From ace9429bb58fd418f0c81d4c2835699bddf6bde6 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Thu, 11 Apr 2024 10:27:49 +0200 Subject: Adding upstream version 6.6.15. Signed-off-by: Daniel Baumann --- drivers/net/vxlan/Makefile | 7 + drivers/net/vxlan/vxlan_core.c | 4827 +++++++++++++++++++++++++++++++++++ drivers/net/vxlan/vxlan_mdb.c | 1462 +++++++++++ drivers/net/vxlan/vxlan_multicast.c | 272 ++ drivers/net/vxlan/vxlan_private.h | 246 ++ drivers/net/vxlan/vxlan_vnifilter.c | 1010 ++++++++ 6 files changed, 7824 insertions(+) create mode 100644 drivers/net/vxlan/Makefile create mode 100644 drivers/net/vxlan/vxlan_core.c create mode 100644 drivers/net/vxlan/vxlan_mdb.c create mode 100644 drivers/net/vxlan/vxlan_multicast.c create mode 100644 drivers/net/vxlan/vxlan_private.h create mode 100644 drivers/net/vxlan/vxlan_vnifilter.c (limited to 'drivers/net/vxlan') diff --git a/drivers/net/vxlan/Makefile b/drivers/net/vxlan/Makefile new file mode 100644 index 0000000000..91b8fec8b6 --- /dev/null +++ b/drivers/net/vxlan/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the vxlan driver +# + +obj-$(CONFIG_VXLAN) += vxlan.o + +vxlan-objs := vxlan_core.o vxlan_multicast.o vxlan_vnifilter.o vxlan_mdb.o diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c new file mode 100644 index 0000000000..5b5597073b --- /dev/null +++ b/drivers/net/vxlan/vxlan_core.c @@ -0,0 +1,4827 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VXLAN: Virtual eXtensible Local Area Network + * + * Copyright (c) 2012-2013 Vyatta Inc. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if IS_ENABLED(CONFIG_IPV6) +#include +#include +#endif + +#include "vxlan_private.h" + +#define VXLAN_VERSION "0.1" + +#define FDB_AGE_DEFAULT 300 /* 5 min */ +#define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */ + +/* UDP port for VXLAN traffic. + * The IANA assigned port is 4789, but the Linux default is 8472 + * for compatibility with early adopters. + */ +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"); + +unsigned int vxlan_net_id; + +const u8 all_zeros_mac[ETH_ALEN + 2]; +static struct rtnl_link_ops vxlan_link_ops; + +static int vxlan_sock_add(struct vxlan_dev *vxlan); + +static void vxlan_vs_del_dev(struct vxlan_dev *vxlan); + +/* salt for hash table */ +static u32 vxlan_salt __read_mostly; + +static inline bool vxlan_collect_metadata(struct vxlan_sock *vs) +{ + return vs->flags & VXLAN_F_COLLECT_METADATA || + ip_tunnel_collect_metadata(); +} + +/* Find VXLAN socket based on network namespace, address family, UDP port, + * enabled unshareable flags and socket device binding (see l3mdev with + * non-default VRF). + */ +static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family, + __be16 port, u32 flags, int ifindex) +{ + struct vxlan_sock *vs; + + flags &= VXLAN_F_RCV_FLAGS; + + hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { + if (inet_sk(vs->sock->sk)->inet_sport == port && + vxlan_get_sk_family(vs) == family && + vs->flags == flags && + vs->sock->sk->sk_bound_dev_if == ifindex) + return vs; + } + return NULL; +} + +static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, + int ifindex, __be32 vni, + struct vxlan_vni_node **vninode) +{ + struct vxlan_vni_node *vnode; + struct vxlan_dev_node *node; + + /* For flow based devices, map all packets to VNI 0 */ + if (vs->flags & VXLAN_F_COLLECT_METADATA && + !(vs->flags & VXLAN_F_VNIFILTER)) + vni = 0; + + hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) { + if (!node->vxlan) + continue; + vnode = NULL; + if (node->vxlan->cfg.flags & VXLAN_F_VNIFILTER) { + vnode = vxlan_vnifilter_lookup(node->vxlan, vni); + if (!vnode) + continue; + } else if (node->vxlan->default_dst.remote_vni != vni) { + continue; + } + + if (IS_ENABLED(CONFIG_IPV6)) { + const struct vxlan_config *cfg = &node->vxlan->cfg; + + if ((cfg->flags & VXLAN_F_IPV6_LINKLOCAL) && + cfg->remote_ifindex != ifindex) + continue; + } + + if (vninode) + *vninode = vnode; + return node->vxlan; + } + + return NULL; +} + +/* Look up VNI in a per net namespace table */ +static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex, + __be32 vni, sa_family_t family, + __be16 port, u32 flags) +{ + struct vxlan_sock *vs; + + vs = vxlan_find_sock(net, family, port, flags, ifindex); + if (!vs) + return NULL; + + return vxlan_vs_find_vni(vs, ifindex, vni, NULL); +} + +/* 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) +{ + unsigned long now = jiffies; + struct nda_cacheinfo ci; + bool send_ip, send_eth; + struct nlmsghdr *nlh; + struct nexthop *nh; + struct ndmsg *ndm; + int nh_family; + u32 nh_id; + + nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + memset(ndm, 0, sizeof(*ndm)); + + send_eth = send_ip = true; + + rcu_read_lock(); + nh = rcu_dereference(fdb->nh); + if (nh) { + nh_family = nexthop_get_family(nh); + nh_id = nh->id; + } + rcu_read_unlock(); + + if (type == RTM_GETNEIGH) { + if (rdst) { + send_ip = !vxlan_addr_any(&rdst->remote_ip); + ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; + } else if (nh) { + ndm->ndm_family = nh_family; + } + 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; + if (rdst && rdst->offloaded) + ndm->ndm_flags |= NTF_OFFLOADED; + ndm->ndm_type = RTN_UNICAST; + + if (!net_eq(dev_net(vxlan->dev), vxlan->net) && + nla_put_s32(skb, NDA_LINK_NETNSID, + peernet2id(dev_net(vxlan->dev), vxlan->net))) + goto nla_put_failure; + + if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr)) + goto nla_put_failure; + if (nh) { + if (nla_put_u32(skb, NDA_NH_ID, nh_id)) + goto nla_put_failure; + } else if (rdst) { + 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->cfg.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_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) + goto nla_put_failure; + if (rdst->remote_ifindex && + nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) + goto nla_put_failure; + } + + if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && + nla_put_u32(skb, NDA_SRC_VNI, + be32_to_cpu(fdb->vni))) + goto nla_put_failure; + + ci.ndm_used = jiffies_to_clock_t(now - fdb->used); + ci.ndm_confirmed = 0; + ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); + ci.ndm_refcnt = 0; + + if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return 0; + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +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(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(__s32)) /* NDA_LINK_NETNSID */ + + nla_total_size(sizeof(struct nda_cacheinfo)); +} + +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; + int err = -ENOBUFS; + + skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + 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); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); +} + +static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, + const struct vxlan_fdb *fdb, + const struct vxlan_rdst *rd, + struct netlink_ext_ack *extack, + struct switchdev_notifier_vxlan_fdb_info *fdb_info) +{ + fdb_info->info.dev = vxlan->dev; + fdb_info->info.extack = extack; + fdb_info->remote_ip = rd->remote_ip; + fdb_info->remote_port = rd->remote_port; + fdb_info->remote_vni = rd->remote_vni; + fdb_info->remote_ifindex = rd->remote_ifindex; + memcpy(fdb_info->eth_addr, fdb->eth_addr, ETH_ALEN); + fdb_info->vni = fdb->vni; + fdb_info->offloaded = rd->offloaded; + fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER; +} + +static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, + struct vxlan_fdb *fdb, + struct vxlan_rdst *rd, + bool adding, + struct netlink_ext_ack *extack) +{ + struct switchdev_notifier_vxlan_fdb_info info; + enum switchdev_notifier_type notifier_type; + int ret; + + if (WARN_ON(!rd)) + return 0; + + notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE + : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE; + vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info); + ret = call_switchdev_notifiers(notifier_type, vxlan->dev, + &info.info, extack); + return notifier_to_errno(ret); +} + +static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, + struct vxlan_rdst *rd, int type, bool swdev_notify, + struct netlink_ext_ack *extack) +{ + int err; + + if (swdev_notify && rd) { + switch (type) { + case RTM_NEWNEIGH: + err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, + true, extack); + if (err) + return err; + break; + case RTM_DELNEIGH: + vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, + false, extack); + break; + } + } + + __vxlan_fdb_notify(vxlan, fdb, rd, type); + return 0; +} + +static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_fdb f = { + .state = NUD_STALE, + }; + struct vxlan_rdst remote = { + .remote_ip = *ipa, /* goes to NDA_DST */ + .remote_vni = cpu_to_be32(VXLAN_N_VID), + }; + + vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); +} + +static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) +{ + struct vxlan_fdb f = { + .state = NUD_STALE, + }; + struct vxlan_rdst remote = { }; + + memcpy(f.eth_addr, eth_addr, ETH_ALEN); + + vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); +} + +/* Hash Ethernet address */ +static u32 eth_hash(const unsigned char *addr) +{ + u64 value = get_unaligned((u64 *)addr); + + /* only want 6 bytes */ +#ifdef __BIG_ENDIAN + value >>= 16; +#else + value <<= 16; +#endif + return hash_64(value, FDB_HASH_BITS); +} + +u32 eth_vni_hash(const unsigned char *addr, __be32 vni) +{ + /* use 1 byte of OUI and 3 bytes of NIC */ + u32 key = get_unaligned((u32 *)(addr + 2)); + + return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1); +} + +u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) +{ + if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) + return eth_vni_hash(mac, vni); + else + return eth_hash(mac); +} + +/* Hash chain to use given mac address */ +static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, + const u8 *mac, __be32 vni) +{ + return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)]; +} + +/* Look up Ethernet address in forwarding table */ +static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, + const u8 *mac, __be32 vni) +{ + struct hlist_head *head = vxlan_fdb_head(vxlan, mac, vni); + struct vxlan_fdb *f; + + hlist_for_each_entry_rcu(f, head, hlist) { + if (ether_addr_equal(mac, f->eth_addr)) { + if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { + if (vni == f->vni) + return f; + } else { + return f; + } + } + } + + return NULL; +} + +static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, + const u8 *mac, __be32 vni) +{ + struct vxlan_fdb *f; + + f = __vxlan_find_mac(vxlan, mac, vni); + if (f && f->used != jiffies) + f->used = jiffies; + + return f; +} + +/* caller should hold vxlan->hash_lock */ +static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, + union vxlan_addr *ip, __be16 port, + __be32 vni, __u32 ifindex) +{ + struct vxlan_rdst *rd; + + 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 rd; + } + + return NULL; +} + +int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, + struct switchdev_notifier_vxlan_fdb_info *fdb_info) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + u8 eth_addr[ETH_ALEN + 2] = { 0 }; + struct vxlan_rdst *rdst; + struct vxlan_fdb *f; + int rc = 0; + + if (is_multicast_ether_addr(mac) || + is_zero_ether_addr(mac)) + return -EINVAL; + + ether_addr_copy(eth_addr, mac); + + rcu_read_lock(); + + f = __vxlan_find_mac(vxlan, eth_addr, vni); + if (!f) { + rc = -ENOENT; + goto out; + } + + rdst = first_remote_rcu(f); + vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, NULL, fdb_info); + +out: + rcu_read_unlock(); + return rc; +} +EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc); + +static int vxlan_fdb_notify_one(struct notifier_block *nb, + const struct vxlan_dev *vxlan, + const struct vxlan_fdb *f, + const struct vxlan_rdst *rdst, + struct netlink_ext_ack *extack) +{ + struct switchdev_notifier_vxlan_fdb_info fdb_info; + int rc; + + vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, extack, &fdb_info); + rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, + &fdb_info); + return notifier_to_errno(rc); +} + +int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, + struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan; + struct vxlan_rdst *rdst; + struct vxlan_fdb *f; + unsigned int h; + int rc = 0; + + if (!netif_is_vxlan(dev)) + return -EINVAL; + vxlan = netdev_priv(dev); + + for (h = 0; h < FDB_HASH_SIZE; ++h) { + spin_lock_bh(&vxlan->hash_lock[h]); + hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) { + if (f->vni == vni) { + list_for_each_entry(rdst, &f->remotes, list) { + rc = vxlan_fdb_notify_one(nb, vxlan, + f, rdst, + extack); + if (rc) + goto unlock; + } + } + } + spin_unlock_bh(&vxlan->hash_lock[h]); + } + return 0; + +unlock: + spin_unlock_bh(&vxlan->hash_lock[h]); + return rc; +} +EXPORT_SYMBOL_GPL(vxlan_fdb_replay); + +void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) +{ + struct vxlan_dev *vxlan; + struct vxlan_rdst *rdst; + struct vxlan_fdb *f; + unsigned int h; + + if (!netif_is_vxlan(dev)) + return; + vxlan = netdev_priv(dev); + + for (h = 0; h < FDB_HASH_SIZE; ++h) { + spin_lock_bh(&vxlan->hash_lock[h]); + hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) + if (f->vni == vni) + list_for_each_entry(rdst, &f->remotes, list) + rdst->offloaded = false; + spin_unlock_bh(&vxlan->hash_lock[h]); + } + +} +EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload); + +/* Replace destination of unicast mac */ +static int vxlan_fdb_replace(struct vxlan_fdb *f, + union vxlan_addr *ip, __be16 port, __be32 vni, + __u32 ifindex, struct vxlan_rdst *oldrd) +{ + 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; + + *oldrd = *rd; + dst_cache_reset(&rd->dst_cache); + rd->remote_ip = *ip; + rd->remote_port = port; + rd->remote_vni = vni; + rd->remote_ifindex = ifindex; + rd->offloaded = false; + return 1; +} + +/* Add/update destinations for multicast */ +static int vxlan_fdb_append(struct vxlan_fdb *f, + union vxlan_addr *ip, __be16 port, __be32 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 -ENOMEM; + + if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { + kfree(rd); + return -ENOMEM; + } + + rd->remote_ip = *ip; + rd->remote_port = port; + rd->offloaded = false; + rd->remote_vni = vni; + rd->remote_ifindex = ifindex; + + list_add_tail_rcu(&rd->list, &f->remotes); + + *rdp = rd; + return 1; +} + +static bool vxlan_parse_gpe_proto(struct vxlanhdr *hdr, __be16 *protocol) +{ + struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)hdr; + + /* Need to have Next Protocol set for interfaces in GPE mode. */ + if (!gpe->np_applied) + return false; + /* "The initial version is 0. If a receiver does not support the + * version indicated it MUST drop the packet. + */ + if (gpe->version != 0) + return false; + /* "When the O bit is set to 1, the packet is an OAM packet and OAM + * processing MUST occur." However, we don't implement OAM + * processing, thus drop the packet. + */ + if (gpe->oam_flag) + return false; + + *protocol = tun_p_to_eth_p(gpe->next_protocol); + if (!*protocol) + return false; + + return true; +} + +static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, + unsigned int off, + struct vxlanhdr *vh, size_t hdrlen, + __be32 vni_field, + struct gro_remcsum *grc, + bool nopartial) +{ + size_t start, offset; + + if (skb->remcsum_offload) + return vh; + + if (!NAPI_GRO_CB(skb)->csum_valid) + return NULL; + + start = vxlan_rco_start(vni_field); + offset = start + vxlan_rco_offset(vni_field); + + vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen, + start, offset, grc, nopartial); + + skb->remcsum_offload = 1; + + return vh; +} + +static struct vxlanhdr *vxlan_gro_prepare_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb, + struct gro_remcsum *grc) +{ + struct sk_buff *p; + struct vxlanhdr *vh, *vh2; + unsigned int hlen, off_vx; + struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk); + __be32 flags; + + skb_gro_remcsum_init(grc); + + off_vx = skb_gro_offset(skb); + hlen = off_vx + sizeof(*vh); + vh = skb_gro_header(skb, hlen, off_vx); + if (unlikely(!vh)) + return NULL; + + skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); + + flags = vh->vx_flags; + + if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { + vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), + vh->vx_vni, grc, + !!(vs->flags & + VXLAN_F_REMCSUM_NOPARTIAL)); + + if (!vh) + return NULL; + } + + skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ + + list_for_each_entry(p, head, list) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + vh2 = (struct vxlanhdr *)(p->data + off_vx); + if (vh->vx_flags != vh2->vx_flags || + vh->vx_vni != vh2->vx_vni) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + } + + return vh; +} + +static struct sk_buff *vxlan_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + struct sk_buff *pp = NULL; + struct gro_remcsum grc; + int flush = 1; + + if (vxlan_gro_prepare_receive(sk, head, skb, &grc)) { + pp = call_gro_receive(eth_gro_receive, head, skb); + flush = 0; + } + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); + return pp; +} + +static struct sk_buff *vxlan_gpe_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + const struct packet_offload *ptype; + struct sk_buff *pp = NULL; + struct gro_remcsum grc; + struct vxlanhdr *vh; + __be16 protocol; + int flush = 1; + + vh = vxlan_gro_prepare_receive(sk, head, skb, &grc); + if (vh) { + if (!vxlan_parse_gpe_proto(vh, &protocol)) + goto out; + ptype = gro_find_receive_by_type(protocol); + if (!ptype) + goto out; + pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); + flush = 0; + } +out: + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); + return pp; +} + +static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) +{ + /* Sets 'skb->inner_mac_header' since we are always called with + * 'skb->encapsulation' set. + */ + return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); +} + +static int vxlan_gpe_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) +{ + struct vxlanhdr *vh = (struct vxlanhdr *)(skb->data + nhoff); + const struct packet_offload *ptype; + int err = -ENOSYS; + __be16 protocol; + + if (!vxlan_parse_gpe_proto(vh, &protocol)) + return err; + ptype = gro_find_complete_by_type(protocol); + if (ptype) + err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); + return err; +} + +static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac, + __u16 state, __be32 src_vni, + __u16 ndm_flags) +{ + struct vxlan_fdb *f; + + f = kmalloc(sizeof(*f), GFP_ATOMIC); + if (!f) + return NULL; + f->state = state; + f->flags = ndm_flags; + f->updated = f->used = jiffies; + f->vni = src_vni; + f->nh = NULL; + RCU_INIT_POINTER(f->vdev, vxlan); + INIT_LIST_HEAD(&f->nh_list); + INIT_LIST_HEAD(&f->remotes); + memcpy(f->eth_addr, mac, ETH_ALEN); + + return f; +} + +static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac, + __be32 src_vni, struct vxlan_fdb *f) +{ + ++vxlan->addrcnt; + hlist_add_head_rcu(&f->hlist, + vxlan_fdb_head(vxlan, mac, src_vni)); +} + +static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, + u32 nhid, struct netlink_ext_ack *extack) +{ + struct nexthop *old_nh = rtnl_dereference(fdb->nh); + struct nexthop *nh; + int err = -EINVAL; + + if (old_nh && old_nh->id == nhid) + return 0; + + nh = nexthop_find_by_id(vxlan->net, nhid); + if (!nh) { + NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); + goto err_inval; + } + + if (!nexthop_get(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + nh = NULL; + goto err_inval; + } + if (!nexthop_is_fdb(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop"); + goto err_inval; + } + + if (!nexthop_is_multipath(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop is not a multipath group"); + goto err_inval; + } + + /* check nexthop group family */ + switch (vxlan->default_dst.remote_ip.sa.sa_family) { + case AF_INET: + if (!nexthop_has_v4(nh)) { + err = -EAFNOSUPPORT; + NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); + goto err_inval; + } + break; + case AF_INET6: + if (nexthop_has_v4(nh)) { + err = -EAFNOSUPPORT; + NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); + goto err_inval; + } + } + + if (old_nh) { + list_del_rcu(&fdb->nh_list); + nexthop_put(old_nh); + } + rcu_assign_pointer(fdb->nh, nh); + list_add_tail_rcu(&fdb->nh_list, &nh->fdb_list); + return 1; + +err_inval: + if (nh) + nexthop_put(nh); + return err; +} + +int vxlan_fdb_create(struct vxlan_dev *vxlan, + const u8 *mac, union vxlan_addr *ip, + __u16 state, __be16 port, __be32 src_vni, + __be32 vni, __u32 ifindex, __u16 ndm_flags, + u32 nhid, struct vxlan_fdb **fdb, + struct netlink_ext_ack *extack) +{ + struct vxlan_rdst *rd = NULL; + struct vxlan_fdb *f; + int rc; + + if (vxlan->cfg.addrmax && + vxlan->addrcnt >= vxlan->cfg.addrmax) + return -ENOSPC; + + netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); + f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); + if (!f) + return -ENOMEM; + + if (nhid) + rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); + else + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + if (rc < 0) + goto errout; + + *fdb = f; + + return 0; + +errout: + kfree(f); + return rc; +} + +static void __vxlan_fdb_free(struct vxlan_fdb *f) +{ + struct vxlan_rdst *rd, *nd; + struct nexthop *nh; + + nh = rcu_dereference_raw(f->nh); + if (nh) { + rcu_assign_pointer(f->nh, NULL); + rcu_assign_pointer(f->vdev, NULL); + nexthop_put(nh); + } + + list_for_each_entry_safe(rd, nd, &f->remotes, list) { + dst_cache_destroy(&rd->dst_cache); + kfree(rd); + } + kfree(f); +} + +static void vxlan_fdb_free(struct rcu_head *head) +{ + struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); + + __vxlan_fdb_free(f); +} + +static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, + bool do_notify, bool swdev_notify) +{ + struct vxlan_rdst *rd; + + netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); + + --vxlan->addrcnt; + if (do_notify) { + if (rcu_access_pointer(f->nh)) + vxlan_fdb_notify(vxlan, f, NULL, RTM_DELNEIGH, + swdev_notify, NULL); + else + list_for_each_entry(rd, &f->remotes, list) + vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, + swdev_notify, NULL); + } + + hlist_del_rcu(&f->hlist); + list_del_rcu(&f->nh_list); + call_rcu(&f->rcu, vxlan_fdb_free); +} + +static void vxlan_dst_free(struct rcu_head *head) +{ + struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); + + dst_cache_destroy(&rd->dst_cache); + kfree(rd); +} + +static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, + union vxlan_addr *ip, + __u16 state, __u16 flags, + __be16 port, __be32 vni, + __u32 ifindex, __u16 ndm_flags, + struct vxlan_fdb *f, u32 nhid, + bool swdev_notify, + struct netlink_ext_ack *extack) +{ + __u16 fdb_flags = (ndm_flags & ~NTF_USE); + struct vxlan_rdst *rd = NULL; + struct vxlan_rdst oldrd; + int notify = 0; + int rc = 0; + int err; + + if (nhid && !rcu_access_pointer(f->nh)) { + NL_SET_ERR_MSG(extack, + "Cannot replace an existing non nexthop fdb with a nexthop"); + return -EOPNOTSUPP; + } + + if (nhid && (flags & NLM_F_APPEND)) { + NL_SET_ERR_MSG(extack, + "Cannot append to a nexthop fdb"); + return -EOPNOTSUPP; + } + + /* Do not allow an externally learned entry to take over an entry added + * by the user. + */ + if (!(fdb_flags & NTF_EXT_LEARNED) || + !(f->flags & NTF_VXLAN_ADDED_BY_USER)) { + if (f->state != state) { + f->state = state; + f->updated = jiffies; + notify = 1; + } + if (f->flags != fdb_flags) { + f->flags = fdb_flags; + 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))) { + if (nhid) { + rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); + if (rc < 0) + return rc; + } else { + rc = vxlan_fdb_replace(f, ip, port, vni, + ifindex, &oldrd); + } + notify |= rc; + } else { + NL_SET_ERR_MSG(extack, "Cannot replace non-unicast fdb entries"); + return -EOPNOTSUPP; + } + } + if ((flags & NLM_F_APPEND) && + (is_multicast_ether_addr(f->eth_addr) || + is_zero_ether_addr(f->eth_addr))) { + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + + if (rc < 0) + return rc; + notify |= rc; + } + + if (ndm_flags & NTF_USE) + f->used = jiffies; + + if (notify) { + if (rd == NULL) + rd = first_remote_rtnl(f); + + err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH, + swdev_notify, extack); + if (err) + goto err_notify; + } + + return 0; + +err_notify: + if (nhid) + return err; + if ((flags & NLM_F_REPLACE) && rc) + *rd = oldrd; + else if ((flags & NLM_F_APPEND) && rc) { + list_del_rcu(&rd->list); + call_rcu(&rd->rcu, vxlan_dst_free); + } + return err; +} + +static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, + const u8 *mac, union vxlan_addr *ip, + __u16 state, __u16 flags, + __be16 port, __be32 src_vni, __be32 vni, + __u32 ifindex, __u16 ndm_flags, u32 nhid, + bool swdev_notify, + struct netlink_ext_ack *extack) +{ + __u16 fdb_flags = (ndm_flags & ~NTF_USE); + struct vxlan_fdb *f; + int rc; + + /* 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); + rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, + vni, ifindex, fdb_flags, nhid, &f, extack); + if (rc < 0) + return rc; + + vxlan_fdb_insert(vxlan, mac, src_vni, f); + rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, + swdev_notify, extack); + if (rc) + goto err_notify; + + return 0; + +err_notify: + vxlan_fdb_destroy(vxlan, f, false, false); + return rc; +} + +/* Add new entry to forwarding table -- assumes lock held */ +int vxlan_fdb_update(struct vxlan_dev *vxlan, + const u8 *mac, union vxlan_addr *ip, + __u16 state, __u16 flags, + __be16 port, __be32 src_vni, __be32 vni, + __u32 ifindex, __u16 ndm_flags, u32 nhid, + bool swdev_notify, + struct netlink_ext_ack *extack) +{ + struct vxlan_fdb *f; + + f = __vxlan_find_mac(vxlan, mac, src_vni); + if (f) { + if (flags & NLM_F_EXCL) { + netdev_dbg(vxlan->dev, + "lost race to create %pM\n", mac); + return -EEXIST; + } + + return vxlan_fdb_update_existing(vxlan, ip, state, flags, port, + vni, ifindex, ndm_flags, f, + nhid, swdev_notify, extack); + } else { + if (!(flags & NLM_F_CREATE)) + return -ENOENT; + + return vxlan_fdb_update_create(vxlan, mac, ip, state, flags, + port, src_vni, vni, ifindex, + ndm_flags, nhid, swdev_notify, + extack); + } +} + +static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, + struct vxlan_rdst *rd, bool swdev_notify) +{ + list_del_rcu(&rd->list); + vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); + call_rcu(&rd->rcu, vxlan_dst_free); +} + +static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, + union vxlan_addr *ip, __be16 *port, __be32 *src_vni, + __be32 *vni, u32 *ifindex, u32 *nhid, + struct netlink_ext_ack *extack) +{ + struct net *net = dev_net(vxlan->dev); + int err; + + if (tb[NDA_NH_ID] && + (tb[NDA_DST] || tb[NDA_VNI] || tb[NDA_IFINDEX] || tb[NDA_PORT])) { + NL_SET_ERR_MSG(extack, "DST, VNI, ifindex and port are mutually exclusive with NH_ID"); + return -EINVAL; + } + + if (tb[NDA_DST]) { + err = vxlan_nla_get_addr(ip, tb[NDA_DST]); + if (err) { + NL_SET_ERR_MSG(extack, "Unsupported address family"); + 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_PORT]) { + if (nla_len(tb[NDA_PORT]) != sizeof(__be16)) { + NL_SET_ERR_MSG(extack, "Invalid vxlan port"); + return -EINVAL; + } + *port = nla_get_be16(tb[NDA_PORT]); + } else { + *port = vxlan->cfg.dst_port; + } + + if (tb[NDA_VNI]) { + if (nla_len(tb[NDA_VNI]) != sizeof(u32)) { + NL_SET_ERR_MSG(extack, "Invalid vni"); + return -EINVAL; + } + *vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); + } else { + *vni = vxlan->default_dst.remote_vni; + } + + if (tb[NDA_SRC_VNI]) { + if (nla_len(tb[NDA_SRC_VNI]) != sizeof(u32)) { + NL_SET_ERR_MSG(extack, "Invalid src vni"); + return -EINVAL; + } + *src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); + } else { + *src_vni = vxlan->default_dst.remote_vni; + } + + if (tb[NDA_IFINDEX]) { + struct net_device *tdev; + + if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) { + NL_SET_ERR_MSG(extack, "Invalid ifindex"); + return -EINVAL; + } + *ifindex = nla_get_u32(tb[NDA_IFINDEX]); + tdev = __dev_get_by_index(net, *ifindex); + if (!tdev) { + NL_SET_ERR_MSG(extack, "Device not found"); + return -EADDRNOTAVAIL; + } + } else { + *ifindex = 0; + } + + if (tb[NDA_NH_ID]) + *nhid = nla_get_u32(tb[NDA_NH_ID]); + else + *nhid = 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 vid, u16 flags, + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + /* struct net *net = dev_net(vxlan->dev); */ + union vxlan_addr ip; + __be16 port; + __be32 src_vni, vni; + u32 ifindex, nhid; + u32 hash_index; + 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 || (!tb[NDA_DST] && !tb[NDA_NH_ID])) + return -EINVAL; + + err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, + &nhid, extack); + if (err) + return err; + + if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) + return -EAFNOSUPPORT; + + hash_index = fdb_head_index(vxlan, addr, src_vni); + spin_lock_bh(&vxlan->hash_lock[hash_index]); + err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, + port, src_vni, vni, ifindex, + ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, + nhid, true, extack); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + + return err; +} + +int __vxlan_fdb_delete(struct vxlan_dev *vxlan, + const unsigned char *addr, union vxlan_addr ip, + __be16 port, __be32 src_vni, __be32 vni, + u32 ifindex, bool swdev_notify) +{ + struct vxlan_rdst *rd = NULL; + struct vxlan_fdb *f; + int err = -ENOENT; + + f = vxlan_find_mac(vxlan, addr, src_vni); + if (!f) + return err; + + if (!vxlan_addr_any(&ip)) { + rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex); + if (!rd) + goto out; + } + + /* 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)) { + vxlan_fdb_dst_destroy(vxlan, f, rd, swdev_notify); + goto out; + } + + vxlan_fdb_destroy(vxlan, f, true, swdev_notify); + +out: + return 0; +} + +/* Delete entry (via netlink) */ +static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + union vxlan_addr ip; + __be32 src_vni, vni; + u32 ifindex, nhid; + u32 hash_index; + __be16 port; + int err; + + err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, + &nhid, extack); + if (err) + return err; + + hash_index = fdb_head_index(vxlan, addr, src_vni); + spin_lock_bh(&vxlan->hash_lock[hash_index]); + err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex, + true); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + + return err; +} + +/* Dump forwarding table */ +static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, + struct net_device *filter_dev, int *idx) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + unsigned int h; + int err = 0; + + for (h = 0; h < FDB_HASH_SIZE; ++h) { + struct vxlan_fdb *f; + + rcu_read_lock(); + hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { + struct vxlan_rdst *rd; + + if (rcu_access_pointer(f->nh)) { + if (*idx < cb->args[2]) + goto skip_nh; + err = vxlan_fdb_info(skb, vxlan, f, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI, NULL); + if (err < 0) { + rcu_read_unlock(); + goto out; + } +skip_nh: + *idx += 1; + continue; + } + + list_for_each_entry_rcu(rd, &f->remotes, list) { + if (*idx < cb->args[2]) + goto skip; + + 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) { + rcu_read_unlock(); + goto out; + } +skip: + *idx += 1; + } + } + rcu_read_unlock(); + } +out: + return err; +} + +static int vxlan_fdb_get(struct sk_buff *skb, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, + u16 vid, u32 portid, u32 seq, + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_fdb *f; + __be32 vni; + int err; + + if (tb[NDA_VNI]) + vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); + else + vni = vxlan->default_dst.remote_vni; + + rcu_read_lock(); + + f = __vxlan_find_mac(vxlan, addr, vni); + if (!f) { + NL_SET_ERR_MSG(extack, "Fdb entry not found"); + err = -ENOENT; + goto errout; + } + + err = vxlan_fdb_info(skb, vxlan, f, portid, seq, + RTM_NEWNEIGH, 0, first_remote_rcu(f)); +errout: + rcu_read_unlock(); + return err; +} + +/* Watch incoming packets to learn mapping between Ethernet address + * and Tunnel endpoint. + * Return true if packet is bogus and should be dropped. + */ +static bool vxlan_snoop(struct net_device *dev, + union vxlan_addr *src_ip, const u8 *src_mac, + u32 src_ifindex, __be32 vni) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_fdb *f; + u32 ifindex = 0; + +#if IS_ENABLED(CONFIG_IPV6) + if (src_ip->sa.sa_family == AF_INET6 && + (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)) + ifindex = src_ifindex; +#endif + + f = vxlan_find_mac(vxlan, src_mac, vni); + if (likely(f)) { + struct vxlan_rdst *rdst = first_remote_rcu(f); + + if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) && + rdst->remote_ifindex == ifindex)) + return false; + + /* Don't migrate static entries, drop packets */ + if (f->state & (NUD_PERMANENT | NUD_NOARP)) + return true; + + /* Don't override an fdb with nexthop with a learnt entry */ + if (rcu_access_pointer(f->nh)) + return true; + + if (net_ratelimit()) + netdev_info(dev, + "%pM migrated from %pIS to %pIS\n", + src_mac, &rdst->remote_ip.sa, &src_ip->sa); + + rdst->remote_ip = *src_ip; + f->updated = jiffies; + vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); + } else { + u32 hash_index = fdb_head_index(vxlan, src_mac, vni); + + /* learned new entry */ + spin_lock(&vxlan->hash_lock[hash_index]); + + /* close off race between vxlan_flush and incoming packets */ + if (netif_running(dev)) + vxlan_fdb_update(vxlan, src_mac, src_ip, + NUD_REACHABLE, + NLM_F_EXCL|NLM_F_CREATE, + vxlan->cfg.dst_port, + vni, + vxlan->default_dst.remote_vni, + ifindex, NTF_SELF, 0, true, NULL); + spin_unlock(&vxlan->hash_lock[hash_index]); + } + + return false; +} + +static bool __vxlan_sock_release_prep(struct vxlan_sock *vs) +{ + struct vxlan_net *vn; + + if (!vs) + return false; + if (!refcount_dec_and_test(&vs->refcnt)) + return false; + + vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); + spin_lock(&vn->sock_lock); + hlist_del_rcu(&vs->hlist); + udp_tunnel_notify_del_rx_port(vs->sock, + (vs->flags & VXLAN_F_GPE) ? + UDP_TUNNEL_TYPE_VXLAN_GPE : + UDP_TUNNEL_TYPE_VXLAN); + spin_unlock(&vn->sock_lock); + + return true; +} + +static void vxlan_sock_release(struct vxlan_dev *vxlan) +{ + struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock); +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock); + + RCU_INIT_POINTER(vxlan->vn6_sock, NULL); +#endif + + RCU_INIT_POINTER(vxlan->vn4_sock, NULL); + synchronize_net(); + + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) + vxlan_vs_del_vnigrp(vxlan); + else + vxlan_vs_del_dev(vxlan); + + if (__vxlan_sock_release_prep(sock4)) { + udp_tunnel_sock_release(sock4->sock); + kfree(sock4); + } + +#if IS_ENABLED(CONFIG_IPV6) + if (__vxlan_sock_release_prep(sock6)) { + udp_tunnel_sock_release(sock6->sock); + kfree(sock6); + } +#endif +} + +static bool vxlan_remcsum(struct vxlanhdr *unparsed, + struct sk_buff *skb, u32 vxflags) +{ + size_t start, offset; + + if (!(unparsed->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload) + goto out; + + start = vxlan_rco_start(unparsed->vx_vni); + offset = start + vxlan_rco_offset(unparsed->vx_vni); + + if (!pskb_may_pull(skb, offset + sizeof(u16))) + return false; + + skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset, + !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL)); +out: + unparsed->vx_flags &= ~VXLAN_HF_RCO; + unparsed->vx_vni &= VXLAN_VNI_MASK; + return true; +} + +static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed, + struct sk_buff *skb, u32 vxflags, + struct vxlan_metadata *md) +{ + struct vxlanhdr_gbp *gbp = (struct vxlanhdr_gbp *)unparsed; + struct metadata_dst *tun_dst; + + if (!(unparsed->vx_flags & VXLAN_HF_GBP)) + goto out; + + md->gbp = ntohs(gbp->policy_id); + + tun_dst = (struct metadata_dst *)skb_dst(skb); + if (tun_dst) { + tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT; + tun_dst->u.tun_info.options_len = sizeof(*md); + } + if (gbp->dont_learn) + md->gbp |= VXLAN_GBP_DONT_LEARN; + + if (gbp->policy_applied) + md->gbp |= VXLAN_GBP_POLICY_APPLIED; + + /* In flow-based mode, GBP is carried in dst_metadata */ + if (!(vxflags & VXLAN_F_COLLECT_METADATA)) + skb->mark = md->gbp; +out: + unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS; +} + +static bool vxlan_set_mac(struct vxlan_dev *vxlan, + struct vxlan_sock *vs, + struct sk_buff *skb, __be32 vni) +{ + union vxlan_addr saddr; + u32 ifindex = skb->dev->ifindex; + + skb_reset_mac_header(skb); + skb->protocol = eth_type_trans(skb, vxlan->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + + /* Ignore packet loops (and multicast echo) */ + if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) + return false; + + /* Get address from the outer IP header */ + if (vxlan_get_sk_family(vs) == AF_INET) { + saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; + saddr.sa.sa_family = AF_INET; +#if IS_ENABLED(CONFIG_IPV6) + } else { + saddr.sin6.sin6_addr = ipv6_hdr(skb)->saddr; + saddr.sa.sa_family = AF_INET6; +#endif + } + + if ((vxlan->cfg.flags & VXLAN_F_LEARN) && + vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, ifindex, vni)) + return false; + + return true; +} + +static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph, + struct sk_buff *skb) +{ + int err = 0; + + if (vxlan_get_sk_family(vs) == AF_INET) + err = IP_ECN_decapsulate(oiph, skb); +#if IS_ENABLED(CONFIG_IPV6) + else + err = IP6_ECN_decapsulate(oiph, skb); +#endif + + if (unlikely(err) && log_ecn_error) { + if (vxlan_get_sk_family(vs) == AF_INET) + net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", + &((struct iphdr *)oiph)->saddr, + ((struct iphdr *)oiph)->tos); + else + net_info_ratelimited("non-ECT from %pI6\n", + &((struct ipv6hdr *)oiph)->saddr); + } + return err <= 1; +} + +/* Callback from net/ipv4/udp.c to receive packets */ +static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) +{ + struct vxlan_vni_node *vninode = NULL; + struct vxlan_dev *vxlan; + struct vxlan_sock *vs; + struct vxlanhdr unparsed; + struct vxlan_metadata _md; + struct vxlan_metadata *md = &_md; + __be16 protocol = htons(ETH_P_TEB); + bool raw_proto = false; + void *oiph; + __be32 vni = 0; + + /* Need UDP and VXLAN header to be present */ + if (!pskb_may_pull(skb, VXLAN_HLEN)) + goto drop; + + unparsed = *vxlan_hdr(skb); + /* VNI flag always required to be set */ + if (!(unparsed.vx_flags & VXLAN_HF_VNI)) { + netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", + ntohl(vxlan_hdr(skb)->vx_flags), + ntohl(vxlan_hdr(skb)->vx_vni)); + /* Return non vxlan pkt */ + goto drop; + } + unparsed.vx_flags &= ~VXLAN_HF_VNI; + unparsed.vx_vni &= ~VXLAN_VNI_MASK; + + vs = rcu_dereference_sk_user_data(sk); + if (!vs) + goto drop; + + vni = vxlan_vni(vxlan_hdr(skb)->vx_vni); + + vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, &vninode); + if (!vxlan) + goto drop; + + /* For backwards compatibility, only allow reserved fields to be + * used by VXLAN extensions if explicitly requested. + */ + if (vs->flags & VXLAN_F_GPE) { + if (!vxlan_parse_gpe_proto(&unparsed, &protocol)) + goto drop; + unparsed.vx_flags &= ~VXLAN_GPE_USED_BITS; + raw_proto = true; + } + + if (__iptunnel_pull_header(skb, VXLAN_HLEN, protocol, raw_proto, + !net_eq(vxlan->net, dev_net(vxlan->dev)))) + goto drop; + + if (vs->flags & VXLAN_F_REMCSUM_RX) + if (unlikely(!vxlan_remcsum(&unparsed, skb, vs->flags))) + goto drop; + + if (vxlan_collect_metadata(vs)) { + struct metadata_dst *tun_dst; + + tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY, + key32_to_tunnel_id(vni), sizeof(*md)); + + if (!tun_dst) + goto drop; + + md = ip_tunnel_info_opts(&tun_dst->u.tun_info); + + skb_dst_set(skb, (struct dst_entry *)tun_dst); + } else { + memset(md, 0, sizeof(*md)); + } + + if (vs->flags & VXLAN_F_GBP) + vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md); + /* Note that GBP and GPE can never be active together. This is + * ensured in vxlan_dev_configure. + */ + + if (unparsed.vx_flags || unparsed.vx_vni) { + /* If there are any unprocessed flags remaining treat + * this as a malformed packet. This behavior diverges from + * VXLAN RFC (RFC7348) which stipulates that bits in reserved + * in reserved fields are to be ignored. The approach here + * maintains compatibility with previous stack code, and also + * is more robust and provides a little more security in + * adding extensions to VXLAN. + */ + goto drop; + } + + if (!raw_proto) { + if (!vxlan_set_mac(vxlan, vs, skb, vni)) + goto drop; + } else { + skb_reset_mac_header(skb); + skb->dev = vxlan->dev; + skb->pkt_type = PACKET_HOST; + } + + oiph = skb_network_header(skb); + skb_reset_network_header(skb); + + if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { + ++vxlan->dev->stats.rx_frame_errors; + ++vxlan->dev->stats.rx_errors; + vxlan_vnifilter_count(vxlan, vni, vninode, + VXLAN_VNI_STATS_RX_ERRORS, 0); + goto drop; + } + + rcu_read_lock(); + + if (unlikely(!(vxlan->dev->flags & IFF_UP))) { + rcu_read_unlock(); + dev_core_stats_rx_dropped_inc(vxlan->dev); + vxlan_vnifilter_count(vxlan, vni, vninode, + VXLAN_VNI_STATS_RX_DROPS, 0); + goto drop; + } + + dev_sw_netstats_rx_add(vxlan->dev, skb->len); + vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX, skb->len); + gro_cells_receive(&vxlan->gro_cells, skb); + + rcu_read_unlock(); + + return 0; + +drop: + /* Consume bad packet */ + kfree_skb(skb); + return 0; +} + +/* Callback from net/ipv{4,6}/udp.c to check that we have a VNI for errors */ +static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb) +{ + struct vxlan_dev *vxlan; + struct vxlan_sock *vs; + struct vxlanhdr *hdr; + __be32 vni; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + VXLAN_HLEN)) + return -EINVAL; + + hdr = vxlan_hdr(skb); + + if (!(hdr->vx_flags & VXLAN_HF_VNI)) + return -EINVAL; + + vs = rcu_dereference_sk_user_data(sk); + if (!vs) + return -ENOENT; + + vni = vxlan_vni(hdr->vx_vni); + vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, NULL); + if (!vxlan) + return -ENOENT; + + return 0; +} + +static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct arphdr *parp; + u8 *arpptr, *sha; + __be32 sip, tip; + struct neighbour *n; + + if (dev->flags & IFF_NOARP) + goto out; + + if (!pskb_may_pull(skb, arp_hdr_len(dev))) { + dev->stats.tx_dropped++; + goto out; + } + parp = arp_hdr(skb); + + if ((parp->ar_hrd != htons(ARPHRD_ETHER) && + parp->ar_hrd != htons(ARPHRD_IEEE802)) || + parp->ar_pro != htons(ETH_P_IP) || + parp->ar_op != htons(ARPOP_REQUEST) || + parp->ar_hln != dev->addr_len || + parp->ar_pln != 4) + goto out; + arpptr = (u8 *)parp + sizeof(struct arphdr); + sha = arpptr; + arpptr += dev->addr_len; /* sha */ + memcpy(&sip, arpptr, sizeof(sip)); + arpptr += sizeof(sip); + arpptr += dev->addr_len; /* tha */ + memcpy(&tip, arpptr, sizeof(tip)); + + if (ipv4_is_loopback(tip) || + ipv4_is_multicast(tip)) + goto out; + + n = neigh_lookup(&arp_tbl, &tip, dev); + + if (n) { + struct vxlan_fdb *f; + struct sk_buff *reply; + + if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { + neigh_release(n); + goto out; + } + + f = vxlan_find_mac(vxlan, n->ha, vni); + if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { + /* bridge-local neighbor */ + neigh_release(n); + goto out; + } + + reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, + n->ha, sha); + + 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; + reply->pkt_type = PACKET_HOST; + + if (netif_rx(reply) == NET_RX_DROP) { + dev->stats.rx_dropped++; + vxlan_vnifilter_count(vxlan, vni, NULL, + VXLAN_VNI_STATS_RX_DROPS, 0); + } + + } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { + union vxlan_addr ipa = { + .sin.sin_addr.s_addr = tip, + .sin.sin_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 || !pskb_may_pull(request, request->len)) + 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_reset_mac_header(reply); + + ns = (struct nd_msg *)(ipv6_hdr(request) + 1); + + daddr = eth_hdr(request)->h_source; + ns_olen = request->len - skb_network_offset(request) - + sizeof(struct ipv6hdr) - sizeof(*ns); + for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { + if (!ns->opt[i + 1]) { + kfree_skb(reply); + return NULL; + } + 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_reset_network_header(reply); + 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_reset_transport_header(reply); + + /* Neighbor Advertisement */ + na = skb_put_zero(reply, 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, __be32 vni) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + const struct in6_addr *daddr; + const struct ipv6hdr *iphdr; + struct inet6_dev *in6_dev; + struct neighbour *n; + struct nd_msg *msg; + + rcu_read_lock(); + in6_dev = __in6_dev_get(dev); + if (!in6_dev) + goto out; + + iphdr = ipv6_hdr(skb); + daddr = &iphdr->daddr; + msg = (struct nd_msg *)(iphdr + 1); + + 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 (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { + neigh_release(n); + goto out; + } + + f = vxlan_find_mac(vxlan, n->ha, vni); + 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(reply) == NET_RX_DROP) { + dev->stats.rx_dropped++; + vxlan_vnifilter_count(vxlan, vni, NULL, + VXLAN_VNI_STATS_RX_DROPS, 0); + } + } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { + union vxlan_addr ipa = { + .sin6.sin6_addr = msg->target, + .sin6.sin6_family = AF_INET6, + }; + + vxlan_ip_miss(dev, &ipa); + } + +out: + rcu_read_unlock(); + 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; + + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) + return false; + + 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->cfg.flags & VXLAN_F_L3MISS)) { + union vxlan_addr ipa = { + .sin.sin_addr.s_addr = pip->daddr, + .sin.sin_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->cfg.flags & VXLAN_F_L3MISS)) { + union vxlan_addr ipa = { + .sin6.sin6_addr = pip6->daddr, + .sin6.sin6_family = AF_INET6, + }; + + vxlan_ip_miss(dev, &ipa); + return false; + } + + break; + } +#endif + default: + return false; + } + + if (n) { + bool diff; + + 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); + memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len); + } + neigh_release(n); + return diff; + } + + return false; +} + +static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, __be16 protocol) +{ + struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh; + + gpe->np_applied = 1; + gpe->next_protocol = tun_p_from_eth_p(protocol); + if (!gpe->next_protocol) + return -EPFNOSUPPORT; + return 0; +} + +static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, + int iphdr_len, __be32 vni, + struct vxlan_metadata *md, u32 vxflags, + bool udp_sum) +{ + struct vxlanhdr *vxh; + int min_headroom; + int err; + int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; + __be16 inner_protocol = htons(ETH_P_TEB); + + if ((vxflags & VXLAN_F_REMCSUM_TX) && + skb->ip_summed == CHECKSUM_PARTIAL) { + int csum_start = skb_checksum_start_offset(skb); + + if (csum_start <= VXLAN_MAX_REMCSUM_START && + !(csum_start & VXLAN_RCO_SHIFT_MASK) && + (skb->csum_offset == offsetof(struct udphdr, check) || + skb->csum_offset == offsetof(struct tcphdr, check))) + type |= SKB_GSO_TUNNEL_REMCSUM; + } + + min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + + VXLAN_HLEN + iphdr_len; + + /* Need space for new headers (invalidates iph ptr) */ + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + return err; + + err = iptunnel_handle_offloads(skb, type); + if (err) + return err; + + vxh = __skb_push(skb, sizeof(*vxh)); + vxh->vx_flags = VXLAN_HF_VNI; + vxh->vx_vni = vxlan_vni_field(vni); + + if (type & SKB_GSO_TUNNEL_REMCSUM) { + unsigned int start; + + start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr); + vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset); + vxh->vx_flags |= VXLAN_HF_RCO; + + if (!skb_is_gso(skb)) { + skb->ip_summed = CHECKSUM_NONE; + skb->encapsulation = 0; + } + } + + if (vxflags & VXLAN_F_GBP) + vxlan_build_gbp_hdr(vxh, md); + if (vxflags & VXLAN_F_GPE) { + err = vxlan_build_gpe_hdr(vxh, skb->protocol); + if (err < 0) + return err; + inner_protocol = skb->protocol; + } + + skb_set_inner_protocol(skb, inner_protocol); + return 0; +} + +static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device *dev, + struct vxlan_sock *sock4, + struct sk_buff *skb, int oif, u8 tos, + __be32 daddr, __be32 *saddr, __be16 dport, __be16 sport, + __u8 flow_flags, struct dst_cache *dst_cache, + const struct ip_tunnel_info *info) +{ + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); + struct rtable *rt = NULL; + struct flowi4 fl4; + + if (!sock4) + return ERR_PTR(-EIO); + + if (tos && !info) + use_cache = false; + if (use_cache) { + rt = dst_cache_get_ip4(dst_cache, saddr); + if (rt) + return rt; + } + + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_oif = oif; + fl4.flowi4_tos = RT_TOS(tos); + fl4.flowi4_mark = skb->mark; + fl4.flowi4_proto = IPPROTO_UDP; + fl4.daddr = daddr; + fl4.saddr = *saddr; + fl4.fl4_dport = dport; + fl4.fl4_sport = sport; + fl4.flowi4_flags = flow_flags; + + rt = ip_route_output_key(vxlan->net, &fl4); + if (!IS_ERR(rt)) { + if (rt->dst.dev == dev) { + netdev_dbg(dev, "circular route to %pI4\n", &daddr); + ip_rt_put(rt); + return ERR_PTR(-ELOOP); + } + + *saddr = fl4.saddr; + if (use_cache) + dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); + } else { + netdev_dbg(dev, "no route to %pI4\n", &daddr); + return ERR_PTR(-ENETUNREACH); + } + return rt; +} + +#if IS_ENABLED(CONFIG_IPV6) +static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, + struct net_device *dev, + struct vxlan_sock *sock6, + struct sk_buff *skb, int oif, u8 tos, + __be32 label, + const struct in6_addr *daddr, + struct in6_addr *saddr, + __be16 dport, __be16 sport, + struct dst_cache *dst_cache, + const struct ip_tunnel_info *info) +{ + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); + struct dst_entry *ndst; + struct flowi6 fl6; + + if (!sock6) + return ERR_PTR(-EIO); + + if (tos && !info) + use_cache = false; + if (use_cache) { + ndst = dst_cache_get_ip6(dst_cache, saddr); + if (ndst) + return ndst; + } + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.daddr = *daddr; + fl6.saddr = *saddr; + fl6.flowlabel = ip6_make_flowinfo(tos, label); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = IPPROTO_UDP; + fl6.fl6_dport = dport; + fl6.fl6_sport = sport; + + ndst = ipv6_stub->ipv6_dst_lookup_flow(vxlan->net, sock6->sock->sk, + &fl6, NULL); + if (IS_ERR(ndst)) { + netdev_dbg(dev, "no route to %pI6\n", daddr); + return ERR_PTR(-ENETUNREACH); + } + + if (unlikely(ndst->dev == dev)) { + netdev_dbg(dev, "circular route to %pI6\n", daddr); + dst_release(ndst); + return ERR_PTR(-ELOOP); + } + + *saddr = fl6.saddr; + if (use_cache) + dst_cache_set_ip6(dst_cache, ndst, saddr); + return ndst; +} +#endif + +/* 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, __be32 vni, + bool snoop) +{ + union vxlan_addr loopback; + union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; + struct net_device *dev; + int len = skb->len; + + 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 + } + + rcu_read_lock(); + dev = skb->dev; + if (unlikely(!(dev->flags & IFF_UP))) { + kfree_skb(skb); + goto drop; + } + + if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) + vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); + + dev_sw_netstats_tx_add(src_vxlan->dev, 1, len); + vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); + + if (__netif_rx(skb) == NET_RX_SUCCESS) { + dev_sw_netstats_rx_add(dst_vxlan->dev, len); + vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, + len); + } else { +drop: + dev->stats.rx_dropped++; + vxlan_vnifilter_count(dst_vxlan, vni, NULL, + VXLAN_VNI_STATS_RX_DROPS, 0); + } + rcu_read_unlock(); +} + +static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, + struct vxlan_dev *vxlan, + union vxlan_addr *daddr, + __be16 dst_port, int dst_ifindex, __be32 vni, + struct dst_entry *dst, + u32 rt_flags) +{ +#if IS_ENABLED(CONFIG_IPV6) + /* IPv6 rt-flags are checked against RTF_LOCAL, but the value of + * RTF_LOCAL is equal to RTCF_LOCAL. So to keep code simple + * we can use RTCF_LOCAL which works for ipv4 and ipv6 route entry. + */ + BUILD_BUG_ON(RTCF_LOCAL != RTF_LOCAL); +#endif + /* Bypass encapsulation if the destination is local */ + if (rt_flags & RTCF_LOCAL && + !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && + vxlan->cfg.flags & VXLAN_F_LOCALBYPASS) { + struct vxlan_dev *dst_vxlan; + + dst_release(dst); + dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni, + daddr->sa.sa_family, dst_port, + vxlan->cfg.flags); + if (!dst_vxlan) { + dev->stats.tx_errors++; + vxlan_vnifilter_count(vxlan, vni, NULL, + VXLAN_VNI_STATS_TX_ERRORS, 0); + kfree_skb(skb); + + return -ENOENT; + } + vxlan_encap_bypass(skb, vxlan, dst_vxlan, vni, true); + return 1; + } + + return 0; +} + +void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, + __be32 default_vni, struct vxlan_rdst *rdst, bool did_rsc) +{ + struct dst_cache *dst_cache; + struct ip_tunnel_info *info; + struct vxlan_dev *vxlan = netdev_priv(dev); + const struct iphdr *old_iph = ip_hdr(skb); + union vxlan_addr *dst; + union vxlan_addr remote_ip, local_ip; + struct vxlan_metadata _md; + struct vxlan_metadata *md = &_md; + unsigned int pkt_len = skb->len; + __be16 src_port = 0, dst_port; + struct dst_entry *ndst = NULL; + __u8 tos, ttl, flow_flags = 0; + int ifindex; + int err; + u32 flags = vxlan->cfg.flags; + bool udp_sum = false; + bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); + __be32 vni = 0; +#if IS_ENABLED(CONFIG_IPV6) + __be32 label; +#endif + + info = skb_tunnel_info(skb); + + if (rdst) { + dst = &rdst->remote_ip; + if (vxlan_addr_any(dst)) { + if (did_rsc) { + /* short-circuited back to local bridge */ + vxlan_encap_bypass(skb, vxlan, vxlan, + default_vni, true); + return; + } + goto drop; + } + + dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; + vni = (rdst->remote_vni) ? : default_vni; + ifindex = rdst->remote_ifindex; + local_ip = vxlan->cfg.saddr; + dst_cache = &rdst->dst_cache; + md->gbp = skb->mark; + if (flags & VXLAN_F_TTL_INHERIT) { + ttl = ip_tunnel_get_ttl(old_iph, skb); + } else { + ttl = vxlan->cfg.ttl; + if (!ttl && vxlan_addr_multicast(dst)) + ttl = 1; + } + + tos = vxlan->cfg.tos; + if (tos == 1) + tos = ip_tunnel_get_dsfield(old_iph, skb); + + if (dst->sa.sa_family == AF_INET) + udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX); + else + udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); +#if IS_ENABLED(CONFIG_IPV6) + label = vxlan->cfg.label; +#endif + } else { + if (!info) { + WARN_ONCE(1, "%s: Missing encapsulation instructions\n", + dev->name); + goto drop; + } + remote_ip.sa.sa_family = ip_tunnel_info_af(info); + if (remote_ip.sa.sa_family == AF_INET) { + remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst; + local_ip.sin.sin_addr.s_addr = info->key.u.ipv4.src; + } else { + remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst; + local_ip.sin6.sin6_addr = info->key.u.ipv6.src; + } + dst = &remote_ip; + dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; + flow_flags = info->key.flow_flags; + vni = tunnel_id_to_key32(info->key.tun_id); + ifindex = 0; + dst_cache = &info->dst_cache; + if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + if (info->options_len < sizeof(*md)) + goto drop; + md = ip_tunnel_info_opts(info); + } + ttl = info->key.ttl; + tos = info->key.tos; +#if IS_ENABLED(CONFIG_IPV6) + label = info->key.label; +#endif + udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + } + src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, + vxlan->cfg.port_max, true); + + rcu_read_lock(); + if (dst->sa.sa_family == AF_INET) { + struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); + struct rtable *rt; + __be16 df = 0; + + if (!ifindex) + ifindex = sock4->sock->sk->sk_bound_dev_if; + + rt = vxlan_get_route(vxlan, dev, sock4, skb, ifindex, tos, + dst->sin.sin_addr.s_addr, + &local_ip.sin.sin_addr.s_addr, + dst_port, src_port, flow_flags, + dst_cache, info); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + goto tx_error; + } + + if (!info) { + /* Bypass encapsulation if the destination is local */ + err = encap_bypass_if_local(skb, dev, vxlan, dst, + dst_port, ifindex, vni, + &rt->dst, rt->rt_flags); + if (err) + goto out_unlock; + + if (vxlan->cfg.df == VXLAN_DF_SET) { + df = htons(IP_DF); + } else if (vxlan->cfg.df == VXLAN_DF_INHERIT) { + struct ethhdr *eth = eth_hdr(skb); + + if (ntohs(eth->h_proto) == ETH_P_IPV6 || + (ntohs(eth->h_proto) == ETH_P_IP && + old_iph->frag_off & htons(IP_DF))) + df = htons(IP_DF); + } + } else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) { + df = htons(IP_DF); + } + + ndst = &rt->dst; + err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom(flags & VXLAN_F_GPE), + netif_is_any_bridge_port(dev)); + if (err < 0) { + goto tx_error; + } else if (err) { + if (info) { + struct ip_tunnel_info *unclone; + struct in_addr src, dst; + + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) + goto tx_error; + + src = remote_ip.sin.sin_addr; + dst = local_ip.sin.sin_addr; + unclone->key.u.ipv4.src = src.s_addr; + unclone->key.u.ipv4.dst = dst.s_addr; + } + vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); + dst_release(ndst); + goto out_unlock; + } + + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); + ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); + err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), + vni, md, flags, udp_sum); + if (err < 0) + goto tx_error; + + udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, local_ip.sin.sin_addr.s_addr, + dst->sin.sin_addr.s_addr, tos, ttl, df, + src_port, dst_port, xnet, !udp_sum); +#if IS_ENABLED(CONFIG_IPV6) + } else { + struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); + + if (!ifindex) + ifindex = sock6->sock->sk->sk_bound_dev_if; + + ndst = vxlan6_get_route(vxlan, dev, sock6, skb, ifindex, tos, + label, &dst->sin6.sin6_addr, + &local_ip.sin6.sin6_addr, + dst_port, src_port, + dst_cache, info); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); + ndst = NULL; + goto tx_error; + } + + if (!info) { + u32 rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags; + + err = encap_bypass_if_local(skb, dev, vxlan, dst, + dst_port, ifindex, vni, + ndst, rt6i_flags); + if (err) + goto out_unlock; + } + + err = skb_tunnel_check_pmtu(skb, ndst, + vxlan_headroom((flags & VXLAN_F_GPE) | VXLAN_F_IPV6), + netif_is_any_bridge_port(dev)); + if (err < 0) { + goto tx_error; + } else if (err) { + if (info) { + struct ip_tunnel_info *unclone; + struct in6_addr src, dst; + + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) + goto tx_error; + + src = remote_ip.sin6.sin6_addr; + dst = local_ip.sin6.sin6_addr; + unclone->key.u.ipv6.src = src; + unclone->key.u.ipv6.dst = dst; + } + + vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); + dst_release(ndst); + goto out_unlock; + } + + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); + ttl = ttl ? : ip6_dst_hoplimit(ndst); + skb_scrub_packet(skb, xnet); + err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), + vni, md, flags, udp_sum); + if (err < 0) + goto tx_error; + + udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, + &local_ip.sin6.sin6_addr, + &dst->sin6.sin6_addr, tos, ttl, + label, src_port, dst_port, !udp_sum); +#endif + } + vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len); +out_unlock: + rcu_read_unlock(); + return; + +drop: + dev->stats.tx_dropped++; + vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); + dev_kfree_skb(skb); + return; + +tx_error: + rcu_read_unlock(); + if (err == -ELOOP) + dev->stats.collisions++; + else if (err == -ENETUNREACH) + dev->stats.tx_carrier_errors++; + dst_release(ndst); + dev->stats.tx_errors++; + vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); + kfree_skb(skb); +} + +static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, + struct vxlan_fdb *f, __be32 vni, bool did_rsc) +{ + struct vxlan_rdst nh_rdst; + struct nexthop *nh; + bool do_xmit; + u32 hash; + + memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); + hash = skb_get_hash(skb); + + rcu_read_lock(); + nh = rcu_dereference(f->nh); + if (!nh) { + rcu_read_unlock(); + goto drop; + } + do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); + rcu_read_unlock(); + + if (likely(do_xmit)) + vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc); + else + goto drop; + + return; + +drop: + dev->stats.tx_dropped++; + vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, + VXLAN_VNI_STATS_TX_DROPS, 0); + dev_kfree_skb(skb); +} + +static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, + u32 nhid, __be32 vni) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_rdst nh_rdst; + struct nexthop *nh; + bool do_xmit; + u32 hash; + + memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); + hash = skb_get_hash(skb); + + rcu_read_lock(); + nh = nexthop_find_by_id(dev_net(dev), nhid); + if (unlikely(!nh || !nexthop_is_fdb(nh) || !nexthop_is_multipath(nh))) { + rcu_read_unlock(); + goto drop; + } + do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); + rcu_read_unlock(); + + if (vxlan->cfg.saddr.sa.sa_family != nh_rdst.remote_ip.sa.sa_family) + goto drop; + + if (likely(do_xmit)) + vxlan_xmit_one(skb, dev, vni, &nh_rdst, false); + else + goto drop; + + return NETDEV_TX_OK; + +drop: + dev->stats.tx_dropped++; + vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, + VXLAN_VNI_STATS_TX_DROPS, 0); + dev_kfree_skb(skb); + return NETDEV_TX_OK; +} + +/* Transmit local packets over Vxlan + * + * Outer IP header inherits ECN and DF from inner header. + * Outer UDP destination is the VXLAN assigned port. + * source port is based on hash of flow + */ +static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_rdst *rdst, *fdst = NULL; + const struct ip_tunnel_info *info; + bool did_rsc = false; + struct vxlan_fdb *f; + struct ethhdr *eth; + __be32 vni = 0; + u32 nhid = 0; + + info = skb_tunnel_info(skb); + + skb_reset_mac_header(skb); + + if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { + if (info && info->mode & IP_TUNNEL_INFO_BRIDGE && + info->mode & IP_TUNNEL_INFO_TX) { + vni = tunnel_id_to_key32(info->key.tun_id); + nhid = info->key.nhid; + } else { + if (info && info->mode & IP_TUNNEL_INFO_TX) + vxlan_xmit_one(skb, dev, vni, NULL, false); + else + kfree_skb(skb); + return NETDEV_TX_OK; + } + } + + if (vxlan->cfg.flags & VXLAN_F_PROXY) { + eth = eth_hdr(skb); + if (ntohs(eth->h_proto) == ETH_P_ARP) + return arp_reduce(dev, skb, vni); +#if IS_ENABLED(CONFIG_IPV6) + else if (ntohs(eth->h_proto) == ETH_P_IPV6 && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1); + + if (m->icmph.icmp6_code == 0 && + m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) + return neigh_reduce(dev, skb, vni); + } +#endif + } + + if (nhid) + return vxlan_xmit_nhid(skb, dev, nhid, vni); + + if (vxlan->cfg.flags & VXLAN_F_MDB) { + struct vxlan_mdb_entry *mdb_entry; + + rcu_read_lock(); + mdb_entry = vxlan_mdb_entry_skb_get(vxlan, skb, vni); + if (mdb_entry) { + netdev_tx_t ret; + + ret = vxlan_mdb_xmit(vxlan, mdb_entry, skb); + rcu_read_unlock(); + return ret; + } + rcu_read_unlock(); + } + + eth = eth_hdr(skb); + f = vxlan_find_mac(vxlan, eth->h_dest, vni); + did_rsc = false; + + if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) && + (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, vni); + } + + if (f == NULL) { + f = vxlan_find_mac(vxlan, all_zeros_mac, vni); + if (f == NULL) { + if ((vxlan->cfg.flags & VXLAN_F_L2MISS) && + !is_multicast_ether_addr(eth->h_dest)) + vxlan_fdb_miss(vxlan, eth->h_dest); + + dev->stats.tx_dropped++; + vxlan_vnifilter_count(vxlan, vni, NULL, + VXLAN_VNI_STATS_TX_DROPS, 0); + kfree_skb(skb); + return NETDEV_TX_OK; + } + } + + if (rcu_access_pointer(f->nh)) { + vxlan_xmit_nh(skb, dev, f, + (vni ? : vxlan->default_dst.remote_vni), did_rsc); + } else { + list_for_each_entry_rcu(rdst, &f->remotes, list) { + struct sk_buff *skb1; + + if (!fdst) { + fdst = rdst; + continue; + } + skb1 = skb_clone(skb, GFP_ATOMIC); + if (skb1) + vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); + } + if (fdst) + vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); + else + kfree_skb(skb); + } + + return NETDEV_TX_OK; +} + +/* Walk the forwarding table and purge stale entries */ +static void vxlan_cleanup(struct timer_list *t) +{ + struct vxlan_dev *vxlan = from_timer(vxlan, t, age_timer); + unsigned long next_timer = jiffies + FDB_AGE_INTERVAL; + unsigned int h; + + if (!netif_running(vxlan->dev)) + return; + + for (h = 0; h < FDB_HASH_SIZE; ++h) { + struct hlist_node *p, *n; + + spin_lock(&vxlan->hash_lock[h]); + hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { + struct vxlan_fdb *f + = container_of(p, struct vxlan_fdb, hlist); + unsigned long timeout; + + if (f->state & (NUD_PERMANENT | NUD_NOARP)) + continue; + + if (f->flags & NTF_EXT_LEARNED) + continue; + + timeout = f->used + vxlan->cfg.age_interval * HZ; + if (time_before_eq(timeout, jiffies)) { + netdev_dbg(vxlan->dev, + "garbage collect %pM\n", + f->eth_addr); + f->state = NUD_STALE; + vxlan_fdb_destroy(vxlan, f, true, true); + } else if (time_before(timeout, next_timer)) + next_timer = timeout; + } + spin_unlock(&vxlan->hash_lock[h]); + } + + mod_timer(&vxlan->age_timer, next_timer); +} + +static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + + spin_lock(&vn->sock_lock); + hlist_del_init_rcu(&vxlan->hlist4.hlist); +#if IS_ENABLED(CONFIG_IPV6) + hlist_del_init_rcu(&vxlan->hlist6.hlist); +#endif + spin_unlock(&vn->sock_lock); +} + +static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan, + struct vxlan_dev_node *node) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + __be32 vni = vxlan->default_dst.remote_vni; + + node->vxlan = vxlan; + spin_lock(&vn->sock_lock); + hlist_add_head_rcu(&node->hlist, vni_head(vs, vni)); + spin_unlock(&vn->sock_lock); +} + +/* Setup stats when device is created */ +static int vxlan_init(struct net_device *dev) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + int err; + + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) + vxlan_vnigroup_init(vxlan); + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) { + err = -ENOMEM; + goto err_vnigroup_uninit; + } + + err = gro_cells_init(&vxlan->gro_cells, dev); + if (err) + goto err_free_percpu; + + err = vxlan_mdb_init(vxlan); + if (err) + goto err_gro_cells_destroy; + + return 0; + +err_gro_cells_destroy: + gro_cells_destroy(&vxlan->gro_cells); +err_free_percpu: + free_percpu(dev->tstats); +err_vnigroup_uninit: + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) + vxlan_vnigroup_uninit(vxlan); + return err; +} + +static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) +{ + struct vxlan_fdb *f; + u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, vni); + + spin_lock_bh(&vxlan->hash_lock[hash_index]); + f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); + if (f) + vxlan_fdb_destroy(vxlan, f, true, true); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); +} + +static void vxlan_uninit(struct net_device *dev) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + + vxlan_mdb_fini(vxlan); + + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) + vxlan_vnigroup_uninit(vxlan); + + gro_cells_destroy(&vxlan->gro_cells); + + vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); + + 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 ret; + + ret = vxlan_sock_add(vxlan); + if (ret < 0) + return ret; + + ret = vxlan_multicast_join(vxlan); + if (ret) { + vxlan_sock_release(vxlan); + return ret; + } + + if (vxlan->cfg.age_interval) + mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL); + + return ret; +} + +/* Purge the forwarding table */ +static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) +{ + unsigned int h; + + for (h = 0; h < FDB_HASH_SIZE; ++h) { + struct hlist_node *p, *n; + + spin_lock_bh(&vxlan->hash_lock[h]); + hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { + struct vxlan_fdb *f + = container_of(p, struct vxlan_fdb, hlist); + if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP))) + continue; + /* the all_zeros_mac entry is deleted at vxlan_uninit */ + if (is_zero_ether_addr(f->eth_addr) && + f->vni == vxlan->cfg.vni) + continue; + vxlan_fdb_destroy(vxlan, f, true, true); + } + spin_unlock_bh(&vxlan->hash_lock[h]); + } +} + +/* Cleanup timer and forwarding table on shutdown */ +static int vxlan_stop(struct net_device *dev) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + + vxlan_multicast_leave(vxlan); + + del_timer_sync(&vxlan->age_timer); + + vxlan_flush(vxlan, false); + vxlan_sock_release(vxlan); + + return 0; +} + +/* Stub, nothing needs to be done. */ +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 = __dev_get_by_index(vxlan->net, + dst->remote_ifindex); + + /* This check is different than dev->max_mtu, because it looks at + * the lowerdev->mtu, rather than the static dev->max_mtu + */ + if (lowerdev) { + int max_mtu = lowerdev->mtu - vxlan_headroom(vxlan->cfg.flags); + if (new_mtu > max_mtu) + return -EINVAL; + } + + dev->mtu = new_mtu; + return 0; +} + +static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct ip_tunnel_info *info = skb_tunnel_info(skb); + __be16 sport, dport; + + sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, + vxlan->cfg.port_max, true); + dport = info->key.tp_dst ? : vxlan->cfg.dst_port; + + if (ip_tunnel_info_af(info) == AF_INET) { + struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); + struct rtable *rt; + + rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos, + info->key.u.ipv4.dst, + &info->key.u.ipv4.src, dport, sport, + info->key.flow_flags, &info->dst_cache, + info); + if (IS_ERR(rt)) + return PTR_ERR(rt); + ip_rt_put(rt); + } else { +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); + struct dst_entry *ndst; + + ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos, + info->key.label, &info->key.u.ipv6.dst, + &info->key.u.ipv6.src, dport, sport, + &info->dst_cache, info); + if (IS_ERR(ndst)) + return PTR_ERR(ndst); + dst_release(ndst); +#else /* !CONFIG_IPV6 */ + return -EPFNOSUPPORT; +#endif + } + info->key.tp_src = sport; + info->key.tp_dst = dport; + return 0; +} + +static const struct net_device_ops vxlan_netdev_ether_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 = dev_get_tstats64, + .ndo_set_rx_mode = vxlan_set_multicast_list, + .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, + .ndo_fdb_del = vxlan_fdb_delete, + .ndo_fdb_dump = vxlan_fdb_dump, + .ndo_fdb_get = vxlan_fdb_get, + .ndo_mdb_add = vxlan_mdb_add, + .ndo_mdb_del = vxlan_mdb_del, + .ndo_mdb_dump = vxlan_mdb_dump, + .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, +}; + +static const struct net_device_ops vxlan_netdev_raw_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 = dev_get_tstats64, + .ndo_change_mtu = vxlan_change_mtu, + .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, +}; + +/* Info for udev, that this is a virtual tunnel endpoint */ +static struct device_type vxlan_type = { + .name = "vxlan", +}; + +/* Calls the ndo_udp_tunnel_add of the caller in order to + * supply the listening VXLAN udp ports. Callers are expected + * to implement the ndo_udp_tunnel_add. + */ +static void vxlan_offload_rx_ports(struct net_device *dev, bool push) +{ + struct vxlan_sock *vs; + struct net *net = dev_net(dev); + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + 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) { + unsigned short type; + + if (vs->flags & VXLAN_F_GPE) + type = UDP_TUNNEL_TYPE_VXLAN_GPE; + else + type = UDP_TUNNEL_TYPE_VXLAN; + + if (push) + udp_tunnel_push_rx_port(dev, vs->sock, type); + else + udp_tunnel_drop_rx_port(dev, vs->sock, type); + } + } + spin_unlock(&vn->sock_lock); +} + +/* Initialize the device structure. */ +static void vxlan_setup(struct net_device *dev) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + unsigned int h; + + eth_hw_addr_random(dev); + ether_setup(dev); + + dev->needs_free_netdev = true; + SET_NETDEV_DEVTYPE(dev, &vxlan_type); + + dev->features |= NETIF_F_LLTX; + dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; + dev->features |= NETIF_F_RXCSUM; + dev->features |= NETIF_F_GSO_SOFTWARE; + + dev->vlan_features = dev->features; + dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; + dev->hw_features |= NETIF_F_RXCSUM; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + netif_keep_dst(dev); + dev->priv_flags |= IFF_NO_QUEUE | IFF_CHANGE_PROTO_DOWN; + + /* MTU range: 68 - 65535 */ + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = ETH_MAX_MTU; + + INIT_LIST_HEAD(&vxlan->next); + + timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); + + vxlan->dev = dev; + + for (h = 0; h < FDB_HASH_SIZE; ++h) { + spin_lock_init(&vxlan->hash_lock[h]); + INIT_HLIST_HEAD(&vxlan->fdb_head[h]); + } +} + +static void vxlan_ether_setup(struct net_device *dev) +{ + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->netdev_ops = &vxlan_netdev_ether_ops; +} + +static void vxlan_raw_setup(struct net_device *dev) +{ + dev->header_ops = NULL; + dev->type = ARPHRD_NONE; + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->netdev_ops = &vxlan_netdev_raw_ops; +} + +static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { + [IFLA_VXLAN_UNSPEC] = { .strict_start_type = IFLA_VXLAN_LOCALBYPASS }, + [IFLA_VXLAN_ID] = { .type = NLA_U32 }, + [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, + [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, + [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, + [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(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_LABEL] = { .type = NLA_U32 }, + [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, + [IFLA_VXLAN_AGEING] = { .type = NLA_U32 }, + [IFLA_VXLAN_LIMIT] = { .type = NLA_U32 }, + [IFLA_VXLAN_PORT_RANGE] = { .len = sizeof(struct ifla_vxlan_port_range) }, + [IFLA_VXLAN_PROXY] = { .type = NLA_U8 }, + [IFLA_VXLAN_RSC] = { .type = NLA_U8 }, + [IFLA_VXLAN_L2MISS] = { .type = NLA_U8 }, + [IFLA_VXLAN_L3MISS] = { .type = NLA_U8 }, + [IFLA_VXLAN_COLLECT_METADATA] = { .type = NLA_U8 }, + [IFLA_VXLAN_PORT] = { .type = NLA_U16 }, + [IFLA_VXLAN_UDP_CSUM] = { .type = NLA_U8 }, + [IFLA_VXLAN_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, + [IFLA_VXLAN_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, + [IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 }, + [IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 }, + [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, + [IFLA_VXLAN_GPE] = { .type = NLA_FLAG, }, + [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, + [IFLA_VXLAN_TTL_INHERIT] = { .type = NLA_FLAG }, + [IFLA_VXLAN_DF] = { .type = NLA_U8 }, + [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, + [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), +}; + +static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], + "Provided link layer address is not Ethernet"); + return -EINVAL; + } + + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], + "Provided Ethernet address is not unicast"); + return -EADDRNOTAVAIL; + } + } + + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + + if (mtu < ETH_MIN_MTU || mtu > ETH_MAX_MTU) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], + "MTU must be between 68 and 65535"); + return -EINVAL; + } + } + + if (!data) { + NL_SET_ERR_MSG(extack, + "Required attributes not provided to perform the operation"); + return -EINVAL; + } + + if (data[IFLA_VXLAN_ID]) { + u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); + + if (id >= VXLAN_N_VID) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID], + "VXLAN ID must be lower than 16777216"); + return -ERANGE; + } + } + + if (data[IFLA_VXLAN_PORT_RANGE]) { + const struct ifla_vxlan_port_range *p + = nla_data(data[IFLA_VXLAN_PORT_RANGE]); + + if (ntohs(p->high) < ntohs(p->low)) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE], + "Invalid source port range"); + return -EINVAL; + } + } + + if (data[IFLA_VXLAN_DF]) { + enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]); + + if (df < 0 || df > VXLAN_DF_MAX) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF], + "Invalid DF attribute"); + return -EINVAL; + } + } + + return 0; +} + +static void vxlan_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + strscpy(drvinfo->version, VXLAN_VERSION, sizeof(drvinfo->version)); + strscpy(drvinfo->driver, "vxlan", sizeof(drvinfo->driver)); +} + +static int vxlan_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_rdst *dst = &vxlan->default_dst; + struct net_device *lowerdev = __dev_get_by_index(vxlan->net, + dst->remote_ifindex); + + if (!lowerdev) { + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->base.port = PORT_OTHER; + cmd->base.speed = SPEED_UNKNOWN; + + return 0; + } + + return __ethtool_get_link_ksettings(lowerdev, cmd); +} + +static const struct ethtool_ops vxlan_ethtool_ops = { + .get_drvinfo = vxlan_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_link_ksettings = vxlan_get_link_ksettings, +}; + +static struct socket *vxlan_create_sock(struct net *net, bool ipv6, + __be16 port, u32 flags, int ifindex) +{ + struct socket *sock; + struct udp_port_cfg udp_conf; + int err; + + memset(&udp_conf, 0, sizeof(udp_conf)); + + if (ipv6) { + udp_conf.family = AF_INET6; + udp_conf.use_udp6_rx_checksums = + !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX); + udp_conf.ipv6_v6only = 1; + } else { + udp_conf.family = AF_INET; + } + + udp_conf.local_udp_port = port; + udp_conf.bind_ifindex = ifindex; + + /* Open UDP socket */ + err = udp_sock_create(net, &udp_conf, &sock); + if (err < 0) + return ERR_PTR(err); + + udp_allow_gso(sock->sk); + return sock; +} + +/* Create new listen socket if needed */ +static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, + __be16 port, u32 flags, + int ifindex) +{ + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_sock *vs; + struct socket *sock; + unsigned int h; + struct udp_tunnel_sock_cfg tunnel_cfg; + + 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]); + + sock = vxlan_create_sock(net, ipv6, port, flags, ifindex); + if (IS_ERR(sock)) { + kfree(vs); + return ERR_CAST(sock); + } + + vs->sock = sock; + refcount_set(&vs->refcnt, 1); + vs->flags = (flags & VXLAN_F_RCV_FLAGS); + + spin_lock(&vn->sock_lock); + hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); + udp_tunnel_notify_add_rx_port(sock, + (vs->flags & VXLAN_F_GPE) ? + UDP_TUNNEL_TYPE_VXLAN_GPE : + UDP_TUNNEL_TYPE_VXLAN); + spin_unlock(&vn->sock_lock); + + /* Mark socket as an encapsulation socket. */ + memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); + tunnel_cfg.sk_user_data = vs; + tunnel_cfg.encap_type = 1; + tunnel_cfg.encap_rcv = vxlan_rcv; + tunnel_cfg.encap_err_lookup = vxlan_err_lookup; + tunnel_cfg.encap_destroy = NULL; + if (vs->flags & VXLAN_F_GPE) { + tunnel_cfg.gro_receive = vxlan_gpe_gro_receive; + tunnel_cfg.gro_complete = vxlan_gpe_gro_complete; + } else { + tunnel_cfg.gro_receive = vxlan_gro_receive; + tunnel_cfg.gro_complete = vxlan_gro_complete; + } + + setup_udp_tunnel_sock(net, sock, &tunnel_cfg); + + return vs; +} + +static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; + struct vxlan_sock *vs = NULL; + struct vxlan_dev_node *node; + int l3mdev_index = 0; + + if (vxlan->cfg.remote_ifindex) + l3mdev_index = l3mdev_master_upper_ifindex_by_index( + vxlan->net, vxlan->cfg.remote_ifindex); + + if (!vxlan->cfg.no_share) { + spin_lock(&vn->sock_lock); + vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, + vxlan->cfg.dst_port, vxlan->cfg.flags, + l3mdev_index); + if (vs && !refcount_inc_not_zero(&vs->refcnt)) { + spin_unlock(&vn->sock_lock); + return -EBUSY; + } + spin_unlock(&vn->sock_lock); + } + if (!vs) + vs = vxlan_socket_create(vxlan->net, ipv6, + vxlan->cfg.dst_port, vxlan->cfg.flags, + l3mdev_index); + if (IS_ERR(vs)) + return PTR_ERR(vs); +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6) { + rcu_assign_pointer(vxlan->vn6_sock, vs); + node = &vxlan->hlist6; + } else +#endif + { + rcu_assign_pointer(vxlan->vn4_sock, vs); + node = &vxlan->hlist4; + } + + if (metadata && (vxlan->cfg.flags & VXLAN_F_VNIFILTER)) + vxlan_vs_add_vnigrp(vxlan, vs, ipv6); + else + vxlan_vs_add_dev(vs, vxlan, node); + + return 0; +} + +static int vxlan_sock_add(struct vxlan_dev *vxlan) +{ + bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; + bool ipv6 = vxlan->cfg.flags & VXLAN_F_IPV6 || metadata; + bool ipv4 = !ipv6 || metadata; + int ret = 0; + + RCU_INIT_POINTER(vxlan->vn4_sock, NULL); +#if IS_ENABLED(CONFIG_IPV6) + RCU_INIT_POINTER(vxlan->vn6_sock, NULL); + if (ipv6) { + ret = __vxlan_sock_add(vxlan, true); + if (ret < 0 && ret != -EAFNOSUPPORT) + ipv4 = false; + } +#endif + if (ipv4) + ret = __vxlan_sock_add(vxlan, false); + if (ret < 0) + vxlan_sock_release(vxlan); + return ret; +} + +int vxlan_vni_in_use(struct net *src_net, struct vxlan_dev *vxlan, + struct vxlan_config *conf, __be32 vni) +{ + struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); + struct vxlan_dev *tmp; + + list_for_each_entry(tmp, &vn->vxlan_list, next) { + if (tmp == vxlan) + continue; + if (tmp->cfg.flags & VXLAN_F_VNIFILTER) { + if (!vxlan_vnifilter_lookup(tmp, vni)) + continue; + } else if (tmp->cfg.vni != vni) { + continue; + } + if (tmp->cfg.dst_port != conf->dst_port) + continue; + if ((tmp->cfg.flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6)) != + (conf->flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6))) + continue; + + if ((conf->flags & VXLAN_F_IPV6_LINKLOCAL) && + tmp->cfg.remote_ifindex != conf->remote_ifindex) + continue; + + return -EEXIST; + } + + return 0; +} + +static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, + struct net_device **lower, + struct vxlan_dev *old, + struct netlink_ext_ack *extack) +{ + bool use_ipv6 = false; + + if (conf->flags & VXLAN_F_GPE) { + /* For now, allow GPE only together with + * COLLECT_METADATA. This can be relaxed later; in such + * case, the other side of the PtP link will have to be + * provided. + */ + if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) || + !(conf->flags & VXLAN_F_COLLECT_METADATA)) { + NL_SET_ERR_MSG(extack, + "VXLAN GPE does not support this combination of attributes"); + return -EINVAL; + } + } + + if (!conf->remote_ip.sa.sa_family && !conf->saddr.sa.sa_family) { + /* Unless IPv6 is explicitly requested, assume IPv4 */ + conf->remote_ip.sa.sa_family = AF_INET; + conf->saddr.sa.sa_family = AF_INET; + } else if (!conf->remote_ip.sa.sa_family) { + conf->remote_ip.sa.sa_family = conf->saddr.sa.sa_family; + } else if (!conf->saddr.sa.sa_family) { + conf->saddr.sa.sa_family = conf->remote_ip.sa.sa_family; + } + + if (conf->saddr.sa.sa_family != conf->remote_ip.sa.sa_family) { + NL_SET_ERR_MSG(extack, + "Local and remote address must be from the same family"); + return -EINVAL; + } + + if (vxlan_addr_multicast(&conf->saddr)) { + NL_SET_ERR_MSG(extack, "Local address cannot be multicast"); + return -EINVAL; + } + + if (conf->saddr.sa.sa_family == AF_INET6) { + if (!IS_ENABLED(CONFIG_IPV6)) { + NL_SET_ERR_MSG(extack, + "IPv6 support not enabled in the kernel"); + return -EPFNOSUPPORT; + } + use_ipv6 = true; + conf->flags |= VXLAN_F_IPV6; + + if (!(conf->flags & VXLAN_F_COLLECT_METADATA)) { + int local_type = + ipv6_addr_type(&conf->saddr.sin6.sin6_addr); + int remote_type = + ipv6_addr_type(&conf->remote_ip.sin6.sin6_addr); + + if (local_type & IPV6_ADDR_LINKLOCAL) { + if (!(remote_type & IPV6_ADDR_LINKLOCAL) && + (remote_type != IPV6_ADDR_ANY)) { + NL_SET_ERR_MSG(extack, + "Invalid combination of local and remote address scopes"); + return -EINVAL; + } + + conf->flags |= VXLAN_F_IPV6_LINKLOCAL; + } else { + if (remote_type == + (IPV6_ADDR_UNICAST | IPV6_ADDR_LINKLOCAL)) { + NL_SET_ERR_MSG(extack, + "Invalid combination of local and remote address scopes"); + return -EINVAL; + } + + conf->flags &= ~VXLAN_F_IPV6_LINKLOCAL; + } + } + } + + if (conf->label && !use_ipv6) { + NL_SET_ERR_MSG(extack, + "Label attribute only applies to IPv6 VXLAN devices"); + return -EINVAL; + } + + if (conf->remote_ifindex) { + struct net_device *lowerdev; + + lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); + if (!lowerdev) { + NL_SET_ERR_MSG(extack, + "Invalid local interface, device not found"); + return -ENODEV; + } + +#if IS_ENABLED(CONFIG_IPV6) + if (use_ipv6) { + struct inet6_dev *idev = __in6_dev_get(lowerdev); + + if (idev && idev->cnf.disable_ipv6) { + NL_SET_ERR_MSG(extack, + "IPv6 support disabled by administrator"); + return -EPERM; + } + } +#endif + + *lower = lowerdev; + } else { + if (vxlan_addr_multicast(&conf->remote_ip)) { + NL_SET_ERR_MSG(extack, + "Local interface required for multicast remote destination"); + + return -EINVAL; + } + +#if IS_ENABLED(CONFIG_IPV6) + if (conf->flags & VXLAN_F_IPV6_LINKLOCAL) { + NL_SET_ERR_MSG(extack, + "Local interface required for link-local local/remote addresses"); + return -EINVAL; + } +#endif + + *lower = NULL; + } + + if (!conf->dst_port) { + if (conf->flags & VXLAN_F_GPE) + conf->dst_port = htons(IANA_VXLAN_GPE_UDP_PORT); + else + conf->dst_port = htons(vxlan_port); + } + + if (!conf->age_interval) + conf->age_interval = FDB_AGE_DEFAULT; + + if (vxlan_vni_in_use(src_net, old, conf, conf->vni)) { + NL_SET_ERR_MSG(extack, + "A VXLAN device with the specified VNI already exists"); + return -EEXIST; + } + + return 0; +} + +static void vxlan_config_apply(struct net_device *dev, + struct vxlan_config *conf, + struct net_device *lowerdev, + struct net *src_net, + bool changelink) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_rdst *dst = &vxlan->default_dst; + unsigned short needed_headroom = ETH_HLEN; + int max_mtu = ETH_MAX_MTU; + u32 flags = conf->flags; + + if (!changelink) { + if (flags & VXLAN_F_GPE) + vxlan_raw_setup(dev); + else + vxlan_ether_setup(dev); + + if (conf->mtu) + dev->mtu = conf->mtu; + + vxlan->net = src_net; + } + + dst->remote_vni = conf->vni; + + memcpy(&dst->remote_ip, &conf->remote_ip, sizeof(conf->remote_ip)); + + if (lowerdev) { + dst->remote_ifindex = conf->remote_ifindex; + + netif_inherit_tso_max(dev, lowerdev); + + needed_headroom = lowerdev->hard_header_len; + needed_headroom += lowerdev->needed_headroom; + + dev->needed_tailroom = lowerdev->needed_tailroom; + + max_mtu = lowerdev->mtu - vxlan_headroom(flags); + if (max_mtu < ETH_MIN_MTU) + max_mtu = ETH_MIN_MTU; + + if (!changelink && !conf->mtu) + dev->mtu = max_mtu; + } + + if (dev->mtu > max_mtu) + dev->mtu = max_mtu; + + if (flags & VXLAN_F_COLLECT_METADATA) + flags |= VXLAN_F_IPV6; + needed_headroom += vxlan_headroom(flags); + dev->needed_headroom = needed_headroom; + + memcpy(&vxlan->cfg, conf, sizeof(*conf)); +} + +static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, + struct vxlan_config *conf, bool changelink, + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct net_device *lowerdev; + int ret; + + ret = vxlan_config_validate(src_net, conf, &lowerdev, vxlan, extack); + if (ret) + return ret; + + vxlan_config_apply(dev, conf, lowerdev, src_net, changelink); + + return 0; +} + +static int __vxlan_dev_create(struct net *net, struct net_device *dev, + struct vxlan_config *conf, + struct netlink_ext_ack *extack) +{ + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_dev *vxlan = netdev_priv(dev); + struct net_device *remote_dev = NULL; + struct vxlan_fdb *f = NULL; + bool unregister = false; + struct vxlan_rdst *dst; + int err; + + dst = &vxlan->default_dst; + err = vxlan_dev_configure(net, dev, conf, false, extack); + if (err) + return err; + + dev->ethtool_ops = &vxlan_ethtool_ops; + + /* create an fdb entry for a valid default destination */ + if (!vxlan_addr_any(&dst->remote_ip)) { + err = vxlan_fdb_create(vxlan, all_zeros_mac, + &dst->remote_ip, + NUD_REACHABLE | NUD_PERMANENT, + vxlan->cfg.dst_port, + dst->remote_vni, + dst->remote_vni, + dst->remote_ifindex, + NTF_SELF, 0, &f, extack); + if (err) + return err; + } + + err = register_netdevice(dev); + if (err) + goto errout; + unregister = true; + + if (dst->remote_ifindex) { + remote_dev = __dev_get_by_index(net, dst->remote_ifindex); + if (!remote_dev) { + err = -ENODEV; + goto errout; + } + + err = netdev_upper_dev_link(remote_dev, dev, extack); + if (err) + goto errout; + } + + err = rtnl_configure_link(dev, NULL, 0, NULL); + if (err < 0) + goto unlink; + + if (f) { + vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f); + + /* notify default fdb entry */ + err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), + RTM_NEWNEIGH, true, extack); + if (err) { + vxlan_fdb_destroy(vxlan, f, false, false); + if (remote_dev) + netdev_upper_dev_unlink(remote_dev, dev); + goto unregister; + } + } + + list_add(&vxlan->next, &vn->vxlan_list); + if (remote_dev) + dst->remote_dev = remote_dev; + return 0; +unlink: + if (remote_dev) + netdev_upper_dev_unlink(remote_dev, dev); +errout: + /* unregister_netdevice() destroys the default FDB entry with deletion + * notification. But the addition notification was not sent yet, so + * destroy the entry by hand here. + */ + if (f) + __vxlan_fdb_free(f); +unregister: + if (unregister) + unregister_netdevice(dev); + return err; +} + +/* Set/clear flags based on attribute */ +static int vxlan_nl2flag(struct vxlan_config *conf, struct nlattr *tb[], + int attrtype, unsigned long mask, bool changelink, + bool changelink_supported, + struct netlink_ext_ack *extack) +{ + unsigned long flags; + + if (!tb[attrtype]) + return 0; + + if (changelink && !changelink_supported) { + vxlan_flag_attr_error(attrtype, extack); + return -EOPNOTSUPP; + } + + if (vxlan_policy[attrtype].type == NLA_FLAG) + flags = conf->flags | mask; + else if (nla_get_u8(tb[attrtype])) + flags = conf->flags | mask; + else + flags = conf->flags & ~mask; + + conf->flags = flags; + + return 0; +} + +static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], + struct net_device *dev, struct vxlan_config *conf, + bool changelink, struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + int err = 0; + + memset(conf, 0, sizeof(*conf)); + + /* if changelink operation, start with old existing cfg */ + if (changelink) + memcpy(conf, &vxlan->cfg, sizeof(*conf)); + + if (data[IFLA_VXLAN_ID]) { + __be32 vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); + + if (changelink && (vni != conf->vni)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID], "Cannot change VNI"); + return -EOPNOTSUPP; + } + conf->vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); + } + + if (data[IFLA_VXLAN_GROUP]) { + if (changelink && (conf->remote_ip.sa.sa_family != AF_INET)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP], "New group address family does not match old group"); + return -EOPNOTSUPP; + } + + conf->remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); + conf->remote_ip.sa.sa_family = AF_INET; + } else if (data[IFLA_VXLAN_GROUP6]) { + if (!IS_ENABLED(CONFIG_IPV6)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "IPv6 support not enabled in the kernel"); + return -EPFNOSUPPORT; + } + + if (changelink && (conf->remote_ip.sa.sa_family != AF_INET6)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "New group address family does not match old group"); + return -EOPNOTSUPP; + } + + conf->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]); + conf->remote_ip.sa.sa_family = AF_INET6; + } + + if (data[IFLA_VXLAN_LOCAL]) { + if (changelink && (conf->saddr.sa.sa_family != AF_INET)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL], "New local address family does not match old"); + return -EOPNOTSUPP; + } + + conf->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]); + conf->saddr.sa.sa_family = AF_INET; + } else if (data[IFLA_VXLAN_LOCAL6]) { + if (!IS_ENABLED(CONFIG_IPV6)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "IPv6 support not enabled in the kernel"); + return -EPFNOSUPPORT; + } + + if (changelink && (conf->saddr.sa.sa_family != AF_INET6)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "New local address family does not match old"); + return -EOPNOTSUPP; + } + + /* TODO: respect scope id */ + conf->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]); + conf->saddr.sa.sa_family = AF_INET6; + } + + if (data[IFLA_VXLAN_LINK]) + conf->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]); + + if (data[IFLA_VXLAN_TOS]) + conf->tos = nla_get_u8(data[IFLA_VXLAN_TOS]); + + if (data[IFLA_VXLAN_TTL]) + conf->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); + + if (data[IFLA_VXLAN_TTL_INHERIT]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_TTL_INHERIT, + VXLAN_F_TTL_INHERIT, changelink, false, + extack); + if (err) + return err; + + } + + if (data[IFLA_VXLAN_LABEL]) + conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & + IPV6_FLOWLABEL_MASK; + + if (data[IFLA_VXLAN_LEARNING]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING, + VXLAN_F_LEARN, changelink, true, + extack); + if (err) + return err; + } else if (!changelink) { + /* default to learn on a new device */ + conf->flags |= VXLAN_F_LEARN; + } + + if (data[IFLA_VXLAN_AGEING]) + conf->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]); + + if (data[IFLA_VXLAN_PROXY]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_PROXY, + VXLAN_F_PROXY, changelink, false, + extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_RSC]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_RSC, + VXLAN_F_RSC, changelink, false, + extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_L2MISS]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L2MISS, + VXLAN_F_L2MISS, changelink, false, + extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_L3MISS]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L3MISS, + VXLAN_F_L3MISS, changelink, false, + extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_LIMIT]) { + if (changelink) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LIMIT], + "Cannot change limit"); + return -EOPNOTSUPP; + } + conf->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]); + } + + if (data[IFLA_VXLAN_COLLECT_METADATA]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_COLLECT_METADATA, + VXLAN_F_COLLECT_METADATA, changelink, false, + extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_PORT_RANGE]) { + if (!changelink) { + const struct ifla_vxlan_port_range *p + = nla_data(data[IFLA_VXLAN_PORT_RANGE]); + conf->port_min = ntohs(p->low); + conf->port_max = ntohs(p->high); + } else { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE], + "Cannot change port range"); + return -EOPNOTSUPP; + } + } + + if (data[IFLA_VXLAN_PORT]) { + if (changelink) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT], + "Cannot change port"); + return -EOPNOTSUPP; + } + conf->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); + } + + if (data[IFLA_VXLAN_UDP_CSUM]) { + if (changelink) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_UDP_CSUM], + "Cannot change UDP_CSUM flag"); + return -EOPNOTSUPP; + } + if (!nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) + conf->flags |= VXLAN_F_UDP_ZERO_CSUM_TX; + } + + if (data[IFLA_VXLAN_LOCALBYPASS]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LOCALBYPASS, + VXLAN_F_LOCALBYPASS, changelink, + true, extack); + if (err) + return err; + } else if (!changelink) { + /* default to local bypass on a new device */ + conf->flags |= VXLAN_F_LOCALBYPASS; + } + + if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + VXLAN_F_UDP_ZERO_CSUM6_TX, changelink, + false, extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + VXLAN_F_UDP_ZERO_CSUM6_RX, changelink, + false, extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_REMCSUM_TX]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_TX, + VXLAN_F_REMCSUM_TX, changelink, false, + extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_REMCSUM_RX]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_RX, + VXLAN_F_REMCSUM_RX, changelink, false, + extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_GBP]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GBP, + VXLAN_F_GBP, changelink, false, extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_GPE]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GPE, + VXLAN_F_GPE, changelink, false, + extack); + if (err) + return err; + } + + if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_NOPARTIAL, + VXLAN_F_REMCSUM_NOPARTIAL, changelink, + false, extack); + if (err) + return err; + } + + if (tb[IFLA_MTU]) { + if (changelink) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], + "Cannot change mtu"); + return -EOPNOTSUPP; + } + conf->mtu = nla_get_u32(tb[IFLA_MTU]); + } + + if (data[IFLA_VXLAN_DF]) + conf->df = nla_get_u8(data[IFLA_VXLAN_DF]); + + if (data[IFLA_VXLAN_VNIFILTER]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_VNIFILTER, + VXLAN_F_VNIFILTER, changelink, false, + extack); + if (err) + return err; + + if ((conf->flags & VXLAN_F_VNIFILTER) && + !