#include <linux/in6.h>
#include <linux/init.h>
#include <linux/if_arp.h>
-
-#ifdef CONFIG_PROC_FS
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
-#endif
-
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#define CLONE_OFFLINK_ROUTE 0
-static int ip6_rt_max_size = 4096;
-static int ip6_rt_gc_min_interval = HZ / 2;
-static int ip6_rt_gc_timeout = 60*HZ;
-int ip6_rt_gc_interval = 30*HZ;
-static int ip6_rt_gc_elasticity = 9;
-static int ip6_rt_mtu_expires = 10*60*HZ;
-static int ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
-
static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void ip6_dst_destroy(struct dst_entry *);
static void ip6_dst_ifdown(struct dst_entry *,
struct net_device *dev, int how);
-static int ip6_dst_gc(void);
+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_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,
.negative_advice = ip6_negative_advice,
.link_failure = ip6_link_failure,
.update_pmtu = ip6_rt_update_pmtu,
+ .local_out = ip6_local_out,
+ .entry_size = sizeof(struct rt6_info),
+ .entries = ATOMIC_INIT(0),
+};
+
+static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
+{
+}
+
+static struct dst_ops ip6_dst_blackhole_ops = {
+ .family = AF_INET6,
+ .protocol = __constant_htons(ETH_P_IPV6),
+ .destroy = ip6_dst_destroy,
+ .check = ip6_dst_check,
+ .update_pmtu = ip6_rt_blackhole_update_pmtu,
.entry_size = sizeof(struct rt6_info),
+ .entries = ATOMIC_INIT(0),
};
-struct rt6_info ip6_null_entry = {
+static struct rt6_info ip6_null_entry_template = {
.u = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
- .dev = &loopback_dev,
.obsolete = -1,
.error = -ENETUNREACH,
.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),
static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct sk_buff *skb);
-static int ip6_pkt_blk_hole(struct sk_buff *skb);
-struct rt6_info ip6_prohibit_entry = {
+struct rt6_info ip6_prohibit_entry_template = {
.u = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
- .dev = &loopback_dev,
.obsolete = -1,
.error = -EACCES,
.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),
.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),
.__use = 1,
- .dev = &loopback_dev,
.obsolete = -1,
.error = -EINVAL,
.metrics = { [RTAX_HOPLIMIT - 1] = 255, },
- .input = ip6_pkt_blk_hole,
- .output = ip6_pkt_blk_hole,
- .ops = &ip6_dst_ops,
- .path = (struct dst_entry*)&ip6_blk_hole_entry,
+ .input = dst_discard,
+ .output = dst_discard,
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
#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)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
+ struct net_device *loopback_dev =
+ dev->nd_net->loopback_dev;
- if (dev != &loopback_dev && idev != NULL && idev->dev == dev) {
- struct inet6_dev *loopback_idev = in6_dev_get(&loopback_dev);
+ if (dev != loopback_dev && idev != NULL && idev->dev == dev) {
+ struct inet6_dev *loopback_idev =
+ in6_dev_get(loopback_dev);
if (loopback_idev != NULL) {
rt->rt6i_idev = loopback_idev;
in6_dev_put(idev);
* 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)
{
return local;
if (strict)
- return &ip6_null_entry;
+ return net->ipv6.ip6_null_entry;
}
return rt;
}
/*
* Default Router Selection (RFC 2461 6.3.6)
*/
-static int inline rt6_check_dev(struct rt6_info *rt, int oif)
+static inline int rt6_check_dev(struct rt6_info *rt, int oif)
{
struct net_device *dev = rt->rt6i_dev;
- int ret = 0;
-
- if (!oif)
+ if (!oif || dev->ifindex == oif)
return 2;
- if (dev->flags & IFF_LOOPBACK) {
- if (!WARN_ON(rt->rt6i_idev == NULL) &&
- rt->rt6i_idev->dev->ifindex == oif)
- ret = 1;
- else
- return 0;
- }
- if (dev->ifindex == oif)
- return 2;
-
- return ret;
+ if ((dev->flags & IFF_LOOPBACK) &&
+ rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif)
+ return 1;
+ return 0;
