From 0b5e8b8eeae40bae6ad7c7e91c97c3c0d0e57882 Mon Sep 17 00:00:00 2001 From: Andy Zhou Date: Fri, 3 Oct 2014 15:35:28 -0700 Subject: net: Add Geneve tunneling protocol driver This adds a device level support for Geneve -- Generic Network Virtualization Encapsulation. The protocol is documented at http://tools.ietf.org/html/draft-gross-geneve-01 Only protocol layer Geneve support is provided by this driver. Openvswitch can be used for configuring, set up and tear down functional Geneve tunnels. Signed-off-by: Jesse Gross Signed-off-by: Andy Zhou Signed-off-by: David S. Miller --- include/net/geneve.h | 91 ++++++++++++ include/net/ip_tunnels.h | 2 + net/ipv4/Kconfig | 14 ++ net/ipv4/Makefile | 1 + net/ipv4/geneve.c | 373 +++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 481 insertions(+) create mode 100644 include/net/geneve.h create mode 100644 net/ipv4/geneve.c diff --git a/include/net/geneve.h b/include/net/geneve.h new file mode 100644 index 000000000000..ce98865318bf --- /dev/null +++ b/include/net/geneve.h @@ -0,0 +1,91 @@ +#ifndef __NET_GENEVE_H +#define __NET_GENEVE_H 1 + +#include + +struct geneve_sock; + +typedef void (geneve_rcv_t)(struct geneve_sock *gs, struct sk_buff *skb); + +struct geneve_sock { + struct hlist_node hlist; + geneve_rcv_t *rcv; + void *rcv_data; + struct work_struct del_work; + struct socket *sock; + struct rcu_head rcu; + atomic_t refcnt; + struct udp_offload udp_offloads; +}; + +/* Geneve Header: + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |Ver| Opt Len |O|C| Rsvd. | Protocol Type | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Virtual Network Identifier (VNI) | Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Variable Length Options | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Option Header: + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Option Class | Type |R|R|R| Length | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Variable Option Data | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ + +struct geneve_opt { + __be16 opt_class; + u8 type; +#ifdef __LITTLE_ENDIAN_BITFIELD + u8 length:5; + u8 r3:1; + u8 r2:1; + u8 r1:1; +#else + u8 r1:1; + u8 r2:1; + u8 r3:1; + u8 length:5; +#endif + u8 opt_data[]; +}; + +#define GENEVE_CRIT_OPT_TYPE (1 << 7) + +struct genevehdr { +#ifdef __LITTLE_ENDIAN_BITFIELD + u8 opt_len:6; + u8 ver:2; + u8 rsvd1:6; + u8 critical:1; + u8 oam:1; +#else + u8 ver:2; + u8 opt_len:6; + u8 oam:1; + u8 critical:1; + u8 rsvd1:6; +#endif + __be16 proto_type; + u8 vni[3]; + u8 rsvd2; + struct geneve_opt options[]; +}; + +#define GENEVE_VER 0 +#define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr)) + +struct geneve_sock *geneve_sock_add(struct net *net, __be16 port, + geneve_rcv_t *rcv, void *data, + bool no_share, bool ipv6); + +void geneve_sock_release(struct geneve_sock *vs); + +int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, + struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, + __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, + __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, + bool xnet); +#endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 7f538ba6e267..a9ce1556d773 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -95,6 +95,8 @@ struct ip_tunnel { #define TUNNEL_VERSION __cpu_to_be16(0x40) #define TUNNEL_NO_KEY __cpu_to_be16(0x80) #define TUNNEL_DONT_FRAGMENT __cpu_to_be16(0x0100) +#define TUNNEL_OAM __cpu_to_be16(0x0200) +#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400) struct tnl_ptk_info { __be16 flags; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 69fb37854449..c2035447e649 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -453,6 +453,20 @@ config TCP_CONG_BIC increase provides TCP friendliness. See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/ +config GENEVE + tristate "Generic Network Virtualization Encapsulation (Geneve)" + depends on INET + select NET_IP_TUNNEL + select NET_UDP_TUNNEL + ---help--- + This allows one to create Geneve virtual interfaces that provide + Layer 2 Networks over Layer 3 Networks. Geneve is often used + to tunnel virtual network infrastructure in virtualized environments. + For more information see: + http://tools.ietf.org/html/draft-gross-geneve-01 + + To compile this driver as a module, choose M here: the module + config TCP_CONG_CUBIC tristate "CUBIC TCP" default y diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index d8105787c199..518c04ed666e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o +obj-$(CONFIG_GENEVE) += geneve.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c new file mode 100644 index 000000000000..f008c5515f48 --- /dev/null +++ b/net/ipv4/geneve.c @@ -0,0 +1,373 @@ +/* + * Geneve: Generic Network Virtualization Encapsulation + * + * Copyright (c) 2014 Nicira, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#if IS_ENABLED(CONFIG_IPV6) +#include +#include +#include +#include +#endif + +#define PORT_HASH_BITS 8 +#define PORT_HASH_SIZE (1<sock_list[hash_32(ntohs(port), PORT_HASH_BITS)]; +} + +/* Find geneve socket based on network namespace and UDP port */ +static struct geneve_sock *geneve_find_sock(struct net *net, __be16 port) +{ + struct geneve_sock *gs; + + hlist_for_each_entry_rcu(gs, gs_head(net, port), hlist) { + if (inet_sk(gs->sock->sk)->inet_sport == port) + return gs; + } + + return NULL; +} + +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); +} + +/* Transmit a fully formated Geneve frame. + * + * When calling this function. The skb->data should point + * to the geneve header which is fully formed. + * + * This function will add other UDP tunnel headers. + */ +int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, + struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, + __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, + __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, + bool xnet) +{ + struct genevehdr *gnvh; + int min_headroom; + int err; + + skb = udp_tunnel_handle_offloads(skb, !gs->sock->sk->sk_no_check_tx); + + min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + + GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr) + + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0); + + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + return err; + + if (vlan_tx_tag_present(skb)) { + if (unlikely(!