diff --git a/mm/slab_common.c b/mm/slab_common.c
index b19ba1b31484..7223a7596dab 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1667,14 +1667,6 @@ static bool kfree_rcu_sheaf(void *obj)
 {
 	struct kmem_cache *s;
 	struct slab *slab;
-	unsigned int free_flags = SLAB_FREE_DEFAULT;
-
-	/*
-	 * It is not safe to spin on PREEMPT_RT because the kernel might be
-	 * holding a raw spinlock and slab acquires sleeping locks.
-	 */
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		free_flags = SLAB_FREE_NOLOCK;
 
 	if (is_vmalloc_addr(obj))
 		return false;
@@ -1685,7 +1677,7 @@ static bool kfree_rcu_sheaf(void *obj)
 
 	s = slab->slab_cache;
 	if (likely(!IS_ENABLED(CONFIG_NUMA) || slab_nid(slab) == numa_mem_id()))
-		return __kfree_rcu_sheaf(s, obj, free_flags);
+		return __kfree_rcu_sheaf(s, obj, SLAB_FREE_DEFAULT);
 
 	return false;
 }
@@ -2034,7 +2026,13 @@ void kvfree_call_rcu(struct kvfree_rcu_head *head, void *ptr)
 	if (!head)
 		might_sleep();
 
-	if (kfree_rcu_sheaf(ptr))
+	/*
+	 * kvfree_rcu() is called by set_cpus_allowed_force() with
+	 * task_struct::pi_lock acquired. On PREEMPT_RT the local_trylock()
+	 * usage below will acquire the waitlock which must be avoided.
+	 * Therefore avoid it on PREEMPT_RT.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && kfree_rcu_sheaf(ptr))
 		return;
 
 	// Queue the object but don't yet schedule the batch.
diff --git a/mm/slub.c b/mm/slub.c
index f9b56cb439e7..54ec12503357 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5680,10 +5680,12 @@ static noinline void free_to_partial_list(
  *
  * Fail if the slab isn't full anymore due to a concurrent free.
  */
-static bool __slab_try_return_freelist(struct kmem_cache *s, struct slab *slab,
-				       void *head, int cnt)
+static bool __slab_try_return_freelist(struct kmem_cache *s,
+				       struct kmem_cache_node *n,
+				       struct slab *slab, void *head, int cnt)
 {
 	struct freelist_counters old, new;
+	unsigned long flags;
 
 	old.freelist = slab->freelist;
 	old.counters = slab->counters;
@@ -5695,9 +5697,15 @@ static bool __slab_try_return_freelist(struct kmem_cache *s, struct slab *slab,
 	new.counters = old.counters;
 	new.inuse -= cnt;
 
-	if (!slab_update_freelist(s, slab, &old, &new, "__slab_try_return_freelist"))
-		return false;
+	spin_lock_irqsave(&n->list_lock, flags);
 
+	if (!slab_update_freelist(s, slab, &old, &new, "__slab_try_return_freelist")) {
+		spin_unlock_irqrestore(&n->list_lock, flags);
+		return false;
+	}
+
+	add_partial(n, slab, ADD_TO_TAIL);
+	spin_unlock_irqrestore(&n->list_lock, flags);
 	return true;
 }
 
@@ -6088,8 +6096,9 @@ static void rcu_free_sheaf(struct rcu_head *head)
 /*
  * kvfree_call_rcu() can be called while holding a raw_spinlock_t. Since
  * __kfree_rcu_sheaf() may acquire a spinlock_t (sleeping lock on PREEMPT_RT),
- * this would violate lock nesting rules. Therefore, kvfree_call_rcu() avoids
- * this problem by passing SLAB_FREE_NOLOCK on PREEMPT_RT.
+ * this would violate lock nesting rules. Therefore, kfree_call_rcu_nolock()
+ * avoids this problem by passing SLAB_FREE_NOLOCK. kvfree_call_rcu() is
+ * bypassing the sheaves layer completely on PREEMPT_RT.
  *
  * However, lockdep still complains that it is invalid to acquire spinlock_t
  * while holding raw_spinlock_t, even on !PREEMPT_RT where spinlock_t is a
@@ -7296,10 +7305,8 @@ __refill_objects_node(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int mi
 			void *head = object;
 			void *tail;
 
-			if (__slab_try_return_freelist(s, slab, head, count)) {
-				list_add(&slab->slab_list, &pc.slabs);
+			if (__slab_try_return_freelist(s, n, slab, head, count))
 				break;
-			}
 
 			do {
 				tail = object;
@@ -7312,7 +7319,7 @@ __refill_objects_node(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int mi
 			break;
 	}
 
-	if (!list_empty(&pc.slabs)) {
+	if (unlikely(!list_empty(&pc.slabs))) {
 		spin_lock_irqsave(&n->list_lock, flags);
 
 		list_for_each_entry(slab, &pc.slabs, slab_list)