Merge branch 'selftests-tc-testing-parallel-tdc'

Pedro Tammela says:

====================
selftests/tc-testing: parallel tdc

As the number of tdc tests is growing, so is our completion wall time.
One of the ideas to improve this is to run tests in parallel, as they
are self contained.

This series allows for tests to run in parallel, in batches of 32 tests.
Not all tests can run in parallel as they might conflict with each other.
The code will still honor this requirement even when trying to run the
tests over the worker pool.

In order to make this happen we had to localize the test resources
(patches 1 and 2), where instead of having all tests sharing one single
namespace and veths devices each test now gets it's own local namespace and devices.

Even though the tests serialize over rtnl_lock in the kernel, we
measured a speedup of about 3x in a test VM.
====================

Link: https://lore.kernel.org/r/20230919135404.1778595-1-pctammela@mojatatu.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

58 files changed, 2720 insertions, 1288 deletions

diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README
index b0954c873e2f..be7b00799b3e 100644
--- a/tools/testing/selftests/tc-testing/README
+++ b/tools/testing/selftests/tc-testing/README
@@ -9,8 +9,7 @@ execute them inside a network namespace dedicated to the task.
 REQUIREMENTS
 ------------
 
-*  Minimum Python version of 3.4. Earlier 3.X versions may work but are not
-   guaranteed.
+*  Minimum Python version of 3.8.
 
 *  The kernel must have network namespace support if using nsPlugin
 
@@ -96,6 +95,15 @@ the stdout with a regular expression.
 
 Each of the commands in any stage will run in a shell instance.
 
+Each test is an atomic unit. A test that for whatever reason spans multiple test
+definitions is a bug.
+
+A test that runs inside a namespace (requires "nsPlugin") will run in parallel
+with other tests.
+
+Tests that use netdevsim or don't run inside a namespace run serially with regards
+to each other.
+
 
 USER-DEFINED CONSTANTS
 ----------------------
@@ -116,59 +124,6 @@ COMMAND LINE ARGUMENTS
 
 Run tdc.py -h to see the full list of available arguments.
 
-usage: tdc.py [-h] [-p PATH] [-D DIR [DIR ...]] [-f FILE [FILE ...]]
-              [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v] [-N]
-              [-d DEVICE] [-P] [-n] [-V]
-
-Linux TC unit tests
-
-optional arguments:
-  -h, --help            show this help message and exit
-  -p PATH, --path PATH  The full path to the tc executable to use
-  -v, --verbose         Show the commands that are being run
-  -N, --notap           Suppress tap results for command under test
-  -d DEVICE, --device DEVICE
-                        Execute test cases that use a physical device, where
-                        DEVICE is its name. (If not defined, tests that require
-                        a physical device will be skipped)
-  -P, --pause           Pause execution just before post-suite stage
-
-selection:
-  select which test cases: files plus directories; filtered by categories
-  plus testids
-
-  -D DIR [DIR ...], --directory DIR [DIR ...]
-                        Collect tests from the specified directory(ies)
-                        (default [tc-tests])
-  -f FILE [FILE ...], --file FILE [FILE ...]
-                        Run tests from the specified file(s)
-  -c [CATG [CATG ...]], --category [CATG [CATG ...]]
-                        Run tests only from the specified category/ies, or if
-                        no category/ies is/are specified, list known
-                        categories.
-  -e ID [ID ...], --execute ID [ID ...]
-                        Execute the specified test cases with specified IDs
-
-action:
-  select action to perform on selected test cases
-
-  -l, --list            List all test cases, or those only within the
-                        specified category
-  -s, --show            Display the selected test cases
-  -i, --id              Generate ID numbers for new test cases
-
-netns:
-  options for nsPlugin (run commands in net namespace)
-
-  -N, --no-namespace
-                        Do not run commands in a network namespace.
-
-valgrind:
-  options for valgrindPlugin (run command under test under Valgrind)
-
-  -V, --valgrind        Run commands under valgrind
-
-
 PLUGIN ARCHITECTURE
 -------------------
 
diff --git a/tools/testing/selftests/tc-testing/TdcPlugin.py b/tools/testing/selftests/tc-testing/TdcPlugin.py
index 79f3ca8617c9..aae85ce4f776 100644
--- a/tools/testing/selftests/tc-testing/TdcPlugin.py
+++ b/tools/testing/selftests/tc-testing/TdcPlugin.py
@@ -5,10 +5,10 @@ class TdcPlugin:
         super().__init__()
         print(' -- {}.__init__'.format(self.sub_class))
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testlist):
         '''run commands before test_runner goes into a test loop'''
         self.testcount = testcount
-        self.testidlist = testidlist
+        self.testlist = testlist
         if self.args.verbose > 1:
             print(' -- {}.pre_suite'.format(self.sub_class))
 
diff --git a/tools/testing/selftests/tc-testing/TdcResults.py b/tools/testing/selftests/tc-testing/TdcResults.py
index 1e4d95fdf8d0..e56817b97f08 100644
--- a/tools/testing/selftests/tc-testing/TdcResults.py
+++ b/tools/testing/selftests/tc-testing/TdcResults.py
@@ -59,7 +59,8 @@ class TestResult:
         return self.steps
 
 class TestSuiteReport():
-    _testsuite = []
+    def __init__(self):
+        self._testsuite = []
 
     def add_resultdata(self, result_data):
         if isinstance(result_data, TestResult):
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
index 9539cffa9e5e..b62429b0fcdb 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
@@ -3,35 +3,96 @@ import signal
 from string import Template
 import subprocess
 import time
+from multiprocessing import Pool
+from functools import cached_property
 from TdcPlugin import TdcPlugin
 
 from tdc_config import *
 
+def prepare_suite(obj, test):
+    original = obj.args.NAMES
+
+    if 'skip' in test and test['skip'] == 'yes':
+        return
+
+    if 'nsPlugin' not in test['plugins']:
+        return
+
+    shadow = {}
+    shadow['IP'] = original['IP']
+    shadow['TC'] = original['TC']
+    shadow['NS'] = '{}-{}'.format(original['NS'], test['random'])
+    shadow['DEV0'] = '{}id{}'.format(original['DEV0'], test['id'])
+    shadow['DEV1'] = '{}id{}'.format(original['DEV1'], test['id'])
+    shadow['DUMMY'] = '{}id{}'.format(original['DUMMY'], test['id'])
+    shadow['DEV2'] = original['DEV2']
+    obj.args.NAMES = shadow
+
+    if obj.args.namespace:
+        obj._ns_create()
+    else:
+        obj._ports_create()
+
+    # Make sure the netns is visible in the fs
+    while True:
+        obj._proc_check()
+        try:
+            ns = obj.args.NAMES['NS']
+            f = open('/run/netns/{}'.format(ns))
+            f.close()
+            break
+        except:
+            time.sleep(0.1)
+            continue
+
+    obj.args.NAMES = original
+
 class SubPlugin(TdcPlugin):
     def __init__(self):
         self.sub_class = 'ns/SubPlugin'
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
-        '''run commands before test_runner goes into a test loop'''
-        super().pre_suite(testcount, testidlist)
+    def pre_suite(self, testcount, testlist):
+        from itertools import cycle
 
-        if self.args.namespace:
-            self._ns_create()
-        else:
-            self._ports_create()
+        super().pre_suite(testcount, testlist)
 
-    def post_suite(self, index):
-        '''run commands after test_runner goes into a test loop'''
-        super().post_suite(index)
+        print("Setting up namespaces and devices...")
+
+        with Pool(self.args.mp) as p:
+            it = zip(cycle([self]), testlist)
+            p.starmap(prepare_suite, it)
+
+    def pre_case(self, caseinfo, test_skip):
         if self.args.verbose:
-            print('{}.post_suite'.format(self.sub_class))
+            print('{}.pre_case'.format(self.sub_class))
+
+        if test_skip:
+            return
+
+
+    def post_case(self):
+        if self.args.verbose:
+            print('{}.post_case'.format(self.sub_class))
 
         if self.args.namespace:
             self._ns_destroy()
         else:
             self._ports_destroy()
 
+    def post_suite(self, index):
+        if self.args.verbose:
+            print('{}.post_suite'.format(self.sub_class))
+
+        # Make sure we don't leak resources
+        for f in os.listdir('/run/netns/'):
+            cmd = self._replace_keywords("$IP netns del {}".format(f))
+
+            if self.args.verbose > 3:
+                print('_exec_cmd:  command "{}"'.format(cmd))
+
+            subprocess.run(cmd, shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+
     def add_args(self, parser):
         super().add_args(parser)
         self.argparser_group = self.argparser.add_argument_group(
@@ -77,18 +138,43 @@ class SubPlugin(TdcPlugin):
             print('adjust_command:  return command [{}]'.format(command))
         return command
 
-    def _ports_create(self):
-        cmd = '$IP link add $DEV0 type veth peer name $DEV1'
-        self._exec_cmd('pre', cmd)
-        cmd = '$IP link set $DEV0 up'
-        self._exec_cmd('pre', cmd)
+    def _ports_create_cmds(self):
+        cmds = []
+
+        cmds.append(self._replace_keywords('link add $DEV0 type veth peer name $DEV1'))
+        cmds.append(self._replace_keywords('link set $DEV0 up'))
+        cmds.append(self._replace_keywords('link add $DUMMY type dummy'))
         if not self.args.namespace:
-            cmd = '$IP link set $DEV1 up'
-            self._exec_cmd('pre', cmd)
+            cmds.append(self._replace_keywords('link set $DEV1 up'))
+
+        return cmds
+
+    def _ports_create(self):
+        self._exec_cmd_batched('pre', self._ports_create_cmds())
+
+    def _ports_destroy_cmd(self):
+        return self._replace_keywords('link del $DEV0')
 
     def _ports_destroy(self):
-        cmd = '$IP link del $DEV0'
-        self._exec_cmd('post', cmd)
+        self._exec_cmd('post', self._ports_destroy_cmd())
+
+    def _ns_create_cmds(self):
+        cmds = []
+
+        if self.args.namespace:
+            ns = self.args.NAMES['NS']
+
+            cmds.append(self._replace_keywords('netns add {}'.format(ns)))
+            cmds.append(self._replace_keywords('link set $DEV1 netns {}'.format(ns)))
+            cmds.append(self._replace_keywords('link set $DUMMY netns {}'.format(ns)))
+            cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV1 up'.format(ns)))
+            cmds.append(self._replace_keywords('netns exec {} $IP link set $DUMMY up'.format(ns)))
+
+            if self.args.device:
+                cmds.append(self._replace_keywords('link set $DEV2 netns {}'.format(ns)))
+                cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV2 up'.format(ns)))
+
+        return cmds
 
     def _ns_create(self):
         '''
@@ -96,18 +182,10 @@ class SubPlugin(TdcPlugin):
         the required network devices for it.
         '''
         self._ports_create()
-        if self.args.namespace:
-            cmd = '$IP netns add {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            cmd = '$IP link set $DEV1 netns {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            cmd = '$IP -n {} link set $DEV1 up'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            if self.args.device:
-                cmd = '$IP link set $DEV2 netns {}'.format(self.args.NAMES['NS'])
-                self._exec_cmd('pre', cmd)
-                cmd = '$IP -n {} link set $DEV2 up'.format(self.args.NAMES['NS'])
-                self._exec_cmd('pre', cmd)
+        self._exec_cmd_batched('pre', self._ns_create_cmds())
+
+    def _ns_destroy_cmd(self):
+        return self._replace_keywords('netns delete {}'.format(self.args.NAMES['NS']))
 
     def _ns_destroy(self):
         '''
@@ -115,35 +193,49 @@ class SubPlugin(TdcPlugin):
         devices as well)
         '''
         if self.args.namespace:
-            cmd = '$IP netns delete {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('post', cmd)
+            self._exec_cmd('post', self._ns_destroy_cmd())
+            self._ports_destroy()
+
+    @cached_property
+    def _proc(self):
+        ip = self._replace_keywords("$IP -b -")
+        proc = subprocess.Popen(ip,
+            shell=True,
+            stdin=subprocess.PIPE,
+            env=ENVIR)
+
+        return proc
+
+    def _proc_check(self):
+        proc = self._proc
+
+        proc.poll()
+
+        if proc.returncode is not None and proc.returncode != 0:
+            raise RuntimeError("iproute2 exited with an error code")
 
     def _exec_cmd(self, stage, command):
         '''
         Perform any required modifications on an executable command, then run
         it in a subprocess and return the results.
         '''
-        if '$' in command:
-            command = self._replace_keywords(command)
 
-        self.adjust_command(stage, command)
-        if self.args.verbose:
+        if self.args.verbose > 3:
             print('_exec_cmd:  command "{}"'.format(command))
-        proc = subprocess.Popen(command,
-            shell=True,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            env=ENVIR)
-        (rawout, serr) = proc.communicate()
 
-        if proc.returncode != 0 and len(serr) > 0:
-            foutput = serr.decode("utf-8")
-        else:
-            foutput = rawout.decode("utf-8")
+        proc = self._proc
+
+        proc.stdin.write((command + '\n').encode())
+        proc.stdin.flush()
+
+        if self.args.verbose > 3:
+            print('_exec_cmd proc: {}'.format(proc))
+
+        self._proc_check()
 
-        proc.stdout.close()
-        proc.stderr.close()
-        return proc, foutput
+    def _exec_cmd_batched(self, stage, commands):
+        for cmd in commands:
+            self._exec_cmd(stage, cmd)
 
     def _replace_keywords(self, cmd):
         """
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py
index e36775bd4d12..8762c0f4a095 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py
@@ -10,9 +10,9 @@ class SubPlugin(TdcPlugin):
         self.sub_class = 'root/SubPlugin'
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testlist):
         # run commands before test_runner goes into a test loop
-        super().pre_suite(testcount, testidlist)
+        super().pre_suite(testcount, testlist)
 
         if os.geteuid():
             print('This script must be run with root privileges', file=sys.stderr)
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
index 4bb866575ea1..c6f61649c430 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
@@ -25,9 +25,10 @@ class SubPlugin(TdcPlugin):
         self._tsr = TestSuiteReport()
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testist):
         '''run commands before test_runner goes into a test loop'''
-        super().pre_suite(testcount, testidlist)
+        self.testidlist = [tidx['id'] for tidx in testlist]
+        super().pre_suite(testcount, testlist)
         if self.args.verbose > 1:
             print('{}.pre_suite'.format(self.sub_class))
         if self.args.valgrind:
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
index 0de2f79ea329..3d0f9310bde4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
@@ -6,6 +6,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -30,6 +33,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -54,6 +60,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -78,6 +87,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -102,6 +114,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -126,6 +141,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -150,6 +168,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [