From 6713fc9b8fa33444aa000f0f31076f6a859ccb34 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 4 May 2015 14:34:05 -0700 Subject: openvswitch: Use eth_proto_is_802_3 Replace "ntohs(proto) >= ETH_P_802_3_MIN" w/ eth_proto_is_802_3(proto). Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/openvswitch/datapath.c | 2 +- net/openvswitch/flow.c | 4 ++-- net/openvswitch/flow_netlink.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'net/openvswitch') diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 096c6276e6b9..3b90461317ec 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -545,7 +545,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) /* Normally, setting the skb 'protocol' field would be handled by a * call to eth_type_trans(), but it assumes there's a sending * device, which we may not have. */ - if (ntohs(eth->h_proto) >= ETH_P_802_3_MIN) + if (eth_proto_is_802_3(eth->h_proto)) packet->protocol = eth->h_proto; else packet->protocol = htons(ETH_P_802_2); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 2dacc7b5af23..bc7b0aba994a 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -332,7 +332,7 @@ static __be16 parse_ethertype(struct sk_buff *skb) proto = *(__be16 *) skb->data; __skb_pull(skb, sizeof(__be16)); - if (ntohs(proto) >= ETH_P_802_3_MIN) + if (eth_proto_is_802_3(proto)) return proto; if (skb->len < sizeof(struct llc_snap_hdr)) @@ -349,7 +349,7 @@ static __be16 parse_ethertype(struct sk_buff *skb) __skb_pull(skb, sizeof(struct llc_snap_hdr)); - if (ntohs(llc->ethertype) >= ETH_P_802_3_MIN) + if (eth_proto_is_802_3(llc->ethertype)) return llc->ethertype; return htons(ETH_P_802_2); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c691b1a1eee0..624e41c4267f 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -816,7 +816,7 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, if (is_mask) { /* Always exact match EtherType. */ eth_type = htons(0xffff); - } else if (ntohs(eth_type) < ETH_P_802_3_MIN) { + } else if (!eth_proto_is_802_3(eth_type)) { OVS_NLERR(log, "EtherType %x is less than min %x", ntohs(eth_type), ETH_P_802_3_MIN); return -EINVAL; -- cgit v1.2.3 From 35d32e8fe4ab44180e46a0dd54abea6985398d00 Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Wed, 13 May 2015 12:57:27 -0400 Subject: geneve: move definition of geneve_hdr() to geneve.h This is a static inline with identical definitions in multiple places... Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/net/geneve.h | 5 +++++ net/ipv4/geneve.c | 5 ----- net/openvswitch/vport-geneve.c | 5 ----- 3 files changed, 5 insertions(+), 10 deletions(-) (limited to 'net/openvswitch') diff --git a/include/net/geneve.h b/include/net/geneve.h index 14fb8d3390b4..2a0543a1899d 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -62,6 +62,11 @@ struct genevehdr { struct geneve_opt options[]; }; +static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) +{ + return (struct genevehdr *)(udp_hdr(skb) + 1); +} + #ifdef CONFIG_INET struct geneve_sock; diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c index 8e6a7fe27a4c..001843d41135 100644 --- a/net/ipv4/geneve.c +++ b/net/ipv4/geneve.c @@ -60,11 +60,6 @@ struct geneve_net { static int geneve_net_id; -static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) -{ - return (struct genevehdr *)(udp_hdr(skb) + 1); -} - static struct geneve_sock *geneve_find_sock(struct net *net, sa_family_t family, __be16 port) { diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index bf02fd5808c9..208c576bd1b6 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -46,11 +46,6 @@ 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) { -- cgit v1.2.3 From 11e1fa46b43216458e0f67f1f0b257586c5d8e5c Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Wed, 13 May 2015 12:57:28 -0400 Subject: geneve: Rename support library as geneve_core net/ipv4/geneve.c -> net/ipv4/geneve_core.c This name better reflects the purpose of the module. Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- net/ipv4/Kconfig | 4 +- net/ipv4/Makefile | 2 +- net/ipv4/geneve.c | 447 ------------------------------------------------ net/ipv4/geneve_core.c | 447 ++++++++++++++++++++++++++++++++++++++++++++++++ net/openvswitch/Kconfig | 2 +- 5 files changed, 451 insertions(+), 451 deletions(-) delete mode 100644 net/ipv4/geneve.c create mode 100644 net/ipv4/geneve_core.c (limited to 'net/openvswitch') diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index bd2901604842..d83071dccd74 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -331,8 +331,8 @@ config NET_FOU_IP_TUNNELS When this option is enabled IP tunnels can be configured to use FOU or GUE encapsulation. -config GENEVE - tristate "Generic Network Virtualization Encapsulation (Geneve)" +config GENEVE_CORE + tristate "Generic Network Virtualization Encapsulation library" depends on INET select NET_UDP_TUNNEL ---help--- diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 518c04ed666e..b36236dd6014 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -56,7 +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_GENEVE_CORE) += geneve_core.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 deleted file mode 100644 index 001843d41135..000000000000 --- a/net/ipv4/geneve.c +++ /dev/null @@ -1,447 +0,0 @@ -/* - * 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 - -/* Protects sock_list and refcounts. */ -static DEFINE_MUTEX(geneve_mutex); - -/* per-network namespace private data for this module */ -struct geneve_net { - struct list_head sock_list; -}; - -static int geneve_net_id; - -static struct geneve_sock *geneve_find_sock(struct net *net, - sa_family_t family, __be16 port) -{ - struct geneve_net *gn = net_generic(net, geneve_net_id); - struct geneve_sock *gs; - - list_for_each_entry(gs, &gn->sock_list, list) { - if (inet_sk(gs->sock->sk)->inet_sport == port && - inet_sk(gs->sock->sk)->sk.sk_family == family) - 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 formatted 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 csum, bool xnet) -{ - struct genevehdr *gnvh; - int min_headroom; - int err; - - 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); - return err; - } - - skb = vlan_hwaccel_push_inside(skb); - if (unlikely(!skb)) - return -ENOMEM; - - skb = udp_tunnel_handle_offloads(skb, csum); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); - geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); - - skb_set_inner_protocol(skb, htons(ETH_P_TEB)); - - return udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, src, dst, - tos, ttl, df, src_port, dst_port, xnet, - !csum); -} -EXPORT_SYMBOL_GPL(geneve_xmit_skb); - -static int geneve_hlen(struct genevehdr *gh) -{ - return sizeof(*gh) + gh->opt_len * 4; -} - -static struct sk_buff **geneve_gro_receive(struct sk_buff **head, - struct sk_buff *skb, - struct udp_offload *uoff) -{ - struct sk_buff *p, **pp = NULL; - struct genevehdr *gh, *gh2; - unsigned int hlen, gh_len, off_gnv; - const struct packet_offload *ptype; - __be16 type; - int flush = 1; - - off_gnv = skb_gro_offset(skb); - hlen = off_gnv + sizeof(*gh); - gh = skb_gro_header_fast(skb, off_gnv); - if (skb_gro_header_hard(skb, hlen)) { - gh = skb_gro_header_slow(skb, hlen, off_gnv); - if (unlikely(!gh)) - goto out; - } - - if (gh->ver != GENEVE_VER || gh->oam) - goto out; - gh_len = geneve_hlen(gh); - - hlen = off_gnv + gh_len; - if (skb_gro_header_hard(skb, hlen)) { - gh = skb_gro_header_slow(skb, hlen, off_gnv); - if (unlikely(!gh)) - goto out; - } - - flush = 0; - - for (p = *head; p; p = p->next) { - if (!NAPI_GRO_CB(p)->same_flow) - continue; - - gh2 = (struct genevehdr *)(p->data + off_gnv); - if (gh->opt_len != gh2->opt_len || - memcmp(gh, gh2, gh_len)) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - } - - type = gh->proto_type; - - rcu_read_lock(); - ptype = gro_find_receive_by_type(type); - if (!ptype) { - flush = 1; - goto out_unlock; - } - - skb_gro_pull(skb, gh_len); - skb_gro_postpull_rcsum(skb, gh, gh_len); - pp = ptype->callbacks.gro_receive(head, skb); - -out_unlock: - rcu_read_unlock(); -out: - NAPI_GRO_CB(skb)->flush |= flush; - - return pp; -} - -static int geneve_gro_complete(struct sk_buff *skb, int nhoff, - struct udp_offload *uoff) -{ - struct genevehdr *gh; - struct packet_offload *ptype; - __be16 type; - int gh_len; - int err = -ENOSYS; - - udp_tunnel_gro_complete(skb, nhoff); - - gh = (struct genevehdr *)(skb->data + nhoff); - gh_len = geneve_hlen(gh); - type = gh->proto_type; - - rcu_read_lock(); - ptype = gro_find_complete_by_type(type); - if (ptype) - err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); - - rcu_read_unlock(); - return err; -} - -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); - } -} - -static void geneve_notify_del_rx_port(struct geneve_sock *gs) -{ - struct sock *sk = gs->sock->sk; - sa_family_t sa_family = sk->sk_family; - - if (sa_family == AF_INET) - udp_del_offload(&gs->udp_offloads); -} - -/* 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 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 = htonl(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); - - sock = geneve_create_sock(net, ipv6, port); - if (IS_ERR(sock)) { - kfree(gs); - return ERR_CAST(sock); - } - - gs->sock = sock; - 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 = geneve_gro_receive; - gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete; - geneve_notify_add_rx_port(gs); - - /* 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); - - list_add(&gs->list, &gn->sock_list); - - 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; - - mutex_lock(&geneve_mutex); - - gs = geneve_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port); - if (gs) { - if (!no_share && gs->rcv == rcv) - gs->refcnt++; - else - gs = ERR_PTR(-EBUSY); - } else { - gs = geneve_socket_create(net, port, rcv, data, ipv6); - } - - mutex_unlock(&geneve_mutex); - - return gs; -} -EXPORT_SYMBOL_GPL(geneve_sock_add); - -void geneve_sock_release(struct geneve_sock *gs) -{ - mutex_lock(&geneve_mutex); - - if (--gs->refcnt) - goto unlock; - - list_del(&gs->list); - geneve_notify_del_rx_port(gs); - udp_tunnel_sock_release(gs->sock); - kfree_rcu(gs, rcu); - -unlock: - mutex_unlock(&geneve_mutex); -} -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); - - INIT_LIST_HEAD(&gn->sock_list); - - return 0; -} - -static struct pernet_operations geneve_net_ops = { - .init = geneve_init_net, - .id = &geneve_net_id, - .size = sizeof(struct geneve_net), -}; - -static int __init geneve_init_module(void) -{ - int rc; - - rc = register_pernet_subsys(&geneve_net_ops); - if (rc) - return rc; - - pr_info("Geneve driver\n"); - - return 0; -} -module_init(geneve_init_module); - -static void __exit geneve_cleanup_module(void) -{ - unregister_pernet_subsys(&geneve_net_ops); -} -module_exit(geneve_cleanup_module); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jesse Gross "); -MODULE_DESCRIPTION("Driver for GENEVE encapsulated traffic"); diff --git a/net/ipv4/geneve_core.c b/net/ipv4/geneve_core.c new file mode 100644 index 000000000000..001843d41135 --- /dev/null +++ b/net/ipv4/geneve_core.c @@ -0,0 +1,447 @@ +/* + * 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 + +/* Protects sock_list and refcounts. */ +static DEFINE_MUTEX(geneve_mutex); + +/* per-network namespace private data for this module */ +struct geneve_net { + struct list_head sock_list; +}; + +static int geneve_net_id; + +static struct geneve_sock *geneve_find_sock(struct net *net, + sa_family_t family, __be16 port) +{ + struct geneve_net *gn = net_generic(net, geneve_net_id); + struct geneve_sock *gs; + + list_for_each_entry(gs, &gn->sock_list, list) { + if (inet_sk(gs->sock->sk)->inet_sport == port && + inet_sk(gs->sock->sk)->sk.sk_family == family) + 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 formatted 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 csum, bool xnet) +{ + struct genevehdr *gnvh; + int min_headroom; + int err; + + 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); + return err; + } + + skb = vlan_hwaccel_push_inside(skb); + if (unlikely(!skb)) + return -ENOMEM; + + skb = udp_tunnel_handle_offloads(skb, csum); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); + geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); + + skb_set_inner_protocol(skb, htons(ETH_P_TEB)); + + return udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, src, dst, + tos, ttl, df, src_port, dst_port, xnet, + !csum); +} +EXPORT_SYMBOL_GPL(geneve_xmit_skb); + +static int geneve_hlen(struct genevehdr *gh) +{ + return sizeof(*gh) + gh->opt_len * 4; +} + +static struct sk_buff **geneve_gro_receive(struct sk_buff **head, + struct sk_buff *skb, + struct udp_offload *uoff) +{ + struct sk_buff *p, **pp = NULL; + struct genevehdr *gh, *gh2; + unsigned int hlen, gh_len, off_gnv; + const struct packet_offload *ptype; + __be16 type; + int flush = 1; + + off_gnv = skb_gro_offset(skb); + hlen = off_gnv + sizeof(*gh); + gh = skb_gro_header_fast(skb, off_gnv); + if (skb_gro_header_hard(skb, hlen)) { + gh = skb_gro_header_slow(skb, hlen, off_gnv); + if (unlikely(!gh)) + goto out; + } + + if (gh->ver != GENEVE_VER || gh->oam) + goto out; + gh_len = geneve_hlen(gh); + + hlen = off_gnv + gh_len; + if (skb_gro_header_hard(skb, hlen)) { + gh = skb_gro_header_slow(skb, hlen, off_gnv); + if (unlikely(!gh)) + goto out; + } + + flush = 0; + + for (p = *head; p; p = p->next) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + gh2 = (struct genevehdr *)(p->data + off_gnv); + if (gh->opt_len != gh2->opt_len || + memcmp(gh, gh2, gh_len)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + } + + type = gh->proto_type; + + rcu_read_lock(); + ptype = gro_find_receive_by_type(type); + if (!ptype) { + flush = 1; + goto out_unlock; + } + + skb_gro_pull(skb, gh_len); + skb_gro_postpull_rcsum(skb, gh, gh_len); + pp = ptype->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int geneve_gro_complete(struct sk_buff *skb, int nhoff, + struct udp_offload *uoff) +{ + struct genevehdr *gh; + struct packet_offload *ptype; + __be16 type; + int gh_len; + int err = -ENOSYS; + + udp_tunnel_gro_complete(skb, nhoff); + + gh = (struct genevehdr *)(skb->data + nhoff); + gh_len = geneve_hlen(gh); + type = gh->proto_type; + + rcu_read_lock(); + ptype = gro_find_complete_by_type(type); + if (ptype) + err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); + + rcu_read_unlock(); + return err; +} + +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); + } +} + +static void geneve_notify_del_rx_port(struct geneve_sock *gs) +{ + struct sock *sk = gs->sock->sk; + sa_family_t sa_family = sk->sk_family; + + if (sa_family == AF_INET) + udp_del_offload(&gs->udp_offloads); +} + +/* 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 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 = htonl(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); + + sock = geneve_create_sock(net, ipv6, port); + if (IS_ERR(sock)) { + kfree(gs); + return ERR_CAST(sock); + } + + gs->sock = sock; + 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 = geneve_gro_receive; + gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete; + geneve_notify_add_rx_port(gs); + + /* 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); + + list_add(&gs->list, &gn->sock_list); + + 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; + + mutex_lock(&geneve_mutex); + + gs = geneve_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port); + if (gs) { + if (!no_share && gs->rcv == rcv) + gs->refcnt++; + else + gs = ERR_PTR(-EBUSY); + } else { + gs = geneve_socket_create(net, port, rcv, data, ipv6); + } + + mutex_unlock(&geneve_mutex); + + return gs; +} +EXPORT_SYMBOL_GPL(geneve_sock_add); + +void geneve_sock_release(struct geneve_sock *gs) +{ + mutex_lock(&geneve_mutex); + + if (--gs->refcnt) + goto unlock; + + list_del(&gs->list); + geneve_notify_del_rx_port(gs); + udp_tunnel_sock_release(gs->sock); + kfree_rcu(gs, rcu); + +unlock: + mutex_unlock(&geneve_mutex); +} +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); + + INIT_LIST_HEAD(&gn->sock_list); + + return 0; +} + +static struct pernet_operations geneve_net_ops = { + .init = geneve_init_net, + .id = &geneve_net_id, + .size = sizeof(struct geneve_net), +}; + +static int __init geneve_init_module(void) +{ + int rc; + + rc = register_pernet_subsys(&geneve_net_ops); + if (rc) + return rc; + + pr_info("Geneve driver\n"); + + return 0; +} +module_init(geneve_init_module); + +static void __exit geneve_cleanup_module(void) +{ + unregister_pernet_subsys(&geneve_net_ops); +} +module_exit(geneve_cleanup_module); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jesse Gross "); +MODULE_DESCRIPTION("Driver for GENEVE encapsulated traffic"); diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index ed6b0f8dd1bb..15840401a2ce 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -59,7 +59,7 @@ config OPENVSWITCH_VXLAN config OPENVSWITCH_GENEVE tristate "Open vSwitch Geneve tunneling support" depends on OPENVSWITCH - depends on GENEVE + depends on GENEVE_CORE default OPENVSWITCH ---help--- If you say Y here, then the Open vSwitch will be able create geneve vport. -- cgit v1.2.3 From ccea74457bbdafe33dce8bffcb5cb183aeb5f2bb Mon Sep 17 00:00:00 2001 From: Neil McKee Date: Tue, 26 May 2015 20:59:43 -0700 Subject: openvswitch: include datapath actions with sampled-packet upcall to userspace If new optional attribute OVS_USERSPACE_ATTR_ACTIONS is added to an OVS_ACTION_ATTR_USERSPACE action, then include the datapath actions in the upcall. This Directly associates the sampled packet with the path it takes through the virtual switch. Path information currently includes mangling, encapsulation and decapsulation actions for tunneling protocols GRE, VXLAN, Geneve, MPLS and QinQ, but this extension requires no further changes to accommodate datapath actions that may be added in the future. Adding path information enhances visibility into complex virtual networks. Signed-off-by: Neil McKee Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 4 ++++ net/openvswitch/actions.c | 23 +++++++++++++++-------- net/openvswitch/datapath.c | 18 ++++++++++++++++-- net/openvswitch/datapath.h | 2 ++ 4 files changed, 37 insertions(+), 10 deletions(-) (limited to 'net/openvswitch') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index bbd49a0c46c7..1dab77601c21 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -153,6 +153,8 @@ enum ovs_packet_cmd { * flow key against the kernel's. * @OVS_PACKET_ATTR_ACTIONS: Contains actions for the packet. Used * for %OVS_PACKET_CMD_EXECUTE. It has nested %OVS_ACTION_ATTR_* attributes. + * Also used in upcall when %OVS_ACTION_ATTR_USERSPACE has optional + * %OVS_USERSPACE_ATTR_ACTIONS attribute. * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content @@ -528,6 +530,7 @@ enum ovs_sample_attr { * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA. * @OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: If present, u32 output port to get * tunnel info. + * @OVS_USERSPACE_ATTR_ACTIONS: If present, send actions with upcall. */ enum ovs_userspace_attr { OVS_USERSPACE_ATTR_UNSPEC, @@ -535,6 +538,7 @@ enum ovs_userspace_attr { OVS_USERSPACE_ATTR_USERDATA, /* Optional user-specified cookie. */ OVS_USERSPACE_ATTR_EGRESS_TUN_PORT, /* Optional, u32 output port * to get tunnel info. */ + OVS_USERSPACE_ATTR_ACTIONS, /* Optional flag to get actions. */ __OVS_USERSPACE_ATTR_MAX }; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b491c1c296fe..8a8c0b8b4f63 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -608,17 +608,16 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port) } static int output_userspace(struct datapath *dp, struct sk_buff *skb, - struct sw_flow_key *key, const struct nlattr *attr) + struct sw_flow_key *key, const struct nlattr *attr, + const struct nlattr *actions, int actions_len) { struct ovs_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; + memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_ACTION; - upcall.userdata = NULL; - upcall.portid = 0; - upcall.egress_tun_info = NULL; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { @@ -647,6 +646,13 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, break; } + case OVS_USERSPACE_ATTR_ACTIONS: { + /* Include actions. */ + upcall.actions = actions; + upcall.actions_len = actions_len; + break; + } + } /* End of switch. */ } @@ -654,7 +660,8 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, } static int sample(struct datapath *dp, struct sk_buff *skb, - struct sw_flow_key *key, const struct nlattr *attr) + struct sw_flow_key *key, const struct nlattr *attr, + const struct nlattr *actions, int actions_len) { const struct nlattr *acts_list = NULL; const struct nlattr *a; @@ -688,7 +695,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, */ if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE && nla_is_last(a, rem))) - return output_userspace(dp, skb, key, a); + return output_userspace(dp, skb, key, a, actions, actions_len); skb = skb_clone(skb, GFP_ATOMIC); if (!skb) @@ -872,7 +879,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_USERSPACE: - output_userspace(dp, skb, key, a); + output_userspace(dp, skb, key, a, attr, len); break; case OVS_ACTION_ATTR_HASH: @@ -916,7 +923,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_SAMPLE: - err = sample(dp, skb, key, a); + err = sample(dp, skb, key, a, attr, len); break; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 3b90461317ec..ff8c4a4c1609 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -272,10 +272,9 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) struct dp_upcall_info upcall; int error; + memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; - upcall.userdata = NULL; upcall.portid = ovs_vport_find_upcall_portid(p, skb); - upcall.egress_tun_info = NULL; error = ovs_dp_upcall(dp, skb, key, &upcall); if (unlikely(error)) kfree_skb(skb); @@ -397,6 +396,10 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info, if (upcall_info->egress_tun_info) size += nla_total_size(ovs_tun_key_attr_size()); + /* OVS_PACKET_ATTR_ACTIONS */ + if (upcall_info->actions_len) + size += nla_total_size(upcall_info->actions_len); + return size; } @@ -478,6 +481,17 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, nla_nest_end(user_skb, nla); } + if (upcall_info->actions_len) { + nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_ACTIONS); + err = ovs_nla_put_actions(upcall_info->actions, + upcall_info->actions_len, + user_skb); + if (!err) + nla_nest_end(user_skb, nla); + else + nla_nest_cancel(user_skb, nla); + } + /* Only reserve room for attribute header, packet data is added * in skb_zerocopy() */ if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 4ec4a480b147..cd691e935e08 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -116,6 +116,8 @@ struct ovs_skb_cb { struct dp_upcall_info { const struct ovs_tunnel_info *egress_tun_info; const struct nlattr *userdata; + const struct nlattr *actions; + int actions_len; u32 portid; u8 cmd; }; -- cgit v1.2.3