memcg: reduce the size of struct memcg 244-fold.

In order to maintain all the memcg bookkeeping, we need per-node
descriptors, which will in turn contain a per-zone descriptor.

Because we want to statically allocate those, this array ends up being
very big.  Part of the reason is that we allocate something large enough
to hold MAX_NUMNODES, the compile time constant that holds the maximum
number of nodes we would ever consider.

However, we can do better in some cases if the firmware help us.  This
is true for modern x86 machines; coincidentally one of the architectures
in which MAX_NUMNODES tends to be very big.

By using the firmware-provided maximum number of nodes instead of
MAX_NUMNODES, we can reduce the memory footprint of struct memcg
considerably.  In the extreme case in which we have only one node, this
reduces the size of the structure from ~ 64k to ~2k.  This is
particularly important because it means that we will no longer resort to
the vmalloc area for the struct memcg on defconfigs.  We also have
enough room for an extra node and still be outside vmalloc.

One also has to keep in mind that with the industry's ability to fit
more processors in a die as fast as the FED prints money, a nodes = 2
configuration is already respectably big.

[akpm@linux-foundation.org: add check for invalid nid, remove inline]
Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ying Han <yinghan@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 26 insertions, 15 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 972f822b142b..ae0433885b69 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -180,7 +180,7 @@ struct mem_cgroup_per_node {
 };
 
 struct mem_cgroup_lru_info {
-	struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
+	struct mem_cgroup_per_node *nodeinfo[0];
 };
 
 /*
@@ -284,17 +284,6 @@ struct mem_cgroup {
 	 */
 	struct res_counter kmem;
 	/*
-	 * Per cgroup active and inactive list, similar to the
-	 * per zone LRU lists.
-	 */
-	struct mem_cgroup_lru_info info;
-	int last_scanned_node;
-#if MAX_NUMNODES > 1
-	nodemask_t	scan_nodes;
-	atomic_t	numainfo_events;
-	atomic_t	numainfo_updating;
-#endif
-	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
 	bool use_hierarchy;
@@ -357,8 +346,29 @@ struct mem_cgroup {
         /* Index in the kmem_cache->memcg_params->memcg_caches array */
 	int kmemcg_id;
 #endif
+
+	int last_scanned_node;
+#if MAX_NUMNODES > 1
+	nodemask_t	scan_nodes;
+	atomic_t	numainfo_events;
+	atomic_t	numainfo_updating;
+#endif
+	/*
+	 * Per cgroup active and inactive list, similar to the
+	 * per zone LRU lists.
+	 *
+	 * WARNING: This has to be the last element of the struct. Don't
+	 * add new fields after this point.
+	 */
+	struct mem_cgroup_lru_info info;
 };
 
+static size_t memcg_size(void)
+{
+	return sizeof(struct mem_cgroup) +
+		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+}
+
 /* internal only representation about the status of kmem accounting. */
 enum {
 	KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
@@ -635,6 +645,7 @@ static void drain_all_stock_async(struct mem_cgroup *memcg);
 static struct mem_cgroup_per_zone *
 mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid)
 {
+	VM_BUG_ON((unsigned)nid >= nr_node_ids);
 	return &memcg->info.nodeinfo[nid]->zoneinfo[zid];
 }
 
@@ -5925,9 +5936,9 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
-	int size = sizeof(struct mem_cgroup);
+	size_t size = memcg_size();
 
-	/* Can be very big if MAX_NUMNODES is very big */
+	/* Can be very big if nr_node_ids is very big */
 	if (size < PAGE_SIZE)
 		memcg = kzalloc(size, GFP_KERNEL);
 	else
@@ -5964,7 +5975,7 @@ out_free:
 static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
-	int size = sizeof(struct mem_cgroup);
+	size_t size = memcg_size();
 
 	mem_cgroup_remove_from_trees(memcg);
 	free_css_id(&mem_cgroup_subsys, &memcg->css);