From 3963a1b70a572132aced1c1a0033e1c8249a0c7e Mon Sep 17 00:00:00 2001 From: hathach Date: Fri, 14 Aug 2026 01:08:40 +0700 Subject: test/hil, ci: contain a wedged USB stack instead of stranding the runner A wedged USB device used to take the whole HIL run with it. Every worker that touched the poisoned node blocked uninterruptibly, the pool could not be joined, map_async discarded every board's result, and the job ran to the GitHub ceiling with no report at all -- while the self-hosted runner's single job slot stayed occupied and every queued job waited behind it. Bound the calls a worker makes itself. read_sysfs, bounded_open and run_cmd all answer within a wall clock; read_sysfs distinguishes "absent" from "unknown", because a blocked read is not evidence of absence, and caps stranded readers at four (each costs a thread and an fd for the life of the process) after which the worker declares itself blind. mtype, the gio unmount, the libmtp session and the arecord/iperf reaps go through those bounds; the MTP session runs in a disposable subprocess, since libmtp's ctypes calls block unkillably in D state. Bound the run. A pool guard (HIL_POOL_TIMEOUT, 60 min) fires before any job ceiling and still writes a report. When the pool will not shut down, the sweep kills what the workers spawned -- descendants, not just direct children, since flashers run in their own session -- confirms each kill actually landed, and exits early so the runner is freed. Whatever survived is named in the report. Deliberately shallow past that point. We do not re-scan process groups, prove pid ownership, or escalate through sudo: a root-owned survivor is reported, not force-killed, because signalling a pid we cannot prove is ours is the worse failure, and the job ceiling backstops whatever this misses. A D-state holder was never killable anyway. Recover instead of reporting a wedge. A HUNG usbtest case reflashes its own DUT through its roster flasher, but only where the flasher can reach its probe past a poisoned node -- openocd pinned to a validated vid_pid, or esptool. Where it cannot, the run says so rather than reserving budget for a path that cannot fire. Raise the CI ceilings above the pool guard so the guard fires first and still writes its report, and pin --retry 1 on every HIL leg: the guard is a flat constant and does not scale with max_retry, so argparse's default of 3 would triple the serialized usbtest tail against an unchanged guard. Split the module: execution in hil_test/hil_flash/usbtest, infrastructure in helper/ (locking, health, selection, shared bounded IO), and the two matrix generators into .github/scripts/ -- ci_set_matrix.py sat in workflows/, where GitHub treats every file as a workflow definition. 193 tests cover the bounded paths, the kill ladder, the guard and the selector against synthetic /proc trees and PATH-injected fakes; a real wedge cannot be manufactured on demand. --- .github/scripts/ci_set_matrix.py | 111 +++++++++++++++++++++++++++++++++++ .github/scripts/hil_ci_set_matrix.py | 92 +++++++++++++++++++++++++++++ 2 files changed, 203 insertions(+) create mode 100755 .github/scripts/ci_set_matrix.py create mode 100644 .github/scripts/hil_ci_set_matrix.py (limited to '.github/scripts') diff --git a/.github/scripts/ci_set_matrix.py b/.github/scripts/ci_set_matrix.py new file mode 100755 index 000000000..50ada5964 --- /dev/null +++ b/.github/scripts/ci_set_matrix.py @@ -0,0 +1,111 @@ +#!/usr/bin/env python3 +import json + +# toolchain, url +toolchain_list = [ + "aarch64-gcc", + "arm-clang", + "arm-iar", + "arm-gcc", + "esp-idf", + "ft9xx-gcc", + "msp430-gcc", + "riscv-gcc", + "rx-gcc" +] + +# family: [supported toolchain] +family_list = { + "apm32f0xx": ["arm-gcc"], + "at32f402_405": ["arm-gcc"], + "at32f403a_407": ["arm-gcc"], + "at32f413": ["arm-gcc"], + "at32f415": ["arm-gcc"], + "at32f423": ["arm-gcc"], + "at32f425": ["arm-gcc"], + "at32f435_437": ["arm-gcc"], + "at32f45x": ["arm-gcc"], + "broadcom_32bit": ["arm-gcc"], + "broadcom_64bit": ["aarch64-gcc"], + "ch32f20x": ["arm-gcc"], + "ch32v10x": ["riscv-gcc"], + "ch32v20x": ["riscv-gcc"], + "ch32v30x": ["riscv-gcc"], + "ch583": ["riscv-gcc"], + "da1469x": ["arm-gcc"], + "fomu": ["riscv-gcc"], + "ft9xx": ["ft9xx-gcc"], + "gd32vf103": ["riscv-gcc"], + "hpmicro": ["riscv-gcc"], + "imxrt": ["arm-gcc", "arm-clang"], + "kinetis_k": ["arm-gcc"], + "kinetis_k32l": ["arm-gcc"], + "kinetis_kl": ["arm-gcc"], + "lpc11": ["arm-gcc", "arm-clang"], + "lpc13": ["arm-gcc", "arm-clang"], + "lpc15": ["arm-gcc", "arm-clang"], + "lpc17": ["arm-gcc", "arm-clang"], + "lpc18": ["arm-gcc", "arm-clang"], + "lpc40": ["arm-gcc", "arm-clang"], + "lpc43": ["arm-gcc", "arm-clang"], + "lpc51": ["arm-gcc", "arm-clang"], + "lpc54": ["arm-gcc", "arm-clang"], + "lpc55": ["arm-gcc", "arm-clang"], + "maxim": ["arm-gcc"], + "mcx": ["arm-gcc"], + "mm32": ["arm-gcc"], + "msp430": ["msp430-gcc"], + "msp432e4": ["arm-gcc"], + "nrf": ["arm-gcc", "arm-clang"], + "nuc100_120": ["arm-gcc"], + "nuc121_125": ["arm-gcc"], + "nuc126": ["arm-gcc"], + "nuc505": ["arm-gcc"], + "ra": ["arm-gcc"], + "rp2040": ["arm-gcc"], + "rw61x": ["arm-gcc"], + "rx": ["rx-gcc"], + "samd11": ["arm-gcc", "arm-clang"], + "samd2x_l2x": ["arm-gcc", "arm-clang"], + "samd5x_e5x": ["arm-gcc", "arm-clang"], + "samg": ["arm-gcc", "arm-clang"], + "stm32c0": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32c5": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32f0": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32f1": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32f2": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32f3": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32f4": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32f7": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32g0": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32g4": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32h5": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32h7": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32h7rs": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32l0": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32l4": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32n6": ["arm-gcc"], + "stm32u0": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32u5": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32wb": ["arm-gcc", "arm-clang", "arm-iar"], + "stm32wba": ["arm-gcc", "arm-clang", "arm-iar"], + "tm4c": ["arm-gcc"], + "xmc4000": ["arm-gcc"], + # S3, P4 will be built by hil test + # "-bespressif_s3_devkitm": ["esp-idf"], + # "-bespressif_p4_function_ev": ["esp-idf"], +} + + +def set_matrix_json(): + matrix = {} + for toolchain in toolchain_list: + filtered_families = [family for family, supported_toolchain in family_list.items() if + toolchain in supported_toolchain] + matrix[toolchain] = filtered_families + + print(json.dumps(matrix)) + + +if __name__ == '__main__': + set_matrix_json() diff --git a/.github/scripts/hil_ci_set_matrix.py b/.github/scripts/hil_ci_set_matrix.py new file mode 100644 index 000000000..65f50788e --- /dev/null +++ b/.github/scripts/hil_ci_set_matrix.py @@ -0,0 +1,92 @@ +import argparse +import json +import os + + +def _resolve_config_path(config_file): + if os.path.exists(config_file): + return config_file + + # bare roster names resolve against the repo's test/hil (this script lives in + # .github/scripts); build.yml passes explicit paths, this is for hand-runs + repo_relative = os.path.join(os.path.dirname(__file__), '..', '..', 'test', 'hil', config_file) + if os.path.exists(repo_relative): + return repo_relative + + raise FileNotFoundError(f'Config file not found: {config_file}') + + +def main(): + parser = argparse.ArgumentParser() + parser.add_argument('config_files', nargs='+', help='Configuration JSON file(s)') + parser.add_argument('--select', help='hil_select.py JSON; scopes boards when full=false') + args = parser.parse_args() + + selected = None + sel = json.loads(args.select) if args.select else None + if sel and not sel.get('full'): + selected = set(sel.get('boards', {})) + + # Toolchain buckets must match the toolchains instantiated by the hil-build + # job in .github/workflows/build.yml. Keep all keys present (even if empty) + # so `fromJSON(hil_json)[toolchain]` always resolves to a list. + matrix = { + 'arm-gcc': [], + 'riscv-gcc': [], + 'esp-idf': [] + } + + seen = {toolchain: set() for toolchain in matrix} + + def append_build_arg(toolchain, build_arg): + if build_arg not in seen[toolchain]: + seen[toolchain].add(build_arg) + matrix[toolchain].append(build_arg) + + for config_file in args.config_files: + with open(_resolve_config_path(config_file)) as f: + config = json.load(f) + + for board in config['boards']: + if selected is not None and board['name'] not in selected: + continue + name = board['name'] + flasher = board['flasher'] + # esptool boards must build under esp-idf; others default to arm-gcc + # but may opt into another bucket via an explicit "toolchain" field + # (e.g. RISC-V boards like ch32v20x need "riscv-gcc"). + if flasher['name'] == 'esptool': + toolchain = 'esp-idf' + else: + toolchain = board.get('toolchain', 'arm-gcc') + if toolchain not in matrix: + # a board in no bucket would never be built, and the bare KeyError + # below would only say so as a traceback from the set-matrix job + raise SystemExit( + f'{name}: toolchain {toolchain!r} is not a build bucket ' + f'({", ".join(matrix)}); add it here and to the hil-build / ' + f'hil-build-esp jobs in .github/workflows/build.yml') + + build_board = f'-b {name}' + if 'build' in board and 'args' in board['build']: + build_board += ' ' + ' '.join(f'-D{a}' for a in board['build']['args']) + + # Each variant builds into cmake-build- with its own cmake + # -D defines and raw CFLAGS. No 'variant' -> a single build named after + # the board. + variants = board.get('variant') or [{'name': name, 'flags': ''}] + for v in variants: + arg = build_board + if v['name'] != name: + arg += f' --build-name {v["name"]}' + for d in v.get('defines', []): + arg += f' -D{d}' + for tok in v.get('flags', '').split(): + arg += f' --cflag={tok}' + append_build_arg(toolchain, arg) + + print(json.dumps(matrix)) + + +if __name__ == '__main__': + main() -- cgit v1.3.1