diff options
Diffstat (limited to 'drivers/net/vxlan.c')
| -rw-r--r-- | drivers/net/vxlan.c | 2287 |
1 files changed, 1791 insertions, 496 deletions
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 3b1d2ee7156..9f79192c9aa 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -6,9 +6,6 @@ * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. - * - * TODO - * - IPv6 (not in RFC) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -27,6 +24,7 @@ #include <linux/igmp.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> +#include <linux/if_vlan.h> #include <linux/hash.h> #include <linux/ethtool.h> #include <net/arp.h> @@ -41,9 +39,19 @@ #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/vxlan.h> +#include <net/protocol.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6.h> +#include <net/addrconf.h> +#include <net/ip6_tunnel.h> +#include <net/ip6_checksum.h> +#endif #define VXLAN_VERSION "0.1" +#define PORT_HASH_BITS 8 +#define PORT_HASH_SIZE (1<<PORT_HASH_BITS) #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) #define FDB_HASH_BITS 8 @@ -53,8 +61,7 @@ #define VXLAN_N_VID (1u << 24) #define VXLAN_VID_MASK (VXLAN_N_VID - 1) -/* IP header + UDP + VXLAN + Ethernet header */ -#define VXLAN_HEADROOM (20 + 8 + 8 + 14) +#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) #define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */ @@ -66,30 +73,40 @@ struct vxlanhdr { /* UDP port for VXLAN traffic. * The IANA assigned port is 4789, but the Linux default is 8472 - * for compatability with early adopters. + * for compatibility with early adopters. */ -static unsigned int vxlan_port __read_mostly = 8472; -module_param_named(udp_port, vxlan_port, uint, 0444); +static unsigned short vxlan_port __read_mostly = 8472; +module_param_named(udp_port, vxlan_port, ushort, 0444); MODULE_PARM_DESC(udp_port, "Destination UDP port"); 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-net private data for this module */ -static unsigned int vxlan_net_id; +static int vxlan_net_id; + +static const u8 all_zeros_mac[ETH_ALEN]; + +/* per-network namespace private data for this module */ struct vxlan_net { - struct socket *sock; /* UDP encap socket */ - struct hlist_head vni_list[VNI_HASH_SIZE]; + struct list_head vxlan_list; + struct hlist_head sock_list[PORT_HASH_SIZE]; + spinlock_t sock_lock; +}; + +union vxlan_addr { + struct sockaddr_in sin; + struct sockaddr_in6 sin6; + struct sockaddr sa; }; struct vxlan_rdst { - struct rcu_head rcu; - __be32 remote_ip; + union vxlan_addr remote_ip; __be16 remote_port; u32 remote_vni; u32 remote_ifindex; - struct vxlan_rdst *remote_next; + struct list_head list; + struct rcu_head rcu; }; /* Forwarding table entry */ @@ -98,7 +115,7 @@ struct vxlan_fdb { struct rcu_head rcu; unsigned long updated; /* jiffies */ unsigned long used; - struct vxlan_rdst remote; + struct list_head remotes; u16 state; /* see ndm_state */ u8 flags; /* see ndm_flags */ u8 eth_addr[ETH_ALEN]; @@ -106,16 +123,23 @@ struct vxlan_fdb { /* Pseudo network device */ struct vxlan_dev { - struct hlist_node hlist; + struct hlist_node hlist; /* vni hash table */ + struct list_head next; /* vxlan's per namespace list */ + struct vxlan_sock *vn_sock; /* listening socket */ struct net_device *dev; + struct net *net; /* netns for packet i/o */ struct vxlan_rdst default_dst; /* default destination */ - __be32 saddr; /* source address */ + union vxlan_addr saddr; /* source address */ __be16 dst_port; __u16 port_min; /* source port range */ __u16 port_max; __u8 tos; /* TOS override */ __u8 ttl; - u32 flags; /* VXLAN_F_* below */ + u32 flags; /* VXLAN_F_* in vxlan.h */ + + struct work_struct sock_work; + struct work_struct igmp_join; + struct work_struct igmp_leave; unsigned long age_interval; struct timer_list age_timer; @@ -126,28 +150,146 @@ struct vxlan_dev { struct hlist_head fdb_head[FDB_HASH_SIZE]; }; -#define VXLAN_F_LEARN 0x01 -#define VXLAN_F_PROXY 0x02 -#define VXLAN_F_RSC 0x04 -#define VXLAN_F_L2MISS 0x08 -#define VXLAN_F_L3MISS 0x10 - /* salt for hash table */ static u32 vxlan_salt __read_mostly; +static struct workqueue_struct *vxlan_wq; -static inline struct hlist_head *vni_head(struct net *net, u32 id) +static void vxlan_sock_work(struct work_struct *work); + +#if IS_ENABLED(CONFIG_IPV6) +static inline +bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b) +{ + if (a->sa.sa_family != b->sa.sa_family) + return false; + if (a->sa.sa_family == AF_INET6) + return ipv6_addr_equal(&a->sin6.sin6_addr, &b->sin6.sin6_addr); + else + return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr; +} + +static inline bool vxlan_addr_any(const union vxlan_addr *ipa) +{ + if (ipa->sa.sa_family == AF_INET6) + return ipv6_addr_any(&ipa->sin6.sin6_addr); + else + return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY); +} + +static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa) +{ + if (ipa->sa.sa_family == AF_INET6) + return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr); + else + return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr)); +} + +static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla) +{ + if (nla_len(nla) >= sizeof(struct in6_addr)) { + nla_memcpy(&ip->sin6.sin6_addr, nla, sizeof(struct in6_addr)); + ip->sa.sa_family = AF_INET6; + return 0; + } else if (nla_len(nla) >= sizeof(__be32)) { + ip->sin.sin_addr.s_addr = nla_get_be32(nla); + ip->sa.sa_family = AF_INET; + return 0; + } else { + return -EAFNOSUPPORT; + } +} + +static int vxlan_nla_put_addr(struct sk_buff *skb, int attr, + const union vxlan_addr *ip) +{ + if (ip->sa.sa_family == AF_INET6) + return nla_put(skb, attr, sizeof(struct in6_addr), &ip->sin6.sin6_addr); + else + return nla_put_be32(skb, attr, ip->sin.sin_addr.s_addr); +} + +#else /* !CONFIG_IPV6 */ + +static inline +bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b) +{ + return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr; +} + +static inline bool vxlan_addr_any(const union vxlan_addr *ipa) +{ + return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY); +} + +static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa) +{ + return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr)); +} + +static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla) +{ + if (nla_len(nla) >= sizeof(struct in6_addr)) { + return -EAFNOSUPPORT; + } else if (nla_len(nla) >= sizeof(__be32)) { + ip->sin.sin_addr.s_addr = nla_get_be32(nla); + ip->sa.sa_family = AF_INET; + return 0; + } else { + return -EAFNOSUPPORT; + } +} + +static int vxlan_nla_put_addr(struct sk_buff *skb, int attr, + const union vxlan_addr *ip) +{ + return nla_put_be32(skb, attr, ip->sin.sin_addr.s_addr); +} +#endif + +/* Virtual Network hash table head */ +static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id) +{ + return &vs->vni_list[hash_32(id, VNI_HASH_BITS)]; +} + +/* Socket hash table head */ +static inline struct hlist_head *vs_head(struct net *net, __be16 port) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); - return &vn->vni_list[hash_32(id, VNI_HASH_BITS)]; + return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)]; } -/* Look up VNI in a per net namespace table */ -static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id) +/* First remote destination for a forwarding entry. + * Guaranteed to be non-NULL because remotes are never deleted. + */ +static inline struct vxlan_rdst *first_remote_rcu(struct vxlan_fdb *fdb) +{ + return list_entry_rcu(fdb->remotes.next, struct vxlan_rdst, list); +} + +static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb) +{ + return list_first_entry(&fdb->remotes, struct vxlan_rdst, list); +} + +/* Find VXLAN socket based on network namespace and UDP port */ +static struct vxlan_sock *vxlan_find_sock(struct net *net, __be16 port) +{ + struct vxlan_sock *vs; + + hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { + if (inet_sk(vs->sock->sk)->inet_sport == port) + return vs; + } + return NULL; +} + +static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id) { struct vxlan_dev *vxlan; - hlist_for_each_entry_rcu(vxlan, vni_head(net, id), hlist) { + hlist_for_each_entry_rcu(vxlan, vni_head(vs, id), hlist) { if (vxlan->default_dst.remote_vni == id) return vxlan; } @@ -155,11 +297,23 @@ static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id) return NULL; } +/* Look up VNI in a per net namespace table */ +static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port) +{ + struct vxlan_sock *vs; + + vs = vxlan_find_sock(net, port); + if (!vs) + return NULL; + + return vxlan_vs_find_vni(vs, id); +} + /* Fill in neighbour message in skbuff. */ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, - const struct vxlan_fdb *fdb, - u32 portid, u32 seq, int type, unsigned int flags, - const struct vxlan_rdst *rdst) + const struct vxlan_fdb *fdb, + u32 portid, u32 seq, int type, unsigned int flags, + const struct vxlan_rdst *rdst) { unsigned long now = jiffies; struct nda_cacheinfo ci; @@ -178,26 +332,26 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, if (type == RTM_GETNEIGH) { ndm->ndm_family = AF_INET; - send_ip = rdst->remote_ip != htonl(INADDR_ANY); + send_ip = !vxlan_addr_any(&rdst->remote_ip); send_eth = !is_zero_ether_addr(fdb->eth_addr); } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; ndm->ndm_ifindex = vxlan->dev->ifindex; ndm->ndm_flags = fdb->flags; - ndm->ndm_type = NDA_DST; + ndm->ndm_type = RTN_UNICAST; if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr)) goto nla_put_failure; - if (send_ip && nla_put_be32(skb, NDA_DST, rdst->remote_ip)) + if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip)) goto nla_put_failure; if (rdst->remote_port && rdst->remote_port != vxlan->dst_port && nla_put_be16(skb, NDA_PORT, rdst->remote_port)) goto nla_put_failure; if (rdst->remote_vni != vxlan->default_dst.remote_vni && - nla_put_be32(skb, NDA_VNI, rdst->remote_vni)) + nla_put_u32(skb, NDA_VNI, rdst->remote_vni)) goto nla_put_failure; if (rdst->remote_ifindex && nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) @@ -222,15 +376,15 @@ static inline size_t vxlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ - + nla_total_size(sizeof(__be32)) /* NDA_DST */ + + nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */ + nla_total_size(sizeof(__be16)) /* NDA_PORT */ + nla_total_size(sizeof(__be32)) /* NDA_VNI */ + nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */ + nla_total_size(sizeof(struct nda_cacheinfo)); } -static void vxlan_fdb_notify(struct vxlan_dev *vxlan, - const struct vxlan_fdb *fdb, int type) +static void vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, + struct vxlan_rdst *rd, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; @@ -240,7 +394,7 @@ static void vxlan_fdb_notify(struct vxlan_dev *vxlan, if (skb == NULL) goto errout; - err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, &fdb->remote); + err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd); if (err < 0) { /* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -255,28 +409,30 @@ errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } -static void vxlan_ip_miss(struct net_device *dev, __be32 ipa) +static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_fdb f; - - memset(&f, 0, sizeof f); - f.state = NUD_STALE; - f.remote.remote_ip = ipa; /* goes to NDA_DST */ - f.remote.remote_vni = VXLAN_N_VID; + struct vxlan_fdb f = { + .state = NUD_STALE, + }; + struct vxlan_rdst remote = { + .remote_ip = *ipa, /* goes to NDA_DST */ + .remote_vni = VXLAN_N_VID, + }; - vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH); + vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH); } static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) { - struct vxlan_fdb f; + struct vxlan_fdb f = { + .state = NUD_STALE, + }; + struct vxlan_rdst remote = { }; - memset(&f, 0, sizeof f); - f.state = NUD_STALE; memcpy(f.eth_addr, eth_addr, ETH_ALEN); - vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH); + vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH); } /* Hash Ethernet address */ @@ -303,13 +459,12 @@ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, /* Look up Ethernet address in forwarding table */ static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac) - { struct hlist_head *head = vxlan_fdb_head(vxlan, mac); struct vxlan_fdb *f; hlist_for_each_entry_rcu(f, head, hlist) { - if (compare_ether_addr(mac, f->eth_addr) == 0) + if (ether_addr_equal(mac, f->eth_addr)) return f; } @@ -328,40 +483,208 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, return f; } -/* Add/update destinations for multicast */ -static int vxlan_fdb_append(struct vxlan_fdb *f, - __be32 ip, __be16 port, __u32 vni, __u32 ifindex) +/* caller should hold vxlan->hash_lock */ +static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, + union vxlan_addr *ip, __be16 port, + __u32 vni, __u32 ifindex) { - struct vxlan_rdst *rd_prev, *rd; + struct vxlan_rdst *rd; - rd_prev = NULL; - for (rd = &f->remote; rd; rd = rd->remote_next) { - if (rd->remote_ip == ip && + list_for_each_entry(rd, &f->remotes, list) { + if (vxlan_addr_equal(&rd->remote_ip, ip) && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex) - return 0; - rd_prev = rd; + return rd; } + + return NULL; +} + +/* Replace destination of unicast mac */ +static int vxlan_fdb_replace(struct vxlan_fdb *f, + union vxlan_addr *ip, __be16 port, __u32 vni, __u32 ifindex) +{ + struct vxlan_rdst *rd; + + rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); + if (rd) + return 0; + + rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); + if (!rd) + return 0; + rd->remote_ip = *ip; + rd->remote_port = port; + rd->remote_vni = vni; + rd->remote_ifindex = ifindex; + return 1; +} + +/* Add/update destinations for multicast */ +static int vxlan_fdb_append(struct vxlan_fdb *f, + union vxlan_addr *ip, __be16 port, __u32 vni, + __u32 ifindex, struct vxlan_rdst **rdp) +{ + struct vxlan_rdst *rd; + + rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); + if (rd) + return 0; + rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) return -ENOBUFS; - rd->remote_ip = ip; + rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex; - rd->remote_next = NULL; - rd_prev->remote_next = rd; + + list_add_tail_rcu(&rd->list, &f->remotes); + + *rdp = rd; return 1; } +static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff *skb) +{ + struct sk_buff *p, **pp = NULL; + struct vxlanhdr *vh, *vh2; + struct ethhdr *eh, *eh2; + unsigned int hlen, off_vx, off_eth; + const struct packet_offload *ptype; + __be16 type; + int flush = 1; + + off_vx = skb_gro_offset(skb); + hlen = off_vx + sizeof(*vh); + vh = skb_gro_header_fast(skb, off_vx); + if (skb_gro_header_hard(skb, hlen)) { + vh = skb_gro_header_slow(skb, hlen, off_vx); + if (unlikely(!vh)) + goto out; + } + skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ + skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); + + off_eth = skb_gro_offset(skb); + hlen = off_eth + sizeof(*eh); + eh = skb_gro_header_fast(skb, off_eth); + if (skb_gro_header_hard(skb, hlen)) { + eh = skb_gro_header_slow(skb, hlen, off_eth); + if (unlikely(!eh)) + goto out; + } + + flush = 0; + + for (p = *head; p; p = p->next) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + vh2 = (struct vxlanhdr *)(p->data + off_vx); + eh2 = (struct ethhdr *)(p->data + off_eth); + if (vh->vx_vni != vh2->vx_vni || compare_ether_header(eh, eh2)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + } + + type = eh->h_proto; + + rcu_read_lock(); + ptype = gro_find_receive_by_type(type); + if (ptype == NULL) { + flush = 1; + goto out_unlock; + } + + skb_gro_pull(skb, sizeof(*eh)); /* pull inner eth header */ + skb_gro_postpull_rcsum(skb, eh, sizeof(*eh)); + pp = ptype->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int vxlan_gro_complete(struct sk_buff *skb, int nhoff) +{ + struct ethhdr *eh; + struct packet_offload *ptype; + __be16 type; + int vxlan_len = sizeof(struct vxlanhdr) + sizeof(struct ethhdr); + int err = -ENOSYS; + + eh = (struct ethhdr *)(skb->data + nhoff + sizeof(struct vxlanhdr)); + type = eh->h_proto; + + rcu_read_lock(); + ptype = gro_find_complete_by_type(type); + if (ptype != NULL) + err = ptype->callbacks.gro_complete(skb, nhoff + vxlan_len); + + rcu_read_unlock(); + return err; +} + +/* Notify netdevs that UDP port started listening */ +static void vxlan_notify_add_rx_port(struct vxlan_sock *vs) +{ + struct net_device *dev; + struct sock *sk = vs->sock->sk; + struct net *net = sock_net(sk); + sa_family_t sa_family = sk->sk_family; + __be16 port = inet_sk(sk)->inet_sport; + int err; + + if (sa_family == AF_INET) { + err = udp_add_offload(&vs->udp_offloads); + if (err) + pr_warn("vxlan: udp_add_offload failed with status %d\n", err); + } + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->netdev_ops->ndo_add_vxlan_port) + dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family, + port); + } + rcu_read_unlock(); +} + +/* Notify netdevs that UDP port is no more listening */ +static void vxlan_notify_del_rx_port(struct vxlan_sock *vs) +{ + struct net_device *dev; + struct sock *sk = vs->sock->sk; + struct net *net = sock_net(sk); + sa_family_t sa_family = sk->sk_family; + __be16 port = inet_sk(sk)->inet_sport; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->netdev_ops->ndo_del_vxlan_port) + dev->netdev_ops->ndo_del_vxlan_port(dev, sa_family, + port); + } + rcu_read_unlock(); + + if (sa_family == AF_INET) + udp_del_offload(&vs->udp_offloads); +} + /* Add new entry to forwarding table -- assumes lock held */ static int vxlan_fdb_create(struct vxlan_dev *vxlan, - const u8 *mac, __be32 ip, + const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __u32 vni, __u32 ifindex, __u8 ndm_flags) { + struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int notify = 0; @@ -382,9 +705,24 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, f->updated = jiffies; notify = 1; } + if ((flags & NLM_F_REPLACE)) { + /* Only change unicasts */ + if (!(is_multicast_ether_addr(f->eth_addr) || + is_zero_ether_addr(f->eth_addr))) { + int rc = vxlan_fdb_replace(f, ip, port, vni, + ifindex); + + if (rc < 0) + return rc; + notify |= rc; + } else + return -EOPNOTSUPP; + } if ((flags & NLM_F_APPEND) && - is_multicast_ether_addr(f->eth_addr)) { - int rc = vxlan_fdb_append(f, ip, port, vni, ifindex); + (is_multicast_ether_addr(f->eth_addr) || + is_zero_ether_addr(f->eth_addr))) { + int rc = vxlan_fdb_append(f, ip, port, vni, ifindex, + &rd); if (rc < 0) return rc; @@ -397,29 +735,35 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if (vxlan->addrmax && vxlan->addrcnt >= vxlan->addrmax) return -ENOSPC; - netdev_dbg(vxlan->dev, "add %pM -> %pI4\n", mac, &ip); + /* Disallow replace to add a multicast entry */ + if ((flags & NLM_F_REPLACE) && + (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) + return -EOPNOTSUPP; + + netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); f = kmalloc(sizeof(*f), GFP_ATOMIC); if (!f) return -ENOMEM; notify = 1; - f->remote.remote_ip = ip; - f->remote.remote_port = port; - f->remote.remote_vni = vni; - f->remote.remote_ifindex = ifindex; - f->remote.remote_next = NULL; f->state = state; f->flags = ndm_flags; f->updated = f->used = jiffies; + INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); + vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, vxlan_fdb_head(vxlan, mac)); } - if (notify) - vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH); + if (notify) { + if (rd == NULL) + rd = first_remote_rtnl(f); + vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH); + } return 0; } @@ -427,13 +771,10 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, static void vxlan_fdb_free(struct rcu_head *head) { struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); + struct vxlan_rdst *rd, *nd; - while (f->remote.remote_next) { - struct vxlan_rdst *rd = f->remote.remote_next; - - f->remote.remote_next = rd->remote_next; + list_for_each_entry_safe(rd, nd, &f->remotes, list) kfree(rd); - } kfree(f); } @@ -443,67 +784,97 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f) "delete %pM\n", f->eth_addr); --vxlan->addrcnt; - vxlan_fdb_notify(vxlan, f, RTM_DELNEIGH); + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH); hlist_del_rcu(&f->hlist); call_rcu(&f->rcu, vxlan_fdb_free); } -/* Add static entry (via netlink) */ -static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 flags) +static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, + union vxlan_addr *ip, __be16 *port, u32 *vni, u32 *ifindex) { - struct vxlan_dev *vxlan = netdev_priv(dev); struct net *net = dev_net(vxlan->dev); - __be32 ip; - __be16 port; - u32 vni, ifindex; int err; - if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { - pr_info("RTM_NEWNEIGH with invalid state %#x\n", - ndm->ndm_state); - return -EINVAL; + if (tb[NDA_DST]) { + err = vxlan_nla_get_addr(ip, tb[NDA_DST]); + if (err) + return err; + } else { + union vxlan_addr *remote = &vxlan->default_dst.remote_ip; + if (remote->sa.sa_family == AF_INET) { + ip->sin.sin_addr.s_addr = htonl(INADDR_ANY); + ip->sa.sa_family = AF_INET; +#if IS_ENABLED(CONFIG_IPV6) + } else { + ip->sin6.sin6_addr = in6addr_any; + ip->sa.sa_family = AF_INET6; +#endif + } } - if (tb[NDA_DST] == NULL) - return -EINVAL; - - if (nla_len(tb[NDA_DST]) != sizeof(__be32)) - return -EAFNOSUPPORT; - - ip = nla_get_be32(tb[NDA_DST]); - if (tb[NDA_PORT]) { if (nla_len(tb[NDA_PORT]) != sizeof(__be16)) return -EINVAL; - port = nla_get_be16(tb[NDA_PORT]); - } else - port = vxlan->dst_port; + *port = nla_get_be16(tb[NDA_PORT]); + } else { + *port = vxlan->dst_port; + } if (tb[NDA_VNI]) { if (nla_len(tb[NDA_VNI]) != sizeof(u32)) return -EINVAL; - vni = nla_get_u32(tb[NDA_VNI]); - } else - vni = vxlan->default_dst.remote_vni; + *vni = nla_get_u32(tb[NDA_VNI]); + } else { + *vni = vxlan->default_dst.remote_vni; + } if (tb[NDA_IFINDEX]) { struct net_device *tdev; if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) return -EINVAL; - ifindex = nla_get_u32(tb[NDA_IFINDEX]); - tdev = dev_get_by_index(net, ifindex); + *ifindex = nla_get_u32(tb[NDA_IFINDEX]); + tdev = __dev_get_by_index(net, *ifindex); if (!tdev) return -EADDRNOTAVAIL; - dev_put(tdev); - } else - ifindex = 0; + } else { + *ifindex = 0; + } + + return 0; +} + +/* Add static entry (via netlink) */ +static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 flags) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + /* struct net *net = dev_net(vxlan->dev); */ + union vxlan_addr ip; + __be16 port; + u32 vni, ifindex; + int err; + + if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { + pr_info("RTM_NEWNEIGH with invalid state %#x\n", + ndm->ndm_state); + return -EINVAL; + } + + if (tb[NDA_DST] == NULL) + return -EINVAL; + + err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &vni, &ifindex); + if (err) + return err; + + if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) + return -EAFNOSUPPORT; spin_lock_bh(&vxlan->hash_lock); - err = vxlan_fdb_create(vxlan, addr, ip, ndm->ndm_state, flags, + err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags, port, vni, ifindex, ndm->ndm_flags); spin_unlock_bh(&vxlan->hash_lock); @@ -517,14 +888,44 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; - int err = -ENOENT; + struct vxlan_rdst *rd = NULL; + union vxlan_addr ip; + __be16 port; + u32 vni, ifindex; + int err; + + err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &vni, &ifindex); + if (err) + return err; + + err = -ENOENT; spin_lock_bh(&vxlan->hash_lock); f = vxlan_find_mac(vxlan, addr); - if (f) { - vxlan_fdb_destroy(vxlan, f); - err = 0; + if (!f) + goto out; + + if (!vxlan_addr_any(&ip)) { + rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex); + if (!rd) + goto out; + } + + err = 0; + + /* remove a destination if it's not the only one on the list, + * otherwise destroy the fdb entry + */ + if (rd && !list_is_singular(&f->remotes)) { + list_del_rcu(&rd->list); + vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH); + kfree_rcu(rd, rcu); + goto out; } + + vxlan_fdb_destroy(vxlan, f); + +out: spin_unlock_bh(&vxlan->hash_lock); return err; @@ -543,156 +944,204 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; - for (rd = &f->remote; rd; rd = rd->remote_next) { - if (idx < cb->args[0]) - goto skip; + if (idx < cb->args[0]) + goto skip; + + list_for_each_entry_rcu(rd, &f->remotes, list) { err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); if (err < 0) - break; -skip: - ++idx; + goto out; } +skip: + ++idx; } } - +out: return idx; } /* Watch incoming packets to learn mapping between Ethernet address * and Tunnel endpoint. + * Return true if packet is bogus and should be droppped. */ -static void vxlan_snoop(struct net_device *dev, - __be32 src_ip, const u8 *src_mac) +static bool vxlan_snoop(struct net_device *dev, + union vxlan_addr *src_ip, const u8 *src_mac) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; - int err; f = vxlan_find_mac(vxlan, src_mac); if (likely(f)) { - if (likely(f->remote.remote_ip == src_ip)) - return; + struct vxlan_rdst *rdst = first_remote_rcu(f); + + if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip))) + return false; + + /* Don't migrate static entries, drop packets */ + if (f->state & NUD_NOARP) + return true; if (net_ratelimit()) netdev_info(dev, - "%pM migrated from %pI4 to %pI4\n", - src_mac, &f->remote.remote_ip, &src_ip); + "%pM migrated from %pIS to %pIS\n", + src_mac, &rdst->remote_ip, &src_ip); - f->remote.remote_ip = src_ip; + rdst->remote_ip = *src_ip; f->updated = jiffies; + vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH); } else { /* learned new entry */ spin_lock(&vxlan->hash_lock); - err = vxlan_fdb_create(vxlan, src_mac, src_ip, - NUD_REACHABLE, - NLM_F_EXCL|NLM_F_CREATE, - vxlan->dst_port, - vxlan->default_dst.remote_vni, - 0, NTF_SELF); + + /* close off race between vxlan_flush and incoming packets */ + if (netif_running(dev)) + vxlan_fdb_create(vxlan, src_mac, src_ip, + NUD_REACHABLE, + NLM_F_EXCL|NLM_F_CREATE, + vxlan->dst_port, + vxlan->default_dst.remote_vni, + 0, NTF_SELF); spin_unlock(&vxlan->hash_lock); } -} + return false; +} /* See if multicast group is already in use by other ID */ -static bool vxlan_group_used(struct vxlan_net *vn, - const struct vxlan_dev *this) +static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) { - const struct vxlan_dev *vxlan; - unsigned h; + struct vxlan_dev *vxlan; - for (h = 0; h < VNI_HASH_SIZE; ++h) - hlist_for_each_entry(vxlan, &vn->vni_list[h], hlist) { - if (vxlan == this) - continue; + /* The vxlan_sock is only used by dev, leaving group has + * no effect on other vxlan devices. + */ + if (atomic_read(&dev->vn_sock->refcnt) == 1) + return false; - if (!netif_running(vxlan->dev)) - continue; + list_for_each_entry(vxlan, &vn->vxlan_list, next) { + if (!netif_running(vxlan->dev) || vxlan == dev) + continue; - if (vxlan->default_dst.remote_ip == this->default_dst.remote_ip) - return true; - } + if (vxlan->vn_sock != dev->vn_sock) + continue; + + if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip, + &dev->default_dst.remote_ip)) + continue; + + if (vxlan->default_dst.remote_ifindex != + dev->default_dst.remote_ifindex) + continue; + + return true; + } return false; } -/* kernel equivalent to IP_ADD_MEMBERSHIP */ -static int vxlan_join_group(struct net_device *dev) +static void vxlan_sock_hold(struct vxlan_sock *vs) { - struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); - struct sock *sk = vn->sock->sk; - struct ip_mreqn mreq = { - .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip, - .imr_ifindex = vxlan->default_dst.remote_ifindex, - }; - int err; + atomic_inc(&vs->refcnt); +} - /* Already a member of group */ - if (vxlan_group_used(vn, vxlan)) - return 0; +void vxlan_sock_release(struct vxlan_sock *vs) +{ + struct sock *sk = vs->sock->sk; + struct net *net = sock_net(sk); + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + + if (!atomic_dec_and_test(&vs->refcnt)) + return; + + spin_lock(&vn->sock_lock); + hlist_del_rcu(&vs->hlist); + rcu_assign_sk_user_data(vs->sock->sk, NULL); + vxlan_notify_del_rx_port(vs); + spin_unlock(&vn->sock_lock); + + queue_work(vxlan_wq, &vs->del_work); +} +EXPORT_SYMBOL_GPL(vxlan_sock_release); + +/* Callback to update multicast group membership when first VNI on + * multicast asddress is brought up + * Done as workqueue because ip_mc_join_group acquires RTNL. + */ +static void vxlan_igmp_join(struct work_struct *work) +{ + struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join); + struct vxlan_sock *vs = vxlan->vn_sock; + struct sock *sk = vs->sock->sk; + union vxlan_addr *ip = &vxlan->default_dst.remote_ip; + int ifindex = vxlan->default_dst.remote_ifindex; - /* Need to drop RTNL to call multicast join */ - rtnl_unlock(); lock_sock(sk); - err = ip_mc_join_group(sk, &mreq); + if (ip->sa.sa_family == AF_INET) { + struct ip_mreqn mreq = { + .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, + .imr_ifindex = ifindex, + }; + + ip_mc_join_group(sk, &mreq); +#if IS_ENABLED(CONFIG_IPV6) + } else { + ipv6_stub->ipv6_sock_mc_join(sk, ifindex, + &ip->sin6.sin6_addr); +#endif + } release_sock(sk); - rtnl_lock(); - return err; + vxlan_sock_release(vs); + dev_put(vxlan->dev); } - -/* kernel equivalent to IP_DROP_MEMBERSHIP */ -static int vxlan_leave_group(struct net_device *dev) +/* Inverse of vxlan_igmp_join when last VNI is brought down */ +static void vxlan_igmp_leave(struct work_struct *work) { - struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); - int err = 0; - struct sock *sk = vn->sock->sk; - struct ip_mreqn mreq = { - .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip, - .imr_ifindex = vxlan->default_dst.remote_ifindex, - }; + struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave); + struct vxlan_sock *vs = vxlan->vn_sock; + struct sock *sk = vs->sock->sk; + union vxlan_addr *ip = &vxlan->default_dst.remote_ip; + int ifindex = vxlan->default_dst.remote_ifindex; - /* Only leave group when last vxlan is done. */ - if (vxlan_group_used(vn, vxlan)) - return 0; - - /* Need to drop RTNL to call multicast leave */ - rtnl_unlock(); lock_sock(sk); - err = ip_mc_leave_group(sk, &mreq); + if (ip->sa.sa_family == AF_INET) { + struct ip_mreqn mreq = { + .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, + .imr_ifindex = ifindex, + }; + + ip_mc_leave_group(sk, &mreq); +#if IS_ENABLED(CONFIG_IPV6) + } else { + ipv6_stub->ipv6_sock_mc_drop(sk, ifindex, + &ip->sin6.sin6_addr); +#endif + } + release_sock(sk); - rtnl_lock(); - return err; + vxlan_sock_release(vs); + dev_put(vxlan->dev); } /* Callback from net/ipv4/udp.c to receive packets */ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { - struct iphdr *oip; + struct vxlan_sock *vs; struct vxlanhdr *vxh; - struct vxlan_dev *vxlan; - struct pcpu_tstats *stats; - __u32 vni; - int err; - - /* pop off outer UDP header */ - __skb_pull(skb, sizeof(struct udphdr)); /* Need Vxlan and inner Ethernet header to be present */ - if (!pskb_may_pull(skb, sizeof(struct vxlanhdr))) + if (!pskb_may_pull(skb, VXLAN_HLEN)) goto error; - /* Drop packets with reserved bits set */ - vxh = (struct vxlanhdr *) skb->data; + /* Return packets with reserved bits set */ + vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1); if (vxh->vx_flags != htonl(VXLAN_FLAGS) || (vxh->vx_vni & htonl(0xff))) { netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", @@ -700,55 +1149,89 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) goto error; } - __skb_pull(skb, sizeof(struct vxlanhdr)); + if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB))) + goto drop; - /* Is this VNI defined? */ - vni = ntohl(vxh->vx_vni) >> 8; - vxlan = vxlan_find_vni(sock_net(sk), vni); - if (!vxlan) { - netdev_dbg(skb->dev, "unknown vni %d\n", vni); + vs = rcu_dereference_sk_user_data(sk); + if (!vs) goto drop; - } - if (!pskb_may_pull(skb, ETH_HLEN)) { - vxlan->dev->stats.rx_length_errors++; - vxlan->dev->stats.rx_errors++; + skb_pop_rcv_encapsulation(skb); + + vs->rcv(vs, skb, vxh->vx_vni); + return 0; + +drop: + /* Consume bad packet */ + kfree_skb(skb); + return 0; + +error: + /* Return non vxlan pkt */ + return 1; +} + +static void vxlan_rcv(struct vxlan_sock *vs, + struct sk_buff *skb, __be32 vx_vni) +{ + struct iphdr *oip = NULL; + struct ipv6hdr *oip6 = NULL; + struct vxlan_dev *vxlan; + struct pcpu_sw_netstats *stats; + union vxlan_addr saddr; + __u32 vni; + int err = 0; + union vxlan_addr *remote_ip; + + vni = ntohl(vx_vni) >> 8; + /* Is this VNI defined? */ + vxlan = vxlan_vs_find_vni(vs, vni); + if (!vxlan) goto drop; - } + remote_ip = &vxlan->default_dst.remote_ip; skb_reset_mac_header(skb); - - /* Re-examine inner Ethernet packet */ - oip = ip_hdr(skb); + skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev))); skb->protocol = eth_type_trans(skb, vxlan->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ - if (compare_ether_addr(eth_hdr(skb)->h_source, - vxlan->dev->dev_addr) == 0) + if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) goto drop; - if (vxlan->flags & VXLAN_F_LEARN) - vxlan_snoop(skb->dev, oip->saddr, eth_hdr(skb)->h_source); + /* Re-examine inner Ethernet packet */ + if (remote_ip->sa.sa_family == AF_INET) { + oip = ip_hdr(skb); + saddr.sin.sin_addr.s_addr = oip->saddr; + saddr.sa.sa_family = AF_INET; +#if IS_ENABLED(CONFIG_IPV6) + } else { + oip6 = ipv6_hdr(skb); + saddr.sin6.sin6_addr = oip6->saddr; + saddr.sa.sa_family = AF_INET6; +#endif + } + + if ((vxlan->flags & VXLAN_F_LEARN) && + vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source)) + goto drop; - __skb_tunnel_rx(skb, vxlan->dev); skb_reset_network_header(skb); - /* If the NIC driver gave us an encapsulated packet with - * CHECKSUM_UNNECESSARY and Rx checksum feature is enabled, - * leave the CHECKSUM_UNNECESSARY, the device checksummed it - * for us. Otherwise force the upper layers to verify it. - */ - if (skb->ip_summed != CHECKSUM_UNNECESSARY || !skb->encapsulation || - !(vxlan->dev->features & NETIF_F_RXCSUM)) - skb->ip_summed = CHECKSUM_NONE; - - skb->encapsulation = 0; + if (oip6) + err = IP6_ECN_decapsulate(oip6, skb); + if (oip) + err = IP_ECN_decapsulate(oip, skb); - err = IP_ECN_decapsulate(oip, skb); if (unlikely(err)) { - if (log_ecn_error) - net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", - &oip->saddr, oip->tos); + if (log_ecn_error) { + if (oip6) + net_info_ratelimited("non-ECT from %pI6\n", + &oip6->saddr); + if (oip) + net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", + &oip->saddr, oip->tos); + } if (err > 1) { ++vxlan->dev->stats.rx_frame_errors; ++vxlan->dev->stats.rx_errors; @@ -764,16 +1247,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) netif_rx(skb); - return 0; -error: - /* Put UDP header back */ - __skb_push(skb, sizeof(struct udphdr)); - - return 1; + return; drop: /* Consume bad packet */ kfree_skb(skb); - return 0; } static int arp_reduce(struct net_device *dev, struct sk_buff *skb) @@ -824,7 +1301,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) } f = vxlan_find_mac(vxlan, n->ha); - if (f && f->remote.remote_ip == htonl(INADDR_ANY)) { + if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; @@ -835,6 +1312,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) neigh_release(n); + if (reply == NULL) + goto out; + skb_reset_mac_header(reply); __skb_pull(reply, skb_network_offset(reply)); reply->ip_summed = CHECKSUM_UNNECESSARY; @@ -842,18 +1322,186 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) if (netif_rx_ni(reply) == NET_RX_DROP) dev->stats.rx_dropped++; - } else if (vxlan->flags & VXLAN_F_L3MISS) - vxlan_ip_miss(dev, tip); + } else if (vxlan->flags & VXLAN_F_L3MISS) { + union vxlan_addr ipa = { + .sin.sin_addr.s_addr = tip, + .sa.sa_family = AF_INET, + }; + + vxlan_ip_miss(dev, &ipa); + } +out: + consume_skb(skb); + return NETDEV_TX_OK; +} + +#if IS_ENABLED(CONFIG_IPV6) + +static struct sk_buff *vxlan_na_create(struct sk_buff *request, + struct neighbour *n, bool isrouter) +{ + struct net_device *dev = request->dev; + struct sk_buff *reply; + struct nd_msg *ns, *na; + struct ipv6hdr *pip6; + u8 *daddr; + int na_olen = 8; /* opt hdr + ETH_ALEN for target */ + int ns_olen; + int i, len; + + if (dev == NULL) + return NULL; + + len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + + sizeof(*na) + na_olen + dev->needed_tailroom; + reply = alloc_skb(len, GFP_ATOMIC); + if (reply == NULL) + return NULL; + + reply->protocol = htons(ETH_P_IPV6); + reply->dev = dev; + skb_reserve(reply, LL_RESERVED_SPACE(request->dev)); + skb_push(reply, sizeof(struct ethhdr)); + skb_set_mac_header(reply, 0); + + ns = (struct nd_msg *)skb_transport_header(request); + + daddr = eth_hdr(request)->h_source; + ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns); + for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { + if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { + daddr = ns->opt + i + sizeof(struct nd_opt_hdr); + break; + } + } + + /* Ethernet header */ + ether_addr_copy(eth_hdr(reply)->h_dest, daddr); + ether_addr_copy(eth_hdr(reply)->h_source, n->ha); + eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); + reply->protocol = htons(ETH_P_IPV6); + + skb_pull(reply, sizeof(struct ethhdr)); + skb_set_network_header(reply, 0); + skb_put(reply, sizeof(struct ipv6hdr)); + + /* IPv6 header */ + + pip6 = ipv6_hdr(reply); + memset(pip6, 0, sizeof(struct ipv6hdr)); + pip6->version = 6; + pip6->priority = ipv6_hdr(request)->priority; + pip6->nexthdr = IPPROTO_ICMPV6; + pip6->hop_limit = 255; + pip6->daddr = ipv6_hdr(request)->saddr; + pip6->saddr = *(struct in6_addr *)n->primary_key; + + skb_pull(reply, sizeof(struct ipv6hdr)); + skb_set_transport_header(reply, 0); + + na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen); + + /* Neighbor Advertisement */ + memset(na, 0, sizeof(*na)+na_olen); + na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; + na->icmph.icmp6_router = isrouter; + na->icmph.icmp6_override = 1; + na->icmph.icmp6_solicited = 1; + na->target = ns->target; + ether_addr_copy(&na->opt[2], n->ha); + na->opt[0] = ND_OPT_TARGET_LL_ADDR; + na->opt[1] = na_olen >> 3; + + na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, + &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6, + csum_partial(na, sizeof(*na)+na_olen, 0)); + + pip6->payload_len = htons(sizeof(*na)+na_olen); + + skb_push(reply, sizeof(struct ipv6hdr)); + + reply->ip_summed = CHECKSUM_UNNECESSARY; + + return reply; +} + +static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct nd_msg *msg; + const struct ipv6hdr *iphdr; + const struct in6_addr *saddr, *daddr; + struct neighbour *n; + struct inet6_dev *in6_dev; + + in6_dev = __in6_dev_get(dev); + if (!in6_dev) + goto out; + + if (!pskb_may_pull(skb, skb->len)) + goto out; + + iphdr = ipv6_hdr(skb); + saddr = &iphdr->saddr; + daddr = &iphdr->daddr; + + msg = (struct nd_msg *)skb_transport_header(skb); + if (msg->icmph.icmp6_code != 0 || + msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + goto out; + + if (ipv6_addr_loopback(daddr) || + ipv6_addr_is_multicast(&msg->target)) + goto out; + + n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev); + + if (n) { + struct vxlan_fdb *f; + struct sk_buff *reply; + + if (!(n->nud_state & NUD_CONNECTED)) { + neigh_release(n); + goto out; + } + + f = vxlan_find_mac(vxlan, n->ha); + if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { + /* bridge-local neighbor */ + neigh_release(n); + goto out; + } + + reply = vxlan_na_create(skb, n, + !!(f ? f->flags & NTF_ROUTER : 0)); + + neigh_release(n); + + if (reply == NULL) + goto out; + + if (netif_rx_ni(reply) == NET_RX_DROP) + dev->stats.rx_dropped++; + + } else if (vxlan->flags & VXLAN_F_L3MISS) { + union vxlan_addr ipa = { + .sin6.sin6_addr = msg->target, + .sa.sa_family = AF_INET6, + }; + + vxlan_ip_miss(dev, &ipa); + } + out: consume_skb(skb); return NETDEV_TX_OK; } +#endif static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct neighbour *n; - struct iphdr *pip; if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) return false; @@ -861,11 +1509,47 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) n = NULL; switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: + { + struct iphdr *pip; + if (!pskb_may_pull(skb, sizeof(struct iphdr))) return false; pip = ip_hdr(skb); n = neigh_lookup(&arp_tbl, &pip->daddr, dev); + if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { + union vxlan_addr ipa = { + .sin.sin_addr.s_addr = pip->daddr, + .sa.sa_family = AF_INET, + }; + + vxlan_ip_miss(dev, &ipa); + return false; + } + break; + } +#if IS_ENABLED(CONFIG_IPV6) + case ETH_P_IPV6: + { + struct ipv6hdr *pip6; + + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + return false; + pip6 = ipv6_hdr(skb); + n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev); + if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { + union vxlan_addr ipa = { + .sin6.sin6_addr = pip6->daddr, + .sa.sa_family = AF_INET6, + }; + + vxlan_ip_miss(dev, &ipa); + return false; + } + + break; + } +#endif default: return false; } @@ -873,7 +1557,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (n) { bool diff; - diff = compare_ether_addr(eth_hdr(skb)->h_dest, n->ha) != 0; + diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha); if (diff) { memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, dev->addr_len); @@ -881,26 +1565,9 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) } neigh_release(n); return diff; - } else if (vxlan->flags & VXLAN_F_L3MISS) - vxlan_ip_miss(dev, pip->daddr); - return false; -} - -static void vxlan_sock_free(struct sk_buff *skb) -{ - sock_put(skb->sk); -} - -/* On transmit, associate with the tunnel socket */ -static void vxlan_set_owner(struct net_device *dev, struct sk_buff *skb) -{ - struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); - struct sock *sk = vn->sock->sk; + } - skb_orphan(skb); - sock_hold(sk); - skb->sk = sk; - skb->destructor = vxlan_sock_free; + return false; } /* Compute source port for outgoing packet @@ -908,48 +1575,185 @@ static void vxlan_set_owner(struct net_device *dev, struct sk_buff *skb) * better and maybe available from hardware * secondary choice is to use jhash on the Ethernet header */ -static __be16 vxlan_src_port(const struct vxlan_dev *vxlan, struct sk_buff *skb) +__be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb) { - unsigned int range = (vxlan->port_max - vxlan->port_min) + 1; + unsigned int range = (port_max - port_min) + 1; u32 hash; - hash = skb_get_rxhash(skb); + hash = skb_get_hash(skb); if (!hash) hash = jhash(skb->data, 2 * ETH_ALEN, (__force u32) skb->protocol); - return htons((((u64) hash * range) >> 32) + vxlan->port_min); + return htons((((u64) hash * range) >> 32) + port_min); } +EXPORT_SYMBOL_GPL(vxlan_src_port); -static int handle_offloads(struct sk_buff *skb) +static inline struct sk_buff *vxlan_handle_offloads(struct sk_buff *skb, + bool udp_csum) { - if (skb_is_gso(skb)) { - int err = skb_unclone(skb, GFP_ATOMIC); - if (unlikely(err)) - return err; + int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; + return iptunnel_handle_offloads(skb, udp_csum, type); +} + +#if IS_ENABLED(CONFIG_IPV6) +static int vxlan6_xmit_skb(struct vxlan_sock *vs, + struct dst_entry *dst, struct sk_buff *skb, + struct net_device *dev, struct in6_addr *saddr, + struct in6_addr *daddr, __u8 prio, __u8 ttl, + __be16 src_port, __be16 dst_port, __be32 vni, + bool xnet) +{ + struct ipv6hdr *ip6h; + struct vxlanhdr *vxh; + struct udphdr *uh; + int min_headroom; + int err; + + skb = vxlan_handle_offloads(skb, !udp_get_no_check6_tx(vs->sock->sk)); + if (IS_ERR(skb)) + return -EINVAL; + + skb_scrub_packet(skb, xnet); + + min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + + VXLAN_HLEN + sizeof(struct ipv6hdr) + + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0); + + /* Need space for new headers (invalidates iph ptr) */ + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + return err; + + if (vlan_tx_tag_present(skb)) { + if (WARN_ON(!__vlan_put_tag(skb, + skb->vlan_proto, + vlan_tx_tag_get(skb)))) + return -ENOMEM; + + skb->vlan_tci = 0; + } + + vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); + vxh->vx_flags = htonl(VXLAN_FLAGS); + vxh->vx_vni = vni; + + __skb_push(skb, sizeof(*uh)); + skb_reset_transport_header(skb); + uh = udp_hdr(skb); - skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; - } else if (skb->ip_summed != CHECKSUM_PARTIAL) - skb->ip_summed = CHECKSUM_NONE; + uh->dest = dst_port; + uh->source = src_port; + + uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | + IPSKB_REROUTED); + skb_dst_set(skb, dst); + + udp6_set_csum(udp_get_no_check6_tx(vs->sock->sk), skb, + saddr, daddr, skb->len); + + __skb_push(skb, sizeof(*ip6h)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + ip6h->version = 6; + ip6h->priority = prio; + ip6h->flow_lbl[0] = 0; + ip6h->flow_lbl[1] = 0; + ip6h->flow_lbl[2] = 0; + ip6h->payload_len = htons(skb->len); + ip6h->nexthdr = IPPROTO_UDP; + ip6h->hop_limit = ttl; + ip6h->daddr = *daddr; + ip6h->saddr = *saddr; + + ip6tunnel_xmit(skb, dev); return 0; } +#endif + +int vxlan_xmit_skb(struct vxlan_sock *vs, + struct rtable *rt, struct sk_buff *skb, + __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, + __be16 src_port, __be16 dst_port, __be32 vni, bool xnet) +{ + struct vxlanhdr *vxh; + struct udphdr *uh; + int min_headroom; + int err; + + skb = vxlan_handle_offloads(skb, !vs->sock->sk->sk_no_check_tx); + if (IS_ERR(skb)) + return -EINVAL; + + min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + + VXLAN_HLEN + sizeof(struct iphdr) + + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0); + + /* Need space for new headers (invalidates iph ptr) */ + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + return err; + + if (vlan_tx_tag_present(skb)) { + if (WARN_ON(!__vlan_put_tag(skb, + skb->vlan_proto, + vlan_tx_tag_get(skb)))) + return -ENOMEM; + + skb->vlan_tci = 0; + } + + vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); + vxh->vx_flags = htonl(VXLAN_FLAGS); + vxh->vx_vni = vni; + + __skb_push(skb, sizeof(*uh)); + skb_reset_transport_header(skb); + uh = udp_hdr(skb); + + uh->dest = dst_port; + uh->source = src_port; + + uh->len = htons(skb->len); + + udp_set_csum(vs->sock->sk->sk_no_check_tx, skb, + src, dst, skb->len); + + return iptunnel_xmit(vs->sock->sk, rt, skb, src, dst, IPPROTO_UDP, + tos, ttl, df, xnet); +} +EXPORT_SYMBOL_GPL(vxlan_xmit_skb); /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan) { - struct pcpu_tstats *tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); - struct pcpu_tstats *rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); + struct pcpu_sw_netstats *tx_stats, *rx_stats; + union vxlan_addr loopback; + union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; + tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); + rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; __skb_pull(skb, skb_network_offset(skb)); + if (remote_ip->sa.sa_family == AF_INET) { + loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + loopback.sa.sa_family = AF_INET; +#if IS_ENABLED(CONFIG_IPV6) + } else { + loopback.sin6.sin6_addr = in6addr_loopback; + loopback.sa.sa_family = AF_INET6; +#endif + } + if (dst_vxlan->flags & VXLAN_F_LEARN) - vxlan_snoop(skb->dev, htonl(INADDR_LOOPBACK), - eth_hdr(skb)->h_source); + vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source); u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; @@ -966,141 +1770,155 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, } } -static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, - struct vxlan_rdst *rdst, bool did_rsc) +static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, + struct vxlan_rdst *rdst, bool did_rsc) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct rtable *rt; + struct rtable *rt = NULL; const struct iphdr *old_iph; - struct iphdr *iph; - struct vxlanhdr *vxh; - struct udphdr *uh; struct flowi4 fl4; - __be32 dst; - __be16 src_port, dst_port; - u32 vni; + union vxlan_addr *dst; + __be16 src_port = 0, dst_port; + u32 vni; __be16 df = 0; __u8 tos, ttl; + int err; dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port; vni = rdst->remote_vni; - dst = rdst->remote_ip; + dst = &rdst->remote_ip; - if (!dst) { + if (vxlan_addr_any(dst)) { if (did_rsc) { /* short-circuited back to local bridge */ vxlan_encap_bypass(skb, vxlan, vxlan); - return NETDEV_TX_OK; + return; } goto drop; } - if (!skb->encapsulation) { - skb_reset_inner_headers(skb); - skb->encapsulation = 1; - } - - /* Need space for new headers (invalidates iph ptr) */ - if (skb_cow_head(skb, VXLAN_HEADROOM)) - goto drop; - old_iph = ip_hdr(skb); ttl = vxlan->ttl; - if (!ttl && IN_MULTICAST(ntohl(dst))) + if (!ttl && vxlan_addr_multicast(dst)) ttl = 1; tos = vxlan->tos; if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); - src_port = vxlan_src_port(vxlan, skb); + src_port = vxlan_src_port(vxlan->port_min, vxlan->port_max, skb); - memset(&fl4, 0, sizeof(fl4)); - fl4.flowi4_oif = rdst->remote_ifindex; - fl4.flowi4_tos = RT_TOS(tos); - fl4.daddr = dst; - fl4.saddr = vxlan->saddr; + if (dst->sa.sa_family == AF_INET) { + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_oif = rdst->remote_ifindex; + fl4.flowi4_tos = RT_TOS(tos); + fl4.daddr = dst->sin.sin_addr.s_addr; + fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr; - rt = ip_route_output_key(dev_net(dev), &fl4); - if (IS_ERR(rt)) { - netdev_dbg(dev, "no route to %pI4\n", &dst); - dev->stats.tx_carrier_errors++; - goto tx_error; - } + rt = ip_route_output_key(vxlan->net, &fl4); + if (IS_ERR(rt)) { + netdev_dbg(dev, "no route to %pI4\n", + &dst->sin.sin_addr.s_addr); + dev->stats.tx_carrier_errors++; + goto tx_error; + } - if (rt->dst.dev == dev) { - netdev_dbg(dev, "circular route to %pI4\n", &dst); - ip_rt_put(rt); - dev->stats.collisions++; - goto tx_error; - } + if (rt->dst.dev == dev) { + netdev_dbg(dev, "circular route to %pI4\n", + &dst->sin.sin_addr.s_addr); + dev->stats.collisions++; + goto rt_tx_error; + } - /* Bypass encapsulation if the destination is local */ - if (rt->rt_flags & RTCF_LOCAL && - !