Messages in this thread | | | Date | Mon, 2 Dec 2019 15:39:44 -0800 | From | "Paul E. McKenney" <> | Subject | Re: Workqueues splat due to ending up on wrong CPU |
| |
On Mon, Dec 02, 2019 at 12:13:38PM -0800, Tejun Heo wrote: > Hello, Paul. > > (cc'ing scheduler folks - workqueue rescuer is very occassionally > triggering a warning which says that it isn't on the cpu it should be > on under rcu cpu hotplug torture test. It's checking smp_processor_id > is the expected one after a successful set_cpus_allowed_ptr() call.) > > On Sun, Dec 01, 2019 at 05:55:48PM -0800, Paul E. McKenney wrote: > > > And hyperthreading seems to have done the trick! One splat thus far, > > > shown below. The run should complete this evening, Pacific Time. > > > > That was the only one for that run, but another 24*56-hour run got three > > more. All of them expected to be on CPU 0 (which never goes offline, so > > why?) and the "XXX" diagnostic never did print. > > Heh, I didn't expect that, so maybe set_cpus_allowed_ptr() is > returning 0 while not migrating the rescuer task to the target cpu for > some reason? > > The rescuer is always calling to migrate itself, so it must always be > running. set_cpus_allowed_ptr() migrates live ones by calling > stop_one_cpu() which schedules a migration function which runs from a > highpri task on the target cpu. Please take a look at the following. > > static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) > { > ... > enabled = stopper->enabled; > if (enabled) > __cpu_stop_queue_work(stopper, work, &wakeq); > else if (work->done) > cpu_stop_signal_done(work->done); > ... > } > > So, if stopper->enabled is clear, it'll signal completion without > running the work. stopper->enabled is cleared during cpu hotunplug > and restored from bringup_cpu() while cpu is being brought back up. > > static int bringup_wait_for_ap(unsigned int cpu) > { > ... > stop_machine_unpark(cpu); > .... > } > > static int bringup_cpu(unsigned int cpu) > { > ... > ret = __cpu_up(cpu, idle); > ... > return bringup_wait_for_ap(cpu); > } > > __cpu_up() is what marks the cpu online and once the cpu is online, > kthreads are free to migrate into the cpu, so it looks like there's a > brief window where a cpu is marked online but the stopper thread is > still disabled meaning that a kthread may schedule into the cpu but > not out of it, which would explain the symptom that you were seeing. > > This makes the cpumask and the cpu the task is actually on disagree > and retries would become noops. I can work around it by excluding > rescuer attachments against hotplugs but this looks like a genuine cpu > hotplug bug. > > It could be that I'm misreading the code. What do you guys think?
I think that I do not understand the code, but I never let that stop me from asking stupid questions! ;-)
Suppose that a given worker is bound to a particular CPU, but has no work pending, and is therefore sleeping in the schedule() call near the end of worker_thread(). During this time, its CPU goes offline and then comes back online. Doesn't this break that task's affinity to that CPU? Then the call to workqueue_online_cpu() is supposed to rebind all the tasks that might have been affected, correct?
I could imagine putting a trace_printk() or two in workqueue_online_cpu() and adding the task_struct pointer (or PID) to the WARN_ONCE(), though I am worried that this might decrease the race probability.
Is there a better way to proceed?
Thanx, Paul
| |