aboutsummaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Makefile4
-rw-r--r--net/ipv6/addrconf.c203
-rw-r--r--net/ipv6/addrlabel.c5
-rw-r--r--net/ipv6/af_inet6.c189
-rw-r--r--net/ipv6/anycast.c2
-rw-r--r--net/ipv6/fib6_rules.c103
-rw-r--r--net/ipv6/icmp.c133
-rw-r--r--net/ipv6/ip6_fib.c292
-rw-r--r--net/ipv6/ip6_input.c5
-rw-r--r--net/ipv6/ip6_output.c8
-rw-r--r--net/ipv6/ip6_tunnel.c6
-rw-r--r--net/ipv6/ipv6_sockglue.c128
-rw-r--r--net/ipv6/mcast.c72
-rw-r--r--net/ipv6/ndisc.c34
-rw-r--r--net/ipv6/netfilter.c4
-rw-r--r--net/ipv6/netfilter/ip6t_REJECT.c2
-rw-r--r--net/ipv6/proc.c9
-rw-r--r--net/ipv6/route.c551
-rw-r--r--net/ipv6/sit.c6
-rw-r--r--net/ipv6/syncookies.c267
-rw-r--r--net/ipv6/sysctl_net_ipv6.c15
-rw-r--r--net/ipv6/tcp_ipv6.c122
-rw-r--r--net/ipv6/udp_ipv6.c (renamed from net/ipv6/udp.c)16
-rw-r--r--net/ipv6/udplite_ipv6.c (renamed from net/ipv6/udplite.c)0
-rw-r--r--net/ipv6/xfrm6_policy.c7
25 files changed, 1415 insertions, 768 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 24f3aa0f2a3..107051f7c22 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_IPV6) += ipv6.o
ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
addrlabel.o \
- route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
+ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp_ipv6.o \
raw.o protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o
@@ -16,6 +16,8 @@ ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \
ipv6-$(CONFIG_NETFILTER) += netfilter.o
ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o
ipv6-$(CONFIG_PROC_FS) += proc.o
+ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o
+ipv6-$(CONFIG_IP_UDPLITE) += udplite_ipv6.o
ipv6-objs += $(ipv6-y)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 101e0e70ba2..c878fb681ef 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -493,7 +493,7 @@ static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
dev_forward_change((struct inet6_dev *)table->extra1);
if (*p)
- rt6_purge_dflt_routers();
+ rt6_purge_dflt_routers(net);
}
#endif
@@ -561,7 +561,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
write_lock(&addrconf_hash_lock);
/* Ignore adding duplicate addresses on an interface */
- if (ipv6_chk_same_addr(&init_net, addr, idev->dev)) {
+ if (ipv6_chk_same_addr(idev->dev->nd_net, addr, idev->dev)) {
ADBG(("ipv6_add_addr: already assigned\n"));
err = -EEXIST;
goto out;
@@ -751,9 +751,9 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) {
struct in6_addr prefix;
struct rt6_info *rt;
-
+ struct net *net = ifp->idev->dev->nd_net;
ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len);
- rt = rt6_lookup(&prefix, NULL, ifp->idev->dev->ifindex, 1);
+ rt = rt6_lookup(net, &prefix, NULL, ifp->idev->dev->ifindex, 1);
if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) {
if (onlink == 0) {
@@ -905,6 +905,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
{
struct ipv6_saddr_score hiscore;
struct inet6_ifaddr *ifa_result = NULL;
+ struct net *net = daddr_dev->nd_net;
int daddr_type = __ipv6_addr_type(daddr);
int daddr_scope = __ipv6_addr_src_scope(daddr_type);
int daddr_ifindex = daddr_dev ? daddr_dev->ifindex : 0;
@@ -916,7 +917,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
read_lock(&dev_base_lock);
rcu_read_lock();
- for_each_netdev(&init_net, dev) {
+ for_each_netdev(net, dev) {
struct inet6_dev *idev;
struct inet6_ifaddr *ifa;
@@ -1125,6 +1126,11 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
if (hiscore.rule < 7)
hiscore.rule++;
#endif
+
+ /* Skip rule 8 for orchid -> non-orchid address pairs. */
+ if (ipv6_addr_orchid(&ifa->addr) && !ipv6_addr_orchid(daddr))
+ continue;
+
/* Rule 8: Use longest matching prefix */
if (hiscore.rule < 8) {
hiscore.matchlen = ipv6_addr_diff(&ifa_result->addr, daddr);
@@ -1162,14 +1168,7 @@ record_it:
return 0;
}
-
-int ipv6_get_saddr(struct dst_entry *dst,
- struct in6_addr *daddr, struct in6_addr *saddr)
-{
- return ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, daddr, saddr);
-}
-
-EXPORT_SYMBOL(ipv6_get_saddr);
+EXPORT_SYMBOL(ipv6_dev_get_saddr);
int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
unsigned char banned_flags)
@@ -1557,7 +1556,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
.fc_expires = expires,
.fc_dst_len = plen,
.fc_flags = RTF_UP | flags,
- .fc_nlinfo.nl_net = &init_net,
+ .fc_nlinfo.nl_net = dev->nd_net,
};
ipv6_addr_copy(&cfg.fc_dst, pfx);
@@ -1584,7 +1583,7 @@ static void addrconf_add_mroute(struct net_device *dev)
.fc_ifindex = dev->ifindex,
.fc_dst_len = 8,
.fc_flags = RTF_UP,
- .fc_nlinfo.nl_net = &init_net,
+ .fc_nlinfo.nl_net = dev->nd_net,
};
ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0);
@@ -1601,7 +1600,7 @@ static void sit_route_add(struct net_device *dev)
.fc_ifindex = dev->ifindex,
.fc_dst_len = 96,
.fc_flags = RTF_UP | RTF_NONEXTHOP,
- .fc_nlinfo.nl_net = &init_net,
+ .fc_nlinfo.nl_net = dev->nd_net,
};
/* prefix length - 96 bits "::d.d.d.d" */
@@ -1702,7 +1701,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
if (pinfo->onlink) {
struct rt6_info *rt;
- rt = rt6_lookup(&pinfo->prefix, NULL, dev->ifindex, 1);
+ rt = rt6_lookup(dev->nd_net, &pinfo->prefix, NULL,
+ dev->ifindex, 1);
if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) {
if (rt->rt6i_flags&RTF_EXPIRES) {
@@ -1745,7 +1745,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
ok:
- ifp = ipv6_get_ifaddr(&init_net, &addr, dev, 1);
+ ifp = ipv6_get_ifaddr(dev->nd_net, &addr, dev, 1);
if (ifp == NULL && valid_lft) {
int max_addresses = in6_dev->cnf.max_addresses;
@@ -1868,7 +1868,7 @@ ok:
* Special case for SIT interfaces where we create a new "virtual"
* device.
*/
-int addrconf_set_dstaddr(void __user *arg)
+int addrconf_set_dstaddr(struct net *net, void __user *arg)
{
struct in6_ifreq ireq;
struct net_device *dev;
@@ -1880,7 +1880,7 @@ int addrconf_set_dstaddr(void __user *arg)
if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq)))
goto err_exit;
- dev = __dev_get_by_index(&init_net, ireq.ifr6_ifindex);
+ dev = __dev_get_by_index(net, ireq.ifr6_ifindex);
err = -ENODEV;
if (dev == NULL)
@@ -1911,7 +1911,8 @@ int addrconf_set_dstaddr(void __user *arg)
if (err == 0) {
err = -ENOBUFS;
- if ((dev = __dev_get_by_name(&init_net, p.name)) == NULL)
+ dev = __dev_get_by_name(net, p.name);
+ if (!dev)
goto err_exit;
err = dev_open(dev);
}
@@ -1926,8 +1927,9 @@ err_exit:
/*
* Manual configuration of address on an interface
*/
-static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen,
- __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft)
+static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx,
+ int plen, __u8 ifa_flags, __u32 prefered_lft,
+ __u32 valid_lft)
{
struct inet6_ifaddr *ifp;
struct inet6_dev *idev;
@@ -1941,7 +1943,8 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen,
if (!valid_lft || prefered_lft > valid_lft)
return -EINVAL;
- if ((dev = __dev_get_by_index(&init_net, ifindex)) == NULL)
+ dev = __dev_get_by_index(net, ifindex);
+ if (!dev)
return -ENODEV;
if ((idev = addrconf_add_dev(dev)) == NULL)
@@ -1986,13 +1989,15 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen,
return PTR_ERR(ifp);
}
-static int inet6_addr_del(int ifindex, struct in6_addr *pfx, int plen)
+static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx,
+ int plen)
{
struct inet6_ifaddr *ifp;
struct inet6_dev *idev;
struct net_device *dev;
- if ((dev = __dev_get_by_index(&init_net, ifindex)) == NULL)
+ dev = __dev_get_by_index(net, ifindex);
+ if (!dev)
return -ENODEV;
if ((idev = __in6_dev_get(dev)) == NULL)
@@ -2020,7 +2025,7 @@ static int inet6_addr_del(int ifindex, struct in6_addr *pfx, int plen)
}
-int addrconf_add_ifaddr(void __user *arg)
+int addrconf_add_ifaddr(struct net *net, void __user *arg)
{
struct in6_ifreq ireq;
int err;
@@ -2032,13 +2037,14 @@ int addrconf_add_ifaddr(void __user *arg)
return -EFAULT;
rtnl_lock();
- err = inet6_addr_add(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen,
- IFA_F_PERMANENT, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
+ err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr,
+ ireq.ifr6_prefixlen, IFA_F_PERMANENT,
+ INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
rtnl_unlock();
return err;
}
-int addrconf_del_ifaddr(void __user *arg)
+int addrconf_del_ifaddr(struct net *net, void __user *arg)
{
struct in6_ifreq ireq;
int err;
@@ -2050,7 +2056,8 @@ int addrconf_del_ifaddr(void __user *arg)
return -EFAULT;
rtnl_lock();
- err = inet6_addr_del(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen);
+ err = inet6_addr_del(net, ireq.ifr6_ifindex, &ireq.ifr6_addr,
+ ireq.ifr6_prefixlen);
rtnl_unlock();
return err;
}
@@ -2061,6 +2068,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
struct inet6_ifaddr * ifp;
struct in6_addr addr;
struct net_device *dev;
+ struct net *net = idev->dev->nd_net;
int scope;
ASSERT_RTNL();
@@ -2087,7 +2095,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
return;
}
- for_each_netdev(&init_net, dev) {
+ for_each_netdev(net, dev) {
struct in_device * in_dev = __in_dev_get_rtnl(dev);
if (in_dev && (dev->flags & IFF_UP)) {
struct in_ifaddr * ifa;
@@ -2250,15 +2258,16 @@ ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev)
static void ip6_tnl_add_linklocal(struct inet6_dev *idev)
{
struct net_device *link_dev;
+ struct net *net = idev->dev->nd_net;
/* first try to inherit the link-local address from the link device */
if (idev->dev->iflink &&
- (link_dev = __dev_get_by_index(&init_net, idev->dev->iflink))) {
+ (link_dev = __dev_get_by_index(net, idev->dev->iflink))) {
if (!ipv6_inherit_linklocal(idev, link_dev))
return;
}
/* then try to inherit it from any device */
- for_each_netdev(&init_net, link_dev) {
+ for_each_netdev(net, link_dev) {
if (!ipv6_inherit_linklocal(idev, link_dev))
return;
}
@@ -2291,9 +2300,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
int run_pending = 0;
int err;
- if (dev->nd_net != &init_net)
- return NOTIFY_DONE;
-
switch(event) {
case NETDEV_REGISTER:
if (!idev && dev->mtu >= IPV6_MIN_MTU) {
@@ -2433,6 +2439,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
{
struct inet6_dev *idev;
struct inet6_ifaddr *ifa, **bifa;
+ struct net *net = dev->nd_net;
int i;
ASSERT_RTNL();
@@ -2440,7 +2447,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
if (dev == init_net.loopback_dev && how == 1)
how = 0;
- rt6_ifdown(dev);
+ rt6_ifdown(net, dev);
neigh_ifdown(&nd_tbl, dev);
idev = __in6_dev_get(dev);
@@ -3050,9 +3057,6 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
struct in6_addr *pfx;
int err;
- if (net != &init_net)
- return -EINVAL;
-
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
if (err < 0)
return err;
@@ -3062,7 +3066,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
if (pfx == NULL)
return -EINVAL;
- return inet6_addr_del(ifm->ifa_index, pfx, ifm->ifa_prefixlen);
+ return inet6_addr_del(net, ifm->ifa_index, pfx, ifm->ifa_prefixlen);
}
static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags,
@@ -3115,9 +3119,6 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
u8 ifa_flags;
int err;
- if (net != &init_net)
- return -EINVAL;
-
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
if (err < 0)
return err;
@@ -3138,7 +3139,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
valid_lft = INFINITY_LIFE_TIME;
}
- dev = __dev_get_by_index(&init_net, ifm->ifa_index);
+ dev = __dev_get_by_index(net, ifm->ifa_index);
if (dev == NULL)
return -ENODEV;
@@ -3151,8 +3152,9 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
* It would be best to check for !NLM_F_CREATE here but
* userspace alreay relies on not having to provide this.
*/
- return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen,
- ifa_flags, preferred_lft, valid_lft);
+ return inet6_addr_add(net, ifm->ifa_index, pfx,
+ ifm->ifa_prefixlen, ifa_flags,
+ preferred_lft, valid_lft);
}
if (nlh->nlmsg_flags & NLM_F_EXCL ||
@@ -3317,12 +3319,13 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
struct inet6_ifaddr *ifa;
struct ifmcaddr6 *ifmca;
struct ifacaddr6 *ifaca;
+ struct net *net = skb->sk->sk_net;
s_idx = cb->args[0];
s_ip_idx = ip_idx = cb->args[1];
idx = 0;
- for_each_netdev(&init_net, dev) {
+ for_each_netdev(net, dev) {
if (idx < s_idx)
goto cont;
if (idx > s_idx)
@@ -3389,35 +3392,23 @@ cont:
static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct net *net = skb->sk->sk_net;
enum addr_type_t type = UNICAST_ADDR;
- if (net != &init_net)
- return 0;
-
return inet6_dump_addr(skb, cb, type);
}
static int inet6_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct net *net = skb->sk->sk_net;
enum addr_type_t type = MULTICAST_ADDR;
- if (net != &init_net)
- return 0;
-
return inet6_dump_addr(skb, cb, type);
}
static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct net *net = skb->sk->sk_net;
enum addr_type_t type = ANYCAST_ADDR;
- if (net != &init_net)
- return 0;
-
return inet6_dump_addr(skb, cb, type);
}
@@ -3433,9 +3424,6 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh,
struct sk_buff *skb;
int err;
- if (net != &init_net)
- return -EINVAL;
-
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
if (err < 0)
goto errout;
@@ -3448,7 +3436,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh,
ifm = nlmsg_data(nlh);
if (ifm->ifa_index)
- dev = __dev_get_by_index(&init_net, ifm->ifa_index);
+ dev = __dev_get_by_index(net, ifm->ifa_index);
if ((ifa = ipv6_get_ifaddr(net, addr, dev, 1)) == NULL) {
err = -EADDRNOTAVAIL;
@@ -3468,7 +3456,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh,
kfree_skb(skb);
goto errout_ifa;
}
- err = rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).pid);
+ err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
errout_ifa:
in6_ifa_put(ifa);
errout:
@@ -3478,6 +3466,7 @@ errout:
static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
{
struct sk_buff *skb;
+ struct net *net = ifa->idev->dev->nd_net;
int err = -ENOBUFS;
skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
@@ -3491,10 +3480,10 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, &init_net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
+ err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
errout:
if (err < 0)
- rtnl_set_sk_err(&init_net, RTNLGRP_IPV6_IFADDR, err);
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err);
}
static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
@@ -3659,12 +3648,9 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
struct net_device *dev;
struct inet6_dev *idev;
- if (net != &init_net)
- return 0;
-
read_lock(&dev_base_lock);
idx = 0;
- for_each_netdev(&init_net, dev) {
+ for_each_netdev(net, dev) {
if (idx < s_idx)
goto cont;
if ((idev = in6_dev_get(dev)) == NULL)
@@ -3686,6 +3672,7 @@ cont:
void inet6_ifinfo_notify(int event, struct inet6_dev *idev)
{
struct sk_buff *skb;
+ struct net *net = idev->dev->nd_net;
int err = -ENOBUFS;
skb = nlmsg_new(inet6_if_nlmsg_size(), GFP_ATOMIC);
@@ -3699,10 +3686,10 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, &init_net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
+ err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
errout:
if (err < 0)
- rtnl_set_sk_err(&init_net, RTNLGRP_IPV6_IFADDR, err);
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err);
}
static inline size_t inet6_prefix_nlmsg_size(void)
@@ -3755,6 +3742,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
struct prefix_info *pinfo)
{
struct sk_buff *skb;
+ struct net *net = idev->dev->nd_net;
int err = -ENOBUFS;
skb = nlmsg_new(inet6_prefix_nlmsg_size(), GFP_ATOMIC);
@@ -3768,10 +3756,10 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, &init_net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC);
+ err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC);
errout:
if (err < 0)
- rtnl_set_sk_err(&init_net, RTNLGRP_IPV6_PREFIX, err);
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
}
static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
@@ -4261,6 +4249,41 @@ int unregister_inet6addr_notifier(struct notifier_block *nb)
EXPORT_SYMBOL(unregister_inet6addr_notifier);
+
+static int addrconf_net_init(struct net *net)
+{
+ return 0;
+}
+
+static void addrconf_net_exit(struct net *net)
+{
+ struct net_device *dev;
+
+ /*
+ * Remove loopback references from default routing entries
+ */
+/* in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev); */
+/* #ifdef CONFIG_IPV6_MULTIPLE_TABLES */
+/* in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev); */
+/* in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev); */
+/* #endif */
+
+ rtnl_lock();
+ /* clean dev list */
+ for_each_netdev(net, dev) {
+ if (__in6_dev_get(dev) == NULL)
+ continue;
+ addrconf_ifdown(dev, 1);
+ }
+ addrconf_ifdown(net->loopback_dev, 2);
+ rtnl_unlock();
+}
+
+static struct pernet_operations addrconf_net_ops = {
+ .init = addrconf_net_init,
+ .exit = addrconf_net_exit,
+};
+
/*
* Init / cleanup code
*/
@@ -4302,14 +4325,9 @@ int __init addrconf_init(void)
if (err)
goto errlo;
- ip6_null_entry.u.dst.dev = init_net.loopback_dev;
- ip6_null_entry.rt6i_idev = in6_dev_get(init_net.loopback_dev);
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
- ip6_prohibit_entry.u.dst.dev = init_net.loopback_dev;
- ip6_prohibit_entry.rt6i_idev = in6_dev_get(init_net.loopback_dev);
- ip6_blk_hole_entry.u.dst.dev = init_net.loopback_dev;
- ip6_blk_hole_entry.rt6i_idev = in6_dev_get(init_net.loopback_dev);
-#endif
+ err = register_pernet_device(&addrconf_net_ops);
+ if (err)
+ return err;
register_netdevice_notifier(&ipv6_dev_notf);
@@ -4339,31 +4357,19 @@ errlo:
void addrconf_cleanup(void)
{
- struct net_device *dev;
struct inet6_ifaddr *ifa;
int i;
unregister_netdevice_notifier(&ipv6_dev_notf);
+ unregister_pernet_device(&addrconf_net_ops);
unregister_pernet_subsys(&addrconf_ops);
rtnl_lock();
/*
- * clean dev list.
