From cb80d58fae76d8ea93555149b2b16e19b89a1f4f Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Thu, 9 Feb 2017 11:21:55 -0800 Subject: openvswitch: Unionize ovs_key_ct_label with a u32 array. Make the array of labels in struct ovs_key_ct_label an union, adding a u32 array of the same byte size as the existing u8 array. It is faster to loop through the labels 32 bits at the time, which is also the alignment of netlink attributes. Signed-off-by: Jarno Rajahalme Acked-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 375d812fea36..96aee34ef55f 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -446,9 +446,13 @@ struct ovs_key_nd { __u8 nd_tll[ETH_ALEN]; }; -#define OVS_CT_LABELS_LEN 16 +#define OVS_CT_LABELS_LEN_32 4 +#define OVS_CT_LABELS_LEN (OVS_CT_LABELS_LEN_32 * sizeof(__u32)) struct ovs_key_ct_labels { - __u8 ct_labels[OVS_CT_LABELS_LEN]; + union { + __u8 ct_labels[OVS_CT_LABELS_LEN]; + __u32 ct_labels_32[OVS_CT_LABELS_LEN_32]; + }; }; /* OVS_KEY_ATTR_CT_STATE flags */ -- cgit From 9dd7f8907c3705dc7a7a375d1c6e30b06e6daffc Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Thu, 9 Feb 2017 11:21:59 -0800 Subject: openvswitch: Add original direction conntrack tuple to sw_flow_key. Add the fields of the conntrack original direction 5-tuple to struct sw_flow_key. The new fields are initially marked as non-existent, and are populated whenever a conntrack action is executed and either finds or generates a conntrack entry. This means that these fields exist for all packets that were not rejected by conntrack as untrackable. The original tuple fields in the sw_flow_key are filled from the original direction tuple of the conntrack entry relating to the current packet, or from the original direction tuple of the master conntrack entry, if the current conntrack entry has a master. Generally, expected connections of connections having an assigned helper (e.g., FTP), have a master conntrack entry. The main purpose of the new conntrack original tuple fields is to allow matching on them for policy decision purposes, with the premise that the admissibility of tracked connections reply packets (as well as original direction packets), and both direction packets of any related connections may be based on ACL rules applying to the master connection's original direction 5-tuple. This also makes it easier to make policy decisions when the actual packet headers might have been transformed by NAT, as the original direction 5-tuple represents the packet headers before any such transformation. When using the original direction 5-tuple the admissibility of return and/or related packets need not be based on the mere existence of a conntrack entry, allowing separation of admission policy from the established conntrack state. While existence of a conntrack entry is required for admission of the return or related packets, policy changes can render connections that were initially admitted to be rejected or dropped afterwards. If the admission of the return and related packets was based on mere conntrack state (e.g., connection being in an established state), a policy change that would make the connection rejected or dropped would need to find and delete all conntrack entries affected by such a change. When using the original direction 5-tuple matching the affected conntrack entries can be allowed to time out instead, as the established state of the connection would not need to be the basis for packet admission any more. It should be noted that the directionality of related connections may be the same or different than that of the master connection, and neither the original direction 5-tuple nor the conntrack state bits carry this information. If needed, the directionality of the master connection can be stored in master's conntrack mark or labels, which are automatically inherited by the expected related connections. The fact that neither ARP nor ND packets are trackable by conntrack allows mutual exclusion between ARP/ND and the new conntrack original tuple fields. Hence, the IP addresses are overlaid in union with ARP and ND fields. This allows the sw_flow_key to not grow much due to this patch, but it also means that we must be careful to never use the new key fields with ARP or ND packets. ARP is easy to distinguish and keep mutually exclusive based on the ethernet type, but ND being an ICMPv6 protocol requires a bit more attention. Signed-off-by: Jarno Rajahalme Acked-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 20 +++++++++- net/openvswitch/actions.c | 2 + net/openvswitch/conntrack.c | 86 +++++++++++++++++++++++++++++++++++++--- net/openvswitch/conntrack.h | 10 ++++- net/openvswitch/flow.c | 34 +++++++++++++--- net/openvswitch/flow.h | 49 ++++++++++++++++++----- net/openvswitch/flow_netlink.c | 85 +++++++++++++++++++++++++++++---------- net/openvswitch/flow_netlink.h | 7 +++- 8 files changed, 246 insertions(+), 47 deletions(-) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 96aee34ef55f..90af8b8e10f8 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -1,6 +1,6 @@ /* - * Copyright (c) 2007-2013 Nicira, Inc. + * Copyright (c) 2007-2017 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -331,6 +331,8 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */ OVS_KEY_ATTR_CT_MARK, /* u32 connection tracking mark */ OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */ + OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ + OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -472,6 +474,22 @@ struct ovs_key_ct_labels { #define OVS_CS_F_NAT_MASK (OVS_CS_F_SRC_NAT | OVS_CS_F_DST_NAT) +struct ovs_key_ct_tuple_ipv4 { + __be32 ipv4_src; + __be32 ipv4_dst; + __be16 src_port; + __be16 dst_port; + __u8 ipv4_proto; +}; + +struct ovs_key_ct_tuple_ipv6 { + __be32 ipv6_src[4]; + __be32 ipv6_dst[4]; + __be16 src_port; + __be16 dst_port; + __u8 ipv6_proto; +}; + /** * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index efa9a8858cc6..b1beb2b94ec7 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1074,6 +1074,8 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_ZONE: case OVS_KEY_ATTR_CT_MARK: case OVS_KEY_ATTR_CT_LABELS: + case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4: + case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6: err = -EINVAL; break; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index f989ccf38eab..bfd7606c8be1 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -147,6 +147,20 @@ static void ovs_ct_get_labels(const struct nf_conn *ct, memset(labels, 0, OVS_CT_LABELS_LEN); } +static void __ovs_ct_update_key_orig_tp(struct sw_flow_key *key, + const struct nf_conntrack_tuple *orig, + u8 icmp_proto) +{ + key->ct.orig_proto = orig->dst.protonum; + if (orig->dst.protonum == icmp_proto) { + key->ct.orig_tp.src = htons(orig->dst.u.icmp.type); + key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code); + } else { + key->ct.orig_tp.src = orig->src.u.all; + key->ct.orig_tp.dst = orig->dst.u.all; + } +} + static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, const struct nf_conntrack_zone *zone, const struct nf_conn *ct) @@ -155,6 +169,35 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, key->ct.zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); ovs_ct_get_labels(ct, &key->ct.labels); + + if (ct) { + const struct nf_conntrack_tuple *orig; + + /* Use the master if we have one. */ + if (ct->master) + ct = ct->master; + orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + + /* IP version must match with the master connection. */ + if (key->eth.type == htons(ETH_P_IP) && + nf_ct_l3num(ct) == NFPROTO_IPV4) { + key->ipv4.ct_orig.src = orig->src.u3.ip; + key->ipv4.ct_orig.dst = orig->dst.u3.ip; + __ovs_ct_update_key_orig_tp(key, orig, IPPROTO_ICMP); + return; + } else if (key->eth.type == htons(ETH_P_IPV6) && + !sw_flow_key_is_nd(key) && + nf_ct_l3num(ct) == NFPROTO_IPV6) { + key->ipv6.ct_orig.src = orig->src.u3.in6; + key->ipv6.ct_orig.dst = orig->dst.u3.in6; + __ovs_ct_update_key_orig_tp(key, orig, NEXTHDR_ICMP); + return; + } + } + /* Clear 'ct.orig_proto' to mark the non-existence of conntrack + * original direction key fields. + */ + key->ct.orig_proto = 0; } /* Update 'key' based on skb->_nfct. If 'post_ct' is true, then OVS has @@ -208,24 +251,55 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) ovs_ct_update_key(skb, NULL, key, false, false); } -int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) +#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) { - if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) + if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct.state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && - nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, key->ct.zone)) + nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct.zone)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && - nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, key->ct.mark)) + nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, output->ct.mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(key->ct.labels), - &key->ct.labels)) + nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(output->ct.labels), + &output->ct.labels)) return -EMSGSIZE; + 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, + }; + 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, + }; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, + sizeof(orig), &orig)) + return -EMSGSIZE; + } + } + return 0; } diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 8f6230bd6183..9e92445dc092 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -32,7 +32,8 @@ int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, const struct ovs_conntrack_info *); void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); -int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); +int ovs_ct_put_key(const struct sw_flow_key *swkey, + const struct sw_flow_key *output, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); #define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \ @@ -79,9 +80,14 @@ static inline void ovs_ct_fill_key(const struct sk_buff *skb, key->ct.zone = 0; key->ct.mark = 0; memset(&key->ct.labels, 0, sizeof(key->ct.labels)); + /* Clear 'ct.orig_proto' to mark the non-existence of original + * direction key fields. + */ + key->ct.orig_proto = 0; } -static inline int ovs_ct_put_key(const struct sw_flow_key *key, +static inline int ovs_ct_put_key(const struct sw_flow_key *swkey, + const struct sw_flow_key *output, struct sk_buff *skb) { return 0; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 2c0a00f7f1b7..9d4bb8eb63f2 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -765,7 +765,7 @@ static int key_extract_mac_proto(struct sk_buff *skb) int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key) { - int res; + int res, err; /* Extract metadata from packet. */ if (tun_info) { @@ -792,7 +792,6 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->phy.priority = skb->priority; key->phy.in_port = OVS_CB(skb)->input_vport->port_no; key->phy.skb_mark = skb->mark; - ovs_ct_fill_key(skb, key); key->ovs_flow_hash = 0; res = key_extract_mac_proto(skb); if (res < 0) @@ -800,17 +799,26 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->mac_proto = res; key->recirc_id = 0; - return key_extract(skb, key); + err = key_extract(skb, key); + if (!err) + ovs_ct_fill_key(skb, key); /* Must be after key_extract(). */ + return err; } int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, struct sk_buff *skb, struct sw_flow_key *key, bool log) { + const struct nlattr *a[OVS_KEY_ATTR_MAX + 1]; + u64 attrs = 0; int err; + err = parse_flow_nlattrs(attr, a, &attrs, log); + if (err) + return -EINVAL; + /* Extract metadata from netlink attributes. */ - err = ovs_nla_get_flow_metadata(net, attr, key, log); + err = ovs_nla_get_flow_metadata(net, a, attrs, key, log); if (err) return err; @@ -824,5 +832,21 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, */ skb->protocol = key->eth.type; - return key_extract(skb, key); + err = key_extract(skb, key); + if (err) + return err; + + /* Check that we have conntrack original direction tuple metadata only + * for packets for which it makes sense. Otherwise the key may be + * corrupted due to overlapping key fields. + */ + if (attrs & (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4) && + key->eth.type != htons(ETH_P_IP)) + return -EINVAL; + if (attrs & (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6) && + (key->eth.type != htons(ETH_P_IPV6) || + sw_flow_key_is_nd(key))) + return -EINVAL; + + return 0; } diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index f61cae7f9030..76e05b25f030 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2014 Nicira, Inc. + * Copyright (c) 2007-2017 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -107,10 +107,16 @@ struct sw_flow_key { __be32 src; /* IP source address. */ __be32 dst; /* IP destination address. */ } addr; - struct { - u8 sha[ETH_ALEN]; /* ARP source hardware address. */ - u8 tha[ETH_ALEN]; /* ARP target hardware address. */ - } arp; + union { + struct { + __be32 src; + __be32 dst; + } ct_orig; /* Conntrack original direction fields. */ + struct { + u8 sha[ETH_ALEN]; /* ARP source hardware address. */ + u8 tha[ETH_ALEN]; /* ARP target hardware address. */ + } arp; + }; } ipv4; struct { struct { @@ -118,23 +124,44 @@ struct sw_flow_key { struct in6_addr dst; /* IPv6 destination address. */ } addr; __be32 label; /* IPv6 flow label. */ - struct { - struct in6_addr target; /* ND target address. */ - u8 sll[ETH_ALEN]; /* ND source link layer address. */ - u8 tll[ETH_ALEN]; /* ND target link layer address. */ - } nd; + union { + struct { + struct in6_addr src; + struct in6_addr dst; + } ct_orig; /* Conntrack original direction fields. */ + struct { + struct in6_addr target; /* ND target address. */ + u8 sll[ETH_ALEN]; /* ND source link layer address. */ + u8 tll[ETH_ALEN]; /* ND target link layer address. */ + } nd; + }; } ipv6; }; struct { /* Connection tracking fields. */ + u8 state; + u8 orig_proto; /* CT orig tuple IP protocol. */ u16 zone; u32 mark; - u8 state; + struct { + __be16 src; /* CT orig tuple tp src port. */ + __be16 dst; /* CT orig tuple tp dst port. */ + } orig_tp; + struct ovs_key_ct_labels labels; } ct; } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ +static inline bool sw_flow_key_is_nd(const struct sw_flow_key *key) +{ + return key->eth.type == htons(ETH_P_IPV6) && + key->ip.proto == NEXTHDR_ICMP && + key->tp.dst == 0 && + (key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) || + key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)); +} + struct sw_flow_key_range { unsigned short int start; unsigned short int end; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c87d359b9b37..989f38f120bb 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -129,7 +129,9 @@ static bool match_validate(const struct sw_flow_match *match, /* The following mask attributes allowed only if they * pass the validation tests. */ mask_allowed &= ~((1 << OVS_KEY_ATTR_IPV4) + | (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4) | (1 << OVS_KEY_ATTR_IPV6) + | (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6) | (1 << OVS_KEY_ATTR_TCP) | (1 << OVS_KEY_ATTR_TCP_FLAGS) | (1 << OVS_KEY_ATTR_UDP) @@ -161,8 +163,10 @@ static bool match_validate(const struct sw_flow_match *match, if (match->key->eth.type == htons(ETH_P_IP)) { key_expected |= 1 << OVS_KEY_ATTR_IPV4; - if (match->mask && (match->mask->key.eth.type == htons(0xffff))) + if (match->mask && match->mask->key.eth.type == htons(0xffff)) { mask_allowed |= 1 << OVS_KEY_ATTR_IPV4; + mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4; + } if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) { if (match->key->ip.proto == IPPROTO_UDP) { @@ -196,8 +200,10 @@ static bool match_validate(const struct sw_flow_match *match, if (match->key->eth.type == htons(ETH_P_IPV6)) { key_expected |= 1 << OVS_KEY_ATTR_IPV6; - if (match->mask && (match->mask->key.eth.type == htons(0xffff))) + if (match->mask && match->mask->key.eth.type == htons(0xffff)) { mask_allowed |= 1 << OVS_KEY_ATTR_IPV6; + mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6; + } if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) { if (match->key->ip.proto == IPPROTO_UDP) { @@ -230,6 +236,12 @@ static bool match_validate(const struct sw_flow_match *match, htons(NDISC_NEIGHBOUR_SOLICITATION) || match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { key_expected |= 1 << OVS_KEY_ATTR_ND; + /* Original direction conntrack tuple + * uses the same space as the ND fields + * in the key, so both are not allowed + * at the same time. + */ + mask_allowed &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6); if (match->mask && (match->mask->key.tp.src == htons(0xff))) mask_allowed |= 1 << OVS_KEY_ATTR_ND; } @@ -282,7 +294,7 @@ size_t ovs_key_attr_size(void) /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 26); + BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 28); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -295,6 +307,7 @@ size_t ovs_key_attr_size(void) + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + + nla_total_size(40) /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -355,6 +368,10 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) }, + [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4] = { + .len = sizeof(struct ovs_key_ct_tuple_ipv4) }, + [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = { + .len = sizeof(struct