vxlan: defer vxlan init as late as possible
Subsystems (3)
PATCH v2 1/4 vxlan: defer vxlan init as late as possible
From: Cong Wang <[email protected]>
When vxlan is compiled as builtin, its init code runs before IPv6 init, this could cause problems if we create IPv6 socket in the latter patch.
--- drivers/net/vxlan.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-)
drivers/net/vxlan.c +1 -1
@@ -1619,7 +1619,7 @@ out2: out1:return rc; } -module_init (vxlan_init_module); +late_initcall (vxlan_init_module); static void __exit vxlan_cleanup_module(void) {
Signature · 1 line
1.7.7.6
PATCH v2 2/4 ipv6: export ipv6_sock_mc_join and ipv6_sock_mc_drop
From: Cong Wang <[email protected]>
They will be used by vxlan module.
--- net/ipv6/mcast.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)
net/ipv6/mcast.c +2 -0
@@ -200,6 +200,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)return 0 ; } +EXPORT_SYMBOL (ipv6_sock_mc_join);/* * socket leave on multicast group
@@ -246,6 +247,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)return -EADDRNOTAVAIL ; } +EXPORT_SYMBOL (ipv6_sock_mc_drop);/* called with rcu_read_lock() */ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
Signature · 1 line
1.7.7.6
PATCH v2 3/4 vxlan: add ipv6 support
In reply to Cong WangFrom: Cong Wang <[email protected]>
v2: fix some compile error when !CONFIG_IPV6
improve some code based by Stephen's comments use sockaddr suggested by David
This patch adds IPv6 support to vxlan device, as the new version RFC already mentioned it:
http://tools.ietf.org/html/draft-mahalingam-dutt-dcops-vxlan-03
--- drivers/net/vxlan.c | 573 +++++++++++++++++++++++++++++++++--------- include/uapi/linux/if_link.h | 2 + 2 files changed, 453 insertions(+), 122 deletions(-)
drivers/net/vxlan.c +451 -122
@@ -9,7 +9,6 @@* * TODO * - use IANA UDP port number (when defined) -* - IPv6 (not in RFC) */ #define pr_fmt (fmt) KBUILD_MODNAME ": " fmt
@@ -42,6 +41,11 @@#include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#if IS_ENABLED (CONFIG_IPV6 ) +#include <net/addrconf.h> +#include <net/ip6_route.h> +#include <net/ip6_tunnel.h> +#endif #define VXLAN_VERSION "0.1"
@@ -56,6 +60,7 @@#define VXLAN_VID_MASK (VXLAN_N_VID - 1)/* IP header + UDP + VXLAN + Ethernet header */ #define VXLAN_HEADROOM (20 + 8 + 8 + 14) +#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)#define VXLAN_FLAGS 0x08000000/* struct vxlanhdr.vx_flags required value. */
@@ -81,9 +86,22 @@ struct vxlan_net {struct hlist_head vni_list[VNI_HASH_SIZE ]; }; +struct vxlan_ip { +union { +struct sockaddr_in sin; +#if IS_ENABLED (CONFIG_IPV6 ) +struct sockaddr_in6 sin6; +#endif +struct sockaddr sa; + } u; +#define ip4 u.sin.sin_addr.s_addr +#define ip6 u.sin6.sin6_addr +#define proto u.sa.sa_family +}; +struct vxlan_rdst {struct rcu_head rcu; -__be32 remote_ip; +struct vxlan_ip remote_ip;__be16 remote_port;u32 remote_vni;u32 remote_ifindex;
@@ -106,8 +124,8 @@ struct vxlan_dev {struct hlist_node hlist;struct net_device *dev;__u32 vni;/* virtual network id */ -__be32 gaddr;/* multicast group */ -__be32 saddr;/* source address */ +struct vxlan_ip gaddr;/* multicast group */ +struct vxlan_ip saddr;/* source address */ unsigned int link;/* link to multicast over */ __u16 port_min;/* source port range */ __u16 port_max;
@@ -130,6 +148,80 @@ struct vxlan_dev {#define VXLAN_F_L2MISS 0x08#define VXLAN_F_L3MISS 0x10 +#if IS_ENABLED (CONFIG_IPV6 ) +static inline bool vxlan_ip_equal (const struct vxlan_ip *a,const struct vxlan_ip *b) +{ +if (a->proto != b->proto) +return false; +switch (a->proto) { +case AF_INET : +return a->ip4 == b->ip4; +case AF_INET6 : +return ipv6_addr_equal (&a->ip6, &b->ip6); + } +return false; +} + +static inline bool vxlan_ip_any (const struct vxlan_ip *ipa) +{ +if (ipa->proto ==AF_INET ) +return ipa->ip4 ==htonl (INADDR_ANY ); +else +return ipv6_addr_any (&ipa->ip6); +} + +static int vxlan_nla_get_addr (struct vxlan_ip *ip,struct nlattr *nla) +{ +if (nla_len (nla) ==sizeof (__be32)) { + ip->ip4 =nla_get_be32 (nla); + ip->proto =AF_INET ; + }else if (nla_len (nla) ==sizeof (struct in6_addr )) { +nla_memcpy (&ip->ip6, nla,sizeof (struct in6_addr )); + ip->proto =AF_INET6 ; + }else +return -EAFNOSUPPORT ; +return 0 ; +} + +static int vxlan_nla_put_addr (struct sk_buff *skb,int attr,const struct vxlan_ip *ip) +{ +if (ip->proto ==AF_INET ) +return nla_put_be32 (skb, attr, ip->ip4); +else if (ip->proto ==AF_INET6 ) +return nla_put (skb, attr,sizeof (struct in6_addr ), &ip->ip6); +else +return -EAFNOSUPPORT ; +} +#else +static inline bool vxlan_ip_equal (const struct vxlan_ip *a,const struct vxlan_ip *b) +{ +return a->ip4 == b->ip4; +} + +static inline bool vxlan_ip_any (const struct vxlan_ip *ipa) +{ +return ipa->ip4 ==htonl (INADDR_ANY ); +} + +static int vxlan_nla_get_addr (struct vxlan_ip *ip,struct nlattr *nla) +{ +if (nla_len (nla) ==sizeof (__be32)) { + ip->ip4 =nla_get_be32 (nla); + ip->proto =AF_INET ; +return 0 ; + }else +return -EAFNOSUPPORT ; +} + +static int vxlan_nla_put_addr (struct sk_buff *skb,int attr,const struct vxlan_ip *ip) +{ +if (ip->proto ==AF_INET ) +return nla_put_be32 (skb, attr, ip->ip4); +else +return -EAFNOSUPPORT ; +} +#endif +/* salt for hash table */ static u32 vxlan_salt__read_mostly ;
@@ -176,7 +268,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,if (type ==RTM_GETNEIGH ) { ndm->ndm_family =AF_INET ; - send_ip = rdst->remote_ip !=htonl (INADDR_ANY ); + send_ip = !vxlan_ip_any (&rdst->remote_ip); send_eth = !is_zero_ether_addr (fdb->eth_addr); }else ndm->ndm_family =AF_BRIDGE ;
@@ -188,7 +280,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,if (send_eth &&nla_put (skb,NDA_LLADDR ,ETH_ALEN , &fdb->eth_addr)) goto nla_put_failure; -if (send_ip &&nla_put_be32 (skb,NDA_DST , rdst->remote_ip)) +if (send_ip &&vxlan_nla_put_addr (skb,NDA_DST , &rdst->remote_ip)) goto nla_put_failure; if (rdst->remote_port && rdst->remote_port != vxlan_port &&
@@ -220,7 +312,7 @@ static inline size_t vxlan_nlmsg_size(void) {return NLMSG_ALIGN (sizeof (struct ndmsg )) +nla_total_size (ETH_ALEN )/* NDA_LLADDR */ - +nla_total_size (sizeof (__be32))/* NDA_DST */ + +nla_total_size (sizeof (struct in6_addr ))/* NDA_DST */ +nla_total_size (sizeof (__be32))/* NDA_PORT */ +nla_total_size (sizeof (__be32))/* NDA_VNI */ +nla_total_size (sizeof (__u32))/* NDA_IFINDEX */
@@ -253,14 +345,14 @@ errout:rtnl_set_sk_err (net,RTNLGRP_NEIGH , err); } -static void vxlan_ip_miss (struct net_device *dev,__be32 ipa) +static void vxlan_ip_miss (struct net_device *dev,struct vxlan_ip *ipa) {struct vxlan_dev *vxlan =netdev_priv (dev);struct vxlan_fdb f;memset (&f,0 ,sizeof f); f.state =NUD_STALE ; - f.remote.remote_ip = ipa;/* goes to NDA_DST */ + f.remote.remote_ip = *ipa;/* goes to NDA_DST */ f.remote.remote_vni =VXLAN_N_VID ;vxlan_fdb_notify (vxlan, &f,RTM_GETNEIGH );
@@ -316,13 +408,13 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,/* Add/update destinations for multicast */ static int vxlan_fdb_append (struct vxlan_fdb *f, -__be32 ip,__u32 port,__u32 vni,__u32 ifindex) +struct vxlan_ip *ip,__u32 port,__u32 vni,__u32 ifindex) {struct vxlan_rdst *rd_prev, *rd; rd_prev =NULL ;for (rd = &f->remote; rd; rd = rd->remote_next) { -if (rd->remote_ip == ip && +if (vxlan_ip_equal (&rd->remote_ip, ip) && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex)
@@ -332,7 +424,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, rd =kmalloc (sizeof (*rd),GFP_ATOMIC );if (rd ==NULL )return -ENOBUFS ; - rd->remote_ip = ip; + rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex;
@@ -343,7 +435,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,/* Add new entry to forwarding table -- assumes lock held */ static int vxlan_fdb_create (struct vxlan_dev *vxlan, -const u8 *mac,__be32 ip, +const u8 *mac,struct vxlan_ip *ip,__u16 state,__u16 flags,__u32 port,__u32 vni,__u32 ifindex) {
@@ -383,7 +475,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,return -ENOMEM ; notify =1 ; - f->remote.remote_ip = ip; + f->remote.remote_ip = *ip; f->remote.remote_port = port; f->remote.remote_vni = vni; f->remote.remote_ifindex = ifindex;
@@ -435,7 +527,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], {struct vxlan_dev *vxlan =netdev_priv (dev);struct net *net =dev_net (vxlan->dev); -__be32 ip; +struct vxlan_ip ip;u32 port, vni, ifindex;int err;
@@ -448,10 +540,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],if (tb[NDA_DST ] ==NULL )return -EINVAL ; -if (nla_len (tb[NDA_DST ]) !=sizeof (__be32)) -return -EAFNOSUPPORT ; - - ip =nla_get_be32 (tb[NDA_DST ]); + err =vxlan_nla_get_addr (&ip, tb[NDA_DST ]); +if (err) +return err;if (tb[NDA_PORT ]) {if (nla_len (tb[NDA_PORT ]) !=sizeof (u32))
@@ -481,7 +572,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], ifindex =0 ;spin_lock_bh (&vxlan->hash_lock); - err =vxlan_fdb_create (vxlan, addr, ip, ndm->ndm_state, flags, port, + err =vxlan_fdb_create (vxlan, addr, &ip, ndm->ndm_state, flags, port, vni, ifindex);spin_unlock_bh (&vxlan->hash_lock);
@@ -545,7 +636,7 @@ skip:* and Tunnel endpoint. */ static void vxlan_snoop (struct net_device *dev, -__be32 src_ip,const u8 *src_mac) +struct vxlan_ip *src_ip,const u8 *src_mac) {struct vxlan_dev *vxlan =netdev_priv (dev);struct vxlan_fdb *f;
@@ -554,7 +645,7 @@ static void vxlan_snoop(struct net_device *dev, f =vxlan_find_mac (vxlan, src_mac);if (likely (f)) { f->used = jiffies; -if (likely (f->remote.remote_ip == src_ip)) +if (likely (vxlan_ip_equal (&f->remote.remote_ip, src_ip)))return ;if (net_ratelimit ())
@@ -562,7 +653,7 @@ static void vxlan_snoop(struct net_device *dev,"%pM migrated from %pI4 to %pI4\n" , src_mac, &f->remote.remote_ip, &src_ip); - f->remote.remote_ip = src_ip; + f->remote.remote_ip = *src_ip; f->updated = jiffies; }else {/* learned new entry */
@@ -591,7 +682,7 @@ static bool vxlan_group_used(struct vxlan_net *vn,if (!netif_running (vxlan->dev))continue ; -if (vxlan->gaddr == this->gaddr) +if (vxlan_ip_equal (&vxlan->gaddr, &this->gaddr))return true; }
