mm: memcontrol: per-lruvec stats infrastructure

lruvecs are at the intersection of the NUMA node and memcg, which is the
scope for most paging activity.

Introduce a convenient accounting infrastructure that maintains
statistics per node, per memcg, and the lruvec itself.

Then convert over accounting sites for statistics that are already
tracked in both nodes and memcgs and can be easily switched.

[hannes@cmpxchg.org: fix crash in the new cgroup stat keeping code]
  Link: http://lkml.kernel.org/r/20170531171450.GA10481@cmpxchg.org
[hannes@cmpxchg.org: don't track uncharged pages at all
  Link: http://lkml.kernel.org/r/20170605175254.GA8547@cmpxchg.org
[hannes@cmpxchg.org: add missing free_percpu()]
  Link: http://lkml.kernel.org/r/20170605175354.GB8547@cmpxchg.org
[linux@roeck-us.net: hexagon: fix build error caused by include file order]
  Link: http://lkml.kernel.org/r/20170617153721.GA4382@roeck-us.net
Link: http://lkml.kernel.org/r/20170530181724.27197-6-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Michal Hocko <mhocko@suse.com>
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>

2 files changed, 216 insertions, 31 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5a72d8377942..3914e3dd6168 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -26,7 +26,8 @@
 #include <linux/page_counter.h>
 #include <linux/vmpressure.h>
 #include <linux/eventfd.h>
-#include <linux/mmzone.h>
+#include <linux/mm.h>
+#include <linux/vmstat.h>
 #include <linux/writeback.h>
 #include <linux/page-flags.h>
 
@@ -98,11 +99,16 @@ struct mem_cgroup_reclaim_iter {
 	unsigned int generation;
 };
 
+struct lruvec_stat {
+	long count[NR_VM_NODE_STAT_ITEMS];
+};
+
 /*
  * per-zone information in memory controller.
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
+	struct lruvec_stat __percpu *lruvec_stat;
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
 	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
@@ -496,23 +502,18 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
 	return val;
 }
 
-static inline void mod_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx, int val)
+static inline void __mod_memcg_state(struct mem_cgroup *memcg,
+				     enum memcg_stat_item idx, int val)
 {
 	if (!mem_cgroup_disabled())
-		this_cpu_add(memcg->stat->count[idx], val);
-}
-
-static inline void inc_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
-{
-	mod_memcg_state(memcg, idx, 1);
+		__this_cpu_add(memcg->stat->count[idx], val);
 }
 
-static inline void dec_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
+static inline void mod_memcg_state(struct mem_cgroup *memcg,
+				   enum memcg_stat_item idx, int val)
 {
-	mod_memcg_state(memcg, idx, -1);
+	if (!mem_cgroup_disabled())
+		this_cpu_add(memcg->stat->count[idx], val);
 }
 
 /**
@@ -532,6 +533,13 @@ static inline void dec_memcg_state(struct mem_cgroup *memcg,
  *
  * Kernel pages are an exception to this, since they'll never move.
  */
+static inline void __mod_memcg_page_state(struct page *page,
+					  enum memcg_stat_item idx, int val)
+{
+	if (page->mem_cgroup)
+		__mod_memcg_state(page->mem_cgroup, idx, val);
+}
+
 static inline void mod_memcg_page_state(struct page *page,
 					enum memcg_stat_item idx, int val)
 {
@@ -539,16 +547,76 @@ static inline void mod_memcg_page_state(struct page *page,
 		mod_memcg_state(page->mem_cgroup, idx, val);
 }
 
-static inline void inc_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
+					      enum node_stat_item idx)
 {
-	mod_memcg_page_state(page, idx, 1);
+	struct mem_cgroup_per_node *pn;
+	long val = 0;
+	int cpu;
+
+	if (mem_cgroup_disabled())
+		return node_page_state(lruvec_pgdat(lruvec), idx);
+
+	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	for_each_possible_cpu(cpu)
+		val += per_cpu(pn->lruvec_stat->count[idx], cpu);
+
+	if (val < 0)
+		val = 0;
+
+	return val;
 }
 
-static inline void dec_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+static inline void __mod_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx, int val)
 {
-	mod_memcg_page_state(page, idx, -1);
+	struct mem_cgroup_per_node *pn;
+
+	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+	if (mem_cgroup_disabled())
+		return;
+	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	__mod_memcg_state(pn->memcg, idx, val);
+	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+}
+
+static inline void mod_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx, int val)
+{
+	struct mem_cgroup_per_node *pn;
+
+	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+	if (mem_cgroup_disabled())
+		return;
+	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	mod_memcg_state(pn->memcg, idx, val);
+	this_cpu_add(pn->lruvec_stat->count[idx], val);
+}
+
+static inline void __mod_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx, int val)
+{
+	struct mem_cgroup_per_node *pn;
+
+	__mod_node_page_state(page_pgdat(page), idx, val);
+	if (mem_cgroup_disabled() || !page->mem_cgroup)
+		return;
+	__mod_memcg_state(page->mem_cgroup, idx, val);
+	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
+	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+}
+
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	struct mem_cgroup_per_node *pn;
+
+	mod_node_page_state(page_pgdat(page), idx, val);
+	if (mem_cgroup_disabled() || !page->mem_cgroup)
+		return;
+	mod_memcg_state(page->mem_cgroup, idx, val);
+	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
+	this_cpu_add(pn->lruvec_stat->count[idx], val);
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
@@ -777,19 +845,21 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
 	return 0;
 }
 
-static inline void mod_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx,
-				   int nr)
+static inline void __mod_memcg_state(struct mem_cgroup *memcg,
+				     enum memcg_stat_item idx,
+				     int nr)
 {
 }
 
-static inline void inc_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
+static inline void mod_memcg_state(struct mem_cgroup *memcg,
+				   enum memcg_stat_item idx,
+				   int nr)
 {
 }
 
-static inline void dec_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
+static inline void __mod_memcg_page_state(struct page *page,
+					  enum memcg_stat_item idx,
+					  int nr)
 {
 }
 
@@ -799,14 +869,34 @@ static inline void mod_memcg_page_state(struct page *page,
 {
 }
 
-static inline void inc_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
+					      enum node_stat_item idx)
 {
+	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
-static inline void dec_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+static inline void __mod_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx, int val)
 {
+	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+}
+
+static inline void mod_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx, int val)
+{
+	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+}
+
+static inline void __mod_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx, int val)
+{
+	__mod_node_page_state(page_pgdat(page), idx, val);
+}
+
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	mod_node_page_state(page_pgdat(page), idx, val);
 }
 
 static inline
@@ -838,6 +928,102 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 }
 #endif /* CONFIG_MEMCG */
 
+static inline void __inc_memcg_state(struct mem_cgroup *memcg,
+				     enum memcg_stat_item idx)
+{
+	__mod_memcg_state(memcg, idx, 1);
+}
+
+static inline void __dec_memcg_state(struct mem_cgroup *memcg,
+				     enum memcg_stat_item idx)
+{
+	__mod_memcg_state(memcg, idx, -1);
+}
+
+static inline void __inc_memcg_page_state(struct page *page,
+					  enum memcg_stat_item idx)
+{
+	__mod_memcg_page_state(page, idx, 1);
+}
+
+static inline void __dec_memcg_page_state(struct page *page,
+					  enum memcg_stat_item idx)
+{
+	__mod_memcg_page_state(page, idx, -1);
+}
+
+static inline void __inc_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx)
+{
+	__mod_lruvec_state(lruvec, idx, 1);
+}
+
+static inline void __dec_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx)
+{
+	__mod_lruvec_state(lruvec, idx, -1);
+}
+
+static inline void __inc_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx)
+{
+	__mod_lruvec_page_state(page, idx, 1);
+}
+
+static inline void __dec_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx)
+{
+	__mod_lruvec_page_state(page, idx, -1);
+}
+
+static inline void inc_memcg_state(struct mem_cgroup *memcg,
+				   enum memcg_stat_item idx)
+{
+	mod_memcg_state(memcg, idx, 1);
+}
+
+static inline void dec_memcg_state(struct mem_cgroup *memcg,
+				   enum memcg_stat_item idx)
+{
+	mod_memcg_state(memcg, idx, -1);
+}
+
+static inline void inc_memcg_page_state(struct page *page,
+					enum memcg_stat_item idx)
+{
+	mod_memcg_page_state(page, idx, 1);
+}
+
+static inline void dec_memcg_page_state(struct page *page,
+					enum memcg_stat_item idx)
+{
+	mod_memcg_page_state(page, idx, -1);
+}
+
+static inline void inc_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx)
+{
+	mod_lruvec_state(lruvec, idx, 1);
+}
+
+static inline void dec_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx)
+{
+	mod_lruvec_state(lruvec, idx, -1);
+}
+
+static inline void inc_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx)
+{
+	mod_lruvec_page_state(page, idx, 1);
+}
+
+static inline void dec_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx)
+{
+	mod_lruvec_page_state(page, idx, -1);
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 613771909b6e..b3d85f30d424 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -3,7 +3,6 @@
 
 #include <linux/types.h>
 #include <linux/percpu.h>
-#include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/vm_event_item.h>
 #include <linux/atomic.h>