memory controller: soft limit reclaim on contention

Implement reclaim from groups over their soft limit

Permit reclaim from memory cgroups on contention (via the direct reclaim
path).

memory cgroup soft limit reclaim finds the group that exceeds its soft
limit by the largest number of pages and reclaims pages from it and then
reinserts the cgroup into its correct place in the rbtree.

Add additional checks to mem_cgroup_hierarchical_reclaim() to detect long
loops in case all swap is turned off.  The code has been refactored and
the loop check (loop < 2) has been enhanced for soft limits.  For soft
limits, we try to do more targetted reclaim.  Instead of bailing out after
two loops, the routine now reclaims memory proportional to the size by
which the soft limit is exceeded.  The proportion has been empirically
determined.

[akpm@linux-foundation.org: build fix]
[kamezawa.hiroyu@jp.fujitsu.com: fix softlimit css refcnt handling]
[nishimura@mxp.nes.nec.co.jp: refcount of the "victim" should be decremented before exiting the loop]
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 15 insertions, 0 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e46a0734ab6e..bf9213b2db8f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -118,6 +118,9 @@ static inline bool mem_cgroup_disabled(void)
 
 extern bool mem_cgroup_oom_called(struct task_struct *task);
 void mem_cgroup_update_mapped_file_stat(struct page *page, int val);
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+                                                gfp_t gfp_mask, int nid,
+                                                int zid);
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct mem_cgroup;
 
@@ -276,6 +279,13 @@ static inline void mem_cgroup_update_mapped_file_stat(struct page *page,
 {
 }
 
+static inline
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+                                            gfp_t gfp_mask, int nid, int zid)
+{
+        return 0;
+}
+
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 6c990e658f4e..4c78fea989b9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -217,6 +217,11 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
                                                   gfp_t gfp_mask, bool noswap,
                                                   unsigned int swappiness);
+extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+                                                gfp_t gfp_mask, bool noswap,
+                                                unsigned int swappiness,
+                                                struct zone *zone,
+                                                int nid);
 extern int __isolate_lru_page(struct page *page, int mode, int file);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;