- */
-
- for_each_netdev(&init_net, dev) {
- if (__in6_dev_get(dev) == NULL)
- continue;
- addrconf_ifdown(dev, 1);
- }
- addrconf_ifdown(init_net.loopback_dev, 2);
-
- /*
* Check hash table.
*/
-
write_lock_bh(&addrconf_hash_lock);
for (i=0; i < IN6_ADDR_HSIZE; i++) {
for (ifa=inet6_addr_lst[i]; ifa; ) {
@@ -4380,6 +4386,7 @@ void addrconf_cleanup(void)
write_unlock_bh(&addrconf_hash_lock);
del_timer(&addr_chk_timer);
-
rtnl_unlock();
+
+ unregister_pernet_subsys(&addrconf_net_ops);
}
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index a3c5a72218f..3a8b3f52da3 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -58,6 +58,7 @@ static struct ip6addrlbl_table
* ::ffff:0:0/96 V4MAPPED 4
* fc00::/7 N/A 5 ULA (RFC 4193)
* 2001::/32 N/A 6 Teredo (RFC 4380)
+ * 2001:10::/28 N/A 7 ORCHID (RFC 4843)
*
* Note: 0xffffffff is used if we do not have any policies.
*/
@@ -85,6 +86,10 @@ static const __initdata struct ip6addrlbl_init_table
.prefix = &(struct in6_addr){{{ 0x20, 0x01 }}},
.prefixlen = 32,
.label = 6,
+ },{ /* 2001:10::/28 */
+ .prefix = &(struct in6_addr){{{ 0x20, 0x01, 0x00, 0x10 }}},
+ .prefixlen = 28,
+ .label = 7,
},{ /* ::ffff:0:0 */
.prefix = &(struct in6_addr){{{ [10] = 0xff, [11] = 0xff }}},
.prefixlen = 96,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f0aa9773874..afe9276d042 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -92,9 +92,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol)
int try_loading_module = 0;
int err;
- if (net != &init_net)
- return -EAFNOSUPPORT;
-
if (sock->type != SOCK_RAW &&
sock->type != SOCK_DGRAM &&
!inet_ehash_secret)
@@ -248,6 +245,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
+ struct net *net = sk->sk_net;
__be32 v4addr = 0;
unsigned short snum;
int addr_type = 0;
@@ -278,7 +276,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
/* Check if the address belongs to the host. */
if (addr_type == IPV6_ADDR_MAPPED) {
v4addr = addr->sin6_addr.s6_addr32[3];
- if (inet_addr_type(&init_net, v4addr) != RTN_LOCAL) {
+ if (inet_addr_type(net, v4addr) != RTN_LOCAL) {
err = -EADDRNOTAVAIL;
goto out;
}
@@ -300,7 +298,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
err = -EINVAL;
goto out;
}
- dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
if (!dev) {
err = -ENODEV;
goto out;
@@ -312,7 +310,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
*/
v4addr = LOOPBACK4_IPV6;
if (!(addr_type & IPV6_ADDR_MULTICAST)) {
- if (!ipv6_chk_addr(&init_net, &addr->sin6_addr,
+ if (!ipv6_chk_addr(net, &addr->sin6_addr,
dev, 0)) {
if (dev)
dev_put(dev);
@@ -440,6 +438,7 @@ EXPORT_SYMBOL(inet6_getname);
int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
+ struct net *net = sk->sk_net;
switch(cmd)
{
@@ -452,14 +451,14 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
case SIOCADDRT:
case SIOCDELRT:
- return(ipv6_route_ioctl(cmd,(void __user *)arg));
+ return(ipv6_route_ioctl(net, cmd, (void __user *)arg));
case SIOCSIFADDR:
- return addrconf_add_ifaddr((void __user *) arg);
+ return addrconf_add_ifaddr(net, (void __user *) arg);
case SIOCDIFADDR:
- return addrconf_del_ifaddr((void __user *) arg);
+ return addrconf_del_ifaddr(net, (void __user *) arg);
case SIOCSIFDSTADDR:
- return addrconf_set_dstaddr((void __user *) arg);
+ return addrconf_set_dstaddr(net, (void __user *) arg);
default:
if (!sk->sk_prot->ioctl)
return -ENOIOCTLCMD;
@@ -678,6 +677,129 @@ int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb)
EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
+static struct inet6_protocol *ipv6_gso_pull_exthdrs(struct sk_buff *skb,
+ int proto)
+{
+ struct inet6_protocol *ops = NULL;
+
+ for (;;) {
+ struct ipv6_opt_hdr *opth;
+ int len;
+
+ if (proto != NEXTHDR_HOP) {
+ ops = rcu_dereference(inet6_protos[proto]);
+
+ if (unlikely(!ops))
+ break;
+
+ if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
+ break;
+ }
+
+ if (unlikely(!pskb_may_pull(skb, 8)))
+ break;
+
+ opth = (void *)skb->data;
+ len = ipv6_optlen(opth);
+
+ if (unlikely(!pskb_may_pull(skb, len)))
+ break;
+
+ proto = opth->nexthdr;
+ __skb_pull(skb, len);
+ }
+
+ return ops;
+}
+
+static int ipv6_gso_send_check(struct sk_buff *skb)
+{
+ struct ipv6hdr *ipv6h;
+ struct inet6_protocol *ops;
+ int err = -EINVAL;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
+ goto out;
+
+ ipv6h = ipv6_hdr(skb);
+ __skb_pull(skb, sizeof(*ipv6h));
+ err = -EPROTONOSUPPORT;
+
+ rcu_read_lock();
+ ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
+ if (likely(ops && ops->gso_send_check)) {
+ skb_reset_transport_header(skb);
+ err = ops->gso_send_check(skb);
+ }
+ rcu_read_unlock();
+
+out:
+ return err;
+}
+
+static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ struct ipv6hdr *ipv6h;
+ struct inet6_protocol *ops;
+
+ if (!(features & NETIF_F_V6_CSUM))
+ features &= ~NETIF_F_SG;
+
+ if (unlikely(skb_shinfo(skb)->gso_type &
+ ~(SKB_GSO_UDP |
+ SKB_GSO_DODGY |
+ SKB_GSO_TCP_ECN |
+ SKB_GSO_TCPV6 |
+ 0)))
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
+ goto out;
+
+ ipv6h = ipv6_hdr(skb);
+ __skb_pull(skb, sizeof(*ipv6h));
+ segs = ERR_PTR(-EPROTONOSUPPORT);
+
+ rcu_read_lock();
+ ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
+ if (likely(ops && ops->gso_segment)) {
+ skb_reset_transport_header(skb);
+ segs = ops->gso_segment(skb, features);
+ }
+ rcu_read_unlock();
+
+ if (unlikely(IS_ERR(segs)))
+ goto out;
+
+ for (skb = segs; skb; skb = skb->next) {
+ ipv6h = ipv6_hdr(skb);
+ ipv6h->payload_len = htons(skb->len - skb->mac_len -
+ sizeof(*ipv6h));
+ }
+
+out:
+ return segs;
+}
+
+static struct packet_type ipv6_packet_type = {
+ .type = __constant_htons(ETH_P_IPV6),
+ .func = ipv6_rcv,
+ .gso_send_check = ipv6_gso_send_check,
+ .gso_segment = ipv6_gso_segment,
+};
+
+static int __init ipv6_packet_init(void)
+{
+ dev_add_pack(&ipv6_packet_type);
+ return 0;
+}
+
+static void ipv6_packet_cleanup(void)
+{
+ dev_remove_pack(&ipv6_packet_type);
+}
+
static int __init init_ipv6_mibs(void)
{
if (snmp_mib_init((void **)ipv6_statistics,
@@ -691,12 +813,16 @@ static int __init init_ipv6_mibs(void)
goto err_icmpmsg_mib;
if (snmp_mib_init((void **)udp_stats_in6, sizeof (struct udp_mib)) < 0)
goto err_udp_mib;
+#ifdef CONFIG_IP_UDPLITE
if (snmp_mib_init((void **)udplite_stats_in6,
sizeof (struct udp_mib)) < 0)
goto err_udplite_mib;
+#endif
return 0;
+#ifdef CONFIG_IP_UDPLITE
err_udplite_mib:
+#endif
snmp_mib_free((void **)udp_stats_in6);
err_udp_mib:
snmp_mib_free((void **)icmpv6msg_statistics);
@@ -715,7 +841,9 @@ static void cleanup_ipv6_mibs(void)
snmp_mib_free((void **)icmpv6_statistics);
snmp_mib_free((void **)icmpv6msg_statistics);
snmp_mib_free((void **)udp_stats_in6);
+#ifdef CONFIG_IP_UDPLITE
snmp_mib_free((void **)udplite_stats_in6);
+#endif
}
static int inet6_net_init(struct net *net)
@@ -760,9 +888,11 @@ static int __init inet6_init(void)
if (err)
goto out_unregister_tcp_proto;
+#ifdef CONFIG_IP_UDPLITE
err = proto_register(&udplitev6_prot, 1);
if (err)
goto out_unregister_udp_proto;
+#endif
err = proto_register(&rawv6_prot, 1);
if (err)
@@ -802,19 +932,13 @@ static int __init inet6_init(void)
err = register_pernet_subsys(&inet6_net_ops);
if (err)
goto register_pernet_fail;
-
-#ifdef CONFIG_SYSCTL
- err = ipv6_sysctl_register();
- if (err)
- goto sysctl_fail;
-#endif
- err = icmpv6_init(&inet6_family_ops);
+ err = icmpv6_init();
if (err)
goto icmp_fail;
- err = ndisc_init(&inet6_family_ops);
+ err = ndisc_init();
if (err)
goto ndisc_fail;
- err = igmp6_init(&inet6_family_ops);
+ err = igmp6_init();
if (err)
goto igmp_fail;
err = ipv6_netfilter_init();
@@ -874,9 +998,19 @@ static int __init inet6_init(void)
err = ipv6_packet_init();
if (err)
goto ipv6_packet_fail;
+
+#ifdef CONFIG_SYSCTL
+ err = ipv6_sysctl_register();
+ if (err)
+ goto sysctl_fail;
+#endif
out:
return err;
+#ifdef CONFIG_SYSCTL
+sysctl_fail:
+ ipv6_packet_cleanup();
+#endif
ipv6_packet_fail:
tcpv6_exit();
tcpv6_fail:
@@ -918,10 +1052,6 @@ igmp_fail:
ndisc_fail:
icmpv6_cleanup();
icmp_fail:
-#ifdef CONFIG_SYSCTL
- ipv6_sysctl_unregister();
-sysctl_fail:
-#endif
unregister_pernet_subsys(&inet6_net_ops);
register_pernet_fail:
cleanup_ipv6_mibs();
@@ -933,8 +1063,10 @@ out_sock_register_fail:
out_unregister_raw_proto:
proto_unregister(&rawv6_prot);
out_unregister_udplite_proto:
+#ifdef CONFIG_IP_UDPLITE
proto_unregister(&udplitev6_prot);
out_unregister_udp_proto:
+#endif
proto_unregister(&udpv6_prot);
out_unregister_tcp_proto:
proto_unregister(&tcpv6_prot);
@@ -949,8 +1081,13 @@ static void __exit inet6_exit(void)
/* Disallow any further netlink messages */
rtnl_unregister_all(PF_INET6);
+#ifdef CONFIG_SYSCTL
+ ipv6_sysctl_unregister();
+#endif
udpv6_exit();
+#ifdef CONFIG_IP_UDPLITE
udplitev6_exit();
+#endif
tcpv6_exit();
/* Cleanup code parts. */
@@ -976,13 +1113,13 @@ static void __exit inet6_exit(void)
ndisc_cleanup();
icmpv6_cleanup();
rawv6_exit();
-#ifdef CONFIG_SYSCTL
- ipv6_sysctl_unregister();
-#endif
+
unregister_pernet_subsys(&inet6_net_ops);
cleanup_ipv6_mibs();
proto_unregister(&rawv6_prot);
+#ifdef CONFIG_IP_UDPLITE
proto_unregister(&udplitev6_prot);
+#endif
proto_unregister(&udpv6_prot);
proto_unregister(&tcpv6_prot);
}
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 9c7f83fbc3a..96868b994b3 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -101,7 +101,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr)
if (ifindex == 0) {
struct rt6_info *rt;
- rt = rt6_lookup(addr, NULL, 0, 0);
+ rt = rt6_lookup(&init_net, addr, NULL, 0, 0);
if (rt) {
dev = rt->rt6i_dev;
dev_hold(dev);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 695c0ca8a41..55137408f05 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -29,24 +29,22 @@ struct fib6_rule
u8 tclass;
};
-static struct fib_rules_ops fib6_rules_ops;
-
-struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
- pol_lookup_t lookup)
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
+ int flags, pol_lookup_t lookup)
{
struct fib_lookup_arg arg = {
.lookup_ptr = lookup,
};
- fib_rules_lookup(&fib6_rules_ops, fl, flags, &arg);
+ fib_rules_lookup(net->ipv6.fib6_rules_ops, fl, flags, &arg);
if (arg.rule)
fib_rule_put(arg.rule);
if (arg.result)
return arg.result;
- dst_hold(&ip6_null_entry.u.dst);
- return &ip6_null_entry.u.dst;
+ dst_hold(&net->ipv6.ip6_null_entry->u.dst);
+ return &net->ipv6.ip6_null_entry->u.dst;
}
static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
@@ -54,28 +52,29 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
{
struct rt6_info *rt = NULL;
struct fib6_table *table;
+ struct net *net = rule->fr_net;
pol_lookup_t lookup = arg->lookup_ptr;
switch (rule->action) {
case FR_ACT_TO_TBL:
break;
case FR_ACT_UNREACHABLE:
- rt = &ip6_null_entry;
+ rt = net->ipv6.ip6_null_entry;
goto discard_pkt;
default:
case FR_ACT_BLACKHOLE:
- rt = &ip6_blk_hole_entry;
+ rt = net->ipv6.ip6_blk_hole_entry;
goto discard_pkt;
case FR_ACT_PROHIBIT:
- rt = &ip6_prohibit_entry;
+ rt = net->ipv6.ip6_prohibit_entry;
goto discard_pkt;
}
- table = fib6_get_table(rule->table);
+ table = fib6_get_table(net, rule->table);
if (table)
- rt = lookup(table, flp, flags);
+ rt = lookup(net, table, flp, flags);
- if (rt != &ip6_null_entry) {
+ if (rt != net->ipv6.ip6_null_entry) {
struct fib6_rule *r = (struct fib6_rule *)rule;
/*
@@ -85,8 +84,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
if ((rule->flags & FIB_RULE_FIND_SADDR) &&
r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
struct in6_addr saddr;
- if (ipv6_get_saddr(&rt->u.dst, &flp->fl6_dst,
- &saddr))
+ if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev,
+ &flp->fl6_dst, &saddr))
goto again;
if (!ipv6_prefix_equal(&saddr, &r->src.addr,
r->src.plen))
@@ -145,13 +144,14 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct nlattr **tb)
{
int err = -EINVAL;
+ struct net *net = skb->sk->sk_net;
struct fib6_rule *rule6 = (struct fib6_rule *) rule;
if (rule->action == FR_ACT_TO_TBL) {
if (rule->table == RT6_TABLE_UNSPEC)
goto errout;
- if (fib6_new_table(rule->table) == NULL) {
+ if (fib6_new_table(net, rule->table) == NULL) {
err = -ENOBUFS;
goto errout;
}
@@ -234,7 +234,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
+ nla_total_size(16); /* src */
}
-static struct fib_rules_ops fib6_rules_ops = {
+static struct fib_rules_ops fib6_rules_ops_template = {
.family = AF_INET6,
.rule_size = sizeof(struct fib6_rule),
.addr_size = sizeof(struct in6_addr),
@@ -247,45 +247,64 @@ static struct fib_rules_ops fib6_rules_ops = {
.nlmsg_payload = fib6_rule_nlmsg_payload,
.nlgroup = RTNLGRP_IPV6_RULE,
.policy = fib6_rule_policy,
- .rules_list = LIST_HEAD_INIT(fib6_rules_ops.rules_list),
.owner = THIS_MODULE,
.fro_net = &init_net,
};
-static int __init fib6_default_rules_init(void)
+static int fib6_rules_net_init(struct net *net)
{
- int err;
+ int err = -ENOMEM;
- err = fib_default_rule_add(&fib6_rules_ops, 0,
- RT6_TABLE_LOCAL, FIB_RULE_PERMANENT);
- if (err < 0)
- return err;
- err = fib_default_rule_add(&fib6_rules_ops, 0x7FFE, RT6_TABLE_MAIN, 0);
- if (err < 0)
- return err;
- return 0;
-}
+ net->ipv6.fib6_rules_ops = kmemdup(&fib6_rules_ops_template,
+ sizeof(*net->ipv6.fib6_rules_ops),
+ GFP_KERNEL);
+ if (!net->ipv6.fib6_rules_ops)
+ goto out;
-int __init fib6_rules_init(void)
-{
- int ret;
+ net->ipv6.fib6_rules_ops->fro_net = net;
+ INIT_LIST_HEAD(&net->ipv6.fib6_rules_ops->rules_list);
- ret = fib6_default_rules_init();
- if (ret)
- goto out;
+ err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0,
+ RT6_TABLE_LOCAL, FIB_RULE_PERMANENT);
+ if (err)
+ goto out_fib6_rules_ops;
- ret = fib_rules_register(&fib6_rules_ops);
- if (ret)
- goto out_default_rules_init;
+ err = fib_default_rule_add(net->ipv6.fib6_rules_ops,
+ 0x7FFE, RT6_TABLE_MAIN, 0);
+ if (err)
+ goto out_fib6_default_rule_add;
+
+ err = fib_rules_register(net->ipv6.fib6_rules_ops);
+ if (err)
+ goto out_fib6_default_rule_add;
out:
- return ret;
+ return err;
-out_default_rules_init:
- fib_rules_cleanup_ops(&fib6_rules_ops);
+out_fib6_default_rule_add:
+ fib_rules_cleanup_ops(net->ipv6.fib6_rules_ops);
+out_fib6_rules_ops:
+ kfree(net->ipv6.fib6_rules_ops);
goto out;
}
+static void fib6_rules_net_exit(struct net *net)
+{
+ fib_rules_unregister(net->ipv6.fib6_rules_ops);
+ kfree(net->ipv6.fib6_rules_ops);
+}
+
+static struct pernet_operations fib6_rules_net_ops = {
+ .init = fib6_rules_net_init,
+ .exit = fib6_rules_net_exit,
+};
+
+int __init fib6_rules_init(void)
+{
+ return register_pernet_subsys(&fib6_rules_net_ops);
+}
+
+
void fib6_rules_cleanup(void)
{
- fib_rules_unregister(&fib6_rules_ops);
+ return unregister_pernet_subsys(&fib6_rules_net_ops);
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 121d517bf91..6b5391ab834 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -80,8 +80,10 @@ EXPORT_SYMBOL(icmpv6msg_statistics);
*
* On SMP we have one ICMP socket per-cpu.
