diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c
index 513c11c..fffcd61 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.c
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.c
@@ -2849,7 +2849,8 @@ static int anx7625_i2c_probe(struct i2c_client *client)
 	if (platform->pdata.intp_irq) {
 		INIT_WORK(&platform->work, anx7625_work_func);
 		platform->workqueue = alloc_workqueue("anx7625_work",
-						      WQ_FREEZABLE | WQ_MEM_RECLAIM, 1);
+						      WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
+						      1);
 		if (!platform->workqueue) {
 			DRM_DEV_ERROR(dev, "fail to create work queue\n");
 			ret = -ENOMEM;
diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 40e6c87..d240e29 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -3430,7 +3430,7 @@ int ddb_init_ddbridge(void)
 
 	if (ddb_class_create() < 0)
 		return -1;
-	ddb_wq = alloc_workqueue("ddbridge", 0, 0);
+	ddb_wq = alloc_workqueue("ddbridge", WQ_PERCPU, 0);
 	if (!ddb_wq)
 		return ddb_exit_ddbridge(1, -1);
 
diff --git a/drivers/media/platform/synopsys/hdmirx/snps_hdmirx.c b/drivers/media/platform/synopsys/hdmirx/snps_hdmirx.c
index 61ad20b..1061ab5 100644
--- a/drivers/media/platform/synopsys/hdmirx/snps_hdmirx.c
+++ b/drivers/media/platform/synopsys/hdmirx/snps_hdmirx.c
@@ -1776,7 +1776,7 @@ static void process_signal_change(struct snps_hdmirx_dev *hdmirx_dev)
 			   FIFO_UNDERFLOW_INT_EN |
 			   HDMIRX_AXI_ERROR_INT_EN, 0);
 	hdmirx_reset_dma(hdmirx_dev);
-	queue_delayed_work(system_unbound_wq,
+	queue_delayed_work(system_dfl_wq,
 			   &hdmirx_dev->delayed_work_res_change,
 			   msecs_to_jiffies(50));
 }
@@ -2238,7 +2238,7 @@ static void hdmirx_delayed_work_res_change(struct work_struct *work)
 
 		if (hdmirx_wait_signal_lock(hdmirx_dev)) {
 			hdmirx_plugout(hdmirx_dev);
-			queue_delayed_work(system_unbound_wq,
+			queue_delayed_work(system_dfl_wq,
 					   &hdmirx_dev->delayed_work_hotplug,
 					   msecs_to_jiffies(200));
 		} else {
@@ -2253,7 +2253,7 @@ static irqreturn_t hdmirx_5v_det_irq_handler(int irq, void *dev_id)
 {
 	struct snps_hdmirx_dev *hdmirx_dev = dev_id;
 
-	queue_delayed_work(system_unbound_wq,
+	queue_delayed_work(system_dfl_wq,
 			   &hdmirx_dev->delayed_work_hotplug,
 			   msecs_to_jiffies(10));
 
@@ -2518,7 +2518,7 @@ static void hdmirx_enable_irq(struct device *dev)
 	enable_irq(hdmirx_dev->dma_irq);
 	enable_irq(hdmirx_dev->det_irq);
 
-	queue_delayed_work(system_unbound_wq,
+	queue_delayed_work(system_dfl_wq,
 			   &hdmirx_dev->delayed_work_hotplug,
 			   msecs_to_jiffies(110));
 }
diff --git a/drivers/net/wireless/ath/ath6kl/usb.c b/drivers/net/wireless/ath/ath6kl/usb.c
index 79c18f5..945984c 100644
--- a/drivers/net/wireless/ath/ath6kl/usb.c
+++ b/drivers/net/wireless/ath/ath6kl/usb.c
@@ -636,7 +636,7 @@ static struct ath6kl_usb *ath6kl_usb_create(struct usb_interface *interface)
 	ar_usb = kzalloc_obj(struct ath6kl_usb);
 	if (ar_usb == NULL)
 		return NULL;
-	ar_usb->wq = alloc_workqueue("ath6kl_wq", 0, 0);
+	ar_usb->wq = alloc_workqueue("ath6kl_wq", WQ_PERCPU, 0);
 	if (!ar_usb->wq) {
 		kfree(ar_usb);
 		return NULL;
diff --git a/drivers/platform/cznic/turris-omnia-mcu-gpio.c b/drivers/platform/cznic/turris-omnia-mcu-gpio.c
index 7f0ada4..4e430d6 100644
--- a/drivers/platform/cznic/turris-omnia-mcu-gpio.c
+++ b/drivers/platform/cznic/turris-omnia-mcu-gpio.c
@@ -893,7 +893,7 @@ static bool omnia_irq_read_pending_old(struct omnia_mcu *mcu,
 
