per-zone and reclaim enhancements for memory controller: calculate the number of pages to be scanned per cgroup

Define function for calculating the number of scan target on each Zone/LRU.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Paul Menage <menage@google.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.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, 48 insertions, 0 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f82158faa494..d87090eb14c0 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -76,6 +76,10 @@ extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
 extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
                                                         int priority);
 
+extern long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
+                                struct zone *zone, int priority);
+extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
+                                struct zone *zone, int priority);
 
 #else /* CONFIG_CGROUP_MEM_CONT */
 static inline void mm_init_cgroup(struct mm_struct *mm,
@@ -173,6 +177,17 @@ static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
 {
 }
 
+static inline long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
+                                        struct zone *zone, int priority)
+{
+        return 0;
+}
+
+static inline long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
+                                        struct zone *zone, int priority)
+{
+        return 0;
+}
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f8a6a39c440d..40cdba68de34 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -471,6 +471,39 @@ void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
         mem->prev_priority = priority;
 }
 
+/*
+ * Calculate # of pages to be scanned in this priority/zone.
+ * See also vmscan.c
+ *
+ * priority starts from "DEF_PRIORITY" and decremented in each loop.
+ * (see include/linux/mmzone.h)
+ */
+
+long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
+                                   struct zone *zone, int priority)
+{
+        long nr_active;
+        int nid = zone->zone_pgdat->node_id;
+        int zid = zone_idx(zone);
+        struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
+
+        nr_active = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE);
+        return (nr_active >> priority);
+}
+
+long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
+                                        struct zone *zone, int priority)
+{
+        long nr_inactive;
+        int nid = zone->zone_pgdat->node_id;
+        int zid = zone_idx(zone);
+        struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
+
+        nr_inactive = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE);
+
+        return (nr_inactive >> priority);
+}
+
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
                                         struct list_head *dst,
                                         unsigned long *scanned, int order,