workqueue: Process rescuer work items one-by-one using a cursor

Previously, the rescuer scanned for all matching work items at once and
processed them within a single rescuer thread, which could cause one
blocking work item to stall all others.

Make the rescuer process work items one-by-one instead of slurping all
matches in a single pass.

Break the rescuer loop after finding and processing the first matching
work item, then restart the search to pick up the next. This gives
normal worker threads a chance to process other items which gives them
the opportunity to be processed instead of waiting on the rescuer's
queue and prevents a blocking work item from stalling the rest once
memory pressure is relieved.

Introduce a dummy cursor work item to avoid potentially O(N^2)
rescans of the work list.  The marker records the resume position for
the next scan, eliminating redundant traversals.

Also introduce RESCUER_BATCH to control the maximum number of work items
the rescuer processes in each turn, and move on to other PWQs when the
limit is reached.

Cc: ying chen <[email protected]>
Reported-by: ying chen <[email protected]>
Fixes: e22bee7 ("workqueue: implement concurrency managed dynamic worker pool")
Signed-off-by: Lai Jiangshan <[email protected]>
Signed-off-by: Tejun Heo <[email protected]>

Author: Lai Jiangshan

kernel/workqueue.c

@@ -117,6 +117,8 @@ enum wq_internal_consts {
 	MAYDAY_INTERVAL		= HZ / 10,	/* and then every 100ms */
 	CREATE_COOLDOWN		= HZ,		/* time to breath after fail */
 
+	RESCUER_BATCH		= 16,		/* process items per turn */
+
 	/*
 	 * Rescue workers are used only on emergencies and shared by
 	 * all cpus.  Give MIN_NICE.
@@ -286,6 +288,7 @@ struct pool_workqueue {
 	struct list_head	pending_node;	/* LN: node on wq_node_nr_active->pending_pwqs */
 	struct list_head	pwqs_node;	/* WR: node on wq->pwqs */
 	struct list_head	mayday_node;	/* MD: node on wq->maydays */
+	struct work_struct	mayday_cursor;	/* L: cursor on pool->worklist */
 
 	u64			stats[PWQ_NR_STATS];
 
@@ -1120,6 +1123,12 @@ static struct worker *find_worker_executing_work(struct worker_pool *pool,
 	return NULL;
 }
 
+static void mayday_cursor_func(struct work_struct *work)
+{
+	/* should not be processed, only for marking position */
+	BUG();
+}
+
 /**
  * move_linked_works - move linked works to a list
  * @work: start of series of works to be scheduled
@@ -1182,6 +1191,16 @@ static bool assign_work(struct work_struct *work, struct worker *worker,
 
 	lockdep_assert_held(&pool->lock);
 
+	/* The cursor work should not be processed */
+	if (unlikely(work->func == mayday_cursor_func)) {
+		/* only worker_thread() can possibly take this branch */
+		WARN_ON_ONCE(worker->rescue_wq);
+		if (nextp)
+			*nextp = list_next_entry(work, entry);
+		list_del_init(&work->entry);
+		return false;
+	}
+
 	/*
 	 * A single work shouldn't be executed concurrently by multiple workers.
 	 * __queue_work() ensures that @work doesn't jump to a different pool
@@ -3439,22 +3458,30 @@ static int worker_thread(void *__worker)
 static bool assign_rescuer_work(struct pool_workqueue *pwq, struct worker *rescuer)
 {
 	struct worker_pool *pool = pwq->pool;
+	struct work_struct *cursor = &pwq->mayday_cursor;
 	struct work_struct *work, *n;
 
 	/* need rescue? */
 	if (!pwq->nr_active || !need_to_create_worker(pool))
 		return false;
 
-	/*
-	 * Slurp in all works issued via this workqueue and
-	 * process'em.
-	 */
-	list_for_each_entry_safe(work, n, &pool->worklist, entry) {
-		if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n))
+	/* search from the start or cursor if available */
+	if (list_empty(&cursor->entry))
+		work = list_first_entry(&pool->worklist, struct work_struct, entry);
+	else
+		work = list_next_entry(cursor, entry);
+
+	/* find the next work item to rescue */
+	list_for_each_entry_safe_from(work, n, &pool->worklist, entry) {
+		if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n)) {
 			pwq->stats[PWQ_STAT_RESCUED]++;
+			/* put the cursor for next search */
+			list_move_tail(&cursor->entry, &n->entry);
+			return true;
+		}
 	}
 
-	return !list_empty(&rescuer->scheduled);
+	return false;
 }
 
 /**
@@ -3511,6 +3538,7 @@ static int rescuer_thread(void *__rescuer)
 		struct pool_workqueue *pwq = list_first_entry(&wq->maydays,
 					struct pool_workqueue, mayday_node);
 		struct worker_pool *pool = pwq->pool;
+		unsigned int count = 0;
 
 		__set_current_state(TASK_RUNNING);
 		list_del_init(&pwq->mayday_node);
@@ -3523,25 +3551,27 @@ static int rescuer_thread(void *__rescuer)
 
 		WARN_ON_ONCE(!list_empty(&rescuer->scheduled));
 
-		if (assign_rescuer_work(pwq, rescuer)) {
+		while (assign_rescuer_work(pwq, rescuer)) {
 			process_scheduled_works(rescuer);
 
 			/*
-			 * The above execution of rescued work items could
-			 * have created more to rescue through
-			 * pwq_activate_first_inactive() or chained
-			 * queueing.  Let's put @pwq back on mayday list so
-			 * that such back-to-back work items, which may be
-			 * being used to relieve memory pressure, don't
-			 * incur MAYDAY_INTERVAL delay inbetween.
+			 * If the per-turn work item limit is reached and other
+			 * PWQs are in mayday, requeue mayday for this PWQ and
+			 * let the rescuer handle the other PWQs first.
 			 */
-			if (pwq->nr_active && need_to_create_worker(pool)) {
+			if (++count > RESCUER_BATCH && !list_empty(&pwq->wq->maydays) &&
+			    pwq->nr_active && need_to_create_worker(pool)) {
 				raw_spin_lock(&wq_mayday_lock);
 				send_mayday(pwq);
 				raw_spin_unlock(&wq_mayday_lock);
+				break;
 			}
 		}
 
+		/* The cursor can not be left behind without the rescuer watching it. */
+		if (!list_empty(&pwq->mayday_cursor.entry) && list_empty(&pwq->mayday_node))
+			list_del_init(&pwq->mayday_cursor.entry);
+
 		/*
 		 * Leave this pool. Notify regular workers; otherwise, we end up
 		 * with 0 concurrency and stalling the execution.
@@ -5160,6 +5190,19 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
 	INIT_LIST_HEAD(&pwq->pwqs_node);
 	INIT_LIST_HEAD(&pwq->mayday_node);
 	kthread_init_work(&pwq->release_work, pwq_release_workfn);
+
+	/*
+	 * Set the dummy cursor work with valid function and get_work_pwq().
+	 *
+	 * The cursor work should only be in the pwq->pool->worklist, and
+	 * should not be treated as a processable work item.
+	 *
+	 * WORK_STRUCT_PENDING and WORK_STRUCT_INACTIVE just make it less
+	 * surprise for kernel debugging tools and reviewers.
+	 */
+	INIT_WORK(&pwq->mayday_cursor, mayday_cursor_func);
+	atomic_long_set(&pwq->mayday_cursor.data, (unsigned long)pwq |
+			WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | WORK_STRUCT_INACTIVE);
 }
 
 /* sync @pwq with the current state of its associated wq and link it */