diff --git a/py/test/plugin/pytest_default.py b/py/test/plugin/pytest_default.py
index 209fa3527..235bc6c5c 100644
--- a/py/test/plugin/pytest_default.py
+++ b/py/test/plugin/pytest_default.py
@@ -114,6 +114,10 @@ class DefaultPlugin:
             from py.__.test.dsession.dsession import  DSession
             config.setsessionclass(DSession)
 
+    def pytest_item_makereport(self, item, excinfo, when, outerr):
+        from py.__.test import event
+        return event.ItemTestReport(item, excinfo, when, outerr)
+
 def test_implied_different_sessions(tmpdir):
     def x(*args):
         config = py.test.config._reparse([tmpdir] + list(args))
diff --git a/py/test/plugin/pytest_plugintester.py b/py/test/plugin/pytest_plugintester.py
index eb3986dbb..0b9b432d2 100644
--- a/py/test/plugin/pytest_plugintester.py
+++ b/py/test/plugin/pytest_plugintester.py
@@ -60,6 +60,8 @@ class PluginTester(Support):
                 if not hasattr(hook, 'func_code'):
                     continue # XXX do some checks on attributes as well? 
                 method_args = getargs(method.func_code) 
+                if '__call__' in method_args[0]:
+                    method_args[0].remove('__call__')
                 hookargs = getargs(hook.func_code)
                 for arg, hookarg in zip(method_args[0], hookargs[0]):
                     if arg != hookarg: 
@@ -119,6 +121,9 @@ class PytestPluginHooks:
     def pytest_pyfunc_call(self, pyfuncitem, args, kwargs):
         """ return True if we consumed/did the call to the python function item. """
 
+    def pytest_item_makereport(self, item, excinfo, when, outerr):
+        """ return ItemTestReport event for the given test outcome. """
+
     # collection hooks
     def pytest_collect_file(self, path, parent):
         """ return Collection node or None. """
@@ -134,6 +139,11 @@ class PytestPluginHooks:
     def pytest_pymodule_makeitem(self, modcol, name, obj):
         """ return custom item/collector for a python object in a module, or None.  """
 
+
+    # from pytest_terminal plugin
+    def pytest_report_teststatus(self, event):
+        """ return shortletter and verbose word. """
+
     # from pytest_terminal plugin
     def pytest_report_teststatus(self, event):
         """ return shortletter and verbose word. """
diff --git a/py/test/plugin/pytest_xfail.py b/py/test/plugin/pytest_xfail.py
index 87fe0d716..208d2e31c 100644
--- a/py/test/plugin/pytest_xfail.py
+++ b/py/test/plugin/pytest_xfail.py
@@ -9,12 +9,25 @@ import py
 
 class XfailPlugin(object):
     """ mark and report specially about "expected to fail" tests. """
+
+    def pytest_item_makereport(self, __call__, item, excinfo, when, outerr):
+        if hasattr(item, 'obj') and hasattr(item.obj, 'func_dict'):
+            if 'xfail' in item.obj.func_dict:
+                res = __call__.execute(firstresult=True)
+                if excinfo:
+                    res.skipped = True
+                    res.failed = res.passed = False
+                else:
+                    res.skipped = res.passed = False
+                    res.failed = True
+                return res 
+
     def pytest_report_teststatus(self, event):
         """ return shortletter and verbose word. """
         if 'xfail' in event.keywords: 
-            if event.failed:
+            if event.skipped:
                 return "xfailed", "x", "xfail"
-            else:
+            elif event.failed:
                 return "xpassed", "P", "xpass" 
 
     # a hook implemented called by the terminalreporter instance/plugin
@@ -22,7 +35,7 @@ class XfailPlugin(object):
         tr = terminalreporter
         xfailed = tr.stats.get("xfailed")
         if xfailed:
-            tr.write_sep("_", "EXPECTED XFAILURES")
+            tr.write_sep("_", "expected failures")
             for event in xfailed:
                 entry = event.longrepr.reprcrash 
                 key = entry.path, entry.lineno, entry.message
@@ -33,7 +46,7 @@ class XfailPlugin(object):
 
         xpassed = terminalreporter.stats.get("xpassed")
         if xpassed:
-            tr.write_sep("_", "UNEXPECTEDLY PASSING")
+            tr.write_sep("_", "UNEXPECTEDLY PASSING TESTS")
             for event in xpassed:
                 tr._tw.line("%s: xpassed" %(event.colitem,))
 
@@ -54,10 +67,16 @@ def test_xfail(plugintester, linecomp):
         @py.test.mark.xfail
         def test_this():
             assert 0
+
+        @py.test.mark.xfail
+        def test_that():
+            assert 1
     """)
     result = testdir.runpytest(p)
     extra = result.stdout.fnmatch_lines([
-        "*XFAILURES*",
+        "*expected failures*",
         "*test_one.test_this*test_one.py:5*",
+        "*UNEXPECTEDLY PASSING*",
+        "*test_that*",
     ])
     assert result.ret == 1
diff --git a/py/test/runner.py b/py/test/runner.py
index e1c20c01e..cf01c012f 100644
--- a/py/test/runner.py
+++ b/py/test/runner.py
@@ -59,7 +59,9 @@ class ItemRunner(RobustRun):
         #self.colitem.config.pytestplugins.post_execute(self.colitem)
 
     def makereport(self, res, when, excinfo, outerr):
-        testrep = event.ItemTestReport(self.colitem, excinfo, when, outerr)
+        testrep = self.colitem._config.pytestplugins.call_firstresult(
+            "pytest_item_makereport", item=self.colitem, 
+            excinfo=excinfo, when=when, outerr=outerr)
         if self.pdb and testrep.failed:
             tw = py.io.TerminalWriter()
             testrep.toterminal(tw)