net/sched: act_ct: fix miss set mru for ovs after defrag in act_ct

When openvswitch conntrack offload with act_ct action. Fragment packets
defrag in the ingress tc act_ct action and miss the next chain. Then the
packet pass to the openvswitch datapath without the mru. The over
mtu packet will be dropped in output action in openvswitch for over mtu.

"kernel: net2: dropped over-mtu packet: 1528 > 1500"

This patch add mru in the tc_skb_ext for adefrag and miss next chain
situation. And also add mru in the qdisc_skb_cb. The act_ct set the mru
to the qdisc_skb_cb when the packet defrag. And When the chain miss,
The mru is set to tc_skb_ext which can be got by ovs datapath.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 11 insertions, 3 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fa817a105517..3ad65d4ce085 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -283,6 +283,7 @@ struct nf_bridge_info {
  */
 struct tc_skb_ext {
 	__u32 chain;
+	__u16 mru;
 };
 #endif
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c510b03b9751..d60e7c39d60c 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -384,6 +384,7 @@ struct qdisc_skb_cb {
 	};
 #define QDISC_CB_PRIV_LEN 20
 	unsigned char		data[QDISC_CB_PRIV_LEN];
+	u16			mru;
 };
 
 typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
@@ -463,7 +464,7 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 {
 	struct qdisc_skb_cb *qcb;
 
-	BUILD_BUG_ON(sizeof(skb->cb) < offsetof(struct qdisc_skb_cb, data) + sz);
+	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb));
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 9d375e74b607..03942c30d83e 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -890,6 +890,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 	if (static_branch_unlikely(&tc_recirc_sharing_support)) {
 		tc_ext = skb_ext_find(skb, TC_SKB_EXT);
 		key->recirc_id = tc_ext ? tc_ext->chain : 0;
+		OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
 	} else {
 		key->recirc_id = 0;
 	}
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 97e27946897f..e6ad42b11835 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -706,8 +706,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		if (err && err != -EINPROGRESS)
 			goto out_free;
 
-		if (!err)
+		if (!err) {
 			*defrag = true;
+			cb.mru = IPCB(skb)->frag_max_size;
+		}
 	} else { /* NFPROTO_IPV6 */
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
@@ -717,8 +719,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		if (err && err != -EINPROGRESS)
 			goto out_free;
 
-		if (!err)
+		if (!err) {
 			*defrag = true;
+			cb.mru = IP6CB(skb)->frag_max_size;
+		}
 #else
 		err = -EOPNOTSUPP;
 		goto out_free;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0b8623b3b24f..41a55c6cbeb8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1629,6 +1629,7 @@ int tcf_classify_ingress(struct sk_buff *skb,
 		if (WARN_ON_ONCE(!ext))
 			return TC_ACT_SHOT;
 		ext->chain = last_executed_chain;
+		ext->mru = qdisc_skb_cb(skb)->mru;
 	}
 
 	return ret;