*/
-static DEFINE_PER_CPU(struct socket *, __icmpv6_socket) = NULL;
-#define icmpv6_socket __get_cpu_var(__icmpv6_socket)
+static inline struct sock *icmpv6_sk(struct net *net)
+{
+ return net->ipv6.icmp_sk[smp_processor_id()];
+}
static int icmpv6_rcv(struct sk_buff *skb);
@@ -90,11 +92,11 @@ static struct inet6_protocol icmpv6_protocol = {
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};
-static __inline__ int icmpv6_xmit_lock(void)
+static __inline__ int icmpv6_xmit_lock(struct sock *sk)
{
local_bh_disable();
- if (unlikely(!spin_trylock(&icmpv6_socket->sk->sk_lock.slock))) {
+ if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
/* This can happen if the output path (f.e. SIT or
* ip6ip6 tunnel) signals dst_link_failure() for an
* outgoing ICMP6 packet.
@@ -105,9 +107,9 @@ static __inline__ int icmpv6_xmit_lock(void)
return 0;
}
-static __inline__ void icmpv6_xmit_unlock(void)
+static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
{
- spin_unlock_bh(&icmpv6_socket->sk->sk_lock.slock);
+ spin_unlock_bh(&sk->sk_lock.slock);
}
/*
@@ -161,6 +163,7 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, int type,
struct flowi *fl)
{
struct dst_entry *dst;
+ struct net *net = sk->sk_net;
int res = 0;
/* Informational messages are not limited. */
@@ -176,7 +179,7 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, int type,
* XXX: perhaps the expire for routing entries cloned by
* this lookup should be more aggressive (not longer than timeout).
*/
- dst = ip6_route_output(sk, fl);
+ dst = ip6_route_output(net, sk, fl);
if (dst->error) {
IP6_INC_STATS(ip6_dst_idev(dst),
IPSTATS_MIB_OUTNOROUTES);
@@ -184,7 +187,7 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, int type,
res = 1;
} else {
struct rt6_info *rt = (struct rt6_info *)dst;
- int tmo = init_net.ipv6.sysctl.icmpv6_time;
+ int tmo = net->ipv6.sysctl.icmpv6_time;
/* Give more bandwidth to wider prefixes. */
if (rt->rt6i_dst.plen < 128)
@@ -303,6 +306,7 @@ static inline void mip6_addr_swap(struct sk_buff *skb) {}
void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
struct net_device *dev)
{
+ struct net *net = skb->dev->nd_net;
struct inet6_dev *idev = NULL;
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct sock *sk;
@@ -332,7 +336,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
*/
addr_type = ipv6_addr_type(&hdr->daddr);
- if (ipv6_chk_addr(&init_net, &hdr->daddr, skb->dev, 0))
+ if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0))
saddr = &hdr->daddr;
/*
@@ -389,12 +393,12 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
fl.fl_icmp_code = code;
security_skb_classify_flow(skb, &fl);
- if (icmpv6_xmit_lock())
- return;
-
- sk = icmpv6_socket->sk;
+ sk = icmpv6_sk(net);
np = inet6_sk(sk);
+ if (icmpv6_xmit_lock(sk))
+ return;
+
if (!icmpv6_xrlim_allow(sk, type, &fl))
goto out;
@@ -498,13 +502,14 @@ out_put:
out_dst_release:
dst_release(dst);
out:
- icmpv6_xmit_unlock();
+ icmpv6_xmit_unlock(sk);
}
EXPORT_SYMBOL(icmpv6_send);
static void icmpv6_echo_reply(struct sk_buff *skb)
{
+ struct net *net = skb->dev->nd_net;
struct sock *sk;
struct inet6_dev *idev;
struct ipv6_pinfo *np;
@@ -535,12 +540,12 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl.fl_icmp_type = ICMPV6_ECHO_REPLY;
security_skb_classify_flow(skb, &fl);
- if (icmpv6_xmit_lock())
- return;
-
- sk = icmpv6_socket->sk;
+ sk = icmpv6_sk(net);
np = inet6_sk(sk);
+ if (icmpv6_xmit_lock(sk))
+ return;
+
if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
fl.oif = np->mcast_oif;
@@ -584,7 +589,7 @@ out_put:
in6_dev_put(idev);
dst_release(dst);
out:
- icmpv6_xmit_unlock();
+ icmpv6_xmit_unlock(sk);
}
static void icmpv6_notify(struct sk_buff *skb, int type, int code, __be32 info)
@@ -775,19 +780,41 @@ drop_no_count:
return 0;
}
+void icmpv6_flow_init(struct sock *sk, struct flowi *fl,
+ u8 type,
+ const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ int oif)
+{
+ memset(fl, 0, sizeof(*fl));
+ ipv6_addr_copy(&fl->fl6_src, saddr);
+ ipv6_addr_copy(&fl->fl6_dst, daddr);
+ fl->proto = IPPROTO_ICMPV6;
+ fl->fl_icmp_type = type;
+ fl->fl_icmp_code = 0;
+ fl->oif = oif;
+ security_sk_classify_flow(sk, fl);
+}
+
/*
- * Special lock-class for __icmpv6_socket:
+ * Special lock-class for __icmpv6_sk:
*/
static struct lock_class_key icmpv6_socket_sk_dst_lock_key;
-int __init icmpv6_init(struct net_proto_family *ops)
+static int __net_init icmpv6_sk_init(struct net *net)
{
struct sock *sk;
int err, i, j;
+ net->ipv6.icmp_sk =
+ kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
+ if (net->ipv6.icmp_sk == NULL)
+ return -ENOMEM;
+
for_each_possible_cpu(i) {
+ struct socket *sock;
err = sock_create_kern(PF_INET6, SOCK_RAW, IPPROTO_ICMPV6,
- &per_cpu(__icmpv6_socket, i));
+ &sock);
if (err < 0) {
printk(KERN_ERR
"Failed to initialize the ICMP6 control socket "
@@ -796,12 +823,14 @@ int __init icmpv6_init(struct net_proto_family *ops)
goto fail;
}
- sk = per_cpu(__icmpv6_socket, i)->sk;
+ net->ipv6.icmp_sk[i] = sk = sock->sk;
+ sk_change_net(sk, net);
+
sk->sk_allocation = GFP_ATOMIC;
/*
* Split off their lock-class, because sk->sk_dst_lock
* gets used from softirqs, which is safe for
- * __icmpv6_socket (because those never get directly used
+ * __icmpv6_sk (because those never get directly used
* via userspace syscalls), but unsafe for normal sockets.
*/
lockdep_set_class(&sk->sk_dst_lock,
@@ -815,36 +844,56 @@ int __init icmpv6_init(struct net_proto_family *ops)
sk->sk_prot->unhash(sk);
}
-
-
- if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) {
- printk(KERN_ERR "Failed to register ICMP6 protocol\n");
- err = -EAGAIN;
- goto fail;
- }
-
return 0;
fail:
- for (j = 0; j < i; j++) {
- if (!cpu_possible(j))
- continue;
- sock_release(per_cpu(__icmpv6_socket, j));
- }
-
+ for (j = 0; j < i; j++)
+ sk_release_kernel(net->ipv6.icmp_sk[j]);
+ kfree(net->ipv6.icmp_sk);
return err;
}
-void icmpv6_cleanup(void)
+static void __net_exit icmpv6_sk_exit(struct net *net)
{
int i;
for_each_possible_cpu(i) {
- sock_release(per_cpu(__icmpv6_socket, i));
+ sk_release_kernel(net->ipv6.icmp_sk[i]);
}
+ kfree(net->ipv6.icmp_sk);
+}
+
+static struct pernet_operations icmpv6_sk_ops = {
+ .init = icmpv6_sk_init,
+ .exit = icmpv6_sk_exit,
+};
+
+int __init icmpv6_init(void)
+{
+ int err;
+
+ err = register_pernet_subsys(&icmpv6_sk_ops);
+ if (err < 0)
+ return err;
+
+ err = -EAGAIN;
+ if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0)
+ goto fail;
+ return 0;
+
+fail:
+ printk(KERN_ERR "Failed to register ICMP6 protocol\n");
+ unregister_pernet_subsys(&icmpv6_sk_ops);
+ return err;
+}
+
+void icmpv6_cleanup(void)
+{
+ unregister_pernet_subsys(&icmpv6_sk_ops);
inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
}
+
static const struct icmp6_err {
int err;
int fatal;
@@ -925,6 +974,10 @@ struct ctl_table *ipv6_icmp_sysctl_init(struct net *net)
table = kmemdup(ipv6_icmp_table_template,
sizeof(ipv6_icmp_table_template),
GFP_KERNEL);
+
+ if (table)
+ table[0].data = &net->ipv6.sysctl.icmpv6_time;
+
return table;
}
#endif
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index bab72b6f144..b0814b0082e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -48,8 +48,6 @@
#define RT6_TRACE(x...) do { ; } while (0)
#endif
-struct rt6_statistics rt6_stats;
-
static struct kmem_cache * fib6_node_kmem __read_mostly;
enum fib_walk_state_t
@@ -66,6 +64,7 @@ enum fib_walk_state_t
struct fib6_cleaner_t
{
struct fib6_walker_t w;
+ struct net *net;
int (*func)(struct rt6_info *, void *arg);
void *arg;
};
@@ -78,9 +77,10 @@ static DEFINE_RWLOCK(fib6_walker_lock);
#define FWS_INIT FWS_L
#endif
-static void fib6_prune_clones(struct fib6_node *fn, struct rt6_info *rt);
-static struct rt6_info * fib6_find_prefix(struct fib6_node *fn);
-static struct fib6_node * fib6_repair_tree(struct fib6_node *fn);
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
+ struct rt6_info *rt);
+static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
+static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
static int fib6_walk(struct fib6_walker_t *w);
static int fib6_walk_continue(struct fib6_walker_t *w);
@@ -93,7 +93,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w);
static __u32 rt_sernum;
-static DEFINE_TIMER(ip6_fib_timer, fib6_run_gc, 0, 0);
+static void fib6_gc_timer_cb(unsigned long arg);
static struct fib6_walker_t fib6_walker_list = {
.prev = &fib6_walker_list,
@@ -166,22 +166,13 @@ static __inline__ void rt6_release(struct rt6_info *rt)
dst_free(&rt->u.dst);
}
-static struct fib6_table fib6_main_tbl = {
- .tb6_id = RT6_TABLE_MAIN,
- .tb6_root = {
- .leaf = &ip6_null_entry,
- .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
- },
-};
-
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
#define FIB_TABLE_HASHSZ 256
#else
#define FIB_TABLE_HASHSZ 1
#endif
-static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
-static void fib6_link_table(struct fib6_table *tb)
+static void fib6_link_table(struct net *net, struct fib6_table *tb)
{
unsigned int h;
@@ -197,52 +188,46 @@ static void fib6_link_table(struct fib6_table *tb)
* No protection necessary, this is the only list mutatation
* operation, tables never disappear once they exist.
*/
- hlist_add_head_rcu(&tb->tb6_hlist, &fib_table_hash[h]);
+ hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]);
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-static struct fib6_table fib6_local_tbl = {
- .tb6_id = RT6_TABLE_LOCAL,
- .tb6_root = {
- .leaf = &ip6_null_entry,
- .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
- },
-};
-static struct fib6_table *fib6_alloc_table(u32 id)
+static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
{
struct fib6_table *table;
table = kzalloc(sizeof(*table), GFP_ATOMIC);
if (table != NULL) {
table->tb6_id = id;
- table->tb6_root.leaf = &ip6_null_entry;
+ table->tb6_root.leaf = net->ipv6.ip6_null_entry;
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
}
return table;
}
-struct fib6_table *fib6_new_table(u32 id)
+struct fib6_table *fib6_new_table(struct net *net, u32 id)
{
struct fib6_table *tb;
if (id == 0)
id = RT6_TABLE_MAIN;
- tb = fib6_get_table(id);
+ tb = fib6_get_table(net, id);
if (tb)
return tb;
- tb = fib6_alloc_table(id);
+ tb = fib6_alloc_table(net, id);
if (tb != NULL)
- fib6_link_table(tb);
+ fib6_link_table(net, tb);
return tb;
}
-struct fib6_table *fib6_get_table(u32 id)
+struct fib6_table *fib6_get_table(struct net *net, u32 id)
{
struct fib6_table *tb;
+ struct hlist_head *head;
struct hlist_node *node;
unsigned int h;
@@ -250,7 +235,8 @@ struct fib6_table *fib6_get_table(u32 id)
id = RT6_TABLE_MAIN;
h = id & (FIB_TABLE_HASHSZ - 1);
rcu_read_lock();
- hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb6_hlist) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) {
if (tb->tb6_id == id) {
rcu_read_unlock();
return tb;
@@ -261,33 +247,32 @@ struct fib6_table *fib6_get_table(u32 id)
return NULL;
}
-static void __init fib6_tables_init(void)
+static void fib6_tables_init(struct net *net)
{
- fib6_link_table(&fib6_main_tbl);
- fib6_link_table(&fib6_local_tbl);
+ fib6_link_table(net, net->ipv6.fib6_main_tbl);
+ fib6_link_table(net, net->ipv6.fib6_local_tbl);
}
-
#else
-struct fib6_table *fib6_new_table(u32 id)
+struct fib6_table *fib6_new_table(struct net *net, u32 id)
{
- return fib6_get_table(id);
+ return fib6_get_table(net, id);
}
-struct fib6_table *fib6_get_table(u32 id)
+struct fib6_table *fib6_get_table(struct net *net, u32 id)
{
- return &fib6_main_tbl;
+ return net->ipv6.fib6_main_tbl;
}
-struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
- pol_lookup_t lookup)
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
+ int flags, pol_lookup_t lookup)
{
- return (struct dst_entry *) lookup(&fib6_main_tbl, fl, flags);
+ return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl, flags);
}
-static void __init fib6_tables_init(void)
+static void fib6_tables_init(struct net *net)
{
- fib6_link_table(&fib6_main_tbl);
+ fib6_link_table(net, net->ipv6.fib6_main_tbl);
}
#endif
@@ -368,11 +353,9 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
struct fib6_walker_t *w;
struct fib6_table *tb;
struct hlist_node *node;
+ struct hlist_head *head;
int res = 0;
- if (net != &init_net)
- return 0;
-
s_h = cb->args[0];
s_e = cb->args[1];
@@ -401,7 +384,8 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
e = 0;
- hlist_for_each_entry(tb, node, &fib_table_hash[h], tb6_hlist) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry(tb, node, head, tb6_hlist) {
if (e < s_e)
goto next;
res = fib6_dump_table(tb, skb, cb);
@@ -667,29 +651,29 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
rt->rt6i_node = fn;
atomic_inc(&rt->rt6i_ref);
inet6_rt_notify(RTM_NEWROUTE, rt, info);
- rt6_stats.fib_rt_entries++;
+ info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
if ((fn->fn_flags & RTN_RTINFO) == 0) {
- rt6_stats.fib_route_nodes++;
+ info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
return 0;
}
-static __inline__ void fib6_start_gc(struct rt6_info *rt)
+static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt)
{
- if (ip6_fib_timer.expires == 0 &&
+ if (net->ipv6.ip6_fib_timer->expires == 0 &&
(rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE)))
- mod_timer(&ip6_fib_timer, jiffies +
- init_net.ipv6.sysctl.ip6_rt_gc_interval);
+ mod_timer(net->ipv6.ip6_fib_timer, jiffies +
+ net->ipv6.sysctl.ip6_rt_gc_interval);
}
-void fib6_force_start_gc(void)
+void fib6_force_start_gc(struct net *net)
{
- if (ip6_fib_timer.expires == 0)
- mod_timer(&ip6_fib_timer, jiffies +
- init_net.ipv6.sysctl.ip6_rt_gc_interval);
+ if (net->ipv6.ip6_fib_timer->expires == 0)
+ mod_timer(net->ipv6.ip6_fib_timer, jiffies +
+ net->ipv6.sysctl.ip6_rt_gc_interval);
}
/*
@@ -733,8 +717,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
if (sfn == NULL)
goto st_failure;
- sfn->leaf = &ip6_null_entry;
- atomic_inc(&ip6_null_entry.rt6i_ref);
+ sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
+ atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
sfn->fn_flags = RTN_ROOT;
sfn->fn_sernum = fib6_new_sernum();
@@ -776,9 +760,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
err = fib6_add_rt2node(fn, rt, info);
if (err == 0) {
- fib6_start_gc(rt);
+ fib6_start_gc(info->nl_net, rt);
if (!(rt->rt6i_flags&RTF_CACHE))
- fib6_prune_clones(pn, rt);
+ fib6_prune_clones(info->nl_net, pn, rt);
}
out:
@@ -789,11 +773,11 @@ out:
* super-tree leaf node we have to find a new one for it.
