1 files changed, 65 insertions, 46 deletions

diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index e795272fbe9e..b6f3583ddfe8 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -6,37 +6,6 @@
 #include <linux/memcontrol.h>
 #include <linux/module.h>
 
-static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft);
-static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
-			    const char *buffer);
-static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event);
-
-static struct cftype tcp_files[] = {
-	{
-		.name = "kmem.tcp.limit_in_bytes",
-		.write_string = tcp_cgroup_write,
-		.read_u64 = tcp_cgroup_read,
-		.private = RES_LIMIT,
-	},
-	{
-		.name = "kmem.tcp.usage_in_bytes",
-		.read_u64 = tcp_cgroup_read,
-		.private = RES_USAGE,
-	},
-	{
-		.name = "kmem.tcp.failcnt",
-		.private = RES_FAILCNT,
-		.trigger = tcp_cgroup_reset,
-		.read_u64 = tcp_cgroup_read,
-	},
-	{
-		.name = "kmem.tcp.max_usage_in_bytes",
-		.private = RES_MAX_USAGE,
-		.trigger = tcp_cgroup_reset,
-		.read_u64 = tcp_cgroup_read,
-	},
-};
-
 static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
 {
 	return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
@@ -49,7 +18,7 @@ static void memcg_tcp_enter_memory_pressure(struct sock *sk)
 }
 EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
 
-int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
+int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	/*
 	 * The root cgroup does not use res_counters, but rather,
@@ -59,13 +28,12 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	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);
 	struct net *net = current->nsproxy->net_ns;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
-		goto create_files;
+		return 0;
 
 	tcp = tcp_from_cgproto(cg_proto);
 
@@ -88,15 +56,12 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
 	cg_proto->memcg = memcg;
 
-create_files:
-	return cgroup_add_files(cgrp, ss, tcp_files,
-				ARRAY_SIZE(tcp_files));
+	return 0;
 }
 EXPORT_SYMBOL(tcp_init_cgroup);
 
-void tcp_destroy_cgroup(struct cgroup *cgrp)
+void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct cg_proto *cg_proto;
 	struct tcp_memcontrol *tcp;
 	u64 val;
@@ -109,9 +74,6 @@ void tcp_destroy_cgroup(struct cgroup *cgrp)
 	percpu_counter_destroy(&tcp->tcp_sockets_allocated);
 
 	val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
-
-	if (val != RESOURCE_MAX)
-		static_key_slow_dec(&memcg_socket_limit_enabled);
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
@@ -142,10 +104,33 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 		tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
 					     net->ipv4.sysctl_tcp_mem[i]);
 
-	if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX)
-		static_key_slow_dec(&memcg_socket_limit_enabled);
-	else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX)
-		static_key_slow_inc(&memcg_socket_limit_enabled);
+	if (val == RESOURCE_MAX)
+		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
+	else if (val != RESOURCE_MAX) {
+		/*
+		 * The active bit needs to be written after the static_key
+		 * update. This is what guarantees that the socket activation
+		 * function is the last one to run. See sock_update_memcg() for
+		 * details, and note that we don't mark any socket as belonging
+		 * to this memcg until that flag is up.
+		 *
+		 * We need to do this, because static_keys will span multiple
+		 * sites, but we can't control their order. If we mark a socket
+		 * as accounted, but the accounting functions are not patched in
+		 * yet, we'll lose accounting.
+		 *
+		 * We never race with the readers in sock_update_memcg(),
+		 * because when this value change, the code to process it is not
+		 * patched in yet.
+		 *
+		 * The activated bit is used to guarantee that no two writers
+		 * will do the update in the same memcg. Without that, we can't
+		 * properly shutdown the static key.
+		 */
+		if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags))
+			static_key_slow_inc(&memcg_socket_limit_enabled);
+		set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
+	}
 
 	return 0;
 }
@@ -270,3 +255,37 @@ void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
 
 	tcp->tcp_prot_mem[idx] = val;
 }
+
+static struct cftype tcp_files[] = {
+	{
+		.name = "kmem.tcp.limit_in_bytes",
+		.write_string = tcp_cgroup_write,
+		.read_u64 = tcp_cgroup_read,
+		.private = RES_LIMIT,
+	},
+	{
+		.name = "kmem.tcp.usage_in_bytes",
+		.read_u64 = tcp_cgroup_read,
+		.private = RES_USAGE,
+	},
+	{
+		.name = "kmem.tcp.failcnt",
+		.private = RES_FAILCNT,
+		.trigger = tcp_cgroup_reset,
+		.read_u64 = tcp_cgroup_read,
+	},
+	{
+		.name = "kmem.tcp.max_usage_in_bytes",
+		.private = RES_MAX_USAGE,
+		.trigger = tcp_cgroup_reset,
+		.read_u64 = tcp_cgroup_read,
+	},
+	{ }	/* terminate */
+};
+
+static int __init tcp_memcontrol_init(void)
+{
+	WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files));
+	return 0;
+}
+__initcall(tcp_memcontrol_init);