ovs_key_ct_tuple_ipv6) }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -430,9 +447,8 @@ static int parse_flow_mask_nlattrs(const struct nlattr *attr, return __parse_flow_nlattrs(attr, a, attrsp, log, true); } -static int parse_flow_nlattrs(const struct nlattr *attr, - const struct nlattr *a[], u64 *attrsp, - bool log) +int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[], + u64 *attrsp, bool log) { return __parse_flow_nlattrs(attr, a, attrsp, log, false); } @@ -1082,6 +1098,34 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, sizeof(*cl), is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS); } + if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4)) { + const struct ovs_key_ct_tuple_ipv4 *ct; + + ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4]); + + SW_FLOW_KEY_PUT(match, ipv4.ct_orig.src, ct->ipv4_src, is_mask); + SW_FLOW_KEY_PUT(match, ipv4.ct_orig.dst, ct->ipv4_dst, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_proto, ct->ipv4_proto, is_mask); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4); + } + if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)) { + const struct ovs_key_ct_tuple_ipv6 *ct; + + ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6]); + + SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.src, &ct->ipv6_src, + sizeof(match->key->ipv6.ct_orig.src), + is_mask); + SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.dst, &ct->ipv6_dst, + sizeof(match->key->ipv6.ct_orig.dst), + is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_proto, ct->ipv6_proto, is_mask); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6); + } /* For layer 3 packets the Ethernet type is provided * and treated as metadata but no MAC addresses are provided. @@ -1493,9 +1537,12 @@ u32 ovs_nla_get_ufid_flags(const struct nlattr *attr) /** * ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key. - * @key: Receives extracted in_port, priority, tun_key and skb_mark. - * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute - * sequence. + * @net: Network namespace. + * @key: Receives extracted in_port, priority, tun_key, skb_mark and conntrack + * metadata. + * @a: Array of netlink attributes holding parsed %OVS_KEY_ATTR_* Netlink + * attributes. + * @attrs: Bit mask for the netlink attributes included in @a. * @log: Boolean to allow kernel error logging. Normally true, but when * probing for feature compatibility this should be passed in as false to * suppress unnecessary error logging. @@ -1504,25 +1551,23 @@ u32 ovs_nla_get_ufid_flags(const struct nlattr *attr) * take the same form accepted by flow_from_nlattrs(), but only enough of it to * get the metadata, that is, the parts of the flow key that cannot be * extracted from the packet itself. + * + * This must be called before the packet key fields are filled in 'key'. */ -int ovs_nla_get_flow_metadata(struct net *net, const struct nlattr *attr, - struct sw_flow_key *key, - bool log) +int ovs_nla_get_flow_metadata(struct net *net, + const struct nlattr *a[OVS_KEY_ATTR_MAX + 1], + u64 attrs, struct sw_flow_key *key, bool log) { - const struct nlattr *a[OVS_KEY_ATTR_MAX + 1]; struct sw_flow_match match; - u64 attrs = 0; - int err; - - err = parse_flow_nlattrs(attr, a, &attrs, log); - if (err) - return -EINVAL; memset(&match, 0, sizeof(match)); match.key = key; memset(&key->ct, 0, sizeof(key->ct)); + memset(&key->ipv4.ct_orig, 0, sizeof(key->ipv4.ct_orig)); + memset(&key->ipv6.ct_orig, 0, sizeof(key->ipv6.ct_orig)); + key->phy.in_port = DP_MAX_PORTS; return metadata_from_nlattrs(net, &match, &attrs, a, false, log); @@ -1584,7 +1629,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, output->phy.skb_mark)) goto nla_put_failure; - if (ovs_ct_put_key(output, skb)) + if (ovs_ct_put_key(swkey, output, skb)) goto nla_put_failure; if (ovs_key_mac_proto(swkey) == MAC_PROTO_ETHERNET) { diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 45f9769e5aac..929c665ac3aa 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -46,8 +46,11 @@ void ovs_match_init(struct sw_flow_match *match, int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *, int attr, bool is_mask, struct sk_buff *); -int ovs_nla_get_flow_metadata(struct net *, const struct nlattr *, - struct sw_flow_key *, bool log); +int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[], + u64 *attrsp, bool log); +int ovs_nla_get_flow_metadata(struct net *net, + const