*/
if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) {
- pn->leaf = fib6_find_prefix(pn);
+ pn->leaf = fib6_find_prefix(info->nl_net, pn);
#if RT6_DEBUG >= 2
if (!pn->leaf) {
BUG_TRAP(pn->leaf != NULL);
- pn->leaf = &ip6_null_entry;
+ pn->leaf = info->nl_net->ipv6.ip6_null_entry;
}
#endif
atomic_inc(&pn->leaf->rt6i_ref);
@@ -809,7 +793,7 @@ out:
*/
st_failure:
if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
- fib6_repair_tree(fn);
+ fib6_repair_tree(info->nl_net, fn);
dst_free(&rt->u.dst);
return err;
#endif
@@ -975,10 +959,10 @@ struct fib6_node * fib6_locate(struct fib6_node *root,
*
*/
-static struct rt6_info * fib6_find_prefix(struct fib6_node *fn)
+static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
{
if (fn->fn_flags&RTN_ROOT)
- return &ip6_null_entry;
+ return net->ipv6.ip6_null_entry;
while(fn) {
if(fn->left)
@@ -997,7 +981,8 @@ static struct rt6_info * fib6_find_prefix(struct fib6_node *fn)
* is the node we want to try and remove.
*/
-static struct fib6_node * fib6_repair_tree(struct fib6_node *fn)
+static struct fib6_node *fib6_repair_tree(struct net *net,
+ struct fib6_node *fn)
{
int children;
int nstate;
@@ -1024,11 +1009,11 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn)
|| (children && fn->fn_flags&RTN_ROOT)
#endif
) {
- fn->leaf = fib6_find_prefix(fn);
+ fn->leaf = fib6_find_prefix(net, fn);
#if RT6_DEBUG >= 2
if (fn->leaf==NULL) {
BUG_TRAP(fn->leaf);
- fn->leaf = &ip6_null_entry;
+ fn->leaf = net->ipv6.ip6_null_entry;
}
#endif
atomic_inc(&fn->leaf->rt6i_ref);
@@ -1101,14 +1086,15 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
{
struct fib6_walker_t *w;
struct rt6_info *rt = *rtp;
+ struct net *net = info->nl_net;
RT6_TRACE("fib6_del_route\n");
/* Unlink it */
*rtp = rt->u.dst.rt6_next;
rt->rt6i_node = NULL;
- rt6_stats.fib_rt_entries--;
- rt6_stats.fib_discarded_routes++;
+ net->ipv6.rt6_stats->fib_rt_entries--;
+ net->ipv6.rt6_stats->fib_discarded_routes++;
/* Reset round-robin state, if necessary */
if (fn->rr_ptr == rt)
@@ -1131,8 +1117,8 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
/* If it was last route, expunge its radix tree node */
if (fn->leaf == NULL) {
fn->fn_flags &= ~RTN_RTINFO;
- rt6_stats.fib_route_nodes--;
- fn = fib6_repair_tree(fn);
+ net->ipv6.rt6_stats->fib_route_nodes--;
+ fn = fib6_repair_tree(net, fn);
}
if (atomic_read(&rt->rt6i_ref) != 1) {
@@ -1144,7 +1130,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
*/
while (fn) {
if (!(fn->fn_flags&RTN_RTINFO) && fn->leaf == rt) {
- fn->leaf = fib6_find_prefix(fn);
+ fn->leaf = fib6_find_prefix(net, fn);
atomic_inc(&fn->leaf->rt6i_ref);
rt6_release(rt);
}
@@ -1160,6 +1146,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
int fib6_del(struct rt6_info *rt, struct nl_info *info)
{
+ struct net *net = info->nl_net;
struct fib6_node *fn = rt->rt6i_node;
struct rt6_info **rtp;
@@ -1169,7 +1156,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
return -ENOENT;
}
#endif
- if (fn == NULL || rt == &ip6_null_entry)
+ if (fn == NULL || rt == net->ipv6.ip6_null_entry)
return -ENOENT;
BUG_TRAP(fn->fn_flags&RTN_RTINFO);
@@ -1184,7 +1171,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
pn = pn->parent;
}
#endif
- fib6_prune_clones(pn, rt);
+ fib6_prune_clones(info->nl_net, pn, rt);
}
/*
@@ -1314,12 +1301,12 @@ static int fib6_walk(struct fib6_walker_t *w)
static int fib6_clean_node(struct fib6_walker_t *w)
{
- struct nl_info info = {
- .nl_net = &init_net,
- };
int res;
struct rt6_info *rt;
struct fib6_cleaner_t *c = container_of(w, struct fib6_cleaner_t, w);
+ struct nl_info info = {
+ .nl_net = c->net,
+ };
for (rt = w->leaf; rt; rt = rt->u.dst.rt6_next) {
res = c->func(rt, c->arg);
@@ -1351,7 +1338,7 @@ static int fib6_clean_node(struct fib6_walker_t *w)
* ignoring pure split nodes) will be scanned.
*/
-static void fib6_clean_tree(struct fib6_node *root,
+static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct rt6_info *, void *arg),
int prune, void *arg)
{
@@ -1362,23 +1349,26 @@ static void fib6_clean_tree(struct fib6_node *root,
c.w.prune = prune;
c.func = func;
c.arg = arg;
+ c.net = net;
fib6_walk(&c.w);
}
-void fib6_clean_all(int (*func)(struct rt6_info *, void *arg),
+void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
int prune, void *arg)
{
struct fib6_table *table;
struct hlist_node *node;
+ struct hlist_head *head;
unsigned int h;
rcu_read_lock();
for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
- hlist_for_each_entry_rcu(table, node, &fib_table_hash[h],
- tb6_hlist) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(table, node, head, tb6_hlist) {
write_lock_bh(&table->tb6_lock);
- fib6_clean_tree(&table->tb6_root, func, prune, arg);
+ fib6_clean_tree(net, &table->tb6_root,
+ func, prune, arg);
write_unlock_bh(&table->tb6_lock);
}
}
@@ -1395,9 +1385,10 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
return 0;
}
-static void fib6_prune_clones(struct fib6_node *fn, struct rt6_info *rt)
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
+ struct rt6_info *rt)
{
- fib6_clean_tree(fn, fib6_prune_clone, 1, rt);
+ fib6_clean_tree(net, fn, fib6_prune_clone, 1, rt);
}
/*
@@ -1447,54 +1438,145 @@ static int fib6_age(struct rt6_info *rt, void *arg)
static DEFINE_SPINLOCK(fib6_gc_lock);
-void fib6_run_gc(unsigned long dummy)
+void fib6_run_gc(unsigned long expires, struct net *net)
{
- if (dummy != ~0UL) {
+ if (expires != ~0UL) {
spin_lock_bh(&fib6_gc_lock);
- gc_args.timeout = dummy ? (int)dummy :
- init_net.ipv6.sysctl.ip6_rt_gc_interval;
+ gc_args.timeout = expires ? (int)expires :
+ net->ipv6.sysctl.ip6_rt_gc_interval;
} else {
local_bh_disable();
if (!spin_trylock(&fib6_gc_lock)) {
- mod_timer(&ip6_fib_timer, jiffies + HZ);
+ mod_timer(net->ipv6.ip6_fib_timer, jiffies + HZ);
local_bh_enable();
return;
}
- gc_args.timeout = init_net.ipv6.sysctl.ip6_rt_gc_interval;
+ gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval;
}
gc_args.more = 0;
- ndisc_dst_gc(&gc_args.more);
- fib6_clean_all(fib6_age, 0, NULL);
+ icmp6_dst_gc(&gc_args.more);
+
+ fib6_clean_all(net, fib6_age, 0, NULL);
if (gc_args.more)
- mod_timer(&ip6_fib_timer, jiffies +
- init_net.ipv6.sysctl.ip6_rt_gc_interval);
+ mod_timer(net->ipv6.ip6_fib_timer, jiffies +
+ net->ipv6.sysctl.ip6_rt_gc_interval);
else {
- del_timer(&ip6_fib_timer);
- ip6_fib_timer.expires = 0;
+ del_timer(net->ipv6.ip6_fib_timer);
+ net->ipv6.ip6_fib_timer->expires = 0;
}
spin_unlock_bh(&fib6_gc_lock);
}
-int __init fib6_init(void)
+static void fib6_gc_timer_cb(unsigned long arg)
+{
+ fib6_run_gc(0, (struct net *)arg);
+}
+
+static int fib6_net_init(struct net *net)
{
int ret;
+ struct timer_list *timer;
+
+ ret = -ENOMEM;
+ timer = kzalloc(sizeof(*timer), GFP_KERNEL);
+ if (!timer)
+ goto out;
+
+ setup_timer(timer, fib6_gc_timer_cb, (unsigned long)net);
+ net->ipv6.ip6_fib_timer = timer;
+
+ net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL);
+ if (!net->ipv6.rt6_stats)
+ goto out_timer;
+
+ net->ipv6.fib_table_hash =
+ kzalloc(sizeof(*net->ipv6.fib_table_hash)*FIB_TABLE_HASHSZ,
+ GFP_KERNEL);
+ if (!net->ipv6.fib_table_hash)
+ goto out_rt6_stats;
+
+ net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl),
+ GFP_KERNEL);
+ if (!net->ipv6.fib6_main_tbl)
+ goto out_fib_table_hash;
+
+ net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
+ net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
+ net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
+ RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl),
+ GFP_KERNEL);
+ if (!net->ipv6.fib6_local_tbl)
+ goto out_fib6_main_tbl;
+ net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
+ net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
+ net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
+ RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+#endif
+ fib6_tables_init(net);
+
+ ret = 0;
+out:
+ return ret;
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+out_fib6_main_tbl:
+ kfree(net->ipv6.fib6_main_tbl);
+#endif
+out_fib_table_hash:
+ kfree(net->ipv6.fib_table_hash);
+out_rt6_stats:
+ kfree(net->ipv6.rt6_stats);
+out_timer:
+ kfree(timer);
+ goto out;
+ }
+
+static void fib6_net_exit(struct net *net)
+{
+ rt6_ifdown(net, NULL);
+ del_timer(net->ipv6.ip6_fib_timer);
+ kfree(net->ipv6.ip6_fib_timer);
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ kfree(net->ipv6.fib6_local_tbl);
+#endif
+ kfree(net->ipv6.fib6_main_tbl);
+ kfree(net->ipv6.fib_table_hash);
+ kfree(net->ipv6.rt6_stats);
+}
+
+static struct pernet_operations fib6_net_ops = {
+ .init = fib6_net_init,
+ .exit = fib6_net_exit,
+};
+
+int __init fib6_init(void)
+{
+ int ret = -ENOMEM;
+
fib6_node_kmem = kmem_cache_create("fib6_nodes",
sizeof(struct fib6_node),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (!fib6_node_kmem)
- return -ENOMEM;
+ goto out;
- fib6_tables_init();
+ ret = register_pernet_subsys(&fib6_net_ops);
+ if (ret)
+ goto out_kmem_cache_create;
ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib);
if (ret)
- goto out_kmem_cache_create;
+ goto out_unregister_subsys;
out:
return ret;
+out_unregister_subsys:
+ unregister_pernet_subsys(&fib6_net_ops);
out_kmem_cache_create:
kmem_cache_destroy(fib6_node_kmem);
goto out;
@@ -1502,6 +1584,6 @@ out_kmem_cache_create:
void fib6_gc_cleanup(void)
{
- del_timer(&ip6_fib_timer);
+ unregister_pernet_subsys(&fib6_net_ops);
kmem_cache_destroy(fib6_node_kmem);
}
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 178aebc0427..7e36269826b 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -61,11 +61,6 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
u32 pkt_len;
struct inet6_dev *idev;
- if (dev->nd_net != &init_net) {
- kfree_skb(skb);
- return 0;
- }
-
if (skb->pkt_type == PACKET_OTHERHOST) {
kfree_skb(skb);
return 0;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 8b67ca07467..937018529d1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -596,7 +596,6 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
return offset;
}
-EXPORT_SYMBOL_GPL(ip6_find_1stfragopt);
static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
@@ -914,13 +913,14 @@ static int ip6_dst_lookup_tail(struct sock *sk,
int err;
if (*dst == NULL)
- *dst = ip6_route_output(sk, fl);
+ *dst = ip6_route_output(sk->sk_net, sk, fl);
if ((err = (*dst)->error))
goto out_err_release;
if (ipv6_addr_any(&fl->fl6_src)) {
- err = ipv6_get_saddr(*dst, &fl->fl6_dst, &fl->fl6_src);
+ err = ipv6_dev_get_saddr(ip6_dst_idev(*dst)->dev,
+ &fl->fl6_dst, &fl->fl6_src);
if (err)
goto out_err_release;
}
@@ -954,7 +954,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
dst_release(*dst);
memcpy(&fl_gw, fl, sizeof(struct flowi));
memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
- *dst = ip6_route_output(sk, &fl_gw);
+ *dst = ip6_route_output(sk->sk_net, sk, &fl_gw);
if ((err = (*dst)->error))
goto out_err_release;
}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 78f43888092..1e1ad1ed87e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -602,7 +602,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
skb_reset_network_header(skb2);
/* Try to guess incoming interface */
- rt = rt6_lookup(&ipv6_hdr(skb2)->saddr, NULL, 0, 0);
+ rt = rt6_lookup(&init_net, &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
if (rt && rt->rt6i_dev)
skb2->dev = rt->rt6i_dev;
@@ -847,7 +847,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
if ((dst = ip6_tnl_dst_check(t)) != NULL)
dst_hold(dst);
else {
- dst = ip6_route_output(NULL, fl);
+ dst = ip6_route_output(&init_net, NULL, fl);
if (dst->error || xfrm_lookup(&dst, fl, NULL, 0) < 0)
goto tx_err_link_failure;
@@ -1112,7 +1112,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
int strict = (ipv6_addr_type(&p->raddr) &
(IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
- struct rt6_info *rt = rt6_lookup(&p->raddr, &p->laddr,
+ struct rt6_info *rt = rt6_lookup(&init_net, &p->raddr, &p->laddr,
p->link, strict);
if (rt == NULL)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index bf2a686aa13..3bbfdff698d 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -57,118 +57,6 @@
DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics) __read_mostly;
-static struct inet6_protocol *ipv6_gso_pull_exthdrs(struct sk_buff *skb,
- int proto)
-{
- struct inet6_protocol *ops = NULL;
-
- for (;;) {
- struct ipv6_opt_hdr *opth;
- int len;
-
- if (proto != NEXTHDR_HOP) {
- ops = rcu_dereference(inet6_protos[proto]);
-
- if (unlikely(!ops))
- break;
-
- if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
- break;
- }
-
- if (unlikely(!pskb_may_pull(skb, 8)))
- break;
-
- opth = (void *)skb->data;
- len = opth->hdrlen * 8 + 8;
-
- if (unlikely(!pskb_may_pull(skb, len)))
- break;
-
- proto = opth->nexthdr;
- __skb_pull(skb, len);
- }
-
- return ops;
-}
-
-static int ipv6_gso_send_check(struct sk_buff *skb)
-{
- struct ipv6hdr *ipv6h;
- struct inet6_protocol *ops;
- int err = -EINVAL;
-
- if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
- goto out;
-
- ipv6h = ipv6_hdr(skb);
- __skb_pull(skb, sizeof(*ipv6h));
- err = -EPROTONOSUPPORT;
-
- rcu_read_lock();
- ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
- if (likely(ops && ops->gso_send_check)) {
- skb_reset_transport_header(skb);
- err = ops->gso_send_check(skb);
- }
- rcu_read_unlock();
-
-out:
- return err;
-}
-
-static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
-{
- struct sk_buff *segs = ERR_PTR(-EINVAL);
- struct ipv6hdr *ipv6h;
- struct inet6_protocol *ops;
-
- if (!(features & NETIF_F_V6_CSUM))
- features &= ~NETIF_F_SG;
-
- if (unlikely(skb_shinfo(skb)->gso_type &
- ~(SKB_GSO_UDP |
- SKB_GSO_DODGY |
- SKB_GSO_TCP_ECN |
- SKB_GSO_TCPV6 |
- 0)))
- goto out;
-
- if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
- goto out;
-
- ipv6h = ipv6_hdr(skb);
- __skb_pull(skb, sizeof(*ipv6h));
- segs = ERR_PTR(-EPROTONOSUPPORT);
-
- rcu_read_lock();
- ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
- if (likely(ops && ops->gso_segment)) {
- skb_reset_transport_header(skb);
- segs = ops->gso_segment(skb, features);
- }
- rcu_read_unlock();
-
- if (unlikely(IS_ERR(segs)))
- goto out;
-
- for (skb = segs; skb; skb = skb->next) {
- ipv6h = ipv6_hdr(skb);
- ipv6h->payload_len = htons(skb->len - skb->mac_len -
- sizeof(*ipv6h));
- }
-
-out:
- return segs;
-}
-
-static struct packet_type ipv6_packet_type = {
- .type = __constant_htons(ETH_P_IPV6),
- .func = ipv6_rcv,
- .gso_send_check = ipv6_gso_send_check,
- .gso_segment = ipv6_gso_segment,
-};
-
struct ip6_ra_chain *ip6_ra_chain;
DEFINE_RWLOCK(ip6_ra_lock);
@@ -239,7 +127,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
struct sk_buff *pktopt;
if (sk->sk_protocol != IPPROTO_UDP &&
+#ifdef CONFIG_IP_UDPLITE
sk->sk_protocol != IPPROTO_UDPLITE &&
+#endif
sk->sk_protocol != IPPROTO_TCP)
break;
@@ -279,7 +169,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
} else {
struct proto *prot = &udp_prot;
- if (sk->sk_protocol == IPPROTO_UDPLITE)
+ if (IS_PROTO_UDPLITE(sk->sk_protocol))
prot = &udplite_prot;
local_bh_disable();
sock_prot_inuse_add(sk->sk_prot, -1);
@@ -844,7 +734,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
switch (optname) {
case IPV6_ADDRFORM:
if (sk->sk_protocol != IPPROTO_UDP &&
+#ifdef CONFIG_IP_UDPLITE
sk->sk_protocol != IPPROTO_UDPLITE &&
+#endif
sk->sk_protocol != IPPROTO_TCP)
return -EINVAL;
if (sk->sk_state != TCP_ESTABLISHED)
@@ -1128,13 +1020,3 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
EXPORT_SYMBOL(compat_ipv6_getsockopt);
#endif
-int __init ipv6_packet_init(void)
-{
- dev_add_pack(&ipv6_packet_type);
- return 0;
-}
-
-void ipv6_packet_cleanup(void)
-{
- dev_remove_pack(&ipv6_packet_type);
-}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index ab228d1ea11..197ca390a15 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -208,7 +208,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr)
if (ifindex == 0) {
struct rt6_info *rt;
- rt = rt6_lookup(addr, NULL, 0, 0);
+ rt = rt6_lookup(&init_net, addr, NULL, 0, 0);
if (rt) {
dev = rt->rt6i_dev;
dev_hold(dev);
@@ -294,7 +294,7 @@ static struct inet6_dev *ip6_mc_find_dev(struct in6_addr *group, int ifindex)
if (ifindex == 0) {
struct rt6_info *rt;
- rt = rt6_lookup(group, NULL, 0, 0);
+ rt = rt6_lookup(&init_net, group, NULL, 0, 0);
if (rt) {
dev = rt->rt6i_dev;
dev_hold(dev);
@@ -1433,25 +1433,6 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size)
return skb;
}
-static inline int mld_dev_queue_xmit2(struct sk_buff *skb)
-{
- struct net_device *dev = skb->dev;
- unsigned char ha[MAX_ADDR_LEN];
-
- ndisc_mc_map(&ipv6_hdr(skb)->daddr, ha, dev, 1);
- if (dev_hard_header(skb, dev, ETH_P_IPV6, ha, NULL, skb->len) < 0) {
- kfree_skb(skb);
- return -EINVAL;
- }
- return dev_queue_xmit(skb);
-}
-
-static inline int mld_dev_queue_xmit(struct sk_buff *skb)
-{
- return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
- mld_dev_queue_xmit2);
-}
-
static void mld_sendpack(struct sk_buff *skb)
{
struct ipv6hdr *pip6 = ipv6_hdr(skb);
@@ -1460,6 +1441,7 @@ static void mld_sendpack(struct sk_buff *skb)
int payload_len, mldlen;
struct inet6_dev *idev = in6_dev_get(skb->dev);
int err;
+ struct flowi fl;
IP6_INC_STATS(idev, IPSTATS_MIB_OUTREQUESTS);
payload_len = (skb->tail - skb->network_header) - sizeof(*pip6);
@@ -1469,8 +1451,25 @@ static void mld_sendpack(struct sk_buff *skb)
pmr->csum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen,
IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb),
mldlen, 0));
+
+ skb->dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr);
+
+ if (!skb->dst) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ icmpv6_flow_init(igmp6_socket->sk, &fl, ICMPV6_MLD2_REPORT,
+ &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
+ skb->dev->ifindex);
+
+ err = xfrm_lookup(&skb->dst, &fl, NULL, 0);
+ if (err)
+ goto err_out;
+
err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
- mld_dev_queue_xmit);
+ dst_output);
+out:
if (!err) {
ICMP6MSGOUT_INC_STATS_BH(idev, ICMPV6_MLD2_REPORT);
ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTMSGS);
@@ -1480,6 +1479,11 @@ static void mld_sendpack(struct sk_buff *skb)
if (likely(idev != NULL))
in6_dev_put(idev);
+ return;
+
+err_out:
+ kfree_skb(skb);
+ goto out;
}
static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel)
@@ -1761,6 +1765,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
u8 ra[8] = { IPPROTO_ICMPV6, 0,
IPV6_TLV_ROUTERALERT, 2, 0, 0,
IPV6_TLV_PADN, 0 };
+ struct flowi fl;
rcu_read_lock();
IP6_INC_STATS(__in6_dev_get(dev),
@@ -1813,8 +1818,23 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
idev = in6_dev_get(skb->dev);
+ skb->dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr);
+ if (!skb->dst) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ icmpv6_flow_init(igmp6_socket->sk, &fl, type,
+ &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
+ skb->dev->ifindex);
+
+ err = xfrm_lookup(&skb->dst, &fl, NULL, 0);
+ if (err)
+ goto err_out;
+
err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
- mld_dev_queue_xmit);
+ dst_output);
+out:
if (!err) {
ICMP6MSGOUT_INC_STATS(idev, type);
ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS);
@@ -1825,6 +1845,10 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
if (likely(idev != NULL))
in6_dev_put(idev);
return;
+
+err_out:
+ kfree_skb(skb);
+ goto out;
}
static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode,
@@ -2597,7 +2621,7 @@ static const struct file_operations igmp6_mcf_seq_fops = {
};
#endif
-int __init igmp6_init(struct net_proto_family *ops)
+int __init igmp6_init(void)
{
struct ipv6_pinfo *np;
struct sock *sk;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 0d33a7d3212..b5b4fd173e9 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -441,21 +441,6 @@ static void pndisc_destructor(struct pneigh_entry *n)
/*
* Send a Neighbour Advertisement
*/
-
-static inline void ndisc_flow_init(struct flowi *fl, u8 type,
- struct in6_addr *saddr, struct in6_addr *daddr,
- int oif)
-{
- memset(fl, 0, sizeof(*fl));
- ipv6_addr_copy(&fl->fl6_src, saddr);
- ipv6_addr_copy(&fl->fl6_dst, daddr);
- fl->proto = IPPROTO_ICMPV6;
- fl->fl_icmp_type = type;
- fl->fl_icmp_code = 0;
- fl->oif = oif;
- security_sk_classify_flow(ndisc_socket->sk, fl);
-}
-
static void __ndisc_send(struct net_device *dev,
struct neighbour *neigh,
struct in6_addr *daddr, struct in6_addr *saddr,
@@ -474,10 +459,10 @@ static void __ndisc_send(struct net_device *dev,
type = icmp6h->icmp6_type;
- ndisc_flow_init(&fl, type, saddr, daddr,
- dev->ifindex);
+ icmpv6_flow_init(ndisc_socket->sk, &fl, type,
+ saddr, daddr, dev->ifindex);
- dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output);
+ dst = icmp6_dst_alloc(dev, neigh, daddr);
if (!dst)
return;
@@ -1439,10 +1424,10 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
return;
}
- ndisc_flow_init(&fl, NDISC_REDIRECT, &saddr_buf, &ipv6_hdr(skb)->saddr,
- dev->ifindex);
+ icmpv6_flow_init(ndisc_socket->sk, &fl, NDISC_REDIRECT,
+ &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex);
- dst = ip6_route_output(NULL, &fl);
+ dst = ip6_route_output(&init_net, NULL, &fl);
if (dst == NULL)
return;
@@ -1613,6 +1598,7 @@ int ndisc_rcv(struct sk_buff *skb)
static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
+ struct net *net = dev->nd_net;
if (dev->nd_net != &init_net)
return NOTIFY_DONE;
@@ -1620,11 +1606,11 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
switch (event) {
case NETDEV_CHANGEADDR:
neigh_changeaddr(&nd_tbl, dev);
- fib6_run_gc(~0UL);
+ fib6_run_gc(~0UL, net);
break;
case NETDEV_DOWN:
neigh_ifdown(&nd_tbl, dev);
- fib6_run_gc(~0UL);
+ fib6_run_gc(~0UL, net);
break;
default:
break;
@@ -1733,7 +1719,7 @@ static int ndisc_ifinfo_sysctl_strategy(ctl_table *ctl, int __user *name,
#endif
-int __init ndisc_init(struct net_proto_family *ops)
+int __init ndisc_init(void)
{
struct ipv6_pinfo *np;
struct sock *sk;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 2e06724dc34..aed51bcc66b 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -23,7 +23,7 @@ int ip6_route_me_harder(struct sk_buff *skb)
.saddr = iph->saddr, } },
};
- dst = ip6_route_output(skb->sk, &fl);
+ dst = ip6_route_output(&init_net, skb->sk, &fl);
#ifdef CONFIG_XFRM
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
@@ -86,7 +86,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl)
{
- *dst = ip6_route_output(NULL, fl);
+ *dst = ip6_route_output(&init_net, NULL, fl);
return (*dst)->error;
}
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index b23baa635fe..831708aeab3 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -93,7 +93,7 @@ static void send_reset(struct sk_buff *oldskb)
fl.fl_ip_sport = otcph.dest;
fl.fl_ip_dport = otcph.source;
security_skb_classify_flow(oldskb, &fl);
- dst = ip6_route_output(NULL, &fl);
+ dst = ip6_route_output(&init_net, NULL, &fl);
if (dst == NULL)
return;
if (dst->error || xfrm_lookup(&dst, &fl, NULL, 0))
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 199ef379e50..2453f2229ef 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -39,8 +39,10 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(&tcpv6_prot));
seq_printf(seq, "UDP6: inuse %d\n",
sock_prot_inuse_get(&udpv6_prot));
+#ifdef CONFIG_IP_UDPLITE
seq_printf(seq, "UDPLITE6: inuse %d\n",
sock_prot_inuse_get(&udplitev6_prot));
+#endif
seq_printf(seq, "RAW6: inuse %d\n",
sock_prot_inuse_get(&rawv6_prot));
seq_printf(seq, "FRAG6: inuse %d memory %d\n",
@@ -111,6 +113,7 @@ static struct snmp_mib snmp6_udp6_list[] = {
SNMP_MIB_SENTINEL
};
+#ifdef CONFIG_IP_UDPLITE
static struct snmp_mib snmp6_udplite6_list[] = {
SNMP_MIB_ITEM("UdpLite6InDatagrams", UDP_MIB_INDATAGRAMS),
SNMP_MIB_ITEM("UdpLite6NoPorts", UDP_MIB_NOPORTS),
@@ -118,6 +121,7 @@ static struct snmp_mib snmp6_udplite6_list[] = {
SNMP_MIB_ITEM("UdpLite6OutDatagrams", UDP_MIB_OUTDATAGRAMS),
SNMP_MIB_SENTINEL
};
+#endif
static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib)
{
@@ -176,7 +180,9 @@ static int snmp6_seq_show(struct seq_file *seq, void *v)
snmp6_seq_show_item(seq, (void **)icmpv6_statistics, snmp6_icmp6_list);
snmp6_seq_show_icmpv6msg(seq, (void **)icmpv6msg_statistics);
snmp6_seq_show_item(seq, (void **)udp_stats_in6, snmp6_udp6_list);
+#ifdef CONFIG_IP_UDPLITE
snmp6_seq_show_item(seq, (void **)udplite_stats_in6, snmp6_udplite6_list);
+#endif
}
return 0;
}
@@ -214,6 +220,9 @@ int snmp6_register_dev(struct inet6_dev *idev)
if (!idev || !idev->dev)
return -EINVAL;
+ if (idev->dev->nd_net != &init_net)
+ return 0;
+
if (!proc_net_devsnmp6)
return -ENOENT;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e8b241cb60b..f31d7dc11e7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -40,6 +40,7 @@
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/nsproxy.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
@@ -87,14 +88,16 @@ static void ip6_link_failure(struct sk_buff *skb);
static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen,
+static struct rt6_info *rt6_add_route_info(struct net *net,
+ struct in6_addr *prefix, int prefixlen,
struct in6_addr *gwaddr, int ifindex,
unsigned pref);
-static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen,
+static struct rt6_info *rt6_get_route_info(struct net *net,
+ struct in6_addr *prefix, int prefixlen,
struct in6_addr *gwaddr, int ifindex);
#endif
-static struct dst_ops ip6_dst_ops = {
+static struct dst_ops ip6_dst_ops_template = {
.family = AF_INET6,
.protocol = __constant_htons(ETH_P_IPV6),
.gc = ip6_dst_gc,
@@ -124,7 +127,7 @@ static struct dst_ops ip6_dst_blackhole_ops = {
.entries = ATOMIC_INIT(0),
};
-struct rt6_info ip6_null_entry = {
+static struct rt6_info ip6_null_entry_template = {
.u = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
@@ -134,8 +137,6 @@ struct rt6_info ip6_null_entry = {
.metrics = { [RTAX_HOPLIMIT - 1] = 255, },
.input = ip6_pkt_discard,
.output = ip6_pkt_discard_out,
- .ops = &ip6_dst_ops,
- .path = (struct dst_entry*)&ip6_null_entry,
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
@@ -148,7 +149,7 @@ struct rt6_info ip6_null_entry = {
static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct sk_buff *skb);
-struct rt6_info ip6_prohibit_entry = {
+struct rt6_info ip6_prohibit_entry_template = {
.u = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
@@ -158,8 +159,6 @@ struct rt6_info ip6_prohibit_entry = {
.metrics = { [RTAX_HOPLIMIT - 1] = 255, },
.input = ip6_pkt_prohibit,
.output = ip6_pkt_prohibit_out,
- .ops = &ip6_dst_ops,
- .path = (struct dst_entry*)&ip6_prohibit_entry,
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
@@ -167,7 +166,7 @@ struct rt6_info ip6_prohibit_entry = {
.rt6i_ref = ATOMIC_INIT(1),
};
-struct rt6_info ip6_blk_hole_entry = {
+static struct rt6_info ip6_blk_hole_entry_template = {
.u = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
@@ -177,8 +176,6 @@ struct rt6_info ip6_blk_hole_entry = {
.metrics = { [RTAX_HOPLIMIT - 1] = 255, },
.input = dst_discard,
.output = dst_discard,
- .ops = &ip6_dst_ops,
- .path = (struct dst_entry*)&ip6_blk_hole_entry,
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
@@ -189,9 +186,9 @@ struct rt6_info ip6_blk_hole_entry = {
#endif
/* allocate dst with ip6_dst_ops */
-static __inline__ struct rt6_info *ip6_dst_alloc(void)
+static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops)
{
- return (struct rt6_info *)dst_alloc(&ip6_dst_ops);
+ return (struct rt6_info *)dst_alloc(ops);
}
static void ip6_dst_destroy(struct dst_entry *dst)
@@ -239,7 +236,8 @@ static inline int rt6_need_strict(struct in6_addr *daddr)
* Route lookup. Any table->tb6_lock is implied.