__vlan_put_tag(skb, + skb->vlan_proto, + vlan_tx_tag_get(skb)))) { + err = -ENOMEM; + return err; + } + skb->vlan_tci = 0; + } + + gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); + geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); + + return udp_tunnel_xmit_skb(gs->sock, rt, skb, src, dst, + tos, ttl, df, src_port, dst_port, xnet); +} +EXPORT_SYMBOL_GPL(geneve_xmit_skb); + +static void geneve_notify_add_rx_port(struct geneve_sock *gs) +{ + struct sock *sk = gs->sock->sk; + sa_family_t sa_family = sk->sk_family; + int err; + + if (sa_family == AF_INET) { + err = udp_add_offload(&gs->udp_offloads); + if (err) + pr_warn("geneve: udp_add_offload failed with status %d\n", + err); + } +} + +/* 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_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; + + /* Return packets with reserved bits set */ + geneveh = geneve_hdr(skb); + + if (unlikely(geneveh->ver != GENEVE_VER)) + goto error; + + 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; + + gs->rcv(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 void geneve_del_work(struct work_struct *work) +{ + struct geneve_sock *gs = container_of(work, struct geneve_sock, + del_work); + + udp_tunnel_sock_release(gs->sock); + kfree_rcu(gs, rcu); +} + +static struct socket *geneve_create_sock(struct net *net, bool ipv6, + __be16 port) +{ + struct socket *sock; + struct udp_port_cfg udp_conf; + int err; + + memset(&udp_conf, 0, sizeof(udp_conf)); + + if (ipv6) { + udp_conf.family = AF_INET6; + } else { + udp_conf.family = AF_INET; + udp_conf.local_ip.s_addr = INADDR_ANY; + } + + udp_conf.local_udp_port = port; + + /* Open UDP socket */ + err = udp_sock_create(net, &udp_conf, &sock); + if (err < 0) + return ERR_PTR(err); + + return sock; +} + +/* Create new listen socket if needed */ +static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, + geneve_rcv_t *rcv, void *data, + bool ipv6) +{ + struct geneve_net *gn = net_generic(net, geneve_net_id); + struct geneve_sock *gs; + struct socket *sock; + struct udp_tunnel_sock_cfg tunnel_cfg; + + gs = kzalloc(sizeof(*gs), GFP_KERNEL); + if (!gs) + return ERR_PTR(-ENOMEM); + + INIT_WORK(&gs->del_work, geneve_del_work); + + sock = geneve_create_sock(net, ipv6, port); + if (IS_ERR(sock)) { + kfree(gs); + return ERR_CAST(sock); + } + + gs->sock = sock; + atomic_set(&gs->refcnt, 1); + gs->rcv = rcv; + gs->rcv_data = data; + + /* Initialize the geneve udp offloads structure */ + gs->udp_offloads.port = port; + gs->udp_offloads.callbacks.gro_receive = NULL; + gs->udp_offloads.callbacks.gro_complete = NULL; + + spin_lock(&gn->sock_lock); + hlist_add_head_rcu(&gs->hlist, gs_head(net, port)); + geneve_notify_add_rx_port(gs); + spin_unlock(&gn->sock_lock); + + /* Mark socket as an encapsulation socket */ + tunnel_cfg.sk_user_data = gs; + tunnel_cfg.encap_type = 1; + tunnel_cfg.encap_rcv = geneve_udp_encap_recv; + tunnel_cfg.encap_destroy = NULL; + setup_udp_tunnel_sock(net, sock, &tunnel_cfg); + + return gs; +} + +struct geneve_sock *geneve_sock_add(struct net *net, __be16 port, + geneve_rcv_t *rcv, void *data, + bool no_share, bool ipv6) +{ + struct geneve_sock *gs; + + gs = geneve_socket_create(net, port, rcv, data, ipv6); + if (!IS_ERR(gs)) + return gs; + + if (no_share) /* Return error if sharing is not allowed. */ + return ERR_PTR(-EINVAL); + + gs = geneve_find_sock(net, port); + if (gs) { + if (gs->rcv == rcv) + atomic_inc(&gs->refcnt); + else + gs = ERR_PTR(-EBUSY); + } else { + gs = ERR_PTR(-EINVAL); + } + + return gs; +} +EXPORT_SYMBOL_GPL(geneve_sock_add); + +void geneve_sock_release(struct geneve_sock *gs) +{ + if (!atomic_dec_and_test(&gs->refcnt)) + return; + + queue_work(geneve_wq, &gs->del_work); +} +EXPORT_SYMBOL_GPL(geneve_sock_release); + +static __net_init int geneve_init_net(struct net *net) +{ + struct geneve_net *gn = net_generic(net, geneve_net_id); + unsigned int h; + + spin_lock_init(&gn->sock_lock); + + for (h = 0; h < PORT_HASH_SIZE; ++h) + INIT_HLIST_HEAD(&gn->sock_list[h]); + + return 0; +} + +static struct pernet_operations geneve_net_ops = { + .init = geneve_init_net, + .exit = NULL, + .id = &geneve_net_id, + .size = sizeof(struct geneve_net), +}; + +static int __init geneve_init_module(void) +{ + int rc; + + geneve_wq = alloc_workqueue("geneve", 0, 0); + if (!geneve_wq) + return -ENOMEM; + + rc = register_pernet_subsys(&geneve_net_ops); + if (rc) + return rc; + + pr_info("Geneve driver\n"); + + return 0; +} +late_initcall(geneve_init_module); + +static void __exit geneve_cleanup_module(void) +{ + destroy_workqueue(geneve_wq); +} +module_exit(geneve_cleanup_module); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jesse Gross "); +MODULE_DESCRIPTION("Driver for GENEVE encapsulated traffic"); +MODULE_ALIAS_RTNL_LINK("geneve"); -- cgit v1.2.3 From 0714812134d7dcadeb7ecfbfeb18788aa7e1eaac Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Fri, 3 Oct 2014 15:35:29 -0700 Subject: openvswitch: Eliminate memset() from flow_extract. As new protocols are added, the size of the flow key tends to increase although few protocols care about all of the fields. In order to optimize this for hashing and matching, OVS uses a variable length portion of the key. However, when fields are extracted from the packet we must still zero out the entire key. This is no longer necessary now that OVS implements masking. Any fields (or holes in the structure) which are not part of a given protocol will be by definition not part of the mask and zeroed out during lookup. Furthermore, since masking already uses variable length keys this zeroing operation automatically benefits as well. In principle, the only thing that needs to be done at this point is remove the memset() at the beginning of flow. However, some fields assume that they are initialized to zero, which now must be done explicitly. In addition, in the event of an error we must also zero out corresponding fields to signal that there is no valid data present. These increase the total amount of code but very little of it is executed in non-error situations. Removing the memset() reduces the profile of ovs_flow_extract() from 0.64% to 0.56% when tested with large packets on a 10G link. Suggested-by: Pravin Shelar Signed-off-by: Jesse Gross Signed-off-by: Andy Zhou Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/flow.c | 54 +++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 45 insertions(+), 9 deletions(-) diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 4010423f2831..913bdc1a83c0 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -462,6 +462,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) * update skb->csum here. */ + key->eth.tci = 0; if (vlan_tx_tag_present(skb)) key->eth.tci = htons(skb->vlan_tci); else if (eth->h_proto == htons(ETH_P_8021Q)) @@ -482,6 +483,8 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) error = check_iphdr(skb); if (unlikely(error)) { + memset(&key->ip, 0, sizeof(key->ip)); + memset(&key->ipv4, 0, sizeof(key->ipv4)); if (error == -EINVAL) { skb->transport_header = skb->network_header; error = 0; @@ -503,8 +506,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) return 0; } if (nh->frag_off & htons(IP_MF) || - skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + skb_shinfo(skb)->gso_type & SKB_GSO_UDP) key->ip.frag = OVS_FRAG_TYPE_FIRST; + else + key->ip.frag = OVS_FRAG_TYPE_NONE; /* Transport layer. */ if (key->ip.proto == IPPROTO_TCP) { @@ -513,18 +518,25 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) key->tp.src = tcp->source; key->tp.dst = tcp->dest; key->tp.flags = TCP_FLAGS_BE16(tcp); + } else { + memset(&key->tp, 0, sizeof(key->tp)); } + } else if (key->ip.proto == IPPROTO_UDP) { if (udphdr_ok(skb)) { struct udphdr *udp = udp_hdr(skb); key->tp.src = udp->source; key->tp.dst = udp->dest; + } else { + memset(&key->tp, 