From 90b34140929bafabaed5776548912a48aa3e45cb Mon Sep 17 00:00:00 2001
From: Tim Burke <tim.burke@gmail.com>
Date: Fri, 20 Apr 2018 19:34:29 +0000
Subject: [PATCH] Verify client input for v4 signatures

Previously, we would use the X-Amz-Content-SHA256 value when calculating
signatures, but wouldn't actually check the content that was sent. This
would allow a malicious third party that managed to capture the headers
for an object upload to overwrite that with arbitrary content provided
they could do so within the 5-minute clock-skew window.

Now, we wrap the wsgi.input that's sent on to the proxy-server app to
hash content as it's read and raise an error if there's a mismatch. Note
that clients using presigned-urls to upload have no defense against a
similar replay attack.

Notwithstanding the above security consideration, this *also* provides
better assurances that the client's payload was received correctly. Note
that this *does not* attempt to send an etag in footers, however, so the
proxy-to-object-server connection is not guarded against bit-flips.

In the future, Swift will hopefully grow a way to perform SHA256
verification on the object-server. This would offer two main benefits:

  - End-to-end message integrity checking.
  - Move CPU load of claculating the hash from the proxy (which is
    somewhat CPU-bound) to the object-server (which tends to have CPU to
    spare).

Change-Id: Ibe92bffaf9ea5e8e0a1148afed9def6430aac2e9
---
 swift3/request.py | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/swift3/request.py b/swift3/request.py
index 7a2936e..16241cf 100644
--- a/swift3/request.py
+++ b/swift3/request.py
@@ -14,6 +14,7 @@
 # limitations under the License.
 
 import base64
+import binascii
 from collections import defaultdict
 from email.header import Header
 from hashlib import sha1, sha256, md5
@@ -108,6 +109,32 @@ def _header_acl_property(resource):
                     doc='Get and set the %s acl property' % resource)
 
 
+class HashingInput(object):
+    """
+    wsgi.input wrapper to verify the hash of the input as it's read.
+    """
+    def __init__(self, reader, content_length, hasher, expected_hash):
+        self._input = reader
+        self._to_read = content_length
+        self._hasher = hasher()
+        self._expected = expected_hash
+
+    def read(self, size):
+        chunk = self._input.read(size)
+        self._hasher.update(chunk)
+        self._to_read -= len(chunk)
+        if self._to_read < 0 or (self._to_read == 0 and
+                                 self._hasher.digest() != self._expected):
+            raise swob.HTTPUnprocessableEntity(
+                'The X-Amz-Content-SHA56 you specified did not match '
+                'what we received.')
+        return chunk
+
+    def close(self):
+        if hasattr(self._input, 'close'):
+            self._input.close()
+
+
 class SigV4Mixin(object):
     """
     A request class mixin to provide S3 signature v4 functionality
@@ -356,6 +383,18 @@ class SigV4Mixin(object):
             raise InvalidRequest(msg)
         else:
             hashed_payload = self.headers['X-Amz-Content-SHA256']
+            if self.content_length == 0:
+                if hashed_payload != sha256().hexdigest():
+                    raise BadDigest(
+                        'The X-Amz-Content-SHA56 you specified did not match '
+                        'what we received.')
+            elif self.content_length:
+                self.environ['wsgi.input'] = HashingInput(
+                    self.environ['wsgi.input'],
+                    self.content_length,
+                    sha256,
+                    binascii.unhexlify(hashed_payload))
+            # else, not provided -- we send back a 411... somehwere...
         cr.append(hashed_payload)
         return '\n'.join(cr).encode('utf-8')
 
-- 
1.9.1