diff options
Diffstat (limited to 'drivers/net/vxlan/vxlan_core.c')
-rw-r--r-- | drivers/net/vxlan/vxlan_core.c | 222 |
1 files changed, 153 insertions, 69 deletions
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 78744549c1b3..e463f59e95c2 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -623,6 +623,32 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, 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, @@ -649,26 +675,24 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, return vh; } -static struct sk_buff *vxlan_gro_receive(struct sock *sk, - struct list_head *head, - struct sk_buff *skb) +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 *pp = NULL; struct sk_buff *p; struct vxlanhdr *vh, *vh2; unsigned int hlen, off_vx; - int flush = 1; struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk); __be32 flags; - struct gro_remcsum grc; - skb_gro_remcsum_init(&grc); + 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)) - goto out; + return NULL; skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); @@ -676,12 +700,12 @@ static struct sk_buff *vxlan_gro_receive(struct sock *sk, 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, + vh->vx_vni, grc, !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); if (!vh) - goto out; + return NULL; } skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ @@ -698,12 +722,48 @@ static struct sk_buff *vxlan_gro_receive(struct sock *sk, } } - pp = call_gro_receive(eth_gro_receive, head, skb); - flush = 0; + return vh; +} -out: +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; } @@ -715,6 +775,21 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) 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) @@ -1525,35 +1600,6 @@ out: unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS; } -static bool vxlan_parse_gpe_hdr(struct vxlanhdr *unparsed, - __be16 *protocol, - struct sk_buff *skb, u32 vxflags) -{ - struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)unparsed; - - /* 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; - - unparsed->vx_flags &= ~VXLAN_GPE_USED_BITS; - return true; -} - static bool vxlan_set_mac(struct vxlan_dev *vxlan, struct vxlan_sock *vs, struct sk_buff *skb, __be32 vni) @@ -1655,8 +1701,9 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) * used by VXLAN extensions if explicitly requested. */ if (vs->flags & VXLAN_F_GPE) { - if (!vxlan_parse_gpe_hdr(&unparsed, &protocol, skb, vs->flags)) + if (!vxlan_parse_gpe_proto(&unparsed, &protocol)) goto drop; + unparsed.vx_flags &= ~VXLAN_GPE_USED_BITS; raw_proto = true; } @@ -2281,14 +2328,11 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan, __be32 vni, bool snoop) { - struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; struct net_device *dev; int len = skb->len; - tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); - rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; @@ -2314,17 +2358,11 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); - u64_stats_update_begin(&tx_stats->syncp); - u64_stats_inc(&tx_stats->tx_packets); - u64_stats_add(&tx_stats->tx_bytes, len); - u64_stats_update_end(&tx_stats->syncp); + 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) { - u64_stats_update_begin(&rx_stats->syncp); - u64_stats_inc(&rx_stats->rx_packets); - u64_stats_add(&rx_stats->rx_bytes, len); - u64_stats_update_end(&rx_stats->syncp); + dev_sw_netstats_rx_add(dst_vxlan->dev, len); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); } else { @@ -2516,7 +2554,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } ndst = &rt->dst; - err = skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM, + 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; @@ -2577,7 +2615,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto out_unlock; } - err = skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM, + 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; @@ -2672,6 +2711,45 @@ drop: 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. @@ -2687,6 +2765,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) struct vxlan_fdb *f; struct ethhdr *eth; __be32 vni = 0; + u32 nhid = 0; info = skb_tunnel_info(skb); @@ -2696,6 +2775,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) 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); @@ -2723,6 +2803,9 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) #endif } + if (nhid) + return vxlan_xmit_nhid(skb, dev, nhid, vni); + if (vxlan->cfg.flags & VXLAN_F_MDB) { struct vxlan_mdb_entry *mdb_entry; @@ -2989,14 +3072,12 @@ static int vxlan_change_mtu(struct net_device *dev, int new_mtu) struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); - bool use_ipv6 = !!(vxlan->cfg.flags & VXLAN_F_IPV6); /* 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 - - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); + int max_mtu = lowerdev->mtu - vxlan_headroom(vxlan->cfg.flags); if (new_mtu > max_mtu) return -EINVAL; } @@ -3379,8 +3460,13 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, tunnel_cfg.encap_rcv = vxlan_rcv; tunnel_cfg.encap_err_lookup = vxlan_err_lookup; tunnel_cfg.encap_destroy = NULL; - tunnel_cfg.gro_receive = vxlan_gro_receive; - tunnel_cfg.gro_complete = vxlan_gro_complete; + 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); @@ -3644,11 +3730,11 @@ static void vxlan_config_apply(struct net_device *dev, struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; unsigned short needed_headroom = ETH_HLEN; - bool use_ipv6 = !!(conf->flags & VXLAN_F_IPV6); int max_mtu = ETH_MAX_MTU; + u32 flags = conf->flags; if (!changelink) { - if (conf->flags & VXLAN_F_GPE) + if (flags & VXLAN_F_GPE) vxlan_raw_setup(dev); else vxlan_ether_setup(dev); @@ -3673,8 +3759,7 @@ static void vxlan_config_apply(struct net_device *dev, dev->needed_tailroom = lowerdev->needed_tailroom; - max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : - VXLAN_HEADROOM); + max_mtu = lowerdev->mtu - vxlan_headroom(flags); if (max_mtu < ETH_MIN_MTU) max_mtu = ETH_MIN_MTU; @@ -3685,10 +3770,9 @@ static void vxlan_config_apply(struct net_device *dev, if (dev->mtu > max_mtu) dev->mtu = max_mtu; - if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA) - needed_headroom += VXLAN6_HEADROOM; - else - needed_headroom += VXLAN_HEADROOM; + 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)); |