0, sizeof(key->tp)); } } else if (key->ip.proto == IPPROTO_SCTP) { if (sctphdr_ok(skb)) { struct sctphdr *sctp = sctp_hdr(skb); key->tp.src = sctp->source; key->tp.dst = sctp->dest; + } else { + memset(&key->tp, 0, sizeof(key->tp)); } } else if (key->ip.proto == IPPROTO_ICMP) { if (icmphdr_ok(skb)) { @@ -534,33 +546,44 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) * them in 16-bit network byte order. */ key->tp.src = htons(icmp->type); key->tp.dst = htons(icmp->code); + } else { + memset(&key->tp, 0, sizeof(key->tp)); } } - } else if ((key->eth.type == htons(ETH_P_ARP) || - key->eth.type == htons(ETH_P_RARP)) && arphdr_ok(skb)) { + } else if (key->eth.type == htons(ETH_P_ARP) || + key->eth.type == htons(ETH_P_RARP)) { struct arp_eth_header *arp; arp = (struct arp_eth_header *)skb_network_header(skb); - if (arp->ar_hrd == htons(ARPHRD_ETHER) - && arp->ar_pro == htons(ETH_P_IP) - && arp->ar_hln == ETH_ALEN - && arp->ar_pln == 4) { + if (arphdr_ok(skb) && + arp->ar_hrd == htons(ARPHRD_ETHER) && + arp->ar_pro == htons(ETH_P_IP) && + arp->ar_hln == ETH_ALEN && + arp->ar_pln == 4) { /* We only match on the lower 8 bits of the opcode. */ if (ntohs(arp->ar_op) <= 0xff) key->ip.proto = ntohs(arp->ar_op); + else + key->ip.proto = 0; + memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src)); memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst)); ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha); ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha); + } else { + memset(&key->ip, 0, sizeof(key->ip)); + memset(&key->ipv4, 0, sizeof(key->ipv4)); } } else if (key->eth.type == htons(ETH_P_IPV6)) { int nh_len; /* IPv6 Header + Extensions */ nh_len = parse_ipv6hdr(skb, key); if (unlikely(nh_len < 0)) { + memset(&key->ip, 0, sizeof(key->ip)); + memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr)); if (nh_len == -EINVAL) { skb->transport_header = skb->network_header; error = 0; @@ -582,24 +605,32 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) key->tp.src = tcp->source; key->tp.dst = tcp->dest; key->tp.flags = TCP_FLAGS_BE16(tcp); + } else { + memset(&key->tp, 0, sizeof(key->tp)); } } else if (key->ip.proto == NEXTHDR_UDP) { if (udphdr_ok(skb)) { struct udphdr *udp = udp_hdr(skb); key->tp.src = udp->source; key->tp.dst = udp->dest; + } else { + memset(&key->tp, 0, sizeof(key->tp)); } } else if (key->ip.proto == NEXTHDR_SCTP) { if (sctphdr_ok(skb)) { struct sctphdr *sctp = sctp_hdr(skb); key->tp.src = sctp->source; key->tp.dst = sctp->dest; + } else { + memset(&key->tp, 0, sizeof(key->tp)); } } else if (key->ip.proto == NEXTHDR_ICMP) { if (icmp6hdr_ok(skb)) { error = parse_icmpv6(skb, key, nh_len); if (error) return error; + } else { + memset(&key->tp, 0, sizeof(key->tp)); } } } @@ -615,13 +646,19 @@ int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key, struct sk_buff *skb, struct sw_flow_key *key) { /* Extract metadata from packet. */ - memset(key, 0, sizeof(*key)); if (tun_key) memcpy(&key->tun_key, tun_key, sizeof(key->tun_key)); + else + memset(&key->tun_key, 0, sizeof(key->tun_key)); key->phy.priority = skb->priority; key->phy.in_port = OVS_CB(skb)->input_vport->port_no; key->phy.skb_mark = skb->mark; + key->ovs_flow_hash = 0; + key->recirc_id = 0; + + /* Flags are always used as part of stats */ + key->tp.flags = 0; return key_extract(skb, key); } @@ -632,7 +669,6 @@ int ovs_flow_key_extract_userspace(const struct nlattr *attr, { int err; - memset(key, 0, sizeof(*key)); /* Extract metadata from netlink attributes. */ err = ovs_nla_get_flow_metadata(attr, key); if (err) -- cgit v1.2.3 From 67fa034194bf82a3d5ca841759d921297daa63ca Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Fri, 3 Oct 2014 15:35:30 -0700 Subject: openvswitch: Add support for matching on OAM packets. Some tunnel formats have mechanisms for indicating that packets are OAM frames that should be handled specially (either as high priority or not forwarded beyond an endpoint). This provides support for allowing those types of packets to be matched. Signed-off-by: Jesse Gross Signed-off-by: Andy Zhou Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 1 + net/openvswitch/datapath.c | 1 + net/openvswitch/flow_netlink.c | 17 ++++++++++++----- 3 files changed, 14 insertions(+), 5 deletions(-) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index f7fc507d82ab..7c06106f5af5 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -309,6 +309,7 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_TTL, /* u8 Tunnel IP TTL. */ OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT, /* No argument, set DF. */ OVS_TUNNEL_KEY_ATTR_CSUM, /* No argument. CSUM packet. */ + OVS_TUNNEL_KEY_ATTR_OAM, /* No argument. OAM frame. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9e3a2fae6a8f..f6bd93d5f435 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -369,6 +369,7 @@ static size_t key_attr_size(void) + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */ + + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */ + nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */ + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index f4c8daa73965..22c855fa0bc2 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -346,6 +346,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, [OVS_TUNNEL_KEY_ATTR_TTL] = 1, [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0, [OVS_TUNNEL_KEY_ATTR_CSUM] = 0, + [OVS_TUNNEL_KEY_ATTR_OAM] = 0, }; if (type > OVS_TUNNEL_KEY_ATTR_MAX) { @@ -390,6 +391,9 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_CSUM: tun_flags |= TUNNEL_CSUM; break; + case OVS_TUNNEL_KEY_ATTR_OAM: + tun_flags |= TUNNEL_OAM; + break; default: return -EINVAL; } @@ -431,21 +435,24 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) return -EMSGSIZE; if (output->ipv4_src && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src)) + nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src)) return -EMSGSIZE; if (output->ipv4_dst && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst)) + nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst)) return -EMSGSIZE; if (output->ipv4_tos && - nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos)) + nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos)) return -EMSGSIZE; if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ipv4_ttl)) return -EMSGSIZE; if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) && - nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) + nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; if ((output->tun_flags & TUNNEL_CSUM) && - nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM)) + nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM)) + return -EMSGSIZE; + if ((output->tun_flags & TUNNEL_OAM) && + nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; nla_nest_end(skb, nla); -- cgit v1.2.3 From f0b128c1e2cc33ad104daf0f51a51e34f7763c5f Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Fri, 3 Oct 2014 15:35:31 -0700 Subject: openvswitch: Wrap struct ovs_key_ipv4_tunnel in a new structure. Currently, the flow information that is