As we already used hld internally for arm64 since 2020, there still doesn't have a proper commit on the upstream and we badly need it. This serise rebase on 5.17-rc3 from [1] and the origin author is Pingfan Liu <kernelfans@xxxxxxxxx> Sumit Garg <sumit.garg@xxxxxxxxxx> [1] wasn't reviewed for its patch v3, I'll take over the further development for this. Qoute from [1]: Hard lockup detector is helpful to diagnose unpaired irq enable/disable. But the current watchdog framework can not cope with arm64 hw perf event easily. On arm64, when lockup_detector_init()->watchdog_nmi_probe(), PMU is not ready until device_initcall(armv8_pmu_driver_init). And it is deeply integrated with the driver model and cpuhp. Hence it is hard to push the initialization of armv8_pmu_driver_init() before smp_init(). But it is easy to take an opposite approach by enabling watchdog_hld to get the capability of PMU async. The async model is achieved by expanding watchdog_nmi_probe() with -EBUSY, and a re-initializing work_struct which waits on a wait_queue_head. [1] https://lore.kernel.org/lkml/20211014024155.15253-1-kernelfans@xxxxxxxxx/ Lecopzer Chen (2): kernel/watchdog: remove WATCHDOG_DEFAULT kernel/watchdog: change watchdog_nmi_enable() to void Pingfan Liu (2): kernel/watchdog_hld: Ensure CPU-bound context when creating hardlockup detector event kernel/watchdog: Adapt the watchdog_hld interface for async model Sumit Garg (1): arm64: Enable perf events based hard lockup detector arch/arm64/Kconfig | 2 ++ arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/perf_event.c | 11 ++++-- arch/arm64/kernel/watchdog_hld.c | 36 +++++++++++++++++++ arch/sparc/kernel/nmi.c | 8 ++--- drivers/perf/arm_pmu.c | 5 +++ include/linux/nmi.h | 11 +++++- include/linux/perf/arm_pmu.h | 2 ++ kernel/watchdog.c | 61 ++++++++++++++++++++++++++++---- kernel/watchdog_hld.c | 8 ++++- 10 files changed, 131 insertions(+), 14 deletions(-) create mode 100644 arch/arm64/kernel/watchdog_hld.c -- 2.25.1
