Merge branch 'WQ_PERCPU' into for-6.17

Author: htejun

Documentation/core-api/workqueue.rst

@@ -183,6 +183,12 @@ resources, scheduled and executed.
   BH work items cannot sleep. All other features such as delayed queueing,
   flushing and canceling are supported.
 
+``WQ_PERCPU``
+  Work items queued to a per-cpu wq are bound to a specific CPU.
+  This flag is the right choice when cpu locality is important.
+
+  This flag is the complement of ``WQ_UNBOUND``.
+
 ``WQ_UNBOUND``
   Work items queued to an unbound wq are served by the special
   worker-pools which host workers which are not bound to any

include/linux/workqueue.h

@@ -402,6 +402,7 @@ enum wq_flags {
 	 * http://thread.gmane.org/gmane.linux.kernel/1480396
 	 */
 	WQ_POWER_EFFICIENT	= 1 << 7,
+	WQ_PERCPU		= 1 << 8, /* bound to a specific cpu */
 
 	__WQ_DESTROYING		= 1 << 15, /* internal: workqueue is destroying */
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
@@ -428,7 +429,7 @@ enum wq_consts {
 /*
  * System-wide workqueues which are always present.
  *
- * system_wq is the one used by schedule[_delayed]_work[_on]().
+ * system_percpu_wq is the one used by schedule[_delayed]_work[_on]().
  * Multi-CPU multi-threaded.  There are users which expect relatively
  * short queue flush time.  Don't queue works which can run for too
  * long.
@@ -439,7 +440,7 @@ enum wq_consts {
  * system_long_wq is similar to system_wq but may host long running
  * works.  Queue flushing might take relatively long.
  *
- * system_unbound_wq is unbound workqueue.  Workers are not bound to
+ * system_dfl_wq is unbound workqueue.  Workers are not bound to
  * any specific CPU, not concurrency managed, and all queued works are
  * executed immediately as long as max_active limit is not reached and
  * resources are available.
@@ -456,10 +457,12 @@ enum wq_consts {
  * system_bh[_highpri]_wq are convenience interface to softirq. BH work items
  * are executed in the queueing CPU's BH context in the queueing order.
  */
-extern struct workqueue_struct *system_wq;
+extern struct workqueue_struct *system_wq; /* use system_percpu_wq, this will be removed */
+extern struct workqueue_struct *system_percpu_wq;
 extern struct workqueue_struct *system_highpri_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_unbound_wq;
+extern struct workqueue_struct *system_dfl_wq;
 extern struct workqueue_struct *system_freezable_wq;
 extern struct workqueue_struct *system_power_efficient_wq;
 extern struct workqueue_struct *system_freezable_power_efficient_wq;

kernel/workqueue.c

@@ -505,12 +505,16 @@ static struct kthread_worker *pwq_release_worker __ro_after_init;
 
 struct workqueue_struct *system_wq __ro_after_init;
 EXPORT_SYMBOL(system_wq);
+struct workqueue_struct *system_percpu_wq __ro_after_init;
+EXPORT_SYMBOL(system_percpu_wq);
 struct workqueue_struct *system_highpri_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_highpri_wq);
 struct workqueue_struct *system_long_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_long_wq);
 struct workqueue_struct *system_unbound_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_unbound_wq);
+struct workqueue_struct *system_dfl_wq __ro_after_init;
+EXPORT_SYMBOL_GPL(system_dfl_wq);
 struct workqueue_struct *system_freezable_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_freezable_wq);
 struct workqueue_struct *system_power_efficient_wq __ro_after_init;
@@ -7826,10 +7830,11 @@ void __init workqueue_init_early(void)
 	}
 
 	system_wq = alloc_workqueue("events", 0, 0);
+	system_percpu_wq = alloc_workqueue("events", 0, 0);
 	system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0);
 	system_long_wq = alloc_workqueue("events_long", 0, 0);
-	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
-					    WQ_MAX_ACTIVE);
+	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
+	system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
 	system_freezable_wq = alloc_workqueue("events_freezable",
 					      WQ_FREEZABLE, 0);
 	system_power_efficient_wq = alloc_workqueue("events_power_efficient",
@@ -7840,8 +7845,8 @@ void __init workqueue_init_early(void)
 	system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0);
 	system_bh_highpri_wq = alloc_workqueue("events_bh_highpri",
 					       WQ_BH | WQ_HIGHPRI, 0);
-	BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
-	       !system_unbound_wq || !system_freezable_wq ||
+	BUG_ON(!system_wq || !system_percpu_wq|| !system_highpri_wq || !system_long_wq ||
+	       !system_unbound_wq || !system_freezable_wq || !system_dfl_wq ||
 	       !system_power_efficient_wq ||
 	       !system_freezable_power_efficient_wq ||
 	       !system_bh_wq || !system_bh_highpri_wq);