> wrote:
> > > >
> > > > On Wed, Nov 23, 2022 at 12:31:38PM -0500, Xin Long wrote:
> > > > > On Wed, Nov 23, 2022 at 10:13 AM Marcelo Ricardo Leitner
> > > > > <marcelo.leitner@gmail.com> wrote:
> > > > > >
> > > > > > On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> > > > > > > On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > > > > > > > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > > > > > > > +           maniptype = NF_NAT_MANIP_SRC;
> > > > > > > > +   } else if (ct_action & (1 << 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);
> > > > > > > > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > > > > > > > index cc643a556ea1..d03c75165663 100644
> > > > > > > > --- a/net/openvswitch/conntrack.c
> > > > > > > > +++ b/net/openvswitch/conntrack.c
> > > > > > > > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> > > > > > > >     }
> > > > > > > >  }
> > > > > > > >
> > > > > > > > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > > > > > > -                         enum ip_conntrack_info ctinfo,
> > > > > > > > -                         const struct nf_nat_range2 *range,
> > > > > > > > -                         enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > > > > > > > -{
> > > > > > > > -   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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > > > > > > > -               skb->protocol == 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) &&
> > > > > > > > -                      skb->protocol == 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);
> > > > > > > > -out:
> > > > > > > > -   /* Update the flow key if NAT successful. */
> > > > > > > > -   if (err == NF_ACCEPT)
> > > > > > > > -           ovs_nat_update_key(key, skb, maniptype);
> > > > > > > > -
> > > > > > > > -   return err;
> > > > > > > > -}
> > > > > > > > -
> > > > > > > >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> > > > > > > >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> > > > > > > >                   const struct ovs_conntrack_info *info,
> > > > > > > >                   struct sk_buff *skb, struct nf_conn *ct,
> > > > > > > >                   enum ip_conntrack_info ctinfo)
> > > > > > > >  {
> > > > > > > > -   enum nf_nat_manip_type maniptype;
> > > > > > > > -   int err;
> > > > > > > > +   int err, action = 0;
> > > > > > > >
> > > > > > > >     if (!(info->nat & OVS_CT_NAT))
> > > > > > > >             return NF_ACCEPT;
> > > > > > > > +   if (info->nat & OVS_CT_SRC_NAT)
> > > > > > > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > > > > > > +   if (info->nat & OVS_CT_DST_NAT)
> > > > > > > > +           action |= (1 << NF_NAT_MANIP_DST);
> > > > > > >
> > > > > > > I'm wondering why this dance at this level with supporting multiple
> > > > > > > MANIPs while actually only one can be used at a time.
> > > > > > >
> > > > > > > act_ct will reject an action using both:
> > > > > > >         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
> > > > > > >             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
> > > > > > >                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
> > > > > > >                 return -EOPNOTSUPP;
> > > > > > >
> > > > > > > I couldn't find this kind of check in ovs code right now (didn't look much, I
> > > > > > > confess :)), but even the code here was already doing:
> > > > > > >
> > > > > > > -     } else if (info->nat & OVS_CT_SRC_NAT) {
> > > > > > > -             maniptype = NF_NAT_MANIP_SRC;
> > > > > > > -     } else if (info->nat & OVS_CT_DST_NAT) {
> > > > > > > -             maniptype = NF_NAT_MANIP_DST;
> > > > > > >
> > > > > > > And in case of tuple conflict, maniptype will be forcibly updated in
> > > > > > > [*] below.
> > > > > >
> > > > > > Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
> > > > > > set both.
> > > > > Right.
> > > > > BTW. The tuple conflict processing actually has provided the
> > > > > code to do full nat (snat and dnat at the same time), which I
> > > > > think is more efficient than doing full nat in two zones. All
> > > > > we have to do is adjust a few lines of code for that.
> > > >
> > > > In this part, yes. But it needs some surgery all around for full
> > > > support. The code in ovs kernel for using only one type starts here:
> > > >
> > > > static int parse_nat(const struct nlattr *attr,
> > > >                      struct ovs_conntrack_info *info, bool log)
> > > > {
> > > > ...
> > > >                 switch (type) {
> > > >                 case OVS_NAT_ATTR_SRC:
> > > >                 case OVS_NAT_ATTR_DST:
> > > >                         if (info->nat) {
> > > >                                 OVS_NLERR(log, "Only one type of NAT may be specified");
> > > >                                 return -ERANGE;
> > > >                         }
> > > > ...
> > > > }
> > > >
> > > > So vswitchd also doesn't support it. And then tc, iproute and drivers
> > > > that offload it as well. Not sure if it has impacts on openflow too.
> > > >
> > > not in one single action, but two actions:
> >
> > Oh.
> >
> > >
> > > "table=1, in_port=veth1,tcp,tcp_dst=2121,ct_state=+trk+new
> > > actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1),
> > > alg=ftp),veth2"
> > >
> > > as long as it allows the 1st one doesn't commit, which is a simple
> > > check in parse_nat().
> > > I tested it, TC already supports it. I'm not sure about drivers, but I
> >
> > There's an outstanding issue with act_ct that it may reuse an old
> > CT cache. Fixing it could (I'm not sure) impact this use case:
> >
> > https://bugzilla.redhat.com/show_bug.cgi?id=2099220
> > same issue in ovs was fixed in
> > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2061ecfdf2350994e5b61c43e50e98a7a70e95ee
> >
> > (please don't ask me who would NAT and then overwrite IP addresses and
> > then NAT it again :D)
> I thought only traditional NAT would change IP, I'm too naive.
> 
> nftables names this as "stateless NAT."
> With two CTs in the same zone for full nat is more close to the
> netfilter's NAT processing (the same CT goes from prerouting to
> postrouting).
> Now I'm wondering how nftables handles the stateful NAT and stateless
> NAT at the same time.

Me too.

> 
> >
> > > think it should be, as with two actions.
> >
> > mlx5 at least currently doesn't support it. Good that tc already
> > supports it, then. Maybe drivers can get up to speed later on.
> So because mlx5 currently only supports one ct action in one tc rule
> or something?

Not sure what you meant here?
Xin Long Nov. 23, 2022, 9:34 p.m. UTC | #10
On Wed, Nov 23, 2022 at 4:21 PM Marcelo Ricardo Leitner
<marcelo.leitner@gmail.com> wrote:
>
> On Wed, Nov 23, 2022 at 02:55:05PM -0500, Xin Long wrote:
> > On Wed, Nov 23, 2022 at 2:17 PM Marcelo Ricardo Leitner
> > <marcelo.leitner@gmail.com> wrote:
> > >
> > > On Wed, Nov 23, 2022 at 01:54:41PM -0500, Xin Long wrote:
> > > > On Wed, Nov 23, 2022 at 1:48 PM Marcelo Ricardo Leitner
> > > > <marcelo.leitner@gmail.com> wrote:
> > > > >
> > > > > On Wed, Nov 23, 2022 at 12:31:38PM -0500, Xin Long wrote:
> > > > > > On Wed, Nov 23, 2022 at 10:13 AM Marcelo Ricardo Leitner
> > > > > > <marcelo.leitner@gmail.com> wrote:
> > > > > > >
> > > > > > > On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> > > > > > > > On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > > > > > > > > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > > > > > > > > +           maniptype = NF_NAT_MANIP_SRC;
> > > > > > > > > +   } else if (ct_action & (1 << 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);
> > > > > > > > > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > > > > > > > > index cc643a556ea1..d03c75165663 100644
> > > > > > > > > --- a/net/openvswitch/conntrack.c
> > > > > > > > > +++ b/net/openvswitch/conntrack.c
> > > > > > > > > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> > > > > > > > >     }
> > > > > > > > >  }
> > > > > > > > >
> > > > > > > > > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > > > > > > > -                         enum ip_conntrack_info ctinfo,
> > > > > > > > > -                         const struct nf_nat_range2 *range,
> > > > > > > > > -                         enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > > > > > > > > -{
> > > > > > > > > -   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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > > > > > > > > -               skb->protocol == 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) &&
> > > > > > > > > -                      skb->protocol == 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);
> > > > > > > > > -out:
> > > > > > > > > -   /* Update the flow key if NAT successful. */
> > > > > > > > > -   if (err == NF_ACCEPT)
> > > > > > > > > -           ovs_nat_update_key(key, skb, maniptype);
> > > > > > > > > -
> > > > > > > > > -   return err;
> > > > > > > > > -}
> > > > > > > > > -
> > > > > > > > >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> > > > > > > > >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> > > > > > > > >                   const struct ovs_conntrack_info *info,
> > > > > > > > >                   struct sk_buff *skb, struct nf_conn *ct,
> > > > > > > > >                   enum ip_conntrack_info ctinfo)
> > > > > > > > >  {
> > > > > > > > > -   enum nf_nat_manip_type maniptype;
> > > > > > > > > -   int err;
> > > > > > > > > +   int err, action = 0;
> > > > > > > > >
> > > > > > > > >     if (!(info->nat & OVS_CT_NAT))
> > > > > > > > >             return NF_ACCEPT;
> > > > > > > > > +   if (info->nat & OVS_CT_SRC_NAT)
> > > > > > > > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > > > > > > > +   if (info->nat & OVS_CT_DST_NAT)
> > > > > > > > > +           action |= (1 << NF_NAT_MANIP_DST);
> > > > > > > >
> > > > > > > > I'm wondering why this dance at this level with supporting multiple
> > > > > > > > MANIPs while actually only one can be used at a time.
> > > > > > > >
> > > > > > > > act_ct will reject an action using both:
> > > > > > > >         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
> > > > > > > >             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
> > > > > > > >                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
> > > > > > > >                 return -EOPNOTSUPP;
> > > > > > > >
> > > > > > > > I couldn't find this kind of check in ovs code right now (didn't look much, I
> > > > > > > > confess :)), but even the code here was already doing:
> > > > > > > >
> > > > > > > > -     } else if (info->nat & OVS_CT_SRC_NAT) {
> > > > > > > > -             maniptype = NF_NAT_MANIP_SRC;
> > > > > > > > -     } else if (info->nat & OVS_CT_DST_NAT) {
> > > > > > > > -             maniptype = NF_NAT_MANIP_DST;
> > > > > > > >
> > > > > > > > And in case of tuple conflict, maniptype will be forcibly updated in
> > > > > > > > [*] below.
> > > > > > >
> > > > > > > Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
> > > > > > > set both.
> > > > > > Right.
> > > > > > BTW. The tuple conflict processing actually has provided the
> > > > > > code to do full nat (snat and dnat at the same time), which I
> > > > > > think is more efficient than doing full nat in two zones. All
> > > > > > we have to do is adjust a few lines of code for that.
> > > > >
> > > > > In this part, yes. But it needs some surgery all around for full
> > > > > support. The code in ovs kernel for using only one type starts here:
> > > > >
> > > > > static int parse_nat(const struct nlattr *attr,
> > > > >                      struct ovs_conntrack_info *info, bool log)
> > > > > {
> > > > > ...
> > > > >                 switch (type) {
> > > > >                 case OVS_NAT_ATTR_SRC:
> > > > >                 case OVS_NAT_ATTR_DST:
> > > > >                         if (info->nat) {
> > > > >                                 OVS_NLERR(log, "Only one type of NAT may be specified");
> > > > >                                 return -ERANGE;
> > > > >                         }
> > > > > ...
> > > > > }
> > > > >
> > > > > So vswitchd also doesn't support it. And then tc, iproute and drivers
> > > > > that offload it as well. Not sure if it has impacts on openflow too.
> > > > >
> > > > not in one single action, but two actions:
> > >
> > > Oh.
> > >
> > > >
> > > > "table=1, in_port=veth1,tcp,tcp_dst=2121,ct_state=+trk+new
> > > > actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1),
> > > > alg=ftp),veth2"
> > > >
> > > > as long as it allows the 1st one doesn't commit, which is a simple
> > > > check in parse_nat().
> > > > I tested it, TC already supports it. I'm not sure about drivers, but I
> > >
> > > There's an outstanding issue with act_ct that it may reuse an old
> > > CT cache. Fixing it could (I'm not sure) impact this use case:
> > >
> > > https://bugzilla.redhat.com/show_bug.cgi?id=2099220
> > > same issue in ovs was fixed in
> > > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2061ecfdf2350994e5b61c43e50e98a7a70e95ee
> > >
> > > (please don't ask me who would NAT and then overwrite IP addresses and
> > > then NAT it again :D)
> > I thought only traditional NAT would change IP, I'm too naive.
> >
> > nftables names this as "stateless NAT."
> > With two CTs in the same zone for full nat is more close to the
> > netfilter's NAT processing (the same CT goes from prerouting to
> > postrouting).
> > Now I'm wondering how nftables handles the stateful NAT and stateless
> > NAT at the same time.
>
> Me too.
>
> >
> > >
> > > > think it should be, as with two actions.
> > >
> > > mlx5 at least currently doesn't support it. Good that tc already
> > > supports it, then. Maybe drivers can get up to speed later on.
> > So because mlx5 currently only supports one ct action in one tc rule
> > or something?
>
> Not sure what you meant here?
Sorry. that might be a silly question, I don't know much about TC
HW offload, and just curious why such a rule can not be offloaded
in mlx5 driver:

"actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1)),veth2"

it doesn't support any tc NAT or just does not support tc full NAT HW offload?

Thanks.
Pablo Neira Ayuso Nov. 24, 2022, 10 a.m. UTC | #11
On Wed, Nov 23, 2022 at 06:21:15PM -0300, Marcelo Ricardo Leitner wrote:
> On Wed, Nov 23, 2022 at 02:55:05PM -0500, Xin Long wrote:
> > On Wed, Nov 23, 2022 at 2:17 PM Marcelo Ricardo Leitner
> > <marcelo.leitner@gmail.com> wrote:
[...]
> > > > "table=1, in_port=veth1,tcp,tcp_dst=2121,ct_state=+trk+new
> > > > actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1),
> > > > alg=ftp),veth2"
> > > >
> > > > as long as it allows the 1st one doesn't commit, which is a simple
> > > > check in parse_nat().
> > > > I tested it, TC already supports it. I'm not sure about drivers, but I
> > >
> > > There's an outstanding issue with act_ct that it may reuse an old
> > > CT cache. Fixing it could (I'm not sure) impact this use case:
> > >
> > > https://bugzilla.redhat.com/show_bug.cgi?id=2099220
> > > same issue in ovs was fixed in
> > > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2061ecfdf2350994e5b61c43e50e98a7a70e95ee
> > >
> > > (please don't ask me who would NAT and then overwrite IP addresses and
> > > then NAT it again :D)
> > I thought only traditional NAT would change IP, I'm too naive.
> > 
> > nftables names this as "stateless NAT."
> > With two CTs in the same zone for full nat is more close to the
> > netfilter's NAT processing (the same CT goes from prerouting to
> > postrouting).
> > Now I'm wondering how nftables handles the stateful NAT and stateless
> > NAT at the same time.
> 
> Me too.

There is a 'notrack' action to skip connection tracking for the flows
where the user needs stateless NAT.
Xin Long Dec. 1, 2022, 4:26 p.m. UTC | #12
On Wed, Nov 23, 2022 at 1:52 PM Marcelo Ricardo Leitner
<marcelo.leitner@gmail.com> wrote:
>
> On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > --- a/net/netfilter/Makefile
> > +++ b/net/netfilter/Makefile
> > @@ -52,7 +52,7 @@ obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
> >  obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
> >  obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o
> >
> > -nf_nat-y     := nf_nat_core.o nf_nat_proto.o nf_nat_helper.o
> > +nf_nat-y     := nf_nat_core.o nf_nat_proto.o nf_nat_helper.o nf_nat_ovs.o
>
> Considering that the code in nf_nat_ovs is only used if ovs or act_ct
> are enabled, shouldn't it be using an invisible knob here that gets
> automatically selected by them? Pablo?
It's good to not build it if no place is using it.
Making nf_nat_ovs a module might be too much.
If it's okay to Netfilter devel, I will change to use "ifdef" in Makefile:

+ifdef CONFIG_OPENVSWITCH
+nf_nat-y += nf_nat_ovs.o
+else ifdef CONFIG_NET_ACT_CT
+nf_nat-y += nf_nat_ovs.o
+endif
+

Thanks.

>
> I think this is my last comment on this series. The rest LGTM.
>
> >
> >  obj-$(CONFIG_NF_LOG_SYSLOG) += nf_log_syslog.o
> >
Marcelo Ricardo Leitner Dec. 1, 2022, 9:37 p.m. UTC | #13
On Wed, Nov 23, 2022 at 04:34:45PM -0500, Xin Long wrote:
> On Wed, Nov 23, 2022 at 4:21 PM Marcelo Ricardo Leitner
> <marcelo.leitner@gmail.com> wrote:
> >
> > On Wed, Nov 23, 2022 at 02:55:05PM -0500, Xin Long wrote:
> > > On Wed, Nov 23, 2022 at 2:17 PM Marcelo Ricardo Leitner
> > > <marcelo.leitner@gmail.com> wrote:
> > > >
> > > > On Wed, Nov 23, 2022 at 01:54:41PM -0500, Xin Long wrote:
> > > > > On Wed, Nov 23, 2022 at 1:48 PM Marcelo Ricardo Leitner
> > > > > <marcelo.leitner@gmail.com> wrote:
> > > > > >
> > > > > > On Wed, Nov 23, 2022 at 12:31:38PM -0500, Xin Long wrote:
> > > > > > > On Wed, Nov 23, 2022 at 10:13 AM Marcelo Ricardo Leitner
> > > > > > > <marcelo.leitner@gmail.com> wrote:
> > > > > > > >
> > > > > > > > On Wed, Nov 23, 2022 at 12:09:55PM -0300, Marcelo Ricardo Leitner wrote:
> > > > > > > > > On Tue, Nov 22, 2022 at 12:32:21PM -0500, Xin Long wrote:
> > > > > > > > > > +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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
> > > > > > > > > > +           maniptype = NF_NAT_MANIP_SRC;
> > > > > > > > > > +   } else if (ct_action & (1 << 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);
> > > > > > > > > > diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
> > > > > > > > > > index cc643a556ea1..d03c75165663 100644
> > > > > > > > > > --- a/net/openvswitch/conntrack.c
> > > > > > > > > > +++ b/net/openvswitch/conntrack.c
> > > > > > > > > > @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
> > > > > > > > > >     }
> > > > > > > > > >  }
> > > > > > > > > >
> > > > > > > > > > -/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
> > > > > > > > > > -                         enum ip_conntrack_info ctinfo,
> > > > > > > > > > -                         const struct nf_nat_range2 *range,
> > > > > > > > > > -                         enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
> > > > > > > > > > -{
> > > > > > > > > > -   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 (IS_ENABLED(CONFIG_NF_NAT) &&
> > > > > > > > > > -               skb->protocol == 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) &&
> > > > > > > > > > -                      skb->protocol == 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);
> > > > > > > > > > -out:
> > > > > > > > > > -   /* Update the flow key if NAT successful. */
> > > > > > > > > > -   if (err == NF_ACCEPT)
> > > > > > > > > > -           ovs_nat_update_key(key, skb, maniptype);
> > > > > > > > > > -
> > > > > > > > > > -   return err;
> > > > > > > > > > -}
> > > > > > > > > > -
> > > > > > > > > >  /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
> > > > > > > > > >  static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
> > > > > > > > > >                   const struct ovs_conntrack_info *info,
> > > > > > > > > >                   struct sk_buff *skb, struct nf_conn *ct,
> > > > > > > > > >                   enum ip_conntrack_info ctinfo)
> > > > > > > > > >  {
> > > > > > > > > > -   enum nf_nat_manip_type maniptype;
> > > > > > > > > > -   int err;
> > > > > > > > > > +   int err, action = 0;
> > > > > > > > > >
> > > > > > > > > >     if (!(info->nat & OVS_CT_NAT))
> > > > > > > > > >             return NF_ACCEPT;
> > > > > > > > > > +   if (info->nat & OVS_CT_SRC_NAT)
> > > > > > > > > > +           action |= (1 << NF_NAT_MANIP_SRC);
> > > > > > > > > > +   if (info->nat & OVS_CT_DST_NAT)
> > > > > > > > > > +           action |= (1 << NF_NAT_MANIP_DST);
> > > > > > > > >
> > > > > > > > > I'm wondering why this dance at this level with supporting multiple
> > > > > > > > > MANIPs while actually only one can be used at a time.
> > > > > > > > >
> > > > > > > > > act_ct will reject an action using both:
> > > > > > > > >         if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
> > > > > > > > >             (p->ct_action & TCA_CT_ACT_NAT_DST)) {
> > > > > > > > >                 NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
> > > > > > > > >                 return -EOPNOTSUPP;
> > > > > > > > >
> > > > > > > > > I couldn't find this kind of check in ovs code right now (didn't look much, I
> > > > > > > > > confess :)), but even the code here was already doing:
> > > > > > > > >
> > > > > > > > > -     } else if (info->nat & OVS_CT_SRC_NAT) {
> > > > > > > > > -             maniptype = NF_NAT_MANIP_SRC;
> > > > > > > > > -     } else if (info->nat & OVS_CT_DST_NAT) {
> > > > > > > > > -             maniptype = NF_NAT_MANIP_DST;
> > > > > > > > >
> > > > > > > > > And in case of tuple conflict, maniptype will be forcibly updated in
> > > > > > > > > [*] below.
> > > > > > > >
> > > > > > > > Ahh.. just found why.. in case of typle conflict, nf_ct_nat() now may
> > > > > > > > set both.
> > > > > > > Right.
> > > > > > > BTW. The tuple conflict processing actually has provided the
> > > > > > > code to do full nat (snat and dnat at the same time), which I
> > > > > > > think is more efficient than doing full nat in two zones. All
> > > > > > > we have to do is adjust a few lines of code for that.
> > > > > >
> > > > > > In this part, yes. But it needs some surgery all around for full
> > > > > > support. The code in ovs kernel for using only one type starts here:
> > > > > >
> > > > > > static int parse_nat(const struct nlattr *attr,
> > > > > >                      struct ovs_conntrack_info *info, bool log)
> > > > > > {
> > > > > > ...
> > > > > >                 switch (type) {
> > > > > >                 case OVS_NAT_ATTR_SRC:
> > > > > >                 case OVS_NAT_ATTR_DST:
> > > > > >                         if (info->nat) {
> > > > > >                                 OVS_NLERR(log, "Only one type of NAT may be specified");
> > > > > >                                 return -ERANGE;
> > > > > >                         }
> > > > > > ...
> > > > > > }
> > > > > >
> > > > > > So vswitchd also doesn't support it. And then tc, iproute and drivers
> > > > > > that offload it as well. Not sure if it has impacts on openflow too.
> > > > > >
> > > > > not in one single action, but two actions:
> > > >
> > > > Oh.
> > > >
> > > > >
> > > > > "table=1, in_port=veth1,tcp,tcp_dst=2121,ct_state=+trk+new
> > > > > actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1),
> > > > > alg=ftp),veth2"
> > > > >
> > > > > as long as it allows the 1st one doesn't commit, which is a simple
> > > > > check in parse_nat().
> > > > > I tested it, TC already supports it. I'm not sure about drivers, but I
> > > >
> > > > There's an outstanding issue with act_ct that it may reuse an old
> > > > CT cache. Fixing it could (I'm not sure) impact this use case:
> > > >
> > > > https://bugzilla.redhat.com/show_bug.cgi?id=2099220
> > > > same issue in ovs was fixed in
> > > > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2061ecfdf2350994e5b61c43e50e98a7a70e95ee
> > > >
> > > > (please don't ask me who would NAT and then overwrite IP addresses and
> > > > then NAT it again :D)
> > > I thought only traditional NAT would change IP, I'm too naive.
> > >
> > > nftables names this as "stateless NAT."
> > > With two CTs in the same zone for full nat is more close to the
> > > netfilter's NAT processing (the same CT goes from prerouting to
> > > postrouting).
> > > Now I'm wondering how nftables handles the stateful NAT and stateless
> > > NAT at the same time.
> >
> > Me too.
> >
> > >
> > > >
> > > > > think it should be, as with two actions.
> > > >
> > > > mlx5 at least currently doesn't support it. Good that tc already
> > > > supports it, then. Maybe drivers can get up to speed later on.
> > > So because mlx5 currently only supports one ct action in one tc rule
> > > or something?
> >
> > Not sure what you meant here?
> Sorry. that might be a silly question, I don't know much about TC
> HW offload, and just curious why such a rule can not be offloaded
> in mlx5 driver:
> 
> "actions=ct(nat(dst=7.7.16.3)),ct(commit, nat(src=7.7.16.1)),veth2"
> 
> it doesn't support any tc NAT or just does not support tc full NAT HW offload?

AFAIK it just doesn't support 2 ct() actions in the same filter. It
can do full NAT HW offload, as long as it's going through 2 filters.
I don't know where the limitation comes from. I was hoping that Nvidia
could comment on it, with at least a "yep, that's not supported" or
otherwise. Maybe this is old stuff already.
diff mbox series

Patch

diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index e9eb01e99d2f..9877f064548a 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -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)
 {
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 1d4db1943936..4fa50d2842ec 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -52,7 +52,7 @@  obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
 obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
 obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o
 
-nf_nat-y	:= nf_nat_core.o nf_nat_proto.o nf_nat_helper.o
+nf_nat-y	:= nf_nat_core.o nf_nat_proto.o nf_nat_helper.o nf_nat_ovs.o
 
 obj-$(CONFIG_NF_LOG_SYSLOG) += nf_log_syslog.o
 
diff --git a/net/netfilter/nf_nat_ovs.c b/net/netfilter/nf_nat_ovs.c
new file mode 100644
index 000000000000..daff80e7a43a
--- /dev/null
+++ b/net/netfilter/nf_nat_ovs.c
@@ -0,0 +1,135 @@ 
+// 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 |= (1 << 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_ACCEPT;   /* 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 & (1 << NF_NAT_MANIP_SRC)) {
+		maniptype = NF_NAT_MANIP_SRC;
+	} else if (ct_action & (1 << 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);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index cc643a556ea1..d03c75165663 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -726,144 +726,27 @@  static void ovs_nat_update_key(struct sw_flow_key *key,
 	}
 }
 
-/* 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 ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
-			      enum ip_conntrack_info ctinfo,
-			      const struct nf_nat_range2 *range,
-			      enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
-{
-	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 (IS_ENABLED(CONFIG_NF_NAT) &&
-		    skb->protocol == 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) &&
-			   skb->protocol == 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);
-out:
-	/* Update the flow key if NAT successful. */
-	if (err == NF_ACCEPT)
-		ovs_nat_update_key(key, skb, maniptype);
-
-	return err;
-}
-
 /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
 static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 		      const struct ovs_conntrack_info *info,
 		      struct sk_buff *skb, struct nf_conn *ct,
 		      enum ip_conntrack_info ctinfo)
 {
-	enum nf_nat_manip_type maniptype;
-	int err;
+	int err, action = 0;
 
 	if (!(info->nat & OVS_CT_NAT))
 		return NF_ACCEPT;
+	if (info->nat & OVS_CT_SRC_NAT)
+		action |= (1 << NF_NAT_MANIP_SRC);
+	if (info->nat & OVS_CT_DST_NAT)
+		action |= (1 << NF_NAT_MANIP_DST);
 
