commit 1b41ec4e9433b05bb0376be4725804c54ef1d80b
author Nick Wellnhofer <wellnhofer@aevum.de> Wed Aug 31 22:11:25 2022 +0200
committer Nick Wellnhofer <wellnhofer@aevum.de> Fri Oct 14 14:26:57 2022 +0200
tree a0403fa4a485c35513feb0bd9e7a46e5a3e87353
parent c846986356fc149915a74972bf198abc266bc2c0

[CVE-2022-40304] Fix dict corruption caused by entity reference cycles

When an entity reference cycle is detected, the entity content is
cleared by setting its first byte to zero. But the entity content might
be allocated from a dict. In this case, the dict entry becomes corrupted
leading to all kinds of logic errors, including memory errors like
double-frees.

Stop storing entity content, orig, ExternalID and SystemID in a dict.
These values are unlikely to occur multiple times in a document, so they
shouldn't have been stored in a dict in the first place.

Thanks to Ned Williamson and Nathan Wachholz working with Google Project
Zero for the report!

entities.c

diff --git a/entities.c b/entities.c
index 8443551..d4e5412 100644
--- a/entities.c
+++ b/entities.c
@@ -128,36 +128,19 @@
     if ((entity->children) && (entity->owner == 1) &&
         (entity == (xmlEntityPtr) entity->children->parent))
         xmlFreeNodeList(entity->children);
-    if (dict != NULL) {
-        if ((entity->name != NULL) && (!xmlDictOwns(dict, entity->name)))
-            xmlFree((char *) entity->name);
-        if ((entity->ExternalID != NULL) &&
-	    (!xmlDictOwns(dict, entity->ExternalID)))
-            xmlFree((char *) entity->ExternalID);
-        if ((entity->SystemID != NULL) &&
-	    (!xmlDictOwns(dict, entity->SystemID)))
-            xmlFree((char *) entity->SystemID);
-        if ((entity->URI != NULL) && (!xmlDictOwns(dict, entity->URI)))
-            xmlFree((char *) entity->URI);
-        if ((entity->content != NULL)
-            && (!xmlDictOwns(dict, entity->content)))
-            xmlFree((char *) entity->content);
-        if ((entity->orig != NULL) && (!xmlDictOwns(dict, entity->orig)))
-            xmlFree((char *) entity->orig);
-    } else {
-        if (entity->name != NULL)
-            xmlFree((char *) entity->name);
-        if (entity->ExternalID != NULL)
-            xmlFree((char *) entity->ExternalID);
-        if (entity->SystemID != NULL)
-            xmlFree((char *) entity->SystemID);
-        if (entity->URI != NULL)
-            xmlFree((char *) entity->URI);
-        if (entity->content != NULL)
-            xmlFree((char *) entity->content);
-        if (entity->orig != NULL)
-            xmlFree((char *) entity->orig);
-    }
+    if ((entity->name != NULL) &&
+        ((dict == NULL) || (!xmlDictOwns(dict, entity->name))))
+        xmlFree((char *) entity->name);
+    if (entity->ExternalID != NULL)
+        xmlFree((char *) entity->ExternalID);
+    if (entity->SystemID != NULL)
+        xmlFree((char *) entity->SystemID);
+    if (entity->URI != NULL)
+        xmlFree((char *) entity->URI);
+    if (entity->content != NULL)
+        xmlFree((char *) entity->content);
+    if (entity->orig != NULL)
+        xmlFree((char *) entity->orig);
     xmlFree(entity);
 }
 
@@ -193,18 +176,12 @@
 	    ret->SystemID = xmlStrdup(SystemID);
     } else {
         ret->name = xmlDictLookup(dict, name, -1);
-	if (ExternalID != NULL)
-	    ret->ExternalID = xmlDictLookup(dict, ExternalID, -1);
-	if (SystemID != NULL)
-	    ret->SystemID = xmlDictLookup(dict, SystemID, -1);
+	ret->ExternalID = xmlStrdup(ExternalID);
+	ret->SystemID = xmlStrdup(SystemID);
     }
     if (content != NULL) {
         ret->length = xmlStrlen(content);
-	if ((dict != NULL) && (ret->length < 5))
-	    ret->content = (xmlChar *)
-	                   xmlDictLookup(dict, content, ret->length);
-	else
-	    ret->content = xmlStrndup(content, ret->length);
+	ret->content = xmlStrndup(content, ret->length);
      } else {
         ret->length = 0;
         ret->content = NULL;