summaryrefslogtreecommitdiff
path: root/net/ipv4/route.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r--net/ipv4/route.c102
1 files changed, 72 insertions, 30 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 352280188578..a4884d434038 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -118,14 +118,15 @@
#define RT_GC_TIMEOUT (300*HZ)
+#define DEFAULT_MIN_PMTU (512 + 20 + 20)
+#define DEFAULT_MTU_EXPIRES (10 * 60 * HZ)
+
static int ip_rt_max_size;
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_mtu_expires __read_mostly = 10 * 60 * HZ;
-static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
@@ -400,7 +401,13 @@ static inline int ip_rt_proc_init(void)
static inline bool rt_is_expired(const struct rtable *rth)
{
- return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev));
+ bool res;
+
+ rcu_read_lock();
+ res = rth->rt_genid != rt_genid_ipv4(dev_net_rcu(rth->dst.dev));
+ rcu_read_unlock();
+
+ return res;
}
void rt_cache_flush(struct net *net)
@@ -1016,9 +1023,9 @@ out: kfree_skb(skb);
static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
struct dst_entry *dst = &rt->dst;
- struct net *net = dev_net(dst->dev);
struct fib_result res;
bool lock = false;
+ struct net *net;
u32 old_mtu;
if (ip_mtu_locked(dst))
@@ -1028,24 +1035,38 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
if (old_mtu < mtu)
return;
- if (mtu < ip_rt_min_pmtu) {
+ rcu_read_lock();
+ net = dev_net_rcu(dst->dev);
+ if (mtu < net->ipv4.ip_rt_min_pmtu) {
lock = true;
- mtu = min(old_mtu, ip_rt_min_pmtu);
+ mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu);
}
if (rt->rt_pmtu == mtu && !lock &&
- time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
- return;
+ time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2))
+ goto out;
- rcu_read_lock();
if (fib_lookup(net, fl4, &res, 0) == 0) {
struct fib_nh_common *nhc;
fib_select_path(net, &res, fl4, NULL);
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+ if (fib_info_num_path(res.fi) > 1) {
+ int nhsel;
+
+ for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) {
+ nhc = fib_info_nhc(res.fi, nhsel);
+ update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
+ jiffies + net->ipv4.ip_rt_mtu_expires);
+ }
+ goto out;
+ }
+#endif /* CONFIG_IP_ROUTE_MULTIPATH */
nhc = FIB_RES_NHC(res);
update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
- jiffies + ip_rt_mtu_expires);
+ jiffies + net->ipv4.ip_rt_mtu_expires);
}
+out:
rcu_read_unlock();
}
@@ -3566,21 +3587,6 @@ static struct ctl_table ipv4_route_table[] = {
.proc_handler = proc_dointvec,
},
{
- .procname = "mtu_expires",
- .data = &ip_rt_mtu_expires,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
- {
- .procname = "min_pmtu",
- .data = &ip_rt_min_pmtu,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &ip_min_valid_pmtu,
- },
- {
.procname = "min_adv_mss",
.data = &ip_rt_min_advmss,
.maxlen = sizeof(int),
@@ -3592,13 +3598,28 @@ static struct ctl_table ipv4_route_table[] = {
static const char ipv4_route_flush_procname[] = "flush";
-static struct ctl_table ipv4_route_flush_table[] = {
+static struct ctl_table ipv4_route_netns_table[] = {
{
.procname = ipv4_route_flush_procname,
.maxlen = sizeof(int),
.mode = 0200,
.proc_handler = ipv4_sysctl_rtcache_flush,
},
+ {
+ .procname = "min_pmtu",
+ .data = &init_net.ipv4.ip_rt_min_pmtu,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &ip_min_valid_pmtu,
+ },
+ {
+ .procname = "mtu_expires",
+ .data = &init_net.ipv4.ip_rt_mtu_expires,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
{ },
};
@@ -3606,9 +3627,11 @@ static __net_init int sysctl_route_net_init(struct net *net)
{
struct ctl_table *tbl;
- tbl = ipv4_route_flush_table;
+ tbl = ipv4_route_netns_table;
if (!net_eq(net, &init_net)) {
- tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
+ int i;
+
+ tbl = kmemdup(tbl, sizeof(ipv4_route_netns_table), GFP_KERNEL);
if (!tbl)
goto err_dup;
@@ -3617,6 +3640,12 @@ static __net_init int sysctl_route_net_init(struct net *net)
if (tbl[0].procname != ipv4_route_flush_procname)
tbl[0].procname = NULL;
}
+
+ /* Update the variables to point into the current struct net
+ * except for the first element flush
+ */
+ for (i = 1; i < ARRAY_SIZE(ipv4_route_netns_table) - 1; i++)
+ tbl[i].data += (void *)net - (void *)&init_net;
}
tbl[0].extra1 = net;
@@ -3626,7 +3655,7 @@ static __net_init int sysctl_route_net_init(struct net *net)
return 0;
err_reg:
- if (tbl != ipv4_route_flush_table)
+ if (tbl != ipv4_route_netns_table)
kfree(tbl);
err_dup:
return -ENOMEM;
@@ -3638,7 +3667,7 @@ static __net_exit void sysctl_route_net_exit(struct net *net)
tbl = net->ipv4.route_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.route_hdr);
- BUG_ON(tbl == ipv4_route_flush_table);
+ BUG_ON(tbl == ipv4_route_netns_table);
kfree(tbl);
}
@@ -3648,6 +3677,18 @@ static __net_initdata struct pernet_operations sysctl_route_ops = {
};
#endif
+static __net_init int netns_ip_rt_init(struct net *net)
+{
+ /* Set default value for namespaceified sysctls */
+ net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU;
+ net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES;
+ return 0;
+}
+
+static struct pernet_operations __net_initdata ip_rt_ops = {
+ .init = netns_ip_rt_init,
+};
+
static __net_init int rt_genid_init(struct net *net)
{
atomic_set(&net->ipv4.rt_genid, 0);
@@ -3753,6 +3794,7 @@ int __init ip_rt_init(void)
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&sysctl_route_ops);
#endif
+ register_pernet_subsys(&ip_rt_ops);
register_pernet_subsys(&rt_genid_ops);
register_pernet_subsys(&ipv4_inetpeer_ops);
return 0;