ARM64: sched: fix bug: remove printk while schedule is in progress

[firefly-linux-kernel-4.4.55.git] / kernel / workqueue.c

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c579dbab2e36ab20dd94a5f753a480df17ae28ff..2c2f971f3e759df3c812d749740047f05864931b 100644 (file)
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -568,6 +568,16 @@ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
                                                  int node)
 {
        assert_rcu_or_wq_mutex_or_pool_mutex(wq);
+
+       /*
+        * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
+        * delayed item is pending.  The plan is to keep CPU -> NODE
+        * mapping valid and stable across CPU on/offlines.  Once that
+        * happens, this workaround can be removed.
+        */
+       if (unlikely(node == NUMA_NO_NODE))
+               return wq->dfl_pwq;
+
        return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
 }
 
@@ -639,6 +649,35 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
         */
        smp_wmb();
        set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
+       /*
+        * The following mb guarantees that previous clear of a PENDING bit
+        * will not be reordered with any speculative LOADS or STORES from
+        * work->current_func, which is executed afterwards.  This possible
+        * reordering can lead to a missed execution on attempt to qeueue
+        * the same @work.  E.g. consider this case:
+        *
+        *   CPU#0                         CPU#1
+        *   ----------------------------  --------------------------------
+        *
+        * 1  STORE event_indicated
+        * 2  queue_work_on() {
+        * 3    test_and_set_bit(PENDING)
+        * 4 }                             set_..._and_clear_pending() {
+        * 5                                 set_work_data() # clear bit
+        * 6                                 smp_mb()
+        * 7                               work->current_func() {
+        * 8                                  LOAD event_indicated
+        *                                 }
+        *
+        * Without an explicit full barrier speculative LOAD on line 8 can
+        * be executed before CPU#0 does STORE on line 1.  If that happens,
+        * CPU#0 observes the PENDING bit is still set and new execution of
+        * a @work is not queued in a hope, that CPU#1 will eventually
+        * finish the queued @work.  Meanwhile CPU#1 does not see
+        * event_indicated is set, because speculative LOAD was executed
+        * before actual STORE.
+        */
+       smp_mb();
 }
 
 static void clear_work_data(struct work_struct *work)
@@ -1458,13 +1497,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
        timer_stats_timer_set_start_info(&dwork->timer);
 
        dwork->wq = wq;
-       /* timer isn't guaranteed to run in this cpu, record earlier */
-       if (cpu == WORK_CPU_UNBOUND)
-               cpu = raw_smp_processor_id();
        dwork->cpu = cpu;
        timer->expires = jiffies + delay;
 
-       add_timer_on(timer, cpu);
+       if (unlikely(cpu != WORK_CPU_UNBOUND))
+               add_timer_on(timer, cpu);
+       else
+               add_timer(timer);
 }
 
 /**
@@ -4418,6 +4457,17 @@ static void rebind_workers(struct worker_pool *pool)
                                                  pool->attrs->cpumask) < 0);
 
        spin_lock_irq(&pool->lock);
+
+       /*
+        * XXX: CPU hotplug notifiers are weird and can call DOWN_FAILED
+        * w/o preceding DOWN_PREPARE.  Work around it.  CPU hotplug is
+        * being reworked and this can go away in time.
+        */
+       if (!(pool->flags & POOL_DISASSOCIATED)) {
+               spin_unlock_irq(&pool->lock);
+               return;
+       }
+
        pool->flags &= ~POOL_DISASSOCIATED;
 
        for_each_pool_worker(worker, pool) {