workqueue: Report work funcs that trigger automatic CPU_INTENSIVE mechanism

Workqueue now automatically marks per-cpu work items that hog CPU for too
long as CPU_INTENSIVE, which excludes them from concurrency management and
prevents stalling other concurrency-managed work items. If a work function
keeps running over the thershold, it likely needs to be switched to use an
unbound workqueue.

This patch adds a debug mechanism which tracks the work functions which
trigger the automatic CPU_INTENSIVE mechanism and report them using
pr_warn() with exponential backoff.

v3: Documentation update.

v2: Drop bouncing to kthread_worker for printing messages. It was to avoid
    introducing circular locking dependency through printk but not effective
    as it still had pool lock -> wci_lock -> printk -> pool lock loop. Let's
    just print directly using printk_deferred().

Signed-off-by: Tejun Heo <tj@kernel.org>
Suggested-by: Peter Zijlstra <peterz@infradead.org>

Documentation/admin-guide/kernel-parameters.txt

@@ -6938,6 +6938,11 @@
 			them from noticeably delaying other per-cpu work
 			items. Default is 10000 (10ms).
 
+			If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
+			will report the work functions which violate this
+			threshold repeatedly. They are likely good
+			candidates for using WQ_UNBOUND workqueues instead.
+
 	workqueue.disable_numa
 			By default, all work items queued to unbound
 			workqueues are affine to the NUMA nodes they're

kernel/workqueue.c

@@ -948,6 +948,98 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
 			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
@@ -1057,6 +1149,7 @@ void wq_worker_tick(struct task_struct *task)
 	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)) {

lib/Kconfig.debug

@@ -1134,6 +1134,19 @@ config WQ_WATCHDOG
 	  state.  This can be configured through kernel parameter
 	  "workqueue.watchdog_thresh" and its sysfs counterpart.
 
+config WQ_CPU_INTENSIVE_REPORT
+	bool "Report per-cpu work items which hog CPU for too long"
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here to enable reporting of concurrency-managed per-cpu work
+	  items that hog CPUs for longer than
+	  workqueue.cpu_intensive_threshold_us. Workqueue automatically
+	  detects and excludes them from concurrency management to prevent
+	  them from stalling other per-cpu work items. Occassional
+	  triggering may not necessarily indicate a problem. Repeated
+	  triggering likely indicates that the work item should be switched
+	  to use an unbound workqueue.
+
 config TEST_LOCKUP
 	tristate "Test module to generate lockups"
 	depends on m