// SPDX-License-Identifier: GPL-2.0/* Bareudp: UDP tunnel encasulation for different Payload types like * MPLS, NSH, IP, etc. * Copyright (c) 2019 Nokia, Inc. * Authors: Martin Varghese, <martin.varghese@nokia.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h>#include <linux/module.h>#include <linux/etherdevice.h>#include <linux/hash.h>#include <net/dst_metadata.h>#include <net/gro_cells.h>#include <net/rtnetlink.h>#include <net/protocol.h>#include <net/ip6_tunnel.h>#include <net/ip_tunnels.h>#include <net/udp_tunnel.h>#include <net/bareudp.h> #define BAREUDP_BASE_HLEN sizeof(struct udphdr)#define BAREUDP_IPV4_HLEN (sizeof(struct iphdr) + \ sizeof(struct udphdr))#define BAREUDP_IPV6_HLEN (sizeof(struct ipv6hdr) + \ sizeof(struct udphdr)) static bool log_ecn_error = true;module_param(log_ecn_error, bool, 0644);MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); /* per-network namespace private data for this module */ static unsigned int bareudp_net_id; struct bareudp_net { struct list_head bareudp_list; struct mutex lock;}; struct bareudp_conf { __be16 ethertype; __be16 port; u16 sport_min; bool multi_proto_mode;}; /* Pseudo network device */struct bareudp_dev { struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for bareudp tunnel */ __be16 ethertype; __be16 port; u16 sport_min; bool multi_proto_mode; struct sock __rcu *sk; struct list_head next; /* bareudp node on namespace list */ struct gro_cells gro_cells;}; static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb){ struct metadata_dst *tun_dst = NULL; IP_TUNNEL_DECLARE_FLAGS(key) = { }; struct bareudp_dev *bareudp; unsigned short family; unsigned int len; __be16 proto; void *oiph; int err; int nh; bareudp = rcu_dereference_sk_user_data(sk); if (!bareudp) goto drop; if (skb->protocol == htons(ETH_P_IP)) family = AF_INET; else family = AF_INET6; if (bareudp->ethertype == htons(ETH_P_IP)) { __u8 ipversion; if (skb_copy_bits(skb, BAREUDP_BASE_HLEN, &ipversion, sizeof(ipversion))) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } ipversion >>= 4; if (ipversion == 4) { proto = htons(ETH_P_IP); } else if (ipversion == 6 && bareudp->multi_proto_mode) { proto = htons(ETH_P_IPV6); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } else if (bareudp->ethertype == htons(ETH_P_MPLS_UC)) { struct iphdr *tunnel_hdr; tunnel_hdr = (struct iphdr *)skb_network_header(skb); if (tunnel_hdr->version == 4) { if (!ipv4_is_multicast(tunnel_hdr->daddr)) { proto = bareudp->ethertype; } else if (bareudp->multi_proto_mode && ipv4_is_multicast(tunnel_hdr->daddr)) { proto = htons(ETH_P_MPLS_MC); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } else { int addr_type; struct ipv6hdr *tunnel_hdr_v6; tunnel_hdr_v6 = (struct ipv6hdr *)skb_network_header(skb); addr_type = ipv6_addr_type((struct in6_addr *)&tunnel_hdr_v6->daddr); if (!(addr_type & IPV6_ADDR_MULTICAST)) { proto = bareudp->ethertype; } else if (bareudp->multi_proto_mode && (addr_type & IPV6_ADDR_MULTICAST)) { proto = htons(ETH_P_MPLS_MC); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } } else { proto = bareudp->ethertype; } if (iptunnel_pull_header(skb, BAREUDP_BASE_HLEN, proto, !net_eq(bareudp->net, dev_net(bareudp->dev)))) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } __set_bit(IP_TUNNEL_KEY_BIT, key); tun_dst = udp_tun_rx_dst(skb, family, key, 0, 0); if (!tun_dst) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } skb_dst_set(skb, &tun_dst->dst); skb->dev = bareudp->dev; skb_reset_mac_header(skb); /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(bareudp->dev, rx_length_errors); DEV_STATS_INC(bareudp->dev, rx_errors); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (!ipv6_mod_enabled() || family == AF_INET) err = IP_ECN_decapsulate(oiph, skb); else err = IP6_ECN_decapsulate(oiph, skb); if (unlikely(err)) { if (log_ecn_error) { if (!ipv6_mod_enabled() || family == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); } if (err > 1) { DEV_STATS_INC(bareudp->dev, rx_frame_errors); DEV_STATS_INC(bareudp->dev, rx_errors); goto drop; } } len = skb->len; err = gro_cells_receive(&bareudp->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) dev_dstats_rx_add(bareudp->dev, len); return 0;drop: /* Consume bad packet */ kfree_skb(skb); return 0;} static int bareudp_err_lookup(struct sock *sk, struct sk_buff *skb){ return 0;} static int bareudp_init(struct net_device *dev){ struct bareudp_dev *bareudp = netdev_priv(dev); int err; err = gro_cells_init(&bareudp->gro_cells, dev); if (err) return err; return 0;} static void bareudp_uninit(struct net_device *dev){ struct bareudp_dev *bareudp = netdev_priv(dev); gro_cells_destroy(&bareudp->gro_cells);} static struct sock *bareudp_create_sock(struct net *net, __be16 port){ struct udp_port_cfg udp_conf; struct socket *sock; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6_mod_enabled()) udp_conf.family = AF_INET6; else udp_conf.family = AF_INET; udp_conf.local_udp_port = port; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock->sk;} /* Create new listen socket if needed */static int bareudp_socket_create(struct bareudp_dev *bareudp, __be16 port){ struct udp_tunnel_sock_cfg tunnel_cfg; struct sock *sk; sk = bareudp_create_sock(bareudp->net, port); if (IS_ERR(sk)) return PTR_ERR(sk); /* Mark socket as an encapsulation socket */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = bareudp; tunnel_cfg.encap_type = 1; tunnel_cfg.encap_rcv = bareudp_udp_encap_recv; tunnel_cfg.encap_err_lookup = bareudp_err_lookup; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(bareudp->net, sk, &tunnel_cfg); rcu_assign_pointer(bareudp->sk, sk); return 0;} static int bareudp_open(struct net_device *dev){ struct bareudp_dev *bareudp = netdev_priv(dev); return bareudp_socket_create(bareudp, bareudp->port);} static void bareudp_sock_release(struct bareudp_dev *bareudp){ struct sock *sk; sk = rtnl_dereference(bareudp->sk); rcu_assign_pointer(bareudp->sk, NULL); udp_tunnel_sock_release(sk);} static int bareudp_stop(struct net_device *dev){ struct bareudp_dev *bareudp = netdev_priv(dev); bareudp_sock_release(bareudp); return 0;} static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info){ bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct sock *sk = rcu_dereference(bareudp->sk); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; __be16 sport, df; int min_headroom; __u8 tos, ttl; __be32 saddr; int err; if (skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB))) return -EINVAL; if (!sk) return -ESHUTDOWN; sport = udp_flow_src_port(bareudp->net, skb, bareudp->sport_min, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, bareudp->net, 0, &saddr, &info->key, sport, bareudp->port, key->tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); skb_tunnel_check_pmtu(skb, &rt->dst, BAREUDP_IPV4_HLEN + info->options_len, false); tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? htons(IP_DF) : 0; skb_scrub_packet(skb, xnet); err = -ENOSPC; if (!skb_pull(skb, skb_network_offset(skb))) goto free_dst; min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr); err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; skb_set_inner_protocol(skb, bareudp->ethertype); udp_tunnel_xmit_skb(rt, sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, bareudp->port, !net_eq(bareudp->net, dev_net(bareudp->dev)), !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags), 0); return 0; free_dst: dst_release(&rt->dst); return err;} static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info){ bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct sock *sk = rcu_dereference(bareudp->sk); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr, daddr; int min_headroom; __u8 prio, ttl; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB))) return -EINVAL; if (!sk) return -ESHUTDOWN; sport = udp_flow_src_port(bareudp->net, skb, bareudp->sport_min, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sk, 0, &saddr, key, sport, bareudp->port, key->tos, use_cache ? (struct dst_cache *) &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); skb_tunnel_check_pmtu(skb, dst, BAREUDP_IPV6_HLEN + info->options_len, false); prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; skb_scrub_packet(skb, xnet); err = -ENOSPC; if (!skb_pull(skb, skb_network_offset(skb))) goto free_dst; min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct ipv6hdr); err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; daddr = info->key.u.ipv6.dst; udp_tunnel6_xmit_skb(dst, sk, skb, dev, &saddr, &daddr, prio, ttl, info->key.label, sport, bareudp->port, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags), 0); return 0; free_dst: dst_release(dst); return err;} static bool bareudp_proto_valid(struct bareudp_dev *bareudp, __be16 proto){ if (bareudp->ethertype == proto) return true; if (!bareudp->multi_proto_mode) return false; if (bareudp->ethertype == htons(ETH_P_MPLS_UC) && proto == htons(ETH_P_MPLS_MC)) return true; if (bareudp->ethertype == htons(ETH_P_IP) && proto == htons(ETH_P_IPV6)) return true; return false;} static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev){ struct bareudp_dev *bareudp = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; if (!bareudp_proto_valid(bareudp, skb->protocol)) { err = -EINVAL; goto tx_error; } info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { err = -EINVAL; goto tx_error; } rcu_read_lock(); if (ipv6_mod_enabled() && info->mode & IP_TUNNEL_INFO_IPV6) err = bareudp6_xmit_skb(skb, dev, bareudp, info); else err = bareudp_xmit_skb(skb, dev, bareudp, info); rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK;tx_error: dev_kfree_skb(skb); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK;} static int bareudp_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)Lines 1–500 of 866. Load more