struct nlattr *a[OVS_KEY_ATTR_MAX + 1], + u64 attrs, struct sw_flow_key *key, bool log); int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb); -- cgit From dd41d33f0b033885211a5d6f3ee19e73238aa9ee Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Thu, 9 Feb 2017 11:22:00 -0800 Subject: openvswitch: Add force commit. Stateful network admission policy may allow connections to one direction and reject connections initiated in the other direction. After policy change it is possible that for a new connection an overlapping conntrack entry already exists, where the original direction of the existing connection is opposed to the new connection's initial packet. Most importantly, conntrack state relating to the current packet gets the "reply" designation based on whether the original direction tuple or the reply direction tuple matched. If this "directionality" is wrong w.r.t. to the stateful network admission policy it may happen that packets in neither direction are correctly admitted. This patch adds a new "force commit" option to the OVS conntrack action that checks the original direction of an existing conntrack entry. If that direction is opposed to the current packet, the existing conntrack entry is deleted and a new one is subsequently created in the correct direction. Signed-off-by: Jarno Rajahalme Acked-by: Pravin B Shelar Acked-by: Joe Stringer Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 5 +++++ net/openvswitch/conntrack.c | 26 ++++++++++++++++++++++++-- 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 90af8b8e10f8..7f41f7d0000f 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -674,6 +674,10 @@ struct ovs_action_hash { * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG. * @OVS_CT_ATTR_NAT: Nested OVS_NAT_ATTR_* for performing L3 network address * translation (NAT) on the packet. + * @OVS_CT_ATTR_FORCE_COMMIT: Like %OVS_CT_ATTR_COMMIT, but instead of doing + * nothing if the connection is already committed will check that the current + * packet is in conntrack entry's original direction. If directionality does + * not match, will delete the existing conntrack entry and commit a new one. */ enum ovs_ct_attr { OVS_CT_ATTR_UNSPEC, @@ -684,6 +688,7 @@ enum ovs_ct_attr { OVS_CT_ATTR_HELPER, /* netlink helper to assist detection of related connections. */ OVS_CT_ATTR_NAT, /* Nested OVS_NAT_ATTR_* */ + OVS_CT_ATTR_FORCE_COMMIT, /* No argument */ __OVS_CT_ATTR_MAX }; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index bfd7606c8be1..8b15bab70583 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -65,6 +65,7 @@ struct ovs_conntrack_info { struct nf_conn *ct; u8 commit : 1; u8 nat : 3; /* enum ovs_ct_nat */ + u8 force : 1; u16 family; struct md_mark mark; struct md_labels labels; @@ -613,10 +614,13 @@ static bool skb_nfct_cached(struct net *net, */ if (!ct && key->ct.state & OVS_CS_F_TRACKED && !(key->ct.state & OVS_CS_F_INVALID) && - key->ct.zone == info->zone.id) + key->ct.zone == info->zone.id) { ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, !!(key->ct.state & OVS_CS_F_NAT_MASK)); + if (ct) + nf_ct_get(skb, &ctinfo); + } if (!ct) return false; if (!net_eq(net, read_pnet(&ct->ct_net))) @@ -630,6 +634,18 @@ static bool skb_nfct_cached(struct net *net, if (help && rcu_access_pointer(help->helper) != info->helper) return false; } + /* Force conntrack entry direction to the current packet? */ + if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { + /* Delete the conntrack entry if confirmed, else just release + * the reference. + */ + if (nf_ct_is_confirmed(ct)) + nf_ct_delete(ct, 0, 0); + else + nf_conntrack_put(&ct->ct_general); + nf_ct_set(skb, NULL, 0); + return false; + } return true; } @@ -1207,6 +1223,7 @@ static int parse_nat(const struct nlattr *attr, static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, + [OVS_CT_ATTR_FORCE_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), @@ -1246,6 +1263,9 @@ 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. */ case OVS_CT_ATTR_COMMIT: info->commit = true; break; @@ -1472,7 +1492,9 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, if (!start) return -EMSGSIZE; - if (ct_info->commit && nla_put_flag(skb, OVS_CT_ATTR_COMMIT)) + if (ct_info->commit && nla_put_flag(skb, ct_info->force + ? OVS_CT_ATTR_FORCE_COMMIT + : OVS_CT_ATTR_COMMIT)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) -- cgit