*/
-static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt,
+static inline struct rt6_info *rt6_device_match(struct net *net,
+ struct rt6_info *rt,
int oif,
int strict)
{
@@ -268,7 +266,7 @@ static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt,
return local;
if (strict)
- return &ip6_null_entry;
+ return net->ipv6.ip6_null_entry;
}
return rt;
}
@@ -409,6 +407,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
{
struct rt6_info *match, *rt0;
+ struct net *net;
RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n",
__FUNCTION__, fn->leaf, oif);
@@ -434,13 +433,15 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
RT6_TRACE("%s() => %p\n",
__FUNCTION__, match);
- return (match ? match : &ip6_null_entry);
+ net = rt0->rt6i_dev->nd_net;
+ return (match ? match : net->ipv6.ip6_null_entry);
}
#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
struct in6_addr *gwaddr)
{
+ struct net *net = dev->nd_net;
struct route_info *rinfo = (struct route_info *) opt;
struct in6_addr prefix_buf, *prefix;
unsigned int pref;
@@ -488,7 +489,8 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
prefix = &prefix_buf;
}
- rt = rt6_get_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex);
+ rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr,
+ dev->ifindex);
if (rt && !lifetime) {
ip6_del_rt(rt);
@@ -496,7 +498,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
}
if (!rt && lifetime)
- rt = rt6_add_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
+ rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
pref);
else if (rt)
rt->rt6i_flags = RTF_ROUTEINFO |
@@ -515,9 +517,9 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
}
#endif
-#define BACKTRACK(saddr) \
+#define BACKTRACK(__net, saddr) \
do { \
- if (rt == &ip6_null_entry) { \
+ if (rt == __net->ipv6.ip6_null_entry) { \
struct fib6_node *pn; \
while (1) { \
if (fn->fn_flags & RTN_TL_ROOT) \
@@ -533,7 +535,8 @@ do { \
} \
} while(0)
-static struct rt6_info *ip6_pol_route_lookup(struct fib6_table *table,
+static struct rt6_info *ip6_pol_route_lookup(struct net *net,
+ struct fib6_table *table,
struct flowi *fl, int flags)
{
struct fib6_node *fn;
@@ -543,8 +546,8 @@ static struct rt6_info *ip6_pol_route_lookup(struct fib6_table *table,
fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
rt = fn->leaf;
- rt = rt6_device_match(rt, fl->oif, flags);
- BACKTRACK(&fl->fl6_src);
+ rt = rt6_device_match(net, rt, fl->oif, flags);
+ BACKTRACK(net, &fl->fl6_src);
out:
dst_use(&rt->u.dst, jiffies);
read_unlock_bh(&table->tb6_lock);
@@ -552,8 +555,8 @@ out:
}
-struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
- int oif, int strict)
+struct rt6_info *rt6_lookup(struct net *net, struct in6_addr *daddr,
+ struct in6_addr *saddr, int oif, int strict)
{
struct flowi fl = {
.oif = oif,
@@ -571,7 +574,7 @@ struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
flags |= RT6_LOOKUP_F_HAS_SADDR;
}
- dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup);
+ dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_lookup);
if (dst->error == 0)
return (struct rt6_info *) dst;
@@ -604,7 +607,7 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
int ip6_ins_rt(struct rt6_info *rt)
{
struct nl_info info = {
- .nl_net = &init_net,
+ .nl_net = rt->rt6i_dev->nd_net,
};
return __ip6_ins_rt(rt, &info);
}
@@ -660,8 +663,8 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d
return rt;
}
-static struct rt6_info *ip6_pol_route(struct fib6_table *table, int oif,
- struct flowi *fl, int flags)
+static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
+ struct flowi *fl, int flags)
{
struct fib6_node *fn;
struct rt6_info *rt, *nrt;
@@ -680,8 +683,9 @@ restart_2:
restart:
rt = rt6_select(fn, oif, strict | reachable);
- BACKTRACK(&fl->fl6_src);
- if (rt == &ip6_null_entry ||
+
+ BACKTRACK(net, &fl->fl6_src);
+ if (rt == net->ipv6.ip6_null_entry ||
rt->rt6i_flags & RTF_CACHE)
goto out;
@@ -699,7 +703,7 @@ restart:
}
dst_release(&rt->u.dst);
- rt = nrt ? : &ip6_null_entry;
+ rt = nrt ? : net->ipv6.ip6_null_entry;
dst_hold(&rt->u.dst);
if (nrt) {
@@ -732,15 +736,16 @@ out2:
return rt;
}
-static struct rt6_info *ip6_pol_route_input(struct fib6_table *table,
+static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
struct flowi *fl, int flags)
{
- return ip6_pol_route(table, fl->iif, fl, flags);
+ return ip6_pol_route(net, table, fl->iif, fl, flags);
}
void ip6_route_input(struct sk_buff *skb)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
+ struct net *net = skb->dev->nd_net;
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct flowi fl = {
.iif = skb->dev->ifindex,
@@ -758,16 +763,17 @@ void ip6_route_input(struct sk_buff *skb)
if (rt6_need_strict(&iph->daddr))
flags |= RT6_LOOKUP_F_IFACE;
- skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input);
+ skb->dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input);
}
-static struct rt6_info *ip6_pol_route_output(struct fib6_table *table,
+static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
struct flowi *fl, int flags)
{
- return ip6_pol_route(table, fl->oif, fl, flags);
+ return ip6_pol_route(net, table, fl->oif, fl, flags);
}
-struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
+struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
+ struct flowi *fl)
{
int flags = 0;
@@ -777,7 +783,7 @@ struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
if (!ipv6_addr_any(&fl->fl6_src))
flags |= RT6_LOOKUP_F_HAS_SADDR;
- return fib6_rule_lookup(fl, flags, ip6_pol_route_output);
+ return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output);
}
EXPORT_SYMBOL(ip6_route_output);
@@ -886,12 +892,12 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
static int ipv6_get_mtu(struct net_device *dev);
-static inline unsigned int ipv6_advmss(unsigned int mtu)
+static inline unsigned int ipv6_advmss(struct net *net, unsigned int mtu)
{
mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
- if (mtu < init_net.ipv6.sysctl.ip6_rt_min_advmss)
- mtu = init_net.ipv6.sysctl.ip6_rt_min_advmss;
+ if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
+ mtu = net->ipv6.sysctl.ip6_rt_min_advmss;
/*
* Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and
@@ -904,21 +910,21 @@ static inline unsigned int ipv6_advmss(unsigned int mtu)
return mtu;
}
-static struct dst_entry *ndisc_dst_gc_list;
-static DEFINE_SPINLOCK(ndisc_lock);
+static struct dst_entry *icmp6_dst_gc_list;
+static DEFINE_SPINLOCK(icmp6_dst_lock);
-struct dst_entry *ndisc_dst_alloc(struct net_device *dev,
+struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
struct neighbour *neigh,
- struct in6_addr *addr,
- int (*output)(struct sk_buff *))
+ struct in6_addr *addr)
{
struct rt6_info *rt;
struct inet6_dev *idev = in6_dev_get(dev);
+ struct net *net = dev->nd_net;
if (unlikely(idev == NULL))
return NULL;
- rt = ip6_dst_alloc();
+ rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
if (unlikely(rt == NULL)) {
in6_dev_put(idev);
goto out;
@@ -936,8 +942,8 @@ struct dst_entry *ndisc_dst_alloc(struct net_device *dev,
atomic_set(&rt->u.dst.__refcnt, 1);
rt->u.dst.metrics[RTAX_HOPLIMIT-1] = 255;
rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
- rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
- rt->u.dst.output = output;
+ rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst));
+ rt->u.dst.output = ip6_output;
#if 0 /* there's no chance to use these for ndisc */
rt->u.dst.flags = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST
@@ -947,18 +953,18 @@ struct dst_entry *ndisc_dst_alloc(struct net_device *dev,
rt->rt6i_dst.plen = 128;
#endif
- spin_lock_bh(&ndisc_lock);
- rt->u.dst.next = ndisc_dst_gc_list;
- ndisc_dst_gc_list = &rt->u.dst;
- spin_unlock_bh(&ndisc_lock);
+ spin_lock_bh(&icmp6_dst_lock);
+ rt->u.dst.next = icmp6_dst_gc_list;
+ icmp6_dst_gc_list = &rt->u.dst;
+ spin_unlock_bh(&icmp6_dst_lock);
- fib6_force_start_gc();
+ fib6_force_start_gc(net);
out:
return &rt->u.dst;
}
-int ndisc_dst_gc(int *more)
+int icmp6_dst_gc(int *more)
{
struct dst_entry *dst, *next, **pprev;
int freed;
@@ -966,8 +972,8 @@ int ndisc_dst_gc(int *more)
next = NULL;
freed = 0;
- spin_lock_bh(&ndisc_lock);
- pprev = &ndisc_dst_gc_list;
+ spin_lock_bh(&icmp6_dst_lock);
+ pprev = &icmp6_dst_gc_list;
while ((dst = *pprev) != NULL) {
if (!atomic_read(&dst->__refcnt)) {
@@ -980,30 +986,33 @@ int ndisc_dst_gc(int *more)
}
}
- spin_unlock_bh(&ndisc_lock);
+ spin_unlock_bh(&icmp6_dst_lock);
return freed;
}
static int ip6_dst_gc(struct dst_ops *ops)
{
- static unsigned expire = 30*HZ;
- static unsigned long last_gc;
unsigned long now = jiffies;
-
- if (time_after(last_gc + init_net.ipv6.sysctl.ip6_rt_gc_min_interval, now) &&
- atomic_read(&ip6_dst_ops.entries) <= init_net.ipv6.sysctl.ip6_rt_max_size)
+ struct net *net = ops->dst_net;
+ int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval;
+ int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size;
+ int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
+ int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
+ unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
+
+ if (time_after(rt_last_gc + rt_min_interval, now) &&
+ atomic_read(&ops->entries) <= rt_max_size)
goto out;
- expire++;
- fib6_run_gc(expire);
- last_gc = now;
- if (atomic_read(&ip6_dst_ops.entries) < ip6_dst_ops.gc_thresh)
- expire = init_net.ipv6.sysctl.ip6_rt_gc_timeout>>1;
-
+ net->ipv6.ip6_rt_gc_expire++;
+ fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net);
+ net->ipv6.ip6_rt_last_gc = now;
+ if (atomic_read(&ops->entries) < ops->gc_thresh)
+ net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
out:
- expire -= expire>>init_net.ipv6.sysctl.ip6_rt_gc_elasticity;
- return (atomic_read(&ip6_dst_ops.entries) > init_net.ipv6.sysctl.ip6_rt_max_size);
+ net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity;
+ return (atomic_read(&ops->entries) > rt_max_size);
}
/* Clean host part of a prefix. Not necessary in radix tree,
@@ -1045,6 +1054,7 @@ int ipv6_get_hoplimit(struct net_device *dev)
int ip6_route_add(struct fib6_config *cfg)
{
int err;
+ struct net *net = cfg->fc_nlinfo.nl_net;
struct rt6_info *rt = NULL;
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
@@ -1059,7 +1069,7 @@ int ip6_route_add(struct fib6_config *cfg)
#endif
if (cfg->fc_ifindex) {
err = -ENODEV;
- dev = dev_get_by_index(&init_net, cfg->fc_ifindex);
+ dev = dev_get_by_index(net, cfg->fc_ifindex);
if (!dev)
goto out;
idev = in6_dev_get(dev);
@@ -1070,13 +1080,13 @@ int ip6_route_add(struct fib6_config *cfg)
if (cfg->fc_metric == 0)
cfg->fc_metric = IP6_RT_PRIO_USER;
- table = fib6_new_table(cfg->fc_table);
+ table = fib6_new_table(net, cfg->fc_table);
if (table == NULL) {
err = -ENOBUFS;
goto out;
}
- rt = ip6_dst_alloc();
+ rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
if (rt == NULL) {
err = -ENOMEM;
@@ -1117,12 +1127,12 @@ int ip6_route_add(struct fib6_config *cfg)
if ((cfg->fc_flags & RTF_REJECT) ||
(dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) {
/* hold loopback dev/idev if we haven't done so. */
- if (dev != init_net.loopback_dev) {
+ if (dev != net->loopback_dev) {
if (dev) {
dev_put(dev);
in6_dev_put(idev);
}
- dev = init_net.loopback_dev;
+ dev = net->loopback_dev;
dev_hold(dev);
idev = in6_dev_get(dev);
if (!idev) {
@@ -1159,7 +1169,7 @@ int ip6_route_add(struct fib6_config *cfg)
if (!(gwa_type&IPV6_ADDR_UNICAST))
goto out;
- grt = rt6_lookup(gw_addr, NULL, cfg->fc_ifindex, 1);
+ grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1);
err = -EHOSTUNREACH;
if (grt == NULL)
@@ -1226,10 +1236,13 @@ install_route:
if (!rt->u.dst.metrics[RTAX_MTU-1])
rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev);
if (!rt->u.dst.metrics[RTAX_ADVMSS-1])
- rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
+ rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst));
rt->u.dst.dev = dev;
rt->rt6i_idev = idev;
rt->rt6i_table = table;
+
+ cfg->fc_nlinfo.nl_net = dev->nd_net;
+
return __ip6_ins_rt(rt, &cfg->fc_nlinfo);
out:
@@ -1246,8 +1259,9 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
{
int err;
struct fib6_table *table;
+ struct net *net = rt->rt6i_dev->nd_net;
- if (rt == &ip6_null_entry)
+ if (rt == net->ipv6.ip6_null_entry)
return -ENOENT;
table = rt->rt6i_table;
@@ -1264,7 +1278,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
int ip6_del_rt(struct rt6_info *rt)
{
struct nl_info info = {
- .nl_net = &init_net,
+ .nl_net = rt->rt6i_dev->nd_net,
};
return __ip6_del_rt(rt, &info);
}
@@ -1276,7 +1290,7 @@ static int ip6_route_del(struct fib6_config *cfg)
struct rt6_info *rt;
int err = -ESRCH;
- table = fib6_get_table(cfg->fc_table);
+ table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table);
if (table == NULL)
return err;
@@ -1316,7 +1330,8 @@ struct ip6rd_flowi {
struct in6_addr gateway;
};
-static struct rt6_info *__ip6_route_redirect(struct fib6_table *table,
+static struct rt6_info *__ip6_route_redirect(struct net *net,
+ struct fib6_table *table,
struct flowi *fl,
int flags)
{
@@ -1359,8 +1374,8 @@ restart:
}
if (!rt)
- rt = &ip6_null_entry;
- BACKTRACK(&fl->fl6_src);
+ rt = net->ipv6.ip6_null_entry;
+ BACKTRACK(net, &fl->fl6_src);
out:
dst_hold(&rt->u.dst);
@@ -1375,6 +1390,7 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
struct net_device *dev)
{
int flags = RT6_LOOKUP_F_HAS_SADDR;
+ struct net *net = dev->nd_net;
struct ip6rd_flowi rdfl = {
.fl = {
.oif = dev->ifindex,
@@ -1391,7 +1407,8 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
if (rt6_need_strict(dest))
flags |= RT6_LOOKUP_F_IFACE;
- return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect);
+ return (struct rt6_info *)fib6_rule_lookup(net, (struct flowi *)&rdfl,
+ flags, __ip6_route_redirect);
}
void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
@@ -1400,10 +1417,11 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
{
struct rt6_info *rt, *nrt = NULL;
struct netevent_redirect netevent;
+ struct net *net = neigh->dev->nd_net;
rt = ip6_route_redirect(dest, src, saddr, neigh->dev);
- if (rt == &ip6_null_entry) {
+ if (rt == net->ipv6.ip6_null_entry) {
if (net_ratelimit())
printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop "
"for redirect target\n");
@@ -1448,7 +1466,8 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
nrt->rt6i_nexthop = neigh_clone(neigh);
/* Reset pmtu, it may be better */
nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev);
- nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&nrt->u.dst));
+ nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(neigh->dev->nd_net,
+ dst_mtu(&nrt->u.dst));
if (ip6_ins_rt(nrt))
goto out;
@@ -1476,9 +1495,10 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
struct net_device *dev, u32 pmtu)
{
struct rt6_info *rt, *nrt;
+ struct net *net = dev->nd_net;
int allfrag = 0;
- rt = rt6_lookup(daddr, saddr, dev->ifindex, 0);
+ rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0);
if (rt == NULL)
return;
@@ -1511,7 +1531,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
rt->u.dst.metrics[RTAX_MTU-1] = pmtu;
if (allfrag)
rt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
- dst_set_expires(&rt->u.dst, init_net.ipv6.sysctl.ip6_rt_mtu_expires);
+ dst_set_expires(&rt->u.dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
goto out;
}
@@ -1537,7 +1557,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
* which is 10 mins. After 10 mins the decreased pmtu is expired
* and detecting PMTU increase will be automatically happened.
*/
- dst_set_expires(&nrt->u.dst, init_net.ipv6.sysctl.ip6_rt_mtu_expires);
+ dst_set_expires(&nrt->u.dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;
ip6_ins_rt(nrt);
@@ -1552,7 +1572,8 @@ out:
static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
{
- struct rt6_info *rt = ip6_dst_alloc();
+ struct net *net = ort->rt6i_dev->nd_net;
+ struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
if (rt) {
rt->u.dst.input = ort->u.dst.input;
@@ -1583,14 +1604,15 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
}
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen,
+static struct rt6_info *rt6_get_route_info(struct net *net,
+ struct in6_addr *prefix, int prefixlen,
struct in6_addr *gwaddr, int ifindex)
{
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
- table = fib6_get_table(RT6_TABLE_INFO);
+ table = fib6_get_table(net, RT6_TABLE_INFO);
if (table == NULL)
return NULL;
@@ -1614,7 +1636,8 @@ out:
return rt;
}
-static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen,
+static struct rt6_info *rt6_add_route_info(struct net *net,
+ struct in6_addr *prefix, int prefixlen,
struct in6_addr *gwaddr, int ifindex,
unsigned pref)
{
@@ -1625,6 +1648,9 @@ static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixle
.fc_dst_len = prefixlen,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
+ .fc_nlinfo.pid = 0,
+ .fc_nlinfo.nlh = NULL,
+ .fc_nlinfo.nl_net = net,
};
ipv6_addr_copy(&cfg.fc_dst, prefix);
@@ -1636,7 +1662,7 @@ static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixle
ip6_route_add(&cfg);
- return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex);
+ return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
}
#endif
@@ -1645,7 +1671,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d
struct rt6_info *rt;
struct fib6_table *table;
- table = fib6_get_table(RT6_TABLE_DFLT);
+ table = fib6_get_table(dev->nd_net, RT6_TABLE_DFLT);
if (table == NULL)
return NULL;
@@ -1674,6 +1700,9 @@ struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
+ .fc_nlinfo.pid = 0,
+ .fc_nlinfo.nlh = NULL,
+ .fc_nlinfo.nl_net = dev->nd_net,
};
ipv6_addr_copy(&cfg.fc_gateway, gwaddr);
@@ -1683,13 +1712,13 @@ struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
return rt6_get_dflt_router(gwaddr, dev);
}
-void rt6_purge_dflt_routers(void)
+void rt6_purge_dflt_routers(struct net *net)
{
struct rt6_info *rt;
struct fib6_table *table;
/* NOTE: Keep consistent with rt6_get_dflt_router */
- table = fib6_get_table(RT6_TABLE_DFLT);
+ table = fib6_get_table(net, RT6_TABLE_DFLT);
if (table == NULL)
return;
@@ -1706,7 +1735,8 @@ restart:
read_unlock_bh(&table->tb6_lock);
}
-static void rtmsg_to_fib6_config(struct in6_rtmsg *rtmsg,
+static void rtmsg_to_fib6_config(struct net *net,
+ struct in6_rtmsg *rtmsg,
struct fib6_config *cfg)
{
memset(cfg, 0, sizeof(*cfg));
@@ -1719,14 +1749,14 @@ static void rtmsg_to_fib6_config(struct in6_rtmsg *rtmsg,
cfg->fc_src_len = rtmsg->rtmsg_src_len;
cfg->fc_flags = rtmsg->rtmsg_flags;
- cfg->fc_nlinfo.nl_net = &init_net;
+ cfg->fc_nlinfo.nl_net = net;
ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst);
ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src);
ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway);
}
-int ipv6_route_ioctl(unsigned int cmd, void __user *arg)
+int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct fib6_config cfg;
struct in6_rtmsg rtmsg;
@@ -1742,7 +1772,7 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg)
if (err)
return -EFAULT;
- rtmsg_to_fib6_config(&rtmsg, &cfg);
+ rtmsg_to_fib6_config(net, &rtmsg, &cfg);
rtnl_lock();
switch (cmd) {
@@ -1821,21 +1851,22 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
const struct in6_addr *addr,
int anycast)
{
- struct rt6_info *rt = ip6_dst_alloc();
+ struct net *net = idev->dev->nd_net;
+ struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
if (rt == NULL)
return ERR_PTR(-ENOMEM);
- dev_hold(init_net.loopback_dev);
+ dev_hold(net->loopback_dev);
in6_dev_hold(idev);
rt->u.dst.flags = DST_HOST;
rt->u.dst.input = ip6_input;
rt->u.dst.output = ip6_output;
- rt->rt6i_dev = init_net.loopback_dev;
+ rt->rt6i_dev = net->loopback_dev;
rt->rt6i_idev = idev;
rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
- rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
+ rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst));
rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1;
rt->u.dst.obsolete = -1;
@@ -1852,26 +1883,39 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
rt->rt6i_dst.plen = 128;
- rt->rt6i_table = fib6_get_table(RT6_TABLE_LOCAL);
+ rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
atomic_set(&rt->u.dst.__refcnt, 1);
return rt;
}
+struct arg_dev_net {
+ struct net_device *dev;
+ struct net *net;
+};
+
static int fib6_ifdown(struct rt6_info *rt, void *arg)
{
- if (((void*)rt->rt6i_dev == arg || arg == NULL) &&
- rt != &ip6_null_entry) {
+ struct net_device *dev = ((struct arg_dev_net *)arg)->dev;
+ struct net *net = ((struct arg_dev_net *)arg)->net;
+
+ if (((void *)rt->rt6i_dev == dev || dev == NULL) &&
+ rt != net->ipv6.ip6_null_entry) {
RT6_TRACE("deleted by ifdown %p\n", rt);
return -1;
}
return 0;
}
-void rt6_ifdown(struct net_device *dev)
+void rt6_ifdown(struct net *net, struct net_device *dev)
{
- fib6_clean_all(fib6_ifdown, 0, dev);
+ struct arg_dev_net adn = {
+ .dev = dev,
+ .net = net,
+ };
+
+ fib6_clean_all(net, fib6_ifdown, 0, &adn);
}
struct rt6_mtu_change_arg
@@ -1884,6 +1928,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
{
struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
struct inet6_dev *idev;
+ struct net *net = arg->dev->nd_net;
/* In IPv6 pmtu discovery is not optional,
so that RTAX_MTU lock cannot disable it.
