X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=datapath%2Flinux%2Fcompat%2Fgeneve.c;h=5b183963d637884902439a87a66598b687ffcee5;hb=9cfa471811be29e88ca89dc698690611cea1707a;hp=50ed3936d03840310b936076ca47a33c33e68021;hpb=06f1a61a87182edc3a6c3a6f6420ab9f2012b2d3;p=mirror_ovs.git diff --git a/datapath/linux/compat/geneve.c b/datapath/linux/compat/geneve.c index 50ed3936d..5b183963d 100644 --- a/datapath/linux/compat/geneve.c +++ b/datapath/linux/compat/geneve.c @@ -16,19 +16,32 @@ #include #include #include +#include +#include +#include #include #include #include #include #include #include +#include +#include +#if IS_ENABLED(CONFIG_IPV6) +#include +#include +#include +#include +#endif + #include "gso.h" #include "vport-netdev.h" #include "compat.h" -#ifndef HAVE_METADATA_DST +#ifndef USE_UPSTREAM_TUNNEL + #define GENEVE_NETDEV_VER "0.6" #define GENEVE_UDP_PORT 6081 @@ -50,31 +63,51 @@ struct geneve_net { static int geneve_net_id; +union geneve_addr { + struct sockaddr_in sin; + struct sockaddr_in6 sin6; + struct sockaddr sa; +}; + +static union geneve_addr geneve_remote_unspec = { .sa.sa_family = AF_UNSPEC, }; + /* Pseudo network device */ struct geneve_dev { struct hlist_node hlist; /* vni hash table */ struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for geneve tunnel */ - struct geneve_sock *sock; /* socket used for geneve tunnel */ + struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */ +#if IS_ENABLED(CONFIG_IPV6) + struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */ +#endif u8 vni[3]; /* virtual network ID for tunnel */ u8 ttl; /* TTL override */ u8 tos; /* TOS override */ - struct sockaddr_in remote; /* IPv4 address for link partner */ + union geneve_addr remote; /* IP address for link partner */ struct list_head next; /* geneve's per namespace list */ + __be32 label; /* IPv6 flowlabel override */ __be16 dst_port; bool collect_md; + u32 flags; + struct dst_cache dst_cache; }; +/* Geneve device flags */ +#define GENEVE_F_UDP_ZERO_CSUM_TX BIT(0) +#define GENEVE_F_UDP_ZERO_CSUM6_TX BIT(1) +#define GENEVE_F_UDP_ZERO_CSUM6_RX BIT(2) + struct geneve_sock { bool collect_md; struct list_head list; struct socket *sock; struct rcu_head rcu; int refcnt; + struct hlist_head vni_list[VNI_HASH_SIZE]; + u32 flags; #ifdef HAVE_UDP_OFFLOAD struct udp_offload udp_offloads; #endif - struct hlist_head vni_list[VNI_HASH_SIZE]; }; static inline __u32 geneve_net_vni_hash(u8 vni[3]) @@ -96,6 +129,11 @@ static __be64 vni_to_tunnel_id(const __u8 *vni) #endif } +static sa_family_t geneve_get_sk_family(struct geneve_sock *gs) +{ + return gs->sock->sk->sk_family; +} + static struct geneve_dev *geneve_lookup(struct geneve_sock *gs, __be32 addr, u8 vni[]) { @@ -108,50 +146,95 @@ static struct geneve_dev *geneve_lookup(struct geneve_sock *gs, vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) { if (!memcmp(vni, geneve->vni, sizeof(geneve->vni)) && - addr == geneve->remote.sin_addr.s_addr) + addr == geneve->remote.sin.sin_addr.s_addr) return geneve; } return NULL; } +#if IS_ENABLED(CONFIG_IPV6) +static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs, + struct in6_addr addr6, u8 vni[]) +{ + struct hlist_head *vni_list_head; + struct geneve_dev *geneve; + __u32 hash; + + /* Find the device for this VNI */ + hash = geneve_net_vni_hash(vni); + vni_list_head = &gs->vni_list[hash]; + hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) { + if (!memcmp(vni, geneve->vni, sizeof(geneve->vni)) && + ipv6_addr_equal(&addr6, &geneve->remote.sin6.sin6_addr)) + return geneve; + } + return NULL; +} +#endif + static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) { return (struct genevehdr *)(udp_hdr(skb) + 1); } -/* geneve receive/decap routine */ -static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb) +static struct geneve_dev *geneve_lookup_skb(struct geneve_sock *gs, + struct sk_buff *skb) { - struct genevehdr *gnvh = geneve_hdr(skb); - struct metadata_dst *tun_dst; - struct geneve_dev *geneve = NULL; -#ifdef HAVE_DEV_TSTATS - struct pcpu_sw_netstats *stats; -#endif - struct iphdr *iph; u8 *vni; __be32 addr; - int err; - union { - struct metadata_dst dst; - char buf[sizeof(struct metadata_dst) + 256]; - } buf; + static u8 zero_vni[3]; +#if IS_ENABLED(CONFIG_IPV6) + static struct in6_addr zero_addr6; +#endif - iph = ip_hdr(skb); /* outer IP header... */ + if (geneve_get_sk_family(gs) == AF_INET) { + struct iphdr *iph; - if (gs->collect_md) { - static u8 zero_vni[3]; + iph = ip_hdr(skb); /* outer IP header... */ - vni = zero_vni; - addr = 0; - } else { - vni = gnvh->vni; - addr = iph->saddr; + if (gs->collect_md) { + vni = zero_vni; + addr = 0; + } else { + vni = geneve_hdr(skb)->vni; + addr = iph->saddr; + } + + return geneve_lookup(gs, addr, vni); +#if IS_ENABLED(CONFIG_IPV6) + } else if (geneve_get_sk_family(gs) == AF_INET6) { + struct ipv6hdr *ip6h; + struct in6_addr addr6; + + ip6h = ipv6_hdr(skb); /* outer IPv6 header... */ + + if (gs->collect_md) { + vni = zero_vni; + addr6 = zero_addr6; + } else { + vni = geneve_hdr(skb)->vni; + addr6 = ip6h->saddr; + } + + return geneve6_lookup(gs, addr6, vni); +#endif } + return NULL; +} - geneve = geneve_lookup(gs, addr, vni); - if (!geneve) - goto drop; +/* geneve receive/decap routine */ +static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, + struct sk_buff *skb) +{ + struct genevehdr *gnvh = geneve_hdr(skb); + struct metadata_dst *tun_dst = NULL; + struct pcpu_sw_netstats *stats; + int err = 0; + void *oiph; + union { + struct metadata_dst dst; + char buf[sizeof(struct metadata_dst) + 256]; + } buf; if (ip_tunnel_collect_metadata() || gs->collect_md) { __be16 flags; @@ -161,119 +244,145 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb) (gnvh->critical ? TUNNEL_CRIT_OPT : 0); tun_dst = &buf.dst; - ovs_udp_tun_rx_dst(&tun_dst->u.tun_info, skb, AF_INET, flags, - vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4); + ovs_udp_tun_rx_dst(tun_dst, + skb, geneve_get_sk_family(gs), flags, + vni_to_tunnel_id(gnvh->vni), + gnvh->opt_len * 4); + if (!tun_dst) + goto drop; /* Update tunnel dst according to Geneve options. */ ip_tunnel_info_opts_set(&tun_dst->u.tun_info, - gnvh->options, gnvh->opt_len * 4); + gnvh->options, gnvh->opt_len * 4, + TUNNEL_GENEVE_OPT); } else { /* Drop packets w/ critical options, * since we don't support any... */ - tun_dst = NULL; if (gnvh->critical) goto drop; } skb_reset_mac_header(skb); - skb_scrub_packet(skb, !net_eq(geneve->net, dev_net(geneve->dev))); skb->protocol = eth_type_trans(skb, geneve->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); if (tun_dst) ovs_skb_dst_set(skb, &tun_dst->dst); - else - goto drop; + /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) goto drop; + oiph = skb_network_header(skb); skb_reset_network_header(skb); - err = IP_ECN_decapsulate(iph, skb); - - if (unlikely(err)) { - if (err > 1) { - ++geneve->dev->stats.rx_frame_errors; - ++geneve->dev->stats.rx_errors; - goto drop; - } + if (geneve_get_sk_family(gs) == AF_INET) + err = IP_ECN_decapsulate(oiph, skb); +#if IS_ENABLED(CONFIG_IPV6) + else + err = IP6_ECN_decapsulate(oiph, skb); +#endif + if (unlikely(err > 1)) { + ++geneve->dev->stats.rx_frame_errors; + ++geneve->dev->stats.rx_errors; + goto drop; } -#ifdef HAVE_DEV_TSTATS - stats = this_cpu_ptr((struct pcpu_sw_netstats __percpu *)geneve->dev->tstats); + stats = this_cpu_ptr(geneve->dev->tstats); u64_stats_update_begin(&stats->syncp); stats->rx_packets++; stats->rx_bytes += skb->len; u64_stats_update_end(&stats->syncp); -#endif - netdev_port_receive(skb, &tun_dst->u.tun_info); + + netdev_port_receive(skb, skb_tunnel_info(skb)); return; drop: /* Consume bad packet */ kfree_skb(skb); } -#ifdef HAVE_DEV_TSTATS /* Setup stats when device is created */ static int geneve_init(struct net_device *dev) { - dev->tstats = (typeof(dev->tstats)) netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + struct geneve_dev *geneve = netdev_priv(dev); + int err; + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + err = dst_cache_init(&geneve->dst_cache, GFP_KERNEL); + if (err) { + free_percpu(dev->tstats); + return err; + } + return 0; } static void geneve_uninit(struct net_device *dev) { + struct geneve_dev *geneve = netdev_priv(dev); + + dst_cache_destroy(&geneve->dst_cache); free_percpu(dev->tstats); } -#endif /* Callback from net/ipv4/udp.c to receive packets */ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; + struct geneve_dev *geneve; struct geneve_sock *gs; int opts_len; /* Need Geneve and inner Ethernet header to be present */ if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN))) - goto error; + goto drop; /* Return packets with reserved bits set */ geneveh = geneve_hdr(skb); if (unlikely(geneveh->ver != GENEVE_VER)) - goto error; + goto drop; if (unlikely(geneveh->proto_type != htons(ETH_P_TEB))) - goto error; - - opts_len = geneveh->opt_len * 4; - if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, - htons(ETH_P_TEB))) goto drop; gs = rcu_dereference_sk_user_data(sk); if (!gs) goto drop; - geneve_rx(gs, skb); +#if IS_ENABLED(CONFIG_IPV6) +#ifdef OVS_CHECK_UDP_TUNNEL_ZERO_CSUM + if (geneve_get_sk_family(gs) == AF_INET6 && + !udp_hdr(skb)->check && + !(gs->flags & GENEVE_F_UDP_ZERO_CSUM6_RX)) { + udp6_csum_zero_error(skb); + goto drop; + } +#endif +#endif + geneve = geneve_lookup_skb(gs, skb); + if (!geneve) + goto drop; + + opts_len = geneveh->opt_len * 4; + if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, + htons(ETH_P_TEB), + !net_eq(geneve->net, dev_net(geneve->dev)))) + goto drop; + + geneve_rx(geneve, gs, skb); return 0; drop: /* Consume bad packet */ kfree_skb(skb); return 0; - -error: - /* Let the UDP layer deal with the skb */ - return 1; } static struct socket *geneve_create_sock(struct net *net, bool ipv6, - __be16 port) + __be16 port, u32 flags) { struct socket *sock; struct udp_port_cfg udp_conf; @@ -283,6 +392,9 @@ static struct socket *geneve_create_sock(struct net *net, bool ipv6, if (ipv6) { udp_conf.family = AF_INET6; + udp_conf.ipv6_v6only = 1; + udp_conf.use_udp6_rx_checksums = + !(flags & GENEVE_F_UDP_ZERO_CSUM6_RX); } else { udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = htonl(INADDR_ANY); @@ -298,21 +410,77 @@ static struct socket *geneve_create_sock(struct net *net, bool ipv6, return sock; } -#ifdef HAVE_UDP_OFFLOAD static void geneve_notify_add_rx_port(struct geneve_sock *gs) { + struct net_device *dev; struct sock *sk = gs->sock->sk; - sa_family_t sa_family = sk->sk_family; + struct net *net = sock_net(sk); + sa_family_t sa_family = geneve_get_sk_family(gs); int err; if (sa_family == AF_INET) { - err = udp_add_offload(&gs->udp_offloads); + err = udp_add_offload(sock_net(sk), &gs->udp_offloads); if (err) pr_warn("geneve: udp_add_offload failed with status %d\n", err); } + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { +#ifdef HAVE_NDO_ADD_GENEVE_PORT + __be16 port = inet_sk(sk)->inet_sport; + + if (dev->netdev_ops->ndo_add_geneve_port) + dev->netdev_ops->ndo_add_geneve_port(dev, sa_family, + port); +#elif defined(HAVE_NDO_UDP_TUNNEL_ADD) + struct udp_tunnel_info ti; + ti.type = UDP_TUNNEL_TYPE_GENEVE; + ti.sa_family = sa_family; + ti.port = inet_sk(sk)->inet_sport; + + if (dev->netdev_ops->ndo_udp_tunnel_add) + dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti); +#endif + } + rcu_read_unlock(); } +static void geneve_notify_del_rx_port(struct geneve_sock *gs) +{ + struct net_device *dev; + struct sock *sk = gs->sock->sk; + struct net *net = sock_net(sk); + sa_family_t sa_family = geneve_get_sk_family(gs); + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { +#ifdef HAVE_NDO_ADD_GENEVE_PORT + __be16 port = inet_sk(sk)->inet_sport; + + if (dev->netdev_ops->ndo_del_geneve_port) + dev->netdev_ops->ndo_del_geneve_port(dev, sa_family, + port); +#elif defined(HAVE_NDO_UDP_TUNNEL_ADD) + struct udp_tunnel_info ti; + ti.type = UDP_TUNNEL_TYPE_GENEVE; + ti.port = inet_sk(sk)->inet_sport; + ti.sa_family = sa_family; + + if (dev->netdev_ops->ndo_udp_tunnel_del) + dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti); +#endif + } + + rcu_read_unlock(); + + if (sa_family == AF_INET) + udp_del_offload(&gs->udp_offloads); +} + +#if defined(HAVE_UDP_OFFLOAD) || \ + defined(HAVE_UDP_TUNNEL_SOCK_CFG_GRO_RECEIVE) + static int geneve_hlen(struct genevehdr *gh) { return sizeof(*gh) + gh->opt_len * 4; @@ -354,8 +522,6 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head, goto out; } - flush = 0; - for (p = *head; p; p = p->next) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -372,14 +538,13 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head, rcu_read_lock(); ptype = gro_find_receive_by_type(type); - if (!ptype) { - flush = 1; + if (!ptype) goto out_unlock; - } skb_gro_pull(skb, gh_len); skb_gro_postpull_rcsum(skb, gh, gh_len); pp = ptype->callbacks.gro_receive(head, skb); + flush = 0; out_unlock: rcu_read_unlock(); @@ -414,13 +579,15 @@ static int geneve_gro_complete(struct sk_buff *skb, int nhoff, err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); rcu_read_unlock(); + + skb_set_inner_mac_header(skb, nhoff + gh_len); return err; } #endif /* Create new listen socket if needed */ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, - bool ipv6) + bool ipv6, u32 flags) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; @@ -432,7 +599,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, if (!gs) return ERR_PTR(-ENOMEM); - sock = geneve_create_sock(net, ipv6, port); + sock = geneve_create_sock(net, ipv6, port, flags); if (IS_ERR(sock)) { kfree(gs); return ERR_CAST(sock); @@ -448,11 +615,17 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, gs->udp_offloads.port = port; gs->udp_offloads.callbacks.gro_receive = geneve_gro_receive; gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete; - geneve_notify_add_rx_port(gs); #endif + + geneve_notify_add_rx_port(gs); /* Mark socket as an encapsulation socket */ + memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = gs; tunnel_cfg.encap_type = 1; +#ifdef HAVE_UDP_TUNNEL_SOCK_CFG_GRO_RECEIVE + tunnel_cfg.gro_receive = geneve_gro_receive; + tunnel_cfg.gro_complete = geneve_gro_complete; +#endif tunnel_cfg.encap_rcv = geneve_udp_encap_recv; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, sock, &tunnel_cfg); @@ -460,125 +633,174 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, return gs; } -static void geneve_notify_del_rx_port(struct geneve_sock *gs) +static void __geneve_sock_release(struct geneve_sock *gs) { -#ifdef HAVE_UDP_OFFLOAD - struct sock *sk = gs->sock->sk; - sa_family_t sa_family = sk->sk_family; + if (!gs || --gs->refcnt) + return; - if (sa_family == AF_INET) - udp_del_offload(&gs->udp_offloads); -#endif + list_del(&gs->list); + geneve_notify_del_rx_port(gs); + udp_tunnel_sock_release(gs->sock); + kfree_rcu(gs, rcu); } -static void free_gs_rcu(struct rcu_head *rcu) +static void geneve_sock_release(struct geneve_dev *geneve) { - struct geneve_sock *gs = container_of(rcu, struct geneve_sock, rcu); + struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4); +#if IS_ENABLED(CONFIG_IPV6) + struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6); - kfree(gs); -} + rcu_assign_pointer(geneve->sock6, NULL); +#endif -static void geneve_sock_release(struct geneve_sock *gs) -{ - if (--gs->refcnt) - return; + rcu_assign_pointer(geneve->sock4, NULL); + synchronize_net(); - list_del(&gs->list); - geneve_notify_del_rx_port(gs); - udp_tunnel_sock_release(gs->sock); - call_rcu(&gs->rcu, free_gs_rcu); + __geneve_sock_release(gs4); +#if IS_ENABLED(CONFIG_IPV6) + __geneve_sock_release(gs6); +#endif } static struct geneve_sock *geneve_find_sock(struct geneve_net *gn, + sa_family_t family, __be16 dst_port) { struct geneve_sock *gs; list_for_each_entry(gs, &gn->sock_list, list) { - if (inet_sport(gs->sock->sk) == dst_port && - inet_sk(gs->sock->sk)->sk.sk_family == AF_INET) { + if (inet_sk(gs->sock->sk)->inet_sport == dst_port && + geneve_get_sk_family(gs) == family) { return gs; } } return NULL; } -static int geneve_open(struct net_device *dev) +static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) { - struct geneve_dev *geneve = netdev_priv(dev); struct net *net = geneve->net; struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; __u32 hash; - gs = geneve_find_sock(gn, geneve->dst_port); + gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET, geneve->dst_port); if (gs) { gs->refcnt++; goto out; } - gs = geneve_socket_create(net, geneve->dst_port, false); + gs = geneve_socket_create(net, geneve->dst_port, ipv6, geneve->flags); if (IS_ERR(gs)) return PTR_ERR(gs); out: gs->collect_md = geneve->collect_md; - geneve->sock = gs; + gs->flags = geneve->flags; +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6) + rcu_assign_pointer(geneve->sock6, gs); + else +#endif + rcu_assign_pointer(geneve->sock4, gs); hash = geneve_net_vni_hash(geneve->vni); hlist_add_head_rcu(&geneve->hlist, &gs->vni_list[hash]); return 0; } +static int geneve_open(struct net_device *dev) +{ + struct geneve_dev *geneve = netdev_priv(dev); + bool ipv6 = geneve->remote.sa.sa_family == AF_INET6; + bool metadata = geneve->collect_md; + int ret = 0; + +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6 || metadata) + ret = geneve_sock_add(geneve, true); +#endif + + if (!ret && (!ipv6 || metadata)) + ret = geneve_sock_add(geneve, false); + if (ret < 0) + geneve_sock_release(geneve); + + return ret; +} + static int geneve_stop(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); - struct geneve_sock *gs = geneve->sock; if (!hlist_unhashed(&geneve->hlist)) hlist_del_rcu(&geneve->hlist); - geneve_sock_release(gs); + geneve_sock_release(geneve); + return 0; +} + +static void geneve_build_header(struct genevehdr *geneveh, + __be16 tun_flags, u8 vni[3], + u8 options_len, u8 *options) +{ + geneveh->ver = GENEVE_VER; + geneveh->opt_len = options_len / 4; + geneveh->oam = !!