summaryrefslogtreecommitdiff
path: root/net/ipv6/route.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/route.c')
-rw-r--r--net/ipv6/route.c742
1 files changed, 397 insertions, 345 deletions
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 496b62712fe8..84f6564dd372 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -24,6 +24,8 @@
* Fixed routing subtrees.
*/
+#define pr_fmt(fmt) "IPv6: " fmt
+
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/export.h>
@@ -62,7 +64,7 @@
#include <linux/sysctl.h>
#endif
-static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
+static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
const struct in6_addr *dest);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
@@ -76,13 +78,16 @@ static int ip6_dst_gc(struct dst_ops *ops);
static int ip6_pkt_discard(struct sk_buff *skb);
static int ip6_pkt_discard_out(struct sk_buff *skb);
static void ip6_link_failure(struct sk_buff *skb);
-static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
+static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu);
+static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb);
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr, int ifindex,
- unsigned pref);
+ unsigned int pref);
static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr, int ifindex);
@@ -97,10 +102,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
if (!(rt->dst.flags & DST_HOST))
return NULL;
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
-
- peer = rt->rt6i_peer;
+ peer = rt6_get_peer_create(rt);
if (peer) {
u32 *old_p = __DST_METRICS_PTR(old);
unsigned long prev, new;
@@ -121,21 +123,27 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
return p;
}
-static inline const void *choose_neigh_daddr(struct rt6_info *rt, const void *daddr)
+static inline const void *choose_neigh_daddr(struct rt6_info *rt,
+ struct sk_buff *skb,
+ const void *daddr)
{
struct in6_addr *p = &rt->rt6i_gateway;
if (!ipv6_addr_any(p))
return (const void *) p;
+ else if (skb)
+ return &ipv6_hdr(skb)->daddr;
return daddr;
}
-static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr)
+static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
+ struct sk_buff *skb,
+ const void *daddr)
{
struct rt6_info *rt = (struct rt6_info *) dst;
struct neighbour *n;
- daddr = choose_neigh_daddr(rt, daddr);
+ daddr = choose_neigh_daddr(rt, skb, daddr);
n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr);
if (n)
return n;
@@ -150,7 +158,7 @@ static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev)
if (IS_ERR(n))
return PTR_ERR(n);
}
- dst_set_neighbour(&rt->dst, n);
+ rt->n = n;
return 0;
}
@@ -169,6 +177,7 @@ static struct dst_ops ip6_dst_ops_template = {
.negative_advice = ip6_negative_advice,
.link_failure = ip6_link_failure,
.update_pmtu = ip6_rt_update_pmtu,
+ .redirect = rt6_do_redirect,
.local_out = __ip6_local_out,
.neigh_lookup = ip6_neigh_lookup,
};
@@ -180,7 +189,13 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
return mtu ? : dst->dev->mtu;
}
-static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu)
+{
+}
+
+static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb)
{
}
@@ -198,6 +213,7 @@ static struct dst_ops ip6_dst_blackhole_ops = {
.mtu = ip6_blackhole_mtu,
.default_advmss = ip6_default_advmss,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
+ .redirect = ip6_rt_blackhole_redirect,
.cow_metrics = ip6_rt_blackhole_cow_metrics,
.neigh_lookup = ip6_neigh_lookup,
};
@@ -259,16 +275,20 @@ static struct rt6_info ip6_blk_hole_entry_template = {
#endif
/* allocate dst with ip6_dst_ops */
-static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
+static inline struct rt6_info *ip6_dst_alloc(struct net *net,
struct net_device *dev,
- int flags)
+ int flags,
+ struct fib6_table *table)
{
- struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags);
+ struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
+ 0, 0, flags);
- if (rt)
- memset(&rt->rt6i_table, 0,
- sizeof(*rt) - sizeof(struct dst_entry));
+ if (rt) {
+ struct dst_entry *dst = &rt->dst;
+ memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
+ rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
+ }
return rt;
}
@@ -276,7 +296,9 @@ static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
- struct inet_peer *peer = rt->rt6i_peer;
+
+ if (rt->n)
+ neigh_release(rt->n);
if (!(rt->dst.flags & DST_HOST))
dst_destroy_metrics_generic(dst);
@@ -285,8 +307,12 @@ static void ip6_dst_destroy(struct dst_entry *dst)
rt->rt6i_idev = NULL;
in6_dev_put(idev);
}
- if (peer) {
- rt->rt6i_peer = NULL;
+
+ if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from)
+ dst_release(dst->from);
+
+ if (rt6_has_peer(rt)) {
+ struct inet_peer *peer = rt6_peer_ptr(rt);
inet_putpeer(peer);
}
}
@@ -300,13 +326,20 @@ static u32 rt6_peer_genid(void)
void rt6_bind_peer(struct rt6_info *rt, int create)
{
+ struct inet_peer_base *base;
struct inet_peer *peer;
- peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create);
