1 files changed, 104 insertions, 77 deletions

diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index f5d332cf8c6..8e7811086b8 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -13,8 +13,8 @@
  *             Pavel Emelianov <xemul@openvz.org>
  */
 
-#include <linux/module.h>
-#include <linux/version.h>
+#include <linux/slab.h>
+#include <linux/export.h>
 #include <linux/nsproxy.h>
 #include <linux/init_task.h>
 #include <linux/mnt_namespace.h>
@@ -22,24 +22,33 @@
 #include <linux/pid_namespace.h>
 #include <net/net_namespace.h>
 #include <linux/ipc_namespace.h>
+#include <linux/proc_ns.h>
+#include <linux/file.h>
+#include <linux/syscalls.h>
 
 static struct kmem_cache *nsproxy_cachep;
 
-struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
-
-/*
- * creates a copy of "orig" with refcount 1.
- */
-static inline struct nsproxy *clone_nsproxy(struct nsproxy *orig)
+struct nsproxy init_nsproxy = {
+	.count			= ATOMIC_INIT(1),
+	.uts_ns			= &init_uts_ns,
+#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
+	.ipc_ns			= &init_ipc_ns,
+#endif
+	.mnt_ns			= NULL,
+	.pid_ns_for_children	= &init_pid_ns,
+#ifdef CONFIG_NET
+	.net_ns			= &init_net,
+#endif
+};
+
+static inline struct nsproxy *create_nsproxy(void)
 {
-	struct nsproxy *ns;
+	struct nsproxy *nsproxy;
 
-	ns = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
-	if (ns) {
-		memcpy(ns, orig, sizeof(struct nsproxy));
-		atomic_set(&ns->count, 1);
-	}
-	return ns;
+	nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
+	if (nsproxy)
+		atomic_set(&nsproxy->count, 1);
+	return nsproxy;
 }
 
 /*
@@ -48,46 +57,42 @@ static inline struct nsproxy *clone_nsproxy(struct nsproxy *orig)
  * leave it to the caller to do proper locking and attach it to task.
  */
 static struct nsproxy *create_new_namespaces(unsigned long flags,
-			struct task_struct *tsk, struct fs_struct *new_fs)
+	struct task_struct *tsk, struct user_namespace *user_ns,
+	struct fs_struct *new_fs)
 {
 	struct nsproxy *new_nsp;
 	int err;
 
-	new_nsp = clone_nsproxy(tsk->nsproxy);
+	new_nsp = create_nsproxy();
 	if (!new_nsp)
 		return ERR_PTR(-ENOMEM);
 
-	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, new_fs);
+	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
 	if (IS_ERR(new_nsp->mnt_ns)) {
 		err = PTR_ERR(new_nsp->mnt_ns);
 		goto out_ns;
 	}
 
-	new_nsp->uts_ns = copy_utsname(flags, tsk->nsproxy->uts_ns);
+	new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
 	if (IS_ERR(new_nsp->uts_ns)) {
 		err = PTR_ERR(new_nsp->uts_ns);
 		goto out_uts;
 	}
 
-	new_nsp->ipc_ns = copy_ipcs(flags, tsk->nsproxy->ipc_ns);
+	new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
 	if (IS_ERR(new_nsp->ipc_ns)) {
 		err = PTR_ERR(new_nsp->ipc_ns);
 		goto out_ipc;
 	}
 
-	new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk));
-	if (IS_ERR(new_nsp->pid_ns)) {
-		err = PTR_ERR(new_nsp->pid_ns);
+	new_nsp->pid_ns_for_children =
+		copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children);
+	if (IS_ERR(new_nsp->pid_ns_for_children)) {
+		err = PTR_ERR(new_nsp->pid_ns_for_children);
 		goto out_pid;
 	}
 
-	new_nsp->user_ns = copy_user_ns(flags, tsk->nsproxy->user_ns);
-	if (IS_ERR(new_nsp->user_ns)) {
-		err = PTR_ERR(new_nsp->user_ns);
-		goto out_user;
-	}
-
-	new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns);
+	new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
 	if (IS_ERR(new_nsp->net_ns)) {
 		err = PTR_ERR(new_nsp->net_ns);
 		goto out_net;
@@ -96,11 +101,8 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 	return new_nsp;
 
 out_net:
-	if (new_nsp->user_ns)
-		put_user_ns(new_nsp->user_ns);
-out_user:
-	if (new_nsp->pid_ns)
-		put_pid_ns(new_nsp->pid_ns);
+	if (new_nsp->pid_ns_for_children)
+		put_pid_ns(new_nsp->pid_ns_for_children);
 out_pid:
 	if (new_nsp->ipc_ns)
 		put_ipc_ns(new_nsp->ipc_ns);
@@ -122,40 +124,35 @@ out_ns:
 int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 {
 	struct nsproxy *old_ns = tsk->nsproxy;
+	struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
 	struct nsproxy *new_ns;
-	int err = 0;
-
-	if (!old_ns)
-		return 0;
-
-	get_nsproxy(old_ns);
 
-	if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-				CLONE_NEWUSER | CLONE_NEWPID | CLONE_NEWNET)))
+	if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
+			      CLONE_NEWPID | CLONE_NEWNET)))) {
+		get_nsproxy(old_ns);
 		return 0;
-
-	if (!capable(CAP_SYS_ADMIN)) {
-		err = -EPERM;
-		goto out;
 	}
 
-	new_ns = create_new_namespaces(flags, tsk, tsk->fs);
-	if (IS_ERR(new_ns)) {
-		err = PTR_ERR(new_ns);
-		goto out;
-	}
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
 
-	err = ns_cgroup_clone(tsk);
-	if (err) {
-		put_nsproxy(new_ns);
-		goto out;
-	}
+	/*
+	 * CLONE_NEWIPC must detach from the undolist: after switching
+	 * to a new ipc namespace, the semaphore arrays from the old
+	 * namespace are unreachable.  In clone parlance, CLONE_SYSVSEM
+	 * means share undolist with parent, so we must forbid using
+	 * it along with CLONE_NEWIPC.
+	 */
+	if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) ==
+		(CLONE_NEWIPC | CLONE_SYSVSEM)) 
+		return -EINVAL;
+
+	new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
+	if (IS_ERR(new_ns))
+		return  PTR_ERR(new_ns);
 
 	tsk->nsproxy = new_ns;
-
-out:
-	put_nsproxy(old_ns);
-	return err;
+	return 0;
 }
 
 void free_nsproxy(struct nsproxy *ns)
@@ -166,10 +163,8 @@ void free_nsproxy(struct nsproxy *ns)
 		put_uts_ns(ns->uts_ns);
 	if (ns->ipc_ns)
 		put_ipc_ns(ns->ipc_ns);
-	if (ns->pid_ns)
-		put_pid_ns(ns->pid_ns);
-	if (ns->user_ns)
-		put_user_ns(ns->user_ns);
+	if (ns->pid_ns_for_children)
+		put_pid_ns(ns->pid_ns_for_children);
 	put_net(ns->net_ns);
 	kmem_cache_free(nsproxy_cachep, ns);
 }
@@ -179,28 +174,26 @@ void free_nsproxy(struct nsproxy *ns)
  * On success, returns the new nsproxy.
  */
 int unshare_nsproxy_namespaces(unsigned long unshare_flags,
-		struct nsproxy **new_nsp, struct fs_struct *new_fs)
+	struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
 {
+	struct user_namespace *user_ns;
 	int err = 0;
 
 	if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-			       CLONE_NEWUSER | CLONE_NEWNET)))
+			       CLONE_NEWNET | CLONE_NEWPID)))
 		return 0;
 
-	if (!capable(CAP_SYS_ADMIN))
+	user_ns = new_cred ? new_cred->user_ns : current_user_ns();
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	*new_nsp = create_new_namespaces(unshare_flags, current,
-				new_fs ? new_fs : current->fs);
+	*new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
+					 new_fs ? new_fs : current->fs);
 	if (IS_ERR(*new_nsp)) {
 		err = PTR_ERR(*new_nsp);
 		goto out;
 	}
 
-	err = ns_cgroup_clone(current);
-	if (err)
-		put_nsproxy(*new_nsp);
-
 out:
 	return err;
 }
@@ -232,10 +225,44 @@ void exit_task_namespaces(struct task_struct *p)
 	switch_task_namespaces(p, NULL);
 }
 
-static int __init nsproxy_cache_init(void)
+SYSCALL_DEFINE2(setns, int, fd, int, nstype)
+{
+	const struct proc_ns_operations *ops;
+	struct task_struct *tsk = current;
+	struct nsproxy *new_nsproxy;
+	struct proc_ns *ei;
+	struct file *file;
+	int err;
+
+	file = proc_ns_fget(fd);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	err = -EINVAL;
+	ei = get_proc_ns(file_inode(file));
+	ops = ei->ns_ops;
+	if (nstype && (ops->type != nstype))
+		goto out;
+
+	new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
+	if (IS_ERR(new_nsproxy)) {
+		err = PTR_ERR(new_nsproxy);
+		goto out;
+	}
+
+	err = ops->install(new_nsproxy, ei->ns);
+	if (err) {
+		free_nsproxy(new_nsproxy);
+		goto out;
+	}
+	switch_task_namespaces(tsk, new_nsproxy);
+out:
+	fput(file);
+	return err;
+}
+
+int __init nsproxy_cache_init(void)
 {
 	nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
 	return 0;
 }
-
-module_init(nsproxy_cache_init);