sock: Move the socket inuse to namespace.

In some case, we want to know how many sockets are in use in
different _net_ namespaces. It's a key resource metric.

This patch add a member in struct netns_core. This is a counter
for socket-inuse in the _net_ namespace. The patch will add/sub
counter in the sk_alloc, sk_clone_lock and __sk_free.

This patch will not counter the socket created in kernel.
It's not very useful for userspace to know how many kernel
sockets we created.

The main reasons for doing this are that:

1. When linux calls the 'do_exit' for process to exit, the functions
'exit_task_namespaces' and 'exit_task_work' will be called sequentially.
'exit_task_namespaces' may have destroyed the _net_ namespace, but
'sock_release' called in 'exit_task_work' may use the _net_ namespace
if we counter the socket-inuse in sock_release.

2. socket and sock are in pair. More important, sock holds the _net_
namespace. We counter the socket-inuse in sock, for avoiding holding
_net_ namespace again in socket. It's a easy way to maintain the code.

Signed-off-by: Martin Zhang <[e-mail]>
Signed-off-by: Tonghao Zhang <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

include/net/netns/core.h

···
 
 	int	sysctl_somaxconn;
 
+#ifdef CONFIG_PROC_FS
+	int __percpu *sock_inuse;
+#endif
 	struct prot_inuse __percpu *prot_inuse;
 };
 

include/net/sock.h

···
 /* Called with local bh disabled */
 void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
 int sock_prot_inuse_get(struct net *net, struct proto *proto);
+int sock_inuse_get(struct net *net);
 #else
 static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
 		int inc)

net/core/sock.c

···
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
+static void sock_inuse_add(struct net *net, int val);
+
 /**
  * sk_ns_capable - General socket capability test
  * @sk: Socket to use a capability on or through
···
 		sk->sk_kern_sock = kern;
 		sock_lock_init(sk);
 		sk->sk_net_refcnt = kern ? 0 : 1;
-		if (likely(sk->sk_net_refcnt))
+		if (likely(sk->sk_net_refcnt)) {
 			get_net(net);
+			sock_inuse_add(net, 1);
+		}
+
 		sock_net_set(sk, net);
 		refcount_set(&sk->sk_wmem_alloc, 1);
 
···
 
 static void __sk_free(struct sock *sk)
 {
+	if (likely(sk->sk_net_refcnt))
+		sock_inuse_add(sock_net(sk), -1);
+
 	if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
 		sock_diag_broadcast_destroy(sk);
 	else
···
 		newsk->sk_priority = 0;
 		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		atomic64_set(&newsk->sk_cookie, 0);
+		if (likely(newsk->sk_net_refcnt))
+			sock_inuse_add(sock_net(newsk), 1);
 
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
···
 }
 EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
 
+static void sock_inuse_add(struct net *net, int val)
+{
+	this_cpu_add(*net->core.sock_inuse, val);
+}
+
+int sock_inuse_get(struct net *net)
+{
+	int cpu, res = 0;
+
+	for_each_possible_cpu(cpu)
+		res += *per_cpu_ptr(net->core.sock_inuse, cpu);
+
+	return res;
+}
+
+EXPORT_SYMBOL_GPL(sock_inuse_get);
+
 static int __net_init sock_inuse_init_net(struct net *net)
 {
 	net->core.prot_inuse = alloc_percpu(struct prot_inuse);
-	return net->core.prot_inuse ? 0 : -ENOMEM;
+	if (net->core.prot_inuse == NULL)
+		return -ENOMEM;
+
+	net->core.sock_inuse = alloc_percpu(int);
+	if (net->core.sock_inuse == NULL)
+		goto out;
+
+	return 0;
+
+out:
+	free_percpu(net->core.prot_inuse);
+	return -ENOMEM;
 }
 
 static void __net_exit sock_inuse_exit_net(struct net *net)
 {
 	free_percpu(net->core.prot_inuse);
+	free_percpu(net->core.sock_inuse);
 }
 
 static struct pernet_operations net_inuse_ops = {
···
 }
 
 static inline void release_proto_idx(struct proto *prot)
+{
+}
+
+static void sock_inuse_add(struct net *net, int val)
 {
 }
 #endif

net/socket.c

···
 static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly;
 
 /*
- *	Statistics counters of the socket lists
- */
-
-static DEFINE_PER_CPU(int, sockets_in_use);
-
-/*
  * Support routines.
  * Move socket addresses back and forth across the kernel/user
  * divide and look after the messy bits.
···
 	inode->i_gid = current_fsgid();
 	inode->i_op = &sockfs_inode_ops;
 
-	this_cpu_add(sockets_in_use, 1);
 	return sock;
 }
 EXPORT_SYMBOL(sock_alloc);
···
 	if (rcu_dereference_protected(sock->wq, 1)->fasync_list)
 		pr_err("%s: fasync list not empty!\n", __func__);
 
-	this_cpu_sub(sockets_in_use, 1);
 	if (!sock->file) {
 		iput(SOCK_INODE(sock));
 		return;
···
 #ifdef CONFIG_PROC_FS
 void socket_seq_show(struct seq_file *seq)
 {
-	int cpu;
-	int counter = 0;
-
-	for_each_possible_cpu(cpu)
-	    counter += per_cpu(sockets_in_use, cpu);
-
-	/* It can be negative, by the way. 8) */
-	if (counter < 0)
-		counter = 0;
-
-	seq_printf(seq, "sockets: used %d\n", counter);
+	seq_printf(seq, "sockets: used %d\n",
+		   sock_inuse_get(seq->private));
 }
 #endif				/* CONFIG_PROC_FS */