From 335a42ebb0ca8ee9997a1731aaaae6dcd704c113 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Tue, 7 Mar 2023 13:53:31 +0100 Subject: [PATCH] workqueue: Fix hung time report of worker pools The workqueue watchdog prints a warning when there is no progress in a worker pool. Where the progress means that the pool started processing a pending work item. Note that it is perfectly fine to process work items much longer. The progress should be guaranteed by waking up or creating idle workers. show_one_worker_pool() prints state of non-idle worker pool. It shows a delay since the last pool->watchdog_ts. The timestamp is updated when a first pending work is queued in __queue_work(). Also it is updated when a work is dequeued for processing in worker_thread() and rescuer_thread(). The delay is misleading when there is no pending work item. In this case it shows how long the last work item is being proceed. Show zero instead. There is no stall if there is no pending work. Fixes: 82607adcf9cdf40fb7b ("workqueue: implement lockup detector") Signed-off-by: Petr Mladek Signed-off-by: Tejun Heo --- kernel/workqueue.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3f1fabea000f..8c0ec21a86a2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5000,10 +5000,16 @@ static void show_one_worker_pool(struct worker_pool *pool) struct worker *worker; bool first = true; unsigned long flags; + unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; + + /* How long the first pending work is waiting for a worker. */ + if (!list_empty(&pool->worklist)) + hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; + /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write @@ -5012,9 +5018,7 @@ static void show_one_worker_pool(struct worker_pool *pool) 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); + pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task));