From 0b5e8b8eeae40bae6ad7c7e91c97c3c0d0e57882 Mon Sep 17 00:00:00 2001 From: Andy Zhou Date: Fri, 3 Oct 2014 15:35:28 -0700 Subject: [PATCH] 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");