Add the meta_page to the per container 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 container on behalf of which
reclaims are carried out. try_to_free_pages() has been extended to become
container aware.

Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: <balbir@linux.vnet.ibm.com>
---

 include/linux/memcontrol.h  |   11 +++
 include/linux/res_counter.h |   23 ++++++++
 include/linux/swap.h        |    3 +
 mm/memcontrol.c             |  120 +++++++++++++++++++++++++++++++++++++++++
 mm/swap.c                   |    2 
 mm/vmscan.c                 |  126 +++++++++++++++++++++++++++++++++++---------
 6 files changed, 259 insertions(+), 26 deletions(-)

diff -puN include/linux/memcontrol.h~mem-control-lru-and-reclaim include/linux/memcontrol.h
--- linux-2.6.22-rc6/include/linux/memcontrol.h~mem-control-lru-and-reclaim	2007-07-20 13:13:25.000000000 +0530
+++ linux-2.6.22-rc6-balbir/include/linux/memcontrol.h	2007-07-20 13:13:25.000000000 +0530
@@ -31,6 +31,13 @@ extern void page_assign_meta_page(struct
 extern struct meta_page *page_get_meta_page(struct page *page);
 extern int mem_container_charge(struct page *page, struct mm_struct *mm);
 extern void mem_container_uncharge(struct meta_page *mp);
+extern void mem_container_move_lists(struct meta_page *mp, bool active);
+extern unsigned long mem_container_isolate_pages(unsigned long nr_to_scan,
+					struct list_head *dst,
+					unsigned long *scanned, int order,
+					int mode, struct zone *z,
+					struct mem_container *mem_cont,
+					int active);
 
 #else /* CONFIG_CONTAINER_MEM_CONT */
 static inline void mm_init_container(struct mm_struct *mm,
@@ -61,6 +68,10 @@ static inline void mem_container_uncharg
 {
 }
 
+static inline void mem_container_move_lists(struct meta_page *mp, bool active)
+{
+}
+
 #endif /* CONFIG_CONTAINER_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff -puN include/linux/swap.h~mem-control-lru-and-reclaim include/linux/swap.h
--- linux-2.6.22-rc6/include/linux/swap.h~mem-control-lru-and-reclaim	2007-07-20 13:13:25.000000000 +0530
+++ linux-2.6.22-rc6-balbir/include/linux/swap.h	2007-07-20 13:13:25.000000000 +0530
@@ -6,6 +6,7 @@
 #include <linux/mmzone.h>
 #include <linux/list.h>
 #include <linux/sched.h>
+#include <linux/memcontrol.h>
 
 #include <asm/atomic.h>
 #include <asm/page.h>
@@ -191,6 +192,8 @@ 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_container_pages(struct mem_container *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);
diff -puN mm/memcontrol.c~mem-control-lru-and-reclaim mm/memcontrol.c
--- linux-2.6.22-rc6/mm/memcontrol.c~mem-control-lru-and-reclaim	2007-07-20 13:13:25.000000000 +0530
+++ linux-2.6.22-rc6-balbir/mm/memcontrol.c	2007-07-20 13:13:25.000000000 +0530
@@ -24,6 +24,8 @@
 #include <linux/page-flags.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/swap.h>
+#include <linux/spinlock.h>
 
 struct container_subsys mem_container_subsys;
 
@@ -51,6 +53,10 @@ struct mem_container {
 	 */
 	struct list_head active_list;
 	struct list_head inactive_list;
+	/*
+	 * spin_lock to protect the per container LRU
+	 */
+	spinlock_t lru_lock;
 };
 
 /*
@@ -108,6 +114,92 @@ void __always_inline unlock_meta_page(st
 	bit_spin_unlock(PG_metapage, &page->flags);
 }
 
+unsigned long mem_container_isolate_pages(unsigned long nr_to_scan,
+					struct list_head *dst,
+					unsigned long *scanned, int order,
+					int mode, struct zone *z,
+					struct mem_container *mem_cont,
+					int active)
+{
+	unsigned long nr_taken = 0;
+	struct page *page;
+	unsigned long scan;
+	LIST_HEAD(mp_list);
+	struct list_head *src;
+	struct meta_page *mp;
+
+	if (active)
+		src = &mem_cont->active_list;
+	else
+		src = &mem_cont->inactive_list;
+
+	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
+		mp = list_entry(src->prev, struct meta_page, lru);
+		page = mp->page;
+
+		if (PageActive(page) && !active) {
+			mem_container_move_lists(mp, true);
+			scan--;
+			continue;
+		}
+		if (!PageActive(page) && active) {
+			mem_container_move_lists(mp, false);
+			scan--;
+			continue;
+		}
+
+		/*
+		 * Reclaim, per zone
+		 * TODO: make the active/inactive lists per zone
+		 */
+		if (page_zone(page) != z)
+			continue;
+
+		spin_lock(&mem_cont->lru_lock);
+		/*
+		 * Check if the meta page went away from under us
+		 */
+		if (!list_empty(&mp->lru))
+			list_move(&mp->lru, &mp_list);
+		else {
+			spin_unlock(&mem_cont->lru_lock);
+			continue;
+		}
+		spin_unlock(&mem_cont->lru_lock);
+
+		if (__isolate_lru_page(page, mode) == 0) {
+			list_move(&page->lru, dst);
+			nr_taken++;
+		}
+	}
+
+	spin_lock(&mem_cont->lru_lock);
+	list_splice(&mp_list, src);
+	spin_unlock(&mem_cont->lru_lock);
+
+	*scanned = scan;
+	return nr_taken;
+}
+
+/*
+ * This routine assumes that the appropriate zone's lru lock is already held
+ */
+void mem_container_move_lists(struct meta_page *mp, bool active)
+{
+	struct mem_container *mem;
+	if (!mp)
+		return;
+
+	mem = mp->mem_container;
+
+	spin_lock(&mem->lru_lock);
+	if (active)
+		list_move(&mp->lru, &mp->mem_container->active_list);
+	else
+		list_move(&mp->lru, &mp->mem_container->inactive_list);
+	spin_unlock(&mem->lru_lock);
+}
+
 /*
  * Charge the memory controller for page usage.
  * Return
@@ -118,6 +210,7 @@ int mem_container_charge(struct page *pa
 {
 	struct mem_container *mem;
 	struct meta_page *mp;
+	unsigned long flags;
 
 	/*
 	 * Should meta_page's go to their own slab?
@@ -164,7 +257,20 @@ int mem_container_charge(struct page *pa
 	 * If we created the meta_page, we should free it on exceeding
 	 * the container limit.
 	 */
-	if (res_counter_charge(&mem->res, 1)) {
+	while (res_counter_charge(&mem->res, 1)) {
+		if (try_to_free_mem_container_pages(mem))
+			continue;
+
+		/*
+ 		 * try_to_free_mem_container_pages() might not give us a full
+ 		 * picture of reclaim. Some pages are reclaimed and might be
+ 		 * moved to swap cache or just unmapped from the container.
+ 		 * Check the limit again to see if the reclaim reduced the
+ 		 * current usage of the container before giving up
+ 		 */
+		if (res_counter_check_under_limit(&mem->res))
+			continue;
+
 		css_put(&mem->css);
 		goto free_mp;
 	}
@@ -184,6 +290,10 @@ int mem_container_charge(struct page *pa
 	mp->page = page;
 	page_assign_meta_page(page, mp);
 
+	spin_lock_irqsave(&mem->lru_lock, flags);
+	list_add(&mp->lru, &mem->active_list);
+	spin_unlock_irqrestore(&mem->lru_lock, flags);
+
 done:
 	unlock_meta_page(page);
 	return 0;
@@ -203,6 +313,7 @@ void mem_container_uncharge(struct meta_
 {
 	struct mem_container *mem;
 	struct page *page;
+	unsigned long flags;
 
 	/*
 	 * This can happen for PAGE_ZERO
@@ -212,12 +323,18 @@ void mem_container_uncharge(struct meta_
 
 	if (atomic_dec_and_test(&mp->ref_cnt)) {
 		page = mp->page;
+
 		lock_meta_page(page);
 		mem = mp->mem_container;
 		css_put(&mem->css);
 		page_assign_meta_page(page, NULL);
 		unlock_meta_page(page);
+
 		res_counter_uncharge(&mem->res, 1);
+
+		spin_lock_irqsave(&mem->lru_lock, flags);
+		list_del_init(&mp->lru);
+		spin_unlock_irqrestore(&mem->lru_lock, flags);
 		kfree(mp);
 	}
 }
@@ -279,6 +396,7 @@ static int mem_container_create(struct c
 	mem->css.container = cont;
 	INIT_LIST_HEAD(&mem->active_list);
 	INIT_LIST_HEAD(&mem->inactive_list);
+	spin_lock_init(&mem->lru_lock);
 	return 0;
 }
 
diff -puN mm/swap.c~mem-control-lru-and-reclaim mm/swap.c
--- linux-2.6.22-rc6/mm/swap.c~mem-control-lru-and-reclaim	2007-07-20 13:13:25.000000000 +0530
+++ linux-2.6.22-rc6-balbir/mm/swap.c	2007-07-20 13:13:25.000000000 +0530
@@ -31,6 +31,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/init.h>
+#include <linux/memcontrol.h>
 
 /* How many pages do we try to swap or page in/out together? */
 int page_cluster;
@@ -148,6 +149,7 @@ void fastcall activate_page(struct page 
 		SetPageActive(page);
 		add_page_to_active_list(zone, page);
 		__count_vm_event(PGACTIVATE);
+		mem_container_move_lists(page_get_meta_page(page), true);
 	}
 	spin_unlock_irq(&zone->lru_lock);
 }
diff -puN mm/vmscan.c~mem-control-lru-and-reclaim mm/vmscan.c
--- linux-2.6.22-rc6/mm/vmscan.c~mem-control-lru-and-reclaim	2007-07-20 13:13:25.000000000 +0530
+++ linux-2.6.22-rc6-balbir/mm/vmscan.c	2007-07-20 13:13:25.000000000 +0530
@@ -39,6 +39,7 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/memcontrol.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -70,6 +71,15 @@ struct scan_control {
 	int all_unreclaimable;
 
 	int order;
+
+	/* Which container do we reclaim from */
+	struct mem_container *mem_container;
+
+	/* Pluggable isolate pages callback */
+	unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
+			unsigned long *scanned, int order, int mode,
+			struct zone *z, struct mem_container *mem_cont,
+			int active);
 };
 
 #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
@@ -604,7 +614,7 @@ keep:
  *
  * returns 0 on success, -ve errno on failure.
  */
-static int __isolate_lru_page(struct page *page, int mode)
+int __isolate_lru_page(struct page