#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/nsproxy.h>
+#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
static struct dst_ops ip6_dst_ops_template = {
.family = AF_INET6,
- .protocol = __constant_htons(ETH_P_IPV6),
+ .protocol = cpu_to_be16(ETH_P_IPV6),
.gc = ip6_dst_gc,
.gc_thresh = 1024,
.check = ip6_dst_check,
static struct dst_ops ip6_dst_blackhole_ops = {
.family = AF_INET6,
- .protocol = __constant_htons(ETH_P_IPV6),
+ .protocol = cpu_to_be16(ETH_P_IPV6),
.destroy = ip6_dst_destroy,
.check = ip6_dst_check,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
pref = rinfo->route_pref;
if (pref == ICMPV6_ROUTER_PREF_INVALID)
- pref = ICMPV6_ROUTER_PREF_MEDIUM;
+ return -EINVAL;
lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ);
rt = ip6_rt_copy(ort);
if (rt) {
+ struct neighbour *neigh;
+ int attempts = !in_softirq();
+
if (!(rt->rt6i_flags&RTF_GATEWAY)) {
if (rt->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))
}
#endif
- rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
+ retry:
+ neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
+ if (IS_ERR(neigh)) {
+ struct net *net = dev_net(rt->rt6i_dev);
+ int saved_rt_min_interval =
+ net->ipv6.sysctl.ip6_rt_gc_min_interval;
+ int saved_rt_elasticity =
+ net->ipv6.sysctl.ip6_rt_gc_elasticity;
+
+ if (attempts-- > 0) {
+ net->ipv6.sysctl.ip6_rt_gc_elasticity = 1;
+ net->ipv6.sysctl.ip6_rt_gc_min_interval = 0;
+
+ ip6_dst_gc(&net->ipv6.ip6_dst_ops);
+
+ net->ipv6.sysctl.ip6_rt_gc_elasticity =
+ saved_rt_elasticity;
+ net->ipv6.sysctl.ip6_rt_gc_min_interval =
+ saved_rt_min_interval;
+ goto retry;
+ }
+
+ if (net_ratelimit())
+ printk(KERN_WARNING
+ "Neighbour table overflow.\n");
+ dst_free(&rt->u.dst);
+ return NULL;
+ }
+ rt->rt6i_nexthop = neigh;
}
.proto = iph->nexthdr,
};
- if (rt6_need_strict(&iph->daddr))
+ if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG)
flags |= RT6_LOOKUP_F_IFACE;
- skb->dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input);
+ skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input));
}
static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
{
int flags = 0;
- if (rt6_need_strict(&fl->fl6_dst))
+ if (fl->oif || rt6_need_strict(&fl->fl6_dst))
flags |= RT6_LOOKUP_F_IFACE;
if (!ipv6_addr_any(&fl->fl6_src))
flags |= RT6_LOOKUP_F_HAS_SADDR;
- else if (sk) {
- unsigned int prefs = inet6_sk(sk)->srcprefs;
- if (prefs & IPV6_PREFER_SRC_TMP)
- flags |= RT6_LOOKUP_F_SRCPREF_TMP;
- if (prefs & IPV6_PREFER_SRC_PUBLIC)
- flags |= RT6_LOOKUP_F_SRCPREF_PUBLIC;
- if (prefs & IPV6_PREFER_SRC_COA)
- flags |= RT6_LOOKUP_F_SRCPREF_COA;
- }
+ else if (sk)
+ flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);
return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output);
}
rt = (struct rt6_info *) dst;
- if (rt && rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
+ if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
return dst;
return NULL;
struct rt6_info *rt = (struct rt6_info *) dst;
if (rt) {
- if (rt->rt6i_flags & RTF_CACHE)
- ip6_del_rt(rt);
- else
+ if (rt->rt6i_flags & RTF_CACHE) {
+ if (rt6_check_expired(rt)) {
+ ip6_del_rt(rt);
+ dst = NULL;
+ }
+ } else {
dst_release(dst);
+ dst = NULL;
+ }
}
- return NULL;
+ return dst;
}
static void ip6_link_failure(struct sk_buff *skb)
{
struct rt6_info *rt;
- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev);
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
- rt = (struct rt6_info *) skb->dst;
+ rt = (struct rt6_info *) skb_dst(skb);
if (rt) {
if (rt->rt6i_flags&RTF_CACHE) {
dst_set_expires(&rt->u.dst, 0);
if (unlikely(idev == NULL))
return NULL;
- rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
+ rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
if (unlikely(rt == NULL)) {
in6_dev_put(idev);
goto out;
dev_hold(dev);
if (neigh)
neigh_hold(neigh);
- else
+ else {
neigh = ndisc_get_neigh(dev, addr);
+ if (IS_ERR(neigh))
+ neigh = NULL;
+ }
rt->rt6i_dev = dev;
rt->rt6i_idev = idev;
static int ip6_dst_gc(struct dst_ops *ops)
{
unsigned long now = jiffies;
- struct net *net = ops->dst_net;
+ struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops);
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;
goto out;
}
- rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
+ rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
if (rt == NULL) {
err = -ENOMEM;
},
},
},
- .gateway = *gateway,
};
+ ipv6_addr_copy(&rdfl.gateway, gateway);
+
if (rt6_need_strict(dest))
flags |= RT6_LOOKUP_F_IFACE;
static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
{
struct net *net = dev_net(ort->rt6i_dev);
- struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
+ struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
if (rt) {
rt->u.dst.input = ort->u.dst.input;
* Drop the packet on the floor
*/
-static int ip6_pkt_drop(struct sk_buff *skb, int code, int ipstats_mib_noroutes)
+static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
{
int type;
- struct dst_entry *dst = skb->dst;
+ struct dst_entry *dst = skb_dst(skb);
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) {
+ if (type == IPV6_ADDR_ANY) {
IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
IPSTATS_MIB_INADDRERRORS);
break;
ipstats_mib_noroutes);
break;
}
- icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0, skb->dev);
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
kfree_skb(skb);
return 0;
}
static int ip6_pkt_discard_out(struct sk_buff *skb)
{
- skb->dev = skb->dst->dev;
+ skb->dev = skb_dst(skb)->dev;
return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
}
static int ip6_pkt_prohibit_out(struct sk_buff *skb)
{
- skb->dev = skb->dst->dev;
+ skb->dev = skb_dst(skb)->dev;
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
}
int anycast)
{
struct net *net = dev_net(idev->dev);
- struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
+ struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+ struct neighbour *neigh;
if (rt == NULL)
return ERR_PTR(-ENOMEM);
rt->rt6i_flags |= RTF_ANYCAST;
else
rt->rt6i_flags |= RTF_LOCAL;
- rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
- if (rt->rt6i_nexthop == NULL) {
+ neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
+ if (IS_ERR(neigh)) {
dst_free(&rt->u.dst);
- return ERR_PTR(-ENOMEM);
+
+ /* We are casting this because that is the return
+ * value type. But an errno encoded pointer is the
+ * same regardless of the underlying pointer type,
+ * and that's what we are returning. So this is OK.
