Ban ecryptfs over ecryptfs

(cherry picked from commit 4403158b)

This is a seriously simplified patch from Eric Sandeen; copy of
rationale follows:
===
  mounting stacked ecryptfs on ecryptfs has been shown to lead to bugs
  in testing.  For crypto info in xattr, there is no mechanism for handling
  this at all, and for normal file headers, we run into other trouble:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
  IP: [<ffffffffa015b0b3>] ecryptfs_d_revalidate+0x43/0xa0 [ecryptfs]
  ...

  There doesn't seem to be any good usecase for this, so I'd suggest just
  disallowing the configuration.

  Based on a patch originally, I believe, from Mike Halcrow.
===
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Tim Gardner <tim.gardner@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

fs/ecryptfs/main.c

@@ -487,6 +487,7 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
 }
 
 struct kmem_cache *ecryptfs_sb_info_cache;
+static struct file_system_type ecryptfs_fs_type;
 
 /**
  * ecryptfs_fill_super
@@ -561,6 +562,13 @@ static int ecryptfs_read_super(struct super_block *sb, const char *dev_name)
 		ecryptfs_printk(KERN_WARNING, "path_lookup() failed\n");
 		goto out;
 	}
+	if (path.dentry->d_sb->s_type == &ecryptfs_fs_type) {
+		rc = -EINVAL;
+		printk(KERN_ERR "Mount on filesystem of type "
+			"eCryptfs explicitly disallowed due to "
+			"known incompatibilities\n");
+		goto out_free;
+	}
 	ecryptfs_set_superblock_lower(sb, path.dentry->d_sb);
 	sb->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	sb->s_blocksize = path.dentry->d_sb->s_blocksize;