(tun_flags & TUNNEL_OAM); + geneveh->critical = !!(tun_flags & TUNNEL_CRIT_OPT); + geneveh->rsvd1 = 0; + memcpy(geneveh->vni, vni, 3); + geneveh->proto_type = htons(ETH_P_TEB); + geneveh->rsvd2 = 0; + + memcpy(geneveh->options, options, options_len); +} + +static int push_vlan_tag(struct sk_buff *skb) +{ + if (skb_vlan_tag_present(skb)) { + __be16 vlan_proto = skb->vlan_proto; + int err; + + err = __vlan_insert_tag(skb, skb->vlan_proto, + skb_vlan_tag_get(skb)); + + if (unlikely(err)) + return err; + skb->vlan_tci = 0; + skb->protocol = vlan_proto; + } return 0; } static int geneve_build_skb(struct rtable *rt, struct sk_buff *skb, __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, - bool csum) + u32 flags, bool xnet) { struct genevehdr *gnvh; int min_headroom; int err; + bool udp_sum = !(flags & GENEVE_F_UDP_ZERO_CSUM_TX); - min_headroom = LL_RESERVED_SPACE(rt_dst(rt).dev) + rt_dst(rt).header_len + skb_scrub_packet(skb, xnet); + + min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr) + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); + err = skb_cow_head(skb, min_headroom); - if (unlikely(err)) { - kfree_skb(skb); + if (unlikely(err)) goto free_rt; - } - skb = vlan_hwaccel_push_inside(skb); - if (!skb) { - err = -ENOMEM; + err = push_vlan_tag(skb); + if (unlikely(err)) goto free_rt; - } - skb = udp_tunnel_handle_offloads(skb, csum, 0, false); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); + err = udp_tunnel_handle_offloads(skb, udp_sum); + if (err) goto free_rt; - } + gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); - gnvh->ver = GENEVE_VER; - gnvh->opt_len = opt_len / 4; - gnvh->oam = !!(tun_flags & TUNNEL_OAM); - gnvh->critical = !!(tun_flags & TUNNEL_CRIT_OPT); - gnvh->rsvd1 = 0; - memcpy(gnvh->vni, vni, 3); - gnvh->proto_type = htons(ETH_P_TEB); - gnvh->rsvd2 = 0; - memcpy(gnvh->options, opt, opt_len); + geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); ovs_skb_set_inner_protocol(skb, htons(ETH_P_TEB)); return 0; @@ -588,50 +810,182 @@ free_rt: return err; } -static struct rtable *geneve_get_rt(struct sk_buff *skb, - struct net_device *dev, - struct flowi4 *fl4, - struct ip_tunnel_info *info) +#if IS_ENABLED(CONFIG_IPV6) +static int geneve6_build_skb(struct dst_entry *dst, struct sk_buff *skb, + __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, + u32 flags, bool xnet) +{ + struct genevehdr *gnvh; + int min_headroom; + int err; + bool udp_sum = !(flags & GENEVE_F_UDP_ZERO_CSUM6_TX); + + skb_scrub_packet(skb, xnet); + + min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + + GENEVE_BASE_HLEN + opt_len + sizeof(struct ipv6hdr) + + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); + + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + goto free_dst; + + err = push_vlan_tag(skb); + if (unlikely(err)) + goto free_dst; + + err = udp_tunnel_handle_offloads(skb, udp_sum); + if (err) + goto free_dst; + + gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); + geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); + + ovs_skb_set_inner_protocol(skb, htons(ETH_P_TEB)); + return 0; + +free_dst: + dst_release(dst); + return err; +} +#endif + +static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, + struct net_device *dev, + struct flowi4 *fl4, + struct ip_tunnel_info *info, + __be16 dport, __be16 sport) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); + struct dst_cache *dst_cache; struct rtable *rt = NULL; __u8 tos; + if (!rcu_dereference(geneve->sock4)) + return ERR_PTR(-EIO); + memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_mark = skb->mark; fl4->flowi4_proto = IPPROTO_UDP; + fl4->fl4_dport = dport; + fl4->fl4_sport = sport; if (info) { fl4->daddr = info->key.u.ipv4.dst; fl4->saddr = info->key.u.ipv4.src; fl4->flowi4_tos = RT_TOS(info->key.tos); + dst_cache = &info->dst_cache; } else { tos = geneve->tos; if (tos == 1) { const struct iphdr *iip = ip_hdr(skb); tos = ip_tunnel_get_dsfield(iip, skb); + use_cache = false; } fl4->flowi4_tos = RT_TOS(tos); - fl4->daddr = geneve->remote.sin_addr.s_addr; + fl4->daddr = geneve->remote.sin.sin_addr.s_addr; + dst_cache = &geneve->dst_cache; + } + + if (use_cache) { + rt = dst_cache_get_ip4(dst_cache, &fl4->saddr); + if (rt) + return rt; } rt = ip_route_output_key(geneve->net, fl4); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &fl4->daddr); - dev->stats.tx_carrier_errors++; - return rt; + return ERR_PTR(-ENETUNREACH); } - if (rt_dst(rt).dev == dev) { /* is this necessary? */ + if (rt->dst.dev == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI4\n", &fl4->daddr); - dev->stats.collisions++; ip_rt_put(rt); - return ERR_PTR(-EINVAL); + return ERR_PTR(-ELOOP); } + if (use_cache) + dst_cache_set_ip4(dst_cache, &rt->dst, fl4->saddr); return rt; } +#if IS_ENABLED(CONFIG_IPV6) +static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, + struct net_device *dev, + struct flowi6 *fl6, + struct ip_tunnel_info *info, + __be16 dport, __be16 sport) +{ + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); + struct geneve_dev *geneve = netdev_priv(dev); + struct dst_entry *dst = NULL; + struct dst_cache *dst_cache; + struct geneve_sock *gs6; + __u8 prio; + + gs6 = rcu_dereference(geneve->sock6); + if (!gs6) + return