tcp memory pressure controls

This patch introduces memory pressure controls for the tcp
protocol. It uses the generic socket memory pressure code
introduced in earlier patches, and fills in the
necessary data in cg_proto struct.

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

5 files changed, 128 insertions, 4 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 6a871b8fdd20..5a6a90620656 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -136,6 +136,46 @@
 #include <net/tcp.h>
 #endif
 
+static DEFINE_RWLOCK(proto_list_lock);
+static LIST_HEAD(proto_list);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct proto *proto;
+	int ret = 0;
+
+	read_lock(&proto_list_lock);
+	list_for_each_entry(proto, &proto_list, node) {
+		if (proto->init_cgroup) {
+			ret = proto->init_cgroup(cgrp, ss);
+			if (ret)
+				goto out;
+		}
+	}
+
+	read_unlock(&proto_list_lock);
+	return ret;
+out:
+	list_for_each_entry_continue_reverse(proto, &proto_list, node)
+		if (proto->destroy_cgroup)
+			proto->destroy_cgroup(cgrp, ss);
+	read_unlock(&proto_list_lock);
+	return ret;
+}
+
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct proto *proto;
+
+	read_lock(&proto_list_lock);
+	list_for_each_entry_reverse(proto, &proto_list, node)
+		if (proto->destroy_cgroup)
+			proto->destroy_cgroup(cgrp, ss);
+	read_unlock(&proto_list_lock);
+}
+#endif
+
 /*
  * Each address family might have different locking rules, so we have
  * one slock key per address family:
@@ -2291,9 +2331,6 @@ void sk_common_release(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_common_release);
 
-static DEFINE_RWLOCK(proto_list_lock);
-static LIST_HEAD(proto_list);
-
 #ifdef CONFIG_PROC_FS
 #define PROTO_INUSE_NR	64	/* should be enough for the first time */
 struct prot_inuse {
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index e9d98e621112..ff75d3bbcd6a 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
 obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
 obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
+obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f48bf312cfe8..42714cb1fef3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -73,6 +73,7 @@
 #include <net/xfrm.h>
 #include <net/netdma.h>
 #include <net/secure_seq.h>
+#include <net/tcp_memcontrol.h>
 
 #include <linux/inet.h>
 #include <linux/ipv6.h>
@@ -1917,6 +1918,7 @@ static int tcp_v4_init_sock(struct sock *sk)
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
 	local_bh_disable();
+	sock_update_memcg(sk);
 	sk_sockets_allocated_inc(sk);
 	local_bh_enable();
 
@@ -1974,6 +1976,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	}
 
 	sk_sockets_allocated_dec(sk);
+	sock_release_memcg(sk);
 }
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
 
@@ -2634,10 +2637,14 @@ struct proto tcp_prot = {
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
 #endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	.init_cgroup		= tcp_init_cgroup,
+	.destroy_cgroup		= tcp_destroy_cgroup,
+	.proto_cgroup		= tcp_proto_cgroup,
+#endif
 };
 EXPORT_SYMBOL(tcp_prot);
 
-
 static int __net_init tcp_sk_init(struct net *net)
 {
 	return inet_ctl_sock_create(&net->ipv4.tcp_sock,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
new file mode 100644
index 000000000000..4a68d2c24556
--- /dev/null
+++ b/net/ipv4/tcp_memcontrol.c
@@ -0,0 +1,74 @@
+#include <net/tcp.h>
+#include <net/tcp_memcontrol.h>
+#include <net/sock.h>
+#include <linux/memcontrol.h>
+#include <linux/module.h>
+
+static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
+{
+	return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
+}
+
+static void memcg_tcp_enter_memory_pressure(struct sock *sk)
+{
+	if (!sk->sk_cgrp->memory_pressure)
+		*sk->sk_cgrp->memory_pressure = 1;
+}
+EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
+
+int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	/*
+	 * The root cgroup does not use res_counters, but rather,
+	 * rely on the data already collected by the network
+	 * subsystem
+	 */
+	struct res_counter *res_parent = NULL;
+	struct cg_proto *cg_proto, *parent_cg;
+	struct tcp_memcontrol *tcp;
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return 0;
+
+	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_memory_pressure = 0;
+
+	parent_cg = tcp_prot.proto_cgroup(parent);
+	if (parent_cg)
+		res_parent = parent_cg->memory_allocated;
+
+	res_counter_init(&tcp->tcp_memory_allocated, res_parent);
+	percpu_counter_init(&tcp->tcp_sockets_allocated, 0);
+
+	cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure;
+	cg_proto->memory_pressure = &tcp->tcp_memory_pressure;
+	cg_proto->sysctl_mem = tcp->tcp_prot_mem;
+	cg_proto->memory_allocated = &tcp->tcp_memory_allocated;
+	cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
+	cg_proto->memcg = memcg;
+
+	return 0;
+}
+EXPORT_SYMBOL(tcp_init_cgroup);
+
+void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+	struct cg_proto *cg_proto;
+	struct tcp_memcontrol *tcp;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return;
+
+	tcp = tcp_from_cgproto(cg_proto);
+	percpu_counter_destroy(&tcp->tcp_sockets_allocated);
+}
+EXPORT_SYMBOL(tcp_destroy_cgroup);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b69c7030aba9..95d3cfb65d39 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -62,6 +62,7 @@
 #include <net/netdma.h>
 #include <net/inet_common.h>
 #include <net/secure_seq.h>
+#include <net/tcp_memcontrol.h>
 
 #include <asm/uaccess.h>
 
@@ -1994,6 +1995,7 @@ static int tcp_v6_init_sock(struct sock *sk)
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
 	local_bh_disable();
+	sock_update_memcg(sk);
 	sk_sockets_allocated_inc(sk);
 	local_bh_enable();
 
@@ -2227,6 +2229,9 @@ struct proto tcpv6_prot = {
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
 #endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	.proto_cgroup		= tcp_proto_cgroup,
+#endif
 };
 
 static const struct inet6_protocol tcpv6_protocol = {