Replace usages of xmlXPathCompile() with xmlXPathCtxtCompile().

tglsfdc · tglsfdc · commit d5622acb32b3 · 2024-09-15T13:33:09.000-04:00
In existing releases of libxml2, xmlXPathCompile can be driven to stack overflow because it fails to protect itself against too-deeply-nested input. While there is an upstream fix as of yesterday, it will take years for that to propagate into all shipping versions. In the meantime, we can protect our own usages basically for free by calling xmlXPathCtxtCompile instead. (The actual bug is that libxml2 keeps its nesting counter in the xmlXPathContext, and its parsing code was willing to just skip counting nesting levels if it didn't have a context. So if we supply a context, all is well. It seems odd actually that it works at all to not supply a context, because this means that XPath parsing does not have access to XML namespace info. Apparently libxml2 never checks namespaces until runtime? Anyway, this seems like good future-proofing even if its only immediate effect is to dodge a bug.) Sadly, this hack only offers protection with libxml2 2.9.11 and newer. Before that there are multiple similar problems, so if you are processing untrusted XML it behooves you to get a newer version. But we have some pretty old libxml2 in the buildfarm, so it seems impractical to add a regression test to verify this fix. Per bug #18617 from Jingzhou Fu. Back-patch to all supported versions. Discussion: https://postgr.es/m/18617-1cee4d2ed1f4e7ae@postgresql.org Discussion: https://gitlab.gnome.org/GNOME/libxml2/-/issues/799
diff --git a/contrib/xml2/xpath.c b/contrib/xml2/xpath.c
@@ -386,7 +386,7 @@ pgxml_xpath(text *document, xmlChar *xpath, xpath_workspace *workspace)
 			workspace->ctxt->node = xmlDocGetRootElement(workspace->doctree);
 
 			/* compile the path */
-			comppath = xmlXPathCompile(xpath);
+			comppath = xmlXPathCtxtCompile(workspace->ctxt, xpath);
 			if (comppath == NULL)
 				xml_ereport(xmlerrcxt, ERROR, ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
 							"XPath Syntax Error");
@@ -649,7 +649,7 @@ xpath_table(PG_FUNCTION_ARGS)
 						ctxt->node = xmlDocGetRootElement(doctree);
 
 						/* compile the path */
-						comppath = xmlXPathCompile(xpaths[j]);
+						comppath = xmlXPathCtxtCompile(ctxt, xpaths[j]);
 						if (comppath == NULL)
 							xml_ereport(xmlerrcxt, ERROR,
 										ERRCODE_EXTERNAL_ROUTINE_EXCEPTION,
diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c
@@ -4448,7 +4448,13 @@ xpath_internal(text *xpath_expr_text, xmltype *data, ArrayType *namespaces,
 			}
 		}
 
-		xpathcomp = xmlXPathCompile(xpath_expr);
+		/*
+		 * Note: here and elsewhere, be careful to use xmlXPathCtxtCompile not
+		 * xmlXPathCompile.  In libxml2 2.13.3 and older, the latter function
+		 * fails to defend itself against recursion-to-stack-overflow.  See
+		 * https://gitlab.gnome.org/GNOME/libxml2/-/issues/799
+		 */
+		xpathcomp = xmlXPathCtxtCompile(xpathctx, xpath_expr);
 		if (xpathcomp == NULL || xmlerrcxt->err_occurred)
 			xml_ereport(xmlerrcxt, ERROR, ERRCODE_INTERNAL_ERROR,
 						"invalid XPath expression");
@@ -4819,7 +4825,10 @@ XmlTableSetRowFilter(TableFuncScanState *state, const char *path)
 
 	xstr = pg_xmlCharStrndup(path, strlen(path));
 
-	xtCxt->xpathcomp = xmlXPathCompile(xstr);
+	/* We require XmlTableSetDocument to have been done already */
+	Assert(xtCxt->xpathcxt != NULL);
+
+	xtCxt->xpathcomp = xmlXPathCtxtCompile(xtCxt->xpathcxt, xstr);
 	if (xtCxt->xpathcomp == NULL || xtCxt->xmlerrcxt->err_occurred)
 		xml_ereport(xtCxt->xmlerrcxt, ERROR, ERRCODE_SYNTAX_ERROR,
 					"invalid XPath expression");
@@ -4850,7 +4859,10 @@ XmlTableSetColumnFilter(TableFuncScanState *state, const char *path, int colnum)
 
 	xstr = pg_xmlCharStrndup(path, strlen(path));
 
-	xtCxt->xpathscomp[colnum] = xmlXPathCompile(xstr);
+	/* We require XmlTableSetDocument to have been done already */
+	Assert(xtCxt->xpathcxt != NULL);
+
+	xtCxt->xpathscomp[colnum] = xmlXPathCtxtCompile(xtCxt->xpathcxt, xstr);
 	if (xtCxt->xpathscomp[colnum] == NULL || xtCxt->xmlerrcxt->err_occurred)
 		xml_ereport(xtCxt->xmlerrcxt, ERROR, ERRCODE_DATA_EXCEPTION,
 					"invalid XPath expression");
