workqueues: shrink cpu_populated_map when CPU dies

When cpu_populated_map was introduced, it was supposed that cwq->thread can
survive after CPU_DEAD, that is why we never shrink cpu_populated_map.

This is not very nice, we can safely remove the already dead CPU from the map.
 The only required change is that destroy_workqueue() must hold the hotplug
lock until it destroys all cwq->thread's, to protect the cpu_populated_map.
We could make the local copy of cpu mask and drop the lock, but
sizeof(cpumask_t) may be very large.

Also, fix the comment near queue_work().  Unless _cpu_down() happens we do
guarantee the cpu-affinity of the work_struct, and we have users which rely on
this.

[akpm@linux-foundation.org: repair comment]
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 9 insertions, 4 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 00ff4d08e370..1ad0ee489cd1 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -158,8 +158,8 @@ static void __queue_work(struct cpu_workqueue_struct *cwq,
  *
  * Returns 0 if @work was already on a queue, non-zero otherwise.
  *
- * We queue the work to the CPU it was submitted, but there is no
- * guarantee that it will be processed by that CPU.
+ * We queue the work to the CPU on which it was submitted, but if the CPU dies
+ * it can be processed by another CPU.
  */
 int queue_work(struct workqueue_struct *wq, struct work_struct *work)
 {
@@ -815,12 +815,12 @@ void destroy_workqueue(struct workqueue_struct *wq)
         spin_lock(&workqueue_lock);
         list_del(&wq->list);
         spin_unlock(&workqueue_lock);
-        put_online_cpus();
 
         for_each_cpu_mask(cpu, *cpu_map) {
                 cwq = per_cpu_ptr(wq->cpu_wq, cpu);
                 cleanup_workqueue_thread(cwq, cpu);
         }
+        put_online_cpus();
 
         free_percpu(wq->cpu_wq);
         kfree(wq);
@@ -838,7 +838,6 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
         action &= ~CPU_TASKS_FROZEN;
 
         switch (action) {
-
         case CPU_UP_PREPARE:
                 cpu_set(cpu, cpu_populated_map);
         }
@@ -866,6 +865,12 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
                 }
         }
 
+        switch (action) {
+        case CPU_UP_CANCELED:
+        case CPU_DEAD:
+                cpu_clear(cpu, cpu_populated_map);
+        }
+
         return NOTIFY_OK;
 }