vxlan: add ipv6 support
Subsystems (5)
v12 cover vxlan: add ipv6 support
From: Cong Wang <[email protected]>
v12: move the EXPORT_SYMBOL inside #ifdef
v11: some coding tyle fix, based on Stephen's comments
remove a useless WARN_ON()
drop scope id patch, leave it to David add a new patch to unify skb_udp_tunnel_segment() make ip6_dst_hoplimit() not inlined
v10: rebase on the latest net-next
fix a deadlock, which didn't exist before
fix another compile error when IPV6=m
some cleanup
v9: rebase on the latest net-next
adjust coding style to make DaveM happy merge disable_ipv6 patch into the previous one add a cleanup patch
v8: fix the bug when bindv6only=1
fix more compile errors when IPV6=m
complete the rest missing features for IPv6
v7: respect disable_ipv6 flag
back to ipv4 only when ipv6 is not supported
v6: use a stub for IPv6 mcast functions
split a few more long lines
rebased on the latest net-next
v5: make David happy on the names of the fields
fix my mistake during rebasing the patches
drop the scope_id patch, because it is broken
export in6addr_loopback
fix a udp checksum bug
rebased on the latest net-next
v4: rename ->sin to ->va_sin
rename ->sin6 to ->va_sin6
rename ->family to ->va_sa
support ll addr
fix more ugly #ifdef
rebased on the latest net-next
v3: fix many coding style issues
fix some ugly #ifdef
rename vxlan_ip to vxlan_addr
rename ->proto to ->family
rename ->ip4/->ip6 to ->sin/->sin6
v2: fix some compile error when !CONFIG_IPV6
improve some code based on Stephen's comments
use sockaddr suggested by David
Cong Wang (11):
ipv6: move ip6_dst_hoplimit() into core kernel
ipv6: move ip6_local_out into core kernel
ipv6: export a stub for IPv6 symbols used by vxlan
ipv6: export in6addr_loopback to modules
ipv6: do not call ndisc_send_rs() with write lock
vxlan: add ipv6 support
vxlan: add ipv6 route short circuit support
ipv6: move in6_dev_finish_destroy() into core kernel
vxlan: add ipv6 proxy support
ipv6: Add generic UDP Tunnel segmentation
net: unify skb_udp_tunnel_segment() and skb_udp6_tunnel_segment()
drivers/net/vxlan.c | 876 ++++++++++++++++++++++++++++++++++------- include/net/addrconf.h | 20 + include/net/ip6_route.h | 2 - include/net/ipv6.h | 2 + include/net/ndisc.h | 5 + include/net/vxlan.h | 2 +- include/uapi/linux/if_link.h | 2 + net/ipv4/udp.c | 13 +- net/ipv6/addrconf.c | 49 +-- net/ipv6/addrconf_core.c | 50 +++ net/ipv6/af_inet6.c | 14 + net/ipv6/ip6_offload.c | 4 +- net/ipv6/ip6_output.c | 25 -- net/ipv6/ndisc.c | 8 +- net/ipv6/output_core.c | 48 +++ net/ipv6/route.c | 19 - net/ipv6/udp_offload.c | 105 +++--- net/openvswitch/vport-vxlan.c | 2 +- 18 files changed, 949 insertions(+), 297 deletions(-)
Signature · 1 line
1.7.7.6
PATCH v12 1/11 ipv6: move ip6_dst_hoplimit() into core kernel
From: Cong Wang <[email protected]>
It will be used by vxlan, and may not be inlined.
--- include/net/ip6_route.h | 2 -- include/net/ipv6.h | 2 ++ net/ipv6/output_core.c | 22 ++++++++++++++++++++++ net/ipv6/route.c | 19 ------------------- 4 files changed, 24 insertions(+), 21 deletions(-)
include/net/ip6_route.h +0 -2
@@ -112,8 +112,6 @@ extern struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,const struct in6_addr *addr, bool anycast); -extern int ip6_dst_hoplimit (struct dst_entry *dst); -/* * support functions for ND *
include/net/ipv6.h +2 -0
@@ -658,6 +658,8 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_addextern void ipv6_select_ident (struct frag_hdr *fhdr,struct rt6_info *rt); +extern int ip6_dst_hoplimit (struct dst_entry *dst); +/* * Header manipulation */
net/ipv6/output_core.c +22 -0
@@ -5,6 +5,7 @@#include <linux/export.h> #include <net/ipv6.h> #include <net/ip6_fib.h> +#include <net/addrconf.h> void ipv6_select_ident (struct frag_hdr *fhdr,struct rt6_info *rt) {
@@ -75,3 +76,24 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)return offset; }EXPORT_SYMBOL (ip6_find_1stfragopt); + +#if IS_ENABLED (CONFIG_IPV6 ) +int ip6_dst_hoplimit (struct dst_entry *dst) +{ +int hoplimit =dst_metric_raw (dst,RTAX_HOPLIMIT ); +if (hoplimit ==0 ) { +struct net_device *dev = dst->dev; +struct inet6_dev *idev; + +rcu_read_lock (); + idev =__in6_dev_get (dev); +if (idev) + hoplimit = idev->cnf.hop_limit; +else + hoplimit =dev_net (dev)->ipv6.devconf_all->hop_limit; +rcu_read_unlock (); + } +return hoplimit; +} +EXPORT_SYMBOL (ip6_dst_hoplimit); +#endif
net/ipv6/route.c +0 -19
@@ -1354,25 +1354,6 @@ out:return entries > rt_max_size; } -int ip6_dst_hoplimit (struct dst_entry *dst) -{ -int hoplimit =dst_metric_raw (dst,RTAX_HOPLIMIT ); -if (hoplimit ==0 ) { -struct net_device *dev = dst->dev; -struct inet6_dev *idev; - -rcu_read_lock (); - idev =__in6_dev_get (dev); -if (idev) - hoplimit = idev->cnf.hop_limit; -else - hoplimit =dev_net (dev)->ipv6.devconf_all->hop_limit; -rcu_read_unlock (); - } -return hoplimit; -} -EXPORT_SYMBOL (ip6_dst_hoplimit); -/* * */
Signature · 1 line
1.7.7.6
PATCH v12 2/11 ipv6: move ip6_local_out into core kernel
In reply to Cong WangFrom: Cong Wang <[email protected]>
It will be used the vxlan kernel module.
--- net/ipv6/ip6_output.c | 25 ------------------------- net/ipv6/output_core.c | 26 ++++++++++++++++++++++++++ 2 files changed, 26 insertions(+), 25 deletions(-)
net/ipv6/ip6_output.c +0 -25
@@ -56,31 +56,6 @@#include <net/checksum.h> #include <linux/mroute6.h> -int __ip6_local_out (struct sk_buff *skb) -{ -int len; - - len = skb->len -sizeof (struct ipv6hdr ); -if (len >IPV6_MAXPLEN ) - len =0 ; -ipv6_hdr (skb)->payload_len =htons (len); - -return nf_hook (NFPROTO_IPV6 ,NF_INET_LOCAL_OUT , skb,NULL , -skb_dst (skb)->dev, dst_output); -} - -int ip6_local_out (struct sk_buff *skb) -{ -int err; - - err =__ip6_local_out (skb); -if (likely (err ==1 )) - err =dst_output (skb); - -return err; -} -EXPORT_SYMBOL_GPL (ip6_local_out); -static int ip6_finish_output2 (struct sk_buff *skb) {struct dst_entry *dst =skb_dst (skb);
net/ipv6/output_core.c +26 -0
@@ -97,3 +97,29 @@ int ip6_dst_hoplimit(struct dst_entry *dst) }EXPORT_SYMBOL (ip6_dst_hoplimit);#endif + +int __ip6_local_out (struct sk_buff *skb) +{ +int len; + + len = skb->len -sizeof (struct ipv6hdr ); +if (len >IPV6_MAXPLEN ) + len =0 ; +ipv6_hdr (skb)->payload_len =htons (len); + +return nf_hook (NFPROTO_IPV6 ,NF_INET_LOCAL_OUT , skb,NULL , +skb_dst (skb)->dev, dst_output); +} +EXPORT_SYMBOL_GPL (__ip6_local_out); + +int ip6_local_out (struct sk_buff *skb) +{ +int err; + + err =__ip6_local_out (skb); +if (likely (err ==1 )) + err =dst_output (skb); + +return err; +} +EXPORT_SYMBOL_GPL (ip6_local_out);
Signature · 1 line
1.7.7.6
PATCH v12 3/11 ipv6: export a stub for IPv6 symbols used by vxlan
In reply to Cong WangFrom: Cong Wang <[email protected]>
In case IPv6 is compiled as a module, introduce a stub for ipv6_sock_mc_join and ipv6_sock_mc_drop etc.. It will be used by vxlan module. Suggested by Ben.
This is an ugly but easy solution for now.
--- include/net/addrconf.h | 15 +++++++++++++++ net/ipv6/addrconf_core.c | 3 +++ net/ipv6/af_inet6.c | 11 +++++++++++ 3 files changed, 29 insertions(+), 0 deletions(-)
include/net/addrconf.h +15 -0
@@ -141,6 +141,21 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr);void ipv6_mc_dad_complete (struct inet6_dev *idev); + +/* A stub used by vxlan module. This is ugly, ideally these +* symbols should be built into the core kernel. +*/ +struct ipv6_stub { +int (*ipv6_sock_mc_join)(struct sock *sk,int ifindex, +const struct in6_addr *addr); +int (*ipv6_sock_mc_drop)(struct sock *sk,int ifindex, +const struct in6_addr *addr); +int (*ipv6_dst_lookup)(struct sock *sk,struct dst_entry **dst, +struct flowi6 *fl6); +void (*udpv6_encap_enable)(void ); +}; +extern const struct ipv6_stub *ipv6_stub__read_mostly ; +/* * identify MLD packets for MLD filter exceptions */
net/ipv6/addrconf_core.c +3 -0
@@ -98,3 +98,6 @@ int inet6addr_notifier_call_chain(unsigned long val, void *v)return atomic_notifier_call_chain (&inet6addr_chain, val, v); }EXPORT_SYMBOL (inet6addr_notifier_call_chain); + +const struct ipv6_stub *ipv6_stub__read_mostly ; +EXPORT_SYMBOL_GPL (ipv6_stub);
net/ipv6/af_inet6.c +11 -0
@@ -810,6 +810,13 @@ static struct pernet_operations inet6_net_ops = { .exit = inet6_net_exit, }; +static const struct ipv6_stub ipv6_stub_impl = { + .ipv6_sock_mc_join = ipv6_sock_mc_join, + .ipv6_sock_mc_drop = ipv6_sock_mc_drop, + .ipv6_dst_lookup = ip6_dst_lookup, + .udpv6_encap_enable = udpv6_encap_enable, +}; +static int __init inet6_init (void ) {struct list_head *r;
@@ -884,6 +891,9 @@ static int __init inet6_init(void) err =igmp6_init ();if (err) goto igmp_fail; + + ipv6_stub = &ipv6_stub_impl; + err =ipv6_netfilter_init ();if (err) goto netfilter_fail;
@@ -1040,6 +1050,7 @@ static void __exit inet6_exit(void)raw6_proc_exit ();#endif ipv6_netfilter_fini (); + ipv6_stub =NULL ;igmp6_cleanup ();ndisc_cleanup ();ip6_mr_cleanup ();
Signature · 1 line
1.7.7.6
PATCH v12 4/11 ipv6: export in6addr_loopback to modules
In reply to Cong WangFrom: Cong Wang <[email protected]>
It is needed by vxlan module. Noticed by Mike.
--- net/ipv6/addrconf.c | 9 --------- net/ipv6/addrconf_core.c | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 9 deletions(-)
net/ipv6/addrconf.c +0 -9
@@ -245,15 +245,6 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .suppress_frag_ndisc = 1, }; -/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ -const struct in6_addr in6addr_any =IN6ADDR_ANY_INIT ; -const struct in6_addr in6addr_loopback =IN6ADDR_LOOPBACK_INIT ; -const struct in6_addr in6addr_linklocal_allnodes =IN6ADDR_LINKLOCAL_ALLNODES_INIT ; -const struct in6_addr in6addr_linklocal_allrouters =IN6ADDR_LINKLOCAL_ALLROUTERS_INIT ; -const struct in6_addr in6addr_interfacelocal_allnodes =IN6ADDR_INTERFACELOCAL_ALLNODES_INIT ; -const struct in6_addr in6addr_interfacelocal_allrouters =IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT ; -const struct in6_addr in6addr_sitelocal_allrouters =IN6ADDR_SITELOCAL_ALLROUTERS_INIT ; -/* Check if a valid qdisc is available */ static inline bool addrconf_qdisc_ok (const struct net_device *dev) {
net/ipv6/addrconf_core.c +16 -0
@@ -101,3 +101,19 @@ EXPORT_SYMBOL(inet6addr_notifier_call_chain);const struct ipv6_stub *ipv6_stub__read_mostly ;EXPORT_SYMBOL_GPL (ipv6_stub); + +/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ +const struct in6_addr in6addr_loopback =IN6ADDR_LOOPBACK_INIT ; +EXPORT_SYMBOL (in6addr_loopback); +const struct in6_addr in6addr_any =IN6ADDR_ANY_INIT ; +EXPORT_SYMBOL (in6addr_any); +const struct in6_addr in6addr_linklocal_allnodes =IN6ADDR_LINKLOCAL_ALLNODES_INIT ; +EXPORT_SYMBOL (in6addr_linklocal_allnodes); +const struct in6_addr in6addr_linklocal_allrouters =IN6ADDR_LINKLOCAL_ALLROUTERS_INIT ; +EXPORT_SYMBOL (in6addr_linklocal_allrouters); +const struct in6_addr in6addr_interfacelocal_allnodes =IN6ADDR_INTERFACELOCAL_ALLNODES_INIT ; +EXPORT_SYMBOL (in6addr_interfacelocal_allnodes); +const struct in6_addr in6addr_interfacelocal_allrouters =IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT ; +EXPORT_SYMBOL (in6addr_interfacelocal_allrouters); +const struct in6_addr in6addr_sitelocal_allrouters =IN6ADDR_SITELOCAL_ALLROUTERS_INIT ; +EXPORT_SYMBOL (in6addr_sitelocal_allrouters);
Signature · 1 line
1.7.7.6
PATCH v12 5/11 ipv6: do not call ndisc_send_rs() with write lock
In reply to Cong WangFrom: Cong Wang <[email protected]>
Because vxlan module will call ip6_dst_lookup() in TX path, which will hold write lock. So we have to release this write lock before calling ndisc_send_rs(), otherwise could deadlock.
--- net/ipv6/addrconf.c | 10 +++++++--- 1 files changed, 7 insertions(+), 3 deletions(-)
net/ipv6/addrconf.c +7 -3
@@ -3090,6 +3090,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)static void addrconf_rs_timer (unsigned long data) {struct inet6_dev *idev = (struct inet6_dev *)data; +struct net_device *dev = idev->dev;struct in6_addr lladdr;write_lock (&idev->lock);
@@ -3104,12 +3105,14 @@ static void addrconf_rs_timer(unsigned long data) goto out;if (idev->rs_probes++ < idev->cnf.rtr_solicits) { -if (!__ipv6_get_lladdr (idev, &lladdr,IFA_F_TENTATIVE )) -ndisc_send_rs (idev->dev, &lladdr, +write_unlock (&idev->lock); +if (!ipv6_get_lladdr (dev, &lladdr,IFA_F_TENTATIVE )) +ndisc_send_rs (dev, &lladdr, &in6addr_linklocal_allrouters);else - goto out; + goto put; +write_lock (&idev->lock);/* The wait after the last probe can be shorter */ addrconf_mod_rs_timer(idev, (idev->rs_probes == idev->cnf.rtr_solicits) ?
@@ -3125,6 +3128,7 @@ static void addrconf_rs_timer(unsigned long data) out:write_unlock (&idev->lock); +put:in6_dev_put (idev); }
Signature · 1 line
1.7.7.6
PATCH v12 6/11 vxlan: add ipv6 support
In reply to Cong WangFrom: Cong Wang <[email protected]>
This patch adds IPv6 support to vxlan device, as the new version RFC already mentions it:
http://tools.ietf.org/html/draft-mahalingam-dutt-dcops-vxlan-03
--- drivers/net/vxlan.c | 764 +++++++++++++++++++++++++++++++++-------- include/net/vxlan.h | 2 +- include/uapi/linux/if_link.h | 2 + net/openvswitch/vport-vxlan.c | 2 +- 4 files changed, 622 insertions(+), 148 deletions(-)
drivers/net/vxlan.c +618 -146
@@ -6,9 +6,6 @@* This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. -* -* TODO -* - IPv6 (not in RFC) */ #define pr_fmt (fmt) KBUILD_MODNAME ": " fmt
@@ -43,6 +40,11 @@#include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/vxlan.h> +#if IS_ENABLED (CONFIG_IPV6 ) +#include <net/ipv6.h> +#include <net/addrconf.h> +#include <net/ip6_tunnel.h> +#endif #define VXLAN_VERSION "0.1"
@@ -59,6 +61,8 @@#define VXLAN_VID_MASK (VXLAN_N_VID - 1)/* IP header + UDP + VXLAN + Ethernet header */ #define VXLAN_HEADROOM (20 + 8 + 8 + 14) +/* IPv6 header + UDP + VXLAN + Ethernet header */ +#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))#define VXLAN_FLAGS 0x08000000/* struct vxlanhdr.vx_flags required value. */
@@ -92,8 +96,14 @@ struct vxlan_net {spinlock_t sock_lock; }; +union vxlan_addr { +struct sockaddr_in sin; +struct sockaddr_in6 sin6; +struct sockaddr sa; +}; +struct vxlan_rdst { -__be32 remote_ip; +union vxlan_addr remote_ip;__be16 remote_port;u32 remote_vni;u32 remote_ifindex;
@@ -120,7 +130,7 @@ struct vxlan_dev {struct vxlan_sock *vn_sock;/* listening socket */ struct net_device *dev;struct vxlan_rdst default_dst;/* default destination */ -__be32 saddr;/* source address */ +union vxlan_addr saddr;/* source address */ __be16 dst_port;__u16 port_min;/* source port range */ __u16 port_max;
@@ -146,6 +156,7 @@ struct vxlan_dev {#define VXLAN_F_RSC 0x04#define VXLAN_F_L2MISS 0x08#define VXLAN_F_L3MISS 0x10 +#define VXLAN_F_IPV6 0x20/* internal flag */ /* salt for hash table */ static u32 vxlan_salt__read_mostly ;
@@ -153,6 +164,96 @@ static struct workqueue_struct *vxlan_wq;static void vxlan_sock_work (struct work_struct *work); +#if IS_ENABLED (CONFIG_IPV6 ) +static inline +bool vxlan_addr_equal (const union vxlan_addr *a,const union vxlan_addr *b) +{ +if (a->sa.sa_family != b->sa.sa_family) +return false; +if (a->sa.sa_family ==AF_INET6 ) +return ipv6_addr_equal (&a->sin6.sin6_addr, &b->sin6.sin6_addr); +else +return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr; +} + +static inline bool vxlan_addr_any (const union vxlan_addr *ipa) +{ +if (ipa->sa.sa_family ==AF_INET6 ) +return ipv6_addr_any (&ipa->sin6.sin6_addr); +else +return ipa->sin.sin_addr.s_addr ==htonl (INADDR_ANY ); +} + +static inline bool vxlan_addr_multicast (const union vxlan_addr *ipa) +{ +if (ipa->sa.sa_family ==AF_INET6 ) +return ipv6_addr_is_multicast (&ipa->sin6.sin6_addr); +else +return IN_MULTICAST (ntohl (ipa->sin.sin_addr.s_addr)); +} + +static int vxlan_nla_get_addr (union vxlan_addr *ip,struct nlattr *nla) +{ +if (nla_len (nla) >=sizeof (struct in6_addr )) { +nla_memcpy (&ip->sin6.sin6_addr, nla,sizeof (struct in6_addr )); + ip->sa.sa_family =AF_INET6 ; +return 0 ; + }else if (nla_len (nla) >=sizeof (__be32)) { + ip->sin.sin_addr.s_addr =nla_get_be32 (nla); + ip->sa.sa_family =AF_INET ; +return 0 ; + }else { +return -EAFNOSUPPORT ; + } +} + +static int vxlan_nla_put_addr (struct sk_buff *skb,int attr, +const union vxlan_addr *ip) +{ +if (ip->sa.sa_family ==AF_INET6 ) +return nla_put (skb, attr,sizeof (struct in6_addr ), &ip->sin6.sin6_addr); +else +return nla_put_be32 (skb, attr, ip->sin.sin_addr.s_addr); +} + +#else /* !CONFIG_IPV6 */ + +static inline +bool vxlan_addr_equal (const union vxlan_addr *a,const union vxlan_addr *b) +{ +return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr; +} + +static inline bool vxlan_addr_any (const union vxlan_addr *ipa) +{ +return ipa->sin.sin_addr.s_addr ==htonl (INADDR_ANY ); +} + +static inline bool vxlan_addr_multicast (const union vxlan_addr *ipa) +{ +return IN_MULTICAST (ntohl (ipa->sin.sin_addr.s_addr)); +} + +static int vxlan_nla_get_addr (union vxlan_addr *ip,struct nlattr *nla) +{ +if (nla_len (nla) >=sizeof (struct in6_addr )) { +return -EAFNOSUPPORT ; + }else if (nla_len (nla) >=sizeof (__be32)) { + ip->sin.sin_addr.s_addr =nla_get_be32 (nla); + ip->sa.sa_family =AF_INET ; +return 0 ; + }else { +return -EAFNOSUPPORT ; + } +} + +static int vxlan_nla_put_addr (struct sk_buff *skb,int attr, +const union vxlan_addr *ip) +{ +return nla_put_be32 (skb, attr, ip->sin.sin_addr.s_addr); +} +#endif +/* Virtual Network hash table head */ static inline struct hlist_head *vni_head (struct vxlan_sock *vs,u32 id) {
@@ -239,7 +340,7 @@ 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_addr_any (&rdst->remote_ip); send_eth = !is_zero_ether_addr (fdb->eth_addr); }else ndm->ndm_family =AF_BRIDGE ;
@@ -251,7 +352,7 @@ 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->dst_port &&
@@ -283,7 +384,7 @@ 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 (__be16))/* NDA_PORT */ +nla_total_size (sizeof (__be32))/* NDA_VNI */ +nla_total_size (sizeof (__u32))/* NDA_IFINDEX */
@@ -317,14 +418,14 @@ 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,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_ip = *ipa,/* goes to NDA_DST */ .remote_vni =VXLAN_N_VID , };
@@ -397,13 +498,13 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,/* caller should hold vxlan->hash_lock */ static struct vxlan_rdst *vxlan_fdb_find_rdst (struct vxlan_fdb *f, -__be32 ip,__be16 port, +union vxlan_addr *ip,__be16 port,__u32 vni,__u32 ifindex) {struct vxlan_rdst *rd;list_for_each_entry (rd, &f->remotes, list) { -if (rd->remote_ip == ip && +if (vxlan_addr_equal (&rd->remote_ip, ip) && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex)
@@ -415,7 +516,7 @@ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f,/* Replace destination of unicast mac */ static int vxlan_fdb_replace (struct vxlan_fdb *f, -__be32 ip,__be16 port,__u32 vni,__u32 ifindex) +union vxlan_addr *ip,__be16 port,__u32 vni,__u32 ifindex) {struct vxlan_rdst *rd;
@@ -426,7 +527,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f, rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list);if (!rd)return 0 ; - rd->remote_ip = ip; + rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex;
@@ -435,7 +536,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f,/* Add/update destinations for multicast */ static int vxlan_fdb_append (struct vxlan_fdb *f, -__be32 ip,__be16 port,__u32 vni,__u32 ifindex) +union vxlan_addr *ip,__be16 port,__u32 vni,__u32 ifindex) {struct vxlan_rdst *rd;
@@ -446,7 +547,7 @@ 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;
@@ -458,7 +559,7 @@ 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,union vxlan_addr *ip,__u16 state,__u16 flags,__be16 port,__u32 vni,__u32 ifindex,__u8 ndm_flags)
@@ -517,7 +618,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))return -EOPNOTSUPP ; -netdev_dbg (vxlan->dev,"add %pM -> %pI4\n" , mac, &ip); +netdev_dbg (vxlan->dev,"add %pM -> %pIS\n" , mac, ip); f =kmalloc (sizeof (*f),GFP_ATOMIC );if (!f)return -ENOMEM ;
@@ -565,17 +666,26 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f) }static int vxlan_fdb_parse (struct nlattr *tb[],struct vxlan_dev *vxlan, -__be32 *ip,__be16 *port,u32 *vni,u32 *ifindex) +union vxlan_addr *ip,__be16 *port,u32 *vni,u32 *ifindex) {struct net *net =dev_net (vxlan->dev); +int err;if (tb[NDA_DST ]) { -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; }else { - *ip =htonl (INADDR_ANY ); +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 ]) {
@@ -618,7 +728,7 @@ 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; +union vxlan_addr ip;__be16 port;u32 vni, ifindex;int err;
@@ -637,7 +747,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],return err;spin_lock_bh (&vxlan->hash_lock); - err =vxlan_fdb_create (vxlan, addr, ip, ndm->ndm_state, flags, + err =vxlan_fdb_create (vxlan, addr, &ip, ndm->ndm_state, flags, port, vni, ifindex, ndm->ndm_flags);spin_unlock_bh (&vxlan->hash_lock);
@@ -652,7 +762,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],struct vxlan_dev *vxlan =netdev_priv (dev);struct vxlan_fdb *f;struct vxlan_rdst *rd =NULL ; -__be32 ip; +union vxlan_addr ip;__be16 port;u32 vni, ifindex;int err;
@@ -668,8 +778,8 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],if (!f) goto out; -if (ip !=htonl (INADDR_ANY )) { - rd =vxlan_fdb_find_rdst (f, ip, port, vni, ifindex); +if (!vxlan_addr_any (&ip)) { + rd =vxlan_fdb_find_rdst (f, &ip, port, vni, ifindex);if (!rd) goto out; }
@@ -732,7 +842,7 @@ out:* Return true if packet is bogus and should be droppped. */ static bool vxlan_snoop (struct net_device *dev, -__be32 src_ip,const u8 *src_mac) +union vxlan_addr *src_ip,const u8 *src_mac) {struct vxlan_dev *vxlan =netdev_priv (dev);struct vxlan_fdb *f;
@@ -741,7 +851,7 @@ static bool vxlan_snoop(struct net_device *dev,if (likely (f)) {struct vxlan_rdst *rdst =first_remote_rcu (f); -if (likely (rdst->remote_ip == src_ip)) +if (likely (vxlan_addr_equal (&rdst->remote_ip, src_ip)))return false;/* Don't migrate static entries, drop packets */
@@ -750,10 +860,10 @@ static bool vxlan_snoop(struct net_device *dev,if (net_ratelimit ())netdev_info (dev, -"%pM migrated from %pI4 to %pI4\n" , +"%pM migrated from %pIS to %pIS\n" , src_mac, &rdst->remote_ip, &src_ip); - rdst->remote_ip = src_ip; + rdst->remote_ip = *src_ip; f->updated = jiffies;vxlan_fdb_notify (vxlan, f,RTM_NEWNEIGH ); }else {
@@ -775,7 +885,7 @@ static bool vxlan_snoop(struct net_device *dev, }/* See if multicast group is already in use by other ID */ -static bool vxlan_group_used (struct vxlan_net *vn,__be32 remote_ip) +static bool vxlan_group_used (struct vxlan_net *vn,union vxlan_addr *remote_ip) {struct vxlan_dev *vxlan;
@@ -783,7 +893,8 @@ static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip)if (!netif_running (vxlan->dev))continue ; -if (vxlan->default_dst.remote_ip == remote_ip) +if (vxlan_addr_equal (&vxlan->default_dst.remote_ip, + remote_ip))return true; }
@@ -819,13 +930,23 @@ static void vxlan_igmp_join(struct work_struct *work) struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join);struct vxlan_sock *vs = vxlan->vn_sock;struct sock *sk = vs->sock->sk; -struct ip_mreqn mreq = { - .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip, - .imr_ifindex = vxlan->default_dst.remote_ifindex, - }; +union vxlan_addr *ip = &vxlan->default_dst.remote_ip; +int ifindex = vxlan->default_dst.remote_ifindex;lock_sock (sk); -ip_mc_join_group (sk, &mreq); +if (ip->sa.sa_family ==AF_INET ) { +struct ip_mreqn mreq = { + .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, + .imr_ifindex = ifindex, + }; + +ip_mc_join_group (sk, &mreq); +#if IS_ENABLED (CONFIG_IPV6 ) + } else { + ipv6_stub->ipv6_sock_mc_join (sk, ifindex, + &ip->sin6.sin6_addr); +#endif + }release_sock (sk);vxlan_sock_release (vs);
@@ -838,13 +959,24 @@ static void vxlan_igmp_leave(struct work_struct *work) struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave);struct vxlan_sock *vs = vxlan->vn_sock;struct sock *sk = vs->sock->sk; -struct ip_mreqn mreq = { - .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip, - .imr_ifindex = vxlan->default_dst.remote_ifindex, - }; +union vxlan_addr *ip = &vxlan->default_dst.remote_ip; +int ifindex = vxlan->default_dst.remote_ifindex;lock_sock (sk); -ip_mc_leave_group (sk, &mreq); +if (ip->sa.sa_family ==AF_INET ) { +struct ip_mreqn mreq = { + .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, + .imr_ifindex = ifindex, + }; + +ip_mc_leave_group (sk, &mreq); +#if IS_ENABLED (CONFIG_IPV6 ) + } else { + ipv6_stub->ipv6_sock_mc_drop (sk, ifindex, + &ip->sin6.sin6_addr); +#endif + } +release_sock (sk);vxlan_sock_release (vs);
@@ -896,11 +1028,14 @@ error:static void vxlan_rcv (struct vxlan_sock *vs,struct sk_buff *skb,__be32 vx_vni) { -struct iphdr *oip; +struct iphdr *oip =NULL ; +struct ipv6hdr *oip6 =NULL ;struct vxlan_dev *vxlan;struct pcpu_tstats *stats; +union vxlan_addr saddr;__u32 vni; -int err; +int err =0 ; +union vxlan_addr *remote_ip; vni =ntohl (vx_vni) >>8 ;/* Is this VNI defined? */
@@ -908,6 +1043,7 @@ static void vxlan_rcv(struct vxlan_sock *vs,if (!vxlan) goto drop; + remote_ip = &vxlan->default_dst.remote_ip;skb_reset_mac_header (skb); skb->protocol =eth_type_trans (skb, vxlan->dev);
@@ -917,9 +1053,20 @@ static void vxlan_rcv(struct vxlan_sock *vs, goto drop;/* Re-examine inner Ethernet packet */ - oip =ip_hdr (skb); +if (remote_ip->sa.sa_family ==AF_INET ) { + oip =ip_hdr (skb); + saddr.sin.sin_addr.s_addr = oip->saddr; + saddr.sa.sa_family =AF_INET ; +#if IS_ENABLED (CONFIG_IPV6 ) + } else { + oip6 =ipv6_hdr (skb); + saddr.sin6.sin6_addr = oip6->saddr; + saddr.sa.sa_family =AF_INET6 ; +#endif + } +if ((vxlan->flags &VXLAN_F_LEARN ) && -vxlan_snoop (skb->dev, oip->saddr,eth_hdr (skb)->h_source)) +vxlan_snoop (skb->dev, &saddr,eth_hdr (skb)->h_source)) goto drop;skb_reset_network_header (skb);
@@ -935,11 +1082,20 @@ static void vxlan_rcv(struct vxlan_sock *vs, skb->encapsulation =0 ; - err =IP_ECN_decapsulate (oip, skb); +if (oip6) + err =IP6_ECN_decapsulate (oip6, skb); +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 (log_ecn_error) { +if (oip6) +net_info_ratelimited ("non-ECT from %pI6\n" , + &oip6->saddr); +if (oip) +net_info_ratelimited ("non-ECT from %pI4 with TOS=%#x\n" , + &oip->saddr, oip->tos); + }if (err >1 ) { ++vxlan->dev->stats.rx_frame_errors; ++vxlan->dev->stats.rx_errors;
@@ -1009,7 +1165,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) } f =vxlan_find_mac (vxlan, n->ha); -if (f &&first_remote_rcu (f)->remote_ip ==htonl (INADDR_ANY )) { +if (f &&vxlan_addr_any (&(first_remote_rcu (f)->remote_ip))) {/* bridge-local neighbor */ neigh_release (n); goto out;
@@ -1027,8 +1183,14 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)if (netif_rx_ni (reply) ==NET_RX_DROP ) dev->stats.rx_dropped++; - }else if (vxlan->flags &VXLAN_F_L3MISS ) -vxlan_ip_miss (dev, tip); + }else if (vxlan->flags &VXLAN_F_L3MISS ) { +union vxlan_addr ipa = { + .sin.sin_addr.s_addr = tip, + .sa.sa_family =AF_INET , + }; + +vxlan_ip_miss (dev, &ipa); + } out:consume_skb (skb);return NETDEV_TX_OK ;
@@ -1050,6 +1212,16 @@ 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 )) { +union vxlan_addr ipa = { + .sin.sin_addr.s_addr = pip->daddr, + .sa.sa_family =AF_INET , + }; + +vxlan_ip_miss (dev, &ipa); +return false; + } +break ;default :return false;
@@ -1066,8 +1238,8 @@ 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; }
@@ -1118,6 +1290,102 @@ static int handle_offloads(struct sk_buff *skb)return 0 ; } +#if IS_ENABLED (CONFIG_IPV6 ) +static int vxlan6_xmit_skb (struct net *net,struct vxlan_sock *vs, +struct dst_entry *dst,struct sk_buff *skb, +struct net_device *dev,struct in6_addr *saddr, +struct in6_addr *daddr,__u8 prio,__u8 ttl, +__be16 src_port,__be16 dst_port,__be32 vni) +{ +struct ipv6hdr *ip6h; +struct vxlanhdr *vxh; +struct udphdr *uh; +int min_headroom; +int err; + +if (!skb->encapsulation) { +skb_reset_inner_headers (skb); + skb->encapsulation =1 ; + } + + min_headroom =LL_RESERVED_SPACE (dst->dev) + dst->header_len + +VXLAN_HLEN +sizeof (struct ipv6hdr ) + + (vlan_tx_tag_present (skb) ?VLAN_HLEN :0 ); + +/* Need space for new headers (invalidates iph ptr) */ + err =skb_cow_head (skb, min_headroom); +if (unlikely (err)) +return err; + +if (vlan_tx_tag_present (skb)) { +if (WARN_ON (!__vlan_put_tag (skb, + skb->vlan_proto, +vlan_tx_tag_get (skb)))) +return -ENOMEM ; + + skb->vlan_tci =0 ; + } + + vxh = (struct vxlanhdr *)__skb_push (skb,sizeof (*vxh)); + vxh->vx_flags =htonl (VXLAN_FLAGS ); + vxh->vx_vni = vni; + +__skb_push (skb,sizeof (*uh)); +skb_reset_transport_header (skb); + uh =udp_hdr (skb); + + uh->dest = dst_port; + uh->source = src_port; + + uh->len =htons (skb->len); + uh->check =0 ; + +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, dst); + +if (!skb_is_gso (skb) && !(dst->dev->features &NETIF_F_IPV6_CSUM )) { +__wsum csum =skb_checksum (skb,0 , skb->len,0 ); + skb->ip_summed =CHECKSUM_UNNECESSARY ; + uh->check =csum_ipv6_magic (saddr, daddr, skb->len, +IPPROTO_UDP , csum); +if (uh->check ==0 ) + uh->check =CSUM_MANGLED_0 ; + }else { + skb->ip_summed =CHECKSUM_PARTIAL ; + skb->csum_start =skb_transport_header (skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr , check); + uh->check = ~csum_ipv6_magic (saddr, daddr, + skb->len,IPPROTO_UDP ,0 ); + } + +__skb_push (skb,sizeof (*ip6h)); +skb_reset_network_header (skb); + ip6h =ipv6_hdr (skb); + ip6h->version =6 ; + ip6h->priority = prio; + ip6h->flow_lbl[0 ] =0 ; + ip6h->flow_lbl[1 ] =0 ; + ip6h->flow_lbl[2 ] =0 ; + ip6h->payload_len =htons (skb->len); + ip6h->nexthdr =IPPROTO_UDP ; + ip6h->hop_limit = ttl; + ip6h->daddr = *daddr; + ip6h->saddr = *saddr; + +vxlan_set_owner (vs->sock->sk, skb); + + err =handle_offloads (skb); +if (err) +return err; + +ip6tunnel_xmit (skb, dev); +return 0 ; +} +#endif + int vxlan_xmit_skb(struct net *net, struct vxlan_sock *vs, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
@@ -1182,15 +1450,26 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, {struct pcpu_tstats *tx_stats =this_cpu_ptr (src_vxlan->dev->tstats);struct pcpu_tstats *rx_stats =this_cpu_ptr (dst_vxlan->dev->tstats); +union vxlan_addr loopback; +union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; skb->pkt_type =PACKET_HOST ; skb->encapsulation =0 ; skb->dev = dst_vxlan->dev;__skb_pull (skb,skb_network_offset (skb)); +if (remote_ip->sa.sa_family ==AF_INET ) { + loopback.sin.sin_addr.s_addr =htonl (INADDR_LOOPBACK ); + loopback.sa.sa_family =AF_INET ; +#if IS_ENABLED (CONFIG_IPV6 ) + } else { + loopback.sin6.sin6_addr = in6addr_loopback; + loopback.sa.sa_family =AF_INET6 ; +#endif + } +if (dst_vxlan->flags &VXLAN_F_LEARN ) -vxlan_snoop (skb->dev,htonl (INADDR_LOOPBACK ), -eth_hdr (skb)->h_source); +vxlan_snoop (skb->dev, &loopback,eth_hdr (skb)->h_source);u64_stats_update_begin (&tx_stats->syncp); tx_stats->tx_packets++;
@@ -1211,11 +1490,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_rdst *rdst, bool did_rsc) {struct vxlan_dev *vxlan =netdev_priv (dev); -struct rtable *rt; +struct rtable *rt =NULL ;const struct iphdr *old_iph;struct flowi4 fl4; -__be32 dst; -__be16 src_port, dst_port; +union vxlan_addr *dst; +__be16 src_port =0 , dst_port;u32 vni;__be16 df =0 ;__u8 tos, ttl;
@@ -1223,9 +1502,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port; vni = rdst->remote_vni; - dst = rdst->remote_ip; + dst = &rdst->remote_ip; -if (!dst) { +if (vxlan_addr_any (dst)) {if (did_rsc) {/* short-circuited back to local bridge */ vxlan_encap_bypass (skb, vxlan, vxlan);
@@ -1237,7 +1516,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, old_iph =ip_hdr (skb); ttl = vxlan->ttl; -if (!ttl &&IN_MULTICAST (ntohl (dst))) +if (!ttl &&vxlan_addr_multicast (dst)) ttl =1 ; tos = vxlan->tos;
@@ -1246,48 +1525,101 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, src_port =vxlan_src_port (vxlan->port_min, vxlan->port_max, skb); -memset (&fl4,0 ,sizeof (fl4)); - fl4.flowi4_oif = rdst->remote_ifindex; - fl4.flowi4_tos =RT_TOS (tos); - fl4.daddr = dst; - fl4.saddr = vxlan->saddr; - - 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; - } +if (dst->sa.sa_family ==AF_INET ) { +memset (&fl4,0 ,sizeof (fl4)); + fl4.flowi4_oif = rdst->remote_ifindex; + fl4.flowi4_tos =RT_TOS (tos); + fl4.daddr = dst->sin.sin_addr.s_addr; + fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr; + + rt =ip_route_output_key (dev_net (dev), &fl4); +if (IS_ERR (rt)) { +netdev_dbg (dev,"no route to %pI4\n" , + &dst->sin.sin_addr.s_addr); + dev->stats.tx_carrier_errors++; + goto tx_error; + } -if (rt->dst.dev == dev) { -netdev_dbg (dev,"circular route to %pI4\n" , &dst); - dev->stats.collisions++; - goto rt_tx_error; - } +if (rt->dst.dev == dev) { +netdev_dbg (dev,"circular route to %pI4\n" , + &dst->sin.sin_addr.s_addr); + dev->stats.collisions++; + goto tx_error; + } + +/* Bypass encapsulation if the destination is local */ +if (rt->rt_flags &RTCF_LOCAL && + !(rt->rt_flags & (RTCF_BROADCAST |RTCF_MULTICAST ))) { +struct vxlan_dev *dst_vxlan; + +ip_rt_put (rt); + dst_vxlan =vxlan_find_vni (dev_net (dev), vni, dst_port); +if (!dst_vxlan) + goto tx_error; +vxlan_encap_bypass (skb, vxlan, dst_vxlan); +return ; + } -/* Bypass encapsulation if the destination is local */ -if (rt->rt_flags &RTCF_LOCAL && - !(rt->rt_flags & (RTCF_BROADCAST |RTCF_MULTICAST ))) { -struct vxlan_dev *dst_vxlan; + tos =ip_tunnel_ecn_encap (tos, old_iph, skb); + ttl = ttl ? :ip4_dst_hoplimit (&rt->dst); -ip_rt_put (rt); - dst_vxlan =vxlan_find_vni (dev_net (dev), vni, dst_port); -if (!dst_vxlan) + err =vxlan_xmit_skb (dev_net (dev), vxlan->vn_sock, rt, skb, + fl4.saddr, dst->sin.sin_addr.s_addr, + tos, ttl, df, src_port, dst_port, +htonl (vni <<8 )); + +if (err <0 ) + goto rt_tx_error; +iptunnel_xmit_stats (err, &dev->stats, dev->tstats); +#if IS_ENABLED (CONFIG_IPV6 ) + } else { +struct sock *sk = vxlan->vn_sock->sock->sk; +struct dst_entry *ndst; +struct flowi6 fl6; +u32 flags; + +memset (&fl6,0 ,sizeof (fl6)); + fl6.flowi6_oif = rdst->remote_ifindex; + fl6.daddr = dst->sin6.sin6_addr; + fl6.saddr = vxlan->saddr.sin6.sin6_addr; + fl6.flowi6_proto = skb->protocol; + +if (ipv6_stub->ipv6_dst_lookup (sk, &ndst, &fl6)) { +netdev_dbg (dev,"no route to %pI6\n" , + &dst->sin6.sin6_addr); + dev->stats.tx_carrier_errors++; goto tx_error; -vxlan_encap_bypass (skb, vxlan, dst_vxlan); -return ; - } + } - tos =ip_tunnel_ecn_encap (tos, old_iph, skb); - ttl = ttl ? :ip4_dst_hoplimit (&rt->dst); +if (ndst->dev == dev) { +netdev_dbg (dev,"circular route to %pI6\n" , + &dst->sin6.sin6_addr); +dst_release (ndst); + dev->stats.collisions++; + goto tx_error; + } - err =vxlan_xmit_skb (dev_net (dev), vxlan->vn_sock, rt, skb, - fl4.saddr, dst, tos, ttl, df, - src_port, dst_port,htonl (vni <<8 )); +/* Bypass encapsulation if the destination is local */ + flags = ((struct rt6_info *)ndst)->rt6i_flags; +if (flags &RTF_LOCAL && + !(flags & (RTCF_BROADCAST |RTCF_MULTICAST ))) { +struct vxlan_dev *dst_vxlan; + +dst_release (ndst); + dst_vxlan =vxlan_find_vni (dev_net (dev), vni, dst_port); +if (!dst_vxlan) + goto tx_error; +vxlan_encap_bypass (skb, vxlan, dst_vxlan); +return ; + } -if (err <0 ) - goto rt_tx_error; -iptunnel_xmit_stats (err, &dev->stats, dev->tstats); + ttl = ttl ? :ip6_dst_hoplimit (ndst); + + err =vxlan6_xmit_skb (dev_net (dev), vxlan->vn_sock, ndst, skb, + dev, &fl6.saddr, &fl6.daddr,0 , ttl, + src_port, dst_port,htonl (vni <<8 )); +#endif + }return ;
@@ -1464,8 +1796,8 @@ static int vxlan_open(struct net_device *dev)if (!vs)return -ENOTCONN ; -if (IN_MULTICAST (ntohl (vxlan->default_dst.remote_ip)) && -vxlan_group_used (vn, vxlan->default_dst.remote_ip)) { +if (vxlan_addr_multicast (&vxlan->default_dst.remote_ip) && +vxlan_group_used (vn, &vxlan->default_dst.remote_ip)) {vxlan_sock_hold (vs);dev_hold (dev);queue_work (vxlan_wq, &vxlan->igmp_join);
@@ -1503,8 +1835,8 @@ static int vxlan_stop(struct net_device *dev)struct vxlan_dev *vxlan =netdev_priv (dev);struct vxlan_sock *vs = vxlan->vn_sock; -if (vs &&IN_MULTICAST (ntohl (vxlan->default_dst.remote_ip)) && - !vxlan_group_used (vn, vxlan->default_dst.remote_ip)) { +if (vs &&vxlan_addr_multicast (&vxlan->default_dst.remote_ip) && + !vxlan_group_used (vn, &vxlan->default_dst.remote_ip)) {vxlan_sock_hold (vs);dev_hold (dev);queue_work (vxlan_wq, &vxlan->igmp_leave);
@@ -1552,7 +1884,10 @@ 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->default_dst.remote_ip.sa.sa_family ==AF_INET6 ) + dev->hard_header_len =ETH_HLEN +VXLAN6_HEADROOM ; +else + dev->hard_header_len =ETH_HLEN +VXLAN_HEADROOM ; dev->netdev_ops = &vxlan_netdev_ops; dev->destructor = free_netdev;
@@ -1597,8 +1932,10 @@ 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 },
@@ -1669,58 +2006,132 @@ static void vxlan_del_work(struct work_struct *work)kfree_rcu (vs, rcu); } -static struct vxlan_sock *vxlan_socket_create (struct net *net,__be16 port, -vxlan_rcv_t *rcv,void *data) +#if IS_ENABLED (CONFIG_IPV6 ) +/* Create UDP socket for encapsulation receive. AF_INET6 socket +* could be used for both IPv4 and IPv6 communications, but +* users may set bindv6only=1. +*/ +static int create_v6_sock (struct net *net,__be16 port,struct socket **psock) +{ +struct sock *sk; +struct socket *sock; +struct sockaddr_in6 vxlan_addr = { + .sin6_family =AF_INET6 , + .sin6_port = port, + }; +int rc, val =1 ; + + rc =sock_create_kern (AF_INET6 ,SOCK_DGRAM ,IPPROTO_UDP , &sock); +if (rc <0 ) { +pr_debug ("UDPv6 socket create failed\n" ); +return rc; + } + +/* Put in proper namespace */ + sk = sock->sk; +sk_change_net (sk, net); + +kernel_setsockopt (sock,SOL_IPV6 ,IPV6_V6ONLY , + (char *)&val,sizeof (val)); + rc =kernel_bind (sock, (struct sockaddr *)&vxlan_addr, +sizeof (struct sockaddr_in6 )); +if (rc <0 ) { +pr_debug ("bind for UDPv6 socket %pI6:%u (%d)\n" , + &vxlan_addr.sin6_addr,ntohs (vxlan_addr.sin6_port), rc); +sk_release_kernel (sk); +return rc; + } +/* At this point, IPv6 module should have been loaded in +* sock_create_kern(). +*/ +BUG_ON (!ipv6_stub); + + *psock = sock; +/* Disable multicast loopback */ +inet_sk (sk)->mc_loop =0 ; +return 0 ; +} + +#else + +static int create_v6_sock (struct net *net,__be16 port,struct socket **psock) +{ +return -EPFNOSUPPORT ; +} +#endif + +static int create_v4_sock (struct net *net,__be16 port,struct socket **psock) { -struct vxlan_net *vn =net_generic (net, vxlan_net_id); -struct vxlan_sock *vs;struct sock *sk; +struct socket *sock;struct sockaddr_in vxlan_addr = { .sin_family =AF_INET , .sin_addr.s_addr =htonl (INADDR_ANY ), .sin_port = port, };int rc; -unsigned int h; - - vs =kmalloc (sizeof (*vs),GFP_KERNEL ); -if (!vs) { -pr_debug ("memory alocation failure\n" ); -return ERR_PTR (-ENOMEM ); - } - -for (h =0 ; h <VNI_HASH_SIZE ; ++h) -INIT_HLIST_HEAD (&vs->vni_list[h]); - -INIT_WORK (&vs->del_work, vxlan_del_work);/* Create UDP socket for encapsulation receive. */ - rc =sock_create_kern (AF_INET ,SOCK_DGRAM ,IPPROTO_UDP , &vs->sock); + rc =sock_create_kern (AF_INET ,SOCK_DGRAM ,IPPROTO_UDP , &sock);if (rc <0 ) {pr_debug ("UDP socket create failed\n" ); -kfree (vs); -return ERR_PTR (rc); +return rc; }/* Put in proper namespace */ - sk = vs->sock->sk; + sk = sock->sk;sk_change_net (sk, net); - rc =kernel_bind (vs->sock, (struct sockaddr *) &vxlan_addr, + rc =kernel_bind (sock, (struct sockaddr *) &vxlan_addr,sizeof (vxlan_addr));if (rc <0 ) {pr_debug ("bind for UDP socket %pI4:%u (%d)\n" , &vxlan_addr.sin_addr,ntohs (vxlan_addr.sin_port), rc);sk_release_kernel (sk); +return rc; + } + + *psock = sock; +/* Disable multicast loopback */ +inet_sk (sk)->mc_loop =0 ; +return 0 ; +} + +/* Create new listen socket if needed */ +static struct vxlan_sock *vxlan_socket_create (struct net *net,__be16 port, +vxlan_rcv_t *rcv,void *data,bool ipv6) +{ +struct vxlan_net *vn =net_generic (net, vxlan_net_id); +struct vxlan_sock *vs; +struct socket *sock; +struct sock *sk; +int rc =0 ; +unsigned int h; + + vs =kmalloc (sizeof (*vs),GFP_KERNEL ); +if (!vs) +return ERR_PTR (-ENOMEM ); + +for (h =0 ; h <VNI_HASH_SIZE ; ++h) +INIT_HLIST_HEAD (&vs->vni_list[h]); + +INIT_WORK (&vs->del_work, vxlan_del_work); + +if (ipv6) + rc =create_v6_sock (net, port, &sock); +else + rc =create_v4_sock (net, port, &sock); +if (rc <0 ) {kfree (vs);return ERR_PTR (rc); } + + vs->sock = sock; + sk = sock->sk;atomic_set (&vs->refcnt,1 ); vs->rcv = rcv; vs->data = data; -/* Disable multicast loopback */ -inet_sk (sk)->mc_loop =0 ;spin_lock (&vn->sock_lock);hlist_add_head_rcu (&vs->hlist,vs_head (net, port));spin_unlock (&vn->sock_lock);
@@ -1728,18 +2139,24 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,/* Mark socket as an encapsulation socket. */ udp_sk (sk)->encap_type =1 ;udp_sk (sk)->encap_rcv = vxlan_udp_encap_recv; -udp_encap_enable (); +#if IS_ENABLED (CONFIG_IPV6 ) +if (ipv6) + ipv6_stub->udpv6_encap_enable (); + else +#endif +udp_encap_enable (); +return vs; }struct vxlan_sock *vxlan_sock_add (struct net *net,__be16 port,vxlan_rcv_t *rcv,void *data, -bool no_share) +bool no_share,bool ipv6) {struct vxlan_net *vn =net_generic (net, vxlan_net_id);struct vxlan_sock *vs; - vs =vxlan_socket_create (net, port, rcv, data); + vs =vxlan_socket_create (net, port, rcv, data, ipv6);if (!IS_ERR (vs))return vs;
@@ -1772,7 +2189,7 @@ static void vxlan_sock_work(struct work_struct *work)__be16 port = vxlan->dst_port;struct vxlan_sock *nvs; - nvs =vxlan_sock_add (net, port, vxlan_rcv,NULL , false); + nvs =vxlan_sock_add (net, port, vxlan_rcv,NULL , false, vxlan->flags &VXLAN_F_IPV6 );spin_lock (&vn->sock_lock);if (!IS_ERR (nvs))vxlan_vs_add_dev (nvs, vxlan);
@@ -1789,6 +2206,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,struct vxlan_rdst *dst = &vxlan->default_dst;__u32 vni;int err; +bool use_ipv6 = false;if (!data[IFLA_VXLAN_ID ])return -EINVAL ;
@@ -1796,11 +2214,32 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, vni =nla_get_u32 (data[IFLA_VXLAN_ID ]); dst->remote_vni = vni; -if (data[IFLA_VXLAN_GROUP ]) - dst->remote_ip =nla_get_be32 (data[IFLA_VXLAN_GROUP ]); +if (data[IFLA_VXLAN_GROUP ]) { + dst->remote_ip.sin.sin_addr.s_addr =nla_get_be32 (data[IFLA_VXLAN_GROUP ]); + dst->remote_ip.sa.sa_family =AF_INET ; + }else if (data[IFLA_VXLAN_GROUP6 ]) { +if (!IS_ENABLED (CONFIG_IPV6 )) +return -EPFNOSUPPORT ; + +nla_memcpy (&dst->remote_ip.sin6.sin6_addr, data[IFLA_VXLAN_GROUP6 ], +sizeof (struct in6_addr )); + dst->remote_ip.sa.sa_family =AF_INET6 ; + use_ipv6 = true; + } -if (data[IFLA_VXLAN_LOCAL ]) - vxlan->saddr =nla_get_be32 (data[IFLA_VXLAN_LOCAL ]); +if (data[IFLA_VXLAN_LOCAL ]) { + vxlan->saddr.sin.sin_addr.s_addr =nla_get_be32 (data[IFLA_VXLAN_LOCAL ]); + vxlan->saddr.sa.sa_family =AF_INET ; + }else if (data[IFLA_VXLAN_LOCAL6 ]) { +if (!IS_ENABLED (CONFIG_IPV6 )) +return -EPFNOSUPPORT ; + +/* TODO: respect scope id */ +nla_memcpy (&vxlan->saddr.sin6.sin6_addr, data[IFLA_VXLAN_LOCAL6 ], +sizeof (struct in6_addr )); + vxlan->saddr.sa.sa_family =AF_INET6 ; + use_ipv6 = true; + }if (data[IFLA_VXLAN_LINK ] && (dst->remote_ifindex =nla_get_u32 (data[IFLA_VXLAN_LINK ]))) {
@@ -1812,12 +2251,23 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,return -ENODEV ; } +#if IS_ENABLED (CONFIG_IPV6 ) +if (use_ipv6) { +struct inet6_dev *idev =__in6_dev_get (lowerdev); +if (idev && idev->cnf.disable_ipv6) { +pr_info ("IPv6 is disabled via sysctl\n" ); +return -EPERM ; + } + vxlan->flags |=VXLAN_F_IPV6 ; + } +#endif +if (!tb[IFLA_MTU ]) - dev->mtu = lowerdev->mtu -VXLAN_HEADROOM ; + dev->mtu = lowerdev->mtu - (use_ipv6 ?VXLAN6_HEADROOM :VXLAN_HEADROOM );/* update header length based on lower device */ dev->hard_header_len = lowerdev->hard_header_len + -VXLAN_HEADROOM ; + (use_ipv6 ?VXLAN6_HEADROOM :VXLAN_HEADROOM ); }if (data[IFLA_VXLAN_TOS ])
@@ -1868,7 +2318,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,/* create an fdb entry for default destination */ err = vxlan_fdb_create(vxlan, all_zeros_mac, - vxlan->default_dst.remote_ip, + &vxlan->default_dst.remote_ip, NUD_REACHABLE|NUD_PERMANENT, NLM_F_EXCL|NLM_F_CREATE, vxlan->dst_port, vxlan->default_dst.remote_vni,
@@ -1905,9 +2355,9 @@ 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 */
@@ -1934,14 +2384,36 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)if (nla_put_u32 (skb,IFLA_VXLAN_ID , dst->remote_vni)) goto nla_put_failure; -if (dst->remote_ip &&nla_put_be32 (skb,IFLA_VXLAN_GROUP , dst->remote_ip)) - goto nla_put_failure; +if (!vxlan_addr_any (&dst->remote_ip)) { +if (dst->remote_ip.sa.sa_family ==AF_INET ) { +if (nla_put_be32 (skb,IFLA_VXLAN_GROUP , + dst->remote_ip.sin.sin_addr.s_addr)) + goto nla_put_failure; +#if IS_ENABLED (CONFIG_IPV6 ) + } else { +if (nla_put (skb,IFLA_VXLAN_GROUP6 ,sizeof (struct in6_addr ), + &dst->remote_ip.sin6.sin6_addr)) + goto nla_put_failure; +#endif + } + }if (dst->remote_ifindex &&nla_put_u32 (skb,IFLA_VXLAN_LINK , dst->remote_ifindex)) goto nla_put_failure; -if (vxlan->saddr &&nla_put_be32 (skb,IFLA_VXLAN_LOCAL , vxlan->saddr)) - goto nla_put_failure; +if (!vxlan_addr_any (&vxlan->saddr)) { +if (vxlan->saddr.sa.sa_family ==AF_INET ) { +if (nla_put_be32 (skb,IFLA_VXLAN_LOCAL , + vxlan->saddr.sin.sin_addr.s_addr)) + goto nla_put_failure; +#if IS_ENABLED (CONFIG_IPV6 ) + } else { +if (nla_put (skb,IFLA_VXLAN_LOCAL6 ,sizeof (struct in6_addr ), + &vxlan->saddr.sin6.sin6_addr)) + goto nla_put_failure; +#endif + } + } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) ||
include/net/vxlan.h +1 -1
@@ -25,7 +25,7 @@ struct vxlan_sock {struct vxlan_sock *vxlan_sock_add (struct net *net,__be16 port,vxlan_rcv_t *rcv,void *data, -bool no_share); +bool no_share,bool ipv6);void vxlan_sock_release (struct vxlan_sock *vs);
include/uapi/linux/if_link.h +2 -0
@@ -314,6 +314,8 @@ enum {IFLA_VXLAN_L2MISS ,IFLA_VXLAN_L3MISS ,IFLA_VXLAN_PORT ,/* destination port */ +IFLA_VXLAN_GROUP6 , +IFLA_VXLAN_LOCAL6 , __IFLA_VXLAN_MAX };#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
net/openvswitch/vport-vxlan.c +1 -1
@@ -123,7 +123,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) vxlan_port =vxlan_vport (vport);strncpy (vxlan_port->name, parms->name,IFNAMSIZ ); - vs =vxlan_sock_add (net,htons (dst_port), vxlan_rcv, vport, true); + vs =vxlan_sock_add (net,htons (dst_port), vxlan_rcv, vport, true, false);if (IS_ERR (vs)) {ovs_vport_free (vport);return (void *)vs;
Signature · 1 line
1.7.7.6
drivers/net/vxlan.c static void vxlan_igmp_join(struct work_struct *work) · line 948
Quoted 5 lines · On Sat, 31 Aug 2013 13:44:33 +0800 Cong Wang <[email protected]> wrote:
drivers/net/vxlan.c +5
-0+#if IS_ENABLED (CONFIG_IPV6 ) + } else { + ipv6_stub->ipv6_sock_mc_join (sk, ifindex, + &ip->sin6.sin6_addr); +#endif
This isn't safe against IPv6 module getting unloaded. You either have to figure out a reference count method, or disable IPv6 module unload.
Since it can only be forced unload anyway, I still argue it should just be disabled (by removing the module exit hook and code).
Quoted 13 lines · Stephen Hemminger
drivers/net/vxlan.c static void vxlan_igmp_join(struct work_struct *work) · line 948
Quoted 5 lines · On Sat, 31 Aug 2013 13:44:33 +0800 Cong Wang <[email protected]> wrote:
drivers/net/vxlan.c +5
-0+#if IS_ENABLED (CONFIG_IPV6 ) + } else { + ipv6_stub->ipv6_sock_mc_join (sk, ifindex, + &ip->sin6.sin6_addr); +#endif This isn't safe against IPv6 module getting unloaded. You either have to figure out a reference count method, or disable IPv6 module unload.
Quoted 3 lines
Since it can only be forced unload anyway, I still argue it should just be disabled (by removing the module exit hook and code).
I will send a patch to remove ipv6 module exit code, since there is other problem too.
Thanks!
PATCH v12 7/11 vxlan: add ipv6 route short circuit support
In reply to Cong WangFrom: Cong Wang <[email protected]>
route short circuit only has IPv4 part, this patch adds the IPv6 part. nd_tbl will be needed.
--- drivers/net/vxlan.c | 30 ++++++++++++++++++++++++++++-- include/net/addrconf.h | 1 + net/ipv6/af_inet6.c | 1 + 3 files changed, 30 insertions(+), 2 deletions(-)
drivers/net/vxlan.c +28 -2
@@ -1200,7 +1200,6 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) {struct vxlan_dev *vxlan =netdev_priv (dev);struct neighbour *n; -struct iphdr *pip;if (is_multicast_ether_addr (eth_hdr (skb)->h_dest))return false;
@@ -1208,6 +1207,9 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) n =NULL ;switch (ntohs (eth_hdr (skb)->h_proto)) {case ETH_P_IP : + { +struct iphdr *pip; +if (!pskb_may_pull (skb,sizeof (struct iphdr )))return false; pip =ip_hdr (skb);
@@ -1223,6 +1225,29 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) }break ; + } +#if IS_ENABLED (CONFIG_IPV6 ) +case ETH_P_IPV6 : + { +struct ipv6hdr *pip6; + +if (!pskb_may_pull (skb,sizeof (struct ipv6hdr ))) +return false; + pip6 =ipv6_hdr (skb); + n =neigh_lookup (ipv6_stub->nd_tbl, &pip6->daddr, dev); +if (!n && (vxlan->flags &VXLAN_F_L3MISS )) { +union vxlan_addr ipa = { + .sin6.sin6_addr = pip6->daddr, + .sa.sa_family =AF_INET6 , + }; + +vxlan_ip_miss (dev, &ipa); +return false; + } + +break ; + } +#endif default :return false; }
@@ -1659,7 +1684,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) did_rsc = false;if (f && (f->flags &NTF_ROUTER ) && (vxlan->flags &VXLAN_F_RSC ) && -ntohs (eth->h_proto) ==ETH_P_IP ) { + (ntohs (eth->h_proto) ==ETH_P_IP || +ntohs (eth->h_proto) ==ETH_P_IPV6 )) { did_rsc =route_shortcircuit (dev, skb);if (did_rsc) f =vxlan_find_mac (vxlan, eth->h_dest);
include/net/addrconf.h +1 -0
@@ -153,6 +153,7 @@ struct ipv6_stub {int (*ipv6_dst_lookup)(struct sock *sk,struct dst_entry **dst,struct flowi6 *fl6);void (*udpv6_encap_enable)(void ); +struct neigh_table *nd_tbl; };extern const struct ipv6_stub *ipv6_stub__read_mostly ;
net/ipv6/af_inet6.c +1 -0
@@ -815,6 +815,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_drop = ipv6_sock_mc_drop, .ipv6_dst_lookup = ip6_dst_lookup, .udpv6_encap_enable = udpv6_encap_enable, + .nd_tbl = &nd_tbl, };static int __init inet6_init (void )
Signature · 1 line
1.7.7.6
PATCH v12 8/11 ipv6: move in6_dev_finish_destroy() into core kernel
In reply to Cong WangFrom: Cong Wang <[email protected]>
in6_dev_put() will be needed by vxlan module, so is in6_dev_finish_destroy().
--- net/ipv6/addrconf.c | 30 ------------------------------ net/ipv6/addrconf_core.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 30 deletions(-)
net/ipv6/addrconf.c +0 -30
@@ -304,36 +304,6 @@ err_ip:return -ENOMEM ; } -static void snmp6_free_dev (struct inet6_dev *idev) -{ -kfree (idev->stats.icmpv6msgdev); -kfree (idev->stats.icmpv6dev); -snmp_mib_free ((void __percpu **)idev->stats.ipv6); -} - -/* Nobody refers to this device, we may destroy it. */ - -void in6_dev_finish_destroy (struct inet6_dev *idev) -{ -struct net_device *dev = idev->dev; - -WARN_ON (!list_empty (&idev->addr_list)); -WARN_ON (idev->mc_list !=NULL ); -WARN_ON (timer_pending (&idev->rs_timer)); - -#ifdef NET_REFCNT_DEBUG -pr_debug ("%s: %s\n" , __func__, dev ? dev->name :"NIL" ); -#endif -dev_put (dev); -if (!idev->dead) { -pr_warn ("Freeing alive inet6 device %p\n" , idev); -return ; - } -snmp6_free_dev (idev); -kfree_rcu (idev, rcu); -} -EXPORT_SYMBOL (in6_dev_finish_destroy); -static struct inet6_dev *ipv6_add_dev (struct net_device *dev) {struct inet6_dev *ndev;
net/ipv6/addrconf_core.c +31 -0
@@ -6,6 +6,7 @@#include <linux/export.h> #include <net/ipv6.h> #include <net/addrconf.h> +#include <net/ip.h> #define IPV6_ADDR_SCOPE_TYPE (scope) ((scope) << 16)
@@ -117,3 +118,33 @@ const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCALEXPORT_SYMBOL (in6addr_interfacelocal_allrouters);const struct in6_addr in6addr_sitelocal_allrouters =IN6ADDR_SITELOCAL_ALLROUTERS_INIT ;EXPORT_SYMBOL (in6addr_sitelocal_allrouters); + +static void snmp6_free_dev (struct inet6_dev *idev) +{ +kfree (idev->stats.icmpv6msgdev); +kfree (idev->stats.icmpv6dev); +snmp_mib_free ((void __percpu **)idev->stats.ipv6); +} + +/* Nobody refers to this device, we may destroy it. */ + +void in6_dev_finish_destroy (struct inet6_dev *idev) +{ +struct net_device *dev = idev->dev; + +WARN_ON (!list_empty (&idev->addr_list)); +WARN_ON (idev->mc_list !=NULL ); +WARN_ON (timer_pending (&idev->rs_timer)); + +#ifdef NET_REFCNT_DEBUG +pr_debug ("%s: %s\n" , __func__, dev ? dev->name :"NIL" ); +#endif +dev_put (dev); +if (!idev->dead) { +pr_warn ("Freeing alive inet6 device %p\n" , idev); +return ; + } +snmp6_free_dev (idev); +kfree_rcu (idev, rcu); +} +EXPORT_SYMBOL (in6_dev_finish_destroy);
Signature · 1 line
1.7.7.6
PATCH v12 9/11 vxlan: add ipv6 proxy support
In reply to Cong WangFrom: Cong Wang <[email protected]>
This patch adds the IPv6 version of "arp_reduce", ndisc_send_na() will be needed.
--- drivers/net/vxlan.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++- include/net/addrconf.h | 4 ++ include/net/ndisc.h | 5 +++ net/ipv6/af_inet6.c | 2 + net/ipv6/ndisc.c | 8 ++-- 5 files changed, 95 insertions(+), 6 deletions(-)
drivers/net/vxlan.c +80 -2
@@ -1196,6 +1196,70 @@ out:return NETDEV_TX_OK ; } +#if IS_ENABLED (CONFIG_IPV6 ) +static int neigh_reduce (struct net_device *dev,struct sk_buff *skb) +{ +struct vxlan_dev *vxlan =netdev_priv (dev); +struct neighbour *n; +union vxlan_addr ipa; +const struct ipv6hdr *iphdr; +const struct in6_addr *saddr, *daddr; +struct nd_msg *msg; +struct inet6_dev *in6_dev =NULL ; + + in6_dev =__in6_dev_get (dev); +if (!in6_dev) + goto out; + +if (!pskb_may_pull (skb, skb->len)) + goto out; + + iphdr =ipv6_hdr (skb); + saddr = &iphdr->saddr; + daddr = &iphdr->daddr; + +if (ipv6_addr_loopback (daddr) || +ipv6_addr_is_multicast (daddr)) + goto out; + + msg = (struct nd_msg *)skb_transport_header (skb); +if (msg->icmph.icmp6_code !=0 || + msg->icmph.icmp6_type !=NDISC_NEIGHBOUR_SOLICITATION ) + goto out; + + n =neigh_lookup (ipv6_stub->nd_tbl, daddr, dev); + +if (n) { +struct vxlan_fdb *f; + +if (!(n->nud_state &NUD_CONNECTED )) { +neigh_release (n); + goto out; + } + + f =vxlan_find_mac (vxlan, n->ha); +if (f &&vxlan_addr_any (&(first_remote_rcu (f)->remote_ip))) { +/* bridge-local neighbor */ +neigh_release (n); + goto out; + } + + ipv6_stub->ndisc_send_na (dev, n, saddr, &msg->target, + !!in6_dev->cnf.forwarding, + true, false, false); +neigh_release (n); + }else if (vxlan->flags &VXLAN_F_L3MISS ) { + ipa.sin6.sin6_addr = *daddr; + ipa.sa.sa_family =AF_INET6 ; +vxlan_ip_miss (dev, &ipa); + } + +out: +consume_skb (skb); +return NETDEV_TX_OK ; +} +#endif +static bool route_shortcircuit (struct net_device *dev,struct sk_buff *skb) {struct vxlan_dev *vxlan =netdev_priv (dev);
@@ -1677,8 +1741,22 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)skb_reset_mac_header (skb); eth =eth_hdr (skb); -if ((vxlan->flags &VXLAN_F_PROXY ) &&ntohs (eth->h_proto) ==ETH_P_ARP ) -return arp_reduce (dev, skb); +if ((vxlan->flags &VXLAN_F_PROXY )) { +if (ntohs (eth->h_proto) ==ETH_P_ARP ) +return arp_reduce (dev, skb); +#if IS_ENABLED(CONFIG_IPV6) + else if (ntohs(eth->h_proto) == ETH_P_IPV6 && + skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { +struct nd_msg *msg; + + msg = (struct nd_msg *)skb_transport_header (skb); +if (msg->icmph.icmp6_code ==0 && + msg->icmph.icmp6_type ==NDISC_NEIGHBOUR_SOLICITATION ) +return neigh_reduce (dev, skb); + } +#endif + } f =vxlan_find_mac (vxlan, eth->h_dest); did_rsc = false;
include/net/addrconf.h +4 -0
@@ -153,6 +153,10 @@ struct ipv6_stub {int (*ipv6_dst_lookup)(struct sock *sk,struct dst_entry **dst,struct flowi6 *fl6);void (*udpv6_encap_enable)(void ); +void (*ndisc_send_na)(struct net_device *dev,struct neighbour *neigh, +const struct in6_addr *daddr, +const struct in6_addr *solicited_addr, +bool router,bool solicited,bool override,bool inc_opt);struct neigh_table *nd_tbl; };extern const struct ipv6_stub *ipv6_stub__read_mostly ;
include/net/ndisc.h +5 -0
@@ -204,6 +204,11 @@ extern void ndisc_send_ns(struct net_device *dev,extern void ndisc_send_rs (struct net_device *dev,const struct in6_addr *saddr,const struct in6_addr *daddr); +extern void ndisc_send_na (struct net_device *dev,struct neighbour *neigh, +const struct in6_addr *daddr, +const struct in6_addr *solicited_addr, +bool router,bool solicited,bool override, +bool inc_opt);extern void ndisc_send_redirect (struct sk_buff *skb,const struct in6_addr *target);
net/ipv6/af_inet6.c +2 -0
@@ -56,6 +56,7 @@#include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> +#include <net/ndisc.h> #ifdef CONFIG_IPV6_TUNNEL #include <net/ip6_tunnel.h> #endif
@@ -815,6 +816,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_drop = ipv6_sock_mc_drop, .ipv6_dst_lookup = ip6_dst_lookup, .udpv6_encap_enable = udpv6_encap_enable, + .ndisc_send_na = ndisc_send_na, .nd_tbl = &nd_tbl, };
net/ipv6/ndisc.c +4 -4
@@ -461,10 +461,10 @@ static void ndisc_send_skb(struct sk_buff *skb,rcu_read_unlock (); } -static void ndisc_send_na (struct net_device *dev,struct neighbour *neigh, -const struct in6_addr *daddr, -const struct in6_addr *solicited_addr, -bool router,bool solicited,bool override,bool inc_opt) +void ndisc_send_na (struct net_device *dev,struct neighbour *neigh, +const struct in6_addr *daddr, +const struct in6_addr *solicited_addr, +bool router,bool solicited,bool override,bool inc_opt) {struct sk_buff *skb;struct in6_addr tmpaddr;
Signature · 1 line
1.7.7.6
PATCH v12 10/11 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 | 159 ++++++++++++++++++++++++++++++++--------------- 2 files changed, 111 insertions(+), 52 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 |
@@ -106,6 +107,7 @@ 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 );
@@ -126,7 +128,7 @@ 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 +108 -51
181 lines not on this page · raw message
Signature · 1 line
1.7.7.6
PATCH v12 11/11 net: unify skb_udp_tunnel_segment() and skb_udp6_tunnel_segment()
In reply to Cong WangFrom: Cong Wang <[email protected]>
As suggested by Pravin, we can unify the code in case of duplicated code.
--- net/ipv4/udp.c | 13 ++++++++++- net/ipv6/udp_offload.c | 56 +----------------------------------------------- 2 files changed, 13 insertions(+), 56 deletions(-)
net/ipv4/udp.c +12 -1
@@ -2337,7 +2337,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, uh->len =htons (skb->len - udp_offset);/* csum segment if tunnel sets skb with csum. */ -if (unlikely (uh->check)) { +if (protocol ==htons (ETH_P_IP ) &&unlikely (uh->check)) {struct iphdr *iph =ip_hdr (skb); uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
@@ -2348,7 +2348,18 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,if (uh->check ==0 ) uh->check =CSUM_MANGLED_0 ; + }else if (protocol ==htons (ETH_P_IPV6 )) { +struct ipv6hdr *ipv6h =ipv6_hdr (skb); +u32 len = skb->len - udp_offset; + + uh->check = ~csum_ipv6_magic (&ipv6h->saddr, &ipv6h->daddr, + len,IPPROTO_UDP ,0 ); + uh->check =csum_fold (skb_checksum (skb, udp_offset, len,0 )); +if (uh->check ==0 ) + uh->check =CSUM_MANGLED_0 ; + skb->ip_summed =CHECKSUM_NONE ; } + skb->protocol = protocol; }while ((skb = skb->next)); out:
net/ipv6/udp_offload.c +1 -55
68 lines not on this page · raw message
Signature · 1 line
1.7.7.6
David Miller
maintainerOk, this has gone through enough revisions I think :-)
All applied, and please try to address any problems people run into from here on out.
Thank you.