(conf->flags & VXLAN_F_COLLECT_METADATA)) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_VNIFILTER], + "vxlan vnifilter only valid in collect metadata mode"); + return -EINVAL; + } + } + + return 0; +} + +static int vxlan_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct vxlan_config conf; + int err; + + err = vxlan_nl2conf(tb, data, dev, &conf, false, extack); + if (err) + return err; + + return __vxlan_dev_create(src_net, dev, &conf, extack); +} + +static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct net_device *lowerdev; + struct vxlan_config conf; + struct vxlan_rdst *dst; + int err; + + dst = &vxlan->default_dst; + err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); + if (err) + return err; + + err = vxlan_config_validate(vxlan->net, &conf, &lowerdev, + vxlan, extack); + if (err) + return err; + + if (dst->remote_dev == lowerdev) + lowerdev = NULL; + + err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev, + extack); + if (err) + return err; + + /* handle default dst entry */ + if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { + u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); + + spin_lock_bh(&vxlan->hash_lock[hash_index]); + if (!vxlan_addr_any(&conf.remote_ip)) { + err = vxlan_fdb_update(vxlan, all_zeros_mac, + &conf.remote_ip, + NUD_REACHABLE | NUD_PERMANENT, + NLM_F_APPEND | NLM_F_CREATE, + vxlan->cfg.dst_port, + conf.vni, conf.vni, + conf.remote_ifindex, + NTF_SELF, 0, true, extack); + if (err) { + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + netdev_adjacent_change_abort(dst->remote_dev, + lowerdev, dev); + return err; + } + } + if (!vxlan_addr_any(&dst->remote_ip)) + __vxlan_fdb_delete(vxlan, all_zeros_mac, + dst->remote_ip, + vxlan->cfg.dst_port, + dst->remote_vni, + dst->remote_vni, + dst->remote_ifindex, + true); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + + /* If vni filtering device, also update fdb entries of + * all vnis that were using default remote ip + */ + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { + err = vxlan_vnilist_update_group(vxlan, &dst->remote_ip, + &conf.remote_ip, extack); + if (err) { + netdev_adjacent_change_abort(dst->remote_dev, + lowerdev, dev); + return err; + } + } + } + + if (conf.age_interval != vxlan->cfg.age_interval) + mod_timer(&vxlan->age_timer, jiffies); + + netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); + if (lowerdev && lowerdev != dst->remote_dev) + dst->remote_dev = lowerdev; + vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); + return 0; +} + +static void vxlan_dellink(struct net_device *dev, struct list_head *head) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + + vxlan_flush(vxlan, true); + + list_del(&vxlan->next); + unregister_netdevice_queue(dev, head); + if (vxlan->default_dst.remote_dev) + netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev); +} + +static size_t vxlan_get_size(const struct net_device *dev) +{ + + return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */ + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{6} */ + nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */ + 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_TTL_INHERIT */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_DF */ + nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L2MISS */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L3MISS */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_COLLECT_METADATA */ + 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(__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 */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LOCALBYPASS */ + nla_total_size(0) + /* IFLA_VXLAN_GBP */ + nla_total_size(0) + /* IFLA_VXLAN_GPE */ + nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ + 0; +} + +static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + const struct vxlan_dev *vxlan = netdev_priv(dev); + const struct vxlan_rdst *dst = &vxlan->default_dst; + struct ifla_vxlan_port_range ports = { + .low = htons(vxlan->cfg.port_min), + .high = htons(vxlan->cfg.port_max), + }; + + if (nla_put_u32(skb, IFLA_VXLAN_ID, be32_to_cpu(dst->remote_vni))) + goto nla_put_failure; + + if (!vxlan_addr_any(&dst->remote_ip)) { + if (dst->remote_ip.sa.sa_family == AF_INET) { + if (nla_put_in_addr(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_in6_addr(skb, IFLA_VXLAN_GROUP6, + &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_addr_any(&vxlan->cfg.saddr)) { + if (vxlan->cfg.saddr.sa.sa_family == AF_INET) { + if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL, + vxlan->cfg.saddr.sin.sin_addr.s_addr)) + goto nla_put_failure; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6, + &vxlan->cfg.saddr.sin6.sin6_addr)) + goto nla_put_failure; +#endif + } + } + + if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || + nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT, + !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) || + nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || + nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) || + nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || + nla_put_u8(skb, IFLA_VXLAN_LEARNING, + !!(vxlan->cfg.flags & VXLAN_F_LEARN)) || + nla_put_u8(skb, IFLA_VXLAN_PROXY, + !!(vxlan->cfg.flags & VXLAN_F_PROXY)) || + nla_put_u8(skb, IFLA_VXLAN_RSC, + !!(vxlan->cfg.flags & VXLAN_F_RSC)) || + nla_put_u8(skb, IFLA_VXLAN_L2MISS, + !!(vxlan->cfg.flags & VXLAN_F_L2MISS)) || + nla_put_u8(skb, IFLA_VXLAN_L3MISS, + !!(vxlan->cfg.flags & VXLAN_F_L3MISS)) || + nla_put_u8(skb, IFLA_VXLAN_COLLECT_METADATA, + !!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) || + nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) || + nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || + nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || + nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, + !(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || + nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || + nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) || + nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX, + !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_TX)) || + nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX, + !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX)) || + nla_put_u8(skb, IFLA_VXLAN_LOCALBYPASS, + !!(vxlan->cfg.flags & VXLAN_F_LOCALBYPASS))) + goto nla_put_failure; + + if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) + goto nla_put_failure; + + if (vxlan->cfg.flags & VXLAN_F_GBP && + nla_put_flag(skb, IFLA_VXLAN_GBP)) + goto nla_put_failure; + + if (vxlan->cfg.flags & VXLAN_F_GPE && + nla_put_flag(skb, IFLA_VXLAN_GPE)) + goto nla_put_failure; + + if (vxlan->cfg.flags & VXLAN_F_REMCSUM_NOPARTIAL && + nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) + goto nla_put_failure; + + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER && + nla_put_u8(skb, IFLA_VXLAN_VNIFILTER, + !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static struct net *vxlan_get_link_net(const struct net_device *dev) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + + return vxlan->net; +} + +static struct rtnl_link_ops vxlan_link_ops __read_mostly = { + .kind = "vxlan", + .maxtype = IFLA_VXLAN_MAX, + .policy = vxlan_policy, + .priv_size = sizeof(struct vxlan_dev), + .setup = vxlan_setup, + .validate = vxlan_validate, + .newlink = vxlan_newlink, + .changelink = vxlan_changelink, + .dellink = vxlan_dellink, + .get_size = vxlan_get_size, + .fill_info = vxlan_fill_info, + .get_link_net = vxlan_get_link_net, +}; + +struct net_device *vxlan_dev_create(struct net *net, const char *name, + u8 name_assign_type, + struct vxlan_config *conf) +{ + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + int err; + + memset(&tb, 0, sizeof(tb)); + + dev = rtnl_create_link(net, name, name_assign_type, + &vxlan_link_ops, tb, NULL); + if (IS_ERR(dev)) + return dev; + + err = __vxlan_dev_create(net, dev, conf, NULL); + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } + + err = rtnl_configure_link(dev, NULL, 0, NULL); + if (err < 0) { + LIST_HEAD(list_kill); + + vxlan_dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + return ERR_PTR(err); + } + + return dev; +} +EXPORT_SYMBOL_GPL(vxlan_dev_create); + +static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn, + struct net_device *dev) +{ + 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); + } + + unregister_netdevice_many(&list_kill); +} + +static int vxlan_netdevice_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); + + if (event == NETDEV_UNREGISTER) + vxlan_handle_lowerdev_unregister(vn, dev); + else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) + vxlan_offload_rx_ports(dev, true); + else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) + vxlan_offload_rx_ports(dev, false); + + return NOTIFY_DONE; +} + +static struct notifier_block vxlan_notifier_block __read_mostly = { + .notifier_call = vxlan_netdevice_event, +}; + +static void +vxlan_fdb_offloaded_set(struct net_device *dev, + struct switchdev_notifier_vxlan_fdb_info *fdb_info) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_rdst *rdst; + struct vxlan_fdb *f; + u32 hash_index; + + hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); + + spin_lock_bh(&vxlan->hash_lock[hash_index]); + + f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); + if (!f) + goto out; + + rdst = vxlan_fdb_find_rdst(f, &fdb_info->remote_ip, + fdb_info->remote_port, + fdb_info->remote_vni, + fdb_info->remote_ifindex); + if (!rdst) + goto out; + + rdst->offloaded = fdb_info->offloaded; + +out: + spin_unlock_bh(&vxlan->hash_lock[hash_index]); +} + +static int +vxlan_fdb_external_learn_add(struct net_device *dev, + struct switchdev_notifier_vxlan_fdb_info *fdb_info) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct netlink_ext_ack *extack; + u32 hash_index; + int err; + + hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); + extack = switchdev_notifier_info_to_extack(&fdb_info->info); + + spin_lock_bh(&vxlan->hash_lock[hash_index]); + err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip, + NUD_REACHABLE, + NLM_F_CREATE | NLM_F_REPLACE, + fdb_info->remote_port, + fdb_info->vni, + fdb_info->remote_vni, + fdb_info->remote_ifindex, + NTF_USE | NTF_SELF | NTF_EXT_LEARNED, + 0, false, extack); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + + return err; +} + +static int +vxlan_fdb_external_learn_del(struct net_device *dev, + struct switchdev_notifier_vxlan_fdb_info *fdb_info) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_fdb *f; + u32 hash_index; + int err = 0; + + hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); + spin_lock_bh(&vxlan->hash_lock[hash_index]); + + f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); + if (!f) + err = -ENOENT; + else if (f->flags & NTF_EXT_LEARNED) + err = __vxlan_fdb_delete(vxlan, fdb_info->eth_addr, + fdb_info->remote_ip, + fdb_info->remote_port, + fdb_info->vni, + fdb_info->remote_vni, + fdb_info->remote_ifindex, + false); + + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + + return err; +} + +static int vxlan_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct switchdev_notifier_vxlan_fdb_info *fdb_info; + int err = 0; + + switch (event) { + case SWITCHDEV_VXLAN_FDB_OFFLOADED: + vxlan_fdb_offloaded_set(dev, ptr); + break; + case SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE: + fdb_info = ptr; + err = vxlan_fdb_external_learn_add(dev, fdb_info); + if (err) { + err = notifier_from_errno(err); + break; + } + fdb_info->offloaded = true; + vxlan_fdb_offloaded_set(dev, fdb_info); + break; + case SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE: + fdb_info = ptr; + err = vxlan_fdb_external_learn_del(dev, fdb_info); + if (err) { + err = notifier_from_errno(err); + break; + } + fdb_info->offloaded = false; + vxlan_fdb_offloaded_set(dev, fdb_info); + break; + } + + return err; +} + +static struct notifier_block vxlan_switchdev_notifier_block __read_mostly = { + .notifier_call = vxlan_switchdev_event, +}; + +static void vxlan_fdb_nh_flush(struct nexthop *nh) +{ + struct vxlan_fdb *fdb; + struct vxlan_dev *vxlan; + u32 hash_index; + + rcu_read_lock(); + list_for_each_entry_rcu(fdb, &nh->fdb_list, nh_list) { + vxlan = rcu_dereference(fdb->vdev); + WARN_ON(!vxlan); + hash_index = fdb_head_index(vxlan, fdb->eth_addr, + vxlan->default_dst.remote_vni); + spin_lock_bh(&vxlan->hash_lock[hash_index]); + if (!hlist_unhashed(&fdb->hlist)) + vxlan_fdb_destroy(vxlan, fdb, false, false); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + } + rcu_read_unlock(); +} + +static int vxlan_nexthop_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct nh_notifier_info *info = ptr; + struct nexthop *nh; + + if (event != NEXTHOP_EVENT_DEL) + return NOTIFY_DONE; + + nh = nexthop_find_by_id(info->net, info->id); + if (!nh) + return NOTIFY_DONE; + + vxlan_fdb_nh_flush(nh); + + return NOTIFY_DONE; +} + +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); + vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event; + + for (h = 0; h < PORT_HASH_SIZE; ++h) + INIT_HLIST_HEAD(&vn->sock_list[h]); + + return register_nexthop_notifier(net, &vn->nexthop_notifier_block, + NULL); +} + +static void vxlan_destroy_tunnels(struct net *net, struct list_head *head) +{ + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_dev *vxlan, *next; + struct net_device *dev, *aux; + + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &vxlan_link_ops) + unregister_netdevice_queue(dev, head); + + 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(vxlan->dev, head); + } + +} + +static void __net_exit vxlan_exit_batch_net(struct list_head *net_list) +{ + struct net *net; + LIST_HEAD(list); + unsigned int h; + + list_for_each_entry(net, net_list, exit_list) { + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + + unregister_nexthop_notifier(net, &vn->nexthop_notifier_block); + } + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) + vxlan_destroy_tunnels(net, &list); + + unregister_netdevice_many(&list); + rtnl_unlock(); + + list_for_each_entry(net, net_list, exit_list) { + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + + for (h = 0; h < PORT_HASH_SIZE; ++h) + WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); + } +} + +static struct pernet_operations vxlan_net_ops = { + .init = vxlan_init_net, + .exit_batch = vxlan_exit_batch_net, + .id = &vxlan_net_id, + .size = sizeof(struct vxlan_net), +}; + +static int __init vxlan_init_module(void) +{ + int rc; + + get_random_bytes(&vxlan_salt, sizeof(vxlan_salt)); + + rc = register_pernet_subsys(&vxlan_net_ops); + if (rc) + goto out1; + + rc = register_netdevice_notifier(&vxlan_notifier_block); + if (rc) + goto out2; + + rc = register_switchdev_notifier(&vxlan_switchdev_notifier_block); + if (rc) + goto out3; + + rc = rtnl_link_register(&vxlan_link_ops); + if (rc) + goto out4; + + vxlan_vnifilter_init(); + + return 0; +out4: + unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); +out3: + unregister_netdevice_notifier(&vxlan_notifier_block); +out2: + unregister_pernet_subsys(&vxlan_net_ops); +out1: + return rc; +} +late_initcall(vxlan_init_module); + +static void __exit vxlan_cleanup_module(void) +{ + vxlan_vnifilter_uninit(); + rtnl_link_unregister(&vxlan_link_ops); + unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); + unregister_netdevice_notifier(&vxlan_notifier_block); + 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 "); +MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic"); +MODULE_ALIAS_RTNL_LINK("vxlan"); diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c new file mode 100644 index 0000000000..5e04162226 --- /dev/null +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -0,0 +1,1462 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "vxlan_private.h" + +struct vxlan_mdb_entry_key { + union vxlan_addr src; + union vxlan_addr dst; + __be32 vni; +}; + +struct vxlan_mdb_entry { + struct rhash_head rhnode; + struct list_head remotes; + struct vxlan_mdb_entry_key key; + struct hlist_node mdb_node; + struct rcu_head rcu; +}; + +#define VXLAN_MDB_REMOTE_F_BLOCKED BIT(0) + +struct vxlan_mdb_remote { + struct list_head list; + struct vxlan_rdst __rcu *rd; + u8 flags; + u8 filter_mode; + u8 rt_protocol; + struct hlist_head src_list; + struct rcu_head rcu; +}; + +#define VXLAN_SGRP_F_DELETE BIT(0) + +struct vxlan_mdb_src_entry { + struct hlist_node node; + union vxlan_addr addr; + u8 flags; +}; + +struct vxlan_mdb_dump_ctx { + long reserved; + long entry_idx; + long remote_idx; +}; + +struct vxlan_mdb_config_src_entry { + union vxlan_addr addr; + struct list_head node; +}; + +struct vxlan_mdb_config { + struct vxlan_dev *vxlan; + struct vxlan_mdb_entry_key group; + struct list_head src_list; + union vxlan_addr remote_ip; + u32 remote_ifindex; + __be32 remote_vni; + __be16 remote_port; + u16 nlflags; + u8 flags; + u8 filter_mode; + u8 rt_protocol; +}; + +static const struct rhashtable_params vxlan_mdb_rht_params = { + .head_offset = offsetof(struct vxlan_mdb_entry, rhnode), + .key_offset = offsetof(struct vxlan_mdb_entry, key), + .key_len = sizeof(struct vxlan_mdb_entry_key), + .automatic_shrinking = true, +}; + +static int __vxlan_mdb_add(const struct vxlan_mdb_config *cfg, + struct netlink_ext_ack *extack); +static int __vxlan_mdb_del(const struct vxlan_mdb_config *cfg, + struct netlink_ext_ack *extack); + +static void vxlan_br_mdb_entry_fill(const struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry *mdb_entry, + const struct vxlan_mdb_remote *remote, + struct br_mdb_entry *e) +{ + const union vxlan_addr *dst = &mdb_entry->key.dst; + + memset(e, 0, sizeof(*e)); + e->ifindex = vxlan->dev->ifindex; + e->state = MDB_PERMANENT; + + if (remote->flags & VXLAN_MDB_REMOTE_F_BLOCKED) + e->flags |= MDB_FLAGS_BLOCKED; + + switch (dst->sa.sa_family) { + case AF_INET: + e->addr.u.ip4 = dst->sin.sin_addr.s_addr; + e->addr.proto = htons(ETH_P_IP); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + e->addr.u.ip6 = dst->sin6.sin6_addr; + e->addr.proto = htons(ETH_P_IPV6); + break; +#endif + } +} + +static int vxlan_mdb_entry_info_fill_srcs(struct sk_buff *skb, + const struct vxlan_mdb_remote *remote) +{ + struct vxlan_mdb_src_entry *ent; + struct nlattr *nest; + + if (hlist_empty(&remote->src_list)) + return 0; + + nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST); + if (!nest) + return -EMSGSIZE; + + hlist_for_each_entry(ent, &remote->src_list, node) { + struct nlattr *nest_ent; + + nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY); + if (!nest_ent) + goto out_cancel_err; + + if (vxlan_nla_put_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, + &ent->addr) || + nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER, 0)) + goto out_cancel_err; + + nla_nest_end(skb, nest_ent); + } + + nla_nest_end(skb, nest); + + return 0; + +out_cancel_err: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int vxlan_mdb_entry_info_fill(const struct vxlan_dev *vxlan, + struct sk_buff *skb, + const struct vxlan_mdb_entry *mdb_entry, + const struct vxlan_mdb_remote *remote) +{ + struct vxlan_rdst *rd = rtnl_dereference(remote->rd); + struct br_mdb_entry e; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY_INFO); + if (!nest) + return -EMSGSIZE; + + vxlan_br_mdb_entry_fill(vxlan, mdb_entry, remote, &e); + + if (nla_put_nohdr(skb, sizeof(e), &e) || + nla_put_u32(skb, MDBA_MDB_EATTR_TIMER, 0)) + goto nest_err; + + if (!vxlan_addr_any(&mdb_entry->key.src) && + vxlan_nla_put_addr(skb, MDBA_MDB_EATTR_SOURCE, &mdb_entry->key.src)) + goto nest_err; + + if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, remote->rt_protocol) || + nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, remote->filter_mode) || + vxlan_mdb_entry_info_fill_srcs(skb, remote) || + vxlan_nla_put_addr(skb, MDBA_MDB_EATTR_DST, &rd->remote_ip)) + goto nest_err; + + if (rd->remote_port && rd->remote_port != vxlan->cfg.dst_port && + nla_put_u16(skb, MDBA_MDB_EATTR_DST_PORT, + be16_to_cpu(rd->remote_port))) + goto nest_err; + + if (rd->remote_vni != vxlan->default_dst.remote_vni && + nla_put_u32(skb, MDBA_MDB_EATTR_VNI, be32_to_cpu(rd->remote_vni))) + goto nest_err; + + if (rd->remote_ifindex && + nla_put_u32(skb, MDBA_MDB_EATTR_IFINDEX, rd->remote_ifindex)) + goto nest_err; + + if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && + mdb_entry->key.vni && nla_put_u32(skb, MDBA_MDB_EATTR_SRC_VNI, + be32_to_cpu(mdb_entry->key.vni))) + goto nest_err; + + nla_nest_end(skb, nest); + + return 0; + +nest_err: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int vxlan_mdb_entry_fill(const struct vxlan_dev *vxlan, + struct sk_buff *skb, + struct vxlan_mdb_dump_ctx *ctx, + const struct vxlan_mdb_entry *mdb_entry) +{ + int remote_idx = 0, s_remote_idx = ctx->remote_idx; + struct vxlan_mdb_remote *remote; + struct nlattr *nest; + int err = 0; + + nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); + if (!nest) + return -EMSGSIZE; + + list_for_each_entry(remote, &mdb_entry->remotes, list) { + if (remote_idx < s_remote_idx) + goto skip; + + err = vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote); + if (err) + break; +skip: + remote_idx++; + } + + ctx->remote_idx = err ? remote_idx : 0; + nla_nest_end(skb, nest); + return err; +} + +static int vxlan_mdb_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, + struct vxlan_mdb_dump_ctx *ctx) +{ + int entry_idx = 0, s_entry_idx = ctx->entry_idx; + struct vxlan_mdb_entry *mdb_entry; + struct nlattr *nest; + int err = 0; + + nest = nla_nest_start_noflag(skb, MDBA_MDB); + if (!nest) + return -EMSGSIZE; + + hlist_for_each_entry(mdb_entry, &vxlan->mdb_list, mdb_node) { + if (entry_idx < s_entry_idx) + goto skip; + + err = vxlan_mdb_entry_fill(vxlan, skb, ctx, mdb_entry); + if (err) + break; +skip: + entry_idx++; + } + + ctx->entry_idx = err ? entry_idx : 0; + nla_nest_end(skb, nest); + return err; +} + +int vxlan_mdb_dump(struct net_device *dev, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct vxlan_mdb_dump_ctx *ctx = (void *)cb->ctx; + struct vxlan_dev *vxlan = netdev_priv(dev); + struct br_port_msg *bpm; + struct nlmsghdr *nlh; + int err; + + ASSERT_RTNL(); + + NL_ASSERT_DUMP_CTX_FITS(struct vxlan_mdb_dump_ctx); + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWMDB, sizeof(*bpm), + NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + bpm = nlmsg_data(nlh); + memset(bpm, 0, sizeof(*bpm)); + bpm->family = AF_BRIDGE; + bpm->ifindex = dev->ifindex; + + err = vxlan_mdb_fill(vxlan, skb, ctx); + + nlmsg_end(skb, nlh); + + cb->seq = vxlan->mdb_seq; + nl_dump_check_consistent(cb, nlh); + + return err; +} + +static const struct nla_policy +vxlan_mdbe_src_list_entry_pol[MDBE_SRCATTR_MAX + 1] = { + [MDBE_SRCATTR_ADDRESS] = NLA_POLICY_RANGE(NLA_BINARY, + sizeof(struct in_addr), + sizeof(struct in6_addr)), +}; + +static const struct nla_policy +vxlan_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = { + [MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_entry_pol), +}; + +static struct netlink_range_validation vni_range = { + .max = VXLAN_N_VID - 1, +}; + +static const struct nla_policy vxlan_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { + [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, + sizeof(struct in_addr), + sizeof(struct in6_addr)), + [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, + MCAST_INCLUDE), + [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_pol), + [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), + [MDBE_ATTR_DST] = NLA_POLICY_RANGE(NLA_BINARY, + sizeof(struct in_addr), + sizeof(struct in6_addr)), + [MDBE_ATTR_DST_PORT] = { .type = NLA_U16 }, + [MDBE_ATTR_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), + [MDBE_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), + [MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), +}; + +static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, + struct netlink_ext_ack *extack) +{ + switch (proto) { + case htons(ETH_P_IP): + if (nla_len(attr) != sizeof(struct in_addr)) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length"); + return false; + } + if (ipv4_is_multicast(nla_get_in_addr(attr))) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); + return false; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): { + struct in6_addr src; + + if (nla_len(attr) != sizeof(struct in6_addr)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length"); + return false; + } + src = nla_get_in6_addr(attr); + if (ipv6_addr_is_multicast(&src)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); + return false; + } + break; + } +#endif + default: + NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address"); + return false; + } + + return true; +} + +static void vxlan_mdb_config_group_set(struct vxlan_mdb_config *cfg, + const struct br_mdb_entry *entry, + const struct nlattr *source_attr) +{ + struct vxlan_mdb_entry_key *group = &cfg->group; + + switch (entry->addr.proto) { + case htons(ETH_P_IP): + group->dst.sa.sa_family = AF_INET; + group->dst.sin.sin_addr.s_addr = entry->addr.u.ip4; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + group->dst.sa.sa_family = AF_INET6; + group->dst.sin6.sin6_addr = entry->addr.u.ip6; + break; +#endif + } + + if (source_attr) + vxlan_nla_get_addr(&group->src, source_attr); +} + +static bool vxlan_mdb_is_star_g(const struct vxlan_mdb_entry_key *group) +{ + return !vxlan_addr_any(&group->dst) && vxlan_addr_any(&group->src); +} + +static bool vxlan_mdb_is_sg(const struct vxlan_mdb_entry_key *group) +{ + return !vxlan_addr_any(&group->dst) && !vxlan_addr_any(&group->src); +} + +static int vxlan_mdb_config_src_entry_init(struct vxlan_mdb_config *cfg, + __be16 proto, + const struct nlattr *src_entry, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[MDBE_SRCATTR_MAX + 1]; + struct vxlan_mdb_config_src_entry *src; + int err; + + err = nla_parse_nested(tb, MDBE_SRCATTR_MAX, src_entry, + vxlan_mdbe_src_list_entry_pol, extack); + if (err) + return err; + + if (NL_REQ_ATTR_CHECK(extack, src_entry, tb, MDBE_SRCATTR_ADDRESS)) + return -EINVAL; + + if (!vxlan_mdb_is_valid_source(tb[MDBE_SRCATTR_ADDRESS], proto, + extack)) + return -EINVAL; + + src = kzalloc(sizeof(*src), GFP_KERNEL); + if (!src) + return -ENOMEM; + + err = vxlan_nla_get_addr(&src->addr, tb[MDBE_SRCATTR_ADDRESS]); + if (err) + goto err_free_src; + + list_add_tail(&src->node, &cfg->src_list); + + return 0; + +err_free_src: + kfree(src); + return err; +} + +static void +vxlan_mdb_config_src_entry_fini(struct vxlan_mdb_config_src_entry *src) +{ + list_del(&src->node); + kfree(src); +} + +static int vxlan_mdb_config_src_list_init(struct vxlan_mdb_config *cfg, + __be16 proto, + const struct nlattr *src_list, + struct netlink_ext_ack *extack) +{ + struct vxlan_mdb_config_src_entry *src, *tmp; + struct nlattr *src_entry; + int rem, err; + + nla_for_each_nested(src_entry, src_list, rem) { + err = vxlan_mdb_config_src_entry_init(cfg, proto, src_entry, + extack); + if (err) + goto err_src_entry_init; + } + + return 0; + +err_src_entry_init: + list_for_each_entry_safe_reverse(src, tmp, &cfg->src_list, node) + vxlan_mdb_config_src_entry_fini(src); + return err; +} + +static void vxlan_mdb_config_src_list_fini(struct vxlan_mdb_config *cfg) +{ + struct vxlan_mdb_config_src_entry *src, *tmp; + + list_for_each_entry_safe_reverse(src, tmp, &cfg->src_list, node) + vxlan_mdb_config_src_entry_fini(src); +} + +static int vxlan_mdb_config_attrs_init(struct vxlan_mdb_config *cfg, + const struct br_mdb_entry *entry, + const struct nlattr *set_attrs, + struct netlink_ext_ack *extack) +{ + struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; + int err; + + err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, set_attrs, + vxlan_mdbe_attrs_pol, extack); + if (err) + return err; + + if (NL_REQ_ATTR_CHECK(extack, set_attrs, mdbe_attrs, MDBE_ATTR_DST)) { + NL_SET_ERR_MSG_MOD(extack, "Missing remote destination IP address"); + return -EINVAL; + } + + if (mdbe_attrs[MDBE_ATTR_SOURCE] && + !vxlan_mdb_is_valid_source(mdbe_attrs[MDBE_ATTR_SOURCE], + entry->addr.proto, extack)) + return -EINVAL; + + vxlan_mdb_config_group_set(cfg, entry, mdbe_attrs[MDBE_ATTR_SOURCE]); + + /* rtnetlink code only validates that IPv4 group address is + * multicast. + */ + if (!vxlan_addr_is_multicast(&cfg->group.dst) && + !vxlan_addr_any(&cfg->group.dst)) { + NL_SET_ERR_MSG_MOD(extack, "Group address is not multicast"); + return -EINVAL; + } + + if (vxlan_addr_any(&cfg->group.dst) && + mdbe_attrs[MDBE_ATTR_SOURCE]) { + NL_SET_ERR_MSG_MOD(extack, "Source cannot be specified for the all-zeros entry"); + return -EINVAL; + } + + if (vxlan_mdb_is_sg(&cfg->group)) + cfg->filter_mode = MCAST_INCLUDE; + + if (mdbe_attrs[MDBE_ATTR_GROUP_MODE]) { + if (!vxlan_mdb_is_star_g(&cfg->group)) { + NL_SET_ERR_MSG_MOD(extack, "Filter mode can only be set for (*, G) entries"); + return -EINVAL; + } + cfg->filter_mode = nla_get_u8(mdbe_attrs[MDBE_ATTR_GROUP_MODE]); + } + + if (mdbe_attrs[MDBE_ATTR_SRC_LIST]) { + if (!vxlan_mdb_is_star_g(&cfg->group)) { + NL_SET_ERR_MSG_MOD(extack, "Source list can only be set for (*, G) entries"); + return -EINVAL; + } + if (!mdbe_attrs[MDBE_ATTR_GROUP_MODE]) { + NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set without filter mode"); + return -EINVAL; + } + err = vxlan_mdb_config_src_list_init(cfg, entry->addr.proto, + mdbe_attrs[MDBE_ATTR_SRC_LIST], + extack); + if (err) + return err; + } + + if (vxlan_mdb_is_star_g(&cfg->group) && list_empty(&cfg->src_list) && + cfg->filter_mode == MCAST_INCLUDE) { + NL_SET_ERR_MSG_MOD(extack, "Cannot add (*, G) INCLUDE with an empty source list"); + return -EINVAL; + } + + if (mdbe_attrs[MDBE_ATTR_RTPROT]) + cfg->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]); + + err = vxlan_nla_get_addr(&cfg->remote_ip, mdbe_attrs[MDBE_ATTR_DST]); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Invalid remote destination address"); + goto err_src_list_fini; + } + + if (mdbe_attrs[MDBE_ATTR_DST_PORT]) + cfg->remote_port = + cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT])); + + if (mdbe_attrs[MDBE_ATTR_VNI]) + cfg->remote_vni = + cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI])); + + if (mdbe_attrs[MDBE_ATTR_IFINDEX]) { + cfg->remote_ifindex = + nla_get_s32(mdbe_attrs[MDBE_ATTR_IFINDEX]); + if (!__dev_get_by_index(cfg->vxlan->net, cfg->remote_ifindex)) { + NL_SET_ERR_MSG_MOD(extack, "Outgoing interface not found"); + err = -EINVAL; + goto err_src_list_fini; + } + } + + if (mdbe_attrs[MDBE_ATTR_SRC_VNI]) + cfg->group.vni = + cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI])); + + return 0; + +err_src_list_fini: + vxlan_mdb_config_src_list_fini(cfg); + return err; +} + +static int vxlan_mdb_config_init(struct vxlan_mdb_config *cfg, + struct net_device *dev, struct nlattr *tb[], + u16 nlmsg_flags, + struct netlink_ext_ack *extack) +{ + struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]); + struct vxlan_dev *vxlan = netdev_priv(dev); + + memset(cfg, 0, sizeof(*cfg)); + cfg->vxlan = vxlan; + cfg->group.vni = vxlan->default_dst.remote_vni; + INIT_LIST_HEAD(&cfg->src_list); + cfg->nlflags = nlmsg_flags; + cfg->filter_mode = MCAST_EXCLUDE; + cfg->rt_protocol = RTPROT_STATIC; + cfg->remote_vni = vxlan->default_dst.remote_vni; + cfg->remote_port = vxlan->cfg.dst_port; + + if (entry->ifindex != dev->ifindex) { + NL_SET_ERR_MSG_MOD(extack, "Port net device must be the VXLAN net device"); + return -EINVAL; + } + + /* State is not part of the entry key and can be ignored on deletion + * requests. + */ + if ((nlmsg_flags & (NLM_F_CREATE | NLM_F_REPLACE)) && + entry->state != MDB_PERMANENT) { + NL_SET_ERR_MSG_MOD(extack, "MDB entry must be permanent"); + return -EINVAL; + } + + if (entry->flags) { + NL_SET_ERR_MSG_MOD(extack, "Invalid MDB entry flags"); + return -EINVAL; + } + + if (entry->vid) { + NL_SET_ERR_MSG_MOD(extack, "VID must not be specified"); + return -EINVAL; + } + + if (entry->addr.proto != htons(ETH_P_IP) && + entry->addr.proto != htons(ETH_P_IPV6)) { + NL_SET_ERR_MSG_MOD(extack, "Group address must be an IPv4 / IPv6 address"); + return -EINVAL; + } + + if (NL_REQ_ATTR_CHECK(extack, NULL, tb, MDBA_SET_ENTRY_ATTRS)) { + NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY_ATTRS attribute"); + return -EINVAL; + } + + return vxlan_mdb_config_attrs_init(cfg, entry, tb[MDBA_SET_ENTRY_ATTRS], + extack); +} + +static void vxlan_mdb_config_fini(struct vxlan_mdb_config *cfg) +{ + vxlan_mdb_config_src_list_fini(cfg); +} + +static struct vxlan_mdb_entry * +vxlan_mdb_entry_lookup(struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry_key *group) +{ + return rhashtable_lookup_fast(&vxlan->mdb_tbl, group, + vxlan_mdb_rht_params); +} + +static struct vxlan_mdb_remote * +vxlan_mdb_remote_lookup(const struct vxlan_mdb_entry *mdb_entry, + const union vxlan_addr *addr) +{ + struct vxlan_mdb_remote *remote; + + list_for_each_entry(remote, &mdb_entry->remotes, list) { + struct vxlan_rdst *rd = rtnl_dereference(remote->rd); + + if (vxlan_addr_equal(addr, &rd->remote_ip)) + return remote; + } + + return NULL; +} + +static void vxlan_mdb_rdst_free(struct rcu_head *head) +{ + struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); + + dst_cache_destroy(&rd->dst_cache); + kfree(rd); +} + +static int vxlan_mdb_remote_rdst_init(const struct vxlan_mdb_config *cfg, + struct vxlan_mdb_remote *remote) +{ + struct vxlan_rdst *rd; + int err; + + rd = kzalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return -ENOMEM; + + err = dst_cache_init(&rd->dst_cache, GFP_KERNEL); + if (err) + goto err_free_rdst; + + rd->remote_ip = cfg->remote_ip; + rd->remote_port = cfg->remote_port; + rd->remote_vni = cfg->remote_vni; + rd->remote_ifindex = cfg->remote_ifindex; + rcu_assign_pointer(remote->rd, rd); + + return 0; + +err_free_rdst: + kfree(rd); + return err; +} + +static void vxlan_mdb_remote_rdst_fini(struct vxlan_rdst *rd) +{ + call_rcu(&rd->rcu, vxlan_mdb_rdst_free); +} + +static int vxlan_mdb_remote_init(const struct vxlan_mdb_config *cfg, + struct vxlan_mdb_remote *remote) +{ + int err; + + err = vxlan_mdb_remote_rdst_init(cfg, remote); + if (err) + return err; + + remote->flags = cfg->flags; + remote->filter_mode = cfg->filter_mode; + remote->rt_protocol = cfg->rt_protocol; + INIT_HLIST_HEAD(&remote->src_list); + + return 0; +} + +static void vxlan_mdb_remote_fini(struct vxlan_dev *vxlan, + struct vxlan_mdb_remote *remote) +{ + WARN_ON_ONCE(!hlist_empty(&remote->src_list)); + vxlan_mdb_remote_rdst_fini(rtnl_dereference(remote->rd)); +} + +static struct vxlan_mdb_src_entry * +vxlan_mdb_remote_src_entry_lookup(const struct vxlan_mdb_remote *remote, + const union vxlan_addr *addr) +{ + struct vxlan_mdb_src_entry *ent; + + hlist_for_each_entry(ent, &remote->src_list, node) { + if (vxlan_addr_equal(&ent->addr, addr)) + return ent; + } + + return NULL; +} + +static struct vxlan_mdb_src_entry * +vxlan_mdb_remote_src_entry_add(struct vxlan_mdb_remote *remote, + const union vxlan_addr *addr) +{ + struct vxlan_mdb_src_entry *ent; + + ent = kzalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return NULL; + + ent->addr = *addr; + hlist_add_head(&ent->node, &remote->src_list); + + return ent; +} + +static void +vxlan_mdb_remote_src_entry_del(struct vxlan_mdb_src_entry *ent) +{ + hlist_del(&ent->node); + kfree(ent); +} + +static int +vxlan_mdb_remote_src_fwd_add(const struct vxlan_mdb_config *cfg, + const union vxlan_addr *addr, + struct netlink_ext_ack *extack) +{ + struct vxlan_mdb_config sg_cfg; + + memset(&sg_cfg, 0, sizeof(sg_cfg)); + sg_cfg.vxlan = cfg->vxlan; + sg_cfg.group.src = *addr; + sg_cfg.group.dst = cfg->group.dst; + sg_cfg.group.vni = cfg->group.vni; + INIT_LIST_HEAD(&sg_cfg.src_list); + sg_cfg.remote_ip = cfg->remote_ip; + sg_cfg.remote_ifindex = cfg->remote_ifindex; + sg_cfg.remote_vni = cfg->remote_vni; + sg_cfg.remote_port = cfg->remote_port; + sg_cfg.nlflags = cfg->nlflags; + sg_cfg.filter_mode = MCAST_INCLUDE; + if (cfg->filter_mode == MCAST_EXCLUDE) + sg_cfg.flags = VXLAN_MDB_REMOTE_F_BLOCKED; + sg_cfg.rt_protocol = cfg->rt_protocol; + + return __vxlan_mdb_add(&sg_cfg, extack); +} + +static void +vxlan_mdb_remote_src_fwd_del(struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry_key *group, + const struct vxlan_mdb_remote *remote, + const union vxlan_addr *addr) +{ + struct vxlan_rdst *rd = rtnl_dereference(remote->rd); + struct vxlan_mdb_config sg_cfg; + + memset(&sg_cfg, 0, sizeof(sg_cfg)); + sg_cfg.vxlan = vxlan; + sg_cfg.group.src = *addr; + sg_cfg.group.dst = group->dst; + sg_cfg.group.vni = group->vni; + INIT_LIST_HEAD(&sg_cfg.src_list); + sg_cfg.remote_ip = rd->remote_ip; + + __vxlan_mdb_del(&sg_cfg, NULL); +} + +static int +vxlan_mdb_remote_src_add(const struct vxlan_mdb_config *cfg, + struct vxlan_mdb_remote *remote, + const struct vxlan_mdb_config_src_entry *src, + struct netlink_ext_ack *extack) +{ + struct vxlan_mdb_src_entry *ent; + int err; + + ent = vxlan_mdb_remote_src_entry_lookup(remote, &src->addr); + if (!ent) { + ent = vxlan_mdb_remote_src_entry_add(remote, &src->addr); + if (!ent) + return -ENOMEM; + } else if (!(cfg->nlflags & NLM_F_REPLACE)) { + NL_SET_ERR_MSG_MOD(extack, "Source entry already exists"); + return -EEXIST; + } + + err = vxlan_mdb_remote_src_fwd_add(cfg, &ent->addr, extack); + if (err) + goto err_src_del; + + /* Clear flags in case source entry was marked for deletion as part of + * replace flow. + */ + ent->flags = 0; + + return 0; + +err_src_del: + vxlan_mdb_remote_src_entry_del(ent); + return err; +} + +static void vxlan_mdb_remote_src_del(struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry_key *group, + const struct vxlan_mdb_remote *remote, + struct vxlan_mdb_src_entry *ent) +{ + vxlan_mdb_remote_src_fwd_del(vxlan, group, remote, &ent->addr); + vxlan_mdb_remote_src_entry_del(ent); +} + +static int vxlan_mdb_remote_srcs_add(const struct vxlan_mdb_config *cfg, + struct vxlan_mdb_remote *remote, + struct netlink_ext_ack *extack) +{ + struct vxlan_mdb_config_src_entry *src; + struct vxlan_mdb_src_entry *ent; + struct hlist_node *tmp; + int err; + + list_for_each_entry(src, &cfg->src_list, node) { + err = vxlan_mdb_remote_src_add(cfg, remote, src, extack); + if (err) + goto err_src_del; + } + + return 0; + +err_src_del: + hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) + vxlan_mdb_remote_src_del(cfg->vxlan, &cfg->group, remote, ent); + return err; +} + +static void vxlan_mdb_remote_srcs_del(struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry_key *group, + struct vxlan_mdb_remote *remote) +{ + struct vxlan_mdb_src_entry *ent; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) + vxlan_mdb_remote_src_del(vxlan, group, remote, ent); +} + +static size_t +vxlan_mdb_nlmsg_src_list_size(const struct vxlan_mdb_entry_key *group, + const struct vxlan_mdb_remote *remote) +{ + struct vxlan_mdb_src_entry *ent; + size_t nlmsg_size; + + if (hlist_empty(&remote->src_list)) + return 0; + + /* MDBA_MDB_EATTR_SRC_LIST */ + nlmsg_size = nla_total_size(0); + + hlist_for_each_entry(ent, &remote->src_list, node) { + /* MDBA_MDB_SRCLIST_ENTRY */ + nlmsg_size += nla_total_size(0) + + /* MDBA_MDB_SRCATTR_ADDRESS */ + nla_total_size(vxlan_addr_size(&group->dst)) + + /* MDBA_MDB_SRCATTR_TIMER */ + nla_total_size(sizeof(u8)); + } + + return nlmsg_size; +} + +static size_t vxlan_mdb_nlmsg_size(const struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry *mdb_entry, + const struct vxlan_mdb_remote *remote) +{ + const struct vxlan_mdb_entry_key *group = &mdb_entry->key; + struct vxlan_rdst *rd = rtnl_dereference(remote->rd); + size_t nlmsg_size; + + nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) + + /* MDBA_MDB */ + nla_total_size(0) + + /* MDBA_MDB_ENTRY */ + nla_total_size(0) + + /* MDBA_MDB_ENTRY_INFO */ + nla_total_size(sizeof(struct br_mdb_entry)) + + /* MDBA_MDB_EATTR_TIMER */ + nla_total_size(sizeof(u32)); + /* MDBA_MDB_EATTR_SOURCE */ + if (vxlan_mdb_is_sg(group)) + nlmsg_size += nla_total_size(vxlan_addr_size(&group->dst)); + /* MDBA_MDB_EATTR_RTPROT */ + nlmsg_size += nla_total_size(sizeof(u8)); + /* MDBA_MDB_EATTR_SRC_LIST */ + nlmsg_size += vxlan_mdb_nlmsg_src_list_size(group, remote); + /* MDBA_MDB_EATTR_GROUP_MODE */ + nlmsg_size += nla_total_size(sizeof(u8)); + /* MDBA_MDB_EATTR_DST */ + nlmsg_size += nla_total_size(vxlan_addr_size(&rd->remote_ip)); + /* MDBA_MDB_EATTR_DST_PORT */ + if (rd->remote_port && rd->remote_port != vxlan->cfg.dst_port) + nlmsg_size += nla_total_size(sizeof(u16)); + /* MDBA_MDB_EATTR_VNI */ + if (rd->remote_vni != vxlan->default_dst.remote_vni) + nlmsg_size += nla_total_size(sizeof(u32)); + /* MDBA_MDB_EATTR_IFINDEX */ + if (rd->remote_ifindex) + nlmsg_size += nla_total_size(sizeof(u32)); + /* MDBA_MDB_EATTR_SRC_VNI */ + if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && group->vni) + nlmsg_size += nla_total_size(sizeof(u32)); + + return nlmsg_size; +} + +static int vxlan_mdb_nlmsg_fill(const struct vxlan_dev *vxlan, + struct sk_buff *skb, + const struct vxlan_mdb_entry *mdb_entry, + const struct vxlan_mdb_remote *remote, + int type) +{ + struct nlattr *mdb_nest, *mdb_entry_nest; + struct br_port_msg *bpm; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, 0, 0, type, sizeof(*bpm), 0); + if (!nlh) + return -EMSGSIZE; + + bpm = nlmsg_data(nlh); + memset(bpm, 0, sizeof(*bpm)); + bpm->family = AF_BRIDGE; + bpm->ifindex = vxlan->dev->ifindex; + + mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB); + if (!mdb_nest) + goto cancel; + mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); + if (!mdb_entry_nest) + goto cancel; + + if (vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote)) + goto cancel; + + nla_nest_end(skb, mdb_entry_nest); + nla_nest_end(skb, mdb_nest); + nlmsg_end(skb, nlh); + + return 0; + +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static void vxlan_mdb_remote_notify(const struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry *mdb_entry, + const struct vxlan_mdb_remote *remote, + int type) +{ + struct net *net = dev_net(vxlan->dev); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(vxlan_mdb_nlmsg_size(vxlan, mdb_entry, remote), + GFP_KERNEL); + if (!skb) + goto errout; + + err = vxlan_mdb_nlmsg_fill(vxlan, skb, mdb_entry, remote, type); + if (err) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_KERNEL); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_MDB, err); +} + +static int +vxlan_mdb_remote_srcs_replace(const struct vxlan_mdb_config *cfg, + const struct vxlan_mdb_entry *mdb_entry, + struct vxlan_mdb_remote *remote, + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = cfg->vxlan; + struct vxlan_mdb_src_entry *ent; + struct hlist_node *tmp; + int err; + + hlist_for_each_entry(ent, &remote->src_list, node) + ent->flags |= VXLAN_SGRP_F_DELETE; + + err = vxlan_mdb_remote_srcs_add(cfg, remote, extack); + if (err) + goto err_clear_delete; + + hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) { + if (ent->flags & VXLAN_SGRP_F_DELETE) + vxlan_mdb_remote_src_del(vxlan, &mdb_entry->key, remote, + ent); + } + + return 0; + +err_clear_delete: + hlist_for_each_entry(ent, &remote->src_list, node) + ent->flags &= ~VXLAN_SGRP_F_DELETE; + return err; +} + +static int vxlan_mdb_remote_replace(const struct vxlan_mdb_config *cfg, + const struct vxlan_mdb_entry *mdb_entry, + struct vxlan_mdb_remote *remote, + struct netlink_ext_ack *extack) +{ + struct vxlan_rdst *new_rd, *old_rd = rtnl_dereference(remote->rd); + struct vxlan_dev *vxlan = cfg->vxlan; + int err; + + err = vxlan_mdb_remote_rdst_init(cfg, remote); + if (err) + return err; + new_rd = rtnl_dereference(remote->rd); + + err = vxlan_mdb_remote_srcs_replace(cfg, mdb_entry, remote, extack); + if (err) + goto err_rdst_reset; + + WRITE_ONCE(remote->flags, cfg->flags); + WRITE_ONCE(remote->filter_mode, cfg->filter_mode); + remote->rt_protocol = cfg->rt_protocol; + vxlan_mdb_remote_notify(vxlan, mdb_entry, remote, RTM_NEWMDB); + + vxlan_mdb_remote_rdst_fini(old_rd); + + return 0; + +err_rdst_reset: + rcu_assign_pointer(remote->rd, old_rd); + vxlan_mdb_remote_rdst_fini(new_rd); + return err; +} + +static int vxlan_mdb_remote_add(const struct vxlan_mdb_config *cfg, + struct vxlan_mdb_entry *mdb_entry, + struct netlink_ext_ack *extack) +{ + struct vxlan_mdb_remote *remote; + int err; + + remote = vxlan_mdb_remote_lookup(mdb_entry, &cfg->remote_ip); + if (remote) { + if (!(cfg->nlflags & NLM_F_REPLACE)) { + NL_SET_ERR_MSG_MOD(extack, "Replace not specified and MDB remote entry already exists"); + return -EEXIST; + } + return vxlan_mdb_remote_replace(cfg, mdb_entry, remote, extack); + } + + if (!(cfg->nlflags & NLM_F_CREATE)) { + NL_SET_ERR_MSG_MOD(extack, "Create not specified and entry does not exist"); + return -ENOENT; + } + + remote = kzalloc(sizeof(*remote), GFP_KERNEL); + if (!remote) + return -ENOMEM; + + err = vxlan_mdb_remote_init(cfg, remote); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to initialize remote MDB entry"); + goto err_free_remote; + } + + err = vxlan_mdb_remote_srcs_add(cfg, remote, extack); + if (err) + goto err_remote_fini; + + list_add_rcu(&remote->list, &mdb_entry->remotes); + vxlan_mdb_remote_notify(cfg->vxlan, mdb_entry, remote, RTM_NEWMDB); + + return 0; + +err_remote_fini: + vxlan_mdb_remote_fini(cfg->vxlan, remote); +err_free_remote: + kfree(remote); + return err; +} + +static void vxlan_mdb_remote_del(struct vxlan_dev *vxlan, + struct vxlan_mdb_entry *mdb_entry, + struct vxlan_mdb_remote *remote) +{ + vxlan_mdb_remote_notify(vxlan, mdb_entry, remote, RTM_DELMDB); + list_del_rcu(&remote->list); + vxlan_mdb_remote_srcs_del(vxlan, &mdb_entry->key, remote); + vxlan_mdb_remote_fini(vxlan, remote); + kfree_rcu(remote, rcu); +} + +static struct vxlan_mdb_entry * +vxlan_mdb_entry_get(struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry_key *group) +{ + struct vxlan_mdb_entry *mdb_entry; + int err; + + mdb_entry = vxlan_mdb_entry_lookup(vxlan, group); + if (mdb_entry) + return mdb_entry; + + mdb_entry = kzalloc(sizeof(*mdb_entry), GFP_KERNEL); + if (!mdb_entry) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&mdb_entry->remotes); + memcpy(&mdb_entry->key, group, sizeof(mdb_entry->key)); + hlist_add_head(&mdb_entry->mdb_node, &vxlan->mdb_list); + + err = rhashtable_lookup_insert_fast(&vxlan->mdb_tbl, + &mdb_entry->rhnode, + vxlan_mdb_rht_params); + if (err) + goto err_free_entry; + + if (hlist_is_singular_node(&mdb_entry->mdb_node, &vxlan->mdb_list)) + vxlan->cfg.flags |= VXLAN_F_MDB; + + return mdb_entry; + +err_free_entry: + hlist_del(&mdb_entry->mdb_node); + kfree(mdb_entry); + return ERR_PTR(err); +} + +static void vxlan_mdb_entry_put(struct vxlan_dev *vxlan, + struct vxlan_mdb_entry *mdb_entry) +{ + if (!list_empty(&mdb_entry->remotes)) + return; + + if (hlist_is_singular_node(&mdb_entry->mdb_node, &vxlan->mdb_list)) + vxlan->cfg.flags &= ~VXLAN_F_MDB; + + rhashtable_remove_fast(&vxlan->mdb_tbl, &mdb_entry->rhnode, + vxlan_mdb_rht_params); + hlist_del(&mdb_entry->mdb_node); + kfree_rcu(mdb_entry, rcu); +} + +static int __vxlan_mdb_add(const struct vxlan_mdb_config *cfg, + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = cfg->vxlan; + struct vxlan_mdb_entry *mdb_entry; + int err; + + mdb_entry = vxlan_mdb_entry_get(vxlan, &cfg->group); + if (IS_ERR(mdb_entry)) + return PTR_ERR(mdb_entry); + + err = vxlan_mdb_remote_add(cfg, mdb_entry, extack); + if (err) + goto err_entry_put; + + vxlan->mdb_seq++; + + return 0; + +err_entry_put: + vxlan_mdb_entry_put(vxlan, mdb_entry); + return err; +} + +static int __vxlan_mdb_del(const struct vxlan_mdb_config *cfg, + struct netlink_ext_ack *extack) +{ + struct vxlan_dev *vxlan = cfg->vxlan; + struct vxlan_mdb_entry *mdb_entry; + struct vxlan_mdb_remote *remote; + + mdb_entry = vxlan_mdb_entry_lookup(vxlan, &cfg->group); + if (!mdb_entry) { + NL_SET_ERR_MSG_MOD(extack, "Did not find MDB entry"); + return -ENOENT; + } + + remote = vxlan_mdb_remote_lookup(mdb_entry, &cfg->remote_ip); + if (!remote) { + NL_SET_ERR_MSG_MOD(extack, "Did not find MDB remote entry"); + return -ENOENT; + } + + vxlan_mdb_remote_del(vxlan, mdb_entry, remote); + vxlan_mdb_entry_put(vxlan, mdb_entry); + + vxlan->mdb_seq++; + + return 0; +} + +int vxlan_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, + struct netlink_ext_ack *extack) +{ + struct vxlan_mdb_config cfg; + int err; + + ASSERT_RTNL(); + + err = vxlan_mdb_config_init(&cfg, dev, tb, nlmsg_flags, extack); + if (err) + return err; + + err = __vxlan_mdb_add(&cfg, extack); + + vxlan_mdb_config_fini(&cfg); + return err; +} + +int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[], + struct netlink_ext_ack *extack) +{ + struct vxlan_mdb_config cfg; + int err; + + ASSERT_RTNL(); + + err = vxlan_mdb_config_init(&cfg, dev, tb, 0, extack); + if (err) + return err; + + err = __vxlan_mdb_del(&cfg, extack); + + vxlan_mdb_config_fini(&cfg); + return err; +} + +struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan, + struct sk_buff *skb, + __be32 src_vni) +{ + struct vxlan_mdb_entry *mdb_entry; + struct vxlan_mdb_entry_key group; + + if (!is_multicast_ether_addr(eth_hdr(skb)->h_dest) || + is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) + return NULL; + + /* When not in collect metadata mode, 'src_vni' is zero, but MDB + * entries are stored with the VNI of the VXLAN device. + */ + if (!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) + src_vni = vxlan->default_dst.remote_vni; + + memset(&group, 0, sizeof(group)); + group.vni = src_vni; + + switch (skb->protocol) { + case htons(ETH_P_IP): + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return NULL; + group.dst.sa.sa_family = AF_INET; + group.dst.sin.sin_addr.s_addr = ip_hdr(skb)->daddr; + group.src.sa.sa_family = AF_INET; + group.src.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + return NULL; + group.dst.sa.sa_family = AF_INET6; + group.dst.sin6.sin6_addr = ipv6_hdr(skb)->daddr; + group.src.sa.sa_family = AF_INET6; + group.src.sin6.sin6_addr = ipv6_hdr(skb)->saddr; + break; +#endif + default: + return NULL; + } + + mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group); + if (mdb_entry) + return mdb_entry; + + memset(&group.src, 0, sizeof(group.src)); + mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group); + if (mdb_entry) + return mdb_entry; + + /* No (S, G) or (*, G) found. Look up the all-zeros entry, but only if + * the destination IP address is not link-local multicast since we want + * to transmit such traffic together with broadcast and unknown unicast + * traffic. + */ + switch (skb->protocol) { + case htons(ETH_P_IP): + if (ipv4_is_local_multicast(group.dst.sin.sin_addr.s_addr)) + return NULL; + group.dst.sin.sin_addr.s_addr = 0; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + if (ipv6_addr_type(&group.dst.sin6.sin6_addr) & + IPV6_ADDR_LINKLOCAL) + return NULL; + memset(&group.dst.sin6.sin6_addr, 0, + sizeof(group.dst.sin6.sin6_addr)); + break; +#endif + default: + return NULL; + } + + return vxlan_mdb_entry_lookup(vxlan, &group); +} + +netdev_tx_t vxlan_mdb_xmit(struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry *mdb_entry, + struct sk_buff *skb) +{ + struct vxlan_mdb_remote *remote, *fremote = NULL; + __be32 src_vni = mdb_entry->key.vni; + + list_for_each_entry_rcu(remote, &mdb_entry->remotes, list) { + struct sk_buff *skb1; + + if ((vxlan_mdb_is_star_g(&mdb_entry->key) && + READ_ONCE(remote->filter_mode) == MCAST_INCLUDE) || + (READ_ONCE(remote->flags) & VXLAN_MDB_REMOTE_F_BLOCKED)) + continue; + + if (!fremote) { + fremote = remote; + continue; + } + + skb1 = skb_clone(skb, GFP_ATOMIC); + if (skb1) + vxlan_xmit_one(skb1, vxlan->dev, src_vni, + rcu_dereference(remote->rd), false); + } + + if (fremote) + vxlan_xmit_one(skb, vxlan->dev, src_vni, + rcu_dereference(fremote->rd), false); + else + kfree_skb(skb); + + return NETDEV_TX_OK; +} + +static void vxlan_mdb_check_empty(void *ptr, void *arg) +{ + WARN_ON_ONCE(1); +} + +static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan, + struct vxlan_mdb_entry *mdb_entry) +{ + struct vxlan_mdb_remote *remote, *tmp; + + list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list) + vxlan_mdb_remote_del(vxlan, mdb_entry, remote); +} + +static void vxlan_mdb_entries_flush(struct vxlan_dev *vxlan) +{ + struct vxlan_mdb_entry *mdb_entry; + struct hlist_node *tmp; + + /* The removal of an entry cannot trigger the removal of another entry + * since entries are always added to the head of the list. + */ + hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) { + vxlan_mdb_remotes_flush(vxlan, mdb_entry); + vxlan_mdb_entry_put(vxlan, mdb_entry); + } +} + +int vxlan_mdb_init(struct vxlan_dev *vxlan) +{ + int err; + + err = rhashtable_init(&vxlan->mdb_tbl, &vxlan_mdb_rht_params); + if (err) + return err; + + INIT_HLIST_HEAD(&vxlan->mdb_list); + + return 0; +} + +void vxlan_mdb_fini(struct vxlan_dev *vxlan) +{ + vxlan_mdb_entries_flush(vxlan); + WARN_ON_ONCE(vxlan->cfg.flags & VXLAN_F_MDB); + rhashtable_free_and_destroy(&vxlan->mdb_tbl, vxlan_mdb_check_empty, + NULL); +} diff --git a/drivers/net/vxlan/vxlan_multicast.c b/drivers/net/vxlan/vxlan_multicast.c new file mode 100644 index 0000000000..a7f2d67dc6 --- /dev/null +++ b/drivers/net/vxlan/vxlan_multicast.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Vxlan multicast group handling + * + */ +#include +#include +#include +#include +#include + +#include "vxlan_private.h" + +/* Update multicast group membership when first VNI on + * multicast address is brought up + */ +int vxlan_igmp_join(struct vxlan_dev *vxlan, union vxlan_addr *rip, + int rifindex) +{ + union vxlan_addr *ip = (rip ? : &vxlan->default_dst.remote_ip); + int ifindex = (rifindex ? : vxlan->default_dst.remote_ifindex); + int ret = -EINVAL; + struct sock *sk; + + if (ip->sa.sa_family == AF_INET) { + struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock); + struct ip_mreqn mreq = { + .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, + .imr_ifindex = ifindex, + }; + + sk = sock4->sock->sk; + lock_sock(sk); + ret = ip_mc_join_group(sk, &mreq); + release_sock(sk); +#if IS_ENABLED(CONFIG_IPV6) + } else { + struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock); + + sk = sock6->sock->sk; + lock_sock(sk); + ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex, + &ip->sin6.sin6_addr); + release_sock(sk); +#endif + } + + return ret; +} + +int vxlan_igmp_leave(struct vxlan_dev *vxlan, union vxlan_addr *rip, + int rifindex) +{ + union vxlan_addr *ip = (rip ? : &vxlan->default_dst.remote_ip); + int ifindex = (rifindex ? : vxlan->default_dst.remote_ifindex); + int ret = -EINVAL; + struct sock *sk; + + if (ip->sa.sa_family == AF_INET) { + struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock); + struct ip_mreqn mreq = { + .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, + .imr_ifindex = ifindex, + }; + + sk = sock4->sock->sk; + lock_sock(sk); + ret = ip_mc_leave_group(sk, &mreq); + release_sock(sk); +#if IS_ENABLED(CONFIG_IPV6) + } else { + struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock); + + sk = sock6->sock->sk; + lock_sock(sk); + ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex, + &ip->sin6.sin6_addr); + release_sock(sk); +#endif + } + + return ret; +} + +static bool vxlan_group_used_match(union vxlan_addr *ip, int ifindex, + union vxlan_addr *rip, int rifindex) +{ + if (!vxlan_addr_multicast(rip)) + return false; + + if (!vxlan_addr_equal(rip, ip)) + return false; + + if (rifindex != ifindex) + return false; + + return true; +} + +static bool vxlan_group_used_by_vnifilter(struct vxlan_dev *vxlan, + union vxlan_addr *ip, int ifindex) +{ + struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); + struct vxlan_vni_node *v, *tmp; + + if (vxlan_group_used_match(ip, ifindex, + &vxlan->default_dst.remote_ip, + vxlan->default_dst.remote_ifindex)) + return true; + + list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { + if (!vxlan_addr_multicast(&v->remote_ip)) + continue; + + if (vxlan_group_used_match(ip, ifindex, + &v->remote_ip, + vxlan->default_dst.remote_ifindex)) + return true; + } + + return false; +} + +/* See if multicast group is already in use by other ID */ +bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev, + __be32 vni, union vxlan_addr *rip, int rifindex) +{ + union vxlan_addr *ip = (rip ? : &dev->default_dst.remote_ip); + int ifindex = (rifindex ? : dev->default_dst.remote_ifindex); + struct vxlan_dev *vxlan; + struct vxlan_sock *sock4; +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_sock *sock6; +#endif + unsigned short family = dev->default_dst.remote_ip.sa.sa_family; + + sock4 = rtnl_dereference(dev->vn4_sock); + + /* The vxlan_sock is only used by dev, leaving group has + * no effect on other vxlan devices. + */ + if (family == AF_INET && sock4 && refcount_read(&sock4->refcnt) == 1) + return false; + +#if IS_ENABLED(CONFIG_IPV6) + sock6 = rtnl_dereference(dev->vn6_sock); + if (family == AF_INET6 && sock6 && refcount_read(&sock6->refcnt) == 1) + return false; +#endif + + list_for_each_entry(vxlan, &vn->vxlan_list, next) { + if (!netif_running(vxlan->dev) || vxlan == dev) + continue; + + if (family == AF_INET && + rtnl_dereference(vxlan->vn4_sock) != sock4) + continue; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && + rtnl_dereference(vxlan->vn6_sock) != sock6) + continue; +#endif + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { + if (!vxlan_group_used_by_vnifilter(vxlan, ip, ifindex)) + continue; + } else { + if (!vxlan_group_used_match(ip, ifindex, + &vxlan->default_dst.remote_ip, + vxlan->default_dst.remote_ifindex)) + continue; + } + + return true; + } + + return false; +} + +static int vxlan_multicast_join_vnigrp(struct vxlan_dev *vxlan) +{ + struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); + struct vxlan_vni_node *v, *tmp, *vgood = NULL; + int ret = 0; + + list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { + if (!vxlan_addr_multicast(&v->remote_ip)) + continue; + /* skip if address is same as default address */ + if (vxlan_addr_equal(&v->remote_ip, + &vxlan->default_dst.remote_ip)) + continue; + ret = vxlan_igmp_join(vxlan, &v->remote_ip, 0); + if (ret == -EADDRINUSE) + ret = 0; + if (ret) + goto out; + vgood = v; + } +out: + if (ret) { + list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { + if (!vxlan_addr_multicast(&v->remote_ip)) + continue; + if (vxlan_addr_equal(&v->remote_ip, + &vxlan->default_dst.remote_ip)) + continue; + vxlan_igmp_leave(vxlan, &v->remote_ip, 0); + if (v == vgood) + break; + } + } + + return ret; +} + +static int vxlan_multicast_leave_vnigrp(struct vxlan_dev *vxlan) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); + struct vxlan_vni_node *v, *tmp; + int last_err = 0, ret; + + list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { + if (vxlan_addr_multicast(&v->remote_ip) && + !vxlan_group_used(vn, vxlan, v->vni, &v->remote_ip, + 0)) { + ret = vxlan_igmp_leave(vxlan, &v->remote_ip, 0); + if (ret) + last_err = ret; + } + } + + return last_err; +} + +int vxlan_multicast_join(struct vxlan_dev *vxlan) +{ + int ret = 0; + + if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) { + ret = vxlan_igmp_join(vxlan, &vxlan->default_dst.remote_ip, + vxlan->default_dst.remote_ifindex); + if (ret == -EADDRINUSE) + ret = 0; + if (ret) + return ret; + } + + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) + return vxlan_multicast_join_vnigrp(vxlan); + + return 0; +} + +int vxlan_multicast_leave(struct vxlan_dev *vxlan) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + int ret = 0; + + if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) && + !vxlan_group_used(vn, vxlan, 0, NULL, 0)) { + ret = vxlan_igmp_leave(vxlan, &vxlan->default_dst.remote_ip, + vxlan->default_dst.remote_ifindex); + if (ret) + return ret; + } + + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) + return vxlan_multicast_leave_vnigrp(vxlan); + + return 0; +} diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h new file mode 100644 index 0000000000..817fa30758 --- /dev/null +++ b/drivers/net/vxlan/vxlan_private.h @@ -0,0 +1,246 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Vxlan private header file + * + */ + +#ifndef _VXLAN_PRIVATE_H +#define _VXLAN_PRIVATE_H + +#include + +extern unsigned int vxlan_net_id; +extern const u8 all_zeros_mac[ETH_ALEN + 2]; +extern const struct rhashtable_params vxlan_vni_rht_params; + +#define PORT_HASH_BITS 8 +#define PORT_HASH_SIZE (1 << PORT_HASH_BITS) + +/* per-network namespace private data for this module */ +struct vxlan_net { + struct list_head vxlan_list; + struct hlist_head sock_list[PORT_HASH_SIZE]; + spinlock_t sock_lock; + struct notifier_block nexthop_notifier_block; +}; + +/* Forwarding table entry */ +struct vxlan_fdb { + struct hlist_node hlist; /* linked list of entries */ + struct rcu_head rcu; + unsigned long updated; /* jiffies */ + unsigned long used; + struct list_head remotes; + u8 eth_addr[ETH_ALEN]; + u16 state; /* see ndm_state */ + __be32 vni; + u16 flags; /* see ndm_flags and below */ + struct list_head nh_list; + struct nexthop __rcu *nh; + struct vxlan_dev __rcu *vdev; +}; + +#define NTF_VXLAN_ADDED_BY_USER 0x100 + +/* Virtual Network hash table head */ +static inline struct hlist_head *vni_head(struct vxlan_sock *vs, __be32 vni) +{ + return &vs->vni_list[hash_32((__force u32)vni, 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->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_rcu(struct vxlan_fdb *fdb) +{ + if (rcu_access_pointer(fdb->nh)) + return NULL; + return list_entry_rcu(fdb->remotes.next, struct vxlan_rdst, list); +} + +static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb) +{ + if (rcu_access_pointer(fdb->nh)) + return NULL; + return list_first_entry(&fdb->remotes, struct vxlan_rdst, list); +} + +#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 int vxlan_nla_get_addr(union vxlan_addr *ip, + const struct nlattr *nla) +{ + if (nla_len(nla) >= sizeof(struct in6_addr)) { + ip->sin6.sin6_addr = nla_get_in6_addr(nla); + ip->sa.sa_family = AF_INET6; + return 0; + } else if (nla_len(nla) >= sizeof(__be32)) { + ip->sin.sin_addr.s_addr = nla_get_in_addr(nla); + ip->sa.sa_family = AF_INET; + return 0; + } else { + return -EAFNOSUPPORT; + } +} + +static inline 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_in6_addr(skb, attr, &ip->sin6.sin6_addr); + else + return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr); +} + +static inline bool vxlan_addr_is_multicast(const union vxlan_addr *ip) +{ + if (ip->sa.sa_family == AF_INET6) + return ipv6_addr_is_multicast(&ip->sin6.sin6_addr); + else + return ipv4_is_multicast(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 int vxlan_nla_get_addr(union vxlan_addr *ip, + const 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_in_addr(nla); + ip->sa.sa_family = AF_INET; + return 0; + } else { + return -EAFNOSUPPORT; + } +} + +static inline int vxlan_nla_put_addr(struct sk_buff *skb, int attr, + const union vxlan_addr *ip) +{ + return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr); +} + +static inline bool vxlan_addr_is_multicast(const union vxlan_addr *ip) +{ + return ipv4_is_multicast(ip->sin.sin_addr.s_addr); +} + +#endif + +static inline size_t vxlan_addr_size(const union vxlan_addr *ip) +{ + if (ip->sa.sa_family == AF_INET6) + return sizeof(struct in6_addr); + else + return sizeof(__be32); +} + +static inline struct vxlan_vni_node * +vxlan_vnifilter_lookup(struct vxlan_dev *vxlan, __be32 vni) +{ + struct vxlan_vni_group *vg; + + vg = rcu_dereference_rtnl(vxlan->vnigrp); + if (!vg) + return NULL; + + return rhashtable_lookup_fast(&vg->vni_hash, &vni, + vxlan_vni_rht_params); +} + +/* vxlan_core.c */ +int vxlan_fdb_create(struct vxlan_dev *vxlan, + const u8 *mac, union vxlan_addr *ip, + __u16 state, __be16 port, __be32 src_vni, + __be32 vni, __u32 ifindex, __u16 ndm_flags, + u32 nhid, struct vxlan_fdb **fdb, + struct netlink_ext_ack *extack); +int __vxlan_fdb_delete(struct vxlan_dev *vxlan, + const unsigned char *addr, union vxlan_addr ip, + __be16 port, __be32 src_vni, __be32 vni, + u32 ifindex, bool swdev_notify); +u32 eth_vni_hash(const unsigned char *addr, __be32 vni); +u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni); +int vxlan_fdb_update(struct vxlan_dev *vxlan, + const u8 *mac, union vxlan_addr *ip, + __u16 state, __u16 flags, + __be16 port, __be32 src_vni, __be32 vni, + __u32 ifindex, __u16 ndm_flags, u32 nhid, + bool swdev_notify, struct netlink_ext_ack *extack); +void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, + __be32 default_vni, struct vxlan_rdst *rdst, bool did_rsc); +int vxlan_vni_in_use(struct net *src_net, struct vxlan_dev *vxlan, + struct vxlan_config *conf, __be32 vni); + +/* vxlan_vnifilter.c */ +int vxlan_vnigroup_init(struct vxlan_dev *vxlan); +void vxlan_vnigroup_uninit(struct vxlan_dev *vxlan); + +void vxlan_vnifilter_init(void); +void vxlan_vnifilter_uninit(void); +void vxlan_vnifilter_count(struct vxlan_dev *vxlan, __be32 vni, + struct vxlan_vni_node *vninode, + int type, unsigned int len); + +void vxlan_vs_add_vnigrp(struct vxlan_dev *vxlan, + struct vxlan_sock *vs, + bool ipv6); +void vxlan_vs_del_vnigrp(struct vxlan_dev *vxlan); +int vxlan_vnilist_update_group(struct vxlan_dev *vxlan, + union vxlan_addr *old_remote_ip, + union vxlan_addr *new_remote_ip, + struct netlink_ext_ack *extack); + + +/* vxlan_multicast.c */ +int vxlan_multicast_join(struct vxlan_dev *vxlan); +int vxlan_multicast_leave(struct vxlan_dev *vxlan); +bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev, + __be32 vni, union vxlan_addr *rip, int rifindex); +int vxlan_igmp_join(struct vxlan_dev *vxlan, union vxlan_addr *rip, + int rifindex); +int vxlan_igmp_leave(struct vxlan_dev *vxlan, union vxlan_addr *rip, + int rifindex); + +/* vxlan_mdb.c */ +int vxlan_mdb_dump(struct net_device *dev, struct sk_buff *skb, + struct netlink_callback *cb); +int vxlan_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, + struct netlink_ext_ack *extack); +int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[], + struct netlink_ext_ack *extack); +struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan, + struct sk_buff *skb, + __be32 src_vni); +netdev_tx_t vxlan_mdb_xmit(struct vxlan_dev *vxlan, + const struct vxlan_mdb_entry *mdb_entry, + struct sk_buff *skb); +int vxlan_mdb_init(struct vxlan_dev *vxlan); +void vxlan_mdb_fini(struct vxlan_dev *vxlan); +#endif diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c new file mode 100644 index 0000000000..9c59d0bf8c --- /dev/null +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -0,0 +1,1010 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Vxlan vni filter for collect metadata mode + * + * Authors: Roopa Prabhu + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "vxlan_private.h" + +static inline int vxlan_vni_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct vxlan_vni_node *vnode = ptr; + __be32 vni = *(__be32 *)arg->key; + + return vnode->vni != vni; +} + +const struct rhashtable_params vxlan_vni_rht_params = { + .head_offset = offsetof(struct