All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paul Blakey <paulb@nvidia.com>
To: Paul Blakey <paulb@nvidia.com>, <dev@openvswitch.org>,
	<netdev@vger.kernel.org>, Cong Wang <xiyou.wangcong@gmail.com>,
	"Jamal Hadi Salim" <jhs@mojatatu.com>,
	Pravin B Shelar <pshelar@ovn.org>, <davem@davemloft.net>,
	Jiri Pirko <jiri@nvidia.com>, Jakub Kicinski <kuba@kernel.org>
Cc: Saeed Mahameed <saeedm@nvidia.com>, Oz Shlomo <ozsh@nvidia.com>,
	"Vlad Buslov" <vladbu@nvidia.com>, Roi Dayan <roid@nvidia.com>
Subject: [PATCH net 1/1] net: openvswitch: Fix ct_state nat flags for conns arriving from tc
Date: Tue, 4 Jan 2022 10:28:21 +0200	[thread overview]
Message-ID: <20220104082821.22487-1-paulb@nvidia.com> (raw)

Netfilter conntrack maintains NAT flags per connection indicating
whether NAT was configured for the connection. Openvswitch maintains
NAT flags on the per packet flow key ct_state field, indicating
whether NAT was actually executed on the packet.

When a packet misses from tc to ovs the conntrack NAT flags are set.
However, NAT was not necessarily executed on the packet because the
connection's state might still be in NEW state. As such, openvswitch wrongly
assumes that NAT was executed and sets an incorrect flow key NAT flags.

Fix this, by flagging to openvswitch which NAT was actually done in
act_ct via tc_skb_ext and tc_skb_cb to the openvswitch module, so
the packet flow key NAT flags will be correctly set.

Signed-off-by: Paul Blakey <paulb@nvidia.com>
---
 include/linux/skbuff.h  |  4 +++-
 include/net/pkt_sched.h |  4 +++-
 net/openvswitch/flow.c  | 16 +++++++++++++---
 net/sched/act_ct.c      |  6 ++++++
 net/sched/cls_api.c     |  2 ++
 5 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4507d77d6941..bab45a009310 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -287,7 +287,9 @@ struct tc_skb_ext {
 	__u32 chain;
 	__u16 mru;
 	__u16 zone;
-	bool post_ct;
+	bool post_ct:1;
+	bool post_ct_snat:1;
+	bool post_ct_dnat:1;
 };
 #endif
 
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 9e71691c491b..a171dfa91910 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -197,7 +197,9 @@ struct tc_skb_cb {
 	struct qdisc_skb_cb qdisc_cb;
 
 	u16 mru;
-	bool post_ct;
+	bool post_ct: 1;
+	bool post_ct_snat:1;
+	bool post_ct_dnat:1;
 	u16 zone; /* Only valid if post_ct = true */
 };
 
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 6d262d9aa10e..02096f2ec678 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -859,7 +859,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
 	struct tc_skb_ext *tc_ext;
 #endif
-	bool post_ct = false;
+	bool post_ct = false, post_ct_snat = false, post_ct_dnat = false;
 	int res, err;
 	u16 zone = 0;
 
@@ -900,6 +900,8 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 		key->recirc_id = tc_ext ? tc_ext->chain : 0;
 		OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
 		post_ct = tc_ext ? tc_ext->post_ct : false;
+		post_ct_snat = post_ct ? tc_ext->post_ct_snat : false;
+		post_ct_dnat = post_ct ? tc_ext->post_ct_dnat : false;
 		zone = post_ct ? tc_ext->zone : 0;
 	} else {
 		key->recirc_id = 0;
@@ -911,8 +913,16 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 	err = key_extract(skb, key);
 	if (!err) {
 		ovs_ct_fill_key(skb, key, post_ct);   /* Must be after key_extract(). */
-		if (post_ct && !skb_get_nfct(skb))
-			key->ct_zone = zone;
+		if (post_ct) {
+			if (!skb_get_nfct(skb)) {
+				key->ct_zone = zone;
+			} else {
+				if (!post_ct_dnat)
+					key->ct_state &= ~OVS_CS_F_DST_NAT;
+				if (!post_ct_snat)
+					key->ct_state &= ~OVS_CS_F_SRC_NAT;
+			}
+		}
 	}
 	return err;
 }
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index ab3591408419..2a17eb77c904 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -839,6 +839,12 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	}
 
 	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
+	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;
+	}
 out:
 	return err;
 }
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 35c74bdde848..cc9409aa755e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1625,6 +1625,8 @@ int tcf_classify(struct sk_buff *skb,
 		ext->chain = last_executed_chain;
 		ext->mru = cb->mru;
 		ext->post_ct = cb->post_ct;
+		ext->post_ct_snat = cb->post_ct_snat;
+		ext->post_ct_dnat = cb->post_ct_dnat;
 		ext->zone = cb->zone;
 	}
 
-- 
2.30.1


             reply	other threads:[~2022-01-04  8:28 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-04  8:28 Paul Blakey [this message]
2022-01-04 18:08 ` [PATCH net 1/1] net: openvswitch: Fix ct_state nat flags for conns arriving from tc Jakub Kicinski
2022-01-05  8:29   ` Paul Blakey
2022-01-05 14:57 ` Jamal Hadi Salim
2022-01-05 15:30   ` Daniel Borkmann
2022-01-05 16:18     ` Paul Blakey
2022-01-06 12:54       ` Jamal Hadi Salim

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220104082821.22487-1-paulb@nvidia.com \
    --to=paulb@nvidia.com \
    --cc=davem@davemloft.net \
    --cc=dev@openvswitch.org \
    --cc=jhs@mojatatu.com \
    --cc=jiri@nvidia.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=ozsh@nvidia.com \
    --cc=pshelar@ovn.org \
    --cc=roid@nvidia.com \
    --cc=saeedm@nvidia.com \
    --cc=vladbu@nvidia.com \
    --cc=xiyou.wangcong@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.