X-Git-Url: http://git.monstr.eu/?a=blobdiff_plain;f=drivers%2Fnet%2Fvxlan.c;h=bdfe46e50c495e6cffe0d505677e4147dd91946d;hb=afbd8bae9c79;hp=57325f356d4f125421bfa297a4beb2302c5f194b;hpb=eb064c3b49931dc73bba59887019c7f5cb97d322;p=linux-2.6-microblaze.git diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 57325f356d4f..bdfe46e50c49 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -44,6 +44,8 @@ #define VXLAN_VERSION "0.1" +#define PORT_HASH_BITS 8 +#define PORT_HASH_SIZE (1<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)]; +} + +/* First remote destination for a forwarding entry. + * Guaranteed to be non-NULL because remotes are never deleted. + */ +static inline struct vxlan_rdst *first_remote(struct vxlan_fdb *fdb) +{ + return list_first_or_null_rcu(&fdb->remotes, struct vxlan_rdst, list); +} + +/* Find VXLAN socket based on network namespace and UDP port */ +static struct vxlan_sock *vxlan_find_port(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; } /* Look up VNI in a per net namespace table */ -static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id) +static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port) { + struct vxlan_sock *vs; struct vxlan_dev *vxlan; - hlist_for_each_entry_rcu(vxlan, vni_head(net, id), hlist) { + vs = vxlan_find_port(net, port); + if (!vs) + return NULL; + + hlist_for_each_entry_rcu(vxlan, vni_head(vs, id), hlist) { if (vxlan->default_dst.remote_vni == id) return vxlan; } @@ -157,9 +212,9 @@ static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 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; @@ -197,7 +252,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, 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)) @@ -230,7 +285,7 @@ static inline size_t vxlan_nlmsg_size(void) } static void vxlan_fdb_notify(struct vxlan_dev *vxlan, - const struct vxlan_fdb *fdb, int type) + struct vxlan_fdb *fdb, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; @@ -240,7 +295,7 @@ 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, first_remote(fdb)); if (err < 0) { /* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -258,22 +313,27 @@ errout: static void vxlan_ip_miss(struct net_device *dev, __be32 ipa) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_fdb f; + struct vxlan_fdb f = { + .state = NUD_STALE, + }; + struct vxlan_rdst remote = { + .remote_ip = ipa, /* goes to NDA_DST */ + .remote_vni = VXLAN_N_VID, + }; - 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; + INIT_LIST_HEAD(&f.remotes); + list_add_rcu(&remote.list, &f.remotes); vxlan_fdb_notify(vxlan, &f, 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, + }; - memset(&f, 0, sizeof f); - f.state = NUD_STALE; + INIT_LIST_HEAD(&f.remotes); memcpy(f.eth_addr, eth_addr, ETH_ALEN); vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH); @@ -332,17 +392,17 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, static int vxlan_fdb_append(struct vxlan_fdb *f, __be32 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) { + /* protected by vxlan->hash_lock */ + list_for_each_entry(rd, &f->remotes, list) { if (rd->remote_ip == ip && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex) return 0; - rd_prev = rd; } + rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) return -ENOBUFS; @@ -350,8 +410,9 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, 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); + return 1; } @@ -403,16 +464,14 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, 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); + ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, vxlan_fdb_head(vxlan, mac)); @@ -427,13 +486,10 @@ 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); } @@ -543,23 +599,24 @@ 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; } @@ -575,7 +632,9 @@ static bool vxlan_snoop(struct net_device *dev, f = vxlan_find_mac(vxlan, src_mac); if (likely(f)) { - if (likely(f->remote.remote_ip == src_ip)) + struct vxlan_rdst *rdst = first_remote(f); + + if (likely(rdst->remote_ip == src_ip)) return false; /* Don't migrate static entries, drop packets */ @@ -585,10 +644,11 @@ static bool vxlan_snoop(struct net_device *dev, if (net_ratelimit()) netdev_info(dev, "%pM migrated from %pI4 to %pI4\n", - src_mac, &f->remote.remote_ip, &src_ip); + 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, RTM_NEWNEIGH); } else { /* learned new entry */ spin_lock(&vxlan->hash_lock); @@ -609,78 +669,61 @@ static bool vxlan_snoop(struct net_device *dev, /* 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, __be32 remote_ip) { - 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; + list_for_each_entry(vxlan, &vn->vxlan_list, next) { + if (!netif_running(vxlan->dev)) + continue; - if (!netif_running(vxlan->dev)) - continue; - - if (vxlan->default_dst.remote_ip == this->default_dst.remote_ip) - return true; - } + if (vxlan->default_dst.remote_ip == remote_ip) + 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; +static void vxlan_sock_release(struct vxlan_net *vn, struct vxlan_sock *vs) +{ + if (!atomic_dec_and_test(&vs->refcnt)) + return; - /* Need to drop RTNL to call multicast join */ - rtnl_unlock(); - lock_sock(sk); - err = ip_mc_join_group(sk, &mreq); - release_sock(sk); - rtnl_lock(); + spin_lock(&vn->sock_lock); + hlist_del_rcu(&vs->hlist); + spin_unlock(&vn->sock_lock); - return err; + queue_work(vxlan_wq, &vs->del_work); } - -/* kernel equivalent to IP_DROP_MEMBERSHIP */ -static int vxlan_leave_group(struct net_device *dev) +/* Callback to update multicast group membership. + * Scheduled when vxlan goes up/down. + */ +static void vxlan_igmp_work(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 vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_work); + struct vxlan_net *vn = net_generic(dev_net(vxlan->dev), vxlan_net_id); + struct vxlan_sock *vs = vxlan->vn_sock; + struct sock *sk = vs->sock->sk; struct ip_mreqn mreq = { .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip, .imr_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 (vxlan_group_used(vn, vxlan->default_dst.remote_ip)) + ip_mc_join_group(sk, &mreq); + else + ip_mc_leave_group(sk, &mreq); release_sock(sk); - rtnl_lock(); - return err; + vxlan_sock_release(vn, vs); + dev_put(vxlan->dev); } /* Callback from net/ipv4/udp.c to receive packets */ @@ -690,6 +733,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) struct vxlanhdr *vxh; struct vxlan_dev *vxlan; struct pcpu_tstats *stats; + __be16 port; __u32 vni; int err; @@ -713,9 +757,11 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) /* Is this VNI defined? */ vni = ntohl(vxh->vx_vni) >> 8; - vxlan = vxlan_find_vni(sock_net(sk), vni); + port = inet_sk(sk)->inet_sport; + vxlan = vxlan_find_vni(sock_net(sk), vni, port); if (!vxlan) { - netdev_dbg(skb->dev, "unknown vni %d\n", vni); + netdev_dbg(skb->dev, "unknown vni %d port %u\n", + vni, ntohs(port)); goto drop; } @@ -834,7 +880,7 @@ 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 && first_remote(f)->remote_ip == htonl(INADDR_ANY)) { /* bridge-local neighbor */ neigh_release(n); goto out; @@ -896,7 +942,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) return false; } -static void vxlan_sock_free(struct sk_buff *skb) +static void vxlan_sock_put(struct sk_buff *skb) { sock_put(skb->sk); } @@ -904,13 +950,13 @@ static void vxlan_sock_free(struct sk_buff *skb) /* 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; + struct vxlan_dev *vxlan = netdev_priv(dev); + struct sock *sk = vxlan->vn_sock->sock->sk; skb_orphan(skb); sock_hold(sk); skb->sk = sk; - skb->destructor = vxlan_sock_free; + skb->destructor = vxlan_sock_put; } /* Compute source port for outgoing packet @@ -976,21 +1022,21 @@ 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; 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; + 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; @@ -1000,7 +1046,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (did_rsc) { /* short-circuited back to local bridge */ vxlan_encap_bypass(skb, vxlan, vxlan); - return NETDEV_TX_OK; + return; } goto drop; } @@ -1052,19 +1098,12 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *dst_vxlan; ip_rt_put(rt); - dst_vxlan = vxlan_find_vni(dev_net(dev), vni); + dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port); if (!dst_vxlan) goto tx_error; vxlan_encap_bypass(skb, vxlan, dst_vxlan); - return NETDEV_TX_OK; + 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); - vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); vxh->vx_flags = htonl(VXLAN_FLAGS); vxh->vx_vni = htonl(vni << 8); @@ -1079,28 +1118,19 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, uh->len = htons(skb->len); uh->check = 0; - __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; - iptunnel_xmit(skb, dev); - return NETDEV_TX_OK; + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); + ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); + + err = iptunnel_xmit(dev_net(dev), rt, skb, fl4.saddr, dst, + IPPROTO_UDP, tos, ttl, df); + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + + return; drop: dev->stats.tx_dropped++; @@ -1110,7 +1140,6 @@ tx_error: dev->stats.tx_errors++; tx_free: dev_kfree_skb(skb); - return NETDEV_TX_OK; } /* Transmit local packets over Vxlan @@ -1124,9 +1153,8 @@ 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; struct vxlan_fdb *f; - int rc1, rc; skb_reset_mac_header(skb); eth = eth_hdr(skb); @@ -1145,33 +1173,28 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) } 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++; + dev_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; skb1 = skb_clone(skb, GFP_ATOMIC); - if (skb1) { - 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; + dev_kfree_skb(skb); + return NETDEV_TX_OK; } /* Walk the forwarding table and purge stale entries */ @@ -1214,23 +1237,70 @@ static void vxlan_cleanup(unsigned long arg) /* Setup stats when device is created */ static int vxlan_init(struct net_device *dev) { + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); + struct vxlan_sock *vs; + __u32 vni = vxlan->default_dst.remote_vni; + dev->tstats = alloc_percpu(struct pcpu_tstats); if (!dev->tstats) return -ENOMEM; + spin_lock(&vn->sock_lock); + vs = vxlan_find_port(dev_net(dev), vxlan->dst_port); + if (vs) { + /* If we have a socket with same port already, reuse it */ + atomic_inc(&vs->refcnt); + vxlan->vn_sock = vs; + hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni)); + } 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_defualt(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_net *vn = net_generic(dev_net(dev), vxlan_net_id); + struct vxlan_sock *vs = vxlan->vn_sock; + + vxlan_fdb_delete_defualt(vxlan); + + if (vs) + vxlan_sock_release(vn, 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; + + /* socket hasn't been created */ + if (!vs) + return -ENOTCONN; if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) { - err = vxlan_join_group(dev); - if (err) - return err; + vxlan_sock_hold(vs); + dev_hold(dev); + queue_work(vxlan_wq, &vxlan->igmp_work); } if (vxlan->age_interval) @@ -1242,7 +1312,7 @@ 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) { @@ -1250,7 +1320,9 @@ 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); @@ -1260,9 +1332,13 @@ static void vxlan_flush(struct vxlan_dev *vxlan) static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_sock *vs = vxlan->vn_sock; - if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) - vxlan_leave_group(dev); + if (vs && IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) { + vxlan_sock_hold(vs); + dev_hold(dev); + queue_work(vxlan_wq, &vxlan->igmp_work); + } del_timer_sync(&vxlan->age_timer); @@ -1278,6 +1354,7 @@ static void vxlan_set_multicast_list(struct net_device *dev) 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, @@ -1296,17 +1373,11 @@ static struct device_type vxlan_type = { .name = "vxlan", }; -static void vxlan_free(struct net_device *dev) -{ - free_percpu(dev->tstats); - free_netdev(dev); -} - /* 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); @@ -1314,7 +1385,7 @@ static void vxlan_setup(struct net_device *dev) dev->hard_header_len = 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; @@ -1329,7 +1400,10 @@ static void vxlan_setup(struct net_device *dev) 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_work, vxlan_igmp_work); + INIT_WORK(&vxlan->sock_work, vxlan_sock_work); init_timer_deferrable(&vxlan->age_timer); vxlan->age_timer.function = vxlan_cleanup; @@ -1413,9 +1487,113 @@ 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); +} + +static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port) +{ + struct vxlan_sock *vs; + struct sock *sk; + struct sockaddr_in vxlan_addr = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_ANY), + .sin_port = port, + }; + int rc; + unsigned int h; + + vs = kmalloc(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); + + /* Create UDP socket for encapsulation receive. */ + rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &vs->sock); + if (rc < 0) { + pr_debug("UDP socket create failed\n"); + kfree(vs); + return ERR_PTR(rc); + } + + /* Put in proper namespace */ + sk = vs->sock->sk; + sk_change_net(sk, net); + + rc = kernel_bind(vs->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); + kfree(vs); + return ERR_PTR(rc); + } + + /* Disable multicast loopback */ + inet_sk(sk)->mc_loop = 0; + + /* Mark socket as an encapsulation socket. */ + udp_sk(sk)->encap_type = 1; + udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv; + udp_encap_enable(); + atomic_set(&vs->refcnt, 1); + + return vs; +} + +/* 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_device *dev = vxlan->dev; + struct net *net = dev_net(dev); + __u32 vni = vxlan->default_dst.remote_vni; + __be16 port = vxlan->dst_port; + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_sock *nvs, *ovs; + + nvs = vxlan_socket_create(net, port); + if (IS_ERR(nvs)) { + netdev_err(vxlan->dev, "Can not create UDP socket, %ld\n", + PTR_ERR(nvs)); + goto out; + } + + spin_lock(&vn->sock_lock); + /* Look again to see if can reuse socket */ + ovs = vxlan_find_port(net, port); + if (ovs) { + atomic_inc(&ovs->refcnt); + vxlan->vn_sock = ovs; + hlist_add_head_rcu(&vxlan->hlist, vni_head(ovs, vni)); + spin_unlock(&vn->sock_lock); + + sk_release_kernel(nvs->sock->sk); + kfree(nvs); + } else { + vxlan->vn_sock = nvs; + hlist_add_head_rcu(&nvs->hlist, vs_head(net, port)); + hlist_add_head_rcu(&vxlan->hlist, vni_head(nvs, vni)); + spin_unlock(&vn->sock_lock); + } +out: + dev_put(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; @@ -1425,10 +1603,6 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, return -EINVAL; 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]) @@ -1494,13 +1668,32 @@ 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]); + if (vxlan_find_vni(net, vni, vxlan->dst_port)) { + pr_info("duplicate VNI %u\n", vni); + return -EEXIST; + } + SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops); + /* create an fdb entry for default destination */ + 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_defualt(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) @@ -1508,7 +1701,7 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head) struct vxlan_dev *vxlan = netdev_priv(dev); hlist_del_rcu(&vxlan->hlist); - + list_del(&vxlan->next); unregister_netdevice_queue(dev, head); } @@ -1595,46 +1788,13 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = { static __net_init int vxlan_init_net(struct net *net) { 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; - } - /* Put in proper namespace */ - sk = vn->sock->sk; - sk_change_net(sk, net); - - vxlan_addr.sin_port = htons(vxlan_port); - - 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; - } - - /* Disable multicast loopback */ - inet_sk(sk)->mc_loop = 0; + unsigned int h; - /* Mark socket as an encapsulation socket. */ - udp_sk(sk)->encap_type = 1; - udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv; - udp_encap_enable(); + INIT_LIST_HEAD(&vn->vxlan_list); + spin_lock_init(&vn->sock_lock); - for (h = 0; h < VNI_HASH_SIZE; ++h) - INIT_HLIST_HEAD(&vn->vni_list[h]); + for (h = 0; h < PORT_HASH_SIZE; ++h) + INIT_HLIST_HEAD(&vn->sock_list[h]); return 0; } @@ -1643,18 +1803,11 @@ static __net_exit void vxlan_exit_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan; - unsigned h; rtnl_lock(); - for (h = 0; h < VNI_HASH_SIZE; ++h) - hlist_for_each_entry(vxlan, &vn->vni_list[h], hlist) - dev_close(vxlan->dev); + list_for_each_entry(vxlan, &vn->vxlan_list, next) + dev_close(vxlan->dev); rtnl_unlock(); - - if (vn->sock) { - sk_release_kernel(vn->sock->sk); - vn->sock = NULL; - } } static struct pernet_operations vxlan_net_ops = { @@ -1668,6 +1821,10 @@ 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); @@ -1683,14 +1840,16 @@ static int __init vxlan_init_module(void) out2: unregister_pernet_device(&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); + rtnl_link_unregister(&vxlan_link_ops); + destroy_workqueue(vxlan_wq); rcu_barrier(); } module_exit(vxlan_cleanup_module);