diff options
Diffstat (limited to 'net/openvswitch')
-rw-r--r-- | net/openvswitch/Kconfig | 4 | ||||
-rw-r--r-- | net/openvswitch/actions.c | 4 | ||||
-rw-r--r-- | net/openvswitch/conntrack.c | 48 | ||||
-rw-r--r-- | net/openvswitch/datapath.c | 30 | ||||
-rw-r--r-- | net/openvswitch/flow_netlink.c | 5 | ||||
-rw-r--r-- | net/openvswitch/vport-internal_dev.c | 3 |
6 files changed, 54 insertions, 40 deletions
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 234a73344c6e..ce947292ae77 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -7,7 +7,9 @@ config OPENVSWITCH depends on INET depends on !NF_CONNTRACK || \ (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ - (!NF_NAT || NF_NAT))) + (!NF_NAT || NF_NAT) && \ + (!NF_NAT_IPV4 || NF_NAT_IPV4) && \ + (!NF_NAT_IPV6 || NF_NAT_IPV6))) select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index e9dd47b2a85b..879185fe183f 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -461,7 +461,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked); if (unlikely(memcmp(saddr, masked, sizeof(masked)))) { - set_ipv6_addr(skb, key->ipv6_proto, saddr, masked, + set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked, true); memcpy(&flow_key->ipv6.addr.src, masked, sizeof(flow_key->ipv6.addr.src)); @@ -483,7 +483,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, NULL, &flags) != NEXTHDR_ROUTING); - set_ipv6_addr(skb, key->ipv6_proto, daddr, masked, + set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked, recalc_csum); memcpy(&flow_key->ipv6.addr.dst, masked, sizeof(flow_key->ipv6.addr.dst)); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index dc5eb29fe7d6..3d5feede962d 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -367,6 +367,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, } else if (key->eth.type == htons(ETH_P_IPV6)) { enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; + skb_orphan(skb); memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); err = nf_ct_frag6_gather(net, skb, user); if (err) @@ -438,20 +439,12 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, u8 protonum; l3proto = __nf_ct_l3proto_find(l3num); - if (!l3proto) { - pr_debug("ovs_ct_find_existing: Can't get l3proto\n"); - return NULL; - } if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, &protonum) <= 0) { pr_debug("ovs_ct_find_existing: Can't get protonum\n"); return NULL; } l4proto = __nf_ct_l4proto_find(l3num, protonum); - if (!l4proto) { - pr_debug("ovs_ct_find_existing: Can't get l4proto\n"); - return NULL; - } if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, protonum, net, &tuple, l3proto, l4proto)) { pr_debug("ovs_ct_find_existing: Can't get tuple\n"); @@ -535,14 +528,15 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: - if (skb->protocol == htons(ETH_P_IP) && + if (IS_ENABLED(CONFIG_NF_NAT_IPV4) && + 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 push; -#if IS_ENABLED(CONFIG_NF_NAT_IPV6) - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) && + skb->protocol == htons(ETH_P_IPV6)) { __be16 frag_off; u8 nexthdr = ipv6_hdr(skb)->nexthdr; int hdrlen = ipv6_skip_exthdr(skb, @@ -557,7 +551,6 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, err = NF_DROP; goto push; } -#endif } /* Non-ICMP, fall thru to initialize if needed. */ case IP_CT_NEW: @@ -664,11 +657,12 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, /* Determine NAT type. * Check if the NAT type can be deduced from the tracked connection. - * Make sure expected traffic is NATted only when committing. + * Make sure new expected connections (IP_CT_RELATED) are NATted only + * when committing. */ if (info->nat & OVS_CT_NAT && ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK && - (!(ct->status & IPS_EXPECTED_BIT) || info->commit)) { + (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 @@ -774,6 +768,19 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, return -EINVAL; } + /* Userspace may decide to perform a ct lookup without a helper + * specified followed by a (recirculate and) commit with one. + * Therefore, for unconfirmed connections which we will commit, + * we need to attach the helper here. + */ + if (!nf_ct_is_confirmed(ct) && info->commit && + info->helper && !nfct_help(ct)) { + int err = __nf_ct_try_assign_helper(ct, info->ct, + GFP_ATOMIC); + if (err) + return err; + } + /* Call the helper only if: * - nf_conntrack_in() was executed above ("!cached") for a * confirmed connection, or @@ -968,7 +975,8 @@ static int parse_nat(const struct nlattr *attr, break; case OVS_NAT_ATTR_IP_MIN: - nla_memcpy(&info->range.min_addr, a, nla_len(a)); + nla_memcpy(&info->range.min_addr, a, + sizeof(info->range.min_addr)); info->range.flags |= NF_NAT_RANGE_MAP_IPS; break; @@ -1238,7 +1246,8 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, } if (info->range.flags & NF_NAT_RANGE_MAP_IPS) { - if (info->family == NFPROTO_IPV4) { + if (IS_ENABLED(CONFIG_NF_NAT_IPV4) && + info->family == NFPROTO_IPV4) { if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN, info->range.min_addr.ip) || (info->range.max_addr.ip @@ -1246,8 +1255,8 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX, info->range.max_addr.ip)))) return false; -#if IS_ENABLED(CONFIG_NF_NAT_IPV6) - } else if (info->family == NFPROTO_IPV6) { + } else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) && + info->family == NFPROTO_IPV6) { if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN, &info->range.min_addr.in6) || (memcmp(&info->range.max_addr.in6, @@ -1256,7 +1265,6 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MAX, &info->range.max_addr.in6)))) return false; -#endif } else { return false; } @@ -1342,7 +1350,7 @@ void ovs_ct_init(struct net *net) unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - if (nf_connlabels_get(net, n_bits)) { + if (nf_connlabels_get(net, n_bits - 1)) { ovs_net->xt_label = false; OVS_NLERR(true, "Failed to set connlabel length"); } else { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 0cc66a4e492d..856bd8dba676 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -738,9 +738,9 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts, len += nla_total_size(acts->orig_len); return len - + nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */ + + nla_total_size_64bit(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */ + nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */ - + nla_total_size(8); /* OVS_FLOW_ATTR_USED */ + + nla_total_size_64bit(8); /* OVS_FLOW_ATTR_USED */ } /* Called with ovs_mutex or RCU read lock. */ @@ -754,11 +754,14 @@ static int ovs_flow_cmd_fill_stats(const struct sw_flow *flow, ovs_flow_stats_get(flow, &stats, &used, &tcp_flags); if (used && - nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used))) + nla_put_u64_64bit(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used), + OVS_FLOW_ATTR_PAD)) return -EMSGSIZE; if (stats.n_packets && - nla_put(skb, OVS_FLOW_ATTR_STATS, sizeof(struct ovs_flow_stats), &stats)) + nla_put_64bit(skb, OVS_FLOW_ATTR_STATS, + sizeof(struct ovs_flow_stats), &stats, + OVS_FLOW_ATTR_PAD)) return -EMSGSIZE; if ((u8)ntohs(tcp_flags) && @@ -1434,8 +1437,8 @@ static size_t ovs_dp_cmd_msg_size(void) size_t msgsize = NLMSG_ALIGN(sizeof(struct ovs_header)); msgsize += nla_total_size(IFNAMSIZ); - msgsize += nla_total_size(sizeof(struct ovs_dp_stats)); - msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats)); + msgsize += nla_total_size_64bit(sizeof(struct ovs_dp_stats)); + msgsize += nla_total_size_64bit(sizeof(struct ovs_dp_megaflow_stats)); msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */ return msgsize; @@ -1462,13 +1465,13 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, goto nla_put_failure; get_dp_stats(dp, &dp_stats, &dp_megaflow_stats); - if (nla_put(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), - &dp_stats)) + if (nla_put_64bit(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), + &dp_stats, OVS_DP_ATTR_PAD)) goto nla_put_failure; - if (nla_put(skb, OVS_DP_ATTR_MEGAFLOW_STATS, - sizeof(struct ovs_dp_megaflow_stats), - &dp_megaflow_stats)) + if (nla_put_64bit(skb, OVS_DP_ATTR_MEGAFLOW_STATS, + sizeof(struct ovs_dp_megaflow_stats), + &dp_megaflow_stats, OVS_DP_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features)) @@ -1837,8 +1840,9 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, goto nla_put_failure; ovs_vport_get_stats(vport, &vport_stats); - if (nla_put(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats), - &vport_stats)) + if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS, + sizeof(struct ovs_vport_stats), &vport_stats, + OVS_VPORT_ATTR_PAD)) goto nla_put_failure; if (ovs_vport_get_upcall_portids(vport, skb)) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 689c17264221..0bb650f4f219 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -261,7 +261,7 @@ size_t ovs_tun_key_attr_size(void) /* Whenever adding new OVS_TUNNEL_KEY_ FIELDS, we should consider * updating this function. */ - return nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */ + return nla_total_size_64bit(8) /* OVS_TUNNEL_KEY_ATTR_ID */ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */ @@ -720,7 +720,8 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, unsigned short tun_proto) { if (output->tun_flags & TUNNEL_KEY && - nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) + nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id, + OVS_TUNNEL_KEY_ATTR_PAD)) return -EMSGSIZE; switch (tun_proto) { case AF_INET: diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 7c8b90bf0e54..2ee48e447b72 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -165,11 +165,10 @@ static void do_setup(struct net_device *netdev) netdev->priv_flags &= ~IFF_TX_SKB_SHARING; netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH | - IFF_PHONY_HEADROOM; + IFF_PHONY_HEADROOM | IFF_NO_QUEUE; netdev->destructor = internal_dev_destructor; netdev->ethtool_ops = &internal_dev_ethtool_ops; netdev->rtnl_link_ops = &internal_dev_link_ops; - netdev->tx_queue_len = 0; netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | |