[PATCH net-next v2] selftests: net: exit cleanly on SIGTERM / timeout

[Jakub Kicinski <kuba@kernel.org>]

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 9616cb34b08e ("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>
---
v2:
 - remove declaration at the global scope
v1: https://lore.kernel.org/20250425151757.1652517-1-kuba@kernel.org

CC: petrm@nvidia.com
CC: willemb@google.com
CC: sdf@fomichev.me
CC: linux-kselftest@vger.kernel.org
---
 tools/testing/selftests/net/lib/py/ksft.py | 25 +++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index 3cfad0fd4570..1b815768bf8a 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/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 @@ KSFT_DISRUPTIVE = True
     pass
 
 
+class KsftTerminate(KeyboardInterrupt):
+    pass
+
+
 def ksft_pr(*objs, **kwargs):
     print("#", *objs, **kwargs)
 
@@ -193,6 +198,17 @@ KSFT_DISRUPTIVE = True
     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 []
 
@@ -205,6 +221,10 @@ KSFT_DISRUPTIVE = True
                     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")
@@ -229,11 +249,12 @@ KSFT_DISRUPTIVE = True
             cnt_key = 'xfail'
         except BaseException as e:
             stop |= isinstance(e, KeyboardInterrupt)
+            stop |= isinstance(e, KsftTerminate)
             tb = traceback.format_exc()
             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'
 
@@ -248,6 +269,8 @@ KSFT_DISRUPTIVE = True
         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"
     )
-- 
2.49.0