1 files changed, 47 insertions, 18 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 5bf8aa81715e..38b33ad9e8cf 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -140,6 +140,7 @@ static void io_wqe_dec_running(struct io_worker *worker);
 static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
 					struct io_wqe_acct *acct,
 					struct io_cb_cancel_data *match);
+static void create_worker_cb(struct callback_head *cb);
 
 static bool io_worker_get(struct io_worker *worker)
 {
@@ -174,12 +175,46 @@ static void io_worker_ref_put(struct io_wq *wq)
 		complete(&wq->worker_done);
 }
 
+static void io_worker_cancel_cb(struct io_worker *worker)
+{
+	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
+	struct io_wqe *wqe = worker->wqe;
+	struct io_wq *wq = wqe->wq;
+
+	atomic_dec(&acct->nr_running);
+	raw_spin_lock(&worker->wqe->lock);
+	acct->nr_workers--;
+	raw_spin_unlock(&worker->wqe->lock);
+	io_worker_ref_put(wq);
+	clear_bit_unlock(0, &worker->create_state);
+	io_worker_release(worker);
+}
+
+static bool io_task_worker_match(struct callback_head *cb, void *data)
+{
+	struct io_worker *worker;
+
+	if (cb->func != create_worker_cb)
+		return false;
+	worker = container_of(cb, struct io_worker, create_work);
+	return worker == data;
+}
+
 static void io_worker_exit(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
+	struct io_wq *wq = wqe->wq;
 
-	if (refcount_dec_and_test(&worker->ref))
-		complete(&worker->ref_done);
+	while (1) {
+		struct callback_head *cb = task_work_cancel_match(wq->task,
+						io_task_worker_match, worker);
+
+		if (!cb)
+			break;
+		io_worker_cancel_cb(worker);
+	}
+
+	io_worker_release(worker);
 	wait_for_completion(&worker->ref_done);
 
 	raw_spin_lock(&wqe->lock);
@@ -253,7 +288,7 @@ static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
 		pr_warn_once("io-wq is not configured for unbound workers");
 
 	raw_spin_lock(&wqe->lock);
-	if (acct->nr_workers == acct->max_workers) {
+	if (acct->nr_workers >= acct->max_workers) {
 		raw_spin_unlock(&wqe->lock);
 		return true;
 	}
@@ -323,8 +358,10 @@ static bool io_queue_worker_create(struct io_worker *worker,
 
 	init_task_work(&worker->create_work, func);
 	worker->create_index = acct->index;
-	if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL))
+	if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
+		clear_bit_unlock(0, &worker->create_state);
 		return true;
+	}
 	clear_bit_unlock(0, &worker->create_state);
 fail_release:
 	io_worker_release(worker);
@@ -716,11 +753,8 @@ static void io_workqueue_create(struct work_struct *work)
 	struct io_worker *worker = container_of(work, struct io_worker, work);
 	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
 
-	if (!io_queue_worker_create(worker, acct, create_worker_cont)) {
-		clear_bit_unlock(0, &worker->create_state);
-		io_worker_release(worker);
+	if (!io_queue_worker_create(worker, acct, create_worker_cont))
 		kfree(worker);
-	}
 }
 
 static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
@@ -1150,17 +1184,9 @@ static void io_wq_exit_workers(struct io_wq *wq)
 
 	while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
 		struct io_worker *worker;
-		struct io_wqe_acct *acct;
 
 		worker = container_of(cb, struct io_worker, create_work);
-		acct = io_wqe_get_acct(worker);
-		atomic_dec(&acct->nr_running);
-		raw_spin_lock(&worker->wqe->lock);
-		acct->nr_workers--;
-		raw_spin_unlock(&worker->wqe->lock);
-		io_worker_ref_put(wq);
-		clear_bit_unlock(0, &worker->create_state);
-		io_worker_release(worker);
+		io_worker_cancel_cb(worker);
 	}
 
 	rcu_read_lock();
@@ -1291,15 +1317,18 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count)
 
 	rcu_read_lock();
 	for_each_node(node) {
+		struct io_wqe *wqe = wq->wqes[node];
 		struct io_wqe_acct *acct;
 
+		raw_spin_lock(&wqe->lock);
 		for (i = 0; i < IO_WQ_ACCT_NR; i++) {
-			acct = &wq->wqes[node]->acct[i];
+			acct = &wqe->acct[i];
 			prev = max_t(int, acct->max_workers, prev);
 			if (new_count[i])
 				acct->max_workers = new_count[i];
 			new_count[i] = prev;
 		}
+		raw_spin_unlock(&wqe->lock);
 	}
 	rcu_read_unlock();
 	return 0;