userns: Add a knob to disable setgroups on a per user namespace basis

- Expose the knob to user space through a proc file /proc/<pid>/setgroups

  A value of "deny" means the setgroups system call is disabled in the
  current processes user namespace and can not be enabled in the
  future in this user namespace.

  A value of "allow" means the segtoups system call is enabled.

- Descendant user namespaces inherit the value of setgroups from
  their parents.

- A proc file is used (instead of a sysctl) as sysctls currently do
  not allow checking the permissions at open time.

- Writing to the proc file is restricted to before the gid_map
  for the user namespace is set.

  This ensures that disabling setgroups at a user namespace
  level will never remove the ability to call setgroups
  from a process that already has that ability.

  A process may opt in to the setgroups disable for itself by
  creating, entering and configuring a user namespace or by calling
  setns on an existing user namespace with setgroups disabled.
  Processes without privileges already can not call setgroups so this
  is a noop.  Prodcess with privilege become processes without
  privilege when entering a user namespace and as with any other path
  to dropping privilege they would not have the ability to call
  setgroups.  So this remains within the bounds of what is possible
  without a knob to disable setgroups permanently in a user namespace.

Cc: stable@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

1 files changed, 53 insertions, 0 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 772efa4..7dc3ea8 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2464,6 +2464,57 @@ static const struct file_operations proc_projid_map_operations = {
 	.llseek		= seq_lseek,
 	.release	= proc_id_map_release,
 };
+
+static int proc_setgroups_open(struct inode *inode, struct file *file)
+{
+	struct user_namespace *ns = NULL;
+	struct task_struct *task;
+	int ret;
+
+	ret = -ESRCH;
+	task = get_proc_task(inode);
+	if (task) {
+		rcu_read_lock();
+		ns = get_user_ns(task_cred_xxx(task, user_ns));
+		rcu_read_unlock();
+		put_task_struct(task);
+	}
+	if (!ns)
+		goto err;
+
+	if (file->f_mode & FMODE_WRITE) {
+		ret = -EACCES;
+		if (!ns_capable(ns, CAP_SYS_ADMIN))
+			goto err_put_ns;
+	}
+
+	ret = single_open(file, &proc_setgroups_show, ns);
+	if (ret)
+		goto err_put_ns;
+
+	return 0;
+err_put_ns:
+	put_user_ns(ns);
+err:
+	return ret;
+}
+
+static int proc_setgroups_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	int ret = single_release(inode, file);
+	put_user_ns(ns);
+	return ret;
+}
+
+static const struct file_operations proc_setgroups_operations = {
+	.open		= proc_setgroups_open,
+	.write		= proc_setgroups_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_setgroups_release,
+};
 #endif /* CONFIG_USER_NS */
 
 static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
@@ -2572,6 +2623,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	REG("timers",	  S_IRUGO, proc_timers_operations),
@@ -2913,6 +2965,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 };