Merge tag 'wq-for-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue updates from Tejun Heo:

 - WQ_PERCPU was added to remaining alloc_workqueue() users and
   system_wq usage was replaced with system_percpu_wq and
   system_unbound_wq with system_dfl_wq.

   These are equivalent conversions with no functional changes,
   preparing for switching default to unbound workqueues from percpu.

 - A handshake mechanism was added for canceling BH workers to avoid
   live lock scenarios under PREEMPT_RT.

 - Unnecessary rcu_read_lock/unlock() calls were dropped in
   wq_watchdog_timer_fn() and workqueue_congested().

 - Documentation was fixed to resolve texinfodocs warnings.

* tag 'wq-for-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: fix texinfodocs warning for WQ_* flags reference
  workqueue: WQ_PERCPU added to alloc_workqueue users
  workqueue: replace use of system_wq with system_percpu_wq
  workqueue: replace use of system_unbound_wq with system_dfl_wq
  workqueue: Provide a handshake for canceling BH workers
  workqueue: Remove rcu_read_lock/unlock() in wq_watchdog_timer_fn()
  workqueue: Remove redundant rcu_read_lock/unlock() in workqueue_congested()

include/linux/workqueue.h

@@ -410,7 +410,7 @@ enum wq_flags {
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	/* BH wq only allows the following flags */
-	__WQ_BH_ALLOWS		= WQ_BH | WQ_HIGHPRI,
+	__WQ_BH_ALLOWS		= WQ_BH | WQ_HIGHPRI | WQ_PERCPU,
 };
 
 enum wq_consts {
@@ -434,10 +434,10 @@ enum wq_consts {
  * short queue flush time.  Don't queue works which can run for too
  * long.
  *
- * system_highpri_wq is similar to system_wq but for work items which
+ * system_highpri_wq is similar to system_percpu_wq but for work items which
  * require WQ_HIGHPRI.
  *
- * system_long_wq is similar to system_wq but may host long running
+ * system_long_wq is similar to system_percpu_wq but may host long running
  * works.  Queue flushing might take relatively long.
  *
  * system_dfl_wq is unbound workqueue.  Workers are not bound to
@@ -445,13 +445,13 @@ enum wq_consts {
  * executed immediately as long as max_active limit is not reached and
  * resources are available.
  *
- * system_freezable_wq is equivalent to system_wq except that it's
+ * system_freezable_wq is equivalent to system_percpu_wq except that it's
  * freezable.
  *
  * *_power_efficient_wq are inclined towards saving power and converted
  * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise,
  * they are same as their non-power-efficient counterparts - e.g.
- * system_power_efficient_wq is identical to system_wq if
+ * system_power_efficient_wq is identical to system_percpu_wq if
  * 'wq_power_efficient' is disabled.  See WQ_POWER_EFFICIENT for more info.
  *
  * system_bh[_highpri]_wq are convenience interface to softirq. BH work items
@@ -502,7 +502,7 @@ void workqueue_softirq_dead(unsigned int cpu);
  * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means
  * that the sum of per-node max_active's may be larger than @max_active.
  *
- * For detailed information on %WQ_* flags, please refer to
+ * For detailed information on %WQ_\* flags, please refer to
  * Documentation/core-api/workqueue.rst.
  *
  * RETURNS:
@@ -570,7 +570,7 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active,
 	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
-	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_PERCPU, 1, (name))
 #define create_freezable_workqueue(name)				\
 	alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND |	\
 			WQ_MEM_RECLAIM, 1, (name))
@@ -708,7 +708,7 @@ static inline bool mod_delayed_work(struct workqueue_struct *wq,
  */
 static inline bool schedule_work_on(int cpu, struct work_struct *work)
 {
-	return queue_work_on(cpu, system_wq, work);
+	return queue_work_on(cpu, system_percpu_wq, work);
 }
 
 /**
@@ -727,7 +727,7 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work)
  */
 static inline bool schedule_work(struct work_struct *work)
 {
-	return queue_work(system_wq, work);
+	return queue_work(system_percpu_wq, work);
 }
 
 /**
@@ -770,21 +770,21 @@ extern void __warn_flushing_systemwide_wq(void)
 #define flush_scheduled_work()						\
 ({									\
 	__warn_flushing_systemwide_wq();				\
-	__flush_workqueue(system_wq);					\
+	__flush_workqueue(system_percpu_wq);					\
 })
 
