From 071aee138410210e3764f3ae8d37ef46dc6d3b42 Mon Sep 17 00:00:00 2001
From: Ying Han <yinghan@google.com>
Date: Tue, 12 Nov 2013 15:07:41 -0800
Subject: memcg: support hierarchical memory.numa_stats

The memory.numa_stat file was not hierarchical.  Memory charged to the
children was not shown in parent's numa_stat.

This change adds the "hierarchical_" stats to the existing stats.  The
new hierarchical stats include the sum of all children's values in
addition to the value of the memcg.

Tested: Create cgroup a, a/b and run workload under b.  The values of
b are included in the "hierarchical_*" under a.

$ cd /sys/fs/cgroup
$ echo 1 > memory.use_hierarchy
$ mkdir a a/b

Run workload in a/b:
$ (echo $BASHPID >> a/b/cgroup.procs && cat /some/file && bash) &

The hierarchical_ fields in parent (a) show use of workload in a/b:
$ cat a/memory.numa_stat
total=0 N0=0 N1=0 N2=0 N3=0
file=0 N0=0 N1=0 N2=0 N3=0
anon=0 N0=0 N1=0 N2=0 N3=0
unevictable=0 N0=0 N1=0 N2=0 N3=0
hierarchical_total=908 N0=552 N1=317 N2=39 N3=0
hierarchical_file=850 N0=549 N1=301 N2=0 N3=0
hierarchical_anon=58 N0=3 N1=16 N2=39 N3=0
hierarchical_unevictable=0 N0=0 N1=0 N2=0 N3=0

$ cat a/b/memory.numa_stat
total=908 N0=552 N1=317 N2=39 N3=0
file=850 N0=549 N1=301 N2=0 N3=0
anon=58 N0=3 N1=16 N2=39 N3=0
unevictable=0 N0=0 N1=0 N2=0 N3=0
hierarchical_total=908 N0=552 N1=317 N2=39 N3=0
hierarchical_file=850 N0=549 N1=301 N2=0 N3=0
hierarchical_anon=58 N0=3 N1=16 N2=39 N3=0
hierarchical_unevictable=0 N0=0 N1=0 N2=0 N3=0

Signed-off-by: Ying Han <yinghan@google.com>
Signed-off-by: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 8af4ad1..e2bc132 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -573,15 +573,19 @@ an memcg since the pages are allowed to be allocated from any physical
 node.  One of the use cases is evaluating application performance by
 combining this information with the application's CPU allocation.
 
-We export "total", "file", "anon" and "unevictable" pages per-node for
-each memcg.  The ouput format of memory.numa_stat is:
+Each memcg's numa_stat file includes "total", "file", "anon" and "unevictable"
+per-node page counts including "hierarchical_<counter>" which sums up all
+hierarchical children's values in addition to the memcg's own value.
+
+The ouput format of memory.numa_stat is:
 
 total=<total pages> N0=<node 0 pages> N1=<node 1 pages> ...
 file=<total file pages> N0=<node 0 pages> N1=<node 1 pages> ...
 anon=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
 unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
+hierarchical_<counter>=<counter pages> N0=<node 0 pages> N1=<node 1 pages> ...
 
-And we have total = file + anon + unevictable.
+The "total" count is sum of file + anon + unevictable.
 
 6. Hierarchy support
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 91b5d3a..c890724 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5396,6 +5396,23 @@ static int memcg_numa_stat_show(struct cgroup_subsys_state *css,
 		seq_putc(m, '\n');
 	}
 
+	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
+		struct mem_cgroup *iter;
+
+		nr = 0;
+		for_each_mem_cgroup_tree(iter, memcg)
+			nr += mem_cgroup_nr_lru_pages(iter, stat->lru_mask);
+		seq_printf(m, "hierarchical_%s=%lu", stat->name, nr);
+		for_each_node_state(nid, N_MEMORY) {
+			nr = 0;
+			for_each_mem_cgroup_tree(iter, memcg)
+				nr += mem_cgroup_node_nr_lru_pages(
+					iter, nid, stat->lru_mask);
+			seq_printf(m, " N%d=%lu", nid, nr);
+		}
+		seq_putc(m, '\n');
+	}
+
 	return 0;
 }
 #endif /* CONFIG_NUMA */
-- 
cgit v0.10.2