mm: memcg/percpu: per-memcg percpu memory statistics

Percpu memory can represent a noticeable chunk of the total memory
consumption, especially on big machines with many CPUs.  Let's track
percpu memory usage for each memcg and display it in memory.stat.

A percpu allocation is usually scattered over multiple pages (and nodes),
and can be significantly smaller than a page.  So let's add a byte-sized
counter on the memcg level: MEMCG_PERCPU_B.  Byte-sized vmstat infra
created for slabs can be perfectly reused for percpu case.

[guro@fb.com: v3]
  Link: http://lkml.kernel.org/r/20200623184515.4132564-4-guro@fb.com

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Dennis Zhou <dennis@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tobin C. Harding <tobin@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>
Cc: Bixuan Cui <cuibixuan@huawei.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200608230819.832349-4-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index fa4018af..6be4378 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1274,6 +1274,10 @@
 		Amount of memory used for storing in-kernel data
 		structures.
 
+	  percpu
+		Amount of memory used for storing per-cpu kernel
+		data structures.
+
 	  sock
 		Amount of memory used in network transmission buffers
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1bb49b6..2c2d301 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -32,6 +32,7 @@ struct kmem_cache;
 enum memcg_stat_item {
 	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
+	MEMCG_PERCPU_B,
 	MEMCG_NR_STAT,
 };
 
@@ -339,6 +340,13 @@ struct mem_cgroup {
 
 extern struct mem_cgroup *root_mem_cgroup;
 
+static __always_inline bool memcg_stat_item_in_bytes(int idx)
+{
+	if (idx == MEMCG_PERCPU_B)
+		return true;
+	return vmstat_item_in_bytes(idx);
+}
+
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return (memcg == root_mem_cgroup);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8d9ceea..36d5300 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -781,7 +781,7 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 	if (mem_cgroup_disabled())
 		return;
 
-	if (vmstat_item_in_bytes(idx))
+	if (memcg_stat_item_in_bytes(idx))
 		threshold <<= PAGE_SHIFT;
 
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
@@ -1488,6 +1488,8 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 	seq_buf_printf(&s, "slab %llu\n",
 		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) +
 			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B)));
+	seq_buf_printf(&s, "percpu %llu\n",
+		       (u64)memcg_page_state(memcg, MEMCG_PERCPU_B));
 	seq_buf_printf(&s, "sock %llu\n",
 		       (u64)memcg_page_state(memcg, MEMCG_SOCK) *
 		       PAGE_SIZE);
diff --git a/mm/percpu.c b/mm/percpu.c
index dc1a213..f470962 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1610,6 +1610,11 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
 
 	if (chunk) {
 		chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg;
+
+		rcu_read_lock();
+		mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
+				size * num_possible_cpus());
+		rcu_read_unlock();
 	} else {
 		obj_cgroup_uncharge(objcg, size * num_possible_cpus());
 		obj_cgroup_put(objcg);
@@ -1628,6 +1633,11 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
 
 	obj_cgroup_uncharge(objcg, size * num_possible_cpus());
 
+	rcu_read_lock();
+	mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
+			-(size * num_possible_cpus()));
+	rcu_read_unlock();
+
 	obj_cgroup_put(objcg);
 }