diff --git a/mm/slub.c b/mm/slub.c
index b0c50df49cf3..7b6d8df06ad9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -883,6 +883,97 @@ static inline unsigned long get_orig_size(struct kmem_cache *s, void *object)
 	return *(unsigned long *)p;
 }
 
+#ifdef CONFIG_SLAB_OBJ_EXT
+
+/*
+ * Check if memory cgroup or memory allocation profiling is enabled.
+ * If enabled, SLUB tries to reduce memory overhead of accounting
+ * slab objects. If neither is enabled when this function is called,
+ * the optimization is simply skipped to avoid affecting caches that do not
+ * need slabobj_ext metadata.
+ *
+ * However, this may disable optimization when memory cgroup or memory
+ * allocation profiling is used, but slabs are created too early
+ * even before those subsystems are initialized.
+ */
+static inline bool need_slab_obj_exts(struct kmem_cache *s)
+{
+	if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT))
+		return true;
+
+	if (mem_alloc_profiling_enabled())
+		return true;
+
+	return false;
+}
+
+static inline unsigned int obj_exts_size_in_slab(struct slab *slab)
+{
+	return sizeof(struct slabobj_ext) * slab->objects;
+}
+
+static inline unsigned long obj_exts_offset_in_slab(struct kmem_cache *s,
+						    struct slab *slab)
+{
+	unsigned long objext_offset;
+
+	objext_offset = s->size * slab->objects;
+	objext_offset = ALIGN(objext_offset, sizeof(struct slabobj_ext));
+	return objext_offset;
+}
+
+static inline bool obj_exts_fit_within_slab_leftover(struct kmem_cache *s,
+						     struct slab *slab)
+{
+	unsigned long objext_offset = obj_exts_offset_in_slab(s, slab);
+	unsigned long objext_size = obj_exts_size_in_slab(slab);
+
+	return objext_offset + objext_size <= slab_size(slab);
+}
+
+static inline bool obj_exts_in_slab(struct kmem_cache *s, struct slab *slab)
+{
+	unsigned long obj_exts;
+	unsigned long start;
+	unsigned long end;
+
+	obj_exts = slab_obj_exts(slab);
+	if (!obj_exts)
+		return false;
+
+	start = (unsigned long)slab_address(slab);
+	end = start + slab_size(slab);
+	return (obj_exts >= start) && (obj_exts < end);
+}
+#else
+static inline bool need_slab_obj_exts(struct kmem_cache *s)
+{
+	return false;
+}
+
+static inline unsigned int obj_exts_size_in_slab(struct slab *slab)
+{
+	return 0;
+}
+
+static inline unsigned long obj_exts_offset_in_slab(struct kmem_cache *s,
+						    struct slab *slab)
+{
+	return 0;
+}
+
+static inline bool obj_exts_fit_within_slab_leftover(struct kmem_cache *s,
+						     struct slab *slab)
+{
+	return false;
+}
+
+static inline bool obj_exts_in_slab(struct kmem_cache *s, struct slab *slab)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SLUB_DEBUG
 
 /*
@@ -1418,7 +1509,15 @@ slab_pad_check(struct kmem_cache *s, struct slab *slab)
 	start = slab_address(slab);
 	length = slab_size(slab);
 	end = start + length;
-	remainder = length % s->size;
+
+	if (obj_exts_in_slab(s, slab)) {
+		remainder = length;
+		remainder -= obj_exts_offset_in_slab(s, slab);
+		remainder -= obj_exts_size_in_slab(slab);
+	} else {
+		remainder = length % s->size;
+	}
+
 	if (!remainder)
 		return;
 
@@ -2238,6 +2337,11 @@ static inline void free_slab_obj_exts(struct slab *slab)
 		return;
 	}
 
+	if (obj_exts_in_slab(slab->slab_cache, slab)) {
+		slab->obj_exts = 0;
+		return;
+	}
+
 	/*
 	 * obj_exts was created with __GFP_NO_OBJ_EXT flag, therefore its
 	 * corresponding extension will be NULL. alloc_tag_sub() will throw a
@@ -2253,6 +2357,36 @@ static inline void free_slab_obj_exts(struct slab *slab)
 	slab->obj_exts = 0;
 }
 
+/*
+ * Try to allocate slabobj_ext array from unused space.
+ * This function must be called on a freshly allocated slab to prevent
+ * concurrency problems.
+ */
+static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
+{
+	void *addr;
+	unsigned long obj_exts;
+
+	if (!need_slab_obj_exts(s))
+		return;
+
+	if (obj_exts_fit_within_slab_leftover(s, slab)) {
+		addr = slab_address(slab) + obj_exts_offset_in_slab(s, slab);
+		addr = kasan_reset_tag(addr);
+		obj_exts = (unsigned long)addr;
+
+		get_slab_obj_exts(obj_exts);
+		memset(addr, 0, obj_exts_size_in_slab(slab));
+		put_slab_obj_exts(obj_exts);
+
+#ifdef CONFIG_MEMCG
+		obj_exts |= MEMCG_DATA_OBJEXTS;
+#endif
+		slab->obj_exts = obj_exts;
+		slab_set_stride(slab, sizeof(struct slabobj_ext));
+	}
+}
+
 #else /* CONFIG_SLAB_OBJ_EXT */
 
 static inline void init_slab_obj_exts(struct slab *slab)
@@ -2269,6 +2403,11 @@ static inline void free_slab_obj_exts(struct slab *slab)
 {
 }
 
+static inline void alloc_slab_obj_exts_early(struct kmem_cache *s,
+						       struct slab *slab)
+{
+}
+
 #endif /* CONFIG_SLAB_OBJ_EXT */
 
 #ifdef CONFIG_MEM_ALLOC_PROFILING
@@ -3265,7 +3404,9 @@ static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
 static __always_inline void account_slab(struct slab *slab, int order,
 					 struct kmem_cache *s, gfp_t gfp)
 {
-	if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT))
+	if (memcg_kmem_online() &&
+			(s->flags & SLAB_ACCOUNT) &&
+			!slab_obj_exts(slab))
 		alloc_slab_obj_exts(slab, s, gfp, true);
 
 	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
@@ -3329,9 +3470,6 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	slab->objects = oo_objects(oo);
 	slab->inuse = 0;
 	slab->frozen = 0;
-	init_slab_obj_exts(slab);
-
-	account_slab(slab, oo_order(oo), s, flags);
 
 	slab->slab_cache = s;
 
@@ -3340,6 +3478,13 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	start = slab_address(slab);
 
 	setup_slab_debug(s, slab, start);
+	init_slab_obj_exts(slab);
+	/*
+	 * Poison the slab before initializing the slabobj_ext array
+	 * to prevent the array from being overwritten.
+	 */
+	alloc_slab_obj_exts_early(s, slab);
+	account_slab(slab, oo_order(oo), s, flags);
 
 	shuffle = shuffle_freelist(s, slab);