summaryrefslogtreecommitdiffstats
path: root/net/ipv4/route.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r--net/ipv4/route.c103
1 files changed, 90 insertions, 13 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a8c651216fa..6e2851464f8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -117,15 +117,11 @@
#define RT_GC_TIMEOUT (300*HZ)
static int ip_rt_max_size;
-static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
-static int ip_rt_gc_interval __read_mostly = 60 * HZ;
-static int ip_rt_gc_min_interval __read_mostly = HZ / 2;
static int ip_rt_redirect_number __read_mostly = 9;
static int ip_rt_redirect_load __read_mostly = HZ / 50;
static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost __read_mostly = HZ;
static int ip_rt_error_burst __read_mostly = 5 * HZ;
-static int ip_rt_gc_elasticity __read_mostly = 8;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
@@ -384,8 +380,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
- pde = proc_net_fops_create(net, "rt_cache", S_IRUGO,
- &rt_cache_seq_fops);
+ pde = proc_create("rt_cache", S_IRUGO, net->proc_net,
+ &rt_cache_seq_fops);
if (!pde)
goto err1;
@@ -912,6 +908,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
struct dst_entry *dst = &rt->dst;
struct fib_result res;
+ if (dst_metric_locked(dst, RTAX_MTU))
+ return;
+
if (dst->dev->mtu < mtu)
return;
@@ -962,7 +961,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
}
EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
-void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
+static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
{
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
@@ -975,6 +974,53 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
ip_rt_put(rt);
}
}
+
+void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
+{
+ const struct iphdr *iph = (const struct iphdr *) skb->data;
+ struct flowi4 fl4;
+ struct rtable *rt;
+ struct dst_entry *dst;
+ bool new = false;
+
+ bh_lock_sock(sk);
+ rt = (struct rtable *) __sk_dst_get(sk);
+
+ if (sock_owned_by_user(sk) || !rt) {
+ __ipv4_sk_update_pmtu(skb, sk, mtu);
+ goto out;
+ }
+
+ __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+
+ if (!__sk_dst_check(sk, 0)) {
+ rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
+ if (IS_ERR(rt))
+ goto out;
+
+ new = true;
+ }
+
+ __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
+
+ dst = dst_check(&rt->dst, 0);
+ if (!dst) {
+ if (new)
+ dst_release(&rt->dst);
+
+ rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
+ if (IS_ERR(rt))
+ goto out;
+
+ new = true;
+ }
+
+ if (new)
+ __sk_dst_set(sk, &rt->dst);
+
+out:
+ bh_unlock_sock(sk);
+}
EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
void ipv4_redirect(struct sk_buff *skb, struct net *net,
@@ -1120,7 +1166,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
if (!mtu || time_after_eq(jiffies, rt->dst.expires))
mtu = dst_metric_raw(dst, RTAX_MTU);
- if (mtu && rt_is_output_route(rt))
+ if (mtu)
return mtu;
mtu = dst->dev->mtu;
@@ -1785,6 +1831,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
+ do_cache = true;
if (type == RTN_BROADCAST) {
flags |= RTCF_BROADCAST | RTCF_LOCAL;
fi = NULL;
@@ -1793,6 +1840,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr,
fl4->flowi4_proto))
flags &= ~RTCF_LOCAL;
+ else
+ do_cache = false;
/* If multicast route do not exist use
* default one, but do not gateway in this case.
* Yes, it is hack.
@@ -1802,8 +1851,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
}
fnhe = NULL;
- do_cache = fi != NULL;
- if (fi) {
+ do_cache &= fi != NULL;
+ if (do_cache) {
struct rtable __rcu **prth;
struct fib_nh *nh = &FIB_RES_NH(*res);
@@ -2229,8 +2278,27 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
error = rt->dst.error;
if (rt_is_input_route(rt)) {
- if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
- goto nla_put_failure;
+#ifdef CONFIG_IP_MROUTE
+ if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
+ IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
+ int err = ipmr_get_route(net, skb,
+ fl4->saddr, fl4->daddr,
+ r, nowait);
+ if (err <= 0) {
+ if (!nowait) {
+ if (err == 0)
+ return 0;
+ goto nla_put_failure;
+ } else {
+ if (err == -EMSGSIZE)
+ goto nla_put_failure;
+ error = err;
+ }
+ }
+ } else
+#endif
+ if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
+ goto nla_put_failure;
}
if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0)
@@ -2351,6 +2419,11 @@ void ip_rt_multicast_event(struct in_device *in_dev)
}
#ifdef CONFIG_SYSCTL
+static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
+static int ip_rt_gc_interval __read_mostly = 60 * HZ;
+static int ip_rt_gc_min_interval __read_mostly = HZ / 2;
+static int ip_rt_gc_elasticity __read_mostly = 8;
+
static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
@@ -2493,6 +2566,10 @@ static __net_init int sysctl_route_net_init(struct net *net)
tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
if (tbl == NULL)
goto err_dup;
+
+ /* Don't export sysctls to unprivileged users */
+ if (net->user_ns != &init_user_ns)
+ tbl[0].procname = NULL;
}
tbl[0].extra1 = net;
@@ -2597,7 +2674,7 @@ int __init ip_rt_init(void)
pr_err("Unable to create route proc files\n");
#ifdef CONFIG_XFRM
xfrm_init();
- xfrm4_init(ip_rt_max_size);
+ xfrm4_init();
#endif
rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-10-28 23:18:04 +0000