}
-static int inline rt6_check_neigh(struct rt6_info *rt)
+static inline int rt6_check_neigh(struct rt6_info *rt)
{
struct neighbour *neigh = rt->rt6i_nexthop;
- int m = 0;
+ int m;
if (rt->rt6i_flags & RTF_NONEXTHOP ||
!(rt->rt6i_flags & RTF_GATEWAY))
m = 1;
read_lock_bh(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
m = 2;
- else if (!(neigh->nud_state & NUD_FAILED))
+#ifdef CONFIG_IPV6_ROUTER_PREF
+ else if (neigh->nud_state & NUD_FAILED)
+ m = 0;
+#endif
+ else
m = 1;
read_unlock_bh(&neigh->lock);
- }
+ } else
+ m = 0;
return m;
}
return m;
}
-static struct rt6_info *rt6_select(struct rt6_info **head, int oif,
- int strict)
+static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
+ int *mpri, struct rt6_info *match)
{
- struct rt6_info *match = NULL, *last = NULL;
- struct rt6_info *rt, *rt0 = *head;
- u32 metric;
+ int m;
+
+ if (rt6_check_expired(rt))
+ goto out;
+
+ m = rt6_score_route(rt, oif, strict);
+ if (m < 0)
+ goto out;
+
+ if (m > *mpri) {
+ if (strict & RT6_LOOKUP_F_REACHABLE)
+ rt6_probe(match);
+ *mpri = m;
+ match = rt;
+ } else if (strict & RT6_LOOKUP_F_REACHABLE) {
+ rt6_probe(rt);
+ }
+
+out:
+ return match;
+}
+
+static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
+ struct rt6_info *rr_head,
+ u32 metric, int oif, int strict)
+{
+ struct rt6_info *rt, *match;
int mpri = -1;
- RT6_TRACE("%s(head=%p(*head=%p), oif=%d)\n",
- __FUNCTION__, head, head ? *head : NULL, oif);
+ match = NULL;
+ for (rt = rr_head; rt && rt->rt6i_metric == metric;
+ rt = rt->u.dst.rt6_next)
+ match = find_match(rt, oif, strict, &mpri, match);
+ for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
+ rt = rt->u.dst.rt6_next)
+ match = find_match(rt, oif, strict, &mpri, match);
- for (rt = rt0, metric = rt0->rt6i_metric;
- rt && rt->rt6i_metric == metric && (!last || rt != rt0);
- rt = rt->u.dst.rt6_next) {
- int m;
+ return match;
+}
- if (rt6_check_expired(rt))
- continue;
+static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
+{
+ struct rt6_info *match, *rt0;
+ struct net *net;
- last = rt;
+ RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n",
+ __FUNCTION__, fn->leaf, oif);
- m = rt6_score_route(rt, oif, strict);
- if (m < 0)
- continue;
+ rt0 = fn->rr_ptr;
+ if (!rt0)
+ fn->rr_ptr = rt0 = fn->leaf;
- if (m > mpri) {
- if (strict & RT6_LOOKUP_F_REACHABLE)
- rt6_probe(match);
- match = rt;
- mpri = m;
- } else if (strict & RT6_LOOKUP_F_REACHABLE) {
- rt6_probe(rt);
- }
- }
+ match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);
if (!match &&
- (strict & RT6_LOOKUP_F_REACHABLE) &&
- last && last != rt0) {
+ (strict & RT6_LOOKUP_F_REACHABLE)) {
+ struct rt6_info *next = rt0->u.dst.rt6_next;
+
/* no entries matched; do round-robin */
- static DEFINE_SPINLOCK(lock);
- spin_lock(&lock);
- *head = rt0->u.dst.rt6_next;
- rt0->u.dst.rt6_next = last->u.dst.rt6_next;
- last->u.dst.rt6_next = rt0;
- spin_unlock(&lock);
+ if (!next || next->rt6i_metric != rt0->rt6i_metric)
+ next = fn->leaf;
+
+ if (next != rt0)
+ fn->rr_ptr = next;
}
- RT6_TRACE("%s() => %p, score=%d\n",
- __FUNCTION__, match, mpri);
+ 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;
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);
}
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 |
}
#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) \
} \
} 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;
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_hold(&rt->u.dst);
+ dst_use(&rt->u.dst, jiffies);
read_unlock_bh(&table->tb6_lock);
-
- rt->u.dst.lastuse = jiffies;
- rt->u.dst.__use++;
-
return rt;
}
-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,
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;
return NULL;
}
+EXPORT_SYMBOL(rt6_lookup);
+
/* ip6_ins_rt is called with FREE table->tb6_lock.
