diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index e62d582f4bf3..7e42f0ca3b7b 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -36,9 +36,12 @@ struct pcpuobj_ext {
 #ifdef CONFIG_MEMCG_KMEM
 	struct obj_cgroup	*cgroup;
 #endif
+#ifdef CONFIG_MEM_ALLOC_PROFILING
+	union codetag_ref	tag;
+#endif
 };
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MEM_ALLOC_PROFILING)
 #define NEED_PCPUOBJ_EXT
 #endif
 
@@ -86,7 +89,11 @@ struct pcpu_chunk {
 
 static inline bool need_pcpuobj_ext(void)
 {
-	return !mem_cgroup_kmem_disabled();
+	if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING))
+		return true;
+	if (!mem_cgroup_kmem_disabled())
+		return true;
+	return false;
 }
 
 extern spinlock_t pcpu_lock;
diff --git a/mm/percpu.c b/mm/percpu.c
index 2e5edaad9cc3..90e9e4004ac9 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1699,6 +1699,32 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
+#ifdef CONFIG_MEM_ALLOC_PROFILING
+static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off,
+				      size_t size)
+{
+	if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) {
+		alloc_tag_add(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag,
+			      current->alloc_tag, size);
+	}
+}
+
+static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
+{
+	if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts))
+		alloc_tag_sub(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, size);
+}
+#else
+static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off,
+				      size_t size)
+{
+}
+
+static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
+{
+}
+#endif
+
 /**
  * pcpu_alloc - the percpu allocator
  * @size: size of area to allocate in bytes