1 files changed, 201 insertions, 131 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index be4dfe87be03..a26dabd62fed 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -856,7 +856,8 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		__mod_zone_page_state(zone, NR_ACTIVE, -nr_active);
 		__mod_zone_page_state(zone, NR_INACTIVE,
 						-(nr_taken - nr_active));
-		zone->pages_scanned += nr_scan;
+		if (scan_global_lru(sc))
+			zone->pages_scanned += nr_scan;
 		spin_unlock_irq(&zone->lru_lock);
 
 		nr_scanned += nr_scan;
@@ -888,8 +889,9 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		if (current_is_kswapd()) {
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
 			__count_vm_events(KSWAPD_STEAL, nr_freed);
-		} else
+		} else if (scan_global_lru(sc))
 			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
+
 		__count_zone_vm_events(PGSTEAL, zone, nr_freed);
 
 		if (nr_taken == 0)
@@ -943,6 +945,113 @@ static inline int zone_is_near_oom(struct zone *zone)
 }
 
 /*
+ * Determine we should try to reclaim mapped pages.
+ * This is called only when sc->mem_cgroup is NULL.
+ */
+static int calc_reclaim_mapped(struct scan_control *sc, struct zone *zone,
+				int priority)
+{
+	long mapped_ratio;
+	long distress;
+	long swap_tendency;
+	long imbalance;
+	int reclaim_mapped = 0;
+	int prev_priority;
+
+	if (scan_global_lru(sc) && zone_is_near_oom(zone))
+		return 1;
+	/*
+	 * `distress' is a measure of how much trouble we're having
+	 * reclaiming pages.  0 -> no problems.  100 -> great trouble.
+	 */
+	if (scan_global_lru(sc))
+		prev_priority = zone->prev_priority;
+	else
+		prev_priority = mem_cgroup_get_reclaim_priority(sc->mem_cgroup);
+
+	distress = 100 >> min(prev_priority, priority);
+
+	/*
+	 * The point of this algorithm is to decide when to start
+	 * reclaiming mapped memory instead of just pagecache.  Work out
+	 * how much memory
+	 * is mapped.
+	 */
+	if (scan_global_lru(sc))
+		mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
+				global_page_state(NR_ANON_PAGES)) * 100) /
+					vm_total_pages;
+	else
+		mapped_ratio = mem_cgroup_calc_mapped_ratio(sc->mem_cgroup);
+
+	/*
+	 * Now decide how much we really want to unmap some pages.  The
+	 * mapped ratio is downgraded - just because there's a lot of
+	 * mapped memory doesn't necessarily mean that page reclaim
+	 * isn't succeeding.
+	 *
+	 * The distress ratio is important - we don't want to start
+	 * going oom.
+	 *
+	 * A 100% value of vm_swappiness overrides this algorithm
+	 * altogether.
+	 */
+	swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
+
+	/*
+	 * If there's huge imbalance between active and inactive
+	 * (think active 100 times larger than inactive) we should
+	 * become more permissive, or the system will take too much
+	 * cpu before it start swapping during memory pressure.
+	 * Distress is about avoiding early-oom, this is about
+	 * making swappiness graceful despite setting it to low
+	 * values.
+	 *
+	 * Avoid div by zero with nr_inactive+1, and max resulting
+	 * value is vm_total_pages.
+	 */
+	if (scan_global_lru(sc)) {
+		imbalance  = zone_page_state(zone, NR_ACTIVE);
+		imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
+	} else
+		imbalance = mem_cgroup_reclaim_imbalance(sc->mem_cgroup);
+
+	/*
+	 * Reduce the effect of imbalance if swappiness is low,
+	 * this means for a swappiness very low, the imbalance
+	 * must be much higher than 100 for this logic to make
+	 * the difference.
+	 *
+	 * Max temporary value is vm_total_pages*100.
+	 */
+	imbalance *= (vm_swappiness + 1);
+	imbalance /= 100;
+
+	/*
+	 * If not much of the ram is mapped, makes the imbalance
+	 * less relevant, it's high priority we refill the inactive
+	 * list with mapped pages only in presence of high ratio of
+	 * mapped pages.
+	 *
+	 * Max temporary value is vm_total_pages*100.
+	 */
+	imbalance *= mapped_ratio;
+	imbalance /= 100;
+
+	/* apply imbalance feedback to swap_tendency */
+	swap_tendency += imbalance;
+
+	/*
+	 * Now use this metric to decide whether to start moving mapped
+	 * memory onto the inactive list.
+	 */
+	if (swap_tendency >= 100)
+		reclaim_mapped = 1;
+
+	return reclaim_mapped;
+}
+
+/*
  * This moves pages from the active list to the inactive list.
  *
  * We move them the other way if the page is referenced by one or more
@@ -959,6 +1068,8 @@ static inline int zone_is_near_oom(struct zone *zone)
  * The downside is that we have to touch page->_count against each page.
  * But we had to alter page->flags anyway.
  */
+
+
 static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 				struct scan_control *sc, int priority)
 {
@@ -972,100 +1083,21 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	struct pagevec pvec;
 	int reclaim_mapped = 0;
 
