Merge tag 'wq-for-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue updates from Tejun Heo:

 - Concurrency-managed per-cpu work items that hog CPUs and delay the
   execution of other work items are now automatically detected and
   excluded from concurrency management. Reporting on such work items
   can also be enabled through a config option.

 - Added tools/workqueue/wq_monitor.py which improves visibility into
   workqueue usages and behaviors.

 - Arnd's minimal fix for gcc-13 enum warning on 32bit compiles,
   superseded by commit afa4bb778e48 in mainline.

* tag 'wq-for-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: Disable per-cpu CPU hog detection when wq_cpu_intensive_thresh_us is 0
  workqueue: Fix WARN_ON_ONCE() triggers in worker_enter_idle()
  workqueue: fix enum type for gcc-13
  workqueue: Track and monitor per-workqueue CPU time usage
  workqueue: Report work funcs that trigger automatic CPU_INTENSIVE mechanism
  workqueue: Automatically mark CPU-hogging work items CPU_INTENSIVE
  workqueue: Improve locking rule description for worker fields
  workqueue: Move worker_set/clr_flags() upwards
  workqueue: Re-order struct worker fields
  workqueue: Add pwq->stats[] and a monitoring script
  Further upgrade queue_work_on() comment

1 files changed, 258 insertions, 64 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c913e333cce8ea..02a8f402eeb543 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -126,6 +126,12 @@ enum {
  *    cpu or grabbing pool->lock is enough for read access.  If
  *    POOL_DISASSOCIATED is set, it's identical to L.
  *
+ * K: Only modified by worker while holding pool->lock. Can be safely read by
+ *    self, while holding pool->lock or from IRQ context if %current is the
+ *    kworker.
+ *
+ * S: Only modified by worker self.
+ *
  * A: wq_pool_attach_mutex protected.
  *
  * PL: wq_pool_mutex protected.
@@ -200,6 +206,22 @@ struct worker_pool {
 };
 
 /*
+ * Per-pool_workqueue statistics. These can be monitored using
+ * tools/workqueue/wq_monitor.py.
+ */
+enum pool_workqueue_stats {
+	PWQ_STAT_STARTED,	/* work items started execution */
+	PWQ_STAT_COMPLETED,	/* work items completed execution */
+	PWQ_STAT_CPU_TIME,	/* total CPU time consumed */
+	PWQ_STAT_CPU_INTENSIVE,	/* wq_cpu_intensive_thresh_us violations */
+	PWQ_STAT_CM_WAKEUP,	/* concurrency-management worker wakeups */
+	PWQ_STAT_MAYDAY,	/* maydays to rescuer */
+	PWQ_STAT_RESCUED,	/* linked work items executed by rescuer */
+
+	PWQ_NR_STATS,
+};
+
+/*
  * The per-pool workqueue.  While queued, the lower WORK_STRUCT_FLAG_BITS
  * of work_struct->data are used for flags and the remaining high bits
  * point to the pwq; thus, pwqs need to be aligned at two's power of the
@@ -236,6 +258,8 @@ struct pool_workqueue {
 	struct list_head	pwqs_node;	/* WR: node on wq->pwqs */
 	struct list_head	mayday_node;	/* MD: node on wq->maydays */
 
+	u64			stats[PWQ_NR_STATS];
+
 	/*
 	 * Release of unbound pwq is punted to system_wq.  See put_pwq()
 	 * and pwq_unbound_release_workfn() for details.  pool_workqueue
@@ -310,6 +334,14 @@ static struct kmem_cache *pwq_cache;
 static cpumask_var_t *wq_numa_possible_cpumask;
 					/* possible CPUs of each node */
 
+/*
+ * Per-cpu work items which run for longer than the following threshold are
+ * automatically considered CPU intensive and excluded from concurrency
+ * management to prevent them from noticeably delaying other per-cpu work items.
+ */
+static unsigned long wq_cpu_intensive_thresh_us = 10000;
+module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644);
+
 static bool wq_disable_numa;
 module_param_named(disable_numa, wq_disable_numa, bool, 0444);
 
@@ -867,6 +899,152 @@ static void wake_up_worker(struct worker_pool *pool)
 }
 
 /**
+ * worker_set_flags - set worker flags and adjust nr_running accordingly
+ * @worker: self
+ * @flags: flags to set
+ *
+ * Set @flags in @worker->flags and adjust nr_running accordingly.
+ *
+ * CONTEXT:
+ * raw_spin_lock_irq(pool->lock)
+ */
+static inline void worker_set_flags(struct worker *worker, unsigned int flags)
+{
+	struct worker_pool *pool = worker->pool;
+
+	WARN_ON_ONCE(worker->task != current);
+
+	/* If transitioning into NOT_RUNNING, adjust nr_running. */
+	if ((flags & WORKER_NOT_RUNNING) &&
+	    !(worker->flags & WORKER_NOT_RUNNING)) {
+		pool->nr_running--;
+	}
+
+	worker->flags |= flags;
+}
+
+/**
+ * worker_clr_flags - clear worker flags and adjust nr_running accordingly
+ * @worker: self
+ * @flags: flags to clear
+ *
+ * Clear @flags in @worker->flags and adjust nr_running accordingly.
+ *
+ * CONTEXT:
+ * raw_spin_lock_irq(pool->lock)
+ */
+static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
+{
+	struct worker_pool *pool = worker->pool;
+	unsigned int oflags = worker->flags;
+
+	WARN_ON_ONCE(worker->task != current);
+
+	worker->flags &= ~flags;
+
+	/*
+	 * If transitioning out of NOT_RUNNING, increment nr_running.  Note
+	 * that the nested NOT_RUNNING is not a noop.  NOT_RUNNING is mask
+	 * of multiple flags, not a single flag.
+	 */
+	if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING))
+		if (!(worker->flags & WORKER_NOT_RUNNING))
+			pool->nr_running++;
+}
+
+#ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT
+
+/*
+ * Concurrency-managed per-cpu work items that hog CPU for longer than
+ * wq_cpu_intensive_thresh_us trigger the automatic CPU_INTENSIVE mechanism,
+ * which prevents them from stalling other concurrency-managed work items. If a
+ * work function keeps triggering this mechanism, it's likely that the work item
+ * should be using an unbound workqueue instead.
+ *
+ * wq_cpu_intensive_report() tracks work functions which trigger such conditions
+ * and report them so that they can be examined and converted to use unbound
+ * workqueues as appropriate. To avoid flooding the console, each violating work
+ * function is tracked and reported with exponential backoff.
+ */
+#define WCI_MAX_ENTS 128
+
+struct wci_ent {
+	work_func_t		func;
+	atomic64_t		cnt;
+	struct hlist_node	hash_node;
+};
+
+static struct wci_ent wci_ents[WCI_MAX_ENTS];
+static int wci_nr_ents;
+static DEFINE_RAW_SPINLOCK(wci_lock);
+static DEFINE_HASHTABLE(wci_hash, ilog2(WCI_MAX_ENTS));
+
+static struct wci_ent *wci_find_ent(work_func_t func)
+{
+	struct wci_ent *ent;
+
+	hash_for_each_possible_rcu(wci_hash, ent, hash_node,
+				   (unsigned long)func) {
+		if (ent->func == func)
+			return ent;
+	}
+	return NULL;
+}
+
+static void wq_cpu_intensive_report(work_func_t func)
+{
+	struct wci_ent *ent;
+
+restart:
+	ent = wci_find_ent(func);
+	if (ent) {
+		u64 cnt;
+
+		/*
+		 * Start reporting from the fourth time and back off
+		 * exponentially.
+		 */
+		cnt = atomic64_inc_return_relaxed(&ent->cnt);
+		if (cnt >= 4 && is_power_of_2(cnt))
+			printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n",
+					ent->func, wq_cpu_intensive_thresh_us,
+					atomic64_read(&ent->cnt));
+		return;
+	}
+
+	/*
+	 * @func is a new violation. Allocate a new entry for it. If wcn_ents[]
+	 * is exhausted, something went really wrong and we probably made enough
+	 * noise already.
+	 */
+	if (wci_nr_ents >= WCI_MAX_ENTS)
+		return;
+
+	raw_spin_lock(&wci_lock);
+
+	if (wci_nr_ents >= WCI_MAX_ENTS) {
+		raw_spin_unlock(&wci_lock);
+		return;
+	}
+
+	if (wci_find_ent(func)) {
+		raw_spin_unlock(&wci_lock);
+		goto restart;
+	}
+
+	ent = &wci_ents[wci_nr_ents++];
+	ent->func = func;
+	atomic64_set(&ent->cnt, 1);
+	hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func);
+
+	raw_spin_unlock(&wci_lock);
+}
+
+#else	/* CONFIG_WQ_CPU_INTENSIVE_REPORT */
+static void wq_cpu_intensive_report(work_func_t func) {}
+#endif	/* CONFIG_WQ_CPU_INTENSIVE_REPORT */
+
+/**
  * wq_worker_running - a worker is running again
  * @task: task waking up
  *
@@ -876,7 +1054,7 @@ void wq_worker_running(struct task_struct *task)
 {
 	struct worker *worker = kthread_data(task);
 
-	if (!worker->sleeping)
+	if (!READ_ONCE(worker->sleeping))
 		return;
 
 	/*
@@ -889,7 +1067,14 @@ void wq_worker_running(struct task_struct *task)
 	if (!(worker->flags & WORKER_NOT_RUNNING))
 		worker->pool->nr_running++;
 	preempt_enable();
-	worker->sleeping = 0;
+
+	/*
+	 * CPU intensive auto-detection cares about how long a work item hogged
+	 * CPU without sleeping. Reset the starting timestamp on wakeup.
+	 */
+	worker->current_at = worker->task->se.sum_exec_runtime;
+
+	WRITE_ONCE(worker->sleeping, 0);
 }
 
 /**
@@ -915,10 +1100,10 @@ void wq_worker_sleeping(struct task_struct *task)
 	pool = worker->pool;
 
 	/* Return if preempted before wq_worker_running() was reached */
-	if (worker->sleeping)
+	if (READ_ONCE(worker->sleeping))
 		return;
 
-	worker->sleeping = 1;
+	WRITE_ONCE(worker->sleeping, 1);
 	raw_spin_lock_irq(&pool->lock);
 
 	/*
@@ -932,12 +1117,66 @@ void wq_worker_sleeping(struct task_struct *task)
 	}
 
 	pool->nr_running--;
-	if (need_more_worker(pool))
+	if (need_more_worker(pool)) {
+		worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++;
 		wake_up_worker(pool);
+	}
 	raw_spin_unlock_irq(&pool->lock);
 }
 
 /**
+ * wq_worker_tick - a scheduler tick occurred while a kworker is running
+ * @task: task currently running
+ *
+ * Called from scheduler_tick(). We're in the IRQ context and the current
+ * worker's fields which follow the 'K' locking rule can be accessed safely.
+ */
+void wq_worker_tick(struct task_struct *task)
+{
+	struct worker *worker = kthread_data(task);
+	struct pool_workqueue *pwq = worker->current_pwq;
+	struct worker_pool *pool = worker->pool;
+
+	if (!pwq)
+		return;
+
+	pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC;
+
+	if (!wq_cpu_intensive_thresh_us)
+		return;
+
+	/*
+	 * If the current worker is concurrency managed and hogged the CPU for
+	 * longer than wq_cpu_intensive_thresh_us, it's automatically marked
+	 * CPU_INTENSIVE to avoid stalling other concurrency-managed work items.
+	 *
+	 * Set @worker->sleeping means that @worker is in the process of
+	 * switching out voluntarily and won't be contributing to
+	 * @pool->nr_running until it wakes up. As wq_worker_sleeping() also
+	 * decrements ->nr_running, setting CPU_INTENSIVE here can lead to
+	 * double decrements. The task is releasing the CPU anyway. Let's skip.
+	 * We probably want to make this prettier in the future.
+	 */
+	if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) ||
+	    worker->task->se.sum_exec_runtime - worker->current_at <
+	    wq_cpu_intensive_thresh_us * NSEC_PER_USEC)
+		return;
+
+	raw_spin_lock(&pool->lock);
+
+	worker_set_flags(worker, WORKER_CPU_INTENSIVE);
+	wq_cpu_intensive_report(worker->current_func);
+	pwq->stats[PWQ_STAT_CPU_INTENSIVE]++;
+
+	if (need_more_worker(pool)) {
+		pwq->stats[PWQ_STAT_CM_WAKEUP]++;
+		wake_up_worker(pool);
+	}
+
+	raw_spin_unlock(&pool->lock);
+}
+
+/**
  * wq_worker_last_func - retrieve worker's last work function
  * @task: Task to retrieve last work function of.
  *
@@ -969,60 +1208,6 @@ work_func_t wq_worker_last_func(struct task_struct *task)
 }
 
 /**
- * worker_set_flags - set worker flags and adjust nr_running accordingly
- * @worker: self
- * @flags: flags to set
- *
- * Set @flags in @worker->flags and adjust nr_running accordingly.
- *
- * CONTEXT:
- * raw_spin_lock_irq(pool->lock)
- */
-static inline void worker_set_flags(struct worker *worker, unsigned int flags)
-{
-	struct worker_pool *pool = worker->pool;
-
-	WARN_ON_ONCE(worker->task != current);
-
-	/* If transitioning into NOT_RUNNING, adjust nr_running. */
-	if ((flags & WORKER_NOT_RUNNING) &&
-	    !(worker->flags & WORKER_NOT_RUNNING)) {
-		pool->nr_running--;
-	}
-
-	worker->flags |= flags;
-}
-
-/**
- * worker_clr_flags - clear worker flags and adjust nr_running accordingly
- * @worker: self
- * @flags: flags to clear
- *
- * Clear @flags in @worker->flags and adjust nr_running accordingly.
- *
- * CONTEXT:
- * raw_spin_lock_irq(pool->lock)
- */
-static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
-{
-	struct worker_pool *pool = worker->pool;
-	unsigned int oflags = worker->flags;
-
-	WARN_ON_ONCE(worker->task != current);
-
-	worker->flags &= ~flags;
-
-	/*
-	 * If transitioning out of NOT_RUNNING, increment nr_running.  Note
-	 * that the nested NOT_RUNNING is not a noop.  NOT_RUNNING is mask
-	 * of multiple flags, not a single flag.
-	 */
-	if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING))
-		if (!(worker->flags & WORKER_NOT_RUNNING))
-			pool->nr_running++;
-}
-
-/**
  * find_worker_executing_work - find worker which is executing a work
  * @pool: pool of interest
  * @work: work to find worker for
@@ -1542,6 +1727,8 @@ out:
  * We queue the work to a specific CPU, the caller must ensure it
  * can't go away.  Callers that fail to ensure that the specified
  * CPU cannot go away will execute on a randomly chosen CPU.
+ * But note well that callers specifying a CPU that never has been
+ * online will get a splat.
  *
  * Return: %false if @work was already on a queue, %true otherwise.
  */
@@ -2166,6 +2353,7 @@ static void send_mayday(struct work_struct *work)
 		get_pwq(pwq);
 		list_add_tail(&pwq->mayday_node, &wq->maydays);
 		wake_up_process(wq->rescuer->task);
+		pwq->stats[PWQ_STAT_MAYDAY]++;
 	}
 }
 
@@ -2303,7 +2491,6 @@ __acquires(&pool->lock)
 {
 	struct pool_workqueue *pwq = get_work_pwq(work);
 	struct worker_pool *pool = worker->pool;
-	bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE;
 	unsigned long work_data;
 	struct worker *collision;
 #ifdef CONFIG_LOCKDEP
@@ -2340,6 +2527,7 @@ __acquires(&pool->lock)
 	worker->current_work = work;
 	worker->current_func = work->func;
 	worker->current_pwq = pwq;
+	worker->current_at = worker->task->se.sum_exec_runtime;
 	work_data = *work_data_bits(work);
 	worker->current_color = get_work_color(work_data);
 
@@ -2357,7 +2545,7 @@ __acquires(&pool->lock)
 	 * of concurrency management and the next code block will chain
 	 * execution of the pending work items.
 	 */
-	if (unlikely(cpu_intensive))
+	if (unlikely(pwq->wq->flags & WQ_CPU_INTENSIVE))
 		worker_set_flags(worker, WORKER_CPU_INTENSIVE);
 
 	/*
@@ -2404,6 +2592,7 @@ __acquires(&pool->lock)
 	 * workqueues), so hiding them isn't a problem.
 	 */
 	lockdep_invariant_state(true);
+	pwq->stats[PWQ_STAT_STARTED]++;
 	trace_workqueue_execute_start(work);
 	worker->current_func(work);
 	/*
@@ -2411,6 +2600,7 @@ __acquires(&pool->lock)
 	 * point will only record its address.
 	 */
 	trace_workqueue_execute_end(work, worker->current_func);
+	pwq->stats[PWQ_STAT_COMPLETED]++;
 	lock_map_release(&lockdep_map);
 	lock_map_release(&pwq->wq->lockdep_map);
 
@@ -2435,9 +2625,12 @@ __acquires(&pool->lock)
 
 	raw_spin_lock_irq(&pool->lock);
 
-	/* clear cpu intensive status */
-	if (unlikely(cpu_intensive))
-		worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
+	/*
+	 * In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked
+	 * CPU intensive by wq_worker_tick() if @work hogged CPU longer than
+	 * wq_cpu_intensive_thresh_us. Clear it.
+	 */
+	worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
 
 	/* tag the worker for identification in schedule() */
 	worker->last_func = worker->current_func;
@@ -2654,6 +2847,7 @@ repeat:
 				if (first)
 					pool->watchdog_ts = jiffies;
 				move_linked_works(work, scheduled, &n);
+				pwq->stats[PWQ_STAT_RESCUED]++;
 			}
 			first = false;
 		}