@@ -1915,7 +1960,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
(dst_mtu(&rt->u.dst) < arg->mtu &&
dst_mtu(&rt->u.dst) == idev->cnf.mtu6))) {
rt->u.dst.metrics[RTAX_MTU-1] = arg->mtu;
- rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(arg->mtu);
+ rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, arg->mtu);
}
return 0;
}
@@ -1927,7 +1972,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned mtu)
.mtu = mtu,
};
- fib6_clean_all(rt6_mtu_change_route, 0, &arg);
+ fib6_clean_all(dev->nd_net, rt6_mtu_change_route, 0, &arg);
}
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
@@ -2010,13 +2055,9 @@ errout:
static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
- struct net *net = skb->sk->sk_net;
struct fib6_config cfg;
int err;
- if (net != &init_net)
- return -EINVAL;
-
err = rtm_to_fib6_config(skb, nlh, &cfg);
if (err < 0)
return err;
@@ -2026,13 +2067,9 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a
static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
- struct net *net = skb->sk->sk_net;
struct fib6_config cfg;
int err;
- if (net != &init_net)
- return -EINVAL;
-
err = rtm_to_fib6_config(skb, nlh, &cfg);
if (err < 0)
return err;
@@ -2122,7 +2159,8 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
NLA_PUT_U32(skb, RTA_IIF, iif);
else if (dst) {
struct in6_addr saddr_buf;
- if (ipv6_get_saddr(&rt->u.dst, dst, &saddr_buf) == 0)
+ if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev,
+ dst, &saddr_buf) == 0)
NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
}
@@ -2175,9 +2213,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
struct flowi fl;
int err, iif = 0;
- if (net != &init_net)
- return -EINVAL;
-
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
if (err < 0)
goto errout;
@@ -2207,7 +2242,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
if (iif) {
struct net_device *dev;
- dev = __dev_get_by_index(&init_net, iif);
+ dev = __dev_get_by_index(net, iif);
if (!dev) {
err = -ENODEV;
goto errout;
@@ -2226,7 +2261,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
skb_reset_mac_header(skb);
skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
- rt = (struct rt6_info*) ip6_route_output(NULL, &fl);
+ rt = (struct rt6_info*) ip6_route_output(&init_net, NULL, &fl);
skb->dst = &rt->u.dst;
err = rt6_fill_node(skb, rt, &fl.fl6_dst, &fl.fl6_src, iif,
@@ -2237,7 +2272,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
goto errout;
}
- err = rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).pid);
+ err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
errout:
return err;
}
@@ -2245,6 +2280,7 @@ errout:
void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
{
struct sk_buff *skb;
+ struct net *net = info->nl_net;
u32 seq;
int err;
@@ -2263,11 +2299,31 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, &init_net, info->pid,
- RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any());
+ err = rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE,
+ info->nlh, gfp_any());
errout:
if (err < 0)
- rtnl_set_sk_err(&init_net, RTNLGRP_IPV6_ROUTE, err);
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
+}
+
+static int ip6_route_dev_notify(struct notifier_block *this,
+ unsigned long event, void *data)
+{
+ struct net_device *dev = (struct net_device *)data;
+ struct net *net = dev->nd_net;
+
+ if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) {
+ net->ipv6.ip6_null_entry->u.dst.dev = dev;
+ net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ net->ipv6.ip6_prohibit_entry->u.dst.dev = dev;
+ net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev);
+ net->ipv6.ip6_blk_hole_entry->u.dst.dev = dev;
+ net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev);
+#endif
+ }
+
+ return NOTIFY_OK;
}
/*
@@ -2316,13 +2372,25 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
static int ipv6_route_show(struct seq_file *m, void *v)
{
- fib6_clean_all(rt6_info_route, 0, m);
+ struct net *net = (struct net *)m->private;
+ fib6_clean_all(net, rt6_info_route, 0, m);
return 0;
}
static int ipv6_route_open(struct inode *inode, struct file *file)
{
- return single_open(file, ipv6_route_show, NULL);
+ struct net *net = get_proc_net(inode);
+ if (!net)
+ return -ENXIO;
+ return single_open(file, ipv6_route_show, net);
+}
+
+static int ipv6_route_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct net *net = seq->private;
+ put_net(net);
+ return single_release(inode, file);
}
static const struct file_operations ipv6_route_proc_fops = {
@@ -2330,24 +2398,36 @@ static const struct file_operations ipv6_route_proc_fops = {
.open = ipv6_route_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = ipv6_route_release,
};
static int rt6_stats_seq_show(struct seq_file *seq, void *v)
{
+ struct net *net = (struct net *)seq->private;
seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n",
- rt6_stats.fib_nodes, rt6_stats.fib_route_nodes,
- rt6_stats.fib_rt_alloc, rt6_stats.fib_rt_entries,
- rt6_stats.fib_rt_cache,
- atomic_read(&ip6_dst_ops.entries),
- rt6_stats.fib_discarded_routes);
+ net->ipv6.rt6_stats->fib_nodes,
+ net->ipv6.rt6_stats->fib_route_nodes,
+ net->ipv6.rt6_stats->fib_rt_alloc,
+ net->ipv6.rt6_stats->fib_rt_entries,
+ net->ipv6.rt6_stats->fib_rt_cache,
+ atomic_read(&net->ipv6.ip6_dst_ops->entries),
+ net->ipv6.rt6_stats->fib_discarded_routes);
return 0;
}
static int rt6_stats_seq_open(struct inode *inode, struct file *file)
{
- return single_open(file, rt6_stats_seq_show, NULL);
+ struct net *net = get_proc_net(inode);
+ return single_open(file, rt6_stats_seq_show, net);
+}
+
+static int rt6_stats_seq_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct net *net = (struct net *)seq->private;
+ put_net(net);
+ return single_release(inode, file);
}
static const struct file_operations rt6_stats_seq_fops = {
@@ -2355,42 +2435,8 @@ static const struct file_operations rt6_stats_seq_fops = {
.open = rt6_stats_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = rt6_stats_seq_release,
};
-
-static int ipv6_route_proc_init(struct net *net)
-{
- int ret = -ENOMEM;
- if (!proc_net_fops_create(net, "ipv6_route",
- 0, &ipv6_route_proc_fops))
- goto out;
-
- if (!proc_net_fops_create(net, "rt6_stats",
- S_IRUGO, &rt6_stats_seq_fops))
- goto out_ipv6_route;
-
- ret = 0;
-out:
- return ret;
-out_ipv6_route:
- proc_net_remove(net, "ipv6_route");
- goto out;
-}
-
-static void ipv6_route_proc_fini(struct net *net)
-{
- proc_net_remove(net, "ipv6_route");
- proc_net_remove(net, "rt6_stats");
-}
-#else
-static inline int ipv6_route_proc_init(struct net *net)
-{
- return 0;
-}
-static inline void ipv6_route_proc_fini(struct net *net)
-{
- return ;
-}
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SYSCTL
@@ -2399,10 +2445,11 @@ static
int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- int delay = init_net.ipv6.sysctl.flush_delay;
+ struct net *net = current->nsproxy->net_ns;
+ int delay = net->ipv6.sysctl.flush_delay;
if (write) {
proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
- fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay);
+ fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
return 0;
} else
return -EINVAL;
@@ -2419,7 +2466,7 @@ ctl_table ipv6_route_table_template[] = {
{
.ctl_name = NET_IPV6_ROUTE_GC_THRESH,
.procname = "gc_thresh",
- .data = &ip6_dst_ops.gc_thresh,
+ .data = &ip6_dst_ops_template.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec,
@@ -2505,33 +2552,141 @@ struct ctl_table *ipv6_route_sysctl_init(struct net *net)
table = kmemdup(ipv6_route_table_template,
sizeof(ipv6_route_table_template),
GFP_KERNEL);
+
+ if (table) {
+ table[0].data = &net->ipv6.sysctl.flush_delay;
+ table[1].data = &net->ipv6.ip6_dst_ops->gc_thresh;
+ table[2].data = &net->ipv6.sysctl.ip6_rt_max_size;
+ table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
+ table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout;
+ table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval;
+ table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity;
+ table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires;
+ table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
+ }
+
return table;
}
#endif
+static int ip6_route_net_init(struct net *net)
+{
+ int ret = 0;
+
+ ret = -ENOMEM;
+ net->ipv6.ip6_dst_ops = kmemdup(&ip6_dst_ops_template,
+ sizeof(*net->ipv6.ip6_dst_ops),
+ GFP_KERNEL);
+ if (!net->ipv6.ip6_dst_ops)
+ goto out;
+ net->ipv6.ip6_dst_ops->dst_net = net;
+
+ net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
+ sizeof(*net->ipv6.ip6_null_entry),
+ GFP_KERNEL);
+ if (!net->ipv6.ip6_null_entry)
+ goto out_ip6_dst_ops;
+ net->ipv6.ip6_null_entry->u.dst.path =
+ (struct dst_entry *)net->ipv6.ip6_null_entry;
+ net->ipv6.ip6_null_entry->u.dst.ops = net->ipv6.ip6_dst_ops;
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template,
+ sizeof(*net->ipv6.ip6_prohibit_entry),
+ GFP_KERNEL);
+ if (!net->ipv6.ip6_prohibit_entry) {
+ kfree(net->ipv6.ip6_null_entry);
+ goto out;
+ }
+ net->ipv6.ip6_prohibit_entry->u.dst.path =
+ (struct dst_entry *)net->ipv6.ip6_prohibit_entry;
+ net->ipv6.ip6_prohibit_entry->u.dst.ops = net->ipv6.ip6_dst_ops;
+
+ net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
+ sizeof(*net->ipv6.ip6_blk_hole_entry),
+ GFP_KERNEL);
+ if (!net->ipv6.ip6_blk_hole_entry) {
+ kfree(net->ipv6.ip6_null_entry);
+ kfree(net->ipv6.ip6_prohibit_entry);
+ goto out;
+ }
+ net->ipv6.ip6_blk_hole_entry->u.dst.path =
+ (struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
+ net->ipv6.ip6_blk_hole_entry->u.dst.ops = net->ipv6.ip6_dst_ops;
+#endif
+
+#ifdef CONFIG_PROC_FS
+ proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops);
+ proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
+#endif
+ net->ipv6.ip6_rt_gc_expire = 30*HZ;
+
+ ret = 0;
+out:
+ return ret;
+
+out_ip6_dst_ops:
+ kfree(net->ipv6.ip6_dst_ops);
+ goto out;
+}
+
+static void ip6_route_net_exit(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+ proc_net_remove(net, "ipv6_route");
+ proc_net_remove(net, "rt6_stats");
+#endif
+ kfree(net->ipv6.ip6_null_entry);
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ kfree(net->ipv6.ip6_prohibit_entry);
+ kfree(net->ipv6.ip6_blk_hole_entry);
+#endif
+ kfree(net->ipv6.ip6_dst_ops);
+}
+
+static struct pernet_operations ip6_route_net_ops = {
+ .init = ip6_route_net_init,
+ .exit = ip6_route_net_exit,
+};
+
+static struct notifier_block ip6_route_dev_notifier = {
+ .notifier_call = ip6_route_dev_notify,
+ .priority = 0,
+};
+
int __init ip6_route_init(void)
{
int ret;
- ip6_dst_ops.kmem_cachep =
+ ret = -ENOMEM;
+ ip6_dst_ops_template.kmem_cachep =
kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0,
SLAB_HWCACHE_ALIGN, NULL);
- if (!ip6_dst_ops.kmem_cachep)
- return -ENOMEM;
+ if (!ip6_dst_ops_template.kmem_cachep)
+ goto out;;
- ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops.kmem_cachep;
-
- ret = fib6_init();
+ ret = register_pernet_subsys(&ip6_route_net_ops);
if (ret)
goto out_kmem_cache;
- ret = ipv6_route_proc_init(&init_net);
+ /* Registering of the loopback is done before this portion of code,
+ * the loopback reference in rt6_info will not be taken, do it
+ * manually for init_net */
+ init_net.ipv6.ip6_null_entry->u.dst.dev = init_net.loopback_dev;
+ init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+ #ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ init_net.ipv6.ip6_prohibit_entry->u.dst.dev = init_net.loopback_dev;
+ init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+ init_net.ipv6.ip6_blk_hole_entry->u.dst.dev = init_net.loopback_dev;
+ init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+ #endif
+ ret = fib6_init();
if (ret)
- goto out_fib6_init;
+ goto out_register_subsys;
ret = xfrm6_init();
if (ret)
- goto out_proc_init;
+ goto out_fib6_init;
ret = fib6_rules_init();
if (ret)
@@ -2543,7 +2698,10 @@ int __init ip6_route_init(void)
__rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL))
goto fib6_rules_init;
- ret = 0;
+ ret = register_netdevice_notifier(&ip6_route_dev_notifier);
+ if (ret)
+ goto fib6_rules_init;
+
out:
return ret;
@@ -2551,22 +2709,21 @@ fib6_rules_init:
fib6_rules_cleanup();
xfrm6_init:
xfrm6_fini();
-out_proc_init:
- ipv6_route_proc_fini(&init_net);
out_fib6_init:
- rt6_ifdown(NULL);
fib6_gc_cleanup();
+out_register_subsys:
+ unregister_pernet_subsys(&ip6_route_net_ops);
out_kmem_cache:
- kmem_cache_destroy(ip6_dst_ops.kmem_cachep);
+ kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
goto out;
}
void ip6_route_cleanup(void)
{
+ unregister_netdevice_notifier(&ip6_route_dev_notifier);
fib6_rules_cleanup();
- ipv6_route_proc_fini(&init_net);
xfrm6_fini();
- rt6_ifdown(NULL);
fib6_gc_cleanup();
- kmem_cache_destroy(ip6_dst_ops.kmem_cachep);
+ unregister_pernet_subsys(&ip6_route_net_ops);
+ kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
}
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 1656c003b98..1b8196c8d14 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -339,11 +339,11 @@ out:
skb_reset_network_header(skb2);
/* Try to guess incoming interface */
- rt6i = rt6_lookup(&iph6->saddr, NULL, NULL, 0);
+ rt6i = rt6_lookup(&init_net, &iph6->saddr, NULL, NULL, 0);
if (rt6i && rt6i->rt6i_dev) {
skb2->dev = rt6i->rt6i_dev;
- rt6i = rt6_lookup(&iph6->daddr, &iph6->saddr, NULL, 0);
+ rt6i = rt6_lookup(&init_net, &iph6->daddr, &iph6->saddr, NULL, 0);
if (rt6i && rt6i->rt6i_dev && rt6i->rt6i_dev->type == ARPHRD_SIT) {
struct ip_tunnel *t = netdev_priv(rt6i->rt6i_dev);
@@ -393,7 +393,7 @@ isatap_srcok(struct sk_buff *skb, struct iphdr *iph, struct net_device *dev)
fl.oif = dev->ifindex;
security_skb_classify_flow(skb, &fl);
- dst = ip6_route_output(NULL, &fl);
+ dst = ip6_route_output(&init_net, NULL, &fl);
if (!dst->error && (dst->dev == dev) && (neigh = dst->neighbour)) {
addr6 = (struct in6_addr*)&neigh->primary_key;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
new file mode 100644
index 00000000000..827c5aa7524
--- /dev/null
+++ b/net/ipv6/syncookies.c
@@ -0,0 +1,267 @@
+/*
+ * IPv6 Syncookies implementation for the Linux kernel
+ *
+ * Authors:
+ * Glenn Griffin <ggriffin.kernel@gmail.com>
+ *
+ * Based on IPv4 implementation by Andi Kleen
+ * linux/net/ipv4/syncookies.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/tcp.h>
+#include <linux/random.h>
+#include <linux/cryptohash.h>
+#include <linux/kernel.h>
+#include <net/ipv6.h>
+#include <net/tcp.h>
+
+extern int sysctl_tcp_syncookies;
+extern __u32 syncookie_secret[2][16-3+SHA_DIGEST_WORDS];
+
+#define COOKIEBITS 24 /* Upper bits store count */
+#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
+
+/*
+ * This table has to be sorted and terminated with (__u16)-1.
+ * XXX generate a better table.
+ * Unresolved Issues: HIPPI with a 64k MSS is not well supported.
+ *
+ * Taken directly from ipv4 implementation.
+ * Should this list be modified for ipv6 use or is it close enough?