matched for tunnels and the tunnel data passed around with packets is the same. However, as additional information is added this is not necessarily desirable, as in the case of pointers. This adds a new structure for tunnel metadata which currently contains only the existing struct. This change is purely internal to the kernel since the current OVS_KEY_ATTR_IPV4_TUNNEL is simply a compressed version of OVS_KEY_ATTR_TUNNEL that is translated at flow setup. Signed-off-by: Jesse Gross Signed-off-by: Andy Zhou Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 +- net/openvswitch/actions.c | 5 +++-- net/openvswitch/datapath.h | 2 +- net/openvswitch/flow.c | 6 +++--- net/openvswitch/flow.h | 30 +++++++++++++++++------------- net/openvswitch/flow_netlink.c | 38 +++++++++++++++++++++++++++++++------- net/openvswitch/vport-gre.c | 16 +++++++++------- net/openvswitch/vport-vxlan.c | 10 +++++----- net/openvswitch/vport.c | 6 +++--- net/openvswitch/vport.h | 2 +- 10 files changed, 74 insertions(+), 43 deletions(-) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 7c06106f5af5..6753032832e2 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -294,7 +294,7 @@ enum ovs_key_attr { OVS_KEY_ATTR_RECIRC_ID, /* u32 recirc id */ #ifdef __KERNEL__ - OVS_KEY_ATTR_IPV4_TUNNEL, /* struct ovs_key_ipv4_tunnel */ + OVS_KEY_ATTR_TUNNEL_INFO, /* struct ovs_tunnel_info */ #endif __OVS_KEY_ATTR_MAX }; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 6932a42e41a2..006886dbee36 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -590,8 +590,8 @@ static int execute_set_action(struct sk_buff *skb, skb->mark = nla_get_u32(nested_attr); break; - case OVS_KEY_ATTR_IPV4_TUNNEL: - OVS_CB(skb)->egress_tun_key = nla_data(nested_attr); + case OVS_KEY_ATTR_TUNNEL_INFO: + OVS_CB(skb)->egress_tun_info = nla_data(nested_attr); break; case OVS_KEY_ATTR_ETHERNET: @@ -778,6 +778,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts); this_cpu_inc(exec_actions_level); + OVS_CB(skb)->egress_tun_info = NULL; err = do_execute_actions(dp, skb, key, acts->actions, acts->actions_len); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index ac3f3df96961..974135439c5c 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -102,8 +102,8 @@ struct datapath { */ struct ovs_skb_cb { struct sw_flow *flow; + struct ovs_tunnel_info *egress_tun_info; struct vport *input_vport; - struct ovs_key_ipv4_tunnel *egress_tun_key; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 913bdc1a83c0..2924cb340868 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -642,12 +642,12 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key) return key_extract(skb, key); } -int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key, +int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key) { /* Extract metadata from packet. */ - if (tun_key) - memcpy(&key->tun_key, tun_key, sizeof(key->tun_key)); + if (tun_info) + memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key)); else memset(&key->tun_key, 0, sizeof(key->tun_key)); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 0f5db4ec565d..fe5a71b81c1f 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -49,20 +49,24 @@ struct ovs_key_ipv4_tunnel { u8 ipv4_ttl; } __packed __aligned(4); /* Minimize padding. */ -static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key, - const struct iphdr *iph, __be64 tun_id, - __be16 tun_flags) +struct ovs_tunnel_info { + struct ovs_key_ipv4_tunnel tunnel; +}; + +static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, + const struct iphdr *iph, + __be64 tun_id, __be16 tun_flags) { - tun_key->tun_id = tun_id; - tun_key->ipv4_src = iph->saddr; - tun_key->ipv4_dst = iph->daddr; - tun_key->ipv4_tos = iph->tos; - tun_key->ipv4_ttl = iph->ttl; - tun_key->tun_flags = tun_flags; + tun_info->tunnel.tun_id = tun_id; + tun_info->tunnel.ipv4_src = iph->saddr; + tun_info->tunnel.ipv4_dst = iph->daddr; + tun_info->tunnel.ipv4_tos = iph->tos; + tun_info->tunnel.ipv4_ttl = iph->ttl; + tun_info->tunnel.tun_flags = tun_flags; /* clear struct padding. */ - memset((unsigned char *) tun_key + OVS_TUNNEL_KEY_SIZE, 0, - sizeof(*tun_key) - OVS_TUNNEL_KEY_SIZE); + memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0, + sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE); } struct sw_flow_key { @@ -190,8 +194,8 @@ void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key); -int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key, - struct sk_buff *skb, struct sw_flow_key *key); +int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info, struct sk_buff *skb, + struct sw_flow_key *key); /* Extract key from packet coming from userspace. */ int ovs_flow_key_extract_userspace(const struct nlattr *attr, struct sk_buff *skb, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 22c855fa0bc2..5d6194d9dadc 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1148,13 +1148,14 @@ out: return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset); } -static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len) +static struct nlattr *__add_action(struct sw_flow_actions **sfa, + int attrtype, void *data, int len) { struct nlattr *a; a = reserve_sfa_size(sfa, nla_attr_size(len)); if (IS_ERR(a)) - return PTR_ERR(a); + return a; a->nla_type = attrtype; a->nla_len = nla_attr_size(len); @@ -1163,6 +1164,18 @@ static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, in memcpy(nla_data(a), data, len); memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len)); + return a; +} + +static int add_action(struct sw_flow_actions **sfa, int attrtype, + void *data, int len) +{ + struct nlattr *a; + + a = __add_action(sfa, attrtype, data, len); + if (IS_ERR(a)) + return PTR_ERR(a); + return 0; } @@ -1268,6 +1281,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, { struct sw_flow_match match; struct sw_flow_key key; + struct ovs_tunnel_info *tun_info; + struct nlattr *a; int err, start; ovs_match_init(&match, &key, NULL); @@ -1279,8 +1294,14 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (start < 0) return start; - err = add_action(sfa, OVS_KEY_ATTR_IPV4_TUNNEL, &match.key->tun_key, - sizeof(match.key->tun_key)); + a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, + sizeof(*tun_info)); + if (IS_ERR(a)) + return PTR_ERR(a); + + tun_info = nla_data(a); + tun_info->tunnel = key.tun_key; + add_nested_action_end(*sfa, start); return err; @@ -1563,17 +1584,20 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) int err; switch (key_type) { - case OVS_KEY_ATTR_IPV4_TUNNEL: + case OVS_KEY_ATTR_TUNNEL_INFO: { + struct ovs_tunnel_info *tun_info = nla_data(ovs_key); + start = nla_nest_start(skb, OVS_ACTION_ATTR_SET); if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, nla_data(ovs_key), - nla_data(ovs_key)); + err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel, + nla_data(ovs_key)); if (err) return err; nla_nest_end(skb, start); break; + } default: if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key)) return -EMSGSIZE; diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 309cca6e816f..fe768bd600eb 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -63,8 +63,10 @@ static __be16 filter_tnl_flags(__be16 flags) static struct sk_buff *__build_header(struct sk_buff *skb, int tunnel_hlen) { - const struct ovs_key_ipv4_tunnel *tun_key = OVS_CB(skb)->egress_tun_key; struct tnl_ptk_info tpi; + const struct ovs_key_ipv4_tunnel *tun_key; + + tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM)); if (IS_ERR(skb)) @@ -92,7 +94,7 @@ static __be64 key_to_tunnel_id(__be32 key, __be32 seq) static int gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) { - struct ovs_key_ipv4_tunnel tun_key; + struct ovs_tunnel_info tun_info; struct ovs_net *ovs_net; struct vport *vport; __be64 key; @@ -103,10 +105,10 @@ static int gre_rcv(struct sk_buff *skb, return PACKET_REJECT; key = key_to_tunnel_id(tpi->key, tpi->seq); - ovs_flow_tun_key_init(&tun_key, ip_hdr(skb), key, - filter_tnl_flags(tpi->flags)); + ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, + filter_tnl_flags(tpi->flags)); - ovs_vport_receive(vport, skb, &tun_key); + ovs_vport_receive(vport, skb, &tun_info); return PACKET_RCVD; } @@ -137,12 +139,12 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) __be16 df; int err; - if (unlikely(!OVS_CB(skb)->egress_tun_key)) { + if (unlikely(!OVS_CB(skb)->egress_tun_info)) { err = -EINVAL; goto error; } - tun_key = OVS_CB(skb)->egress_tun_key; + tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; /* Route lookup */ memset(&fl, 0, sizeof(fl)); fl.daddr = tun_key->ipv4_dst; diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index f19539bb8adc..5fbff2c1ee49 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -58,7 +58,7 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport) /* Called with rcu_read_lock and BH disabled. */ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni) { - struct ovs_key_ipv4_tunnel tun_key; + struct ovs_tunnel_info tun_info; struct vport *vport = vs->data; struct iphdr *iph; __be64 key; @@ -66,9 +66,9 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni) /* Save outer tunnel values */ iph = ip_hdr(skb); key = cpu_to_be64(ntohl(vx_vni) >> 8); - ovs_flow_tun_key_init(&tun_key, iph, key, TUNNEL_KEY); + ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY); - ovs_vport_receive(vport, skb, &tun_key); + ovs_vport_receive(vport, skb, &tun_info); } static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) @@ -147,12 +147,12 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) __be16 df; int err; - if (unlikely(!OVS_CB(skb)->egress_tun_key)) { + if (unlikely(!OVS_CB(skb)->egress_tun_info)) { err = -EINVAL; goto error; } - tun_key = OVS_CB(skb)->egress_tun_key; + tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; /* Route lookup */ memset(&fl, 0, sizeof(fl)); fl.daddr = tun_key->ipv4_dst; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 5df8377fcfb1..3e50ee8a218c 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -432,7 +432,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *p, struct sk_buff *skb) * skb->data should point to the Ethernet header. */ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, - struct ovs_key_ipv4_tunnel *tun_key) + struct ovs_tunnel_info *tun_info) { struct pcpu_sw_netstats *stats; struct sw_flow_key key; @@ -445,9 +445,9 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, u64_stats_update_end(&stats->syncp); OVS_CB(skb)->input_vport = vport; - OVS_CB(skb)->egress_tun_key = NULL; + OVS_CB(skb)->egress_tun_info = NULL; /* Extract flow from 'skb' into 'key'. */ - error = ovs_flow_key_extract(tun_key, skb, &key); + error = ovs_flow_key_extract(tun_info, skb, &key); if (unlikely(error)) { kfree_skb(skb); return; diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 0efd62fef1e8..e28964aba021 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -207,7 +207,7 @@ static inline struct vport *vport_from_priv(void *priv) } void ovs_vport_receive(struct vport *, struct sk_buff *, - struct ovs_key_ipv4_tunnel *); + struct ovs_tunnel_info *); /* List of statically compiled vport implementations. Don't forget to also * add yours to the list at the top of vport.c. */ -- cgit v1.2.3 From 6b205b2ca17e88ef5e10451b720056b790cc63a5 Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Fri, 3 Oct 2014 15:35:32 -0700 Subject: openvswitch: Factor out allocation and verification of actions. As the size of the flow key grows, it can put some pressure on the stack. This is particularly true in ovs_flow_cmd_set(), which needs several copies of the key on the stack. One of those uses is logically separate, so this factors it out to reduce stack pressure and improve readibility. Signed-off-by: Jesse Gross Signed-off-by: Andy Zhou Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/datapath.c | 38 +++++++++++++++++++++++++++----------- 1 file changed, 27 insertions(+), 11 deletions(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f6bd93d5f435..010125c48244 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -933,11 +933,34 @@ error: return error; } +static struct sw_flow_actions *get_flow_actions(const struct nlattr *a, + const struct sw_flow_key *key, + const struct sw_flow_mask *mask) +{ + struct sw_flow_actions *acts; + struct sw_flow_key masked_key; + int error; + + acts = ovs_nla_alloc_flow_actions(nla_len(a)); + if (IS_ERR(acts)) + return acts; + + ovs_flow_mask_key(&masked_key, key, mask); + error = ovs_nla_copy_actions(a, &masked_key, 0, &acts); + if (error) { + OVS_NLERR("Flow actions may not be safe on all matching packets.\n"); + kfree(acts); + return ERR_PTR(error); + } + + return acts; +} + static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = info->userhdr; - struct sw_flow_key key, masked_key; + struct sw_flow_key key; struct sw_flow *flow; struct sw_flow_mask mask; struct sk_buff *reply = NULL; @@ -959,17 +982,10 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) /* Validate actions. */ if (a[OVS_FLOW_ATTR_ACTIONS]) { - acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS])); - error = PTR_ERR(acts); - if (IS_ERR(acts)) + acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask); + if (IS_ERR(acts)) { + error = PTR_ERR(acts); goto error; - - ovs_flow_mask_key(&masked_key, &key, &mask); - error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], - &masked_key, 0, &acts); - if (error) { - OVS_NLERR("Flow actions may not be safe on all matching packets.\n"); - goto err_kfree_acts; } } -- cgit v1.2.3 From f5796684069e0c71c65bce6a6d4766114aec1396 Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Fri, 3 Oct 2014 15:35:33 -0700 Subject: openvswitch: Add support for Geneve tunneling. The Openvswitch implementation is completely agnostic to the options that are in use and can handle newly defined options without further work. It does this by simply matching on a byte array of options and allowing userspace to setup flows on this array. Signed-off-by: Jesse Gross Singed-off-by: Ansis Atteka Signed-off-by: Andy Zhou Acked-by: Thomas Graf Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 21 ++-- include/uapi/linux/openvswitch.h | 2 + net/openvswitch/Kconfig | 11 ++ net/openvswitch/Makefile | 4 + net/openvswitch/datapath.c | 5 +- net/openvswitch/flow.c | 20 +++- net/openvswitch/flow.h | 20 +++- net/openvswitch/flow_netlink.c | 176 ++++++++++++++++++++++++----- net/openvswitch/vport-geneve.c | 236 +++++++++++++++++++++++++++++++++++++++ net/openvswitch/vport-gre.c | 2 +- net/openvswitch/vport-vxlan.c | 2 +- net/openvswitch/vport.c | 3 + net/openvswitch/vport.h | 1 + 13 files changed, 461 insertions(+), 42 deletions(-) create mode 100644 net/openvswitch/vport-geneve.c diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index a9ce1556d773..5bc6edeb7143 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -86,17 +86,18 @@ struct ip_tunnel { struct gro_cells gro_cells; }; -#define TUNNEL_CSUM __cpu_to_be16(0x01) -#define TUNNEL_ROUTING __cpu_to_be16(0x02) -#define TUNNEL_KEY __cpu_to_be16(0x04) -#define TUNNEL_SEQ __cpu_to_be16(0x08) -#define TUNNEL_STRICT __cpu_to_be16(0x10) -#define TUNNEL_REC __cpu_to_be16(0x20) -#define TUNNEL_VERSION __cpu_to_be16(0x40) -#define TUNNEL_NO_KEY __cpu_to_be16(0x80) +#define TUNNEL_CSUM __cpu_to_be16(0x01) +#define TUNNEL_ROUTING __cpu_to_be16(0x02) +#define TUNNEL_KEY __cpu_to_be16(0x04) +#define TUNNEL_SEQ __cpu_to_be16(0x08) +#define TUNNEL_STRICT __cpu_to_be16(0x10) +#define TUNNEL_REC __cpu_to_be16(0x20) +#define TUNNEL_VERSION __cpu_to_be16(0x40) +#define TUNNEL_NO_KEY __cpu_to_be16(0x80) #define TUNNEL_DONT_FRAGMENT __cpu_to_be16(0x0100) -#define TUNNEL_OAM __cpu_to_be16(0x0200) -#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400) +#define TUNNEL_OAM __cpu_to_be16(0x0200) +#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400) +#define TUNNEL_OPTIONS_PRESENT __cpu_to_be16(0x0800) struct tnl_ptk_info { __be16 flags; diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 6753032832e2..435eabc5ffaa 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -192,6 +192,7 @@ enum ovs_vport_type { OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */ OVS_VPORT_TYPE_GRE, /* GRE tunnel. */ OVS_VPORT_TYPE_VXLAN, /* VXLAN tunnel. */ + OVS_VPORT_TYPE_GENEVE, /* Geneve tunnel. */ __OVS_VPORT_TYPE_MAX }; @@ -310,6 +311,7 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT, /* No argument, set DF. */ OVS_TUNNEL_KEY_ATTR_CSUM, /* No argument. CSUM packet. */ OVS_TUNNEL_KEY_ATTR_OAM, /* No argument. OAM frame. */ + OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, /* Array of Geneve options. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 6ecf491ad509..ba3bb8203b99 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -54,3 +54,14 @@ config OPENVSWITCH_VXLAN Say N to exclude this support and reduce the binary size. If unsure, say Y. + +config OPENVSWITCH_GENEVE + bool "Open vSwitch Geneve tunneling support" + depends on INET + depends on OPENVSWITCH + depends on GENEVE && !(OPENVSWITCH=y && GENEVE=m) + default y + ---help--- + If you say Y here, then the Open vSwitch will be able create geneve vport. + + Say N to exclude this support and reduce the binary size. diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 3591cb5dae91..9a33a273c375 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -15,6 +15,10 @@ openvswitch-y := \ vport-internal_dev.o \ vport-netdev.o +ifneq ($(CONFIG_OPENVSWITCH_GENEVE),) +openvswitch-y += vport-geneve.o +endif + ifneq ($(CONFIG_OPENVSWITCH_VXLAN),) openvswitch-y += vport-vxlan.o endif diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 010125c48244..2e31d9e7f4dc 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -370,6 +370,7 @@ static size_t key_attr_size(void) + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */ + + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */ + nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */ + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ @@ -556,10 +557,12 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS], &flow->key, 0, &acts); - rcu_assign_pointer(flow->sf_acts, acts); if (err) goto err_flow_free; + rcu_assign_pointer(flow->sf_acts, acts); + + OVS_CB(packet)->egress_tun_info = NULL; OVS_CB(packet)->flow = flow; packet->priority = flow->key.phy.priority; packet->mark = flow->key.phy.skb_mark; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 2924cb340868..62db02ba36bc 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -448,6 +448,9 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) int error; struct ethhdr *eth; + /* Flags are always used as part of stats */ + key->tp.flags = 0; + skb_reset_mac_header(skb); /* Link layer. We are guaranteed to have at least the 14 byte Ethernet @@ -646,10 +649,23 @@ int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key) { /* Extract metadata from packet. */ - if (tun_info) + if (tun_info) { memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key)); - else + + if (tun_info->options) { + BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) * + 8)) - 1 + > sizeof(key->tun_opts)); + memcpy(GENEVE_OPTS(key, tun_info->options_len), + tun_info->options, tun_info->options_len); + key->tun_opts_len = tun_info->options_len; + } else { + key->tun_opts_len = 0; + } + } else { + key->tun_opts_len = 0; memset(&key->tun_key, 0, sizeof(key->tun_key)); + } key->phy.priority = skb->priority; key->phy.in_port = OVS_CB(skb)->input_vport->port_no; diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index fe5a71b81c1f..71813318c8c7 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -51,11 +51,24 @@ struct ovs_key_ipv4_tunnel { struct ovs_tunnel_info { struct ovs_key_ipv4_tunnel tunnel; + struct geneve_opt *options; + u8 options_len; }; +/* Store options at the end of the array if they are less than the + * maximum size. This allows us to get the benefits of variable length + * matching for small options. + */ +#define GENEVE_OPTS(flow_key, opt_len) \ + ((struct geneve_opt *)((flow_key)->tun_opts + \ + FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \ + opt_len)) + static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, const struct iphdr *iph, - __be64 tun_id, __be16 tun_flags) + __be64 tun_id, __be16 tun_flags, + struct geneve_opt *opts, + u8 opts_len) { tun_info->tunnel.tun_id = tun_id; tun_info->tunnel.ipv4_src = iph->saddr; @@ -67,9 +80,14 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, /* clear struct padding. */ memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE); + + tun_info->options = opts; + tun_info->options_len = opts_len; } struct sw_flow_key { + u8 tun_opts[255]; + u8 tun_opts_len; struct ovs_key_ipv4_tunnel tun_key; /* Encapsulating tunnel key. */ struct { u32 priority; /* Packet QoS priority. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 5d6194d9dadc..368f23307911 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -88,18 +89,20 @@ static void update_range__(struct sw_flow_match *match, } \ } while (0) -#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \ - do { \ - update_range__(match, offsetof(struct sw_flow_key, field), \ - len, is_mask); \ - if (is_mask) { \ - if ((match)->mask) \ - memcpy(&(match)->mask->key.field, value_p, len);\ - } else { \ - memcpy(&(match)->key->field, value_p, len); \ - } \ +#define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask) \ + do { \ + update_range__(match, offset, len, is_mask); \ + if (is_mask) \ + memcpy((u8 *)&(match)->mask->key + offset, value_p, \ + len); \ + else \ + memcpy((u8 *)(match)->key + offset, value_p, len); \ } while (0) +#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \ + SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \ + value_p, len, is_mask) + static u16 range_n_bytes(const struct sw_flow_key_range *range) { return range->end - range->start; @@ -335,6 +338,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, int rem; bool ttl = false; __be16 tun_flags = 0; + unsigned long opt_key_offset; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); @@ -347,6 +351,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0, [OVS_TUNNEL_KEY_ATTR_CSUM] = 0, [OVS_TUNNEL_KEY_ATTR_OAM] = 0, + [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1, }; if (type > OVS_TUNNEL_KEY_ATTR_MAX) { @@ -355,7 +360,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, return -EINVAL; } - if (ovs_tunnel_key_lens[type] != nla_len(a)) { + if (ovs_tunnel_key_lens[type] != nla_len(a) && + ovs_tunnel_key_lens[type] != -1) { OVS_NLERR("IPv4 tunnel attribute type has unexpected " " length (type=%d, length=%d, expected=%d).\n", type, nla_len(a), ovs_tunnel_key_lens[type]); @@ -394,7 +400,60 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_OAM: tun_flags |= TUNNEL_OAM; break; + case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: + tun_flags |= TUNNEL_OPTIONS_PRESENT; + if (nla_len(a) > sizeof(match->key->tun_opts)) { + OVS_NLERR("Geneve option length exceeds maximum size (len %d, max %zu).\n", + nla_len(a), + sizeof(match->key->tun_opts)); + return -EINVAL; + } + + if (nla_len(a) % 4 != 0) { + OVS_NLERR("Geneve option length is not a multiple of 4 (len %d).\n", + nla_len(a)); + return -EINVAL; + } + + /* We need to record the length of the options passed + * down, otherwise packets with the same format but + * additional options will be silently matched. + */ + if (!is_mask) { + SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a), + false); + } else { + /* This is somewhat unusual because it looks at + * both the key and mask while parsing the + * attributes (and by extension assumes the key + * is parsed first). Normally, we would verify + * that each is the correct length and that the + * attributes line up in the validate function. + * However, that is difficult because this is + * variable length and we won't have the + * information later. + */ + if (match->key->tun_opts_len != nla_len(a)) { + OVS_NLERR("Geneve option key length (%d) is different from mask length (%d).", + match->key->tun_opts_len, + nla_len(a)); + return -EINVAL; + } + + SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, + true); + } + + opt_key_offset = (unsigned long)GENEVE_OPTS( + (struct sw_flow_key *)0, + nla_len(a)); + SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, + nla_data(a), nla_len(a), + is_mask); + break; default: + OVS_NLERR("Unknown IPv4 tunnel attribute (%d).\n", + type); return -EINVAL; } } @@ -421,16 +480,11 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, return 0; } -static int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *tun_key, - const struct ovs_key_ipv4_tunnel *output) +static int __ipv4_tun_to_nlattr(struct sk_buff *skb, + const struct ovs_key_ipv4_tunnel *output, + const struct geneve_opt *tun_opts, + int swkey_tun_opts_len) { - struct nlattr *nla; - - nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL); - if (!nla) - return -EMSGSIZE; - if (output->tun_flags & TUNNEL_KEY && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) return -EMSGSIZE; @@ -454,12 +508,35 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, if ((output->tun_flags & TUNNEL_OAM) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; + if (tun_opts && + nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, + swkey_tun_opts_len, tun_opts)) + return -EMSGSIZE; - nla_nest_end(skb, nla); return 0; } +static int ipv4_tun_to_nlattr(struct sk_buff *skb, + const struct ovs_key_ipv4_tunnel *output, + const struct geneve_opt *tun_opts, + int swkey_tun_opts_len) +{ + struct nlattr *nla; + int err; + + nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL); + if (!nla) + return -EMSGSIZE; + + err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len); + if (err) + return err; + + nla_nest_end(skb, nla); + return 0; +} + static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs, const struct nlattr **a, bool is_mask) { @@ -905,9 +982,16 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority)) goto nla_put_failure; - if ((swkey->tun_key.ipv4_dst || is_mask) && - ipv4_tun_to_nlattr(skb, &swkey->tun_key, &output->tun_key)) - goto nla_put_failure; + if ((swkey->tun_key.ipv4_dst || is_mask)) { + const struct geneve_opt *opts = NULL; + + if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) + opts = GENEVE_OPTS(output, swkey->tun_opts_len); + + if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts, + swkey->tun_opts_len)) + goto nla_put_failure; + } if (swkey->phy.in_port == DP_MAX_PORTS) { if (is_mask && (output->phy.in_port == 0xffff)) @@ -1290,17 +1374,55 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (err) return err; + if (key.tun_opts_len) { + struct geneve_opt *option = GENEVE_OPTS(&key, + key.tun_opts_len); + int opts_len = key.tun_opts_len; + bool crit_opt = false; + + while (opts_len > 0) { + int len; + + if (opts_len < sizeof(*option)) + return -EINVAL; + + len = sizeof(*option) + option->length * 4; + if (len > opts_len) + return -EINVAL; + + crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE); + + option = (struct geneve_opt *)((u8 *)option + len); + opts_len -= len; + }; + + key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + }; + start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET); if (start < 0) return start; a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, - sizeof(*tun_info)); + sizeof(*tun_info) + key.tun_opts_len); if (IS_ERR(a)) return PTR_ERR(a); tun_info = nla_data(a); tun_info->tunnel = key.tun_key; + tun_info->options_len = key.tun_opts_len; + + if (tun_info->options_len) { + /* We need to store the options in the action itself since + * everything else will go away after flow setup. We can append + * it to tun_info and then point there. + */ + memcpy((tun_info + 1), GENEVE_OPTS(&key, key.tun_opts_len), + key.tun_opts_len); + tun_info->options = (struct geneve_opt *)(tun_info + 1); + } else { + tun_info->options = NULL; + } add_nested_action_end(*sfa, start); @@ -1592,7 +1714,9 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) return -EMSGSIZE; err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel, - nla_data(ovs_key)); + tun_info->options_len ? + tun_info->options : NULL, + tun_info->options_len); if (err) return err; nla_nest_end(skb, start); diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c new file mode 100644 index 000000000000..5572d482f285 --- /dev/null +++ b/net/openvswitch/vport-geneve.c @@ -0,0 +1,236 @@ +/* + * Copyright (c) 2014 Nicira, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +#include "datapath.h" +#include "vport.h" + +/** + * struct geneve_port - Keeps track of open UDP ports + * @sock: The socket created for this port number. + * @name: vport name. + */ +struct geneve_port { + struct geneve_sock *gs; + char name[IFNAMSIZ]; +}; + +static LIST_HEAD(geneve_ports); + +static inline struct geneve_port *geneve_vport(const struct vport *vport) +{ + return vport_priv(vport); +} + +static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) +{ + return (struct genevehdr *)(udp_hdr(skb) + 1); +} + +/* Convert 64 bit tunnel ID to 24 bit VNI. */ +static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) +{ +#ifdef __BIG_ENDIAN + vni[0] = (__force __u8)(tun_id >> 16); + vni[1] = (__force __u8)(tun_id >> 8); + vni[2] = (__force __u8)tun_id; +#else + vni[0] = (__force __u8)((__force u64)tun_id >> 40); + vni[1] = (__force __u8)((__force u64)tun_id >> 48); + vni[2] = (__force __u8)((__force u64)tun_id >> 56); +#endif +} + +/* Convert 24 bit VNI to 64 bit tunnel ID. */ +static __be64 vni_to_tunnel_id(__u8 *vni) +{ +#ifdef __BIG_ENDIAN + return (vni[0] << 16) | (vni[1] << 8) | vni[2]; +#else + return (__force __be64)(((__force u64)vni[0] << 40) | + ((__force u64)vni[1] << 48) | + ((__force u64)vni[2] << 56)); +#endif +} + +static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb) +{ + struct vport *vport = gs->rcv_data; + struct genevehdr *geneveh = geneve_hdr(skb); + int opts_len; + struct ovs_tunnel_info tun_info; + __be64 key; + __be16 flags; + + opts_len = geneveh->opt_len * 4; + + flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT | + (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) | + (geneveh->oam ? TUNNEL_OAM : 0) | + (geneveh->critical ? TUNNEL_CRIT_OPT : 0); + + key = vni_to_tunnel_id(geneveh->vni); + + ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags, + geneveh->options, opts_len); + + ovs_vport_receive(vport, skb, &tun_info); +} + +static int geneve_get_options(const struct vport *vport, + struct sk_buff *skb) +{ + struct geneve_port *geneve_port = geneve_vport(vport); + __be16 sport; + + sport = ntohs(inet_sk(geneve_port->gs->sock->sk)->inet_sport); + if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, sport)) + return -EMSGSIZE; + return 0; +} + +static void geneve_tnl_destroy(struct vport *vport) +{ + struct geneve_port *geneve_port = geneve_vport(vport); + + geneve_sock_release(geneve_port->gs); + + ovs_vport_deferred_free(vport); +} + +static struct vport *geneve_tnl_create(const struct vport_parms *parms) +{ + struct net *net = ovs_dp_get_net(parms->dp); + struct nlattr *options = parms->options; + struct geneve_port *geneve_port; + struct geneve_sock *gs; + struct vport *vport; + struct nlattr *a; + int err; + u16 dst_port; + + if (!options) { + err = -EINVAL; + goto error; + } + + a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT); + if (a && nla_len(a) == sizeof(u16)) { + dst_port = nla_get_u16(a); + } else { + /* Require destination port from userspace. */ + err = -EINVAL; + goto error; + } + + vport = ovs_vport_alloc(sizeof(struct geneve_port), + &ovs_geneve_vport_ops, parms); + if (IS_ERR(vport)) + return vport; + + geneve_port = geneve_vport(vport); + strncpy(geneve_port->name, parms->name, IFNAMSIZ); + + gs = geneve_sock_add(net, htons(dst_port), geneve_rcv, vport, true, 0); + if (IS_ERR(gs)) { + ovs_vport_free(vport); + return (void *)gs; + } + geneve_port->gs = gs; + + return vport; +error: + return ERR_PTR(err); +} + +static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) +{ + struct ovs_key_ipv4_tunnel *tun_key; + struct ovs_tunnel_info *tun_info; + struct net *net = ovs_dp_get_net(vport->dp); + struct geneve_port *geneve_port = geneve_vport(vport); + __be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport; + __be16 sport; + struct rtable *rt; + struct flowi4 fl; + u8 vni[3]; + __be16 df; + int err; + + tun_info = OVS_CB(skb)->egress_tun_info; + if (unlikely(!tun_info)) { + err = -EINVAL; + goto error; + } + + tun_key = &tun_info->tunnel; + + /* Route lookup */ + memset(&fl, 0, sizeof(fl)); + fl.daddr = tun_key->ipv4_dst; + fl.saddr = tun_key->ipv4_src; + fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); + fl.flowi4_mark = skb->mark; + fl.flowi4_proto = IPPROTO_UDP; + + rt = ip_route_output_key(net, &fl); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + goto error; + } + + df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true); + tunnel_id_to_vni(tun_key->tun_id, vni); + skb->ignore_df = 1; + + err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr, + tun_key->ipv4_dst, tun_key->ipv4_tos, + tun_key->ipv4_ttl, df, sport, dport, + tun_key->tun_flags, vni, + tun_info->options_len, (u8 *)tun_info->options, + false); + if (err < 0) + ip_rt_put(rt); +error: + return err; +} + +static const char *geneve_get_name(const struct vport *vport) +{ + struct geneve_port *geneve_port = geneve_vport(vport); + + return geneve_port->name; +} + +const struct vport_ops ovs_geneve_vport_ops = { + .type = OVS_VPORT_TYPE_GENEVE, + .create = geneve_tnl_create, + .destroy = geneve_tnl_destroy, + .get_name = geneve_get_name, + .get_options = geneve_get_options, + .send = geneve_tnl_send, +}; diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index fe768bd600eb..108b82da2fd9 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -106,7 +106,7 @@ static int gre_rcv(struct sk_buff *skb, key = key_to_tunnel_id(tpi->key, tpi->seq); ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, - filter_tnl_flags(tpi->flags)); + filter_tnl_flags(tpi->flags), NULL, 0); ovs_vport_receive(vport, skb, &tun_info); return PACKET_RCVD; diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 5fbff2c1ee49..2735e01dca73 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -66,7 +66,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni) /* Save outer tunnel values */ iph = ip_hdr(skb); key = cpu_to_be64(ntohl(vx_vni) >> 8); - ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY); + ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0); ovs_vport_receive(vport, skb, &tun_info); } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 3e50ee8a218c..53001b020ca7 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -48,6 +48,9 @@ static const struct vport_ops *vport_ops_list[] = { #ifdef CONFIG_OPENVSWITCH_VXLAN &ovs_vxlan_vport_ops, #endif +#ifdef CONFIG_OPENVSWITCH_GENEVE + &ovs_geneve_vport_ops, +#endif }; /* Protected by RCU read lock for reading, ovs_mutex for writing. */ diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index e28964aba021..8942125de3a6 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -215,6 +215,7 @@ extern const struct vport_ops ovs_netdev_vport_ops; extern const struct vport_ops ovs_internal_vport_ops; extern const struct vport_ops ovs_gre_vport_ops; extern const struct vport_ops ovs_vxlan_vport_ops; +extern const struct vport_ops ovs_geneve_vport_ops; static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) -- cgit v1.2.3