ERR_PTR(-EIO); + + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_mark = skb->mark; + fl6->flowi6_proto = IPPROTO_UDP; + fl6->fl6_dport = dport; + fl6->fl6_sport = sport; + + if (info) { + fl6->daddr = info->key.u.ipv6.dst; + fl6->saddr = info->key.u.ipv6.src; + fl6->flowlabel = ip6_make_flowinfo(RT_TOS(info->key.tos), + info->key.label); + dst_cache = &info->dst_cache; + } else { + prio = geneve->tos; + if (prio == 1) { + const struct iphdr *iip = ip_hdr(skb); + + prio = ip_tunnel_get_dsfield(iip, skb); + use_cache = false; + } + + fl6->flowlabel = ip6_make_flowinfo(RT_TOS(prio), + geneve->label); + fl6->daddr = geneve->remote.sin6.sin6_addr; + dst_cache = &geneve->dst_cache; + } + + if (use_cache) { + dst = dst_cache_get_ip6(dst_cache, &fl6->saddr); + if (dst) + return dst; + } + +#ifdef HAVE_IPV6_DST_LOOKUP_NET + if (ipv6_stub->ipv6_dst_lookup(geneve->net, gs6->sock->sk, &dst, fl6)) { +#else +#ifdef HAVE_IPV6_STUB + if (ipv6_stub->ipv6_dst_lookup(gs6->sock->sk, &dst, fl6)) { +#else + if (ip6_dst_lookup(gs6->sock->sk, &dst, fl6)) { +#endif +#endif + netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr); + return ERR_PTR(-ENETUNREACH); + } + if (dst->dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI6\n", &fl6->daddr); + dst_release(dst); + return ERR_PTR(-ELOOP); + } + + if (use_cache) + dst_cache_set_ip6(dst_cache, dst, &fl6->saddr); + return dst; +} +#endif + /* Convert 64 bit tunnel ID to 24 bit VNI. */ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) { @@ -646,24 +1000,27 @@ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) #endif } -netdev_tx_t rpl_geneve_xmit(struct sk_buff *skb) +static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, + struct ip_tunnel_info *info) { - struct net_device *dev = skb->dev; struct geneve_dev *geneve = netdev_priv(dev); - struct geneve_sock *gs = geneve->sock; - struct ip_tunnel_info *info = NULL; + struct geneve_sock *gs4; struct rtable *rt = NULL; const struct iphdr *iip; /* interior IP header */ + int err = -EINVAL; struct flowi4 fl4; __u8 tos, ttl; __be16 sport; - bool udp_csum; __be16 df; - int err; + bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); + u32 flags = geneve->flags; + + gs4 = rcu_dereference(geneve->sock4); + if (!gs4) + goto tx_error; if (geneve->collect_md) { - info = skb_tunnel_info(skb); - if (unlikely(info && !(info->mode & IP_TUNNEL_INFO_TX))) { + if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { netdev_dbg(dev, "no tunnel metadata\n"); goto tx_error; } @@ -671,14 +1028,13 @@ netdev_tx_t rpl_geneve_xmit(struct sk_buff *skb) goto tx_error; } - rt = geneve_get_rt(skb, dev, &fl4, info); + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); + rt = geneve_get_v4_rt(skb, dev, &fl4, info, geneve->dst_port, sport); if (IS_ERR(rt)) { - netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); - dev->stats.tx_carrier_errors++; + err = PTR_ERR(rt); goto tx_error; } - sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); skb_reset_mac_header(skb); iip = ip_hdr(skb); @@ -689,47 +1045,165 @@ netdev_tx_t rpl_geneve_xmit(struct sk_buff *skb) u8 vni[3]; tunnel_id_to_vni(key->tun_id, vni); - if (key->tun_flags & TUNNEL_GENEVE_OPT) + if (info->options_len) opts = ip_tunnel_info_opts(info); - udp_csum = !!(key->tun_flags & TUNNEL_CSUM); + if (key->tun_flags & TUNNEL_CSUM) + flags &= ~GENEVE_F_UDP_ZERO_CSUM_TX; + else + flags |= GENEVE_F_UDP_ZERO_CSUM_TX; + err = geneve_build_skb(rt, skb, key->tun_flags, vni, - info->options_len, opts, udp_csum); + info->options_len, opts, flags, xnet); if (unlikely(err)) - goto err; + goto tx_error; tos = ip_tunnel_ecn_encap(key->tos, iip, skb); ttl = key->ttl; df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; } else { - udp_csum = false; err = geneve_build_skb(rt, skb, 0, geneve->vni, - 0, NULL, udp_csum); + 0, NULL, flags, xnet); if (unlikely(err)) - goto err; + goto tx_error; tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb); ttl = geneve->ttl; if (!ttl && IN_MULTICAST(ntohl(fl4.daddr))) ttl = 1; - ttl = ttl ? : ip4_dst_hoplimit(&rt_dst(rt)); + ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); df = 0; } - err = udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, fl4.saddr, fl4.daddr, - tos, ttl, df, sport, geneve->dst_port, - !net_eq(geneve->net, dev_net(geneve->dev)), - !udp_csum); + udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, fl4.saddr, fl4.daddr, + tos, ttl, df, sport, geneve->dst_port, + !net_eq(geneve->net, dev_net(geneve->dev)), + !!(flags & GENEVE_F_UDP_ZERO_CSUM_TX)); + + return NETDEV_TX_OK; + +tx_error: + dev_kfree_skb(skb); + + if (err == -ELOOP) + dev->stats.collisions++; + else if (err == -ENETUNREACH) + dev->stats.tx_carrier_errors++; + + dev->stats.tx_errors++; + return NETDEV_TX_OK; +} + +#if IS_ENABLED(CONFIG_IPV6) +static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, + struct ip_tunnel_info *info) +{ + struct geneve_dev *geneve = netdev_priv(dev); + struct dst_entry *dst = NULL; + const struct iphdr *iip; /* interior IP header */ + struct geneve_sock *gs6; + int err = -EINVAL; + struct flowi6 fl6; + __u8 prio, ttl; + __be16 sport; + __be32 label; + bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); + u32 flags = geneve->flags; + + gs6 = rcu_dereference(geneve->sock6); + if (!gs6) + goto tx_error; + + if (geneve->collect_md) { + if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { + netdev_dbg(dev, "no tunnel metadata\n"); + goto tx_error; + } + } + + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); + dst = geneve_get_v6_dst(skb, dev, &fl6, info, geneve->dst_port, sport); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + goto tx_error; + } + + skb_reset_mac_header(skb); + + iip = ip_hdr(skb); + + if (info) { + const struct ip_tunnel_key *key = &info->key; + u8 *opts = NULL; + u8 