- if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL)
- inet_putpeer(peer);
- else
- rt->rt6i_peer_genid = rt6_peer_genid();
+ base = inetpeer_base_ptr(rt->_rt6i_peer);
+ if (!base)
+ return;
+
+ peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
+ if (peer) {
+ if (!rt6_set_peer(rt, peer))
+ inet_putpeer(peer);
+ else
+ rt->rt6i_peer_genid = rt6_peer_genid();
+ }
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -317,23 +350,39 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
struct net_device *loopback_dev =
dev_net(dev)->loopback_dev;
- if (dev != loopback_dev && idev && idev->dev == dev) {
- struct inet6_dev *loopback_idev =
- in6_dev_get(loopback_dev);
- if (loopback_idev) {
- rt->rt6i_idev = loopback_idev;
- in6_dev_put(idev);
+ if (dev != loopback_dev) {
+ if (idev && idev->dev == dev) {
+ struct inet6_dev *loopback_idev =
+ in6_dev_get(loopback_dev);
+ if (loopback_idev) {
+ rt->rt6i_idev = loopback_idev;
+ in6_dev_put(idev);
+ }
+ }
+ if (rt->n && rt->n->dev == dev) {
+ rt->n->dev = loopback_dev;
+ dev_hold(loopback_dev);
+ dev_put(dev);
}
}
}
-static __inline__ int rt6_check_expired(const struct rt6_info *rt)
+static bool rt6_check_expired(const struct rt6_info *rt)
{
- return (rt->rt6i_flags & RTF_EXPIRES) &&
- time_after(jiffies, rt->dst.expires);
+ struct rt6_info *ort = NULL;
+
+ if (rt->rt6i_flags & RTF_EXPIRES) {
+ if (time_after(jiffies, rt->dst.expires))
+ return true;
+ } else if (rt->dst.from) {
+ ort = (struct rt6_info *) rt->dst.from;
+ return (ort->rt6i_flags & RTF_EXPIRES) &&
+ time_after(jiffies, ort->dst.expires);
+ }
+ return false;
}
-static inline int rt6_need_strict(const struct in6_addr *daddr)
+static bool rt6_need_strict(const struct in6_addr *daddr)
{
return ipv6_addr_type(daddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
@@ -403,7 +452,7 @@ static void rt6_probe(struct rt6_info *rt)
* to no more than one per minute.
*/
rcu_read_lock();
- neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL;
+ neigh = rt ? rt->n : NULL;
if (!neigh || (neigh->nud_state & NUD_VALID))
goto out;
read_lock_bh(&neigh->lock);
@@ -450,7 +499,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt)
int m;
rcu_read_lock();
- neigh = dst_get_neighbour_noref(&rt->dst);
+ neigh = rt->n;
if (rt->rt6i_flags & RTF_NONEXTHOP ||
!(rt->rt6i_flags & RTF_GATEWAY))
m = 1;
@@ -620,12 +669,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
(rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
if (rt) {
- if (!addrconf_finite_timeout(lifetime)) {
- rt->rt6i_flags &= ~RTF_EXPIRES;
- } else {
- rt->dst.expires = jiffies + HZ * lifetime;
- rt->rt6i_flags |= RTF_EXPIRES;
- }
+ if (!addrconf_finite_timeout(lifetime))
+ rt6_clean_expires(rt);
+ else
+ rt6_set_expires(rt, jiffies + HZ * lifetime);
+
dst_release(&rt->dst);
}
return 0;
@@ -730,7 +778,7 @@ int ip6_ins_rt(struct rt6_info *rt)
return __ip6_ins_rt(rt, &info);
}
-static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort,
+static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
@@ -782,9 +830,7 @@ static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort,
goto retry;
}
- if (net_ratelimit())
- printk(KERN_WARNING
- "ipv6: Neighbour table overflow.\n");
+ net_warn_ratelimited("Neighbour table overflow\n");
dst_free(&rt->dst);
return NULL;
}
@@ -800,7 +846,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
if (rt) {
rt->rt6i_flags |= RTF_CACHE;
- dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst)));
+ rt->n = neigh_clone(ort->n);
}
return rt;
}
@@ -834,7 +880,7 @@ restart:
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
- if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+ if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
else if (!(rt->dst.flags & DST_HOST))
nrt = rt6_alloc_clone(rt, &fl6->daddr);
@@ -881,6 +927,16 @@ static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *
return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags);
}
+static struct dst_entry *ip6_route_input_lookup(struct net *net,
+ struct net_device *dev,
+ struct flowi6 *fl6, int flags)
+{
+ if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG)
+ flags |= RT6_LOOKUP_F_IFACE;
+
+ return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input);
+}
+
void ip6_route_input(struct sk_buff *skb)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
@@ -895,10 +951,7 @@ void ip6_route_input(struct sk_buff *skb)
.flowi6_proto = iph->nexthdr,
};
- if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG)
- flags |= RT6_LOOKUP_F_IFACE;
-
- skb_dst_set(skb, fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_input));
+ skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags));
}
static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
@@ -912,6 +965,8 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
{
int flags = 0;
+ fl6->flowi6_iif = net->loopback_dev->ifindex;
+
if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
