1 files changed, 53 insertions, 27 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c6b79b3675c3..45320e27a16c 100644
--- a/kernel/workqueue.c
+++ b/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 @@ restart:
 		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 @@ done:
 	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 ||