From 85d7dae377ac172a5361bbb526b552db39c5ceca Mon Sep 17 00:00:00 2001
From: Simon Glass <sjg@chromium.org>
Date: Wed, 9 Oct 2024 18:29:03 -0600
Subject: [PATCH] test: Detect dead connections

When the connection to a board dies, assume it is dead forever until
some user action is taken. Skip all remaining tests. This avoids CI
runs taking an hour, with hundreds of 30-second timeouts all to no
avail.

Signed-off-by: Simon Glass <sjg@chromium.org>
---
 test/py/conftest.py     | 19 +++++++++++++++++--
 test/py/u_boot_spawn.py | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+), 2 deletions(-)

diff --git a/test/py/conftest.py b/test/py/conftest.py
index 85e1979dc7..46a410cf26 100644
--- a/test/py/conftest.py
+++ b/test/py/conftest.py
@@ -24,6 +24,7 @@ import pytest
 import re
 from _pytest.runner import runtestprotocol
 import sys
+from u_boot_spawn import BootFail, Timeout, Unexpected, handle_exception
 
 # Globals: The HTML log file, and the connection to the U-Boot console.
 log = None
@@ -254,6 +255,7 @@ def pytest_configure(config):
     ubconfig.board_identity = board_identity
     ubconfig.gdbserver = gdbserver
     ubconfig.dtb = build_dir + '/arch/sandbox/dts/test.dtb'
+    ubconfig.connection_ok = True
 
     env_vars = (
         'board_type',
@@ -420,8 +422,21 @@ def u_boot_console(request):
     Returns:
         The fixture value.
     """
-
-    console.ensure_spawned()
+    if not ubconfig.connection_ok:
+        pytest.skip('Cannot get target connection')
+        return None
+    try:
+        console.ensure_spawned()
+    except OSError as err:
+        handle_exception(ubconfig, console, log, err, 'Lab failure', True)
+    except Timeout as err:
+        handle_exception(ubconfig, console, log, err, 'Lab timeout', True)
+    except BootFail as err:
+        handle_exception(ubconfig, console, log, err, 'Boot fail', True,
+                         console.get_spawn_output())
+    except Unexpected:
+        handle_exception(ubconfig, console, log, err, 'Unexpected test output',
+                         False)
     return console
 
 anchors = {}
diff --git a/test/py/u_boot_spawn.py b/test/py/u_boot_spawn.py
index bcba7b5cd4..24d369035e 100644
--- a/test/py/u_boot_spawn.py
+++ b/test/py/u_boot_spawn.py
@@ -8,6 +8,7 @@ Logic to spawn a sub-process and interact with its stdio.
 import os
 import re
 import pty
+import pytest
 import signal
 import select
 import time
@@ -27,6 +28,43 @@ class BootFail(Exception):
 class Unexpected(Exception):
     """An exception sub-class that indicates that unexpected test was seen."""
 
+
+def handle_exception(ubconfig, console, log, err, name, fatal, output=''):
+    """Handle an exception from the console
+
+    Exceptions can occur when there is unexpected output or due to the board
+    crashing or hanging. Some exceptions are likely fatal, where retrying will
+    just chew up time to no available. In those cases it is best to cause
+    further tests be skipped.
+
+    Args:
+        ubconfig (ArbitraryAttributeContainer): ubconfig object
+        log (Logfile): Place to log errors
+        console (ConsoleBase): Console to clean up, if fatal
+        err (Exception): Exception which was thrown
+        name (str): Name of problem, to log
+        fatal (bool): True to abort all tests
+        output (str): Extra output to report on boot failure. This can show the
+           target's console output as it tried to boot
+    """
+    msg = f'{name}: '
+    if fatal:
+        msg += 'Marking connection bad - no other tests will run'
+    else:
+        msg += 'Assuming that lab is healthy'
+    print(msg)
+    log.error(msg)
+    log.error(f'Error: {err}')
+
+    if output:
+        msg += f'; output {output}'
+
+    if fatal:
+        ubconfig.connection_ok = False
+        console.cleanup_spawn()
+        pytest.exit(msg)
+
+
 class Spawn:
     """Represents the stdio of a freshly created sub-process. Commands may be
     sent to the process, and responses waited for.
-- 
2.39.5