Compare varnullingrels too in assign_param_for_var().

Oversight in 2489d76.  Preliminary analysis suggests that the
problem may be unreachable --- but if we did have instances of
the same column with different varnullingrels, we'd surely need
to treat them as different Params.

Discussion: https://postgr.es/m/412552.1706203379@sss.pgh.pa.us

Author: tglsfdc

src/backend/optimizer/util/paramassign.c

@@ -90,7 +90,8 @@ assign_param_for_var(PlannerInfo *root, Var *var)
 				pvar->varattno == var->varattno &&
 				pvar->vartype == var->vartype &&
 				pvar->vartypmod == var->vartypmod &&
-				pvar->varcollid == var->varcollid)
+				pvar->varcollid == var->varcollid &&
+				bms_equal(pvar->varnullingrels, var->varnullingrels))
 				return pitem->paramId;
 		}
 	}