It takes new route entry, the addition fails by any reason the
route is freed. In any case, if caller does not hold it, it may
int ip6_ins_rt(struct rt6_info *rt)
{
- return __ip6_ins_rt(rt, NULL);
+ struct nl_info info = {
+ .nl_net = rt->rt6i_dev->nd_net,
+ };
+ return __ip6_ins_rt(rt, &info);
}
static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr,
return rt;
}
-static struct rt6_info *ip6_pol_route_input(struct fib6_table *table,
- 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;
fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
- rt = rt6_select(&fn->leaf, fl->iif, strict | reachable);
- BACKTRACK(&fl->fl6_src);
- if (rt == &ip6_null_entry ||
+ rt = rt6_select(fn, oif, strict | reachable);
+
+ BACKTRACK(net, &fl->fl6_src);
+ if (rt == net->ipv6.ip6_null_entry ||
rt->rt6i_flags & RTF_CACHE)
goto out;
}
dst_release(&rt->u.dst);
- rt = nrt ? : &ip6_null_entry;
+ rt = nrt ? : net->ipv6.ip6_null_entry;
dst_hold(&rt->u.dst);
if (nrt) {
return rt;
}
+static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
+ struct flowi *fl, int flags)
+{
+ return ip6_pol_route(net, table, fl->iif, fl, flags);
+}
+
void ip6_route_input(struct sk_buff *skb)
{
- struct ipv6hdr *iph = skb->nh.ipv6h;
+ 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,
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)
{
- struct fib6_node *fn;
- struct rt6_info *rt, *nrt;
- int strict = 0;
- int attempts = 3;
- int err;
- int reachable = ipv6_devconf.forwarding ? 0 : RT6_LOOKUP_F_REACHABLE;
-
- strict |= flags & RT6_LOOKUP_F_IFACE;
-
-relookup:
- read_lock_bh(&table->tb6_lock);
-
-restart_2:
- fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
-
-restart:
- rt = rt6_select(&fn->leaf, fl->oif, strict | reachable);
- BACKTRACK(&fl->fl6_src);
- if (rt == &ip6_null_entry ||
- rt->rt6i_flags & RTF_CACHE)
- goto out;
-
- dst_hold(&rt->u.dst);
- read_unlock_bh(&table->tb6_lock);
-
- if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
- nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
- else {
-#if CLONE_OFFLINK_ROUTE
- nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
-#else
- goto out2;
-#endif
- }
-
- dst_release(&rt->u.dst);
- rt = nrt ? : &ip6_null_entry;
-
- dst_hold(&rt->u.dst);
- if (nrt) {
- err = ip6_ins_rt(nrt);
- if (!err)
- goto out2;
- }
-
- if (--attempts <= 0)
- goto out2;
-
- /*
- * Race condition! In the gap, when table->tb6_lock was
- * released someone could insert this route. Relookup.
- */
- dst_release(&rt->u.dst);
- goto relookup;
-
-out:
- if (reachable) {
- reachable = 0;
- goto restart_2;
- }
- dst_hold(&rt->u.dst);
- read_unlock_bh(&table->tb6_lock);
-out2:
- rt->u.dst.lastuse = jiffies;
- rt->u.dst.__use++;
- return rt;
+ return ip6_pol_route(net, table, fl->oif, fl, flags);
}
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(&init_net, fl, flags, ip6_pol_route_output);
}
+EXPORT_SYMBOL(ip6_route_output);
+
+int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl)
+{
+ struct rt6_info *ort = (struct rt6_info *) *dstp;
+ struct rt6_info *rt = (struct rt6_info *)
+ dst_alloc(&ip6_dst_blackhole_ops);
+ struct dst_entry *new = NULL;
+
+ if (rt) {
+ new = &rt->u.dst;
+
+ atomic_set(&new->__refcnt, 1);
+ new->__use = 1;
+ new->input = dst_discard;
+ new->output = dst_discard;
+
+ memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
+ new->dev = ort->u.dst.dev;
+ if (new->dev)
+ dev_hold(new->dev);
+ rt->rt6i_idev = ort->rt6i_idev;
+ if (rt->rt6i_idev)
+ in6_dev_hold(rt->rt6i_idev);
+ rt->rt6i_expires = 0;
+
+ ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
+ rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
+ rt->rt6i_metric = 0;
+
+ memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
+#ifdef CONFIG_IPV6_SUBTREES
+ memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
+#endif
+
+ dst_free(new);
+ }
+
+ dst_release(*dstp);
+ *dstp = new;
+ return (new ? 0 : -ENOMEM);
+}
+EXPORT_SYMBOL_GPL(ip6_dst_blackhole);
/*
* Destination cache support functions
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 < ip6_rt_min_advmss)
- mtu = 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
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;
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
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;
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)) {
}
}
- spin_unlock_bh(&ndisc_lock);
+ spin_unlock_bh(&icmp6_dst_lock);
return freed;
}
-static int ip6_dst_gc(void)
+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 + ip6_rt_gc_min_interval, now) &&
- atomic_read(&ip6_dst_ops.entries) <= ip6_rt_max_size)
+ if (time_after(last_gc + init_net.ipv6.sysctl.ip6_rt_gc_min_interval, now) &&
+ atomic_read(&init_net.ipv6.ip6_dst_ops->entries) <= init_net.ipv6.sysctl.ip6_rt_max_size)
goto out;
expire++;
- fib6_run_gc(expire);
+ fib6_run_gc(expire, &init_net);
last_gc = now;
- if (atomic_read(&ip6_dst_ops.entries) < ip6_dst_ops.gc_thresh)
- expire = ip6_rt_gc_timeout>>1;
+ if (atomic_read(&init_net.ipv6.ip6_dst_ops->entries) < init_net.ipv6.ip6_dst_ops->gc_thresh)
+ expire = init_net.ipv6.sysctl.ip6_rt_gc_timeout>>1;
out:
- expire -= expire>>ip6_rt_gc_elasticity;
- return (atomic_read(&ip6_dst_ops.entries) > ip6_rt_max_size);
+ expire -= expire>>init_net.ipv6.sysctl.ip6_rt_gc_elasticity;
+ return (atomic_read(&init_net.ipv6.ip6_dst_ops->entries) > init_net.ipv6.sysctl.ip6_rt_max_size);
}
/* Clean host part of a prefix. Not necessary in radix tree,
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;
#endif
if (cfg->fc_ifindex) {
err = -ENODEV;
- dev = dev_get_by_index(cfg->fc_ifindex);
+ dev = dev_get_by_index(net, cfg->fc_ifindex);
if (!dev)
goto out;
idev = in6_dev_get(dev);
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;
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 != &loopback_dev) {
+ if (dev != net->loopback_dev) {
if (dev) {
dev_put(dev);
in6_dev_put(idev);
}
- dev = &loopback_dev;
+ dev = net->loopback_dev;
dev_hold(dev);
idev = in6_dev_get(dev);
if (!idev) {
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)
int remaining;
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
- int type = nla->nla_type;
+ int type = nla_type(nla);
if (type) {
if (type > RTAX_MAX) {
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:
{
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;
int ip6_del_rt(struct rt6_info *rt)
{
- return __ip6_del_rt(rt, NULL);
+ struct nl_info info = {
+ .nl_net = rt->rt6i_dev->nd_net,
+ };
+ return __ip6_del_rt(rt, &info);
}
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;
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)
{
}
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);
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,
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,
{
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");
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;
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;
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, 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;
}
* 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, 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);
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;
}
#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;
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)
{
struct fib6_config cfg = {
.fc_table = RT6_TABLE_INFO,
- .fc_metric = 1024,
+ .fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = ifindex,
.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);
ip6_route_add(&cfg);
- return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex);
+ return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
}
#endif
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;
return rt;
}
+EXPORT_SYMBOL(rt6_get_dflt_router);
+
struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref)
{
struct fib6_config cfg = {
.fc_table = RT6_TABLE_DFLT,