flags |= RT6_LOOKUP_F_IFACE;
@@ -932,10 +987,11 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
if (rt) {
- memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
-
new = &rt->dst;
+ memset(new + 1, 0, sizeof(*rt) - sizeof(*new));
+ rt6_init_peer(rt, net->ipv6.peers);
+
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard;
@@ -947,10 +1003,10 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
- rt->dst.expires = 0;
rt->rt6i_gateway = ort->rt6i_gateway;
- rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
+ rt->rt6i_flags = ort->rt6i_flags;
+ rt6_clean_expires(rt);
rt->rt6i_metric = 0;
memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
@@ -977,7 +1033,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
if (rt->rt6i_peer_genid != rt6_peer_genid()) {
- if (!rt->rt6i_peer)
+ if (!rt6_has_peer(rt))
rt6_bind_peer(rt, 0);
rt->rt6i_peer_genid = rt6_peer_genid();
}
@@ -1012,19 +1068,22 @@ static void ip6_link_failure(struct sk_buff *skb)
rt = (struct rt6_info *) skb_dst(skb);
if (rt) {
- if (rt->rt6i_flags & RTF_CACHE) {
- dst_set_expires(&rt->dst, 0);
- rt->rt6i_flags |= RTF_EXPIRES;
- } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
+ if (rt->rt6i_flags & RTF_CACHE)
+ rt6_update_expires(rt, 0);
+ else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
rt->rt6i_node->fn_sernum = -1;
}
}
-static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu)
{
struct rt6_info *rt6 = (struct rt6_info*)dst;
+ dst_confirm(dst);
if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
+ struct net *net = dev_net(dst->dev);
+
rt6->rt6i_flags |= RTF_MODIFIED;
if (mtu < IPV6_MIN_MTU) {
u32 features = dst_metric(dst, RTAX_FEATURES);
@@ -1033,9 +1092,66 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
dst_metric_set(dst, RTAX_FEATURES, features);
}
dst_metric_set(dst, RTAX_MTU, mtu);
+ rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
}
+void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
+ int oif, u32 mark)
+{
+ const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
+ struct dst_entry *dst;
+ struct flowi6 fl6;
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = oif;
+ fl6.flowi6_mark = mark;
+ fl6.flowi6_flags = 0;
+ fl6.daddr = iph->daddr;
+ fl6.saddr = iph->saddr;
+ fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (!dst->error)
+ ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu));
+ dst_release(dst);
+}
+EXPORT_SYMBOL_GPL(ip6_update_pmtu);
+
+void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
+{
+ ip6_update_pmtu(skb, sock_net(sk), mtu,
+ sk->sk_bound_dev_if, sk->sk_mark);
+}
+EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
+
+void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
+{
+ const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
+ struct dst_entry *dst;
+ struct flowi6 fl6;
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = oif;
+ fl6.flowi6_mark = mark;
+ fl6.flowi6_flags = 0;
+ fl6.daddr = iph->daddr;
+ fl6.saddr = iph->saddr;
+ fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (!dst->error)
+ rt6_do_redirect(dst, NULL, skb);
+ dst_release(dst);
+}
+EXPORT_SYMBOL_GPL(ip6_redirect);
+
+void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk)
+{
+ ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark);
+}
+EXPORT_SYMBOL_GPL(ip6_sk_redirect);
+
static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
@@ -1092,7 +1208,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
if (unlikely(!idev))
return ERR_PTR(-ENODEV);
- rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0);
+ rt = ip6_dst_alloc(net, dev, 0, NULL);
if (unlikely(!rt)) {
in6_dev_put(idev);
dst = ERR_PTR(-ENOMEM);
@@ -1102,7 +1218,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
if (neigh)
neigh_hold(neigh);
else {
- neigh = ip6_neigh_lookup(&rt->dst, &fl6->daddr);
+ neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr);
if (IS_ERR(neigh)) {
in6_dev_put(idev);
dst_free(&rt->dst);
@@ -1112,7 +1228,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
rt->dst.flags |= DST_HOST;
rt->dst.output = ip6_output;
- dst_set_neighbour(&rt->dst, neigh);
+ rt->n = neigh;
atomic_set(&rt->dst.__refcnt, 1);
rt->rt6i_dst.addr = fl6->daddr;
rt->rt6i_dst.plen = 128;
@@ -1264,7 +1380,7 @@ int ip6_route_add(struct fib6_config *cfg)
!(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) {
table = fib6_get_table(net, cfg->fc_table);
if (!table) {
- printk(KERN_WARNING "IPv6: NLM_F_CREATE should be specified when creating new route\n");
+ pr_warn("NLM_F_CREATE should be specified when creating new route\n");
table = fib6_new_table(net, cfg->fc_table);
}
} else {
@@ -1274,7 +1390,7 @@ int ip6_route_add(struct fib6_config *cfg)
if (!table)
goto out;
- rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT);
+ rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
if (!rt) {
err = -ENOMEM;
@@ -1282,9 +1398,12 @@ int ip6_route_add(struct fib6_config *cfg)
}
rt->dst.obsolete = -1;
- rt->dst.expires = (cfg->fc_flags & RTF_EXPIRES) ?
