Memory controller: add per cgroup LRU and reclaim

Add the page_cgroup to the per cgroup LRU.  The reclaim algorithm has
been modified to make the isolate_lru_pages() as a pluggable component.  The
scan_control data structure now accepts the cgroup on behalf of which
reclaims are carried out.  try_to_free_pages() has been extended to become
cgroup aware.

[akpm@linux-foundation.org: fix warning]
[Lee.Schermerhorn@hp.com: initialize all scan_control's isolate_pages member]
[bunk@kernel.org: make do_try_to_free_pages() static]
[hugh@veritas.com: memcgroup: fix try_to_free order]
[kamezawa.hiroyu@jp.fujitsu.com: this unlock_page_cgroup() is unnecessary]
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: David Rientjes <rientjes@google.com>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/memcontrol.h

@@ -32,6 +32,13 @@ extern void page_assign_page_cgroup(struct page *page,
 extern struct page_cgroup *page_get_page_cgroup(struct page *page);
 extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm);
 extern void mem_cgroup_uncharge(struct page_cgroup *pc);
+extern void mem_cgroup_move_lists(struct page_cgroup *pc, bool active);
+extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
+					struct list_head *dst,
+					unsigned long *scanned, int order,
+					int mode, struct zone *z,
+					struct mem_cgroup *mem_cont,
+					int active);
 
 static inline void mem_cgroup_uncharge_page(struct page *page)
 {
@@ -71,6 +78,11 @@ static inline void mem_cgroup_uncharge_page(struct page *page)
 {
 }
 
+static inline void mem_cgroup_move_lists(struct page_cgroup *pc,
+						bool active)
+{
+}
+
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */

include/linux/res_counter.h

@@ -99,4 +99,27 @@ int res_counter_charge(struct res_counter *counter, unsigned long val);
 void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
 void res_counter_uncharge(struct res_counter *counter, unsigned long val);
 
+static inline bool res_counter_limit_check_locked(struct res_counter *cnt)
+{
+	if (cnt->usage < cnt->limit)
+		return true;
+
+	return false;
+}
+
+/*
+ * Helper function to detect if the cgroup is within it's limit or
+ * not. It's currently called from cgroup_rss_prepare()
+ */
+static inline bool res_counter_check_under_limit(struct res_counter *cnt)
+{
+	bool ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cnt->lock, flags);
+	ret = res_counter_limit_check_locked(cnt);
+	spin_unlock_irqrestore(&cnt->lock, flags);
+	return ret;
+}
+
 #endif

include/linux/swap.h

@@ -5,6 +5,7 @@
 #include <linux/linkage.h>
 #include <linux/mmzone.h>
 #include <linux/list.h>
+#include <linux/memcontrol.h>
 #include <linux/sched.h>
 
 #include <asm/atomic.h>
@@ -182,6 +183,8 @@ extern void swap_setup(void);
 /* linux/mm/vmscan.c */
 extern unsigned long try_to_free_pages(struct zone **zones, int order,
 					gfp_t gfp_mask);
+extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem);
+extern int __isolate_lru_page(struct page *page, int mode);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
 extern int remove_mapping(struct address_space *mapping, struct page *page);