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) { - struct vxlan_dev *dst_vxlan; + /* Bypass encapsulation if the destination is local */ + if (rt->rt_flags & RTCF_LOCAL && + !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) { + struct vxlan_dev *dst_vxlan; - ip_rt_put(rt); - dst_vxlan = vxlan_find_vni(dev_net(dev), vni); - if (!dst_vxlan) - goto tx_error; - vxlan_encap_bypass(skb, vxlan, dst_vxlan); - return NETDEV_TX_OK; - } + ip_rt_put(rt); + dst_vxlan = vxlan_find_vni(vxlan->net, vni, dst_port); + if (!dst_vxlan) + goto tx_error; + vxlan_encap_bypass(skb, vxlan, dst_vxlan); + return; + } - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | - IPSKB_REROUTED); - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); + ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); - vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); - vxh->vx_flags = htonl(VXLAN_FLAGS); - vxh->vx_vni = htonl(vni << 8); + err = vxlan_xmit_skb(vxlan->vn_sock, rt, skb, + fl4.saddr, dst->sin.sin_addr.s_addr, + tos, ttl, df, src_port, dst_port, + htonl(vni << 8), + !net_eq(vxlan->net, dev_net(vxlan->dev))); - __skb_push(skb, sizeof(*uh)); - skb_reset_transport_header(skb); - uh = udp_hdr(skb); + if (err < 0) + goto rt_tx_error; + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); +#if IS_ENABLED(CONFIG_IPV6) + } else { + struct sock *sk = vxlan->vn_sock->sock->sk; + struct dst_entry *ndst; + struct flowi6 fl6; + u32 flags; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = rdst->remote_ifindex; + fl6.daddr = dst->sin6.sin6_addr; + fl6.saddr = vxlan->saddr.sin6.sin6_addr; + fl6.flowi6_proto = IPPROTO_UDP; + + if (ipv6_stub->ipv6_dst_lookup(sk, &ndst, &fl6)) { + netdev_dbg(dev, "no route to %pI6\n", + &dst->sin6.sin6_addr); + dev->stats.tx_carrier_errors++; + goto tx_error; + } - uh->dest = dst_port; - uh->source = src_port; + if (ndst->dev == dev) { + netdev_dbg(dev, "circular route to %pI6\n", + &dst->sin6.sin6_addr); + dst_release(ndst); + dev->stats.collisions++; + goto tx_error; + } - uh->len = htons(skb->len); - uh->check = 0; + /* Bypass encapsulation if the destination is local */ + flags = ((struct rt6_info *)ndst)->rt6i_flags; + if (flags & RTF_LOCAL && + !(flags & (RTCF_BROADCAST | RTCF_MULTICAST))) { + struct vxlan_dev *dst_vxlan; + + dst_release(ndst); + dst_vxlan = vxlan_find_vni(vxlan->net, vni, dst_port); + if (!dst_vxlan) + goto tx_error; + vxlan_encap_bypass(skb, vxlan, dst_vxlan); + return; + } - __skb_push(skb, sizeof(*iph)); - skb_reset_network_header(skb); - iph = ip_hdr(skb); - iph->version = 4; - iph->ihl = sizeof(struct iphdr) >> 2; - iph->frag_off = df; - iph->protocol = IPPROTO_UDP; - iph->tos = ip_tunnel_ecn_encap(tos, old_iph, skb); - iph->daddr = dst; - iph->saddr = fl4.saddr; - iph->ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); - tunnel_ip_select_ident(skb, old_iph, &rt->dst); - - nf_reset(skb); - - vxlan_set_owner(dev, skb); - - if (handle_offloads(skb)) - goto drop; + ttl = ttl ? : ip6_dst_hoplimit(ndst); - iptunnel_xmit(skb, dev); - return NETDEV_TX_OK; + err = vxlan6_xmit_skb(vxlan->vn_sock, ndst, skb, + dev, &fl6.saddr, &fl6.daddr, 0, ttl, + src_port, dst_port, htonl(vni << 8), + !net_eq(vxlan->net, dev_net(vxlan->dev))); +#endif + } + + return; drop: dev->stats.tx_dropped++; goto tx_free; +rt_tx_error: + ip_rt_put(rt); tx_error: dev->stats.tx_errors++; tx_free: dev_kfree_skb(skb); - return NETDEV_TX_OK; } /* Transmit local packets over Vxlan @@ -1114,52 +1932,70 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) struct vxlan_dev *vxlan = netdev_priv(dev); struct ethhdr *eth; bool did_rsc = false; - struct vxlan_rdst *rdst0, *rdst; + struct vxlan_rdst *rdst, *fdst = NULL; struct vxlan_fdb *f; - int rc1, rc; skb_reset_mac_header(skb); eth = eth_hdr(skb); - if ((vxlan->flags & VXLAN_F_PROXY) && ntohs(eth->h_proto) == ETH_P_ARP) - return arp_reduce(dev, skb); + if ((vxlan->flags & VXLAN_F_PROXY)) { + if (ntohs(eth->h_proto) == ETH_P_ARP) + return arp_reduce(dev, skb); +#if IS_ENABLED(CONFIG_IPV6) + else if (ntohs(eth->h_proto) == ETH_P_IPV6 && + skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *msg; + + msg = (struct nd_msg *)skb_transport_header(skb); + if (msg->icmph.icmp6_code == 0 && + msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) + return neigh_reduce(dev, skb); + } +#endif + } f = vxlan_find_mac(vxlan, eth->h_dest); did_rsc = false; if (f && (f->flags & NTF_ROUTER) && (vxlan->flags & VXLAN_F_RSC) && - ntohs(eth->h_proto) == ETH_P_IP) { + (ntohs(eth->h_proto) == ETH_P_IP || + ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); if (did_rsc) f = vxlan_find_mac(vxlan, eth->h_dest); } if (f == NULL) { - rdst0 = &vxlan->default_dst; - - if (rdst0->remote_ip == htonl(INADDR_ANY) && - (vxlan->flags & VXLAN_F_L2MISS) && - !is_multicast_ether_addr(eth->h_dest)) - vxlan_fdb_miss(vxlan, eth->h_dest); - } else - rdst0 = &f->remote; - - rc = NETDEV_TX_OK; + f = vxlan_find_mac(vxlan, all_zeros_mac); + if (f == NULL) { + if ((vxlan->flags & VXLAN_F_L2MISS) && + !is_multicast_ether_addr(eth->h_dest)) + vxlan_fdb_miss(vxlan, eth->h_dest); + + dev->stats.tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; + } + } - /* if there are multiple destinations, send copies */ - for (rdst = rdst0->remote_next; rdst; rdst = rdst->remote_next) { + list_for_each_entry_rcu(rdst, &f->remotes, list) { struct sk_buff *skb1; + if (!fdst) { + fdst = rdst; + continue; + } skb1 = skb_clone(skb, GFP_ATOMIC); - rc1 = vxlan_xmit_one(skb1, dev, rdst, did_rsc); - if (rc == NETDEV_TX_OK) - rc = rc1; + if (skb1) + vxlan_xmit_one(skb1, dev, rdst, did_rsc); } - rc1 = vxlan_xmit_one(skb, dev, rdst0, did_rsc); - if (rc == NETDEV_TX_OK) - rc = rc1; - return rc; + if (fdst) + vxlan_xmit_one(skb, dev, fdst, did_rsc); + else + kfree_skb(skb); + return NETDEV_TX_OK; } /* Walk the forwarding table and purge stale entries */ @@ -1199,26 +2035,78 @@ static void vxlan_cleanup(unsigned long arg) mod_timer(&vxlan->age_timer, next_timer); } +static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan) +{ + __u32 vni = vxlan->default_dst.remote_vni; + + vxlan->vn_sock = vs; + hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni)); +} + /* Setup stats when device is created */ static int vxlan_init(struct net_device *dev) { - dev->tstats = alloc_percpu(struct pcpu_tstats); + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_sock *vs; + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + spin_lock(&vn->sock_lock); + vs = vxlan_find_sock(vxlan->net, vxlan->dst_port); + if (vs) { + /* If we have a socket with same port already, reuse it */ + atomic_inc(&vs->refcnt); + vxlan_vs_add_dev(vs, vxlan); + } else { + /* otherwise make new socket outside of RTNL */ + dev_hold(dev); + queue_work(vxlan_wq, &vxlan->sock_work); + } + spin_unlock(&vn->sock_lock); + return 0; } +static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan) +{ + struct vxlan_fdb *f; + + spin_lock_bh(&vxlan->hash_lock); + f = __vxlan_find_mac(vxlan, all_zeros_mac); + if (f) + vxlan_fdb_destroy(vxlan, f); + spin_unlock_bh(&vxlan->hash_lock); +} + +static void vxlan_uninit(struct net_device *dev) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_sock *vs = vxlan->vn_sock; + + vxlan_fdb_delete_default(vxlan); + + if (vs) + vxlan_sock_release(vs); + free_percpu(dev->tstats); +} + /* Start ageing timer and join group when device is brought up */ static int vxlan_open(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); - int err; + struct vxlan_sock *vs = vxlan->vn_sock; - if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) { - err = vxlan_join_group(dev); - if (err) - return err; + /* socket hasn't been created */ + if (!vs) + return -ENOTCONN; + + if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) { + vxlan_sock_hold(vs); + dev_hold(dev); + queue_work(vxlan_wq, &vxlan->igmp_join); } if (vxlan->age_interval) @@ -1230,7 +2118,7 @@ static int vxlan_open(struct net_device *dev) /* Purge the forwarding table */ static void vxlan_flush(struct vxlan_dev *vxlan) { - unsigned h; + unsigned int h; spin_lock_bh(&vxlan->hash_lock); for (h = 0; h < FDB_HASH_SIZE; ++h) { @@ -1238,7 +2126,9 @@ static void vxlan_flush(struct vxlan_dev *vxlan) hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); - vxlan_fdb_destroy(vxlan, f); + /* the all_zeros_mac entry is deleted at vxlan_uninit */ + if (!is_zero_ether_addr(f->eth_addr)) + vxlan_fdb_destroy(vxlan, f); } } spin_unlock_bh(&vxlan->hash_lock); @@ -1248,9 +2138,15 @@ static void vxlan_flush(struct vxlan_dev *vxlan) static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); - - if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) - vxlan_leave_group(dev); + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_sock *vs = vxlan->vn_sock; + + if (vs && vxlan_addr_multicast(&vxlan->default_dst.remote_ip) && + !vxlan_group_used(vn, vxlan)) { + vxlan_sock_hold(vs); + dev_hold(dev); + queue_work(vxlan_wq, &vxlan->igmp_leave); + } del_timer_sync(&vxlan->age_timer); @@ -1264,14 +2160,38 @@ static void vxlan_set_multicast_list(struct net_device *dev) { } +static int vxlan_change_mtu(struct net_device *dev, int new_mtu) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_rdst *dst = &vxlan->default_dst; + struct net_device *lowerdev; + int max_mtu; + + lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); + if (lowerdev == NULL) + return eth_change_mtu(dev, new_mtu); + + if (dst->remote_ip.sa.sa_family == AF_INET6) + max_mtu = lowerdev->mtu - VXLAN6_HEADROOM; + else + max_mtu = lowerdev->mtu - VXLAN_HEADROOM; + + if (new_mtu < 68 || new_mtu > max_mtu) + return -EINVAL; + + dev->mtu = new_mtu; + return 0; +} + static const struct net_device_ops vxlan_netdev_ops = { .ndo_init = vxlan_init, + .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_set_rx_mode = vxlan_set_multicast_list, - .ndo_change_mtu = eth_change_mtu, + .ndo_change_mtu = vxlan_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fdb_add = vxlan_fdb_add, @@ -1284,46 +2204,75 @@ static struct device_type vxlan_type = { .name = "vxlan", }; -static void vxlan_free(struct net_device *dev) +/* Calls the ndo_add_vxlan_port of the caller in order to + * supply the listening VXLAN udp ports. Callers are expected + * to implement the ndo_add_vxlan_port. + */ +void vxlan_get_rx_port(struct net_device *dev) { - free_percpu(dev->tstats); - free_netdev(dev); + struct vxlan_sock *vs; + struct net *net = dev_net(dev); + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + sa_family_t sa_family; + __be16 port; + unsigned int i; + + spin_lock(&vn->sock_lock); + for (i = 0; i < PORT_HASH_SIZE; ++i) { + hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) { + port = inet_sk(vs->sock->sk)->inet_sport; + sa_family = vs->sock->sk->sk_family; + dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family, + port); + } + } + spin_unlock(&vn->sock_lock); } +EXPORT_SYMBOL_GPL(vxlan_get_rx_port); /* Initialize the device structure. */ static void vxlan_setup(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); - unsigned h; + unsigned int h; int low, high; eth_hw_addr_random(dev); ether_setup(dev); - dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM; + if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6) + dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM; + else + dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM; dev->netdev_ops = &vxlan_netdev_ops; - dev->destructor = vxlan_free; + dev->destructor = free_netdev; SET_NETDEV_DEVTYPE(dev, &vxlan_type); dev->tx_queue_len = 0; dev->features |= NETIF_F_LLTX; - dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; + dev->vlan_features = dev->features; + dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + INIT_LIST_HEAD(&vxlan->next); spin_lock_init(&vxlan->hash_lock); + INIT_WORK(&vxlan->igmp_join, vxlan_igmp_join); + INIT_WORK(&vxlan->igmp_leave, vxlan_igmp_leave); + INIT_WORK(&vxlan->sock_work, vxlan_sock_work); init_timer_deferrable(&vxlan->age_timer); vxlan->age_timer.function = vxlan_cleanup; vxlan->age_timer.data = (unsigned long) vxlan; - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(dev_net(dev), &low, &high); vxlan->port_min = low; vxlan->port_max = high; vxlan->dst_port = htons(vxlan_port); @@ -1337,8 +2286,10 @@ static void vxlan_setup(struct net_device *dev) static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_ID] = { .type = NLA_U32 }, [IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, [IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, + [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, @@ -1401,29 +2352,268 @@ static const struct ethtool_ops vxlan_ethtool_ops = { .get_link = ethtool_op_get_link, }; +static void vxlan_del_work(struct work_struct *work) +{ + struct vxlan_sock *vs = container_of(work, struct vxlan_sock, del_work); + + sk_release_kernel(vs->sock->sk); + kfree_rcu(vs, rcu); +} + +#if IS_ENABLED(CONFIG_IPV6) +/* Create UDP socket for encapsulation receive. AF_INET6 socket + * could be used for both IPv4 and IPv6 communications, but + * users may set bindv6only=1. + */ +static struct socket *create_v6_sock(struct net *net, __be16 port, u32 flags) +{ + struct sock *sk; + struct socket *sock; + struct sockaddr_in6 vxlan_addr = { + .sin6_family = AF_INET6, + .sin6_port = port, + }; + int rc, val = 1; + + rc = sock_create_kern(AF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock); + if (rc < 0) { + pr_debug("UDPv6 socket create failed\n"); + return ERR_PTR(rc); + } + + /* Put in proper namespace */ + sk = sock->sk; + sk_change_net(sk, net); + + kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY, + (char *)&val, sizeof(val)); + rc = kernel_bind(sock, (struct sockaddr *)&vxlan_addr, + sizeof(struct sockaddr_in6)); + if (rc < 0) { + pr_debug("bind for UDPv6 socket %pI6:%u (%d)\n", + &vxlan_addr.sin6_addr, ntohs(vxlan_addr.sin6_port), rc); + sk_release_kernel(sk); + return ERR_PTR(rc); + } + /* At this point, IPv6 module should have been loaded in + * sock_create_kern(). + */ + BUG_ON(!ipv6_stub); + + /* Disable multicast loopback */ + inet_sk(sk)->mc_loop = 0; + + if (flags & VXLAN_F_UDP_ZERO_CSUM6_TX) + udp_set_no_check6_tx(sk, true); + + if (flags & VXLAN_F_UDP_ZERO_CSUM6_RX) + udp_set_no_check6_rx(sk, true); + + return sock; +} + +#else + +static struct socket *create_v6_sock(struct net *net, __be16 port, u32 flags) +{ + return ERR_PTR(-EPFNOSUPPORT); +} +#endif + +static struct socket *create_v4_sock(struct net *net, __be16 port, u32 flags) +{ + struct sock *sk; + struct socket *sock; + struct sockaddr_in vxlan_addr = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_ANY), + .sin_port = port, + }; + int rc; + + /* Create UDP socket for encapsulation receive. */ + rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + if (rc < 0) { + pr_debug("UDP socket create failed\n"); + return ERR_PTR(rc); + } + + /* Put in proper namespace */ + sk = sock->sk; + sk_change_net(sk, net); + + rc = kernel_bind(sock, (struct sockaddr *) &vxlan_addr, + sizeof(vxlan_addr)); + if (rc < 0) { + pr_debug("bind for UDP socket %pI4:%u (%d)\n", + &vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc); + sk_release_kernel(sk); + return ERR_PTR(rc); + } + + /* Disable multicast loopback */ + inet_sk(sk)->mc_loop = 0; + + if (!(flags & VXLAN_F_UDP_CSUM)) + sock->sk->sk_no_check_tx = 1; + + return sock; +} + +/* Create new listen socket if needed */ +static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, + vxlan_rcv_t *rcv, void *data, + u32 flags) +{ + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_sock *vs; + struct socket *sock; + struct sock *sk; + unsigned int h; + bool ipv6 = !!(flags & VXLAN_F_IPV6); + + vs = kzalloc(sizeof(*vs), GFP_KERNEL); + if (!vs) + return ERR_PTR(-ENOMEM); + + for (h = 0; h < VNI_HASH_SIZE; ++h) + INIT_HLIST_HEAD(&vs->vni_list[h]); + + INIT_WORK(&vs->del_work, vxlan_del_work); + + if (ipv6) + sock = create_v6_sock(net, port, flags); + else + sock = create_v4_sock(net, port, flags); + if (IS_ERR(sock)) { + kfree(vs); + return ERR_CAST(sock); + } + + vs->sock = sock; + sk = sock->sk; + atomic_set(&vs->refcnt, 1); + vs->rcv = rcv; + vs->data = data; + rcu_assign_sk_user_data(vs->sock->sk, vs); + + /* Initialize the vxlan udp offloads structure */ + vs->udp_offloads.port = port; + vs->udp_offloads.callbacks.gro_receive = vxlan_gro_receive; + vs->udp_offloads.callbacks.gro_complete = vxlan_gro_complete; + + spin_lock(&vn->sock_lock); + hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); + vxlan_notify_add_rx_port(vs); + spin_unlock(&vn->sock_lock); + + /* Mark socket as an encapsulation socket. */ + udp_sk(sk)->encap_type = 1; + udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv; +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6) + ipv6_stub->udpv6_encap_enable(); + else +#endif + udp_encap_enable(); + + return vs; +} + +struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, + vxlan_rcv_t *rcv, void *data, + bool no_share, u32 flags) +{ + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_sock *vs; + + vs = vxlan_socket_create(net, port, rcv, data, flags); + if (!IS_ERR(vs)) + return vs; + + if (no_share) /* Return error if sharing is not allowed. */ + return vs; + + spin_lock(&vn->sock_lock); + vs = vxlan_find_sock(net, port); + if (vs) { + if (vs->rcv == rcv) + atomic_inc(&vs->refcnt); + else + vs = ERR_PTR(-EBUSY); + } + spin_unlock(&vn->sock_lock); + + if (!vs) + vs = ERR_PTR(-EINVAL); + + return vs; +} +EXPORT_SYMBOL_GPL(vxlan_sock_add); + +/* Scheduled at device creation to bind to a socket */ +static void vxlan_sock_work(struct work_struct *work) +{ + struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, sock_work); + struct net *net = vxlan->net; + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + __be16 port = vxlan->dst_port; + struct vxlan_sock *nvs; + + nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags); + spin_lock(&vn->sock_lock); + if (!IS_ERR(nvs)) + vxlan_vs_add_dev(nvs, vxlan); + spin_unlock(&vn->sock_lock); + + dev_put(vxlan->dev); +} + static int vxlan_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { + struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; __u32 vni; int err; + bool use_ipv6 = false; if (!data[IFLA_VXLAN_ID]) return -EINVAL; + vxlan->net = dev_net(dev); + vni = nla_get_u32(data[IFLA_VXLAN_ID]); - if (vxlan_find_vni(net, vni)) { - pr_info("duplicate VNI %u\n", vni); - return -EEXIST; - } dst->remote_vni = vni; - if (data[IFLA_VXLAN_GROUP]) - dst->remote_ip = nla_get_be32(data[IFLA_VXLAN_GROUP]); + /* Unless IPv6 is explicitly requested, assume IPv4 */ + dst->remote_ip.sa.sa_family = AF_INET; + if (data[IFLA_VXLAN_GROUP]) { + dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]); + } else if (data[IFLA_VXLAN_GROUP6]) { + if (!IS_ENABLED(CONFIG_IPV6)) + return -EPFNOSUPPORT; + + nla_memcpy(&dst->remote_ip.sin6.sin6_addr, data[IFLA_VXLAN_GROUP6], + sizeof(struct in6_addr)); + dst->remote_ip.sa.sa_family = AF_INET6; + use_ipv6 = true; + } - if (data[IFLA_VXLAN_LOCAL]) - vxlan->saddr = nla_get_be32(data[IFLA_VXLAN_LOCAL]); + if (data[IFLA_VXLAN_LOCAL]) { + vxlan->saddr.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_LOCAL]); + vxlan->saddr.sa.sa_family = AF_INET; + } else if (data[IFLA_VXLAN_LOCAL6]) { + if (!IS_ENABLED(CONFIG_IPV6)) + return -EPFNOSUPPORT; + + /* TODO: respect scope id */ + nla_memcpy(&vxlan->saddr.sin6.sin6_addr, data[IFLA_VXLAN_LOCAL6], + sizeof(struct in6_addr)); + vxlan->saddr.sa.sa_family = AF_INET6; + use_ipv6 = true; + } if (data[IFLA_VXLAN_LINK] && (dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) { @@ -1435,13 +2625,24 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, return -ENODEV; } +#if IS_ENABLED(CONFIG_IPV6) + if (use_ipv6) { + struct inet6_dev *idev = __in6_dev_get(lowerdev); + if (idev && idev->cnf.disable_ipv6) { + pr_info("IPv6 is disabled via sysctl\n"); + return -EPERM; + } + vxlan->flags |= VXLAN_F_IPV6; + } +#endif + if (!tb[IFLA_MTU]) - dev->mtu = lowerdev->mtu - VXLAN_HEADROOM; + dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); - /* update header length based on lower device */ - dev->hard_header_len = lowerdev->hard_header_len + - VXLAN_HEADROOM; - } + dev->needed_headroom = lowerdev->hard_header_len + + (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); + } else if (use_ipv6) + vxlan->flags |= VXLAN_F_IPV6; if (data[IFLA_VXLAN_TOS]) vxlan->tos = nla_get_u8(data[IFLA_VXLAN_TOS]); @@ -1482,21 +2683,60 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, if (data[IFLA_VXLAN_PORT]) vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); - SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops); + if (data[IFLA_VXLAN_UDP_CSUM] && nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) + vxlan->flags |= VXLAN_F_UDP_CSUM; + + if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] && + nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX])) + vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_TX; + + if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] && + nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX])) + vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX; + + if (vxlan_find_vni(net, vni, vxlan->dst_port)) { + pr_info("duplicate VNI %u\n", vni); + return -EEXIST; + } + + dev->ethtool_ops = &vxlan_ethtool_ops; + + /* create an fdb entry for a valid default destination */ + if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) { + err = vxlan_fdb_create(vxlan, all_zeros_mac, + &vxlan->default_dst.remote_ip, + NUD_REACHABLE|NUD_PERMANENT, + NLM_F_EXCL|NLM_F_CREATE, + vxlan->dst_port, + vxlan->default_dst.remote_vni, + vxlan->default_dst.remote_ifindex, + NTF_SELF); + if (err) + return err; + } err = register_netdevice(dev); - if (!err) - hlist_add_head_rcu(&vxlan->hlist, vni_head(net, dst->remote_vni)); + if (err) { + vxlan_fdb_delete_default(vxlan); + return err; + } - return err; + list_add(&vxlan->next, &vn->vxlan_list); + + return 0; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) { struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); - hlist_del_rcu(&vxlan->hlist); + spin_lock(&vn->sock_lock); + if (!hlist_unhashed(&vxlan->hlist)) + hlist_del_rcu(&vxlan->hlist); + spin_unlock(&vn->sock_lock); + list_del(&vxlan->next); unregister_netdevice_queue(dev, head); } @@ -1504,9 +2744,9 @@ static size_t vxlan_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */ - nla_total_size(sizeof(__be32)) +/* IFLA_VXLAN_GROUP */ + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{6} */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */ - nla_total_size(sizeof(__be32))+ /* IFLA_VXLAN_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ @@ -1517,7 +2757,10 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_AGEING */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LIMIT */ nla_total_size(sizeof(struct ifla_vxlan_port_range)) + - nla_total_size(sizeof(__be16))+ /* IFLA_VXLAN_PORT */ + nla_total_size(sizeof(__be16)) + /* IFLA_VXLAN_PORT */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */ 0; } @@ -1533,14 +2776,36 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_VXLAN_ID, dst->remote_vni)) goto nla_put_failure; - if (dst->remote_ip && nla_put_be32(skb, IFLA_VXLAN_GROUP, dst->remote_ip)) - goto nla_put_failure; + if (!vxlan_addr_any(&dst->remote_ip)) { + if (dst->remote_ip.sa.sa_family == AF_INET) { + if (nla_put_be32(skb, IFLA_VXLAN_GROUP, + dst->remote_ip.sin.sin_addr.s_addr)) + goto nla_put_failure; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (nla_put(skb, IFLA_VXLAN_GROUP6, sizeof(struct in6_addr), + &dst->remote_ip.sin6.sin6_addr)) + goto nla_put_failure; +#endif + } + } if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex)) goto nla_put_failure; - if (vxlan->saddr && nla_put_be32(skb, IFLA_VXLAN_LOCAL, vxlan->saddr)) - goto nla_put_failure; + if (!vxlan_addr_any(&vxlan->saddr)) { + if (vxlan->saddr.sa.sa_family == AF_INET) { + if (nla_put_be32(skb, IFLA_VXLAN_LOCAL, + vxlan->saddr.sin.sin_addr.s_addr)) + goto nla_put_failure; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (nla_put(skb, IFLA_VXLAN_LOCAL6, sizeof(struct in6_addr), + &vxlan->saddr.sin6.sin6_addr)) + goto nla_put_failure; +#endif + } + } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) || @@ -1555,7 +2820,13 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) !!(vxlan->flags & VXLAN_F_L3MISS)) || nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->age_interval) || nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->addrmax) || - nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port)) + nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port) || + nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, + !!(vxlan->flags & VXLAN_F_UDP_CSUM)) || + nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || + nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_RX))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) @@ -1580,69 +2851,80 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = { .fill_info = vxlan_fill_info, }; -static __net_init int vxlan_init_net(struct net *net) +static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn, + struct net_device *dev) { - struct vxlan_net *vn = net_generic(net, vxlan_net_id); - struct sock *sk; - struct sockaddr_in vxlan_addr = { - .sin_family = AF_INET, - .sin_addr.s_addr = htonl(INADDR_ANY), - }; - int rc; - unsigned h; - - /* Create UDP socket for encapsulation receive. */ - rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &vn->sock); - if (rc < 0) { - pr_debug("UDP socket create failed\n"); - return rc; + struct vxlan_dev *vxlan, *next; + LIST_HEAD(list_kill); + + list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) { + struct vxlan_rdst *dst = &vxlan->default_dst; + + /* In case we created vxlan device with carrier + * and we loose the carrier due to module unload + * we also need to remove vxlan device. In other + * cases, it's not necessary and remote_ifindex + * is 0 here, so no matches. + */ + if (dst->remote_ifindex == dev->ifindex) + vxlan_dellink(vxlan->dev, &list_kill); } - /* Put in proper namespace */ - sk = vn->sock->sk; - sk_change_net(sk, net); - vxlan_addr.sin_port = htons(vxlan_port); + unregister_netdevice_many(&list_kill); +} - rc = kernel_bind(vn->sock, (struct sockaddr *) &vxlan_addr, - sizeof(vxlan_addr)); - if (rc < 0) { - pr_debug("bind for UDP socket %pI4:%u (%d)\n", - &vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc); - sk_release_kernel(sk); - vn->sock = NULL; - return rc; - } +static int vxlan_lowerdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); - /* Disable multicast loopback */ - inet_sk(sk)->mc_loop = 0; + if (event == NETDEV_UNREGISTER) + vxlan_handle_lowerdev_unregister(vn, dev); - /* Mark socket as an encapsulation socket. */ - udp_sk(sk)->encap_type = 1; - udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv; - udp_encap_enable(); + return NOTIFY_DONE; +} - for (h = 0; h < VNI_HASH_SIZE; ++h) - INIT_HLIST_HEAD(&vn->vni_list[h]); +static struct notifier_block vxlan_notifier_block __read_mostly = { + .notifier_call = vxlan_lowerdev_event, +}; + +static __net_init int vxlan_init_net(struct net *net) +{ + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + unsigned int h; + + INIT_LIST_HEAD(&vn->vxlan_list); + spin_lock_init(&vn->sock_lock); + + for (h = 0; h < PORT_HASH_SIZE; ++h) + INIT_HLIST_HEAD(&vn->sock_list[h]); return 0; } -static __net_exit void vxlan_exit_net(struct net *net) +static void __net_exit vxlan_exit_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); - struct vxlan_dev *vxlan; - unsigned h; + struct vxlan_dev *vxlan, *next; + struct net_device *dev, *aux; + LIST_HEAD(list); rtnl_lock(); - for (h = 0; h < VNI_HASH_SIZE; ++h) - hlist_for_each_entry(vxlan, &vn->vni_list[h], hlist) - dev_close(vxlan->dev); - rtnl_unlock(); - - if (vn->sock) { - sk_release_kernel(vn->sock->sk); - vn->sock = NULL; + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &vxlan_link_ops) + unregister_netdevice_queue(dev, &list); + + list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) { + /* If vxlan->dev is in the same netns, it has already been added + * to the list by the previous loop. + */ + if (!net_eq(dev_net(vxlan->dev), net)) + unregister_netdevice_queue(dev, &list); } + + unregister_netdevice_many(&list); + rtnl_unlock(); } static struct pernet_operations vxlan_net_ops = { @@ -1656,34 +2938,47 @@ static int __init vxlan_init_module(void) { int rc; + vxlan_wq = alloc_workqueue("vxlan", 0, 0); + if (!vxlan_wq) + return -ENOMEM; + get_random_bytes(&vxlan_salt, sizeof(vxlan_salt)); - rc = register_pernet_device(&vxlan_net_ops); + rc = register_pernet_subsys(&vxlan_net_ops); if (rc) goto out1; - rc = rtnl_link_register(&vxlan_link_ops); + rc = register_netdevice_notifier(&vxlan_notifier_block); if (rc) goto out2; - return 0; + rc = rtnl_link_register(&vxlan_link_ops); + if (rc) + goto out3; + return 0; +out3: + unregister_netdevice_notifier(&vxlan_notifier_block); out2: - unregister_pernet_device(&vxlan_net_ops); + unregister_pernet_subsys(&vxlan_net_ops); out1: + destroy_workqueue(vxlan_wq); return rc; } -module_init(vxlan_init_module); +late_initcall(vxlan_init_module); static void __exit vxlan_cleanup_module(void) { rtnl_link_unregister(&vxlan_link_ops); - unregister_pernet_device(&vxlan_net_ops); - rcu_barrier(); + unregister_netdevice_notifier(&vxlan_notifier_block); + destroy_workqueue(vxlan_wq); + unregister_pernet_subsys(&vxlan_net_ops); + /* rcu_barrier() is called by netns */ } module_exit(vxlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(VXLAN_VERSION); MODULE_AUTHOR("Stephen Hemminger <stephen@networkplumber.org>"); +MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("vxlan"); |