Merge branch 'for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue updates from Tejun Heo:
 "Nothing too interesting. An optimization to short-circuit noop cpumask
  updates, debug dump code reorg, and doc update"

* 'for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: doc: Call out the non-reentrance conditions
  workqueue: Introduce show_one_worker_pool and show_one_workqueue.
  workqueue: make sysfs of unbound kworker cpumask more clever

Author: torvalds

Documentation/core-api/workqueue.rst

@@ -216,10 +216,6 @@ resources, scheduled and executed.
 
   This flag is meaningless for unbound wq.
 
-Note that the flag ``WQ_NON_REENTRANT`` no longer exists as all
-workqueues are now non-reentrant - any work item is guaranteed to be
-executed by at most one worker system-wide at any given time.
-
 
 ``max_active``
 --------------
@@ -391,6 +387,23 @@ the stack trace of the offending worker thread. ::
 The work item's function should be trivially visible in the stack
 trace.
 
+Non-reentrance Conditions
+=========================
+
+Workqueue guarantees that a work item cannot be re-entrant if the following
+conditions hold after a work item gets queued:
+
+        1. The work function hasn't been changed.
+        2. No one queues the work item to another workqueue.
+        3. The work item hasn't been reinitiated.
+
+In other words, if the above conditions hold, the work item is guaranteed to be
+executed by at most one worker system-wide at any given time.
+
+Note that requeuing the work item (to the same queue) in the self function
+doesn't break these conditions, so it's safe to do. Otherwise, caution is
+required when breaking the conditions inside a work function.
+
 
 Kernel Inline Documentations Reference
 ======================================

drivers/tty/sysrq.c

@@ -296,7 +296,7 @@ static const struct sysrq_key_op sysrq_showregs_op = {
 static void sysrq_handle_showstate(int key)
 {
 	show_state();
-	show_workqueue_state();
+	show_all_workqueues();
 }
 static const struct sysrq_key_op sysrq_showstate_op = {
 	.handler	= sysrq_handle_showstate,

include/linux/workqueue.h

@@ -469,7 +469,8 @@ extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
 extern unsigned int work_busy(struct work_struct *work);
 extern __printf(1, 2) void set_worker_desc(const char *fmt, ...);
 extern void print_worker_info(const char *log_lvl, struct task_struct *task);
-extern void show_workqueue_state(void);
+extern void show_all_workqueues(void);
+extern void show_one_workqueue(struct workqueue_struct *wq);
 extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task);
 
 /**

kernel/power/process.c

@@ -94,7 +94,7 @@ static int try_to_freeze_tasks(bool user_only)
 		       todo - wq_busy, wq_busy);
 
 		if (wq_busy)
-			show_workqueue_state();
+			show_all_workqueues();
 
 		if (!wakeup || pm_debug_messages_on) {
 			read_lock(&tasklist_lock);

kernel/workqueue.c

@@ -375,6 +375,7 @@ EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
 static int worker_thread(void *__worker);
 static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
 static void show_pwq(struct pool_workqueue *pwq);
+static void show_one_worker_pool(struct worker_pool *pool);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/workqueue.h>
@@ -4447,7 +4448,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
 			raw_spin_unlock_irq(&pwq->pool->lock);
 			mutex_unlock(&wq->mutex);
 			mutex_unlock(&wq_pool_mutex);
-			show_workqueue_state();
+			show_one_workqueue(wq);
 			return;
 		}
 		raw_spin_unlock_irq(&pwq->pool->lock);
@@ -4797,97 +4798,116 @@ static void show_pwq(struct pool_workqueue *pwq)
 }
 
 /**
- * show_workqueue_state - dump workqueue state
- *
- * Called from a sysrq handler or try_to_freeze_tasks() and prints out
- * all busy workqueues and pools.
+ * show_one_workqueue - dump state of specified workqueue
+ * @wq: workqueue whose state will be printed
  */
-void show_workqueue_state(void)
+void show_one_workqueue(struct workqueue_struct *wq)
 {
-	struct workqueue_struct *wq;
-	struct worker_pool *pool;
+	struct pool_workqueue *pwq;
+	bool idle = true;
 	unsigned long flags;
-	int pi;
-
-	rcu_read_lock();
-
-	pr_info("Showing busy workqueues and worker pools:\n");
-
-	list_for_each_entry_rcu(wq, &workqueues, list) {
-		struct pool_workqueue *pwq;
-		bool idle = true;
 
-		for_each_pwq(pwq, wq) {
-			if (pwq->nr_active || !list_empty(&pwq->inactive_works)) {
-				idle = false;
-				break;
-			}
+	for_each_pwq(pwq, wq) {
+		if (pwq->nr_active || !list_empty(&pwq->inactive_works)) {
+			idle = false;
+			break;
 		}
-		if (idle)
-			continue;
+	}
+	if (idle) /* Nothing to print for idle workqueue */
+		return;
 
-		pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags);
+	pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags);
 
-		for_each_pwq(pwq, wq) {
-			raw_spin_lock_irqsave(&pwq->pool->lock, flags);
-			if (pwq->nr_active || !list_empty(&pwq->inactive_works)) {
-				/*
-				 * Defer printing to avoid deadlocks in console
-				 * drivers that queue work while holding locks
-				 * also taken in their write paths.
-				 */
-				printk_deferred_enter();
-				show_pwq(pwq);
-				printk_deferred_exit();
-			}
-			raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
+	for_each_pwq(pwq, wq) {
+		raw_spin_lock_irqsave(&pwq->pool->lock, flags);
+		if (pwq->nr_active || !list_empty(&pwq->inactive_works)) {
 			/*
-			 * We could be printing a lot from atomic context, e.g.
-			 * sysrq-t -> show_workqueue_state(). Avoid triggering
-			 * hard lockup.
+			 * Defer printing to avoid deadlocks in console
+			 * drivers that queue work while holding locks
+			 * also taken in their write paths.
 			 */
-			touch_nmi_watchdog();
-		}
-	}
-
-	for_each_pool(pool, pi) {
-		struct worker *worker;
-		bool first = true;
-
-		raw_spin_lock_irqsave(&pool->lock, flags);
-		if (pool->nr_workers == pool->nr_idle)
-			goto next_pool;
-		/*
-		 * Defer printing to avoid deadlocks in console drivers that
-		 * queue work while holding locks also taken in their write
-		 * paths.
-		 */
-		printk_deferred_enter();
-		pr_info("pool %d:", pool->id);
-		pr_cont_pool_info(pool);
-		pr_cont(" hung=%us workers=%d",
-			jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000,
-			pool->nr_workers);
-		if (pool->manager)
-			pr_cont(" manager: %d",
-				task_pid_nr(pool->manager->task));
-		list_for_each_entry(worker, &pool->idle_list, entry) {
-			pr_cont(" %s%d", first ? "idle: " : "",
-				task_pid_nr(worker->task));
-			first = false;
+			printk_deferred_enter();
+			show_pwq(pwq);
+			printk_deferred_exit();
 		}
-		pr_cont("\n");
-		printk_deferred_exit();
-	next_pool:
-		raw_spin_unlock_irqrestore(&pool->lock, flags);
+		raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
 		/*
 		 * We could be printing a lot from atomic context, e.g.
-		 * sysrq-t -> show_workqueue_state(). Avoid triggering
+		 * sysrq-t -> show_all_workqueues(). Avoid triggering
 		 * hard lockup.
 		 */
 		touch_nmi_watchdog();
 	}
 
+}
+
+/**
+ * show_one_worker_pool - dump state of specified worker pool
+ * @pool: worker pool whose state will be printed
+ */
+static void show_one_worker_pool(struct worker_pool *pool)
+{
+	struct worker *worker;
+	bool first = true;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&pool->lock, flags);
+	if (pool->nr_workers == pool->nr_idle)
+		goto next_pool;
+	/*
+	 * Defer printing to avoid deadlocks in console drivers that
+	 * queue work while holding locks also taken in their write
+	 * paths.
+	 */
+	printk_deferred_enter();
+	pr_info("pool %d:", pool->id);
+	pr_cont_pool_info(pool);
+	pr_cont(" hung=%us workers=%d",
+		jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000,
+		pool->nr_workers);
+	if (pool->manager)
+		pr_cont(" manager: %d",
+			task_pid_nr(pool->manager->task));
+	list_for_each_entry(worker, &pool->idle_list, entry) {
+		pr_cont(" %s%d", first ? "idle: " : "",
+			task_pid_nr(worker->task));
+		first = false;
+	}
+	pr_cont("\n");
+	printk_deferred_exit();
+next_pool:
+	raw_spin_unlock_irqrestore(&pool->lock, flags);
+	/*
+	 * We could be printing a lot from atomic context, e.g.
+	 * sysrq-t -> show_all_workqueues(). Avoid triggering
+	 * hard lockup.
+	 */
+	touch_nmi_watchdog();
+
+}
+
+/**
+ * show_all_workqueues - dump workqueue state
+ *
+ * Called from a sysrq handler or try_to_freeze_tasks() and prints out
+ * all busy workqueues and pools.
+ */
+void show_all_workqueues(void)
+{
+	struct workqueue_struct *wq;
+	struct worker_pool *pool;
+	int pi;
+
+	rcu_read_lock();
+
+	pr_info("Showing busy workqueues and worker pools:\n");
+
+	list_for_each_entry_rcu(wq, &workqueues, list)
+		show_one_workqueue(wq);
+
+	for_each_pool(pool, pi)
+		show_one_worker_pool(pool);
+
 	rcu_read_unlock();
 }
 
@@ -5384,16 +5404,22 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
 	int ret = -EINVAL;
 	cpumask_var_t saved_cpumask;
 
-	if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL))
-		return -ENOMEM;
-
 	/*
 	 * Not excluding isolated cpus on purpose.
 	 * If the user wishes to include them, we allow that.
 	 */
 	cpumask_and(cpumask, cpumask, cpu_possible_mask);
 	if (!cpumask_empty(cpumask)) {
 		apply_wqattrs_lock();
+		if (cpumask_equal(cpumask, wq_unbound_cpumask)) {
+			ret = 0;
+			goto out_unlock;
+		}
+
+		if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL)) {
+			ret = -ENOMEM;
+			goto out_unlock;
+		}
 
 		/* save the old wq_unbound_cpumask. */
 		cpumask_copy(saved_cpumask, wq_unbound_cpumask);
@@ -5406,10 +5432,11 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
 		if (ret < 0)
 			cpumask_copy(wq_unbound_cpumask, saved_cpumask);
 
+		free_cpumask_var(saved_cpumask);
+out_unlock:
 		apply_wqattrs_unlock();
 	}
 
-	free_cpumask_var(saved_cpumask);
 	return ret;
 }
 
@@ -5869,7 +5896,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 	rcu_read_unlock();
 
 	if (lockup_detected)
-		show_workqueue_state();
+		show_all_workqueues();
 
 	wq_watchdog_reset_touched();
 	mod_timer(&wq_watchdog_timer, jiffies + thresh);