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]);
}
*/
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)
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);
}
/**
u32 hash = wqattrs_hash(attrs);
struct worker_pool *pool;
int node;
+ int target_node = NUMA_NO_NODE;
lockdep_assert_held(&wq_pool_mutex);
}
}
+ /* if cpumask is contained inside a NUMA node, we belong to that node */
+ if (wq_numa_enabled) {
+ for_each_node(node) {
+ if (cpumask_subset(attrs->cpumask,
+ wq_numa_possible_cpumask[node])) {
+ target_node = node;
+ break;
+ }
+ }
+ }
+
/* nope, create a new one */
- pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_node);
if (!pool || init_worker_pool(pool) < 0)
goto fail;
lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */
copy_workqueue_attrs(pool->attrs, attrs);
+ pool->node = target_node;
/*
* no_numa isn't a worker_pool attribute, always clear it. See
*/
pool->attrs->no_numa = false;
- /* if cpumask is contained inside a NUMA node, we belong to that node */
- if (wq_numa_enabled) {
- for_each_node(node) {
- if (cpumask_subset(pool->attrs->cpumask,
- wq_numa_possible_cpumask[node])) {
- pool->node = node;
- break;
- }
- }
- }
-
if (worker_pool_assign_id(pool) < 0)
goto fail;
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) {