- jiffies + clock_t_to_jiffies(cfg->fc_expires) :
- 0;
+
+ if (cfg->fc_flags & RTF_EXPIRES)
+ rt6_set_expires(rt, jiffies +
+ clock_t_to_jiffies(cfg->fc_expires));
+ else
+ rt6_clean_expires(rt);
if (cfg->fc_protocol == RTPROT_UNSPEC)
cfg->fc_protocol = RTPROT_BOOT;
@@ -1525,108 +1644,93 @@ static int ip6_route_del(struct fib6_config *cfg)
return err;
}
-/*
- * Handle redirects
- */
-struct ip6rd_flowi {
- struct flowi6 fl6;
- struct in6_addr gateway;
-};
-
-static struct rt6_info *__ip6_route_redirect(struct net *net,
- struct fib6_table *table,
- struct flowi6 *fl6,
- int flags)
+static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
{
- struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
- struct rt6_info *rt;
- struct fib6_node *fn;
+ struct net *net = dev_net(skb->dev);
+ struct netevent_redirect netevent;
+ struct rt6_info *rt, *nrt = NULL;
+ const struct in6_addr *target;
+ struct ndisc_options ndopts;
+ const struct in6_addr *dest;
+ struct neighbour *old_neigh;
+ struct inet6_dev *in6_dev;
+ struct neighbour *neigh;
+ struct icmp6hdr *icmph;
+ int optlen, on_link;
+ u8 *lladdr;
- /*
- * Get the "current" route for this destination and
- * check if the redirect has come from approriate router.
- *
- * RFC 2461 specifies that redirects should only be
- * accepted if they come from the nexthop to the target.
- * Due to the way the routes are chosen, this notion
- * is a bit fuzzy and one might need to check all possible
- * routes.
- */
+ optlen = skb->tail - skb->transport_header;
+ optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr);
- read_lock_bh(&table->tb6_lock);
- fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
-restart:
- for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
- /*
- * Current route is on-link; redirect is always invalid.
- *
- * Seems, previous statement is not true. It could
- * be node, which looks for us as on-link (f.e. proxy ndisc)
- * But then router serving it might decide, that we should
- * know truth 8)8) --ANK (980726).
- */
- if (rt6_check_expired(rt))
- continue;
- if (!(rt->rt6i_flags & RTF_GATEWAY))
- continue;
- if (fl6->flowi6_oif != rt->dst.dev->ifindex)
- continue;
- if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
- continue;
- break;
+ if (optlen < 0) {
+ net_dbg_ratelimited("rt6_do_redirect: packet too short\n");
+ return;
}
- if (!rt)
- rt = net->ipv6.ip6_null_entry;
- BACKTRACK(net, &fl6->saddr);
-out:
- dst_hold(&rt->dst);
+ icmph = icmp6_hdr(skb);
+ target = (const struct in6_addr *) (icmph + 1);
+ dest = target + 1;
- read_unlock_bh(&table->tb6_lock);
+ if (ipv6_addr_is_multicast(dest)) {
+ net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n");
+ return;
+ }
- return rt;
-};
+ on_link = 0;
+ if (ipv6_addr_equal(dest, target)) {
+ on_link = 1;
+ } else if (ipv6_addr_type(target) !=
+ (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) {
+ net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n");
+ return;
+ }
-static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest,
- const struct in6_addr *src,
- const struct in6_addr *gateway,
- struct net_device *dev)
-{
- int flags = RT6_LOOKUP_F_HAS_SADDR;
- struct net *net = dev_net(dev);
- struct ip6rd_flowi rdfl = {
- .fl6 = {
- .flowi6_oif = dev->ifindex,
- .daddr = *dest,
- .saddr = *src,
- },
- };
+ in6_dev = __in6_dev_get(skb->dev);
+ if (!in6_dev)
+ return;
+ if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects)
+ return;
- rdfl.gateway = *gateway;
+ /* RFC2461 8.1:
+ * The IP source address of the Redirect MUST be the same as the current
+ * first-hop router for the specified ICMP Destination Address.