+ * rfc 2460 8.3 suggests mss values 20 bytes less than ipv4 counterpart
+ */
+static __u16 const msstab[] = {
+ 64 - 1,
+ 256 - 1,
+ 512 - 1,
+ 536 - 1,
+ 1024 - 1,
+ 1440 - 1,
+ 1460 - 1,
+ 4312 - 1,
+ (__u16)-1
+};
+/* The number doesn't include the -1 terminator */
+#define NUM_MSS (ARRAY_SIZE(msstab) - 1)
+
+/*
+ * This (misnamed) value is the age of syncookie which is permitted.
+ * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
+ * sysctl_tcp_retries1. It's a rather complicated formula (exponential
+ * backoff) to compute at runtime so it's currently hardcoded here.
+ */
+#define COUNTER_TRIES 4
+
+static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
+ struct request_sock *req,
+ struct dst_entry *dst)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct sock *child;
+
+ child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
+ if (child)
+ inet_csk_reqsk_queue_add(sk, req, child);
+ else
+ reqsk_free(req);
+
+ return child;
+}
+
+static DEFINE_PER_CPU(__u32, cookie_scratch)[16 + 5 + SHA_WORKSPACE_WORDS];
+
+static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr,
+ __be16 sport, __be16 dport, u32 count, int c)
+{
+ __u32 *tmp = __get_cpu_var(cookie_scratch);
+
+ /*
+ * we have 320 bits of information to hash, copy in the remaining
+ * 192 bits required for sha_transform, from the syncookie_secret
+ * and overwrite the digest with the secret
+ */
+ memcpy(tmp + 10, syncookie_secret[c], 44);
+ memcpy(tmp, saddr, 16);
+ memcpy(tmp + 4, daddr, 16);
+ tmp[8] = ((__force u32)sport << 16) + (__force u32)dport;
+ tmp[9] = count;
+ sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
+
+ return tmp[17];
+}
+
+static __u32 secure_tcp_syn_cookie(struct in6_addr *saddr, struct in6_addr *daddr,
+ __be16 sport, __be16 dport, __u32 sseq,
+ __u32 count, __u32 data)
+{
+ return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
+ sseq + (count << COOKIEBITS) +
+ ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
+ & COOKIEMASK));
+}
+
+static __u32 check_tcp_syn_cookie(__u32 cookie, struct in6_addr *saddr,
+ struct in6_addr *daddr, __be16 sport,
+ __be16 dport, __u32 sseq, __u32 count,
+ __u32 maxdiff)
+{
+ __u32 diff;
+
+ cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
+
+ diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
+ if (diff >= maxdiff)
+ return (__u32)-1;
+
+ return (cookie -
+ cookie_hash(saddr, daddr, sport, dport, count - diff, 1))
+ & COOKIEMASK;
+}
+
+__u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
+{
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+ const struct tcphdr *th = tcp_hdr(skb);
+ int mssind;
+ const __u16 mss = *mssp;
+
+ tcp_sk(sk)->last_synq_overflow = jiffies;
+
+ for (mssind = 0; mss > msstab[mssind + 1]; mssind++)
+ ;
+ *mssp = msstab[mssind] + 1;
+
+ NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESSENT);
+
+ return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source,
+ th->dest, ntohl(th->seq),
+ jiffies / (HZ * 60), mssind);
+}
+
+static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
+{
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+ const struct tcphdr *th = tcp_hdr(skb);
+ __u32 seq = ntohl(th->seq) - 1;
+ __u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
+ th->source, th->dest, seq,
+ jiffies / (HZ * 60), COUNTER_TRIES);
+
+ return mssind < NUM_MSS ? msstab[mssind] + 1 : 0;
+}
+
+struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
+{
+ struct inet_request_sock *ireq;
+ struct inet6_request_sock *ireq6;
+ struct tcp_request_sock *treq;
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ const struct tcphdr *th = tcp_hdr(skb);
+ __u32 cookie = ntohl(th->ack_seq) - 1;
+ struct sock *ret = sk;
+ struct request_sock *req;
+ int mss;
+ struct dst_entry *dst;
+ __u8 rcv_wscale;
+
+ if (!sysctl_tcp_syncookies || !th->ack)
+ goto out;
+
+ if (time_after(jiffies, tp->last_synq_overflow + TCP_TIMEOUT_INIT) ||
+ (mss = cookie_check(skb, cookie)) == 0) {
+ NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESFAILED);
+ goto out;
+ }
+
+ NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESRECV);
+
+ ret = NULL;
+ req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
+ if (!req)
+ goto out;
+
+ ireq = inet_rsk(req);
+ ireq6 = inet6_rsk(req);
+ treq = tcp_rsk(req);
+ ireq6->pktopts = NULL;
+
+ if (security_inet_conn_request(sk, skb, req)) {
+ reqsk_free(req);
+ goto out;
+ }
+
+ req->mss = mss;
+ ireq->rmt_port = th->source;
+ ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr);
+ ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr);
+ if (ipv6_opt_accepted(sk, skb) ||
+ np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
+ np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
+ atomic_inc(&skb->users);
+ ireq6->pktopts = skb;
+ }
+
+ ireq6->iif = sk->sk_bound_dev_if;
+ /* So that link locals have meaning */
+ if (!sk->sk_bound_dev_if &&
+ ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
+ ireq6->iif = inet6_iif(skb);
+
+ req->expires = 0UL;
+ req->retrans = 0;
+ ireq->snd_wscale = ireq->rcv_wscale = ireq->tstamp_ok = 0;
+ ireq->wscale_ok = ireq->sack_ok = 0;
+ treq->rcv_isn = ntohl(th->seq) - 1;
+ treq->snt_isn = cookie;
+
+ /*
+ * We need to lookup the dst_entry to get the correct window size.
+ * This is taken from tcp_v6_syn_recv_sock. Somebody please enlighten
+ * me if there is a preferred way.
+ */
+ {
+ struct in6_addr *final_p = NULL, final;
+ struct flowi fl;
+ memset(&fl, 0, sizeof(fl));
+ fl.proto = IPPROTO_TCP;
+ ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
+ if (np->opt && np->opt->srcrt) {
+ struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
+ ipv6_addr_copy(&final, &fl.fl6_dst);
+ ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
+ final_p = &final;
+ }
+ ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
+ fl.oif = sk->sk_bound_dev_if;
+ fl.fl_ip_dport = inet_rsk(req)->rmt_port;
+ fl.fl_ip_sport = inet_sk(sk)->sport;
+ security_req_classify_flow(req, &fl);
+ if (ip6_dst_lookup(sk, &dst, &fl)) {
+ reqsk_free(req);
+ goto out;
+ }
+ if (final_p)
+ ipv6_addr_copy(&fl.fl6_dst, final_p);
+ if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0)
+ goto out;
+ }
+
+ req->window_clamp = dst_metric(dst, RTAX_WINDOW);
+ tcp_select_initial_window(tcp_full_space(sk), req->mss,
+ &req->rcv_wnd, &req->window_clamp,
+ 0, &rcv_wscale);
+
+ ireq->rcv_wscale = rcv_wscale;
+
+ ret = get_cookie_sock(sk, skb, req, dst);
+
+out: return ret;
+}
+
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index d6d3e68086f..3804dcbbfab 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -71,24 +71,11 @@ static int ipv6_sysctl_net_init(struct net *net)
ipv6_route_table = ipv6_route_sysctl_init(net);
if (!ipv6_route_table)
goto out_ipv6_table;
+ ipv6_table[0].child = ipv6_route_table;
ipv6_icmp_table = ipv6_icmp_sysctl_init(net);
if (!ipv6_icmp_table)
goto out_ipv6_route_table;
-
- ipv6_route_table[0].data = &net->ipv6.sysctl.flush_delay;
- /* ipv6_route_table[1].data will be handled when we have
- routes per namespace */
- ipv6_route_table[2].data = &net->ipv6.sysctl.ip6_rt_max_size;
- ipv6_route_table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
- ipv6_route_table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout;
- ipv6_route_table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval;
- ipv6_route_table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity;
- ipv6_route_table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires;
- ipv6_route_table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
- ipv6_table[0].child = ipv6_route_table;
-
- ipv6_icmp_table[0].data = &net->ipv6.sysctl.icmpv6_time;
ipv6_table[1].child = ipv6_icmp_table;
ipv6_table[2].data = &net->ipv6.sysctl.bindv6only;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 12750f2b05a..aacbb7688bf 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -455,8 +455,7 @@ out:
}
-static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
- struct dst_entry *dst)
+static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req)
{
struct inet6_request_sock *treq = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -464,6 +463,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
struct ipv6_txoptions *opt = NULL;
struct in6_addr * final_p = NULL, final;
struct flowi fl;
+ struct dst_entry *dst;
int err = -1;
memset(&fl, 0, sizeof(fl));
@@ -476,24 +476,22 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
fl.fl_ip_sport = inet_sk(sk)->sport;
security_req_classify_flow(req, &fl);
- if (dst == NULL) {
- opt = np->opt;
- if (opt && opt->srcrt) {
- struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
- ipv6_addr_copy(&final, &fl.fl6_dst);
- ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
- final_p = &final;
- }
-
- err = ip6_dst_lookup(sk, &dst, &fl);
- if (err)
- goto done;
- if (final_p)
- ipv6_addr_copy(&fl.fl6_dst, final_p);
- if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
- goto done;
+ opt = np->opt;
+ if (opt && opt->srcrt) {
+ struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
+ ipv6_addr_copy(&final, &fl.fl6_dst);
+ ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
+ final_p = &final;
}
+ err = ip6_dst_lookup(sk, &dst, &fl);
+ if (err)
+ goto done;
+ if (final_p)
+ ipv6_addr_copy(&fl.fl6_dst, final_p);
+ if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
+ goto done;
+
skb = tcp_make_synack(sk, dst, req);
if (skb) {
struct tcphdr *th = tcp_hdr(skb);
@@ -514,6 +512,20 @@ done:
return err;
}
+static inline void syn_flood_warning(struct sk_buff *skb)
+{
+#ifdef CONFIG_SYN_COOKIES
+ if (sysctl_tcp_syncookies)
+ printk(KERN_INFO
+ "TCPv6: Possible SYN flooding on port %d. "
+ "Sending cookies.\n", ntohs(tcp_hdr(skb)->dest));
+ else
+#endif
+ printk(KERN_INFO
+ "TCPv6: Possible SYN flooding on port %d. "
+ "Dropping request.\n", ntohs(tcp_hdr(skb)->dest));
+}
+
static void tcp_v6_reqsk_destructor(struct request_sock *req)
{
if (inet6_rsk(req)->pktopts)
@@ -917,7 +929,7 @@ done_opts:
}
#endif
-static struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
+struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
.family = AF_INET6,
.obj_size = sizeof(struct tcp6_request_sock),
.rtx_syn_ack = tcp_v6_send_synack,
@@ -1059,8 +1071,11 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
fl.fl_ip_sport = t1->source;
security_skb_classify_flow(skb, &fl);
- /* sk = NULL, but it is safe for now. RST socket required. */
- if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {
+ /* Pass a socket to ip6_dst_lookup either it is for RST
+ * Underlying function will use this to retrieve the network
+ * namespace
+ */
+ if (!ip6_dst_lookup(tcp6_socket->sk, &buff->dst, &fl)) {
if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) {
ip6_xmit(tcp6_socket->sk, buff, &fl, NULL, 0);
@@ -1160,7 +1175,7 @@ static void tcp_v6_send_ack(struct tcp_timewait_sock *tw,
fl.fl_ip_sport = t1->source;
security_skb_classify_flow(skb, &fl);
- if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {
+ if (!ip6_dst_lookup(tcp6_socket->sk, &buff->dst, &fl)) {
if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) {
ip6_xmit(tcp6_socket->sk, buff, &fl, NULL, 0);
TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
@@ -1215,9 +1230,9 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
return NULL;
}
-#if 0 /*def CONFIG_SYN_COOKIES*/
+#ifdef CONFIG_SYN_COOKIES
if (!th->rst && !th->syn && th->ack)
- sk = cookie_v6_check(sk, skb, &(IPCB(skb)->opt));
+ sk = cookie_v6_check(sk, skb);
#endif
return sk;
}
@@ -1233,6 +1248,11 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock *req = NULL;
__u32 isn = TCP_SKB_CB(skb)->when;
+#ifdef CONFIG_SYN_COOKIES
+ int want_cookie = 0;
+#else
+#define want_cookie 0
+#endif
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_conn_request(sk, skb);
@@ -1240,12 +1260,14 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
if (!ipv6_unicast_destination(skb))
goto drop;
- /*
- * There are no SYN attacks on IPv6, yet...
- */
if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
if (net_ratelimit())
- printk(KERN_INFO "TCPv6: dropping request, synflood is possible\n");
+ syn_flood_warning(skb);
+#ifdef CONFIG_SYN_COOKIES
+ if (sysctl_tcp_syncookies)
+ want_cookie = 1;
+ else
+#endif
goto drop;
}
@@ -1266,39 +1288,51 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_parse_options(skb, &tmp_opt, 0);
+ if (want_cookie) {
+ tcp_clear_options(&tmp_opt);
+ tmp_opt.saw_tstamp = 0;
+ }
+
tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
tcp_openreq_init(req, &tmp_opt, skb);
treq = inet6_rsk(req);
ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr);
ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr);
- TCP_ECN_create_request(req, tcp_hdr(skb));
treq->pktopts = NULL;
- if (ipv6_opt_accepted(sk, skb) ||
- np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
- np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
- atomic_inc(&skb->users);
- treq->pktopts = skb;
- }
- treq->iif = sk->sk_bound_dev_if;
+ if (!want_cookie)
+ TCP_ECN_create_request(req, tcp_hdr(skb));
+
+ if (want_cookie) {
+ isn = cookie_v6_init_sequence(sk, skb, &req->mss);
+ } else if (!isn) {
+ if (ipv6_opt_accepted(sk, skb) ||
+ np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
+ np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
+ atomic_inc(&skb->users);
+ treq->pktopts = skb;
+ }
+ treq->iif = sk->sk_bound_dev_if;
- /* So that link locals have meaning */
- if (!sk->sk_bound_dev_if &&
- ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
- treq->iif = inet6_iif(skb);
+ /* So that link locals have meaning */
+ if (!sk->sk_bound_dev_if &&
+ ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
+ treq->iif = inet6_iif(skb);
- if (isn == 0)
isn = tcp_v6_init_sequence(skb);
+ }
tcp_rsk(req)->snt_isn = isn;
security_inet_conn_request(sk, skb, req);
- if (tcp_v6_send_synack(sk, req, NULL))
+ if (tcp_v6_send_synack(sk, req))
goto drop;
- inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
- return 0;
+ if (!want_cookie) {
+ inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+ return 0;
+ }
drop:
if (req)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp_ipv6.c
index 53739de829d..55feac7ba71 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp_ipv6.c
@@ -400,7 +400,7 @@ static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh,
UDP_SKB_CB(skb)->partial_cov = 0;
UDP_SKB_CB(skb)->cscov = skb->len;
- if (proto == IPPROTO_UDPLITE) {
+ if (IS_PROTO_UDPLITE(proto)) {
err = udplite_checksum_init(skb, uh);
if (err)
return err;
@@ -489,7 +489,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
if (udp_lib_checksum_complete(skb))
goto discard;
- UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
+ UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, IS_PROTO_UDPLITE(proto));
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev);
@@ -510,11 +510,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
short_packet:
LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n",
- proto == IPPROTO_UDPLITE ? "-Lite" : "",
+ IS_PROTO_UDPLITE(proto) ? "-Lite" : "",
ulen, skb->len);
discard:
- UDP6_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
+ UDP6_INC_STATS_BH(UDP_MIB_INERRORS, IS_PROTO_UDPLITE(proto));
kfree_skb(skb);
return 0;
}
@@ -890,7 +890,7 @@ int udpv6_destroy_sock(struct sock *sk)
int udpv6_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, int optlen)
{
- if (level == SOL_UDP || level == SOL_UDPLITE)
+ if (IS_SOL_UDPFAMILY(level))
return udp_lib_setsockopt(sk, level, optname, optval, optlen,
udp_v6_push_pending_frames);
return ipv6_setsockopt(sk, level, optname, optval, optlen);
@@ -900,7 +900,7 @@ int udpv6_setsockopt(struct sock *sk, int level, int optname,
int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, int optlen)
{
- if (level == SOL_UDP || level == SOL_UDPLITE)
+ if (IS_SOL_UDPFAMILY(level))
return udp_lib_setsockopt(sk, level, optname, optval, optlen,
udp_v6_push_pending_frames);
return compat_ipv6_setsockopt(sk, level, optname, optval, optlen);
@@ -910,7 +910,7 @@ int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
int udpv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
- if (level == SOL_UDP || level == SOL_UDPLITE)
+ if (IS_SOL_UDPFAMILY(level))
return udp_lib_getsockopt(sk, level, optname, optval, optlen);
return ipv6_getsockopt(sk, level, optname, optval, optlen);
}
@@ -919,7 +919,7 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname,
int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
- if (level == SOL_UDP || level == SOL_UDPLITE)
+ if (IS_SOL_UDPFAMILY(level))
return udp_lib_getsockopt(sk, level, optname, optval, optlen);
return compat_ipv6_getsockopt(sk, level, optname, optval, optlen);
}
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite_ipv6.c
index 87d4202522e..87d4202522e 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite_ipv6.c
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 7d20199ee1f..e96dafdc703 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -38,7 +38,7 @@ static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr,
if (saddr)
memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src));
- dst = ip6_route_output(NULL, &fl);
+ dst = ip6_route_output(&init_net, NULL, &fl);
err = dst->error;
if (dst->error) {
@@ -57,8 +57,9 @@ static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr)
if (IS_ERR(dst))
return -EHOSTUNREACH;
- ipv6_get_saddr(dst, (struct in6_addr *)&daddr->a6,
- (struct in6_addr *)&saddr->a6);
+ ipv6_dev_get_saddr(ip6_dst_idev(dst)->dev,
+ (struct in6_addr *)&daddr->a6,
+ (struct in6_addr *)&saddr->a6);
dst_release(dst);
return 0;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-06 11:40:54 +0000