- .fc_metric = 1024,
+ .fc_metric = IP6_RT_PRIO_USER,
.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);
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;
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));
cfg->fc_src_len = rtmsg->rtmsg_src_len;
cfg->fc_flags = rtmsg->rtmsg_flags;
+ 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;
if (err)
return -EFAULT;
- rtmsg_to_fib6_config(&rtmsg, &cfg);
+ rtmsg_to_fib6_config(net, &rtmsg, &cfg);
rtnl_lock();
switch (cmd) {
rtnl_unlock();
return err;
- };
+ }
return -EINVAL;
}
* Drop the packet on the floor
*/
-static inline int ip6_pkt_drop(struct sk_buff *skb, int code)
+static int ip6_pkt_drop(struct sk_buff *skb, int code, int ipstats_mib_noroutes)
{
- int type = ipv6_addr_type(&skb->nh.ipv6h->daddr);
- if (type == IPV6_ADDR_ANY || type == IPV6_ADDR_RESERVED)
- IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_INADDRERRORS);
-
- IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_OUTNOROUTES);
+ int type;
+ switch (ipstats_mib_noroutes) {
+ case IPSTATS_MIB_INNOROUTES:
+ type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
+ if (type == IPV6_ADDR_ANY || type == IPV6_ADDR_RESERVED) {
+ IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_INADDRERRORS);
+ break;
+ }
+ /* FALLTHROUGH */
+ case IPSTATS_MIB_OUTNOROUTES:
+ IP6_INC_STATS(ip6_dst_idev(skb->dst), ipstats_mib_noroutes);
+ break;
+ }
icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0, skb->dev);
kfree_skb(skb);
return 0;
static int ip6_pkt_discard(struct sk_buff *skb)
{
- return ip6_pkt_drop(skb, ICMPV6_NOROUTE);
+ return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
}
static int ip6_pkt_discard_out(struct sk_buff *skb)
{
skb->dev = skb->dst->dev;
- return ip6_pkt_discard(skb);
+ return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
static int ip6_pkt_prohibit(struct sk_buff *skb)
{
- return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED);
+ return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
}
static int ip6_pkt_prohibit_out(struct sk_buff *skb)
{
skb->dev = skb->dst->dev;
- return ip6_pkt_prohibit(skb);
-}
-
-static int ip6_pkt_blk_hole(struct sk_buff *skb)
-{
- kfree_skb(skb);
- return 0;
+ return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
}
#endif
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(&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 = &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;
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
{
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.
*/
if (rt->rt6i_dev == arg->dev &&
!dst_metric_locked(&rt->u.dst, RTAX_MTU) &&
- (dst_mtu(&rt->u.dst) > arg->mtu ||
+ (dst_mtu(&rt->u.dst) >= arg->mtu ||
(dst_mtu(&rt->u.dst) < arg->mtu &&
- dst_mtu(&rt->u.dst) == idev->cnf.mtu6)))
+ 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;
}
.mtu = mtu,
};
- fib6_clean_all(rt6_mtu_change_route, 0, &arg);
+ fib6_clean_all(dev->nd_net, rt6_mtu_change_route, 0, &arg);
}
-static struct nla_policy rtm_ipv6_policy[RTA_MAX+1] __read_mostly = {
+static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
cfg->fc_nlinfo.nlh = nlh;
+ cfg->fc_nlinfo.nl_net = skb->sk->sk_net;
if (tb[RTA_GATEWAY]) {
nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16);
return err;
}
-int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
struct fib6_config cfg;
int err;
return ip6_route_del(&cfg);
}
-int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
struct fib6_config cfg;
int err;
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);
}
prefix, NLM_F_MULTI);
}
-int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
+ struct net *net = in_skb->sk->sk_net;
struct nlattr *tb[RTA_MAX+1];
struct rt6_info *rt;
struct sk_buff *skb;
if (iif) {
struct net_device *dev;
- dev = __dev_get_by_index(iif);
+ dev = __dev_get_by_index(net, iif);
if (!dev) {
err = -ENODEV;
goto errout;
/* Reserve room for dummy headers, this skb can pass
through good chunk of routing engine.