+ */
- if (rt6_need_strict(dest))
- flags |= RT6_LOOKUP_F_IFACE;
+ if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) {
+ net_dbg_ratelimited("rt6_redirect: invalid ND options\n");
+ return;
+ }
- return (struct rt6_info *)fib6_rule_lookup(net, &rdfl.fl6,
- flags, __ip6_route_redirect);
-}
+ lladdr = NULL;
+ if (ndopts.nd_opts_tgt_lladdr) {
+ lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr,
+ skb->dev);
+ if (!lladdr) {
+ net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n");
+ return;
+ }
+ }
-void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
- const struct in6_addr *saddr,
- struct neighbour *neigh, u8 *lladdr, int on_link)
-{
- struct rt6_info *rt, *nrt = NULL;
- struct netevent_redirect netevent;
- struct net *net = dev_net(neigh->dev);
+ rt = (struct rt6_info *) dst;
+ if (rt == net->ipv6.ip6_null_entry) {
+ net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n");
+ return;
+ }
- rt = ip6_route_redirect(dest, src, saddr, neigh->dev);
+ /* Redirect received -> path was valid.
+ * Look, redirects are sent only in response to data packets,
+ * so that this nexthop apparently is reachable. --ANK
+ */
+ dst_confirm(&rt->dst);
- 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");
+ neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1);
+ if (!neigh)
+ return;
+
+ /* Duplicate redirect: silently ignore. */
+ old_neigh = rt->n;
+ if (neigh == old_neigh)
goto out;
- }
/*
* We have finally decided to accept it.
@@ -1639,17 +1743,6 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
NEIGH_UPDATE_F_ISROUTER))
);
- /*
- * Redirect received -> path was valid.
- * Look, redirects are sent only in response to data packets,
- * so that this nexthop apparently is reachable. --ANK
- */
- dst_confirm(&rt->dst);
-
- /* Duplicate redirect: silently ignore. */
- if (neigh == dst_get_neighbour_noref_raw(&rt->dst))
- goto out;
-
nrt = ip6_rt_copy(rt, dest);
if (!nrt)
goto out;
@@ -1659,145 +1752,37 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
nrt->rt6i_flags &= ~RTF_GATEWAY;
nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
- dst_set_neighbour(&nrt->dst, neigh_clone(neigh));
+ nrt->n = neigh_clone(neigh);
if (ip6_ins_rt(nrt))
goto out;
netevent.old = &rt->dst;
+ netevent.old_neigh = old_neigh;
netevent.new = &nrt->dst;
+ netevent.new_neigh = neigh;
+ netevent.daddr = dest;
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
if (rt->rt6i_flags & RTF_CACHE) {
+ rt = (struct rt6_info *) dst_clone(&rt->dst);
ip6_del_rt(rt);
- return;
- }
-
-out:
- dst_release(&rt->dst);
-}
-
-/*
- * Handle ICMP "packet too big" messages
- * i.e. Path MTU discovery
- */
-
-static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct net *net, u32 pmtu, int ifindex)
-{
- struct rt6_info *rt, *nrt;
- int allfrag = 0;
-again:
- rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
- if (!rt)
- return;
-
- if (rt6_check_expired(rt)) {
- ip6_del_rt(rt);
- goto again;
- }
-
- if (pmtu >= dst_mtu(&rt->dst))
- goto out;
-
- if (pmtu < IPV6_MIN_MTU) {
- /*
- * According to RFC2460, PMTU is set to the IPv6 Minimum Link
- * MTU (1280) and a fragment header should always be included
- * after a node receiving Too Big message reporting PMTU is
- * less than the IPv6 Minimum Link MTU.
- */
- pmtu = IPV6_MIN_MTU;
- allfrag = 1;
- }
-
- /* New mtu received -> path was valid.
- They are sent only in response to data packets,
- so that this nexthop apparently is reachable. --ANK
- */
- dst_confirm(&rt->dst);
-
- /* Host route. If it is static, it would be better
- not to override it, but add new one, so that
- when cache entry will expire old pmtu
- would return automatically.
- */
- if (rt->rt6i_flags & RTF_CACHE) {
- dst_metric_set(&rt->dst, RTAX_MTU, pmtu);
- if (allfrag) {
- u32 features = dst_metric(&rt->dst, RTAX_FEATURES);
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(&rt->dst, RTAX_FEATURES, features);
- }
- dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
- rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
- goto out;
}
- /* Network route.