-	if (sc->may_swap) {
-		long mapped_ratio;
-		long distress;
-		long swap_tendency;
-		long imbalance;
-
-		if (zone_is_near_oom(zone))
-			goto force_reclaim_mapped;
-
-		/*
-		 * `distress' is a measure of how much trouble we're having
-		 * reclaiming pages.  0 -> no problems.  100 -> great trouble.
-		 */
-		distress = 100 >> min(zone->prev_priority, priority);
-
-		/*
-		 * The point of this algorithm is to decide when to start
-		 * reclaiming mapped memory instead of just pagecache.  Work out
-		 * how much memory
-		 * is mapped.
-		 */
-		mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
-				global_page_state(NR_ANON_PAGES)) * 100) /
-					vm_total_pages;
-
-		/*
-		 * Now decide how much we really want to unmap some pages.  The
-		 * mapped ratio is downgraded - just because there's a lot of
-		 * mapped memory doesn't necessarily mean that page reclaim
-		 * isn't succeeding.
-		 *
-		 * The distress ratio is important - we don't want to start
-		 * going oom.
-		 *
-		 * A 100% value of vm_swappiness overrides this algorithm
-		 * altogether.
-		 */
-		swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
-
-		/*
-		 * If there's huge imbalance between active and inactive
-		 * (think active 100 times larger than inactive) we should
-		 * become more permissive, or the system will take too much
-		 * cpu before it start swapping during memory pressure.
-		 * Distress is about avoiding early-oom, this is about
-		 * making swappiness graceful despite setting it to low
-		 * values.
-		 *
-		 * Avoid div by zero with nr_inactive+1, and max resulting
-		 * value is vm_total_pages.
-		 */
-		imbalance  = zone_page_state(zone, NR_ACTIVE);
-		imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
-
-		/*
-		 * Reduce the effect of imbalance if swappiness is low,
-		 * this means for a swappiness very low, the imbalance
-		 * must be much higher than 100 for this logic to make
-		 * the difference.
-		 *
-		 * Max temporary value is vm_total_pages*100.
-		 */
-		imbalance *= (vm_swappiness + 1);
-		imbalance /= 100;
-
-		/*
-		 * If not much of the ram is mapped, makes the imbalance
-		 * less relevant, it's high priority we refill the inactive
-		 * list with mapped pages only in presence of high ratio of
-		 * mapped pages.
-		 *
-		 * Max temporary value is vm_total_pages*100.
-		 */
-		imbalance *= mapped_ratio;
-		imbalance /= 100;
-
-		/* apply imbalance feedback to swap_tendency */
-		swap_tendency += imbalance;
-
-		/*
-		 * Now use this metric to decide whether to start moving mapped
-		 * memory onto the inactive list.
-		 */
-		if (swap_tendency >= 100)
-force_reclaim_mapped:
-			reclaim_mapped = 1;
-	}
+	if (sc->may_swap)
+		reclaim_mapped = calc_reclaim_mapped(sc, zone, priority);
 
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
 	pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
 					ISOLATE_ACTIVE, zone,
 					sc->mem_cgroup, 1);
-	zone->pages_scanned += pgscanned;
+	/*
+	 * zone->pages_scanned is used for detect zone's oom
+	 * mem_cgroup remembers nr_scan by itself.
+	 */
+	if (scan_global_lru(sc))
+		zone->pages_scanned += pgscanned;
+
 	__mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
 	spin_unlock_irq(&zone->lru_lock);
 
@@ -1155,25 +1187,39 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 	unsigned long nr_to_scan;
 	unsigned long nr_reclaimed = 0;
 
-	/*
-	 * Add one to `nr_to_scan' just to make sure that the kernel will
-	 * slowly sift through the active list.
-	 */
-	zone->nr_scan_active +=
-		(zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
-	nr_active = zone->nr_scan_active;
-	if (nr_active >= sc->swap_cluster_max)
-		zone->nr_scan_active = 0;
-	else
-		nr_active = 0;
+	if (scan_global_lru(sc)) {
+		/*
+		 * Add one to nr_to_scan just to make sure that the kernel
+		 * will slowly sift through the active list.
+		 */
+		zone->nr_scan_active +=
+			(zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
+		nr_active = zone->nr_scan_active;
+		zone->nr_scan_inactive +=
+			(zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
+		nr_inactive = zone->nr_scan_inactive;
+		if (nr_inactive >= sc->swap_cluster_max)
+			zone->nr_scan_inactive = 0;
+		else
+			nr_inactive = 0;
+
+		if (nr_active >= sc->swap_cluster_max)
+			zone->nr_scan_active = 0;
+		else
+			nr_active = 0;
+	} else {
+		/*
+		 * This reclaim occurs not because zone memory shortage but
+		 * because memory controller hits its limit.
+		 * Then, don't modify zone reclaim related data.
+		 */
+		nr_active = mem_cgroup_calc_reclaim_active(sc->mem_cgroup,
+					zone, priority);
+
+		nr_inactive = mem_cgroup_calc_reclaim_inactive(sc->mem_cgroup,
+					zone, priority);
+	}
 
-	zone->nr_scan_inactive +=
-		(zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
-	nr_inactive = zone->nr_scan_inactive;
-	if (nr_inactive >= sc->swap_cluster_max)
-		zone->nr_scan_inactive = 0;
-	else
-		nr_inactive = 0;
 
 	while (nr_active || nr_inactive) {
 		if (nr_active) {
@@ -1218,25 +1264,39 @@ static unsigned long shrink_zones(int priority, struct zone **zones,
 	unsigned long nr_reclaimed = 0;
 	int i;
 
+
 	sc->all_unreclaimable = 1;
 	for (i = 0; zones[i] != NULL; i++) {
 		struct zone *zone = zones[i];
 
 		if (!populated_zone(zone))
 			continue;
+		/*
+		 * Take care memory controller reclaiming has small influence
+		 * to global LRU.
+		 */
+		if (scan_global_lru(sc)) {
+			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+				continue;
+			note_zone_scanning_priority(zone, priority);
 
-		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-			continue;
-
-		note_zone_scanning_priority(zone, priority);
-
-		if (zone_is_all_unreclaimable(zone) && priority != DEF_PRIORITY)
-			continue;	/* Let kswapd poll it */
-
-		sc->all_unreclaimable = 0;
+			if (zone_is_all_unreclaimable(zone) &&
+						priority != DEF_PRIORITY)
+				continue;	/* Let kswapd poll it */
+			sc->all_unreclaimable = 0;
+		} else {
+			/*
+			 * Ignore cpuset limitation here. We just want to reduce
+			 * # of used pages by us regardless of memory shortage.
+			 */
+			sc->all_unreclaimable = 0;
+			mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
+							priority);
+		}
 
 		nr_reclaimed += shrink_zone(priority, zone, sc);
 	}
+
 	return nr_reclaimed;
 }
  
@@ -1264,16 +1324,21 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 	unsigned long lru_pages = 0;
 	int i;
 
-	count_vm_event(ALLOCSTALL);
-
-	for (i = 0; zones[i] != NULL; i++) {
-		struct zone *zone = zones[i];
+	if (scan_global_lru(sc))
+		count_vm_event(ALLOCSTALL);
+	/*
+	 * mem_cgroup will not do shrink_slab.
+	 */
+	if (scan_global_lru(sc)) {
+		for (i = 0; zones[i] != NULL; i++) {
+			struct zone *zone = zones[i];
 
-		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-			continue;
+			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+				continue;
 
-		lru_pages += zone_page_state(zone, NR_ACTIVE)
-				+ zone_page_state(zone, NR_INACTIVE);
+			lru_pages += zone_page_state(zone, NR_ACTIVE)
+					+ zone_page_state(zone, NR_INACTIVE);
+		}
 	}
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
@@ -1330,14 +1395,19 @@ out:
 	 */
 	if (priority < 0)
 		priority = 0;
-	for (i = 0; zones[i] != NULL; i++) {
-		struct zone *zone = zones[i];
 
-		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-			continue;
+	if (scan_global_lru(sc)) {
+		for (i = 0; zones[i] != NULL; i++) {
+			struct zone *zone = zones[i];
+
+			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+				continue;
+
+			zone->prev_priority = priority;
+		}
+	} else
+		mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);
 
-		zone->prev_priority = priority;
-	}
 	return ret;
 }