Retain vault password as bytes in 2.2vault-pass-nonutf8-2.2-compat

Prior to 2.2.1, the vault password was read in as byes and then remained
bytes all the way through the code.  A bug existed where bytes and text
were mixed, leading to a traceback with non-ascii passwords.  In devel,
this was fixed by changing the read in password to text type to match
with our overall strategy of converting at the borders.  This was
backported to stable-2.2 for the 2.2.1 release.

On reflection, this should not have been backported as it causes
passwords which were originally non-utf-8 to become utf-8.  People will
then have their working 2.2.x vault files become in-accessible.

this commit pipes bytes all the way through the system for vault
password.  That way if a password is read in as a non-utf-8 character
sequence, it will continue to work in 2.2.2+.  This change is only for
the 2.2 branch, not for 2.3 and beyond.

Why not everywhere?  The reason is that non-utf-8 passwords will cause
problems when vault files are shared between systems or users.  If the
password is read from the prompt and one user/machine has a latin1
encoded locale while a second one has utf-8, the non-ascii password
typed in won't match between machines.  Deal with this by making sure
that when we encrypt the data, we always use valid utf-8.

Fixes #20398

8 files changed, 45 insertions, 45 deletions

diff --git a/lib/ansible/cli/__init__.py b/lib/ansible/cli/__init__.py
index 667b54b0aa..cc71cd560b 100644
--- a/lib/ansible/cli/__init__.py
+++ b/lib/ansible/cli/__init__.py
@@ -169,7 +169,7 @@ class CLI(object):
 
         # enforce no newline chars at the end of passwords
         if vault_pass:
-            vault_pass = to_text(vault_pass, errors='surrogate_or_strict', nonstring='simplerepr').strip()
+            vault_pass = to_bytes(vault_pass, errors='surrogate_or_strict', nonstring='simplerepr').strip()
 
         return vault_pass
 
@@ -185,7 +185,7 @@ class CLI(object):
             pass
 
         if new_vault_pass:
-            new_vault_pass = to_text(new_vault_pass, errors='surrogate_or_strict', nonstring='simplerepr').strip()
+            new_vault_pass = to_bytes(new_vault_pass, errors='surrogate_or_strict', nonstring='simplerepr').strip()
 
         return new_vault_pass
 
@@ -586,7 +586,7 @@ class CLI(object):
             except (OSError, IOError) as e:
                 raise AnsibleError("Could not read vault password file %s: %s" % (this_path, e))
 
-        return to_text(vault_pass, errors='surrogate_or_strict')
+        return vault_pass
 
     def get_opt(self, k, defval=""):
         """
diff --git a/lib/ansible/cli/adhoc.py b/lib/ansible/cli/adhoc.py
index 70bac64849..a40823ab36 100644
--- a/lib/ansible/cli/adhoc.py
+++ b/lib/ansible/cli/adhoc.py
@@ -107,7 +107,7 @@ class AdHocCLI(CLI):
 
         sshpass    = None
         becomepass = None
-        vault_pass = None
+        b_vault_pass = None
 
         self.normalize_become_options()
         (sshpass, becomepass) = self.ask_passwords()
@@ -117,11 +117,11 @@ class AdHocCLI(CLI):
 
         if self.options.vault_password_file:
             # read vault_pass from a file
-            vault_pass = CLI.read_vault_password_file(self.options.vault_password_file, loader=loader)
-            loader.set_vault_password(vault_pass)
+            b_vault_pass = CLI.read_vault_password_file(self.options.vault_password_file, loader=loader)
+            loader.set_vault_password(b_vault_pass)
         elif self.options.ask_vault_pass:
-            vault_pass = self.ask_vault_passwords()
-            loader.set_vault_password(vault_pass)
+            b_vault_pass = self.ask_vault_passwords()
+            loader.set_vault_password(b_vault_pass)
 
         variable_manager = VariableManager()
         variable_manager.extra_vars = load_extra_vars(loader=loader, options=self.options)
diff --git a/lib/ansible/cli/playbook.py b/lib/ansible/cli/playbook.py
index 609819da0b..ae00ab8ddd 100644
--- a/lib/ansible/cli/playbook.py
+++ b/lib/ansible/cli/playbook.py
@@ -94,7 +94,7 @@ class PlaybookCLI(CLI):
         # Manage passwords
         sshpass    = None
         becomepass    = None
-        vault_pass = None
+        b_vault_pass = None
         passwords = {}
 
         # don't deal with privilege escalation or passwords when we don't need to
@@ -107,11 +107,11 @@ class PlaybookCLI(CLI):
 
         if self.options.vault_password_file:
             # read vault_pass from a file
-            vault_pass = CLI.read_vault_password_file(self.options.vault_password_file, loader=loader)
-            loader.set_vault_password(vault_pass)
+            b_vault_pass = CLI.read_vault_password_file(self.options.vault_password_file, loader=loader)
+            loader.set_vault_password(b_vault_pass)
         elif self.options.ask_vault_pass:
-            vault_pass = self.ask_vault_passwords()
-            loader.set_vault_password(vault_pass)
+            b_vault_pass = self.ask_vault_passwords()
+            loader.set_vault_password(b_vault_pass)
 
         # initial error check, to make sure all specified playbooks are accessible
         # before we start running anything through the playbook executor
diff --git a/lib/ansible/cli/vault.py b/lib/ansible/cli/vault.py
index eb278565c7..b806ac06a2 100644
--- a/lib/ansible/cli/vault.py
+++ b/lib/ansible/cli/vault.py
@@ -42,8 +42,8 @@ class VaultCLI(CLI):
 
     def __init__(self, args):
 
-        self.vault_pass = None
-        self.new_vault_pass = None
+        self.b_vault_pass = None
+        self.b_new_vault_pass = None
         super(VaultCLI, self).__init__(args)
 
     def parse(self):
@@ -99,25 +99,25 @@ class VaultCLI(CLI):
 
         if self.options.vault_password_file:
             # read vault_pass from a file
-            self.vault_pass = CLI.read_vault_password_file(self.options.vault_password_file, loader)
+            self.b_vault_pass = CLI.read_vault_password_file(self.options.vault_password_file, loader)
 
         if self.options.new_vault_password_file:
             # for rekey only
-            self.new_vault_pass = CLI.read_vault_password_file(self.options.new_vault_password_file, loader)
+            self.b_new_vault_pass = CLI.read_vault_password_file(self.options.new_vault_password_file, loader)
 
-        if not self.vault_pass or self.options.ask_vault_pass:
-            self.vault_pass = self.ask_vault_passwords()
+        if not self.b_vault_pass or self.options.ask_vault_pass:
+            self.b_vault_pass = self.ask_vault_passwords()
 
-        if not self.vault_pass:
+        if not self.b_vault_pass:
             raise AnsibleOptionsError("A password is required to use Ansible's Vault")
 
         if self.action == 'rekey':
-            if not self.new_vault_pass:
-                self.new_vault_pass = self.ask_new_vault_passwords()
-            if not self.new_vault_pass:
+            if not self.b_new_vault_pass:
+                self.b_new_vault_pass = self.ask_new_vault_passwords()
+            if not self.b_new_vault_pass:
                 raise AnsibleOptionsError("A password is required to rekey Ansible's Vault")
 
-        self.editor = VaultEditor(self.vault_pass)
+        self.editor = VaultEditor(self.b_vault_pass)
 
         self.execute()
 
@@ -173,6 +173,6 @@ class VaultCLI(CLI):
                 raise AnsibleError(f + " does not exist")
 
         for f in self.args:
-            self.editor.rekey_file(f, self.new_vault_pass)
+            self.editor.rekey_file(f, self.b_new_vault_pass)
 
         display.display("Rekey successful", stderr=True)
diff --git a/lib/ansible/parsing/dataloader.py b/lib/ansible/parsing/dataloader.py
index 6bac8e7237..a47638ec6c 100644
--- a/lib/ansible/parsing/dataloader.py
+++ b/lib/ansible/parsing/dataloader.py
@@ -71,9 +71,9 @@ class DataLoader():
         # initialize the vault stuff with an empty password
         self.set_vault_password(None)
 
-    def set_vault_password(self, vault_password):
-        self._vault_password = vault_password
-        self._vault = VaultLib(password=vault_password)
+    def set_vault_password(self, b_vault_password):
+        self._b_vault_password = b_vault_password
+        self._vault = VaultLib(b_password=b_vault_password)
 
     def load(self, data, file_name='<string>', show_content=True):
         '''
@@ -151,7 +151,7 @@ class DataLoader():
     def _safe_load(self, stream, file_name=None):
         ''' Implements yaml.safe_load(), except using our custom loader class. '''
 
-        loader = AnsibleLoader(stream, file_name, self._vault_password)
+        loader = AnsibleLoader(stream, file_name, self._b_vault_password)
         try:
             return loader.get_single_data()
         finally:
@@ -359,7 +359,7 @@ class DataLoader():
                 raise AnsibleError("Problem running vault password script %s (%s)."
                         " If this is not a script, remove the executable bit from the file." % (' '.join(this_path), to_native(e)))
             stdout, stderr = p.communicate()
-            self.set_vault_password(stdout.strip('\r\n'))
+            self.set_vault_password(stdout.strip(b'\r\n'))
         else:
             try:
                 f = open(this_path, "rb")
@@ -397,7 +397,7 @@ class DataLoader():
             raise AnsibleFileNotFound("the file_name '%s' does not exist, or is not readable" % to_native(file_path))
 
         if not self._vault:
-            self._vault = VaultLib(password="")
+            self._vault = VaultLib(b_password="")
 
         real_path = self.path_dwim(file_path)
 
@@ -411,7 +411,7 @@ class DataLoader():
                     # the decrypt call would throw an error, but we check first
                     # since the decrypt function doesn't know the file name
                     data = f.read()
-                    if not self._vault_password:
+                    if not self._b_vault_password:
                         raise AnsibleParserError("A vault password must be specified to decrypt %s" % file_path)
 
                     data = self._vault.decrypt(data, filename=real_path)
diff --git a/lib/ansible/parsing/vault/__init__.py b/lib/ansible/parsing/vault/__init__.py
index fcab458fce..8ce705c8a6 100644
--- a/lib/ansible/parsing/vault/__init__.py
+++ b/lib/ansible/parsing/vault/__init__.py
@@ -164,8 +164,8 @@ def is_encrypted_file(file_obj, start_pos=0, count=-1):
 
 class VaultLib:
 
-    def __init__(self, password):
-        self.b_password = to_bytes(password, errors='strict', encoding='utf-8')
+    def __init__(self, b_password):
+        self.b_password = to_bytes(b_password, errors='strict', encoding='utf-8')
         self.cipher_name = None
         self.b_version = b'1.1'
 
@@ -311,8 +311,8 @@ class VaultLib:
 
 class VaultEditor:
 
-    def __init__(self, password):
-        self.vault = VaultLib(password)
+    def __init__(self, b_password):
+        self.vault = VaultLib(b_password)
 
     # TODO: mv shred file stuff to it's own class
     def _shred_file_custom(self, tmp_path):
@@ -475,7 +475,7 @@ class VaultEditor:
 
         return plaintext
 
-    def rekey_file(self, filename, new_password):
+    def rekey_file(self, filename, b_new_password):
 
         check_prereqs()
 
@@ -487,10 +487,10 @@ class VaultEditor:
             raise AnsibleError("%s for %s" % (to_bytes(e),to_bytes(filename)))
 
         # This is more or less an assert, see #18247
-        if new_password is None:
+        if b_new_password is None:
             raise AnsibleError('The value for the new_password to rekey %s with is not valid' % filename)
 
-        new_vault = VaultLib(new_password)
+        new_vault = VaultLib(b_new_password)
         new_ciphertext = new_vault.encrypt(plaintext)
 
         self.write_data(new_ciphertext, filename)
diff --git a/lib/ansible/parsing/yaml/constructor.py b/lib/ansible/parsing/yaml/constructor.py
index 0a53fb1c7f..eb836c842c 100644
--- a/lib/ansible/parsing/yaml/constructor.py
+++ b/lib/ansible/parsing/yaml/constructor.py
@@ -36,12 +36,12 @@ except ImportError:
 
 
 class AnsibleConstructor(Constructor):
-    def __init__(self, file_name=None, vault_password=None):
-        self._vault_password = vault_password
+    def __init__(self, file_name=None, b_vault_password=None):
+        self._b_vault_password = b_vault_password
         self._ansible_file_name = file_name
         super(AnsibleConstructor, self).__init__()
         self._vaults = {}
-        self._vaults['default'] = VaultLib(password=self._vault_password)
+        self._vaults['default'] = VaultLib(b_password=self._b_vault_password)
 
     def construct_yaml_map(self, node):
         data = AnsibleMapping()
@@ -98,7 +98,7 @@ class AnsibleConstructor(Constructor):
         value = self.construct_scalar(node)
         ciphertext_data = to_bytes(value)
 
-        if self._vault_password is None:
+        if self._b_vault_password is None:
             raise ConstructorError(None, None,
                     "found vault but no vault password provided", node.start_mark)
 
diff --git a/lib/ansible/parsing/yaml/loader.py b/lib/ansible/parsing/yaml/loader.py
index 050e9f0553..7ff309d82c 100644
--- a/lib/ansible/parsing/yaml/loader.py
+++ b/lib/ansible/parsing/yaml/loader.py
@@ -34,7 +34,7 @@ if HAVE_PYYAML_C:
     class AnsibleLoader(CParser, AnsibleConstructor, Resolver):
         def __init__(self, stream, file_name=None, vault_password=None):
             CParser.__init__(self, stream)
-            AnsibleConstructor.__init__(self, file_name=file_name, vault_password=vault_password)
+            AnsibleConstructor.__init__(self, file_name=file_name, b_vault_password=vault_password)
             Resolver.__init__(self)
 else:
     from yaml.composer import Composer
@@ -48,5 +48,5 @@ else:
             Scanner.__init__(self)
             Parser.__init__(self)
             Composer.__init__(self)
-            AnsibleConstructor.__init__(self, file_name=file_name, vault_password=vault_password)
+            AnsibleConstructor.__init__(self, file_name=file_name, b_vault_password=vault_password)
             Resolver.__init__(self)