diff --git a/src/_pytest/stepwise.py b/src/_pytest/stepwise.py
index f408e1fa9..9af975ce1 100644
--- a/src/_pytest/stepwise.py
+++ b/src/_pytest/stepwise.py
@@ -3,28 +3,37 @@ import pytest
 
 
 def pytest_addoption(parser):
-    group = parser.getgroup('general')
-    group.addoption('--sw', '--stepwise', action='store_true', dest='stepwise',
-                    help='exit on test fail and continue from last failing test next time')
-    group.addoption('--stepwise-skip', action='store_true', dest='stepwise_skip',
-                    help='ignore the first failing test but stop on the next failing test')
+    group = parser.getgroup("general")
+    group.addoption(
+        "--sw",
+        "--stepwise",
+        action="store_true",
+        dest="stepwise",
+        help="exit on test fail and continue from last failing test next time",
+    )
+    group.addoption(
+        "--stepwise-skip",
+        action="store_true",
+        dest="stepwise_skip",
+        help="ignore the first failing test but stop on the next failing test",
+    )
 
 
 @pytest.hookimpl(tryfirst=True)
 def pytest_configure(config):
     config.cache = Cache.for_config(config)
-    config.pluginmanager.register(StepwisePlugin(config), 'stepwiseplugin')
+    config.pluginmanager.register(StepwisePlugin(config), "stepwiseplugin")
 
 
 class StepwisePlugin:
     def __init__(self, config):
         self.config = config
-        self.active = config.getvalue('stepwise')
+        self.active = config.getvalue("stepwise")
         self.session = None
 
         if self.active:
-            self.lastfailed = config.cache.get('cache/stepwise', None)
-            self.skip = config.getvalue('stepwise_skip')
+            self.lastfailed = config.cache.get("cache/stepwise", None)
+            self.skip = config.getvalue("stepwise_skip")
 
     def pytest_sessionstart(self, session):
         self.session = session
@@ -56,11 +65,13 @@ class StepwisePlugin:
 
     def pytest_collectreport(self, report):
         if self.active and report.failed:
-            self.session.shouldstop = 'Error when collecting test, stopping test execution.'
+            self.session.shouldstop = (
+                "Error when collecting test, stopping test execution."
+            )
 
     def pytest_runtest_logreport(self, report):
         # Skip this hook if plugin is not active or the test is xfailed.
-        if not self.active or 'xfail' in report.keywords:
+        if not self.active or "xfail" in report.keywords:
             return
 
         if report.failed:
@@ -74,18 +85,20 @@ class StepwisePlugin:
             else:
                 # Mark test as the last failing and interrupt the test session.
                 self.lastfailed = report.nodeid
-                self.session.shouldstop = 'Test failed, continuing from this test next run.'
+                self.session.shouldstop = (
+                    "Test failed, continuing from this test next run."
+                )
 
         else:
             # If the test was actually run and did pass.
-            if report.when == 'call':
+            if report.when == "call":
                 # Remove test from the failed ones, if exists.
                 if report.nodeid == self.lastfailed:
                     self.lastfailed = None
 
     def pytest_sessionfinish(self, session):
         if self.active:
-            self.config.cache.set('cache/stepwise', self.lastfailed)
+            self.config.cache.set("cache/stepwise", self.lastfailed)
         else:
             # Clear the list of failing tests if the plugin is not active.
-            self.config.cache.set('cache/stepwise', [])
+            self.config.cache.set("cache/stepwise", [])
diff --git a/testing/test_stepwise.py b/testing/test_stepwise.py
index 0e1e53226..0e52911f4 100644
--- a/testing/test_stepwise.py
+++ b/testing/test_stepwise.py
@@ -5,15 +5,18 @@ import pytest
 def stepwise_testdir(testdir):
     # Rather than having to modify our testfile between tests, we introduce
     # a flag for wether or not the second test should fail.
-    testdir.makeconftest('''
+    testdir.makeconftest(
+        """
 def pytest_addoption(parser):
     group = parser.getgroup('general')
     group.addoption('--fail', action='store_true', dest='fail')
     group.addoption('--fail-last', action='store_true', dest='fail_last')
-''')
+"""
+    )
 
     # Create a simple test suite.
-    testdir.makepyfile(test_a='''
+    testdir.makepyfile(
+        test_a="""
 def test_success_before_fail():
     assert 1
 
@@ -28,111 +31,121 @@ def test_fail_last_on_flag(request):
 
 def test_success_after_last_fail():
     assert 1
-''')
+"""
+    )
 
-    testdir.makepyfile(test_b='''
+    testdir.makepyfile(
+        test_b="""
 def test_success():
     assert 1
-''')
+"""
+    )
 
     return testdir
 
 
 @pytest.fixture
 def error_testdir(testdir):
-    testdir.makepyfile(test_a='''
+    testdir.makepyfile(
+        test_a="""
 def test_error(nonexisting_fixture):
     assert 1
 
 def test_success_after_fail():
     assert 1
-''')
+"""
+    )
 
     return testdir
 
 
 @pytest.fixture
 def broken_testdir(testdir):
-    testdir.makepyfile(working_testfile='def test_proper(): assert 1', broken_testfile='foobar')
+    testdir.makepyfile(
+        working_testfile="def test_proper(): assert 1", broken_testfile="foobar"
+    )
     return testdir
 
 
 def test_run_without_stepwise(stepwise_testdir):
-    result = stepwise_testdir.runpytest('-v', '--strict', '--fail')
+    result = stepwise_testdir.runpytest("-v", "--strict", "--fail")
 
-    result.stdout.fnmatch_lines(['*test_success_before_fail PASSED*'])
-    result.stdout.fnmatch_lines(['*test_fail_on_flag FAILED*'])
-    result.stdout.fnmatch_lines(['*test_success_after_fail PASSED*'])
+    result.stdout.fnmatch_lines(["*test_success_before_fail PASSED*"])
+    result.stdout.fnmatch_lines(["*test_fail_on_flag FAILED*"])
+    result.stdout.fnmatch_lines(["*test_success_after_fail PASSED*"])
 
 
 def test_fail_and_continue_with_stepwise(stepwise_testdir):
     # Run the tests with a failing second test.
-    result = stepwise_testdir.runpytest('-v', '--strict', '--stepwise', '--fail')
+    result = stepwise_testdir.runpytest("-v", "--strict", "--stepwise", "--fail")
     assert not result.stderr.str()
 
     stdout = result.stdout.str()
     # Make sure we stop after first failing test.
-    assert 'test_success_before_fail PASSED' in stdout
-    assert 'test_fail_on_flag FAILED' in stdout
-    assert 'test_success_after_fail' not in stdout
+    assert "test_success_before_fail PASSED" in stdout
+    assert "test_fail_on_flag FAILED" in stdout
+    assert "test_success_after_fail" not in stdout
 
     # "Fix" the test that failed in the last run and run it again.
-    result = stepwise_testdir.runpytest('-v', '--strict', '--stepwise')
+    result = stepwise_testdir.runpytest("-v", "--strict", "--stepwise")
     assert not result.stderr.str()
 
     stdout = result.stdout.str()
     # Make sure the latest failing test runs and then continues.
-    assert 'test_success_before_fail' not in stdout
-    assert 'test_fail_on_flag PASSED' in stdout
-    assert 'test_success_after_fail PASSED' in stdout
+    assert "test_success_before_fail" not in stdout
+    assert "test_fail_on_flag PASSED" in stdout
+    assert "test_success_after_fail PASSED" in stdout
 
 
 def test_run_with_skip_option(stepwise_testdir):
-    result = stepwise_testdir.runpytest('-v', '--strict', '--stepwise', '--stepwise-skip',
-                                        '--fail', '--fail-last')
+    result = stepwise_testdir.runpytest(
+        "-v", "--strict", "--stepwise", "--stepwise-skip", "--fail", "--fail-last"
+    )
     assert not result.stderr.str()
 
     stdout = result.stdout.str()
     # Make sure first fail is ignore and second fail stops the test run.
-    assert 'test_fail_on_flag FAILED' in stdout
-    assert 'test_success_after_fail PASSED' in stdout
-    assert 'test_fail_last_on_flag FAILED' in stdout
-    assert 'test_success_after_last_fail' not in stdout
+    assert "test_fail_on_flag FAILED" in stdout
+    assert "test_success_after_fail PASSED" in stdout
+    assert "test_fail_last_on_flag FAILED" in stdout
+    assert "test_success_after_last_fail" not in stdout
 
 
 def test_fail_on_errors(error_testdir):
-    result = error_testdir.runpytest('-v', '--strict', '--stepwise')
+    result = error_testdir.runpytest("-v", "--strict", "--stepwise")
 
     assert not result.stderr.str()
     stdout = result.stdout.str()
 
-    assert 'test_error ERROR' in stdout
-    assert 'test_success_after_fail' not in stdout
+    assert "test_error ERROR" in stdout
+    assert "test_success_after_fail" not in stdout
 
 
 def test_change_testfile(stepwise_testdir):
-    result = stepwise_testdir.runpytest('-v', '--strict', '--stepwise', '--fail',
-                                        'test_a.py')
+    result = stepwise_testdir.runpytest(
+        "-v", "--strict", "--stepwise", "--fail", "test_a.py"
+    )
     assert not result.stderr.str()
 
     stdout = result.stdout.str()
-    assert 'test_fail_on_flag FAILED' in stdout
+    assert "test_fail_on_flag FAILED" in stdout
 
     # Make sure the second test run starts from the beginning, since the
     # test to continue from does not exist in testfile_b.
-    result = stepwise_testdir.runpytest('-v', '--strict', '--stepwise',
-                                        'test_b.py')
+    result = stepwise_testdir.runpytest("-v", "--strict", "--stepwise", "test_b.py")
     assert not result.stderr.str()
 
     stdout = result.stdout.str()
-    assert 'test_success PASSED' in stdout
+    assert "test_success PASSED" in stdout
 
 
 def test_stop_on_collection_errors(broken_testdir):
-    result = broken_testdir.runpytest('-v', '--strict', '--stepwise', 'working_testfile.py', 'broken_testfile.py')
+    result = broken_testdir.runpytest(
+        "-v", "--strict", "--stepwise", "working_testfile.py", "broken_testfile.py"
+    )
 
     stdout = result.stdout.str()
-    if pytest.__version__ < '3.0.0':
-        assert 'Error when collecting test' in stdout
+    if pytest.__version__ < "3.0.0":
+        assert "Error when collecting test" in stdout
     else:
-        assert 'errors during collection' in stdout
+        assert "errors during collection" in stdout