 #define flush_workqueue(wq)						\
 ({									\
 	struct workqueue_struct *_wq = (wq);				\
 									\
-	if ((__builtin_constant_p(_wq == system_wq) &&			\
-	     _wq == system_wq) ||					\
+	if ((__builtin_constant_p(_wq == system_percpu_wq) &&			\
+	     _wq == system_percpu_wq) ||					\
 	    (__builtin_constant_p(_wq == system_highpri_wq) &&		\
 	     _wq == system_highpri_wq) ||				\
 	    (__builtin_constant_p(_wq == system_long_wq) &&		\
 	     _wq == system_long_wq) ||					\
-	    (__builtin_constant_p(_wq == system_unbound_wq) &&		\
-	     _wq == system_unbound_wq) ||				\
+	    (__builtin_constant_p(_wq == system_dfl_wq) &&		\
+	     _wq == system_dfl_wq) ||				\
 	    (__builtin_constant_p(_wq == system_freezable_wq) &&	\
 	     _wq == system_freezable_wq) ||				\
 	    (__builtin_constant_p(_wq == system_power_efficient_wq) &&	\
@@ -807,7 +807,7 @@ extern void __warn_flushing_systemwide_wq(void)
 static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
 					    unsigned long delay)
 {
-	return queue_delayed_work_on(cpu, system_wq, dwork, delay);
+	return queue_delayed_work_on(cpu, system_percpu_wq, dwork, delay);
 }
 
 /**
@@ -821,7 +821,7 @@ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
 static inline bool schedule_delayed_work(struct delayed_work *dwork,
 					 unsigned long delay)
 {
-	return queue_delayed_work(system_wq, dwork, delay);
+	return queue_delayed_work(system_percpu_wq, dwork, delay);
 }
 
 #ifndef CONFIG_SMP

kernel/workqueue.c

@@ -222,7 +222,9 @@ struct worker_pool {
 	struct workqueue_attrs	*attrs;		/* I: worker attributes */
 	struct hlist_node	hash_node;	/* PL: unbound_pool_hash node */
 	int			refcnt;		/* PL: refcnt for unbound pools */
-
+#ifdef CONFIG_PREEMPT_RT
+	spinlock_t		cb_lock;	/* BH worker cancel lock */
+#endif
 	/*
 	 * Destruction of pool is RCU protected to allow dereferences
 	 * from get_work_pool().
@@ -2930,7 +2932,7 @@ static void idle_worker_timeout(struct timer_list *t)
 	raw_spin_unlock_irq(&pool->lock);
 
 	if (do_cull)
-		queue_work(system_unbound_wq, &pool->idle_cull_work);
+		queue_work(system_dfl_wq, &pool->idle_cull_work);
 }
 
 /**
@@ -3078,6 +3080,31 @@ __acquires(&pool->lock)
 		goto restart;
 }
 
+#ifdef CONFIG_PREEMPT_RT
+static void worker_lock_callback(struct worker_pool *pool)
+{
+	spin_lock(&pool->cb_lock);
+}
+
+static void worker_unlock_callback(struct worker_pool *pool)
+{
+	spin_unlock(&pool->cb_lock);
+}
+
+static void workqueue_callback_cancel_wait_running(struct worker_pool *pool)
+{
+	spin_lock(&pool->cb_lock);
+	spin_unlock(&pool->cb_lock);
+}
+
+#else
+
+static void worker_lock_callback(struct worker_pool *pool) { }
+static void worker_unlock_callback(struct worker_pool *pool) { }
+static void workqueue_callback_cancel_wait_running(struct worker_pool *pool) { }
+
+#endif
+
 /**
  * manage_workers - manage worker pool
  * @worker: self
@@ -3557,6 +3584,7 @@ static void bh_worker(struct worker *worker)
 	int nr_restarts = BH_WORKER_RESTARTS;
 	unsigned long end = jiffies + BH_WORKER_JIFFIES;
 
+	worker_lock_callback(pool);
 	raw_spin_lock_irq(&pool->lock);
 	worker_leave_idle(worker);
 