vni[3]; + + tunnel_id_to_vni(key->tun_id, vni); + if (info->options_len) + opts = ip_tunnel_info_opts(info); + + if (key->tun_flags & TUNNEL_CSUM) + flags &= ~GENEVE_F_UDP_ZERO_CSUM6_TX; + else + flags |= GENEVE_F_UDP_ZERO_CSUM6_TX; - iptunnel_xmit_stats(err, &dev->stats, (struct pcpu_sw_netstats __percpu *) dev->tstats); + err = geneve6_build_skb(dst, skb, key->tun_flags, vni, + info->options_len, opts, + flags, xnet); + if (unlikely(err)) + goto tx_error; + + prio = ip_tunnel_ecn_encap(key->tos, iip, skb); + ttl = key->ttl; + label = info->key.label; + } else { + err = geneve6_build_skb(dst, skb, 0, geneve->vni, + 0, NULL, flags, xnet); + if (unlikely(err)) + goto tx_error; + + prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel), + iip, skb); + ttl = geneve->ttl; + if (!ttl && ipv6_addr_is_multicast(&fl6.daddr)) + ttl = 1; + ttl = ttl ? : ip6_dst_hoplimit(dst); + label = geneve->label; + } + udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, + &fl6.saddr, &fl6.daddr, prio, ttl, label, + sport, geneve->dst_port, + !!(flags & GENEVE_F_UDP_ZERO_CSUM6_TX)); return NETDEV_TX_OK; tx_error: dev_kfree_skb(skb); -err: + + if (err == -ELOOP) + dev->stats.collisions++; + else if (err == -ENETUNREACH) + dev->stats.tx_carrier_errors++; + dev->stats.tx_errors++; return NETDEV_TX_OK; } -EXPORT_SYMBOL(rpl_geneve_xmit); +#endif + +netdev_tx_t rpl_geneve_xmit(struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + struct geneve_dev *geneve = netdev_priv(dev); + struct ip_tunnel_info *info = NULL; + + if (geneve->collect_md) + info = skb_tunnel_info(skb); + +#if IS_ENABLED(CONFIG_IPV6) + if ((info && ip_tunnel_info_af(info) == AF_INET6) || + (!info && geneve->remote.sa.sa_family == AF_INET6)) + return geneve6_xmit_skb(skb, dev, info); +#endif + return geneve_xmit_skb(skb, dev, info); +} +EXPORT_SYMBOL_GPL(rpl_geneve_xmit); static netdev_tx_t geneve_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -742,29 +1216,98 @@ static netdev_tx_t geneve_dev_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static int geneve_change_mtu(struct net_device *dev, int new_mtu) +static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict) { - /* GENEVE overhead is not fixed, so we can't enforce a more - * precise max MTU. + struct geneve_dev *geneve = netdev_priv(dev); + /* The max_mtu calculation does not take account of GENEVE + * options, to avoid excluding potentially valid + * configurations. */ - if (new_mtu < 68 || new_mtu > IP_MAX_MTU) + int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len; + + if (geneve->remote.sa.sa_family == AF_INET6) + max_mtu -= sizeof(struct ipv6hdr); + else + max_mtu -= sizeof(struct iphdr); + + if (new_mtu < 68) return -EINVAL; + + if (new_mtu > max_mtu) { + if (strict) + return -EINVAL; + + new_mtu = max_mtu; + } + dev->mtu = new_mtu; return 0; } +static int geneve_change_mtu(struct net_device *dev, int new_mtu) +{ + return __geneve_change_mtu(dev, new_mtu, true); +} + +int ovs_geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info = skb_tunnel_info(skb); + struct geneve_dev *geneve = netdev_priv(dev); + struct rtable *rt; + struct flowi4 fl4; + __be16 sport; +#if IS_ENABLED(CONFIG_IPV6) + struct dst_entry *dst; + struct flowi6 fl6; +#endif + + sport = udp_flow_src_port(geneve->net, skb, + 1, USHRT_MAX, true); + + if (ip_tunnel_info_af(info) == AF_INET) { + rt = geneve_get_v4_rt(skb, dev, &fl4, info, geneve->dst_port, sport); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + ip_rt_put(rt); + info->key.u.ipv4.src = fl4.saddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (ip_tunnel_info_af(info) == AF_INET6) { + dst = geneve_get_v6_dst(skb, dev, &fl6, info, geneve->dst_port, sport); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + dst_release(dst); + info->key.u.ipv6.src = fl6.saddr; +#endif + } else { + return -EINVAL; + } + + info->key.tp_src = sport; + info->key.tp_dst = geneve->dst_port; + return 0; +} +EXPORT_SYMBOL_GPL(ovs_geneve_fill_metadata_dst); + static const struct net_device_ops geneve_netdev_ops = { -#ifdef HAVE_DEV_TSTATS .ndo_init = geneve_init, .ndo_uninit = geneve_uninit, - .ndo_get_stats64 = ip_tunnel_get_stats64, -#endif .ndo_open = geneve_open, .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_dev_xmit, + .ndo_get_stats64 = ip_tunnel_get_stats64, +#ifdef HAVE_RHEL7_MAX_MTU + .ndo_size = sizeof(struct net_device_ops), + .extended.ndo_change_mtu = geneve_change_mtu, +#else .ndo_change_mtu = geneve_change_mtu, +#endif .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, +#ifdef HAVE_NDO_FILL_METADATA_DST + .ndo_fill_metadata_dst = geneve_fill_metadata_dst, +#endif }; static void geneve_get_drvinfo(struct net_device *dev, @@ -784,6 +1327,53 @@ static struct device_type geneve_type = { .name = "geneve", }; +/* Calls the ndo_add_geneve_port or ndo_udp_tunnel_add of the caller + * in order to supply the listening GENEVE udp ports. Callers are + * expected to implement the ndo_add_geneve_port. + */ +static void geneve_push_rx_ports(struct net_device *dev) +{ +#ifdef HAVE_NDO_ADD_GENEVE_PORT + struct net *net = dev_net(dev); + struct geneve_net *gn = net_generic(net, geneve_net_id); + struct geneve_sock *gs; + sa_family_t sa_family; + struct sock *sk; + __be16 port; + + if (!dev->netdev_ops->ndo_add_geneve_port) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(gs, &gn->sock_list, list) { + sk = gs->sock->sk; + sa_family = sk->sk_family; + port = inet_sk(sk)->inet_sport; + dev->netdev_ops->ndo_add_geneve_port(dev, sa_family, port); + } + rcu_read_unlock(); +#elif defined(HAVE_NDO_UDP_TUNNEL_ADD) + struct net *net = dev_net(dev); + struct geneve_net *gn = net_generic(net, geneve_net_id); + struct geneve_sock *gs; + struct sock *sk; + + if (!dev->netdev_ops->ndo_udp_tunnel_add) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(gs, &gn->sock_list, list) { + struct