diff options
Diffstat (limited to 'net/openvswitch/conntrack.c')
-rw-r--r-- | net/openvswitch/conntrack.c | 270 |
1 files changed, 148 insertions, 122 deletions
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e726159cfcfa..c7b10234cf7c 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -25,6 +25,8 @@ #include <net/netfilter/nf_nat.h> #endif +#include <net/netfilter/nf_conntrack_act_ct.h> + #include "datapath.h" #include "conntrack.h" #include "flow.h" @@ -271,15 +273,13 @@ static void ovs_ct_update_key(const struct sk_buff *skb, /* This is called to initialize CT key fields possibly coming in from the local * stack. */ -void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) +void ovs_ct_fill_key(const struct sk_buff *skb, + struct sw_flow_key *key, + bool post_ct) { - ovs_ct_update_key(skb, NULL, key, false, false); + ovs_ct_update_key(skb, NULL, key, post_ct, false); } -#define IN6_ADDR_INITIALIZER(ADDR) \ - { (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \ - (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] } - int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb) { @@ -301,24 +301,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey, if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { - struct ovs_key_ct_tuple_ipv4 orig = { - output->ipv4.ct_orig.src, - output->ipv4.ct_orig.dst, - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv4 orig; + + memset(&orig, 0, sizeof(orig)); + orig.ipv4_src = output->ipv4.ct_orig.src; + orig.ipv4_dst = output->ipv4.ct_orig.dst; + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv4_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - struct ovs_key_ct_tuple_ipv6 orig = { - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src), - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst), - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv6 orig; + + memset(&orig, 0, sizeof(orig)); + memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, + sizeof(orig.ipv6_src)); + memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, + sizeof(orig.ipv6_dst)); + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv6_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; @@ -570,7 +576,7 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); nf_ct_delete(ct, 0, 0); - nf_conntrack_put(&ct->ct_general); + nf_ct_put(ct); } } @@ -719,7 +725,7 @@ static bool skb_nfct_cached(struct net *net, if (nf_ct_is_confirmed(ct)) nf_ct_delete(ct, 0, 0); - nf_conntrack_put(&ct->ct_general); + nf_ct_put(ct); nf_ct_set(skb, NULL, 0); return false; } @@ -728,6 +734,57 @@ 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. @@ -735,7 +792,7 @@ 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; @@ -776,7 +833,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, } } /* Non-ICMP, fall thru to initialize if needed. */ - /* fall through */ + fallthrough; case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. @@ -805,61 +862,13 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, err = nf_nat_packet(ct, ctinfo, hooknum, skb); push: - skb_push(skb, nh_off); - skb_postpush_rcsum(skb, skb->data, nh_off); - - return err; -} + skb_push_rcsum(skb, nh_off); -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. */ @@ -901,23 +910,23 @@ 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_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; + 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); + 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); + } } - /* 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 */ @@ -960,8 +969,8 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, /* Associate skb with specified zone. */ if (tmpl) { - if (skb_nfct(skb)) - nf_conntrack_put(skb_nfct(skb)); + ct = nf_ct_get(skb, &ctinfo); + nf_ct_put(ct); nf_conntrack_get(&tmpl->ct_general); nf_ct_set(skb, tmpl, IP_CT_NEW); } @@ -1006,7 +1015,8 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, * connections which we will commit, we may need to attach * the helper here. */ - if (info->commit && info->helper && !nfct_help(ct)) { + 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) @@ -1031,6 +1041,16 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, ovs_ct_helper(skb, info->family) != NF_ACCEPT) { return -EINVAL; } + + if (nf_ct_protonum(ct) == IPPROTO_TCP && + nf_ct_is_confirmed(ct) && nf_conntrack_tcp_established(ct)) { + /* Be liberal for tcp packets so that out-of-window + * packets are not marked invalid. + */ + nf_ct_set_tcp_be_liberal(ct); + } + + nf_conn_act_ct_ext_fill(skb, ct, ctinfo); } return 0; @@ -1231,6 +1251,8 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, &info->labels.mask); if (err) return err; + + nf_conn_act_ct_ext_add(ct); } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, @@ -1306,8 +1328,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, else err = ovs_ct_lookup(net, key, info, skb); - skb_push(skb, nh_ofs); - skb_postpush_rcsum(skb, skb->data, nh_ofs); + skb_push_rcsum(skb, nh_ofs); if (err) kfree_skb(skb); return err; @@ -1315,11 +1336,16 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) { - if (skb_nfct(skb)) { - nf_conntrack_put(skb_nfct(skb)); - nf_ct_set(skb, NULL, IP_CT_UNTRACKED); - ovs_ct_fill_key(skb, key); - } + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + + nf_ct_put(ct); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + + if (key) + ovs_ct_fill_key(skb, key, false); return 0; } @@ -1538,7 +1564,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, switch (type) { case OVS_CT_ATTR_FORCE_COMMIT: info->force = true; - /* fall through. */ + fallthrough; case OVS_CT_ATTR_COMMIT: info->commit = true; break; @@ -1705,7 +1731,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, goto err_free_ct; __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); - nf_conntrack_get(&ct_info.ct->ct_general); return 0; err_free_ct: __ovs_ct_free_action(&ct_info); @@ -1895,11 +1920,12 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node) + hlist_for_each_entry_rcu(ct_limit, head, hlist_node, + lockdep_ovsl_is_held()) kfree_rcu(ct_limit, rcu); } - kfree(ovs_net->ct_limit_info->limits); - kfree(ovs_net->ct_limit_info); + kfree(info->limits); + kfree(info); } static struct sk_buff * @@ -1957,7 +1983,8 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, } else { struct ovs_ct_limit *ct_limit; - ct_limit = kmalloc(sizeof(*ct_limit), GFP_KERNEL); + ct_limit = kmalloc(sizeof(*ct_limit), + GFP_KERNEL_ACCOUNT); if (!ct_limit) return -ENOMEM; @@ -2017,16 +2044,12 @@ static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, static int ovs_ct_limit_get_default_limit(struct ovs_ct_limit_info *info, struct sk_buff *reply) { - struct ovs_zone_limit zone_limit; - int err; - - zone_limit.zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE; - zone_limit.limit = info->default_limit; - err = nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); - if (err) - return err; + struct ovs_zone_limit zone_limit = { + .zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE, + .limit = info->default_limit, + }; - return 0; + return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); } static int __ovs_ct_limit_get_zone_limit(struct net *net, @@ -2228,17 +2251,19 @@ exit_err: return err; } -static struct genl_ops ct_limit_genl_ops[] = { +static const struct genl_small_ops ct_limit_genl_ops[] = { { .cmd = OVS_CT_LIMIT_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN - * privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN + * privilege. + */ .doit = ovs_ct_limit_cmd_set, }, { .cmd = OVS_CT_LIMIT_CMD_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN - * privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN + * privilege. + */ .doit = ovs_ct_limit_cmd_del, }, { .cmd = OVS_CT_LIMIT_CMD_GET, @@ -2260,8 +2285,9 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = { .policy = ct_limit_policy, .netnsok = true, .parallel_ops = true, - .ops = ct_limit_genl_ops, - .n_ops = ARRAY_SIZE(ct_limit_genl_ops), + .small_ops = ct_limit_genl_ops, + .n_small_ops = ARRAY_SIZE(ct_limit_genl_ops), + .resv_start_op = OVS_CT_LIMIT_CMD_GET + 1, .mcgrps = &ovs_ct_limit_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, |