per-netns ipv4 sysctl_tcp_mem

This patch allows each namespace to independently set up
its levels for tcp memory pressure thresholds. This patch
alone does not buy much: we need to make this values
per group of process somehow. This is achieved in the
patches that follows in this patchset.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
CC: David S. Miller <davem@davemloft.net>
CC: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 56 insertions, 21 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 15dc4c4..f7b5670 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1672,6 +1672,8 @@ static int __init inet_init(void)
 	ip_static_sysctl_init();
 #endif
 
+	tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
+
 	/*
 	 *	Add all the base protocols.
 	 */
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 69fd720..bbd67ab 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/nsproxy.h>
+#include <linux/swap.h>
 #include <net/snmp.h>
 #include <net/icmp.h>
 #include <net/ip.h>
@@ -174,6 +175,36 @@ static int proc_allowed_congestion_control(ctl_table *ctl,
 	return ret;
 }
 
+static int ipv4_tcp_mem(ctl_table *ctl, int write,
+			   void __user *buffer, size_t *lenp,
+			   loff_t *ppos)
+{
+	int ret;
+	unsigned long vec[3];
+	struct net *net = current->nsproxy->net_ns;
+
+	ctl_table tmp = {
+		.data = &vec,
+		.maxlen = sizeof(vec),
+		.mode = ctl->mode,
+	};
+
+	if (!write) {
+		ctl->data = &net->ipv4.sysctl_tcp_mem;
+		return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos);
+	}
+
+	ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
+
+	net->ipv4.sysctl_tcp_mem[0] = vec[0];
+	net->ipv4.sysctl_tcp_mem[1] = vec[1];
+	net->ipv4.sysctl_tcp_mem[2] = vec[2];
+
+	return 0;
+}
+
 static struct ctl_table ipv4_table[] = {
 	{
 		.procname	= "tcp_timestamps",
@@ -433,13 +464,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "tcp_mem",
-		.data		= &sysctl_tcp_mem,
-		.maxlen		= sizeof(sysctl_tcp_mem),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax
-	},
-	{
 		.procname	= "tcp_wmem",
 		.data		= &sysctl_tcp_wmem,
 		.maxlen		= sizeof(sysctl_tcp_wmem),
@@ -721,6 +745,12 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_ping_group_range,
 	},
+	{
+		.procname	= "tcp_mem",
+		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_mem),
+		.mode		= 0644,
+		.proc_handler	= ipv4_tcp_mem,
+	},
 	{ }
 };
 
@@ -734,6 +764,7 @@ EXPORT_SYMBOL_GPL(net_ipv4_ctl_path);
 static __net_init int ipv4_sysctl_init_net(struct net *net)
 {
 	struct ctl_table *table;
+	unsigned long limit;
 
 	table = ipv4_net_table;
 	if (!net_eq(net, &init_net)) {
@@ -769,6 +800,12 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 
 	net->ipv4.sysctl_rt_cache_rebuild_count = 4;
 
+	limit = nr_free_buffer_pages() / 8;
+	limit = max(limit, 128UL);
+	net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
+	net->ipv4.sysctl_tcp_mem[1] = limit;
+	net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2;
+
 	net->ipv4.ipv4_hdr = register_net_sysctl_table(net,
 			net_ipv4_ctl_path, table);
 	if (net->ipv4.ipv4_hdr == NULL)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 43dfccc..9bcdec3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,11 +282,9 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
-long sysctl_tcp_mem[3] __read_mostly;
 int sysctl_tcp_wmem[3] __read_mostly;
 int sysctl_tcp_rmem[3] __read_mostly;
 
-EXPORT_SYMBOL(sysctl_tcp_mem);
 EXPORT_SYMBOL(sysctl_tcp_rmem);
 EXPORT_SYMBOL(sysctl_tcp_wmem);
 
@@ -3278,14 +3276,9 @@ void __init tcp_init(void)
 	sysctl_tcp_max_orphans = cnt / 2;
 	sysctl_max_syn_backlog = max(128, cnt / 256);
 
-	limit = nr_free_buffer_pages() / 8;
-	limit = max(limit, 128UL);
-	sysctl_tcp_mem[0] = limit / 4 * 3;
-	sysctl_tcp_mem[1] = limit;
-	sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
-
 	/* Set per-socket limits to no more than 1/128 the pressure threshold */
-	limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
+	limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1])
+		<< (PAGE_SHIFT - 7);
 	max_share = min(4UL*1024*1024, limit);
 
 	sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 42714cb..1eb4ad5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2623,7 +2623,6 @@ struct proto tcp_prot = {
 	.orphan_count		= &tcp_orphan_count,
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
-	.sysctl_mem		= sysctl_tcp_mem,
 	.sysctl_wmem		= sysctl_tcp_wmem,
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 4a68d2c..bfb0c2b 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -1,6 +1,8 @@
 #include <net/tcp.h>
 #include <net/tcp_memcontrol.h>
 #include <net/sock.h>
+#include <net/ip.h>
+#include <linux/nsproxy.h>
 #include <linux/memcontrol.h>
 #include <linux/module.h>
 
@@ -28,6 +30,7 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	struct tcp_memcontrol *tcp;
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct net *net = current->nsproxy->net_ns;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
@@ -35,9 +38,9 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 
 	tcp = tcp_from_cgproto(cg_proto);
 
-	tcp->tcp_prot_mem[0] = sysctl_tcp_mem[0];
-	tcp->tcp_prot_mem[1] = sysctl_tcp_mem[1];
-	tcp->tcp_prot_mem[2] = sysctl_tcp_mem[2];
+	tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0];
+	tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1];
+	tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2];
 	tcp->tcp_memory_pressure = 0;
 
 	parent_cg = tcp_prot.proto_cgroup(parent);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7694c82..273f48d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1116,6 +1116,8 @@ static int __init inet6_init(void)
 	if (err)
 		goto static_sysctl_fail;
 #endif
+	tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
+
 	/*
 	 *	ipngwg API draft makes clear that the correct semantics
 	 *	for TCP and UDP is to consider one TCP and UDP instance
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 95d3cfb..906c7ca 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2215,7 +2215,6 @@ struct proto tcpv6_prot = {
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
 	.orphan_count		= &tcp_orphan_count,
-	.sysctl_mem		= sysctl_tcp_mem,
 	.sysctl_wmem		= sysctl_tcp_wmem,
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,