[PATCH net-next v2 7/9] selftests: rds: Register network teardown via atexit

[Allison Henderson <achender@kernel.org>]

This patch adds a teardown_tcp() helper that removes net0/net1.
The cmd calls here use fail=False so they can be called from
completed or partially-setup states on error. Also call
teardown_tcp() at the top of setup_tcp() so a previous
interrupted run does not leave net0/net1 lingering and break a
subsequent ip netns add.  Register teardown_tcp() with atexit
before setup_tcp() is invoked.

Likewise, we can simpliy stop_pcaps() handling by registering it
with atexit instead of calling it from the signal handler.

atexit handlers run on any exit path - normal completion, raised
exception, and sys.exit() from the timeout signal handler.  This
guarantees cleanup are called without further wrapping the test
body in a try/finally blocks.

atexit LIFO ordering keeps stop_pcaps before teardown_tcp so
tcpdumps are killed cleanly before their namespaces go away.

This is a preparatory cleanup for the upcoming ROCE patch which
will also register a teardown_rdma() alongside teardown_tcp()

Signed-off-by: Allison Henderson <achender@kernel.org>
---
 tools/testing/selftests/net/rds/test.py | 27 +++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/rds/test.py b/tools/testing/selftests/net/rds/test.py
index f7d0dba85131..7738c7e2af36 100755
--- a/tools/testing/selftests/net/rds/test.py
+++ b/tools/testing/selftests/net/rds/test.py
@@ -5,6 +5,7 @@ This module provides functional testing for the net/rds component.
 """
 
 import argparse
+import atexit
 import ctypes
 import errno
 import hashlib
@@ -19,7 +20,7 @@ import sys
 this_dir = os.path.dirname(os.path.realpath(__file__))
 sys.path.append(os.path.join(this_dir, "../"))
 # pylint: disable-next=wrong-import-position,import-error,no-name-in-module
-from lib.py.utils import ip # noqa: E402
+from lib.py.utils import ip, cmd # noqa: E402
 # pylint: disable-next=wrong-import-position,import-error,no-name-in-module
 from lib.py.ksft import ksft_pr # noqa: E402
 
@@ -246,7 +247,6 @@ def signal_handler(_sig, _frame):
     Test timed out signal handler
     """
     ksft_pr("Test timed out")
-    stop_pcaps()
     print("not ok 1 rds selftest")
     sys.exit(1)
 
@@ -255,6 +255,9 @@ def setup_tcp():
     Configure tcp network
     """
 
+    # clean up any leftovers from a previously interrupted run
+    teardown_tcp()
+
     ip(f"netns add {NET0}")
     ip(f"netns add {NET1}")
     ip("link add type veth")
@@ -299,6 +302,17 @@ def setup_tcp():
              corrupt {PACKET_CORRUPTION} loss {PACKET_LOSS} duplicate  \
              {PACKET_DUPLICATE}")
 
+def teardown_tcp():
+    """
+    Tear down the tcp network configured by setup_tcp().
+
+    Removing the namespaces also removes the veth pair, addresses,
+    routes, and netem qdisc that live inside them.  fail=False so
+    this is safe to call in error paths after a partial or complete setup.
+    """
+    cmd(f"ip netns del {NET0}", fail=False)
+    cmd(f"ip netns del {NET1}", fail=False)
+
 #Parse out command line arguments.  We take an optional
 # timeout parameter and an optional log output folder
 parser = argparse.ArgumentParser(description="init script args",
@@ -319,6 +333,13 @@ PACKET_LOSS=str(args.loss)+'%'
 PACKET_CORRUPTION=str(args.corruption)+'%'
 PACKET_DUPLICATE=str(args.duplicate)+'%'
 
+# Register cleanup before setup so a partial-setup crash still tears down
+# whatever state did get created.  atexit runs LIFO, so registering
+# teardown_tcp first means stop_pcaps (registered second) runs first,
+# killing tcpdumps before their namespaces go away.
+atexit.register(teardown_tcp)
+atexit.register(stop_pcaps)
+
 setup_tcp()
 
 print("TAP version 13")
@@ -334,8 +355,6 @@ ret = snd_rcv_packets(tcp_addrs, [NET0, NET1])
 # cancel timeout
 signal.alarm(0)
 
-stop_pcaps()
-
 if ret == 0:
     ksft_pr("Success")
     print("ok 1 rds selftest")
-- 
2.25.1