*/
- skb->mac.raw = skb->data;
+ skb_reset_mac_header(skb);
skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
rt = (struct rt6_info*) ip6_route_output(NULL, &fl);
goto errout;
}
- err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid);
+ err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
errout:
return err;
}
void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
{
struct sk_buff *skb;
- u32 pid = 0, seq = 0;
- struct nlmsghdr *nlh = NULL;
- int err = -ENOBUFS;
+ struct net *net = info->nl_net;
+ u32 seq;
+ int err;
- if (info) {
- pid = info->pid;
- nlh = info->nlh;
- if (nlh)
- seq = nlh->nlmsg_seq;
- }
+ err = -ENOBUFS;
+ seq = info->nlh != NULL ? info->nlh->nlmsg_seq : 0;
skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
if (skb == NULL)
goto errout;
- err = rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0);
+ err = rt6_fill_node(skb, rt, NULL, NULL, 0,
+ event, info->pid, seq, 0, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, pid, RTNLGRP_IPV6_ROUTE, 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(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;
}
/*
static int rt6_info_route(struct rt6_info *rt, void *p_arg)
{
- struct rt6_proc_arg *arg = (struct rt6_proc_arg *) p_arg;
+ struct seq_file *m = p_arg;
- if (arg->skip < arg->offset / RT6_INFO_LEN) {
- arg->skip++;
- return 0;
- }
-
- if (arg->len >= arg->length)
- return 0;
-
- arg->len += sprintf(arg->buffer + arg->len,
- NIP6_SEQFMT " %02x ",
- NIP6(rt->rt6i_dst.addr),
- rt->rt6i_dst.plen);
+ seq_printf(m, NIP6_SEQFMT " %02x ", NIP6(rt->rt6i_dst.addr),
+ rt->rt6i_dst.plen);
#ifdef CONFIG_IPV6_SUBTREES
- arg->len += sprintf(arg->buffer + arg->len,
- NIP6_SEQFMT " %02x ",
- NIP6(rt->rt6i_src.addr),
- rt->rt6i_src.plen);
+ seq_printf(m, NIP6_SEQFMT " %02x ", NIP6(rt->rt6i_src.addr),
+ rt->rt6i_src.plen);
#else
- arg->len += sprintf(arg->buffer + arg->len,
- "00000000000000000000000000000000 00 ");
+ seq_puts(m, "00000000000000000000000000000000 00 ");
#endif
if (rt->rt6i_nexthop) {
- arg->len += sprintf(arg->buffer + arg->len,
- NIP6_SEQFMT,
- NIP6(*((struct in6_addr *)rt->rt6i_nexthop->primary_key)));
+ seq_printf(m, NIP6_SEQFMT,
+ NIP6(*((struct in6_addr *)rt->rt6i_nexthop->primary_key)));
} else {
- arg->len += sprintf(arg->buffer + arg->len,
- "00000000000000000000000000000000");
- }
- arg->len += sprintf(arg->buffer + arg->len,
- " %08x %08x %08x %08x %8s\n",
- rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt),
- rt->u.dst.__use, rt->rt6i_flags,
- rt->rt6i_dev ? rt->rt6i_dev->name : "");
+ seq_puts(m, "00000000000000000000000000000000");
+ }
+ seq_printf(m, " %08x %08x %08x %08x %8s\n",
+ rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt),
+ rt->u.dst.__use, rt->rt6i_flags,
+ rt->rt6i_dev ? rt->rt6i_dev->name : "");
return 0;
}
-static int rt6_proc_info(char *buffer, char **start, off_t offset, int length)
+static int ipv6_route_show(struct seq_file *m, void *v)
{
- struct rt6_proc_arg arg = {
- .buffer = buffer,
- .offset = offset,
- .length = length,
- };
-
- fib6_clean_all(rt6_info_route, 0, &arg);
-
- *start = buffer;
- if (offset)
- *start += offset % RT6_INFO_LEN;
-
- arg.len -= offset % RT6_INFO_LEN;
+ struct net *net = (struct net *)m->private;
+ fib6_clean_all(net, rt6_info_route, 0, m);
+ return 0;
+}
- if (arg.len > length)
- arg.len = length;
- if (arg.len < 0)
- arg.len = 0;
+static int ipv6_route_open(struct inode *inode, struct file *file)
+{
+ struct net *net = get_proc_net(inode);
+ if (!net)
+ return -ENXIO;
+ return single_open(file, ipv6_route_show, net);
+}
- return arg.len;
+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 = {
+ .owner = THIS_MODULE,
+ .open = ipv6_route_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .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 struct file_operations rt6_stats_seq_fops = {
+static const struct file_operations rt6_stats_seq_fops = {
.owner = THIS_MODULE,
.open = rt6_stats_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = rt6_stats_seq_release,
};
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SYSCTL
-static int flush_delay;
-
static
int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
+ 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(flush_delay <= 0 ? ~0UL : (unsigned long)flush_delay);
+ fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
return 0;
} else
return -EINVAL;
}
-ctl_table ipv6_route_table[] = {
+ctl_table ipv6_route_table_template[] = {
{
- .ctl_name = NET_IPV6_ROUTE_FLUSH,
.procname = "flush",
- .data = &flush_delay,
+ .data = &init_net.ipv6.sysctl.flush_delay,
.maxlen = sizeof(int),
.mode = 0200,
.proc_handler = &ipv6_sysctl_rtcache_flush
{
.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,
{
.ctl_name = NET_IPV6_ROUTE_MAX_SIZE,
.procname = "max_size",
- .data = &ip6_rt_max_size,
+ .data = &init_net.ipv6.sysctl.ip6_rt_max_size,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec,
{
.ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL,
.procname = "gc_min_interval",
- .data = &ip6_rt_gc_min_interval,
+ .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_jiffies,
{
.ctl_name = NET_IPV6_ROUTE_GC_TIMEOUT,
.procname = "gc_timeout",
- .data = &ip6_rt_gc_timeout,
+ .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_jiffies,
{
.ctl_name = NET_IPV6_ROUTE_GC_INTERVAL,
.procname = "gc_interval",
- .data = &ip6_rt_gc_interval,
+ .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_jiffies,
{
.ctl_name = NET_IPV6_ROUTE_GC_ELASTICITY,
.procname = "gc_elasticity",
- .data = &ip6_rt_gc_elasticity,
+ .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_jiffies,
{
.ctl_name = NET_IPV6_ROUTE_MTU_EXPIRES,
.procname = "mtu_expires",
- .data = &ip6_rt_mtu_expires,
+ .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_jiffies,
{
.ctl_name = NET_IPV6_ROUTE_MIN_ADVMSS,
.procname = "min_adv_mss",
- .data = &ip6_rt_min_advmss,
+ .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_jiffies,
{
.ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS,
.procname = "gc_min_interval_ms",
- .data = &ip6_rt_gc_min_interval,
+ .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_ms_jiffies,
{ .ctl_name = 0 }
};
+struct ctl_table *ipv6_route_sysctl_init(struct net *net)
+{
+ struct ctl_table *table;
+
+ 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
-void __init ip6_route_init(void)
+static int ip6_route_net_init(struct net *net)
{
- struct proc_dir_entry *p;
+ int ret = 0;
- ip6_dst_ops.kmem_cachep =
- kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
- fib6_init();
-#ifdef CONFIG_PROC_FS
- p = proc_net_create("ipv6_route", 0, rt6_proc_info);
- if (p)
- p->owner = THIS_MODULE;
-
- proc_net_fops_create("rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
+ 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_XFRM
- xfrm6_init();
+
+#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
+ 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
- fib6_rules_init();
+ 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;
+
+ 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_template.kmem_cachep)
+ goto out;;
+
+ ret = register_pernet_subsys(&ip6_route_net_ops);
+ if (ret)
+ goto out_kmem_cache;
+
+ /* 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_register_subsys;
+
+ ret = xfrm6_init();
+ if (ret)
+ goto out_fib6_init;
+
+ ret = fib6_rules_init();
+ if (ret)
+ goto xfrm6_init;
+
+ ret = -ENOBUFS;
+ if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL) ||
+ __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL) ||
+ __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL))
+ goto fib6_rules_init;
+
+ ret = register_netdevice_notifier(&ip6_route_dev_notifier);
+ if (ret)
+ goto fib6_rules_init;
+
+out:
+ return ret;
+
+fib6_rules_init:
+ fib6_rules_cleanup();
+xfrm6_init:
+ xfrm6_fini();
+out_fib6_init:
+ fib6_gc_cleanup();
+out_register_subsys:
+ unregister_pernet_subsys(&ip6_route_net_ops);
+out_kmem_cache:
+ kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
+ goto out;
}
void ip6_route_cleanup(void)
{
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ unregister_netdevice_notifier(&ip6_route_dev_notifier);
fib6_rules_cleanup();
-#endif
-#ifdef CONFIG_PROC_FS
- proc_net_remove("ipv6_route");
- proc_net_remove("rt6_stats");
-#endif
-#ifdef CONFIG_XFRM
xfrm6_fini();
-#endif
- 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);
}