- Two cases are possible:
- 1. It is connected route. Action: COW
- 2. It is gatewayed route or NONEXTHOP route. Action: clone it.
- */
- if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
- nrt = rt6_alloc_cow(rt, daddr, saddr);
- else
- nrt = rt6_alloc_clone(rt, daddr);
-
- if (nrt) {
- dst_metric_set(&nrt->dst, RTAX_MTU, pmtu);
- if (allfrag) {
- u32 features = dst_metric(&nrt->dst, RTAX_FEATURES);
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(&nrt->dst, RTAX_FEATURES, features);
- }
-
- /* According to RFC 1981, detecting PMTU increase shouldn't be
- * happened within 5 mins, the recommended timer is 10 mins.
- * Here this route expiration time is set to ip6_rt_mtu_expires
- * which is 10 mins. After 10 mins the decreased pmtu is expired
- * and detecting PMTU increase will be automatically happened.
- */
- dst_set_expires(&nrt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
- nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;
-
- ip6_ins_rt(nrt);
- }
out:
- dst_release(&rt->dst);
-}
-
-void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct net_device *dev, u32 pmtu)
-{
- struct net *net = dev_net(dev);
-
- /*
- * RFC 1981 states that a node "MUST reduce the size of the packets it
- * is sending along the path" that caused the Packet Too Big message.
- * Since it's not possible in the general case to determine which
- * interface was used to send the original packet, we update the MTU
- * on the interface that will be used to send future packets. We also
- * update the MTU on the interface that received the Packet Too Big in
- * case the original packet was forced out that interface with
- * SO_BINDTODEVICE or similar. This is the next best thing to the
- * correct behaviour, which would be to update the MTU on all
- * interfaces.
- */
- rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
- rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
+ neigh_release(neigh);
}
/*
* Misc support functions
*/
-static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
+static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
const struct in6_addr *dest)
{
struct net *net = dev_net(ort->dst.dev);
- struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
- ort->dst.dev, 0);
+ struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0,
+ ort->rt6i_table);
if (rt) {
rt->dst.input = ort->dst.input;
@@ -1812,10 +1797,14 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
- rt->dst.expires = 0;
rt->rt6i_gateway = ort->rt6i_gateway;
- rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
+ rt->rt6i_flags = ort->rt6i_flags;
+ if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
+ (RTF_DEFAULT | RTF_ADDRCONF))
+ rt6_set_from(rt, ort);
+ else
+ rt6_clean_expires(rt);
rt->rt6i_metric = 0;
#ifdef CONFIG_IPV6_SUBTREES
@@ -1863,7 +1852,7 @@ out:
static struct rt6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr, int ifindex,
- unsigned pref)
+ unsigned int pref)
{
struct fib6_config cfg = {
.fc_table = RT6_TABLE_INFO,
@@ -2077,14 +2066,11 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
bool anycast)
{
struct net *net = dev_net(idev->dev);
- struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
- net->loopback_dev, 0);
+ struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL);
int err;
if (!rt) {
- if (net_ratelimit())
- pr_warning("IPv6: Maximum number of routes reached,"
- " consider increasing route/max_size.\n");
+ net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n");
return ERR_PTR(-ENOMEM);
}
@@ -2193,10 +2179,9 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
icmp6_clean_all(fib6_ifdown, &adn);
}
-struct rt6_mtu_change_arg
-{
+struct rt6_mtu_change_arg {
struct net_device *dev;
- unsigned mtu;
+ unsigned int mtu;
};
static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
@@ -2238,7 +2223,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
return 0;
}
-void rt6_mtu_change(struct net_device *dev, unsigned mtu)
+void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
{
struct rt6_mtu_change_arg arg = {
.dev = dev,
@@ -2377,13 +2362,11 @@ static int rt6_fill_node(struct net *net,
int iif, int type, u32 pid, u32 seq,
int prefix, int nowait, unsigned int flags)
{
- const struct inet_peer *peer;
struct rtmsg *rtm;
struct nlmsghdr *nlh;
long expires;
u32 table;
struct neighbour *n;
- u32 ts, tsage;
if (prefix) { /* user wants prefix routes only */
if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
@@ -2406,7 +2389,8 @@ static int rt6_fill_node(struct net *net,
else
table = RT6_TABLE_UNSPEC;
rtm->rtm_table = table;
- NLA_PUT_U32(skb, RTA_TABLE, table);
+ if (nla_put_u32(skb, RTA_TABLE, table))
+ goto nla_put_failure;
if (rt->rt6i_flags & RTF_REJECT)
rtm->rtm_type = RTN_UNREACHABLE;
else if (rt->rt6i_flags & RTF_LOCAL)
@@ -2420,25 +2404,31 @@ static int rt6_fill_node(struct net *net,
rtm->rtm_protocol = rt->rt6i_protocol;
if (rt->rt6i_flags & RTF_DYNAMIC)
rtm->rtm_protocol = RTPROT_REDIRECT;
- else if (rt->rt6i_flags & RTF_ADDRCONF)
- rtm->rtm_protocol = RTPROT_KERNEL;
- else if (rt->rt6i_flags & RTF_DEFAULT)
- rtm->rtm_protocol = RTPROT_RA;
+ else if (rt->rt6i_flags & RTF_ADDRCONF) {
+ if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO))
+ rtm->rtm_protocol = RTPROT_RA;
+ else
+ rtm->rtm_protocol = RTPROT_KERNEL;
+ }
if (rt->rt6i_flags & RTF_CACHE)
rtm->rtm_flags |= RTM_F_CLONED;
if (dst) {
- NLA_PUT(skb, RTA_DST, 16, dst);
+ if (nla_put(skb, RTA_DST, 16, dst))
+ goto nla_put_failure;
rtm->rtm_dst_len = 128;
} else if (rtm->rtm_dst_len)
- NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr);
+ if (nla_put(skb, RTA_DST, 16, &rt->rt6i_dst.addr))
+ goto nla_put_failure;
#ifdef CONFIG_IPV6_SUBTREES
if (src) {
- NLA_PUT(skb, RTA_SRC, 16, src);
+ if (nla_put(skb, RTA_SRC, 16, src))
+ goto nla_put_failure;
rtm->rtm_src_len = 128;
- } else if (rtm->rtm_src_len)
- NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr);
+ } else if (rtm->rtm_src_len &&
+ nla_put(skb, RTA_SRC, 16, &rt->rt6i_src.addr))
+ goto nla_put_failure;
#endif
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
@@ -2456,24 +2446,27 @@ static int rt6_fill_node(struct net *net,
}
} else
#endif
- NLA_PUT_U32(skb, RTA_IIF, iif);
+ if (nla_put_u32(skb, RTA_IIF, iif))
+ goto nla_put_failure;
} else if (dst) {
struct in6_addr saddr_buf;
- if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0)
- NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
+ if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 &&
+ nla_put(skb, RTA_PREFSRC, 16, &saddr_buf))
+ goto nla_put_failure;
}
if (rt->rt6i_prefsrc.plen) {
struct in6_addr saddr_buf;
saddr_buf = rt->rt6i_prefsrc.addr;
- NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
+ if (nla_put(skb, RTA_PREFSRC, 16, &saddr_buf))
+ goto nla_put_failure;
}
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
rcu_read_lock();
- n = dst_get_neighbour_noref(&rt->dst);
+ n = rt->n;
if (n) {
if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) {
rcu_read_unlock();
@@ -2482,11 +2475,11 @@ static int rt6_fill_node(struct net *net,
}
rcu_read_unlock();
- if (rt->dst.dev)
- NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
-
- NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric);
-
+ if (rt->dst.dev &&
+ nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
+ goto nla_put_failure;
+ if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric))
+ goto nla_put_failure;
if (!(rt->rt6i_flags & RTF_EXPIRES))
expires = 0;
else if (rt->dst.expires - jiffies < INT_MAX)
@@ -2494,15 +2487,7 @@ static int rt6_fill_node(struct net *net,
else
expires = INT_MAX;
- peer = rt->rt6i_peer;
- ts = tsage = 0;
- if (peer && peer->tcp_ts_stamp) {
- ts = peer->tcp_ts;
- tsage = get_seconds() - peer->tcp_ts_stamp;
- }
-
- if (rtnl_put_cacheinfo(skb, &rt->dst, 0, ts, tsage,
- expires, rt->dst.error) < 0)
+ if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
goto nla_put_failure;
return nlmsg_end(skb, nlh);
@@ -2537,7 +2522,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
struct sk_buff *skb;
struct rtmsg *rtm;
struct flowi6 fl6;
- int err, iif = 0;
+ int err, iif = 0, oif = 0;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
if (err < 0)
@@ -2564,19 +2549,34 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
iif = nla_get_u32(tb[RTA_IIF]);
if (tb[RTA_OIF])
- fl6.flowi6_oif = nla_get_u32(tb[RTA_OIF]);
+ oif = nla_get_u32(tb[RTA_OIF]);
if (iif) {
struct net_device *dev;
+ int flags = 0;
+
dev = __dev_get_by_index(net, iif);
if (!dev) {
err = -ENODEV;
goto errout;
}
+
+ fl6.flowi6_iif = iif;
+
+ if (!ipv6_addr_any(&fl6.saddr))
+ flags |= RT6_LOOKUP_F_HAS_SADDR;
+
+ rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6,
+ flags);
+ } else {
+ fl6.flowi6_oif = oif;
+
+ rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
}
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
+ dst_release(&rt->dst);
err = -ENOBUFS;
goto errout;
}
@@ -2587,7 +2587,6 @@ 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(net, NULL, &fl6);
skb_dst_set(skb, &rt->dst);
err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
@@ -2681,7 +2680,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
seq_puts(m, "00000000000000000000000000000000 00 ");
#endif
rcu_read_lock();
- n = dst_get_neighbour_noref(&rt->dst);
+ n = rt->n;
if (n) {
seq_printf(m, "%pi6", n->primary_key);
} else {
@@ -2916,10 +2915,6 @@ static int __net_init ip6_route_net_init(struct net *net)
net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
-#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;
@@ -2940,10 +2935,6 @@ out_ip6_dst_ops:
static void __net_exit 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);
@@ -2952,11 +2943,58 @@ static void __net_exit ip6_route_net_exit(struct net *net)
dst_entries_destroy(&net->ipv6.ip6_dst_ops);
}
+static int __net_init ip6_route_net_init_late(struct net *net)
+{
+#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
+ return 0;
+}
+
+static void __net_exit ip6_route_net_exit_late(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+ proc_net_remove(net, "ipv6_route");
+ proc_net_remove(net, "rt6_stats");
+#endif
+}
+
static struct pernet_operations ip6_route_net_ops = {
.init = ip6_route_net_init,
.exit = ip6_route_net_exit,
};
+static int __net_init ipv6_inetpeer_init(struct net *net)
+{
+ struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL);
+
+ if (!bp)
+ return -ENOMEM;
+ inet_peer_base_init(bp);
+ net->ipv6.peers = bp;
+ return 0;
+}
+
+static void __net_exit ipv6_inetpeer_exit(struct net *net)
+{
+ struct inet_peer_base *bp = net->ipv6.peers;
+
+ net->ipv6.peers = NULL;
+ inetpeer_invalidate_tree(bp);
+ kfree(bp);
+}
+
+static struct pernet_operations ipv6_inetpeer_ops = {
+ .init = ipv6_inetpeer_init,
+ .exit = ipv6_inetpeer_exit,
+};
+
+static struct pernet_operations ip6_route_net_late_ops = {
+ .init = ip6_route_net_init_late,
+ .exit = ip6_route_net_exit_late,
+};
+
static struct notifier_block ip6_route_dev_notifier = {
.notifier_call = ip6_route_dev_notify,
.priority = 0,
@@ -2977,10 +3015,14 @@ int __init ip6_route_init(void)
if (ret)
goto out_kmem_cache;
- ret = register_pernet_subsys(&ip6_route_net_ops);
+ ret = register_pernet_subsys(&ipv6_inetpeer_ops);
if (ret)
goto out_dst_entries;
+ ret = register_pernet_subsys(&ip6_route_net_ops);
+ if (ret)
+ goto out_register_inetpeer;
+
ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
/* Registering of the loopback is done before this portion of code,
@@ -3006,19 +3048,25 @@ int __init ip6_route_init(void)
if (ret)
goto xfrm6_init;
+ ret = register_pernet_subsys(&ip6_route_net_late_ops);
+ if (ret)
+ goto fib6_rules_init;
+
ret = -ENOBUFS;
if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, NULL) ||
__rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, NULL) ||
__rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, NULL))
- goto fib6_rules_init;
+ goto out_register_late_subsys;
ret = register_netdevice_notifier(&ip6_route_dev_notifier);
if (ret)
- goto fib6_rules_init;
+ goto out_register_late_subsys;
out:
return ret;
+out_register_late_subsys:
+ unregister_pernet_subsys(&ip6_route_net_late_ops);
fib6_rules_init:
fib6_rules_cleanup();
xfrm6_init:
@@ -3027,6 +3075,8 @@ out_fib6_init:
fib6_gc_cleanup();
out_register_subsys:
unregister_pernet_subsys(&ip6_route_net_ops);
+out_register_inetpeer:
+ unregister_pernet_subsys(&ipv6_inetpeer_ops);
out_dst_entries:
dst_entries_destroy(&ip6_dst_blackhole_ops);
out_kmem_cache:
@@ -3037,9 +3087,11 @@ out_kmem_cache:
void ip6_route_cleanup(void)
{
unregister_netdevice_notifier(&ip6_route_dev_notifier);
+ unregister_pernet_subsys(&ip6_route_net_late_ops);
fib6_rules_cleanup();
xfrm6_fini();
fib6_gc_cleanup();
+ unregister_pernet_subsys(&ipv6_inetpeer_ops);
unregister_pernet_subsys(&ip6_route_net_ops);
dst_entries_destroy(&ip6_dst_blackhole_ops);
kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-08 16:51:14 +0000