[PATCH 0/2] ipv4: Namespaceify two sysctls related with mtu

[PATCH 0/2] ipv4: Namespaceify two sysctls related with mtu

[cgel.zte]

From: xu xin <xu.xin16@zte.com.cn>

The following patch series enables the min_pmtu and mtu_expires to
be visible and configurable per net namespace. Different namespace
application might have different requirements on the setting of
min_pmtu and mtu_expires.

If these two patches are applied, inside a net namespace we create,
we can see two more sysctls under /proc/sys/net/ipv4/route:
1. min_pmtu
2. mtu_expires

where min_pmtu and mtu_expires are configurable.

xu xin (2):
namespaceify-min-pmtu
Namespaceify pmtu_expires

xu xin (2):
  Namespaceify min_pmtu sysctl
  Namespaceify mtu_expires sysctl

 include/net/netns/ipv4.h |  3 ++
 net/ipv4/route.c         | 74 ++++++++++++++++++++++++++--------------
 2 files changed, 51 insertions(+), 26 deletions(-)

-- 
2.25.1

[PATCH 1/2] Namespaceify min_pmtu sysctl

[cgel.zte]

From: xu xin <xu.xin16@zte.com.cn>

This patch enables the sysctl min_pmtu to be configured per net
namespace.

Signed-off-by: xu xin <xu.xin16@zte.com.cn>
---
 include/net/netns/ipv4.h |  2 ++
 net/ipv4/route.c         | 53 ++++++++++++++++++++++++++++------------
 2 files changed, 39 insertions(+), 16 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 6c5b2efc4f17..1ecbf82b07f1 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -85,6 +85,8 @@ 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 843a7a3699fe..f29637e85c05 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -110,6 +110,8 @@
 
 #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;
@@ -117,7 +119,6 @@ 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;
@@ -1018,9 +1019,9 @@ 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 &&
@@ -3541,14 +3542,6 @@ 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,
@@ -3561,13 +3554,21 @@ 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,
+	},
 	{ },
 };
 
@@ -3575,9 +3576,11 @@ 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;
 
@@ -3586,6 +3589,12 @@ 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;
 
@@ -3595,7 +3604,7 @@ 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;
@@ -3607,7 +3616,7 @@ 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);
 }
 
@@ -3617,6 +3626,17 @@ 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);
@@ -3722,6 +3742,7 @@ 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;
-- 
2.25.1

[PATCH 2/2] Namespaceify mtu_expires sysctl

[cgel.zte]

From: xu xin <xu.xin16@zte.com.cn>

This patch enables the sysctl mtu_expires to be configured per net
namespace.

Signed-off-by: xu xin <xu.xin16@zte.com.cn>

---
 include/net/netns/ipv4.h |  1 +
 net/ipv4/route.c         | 21 +++++++++++----------
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 1ecbf82b07f1..78557643526e 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -86,6 +86,7 @@ struct netns_ipv4 {
 	int sysctl_icmp_ratemask;
 
 	u32 ip_rt_min_pmtu;
+	int ip_rt_mtu_expires;
 
 	struct local_ports ip_local_ports;
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f29637e85c05..ff6f91cdb6c4 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -111,6 +111,7 @@
 #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;
@@ -118,7 +119,6 @@ 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 int ip_rt_min_advmss __read_mostly	= 256;
 
 static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
@@ -1025,7 +1025,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 	}
 
 	if (rt->rt_pmtu == mtu && !lock &&
-	    time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
+	    time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2))
 		return;
 
 	rcu_read_lock();
@@ -1035,7 +1035,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		fib_select_path(net, &res, fl4, NULL);
 		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);
 	}
 	rcu_read_unlock();
 }
@@ -3535,13 +3535,6 @@ static struct ctl_table ipv4_route_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "mtu_expires",
-		.data		= &ip_rt_mtu_expires,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
 	{
 		.procname	= "min_adv_mss",
 		.data		= &ip_rt_min_advmss,
@@ -3569,6 +3562,13 @@ static struct ctl_table ipv4_route_netns_table[] = {
 		.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,
+	},
 	{ },
 };
 
@@ -3630,6 +3630,7 @@ 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;
 }
 
-- 
2.25.1

Re: [PATCH 0/2] ipv4: Namespaceify two sysctls related with mtu

[patchwork-bot+netdevbpf]

Hello:

This series was applied to netdev/net-next.git (master)
by David S. Miller <davem@davemloft.net>:

On Tue,  4 Jan 2022 10:57:39 +0000 you wrote:
> From: xu xin <xu.xin16@zte.com.cn>
> 
> The following patch series enables the min_pmtu and mtu_expires to
> be visible and configurable per net namespace. Different namespace
> application might have different requirements on the setting of
> min_pmtu and mtu_expires.
> 
> [...]

Here is the summary with links:
  - [1/2] Namespaceify min_pmtu sysctl
    https://git.kernel.org/netdev/net-next/c/1de6b15a434c
  - [2/2] Namespaceify mtu_expires sysctl
    https://git.kernel.org/netdev/net-next/c/1135fad20480

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html