From: Oleg Nesterov "[PATCH 1/2] reimplement flush_workqueue()" fixed one race when CPU goes down while flush_cpu_workqueue() plays with it. But there is another problem, CPU can die before flush_workqueue() has a chance to call flush_cpu_workqueue(). In that case pending work_structs can migrate to CPU which was already checked, so we should redo the "for_each_online_cpu(cpu)" loop. Signed-off-by: Oleg Nesterov Cc: Gautham R Shenoy Signed-off-by: Andrew Morton --- kernel/workqueue.c | 8 ++++++++ 1 files changed, 8 insertions(+) diff -puN kernel/workqueue.c~fix-flush_workqueue-vs-cpu_dead-race kernel/workqueue.c --- a/kernel/workqueue.c~fix-flush_workqueue-vs-cpu_dead-race +++ a/kernel/workqueue.c @@ -65,6 +65,7 @@ struct workqueue_struct { /* All the per-cpu workqueues on the system, for hotplug cpu to add/remove threads to each one as cpus come/go. */ +static long hotplug_sequence __read_mostly; static DEFINE_MUTEX(workqueue_mutex); static LIST_HEAD(workqueues); @@ -454,10 +455,16 @@ void fastcall flush_workqueue(struct wor /* Always use first cpu's area. */ flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, singlethread_cpu)); } else { + long sequence; int cpu; +again: + sequence = hotplug_sequence; for_each_online_cpu(cpu) flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu)); + + if (unlikely(sequence != hotplug_sequence)) + goto again; } mutex_unlock(&workqueue_mutex); } @@ -880,6 +887,7 @@ static int __devinit workqueue_cpu_callb cleanup_workqueue_thread(wq, hotcpu); list_for_each_entry(wq, &workqueues, list) take_over_work(wq, hotcpu); + hotplug_sequence++; break; case CPU_LOCK_RELEASE: _