1 files changed, 157 insertions, 56 deletions

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 3f860261c5e..85b62691f4f 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -1,3 +1,5 @@
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/workqueue.h>
 #include <linux/rtnetlink.h>
 #include <linux/cache.h>
@@ -8,6 +10,11 @@
 #include <linux/idr.h>
 #include <linux/rculist.h>
 #include <linux/nsproxy.h>
+#include <linux/fs.h>
+#include <linux/proc_ns.h>
+#include <linux/file.h>
+#include <linux/export.h>
+#include <linux/user_namespace.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -17,22 +24,30 @@
 
 static LIST_HEAD(pernet_list);
 static struct list_head *first_device = &pernet_list;
-static DEFINE_MUTEX(net_mutex);
+DEFINE_MUTEX(net_mutex);
 
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
 
-struct net init_net;
+struct net init_net = {
+	.dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head),
+};
 EXPORT_SYMBOL(init_net);
 
 #define INITIAL_NET_GEN_PTRS	13 /* +1 for len +2 for rcu_head */
 
-static void net_generic_release(struct rcu_head *rcu)
+static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;
+
+static struct net_generic *net_alloc_generic(void)
 {
 	struct net_generic *ng;
+	size_t generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]);
 
-	ng = container_of(rcu, struct net_generic, rcu);
-	kfree(ng);
+	ng = kzalloc(generic_size, GFP_KERNEL);
+	if (ng)
+		ng->len = max_gen_ptrs;
+
+	return ng;
 }
 
 static int net_assign_generic(struct net *net, int id, void *data)
@@ -48,8 +63,7 @@ static int net_assign_generic(struct net *net, int id, void *data)
 	if (old_ng->len >= id)
 		goto assign;
 
-	ng = kzalloc(sizeof(struct net_generic) +
-			id * sizeof(void *), GFP_KERNEL);
+	ng = net_alloc_generic();
 	if (ng == NULL)
 		return -ENOMEM;
 
@@ -64,11 +78,10 @@ static int net_assign_generic(struct net *net, int id, void *data)
 	 * the old copy for kfree after a grace period.
 	 */
 
-	ng->len = id;
 	memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*));
 
 	rcu_assign_pointer(net->gen, ng);
-	call_rcu(&old_ng->rcu, net_generic_release);
+	kfree_rcu(old_ng, rcu);
 assign:
 	ng->ptr[id - 1] = data;
 	return 0;
@@ -76,21 +89,29 @@ assign:
 
 static int ops_init(const struct pernet_operations *ops, struct net *net)
 {
-	int err;
+	int err = -ENOMEM;
+	void *data = NULL;
+
 	if (ops->id && ops->size) {
-		void *data = kzalloc(ops->size, GFP_KERNEL);
+		data = kzalloc(ops->size, GFP_KERNEL);
 		if (!data)
-			return -ENOMEM;
+			goto out;
 
 		err = net_assign_generic(net, *ops->id, data);
-		if (err) {
-			kfree(data);
-			return err;
-		}
+		if (err)
+			goto cleanup;
 	}
+	err = 0;
 	if (ops->init)
-		return ops->init(net);
-	return 0;
+		err = ops->init(net);
+	if (!err)
+		return 0;
+
+cleanup:
+	kfree(data);
+
+out:
+	return err;
 }
 
 static void ops_free(const struct pernet_operations *ops, struct net *net)
@@ -126,7 +147,7 @@ static void ops_free_list(const struct pernet_operations *ops,
 /*
  * setup_net runs the initializers for the network namespace object.
  */
-static __net_init int setup_net(struct net *net)
+static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 {
 	/* Must be called with net_mutex held */
 	const struct pernet_operations *ops, *saved_ops;
@@ -134,6 +155,9 @@ static __net_init int setup_net(struct net *net)
 	LIST_HEAD(net_exit_list);
 
 	atomic_set(&net->count, 1);
+	atomic_set(&net->passive, 1);
+	net->dev_base_seq = 1;
+	net->user_ns = user_ns;
 
 #ifdef NETNS_REFCNT_DEBUG
 	atomic_set(&net->use_count, 0);
@@ -164,18 +188,6 @@ out_undo:
 	goto out;
 }
 
-static struct net_generic *net_alloc_generic(void)
-{
-	struct net_generic *ng;
-	size_t generic_size = sizeof(struct net_generic) +
-		INITIAL_NET_GEN_PTRS * sizeof(void *);
-
-	ng = kzalloc(generic_size, GFP_KERNEL);
-	if (ng)
-		ng->len = INITIAL_NET_GEN_PTRS;
-
-	return ng;
-}
 
 #ifdef CONFIG_NET_NS
 static struct kmem_cache *net_cachep;
@@ -207,8 +219,8 @@ static void net_free(struct net *net)
 {
 #ifdef NETNS_REFCNT_DEBUG
 	if (unlikely(atomic_read(&net->use_count) != 0)) {
-		printk(KERN_EMERG "network namespace not free! Usage: %d\n",
-			atomic_read(&net->use_count));
+		pr_emerg("network namespace not free! Usage: %d\n",
+			 atomic_read(&net->use_count));
 		return;
 	}
 #endif
@@ -216,16 +228,30 @@ static void net_free(struct net *net)
 	kmem_cache_free(net_cachep, net);
 }
 
-static struct net *net_create(void)
+void net_drop_ns(void *p)
+{
+	struct net *ns = p;
+	if (ns && atomic_dec_and_test(&ns->passive))
+		net_free(ns);
+}
+
+struct net *copy_net_ns(unsigned long flags,
+			struct user_namespace *user_ns, struct net *old_net)
 {
 	struct net *net;
 	int rv;
 
+	if (!(flags & CLONE_NEWNET))
+		return get_net(old_net);
+
 	net = net_alloc();
 	if (!net)
 		return ERR_PTR(-ENOMEM);
+
+	get_user_ns(user_ns);
+
 	mutex_lock(&net_mutex);
-	rv = setup_net(net);
+	rv = setup_net(net, user_ns);
 	if (rv == 0) {
 		rtnl_lock();
 		list_add_tail_rcu(&net->list, &net_namespace_list);
@@ -233,19 +259,13 @@ static struct net *net_create(void)
 	}
 	mutex_unlock(&net_mutex);
 	if (rv < 0) {
-		net_free(net);
+		put_user_ns(user_ns);
+		net_drop_ns(net);
 		return ERR_PTR(rv);
 	}
 	return net;
 }
 
-struct net *copy_net_ns(unsigned long flags, struct net *old_net)
-{
-	if (!(flags & CLONE_NEWNET))
-		return get_net(old_net);
-	return net_create();
-}
-
 static DEFINE_SPINLOCK(cleanup_list_lock);
 static LIST_HEAD(cleanup_list);  /* Must hold cleanup_list_lock to touch */
 
@@ -253,7 +273,7 @@ static void cleanup_net(struct work_struct *work)
 {
 	const struct pernet_operations *ops;
 	struct net *net, *tmp;
-	LIST_HEAD(net_kill_list);
+	struct list_head net_kill_list;
 	LIST_HEAD(net_exit_list);
 
 	/* Atomically snapshot the list of namespaces to cleanup */
@@ -296,7 +316,8 @@ static void cleanup_net(struct work_struct *work)
 	/* Finally it is safe to free my network namespace structure */
 	list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
 		list_del_init(&net->exit_list);
-		net_free(net);
+		put_user_ns(net->user_ns);
+		net_drop_ns(net);
 	}
 }
 static DECLARE_WORK(net_cleanup_work, cleanup_net);
@@ -314,12 +335,30 @@ void __put_net(struct net *net)
 }
 EXPORT_SYMBOL_GPL(__put_net);
 
+struct net *get_net_ns_by_fd(int fd)
+{
+	struct proc_ns *ei;
+	struct file *file;
+	struct net *net;
+
+	file = proc_ns_fget(fd);
+	if (IS_ERR(file))
+		return ERR_CAST(file);
+
+	ei = get_proc_ns(file_inode(file));
+	if (ei->ns_ops == &netns_operations)
+		net = get_net(ei->ns);
+	else
+		net = ERR_PTR(-EINVAL);
+
+	fput(file);
+	return net;
+}
+
 #else
-struct net *copy_net_ns(unsigned long flags, struct net *old_net)
+struct net *get_net_ns_by_fd(int fd)
 {
-	if (flags & CLONE_NEWNET)
-		return ERR_PTR(-EINVAL);
-	return old_net;
+	return ERR_PTR(-EINVAL);
 }
 #endif
 
@@ -343,6 +382,21 @@ struct net *get_net_ns_by_pid(pid_t pid)
 }
 EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
 
+static __net_init int net_ns_net_init(struct net *net)
+{
+	return proc_alloc_inum(&net->proc_inum);
+}
+
+static __net_exit void net_ns_net_exit(struct net *net)
+{
+	proc_free_inum(net->proc_inum);
+}
+
+static struct pernet_operations __net_initdata net_ns_ops = {
+	.init = net_ns_net_init,
+	.exit = net_ns_net_exit,
+};
+
 static int __init net_ns_init(void)
 {
 	struct net_generic *ng;
@@ -365,7 +419,7 @@ static int __init net_ns_init(void)
 	rcu_assign_pointer(init_net.gen, ng);
 
 	mutex_lock(&net_mutex);
-	if (setup_net(&init_net))
+	if (setup_net(&init_net, &init_user_ns))
 		panic("Could not setup the initial network namespace");
 
 	rtnl_lock();
@@ -374,6 +428,8 @@ static int __init net_ns_init(void)
 
 	mutex_unlock(&net_mutex);
 
+	register_pernet_subsys(&net_ns_ops);
+
 	return 0;
 }
 
@@ -423,12 +479,7 @@ static void __unregister_pernet_operations(struct pernet_operations *ops)
 static int __register_pernet_operations(struct list_head *list,
 					struct pernet_operations *ops)
 {
-	int err = 0;
-	err = ops_init(ops, &init_net);
-	if (err)
-		ops_free(ops, &init_net);
-	return err;
-	
+	return ops_init(ops, &init_net);
 }
 
 static void __unregister_pernet_operations(struct pernet_operations *ops)
@@ -458,6 +509,7 @@ again:
 			}
 			return error;
 		}
+		max_gen_ptrs = max_t(unsigned int, max_gen_ptrs, *ops->id);
 	}
 	error = __register_pernet_operations(list, ops);
 	if (error) {
@@ -573,3 +625,52 @@ void unregister_pernet_device(struct pernet_operations *ops)
 	mutex_unlock(&net_mutex);
 }
 EXPORT_SYMBOL_GPL(unregister_pernet_device);
+
+#ifdef CONFIG_NET_NS
+static void *netns_get(struct task_struct *task)
+{
+	struct net *net = NULL;
+	struct nsproxy *nsproxy;
+
+	rcu_read_lock();
+	nsproxy = task_nsproxy(task);
+	if (nsproxy)
+		net = get_net(nsproxy->net_ns);
+	rcu_read_unlock();
+
+	return net;
+}
+
+static void netns_put(void *ns)
+{
+	put_net(ns);
+}
+
+static int netns_install(struct nsproxy *nsproxy, void *ns)
+{
+	struct net *net = ns;
+
+	if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) ||
+	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+		return -EPERM;
+
+	put_net(nsproxy->net_ns);
+	nsproxy->net_ns = get_net(net);
+	return 0;
+}
+
+static unsigned int netns_inum(void *ns)
+{
+	struct net *net = ns;
+	return net->proc_inum;
+}
+
+const struct proc_ns_operations netns_operations = {
+	.name		= "net",
+	.type		= CLONE_NEWNET,
+	.get		= netns_get,
+	.put		= netns_put,
+	.install	= netns_install,
+	.inum		= netns_inum,
+};
+#endif