mm: fix vm-scalability regression in cgroup-aware workingset code

Commit 23047a96d7cf ("mm: workingset: per-cgroup cache thrash
detection") added a page->mem_cgroup lookup to the cache eviction,
refault, and activation paths, as well as locking to the activation
path, and the vm-scalability tests showed a regression of -23%.

While the test in question is an artificial worst-case scenario that
doesn't occur in real workloads - reading two sparse files in parallel
at full CPU speed just to hammer the LRU paths - there is still some
optimizations that can be done in those paths.

Inline the lookup functions to eliminate calls.  Also, page->mem_cgroup
doesn't need to be stabilized when counting an activation; we merely
need to hold the RCU lock to prevent the memcg from being freed.

This cuts down on overhead quite a bit:

23047a96d7cfcfca 063f6715e77a7be5770d6081fe
---------------- --------------------------
         %stddev     %change         %stddev
             \          |                \
  21621405 +- 0%     +11.3%   24069657 +- 2%  vm-scalability.throughput

[linux@roeck-us.net: drop unnecessary include file]
[hannes@cmpxchg.org: add WARN_ON_ONCE()s]
  Link: http://lkml.kernel.org/r/20160707194024.GA26580@cmpxchg.org
Link: http://lkml.kernel.org/r/20160624175101.GA3024@cmpxchg.org
Reported-by: Ye Xiaolong <xiaolong.ye@intel.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 52 insertions, 1 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 71aff733a497..1c4df4420258 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -314,7 +314,48 @@ void mem_cgroup_uncharge_list(struct list_head *page_list);
 
 void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
 
-struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
+static inline struct mem_cgroup_per_zone *
+mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
+{
+	int nid = zone_to_nid(zone);
+	int zid = zone_idx(zone);
+
+	return &memcg->nodeinfo[nid]->zoneinfo[zid];
+}
+
+/**
+ * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
+ * @zone: zone of the wanted lruvec
+ * @memcg: memcg of the wanted lruvec
+ *
+ * Returns the lru list vector holding pages for the given @zone and
+ * @mem.  This can be the global zone lruvec, if the memory controller
+ * is disabled.
+ */
+static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
+						    struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_per_zone *mz;
+	struct lruvec *lruvec;
+
+	if (mem_cgroup_disabled()) {
+		lruvec = &zone->lruvec;
+		goto out;
+	}
+
+	mz = mem_cgroup_zone_zoneinfo(memcg, zone);
+	lruvec = &mz->lruvec;
+out:
+	/*
+	 * Since a node can be onlined after the mem_cgroup was created,
+	 * we have to be prepared to initialize lruvec->zone here;
+	 * and if offlined then reonlined, we need to reinitialize it.
+	 */
+	if (unlikely(lruvec->zone != zone))
+		lruvec->zone = zone;
+	return lruvec;
+}
+
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c606fe4f9a7f..97065e1f0237 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -973,11 +973,21 @@ static inline struct mem_cgroup *page_memcg(struct page *page)
 {
 	return page->mem_cgroup;
 }
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return READ_ONCE(page->mem_cgroup);
+}
 #else
 static inline struct mem_cgroup *page_memcg(struct page *page)
 {
 	return NULL;
 }
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return NULL;
+}
 #endif
 
 /*