[BUGFIX][PATCH 1/4] memcg: fix limit estimation at reclaim for hugepage

[KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>]

From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>

Current memory cgroup's code tends to assume page_size == PAGE_SIZE
and arrangement for THP is not enough yet.

This is one of fixes for supporing THP. This adds
mem_cgroup_check_margin() and checks whether there are required amount of
free resource after memory reclaim. By this, THP page allocation
can know whether it really succeeded or not and avoid infinite-loop
and hangup.

Total fixes for do_charge()/reclaim memory will follow this patch.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
 include/linux/res_counter.h |   11 +++++++++++
 mm/memcontrol.c             |   25 ++++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 1 deletion(-)

Index: mmotm-0125/include/linux/res_counter.h
===================================================================
--- mmotm-0125.orig/include/linux/res_counter.h
+++ mmotm-0125/include/linux/res_counter.h
@@ -182,6 +182,17 @@ static inline bool res_counter_check_und
 	return ret;
 }
 
+static inline s64 res_counter_check_margin(struct res_counter *cnt)
+{
+	s64 ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cnt->lock, flags);
+	ret = cnt->limit - cnt->usage;
+	spin_unlock_irqrestore(&cnt->lock, flags);
+	return ret;
+}
+
 static inline bool res_counter_check_under_soft_limit(struct res_counter *cnt)
 {
 	bool ret;
Index: mmotm-0125/mm/memcontrol.c
===================================================================
--- mmotm-0125.orig/mm/memcontrol.c
+++ mmotm-0125/mm/memcontrol.c
@@ -1111,6 +1111,22 @@ static bool mem_cgroup_check_under_limit
 	return false;
 }
 
+static s64  mem_cgroup_check_margin(struct mem_cgroup *mem)
+{
+	s64 mem_margin;
+
+	if (do_swap_account) {
+		s64 memsw_margin;
+
+		mem_margin = res_counter_check_margin(&mem->res);
+		memsw_margin = res_counter_check_margin(&mem->memsw);
+		if (mem_margin > memsw_margin)
+			mem_margin = memsw_margin;
+	} else
+		mem_margin = res_counter_check_margin(&mem->res);
+	return mem_margin;
+}
+
 static unsigned int get_swappiness(struct mem_cgroup *memcg)
 {
 	struct cgroup *cgrp = memcg->css.cgroup;
@@ -1853,7 +1869,14 @@ static int __mem_cgroup_do_charge(struct
 	 * Check the limit again to see if the reclaim reduced the
 	 * current usage of the cgroup before giving up
 	 */
-	if (ret || mem_cgroup_check_under_limit(mem_over_limit))
+	if (mem_cgroup_check_margin(mem_over_limit) >= csize)
+		return CHARGE_RETRY;
+
+	/*
+ 	 * If the charge size is a PAGE_SIZE, it's not hopeless while
+ 	 * we can reclaim a page.
+ 	 */
+	if (csize == PAGE_SIZE && ret)
 		return CHARGE_RETRY;
 
 	/*