workqueue: fix schedule_on_each_cpu()
PATCH 1/1 workqueue: fix schedule_on_each_cpu()
From: Ingo Molnar <[email protected]>
Subject: [patch] workqueue: fix schedule_on_each_cpu()
fix the schedule_on_each_cpu() implementation: __queue_work() is now stricter, hence set the work-pending bit before passing in the new work.
(found in the -rt tree, using Peter Zijlstra's files-lock scalability patchset)
Signed-off-by Ingo Molnar <[email protected]>
--- kernel/workqueue.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
kernel/workqueue.c +5 -3
@@ -637,9 +637,11 @@ int schedule_on_each_cpu(work_func_t funmutex_lock (&workqueue_mutex);for_each_online_cpu (cpu) { -INIT_WORK (per_cpu_ptr (works, cpu), func); -__queue_work (per_cpu_ptr (keventd_wq->cpu_wq, cpu), -per_cpu_ptr (works, cpu)); +struct work_struct *work =per_cpu_ptr (works, cpu); + +INIT_WORK (work, func); +set_bit (WORK_STRUCT_PENDING ,work_data_bits (work)); +__queue_work (per_cpu_ptr (keventd_wq->cpu_wq, cpu), work); }mutex_unlock (&workqueue_mutex);flush_workqueue (keventd_wq);