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>
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f5b47ef..9c3c1c9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -32,6 +32,13 @@
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_move_lists(struct page_cgroup *pc,
+ bool active)
+{
+}
+
#endif /* CONFIG_CGROUP_MEM_CONT */
#endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index eeb3f77..5e60a4f 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -99,4 +99,27 @@
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
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 353153e..4d91bc0 100644
--- a/include/linux/swap.h
+++ b/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 @@
/* 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);