padata: use separate workqueues for parallel and serial work

padata currently uses one per-CPU workqueue per instance for all work.

Prepare for running parallel jobs on an unbound workqueue by introducing
dedicated workqueues for parallel and serial work.
Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: linux-crypto@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

include/linux/padata.h

@@ -127,7 +127,8 @@ struct parallel_data {
  * struct padata_instance - The overall control structure.
  *
  * @cpu_notifier: cpu hotplug notifier.
- * @wq: The workqueue in use.
+ * @parallel_wq: The workqueue used for parallel work.
+ * @serial_wq: The workqueue used for serial work.
  * @pd: The internal control structure.
  * @cpumask: User supplied cpumasks for parallel and serial works.
  * @cpumask_change_notifier: Notifiers chain for user-defined notify
@@ -139,7 +140,8 @@ struct parallel_data {
  */
 struct padata_instance {
 	struct hlist_node		 node;
-	struct workqueue_struct		*wq;
+	struct workqueue_struct		*parallel_wq;
+	struct workqueue_struct		*serial_wq;
 	struct parallel_data		*pd;
 	struct padata_cpumask		cpumask;
 	struct blocking_notifier_head	 cpumask_change_notifier;

kernel/padata.c

@@ -152,7 +152,7 @@ int padata_do_parallel(struct padata_instance *pinst,
 	list_add_tail(&padata->list, &queue->parallel.list);
 	spin_unlock(&queue->parallel.lock);
 
-	queue_work_on(target_cpu, pinst->wq, &queue->work);
+	queue_work_on(target_cpu, pinst->parallel_wq, &queue->work);
 
 out:
 	rcu_read_unlock_bh();
@@ -261,7 +261,7 @@ static void padata_reorder(struct parallel_data *pd)
 		list_add_tail(&padata->list, &squeue->serial.list);
 		spin_unlock(&squeue->serial.lock);
 
-		queue_work_on(cb_cpu, pinst->wq, &squeue->work);
+		queue_work_on(cb_cpu, pinst->serial_wq, &squeue->work);
 	}
 
 	spin_unlock_bh(&pd->lock);
@@ -278,7 +278,7 @@ static void padata_reorder(struct parallel_data *pd)
 
 	next_queue = per_cpu_ptr(pd->pqueue, pd->cpu);
 	if (!list_empty(&next_queue->reorder.list))
-		queue_work(pinst->wq, &pd->reorder_work);
+		queue_work(pinst->serial_wq, &pd->reorder_work);
 }
 
 static void invoke_padata_reorder(struct work_struct *work)
@@ -818,7 +818,8 @@ static void __padata_free(struct padata_instance *pinst)
 	padata_free_pd(pinst->pd);
 	free_cpumask_var(pinst->cpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.cbcpu);
-	destroy_workqueue(pinst->wq);
+	destroy_workqueue(pinst->serial_wq);
+	destroy_workqueue(pinst->parallel_wq);
 	kfree(pinst);
 }
 
@@ -967,18 +968,23 @@ static struct padata_instance *padata_alloc(const char *name,
 	if (!pinst)
 		goto err;
 
-	pinst->wq = alloc_workqueue("%s", WQ_MEM_RECLAIM | WQ_CPU_INTENSIVE,
-				    1, name);
-	if (!pinst->wq)
+	pinst->parallel_wq = alloc_workqueue("%s_parallel", WQ_MEM_RECLAIM |
+					     WQ_CPU_INTENSIVE, 1, name);
+	if (!pinst->parallel_wq)
 		goto err_free_inst;
 
 	get_online_cpus();
 
-	if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
+	pinst->serial_wq = alloc_workqueue("%s_serial", WQ_MEM_RECLAIM |
+					   WQ_CPU_INTENSIVE, 1, name);
+	if (!pinst->serial_wq)
 		goto err_put_cpus;
+
+	if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
+		goto err_free_serial_wq;
 	if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) {
 		free_cpumask_var(pinst->cpumask.pcpu);
-		goto err_put_cpus;
+		goto err_free_serial_wq;
 	}
 	if (!padata_validate_cpumask(pinst, pcpumask) ||
 	    !padata_validate_cpumask(pinst, cbcpumask))
@@ -1010,9 +1016,11 @@ static struct padata_instance *padata_alloc(const char *name,
 err_free_masks:
 	free_cpumask_var(pinst->cpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.cbcpu);
+err_free_serial_wq:
+	destroy_workqueue(pinst->serial_wq);
 err_put_cpus:
 	put_online_cpus();
-	destroy_workqueue(pinst->wq);
+	destroy_workqueue(pinst->parallel_wq);
 err_free_inst:
 	kfree(pinst);
 err: