userns: Better restrictions on when proc and sysfs can be mounted

Rely on the fact that another flavor of the filesystem is already
mounted and do not rely on state in the user namespace.

Verify that the mounted filesystem is not covered in any significant
way.  I would love to verify that the previously mounted filesystem
has no mounts on top but there are at least the directories
/proc/sys/fs/binfmt_misc and /sys/fs/cgroup/ that exist explicitly
for other filesystems to mount on top of.

Refactor the test into a function named fs_fully_visible and call that
function from the mount routines of proc and sysfs.  This makes this
test local to the filesystems involved and the results current of when
the mounts take place, removing a weird threading of the user
namespace, the mount namespace and the filesystems themselves.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

3 files changed, 32 insertions, 15 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 64627f8..877e427 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2867,25 +2867,38 @@ bool current_chrooted(void)
 	return chrooted;
 }
 
-void update_mnt_policy(struct user_namespace *userns)
+bool fs_fully_visible(struct file_system_type *type)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
 	struct mount *mnt;
+	bool visible = false;
 
-	down_read(&namespace_sem);
+	if (unlikely(!ns))
+		return false;
+
+	namespace_lock();
 	list_for_each_entry(mnt, &ns->list, mnt_list) {
-		switch (mnt->mnt.mnt_sb->s_magic) {
-		case SYSFS_MAGIC:
-			userns->may_mount_sysfs = true;
-			break;
-		case PROC_SUPER_MAGIC:
-			userns->may_mount_proc = true;
-			break;
+		struct mount *child;
+		if (mnt->mnt.mnt_sb->s_type != type)
+			continue;
+
+		/* This mount is not fully visible if there are any child mounts
+		 * that cover anything except for empty directories.
+		 */
+		list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+			struct inode *inode = child->mnt_mountpoint->d_inode;
+			if (!S_ISDIR(inode->i_mode))
+				goto next;
+			if (inode->i_nlink != 2)
+				goto next;
 		}
-		if (userns->may_mount_sysfs && userns->may_mount_proc)
-			break;
+		visible = true;
+		goto found;
+	next:	;
 	}
-	up_read(&namespace_sem);
+found:
+	namespace_unlock();
+	return visible;
 }
 
 static void *mntns_get(struct task_struct *task)
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 38bd5d4..45e5fb7 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -110,8 +110,11 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 		ns = task_active_pid_ns(current);
 		options = data;
 
-		if (!current_user_ns()->may_mount_proc ||
-		    !ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
+			return ERR_PTR(-EPERM);
+
+		/* Does the mounter have privilege over the pid namespace? */
+		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
 			return ERR_PTR(-EPERM);
 	}
 
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index afd8327..4a2da3a 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -112,7 +112,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	struct super_block *sb;
 	int error;
 
-	if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs)
+	if (!(flags & MS_KERNMOUNT) && !capable(CAP_SYS_ADMIN) &&
+	    !fs_fully_visible(fs_type))
 		return ERR_PTR(-EPERM);
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);