This is a note to let you know that I've just added the patch titled
Namespaceify min_pmtu sysctl
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
namespaceify-min_pmtu-sysctl.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit aad943d05c2b69b1cef568185aa1787eeec0d8d2
Author: xu xin <xu.xin16@xxxxxxxxxx>
Date: Tue Jan 4 10:59:34 2022 +0000
Namespaceify min_pmtu sysctl
[ Upstream commit 1de6b15a434c0068253fea5d719f71143e7e3a79 ]
This patch enables the sysctl min_pmtu to be configured per net
namespace.
Signed-off-by: xu xin <xu.xin16@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Stable-dep-of: 139512191bd0 ("ipv4: use RCU protection in __ip_rt_update_pmtu()")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index d60a10cfc3823..16515c04a46a7 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -84,6 +84,8 @@ struct netns_ipv4 {
int sysctl_icmp_ratelimit;
int sysctl_icmp_ratemask;
+ u32 ip_rt_min_pmtu;
+
struct local_ports ip_local_ports;
u8 sysctl_tcp_ecn;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3ad78bbd6261b..9a837cd2b925a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -118,6 +118,8 @@
#define RT_GC_TIMEOUT (300*HZ)
+#define DEFAULT_MIN_PMTU (512 + 20 + 20)
+
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;
@@ -125,7 +127,6 @@ 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;
@@ -1034,9 +1035,9 @@ 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) {
+ 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 &&
@@ -3578,14 +3579,6 @@ static struct ctl_table ipv4_route_table[] = {
.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,
@@ -3598,13 +3591,21 @@ 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,
+ },
{ },
};
@@ -3612,9 +3613,11 @@ 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;
@@ -3623,6 +3626,12 @@ 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;
@@ -3632,7 +3641,7 @@ 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;
@@ -3644,7 +3653,7 @@ 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);
}
@@ -3654,6 +3663,17 @@ 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;
+ 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);
@@ -3759,6 +3779,7 @@ 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;
