"value":"In the Linux kernel, the following vulnerability has been resolved:\n\nworkqueue: Improve scalability of workqueue watchdog touch\n\nOn a ~2000 CPU powerpc system, hard lockups have been observed in the\nworkqueue code when stop_machine runs (in this case due to CPU hotplug).\nThis is due to lots of CPUs spinning in multi_cpu_stop, calling\ntouch_nmi_watchdog() which ends up calling wq_watchdog_touch().\nwq_watchdog_touch() writes to the global variable wq_watchdog_touched,\nand that can find itself in the same cacheline as other important\nworkqueue data, which slows down operations to the point of lockups.\n\nIn the case of the following abridged trace, worker_pool_idr was in\nthe hot line, causing the lockups to always appear at idr_find.\n\n watchdog: CPU 1125 self-detected hard LOCKUP @ idr_find\n Call Trace:\n get_work_pool\n __queue_work\n call_timer_fn\n run_timer_softirq\n __do_softirq\n do_softirq_own_stack\n irq_exit\n timer_interrupt\n decrementer_common_virt\n * interrupt: 900 (timer) at multi_cpu_stop\n multi_cpu_stop\n cpu_stopper_thread\n smpboot_thread_fn\n kthread\n\nFix this by having wq_watchdog_touch() only write to the line if the\nlast time a touch was recorded exceeds 1/4 of the watchdog threshold."