+ */
+ return (struct rt6_info *) neigh;
}
+ rt->rt6i_nexthop = neigh;
ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
rt->rt6i_dst.plen = 128;
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
- int err = ip6mr_get_route(skb, rtm, nowait);
+ int err = ip6mr_get_route(net, skb, rtm, nowait);
if (err <= 0) {
if (!nowait) {
if (err == 0)
skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl);
- skb->dst = &rt->u.dst;
+ skb_dst_set(skb, &rt->u.dst);
err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif,
RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
kfree_skb(skb);
goto errout;
}
- err = rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE,
- info->nlh, gfp_any());
+ rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE,
+ info->nlh, gfp_any());
+ return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
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),
+ atomic_read(&net->ipv6.ip6_dst_ops.entries),
net->ipv6.rt6_stats->fib_discarded_routes);
return 0;
#ifdef CONFIG_SYSCTL
static
-int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp,
+int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
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);
+ proc_dointvec(ctl, write, buffer, lenp, ppos);
fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
return 0;
} else
.proc_handler = ipv6_sysctl_rtcache_flush
},
{
- .ctl_name = NET_IPV6_ROUTE_GC_THRESH,
.procname = "gc_thresh",
.data = &ip6_dst_ops_template.gc_thresh,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV6_ROUTE_MAX_SIZE,
.procname = "max_size",
.data = &init_net.ipv6.sysctl.ip6_rt_max_size,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL,
.procname = "gc_min_interval",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV6_ROUTE_GC_TIMEOUT,
.procname = "gc_timeout",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV6_ROUTE_GC_INTERVAL,
.procname = "gc_interval",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV6_ROUTE_GC_ELASTICITY,
.procname = "gc_elasticity",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV6_ROUTE_MTU_EXPIRES,
.procname = "mtu_expires",
.data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV6_ROUTE_MIN_ADVMSS,
.procname = "min_adv_mss",
.data = &init_net.ipv6.sysctl.ip6_rt_min_advmss,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS,
.procname = "gc_min_interval_ms",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
- .strategy = sysctl_ms_jiffies,
},
- { .ctl_name = 0 }
+ { }
};
-struct ctl_table *ipv6_route_sysctl_init(struct net *net)
+struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
{
struct ctl_table *table;
if (table) {
table[0].data = &net->ipv6.sysctl.flush_delay;
- table[1].data = &net->ipv6.ip6_dst_ops->gc_thresh;
+ 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[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;
+ table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
}
return table;
}
#endif
-static int ip6_route_net_init(struct net *net)
+static int __net_init ip6_route_net_init(struct net *net)
{
int 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 = hold_net(net);
+ memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template,
+ sizeof(net->ipv6.ip6_dst_ops));
net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
sizeof(*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;
+ 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,
goto out_ip6_null_entry;
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_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),
goto out_ip6_prohibit_entry;
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;
+ net->ipv6.ip6_blk_hole_entry->u.dst.ops = &net->ipv6.ip6_dst_ops;
#endif
net->ipv6.sysctl.flush_delay = 0;
kfree(net->ipv6.ip6_null_entry);
#endif
out_ip6_dst_ops:
- release_net(net->ipv6.ip6_dst_ops->dst_net);
- kfree(net->ipv6.ip6_dst_ops);
goto out;
}
-static void ip6_route_net_exit(struct net *net)
+static void __net_exit ip6_route_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
proc_net_remove(net, "ipv6_route");
kfree(net->ipv6.ip6_prohibit_entry);
kfree(net->ipv6.ip6_blk_hole_entry);
#endif
- release_net(net->ipv6.ip6_dst_ops->dst_net);
- kfree(net->ipv6.ip6_dst_ops);
}
static struct pernet_operations ip6_route_net_ops = {
kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (!ip6_dst_ops_template.kmem_cachep)
- goto out;;
+ goto out;
ret = register_pernet_subsys(&ip6_route_net_ops);
if (ret)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff