mm: memcg/percpu: account extra objcg space to memory cgroups

Similar to slab memory allocator, for each accounted percpu object there
is an extra space which is used to store obj_cgroup membership.  Charge
it too.

[akpm@linux-foundation.org: fix layout]

Link: https://lkml.kernel.org/r/20211126040606.97836-1-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/percpu-internal.h

@@ -113,6 +113,24 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk)
 	return pcpu_nr_pages_to_map_bits(chunk->nr_pages);
 }
 
+#ifdef CONFIG_MEMCG_KMEM
+/**
+ * pcpu_obj_full_size - helper to calculate size of each accounted object
+ * @size: size of area to allocate in bytes
+ *
+ * For each accounted object there is an extra space which is used to store
+ * obj_cgroup membership. Charge it too.
+ */
+static inline size_t pcpu_obj_full_size(size_t size)
+{
+	size_t extra_size;
+
+	extra_size = size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *);
+
+	return size * num_possible_cpus() + extra_size;
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 #ifdef CONFIG_PERCPU_STATS
 
 #include <linux/spinlock.h>

mm/percpu.c

@@ -1635,7 +1635,7 @@ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp,
 	if (!objcg)
 		return true;
 
-	if (obj_cgroup_charge(objcg, gfp, size * num_possible_cpus())) {
+	if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) {
 		obj_cgroup_put(objcg);
 		return false;
 	}
@@ -1656,10 +1656,10 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
 
 		rcu_read_lock();
 		mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
-				size * num_possible_cpus());
+				pcpu_obj_full_size(size));
 		rcu_read_unlock();
 	} else {
-		obj_cgroup_uncharge(objcg, size * num_possible_cpus());
+		obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size));
 		obj_cgroup_put(objcg);
 	}
 }
@@ -1676,11 +1676,11 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
 		return;
 	chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL;
 
-	obj_cgroup_uncharge(objcg, size * num_possible_cpus());
+	obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size));
 
 	rcu_read_lock();
 	mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
-			-(size * num_possible_cpus()));
+			-pcpu_obj_full_size(size));
 	rcu_read_unlock();
 
 	obj_cgroup_put(objcg);