 	if (status & OMNIA_STS_BUTTON_PRESSED) {
 		mcu->button_pressed_emul = true;
-		mod_delayed_work(system_wq, &mcu->button_release_emul_work,
+		mod_delayed_work(system_percpu_wq, &mcu->button_release_emul_work,
 				 msecs_to_jiffies(FRONT_BUTTON_RELEASE_DELAY_MS));
 	} else if (mcu->button_pressed_emul) {
 		status |= OMNIA_STS_BUTTON_PRESSED;
diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c
index 0c175e6..f45e58b 100644
--- a/drivers/rapidio/rio.c
+++ b/drivers/rapidio/rio.c
@@ -1994,7 +1994,7 @@ int rio_init_mports(void)
 	 * TODO: Implement restart of discovery process for all or
 	 * individual discovering mports.
 	 */
-	rio_wq = alloc_workqueue("riodisc", 0, 0);
+	rio_wq = alloc_workqueue("riodisc", WQ_PERCPU, 0);
 	if (!rio_wq) {
 		pr_err("RIO: unable allocate rio_wq\n");
 		goto no_disc;
diff --git a/drivers/virt/acrn/irqfd.c b/drivers/virt/acrn/irqfd.c
index acf8cd5..aab15f9 100644
--- a/drivers/virt/acrn/irqfd.c
+++ b/drivers/virt/acrn/irqfd.c
@@ -206,7 +206,7 @@ int acrn_irqfd_init(struct acrn_vm *vm)
 {
 	INIT_LIST_HEAD(&vm->irqfds);
 	mutex_init(&vm->irqfds_lock);
-	vm->irqfd_wq = alloc_workqueue("acrn_irqfd-%u", 0, 0, vm->vmid);
+	vm->irqfd_wq = alloc_workqueue("acrn_irqfd-%u", WQ_PERCPU, 0, vm->vmid);
 	if (!vm->irqfd_wq)
 		return -ENOMEM;
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 0a7d80d..274e2f0 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1951,7 +1951,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info)
 {
 	u32 max_active = fs_info->thread_pool_size;
 	unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
-	unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU;
+	unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE;
 
 	fs_info->workers =
 		btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16);
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 6177624..a283766 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -409,6 +409,7 @@ enum wq_flags {
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
+	__WQ_DEPRECATED		= 1 << 19, /* internal: workqueue is deprecated */
 
 	/* BH wq only allows the following flags */
 	__WQ_BH_ALLOWS		= WQ_BH | WQ_HIGHPRI | WQ_PERCPU,
diff --git a/kernel/umh.c b/kernel/umh.c
index cffda97..48117c5 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -430,7 +430,7 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 	sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done;
 	sub_info->wait = wait;
 
-	queue_work(system_unbound_wq, &sub_info->work);
+	queue_work(system_dfl_wq, &sub_info->work);
 	if (wait == UMH_NO_WAIT)	/* task has freed sub_info */
 		goto unlock;
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0c265ea..78068ae 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2281,6 +2281,14 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	unsigned int req_cpu = cpu;
 
 	/*
+	 * NOTE: Check whether the used workqueue is deprecated and warn
+	 */
+	if (unlikely(wq->flags & __WQ_DEPRECATED))
+		pr_warn_once("workqueue: work func %ps enqueued on deprecated workqueue. "
+			"Use system_{percpu|dfl}_wq instead.\n",
+			work->func);
+
+	/*
 	 * While a work item is PENDING && off queue, a task trying to
 	 * steal the PENDING will busy-loop waiting for it to either get
 	 * queued or lose PENDING.  Grabbing PENDING and queueing should
@@ -5312,16 +5320,6 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq,
 	return pwq;
 }
 
-static void apply_wqattrs_lock(void)
-{
-	mutex_lock(&wq_pool_mutex);
-}
-
-static void apply_wqattrs_unlock(void)
-{
-	mutex_unlock(&wq_pool_mutex);
-}
-
 /**
  * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod
  * @attrs: the wq_attrs of the default pwq of the target workqueue
@@ -5818,7 +5816,7 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
 
 	/* see the comment above the definition of WQ_POWER_EFFICIENT */
 	if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
-		flags |= WQ_UNBOUND;
+		flags = (flags & ~WQ_PERCPU) | WQ_UNBOUND;
 
 	/* allocate wq and format name */
 	if (flags & WQ_UNBOUND)
@@ -5842,6 +5840,23 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
 		pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n",
 			     wq->name);
 
+	/*
+	 * One among WQ_PERCPU and WQ_UNBOUND must be set, but not both.
+	 * - If neither is set, default to WQ_PERCPU
+	 * - If both are set, default to WQ_UNBOUND
+	 *
+	 * This code can be removed after workqueue are unbound by default
+	 */
+	if (unlikely(!(flags & (WQ_UNBOUND | WQ_PERCPU)))) {
+		WARN_ONCE(1, "workqueue: %s is using neither WQ_PERCPU or WQ_UNBOUND. "
+			  "Setting WQ_PERCPU.\n", wq->name);
+		flags |= WQ_PERCPU;
+	} else if (unlikely((flags & WQ_PERCPU) && (flags & WQ_UNBOUND))) {
+		WARN_ONCE(1, "workqueue: %s uses both WQ_PERCPU and WQ_UNBOUND. "
+			  "Dropped WQ_PERCPU, keeping WQ_UNBOUND.\n", wq->name);
+		flags &= ~WQ_PERCPU;
+	}
+
 	if (flags & WQ_BH) {
 		/*
 		 * BH workqueues always share a single execution context per CPU
@@ -5877,7 +5892,7 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
 	 * wq_pool_mutex protects the workqueues list, allocations of PWQs,
 	 * and the global freeze state.
 	 */
-	apply_wqattrs_lock();
+	mutex_lock(&wq_pool_mutex);
 
 	if (alloc_and_link_pwqs(wq) < 0)
 		goto err_unlock_free_node_nr_active;
@@ -5891,7 +5906,7 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
 	if (wq_online && init_rescuer(wq) < 0)
 		goto err_unlock_destroy;
 
-	apply_wqattrs_unlock();
+	mutex_unlock(&wq_pool_mutex);
 
 	if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq))
 		goto err_destroy;
@@ -5899,7 +5914,7 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
 	return wq;
 
 err_unlock_free_node_nr_active:
-	apply_wqattrs_unlock();
+	mutex_unlock(&wq_pool_mutex);
 	/*
 	 * Failed alloc_and_link_pwqs() may leave pending pwq->release_work,
 	 * flushing the pwq_release_worker ensures that the pwq_release_workfn()
@@ -5914,7 +5929,7 @@ err_free_wq:
 	kfree(wq);
 	return NULL;
 err_unlock_destroy:
-	apply_wqattrs_unlock();
+	mutex_unlock(&wq_pool_mutex);
 err_destroy:
 	destroy_workqueue(wq);
 	return NULL;
@@ -6310,7 +6325,7 @@ EXPORT_SYMBOL_GPL(set_worker_desc);
  */
 void print_worker_info(const char *log_lvl, struct task_struct *task)
 {
-	work_func_t *fn = NULL;
+	work_func_t fn = NULL;
 	char name[WQ_NAME_LEN] = { };
 	char desc[WORKER_DESC_LEN] = { };
 	struct pool_workqueue *pwq = NULL;
@@ -7315,7 +7330,7 @@ static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
 	struct workqueue_attrs *attrs;
 	int ret = -ENOMEM;
 
-	apply_wqattrs_lock();
+	mutex_lock(&wq_pool_mutex);
 
 	attrs = wq_sysfs_prep_attrs(wq);
 	if (!attrs)
@@ -7328,7 +7343,7 @@ static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
 		ret = -EINVAL;
 
 out_unlock:
-	apply_wqattrs_unlock();
+	mutex_unlock(&wq_pool_mutex);
 	free_workqueue_attrs(attrs);
 	return ret ?: count;
 }
@@ -7354,7 +7369,7 @@ static ssize_t wq_cpumask_store(struct device *dev,
 	struct workqueue_attrs *attrs;
 	int ret = -ENOMEM;
 
-	apply_wqattrs_lock();
+	mutex_lock(&wq_pool_mutex);
 
 	attrs = wq_sysfs_prep_attrs(wq);
 	if (!attrs)
@@ -7365,7 +7380,7 @@ static ssize_t wq_cpumask_store(struct device *dev,
 		ret = apply_workqueue_attrs_locked(wq, attrs);
 
 out_unlock:
-	apply_wqattrs_unlock();
+	mutex_unlock(&wq_pool_mutex);
 	free_workqueue_attrs(attrs);
 	return ret ?: count;
 }
@@ -7401,13 +7416,13 @@ static ssize_t wq_affn_scope_store(struct device *dev,
 	if (affn < 0)
 		return affn;
 
-	apply_wqattrs_lock();
+	mutex_lock(&wq_pool_mutex);
 	attrs = wq_sysfs_prep_attrs(wq);
 	if (attrs) {
 		attrs->affn_scope = affn;
 		ret = apply_workqueue_attrs_locked(wq, attrs);
 	}
-	apply_wqattrs_unlock();
+	mutex_unlock(&wq_pool_mutex);
 	free_workqueue_attrs(attrs);
 	return ret ?: count;
 }
@@ -7432,13 +7447,13 @@ static ssize_t wq_affinity_strict_store(struct device *dev,
 	if (sscanf(buf, "%d", &v) != 1)
 		return -EINVAL;
 
-	apply_wqattrs_lock();
+	mutex_lock(&wq_pool_mutex);
 	attrs = wq_sysfs_prep_attrs(wq);
 	if (attrs) {
 		attrs->affn_strict = (bool)v;
 		ret = apply_workqueue_attrs_locked(wq, attrs);
 	}
-	apply_wqattrs_unlock();
+	mutex_unlock(&wq_pool_mutex);
 	free_workqueue_attrs(attrs);
 	return ret ?: count;
 }
@@ -7479,12 +7494,12 @@ static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
 	cpumask_and(cpumask, cpumask, cpu_possible_mask);
 	if (!cpumask_empty(cpumask)) {
 		ret = 0;
-		apply_wqattrs_lock();
+		mutex_lock(&wq_pool_mutex);
 		if (!cpumask_equal(cpumask, wq_unbound_cpumask))
 			ret = workqueue_apply_unbound_cpumask(cpumask);
 		if (!ret)
 			cpumask_copy(wq_requested_unbound_cpumask, cpumask);
-		apply_wqattrs_unlock();
+		mutex_unlock(&wq_pool_mutex);
 	}
 
 	return ret;
@@ -8037,12 +8052,12 @@ void __init workqueue_init_early(void)
 		ordered_wq_attrs[i] = attrs;
 	}
 
-	system_wq = alloc_workqueue("events", WQ_PERCPU, 0);
+	system_wq = alloc_workqueue("events", WQ_PERCPU | __WQ_DEPRECATED, 0);
 	system_percpu_wq = alloc_workqueue("events", WQ_PERCPU, 0);
 	system_highpri_wq = alloc_workqueue("events_highpri",
 					    WQ_HIGHPRI | WQ_PERCPU, 0);
 	system_long_wq = alloc_workqueue("events_long", WQ_PERCPU, 0);
-	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
+	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND | __WQ_DEPRECATED, WQ_MAX_ACTIVE);
 	system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
 	system_freezable_wq = alloc_workqueue("events_freezable",
 					      WQ_FREEZABLE | WQ_PERCPU, 0);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index d9d7556..3ca343f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2649,12 +2649,17 @@ config TEST_VMALLOC
 
 config TEST_WORKQUEUE
 	tristate "Test module for stress/performance analysis of workqueue"
+	depends on m
 	default n
 	help
 	  This builds the "test_workqueue" module for benchmarking
 	  workqueue throughput under contention. Useful for evaluating
 	  affinity scope changes (e.g., cache_shard vs cache).
 
+	  The test drives sysfs to switch affinity scopes, so it must be
+	  loaded after userspace has mounted sysfs; building it in (=y)
+	  would run module_init before /sys is available.
+
 	  If unsure, say N.
 
 config TEST_BPF