udp_tunnel_info ti; + ti.type = UDP_TUNNEL_TYPE_GENEVE; + sk = gs->sock->sk; + ti.port = inet_sk(sk)->inet_sport; + ti.sa_family = sk->sk_family; + dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti); + } + rcu_read_unlock(); +#endif +} + /* Initialize the device structure. */ static void geneve_setup(struct net_device *dev) { @@ -791,7 +1381,11 @@ static void geneve_setup(struct net_device *dev) dev->netdev_ops = &geneve_netdev_ops; dev->ethtool_ops = &geneve_ethtool_ops; +#ifndef HAVE_NEEDS_FREE_NETDEV dev->destructor = free_netdev; +#else + dev->needs_free_netdev = true; +#endif SET_NETDEV_DEVTYPE(dev, &geneve_type); @@ -800,28 +1394,37 @@ static void geneve_setup(struct net_device *dev) dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; -#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,39) dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; -#endif + #if 0 - /* Not required */ netif_keep_dst(dev); #endif + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; eth_hw_addr_random(dev); } static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_ID] = { .type = NLA_U32 }, - [IFLA_GENEVE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, + [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, + [IFLA_GENEVE_LABEL] = { .type = NLA_U32 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, [IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG }, + [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, + [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, + [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, }; +#ifdef HAVE_EXT_ACK_IN_RTNL_LINKOPS +static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +#else static int geneve_validate(struct nlattr *tb[], struct nlattr *data[]) +#endif { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) @@ -846,7 +1449,7 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[]) static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, __be16 dst_port, - __be32 rem_addr, + union geneve_addr *remote, u8 vni[], bool *tun_on_same_port, bool *tun_collect_md) @@ -862,7 +1465,7 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, *tun_on_same_port = true; } if (!memcmp(vni, geneve->vni, sizeof(geneve->vni)) && - rem_addr == geneve->remote.sin_addr.s_addr && + !memcmp(remote, &geneve->remote, sizeof(geneve->remote)) && dst_port == geneve->dst_port) t = geneve; } @@ -870,18 +1473,20 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, } static int geneve_configure(struct net *net, struct net_device *dev, - __be32 rem_addr, __u32 vni, __u8 ttl, __u8 tos, - __be16 dst_port, bool metadata) + union geneve_addr *remote, + __u32 vni, __u8 ttl, __u8 tos, __be32 label, + __be16 dst_port, bool metadata, u32 flags) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); bool tun_collect_md, tun_on_same_port; - int err; + int err, encap_len; - if (metadata) { - if (rem_addr || vni || tos || ttl) - return -EINVAL; - } + if (!remote) + return -EINVAL; + if (metadata && + (remote->sa.sa_family != AF_UNSPEC || vni || tos || ttl || label)) + return -EINVAL; geneve->net = net; geneve->dev = dev; @@ -890,20 +1495,36 @@ static int geneve_configure(struct net *net, struct net_device *dev, geneve->vni[1] = (vni & 0x0000ff00) >> 8; geneve->vni[2] = vni & 0x000000ff; - geneve->remote.sin_addr.s_addr = rem_addr; - if (IN_MULTICAST(ntohl(geneve->remote.sin_addr.s_addr))) + if ((remote->sa.sa_family == AF_INET && + IN_MULTICAST(ntohl(remote->sin.sin_addr.s_addr))) || + (remote->sa.sa_family == AF_INET6 && + ipv6_addr_is_multicast(&remote->sin6.sin6_addr))) + return -EINVAL; + if (label && remote->sa.sa_family != AF_INET6) return -EINVAL; + geneve->remote = *remote; + geneve->ttl = ttl; geneve->tos = tos; + geneve->label = label; geneve->dst_port = dst_port; geneve->collect_md = metadata; + geneve->flags = flags; - t = geneve_find_dev(gn, dst_port, rem_addr, geneve->vni, + t = geneve_find_dev(gn, dst_port, remote, geneve->vni, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; + /* make enough headroom for basic scenario */ + encap_len = GENEVE_BASE_HLEN + ETH_HLEN; + if (remote->sa.sa_family == AF_INET) + encap_len += sizeof(struct iphdr); + else + encap_len += sizeof(struct ipv6hdr); + dev->needed_headroom = encap_len + ETH_HLEN; + if (metadata) { if (tun_on_same_port) return -EPERM; @@ -912,6 +1533,8 @@ static int geneve_configure(struct net *net, struct net_device *dev, return -EPERM; } + dst_cache_reset(&geneve->dst_cache); + err = register_netdevice(dev); if (err) return err; @@ -920,27 +1543,49 @@ static int geneve_configure(struct net *net, struct net_device *dev, return 0; } -#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,39) -static int geneve_newlink(struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) -{ - struct net *net = &init_net; +#ifdef HAVE_EXT_ACK_IN_RTNL_LINKOPS +static int geneve_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) #else static int geneve_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) -{ #endif +{ __be16 dst_port = htons(GENEVE_UDP_PORT); __u8 ttl = 0, tos = 0; bool metadata = false; - __be32 rem_addr; - __u32 vni; + union geneve_addr remote = geneve_remote_unspec; + __be32 label = 0; + __u32 vni = 0; + u32 flags = 0; - if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE]) + if (data[IFLA_GENEVE_REMOTE] && data[IFLA_GENEVE_REMOTE6]) return -EINVAL; - vni = nla_get_u32(data[IFLA_GENEVE_ID]); - rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); + if (data[IFLA_GENEVE_REMOTE]) { + remote.sa.sa_family = AF_INET; + remote.sin.sin_addr.s_addr = + nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); + } + + if (data[IFLA_GENEVE_REMOTE6]) { + if (!IS_ENABLED(CONFIG_IPV6)) + return -EPFNOSUPPORT; + + remote.sa.sa_family = AF_INET6; + remote.sin6.sin6_addr = + nla_get_in6_addr(data[IFLA_GENEVE_REMOTE6]); + + if (ipv6_addr_type(&remote.sin6.sin6_addr) & + IPV6_ADDR_LINKLOCAL) { + netdev_dbg(dev, "link-local remote is unsupported\n"); + return -EINVAL; + } + } + + if (data[IFLA_GENEVE_ID]) + vni = nla_get_u32(data[IFLA_GENEVE_ID]); if (data[IFLA_GENEVE_TTL]) ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); @@ -948,21 +1593,33 @@ static int geneve_newlink(struct net *net, struct net_device *dev, if (data[IFLA_GENEVE_TOS]) tos = nla_get_u8(data[IFLA_GENEVE_TOS]); + if (data[IFLA_GENEVE_LABEL]) + label = nla_get_be32(data[IFLA_GENEVE_LABEL]) & + IPV6_FLOWLABEL_MASK; + if (data[IFLA_GENEVE_PORT]) dst_port = nla_get_be16(data[IFLA_GENEVE_PORT]); if (data[IFLA_GENEVE_COLLECT_METADATA]) metadata = true; - return geneve_configure(net, dev, rem_addr, vni, - ttl, tos, dst_port, metadata); + if (data[IFLA_GENEVE_UDP_CSUM] && + !nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) + flags |= GENEVE_F_UDP_ZERO_CSUM_TX; + + if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX] && + nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) + flags |= GENEVE_F_UDP_ZERO_CSUM6_TX; + + if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX] && + nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) + flags |= GENEVE_F_UDP_ZERO_CSUM6_RX; + + return geneve_configure(net, dev, &remote, vni, ttl, tos, label, + dst_port, metadata, flags); } -#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,39) -static void geneve_dellink(struct net_device *dev) -#else static void geneve_dellink(struct net_device *dev, struct list_head *head) -#endif { struct geneve_dev *geneve = netdev_priv(dev); @@ -973,11 +1630,15 @@ static void geneve_dellink(struct net_device *dev, struct list_head *head) static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ - nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ + nla_total_size(sizeof(__be32)) + /* IFLA_GENEVE_LABEL */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ 0; } @@ -990,12 +1651,21 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_GENEVE_ID, vni)) goto nla_put_failure; - if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, - geneve->remote.sin_addr.s_addr)) - goto nla_put_failure; + if (geneve->remote.sa.sa_family == AF_INET) { + if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, + geneve->remote.sin.sin_addr.s_addr)) + goto nla_put_failure; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6, + &geneve->remote.sin6.sin6_addr)) + goto nla_put_failure; +#endif + } if (nla_put_u8(skb, IFLA_GENEVE_TTL, geneve->ttl) || - nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos)) + nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos) || + nla_put_be32(skb, IFLA_GENEVE_LABEL, geneve->label)) goto nla_put_failure; if (nla_put_be16(skb, IFLA_GENEVE_PORT, geneve->dst_port)) @@ -1006,6 +1676,14 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } + if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, + !(geneve->flags & GENEVE_F_UDP_ZERO_CSUM_TX)) || + nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + !!(geneve->flags & GENEVE_F_UDP_ZERO_CSUM6_TX)) || + nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + !!(geneve->flags & GENEVE_F_UDP_ZERO_CSUM6_RX))) + goto nla_put_failure; + return 0; nla_put_failure: @@ -1026,37 +1704,62 @@ static struct rtnl_link_ops geneve_link_ops __read_mostly = { }; struct net_device *rpl_geneve_dev_create_fb(struct net *net, const char *name, - u8 name_assign_type, u16 dst_port) + u8 name_assign_type, u16 dst_port) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; + LIST_HEAD(list_kill); int err; memset(tb, 0, sizeof(tb)); - dev = rtnl_create_link(net, (char *) name, name_assign_type, + dev = rtnl_create_link(net, name, name_assign_type, &geneve_link_ops, tb); if (IS_ERR(dev)) return dev; - err = geneve_configure(net, dev, 0, 0, 0, 0, htons(dst_port), true); - if (err) - goto err; + err = geneve_configure(net, dev, &geneve_remote_unspec, + 0, 0, 0, 0, htons(dst_port), true, + GENEVE_F_UDP_ZERO_CSUM6_RX); + if (err) { + free_netdev(dev); + return ERR_PTR(err); + } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ - err = geneve_change_mtu(dev, IP_MAX_MTU); + err = __geneve_change_mtu(dev, IP_MAX_MTU, false); if (err) goto err; + err = rtnl_configure_link(dev, NULL); + if (err < 0) + goto err; + return dev; -err: - free_netdev(dev); + err: + geneve_dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(rpl_geneve_dev_create_fb); +static int geneve_netdevice_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (event == NETDEV_OFFLOAD_PUSH_GENEVE) + geneve_push_rx_ports(dev); + + return NOTIFY_DONE; +} + +static struct notifier_block geneve_notifier_block __read_mostly = { + .notifier_call = geneve_netdevice_event, +}; + static __net_init int geneve_init_net(struct net *net) { struct geneve_net *gn = net_generic(net, geneve_net_id); @@ -1101,7 +1804,6 @@ static struct pernet_operations geneve_net_ops = { .size = sizeof(struct geneve_net), }; -DEFINE_COMPAT_PNET_REG_FUNC(device) int rpl_geneve_init_module(void) { int rc; @@ -1110,21 +1812,31 @@ int rpl_geneve_init_module(void) if (rc) goto out1; - rc = rtnl_link_register(&geneve_link_ops); + rc = register_netdevice_notifier(&geneve_notifier_block); if (rc) goto out2; + rc = rtnl_link_register(&geneve_link_ops); + if (rc) + goto out3; + pr_info("Geneve tunneling driver\n"); return 0; + +out3: + unregister_netdevice_notifier(&geneve_notifier_block); out2: unregister_pernet_subsys(&geneve_net_ops); out1: + pr_err("Error while initializing GENEVE %d\n", rc); return rc; } void rpl_geneve_cleanup_module(void) { rtnl_link_unregister(&geneve_link_ops); + unregister_netdevice_notifier(&geneve_notifier_block); unregister_pernet_subsys(&geneve_net_ops); } + #endif