selftests: net: exit cleanly on SIGTERM / timeout

JIRA: https://issues.redhat.com/browse/RHEL-115594

commit 8f0ae19
Author: Jakub Kicinski <kuba@kernel.org>
Date:   Fri May 2 18:18:56 2025 -0700

    selftests: net: exit cleanly on SIGTERM / timeout

    ksft runner sends 2 SIGTERMs in a row if a test runs out of time.
    Handle this in a similar way we handle SIGINT - cleanup and stop
    running further tests.

    Because we get 2 signals we need a bit of logic to ignore
    the subsequent one, they come immediately one after the other
    (due to commit 9616cb3 ("kselftest/runner.sh: Propagate SIGTERM
    to runner child")).

    This change makes sure we run cleanup (scheduled defer()s)
    and also print a stack trace on SIGTERM, which doesn't happen
    by default. Tests occasionally hang in NIPA and it's impossible
    to tell what they are waiting from or doing.

    Signed-off-by: Jakub Kicinski <kuba@kernel.org>
    Link: https://patch.msgid.link/20250503011856.46308-1-kuba@kernel.org
    Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Signed-off-by: CKI Backport Bot <cki-ci-bot+cki-gitlab-backport-bot@redhat.com>

Author: CKI Backport Bot

tools/testing/selftests/net/lib/py/ksft.py

@@ -3,6 +3,7 @@
 import builtins
 import functools
 import inspect
+import signal
 import sys
 import time
 import traceback
@@ -26,6 +27,10 @@ class KsftXfailEx(Exception):
     pass
 
 
+class KsftTerminate(KeyboardInterrupt):
+    pass
+
+
 def ksft_pr(*objs, **kwargs):
     print("#", *objs, **kwargs)
 
@@ -183,6 +188,17 @@ def get_bool(env, name):
     return env
 
 
+def _ksft_intr(signum, frame):
+    # ksft runner.sh sends 2 SIGTERMs in a row on a timeout
+    # if we don't ignore the second one it will stop us from handling cleanup
+    global term_cnt
+    term_cnt += 1
+    if term_cnt == 1:
+        raise KsftTerminate()
+    else:
+        ksft_pr(f"Ignoring SIGTERM (cnt: {term_cnt}), already exiting...")
+
+
 def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
     cases = cases or []
 
@@ -195,6 +211,10 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
                     cases.append(value)
                     break
 
+    global term_cnt
+    term_cnt = 0
+    prev_sigterm = signal.signal(signal.SIGTERM, _ksft_intr)
+
     totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0}
 
     print("TAP version 13")
@@ -223,7 +243,7 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
             for line in tb.strip().split('\n'):
                 ksft_pr("Exception|", line)
             if stop:
-                ksft_pr("Stopping tests due to KeyboardInterrupt.")
+                ksft_pr(f"Stopping tests due to {type(e).__name__}.")
             KSFT_RESULT = False
             cnt_key = 'fail'
 
@@ -238,6 +258,8 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
         if stop:
             break
 
+    signal.signal(signal.SIGTERM, prev_sigterm)
+
     print(
         f"# Totals: pass:{totals['pass']} fail:{totals['fail']} xfail:{totals['xfail']} xpass:0 skip:{totals['skip']} error:0"
     )