bpo-44022: Fix http client infinite line reading (DoS) after a HTTP 100 Continue (GH-25916)

Fixes http.client potential denial of service where it could get stuck reading lines from a malicious server after a 100 Continue response.

Co-authored-by: Gregory P. Smith <greg@krypto.org>

1 files changed, 21 insertions, 17 deletions

diff --git a/Lib/http/client.py b/Lib/http/client.py
index 4b1f692..08cf2ed 100644
--- a/Lib/http/client.py
+++ b/Lib/http/client.py
@@ -202,15 +202,11 @@ class HTTPMessage(email.message.Message):
                 lst.append(line)
         return lst
 
-def parse_headers(fp, _class=HTTPMessage):
-    """Parses only RFC2822 headers from a file pointer.
-
-    email Parser wants to see strings rather than bytes.
-    But a TextIOWrapper around self.rfile would buffer too many bytes
-    from the stream, bytes which we later need to read as bytes.
-    So we read the correct bytes here, as bytes, for email Parser
-    to parse.
+def _read_headers(fp):
+    """Reads potential header lines into a list from a file pointer.
 
+    Length of line is limited by _MAXLINE, and number of
+    headers is limited by _MAXHEADERS.
     """
     headers = []
     while True:
@@ -222,6 +218,19 @@ def parse_headers(fp, _class=HTTPMessage):
             raise HTTPException("got more than %d headers" % _MAXHEADERS)
         if line in (b'\r\n', b'\n', b''):
             break
+    return headers
+
+def parse_headers(fp, _class=HTTPMessage):
+    """Parses only RFC2822 headers from a file pointer.
+
+    email Parser wants to see strings rather than bytes.
+    But a TextIOWrapper around self.rfile would buffer too many bytes
+    from the stream, bytes which we later need to read as bytes.
+    So we read the correct bytes here, as bytes, for email Parser
+    to parse.
+
+    """
+    headers = _read_headers(fp)
     hstring = b''.join(headers).decode('iso-8859-1')
     return email.parser.Parser(_class=_class).parsestr(hstring)
 
@@ -309,15 +318,10 @@ class HTTPResponse(io.BufferedIOBase):
             if status != CONTINUE:
                 break
             # skip the header from the 100 response
-            while True:
-                skip = self.fp.readline(_MAXLINE + 1)
-                if len(skip) > _MAXLINE:
-                    raise LineTooLong("header line")
-                skip = skip.strip()
-                if not skip:
-                    break
-                if self.debuglevel > 0:
-                    print("header:", skip)
+            skipped_headers = _read_headers(self.fp)
+            if self.debuglevel > 0:
+                print("headers:", skipped_headers)
+            del skipped_headers
 
         self.code = self.status = status
         self.reason = reason.strip()