From: Aaron Conole aconole@redhat.com
stable inclusion from stable-v5.10.110 commit 5d8162371ce80542f882aaec24fad8bfd9724f9b bugzilla: https://gitee.com/openeuler/kernel/issues/I574AL
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit 60b44ca6bd7518dd38fa2719bc9240378b6172c3 ]
During NAT, a tuple collision may occur. When this happens, openvswitch will make a second pass through NAT which will perform additional packet modification. This will update the skb data, but not the flow key that OVS uses. This means that future flow lookups, and packet matches will have incorrect data. This has been supported since 5d50aa83e2c8 ("openvswitch: support asymmetric conntrack").
That commit failed to properly update the sw_flow_key attributes, since it only called the ovs_ct_nat_update_key once, rather than each time ovs_ct_nat_execute was called. As these two operations are linked, the ovs_ct_nat_execute() function should always make sure that the sw_flow_key is updated after a successful call through NAT infrastructure.
Fixes: 5d50aa83e2c8 ("openvswitch: support asymmetric conntrack") Cc: Dumitru Ceara dceara@redhat.com Cc: Numan Siddique nusiddiq@redhat.com Signed-off-by: Aaron Conole aconole@redhat.com Acked-by: Eelco Chaudron echaudro@redhat.com Link: https://lore.kernel.org/r/20220318124319.3056455-1-aconole@redhat.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yu Liao liaoyu15@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/openvswitch/conntrack.c | 118 ++++++++++++++++++------------------ 1 file changed, 59 insertions(+), 59 deletions(-)
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index a11b558813c1..7ff98d39ec94 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -730,6 +730,57 @@ static bool skb_nfct_cached(struct net *net, }
#if IS_ENABLED(CONFIG_NF_NAT) +static void ovs_nat_update_key(struct sw_flow_key *key, + const struct sk_buff *skb, + enum nf_nat_manip_type maniptype) +{ + if (maniptype == NF_NAT_MANIP_SRC) { + __be16 src; + + key->ct_state |= OVS_CS_F_SRC_NAT; + if (key->eth.type == htons(ETH_P_IP)) + key->ipv4.addr.src = ip_hdr(skb)->saddr; + else if (key->eth.type == htons(ETH_P_IPV6)) + memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr, + sizeof(key->ipv6.addr.src)); + else + return; + + if (key->ip.proto == IPPROTO_UDP) + src = udp_hdr(skb)->source; + else if (key->ip.proto == IPPROTO_TCP) + src = tcp_hdr(skb)->source; + else if (key->ip.proto == IPPROTO_SCTP) + src = sctp_hdr(skb)->source; + else + return; + + key->tp.src = src; + } else { + __be16 dst; + + key->ct_state |= OVS_CS_F_DST_NAT; + if (key->eth.type == htons(ETH_P_IP)) + key->ipv4.addr.dst = ip_hdr(skb)->daddr; + else if (key->eth.type == htons(ETH_P_IPV6)) + memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr, + sizeof(key->ipv6.addr.dst)); + else + return; + + if (key->ip.proto == IPPROTO_UDP) + dst = udp_hdr(skb)->dest; + else if (key->ip.proto == IPPROTO_TCP) + dst = tcp_hdr(skb)->dest; + else if (key->ip.proto == IPPROTO_SCTP) + dst = sctp_hdr(skb)->dest; + else + return; + + key->tp.dst = dst; + } +} + /* Modelled after nf_nat_ipv[46]_fn(). * range is only used for new, uninitialized NAT state. * Returns either NF_ACCEPT or NF_DROP. @@ -737,7 +788,7 @@ static bool skb_nfct_cached(struct net *net, 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) + enum nf_nat_manip_type maniptype, struct sw_flow_key *key) { int hooknum, nh_off, err = NF_ACCEPT;
@@ -810,58 +861,11 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, skb_push(skb, nh_off); skb_postpush_rcsum(skb, skb->data, nh_off);
- return err; -} - -static void ovs_nat_update_key(struct sw_flow_key *key, - const struct sk_buff *skb, - enum nf_nat_manip_type maniptype) -{ - if (maniptype == NF_NAT_MANIP_SRC) { - __be16 src; - - key->ct_state |= OVS_CS_F_SRC_NAT; - if (key->eth.type == htons(ETH_P_IP)) - key->ipv4.addr.src = ip_hdr(skb)->saddr; - else if (key->eth.type == htons(ETH_P_IPV6)) - memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr, - sizeof(key->ipv6.addr.src)); - else - return; - - if (key->ip.proto == IPPROTO_UDP) - src = udp_hdr(skb)->source; - else if (key->ip.proto == IPPROTO_TCP) - src = tcp_hdr(skb)->source; - else if (key->ip.proto == IPPROTO_SCTP) - src = sctp_hdr(skb)->source; - else - return; - - key->tp.src = src; - } else { - __be16 dst; - - key->ct_state |= OVS_CS_F_DST_NAT; - if (key->eth.type == htons(ETH_P_IP)) - key->ipv4.addr.dst = ip_hdr(skb)->daddr; - else if (key->eth.type == htons(ETH_P_IPV6)) - memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr, - sizeof(key->ipv6.addr.dst)); - else - return; - - if (key->ip.proto == IPPROTO_UDP) - dst = udp_hdr(skb)->dest; - else if (key->ip.proto == IPPROTO_TCP) - dst = tcp_hdr(skb)->dest; - else if (key->ip.proto == IPPROTO_SCTP) - dst = sctp_hdr(skb)->dest; - else - return; + /* Update the flow key if NAT successful. */ + if (err == NF_ACCEPT) + ovs_nat_update_key(key, skb, maniptype);
- key->tp.dst = dst; - } + return err; }
/* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */ @@ -903,7 +907,7 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, } else { return NF_ACCEPT; /* Connection is not NATed. */ } - err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype); + 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) { @@ -913,17 +917,13 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, maniptype = NF_NAT_MANIP_SRC;
err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, - maniptype); + maniptype, key); } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL, - NF_NAT_MANIP_SRC); + NF_NAT_MANIP_SRC, key); } }
- /* Mark NAT done if successful and update the flow key. */ - if (err == NF_ACCEPT) - ovs_nat_update_key(key, skb, maniptype); - return err; } #else /* !CONFIG_NF_NAT */