linux-kernel - [PATCH RFC 09/14] mm: memcg: introduce __mod_lruvec_memcg

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190905214553.1643060-10-guro@fb.com>
Date:   Thu, 5 Sep 2019 14:45:53 -0700
From:   Roman Gushchin <guro@...com>
To:     <linux-mm@...ck.org>
CC:     Michal Hocko <mhocko@...nel.org>,
        Johannes Weiner <hannes@...xchg.org>,
        <linux-kernel@...r.kernel.org>, <kernel-team@...com>,
        Shakeel Butt <shakeelb@...gle.com>,
        Vladimir Davydov <vdavydov.dev@...il.com>,
        Waiman Long <longman@...hat.com>, Roman Gushchin <guro@...com>
Subject: [PATCH RFC 09/14] mm: memcg: introduce __mod_lruvec_memcg_state()

To prepare for per-object accounting of slab objects, let's introduce
__mod_lruvec_memcg_state() and mod_lruvec_memcg_state() helpers,
which are similar to mod_lruvec_state(), but do not update global
node counters, only lruvec and per-cgroup.

It's necessary because soon node slab counters will be used for
accounting of all memory used by slab pages, however on memcg level
only the actually used memory will be counted. Free space will be
shared between all cgroups, so it can't be accounted to any.

Signed-off-by: Roman Gushchin <guro@...com>
---
 include/linux/memcontrol.h | 22 ++++++++++++++++++++++
 mm/memcontrol.c            | 37 +++++++++++++++++++++++++++----------
 2 files changed, 49 insertions(+), 10 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8f1d7161579f..cef8a9c51482 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -739,6 +739,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 
 void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val);
+void __mod_lruvec_memcg_state(struct lruvec *lruvec, enum node_stat_item idx,
+			      int val);
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val);
 
 static inline void mod_lruvec_state(struct lruvec *lruvec,
@@ -751,6 +753,16 @@ static inline void mod_lruvec_state(struct lruvec *lruvec,
 	local_irq_restore(flags);
 }
 
+static inline void mod_lruvec_memcg_state(struct lruvec *lruvec,
+					  enum node_stat_item idx, int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_lruvec_memcg_state(lruvec, idx, val);
+	local_irq_restore(flags);
+}
+
 static inline void __mod_lruvec_page_state(struct page *page,
 					   enum node_stat_item idx, int val)
 {
@@ -1143,6 +1155,16 @@ static inline void mod_lruvec_state(struct lruvec *lruvec,
 	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
 }
 
+static inline void __mod_lruvec_memcg_state(struct lruvec *lruvec,
+					    enum node_stat_item idx, int val)
+{
+}
+
+static inline void mod_lruvec_memcg_state(struct lruvec *lruvec,
+					  enum node_stat_item idx, int val)
+{
+}
+
 static inline void __mod_lruvec_page_state(struct page *page,
 					   enum node_stat_item idx, int val)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d57f95177aec..89a892ef7699 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -795,16 +795,16 @@ parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid)
 }
 
 /**
- * __mod_lruvec_state - update lruvec memory statistics
+ * __mod_lruvec_memcg_state - update lruvec memory statistics
  * @lruvec: the lruvec
  * @idx: the stat item
  * @val: delta to add to the counter, can be negative
  *
  * The lruvec is the intersection of the NUMA node and a cgroup. This
- * function updates the all three counters that are affected by a
- * change of state at this level: per-node, per-cgroup, per-lruvec.
+ * function updates the two of three counters that are affected by a
+ * change of state at this level: per-cgroup and per-lruvec.
  */
-void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+void __mod_lruvec_memcg_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val)
 {
 	pg_data_t *pgdat = lruvec_pgdat(lruvec);
@@ -812,12 +812,6 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	struct mem_cgroup *memcg;
 	long x, threshold = MEMCG_CHARGE_BATCH;
 
-	/* Update node */
-	__mod_node_page_state(pgdat, idx, val);
-
-	if (mem_cgroup_disabled())
-		return;
-
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	memcg = pn->memcg;
 
@@ -841,6 +835,29 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
 }
 
+/**
+ * __mod_lruvec_state - update lruvec memory statistics
+ * @lruvec: the lruvec
+ * @idx: the stat item
+ * @val: delta to add to the counter, can be negative
+ *
+ * The lruvec is the intersection of the NUMA node and a cgroup. This
+ * function updates the all three counters that are affected by a
+ * change of state at this level: per-node, per-cgroup, per-lruvec.
+ */
+void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			int val)
+{
+	pg_data_t *pgdat = lruvec_pgdat(lruvec);
+
+	/* Update node */
+	__mod_node_page_state(pgdat, idx, val);
+
+	/* Update per-cgroup and per-lruvec stats */
+	if (!mem_cgroup_disabled())
+		__mod_lruvec_memcg_state(lruvec, idx, val);
+}
+
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 {
 	struct page *page = virt_to_head_page(p);
-- 
2.21.0