// SPDX-License-Identifier: GPL-2.0 /* Bareudp: UDP tunnel encasulation for different Payload types like * MPLS, NSH, IP, etc. * Copyright (c) 2019 Nokia, Inc. * Authors: Martin Varghese, <martin.varghese@nokia.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/hash.h> #include <net/dst_metadata.h> #include <net/gro_cells.h> #include <net/rtnetlink.h> #include <net/protocol.h> #include <net/ip6_tunnel.h> #include <net/ip_tunnels.h> #include <net/udp_tunnel.h> #include <net/bareudp.h> #define BAREUDP_BASE_HLEN sizeof(struct udphdr) #define BAREUDP_IPV4_HLEN (sizeof(struct iphdr) + \ sizeof(struct udphdr)) #define BAREUDP_IPV6_HLEN (sizeof(struct ipv6hdr) + \ sizeof(struct udphdr)) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); /* per-network namespace private data for this module */ static unsigned int bareudp_net_id; struct bareudp_net { struct list_head bareudp_list; struct mutex lock; }; struct bareudp_conf { __be16 ethertype; __be16 port; u16 sport_min; bool multi_proto_mode; }; /* Pseudo network device */ struct bareudp_dev { struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for bareudp tunnel */ __be16 ethertype; __be16 port; u16 sport_min; bool multi_proto_mode; struct sock __rcu *sk; struct list_head next; /* bareudp node on namespace list */ struct gro_cells gro_cells; }; static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct metadata_dst *tun_dst = NULL; IP_TUNNEL_DECLARE_FLAGS(key) = { }; struct bareudp_dev *bareudp; unsigned short family; unsigned int len; __be16 proto; void *oiph; int err; int nh; bareudp = rcu_dereference_sk_user_data(sk); if (!bareudp) goto drop; if (skb->protocol == htons(ETH_P_IP)) family = AF_INET; else family = AF_INET6; if (bareudp->ethertype == htons(ETH_P_IP)) { __u8 ipversion; if (skb_copy_bits(skb, BAREUDP_BASE_HLEN, &ipversion, sizeof(ipversion))) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } ipversion >>= 4; if (ipversion == 4) { proto = htons(ETH_P_IP); } else if (ipversion == 6 && bareudp->multi_proto_mode) { proto = htons(ETH_P_IPV6); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } else if (bareudp->ethertype == htons(ETH_P_MPLS_UC)) { struct iphdr *tunnel_hdr; tunnel_hdr = (struct iphdr *)skb_network_header(skb); if (tunnel_hdr->version == 4) { if (!ipv4_is_multicast(tunnel_hdr->daddr)) { proto = bareudp->ethertype; } else if (bareudp->multi_proto_mode && ipv4_is_multicast(tunnel_hdr->daddr)) { proto = htons(ETH_P_MPLS_MC); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } else { int addr_type; struct ipv6hdr *tunnel_hdr_v6; tunnel_hdr_v6 = (struct ipv6hdr *)skb_network_header(skb); addr_type = ipv6_addr_type((struct in6_addr *)&tunnel_hdr_v6->daddr); if (!(addr_type & IPV6_ADDR_MULTICAST)) { proto = bareudp->ethertype; } else if (bareudp->multi_proto_mode && (addr_type & IPV6_ADDR_MULTICAST)) { proto = htons(ETH_P_MPLS_MC); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } } else { proto = bareudp->ethertype; } if (iptunnel_pull_header(skb, BAREUDP_BASE_HLEN, proto, !net_eq(bareudp->net, dev_net(bareudp->dev)))) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } __set_bit(IP_TUNNEL_KEY_BIT, key); tun_dst = udp_tun_rx_dst(skb, family, key, 0, 0); if (!tun_dst) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } skb_dst_set(skb, &tun_dst->dst); skb->dev = bareudp->dev; skb_reset_mac_header(skb); /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(bareudp->dev, rx_length_errors); DEV_STATS_INC(bareudp->dev, rx_errors); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (!ipv6_mod_enabled() || family == AF_INET) err = IP_ECN_decapsulate(oiph, skb); else err = IP6_ECN_decapsulate(oiph, skb); if (unlikely(err)) { if (log_ecn_error) { if (!ipv6_mod_enabled() || family == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); } if (err > 1) { DEV_STATS_INC(bareudp->dev, rx_frame_errors); DEV_STATS_INC(bareudp->dev, rx_errors); goto drop; } } len = skb->len; err = gro_cells_receive(&bareudp->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) dev_dstats_rx_add(bareudp->dev, len); return 0; drop: /* Consume bad packet */ kfree_skb(skb); return 0; } static int bareudp_err_lookup(struct sock *sk, struct sk_buff *skb) { return 0; } static int bareudp_init(struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); int err; err = gro_cells_init(&bareudp->gro_cells, dev); if (err) return err; return 0; } static void bareudp_uninit(struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); gro_cells_destroy(&bareudp->gro_cells); } static struct sock *bareudp_create_sock(struct net *net, __be16 port) { struct udp_port_cfg udp_conf; struct socket *sock; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6_mod_enabled()) udp_conf.family = AF_INET6; else udp_conf.family = AF_INET; udp_conf.local_udp_port = port; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock->sk; } /* Create new listen socket if needed */ static int bareudp_socket_create(struct bareudp_dev *bareudp, __be16 port) { struct udp_tunnel_sock_cfg tunnel_cfg; struct sock *sk; sk = bareudp_create_sock(bareudp->net, port); if (IS_ERR(sk)) return PTR_ERR(sk); /* Mark socket as an encapsulation socket */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = bareudp; tunnel_cfg.encap_type = 1; tunnel_cfg.encap_rcv = bareudp_udp_encap_recv; tunnel_cfg.encap_err_lookup = bareudp_err_lookup; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(bareudp->net, sk, &tunnel_cfg); rcu_assign_pointer(bareudp->sk, sk); return 0; } static int bareudp_open(struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); return bareudp_socket_create(bareudp, bareudp->port); } static void bareudp_sock_release(struct bareudp_dev *bareudp) { struct sock *sk; sk = rtnl_dereference(bareudp->sk); rcu_assign_pointer(bareudp->sk, NULL); udp_tunnel_sock_release(sk); } static int bareudp_stop(struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); bareudp_sock_release(bareudp); return 0; } static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct sock *sk = rcu_dereference(bareudp->sk); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; __be16 sport, df; int min_headroom; __u8 tos, ttl; __be32 saddr; int err; if (skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB))) return -EINVAL; if (!sk) return -ESHUTDOWN; sport = udp_flow_src_port(bareudp->net, skb, bareudp->sport_min, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, bareudp->net, 0, &saddr, &info->key, sport, bareudp->port, key->tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); skb_tunnel_check_pmtu(skb, &rt->dst, BAREUDP_IPV4_HLEN + info->options_len, false); tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? htons(IP_DF) : 0; skb_scrub_packet(skb, xnet); err = -ENOSPC; if (!skb_pull(skb, skb_network_offset(skb))) goto free_dst; min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr); err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; skb_set_inner_protocol(skb, bareudp->ethertype); udp_tunnel_xmit_skb(rt, sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, bareudp->port, !net_eq(bareudp->net, dev_net(bareudp->dev)), !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags), 0); return 0; free_dst: dst_release(&rt->dst); return err; } static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct sock *sk = rcu_dereference(bareudp->sk); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr, daddr; int min_headroom; __u8 prio, ttl; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB))) return -EINVAL; if (!sk) return -ESHUTDOWN; sport = udp_flow_src_port(bareudp->net, skb, bareudp->sport_min, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sk, 0, &saddr, key, sport, bareudp->port, key->tos, use_cache ? (struct dst_cache *) &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); skb_tunnel_check_pmtu(skb, dst, BAREUDP_IPV6_HLEN + info->options_len, false); prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; skb_scrub_packet(skb, xnet); err = -ENOSPC; if (!skb_pull(skb, skb_network_offset(skb))) goto free_dst; min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct ipv6hdr); err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; daddr = info->key.u.ipv6.dst; udp_tunnel6_xmit_skb(dst, sk, skb, dev, &saddr, &daddr, prio, ttl, info->key.label, sport, bareudp->port, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags), 0); return 0; free_dst: dst_release(dst); return err; } static bool bareudp_proto_valid(struct bareudp_dev *bareudp, __be16 proto) { if (bareudp->ethertype == proto) return true; if (!bareudp->multi_proto_mode) return false; if (bareudp->ethertype == htons(ETH_P_MPLS_UC) && proto == htons(ETH_P_MPLS_MC)) return true; if (bareudp->ethertype == htons(ETH_P_IP) && proto == htons(ETH_P_IPV6)) return true; return false; } static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; if (!bareudp_proto_valid(bareudp, skb->protocol)) { err = -EINVAL; goto tx_error; } info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { err = -EINVAL; goto tx_error; } rcu_read_lock(); if (ipv6_mod_enabled() && info->mode & IP_TUNNEL_INFO_IPV6) err = bareudp6_xmit_skb(skb, dev, bareudp, info); else err = bareudp_xmit_skb(skb, dev, bareudp, info); rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; tx_error: dev_kfree_skb(skb); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static int bareudp_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)