workqueue: Call wq_update_unbound_numa() on all CPUs in NUMA node on CPU hotplug

When a CPU went online or offline, wq_update_unbound_numa() was called only
on the CPU which was going up or down. This works fine because all CPUs on
the same NUMA node share the same pool_workqueue slot - one CPU updating it
updates it for everyone in the node.

However, future changes will make each CPU use a separate pool_workqueue
even when they're sharing the same worker_pool, which requires updating
pool_workqueue's for all CPUs which may be sharing the same pool_workqueue
on hotplug.

To accommodate the planned changes, this patch updates
workqueue_on/offline_cpu() so that they call wq_update_unbound_numa() for
all CPUs sharing the same NUMA node as the CPU going up or down. In the
current code, the second+ calls would be noops and there shouldn't be any
behavior changes.

* As wq_update_unbound_numa() is now called on multiple CPUs per each
  hotplug event, @cpu is renamed to @hotplug_cpu and another @cpu argument
  is added. The former indicates the CPU being hot[un]plugged and the latter
  the CPU whose pool_workqueue is being updated.

* In wq_update_unbound_numa(), cpu_off is renamed to off_cpu for consistency
  with the new @hotplug_cpu.
Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/workqueue.c

@@ -4422,7 +4422,8 @@ int apply_workqueue_attrs(struct workqueue_struct *wq,
 /**
  * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug
  * @wq: the target workqueue
- * @cpu: the CPU coming up or going down
+ * @cpu: the CPU to update pool association for
+ * @hotplug_cpu: the CPU coming up or going down
  * @online: whether @cpu is coming up or going down
  *
  * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and
@@ -4442,10 +4443,10 @@ int apply_workqueue_attrs(struct workqueue_struct *wq,
  * CPU_DOWN_PREPARE.
  */
 static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
-				   bool online)
+				   int hotplug_cpu, bool online)
 {
 	int node = cpu_to_node(cpu);
-	int cpu_off = online ? -1 : cpu;
+	int off_cpu = online ? -1 : hotplug_cpu;
 	struct pool_workqueue *old_pwq = NULL, *pwq;
 	struct workqueue_attrs *target_attrs;
 	cpumask_t *cpumask;
@@ -4473,7 +4474,7 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	 * and create a new one if they don't match.  If the target cpumask
 	 * equals the default pwq's, the default pwq should be used.
 	 */
-	if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, cpu_off, cpumask)) {
+	if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, off_cpu, cpumask)) {
 		if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask))
 			return;
 	} else {
@@ -5514,8 +5515,15 @@ int workqueue_online_cpu(unsigned int cpu)
 	}
 
 	/* update NUMA affinity of unbound workqueues */
-	list_for_each_entry(wq, &workqueues, list)
-		wq_update_unbound_numa(wq, cpu, true);
+	list_for_each_entry(wq, &workqueues, list) {
+		int tcpu;
+
+		for_each_possible_cpu(tcpu) {
+			if (cpu_to_node(tcpu) == cpu_to_node(cpu)) {
+				wq_update_unbound_numa(wq, tcpu, cpu, true);
+			}
+		}
+	}
 
 	mutex_unlock(&wq_pool_mutex);
 	return 0;
@@ -5533,8 +5541,15 @@ int workqueue_offline_cpu(unsigned int cpu)
 
 	/* update NUMA affinity of unbound workqueues */
 	mutex_lock(&wq_pool_mutex);
-	list_for_each_entry(wq, &workqueues, list)
-		wq_update_unbound_numa(wq, cpu, false);
+	list_for_each_entry(wq, &workqueues, list) {
+		int tcpu;
+
+		for_each_possible_cpu(tcpu) {
+			if (cpu_to_node(tcpu) == cpu_to_node(cpu)) {
+				wq_update_unbound_numa(wq, tcpu, cpu, false);
+			}
+		}
+	}
 	mutex_unlock(&wq_pool_mutex);
 
 	return 0;
@@ -6509,7 +6524,8 @@ void __init workqueue_init(void)
 	}
 
 	list_for_each_entry(wq, &workqueues, list) {
-		wq_update_unbound_numa(wq, smp_processor_id(), true);
+		wq_update_unbound_numa(wq, smp_processor_id(), smp_processor_id(),
+				       true);
 		WARN(init_rescuer(wq),
 		     "workqueue: failed to create early rescuer for %s",
 		     wq->name);