[PATCH] namespaces: incorporate fs namespace into nsproxy

This moves the mount namespace into the nsproxy.  The mount namespace count
now refers to the number of nsproxies point to it, rather than the number of
tasks.  As a result, the unshare_namespace() function in kernel/fork.c no
longer checks whether it is being shared.

Signed-off-by: Serge Hallyn <serue@us.ibm.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Andrey Savochkin <saw@sw.ru>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 37 insertions, 16 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 1d0e9ea..741bbe4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -399,11 +399,8 @@ void daemonize(const char *name, ...)
 	current->fs = fs;
 	atomic_inc(&fs->count);
 
-	exit_namespace(current);
 	exit_task_namespaces(current);
-	current->namespace = init_task.namespace;
 	current->nsproxy = init_task.nsproxy;
-	get_namespace(current->namespace);
 	get_task_namespaces(current);
 
  	exit_files(current);
@@ -923,7 +920,6 @@ fastcall NORET_TYPE void do_exit(long code)
 	exit_sem(tsk);
 	__exit_files(tsk);
 	__exit_fs(tsk);
-	exit_namespace(tsk);
 	exit_task_namespaces(tsk);
 	exit_thread();
 	cpuset_exit(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index c9e660a..33fcf07 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1119,11 +1119,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_mm;
 	if ((retval = copy_namespaces(clone_flags, p)))
 		goto bad_fork_cleanup_keys;
-	if ((retval = copy_namespace(clone_flags, p)))
-		goto bad_fork_cleanup_namespaces;
 	retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
 	if (retval)
-		goto bad_fork_cleanup_namespace;
+		goto bad_fork_cleanup_namespaces;
 
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
 	/*
@@ -1215,7 +1213,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		spin_unlock(&current->sighand->siglock);
 		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
-		goto bad_fork_cleanup_namespace;
+		goto bad_fork_cleanup_namespaces;
 	}
 
 	if (clone_flags & CLONE_THREAD) {
@@ -1263,8 +1261,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	proc_fork_connector(p);
 	return p;
 
-bad_fork_cleanup_namespace:
-	exit_namespace(p);
 bad_fork_cleanup_namespaces:
 	exit_task_namespaces(p);
 bad_fork_cleanup_keys:
@@ -1519,10 +1515,9 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
  */
 static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs)
 {
-	struct namespace *ns = current->namespace;
+	struct namespace *ns = current->nsproxy->namespace;
 
-	if ((unshare_flags & CLONE_NEWNS) &&
-	    (ns && atomic_read(&ns->count) > 1)) {
+	if ((unshare_flags & CLONE_NEWNS) && ns) {
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
@@ -1655,8 +1650,8 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
 		}
 
 		if (new_ns) {
-			ns = current->namespace;
-			current->namespace = new_ns;
+			ns = current->nsproxy->namespace;
+			current->nsproxy->namespace = new_ns;
 			new_ns = ns;
 		}
 
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index a3612f8..e10385c 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -13,6 +13,7 @@
 #include <linux/version.h>
 #include <linux/nsproxy.h>
 #include <linux/init_task.h>
+#include <linux/namespace.h>
 
 struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
 
@@ -55,6 +56,11 @@ struct nsproxy *dup_namespaces(struct nsproxy *orig)
 {
 	struct nsproxy *ns = clone_namespaces(orig);
 
+	if (ns) {
+		if (ns->namespace)
+			get_namespace(ns->namespace);
+	}
+
 	return ns;
 }
 
@@ -65,16 +71,40 @@ struct nsproxy *dup_namespaces(struct nsproxy *orig)
 int copy_namespaces(int flags, struct task_struct *tsk)
 {
 	struct nsproxy *old_ns = tsk->nsproxy;
+	struct nsproxy *new_ns;
+	int err = 0;
 
 	if (!old_ns)
 		return 0;
 
 	get_nsproxy(old_ns);
 
-	return 0;
+	if (!(flags & CLONE_NEWNS))
+		return 0;
+
+	new_ns = clone_namespaces(old_ns);
+	if (!new_ns) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	tsk->nsproxy = new_ns;
+
+	err = copy_namespace(flags, tsk);
+	if (err) {
+		tsk->nsproxy = old_ns;
+		put_nsproxy(new_ns);
+		goto out;
+	}
+
+out:
+	put_nsproxy(old_ns);
+	return err;
 }
 
 void free_nsproxy(struct nsproxy *ns)
 {
+		if (ns->namespace)
+			put_namespace(ns->namespace);
 		kfree(ns);
 }