workqueues: make get_online_cpus() useable for work->func()
workqueue_cpu_callback(CPU_DEAD) flushes cwq->thread under
cpu_maps_update_begin(). This means that the multithreaded workqueues
can't use get_online_cpus() due to the possible deadlock, very bad and
very old problem.
Introduce the new state, CPU_POST_DEAD, which is called after
cpu_hotplug_done() but before cpu_maps_update_done().
Change workqueue_cpu_callback() to use CPU_POST_DEAD instead of CPU_DEAD.
This means that create/destroy functions can't rely on get_online_cpus()
any longer and should take cpu_add_remove_lock instead.
[akpm@linux-foundation.org: fix CONFIG_SMP=n]
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Max Krasnyansky <maxk@qualcomm.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 5fbffd3..828e582 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -828,7 +828,7 @@
err = create_workqueue_thread(cwq, singlethread_cpu);
start_workqueue_thread(cwq, -1);
} else {
- get_online_cpus();
+ cpu_maps_update_begin();
spin_lock(&workqueue_lock);
list_add(&wq->list, &workqueues);
spin_unlock(&workqueue_lock);
@@ -840,7 +840,7 @@
err = create_workqueue_thread(cwq, cpu);
start_workqueue_thread(cwq, cpu);
}
- put_online_cpus();
+ cpu_maps_update_done();
}
if (err) {
@@ -854,8 +854,8 @@
static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
{
/*
- * Our caller is either destroy_workqueue() or CPU_DEAD,
- * get_online_cpus() protects cwq->thread.
+ * Our caller is either destroy_workqueue() or CPU_POST_DEAD,
+ * cpu_add_remove_lock protects cwq->thread.
*/
if (cwq->thread == NULL)
return;
@@ -865,7 +865,7 @@
flush_cpu_workqueue(cwq);
/*
- * If the caller is CPU_DEAD and cwq->worklist was not empty,
+ * If the caller is CPU_POST_DEAD and cwq->worklist was not empty,
* a concurrent flush_workqueue() can insert a barrier after us.
* However, in that case run_workqueue() won't return and check
* kthread_should_stop() until it flushes all work_struct's.
@@ -889,14 +889,14 @@
const cpumask_t *cpu_map = wq_cpu_map(wq);
int cpu;
- get_online_cpus();
+ cpu_maps_update_begin();
spin_lock(&workqueue_lock);
list_del(&wq->list);
spin_unlock(&workqueue_lock);
for_each_cpu_mask_nr(cpu, *cpu_map)
cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
- put_online_cpus();
+ cpu_maps_update_done();
free_percpu(wq->cpu_wq);
kfree(wq);
@@ -935,7 +935,7 @@
case CPU_UP_CANCELED:
start_workqueue_thread(cwq, -1);
- case CPU_DEAD:
+ case CPU_POST_DEAD:
cleanup_workqueue_thread(cwq);
break;
}
@@ -943,7 +943,7 @@
switch (action) {
case CPU_UP_CANCELED:
- case CPU_DEAD:
+ case CPU_POST_DEAD:
cpu_clear(cpu, cpu_populated_map);
}