vxlan_vni_node, vnode), + .key_offset = offsetof(struct vxlan_vni_node, vni), + .key_len = sizeof(__be32), + .nelem_hint = 3, + .max_size = VXLAN_N_VID, + .obj_cmpfn = vxlan_vni_cmp, + .automatic_shrinking = true, +}; + +static void vxlan_vs_add_del_vninode(struct vxlan_dev *vxlan, + struct vxlan_vni_node *v, + bool del) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_dev_node *node; + struct vxlan_sock *vs; + + spin_lock(&vn->sock_lock); + if (del) { + if (!hlist_unhashed(&v->hlist4.hlist)) + hlist_del_init_rcu(&v->hlist4.hlist); +#if IS_ENABLED(CONFIG_IPV6) + if (!hlist_unhashed(&v->hlist6.hlist)) + hlist_del_init_rcu(&v->hlist6.hlist); +#endif + goto out; + } + +#if IS_ENABLED(CONFIG_IPV6) + vs = rtnl_dereference(vxlan->vn6_sock); + if (vs && v) { + node = &v->hlist6; + hlist_add_head_rcu(&node->hlist, vni_head(vs, v->vni)); + } +#endif + vs = rtnl_dereference(vxlan->vn4_sock); + if (vs && v) { + node = &v->hlist4; + hlist_add_head_rcu(&node->hlist, vni_head(vs, v->vni)); + } +out: + spin_unlock(&vn->sock_lock); +} + +void vxlan_vs_add_vnigrp(struct vxlan_dev *vxlan, + struct vxlan_sock *vs, + bool ipv6) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); + struct vxlan_vni_node *v, *tmp; + struct vxlan_dev_node *node; + + if (!vg) + return; + + spin_lock(&vn->sock_lock); + list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6) + node = &v->hlist6; + else +#endif + node = &v->hlist4; + node->vxlan = vxlan; + hlist_add_head_rcu(&node->hlist, vni_head(vs, v->vni)); + } + spin_unlock(&vn->sock_lock); +} + +void vxlan_vs_del_vnigrp(struct vxlan_dev *vxlan) +{ + struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_vni_node *v, *tmp; + + if (!vg) + return; + + spin_lock(&vn->sock_lock); + list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { + hlist_del_init_rcu(&v->hlist4.hlist); +#if IS_ENABLED(CONFIG_IPV6) + hlist_del_init_rcu(&v->hlist6.hlist); +#endif + } + spin_unlock(&vn->sock_lock); +} + +static void vxlan_vnifilter_stats_get(const struct vxlan_vni_node *vninode, + struct vxlan_vni_stats *dest) +{ + int i; + + memset(dest, 0, sizeof(*dest)); + for_each_possible_cpu(i) { + struct vxlan_vni_stats_pcpu *pstats; + struct vxlan_vni_stats temp; + unsigned int start; + + pstats = per_cpu_ptr(vninode->stats, i); + do { + start = u64_stats_fetch_begin(&pstats->syncp); + memcpy(&temp, &pstats->stats, sizeof(temp)); + } while (u64_stats_fetch_retry(&pstats->syncp, start)); + + dest->rx_packets += temp.rx_packets; + dest->rx_bytes += temp.rx_bytes; + dest->rx_drops += temp.rx_drops; + dest->rx_errors += temp.rx_errors; + dest->tx_packets += temp.tx_packets; + dest->tx_bytes += temp.tx_bytes; + dest->tx_drops += temp.tx_drops; + dest->tx_errors += temp.tx_errors; + } +} + +static void vxlan_vnifilter_stats_add(struct vxlan_vni_node *vninode, + int type, unsigned int len) +{ + struct vxlan_vni_stats_pcpu *pstats = this_cpu_ptr(vninode->stats); + + u64_stats_update_begin(&pstats->syncp); + switch (type) { + case VXLAN_VNI_STATS_RX: + pstats->stats.rx_bytes += len; + pstats->stats.rx_packets++; + break; + case VXLAN_VNI_STATS_RX_DROPS: + pstats->stats.rx_drops++; + break; + case VXLAN_VNI_STATS_RX_ERRORS: + pstats->stats.rx_errors++; + break; + case VXLAN_VNI_STATS_TX: + pstats->stats.tx_bytes += len; + pstats->stats.tx_packets++; + break; + case VXLAN_VNI_STATS_TX_DROPS: + pstats->stats.tx_drops++; + break; + case VXLAN_VNI_STATS_TX_ERRORS: + pstats->stats.tx_errors++; + break; + } + u64_stats_update_end(&pstats->syncp); +} + +void vxlan_vnifilter_count(struct vxlan_dev *vxlan, __be32 vni, + struct vxlan_vni_node *vninode, + int type, unsigned int len) +{ + struct vxlan_vni_node *vnode; + + if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) + return; + + if (vninode) { + vnode = vninode; + } else { + vnode = vxlan_vnifilter_lookup(vxlan, vni); + if (!vnode) + return; + } + + vxlan_vnifilter_stats_add(vnode, type, len); +} + +static u32 vnirange(struct vxlan_vni_node *vbegin, + struct vxlan_vni_node *vend) +{ + return (be32_to_cpu(vend->vni) - be32_to_cpu(vbegin->vni)); +} + +static size_t vxlan_vnifilter_entry_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct tunnel_msg)) + + nla_total_size(0) /* VXLAN_VNIFILTER_ENTRY */ + + nla_total_size(sizeof(u32)) /* VXLAN_VNIFILTER_ENTRY_START */ + + nla_total_size(sizeof(u32)) /* VXLAN_VNIFILTER_ENTRY_END */ + + nla_total_size(sizeof(struct in6_addr));/* VXLAN_VNIFILTER_ENTRY_GROUP{6} */ +} + +static int __vnifilter_entry_fill_stats(struct sk_buff *skb, + const struct vxlan_vni_node *vbegin) +{ + struct vxlan_vni_stats vstats; + struct nlattr *vstats_attr; + + vstats_attr = nla_nest_start(skb, VXLAN_VNIFILTER_ENTRY_STATS); + if (!vstats_attr) + goto out_stats_err; + + vxlan_vnifilter_stats_get(vbegin, &vstats); + if (nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_BYTES, + vstats.rx_bytes, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_PKTS, + vstats.rx_packets, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_DROPS, + vstats.rx_drops, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_ERRORS, + vstats.rx_errors, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_BYTES, + vstats.tx_bytes, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_PKTS, + vstats.tx_packets, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_DROPS, + vstats.tx_drops, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_ERRORS, + vstats.tx_errors, VNIFILTER_ENTRY_STATS_PAD)) + goto out_stats_err; + + nla_nest_end(skb, vstats_attr); + + return 0; + +out_stats_err: + nla_nest_cancel(skb, vstats_attr); + return -EMSGSIZE; +} + +static bool vxlan_fill_vni_filter_entry(struct sk_buff *skb, + struct vxlan_vni_node *vbegin, + struct vxlan_vni_node *vend, + bool fill_stats) +{ + struct nlattr *ventry; + u32 vs = be32_to_cpu(vbegin->vni); + u32 ve = 0; + + if (vbegin != vend) + ve = be32_to_cpu(vend->vni); + + ventry = nla_nest_start(skb, VXLAN_VNIFILTER_ENTRY); + if (!ventry) + return false; + + if (nla_put_u32(skb, VXLAN_VNIFILTER_ENTRY_START, vs)) + goto out_err; + + if (ve && nla_put_u32(skb, VXLAN_VNIFILTER_ENTRY_END, ve)) + goto out_err; + + if (!vxlan_addr_any(&vbegin->remote_ip)) { + if (vbegin->remote_ip.sa.sa_family == AF_INET) { + if (nla_put_in_addr(skb, VXLAN_VNIFILTER_ENTRY_GROUP, + vbegin->remote_ip.sin.sin_addr.s_addr)) + goto out_err; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (nla_put_in6_addr(skb, VXLAN_VNIFILTER_ENTRY_GROUP6, + &vbegin->remote_ip.sin6.sin6_addr)) + goto out_err; +#endif + } + } + + if (fill_stats && __vnifilter_entry_fill_stats(skb, vbegin)) + goto out_err; + + nla_nest_end(skb, ventry); + + return true; + +out_err: + nla_nest_cancel(skb, ventry); + + return false; +} + +static void vxlan_vnifilter_notify(const struct vxlan_dev *vxlan, + struct vxlan_vni_node *vninode, int cmd) +{ + struct tunnel_msg *tmsg; + struct sk_buff *skb; + struct nlmsghdr *nlh; + struct net *net = dev_net(vxlan->dev); + int err = -ENOBUFS; + + skb = nlmsg_new(vxlan_vnifilter_entry_nlmsg_size(), GFP_KERNEL); + if (!skb) + goto out_err; + + err = -EMSGSIZE; + nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*tmsg), 0); + if (!nlh) + goto out_err; + tmsg = nlmsg_data(nlh); + memset(tmsg, 0, sizeof(*tmsg)); + tmsg->family = AF_BRIDGE; + tmsg->ifindex = vxlan->dev->ifindex; + + if (!vxlan_fill_vni_filter_entry(skb, vninode, vninode, false)) + goto out_err; + + nlmsg_end(skb, nlh); + rtnl_notify(skb, net, 0, RTNLGRP_TUNNEL, NULL, GFP_KERNEL); + + return; + +out_err: + rtnl_set_sk_err(net, RTNLGRP_TUNNEL, err); + + kfree_skb(skb); +} + +static int vxlan_vnifilter_dump_dev(const struct net_device *dev, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct vxlan_vni_node *tmp, *v, *vbegin = NULL, *vend = NULL; + struct vxlan_dev *vxlan = netdev_priv(dev); + struct tunnel_msg *new_tmsg, *tmsg; + int idx = 0, s_idx = cb->args[1]; + struct vxlan_vni_group *vg; + struct nlmsghdr *nlh; + bool dump_stats; + int err = 0; + + if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) + return -EINVAL; + + /* RCU needed because of the vni locking rules (rcu || rtnl) */ + vg = rcu_dereference(vxlan->vnigrp); + if (!vg || !vg->num_vnis) + return 0; + + tmsg = nlmsg_data(cb->nlh); + dump_stats = !!(tmsg->flags & TUNNEL_MSG_FLAG_STATS); + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + RTM_NEWTUNNEL, sizeof(*new_tmsg), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + new_tmsg = nlmsg_data(nlh); + memset(new_tmsg, 0, sizeof(*new_tmsg)); + new_tmsg->family = PF_BRIDGE; + new_tmsg->ifindex = dev->ifindex; + + list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { + if (idx < s_idx) { + idx++; + continue; + } + if (!vbegin) { + vbegin = v; + vend = v; + continue; + } + if (!dump_stats && vnirange(vend, v) == 1 && + vxlan_addr_equal(&v->remote_ip, &vend->remote_ip)) { + goto update_end; + } else { + if (!vxlan_fill_vni_filter_entry(skb, vbegin, vend, + dump_stats)) { + err = -EMSGSIZE; + break; + } + idx += vnirange(vbegin, vend) + 1; + vbegin = v; + } +update_end: + vend = v; + } + + if (!err && vbegin) { + if (!vxlan_fill_vni_filter_entry(skb, vbegin, vend, dump_stats)) + err = -EMSGSIZE; + } + + cb->args[1] = err ? idx : 0; + + nlmsg_end(skb, nlh); + + return err; +} + +static int vxlan_vnifilter_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int idx = 0, err = 0, s_idx = cb->args[0]; + struct net *net = sock_net(skb->sk); + struct tunnel_msg *tmsg; + struct net_device *dev; + + tmsg = nlmsg_data(cb->nlh); + + if (tmsg->flags & ~TUNNEL_MSG_VALID_USER_FLAGS) { + NL_SET_ERR_MSG(cb->extack, "Invalid tunnelmsg flags in ancillary header"); + return -EINVAL; + } + + rcu_read_lock(); + if (tmsg->ifindex) { + dev = dev_get_by_index_rcu(net, tmsg->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + if (!netif_is_vxlan(dev)) { + NL_SET_ERR_MSG(cb->extack, + "The device is not a vxlan device"); + err = -EINVAL; + goto out_err; + } + err = vxlan_vnifilter_dump_dev(dev, skb, cb); + /* if the dump completed without an error we return 0 here */ + if (err != -EMSGSIZE) + goto out_err; + } else { + for_each_netdev_rcu(net, dev) { + if (!netif_is_vxlan(dev)) + continue; + if (idx < s_idx) + goto skip; + err = vxlan_vnifilter_dump_dev(dev, skb, cb); + if (err == -EMSGSIZE) + break; +skip: + idx++; + } + } + cb->args[0] = idx; + rcu_read_unlock(); + + return skb->len; + +out_err: + rcu_read_unlock(); + + return err; +} + +static const struct nla_policy vni_filter_entry_policy[VXLAN_VNIFILTER_ENTRY_MAX + 1] = { + [VXLAN_VNIFILTER_ENTRY_START] = { .type = NLA_U32 }, + [VXLAN_VNIFILTER_ENTRY_END] = { .type = NLA_U32 }, + [VXLAN_VNIFILTER_ENTRY_GROUP] = { .type = NLA_BINARY, + .len = sizeof_field(struct iphdr, daddr) }, + [VXLAN_VNIFILTER_ENTRY_GROUP6] = { .type = NLA_BINARY, + .len = sizeof(struct in6_addr) }, +}; + +static const struct nla_policy vni_filter_policy[VXLAN_VNIFILTER_MAX + 1] = { + [VXLAN_VNIFILTER_ENTRY] = { .type = NLA_NESTED }, +}; + +static int vxlan_update_default_fdb_entry(struct vxlan_dev *vxlan, __be32 vni, + union vxlan_addr *old_remote_ip, + union vxlan_addr *remote_ip, + struct netlink_ext_ack *extack) +{ + struct vxlan_rdst *dst = &vxlan->default_dst; + u32 hash_index; + int err = 0; + + hash_index = fdb_head_index(vxlan, all_zeros_mac, vni); + spin_lock_bh(&vxlan->hash_lock[hash_index]); + if (remote_ip && !vxlan_addr_any(remote_ip)) { + err = vxlan_fdb_update(vxlan, all_zeros_mac, + remote_ip, + NUD_REACHABLE | NUD_PERMANENT, + NLM_F_APPEND | NLM_F_CREATE, + vxlan->cfg.dst_port, + vni, + vni, + dst->remote_ifindex, + NTF_SELF, 0, true, extack); + if (err) { + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + return err; + } + } + + if (old_remote_ip && !vxlan_addr_any(old_remote_ip)) { + __vxlan_fdb_delete(vxlan, all_zeros_mac, + *old_remote_ip, + vxlan->cfg.dst_port, + vni, vni, + dst->remote_ifindex, + true); + } + spin_unlock_bh(&vxlan->hash_lock[hash_index]); + + return err; +} + +static int vxlan_vni_update_group(struct vxlan_dev *vxlan, + struct vxlan_vni_node *vninode, + union vxlan_addr *group, + bool create, bool *changed, + struct netlink_ext_ack *extack) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_rdst *dst = &vxlan->default_dst; + union vxlan_addr *newrip = NULL, *oldrip = NULL; + union vxlan_addr old_remote_ip; + int ret = 0; + + memcpy(&old_remote_ip, &vninode->remote_ip, sizeof(old_remote_ip)); + + /* if per vni remote ip is not present use vxlan dev + * default dst remote ip for fdb entry + */ + if (group && !vxlan_addr_any(group)) { + newrip = group; + } else { + if (!vxlan_addr_any(&dst->remote_ip)) + newrip = &dst->remote_ip; + } + + /* if old rip exists, and no newrip, + * explicitly delete old rip + */ + if (!newrip && !vxlan_addr_any(&old_remote_ip)) + oldrip = &old_remote_ip; + + if (!newrip && !oldrip) + return 0; + + if (!create && oldrip && newrip && vxlan_addr_equal(oldrip, newrip)) + return 0; + + ret = vxlan_update_default_fdb_entry(vxlan, vninode->vni, + oldrip, newrip, + extack); + if (ret) + goto out; + + if (group) + memcpy(&vninode->remote_ip, group, sizeof(vninode->remote_ip)); + + if (vxlan->dev->flags & IFF_UP) { + if (vxlan_addr_multicast(&old_remote_ip) && + !vxlan_group_used(vn, vxlan, vninode->vni, + &old_remote_ip, + vxlan->default_dst.remote_ifindex)) { + ret = vxlan_igmp_leave(vxlan, &old_remote_ip, + 0); + if (ret) + goto out; + } + + if (vxlan_addr_multicast(&vninode->remote_ip)) { + ret = vxlan_igmp_join(vxlan, &vninode->remote_ip, 0); + if (ret == -EADDRINUSE) + ret = 0; + if (ret) + goto out; + } + } + + *changed = true; + + return 0; +out: + return ret; +} + +int vxlan_vnilist_update_group(struct vxlan_dev *vxlan, + union vxlan_addr *old_remote_ip, + union vxlan_addr *new_remote_ip, + struct netlink_ext_ack *extack) +{ + struct list_head *headp, *hpos; + struct vxlan_vni_group *vg; + struct vxlan_vni_node *vent; + int ret; + + vg = rtnl_dereference(vxlan->vnigrp); + + headp = &vg->vni_list; + list_for_each_prev(hpos, headp) { + vent = list_entry(hpos, struct vxlan_vni_node, vlist); + if (vxlan_addr_any(&vent->remote_ip)) { + ret = vxlan_update_default_fdb_entry(vxlan, vent->vni, + old_remote_ip, + new_remote_ip, + extack); + if (ret) + return ret; + } + } + + return 0; +} + +static void vxlan_vni_delete_group(struct vxlan_dev *vxlan, + struct vxlan_vni_node *vninode) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_rdst *dst = &vxlan->default_dst; + + /* if per vni remote_ip not present, delete the + * default dst remote_ip previously added for this vni + */ + if (!vxlan_addr_any(&vninode->remote_ip) || + !vxlan_addr_any(&dst->remote_ip)) + __vxlan_fdb_delete(vxlan, all_zeros_mac, + (vxlan_addr_any(&vninode->remote_ip) ? + dst->remote_ip : vninode->remote_ip), + vxlan->cfg.dst_port, + vninode->vni, vninode->vni, + dst->remote_ifindex, + true); + + if (vxlan->dev->flags & IFF_UP) { + if (vxlan_addr_multicast(&vninode->remote_ip) && + !vxlan_group_used(vn, vxlan, vninode->vni, + &vninode->remote_ip, + dst->remote_ifindex)) { + vxlan_igmp_leave(vxlan, &vninode->remote_ip, 0); + } + } +} + +static int vxlan_vni_update(struct vxlan_dev *vxlan, + struct vxlan_vni_group *vg, + __be32 vni, union vxlan_addr *group, + bool *changed, + struct netlink_ext_ack *extack) +{ + struct vxlan_vni_node *vninode; + int ret; + + vninode = rhashtable_lookup_fast(&vg->vni_hash, &vni, + vxlan_vni_rht_params); + if (!vninode) + return 0; + + ret = vxlan_vni_update_group(vxlan, vninode, group, false, changed, + extack); + if (ret) + return ret; + + if (changed) + vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL); + + return 0; +} + +static void __vxlan_vni_add_list(struct vxlan_vni_group *vg, + struct vxlan_vni_node *v) +{ + struct list_head *headp, *hpos; + struct vxlan_vni_node *vent; + + headp = &vg->vni_list; + list_for_each_prev(hpos, headp) { + vent = list_entry(hpos, struct vxlan_vni_node, vlist); + if (be32_to_cpu(v->vni) < be32_to_cpu(vent->vni)) + continue; + else + break; + } + list_add_rcu(&v->vlist, hpos); + vg->num_vnis++; +} + +static void __vxlan_vni_del_list(struct vxlan_vni_group *vg, + struct vxlan_vni_node *v) +{ + list_del_rcu(&v->vlist); + vg->num_vnis--; +} + +static struct vxlan_vni_node *vxlan_vni_alloc(struct vxlan_dev *vxlan, + __be32 vni) +{ + struct vxlan_vni_node *vninode; + + vninode = kzalloc(sizeof(*vninode), GFP_KERNEL); + if (!vninode) + return NULL; + vninode->stats = netdev_alloc_pcpu_stats(struct vxlan_vni_stats_pcpu); + if (!vninode->stats) { + kfree(vninode); + return NULL; + } + vninode->vni = vni; + vninode->hlist4.vxlan = vxlan; +#if IS_ENABLED(CONFIG_IPV6) + vninode->hlist6.vxlan = vxlan; +#endif + + return vninode; +} + +static void vxlan_vni_free(struct vxlan_vni_node *vninode) +{ + free_percpu(vninode->stats); + kfree(vninode); +} + +static int vxlan_vni_add(struct vxlan_dev *vxlan, + struct vxlan_vni_group *vg, + u32 vni, union vxlan_addr *group, + struct netlink_ext_ack *extack) +{ + struct vxlan_vni_node *vninode; + __be32 v = cpu_to_be32(vni); + bool changed = false; + int err = 0; + + if (vxlan_vnifilter_lookup(vxlan, v)) + return vxlan_vni_update(vxlan, vg, v, group, &changed, extack); + + err = vxlan_vni_in_use(vxlan->net, vxlan, &vxlan->cfg, v); + if (err) { + NL_SET_ERR_MSG(extack, "VNI in use"); + return err; + } + + vninode = vxlan_vni_alloc(vxlan, v); + if (!vninode) + return -ENOMEM; + + err = rhashtable_lookup_insert_fast(&vg->vni_hash, + &vninode->vnode, + vxlan_vni_rht_params); + if (err) { + vxlan_vni_free(vninode); + return err; + } + + __vxlan_vni_add_list(vg, vninode); + + if (vxlan->dev->flags & IFF_UP) + vxlan_vs_add_del_vninode(vxlan, vninode, false); + + err = vxlan_vni_update_group(vxlan, vninode, group, true, &changed, + extack); + + if (changed) + vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL); + + return err; +} + +static void vxlan_vni_node_rcu_free(struct rcu_head *rcu) +{ + struct vxlan_vni_node *v; + + v = container_of(rcu, struct vxlan_vni_node, rcu); + vxlan_vni_free(v); +} + +static int vxlan_vni_del(struct vxlan_dev *vxlan, + struct vxlan_vni_group *vg, + u32 vni, struct netlink_ext_ack *extack) +{ + struct vxlan_vni_node *vninode; + __be32 v = cpu_to_be32(vni); + int err = 0; + + vg = rtnl_dereference(vxlan->vnigrp); + + vninode = rhashtable_lookup_fast(&vg->vni_hash, &v, + vxlan_vni_rht_params); + if (!vninode) { + err = -ENOENT; + goto out; + } + + vxlan_vni_delete_group(vxlan, vninode); + + err = rhashtable_remove_fast(&vg->vni_hash, + &vninode->vnode, + vxlan_vni_rht_params); + if (err) + goto out; + + __vxlan_vni_del_list(vg, vninode); + + vxlan_vnifilter_notify(vxlan, vninode, RTM_DELTUNNEL); + + if (vxlan->dev->flags & IFF_UP) + vxlan_vs_add_del_vninode(vxlan, vninode, true); + + call_rcu(&vninode->rcu, vxlan_vni_node_rcu_free); + + return 0; +out: + return err; +} + +static int vxlan_vni_add_del(struct vxlan_dev *vxlan, __u32 start_vni, + __u32 end_vni, union vxlan_addr *group, + int cmd, struct netlink_ext_ack *extack) +{ + struct vxlan_vni_group *vg; + int v, err = 0; + + vg = rtnl_dereference(vxlan->vnigrp); + + for (v = start_vni; v <= end_vni; v++) { + switch (cmd) { + case RTM_NEWTUNNEL: + err = vxlan_vni_add(vxlan, vg, v, group, extack); + break; + case RTM_DELTUNNEL: + err = vxlan_vni_del(vxlan, vg, v, extack); + break; + default: + err = -EOPNOTSUPP; + break; + } + if (err) + goto out; + } + + return 0; +out: + return err; +} + +static int vxlan_process_vni_filter(struct vxlan_dev *vxlan, + struct nlattr *nlvnifilter, + int cmd, struct netlink_ext_ack *extack) +{ + struct nlattr *vattrs[VXLAN_VNIFILTER_ENTRY_MAX + 1]; + u32 vni_start = 0, vni_end = 0; + union vxlan_addr group; + int err; + + err = nla_parse_nested(vattrs, + VXLAN_VNIFILTER_ENTRY_MAX, + nlvnifilter, vni_filter_entry_policy, + extack); + if (err) + return err; + + if (vattrs[VXLAN_VNIFILTER_ENTRY_START]) { + vni_start = nla_get_u32(vattrs[VXLAN_VNIFILTER_ENTRY_START]); + vni_end = vni_start; + } + + if (vattrs[VXLAN_VNIFILTER_ENTRY_END]) + vni_end = nla_get_u32(vattrs[VXLAN_VNIFILTER_ENTRY_END]); + + if (!vni_start && !vni_end) { + NL_SET_ERR_MSG_ATTR(extack, nlvnifilter, + "vni start nor end found in vni entry"); + return -EINVAL; + } + + if (vattrs[VXLAN_VNIFILTER_ENTRY_GROUP]) { + group.sin.sin_addr.s_addr = + nla_get_in_addr(vattrs[VXLAN_VNIFILTER_ENTRY_GROUP]); + group.sa.sa_family = AF_INET; + } else if (vattrs[VXLAN_VNIFILTER_ENTRY_GROUP6]) { + group.sin6.sin6_addr = + nla_get_in6_addr(vattrs[VXLAN_VNIFILTER_ENTRY_GROUP6]); + group.sa.sa_family = AF_INET6; + } else { + memset(&group, 0, sizeof(group)); + } + + if (vxlan_addr_multicast(&group) && !vxlan->default_dst.remote_ifindex) { + NL_SET_ERR_MSG(extack, + "Local interface required for multicast remote group"); + + return -EINVAL; + } + + err = vxlan_vni_add_del(vxlan, vni_start, vni_end, &group, cmd, + extack); + if (err) + return err; + + return 0; +} + +void vxlan_vnigroup_uninit(struct vxlan_dev *vxlan) +{ + struct vxlan_vni_node *v, *tmp; + struct vxlan_vni_group *vg; + + vg = rtnl_dereference(vxlan->vnigrp); + list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { + rhashtable_remove_fast(&vg->vni_hash, &v->vnode, + vxlan_vni_rht_params); + hlist_del_init_rcu(&v->hlist4.hlist); +#if IS_ENABLED(CONFIG_IPV6) + hlist_del_init_rcu(&v->hlist6.hlist); +#endif + __vxlan_vni_del_list(vg, v); + vxlan_vnifilter_notify(vxlan, v, RTM_DELTUNNEL); + call_rcu(&v->rcu, vxlan_vni_node_rcu_free); + } + rhashtable_destroy(&vg->vni_hash); + kfree(vg); +} + +int vxlan_vnigroup_init(struct vxlan_dev *vxlan) +{ + struct vxlan_vni_group *vg; + int ret; + + vg = kzalloc(sizeof(*vg), GFP_KERNEL); + if (!vg) + return -ENOMEM; + ret = rhashtable_init(&vg->vni_hash, &vxlan_vni_rht_params); + if (ret) { + kfree(vg); + return ret; + } + INIT_LIST_HEAD(&vg->vni_list); + rcu_assign_pointer(vxlan->vnigrp, vg); + + return 0; +} + +static int vxlan_vnifilter_process(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct tunnel_msg *tmsg; + struct vxlan_dev *vxlan; + struct net_device *dev; + struct nlattr *attr; + int err, vnis = 0; + int rem; + + /* this should validate the header and check for remaining bytes */ + err = nlmsg_parse(nlh, sizeof(*tmsg), NULL, VXLAN_VNIFILTER_MAX, + vni_filter_policy, extack); + if (err < 0) + return err; + + tmsg = nlmsg_data(nlh); + dev = __dev_get_by_index(net, tmsg->ifindex); + if (!dev) + return -ENODEV; + + if (!netif_is_vxlan(dev)) { + NL_SET_ERR_MSG_MOD(extack, "The device is not a vxlan device"); + return -EINVAL; + } + + vxlan = netdev_priv(dev); + + if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) + return -EOPNOTSUPP; + + nlmsg_for_each_attr(attr, nlh, sizeof(*tmsg), rem) { + switch (nla_type(attr)) { + case VXLAN_VNIFILTER_ENTRY: + err = vxlan_process_vni_filter(vxlan, attr, + nlh->nlmsg_type, extack); + break; + default: + continue; + } + vnis++; + if (err) + break; + } + + if (!vnis) { + NL_SET_ERR_MSG_MOD(extack, "No vnis found to process"); + err = -EINVAL; + } + + return err; +} + +void vxlan_vnifilter_init(void) +{ + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETTUNNEL, NULL, + vxlan_vnifilter_dump, 0); + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWTUNNEL, + vxlan_vnifilter_process, NULL, 0); + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELTUNNEL, + vxlan_vnifilter_process, NULL, 0); +} + +void vxlan_vnifilter_uninit(void) +{ + rtnl_unregister(PF_BRIDGE, RTM_GETTUNNEL); + rtnl_unregister(PF_BRIDGE, RTM_NEWTUNNEL); + rtnl_unregister(PF_BRIDGE, RTM_DELTUNNEL); +} -- cgit v1.2.3