Merge tag 'wq-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue updates from Tejun Heo:
 "Mostly changes from Petr to improve warning and error reporting.

  Workqueue now reports more of the relevant failures with better
  context which should help debugging"

* tag 'wq-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: Introduce show_freezable_workqueues
  workqueue: Print backtraces from CPUs with hung CPU bound workqueues
  workqueue: Warn when a rescuer could not be created
  workqueue: Interrupted create_worker() is not a repeated event
  workqueue: Warn when a new worker could not be created
  workqueue: Fix hung time report of worker pools
  workqueue: Simplify a pr_warn() call in wq_select_unbound_cpu()
  MAINTAINERS: Add workqueue_internal.h to the WORKQUEUE entry

4 files changed, 124 insertions, 14 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 4e9370793300..e2a91d048365 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22743,6 +22743,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git
 F:	Documentation/core-api/workqueue.rst
 F:	include/linux/workqueue.h
 F:	kernel/workqueue.c
+F:	kernel/workqueue_internal.h
 
 WWAN DRIVERS
 M:	Loic Poulain <loic.poulain@linaro.org>
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index ac551b8ee7d9..3992c994787f 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -472,6 +472,7 @@ 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_all_workqueues(void);
+extern void show_freezable_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);
 
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 6c1c7e566d35..cae81a87cc91 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -93,7 +93,7 @@ static int try_to_freeze_tasks(bool user_only)
 		       todo - wq_busy, wq_busy);
 
 		if (wq_busy)
-			show_all_workqueues();
+			show_freezable_workqueues();
 
 		if (!wakeup || pm_debug_messages_on) {
 			read_lock(&tasklist_lock);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 209917792fa4..4666a1a92a31 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -49,6 +49,7 @@
 #include <linux/moduleparam.h>
 #include <linux/uaccess.h>
 #include <linux/sched/isolation.h>
+#include <linux/sched/debug.h>
 #include <linux/nmi.h>
 #include <linux/kvm_para.h>
 
@@ -141,6 +142,8 @@ enum {
  * WR: wq->mutex protected for writes.  RCU protected for reads.
  *
  * MD: wq_mayday_lock protected.
+ *
+ * WD: Used internally by the watchdog.
  */
 
 /* struct worker is defined in workqueue_internal.h */
@@ -153,6 +156,7 @@ struct worker_pool {
 	unsigned int		flags;		/* X: flags */
 
 	unsigned long		watchdog_ts;	/* L: watchdog timestamp */
+	bool			cpu_stall;	/* WD: stalled cpu bound pool */
 
 	/*
 	 * The counter is incremented in a process context on the associated CPU
@@ -1392,15 +1396,13 @@ static bool is_chained_work(struct workqueue_struct *wq)
  */
 static int wq_select_unbound_cpu(int cpu)
 {
-	static bool printed_dbg_warning;
 	int new_cpu;
 
 	if (likely(!wq_debug_force_rr_cpu)) {
 		if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
 			return cpu;
-	} else if (!printed_dbg_warning) {
-		pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n");
-		printed_dbg_warning = true;
+	} else {
+		pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n");
 	}
 
 	if (cpumask_empty(wq_unbound_cpumask))
@@ -1938,12 +1940,17 @@ static struct worker *create_worker(struct worker_pool *pool)
 
 	/* ID is needed to determine kthread name */
 	id = ida_alloc(&pool->worker_ida, GFP_KERNEL);
-	if (id < 0)
+	if (id < 0) {
+		pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n",
+			    ERR_PTR(id));
 		return NULL;
+	}
 
 	worker = alloc_worker(pool->node);
-	if (!worker)
+	if (!worker) {
+		pr_err_once("workqueue: Failed to allocate a worker\n");
 		goto fail;
+	}
 
 	worker->id = id;
 
@@ -1955,8 +1962,16 @@ static struct worker *create_worker(struct worker_pool *pool)
 
 	worker->task = kthread_create_on_node(worker_thread, worker, pool->node,
 					      "kworker/%s", id_buf);
-	if (IS_ERR(worker->task))
+	if (IS_ERR(worker->task)) {
+		if (PTR_ERR(worker->task) == -EINTR) {
+			pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n",
+			       id_buf);
+		} else {
+			pr_err_once("workqueue: Failed to create a worker thread: %pe",
+				    worker->task);
+		}
 		goto fail;
+	}
 
 	set_user_nice(worker->task, pool->attrs->nice);
 	kthread_bind_mask(worker->task, pool->attrs->cpumask);
@@ -4380,13 +4395,18 @@ static int init_rescuer(struct workqueue_struct *wq)
 		return 0;
 
 	rescuer = alloc_worker(NUMA_NO_NODE);
-	if (!rescuer)
+	if (!rescuer) {
+		pr_err("workqueue: Failed to allocate a rescuer for wq \"%s\"\n",
+		       wq->name);
 		return -ENOMEM;
+	}
 
 	rescuer->rescue_wq = wq;
 	rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name);
 	if (IS_ERR(rescuer->task)) {
 		ret = PTR_ERR(rescuer->task);
+		pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe",
+		       wq->name, ERR_PTR(ret));
 		kfree(rescuer);
 		return ret;
 	}
@@ -5002,10 +5022,16 @@ 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
@@ -5014,9 +5040,7 @@ 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));
@@ -5041,8 +5065,7 @@ next_pool:
 /**
  * show_all_workqueues - dump workqueue state
  *
- * Called from a sysrq handler or try_to_freeze_tasks() and prints out
- * all busy workqueues and pools.
+ * Called from a sysrq handler and prints out all busy workqueues and pools.
  */
 void show_all_workqueues(void)
 {
@@ -5063,6 +5086,29 @@ void show_all_workqueues(void)
 	rcu_read_unlock();
 }
 
+/**
+ * show_freezable_workqueues - dump freezable workqueue state
+ *
+ * Called from try_to_freeze_tasks() and prints out all freezable workqueues
+ * still busy.
+ */
+void show_freezable_workqueues(void)
+{
+	struct workqueue_struct *wq;
+
+	rcu_read_lock();
+
+	pr_info("Showing freezable workqueues that are still busy:\n");
+
+	list_for_each_entry_rcu(wq, &workqueues, list) {
+		if (!(wq->flags & WQ_FREEZABLE))
+			continue;
+		show_one_workqueue(wq);
+	}
+
+	rcu_read_unlock();
+}
+
 /* used to show worker information through /proc/PID/{comm,stat,status} */
 void wq_worker_comm(char *buf, size_t size, struct task_struct *task)
 {
@@ -5962,6 +6008,57 @@ static struct timer_list wq_watchdog_timer;
 static unsigned long wq_watchdog_touched = INITIAL_JIFFIES;
 static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES;
 
+/*
+ * Show workers that might prevent the processing of pending work items.
+ * The only candidates are CPU-bound workers in the running state.
+ * Pending work items should be handled by another idle worker
+ * in all other situations.
+ */
+static void show_cpu_pool_hog(struct worker_pool *pool)
+{
+	struct worker *worker;
+	unsigned long flags;
+	int bkt;
+
+	raw_spin_lock_irqsave(&pool->lock, flags);
+
+	hash_for_each(pool->busy_hash, bkt, worker, hentry) {
+		if (task_is_running(worker->task)) {
+			/*
+			 * 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:\n", pool->id);
+			sched_show_task(worker->task);
+
+			printk_deferred_exit();
+		}
+	}
+
+	raw_spin_unlock_irqrestore(&pool->lock, flags);
+}
+
+static void show_cpu_pools_hogs(void)
+{
+	struct worker_pool *pool;
+	int pi;
+
+	pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n");
+
+	rcu_read_lock();
+
+	for_each_pool(pool, pi) {
+		if (pool->cpu_stall)
+			show_cpu_pool_hog(pool);
+
+	}
+
+	rcu_read_unlock();
+}
+
 static void wq_watchdog_reset_touched(void)
 {
 	int cpu;
@@ -5975,6 +6072,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 {
 	unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ;
 	bool lockup_detected = false;
+	bool cpu_pool_stall = false;
 	unsigned long now = jiffies;
 	struct worker_pool *pool;
 	int pi;
@@ -5987,6 +6085,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 	for_each_pool(pool, pi) {
 		unsigned long pool_ts, touched, ts;
 
+		pool->cpu_stall = false;
 		if (list_empty(&pool->worklist))
 			continue;
 
@@ -6011,11 +6110,17 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		/* did we stall? */
 		if (time_after(now, ts + thresh)) {
 			lockup_detected = true;
+			if (pool->cpu >= 0) {
+				pool->cpu_stall = true;
+				cpu_pool_stall = true;
+			}
 			pr_emerg("BUG: workqueue lockup - pool");
 			pr_cont_pool_info(pool);
 			pr_cont(" stuck for %us!\n",
 				jiffies_to_msecs(now - pool_ts) / 1000);
 		}
+
+
 	}
 
 	rcu_read_unlock();
@@ -6023,6 +6128,9 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 	if (lockup_detected)
 		show_all_workqueues();
 
+	if (cpu_pool_stall)
+		show_cpu_pools_hogs();
+
 	wq_watchdog_reset_touched();
 	mod_timer(&wq_watchdog_timer, jiffies + thresh);
 }