@@ -605,7 +696,7 @@ static int vxlan_join_group(struct net_device *dev)struct vxlan_net *vn =net_generic (dev_net (dev), vxlan_net_id);struct sock *sk = vn->sock->sk;struct ip_mreqn mreq = { - .imr_multiaddr.s_addr = vxlan->gaddr, + .imr_multiaddr.s_addr = vxlan->gaddr.ip4, .imr_ifindex = vxlan->link, };int err;
@@ -617,7 +708,14 @@ static int vxlan_join_group(struct net_device *dev)/* Need to drop RTNL to call multicast join */ rtnl_unlock ();lock_sock (sk); +#if IS_ENABLED (CONFIG_IPV6 ) +if (vxlan->gaddr.proto ==AF_INET ) + err =ip_mc_join_group (sk, &mreq); +else + err =ipv6_sock_mc_join (sk, vxlan->link, &vxlan->gaddr.ip6); +#else err =ip_mc_join_group (sk, &mreq); +#endif release_sock (sk);rtnl_lock ();
@@ -633,7 +731,7 @@ static int vxlan_leave_group(struct net_device *dev)int err =0 ;struct sock *sk = vn->sock->sk;struct ip_mreqn mreq = { - .imr_multiaddr.s_addr = vxlan->gaddr, + .imr_multiaddr.s_addr = vxlan->gaddr.ip4, .imr_ifindex = vxlan->link, };
@@ -644,7 +742,14 @@ static int vxlan_leave_group(struct net_device *dev)/* Need to drop RTNL to call multicast leave */ rtnl_unlock ();lock_sock (sk); +#if IS_ENABLED (CONFIG_IPV6 ) +if (vxlan->gaddr.proto ==AF_INET ) + err =ip_mc_leave_group (sk, &mreq); +else + err =ipv6_sock_mc_drop (sk, vxlan->link, &vxlan->gaddr.ip6); +#else err =ip_mc_leave_group (sk, &mreq); +#endif release_sock (sk);rtnl_lock ();
@@ -654,10 +759,14 @@ static int vxlan_leave_group(struct net_device *dev)/* Callback from net/ipv4/udp.c to receive packets */ static int vxlan_udp_encap_recv (struct sock *sk,struct sk_buff *skb) { -struct iphdr *oip; +struct iphdr *oip =NULL ; +#if IS_ENABLED (CONFIG_IPV6 ) +struct ipv6hdr *oip6 =NULL ; +#endif struct vxlanhdr *vxh;struct vxlan_dev *vxlan;struct pcpu_tstats *stats; +struct vxlan_ip src_ip;__u32 vni;int err;
@@ -696,7 +805,13 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)skb_reset_mac_header (skb);/* Re-examine inner Ethernet packet */ - oip =ip_hdr (skb); +if (skb->protocol ==htons (ETH_P_IP )) + oip =ip_hdr (skb); +#if IS_ENABLED (CONFIG_IPV6 ) + else + oip6 =ipv6_hdr (skb); +#endif + skb->protocol =eth_type_trans (skb, vxlan->dev);/* Ignore packet loops (and multicast echo) */
@@ -704,8 +819,19 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) vxlan->dev->dev_addr) == 0) goto drop; -if (vxlan->flags &VXLAN_F_LEARN ) -vxlan_snoop (skb->dev, oip->saddr,eth_hdr (skb)->h_source); +if (vxlan->flags &VXLAN_F_LEARN ) { +if (oip) { + src_ip.ip4 = oip->saddr; + src_ip.proto =AF_INET ; + } +#if IS_ENABLED (CONFIG_IPV6 ) +if (oip6) { + src_ip.ip6 = oip6->saddr; + src_ip.proto =AF_INET6 ; + } +#endif +vxlan_snoop (skb->dev, &src_ip,eth_hdr (skb)->h_source); + }__skb_tunnel_rx (skb, vxlan->dev);skb_reset_network_header (skb);
@@ -721,15 +847,32 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) skb->encapsulation =0 ; - err =IP_ECN_decapsulate (oip, skb); -if (unlikely (err)) { -if (log_ecn_error) -net_info_ratelimited ("non-ECT from %pI4 with TOS=%#x\n" , - &oip->saddr, oip->tos); -if (err >1 ) { - ++vxlan->dev->stats.rx_frame_errors; - ++vxlan->dev->stats.rx_errors; - goto drop; +#if IS_ENABLED (CONFIG_IPV6 ) +if (oip6) { + err =IP6_ECN_decapsulate (oip6, skb); +if (unlikely (err)) { +if (log_ecn_error) +net_info_ratelimited ("non-ECT from %pI4\n" , + &oip6->saddr); +if (err >1 ) { + ++vxlan->dev->stats.rx_frame_errors; + ++vxlan->dev->stats.rx_errors; + goto drop; + } + } + } +#endif +if (oip) { + err =IP_ECN_decapsulate (oip, skb); +if (unlikely (err)) { +if (log_ecn_error) +net_info_ratelimited ("non-ECT from %pI4 with TOS=%#x\n" , + &oip->saddr, oip->tos); +if (err >1 ) { + ++vxlan->dev->stats.rx_frame_errors; + ++vxlan->dev->stats.rx_errors; + goto drop; + } } }
@@ -760,6 +903,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)u8 *arpptr, *sha;__be32 sip, tip;struct neighbour *n; +struct vxlan_ip ipa;if (dev->flags &IFF_NOARP ) goto out;
@@ -801,7 +945,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) } f =vxlan_find_mac (vxlan, n->ha); -if (f && f->remote.remote_ip ==htonl (INADDR_ANY )) { +if (f &&vxlan_ip_any (&f->remote.remote_ip)) {/* bridge-local neighbor */ neigh_release (n); goto out;
@@ -819,8 +963,11 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)if (netif_rx_ni (reply) ==NET_RX_DROP ) dev->stats.rx_dropped++; - }else if (vxlan->flags &VXLAN_F_L3MISS ) -vxlan_ip_miss (dev, tip); + }else if (vxlan->flags &VXLAN_F_L3MISS ) { + ipa.ip4 = tip; + ipa.proto =AF_INET ; +vxlan_ip_miss (dev, &ipa); + } out:consume_skb (skb);return NETDEV_TX_OK ;
@@ -842,6 +989,14 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)return false; pip =ip_hdr (skb); n =neigh_lookup (&arp_tbl, &pip->daddr, dev); +if (!n && vxlan->flags &VXLAN_F_L3MISS ) { +struct vxlan_ip ipa; + ipa.ip4 = pip->daddr; + ipa.proto =AF_INET ; +vxlan_ip_miss (dev, &ipa); +return false; + } +break ;default :return false;
@@ -858,8 +1013,8 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) }neigh_release (n);return diff; - }else if (vxlan->flags &VXLAN_F_L3MISS ) -vxlan_ip_miss (dev, pip->daddr); + } +return false; }
@@ -869,7 +1024,8 @@ static void vxlan_sock_free(struct sk_buff *skb) }/* On transmit, associate with the tunnel socket */ -static void vxlan_set_owner (struct net_device *dev,struct sk_buff *skb) +static inline void vxlan_set_owner (struct net_device *dev, +struct sk_buff *skb) {struct vxlan_net *vn =net_generic (dev_net (dev), vxlan_net_id);struct sock *sk = vn->sock->sk;
@@ -917,23 +1073,30 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, {struct vxlan_dev *vxlan =netdev_priv (dev);struct rtable *rt; -const struct iphdr *old_iph; +const struct iphdr *old_iph =NULL ;struct iphdr *iph;struct vxlanhdr *vxh;struct udphdr *uh;struct flowi4 fl4; +#if IS_ENABLED (CONFIG_IPV6 ) +struct flowi6 fl6; +struct vxlan_net *vn =net_generic (dev_net (dev), vxlan_net_id); +struct sock *sk = vn->sock->sk; +struct ipv6hdr *ip6h; +#endif unsigned int pkt_len = skb->len; -__be32 dst; -__u16 src_port, dst_port; +const struct vxlan_ip *dst; +struct dst_entry *ndst =NULL ; +__u16 src_port =0 , dst_port;u32 vni;__be16 df =0 ;__u8 tos, ttl; dst_port = rdst->remote_port ? rdst->remote_port : vxlan_port; vni = rdst->remote_vni; - dst = rdst->remote_ip; + dst = &rdst->remote_ip; -if (!dst) { +if (vxlan_ip_any (dst)) {if (did_rsc) {__skb_pull (skb,skb_network_offset (skb)); skb->ip_summed =CHECKSUM_NONE ;
@@ -961,47 +1124,86 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, skb->encapsulation =1 ; } -/* Need space for new headers (invalidates iph ptr) */ -if (skb_cow_head (skb,VXLAN_HEADROOM )) - goto drop; + ttl = vxlan->ttl; + tos = vxlan->tos; +if (dst->proto ==AF_INET ) { +/* Need space for new headers (invalidates iph ptr) */ +if (skb_cow_head (skb,VXLAN_HEADROOM )) + goto drop; - old_iph =ip_hdr (skb); + old_iph =ip_hdr (skb); +if (!ttl &&IN_MULTICAST (ntohl (dst->ip4))) + ttl =1 ; - ttl = vxlan->ttl; -if (!ttl &&IN_MULTICAST (ntohl (dst))) - ttl =1 ; +if (tos ==1 ) + tos =ip_tunnel_get_dsfield (old_iph, skb); - tos = vxlan->tos; -if (tos ==1 ) - tos =ip_tunnel_get_dsfield (old_iph, skb); - - src_port =vxlan_src_port (vxlan, skb); - -memset (&fl4,0 ,sizeof (fl4)); - fl4.flowi4_oif = rdst->remote_ifindex; - fl4.flowi4_tos =RT_TOS (tos); - fl4.daddr = dst; - fl4.saddr = vxlan->saddr; - - rt =ip_route_output_key (dev_net (dev), &fl4); -if (IS_ERR (rt)) { -netdev_dbg (dev,"no route to %pI4\n" , &dst); - dev->stats.tx_carrier_errors++; - goto tx_error; - } + src_port =vxlan_src_port (vxlan, skb); + +memset (&fl4,0 ,sizeof (fl4)); + fl4.flowi4_oif = rdst->remote_ifindex; + fl4.flowi4_tos =RT_TOS (tos); + fl4.daddr = dst->ip4; + fl4.saddr = vxlan->saddr.ip4; + + rt =ip_route_output_key (dev_net (dev), &fl4); +if (IS_ERR (rt)) { +netdev_dbg (dev,"no route to %pI4\n" , &dst->ip4); + dev->stats.tx_carrier_errors++; + goto tx_error; + } + +if (rt->dst.dev == dev) { +netdev_dbg (dev,"circular route to %pI4\n" , &dst->ip4); +ip_rt_put (rt); + dev->stats.collisions++; + goto tx_error; + } + ndst = &rt->dst; +memset (&(IPCB (skb)->opt),0 ,sizeof (IPCB (skb)->opt)); + }else { +#if IS_ENABLED (CONFIG_IPV6 ) +const struct ipv6hdr *old_iph6; + +/* Need space for new headers (invalidates iph ptr) */ +if (skb_cow_head (skb,VXLAN6_HEADROOM )) + goto drop; + + old_iph6 =ipv6_hdr (skb); +if (!ttl &&ipv6_addr_is_multicast (&dst->ip6)) + ttl =1 ; -if (rt->dst.dev == dev) { -netdev_dbg (dev,"circular route to %pI4\n" , &dst); -ip_rt_put (rt); - dev->stats.collisions++; - goto tx_error; +if (tos ==1 ) + tos =ipv6_get_dsfield (old_iph6); + + src_port =vxlan_src_port (vxlan, skb); + +memset (&fl6,0 ,sizeof (fl6)); + fl6.flowi6_oif = vxlan->link; + fl6.flowi6_tos =RT_TOS (tos); + fl6.daddr = dst->ip6; + fl6.saddr = vxlan->saddr.ip6; + fl6.flowi6_proto = skb->protocol; + +if (ip6_dst_lookup (sk, &ndst, &fl6)) { +netdev_dbg (dev,"no route to %pI6\n" , &dst->ip6); + dev->stats.tx_carrier_errors++; + goto tx_error; + } + +if (ndst->dev == dev) { +netdev_dbg (dev,"circular route to %pI6\n" , &dst->ip6); +dst_release (ndst); + dev->stats.collisions++; + goto tx_error; + } +#endif } -memset (&(IPCB (skb)->opt),0 ,sizeof (IPCB (skb)->opt));IPCB (skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE |IPSKB_XFRM_TRANSFORMED |IPSKB_REROUTED );skb_dst_drop (skb); -skb_dst_set (skb, &rt->dst); +skb_dst_set (skb, ndst); vxh = (struct vxlanhdr *)__skb_push (skb,sizeof (*vxh)); vxh->vx_flags =htonl (VXLAN_FLAGS );
@@ -1017,27 +1219,55 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, uh->len =htons (skb->len); uh->check =0 ; -__skb_push (skb,sizeof (*iph)); -skb_reset_network_header (skb); - iph =ip_hdr (skb); - iph->version =4 ; - iph->ihl =sizeof (struct iphdr ) >>2 ; - iph->frag_off = df; - iph->protocol =IPPROTO_UDP ; - iph->tos =ip_tunnel_ecn_encap (tos, old_iph, skb); - iph->daddr = dst; - iph->saddr = fl4.saddr; - iph->ttl = ttl ? :ip4_dst_hoplimit (&rt->dst); -tunnel_ip_select_ident (skb, old_iph, &rt->dst); - -nf_reset (skb); +if (dst->proto ==AF_INET ) { +__skb_push (skb,sizeof (*iph)); +skb_reset_network_header (skb); + iph =ip_hdr (skb); + iph->version =4 ; + iph->ihl =sizeof (struct iphdr ) >>2 ; + iph->frag_off = df; + iph->protocol =IPPROTO_UDP ; + iph->tos =ip_tunnel_ecn_encap (tos, old_iph, skb); + iph->daddr = dst->ip4; + iph->saddr = fl4.saddr; + iph->ttl = ttl ? :ip4_dst_hoplimit (ndst); +tunnel_ip_select_ident (skb, old_iph, ndst); + }else { +#if IS_ENABLED (CONFIG_IPV6 ) +if (skb->ip_summed ==CHECKSUM_PARTIAL ) { + skb->csum_start =skb_transport_header (skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr , check); + }else + uh->check =csum_ipv6_magic (&fl6.saddr, &fl6.daddr, + skb->len,IPPROTO_UDP , +csum_partial (uh, skb->len,0 )); +__skb_push (skb,sizeof (*ip6h)); +skb_reset_network_header (skb); + ip6h =ipv6_hdr (skb); + ip6h->version =6 ; + ip6h->priority =0 ; + ip6h->flow_lbl[0 ] =0 ; + ip6h->flow_lbl[1 ] =0 ; + ip6h->flow_lbl[2 ] =0 ; + ip6h->payload_len =htons (skb->len); + ip6h->nexthdr =IPPROTO_UDP ; + ip6h->hop_limit = ttl ? :ip6_dst_hoplimit (ndst); + ip6h->daddr = fl6.daddr; + ip6h->saddr = fl6.saddr; +#endif + }vxlan_set_owner (dev, skb);if (handle_offloads (skb)) goto drop; -iptunnel_xmit (skb, dev); +if (dst->proto ==AF_INET ) +iptunnel_xmit (skb, dev); +#if IS_ENABLED (CONFIG_IPV6 ) + else +ip6tunnel_xmit (skb ,dev ); +#endif return NETDEV_TX_OK ; drop:
@@ -1084,7 +1314,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) group.remote_next =0 ; rdst0 = &group; -if (group.remote_ip ==htonl (INADDR_ANY ) && +if (vxlan_ip_any (&group.remote_ip) && (vxlan->flags &VXLAN_F_L2MISS ) && !is_multicast_ether_addr (eth->h_dest))vxlan_fdb_miss (vxlan, eth->h_dest);
@@ -1162,7 +1392,7 @@ static int vxlan_open(struct net_device *dev)struct vxlan_dev *vxlan =netdev_priv (dev);int err; -if (vxlan->gaddr) { +if (!vxlan_ip_any (&vxlan->gaddr)) { err =vxlan_join_group (dev);if (err)return err;
@@ -1196,7 +1426,7 @@ static int vxlan_stop(struct net_device *dev) {struct vxlan_dev *vxlan =netdev_priv (dev); -if (vxlan->gaddr) +if (!vxlan_ip_any (&vxlan->gaddr))vxlan_leave_group (dev);del_timer_sync (&vxlan->age_timer);
@@ -1246,7 +1476,10 @@ static void vxlan_setup(struct net_device *dev)eth_hw_addr_random (dev);ether_setup (dev); - dev->hard_header_len =ETH_HLEN +VXLAN_HEADROOM ; +if (vxlan->gaddr.proto ==AF_INET ) + dev->hard_header_len =ETH_HLEN +VXLAN_HEADROOM ; +else + dev->hard_header_len =ETH_HLEN +VXLAN6_HEADROOM ; dev->netdev_ops = &vxlan_netdev_ops; dev->destructor = vxlan_free;
@@ -1283,8 +1516,10 @@ static void vxlan_setup(struct net_device *dev)static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX +1 ] = { [IFLA_VXLAN_ID ] = { .type =NLA_U32 }, [IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VXLAN_GROUP6 ] = { .len =sizeof (struct in6_addr ) }, [IFLA_VXLAN_LINK ] = { .type =NLA_U32 }, [IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, + [IFLA_VXLAN_LOCAL6 ] = { .len =sizeof (struct in6_addr ) }, [IFLA_VXLAN_TOS ] = { .type =NLA_U8 }, [IFLA_VXLAN_TTL ] = { .type =NLA_U8 }, [IFLA_VXLAN_LEARNING ] = { .type =NLA_U8 },
@@ -1326,6 +1561,17 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])pr_debug ("group address is not IPv4 multicast\n" );return -EADDRNOTAVAIL ; } + }else if (data[IFLA_VXLAN_GROUP6 ]) { +#if IS_ENABLED (CONFIG_IPV6 ) +struct in6_addr gaddr; +nla_memcpy (&gaddr, data[IFLA_VXLAN_GROUP6 ],sizeof (struct in6_addr )); +if (!ipv6_addr_is_multicast (&gaddr)) { +pr_debug ("group address is not IPv6 multicast\n" ); +return -EADDRNOTAVAIL ; + } +#else +return -EPFNOSUPPORT ; +#endif }if (data[IFLA_VXLAN_PORT_RANGE ]) {
@@ -1371,11 +1617,29 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, } vxlan->vni = vni; -if (data[IFLA_VXLAN_GROUP ]) - vxlan->gaddr =nla_get_be32 (data[IFLA_VXLAN_GROUP ]); +if (data[IFLA_VXLAN_GROUP ]) { + vxlan->gaddr.ip4 =nla_get_be32 (data[IFLA_VXLAN_GROUP ]); + vxlan->gaddr.proto =AF_INET ; + }else if (data[IFLA_VXLAN_GROUP6 ]) { +#if IS_ENABLED (CONFIG_IPV6 ) +nla_memcpy (&vxlan->gaddr.ip6, data[IFLA_VXLAN_GROUP6 ],sizeof (struct in6_addr )); + vxlan->gaddr.proto =AF_INET6 ; +#else +return -EPFNOSUPPORT ; +#endif + } -if (data[IFLA_VXLAN_LOCAL ]) - vxlan->saddr =nla_get_be32 (data[IFLA_VXLAN_LOCAL ]); +if (data[IFLA_VXLAN_LOCAL ]) { + vxlan->saddr.ip4 =nla_get_be32 (data[IFLA_VXLAN_GROUP ]); + vxlan->saddr.proto =AF_INET ; + }else if (data[IFLA_VXLAN_LOCAL6 ]) { +#if IS_ENABLED (CONFIG_IPV6 ) +nla_memcpy (&vxlan->saddr.ip6, data[IFLA_VXLAN_GROUP6 ],sizeof (struct in6_addr )); + vxlan->saddr.proto =AF_INET6 ; +#else +return -EPFNOSUPPORT ; +#endif + }if (data[IFLA_VXLAN_LINK ] && (vxlan->link =nla_get_u32 (data[IFLA_VXLAN_LINK ]))) {
@@ -1453,9 +1717,9 @@ static size_t vxlan_get_size(const struct net_device *dev) {return nla_total_size (sizeof (__u32)) +/* IFLA_VXLAN_ID */ -nla_total_size (sizeof (__be32)) +/* IFLA_VXLAN_GROUP */ +nla_total_size (sizeof (struct in6_addr )) +/* IFLA_VXLAN_GROUP{6} */ nla_total_size (sizeof (__u32)) +/* IFLA_VXLAN_LINK */ -nla_total_size (sizeof (__be32))+/* IFLA_VXLAN_LOCAL */ +nla_total_size (sizeof (struct in6_addr )) +/* IFLA_VXLAN_LOCAL{6} */ nla_total_size (sizeof (__u8)) +/* IFLA_VXLAN_TTL */ nla_total_size (sizeof (__u8)) +/* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */
@@ -1480,14 +1744,32 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)if (nla_put_u32 (skb,IFLA_VXLAN_ID , vxlan->vni)) goto nla_put_failure; -if (vxlan->gaddr &&nla_put_be32 (skb,IFLA_VXLAN_GROUP , vxlan->gaddr)) - goto nla_put_failure; +if (!vxlan_ip_any (&vxlan->gaddr)) { +if (vxlan->gaddr.proto ==AF_INET ) { +if (nla_put_be32 (skb,IFLA_VXLAN_GROUP , vxlan->gaddr.ip4)) + goto nla_put_failure; + }else { +#if IS_ENABLED (CONFIG_IPV6 ) +if (nla_put (skb,IFLA_VXLAN_GROUP6 ,sizeof (struct in6_addr ), &vxlan->gaddr.ip6)) + goto nla_put_failure; +#endif + } + }if (vxlan->link &&nla_put_u32 (skb,IFLA_VXLAN_LINK , vxlan->link)) goto nla_put_failure; -if (vxlan->saddr &&nla_put_be32 (skb,IFLA_VXLAN_LOCAL , vxlan->saddr)) - goto nla_put_failure; +if (!vxlan_ip_any (&vxlan->saddr)) { +if (vxlan->saddr.proto ==AF_INET ) { +if (nla_put_be32 (skb,IFLA_VXLAN_LOCAL , vxlan->saddr.ip4)) + goto nla_put_failure; + }else { +#if IS_ENABLED (CONFIG_IPV6 ) +if (nla_put (skb,IFLA_VXLAN_LOCAL6 ,sizeof (struct in6_addr ), &vxlan->saddr.ip6)) + goto nla_put_failure; +#endif + } + } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) ||
@@ -1526,38 +1808,82 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = { .fill_info = vxlan_fill_info, }; -static __net_init int vxlan_init_net (struct net *net) +/* Create UDP socket for encapsulation receive. AF_INET6 sockets +* could be used for both IPv4 and IPv6 communications. +*/ +#if IS_ENABLED (CONFIG_IPV6 ) +static __net_init int create_sock (struct net *net,struct sock **sk) +{ +struct vxlan_net *vn =net_generic (net, vxlan_net_id); +struct sockaddr_in6 vxlan_addr = { + .sin6_family =AF_INET6 , + .sin6_port =htons (vxlan_port), + }; +int rc; + + rc =sock_create_kern (AF_INET6 ,SOCK_DGRAM ,IPPROTO_UDP , &vn->sock); +if (rc <0 ) { +pr_debug ("UDP socket create failed\n" ); +return rc; + } +/* Put in proper namespace */ + *sk = vn->sock->sk; +sk_change_net (*sk, net); + + rc =kernel_bind (vn->sock, (struct sockaddr *)&vxlan_addr, +sizeof (struct sockaddr_in6 )); +if (rc <0 ) { +pr_debug ("bind for UDP socket %pI6:%u (%d)\n" , + &vxlan_addr.sin6_addr,ntohs (vxlan_addr.sin6_port), rc); +sk_release_kernel (*sk); + vn->sock =NULL ; +return rc; + } +return 0 ; +} +#else +static __net_init int create_sock (struct net *net,struct sock **sk) {struct vxlan_net *vn =net_generic (net, vxlan_net_id); -struct sock *sk;struct sockaddr_in vxlan_addr = { .sin_family =AF_INET , + .sin_port =htons (vxlan_port), .sin_addr.s_addr =htonl (INADDR_ANY ), };int rc; -unsigned h; -/* Create UDP socket for encapsulation receive. */ rc =sock_create_kern (AF_INET ,SOCK_DGRAM ,IPPROTO_UDP , &vn->sock);if (rc <0 ) {pr_debug ("UDP socket create failed\n" );return rc; }/* Put in proper namespace */ - sk = vn->sock->sk; -sk_change_net (sk, net); + *sk = vn->sock->sk; +sk_change_net (*sk, net); - vxlan_addr.sin_port =htons (vxlan_port); - - rc =kernel_bind (vn->sock, (struct sockaddr *) &vxlan_addr, -sizeof (vxlan_addr)); + rc =kernel_bind (vn->sock, (struct sockaddr *)&vxlan_addr, +sizeof (struct sockaddr_in ));if (rc <0 ) {pr_debug ("bind for UDP socket %pI4:%u (%d)\n" , &vxlan_addr.sin_addr,ntohs (vxlan_addr.sin_port), rc); -sk_release_kernel (sk); +sk_release_kernel (*sk); vn->sock =NULL ;return rc; } +return 0 ; +} +#endif + +static __net_init int vxlan_init_net (struct net *net) +{ +struct vxlan_net *vn =net_generic (net, vxlan_net_id); +struct sock *sk; +int rc; +unsigned h; + + rc =create_sock (net, &sk); +if (rc <0 ) +return rc;/* Disable multicast loopback */ inet_sk (sk)->mc_loop =0 ;
@@ -1566,6 +1892,9 @@ static __net_init int vxlan_init_net(struct net *net)udp_sk (sk)->encap_type =1 ;udp_sk (sk)->encap_rcv = vxlan_udp_encap_recv;udp_encap_enable (); +#if IS_ENABLED (CONFIG_IPV6 ) +udpv6_encap_enable (); +#endif for (h =0 ; h <VNI_HASH_SIZE ; ++h)INIT_HLIST_HEAD (&vn->vni_list[h]);
include/uapi/linux/if_link.h +2 -0
@@ -308,6 +308,8 @@ enum {IFLA_VXLAN_RSC ,IFLA_VXLAN_L2MISS ,IFLA_VXLAN_L3MISS , +IFLA_VXLAN_GROUP6 , +IFLA_VXLAN_LOCAL6 , __IFLA_VXLAN_MAX };#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
Signature · 1 line
1.7.7.6
Re: [Patch net-next v2 3/4] vxlan: add ipv6 support
Cong Wang <[email protected]> wrote on 04/05/2013 08:16:24 AM:
drivers/net/vxlan.c struct vxlan_net { · line 101
Quoted 13 lines
drivers/net/vxlan.c +13
-0+struct vxlan_ip { +union { +struct sockaddr_in sin; +#if IS_ENABLED (CONFIG_IPV6 ) +struct sockaddr_in6 sin6; +#endif +struct sockaddr sa; + } u; +#define ip4 u.sin.sin_addr.s_addr +#define ip6 u.sin6.sin6_addr +#define proto u.sa.sa_family +}; +
I'd prefer:
1) all #defines at the same level in the union/struct -- you have a) a field within an in6_addr struct, b) a in6_addr struct and c) a field within a sockaddr -- all at a different level in the union/struct
2) union tags the odd names and the defines indicating the type and also not something likely to appear as a variable name (ie, maybe sun_sin6 for the union and vip_sin6 for the #define)
3) a family (e.g. AF_INET6) is not a proto (e.g. IPPROTO_IPV6)
4) "vxlan_ip" sounds like an ipv4 type to me -- maybe "vxlan_addr"?
5) I'd leave out the #ifdef; I believe sockaddr_in6 is defined without CONFIG_IPV6. I may me wrong on that, and it makes it bigger for v4-only configs, but fewer #ifdefs makes maintenance easier and there's an advantage in it always being the same size; this one is more a matter of taste.
So:
struct vxlan_addr {
union {
struct sockaddr_in sun_sin
struct sockaddr_in6 sun_sin6;
struct sockaddr sun_sa;
} sun;
}#define vip_sin sun.sin
#define vip_sin6 sun.sin6
#define vip_sa sun.sa
As it is, you're trying to hide that it's a sockaddr, which makes the code more difficult to read in context. "vip_sa.sa_family" is obviously the sa_family field of a sockaddr, "proto" could be lots of things.
Quoted 12 lines
(quoted diff) +2
-0+#if IS_ENABLED(CONFIG_IPV6) +static inline bool vxlan_ip_equal(const struct vxlan_ip *a, conststruct
vxlan_ip*b)drivers/net/vxlan.c +9
-0+{ +if (a->proto != b->proto) +return false; +switch (a->proto) { +case AF_INET : +return a->ip4 == b->ip4; +case AF_INET6 : +return ipv6_addr_equal (&a->ip6, &b->ip6); + }
drivers/net/vxlan.c struct vxlan_dev { · line 171
Quoted 10 lines
drivers/net/vxlan.c +10
-0+return false; +} + +static inline bool vxlan_ip_any (const struct vxlan_ip *ipa) +{ +if (ipa->proto ==AF_INET ) +return ipa->ip4 ==htonl (INADDR_ANY ); +else +return ipv6_addr_any (&ipa->ip6); +}
I think these functions shouldn't be under the #ifdef; ifCONFIG_IPV6 is not set, you'll never have AF_INET6. Also, if you zero everything on allocation, you can use "memcmp" on the whole thing and don't need to check family and addresses separately or explicitly, or use ipv6_addr_equal() with a CONFIG_IPV6 dependency.
drivers/net/vxlan.c struct vxlan_dev { · line 184
Quoted 13 lines
drivers/net/vxlan.c +13
-0+ +static int vxlan_nla_get_addr (struct vxlan_ip *ip,struct nlattr *nla) +{ +if (nla_len (nla) ==sizeof (__be32)) { + ip->ip4 =nla_get_be32 (nla); + ip->proto =AF_INET ; + }else if (nla_len (nla) ==sizeof (struct in6_addr )) { +nla_memcpy (&ip->ip6, nla,sizeof (struct in6_addr )); + ip->proto =AF_INET6 ; + }else +return -EAFNOSUPPORT ; +return 0 ; +}
netlink messages use padding -- I'm not sure nla_len() will
be correct in all cases here. I think using a sockaddr here too would be better (then the family tells you the address type), as long as that doesn't create include issues Dave mentioned within the "ip" and "bridge" commands. Otherwise, maybe use a different NL type for v6.
Another reason to do this is that link-local v6 addresses
require a scope_id and matching addresses are only equal if the interfaces are equal. You need to get that from user level and compare it in address matching, too, but it is in the sockaddr_in6 so if you set it there, memcmp() will cover that as well.
drivers/net/vxlan.c struct vxlan_dev { · line 161
Quoted 5 lines
+static inline bool
vxlan_ip_equal(const struct vxlan_ip *a, const struct vxlan_ip *b)drivers/net/vxlan.c +3
-0+{ +return a->ip4 == b->ip4; +}
Again, shouldn't have entirely separate function for v4;
either use memcmp() on the whole thing, or just #ifdef the v6 case in the switch.
drivers/net/vxlan.c struct vxlan_dev { · line 171
Quoted 5 lines
drivers/net/vxlan.c +5
-0+ +static inline bool vxlan_ip_any (const struct vxlan_ip *ipa) +{ +return ipa->ip4 ==htonl (INADDR_ANY ); +}
ditto. And also for nla_get/put funcs.
drivers/net/vxlan.c static int vxlan_join_group(struct net_device *dev) · line 718
Quoted 12 lines
drivers/net/vxlan.c +7
-0@@ -617,7 +708,14 @@ static int vxlan_join_group(struct net_device *dev)/* Need to drop RTNL to call multicast join */ rtnl_unlock ();lock_sock (sk); +#if IS_ENABLED (CONFIG_IPV6 ) +if (vxlan->gaddr.proto ==AF_INET ) + err =ip_mc_join_group (sk, &mreq); +else + err =ipv6_sock_mc_join (sk, vxlan->link, &vxlan->gaddr.ip6); +#else err =ip_mc_join_group (sk, &mreq); +#endif
#if IS_ENABLED(CONFIG_IPV6)
if (vxlan->gaddr.proto == AF_INET6)
err = ipv6_sock_mc_join....
else#endif
err = ip_mc_join_group..
Review static int vxlan_leave_group(struct net_device
Quoted 1 line
(quoted diff) +0
-0@@ -644,7 +742,14 @@ static int vxlan_leave_group(struct net_device
*dev)
drivers/net/vxlan.c static int vxlan_leave_group(struct net_device *dev) · line 754
Quoted 13 lines
drivers/net/vxlan.c +7
-0/* Need to drop RTNL to call multicast leave */ rtnl_unlock ();lock_sock (sk); +#if IS_ENABLED (CONFIG_IPV6 ) +if (vxlan->gaddr.proto ==AF_INET ) + err =ip_mc_leave_group (sk, &mreq); +else + err =ipv6_sock_mc_drop (sk, vxlan->link, &vxlan->gaddr.ip6); +#else err =ip_mc_leave_group (sk, &mreq); +#endif release_sock (sk);rtnl_lock ();
Again, arrange as above so only one instance of v4 leave
and #ifdefs for the optional v6 code.
drivers/net/vxlan.c static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) · line 855
Quoted 6 lines
drivers/net/vxlan.c +6
-0+#if IS_ENABLED (CONFIG_IPV6 ) +if (oip6) { + err =IP6_ECN_decapsulate (oip6, skb); +if (unlikely (err)) { +if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI4\n",
%pI6
Quoted 12 lines
drivers/net/vxlan.c +12
-0+ &oip6->saddr); +if (err >1 ) { + ++vxlan->dev->stats.rx_frame_errors; + ++vxlan->dev->stats.rx_errors; + goto drop; + } + } + } +#endif +if (oip) { + err =IP_ECN_decapsulate (oip, skb); +if (unlikely (err)) {
drivers/net/vxlan.c static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) · line 877
Quoted 10 lines
drivers/net/vxlan.c +8
-0+if (log_ecn_error) +net_info_ratelimited ("non-ECT from %pI4 with TOS=%#x\n" , + &oip->saddr, oip->tos); +if (err >1 ) { + ++vxlan->dev->stats.rx_frame_errors; + ++vxlan->dev->stats.rx_errors; + goto drop; + } } }
These are duplicated sections of code -- would rather
see one common section for stats based on err, though the logging would still need an ifdef.
I think the IP v6/v4 header and routing code can be refactored better -- maybe separate functions to handle each, since it's all one or the other.
+-DLS
Re: [Patch net-next v2 3/4] vxlan: add ipv6 support
Quoted 18 lines · David Stevens
Cong Wang <[email protected]> wrote on 04/05/2013 08:16:24 AM:
drivers/net/vxlan.c struct vxlan_net { · line 101
Quoted 13 lines
drivers/net/vxlan.c +13
-0+struct vxlan_ip { +union { +struct sockaddr_in sin; +#if IS_ENABLED (CONFIG_IPV6 ) +struct sockaddr_in6 sin6; +#endif +struct sockaddr sa; + } u; +#define ip4 u.sin.sin_addr.s_addr +#define ip6 u.sin6.sin6_addr +#define proto u.sa.sa_family +}; +I'd prefer:
Quoted 4 lines
1) all #defines at the same level in the union/struct -- you have a) a field within an
in6_addrstruct, b) ain6_addrstruct and c) a field within a sockaddr -- all at a different level in the union/struct
Why? They are aliases of the fields, so should stay inside the union/struct.
Quoted 3 lines
2) union tags the odd names and the defines indicating the type and also not something likely to appear as a variable name (ie, maybe
sun_sin6for the union andvip_sin6for the #define)
Why "sun_" prefix?
Quoted 1 line
3) a family (e.g.
AF_INET6) is not a proto (e.g.IPPROTO_IPV6)
Agreed, s/proto/family/.
Quoted 1 line
4) "
vxlan_ip" sounds like an ipv4 type to me -- maybe "vxlan_addr"?
Agreed.
Quoted 6 lines
5) I'd leave out the #ifdef; I believe
sockaddr_in6is defined withoutCONFIG_IPV6. I may me wrong on that, and it makes it bigger for v4-only configs, but fewer #ifdefs makes maintenance easier and there's an advantage in it always being the same size; this one is more a matter of taste.
Yeah, you are right.
Quoted 9 lines
So:
struct vxlan_addr { union { struct sockaddr_in sun_sin struct sockaddr_in6 sun_sin6; struct sockaddr sun_sa; } sun; }
Quoted 9 lines
#define
vip_sinsun.sin
#definevip_sin6sun.sin6
#definevip_sasun.saAs it is, you're trying to hide that it's a sockaddr, which makes the code more difficult to read in context. "vip_sa.sa_family" is obviously the
sa_familyfield of a sockaddr, "proto" could be lots of things.
No, I just want to keep them short. I don't think "vip_sin6" is better than "ip6".
Quoted 12 lines
Quoted 12 lines
drivers/net/vxlan.c +12
-0+ +static int vxlan_nla_get_addr (struct vxlan_ip *ip,struct nlattr *nla) +{ +if (nla_len (nla) ==sizeof (__be32)) { + ip->ip4 =nla_get_be32 (nla); + ip->proto =AF_INET ; + }else if (nla_len (nla) ==sizeof (struct in6_addr )) { +nla_memcpy (&ip->ip6, nla,sizeof (struct in6_addr )); + ip->proto =AF_INET6 ; + }else +return -EAFNOSUPPORT ; +return 0 ;
Quoted 8 lines
Quoted 1 line
+}
netlink messages use padding -- I'm not sure
nla_len()will
be correct in all cases here. I think using a sockaddr here too would be better (then the family tells you the address type), as long as that doesn't create include issues Dave mentioned within the "ip" and "bridge" commands. Otherwise, maybe use a different NL type for v6.
At least Thomas doesn't object this, although he pointed out the same thing.
Quoted 6 lines
Another reason to do this is that link-local v6 addresses
require ascope_idand matching addresses are only equal if the interfaces are equal. You need to get that from user level and compare it in address matching, too, but it is in thesockaddr_in6so if you set it there,memcmp()will cover that as well.
It is not convenient to zero the whole struct just for memcmp(), just compare the part we need is sufficient.
All the rest you point out are all fixed in v3.
Thanks for review!
PATCH v2 4/4 ipv6: Add generic UDP Tunnel segmentation
In reply to Cong WangFrom: Cong Wang <[email protected]>
Similar to commit 731362674580cb0c696cd1b1a03d8461a10cf90a (tunneling: Add generic Tunnel segmentation)
This patch adds generic tunneling offloading support for IPv6-UDP based tunnels.
This can be used by tunneling protocols like VXLAN.
--- net/ipv6/ip6_offload.c | 4 +- net/ipv6/udp_offload.c | 155 +++++++++++++++++++++++++++++++++--------------- 2 files changed, 110 insertions(+), 49 deletions(-)
net/ipv6/ip6_offload.c +3 -1
@@ -91,6 +91,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,unsigned int unfrag_ip6hlen;u8 *prevhdr;int offset =0 ; +bool tunnel; if (unlikely(skb_shinfo(skb)->gso_type & ~(SKB_GSO_UDP |
@@ -105,6 +106,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,if (unlikely (!pskb_may_pull (skb,sizeof (*ipv6h)))) goto out; + tunnel = !!skb->encapsulation; ipv6h =ipv6_hdr (skb);__skb_pull (skb,sizeof (*ipv6h)); segs =ERR_PTR (-EPROTONOSUPPORT );
@@ -125,7 +127,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, ipv6h =ipv6_hdr (skb); ipv6h->payload_len =htons (skb->len - skb->mac_len -sizeof (*ipv6h)); -if (proto ==IPPROTO_UDP ) { +if (!tunnel && proto ==IPPROTO_UDP ) { unfrag_ip6hlen =ip6_find_1stfragopt (skb, &prevhdr); fptr = (struct frag_hdr *)(skb_network_header (skb) + unfrag_ip6hlen);
net/ipv6/udp_offload.c +107 -48
176 lines not on this page · raw message
Signature · 1 line
1.7.7.6
PATCH 1/1 vxlan: add ipv6 support
In reply to Cong WangFrom: Cong Wang <[email protected]>
--- include/linux/if_link.h | 2 ++ ip/iplink_vxlan.c | 45 ++++++++++++++++++++++++++++++++++++++------- 2 files changed, 40 insertions(+), 7 deletions(-)
include/linux/if_link.h +2 -0
@@ -306,6 +306,8 @@ enum {IFLA_VXLAN_RSC ,IFLA_VXLAN_L2MISS ,IFLA_VXLAN_L3MISS , +IFLA_VXLAN_GROUP6 , +IFLA_VXLAN_LOCAL6 , __IFLA_VXLAN_MAX };#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
ip/iplink_vxlan.c +38 -7
79 lines not on this page · raw message
Signature · 1 line
1.7.7.6