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: [e-mail]
Signed-off-by: "Eric W. Biederman" <[e-mail]>

fs/proc/base.c

···
 	.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,
···
 	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),
···
 	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
 };
 

include/linux/user_namespace.h

···
 	} extent[UID_GID_MAP_MAX_EXTENTS];
 };
 
+#define USERNS_SETGROUPS_ALLOWED 1UL
+
+#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
+
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
···
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+	unsigned long		flags;
 
 	/* Register of per-UID persistent keyrings for this namespace */
 #ifdef CONFIG_PERSISTENT_KEYRINGS
···
 extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
+extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
+extern int proc_setgroups_show(struct seq_file *m, void *v);
 extern bool userns_may_setgroups(const struct user_namespace *ns);
 #else
 

kernel/user.c

···
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.flags = USERNS_INIT_FLAGS,
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	.persistent_keyring_register_sem =
 	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),

kernel/user_namespace.c

···
 	ns->owner = owner;
 	ns->group = group;
 
+	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
+	mutex_lock(&userns_state_mutex);
+	ns->flags = parent_ns->flags;
+	mutex_unlock(&userns_state_mutex);
+
 	set_cred_user_ns(new, ns);
 
 #ifdef CONFIG_PERSISTENT_KEYRINGS
···
 	return false;
 }
 
+int proc_setgroups_show(struct seq_file *seq, void *v)
+{
+	struct user_namespace *ns = seq->private;
+	unsigned long userns_flags = ACCESS_ONCE(ns->flags);
+
+	seq_printf(seq, "%s\n",
+		   (userns_flags & USERNS_SETGROUPS_ALLOWED) ?
+		   "allow" : "deny");
+	return 0;
+}
+
+ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	char kbuf[8], *pos;
+	bool setgroups_allowed;
+	ssize_t ret;
+
+	/* Only allow a very narrow range of strings to be written */
+	ret = -EINVAL;
+	if ((*ppos != 0) || (count >= sizeof(kbuf)))
+		goto out;
+
+	/* What was written? */
+	ret = -EFAULT;
+	if (copy_from_user(kbuf, buf, count))
+		goto out;
+	kbuf[count] = '\0';
+	pos = kbuf;
+
+	/* What is being requested? */
+	ret = -EINVAL;
+	if (strncmp(pos, "allow", 5) == 0) {
+		pos += 5;
+		setgroups_allowed = true;
+	}
+	else if (strncmp(pos, "deny", 4) == 0) {
+		pos += 4;
+		setgroups_allowed = false;
+	}
+	else
+		goto out;
+
+	/* Verify there is not trailing junk on the line */
+	pos = skip_spaces(pos);
+	if (*pos != '\0')
+		goto out;
+
+	ret = -EPERM;
+	mutex_lock(&userns_state_mutex);
+	if (setgroups_allowed) {
+		/* Enabling setgroups after setgroups has been disabled
+		 * is not allowed.
+		 */
+		if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
+			goto out_unlock;
+	} else {
+		/* Permanently disabling setgroups after setgroups has
+		 * been enabled by writing the gid_map is not allowed.
+		 */
+		if (ns->gid_map.nr_extents != 0)
+			goto out_unlock;
+		ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
+	}
+	mutex_unlock(&userns_state_mutex);
+
+	/* Report a successful write */
+	*ppos = count;
+	ret = count;
+out:
+	return ret;
+out_unlock:
+	mutex_unlock(&userns_state_mutex);
+	goto out;
+}
+
 bool userns_may_setgroups(const struct user_namespace *ns)
 {
 	bool allowed;
···
 	 * the user namespace has been established.
 	 */
 	allowed = ns->gid_map.nr_extents != 0;
+	/* Is setgroups allowed? */
+	allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
 	mutex_unlock(&userns_state_mutex);
 
 	return allowed;