@@ -3585,6 +3613,7 @@ static void bh_worker(struct worker *worker)
 	worker_enter_idle(worker);
 	kick_pool(pool);
 	raw_spin_unlock_irq(&pool->lock);
+	worker_unlock_callback(pool);
 }
 
 /*
@@ -4222,17 +4251,17 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
 		    (data & WORK_OFFQ_BH)) {
 			/*
 			 * On RT, prevent a live lock when %current preempted
-			 * soft interrupt processing or prevents ksoftirqd from
-			 * running by keeping flipping BH. If the BH work item
-			 * runs on a different CPU then this has no effect other
-			 * than doing the BH disable/enable dance for nothing.
-			 * This is copied from
-			 * kernel/softirq.c::tasklet_unlock_spin_wait().
+			 * soft interrupt processing by blocking on lock which
+			 * is owned by the thread invoking the callback.
 			 */
 			while (!try_wait_for_completion(&barr.done)) {
 				if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
-					local_bh_disable();
-					local_bh_enable();
+					struct worker_pool *pool;
+
+					guard(rcu)();
+					pool = get_work_pool(work);
+					if (pool)
+						workqueue_callback_cancel_wait_running(pool);
 				} else {
 					cpu_relax();
 				}
@@ -4782,6 +4811,9 @@ static int init_worker_pool(struct worker_pool *pool)
 	ida_init(&pool->worker_ida);
 	INIT_HLIST_NODE(&pool->hash_node);
 	pool->refcnt = 1;
+#ifdef CONFIG_PREEMPT_RT
+	spin_lock_init(&pool->cb_lock);
+#endif
 
 	/* shouldn't fail above this point */
 	pool->attrs = alloc_workqueue_attrs();
@@ -6046,7 +6078,6 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
 	struct pool_workqueue *pwq;
 	bool ret;
 
-	rcu_read_lock();
 	preempt_disable();
 
 	if (cpu == WORK_CPU_UNBOUND)
@@ -6056,7 +6087,6 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
 	ret = !list_empty(&pwq->inactive_works);
 
 	preempt_enable();
-	rcu_read_unlock();
 
 	return ret;
 }
@@ -7546,8 +7576,6 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 	if (!thresh)
 		return;
 
-	rcu_read_lock();
-
 	for_each_pool(pool, pi) {
 		unsigned long pool_ts, touched, ts;
 
@@ -7589,8 +7617,6 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 
 	}
 
-	rcu_read_unlock();
-
 	if (lockup_detected)
 		show_all_workqueues();
 
@@ -7642,7 +7668,7 @@ static int wq_watchdog_param_set_thresh(const char *val,
 	if (ret)
 		return ret;
 
-	if (system_wq)
+	if (system_percpu_wq)
 		wq_watchdog_set_thresh(thresh);
 	else
 		wq_watchdog_thresh = thresh;
@@ -7802,22 +7828,22 @@ void __init workqueue_init_early(void)
 		ordered_wq_attrs[i] = attrs;
 	}
 
-	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_wq = alloc_workqueue("events", WQ_PERCPU, 0);
+	system_percpu_wq = alloc_workqueue("events", WQ_PERCPU, 0);
+	system_highpri_wq = alloc_workqueue("events_highpri",
+					    WQ_HIGHPRI | WQ_PERCPU, 0);
+	system_long_wq = alloc_workqueue("events_long", WQ_PERCPU, 0);
 	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);
+					      WQ_FREEZABLE | WQ_PERCPU, 0);
 	system_power_efficient_wq = alloc_workqueue("events_power_efficient",
-					      WQ_POWER_EFFICIENT, 0);
+					      WQ_POWER_EFFICIENT | WQ_PERCPU, 0);
 	system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient",
-					      WQ_FREEZABLE | WQ_POWER_EFFICIENT,
-					      0);
-	system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0);
+					      WQ_FREEZABLE | WQ_POWER_EFFICIENT | WQ_PERCPU, 0);
+	system_bh_wq = alloc_workqueue("events_bh", WQ_BH | WQ_PERCPU, 0);
 	system_bh_highpri_wq = alloc_workqueue("events_bh_highpri",
-					       WQ_BH | WQ_HIGHPRI, 0);
+					       WQ_BH | WQ_HIGHPRI | WQ_PERCPU, 0);
 	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 ||