# HG changeset patch
# User Gregory Szorc <gregory.szorc@gmail.com>
# Date 2018-11-13 20:30:59
# Node ID 87a872555e908f95ce4f2bfff6559f899db2cf2e
# Parent  39369475445cd11b7e0e4c2b2081560b29478d18

revlog: detect incomplete revlog reads

_readsegment() is supposed to return N bytes of revlog revision
data starting at a file offset. Surprisingly, its behavior before
this patch never verified that it actually read and returned N
bytes! Instead, it would perform the read(), then return whatever
data was available. And even more surprisingly, nothing in the
call chain appears to have been validating that it received all
the data it was expecting.

This behavior could lead to partial or incomplete revision chunks
being operated on. This could result in e.g. cached deltas being
applied against incomplete base revisions. The delta application
process would happily perform this operation. Only hash
verification would detect the corruption and save us.

This commit changes the behavior of raw revlog reading to validate
that we actually read() the number of bytes that were requested.
We will raise a more specific error faster, rather than possibly
have it go undetected or manifest later in the call stack, at
delta application or hash verification.

Differential Revision: https://phab.mercurial-scm.org/D5266

diff --git a/mercurial/revlog.py b/mercurial/revlog.py
--- a/mercurial/revlog.py
+++ b/mercurial/revlog.py
@@ -1342,6 +1342,8 @@ class revlog(object):
         original seek position will NOT be restored.
 
         Returns a str or buffer of raw byte data.
+
+        Raises if the requested number of bytes could not be read.
         """
         # Cache data both forward and backward around the requested
         # data, in a fixed size window. This helps speed up operations
@@ -1353,9 +1355,26 @@ class revlog(object):
         with self._datareadfp(df) as df:
             df.seek(realoffset)
             d = df.read(reallength)
+
         self._cachesegment(realoffset, d)
         if offset != realoffset or reallength != length:
-            return util.buffer(d, offset - realoffset, length)
+            startoffset = offset - realoffset
+            if len(d) - startoffset < length:
+                raise error.RevlogError(
+                    _('partial read of revlog %s; expected %d bytes from '
+                      'offset %d, got %d') %
+                    (self.indexfile if self._inline else self.datafile,
+                     length, realoffset, len(d) - startoffset))
+
+            return util.buffer(d, startoffset, length)
+
+        if len(d) < length:
+            raise error.RevlogError(
+                _('partial read of revlog %s; expected %d bytes from offset '
+                  '%d, got %d') %
+                (self.indexfile if self._inline else self.datafile,
+                 length, offset, len(d)))
+
         return d
 
     def _getsegment(self, offset, length, df=None):