diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 69361742893a..e319bd5e8b75 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -974,7 +974,7 @@ static int __init cgwb_init(void)
 	 * system_percpu_wq.  Put them in a separate wq and limit concurrency.
 	 * There's no point in executing many of these in parallel.
 	 */
-	cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1);
+	cgwb_release_wq = alloc_workqueue("cgwb_release", WQ_PERCPU, 1);
 	if (!cgwb_release_wq)
 		return -ENOMEM;
 
diff --git a/mm/slub.c b/mm/slub.c
index 861592ac5425..409d16695c8b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -8542,7 +8542,8 @@ void __init kmem_cache_init(void)
 
 void __init kmem_cache_init_late(void)
 {
-	flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM, 0);
+	flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM | WQ_PERCPU,
+				  0);
 	WARN_ON(!flushwq);
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 23e176e1d09d..99270713e0c1 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2259,7 +2259,8 @@ void __init init_mm_internals(void)
 {
 	int ret __maybe_unused;
 
-	mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0);
+	mm_percpu_wq = alloc_workqueue("mm_percpu_wq",
+				       WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 
 #ifdef CONFIG_SMP
 	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",