-	/* Add NAT extension if not confirmed yet. */
-	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
-		return NF_ACCEPT;   /* Can't NAT. */
+	err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit);
 
-	/* Determine NAT type.
-	 * Check if the NAT type can be deduced from the tracked connection.
-	 * Make sure new expected connections (IP_CT_RELATED) are NATted only
-	 * when committing.
-	 */
-	if (ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK &&
-	    (ctinfo != IP_CT_RELATED || info->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 (info->nat & OVS_CT_SRC_NAT) {
-		maniptype = NF_NAT_MANIP_SRC;
-	} else if (info->nat & OVS_CT_DST_NAT) {
-		maniptype = NF_NAT_MANIP_DST;
-	} else {
-		return NF_ACCEPT; /* Connection is not NATed. */
-	}
-	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key);
-
-	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 = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
-						 maniptype, key);
-		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
-			err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
-						 NF_NAT_MANIP_SRC, key);
-		}
-	}
+	if (action & (1 << NF_NAT_MANIP_SRC))
+		ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC);
+	if (action & (1 << NF_NAT_MANIP_DST))
+		ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST);
 
 	return err;
 }
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index c7782c9a6ab6..0c410220239f 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -863,90 +863,6 @@  static void tcf_ct_params_free_rcu(struct rcu_head *head)
 	tcf_ct_params_free(params);
 }
 
-#if IS_ENABLED(CONFIG_NF_NAT)
-/* 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 ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
-			  enum ip_conntrack_info ctinfo,
-			  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);
-out:
-	if (err == NF_ACCEPT) {
-		if (maniptype == NF_NAT_MANIP_SRC)
-			tc_skb_cb(skb)->post_ct_snat = 1;
-		if (maniptype == NF_NAT_MANIP_DST)
-			tc_skb_cb(skb)->post_ct_dnat = 1;
-	}
-	return err;
-}
-#endif /* CONFIG_NF_NAT */
-
 static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
 {
 #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
@@ -986,52 +902,22 @@  static int tcf_ct_act_nat(struct sk_buff *skb,
 			  bool commit)
 {
 #if IS_ENABLED(CONFIG_NF_NAT)
-	int err;
-	enum nf_nat_manip_type maniptype;
+	int err, action = 0;
 
 	if (!(ct_action & TCA_CT_ACT_NAT))
 		return NF_ACCEPT;
+	if (ct_action & TCA_CT_ACT_NAT_SRC)
+		action |= (1 << NF_NAT_MANIP_SRC);
+	if (ct_action & TCA_CT_ACT_NAT_DST)
+		action |= (1 << NF_NAT_MANIP_DST);
 
-	/* Add NAT extension if not confirmed yet. */
-	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
-		return NF_ACCEPT;   /* 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 & TCA_CT_ACT_NAT_SRC) {
-		maniptype = NF_NAT_MANIP_SRC;
-	} else if (ct_action & TCA_CT_ACT_NAT_DST) {
-		maniptype = NF_NAT_MANIP_DST;
-	} else {
-		return NF_ACCEPT;
-	}
+	err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
+
+	if (action & (1 << NF_NAT_MANIP_SRC))
+		tc_skb_cb(skb)->post_ct_snat = 1;
+	if (action & (1 << NF_NAT_MANIP_DST))
+		tc_skb_cb(skb)->post_ct_dnat = 1;
 
-	err = ct_nat_execute(skb, ct, ctinfo, 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 = ct_nat_execute(skb, ct, ctinfo, range,
-					     maniptype);
-		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
-			err = ct_nat_execute(skb, ct, ctinfo, NULL,
-					     NF_NAT_MANIP_SRC);
-		}
-	}
 	return err;
 #else
 	return NF_ACCEPT;